The cache for model files in Transformers v4.22.0 has been updated. Migrating your old cache. This is a one-time only operation. You can interrupt this and resume the migration later on by calling `transformers.utils.move_cache()`.

0it [00:00, ?it/s]
0it [00:00, ?it/s]
/opt/conda/lib/python3.10/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: '/opt/conda/lib/python3.10/site-packages/torchvision/image.so: undefined symbol: _ZN3c1017RegisterOperatorsD1Ev'If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?
  warn(
2024-10-28 15:22:21.126391: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2024-10-28 15:22:21.126494: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2024-10-28 15:22:21.332900: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
/opt/conda/lib/python3.10/site-packages/transformers/deepspeed.py:24: FutureWarning: transformers.deepspeed module is deprecated and will be removed in a future version. Please import deepspeed modules directly from transformers.integrations
  warnings.warn(
/opt/conda/lib/python3.10/site-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of 🤗 Transformers. Use `eval_strategy` instead
  warnings.warn(
last_checkpoint=None

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 898 examples [00:00, 6110.14 examples/s]
Generating train split: 2225 examples [00:00, 9637.85 examples/s]
Generating train split: 4000 examples [00:00, 12899.94 examples/s]
Generating train split: 5828 examples [00:00, 14884.91 examples/s]
Generating train split: 7523 examples [00:00, 15595.32 examples/s]
Generating train split: 9285 examples [00:00, 16260.22 examples/s]
Generating train split: 11058 examples [00:00, 16728.66 examples/s]
Generating train split: 12987 examples [00:00, 17463.21 examples/s]
Generating train split: 15664 examples [00:01, 17614.10 examples/s]
Generating train split: 17488 examples [00:01, 17785.65 examples/s]
Generating train split: 19329 examples [00:01, 17959.16 examples/s]
Generating train split: 21183 examples [00:01, 18123.64 examples/s]
Generating train split: 23018 examples [00:01, 18187.32 examples/s]
Generating train split: 24889 examples [00:01, 18338.05 examples/s]
Generating train split: 27601 examples [00:01, 18234.38 examples/s]
Generating train split: 30329 examples [00:01, 18215.43 examples/s]
Generating train split: 33000 examples [00:01, 18044.72 examples/s]
Generating train split: 34879 examples [00:02, 18223.20 examples/s]
Generating train split: 37557 examples [00:02, 18092.41 examples/s]
Generating train split: 39383 examples [00:02, 18130.29 examples/s]
Generating train split: 42043 examples [00:02, 17990.14 examples/s]
Generating train split: 43985 examples [00:02, 18209.20 examples/s]
Generating train split: 46627 examples [00:02, 18001.74 examples/s]
Generating train split: 49281 examples [00:02, 17896.12 examples/s]
Generating train split: 51952 examples [00:03, 17822.14 examples/s]
Generating train split: 54598 examples [00:03, 17763.31 examples/s]
Generating train split: 57204 examples [00:03, 17638.45 examples/s]
Generating train split: 59000 examples [00:03, 17635.96 examples/s]
Generating train split: 60891 examples [00:03, 17946.43 examples/s]
Generating train split: 62703 examples [00:03, 17989.09 examples/s]
Generating train split: 64521 examples [00:03, 18038.81 examples/s]
Generating train split: 67228 examples [00:03, 18040.38 examples/s]
Generating train split: 70000 examples [00:04, 18065.80 examples/s]
Generating train split: 71836 examples [00:04, 18134.41 examples/s]
Generating train split: 74547 examples [00:04, 18110.82 examples/s]
Generating train split: 77226 examples [00:04, 18024.54 examples/s]
Generating train split: 79988 examples [00:04, 18082.97 examples/s]
Generating train split: 81799 examples [00:04, 18086.64 examples/s]
Generating train split: 84394 examples [00:04, 17822.59 examples/s]
Generating train split: 86197 examples [00:04, 17871.89 examples/s]
Generating train split: 88000 examples [00:05, 17866.84 examples/s]
Generating train split: 89877 examples [00:05, 18103.63 examples/s]
Generating train split: 92512 examples [00:05, 17904.66 examples/s]
Generating train split: 92867 examples [00:05, 17531.75 examples/s]

Generating validation split: 0 examples [00:00, ? examples/s]
Generating validation split: 1722 examples [00:00, 17097.36 examples/s]

Running tokenizer on train dataset:   0%|          | 0/92867 [00:00<?, ? examples/s]/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_base.py:4126: UserWarning: `as_target_tokenizer` is deprecated and will be removed in v5 of Transformers. You can tokenize your labels by using the argument `text_target` of the regular `__call__` method (either in the same call as your input texts if you use the same keyword arguments, or in a separate call.
  warnings.warn(

Running tokenizer on train dataset:   1%|          | 1000/92867 [00:01<02:32, 601.83 examples/s]
Running tokenizer on train dataset:   2%|▏         | 2000/92867 [00:02<01:53, 799.00 examples/s]
Running tokenizer on train dataset:   3%|▎         | 3000/92867 [00:04<02:07, 702.11 examples/s]
Running tokenizer on train dataset:   4%|▍         | 4000/92867 [00:06<02:27, 601.95 examples/s]
Running tokenizer on train dataset:   5%|▌         | 5000/92867 [00:08<02:31, 581.00 examples/s]
Running tokenizer on train dataset:   6%|▋         | 6000/92867 [00:09<02:33, 566.75 examples/s]
Running tokenizer on train dataset:   8%|▊         | 7000/92867 [00:11<02:34, 556.50 examples/s]
Running tokenizer on train dataset:   9%|▊         | 8000/92867 [00:13<02:34, 550.04 examples/s]
Running tokenizer on train dataset:  10%|▉         | 9000/92867 [00:15<02:28, 564.78 examples/s]
Running tokenizer on train dataset:  11%|█         | 10000/92867 [00:16<02:11, 629.17 examples/s]
Running tokenizer on train dataset:  12%|█▏        | 11000/92867 [00:17<02:00, 680.01 examples/s]
Running tokenizer on train dataset:  13%|█▎        | 12000/92867 [00:19<01:55, 697.87 examples/s]
Running tokenizer on train dataset:  14%|█▍        | 13000/92867 [00:20<01:51, 714.08 examples/s]
Running tokenizer on train dataset:  15%|█▌        | 14000/92867 [00:21<01:43, 762.51 examples/s]
Running tokenizer on train dataset:  16%|█▌        | 15000/92867 [00:22<01:39, 783.31 examples/s]
Running tokenizer on train dataset:  17%|█▋        | 16000/92867 [00:23<01:35, 806.86 examples/s]
Running tokenizer on train dataset:  18%|█▊        | 17000/92867 [00:25<01:32, 820.87 examples/s]
Running tokenizer on train dataset:  19%|█▉        | 18000/92867 [00:26<01:31, 820.77 examples/s]
Running tokenizer on train dataset:  20%|██        | 19000/92867 [00:27<01:33, 791.95 examples/s]
Running tokenizer on train dataset:  22%|██▏       | 20000/92867 [00:28<01:30, 804.26 examples/s]
Running tokenizer on train dataset:  23%|██▎       | 21000/92867 [00:29<01:27, 821.53 examples/s]
Running tokenizer on train dataset:  24%|██▎       | 22000/92867 [00:31<01:25, 825.39 examples/s]
Running tokenizer on train dataset:  25%|██▍       | 23000/92867 [00:32<01:27, 799.29 examples/s]
Running tokenizer on train dataset:  26%|██▌       | 24000/92867 [00:33<01:29, 772.25 examples/s]
Running tokenizer on train dataset:  27%|██▋       | 25000/92867 [00:35<01:28, 770.51 examples/s]
Running tokenizer on train dataset:  28%|██▊       | 26000/92867 [00:36<01:27, 762.65 examples/s]
Running tokenizer on train dataset:  29%|██▉       | 27000/92867 [00:37<01:28, 745.81 examples/s]
Running tokenizer on train dataset:  30%|███       | 28000/92867 [00:39<01:31, 710.80 examples/s]
Running tokenizer on train dataset:  31%|███       | 29000/92867 [00:41<01:31, 699.46 examples/s]
Running tokenizer on train dataset:  32%|███▏      | 30000/92867 [00:42<01:30, 692.94 examples/s]
Running tokenizer on train dataset:  33%|███▎      | 31000/92867 [00:44<01:31, 673.73 examples/s]
Running tokenizer on train dataset:  34%|███▍      | 32000/92867 [00:45<01:34, 642.28 examples/s]
Running tokenizer on train dataset:  36%|███▌      | 33000/92867 [00:47<01:33, 642.81 examples/s]
Running tokenizer on train dataset:  37%|███▋      | 34000/92867 [00:48<01:32, 633.36 examples/s]
Running tokenizer on train dataset:  38%|███▊      | 35000/92867 [00:50<01:31, 629.90 examples/s]
Running tokenizer on train dataset:  39%|███▉      | 36000/92867 [00:52<01:31, 621.95 examples/s]
Running tokenizer on train dataset:  40%|███▉      | 37000/92867 [00:53<01:28, 631.56 examples/s]
Running tokenizer on train dataset:  41%|████      | 38000/92867 [00:55<01:25, 643.47 examples/s]
Running tokenizer on train dataset:  42%|████▏     | 39000/92867 [00:56<01:23, 646.27 examples/s]
Running tokenizer on train dataset:  43%|████▎     | 40000/92867 [00:58<01:24, 622.24 examples/s]
Running tokenizer on train dataset:  44%|████▍     | 41000/92867 [01:00<01:36, 538.24 examples/s]
Running tokenizer on train dataset:  45%|████▌     | 42000/92867 [01:02<01:33, 546.13 examples/s]
Running tokenizer on train dataset:  46%|████▋     | 43000/92867 [01:04<01:28, 564.59 examples/s]
Running tokenizer on train dataset:  47%|████▋     | 44000/92867 [01:05<01:22, 589.55 examples/s]
Running tokenizer on train dataset:  48%|████▊     | 45000/92867 [01:07<01:21, 589.89 examples/s]
Running tokenizer on train dataset:  50%|████▉     | 46000/92867 [01:09<01:20, 580.46 examples/s]
Running tokenizer on train dataset:  51%|█████     | 47000/92867 [01:10<01:16, 596.81 examples/s]
Running tokenizer on train dataset:  52%|█████▏    | 48000/92867 [01:12<01:17, 577.11 examples/s]
Running tokenizer on train dataset:  53%|█████▎    | 49000/92867 [01:14<01:13, 599.01 examples/s]
Running tokenizer on train dataset:  54%|█████▍    | 50000/92867 [01:16<01:15, 564.56 examples/s]
Running tokenizer on train dataset:  55%|█████▍    | 51000/92867 [01:18<01:17, 539.92 examples/s]
Running tokenizer on train dataset:  56%|█████▌    | 52000/92867 [01:20<01:15, 544.80 examples/s]
Running tokenizer on train dataset:  57%|█████▋    | 53000/92867 [01:22<01:14, 532.66 examples/s]
Running tokenizer on train dataset:  58%|█████▊    | 54000/92867 [01:23<01:11, 545.89 examples/s]
Running tokenizer on train dataset:  59%|█████▉    | 55000/92867 [01:25<01:07, 560.02 examples/s]
Running tokenizer on train dataset:  60%|██████    | 56000/92867 [01:27<01:09, 528.99 examples/s]
Running tokenizer on train dataset:  61%|██████▏   | 57000/92867 [01:29<01:09, 513.87 examples/s]
Running tokenizer on train dataset:  62%|██████▏   | 58000/92867 [01:31<01:08, 506.26 examples/s]
Running tokenizer on train dataset:  64%|██████▎   | 59000/92867 [01:33<01:07, 502.80 examples/s]
Running tokenizer on train dataset:  65%|██████▍   | 60000/92867 [01:35<00:58, 564.08 examples/s]
Running tokenizer on train dataset:  66%|██████▌   | 61000/92867 [01:36<00:52, 605.66 examples/s]
Running tokenizer on train dataset:  67%|██████▋   | 62000/92867 [01:37<00:49, 627.92 examples/s]
Running tokenizer on train dataset:  68%|██████▊   | 63000/92867 [01:39<00:44, 665.65 examples/s]
Running tokenizer on train dataset:  69%|██████▉   | 64000/92867 [01:40<00:41, 701.61 examples/s]
Running tokenizer on train dataset:  70%|██████▉   | 65000/92867 [01:41<00:39, 713.10 examples/s]
Running tokenizer on train dataset:  71%|███████   | 66000/92867 [01:43<00:37, 720.17 examples/s]
Running tokenizer on train dataset:  72%|███████▏  | 67000/92867 [01:44<00:36, 714.77 examples/s]
Running tokenizer on train dataset:  73%|███████▎  | 68000/92867 [01:45<00:34, 720.30 examples/s]
Running tokenizer on train dataset:  74%|███████▍  | 69000/92867 [01:47<00:32, 728.11 examples/s]
Running tokenizer on train dataset:  75%|███████▌  | 70000/92867 [01:48<00:32, 708.42 examples/s]
Running tokenizer on train dataset:  76%|███████▋  | 71000/92867 [01:50<00:31, 702.07 examples/s]
Running tokenizer on train dataset:  78%|███████▊  | 72000/92867 [01:51<00:30, 693.11 examples/s]
Running tokenizer on train dataset:  79%|███████▊  | 73000/92867 [01:53<00:29, 666.73 examples/s]
Running tokenizer on train dataset:  80%|███████▉  | 74000/92867 [01:55<00:29, 647.38 examples/s]
Running tokenizer on train dataset:  81%|████████  | 75000/92867 [01:56<00:27, 638.56 examples/s]
Running tokenizer on train dataset:  82%|████████▏ | 76000/92867 [01:58<00:27, 610.40 examples/s]
Running tokenizer on train dataset:  83%|████████▎ | 77000/92867 [02:00<00:26, 602.23 examples/s]
Running tokenizer on train dataset:  84%|████████▍ | 78000/92867 [02:01<00:25, 588.00 examples/s]
Running tokenizer on train dataset:  85%|████████▌ | 79000/92867 [02:03<00:23, 580.59 examples/s]
Running tokenizer on train dataset:  86%|████████▌ | 80000/92867 [02:05<00:22, 581.62 examples/s]
Running tokenizer on train dataset:  87%|████████▋ | 81000/92867 [02:07<00:20, 591.51 examples/s]
Running tokenizer on train dataset:  88%|████████▊ | 82000/92867 [02:08<00:17, 607.16 examples/s]
Running tokenizer on train dataset:  89%|████████▉ | 83000/92867 [02:11<00:18, 522.87 examples/s]
Running tokenizer on train dataset:  90%|█████████ | 84000/92867 [02:13<00:17, 510.63 examples/s]
Running tokenizer on train dataset:  92%|█████████▏| 85000/92867 [02:14<00:14, 533.85 examples/s]
Running tokenizer on train dataset:  93%|█████████▎| 86000/92867 [02:16<00:12, 553.31 examples/s]
Running tokenizer on train dataset:  94%|█████████▎| 87000/92867 [02:18<00:10, 550.57 examples/s]
Running tokenizer on train dataset:  95%|█████████▍| 88000/92867 [02:20<00:08, 559.95 examples/s]
Running tokenizer on train dataset:  96%|█████████▌| 89000/92867 [02:21<00:06, 553.74 examples/s]
Running tokenizer on train dataset:  97%|█████████▋| 90000/92867 [02:23<00:05, 561.42 examples/s]
Running tokenizer on train dataset:  98%|█████████▊| 91000/92867 [02:25<00:03, 519.96 examples/s]
Running tokenizer on train dataset:  99%|█████████▉| 92000/92867 [02:27<00:01, 514.55 examples/s]
Running tokenizer on train dataset: 100%|██████████| 92867/92867 [02:29<00:00, 505.92 examples/s]
Running tokenizer on train dataset: 100%|██████████| 92867/92867 [02:29<00:00, 620.33 examples/s]
Saving cached train data ...

Saving the dataset (0/1 shards):   0%|          | 0/92867 [00:00<?, ? examples/s]
Saving the dataset (0/1 shards): 100%|██████████| 92867/92867 [00:00<00:00, 913700.69 examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 92867/92867 [00:00<00:00, 913700.69 examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 92867/92867 [00:00<00:00, 909559.36 examples/s]

Running tokenizer on validation dataset:   0%|          | 0/1722 [00:00<?, ? examples/s]
Running tokenizer on validation dataset:  58%|█████▊    | 1000/1722 [00:01<00:01, 555.53 examples/s]
Running tokenizer on validation dataset: 100%|██████████| 1722/1722 [00:03<00:00, 537.31 examples/s]
Running tokenizer on validation dataset: 100%|██████████| 1722/1722 [00:03<00:00, 539.63 examples/s]
Saving cached validation data ...

Saving the dataset (0/1 shards):   0%|          | 0/1722 [00:00<?, ? examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 1722/1722 [00:00<00:00, 316585.93 examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 1722/1722 [00:00<00:00, 306600.65 examples/s]
training_args.use_lang_prefix=True

Downloading builder script:   0%|          | 0.00/8.15k [00:00<?, ?B/s]
Downloading builder script: 100%|██████████| 8.15k/8.15k [00:00<00:00, 20.6MB/s]
[WARNING|trainer.py:2764] 2024-10-28 15:25:16,687 >> There were missing keys in the checkpoint model loaded: ['model.encoder.embed_tokens.weight', 'model.decoder.embed_tokens.weight', 'lm_head.weight'].
/opt/conda/lib/python3.10/site-packages/transformers/optimization.py:591: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
  warnings.warn(
All 61904 steps, warm_up steps: 200
/opt/conda/lib/python3.10/site-packages/transformers/trainer.py:3108: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  torch.load(os.path.join(checkpoint, OPTIMIZER_NAME), map_location=map_location)
wandb: WARNING The `run_name` is currently set to the same value as `TrainingArguments.output_dir`. If this was not intended, please specify a different run name by setting the `TrainingArguments.run_name` parameter.
wandb: Currently logged in as: abdiharyadi. Use `wandb login --relogin` to force relogin
wandb: wandb version 0.18.5 is available!  To upgrade, please run:
wandb:  $ pip install wandb --upgrade
wandb: Tracking run with wandb version 0.17.5
wandb: Run data is saved locally in /kaggle/tmp/amr-tst-indo/AMRBART-id/fine-tune/wandb/run-20241028_152523-2rzpheht
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run /kaggle/tmp/amr-tst-indo/AMRBART-id/fine-tune/../outputs/mbart-en-id-smaller-fted
wandb: ⭐️ View project at https://wandb.ai/abdiharyadi/amr-tst
wandb: 🚀 View run at https://wandb.ai/abdiharyadi/amr-tst/runs/2rzpheht

  0%|          | 0/61904 [00:00<?, ?it/s]/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()
/opt/conda/lib/python3.10/site-packages/transformers/trainer.py:2843: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  checkpoint_rng_state = torch.load(rng_file)

 69%|██████▉   | 42563/61904 [00:02<00:01, 15111.16it/s]
 69%|██████▉   | 42571/61904 [00:15<00:01, 15111.16it/s]
 69%|██████▉   | 42572/61904 [00:15<00:09, 2037.43it/s] 
 69%|██████▉   | 42573/61904 [00:16<00:10, 1794.87it/s]
                                                       
{'loss': 2.4441, 'learning_rate': 1.3131725657980034e-07, 'epoch': 11.01}

 69%|██████▉   | 42580/61904 [00:27<00:10, 1794.87it/s]
 69%|██████▉   | 42585/61904 [00:35<00:10, 1794.87it/s]
 69%|██████▉   | 42586/61904 [00:35<00:35, 542.13it/s] 
 69%|██████▉   | 42587/61904 [00:37<00:38, 506.46it/s]
                                                      
{'loss': 2.5027, 'learning_rate': 1.31284843770258e-07, 'epoch': 11.01}

 69%|██████▉   | 42600/61904 [00:54<00:38, 506.46it/s]
 69%|██████▉   | 42600/61904 [00:55<00:38, 506.46it/s]
 69%|██████▉   | 42601/61904 [00:56<01:29, 214.84it/s]
 69%|██████▉   | 42602/61904 [00:57<01:35, 202.87it/s]
 69%|██████▉   | 42614/61904 [01:15<01:35, 202.87it/s]
 69%|██████▉   | 42615/61904 [01:15<03:13, 99.79it/s] 
 69%|██████▉   | 42616/61904 [01:16<03:22, 95.09it/s]
                                                     
{'loss': 2.4709, 'learning_rate': 1.3125243096071566e-07, 'epoch': 11.02}

 69%|██████▉   | 42620/61904 [01:22<03:22, 95.09it/s]
 69%|██████▉   | 42628/61904 [01:35<03:22, 95.09it/s]
 69%|██████▉   | 42629/61904 [01:35<06:44, 47.68it/s]
 69%|██████▉   | 42630/61904 [01:36<07:05, 45.29it/s]
                                                     
{'loss': 2.4576, 'learning_rate': 1.3122001815117335e-07, 'epoch': 11.02}

 69%|██████▉   | 42640/61904 [01:50<07:05, 45.29it/s]
 69%|██████▉   | 42643/61904 [01:55<07:05, 45.29it/s]
 69%|██████▉   | 42644/61904 [01:56<14:13, 22.55it/s]
 69%|██████▉   | 42645/61904 [01:57<14:58, 21.43it/s]
 69%|██████▉   | 42657/61904 [02:15<14:58, 21.43it/s]
 69%|██████▉   | 42658/61904 [02:16<28:03, 11.43it/s]
 69%|██████▉   | 42659/61904 [02:17<29:30, 10.87it/s]
                                                     
{'loss': 2.4395, 'learning_rate': 1.31187605341631e-07, 'epoch': 11.03}

 69%|██████▉   | 42660/61904 [02:19<29:30, 10.87it/s]
 69%|██████▉   | 42671/61904 [02:35<29:29, 10.87it/s]
 69%|██████▉   | 42672/61904 [02:36<53:29,  5.99it/s]
 69%|██████▉   | 42673/61904 [02:37<55:56,  5.73it/s]
                                                     
{'loss': 2.504, 'learning_rate': 1.3115519253208867e-07, 'epoch': 11.03}

 69%|██████▉   | 42680/61904 [02:47<55:55,  5.73it/s]
 69%|██████▉   | 42685/61904 [02:55<55:54,  5.73it/s]
 69%|██████▉   | 42686/61904 [02:56<1:37:42,  3.28it/s]
 69%|██████▉   | 42687/61904 [02:57<1:41:20,  3.16it/s]
 69%|██████▉   | 42699/61904 [03:15<1:41:16,  3.16it/s]
 69%|██████▉   | 42700/61904 [03:15<2:39:04,  2.01it/s]
                                                       
{'loss': 2.5521, 'learning_rate': 1.3112277972254634e-07, 'epoch': 11.04}

 69%|██████▉   | 42700/61904 [03:15<2:39:04,  2.01it/s]
 69%|██████▉   | 42701/61904 [03:16<2:44:42,  1.94it/s]
 69%|██████▉   | 42713/61904 [03:35<2:44:36,  1.94it/s]
 69%|██████▉   | 42714/61904 [03:35<4:03:26,  1.31it/s]
 69%|██████▉   | 42715/61904 [03:37<4:09:00,  1.28it/s]
                                                       
{'loss': 2.5074, 'learning_rate': 1.31090366913004e-07, 'epoch': 11.04}

 69%|██████▉   | 42720/61904 [03:44<4:08:56,  1.28it/s]
 69%|██████▉   | 42725/61904 [03:51<5:03:16,  1.05it/s]
 69%|██████▉   | 42726/61904 [03:52<5:08:56,  1.03it/s]
 69%|██████▉   | 42733/61904 [04:02<5:44:09,  1.08s/it]
 69%|██████▉   | 42738/61904 [04:08<5:59:06,  1.12s/it]
                                                       
{'loss': 2.5079, 'learning_rate': 1.3105795410346169e-07, 'epoch': 11.05}

 69%|██████▉   | 42740/61904 [04:11<5:59:04,  1.12s/it]
 69%|██████▉   | 42742/61904 [04:14<6:14:27,  1.17s/it]
 69%|██████▉   | 42745/61904 [04:18<6:26:10,  1.21s/it]
 69%|██████▉   | 42747/61904 [04:20<6:29:18,  1.22s/it]
 69%|██████▉   | 42749/61904 [04:23<6:40:38,  1.25s/it]
 69%|██████▉   | 42750/61904 [04:24<6:43:45,  1.26s/it]
 69%|██████▉   | 42751/61904 [04:26<6:58:22,  1.31s/it]
 69%|██████▉   | 42752/61904 [04:27<7:01:38,  1.32s/it]
 69%|██████▉   | 42753/61904 [04:29<7:02:38,  1.32s/it]
 69%|██████▉   | 42754/61904 [04:30<7:07:03,  1.34s/it]
 69%|██████▉   | 42755/61904 [04:32<7:10:05,  1.35s/it]
 69%|██████▉   | 42756/61904 [04:33<7:18:24,  1.37s/it]
 69%|██████▉   | 42757/61904 [04:34<7:20:48,  1.38s/it]
 69%|██████▉   | 42758/61904 [04:36<7:12:12,  1.35s/it]
 69%|██████▉   | 42759/61904 [04:37<7:17:53,  1.37s/it]
 69%|██████▉   | 42760/61904 [04:38<7:06:44,  1.34s/it]
                                                       
{'loss': 2.5337, 'learning_rate': 1.3102554129391935e-07, 'epoch': 11.05}

 69%|██████▉   | 42760/61904 [04:38<7:06:44,  1.34s/it]
 69%|██████▉   | 42761/61904 [04:40<7:09:44,  1.35s/it]
 69%|██████▉   | 42762/61904 [04:41<7:11:36,  1.35s/it]
 69%|██████▉   | 42763/61904 [04:43<7:29:58,  1.41s/it]
 69%|██████▉   | 42764/61904 [04:44<7:15:09,  1.36s/it]
 69%|██████▉   | 42765/61904 [04:45<7:11:15,  1.35s/it]
 69%|██████▉   | 42766/61904 [04:47<7:24:03,  1.39s/it]
 69%|██████▉   | 42767/61904 [04:48<7:23:49,  1.39s/it]
 69%|██████▉   | 42768/61904 [04:49<7:15:42,  1.37s/it]
 69%|██████▉   | 42769/61904 [04:51<7:05:52,  1.34s/it]
 69%|██████▉   | 42770/61904 [04:52<7:12:41,  1.36s/it]
 69%|██████▉   | 42771/61904 [04:53<7:09:17,  1.35s/it]
 69%|██████▉   | 42772/61904 [04:55<7:34:28,  1.43s/it]
 69%|██████▉   | 42773/61904 [04:56<7:27:30,  1.40s/it]
 69%|██████▉   | 42774/61904 [04:58<7:23:01,  1.39s/it]
 69%|██████▉   | 42775/61904 [04:59<7:42:35,  1.45s/it]
 69%|██████▉   | 42776/61904 [05:01<7:35:08,  1.43s/it]
 69%|██████▉   | 42777/61904 [05:02<7:20:15,  1.38s/it]
 69%|██████▉   | 42778/61904 [05:03<7:27:29,  1.40s/it]
 69%|██████▉   | 42779/61904 [05:05<7:28:05,  1.41s/it]
 69%|██████▉   | 42780/61904 [05:06<7:18:40,  1.38s/it]
                                                       
{'loss': 2.4815, 'learning_rate': 1.30993128484377e-07, 'epoch': 11.06}

 69%|██████▉   | 42780/61904 [05:06<7:18:40,  1.38s/it]
 69%|██████▉   | 42781/61904 [05:07<7:07:01,  1.34s/it]
 69%|██████▉   | 42782/61904 [05:09<7:26:11,  1.40s/it]
 69%|██████▉   | 42783/61904 [05:10<7:42:01,  1.45s/it]
 69%|██████▉   | 42784/61904 [05:12<7:37:45,  1.44s/it]
 69%|██████▉   | 42785/61904 [05:13<7:32:04,  1.42s/it]
 69%|██████▉   | 42786/61904 [05:15<7:32:45,  1.42s/it]
 69%|██████▉   | 42787/61904 [05:16<7:21:50,  1.39s/it]
 69%|██████▉   | 42788/61904 [05:17<7:17:17,  1.37s/it]
 69%|██████▉   | 42789/61904 [05:19<7:18:34,  1.38s/it]
 69%|██████▉   | 42790/61904 [05:20<7:14:57,  1.37s/it]
 69%|██████▉   | 42791/61904 [05:21<7:11:49,  1.36s/it]
 69%|██████▉   | 42792/61904 [05:23<7:06:00,  1.34s/it]
 69%|██████▉   | 42793/61904 [05:24<6:57:11,  1.31s/it]
 69%|██████▉   | 42794/61904 [05:25<7:06:40,  1.34s/it]
 69%|██████▉   | 42795/61904 [05:27<7:17:07,  1.37s/it]
 69%|██████▉   | 42796/61904 [05:28<7:27:36,  1.41s/it]
 69%|██████▉   | 42797/61904 [05:30<7:23:02,  1.39s/it]
 69%|██████▉   | 42798/61904 [05:31<7:27:14,  1.40s/it]
 69%|██████▉   | 42799/61904 [05:33<7:38:21,  1.44s/it]
 69%|██████▉   | 42800/61904 [05:34<7:37:48,  1.44s/it]
                                                       
{'loss': 2.4897, 'learning_rate': 1.309607156748347e-07, 'epoch': 11.06}

 69%|██████▉   | 42800/61904 [05:34<7:37:48,  1.44s/it]
 69%|██████▉   | 42801/61904 [05:35<7:27:45,  1.41s/it]
 69%|██████▉   | 42802/61904 [05:37<7:36:56,  1.44s/it]
 69%|██████▉   | 42803/61904 [05:38<7:28:51,  1.41s/it]
 69%|██████▉   | 42804/61904 [05:40<7:23:58,  1.39s/it]
 69%|██████▉   | 42805/61904 [05:41<7:23:22,  1.39s/it]
 69%|██████▉   | 42806/61904 [05:42<7:16:54,  1.37s/it]
 69%|██████▉   | 42807/61904 [05:44<7:37:10,  1.44s/it]
 69%|██████▉   | 42808/61904 [05:45<7:25:29,  1.40s/it]
 69%|██████▉   | 42809/61904 [05:47<7:43:01,  1.45s/it]
 69%|██████▉   | 42810/61904 [05:48<7:33:33,  1.43s/it]
 69%|██████▉   | 42811/61904 [05:49<7:25:22,  1.40s/it]
 69%|██████▉   | 42812/61904 [05:51<7:21:32,  1.39s/it]
 69%|██████▉   | 42813/61904 [05:52<7:27:17,  1.41s/it]
 69%|██████▉   | 42814/61904 [05:54<7:36:48,  1.44s/it]
 69%|██████▉   | 42815/61904 [05:55<7:31:09,  1.42s/it]
 69%|██████▉   | 42816/61904 [05:57<7:41:34,  1.45s/it]
 69%|██████▉   | 42817/61904 [05:58<7:40:51,  1.45s/it]
 69%|██████▉   | 42818/61904 [05:59<7:30:10,  1.42s/it]
 69%|██████▉   | 42819/61904 [06:01<7:27:44,  1.41s/it]
 69%|██████▉   | 42820/61904 [06:02<7:22:23,  1.39s/it]
                                                       
{'loss': 2.5184, 'learning_rate': 1.3092830286529236e-07, 'epoch': 11.07}

 69%|██████▉   | 42820/61904 [06:02<7:22:23,  1.39s/it]
 69%|██████▉   | 42821/61904 [06:04<7:29:51,  1.41s/it]
 69%|██████▉   | 42822/61904 [06:05<7:19:46,  1.38s/it]
 69%|██████▉   | 42823/61904 [06:06<7:28:08,  1.41s/it]
 69%|██████▉   | 42824/61904 [06:08<7:39:20,  1.44s/it]
 69%|██████▉   | 42825/61904 [06:10<7:51:07,  1.48s/it]
 69%|██████▉   | 42826/61904 [06:11<7:48:03,  1.47s/it]
 69%|██████▉   | 42827/61904 [06:12<7:37:19,  1.44s/it]
 69%|██████▉   | 42828/61904 [06:14<7:36:45,  1.44s/it]
 69%|██████▉   | 42829/61904 [06:15<7:19:32,  1.38s/it]
 69%|██████▉   | 42830/61904 [06:16<7:21:24,  1.39s/it]
 69%|██████▉   | 42831/61904 [06:18<7:10:16,  1.35s/it]
 69%|██████▉   | 42832/61904 [06:19<7:14:20,  1.37s/it]
 69%|██████▉   | 42833/61904 [06:21<7:22:32,  1.39s/it]
 69%|██████▉   | 42834/61904 [06:22<7:24:07,  1.40s/it]
 69%|██████▉   | 42835/61904 [06:23<7:24:44,  1.40s/it]
 69%|██████▉   | 42836/61904 [06:25<7:13:17,  1.36s/it]
 69%|██████▉   | 42837/61904 [06:26<7:06:43,  1.34s/it]
 69%|██████▉   | 42838/61904 [06:27<6:59:31,  1.32s/it]
 69%|██████▉   | 42839/61904 [06:29<6:59:32,  1.32s/it]
 69%|██████▉   | 42840/61904 [06:30<6:56:26,  1.31s/it]
                                                       
{'loss': 2.459, 'learning_rate': 1.3089589005575002e-07, 'epoch': 11.07}

 69%|██████▉   | 42840/61904 [06:30<6:56:26,  1.31s/it]
 69%|██████▉   | 42841/61904 [06:31<6:59:56,  1.32s/it]
 69%|██████▉   | 42842/61904 [06:32<7:00:08,  1.32s/it]
 69%|██████▉   | 42843/61904 [06:34<7:16:02,  1.37s/it]
 69%|██████▉   | 42844/61904 [06:35<7:22:41,  1.39s/it]
 69%|██████▉   | 42845/61904 [06:37<7:12:17,  1.36s/it]
 69%|██████▉   | 42846/61904 [06:38<7:16:31,  1.37s/it]
 69%|██████▉   | 42847/61904 [06:40<7:23:33,  1.40s/it]
 69%|██████▉   | 42848/61904 [06:41<7:15:51,  1.37s/it]
 69%|██████▉   | 42849/61904 [06:42<7:10:23,  1.36s/it]
 69%|██████▉   | 42850/61904 [06:44<7:18:25,  1.38s/it]
 69%|██████▉   | 42851/61904 [06:45<7:14:36,  1.37s/it]
 69%|██████▉   | 42852/61904 [06:46<7:23:56,  1.40s/it]
 69%|██████▉   | 42853/61904 [06:48<7:28:49,  1.41s/it]
 69%|██████▉   | 42854/61904 [06:49<7:15:42,  1.37s/it]
 69%|██████▉   | 42855/61904 [06:51<7:16:48,  1.38s/it]
 69%|██████▉   | 42856/61904 [06:52<7:10:03,  1.35s/it]
 69%|██████▉   | 42857/61904 [06:53<7:26:09,  1.41s/it]
 69%|██████▉   | 42858/61904 [06:55<7:18:09,  1.38s/it]
 69%|██████▉   | 42859/61904 [06:56<7:20:47,  1.39s/it]
 69%|██████▉   | 42860/61904 [06:57<7:15:57,  1.37s/it]
                                                       
{'loss': 2.4623, 'learning_rate': 1.308634772462077e-07, 'epoch': 11.08}

 69%|██████▉   | 42860/61904 [06:57<7:15:57,  1.37s/it]
 69%|██████▉   | 42861/61904 [06:59<7:04:17,  1.34s/it]
 69%|██████▉   | 42862/61904 [07:00<7:08:49,  1.35s/it]
 69%|██████▉   | 42863/61904 [07:01<7:12:30,  1.36s/it]
 69%|██████▉   | 42864/61904 [07:03<7:31:19,  1.42s/it]
 69%|██████▉   | 42865/61904 [07:04<7:29:56,  1.42s/it]
 69%|██████▉   | 42866/61904 [07:06<7:38:35,  1.45s/it]
 69%|██████▉   | 42867/61904 [07:07<7:39:48,  1.45s/it]
 69%|██████▉   | 42868/61904 [07:09<7:28:47,  1.41s/it]
 69%|██████▉   | 42869/61904 [07:10<7:25:26,  1.40s/it]
 69%|██████▉   | 42870/61904 [07:11<7:17:59,  1.38s/it]
 69%|██████▉   | 42871/61904 [07:13<7:07:09,  1.35s/it]
 69%|██████▉   | 42872/61904 [07:14<7:28:55,  1.42s/it]
 69%|██████▉   | 42873/61904 [07:16<7:13:52,  1.37s/it]
 69%|██████▉   | 42874/61904 [07:17<7:19:15,  1.38s/it]
 69%|██████▉   | 42875/61904 [07:18<7:25:28,  1.40s/it]
 69%|██████▉   | 42876/61904 [07:20<7:34:26,  1.43s/it]
 69%|██████▉   | 42877/61904 [07:21<7:25:34,  1.41s/it]
 69%|██████▉   | 42878/61904 [07:23<7:29:35,  1.42s/it]
 69%|██████▉   | 42879/61904 [07:24<7:26:17,  1.41s/it]
 69%|██████▉   | 42880/61904 [07:26<7:29:47,  1.42s/it]
                                                       
{'loss': 2.4422, 'learning_rate': 1.3083106443666535e-07, 'epoch': 11.08}

 69%|██████▉   | 42880/61904 [07:26<7:29:47,  1.42s/it]
 69%|██████▉   | 42881/61904 [07:27<7:33:33,  1.43s/it]
 69%|██████▉   | 42882/61904 [07:28<7:10:58,  1.36s/it]
 69%|██████▉   | 42883/61904 [07:30<7:09:58,  1.36s/it]
 69%|██████▉   | 42884/61904 [07:31<7:05:03,  1.34s/it]
 69%|██████▉   | 42885/61904 [07:32<7:11:59,  1.36s/it]
 69%|██████▉   | 42886/61904 [07:34<7:04:29,  1.34s/it]
 69%|██████▉   | 42887/61904 [07:35<7:08:35,  1.35s/it]
 69%|██████▉   | 42888/61904 [07:36<7:17:21,  1.38s/it]
 69%|██████▉   | 42889/61904 [07:38<7:12:59,  1.37s/it]
 69%|██████▉   | 42890/61904 [07:39<7:12:41,  1.37s/it]
 69%|██████▉   | 42891/61904 [07:40<7:17:41,  1.38s/it]
 69%|██████▉   | 42892/61904 [07:42<7:13:04,  1.37s/it]
 69%|██████▉   | 42893/61904 [07:43<7:16:50,  1.38s/it]
 69%|██████▉   | 42894/61904 [07:45<7:19:22,  1.39s/it]
 69%|██████▉   | 42895/61904 [07:46<7:28:33,  1.42s/it]
 69%|██████▉   | 42896/61904 [07:47<7:21:04,  1.39s/it]
 69%|██████▉   | 42897/61904 [07:49<7:14:24,  1.37s/it]
 69%|██████▉   | 42898/61904 [07:50<7:06:40,  1.35s/it]
 69%|██████▉   | 42899/61904 [07:51<7:06:30,  1.35s/it]
 69%|██████▉   | 42900/61904 [07:53<7:11:31,  1.36s/it]
                                                       
{'loss': 2.5212, 'learning_rate': 1.3079865162712303e-07, 'epoch': 11.09}

 69%|██████▉   | 42900/61904 [07:53<7:11:31,  1.36s/it]
 69%|██████▉   | 42901/61904 [07:54<7:13:46,  1.37s/it]
 69%|██████▉   | 42902/61904 [07:55<7:04:58,  1.34s/it]
 69%|██████▉   | 42903/61904 [07:57<7:10:35,  1.36s/it]
 69%|██████▉   | 42904/61904 [07:58<7:20:54,  1.39s/it]
 69%|██████▉   | 42905/61904 [08:00<7:20:25,  1.39s/it]
 69%|██████▉   | 42906/61904 [08:01<7:15:49,  1.38s/it]
 69%|██████▉   | 42907/61904 [08:02<7:10:16,  1.36s/it]
 69%|██████▉   | 42908/61904 [08:04<7:05:18,  1.34s/it]
 69%|██████▉   | 42909/61904 [08:05<7:06:24,  1.35s/it]
 69%|██████▉   | 42910/61904 [08:06<7:01:36,  1.33s/it]
 69%|██████▉   | 42911/61904 [08:08<7:06:59,  1.35s/it]
 69%|██████▉   | 42912/61904 [08:09<7:08:11,  1.35s/it]
 69%|██████▉   | 42913/61904 [08:11<7:45:14,  1.47s/it]
 69%|██████▉   | 42914/61904 [08:12<7:24:31,  1.40s/it]
 69%|██████▉   | 42915/61904 [08:13<7:21:17,  1.39s/it]
 69%|██████▉   | 42916/61904 [08:15<7:07:42,  1.35s/it]
 69%|██████▉   | 42917/61904 [08:16<7:18:44,  1.39s/it]
 69%|██████▉   | 42918/61904 [08:18<7:29:04,  1.42s/it]
 69%|██████▉   | 42919/61904 [08:19<7:31:28,  1.43s/it]
 69%|██████▉   | 42920/61904 [08:21<7:34:15,  1.44s/it]
                                                       
{'loss': 2.4923, 'learning_rate': 1.307662388175807e-07, 'epoch': 11.09}

 69%|██████▉   | 42920/61904 [08:21<7:34:15,  1.44s/it]
 69%|██████▉   | 42921/61904 [08:22<7:36:44,  1.44s/it]
 69%|██████▉   | 42922/61904 [08:23<7:21:47,  1.40s/it]
 69%|██████▉   | 42923/61904 [08:25<7:09:44,  1.36s/it]
 69%|██████▉   | 42924/61904 [08:26<7:05:19,  1.34s/it]
 69%|██████▉   | 42925/61904 [08:27<7:23:00,  1.40s/it]
 69%|██████▉   | 42926/61904 [08:29<7:26:12,  1.41s/it]
 69%|██████▉   | 42927/61904 [08:30<7:32:45,  1.43s/it]
 69%|██████▉   | 42928/61904 [08:32<7:17:30,  1.38s/it]
 69%|██████▉   | 42929/61904 [08:33<7:18:52,  1.39s/it]
 69%|██████▉   | 42930/61904 [08:35<7:36:21,  1.44s/it]
 69%|██████▉   | 42931/61904 [08:36<7:19:33,  1.39s/it]
 69%|██████▉   | 42932/61904 [08:37<7:13:42,  1.37s/it]
 69%|██████▉   | 42933/61904 [08:39<7:14:51,  1.38s/it]
 69%|██████▉   | 42934/61904 [08:40<7:28:35,  1.42s/it]
 69%|██████▉   | 42935/61904 [08:41<7:19:30,  1.39s/it]
 69%|██████▉   | 42936/61904 [08:43<7:25:27,  1.41s/it]
 69%|██████▉   | 42937/61904 [08:44<7:12:21,  1.37s/it]
 69%|██████▉   | 42938/61904 [08:45<7:07:38,  1.35s/it]
 69%|██████▉   | 42939/61904 [08:47<6:53:51,  1.31s/it]
 69%|██████▉   | 42940/61904 [08:48<7:09:33,  1.36s/it]
                                                       
{'loss': 2.5076, 'learning_rate': 1.3073382600803836e-07, 'epoch': 11.1}

 69%|██████▉   | 42940/61904 [08:48<7:09:33,  1.36s/it]
 69%|██████▉   | 42941/61904 [08:49<7:01:10,  1.33s/it]
 69%|██████▉   | 42942/61904 [08:51<7:01:12,  1.33s/it]
 69%|██████▉   | 42943/61904 [08:52<7:06:33,  1.35s/it]
 69%|██████▉   | 42944/61904 [08:53<7:05:59,  1.35s/it]
 69%|██████▉   | 42945/61904 [08:55<7:15:41,  1.38s/it]
 69%|██████▉   | 42946/61904 [08:56<7:03:36,  1.34s/it]
 69%|██████▉   | 42947/61904 [08:57<6:55:23,  1.31s/it]
 69%|██████▉   | 42948/61904 [08:59<7:07:49,  1.35s/it]
 69%|██████▉   | 42949/61904 [09:00<7:20:19,  1.39s/it]
 69%|██████▉   | 42950/61904 [09:02<7:23:08,  1.40s/it]
 69%|██████▉   | 42951/61904 [09:03<7:35:31,  1.44s/it]
 69%|██████▉   | 42952/61904 [09:05<7:29:29,  1.42s/it]
 69%|██████▉   | 42953/61904 [09:06<7:40:01,  1.46s/it]
 69%|██████▉   | 42954/61904 [09:08<7:26:35,  1.41s/it]
 69%|██████▉   | 42955/61904 [09:09<7:28:54,  1.42s/it]
 69%|██████▉   | 42956/61904 [09:10<7:20:19,  1.39s/it]
 69%|██████▉   | 42957/61904 [09:12<7:27:27,  1.42s/it]
 69%|██████▉   | 42958/61904 [09:13<7:30:01,  1.43s/it]
 69%|██████▉   | 42959/61904 [09:15<7:29:30,  1.42s/it]
 69%|██████▉   | 42960/61904 [09:16<7:23:46,  1.41s/it]
                                                       
{'loss': 2.5291, 'learning_rate': 1.3070141319849605e-07, 'epoch': 11.1}

 69%|██████▉   | 42960/61904 [09:16<7:23:46,  1.41s/it]
 69%|██████▉   | 42961/61904 [09:17<7:18:46,  1.39s/it]
 69%|██████▉   | 42962/61904 [09:19<7:07:19,  1.35s/it]
 69%|██████▉   | 42963/61904 [09:20<6:59:50,  1.33s/it]
 69%|██████▉   | 42964/61904 [09:21<6:57:35,  1.32s/it]
 69%|██████▉   | 42965/61904 [09:22<6:52:36,  1.31s/it]
 69%|██████▉   | 42966/61904 [09:24<7:19:34,  1.39s/it]
 69%|██████▉   | 42967/61904 [09:26<7:24:34,  1.41s/it]
 69%|██████▉   | 42968/61904 [09:27<7:25:12,  1.41s/it]
 69%|██████▉   | 42969/61904 [09:28<7:25:55,  1.41s/it]
 69%|██████▉   | 42970/61904 [09:30<7:23:50,  1.41s/it]
 69%|██████▉   | 42971/61904 [09:31<7:20:55,  1.40s/it]
 69%|██████▉   | 42972/61904 [09:32<7:15:14,  1.38s/it]
 69%|██████▉   | 42973/61904 [09:34<7:22:58,  1.40s/it]
 69%|██████▉   | 42974/61904 [09:35<7:25:41,  1.41s/it]
 69%|██████▉   | 42975/61904 [09:37<7:20:33,  1.40s/it]
 69%|██████▉   | 42976/61904 [09:38<7:16:05,  1.38s/it]
 69%|██████▉   | 42977/61904 [09:39<7:17:07,  1.39s/it]
 69%|██████▉   | 42978/61904 [09:41<7:13:15,  1.37s/it]
 69%|██████▉   | 42979/61904 [09:42<7:15:25,  1.38s/it]
 69%|██████▉   | 42980/61904 [09:44<7:09:50,  1.36s/it]
                                                       
{'loss': 2.4459, 'learning_rate': 1.306690003889537e-07, 'epoch': 11.11}

 69%|██████▉   | 42980/61904 [09:44<7:09:50,  1.36s/it]
 69%|██████▉   | 42981/61904 [09:45<7:20:34,  1.40s/it]
 69%|██████▉   | 42982/61904 [09:46<7:13:38,  1.38s/it]
 69%|██████▉   | 42983/61904 [09:48<7:15:49,  1.38s/it]
 69%|██████▉   | 42984/61904 [09:49<7:08:51,  1.36s/it]
 69%|██████▉   | 42985/61904 [09:50<7:04:47,  1.35s/it]
 69%|██████▉   | 42986/61904 [09:52<6:59:37,  1.33s/it]
 69%|██████▉   | 42987/61904 [09:53<7:05:27,  1.35s/it]
 69%|██████▉   | 42988/61904 [09:54<7:08:41,  1.36s/it]
 69%|██████▉   | 42989/61904 [09:56<7:01:03,  1.34s/it]
 69%|██████▉   | 42990/61904 [09:57<6:58:16,  1.33s/it]
 69%|██████▉   | 42991/61904 [09:58<7:01:48,  1.34s/it]
 69%|██████▉   | 42992/61904 [10:00<7:08:29,  1.36s/it]
 69%|██████▉   | 42993/61904 [10:01<7:06:56,  1.35s/it]
 69%|██████▉   | 42994/61904 [10:02<7:00:31,  1.33s/it]
 69%|██████▉   | 42995/61904 [10:04<7:13:46,  1.38s/it]
 69%|██████▉   | 42996/61904 [10:05<7:15:30,  1.38s/it]
 69%|██████▉   | 42997/61904 [10:07<7:16:25,  1.38s/it]
 69%|██████▉   | 42998/61904 [10:08<7:08:26,  1.36s/it]
 69%|██████▉   | 42999/61904 [10:09<7:01:07,  1.34s/it]
 69%|██████▉   | 43000/61904 [10:11<7:01:28,  1.34s/it]
                                                       
{'loss': 2.4522, 'learning_rate': 1.3063658757941137e-07, 'epoch': 11.11}

 69%|██████▉   | 43000/61904 [10:11<7:01:28,  1.34s/it]
 69%|██████▉   | 43001/61904 [10:12<7:10:11,  1.37s/it]
 69%|██████▉   | 43002/61904 [10:13<7:08:55,  1.36s/it]
 69%|██████▉   | 43003/61904 [10:15<7:03:51,  1.35s/it]
 69%|██████▉   | 43004/61904 [10:16<7:03:37,  1.34s/it]
 69%|██████▉   | 43005/61904 [10:17<6:57:56,  1.33s/it]
 69%|██████▉   | 43006/61904 [10:19<6:48:56,  1.30s/it]
 69%|██████▉   | 43007/61904 [10:20<7:06:31,  1.35s/it]
 69%|██████▉   | 43008/61904 [10:21<7:09:50,  1.36s/it]
 69%|██████▉   | 43009/61904 [10:23<7:11:34,  1.37s/it]
 69%|██████▉   | 43010/61904 [10:24<7:20:29,  1.40s/it]
 69%|██████▉   | 43011/61904 [10:26<7:16:55,  1.39s/it]
 69%|██████▉   | 43012/61904 [10:27<7:14:04,  1.38s/it]
 69%|██████▉   | 43013/61904 [10:28<7:02:22,  1.34s/it]
 69%|██████▉   | 43014/61904 [10:30<6:58:56,  1.33s/it]
 69%|██████▉   | 43015/61904 [10:31<6:53:30,  1.31s/it]
 69%|██████▉   | 43016/61904 [10:32<7:07:09,  1.36s/it]
 69%|██████▉   | 43017/61904 [10:34<7:10:49,  1.37s/it]
 69%|██████▉   | 43018/61904 [10:35<7:08:25,  1.36s/it]
 69%|██████▉   | 43019/61904 [10:36<7:15:17,  1.38s/it]
 69%|██████▉   | 43020/61904 [10:38<7:09:32,  1.36s/it]
                                                       
{'loss': 2.4752, 'learning_rate': 1.3060417476986906e-07, 'epoch': 11.12}

 69%|██████▉   | 43020/61904 [10:38<7:09:32,  1.36s/it]
 69%|██████▉   | 43021/61904 [10:39<7:08:39,  1.36s/it]
 69%|██████▉   | 43022/61904 [10:40<7:06:54,  1.36s/it]
 69%|██████▉   | 43023/61904 [10:42<6:58:59,  1.33s/it]
 70%|██████▉   | 43024/61904 [10:43<6:56:57,  1.33s/it]
 70%|██████▉   | 43025/61904 [10:44<7:02:19,  1.34s/it]
 70%|██████▉   | 43026/61904 [10:46<7:13:03,  1.38s/it]
 70%|██████▉   | 43027/61904 [10:47<7:13:45,  1.38s/it]
 70%|██████▉   | 43028/61904 [10:49<7:17:57,  1.39s/it]
 70%|██████▉   | 43029/61904 [10:50<7:25:42,  1.42s/it]
 70%|██████▉   | 43030/61904 [10:51<7:14:56,  1.38s/it]
 70%|██████▉   | 43031/61904 [10:53<7:24:39,  1.41s/it]
 70%|██████▉   | 43032/61904 [10:54<7:20:26,  1.40s/it]
 70%|██████▉   | 43033/61904 [10:56<7:16:37,  1.39s/it]
 70%|██████▉   | 43034/61904 [10:57<7:29:28,  1.43s/it]
 70%|██████▉   | 43035/61904 [10:58<7:09:54,  1.37s/it]
 70%|██████▉   | 43036/61904 [11:00<7:21:55,  1.41s/it]
 70%|██████▉   | 43037/61904 [11:01<7:20:24,  1.40s/it]
 70%|██████▉   | 43038/61904 [11:03<7:14:15,  1.38s/it]
 70%|██████▉   | 43039/61904 [11:04<7:18:38,  1.40s/it]
 70%|██████▉   | 43040/61904 [11:06<7:27:56,  1.42s/it]
                                                       
{'loss': 2.4877, 'learning_rate': 1.3057176196032672e-07, 'epoch': 11.12}

 70%|██████▉   | 43040/61904 [11:06<7:27:56,  1.42s/it]
 70%|██████▉   | 43041/61904 [11:07<7:36:19,  1.45s/it]
 70%|██████▉   | 43042/61904 [11:09<7:32:59,  1.44s/it]
 70%|██████▉   | 43043/61904 [11:10<7:37:13,  1.45s/it]
 70%|██████▉   | 43044/61904 [11:12<8:08:20,  1.55s/it]
 70%|██████▉   | 43045/61904 [11:13<7:59:29,  1.53s/it]
 70%|██████▉   | 43046/61904 [11:15<7:55:41,  1.51s/it]
 70%|██████▉   | 43047/61904 [11:16<7:43:01,  1.47s/it]
 70%|██████▉   | 43048/61904 [11:18<7:41:23,  1.47s/it]
 70%|██████▉   | 43049/61904 [11:19<7:30:20,  1.43s/it]
 70%|██████▉   | 43050/61904 [11:20<7:21:40,  1.41s/it]
 70%|██████▉   | 43051/61904 [11:22<7:40:25,  1.47s/it]
 70%|██████▉   | 43052/61904 [11:23<7:37:46,  1.46s/it]
 70%|██████▉   | 43053/61904 [11:25<7:30:01,  1.43s/it]
 70%|██████▉   | 43054/61904 [11:26<7:25:56,  1.42s/it]
 70%|██████▉   | 43055/61904 [11:27<7:08:54,  1.37s/it]
 70%|██████▉   | 43056/61904 [11:29<7:05:08,  1.35s/it]
 70%|██████▉   | 43057/61904 [11:30<7:01:00,  1.34s/it]
 70%|██████▉   | 43058/61904 [11:31<7:05:44,  1.36s/it]
 70%|██████▉   | 43059/61904 [11:33<7:07:47,  1.36s/it]
 70%|██████▉   | 43060/61904 [11:34<7:07:14,  1.36s/it]
                                                       
{'loss': 2.4969, 'learning_rate': 1.3053934915078438e-07, 'epoch': 11.13}

 70%|██████▉   | 43060/61904 [11:34<7:07:14,  1.36s/it]
 70%|██████▉   | 43061/61904 [11:35<7:07:46,  1.36s/it]
 70%|██████▉   | 43062/61904 [11:37<7:13:27,  1.38s/it]
 70%|██████▉   | 43063/61904 [11:38<7:07:30,  1.36s/it]
 70%|██████▉   | 43064/61904 [11:40<7:15:50,  1.39s/it]
 70%|██████▉   | 43065/61904 [11:41<7:19:14,  1.40s/it]
 70%|██████▉   | 43066/61904 [11:42<7:09:07,  1.37s/it]
 70%|██████▉   | 43067/61904 [11:44<7:15:59,  1.39s/it]
 70%|██████▉   | 43068/61904 [11:45<7:23:51,  1.41s/it]
 70%|██████▉   | 43069/61904 [11:47<7:13:26,  1.38s/it]
 70%|██████▉   | 43070/61904 [11:48<7:11:12,  1.37s/it]
 70%|██████▉   | 43071/61904 [11:49<7:07:01,  1.36s/it]
 70%|██████▉   | 43072/61904 [11:51<6:59:04,  1.34s/it]
 70%|██████▉   | 43073/61904 [11:52<6:49:12,  1.30s/it]
 70%|██████▉   | 43074/61904 [11:53<7:09:57,  1.37s/it]
 70%|██████▉   | 43075/61904 [11:55<7:07:35,  1.36s/it]
 70%|██████▉   | 43076/61904 [11:56<7:01:15,  1.34s/it]
 70%|██████▉   | 43077/61904 [11:57<6:53:09,  1.32s/it]
 70%|██████▉   | 43078/61904 [11:59<6:58:05,  1.33s/it]
 70%|██████▉   | 43079/61904 [12:00<6:58:37,  1.33s/it]
 70%|██████▉   | 43080/61904 [12:01<7:05:28,  1.36s/it]
                                                       
{'loss': 2.5331, 'learning_rate': 1.3050693634124207e-07, 'epoch': 11.13}

 70%|██████▉   | 43080/61904 [12:01<7:05:28,  1.36s/it]
 70%|██████▉   | 43081/61904 [12:03<7:14:08,  1.38s/it]
 70%|██████▉   | 43082/61904 [12:04<7:08:41,  1.37s/it]
 70%|██████▉   | 43083/61904 [12:05<7:01:39,  1.34s/it]
 70%|██████▉   | 43084/61904 [12:07<6:56:09,  1.33s/it]
 70%|██████▉   | 43085/61904 [12:08<7:13:19,  1.38s/it]
 70%|██████▉   | 43086/61904 [12:10<7:12:25,  1.38s/it]
 70%|██████▉   | 43087/61904 [12:11<7:13:18,  1.38s/it]
 70%|██████▉   | 43088/61904 [12:12<7:21:37,  1.41s/it]
 70%|██████▉   | 43089/61904 [12:14<7:24:11,  1.42s/it]
 70%|██████▉   | 43090/61904 [12:15<7:20:14,  1.40s/it]
 70%|██████▉   | 43091/61904 [12:16<7:08:32,  1.37s/it]
 70%|██████▉   | 43092/61904 [12:18<7:31:30,  1.44s/it]
 70%|██████▉   | 43093/61904 [12:19<7:24:51,  1.42s/it]
 70%|██████▉   | 43094/61904 [12:21<7:30:33,  1.44s/it]
 70%|██████▉   | 43095/61904 [12:22<7:28:07,  1.43s/it]
 70%|██████▉   | 43096/61904 [12:24<7:19:34,  1.40s/it]
 70%|██████▉   | 43097/61904 [12:25<7:31:08,  1.44s/it]
 70%|██████▉   | 43098/61904 [12:27<7:20:00,  1.40s/it]
 70%|██████▉   | 43099/61904 [12:28<7:11:13,  1.38s/it]
 70%|██████▉   | 43100/61904 [12:29<7:12:58,  1.38s/it]
                                                       
{'loss': 2.4214, 'learning_rate': 1.304745235316997e-07, 'epoch': 11.14}

 70%|██████▉   | 43100/61904 [12:29<7:12:58,  1.38s/it]
 70%|██████▉   | 43101/61904 [12:31<7:14:48,  1.39s/it]
 70%|██████▉   | 43102/61904 [12:32<7:09:54,  1.37s/it]
 70%|██████▉   | 43103/61904 [12:33<7:12:12,  1.38s/it]
 70%|██████▉   | 43104/61904 [12:35<7:22:28,  1.41s/it]
 70%|██████▉   | 43105/61904 [12:36<7:18:50,  1.40s/it]
 70%|██████▉   | 43106/61904 [12:38<7:25:17,  1.42s/it]
 70%|██████▉   | 43107/61904 [12:39<7:13:04,  1.38s/it]
 70%|██████▉   | 43108/61904 [12:40<7:22:18,  1.41s/it]
 70%|██████▉   | 43109/61904 [12:42<7:14:52,  1.39s/it]
 70%|██████▉   | 43110/61904 [12:43<7:04:27,  1.36s/it]
 70%|██████▉   | 43111/61904 [12:44<7:04:05,  1.35s/it]
 70%|██████▉   | 43112/61904 [12:46<7:11:15,  1.38s/it]
 70%|██████▉   | 43113/61904 [12:47<7:08:15,  1.37s/it]
 70%|██████▉   | 43114/61904 [12:49<7:04:54,  1.36s/it]
 70%|██████▉   | 43115/61904 [12:50<7:04:57,  1.36s/it]
 70%|██████▉   | 43116/61904 [12:51<7:03:05,  1.35s/it]
 70%|██████▉   | 43117/61904 [12:53<7:07:49,  1.37s/it]
 70%|██████▉   | 43118/61904 [12:54<7:10:45,  1.38s/it]
 70%|██████▉   | 43119/61904 [12:55<7:01:49,  1.35s/it]
 70%|██████▉   | 43120/61904 [12:57<7:01:06,  1.35s/it]
                                                       
{'loss': 2.4795, 'learning_rate': 1.304421107221574e-07, 'epoch': 11.14}

 70%|██████▉   | 43120/61904 [12:57<7:01:06,  1.35s/it]
 70%|██████▉   | 43121/61904 [12:58<7:02:44,  1.35s/it]
 70%|██████▉   | 43122/61904 [12:59<7:07:37,  1.37s/it]
 70%|██████▉   | 43123/61904 [13:01<7:04:28,  1.36s/it]
 70%|██████▉   | 43124/61904 [13:02<7:05:22,  1.36s/it]
 70%|██████▉   | 43125/61904 [13:04<7:17:04,  1.40s/it]
 70%|██████▉   | 43126/61904 [13:05<7:29:57,  1.44s/it]
 70%|██████▉   | 43127/61904 [13:06<7:21:09,  1.41s/it]
 70%|██████▉   | 43128/61904 [13:08<7:22:04,  1.41s/it]
 70%|██████▉   | 43129/61904 [13:09<7:28:13,  1.43s/it]
 70%|██████▉   | 43130/61904 [13:11<7:25:18,  1.42s/it]
 70%|██████▉   | 43131/61904 [13:12<7:30:33,  1.44s/it]
 70%|██████▉   | 43132/61904 [13:14<7:23:44,  1.42s/it]
 70%|██████▉   | 43133/61904 [13:15<7:26:35,  1.43s/it]
 70%|██████▉   | 43134/61904 [13:17<7:38:56,  1.47s/it]
 70%|██████▉   | 43135/61904 [13:18<7:22:25,  1.41s/it]
 70%|██████▉   | 43136/61904 [13:19<7:20:51,  1.41s/it]
 70%|██████▉   | 43137/61904 [13:21<7:21:26,  1.41s/it]
 70%|██████▉   | 43138/61904 [13:22<7:23:50,  1.42s/it]
 70%|██████▉   | 43139/61904 [13:24<7:23:26,  1.42s/it]
 70%|██████▉   | 43140/61904 [13:25<7:20:52,  1.41s/it]
                                                       
{'loss': 2.491, 'learning_rate': 1.3040969791261506e-07, 'epoch': 11.15}

 70%|██████▉   | 43140/61904 [13:25<7:20:52,  1.41s/it]
 70%|██████▉   | 43141/61904 [13:26<7:11:41,  1.38s/it]
 70%|██████▉   | 43142/61904 [13:28<7:05:37,  1.36s/it]
 70%|██████▉   | 43143/61904 [13:29<7:10:58,  1.38s/it]
 70%|██████▉   | 43144/61904 [13:31<7:22:13,  1.41s/it]
 70%|██████▉   | 43145/61904 [13:32<7:11:15,  1.38s/it]
 70%|██████▉   | 43146/61904 [13:33<7:18:56,  1.40s/it]
 70%|██████▉   | 43147/61904 [13:35<7:16:11,  1.40s/it]
 70%|██████▉   | 43148/61904 [13:36<7:14:37,  1.39s/it]
 70%|██████▉   | 43149/61904 [13:37<7:03:16,  1.35s/it]
 70%|██████▉   | 43150/61904 [13:39<7:00:43,  1.35s/it]
 70%|██████▉   | 43151/61904 [13:40<7:02:14,  1.35s/it]
 70%|██████▉   | 43152/61904 [13:41<7:02:33,  1.35s/it]
 70%|██████▉   | 43153/61904 [13:43<7:02:24,  1.35s/it]
 70%|██████▉   | 43154/61904 [13:44<6:58:08,  1.34s/it]
 70%|██████▉   | 43155/61904 [13:45<6:59:18,  1.34s/it]
 70%|██████▉   | 43156/61904 [13:47<6:49:51,  1.31s/it]
 70%|██████▉   | 43157/61904 [13:48<6:50:30,  1.31s/it]
 70%|██████▉   | 43158/61904 [13:49<6:57:26,  1.34s/it]
 70%|██████▉   | 43159/61904 [13:51<7:00:49,  1.35s/it]
 70%|██████▉   | 43160/61904 [13:52<7:12:29,  1.38s/it]
                                                       
{'loss': 2.4823, 'learning_rate': 1.3037728510307272e-07, 'epoch': 11.16}

 70%|██████▉   | 43160/61904 [13:52<7:12:29,  1.38s/it]
 70%|██████▉   | 43161/61904 [13:54<7:51:00,  1.51s/it]
 70%|██████▉   | 43162/61904 [13:55<7:40:42,  1.47s/it]
 70%|██████▉   | 43163/61904 [13:57<7:33:06,  1.45s/it]
 70%|██████▉   | 43164/61904 [13:58<7:40:06,  1.47s/it]
 70%|██████▉   | 43165/61904 [14:00<7:35:53,  1.46s/it]
 70%|██████▉   | 43166/61904 [14:01<7:21:42,  1.41s/it]
 70%|██████▉   | 43167/61904 [14:02<7:15:39,  1.40s/it]
 70%|██████▉   | 43168/61904 [14:04<7:26:35,  1.43s/it]
 70%|██████▉   | 43169/61904 [14:05<7:16:23,  1.40s/it]
 70%|██████▉   | 43170/61904 [14:07<7:08:38,  1.37s/it]
 70%|██████▉   | 43171/61904 [14:08<7:02:03,  1.35s/it]
 70%|██████▉   | 43172/61904 [14:09<7:13:01,  1.39s/it]
 70%|██████▉   | 43173/61904 [14:11<7:11:35,  1.38s/it]
 70%|██████▉   | 43174/61904 [14:12<7:05:26,  1.36s/it]
 70%|██████▉   | 43175/61904 [14:13<7:13:05,  1.39s/it]
 70%|██████▉   | 43176/61904 [14:15<7:23:17,  1.42s/it]
 70%|██████▉   | 43177/61904 [14:16<7:20:56,  1.41s/it]
 70%|██████▉   | 43178/61904 [14:18<7:19:08,  1.41s/it]
 70%|██████▉   | 43179/61904 [14:19<7:14:36,  1.39s/it]
 70%|██████▉   | 43180/61904 [14:20<7:08:11,  1.37s/it]
                                                       
{'loss': 2.5129, 'learning_rate': 1.303448722935304e-07, 'epoch': 11.16}

 70%|██████▉   | 43180/61904 [14:20<7:08:11,  1.37s/it]
 70%|██████▉   | 43181/61904 [14:22<7:30:53,  1.44s/it]
 70%|██████▉   | 43182/61904 [14:23<7:31:40,  1.45s/it]
 70%|██████▉   | 43183/61904 [14:25<7:24:08,  1.42s/it]
 70%|██████▉   | 43184/61904 [14:26<7:16:23,  1.40s/it]
 70%|██████▉   | 43185/61904 [14:28<7:11:09,  1.38s/it]
 70%|██████▉   | 43186/61904 [14:29<7:10:05,  1.38s/it]
 70%|██████▉   | 43187/61904 [14:30<7:17:41,  1.40s/it]
 70%|██████▉   | 43188/61904 [14:32<7:13:24,  1.39s/it]
 70%|██████▉   | 43189/61904 [14:33<7:11:32,  1.38s/it]
 70%|██████▉   | 43190/61904 [14:34<7:08:52,  1.38s/it]
 70%|██████▉   | 43191/61904 [14:36<7:01:22,  1.35s/it]
 70%|██████▉   | 43192/61904 [14:37<6:54:31,  1.33s/it]
 70%|██████▉   | 43193/61904 [14:38<7:05:11,  1.36s/it]
 70%|██████▉   | 43194/61904 [14:40<7:13:26,  1.39s/it]
 70%|██████▉   | 43195/61904 [14:41<7:20:16,  1.41s/it]
 70%|██████▉   | 43196/61904 [14:43<7:15:49,  1.40s/it]
 70%|██████▉   | 43197/61904 [14:44<7:17:40,  1.40s/it]
 70%|██████▉   | 43198/61904 [14:46<7:16:57,  1.40s/it]
 70%|██████▉   | 43199/61904 [14:47<7:21:19,  1.42s/it]
 70%|██████▉   | 43200/61904 [14:48<7:22:21,  1.42s/it]
                                                       
{'loss': 2.4543, 'learning_rate': 1.3031245948398807e-07, 'epoch': 11.17}

 70%|██████▉   | 43200/61904 [14:48<7:22:21,  1.42s/it]
 70%|██████▉   | 43201/61904 [14:50<7:21:04,  1.42s/it]
 70%|██████▉   | 43202/61904 [14:51<7:09:08,  1.38s/it]
 70%|██████▉   | 43203/61904 [14:53<7:13:25,  1.39s/it]
 70%|██████▉   | 43204/61904 [14:54<7:11:12,  1.38s/it]
 70%|██████▉   | 43205/61904 [14:55<7:03:48,  1.36s/it]
 70%|██████▉   | 43206/61904 [14:57<7:05:55,  1.37s/it]
 70%|██████▉   | 43207/61904 [14:58<7:21:08,  1.42s/it]
 70%|██████▉   | 43208/61904 [14:59<7:10:38,  1.38s/it]
 70%|██████▉   | 43209/61904 [15:01<7:10:07,  1.38s/it]
 70%|██████▉   | 43210/61904 [15:02<7:07:10,  1.37s/it]
 70%|██████▉   | 43211/61904 [15:03<7:01:09,  1.35s/it]
 70%|██████▉   | 43212/61904 [15:05<7:08:30,  1.38s/it]
 70%|██████▉   | 43213/61904 [15:06<7:09:24,  1.38s/it]
 70%|██████▉   | 43214/61904 [15:08<7:04:27,  1.36s/it]
 70%|██████▉   | 43215/61904 [15:09<7:14:55,  1.40s/it]
 70%|██████▉   | 43216/61904 [15:11<7:21:29,  1.42s/it]
 70%|██████▉   | 43217/61904 [15:12<7:12:30,  1.39s/it]
 70%|██████▉   | 43218/61904 [15:13<7:13:53,  1.39s/it]
 70%|██████▉   | 43219/61904 [15:15<7:06:23,  1.37s/it]
 70%|██████▉   | 43220/61904 [15:16<7:07:34,  1.37s/it]
                                                       
{'loss': 2.4735, 'learning_rate': 1.3028004667444573e-07, 'epoch': 11.17}

 70%|██████▉   | 43220/61904 [15:16<7:07:34,  1.37s/it]
 70%|██████▉   | 43221/61904 [15:17<7:10:55,  1.38s/it]
 70%|██████▉   | 43222/61904 [15:19<7:08:01,  1.37s/it]
 70%|██████▉   | 43223/61904 [15:20<7:01:30,  1.35s/it]
 70%|██████▉   | 43224/61904 [15:21<7:09:34,  1.38s/it]
 70%|██████▉   | 43225/61904 [15:23<6:58:31,  1.34s/it]
 70%|██████▉   | 43226/61904 [15:24<6:56:02,  1.34s/it]
 70%|██████▉   | 43227/61904 [15:25<7:04:46,  1.36s/it]
 70%|██████▉   | 43228/61904 [15:27<7:04:40,  1.36s/it]
 70%|██████▉   | 43229/61904 [15:28<7:09:18,  1.38s/it]
 70%|██████▉   | 43230/61904 [15:30<7:11:05,  1.39s/it]
 70%|██████▉   | 43231/61904 [15:31<7:09:59,  1.38s/it]
 70%|██████▉   | 43232/61904 [15:32<7:12:18,  1.39s/it]
 70%|██████▉   | 43233/61904 [15:34<7:10:45,  1.38s/it]
 70%|██████▉   | 43234/61904 [15:35<7:24:41,  1.43s/it]
 70%|██████▉   | 43235/61904 [15:37<7:21:01,  1.42s/it]
 70%|██████▉   | 43236/61904 [15:38<7:16:41,  1.40s/it]
 70%|██████▉   | 43237/61904 [15:39<7:06:01,  1.37s/it]
 70%|██████▉   | 43238/61904 [15:41<7:00:55,  1.35s/it]
 70%|██████▉   | 43239/61904 [15:42<7:09:10,  1.38s/it]
 70%|██████▉   | 43240/61904 [15:44<7:11:00,  1.39s/it]
                                                       
{'loss': 2.5127, 'learning_rate': 1.3024763386490342e-07, 'epoch': 11.18}

 70%|██████▉   | 43240/61904 [15:44<7:11:00,  1.39s/it]
 70%|██████▉   | 43241/61904 [15:45<7:32:52,  1.46s/it]
 70%|██████▉   | 43242/61904 [15:46<7:13:52,  1.39s/it]
 70%|██████▉   | 43243/61904 [15:48<7:33:29,  1.46s/it]
 70%|██████▉   | 43244/61904 [15:50<7:48:05,  1.51s/it]
 70%|██████▉   | 43245/61904 [15:51<7:44:05,  1.49s/it]
 70%|██████▉   | 43246/61904 [15:52<7:31:54,  1.45s/it]
 70%|██████▉   | 43247/61904 [15:54<7:34:11,  1.46s/it]
 70%|██████▉   | 43248/61904 [15:55<7:27:17,  1.44s/it]
 70%|██████▉   | 43249/61904 [15:57<7:13:29,  1.39s/it]
 70%|██████▉   | 43250/61904 [15:58<7:07:00,  1.37s/it]
 70%|██████▉   | 43251/61904 [15:59<7:16:14,  1.40s/it]
 70%|██████▉   | 43252/61904 [16:01<7:27:33,  1.44s/it]
 70%|██████▉   | 43253/61904 [16:02<7:17:37,  1.41s/it]
 70%|██████▉   | 43254/61904 [16:04<7:31:21,  1.45s/it]
 70%|██████▉   | 43255/61904 [16:05<7:34:23,  1.46s/it]
 70%|██████▉   | 43256/61904 [16:07<7:19:49,  1.42s/it]
 70%|██████▉   | 43257/61904 [16:08<7:13:14,  1.39s/it]
 70%|██████▉   | 43258/61904 [16:09<7:21:14,  1.42s/it]
 70%|██████▉   | 43259/61904 [16:11<7:30:22,  1.45s/it]
 70%|██████▉   | 43260/61904 [16:12<7:16:52,  1.41s/it]
                                                       
{'loss': 2.4045, 'learning_rate': 1.3021522105536105e-07, 'epoch': 11.18}

 70%|██████▉   | 43260/61904 [16:12<7:16:52,  1.41s/it]
 70%|██████▉   | 43261/61904 [16:14<7:23:12,  1.43s/it]
 70%|██████▉   | 43262/61904 [16:15<7:09:17,  1.38s/it]
 70%|██████▉   | 43263/61904 [16:16<7:09:36,  1.38s/it]
 70%|██████▉   | 43264/61904 [16:18<7:26:22,  1.44s/it]
 70%|██████▉   | 43265/61904 [16:19<7:29:10,  1.45s/it]
 70%|██████▉   | 43266/61904 [16:21<7:18:24,  1.41s/it]
 70%|██████▉   | 43267/61904 [16:22<7:07:16,  1.38s/it]
 70%|██████▉   | 43268/61904 [16:23<7:13:46,  1.40s/it]
 70%|██████▉   | 43269/61904 [16:25<7:07:45,  1.38s/it]
 70%|██████▉   | 43270/61904 [16:26<7:04:10,  1.37s/it]
 70%|██████▉   | 43271/61904 [16:28<7:03:02,  1.36s/it]
 70%|██████▉   | 43272/61904 [16:29<7:19:41,  1.42s/it]
 70%|██████▉   | 43273/61904 [16:30<7:04:49,  1.37s/it]
 70%|██████▉   | 43274/61904 [16:32<7:04:54,  1.37s/it]
 70%|██████▉   | 43275/61904 [16:33<7:18:21,  1.41s/it]
 70%|██████▉   | 43276/61904 [16:35<7:18:21,  1.41s/it]
 70%|██████▉   | 43277/61904 [16:36<7:08:48,  1.38s/it]
 70%|██████▉   | 43278/61904 [16:37<7:07:46,  1.38s/it]
 70%|██████▉   | 43279/61904 [16:39<7:20:37,  1.42s/it]
 70%|██████▉   | 43280/61904 [16:40<7:24:48,  1.43s/it]
                                                       
{'loss': 2.4599, 'learning_rate': 1.3018280824581874e-07, 'epoch': 11.19}

 70%|██████▉   | 43280/61904 [16:40<7:24:48,  1.43s/it]
 70%|██████▉   | 43281/61904 [16:42<7:28:35,  1.45s/it]
 70%|██████▉   | 43282/61904 [16:43<7:20:24,  1.42s/it]
 70%|██████▉   | 43283/61904 [16:44<7:08:44,  1.38s/it]
 70%|██████▉   | 43284/61904 [16:46<7:05:47,  1.37s/it]
 70%|██████▉   | 43285/61904 [16:47<7:07:06,  1.38s/it]
 70%|██████▉   | 43286/61904 [16:49<7:07:43,  1.38s/it]
 70%|██████▉   | 43287/61904 [16:50<7:09:02,  1.38s/it]
 70%|██████▉   | 43288/61904 [16:51<7:16:40,  1.41s/it]
 70%|██████▉   | 43289/61904 [16:53<7:13:33,  1.40s/it]
 70%|██████▉   | 43290/61904 [16:54<7:09:32,  1.38s/it]
 70%|██████▉   | 43291/61904 [16:55<7:05:36,  1.37s/it]
 70%|██████▉   | 43292/61904 [16:57<6:54:48,  1.34s/it]
 70%|██████▉   | 43293/61904 [16:58<6:48:04,  1.32s/it]
 70%|██████▉   | 43294/61904 [16:59<6:56:47,  1.34s/it]
 70%|██████▉   | 43295/61904 [17:01<6:54:57,  1.34s/it]
 70%|██████▉   | 43296/61904 [17:02<7:24:04,  1.43s/it]
 70%|██████▉   | 43297/61904 [17:04<7:30:03,  1.45s/it]
 70%|██████▉   | 43298/61904 [17:05<7:36:19,  1.47s/it]
 70%|██████▉   | 43299/61904 [17:07<7:40:32,  1.49s/it]
 70%|██████▉   | 43300/61904 [17:08<7:35:08,  1.47s/it]
                                                       
{'loss': 2.4875, 'learning_rate': 1.301503954362764e-07, 'epoch': 11.19}

 70%|██████▉   | 43300/61904 [17:08<7:35:08,  1.47s/it]
 70%|██████▉   | 43301/61904 [17:10<7:24:21,  1.43s/it]
 70%|██████▉   | 43302/61904 [17:11<7:20:14,  1.42s/it]
 70%|██████▉   | 43303/61904 [17:12<7:17:28,  1.41s/it]
 70%|██████▉   | 43304/61904 [17:14<7:10:38,  1.39s/it]
 70%|██████▉   | 43305/61904 [17:15<7:15:40,  1.41s/it]
 70%|██████▉   | 43306/61904 [17:17<7:16:26,  1.41s/it]
 70%|██████▉   | 43307/61904 [17:18<7:24:35,  1.43s/it]
 70%|██████▉   | 43308/61904 [17:20<7:36:33,  1.47s/it]
 70%|██████▉   | 43309/61904 [17:21<7:37:22,  1.48s/it]
 70%|██████▉   | 43310/61904 [17:23<7:34:31,  1.47s/it]
 70%|██████▉   | 43311/61904 [17:24<7:27:44,  1.44s/it]
 70%|██████▉   | 43312/61904 [17:26<7:40:22,  1.49s/it]
 70%|██████▉   | 43313/61904 [17:27<7:51:10,  1.52s/it]
 70%|██████▉   | 43314/61904 [17:29<7:59:40,  1.55s/it]
 70%|██████▉   | 43315/61904 [17:30<7:55:58,  1.54s/it]
 70%|██████▉   | 43316/61904 [17:32<7:50:06,  1.52s/it]
 70%|██████▉   | 43317/61904 [17:33<7:37:43,  1.48s/it]
 70%|██████▉   | 43318/61904 [17:35<7:37:24,  1.48s/it]
 70%|██████▉   | 43319/61904 [17:36<7:36:26,  1.47s/it]
 70%|██████▉   | 43320/61904 [17:38<7:42:18,  1.49s/it]
                                                       
{'loss': 2.4523, 'learning_rate': 1.3011798262673407e-07, 'epoch': 11.2}

 70%|██████▉   | 43320/61904 [17:38<7:42:18,  1.49s/it]
 70%|██████▉   | 43321/61904 [17:39<7:36:44,  1.47s/it]
 70%|██████▉   | 43322/61904 [17:40<7:21:40,  1.43s/it]
 70%|██████▉   | 43323/61904 [17:42<7:24:23,  1.44s/it]
 70%|██████▉   | 43324/61904 [17:43<7:31:36,  1.46s/it]
 70%|██████▉   | 43325/61904 [17:45<7:26:52,  1.44s/it]
 70%|██████▉   | 43326/61904 [17:46<7:37:00,  1.48s/it]
 70%|██████▉   | 43327/61904 [17:48<7:23:56,  1.43s/it]
 70%|██████▉   | 43328/61904 [17:49<7:19:48,  1.42s/it]
 70%|██████▉   | 43329/61904 [17:51<7:27:22,  1.45s/it]
 70%|██████▉   | 43330/61904 [17:52<7:24:00,  1.43s/it]
 70%|██████▉   | 43331/61904 [17:54<7:32:59,  1.46s/it]
 70%|██████▉   | 43332/61904 [17:55<7:15:04,  1.41s/it]
 70%|███████   | 43333/61904 [17:56<7:03:01,  1.37s/it]
 70%|███████   | 43334/61904 [17:57<7:03:25,  1.37s/it]
 70%|███████   | 43335/61904 [17:59<7:19:16,  1.42s/it]
 70%|███████   | 43336/61904 [18:00<7:22:56,  1.43s/it]
 70%|███████   | 43337/61904 [18:02<7:13:53,  1.40s/it]
 70%|███████   | 43338/61904 [18:03<7:24:04,  1.44s/it]
 70%|███████   | 43339/61904 [18:05<7:10:14,  1.39s/it]
 70%|███████   | 43340/61904 [18:06<7:12:32,  1.40s/it]
                                                       
{'loss': 2.47, 'learning_rate': 1.3008556981719175e-07, 'epoch': 11.2}

 70%|███████   | 43340/61904 [18:06<7:12:32,  1.40s/it]
 70%|███████   | 43341/61904 [18:07<7:16:08,  1.41s/it]
 70%|███████   | 43342/61904 [18:09<7:16:53,  1.41s/it]
 70%|███████   | 43343/61904 [18:10<7:10:07,  1.39s/it]
 70%|███████   | 43344/61904 [18:12<7:06:03,  1.38s/it]
 70%|███████   | 43345/61904 [18:13<7:10:57,  1.39s/it]
 70%|███████   | 43346/61904 [18:14<7:12:45,  1.40s/it]
 70%|███████   | 43347/61904 [18:16<7:22:21,  1.43s/it]
 70%|███████   | 43348/61904 [18:17<7:12:18,  1.40s/it]
 70%|███████   | 43349/61904 [18:18<6:58:37,  1.35s/it]
 70%|███████   | 43350/61904 [18:20<6:45:12,  1.31s/it]
 70%|███████   | 43351/61904 [18:21<6:55:16,  1.34s/it]
 70%|███████   | 43352/61904 [18:22<7:02:37,  1.37s/it]
 70%|███████   | 43353/61904 [18:24<6:51:23,  1.33s/it]
 70%|███████   | 43354/61904 [18:25<6:52:50,  1.34s/it]
 70%|███████   | 43355/61904 [18:26<6:50:58,  1.33s/it]
 70%|███████   | 43356/61904 [18:28<6:45:01,  1.31s/it]
 70%|███████   | 43357/61904 [18:29<6:43:16,  1.30s/it]
 70%|███████   | 43358/61904 [18:30<6:42:20,  1.30s/it]
 70%|███████   | 43359/61904 [18:32<6:46:11,  1.31s/it]
 70%|███████   | 43360/61904 [18:33<6:50:01,  1.33s/it]
                                                       
{'loss': 2.464, 'learning_rate': 1.3005315700764942e-07, 'epoch': 11.21}

 70%|███████   | 43360/61904 [18:33<6:50:01,  1.33s/it]
 70%|███████   | 43361/61904 [18:34<6:54:52,  1.34s/it]
 70%|███████   | 43362/61904 [18:36<7:01:56,  1.37s/it]
 70%|███████   | 43363/61904 [18:37<6:58:40,  1.35s/it]
 70%|███████   | 43364/61904 [18:38<6:57:40,  1.35s/it]
 70%|███████   | 43365/61904 [18:40<6:50:46,  1.33s/it]
 70%|███████   | 43366/61904 [18:41<7:01:57,  1.37s/it]
 70%|███████   | 43367/61904 [18:43<7:05:48,  1.38s/it]
 70%|███████   | 43368/61904 [18:44<7:08:34,  1.39s/it]
 70%|███████   | 43369/61904 [18:45<7:04:18,  1.37s/it]
 70%|███████   | 43370/61904 [18:47<6:50:03,  1.33s/it]
 70%|███████   | 43371/61904 [18:48<6:54:53,  1.34s/it]
 70%|███████   | 43372/61904 [18:49<7:07:19,  1.38s/it]
 70%|███████   | 43373/61904 [18:51<7:25:13,  1.44s/it]
 70%|███████   | 43374/61904 [18:52<7:08:57,  1.39s/it]
 70%|███████   | 43375/61904 [18:54<7:03:39,  1.37s/it]
 70%|███████   | 43376/61904 [18:55<7:14:18,  1.41s/it]
 70%|███████   | 43377/61904 [18:56<7:02:48,  1.37s/it]
 70%|███████   | 43378/61904 [18:58<7:11:32,  1.40s/it]
 70%|███████   | 43379/61904 [18:59<7:03:05,  1.37s/it]
 70%|███████   | 43380/61904 [19:00<6:45:33,  1.31s/it]
                                                       
{'loss': 2.5223, 'learning_rate': 1.3002074419810708e-07, 'epoch': 11.21}

 70%|███████   | 43380/61904 [19:00<6:45:33,  1.31s/it]
 70%|███████   | 43381/61904 [19:02<7:06:29,  1.38s/it]
 70%|███████   | 43382/61904 [19:03<7:03:05,  1.37s/it]
 70%|███████   | 43383/61904 [19:04<6:59:41,  1.36s/it]
 70%|███████   | 43384/61904 [19:06<7:00:25,  1.36s/it]
 70%|███████   | 43385/61904 [19:07<7:05:15,  1.38s/it]
 70%|███████   | 43386/61904 [19:09<6:55:06,  1.34s/it]
 70%|███████   | 43387/61904 [19:10<7:00:28,  1.36s/it]
 70%|███████   | 43388/61904 [19:11<7:04:57,  1.38s/it]
 70%|███████   | 43389/61904 [19:13<7:00:02,  1.36s/it]
 70%|███████   | 43390/61904 [19:14<7:01:02,  1.36s/it]
 70%|███████   | 43391/61904 [19:15<7:04:57,  1.38s/it]
 70%|███████   | 43392/61904 [19:17<7:12:37,  1.40s/it]
 70%|███████   | 43393/61904 [19:18<7:12:25,  1.40s/it]
 70%|███████   | 43394/61904 [19:20<6:55:00,  1.35s/it]
 70%|███████   | 43395/61904 [19:21<6:41:56,  1.30s/it]
 70%|███████   | 43396/61904 [19:22<6:50:58,  1.33s/it]
 70%|███████   | 43397/61904 [19:24<7:03:53,  1.37s/it]
 70%|███████   | 43398/61904 [19:25<7:09:21,  1.39s/it]
 70%|███████   | 43399/61904 [19:27<7:27:59,  1.45s/it]
 70%|███████   | 43400/61904 [19:28<7:49:10,  1.52s/it]
                                                       
{'loss': 2.4749, 'learning_rate': 1.2998833138856477e-07, 'epoch': 11.22}

 70%|███████   | 43400/61904 [19:28<7:49:10,  1.52s/it]
 70%|███████   | 43401/61904 [19:30<7:25:39,  1.45s/it]
 70%|███████   | 43402/61904 [19:31<7:14:03,  1.41s/it]
 70%|███████   | 43403/61904 [19:32<7:06:11,  1.38s/it]
 70%|███████   | 43404/61904 [19:34<7:07:03,  1.39s/it]
 70%|███████   | 43405/61904 [19:35<7:03:39,  1.37s/it]
 70%|███████   | 43406/61904 [19:36<6:53:30,  1.34s/it]
 70%|███████   | 43407/61904 [19:38<7:04:32,  1.38s/it]
 70%|███████   | 43408/61904 [19:39<7:06:34,  1.38s/it]
 70%|███████   | 43409/61904 [19:40<7:06:48,  1.38s/it]
 70%|███████   | 43410/61904 [19:42<7:03:49,  1.38s/it]
 70%|███████   | 43411/61904 [19:43<6:54:35,  1.35s/it]
 70%|███████   | 43412/61904 [19:44<6:55:40,  1.35s/it]
 70%|███████   | 43413/61904 [19:46<6:44:01,  1.31s/it]
 70%|███████   | 43414/61904 [19:47<6:43:07,  1.31s/it]
 70%|███████   | 43415/61904 [19:48<6:45:32,  1.32s/it]
 70%|███████   | 43416/61904 [19:50<6:58:47,  1.36s/it]
 70%|███████   | 43417/61904 [19:51<6:58:03,  1.36s/it]
 70%|███████   | 43418/61904 [19:53<7:16:47,  1.42s/it]
 70%|███████   | 43419/61904 [19:54<7:04:29,  1.38s/it]
 70%|███████   | 43420/61904 [19:55<7:10:28,  1.40s/it]
                                                       
{'loss': 2.5268, 'learning_rate': 1.2995591857902243e-07, 'epoch': 11.22}

 70%|███████   | 43420/61904 [19:55<7:10:28,  1.40s/it]
 70%|███████   | 43421/61904 [19:57<7:15:55,  1.42s/it]
 70%|███████   | 43422/61904 [19:58<7:11:15,  1.40s/it]
 70%|███████   | 43423/61904 [20:00<7:11:40,  1.40s/it]
 70%|███████   | 43424/61904 [20:01<7:14:33,  1.41s/it]
 70%|███████   | 43425/61904 [20:03<7:19:32,  1.43s/it]
 70%|███████   | 43426/61904 [20:04<7:10:48,  1.40s/it]
 70%|███████   | 43427/61904 [20:05<6:54:59,  1.35s/it]
 70%|███████   | 43428/61904 [20:07<7:24:42,  1.44s/it]
 70%|███████   | 43429/61904 [20:08<7:23:09,  1.44s/it]
 70%|███████   | 43430/61904 [20:09<7:08:40,  1.39s/it]
 70%|███████   | 43431/61904 [20:11<7:11:45,  1.40s/it]
 70%|███████   | 43432/61904 [20:12<7:28:48,  1.46s/it]
 70%|███████   | 43433/61904 [20:14<7:21:05,  1.43s/it]
 70%|███████   | 43434/61904 [20:15<7:17:22,  1.42s/it]
 70%|███████   | 43435/61904 [20:17<7:12:54,  1.41s/it]
 70%|███████   | 43436/61904 [20:18<7:16:22,  1.42s/it]
 70%|███████   | 43437/61904 [20:19<7:06:38,  1.39s/it]
 70%|███████   | 43438/61904 [20:21<7:04:01,  1.38s/it]
 70%|███████   | 43439/61904 [20:22<6:49:54,  1.33s/it]
 70%|███████   | 43440/61904 [20:23<6:53:04,  1.34s/it]
                                                       
{'loss': 2.4837, 'learning_rate': 1.299235057694801e-07, 'epoch': 11.23}

 70%|███████   | 43440/61904 [20:23<6:53:04,  1.34s/it]
 70%|███████   | 43441/61904 [20:25<6:43:53,  1.31s/it]
 70%|███████   | 43442/61904 [20:26<6:48:31,  1.33s/it]
 70%|███████   | 43443/61904 [20:27<6:54:52,  1.35s/it]
 70%|███████   | 43444/61904 [20:29<6:59:44,  1.36s/it]
 70%|███████   | 43445/61904 [20:30<6:55:55,  1.35s/it]
 70%|███████   | 43446/61904 [20:31<6:54:01,  1.35s/it]
 70%|███████   | 43447/61904 [20:33<7:00:04,  1.37s/it]
 70%|███████   | 43448/61904 [20:34<6:52:40,  1.34s/it]
 70%|███████   | 43449/61904 [20:36<7:04:04,  1.38s/it]
 70%|███████   | 43450/61904 [20:37<7:08:49,  1.39s/it]
 70%|███████   | 43451/61904 [20:38<7:10:00,  1.40s/it]
 70%|███████   | 43452/61904 [20:40<7:06:33,  1.39s/it]
 70%|███████   | 43453/61904 [20:41<7:04:07,  1.38s/it]
 70%|███████   | 43454/61904 [20:43<7:09:52,  1.40s/it]
 70%|███████   | 43455/61904 [20:44<7:08:58,  1.40s/it]
 70%|███████   | 43456/61904 [20:45<7:00:41,  1.37s/it]
 70%|███████   | 43457/61904 [20:47<7:02:05,  1.37s/it]
 70%|███████   | 43458/61904 [20:48<7:03:06,  1.38s/it]
 70%|███████   | 43459/61904 [20:49<6:59:48,  1.37s/it]
 70%|███████   | 43460/61904 [20:51<6:49:29,  1.33s/it]
                                                       
{'loss': 2.4285, 'learning_rate': 1.2989109295993778e-07, 'epoch': 11.23}

 70%|███████   | 43460/61904 [20:51<6:49:29,  1.33s/it]
 70%|███████   | 43461/61904 [20:52<6:45:40,  1.32s/it]
 70%|███████   | 43462/61904 [20:53<6:49:34,  1.33s/it]
 70%|███████   | 43463/61904 [20:55<6:57:07,  1.36s/it]
 70%|███████   | 43464/61904 [20:56<6:46:21,  1.32s/it]
 70%|███████   | 43465/61904 [20:57<7:01:35,  1.37s/it]
 70%|███████   | 43466/61904 [20:59<6:51:34,  1.34s/it]
 70%|███████   | 43467/61904 [21:00<6:52:41,  1.34s/it]
 70%|███████   | 43468/61904 [21:01<6:58:13,  1.36s/it]
 70%|███████   | 43469/61904 [21:03<7:04:06,  1.38s/it]
 70%|███████   | 43470/61904 [21:04<7:12:43,  1.41s/it]
 70%|███████   | 43471/61904 [21:06<7:16:28,  1.42s/it]
 70%|███████   | 43472/61904 [21:07<7:08:21,  1.39s/it]
 70%|███████   | 43473/61904 [21:08<7:03:05,  1.38s/it]
 70%|███████   | 43474/61904 [21:10<7:03:13,  1.38s/it]
 70%|███████   | 43475/61904 [21:11<7:06:33,  1.39s/it]
 70%|███████   | 43476/61904 [21:13<7:03:30,  1.38s/it]
 70%|███████   | 43477/61904 [21:14<7:04:49,  1.38s/it]
 70%|███████   | 43478/61904 [21:15<7:10:02,  1.40s/it]
 70%|███████   | 43479/61904 [21:17<7:03:27,  1.38s/it]
 70%|███████   | 43480/61904 [21:18<7:00:31,  1.37s/it]
                                                       
{'loss': 2.4918, 'learning_rate': 1.2985868015039541e-07, 'epoch': 11.24}

 70%|███████   | 43480/61904 [21:18<7:00:31,  1.37s/it]
 70%|███████   | 43481/61904 [21:19<6:51:12,  1.34s/it]
 70%|███████   | 43482/61904 [21:21<6:47:29,  1.33s/it]
 70%|███████   | 43483/61904 [21:22<6:47:30,  1.33s/it]
 70%|███████   | 43484/61904 [21:23<6:58:58,  1.36s/it]
 70%|███████   | 43485/61904 [21:25<6:54:53,  1.35s/it]
 70%|███████   | 43486/61904 [21:26<6:56:22,  1.36s/it]
 70%|███████   | 43487/61904 [21:28<7:04:24,  1.38s/it]
 70%|███████   | 43488/61904 [21:29<6:45:29,  1.32s/it]
 70%|███████   | 43489/61904 [21:30<6:42:31,  1.31s/it]
 70%|███████   | 43490/61904 [21:32<6:56:33,  1.36s/it]
 70%|███████   | 43491/61904 [21:33<7:17:28,  1.43s/it]
 70%|███████   | 43492/61904 [21:34<7:10:51,  1.40s/it]
 70%|███████   | 43493/61904 [21:36<7:01:35,  1.37s/it]
 70%|███████   | 43494/61904 [21:37<6:57:07,  1.36s/it]
 70%|███████   | 43495/61904 [21:38<6:59:14,  1.37s/it]
 70%|███████   | 43496/61904 [21:40<6:54:44,  1.35s/it]
 70%|███████   | 43497/61904 [21:41<6:53:40,  1.35s/it]
 70%|███████   | 43498/61904 [21:42<6:45:18,  1.32s/it]
 70%|███████   | 43499/61904 [21:44<6:53:42,  1.35s/it]
 70%|███████   | 43500/61904 [21:45<6:56:08,  1.36s/it]
                                                       
{'loss': 2.4585, 'learning_rate': 1.298262673408531e-07, 'epoch': 11.24}

 70%|███████   | 43500/61904 [21:45<6:56:08,  1.36s/it]
 70%|███████   | 43501/61904 [21:47<7:15:28,  1.42s/it]
 70%|███████   | 43502/61904 [21:48<7:15:19,  1.42s/it]
 70%|███████   | 43503/61904 [21:49<7:05:57,  1.39s/it]
 70%|███████   | 43504/61904 [21:51<7:00:16,  1.37s/it]
 70%|███████   | 43505/61904 [21:52<6:56:33,  1.36s/it]
 70%|███████   | 43506/61904 [21:53<6:52:04,  1.34s/it]
 70%|███████   | 43507/61904 [21:55<6:48:27,  1.33s/it]
 70%|███████   | 43508/61904 [21:56<6:51:09,  1.34s/it]
 70%|███████   | 43509/61904 [21:58<6:55:01,  1.35s/it]
 70%|███████   | 43510/61904 [21:59<7:00:01,  1.37s/it]
 70%|███████   | 43511/61904 [22:00<7:19:33,  1.43s/it]
 70%|███████   | 43512/61904 [22:02<7:05:18,  1.39s/it]
 70%|███████   | 43513/61904 [22:03<7:03:48,  1.38s/it]
 70%|███████   | 43514/61904 [22:04<7:00:42,  1.37s/it]
 70%|███████   | 43515/61904 [22:06<7:14:59,  1.42s/it]
 70%|███████   | 43516/61904 [22:07<7:00:35,  1.37s/it]
 70%|███████   | 43517/61904 [22:09<7:09:21,  1.40s/it]
 70%|███████   | 43518/61904 [22:10<7:09:42,  1.40s/it]
 70%|███████   | 43519/61904 [22:12<7:24:01,  1.45s/it]
 70%|███████   | 43520/61904 [22:13<7:19:54,  1.44s/it]
                                                       
{'loss': 2.5156, 'learning_rate': 1.2979385453131076e-07, 'epoch': 11.25}

 70%|███████   | 43520/61904 [22:13<7:19:54,  1.44s/it]
 70%|███████   | 43521/61904 [22:15<7:19:28,  1.43s/it]
 70%|███████   | 43522/61904 [22:16<7:32:36,  1.48s/it]
 70%|███████   | 43523/61904 [22:18<7:23:48,  1.45s/it]
 70%|███████   | 43524/61904 [22:19<7:14:55,  1.42s/it]
 70%|███████   | 43525/61904 [22:20<7:11:22,  1.41s/it]
 70%|███████   | 43526/61904 [22:22<7:02:06,  1.38s/it]
 70%|███████   | 43527/61904 [22:23<6:59:07,  1.37s/it]
 70%|███████   | 43528/61904 [22:24<7:02:28,  1.38s/it]
 70%|███████   | 43529/61904 [22:26<7:12:28,  1.41s/it]
 70%|███████   | 43530/61904 [22:27<6:59:28,  1.37s/it]
 70%|███████   | 43531/61904 [22:28<6:50:10,  1.34s/it]
 70%|███████   | 43532/61904 [22:30<6:39:51,  1.31s/it]
 70%|███████   | 43533/61904 [22:31<6:51:19,  1.34s/it]
 70%|███████   | 43534/61904 [22:32<6:55:23,  1.36s/it]
 70%|███████   | 43535/61904 [22:34<6:54:41,  1.35s/it]
 70%|███████   | 43536/61904 [22:35<6:51:03,  1.34s/it]
 70%|███████   | 43537/61904 [22:36<6:45:34,  1.32s/it]
 70%|███████   | 43538/61904 [22:38<6:45:10,  1.32s/it]
 70%|███████   | 43539/61904 [22:39<6:51:49,  1.35s/it]
 70%|███████   | 43540/61904 [22:40<6:54:48,  1.36s/it]
                                                       
{'loss': 2.5031, 'learning_rate': 1.2976144172176843e-07, 'epoch': 11.25}

 70%|███████   | 43540/61904 [22:40<6:54:48,  1.36s/it]
 70%|███████   | 43541/61904 [22:42<7:01:03,  1.38s/it]
 70%|███████   | 43542/61904 [22:43<7:04:21,  1.39s/it]
 70%|███████   | 43543/61904 [22:45<7:01:50,  1.38s/it]
 70%|███████   | 43544/61904 [22:46<6:51:44,  1.35s/it]
 70%|███████   | 43545/61904 [22:47<6:46:04,  1.33s/it]
 70%|███████   | 43546/61904 [22:48<6:37:16,  1.30s/it]
 70%|███████   | 43547/61904 [22:50<6:40:59,  1.31s/it]
 70%|███████   | 43548/61904 [22:51<6:43:02,  1.32s/it]
 70%|███████   | 43549/61904 [22:53<6:58:34,  1.37s/it]
 70%|███████   | 43550/61904 [22:54<7:03:33,  1.38s/it]
 70%|███████   | 43551/61904 [22:55<7:15:15,  1.42s/it]
 70%|███████   | 43552/61904 [22:57<7:32:24,  1.48s/it]
 70%|███████   | 43553/61904 [22:58<7:13:51,  1.42s/it]
 70%|███████   | 43554/61904 [23:00<7:18:38,  1.43s/it]
 70%|███████   | 43555/61904 [23:01<7:19:48,  1.44s/it]
 70%|███████   | 43556/61904 [23:03<7:14:09,  1.42s/it]
 70%|███████   | 43557/61904 [23:04<6:59:53,  1.37s/it]
 70%|███████   | 43558/61904 [23:05<7:05:23,  1.39s/it]
 70%|███████   | 43559/61904 [23:07<6:56:14,  1.36s/it]
 70%|███████   | 43560/61904 [23:08<6:56:42,  1.36s/it]
                                                       
{'loss': 2.456, 'learning_rate': 1.2972902891222611e-07, 'epoch': 11.26}

 70%|███████   | 43560/61904 [23:08<6:56:42,  1.36s/it]
 70%|███████   | 43561/61904 [23:09<6:47:39,  1.33s/it]
 70%|███████   | 43562/61904 [23:11<6:51:17,  1.35s/it]
 70%|███████   | 43563/61904 [23:12<6:54:54,  1.36s/it]
 70%|███████   | 43564/61904 [23:13<7:00:34,  1.38s/it]
 70%|███████   | 43565/61904 [23:15<6:54:15,  1.36s/it]
 70%|███████   | 43566/61904 [23:16<7:09:38,  1.41s/it]
 70%|███████   | 43567/61904 [23:18<7:01:30,  1.38s/it]
 70%|███████   | 43568/61904 [23:19<6:52:44,  1.35s/it]
 70%|███████   | 43569/61904 [23:20<7:01:04,  1.38s/it]
 70%|███████   | 43570/61904 [23:22<6:54:06,  1.36s/it]
 70%|███████   | 43571/61904 [23:23<7:06:43,  1.40s/it]
 70%|███████   | 43572/61904 [23:24<6:51:38,  1.35s/it]
 70%|███████   | 43573/61904 [23:26<7:04:14,  1.39s/it]
 70%|███████   | 43574/61904 [23:27<7:06:37,  1.40s/it]
 70%|███████   | 43575/61904 [23:29<6:51:56,  1.35s/it]
 70%|███████   | 43576/61904 [23:30<6:56:06,  1.36s/it]
 70%|███████   | 43577/61904 [23:31<6:56:27,  1.36s/it]
 70%|███████   | 43578/61904 [23:33<6:50:20,  1.34s/it]
 70%|███████   | 43579/61904 [23:34<7:01:00,  1.38s/it]
 70%|███████   | 43580/61904 [23:35<6:55:21,  1.36s/it]
                                                       
{'loss': 2.5083, 'learning_rate': 1.2969661610268378e-07, 'epoch': 11.26}

 70%|███████   | 43580/61904 [23:35<6:55:21,  1.36s/it]
 70%|███████   | 43581/61904 [23:37<6:54:54,  1.36s/it]
 70%|███████   | 43582/61904 [23:38<6:52:09,  1.35s/it]
 70%|███████   | 43583/61904 [23:39<6:49:42,  1.34s/it]
 70%|███████   | 43584/61904 [23:41<6:55:44,  1.36s/it]
 70%|███████   | 43585/61904 [23:42<7:10:18,  1.41s/it]
 70%|███████   | 43586/61904 [23:44<7:19:00,  1.44s/it]
 70%|███████   | 43587/61904 [23:45<6:59:22,  1.37s/it]
 70%|███████   | 43588/61904 [23:46<7:05:10,  1.39s/it]
 70%|███████   | 43589/61904 [23:48<7:33:53,  1.49s/it]
 70%|███████   | 43590/61904 [23:49<7:17:32,  1.43s/it]
 70%|███████   | 43591/61904 [23:51<7:08:47,  1.40s/it]
 70%|███████   | 43592/61904 [23:52<7:06:58,  1.40s/it]
 70%|███████   | 43593/61904 [23:54<7:12:54,  1.42s/it]
 70%|███████   | 43594/61904 [23:55<7:22:33,  1.45s/it]
 70%|███████   | 43595/61904 [23:57<7:25:49,  1.46s/it]
 70%|███████   | 43596/61904 [23:58<7:07:26,  1.40s/it]
 70%|███████   | 43597/61904 [23:59<7:05:21,  1.39s/it]
 70%|███████   | 43598/61904 [24:01<7:10:37,  1.41s/it]
 70%|███████   | 43599/61904 [24:02<7:09:54,  1.41s/it]
 70%|███████   | 43600/61904 [24:03<6:59:44,  1.38s/it]
                                                       
{'loss': 2.5241, 'learning_rate': 1.2966420329314144e-07, 'epoch': 11.27}

 70%|███████   | 43600/61904 [24:03<6:59:44,  1.38s/it]
 70%|███████   | 43601/61904 [24:05<6:57:50,  1.37s/it]
 70%|███████   | 43602/61904 [24:06<7:06:29,  1.40s/it]
 70%|███████   | 43603/61904 [24:08<6:53:23,  1.36s/it]
 70%|███████   | 43604/61904 [24:09<6:56:10,  1.36s/it]
 70%|███████   | 43605/61904 [24:10<7:05:34,  1.40s/it]
 70%|███████   | 43606/61904 [24:12<7:11:05,  1.41s/it]
 70%|███████   | 43607/61904 [24:13<7:07:43,  1.40s/it]
 70%|███████   | 43608/61904 [24:15<7:04:55,  1.39s/it]
 70%|███████   | 43609/61904 [24:16<7:06:53,  1.40s/it]
 70%|███████   | 43610/61904 [24:17<7:02:26,  1.39s/it]
 70%|███████   | 43611/61904 [24:19<7:03:28,  1.39s/it]
 70%|███████   | 43612/61904 [24:20<6:52:37,  1.35s/it]
 70%|███████   | 43613/61904 [24:21<6:40:31,  1.31s/it]
 70%|███████   | 43614/61904 [24:23<6:43:51,  1.32s/it]
 70%|███████   | 43615/61904 [24:24<6:48:36,  1.34s/it]
 70%|███████   | 43616/61904 [24:25<6:54:33,  1.36s/it]
 70%|███████   | 43617/61904 [24:27<6:55:53,  1.36s/it]
 70%|███████   | 43618/61904 [24:28<6:48:38,  1.34s/it]
 70%|███████   | 43619/61904 [24:30<7:00:29,  1.38s/it]
 70%|███████   | 43620/61904 [24:31<7:21:34,  1.45s/it]
                                                       
{'loss': 2.4751, 'learning_rate': 1.2963179048359913e-07, 'epoch': 11.27}

 70%|███████   | 43620/61904 [24:31<7:21:34,  1.45s/it]
 70%|███████   | 43621/61904 [24:32<7:10:40,  1.41s/it]
 70%|███████   | 43622/61904 [24:34<7:17:47,  1.44s/it]
 70%|███████   | 43623/61904 [24:35<7:26:02,  1.46s/it]
 70%|███████   | 43624/61904 [24:37<7:26:31,  1.47s/it]
 70%|███████   | 43625/61904 [24:38<7:13:37,  1.42s/it]
 70%|███████   | 43626/61904 [24:40<7:28:56,  1.47s/it]
 70%|███████   | 43627/61904 [24:41<7:17:36,  1.44s/it]
 70%|███████   | 43628/61904 [24:43<7:06:06,  1.40s/it]
 70%|███████   | 43629/61904 [24:44<7:33:46,  1.49s/it]
 70%|███████   | 43630/61904 [24:46<7:24:09,  1.46s/it]
 70%|███████   | 43631/61904 [24:47<7:29:17,  1.48s/it]
 70%|███████   | 43632/61904 [24:48<7:11:12,  1.42s/it]
 70%|███████   | 43633/61904 [24:50<7:03:32,  1.39s/it]
 70%|███████   | 43634/61904 [24:51<7:08:59,  1.41s/it]
 70%|███████   | 43635/61904 [24:52<6:59:41,  1.38s/it]
 70%|███████   | 43636/61904 [24:54<6:54:38,  1.36s/it]
 70%|███████   | 43637/61904 [24:55<7:18:08,  1.44s/it]
 70%|███████   | 43638/61904 [24:57<7:08:37,  1.41s/it]
 70%|███████   | 43639/61904 [24:58<7:09:49,  1.41s/it]
 70%|███████   | 43640/61904 [25:00<7:08:21,  1.41s/it]
                                                       
{'loss': 2.4695, 'learning_rate': 1.295993776740568e-07, 'epoch': 11.28}

 70%|███████   | 43640/61904 [25:00<7:08:21,  1.41s/it]
 70%|███████   | 43641/61904 [25:01<7:20:32,  1.45s/it]
 70%|███████   | 43642/61904 [25:03<7:22:18,  1.45s/it]
 71%|███████   | 43643/61904 [25:04<7:28:25,  1.47s/it]
 71%|███████   | 43644/61904 [25:06<7:25:03,  1.46s/it]
 71%|███████   | 43645/61904 [25:07<7:09:58,  1.41s/it]
 71%|███████   | 43646/61904 [25:08<7:01:42,  1.39s/it]
 71%|███████   | 43647/61904 [25:09<6:50:31,  1.35s/it]
 71%|███████   | 43648/61904 [25:11<6:42:54,  1.32s/it]
 71%|███████   | 43649/61904 [25:12<6:53:32,  1.36s/it]
 71%|███████   | 43650/61904 [25:13<6:43:51,  1.33s/it]
 71%|███████   | 43651/61904 [25:15<6:46:37,  1.34s/it]
 71%|███████   | 43652/61904 [25:16<6:45:49,  1.33s/it]
 71%|███████   | 43653/61904 [25:17<6:44:09,  1.33s/it]
 71%|███████   | 43654/61904 [25:19<7:08:33,  1.41s/it]
 71%|███████   | 43655/61904 [25:20<7:03:09,  1.39s/it]
 71%|███████   | 43656/61904 [25:22<6:55:51,  1.37s/it]
 71%|███████   | 43657/61904 [25:23<7:04:01,  1.39s/it]
 71%|███████   | 43658/61904 [25:24<7:03:09,  1.39s/it]
 71%|███████   | 43659/61904 [25:26<7:08:09,  1.41s/it]
 71%|███████   | 43660/61904 [25:27<6:58:08,  1.38s/it]
                                                       
{'loss': 2.5578, 'learning_rate': 1.2956696486451445e-07, 'epoch': 11.28}

 71%|███████   | 43660/61904 [25:27<6:58:08,  1.38s/it]
 71%|███████   | 43661/61904 [25:29<7:11:22,  1.42s/it]
 71%|███████   | 43662/61904 [25:30<7:06:13,  1.40s/it]
 71%|███████   | 43663/61904 [25:31<7:02:58,  1.39s/it]
 71%|███████   | 43664/61904 [25:33<6:59:27,  1.38s/it]
 71%|███████   | 43665/61904 [25:34<6:49:44,  1.35s/it]
 71%|███████   | 43666/61904 [25:36<7:00:58,  1.38s/it]
 71%|███████   | 43667/61904 [25:37<7:01:12,  1.39s/it]
 71%|███████   | 43668/61904 [25:38<6:51:17,  1.35s/it]
 71%|███████   | 43669/61904 [25:40<6:45:40,  1.33s/it]
 71%|███████   | 43670/61904 [25:41<6:43:01,  1.33s/it]
 71%|███████   | 43671/61904 [25:42<6:41:54,  1.32s/it]
 71%|███████   | 43672/61904 [25:43<6:42:22,  1.32s/it]
 71%|███████   | 43673/61904 [25:45<6:36:57,  1.31s/it]
 71%|███████   | 43674/61904 [25:46<6:50:09,  1.35s/it]
 71%|███████   | 43675/61904 [25:47<6:39:53,  1.32s/it]
 71%|███████   | 43676/61904 [25:49<6:39:13,  1.31s/it]
 71%|███████   | 43677/61904 [25:50<6:29:53,  1.28s/it]
 71%|███████   | 43678/61904 [25:51<6:34:48,  1.30s/it]
 71%|███████   | 43679/61904 [25:53<6:41:46,  1.32s/it]
 71%|███████   | 43680/61904 [25:54<6:38:47,  1.31s/it]
                                                       
{'loss': 2.4649, 'learning_rate': 1.2953455205497214e-07, 'epoch': 11.29}

 71%|███████   | 43680/61904 [25:54<6:38:47,  1.31s/it]
 71%|███████   | 43681/61904 [25:55<6:43:26,  1.33s/it]
 71%|███████   | 43682/61904 [25:57<6:49:38,  1.35s/it]
 71%|███████   | 43683/61904 [25:58<6:50:00,  1.35s/it]
 71%|███████   | 43684/61904 [26:00<7:03:51,  1.40s/it]
 71%|███████   | 43685/61904 [26:01<7:03:58,  1.40s/it]
 71%|███████   | 43686/61904 [26:02<7:01:51,  1.39s/it]
 71%|███████   | 43687/61904 [26:04<7:13:22,  1.43s/it]
 71%|███████   | 43688/61904 [26:05<6:57:17,  1.37s/it]
 71%|███████   | 43689/61904 [26:07<7:00:31,  1.39s/it]
 71%|███████   | 43690/61904 [26:08<7:01:32,  1.39s/it]
 71%|███████   | 43691/61904 [26:09<7:01:18,  1.39s/it]
 71%|███████   | 43692/61904 [26:11<7:12:03,  1.42s/it]
 71%|███████   | 43693/61904 [26:12<7:02:31,  1.39s/it]
 71%|███████   | 43694/61904 [26:13<6:50:53,  1.35s/it]
 71%|███████   | 43695/61904 [26:15<6:45:37,  1.34s/it]
 71%|███████   | 43696/61904 [26:16<6:48:03,  1.34s/it]
 71%|███████   | 43697/61904 [26:17<6:42:11,  1.33s/it]
 71%|███████   | 43698/61904 [26:19<6:47:02,  1.34s/it]
 71%|███████   | 43699/61904 [26:20<6:50:04,  1.35s/it]
 71%|███████   | 43700/61904 [26:21<6:36:26,  1.31s/it]
                                                       
{'loss': 2.4747, 'learning_rate': 1.2950213924542977e-07, 'epoch': 11.29}

 71%|███████   | 43700/61904 [26:21<6:36:26,  1.31s/it]
 71%|███████   | 43701/61904 [26:23<6:41:13,  1.32s/it]
 71%|███████   | 43702/61904 [26:24<6:53:27,  1.36s/it]
 71%|███████   | 43703/61904 [26:25<6:48:27,  1.35s/it]
 71%|███████   | 43704/61904 [26:27<6:45:03,  1.34s/it]
 71%|███████   | 43705/61904 [26:29<7:24:29,  1.47s/it]
 71%|███████   | 43706/61904 [26:30<7:18:34,  1.45s/it]
 71%|███████   | 43707/61904 [26:31<7:24:36,  1.47s/it]
 71%|███████   | 43708/61904 [26:33<7:26:36,  1.47s/it]
 71%|███████   | 43709/61904 [26:34<7:10:23,  1.42s/it]
 71%|███████   | 43710/61904 [26:35<6:53:55,  1.37s/it]
 71%|███████   | 43711/61904 [26:37<7:03:14,  1.40s/it]
 71%|███████   | 43712/61904 [26:38<6:54:37,  1.37s/it]
 71%|███████   | 43713/61904 [26:40<6:54:33,  1.37s/it]
 71%|███████   | 43714/61904 [26:41<6:51:55,  1.36s/it]
 71%|███████   | 43715/61904 [26:42<6:55:43,  1.37s/it]
 71%|███████   | 43716/61904 [26:44<7:01:43,  1.39s/it]
 71%|███████   | 43717/61904 [26:45<6:55:03,  1.37s/it]
 71%|███████   | 43718/61904 [26:46<6:57:19,  1.38s/it]
 71%|███████   | 43719/61904 [26:48<7:01:49,  1.39s/it]
 71%|███████   | 43720/61904 [26:49<6:59:04,  1.38s/it]
                                                       
{'loss': 2.4679, 'learning_rate': 1.2946972643588746e-07, 'epoch': 11.3}

 71%|███████   | 43720/61904 [26:49<6:59:04,  1.38s/it]
 71%|███████   | 43721/61904 [26:51<7:01:50,  1.39s/it]
 71%|███████   | 43722/61904 [26:52<7:14:09,  1.43s/it]
 71%|███████   | 43723/61904 [26:54<7:12:05,  1.43s/it]
 71%|███████   | 43724/61904 [26:55<7:03:34,  1.40s/it]
 71%|███████   | 43725/61904 [26:56<7:06:16,  1.41s/it]
 71%|███████   | 43726/61904 [26:58<7:08:02,  1.41s/it]
 71%|███████   | 43727/61904 [26:59<7:12:11,  1.43s/it]
 71%|███████   | 43728/61904 [27:01<7:08:03,  1.41s/it]
 71%|███████   | 43729/61904 [27:02<7:00:36,  1.39s/it]
 71%|███████   | 43730/61904 [27:03<7:10:40,  1.42s/it]
 71%|███████   | 43731/61904 [27:05<6:57:33,  1.38s/it]
 71%|███████   | 43732/61904 [27:06<7:03:50,  1.40s/it]
 71%|███████   | 43733/61904 [27:08<7:21:28,  1.46s/it]
 71%|███████   | 43734/61904 [27:09<7:18:38,  1.45s/it]
 71%|███████   | 43735/61904 [27:11<7:19:13,  1.45s/it]
 71%|███████   | 43736/61904 [27:12<7:19:08,  1.45s/it]
 71%|███████   | 43737/61904 [27:14<7:13:35,  1.43s/it]
 71%|███████   | 43738/61904 [27:15<7:07:48,  1.41s/it]
 71%|███████   | 43739/61904 [27:16<7:14:05,  1.43s/it]
 71%|███████   | 43740/61904 [27:18<7:14:12,  1.43s/it]
                                                       
{'loss': 2.4683, 'learning_rate': 1.2943731362634512e-07, 'epoch': 11.31}

 71%|███████   | 43740/61904 [27:18<7:14:12,  1.43s/it]
 71%|███████   | 43741/61904 [27:19<7:10:54,  1.42s/it]
 71%|███████   | 43742/61904 [27:21<7:08:59,  1.42s/it]
 71%|███████   | 43743/61904 [27:22<6:54:22,  1.37s/it]
 71%|███████   | 43744/61904 [27:23<6:59:35,  1.39s/it]
 71%|███████   | 43745/61904 [27:25<7:01:20,  1.39s/it]
 71%|███████   | 43746/61904 [27:26<7:02:13,  1.40s/it]
 71%|███████   | 43747/61904 [27:27<6:58:06,  1.38s/it]
 71%|███████   | 43748/61904 [27:29<7:05:20,  1.41s/it]
 71%|███████   | 43749/61904 [27:30<6:59:31,  1.39s/it]
 71%|███████   | 43750/61904 [27:32<7:02:37,  1.40s/it]
 71%|███████   | 43751/61904 [27:33<6:53:39,  1.37s/it]
 71%|███████   | 43752/61904 [27:34<6:55:47,  1.37s/it]
 71%|███████   | 43753/61904 [27:36<6:51:04,  1.36s/it]
 71%|███████   | 43754/61904 [27:37<6:46:20,  1.34s/it]
 71%|███████   | 43755/61904 [27:38<6:41:02,  1.33s/it]
 71%|███████   | 43756/61904 [27:40<6:55:47,  1.37s/it]
 71%|███████   | 43757/61904 [27:41<7:06:07,  1.41s/it]
 71%|███████   | 43758/61904 [27:43<7:05:34,  1.41s/it]
 71%|███████   | 43759/61904 [27:44<7:06:53,  1.41s/it]
 71%|███████   | 43760/61904 [27:45<6:57:08,  1.38s/it]
                                                       
{'loss': 2.4857, 'learning_rate': 1.2940490081680279e-07, 'epoch': 11.31}

 71%|███████   | 43760/61904 [27:45<6:57:08,  1.38s/it]
 71%|███████   | 43761/61904 [27:47<6:54:31,  1.37s/it]
 71%|███████   | 43762/61904 [27:48<6:48:42,  1.35s/it]
 71%|███████   | 43763/61904 [27:49<6:36:46,  1.31s/it]
 71%|███████   | 43764/61904 [27:51<6:50:10,  1.36s/it]
 71%|███████   | 43765/61904 [27:52<6:45:15,  1.34s/it]
 71%|███████   | 43766/61904 [27:53<6:46:40,  1.35s/it]
 71%|███████   | 43767/61904 [27:55<6:54:42,  1.37s/it]
 71%|███████   | 43768/61904 [27:56<6:49:47,  1.36s/it]
 71%|███████   | 43769/61904 [27:58<6:52:57,  1.37s/it]
 71%|███████   | 43770/61904 [27:59<7:00:51,  1.39s/it]
 71%|███████   | 43771/61904 [28:00<6:59:15,  1.39s/it]
 71%|███████   | 43772/61904 [28:02<6:55:51,  1.38s/it]
 71%|███████   | 43773/61904 [28:03<7:04:47,  1.41s/it]
 71%|███████   | 43774/61904 [28:05<7:00:54,  1.39s/it]
 71%|███████   | 43775/61904 [28:06<6:55:51,  1.38s/it]
 71%|███████   | 43776/61904 [28:07<6:58:11,  1.38s/it]
 71%|███████   | 43777/61904 [28:09<6:51:25,  1.36s/it]
 71%|███████   | 43778/61904 [28:10<6:57:29,  1.38s/it]
 71%|███████   | 43779/61904 [28:11<6:58:40,  1.39s/it]
 71%|███████   | 43780/61904 [28:13<7:07:47,  1.42s/it]
                                                       
{'loss': 2.426, 'learning_rate': 1.2937248800726047e-07, 'epoch': 11.32}

 71%|███████   | 43780/61904 [28:13<7:07:47,  1.42s/it]
 71%|███████   | 43781/61904 [28:14<7:11:25,  1.43s/it]
 71%|███████   | 43782/61904 [28:16<7:03:31,  1.40s/it]
 71%|███████   | 43783/61904 [28:17<7:05:43,  1.41s/it]
 71%|███████   | 43784/61904 [28:19<7:18:55,  1.45s/it]
 71%|███████   | 43785/61904 [28:20<7:33:03,  1.50s/it]
 71%|███████   | 43786/61904 [28:22<7:27:10,  1.48s/it]
 71%|███████   | 43787/61904 [28:23<7:19:19,  1.45s/it]
 71%|███████   | 43788/61904 [28:25<7:17:56,  1.45s/it]
 71%|███████   | 43789/61904 [28:26<7:09:05,  1.42s/it]
 71%|███████   | 43790/61904 [28:27<7:02:46,  1.40s/it]
 71%|███████   | 43791/61904 [28:29<6:53:35,  1.37s/it]
 71%|███████   | 43792/61904 [28:30<7:10:45,  1.43s/it]
 71%|███████   | 43793/61904 [28:31<7:01:58,  1.40s/it]
 71%|███████   | 43794/61904 [28:33<7:03:20,  1.40s/it]
 71%|███████   | 43795/61904 [28:34<7:01:54,  1.40s/it]
 71%|███████   | 43796/61904 [28:36<7:06:10,  1.41s/it]
 71%|███████   | 43797/61904 [28:37<7:12:41,  1.43s/it]
 71%|███████   | 43798/61904 [28:39<7:13:08,  1.44s/it]
 71%|███████   | 43799/61904 [28:40<7:20:47,  1.46s/it]
 71%|███████   | 43800/61904 [28:42<7:15:28,  1.44s/it]
                                                       
{'loss': 2.4733, 'learning_rate': 1.2934007519771814e-07, 'epoch': 11.32}

 71%|███████   | 43800/61904 [28:42<7:15:28,  1.44s/it]
 71%|███████   | 43801/61904 [28:43<7:10:40,  1.43s/it]
 71%|███████   | 43802/61904 [28:44<6:53:03,  1.37s/it]
 71%|███████   | 43803/61904 [28:45<6:46:45,  1.35s/it]
 71%|███████   | 43804/61904 [28:47<6:48:16,  1.35s/it]
 71%|███████   | 43805/61904 [28:48<7:01:42,  1.40s/it]
 71%|███████   | 43806/61904 [28:50<7:01:20,  1.40s/it]
 71%|███████   | 43807/61904 [28:51<6:58:25,  1.39s/it]
 71%|███████   | 43808/61904 [28:52<6:52:01,  1.37s/it]
 71%|███████   | 43809/61904 [28:54<6:59:45,  1.39s/it]
 71%|███████   | 43810/61904 [28:55<6:50:23,  1.36s/it]
 71%|███████   | 43811/61904 [28:57<7:08:43,  1.42s/it]
 71%|███████   | 43812/61904 [28:58<7:00:51,  1.40s/it]
 71%|███████   | 43813/61904 [28:59<6:56:16,  1.38s/it]
 71%|███████   | 43814/61904 [29:01<6:47:25,  1.35s/it]
 71%|███████   | 43815/61904 [29:02<6:42:49,  1.34s/it]
 71%|███████   | 43816/61904 [29:03<6:47:40,  1.35s/it]
 71%|███████   | 43817/61904 [29:05<6:43:59,  1.34s/it]
 71%|███████   | 43818/61904 [29:06<6:46:50,  1.35s/it]
 71%|███████   | 43819/61904 [29:07<6:40:36,  1.33s/it]
 71%|███████   | 43820/61904 [29:09<6:47:39,  1.35s/it]
                                                       
{'loss': 2.4812, 'learning_rate': 1.293076623881758e-07, 'epoch': 11.33}

 71%|███████   | 43820/61904 [29:09<6:47:39,  1.35s/it]
 71%|███████   | 43821/61904 [29:10<6:45:38,  1.35s/it]
 71%|███████   | 43822/61904 [29:12<6:59:01,  1.39s/it]
 71%|███████   | 43823/61904 [29:13<6:57:44,  1.39s/it]
 71%|███████   | 43824/61904 [29:14<7:02:15,  1.40s/it]
 71%|███████   | 43825/61904 [29:16<7:13:02,  1.44s/it]
 71%|███████   | 43826/61904 [29:17<6:53:55,  1.37s/it]
 71%|███████   | 43827/61904 [29:19<6:58:38,  1.39s/it]
 71%|███████   | 43828/61904 [29:20<7:05:23,  1.41s/it]
 71%|███████   | 43829/61904 [29:21<7:03:59,  1.41s/it]
 71%|███████   | 43830/61904 [29:23<6:58:15,  1.39s/it]
 71%|███████   | 43831/61904 [29:24<6:57:48,  1.39s/it]
 71%|███████   | 43832/61904 [29:26<7:02:19,  1.40s/it]
 71%|███████   | 43833/61904 [29:27<7:00:52,  1.40s/it]
 71%|███████   | 43834/61904 [29:29<7:15:29,  1.45s/it]
 71%|███████   | 43835/61904 [29:30<7:19:47,  1.46s/it]
 71%|███████   | 43836/61904 [29:31<7:14:52,  1.44s/it]
 71%|███████   | 43837/61904 [29:33<7:12:21,  1.44s/it]
 71%|███████   | 43838/61904 [29:34<7:05:25,  1.41s/it]
 71%|███████   | 43839/61904 [29:36<7:00:57,  1.40s/it]
 71%|███████   | 43840/61904 [29:37<6:57:34,  1.39s/it]
                                                       
{'loss': 2.4528, 'learning_rate': 1.2927524957863349e-07, 'epoch': 11.33}

 71%|███████   | 43840/61904 [29:37<6:57:34,  1.39s/it]
 71%|███████   | 43841/61904 [29:38<6:48:20,  1.36s/it]
 71%|███████   | 43842/61904 [29:40<7:19:33,  1.46s/it]
 71%|███████   | 43843/61904 [29:41<7:30:13,  1.50s/it]
 71%|███████   | 43844/61904 [29:43<7:21:30,  1.47s/it]
 71%|███████   | 43845/61904 [29:44<7:08:59,  1.43s/it]
 71%|███████   | 43846/61904 [29:46<7:00:43,  1.40s/it]
 71%|███████   | 43847/61904 [29:47<7:11:15,  1.43s/it]
 71%|███████   | 43848/61904 [29:48<7:06:41,  1.42s/it]
 71%|███████   | 43849/61904 [29:50<7:05:58,  1.42s/it]
 71%|███████   | 43850/61904 [29:51<6:58:24,  1.39s/it]
 71%|███████   | 43851/61904 [29:52<6:41:21,  1.33s/it]
 71%|███████   | 43852/61904 [29:54<6:52:04,  1.37s/it]
 71%|███████   | 43853/61904 [29:55<6:49:37,  1.36s/it]
 71%|███████   | 43854/61904 [29:56<6:43:23,  1.34s/it]
 71%|███████   | 43855/61904 [29:58<6:54:58,  1.38s/it]
 71%|███████   | 43856/61904 [29:59<6:45:41,  1.35s/it]
 71%|███████   | 43857/61904 [30:01<7:03:45,  1.41s/it]
 71%|███████   | 43858/61904 [30:02<6:51:01,  1.37s/it]
 71%|███████   | 43859/61904 [30:04<7:09:20,  1.43s/it]
 71%|███████   | 43860/61904 [30:05<7:12:28,  1.44s/it]
                                                       
{'loss': 2.494, 'learning_rate': 1.2924283676909112e-07, 'epoch': 11.34}

 71%|███████   | 43860/61904 [30:05<7:12:28,  1.44s/it]
 71%|███████   | 43861/61904 [30:06<7:10:20,  1.43s/it]
 71%|███████   | 43862/61904 [30:08<7:06:52,  1.42s/it]
 71%|███████   | 43863/61904 [30:09<6:57:16,  1.39s/it]
 71%|███████   | 43864/61904 [30:11<6:56:33,  1.39s/it]
 71%|███████   | 43865/61904 [30:12<7:00:15,  1.40s/it]
 71%|███████   | 43866/61904 [30:13<6:55:35,  1.38s/it]
 71%|███████   | 43867/61904 [30:15<7:03:53,  1.41s/it]
 71%|███████   | 43868/61904 [30:16<7:08:00,  1.42s/it]
 71%|███████   | 43869/61904 [30:18<6:56:19,  1.39s/it]
 71%|███████   | 43870/61904 [30:19<7:03:11,  1.41s/it]
 71%|███████   | 43871/61904 [30:20<6:59:00,  1.39s/it]
 71%|███████   | 43872/61904 [30:22<7:12:24,  1.44s/it]
 71%|███████   | 43873/61904 [30:23<7:00:31,  1.40s/it]
 71%|███████   | 43874/61904 [30:25<6:59:43,  1.40s/it]
 71%|███████   | 43875/61904 [30:26<6:59:24,  1.40s/it]
 71%|███████   | 43876/61904 [30:27<6:54:18,  1.38s/it]
 71%|███████   | 43877/61904 [30:29<6:53:47,  1.38s/it]
 71%|███████   | 43878/61904 [30:30<7:02:43,  1.41s/it]
 71%|███████   | 43879/61904 [30:32<6:59:47,  1.40s/it]
 71%|███████   | 43880/61904 [30:33<6:58:39,  1.39s/it]
                                                       
{'loss': 2.4795, 'learning_rate': 1.292104239595488e-07, 'epoch': 11.34}

 71%|███████   | 43880/61904 [30:33<6:58:39,  1.39s/it]
 71%|███████   | 43881/61904 [30:34<7:00:31,  1.40s/it]
 71%|███████   | 43882/61904 [30:36<7:01:04,  1.40s/it]
 71%|███████   | 43883/61904 [30:37<6:58:28,  1.39s/it]
 71%|███████   | 43884/61904 [30:39<6:59:08,  1.40s/it]
 71%|███████   | 43885/61904 [30:40<6:55:53,  1.38s/it]
 71%|███████   | 43886/61904 [30:41<6:50:34,  1.37s/it]
 71%|███████   | 43887/61904 [30:43<6:56:27,  1.39s/it]
 71%|███████   | 43888/61904 [30:44<7:02:05,  1.41s/it]
 71%|███████   | 43889/61904 [30:46<6:59:35,  1.40s/it]
 71%|███████   | 43890/61904 [30:47<7:11:07,  1.44s/it]
 71%|███████   | 43891/61904 [30:49<7:14:31,  1.45s/it]
 71%|███████   | 43892/61904 [30:50<7:12:49,  1.44s/it]
 71%|███████   | 43893/61904 [30:51<6:56:52,  1.39s/it]
 71%|███████   | 43894/61904 [30:52<6:45:19,  1.35s/it]
 71%|███████   | 43895/61904 [30:54<6:55:29,  1.38s/it]
 71%|███████   | 43896/61904 [30:55<6:57:00,  1.39s/it]
 71%|███████   | 43897/61904 [30:57<7:00:21,  1.40s/it]
 71%|███████   | 43898/61904 [30:58<7:10:14,  1.43s/it]
 71%|███████   | 43899/61904 [31:00<7:02:00,  1.41s/it]
 71%|███████   | 43900/61904 [31:01<6:57:21,  1.39s/it]
                                                       
{'loss': 2.4816, 'learning_rate': 1.2917801115000647e-07, 'epoch': 11.35}

 71%|███████   | 43900/61904 [31:01<6:57:21,  1.39s/it]
 71%|███████   | 43901/61904 [31:02<6:56:50,  1.39s/it]
 71%|███████   | 43902/61904 [31:04<6:47:38,  1.36s/it]
 71%|███████   | 43903/61904 [31:05<6:48:28,  1.36s/it]
 71%|███████   | 43904/61904 [31:06<6:38:07,  1.33s/it]
 71%|███████   | 43905/61904 [31:08<6:32:12,  1.31s/it]
 71%|███████   | 43906/61904 [31:09<6:35:47,  1.32s/it]
 71%|███████   | 43907/61904 [31:10<6:38:41,  1.33s/it]
 71%|███████   | 43908/61904 [31:12<6:44:32,  1.35s/it]
 71%|███████   | 43909/61904 [31:13<6:45:06,  1.35s/it]
 71%|███████   | 43910/61904 [31:14<6:58:59,  1.40s/it]
 71%|███████   | 43911/61904 [31:16<6:51:23,  1.37s/it]
 71%|███████   | 43912/61904 [31:17<6:49:01,  1.36s/it]
 71%|███████   | 43913/61904 [31:18<6:38:29,  1.33s/it]
 71%|███████   | 43914/61904 [31:20<6:40:45,  1.34s/it]
 71%|███████   | 43915/61904 [31:21<6:54:06,  1.38s/it]
 71%|███████   | 43916/61904 [31:23<7:02:49,  1.41s/it]
 71%|███████   | 43917/61904 [31:24<6:57:09,  1.39s/it]
 71%|███████   | 43918/61904 [31:26<7:08:16,  1.43s/it]
 71%|███████   | 43919/61904 [31:27<7:02:12,  1.41s/it]
 71%|███████   | 43920/61904 [31:28<7:02:10,  1.41s/it]
                                                       
{'loss': 2.5282, 'learning_rate': 1.2914559834046413e-07, 'epoch': 11.35}

 71%|███████   | 43920/61904 [31:28<7:02:10,  1.41s/it]
 71%|███████   | 43921/61904 [31:30<6:55:53,  1.39s/it]
 71%|███████   | 43922/61904 [31:31<6:59:37,  1.40s/it]
 71%|███████   | 43923/61904 [31:32<6:53:05,  1.38s/it]
 71%|███████   | 43924/61904 [31:34<6:48:18,  1.36s/it]
 71%|███████   | 43925/61904 [31:35<6:53:38,  1.38s/it]
 71%|███████   | 43926/61904 [31:37<6:54:11,  1.38s/it]
 71%|███████   | 43927/61904 [31:38<6:50:25,  1.37s/it]
 71%|███████   | 43928/61904 [31:39<6:50:01,  1.37s/it]
 71%|███████   | 43929/61904 [31:41<6:48:13,  1.36s/it]
 71%|███████   | 43930/61904 [31:42<6:57:28,  1.39s/it]
 71%|███████   | 43931/61904 [31:43<6:55:56,  1.39s/it]
 71%|███████   | 43932/61904 [31:45<6:56:31,  1.39s/it]
 71%|███████   | 43933/61904 [31:46<6:52:12,  1.38s/it]
 71%|███████   | 43934/61904 [31:48<6:56:04,  1.39s/it]
 71%|███████   | 43935/61904 [31:49<6:59:22,  1.40s/it]
 71%|███████   | 43936/61904 [31:50<6:56:58,  1.39s/it]
 71%|███████   | 43937/61904 [31:52<6:53:02,  1.38s/it]
 71%|███████   | 43938/61904 [31:53<6:39:24,  1.33s/it]
 71%|███████   | 43939/61904 [31:54<6:47:18,  1.36s/it]
 71%|███████   | 43940/61904 [31:56<6:59:02,  1.40s/it]
                                                       
{'loss': 2.4849, 'learning_rate': 1.2911318553092182e-07, 'epoch': 11.36}

 71%|███████   | 43940/61904 [31:56<6:59:02,  1.40s/it]
 71%|███████   | 43941/61904 [31:57<6:47:35,  1.36s/it]
 71%|███████   | 43942/61904 [31:59<6:59:54,  1.40s/it]
 71%|███████   | 43943/61904 [32:00<6:47:43,  1.36s/it]
 71%|███████   | 43944/61904 [32:01<6:45:28,  1.35s/it]
 71%|███████   | 43945/61904 [32:03<6:37:10,  1.33s/it]
 71%|███████   | 43946/61904 [32:04<6:36:16,  1.32s/it]
 71%|███████   | 43947/61904 [32:05<6:49:21,  1.37s/it]
 71%|███████   | 43948/61904 [32:07<6:49:15,  1.37s/it]
 71%|███████   | 43949/61904 [32:08<6:42:50,  1.35s/it]
 71%|███████   | 43950/61904 [32:09<6:33:54,  1.32s/it]
 71%|███████   | 43951/61904 [32:11<6:47:12,  1.36s/it]
 71%|███████   | 43952/61904 [32:12<6:43:29,  1.35s/it]
 71%|███████   | 43953/61904 [32:13<6:45:28,  1.36s/it]
 71%|███████   | 43954/61904 [32:15<6:51:05,  1.37s/it]
 71%|███████   | 43955/61904 [32:16<6:40:21,  1.34s/it]
 71%|███████   | 43956/61904 [32:18<6:56:12,  1.39s/it]
 71%|███████   | 43957/61904 [32:19<6:57:55,  1.40s/it]
 71%|███████   | 43958/61904 [32:20<6:57:17,  1.40s/it]
 71%|███████   | 43959/61904 [32:22<6:58:01,  1.40s/it]
 71%|███████   | 43960/61904 [32:23<6:52:01,  1.38s/it]
                                                       
{'loss': 2.4246, 'learning_rate': 1.2908077272137948e-07, 'epoch': 11.36}

 71%|███████   | 43960/61904 [32:23<6:52:01,  1.38s/it]
 71%|███████   | 43961/61904 [32:24<6:47:49,  1.36s/it]
 71%|███████   | 43962/61904 [32:26<6:43:22,  1.35s/it]
 71%|███████   | 43963/61904 [32:27<6:47:32,  1.36s/it]
 71%|███████   | 43964/61904 [32:29<6:55:11,  1.39s/it]
 71%|███████   | 43965/61904 [32:30<6:53:19,  1.38s/it]
 71%|███████   | 43966/61904 [32:31<6:53:47,  1.38s/it]
 71%|███████   | 43967/61904 [32:33<6:52:25,  1.38s/it]
 71%|███████   | 43968/61904 [32:34<6:46:01,  1.36s/it]
 71%|███████   | 43969/61904 [32:35<6:48:34,  1.37s/it]
 71%|███████   | 43970/61904 [32:37<6:53:32,  1.38s/it]
 71%|███████   | 43971/61904 [32:38<6:54:37,  1.39s/it]
 71%|███████   | 43972/61904 [32:40<6:57:13,  1.40s/it]
 71%|███████   | 43973/61904 [32:41<7:06:03,  1.43s/it]
 71%|███████   | 43974/61904 [32:42<6:47:59,  1.37s/it]
 71%|███████   | 43975/61904 [32:44<6:52:38,  1.38s/it]
 71%|███████   | 43976/61904 [32:45<6:46:14,  1.36s/it]
 71%|███████   | 43977/61904 [32:46<6:35:44,  1.32s/it]
 71%|███████   | 43978/61904 [32:48<6:36:45,  1.33s/it]
 71%|███████   | 43979/61904 [32:49<6:33:45,  1.32s/it]
 71%|███████   | 43980/61904 [32:50<6:39:12,  1.34s/it]
                                                       
{'loss': 2.5491, 'learning_rate': 1.2904835991183715e-07, 'epoch': 11.37}

 71%|███████   | 43980/61904 [32:50<6:39:12,  1.34s/it]
 71%|███████   | 43981/61904 [32:52<6:46:52,  1.36s/it]
 71%|███████   | 43982/61904 [32:53<6:53:42,  1.39s/it]
 71%|███████   | 43983/61904 [32:55<6:56:59,  1.40s/it]
 71%|███████   | 43984/61904 [32:56<6:53:16,  1.38s/it]
 71%|███████   | 43985/61904 [32:57<6:53:15,  1.38s/it]
 71%|███████   | 43986/61904 [32:59<6:46:21,  1.36s/it]
 71%|███████   | 43987/61904 [33:00<6:47:15,  1.36s/it]
 71%|███████   | 43988/61904 [33:01<6:46:10,  1.36s/it]
 71%|███████   | 43989/61904 [33:03<6:45:37,  1.36s/it]
 71%|███████   | 43990/61904 [33:04<6:53:45,  1.39s/it]
 71%|███████   | 43991/61904 [33:05<6:38:52,  1.34s/it]
 71%|███████   | 43992/61904 [33:07<6:49:19,  1.37s/it]
 71%|███████   | 43993/61904 [33:08<6:43:40,  1.35s/it]
 71%|███████   | 43994/61904 [33:10<7:02:09,  1.41s/it]
 71%|███████   | 43995/61904 [33:11<6:48:05,  1.37s/it]
 71%|███████   | 43996/61904 [33:13<7:04:20,  1.42s/it]
 71%|███████   | 43997/61904 [33:14<7:03:41,  1.42s/it]
 71%|███████   | 43998/61904 [33:15<6:58:41,  1.40s/it]
 71%|███████   | 43999/61904 [33:17<6:48:57,  1.37s/it]
 71%|███████   | 44000/61904 [33:18<6:58:26,  1.40s/it]
                                                       
{'loss': 2.4584, 'learning_rate': 1.2901594710229483e-07, 'epoch': 11.37}

 71%|███████   | 44000/61904 [33:18<6:58:26,  1.40s/it]
 71%|███████   | 44001/61904 [33:20<7:01:36,  1.41s/it]
 71%|███████   | 44002/61904 [33:21<7:12:08,  1.45s/it]
 71%|███████   | 44003/61904 [33:22<7:05:07,  1.42s/it]
 71%|███████   | 44004/61904 [33:24<6:54:37,  1.39s/it]
 71%|███████   | 44005/61904 [33:25<6:49:56,  1.37s/it]
 71%|███████   | 44006/61904 [33:27<7:05:40,  1.43s/it]
 71%|███████   | 44007/61904 [33:28<6:57:35,  1.40s/it]
 71%|███████   | 44008/61904 [33:29<6:53:16,  1.39s/it]
 71%|███████   | 44009/61904 [33:31<6:39:06,  1.34s/it]
 71%|███████   | 44010/61904 [33:32<6:48:32,  1.37s/it]
 71%|███████   | 44011/61904 [33:33<6:41:29,  1.35s/it]
 71%|███████   | 44012/61904 [33:35<6:59:04,  1.41s/it]
 71%|███████   | 44013/61904 [33:36<7:00:09,  1.41s/it]
 71%|███████   | 44014/61904 [33:38<6:50:52,  1.38s/it]
 71%|███████   | 44015/61904 [33:39<6:40:00,  1.34s/it]
 71%|███████   | 44016/61904 [33:40<6:39:35,  1.34s/it]
 71%|███████   | 44017/61904 [33:42<6:52:32,  1.38s/it]
 71%|███████   | 44018/61904 [33:43<6:49:50,  1.37s/it]
 71%|███████   | 44019/61904 [33:44<6:48:25,  1.37s/it]
 71%|███████   | 44020/61904 [33:46<6:51:00,  1.38s/it]
                                                       
{'loss': 2.5351, 'learning_rate': 1.289835342927525e-07, 'epoch': 11.38}

 71%|███████   | 44020/61904 [33:46<6:51:00,  1.38s/it]
 71%|███████   | 44021/61904 [33:47<6:49:04,  1.37s/it]
 71%|███████   | 44022/61904 [33:48<6:43:28,  1.35s/it]
 71%|███████   | 44023/61904 [33:50<6:34:40,  1.32s/it]
 71%|███████   | 44024/61904 [33:51<6:33:52,  1.32s/it]
 71%|███████   | 44025/61904 [33:52<6:39:28,  1.34s/it]
 71%|███████   | 44026/61904 [33:54<6:51:16,  1.38s/it]
 71%|███████   | 44027/61904 [33:55<6:47:03,  1.37s/it]
 71%|███████   | 44028/61904 [33:57<6:42:22,  1.35s/it]
 71%|███████   | 44029/61904 [33:58<6:37:42,  1.33s/it]
 71%|███████   | 44030/61904 [33:59<6:35:18,  1.33s/it]
 71%|███████   | 44031/61904 [34:01<6:45:24,  1.36s/it]
 71%|███████   | 44032/61904 [34:02<6:39:23,  1.34s/it]
 71%|███████   | 44033/61904 [34:03<6:39:49,  1.34s/it]
 71%|███████   | 44034/61904 [34:05<6:48:38,  1.37s/it]
 71%|███████   | 44035/61904 [34:06<6:50:49,  1.38s/it]
 71%|███████   | 44036/61904 [34:07<6:42:46,  1.35s/it]
 71%|███████   | 44037/61904 [34:09<6:38:58,  1.34s/it]
 71%|███████   | 44038/61904 [34:10<6:31:40,  1.32s/it]
 71%|███████   | 44039/61904 [34:11<6:27:11,  1.30s/it]
 71%|███████   | 44040/61904 [34:13<6:54:53,  1.39s/it]
                                                       
{'loss': 2.5108, 'learning_rate': 1.2895112148321016e-07, 'epoch': 11.38}

 71%|███████   | 44040/61904 [34:13<6:54:53,  1.39s/it]
 71%|███████   | 44041/61904 [34:14<6:48:15,  1.37s/it]
 71%|███████   | 44042/61904 [34:15<6:48:26,  1.37s/it]
 71%|███████   | 44043/61904 [34:17<6:43:25,  1.36s/it]
 71%|███████   | 44044/61904 [34:18<6:51:53,  1.38s/it]
 71%|███████   | 44045/61904 [34:20<6:44:11,  1.36s/it]
 71%|███████   | 44046/61904 [34:21<6:40:37,  1.35s/it]
 71%|███████   | 44047/61904 [34:22<6:38:34,  1.34s/it]
 71%|███████   | 44048/61904 [34:24<6:38:25,  1.34s/it]
 71%|███████   | 44049/61904 [34:25<7:01:08,  1.42s/it]
 71%|███████   | 44050/61904 [34:26<6:53:09,  1.39s/it]
 71%|███████   | 44051/61904 [34:28<6:48:37,  1.37s/it]
 71%|███████   | 44052/61904 [34:29<6:48:48,  1.37s/it]
 71%|███████   | 44053/61904 [34:30<6:45:49,  1.36s/it]
 71%|███████   | 44054/61904 [34:32<6:49:34,  1.38s/it]
 71%|███████   | 44055/61904 [34:33<6:59:42,  1.41s/it]
 71%|███████   | 44056/61904 [34:35<6:53:44,  1.39s/it]
 71%|███████   | 44057/61904 [34:36<6:44:32,  1.36s/it]
 71%|███████   | 44058/61904 [34:37<6:47:52,  1.37s/it]
 71%|███████   | 44059/61904 [34:39<6:46:28,  1.37s/it]
 71%|███████   | 44060/61904 [34:40<6:43:08,  1.36s/it]
                                                       
{'loss': 2.5328, 'learning_rate': 1.2891870867366782e-07, 'epoch': 11.39}

 71%|███████   | 44060/61904 [34:40<6:43:08,  1.36s/it]
 71%|███████   | 44061/61904 [34:41<6:44:56,  1.36s/it]
 71%|███████   | 44062/61904 [34:43<6:47:06,  1.37s/it]
 71%|███████   | 44063/61904 [34:44<6:54:52,  1.40s/it]
 71%|███████   | 44064/61904 [34:46<6:48:10,  1.37s/it]
 71%|███████   | 44065/61904 [34:47<6:42:09,  1.35s/it]
 71%|███████   | 44066/61904 [34:48<6:43:06,  1.36s/it]
 71%|███████   | 44067/61904 [34:50<6:32:06,  1.32s/it]
 71%|███████   | 44068/61904 [34:51<6:33:38,  1.32s/it]
 71%|███████   | 44069/61904 [34:52<6:23:44,  1.29s/it]
 71%|███████   | 44070/61904 [34:54<6:37:24,  1.34s/it]
 71%|███████   | 44071/61904 [34:55<6:44:22,  1.36s/it]
 71%|███████   | 44072/61904 [34:56<6:48:38,  1.37s/it]
 71%|███████   | 44073/61904 [34:58<6:52:19,  1.39s/it]
 71%|███████   | 44074/61904 [34:59<6:48:04,  1.37s/it]
 71%|███████   | 44075/61904 [35:00<6:48:56,  1.38s/it]
 71%|███████   | 44076/61904 [35:02<6:43:38,  1.36s/it]
 71%|███████   | 44077/61904 [35:03<6:51:20,  1.38s/it]
 71%|███████   | 44078/61904 [35:05<6:40:52,  1.35s/it]
 71%|███████   | 44079/61904 [35:06<6:58:36,  1.41s/it]
 71%|███████   | 44080/61904 [35:07<6:50:20,  1.38s/it]
                                                       
{'loss': 2.4501, 'learning_rate': 1.2888629586412548e-07, 'epoch': 11.39}

 71%|███████   | 44080/61904 [35:07<6:50:20,  1.38s/it]
 71%|███████   | 44081/61904 [35:09<7:01:45,  1.42s/it]
 71%|███████   | 44082/61904 [35:10<6:57:05,  1.40s/it]
 71%|███████   | 44083/61904 [35:12<7:05:19,  1.43s/it]
 71%|███████   | 44084/61904 [35:13<7:14:19,  1.46s/it]
 71%|███████   | 44085/61904 [35:15<7:04:19,  1.43s/it]
 71%|███████   | 44086/61904 [35:16<6:58:37,  1.41s/it]
 71%|███████   | 44087/61904 [35:17<6:51:24,  1.39s/it]
 71%|███████   | 44088/61904 [35:19<6:50:17,  1.38s/it]
 71%|███████   | 44089/61904 [35:20<6:48:48,  1.38s/it]
 71%|███████   | 44090/61904 [35:21<6:33:48,  1.33s/it]
 71%|███████   | 44091/61904 [35:23<6:35:01,  1.33s/it]
 71%|███████   | 44092/61904 [35:24<6:40:03,  1.35s/it]
 71%|███████   | 44093/61904 [35:25<6:38:13,  1.34s/it]
 71%|███████   | 44094/61904 [35:27<6:56:56,  1.40s/it]
 71%|███████   | 44095/61904 [35:28<6:50:46,  1.38s/it]
 71%|███████   | 44096/61904 [35:29<6:39:33,  1.35s/it]
 71%|███████   | 44097/61904 [35:31<6:38:26,  1.34s/it]
 71%|███████   | 44098/61904 [35:32<6:30:36,  1.32s/it]
 71%|███████   | 44099/61904 [35:34<6:48:50,  1.38s/it]
 71%|███████   | 44100/61904 [35:35<6:52:33,  1.39s/it]
                                                       
{'loss': 2.434, 'learning_rate': 1.2885388305458317e-07, 'epoch': 11.4}

 71%|███████   | 44100/61904 [35:35<6:52:33,  1.39s/it]
 71%|███████   | 44101/61904 [35:36<6:40:20,  1.35s/it]
 71%|███████   | 44102/61904 [35:38<6:50:30,  1.38s/it]
 71%|███████   | 44103/61904 [35:39<6:52:43,  1.39s/it]
 71%|███████   | 44104/61904 [35:40<6:43:51,  1.36s/it]
 71%|███████   | 44105/61904 [35:42<6:37:32,  1.34s/it]
 71%|███████   | 44106/61904 [35:43<6:51:36,  1.39s/it]
 71%|███████▏  | 44107/61904 [35:45<6:56:27,  1.40s/it]
 71%|███████▏  | 44108/61904 [35:46<6:42:52,  1.36s/it]
 71%|███████▏  | 44109/61904 [35:47<6:43:52,  1.36s/it]
 71%|███████▏  | 44110/61904 [35:49<6:35:00,  1.33s/it]
 71%|███████▏  | 44111/61904 [35:50<6:30:25,  1.32s/it]
 71%|███████▏  | 44112/61904 [35:51<6:27:39,  1.31s/it]
 71%|███████▏  | 44113/61904 [35:52<6:26:04,  1.30s/it]
 71%|███████▏  | 44114/61904 [35:54<6:32:10,  1.32s/it]
 71%|███████▏  | 44115/61904 [35:55<6:24:25,  1.30s/it]
 71%|███████▏  | 44116/61904 [35:57<6:49:54,  1.38s/it]
 71%|███████▏  | 44117/61904 [35:58<6:34:20,  1.33s/it]
 71%|███████▏  | 44118/61904 [35:59<6:37:43,  1.34s/it]
 71%|███████▏  | 44119/61904 [36:00<6:34:18,  1.33s/it]
 71%|███████▏  | 44120/61904 [36:02<6:40:21,  1.35s/it]
                                                       
{'loss': 2.4713, 'learning_rate': 1.2882147024504083e-07, 'epoch': 11.4}

 71%|███████▏  | 44120/61904 [36:02<6:40:21,  1.35s/it]
 71%|███████▏  | 44121/61904 [36:03<6:44:07,  1.36s/it]
 71%|███████▏  | 44122/61904 [36:04<6:32:29,  1.32s/it]
 71%|███████▏  | 44123/61904 [36:06<6:32:35,  1.32s/it]
 71%|███████▏  | 44124/61904 [36:07<6:40:18,  1.35s/it]
 71%|███████▏  | 44125/61904 [36:09<6:43:40,  1.36s/it]
 71%|███████▏  | 44126/61904 [36:10<6:45:22,  1.37s/it]
 71%|███████▏  | 44127/61904 [36:11<6:35:21,  1.33s/it]
 71%|███████▏  | 44128/61904 [36:13<6:50:09,  1.38s/it]
 71%|███████▏  | 44129/61904 [36:14<6:58:15,  1.41s/it]
 71%|███████▏  | 44130/61904 [36:16<6:46:56,  1.37s/it]
 71%|███████▏  | 44131/61904 [36:17<6:47:50,  1.38s/it]
 71%|███████▏  | 44132/61904 [36:18<6:41:55,  1.36s/it]
 71%|███████▏  | 44133/61904 [36:20<6:46:21,  1.37s/it]
 71%|███████▏  | 44134/61904 [36:21<7:01:58,  1.42s/it]
 71%|███████▏  | 44135/61904 [36:23<7:01:57,  1.42s/it]
 71%|███████▏  | 44136/61904 [36:24<7:04:54,  1.43s/it]
 71%|███████▏  | 44137/61904 [36:25<6:50:04,  1.38s/it]
 71%|███████▏  | 44138/61904 [36:27<6:52:49,  1.39s/it]
 71%|███████▏  | 44139/61904 [36:28<7:02:52,  1.43s/it]
 71%|███████▏  | 44140/61904 [36:30<7:11:23,  1.46s/it]
                                                       
{'loss': 2.5093, 'learning_rate': 1.287890574354985e-07, 'epoch': 11.41}

 71%|███████▏  | 44140/61904 [36:30<7:11:23,  1.46s/it]
 71%|███████▏  | 44141/61904 [36:31<7:14:24,  1.47s/it]
 71%|███████▏  | 44142/61904 [36:33<7:01:48,  1.42s/it]
 71%|███████▏  | 44143/61904 [36:34<6:54:47,  1.40s/it]
 71%|███████▏  | 44144/61904 [36:35<7:02:48,  1.43s/it]
 71%|███████▏  | 44145/61904 [36:37<6:56:37,  1.41s/it]
 71%|███████▏  | 44146/61904 [36:38<6:50:21,  1.39s/it]
 71%|███████▏  | 44147/61904 [36:39<6:41:35,  1.36s/it]
 71%|███████▏  | 44148/61904 [36:41<6:43:54,  1.36s/it]
 71%|███████▏  | 44149/61904 [36:42<6:43:18,  1.36s/it]
 71%|███████▏  | 44150/61904 [36:44<6:46:22,  1.37s/it]
 71%|███████▏  | 44151/61904 [36:45<6:37:04,  1.34s/it]
 71%|███████▏  | 44152/61904 [36:46<6:31:14,  1.32s/it]
 71%|███████▏  | 44153/61904 [36:47<6:38:30,  1.35s/it]
 71%|███████▏  | 44154/61904 [36:49<6:29:38,  1.32s/it]
 71%|███████▏  | 44155/61904 [36:50<6:50:07,  1.39s/it]
 71%|███████▏  | 44156/61904 [36:52<6:53:47,  1.40s/it]
 71%|███████▏  | 44157/61904 [36:53<6:55:46,  1.41s/it]
 71%|███████▏  | 44158/61904 [36:54<6:50:27,  1.39s/it]
 71%|███████▏  | 44159/61904 [36:56<7:01:07,  1.42s/it]
 71%|███████▏  | 44160/61904 [36:57<6:55:13,  1.40s/it]
                                                       
{'loss': 2.5031, 'learning_rate': 1.2875664462595618e-07, 'epoch': 11.41}

 71%|███████▏  | 44160/61904 [36:57<6:55:13,  1.40s/it]
 71%|███████▏  | 44161/61904 [36:59<6:44:09,  1.37s/it]
 71%|███████▏  | 44162/61904 [37:00<6:36:10,  1.34s/it]
 71%|███████▏  | 44163/61904 [37:01<6:26:59,  1.31s/it]
 71%|███████▏  | 44164/61904 [37:03<6:41:31,  1.36s/it]
 71%|███████▏  | 44165/61904 [37:04<6:39:17,  1.35s/it]
 71%|███████▏  | 44166/61904 [37:05<6:33:29,  1.33s/it]
 71%|███████▏  | 44167/61904 [37:07<6:41:26,  1.36s/it]
 71%|███████▏  | 44168/61904 [37:08<6:46:51,  1.38s/it]
 71%|███████▏  | 44169/61904 [37:09<6:47:00,  1.38s/it]
 71%|███████▏  | 44170/61904 [37:11<6:45:27,  1.37s/it]
 71%|███████▏  | 44171/61904 [37:12<6:56:04,  1.41s/it]
 71%|███████▏  | 44172/61904 [37:14<6:42:14,  1.36s/it]
 71%|███████▏  | 44173/61904 [37:15<6:34:09,  1.33s/it]
 71%|███████▏  | 44174/61904 [37:16<6:32:01,  1.33s/it]
 71%|███████▏  | 44175/61904 [37:17<6:29:22,  1.32s/it]
 71%|███████▏  | 44176/61904 [37:19<6:43:48,  1.37s/it]
 71%|███████▏  | 44177/61904 [37:20<6:41:46,  1.36s/it]
 71%|███████▏  | 44178/61904 [37:22<6:50:09,  1.39s/it]
 71%|███████▏  | 44179/61904 [37:23<6:58:58,  1.42s/it]
 71%|███████▏  | 44180/61904 [37:25<6:48:48,  1.38s/it]
                                                       
{'loss': 2.4712, 'learning_rate': 1.2872423181641384e-07, 'epoch': 11.42}

 71%|███████▏  | 44180/61904 [37:25<6:48:48,  1.38s/it]
 71%|███████▏  | 44181/61904 [37:26<7:00:54,  1.42s/it]
 71%|███████▏  | 44182/61904 [37:27<6:47:38,  1.38s/it]
 71%|███████▏  | 44183/61904 [37:29<6:36:40,  1.34s/it]
 71%|███████▏  | 44184/61904 [37:30<6:47:50,  1.38s/it]
 71%|███████▏  | 44185/61904 [37:32<7:01:00,  1.43s/it]
 71%|███████▏  | 44186/61904 [37:33<7:29:44,  1.52s/it]
 71%|███████▏  | 44187/61904 [37:35<7:19:11,  1.49s/it]
 71%|███████▏  | 44188/61904 [37:36<7:02:50,  1.43s/it]
 71%|███████▏  | 44189/61904 [37:37<6:53:01,  1.40s/it]
 71%|███████▏  | 44190/61904 [37:39<6:51:20,  1.39s/it]
 71%|███████▏  | 44191/61904 [37:40<6:46:26,  1.38s/it]
 71%|███████▏  | 44192/61904 [37:42<6:55:38,  1.41s/it]
 71%|███████▏  | 44193/61904 [37:43<6:52:13,  1.40s/it]
 71%|███████▏  | 44194/61904 [37:44<6:51:08,  1.39s/it]
 71%|███████▏  | 44195/61904 [37:46<6:41:53,  1.36s/it]
 71%|███████▏  | 44196/61904 [37:47<7:06:23,  1.44s/it]
 71%|███████▏  | 44197/61904 [37:48<6:49:13,  1.39s/it]
 71%|███████▏  | 44198/61904 [37:50<6:47:03,  1.38s/it]
 71%|███████▏  | 44199/61904 [37:51<6:47:51,  1.38s/it]
 71%|███████▏  | 44200/61904 [37:53<6:43:55,  1.37s/it]
                                                       
{'loss': 2.4963, 'learning_rate': 1.286918190068715e-07, 'epoch': 11.42}

 71%|███████▏  | 44200/61904 [37:53<6:43:55,  1.37s/it]
 71%|███████▏  | 44201/61904 [37:54<6:45:15,  1.37s/it]
 71%|███████▏  | 44202/61904 [37:55<6:50:29,  1.39s/it]
 71%|███████▏  | 44203/61904 [37:57<6:47:12,  1.38s/it]
 71%|███████▏  | 44204/61904 [37:58<6:39:23,  1.35s/it]
 71%|███████▏  | 44205/61904 [38:00<7:05:18,  1.44s/it]
 71%|███████▏  | 44206/61904 [38:01<6:56:48,  1.41s/it]
 71%|███████▏  | 44207/61904 [38:02<6:51:28,  1.40s/it]
 71%|███████▏  | 44208/61904 [38:04<6:53:05,  1.40s/it]
 71%|███████▏  | 44209/61904 [38:05<7:14:11,  1.47s/it]
 71%|███████▏  | 44210/61904 [38:07<7:03:20,  1.44s/it]
 71%|███████▏  | 44211/61904 [38:08<6:52:17,  1.40s/it]
 71%|███████▏  | 44212/61904 [38:09<6:37:38,  1.35s/it]
 71%|███████▏  | 44213/61904 [38:11<6:42:21,  1.36s/it]
 71%|███████▏  | 44214/61904 [38:12<6:31:04,  1.33s/it]
 71%|███████▏  | 44215/61904 [38:13<6:23:17,  1.30s/it]
 71%|███████▏  | 44216/61904 [38:15<6:28:16,  1.32s/it]
 71%|███████▏  | 44217/61904 [38:16<6:43:46,  1.37s/it]
 71%|███████▏  | 44218/61904 [38:17<6:35:28,  1.34s/it]
 71%|███████▏  | 44219/61904 [38:19<6:53:53,  1.40s/it]
 71%|███████▏  | 44220/61904 [38:20<6:57:40,  1.42s/it]
                                                       
{'loss': 2.4866, 'learning_rate': 1.2865940619732917e-07, 'epoch': 11.43}

 71%|███████▏  | 44220/61904 [38:20<6:57:40,  1.42s/it]
 71%|███████▏  | 44221/61904 [38:22<6:52:50,  1.40s/it]
 71%|███████▏  | 44222/61904 [38:23<6:55:06,  1.41s/it]
 71%|███████▏  | 44223/61904 [38:25<6:57:29,  1.42s/it]
 71%|███████▏  | 44224/61904 [38:26<6:55:01,  1.41s/it]
 71%|███████▏  | 44225/61904 [38:27<6:50:33,  1.39s/it]
 71%|███████▏  | 44226/61904 [38:29<6:58:00,  1.42s/it]
 71%|███████▏  | 44227/61904 [38:30<6:49:38,  1.39s/it]
 71%|███████▏  | 44228/61904 [38:31<6:37:56,  1.35s/it]
 71%|███████▏  | 44229/61904 [38:33<6:43:46,  1.37s/it]
 71%|███████▏  | 44230/61904 [38:34<6:42:13,  1.37s/it]
 71%|███████▏  | 44231/61904 [38:35<6:35:08,  1.34s/it]
 71%|███████▏  | 44232/61904 [38:37<6:40:22,  1.36s/it]
 71%|███████▏  | 44233/61904 [38:38<6:54:57,  1.41s/it]
 71%|███████▏  | 44234/61904 [38:40<6:46:06,  1.38s/it]
 71%|███████▏  | 44235/61904 [38:41<6:40:28,  1.36s/it]
 71%|███████▏  | 44236/61904 [38:42<6:40:06,  1.36s/it]
 71%|███████▏  | 44237/61904 [38:44<6:48:05,  1.39s/it]
 71%|███████▏  | 44238/61904 [38:45<6:38:43,  1.35s/it]
 71%|███████▏  | 44239/61904 [38:46<6:25:42,  1.31s/it]
 71%|███████▏  | 44240/61904 [38:48<6:53:18,  1.40s/it]
                                                       
{'loss': 2.4665, 'learning_rate': 1.2862699338778686e-07, 'epoch': 11.43}

 71%|███████▏  | 44240/61904 [38:48<6:53:18,  1.40s/it]
 71%|███████▏  | 44241/61904 [38:49<6:39:45,  1.36s/it]
 71%|███████▏  | 44242/61904 [38:51<6:42:38,  1.37s/it]
 71%|███████▏  | 44243/61904 [38:52<6:51:31,  1.40s/it]
 71%|███████▏  | 44244/61904 [38:54<7:05:00,  1.44s/it]
 71%|███████▏  | 44245/61904 [38:55<7:18:31,  1.49s/it]
 71%|███████▏  | 44246/61904 [38:56<7:03:58,  1.44s/it]
 71%|███████▏  | 44247/61904 [38:58<7:01:27,  1.43s/it]
 71%|███████▏  | 44248/61904 [38:59<7:00:36,  1.43s/it]
 71%|███████▏  | 44249/61904 [39:01<6:52:41,  1.40s/it]
 71%|███████▏  | 44250/61904 [39:02<6:45:55,  1.38s/it]
 71%|███████▏  | 44251/61904 [39:03<6:55:52,  1.41s/it]
 71%|███████▏  | 44252/61904 [39:05<6:57:23,  1.42s/it]
 71%|███████▏  | 44253/61904 [39:06<6:50:38,  1.40s/it]
 71%|███████▏  | 44254/61904 [39:08<6:58:25,  1.42s/it]
 71%|███████▏  | 44255/61904 [39:09<6:48:46,  1.39s/it]
 71%|███████▏  | 44256/61904 [39:10<6:39:50,  1.36s/it]
 71%|███████▏  | 44257/61904 [39:12<6:32:10,  1.33s/it]
 71%|███████▏  | 44258/61904 [39:13<6:44:13,  1.37s/it]
 71%|███████▏  | 44259/61904 [39:15<6:51:53,  1.40s/it]
 71%|███████▏  | 44260/61904 [39:16<6:42:38,  1.37s/it]
                                                       
{'loss': 2.4525, 'learning_rate': 1.2859458057824452e-07, 'epoch': 11.44}

 71%|███████▏  | 44260/61904 [39:16<6:42:38,  1.37s/it]
 71%|███████▏  | 44261/61904 [39:17<6:38:31,  1.36s/it]
 72%|███████▏  | 44262/61904 [39:18<6:29:14,  1.32s/it]
 72%|███████▏  | 44263/61904 [39:20<6:38:10,  1.35s/it]
 72%|███████▏  | 44264/61904 [39:21<6:49:27,  1.39s/it]
 72%|███████▏  | 44265/61904 [39:23<6:41:17,  1.36s/it]
 72%|███████▏  | 44266/61904 [39:24<6:31:11,  1.33s/it]
 72%|███████▏  | 44267/61904 [39:25<6:30:50,  1.33s/it]
 72%|███████▏  | 44268/61904 [39:27<6:42:15,  1.37s/it]
 72%|███████▏  | 44269/61904 [39:28<6:47:21,  1.39s/it]
 72%|███████▏  | 44270/61904 [39:29<6:49:09,  1.39s/it]
 72%|███████▏  | 44271/61904 [39:31<6:45:25,  1.38s/it]
 72%|███████▏  | 44272/61904 [39:32<7:02:26,  1.44s/it]
 72%|███████▏  | 44273/61904 [39:34<6:45:40,  1.38s/it]
 72%|███████▏  | 44274/61904 [39:35<6:47:19,  1.39s/it]
 72%|███████▏  | 44275/61904 [39:36<6:41:10,  1.37s/it]
 72%|███████▏  | 44276/61904 [39:38<6:31:30,  1.33s/it]
 72%|███████▏  | 44277/61904 [39:39<6:45:18,  1.38s/it]
 72%|███████▏  | 44278/61904 [39:40<6:42:41,  1.37s/it]
 72%|███████▏  | 44279/61904 [39:42<6:44:01,  1.38s/it]
 72%|███████▏  | 44280/61904 [39:43<6:33:30,  1.34s/it]
                                                       
{'loss': 2.5271, 'learning_rate': 1.2856216776870218e-07, 'epoch': 11.44}

 72%|███████▏  | 44280/61904 [39:43<6:33:30,  1.34s/it]
 72%|███████▏  | 44281/61904 [39:44<6:36:48,  1.35s/it]
 72%|███████▏  | 44282/61904 [39:46<6:40:29,  1.36s/it]
 72%|███████▏  | 44283/61904 [39:47<6:23:06,  1.30s/it]
 72%|███████▏  | 44284/61904 [39:48<6:21:58,  1.30s/it]
 72%|███████▏  | 44285/61904 [39:50<6:26:41,  1.32s/it]
 72%|███████▏  | 44286/61904 [39:51<6:32:35,  1.34s/it]
 72%|███████▏  | 44287/61904 [39:52<6:30:41,  1.33s/it]
 72%|███████▏  | 44288/61904 [39:54<6:40:13,  1.36s/it]
 72%|███████▏  | 44289/61904 [39:55<6:33:29,  1.34s/it]
 72%|███████▏  | 44290/61904 [39:56<6:31:48,  1.33s/it]
 72%|███████▏  | 44291/61904 [39:58<6:31:10,  1.33s/it]
 72%|███████▏  | 44292/61904 [39:59<6:40:07,  1.36s/it]
 72%|███████▏  | 44293/61904 [40:00<6:35:38,  1.35s/it]
 72%|███████▏  | 44294/61904 [40:02<6:38:30,  1.36s/it]
 72%|███████▏  | 44295/61904 [40:03<6:47:13,  1.39s/it]
 72%|███████▏  | 44296/61904 [40:05<6:48:01,  1.39s/it]
 72%|███████▏  | 44297/61904 [40:06<6:34:14,  1.34s/it]
 72%|███████▏  | 44298/61904 [40:07<6:38:19,  1.36s/it]
 72%|███████▏  | 44299/61904 [40:09<6:48:11,  1.39s/it]
 72%|███████▏  | 44300/61904 [40:10<6:43:18,  1.37s/it]
                                                       
{'loss': 2.4676, 'learning_rate': 1.2852975495915984e-07, 'epoch': 11.45}

 72%|███████▏  | 44300/61904 [40:10<6:43:18,  1.37s/it]
 72%|███████▏  | 44301/61904 [40:12<6:46:30,  1.39s/it]
 72%|███████▏  | 44302/61904 [40:13<6:47:51,  1.39s/it]
 72%|███████▏  | 44303/61904 [40:15<7:01:44,  1.44s/it]
 72%|███████▏  | 44304/61904 [40:16<6:46:16,  1.39s/it]
 72%|███████▏  | 44305/61904 [40:17<6:43:54,  1.38s/it]
 72%|███████▏  | 44306/61904 [40:18<6:41:18,  1.37s/it]
 72%|███████▏  | 44307/61904 [40:20<6:51:53,  1.40s/it]
 72%|███████▏  | 44308/61904 [40:21<6:41:51,  1.37s/it]
 72%|███████▏  | 44309/61904 [40:23<6:42:05,  1.37s/it]
 72%|███████▏  | 44310/61904 [40:24<6:36:44,  1.35s/it]
 72%|███████▏  | 44311/61904 [40:25<6:39:29,  1.36s/it]
 72%|███████▏  | 44312/61904 [40:27<6:36:14,  1.35s/it]
 72%|███████▏  | 44313/61904 [40:28<6:40:08,  1.36s/it]
 72%|███████▏  | 44314/61904 [40:29<6:36:28,  1.35s/it]
 72%|███████▏  | 44315/61904 [40:31<6:24:11,  1.31s/it]
 72%|███████▏  | 44316/61904 [40:32<6:18:41,  1.29s/it]
 72%|███████▏  | 44317/61904 [40:33<6:40:48,  1.37s/it]
 72%|███████▏  | 44318/61904 [40:35<6:30:53,  1.33s/it]
 72%|███████▏  | 44319/61904 [40:36<6:29:56,  1.33s/it]
 72%|███████▏  | 44320/61904 [40:37<6:32:44,  1.34s/it]
                                                       
{'loss': 2.4996, 'learning_rate': 1.2849734214961753e-07, 'epoch': 11.46}

 72%|███████▏  | 44320/61904 [40:37<6:32:44,  1.34s/it]
 72%|███████▏  | 44321/61904 [40:39<6:35:33,  1.35s/it]
 72%|███████▏  | 44322/61904 [40:40<6:34:17,  1.35s/it]
 72%|███████▏  | 44323/61904 [40:41<6:31:16,  1.34s/it]
 72%|███████▏  | 44324/61904 [40:43<6:36:58,  1.35s/it]
 72%|███████▏  | 44325/61904 [40:44<6:26:10,  1.32s/it]
 72%|███████▏  | 44326/61904 [40:45<6:39:28,  1.36s/it]
 72%|███████▏  | 44327/61904 [40:47<6:40:56,  1.37s/it]
 72%|███████▏  | 44328/61904 [40:48<6:37:52,  1.36s/it]
 72%|███████▏  | 44329/61904 [40:50<6:43:38,  1.38s/it]
 72%|███████▏  | 44330/61904 [40:51<6:38:02,  1.36s/it]
 72%|███████▏  | 44331/61904 [40:52<6:38:25,  1.36s/it]
 72%|███████▏  | 44332/61904 [40:54<6:31:24,  1.34s/it]
 72%|███████▏  | 44333/61904 [40:55<6:43:34,  1.38s/it]
 72%|███████▏  | 44334/61904 [40:56<6:35:28,  1.35s/it]
 72%|███████▏  | 44335/61904 [40:58<6:35:46,  1.35s/it]
 72%|███████▏  | 44336/61904 [40:59<6:36:27,  1.35s/it]
 72%|███████▏  | 44337/61904 [41:00<6:29:57,  1.33s/it]
 72%|███████▏  | 44338/61904 [41:02<6:30:41,  1.33s/it]
 72%|███████▏  | 44339/61904 [41:03<6:35:42,  1.35s/it]
 72%|███████▏  | 44340/61904 [41:04<6:33:16,  1.34s/it]
                                                       
{'loss': 2.4901, 'learning_rate': 1.284649293400752e-07, 'epoch': 11.46}

 72%|███████▏  | 44340/61904 [41:04<6:33:16,  1.34s/it]
 72%|███████▏  | 44341/61904 [41:06<6:31:41,  1.34s/it]
 72%|███████▏  | 44342/61904 [41:07<6:31:52,  1.34s/it]
 72%|███████▏  | 44343/61904 [41:09<6:45:07,  1.38s/it]
 72%|███████▏  | 44344/61904 [41:10<6:59:51,  1.43s/it]
 72%|███████▏  | 44345/61904 [41:11<6:53:55,  1.41s/it]
 72%|███████▏  | 44346/61904 [41:13<7:02:50,  1.44s/it]
 72%|███████▏  | 44347/61904 [41:14<7:02:46,  1.44s/it]
 72%|███████▏  | 44348/61904 [41:16<7:01:07,  1.44s/it]
 72%|███████▏  | 44349/61904 [41:17<6:48:57,  1.40s/it]
 72%|███████▏  | 44350/61904 [41:18<6:45:50,  1.39s/it]
 72%|███████▏  | 44351/61904 [41:20<6:47:48,  1.39s/it]
 72%|███████▏  | 44352/61904 [41:21<6:42:53,  1.38s/it]
 72%|███████▏  | 44353/61904 [41:23<6:39:48,  1.37s/it]
 72%|███████▏  | 44354/61904 [41:24<6:34:47,  1.35s/it]
 72%|███████▏  | 44355/61904 [41:25<6:34:58,  1.35s/it]
 72%|███████▏  | 44356/61904 [41:27<7:00:37,  1.44s/it]
 72%|███████▏  | 44357/61904 [41:28<7:01:55,  1.44s/it]
 72%|███████▏  | 44358/61904 [41:30<6:52:45,  1.41s/it]
 72%|███████▏  | 44359/61904 [41:31<6:52:19,  1.41s/it]
 72%|███████▏  | 44360/61904 [41:32<6:40:01,  1.37s/it]
                                                       
{'loss': 2.411, 'learning_rate': 1.2843251653053285e-07, 'epoch': 11.47}

 72%|███████▏  | 44360/61904 [41:32<6:40:01,  1.37s/it]
 72%|███████▏  | 44361/61904 [41:34<6:42:17,  1.38s/it]
 72%|███████▏  | 44362/61904 [41:35<6:42:44,  1.38s/it]
 72%|███████▏  | 44363/61904 [41:37<6:52:09,  1.41s/it]
 72%|███████▏  | 44364/61904 [41:38<6:39:24,  1.37s/it]
 72%|███████▏  | 44365/61904 [41:39<6:39:03,  1.37s/it]
 72%|███████▏  | 44366/61904 [41:41<6:31:57,  1.34s/it]
 72%|███████▏  | 44367/61904 [41:42<6:38:03,  1.36s/it]
 72%|███████▏  | 44368/61904 [41:43<6:41:36,  1.37s/it]
 72%|███████▏  | 44369/61904 [41:45<6:38:41,  1.36s/it]
 72%|███████▏  | 44370/61904 [41:46<6:44:44,  1.39s/it]
 72%|███████▏  | 44371/61904 [41:47<6:31:08,  1.34s/it]
 72%|███████▏  | 44372/61904 [41:49<6:33:02,  1.35s/it]
 72%|███████▏  | 44373/61904 [41:50<6:43:05,  1.38s/it]
 72%|███████▏  | 44374/61904 [41:51<6:33:55,  1.35s/it]
 72%|███████▏  | 44375/61904 [41:53<6:30:07,  1.34s/it]
 72%|███████▏  | 44376/61904 [41:54<6:33:14,  1.35s/it]
 72%|███████▏  | 44377/61904 [41:56<6:45:10,  1.39s/it]
 72%|███████▏  | 44378/61904 [41:57<6:54:27,  1.42s/it]
 72%|███████▏  | 44379/61904 [41:58<6:49:36,  1.40s/it]
 72%|███████▏  | 44380/61904 [42:00<6:41:23,  1.37s/it]
                                                       
{'loss': 2.4688, 'learning_rate': 1.2840010372099054e-07, 'epoch': 11.47}

 72%|███████▏  | 44380/61904 [42:00<6:41:23,  1.37s/it]
 72%|███████▏  | 44381/61904 [42:01<6:42:14,  1.38s/it]
 72%|███████▏  | 44382/61904 [42:03<7:02:26,  1.45s/it]
 72%|███████▏  | 44383/61904 [42:04<7:02:35,  1.45s/it]
 72%|███████▏  | 44384/61904 [42:06<7:02:44,  1.45s/it]
 72%|███████▏  | 44385/61904 [42:07<6:54:12,  1.42s/it]
 72%|███████▏  | 44386/61904 [42:08<6:36:42,  1.36s/it]
 72%|███████▏  | 44387/61904 [42:10<6:53:14,  1.42s/it]
 72%|███████▏  | 44388/61904 [42:11<6:45:01,  1.39s/it]
 72%|███████▏  | 44389/61904 [42:12<6:37:19,  1.36s/it]
 72%|███████▏  | 44390/61904 [42:14<6:35:02,  1.35s/it]
 72%|███████▏  | 44391/61904 [42:15<6:47:26,  1.40s/it]
 72%|███████▏  | 44392/61904 [42:17<6:48:20,  1.40s/it]
 72%|███████▏  | 44393/61904 [42:18<6:38:01,  1.36s/it]
 72%|███████▏  | 44394/61904 [42:19<6:37:01,  1.36s/it]
 72%|███████▏  | 44395/61904 [42:21<6:35:43,  1.36s/it]
 72%|███████▏  | 44396/61904 [42:22<6:27:58,  1.33s/it]
 72%|███████▏  | 44397/61904 [42:23<6:37:46,  1.36s/it]
 72%|███████▏  | 44398/61904 [42:25<6:33:50,  1.35s/it]
 72%|███████▏  | 44399/61904 [42:26<6:50:07,  1.41s/it]
 72%|███████▏  | 44400/61904 [42:28<6:44:54,  1.39s/it]
                                                       
{'loss': 2.4458, 'learning_rate': 1.283676909114482e-07, 'epoch': 11.48}

 72%|███████▏  | 44400/61904 [42:28<6:44:54,  1.39s/it]
 72%|███████▏  | 44401/61904 [42:29<6:43:49,  1.38s/it]
 72%|███████▏  | 44402/61904 [42:30<6:33:30,  1.35s/it]
 72%|███████▏  | 44403/61904 [42:31<6:19:01,  1.30s/it]
 72%|███████▏  | 44404/61904 [42:33<6:16:14,  1.29s/it]
 72%|███████▏  | 44405/61904 [42:34<6:21:27,  1.31s/it]
 72%|███████▏  | 44406/61904 [42:35<6:30:42,  1.34s/it]
 72%|███████▏  | 44407/61904 [42:37<6:25:29,  1.32s/it]
 72%|███████▏  | 44408/61904 [42:38<6:26:31,  1.33s/it]
 72%|███████▏  | 44409/61904 [42:39<6:24:57,  1.32s/it]
 72%|███████▏  | 44410/61904 [42:41<6:35:59,  1.36s/it]
 72%|███████▏  | 44411/61904 [42:42<6:22:59,  1.31s/it]
 72%|███████▏  | 44412/61904 [42:43<6:33:54,  1.35s/it]
 72%|███████▏  | 44413/61904 [42:45<6:29:24,  1.34s/it]
 72%|███████▏  | 44414/61904 [42:46<6:22:18,  1.31s/it]
 72%|███████▏  | 44415/61904 [42:47<6:29:57,  1.34s/it]
 72%|███████▏  | 44416/61904 [42:49<6:30:29,  1.34s/it]
 72%|███████▏  | 44417/61904 [42:50<6:28:36,  1.33s/it]
 72%|███████▏  | 44418/61904 [42:51<6:34:23,  1.35s/it]
 72%|███████▏  | 44419/61904 [42:53<6:26:37,  1.33s/it]
 72%|███████▏  | 44420/61904 [42:54<6:28:26,  1.33s/it]
                                                       
{'loss': 2.4871, 'learning_rate': 1.2833527810190587e-07, 'epoch': 11.48}

 72%|███████▏  | 44420/61904 [42:54<6:28:26,  1.33s/it]
 72%|███████▏  | 44421/61904 [42:55<6:39:47,  1.37s/it]
 72%|███████▏  | 44422/61904 [42:57<6:23:58,  1.32s/it]
 72%|███████▏  | 44423/61904 [42:58<6:35:30,  1.36s/it]
 72%|███████▏  | 44424/61904 [43:00<6:41:01,  1.38s/it]
 72%|███████▏  | 44425/61904 [43:01<6:49:13,  1.40s/it]
 72%|███████▏  | 44426/61904 [43:02<6:44:46,  1.39s/it]
 72%|███████▏  | 44427/61904 [43:04<6:37:29,  1.36s/it]
 72%|███████▏  | 44428/61904 [43:05<6:45:08,  1.39s/it]
 72%|███████▏  | 44429/61904 [43:06<6:37:44,  1.37s/it]
 72%|███████▏  | 44430/61904 [43:08<6:35:42,  1.36s/it]
 72%|███████▏  | 44431/61904 [43:09<6:27:49,  1.33s/it]
 72%|███████▏  | 44432/61904 [43:10<6:26:53,  1.33s/it]
 72%|███████▏  | 44433/61904 [43:12<6:27:16,  1.33s/it]
 72%|███████▏  | 44434/61904 [43:13<6:50:50,  1.41s/it]
 72%|███████▏  | 44435/61904 [43:15<6:53:07,  1.42s/it]
 72%|███████▏  | 44436/61904 [43:16<7:03:36,  1.46s/it]
 72%|███████▏  | 44437/61904 [43:18<7:14:19,  1.49s/it]
 72%|███████▏  | 44438/61904 [43:19<7:06:02,  1.46s/it]
 72%|███████▏  | 44439/61904 [43:21<7:00:32,  1.44s/it]
 72%|███████▏  | 44440/61904 [43:22<6:49:54,  1.41s/it]
                                                       
{'loss': 2.4476, 'learning_rate': 1.2830286529236353e-07, 'epoch': 11.49}

 72%|███████▏  | 44440/61904 [43:22<6:49:54,  1.41s/it]
 72%|███████▏  | 44441/61904 [43:23<6:43:50,  1.39s/it]
 72%|███████▏  | 44442/61904 [43:25<6:43:06,  1.39s/it]
 72%|███████▏  | 44443/61904 [43:26<6:51:45,  1.41s/it]
 72%|███████▏  | 44444/61904 [43:28<6:44:38,  1.39s/it]
 72%|███████▏  | 44445/61904 [43:29<6:34:45,  1.36s/it]
 72%|███████▏  | 44446/61904 [43:30<6:29:33,  1.34s/it]
 72%|███████▏  | 44447/61904 [43:32<6:46:44,  1.40s/it]
 72%|███████▏  | 44448/61904 [43:33<6:52:54,  1.42s/it]
 72%|███████▏  | 44449/61904 [43:34<6:50:53,  1.41s/it]
 72%|███████▏  | 44450/61904 [43:36<7:01:47,  1.45s/it]
 72%|███████▏  | 44451/61904 [43:37<6:45:59,  1.40s/it]
 72%|███████▏  | 44452/61904 [43:39<6:48:45,  1.41s/it]
 72%|███████▏  | 44453/61904 [43:40<6:39:36,  1.37s/it]
 72%|███████▏  | 44454/61904 [43:42<7:03:16,  1.46s/it]
 72%|███████▏  | 44455/61904 [43:43<7:19:10,  1.51s/it]
 72%|███████▏  | 44456/61904 [43:45<6:58:30,  1.44s/it]
 72%|███████▏  | 44457/61904 [43:46<6:59:22,  1.44s/it]
 72%|███████▏  | 44458/61904 [43:47<6:54:47,  1.43s/it]
 72%|███████▏  | 44459/61904 [43:49<6:51:27,  1.42s/it]
 72%|███████▏  | 44460/61904 [43:50<6:41:55,  1.38s/it]
                                                       
{'loss': 2.4647, 'learning_rate': 1.282704524828212e-07, 'epoch': 11.49}

 72%|███████▏  | 44460/61904 [43:50<6:41:55,  1.38s/it]
 72%|███████▏  | 44461/61904 [43:52<6:48:48,  1.41s/it]
 72%|███████▏  | 44462/61904 [43:53<6:40:44,  1.38s/it]
 72%|███████▏  | 44463/61904 [43:54<6:52:04,  1.42s/it]
 72%|███████▏  | 44464/61904 [43:56<6:53:25,  1.42s/it]
 72%|███████▏  | 44465/61904 [43:57<6:48:17,  1.40s/it]
 72%|███████▏  | 44466/61904 [43:59<6:45:27,  1.40s/it]
 72%|███████▏  | 44467/61904 [44:00<6:47:04,  1.40s/it]
 72%|███████▏  | 44468/61904 [44:01<6:36:43,  1.37s/it]
 72%|███████▏  | 44469/61904 [44:03<6:30:30,  1.34s/it]
 72%|███████▏  | 44470/61904 [44:04<6:39:21,  1.37s/it]
 72%|███████▏  | 44471/61904 [44:05<6:30:27,  1.34s/it]
 72%|███████▏  | 44472/61904 [44:07<7:07:22,  1.47s/it]
 72%|███████▏  | 44473/61904 [44:08<7:01:36,  1.45s/it]
 72%|███████▏  | 44474/61904 [44:10<6:44:46,  1.39s/it]
 72%|███████▏  | 44475/61904 [44:11<6:50:30,  1.41s/it]
 72%|███████▏  | 44476/61904 [44:13<6:48:47,  1.41s/it]
 72%|███████▏  | 44477/61904 [44:14<6:40:47,  1.38s/it]
 72%|███████▏  | 44478/61904 [44:15<6:28:08,  1.34s/it]
 72%|███████▏  | 44479/61904 [44:16<6:22:36,  1.32s/it]
 72%|███████▏  | 44480/61904 [44:18<6:36:20,  1.36s/it]
                                                       
{'loss': 2.4887, 'learning_rate': 1.2823803967327888e-07, 'epoch': 11.5}

 72%|███████▏  | 44480/61904 [44:18<6:36:20,  1.36s/it]
 72%|███████▏  | 44481/61904 [44:19<6:30:36,  1.35s/it]
 72%|███████▏  | 44482/61904 [44:21<6:37:15,  1.37s/it]
 72%|███████▏  | 44483/61904 [44:22<6:36:10,  1.36s/it]
 72%|███████▏  | 44484/61904 [44:23<6:48:25,  1.41s/it]
 72%|███████▏  | 44485/61904 [44:25<6:55:22,  1.43s/it]
 72%|███████▏  | 44486/61904 [44:26<6:42:27,  1.39s/it]
 72%|███████▏  | 44487/61904 [44:28<6:40:25,  1.38s/it]
 72%|███████▏  | 44488/61904 [44:29<6:52:50,  1.42s/it]
 72%|███████▏  | 44489/61904 [44:30<6:40:46,  1.38s/it]
 72%|███████▏  | 44490/61904 [44:32<6:56:40,  1.44s/it]
 72%|███████▏  | 44491/61904 [44:33<7:00:15,  1.45s/it]
 72%|███████▏  | 44492/61904 [44:35<6:43:51,  1.39s/it]
 72%|███████▏  | 44493/61904 [44:36<6:39:59,  1.38s/it]
 72%|███████▏  | 44494/61904 [44:37<6:36:06,  1.37s/it]
 72%|███████▏  | 44495/61904 [44:39<6:29:06,  1.34s/it]
 72%|███████▏  | 44496/61904 [44:40<6:34:20,  1.36s/it]
 72%|███████▏  | 44497/61904 [44:41<6:37:29,  1.37s/it]
 72%|███████▏  | 44498/61904 [44:43<6:32:08,  1.35s/it]
 72%|███████▏  | 44499/61904 [44:44<6:30:31,  1.35s/it]
 72%|███████▏  | 44500/61904 [44:46<6:40:23,  1.38s/it]
                                                       
{'loss': 2.4835, 'learning_rate': 1.2820562686373654e-07, 'epoch': 11.5}

 72%|███████▏  | 44500/61904 [44:46<6:40:23,  1.38s/it]
 72%|███████▏  | 44501/61904 [44:47<6:51:44,  1.42s/it]
 72%|███████▏  | 44502/61904 [44:48<6:49:51,  1.41s/it]
 72%|███████▏  | 44503/61904 [44:50<6:41:11,  1.38s/it]
 72%|███████▏  | 44504/61904 [44:51<6:42:03,  1.39s/it]
 72%|███████▏  | 44505/61904 [44:52<6:36:32,  1.37s/it]
 72%|███████▏  | 44506/61904 [44:54<6:42:20,  1.39s/it]
 72%|███████▏  | 44507/61904 [44:55<6:41:07,  1.38s/it]
 72%|███████▏  | 44508/61904 [44:57<6:35:03,  1.36s/it]
 72%|███████▏  | 44509/61904 [44:58<6:43:41,  1.39s/it]
 72%|███████▏  | 44510/61904 [44:59<6:34:49,  1.36s/it]
 72%|███████▏  | 44511/61904 [45:01<6:26:21,  1.33s/it]
 72%|███████▏  | 44512/61904 [45:02<6:30:02,  1.35s/it]
 72%|███████▏  | 44513/61904 [45:03<6:26:07,  1.33s/it]
 72%|███████▏  | 44514/61904 [45:05<6:34:38,  1.36s/it]
 72%|███████▏  | 44515/61904 [45:06<6:25:17,  1.33s/it]
 72%|███████▏  | 44516/61904 [45:07<6:28:52,  1.34s/it]
 72%|███████▏  | 44517/61904 [45:09<6:29:47,  1.35s/it]
 72%|███████▏  | 44518/61904 [45:10<6:29:27,  1.34s/it]
 72%|███████▏  | 44519/61904 [45:11<6:35:51,  1.37s/it]
 72%|███████▏  | 44520/61904 [45:13<6:39:05,  1.38s/it]
                                                       
{'loss': 2.4435, 'learning_rate': 1.281732140541942e-07, 'epoch': 11.51}

 72%|███████▏  | 44520/61904 [45:13<6:39:05,  1.38s/it]
 72%|███████▏  | 44521/61904 [45:14<6:33:48,  1.36s/it]
 72%|███████▏  | 44522/61904 [45:16<6:30:56,  1.35s/it]
 72%|███████▏  | 44523/61904 [45:17<6:37:26,  1.37s/it]
 72%|███████▏  | 44524/61904 [45:18<6:28:15,  1.34s/it]
 72%|███████▏  | 44525/61904 [45:20<6:43:47,  1.39s/it]
 72%|███████▏  | 44526/61904 [45:21<6:44:28,  1.40s/it]
 72%|███████▏  | 44527/61904 [45:22<6:32:28,  1.36s/it]
 72%|███████▏  | 44528/61904 [45:24<6:38:49,  1.38s/it]
 72%|███████▏  | 44529/61904 [45:25<6:50:10,  1.42s/it]
 72%|███████▏  | 44530/61904 [45:27<6:48:34,  1.41s/it]
 72%|███████▏  | 44531/61904 [45:28<6:38:13,  1.38s/it]
 72%|███████▏  | 44532/61904 [45:30<6:51:06,  1.42s/it]
 72%|███████▏  | 44533/61904 [45:31<6:37:40,  1.37s/it]
 72%|███████▏  | 44534/61904 [45:32<6:28:41,  1.34s/it]
 72%|███████▏  | 44535/61904 [45:33<6:28:12,  1.34s/it]
 72%|███████▏  | 44536/61904 [45:35<6:24:27,  1.33s/it]
 72%|███████▏  | 44537/61904 [45:36<6:27:23,  1.34s/it]
 72%|███████▏  | 44538/61904 [45:37<6:21:36,  1.32s/it]
 72%|███████▏  | 44539/61904 [45:39<6:26:23,  1.34s/it]
 72%|███████▏  | 44540/61904 [45:40<6:26:11,  1.33s/it]
                                                       
{'loss': 2.4716, 'learning_rate': 1.281408012446519e-07, 'epoch': 11.51}

 72%|███████▏  | 44540/61904 [45:40<6:26:11,  1.33s/it]
 72%|███████▏  | 44541/61904 [45:42<6:36:11,  1.37s/it]
 72%|███████▏  | 44542/61904 [45:43<6:34:27,  1.36s/it]
 72%|███████▏  | 44543/61904 [45:44<6:28:41,  1.34s/it]
 72%|███████▏  | 44544/61904 [45:45<6:18:42,  1.31s/it]
 72%|███████▏  | 44545/61904 [45:47<6:13:39,  1.29s/it]
 72%|███████▏  | 44546/61904 [45:48<6:06:44,  1.27s/it]
 72%|███████▏  | 44547/61904 [45:49<6:25:15,  1.33s/it]
 72%|███████▏  | 44548/61904 [45:51<6:31:13,  1.35s/it]
 72%|███████▏  | 44549/61904 [45:52<6:32:45,  1.36s/it]
 72%|███████▏  | 44550/61904 [45:54<6:50:04,  1.42s/it]
 72%|███████▏  | 44551/61904 [45:55<6:39:06,  1.38s/it]
 72%|███████▏  | 44552/61904 [45:56<6:42:59,  1.39s/it]
 72%|███████▏  | 44553/61904 [45:58<6:46:36,  1.41s/it]
 72%|███████▏  | 44554/61904 [45:59<6:48:16,  1.41s/it]
 72%|███████▏  | 44555/61904 [46:01<6:47:23,  1.41s/it]
 72%|███████▏  | 44556/61904 [46:02<7:03:05,  1.46s/it]
 72%|███████▏  | 44557/61904 [46:04<6:48:12,  1.41s/it]
 72%|███████▏  | 44558/61904 [46:05<6:58:00,  1.45s/it]
 72%|███████▏  | 44559/61904 [46:07<7:01:15,  1.46s/it]
 72%|███████▏  | 44560/61904 [46:08<6:51:49,  1.42s/it]
                                                       
{'loss': 2.457, 'learning_rate': 1.2810838843510955e-07, 'epoch': 11.52}

 72%|███████▏  | 44560/61904 [46:08<6:51:49,  1.42s/it]
 72%|███████▏  | 44561/61904 [46:09<6:37:45,  1.38s/it]
 72%|███████▏  | 44562/61904 [46:10<6:33:00,  1.36s/it]
 72%|███████▏  | 44563/61904 [46:12<6:40:28,  1.39s/it]
 72%|███████▏  | 44564/61904 [46:13<6:44:37,  1.40s/it]
 72%|███████▏  | 44565/61904 [46:15<6:33:11,  1.36s/it]
 72%|███████▏  | 44566/61904 [46:16<6:46:09,  1.41s/it]
 72%|███████▏  | 44567/61904 [46:18<6:48:32,  1.41s/it]
 72%|███████▏  | 44568/61904 [46:19<6:54:36,  1.43s/it]
 72%|███████▏  | 44569/61904 [46:20<6:37:42,  1.38s/it]
 72%|███████▏  | 44570/61904 [46:22<6:52:13,  1.43s/it]
 72%|███████▏  | 44571/61904 [46:23<6:49:50,  1.42s/it]
 72%|███████▏  | 44572/61904 [46:24<6:26:19,  1.34s/it]
 72%|███████▏  | 44573/61904 [46:26<6:29:01,  1.35s/it]
 72%|███████▏  | 44574/61904 [46:27<6:30:11,  1.35s/it]
 72%|███████▏  | 44575/61904 [46:29<6:36:19,  1.37s/it]
 72%|███████▏  | 44576/61904 [46:30<6:37:06,  1.38s/it]
 72%|███████▏  | 44577/61904 [46:31<6:35:44,  1.37s/it]
 72%|███████▏  | 44578/61904 [46:33<6:25:06,  1.33s/it]
 72%|███████▏  | 44579/61904 [46:34<6:20:54,  1.32s/it]
 72%|███████▏  | 44580/61904 [46:35<6:31:26,  1.36s/it]
                                                       
{'loss': 2.4465, 'learning_rate': 1.2807597562556721e-07, 'epoch': 11.52}

 72%|███████▏  | 44580/61904 [46:35<6:31:26,  1.36s/it]
 72%|███████▏  | 44581/61904 [46:37<6:29:31,  1.35s/it]
 72%|███████▏  | 44582/61904 [46:38<6:33:51,  1.36s/it]
 72%|███████▏  | 44583/61904 [46:39<6:31:44,  1.36s/it]
 72%|███████▏  | 44584/61904 [46:41<6:26:02,  1.34s/it]
 72%|███████▏  | 44585/61904 [46:42<6:23:24,  1.33s/it]
 72%|███████▏  | 44586/61904 [46:43<6:29:55,  1.35s/it]
 72%|███████▏  | 44587/61904 [46:45<6:33:05,  1.36s/it]
 72%|███████▏  | 44588/61904 [46:46<6:34:12,  1.37s/it]
 72%|███████▏  | 44589/61904 [46:47<6:24:32,  1.33s/it]
 72%|███████▏  | 44590/61904 [46:49<6:34:41,  1.37s/it]
 72%|███████▏  | 44591/61904 [46:50<6:31:22,  1.36s/it]
 72%|███████▏  | 44592/61904 [46:52<6:43:46,  1.40s/it]
 72%|███████▏  | 44593/61904 [46:53<6:31:04,  1.36s/it]
 72%|███████▏  | 44594/61904 [46:54<6:33:49,  1.37s/it]
 72%|███████▏  | 44595/61904 [46:56<6:24:30,  1.33s/it]
 72%|███████▏  | 44596/61904 [46:57<6:42:32,  1.40s/it]
 72%|███████▏  | 44597/61904 [46:58<6:35:45,  1.37s/it]
 72%|███████▏  | 44598/61904 [47:00<6:32:20,  1.36s/it]
 72%|███████▏  | 44599/61904 [47:01<6:39:34,  1.39s/it]
 72%|███████▏  | 44600/61904 [47:02<6:37:05,  1.38s/it]
                                                       
{'loss': 2.4804, 'learning_rate': 1.2804356281602488e-07, 'epoch': 11.53}

 72%|███████▏  | 44600/61904 [47:02<6:37:05,  1.38s/it]
 72%|███████▏  | 44601/61904 [47:04<6:35:42,  1.37s/it]
 72%|███████▏  | 44602/61904 [47:05<6:31:08,  1.36s/it]
 72%|███████▏  | 44603/61904 [47:07<6:38:19,  1.38s/it]
 72%|███████▏  | 44604/61904 [47:08<6:25:24,  1.34s/it]
 72%|███████▏  | 44605/61904 [47:09<6:25:17,  1.34s/it]
 72%|███████▏  | 44606/61904 [47:10<6:18:07,  1.31s/it]
 72%|███████▏  | 44607/61904 [47:12<6:22:11,  1.33s/it]
 72%|███████▏  | 44608/61904 [47:13<6:25:39,  1.34s/it]
 72%|███████▏  | 44609/61904 [47:15<6:30:42,  1.36s/it]
 72%|███████▏  | 44610/61904 [47:16<6:20:24,  1.32s/it]
 72%|███████▏  | 44611/61904 [47:17<6:43:37,  1.40s/it]
 72%|███████▏  | 44612/61904 [47:19<6:36:21,  1.38s/it]
 72%|███████▏  | 44613/61904 [47:20<6:27:43,  1.35s/it]
 72%|███████▏  | 44614/61904 [47:21<6:17:24,  1.31s/it]
 72%|███████▏  | 44615/61904 [47:23<6:19:01,  1.32s/it]
 72%|███████▏  | 44616/61904 [47:24<6:21:04,  1.32s/it]
 72%|███████▏  | 44617/61904 [47:25<6:26:39,  1.34s/it]
 72%|███████▏  | 44618/61904 [47:27<6:32:41,  1.36s/it]
 72%|███████▏  | 44619/61904 [47:28<6:31:12,  1.36s/it]
 72%|███████▏  | 44620/61904 [47:29<6:24:07,  1.33s/it]
                                                       
{'loss': 2.5168, 'learning_rate': 1.2801115000648256e-07, 'epoch': 11.53}

 72%|███████▏  | 44620/61904 [47:29<6:24:07,  1.33s/it]
 72%|███████▏  | 44621/61904 [47:31<6:16:56,  1.31s/it]
 72%|███████▏  | 44622/61904 [47:32<6:37:28,  1.38s/it]
 72%|███████▏  | 44623/61904 [47:34<6:56:56,  1.45s/it]
 72%|███████▏  | 44624/61904 [47:35<6:49:54,  1.42s/it]
 72%|███████▏  | 44625/61904 [47:36<6:42:39,  1.40s/it]
 72%|███████▏  | 44626/61904 [47:38<6:31:01,  1.36s/it]
 72%|███████▏  | 44627/61904 [47:39<6:20:29,  1.32s/it]
 72%|███████▏  | 44628/61904 [47:40<6:27:44,  1.35s/it]
 72%|███████▏  | 44629/61904 [47:42<6:22:45,  1.33s/it]
 72%|███████▏  | 44630/61904 [47:43<6:22:32,  1.33s/it]
 72%|███████▏  | 44631/61904 [47:44<6:25:38,  1.34s/it]
 72%|███████▏  | 44632/61904 [47:46<6:31:06,  1.36s/it]
 72%|███████▏  | 44633/61904 [47:47<6:34:25,  1.37s/it]
 72%|███████▏  | 44634/61904 [47:48<6:29:09,  1.35s/it]
 72%|███████▏  | 44635/61904 [47:50<6:22:50,  1.33s/it]
 72%|███████▏  | 44636/61904 [47:51<6:27:37,  1.35s/it]
 72%|███████▏  | 44637/61904 [47:53<6:38:10,  1.38s/it]
 72%|███████▏  | 44638/61904 [47:54<6:37:33,  1.38s/it]
 72%|███████▏  | 44639/61904 [47:55<6:35:25,  1.37s/it]
 72%|███████▏  | 44640/61904 [47:57<6:23:32,  1.33s/it]
                                                       
{'loss': 2.4759, 'learning_rate': 1.2797873719694023e-07, 'epoch': 11.54}

 72%|███████▏  | 44640/61904 [47:57<6:23:32,  1.33s/it]
 72%|███████▏  | 44641/61904 [47:58<6:24:44,  1.34s/it]
 72%|███████▏  | 44642/61904 [47:59<6:23:02,  1.33s/it]
 72%|███████▏  | 44643/61904 [48:01<6:41:13,  1.39s/it]
 72%|███████▏  | 44644/61904 [48:02<6:34:12,  1.37s/it]
 72%|███████▏  | 44645/61904 [48:04<6:44:23,  1.41s/it]
 72%|███████▏  | 44646/61904 [48:05<6:39:11,  1.39s/it]
 72%|███████▏  | 44647/61904 [48:06<6:30:14,  1.36s/it]
 72%|███████▏  | 44648/61904 [48:07<6:28:41,  1.35s/it]
 72%|███████▏  | 44649/61904 [48:09<6:31:34,  1.36s/it]
 72%|███████▏  | 44650/61904 [48:10<6:36:16,  1.38s/it]
 72%|███████▏  | 44651/61904 [48:12<6:34:34,  1.37s/it]
 72%|███████▏  | 44652/61904 [48:13<6:28:52,  1.35s/it]
 72%|███████▏  | 44653/61904 [48:14<6:31:54,  1.36s/it]
 72%|███████▏  | 44654/61904 [48:16<6:46:33,  1.41s/it]
 72%|███████▏  | 44655/61904 [48:17<6:42:44,  1.40s/it]
 72%|███████▏  | 44656/61904 [48:19<6:34:48,  1.37s/it]
 72%|███████▏  | 44657/61904 [48:20<6:21:11,  1.33s/it]
 72%|███████▏  | 44658/61904 [48:21<6:27:57,  1.35s/it]
 72%|███████▏  | 44659/61904 [48:23<6:40:46,  1.39s/it]
 72%|███████▏  | 44660/61904 [48:24<6:36:55,  1.38s/it]
                                                       
{'loss': 2.4929, 'learning_rate': 1.279463243873979e-07, 'epoch': 11.54}

 72%|███████▏  | 44660/61904 [48:24<6:36:55,  1.38s/it]
 72%|███████▏  | 44661/61904 [48:25<6:21:07,  1.33s/it]
 72%|███████▏  | 44662/61904 [48:27<6:23:49,  1.34s/it]
 72%|███████▏  | 44663/61904 [48:28<6:16:00,  1.31s/it]
 72%|███████▏  | 44664/61904 [48:29<6:16:33,  1.31s/it]
 72%|███████▏  | 44665/61904 [48:30<6:14:43,  1.30s/it]
 72%|███████▏  | 44666/61904 [48:32<6:34:27,  1.37s/it]
 72%|███████▏  | 44667/61904 [48:33<6:30:16,  1.36s/it]
 72%|███████▏  | 44668/61904 [48:35<6:28:17,  1.35s/it]
 72%|███████▏  | 44669/61904 [48:36<6:31:26,  1.36s/it]
 72%|███████▏  | 44670/61904 [48:37<6:27:15,  1.35s/it]
 72%|███████▏  | 44671/61904 [48:39<6:31:56,  1.36s/it]
 72%|███████▏  | 44672/61904 [48:40<6:34:00,  1.37s/it]
 72%|███████▏  | 44673/61904 [48:42<6:45:17,  1.41s/it]
 72%|███████▏  | 44674/61904 [48:43<6:39:53,  1.39s/it]
 72%|███████▏  | 44675/61904 [48:44<6:45:07,  1.41s/it]
 72%|███████▏  | 44676/61904 [48:46<6:47:44,  1.42s/it]
 72%|███████▏  | 44677/61904 [48:47<6:42:10,  1.40s/it]
 72%|███████▏  | 44678/61904 [48:49<6:43:40,  1.41s/it]
 72%|███████▏  | 44679/61904 [48:50<6:29:32,  1.36s/it]
 72%|███████▏  | 44680/61904 [48:51<6:30:44,  1.36s/it]
                                                       
{'loss': 2.4136, 'learning_rate': 1.2791391157785555e-07, 'epoch': 11.55}

 72%|███████▏  | 44680/61904 [48:51<6:30:44,  1.36s/it]
 72%|███████▏  | 44681/61904 [48:53<6:40:19,  1.39s/it]
 72%|███████▏  | 44682/61904 [48:54<6:35:37,  1.38s/it]
 72%|███████▏  | 44683/61904 [48:55<6:39:47,  1.39s/it]
 72%|███████▏  | 44684/61904 [48:57<6:40:07,  1.39s/it]
 72%|███████▏  | 44685/61904 [48:58<6:37:29,  1.39s/it]
 72%|███████▏  | 44686/61904 [48:59<6:21:52,  1.33s/it]
 72%|███████▏  | 44687/61904 [49:01<6:34:41,  1.38s/it]
 72%|███████▏  | 44688/61904 [49:02<6:30:20,  1.36s/it]
 72%|███████▏  | 44689/61904 [49:04<6:24:58,  1.34s/it]
 72%|███████▏  | 44690/61904 [49:05<6:50:23,  1.43s/it]
 72%|███████▏  | 44691/61904 [49:07<6:49:38,  1.43s/it]
 72%|███████▏  | 44692/61904 [49:08<6:30:54,  1.36s/it]
 72%|███████▏  | 44693/61904 [49:09<6:38:55,  1.39s/it]
 72%|███████▏  | 44694/61904 [49:11<6:37:25,  1.39s/it]
 72%|███████▏  | 44695/61904 [49:12<6:43:03,  1.41s/it]
 72%|███████▏  | 44696/61904 [49:14<6:49:46,  1.43s/it]
 72%|███████▏  | 44697/61904 [49:15<6:37:17,  1.39s/it]
 72%|███████▏  | 44698/61904 [49:16<6:38:59,  1.39s/it]
 72%|███████▏  | 44699/61904 [49:18<6:38:20,  1.39s/it]
 72%|███████▏  | 44700/61904 [49:19<6:28:15,  1.35s/it]
                                                       
{'loss': 2.4497, 'learning_rate': 1.2788149876831324e-07, 'epoch': 11.55}

 72%|███████▏  | 44700/61904 [49:19<6:28:15,  1.35s/it]
 72%|███████▏  | 44701/61904 [49:20<6:26:19,  1.35s/it]
 72%|███████▏  | 44702/61904 [49:22<6:28:44,  1.36s/it]
 72%|███████▏  | 44703/61904 [49:23<6:35:46,  1.38s/it]
 72%|███████▏  | 44704/61904 [49:24<6:25:30,  1.34s/it]
 72%|███████▏  | 44705/61904 [49:26<6:17:37,  1.32s/it]
 72%|███████▏  | 44706/61904 [49:27<6:09:08,  1.29s/it]
 72%|███████▏  | 44707/61904 [49:28<6:06:48,  1.28s/it]
 72%|███████▏  | 44708/61904 [49:30<6:22:25,  1.33s/it]
 72%|███████▏  | 44709/61904 [49:31<6:28:22,  1.36s/it]
 72%|███████▏  | 44710/61904 [49:32<6:27:17,  1.35s/it]
 72%|███████▏  | 44711/61904 [49:34<6:29:32,  1.36s/it]
 72%|███████▏  | 44712/61904 [49:35<6:20:43,  1.33s/it]
 72%|███████▏  | 44713/61904 [49:36<6:21:52,  1.33s/it]
 72%|███████▏  | 44714/61904 [49:38<6:18:25,  1.32s/it]
 72%|███████▏  | 44715/61904 [49:39<6:37:51,  1.39s/it]
 72%|███████▏  | 44716/61904 [49:40<6:34:51,  1.38s/it]
 72%|███████▏  | 44717/61904 [49:42<6:27:15,  1.35s/it]
 72%|███████▏  | 44718/61904 [49:43<6:36:20,  1.38s/it]
 72%|███████▏  | 44719/61904 [49:45<6:34:07,  1.38s/it]
 72%|███████▏  | 44720/61904 [49:46<6:42:38,  1.41s/it]
                                                       
{'loss': 2.4912, 'learning_rate': 1.278490859587709e-07, 'epoch': 11.56}

 72%|███████▏  | 44720/61904 [49:46<6:42:38,  1.41s/it]
 72%|███████▏  | 44721/61904 [49:47<6:36:51,  1.39s/it]
 72%|███████▏  | 44722/61904 [49:49<6:37:01,  1.39s/it]
 72%|███████▏  | 44723/61904 [49:50<6:26:23,  1.35s/it]
 72%|███████▏  | 44724/61904 [49:51<6:29:49,  1.36s/it]
 72%|███████▏  | 44725/61904 [49:53<6:36:24,  1.38s/it]
 72%|███████▏  | 44726/61904 [49:54<6:28:02,  1.36s/it]
 72%|███████▏  | 44727/61904 [49:56<6:35:17,  1.38s/it]
 72%|███████▏  | 44728/61904 [49:57<6:39:02,  1.39s/it]
 72%|███████▏  | 44729/61904 [49:58<6:31:07,  1.37s/it]
 72%|███████▏  | 44730/61904 [50:00<6:43:52,  1.41s/it]
 72%|███████▏  | 44731/61904 [50:01<6:50:16,  1.43s/it]
 72%|███████▏  | 44732/61904 [50:03<6:50:12,  1.43s/it]
 72%|███████▏  | 44733/61904 [50:04<6:48:29,  1.43s/it]
 72%|███████▏  | 44734/61904 [50:06<6:41:40,  1.40s/it]
 72%|███████▏  | 44735/61904 [50:07<6:39:55,  1.40s/it]
 72%|███████▏  | 44736/61904 [50:08<6:46:19,  1.42s/it]
 72%|███████▏  | 44737/61904 [50:10<6:45:43,  1.42s/it]
 72%|███████▏  | 44738/61904 [50:11<6:58:56,  1.46s/it]
 72%|███████▏  | 44739/61904 [50:13<6:55:53,  1.45s/it]
 72%|███████▏  | 44740/61904 [50:14<7:02:06,  1.48s/it]
                                                       
{'loss': 2.5089, 'learning_rate': 1.2781667314922856e-07, 'epoch': 11.56}

 72%|███████▏  | 44740/61904 [50:14<7:02:06,  1.48s/it]
 72%|███████▏  | 44741/61904 [50:16<6:59:10,  1.47s/it]
 72%|███████▏  | 44742/61904 [50:17<6:46:28,  1.42s/it]
 72%|███████▏  | 44743/61904 [50:18<6:39:40,  1.40s/it]
 72%|███████▏  | 44744/61904 [50:20<6:46:25,  1.42s/it]
 72%|███████▏  | 44745/61904 [50:21<6:38:49,  1.39s/it]
 72%|███████▏  | 44746/61904 [50:22<6:28:08,  1.36s/it]
 72%|███████▏  | 44747/61904 [50:24<6:25:21,  1.35s/it]
 72%|███████▏  | 44748/61904 [50:25<6:16:55,  1.32s/it]
 72%|███████▏  | 44749/61904 [50:26<6:10:23,  1.30s/it]
 72%|███████▏  | 44750/61904 [50:28<6:24:53,  1.35s/it]
 72%|███████▏  | 44751/61904 [50:29<6:26:25,  1.35s/it]
 72%|███████▏  | 44752/61904 [50:30<6:23:39,  1.34s/it]
 72%|███████▏  | 44753/61904 [50:32<6:21:36,  1.33s/it]
 72%|███████▏  | 44754/61904 [50:33<6:38:41,  1.39s/it]
 72%|███████▏  | 44755/61904 [50:35<6:38:22,  1.39s/it]
 72%|███████▏  | 44756/61904 [50:36<6:36:11,  1.39s/it]
 72%|███████▏  | 44757/61904 [50:37<6:29:50,  1.36s/it]
 72%|███████▏  | 44758/61904 [50:39<6:17:41,  1.32s/it]
 72%|███████▏  | 44759/61904 [50:40<6:30:15,  1.37s/it]
 72%|███████▏  | 44760/61904 [50:41<6:34:38,  1.38s/it]
                                                       
{'loss': 2.4516, 'learning_rate': 1.2778426033968622e-07, 'epoch': 11.57}

 72%|███████▏  | 44760/61904 [50:41<6:34:38,  1.38s/it]
 72%|███████▏  | 44761/61904 [50:43<6:43:50,  1.41s/it]
 72%|███████▏  | 44762/61904 [50:44<6:42:06,  1.41s/it]
 72%|███████▏  | 44763/61904 [50:46<6:40:11,  1.40s/it]
 72%|███████▏  | 44764/61904 [50:47<6:34:13,  1.38s/it]
 72%|███████▏  | 44765/61904 [50:48<6:32:08,  1.37s/it]
 72%|███████▏  | 44766/61904 [50:50<6:40:24,  1.40s/it]
 72%|███████▏  | 44767/61904 [50:51<6:37:37,  1.39s/it]
 72%|███████▏  | 44768/61904 [50:53<6:28:50,  1.36s/it]
 72%|███████▏  | 44769/61904 [50:54<6:41:44,  1.41s/it]
 72%|███████▏  | 44770/61904 [50:55<6:39:34,  1.40s/it]
 72%|███████▏  | 44771/61904 [50:57<6:32:30,  1.37s/it]
 72%|███████▏  | 44772/61904 [50:58<6:35:38,  1.39s/it]
 72%|███████▏  | 44773/61904 [51:00<6:35:14,  1.38s/it]
 72%|███████▏  | 44774/61904 [51:01<6:40:12,  1.40s/it]
 72%|███████▏  | 44775/61904 [51:02<6:34:11,  1.38s/it]
 72%|███████▏  | 44776/61904 [51:04<6:37:09,  1.39s/it]
 72%|███████▏  | 44777/61904 [51:05<6:28:57,  1.36s/it]
 72%|███████▏  | 44778/61904 [51:07<6:37:25,  1.39s/it]
 72%|███████▏  | 44779/61904 [51:08<6:23:15,  1.34s/it]
 72%|███████▏  | 44780/61904 [51:09<6:32:17,  1.37s/it]
                                                       
{'loss': 2.5023, 'learning_rate': 1.277518475301439e-07, 'epoch': 11.57}

 72%|███████▏  | 44780/61904 [51:09<6:32:17,  1.37s/it]
 72%|███████▏  | 44781/61904 [51:11<6:32:25,  1.38s/it]
 72%|███████▏  | 44782/61904 [51:12<6:23:02,  1.34s/it]
 72%|███████▏  | 44783/61904 [51:13<6:30:51,  1.37s/it]
 72%|███████▏  | 44784/61904 [51:15<6:20:46,  1.33s/it]
 72%|███████▏  | 44785/61904 [51:16<6:21:21,  1.34s/it]
 72%|███████▏  | 44786/61904 [51:17<6:19:10,  1.33s/it]
 72%|███████▏  | 44787/61904 [51:18<6:08:22,  1.29s/it]
 72%|███████▏  | 44788/61904 [51:20<6:14:55,  1.31s/it]
 72%|███████▏  | 44789/61904 [51:21<6:22:22,  1.34s/it]
 72%|███████▏  | 44790/61904 [51:22<6:21:04,  1.34s/it]
 72%|███████▏  | 44791/61904 [51:24<6:27:31,  1.36s/it]
 72%|███████▏  | 44792/61904 [51:25<6:33:02,  1.38s/it]
 72%|███████▏  | 44793/61904 [51:27<6:25:08,  1.35s/it]
 72%|███████▏  | 44794/61904 [51:28<6:26:40,  1.36s/it]
 72%|███████▏  | 44795/61904 [51:29<6:18:54,  1.33s/it]
 72%|███████▏  | 44796/61904 [51:30<6:10:58,  1.30s/it]
 72%|███████▏  | 44797/61904 [51:32<6:06:06,  1.28s/it]
 72%|███████▏  | 44798/61904 [51:33<6:08:41,  1.29s/it]
 72%|███████▏  | 44799/61904 [51:34<6:15:45,  1.32s/it]
 72%|███████▏  | 44800/61904 [51:36<6:30:17,  1.37s/it]
                                                       
{'loss': 2.4883, 'learning_rate': 1.2771943472060157e-07, 'epoch': 11.58}

 72%|███████▏  | 44800/61904 [51:36<6:30:17,  1.37s/it]
 72%|███████▏  | 44801/61904 [51:37<6:32:24,  1.38s/it]
 72%|███████▏  | 44802/61904 [51:39<6:33:07,  1.38s/it]
 72%|███████▏  | 44803/61904 [51:40<6:30:10,  1.37s/it]
 72%|███████▏  | 44804/61904 [51:41<6:30:16,  1.37s/it]
 72%|███████▏  | 44805/61904 [51:43<6:34:37,  1.38s/it]
 72%|███████▏  | 44806/61904 [51:44<6:30:11,  1.37s/it]
 72%|███████▏  | 44807/61904 [51:45<6:25:25,  1.35s/it]
 72%|███████▏  | 44808/61904 [51:47<6:17:44,  1.33s/it]
 72%|███████▏  | 44809/61904 [51:48<6:20:56,  1.34s/it]
 72%|███████▏  | 44810/61904 [51:50<6:44:19,  1.42s/it]
 72%|███████▏  | 44811/61904 [51:51<6:39:11,  1.40s/it]
 72%|███████▏  | 44812/61904 [51:52<6:22:13,  1.34s/it]
 72%|███████▏  | 44813/61904 [51:54<6:22:20,  1.34s/it]
 72%|███████▏  | 44814/61904 [51:55<6:25:04,  1.35s/it]
 72%|███████▏  | 44815/61904 [51:56<6:32:51,  1.38s/it]
 72%|███████▏  | 44816/61904 [51:58<6:29:50,  1.37s/it]
 72%|███████▏  | 44817/61904 [51:59<6:27:05,  1.36s/it]
 72%|███████▏  | 44818/61904 [52:01<6:37:53,  1.40s/it]
 72%|███████▏  | 44819/61904 [52:02<6:28:24,  1.36s/it]
 72%|███████▏  | 44820/61904 [52:03<6:25:29,  1.35s/it]
                                                       
{'loss': 2.4885, 'learning_rate': 1.2768702191105924e-07, 'epoch': 11.58}

 72%|███████▏  | 44820/61904 [52:03<6:25:29,  1.35s/it]
 72%|███████▏  | 44821/61904 [52:05<6:30:57,  1.37s/it]
 72%|███████▏  | 44822/61904 [52:06<6:35:48,  1.39s/it]
 72%|███████▏  | 44823/61904 [52:07<6:34:04,  1.38s/it]
 72%|███████▏  | 44824/61904 [52:09<6:29:36,  1.37s/it]
 72%|███████▏  | 44825/61904 [52:10<6:24:36,  1.35s/it]
 72%|███████▏  | 44826/61904 [52:11<6:27:52,  1.36s/it]
 72%|███████▏  | 44827/61904 [52:13<6:26:13,  1.36s/it]
 72%|███████▏  | 44828/61904 [52:14<6:39:50,  1.40s/it]
 72%|███████▏  | 44829/61904 [52:16<6:30:35,  1.37s/it]
 72%|███████▏  | 44830/61904 [52:17<6:32:01,  1.38s/it]
 72%|███████▏  | 44831/61904 [52:18<6:29:59,  1.37s/it]
 72%|███████▏  | 44832/61904 [52:20<6:27:06,  1.36s/it]
 72%|███████▏  | 44833/61904 [52:21<6:32:17,  1.38s/it]
 72%|███████▏  | 44834/61904 [52:22<6:23:26,  1.35s/it]
 72%|███████▏  | 44835/61904 [52:24<6:17:17,  1.33s/it]
 72%|███████▏  | 44836/61904 [52:25<6:14:10,  1.32s/it]
 72%|███████▏  | 44837/61904 [52:26<6:07:23,  1.29s/it]
 72%|███████▏  | 44838/61904 [52:28<6:16:58,  1.33s/it]
 72%|███████▏  | 44839/61904 [52:29<6:24:44,  1.35s/it]
 72%|███████▏  | 44840/61904 [52:30<6:21:56,  1.34s/it]
                                                       
{'loss': 2.5421, 'learning_rate': 1.2765460910151692e-07, 'epoch': 11.59}

 72%|███████▏  | 44840/61904 [52:30<6:21:56,  1.34s/it]
 72%|███████▏  | 44841/61904 [52:32<6:23:18,  1.35s/it]
 72%|███████▏  | 44842/61904 [52:33<6:22:04,  1.34s/it]
 72%|███████▏  | 44843/61904 [52:34<6:22:42,  1.35s/it]
 72%|███████▏  | 44844/61904 [52:36<6:28:53,  1.37s/it]
 72%|███████▏  | 44845/61904 [52:37<6:28:21,  1.37s/it]
 72%|███████▏  | 44846/61904 [52:39<6:29:16,  1.37s/it]
 72%|███████▏  | 44847/61904 [52:40<6:28:31,  1.37s/it]
 72%|███████▏  | 44848/61904 [52:41<6:35:10,  1.39s/it]
 72%|███████▏  | 44849/61904 [52:43<6:23:11,  1.35s/it]
 72%|███████▏  | 44850/61904 [52:44<6:15:27,  1.32s/it]
 72%|███████▏  | 44851/61904 [52:45<6:27:31,  1.36s/it]
 72%|███████▏  | 44852/61904 [52:47<6:31:26,  1.38s/it]
 72%|███████▏  | 44853/61904 [52:48<6:33:42,  1.39s/it]
 72%|███████▏  | 44854/61904 [52:50<6:35:51,  1.39s/it]
 72%|███████▏  | 44855/61904 [52:51<6:36:59,  1.40s/it]
 72%|███████▏  | 44856/61904 [52:52<6:32:03,  1.38s/it]
 72%|███████▏  | 44857/61904 [52:54<6:27:25,  1.36s/it]
 72%|███████▏  | 44858/61904 [52:55<6:23:05,  1.35s/it]
 72%|███████▏  | 44859/61904 [52:56<6:36:49,  1.40s/it]
 72%|███████▏  | 44860/61904 [52:58<6:31:39,  1.38s/it]
                                                       
{'loss': 2.4938, 'learning_rate': 1.2762219629197459e-07, 'epoch': 11.59}

 72%|███████▏  | 44860/61904 [52:58<6:31:39,  1.38s/it]
 72%|███████▏  | 44861/61904 [52:59<6:39:39,  1.41s/it]
 72%|███████▏  | 44862/61904 [53:01<6:38:46,  1.40s/it]
 72%|███████▏  | 44863/61904 [53:02<6:44:03,  1.42s/it]
 72%|███████▏  | 44864/61904 [53:03<6:38:00,  1.40s/it]
 72%|███████▏  | 44865/61904 [53:05<6:41:10,  1.41s/it]
 72%|███████▏  | 44866/61904 [53:06<6:34:11,  1.39s/it]
 72%|███████▏  | 44867/61904 [53:08<6:49:47,  1.44s/it]
 72%|███████▏  | 44868/61904 [53:09<6:48:22,  1.44s/it]
 72%|███████▏  | 44869/61904 [53:10<6:35:14,  1.39s/it]
 72%|███████▏  | 44870/61904 [53:12<6:32:30,  1.38s/it]
 72%|███████▏  | 44871/61904 [53:13<6:28:06,  1.37s/it]
 72%|███████▏  | 44872/61904 [53:15<6:29:12,  1.37s/it]
 72%|███████▏  | 44873/61904 [53:16<6:28:40,  1.37s/it]
 72%|███████▏  | 44874/61904 [53:17<6:28:45,  1.37s/it]
 72%|███████▏  | 44875/61904 [53:19<6:51:15,  1.45s/it]
 72%|███████▏  | 44876/61904 [53:20<6:45:21,  1.43s/it]
 72%|███████▏  | 44877/61904 [53:22<6:32:18,  1.38s/it]
 72%|███████▏  | 44878/61904 [53:23<6:39:59,  1.41s/it]
 72%|███████▏  | 44879/61904 [53:24<6:40:09,  1.41s/it]
 72%|███████▏  | 44880/61904 [53:26<6:47:41,  1.44s/it]
                                                       
{'loss': 2.4712, 'learning_rate': 1.2758978348243225e-07, 'epoch': 11.6}

 72%|███████▏  | 44880/61904 [53:26<6:47:41,  1.44s/it]
 73%|███████▎  | 44881/61904 [53:27<6:33:05,  1.39s/it]
 73%|███████▎  | 44882/61904 [53:29<6:28:24,  1.37s/it]
 73%|███████▎  | 44883/61904 [53:30<6:35:44,  1.39s/it]
 73%|███████▎  | 44884/61904 [53:32<6:51:02,  1.45s/it]
 73%|███████▎  | 44885/61904 [53:33<6:38:05,  1.40s/it]
 73%|███████▎  | 44886/61904 [53:34<6:27:44,  1.37s/it]
 73%|███████▎  | 44887/61904 [53:36<6:23:44,  1.35s/it]
 73%|███████▎  | 44888/61904 [53:37<6:27:21,  1.37s/it]
 73%|███████▎  | 44889/61904 [53:38<6:26:26,  1.36s/it]
 73%|███████▎  | 44890/61904 [53:40<6:33:37,  1.39s/it]
 73%|███████▎  | 44891/61904 [53:41<6:26:52,  1.36s/it]
 73%|███████▎  | 44892/61904 [53:42<6:30:24,  1.38s/it]
 73%|███████▎  | 44893/61904 [53:44<6:28:02,  1.37s/it]
 73%|███████▎  | 44894/61904 [53:45<6:20:08,  1.34s/it]
 73%|███████▎  | 44895/61904 [53:46<6:18:35,  1.34s/it]
 73%|███████▎  | 44896/61904 [53:48<6:22:04,  1.35s/it]
 73%|███████▎  | 44897/61904 [53:49<6:14:25,  1.32s/it]
 73%|███████▎  | 44898/61904 [53:50<6:26:54,  1.37s/it]
 73%|███████▎  | 44899/61904 [53:52<6:15:44,  1.33s/it]
 73%|███████▎  | 44900/61904 [53:53<6:21:23,  1.35s/it]
                                                       
{'loss': 2.5227, 'learning_rate': 1.275573706728899e-07, 'epoch': 11.6}

 73%|███████▎  | 44900/61904 [53:53<6:21:23,  1.35s/it]
 73%|███████▎  | 44901/61904 [53:55<6:36:16,  1.40s/it]
 73%|███████▎  | 44902/61904 [53:56<6:47:59,  1.44s/it]
 73%|███████▎  | 44903/61904 [53:58<6:41:27,  1.42s/it]
 73%|███████▎  | 44904/61904 [53:59<6:42:06,  1.42s/it]
 73%|███████▎  | 44905/61904 [54:00<6:47:47,  1.44s/it]
 73%|███████▎  | 44906/61904 [54:02<6:51:23,  1.45s/it]
 73%|███████▎  | 44907/61904 [54:03<6:51:33,  1.45s/it]
 73%|███████▎  | 44908/61904 [54:05<6:47:31,  1.44s/it]
 73%|███████▎  | 44909/61904 [54:06<6:37:59,  1.41s/it]
 73%|███████▎  | 44910/61904 [54:08<6:40:56,  1.42s/it]
 73%|███████▎  | 44911/61904 [54:09<6:35:02,  1.39s/it]
 73%|███████▎  | 44912/61904 [54:10<6:45:48,  1.43s/it]
 73%|███████▎  | 44913/61904 [54:12<6:37:42,  1.40s/it]
 73%|███████▎  | 44914/61904 [54:13<6:29:32,  1.38s/it]
 73%|███████▎  | 44915/61904 [54:15<6:49:10,  1.45s/it]
 73%|███████▎  | 44916/61904 [54:16<6:51:44,  1.45s/it]
 73%|███████▎  | 44917/61904 [54:18<6:48:49,  1.44s/it]
 73%|███████▎  | 44918/61904 [54:19<7:17:32,  1.55s/it]
 73%|███████▎  | 44919/61904 [54:21<7:09:40,  1.52s/it]
 73%|███████▎  | 44920/61904 [54:22<7:07:05,  1.51s/it]
                                                       
{'loss': 2.4463, 'learning_rate': 1.275249578633476e-07, 'epoch': 11.61}

 73%|███████▎  | 44920/61904 [54:22<7:07:05,  1.51s/it]
 73%|███████▎  | 44921/61904 [54:24<6:53:55,  1.46s/it]
 73%|███████▎  | 44922/61904 [54:25<6:56:42,  1.47s/it]
 73%|███████▎  | 44923/61904 [54:27<6:50:14,  1.45s/it]
 73%|███████▎  | 44924/61904 [54:28<6:37:40,  1.41s/it]
 73%|███████▎  | 44925/61904 [54:29<6:39:39,  1.41s/it]
 73%|███████▎  | 44926/61904 [54:31<6:30:14,  1.38s/it]
 73%|███████▎  | 44927/61904 [54:32<6:44:37,  1.43s/it]
 73%|███████▎  | 44928/61904 [54:34<6:42:45,  1.42s/it]
 73%|███████▎  | 44929/61904 [54:35<6:59:00,  1.48s/it]
 73%|███████▎  | 44930/61904 [54:36<6:39:03,  1.41s/it]
 73%|███████▎  | 44931/61904 [54:38<6:37:18,  1.40s/it]
 73%|███████▎  | 44932/61904 [54:39<6:28:06,  1.37s/it]
 73%|███████▎  | 44933/61904 [54:40<6:29:53,  1.38s/it]
 73%|███████▎  | 44934/61904 [54:42<6:37:22,  1.40s/it]
 73%|███████▎  | 44935/61904 [54:43<6:28:42,  1.37s/it]
 73%|███████▎  | 44936/61904 [54:45<6:31:50,  1.39s/it]
 73%|███████▎  | 44937/61904 [54:46<6:23:54,  1.36s/it]
 73%|███████▎  | 44938/61904 [54:47<6:17:46,  1.34s/it]
 73%|███████▎  | 44939/61904 [54:49<6:19:59,  1.34s/it]
 73%|███████▎  | 44940/61904 [54:50<6:19:14,  1.34s/it]
                                                       
{'loss': 2.4526, 'learning_rate': 1.2749254505380526e-07, 'epoch': 11.62}

 73%|███████▎  | 44940/61904 [54:50<6:19:14,  1.34s/it]
 73%|███████▎  | 44941/61904 [54:51<6:28:44,  1.38s/it]
 73%|███████▎  | 44942/61904 [54:53<6:23:13,  1.36s/it]
 73%|███████▎  | 44943/61904 [54:54<6:20:49,  1.35s/it]
 73%|███████▎  | 44944/61904 [54:55<6:23:57,  1.36s/it]
 73%|███████▎  | 44945/61904 [54:57<6:29:35,  1.38s/it]
 73%|███████▎  | 44946/61904 [54:58<6:35:40,  1.40s/it]
 73%|███████▎  | 44947/61904 [55:00<6:32:00,  1.39s/it]
 73%|███████▎  | 44948/61904 [55:01<6:30:39,  1.38s/it]
 73%|███████▎  | 44949/61904 [55:02<6:29:47,  1.38s/it]
 73%|███████▎  | 44950/61904 [55:04<6:40:26,  1.42s/it]
 73%|███████▎  | 44951/61904 [55:05<6:35:44,  1.40s/it]
 73%|███████▎  | 44952/61904 [55:07<6:29:29,  1.38s/it]
 73%|███████▎  | 44953/61904 [55:08<6:31:08,  1.38s/it]
 73%|███████▎  | 44954/61904 [55:09<6:31:19,  1.39s/it]
 73%|███████▎  | 44955/61904 [55:11<6:24:52,  1.36s/it]
 73%|███████▎  | 44956/61904 [55:12<6:26:47,  1.37s/it]
 73%|███████▎  | 44957/61904 [55:14<6:36:54,  1.41s/it]
 73%|███████▎  | 44958/61904 [55:15<6:34:06,  1.40s/it]
 73%|███████▎  | 44959/61904 [55:16<6:49:45,  1.45s/it]
 73%|███████▎  | 44960/61904 [55:18<6:53:03,  1.46s/it]
                                                       
{'loss': 2.4763, 'learning_rate': 1.2746013224426292e-07, 'epoch': 11.62}

 73%|███████▎  | 44960/61904 [55:18<6:53:03,  1.46s/it]
 73%|███████▎  | 44961/61904 [55:19<6:39:18,  1.41s/it]
 73%|███████▎  | 44962/61904 [55:21<6:38:06,  1.41s/it]
 73%|███████▎  | 44963/61904 [55:22<6:44:32,  1.43s/it]
 73%|███████▎  | 44964/61904 [55:24<6:39:13,  1.41s/it]
 73%|███████▎  | 44965/61904 [55:25<6:38:13,  1.41s/it]
 73%|███████▎  | 44966/61904 [55:26<6:26:18,  1.37s/it]
 73%|███████▎  | 44967/61904 [55:28<6:26:58,  1.37s/it]
 73%|███████▎  | 44968/61904 [55:29<6:30:36,  1.38s/it]
 73%|███████▎  | 44969/61904 [55:30<6:22:23,  1.35s/it]
 73%|███████▎  | 44970/61904 [55:32<6:27:02,  1.37s/it]
 73%|███████▎  | 44971/61904 [55:33<6:28:39,  1.38s/it]
 73%|███████▎  | 44972/61904 [55:34<6:25:31,  1.37s/it]
 73%|███████▎  | 44973/61904 [55:36<6:28:42,  1.38s/it]
 73%|███████▎  | 44974/61904 [55:37<6:31:21,  1.39s/it]
 73%|███████▎  | 44975/61904 [55:39<6:21:57,  1.35s/it]
 73%|███████▎  | 44976/61904 [55:40<6:31:02,  1.39s/it]
 73%|███████▎  | 44977/61904 [55:41<6:22:14,  1.35s/it]
 73%|███████▎  | 44978/61904 [55:43<6:19:14,  1.34s/it]
 73%|███████▎  | 44979/61904 [55:44<6:18:35,  1.34s/it]
 73%|███████▎  | 44980/61904 [55:45<6:13:57,  1.33s/it]
                                                       
{'loss': 2.5575, 'learning_rate': 1.2742771943472058e-07, 'epoch': 11.63}

 73%|███████▎  | 44980/61904 [55:45<6:13:57,  1.33s/it]
 73%|███████▎  | 44981/61904 [55:47<6:14:47,  1.33s/it]
 73%|███████▎  | 44982/61904 [55:48<6:17:11,  1.34s/it]
 73%|███████▎  | 44983/61904 [55:49<6:23:52,  1.36s/it]
 73%|███████▎  | 44984/61904 [55:51<6:22:16,  1.36s/it]
 73%|███████▎  | 44985/61904 [55:52<6:14:46,  1.33s/it]
 73%|███████▎  | 44986/61904 [55:53<6:22:00,  1.35s/it]
 73%|███████▎  | 44987/61904 [55:55<6:34:23,  1.40s/it]
 73%|███████▎  | 44988/61904 [55:57<7:11:18,  1.53s/it]
 73%|███████▎  | 44989/61904 [55:58<6:59:21,  1.49s/it]
 73%|███████▎  | 44990/61904 [55:59<6:52:38,  1.46s/it]
 73%|███████▎  | 44991/61904 [56:01<6:54:26,  1.47s/it]
 73%|███████▎  | 44992/61904 [56:02<6:39:52,  1.42s/it]
 73%|███████▎  | 44993/61904 [56:04<6:35:19,  1.40s/it]
 73%|███████▎  | 44994/61904 [56:05<6:17:48,  1.34s/it]
 73%|███████▎  | 44995/61904 [56:06<6:21:36,  1.35s/it]
 73%|███████▎  | 44996/61904 [56:08<6:47:32,  1.45s/it]
 73%|███████▎  | 44997/61904 [56:09<6:30:05,  1.38s/it]
 73%|███████▎  | 44998/61904 [56:10<6:25:54,  1.37s/it]
 73%|███████▎  | 44999/61904 [56:12<6:16:34,  1.34s/it]
 73%|███████▎  | 45000/61904 [56:13<6:11:10,  1.32s/it]
                                                       
{'loss': 2.5079, 'learning_rate': 1.2739530662517827e-07, 'epoch': 11.63}

 73%|███████▎  | 45000/61904 [56:13<6:11:10,  1.32s/it]
 73%|███████▎  | 45001/61904 [56:14<6:15:13,  1.33s/it]
 73%|███████▎  | 45002/61904 [56:16<6:24:19,  1.36s/it]
 73%|███████▎  | 45003/61904 [56:17<6:17:19,  1.34s/it]
 73%|███████▎  | 45004/61904 [56:18<6:23:33,  1.36s/it]
 73%|███████▎  | 45005/61904 [56:20<6:44:48,  1.44s/it]
 73%|███████▎  | 45006/61904 [56:21<6:37:05,  1.41s/it]
 73%|███████▎  | 45007/61904 [56:23<6:47:22,  1.45s/it]
 73%|███████▎  | 45008/61904 [56:24<6:29:57,  1.38s/it]
 73%|███████▎  | 45009/61904 [56:26<6:35:04,  1.40s/it]
 73%|███████▎  | 45010/61904 [56:27<6:21:04,  1.35s/it]
 73%|███████▎  | 45011/61904 [56:28<6:16:00,  1.34s/it]
 73%|███████▎  | 45012/61904 [56:30<6:33:05,  1.40s/it]
 73%|███████▎  | 45013/61904 [56:31<6:50:25,  1.46s/it]
 73%|███████▎  | 45014/61904 [56:33<6:34:11,  1.40s/it]
 73%|███████▎  | 45015/61904 [56:34<6:39:08,  1.42s/it]
 73%|███████▎  | 45016/61904 [56:35<6:27:48,  1.38s/it]
 73%|███████▎  | 45017/61904 [56:37<6:21:55,  1.36s/it]
 73%|███████▎  | 45018/61904 [56:38<6:17:05,  1.34s/it]
 73%|███████▎  | 45019/61904 [56:39<6:15:41,  1.33s/it]
 73%|███████▎  | 45020/61904 [56:41<6:23:07,  1.36s/it]
                                                       
{'loss': 2.4868, 'learning_rate': 1.2736289381563593e-07, 'epoch': 11.64}

 73%|███████▎  | 45020/61904 [56:41<6:23:07,  1.36s/it]
 73%|███████▎  | 45021/61904 [56:42<6:27:44,  1.38s/it]
 73%|███████▎  | 45022/61904 [56:44<6:38:32,  1.42s/it]
 73%|███████▎  | 45023/61904 [56:45<6:32:22,  1.39s/it]
 73%|███████▎  | 45024/61904 [56:46<6:35:36,  1.41s/it]
 73%|███████▎  | 45025/61904 [56:48<6:27:40,  1.38s/it]
 73%|███████▎  | 45026/61904 [56:49<6:40:04,  1.42s/it]
 73%|███████▎  | 45027/61904 [56:51<6:45:08,  1.44s/it]
 73%|███████▎  | 45028/61904 [56:52<6:37:30,  1.41s/it]
 73%|███████▎  | 45029/61904 [56:53<6:29:08,  1.38s/it]
 73%|███████▎  | 45030/61904 [56:55<6:30:06,  1.39s/it]
 73%|███████▎  | 45031/61904 [56:56<6:30:14,  1.39s/it]
 73%|███████▎  | 45032/61904 [56:58<6:30:37,  1.39s/it]
 73%|███████▎  | 45033/61904 [56:59<6:30:46,  1.39s/it]
 73%|███████▎  | 45034/61904 [57:00<6:28:39,  1.38s/it]
 73%|███████▎  | 45035/61904 [57:02<6:33:24,  1.40s/it]
 73%|███████▎  | 45036/61904 [57:04<7:05:52,  1.51s/it]
 73%|███████▎  | 45037/61904 [57:05<6:52:31,  1.47s/it]
 73%|███████▎  | 45038/61904 [57:06<6:59:03,  1.49s/it]
 73%|███████▎  | 45039/61904 [57:08<6:45:05,  1.44s/it]
 73%|███████▎  | 45040/61904 [57:09<6:50:06,  1.46s/it]
                                                       
{'loss': 2.4547, 'learning_rate': 1.273304810060936e-07, 'epoch': 11.64}

 73%|███████▎  | 45040/61904 [57:09<6:50:06,  1.46s/it]
 73%|███████▎  | 45041/61904 [57:11<6:32:38,  1.40s/it]
 73%|███████▎  | 45042/61904 [57:12<6:33:35,  1.40s/it]
 73%|███████▎  | 45043/61904 [57:14<6:55:33,  1.48s/it]
 73%|███████▎  | 45044/61904 [57:15<6:42:27,  1.43s/it]
 73%|███████▎  | 45045/61904 [57:16<6:35:16,  1.41s/it]
 73%|███████▎  | 45046/61904 [57:18<6:44:31,  1.44s/it]
 73%|███████▎  | 45047/61904 [57:19<6:49:49,  1.46s/it]
 73%|███████▎  | 45048/61904 [57:21<6:36:03,  1.41s/it]
 73%|███████▎  | 45049/61904 [57:22<6:19:43,  1.35s/it]
 73%|███████▎  | 45050/61904 [57:23<6:36:58,  1.41s/it]
 73%|███████▎  | 45051/61904 [57:25<6:28:40,  1.38s/it]
 73%|███████▎  | 45052/61904 [57:26<6:29:41,  1.39s/it]
 73%|███████▎  | 45053/61904 [57:27<6:26:43,  1.38s/it]
 73%|███████▎  | 45054/61904 [57:29<6:32:57,  1.40s/it]
 73%|███████▎  | 45055/61904 [57:30<6:24:52,  1.37s/it]
 73%|███████▎  | 45056/61904 [57:32<6:23:38,  1.37s/it]
 73%|███████▎  | 45057/61904 [57:33<6:26:46,  1.38s/it]
 73%|███████▎  | 45058/61904 [57:34<6:34:17,  1.40s/it]
 73%|███████▎  | 45059/61904 [57:36<6:32:19,  1.40s/it]
 73%|███████▎  | 45060/61904 [57:37<6:40:36,  1.43s/it]
                                                       
{'loss': 2.4594, 'learning_rate': 1.2729806819655126e-07, 'epoch': 11.65}

 73%|███████▎  | 45060/61904 [57:37<6:40:36,  1.43s/it]
 73%|███████▎  | 45061/61904 [57:39<6:49:51,  1.46s/it]
 73%|███████▎  | 45062/61904 [57:40<6:42:13,  1.43s/it]
 73%|███████▎  | 45063/61904 [57:42<6:55:49,  1.48s/it]
 73%|███████▎  | 45064/61904 [57:43<6:45:43,  1.45s/it]
 73%|███████▎  | 45065/61904 [57:44<6:33:54,  1.40s/it]
 73%|███████▎  | 45066/61904 [57:46<6:36:41,  1.41s/it]
 73%|███████▎  | 45067/61904 [57:47<6:26:21,  1.38s/it]
 73%|███████▎  | 45068/61904 [57:49<6:37:10,  1.42s/it]
 73%|███████▎  | 45069/61904 [57:50<6:40:02,  1.43s/it]
 73%|███████▎  | 45070/61904 [57:51<6:30:07,  1.39s/it]
 73%|███████▎  | 45071/61904 [57:53<6:27:29,  1.38s/it]
 73%|███████▎  | 45072/61904 [57:54<6:19:23,  1.35s/it]
 73%|███████▎  | 45073/61904 [57:55<6:17:28,  1.35s/it]
 73%|███████▎  | 45074/61904 [57:57<6:17:53,  1.35s/it]
 73%|███████▎  | 45075/61904 [57:58<6:13:50,  1.33s/it]
 73%|███████▎  | 45076/61904 [57:59<6:20:26,  1.36s/it]
 73%|███████▎  | 45077/61904 [58:01<6:13:38,  1.33s/it]
 73%|███████▎  | 45078/61904 [58:02<6:23:01,  1.37s/it]
 73%|███████▎  | 45079/61904 [58:04<6:21:35,  1.36s/it]
 73%|███████▎  | 45080/61904 [58:05<6:16:51,  1.34s/it]
                                                       
{'loss': 2.495, 'learning_rate': 1.2726565538700895e-07, 'epoch': 11.65}

 73%|███████▎  | 45080/61904 [58:05<6:16:51,  1.34s/it]
 73%|███████▎  | 45081/61904 [58:06<6:14:58,  1.34s/it]
 73%|███████▎  | 45082/61904 [58:08<6:35:54,  1.41s/it]
 73%|███████▎  | 45083/61904 [58:09<6:36:54,  1.42s/it]
 73%|███████▎  | 45084/61904 [58:11<6:37:03,  1.42s/it]
 73%|███████▎  | 45085/61904 [58:12<6:34:01,  1.41s/it]
 73%|███████▎  | 45086/61904 [58:13<6:30:42,  1.39s/it]
 73%|███████▎  | 45087/61904 [58:15<6:36:14,  1.41s/it]
 73%|███████▎  | 45088/61904 [58:16<6:31:13,  1.40s/it]
 73%|███████▎  | 45089/61904 [58:17<6:20:50,  1.36s/it]
 73%|███████▎  | 45090/61904 [58:19<6:23:39,  1.37s/it]
 73%|███████▎  | 45091/61904 [58:20<6:18:26,  1.35s/it]
 73%|███████▎  | 45092/61904 [58:22<6:22:17,  1.36s/it]
 73%|███████▎  | 45093/61904 [58:23<6:36:41,  1.42s/it]
 73%|███████▎  | 45094/61904 [58:24<6:35:30,  1.41s/it]
 73%|███████▎  | 45095/61904 [58:26<6:39:45,  1.43s/it]
 73%|███████▎  | 45096/61904 [58:27<6:34:02,  1.41s/it]
 73%|███████▎  | 45097/61904 [58:29<6:28:59,  1.39s/it]
 73%|███████▎  | 45098/61904 [58:30<6:29:24,  1.39s/it]
 73%|███████▎  | 45099/61904 [58:31<6:25:02,  1.37s/it]
 73%|███████▎  | 45100/61904 [58:33<6:25:39,  1.38s/it]
                                                       
{'loss': 2.5174, 'learning_rate': 1.272332425774666e-07, 'epoch': 11.66}

 73%|███████▎  | 45100/61904 [58:33<6:25:39,  1.38s/it]
 73%|███████▎  | 45101/61904 [58:34<6:38:03,  1.42s/it]
 73%|███████▎  | 45102/61904 [58:36<6:32:41,  1.40s/it]
 73%|███████▎  | 45103/61904 [58:37<6:33:49,  1.41s/it]
 73%|███████▎  | 45104/61904 [58:38<6:23:38,  1.37s/it]
 73%|███████▎  | 45105/61904 [58:40<6:11:34,  1.33s/it]
 73%|███████▎  | 45106/61904 [58:41<6:22:46,  1.37s/it]
 73%|███████▎  | 45107/61904 [58:42<6:23:40,  1.37s/it]
 73%|███████▎  | 45108/61904 [58:44<6:27:19,  1.38s/it]
 73%|███████▎  | 45109/61904 [58:45<6:26:28,  1.38s/it]
 73%|███████▎  | 45110/61904 [58:47<6:31:46,  1.40s/it]
 73%|███████▎  | 45111/61904 [58:48<6:29:27,  1.39s/it]
 73%|███████▎  | 45112/61904 [58:49<6:19:41,  1.36s/it]
 73%|███████▎  | 45113/61904 [58:51<6:11:57,  1.33s/it]
 73%|███████▎  | 45114/61904 [58:52<6:18:39,  1.35s/it]
 73%|███████▎  | 45115/61904 [58:53<6:23:10,  1.37s/it]
 73%|███████▎  | 45116/61904 [58:55<6:31:42,  1.40s/it]
 73%|███████▎  | 45117/61904 [58:56<6:43:39,  1.44s/it]
 73%|███████▎  | 45118/61904 [58:58<6:31:30,  1.40s/it]
 73%|███████▎  | 45119/61904 [58:59<6:29:17,  1.39s/it]
 73%|███████▎  | 45120/61904 [59:00<6:20:59,  1.36s/it]
                                                       
{'loss': 2.4223, 'learning_rate': 1.2720082976792427e-07, 'epoch': 11.66}

 73%|███████▎  | 45120/61904 [59:00<6:20:59,  1.36s/it]
 73%|███████▎  | 45121/61904 [59:02<6:15:50,  1.34s/it]
 73%|███████▎  | 45122/61904 [59:03<6:17:35,  1.35s/it]
 73%|███████▎  | 45123/61904 [59:04<6:11:53,  1.33s/it]
 73%|███████▎  | 45124/61904 [59:06<6:22:01,  1.37s/it]
 73%|███████▎  | 45125/61904 [59:07<6:32:29,  1.40s/it]
 73%|███████▎  | 45126/61904 [59:09<6:32:13,  1.40s/it]
 73%|███████▎  | 45127/61904 [59:10<6:31:45,  1.40s/it]
 73%|███████▎  | 45128/61904 [59:11<6:36:05,  1.42s/it]
 73%|███████▎  | 45129/61904 [59:13<6:33:50,  1.41s/it]
 73%|███████▎  | 45130/61904 [59:14<6:32:02,  1.40s/it]
 73%|███████▎  | 45131/61904 [59:16<6:39:34,  1.43s/it]
 73%|███████▎  | 45132/61904 [59:17<6:26:05,  1.38s/it]
 73%|███████▎  | 45133/61904 [59:18<6:16:13,  1.35s/it]
 73%|███████▎  | 45134/61904 [59:20<6:08:12,  1.32s/it]
 73%|███████▎  | 45135/61904 [59:21<6:03:18,  1.30s/it]
 73%|███████▎  | 45136/61904 [59:22<6:08:04,  1.32s/it]
 73%|███████▎  | 45137/61904 [59:24<6:12:49,  1.33s/it]
 73%|███████▎  | 45138/61904 [59:25<6:14:41,  1.34s/it]
 73%|███████▎  | 45139/61904 [59:26<6:25:11,  1.38s/it]
 73%|███████▎  | 45140/61904 [59:28<6:37:16,  1.42s/it]
                                                       
{'loss': 2.4523, 'learning_rate': 1.2716841695838196e-07, 'epoch': 11.67}

 73%|███████▎  | 45140/61904 [59:28<6:37:16,  1.42s/it]
 73%|███████▎  | 45141/61904 [59:29<6:52:52,  1.48s/it]
 73%|███████▎  | 45142/61904 [59:31<6:34:54,  1.41s/it]
 73%|███████▎  | 45143/61904 [59:32<6:37:06,  1.42s/it]
 73%|███████▎  | 45144/61904 [59:34<6:37:03,  1.42s/it]
 73%|███████▎  | 45145/61904 [59:35<6:27:50,  1.39s/it]
 73%|███████▎  | 45146/61904 [59:36<6:25:38,  1.38s/it]
 73%|███████▎  | 45147/61904 [59:38<6:31:51,  1.40s/it]
 73%|███████▎  | 45148/61904 [59:39<6:29:01,  1.39s/it]
 73%|███████▎  | 45149/61904 [59:40<6:26:04,  1.38s/it]
 73%|███████▎  | 45150/61904 [59:42<6:29:57,  1.40s/it]
 73%|███████▎  | 45151/61904 [59:43<6:39:28,  1.43s/it]
 73%|███████▎  | 45152/61904 [59:45<6:38:04,  1.43s/it]
 73%|███████▎  | 45153/61904 [59:46<6:25:48,  1.38s/it]
 73%|███████▎  | 45154/61904 [59:48<6:34:05,  1.41s/it]
 73%|███████▎  | 45155/61904 [59:49<6:33:06,  1.41s/it]
 73%|███████▎  | 45156/61904 [59:50<6:27:27,  1.39s/it]
 73%|███████▎  | 45157/61904 [59:52<6:16:31,  1.35s/it]
 73%|███████▎  | 45158/61904 [59:53<6:15:09,  1.34s/it]
 73%|███████▎  | 45159/61904 [59:54<6:12:07,  1.33s/it]
 73%|███████▎  | 45160/61904 [59:55<6:06:53,  1.31s/it]
                                                       
{'loss': 2.4271, 'learning_rate': 1.2713600414883962e-07, 'epoch': 11.67}

 73%|███████▎  | 45160/61904 [59:55<6:06:53,  1.31s/it]
 73%|███████▎  | 45161/61904 [59:57<6:13:10,  1.34s/it]
 73%|███████▎  | 45162/61904 [59:58<6:14:30,  1.34s/it]
 73%|███████▎  | 45163/61904 [59:59<6:04:17,  1.31s/it]
 73%|███████▎  | 45164/61904 [1:00:01<6:03:51,  1.30s/it]
 73%|███████▎  | 45165/61904 [1:00:02<6:06:01,  1.31s/it]
 73%|███████▎  | 45166/61904 [1:00:03<6:06:17,  1.31s/it]
 73%|███████▎  | 45167/61904 [1:00:05<6:04:32,  1.31s/it]
 73%|███████▎  | 45168/61904 [1:00:06<6:07:17,  1.32s/it]
 73%|███████▎  | 45169/61904 [1:00:07<6:16:15,  1.35s/it]
 73%|███████▎  | 45170/61904 [1:00:09<6:11:40,  1.33s/it]
 73%|███████▎  | 45171/61904 [1:00:10<6:19:59,  1.36s/it]
 73%|███████▎  | 45172/61904 [1:00:12<6:24:58,  1.38s/it]
 73%|███████▎  | 45173/61904 [1:00:13<6:17:49,  1.35s/it]
 73%|███████▎  | 45174/61904 [1:00:14<6:12:31,  1.34s/it]
 73%|███████▎  | 45175/61904 [1:00:16<6:12:37,  1.34s/it]
 73%|███████▎  | 45176/61904 [1:00:17<6:15:55,  1.35s/it]
 73%|███████▎  | 45177/61904 [1:00:18<6:10:51,  1.33s/it]
 73%|███████▎  | 45178/61904 [1:00:19<6:03:05,  1.30s/it]
 73%|███████▎  | 45179/61904 [1:00:21<6:07:23,  1.32s/it]
 73%|███████▎  | 45180/61904 [1:00:22<6:09:01,  1.32s/it]
                                                         
{'loss': 2.5235, 'learning_rate': 1.2710359133929728e-07, 'epoch': 11.68}

 73%|███████▎  | 45180/61904 [1:00:22<6:09:01,  1.32s/it]
 73%|███████▎  | 45181/61904 [1:00:23<6:07:31,  1.32s/it]
 73%|███████▎  | 45182/61904 [1:00:25<6:05:17,  1.31s/it]
 73%|███████▎  | 45183/61904 [1:00:26<6:23:11,  1.37s/it]
 73%|███████▎  | 45184/61904 [1:00:28<6:21:16,  1.37s/it]
 73%|███████▎  | 45185/61904 [1:00:29<6:29:27,  1.40s/it]
 73%|███████▎  | 45186/61904 [1:00:31<6:41:32,  1.44s/it]
 73%|███████▎  | 45187/61904 [1:00:32<6:36:29,  1.42s/it]
 73%|███████▎  | 45188/61904 [1:00:33<6:30:03,  1.40s/it]
 73%|███████▎  | 45189/61904 [1:00:35<6:26:06,  1.39s/it]
 73%|███████▎  | 45190/61904 [1:00:36<6:16:34,  1.35s/it]
 73%|███████▎  | 45191/61904 [1:00:37<6:18:06,  1.36s/it]
 73%|███████▎  | 45192/61904 [1:00:39<6:24:45,  1.38s/it]
 73%|███████▎  | 45193/61904 [1:00:40<6:27:18,  1.39s/it]
 73%|███████▎  | 45194/61904 [1:00:42<6:30:34,  1.40s/it]
 73%|███████▎  | 45195/61904 [1:00:43<6:30:10,  1.40s/it]
 73%|███████▎  | 45196/61904 [1:00:44<6:18:45,  1.36s/it]
 73%|███████▎  | 45197/61904 [1:00:46<6:17:28,  1.36s/it]
 73%|███████▎  | 45198/61904 [1:00:47<6:25:31,  1.38s/it]
 73%|███████▎  | 45199/61904 [1:00:48<6:18:18,  1.36s/it]
 73%|███████▎  | 45200/61904 [1:00:50<6:12:33,  1.34s/it]
                                                         
{'loss': 2.4666, 'learning_rate': 1.2707117852975494e-07, 'epoch': 11.68}

 73%|███████▎  | 45200/61904 [1:00:50<6:12:33,  1.34s/it]
 73%|███████▎  | 45201/61904 [1:00:51<6:14:23,  1.34s/it]
 73%|███████▎  | 45202/61904 [1:00:52<6:11:25,  1.33s/it]
 73%|███████▎  | 45203/61904 [1:00:54<6:17:31,  1.36s/it]
 73%|███████▎  | 45204/61904 [1:00:55<6:09:51,  1.33s/it]
 73%|███████▎  | 45205/61904 [1:00:57<6:56:35,  1.50s/it]
 73%|███████▎  | 45206/61904 [1:00:58<6:40:46,  1.44s/it]
 73%|███████▎  | 45207/61904 [1:00:59<6:30:14,  1.40s/it]
 73%|███████▎  | 45208/61904 [1:01:01<6:26:12,  1.39s/it]
 73%|███████▎  | 45209/61904 [1:01:02<6:27:05,  1.39s/it]
 73%|███████▎  | 45210/61904 [1:01:03<6:16:03,  1.35s/it]
 73%|███████▎  | 45211/61904 [1:01:05<6:25:36,  1.39s/it]
 73%|███████▎  | 45212/61904 [1:01:06<6:18:47,  1.36s/it]
 73%|███████▎  | 45213/61904 [1:01:08<6:21:30,  1.37s/it]
 73%|███████▎  | 45214/61904 [1:01:09<6:20:42,  1.37s/it]
 73%|███████▎  | 45215/61904 [1:01:10<6:03:56,  1.31s/it]
 73%|███████▎  | 45216/61904 [1:01:11<5:58:11,  1.29s/it]
 73%|███████▎  | 45217/61904 [1:01:13<5:57:22,  1.29s/it]
 73%|███████▎  | 45218/61904 [1:01:14<6:08:50,  1.33s/it]
 73%|███████▎  | 45219/61904 [1:01:15<6:06:52,  1.32s/it]
 73%|███████▎  | 45220/61904 [1:01:17<6:13:10,  1.34s/it]
                                                         
{'loss': 2.4413, 'learning_rate': 1.2703876572021263e-07, 'epoch': 11.69}

 73%|███████▎  | 45220/61904 [1:01:17<6:13:10,  1.34s/it]
 73%|███████▎  | 45221/61904 [1:01:18<6:17:47,  1.36s/it]
 73%|███████▎  | 45222/61904 [1:01:20<6:11:01,  1.33s/it]
 73%|███████▎  | 45223/61904 [1:01:21<6:18:40,  1.36s/it]
 73%|███████▎  | 45224/61904 [1:01:22<6:27:04,  1.39s/it]
 73%|███████▎  | 45225/61904 [1:01:24<6:19:20,  1.36s/it]
 73%|███████▎  | 45226/61904 [1:01:25<6:11:40,  1.34s/it]
 73%|███████▎  | 45227/61904 [1:01:26<6:03:29,  1.31s/it]
 73%|███████▎  | 45228/61904 [1:01:27<6:00:21,  1.30s/it]
 73%|███████▎  | 45229/61904 [1:01:29<6:05:07,  1.31s/it]
 73%|███████▎  | 45230/61904 [1:01:30<6:15:53,  1.35s/it]
 73%|███████▎  | 45231/61904 [1:01:32<6:19:40,  1.37s/it]
 73%|███████▎  | 45232/61904 [1:01:33<6:20:52,  1.37s/it]
 73%|███████▎  | 45233/61904 [1:01:34<6:15:49,  1.35s/it]
 73%|███████▎  | 45234/61904 [1:01:36<6:10:09,  1.33s/it]
 73%|███████▎  | 45235/61904 [1:01:37<6:13:40,  1.35s/it]
 73%|███████▎  | 45236/61904 [1:01:39<6:27:58,  1.40s/it]
 73%|███████▎  | 45237/61904 [1:01:40<6:22:35,  1.38s/it]
 73%|███████▎  | 45238/61904 [1:01:41<6:26:54,  1.39s/it]
 73%|███████▎  | 45239/61904 [1:01:43<6:28:39,  1.40s/it]
 73%|███████▎  | 45240/61904 [1:01:44<6:26:33,  1.39s/it]
                                                         
{'loss': 2.422, 'learning_rate': 1.270063529106703e-07, 'epoch': 11.69}

 73%|███████▎  | 45240/61904 [1:01:44<6:26:33,  1.39s/it]
 73%|███████▎  | 45241/61904 [1:01:45<6:09:25,  1.33s/it]
 73%|███████▎  | 45242/61904 [1:01:47<6:18:00,  1.36s/it]
 73%|███████▎  | 45243/61904 [1:01:48<6:23:34,  1.38s/it]
 73%|███████▎  | 45244/61904 [1:01:50<6:30:24,  1.41s/it]
 73%|███████▎  | 45245/61904 [1:01:51<6:24:40,  1.39s/it]
 73%|███████▎  | 45246/61904 [1:01:52<6:16:07,  1.35s/it]
 73%|███████▎  | 45247/61904 [1:01:54<6:22:02,  1.38s/it]
 73%|███████▎  | 45248/61904 [1:01:55<6:22:46,  1.38s/it]
 73%|███████▎  | 45249/61904 [1:01:56<6:21:18,  1.37s/it]
 73%|███████▎  | 45250/61904 [1:01:58<6:10:06,  1.33s/it]
 73%|███████▎  | 45251/61904 [1:01:59<6:18:15,  1.36s/it]
 73%|███████▎  | 45252/61904 [1:02:00<6:14:27,  1.35s/it]
 73%|███████▎  | 45253/61904 [1:02:02<6:11:57,  1.34s/it]
 73%|███████▎  | 45254/61904 [1:02:03<6:29:31,  1.40s/it]
 73%|███████▎  | 45255/61904 [1:02:05<6:22:03,  1.38s/it]
 73%|███████▎  | 45256/61904 [1:02:06<6:31:26,  1.41s/it]
 73%|███████▎  | 45257/61904 [1:02:08<6:34:09,  1.42s/it]
 73%|███████▎  | 45258/61904 [1:02:09<6:27:18,  1.40s/it]
 73%|███████▎  | 45259/61904 [1:02:10<6:19:11,  1.37s/it]
 73%|███████▎  | 45260/61904 [1:02:11<6:14:35,  1.35s/it]
                                                         
{'loss': 2.5057, 'learning_rate': 1.2697394010112796e-07, 'epoch': 11.7}

 73%|███████▎  | 45260/61904 [1:02:11<6:14:35,  1.35s/it]
 73%|███████▎  | 45261/61904 [1:02:13<6:14:58,  1.35s/it]
 73%|███████▎  | 45262/61904 [1:02:14<6:17:30,  1.36s/it]
 73%|███████▎  | 45263/61904 [1:02:16<6:22:41,  1.38s/it]
 73%|███████▎  | 45264/61904 [1:02:17<6:10:44,  1.34s/it]
 73%|███████▎  | 45265/61904 [1:02:18<6:16:17,  1.36s/it]
 73%|███████▎  | 45266/61904 [1:02:20<6:08:30,  1.33s/it]
 73%|███████▎  | 45267/61904 [1:02:21<6:11:39,  1.34s/it]
 73%|███████▎  | 45268/61904 [1:02:22<6:03:47,  1.31s/it]
 73%|███████▎  | 45269/61904 [1:02:24<6:16:18,  1.36s/it]
 73%|███████▎  | 45270/61904 [1:02:25<6:15:19,  1.35s/it]
 73%|███████▎  | 45271/61904 [1:02:26<6:07:52,  1.33s/it]
 73%|███████▎  | 45272/61904 [1:02:28<6:10:33,  1.34s/it]
 73%|███████▎  | 45273/61904 [1:02:29<6:14:23,  1.35s/it]
 73%|███████▎  | 45274/61904 [1:02:30<6:12:33,  1.34s/it]
 73%|███████▎  | 45275/61904 [1:02:32<6:16:11,  1.36s/it]
 73%|███████▎  | 45276/61904 [1:02:33<6:19:07,  1.37s/it]
 73%|███████▎  | 45277/61904 [1:02:34<6:16:57,  1.36s/it]
 73%|███████▎  | 45278/61904 [1:02:36<6:29:56,  1.41s/it]
 73%|███████▎  | 45279/61904 [1:02:37<6:28:14,  1.40s/it]
 73%|███████▎  | 45280/61904 [1:02:39<6:14:19,  1.35s/it]
                                                         
{'loss': 2.5153, 'learning_rate': 1.2694152729158562e-07, 'epoch': 11.7}

 73%|███████▎  | 45280/61904 [1:02:39<6:14:19,  1.35s/it]
 73%|███████▎  | 45281/61904 [1:02:40<6:18:48,  1.37s/it]
 73%|███████▎  | 45282/61904 [1:02:41<6:13:11,  1.35s/it]
 73%|███████▎  | 45283/61904 [1:02:43<6:22:33,  1.38s/it]
 73%|███████▎  | 45284/61904 [1:02:44<6:13:15,  1.35s/it]
 73%|███████▎  | 45285/61904 [1:02:45<6:19:20,  1.37s/it]
 73%|███████▎  | 45286/61904 [1:02:47<6:13:04,  1.35s/it]
 73%|███████▎  | 45287/61904 [1:02:48<6:16:43,  1.36s/it]
 73%|███████▎  | 45288/61904 [1:02:49<6:18:46,  1.37s/it]
 73%|███████▎  | 45289/61904 [1:02:51<6:11:23,  1.34s/it]
 73%|███████▎  | 45290/61904 [1:02:52<6:06:40,  1.32s/it]
 73%|███████▎  | 45291/61904 [1:02:53<6:13:00,  1.35s/it]
 73%|███████▎  | 45292/61904 [1:02:55<6:10:10,  1.34s/it]
 73%|███████▎  | 45293/61904 [1:02:56<6:15:43,  1.36s/it]
 73%|███████▎  | 45294/61904 [1:02:58<6:18:09,  1.37s/it]
 73%|███████▎  | 45295/61904 [1:02:59<6:20:13,  1.37s/it]
 73%|███████▎  | 45296/61904 [1:03:00<6:14:39,  1.35s/it]
 73%|███████▎  | 45297/61904 [1:03:02<6:18:31,  1.37s/it]
 73%|███████▎  | 45298/61904 [1:03:03<6:22:21,  1.38s/it]
 73%|███████▎  | 45299/61904 [1:03:04<6:15:47,  1.36s/it]
 73%|███████▎  | 45300/61904 [1:03:06<6:14:33,  1.35s/it]
                                                         
{'loss': 2.4894, 'learning_rate': 1.269091144820433e-07, 'epoch': 11.71}

 73%|███████▎  | 45300/61904 [1:03:06<6:14:33,  1.35s/it]
 73%|███████▎  | 45301/61904 [1:03:07<6:36:24,  1.43s/it]
 73%|███████▎  | 45302/61904 [1:03:09<6:51:19,  1.49s/it]
 73%|███████▎  | 45303/61904 [1:03:10<6:30:01,  1.41s/it]
 73%|███████▎  | 45304/61904 [1:03:12<6:37:03,  1.44s/it]
 73%|███████▎  | 45305/61904 [1:03:13<6:46:04,  1.47s/it]
 73%|███████▎  | 45306/61904 [1:03:15<6:33:29,  1.42s/it]
 73%|███████▎  | 45307/61904 [1:03:16<6:38:49,  1.44s/it]
 73%|███████▎  | 45308/61904 [1:03:17<6:31:37,  1.42s/it]
 73%|███████▎  | 45309/61904 [1:03:19<6:24:39,  1.39s/it]
 73%|███████▎  | 45310/61904 [1:03:20<6:24:28,  1.39s/it]
 73%|███████▎  | 45311/61904 [1:03:21<6:23:52,  1.39s/it]
 73%|███████▎  | 45312/61904 [1:03:23<6:29:09,  1.41s/it]
 73%|███████▎  | 45313/61904 [1:03:24<6:18:42,  1.37s/it]
 73%|███████▎  | 45314/61904 [1:03:26<6:19:06,  1.37s/it]
 73%|███████▎  | 45315/61904 [1:03:27<6:11:23,  1.34s/it]
 73%|███████▎  | 45316/61904 [1:03:28<6:22:26,  1.38s/it]
 73%|███████▎  | 45317/61904 [1:03:30<6:23:21,  1.39s/it]
 73%|███████▎  | 45318/61904 [1:03:31<6:13:19,  1.35s/it]
 73%|███████▎  | 45319/61904 [1:03:32<6:22:46,  1.38s/it]
 73%|███████▎  | 45320/61904 [1:03:34<6:20:48,  1.38s/it]
                                                         
{'loss': 2.5211, 'learning_rate': 1.2687670167250097e-07, 'epoch': 11.71}

 73%|███████▎  | 45320/61904 [1:03:34<6:20:48,  1.38s/it]
 73%|███████▎  | 45321/61904 [1:03:35<6:35:43,  1.43s/it]
 73%|███████▎  | 45322/61904 [1:03:37<6:39:16,  1.44s/it]
 73%|███████▎  | 45323/61904 [1:03:38<6:48:26,  1.48s/it]
 73%|███████▎  | 45324/61904 [1:03:40<6:44:35,  1.46s/it]
 73%|███████▎  | 45325/61904 [1:03:41<6:48:58,  1.48s/it]
 73%|███████▎  | 45326/61904 [1:03:43<6:56:03,  1.51s/it]
 73%|███████▎  | 45327/61904 [1:03:44<6:42:09,  1.46s/it]
 73%|███████▎  | 45328/61904 [1:03:46<6:28:14,  1.41s/it]
 73%|███████▎  | 45329/61904 [1:03:47<6:26:36,  1.40s/it]
 73%|███████▎  | 45330/61904 [1:03:48<6:13:27,  1.35s/it]
 73%|███████▎  | 45331/61904 [1:03:50<6:13:06,  1.35s/it]
 73%|███████▎  | 45332/61904 [1:03:51<6:15:12,  1.36s/it]
 73%|███████▎  | 45333/61904 [1:03:52<6:24:28,  1.39s/it]
 73%|███████▎  | 45334/61904 [1:03:54<6:26:22,  1.40s/it]
 73%|███████▎  | 45335/61904 [1:03:55<6:23:27,  1.39s/it]
 73%|███████▎  | 45336/61904 [1:03:56<6:16:34,  1.36s/it]
 73%|███████▎  | 45337/61904 [1:03:58<6:10:06,  1.34s/it]
 73%|███████▎  | 45338/61904 [1:03:59<6:21:45,  1.38s/it]
 73%|███████▎  | 45339/61904 [1:04:01<6:23:02,  1.39s/it]
 73%|███████▎  | 45340/61904 [1:04:02<6:43:54,  1.46s/it]
                                                         
{'loss': 2.4449, 'learning_rate': 1.2684428886295863e-07, 'epoch': 11.72}

 73%|███████▎  | 45340/61904 [1:04:02<6:43:54,  1.46s/it]
 73%|███████▎  | 45341/61904 [1:04:04<6:34:24,  1.43s/it]
 73%|███████▎  | 45342/61904 [1:04:05<6:22:37,  1.39s/it]
 73%|███████▎  | 45343/61904 [1:04:06<6:30:16,  1.41s/it]
 73%|███████▎  | 45344/61904 [1:04:08<6:36:01,  1.43s/it]
 73%|███████▎  | 45345/61904 [1:04:09<6:43:56,  1.46s/it]
 73%|███████▎  | 45346/61904 [1:04:11<6:40:18,  1.45s/it]
 73%|███████▎  | 45347/61904 [1:04:12<6:31:38,  1.42s/it]
 73%|███████▎  | 45348/61904 [1:04:13<6:21:00,  1.38s/it]
 73%|███████▎  | 45349/61904 [1:04:15<6:26:38,  1.40s/it]
 73%|███████▎  | 45350/61904 [1:04:16<6:29:33,  1.41s/it]
 73%|███████▎  | 45351/61904 [1:04:18<6:21:35,  1.38s/it]
 73%|███████▎  | 45352/61904 [1:04:19<6:12:32,  1.35s/it]
 73%|███████▎  | 45353/61904 [1:04:21<6:34:00,  1.43s/it]
 73%|███████▎  | 45354/61904 [1:04:22<6:24:11,  1.39s/it]
 73%|███████▎  | 45355/61904 [1:04:23<6:22:29,  1.39s/it]
 73%|███████▎  | 45356/61904 [1:04:25<6:36:37,  1.44s/it]
 73%|███████▎  | 45357/61904 [1:04:26<6:27:23,  1.40s/it]
 73%|███████▎  | 45358/61904 [1:04:27<6:23:38,  1.39s/it]
 73%|███████▎  | 45359/61904 [1:04:29<6:48:09,  1.48s/it]
 73%|███████▎  | 45360/61904 [1:04:31<6:43:39,  1.46s/it]
                                                         
{'loss': 2.4859, 'learning_rate': 1.268118760534163e-07, 'epoch': 11.72}

 73%|███████▎  | 45360/61904 [1:04:31<6:43:39,  1.46s/it]
 73%|███████▎  | 45361/61904 [1:04:32<6:31:43,  1.42s/it]
 73%|███████▎  | 45362/61904 [1:04:33<6:34:16,  1.43s/it]
 73%|███████▎  | 45363/61904 [1:04:35<6:28:15,  1.41s/it]
 73%|███████▎  | 45364/61904 [1:04:36<6:21:44,  1.38s/it]
 73%|███████▎  | 45365/61904 [1:04:38<6:34:56,  1.43s/it]
 73%|███████▎  | 45366/61904 [1:04:39<6:23:01,  1.39s/it]
 73%|███████▎  | 45367/61904 [1:04:40<6:16:08,  1.36s/it]
 73%|███████▎  | 45368/61904 [1:04:42<6:28:01,  1.41s/it]
 73%|███████▎  | 45369/61904 [1:04:43<6:51:08,  1.49s/it]
 73%|███████▎  | 45370/61904 [1:04:45<6:38:00,  1.44s/it]
 73%|███████▎  | 45371/61904 [1:04:46<6:18:34,  1.37s/it]
 73%|███████▎  | 45372/61904 [1:04:47<6:22:15,  1.39s/it]
 73%|███████▎  | 45373/61904 [1:04:49<6:29:30,  1.41s/it]
 73%|███████▎  | 45374/61904 [1:04:50<6:21:01,  1.38s/it]
 73%|███████▎  | 45375/61904 [1:04:51<6:19:23,  1.38s/it]
 73%|███████▎  | 45376/61904 [1:04:53<6:16:31,  1.37s/it]
 73%|███████▎  | 45377/61904 [1:04:54<6:05:33,  1.33s/it]
 73%|███████▎  | 45378/61904 [1:04:55<6:08:34,  1.34s/it]
 73%|███████▎  | 45379/61904 [1:04:57<6:18:39,  1.37s/it]
 73%|███████▎  | 45380/61904 [1:04:58<6:18:48,  1.38s/it]
                                                         
{'loss': 2.4578, 'learning_rate': 1.2677946324387398e-07, 'epoch': 11.73}

 73%|███████▎  | 45380/61904 [1:04:58<6:18:48,  1.38s/it]
 73%|███████▎  | 45381/61904 [1:05:00<6:17:04,  1.37s/it]
 73%|███████▎  | 45382/61904 [1:05:01<6:10:31,  1.35s/it]
 73%|███████▎  | 45383/61904 [1:05:02<6:07:14,  1.33s/it]
 73%|███████▎  | 45384/61904 [1:05:04<6:07:04,  1.33s/it]
 73%|███████▎  | 45385/61904 [1:05:05<6:17:36,  1.37s/it]
 73%|███████▎  | 45386/61904 [1:05:06<6:20:58,  1.38s/it]
 73%|███████▎  | 45387/61904 [1:05:08<6:22:12,  1.39s/it]
 73%|███████▎  | 45388/61904 [1:05:09<6:27:45,  1.41s/it]
 73%|███████▎  | 45389/61904 [1:05:11<6:33:44,  1.43s/it]
 73%|███████▎  | 45390/61904 [1:05:12<6:34:45,  1.43s/it]
 73%|███████▎  | 45391/61904 [1:05:14<6:44:13,  1.47s/it]
 73%|███████▎  | 45392/61904 [1:05:15<6:40:57,  1.46s/it]
 73%|███████▎  | 45393/61904 [1:05:17<6:38:32,  1.45s/it]
 73%|███████▎  | 45394/61904 [1:05:18<6:38:23,  1.45s/it]
 73%|███████▎  | 45395/61904 [1:05:19<6:31:09,  1.42s/it]
 73%|███████▎  | 45396/61904 [1:05:21<6:38:32,  1.45s/it]
 73%|███████▎  | 45397/61904 [1:05:22<6:31:25,  1.42s/it]
 73%|███████▎  | 45398/61904 [1:05:24<6:24:17,  1.40s/it]
 73%|███████▎  | 45399/61904 [1:05:25<6:19:25,  1.38s/it]
 73%|███████▎  | 45400/61904 [1:05:26<6:14:19,  1.36s/it]
                                                         
{'loss': 2.4715, 'learning_rate': 1.2674705043433164e-07, 'epoch': 11.73}

 73%|███████▎  | 45400/61904 [1:05:26<6:14:19,  1.36s/it]
 73%|███████▎  | 45401/61904 [1:05:28<6:19:18,  1.38s/it]
 73%|███████▎  | 45402/61904 [1:05:29<6:17:52,  1.37s/it]
 73%|███████▎  | 45403/61904 [1:05:30<6:08:35,  1.34s/it]
 73%|███████▎  | 45404/61904 [1:05:32<6:09:41,  1.34s/it]
 73%|███████▎  | 45405/61904 [1:05:33<6:19:38,  1.38s/it]
 73%|███████▎  | 45406/61904 [1:05:35<6:20:55,  1.39s/it]
 73%|███████▎  | 45407/61904 [1:05:36<6:15:32,  1.37s/it]
 73%|███████▎  | 45408/61904 [1:05:37<6:07:56,  1.34s/it]
 73%|███████▎  | 45409/61904 [1:05:39<6:19:46,  1.38s/it]
 73%|███████▎  | 45410/61904 [1:05:40<6:08:44,  1.34s/it]
 73%|███████▎  | 45411/61904 [1:05:41<6:30:57,  1.42s/it]
 73%|███████▎  | 45412/61904 [1:05:43<6:32:29,  1.43s/it]
 73%|███████▎  | 45413/61904 [1:05:44<6:41:46,  1.46s/it]
 73%|███████▎  | 45414/61904 [1:05:46<6:42:25,  1.46s/it]
 73%|███████▎  | 45415/61904 [1:05:47<6:36:37,  1.44s/it]
 73%|███████▎  | 45416/61904 [1:05:49<6:38:27,  1.45s/it]
 73%|███████▎  | 45417/61904 [1:05:50<6:32:49,  1.43s/it]
 73%|███████▎  | 45418/61904 [1:05:52<6:26:40,  1.41s/it]
 73%|███████▎  | 45419/61904 [1:05:53<6:21:34,  1.39s/it]
 73%|███████▎  | 45420/61904 [1:05:54<6:23:29,  1.40s/it]
                                                         
{'loss': 2.4258, 'learning_rate': 1.267146376247893e-07, 'epoch': 11.74}

 73%|███████▎  | 45420/61904 [1:05:54<6:23:29,  1.40s/it]
 73%|███████▎  | 45421/61904 [1:05:56<6:18:09,  1.38s/it]
 73%|███████▎  | 45422/61904 [1:05:57<6:18:20,  1.38s/it]
 73%|███████▎  | 45423/61904 [1:05:58<6:15:40,  1.37s/it]
 73%|███████▎  | 45424/61904 [1:06:00<6:09:55,  1.35s/it]
 73%|███████▎  | 45425/61904 [1:06:01<6:15:58,  1.37s/it]
 73%|███████▎  | 45426/61904 [1:06:02<6:17:56,  1.38s/it]
 73%|███████▎  | 45427/61904 [1:06:04<6:26:12,  1.41s/it]
 73%|███████▎  | 45428/61904 [1:06:05<6:12:45,  1.36s/it]
 73%|███████▎  | 45429/61904 [1:06:06<6:07:42,  1.34s/it]
 73%|███████▎  | 45430/61904 [1:06:08<6:11:02,  1.35s/it]
 73%|███████▎  | 45431/61904 [1:06:09<6:06:30,  1.33s/it]
 73%|███████▎  | 45432/61904 [1:06:11<6:23:51,  1.40s/it]
 73%|███████▎  | 45433/61904 [1:06:12<6:24:52,  1.40s/it]
 73%|███████▎  | 45434/61904 [1:06:13<6:25:02,  1.40s/it]
 73%|███████▎  | 45435/61904 [1:06:15<6:35:25,  1.44s/it]
 73%|███████▎  | 45436/61904 [1:06:16<6:27:58,  1.41s/it]
 73%|███████▎  | 45437/61904 [1:06:18<6:16:46,  1.37s/it]
 73%|███████▎  | 45438/61904 [1:06:19<6:08:21,  1.34s/it]
 73%|███████▎  | 45439/61904 [1:06:20<6:12:44,  1.36s/it]
 73%|███████▎  | 45440/61904 [1:06:22<6:09:41,  1.35s/it]
                                                         
{'loss': 2.4635, 'learning_rate': 1.26682224815247e-07, 'epoch': 11.74}

 73%|███████▎  | 45440/61904 [1:06:22<6:09:41,  1.35s/it]
 73%|███████▎  | 45441/61904 [1:06:23<6:16:09,  1.37s/it]
 73%|███████▎  | 45442/61904 [1:06:24<6:20:32,  1.39s/it]
 73%|███████▎  | 45443/61904 [1:06:26<6:21:36,  1.39s/it]
 73%|███████▎  | 45444/61904 [1:06:27<6:07:17,  1.34s/it]
 73%|███████▎  | 45445/61904 [1:06:28<6:09:03,  1.35s/it]
 73%|███████▎  | 45446/61904 [1:06:30<6:07:38,  1.34s/it]
 73%|███████▎  | 45447/61904 [1:06:31<6:09:06,  1.35s/it]
 73%|███████▎  | 45448/61904 [1:06:32<6:06:51,  1.34s/it]
 73%|███████▎  | 45449/61904 [1:06:34<6:18:11,  1.38s/it]
 73%|███████▎  | 45450/61904 [1:06:35<6:08:10,  1.34s/it]
 73%|███████▎  | 45451/61904 [1:06:37<6:16:15,  1.37s/it]
 73%|███████▎  | 45452/61904 [1:06:38<6:13:14,  1.36s/it]
 73%|███████▎  | 45453/61904 [1:06:39<6:12:04,  1.36s/it]
 73%|███████▎  | 45454/61904 [1:06:41<6:36:39,  1.45s/it]
 73%|███████▎  | 45455/61904 [1:06:42<6:29:31,  1.42s/it]
 73%|███████▎  | 45456/61904 [1:06:44<6:22:16,  1.39s/it]
 73%|███████▎  | 45457/61904 [1:06:45<6:23:58,  1.40s/it]
 73%|███████▎  | 45458/61904 [1:06:47<6:34:37,  1.44s/it]
 73%|███████▎  | 45459/61904 [1:06:48<6:33:43,  1.44s/it]
 73%|███████▎  | 45460/61904 [1:06:49<6:21:19,  1.39s/it]
                                                         
{'loss': 2.4803, 'learning_rate': 1.2664981200570465e-07, 'epoch': 11.75}

 73%|███████▎  | 45460/61904 [1:06:49<6:21:19,  1.39s/it]
 73%|███████▎  | 45461/61904 [1:06:51<6:08:23,  1.34s/it]
 73%|███████▎  | 45462/61904 [1:06:52<6:02:46,  1.32s/it]
 73%|███████▎  | 45463/61904 [1:06:53<6:13:12,  1.36s/it]
 73%|███████▎  | 45464/61904 [1:06:55<6:17:32,  1.38s/it]
 73%|███████▎  | 45465/61904 [1:06:56<6:13:39,  1.36s/it]
 73%|███████▎  | 45466/61904 [1:06:57<6:05:42,  1.33s/it]
 73%|███████▎  | 45467/61904 [1:06:59<6:26:52,  1.41s/it]
 73%|███████▎  | 45468/61904 [1:07:00<6:25:49,  1.41s/it]
 73%|███████▎  | 45469/61904 [1:07:02<6:20:54,  1.39s/it]
 73%|███████▎  | 45470/61904 [1:07:03<6:37:00,  1.45s/it]
 73%|███████▎  | 45471/61904 [1:07:05<6:29:12,  1.42s/it]
 73%|███████▎  | 45472/61904 [1:07:06<6:14:46,  1.37s/it]
 73%|███████▎  | 45473/61904 [1:07:07<6:08:34,  1.35s/it]
 73%|███████▎  | 45474/61904 [1:07:08<6:05:35,  1.34s/it]
 73%|███████▎  | 45475/61904 [1:07:10<6:13:49,  1.37s/it]
 73%|███████▎  | 45476/61904 [1:07:11<6:23:59,  1.40s/it]
 73%|███████▎  | 45477/61904 [1:07:13<6:11:51,  1.36s/it]
 73%|███████▎  | 45478/61904 [1:07:14<6:10:23,  1.35s/it]
 73%|███████▎  | 45479/61904 [1:07:15<6:11:50,  1.36s/it]
 73%|███████▎  | 45480/61904 [1:07:17<6:13:03,  1.36s/it]
                                                         
{'loss': 2.4333, 'learning_rate': 1.2661739919616232e-07, 'epoch': 11.75}

 73%|███████▎  | 45480/61904 [1:07:17<6:13:03,  1.36s/it]
 73%|███████▎  | 45481/61904 [1:07:18<6:23:09,  1.40s/it]
 73%|███████▎  | 45482/61904 [1:07:20<6:26:12,  1.41s/it]
 73%|███████▎  | 45483/61904 [1:07:21<6:13:03,  1.36s/it]
 73%|███████▎  | 45484/61904 [1:07:22<6:09:37,  1.35s/it]
 73%|███████▎  | 45485/61904 [1:07:24<6:15:26,  1.37s/it]
 73%|███████▎  | 45486/61904 [1:07:25<6:10:33,  1.35s/it]
 73%|███████▎  | 45487/61904 [1:07:26<6:24:38,  1.41s/it]
 73%|███████▎  | 45488/61904 [1:07:28<6:15:44,  1.37s/it]
 73%|███████▎  | 45489/61904 [1:07:29<6:13:31,  1.37s/it]
 73%|███████▎  | 45490/61904 [1:07:30<6:11:37,  1.36s/it]
 73%|███████▎  | 45491/61904 [1:07:32<6:18:38,  1.38s/it]
 73%|███████▎  | 45492/61904 [1:07:33<6:10:41,  1.36s/it]
 73%|███████▎  | 45493/61904 [1:07:35<6:11:31,  1.36s/it]
 73%|███████▎  | 45494/61904 [1:07:36<6:23:20,  1.40s/it]
 73%|███████▎  | 45495/61904 [1:07:37<6:14:20,  1.37s/it]
 73%|███████▎  | 45496/61904 [1:07:39<6:07:37,  1.34s/it]
 73%|███████▎  | 45497/61904 [1:07:40<6:15:34,  1.37s/it]
 73%|███████▎  | 45498/61904 [1:07:41<6:11:36,  1.36s/it]
 73%|███████▎  | 45499/61904 [1:07:43<6:10:00,  1.35s/it]
 74%|███████▎  | 45500/61904 [1:07:44<6:10:35,  1.36s/it]
                                                         
{'loss': 2.5486, 'learning_rate': 1.2658498638661998e-07, 'epoch': 11.76}

 74%|███████▎  | 45500/61904 [1:07:44<6:10:35,  1.36s/it]
 74%|███████▎  | 45501/61904 [1:07:45<6:14:10,  1.37s/it]
 74%|███████▎  | 45502/61904 [1:07:47<6:11:25,  1.36s/it]
 74%|███████▎  | 45503/61904 [1:07:48<6:12:14,  1.36s/it]
 74%|███████▎  | 45504/61904 [1:07:50<6:06:53,  1.34s/it]
 74%|███████▎  | 45505/61904 [1:07:51<6:08:45,  1.35s/it]
 74%|███████▎  | 45506/61904 [1:07:52<6:03:36,  1.33s/it]
 74%|███████▎  | 45507/61904 [1:07:54<6:16:54,  1.38s/it]
 74%|███████▎  | 45508/61904 [1:07:55<6:11:23,  1.36s/it]
 74%|███████▎  | 45509/61904 [1:07:56<6:00:17,  1.32s/it]
 74%|███████▎  | 45510/61904 [1:07:58<6:07:58,  1.35s/it]
 74%|███████▎  | 45511/61904 [1:07:59<6:33:20,  1.44s/it]
 74%|███████▎  | 45512/61904 [1:08:01<6:33:09,  1.44s/it]
 74%|███████▎  | 45513/61904 [1:08:02<6:39:50,  1.46s/it]
 74%|███████▎  | 45514/61904 [1:08:04<6:29:11,  1.42s/it]
 74%|███████▎  | 45515/61904 [1:08:05<6:17:08,  1.38s/it]
 74%|███████▎  | 45516/61904 [1:08:06<6:12:00,  1.36s/it]
 74%|███████▎  | 45517/61904 [1:08:08<6:18:57,  1.39s/it]
 74%|███████▎  | 45518/61904 [1:08:09<6:12:35,  1.36s/it]
 74%|███████▎  | 45519/61904 [1:08:10<6:27:04,  1.42s/it]
 74%|███████▎  | 45520/61904 [1:08:12<6:30:28,  1.43s/it]
                                                         
{'loss': 2.4803, 'learning_rate': 1.2655257357707767e-07, 'epoch': 11.77}

 74%|███████▎  | 45520/61904 [1:08:12<6:30:28,  1.43s/it]
 74%|███████▎  | 45521/61904 [1:08:13<6:16:20,  1.38s/it]
 74%|███████▎  | 45522/61904 [1:08:14<6:03:22,  1.33s/it]
 74%|███████▎  | 45523/61904 [1:08:16<6:11:13,  1.36s/it]
 74%|███████▎  | 45524/61904 [1:08:17<6:17:38,  1.38s/it]
 74%|███████▎  | 45525/61904 [1:08:19<6:19:01,  1.39s/it]
 74%|███████▎  | 45526/61904 [1:08:20<6:06:41,  1.34s/it]
 74%|███████▎  | 45527/61904 [1:08:21<6:10:22,  1.36s/it]
 74%|███████▎  | 45528/61904 [1:08:23<6:19:34,  1.39s/it]
 74%|███████▎  | 45529/61904 [1:08:24<6:16:37,  1.38s/it]
 74%|███████▎  | 45530/61904 [1:08:25<6:13:42,  1.37s/it]
 74%|███████▎  | 45531/61904 [1:08:27<6:03:40,  1.33s/it]
 74%|███████▎  | 45532/61904 [1:08:28<5:57:57,  1.31s/it]
 74%|███████▎  | 45533/61904 [1:08:29<5:51:40,  1.29s/it]
 74%|███████▎  | 45534/61904 [1:08:31<6:05:14,  1.34s/it]
 74%|███████▎  | 45535/61904 [1:08:32<6:13:45,  1.37s/it]
 74%|███████▎  | 45536/61904 [1:08:33<6:04:44,  1.34s/it]
 74%|███████▎  | 45537/61904 [1:08:35<6:08:21,  1.35s/it]
 74%|███████▎  | 45538/61904 [1:08:36<5:57:31,  1.31s/it]
 74%|███████▎  | 45539/61904 [1:08:37<6:01:09,  1.32s/it]
 74%|███████▎  | 45540/61904 [1:08:39<6:06:59,  1.35s/it]
                                                         
{'loss': 2.4958, 'learning_rate': 1.2652016076753533e-07, 'epoch': 11.77}

 74%|███████▎  | 45540/61904 [1:08:39<6:06:59,  1.35s/it]
 74%|███████▎  | 45541/61904 [1:08:40<6:03:09,  1.33s/it]
 74%|███████▎  | 45542/61904 [1:08:42<6:22:19,  1.40s/it]
 74%|███████▎  | 45543/61904 [1:08:43<6:27:52,  1.42s/it]
 74%|███████▎  | 45544/61904 [1:08:44<6:13:48,  1.37s/it]
 74%|███████▎  | 45545/61904 [1:08:46<6:18:16,  1.39s/it]
 74%|███████▎  | 45546/61904 [1:08:47<6:16:24,  1.38s/it]
 74%|███████▎  | 45547/61904 [1:08:48<6:08:56,  1.35s/it]
 74%|███████▎  | 45548/61904 [1:08:50<6:00:33,  1.32s/it]
 74%|███████▎  | 45549/61904 [1:08:51<6:16:30,  1.38s/it]
 74%|███████▎  | 45550/61904 [1:08:53<6:16:10,  1.38s/it]
 74%|███████▎  | 45551/61904 [1:08:54<6:21:04,  1.40s/it]
 74%|███████▎  | 45552/61904 [1:08:55<6:13:16,  1.37s/it]
 74%|███████▎  | 45553/61904 [1:08:57<6:16:02,  1.38s/it]
 74%|███████▎  | 45554/61904 [1:08:58<6:15:53,  1.38s/it]
 74%|███████▎  | 45555/61904 [1:08:59<6:10:48,  1.36s/it]
 74%|███████▎  | 45556/61904 [1:09:01<6:19:54,  1.39s/it]
 74%|███████▎  | 45557/61904 [1:09:02<6:05:08,  1.34s/it]
 74%|███████▎  | 45558/61904 [1:09:03<6:00:25,  1.32s/it]
 74%|███████▎  | 45559/61904 [1:09:05<6:14:47,  1.38s/it]
 74%|███████▎  | 45560/61904 [1:09:06<6:09:41,  1.36s/it]
                                                         
{'loss': 2.4918, 'learning_rate': 1.26487747957993e-07, 'epoch': 11.78}

 74%|███████▎  | 45560/61904 [1:09:06<6:09:41,  1.36s/it]
 74%|███████▎  | 45561/61904 [1:09:08<6:15:56,  1.38s/it]
 74%|███████▎  | 45562/61904 [1:09:09<6:16:51,  1.38s/it]
 74%|███████▎  | 45563/61904 [1:09:10<6:26:00,  1.42s/it]
 74%|███████▎  | 45564/61904 [1:09:12<6:20:48,  1.40s/it]
 74%|███████▎  | 45565/61904 [1:09:13<6:16:24,  1.38s/it]
 74%|███████▎  | 45566/61904 [1:09:15<6:27:42,  1.42s/it]
 74%|███████▎  | 45567/61904 [1:09:16<6:24:01,  1.41s/it]
 74%|███████▎  | 45568/61904 [1:09:17<6:09:58,  1.36s/it]
 74%|███████▎  | 45569/61904 [1:09:19<6:23:52,  1.41s/it]
 74%|███████▎  | 45570/61904 [1:09:20<6:30:12,  1.43s/it]
 74%|███████▎  | 45571/61904 [1:09:22<6:23:30,  1.41s/it]
 74%|███████▎  | 45572/61904 [1:09:23<6:39:37,  1.47s/it]
 74%|███████▎  | 45573/61904 [1:09:25<6:22:08,  1.40s/it]
 74%|███████▎  | 45574/61904 [1:09:26<6:22:45,  1.41s/it]
 74%|███████▎  | 45575/61904 [1:09:27<6:14:52,  1.38s/it]
 74%|███████▎  | 45576/61904 [1:09:29<6:15:31,  1.38s/it]
 74%|███████▎  | 45577/61904 [1:09:30<6:23:31,  1.41s/it]
 74%|███████▎  | 45578/61904 [1:09:32<6:26:18,  1.42s/it]
 74%|███████▎  | 45579/61904 [1:09:33<6:23:52,  1.41s/it]
 74%|███████▎  | 45580/61904 [1:09:34<6:23:41,  1.41s/it]
                                                         
{'loss': 2.513, 'learning_rate': 1.2645533514845065e-07, 'epoch': 11.78}

 74%|███████▎  | 45580/61904 [1:09:34<6:23:41,  1.41s/it]
 74%|███████▎  | 45581/61904 [1:09:36<6:31:11,  1.44s/it]
 74%|███████▎  | 45582/61904 [1:09:37<6:25:41,  1.42s/it]
 74%|███████▎  | 45583/61904 [1:09:39<6:19:50,  1.40s/it]
 74%|███████▎  | 45584/61904 [1:09:40<6:29:49,  1.43s/it]
 74%|███████▎  | 45585/61904 [1:09:41<6:18:58,  1.39s/it]
 74%|███████▎  | 45586/61904 [1:09:43<6:22:53,  1.41s/it]
 74%|███████▎  | 45587/61904 [1:09:44<6:10:13,  1.36s/it]
 74%|███████▎  | 45588/61904 [1:09:45<6:14:47,  1.38s/it]
 74%|███████▎  | 45589/61904 [1:09:47<6:11:16,  1.37s/it]
 74%|███████▎  | 45590/61904 [1:09:48<6:10:24,  1.36s/it]
 74%|███████▎  | 45591/61904 [1:09:49<6:03:36,  1.34s/it]
 74%|███████▎  | 45592/61904 [1:09:51<6:04:51,  1.34s/it]
 74%|███████▎  | 45593/61904 [1:09:52<5:58:22,  1.32s/it]
 74%|███████▎  | 45594/61904 [1:09:53<6:00:37,  1.33s/it]
 74%|███████▎  | 45595/61904 [1:09:55<5:53:45,  1.30s/it]
 74%|███████▎  | 45596/61904 [1:09:56<5:55:53,  1.31s/it]
 74%|███████▎  | 45597/61904 [1:09:57<5:56:52,  1.31s/it]
 74%|███████▎  | 45598/61904 [1:09:59<5:52:29,  1.30s/it]
 74%|███████▎  | 45599/61904 [1:10:00<5:54:18,  1.30s/it]
 74%|███████▎  | 45600/61904 [1:10:01<5:53:41,  1.30s/it]
                                                         
{'loss': 2.4897, 'learning_rate': 1.2642292233890834e-07, 'epoch': 11.79}

 74%|███████▎  | 45600/61904 [1:10:01<5:53:41,  1.30s/it]
 74%|███████▎  | 45601/61904 [1:10:02<5:50:21,  1.29s/it]
 74%|███████▎  | 45602/61904 [1:10:04<5:54:31,  1.30s/it]
 74%|███████▎  | 45603/61904 [1:10:05<6:07:37,  1.35s/it]
 74%|███████▎  | 45604/61904 [1:10:07<6:01:51,  1.33s/it]
 74%|███████▎  | 45605/61904 [1:10:08<6:03:11,  1.34s/it]
 74%|███████▎  | 45606/61904 [1:10:09<6:06:14,  1.35s/it]
 74%|███████▎  | 45607/61904 [1:10:11<6:01:45,  1.33s/it]
 74%|███████▎  | 45608/61904 [1:10:12<6:07:10,  1.35s/it]
 74%|███████▎  | 45609/61904 [1:10:13<6:00:18,  1.33s/it]
 74%|███████▎  | 45610/61904 [1:10:15<6:25:48,  1.42s/it]
 74%|███████▎  | 45611/61904 [1:10:16<6:22:43,  1.41s/it]
 74%|███████▎  | 45612/61904 [1:10:18<6:10:04,  1.36s/it]
 74%|███████▎  | 45613/61904 [1:10:19<6:08:53,  1.36s/it]
 74%|███████▎  | 45614/61904 [1:10:20<6:08:02,  1.36s/it]
 74%|███████▎  | 45615/61904 [1:10:22<6:08:34,  1.36s/it]
 74%|███████▎  | 45616/61904 [1:10:23<6:09:36,  1.36s/it]
 74%|███████▎  | 45617/61904 [1:10:24<6:16:21,  1.39s/it]
 74%|███████▎  | 45618/61904 [1:10:26<6:10:49,  1.37s/it]
 74%|███████▎  | 45619/61904 [1:10:27<6:05:41,  1.35s/it]
 74%|███████▎  | 45620/61904 [1:10:29<6:17:42,  1.39s/it]
                                                         
{'loss': 2.4468, 'learning_rate': 1.26390509529366e-07, 'epoch': 11.79}

 74%|███████▎  | 45620/61904 [1:10:29<6:17:42,  1.39s/it]
 74%|███████▎  | 45621/61904 [1:10:30<6:21:59,  1.41s/it]
 74%|███████▎  | 45622/61904 [1:10:31<6:22:49,  1.41s/it]
 74%|███████▎  | 45623/61904 [1:10:33<6:12:40,  1.37s/it]
 74%|███████▎  | 45624/61904 [1:10:34<6:15:58,  1.39s/it]
 74%|███████▎  | 45625/61904 [1:10:35<6:11:07,  1.37s/it]
 74%|███████▎  | 45626/61904 [1:10:37<6:15:56,  1.39s/it]
 74%|███████▎  | 45627/61904 [1:10:38<6:10:28,  1.37s/it]
 74%|███████▎  | 45628/61904 [1:10:40<6:22:27,  1.41s/it]
 74%|███████▎  | 45629/61904 [1:10:41<6:38:04,  1.47s/it]
 74%|███████▎  | 45630/61904 [1:10:43<6:36:13,  1.46s/it]
 74%|███████▎  | 45631/61904 [1:10:44<6:37:10,  1.46s/it]
 74%|███████▎  | 45632/61904 [1:10:46<6:29:21,  1.44s/it]
 74%|███████▎  | 45633/61904 [1:10:47<6:23:36,  1.41s/it]
 74%|███████▎  | 45634/61904 [1:10:48<6:13:54,  1.38s/it]
 74%|███████▎  | 45635/61904 [1:10:50<6:07:47,  1.36s/it]
 74%|███████▎  | 45636/61904 [1:10:51<6:15:55,  1.39s/it]
 74%|███████▎  | 45637/61904 [1:10:52<6:10:32,  1.37s/it]
 74%|███████▎  | 45638/61904 [1:10:54<6:13:00,  1.38s/it]
 74%|███████▎  | 45639/61904 [1:10:55<6:06:42,  1.35s/it]
 74%|███████▎  | 45640/61904 [1:10:56<6:06:45,  1.35s/it]
                                                         
{'loss': 2.4928, 'learning_rate': 1.2635809671982366e-07, 'epoch': 11.8}

 74%|███████▎  | 45640/61904 [1:10:56<6:06:45,  1.35s/it]
 74%|███████▎  | 45641/61904 [1:10:58<6:16:29,  1.39s/it]
 74%|███████▎  | 45642/61904 [1:10:59<6:10:20,  1.37s/it]
 74%|███████▎  | 45643/61904 [1:11:00<6:06:20,  1.35s/it]
 74%|███████▎  | 45644/61904 [1:11:02<6:24:26,  1.42s/it]
 74%|███████▎  | 45645/61904 [1:11:03<6:19:05,  1.40s/it]
 74%|███████▎  | 45646/61904 [1:11:05<6:09:33,  1.36s/it]
 74%|███████▎  | 45647/61904 [1:11:06<5:58:26,  1.32s/it]
 74%|███████▎  | 45648/61904 [1:11:07<6:03:30,  1.34s/it]
 74%|███████▎  | 45649/61904 [1:11:09<6:01:15,  1.33s/it]
 74%|███████▎  | 45650/61904 [1:11:10<6:06:50,  1.35s/it]
 74%|███████▎  | 45651/61904 [1:11:11<6:14:05,  1.38s/it]
 74%|███████▎  | 45652/61904 [1:11:13<6:04:50,  1.35s/it]
 74%|███████▎  | 45653/61904 [1:11:14<6:08:19,  1.36s/it]
 74%|███████▎  | 45654/61904 [1:11:15<6:08:59,  1.36s/it]
 74%|███████▍  | 45655/61904 [1:11:17<6:06:19,  1.35s/it]
 74%|███████▍  | 45656/61904 [1:11:18<6:09:30,  1.36s/it]
 74%|███████▍  | 45657/61904 [1:11:20<6:09:36,  1.36s/it]
 74%|███████▍  | 45658/61904 [1:11:21<6:00:33,  1.33s/it]
 74%|███████▍  | 45659/61904 [1:11:22<6:08:32,  1.36s/it]
 74%|███████▍  | 45660/61904 [1:11:24<6:05:05,  1.35s/it]
                                                         
{'loss': 2.4793, 'learning_rate': 1.2632568391028132e-07, 'epoch': 11.8}

 74%|███████▍  | 45660/61904 [1:11:24<6:05:05,  1.35s/it]
 74%|███████▍  | 45661/61904 [1:11:25<6:07:45,  1.36s/it]
 74%|███████▍  | 45662/61904 [1:11:26<6:09:33,  1.37s/it]
 74%|███████▍  | 45663/61904 [1:11:28<6:10:50,  1.37s/it]
 74%|███████▍  | 45664/61904 [1:11:29<6:20:38,  1.41s/it]
 74%|███████▍  | 45665/61904 [1:11:30<6:11:03,  1.37s/it]
 74%|███████▍  | 45666/61904 [1:11:32<6:10:54,  1.37s/it]
 74%|███████▍  | 45667/61904 [1:11:33<6:18:40,  1.40s/it]
 74%|███████▍  | 45668/61904 [1:11:35<6:14:11,  1.38s/it]
 74%|███████▍  | 45669/61904 [1:11:36<6:13:28,  1.38s/it]
 74%|███████▍  | 45670/61904 [1:11:37<6:04:54,  1.35s/it]
 74%|███████▍  | 45671/61904 [1:11:39<6:05:49,  1.35s/it]
 74%|███████▍  | 45672/61904 [1:11:40<6:35:50,  1.46s/it]
 74%|███████▍  | 45673/61904 [1:11:42<6:44:28,  1.50s/it]
 74%|███████▍  | 45674/61904 [1:11:43<6:29:42,  1.44s/it]
 74%|███████▍  | 45675/61904 [1:11:45<6:27:45,  1.43s/it]
 74%|███████▍  | 45676/61904 [1:11:46<6:22:08,  1.41s/it]
 74%|███████▍  | 45677/61904 [1:11:47<6:24:21,  1.42s/it]
 74%|███████▍  | 45678/61904 [1:11:49<6:27:15,  1.43s/it]
 74%|███████▍  | 45679/61904 [1:11:50<6:21:29,  1.41s/it]
 74%|███████▍  | 45680/61904 [1:11:52<6:07:59,  1.36s/it]
                                                         
{'loss': 2.4788, 'learning_rate': 1.26293271100739e-07, 'epoch': 11.81}

 74%|███████▍  | 45680/61904 [1:11:52<6:07:59,  1.36s/it]
 74%|███████▍  | 45681/61904 [1:11:53<6:07:23,  1.36s/it]
 74%|███████▍  | 45682/61904 [1:11:54<6:03:57,  1.35s/it]
 74%|███████▍  | 45683/61904 [1:11:56<6:19:55,  1.41s/it]
 74%|███████▍  | 45684/61904 [1:11:57<6:06:47,  1.36s/it]
 74%|███████▍  | 45685/61904 [1:11:58<6:05:33,  1.35s/it]
 74%|███████▍  | 45686/61904 [1:12:00<5:56:47,  1.32s/it]
 74%|███████▍  | 45687/61904 [1:12:01<5:57:46,  1.32s/it]
 74%|███████▍  | 45688/61904 [1:12:02<5:50:53,  1.30s/it]
 74%|███████▍  | 45689/61904 [1:12:04<5:59:17,  1.33s/it]
 74%|███████▍  | 45690/61904 [1:12:05<6:00:34,  1.33s/it]
 74%|███████▍  | 45691/61904 [1:12:06<6:10:45,  1.37s/it]
 74%|███████▍  | 45692/61904 [1:12:08<6:12:12,  1.38s/it]
 74%|███████▍  | 45693/61904 [1:12:09<6:04:11,  1.35s/it]
 74%|███████▍  | 45694/61904 [1:12:10<6:08:11,  1.36s/it]
 74%|███████▍  | 45695/61904 [1:12:12<6:03:36,  1.35s/it]
 74%|███████▍  | 45696/61904 [1:12:13<6:06:37,  1.36s/it]
 74%|███████▍  | 45697/61904 [1:12:14<6:05:51,  1.35s/it]
 74%|███████▍  | 45698/61904 [1:12:16<6:16:06,  1.39s/it]
 74%|███████▍  | 45699/61904 [1:12:18<6:52:01,  1.53s/it]
 74%|███████▍  | 45700/61904 [1:12:19<6:37:33,  1.47s/it]
                                                         
{'loss': 2.4913, 'learning_rate': 1.2626085829119668e-07, 'epoch': 11.81}

 74%|███████▍  | 45700/61904 [1:12:19<6:37:33,  1.47s/it]
 74%|███████▍  | 45701/61904 [1:12:20<6:29:10,  1.44s/it]
 74%|███████▍  | 45702/61904 [1:12:22<6:32:18,  1.45s/it]
 74%|███████▍  | 45703/61904 [1:12:23<6:27:38,  1.44s/it]
 74%|███████▍  | 45704/61904 [1:12:25<6:28:25,  1.44s/it]
 74%|███████▍  | 45705/61904 [1:12:26<6:21:37,  1.41s/it]
 74%|███████▍  | 45706/61904 [1:12:28<6:20:41,  1.41s/it]
 74%|███████▍  | 45707/61904 [1:12:29<6:16:35,  1.40s/it]
 74%|███████▍  | 45708/61904 [1:12:30<6:14:09,  1.39s/it]
 74%|███████▍  | 45709/61904 [1:12:32<6:45:02,  1.50s/it]
 74%|███████▍  | 45710/61904 [1:12:33<6:29:49,  1.44s/it]
 74%|███████▍  | 45711/61904 [1:12:35<6:20:32,  1.41s/it]
 74%|███████▍  | 45712/61904 [1:12:36<6:17:21,  1.40s/it]
 74%|███████▍  | 45713/61904 [1:12:37<6:13:44,  1.39s/it]
 74%|███████▍  | 45714/61904 [1:12:39<6:09:27,  1.37s/it]
 74%|███████▍  | 45715/61904 [1:12:40<6:07:24,  1.36s/it]
 74%|███████▍  | 45716/61904 [1:12:41<5:54:39,  1.31s/it]
 74%|███████▍  | 45717/61904 [1:12:43<6:02:51,  1.35s/it]
 74%|███████▍  | 45718/61904 [1:12:44<6:06:09,  1.36s/it]
 74%|███████▍  | 45719/61904 [1:12:45<6:04:24,  1.35s/it]
 74%|███████▍  | 45720/61904 [1:12:47<6:13:30,  1.38s/it]
                                                         
{'loss': 2.4966, 'learning_rate': 1.2622844548165434e-07, 'epoch': 11.82}

 74%|███████▍  | 45720/61904 [1:12:47<6:13:30,  1.38s/it]
 74%|███████▍  | 45721/61904 [1:12:48<6:06:57,  1.36s/it]
 74%|███████▍  | 45722/61904 [1:12:50<5:59:58,  1.33s/it]
 74%|███████▍  | 45723/61904 [1:12:51<5:53:31,  1.31s/it]
 74%|███████▍  | 45724/61904 [1:12:52<5:53:11,  1.31s/it]
 74%|███████▍  | 45725/61904 [1:12:53<5:45:31,  1.28s/it]
 74%|███████▍  | 45726/61904 [1:12:55<5:50:44,  1.30s/it]
 74%|███████▍  | 45727/61904 [1:12:56<5:51:27,  1.30s/it]
 74%|███████▍  | 45728/61904 [1:12:57<5:58:55,  1.33s/it]
 74%|███████▍  | 45729/61904 [1:12:59<6:14:36,  1.39s/it]
 74%|███████▍  | 45730/61904 [1:13:00<6:10:56,  1.38s/it]
 74%|███████▍  | 45731/61904 [1:13:02<6:06:45,  1.36s/it]
 74%|███████▍  | 45732/61904 [1:13:03<5:59:04,  1.33s/it]
 74%|███████▍  | 45733/61904 [1:13:04<5:53:24,  1.31s/it]
 74%|███████▍  | 45734/61904 [1:13:06<6:06:19,  1.36s/it]
 74%|███████▍  | 45735/61904 [1:13:07<6:13:02,  1.38s/it]
 74%|███████▍  | 45736/61904 [1:13:08<6:06:56,  1.36s/it]
 74%|███████▍  | 45737/61904 [1:13:10<5:58:13,  1.33s/it]
 74%|███████▍  | 45738/61904 [1:13:11<5:52:54,  1.31s/it]
 74%|███████▍  | 45739/61904 [1:13:12<6:00:58,  1.34s/it]
 74%|███████▍  | 45740/61904 [1:13:14<6:27:26,  1.44s/it]
                                                         
{'loss': 2.4954, 'learning_rate': 1.2619603267211203e-07, 'epoch': 11.82}

 74%|███████▍  | 45740/61904 [1:13:14<6:27:26,  1.44s/it]
 74%|███████▍  | 45741/61904 [1:13:15<6:22:55,  1.42s/it]
 74%|███████▍  | 45742/61904 [1:13:17<6:09:05,  1.37s/it]
 74%|███████▍  | 45743/61904 [1:13:18<6:01:39,  1.34s/it]
 74%|███████▍  | 45744/61904 [1:13:19<5:59:52,  1.34s/it]
 74%|███████▍  | 45745/61904 [1:13:21<6:15:44,  1.40s/it]
 74%|███████▍  | 45746/61904 [1:13:22<6:07:24,  1.36s/it]
 74%|███████▍  | 45747/61904 [1:13:23<6:06:59,  1.36s/it]
 74%|███████▍  | 45748/61904 [1:13:25<6:04:53,  1.36s/it]
 74%|███████▍  | 45749/61904 [1:13:26<5:59:24,  1.33s/it]
 74%|███████▍  | 45750/61904 [1:13:27<6:02:50,  1.35s/it]
 74%|███████▍  | 45751/61904 [1:13:29<6:08:37,  1.37s/it]
 74%|███████▍  | 45752/61904 [1:13:30<5:55:51,  1.32s/it]
 74%|███████▍  | 45753/61904 [1:13:31<5:59:07,  1.33s/it]
 74%|███████▍  | 45754/61904 [1:13:33<6:03:40,  1.35s/it]
 74%|███████▍  | 45755/61904 [1:13:34<6:03:59,  1.35s/it]
 74%|███████▍  | 45756/61904 [1:13:35<6:12:09,  1.38s/it]
 74%|███████▍  | 45757/61904 [1:13:37<6:24:36,  1.43s/it]
 74%|███████▍  | 45758/61904 [1:13:38<6:21:05,  1.42s/it]
 74%|███████▍  | 45759/61904 [1:13:40<6:17:37,  1.40s/it]
 74%|███████▍  | 45760/61904 [1:13:41<6:20:10,  1.41s/it]
                                                         
{'loss': 2.4608, 'learning_rate': 1.261636198625697e-07, 'epoch': 11.83}

 74%|███████▍  | 45760/61904 [1:13:41<6:20:10,  1.41s/it]
 74%|███████▍  | 45761/61904 [1:13:43<6:10:44,  1.38s/it]
 74%|███████▍  | 45762/61904 [1:13:44<6:09:05,  1.37s/it]
 74%|███████▍  | 45763/61904 [1:13:45<6:12:40,  1.39s/it]
 74%|███████▍  | 45764/61904 [1:13:47<6:13:02,  1.39s/it]
 74%|███████▍  | 45765/61904 [1:13:48<6:23:14,  1.42s/it]
 74%|███████▍  | 45766/61904 [1:13:49<6:11:04,  1.38s/it]
 74%|███████▍  | 45767/61904 [1:13:51<6:12:49,  1.39s/it]
 74%|███████▍  | 45768/61904 [1:13:52<6:08:24,  1.37s/it]
 74%|███████▍  | 45769/61904 [1:13:54<6:14:47,  1.39s/it]
 74%|███████▍  | 45770/61904 [1:13:55<6:07:01,  1.36s/it]
 74%|███████▍  | 45771/61904 [1:13:56<6:10:47,  1.38s/it]
 74%|███████▍  | 45772/61904 [1:13:58<5:56:42,  1.33s/it]
 74%|███████▍  | 45773/61904 [1:13:59<5:58:23,  1.33s/it]
 74%|███████▍  | 45774/61904 [1:14:00<5:55:12,  1.32s/it]
 74%|███████▍  | 45775/61904 [1:14:02<6:05:43,  1.36s/it]
 74%|███████▍  | 45776/61904 [1:14:03<6:13:06,  1.39s/it]
 74%|███████▍  | 45777/61904 [1:14:04<6:10:42,  1.38s/it]
 74%|███████▍  | 45778/61904 [1:14:06<6:10:07,  1.38s/it]
 74%|███████▍  | 45779/61904 [1:14:07<6:15:27,  1.40s/it]
 74%|███████▍  | 45780/61904 [1:14:09<6:15:17,  1.40s/it]
                                                         
{'loss': 2.4901, 'learning_rate': 1.2613120705302735e-07, 'epoch': 11.83}

 74%|███████▍  | 45780/61904 [1:14:09<6:15:17,  1.40s/it]
 74%|███████▍  | 45781/61904 [1:14:10<6:15:31,  1.40s/it]
 74%|███████▍  | 45782/61904 [1:14:11<6:05:11,  1.36s/it]
 74%|███████▍  | 45783/61904 [1:14:13<5:58:37,  1.33s/it]
 74%|███████▍  | 45784/61904 [1:14:14<5:57:12,  1.33s/it]
 74%|███████▍  | 45785/61904 [1:14:15<5:51:45,  1.31s/it]
 74%|███████▍  | 45786/61904 [1:14:17<5:59:56,  1.34s/it]
 74%|███████▍  | 45787/61904 [1:14:18<6:01:25,  1.35s/it]
 74%|███████▍  | 45788/61904 [1:14:19<5:57:33,  1.33s/it]
 74%|███████▍  | 45789/61904 [1:14:21<6:02:15,  1.35s/it]
 74%|███████▍  | 45790/61904 [1:14:22<6:03:05,  1.35s/it]
 74%|███████▍  | 45791/61904 [1:14:23<6:08:24,  1.37s/it]
 74%|███████▍  | 45792/61904 [1:14:25<6:04:59,  1.36s/it]
 74%|███████▍  | 45793/61904 [1:14:26<6:20:48,  1.42s/it]
 74%|███████▍  | 45794/61904 [1:14:28<6:28:18,  1.45s/it]
 74%|███████▍  | 45795/61904 [1:14:29<6:40:11,  1.49s/it]
 74%|███████▍  | 45796/61904 [1:14:31<6:32:02,  1.46s/it]
 74%|███████▍  | 45797/61904 [1:14:32<6:37:44,  1.48s/it]
 74%|███████▍  | 45798/61904 [1:14:34<6:31:31,  1.46s/it]
 74%|███████▍  | 45799/61904 [1:14:35<6:16:26,  1.40s/it]
 74%|███████▍  | 45800/61904 [1:14:36<6:07:05,  1.37s/it]
                                                         
{'loss': 2.5462, 'learning_rate': 1.26098794243485e-07, 'epoch': 11.84}

 74%|███████▍  | 45800/61904 [1:14:36<6:07:05,  1.37s/it]
 74%|███████▍  | 45801/61904 [1:14:38<5:58:02,  1.33s/it]
 74%|███████▍  | 45802/61904 [1:14:39<6:01:39,  1.35s/it]
 74%|███████▍  | 45803/61904 [1:14:40<5:54:19,  1.32s/it]
 74%|███████▍  | 45804/61904 [1:14:42<6:07:14,  1.37s/it]
 74%|███████▍  | 45805/61904 [1:14:43<6:06:13,  1.36s/it]
 74%|███████▍  | 45806/61904 [1:14:44<6:03:49,  1.36s/it]
 74%|███████▍  | 45807/61904 [1:14:46<6:02:40,  1.35s/it]
 74%|███████▍  | 45808/61904 [1:14:47<5:58:23,  1.34s/it]
 74%|███████▍  | 45809/61904 [1:14:48<5:44:29,  1.28s/it]
 74%|███████▍  | 45810/61904 [1:14:50<5:58:57,  1.34s/it]
 74%|███████▍  | 45811/61904 [1:14:51<6:00:11,  1.34s/it]
 74%|███████▍  | 45812/61904 [1:14:52<5:56:48,  1.33s/it]
 74%|███████▍  | 45813/61904 [1:14:54<6:05:56,  1.36s/it]
 74%|███████▍  | 45814/61904 [1:14:55<6:13:46,  1.39s/it]
 74%|███████▍  | 45815/61904 [1:14:57<6:11:44,  1.39s/it]
 74%|███████▍  | 45816/61904 [1:14:58<6:21:44,  1.42s/it]
 74%|███████▍  | 45817/61904 [1:14:59<6:02:01,  1.35s/it]
 74%|███████▍  | 45818/61904 [1:15:01<5:53:57,  1.32s/it]
 74%|███████▍  | 45819/61904 [1:15:02<5:48:57,  1.30s/it]
 74%|███████▍  | 45820/61904 [1:15:03<6:02:30,  1.35s/it]
                                                         
{'loss': 2.5217, 'learning_rate': 1.260663814339427e-07, 'epoch': 11.84}

 74%|███████▍  | 45820/61904 [1:15:03<6:02:30,  1.35s/it]
 74%|███████▍  | 45821/61904 [1:15:05<6:07:09,  1.37s/it]
 74%|███████▍  | 45822/61904 [1:15:06<5:59:42,  1.34s/it]
 74%|███████▍  | 45823/61904 [1:15:07<5:50:48,  1.31s/it]
 74%|███████▍  | 45824/61904 [1:15:09<6:03:21,  1.36s/it]
 74%|███████▍  | 45825/61904 [1:15:10<5:56:33,  1.33s/it]
 74%|███████▍  | 45826/61904 [1:15:11<5:57:01,  1.33s/it]
 74%|███████▍  | 45827/61904 [1:15:13<5:58:26,  1.34s/it]
 74%|███████▍  | 45828/61904 [1:15:14<6:20:20,  1.42s/it]
 74%|███████▍  | 45829/61904 [1:15:15<6:00:54,  1.35s/it]
 74%|███████▍  | 45830/61904 [1:15:17<6:04:08,  1.36s/it]
 74%|███████▍  | 45831/61904 [1:15:18<6:08:04,  1.37s/it]
 74%|███████▍  | 45832/61904 [1:15:19<6:03:44,  1.36s/it]
 74%|███████▍  | 45833/61904 [1:15:21<6:00:47,  1.35s/it]
 74%|███████▍  | 45834/61904 [1:15:22<6:05:34,  1.36s/it]
 74%|███████▍  | 45835/61904 [1:15:24<5:58:32,  1.34s/it]
 74%|███████▍  | 45836/61904 [1:15:25<6:14:35,  1.40s/it]
 74%|███████▍  | 45837/61904 [1:15:26<6:08:46,  1.38s/it]
 74%|███████▍  | 45838/61904 [1:15:28<6:00:30,  1.35s/it]
 74%|███████▍  | 45839/61904 [1:15:29<6:10:37,  1.38s/it]
 74%|███████▍  | 45840/61904 [1:15:31<6:13:53,  1.40s/it]
                                                         
{'loss': 2.4889, 'learning_rate': 1.2603396862440036e-07, 'epoch': 11.85}

 74%|███████▍  | 45840/61904 [1:15:31<6:13:53,  1.40s/it]
 74%|███████▍  | 45841/61904 [1:15:32<6:09:11,  1.38s/it]
 74%|███████▍  | 45842/61904 [1:15:33<6:07:56,  1.37s/it]
 74%|███████▍  | 45843/61904 [1:15:35<6:07:23,  1.37s/it]
 74%|███████▍  | 45844/61904 [1:15:36<6:06:52,  1.37s/it]
 74%|███████▍  | 45845/61904 [1:15:37<5:58:05,  1.34s/it]
 74%|███████▍  | 45846/61904 [1:15:39<6:05:15,  1.36s/it]
 74%|███████▍  | 45847/61904 [1:15:40<5:56:05,  1.33s/it]
 74%|███████▍  | 45848/61904 [1:15:41<5:58:58,  1.34s/it]
 74%|███████▍  | 45849/61904 [1:15:43<6:00:55,  1.35s/it]
 74%|███████▍  | 45850/61904 [1:15:44<6:00:30,  1.35s/it]
 74%|███████▍  | 45851/61904 [1:15:45<5:59:44,  1.34s/it]
 74%|███████▍  | 45852/61904 [1:15:47<6:07:38,  1.37s/it]
 74%|███████▍  | 45853/61904 [1:15:48<6:07:25,  1.37s/it]
 74%|███████▍  | 45854/61904 [1:15:50<6:10:55,  1.39s/it]
 74%|███████▍  | 45855/61904 [1:15:51<6:05:23,  1.37s/it]
 74%|███████▍  | 45856/61904 [1:15:52<6:04:11,  1.36s/it]
 74%|███████▍  | 45857/61904 [1:15:54<5:59:03,  1.34s/it]
 74%|███████▍  | 45858/61904 [1:15:55<5:49:33,  1.31s/it]
 74%|███████▍  | 45859/61904 [1:15:56<5:59:50,  1.35s/it]
 74%|███████▍  | 45860/61904 [1:15:58<6:11:28,  1.39s/it]
                                                         
{'loss': 2.5021, 'learning_rate': 1.2600155581485802e-07, 'epoch': 11.85}

 74%|███████▍  | 45860/61904 [1:15:58<6:11:28,  1.39s/it]
 74%|███████▍  | 45861/61904 [1:15:59<6:17:18,  1.41s/it]
 74%|███████▍  | 45862/61904 [1:16:01<6:16:10,  1.41s/it]
 74%|███████▍  | 45863/61904 [1:16:02<6:10:25,  1.39s/it]
 74%|███████▍  | 45864/61904 [1:16:03<6:00:54,  1.35s/it]
 74%|███████▍  | 45865/61904 [1:16:05<6:02:20,  1.36s/it]
 74%|███████▍  | 45866/61904 [1:16:06<5:57:39,  1.34s/it]
 74%|███████▍  | 45867/61904 [1:16:07<5:59:36,  1.35s/it]
 74%|███████▍  | 45868/61904 [1:16:09<5:59:41,  1.35s/it]
 74%|███████▍  | 45869/61904 [1:16:10<5:53:05,  1.32s/it]
 74%|███████▍  | 45870/61904 [1:16:11<5:54:49,  1.33s/it]
 74%|███████▍  | 45871/61904 [1:16:12<5:55:34,  1.33s/it]
 74%|███████▍  | 45872/61904 [1:16:14<6:04:35,  1.36s/it]
 74%|███████▍  | 45873/61904 [1:16:15<5:57:46,  1.34s/it]
 74%|███████▍  | 45874/61904 [1:16:17<6:09:28,  1.38s/it]
 74%|███████▍  | 45875/61904 [1:16:18<6:09:24,  1.38s/it]
 74%|███████▍  | 45876/61904 [1:16:19<6:07:56,  1.38s/it]
 74%|███████▍  | 45877/61904 [1:16:21<6:05:09,  1.37s/it]
 74%|███████▍  | 45878/61904 [1:16:22<6:02:47,  1.36s/it]
 74%|███████▍  | 45879/61904 [1:16:23<5:57:29,  1.34s/it]
 74%|███████▍  | 45880/61904 [1:16:25<5:56:56,  1.34s/it]
                                                         
{'loss': 2.5027, 'learning_rate': 1.2596914300531568e-07, 'epoch': 11.86}

 74%|███████▍  | 45880/61904 [1:16:25<5:56:56,  1.34s/it]
 74%|███████▍  | 45881/61904 [1:16:26<6:01:05,  1.35s/it]
 74%|███████▍  | 45882/61904 [1:16:27<5:54:43,  1.33s/it]
 74%|███████▍  | 45883/61904 [1:16:29<5:58:11,  1.34s/it]
 74%|███████▍  | 45884/61904 [1:16:30<6:01:13,  1.35s/it]
 74%|███████▍  | 45885/61904 [1:16:31<6:00:18,  1.35s/it]
 74%|███████▍  | 45886/61904 [1:16:33<6:10:38,  1.39s/it]
 74%|███████▍  | 45887/61904 [1:16:34<6:11:27,  1.39s/it]
 74%|███████▍  | 45888/61904 [1:16:36<5:56:03,  1.33s/it]
 74%|███████▍  | 45889/61904 [1:16:37<5:54:13,  1.33s/it]
 74%|███████▍  | 45890/61904 [1:16:38<5:57:41,  1.34s/it]
 74%|███████▍  | 45891/61904 [1:16:40<6:09:04,  1.38s/it]
 74%|███████▍  | 45892/61904 [1:16:41<6:22:07,  1.43s/it]
 74%|███████▍  | 45893/61904 [1:16:43<6:22:29,  1.43s/it]
 74%|███████▍  | 45894/61904 [1:16:44<6:10:02,  1.39s/it]
 74%|███████▍  | 45895/61904 [1:16:45<6:02:24,  1.36s/it]
 74%|███████▍  | 45896/61904 [1:16:47<5:56:32,  1.34s/it]
 74%|███████▍  | 45897/61904 [1:16:48<5:59:40,  1.35s/it]
 74%|███████▍  | 45898/61904 [1:16:49<5:58:08,  1.34s/it]
 74%|███████▍  | 45899/61904 [1:16:51<5:55:46,  1.33s/it]
 74%|███████▍  | 45900/61904 [1:16:52<6:24:46,  1.44s/it]
                                                         
{'loss': 2.4681, 'learning_rate': 1.2593673019577337e-07, 'epoch': 11.86}

 74%|███████▍  | 45900/61904 [1:16:52<6:24:46,  1.44s/it]
 74%|███████▍  | 45901/61904 [1:16:54<6:15:26,  1.41s/it]
 74%|███████▍  | 45902/61904 [1:16:55<6:04:40,  1.37s/it]
 74%|███████▍  | 45903/61904 [1:16:56<5:53:15,  1.32s/it]
 74%|███████▍  | 45904/61904 [1:16:57<5:53:22,  1.33s/it]
 74%|███████▍  | 45905/61904 [1:16:59<6:17:25,  1.42s/it]
 74%|███████▍  | 45906/61904 [1:17:00<6:14:57,  1.41s/it]
 74%|███████▍  | 45907/61904 [1:17:02<6:02:00,  1.36s/it]
 74%|███████▍  | 45908/61904 [1:17:03<5:59:22,  1.35s/it]
 74%|███████▍  | 45909/61904 [1:17:04<6:07:53,  1.38s/it]
 74%|███████▍  | 45910/61904 [1:17:06<6:01:00,  1.35s/it]
 74%|███████▍  | 45911/61904 [1:17:07<6:04:49,  1.37s/it]
 74%|███████▍  | 45912/61904 [1:17:08<6:01:42,  1.36s/it]
 74%|███████▍  | 45913/61904 [1:17:10<5:57:05,  1.34s/it]
 74%|███████▍  | 45914/61904 [1:17:11<5:55:32,  1.33s/it]
 74%|███████▍  | 45915/61904 [1:17:12<5:57:53,  1.34s/it]
 74%|███████▍  | 45916/61904 [1:17:14<6:05:07,  1.37s/it]
 74%|███████▍  | 45917/61904 [1:17:15<6:10:08,  1.39s/it]
 74%|███████▍  | 45918/61904 [1:17:17<6:02:50,  1.36s/it]
 74%|███████▍  | 45919/61904 [1:17:18<5:54:13,  1.33s/it]
 74%|███████▍  | 45920/61904 [1:17:19<5:57:58,  1.34s/it]
                                                         
{'loss': 2.409, 'learning_rate': 1.2590431738623104e-07, 'epoch': 11.87}

 74%|███████▍  | 45920/61904 [1:17:19<5:57:58,  1.34s/it]
 74%|███████▍  | 45921/61904 [1:17:21<6:01:35,  1.36s/it]
 74%|███████▍  | 45922/61904 [1:17:22<6:13:31,  1.40s/it]
 74%|███████▍  | 45923/61904 [1:17:24<6:12:45,  1.40s/it]
 74%|███████▍  | 45924/61904 [1:17:25<6:04:25,  1.37s/it]
 74%|███████▍  | 45925/61904 [1:17:26<6:00:14,  1.35s/it]
 74%|███████▍  | 45926/61904 [1:17:28<6:09:01,  1.39s/it]
 74%|███████▍  | 45927/61904 [1:17:29<6:17:43,  1.42s/it]
 74%|███████▍  | 45928/61904 [1:17:30<6:09:14,  1.39s/it]
 74%|███████▍  | 45929/61904 [1:17:32<6:10:00,  1.39s/it]
 74%|███████▍  | 45930/61904 [1:17:33<6:12:37,  1.40s/it]
 74%|███████▍  | 45931/61904 [1:17:34<5:58:00,  1.34s/it]
 74%|███████▍  | 45932/61904 [1:17:36<5:56:43,  1.34s/it]
 74%|███████▍  | 45933/61904 [1:17:38<6:35:31,  1.49s/it]
 74%|███████▍  | 45934/61904 [1:17:39<6:25:29,  1.45s/it]
 74%|███████▍  | 45935/61904 [1:17:40<6:13:08,  1.40s/it]
 74%|███████▍  | 45936/61904 [1:17:42<6:17:31,  1.42s/it]
 74%|███████▍  | 45937/61904 [1:17:43<6:18:24,  1.42s/it]
 74%|███████▍  | 45938/61904 [1:17:45<6:22:47,  1.44s/it]
 74%|███████▍  | 45939/61904 [1:17:46<6:18:51,  1.42s/it]
 74%|███████▍  | 45940/61904 [1:17:47<6:15:28,  1.41s/it]
                                                         
{'loss': 2.4426, 'learning_rate': 1.258719045766887e-07, 'epoch': 11.87}

 74%|███████▍  | 45940/61904 [1:17:47<6:15:28,  1.41s/it]
 74%|███████▍  | 45941/61904 [1:17:49<6:21:37,  1.43s/it]
 74%|███████▍  | 45942/61904 [1:17:50<6:20:45,  1.43s/it]
 74%|███████▍  | 45943/61904 [1:17:52<6:13:10,  1.40s/it]
 74%|███████▍  | 45944/61904 [1:17:53<6:18:09,  1.42s/it]
 74%|███████▍  | 45945/61904 [1:17:55<6:27:15,  1.46s/it]
 74%|███████▍  | 45946/61904 [1:17:56<6:04:45,  1.37s/it]
 74%|███████▍  | 45947/61904 [1:17:57<6:01:21,  1.36s/it]
 74%|███████▍  | 45948/61904 [1:17:59<6:08:08,  1.38s/it]
 74%|███████▍  | 45949/61904 [1:18:00<6:09:53,  1.39s/it]
 74%|███████▍  | 45950/61904 [1:18:01<6:12:53,  1.40s/it]
 74%|███████▍  | 45951/61904 [1:18:03<6:10:07,  1.39s/it]
 74%|███████▍  | 45952/61904 [1:18:04<6:04:16,  1.37s/it]
 74%|███████▍  | 45953/61904 [1:18:06<6:14:25,  1.41s/it]
 74%|███████▍  | 45954/61904 [1:18:07<6:09:50,  1.39s/it]
 74%|███████▍  | 45955/61904 [1:18:09<6:29:09,  1.46s/it]
 74%|███████▍  | 45956/61904 [1:18:10<6:21:51,  1.44s/it]
 74%|███████▍  | 45957/61904 [1:18:12<6:30:39,  1.47s/it]
 74%|███████▍  | 45958/61904 [1:18:13<6:33:49,  1.48s/it]
 74%|███████▍  | 45959/61904 [1:18:14<6:30:43,  1.47s/it]
 74%|███████▍  | 45960/61904 [1:18:16<6:15:02,  1.41s/it]
                                                         
{'loss': 2.4285, 'learning_rate': 1.2583949176714636e-07, 'epoch': 11.88}

 74%|███████▍  | 45960/61904 [1:18:16<6:15:02,  1.41s/it]
 74%|███████▍  | 45961/61904 [1:18:17<5:57:59,  1.35s/it]
 74%|███████▍  | 45962/61904 [1:18:18<6:00:39,  1.36s/it]
 74%|███████▍  | 45963/61904 [1:18:20<6:08:35,  1.39s/it]
 74%|███████▍  | 45964/61904 [1:18:21<6:02:22,  1.36s/it]
 74%|███████▍  | 45965/61904 [1:18:23<6:10:41,  1.40s/it]
 74%|███████▍  | 45966/61904 [1:18:24<6:11:04,  1.40s/it]
 74%|███████▍  | 45967/61904 [1:18:25<6:06:33,  1.38s/it]
 74%|███████▍  | 45968/61904 [1:18:27<6:00:49,  1.36s/it]
 74%|███████▍  | 45969/61904 [1:18:28<6:03:17,  1.37s/it]
 74%|███████▍  | 45970/61904 [1:18:30<6:12:42,  1.40s/it]
 74%|███████▍  | 45971/61904 [1:18:31<6:08:34,  1.39s/it]
 74%|███████▍  | 45972/61904 [1:18:32<6:09:33,  1.39s/it]
 74%|███████▍  | 45973/61904 [1:18:34<6:07:22,  1.38s/it]
 74%|███████▍  | 45974/61904 [1:18:35<6:04:18,  1.37s/it]
 74%|███████▍  | 45975/61904 [1:18:36<5:51:34,  1.32s/it]
 74%|███████▍  | 45976/61904 [1:18:37<5:46:36,  1.31s/it]
 74%|███████▍  | 45977/61904 [1:18:39<5:55:06,  1.34s/it]
 74%|███████▍  | 45978/61904 [1:18:40<6:08:36,  1.39s/it]
 74%|███████▍  | 45979/61904 [1:18:42<6:11:55,  1.40s/it]
 74%|███████▍  | 45980/61904 [1:18:43<6:21:38,  1.44s/it]
                                                         
{'loss': 2.4452, 'learning_rate': 1.2580707895760405e-07, 'epoch': 11.88}

 74%|███████▍  | 45980/61904 [1:18:43<6:21:38,  1.44s/it]
 74%|███████▍  | 45981/61904 [1:18:45<6:09:53,  1.39s/it]
 74%|███████▍  | 45982/61904 [1:18:46<6:07:38,  1.39s/it]
 74%|███████▍  | 45983/61904 [1:18:47<6:04:14,  1.37s/it]
 74%|███████▍  | 45984/61904 [1:18:49<6:01:59,  1.36s/it]
 74%|███████▍  | 45985/61904 [1:18:50<6:04:05,  1.37s/it]
 74%|███████▍  | 45986/61904 [1:18:51<5:50:55,  1.32s/it]
 74%|███████▍  | 45987/61904 [1:18:53<5:48:34,  1.31s/it]
 74%|███████▍  | 45988/61904 [1:18:54<5:39:56,  1.28s/it]
 74%|███████▍  | 45989/61904 [1:18:55<5:53:52,  1.33s/it]
 74%|███████▍  | 45990/61904 [1:18:56<5:44:59,  1.30s/it]
 74%|███████▍  | 45991/61904 [1:18:58<6:02:24,  1.37s/it]
 74%|███████▍  | 45992/61904 [1:18:59<6:03:41,  1.37s/it]
 74%|███████▍  | 45993/61904 [1:19:01<5:54:02,  1.34s/it]
 74%|███████▍  | 45994/61904 [1:19:02<5:55:13,  1.34s/it]
 74%|███████▍  | 45995/61904 [1:19:03<5:55:49,  1.34s/it]
 74%|███████▍  | 45996/61904 [1:19:05<6:00:20,  1.36s/it]
 74%|███████▍  | 45997/61904 [1:19:06<5:54:09,  1.34s/it]
 74%|███████▍  | 45998/61904 [1:19:07<5:57:16,  1.35s/it]
 74%|███████▍  | 45999/61904 [1:19:09<5:59:22,  1.36s/it]
 74%|███████▍  | 46000/61904 [1:19:10<5:51:48,  1.33s/it]
                                                         
{'loss': 2.4816, 'learning_rate': 1.257746661480617e-07, 'epoch': 11.89}

 74%|███████▍  | 46000/61904 [1:19:10<5:51:48,  1.33s/it]
 74%|███████▍  | 46001/61904 [1:19:11<5:54:11,  1.34s/it]
 74%|███████▍  | 46002/61904 [1:19:13<5:47:57,  1.31s/it]
 74%|███████▍  | 46003/61904 [1:19:14<5:42:47,  1.29s/it]
 74%|███████▍  | 46004/61904 [1:19:15<5:35:39,  1.27s/it]
 74%|███████▍  | 46005/61904 [1:19:16<5:42:58,  1.29s/it]
 74%|███████▍  | 46006/61904 [1:19:18<6:04:19,  1.37s/it]
 74%|███████▍  | 46007/61904 [1:19:19<5:58:10,  1.35s/it]
 74%|███████▍  | 46008/61904 [1:19:21<6:28:46,  1.47s/it]
 74%|███████▍  | 46009/61904 [1:19:23<6:32:17,  1.48s/it]
 74%|███████▍  | 46010/61904 [1:19:24<6:38:30,  1.50s/it]
 74%|███████▍  | 46011/61904 [1:19:25<6:21:35,  1.44s/it]
 74%|███████▍  | 46012/61904 [1:19:27<6:28:30,  1.47s/it]
 74%|███████▍  | 46013/61904 [1:19:28<6:13:27,  1.41s/it]
 74%|███████▍  | 46014/61904 [1:19:29<6:01:09,  1.36s/it]
 74%|███████▍  | 46015/61904 [1:19:31<5:52:08,  1.33s/it]
 74%|███████▍  | 46016/61904 [1:19:32<5:51:07,  1.33s/it]
 74%|███████▍  | 46017/61904 [1:19:33<5:59:38,  1.36s/it]
 74%|███████▍  | 46018/61904 [1:19:35<6:04:02,  1.37s/it]
 74%|███████▍  | 46019/61904 [1:19:36<5:59:53,  1.36s/it]
 74%|███████▍  | 46020/61904 [1:19:37<5:52:05,  1.33s/it]
                                                         
{'loss': 2.4585, 'learning_rate': 1.2574225333851937e-07, 'epoch': 11.89}

 74%|███████▍  | 46020/61904 [1:19:37<5:52:05,  1.33s/it]
 74%|███████▍  | 46021/61904 [1:19:39<5:56:09,  1.35s/it]
 74%|███████▍  | 46022/61904 [1:19:40<5:55:32,  1.34s/it]
 74%|███████▍  | 46023/61904 [1:19:42<6:02:15,  1.37s/it]
 74%|███████▍  | 46024/61904 [1:19:43<6:07:14,  1.39s/it]
 74%|███████▍  | 46025/61904 [1:19:44<5:54:42,  1.34s/it]
 74%|███████▍  | 46026/61904 [1:19:45<5:47:26,  1.31s/it]
 74%|███████▍  | 46027/61904 [1:19:47<5:58:30,  1.35s/it]
 74%|███████▍  | 46028/61904 [1:19:48<6:01:48,  1.37s/it]
 74%|███████▍  | 46029/61904 [1:19:50<6:04:23,  1.38s/it]
 74%|███████▍  | 46030/61904 [1:19:51<5:56:51,  1.35s/it]
 74%|███████▍  | 46031/61904 [1:19:53<6:09:53,  1.40s/it]
 74%|███████▍  | 46032/61904 [1:19:54<5:58:24,  1.35s/it]
 74%|███████▍  | 46033/61904 [1:19:55<5:58:14,  1.35s/it]
 74%|███████▍  | 46034/61904 [1:19:56<5:56:25,  1.35s/it]
 74%|███████▍  | 46035/61904 [1:19:58<5:53:26,  1.34s/it]
 74%|███████▍  | 46036/61904 [1:19:59<6:03:49,  1.38s/it]
 74%|███████▍  | 46037/61904 [1:20:01<5:56:39,  1.35s/it]
 74%|███████▍  | 46038/61904 [1:20:02<6:05:13,  1.38s/it]
 74%|███████▍  | 46039/61904 [1:20:03<6:10:56,  1.40s/it]
 74%|███████▍  | 46040/61904 [1:20:05<6:13:57,  1.41s/it]
                                                         
{'loss': 2.4171, 'learning_rate': 1.2570984052897706e-07, 'epoch': 11.9}

 74%|███████▍  | 46040/61904 [1:20:05<6:13:57,  1.41s/it]
 74%|███████▍  | 46041/61904 [1:20:06<6:00:19,  1.36s/it]
 74%|███████▍  | 46042/61904 [1:20:07<5:55:05,  1.34s/it]
 74%|███████▍  | 46043/61904 [1:20:09<5:50:09,  1.32s/it]
 74%|███████▍  | 46044/61904 [1:20:10<5:51:17,  1.33s/it]
 74%|███████▍  | 46045/61904 [1:20:11<5:41:29,  1.29s/it]
 74%|███████▍  | 46046/61904 [1:20:13<5:40:25,  1.29s/it]
 74%|███████▍  | 46047/61904 [1:20:14<5:59:46,  1.36s/it]
 74%|███████▍  | 46048/61904 [1:20:16<6:05:47,  1.38s/it]
 74%|███████▍  | 46049/61904 [1:20:17<5:54:53,  1.34s/it]
 74%|███████▍  | 46050/61904 [1:20:18<5:55:36,  1.35s/it]
 74%|███████▍  | 46051/61904 [1:20:19<5:50:50,  1.33s/it]
 74%|███████▍  | 46052/61904 [1:20:21<5:53:41,  1.34s/it]
 74%|███████▍  | 46053/61904 [1:20:22<5:51:02,  1.33s/it]
 74%|███████▍  | 46054/61904 [1:20:23<5:51:19,  1.33s/it]
 74%|███████▍  | 46055/61904 [1:20:25<5:53:06,  1.34s/it]
 74%|███████▍  | 46056/61904 [1:20:26<5:54:31,  1.34s/it]
 74%|███████▍  | 46057/61904 [1:20:27<5:43:39,  1.30s/it]
 74%|███████▍  | 46058/61904 [1:20:29<5:55:42,  1.35s/it]
 74%|███████▍  | 46059/61904 [1:20:30<5:53:36,  1.34s/it]
 74%|███████▍  | 46060/61904 [1:20:31<5:57:55,  1.36s/it]
                                                         
{'loss': 2.4597, 'learning_rate': 1.2567742771943472e-07, 'epoch': 11.9}

 74%|███████▍  | 46060/61904 [1:20:31<5:57:55,  1.36s/it]
 74%|███████▍  | 46061/61904 [1:20:33<5:57:23,  1.35s/it]
 74%|███████▍  | 46062/61904 [1:20:34<5:53:55,  1.34s/it]
 74%|███████▍  | 46063/61904 [1:20:36<6:17:17,  1.43s/it]
 74%|███████▍  | 46064/61904 [1:20:37<6:04:45,  1.38s/it]
 74%|███████▍  | 46065/61904 [1:20:38<6:09:16,  1.40s/it]
 74%|███████▍  | 46066/61904 [1:20:40<6:13:46,  1.42s/it]
 74%|███████▍  | 46067/61904 [1:20:41<6:04:51,  1.38s/it]
 74%|███████▍  | 46068/61904 [1:20:42<5:55:12,  1.35s/it]
 74%|███████▍  | 46069/61904 [1:20:44<5:58:00,  1.36s/it]
 74%|███████▍  | 46070/61904 [1:20:45<5:58:48,  1.36s/it]
 74%|███████▍  | 46071/61904 [1:20:47<6:03:48,  1.38s/it]
 74%|███████▍  | 46072/61904 [1:20:48<6:08:51,  1.40s/it]
 74%|███████▍  | 46073/61904 [1:20:50<6:08:47,  1.40s/it]
 74%|███████▍  | 46074/61904 [1:20:51<6:07:59,  1.39s/it]
 74%|███████▍  | 46075/61904 [1:20:52<5:59:28,  1.36s/it]
 74%|███████▍  | 46076/61904 [1:20:54<6:05:55,  1.39s/it]
 74%|███████▍  | 46077/61904 [1:20:55<6:05:09,  1.38s/it]
 74%|███████▍  | 46078/61904 [1:20:57<6:16:07,  1.43s/it]
 74%|███████▍  | 46079/61904 [1:20:58<6:09:31,  1.40s/it]
 74%|███████▍  | 46080/61904 [1:20:59<6:13:28,  1.42s/it]
                                                         
{'loss': 2.4195, 'learning_rate': 1.2564501490989238e-07, 'epoch': 11.91}

 74%|███████▍  | 46080/61904 [1:20:59<6:13:28,  1.42s/it]
 74%|███████▍  | 46081/61904 [1:21:01<6:04:42,  1.38s/it]
 74%|███████▍  | 46082/61904 [1:21:02<5:55:52,  1.35s/it]
 74%|███████▍  | 46083/61904 [1:21:03<5:57:29,  1.36s/it]
 74%|███████▍  | 46084/61904 [1:21:05<6:03:28,  1.38s/it]
 74%|███████▍  | 46085/61904 [1:21:06<6:02:57,  1.38s/it]
 74%|███████▍  | 46086/61904 [1:21:07<5:57:39,  1.36s/it]
 74%|███████▍  | 46087/61904 [1:21:09<6:02:47,  1.38s/it]
 74%|███████▍  | 46088/61904 [1:21:10<6:10:57,  1.41s/it]
 74%|███████▍  | 46089/61904 [1:21:12<6:21:46,  1.45s/it]
 74%|███████▍  | 46090/61904 [1:21:13<6:21:38,  1.45s/it]
 74%|███████▍  | 46091/61904 [1:21:15<6:12:00,  1.41s/it]
 74%|███████▍  | 46092/61904 [1:21:16<6:00:56,  1.37s/it]
 74%|███████▍  | 46093/61904 [1:21:17<5:53:32,  1.34s/it]
 74%|███████▍  | 46094/61904 [1:21:18<5:53:38,  1.34s/it]
 74%|███████▍  | 46095/61904 [1:21:20<5:46:42,  1.32s/it]
 74%|███████▍  | 46096/61904 [1:21:21<5:56:56,  1.35s/it]
 74%|███████▍  | 46097/61904 [1:21:23<5:57:32,  1.36s/it]
 74%|███████▍  | 46098/61904 [1:21:24<5:56:38,  1.35s/it]
 74%|███████▍  | 46099/61904 [1:21:25<5:52:47,  1.34s/it]
 74%|███████▍  | 46100/61904 [1:21:27<5:57:22,  1.36s/it]
                                                         
{'loss': 2.5034, 'learning_rate': 1.2561260210035004e-07, 'epoch': 11.92}

 74%|███████▍  | 46100/61904 [1:21:27<5:57:22,  1.36s/it]
 74%|███████▍  | 46101/61904 [1:21:28<6:01:25,  1.37s/it]
 74%|███████▍  | 46102/61904 [1:21:29<5:53:35,  1.34s/it]
 74%|███████▍  | 46103/61904 [1:21:31<5:53:33,  1.34s/it]
 74%|███████▍  | 46104/61904 [1:21:32<5:57:49,  1.36s/it]
 74%|███████▍  | 46105/61904 [1:21:33<5:58:04,  1.36s/it]
 74%|███████▍  | 46106/61904 [1:21:35<6:10:51,  1.41s/it]
 74%|███████▍  | 46107/61904 [1:21:36<6:14:00,  1.42s/it]
 74%|███████▍  | 46108/61904 [1:21:38<6:08:53,  1.40s/it]
 74%|███████▍  | 46109/61904 [1:21:39<6:04:57,  1.39s/it]
 74%|███████▍  | 46110/61904 [1:21:40<5:55:02,  1.35s/it]
 74%|███████▍  | 46111/61904 [1:21:42<5:51:45,  1.34s/it]
 74%|███████▍  | 46112/61904 [1:21:43<5:53:55,  1.34s/it]
 74%|███████▍  | 46113/61904 [1:21:44<5:52:24,  1.34s/it]
 74%|███████▍  | 46114/61904 [1:21:46<5:54:38,  1.35s/it]
 74%|███████▍  | 46115/61904 [1:21:47<5:52:50,  1.34s/it]
 74%|███████▍  | 46116/61904 [1:21:48<5:53:24,  1.34s/it]
 74%|███████▍  | 46117/61904 [1:21:50<5:59:20,  1.37s/it]
 74%|███████▍  | 46118/61904 [1:21:51<5:57:21,  1.36s/it]
 75%|███████▍  | 46119/61904 [1:21:52<5:51:41,  1.34s/it]
 75%|███████▍  | 46120/61904 [1:21:54<5:50:20,  1.33s/it]
                                                         
{'loss': 2.4407, 'learning_rate': 1.2558018929080773e-07, 'epoch': 11.92}

 75%|███████▍  | 46120/61904 [1:21:54<5:50:20,  1.33s/it]
 75%|███████▍  | 46121/61904 [1:21:55<5:57:09,  1.36s/it]
 75%|███████▍  | 46122/61904 [1:21:57<6:05:08,  1.39s/it]
 75%|███████▍  | 46123/61904 [1:21:58<6:04:05,  1.38s/it]
 75%|███████▍  | 46124/61904 [1:21:59<5:59:14,  1.37s/it]
 75%|███████▍  | 46125/61904 [1:22:01<5:46:32,  1.32s/it]
 75%|███████▍  | 46126/61904 [1:22:02<5:54:55,  1.35s/it]
 75%|███████▍  | 46127/61904 [1:22:03<5:59:06,  1.37s/it]
 75%|███████▍  | 46128/61904 [1:22:05<6:01:30,  1.37s/it]
 75%|███████▍  | 46129/61904 [1:22:06<6:10:23,  1.41s/it]
 75%|███████▍  | 46130/61904 [1:22:08<6:05:56,  1.39s/it]
 75%|███████▍  | 46131/61904 [1:22:09<6:06:48,  1.40s/it]
 75%|███████▍  | 46132/61904 [1:22:10<6:08:55,  1.40s/it]
 75%|███████▍  | 46133/61904 [1:22:12<6:00:01,  1.37s/it]
 75%|███████▍  | 46134/61904 [1:22:13<5:58:05,  1.36s/it]
 75%|███████▍  | 46135/61904 [1:22:14<5:49:56,  1.33s/it]
 75%|███████▍  | 46136/61904 [1:22:16<5:54:29,  1.35s/it]
 75%|███████▍  | 46137/61904 [1:22:17<5:50:38,  1.33s/it]
 75%|███████▍  | 46138/61904 [1:22:18<5:56:55,  1.36s/it]
 75%|███████▍  | 46139/61904 [1:22:20<5:51:33,  1.34s/it]
 75%|███████▍  | 46140/61904 [1:22:21<5:49:06,  1.33s/it]
                                                         
{'loss': 2.4813, 'learning_rate': 1.255477764812654e-07, 'epoch': 11.93}

 75%|███████▍  | 46140/61904 [1:22:21<5:49:06,  1.33s/it]
 75%|███████▍  | 46141/61904 [1:22:23<6:07:11,  1.40s/it]
 75%|███████▍  | 46142/61904 [1:22:24<6:03:20,  1.38s/it]
 75%|███████▍  | 46143/61904 [1:22:25<5:59:21,  1.37s/it]
 75%|███████▍  | 46144/61904 [1:22:27<6:05:23,  1.39s/it]
 75%|███████▍  | 46145/61904 [1:22:28<5:54:41,  1.35s/it]
 75%|███████▍  | 46146/61904 [1:22:29<6:00:19,  1.37s/it]
 75%|███████▍  | 46147/61904 [1:22:31<6:05:15,  1.39s/it]
 75%|███████▍  | 46148/61904 [1:22:32<6:03:35,  1.38s/it]
 75%|███████▍  | 46149/61904 [1:22:34<6:14:21,  1.43s/it]
 75%|███████▍  | 46150/61904 [1:22:35<6:18:41,  1.44s/it]
 75%|███████▍  | 46151/61904 [1:22:37<6:13:38,  1.42s/it]
 75%|███████▍  | 46152/61904 [1:22:38<6:07:32,  1.40s/it]
 75%|███████▍  | 46153/61904 [1:22:39<6:07:27,  1.40s/it]
 75%|███████▍  | 46154/61904 [1:22:41<6:01:59,  1.38s/it]
 75%|███████▍  | 46155/61904 [1:22:42<6:04:30,  1.39s/it]
 75%|███████▍  | 46156/61904 [1:22:43<6:04:11,  1.39s/it]
 75%|███████▍  | 46157/61904 [1:22:45<6:01:48,  1.38s/it]
 75%|███████▍  | 46158/61904 [1:22:46<6:04:23,  1.39s/it]
 75%|███████▍  | 46159/61904 [1:22:48<6:00:17,  1.37s/it]
 75%|███████▍  | 46160/61904 [1:22:49<6:03:29,  1.39s/it]
                                                         
{'loss': 2.4599, 'learning_rate': 1.2551536367172306e-07, 'epoch': 11.93}

 75%|███████▍  | 46160/61904 [1:22:49<6:03:29,  1.39s/it]
 75%|███████▍  | 46161/61904 [1:22:50<6:04:18,  1.39s/it]
 75%|███████▍  | 46162/61904 [1:22:52<5:56:16,  1.36s/it]
 75%|███████▍  | 46163/61904 [1:22:53<5:47:51,  1.33s/it]
 75%|███████▍  | 46164/61904 [1:22:54<5:43:59,  1.31s/it]
 75%|███████▍  | 46165/61904 [1:22:55<5:38:37,  1.29s/it]
 75%|███████▍  | 46166/61904 [1:22:57<5:53:29,  1.35s/it]
 75%|███████▍  | 46167/61904 [1:22:58<5:55:29,  1.36s/it]
 75%|███████▍  | 46168/61904 [1:23:00<5:59:48,  1.37s/it]
 75%|███████▍  | 46169/61904 [1:23:01<5:56:27,  1.36s/it]
 75%|███████▍  | 46170/61904 [1:23:02<5:45:20,  1.32s/it]
 75%|███████▍  | 46171/61904 [1:23:03<5:42:20,  1.31s/it]
 75%|███████▍  | 46172/61904 [1:23:05<5:44:03,  1.31s/it]
 75%|███████▍  | 46173/61904 [1:23:06<5:51:08,  1.34s/it]
 75%|███████▍  | 46174/61904 [1:23:08<6:04:33,  1.39s/it]
 75%|███████▍  | 46175/61904 [1:23:09<6:07:02,  1.40s/it]
 75%|███████▍  | 46176/61904 [1:23:11<6:05:43,  1.40s/it]
 75%|███████▍  | 46177/61904 [1:23:12<6:09:42,  1.41s/it]
 75%|███████▍  | 46178/61904 [1:23:13<6:12:09,  1.42s/it]
 75%|███████▍  | 46179/61904 [1:23:15<6:01:37,  1.38s/it]
 75%|███████▍  | 46180/61904 [1:23:16<6:06:32,  1.40s/it]
                                                         
{'loss': 2.4641, 'learning_rate': 1.2548295086218072e-07, 'epoch': 11.94}

 75%|███████▍  | 46180/61904 [1:23:16<6:06:32,  1.40s/it]
 75%|███████▍  | 46181/61904 [1:23:17<5:59:14,  1.37s/it]
 75%|███████▍  | 46182/61904 [1:23:19<5:54:51,  1.35s/it]
 75%|███████▍  | 46183/61904 [1:23:20<5:49:06,  1.33s/it]
 75%|███████▍  | 46184/61904 [1:23:22<6:00:34,  1.38s/it]
 75%|███████▍  | 46185/61904 [1:23:23<6:12:44,  1.42s/it]
 75%|███████▍  | 46186/61904 [1:23:24<6:11:10,  1.42s/it]
 75%|███████▍  | 46187/61904 [1:23:26<5:57:16,  1.36s/it]
 75%|███████▍  | 46188/61904 [1:23:27<5:46:53,  1.32s/it]
 75%|███████▍  | 46189/61904 [1:23:28<5:57:13,  1.36s/it]
 75%|███████▍  | 46190/61904 [1:23:30<6:00:52,  1.38s/it]
 75%|███████▍  | 46191/61904 [1:23:31<5:58:24,  1.37s/it]
 75%|███████▍  | 46192/61904 [1:23:33<5:56:38,  1.36s/it]
 75%|███████▍  | 46193/61904 [1:23:34<5:54:04,  1.35s/it]
 75%|███████▍  | 46194/61904 [1:23:35<6:03:23,  1.39s/it]
 75%|███████▍  | 46195/61904 [1:23:37<6:02:47,  1.39s/it]
 75%|███████▍  | 46196/61904 [1:23:38<5:59:45,  1.37s/it]
 75%|███████▍  | 46197/61904 [1:23:40<6:15:46,  1.44s/it]
 75%|███████▍  | 46198/61904 [1:23:41<6:04:47,  1.39s/it]
 75%|███████▍  | 46199/61904 [1:23:42<5:55:22,  1.36s/it]
 75%|███████▍  | 46200/61904 [1:23:44<5:53:28,  1.35s/it]
                                                         
{'loss': 2.5262, 'learning_rate': 1.254505380526384e-07, 'epoch': 11.94}

 75%|███████▍  | 46200/61904 [1:23:44<5:53:28,  1.35s/it]
 75%|███████▍  | 46201/61904 [1:23:45<6:00:03,  1.38s/it]
 75%|███████▍  | 46202/61904 [1:23:46<6:03:43,  1.39s/it]
 75%|███████▍  | 46203/61904 [1:23:48<5:55:59,  1.36s/it]
 75%|███████▍  | 46204/61904 [1:23:49<5:57:02,  1.36s/it]
 75%|███████▍  | 46205/61904 [1:23:50<6:00:51,  1.38s/it]
 75%|███████▍  | 46206/61904 [1:23:52<6:03:25,  1.39s/it]
 75%|███████▍  | 46207/61904 [1:23:53<6:00:29,  1.38s/it]
 75%|███████▍  | 46208/61904 [1:23:54<5:52:20,  1.35s/it]
 75%|███████▍  | 46209/61904 [1:23:56<5:46:44,  1.33s/it]
 75%|███████▍  | 46210/61904 [1:23:57<5:43:47,  1.31s/it]
 75%|███████▍  | 46211/61904 [1:23:58<5:46:06,  1.32s/it]
 75%|███████▍  | 46212/61904 [1:24:00<5:49:00,  1.33s/it]
 75%|███████▍  | 46213/61904 [1:24:01<5:50:04,  1.34s/it]
 75%|███████▍  | 46214/61904 [1:24:02<5:53:57,  1.35s/it]
 75%|███████▍  | 46215/61904 [1:24:04<6:07:01,  1.40s/it]
 75%|███████▍  | 46216/61904 [1:24:05<6:03:32,  1.39s/it]
 75%|███████▍  | 46217/61904 [1:24:07<6:09:03,  1.41s/it]
 75%|███████▍  | 46218/61904 [1:24:08<6:16:01,  1.44s/it]
 75%|███████▍  | 46219/61904 [1:24:10<6:07:03,  1.40s/it]
 75%|███████▍  | 46220/61904 [1:24:11<6:04:33,  1.39s/it]
                                                         
{'loss': 2.4518, 'learning_rate': 1.2541812524309607e-07, 'epoch': 11.95}

 75%|███████▍  | 46220/61904 [1:24:11<6:04:33,  1.39s/it]
 75%|███████▍  | 46221/61904 [1:24:12<6:03:30,  1.39s/it]
 75%|███████▍  | 46222/61904 [1:24:14<5:51:09,  1.34s/it]
 75%|███████▍  | 46223/61904 [1:24:15<5:55:03,  1.36s/it]
 75%|███████▍  | 46224/61904 [1:24:16<5:46:53,  1.33s/it]
 75%|███████▍  | 46225/61904 [1:24:18<5:55:52,  1.36s/it]
 75%|███████▍  | 46226/61904 [1:24:19<6:03:49,  1.39s/it]
 75%|███████▍  | 46227/61904 [1:24:21<6:01:28,  1.38s/it]
 75%|███████▍  | 46228/61904 [1:24:22<5:56:41,  1.37s/it]
 75%|███████▍  | 46229/61904 [1:24:23<5:55:36,  1.36s/it]
 75%|███████▍  | 46230/61904 [1:24:25<6:09:17,  1.41s/it]
 75%|███████▍  | 46231/61904 [1:24:26<6:32:44,  1.50s/it]
 75%|███████▍  | 46232/61904 [1:24:28<6:30:42,  1.50s/it]
 75%|███████▍  | 46233/61904 [1:24:29<6:26:31,  1.48s/it]
 75%|███████▍  | 46234/61904 [1:24:31<6:11:18,  1.42s/it]
 75%|███████▍  | 46235/61904 [1:24:32<6:15:48,  1.44s/it]
 75%|███████▍  | 46236/61904 [1:24:34<6:14:07,  1.43s/it]
 75%|███████▍  | 46237/61904 [1:24:35<6:06:51,  1.40s/it]
 75%|███████▍  | 46238/61904 [1:24:36<6:10:38,  1.42s/it]
 75%|███████▍  | 46239/61904 [1:24:38<5:59:33,  1.38s/it]
 75%|███████▍  | 46240/61904 [1:24:39<6:03:14,  1.39s/it]
                                                         
{'loss': 2.5018, 'learning_rate': 1.2538571243355373e-07, 'epoch': 11.95}

 75%|███████▍  | 46240/61904 [1:24:39<6:03:14,  1.39s/it]
 75%|███████▍  | 46241/61904 [1:24:40<5:54:57,  1.36s/it]
 75%|███████▍  | 46242/61904 [1:24:42<6:00:03,  1.38s/it]
 75%|███████▍  | 46243/61904 [1:24:43<6:06:44,  1.41s/it]
 75%|███████▍  | 46244/61904 [1:24:45<5:53:31,  1.35s/it]
 75%|███████▍  | 46245/61904 [1:24:46<6:13:02,  1.43s/it]
 75%|███████▍  | 46246/61904 [1:24:47<6:01:26,  1.39s/it]
 75%|███████▍  | 46247/61904 [1:24:49<6:02:39,  1.39s/it]
 75%|███████▍  | 46248/61904 [1:24:50<6:07:17,  1.41s/it]
 75%|███████▍  | 46249/61904 [1:24:51<5:55:44,  1.36s/it]
 75%|███████▍  | 46250/61904 [1:24:53<5:53:22,  1.35s/it]
 75%|███████▍  | 46251/61904 [1:24:54<6:16:27,  1.44s/it]
 75%|███████▍  | 46252/61904 [1:24:56<6:05:45,  1.40s/it]
 75%|███████▍  | 46253/61904 [1:24:57<5:52:48,  1.35s/it]
 75%|███████▍  | 46254/61904 [1:24:58<5:54:40,  1.36s/it]
 75%|███████▍  | 46255/61904 [1:25:00<6:13:23,  1.43s/it]
 75%|███████▍  | 46256/61904 [1:25:01<6:11:30,  1.42s/it]
 75%|███████▍  | 46257/61904 [1:25:03<6:05:29,  1.40s/it]
 75%|███████▍  | 46258/61904 [1:25:04<6:12:04,  1.43s/it]
 75%|███████▍  | 46259/61904 [1:25:06<6:13:54,  1.43s/it]
 75%|███████▍  | 46260/61904 [1:25:07<6:07:32,  1.41s/it]
                                                         
{'loss': 2.4634, 'learning_rate': 1.253532996240114e-07, 'epoch': 11.96}

 75%|███████▍  | 46260/61904 [1:25:07<6:07:32,  1.41s/it]
 75%|███████▍  | 46261/61904 [1:25:08<5:59:46,  1.38s/it]
 75%|███████▍  | 46262/61904 [1:25:10<5:58:16,  1.37s/it]
 75%|███████▍  | 46263/61904 [1:25:11<5:52:19,  1.35s/it]
 75%|███████▍  | 46264/61904 [1:25:12<5:43:03,  1.32s/it]
 75%|███████▍  | 46265/61904 [1:25:14<5:47:34,  1.33s/it]
 75%|███████▍  | 46266/61904 [1:25:15<5:51:57,  1.35s/it]
 75%|███████▍  | 46267/61904 [1:25:16<5:52:26,  1.35s/it]
 75%|███████▍  | 46268/61904 [1:25:18<5:56:05,  1.37s/it]
 75%|███████▍  | 46269/61904 [1:25:19<6:09:00,  1.42s/it]
 75%|███████▍  | 46270/61904 [1:25:21<6:18:21,  1.45s/it]
 75%|███████▍  | 46271/61904 [1:25:22<6:05:52,  1.40s/it]
 75%|███████▍  | 46272/61904 [1:25:23<5:56:25,  1.37s/it]
 75%|███████▍  | 46273/61904 [1:25:25<5:56:01,  1.37s/it]
 75%|███████▍  | 46274/61904 [1:25:26<6:01:08,  1.39s/it]
 75%|███████▍  | 46275/61904 [1:25:28<6:03:06,  1.39s/it]
 75%|███████▍  | 46276/61904 [1:25:29<6:11:41,  1.43s/it]
 75%|███████▍  | 46277/61904 [1:25:31<6:13:50,  1.44s/it]
 75%|███████▍  | 46278/61904 [1:25:32<6:14:39,  1.44s/it]
 75%|███████▍  | 46279/61904 [1:25:33<6:08:08,  1.41s/it]
 75%|███████▍  | 46280/61904 [1:25:35<6:01:34,  1.39s/it]
                                                         
{'loss': 2.4889, 'learning_rate': 1.2532088681446908e-07, 'epoch': 11.96}

 75%|███████▍  | 46280/61904 [1:25:35<6:01:34,  1.39s/it]
 75%|███████▍  | 46281/61904 [1:25:36<6:06:58,  1.41s/it]
 75%|███████▍  | 46282/61904 [1:25:37<5:55:39,  1.37s/it]
 75%|███████▍  | 46283/61904 [1:25:39<6:02:13,  1.39s/it]
 75%|███████▍  | 46284/61904 [1:25:40<6:03:21,  1.40s/it]
 75%|███████▍  | 46285/61904 [1:25:42<6:02:42,  1.39s/it]
 75%|███████▍  | 46286/61904 [1:25:43<5:50:49,  1.35s/it]
 75%|███████▍  | 46287/61904 [1:25:44<5:46:25,  1.33s/it]
 75%|███████▍  | 46288/61904 [1:25:46<5:48:01,  1.34s/it]
 75%|███████▍  | 46289/61904 [1:25:47<5:58:44,  1.38s/it]
 75%|███████▍  | 46290/61904 [1:25:49<6:26:58,  1.49s/it]
 75%|███████▍  | 46291/61904 [1:25:50<6:22:25,  1.47s/it]
 75%|███████▍  | 46292/61904 [1:25:52<6:19:55,  1.46s/it]
 75%|███████▍  | 46293/61904 [1:25:53<6:18:01,  1.45s/it]
 75%|███████▍  | 46294/61904 [1:25:55<6:17:34,  1.45s/it]
 75%|███████▍  | 46295/61904 [1:25:56<6:18:45,  1.46s/it]
 75%|███████▍  | 46296/61904 [1:25:57<6:03:10,  1.40s/it]
 75%|███████▍  | 46297/61904 [1:25:59<5:57:23,  1.37s/it]
 75%|███████▍  | 46298/61904 [1:26:00<5:45:05,  1.33s/it]
 75%|███████▍  | 46299/61904 [1:26:01<5:43:50,  1.32s/it]
 75%|███████▍  | 46300/61904 [1:26:02<5:40:41,  1.31s/it]
                                                         
{'loss': 2.4577, 'learning_rate': 1.2528847400492674e-07, 'epoch': 11.97}

 75%|███████▍  | 46300/61904 [1:26:02<5:40:41,  1.31s/it]
 75%|███████▍  | 46301/61904 [1:26:04<5:36:51,  1.30s/it]
 75%|███████▍  | 46302/61904 [1:26:05<5:37:48,  1.30s/it]
 75%|███████▍  | 46303/61904 [1:26:06<5:43:48,  1.32s/it]
 75%|███████▍  | 46304/61904 [1:26:08<5:39:30,  1.31s/it]
 75%|███████▍  | 46305/61904 [1:26:09<5:40:47,  1.31s/it]
 75%|███████▍  | 46306/61904 [1:26:10<5:47:37,  1.34s/it]
 75%|███████▍  | 46307/61904 [1:26:12<5:47:24,  1.34s/it]
 75%|███████▍  | 46308/61904 [1:26:13<5:43:53,  1.32s/it]
 75%|███████▍  | 46309/61904 [1:26:14<5:52:19,  1.36s/it]
 75%|███████▍  | 46310/61904 [1:26:16<5:49:10,  1.34s/it]
 75%|███████▍  | 46311/61904 [1:26:17<5:54:56,  1.37s/it]
 75%|███████▍  | 46312/61904 [1:26:19<6:03:04,  1.40s/it]
 75%|███████▍  | 46313/61904 [1:26:20<6:02:52,  1.40s/it]
 75%|███████▍  | 46314/61904 [1:26:21<5:56:34,  1.37s/it]
 75%|███████▍  | 46315/61904 [1:26:23<5:48:45,  1.34s/it]
 75%|███████▍  | 46316/61904 [1:26:24<5:53:24,  1.36s/it]
 75%|███████▍  | 46317/61904 [1:26:25<5:50:55,  1.35s/it]
 75%|███████▍  | 46318/61904 [1:26:27<5:49:40,  1.35s/it]
 75%|███████▍  | 46319/61904 [1:26:28<5:56:09,  1.37s/it]
 75%|███████▍  | 46320/61904 [1:26:29<5:57:44,  1.38s/it]
                                                         
{'loss': 2.4812, 'learning_rate': 1.252560611953844e-07, 'epoch': 11.97}

 75%|███████▍  | 46320/61904 [1:26:29<5:57:44,  1.38s/it]
 75%|███████▍  | 46321/61904 [1:26:31<6:06:32,  1.41s/it]
 75%|███████▍  | 46322/61904 [1:26:32<6:11:32,  1.43s/it]
 75%|███████▍  | 46323/61904 [1:26:34<5:59:38,  1.38s/it]
 75%|███████▍  | 46324/61904 [1:26:35<6:04:43,  1.40s/it]
 75%|███████▍  | 46325/61904 [1:26:36<5:55:31,  1.37s/it]
 75%|███████▍  | 46326/61904 [1:26:38<5:51:54,  1.36s/it]
 75%|███████▍  | 46327/61904 [1:26:39<5:44:12,  1.33s/it]
 75%|███████▍  | 46328/61904 [1:26:41<6:00:08,  1.39s/it]
 75%|███████▍  | 46329/61904 [1:26:42<5:48:25,  1.34s/it]
 75%|███████▍  | 46330/61904 [1:26:43<5:53:06,  1.36s/it]
 75%|███████▍  | 46331/61904 [1:26:45<5:54:11,  1.36s/it]
 75%|███████▍  | 46332/61904 [1:26:46<5:47:57,  1.34s/it]
 75%|███████▍  | 46333/61904 [1:26:47<6:05:48,  1.41s/it]
 75%|███████▍  | 46334/61904 [1:26:49<6:04:49,  1.41s/it]
 75%|███████▍  | 46335/61904 [1:26:50<5:59:54,  1.39s/it]
 75%|███████▍  | 46336/61904 [1:26:52<6:09:39,  1.42s/it]
 75%|███████▍  | 46337/61904 [1:26:53<6:03:43,  1.40s/it]
 75%|███████▍  | 46338/61904 [1:26:54<5:56:24,  1.37s/it]
 75%|███████▍  | 46339/61904 [1:26:56<6:00:46,  1.39s/it]
 75%|███████▍  | 46340/61904 [1:26:57<6:04:40,  1.41s/it]
                                                         
{'loss': 2.4448, 'learning_rate': 1.252236483858421e-07, 'epoch': 11.98}

 75%|███████▍  | 46340/61904 [1:26:57<6:04:40,  1.41s/it]
 75%|███████▍  | 46341/61904 [1:26:59<6:04:56,  1.41s/it]
 75%|███████▍  | 46342/61904 [1:27:00<6:06:45,  1.41s/it]
 75%|███████▍  | 46343/61904 [1:27:01<6:04:54,  1.41s/it]
 75%|███████▍  | 46344/61904 [1:27:03<6:08:17,  1.42s/it]
 75%|███████▍  | 46345/61904 [1:27:04<6:04:01,  1.40s/it]
 75%|███████▍  | 46346/61904 [1:27:05<5:51:24,  1.36s/it]
 75%|███████▍  | 46347/61904 [1:27:07<5:44:55,  1.33s/it]
 75%|███████▍  | 46348/61904 [1:27:08<5:39:35,  1.31s/it]
 75%|███████▍  | 46349/61904 [1:27:10<5:53:33,  1.36s/it]
 75%|███████▍  | 46350/61904 [1:27:11<6:00:56,  1.39s/it]
 75%|███████▍  | 46351/61904 [1:27:12<6:01:08,  1.39s/it]
 75%|███████▍  | 46352/61904 [1:27:14<5:55:00,  1.37s/it]
 75%|███████▍  | 46353/61904 [1:27:15<5:44:52,  1.33s/it]
 75%|███████▍  | 46354/61904 [1:27:16<5:41:44,  1.32s/it]
 75%|███████▍  | 46355/61904 [1:27:18<6:12:32,  1.44s/it]
 75%|███████▍  | 46356/61904 [1:27:19<6:02:09,  1.40s/it]
 75%|███████▍  | 46357/61904 [1:27:21<6:03:56,  1.40s/it]
 75%|███████▍  | 46358/61904 [1:27:22<6:05:21,  1.41s/it]
 75%|███████▍  | 46359/61904 [1:27:23<5:57:09,  1.38s/it]
 75%|███████▍  | 46360/61904 [1:27:25<6:10:54,  1.43s/it]
                                                         
{'loss': 2.4594, 'learning_rate': 1.2519123557629975e-07, 'epoch': 11.98}

 75%|███████▍  | 46360/61904 [1:27:25<6:10:54,  1.43s/it]
 75%|███████▍  | 46361/61904 [1:27:26<6:06:00,  1.41s/it]
 75%|███████▍  | 46362/61904 [1:27:28<6:06:36,  1.42s/it]
 75%|███████▍  | 46363/61904 [1:27:29<5:57:22,  1.38s/it]
 75%|███████▍  | 46364/61904 [1:27:30<5:58:43,  1.39s/it]
 75%|███████▍  | 46365/61904 [1:27:32<5:52:40,  1.36s/it]
 75%|███████▍  | 46366/61904 [1:27:33<5:53:12,  1.36s/it]
 75%|███████▍  | 46367/61904 [1:27:34<5:52:26,  1.36s/it]
 75%|███████▍  | 46368/61904 [1:27:36<5:50:55,  1.36s/it]
 75%|███████▍  | 46369/61904 [1:27:37<5:48:28,  1.35s/it]
 75%|███████▍  | 46370/61904 [1:27:38<5:49:30,  1.35s/it]
 75%|███████▍  | 46371/61904 [1:27:40<5:50:17,  1.35s/it]
 75%|███████▍  | 46372/61904 [1:27:41<5:44:42,  1.33s/it]
 75%|███████▍  | 46373/61904 [1:27:42<5:45:46,  1.34s/it]
 75%|███████▍  | 46374/61904 [1:27:44<6:04:20,  1.41s/it]
 75%|███████▍  | 46375/61904 [1:27:45<6:06:13,  1.41s/it]
 75%|███████▍  | 46376/61904 [1:27:47<6:05:02,  1.41s/it]
 75%|███████▍  | 46377/61904 [1:27:48<5:58:18,  1.38s/it]
 75%|███████▍  | 46378/61904 [1:27:50<5:52:45,  1.36s/it]
 75%|███████▍  | 46379/61904 [1:27:51<5:50:35,  1.35s/it]
 75%|███████▍  | 46380/61904 [1:27:52<5:43:32,  1.33s/it]
                                                         
{'loss': 2.4473, 'learning_rate': 1.2515882276675742e-07, 'epoch': 11.99}

 75%|███████▍  | 46380/61904 [1:27:52<5:43:32,  1.33s/it]
 75%|███████▍  | 46381/61904 [1:27:53<5:47:41,  1.34s/it]
 75%|███████▍  | 46382/61904 [1:27:55<5:53:40,  1.37s/it]
 75%|███████▍  | 46383/61904 [1:27:56<5:47:39,  1.34s/it]
 75%|███████▍  | 46384/61904 [1:27:57<5:44:32,  1.33s/it]
 75%|███████▍  | 46385/61904 [1:27:59<5:49:02,  1.35s/it]
 75%|███████▍  | 46386/61904 [1:28:00<5:56:06,  1.38s/it]
 75%|███████▍  | 46387/61904 [1:28:02<5:52:47,  1.36s/it]
 75%|███████▍  | 46388/61904 [1:28:03<5:52:39,  1.36s/it]
 75%|███████▍  | 46389/61904 [1:28:05<6:07:40,  1.42s/it]
 75%|███████▍  | 46390/61904 [1:28:06<6:04:39,  1.41s/it]
 75%|███████▍  | 46391/61904 [1:28:07<5:58:05,  1.38s/it]
 75%|███████▍  | 46392/61904 [1:28:09<5:51:59,  1.36s/it]
 75%|███████▍  | 46393/61904 [1:28:10<6:01:08,  1.40s/it]
 75%|███████▍  | 46394/61904 [1:28:11<5:57:19,  1.38s/it]
 75%|███████▍  | 46395/61904 [1:28:13<5:55:42,  1.38s/it]
 75%|███████▍  | 46396/61904 [1:28:14<5:51:43,  1.36s/it]
 75%|███████▍  | 46397/61904 [1:28:15<5:47:24,  1.34s/it]
 75%|███████▍  | 46398/61904 [1:28:17<5:47:48,  1.35s/it]
 75%|███████▍  | 46399/61904 [1:28:18<5:58:04,  1.39s/it]
 75%|███████▍  | 46400/61904 [1:28:20<5:59:25,  1.39s/it]
                                                         
{'loss': 2.4831, 'learning_rate': 1.2512640995721508e-07, 'epoch': 11.99}

 75%|███████▍  | 46400/61904 [1:28:20<5:59:25,  1.39s/it]
 75%|███████▍  | 46401/61904 [1:28:21<5:45:28,  1.34s/it]
 75%|███████▍  | 46402/61904 [1:28:22<5:50:03,  1.35s/it]
 75%|███████▍  | 46403/61904 [1:28:24<5:57:16,  1.38s/it]
 75%|███████▍  | 46404/61904 [1:28:25<5:53:32,  1.37s/it]
 75%|███████▍  | 46405/61904 [1:28:26<5:55:36,  1.38s/it]
 75%|███████▍  | 46406/61904 [1:28:28<5:57:37,  1.38s/it]
 75%|███████▍  | 46407/61904 [1:28:29<5:53:15,  1.37s/it]
 75%|███████▍  | 46408/61904 [1:28:31<5:51:44,  1.36s/it]
 75%|███████▍  | 46409/61904 [1:28:32<6:03:10,  1.41s/it]
 75%|███████▍  | 46410/61904 [1:28:33<6:00:21,  1.40s/it]
 75%|███████▍  | 46411/61904 [1:28:35<5:53:18,  1.37s/it]
 75%|███████▍  | 46412/61904 [1:28:36<5:57:28,  1.38s/it]
 75%|███████▍  | 46413/61904 [1:28:38<5:57:04,  1.38s/it]
 75%|███████▍  | 46414/61904 [1:28:39<5:52:35,  1.37s/it]
 75%|███████▍  | 46415/61904 [1:28:40<5:48:58,  1.35s/it]
 75%|███████▍  | 46416/61904 [1:28:41<5:45:52,  1.34s/it]
 75%|███████▍  | 46417/61904 [1:28:43<5:43:19,  1.33s/it]
 75%|███████▍  | 46418/61904 [1:28:44<5:46:09,  1.34s/it]
 75%|███████▍  | 46419/61904 [1:28:46<5:54:07,  1.37s/it]
 75%|███████▍  | 46420/61904 [1:28:47<5:56:51,  1.38s/it]
                                                         
{'loss': 2.4706, 'learning_rate': 1.2509399714767277e-07, 'epoch': 12.0}

 75%|███████▍  | 46420/61904 [1:28:47<5:56:51,  1.38s/it]
 75%|███████▍  | 46421/61904 [1:28:48<5:50:55,  1.36s/it]
 75%|███████▍  | 46422/61904 [1:28:50<5:57:30,  1.39s/it]
 75%|███████▍  | 46423/61904 [1:28:51<5:56:53,  1.38s/it]
 75%|███████▍  | 46424/61904 [1:28:53<6:08:39,  1.43s/it]
 75%|███████▍  | 46425/61904 [1:28:54<5:59:34,  1.39s/it]
 75%|███████▍  | 46426/61904 [1:28:55<6:03:16,  1.41s/it]
 75%|███████▍  | 46427/61904 [1:28:57<5:56:44,  1.38s/it]
 75%|███████▌  | 46428/61904 [1:28:58<6:11:43,  1.44s/it]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/861 [00:00<?, ?it/s]

  0%|          | 2/861 [00:01<07:43,  1.85it/s]

  0%|          | 3/861 [00:03<16:09,  1.13s/it]

  0%|          | 4/861 [00:05<21:52,  1.53s/it]

  1%|          | 5/861 [00:06<18:54,  1.32s/it]

  1%|          | 6/861 [00:07<19:07,  1.34s/it]

  1%|          | 7/861 [00:07<14:56,  1.05s/it]

  1%|          | 8/861 [00:09<15:00,  1.06s/it]

  1%|          | 9/861 [00:09<13:49,  1.03it/s]

  1%|          | 10/861 [00:10<13:06,  1.08it/s]

  1%|▏         | 11/861 [00:12<15:18,  1.08s/it]

  1%|▏         | 12/861 [00:13<16:02,  1.13s/it]

  2%|▏         | 13/861 [00:14<14:47,  1.05s/it]

  2%|▏         | 14/861 [00:14<11:34,  1.22it/s]

  2%|▏         | 15/861 [00:15<10:20,  1.36it/s]

  2%|▏         | 16/861 [00:15<08:41,  1.62it/s]

  2%|▏         | 17/861 [00:16<11:26,  1.23it/s]

  2%|▏         | 18/861 [00:16<08:57,  1.57it/s]

  2%|▏         | 19/861 [00:18<13:27,  1.04it/s]

  2%|▏         | 20/861 [00:19<13:58,  1.00it/s]

  2%|▏         | 21/861 [00:20<12:01,  1.16it/s]

  3%|▎         | 22/861 [00:21<13:54,  1.01it/s]

  3%|▎         | 23/861 [00:21<11:00,  1.27it/s]

  3%|▎         | 24/861 [00:23<13:47,  1.01it/s]

  3%|▎         | 25/861 [00:24<13:46,  1.01it/s]

  3%|▎         | 26/861 [00:25<14:30,  1.04s/it]

  3%|▎         | 27/861 [00:26<15:56,  1.15s/it]

  3%|▎         | 28/861 [00:29<20:28,  1.48s/it]

  3%|▎         | 29/861 [00:29<15:32,  1.12s/it]

  3%|▎         | 30/861 [00:30<17:21,  1.25s/it]

  4%|▎         | 31/861 [00:31<14:19,  1.04s/it]

  4%|▎         | 32/861 [00:31<11:33,  1.19it/s]

  4%|▍         | 33/861 [00:32<12:28,  1.11it/s]

  4%|▍         | 34/861 [00:33<12:25,  1.11it/s]

  4%|▍         | 35/861 [00:35<13:43,  1.00it/s]

  4%|▍         | 36/861 [00:35<13:00,  1.06it/s]

  4%|▍         | 37/861 [00:36<12:54,  1.06it/s]

  4%|▍         | 38/861 [00:37<14:07,  1.03s/it]

  5%|▍         | 39/861 [00:38<12:44,  1.07it/s]

  5%|▍         | 40/861 [00:39<11:49,  1.16it/s]

  5%|▍         | 41/861 [00:39<09:38,  1.42it/s]

  5%|▍         | 42/861 [00:40<11:28,  1.19it/s]

  5%|▍         | 43/861 [00:41<12:09,  1.12it/s]

  5%|▌         | 44/861 [00:42<11:45,  1.16it/s]

  5%|▌         | 45/861 [00:43<11:53,  1.14it/s]

  5%|▌         | 46/861 [00:45<16:14,  1.20s/it]

  5%|▌         | 47/861 [00:46<16:25,  1.21s/it]

  6%|▌         | 48/861 [00:48<18:01,  1.33s/it]

  6%|▌         | 49/861 [00:49<17:20,  1.28s/it]

  6%|▌         | 50/861 [00:49<12:50,  1.05it/s]

  6%|▌         | 51/861 [00:50<12:56,  1.04it/s]

  6%|▌         | 52/861 [00:51<11:57,  1.13it/s]

  6%|▌         | 53/861 [00:52<11:11,  1.20it/s]

  6%|▋         | 54/861 [00:52<08:47,  1.53it/s]

  6%|▋         | 55/861 [00:52<08:24,  1.60it/s]

  7%|▋         | 56/861 [00:53<08:32,  1.57it/s]

  7%|▋         | 57/861 [00:53<07:12,  1.86it/s]

  7%|▋         | 58/861 [00:54<06:15,  2.14it/s]

  7%|▋         | 59/861 [00:55<07:41,  1.74it/s]

  7%|▋         | 60/861 [00:55<08:09,  1.64it/s]

  7%|▋         | 61/861 [00:56<07:23,  1.81it/s]

  7%|▋         | 62/861 [00:56<06:41,  1.99it/s]

  7%|▋         | 63/861 [00:57<06:32,  2.03it/s]

  7%|▋         | 64/861 [00:57<06:35,  2.01it/s]

  8%|▊         | 65/861 [00:58<06:32,  2.03it/s]

  8%|▊         | 66/861 [00:58<06:29,  2.04it/s]

  8%|▊         | 67/861 [00:59<07:48,  1.70it/s]

  8%|▊         | 68/861 [01:00<09:25,  1.40it/s]

  8%|▊         | 69/861 [01:01<10:52,  1.21it/s]

  8%|▊         | 70/861 [01:02<13:12,  1.00s/it]

  8%|▊         | 71/861 [01:04<14:36,  1.11s/it]

  8%|▊         | 72/861 [01:05<13:39,  1.04s/it]

  8%|▊         | 73/861 [01:05<10:38,  1.23it/s]

  9%|▊         | 74/861 [01:06<10:09,  1.29it/s]

  9%|▊         | 75/861 [01:07<11:33,  1.13it/s]

  9%|▉         | 76/861 [01:07<10:03,  1.30it/s]

  9%|▉         | 77/861 [01:08<10:54,  1.20it/s]

  9%|▉         | 78/861 [01:09<10:25,  1.25it/s]

  9%|▉         | 79/861 [01:10<11:36,  1.12it/s]

  9%|▉         | 80/861 [01:10<09:58,  1.30it/s]

  9%|▉         | 81/861 [01:11<10:37,  1.22it/s]

 10%|▉         | 82/861 [01:12<09:27,  1.37it/s]

 10%|▉         | 83/861 [01:13<09:41,  1.34it/s]

 10%|▉         | 84/861 [01:14<11:20,  1.14it/s]

 10%|▉         | 85/861 [01:14<10:22,  1.25it/s]

 10%|▉         | 86/861 [01:15<09:07,  1.41it/s]

 10%|█         | 87/861 [01:16<10:58,  1.17it/s]

 10%|█         | 88/861 [01:16<08:21,  1.54it/s]

 10%|█         | 89/861 [01:17<08:14,  1.56it/s]

 10%|█         | 90/861 [01:19<13:31,  1.05s/it]

 11%|█         | 91/861 [01:20<11:46,  1.09it/s]

 11%|█         | 92/861 [01:20<11:34,  1.11it/s]

 11%|█         | 93/861 [01:22<12:09,  1.05it/s]

 11%|█         | 94/861 [01:22<09:34,  1.34it/s]

 11%|█         | 95/861 [01:22<09:03,  1.41it/s]

 11%|█         | 96/861 [01:23<10:07,  1.26it/s]

 11%|█▏        | 97/861 [01:25<11:40,  1.09it/s]

 11%|█▏        | 98/861 [01:25<11:34,  1.10it/s]

 11%|█▏        | 99/861 [01:27<14:29,  1.14s/it]

 12%|█▏        | 100/861 [01:28<12:14,  1.04it/s]

 12%|█▏        | 101/861 [01:28<10:25,  1.21it/s]

 12%|█▏        | 102/861 [01:29<09:24,  1.34it/s]

 12%|█▏        | 103/861 [01:29<07:59,  1.58it/s]

 12%|█▏        | 104/861 [01:31<11:17,  1.12it/s]

 12%|█▏        | 105/861 [01:32<12:02,  1.05it/s]

 12%|█▏        | 106/861 [01:32<10:10,  1.24it/s]

 12%|█▏        | 107/861 [01:33<09:01,  1.39it/s]

 13%|█▎        | 108/861 [01:33<07:14,  1.73it/s]

 13%|█▎        | 109/861 [01:33<06:02,  2.07it/s]

 13%|█▎        | 110/861 [01:34<07:17,  1.72it/s]

 13%|█▎        | 111/861 [01:35<09:41,  1.29it/s]

 13%|█▎        | 112/861 [01:36<07:56,  1.57it/s]

 13%|█▎        | 113/861 [01:36<08:16,  1.51it/s]

 13%|█▎        | 114/861 [01:37<08:55,  1.40it/s]

 13%|█▎        | 115/861 [01:38<07:40,  1.62it/s]

 13%|█▎        | 116/861 [01:38<06:38,  1.87it/s]

 14%|█▎        | 117/861 [01:39<09:26,  1.31it/s]

 14%|█▎        | 118/861 [01:40<09:20,  1.33it/s]

 14%|█▍        | 119/861 [01:41<08:47,  1.41it/s]

 14%|█▍        | 120/861 [01:41<06:55,  1.79it/s]

 14%|█▍        | 121/861 [01:42<08:36,  1.43it/s]

 14%|█▍        | 122/861 [01:43<10:13,  1.20it/s]

 14%|█▍        | 123/861 [01:44<09:40,  1.27it/s]

 14%|█▍        | 124/861 [01:45<13:43,  1.12s/it]

 15%|█▍        | 125/861 [01:46<12:02,  1.02it/s]

 15%|█▍        | 126/861 [01:47<12:27,  1.02s/it]

 15%|█▍        | 127/861 [01:48<12:34,  1.03s/it]

 15%|█▍        | 128/861 [01:49<10:37,  1.15it/s]

 15%|█▍        | 129/861 [01:50<11:09,  1.09it/s]

 15%|█▌        | 130/861 [01:51<10:55,  1.12it/s]

 15%|█▌        | 131/861 [01:51<10:24,  1.17it/s]

 15%|█▌        | 132/861 [01:53<11:17,  1.08it/s]

 15%|█▌        | 133/861 [01:53<10:58,  1.11it/s]

 16%|█▌        | 134/861 [01:54<08:21,  1.45it/s]

 16%|█▌        | 135/861 [01:54<07:19,  1.65it/s]

 16%|█▌        | 136/861 [01:54<06:58,  1.73it/s]

 16%|█▌        | 137/861 [01:55<06:10,  1.96it/s]

 16%|█▌        | 138/861 [01:55<05:49,  2.07it/s]

 16%|█▌        | 139/861 [01:56<05:17,  2.27it/s]

 16%|█▋        | 140/861 [01:56<05:04,  2.37it/s]

 16%|█▋        | 141/861 [01:56<04:55,  2.44it/s]

 16%|█▋        | 142/861 [01:57<04:47,  2.50it/s]

 17%|█▋        | 143/861 [01:58<08:04,  1.48it/s]

 17%|█▋        | 144/861 [01:59<10:17,  1.16it/s]

 17%|█▋        | 145/861 [02:00<08:54,  1.34it/s]

 17%|█▋        | 146/861 [02:01<08:43,  1.37it/s]

 17%|█▋        | 147/861 [02:01<08:56,  1.33it/s]

 17%|█▋        | 148/861 [02:02<07:09,  1.66it/s]

 17%|█▋        | 149/861 [02:02<06:28,  1.83it/s]

 17%|█▋        | 150/861 [02:04<10:45,  1.10it/s]

 18%|█▊        | 151/861 [02:05<13:01,  1.10s/it]

 18%|█▊        | 152/861 [02:06<11:28,  1.03it/s]

 18%|█▊        | 153/861 [02:07<11:16,  1.05it/s]

 18%|█▊        | 154/861 [02:07<09:13,  1.28it/s]

 18%|█▊        | 155/861 [02:09<12:08,  1.03s/it]

 18%|█▊        | 156/861 [02:10<12:28,  1.06s/it]

 18%|█▊        | 157/861 [02:11<11:14,  1.04it/s]

 18%|█▊        | 158/861 [02:12<11:16,  1.04it/s]

 18%|█▊        | 159/861 [02:12<09:59,  1.17it/s]

 19%|█▊        | 160/861 [02:13<09:48,  1.19it/s]

 19%|█▊        | 161/861 [02:15<13:38,  1.17s/it]

 19%|█▉        | 162/861 [02:15<10:28,  1.11it/s]

 19%|█▉        | 163/861 [02:16<08:12,  1.42it/s]

 19%|█▉        | 164/861 [02:17<11:17,  1.03it/s]

 19%|█▉        | 165/861 [02:18<11:44,  1.01s/it]

 19%|█▉        | 166/861 [02:19<11:11,  1.04it/s]

 19%|█▉        | 167/861 [02:19<08:25,  1.37it/s]

 20%|█▉        | 168/861 [02:20<08:44,  1.32it/s]

 20%|█▉        | 169/861 [02:21<10:16,  1.12it/s]

 20%|█▉        | 170/861 [02:22<10:01,  1.15it/s]

 20%|█▉        | 171/861 [02:23<09:23,  1.22it/s]

 20%|█▉        | 172/861 [02:23<08:23,  1.37it/s]

 20%|██        | 173/861 [02:24<08:13,  1.39it/s]

 20%|██        | 174/861 [02:26<11:25,  1.00it/s]

 20%|██        | 175/861 [02:26<10:25,  1.10it/s]

 20%|██        | 176/861 [02:27<07:59,  1.43it/s]

 21%|██        | 177/861 [02:27<08:29,  1.34it/s]

 21%|██        | 178/861 [02:28<09:17,  1.22it/s]

 21%|██        | 179/861 [02:29<08:56,  1.27it/s]

 21%|██        | 180/861 [02:30<08:28,  1.34it/s]

 21%|██        | 181/861 [02:30<07:15,  1.56it/s]

 21%|██        | 182/861 [02:31<06:26,  1.76it/s]

 21%|██▏       | 183/861 [02:32<07:49,  1.44it/s]

 21%|██▏       | 184/861 [02:33<09:22,  1.20it/s]

 21%|██▏       | 185/861 [02:33<08:14,  1.37it/s]

 22%|██▏       | 186/861 [02:34<07:17,  1.54it/s]

 22%|██▏       | 187/861 [02:35<08:15,  1.36it/s]

 22%|██▏       | 188/861 [02:36<09:09,  1.23it/s]

 22%|██▏       | 189/861 [02:37<11:21,  1.01s/it]

 22%|██▏       | 190/861 [02:38<11:38,  1.04s/it]

 22%|██▏       | 191/861 [02:39<09:37,  1.16it/s]

 22%|██▏       | 192/861 [02:39<09:19,  1.20it/s]

 22%|██▏       | 193/861 [02:40<09:49,  1.13it/s]

 23%|██▎       | 194/861 [02:41<08:37,  1.29it/s]

 23%|██▎       | 195/861 [02:41<07:39,  1.45it/s]

 23%|██▎       | 196/861 [02:42<07:00,  1.58it/s]

 23%|██▎       | 197/861 [02:42<06:30,  1.70it/s]

 23%|██▎       | 198/861 [02:43<05:45,  1.92it/s]

 23%|██▎       | 199/861 [02:44<06:34,  1.68it/s]

 23%|██▎       | 200/861 [02:45<08:07,  1.36it/s]

 23%|██▎       | 201/861 [02:46<09:10,  1.20it/s]

 23%|██▎       | 202/861 [02:47<09:51,  1.11it/s]

 24%|██▎       | 203/861 [02:47<07:49,  1.40it/s]

 24%|██▎       | 204/861 [02:47<06:02,  1.81it/s]

 24%|██▍       | 205/861 [02:48<05:33,  1.97it/s]

 24%|██▍       | 206/861 [02:48<06:08,  1.78it/s]

 24%|██▍       | 207/861 [02:49<06:33,  1.66it/s]

 24%|██▍       | 208/861 [02:50<06:50,  1.59it/s]

 24%|██▍       | 209/861 [02:50<06:47,  1.60it/s]

 24%|██▍       | 210/861 [02:51<07:01,  1.54it/s]

 25%|██▍       | 211/861 [02:52<09:36,  1.13it/s]

 25%|██▍       | 212/861 [02:53<09:38,  1.12it/s]

 25%|██▍       | 213/861 [02:54<08:20,  1.29it/s]

 25%|██▍       | 214/861 [02:54<07:39,  1.41it/s]

 25%|██▍       | 215/861 [02:55<08:21,  1.29it/s]

 25%|██▌       | 216/861 [02:56<07:22,  1.46it/s]

 25%|██▌       | 217/861 [02:56<05:59,  1.79it/s]

 25%|██▌       | 218/861 [02:56<05:20,  2.01it/s]

 25%|██▌       | 219/861 [02:57<06:49,  1.57it/s]

 26%|██▌       | 220/861 [02:58<07:33,  1.41it/s]

 26%|██▌       | 221/861 [02:59<06:43,  1.59it/s]

 26%|██▌       | 222/861 [03:00<08:35,  1.24it/s]

 26%|██▌       | 223/861 [03:01<09:07,  1.16it/s]

 26%|██▌       | 224/861 [03:02<08:28,  1.25it/s]

 26%|██▌       | 225/861 [03:03<10:31,  1.01it/s]

 26%|██▌       | 226/861 [03:05<12:40,  1.20s/it]

 26%|██▋       | 227/861 [03:05<11:16,  1.07s/it]

 26%|██▋       | 228/861 [03:06<11:03,  1.05s/it]

 27%|██▋       | 229/861 [03:07<09:29,  1.11it/s]

 27%|██▋       | 230/861 [03:08<09:42,  1.08it/s]

 27%|██▋       | 231/861 [03:11<15:12,  1.45s/it]

 27%|██▋       | 232/861 [03:11<11:11,  1.07s/it]

 27%|██▋       | 233/861 [03:12<10:03,  1.04it/s]

 27%|██▋       | 234/861 [03:12<08:52,  1.18it/s]

 27%|██▋       | 235/861 [03:13<09:00,  1.16it/s]

 27%|██▋       | 236/861 [03:14<08:27,  1.23it/s]

 28%|██▊       | 237/861 [03:14<08:08,  1.28it/s]

 28%|██▊       | 238/861 [03:15<06:35,  1.57it/s]

 28%|██▊       | 239/861 [03:16<08:05,  1.28it/s]

 28%|██▊       | 240/861 [03:17<08:22,  1.24it/s]

 28%|██▊       | 241/861 [03:18<09:49,  1.05it/s]

 28%|██▊       | 242/861 [03:19<08:28,  1.22it/s]

 28%|██▊       | 243/861 [03:20<09:35,  1.07it/s]

 28%|██▊       | 244/861 [03:21<09:07,  1.13it/s]

 28%|██▊       | 245/861 [03:22<10:01,  1.02it/s]

 29%|██▊       | 246/861 [03:23<09:47,  1.05it/s]

 29%|██▊       | 247/861 [03:23<07:55,  1.29it/s]

 29%|██▉       | 248/861 [03:23<06:04,  1.68it/s]

 29%|██▉       | 249/861 [03:24<05:52,  1.74it/s]

 29%|██▉       | 250/861 [03:25<07:48,  1.30it/s]

 29%|██▉       | 251/861 [03:26<08:04,  1.26it/s]

 29%|██▉       | 252/861 [03:26<07:55,  1.28it/s]

 29%|██▉       | 253/861 [03:27<07:08,  1.42it/s]

 30%|██▉       | 254/861 [03:27<05:46,  1.75it/s]

 30%|██▉       | 255/861 [03:28<06:16,  1.61it/s]

 30%|██▉       | 256/861 [03:29<08:07,  1.24it/s]

 30%|██▉       | 257/861 [03:30<08:22,  1.20it/s]

 30%|██▉       | 258/861 [03:31<08:47,  1.14it/s]

 30%|███       | 259/861 [03:32<09:38,  1.04it/s]

 30%|███       | 260/861 [03:33<09:45,  1.03it/s]

 30%|███       | 261/861 [03:36<13:48,  1.38s/it]

 30%|███       | 262/861 [03:36<11:29,  1.15s/it]

 31%|███       | 263/861 [03:36<08:32,  1.17it/s]

 31%|███       | 264/861 [03:37<07:46,  1.28it/s]

 31%|███       | 265/861 [03:37<06:48,  1.46it/s]

 31%|███       | 266/861 [03:38<05:41,  1.74it/s]

 31%|███       | 267/861 [03:38<05:29,  1.81it/s]

 31%|███       | 268/861 [03:39<05:56,  1.67it/s]

 31%|███       | 269/861 [03:40<06:05,  1.62it/s]

 31%|███▏      | 270/861 [03:40<06:16,  1.57it/s]

 31%|███▏      | 271/861 [03:41<06:43,  1.46it/s]

 32%|███▏      | 272/861 [03:42<08:38,  1.13it/s]

 32%|███▏      | 273/861 [03:43<08:51,  1.11it/s]

 32%|███▏      | 274/861 [03:45<10:20,  1.06s/it]

 32%|███▏      | 275/861 [03:45<07:44,  1.26it/s]

 32%|███▏      | 276/861 [03:46<08:07,  1.20it/s]

 32%|███▏      | 277/861 [03:47<10:03,  1.03s/it]

 32%|███▏      | 278/861 [03:49<10:42,  1.10s/it]

 32%|███▏      | 279/861 [03:50<10:07,  1.04s/it]

 33%|███▎      | 280/861 [03:51<09:59,  1.03s/it]

 33%|███▎      | 281/861 [03:52<10:51,  1.12s/it]

 33%|███▎      | 282/861 [03:53<09:53,  1.03s/it]

 33%|███▎      | 283/861 [03:53<08:54,  1.08it/s]

 33%|███▎      | 284/861 [03:54<07:21,  1.31it/s]

 33%|███▎      | 285/861 [03:54<06:58,  1.38it/s]

 33%|███▎      | 286/861 [03:56<10:42,  1.12s/it]

 33%|███▎      | 287/861 [03:58<12:22,  1.29s/it]

 33%|███▎      | 288/861 [03:59<11:06,  1.16s/it]

 34%|███▎      | 289/861 [03:59<08:44,  1.09it/s]

 34%|███▎      | 290/861 [04:00<07:54,  1.20it/s]

 34%|███▍      | 291/861 [04:01<07:43,  1.23it/s]

 34%|███▍      | 292/861 [04:02<09:12,  1.03it/s]

 34%|███▍      | 293/861 [04:03<09:02,  1.05it/s]

 34%|███▍      | 294/861 [04:04<09:30,  1.01s/it]

 34%|███▍      | 295/861 [04:04<07:16,  1.30it/s]

 34%|███▍      | 296/861 [04:05<06:57,  1.35it/s]

 34%|███▍      | 297/861 [04:06<08:49,  1.06it/s]

 35%|███▍      | 298/861 [04:08<09:44,  1.04s/it]

 35%|███▍      | 299/861 [04:10<11:45,  1.26s/it]

 35%|███▍      | 300/861 [04:10<09:55,  1.06s/it]

 35%|███▍      | 301/861 [04:13<13:42,  1.47s/it]

 35%|███▌      | 302/861 [04:13<10:17,  1.11s/it]

 35%|███▌      | 303/861 [04:14<11:15,  1.21s/it]

 35%|███▌      | 304/861 [04:15<11:13,  1.21s/it]

 35%|███▌      | 305/861 [04:17<11:44,  1.27s/it]

 36%|███▌      | 306/861 [04:18<12:05,  1.31s/it]

 36%|███▌      | 307/861 [04:20<13:53,  1.50s/it]

 36%|███▌      | 308/861 [04:20<10:11,  1.11s/it]

 36%|███▌      | 309/861 [04:21<07:59,  1.15it/s]

 36%|███▌      | 310/861 [04:21<07:24,  1.24it/s]

 36%|███▌      | 311/861 [04:23<08:20,  1.10it/s]

 36%|███▌      | 312/861 [04:24<08:53,  1.03it/s]

 36%|███▋      | 313/861 [04:25<10:42,  1.17s/it]

 36%|███▋      | 314/861 [04:26<10:10,  1.12s/it]

 37%|███▋      | 315/861 [04:27<08:45,  1.04it/s]

 37%|███▋      | 316/861 [04:28<09:23,  1.03s/it]

 37%|███▋      | 317/861 [04:28<07:04,  1.28it/s]

 37%|███▋      | 318/861 [04:29<05:39,  1.60it/s]

 37%|███▋      | 319/861 [04:30<08:36,  1.05it/s]

 37%|███▋      | 320/861 [04:31<07:55,  1.14it/s]

 37%|███▋      | 321/861 [04:32<09:22,  1.04s/it]

 37%|███▋      | 322/861 [04:34<11:29,  1.28s/it]

 38%|███▊      | 323/861 [04:35<10:35,  1.18s/it]

 38%|███▊      | 324/861 [04:37<11:08,  1.24s/it]

 38%|███▊      | 325/861 [04:38<11:02,  1.24s/it]

 38%|███▊      | 326/861 [04:38<08:13,  1.08it/s]

 38%|███▊      | 327/861 [04:39<08:10,  1.09it/s]

 38%|███▊      | 328/861 [04:40<08:28,  1.05it/s]

 38%|███▊      | 329/861 [04:41<09:09,  1.03s/it]

 38%|███▊      | 330/861 [04:42<08:26,  1.05it/s]

 38%|███▊      | 331/861 [04:45<14:05,  1.59s/it]

 39%|███▊      | 332/861 [04:46<12:09,  1.38s/it]

 39%|███▊      | 333/861 [04:48<12:59,  1.48s/it]

 39%|███▉      | 334/861 [04:49<12:54,  1.47s/it]

 39%|███▉      | 335/861 [04:50<10:45,  1.23s/it]

 39%|███▉      | 336/861 [04:51<11:19,  1.30s/it]

 39%|███▉      | 337/861 [04:52<09:33,  1.09s/it]

 39%|███▉      | 338/861 [04:53<08:52,  1.02s/it]

 39%|███▉      | 339/861 [04:54<09:18,  1.07s/it]

 39%|███▉      | 340/861 [04:54<07:31,  1.15it/s]

 40%|███▉      | 341/861 [04:54<05:58,  1.45it/s]

 40%|███▉      | 342/861 [04:55<05:55,  1.46it/s]

 40%|███▉      | 343/861 [04:56<06:24,  1.35it/s]

 40%|███▉      | 344/861 [04:56<05:38,  1.53it/s]

 40%|████      | 345/861 [04:58<06:41,  1.29it/s]

 40%|████      | 346/861 [04:58<07:08,  1.20it/s]

 40%|████      | 347/861 [04:59<06:04,  1.41it/s]

 40%|████      | 348/861 [04:59<05:48,  1.47it/s]

 41%|████      | 349/861 [05:00<05:55,  1.44it/s]

 41%|████      | 350/861 [05:01<06:34,  1.29it/s]

 41%|████      | 351/861 [05:02<06:25,  1.32it/s]

 41%|████      | 352/861 [05:03<06:36,  1.28it/s]

 41%|████      | 353/861 [05:03<06:15,  1.35it/s]

 41%|████      | 354/861 [05:04<05:56,  1.42it/s]

 41%|████      | 355/861 [05:04<05:11,  1.62it/s]

 41%|████▏     | 356/861 [05:05<04:40,  1.80it/s]

 41%|████▏     | 357/861 [05:05<04:00,  2.10it/s]

 42%|████▏     | 358/861 [05:06<04:40,  1.79it/s]

 42%|████▏     | 359/861 [05:07<06:44,  1.24it/s]

 42%|████▏     | 360/861 [05:09<08:07,  1.03it/s]

 42%|████▏     | 361/861 [05:09<07:45,  1.07it/s]

 42%|████▏     | 362/861 [05:11<08:08,  1.02it/s]

 42%|████▏     | 363/861 [05:11<07:19,  1.13it/s]

 42%|████▏     | 364/861 [05:12<06:42,  1.23it/s]

 42%|████▏     | 365/861 [05:14<10:05,  1.22s/it]

 43%|████▎     | 366/861 [05:15<09:09,  1.11s/it]

 43%|████▎     | 367/861 [05:17<10:32,  1.28s/it]

 43%|████▎     | 368/861 [05:18<11:32,  1.40s/it]

 43%|████▎     | 369/861 [05:19<10:04,  1.23s/it]

 43%|████▎     | 370/861 [05:20<08:44,  1.07s/it]

 43%|████▎     | 371/861 [05:21<07:57,  1.03it/s]

 43%|████▎     | 372/861 [05:22<08:21,  1.03s/it]

 43%|████▎     | 373/861 [05:22<07:23,  1.10it/s]

 43%|████▎     | 374/861 [05:25<10:58,  1.35s/it]

 44%|████▎     | 375/861 [05:27<12:34,  1.55s/it]

 44%|████▎     | 376/861 [05:27<10:27,  1.29s/it]

 44%|████▍     | 377/861 [05:29<11:35,  1.44s/it]

 44%|████▍     | 378/861 [05:31<12:37,  1.57s/it]

 44%|████▍     | 379/861 [05:31<09:14,  1.15s/it]

 44%|████▍     | 380/861 [05:32<08:33,  1.07s/it]

 44%|████▍     | 381/861 [05:33<08:01,  1.00s/it]

 44%|████▍     | 382/861 [05:34<07:06,  1.12it/s]

 44%|████▍     | 383/861 [05:34<07:07,  1.12it/s]

 45%|████▍     | 384/861 [05:35<06:51,  1.16it/s]

 45%|████▍     | 385/861 [05:36<05:37,  1.41it/s]

 45%|████▍     | 386/861 [05:36<05:49,  1.36it/s]

 45%|████▍     | 387/861 [05:38<07:40,  1.03it/s]

 45%|████▌     | 388/861 [05:39<07:02,  1.12it/s]

 45%|████▌     | 389/861 [05:39<05:57,  1.32it/s]

 45%|████▌     | 390/861 [05:40<05:28,  1.44it/s]

 45%|████▌     | 391/861 [05:40<05:50,  1.34it/s]

 46%|████▌     | 392/861 [05:41<06:14,  1.25it/s]

 46%|████▌     | 393/861 [05:43<07:34,  1.03it/s]

 46%|████▌     | 394/861 [05:44<08:22,  1.08s/it]

 46%|████▌     | 395/861 [05:45<07:11,  1.08it/s]

 46%|████▌     | 396/861 [05:45<06:00,  1.29it/s]

 46%|████▌     | 397/861 [05:45<04:38,  1.67it/s]

 46%|████▌     | 398/861 [05:46<05:10,  1.49it/s]

 46%|████▋     | 399/861 [05:47<06:08,  1.25it/s]

 46%|████▋     | 400/861 [05:48<06:47,  1.13it/s]

 47%|████▋     | 401/861 [05:49<05:43,  1.34it/s]

 47%|████▋     | 402/861 [05:49<05:39,  1.35it/s]

 47%|████▋     | 403/861 [05:50<05:37,  1.36it/s]

 47%|████▋     | 404/861 [05:51<06:18,  1.21it/s]

 47%|████▋     | 405/861 [05:52<05:18,  1.43it/s]

 47%|████▋     | 406/861 [05:53<06:34,  1.15it/s]

 47%|████▋     | 407/861 [05:54<06:51,  1.10it/s]

 47%|████▋     | 408/861 [05:55<06:16,  1.20it/s]

 48%|████▊     | 409/861 [05:55<05:32,  1.36it/s]

 48%|████▊     | 410/861 [05:56<05:31,  1.36it/s]

 48%|████▊     | 411/861 [05:56<04:38,  1.61it/s]

 48%|████▊     | 412/861 [05:58<06:33,  1.14it/s]

 48%|████▊     | 413/861 [05:58<06:10,  1.21it/s]

 48%|████▊     | 414/861 [05:59<05:26,  1.37it/s]

 48%|████▊     | 415/861 [05:59<04:42,  1.58it/s]

 48%|████▊     | 416/861 [06:00<04:37,  1.60it/s]

 48%|████▊     | 417/861 [06:00<04:35,  1.61it/s]

 49%|████▊     | 418/861 [06:01<04:26,  1.66it/s]

 49%|████▊     | 419/861 [06:02<05:10,  1.42it/s]

 49%|████▉     | 420/861 [06:03<05:03,  1.45it/s]

 49%|████▉     | 421/861 [06:03<04:41,  1.57it/s]

 49%|████▉     | 422/861 [06:04<04:05,  1.79it/s]

 49%|████▉     | 423/861 [06:05<05:02,  1.45it/s]

 49%|████▉     | 424/861 [06:05<04:43,  1.54it/s]

 49%|████▉     | 425/861 [06:06<04:54,  1.48it/s]

 49%|████▉     | 426/861 [06:07<05:38,  1.29it/s]

 50%|████▉     | 427/861 [06:08<05:51,  1.23it/s]

 50%|████▉     | 428/861 [06:08<05:44,  1.26it/s]

 50%|████▉     | 429/861 [06:09<05:36,  1.28it/s]

 50%|████▉     | 430/861 [06:10<06:07,  1.17it/s]

 50%|█████     | 431/861 [06:12<07:18,  1.02s/it]

 50%|█████     | 432/861 [06:13<08:11,  1.15s/it]

 50%|█████     | 433/861 [06:14<08:24,  1.18s/it]

 50%|█████     | 434/861 [06:15<06:50,  1.04it/s]

 51%|█████     | 435/861 [06:15<05:09,  1.38it/s]

 51%|█████     | 436/861 [06:15<04:11,  1.69it/s]

 51%|█████     | 437/861 [06:16<04:01,  1.76it/s]

 51%|█████     | 438/861 [06:16<03:30,  2.01it/s]

 51%|█████     | 439/861 [06:17<03:48,  1.84it/s]

 51%|█████     | 440/861 [06:17<03:17,  2.13it/s]

 51%|█████     | 441/861 [06:17<02:57,  2.37it/s]

 51%|█████▏    | 442/861 [06:18<03:09,  2.21it/s]

 51%|█████▏    | 443/861 [06:18<03:18,  2.11it/s]

 52%|█████▏    | 444/861 [06:19<03:31,  1.97it/s]

 52%|█████▏    | 445/861 [06:19<03:08,  2.21it/s]

 52%|█████▏    | 446/861 [06:20<02:59,  2.31it/s]

 52%|█████▏    | 447/861 [06:21<04:12,  1.64it/s]

 52%|█████▏    | 448/861 [06:22<05:28,  1.26it/s]

 52%|█████▏    | 449/861 [06:23<06:19,  1.09it/s]

 52%|█████▏    | 450/861 [06:24<06:40,  1.03it/s]

 52%|█████▏    | 451/861 [06:25<05:44,  1.19it/s]

 52%|█████▏    | 452/861 [06:25<05:19,  1.28it/s]

 53%|█████▎    | 453/861 [06:26<04:38,  1.46it/s]

 53%|█████▎    | 454/861 [06:26<04:24,  1.54it/s]

 53%|█████▎    | 455/861 [06:27<03:48,  1.78it/s]

 53%|█████▎    | 456/861 [06:27<03:44,  1.81it/s]

 53%|█████▎    | 457/861 [06:28<03:51,  1.74it/s]

 53%|█████▎    | 458/861 [06:29<04:22,  1.54it/s]

 53%|█████▎    | 459/861 [06:29<03:41,  1.81it/s]

 53%|█████▎    | 460/861 [06:30<03:54,  1.71it/s]

 54%|█████▎    | 461/861 [06:31<04:40,  1.43it/s]

 54%|█████▎    | 462/861 [06:31<04:18,  1.54it/s]

 54%|█████▍    | 463/861 [06:32<04:26,  1.49it/s]

 54%|█████▍    | 464/861 [06:32<03:54,  1.70it/s]

 54%|█████▍    | 465/861 [06:33<03:06,  2.12it/s]

 54%|█████▍    | 466/861 [06:33<03:13,  2.04it/s]

 54%|█████▍    | 467/861 [06:34<04:28,  1.47it/s]

 54%|█████▍    | 468/861 [06:35<03:43,  1.76it/s]

 54%|█████▍    | 469/861 [06:35<03:43,  1.75it/s]

 55%|█████▍    | 470/861 [06:35<03:07,  2.09it/s]

 55%|█████▍    | 471/861 [06:36<03:08,  2.07it/s]

 55%|█████▍    | 472/861 [06:36<03:09,  2.06it/s]

 55%|█████▍    | 473/861 [06:37<03:16,  1.98it/s]

 55%|█████▌    | 474/861 [06:37<02:48,  2.29it/s]

 55%|█████▌    | 475/861 [06:38<03:16,  1.96it/s]

 55%|█████▌    | 476/861 [06:38<03:00,  2.14it/s]

 55%|█████▌    | 477/861 [06:39<03:40,  1.74it/s]

 56%|█████▌    | 478/861 [06:40<03:31,  1.81it/s]

 56%|█████▌    | 479/861 [06:40<02:54,  2.19it/s]

 56%|█████▌    | 480/861 [06:40<03:16,  1.94it/s]

 56%|█████▌    | 481/861 [06:41<02:51,  2.22it/s]

 56%|█████▌    | 482/861 [06:41<02:34,  2.45it/s]

 56%|█████▌    | 483/861 [06:41<02:18,  2.74it/s]

 56%|█████▌    | 484/861 [06:42<02:25,  2.58it/s]

 56%|█████▋    | 485/861 [06:42<02:12,  2.85it/s]

 56%|█████▋    | 486/861 [06:42<01:58,  3.16it/s]

 57%|█████▋    | 487/861 [06:43<02:33,  2.44it/s]

 57%|█████▋    | 488/861 [06:43<02:13,  2.80it/s]

 57%|█████▋    | 489/861 [06:44<02:17,  2.71it/s]

 57%|█████▋    | 490/861 [06:44<02:09,  2.86it/s]

 57%|█████▋    | 491/861 [06:44<02:15,  2.74it/s]

 57%|█████▋    | 492/861 [06:45<02:19,  2.64it/s]

 57%|█████▋    | 493/861 [06:45<02:25,  2.52it/s]

 57%|█████▋    | 494/861 [06:45<02:10,  2.80it/s]

 57%|█████▋    | 495/861 [06:46<03:25,  1.78it/s]

 58%|█████▊    | 496/861 [06:47<03:54,  1.56it/s]

 58%|█████▊    | 497/861 [06:47<03:09,  1.92it/s]

 58%|█████▊    | 498/861 [06:48<02:54,  2.08it/s]

 58%|█████▊    | 499/861 [06:48<02:30,  2.40it/s]

 58%|█████▊    | 500/861 [06:49<02:44,  2.20it/s]

 58%|█████▊    | 501/861 [06:49<02:23,  2.52it/s]

 58%|█████▊    | 502/861 [06:50<02:54,  2.06it/s]

 58%|█████▊    | 503/861 [06:50<02:47,  2.13it/s]

 59%|█████▊    | 504/861 [06:51<02:47,  2.14it/s]

 59%|█████▊    | 505/861 [06:51<02:26,  2.43it/s]

 59%|█████▉    | 506/861 [06:51<02:11,  2.69it/s]

 59%|█████▉    | 507/861 [06:51<02:01,  2.92it/s]

 59%|█████▉    | 508/861 [06:52<02:57,  1.99it/s]

 59%|█████▉    | 509/861 [06:53<03:52,  1.51it/s]

 59%|█████▉    | 510/861 [06:54<03:35,  1.63it/s]

 59%|█████▉    | 511/861 [06:54<03:30,  1.66it/s]

 59%|█████▉    | 512/861 [06:55<03:20,  1.74it/s]

 60%|█████▉    | 513/861 [06:55<03:26,  1.68it/s]

 60%|█████▉    | 514/861 [06:56<03:12,  1.80it/s]

 60%|█████▉    | 515/861 [06:56<02:32,  2.27it/s]

 60%|█████▉    | 516/861 [06:56<02:07,  2.70it/s]

 60%|██████    | 517/861 [06:57<01:55,  2.97it/s]

 60%|██████    | 518/861 [06:57<02:12,  2.59it/s]

 60%|██████    | 519/861 [06:58<02:49,  2.02it/s]

 60%|██████    | 520/861 [06:58<03:02,  1.87it/s]

 61%|██████    | 521/861 [06:59<02:35,  2.19it/s]

 61%|██████    | 522/861 [06:59<02:51,  1.98it/s]

 61%|██████    | 523/861 [07:00<03:36,  1.56it/s]

 61%|██████    | 524/861 [07:02<04:33,  1.23it/s]

 61%|██████    | 525/861 [07:02<03:56,  1.42it/s]

 61%|██████    | 526/861 [07:03<03:55,  1.42it/s]

 61%|██████    | 527/861 [07:03<03:51,  1.44it/s]

 61%|██████▏   | 528/861 [07:04<04:27,  1.25it/s]

 61%|██████▏   | 529/861 [07:05<03:39,  1.51it/s]

 62%|██████▏   | 530/861 [07:05<03:09,  1.75it/s]

 62%|██████▏   | 531/861 [07:06<02:59,  1.84it/s]

 62%|██████▏   | 532/861 [07:06<03:11,  1.72it/s]

 62%|██████▏   | 533/861 [07:07<02:55,  1.87it/s]

 62%|██████▏   | 534/861 [07:07<03:00,  1.81it/s]

 62%|██████▏   | 535/861 [07:08<02:57,  1.84it/s]

 62%|██████▏   | 536/861 [07:08<03:02,  1.78it/s]

 62%|██████▏   | 537/861 [07:10<04:40,  1.16it/s]

 62%|██████▏   | 538/861 [07:10<03:53,  1.38it/s]

 63%|██████▎   | 539/861 [07:12<06:01,  1.12s/it]

 63%|██████▎   | 540/861 [07:13<05:35,  1.04s/it]

 63%|██████▎   | 541/861 [07:14<04:38,  1.15it/s]

 63%|██████▎   | 542/861 [07:14<03:38,  1.46it/s]

 63%|██████▎   | 543/861 [07:15<03:36,  1.47it/s]

 63%|██████▎   | 544/861 [07:15<03:20,  1.58it/s]

 63%|██████▎   | 545/861 [07:17<04:26,  1.19it/s]

 63%|██████▎   | 546/861 [07:18<04:47,  1.10it/s]

 64%|██████▎   | 547/861 [07:18<04:25,  1.18it/s]

 64%|██████▎   | 548/861 [07:20<05:09,  1.01it/s]

 64%|██████▍   | 549/861 [07:21<05:18,  1.02s/it]

 64%|██████▍   | 550/861 [07:22<04:57,  1.05it/s]

 64%|██████▍   | 551/861 [07:22<04:34,  1.13it/s]

 64%|██████▍   | 552/861 [07:23<04:23,  1.17it/s]

 64%|██████▍   | 553/861 [07:24<04:55,  1.04it/s]

 64%|██████▍   | 554/861 [07:26<05:29,  1.07s/it]

 64%|██████▍   | 555/861 [07:27<06:19,  1.24s/it]

 65%|██████▍   | 556/861 [07:28<06:18,  1.24s/it]

 65%|██████▍   | 557/861 [07:30<06:50,  1.35s/it]

 65%|██████▍   | 558/861 [07:31<05:53,  1.17s/it]

 65%|██████▍   | 559/861 [07:32<06:30,  1.29s/it]

 65%|██████▌   | 560/861 [07:34<06:17,  1.26s/it]

 65%|██████▌   | 561/861 [07:35<05:59,  1.20s/it]

 65%|██████▌   | 562/861 [07:35<05:23,  1.08s/it]

 65%|██████▌   | 563/861 [07:36<04:52,  1.02it/s]

 66%|██████▌   | 564/861 [07:37<04:46,  1.04it/s]

 66%|██████▌   | 565/861 [07:38<04:30,  1.09it/s]

 66%|██████▌   | 566/861 [07:39<05:13,  1.06s/it]

 66%|██████▌   | 567/861 [07:41<05:33,  1.14s/it]

 66%|██████▌   | 568/861 [07:42<05:45,  1.18s/it]

 66%|██████▌   | 569/861 [07:43<05:15,  1.08s/it]

 66%|██████▌   | 570/861 [07:44<05:30,  1.14s/it]

 66%|██████▋   | 571/861 [07:45<05:40,  1.17s/it]

 66%|██████▋   | 572/861 [07:46<05:42,  1.19s/it]

 67%|██████▋   | 573/861 [07:47<04:55,  1.03s/it]

 67%|██████▋   | 574/861 [07:49<05:39,  1.18s/it]

 67%|██████▋   | 575/861 [07:50<05:16,  1.11s/it]

 67%|██████▋   | 576/861 [07:52<06:23,  1.34s/it]

 67%|██████▋   | 577/861 [07:53<06:57,  1.47s/it]

 67%|██████▋   | 578/861 [07:55<06:58,  1.48s/it]

 67%|██████▋   | 579/861 [07:57<07:37,  1.62s/it]

 67%|██████▋   | 580/861 [07:58<06:56,  1.48s/it]

 67%|██████▋   | 581/861 [07:59<06:18,  1.35s/it]

 68%|██████▊   | 582/861 [08:01<07:14,  1.56s/it]

 68%|██████▊   | 583/861 [08:02<06:38,  1.43s/it]

 68%|██████▊   | 584/861 [08:03<06:02,  1.31s/it]

 68%|██████▊   | 585/861 [08:04<05:15,  1.14s/it]

 68%|██████▊   | 586/861 [08:04<04:28,  1.02it/s]

 68%|██████▊   | 587/861 [08:06<04:37,  1.01s/it]

 68%|██████▊   | 588/861 [08:07<04:31,  1.01it/s]

 68%|██████▊   | 589/861 [08:07<04:11,  1.08it/s]

 69%|██████▊   | 590/861 [08:09<04:59,  1.11s/it]

 69%|██████▊   | 591/861 [08:09<04:14,  1.06it/s]

 69%|██████▉   | 592/861 [08:11<04:36,  1.03s/it]

 69%|██████▉   | 593/861 [08:12<05:35,  1.25s/it]

 69%|██████▉   | 594/861 [08:14<05:49,  1.31s/it]

 69%|██████▉   | 595/861 [08:14<04:54,  1.11s/it]

 69%|██████▉   | 596/861 [08:15<04:00,  1.10it/s]

 69%|██████▉   | 597/861 [08:15<03:30,  1.26it/s]

 69%|██████▉   | 598/861 [08:16<03:40,  1.19it/s]

 70%|██████▉   | 599/861 [08:17<03:43,  1.17it/s]

 70%|██████▉   | 600/861 [08:18<03:28,  1.25it/s]

 70%|██████▉   | 601/861 [08:19<03:21,  1.29it/s]

 70%|██████▉   | 602/861 [08:20<04:43,  1.10s/it]

 70%|███████   | 603/861 [08:22<05:10,  1.20s/it]

 70%|███████   | 604/861 [08:23<04:44,  1.11s/it]

 70%|███████   | 605/861 [08:23<04:04,  1.05it/s]

 70%|███████   | 606/861 [08:24<04:01,  1.06it/s]

 70%|███████   | 607/861 [08:25<03:43,  1.14it/s]

 71%|███████   | 608/861 [08:26<03:21,  1.25it/s]

 71%|███████   | 609/861 [08:27<03:30,  1.20it/s]

 71%|███████   | 610/861 [08:28<04:27,  1.07s/it]

 71%|███████   | 611/861 [08:29<04:35,  1.10s/it]

 71%|███████   | 612/861 [08:31<04:37,  1.11s/it]

 71%|███████   | 613/861 [08:31<03:46,  1.10it/s]

 71%|███████▏  | 614/861 [08:32<04:05,  1.00it/s]

 71%|███████▏  | 615/861 [08:33<04:12,  1.02s/it]

 72%|███████▏  | 616/861 [08:35<05:38,  1.38s/it]

 72%|███████▏  | 617/861 [08:37<05:40,  1.39s/it]

 72%|███████▏  | 618/861 [08:38<05:28,  1.35s/it]

 72%|███████▏  | 619/861 [08:39<05:08,  1.27s/it]

 72%|███████▏  | 620/861 [08:41<05:22,  1.34s/it]

 72%|███████▏  | 621/861 [08:42<05:11,  1.30s/it]

 72%|███████▏  | 622/861 [08:42<04:12,  1.05s/it]

 72%|███████▏  | 623/861 [08:44<05:07,  1.29s/it]

 72%|███████▏  | 624/861 [08:45<04:18,  1.09s/it]

 73%|███████▎  | 625/861 [08:45<03:40,  1.07it/s]

 73%|███████▎  | 626/861 [08:46<03:32,  1.11it/s]

 73%|███████▎  | 627/861 [08:47<03:23,  1.15it/s]

 73%|███████▎  | 628/861 [08:48<03:42,  1.05it/s]

 73%|███████▎  | 629/861 [08:49<03:54,  1.01s/it]

 73%|███████▎  | 630/861 [08:50<03:26,  1.12it/s]

 73%|███████▎  | 631/861 [08:50<02:47,  1.37it/s]

 73%|███████▎  | 632/861 [08:52<03:58,  1.04s/it]

 74%|███████▎  | 633/861 [08:53<03:28,  1.09it/s]

 74%|███████▎  | 634/861 [08:55<04:34,  1.21s/it]

 74%|███████▍  | 635/861 [08:56<04:32,  1.21s/it]

 74%|███████▍  | 636/861 [08:56<03:54,  1.04s/it]

 74%|███████▍  | 637/861 [08:57<03:39,  1.02it/s]

 74%|███████▍  | 638/861 [08:58<03:35,  1.04it/s]

 74%|███████▍  | 639/861 [09:00<04:03,  1.10s/it]

 74%|███████▍  | 640/861 [09:00<03:39,  1.01it/s]

 74%|███████▍  | 641/861 [09:01<03:24,  1.08it/s]

 75%|███████▍  | 642/861 [09:02<03:43,  1.02s/it]

 75%|███████▍  | 643/861 [09:03<03:21,  1.08it/s]

 75%|███████▍  | 644/861 [09:04<03:17,  1.10it/s]

 75%|███████▍  | 645/861 [09:04<02:43,  1.32it/s]

 75%|███████▌  | 646/861 [09:05<02:33,  1.40it/s]

 75%|███████▌  | 647/861 [09:06<02:25,  1.47it/s]

 75%|███████▌  | 648/861 [09:07<02:44,  1.29it/s]

 75%|███████▌  | 649/861 [09:07<02:34,  1.37it/s]

 75%|███████▌  | 650/861 [09:08<02:13,  1.58it/s]

 76%|███████▌  | 651/861 [09:08<01:55,  1.81it/s]

 76%|███████▌  | 652/861 [09:09<02:19,  1.50it/s]

 76%|███████▌  | 653/861 [09:09<02:05,  1.66it/s]

 76%|███████▌  | 654/861 [09:10<02:10,  1.59it/s]

 76%|███████▌  | 655/861 [09:10<01:51,  1.85it/s]

 76%|███████▌  | 656/861 [09:11<01:40,  2.04it/s]

 76%|███████▋  | 657/861 [09:11<01:39,  2.05it/s]

 76%|███████▋  | 658/861 [09:12<02:16,  1.48it/s]

 77%|███████▋  | 659/861 [09:13<02:10,  1.54it/s]

 77%|███████▋  | 660/861 [09:14<02:26,  1.38it/s]

 77%|███████▋  | 661/861 [09:14<02:05,  1.59it/s]

 77%|███████▋  | 662/861 [09:15<02:29,  1.33it/s]

 77%|███████▋  | 663/861 [09:17<03:37,  1.10s/it]

 77%|███████▋  | 664/861 [09:18<03:02,  1.08it/s]

 77%|███████▋  | 665/861 [09:18<02:29,  1.31it/s]

 77%|███████▋  | 666/861 [09:18<02:03,  1.58it/s]

 77%|███████▋  | 667/861 [09:19<02:15,  1.43it/s]

 78%|███████▊  | 668/861 [09:20<02:04,  1.55it/s]

 78%|███████▊  | 669/861 [09:20<01:47,  1.79it/s]

 78%|███████▊  | 670/861 [09:21<01:55,  1.65it/s]

 78%|███████▊  | 671/861 [09:21<01:35,  1.98it/s]

 78%|███████▊  | 672/861 [09:23<02:33,  1.23it/s]

 78%|███████▊  | 673/861 [09:23<02:20,  1.34it/s]

 78%|███████▊  | 674/861 [09:24<01:52,  1.66it/s]

 78%|███████▊  | 675/861 [09:25<02:15,  1.37it/s]

 79%|███████▊  | 676/861 [09:25<02:04,  1.49it/s]

 79%|███████▊  | 677/861 [09:26<01:50,  1.67it/s]

 79%|███████▊  | 678/861 [09:26<01:42,  1.79it/s]

 79%|███████▉  | 679/861 [09:26<01:27,  2.07it/s]

 79%|███████▉  | 680/861 [09:27<01:14,  2.41it/s]

 79%|███████▉  | 681/861 [09:27<01:12,  2.50it/s]

 79%|███████▉  | 682/861 [09:28<01:38,  1.82it/s]

 79%|███████▉  | 683/861 [09:28<01:33,  1.90it/s]

 79%|███████▉  | 684/861 [09:29<01:47,  1.65it/s]

 80%|███████▉  | 685/861 [09:30<01:47,  1.64it/s]

 80%|███████▉  | 686/861 [09:30<01:39,  1.76it/s]

 80%|███████▉  | 687/861 [09:32<02:45,  1.05it/s]

 80%|███████▉  | 688/861 [09:32<02:12,  1.30it/s]

 80%|████████  | 689/861 [09:33<02:10,  1.32it/s]

 80%|████████  | 690/861 [09:34<02:02,  1.39it/s]

 80%|████████  | 691/861 [09:35<02:05,  1.35it/s]

 80%|████████  | 692/861 [09:35<01:47,  1.57it/s]

 80%|████████  | 693/861 [09:36<01:55,  1.45it/s]

 81%|████████  | 694/861 [09:36<01:37,  1.72it/s]

 81%|████████  | 695/861 [09:37<01:33,  1.77it/s]

 81%|████████  | 696/861 [09:37<01:17,  2.12it/s]

 81%|████████  | 697/861 [09:37<01:21,  2.00it/s]

 81%|████████  | 698/861 [09:38<01:36,  1.70it/s]

 81%|████████  | 699/861 [09:39<01:43,  1.56it/s]

 81%|████████▏ | 700/861 [09:40<01:49,  1.47it/s]

 81%|████████▏ | 701/861 [09:41<01:58,  1.35it/s]

 82%|████████▏ | 702/861 [09:41<01:46,  1.49it/s]

 82%|████████▏ | 703/861 [09:42<01:33,  1.69it/s]

 82%|████████▏ | 704/861 [09:42<01:33,  1.68it/s]

 82%|████████▏ | 705/861 [09:43<01:31,  1.71it/s]

 82%|████████▏ | 706/861 [09:43<01:24,  1.84it/s]

 82%|████████▏ | 707/861 [09:44<01:15,  2.03it/s]

 82%|████████▏ | 708/861 [09:44<01:13,  2.08it/s]

 82%|████████▏ | 709/861 [09:44<01:08,  2.23it/s]

 82%|████████▏ | 710/861 [09:46<01:42,  1.47it/s]

 83%|████████▎ | 711/861 [09:46<01:40,  1.50it/s]

 83%|████████▎ | 712/861 [09:47<01:27,  1.71it/s]

 83%|████████▎ | 713/861 [09:47<01:13,  2.01it/s]

 83%|████████▎ | 714/861 [09:48<01:21,  1.81it/s]

 83%|████████▎ | 715/861 [09:49<01:39,  1.46it/s]

 83%|████████▎ | 716/861 [09:49<01:50,  1.31it/s]

 83%|████████▎ | 717/861 [09:50<01:42,  1.40it/s]

 83%|████████▎ | 718/861 [09:51<02:01,  1.17it/s]

 84%|████████▎ | 719/861 [09:52<01:49,  1.30it/s]

 84%|████████▎ | 720/861 [09:52<01:39,  1.42it/s]

 84%|████████▎ | 721/861 [09:53<01:32,  1.51it/s]

 84%|████████▍ | 722/861 [09:54<01:31,  1.52it/s]

 84%|████████▍ | 723/861 [09:54<01:19,  1.73it/s]

 84%|████████▍ | 724/861 [09:55<01:17,  1.77it/s]

 84%|████████▍ | 725/861 [09:55<01:16,  1.78it/s]

 84%|████████▍ | 726/861 [09:56<01:28,  1.52it/s]

 84%|████████▍ | 727/861 [09:58<02:12,  1.01it/s]

 85%|████████▍ | 728/861 [09:59<02:07,  1.05it/s]

 85%|████████▍ | 729/861 [09:59<01:48,  1.22it/s]

 85%|████████▍ | 730/861 [09:59<01:28,  1.48it/s]

 85%|████████▍ | 731/861 [10:00<01:30,  1.44it/s]

 85%|████████▌ | 732/861 [10:01<01:21,  1.58it/s]

 85%|████████▌ | 733/861 [10:01<01:21,  1.57it/s]

 85%|████████▌ | 734/861 [10:02<01:06,  1.91it/s]

 85%|████████▌ | 735/861 [10:02<01:03,  1.98it/s]

 85%|████████▌ | 736/861 [10:03<01:07,  1.85it/s]

 86%|████████▌ | 737/861 [10:03<01:09,  1.79it/s]

 86%|████████▌ | 738/861 [10:04<01:05,  1.87it/s]

 86%|████████▌ | 739/861 [10:04<00:59,  2.04it/s]

 86%|████████▌ | 740/861 [10:05<01:03,  1.91it/s]

 86%|████████▌ | 741/861 [10:05<01:02,  1.91it/s]

 86%|████████▌ | 742/861 [10:06<01:15,  1.58it/s]

 86%|████████▋ | 743/861 [10:07<01:15,  1.55it/s]

 86%|████████▋ | 744/861 [10:07<01:07,  1.74it/s]

 87%|████████▋ | 745/861 [10:08<01:13,  1.57it/s]

 87%|████████▋ | 746/861 [10:08<00:58,  1.95it/s]

 87%|████████▋ | 747/861 [10:09<01:05,  1.73it/s]

 87%|████████▋ | 748/861 [10:09<01:03,  1.78it/s]

 87%|████████▋ | 749/861 [10:10<01:16,  1.47it/s]

 87%|████████▋ | 750/861 [10:11<01:00,  1.84it/s]

 87%|████████▋ | 751/861 [10:11<00:49,  2.22it/s]

 87%|████████▋ | 752/861 [10:12<01:11,  1.53it/s]

 87%|████████▋ | 753/861 [10:13<01:08,  1.57it/s]

 88%|████████▊ | 754/861 [10:13<01:00,  1.76it/s]

 88%|████████▊ | 755/861 [10:14<00:56,  1.86it/s]

 88%|████████▊ | 756/861 [10:14<00:51,  2.02it/s]

 88%|████████▊ | 757/861 [10:15<01:09,  1.49it/s]

 88%|████████▊ | 758/861 [10:16<01:10,  1.46it/s]

 88%|████████▊ | 759/861 [10:16<01:03,  1.60it/s]

 88%|████████▊ | 760/861 [10:17<01:13,  1.37it/s]

 88%|████████▊ | 761/861 [10:19<01:35,  1.05it/s]

 89%|████████▊ | 762/861 [10:19<01:17,  1.27it/s]

 89%|████████▊ | 763/861 [10:20<01:08,  1.43it/s]

 89%|████████▊ | 764/861 [10:20<01:12,  1.35it/s]

 89%|████████▉ | 765/861 [10:21<01:10,  1.36it/s]

 89%|████████▉ | 766/861 [10:22<01:09,  1.36it/s]

 89%|████████▉ | 767/861 [10:25<02:14,  1.43s/it]

 89%|████████▉ | 768/861 [10:26<01:57,  1.26s/it]

 89%|████████▉ | 769/861 [10:27<01:49,  1.19s/it]

 89%|████████▉ | 770/861 [10:27<01:25,  1.06it/s]

 90%|████████▉ | 771/861 [10:28<01:11,  1.26it/s]

 90%|████████▉ | 772/861 [10:28<01:06,  1.35it/s]

 90%|████████▉ | 773/861 [10:30<01:46,  1.21s/it]

 90%|████████▉ | 774/861 [10:31<01:35,  1.09s/it]

 90%|█████████ | 775/861 [10:32<01:26,  1.01s/it]

 90%|█████████ | 776/861 [10:33<01:22,  1.03it/s]

 90%|█████████ | 777/861 [10:34<01:19,  1.06it/s]

 90%|█████████ | 778/861 [10:35<01:16,  1.08it/s]

 90%|█████████ | 779/861 [10:36<01:24,  1.03s/it]

 91%|█████████ | 780/861 [10:38<01:45,  1.30s/it]

 91%|█████████ | 781/861 [10:40<02:03,  1.54s/it]

 91%|█████████ | 782/861 [10:42<02:02,  1.55s/it]

 91%|█████████ | 783/861 [10:42<01:40,  1.29s/it]

 91%|█████████ | 784/861 [10:43<01:27,  1.14s/it]

 91%|█████████ | 785/861 [10:44<01:18,  1.04s/it]

 91%|█████████▏| 786/861 [10:45<01:11,  1.05it/s]

 91%|█████████▏| 787/861 [10:45<01:00,  1.21it/s]

 92%|█████████▏| 788/861 [10:46<00:56,  1.29it/s]

 92%|█████████▏| 789/861 [10:47<00:56,  1.27it/s]

 92%|█████████▏| 790/861 [10:47<00:55,  1.28it/s]

 92%|█████████▏| 791/861 [10:48<00:49,  1.42it/s]

 92%|█████████▏| 792/861 [10:49<00:47,  1.46it/s]

 92%|█████████▏| 793/861 [10:49<00:47,  1.42it/s]

 92%|█████████▏| 794/861 [10:50<00:42,  1.56it/s]

 92%|█████████▏| 795/861 [10:50<00:40,  1.61it/s]

 92%|█████████▏| 796/861 [10:51<00:34,  1.89it/s]

 93%|█████████▎| 797/861 [10:52<00:39,  1.62it/s]

 93%|█████████▎| 798/861 [10:52<00:34,  1.84it/s]

 93%|█████████▎| 799/861 [10:52<00:31,  1.94it/s]

 93%|█████████▎| 800/861 [10:53<00:34,  1.79it/s]

 93%|█████████▎| 801/861 [10:54<00:48,  1.24it/s]

 93%|█████████▎| 802/861 [10:55<00:41,  1.42it/s]

 93%|█████████▎| 803/861 [10:56<00:48,  1.19it/s]

 93%|█████████▎| 804/861 [10:58<01:07,  1.18s/it]

 93%|█████████▎| 805/861 [10:59<01:06,  1.18s/it]

 94%|█████████▎| 806/861 [11:00<00:52,  1.06it/s]

 94%|█████████▎| 807/861 [11:01<00:55,  1.02s/it]

 94%|█████████▍| 808/861 [11:02<01:01,  1.17s/it]

 94%|█████████▍| 809/861 [11:03<00:47,  1.09it/s]

 94%|█████████▍| 810/861 [11:03<00:41,  1.22it/s]

 94%|█████████▍| 811/861 [11:04<00:37,  1.34it/s]

 94%|█████████▍| 812/861 [11:04<00:34,  1.44it/s]

 94%|█████████▍| 813/861 [11:06<00:41,  1.15it/s]

 95%|█████████▍| 814/861 [11:07<00:46,  1.01it/s]

 95%|█████████▍| 815/861 [11:08<00:45,  1.01it/s]

 95%|█████████▍| 816/861 [11:09<00:39,  1.14it/s]

 95%|█████████▍| 817/861 [11:09<00:38,  1.14it/s]

 95%|█████████▌| 818/861 [11:10<00:40,  1.07it/s]

 95%|█████████▌| 819/861 [11:11<00:34,  1.21it/s]

 95%|█████████▌| 820/861 [11:12<00:36,  1.12it/s]

 95%|█████████▌| 821/861 [11:13<00:33,  1.18it/s]

 95%|█████████▌| 822/861 [11:14<00:40,  1.05s/it]

 96%|█████████▌| 823/861 [11:16<00:48,  1.27s/it]

 96%|█████████▌| 824/861 [11:17<00:37,  1.02s/it]

 96%|█████████▌| 825/861 [11:17<00:31,  1.14it/s]

 96%|█████████▌| 826/861 [11:19<00:38,  1.11s/it]

 96%|█████████▌| 827/861 [11:20<00:38,  1.13s/it]

 96%|█████████▌| 828/861 [11:20<00:29,  1.13it/s]

 96%|█████████▋| 829/861 [11:22<00:32,  1.02s/it]

 96%|█████████▋| 830/861 [11:23<00:30,  1.00it/s]

 97%|█████████▋| 831/861 [11:24<00:36,  1.21s/it]

 97%|█████████▋| 832/861 [11:25<00:29,  1.02s/it]

 97%|█████████▋| 833/861 [11:25<00:24,  1.14it/s]

 97%|█████████▋| 834/861 [11:27<00:25,  1.06it/s]

 97%|█████████▋| 835/861 [11:27<00:24,  1.07it/s]

 97%|█████████▋| 836/861 [11:28<00:23,  1.06it/s]

 97%|█████████▋| 837/861 [11:30<00:24,  1.03s/it]

 97%|█████████▋| 838/861 [11:31<00:25,  1.10s/it]

 97%|█████████▋| 839/861 [11:32<00:21,  1.03it/s]

 98%|█████████▊| 840/861 [11:32<00:17,  1.18it/s]

 98%|█████████▊| 841/861 [11:33<00:16,  1.25it/s]

 98%|█████████▊| 842/861 [11:33<00:13,  1.38it/s]

 98%|█████████▊| 843/861 [11:34<00:12,  1.41it/s]

 98%|█████████▊| 844/861 [11:35<00:11,  1.46it/s]

 98%|█████████▊| 845/861 [11:36<00:13,  1.19it/s]

 98%|█████████▊| 846/861 [11:36<00:10,  1.38it/s]

 98%|█████████▊| 847/861 [11:37<00:10,  1.29it/s]

 98%|█████████▊| 848/861 [11:38<00:10,  1.29it/s]

 99%|█████████▊| 849/861 [11:39<00:10,  1.14it/s]

 99%|█████████▊| 850/861 [11:40<00:08,  1.27it/s]

 99%|█████████▉| 851/861 [11:40<00:07,  1.41it/s]

 99%|█████████▉| 852/861 [11:41<00:05,  1.52it/s]

 99%|█████████▉| 853/861 [11:41<00:05,  1.54it/s]

 99%|█████████▉| 854/861 [11:42<00:04,  1.59it/s]

 99%|█████████▉| 855/861 [11:43<00:04,  1.35it/s]

 99%|█████████▉| 856/861 [11:44<00:04,  1.06it/s]

100%|█████████▉| 857/861 [11:45<00:03,  1.05it/s]

100%|█████████▉| 858/861 [11:46<00:02,  1.05it/s]

100%|█████████▉| 859/861 [11:47<00:01,  1.12it/s]

100%|█████████▉| 860/861 [11:48<00:00,  1.07it/s]

100%|██████████| 861/861 [11:49<00:00,  1.05it/s]{'score': 12.509961638161249, 'counts': [18011, 8302, 4221, 2162], 'totals': [51205, 49483, 47761, 46039], 'precisions': [35.1742993848257, 16.777479134248125, 8.83775465337828, 4.696018592932079], 'bp': 1.0, 'sys_len': 51205, 'ref_len': 32555}

                                                         

                                                 
{'eval_loss': 2.4478776454925537, 'eval_bleu': 12.51, 'eval_gen_len': 37.4146, 'eval_runtime': 807.7318, 'eval_samples_per_second': 2.132, 'eval_steps_per_second': 1.066, 'epoch': 12.0}

 75%|███████▌  | 46428/61904 [1:42:27<6:11:43,  1.44s/it]

100%|██████████| 861/861 [13:26<00:00,  1.05it/s]

                                                 [WARNING|configuration_utils.py:448] 2024-10-28 17:08:07,139 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 75%|███████▌  | 46429/61904 [1:42:46<1071:42:26, 249.31s/it]
 75%|███████▌  | 46430/61904 [1:42:48<752:13:49, 175.01s/it] 
 75%|███████▌  | 46431/61904 [1:42:49<528:27:03, 122.95s/it]
 75%|███████▌  | 46432/61904 [1:42:51<371:51:40, 86.52s/it] 
 75%|███████▌  | 46433/61904 [1:42:52<262:06:56, 60.99s/it]
 75%|███████▌  | 46434/61904 [1:42:53<185:19:45, 43.13s/it]
 75%|███████▌  | 46435/61904 [1:42:55<131:31:54, 30.61s/it]
 75%|███████▌  | 46436/61904 [1:42:56<93:45:21, 21.82s/it] 
 75%|███████▌  | 46437/61904 [1:42:58<67:32:22, 15.72s/it]
 75%|███████▌  | 46438/61904 [1:42:59<49:09:39, 11.44s/it]
 75%|███████▌  | 46439/61904 [1:43:01<36:13:35,  8.43s/it]
 75%|███████▌  | 46440/61904 [1:43:02<27:10:21,  6.33s/it]
                                                          
{'loss': 2.4527, 'learning_rate': 1.2506158433813043e-07, 'epoch': 12.0}

 75%|███████▌  | 46440/61904 [1:43:02<27:10:21,  6.33s/it]
 75%|███████▌  | 46441/61904 [1:43:03<20:55:43,  4.87s/it]
 75%|███████▌  | 46442/61904 [1:43:05<16:29:49,  3.84s/it]
 75%|███████▌  | 46443/61904 [1:43:06<13:28:42,  3.14s/it]
 75%|███████▌  | 46444/61904 [1:43:08<11:29:30,  2.68s/it]
 75%|███████▌  | 46445/61904 [1:43:09<9:53:21,  2.30s/it] 
 75%|███████▌  | 46446/61904 [1:43:11<8:38:04,  2.01s/it]
 75%|███████▌  | 46447/61904 [1:43:12<8:09:47,  1.90s/it]
 75%|███████▌  | 46448/61904 [1:43:14<7:37:23,  1.78s/it]
 75%|███████▌  | 46449/61904 [1:43:15<7:16:07,  1.69s/it]
 75%|███████▌  | 46450/61904 [1:43:17<6:55:58,  1.61s/it]
 75%|███████▌  | 46451/61904 [1:43:18<6:49:45,  1.59s/it]
 75%|███████▌  | 46452/61904 [1:43:20<6:34:49,  1.53s/it]
 75%|███████▌  | 46453/61904 [1:43:21<6:30:23,  1.52s/it]
 75%|███████▌  | 46454/61904 [1:43:23<6:24:05,  1.49s/it]
 75%|███████▌  | 46455/61904 [1:43:24<6:11:39,  1.44s/it]
 75%|███████▌  | 46456/61904 [1:43:25<6:00:46,  1.40s/it]
 75%|███████▌  | 46457/61904 [1:43:27<6:07:43,  1.43s/it]
 75%|███████▌  | 46458/61904 [1:43:28<5:58:29,  1.39s/it]
 75%|███████▌  | 46459/61904 [1:43:30<6:02:24,  1.41s/it]
 75%|███████▌  | 46460/61904 [1:43:31<6:05:42,  1.42s/it]
                                                         
{'loss': 2.436, 'learning_rate': 1.250291715285881e-07, 'epoch': 12.01}

 75%|███████▌  | 46460/61904 [1:43:31<6:05:42,  1.42s/it]
 75%|███████▌  | 46461/61904 [1:43:32<5:59:07,  1.40s/it]
 75%|███████▌  | 46462/61904 [1:43:34<6:19:38,  1.48s/it]
 75%|███████▌  | 46463/61904 [1:43:35<6:04:33,  1.42s/it]
 75%|███████▌  | 46464/61904 [1:43:37<6:06:03,  1.42s/it]
 75%|███████▌  | 46465/61904 [1:43:38<5:56:54,  1.39s/it]
 75%|███████▌  | 46466/61904 [1:43:40<6:05:41,  1.42s/it]
 75%|███████▌  | 46467/61904 [1:43:41<6:33:40,  1.53s/it]
 75%|███████▌  | 46468/61904 [1:43:43<6:11:53,  1.45s/it]
 75%|███████▌  | 46469/61904 [1:43:44<6:02:19,  1.41s/it]
 75%|███████▌  | 46470/61904 [1:43:45<5:58:53,  1.40s/it]
 75%|███████▌  | 46471/61904 [1:43:47<6:09:47,  1.44s/it]
 75%|███████▌  | 46472/61904 [1:43:48<6:04:29,  1.42s/it]
 75%|███████▌  | 46473/61904 [1:43:49<5:57:32,  1.39s/it]
 75%|███████▌  | 46474/61904 [1:43:51<6:04:04,  1.42s/it]
 75%|███████▌  | 46475/61904 [1:43:52<6:07:06,  1.43s/it]
 75%|███████▌  | 46476/61904 [1:43:54<6:03:32,  1.41s/it]
 75%|███████▌  | 46477/61904 [1:43:55<6:01:12,  1.40s/it]
 75%|███████▌  | 46478/61904 [1:43:57<6:06:32,  1.43s/it]
 75%|███████▌  | 46479/61904 [1:43:58<6:13:43,  1.45s/it]
 75%|███████▌  | 46480/61904 [1:44:00<6:08:51,  1.43s/it]
                                                         
{'loss': 2.4514, 'learning_rate': 1.2499675871904575e-07, 'epoch': 12.01}

 75%|███████▌  | 46480/61904 [1:44:00<6:08:51,  1.43s/it]
 75%|███████▌  | 46481/61904 [1:44:01<6:03:09,  1.41s/it]
 75%|███████▌  | 46482/61904 [1:44:02<6:12:59,  1.45s/it]
 75%|███████▌  | 46483/61904 [1:44:04<6:12:53,  1.45s/it]
 75%|███████▌  | 46484/61904 [1:44:05<6:09:21,  1.44s/it]
 75%|███████▌  | 46485/61904 [1:44:07<6:21:03,  1.48s/it]
 75%|███████▌  | 46486/61904 [1:44:08<6:22:24,  1.49s/it]
 75%|███████▌  | 46487/61904 [1:44:10<6:06:39,  1.43s/it]
 75%|███████▌  | 46488/61904 [1:44:11<6:05:38,  1.42s/it]
 75%|███████▌  | 46489/61904 [1:44:13<6:15:42,  1.46s/it]
 75%|███████▌  | 46490/61904 [1:44:14<6:24:35,  1.50s/it]
 75%|███████▌  | 46491/61904 [1:44:16<6:21:28,  1.48s/it]
 75%|███████▌  | 46492/61904 [1:44:17<6:14:18,  1.46s/it]
 75%|███████▌  | 46493/61904 [1:44:18<6:01:39,  1.41s/it]
 75%|███████▌  | 46494/61904 [1:44:20<6:01:36,  1.41s/it]
 75%|███████▌  | 46495/61904 [1:44:21<5:58:13,  1.39s/it]
 75%|███████▌  | 46496/61904 [1:44:23<5:58:53,  1.40s/it]
 75%|███████▌  | 46497/61904 [1:44:24<6:00:11,  1.40s/it]
 75%|███████▌  | 46498/61904 [1:44:25<6:10:38,  1.44s/it]
 75%|███████▌  | 46499/61904 [1:44:27<6:10:45,  1.44s/it]
 75%|███████▌  | 46500/61904 [1:44:28<6:08:40,  1.44s/it]
                                                         
{'loss': 2.4921, 'learning_rate': 1.2496434590950344e-07, 'epoch': 12.02}

 75%|███████▌  | 46500/61904 [1:44:28<6:08:40,  1.44s/it]
 75%|███████▌  | 46501/61904 [1:44:30<6:11:17,  1.45s/it]
 75%|███████▌  | 46502/61904 [1:44:31<6:08:40,  1.44s/it]
 75%|███████▌  | 46503/61904 [1:44:33<6:09:02,  1.44s/it]
 75%|███████▌  | 46504/61904 [1:44:34<6:03:57,  1.42s/it]
 75%|███████▌  | 46505/61904 [1:44:36<6:23:08,  1.49s/it]
 75%|███████▌  | 46506/61904 [1:44:37<6:20:43,  1.48s/it]
 75%|███████▌  | 46507/61904 [1:44:39<6:11:00,  1.45s/it]
 75%|███████▌  | 46508/61904 [1:44:40<6:13:40,  1.46s/it]
 75%|███████▌  | 46509/61904 [1:44:41<6:04:44,  1.42s/it]
 75%|███████▌  | 46510/61904 [1:44:43<6:05:34,  1.42s/it]
 75%|███████▌  | 46511/61904 [1:44:44<6:00:37,  1.41s/it]
 75%|███████▌  | 46512/61904 [1:44:46<5:57:16,  1.39s/it]
 75%|███████▌  | 46513/61904 [1:44:47<6:11:53,  1.45s/it]
 75%|███████▌  | 46514/61904 [1:44:49<6:09:06,  1.44s/it]
 75%|███████▌  | 46515/61904 [1:44:50<5:57:08,  1.39s/it]
 75%|███████▌  | 46516/61904 [1:44:51<5:56:15,  1.39s/it]
 75%|███████▌  | 46517/61904 [1:44:53<6:25:19,  1.50s/it]
 75%|███████▌  | 46518/61904 [1:44:54<6:21:17,  1.49s/it]
 75%|███████▌  | 46519/61904 [1:44:56<6:16:53,  1.47s/it]
 75%|███████▌  | 46520/61904 [1:44:57<6:13:41,  1.46s/it]
                                                         
{'loss': 2.4637, 'learning_rate': 1.249319330999611e-07, 'epoch': 12.02}

 75%|███████▌  | 46520/61904 [1:44:57<6:13:41,  1.46s/it]
 75%|███████▌  | 46521/61904 [1:44:59<6:14:15,  1.46s/it]
 75%|███████▌  | 46522/61904 [1:45:00<6:10:10,  1.44s/it]
 75%|███████▌  | 46523/61904 [1:45:01<6:02:10,  1.41s/it]
 75%|███████▌  | 46524/61904 [1:45:03<5:58:39,  1.40s/it]
 75%|███████▌  | 46525/61904 [1:45:04<6:10:47,  1.45s/it]
 75%|███████▌  | 46526/61904 [1:45:06<6:22:39,  1.49s/it]
 75%|███████▌  | 46527/61904 [1:45:07<6:09:06,  1.44s/it]
 75%|███████▌  | 46528/61904 [1:45:09<6:13:14,  1.46s/it]
 75%|███████▌  | 46529/61904 [1:45:10<6:09:25,  1.44s/it]
 75%|███████▌  | 46530/61904 [1:45:12<6:05:26,  1.43s/it]
 75%|███████▌  | 46531/61904 [1:45:13<6:05:07,  1.43s/it]
 75%|███████▌  | 46532/61904 [1:45:15<6:13:37,  1.46s/it]
 75%|███████▌  | 46533/61904 [1:45:16<6:06:48,  1.43s/it]
 75%|███████▌  | 46534/61904 [1:45:17<6:16:55,  1.47s/it]
 75%|███████▌  | 46535/61904 [1:45:19<6:08:03,  1.44s/it]
 75%|███████▌  | 46536/61904 [1:45:20<6:09:34,  1.44s/it]
 75%|███████▌  | 46537/61904 [1:45:22<6:07:05,  1.43s/it]
 75%|███████▌  | 46538/61904 [1:45:23<6:06:29,  1.43s/it]
 75%|███████▌  | 46539/61904 [1:45:24<5:56:15,  1.39s/it]
 75%|███████▌  | 46540/61904 [1:45:26<6:12:00,  1.45s/it]
                                                         
{'loss': 2.4924, 'learning_rate': 1.2489952029041876e-07, 'epoch': 12.03}

 75%|███████▌  | 46540/61904 [1:45:26<6:12:00,  1.45s/it]
 75%|███████▌  | 46541/61904 [1:45:27<5:59:37,  1.40s/it]
 75%|███████▌  | 46542/61904 [1:45:29<6:15:03,  1.46s/it]
 75%|███████▌  | 46543/61904 [1:45:30<6:06:06,  1.43s/it]
 75%|███████▌  | 46544/61904 [1:45:32<6:11:26,  1.45s/it]
 75%|███████▌  | 46545/61904 [1:45:33<6:08:02,  1.44s/it]
 75%|███████▌  | 46546/61904 [1:45:35<6:06:27,  1.43s/it]
 75%|███████▌  | 46547/61904 [1:45:36<6:07:01,  1.43s/it]
 75%|███████▌  | 46548/61904 [1:45:37<6:05:03,  1.43s/it]
 75%|███████▌  | 46549/61904 [1:45:39<6:00:49,  1.41s/it]
 75%|███████▌  | 46550/61904 [1:45:40<6:03:49,  1.42s/it]
 75%|███████▌  | 46551/61904 [1:45:42<6:02:40,  1.42s/it]
 75%|███████▌  | 46552/61904 [1:45:43<6:00:43,  1.41s/it]
 75%|███████▌  | 46553/61904 [1:45:44<5:58:25,  1.40s/it]
 75%|███████▌  | 46554/61904 [1:45:46<6:02:38,  1.42s/it]
 75%|███████▌  | 46555/61904 [1:45:48<6:16:35,  1.47s/it]
 75%|███████▌  | 46556/61904 [1:45:49<6:05:02,  1.43s/it]
 75%|███████▌  | 46557/61904 [1:45:50<6:14:31,  1.46s/it]
 75%|███████▌  | 46558/61904 [1:45:52<6:08:42,  1.44s/it]
 75%|███████▌  | 46559/61904 [1:45:53<6:00:12,  1.41s/it]
 75%|███████▌  | 46560/61904 [1:45:54<5:58:42,  1.40s/it]
                                                         
{'loss': 2.4788, 'learning_rate': 1.2486710748087643e-07, 'epoch': 12.03}

 75%|███████▌  | 46560/61904 [1:45:54<5:58:42,  1.40s/it]
 75%|███████▌  | 46561/61904 [1:45:56<6:04:12,  1.42s/it]
 75%|███████▌  | 46562/61904 [1:45:57<6:02:27,  1.42s/it]
 75%|███████▌  | 46563/61904 [1:45:59<5:59:00,  1.40s/it]
 75%|███████▌  | 46564/61904 [1:46:00<5:54:51,  1.39s/it]
 75%|███████▌  | 46565/61904 [1:46:02<5:58:12,  1.40s/it]
 75%|███████▌  | 46566/61904 [1:46:03<5:55:26,  1.39s/it]
 75%|███████▌  | 46567/61904 [1:46:04<5:44:22,  1.35s/it]
 75%|███████▌  | 46568/61904 [1:46:06<5:58:16,  1.40s/it]
 75%|███████▌  | 46569/61904 [1:46:07<5:56:17,  1.39s/it]
 75%|███████▌  | 46570/61904 [1:46:09<6:10:59,  1.45s/it]
 75%|███████▌  | 46571/61904 [1:46:10<6:14:12,  1.46s/it]
 75%|███████▌  | 46572/61904 [1:46:12<6:08:31,  1.44s/it]
 75%|███████▌  | 46573/61904 [1:46:13<6:07:39,  1.44s/it]
 75%|███████▌  | 46574/61904 [1:46:14<5:58:34,  1.40s/it]
 75%|███████▌  | 46575/61904 [1:46:16<5:58:23,  1.40s/it]
 75%|███████▌  | 46576/61904 [1:46:17<6:02:21,  1.42s/it]
 75%|███████▌  | 46577/61904 [1:46:19<6:04:54,  1.43s/it]
 75%|███████▌  | 46578/61904 [1:46:20<6:07:04,  1.44s/it]
 75%|███████▌  | 46579/61904 [1:46:21<6:03:50,  1.42s/it]
 75%|███████▌  | 46580/61904 [1:46:23<6:02:05,  1.42s/it]
                                                         
{'loss': 2.5291, 'learning_rate': 1.2483469467133411e-07, 'epoch': 12.04}

 75%|███████▌  | 46580/61904 [1:46:23<6:02:05,  1.42s/it]
 75%|███████▌  | 46581/61904 [1:46:24<6:07:38,  1.44s/it]
 75%|███████▌  | 46582/61904 [1:46:26<6:05:22,  1.43s/it]
 75%|███████▌  | 46583/61904 [1:46:27<6:10:57,  1.45s/it]
 75%|███████▌  | 46584/61904 [1:46:29<6:05:36,  1.43s/it]
 75%|███████▌  | 46585/61904 [1:46:30<5:59:31,  1.41s/it]
 75%|███████▌  | 46586/61904 [1:46:31<5:59:57,  1.41s/it]
 75%|███████▌  | 46587/61904 [1:46:33<5:57:22,  1.40s/it]
 75%|███████▌  | 46588/61904 [1:46:34<5:46:18,  1.36s/it]
 75%|███████▌  | 46589/61904 [1:46:35<5:41:29,  1.34s/it]
 75%|███████▌  | 46590/61904 [1:46:37<5:44:10,  1.35s/it]
 75%|███████▌  | 46591/61904 [1:46:38<5:57:07,  1.40s/it]
 75%|███████▌  | 46592/61904 [1:46:40<5:51:20,  1.38s/it]
 75%|███████▌  | 46593/61904 [1:46:41<5:55:09,  1.39s/it]
 75%|███████▌  | 46594/61904 [1:46:42<6:02:39,  1.42s/it]
 75%|███████▌  | 46595/61904 [1:46:44<5:47:30,  1.36s/it]
 75%|███████▌  | 46596/61904 [1:46:45<5:36:09,  1.32s/it]
 75%|███████▌  | 46597/61904 [1:46:46<5:46:23,  1.36s/it]
 75%|███████▌  | 46598/61904 [1:46:48<5:52:13,  1.38s/it]
 75%|███████▌  | 46599/61904 [1:46:49<5:39:41,  1.33s/it]
 75%|███████▌  | 46600/61904 [1:46:50<5:46:27,  1.36s/it]
                                                         
{'loss': 2.4419, 'learning_rate': 1.2480228186179178e-07, 'epoch': 12.04}

 75%|███████▌  | 46600/61904 [1:46:50<5:46:27,  1.36s/it]
 75%|███████▌  | 46601/61904 [1:46:52<5:42:02,  1.34s/it]
 75%|███████▌  | 46602/61904 [1:46:53<5:43:13,  1.35s/it]
 75%|███████▌  | 46603/61904 [1:46:54<5:49:50,  1.37s/it]
 75%|███████▌  | 46604/61904 [1:46:56<5:50:05,  1.37s/it]
 75%|███████▌  | 46605/61904 [1:46:57<5:59:08,  1.41s/it]
 75%|███████▌  | 46606/61904 [1:46:59<5:58:19,  1.41s/it]
 75%|███████▌  | 46607/61904 [1:47:00<5:59:03,  1.41s/it]
 75%|███████▌  | 46608/61904 [1:47:02<5:58:48,  1.41s/it]
 75%|███████▌  | 46609/61904 [1:47:03<5:54:27,  1.39s/it]
 75%|███████▌  | 46610/61904 [1:47:04<5:54:56,  1.39s/it]
 75%|███████▌  | 46611/61904 [1:47:06<5:55:00,  1.39s/it]
 75%|███████▌  | 46612/61904 [1:47:07<5:55:50,  1.40s/it]
 75%|███████▌  | 46613/61904 [1:47:09<6:07:40,  1.44s/it]
 75%|███████▌  | 46614/61904 [1:47:10<5:56:11,  1.40s/it]
 75%|███████▌  | 46615/61904 [1:47:11<5:53:06,  1.39s/it]
 75%|███████▌  | 46616/61904 [1:47:13<5:45:49,  1.36s/it]
 75%|███████▌  | 46617/61904 [1:47:14<5:47:19,  1.36s/it]
 75%|███████▌  | 46618/61904 [1:47:15<5:48:59,  1.37s/it]
 75%|███████▌  | 46619/61904 [1:47:17<5:41:33,  1.34s/it]
 75%|███████▌  | 46620/61904 [1:47:18<5:43:26,  1.35s/it]
                                                         
{'loss': 2.4768, 'learning_rate': 1.2476986905224944e-07, 'epoch': 12.05}

 75%|███████▌  | 46620/61904 [1:47:18<5:43:26,  1.35s/it]
 75%|███████▌  | 46621/61904 [1:47:20<6:00:42,  1.42s/it]
 75%|███████▌  | 46622/61904 [1:47:21<5:56:09,  1.40s/it]
 75%|███████▌  | 46623/61904 [1:47:22<5:54:02,  1.39s/it]
 75%|███████▌  | 46624/61904 [1:47:24<6:04:44,  1.43s/it]
 75%|███████▌  | 46625/61904 [1:47:25<5:57:42,  1.40s/it]
 75%|███████▌  | 46626/61904 [1:47:26<5:47:52,  1.37s/it]
 75%|███████▌  | 46627/61904 [1:47:28<5:48:03,  1.37s/it]
 75%|███████▌  | 46628/61904 [1:47:29<5:50:06,  1.38s/it]
 75%|███████▌  | 46629/61904 [1:47:31<5:52:05,  1.38s/it]
 75%|███████▌  | 46630/61904 [1:47:32<5:59:10,  1.41s/it]
 75%|███████▌  | 46631/61904 [1:47:33<5:58:20,  1.41s/it]
 75%|███████▌  | 46632/61904 [1:47:35<5:57:40,  1.41s/it]
 75%|███████▌  | 46633/61904 [1:47:36<6:10:56,  1.46s/it]
 75%|███████▌  | 46634/61904 [1:47:38<6:00:49,  1.42s/it]
 75%|███████▌  | 46635/61904 [1:47:39<5:56:56,  1.40s/it]
 75%|███████▌  | 46636/61904 [1:47:41<5:57:03,  1.40s/it]
 75%|███████▌  | 46637/61904 [1:47:42<6:06:48,  1.44s/it]
 75%|███████▌  | 46638/61904 [1:47:43<6:00:37,  1.42s/it]
 75%|███████▌  | 46639/61904 [1:47:45<5:59:13,  1.41s/it]
 75%|███████▌  | 46640/61904 [1:47:46<5:59:19,  1.41s/it]
                                                         
{'loss': 2.444, 'learning_rate': 1.2473745624270713e-07, 'epoch': 12.05}

 75%|███████▌  | 46640/61904 [1:47:46<5:59:19,  1.41s/it]
 75%|███████▌  | 46641/61904 [1:47:48<6:00:59,  1.42s/it]
 75%|███████▌  | 46642/61904 [1:47:49<5:58:31,  1.41s/it]
 75%|███████▌  | 46643/61904 [1:47:50<5:57:50,  1.41s/it]
 75%|███████▌  | 46644/61904 [1:47:52<5:56:55,  1.40s/it]
 75%|███████▌  | 46645/61904 [1:47:53<5:58:31,  1.41s/it]
 75%|███████▌  | 46646/61904 [1:47:55<5:56:02,  1.40s/it]
 75%|███████▌  | 46647/61904 [1:47:56<5:51:30,  1.38s/it]
 75%|███████▌  | 46648/61904 [1:47:57<5:57:10,  1.40s/it]
 75%|███████▌  | 46649/61904 [1:47:59<5:49:00,  1.37s/it]
 75%|███████▌  | 46650/61904 [1:48:00<5:41:21,  1.34s/it]
 75%|███████▌  | 46651/61904 [1:48:01<5:42:51,  1.35s/it]
 75%|███████▌  | 46652/61904 [1:48:03<5:42:20,  1.35s/it]
 75%|███████▌  | 46653/61904 [1:48:04<5:45:19,  1.36s/it]
 75%|███████▌  | 46654/61904 [1:48:06<5:44:52,  1.36s/it]
 75%|███████▌  | 46655/61904 [1:48:07<5:40:47,  1.34s/it]
 75%|███████▌  | 46656/61904 [1:48:08<5:44:12,  1.35s/it]
 75%|███████▌  | 46657/61904 [1:48:09<5:39:10,  1.33s/it]
 75%|███████▌  | 46658/61904 [1:48:11<5:37:16,  1.33s/it]
 75%|███████▌  | 46659/61904 [1:48:12<5:43:01,  1.35s/it]
 75%|███████▌  | 46660/61904 [1:48:14<5:44:18,  1.36s/it]
                                                         
{'loss': 2.5193, 'learning_rate': 1.247050434331648e-07, 'epoch': 12.06}

 75%|███████▌  | 46660/61904 [1:48:14<5:44:18,  1.36s/it]
 75%|███████▌  | 46661/61904 [1:48:15<5:47:35,  1.37s/it]
 75%|███████▌  | 46662/61904 [1:48:16<5:43:49,  1.35s/it]
 75%|███████▌  | 46663/61904 [1:48:18<5:37:23,  1.33s/it]
 75%|███████▌  | 46664/61904 [1:48:19<5:49:00,  1.37s/it]
 75%|███████▌  | 46665/61904 [1:48:21<5:56:11,  1.40s/it]
 75%|███████▌  | 46666/61904 [1:48:22<5:53:06,  1.39s/it]
 75%|███████▌  | 46667/61904 [1:48:23<5:45:40,  1.36s/it]
 75%|███████▌  | 46668/61904 [1:48:25<5:45:13,  1.36s/it]
 75%|███████▌  | 46669/61904 [1:48:26<5:40:49,  1.34s/it]
 75%|███████▌  | 46670/61904 [1:48:27<5:44:02,  1.36s/it]
 75%|███████▌  | 46671/61904 [1:48:28<5:34:14,  1.32s/it]
 75%|███████▌  | 46672/61904 [1:48:30<5:37:33,  1.33s/it]
 75%|███████▌  | 46673/61904 [1:48:31<5:40:23,  1.34s/it]
 75%|███████▌  | 46674/61904 [1:48:33<5:48:38,  1.37s/it]
 75%|███████▌  | 46675/61904 [1:48:34<5:45:59,  1.36s/it]
 75%|███████▌  | 46676/61904 [1:48:35<5:46:10,  1.36s/it]
 75%|███████▌  | 46677/61904 [1:48:37<5:39:58,  1.34s/it]
 75%|███████▌  | 46678/61904 [1:48:38<5:45:21,  1.36s/it]
 75%|███████▌  | 46679/61904 [1:48:39<5:51:25,  1.38s/it]
 75%|███████▌  | 46680/61904 [1:48:41<5:53:15,  1.39s/it]
                                                         
{'loss': 2.5019, 'learning_rate': 1.2467263062362245e-07, 'epoch': 12.06}

 75%|███████▌  | 46680/61904 [1:48:41<5:53:15,  1.39s/it]
 75%|███████▌  | 46681/61904 [1:48:42<5:56:19,  1.40s/it]
 75%|███████▌  | 46682/61904 [1:48:44<5:54:24,  1.40s/it]
 75%|███████▌  | 46683/61904 [1:48:45<5:51:31,  1.39s/it]
 75%|███████▌  | 46684/61904 [1:48:46<5:50:17,  1.38s/it]
 75%|███████▌  | 46685/61904 [1:48:48<5:42:19,  1.35s/it]
 75%|███████▌  | 46686/61904 [1:48:49<5:47:02,  1.37s/it]
 75%|███████▌  | 46687/61904 [1:48:50<5:48:39,  1.37s/it]
 75%|███████▌  | 46688/61904 [1:48:52<5:46:11,  1.37s/it]
 75%|███████▌  | 46689/61904 [1:48:53<5:42:59,  1.35s/it]
 75%|███████▌  | 46690/61904 [1:48:55<5:53:49,  1.40s/it]
 75%|███████▌  | 46691/61904 [1:48:56<6:08:28,  1.45s/it]
 75%|███████▌  | 46692/61904 [1:48:58<5:59:25,  1.42s/it]
 75%|███████▌  | 46693/61904 [1:48:59<5:59:06,  1.42s/it]
 75%|███████▌  | 46694/61904 [1:49:00<5:51:16,  1.39s/it]
 75%|███████▌  | 46695/61904 [1:49:02<6:01:22,  1.43s/it]
 75%|███████▌  | 46696/61904 [1:49:03<6:05:16,  1.44s/it]
 75%|███████▌  | 46697/61904 [1:49:05<6:15:06,  1.48s/it]
 75%|███████▌  | 46698/61904 [1:49:06<6:11:09,  1.46s/it]
 75%|███████▌  | 46699/61904 [1:49:08<6:01:31,  1.43s/it]
 75%|███████▌  | 46700/61904 [1:49:09<6:00:29,  1.42s/it]
                                                         
{'loss': 2.465, 'learning_rate': 1.246402178140801e-07, 'epoch': 12.07}

 75%|███████▌  | 46700/61904 [1:49:09<6:00:29,  1.42s/it]
 75%|███████▌  | 46701/61904 [1:49:10<6:00:07,  1.42s/it]
 75%|███████▌  | 46702/61904 [1:49:12<5:55:28,  1.40s/it]
 75%|███████▌  | 46703/61904 [1:49:13<6:05:00,  1.44s/it]
 75%|███████▌  | 46704/61904 [1:49:15<5:53:33,  1.40s/it]
 75%|███████▌  | 46705/61904 [1:49:16<5:59:37,  1.42s/it]
 75%|███████▌  | 46706/61904 [1:49:17<5:51:42,  1.39s/it]
 75%|███████▌  | 46707/61904 [1:49:19<5:55:32,  1.40s/it]
 75%|███████▌  | 46708/61904 [1:49:20<5:50:30,  1.38s/it]
 75%|███████▌  | 46709/61904 [1:49:22<5:45:57,  1.37s/it]
 75%|███████▌  | 46710/61904 [1:49:23<5:43:59,  1.36s/it]
 75%|███████▌  | 46711/61904 [1:49:24<5:40:39,  1.35s/it]
 75%|███████▌  | 46712/61904 [1:49:26<5:50:28,  1.38s/it]
 75%|███████▌  | 46713/61904 [1:49:27<6:01:09,  1.43s/it]
 75%|███████▌  | 46714/61904 [1:49:29<6:00:04,  1.42s/it]
 75%|███████▌  | 46715/61904 [1:49:30<5:57:19,  1.41s/it]
 75%|███████▌  | 46716/61904 [1:49:31<5:54:29,  1.40s/it]
 75%|███████▌  | 46717/61904 [1:49:33<5:50:10,  1.38s/it]
 75%|███████▌  | 46718/61904 [1:49:34<5:56:46,  1.41s/it]
 75%|███████▌  | 46719/61904 [1:49:36<6:13:27,  1.48s/it]
 75%|███████▌  | 46720/61904 [1:49:37<5:59:33,  1.42s/it]
                                                         
{'loss': 2.4508, 'learning_rate': 1.246078050045378e-07, 'epoch': 12.08}

 75%|███████▌  | 46720/61904 [1:49:37<5:59:33,  1.42s/it]
 75%|███████▌  | 46721/61904 [1:49:39<6:07:08,  1.45s/it]
 75%|███████▌  | 46722/61904 [1:49:40<5:50:30,  1.39s/it]
 75%|███████▌  | 46723/61904 [1:49:41<5:53:12,  1.40s/it]
 75%|███████▌  | 46724/61904 [1:49:43<5:56:53,  1.41s/it]
 75%|███████▌  | 46725/61904 [1:49:44<6:01:31,  1.43s/it]
 75%|███████▌  | 46726/61904 [1:49:46<5:59:08,  1.42s/it]
 75%|███████▌  | 46727/61904 [1:49:47<5:56:15,  1.41s/it]
 75%|███████▌  | 46728/61904 [1:49:48<5:57:15,  1.41s/it]
 75%|███████▌  | 46729/61904 [1:49:50<6:01:39,  1.43s/it]
 75%|███████▌  | 46730/61904 [1:49:51<5:50:56,  1.39s/it]
 75%|███████▌  | 46731/61904 [1:49:52<5:47:59,  1.38s/it]
 75%|███████▌  | 46732/61904 [1:49:54<5:45:13,  1.37s/it]
 75%|███████▌  | 46733/61904 [1:49:55<5:42:49,  1.36s/it]
 75%|███████▌  | 46734/61904 [1:49:57<5:44:52,  1.36s/it]
 75%|███████▌  | 46735/61904 [1:49:58<5:51:30,  1.39s/it]
 75%|███████▌  | 46736/61904 [1:49:59<5:59:07,  1.42s/it]
 75%|███████▌  | 46737/61904 [1:50:01<5:56:13,  1.41s/it]
 76%|███████▌  | 46738/61904 [1:50:02<5:59:27,  1.42s/it]
 76%|███████▌  | 46739/61904 [1:50:04<5:56:20,  1.41s/it]
 76%|███████▌  | 46740/61904 [1:50:05<6:00:43,  1.43s/it]
                                                         
{'loss': 2.4784, 'learning_rate': 1.2457539219499546e-07, 'epoch': 12.08}

 76%|███████▌  | 46740/61904 [1:50:05<6:00:43,  1.43s/it]
 76%|███████▌  | 46741/61904 [1:50:07<5:53:39,  1.40s/it]
 76%|███████▌  | 46742/61904 [1:50:08<5:50:28,  1.39s/it]
 76%|███████▌  | 46743/61904 [1:50:09<5:45:29,  1.37s/it]
 76%|███████▌  | 46744/61904 [1:50:11<5:55:15,  1.41s/it]
 76%|███████▌  | 46745/61904 [1:50:12<5:45:26,  1.37s/it]
 76%|███████▌  | 46746/61904 [1:50:13<5:46:17,  1.37s/it]
 76%|███████▌  | 46747/61904 [1:50:15<5:35:09,  1.33s/it]
 76%|███████▌  | 46748/61904 [1:50:16<5:33:05,  1.32s/it]
 76%|███████▌  | 46749/61904 [1:50:17<5:26:46,  1.29s/it]
 76%|███████▌  | 46750/61904 [1:50:18<5:30:01,  1.31s/it]
 76%|███████▌  | 46751/61904 [1:50:20<5:31:01,  1.31s/it]
 76%|███████▌  | 46752/61904 [1:50:21<5:37:36,  1.34s/it]
 76%|███████▌  | 46753/61904 [1:50:23<5:40:02,  1.35s/it]
 76%|███████▌  | 46754/61904 [1:50:24<5:45:10,  1.37s/it]
 76%|███████▌  | 46755/61904 [1:50:25<5:43:32,  1.36s/it]
 76%|███████▌  | 46756/61904 [1:50:27<5:48:34,  1.38s/it]
 76%|███████▌  | 46757/61904 [1:50:28<5:54:40,  1.40s/it]
 76%|███████▌  | 46758/61904 [1:50:30<5:52:31,  1.40s/it]
 76%|███████▌  | 46759/61904 [1:50:31<5:54:37,  1.40s/it]
 76%|███████▌  | 46760/61904 [1:50:32<5:55:32,  1.41s/it]
                                                         
{'loss': 2.5013, 'learning_rate': 1.2454297938545312e-07, 'epoch': 12.09}

 76%|███████▌  | 46760/61904 [1:50:32<5:55:32,  1.41s/it]
 76%|███████▌  | 46761/61904 [1:50:34<6:02:00,  1.43s/it]
 76%|███████▌  | 46762/61904 [1:50:35<5:53:00,  1.40s/it]
 76%|███████▌  | 46763/61904 [1:50:37<5:49:34,  1.39s/it]
 76%|███████▌  | 46764/61904 [1:50:38<5:44:49,  1.37s/it]
 76%|███████▌  | 46765/61904 [1:50:39<5:43:58,  1.36s/it]
 76%|███████▌  | 46766/61904 [1:50:41<5:45:05,  1.37s/it]
 76%|███████▌  | 46767/61904 [1:50:42<5:50:07,  1.39s/it]
 76%|███████▌  | 46768/61904 [1:50:43<5:39:59,  1.35s/it]
 76%|███████▌  | 46769/61904 [1:50:45<5:41:29,  1.35s/it]
 76%|███████▌  | 46770/61904 [1:50:46<5:44:37,  1.37s/it]
 76%|███████▌  | 46771/61904 [1:50:47<5:44:28,  1.37s/it]
 76%|███████▌  | 46772/61904 [1:50:49<5:43:21,  1.36s/it]
 76%|███████▌  | 46773/61904 [1:50:50<5:39:23,  1.35s/it]
 76%|███████▌  | 46774/61904 [1:50:51<5:41:30,  1.35s/it]
 76%|███████▌  | 46775/61904 [1:50:53<5:41:27,  1.35s/it]
 76%|███████▌  | 46776/61904 [1:50:54<5:49:45,  1.39s/it]
 76%|███████▌  | 46777/61904 [1:50:56<6:01:44,  1.43s/it]
 76%|███████▌  | 46778/61904 [1:50:57<5:51:56,  1.40s/it]
 76%|███████▌  | 46779/61904 [1:50:59<6:00:09,  1.43s/it]
 76%|███████▌  | 46780/61904 [1:51:00<6:02:33,  1.44s/it]
                                                         
{'loss': 2.3997, 'learning_rate': 1.2451056657591079e-07, 'epoch': 12.09}

 76%|███████▌  | 46780/61904 [1:51:00<6:02:33,  1.44s/it]
 76%|███████▌  | 46781/61904 [1:51:02<6:01:14,  1.43s/it]
 76%|███████▌  | 46782/61904 [1:51:03<5:57:38,  1.42s/it]
 76%|███████▌  | 46783/61904 [1:51:04<6:01:10,  1.43s/it]
 76%|███████▌  | 46784/61904 [1:51:06<5:56:09,  1.41s/it]
 76%|███████▌  | 46785/61904 [1:51:07<5:42:04,  1.36s/it]
 76%|███████▌  | 46786/61904 [1:51:08<5:39:16,  1.35s/it]
 76%|███████▌  | 46787/61904 [1:51:10<5:42:21,  1.36s/it]
 76%|███████▌  | 46788/61904 [1:51:11<5:55:32,  1.41s/it]
 76%|███████▌  | 46789/61904 [1:51:13<5:47:18,  1.38s/it]
 76%|███████▌  | 46790/61904 [1:51:14<5:55:30,  1.41s/it]
 76%|███████▌  | 46791/61904 [1:51:15<5:53:52,  1.40s/it]
 76%|███████▌  | 46792/61904 [1:51:17<5:51:01,  1.39s/it]
 76%|███████▌  | 46793/61904 [1:51:18<5:42:22,  1.36s/it]
 76%|███████▌  | 46794/61904 [1:51:19<5:47:21,  1.38s/it]
 76%|███████▌  | 46795/61904 [1:51:21<5:54:39,  1.41s/it]
 76%|███████▌  | 46796/61904 [1:51:22<5:57:21,  1.42s/it]
 76%|███████▌  | 46797/61904 [1:51:24<6:00:43,  1.43s/it]
 76%|███████▌  | 46798/61904 [1:51:25<5:56:05,  1.41s/it]
 76%|███████▌  | 46799/61904 [1:51:27<5:58:21,  1.42s/it]
 76%|███████▌  | 46800/61904 [1:51:28<5:47:03,  1.38s/it]
                                                         
{'loss': 2.4475, 'learning_rate': 1.2447815376636847e-07, 'epoch': 12.1}

 76%|███████▌  | 46800/61904 [1:51:28<5:47:03,  1.38s/it]
 76%|███████▌  | 46801/61904 [1:51:29<5:54:31,  1.41s/it]
 76%|███████▌  | 46802/61904 [1:51:31<5:49:56,  1.39s/it]
 76%|███████▌  | 46803/61904 [1:51:32<5:53:42,  1.41s/it]
 76%|███████▌  | 46804/61904 [1:51:34<5:49:09,  1.39s/it]
 76%|███████▌  | 46805/61904 [1:51:35<6:01:22,  1.44s/it]
 76%|███████▌  | 46806/61904 [1:51:36<5:54:10,  1.41s/it]
 76%|███████▌  | 46807/61904 [1:51:38<5:45:44,  1.37s/it]
 76%|███████▌  | 46808/61904 [1:51:39<6:02:09,  1.44s/it]
 76%|███████▌  | 46809/61904 [1:51:41<6:02:46,  1.44s/it]
 76%|███████▌  | 46810/61904 [1:51:42<5:58:56,  1.43s/it]
 76%|███████▌  | 46811/61904 [1:51:44<5:56:48,  1.42s/it]
 76%|███████▌  | 46812/61904 [1:51:45<5:53:03,  1.40s/it]
 76%|███████▌  | 46813/61904 [1:51:46<5:45:47,  1.37s/it]
 76%|███████▌  | 46814/61904 [1:51:48<5:46:19,  1.38s/it]
 76%|███████▌  | 46815/61904 [1:51:49<6:04:08,  1.45s/it]
 76%|███████▌  | 46816/61904 [1:51:51<6:02:11,  1.44s/it]
 76%|███████▌  | 46817/61904 [1:51:52<6:02:38,  1.44s/it]
 76%|███████▌  | 46818/61904 [1:51:54<6:25:33,  1.53s/it]
 76%|███████▌  | 46819/61904 [1:51:55<6:12:40,  1.48s/it]
 76%|███████▌  | 46820/61904 [1:51:57<6:05:58,  1.46s/it]
                                                         
{'loss': 2.4564, 'learning_rate': 1.2444574095682614e-07, 'epoch': 12.1}

 76%|███████▌  | 46820/61904 [1:51:57<6:05:58,  1.46s/it]
 76%|███████▌  | 46821/61904 [1:51:58<6:04:16,  1.45s/it]
 76%|███████▌  | 46822/61904 [1:51:59<6:03:12,  1.44s/it]
 76%|███████▌  | 46823/61904 [1:52:01<5:53:26,  1.41s/it]
 76%|███████▌  | 46824/61904 [1:52:02<5:45:46,  1.38s/it]
 76%|███████▌  | 46825/61904 [1:52:03<5:45:25,  1.37s/it]
 76%|███████▌  | 46826/61904 [1:52:05<5:41:53,  1.36s/it]
 76%|███████▌  | 46827/61904 [1:52:06<5:50:52,  1.40s/it]
 76%|███████▌  | 46828/61904 [1:52:08<5:41:21,  1.36s/it]
 76%|███████▌  | 46829/61904 [1:52:09<5:47:04,  1.38s/it]
 76%|███████▌  | 46830/61904 [1:52:10<5:50:42,  1.40s/it]
 76%|███████▌  | 46831/61904 [1:52:12<5:44:29,  1.37s/it]
 76%|███████▌  | 46832/61904 [1:52:13<5:55:57,  1.42s/it]
 76%|███████▌  | 46833/61904 [1:52:15<5:49:41,  1.39s/it]
 76%|███████▌  | 46834/61904 [1:52:16<6:02:13,  1.44s/it]
 76%|███████▌  | 46835/61904 [1:52:18<5:59:16,  1.43s/it]
 76%|███████▌  | 46836/61904 [1:52:19<5:54:40,  1.41s/it]
 76%|███████▌  | 46837/61904 [1:52:20<5:57:48,  1.42s/it]
 76%|███████▌  | 46838/61904 [1:52:22<5:59:39,  1.43s/it]
 76%|███████▌  | 46839/61904 [1:52:23<5:54:59,  1.41s/it]
 76%|███████▌  | 46840/61904 [1:52:25<5:49:27,  1.39s/it]
                                                         
{'loss': 2.5028, 'learning_rate': 1.244133281472838e-07, 'epoch': 12.11}

 76%|███████▌  | 46840/61904 [1:52:25<5:49:27,  1.39s/it]
 76%|███████▌  | 46841/61904 [1:52:26<5:49:52,  1.39s/it]
 76%|███████▌  | 46842/61904 [1:52:27<5:43:05,  1.37s/it]
 76%|███████▌  | 46843/61904 [1:52:29<5:41:36,  1.36s/it]
 76%|███████▌  | 46844/61904 [1:52:30<5:43:58,  1.37s/it]
 76%|███████▌  | 46845/61904 [1:52:31<5:37:26,  1.34s/it]
 76%|███████▌  | 46846/61904 [1:52:32<5:28:33,  1.31s/it]
 76%|███████▌  | 46847/61904 [1:52:34<5:47:30,  1.38s/it]
 76%|███████▌  | 46848/61904 [1:52:35<5:49:33,  1.39s/it]
 76%|███████▌  | 46849/61904 [1:52:37<6:01:50,  1.44s/it]
 76%|███████▌  | 46850/61904 [1:52:38<5:55:29,  1.42s/it]
 76%|███████▌  | 46851/61904 [1:52:40<5:50:07,  1.40s/it]
 76%|███████▌  | 46852/61904 [1:52:41<5:47:12,  1.38s/it]
 76%|███████▌  | 46853/61904 [1:52:42<5:44:27,  1.37s/it]
 76%|███████▌  | 46854/61904 [1:52:44<5:40:32,  1.36s/it]
 76%|███████▌  | 46855/61904 [1:52:45<5:35:14,  1.34s/it]
 76%|███████▌  | 46856/61904 [1:52:46<5:38:54,  1.35s/it]
 76%|███████▌  | 46857/61904 [1:52:48<5:49:32,  1.39s/it]
 76%|███████▌  | 46858/61904 [1:52:49<5:53:15,  1.41s/it]
 76%|███████▌  | 46859/61904 [1:52:51<5:40:27,  1.36s/it]
 76%|███████▌  | 46860/61904 [1:52:52<5:34:53,  1.34s/it]
                                                         
{'loss': 2.4969, 'learning_rate': 1.2438091533774146e-07, 'epoch': 12.11}

 76%|███████▌  | 46860/61904 [1:52:52<5:34:53,  1.34s/it]
 76%|███████▌  | 46861/61904 [1:52:53<5:46:10,  1.38s/it]
 76%|███████▌  | 46862/61904 [1:52:55<5:47:06,  1.38s/it]
 76%|███████▌  | 46863/61904 [1:52:56<5:41:07,  1.36s/it]
 76%|███████▌  | 46864/61904 [1:52:57<5:42:38,  1.37s/it]
 76%|███████▌  | 46865/61904 [1:52:59<5:53:20,  1.41s/it]
 76%|███████▌  | 46866/61904 [1:53:00<5:42:03,  1.36s/it]
 76%|███████▌  | 46867/61904 [1:53:02<5:50:29,  1.40s/it]
 76%|███████▌  | 46868/61904 [1:53:03<5:59:30,  1.43s/it]
 76%|███████▌  | 46869/61904 [1:53:04<5:47:05,  1.39s/it]
 76%|███████▌  | 46870/61904 [1:53:06<5:39:03,  1.35s/it]
 76%|███████▌  | 46871/61904 [1:53:07<5:45:58,  1.38s/it]
 76%|███████▌  | 46872/61904 [1:53:09<5:39:43,  1.36s/it]
 76%|███████▌  | 46873/61904 [1:53:10<5:44:14,  1.37s/it]
 76%|███████▌  | 46874/61904 [1:53:11<5:43:44,  1.37s/it]
 76%|███████▌  | 46875/61904 [1:53:13<5:53:27,  1.41s/it]
 76%|███████▌  | 46876/61904 [1:53:14<5:49:31,  1.40s/it]
 76%|███████▌  | 46877/61904 [1:53:15<5:44:56,  1.38s/it]
 76%|███████▌  | 46878/61904 [1:53:17<5:48:25,  1.39s/it]
 76%|███████▌  | 46879/61904 [1:53:18<6:00:33,  1.44s/it]
 76%|███████▌  | 46880/61904 [1:53:20<5:51:46,  1.40s/it]
                                                         
{'loss': 2.4488, 'learning_rate': 1.2434850252819915e-07, 'epoch': 12.12}

 76%|███████▌  | 46880/61904 [1:53:20<5:51:46,  1.40s/it]
 76%|███████▌  | 46881/61904 [1:53:21<5:43:55,  1.37s/it]
 76%|███████▌  | 46882/61904 [1:53:23<5:50:21,  1.40s/it]
 76%|███████▌  | 46883/61904 [1:53:24<5:47:43,  1.39s/it]
 76%|███████▌  | 46884/61904 [1:53:25<5:44:39,  1.38s/it]
 76%|███████▌  | 46885/61904 [1:53:27<5:38:14,  1.35s/it]
 76%|███████▌  | 46886/61904 [1:53:28<5:36:10,  1.34s/it]
 76%|███████▌  | 46887/61904 [1:53:29<5:35:45,  1.34s/it]
 76%|███████▌  | 46888/61904 [1:53:30<5:29:59,  1.32s/it]
 76%|███████▌  | 46889/61904 [1:53:32<5:31:12,  1.32s/it]
 76%|███████▌  | 46890/61904 [1:53:33<5:31:47,  1.33s/it]
 76%|███████▌  | 46891/61904 [1:53:35<5:35:52,  1.34s/it]
 76%|███████▌  | 46892/61904 [1:53:36<5:44:38,  1.38s/it]
 76%|███████▌  | 46893/61904 [1:53:37<5:48:50,  1.39s/it]
 76%|███████▌  | 46894/61904 [1:53:39<5:55:21,  1.42s/it]
 76%|███████▌  | 46895/61904 [1:53:40<5:53:34,  1.41s/it]
 76%|███████▌  | 46896/61904 [1:53:42<5:50:16,  1.40s/it]
 76%|███████▌  | 46897/61904 [1:53:43<5:58:47,  1.43s/it]
 76%|███████▌  | 46898/61904 [1:53:44<5:48:57,  1.40s/it]
 76%|███████▌  | 46899/61904 [1:53:46<5:55:52,  1.42s/it]
 76%|███████▌  | 46900/61904 [1:53:47<5:56:20,  1.43s/it]
                                                         
{'loss': 2.4779, 'learning_rate': 1.243160897186568e-07, 'epoch': 12.12}

 76%|███████▌  | 46900/61904 [1:53:47<5:56:20,  1.43s/it]
 76%|███████▌  | 46901/61904 [1:53:49<5:51:18,  1.40s/it]
 76%|███████▌  | 46902/61904 [1:53:50<5:38:24,  1.35s/it]
 76%|███████▌  | 46903/61904 [1:53:51<5:33:30,  1.33s/it]
 76%|███████▌  | 46904/61904 [1:53:53<5:41:27,  1.37s/it]
 76%|███████▌  | 46905/61904 [1:53:54<5:39:03,  1.36s/it]
 76%|███████▌  | 46906/61904 [1:53:55<5:39:56,  1.36s/it]
 76%|███████▌  | 46907/61904 [1:53:57<5:58:19,  1.43s/it]
 76%|███████▌  | 46908/61904 [1:53:58<5:53:54,  1.42s/it]
 76%|███████▌  | 46909/61904 [1:54:00<5:54:39,  1.42s/it]
 76%|███████▌  | 46910/61904 [1:54:01<5:53:32,  1.41s/it]
 76%|███████▌  | 46911/61904 [1:54:03<5:56:25,  1.43s/it]
 76%|███████▌  | 46912/61904 [1:54:04<5:54:47,  1.42s/it]
 76%|███████▌  | 46913/61904 [1:54:05<5:48:45,  1.40s/it]
 76%|███████▌  | 46914/61904 [1:54:07<5:42:30,  1.37s/it]
 76%|███████▌  | 46915/61904 [1:54:08<5:40:25,  1.36s/it]
 76%|███████▌  | 46916/61904 [1:54:09<5:38:20,  1.35s/it]
 76%|███████▌  | 46917/61904 [1:54:11<5:44:51,  1.38s/it]
 76%|███████▌  | 46918/61904 [1:54:12<5:39:45,  1.36s/it]
 76%|███████▌  | 46919/61904 [1:54:14<6:03:05,  1.45s/it]
 76%|███████▌  | 46920/61904 [1:54:15<6:02:08,  1.45s/it]
                                                         
{'loss': 2.4605, 'learning_rate': 1.2428367690911447e-07, 'epoch': 12.13}

 76%|███████▌  | 46920/61904 [1:54:15<6:02:08,  1.45s/it]
 76%|███████▌  | 46921/61904 [1:54:17<5:47:07,  1.39s/it]
 76%|███████▌  | 46922/61904 [1:54:18<5:47:58,  1.39s/it]
 76%|███████▌  | 46923/61904 [1:54:19<5:53:15,  1.41s/it]
 76%|███████▌  | 46924/61904 [1:54:21<5:52:33,  1.41s/it]
 76%|███████▌  | 46925/61904 [1:54:22<5:49:15,  1.40s/it]
 76%|███████▌  | 46926/61904 [1:54:24<5:44:27,  1.38s/it]
 76%|███████▌  | 46927/61904 [1:54:25<5:44:36,  1.38s/it]
 76%|███████▌  | 46928/61904 [1:54:26<5:51:21,  1.41s/it]
 76%|███████▌  | 46929/61904 [1:54:28<5:44:37,  1.38s/it]
 76%|███████▌  | 46930/61904 [1:54:29<5:58:56,  1.44s/it]
 76%|███████▌  | 46931/61904 [1:54:31<5:59:56,  1.44s/it]
 76%|███████▌  | 46932/61904 [1:54:32<5:55:09,  1.42s/it]
 76%|███████▌  | 46933/61904 [1:54:34<5:59:50,  1.44s/it]
 76%|███████▌  | 46934/61904 [1:54:35<5:49:06,  1.40s/it]
 76%|███████▌  | 46935/61904 [1:54:36<5:43:25,  1.38s/it]
 76%|███████▌  | 46936/61904 [1:54:38<5:49:23,  1.40s/it]
 76%|███████▌  | 46937/61904 [1:54:39<6:11:43,  1.49s/it]
 76%|███████▌  | 46938/61904 [1:54:41<6:02:34,  1.45s/it]
 76%|███████▌  | 46939/61904 [1:54:42<5:55:03,  1.42s/it]
 76%|███████▌  | 46940/61904 [1:54:43<5:51:05,  1.41s/it]
                                                         
{'loss': 2.4592, 'learning_rate': 1.2425126409957216e-07, 'epoch': 12.13}

 76%|███████▌  | 46940/61904 [1:54:43<5:51:05,  1.41s/it]
 76%|███████▌  | 46941/61904 [1:54:45<5:55:13,  1.42s/it]
 76%|███████▌  | 46942/61904 [1:54:46<5:51:26,  1.41s/it]
 76%|███████▌  | 46943/61904 [1:54:48<5:41:13,  1.37s/it]
 76%|███████▌  | 46944/61904 [1:54:49<5:38:31,  1.36s/it]
 76%|███████▌  | 46945/61904 [1:54:50<5:41:34,  1.37s/it]
 76%|███████▌  | 46946/61904 [1:54:52<5:51:53,  1.41s/it]
 76%|███████▌  | 46947/61904 [1:54:53<5:57:26,  1.43s/it]
 76%|███████▌  | 46948/61904 [1:54:55<6:00:06,  1.44s/it]
 76%|███████▌  | 46949/61904 [1:54:56<5:55:20,  1.43s/it]
 76%|███████▌  | 46950/61904 [1:54:58<6:08:02,  1.48s/it]
 76%|███████▌  | 46951/61904 [1:54:59<6:02:55,  1.46s/it]
 76%|███████▌  | 46952/61904 [1:55:01<6:00:02,  1.44s/it]
 76%|███████▌  | 46953/61904 [1:55:02<5:57:31,  1.43s/it]
 76%|███████▌  | 46954/61904 [1:55:03<5:52:29,  1.41s/it]
 76%|███████▌  | 46955/61904 [1:55:05<5:57:48,  1.44s/it]
 76%|███████▌  | 46956/61904 [1:55:06<6:00:06,  1.45s/it]
 76%|███████▌  | 46957/61904 [1:55:08<5:58:00,  1.44s/it]
 76%|███████▌  | 46958/61904 [1:55:09<5:53:31,  1.42s/it]
 76%|███████▌  | 46959/61904 [1:55:11<5:55:36,  1.43s/it]
 76%|███████▌  | 46960/61904 [1:55:12<5:41:42,  1.37s/it]
                                                         
{'loss': 2.5115, 'learning_rate': 1.2421885129002982e-07, 'epoch': 12.14}

 76%|███████▌  | 46960/61904 [1:55:12<5:41:42,  1.37s/it]
 76%|███████▌  | 46961/61904 [1:55:13<5:32:35,  1.34s/it]
 76%|███████▌  | 46962/61904 [1:55:14<5:37:45,  1.36s/it]
 76%|███████▌  | 46963/61904 [1:55:16<5:49:47,  1.40s/it]
 76%|███████▌  | 46964/61904 [1:55:17<5:35:45,  1.35s/it]
 76%|███████▌  | 46965/61904 [1:55:19<5:44:32,  1.38s/it]
 76%|███████▌  | 46966/61904 [1:55:20<5:44:55,  1.39s/it]
 76%|███████▌  | 46967/61904 [1:55:21<5:43:57,  1.38s/it]
 76%|███████▌  | 46968/61904 [1:55:23<5:34:34,  1.34s/it]
 76%|███████▌  | 46969/61904 [1:55:24<5:35:23,  1.35s/it]
 76%|███████▌  | 46970/61904 [1:55:25<5:36:09,  1.35s/it]
 76%|███████▌  | 46971/61904 [1:55:27<5:38:39,  1.36s/it]
 76%|███████▌  | 46972/61904 [1:55:28<5:39:00,  1.36s/it]
 76%|███████▌  | 46973/61904 [1:55:30<5:43:11,  1.38s/it]
 76%|███████▌  | 46974/61904 [1:55:31<5:50:45,  1.41s/it]
 76%|███████▌  | 46975/61904 [1:55:32<5:50:21,  1.41s/it]
 76%|███████▌  | 46976/61904 [1:55:34<6:15:41,  1.51s/it]
 76%|███████▌  | 46977/61904 [1:55:36<6:10:17,  1.49s/it]
 76%|███████▌  | 46978/61904 [1:55:37<6:13:18,  1.50s/it]
 76%|███████▌  | 46979/61904 [1:55:38<6:00:52,  1.45s/it]
 76%|███████▌  | 46980/61904 [1:55:40<6:02:01,  1.46s/it]
                                                         
{'loss': 2.494, 'learning_rate': 1.2418643848048748e-07, 'epoch': 12.14}

 76%|███████▌  | 46980/61904 [1:55:40<6:02:01,  1.46s/it]
 76%|███████▌  | 46981/61904 [1:55:41<5:58:23,  1.44s/it]
 76%|███████▌  | 46982/61904 [1:55:43<6:08:44,  1.48s/it]
 76%|███████▌  | 46983/61904 [1:55:44<5:57:30,  1.44s/it]
 76%|███████▌  | 46984/61904 [1:55:46<5:47:42,  1.40s/it]
 76%|███████▌  | 46985/61904 [1:55:47<5:55:39,  1.43s/it]
 76%|███████▌  | 46986/61904 [1:55:48<5:54:45,  1.43s/it]
 76%|███████▌  | 46987/61904 [1:55:50<5:52:42,  1.42s/it]
 76%|███████▌  | 46988/61904 [1:55:51<5:47:43,  1.40s/it]
 76%|███████▌  | 46989/61904 [1:55:53<5:48:37,  1.40s/it]
 76%|███████▌  | 46990/61904 [1:55:54<5:45:21,  1.39s/it]
 76%|███████▌  | 46991/61904 [1:55:56<6:20:00,  1.53s/it]
 76%|███████▌  | 46992/61904 [1:55:57<6:12:34,  1.50s/it]
 76%|███████▌  | 46993/61904 [1:55:59<6:00:39,  1.45s/it]
 76%|███████▌  | 46994/61904 [1:56:00<5:57:28,  1.44s/it]
 76%|███████▌  | 46995/61904 [1:56:01<5:41:05,  1.37s/it]
 76%|███████▌  | 46996/61904 [1:56:03<5:47:31,  1.40s/it]
 76%|███████▌  | 46997/61904 [1:56:04<5:43:24,  1.38s/it]
 76%|███████▌  | 46998/61904 [1:56:06<5:55:39,  1.43s/it]
 76%|███████▌  | 46999/61904 [1:56:07<5:52:14,  1.42s/it]
 76%|███████▌  | 47000/61904 [1:56:08<5:46:06,  1.39s/it]
                                                         
{'loss': 2.4545, 'learning_rate': 1.2415402567094515e-07, 'epoch': 12.15}

 76%|███████▌  | 47000/61904 [1:56:08<5:46:06,  1.39s/it]
 76%|███████▌  | 47001/61904 [1:56:10<5:46:53,  1.40s/it]
 76%|███████▌  | 47002/61904 [1:56:11<5:46:47,  1.40s/it]
 76%|███████▌  | 47003/61904 [1:56:12<5:45:01,  1.39s/it]
 76%|███████▌  | 47004/61904 [1:56:14<5:53:48,  1.42s/it]
 76%|███████▌  | 47005/61904 [1:56:15<5:47:00,  1.40s/it]
 76%|███████▌  | 47006/61904 [1:56:17<5:43:07,  1.38s/it]
 76%|███████▌  | 47007/61904 [1:56:18<5:45:03,  1.39s/it]
 76%|███████▌  | 47008/61904 [1:56:19<5:44:12,  1.39s/it]
 76%|███████▌  | 47009/61904 [1:56:21<5:47:24,  1.40s/it]
 76%|███████▌  | 47010/61904 [1:56:22<5:44:39,  1.39s/it]
 76%|███████▌  | 47011/61904 [1:56:24<5:49:17,  1.41s/it]
 76%|███████▌  | 47012/61904 [1:56:25<5:44:45,  1.39s/it]
 76%|███████▌  | 47013/61904 [1:56:27<6:00:47,  1.45s/it]
 76%|███████▌  | 47014/61904 [1:56:28<5:45:48,  1.39s/it]
 76%|███████▌  | 47015/61904 [1:56:29<5:54:56,  1.43s/it]
 76%|███████▌  | 47016/61904 [1:56:31<5:41:22,  1.38s/it]
 76%|███████▌  | 47017/61904 [1:56:32<5:45:20,  1.39s/it]
 76%|███████▌  | 47018/61904 [1:56:33<5:42:05,  1.38s/it]
 76%|███████▌  | 47019/61904 [1:56:35<5:34:47,  1.35s/it]
 76%|███████▌  | 47020/61904 [1:56:36<5:41:58,  1.38s/it]
                                                         
{'loss': 2.5211, 'learning_rate': 1.2412161286140283e-07, 'epoch': 12.15}

 76%|███████▌  | 47020/61904 [1:56:36<5:41:58,  1.38s/it]
 76%|███████▌  | 47021/61904 [1:56:37<5:27:51,  1.32s/it]
 76%|███████▌  | 47022/61904 [1:56:39<5:33:37,  1.35s/it]
 76%|███████▌  | 47023/61904 [1:56:40<5:41:31,  1.38s/it]
 76%|███████▌  | 47024/61904 [1:56:42<5:46:20,  1.40s/it]
 76%|███████▌  | 47025/61904 [1:56:43<5:49:23,  1.41s/it]
 76%|███████▌  | 47026/61904 [1:56:45<5:51:24,  1.42s/it]
 76%|███████▌  | 47027/61904 [1:56:46<5:39:47,  1.37s/it]
 76%|███████▌  | 47028/61904 [1:56:47<5:47:30,  1.40s/it]
 76%|███████▌  | 47029/61904 [1:56:49<5:51:21,  1.42s/it]
 76%|███████▌  | 47030/61904 [1:56:50<5:49:48,  1.41s/it]
 76%|███████▌  | 47031/61904 [1:56:52<5:52:38,  1.42s/it]
 76%|███████▌  | 47032/61904 [1:56:53<5:51:28,  1.42s/it]
 76%|███████▌  | 47033/61904 [1:56:54<5:50:34,  1.41s/it]
 76%|███████▌  | 47034/61904 [1:56:56<5:46:17,  1.40s/it]
 76%|███████▌  | 47035/61904 [1:56:57<5:46:06,  1.40s/it]
 76%|███████▌  | 47036/61904 [1:56:59<5:43:03,  1.38s/it]
 76%|███████▌  | 47037/61904 [1:57:00<5:34:51,  1.35s/it]
 76%|███████▌  | 47038/61904 [1:57:01<5:36:55,  1.36s/it]
 76%|███████▌  | 47039/61904 [1:57:03<5:47:12,  1.40s/it]
 76%|███████▌  | 47040/61904 [1:57:04<5:44:55,  1.39s/it]
                                                         
{'loss': 2.4661, 'learning_rate': 1.240892000518605e-07, 'epoch': 12.16}

 76%|███████▌  | 47040/61904 [1:57:04<5:44:55,  1.39s/it]
 76%|███████▌  | 47041/61904 [1:57:06<5:51:37,  1.42s/it]
 76%|███████▌  | 47042/61904 [1:57:07<5:50:14,  1.41s/it]
 76%|███████▌  | 47043/61904 [1:57:08<5:53:40,  1.43s/it]
 76%|███████▌  | 47044/61904 [1:57:10<5:50:47,  1.42s/it]
 76%|███████▌  | 47045/61904 [1:57:11<5:46:18,  1.40s/it]
 76%|███████▌  | 47046/61904 [1:57:12<5:43:42,  1.39s/it]
 76%|███████▌  | 47047/61904 [1:57:14<5:43:36,  1.39s/it]
 76%|███████▌  | 47048/61904 [1:57:15<5:33:04,  1.35s/it]
 76%|███████▌  | 47049/61904 [1:57:17<5:41:01,  1.38s/it]
 76%|███████▌  | 47050/61904 [1:57:18<5:46:58,  1.40s/it]
 76%|███████▌  | 47051/61904 [1:57:19<5:51:05,  1.42s/it]
 76%|███████▌  | 47052/61904 [1:57:21<5:53:58,  1.43s/it]
 76%|███████▌  | 47053/61904 [1:57:22<5:52:05,  1.42s/it]
 76%|███████▌  | 47054/61904 [1:57:24<6:14:53,  1.51s/it]
 76%|███████▌  | 47055/61904 [1:57:25<6:05:56,  1.48s/it]
 76%|███████▌  | 47056/61904 [1:57:27<6:02:43,  1.47s/it]
 76%|███████▌  | 47057/61904 [1:57:28<5:58:08,  1.45s/it]
 76%|███████▌  | 47058/61904 [1:57:30<5:44:14,  1.39s/it]
 76%|███████▌  | 47059/61904 [1:57:31<5:42:52,  1.39s/it]
 76%|███████▌  | 47060/61904 [1:57:32<5:41:38,  1.38s/it]
                                                         
{'loss': 2.4593, 'learning_rate': 1.2405678724231816e-07, 'epoch': 12.16}

 76%|███████▌  | 47060/61904 [1:57:32<5:41:38,  1.38s/it]
 76%|███████▌  | 47061/61904 [1:57:34<5:36:53,  1.36s/it]
 76%|███████▌  | 47062/61904 [1:57:35<5:29:32,  1.33s/it]
 76%|███████▌  | 47063/61904 [1:57:36<5:39:15,  1.37s/it]
 76%|███████▌  | 47064/61904 [1:57:38<5:33:07,  1.35s/it]
 76%|███████▌  | 47065/61904 [1:57:39<5:28:22,  1.33s/it]
 76%|███████▌  | 47066/61904 [1:57:40<5:41:02,  1.38s/it]
 76%|███████▌  | 47067/61904 [1:57:42<5:36:23,  1.36s/it]
 76%|███████▌  | 47068/61904 [1:57:43<5:33:05,  1.35s/it]
 76%|███████▌  | 47069/61904 [1:57:44<5:36:30,  1.36s/it]
 76%|███████▌  | 47070/61904 [1:57:46<5:33:40,  1.35s/it]
 76%|███████▌  | 47071/61904 [1:57:47<5:27:36,  1.33s/it]
 76%|███████▌  | 47072/61904 [1:57:49<5:37:18,  1.36s/it]
 76%|███████▌  | 47073/61904 [1:57:50<5:39:07,  1.37s/it]
 76%|███████▌  | 47074/61904 [1:57:51<5:40:42,  1.38s/it]
 76%|███████▌  | 47075/61904 [1:57:53<5:57:24,  1.45s/it]
 76%|███████▌  | 47076/61904 [1:57:54<6:02:10,  1.47s/it]
 76%|███████▌  | 47077/61904 [1:57:56<5:53:49,  1.43s/it]
 76%|███████▌  | 47078/61904 [1:57:57<5:46:33,  1.40s/it]
 76%|███████▌  | 47079/61904 [1:57:58<5:42:53,  1.39s/it]
 76%|███████▌  | 47080/61904 [1:58:00<5:31:44,  1.34s/it]
                                                         
{'loss': 2.555, 'learning_rate': 1.2402437443277582e-07, 'epoch': 12.17}

 76%|███████▌  | 47080/61904 [1:58:00<5:31:44,  1.34s/it]
 76%|███████▌  | 47081/61904 [1:58:01<5:30:02,  1.34s/it]
 76%|███████▌  | 47082/61904 [1:58:02<5:34:41,  1.35s/it]
 76%|███████▌  | 47083/61904 [1:58:04<5:29:12,  1.33s/it]
 76%|███████▌  | 47084/61904 [1:58:05<5:33:04,  1.35s/it]
 76%|███████▌  | 47085/61904 [1:58:06<5:39:08,  1.37s/it]
 76%|███████▌  | 47086/61904 [1:58:08<5:33:16,  1.35s/it]
 76%|███████▌  | 47087/61904 [1:58:09<5:31:39,  1.34s/it]
 76%|███████▌  | 47088/61904 [1:58:10<5:19:53,  1.30s/it]
 76%|███████▌  | 47089/61904 [1:58:12<5:23:49,  1.31s/it]
 76%|███████▌  | 47090/61904 [1:58:13<5:30:40,  1.34s/it]
 76%|███████▌  | 47091/61904 [1:58:14<5:26:19,  1.32s/it]
 76%|███████▌  | 47092/61904 [1:58:16<5:30:32,  1.34s/it]
 76%|███████▌  | 47093/61904 [1:58:17<5:31:01,  1.34s/it]
 76%|███████▌  | 47094/61904 [1:58:18<5:35:07,  1.36s/it]
 76%|███████▌  | 47095/61904 [1:58:20<5:28:46,  1.33s/it]
 76%|███████▌  | 47096/61904 [1:58:21<5:30:38,  1.34s/it]
 76%|███████▌  | 47097/61904 [1:58:23<5:52:48,  1.43s/it]
 76%|███████▌  | 47098/61904 [1:58:24<5:53:45,  1.43s/it]
 76%|███████▌  | 47099/61904 [1:58:26<5:54:48,  1.44s/it]
 76%|███████▌  | 47100/61904 [1:58:27<5:56:19,  1.44s/it]
                                                         
{'loss': 2.5006, 'learning_rate': 1.239919616232335e-07, 'epoch': 12.17}

 76%|███████▌  | 47100/61904 [1:58:27<5:56:19,  1.44s/it]
 76%|███████▌  | 47101/61904 [1:58:28<5:48:05,  1.41s/it]
 76%|███████▌  | 47102/61904 [1:58:30<5:47:38,  1.41s/it]
 76%|███████▌  | 47103/61904 [1:58:31<5:47:05,  1.41s/it]
 76%|███████▌  | 47104/61904 [1:58:33<5:46:48,  1.41s/it]
 76%|███████▌  | 47105/61904 [1:58:34<5:46:11,  1.40s/it]
 76%|███████▌  | 47106/61904 [1:58:35<5:43:29,  1.39s/it]
 76%|███████▌  | 47107/61904 [1:58:37<5:30:01,  1.34s/it]
 76%|███████▌  | 47108/61904 [1:58:38<5:25:24,  1.32s/it]
 76%|███████▌  | 47109/61904 [1:58:39<5:35:19,  1.36s/it]
 76%|███████▌  | 47110/61904 [1:58:41<5:36:21,  1.36s/it]
 76%|███████▌  | 47111/61904 [1:58:42<5:46:52,  1.41s/it]
 76%|███████▌  | 47112/61904 [1:58:43<5:38:20,  1.37s/it]
 76%|███████▌  | 47113/61904 [1:58:45<5:45:32,  1.40s/it]
 76%|███████▌  | 47114/61904 [1:58:46<5:50:20,  1.42s/it]
 76%|███████▌  | 47115/61904 [1:58:48<5:48:46,  1.42s/it]
 76%|███████▌  | 47116/61904 [1:58:49<5:44:51,  1.40s/it]
 76%|███████▌  | 47117/61904 [1:58:50<5:36:55,  1.37s/it]
 76%|███████▌  | 47118/61904 [1:58:52<5:37:45,  1.37s/it]
 76%|███████▌  | 47119/61904 [1:58:53<5:36:33,  1.37s/it]
 76%|███████▌  | 47120/61904 [1:58:55<5:36:52,  1.37s/it]
                                                         
{'loss': 2.4607, 'learning_rate': 1.2395954881369117e-07, 'epoch': 12.18}

 76%|███████▌  | 47120/61904 [1:58:55<5:36:52,  1.37s/it]
 76%|███████▌  | 47121/61904 [1:58:56<5:31:28,  1.35s/it]
 76%|███████▌  | 47122/61904 [1:58:57<5:30:07,  1.34s/it]
 76%|███████▌  | 47123/61904 [1:58:59<5:30:05,  1.34s/it]
 76%|███████▌  | 47124/61904 [1:59:00<5:28:29,  1.33s/it]
 76%|███████▌  | 47125/61904 [1:59:01<5:31:17,  1.34s/it]
 76%|███████▌  | 47126/61904 [1:59:03<5:37:40,  1.37s/it]
 76%|███████▌  | 47127/61904 [1:59:04<5:38:16,  1.37s/it]
 76%|███████▌  | 47128/61904 [1:59:05<5:39:18,  1.38s/it]
 76%|███████▌  | 47129/61904 [1:59:07<5:31:43,  1.35s/it]
 76%|███████▌  | 47130/61904 [1:59:08<5:38:50,  1.38s/it]
 76%|███████▌  | 47131/61904 [1:59:10<5:48:10,  1.41s/it]
 76%|███████▌  | 47132/61904 [1:59:11<5:45:37,  1.40s/it]
 76%|███████▌  | 47133/61904 [1:59:12<5:40:41,  1.38s/it]
 76%|███████▌  | 47134/61904 [1:59:14<5:32:48,  1.35s/it]
 76%|███████▌  | 47135/61904 [1:59:15<5:31:26,  1.35s/it]
 76%|███████▌  | 47136/61904 [1:59:17<5:44:21,  1.40s/it]
 76%|███████▌  | 47137/61904 [1:59:18<5:46:22,  1.41s/it]
 76%|███████▌  | 47138/61904 [1:59:19<5:38:40,  1.38s/it]
 76%|███████▌  | 47139/61904 [1:59:21<5:49:51,  1.42s/it]
 76%|███████▌  | 47140/61904 [1:59:22<5:43:03,  1.39s/it]
                                                         
{'loss': 2.4595, 'learning_rate': 1.2392713600414883e-07, 'epoch': 12.18}

 76%|███████▌  | 47140/61904 [1:59:22<5:43:03,  1.39s/it]
 76%|███████▌  | 47141/61904 [1:59:24<5:44:37,  1.40s/it]
 76%|███████▌  | 47142/61904 [1:59:25<5:54:26,  1.44s/it]
 76%|███████▌  | 47143/61904 [1:59:26<5:42:14,  1.39s/it]
 76%|███████▌  | 47144/61904 [1:59:28<5:36:20,  1.37s/it]
 76%|███████▌  | 47145/61904 [1:59:29<5:54:01,  1.44s/it]
 76%|███████▌  | 47146/61904 [1:59:31<5:57:13,  1.45s/it]
 76%|███████▌  | 47147/61904 [1:59:32<5:54:02,  1.44s/it]
 76%|███████▌  | 47148/61904 [1:59:34<5:52:30,  1.43s/it]
 76%|███████▌  | 47149/61904 [1:59:35<5:38:58,  1.38s/it]
 76%|███████▌  | 47150/61904 [1:59:36<5:48:23,  1.42s/it]
 76%|███████▌  | 47151/61904 [1:59:38<5:42:10,  1.39s/it]
 76%|███████▌  | 47152/61904 [1:59:39<5:37:24,  1.37s/it]
 76%|███████▌  | 47153/61904 [1:59:40<5:28:17,  1.34s/it]
 76%|███████▌  | 47154/61904 [1:59:42<5:35:39,  1.37s/it]
 76%|███████▌  | 47155/61904 [1:59:43<5:50:44,  1.43s/it]
 76%|███████▌  | 47156/61904 [1:59:45<5:42:32,  1.39s/it]
 76%|███████▌  | 47157/61904 [1:59:46<5:30:45,  1.35s/it]
 76%|███████▌  | 47158/61904 [1:59:47<5:23:56,  1.32s/it]
 76%|███████▌  | 47159/61904 [1:59:48<5:16:20,  1.29s/it]
 76%|███████▌  | 47160/61904 [1:59:50<5:18:59,  1.30s/it]
                                                         
{'loss': 2.444, 'learning_rate': 1.238947231946065e-07, 'epoch': 12.19}

 76%|███████▌  | 47160/61904 [1:59:50<5:18:59,  1.30s/it]
 76%|███████▌  | 47161/61904 [1:59:51<5:29:08,  1.34s/it]
 76%|███████▌  | 47162/61904 [1:59:52<5:24:51,  1.32s/it]
 76%|███████▌  | 47163/61904 [1:59:54<5:34:11,  1.36s/it]
 76%|███████▌  | 47164/61904 [1:59:55<5:28:52,  1.34s/it]
 76%|███████▌  | 47165/61904 [1:59:57<5:40:24,  1.39s/it]
 76%|███████▌  | 47166/61904 [1:59:58<5:38:18,  1.38s/it]
 76%|███████▌  | 47167/61904 [1:59:59<5:50:47,  1.43s/it]
 76%|███████▌  | 47168/61904 [2:00:01<5:42:58,  1.40s/it]
 76%|███████▌  | 47169/61904 [2:00:02<5:46:52,  1.41s/it]
 76%|███████▌  | 47170/61904 [2:00:04<5:44:05,  1.40s/it]
 76%|███████▌  | 47171/61904 [2:00:05<5:35:42,  1.37s/it]
 76%|███████▌  | 47172/61904 [2:00:06<5:32:23,  1.35s/it]
 76%|███████▌  | 47173/61904 [2:00:07<5:24:02,  1.32s/it]
 76%|███████▌  | 47174/61904 [2:00:09<5:20:58,  1.31s/it]
 76%|███████▌  | 47175/61904 [2:00:10<5:16:58,  1.29s/it]
 76%|███████▌  | 47176/61904 [2:00:11<5:18:40,  1.30s/it]
 76%|███████▌  | 47177/61904 [2:00:13<5:17:31,  1.29s/it]
 76%|███████▌  | 47178/61904 [2:00:14<5:30:44,  1.35s/it]
 76%|███████▌  | 47179/61904 [2:00:15<5:25:41,  1.33s/it]
 76%|███████▌  | 47180/61904 [2:00:17<5:28:08,  1.34s/it]
                                                         
{'loss': 2.4657, 'learning_rate': 1.2386231038506418e-07, 'epoch': 12.19}

 76%|███████▌  | 47180/61904 [2:00:17<5:28:08,  1.34s/it]
 76%|███████▌  | 47181/61904 [2:00:18<5:24:48,  1.32s/it]
 76%|███████▌  | 47182/61904 [2:00:19<5:22:40,  1.32s/it]
 76%|███████▌  | 47183/61904 [2:00:21<5:20:18,  1.31s/it]
 76%|███████▌  | 47184/61904 [2:00:22<5:35:28,  1.37s/it]
 76%|███████▌  | 47185/61904 [2:00:24<5:42:41,  1.40s/it]
 76%|███████▌  | 47186/61904 [2:00:25<5:40:15,  1.39s/it]
 76%|███████▌  | 47187/61904 [2:00:26<5:44:49,  1.41s/it]
 76%|███████▌  | 47188/61904 [2:00:28<5:42:37,  1.40s/it]
 76%|███████▌  | 47189/61904 [2:00:29<5:48:27,  1.42s/it]
 76%|███████▌  | 47190/61904 [2:00:31<5:43:34,  1.40s/it]
 76%|███████▌  | 47191/61904 [2:00:32<5:45:32,  1.41s/it]
 76%|███████▌  | 47192/61904 [2:00:33<5:46:31,  1.41s/it]
 76%|███████▌  | 47193/61904 [2:00:35<5:40:56,  1.39s/it]
 76%|███████▌  | 47194/61904 [2:00:36<5:44:28,  1.41s/it]
 76%|███████▌  | 47195/61904 [2:00:37<5:36:42,  1.37s/it]
 76%|███████▌  | 47196/61904 [2:00:39<5:34:53,  1.37s/it]
 76%|███████▌  | 47197/61904 [2:00:40<5:35:36,  1.37s/it]
 76%|███████▌  | 47198/61904 [2:00:42<5:38:52,  1.38s/it]
 76%|███████▌  | 47199/61904 [2:00:43<5:34:37,  1.37s/it]
 76%|███████▌  | 47200/61904 [2:00:44<5:31:30,  1.35s/it]
                                                         
{'loss': 2.454, 'learning_rate': 1.2382989757552184e-07, 'epoch': 12.2}

 76%|███████▌  | 47200/61904 [2:00:44<5:31:30,  1.35s/it]
 76%|███████▌  | 47201/61904 [2:00:46<5:35:22,  1.37s/it]
 76%|███████▋  | 47202/61904 [2:00:47<5:25:44,  1.33s/it]
 76%|███████▋  | 47203/61904 [2:00:48<5:28:50,  1.34s/it]
 76%|███████▋  | 47204/61904 [2:00:50<5:37:31,  1.38s/it]
 76%|███████▋  | 47205/61904 [2:00:51<5:48:37,  1.42s/it]
 76%|███████▋  | 47206/61904 [2:00:53<5:39:53,  1.39s/it]
 76%|███████▋  | 47207/61904 [2:00:54<5:36:57,  1.38s/it]
 76%|███████▋  | 47208/61904 [2:00:55<5:40:07,  1.39s/it]
 76%|███████▋  | 47209/61904 [2:00:57<5:29:10,  1.34s/it]
 76%|███████▋  | 47210/61904 [2:00:58<5:25:38,  1.33s/it]
 76%|███████▋  | 47211/61904 [2:00:59<5:36:34,  1.37s/it]
 76%|███████▋  | 47212/61904 [2:01:01<5:40:51,  1.39s/it]
 76%|███████▋  | 47213/61904 [2:01:02<5:38:06,  1.38s/it]
 76%|███████▋  | 47214/61904 [2:01:04<5:46:16,  1.41s/it]
 76%|███████▋  | 47215/61904 [2:01:05<5:47:12,  1.42s/it]
 76%|███████▋  | 47216/61904 [2:01:06<5:35:59,  1.37s/it]
 76%|███████▋  | 47217/61904 [2:01:08<5:24:50,  1.33s/it]
 76%|███████▋  | 47218/61904 [2:01:09<5:25:33,  1.33s/it]
 76%|███████▋  | 47219/61904 [2:01:10<5:28:43,  1.34s/it]
 76%|███████▋  | 47220/61904 [2:01:12<5:40:21,  1.39s/it]
                                                         
{'loss': 2.4939, 'learning_rate': 1.237974847659795e-07, 'epoch': 12.2}

 76%|███████▋  | 47220/61904 [2:01:12<5:40:21,  1.39s/it]
 76%|███████▋  | 47221/61904 [2:01:13<5:41:49,  1.40s/it]
 76%|███████▋  | 47222/61904 [2:01:15<5:42:06,  1.40s/it]
 76%|███████▋  | 47223/61904 [2:01:16<5:36:04,  1.37s/it]
 76%|███████▋  | 47224/61904 [2:01:17<5:31:56,  1.36s/it]
 76%|███████▋  | 47225/61904 [2:01:19<5:28:30,  1.34s/it]
 76%|███████▋  | 47226/61904 [2:01:20<5:26:31,  1.33s/it]
 76%|███████▋  | 47227/61904 [2:01:21<5:29:42,  1.35s/it]
 76%|███████▋  | 47228/61904 [2:01:22<5:22:56,  1.32s/it]
 76%|███████▋  | 47229/61904 [2:01:24<5:25:26,  1.33s/it]
 76%|███████▋  | 47230/61904 [2:01:25<5:18:11,  1.30s/it]
 76%|███████▋  | 47231/61904 [2:01:26<5:21:48,  1.32s/it]
 76%|███████▋  | 47232/61904 [2:01:28<5:32:43,  1.36s/it]
 76%|███████▋  | 47233/61904 [2:01:29<5:41:04,  1.39s/it]
 76%|███████▋  | 47234/61904 [2:01:31<5:41:00,  1.39s/it]
 76%|███████▋  | 47235/61904 [2:01:32<5:46:42,  1.42s/it]
 76%|███████▋  | 47236/61904 [2:01:34<5:39:08,  1.39s/it]
 76%|███████▋  | 47237/61904 [2:01:35<5:47:18,  1.42s/it]
 76%|███████▋  | 47238/61904 [2:01:36<5:44:55,  1.41s/it]
 76%|███████▋  | 47239/61904 [2:01:38<5:40:28,  1.39s/it]
 76%|███████▋  | 47240/61904 [2:01:39<5:35:25,  1.37s/it]
                                                         
{'loss': 2.4465, 'learning_rate': 1.237650719564372e-07, 'epoch': 12.21}

 76%|███████▋  | 47240/61904 [2:01:39<5:35:25,  1.37s/it]
 76%|███████▋  | 47241/61904 [2:01:41<5:41:01,  1.40s/it]
 76%|███████▋  | 47242/61904 [2:01:42<5:48:51,  1.43s/it]
 76%|███████▋  | 47243/61904 [2:01:43<5:37:44,  1.38s/it]
 76%|███████▋  | 47244/61904 [2:01:45<5:37:16,  1.38s/it]
 76%|███████▋  | 47245/61904 [2:01:46<5:38:31,  1.39s/it]
 76%|███████▋  | 47246/61904 [2:01:47<5:39:47,  1.39s/it]
 76%|███████▋  | 47247/61904 [2:01:49<5:48:12,  1.43s/it]
 76%|███████▋  | 47248/61904 [2:01:50<5:39:18,  1.39s/it]
 76%|███████▋  | 47249/61904 [2:01:52<5:37:40,  1.38s/it]
 76%|███████▋  | 47250/61904 [2:01:53<5:37:45,  1.38s/it]
 76%|███████▋  | 47251/61904 [2:01:54<5:38:24,  1.39s/it]
 76%|███████▋  | 47252/61904 [2:01:56<5:37:09,  1.38s/it]
 76%|███████▋  | 47253/61904 [2:01:57<5:27:46,  1.34s/it]
 76%|███████▋  | 47254/61904 [2:01:58<5:21:38,  1.32s/it]
 76%|███████▋  | 47255/61904 [2:02:00<5:30:12,  1.35s/it]
 76%|███████▋  | 47256/61904 [2:02:01<5:25:44,  1.33s/it]
 76%|███████▋  | 47257/61904 [2:02:03<5:40:14,  1.39s/it]
 76%|███████▋  | 47258/61904 [2:02:04<5:36:57,  1.38s/it]
 76%|███████▋  | 47259/61904 [2:02:05<5:36:56,  1.38s/it]
 76%|███████▋  | 47260/61904 [2:02:07<5:54:49,  1.45s/it]
                                                         
{'loss': 2.5464, 'learning_rate': 1.2373265914689486e-07, 'epoch': 12.21}

 76%|███████▋  | 47260/61904 [2:02:07<5:54:49,  1.45s/it]
 76%|███████▋  | 47261/61904 [2:02:08<5:47:13,  1.42s/it]
 76%|███████▋  | 47262/61904 [2:02:10<5:41:35,  1.40s/it]
 76%|███████▋  | 47263/61904 [2:02:11<5:35:38,  1.38s/it]
 76%|███████▋  | 47264/61904 [2:02:12<5:38:46,  1.39s/it]
 76%|███████▋  | 47265/61904 [2:02:14<5:29:44,  1.35s/it]
 76%|███████▋  | 47266/61904 [2:02:15<5:30:16,  1.35s/it]
 76%|███████▋  | 47267/61904 [2:02:16<5:34:06,  1.37s/it]
 76%|███████▋  | 47268/61904 [2:02:18<5:31:12,  1.36s/it]
 76%|███████▋  | 47269/61904 [2:02:19<5:33:03,  1.37s/it]
 76%|███████▋  | 47270/61904 [2:02:20<5:32:31,  1.36s/it]
 76%|███████▋  | 47271/61904 [2:02:22<5:34:16,  1.37s/it]
 76%|███████▋  | 47272/61904 [2:02:23<5:37:09,  1.38s/it]
 76%|███████▋  | 47273/61904 [2:02:25<5:42:52,  1.41s/it]
 76%|███████▋  | 47274/61904 [2:02:26<5:42:13,  1.40s/it]
 76%|███████▋  | 47275/61904 [2:02:28<5:42:10,  1.40s/it]
 76%|███████▋  | 47276/61904 [2:02:29<5:53:27,  1.45s/it]
 76%|███████▋  | 47277/61904 [2:02:30<5:47:35,  1.43s/it]
 76%|███████▋  | 47278/61904 [2:02:32<5:41:09,  1.40s/it]
 76%|███████▋  | 47279/61904 [2:02:33<5:34:48,  1.37s/it]
 76%|███████▋  | 47280/61904 [2:02:34<5:31:43,  1.36s/it]
                                                         
{'loss': 2.4521, 'learning_rate': 1.2370024633735252e-07, 'epoch': 12.22}

 76%|███████▋  | 47280/61904 [2:02:34<5:31:43,  1.36s/it]
 76%|███████▋  | 47281/61904 [2:02:36<5:44:22,  1.41s/it]
 76%|███████▋  | 47282/61904 [2:02:37<5:45:42,  1.42s/it]
 76%|███████▋  | 47283/61904 [2:02:39<5:53:28,  1.45s/it]
 76%|███████▋  | 47284/61904 [2:02:40<5:44:10,  1.41s/it]
 76%|███████▋  | 47285/61904 [2:02:42<5:35:02,  1.38s/it]
 76%|███████▋  | 47286/61904 [2:02:43<5:33:57,  1.37s/it]
 76%|███████▋  | 47287/61904 [2:02:44<5:36:49,  1.38s/it]
 76%|███████▋  | 47288/61904 [2:02:46<5:32:03,  1.36s/it]
 76%|███████▋  | 47289/61904 [2:02:47<5:24:40,  1.33s/it]
 76%|███████▋  | 47290/61904 [2:02:48<5:30:36,  1.36s/it]
 76%|███████▋  | 47291/61904 [2:02:50<5:27:10,  1.34s/it]
 76%|███████▋  | 47292/61904 [2:02:51<5:29:12,  1.35s/it]
 76%|███████▋  | 47293/61904 [2:02:52<5:22:36,  1.32s/it]
 76%|███████▋  | 47294/61904 [2:02:54<5:21:52,  1.32s/it]
 76%|███████▋  | 47295/61904 [2:02:55<5:29:45,  1.35s/it]
 76%|███████▋  | 47296/61904 [2:02:56<5:34:13,  1.37s/it]
 76%|███████▋  | 47297/61904 [2:02:58<5:35:25,  1.38s/it]
 76%|███████▋  | 47298/61904 [2:02:59<5:28:38,  1.35s/it]
 76%|███████▋  | 47299/61904 [2:03:01<5:48:42,  1.43s/it]
 76%|███████▋  | 47300/61904 [2:03:02<5:49:26,  1.44s/it]
                                                         
{'loss': 2.5132, 'learning_rate': 1.2366783352781018e-07, 'epoch': 12.23}

 76%|███████▋  | 47300/61904 [2:03:02<5:49:26,  1.44s/it]
 76%|███████▋  | 47301/61904 [2:03:04<5:48:15,  1.43s/it]
 76%|███████▋  | 47302/61904 [2:03:05<5:56:00,  1.46s/it]
 76%|███████▋  | 47303/61904 [2:03:06<5:47:12,  1.43s/it]
 76%|███████▋  | 47304/61904 [2:03:08<5:38:49,  1.39s/it]
 76%|███████▋  | 47305/61904 [2:03:09<5:28:32,  1.35s/it]
 76%|███████▋  | 47306/61904 [2:03:11<5:41:37,  1.40s/it]
 76%|███████▋  | 47307/61904 [2:03:12<5:34:16,  1.37s/it]
 76%|███████▋  | 47308/61904 [2:03:13<5:28:47,  1.35s/it]
 76%|███████▋  | 47309/61904 [2:03:15<5:42:03,  1.41s/it]
 76%|███████▋  | 47310/61904 [2:03:16<5:41:28,  1.40s/it]
 76%|███████▋  | 47311/61904 [2:03:17<5:28:45,  1.35s/it]
 76%|███████▋  | 47312/61904 [2:03:19<5:24:41,  1.34s/it]
 76%|███████▋  | 47313/61904 [2:03:20<5:26:52,  1.34s/it]
 76%|███████▋  | 47314/61904 [2:03:21<5:32:08,  1.37s/it]
 76%|███████▋  | 47315/61904 [2:03:23<5:41:11,  1.40s/it]
 76%|███████▋  | 47316/61904 [2:03:24<5:40:10,  1.40s/it]
 76%|███████▋  | 47317/61904 [2:03:26<5:42:31,  1.41s/it]
 76%|███████▋  | 47318/61904 [2:03:27<5:52:46,  1.45s/it]
 76%|███████▋  | 47319/61904 [2:03:29<6:01:17,  1.49s/it]
 76%|███████▋  | 47320/61904 [2:03:30<5:45:15,  1.42s/it]
                                                         
{'loss': 2.43, 'learning_rate': 1.2363542071826787e-07, 'epoch': 12.23}

 76%|███████▋  | 47320/61904 [2:03:30<5:45:15,  1.42s/it]
 76%|███████▋  | 47321/61904 [2:03:31<5:43:20,  1.41s/it]
 76%|███████▋  | 47322/61904 [2:03:33<5:33:51,  1.37s/it]
 76%|███████▋  | 47323/61904 [2:03:34<5:34:36,  1.38s/it]
 76%|███████▋  | 47324/61904 [2:03:36<5:42:45,  1.41s/it]
 76%|███████▋  | 47325/61904 [2:03:37<5:35:10,  1.38s/it]
 76%|███████▋  | 47326/61904 [2:03:38<5:23:15,  1.33s/it]
 76%|███████▋  | 47327/61904 [2:03:39<5:17:23,  1.31s/it]
 76%|███████▋  | 47328/61904 [2:03:41<5:22:20,  1.33s/it]
 76%|███████▋  | 47329/61904 [2:03:42<5:26:49,  1.35s/it]
 76%|███████▋  | 47330/61904 [2:03:44<5:33:13,  1.37s/it]
 76%|███████▋  | 47331/61904 [2:03:45<5:25:37,  1.34s/it]
 76%|███████▋  | 47332/61904 [2:03:46<5:40:43,  1.40s/it]
 76%|███████▋  | 47333/61904 [2:03:48<5:35:35,  1.38s/it]
 76%|███████▋  | 47334/61904 [2:03:49<5:41:09,  1.40s/it]
 76%|███████▋  | 47335/61904 [2:03:51<5:35:24,  1.38s/it]
 76%|███████▋  | 47336/61904 [2:03:52<5:45:01,  1.42s/it]
 76%|███████▋  | 47337/61904 [2:03:53<5:43:31,  1.41s/it]
 76%|███████▋  | 47338/61904 [2:03:55<5:35:02,  1.38s/it]
 76%|███████▋  | 47339/61904 [2:03:56<5:27:15,  1.35s/it]
 76%|███████▋  | 47340/61904 [2:03:57<5:25:29,  1.34s/it]
                                                         
{'loss': 2.4295, 'learning_rate': 1.2360300790872553e-07, 'epoch': 12.24}

 76%|███████▋  | 47340/61904 [2:03:57<5:25:29,  1.34s/it]
 76%|███████▋  | 47341/61904 [2:03:59<5:25:34,  1.34s/it]
 76%|███████▋  | 47342/61904 [2:04:00<5:26:42,  1.35s/it]
 76%|███████▋  | 47343/61904 [2:04:02<5:42:18,  1.41s/it]
 76%|███████▋  | 47344/61904 [2:04:03<5:51:38,  1.45s/it]
 76%|███████▋  | 47345/61904 [2:04:05<6:08:40,  1.52s/it]
 76%|███████▋  | 47346/61904 [2:04:06<5:59:45,  1.48s/it]
 76%|███████▋  | 47347/61904 [2:04:08<5:56:37,  1.47s/it]
 76%|███████▋  | 47348/61904 [2:04:09<5:57:08,  1.47s/it]
 76%|███████▋  | 47349/61904 [2:04:11<5:49:09,  1.44s/it]
 76%|███████▋  | 47350/61904 [2:04:12<5:42:55,  1.41s/it]
 76%|███████▋  | 47351/61904 [2:04:13<5:38:48,  1.40s/it]
 76%|███████▋  | 47352/61904 [2:04:15<5:47:12,  1.43s/it]
 76%|███████▋  | 47353/61904 [2:04:16<5:45:04,  1.42s/it]
 76%|███████▋  | 47354/61904 [2:04:17<5:32:24,  1.37s/it]
 76%|███████▋  | 47355/61904 [2:04:19<5:35:23,  1.38s/it]
 76%|███████▋  | 47356/61904 [2:04:20<5:34:20,  1.38s/it]
 77%|███████▋  | 47357/61904 [2:04:22<5:34:44,  1.38s/it]
 77%|███████▋  | 47358/61904 [2:04:23<5:43:27,  1.42s/it]
 77%|███████▋  | 47359/61904 [2:04:24<5:41:32,  1.41s/it]
 77%|███████▋  | 47360/61904 [2:04:26<5:42:44,  1.41s/it]
                                                         
{'loss': 2.5134, 'learning_rate': 1.235705950991832e-07, 'epoch': 12.24}

 77%|███████▋  | 47360/61904 [2:04:26<5:42:44,  1.41s/it]
 77%|███████▋  | 47361/61904 [2:04:27<5:35:40,  1.38s/it]
 77%|███████▋  | 47362/61904 [2:04:28<5:28:09,  1.35s/it]
 77%|███████▋  | 47363/61904 [2:04:30<6:05:47,  1.51s/it]
 77%|███████▋  | 47364/61904 [2:04:32<5:47:49,  1.44s/it]
 77%|███████▋  | 47365/61904 [2:04:33<5:47:06,  1.43s/it]
 77%|███████▋  | 47366/61904 [2:04:34<5:43:38,  1.42s/it]
 77%|███████▋  | 47367/61904 [2:04:36<5:38:49,  1.40s/it]
 77%|███████▋  | 47368/61904 [2:04:37<5:41:25,  1.41s/it]
 77%|███████▋  | 47369/61904 [2:04:38<5:30:53,  1.37s/it]
 77%|███████▋  | 47370/61904 [2:04:40<5:38:27,  1.40s/it]
 77%|███████▋  | 47371/61904 [2:04:41<5:44:20,  1.42s/it]
 77%|███████▋  | 47372/61904 [2:04:43<5:51:04,  1.45s/it]
 77%|███████▋  | 47373/61904 [2:04:44<5:44:00,  1.42s/it]
 77%|███████▋  | 47374/61904 [2:04:46<5:44:13,  1.42s/it]
 77%|███████▋  | 47375/61904 [2:04:47<5:47:03,  1.43s/it]
 77%|███████▋  | 47376/61904 [2:04:49<5:47:54,  1.44s/it]
 77%|███████▋  | 47377/61904 [2:04:50<5:47:50,  1.44s/it]
 77%|███████▋  | 47378/61904 [2:04:51<5:39:57,  1.40s/it]
 77%|███████▋  | 47379/61904 [2:04:53<5:32:21,  1.37s/it]
 77%|███████▋  | 47380/61904 [2:04:54<5:20:58,  1.33s/it]
                                                         
{'loss': 2.461, 'learning_rate': 1.2353818228964085e-07, 'epoch': 12.25}

 77%|███████▋  | 47380/61904 [2:04:54<5:20:58,  1.33s/it]
 77%|███████▋  | 47381/61904 [2:04:55<5:31:47,  1.37s/it]
 77%|███████▋  | 47382/61904 [2:04:57<5:30:23,  1.37s/it]
 77%|███████▋  | 47383/61904 [2:04:58<5:35:36,  1.39s/it]
 77%|███████▋  | 47384/61904 [2:04:59<5:27:08,  1.35s/it]
 77%|███████▋  | 47385/61904 [2:05:01<5:26:15,  1.35s/it]
 77%|███████▋  | 47386/61904 [2:05:02<5:20:44,  1.33s/it]
 77%|███████▋  | 47387/61904 [2:05:04<5:32:09,  1.37s/it]
 77%|███████▋  | 47388/61904 [2:05:05<5:30:04,  1.36s/it]
 77%|███████▋  | 47389/61904 [2:05:06<5:22:54,  1.33s/it]
 77%|███████▋  | 47390/61904 [2:05:08<5:26:10,  1.35s/it]
 77%|███████▋  | 47391/61904 [2:05:09<5:23:55,  1.34s/it]
 77%|███████▋  | 47392/61904 [2:05:10<5:29:12,  1.36s/it]
 77%|███████▋  | 47393/61904 [2:05:12<5:22:35,  1.33s/it]
 77%|███████▋  | 47394/61904 [2:05:13<5:17:00,  1.31s/it]
 77%|███████▋  | 47395/61904 [2:05:14<5:36:46,  1.39s/it]
 77%|███████▋  | 47396/61904 [2:05:16<5:32:27,  1.37s/it]
 77%|███████▋  | 47397/61904 [2:05:17<5:30:46,  1.37s/it]
 77%|███████▋  | 47398/61904 [2:05:18<5:31:12,  1.37s/it]
 77%|███████▋  | 47399/61904 [2:05:20<5:45:54,  1.43s/it]
 77%|███████▋  | 47400/61904 [2:05:21<5:40:16,  1.41s/it]
                                                         
{'loss': 2.4942, 'learning_rate': 1.2350576948009854e-07, 'epoch': 12.25}

 77%|███████▋  | 47400/61904 [2:05:21<5:40:16,  1.41s/it]
 77%|███████▋  | 47401/61904 [2:05:23<5:51:24,  1.45s/it]
 77%|███████▋  | 47402/61904 [2:05:24<5:46:48,  1.43s/it]
 77%|███████▋  | 47403/61904 [2:05:26<5:43:58,  1.42s/it]
 77%|███████▋  | 47404/61904 [2:05:27<5:38:55,  1.40s/it]
 77%|███████▋  | 47405/61904 [2:05:29<5:45:50,  1.43s/it]
 77%|███████▋  | 47406/61904 [2:05:30<5:58:49,  1.49s/it]
 77%|███████▋  | 47407/61904 [2:05:32<5:52:11,  1.46s/it]
 77%|███████▋  | 47408/61904 [2:05:33<5:47:25,  1.44s/it]
 77%|███████▋  | 47409/61904 [2:05:34<5:46:48,  1.44s/it]
 77%|███████▋  | 47410/61904 [2:05:36<5:50:41,  1.45s/it]
 77%|███████▋  | 47411/61904 [2:05:37<5:37:49,  1.40s/it]
 77%|███████▋  | 47412/61904 [2:05:38<5:30:10,  1.37s/it]
 77%|███████▋  | 47413/61904 [2:05:40<5:26:28,  1.35s/it]
 77%|███████▋  | 47414/61904 [2:05:41<5:23:16,  1.34s/it]
 77%|███████▋  | 47415/61904 [2:05:43<5:31:09,  1.37s/it]
 77%|███████▋  | 47416/61904 [2:05:44<5:29:11,  1.36s/it]
 77%|███████▋  | 47417/61904 [2:05:45<5:36:43,  1.39s/it]
 77%|███████▋  | 47418/61904 [2:05:47<5:37:31,  1.40s/it]
 77%|███████▋  | 47419/61904 [2:05:48<5:33:51,  1.38s/it]
 77%|███████▋  | 47420/61904 [2:05:49<5:34:56,  1.39s/it]
                                                         
{'loss': 2.4607, 'learning_rate': 1.234733566705562e-07, 'epoch': 12.26}

 77%|███████▋  | 47420/61904 [2:05:49<5:34:56,  1.39s/it]
 77%|███████▋  | 47421/61904 [2:05:51<5:35:06,  1.39s/it]
 77%|███████▋  | 47422/61904 [2:05:52<5:32:36,  1.38s/it]
 77%|███████▋  | 47423/61904 [2:05:54<5:29:34,  1.37s/it]
 77%|███████▋  | 47424/61904 [2:05:55<5:44:50,  1.43s/it]
 77%|███████▋  | 47425/61904 [2:05:56<5:35:37,  1.39s/it]
 77%|███████▋  | 47426/61904 [2:05:58<5:27:24,  1.36s/it]
 77%|███████▋  | 47427/61904 [2:05:59<5:23:37,  1.34s/it]
 77%|███████▋  | 47428/61904 [2:06:00<5:23:50,  1.34s/it]
 77%|███████▋  | 47429/61904 [2:06:02<5:41:40,  1.42s/it]
 77%|███████▋  | 47430/61904 [2:06:03<5:35:25,  1.39s/it]
 77%|███████▋  | 47431/61904 [2:06:05<5:29:49,  1.37s/it]
 77%|███████▋  | 47432/61904 [2:06:06<5:29:25,  1.37s/it]
 77%|███████▋  | 47433/61904 [2:06:07<5:28:56,  1.36s/it]
 77%|███████▋  | 47434/61904 [2:06:09<5:30:54,  1.37s/it]
 77%|███████▋  | 47435/61904 [2:06:10<5:23:17,  1.34s/it]
 77%|███████▋  | 47436/61904 [2:06:11<5:21:22,  1.33s/it]
 77%|███████▋  | 47437/61904 [2:06:13<5:40:48,  1.41s/it]
 77%|███████▋  | 47438/61904 [2:06:14<5:43:36,  1.43s/it]
 77%|███████▋  | 47439/61904 [2:06:16<5:38:44,  1.41s/it]
 77%|███████▋  | 47440/61904 [2:06:17<5:38:20,  1.40s/it]
                                                         
{'loss': 2.4634, 'learning_rate': 1.2344094386101387e-07, 'epoch': 12.26}

 77%|███████▋  | 47440/61904 [2:06:17<5:38:20,  1.40s/it]
 77%|███████▋  | 47441/61904 [2:06:18<5:37:54,  1.40s/it]
 77%|███████▋  | 47442/61904 [2:06:20<5:40:47,  1.41s/it]
 77%|███████▋  | 47443/61904 [2:06:21<5:28:13,  1.36s/it]
 77%|███████▋  | 47444/61904 [2:06:22<5:18:02,  1.32s/it]
 77%|███████▋  | 47445/61904 [2:06:24<5:18:51,  1.32s/it]
 77%|███████▋  | 47446/61904 [2:06:25<5:40:10,  1.41s/it]
 77%|███████▋  | 47447/61904 [2:06:27<5:35:34,  1.39s/it]
 77%|███████▋  | 47448/61904 [2:06:28<5:42:17,  1.42s/it]
 77%|███████▋  | 47449/61904 [2:06:30<5:43:42,  1.43s/it]
 77%|███████▋  | 47450/61904 [2:06:31<5:40:14,  1.41s/it]
 77%|███████▋  | 47451/61904 [2:06:32<5:33:27,  1.38s/it]
 77%|███████▋  | 47452/61904 [2:06:34<5:29:29,  1.37s/it]
 77%|███████▋  | 47453/61904 [2:06:35<5:21:46,  1.34s/it]
 77%|███████▋  | 47454/61904 [2:06:36<5:33:27,  1.38s/it]
 77%|███████▋  | 47455/61904 [2:06:38<5:38:27,  1.41s/it]
 77%|███████▋  | 47456/61904 [2:06:39<5:30:14,  1.37s/it]
 77%|███████▋  | 47457/61904 [2:06:40<5:24:15,  1.35s/it]
 77%|███████▋  | 47458/61904 [2:06:42<5:37:22,  1.40s/it]
 77%|███████▋  | 47459/61904 [2:06:43<5:36:02,  1.40s/it]
 77%|███████▋  | 47460/61904 [2:06:45<5:29:54,  1.37s/it]
                                                         
{'loss': 2.4448, 'learning_rate': 1.2340853105147153e-07, 'epoch': 12.27}

 77%|███████▋  | 47460/61904 [2:06:45<5:29:54,  1.37s/it]
 77%|███████▋  | 47461/61904 [2:06:46<5:25:22,  1.35s/it]
 77%|███████▋  | 47462/61904 [2:06:47<5:28:20,  1.36s/it]
 77%|███████▋  | 47463/61904 [2:06:49<5:24:04,  1.35s/it]
 77%|███████▋  | 47464/61904 [2:06:50<5:25:00,  1.35s/it]
 77%|███████▋  | 47465/61904 [2:06:51<5:27:45,  1.36s/it]
 77%|███████▋  | 47466/61904 [2:06:53<5:26:42,  1.36s/it]
 77%|███████▋  | 47467/61904 [2:06:54<5:24:32,  1.35s/it]
 77%|███████▋  | 47468/61904 [2:06:55<5:23:35,  1.34s/it]
 77%|███████▋  | 47469/61904 [2:06:57<5:21:09,  1.33s/it]
 77%|███████▋  | 47470/61904 [2:06:58<5:19:16,  1.33s/it]
 77%|███████▋  | 47471/61904 [2:06:59<5:12:25,  1.30s/it]
 77%|███████▋  | 47472/61904 [2:07:01<5:30:54,  1.38s/it]
 77%|███████▋  | 47473/61904 [2:07:02<5:28:28,  1.37s/it]
 77%|███████▋  | 47474/61904 [2:07:04<5:32:08,  1.38s/it]
 77%|███████▋  | 47475/61904 [2:07:05<5:28:02,  1.36s/it]
 77%|███████▋  | 47476/61904 [2:07:06<5:29:43,  1.37s/it]
 77%|███████▋  | 47477/61904 [2:07:08<5:38:28,  1.41s/it]
 77%|███████▋  | 47478/61904 [2:07:09<5:45:29,  1.44s/it]
 77%|███████▋  | 47479/61904 [2:07:11<5:46:58,  1.44s/it]
 77%|███████▋  | 47480/61904 [2:07:12<5:41:01,  1.42s/it]
                                                         
{'loss': 2.4803, 'learning_rate': 1.2337611824192922e-07, 'epoch': 12.27}

 77%|███████▋  | 47480/61904 [2:07:12<5:41:01,  1.42s/it]
 77%|███████▋  | 47481/61904 [2:07:14<5:41:03,  1.42s/it]
 77%|███████▋  | 47482/61904 [2:07:15<5:30:44,  1.38s/it]
 77%|███████▋  | 47483/61904 [2:07:16<5:45:39,  1.44s/it]
 77%|███████▋  | 47484/61904 [2:07:18<5:41:31,  1.42s/it]
 77%|███████▋  | 47485/61904 [2:07:19<5:32:08,  1.38s/it]
 77%|███████▋  | 47486/61904 [2:07:20<5:33:52,  1.39s/it]
 77%|███████▋  | 47487/61904 [2:07:22<5:27:58,  1.36s/it]
 77%|███████▋  | 47488/61904 [2:07:23<5:35:03,  1.39s/it]
 77%|███████▋  | 47489/61904 [2:07:25<5:30:31,  1.38s/it]
 77%|███████▋  | 47490/61904 [2:07:26<5:19:27,  1.33s/it]
 77%|███████▋  | 47491/61904 [2:07:27<5:12:37,  1.30s/it]
 77%|███████▋  | 47492/61904 [2:07:28<5:11:47,  1.30s/it]
 77%|███████▋  | 47493/61904 [2:07:30<5:11:45,  1.30s/it]
 77%|███████▋  | 47494/61904 [2:07:31<5:22:07,  1.34s/it]
 77%|███████▋  | 47495/61904 [2:07:32<5:15:59,  1.32s/it]
 77%|███████▋  | 47496/61904 [2:07:34<5:23:05,  1.35s/it]
 77%|███████▋  | 47497/61904 [2:07:35<5:27:19,  1.36s/it]
 77%|███████▋  | 47498/61904 [2:07:37<5:28:49,  1.37s/it]
 77%|███████▋  | 47499/61904 [2:07:38<5:25:04,  1.35s/it]
 77%|███████▋  | 47500/61904 [2:07:39<5:40:39,  1.42s/it]
                                                         
{'loss': 2.4154, 'learning_rate': 1.2334370543238688e-07, 'epoch': 12.28}

 77%|███████▋  | 47500/61904 [2:07:39<5:40:39,  1.42s/it]
 77%|███████▋  | 47501/61904 [2:07:41<5:37:25,  1.41s/it]
 77%|███████▋  | 47502/61904 [2:07:42<5:34:07,  1.39s/it]
 77%|███████▋  | 47503/61904 [2:07:43<5:26:29,  1.36s/it]
 77%|███████▋  | 47504/61904 [2:07:45<5:23:46,  1.35s/it]
 77%|███████▋  | 47505/61904 [2:07:46<5:31:05,  1.38s/it]
 77%|███████▋  | 47506/61904 [2:07:48<5:29:04,  1.37s/it]
 77%|███████▋  | 47507/61904 [2:07:49<5:27:12,  1.36s/it]
 77%|███████▋  | 47508/61904 [2:07:50<5:36:25,  1.40s/it]
 77%|███████▋  | 47509/61904 [2:07:52<5:31:31,  1.38s/it]
 77%|███████▋  | 47510/61904 [2:07:53<5:24:03,  1.35s/it]
 77%|███████▋  | 47511/61904 [2:07:54<5:30:16,  1.38s/it]
 77%|███████▋  | 47512/61904 [2:07:56<5:27:03,  1.36s/it]
 77%|███████▋  | 47513/61904 [2:07:57<5:24:02,  1.35s/it]
 77%|███████▋  | 47514/61904 [2:07:59<5:31:37,  1.38s/it]
 77%|███████▋  | 47515/61904 [2:08:00<5:34:36,  1.40s/it]
 77%|███████▋  | 47516/61904 [2:08:01<5:27:22,  1.37s/it]
 77%|███████▋  | 47517/61904 [2:08:03<5:32:23,  1.39s/it]
 77%|███████▋  | 47518/61904 [2:08:04<5:24:12,  1.35s/it]
 77%|███████▋  | 47519/61904 [2:08:05<5:22:51,  1.35s/it]
 77%|███████▋  | 47520/61904 [2:08:07<5:27:58,  1.37s/it]
                                                         
{'loss': 2.5181, 'learning_rate': 1.2331129262284454e-07, 'epoch': 12.28}

 77%|███████▋  | 47520/61904 [2:08:07<5:27:58,  1.37s/it]
 77%|███████▋  | 47521/61904 [2:08:08<5:27:21,  1.37s/it]
 77%|███████▋  | 47522/61904 [2:08:10<5:43:49,  1.43s/it]
 77%|███████▋  | 47523/61904 [2:08:11<5:39:41,  1.42s/it]
 77%|███████▋  | 47524/61904 [2:08:12<5:39:23,  1.42s/it]
 77%|███████▋  | 47525/61904 [2:08:14<5:38:04,  1.41s/it]
 77%|███████▋  | 47526/61904 [2:08:15<5:32:41,  1.39s/it]
 77%|███████▋  | 47527/61904 [2:08:17<5:35:10,  1.40s/it]
 77%|███████▋  | 47528/61904 [2:08:18<5:39:49,  1.42s/it]
 77%|███████▋  | 47529/61904 [2:08:19<5:36:51,  1.41s/it]
 77%|███████▋  | 47530/61904 [2:08:21<5:24:21,  1.35s/it]
 77%|███████▋  | 47531/61904 [2:08:22<5:25:43,  1.36s/it]
 77%|███████▋  | 47532/61904 [2:08:23<5:25:35,  1.36s/it]
 77%|███████▋  | 47533/61904 [2:08:25<5:38:12,  1.41s/it]
 77%|███████▋  | 47534/61904 [2:08:26<5:33:05,  1.39s/it]
 77%|███████▋  | 47535/61904 [2:08:28<5:37:03,  1.41s/it]
 77%|███████▋  | 47536/61904 [2:08:29<5:35:21,  1.40s/it]
 77%|███████▋  | 47537/61904 [2:08:31<5:32:58,  1.39s/it]
 77%|███████▋  | 47538/61904 [2:08:32<5:29:57,  1.38s/it]
 77%|███████▋  | 47539/61904 [2:08:33<5:24:54,  1.36s/it]
 77%|███████▋  | 47540/61904 [2:08:35<5:36:35,  1.41s/it]
                                                         
{'loss': 2.5086, 'learning_rate': 1.2327887981330223e-07, 'epoch': 12.29}

 77%|███████▋  | 47540/61904 [2:08:35<5:36:35,  1.41s/it]
 77%|███████▋  | 47541/61904 [2:08:36<5:44:16,  1.44s/it]
 77%|███████▋  | 47542/61904 [2:08:38<5:36:34,  1.41s/it]
 77%|███████▋  | 47543/61904 [2:08:39<5:26:07,  1.36s/it]
 77%|███████▋  | 47544/61904 [2:08:40<5:22:09,  1.35s/it]
 77%|███████▋  | 47545/61904 [2:08:42<5:31:59,  1.39s/it]
 77%|███████▋  | 47546/61904 [2:08:43<5:31:57,  1.39s/it]
 77%|███████▋  | 47547/61904 [2:08:44<5:23:22,  1.35s/it]
 77%|███████▋  | 47548/61904 [2:08:46<5:30:34,  1.38s/it]
 77%|███████▋  | 47549/61904 [2:08:47<5:30:34,  1.38s/it]
 77%|███████▋  | 47550/61904 [2:08:48<5:31:20,  1.39s/it]
 77%|███████▋  | 47551/61904 [2:08:50<5:32:36,  1.39s/it]
 77%|███████▋  | 47552/61904 [2:08:51<5:22:31,  1.35s/it]
 77%|███████▋  | 47553/61904 [2:08:52<5:14:59,  1.32s/it]
 77%|███████▋  | 47554/61904 [2:08:54<5:20:18,  1.34s/it]
 77%|███████▋  | 47555/61904 [2:08:55<5:10:06,  1.30s/it]
 77%|███████▋  | 47556/61904 [2:08:56<5:15:11,  1.32s/it]
 77%|███████▋  | 47557/61904 [2:08:58<5:20:01,  1.34s/it]
 77%|███████▋  | 47558/61904 [2:08:59<5:18:21,  1.33s/it]
 77%|███████▋  | 47559/61904 [2:09:01<5:27:35,  1.37s/it]
 77%|███████▋  | 47560/61904 [2:09:02<5:23:10,  1.35s/it]
                                                         
{'loss': 2.4487, 'learning_rate': 1.232464670037599e-07, 'epoch': 12.29}

 77%|███████▋  | 47560/61904 [2:09:02<5:23:10,  1.35s/it]
 77%|███████▋  | 47561/61904 [2:09:03<5:34:23,  1.40s/it]
 77%|███████▋  | 47562/61904 [2:09:05<5:23:13,  1.35s/it]
 77%|███████▋  | 47563/61904 [2:09:06<5:20:33,  1.34s/it]
 77%|███████▋  | 47564/61904 [2:09:07<5:32:33,  1.39s/it]
 77%|███████▋  | 47565/61904 [2:09:09<5:30:49,  1.38s/it]
 77%|███████▋  | 47566/61904 [2:09:10<5:33:52,  1.40s/it]
 77%|███████▋  | 47567/61904 [2:09:12<5:34:25,  1.40s/it]
 77%|███████▋  | 47568/61904 [2:09:13<5:29:19,  1.38s/it]
 77%|███████▋  | 47569/61904 [2:09:14<5:24:53,  1.36s/it]
 77%|███████▋  | 47570/61904 [2:09:16<5:27:12,  1.37s/it]
 77%|███████▋  | 47571/61904 [2:09:17<5:27:51,  1.37s/it]
 77%|███████▋  | 47572/61904 [2:09:18<5:31:41,  1.39s/it]
 77%|███████▋  | 47573/61904 [2:09:20<5:40:53,  1.43s/it]
 77%|███████▋  | 47574/61904 [2:09:21<5:34:28,  1.40s/it]
 77%|███████▋  | 47575/61904 [2:09:23<5:23:36,  1.36s/it]
 77%|███████▋  | 47576/61904 [2:09:24<5:23:43,  1.36s/it]
 77%|███████▋  | 47577/61904 [2:09:25<5:23:28,  1.35s/it]
 77%|███████▋  | 47578/61904 [2:09:27<5:19:26,  1.34s/it]
 77%|███████▋  | 47579/61904 [2:09:28<5:20:05,  1.34s/it]
 77%|███████▋  | 47580/61904 [2:09:29<5:32:24,  1.39s/it]
                                                         
{'loss': 2.4109, 'learning_rate': 1.2321405419421755e-07, 'epoch': 12.3}

 77%|███████▋  | 47580/61904 [2:09:29<5:32:24,  1.39s/it]
 77%|███████▋  | 47581/61904 [2:09:31<5:26:25,  1.37s/it]
 77%|███████▋  | 47582/61904 [2:09:32<5:22:42,  1.35s/it]
 77%|███████▋  | 47583/61904 [2:09:33<5:23:54,  1.36s/it]
 77%|███████▋  | 47584/61904 [2:09:35<5:27:02,  1.37s/it]
 77%|███████▋  | 47585/61904 [2:09:36<5:25:49,  1.37s/it]
 77%|███████▋  | 47586/61904 [2:09:37<5:19:13,  1.34s/it]
 77%|███████▋  | 47587/61904 [2:09:39<5:28:26,  1.38s/it]
 77%|███████▋  | 47588/61904 [2:09:40<5:20:12,  1.34s/it]
 77%|███████▋  | 47589/61904 [2:09:42<5:23:22,  1.36s/it]
 77%|███████▋  | 47590/61904 [2:09:43<5:22:59,  1.35s/it]
 77%|███████▋  | 47591/61904 [2:09:44<5:28:52,  1.38s/it]
 77%|███████▋  | 47592/61904 [2:09:46<5:34:51,  1.40s/it]
 77%|███████▋  | 47593/61904 [2:09:47<5:26:03,  1.37s/it]
 77%|███████▋  | 47594/61904 [2:09:48<5:23:06,  1.35s/it]
 77%|███████▋  | 47595/61904 [2:09:50<5:19:11,  1.34s/it]
 77%|███████▋  | 47596/61904 [2:09:51<5:14:45,  1.32s/it]
 77%|███████▋  | 47597/61904 [2:09:52<5:23:33,  1.36s/it]
 77%|███████▋  | 47598/61904 [2:09:54<5:24:48,  1.36s/it]
 77%|███████▋  | 47599/61904 [2:09:55<5:35:55,  1.41s/it]
 77%|███████▋  | 47600/61904 [2:09:57<5:28:17,  1.38s/it]
                                                         
{'loss': 2.4675, 'learning_rate': 1.2318164138467521e-07, 'epoch': 12.3}

 77%|███████▋  | 47600/61904 [2:09:57<5:28:17,  1.38s/it]
 77%|███████▋  | 47601/61904 [2:09:58<5:23:41,  1.36s/it]
 77%|███████▋  | 47602/61904 [2:09:59<5:22:04,  1.35s/it]
 77%|███████▋  | 47603/61904 [2:10:01<5:33:00,  1.40s/it]
 77%|███████▋  | 47604/61904 [2:10:02<5:26:20,  1.37s/it]
 77%|███████▋  | 47605/61904 [2:10:03<5:26:16,  1.37s/it]
 77%|███████▋  | 47606/61904 [2:10:05<5:19:45,  1.34s/it]
 77%|███████▋  | 47607/61904 [2:10:06<5:30:58,  1.39s/it]
 77%|███████▋  | 47608/61904 [2:10:08<5:25:30,  1.37s/it]
 77%|███████▋  | 47609/61904 [2:10:09<5:32:10,  1.39s/it]
 77%|███████▋  | 47610/61904 [2:10:10<5:24:57,  1.36s/it]
 77%|███████▋  | 47611/61904 [2:10:12<5:32:03,  1.39s/it]
 77%|███████▋  | 47612/61904 [2:10:13<5:30:59,  1.39s/it]
 77%|███████▋  | 47613/61904 [2:10:14<5:26:49,  1.37s/it]
 77%|███████▋  | 47614/61904 [2:10:16<5:23:59,  1.36s/it]
 77%|███████▋  | 47615/61904 [2:10:17<5:18:28,  1.34s/it]
 77%|███████▋  | 47616/61904 [2:10:18<5:19:53,  1.34s/it]
 77%|███████▋  | 47617/61904 [2:10:20<5:19:23,  1.34s/it]
 77%|███████▋  | 47618/61904 [2:10:21<5:27:03,  1.37s/it]
 77%|███████▋  | 47619/61904 [2:10:23<5:24:49,  1.36s/it]
 77%|███████▋  | 47620/61904 [2:10:24<5:32:07,  1.40s/it]
                                                         
{'loss': 2.4326, 'learning_rate': 1.2314922857513288e-07, 'epoch': 12.31}

 77%|███████▋  | 47620/61904 [2:10:24<5:32:07,  1.40s/it]
 77%|███████▋  | 47621/61904 [2:10:25<5:22:36,  1.36s/it]
 77%|███████▋  | 47622/61904 [2:10:27<5:30:36,  1.39s/it]
 77%|███████▋  | 47623/61904 [2:10:28<5:25:40,  1.37s/it]
 77%|███████▋  | 47624/61904 [2:10:30<5:31:54,  1.39s/it]
 77%|███████▋  | 47625/61904 [2:10:31<5:36:50,  1.42s/it]
 77%|███████▋  | 47626/61904 [2:10:32<5:26:39,  1.37s/it]
 77%|███████▋  | 47627/61904 [2:10:34<5:24:36,  1.36s/it]
 77%|███████▋  | 47628/61904 [2:10:35<5:25:01,  1.37s/it]
 77%|███████▋  | 47629/61904 [2:10:36<5:25:44,  1.37s/it]
 77%|███████▋  | 47630/61904 [2:10:38<5:20:26,  1.35s/it]
 77%|███████▋  | 47631/61904 [2:10:39<5:35:30,  1.41s/it]
 77%|███████▋  | 47632/61904 [2:10:41<5:37:14,  1.42s/it]
 77%|███████▋  | 47633/61904 [2:10:42<5:33:32,  1.40s/it]
 77%|███████▋  | 47634/61904 [2:10:43<5:31:03,  1.39s/it]
 77%|███████▋  | 47635/61904 [2:10:45<5:34:53,  1.41s/it]
 77%|███████▋  | 47636/61904 [2:10:46<5:39:44,  1.43s/it]
 77%|███████▋  | 47637/61904 [2:10:48<5:28:24,  1.38s/it]
 77%|███████▋  | 47638/61904 [2:10:49<5:27:52,  1.38s/it]
 77%|███████▋  | 47639/61904 [2:10:50<5:24:39,  1.37s/it]
 77%|███████▋  | 47640/61904 [2:10:52<5:23:04,  1.36s/it]
                                                         
{'loss': 2.441, 'learning_rate': 1.2311681576559056e-07, 'epoch': 12.31}

 77%|███████▋  | 47640/61904 [2:10:52<5:23:04,  1.36s/it]
 77%|███████▋  | 47641/61904 [2:10:53<5:25:48,  1.37s/it]
 77%|███████▋  | 47642/61904 [2:10:55<5:33:53,  1.40s/it]
 77%|███████▋  | 47643/61904 [2:10:56<5:25:57,  1.37s/it]
 77%|███████▋  | 47644/61904 [2:10:57<5:25:23,  1.37s/it]
 77%|███████▋  | 47645/61904 [2:10:59<5:28:24,  1.38s/it]
 77%|███████▋  | 47646/61904 [2:11:00<5:27:01,  1.38s/it]
 77%|███████▋  | 47647/61904 [2:11:01<5:27:06,  1.38s/it]
 77%|███████▋  | 47648/61904 [2:11:03<5:28:54,  1.38s/it]
 77%|███████▋  | 47649/61904 [2:11:04<5:24:27,  1.37s/it]
 77%|███████▋  | 47650/61904 [2:11:05<5:21:39,  1.35s/it]
 77%|███████▋  | 47651/61904 [2:11:07<5:33:35,  1.40s/it]
 77%|███████▋  | 47652/61904 [2:11:08<5:22:48,  1.36s/it]
 77%|███████▋  | 47653/61904 [2:11:09<5:21:22,  1.35s/it]
 77%|███████▋  | 47654/61904 [2:11:11<5:14:40,  1.32s/it]
 77%|███████▋  | 47655/61904 [2:11:12<5:14:19,  1.32s/it]
 77%|███████▋  | 47656/61904 [2:11:13<5:19:59,  1.35s/it]
 77%|███████▋  | 47657/61904 [2:11:15<5:35:12,  1.41s/it]
 77%|███████▋  | 47658/61904 [2:11:16<5:28:46,  1.38s/it]
 77%|███████▋  | 47659/61904 [2:11:18<5:21:38,  1.35s/it]
 77%|███████▋  | 47660/61904 [2:11:19<5:25:17,  1.37s/it]
                                                         
{'loss': 2.4154, 'learning_rate': 1.2308440295604823e-07, 'epoch': 12.32}

 77%|███████▋  | 47660/61904 [2:11:19<5:25:17,  1.37s/it]
 77%|███████▋  | 47661/61904 [2:11:20<5:29:02,  1.39s/it]
 77%|███████▋  | 47662/61904 [2:11:22<5:35:33,  1.41s/it]
 77%|███████▋  | 47663/61904 [2:11:23<5:32:22,  1.40s/it]
 77%|███████▋  | 47664/61904 [2:11:25<5:25:35,  1.37s/it]
 77%|███████▋  | 47665/61904 [2:11:26<5:20:04,  1.35s/it]
 77%|███████▋  | 47666/61904 [2:11:27<5:23:17,  1.36s/it]
 77%|███████▋  | 47667/61904 [2:11:29<5:18:03,  1.34s/it]
 77%|███████▋  | 47668/61904 [2:11:30<5:15:39,  1.33s/it]
 77%|███████▋  | 47669/61904 [2:11:31<5:20:27,  1.35s/it]
 77%|███████▋  | 47670/61904 [2:11:32<5:09:13,  1.30s/it]
 77%|███████▋  | 47671/61904 [2:11:34<5:18:50,  1.34s/it]
 77%|███████▋  | 47672/61904 [2:11:35<5:18:18,  1.34s/it]
 77%|███████▋  | 47673/61904 [2:11:37<5:21:07,  1.35s/it]
 77%|███████▋  | 47674/61904 [2:11:38<5:23:41,  1.36s/it]
 77%|███████▋  | 47675/61904 [2:11:40<5:35:53,  1.42s/it]
 77%|███████▋  | 47676/61904 [2:11:41<5:35:44,  1.42s/it]
 77%|███████▋  | 47677/61904 [2:11:42<5:28:03,  1.38s/it]
 77%|███████▋  | 47678/61904 [2:11:44<5:19:01,  1.35s/it]
 77%|███████▋  | 47679/61904 [2:11:45<5:30:19,  1.39s/it]
 77%|███████▋  | 47680/61904 [2:11:47<5:34:18,  1.41s/it]
                                                         
{'loss': 2.4491, 'learning_rate': 1.230519901465059e-07, 'epoch': 12.32}

 77%|███████▋  | 47680/61904 [2:11:47<5:34:18,  1.41s/it]
 77%|███████▋  | 47681/61904 [2:11:48<5:38:06,  1.43s/it]
 77%|███████▋  | 47682/61904 [2:11:49<5:28:29,  1.39s/it]
 77%|███████▋  | 47683/61904 [2:11:51<5:25:11,  1.37s/it]
 77%|███████▋  | 47684/61904 [2:11:52<5:32:08,  1.40s/it]
 77%|███████▋  | 47685/61904 [2:11:53<5:26:24,  1.38s/it]
 77%|███████▋  | 47686/61904 [2:11:55<5:18:27,  1.34s/it]
 77%|███████▋  | 47687/61904 [2:11:56<5:21:01,  1.35s/it]
 77%|███████▋  | 47688/61904 [2:11:57<5:21:39,  1.36s/it]
 77%|███████▋  | 47689/61904 [2:11:59<5:27:42,  1.38s/it]
 77%|███████▋  | 47690/61904 [2:12:00<5:13:45,  1.32s/it]
 77%|███████▋  | 47691/61904 [2:12:01<5:12:41,  1.32s/it]
 77%|███████▋  | 47692/61904 [2:12:03<5:14:27,  1.33s/it]
 77%|███████▋  | 47693/61904 [2:12:04<5:32:09,  1.40s/it]
 77%|███████▋  | 47694/61904 [2:12:06<5:21:21,  1.36s/it]
 77%|███████▋  | 47695/61904 [2:12:07<5:21:58,  1.36s/it]
 77%|███████▋  | 47696/61904 [2:12:08<5:22:04,  1.36s/it]
 77%|███████▋  | 47697/61904 [2:12:10<5:28:25,  1.39s/it]
 77%|███████▋  | 47698/61904 [2:12:11<5:18:42,  1.35s/it]
 77%|███████▋  | 47699/61904 [2:12:12<5:21:03,  1.36s/it]
 77%|███████▋  | 47700/61904 [2:12:14<5:15:05,  1.33s/it]
                                                         
{'loss': 2.4764, 'learning_rate': 1.2301957733696358e-07, 'epoch': 12.33}

 77%|███████▋  | 47700/61904 [2:12:14<5:15:05,  1.33s/it]
 77%|███████▋  | 47701/61904 [2:12:15<5:11:56,  1.32s/it]
 77%|███████▋  | 47702/61904 [2:12:16<5:19:59,  1.35s/it]
 77%|███████▋  | 47703/61904 [2:12:18<5:23:14,  1.37s/it]
 77%|███████▋  | 47704/61904 [2:12:19<5:16:45,  1.34s/it]
 77%|███████▋  | 47705/61904 [2:12:20<5:10:40,  1.31s/it]
 77%|███████▋  | 47706/61904 [2:12:22<5:12:24,  1.32s/it]
 77%|███████▋  | 47707/61904 [2:12:23<5:32:48,  1.41s/it]
 77%|███████▋  | 47708/61904 [2:12:25<5:36:50,  1.42s/it]
 77%|███████▋  | 47709/61904 [2:12:26<5:29:24,  1.39s/it]
 77%|███████▋  | 47710/61904 [2:12:27<5:21:04,  1.36s/it]
 77%|███████▋  | 47711/61904 [2:12:29<5:26:56,  1.38s/it]
 77%|███████▋  | 47712/61904 [2:12:30<5:32:13,  1.40s/it]
 77%|███████▋  | 47713/61904 [2:12:31<5:19:50,  1.35s/it]
 77%|███████▋  | 47714/61904 [2:12:33<5:15:46,  1.34s/it]
 77%|███████▋  | 47715/61904 [2:12:34<5:26:53,  1.38s/it]
 77%|███████▋  | 47716/61904 [2:12:35<5:20:07,  1.35s/it]
 77%|███████▋  | 47717/61904 [2:12:37<5:18:48,  1.35s/it]
 77%|███████▋  | 47718/61904 [2:12:38<5:28:47,  1.39s/it]
 77%|███████▋  | 47719/61904 [2:12:40<5:25:55,  1.38s/it]
 77%|███████▋  | 47720/61904 [2:12:41<5:25:25,  1.38s/it]
                                                         
{'loss': 2.4786, 'learning_rate': 1.2298716452742124e-07, 'epoch': 12.33}

 77%|███████▋  | 47720/61904 [2:12:41<5:25:25,  1.38s/it]
 77%|███████▋  | 47721/61904 [2:12:42<5:27:37,  1.39s/it]
 77%|███████▋  | 47722/61904 [2:12:44<5:27:56,  1.39s/it]
 77%|███████▋  | 47723/61904 [2:12:45<5:34:12,  1.41s/it]
 77%|███████▋  | 47724/61904 [2:12:47<5:33:16,  1.41s/it]
 77%|███████▋  | 47725/61904 [2:12:48<5:26:50,  1.38s/it]
 77%|███████▋  | 47726/61904 [2:12:50<5:52:14,  1.49s/it]
 77%|███████▋  | 47727/61904 [2:12:51<5:47:17,  1.47s/it]
 77%|███████▋  | 47728/61904 [2:12:53<5:45:24,  1.46s/it]
 77%|███████▋  | 47729/61904 [2:12:54<5:39:43,  1.44s/it]
 77%|███████▋  | 47730/61904 [2:12:55<5:34:08,  1.41s/it]
 77%|███████▋  | 47731/61904 [2:12:57<5:25:06,  1.38s/it]
 77%|███████▋  | 47732/61904 [2:12:58<5:21:30,  1.36s/it]
 77%|███████▋  | 47733/61904 [2:12:59<5:28:15,  1.39s/it]
 77%|███████▋  | 47734/61904 [2:13:01<5:16:29,  1.34s/it]
 77%|███████▋  | 47735/61904 [2:13:02<5:16:24,  1.34s/it]
 77%|███████▋  | 47736/61904 [2:13:03<5:14:20,  1.33s/it]
 77%|███████▋  | 47737/61904 [2:13:05<5:11:55,  1.32s/it]
 77%|███████▋  | 47738/61904 [2:13:06<5:03:31,  1.29s/it]
 77%|███████▋  | 47739/61904 [2:13:07<5:15:31,  1.34s/it]
 77%|███████▋  | 47740/61904 [2:13:09<5:24:51,  1.38s/it]
                                                         
{'loss': 2.4033, 'learning_rate': 1.229547517178789e-07, 'epoch': 12.34}

 77%|███████▋  | 47740/61904 [2:13:09<5:24:51,  1.38s/it]
 77%|███████▋  | 47741/61904 [2:13:10<5:20:58,  1.36s/it]
 77%|███████▋  | 47742/61904 [2:13:11<5:17:36,  1.35s/it]
 77%|███████▋  | 47743/61904 [2:13:13<5:16:54,  1.34s/it]
 77%|███████▋  | 47744/61904 [2:13:14<5:17:28,  1.35s/it]
 77%|███████▋  | 47745/61904 [2:13:15<5:20:34,  1.36s/it]
 77%|███████▋  | 47746/61904 [2:13:17<5:22:35,  1.37s/it]
 77%|███████▋  | 47747/61904 [2:13:18<5:23:56,  1.37s/it]
 77%|███████▋  | 47748/61904 [2:13:20<5:26:04,  1.38s/it]
 77%|███████▋  | 47749/61904 [2:13:21<5:27:57,  1.39s/it]
 77%|███████▋  | 47750/61904 [2:13:22<5:29:47,  1.40s/it]
 77%|███████▋  | 47751/61904 [2:13:24<5:18:37,  1.35s/it]
 77%|███████▋  | 47752/61904 [2:13:25<5:19:34,  1.35s/it]
 77%|███████▋  | 47753/61904 [2:13:26<5:15:48,  1.34s/it]
 77%|███████▋  | 47754/61904 [2:13:28<5:25:50,  1.38s/it]
 77%|███████▋  | 47755/61904 [2:13:29<5:37:19,  1.43s/it]
 77%|███████▋  | 47756/61904 [2:13:31<5:40:44,  1.45s/it]
 77%|███████▋  | 47757/61904 [2:13:32<5:37:20,  1.43s/it]
 77%|███████▋  | 47758/61904 [2:13:34<5:30:28,  1.40s/it]
 77%|███████▋  | 47759/61904 [2:13:35<5:21:31,  1.36s/it]
 77%|███████▋  | 47760/61904 [2:13:36<5:16:46,  1.34s/it]
                                                         
{'loss': 2.4742, 'learning_rate': 1.2292233890833656e-07, 'epoch': 12.34}

 77%|███████▋  | 47760/61904 [2:13:36<5:16:46,  1.34s/it]
 77%|███████▋  | 47761/61904 [2:13:37<5:13:19,  1.33s/it]
 77%|███████▋  | 47762/61904 [2:13:39<5:19:06,  1.35s/it]
 77%|███████▋  | 47763/61904 [2:13:40<5:13:52,  1.33s/it]
 77%|███████▋  | 47764/61904 [2:13:41<5:16:42,  1.34s/it]
 77%|███████▋  | 47765/61904 [2:13:43<5:38:05,  1.43s/it]
 77%|███████▋  | 47766/61904 [2:13:45<5:42:09,  1.45s/it]
 77%|███████▋  | 47767/61904 [2:13:46<5:39:37,  1.44s/it]
 77%|███████▋  | 47768/61904 [2:13:47<5:33:30,  1.42s/it]
 77%|███████▋  | 47769/61904 [2:13:49<5:32:39,  1.41s/it]
 77%|███████▋  | 47770/61904 [2:13:50<5:31:37,  1.41s/it]
 77%|███████▋  | 47771/61904 [2:13:52<5:27:34,  1.39s/it]
 77%|███████▋  | 47772/61904 [2:13:53<5:20:59,  1.36s/it]
 77%|███████▋  | 47773/61904 [2:13:54<5:15:15,  1.34s/it]
 77%|███████▋  | 47774/61904 [2:13:56<5:21:19,  1.36s/it]
 77%|███████▋  | 47775/61904 [2:13:57<5:11:30,  1.32s/it]
 77%|███████▋  | 47776/61904 [2:13:58<5:16:26,  1.34s/it]
 77%|███████▋  | 47777/61904 [2:14:00<5:24:22,  1.38s/it]
 77%|███████▋  | 47778/61904 [2:14:01<5:27:06,  1.39s/it]
 77%|███████▋  | 47779/61904 [2:14:02<5:25:14,  1.38s/it]
 77%|███████▋  | 47780/61904 [2:14:04<5:25:39,  1.38s/it]
                                                         
{'loss': 2.5316, 'learning_rate': 1.2288992609879422e-07, 'epoch': 12.35}

 77%|███████▋  | 47780/61904 [2:14:04<5:25:39,  1.38s/it]
 77%|███████▋  | 47781/61904 [2:14:05<5:23:04,  1.37s/it]
 77%|███████▋  | 47782/61904 [2:14:06<5:19:52,  1.36s/it]
 77%|███████▋  | 47783/61904 [2:14:08<5:10:16,  1.32s/it]
 77%|███████▋  | 47784/61904 [2:14:09<5:20:53,  1.36s/it]
 77%|███████▋  | 47785/61904 [2:14:11<5:20:27,  1.36s/it]
 77%|███████▋  | 47786/61904 [2:14:12<5:25:24,  1.38s/it]
 77%|███████▋  | 47787/61904 [2:14:13<5:24:54,  1.38s/it]
 77%|███████▋  | 47788/61904 [2:14:15<5:22:46,  1.37s/it]
 77%|███████▋  | 47789/61904 [2:14:16<5:21:58,  1.37s/it]
 77%|███████▋  | 47790/61904 [2:14:17<5:15:09,  1.34s/it]
 77%|███████▋  | 47791/61904 [2:14:19<5:15:36,  1.34s/it]
 77%|███████▋  | 47792/61904 [2:14:20<5:21:19,  1.37s/it]
 77%|███████▋  | 47793/61904 [2:14:21<5:16:44,  1.35s/it]
 77%|███████▋  | 47794/61904 [2:14:23<5:16:31,  1.35s/it]
 77%|███████▋  | 47795/61904 [2:14:24<5:17:51,  1.35s/it]
 77%|███████▋  | 47796/61904 [2:14:26<5:23:49,  1.38s/it]
 77%|███████▋  | 47797/61904 [2:14:27<5:16:02,  1.34s/it]
 77%|███████▋  | 47798/61904 [2:14:28<5:14:57,  1.34s/it]
 77%|███████▋  | 47799/61904 [2:14:29<5:11:42,  1.33s/it]
 77%|███████▋  | 47800/61904 [2:14:31<5:08:22,  1.31s/it]
                                                         
{'loss': 2.4717, 'learning_rate': 1.228575132892519e-07, 'epoch': 12.35}

 77%|███████▋  | 47800/61904 [2:14:31<5:08:22,  1.31s/it]
 77%|███████▋  | 47801/61904 [2:14:32<5:20:37,  1.36s/it]
 77%|███████▋  | 47802/61904 [2:14:33<5:13:00,  1.33s/it]
 77%|███████▋  | 47803/61904 [2:14:35<5:12:59,  1.33s/it]
 77%|███████▋  | 47804/61904 [2:14:36<5:17:22,  1.35s/it]
 77%|███████▋  | 47805/61904 [2:14:38<5:17:05,  1.35s/it]
 77%|███████▋  | 47806/61904 [2:14:39<5:20:16,  1.36s/it]
 77%|███████▋  | 47807/61904 [2:14:40<5:13:18,  1.33s/it]
 77%|███████▋  | 47808/61904 [2:14:41<5:11:35,  1.33s/it]
 77%|███████▋  | 47809/61904 [2:14:43<5:12:44,  1.33s/it]
 77%|███████▋  | 47810/61904 [2:14:44<5:11:52,  1.33s/it]
 77%|███████▋  | 47811/61904 [2:14:46<5:16:35,  1.35s/it]
 77%|███████▋  | 47812/61904 [2:14:47<5:20:18,  1.36s/it]
 77%|███████▋  | 47813/61904 [2:14:48<5:19:46,  1.36s/it]
 77%|███████▋  | 47814/61904 [2:14:50<5:29:11,  1.40s/it]
 77%|███████▋  | 47815/61904 [2:14:51<5:25:42,  1.39s/it]
 77%|███████▋  | 47816/61904 [2:14:53<5:23:42,  1.38s/it]
 77%|███████▋  | 47817/61904 [2:14:54<5:29:20,  1.40s/it]
 77%|███████▋  | 47818/61904 [2:14:55<5:20:49,  1.37s/it]
 77%|███████▋  | 47819/61904 [2:14:57<5:17:01,  1.35s/it]
 77%|███████▋  | 47820/61904 [2:14:58<5:21:10,  1.37s/it]
                                                         
{'loss': 2.4518, 'learning_rate': 1.2282510047970957e-07, 'epoch': 12.36}

 77%|███████▋  | 47820/61904 [2:14:58<5:21:10,  1.37s/it]
 77%|███████▋  | 47821/61904 [2:14:59<5:15:28,  1.34s/it]
 77%|███████▋  | 47822/61904 [2:15:01<5:10:07,  1.32s/it]
 77%|███████▋  | 47823/61904 [2:15:02<5:07:21,  1.31s/it]
 77%|███████▋  | 47824/61904 [2:15:03<5:06:53,  1.31s/it]
 77%|███████▋  | 47825/61904 [2:15:04<5:03:54,  1.30s/it]
 77%|███████▋  | 47826/61904 [2:15:06<5:15:16,  1.34s/it]
 77%|███████▋  | 47827/61904 [2:15:07<5:29:45,  1.41s/it]
 77%|███████▋  | 47828/61904 [2:15:09<5:23:53,  1.38s/it]
 77%|███████▋  | 47829/61904 [2:15:10<5:25:36,  1.39s/it]
 77%|███████▋  | 47830/61904 [2:15:12<5:26:51,  1.39s/it]
 77%|███████▋  | 47831/61904 [2:15:13<5:23:04,  1.38s/it]
 77%|███████▋  | 47832/61904 [2:15:14<5:35:52,  1.43s/it]
 77%|███████▋  | 47833/61904 [2:15:16<5:24:41,  1.38s/it]
 77%|███████▋  | 47834/61904 [2:15:17<5:31:47,  1.41s/it]
 77%|███████▋  | 47835/61904 [2:15:18<5:23:58,  1.38s/it]
 77%|███████▋  | 47836/61904 [2:15:20<5:14:12,  1.34s/it]
 77%|███████▋  | 47837/61904 [2:15:21<5:11:47,  1.33s/it]
 77%|███████▋  | 47838/61904 [2:15:22<5:15:16,  1.34s/it]
 77%|███████▋  | 47839/61904 [2:15:24<5:20:20,  1.37s/it]
 77%|███████▋  | 47840/61904 [2:15:25<5:20:02,  1.37s/it]
                                                         
{'loss': 2.4747, 'learning_rate': 1.2279268767016724e-07, 'epoch': 12.36}

 77%|███████▋  | 47840/61904 [2:15:25<5:20:02,  1.37s/it]
 77%|███████▋  | 47841/61904 [2:15:27<5:35:52,  1.43s/it]
 77%|███████▋  | 47842/61904 [2:15:28<5:31:10,  1.41s/it]
 77%|███████▋  | 47843/61904 [2:15:30<5:29:15,  1.41s/it]
 77%|███████▋  | 47844/61904 [2:15:31<5:28:34,  1.40s/it]
 77%|███████▋  | 47845/61904 [2:15:32<5:24:18,  1.38s/it]
 77%|███████▋  | 47846/61904 [2:15:34<5:17:42,  1.36s/it]
 77%|███████▋  | 47847/61904 [2:15:35<5:15:09,  1.35s/it]
 77%|███████▋  | 47848/61904 [2:15:36<5:23:23,  1.38s/it]
 77%|███████▋  | 47849/61904 [2:15:38<5:18:07,  1.36s/it]
 77%|███████▋  | 47850/61904 [2:15:39<5:15:15,  1.35s/it]
 77%|███████▋  | 47851/61904 [2:15:40<5:20:42,  1.37s/it]
 77%|███████▋  | 47852/61904 [2:15:42<5:15:49,  1.35s/it]
 77%|███████▋  | 47853/61904 [2:15:43<5:21:50,  1.37s/it]
 77%|███████▋  | 47854/61904 [2:15:45<5:23:45,  1.38s/it]
 77%|███████▋  | 47855/61904 [2:15:46<5:28:45,  1.40s/it]
 77%|███████▋  | 47856/61904 [2:15:47<5:26:40,  1.40s/it]
 77%|███████▋  | 47857/61904 [2:15:49<5:21:41,  1.37s/it]
 77%|███████▋  | 47858/61904 [2:15:50<5:32:56,  1.42s/it]
 77%|███████▋  | 47859/61904 [2:15:52<5:22:45,  1.38s/it]
 77%|███████▋  | 47860/61904 [2:15:53<5:16:35,  1.35s/it]
                                                         
{'loss': 2.4391, 'learning_rate': 1.2276027486062492e-07, 'epoch': 12.37}

 77%|███████▋  | 47860/61904 [2:15:53<5:16:35,  1.35s/it]
 77%|███████▋  | 47861/61904 [2:15:54<5:08:41,  1.32s/it]
 77%|███████▋  | 47862/61904 [2:15:55<5:09:51,  1.32s/it]
 77%|███████▋  | 47863/61904 [2:15:57<5:26:30,  1.40s/it]
 77%|███████▋  | 47864/61904 [2:15:58<5:29:52,  1.41s/it]
 77%|███████▋  | 47865/61904 [2:16:00<5:25:41,  1.39s/it]
 77%|███████▋  | 47866/61904 [2:16:01<5:27:30,  1.40s/it]
 77%|███████▋  | 47867/61904 [2:16:03<5:24:37,  1.39s/it]
 77%|███████▋  | 47868/61904 [2:16:04<5:23:58,  1.38s/it]
 77%|███████▋  | 47869/61904 [2:16:05<5:24:09,  1.39s/it]
 77%|███████▋  | 47870/61904 [2:16:07<5:22:11,  1.38s/it]
 77%|███████▋  | 47871/61904 [2:16:08<5:17:31,  1.36s/it]
 77%|███████▋  | 47872/61904 [2:16:09<5:13:15,  1.34s/it]
 77%|███████▋  | 47873/61904 [2:16:11<5:14:19,  1.34s/it]
 77%|███████▋  | 47874/61904 [2:16:12<5:11:48,  1.33s/it]
 77%|███████▋  | 47875/61904 [2:16:13<5:09:24,  1.32s/it]
 77%|███████▋  | 47876/61904 [2:16:15<5:22:11,  1.38s/it]
 77%|███████▋  | 47877/61904 [2:16:16<5:19:52,  1.37s/it]
 77%|███████▋  | 47878/61904 [2:16:17<5:18:28,  1.36s/it]
 77%|███████▋  | 47879/61904 [2:16:19<5:26:14,  1.40s/it]
 77%|███████▋  | 47880/61904 [2:16:20<5:24:39,  1.39s/it]
                                                         
{'loss': 2.4076, 'learning_rate': 1.2272786205108259e-07, 'epoch': 12.38}

 77%|███████▋  | 47880/61904 [2:16:20<5:24:39,  1.39s/it]
 77%|███████▋  | 47881/61904 [2:16:22<5:20:50,  1.37s/it]
 77%|███████▋  | 47882/61904 [2:16:23<5:11:48,  1.33s/it]
 77%|███████▋  | 47883/61904 [2:16:24<5:18:20,  1.36s/it]
 77%|███████▋  | 47884/61904 [2:16:26<5:12:34,  1.34s/it]
 77%|███████▋  | 47885/61904 [2:16:27<5:16:49,  1.36s/it]
 77%|███████▋  | 47886/61904 [2:16:28<5:21:28,  1.38s/it]
 77%|███████▋  | 47887/61904 [2:16:30<5:20:19,  1.37s/it]
 77%|███████▋  | 47888/61904 [2:16:31<5:16:36,  1.36s/it]
 77%|███████▋  | 47889/61904 [2:16:32<5:16:06,  1.35s/it]
 77%|███████▋  | 47890/61904 [2:16:34<5:18:59,  1.37s/it]
 77%|███████▋  | 47891/61904 [2:16:35<5:17:05,  1.36s/it]
 77%|███████▋  | 47892/61904 [2:16:37<5:20:28,  1.37s/it]
 77%|███████▋  | 47893/61904 [2:16:38<5:36:38,  1.44s/it]
 77%|███████▋  | 47894/61904 [2:16:40<5:32:50,  1.43s/it]
 77%|███████▋  | 47895/61904 [2:16:41<5:25:40,  1.39s/it]
 77%|███████▋  | 47896/61904 [2:16:42<5:24:51,  1.39s/it]
 77%|███████▋  | 47897/61904 [2:16:44<5:19:03,  1.37s/it]
 77%|███████▋  | 47898/61904 [2:16:45<5:19:20,  1.37s/it]
 77%|███████▋  | 47899/61904 [2:16:46<5:16:01,  1.35s/it]
 77%|███████▋  | 47900/61904 [2:16:48<5:19:37,  1.37s/it]
                                                         
{'loss': 2.4275, 'learning_rate': 1.2269544924154025e-07, 'epoch': 12.38}

 77%|███████▋  | 47900/61904 [2:16:48<5:19:37,  1.37s/it]
 77%|███████▋  | 47901/61904 [2:16:49<5:12:39,  1.34s/it]
 77%|███████▋  | 47902/61904 [2:16:50<5:15:39,  1.35s/it]
 77%|███████▋  | 47903/61904 [2:16:52<5:19:59,  1.37s/it]
 77%|███████▋  | 47904/61904 [2:16:53<5:16:01,  1.35s/it]
 77%|███████▋  | 47905/61904 [2:16:54<5:21:23,  1.38s/it]
 77%|███████▋  | 47906/61904 [2:16:56<5:21:52,  1.38s/it]
 77%|███████▋  | 47907/61904 [2:16:57<5:22:28,  1.38s/it]
 77%|███████▋  | 47908/61904 [2:16:59<5:21:10,  1.38s/it]
 77%|███████▋  | 47909/61904 [2:17:00<5:23:58,  1.39s/it]
 77%|███████▋  | 47910/61904 [2:17:01<5:30:03,  1.42s/it]
 77%|███████▋  | 47911/61904 [2:17:03<5:30:06,  1.42s/it]
 77%|███████▋  | 47912/61904 [2:17:04<5:33:41,  1.43s/it]
 77%|███████▋  | 47913/61904 [2:17:06<5:25:41,  1.40s/it]
 77%|███████▋  | 47914/61904 [2:17:07<5:27:09,  1.40s/it]
 77%|███████▋  | 47915/61904 [2:17:08<5:27:15,  1.40s/it]
 77%|███████▋  | 47916/61904 [2:17:10<5:26:48,  1.40s/it]
 77%|███████▋  | 47917/61904 [2:17:11<5:29:22,  1.41s/it]
 77%|███████▋  | 47918/61904 [2:17:13<5:29:42,  1.41s/it]
 77%|███████▋  | 47919/61904 [2:17:14<5:34:50,  1.44s/it]
 77%|███████▋  | 47920/61904 [2:17:16<5:25:31,  1.40s/it]
                                                         
{'loss': 2.4593, 'learning_rate': 1.2266303643199794e-07, 'epoch': 12.39}

 77%|███████▋  | 47920/61904 [2:17:16<5:25:31,  1.40s/it]
 77%|███████▋  | 47921/61904 [2:17:17<5:24:21,  1.39s/it]
 77%|███████▋  | 47922/61904 [2:17:18<5:12:43,  1.34s/it]
 77%|███████▋  | 47923/61904 [2:17:20<5:21:23,  1.38s/it]
 77%|███████▋  | 47924/61904 [2:17:21<5:16:52,  1.36s/it]
 77%|███████▋  | 47925/61904 [2:17:22<5:08:04,  1.32s/it]
 77%|███████▋  | 47926/61904 [2:17:24<5:09:30,  1.33s/it]
 77%|███████▋  | 47927/61904 [2:17:25<5:13:59,  1.35s/it]
 77%|███████▋  | 47928/61904 [2:17:26<5:05:56,  1.31s/it]
 77%|███████▋  | 47929/61904 [2:17:27<5:04:57,  1.31s/it]
 77%|███████▋  | 47930/61904 [2:17:29<5:05:01,  1.31s/it]
 77%|███████▋  | 47931/61904 [2:17:30<5:14:39,  1.35s/it]
 77%|███████▋  | 47932/61904 [2:17:32<5:27:52,  1.41s/it]
 77%|███████▋  | 47933/61904 [2:17:33<5:21:31,  1.38s/it]
 77%|███████▋  | 47934/61904 [2:17:34<5:19:54,  1.37s/it]
 77%|███████▋  | 47935/61904 [2:17:36<5:16:16,  1.36s/it]
 77%|███████▋  | 47936/61904 [2:17:37<5:29:45,  1.42s/it]
 77%|███████▋  | 47937/61904 [2:17:39<5:44:54,  1.48s/it]
 77%|███████▋  | 47938/61904 [2:17:40<5:28:01,  1.41s/it]
 77%|███████▋  | 47939/61904 [2:17:42<5:31:00,  1.42s/it]
 77%|███████▋  | 47940/61904 [2:17:43<5:28:36,  1.41s/it]
                                                         
{'loss': 2.4666, 'learning_rate': 1.226306236224556e-07, 'epoch': 12.39}

 77%|███████▋  | 47940/61904 [2:17:43<5:28:36,  1.41s/it]
 77%|███████▋  | 47941/61904 [2:17:44<5:23:10,  1.39s/it]
 77%|███████▋  | 47942/61904 [2:17:46<5:26:37,  1.40s/it]
 77%|███████▋  | 47943/61904 [2:17:47<5:27:23,  1.41s/it]
 77%|███████▋  | 47944/61904 [2:17:49<5:23:47,  1.39s/it]
 77%|███████▋  | 47945/61904 [2:17:50<5:19:04,  1.37s/it]
 77%|███████▋  | 47946/61904 [2:17:51<5:17:46,  1.37s/it]
 77%|███████▋  | 47947/61904 [2:17:52<5:09:43,  1.33s/it]
 77%|███████▋  | 47948/61904 [2:17:54<5:13:25,  1.35s/it]
 77%|███████▋  | 47949/61904 [2:17:55<5:15:32,  1.36s/it]
 77%|███████▋  | 47950/61904 [2:17:57<5:19:43,  1.37s/it]
 77%|███████▋  | 47951/61904 [2:17:58<5:18:32,  1.37s/it]
 77%|███████▋  | 47952/61904 [2:17:59<5:17:03,  1.36s/it]
 77%|███████▋  | 47953/61904 [2:18:01<5:10:50,  1.34s/it]
 77%|███████▋  | 47954/61904 [2:18:02<5:09:39,  1.33s/it]
 77%|███████▋  | 47955/61904 [2:18:03<5:06:53,  1.32s/it]
 77%|███████▋  | 47956/61904 [2:18:05<5:18:51,  1.37s/it]
 77%|███████▋  | 47957/61904 [2:18:06<5:17:55,  1.37s/it]
 77%|███████▋  | 47958/61904 [2:18:08<5:23:55,  1.39s/it]
 77%|███████▋  | 47959/61904 [2:18:09<5:17:54,  1.37s/it]
 77%|███████▋  | 47960/61904 [2:18:10<5:34:01,  1.44s/it]
                                                         
{'loss': 2.4939, 'learning_rate': 1.2259821081291326e-07, 'epoch': 12.4}

 77%|███████▋  | 47960/61904 [2:18:10<5:34:01,  1.44s/it]
 77%|███████▋  | 47961/61904 [2:18:12<5:23:54,  1.39s/it]
 77%|███████▋  | 47962/61904 [2:18:13<5:37:28,  1.45s/it]
 77%|███████▋  | 47963/61904 [2:18:15<5:30:50,  1.42s/it]
 77%|███████▋  | 47964/61904 [2:18:16<5:29:16,  1.42s/it]
 77%|███████▋  | 47965/61904 [2:18:17<5:20:09,  1.38s/it]
 77%|███████▋  | 47966/61904 [2:18:19<5:24:13,  1.40s/it]
 77%|███████▋  | 47967/61904 [2:18:20<5:25:21,  1.40s/it]
 77%|███████▋  | 47968/61904 [2:18:22<5:19:55,  1.38s/it]
 77%|███████▋  | 47969/61904 [2:18:23<5:12:05,  1.34s/it]
 77%|███████▋  | 47970/61904 [2:18:24<5:13:37,  1.35s/it]
 77%|███████▋  | 47971/61904 [2:18:26<5:29:22,  1.42s/it]
 77%|███████▋  | 47972/61904 [2:18:27<5:34:01,  1.44s/it]
 77%|███████▋  | 47973/61904 [2:18:29<5:26:36,  1.41s/it]
 77%|███████▋  | 47974/61904 [2:18:30<5:22:31,  1.39s/it]
 77%|███████▋  | 47975/61904 [2:18:31<5:21:17,  1.38s/it]
 78%|███████▊  | 47976/61904 [2:18:33<5:18:06,  1.37s/it]
 78%|███████▊  | 47977/61904 [2:18:34<5:27:17,  1.41s/it]
 78%|███████▊  | 47978/61904 [2:18:36<5:36:40,  1.45s/it]
 78%|███████▊  | 47979/61904 [2:18:37<5:23:07,  1.39s/it]
 78%|███████▊  | 47980/61904 [2:18:38<5:23:34,  1.39s/it]
                                                         
{'loss': 2.4933, 'learning_rate': 1.2256579800337092e-07, 'epoch': 12.4}

 78%|███████▊  | 47980/61904 [2:18:38<5:23:34,  1.39s/it]
 78%|███████▊  | 47981/61904 [2:18:40<5:15:24,  1.36s/it]
 78%|███████▊  | 47982/61904 [2:18:41<5:05:25,  1.32s/it]
 78%|███████▊  | 47983/61904 [2:18:42<5:01:50,  1.30s/it]
 78%|███████▊  | 47984/61904 [2:18:44<5:10:26,  1.34s/it]
 78%|███████▊  | 47985/61904 [2:18:45<5:14:44,  1.36s/it]
 78%|███████▊  | 47986/61904 [2:18:46<5:10:47,  1.34s/it]
 78%|███████▊  | 47987/61904 [2:18:48<5:16:43,  1.37s/it]
 78%|███████▊  | 47988/61904 [2:18:49<5:17:24,  1.37s/it]
 78%|███████▊  | 47989/61904 [2:18:50<5:11:56,  1.35s/it]
 78%|███████▊  | 47990/61904 [2:18:52<5:08:31,  1.33s/it]
 78%|███████▊  | 47991/61904 [2:18:53<5:11:47,  1.34s/it]
 78%|███████▊  | 47992/61904 [2:18:54<5:10:06,  1.34s/it]
 78%|███████▊  | 47993/61904 [2:18:56<5:13:06,  1.35s/it]
 78%|███████▊  | 47994/61904 [2:18:57<5:12:34,  1.35s/it]
 78%|███████▊  | 47995/61904 [2:18:58<5:13:28,  1.35s/it]
 78%|███████▊  | 47996/61904 [2:19:00<5:15:03,  1.36s/it]
 78%|███████▊  | 47997/61904 [2:19:01<5:17:34,  1.37s/it]
 78%|███████▊  | 47998/61904 [2:19:03<5:32:53,  1.44s/it]
 78%|███████▊  | 47999/61904 [2:19:04<5:26:17,  1.41s/it]
 78%|███████▊  | 48000/61904 [2:19:05<5:18:06,  1.37s/it]
                                                         
{'loss': 2.4298, 'learning_rate': 1.2253338519382858e-07, 'epoch': 12.41}

 78%|███████▊  | 48000/61904 [2:19:05<5:18:06,  1.37s/it]
 78%|███████▊  | 48001/61904 [2:19:07<5:19:52,  1.38s/it]
 78%|███████▊  | 48002/61904 [2:19:08<5:12:51,  1.35s/it]
 78%|███████▊  | 48003/61904 [2:19:09<5:16:29,  1.37s/it]
 78%|███████▊  | 48004/61904 [2:19:11<5:13:51,  1.35s/it]
 78%|███████▊  | 48005/61904 [2:19:12<5:32:53,  1.44s/it]
 78%|███████▊  | 48006/61904 [2:19:14<5:37:12,  1.46s/it]
 78%|███████▊  | 48007/61904 [2:19:15<5:29:13,  1.42s/it]
 78%|███████▊  | 48008/61904 [2:19:16<5:14:52,  1.36s/it]
 78%|███████▊  | 48009/61904 [2:19:18<5:16:00,  1.36s/it]
 78%|███████▊  | 48010/61904 [2:19:19<5:14:20,  1.36s/it]
 78%|███████▊  | 48011/61904 [2:19:21<5:15:05,  1.36s/it]
 78%|███████▊  | 48012/61904 [2:19:22<5:18:31,  1.38s/it]
 78%|███████▊  | 48013/61904 [2:19:24<5:35:34,  1.45s/it]
 78%|███████▊  | 48014/61904 [2:19:25<5:35:47,  1.45s/it]
 78%|███████▊  | 48015/61904 [2:19:26<5:19:44,  1.38s/it]
 78%|███████▊  | 48016/61904 [2:19:28<5:12:23,  1.35s/it]
 78%|███████▊  | 48017/61904 [2:19:29<5:06:36,  1.32s/it]
 78%|███████▊  | 48018/61904 [2:19:30<5:22:21,  1.39s/it]
 78%|███████▊  | 48019/61904 [2:19:32<5:18:02,  1.37s/it]
 78%|███████▊  | 48020/61904 [2:19:33<5:20:20,  1.38s/it]
                                                         
{'loss': 2.4923, 'learning_rate': 1.2250097238428627e-07, 'epoch': 12.41}

 78%|███████▊  | 48020/61904 [2:19:33<5:20:20,  1.38s/it]
 78%|███████▊  | 48021/61904 [2:19:35<5:25:57,  1.41s/it]
 78%|███████▊  | 48022/61904 [2:19:36<5:29:33,  1.42s/it]
 78%|███████▊  | 48023/61904 [2:19:37<5:19:58,  1.38s/it]
 78%|███████▊  | 48024/61904 [2:19:39<5:27:14,  1.41s/it]
 78%|███████▊  | 48025/61904 [2:19:40<5:28:32,  1.42s/it]
 78%|███████▊  | 48026/61904 [2:19:42<5:35:17,  1.45s/it]
 78%|███████▊  | 48027/61904 [2:19:43<5:21:45,  1.39s/it]
 78%|███████▊  | 48028/61904 [2:19:44<5:22:03,  1.39s/it]
 78%|███████▊  | 48029/61904 [2:19:46<5:13:52,  1.36s/it]
 78%|███████▊  | 48030/61904 [2:19:47<5:17:40,  1.37s/it]
 78%|███████▊  | 48031/61904 [2:19:48<5:09:12,  1.34s/it]
 78%|███████▊  | 48032/61904 [2:19:50<5:14:41,  1.36s/it]
 78%|███████▊  | 48033/61904 [2:19:51<5:19:19,  1.38s/it]
 78%|███████▊  | 48034/61904 [2:19:52<5:10:16,  1.34s/it]
 78%|███████▊  | 48035/61904 [2:19:54<5:22:03,  1.39s/it]
 78%|███████▊  | 48036/61904 [2:19:55<5:08:32,  1.33s/it]
 78%|███████▊  | 48037/61904 [2:19:56<5:07:12,  1.33s/it]
 78%|███████▊  | 48038/61904 [2:19:58<5:06:55,  1.33s/it]
 78%|███████▊  | 48039/61904 [2:19:59<5:09:06,  1.34s/it]
 78%|███████▊  | 48040/61904 [2:20:01<5:11:19,  1.35s/it]
                                                         
{'loss': 2.4368, 'learning_rate': 1.2246855957474393e-07, 'epoch': 12.42}

 78%|███████▊  | 48040/61904 [2:20:01<5:11:19,  1.35s/it]
 78%|███████▊  | 48041/61904 [2:20:02<5:18:36,  1.38s/it]
 78%|███████▊  | 48042/61904 [2:20:03<5:20:31,  1.39s/it]
 78%|███████▊  | 48043/61904 [2:20:05<5:19:06,  1.38s/it]
 78%|███████▊  | 48044/61904 [2:20:06<5:26:06,  1.41s/it]
 78%|███████▊  | 48045/61904 [2:20:08<5:23:00,  1.40s/it]
 78%|███████▊  | 48046/61904 [2:20:09<5:28:44,  1.42s/it]
 78%|███████▊  | 48047/61904 [2:20:10<5:21:22,  1.39s/it]
 78%|███████▊  | 48048/61904 [2:20:12<5:27:40,  1.42s/it]
 78%|███████▊  | 48049/61904 [2:20:13<5:19:01,  1.38s/it]
 78%|███████▊  | 48050/61904 [2:20:15<5:19:05,  1.38s/it]
 78%|███████▊  | 48051/61904 [2:20:16<5:20:13,  1.39s/it]
 78%|███████▊  | 48052/61904 [2:20:17<5:16:14,  1.37s/it]
 78%|███████▊  | 48053/61904 [2:20:19<5:19:15,  1.38s/it]
 78%|███████▊  | 48054/61904 [2:20:20<5:13:57,  1.36s/it]
 78%|███████▊  | 48055/61904 [2:20:21<5:11:24,  1.35s/it]
 78%|███████▊  | 48056/61904 [2:20:23<5:05:45,  1.32s/it]
 78%|███████▊  | 48057/61904 [2:20:24<5:02:26,  1.31s/it]
 78%|███████▊  | 48058/61904 [2:20:25<5:01:52,  1.31s/it]
 78%|███████▊  | 48059/61904 [2:20:27<5:16:38,  1.37s/it]
 78%|███████▊  | 48060/61904 [2:20:28<5:10:20,  1.35s/it]
                                                         
{'loss': 2.4882, 'learning_rate': 1.224361467652016e-07, 'epoch': 12.42}

 78%|███████▊  | 48060/61904 [2:20:28<5:10:20,  1.35s/it]
 78%|███████▊  | 48061/61904 [2:20:29<5:12:39,  1.36s/it]
 78%|███████▊  | 48062/61904 [2:20:31<5:14:36,  1.36s/it]
 78%|███████▊  | 48063/61904 [2:20:32<5:15:30,  1.37s/it]
 78%|███████▊  | 48064/61904 [2:20:34<5:22:43,  1.40s/it]
 78%|███████▊  | 48065/61904 [2:20:35<5:15:41,  1.37s/it]
 78%|███████▊  | 48066/61904 [2:20:36<5:20:24,  1.39s/it]
 78%|███████▊  | 48067/61904 [2:20:38<5:16:56,  1.37s/it]
 78%|███████▊  | 48068/61904 [2:20:39<5:16:45,  1.37s/it]
 78%|███████▊  | 48069/61904 [2:20:40<5:14:07,  1.36s/it]
 78%|███████▊  | 48070/61904 [2:20:42<5:17:21,  1.38s/it]
 78%|███████▊  | 48071/61904 [2:20:43<5:09:22,  1.34s/it]
 78%|███████▊  | 48072/61904 [2:20:44<5:09:51,  1.34s/it]
 78%|███████▊  | 48073/61904 [2:20:46<5:07:46,  1.34s/it]
 78%|███████▊  | 48074/61904 [2:20:47<5:14:01,  1.36s/it]
 78%|███████▊  | 48075/61904 [2:20:48<5:07:25,  1.33s/it]
 78%|███████▊  | 48076/61904 [2:20:50<5:07:25,  1.33s/it]
 78%|███████▊  | 48077/61904 [2:20:51<5:19:52,  1.39s/it]
 78%|███████▊  | 48078/61904 [2:20:53<5:15:37,  1.37s/it]
 78%|███████▊  | 48079/61904 [2:20:54<5:11:22,  1.35s/it]
 78%|███████▊  | 48080/61904 [2:20:55<5:19:48,  1.39s/it]
                                                         
{'loss': 2.4417, 'learning_rate': 1.2240373395565928e-07, 'epoch': 12.43}

 78%|███████▊  | 48080/61904 [2:20:55<5:19:48,  1.39s/it]
 78%|███████▊  | 48081/61904 [2:20:57<5:08:26,  1.34s/it]
 78%|███████▊  | 48082/61904 [2:20:58<5:17:32,  1.38s/it]
 78%|███████▊  | 48083/61904 [2:21:00<5:27:22,  1.42s/it]
 78%|███████▊  | 48084/61904 [2:21:01<5:33:11,  1.45s/it]
 78%|███████▊  | 48085/61904 [2:21:03<5:41:17,  1.48s/it]
 78%|███████▊  | 48086/61904 [2:21:04<5:38:05,  1.47s/it]
 78%|███████▊  | 48087/61904 [2:21:05<5:23:04,  1.40s/it]
 78%|███████▊  | 48088/61904 [2:21:07<5:31:20,  1.44s/it]
 78%|███████▊  | 48089/61904 [2:21:08<5:23:55,  1.41s/it]
 78%|███████▊  | 48090/61904 [2:21:10<5:19:27,  1.39s/it]
 78%|███████▊  | 48091/61904 [2:21:11<5:22:52,  1.40s/it]
 78%|███████▊  | 48092/61904 [2:21:12<5:29:42,  1.43s/it]
 78%|███████▊  | 48093/61904 [2:21:14<5:27:40,  1.42s/it]
 78%|███████▊  | 48094/61904 [2:21:15<5:19:18,  1.39s/it]
 78%|███████▊  | 48095/61904 [2:21:16<5:13:06,  1.36s/it]
 78%|███████▊  | 48096/61904 [2:21:18<5:11:43,  1.35s/it]
 78%|███████▊  | 48097/61904 [2:21:19<5:08:14,  1.34s/it]
 78%|███████▊  | 48098/61904 [2:21:20<5:06:06,  1.33s/it]
 78%|███████▊  | 48099/61904 [2:21:22<5:15:23,  1.37s/it]
 78%|███████▊  | 48100/61904 [2:21:23<5:20:00,  1.39s/it]
                                                         
{'loss': 2.4881, 'learning_rate': 1.2237132114611695e-07, 'epoch': 12.43}

 78%|███████▊  | 48100/61904 [2:21:23<5:20:00,  1.39s/it]
 78%|███████▊  | 48101/61904 [2:21:25<5:20:59,  1.40s/it]
 78%|███████▊  | 48102/61904 [2:21:26<5:14:30,  1.37s/it]
 78%|███████▊  | 48103/61904 [2:21:27<5:15:54,  1.37s/it]
 78%|███████▊  | 48104/61904 [2:21:29<5:15:18,  1.37s/it]
 78%|███████▊  | 48105/61904 [2:21:30<5:19:38,  1.39s/it]
 78%|███████▊  | 48106/61904 [2:21:31<5:08:10,  1.34s/it]
 78%|███████▊  | 48107/61904 [2:21:33<5:14:52,  1.37s/it]
 78%|███████▊  | 48108/61904 [2:21:34<5:16:19,  1.38s/it]
 78%|███████▊  | 48109/61904 [2:21:36<5:25:57,  1.42s/it]
 78%|███████▊  | 48110/61904 [2:21:37<5:25:15,  1.41s/it]
 78%|███████▊  | 48111/61904 [2:21:39<5:18:44,  1.39s/it]
 78%|███████▊  | 48112/61904 [2:21:40<5:15:55,  1.37s/it]
 78%|███████▊  | 48113/61904 [2:21:41<5:24:22,  1.41s/it]
 78%|███████▊  | 48114/61904 [2:21:43<5:27:54,  1.43s/it]
 78%|███████▊  | 48115/61904 [2:21:44<5:29:23,  1.43s/it]
 78%|███████▊  | 48116/61904 [2:21:46<5:22:13,  1.40s/it]
 78%|███████▊  | 48117/61904 [2:21:47<5:15:41,  1.37s/it]
 78%|███████▊  | 48118/61904 [2:21:48<5:12:36,  1.36s/it]
 78%|███████▊  | 48119/61904 [2:21:50<5:21:51,  1.40s/it]
 78%|███████▊  | 48120/61904 [2:21:51<5:16:33,  1.38s/it]
                                                         
{'loss': 2.4633, 'learning_rate': 1.223389083365746e-07, 'epoch': 12.44}

 78%|███████▊  | 48120/61904 [2:21:51<5:16:33,  1.38s/it]
 78%|███████▊  | 48121/61904 [2:21:53<5:23:47,  1.41s/it]
 78%|███████▊  | 48122/61904 [2:21:54<5:20:58,  1.40s/it]
 78%|███████▊  | 48123/61904 [2:21:55<5:23:36,  1.41s/it]
 78%|███████▊  | 48124/61904 [2:21:57<5:18:03,  1.38s/it]
 78%|███████▊  | 48125/61904 [2:21:58<5:09:11,  1.35s/it]
 78%|███████▊  | 48126/61904 [2:21:59<5:13:52,  1.37s/it]
 78%|███████▊  | 48127/61904 [2:22:01<5:13:06,  1.36s/it]
 78%|███████▊  | 48128/61904 [2:22:02<5:19:13,  1.39s/it]
 78%|███████▊  | 48129/61904 [2:22:04<5:32:43,  1.45s/it]
 78%|███████▊  | 48130/61904 [2:22:05<5:39:39,  1.48s/it]
 78%|███████▊  | 48131/61904 [2:22:07<5:28:00,  1.43s/it]
 78%|███████▊  | 48132/61904 [2:22:08<5:29:56,  1.44s/it]
 78%|███████▊  | 48133/61904 [2:22:09<5:26:08,  1.42s/it]
 78%|███████▊  | 48134/61904 [2:22:11<5:32:36,  1.45s/it]
 78%|███████▊  | 48135/61904 [2:22:12<5:31:39,  1.45s/it]
 78%|███████▊  | 48136/61904 [2:22:14<5:39:50,  1.48s/it]
 78%|███████▊  | 48137/61904 [2:22:15<5:34:04,  1.46s/it]
 78%|███████▊  | 48138/61904 [2:22:17<5:23:20,  1.41s/it]
 78%|███████▊  | 48139/61904 [2:22:18<5:12:27,  1.36s/it]
 78%|███████▊  | 48140/61904 [2:22:19<5:03:27,  1.32s/it]
                                                         
{'loss': 2.4914, 'learning_rate': 1.223064955270323e-07, 'epoch': 12.44}

 78%|███████▊  | 48140/61904 [2:22:19<5:03:27,  1.32s/it]
 78%|███████▊  | 48141/61904 [2:22:21<5:22:19,  1.41s/it]
 78%|███████▊  | 48142/61904 [2:22:22<5:10:02,  1.35s/it]
 78%|███████▊  | 48143/61904 [2:22:23<4:58:54,  1.30s/it]
 78%|███████▊  | 48144/61904 [2:22:25<5:01:18,  1.31s/it]
 78%|███████▊  | 48145/61904 [2:22:26<5:00:24,  1.31s/it]
 78%|███████▊  | 48146/61904 [2:22:27<5:03:34,  1.32s/it]
 78%|███████▊  | 48147/61904 [2:22:29<5:06:10,  1.34s/it]
 78%|███████▊  | 48148/61904 [2:22:30<5:04:07,  1.33s/it]
 78%|███████▊  | 48149/61904 [2:22:31<5:04:44,  1.33s/it]
 78%|███████▊  | 48150/61904 [2:22:33<5:07:51,  1.34s/it]
 78%|███████▊  | 48151/61904 [2:22:34<5:05:47,  1.33s/it]
 78%|███████▊  | 48152/61904 [2:22:35<5:05:01,  1.33s/it]
 78%|███████▊  | 48153/61904 [2:22:37<5:05:36,  1.33s/it]
 78%|███████▊  | 48154/61904 [2:22:38<5:08:10,  1.34s/it]
 78%|███████▊  | 48155/61904 [2:22:39<5:16:12,  1.38s/it]
 78%|███████▊  | 48156/61904 [2:22:41<5:18:12,  1.39s/it]
 78%|███████▊  | 48157/61904 [2:22:42<5:13:22,  1.37s/it]
 78%|███████▊  | 48158/61904 [2:22:43<5:12:25,  1.36s/it]
 78%|███████▊  | 48159/61904 [2:22:45<5:03:54,  1.33s/it]
 78%|███████▊  | 48160/61904 [2:22:46<5:05:50,  1.34s/it]
                                                         
{'loss': 2.4236, 'learning_rate': 1.2227408271748993e-07, 'epoch': 12.45}

 78%|███████▊  | 48160/61904 [2:22:46<5:05:50,  1.34s/it]
 78%|███████▊  | 48161/61904 [2:22:47<5:10:10,  1.35s/it]
 78%|███████▊  | 48162/61904 [2:22:49<5:13:56,  1.37s/it]
 78%|███████▊  | 48163/61904 [2:22:50<5:24:19,  1.42s/it]
 78%|███████▊  | 48164/61904 [2:22:52<5:20:25,  1.40s/it]
 78%|███████▊  | 48165/61904 [2:22:53<5:13:46,  1.37s/it]
 78%|███████▊  | 48166/61904 [2:22:54<5:06:50,  1.34s/it]
 78%|███████▊  | 48167/61904 [2:22:55<4:56:29,  1.29s/it]
 78%|███████▊  | 48168/61904 [2:22:57<4:56:57,  1.30s/it]
 78%|███████▊  | 48169/61904 [2:22:58<5:03:34,  1.33s/it]
 78%|███████▊  | 48170/61904 [2:23:00<5:03:37,  1.33s/it]
 78%|███████▊  | 48171/61904 [2:23:01<5:05:01,  1.33s/it]
 78%|███████▊  | 48172/61904 [2:23:02<5:11:54,  1.36s/it]
 78%|███████▊  | 48173/61904 [2:23:04<5:10:55,  1.36s/it]
 78%|███████▊  | 48174/61904 [2:23:05<5:25:40,  1.42s/it]
 78%|███████▊  | 48175/61904 [2:23:07<5:25:08,  1.42s/it]
 78%|███████▊  | 48176/61904 [2:23:08<5:21:22,  1.40s/it]
 78%|███████▊  | 48177/61904 [2:23:09<5:17:32,  1.39s/it]
 78%|███████▊  | 48178/61904 [2:23:11<5:18:45,  1.39s/it]
 78%|███████▊  | 48179/61904 [2:23:12<5:10:43,  1.36s/it]
 78%|███████▊  | 48180/61904 [2:23:13<5:14:56,  1.38s/it]
                                                         
{'loss': 2.4603, 'learning_rate': 1.2224166990794762e-07, 'epoch': 12.45}

 78%|███████▊  | 48180/61904 [2:23:13<5:14:56,  1.38s/it]
 78%|███████▊  | 48181/61904 [2:23:15<5:09:05,  1.35s/it]
 78%|███████▊  | 48182/61904 [2:23:16<5:06:37,  1.34s/it]
 78%|███████▊  | 48183/61904 [2:23:17<5:12:28,  1.37s/it]
 78%|███████▊  | 48184/61904 [2:23:19<5:11:02,  1.36s/it]
 78%|███████▊  | 48185/61904 [2:23:20<5:03:24,  1.33s/it]
 78%|███████▊  | 48186/61904 [2:23:21<5:03:44,  1.33s/it]
 78%|███████▊  | 48187/61904 [2:23:23<5:07:02,  1.34s/it]
 78%|███████▊  | 48188/61904 [2:23:24<5:11:00,  1.36s/it]
 78%|███████▊  | 48189/61904 [2:23:26<5:09:11,  1.35s/it]
 78%|███████▊  | 48190/61904 [2:23:27<5:20:35,  1.40s/it]
 78%|███████▊  | 48191/61904 [2:23:28<5:14:11,  1.37s/it]
 78%|███████▊  | 48192/61904 [2:23:30<5:07:30,  1.35s/it]
 78%|███████▊  | 48193/61904 [2:23:31<5:04:51,  1.33s/it]
 78%|███████▊  | 48194/61904 [2:23:32<5:11:01,  1.36s/it]
 78%|███████▊  | 48195/61904 [2:23:34<5:13:39,  1.37s/it]
 78%|███████▊  | 48196/61904 [2:23:35<5:17:14,  1.39s/it]
 78%|███████▊  | 48197/61904 [2:23:37<5:21:42,  1.41s/it]
 78%|███████▊  | 48198/61904 [2:23:38<5:12:07,  1.37s/it]
 78%|███████▊  | 48199/61904 [2:23:39<5:14:26,  1.38s/it]
 78%|███████▊  | 48200/61904 [2:23:41<5:16:37,  1.39s/it]
                                                         
{'loss': 2.5019, 'learning_rate': 1.2220925709840528e-07, 'epoch': 12.46}

 78%|███████▊  | 48200/61904 [2:23:41<5:16:37,  1.39s/it]
 78%|███████▊  | 48201/61904 [2:23:42<5:23:39,  1.42s/it]
 78%|███████▊  | 48202/61904 [2:23:44<5:16:49,  1.39s/it]
 78%|███████▊  | 48203/61904 [2:23:45<5:16:49,  1.39s/it]
 78%|███████▊  | 48204/61904 [2:23:46<5:09:06,  1.35s/it]
 78%|███████▊  | 48205/61904 [2:23:48<5:18:01,  1.39s/it]
 78%|███████▊  | 48206/61904 [2:23:49<5:15:43,  1.38s/it]
 78%|███████▊  | 48207/61904 [2:23:50<5:21:26,  1.41s/it]
 78%|███████▊  | 48208/61904 [2:23:52<5:19:44,  1.40s/it]
 78%|███████▊  | 48209/61904 [2:23:53<5:29:18,  1.44s/it]
 78%|███████▊  | 48210/61904 [2:23:55<5:22:31,  1.41s/it]
 78%|███████▊  | 48211/61904 [2:23:56<5:12:48,  1.37s/it]
 78%|███████▊  | 48212/61904 [2:23:57<5:17:52,  1.39s/it]
 78%|███████▊  | 48213/61904 [2:23:59<5:19:59,  1.40s/it]
 78%|███████▊  | 48214/61904 [2:24:00<5:13:02,  1.37s/it]
 78%|███████▊  | 48215/61904 [2:24:01<5:04:54,  1.34s/it]
 78%|███████▊  | 48216/61904 [2:24:03<5:01:03,  1.32s/it]
 78%|███████▊  | 48217/61904 [2:24:04<5:04:02,  1.33s/it]
 78%|███████▊  | 48218/61904 [2:24:05<5:03:20,  1.33s/it]
 78%|███████▊  | 48219/61904 [2:24:07<5:15:18,  1.38s/it]
 78%|███████▊  | 48220/61904 [2:24:08<5:19:03,  1.40s/it]
                                                         
{'loss': 2.4368, 'learning_rate': 1.2217684428886294e-07, 'epoch': 12.46}

 78%|███████▊  | 48220/61904 [2:24:08<5:19:03,  1.40s/it]
 78%|███████▊  | 48221/61904 [2:24:10<5:11:04,  1.36s/it]
 78%|███████▊  | 48222/61904 [2:24:11<5:16:14,  1.39s/it]
 78%|███████▊  | 48223/61904 [2:24:12<5:15:03,  1.38s/it]
 78%|███████▊  | 48224/61904 [2:24:14<5:20:49,  1.41s/it]
 78%|███████▊  | 48225/61904 [2:24:15<5:19:05,  1.40s/it]
 78%|███████▊  | 48226/61904 [2:24:17<5:20:51,  1.41s/it]
 78%|███████▊  | 48227/61904 [2:24:18<5:19:42,  1.40s/it]
 78%|███████▊  | 48228/61904 [2:24:20<5:22:26,  1.41s/it]
 78%|███████▊  | 48229/61904 [2:24:21<5:13:43,  1.38s/it]
 78%|███████▊  | 48230/61904 [2:24:22<5:12:28,  1.37s/it]
 78%|███████▊  | 48231/61904 [2:24:24<5:15:21,  1.38s/it]
 78%|███████▊  | 48232/61904 [2:24:25<5:11:30,  1.37s/it]
 78%|███████▊  | 48233/61904 [2:24:26<5:14:35,  1.38s/it]
 78%|███████▊  | 48234/61904 [2:24:28<5:19:14,  1.40s/it]
 78%|███████▊  | 48235/61904 [2:24:29<5:19:08,  1.40s/it]
 78%|███████▊  | 48236/61904 [2:24:31<5:22:09,  1.41s/it]
 78%|███████▊  | 48237/61904 [2:24:32<5:20:19,  1.41s/it]
 78%|███████▊  | 48238/61904 [2:24:33<5:15:28,  1.39s/it]
 78%|███████▊  | 48239/61904 [2:24:35<5:13:59,  1.38s/it]
 78%|███████▊  | 48240/61904 [2:24:36<5:14:00,  1.38s/it]
                                                         
{'loss': 2.5019, 'learning_rate': 1.2214443147932063e-07, 'epoch': 12.47}

 78%|███████▊  | 48240/61904 [2:24:36<5:14:00,  1.38s/it]
 78%|███████▊  | 48241/61904 [2:24:37<5:12:34,  1.37s/it]
 78%|███████▊  | 48242/61904 [2:24:39<5:15:19,  1.38s/it]
 78%|███████▊  | 48243/61904 [2:24:40<5:06:05,  1.34s/it]
 78%|███████▊  | 48244/61904 [2:24:41<5:06:12,  1.34s/it]
 78%|███████▊  | 48245/61904 [2:24:43<5:07:40,  1.35s/it]
 78%|███████▊  | 48246/61904 [2:24:44<5:15:28,  1.39s/it]
 78%|███████▊  | 48247/61904 [2:24:46<5:18:13,  1.40s/it]
 78%|███████▊  | 48248/61904 [2:24:47<5:10:06,  1.36s/it]
 78%|███████▊  | 48249/61904 [2:24:49<5:28:30,  1.44s/it]
 78%|███████▊  | 48250/61904 [2:24:50<5:21:43,  1.41s/it]
 78%|███████▊  | 48251/61904 [2:24:52<5:27:17,  1.44s/it]
 78%|███████▊  | 48252/61904 [2:24:53<5:17:44,  1.40s/it]
 78%|███████▊  | 48253/61904 [2:24:54<5:22:20,  1.42s/it]
 78%|███████▊  | 48254/61904 [2:24:56<5:16:18,  1.39s/it]
 78%|███████▊  | 48255/61904 [2:24:57<5:12:59,  1.38s/it]
 78%|███████▊  | 48256/61904 [2:24:58<5:05:34,  1.34s/it]
 78%|███████▊  | 48257/61904 [2:25:00<5:18:23,  1.40s/it]
 78%|███████▊  | 48258/61904 [2:25:01<5:12:51,  1.38s/it]
 78%|███████▊  | 48259/61904 [2:25:02<5:11:13,  1.37s/it]
 78%|███████▊  | 48260/61904 [2:25:04<5:11:11,  1.37s/it]
                                                         
{'loss': 2.4857, 'learning_rate': 1.221120186697783e-07, 'epoch': 12.47}

 78%|███████▊  | 48260/61904 [2:25:04<5:11:11,  1.37s/it]
 78%|███████▊  | 48261/61904 [2:25:05<5:13:25,  1.38s/it]
 78%|███████▊  | 48262/61904 [2:25:07<5:12:04,  1.37s/it]
 78%|███████▊  | 48263/61904 [2:25:08<5:06:01,  1.35s/it]
 78%|███████▊  | 48264/61904 [2:25:09<5:00:58,  1.32s/it]
 78%|███████▊  | 48265/61904 [2:25:10<5:03:46,  1.34s/it]
 78%|███████▊  | 48266/61904 [2:25:12<5:02:03,  1.33s/it]
 78%|███████▊  | 48267/61904 [2:25:13<5:05:01,  1.34s/it]
 78%|███████▊  | 48268/61904 [2:25:14<4:58:32,  1.31s/it]
 78%|███████▊  | 48269/61904 [2:25:16<4:53:44,  1.29s/it]
 78%|███████▊  | 48270/61904 [2:25:17<5:01:40,  1.33s/it]
 78%|███████▊  | 48271/61904 [2:25:18<5:04:40,  1.34s/it]
 78%|███████▊  | 48272/61904 [2:25:20<5:17:30,  1.40s/it]
 78%|███████▊  | 48273/61904 [2:25:21<5:19:52,  1.41s/it]
 78%|███████▊  | 48274/61904 [2:25:23<5:26:58,  1.44s/it]
 78%|███████▊  | 48275/61904 [2:25:24<5:28:17,  1.45s/it]
 78%|███████▊  | 48276/61904 [2:25:26<5:22:27,  1.42s/it]
 78%|███████▊  | 48277/61904 [2:25:27<5:18:49,  1.40s/it]
 78%|███████▊  | 48278/61904 [2:25:28<5:12:50,  1.38s/it]
 78%|███████▊  | 48279/61904 [2:25:30<5:05:51,  1.35s/it]
 78%|███████▊  | 48280/61904 [2:25:31<5:05:56,  1.35s/it]
                                                         
{'loss': 2.4496, 'learning_rate': 1.2207960586023596e-07, 'epoch': 12.48}

 78%|███████▊  | 48280/61904 [2:25:31<5:05:56,  1.35s/it]
 78%|███████▊  | 48281/61904 [2:25:32<4:58:06,  1.31s/it]
 78%|███████▊  | 48282/61904 [2:25:34<5:01:33,  1.33s/it]
 78%|███████▊  | 48283/61904 [2:25:35<4:58:58,  1.32s/it]
 78%|███████▊  | 48284/61904 [2:25:36<4:59:22,  1.32s/it]
 78%|███████▊  | 48285/61904 [2:25:38<5:24:15,  1.43s/it]
 78%|███████▊  | 48286/61904 [2:25:39<5:17:31,  1.40s/it]
 78%|███████▊  | 48287/61904 [2:25:41<5:18:50,  1.40s/it]
 78%|███████▊  | 48288/61904 [2:25:42<5:05:46,  1.35s/it]
 78%|███████▊  | 48289/61904 [2:25:43<5:00:20,  1.32s/it]
 78%|███████▊  | 48290/61904 [2:25:44<4:57:23,  1.31s/it]
 78%|███████▊  | 48291/61904 [2:25:46<4:56:23,  1.31s/it]
 78%|███████▊  | 48292/61904 [2:25:47<5:01:41,  1.33s/it]
 78%|███████▊  | 48293/61904 [2:25:49<5:16:11,  1.39s/it]
 78%|███████▊  | 48294/61904 [2:25:50<5:14:55,  1.39s/it]
 78%|███████▊  | 48295/61904 [2:25:52<5:21:18,  1.42s/it]
 78%|███████▊  | 48296/61904 [2:25:53<5:22:17,  1.42s/it]
 78%|███████▊  | 48297/61904 [2:25:54<5:22:08,  1.42s/it]
 78%|███████▊  | 48298/61904 [2:25:56<5:16:15,  1.39s/it]
 78%|███████▊  | 48299/61904 [2:25:57<5:14:48,  1.39s/it]
 78%|███████▊  | 48300/61904 [2:25:59<5:29:38,  1.45s/it]
                                                         
{'loss': 2.5045, 'learning_rate': 1.2204719305069364e-07, 'epoch': 12.48}

 78%|███████▊  | 48300/61904 [2:25:59<5:29:38,  1.45s/it]
 78%|███████▊  | 48301/61904 [2:26:00<5:32:29,  1.47s/it]
 78%|███████▊  | 48302/61904 [2:26:02<5:25:08,  1.43s/it]
 78%|███████▊  | 48303/61904 [2:26:03<5:20:48,  1.42s/it]
 78%|███████▊  | 48304/61904 [2:26:04<5:28:43,  1.45s/it]
 78%|███████▊  | 48305/61904 [2:26:06<5:31:14,  1.46s/it]
 78%|███████▊  | 48306/61904 [2:26:07<5:32:17,  1.47s/it]
 78%|███████▊  | 48307/61904 [2:26:09<5:28:01,  1.45s/it]
 78%|███████▊  | 48308/61904 [2:26:10<5:25:56,  1.44s/it]
 78%|███████▊  | 48309/61904 [2:26:12<5:26:31,  1.44s/it]
 78%|███████▊  | 48310/61904 [2:26:13<5:24:44,  1.43s/it]
 78%|███████▊  | 48311/61904 [2:26:14<5:23:40,  1.43s/it]
 78%|███████▊  | 48312/61904 [2:26:16<5:15:39,  1.39s/it]
 78%|███████▊  | 48313/61904 [2:26:17<5:19:54,  1.41s/it]
 78%|███████▊  | 48314/61904 [2:26:19<5:18:26,  1.41s/it]
 78%|███████▊  | 48315/61904 [2:26:20<5:08:21,  1.36s/it]
 78%|███████▊  | 48316/61904 [2:26:21<5:07:02,  1.36s/it]
 78%|███████▊  | 48317/61904 [2:26:23<5:14:38,  1.39s/it]
 78%|███████▊  | 48318/61904 [2:26:24<5:08:36,  1.36s/it]
 78%|███████▊  | 48319/61904 [2:26:25<5:09:51,  1.37s/it]
 78%|███████▊  | 48320/61904 [2:26:27<5:05:37,  1.35s/it]
                                                         
{'loss': 2.4589, 'learning_rate': 1.2201478024115128e-07, 'epoch': 12.49}

 78%|███████▊  | 48320/61904 [2:26:27<5:05:37,  1.35s/it]
 78%|███████▊  | 48321/61904 [2:26:28<4:59:26,  1.32s/it]
 78%|███████▊  | 48322/61904 [2:26:29<4:58:49,  1.32s/it]
 78%|███████▊  | 48323/61904 [2:26:31<4:58:34,  1.32s/it]
 78%|███████▊  | 48324/61904 [2:26:32<5:09:23,  1.37s/it]
 78%|███████▊  | 48325/61904 [2:26:34<5:14:56,  1.39s/it]
 78%|███████▊  | 48326/61904 [2:26:35<5:08:10,  1.36s/it]
 78%|███████▊  | 48327/61904 [2:26:36<5:18:55,  1.41s/it]
 78%|███████▊  | 48328/61904 [2:26:38<5:13:37,  1.39s/it]
 78%|███████▊  | 48329/61904 [2:26:39<5:26:19,  1.44s/it]
 78%|███████▊  | 48330/61904 [2:26:41<5:38:36,  1.50s/it]
 78%|███████▊  | 48331/61904 [2:26:42<5:30:52,  1.46s/it]
 78%|███████▊  | 48332/61904 [2:26:44<5:21:03,  1.42s/it]
 78%|███████▊  | 48333/61904 [2:26:45<5:26:10,  1.44s/it]
 78%|███████▊  | 48334/61904 [2:26:46<5:15:27,  1.39s/it]
 78%|███████▊  | 48335/61904 [2:26:48<5:08:01,  1.36s/it]
 78%|███████▊  | 48336/61904 [2:26:49<5:07:36,  1.36s/it]
 78%|███████▊  | 48337/61904 [2:26:50<5:08:19,  1.36s/it]
 78%|███████▊  | 48338/61904 [2:26:52<5:03:50,  1.34s/it]
 78%|███████▊  | 48339/61904 [2:26:53<5:10:54,  1.38s/it]
 78%|███████▊  | 48340/61904 [2:26:54<5:10:40,  1.37s/it]
                                                         
{'loss': 2.4778, 'learning_rate': 1.2198236743160897e-07, 'epoch': 12.49}

 78%|███████▊  | 48340/61904 [2:26:54<5:10:40,  1.37s/it]
 78%|███████▊  | 48341/61904 [2:26:56<5:11:32,  1.38s/it]
 78%|███████▊  | 48342/61904 [2:26:57<5:09:10,  1.37s/it]
 78%|███████▊  | 48343/61904 [2:26:59<5:07:28,  1.36s/it]
 78%|███████▊  | 48344/61904 [2:27:00<5:02:58,  1.34s/it]
 78%|███████▊  | 48345/61904 [2:27:01<5:07:11,  1.36s/it]
 78%|███████▊  | 48346/61904 [2:27:03<5:13:53,  1.39s/it]
 78%|███████▊  | 48347/61904 [2:27:04<5:01:38,  1.33s/it]
 78%|███████▊  | 48348/61904 [2:27:05<5:09:55,  1.37s/it]
 78%|███████▊  | 48349/61904 [2:27:07<5:08:55,  1.37s/it]
 78%|███████▊  | 48350/61904 [2:27:08<5:27:11,  1.45s/it]
 78%|███████▊  | 48351/61904 [2:27:10<5:18:26,  1.41s/it]
 78%|███████▊  | 48352/61904 [2:27:11<5:14:40,  1.39s/it]
 78%|███████▊  | 48353/61904 [2:27:12<5:11:50,  1.38s/it]
 78%|███████▊  | 48354/61904 [2:27:14<5:15:16,  1.40s/it]
 78%|███████▊  | 48355/61904 [2:27:15<5:12:50,  1.39s/it]
 78%|███████▊  | 48356/61904 [2:27:16<5:06:34,  1.36s/it]
 78%|███████▊  | 48357/61904 [2:27:18<5:04:34,  1.35s/it]
 78%|███████▊  | 48358/61904 [2:27:19<5:11:17,  1.38s/it]
 78%|███████▊  | 48359/61904 [2:27:21<5:15:31,  1.40s/it]
 78%|███████▊  | 48360/61904 [2:27:22<5:13:45,  1.39s/it]
                                                         
{'loss': 2.4297, 'learning_rate': 1.2194995462206663e-07, 'epoch': 12.5}

 78%|███████▊  | 48360/61904 [2:27:22<5:13:45,  1.39s/it]
 78%|███████▊  | 48361/61904 [2:27:23<5:06:21,  1.36s/it]
 78%|███████▊  | 48362/61904 [2:27:25<5:10:25,  1.38s/it]
 78%|███████▊  | 48363/61904 [2:27:26<5:02:23,  1.34s/it]
 78%|███████▊  | 48364/61904 [2:27:27<4:59:16,  1.33s/it]
 78%|███████▊  | 48365/61904 [2:27:29<5:10:33,  1.38s/it]
 78%|███████▊  | 48366/61904 [2:27:30<5:15:58,  1.40s/it]
 78%|███████▊  | 48367/61904 [2:27:32<5:11:31,  1.38s/it]
 78%|███████▊  | 48368/61904 [2:27:33<5:09:53,  1.37s/it]
 78%|███████▊  | 48369/61904 [2:27:34<5:15:35,  1.40s/it]
 78%|███████▊  | 48370/61904 [2:27:36<5:08:52,  1.37s/it]
 78%|███████▊  | 48371/61904 [2:27:37<5:16:38,  1.40s/it]
 78%|███████▊  | 48372/61904 [2:27:39<5:10:01,  1.37s/it]
 78%|███████▊  | 48373/61904 [2:27:40<5:03:11,  1.34s/it]
 78%|███████▊  | 48374/61904 [2:27:41<5:08:40,  1.37s/it]
 78%|███████▊  | 48375/61904 [2:27:43<5:03:32,  1.35s/it]
 78%|███████▊  | 48376/61904 [2:27:44<5:11:22,  1.38s/it]
 78%|███████▊  | 48377/61904 [2:27:45<5:07:53,  1.37s/it]
 78%|███████▊  | 48378/61904 [2:27:47<4:58:42,  1.33s/it]
 78%|███████▊  | 48379/61904 [2:27:48<4:55:06,  1.31s/it]
 78%|███████▊  | 48380/61904 [2:27:49<5:06:57,  1.36s/it]
                                                         
{'loss': 2.395, 'learning_rate': 1.219175418125243e-07, 'epoch': 12.5}

 78%|███████▊  | 48380/61904 [2:27:49<5:06:57,  1.36s/it]
 78%|███████▊  | 48381/61904 [2:27:51<5:03:01,  1.34s/it]
 78%|███████▊  | 48382/61904 [2:27:52<5:02:28,  1.34s/it]
 78%|███████▊  | 48383/61904 [2:27:53<5:08:02,  1.37s/it]
 78%|███████▊  | 48384/61904 [2:27:55<5:14:33,  1.40s/it]
 78%|███████▊  | 48385/61904 [2:27:56<5:17:06,  1.41s/it]
 78%|███████▊  | 48386/61904 [2:27:58<5:13:22,  1.39s/it]
 78%|███████▊  | 48387/61904 [2:27:59<5:04:44,  1.35s/it]
 78%|███████▊  | 48388/61904 [2:28:00<5:06:43,  1.36s/it]
 78%|███████▊  | 48389/61904 [2:28:02<5:07:54,  1.37s/it]
 78%|███████▊  | 48390/61904 [2:28:03<5:10:49,  1.38s/it]
 78%|███████▊  | 48391/61904 [2:28:04<5:07:51,  1.37s/it]
 78%|███████▊  | 48392/61904 [2:28:06<5:08:52,  1.37s/it]
 78%|███████▊  | 48393/61904 [2:28:07<5:05:21,  1.36s/it]
 78%|███████▊  | 48394/61904 [2:28:09<5:12:03,  1.39s/it]
 78%|███████▊  | 48395/61904 [2:28:10<5:07:29,  1.37s/it]
 78%|███████▊  | 48396/61904 [2:28:11<5:14:27,  1.40s/it]
 78%|███████▊  | 48397/61904 [2:28:13<5:21:09,  1.43s/it]
 78%|███████▊  | 48398/61904 [2:28:14<5:18:54,  1.42s/it]
 78%|███████▊  | 48399/61904 [2:28:16<5:15:40,  1.40s/it]
 78%|███████▊  | 48400/61904 [2:28:17<5:13:55,  1.39s/it]
                                                         
{'loss': 2.4515, 'learning_rate': 1.2188512900298198e-07, 'epoch': 12.51}

 78%|███████▊  | 48400/61904 [2:28:17<5:13:55,  1.39s/it]
 78%|███████▊  | 48401/61904 [2:28:18<5:10:38,  1.38s/it]
 78%|███████▊  | 48402/61904 [2:28:20<5:12:10,  1.39s/it]
 78%|███████▊  | 48403/61904 [2:28:21<5:05:20,  1.36s/it]
 78%|███████▊  | 48404/61904 [2:28:22<5:06:18,  1.36s/it]
 78%|███████▊  | 48405/61904 [2:28:24<5:11:56,  1.39s/it]
 78%|███████▊  | 48406/61904 [2:28:25<5:05:31,  1.36s/it]
 78%|███████▊  | 48407/61904 [2:28:26<5:05:38,  1.36s/it]
 78%|███████▊  | 48408/61904 [2:28:28<5:06:01,  1.36s/it]
 78%|███████▊  | 48409/61904 [2:28:29<5:02:08,  1.34s/it]
 78%|███████▊  | 48410/61904 [2:28:30<5:01:44,  1.34s/it]
 78%|███████▊  | 48411/61904 [2:28:32<5:04:15,  1.35s/it]
 78%|███████▊  | 48412/61904 [2:28:33<5:10:35,  1.38s/it]
 78%|███████▊  | 48413/61904 [2:28:35<5:11:08,  1.38s/it]
 78%|███████▊  | 48414/61904 [2:28:36<5:13:32,  1.39s/it]
 78%|███████▊  | 48415/61904 [2:28:37<5:13:00,  1.39s/it]
 78%|███████▊  | 48416/61904 [2:28:39<5:19:48,  1.42s/it]
 78%|███████▊  | 48417/61904 [2:28:40<5:25:20,  1.45s/it]
 78%|███████▊  | 48418/61904 [2:28:42<5:42:57,  1.53s/it]
 78%|███████▊  | 48419/61904 [2:28:44<5:31:57,  1.48s/it]
 78%|███████▊  | 48420/61904 [2:28:45<5:22:51,  1.44s/it]
                                                         
{'loss': 2.4912, 'learning_rate': 1.2185271619343964e-07, 'epoch': 12.51}

 78%|███████▊  | 48420/61904 [2:28:45<5:22:51,  1.44s/it]
 78%|███████▊  | 48421/61904 [2:28:47<5:35:43,  1.49s/it]
 78%|███████▊  | 48422/61904 [2:28:48<5:34:37,  1.49s/it]
 78%|███████▊  | 48423/61904 [2:28:49<5:33:14,  1.48s/it]
 78%|███████▊  | 48424/61904 [2:28:51<5:18:47,  1.42s/it]
 78%|███████▊  | 48425/61904 [2:28:52<5:17:35,  1.41s/it]
 78%|███████▊  | 48426/61904 [2:28:54<5:30:07,  1.47s/it]
 78%|███████▊  | 48427/61904 [2:28:55<5:25:33,  1.45s/it]
 78%|███████▊  | 48428/61904 [2:28:57<5:18:36,  1.42s/it]
 78%|███████▊  | 48429/61904 [2:28:58<5:17:48,  1.42s/it]
 78%|███████▊  | 48430/61904 [2:28:59<5:28:46,  1.46s/it]
 78%|███████▊  | 48431/61904 [2:29:01<5:11:13,  1.39s/it]
 78%|███████▊  | 48432/61904 [2:29:02<5:12:00,  1.39s/it]
 78%|███████▊  | 48433/61904 [2:29:04<5:18:07,  1.42s/it]
 78%|███████▊  | 48434/61904 [2:29:05<5:07:50,  1.37s/it]
 78%|███████▊  | 48435/61904 [2:29:06<5:00:19,  1.34s/it]
 78%|███████▊  | 48436/61904 [2:29:08<5:14:57,  1.40s/it]
 78%|███████▊  | 48437/61904 [2:29:09<5:20:17,  1.43s/it]
 78%|███████▊  | 48438/61904 [2:29:10<5:14:49,  1.40s/it]
 78%|███████▊  | 48439/61904 [2:29:12<5:10:48,  1.38s/it]
 78%|███████▊  | 48440/61904 [2:29:13<5:15:32,  1.41s/it]
                                                         
{'loss': 2.4681, 'learning_rate': 1.218203033838973e-07, 'epoch': 12.52}

 78%|███████▊  | 48440/61904 [2:29:13<5:15:32,  1.41s/it]
 78%|███████▊  | 48441/61904 [2:29:15<5:21:36,  1.43s/it]
 78%|███████▊  | 48442/61904 [2:29:16<5:27:59,  1.46s/it]
 78%|███████▊  | 48443/61904 [2:29:18<5:18:32,  1.42s/it]
 78%|███████▊  | 48444/61904 [2:29:19<5:11:20,  1.39s/it]
 78%|███████▊  | 48445/61904 [2:29:20<5:03:02,  1.35s/it]
 78%|███████▊  | 48446/61904 [2:29:21<4:58:18,  1.33s/it]
 78%|███████▊  | 48447/61904 [2:29:23<5:06:29,  1.37s/it]
 78%|███████▊  | 48448/61904 [2:29:24<5:07:47,  1.37s/it]
 78%|███████▊  | 48449/61904 [2:29:26<5:07:15,  1.37s/it]
 78%|███████▊  | 48450/61904 [2:29:27<5:09:14,  1.38s/it]
 78%|███████▊  | 48451/61904 [2:29:28<5:10:20,  1.38s/it]
 78%|███████▊  | 48452/61904 [2:29:30<5:03:35,  1.35s/it]
 78%|███████▊  | 48453/61904 [2:29:31<5:06:04,  1.37s/it]
 78%|███████▊  | 48454/61904 [2:29:33<5:11:39,  1.39s/it]
 78%|███████▊  | 48455/61904 [2:29:34<5:17:43,  1.42s/it]
 78%|███████▊  | 48456/61904 [2:29:35<5:14:44,  1.40s/it]
 78%|███████▊  | 48457/61904 [2:29:37<5:10:49,  1.39s/it]
 78%|███████▊  | 48458/61904 [2:29:38<5:11:11,  1.39s/it]
 78%|███████▊  | 48459/61904 [2:29:40<5:16:27,  1.41s/it]
 78%|███████▊  | 48460/61904 [2:29:41<5:16:51,  1.41s/it]
                                                         
{'loss': 2.4598, 'learning_rate': 1.21787890574355e-07, 'epoch': 12.53}

 78%|███████▊  | 48460/61904 [2:29:41<5:16:51,  1.41s/it]
 78%|███████▊  | 48461/61904 [2:29:42<5:08:39,  1.38s/it]
 78%|███████▊  | 48462/61904 [2:29:44<5:13:21,  1.40s/it]
 78%|███████▊  | 48463/61904 [2:29:45<5:07:34,  1.37s/it]
 78%|███████▊  | 48464/61904 [2:29:46<5:05:04,  1.36s/it]
 78%|███████▊  | 48465/61904 [2:29:48<5:04:09,  1.36s/it]
 78%|███████▊  | 48466/61904 [2:29:49<5:06:43,  1.37s/it]
 78%|███████▊  | 48467/61904 [2:29:51<5:00:53,  1.34s/it]
 78%|███████▊  | 48468/61904 [2:29:52<4:59:03,  1.34s/it]
 78%|███████▊  | 48469/61904 [2:29:53<5:01:14,  1.35s/it]
 78%|███████▊  | 48470/61904 [2:29:55<5:01:27,  1.35s/it]
 78%|███████▊  | 48471/61904 [2:29:56<4:54:49,  1.32s/it]
 78%|███████▊  | 48472/61904 [2:29:57<4:56:13,  1.32s/it]
 78%|███████▊  | 48473/61904 [2:29:58<4:49:08,  1.29s/it]
 78%|███████▊  | 48474/61904 [2:30:00<4:50:14,  1.30s/it]
 78%|███████▊  | 48475/61904 [2:30:01<4:50:11,  1.30s/it]
 78%|███████▊  | 48476/61904 [2:30:02<4:56:04,  1.32s/it]
 78%|███████▊  | 48477/61904 [2:30:04<4:59:54,  1.34s/it]
 78%|███████▊  | 48478/61904 [2:30:05<5:03:31,  1.36s/it]
 78%|███████▊  | 48479/61904 [2:30:06<4:58:13,  1.33s/it]
 78%|███████▊  | 48480/61904 [2:30:08<5:06:40,  1.37s/it]
                                                         
{'loss': 2.4792, 'learning_rate': 1.2175547776481265e-07, 'epoch': 12.53}

 78%|███████▊  | 48480/61904 [2:30:08<5:06:40,  1.37s/it]
 78%|███████▊  | 48481/61904 [2:30:09<4:59:35,  1.34s/it]
 78%|███████▊  | 48482/61904 [2:30:10<5:00:59,  1.35s/it]
 78%|███████▊  | 48483/61904 [2:30:12<5:03:52,  1.36s/it]
 78%|███████▊  | 48484/61904 [2:30:13<5:14:02,  1.40s/it]
 78%|███████▊  | 48485/61904 [2:30:15<5:12:16,  1.40s/it]
 78%|███████▊  | 48486/61904 [2:30:16<5:16:11,  1.41s/it]
 78%|███████▊  | 48487/61904 [2:30:17<5:04:07,  1.36s/it]
 78%|███████▊  | 48488/61904 [2:30:19<5:08:51,  1.38s/it]
 78%|███████▊  | 48489/61904 [2:30:20<5:09:34,  1.38s/it]
 78%|███████▊  | 48490/61904 [2:30:22<5:06:13,  1.37s/it]
 78%|███████▊  | 48491/61904 [2:30:23<5:11:00,  1.39s/it]
 78%|███████▊  | 48492/61904 [2:30:24<5:10:56,  1.39s/it]
 78%|███████▊  | 48493/61904 [2:30:26<5:06:12,  1.37s/it]
 78%|███████▊  | 48494/61904 [2:30:27<5:11:37,  1.39s/it]
 78%|███████▊  | 48495/61904 [2:30:28<5:00:43,  1.35s/it]
 78%|███████▊  | 48496/61904 [2:30:30<4:53:57,  1.32s/it]
 78%|███████▊  | 48497/61904 [2:30:31<5:12:53,  1.40s/it]
 78%|███████▊  | 48498/61904 [2:30:33<5:05:54,  1.37s/it]
 78%|███████▊  | 48499/61904 [2:30:34<5:09:36,  1.39s/it]
 78%|███████▊  | 48500/61904 [2:30:35<5:13:35,  1.40s/it]
                                                         
{'loss': 2.4331, 'learning_rate': 1.2172306495527032e-07, 'epoch': 12.54}

 78%|███████▊  | 48500/61904 [2:30:35<5:13:35,  1.40s/it]
 78%|███████▊  | 48501/61904 [2:30:37<5:17:59,  1.42s/it]
 78%|███████▊  | 48502/61904 [2:30:38<5:10:00,  1.39s/it]
 78%|███████▊  | 48503/61904 [2:30:40<5:21:14,  1.44s/it]
 78%|███████▊  | 48504/61904 [2:30:41<5:12:19,  1.40s/it]
 78%|███████▊  | 48505/61904 [2:30:43<5:14:44,  1.41s/it]
 78%|███████▊  | 48506/61904 [2:30:44<5:15:33,  1.41s/it]
 78%|███████▊  | 48507/61904 [2:30:45<5:15:02,  1.41s/it]
 78%|███████▊  | 48508/61904 [2:30:47<5:06:33,  1.37s/it]
 78%|███████▊  | 48509/61904 [2:30:48<5:01:05,  1.35s/it]
 78%|███████▊  | 48510/61904 [2:30:49<5:07:16,  1.38s/it]
 78%|███████▊  | 48511/61904 [2:30:51<5:01:39,  1.35s/it]
 78%|███████▊  | 48512/61904 [2:30:52<5:05:21,  1.37s/it]
 78%|███████▊  | 48513/61904 [2:30:53<5:03:30,  1.36s/it]
 78%|███████▊  | 48514/61904 [2:30:55<5:03:26,  1.36s/it]
 78%|███████▊  | 48515/61904 [2:30:56<4:56:33,  1.33s/it]
 78%|███████▊  | 48516/61904 [2:30:57<4:44:15,  1.27s/it]
 78%|███████▊  | 48517/61904 [2:30:58<4:47:53,  1.29s/it]
 78%|███████▊  | 48518/61904 [2:31:00<4:56:14,  1.33s/it]
 78%|███████▊  | 48519/61904 [2:31:01<4:51:21,  1.31s/it]
 78%|███████▊  | 48520/61904 [2:31:02<4:47:32,  1.29s/it]
                                                         
{'loss': 2.4537, 'learning_rate': 1.21690652145728e-07, 'epoch': 12.54}

 78%|███████▊  | 48520/61904 [2:31:02<4:47:32,  1.29s/it]
 78%|███████▊  | 48521/61904 [2:31:04<4:51:11,  1.31s/it]
 78%|███████▊  | 48522/61904 [2:31:05<5:02:27,  1.36s/it]
 78%|███████▊  | 48523/61904 [2:31:07<5:03:55,  1.36s/it]
 78%|███████▊  | 48524/61904 [2:31:08<5:17:49,  1.43s/it]
 78%|███████▊  | 48525/61904 [2:31:09<5:10:10,  1.39s/it]
 78%|███████▊  | 48526/61904 [2:31:11<5:10:16,  1.39s/it]
 78%|███████▊  | 48527/61904 [2:31:12<5:03:18,  1.36s/it]
 78%|███████▊  | 48528/61904 [2:31:14<5:05:46,  1.37s/it]
 78%|███████▊  | 48529/61904 [2:31:15<4:59:34,  1.34s/it]
 78%|███████▊  | 48530/61904 [2:31:16<5:08:32,  1.38s/it]
 78%|███████▊  | 48531/61904 [2:31:18<5:01:40,  1.35s/it]
 78%|███████▊  | 48532/61904 [2:31:19<5:01:23,  1.35s/it]
 78%|███████▊  | 48533/61904 [2:31:20<5:02:06,  1.36s/it]
 78%|███████▊  | 48534/61904 [2:31:22<5:02:17,  1.36s/it]
 78%|███████▊  | 48535/61904 [2:31:23<5:05:34,  1.37s/it]
 78%|███████▊  | 48536/61904 [2:31:25<5:11:35,  1.40s/it]
 78%|███████▊  | 48537/61904 [2:31:26<5:07:02,  1.38s/it]
 78%|███████▊  | 48538/61904 [2:31:27<4:59:02,  1.34s/it]
 78%|███████▊  | 48539/61904 [2:31:29<5:05:42,  1.37s/it]
 78%|███████▊  | 48540/61904 [2:31:30<4:55:59,  1.33s/it]
                                                         
{'loss': 2.5384, 'learning_rate': 1.2165823933618564e-07, 'epoch': 12.55}

 78%|███████▊  | 48540/61904 [2:31:30<4:55:59,  1.33s/it]
 78%|███████▊  | 48541/61904 [2:31:31<4:56:40,  1.33s/it]
 78%|███████▊  | 48542/61904 [2:31:33<4:59:22,  1.34s/it]
 78%|███████▊  | 48543/61904 [2:31:34<4:57:54,  1.34s/it]
 78%|███████▊  | 48544/61904 [2:31:35<4:55:25,  1.33s/it]
 78%|███████▊  | 48545/61904 [2:31:37<4:58:07,  1.34s/it]
 78%|███████▊  | 48546/61904 [2:31:38<5:01:11,  1.35s/it]
 78%|███████▊  | 48547/61904 [2:31:39<4:54:03,  1.32s/it]
 78%|███████▊  | 48548/61904 [2:31:41<5:00:17,  1.35s/it]
 78%|███████▊  | 48549/61904 [2:31:42<4:58:42,  1.34s/it]
 78%|███████▊  | 48550/61904 [2:31:43<5:11:19,  1.40s/it]
 78%|███████▊  | 48551/61904 [2:31:45<5:05:58,  1.37s/it]
 78%|███████▊  | 48552/61904 [2:31:46<5:00:24,  1.35s/it]
 78%|███████▊  | 48553/61904 [2:31:47<5:04:03,  1.37s/it]
 78%|███████▊  | 48554/61904 [2:31:49<5:10:01,  1.39s/it]
 78%|███████▊  | 48555/61904 [2:31:50<5:05:34,  1.37s/it]
 78%|███████▊  | 48556/61904 [2:31:52<5:01:20,  1.35s/it]
 78%|███████▊  | 48557/61904 [2:31:53<5:03:21,  1.36s/it]
 78%|███████▊  | 48558/61904 [2:31:54<5:00:44,  1.35s/it]
 78%|███████▊  | 48559/61904 [2:31:56<5:02:06,  1.36s/it]
 78%|███████▊  | 48560/61904 [2:31:57<5:04:53,  1.37s/it]
                                                         
{'loss': 2.5251, 'learning_rate': 1.2162582652664333e-07, 'epoch': 12.55}

 78%|███████▊  | 48560/61904 [2:31:57<5:04:53,  1.37s/it]
 78%|███████▊  | 48561/61904 [2:31:58<5:02:54,  1.36s/it]
 78%|███████▊  | 48562/61904 [2:32:00<5:01:50,  1.36s/it]
 78%|███████▊  | 48563/61904 [2:32:01<4:59:14,  1.35s/it]
 78%|███████▊  | 48564/61904 [2:32:02<4:57:29,  1.34s/it]
 78%|███████▊  | 48565/61904 [2:32:04<4:58:03,  1.34s/it]
 78%|███████▊  | 48566/61904 [2:32:05<4:56:49,  1.34s/it]
 78%|███████▊  | 48567/61904 [2:32:07<5:09:52,  1.39s/it]
 78%|███████▊  | 48568/61904 [2:32:08<5:05:30,  1.37s/it]
 78%|███████▊  | 48569/61904 [2:32:09<5:09:47,  1.39s/it]
 78%|███████▊  | 48570/61904 [2:32:11<5:06:38,  1.38s/it]
 78%|███████▊  | 48571/61904 [2:32:12<5:03:16,  1.36s/it]
 78%|███████▊  | 48572/61904 [2:32:14<5:15:55,  1.42s/it]
 78%|███████▊  | 48573/61904 [2:32:15<5:25:26,  1.46s/it]
 78%|███████▊  | 48574/61904 [2:32:16<5:20:49,  1.44s/it]
 78%|███████▊  | 48575/61904 [2:32:18<5:13:01,  1.41s/it]
 78%|███████▊  | 48576/61904 [2:32:19<5:17:49,  1.43s/it]
 78%|███████▊  | 48577/61904 [2:32:21<5:07:14,  1.38s/it]
 78%|███████▊  | 48578/61904 [2:32:22<4:57:25,  1.34s/it]
 78%|███████▊  | 48579/61904 [2:32:23<5:01:46,  1.36s/it]
 78%|███████▊  | 48580/61904 [2:32:25<5:10:15,  1.40s/it]
                                                         
{'loss': 2.4403, 'learning_rate': 1.21593413717101e-07, 'epoch': 12.56}

 78%|███████▊  | 48580/61904 [2:32:25<5:10:15,  1.40s/it]
 78%|███████▊  | 48581/61904 [2:32:26<5:04:40,  1.37s/it]
 78%|███████▊  | 48582/61904 [2:32:27<5:00:47,  1.35s/it]
 78%|███████▊  | 48583/61904 [2:32:29<4:59:17,  1.35s/it]
 78%|███████▊  | 48584/61904 [2:32:30<4:58:57,  1.35s/it]
 78%|███████▊  | 48585/61904 [2:32:31<4:59:46,  1.35s/it]
 78%|███████▊  | 48586/61904 [2:32:33<5:02:46,  1.36s/it]
 78%|███████▊  | 48587/61904 [2:32:34<5:09:07,  1.39s/it]
 78%|███████▊  | 48588/61904 [2:32:36<5:20:42,  1.45s/it]
 78%|███████▊  | 48589/61904 [2:32:37<5:08:38,  1.39s/it]
 78%|███████▊  | 48590/61904 [2:32:39<5:14:13,  1.42s/it]
 78%|███████▊  | 48591/61904 [2:32:40<5:13:26,  1.41s/it]
 78%|███████▊  | 48592/61904 [2:32:41<5:06:35,  1.38s/it]
 78%|███████▊  | 48593/61904 [2:32:43<5:19:29,  1.44s/it]
 78%|███████▊  | 48594/61904 [2:32:44<5:10:28,  1.40s/it]
 79%|███████▊  | 48595/61904 [2:32:46<5:16:09,  1.43s/it]
 79%|███████▊  | 48596/61904 [2:32:47<5:12:33,  1.41s/it]
 79%|███████▊  | 48597/61904 [2:32:48<5:04:14,  1.37s/it]
 79%|███████▊  | 48598/61904 [2:32:50<4:55:59,  1.33s/it]
 79%|███████▊  | 48599/61904 [2:32:51<4:51:52,  1.32s/it]
 79%|███████▊  | 48600/61904 [2:32:52<4:58:16,  1.35s/it]
                                                         
{'loss': 2.4652, 'learning_rate': 1.2156100090755865e-07, 'epoch': 12.56}

 79%|███████▊  | 48600/61904 [2:32:52<4:58:16,  1.35s/it]
 79%|███████▊  | 48601/61904 [2:32:54<5:02:32,  1.36s/it]
 79%|███████▊  | 48602/61904 [2:32:55<5:17:30,  1.43s/it]
 79%|███████▊  | 48603/61904 [2:32:57<5:14:59,  1.42s/it]
 79%|███████▊  | 48604/61904 [2:32:58<5:03:15,  1.37s/it]
 79%|███████▊  | 48605/61904 [2:32:59<5:04:05,  1.37s/it]
 79%|███████▊  | 48606/61904 [2:33:01<5:06:55,  1.38s/it]
 79%|███████▊  | 48607/61904 [2:33:02<4:59:54,  1.35s/it]
 79%|███████▊  | 48608/61904 [2:33:03<4:57:01,  1.34s/it]
 79%|███████▊  | 48609/61904 [2:33:05<5:04:43,  1.38s/it]
 79%|███████▊  | 48610/61904 [2:33:06<4:57:53,  1.34s/it]
 79%|███████▊  | 48611/61904 [2:33:07<4:53:11,  1.32s/it]
 79%|███████▊  | 48612/61904 [2:33:09<4:59:17,  1.35s/it]
 79%|███████▊  | 48613/61904 [2:33:10<4:56:35,  1.34s/it]
 79%|███████▊  | 48614/61904 [2:33:11<5:00:33,  1.36s/it]
 79%|███████▊  | 48615/61904 [2:33:13<4:52:36,  1.32s/it]
 79%|███████▊  | 48616/61904 [2:33:14<4:52:31,  1.32s/it]
 79%|███████▊  | 48617/61904 [2:33:15<4:56:51,  1.34s/it]
 79%|███████▊  | 48618/61904 [2:33:17<5:05:55,  1.38s/it]
 79%|███████▊  | 48619/61904 [2:33:18<5:06:34,  1.38s/it]
 79%|███████▊  | 48620/61904 [2:33:20<5:09:43,  1.40s/it]
                                                         
{'loss': 2.5051, 'learning_rate': 1.2152858809801634e-07, 'epoch': 12.57}

 79%|███████▊  | 48620/61904 [2:33:20<5:09:43,  1.40s/it]
 79%|███████▊  | 48621/61904 [2:33:21<5:13:53,  1.42s/it]
 79%|███████▊  | 48622/61904 [2:33:23<5:16:35,  1.43s/it]
 79%|███████▊  | 48623/61904 [2:33:24<5:14:19,  1.42s/it]
 79%|███████▊  | 48624/61904 [2:33:25<5:10:44,  1.40s/it]
 79%|███████▊  | 48625/61904 [2:33:27<5:07:23,  1.39s/it]
 79%|███████▊  | 48626/61904 [2:33:28<5:22:32,  1.46s/it]
 79%|███████▊  | 48627/61904 [2:33:30<5:12:49,  1.41s/it]
 79%|███████▊  | 48628/61904 [2:33:31<5:07:40,  1.39s/it]
 79%|███████▊  | 48629/61904 [2:33:32<5:00:47,  1.36s/it]
 79%|███████▊  | 48630/61904 [2:33:34<5:00:01,  1.36s/it]
 79%|███████▊  | 48631/61904 [2:33:35<5:04:13,  1.38s/it]
 79%|███████▊  | 48632/61904 [2:33:36<5:00:34,  1.36s/it]
 79%|███████▊  | 48633/61904 [2:33:38<4:53:24,  1.33s/it]
 79%|███████▊  | 48634/61904 [2:33:39<4:52:00,  1.32s/it]
 79%|███████▊  | 48635/61904 [2:33:40<4:52:46,  1.32s/it]
 79%|███████▊  | 48636/61904 [2:33:42<4:55:22,  1.34s/it]
 79%|███████▊  | 48637/61904 [2:33:43<4:56:18,  1.34s/it]
 79%|███████▊  | 48638/61904 [2:33:44<4:51:37,  1.32s/it]
 79%|███████▊  | 48639/61904 [2:33:46<5:05:11,  1.38s/it]
 79%|███████▊  | 48640/61904 [2:33:47<4:58:04,  1.35s/it]
                                                         
{'loss': 2.4572, 'learning_rate': 1.21496175288474e-07, 'epoch': 12.57}

 79%|███████▊  | 48640/61904 [2:33:47<4:58:04,  1.35s/it]
 79%|███████▊  | 48641/61904 [2:33:48<4:55:43,  1.34s/it]
 79%|███████▊  | 48642/61904 [2:33:50<5:06:18,  1.39s/it]
 79%|███████▊  | 48643/61904 [2:33:51<5:06:25,  1.39s/it]
 79%|███████▊  | 48644/61904 [2:33:52<4:58:22,  1.35s/it]
 79%|███████▊  | 48645/61904 [2:33:54<4:59:17,  1.35s/it]
 79%|███████▊  | 48646/61904 [2:33:55<5:13:54,  1.42s/it]
 79%|███████▊  | 48647/61904 [2:33:57<5:04:57,  1.38s/it]
 79%|███████▊  | 48648/61904 [2:33:58<5:02:42,  1.37s/it]
 79%|███████▊  | 48649/61904 [2:33:59<5:11:23,  1.41s/it]
 79%|███████▊  | 48650/61904 [2:34:01<5:07:22,  1.39s/it]
 79%|███████▊  | 48651/61904 [2:34:02<5:02:35,  1.37s/it]
 79%|███████▊  | 48652/61904 [2:34:04<5:03:45,  1.38s/it]
 79%|███████▊  | 48653/61904 [2:34:05<4:58:47,  1.35s/it]
 79%|███████▊  | 48654/61904 [2:34:06<4:54:27,  1.33s/it]
 79%|███████▊  | 48655/61904 [2:34:07<4:52:30,  1.32s/it]
 79%|███████▊  | 48656/61904 [2:34:09<4:48:09,  1.31s/it]
 79%|███████▊  | 48657/61904 [2:34:10<4:42:31,  1.28s/it]
 79%|███████▊  | 48658/61904 [2:34:11<4:41:56,  1.28s/it]
 79%|███████▊  | 48659/61904 [2:34:13<4:48:38,  1.31s/it]
 79%|███████▊  | 48660/61904 [2:34:14<4:53:03,  1.33s/it]
                                                         
{'loss': 2.4891, 'learning_rate': 1.2146376247893166e-07, 'epoch': 12.58}

 79%|███████▊  | 48660/61904 [2:34:14<4:53:03,  1.33s/it]
 79%|███████▊  | 48661/61904 [2:34:15<4:51:37,  1.32s/it]
 79%|███████▊  | 48662/61904 [2:34:17<4:59:56,  1.36s/it]
 79%|███████▊  | 48663/61904 [2:34:18<5:09:54,  1.40s/it]
 79%|███████▊  | 48664/61904 [2:34:19<5:02:49,  1.37s/it]
 79%|███████▊  | 48665/61904 [2:34:21<5:04:37,  1.38s/it]
 79%|███████▊  | 48666/61904 [2:34:22<5:10:15,  1.41s/it]
 79%|███████▊  | 48667/61904 [2:34:24<5:07:01,  1.39s/it]
 79%|███████▊  | 48668/61904 [2:34:25<4:57:25,  1.35s/it]
 79%|███████▊  | 48669/61904 [2:34:26<4:48:40,  1.31s/it]
 79%|███████▊  | 48670/61904 [2:34:28<4:59:59,  1.36s/it]
 79%|███████▊  | 48671/61904 [2:34:29<4:55:20,  1.34s/it]
 79%|███████▊  | 48672/61904 [2:34:30<4:55:40,  1.34s/it]
 79%|███████▊  | 48673/61904 [2:34:32<5:05:51,  1.39s/it]
 79%|███████▊  | 48674/61904 [2:34:33<5:06:19,  1.39s/it]
 79%|███████▊  | 48675/61904 [2:34:35<5:06:52,  1.39s/it]
 79%|███████▊  | 48676/61904 [2:34:36<5:02:29,  1.37s/it]
 79%|███████▊  | 48677/61904 [2:34:37<5:02:42,  1.37s/it]
 79%|███████▊  | 48678/61904 [2:34:39<4:58:44,  1.36s/it]
 79%|███████▊  | 48679/61904 [2:34:40<5:15:46,  1.43s/it]
 79%|███████▊  | 48680/61904 [2:34:42<5:12:50,  1.42s/it]
                                                         
{'loss': 2.5186, 'learning_rate': 1.2143134966938935e-07, 'epoch': 12.58}

 79%|███████▊  | 48680/61904 [2:34:42<5:12:50,  1.42s/it]
 79%|███████▊  | 48681/61904 [2:34:43<5:10:27,  1.41s/it]
 79%|███████▊  | 48682/61904 [2:34:44<4:57:52,  1.35s/it]
 79%|███████▊  | 48683/61904 [2:34:46<5:01:23,  1.37s/it]
 79%|███████▊  | 48684/61904 [2:34:47<5:11:32,  1.41s/it]
 79%|███████▊  | 48685/61904 [2:34:48<5:03:18,  1.38s/it]
 79%|███████▊  | 48686/61904 [2:34:50<4:59:08,  1.36s/it]
 79%|███████▊  | 48687/61904 [2:34:51<4:57:43,  1.35s/it]
 79%|███████▊  | 48688/61904 [2:34:52<4:59:24,  1.36s/it]
 79%|███████▊  | 48689/61904 [2:34:54<5:01:40,  1.37s/it]
 79%|███████▊  | 48690/61904 [2:34:55<5:02:56,  1.38s/it]
 79%|███████▊  | 48691/61904 [2:34:56<4:52:51,  1.33s/it]
 79%|███████▊  | 48692/61904 [2:34:58<4:58:08,  1.35s/it]
 79%|███████▊  | 48693/61904 [2:34:59<4:56:50,  1.35s/it]
 79%|███████▊  | 48694/61904 [2:35:01<5:01:10,  1.37s/it]
 79%|███████▊  | 48695/61904 [2:35:02<4:57:49,  1.35s/it]
 79%|███████▊  | 48696/61904 [2:35:03<5:00:08,  1.36s/it]
 79%|███████▊  | 48697/61904 [2:35:05<4:51:08,  1.32s/it]
 79%|███████▊  | 48698/61904 [2:35:06<4:58:12,  1.35s/it]
 79%|███████▊  | 48699/61904 [2:35:07<5:00:59,  1.37s/it]
 79%|███████▊  | 48700/61904 [2:35:09<5:02:35,  1.38s/it]
                                                         
{'loss': 2.4751, 'learning_rate': 1.21398936859847e-07, 'epoch': 12.59}

 79%|███████▊  | 48700/61904 [2:35:09<5:02:35,  1.38s/it]
 79%|███████▊  | 48701/61904 [2:35:10<4:57:00,  1.35s/it]
 79%|███████▊  | 48702/61904 [2:35:11<4:55:57,  1.35s/it]
 79%|███████▊  | 48703/61904 [2:35:13<4:55:37,  1.34s/it]
 79%|███████▊  | 48704/61904 [2:35:14<4:58:09,  1.36s/it]
 79%|███████▊  | 48705/61904 [2:35:15<4:53:57,  1.34s/it]
 79%|███████▊  | 48706/61904 [2:35:17<5:03:01,  1.38s/it]
 79%|███████▊  | 48707/61904 [2:35:18<5:04:25,  1.38s/it]
 79%|███████▊  | 48708/61904 [2:35:20<5:01:48,  1.37s/it]
 79%|███████▊  | 48709/61904 [2:35:21<4:58:54,  1.36s/it]
 79%|███████▊  | 48710/61904 [2:35:22<4:57:23,  1.35s/it]
 79%|███████▊  | 48711/61904 [2:35:24<4:51:43,  1.33s/it]
 79%|███████▊  | 48712/61904 [2:35:25<4:58:11,  1.36s/it]
 79%|███████▊  | 48713/61904 [2:35:26<4:53:02,  1.33s/it]
 79%|███████▊  | 48714/61904 [2:35:28<5:04:20,  1.38s/it]
 79%|███████▊  | 48715/61904 [2:35:29<4:53:53,  1.34s/it]
 79%|███████▊  | 48716/61904 [2:35:30<4:52:50,  1.33s/it]
 79%|███████▊  | 48717/61904 [2:35:32<4:57:58,  1.36s/it]
 79%|███████▊  | 48718/61904 [2:35:33<4:59:05,  1.36s/it]
 79%|███████▊  | 48719/61904 [2:35:35<5:11:14,  1.42s/it]
 79%|███████▊  | 48720/61904 [2:35:36<5:14:47,  1.43s/it]
                                                         
{'loss': 2.4716, 'learning_rate': 1.2136652405030468e-07, 'epoch': 12.59}

 79%|███████▊  | 48720/61904 [2:35:36<5:14:47,  1.43s/it]
 79%|███████▊  | 48721/61904 [2:35:37<5:09:24,  1.41s/it]
 79%|███████▊  | 48722/61904 [2:35:39<5:20:30,  1.46s/it]
 79%|███████▊  | 48723/61904 [2:35:41<5:22:46,  1.47s/it]
 79%|███████▊  | 48724/61904 [2:35:42<5:19:48,  1.46s/it]
 79%|███████▊  | 48725/61904 [2:35:43<5:15:43,  1.44s/it]
 79%|███████▊  | 48726/61904 [2:35:45<5:12:30,  1.42s/it]
 79%|███████▊  | 48727/61904 [2:35:46<5:13:36,  1.43s/it]
 79%|███████▊  | 48728/61904 [2:35:48<5:12:46,  1.42s/it]
 79%|███████▊  | 48729/61904 [2:35:49<5:03:15,  1.38s/it]
 79%|███████▊  | 48730/61904 [2:35:50<5:02:48,  1.38s/it]
 79%|███████▊  | 48731/61904 [2:35:51<4:54:08,  1.34s/it]
 79%|███████▊  | 48732/61904 [2:35:53<4:57:07,  1.35s/it]
 79%|███████▊  | 48733/61904 [2:35:54<4:57:04,  1.35s/it]
 79%|███████▊  | 48734/61904 [2:35:56<4:57:27,  1.36s/it]
 79%|███████▊  | 48735/61904 [2:35:57<4:55:43,  1.35s/it]
 79%|███████▊  | 48736/61904 [2:35:58<5:02:23,  1.38s/it]
 79%|███████▊  | 48737/61904 [2:36:00<5:07:25,  1.40s/it]
 79%|███████▊  | 48738/61904 [2:36:01<4:56:08,  1.35s/it]
 79%|███████▊  | 48739/61904 [2:36:02<4:56:12,  1.35s/it]
 79%|███████▊  | 48740/61904 [2:36:04<4:55:21,  1.35s/it]
                                                         
{'loss': 2.4849, 'learning_rate': 1.2133411124076234e-07, 'epoch': 12.6}

 79%|███████▊  | 48740/61904 [2:36:04<4:55:21,  1.35s/it]
 79%|███████▊  | 48741/61904 [2:36:05<4:53:35,  1.34s/it]
 79%|███████▊  | 48742/61904 [2:36:06<4:57:06,  1.35s/it]
 79%|███████▊  | 48743/61904 [2:36:08<4:54:46,  1.34s/it]
 79%|███████▊  | 48744/61904 [2:36:09<4:47:46,  1.31s/it]
 79%|███████▊  | 48745/61904 [2:36:11<5:06:27,  1.40s/it]
 79%|███████▊  | 48746/61904 [2:36:12<5:10:38,  1.42s/it]
 79%|███████▊  | 48747/61904 [2:36:13<5:01:07,  1.37s/it]
 79%|███████▊  | 48748/61904 [2:36:15<4:59:27,  1.37s/it]
 79%|███████▊  | 48749/61904 [2:36:16<4:54:02,  1.34s/it]
 79%|███████▉  | 48750/61904 [2:36:17<5:00:53,  1.37s/it]
 79%|███████▉  | 48751/61904 [2:36:19<5:01:34,  1.38s/it]
 79%|███████▉  | 48752/61904 [2:36:20<4:55:41,  1.35s/it]
 79%|███████▉  | 48753/61904 [2:36:22<5:04:57,  1.39s/it]
 79%|███████▉  | 48754/61904 [2:36:23<5:01:52,  1.38s/it]
 79%|███████▉  | 48755/61904 [2:36:24<4:59:46,  1.37s/it]
 79%|███████▉  | 48756/61904 [2:36:26<5:03:29,  1.38s/it]
 79%|███████▉  | 48757/61904 [2:36:27<5:02:07,  1.38s/it]
 79%|███████▉  | 48758/61904 [2:36:28<4:59:55,  1.37s/it]
 79%|███████▉  | 48759/61904 [2:36:30<5:08:01,  1.41s/it]
 79%|███████▉  | 48760/61904 [2:36:31<5:02:50,  1.38s/it]
                                                         
{'loss': 2.4891, 'learning_rate': 1.2130169843122e-07, 'epoch': 12.6}

 79%|███████▉  | 48760/61904 [2:36:31<5:02:50,  1.38s/it]
 79%|███████▉  | 48761/61904 [2:36:33<5:02:27,  1.38s/it]
 79%|███████▉  | 48762/61904 [2:36:34<5:10:31,  1.42s/it]
 79%|███████▉  | 48763/61904 [2:36:36<5:09:31,  1.41s/it]
 79%|███████▉  | 48764/61904 [2:36:37<5:07:05,  1.40s/it]
 79%|███████▉  | 48765/61904 [2:36:38<5:05:59,  1.40s/it]
 79%|███████▉  | 48766/61904 [2:36:40<5:08:37,  1.41s/it]
 79%|███████▉  | 48767/61904 [2:36:41<5:05:24,  1.39s/it]
 79%|███████▉  | 48768/61904 [2:36:42<4:57:40,  1.36s/it]
 79%|███████▉  | 48769/61904 [2:36:44<4:58:12,  1.36s/it]
 79%|███████▉  | 48770/61904 [2:36:45<4:55:52,  1.35s/it]
 79%|███████▉  | 48771/61904 [2:36:46<4:56:44,  1.36s/it]
 79%|███████▉  | 48772/61904 [2:36:48<4:53:27,  1.34s/it]
 79%|███████▉  | 48773/61904 [2:36:49<5:00:09,  1.37s/it]
 79%|███████▉  | 48774/61904 [2:36:51<5:04:43,  1.39s/it]
 79%|███████▉  | 48775/61904 [2:36:52<5:07:58,  1.41s/it]
 79%|███████▉  | 48776/61904 [2:36:54<5:18:19,  1.45s/it]
 79%|███████▉  | 48777/61904 [2:36:55<5:07:19,  1.40s/it]
 79%|███████▉  | 48778/61904 [2:36:56<5:08:45,  1.41s/it]
 79%|███████▉  | 48779/61904 [2:36:58<5:01:34,  1.38s/it]
 79%|███████▉  | 48780/61904 [2:36:59<4:50:37,  1.33s/it]
                                                         
{'loss': 2.4776, 'learning_rate': 1.212692856216777e-07, 'epoch': 12.61}

 79%|███████▉  | 48780/61904 [2:36:59<4:50:37,  1.33s/it]
 79%|███████▉  | 48781/61904 [2:37:00<4:45:44,  1.31s/it]
 79%|███████▉  | 48782/61904 [2:37:01<4:45:05,  1.30s/it]
 79%|███████▉  | 48783/61904 [2:37:03<4:51:41,  1.33s/it]
 79%|███████▉  | 48784/61904 [2:37:04<4:50:22,  1.33s/it]
 79%|███████▉  | 48785/61904 [2:37:06<4:56:17,  1.36s/it]
 79%|███████▉  | 48786/61904 [2:37:07<4:53:29,  1.34s/it]
 79%|███████▉  | 48787/61904 [2:37:08<5:06:40,  1.40s/it]
 79%|███████▉  | 48788/61904 [2:37:10<5:00:29,  1.37s/it]
 79%|███████▉  | 48789/61904 [2:37:11<4:57:00,  1.36s/it]
 79%|███████▉  | 48790/61904 [2:37:12<5:02:39,  1.38s/it]
 79%|███████▉  | 48791/61904 [2:37:14<5:02:04,  1.38s/it]
 79%|███████▉  | 48792/61904 [2:37:15<5:07:14,  1.41s/it]
 79%|███████▉  | 48793/61904 [2:37:17<5:18:07,  1.46s/it]
 79%|███████▉  | 48794/61904 [2:37:18<5:14:30,  1.44s/it]
 79%|███████▉  | 48795/61904 [2:37:20<5:02:36,  1.39s/it]
 79%|███████▉  | 48796/61904 [2:37:21<4:58:57,  1.37s/it]
 79%|███████▉  | 48797/61904 [2:37:22<4:54:32,  1.35s/it]
 79%|███████▉  | 48798/61904 [2:37:24<4:56:40,  1.36s/it]
 79%|███████▉  | 48799/61904 [2:37:25<5:09:08,  1.42s/it]
 79%|███████▉  | 48800/61904 [2:37:26<5:04:14,  1.39s/it]
                                                         
{'loss': 2.5003, 'learning_rate': 1.2123687281213535e-07, 'epoch': 12.61}

 79%|███████▉  | 48800/61904 [2:37:26<5:04:14,  1.39s/it]
 79%|███████▉  | 48801/61904 [2:37:28<5:05:15,  1.40s/it]
 79%|███████▉  | 48802/61904 [2:37:29<5:05:26,  1.40s/it]
 79%|███████▉  | 48803/61904 [2:37:30<4:52:43,  1.34s/it]
 79%|███████▉  | 48804/61904 [2:37:32<4:47:15,  1.32s/it]
 79%|███████▉  | 48805/61904 [2:37:33<4:47:36,  1.32s/it]
 79%|███████▉  | 48806/61904 [2:37:34<4:46:02,  1.31s/it]
 79%|███████▉  | 48807/61904 [2:37:36<4:42:27,  1.29s/it]
 79%|███████▉  | 48808/61904 [2:37:37<4:54:16,  1.35s/it]
 79%|███████▉  | 48809/61904 [2:37:38<4:46:36,  1.31s/it]
 79%|███████▉  | 48810/61904 [2:37:40<4:59:57,  1.37s/it]
 79%|███████▉  | 48811/61904 [2:37:41<5:01:27,  1.38s/it]
 79%|███████▉  | 48812/61904 [2:37:43<5:08:46,  1.42s/it]
 79%|███████▉  | 48813/61904 [2:37:44<4:58:29,  1.37s/it]
 79%|███████▉  | 48814/61904 [2:37:45<4:53:15,  1.34s/it]
 79%|███████▉  | 48815/61904 [2:37:46<4:45:58,  1.31s/it]
 79%|███████▉  | 48816/61904 [2:37:48<4:46:12,  1.31s/it]
 79%|███████▉  | 48817/61904 [2:37:49<4:47:24,  1.32s/it]
 79%|███████▉  | 48818/61904 [2:37:50<4:50:17,  1.33s/it]
 79%|███████▉  | 48819/61904 [2:37:52<4:53:21,  1.35s/it]
 79%|███████▉  | 48820/61904 [2:37:53<4:54:09,  1.35s/it]
                                                         
{'loss': 2.4541, 'learning_rate': 1.21204460002593e-07, 'epoch': 12.62}

 79%|███████▉  | 48820/61904 [2:37:53<4:54:09,  1.35s/it]
 79%|███████▉  | 48821/61904 [2:37:55<5:07:29,  1.41s/it]
 79%|███████▉  | 48822/61904 [2:37:56<5:05:26,  1.40s/it]
 79%|███████▉  | 48823/61904 [2:37:57<5:00:59,  1.38s/it]
 79%|███████▉  | 48824/61904 [2:37:59<5:08:29,  1.42s/it]
 79%|███████▉  | 48825/61904 [2:38:00<4:59:33,  1.37s/it]
 79%|███████▉  | 48826/61904 [2:38:02<5:03:07,  1.39s/it]
 79%|███████▉  | 48827/61904 [2:38:03<5:04:43,  1.40s/it]
 79%|███████▉  | 48828/61904 [2:38:04<5:01:31,  1.38s/it]
 79%|███████▉  | 48829/61904 [2:38:06<4:57:20,  1.36s/it]
 79%|███████▉  | 48830/61904 [2:38:07<4:52:06,  1.34s/it]
 79%|███████▉  | 48831/61904 [2:38:09<4:59:59,  1.38s/it]
 79%|███████▉  | 48832/61904 [2:38:10<4:59:31,  1.37s/it]
 79%|███████▉  | 48833/61904 [2:38:11<5:02:56,  1.39s/it]
 79%|███████▉  | 48834/61904 [2:38:13<5:03:10,  1.39s/it]
 79%|███████▉  | 48835/61904 [2:38:14<4:58:25,  1.37s/it]
 79%|███████▉  | 48836/61904 [2:38:15<4:59:55,  1.38s/it]
 79%|███████▉  | 48837/61904 [2:38:17<4:53:41,  1.35s/it]
 79%|███████▉  | 48838/61904 [2:38:18<5:00:52,  1.38s/it]
 79%|███████▉  | 48839/61904 [2:38:20<4:59:20,  1.37s/it]
 79%|███████▉  | 48840/61904 [2:38:21<5:03:39,  1.39s/it]
                                                         
{'loss': 2.3995, 'learning_rate': 1.211720471930507e-07, 'epoch': 12.62}

 79%|███████▉  | 48840/61904 [2:38:21<5:03:39,  1.39s/it]
 79%|███████▉  | 48841/61904 [2:38:22<5:06:32,  1.41s/it]
 79%|███████▉  | 48842/61904 [2:38:24<5:01:59,  1.39s/it]
 79%|███████▉  | 48843/61904 [2:38:25<4:58:54,  1.37s/it]
 79%|███████▉  | 48844/61904 [2:38:27<5:33:24,  1.53s/it]
 79%|███████▉  | 48845/61904 [2:38:28<5:28:53,  1.51s/it]
 79%|███████▉  | 48846/61904 [2:38:30<5:29:51,  1.52s/it]
 79%|███████▉  | 48847/61904 [2:38:31<5:16:23,  1.45s/it]
 79%|███████▉  | 48848/61904 [2:38:33<5:16:41,  1.46s/it]
 79%|███████▉  | 48849/61904 [2:38:34<5:09:43,  1.42s/it]
 79%|███████▉  | 48850/61904 [2:38:36<5:16:15,  1.45s/it]
 79%|███████▉  | 48851/61904 [2:38:37<5:11:26,  1.43s/it]
 79%|███████▉  | 48852/61904 [2:38:38<5:00:53,  1.38s/it]
 79%|███████▉  | 48853/61904 [2:38:40<5:07:36,  1.41s/it]
 79%|███████▉  | 48854/61904 [2:38:41<5:02:36,  1.39s/it]
 79%|███████▉  | 48855/61904 [2:38:42<5:00:43,  1.38s/it]
 79%|███████▉  | 48856/61904 [2:38:44<4:58:19,  1.37s/it]
 79%|███████▉  | 48857/61904 [2:38:45<4:58:14,  1.37s/it]
 79%|███████▉  | 48858/61904 [2:38:47<5:00:15,  1.38s/it]
 79%|███████▉  | 48859/61904 [2:38:48<5:17:06,  1.46s/it]
 79%|███████▉  | 48860/61904 [2:38:50<5:14:18,  1.45s/it]
                                                         
{'loss': 2.4991, 'learning_rate': 1.2113963438350836e-07, 'epoch': 12.63}

 79%|███████▉  | 48860/61904 [2:38:50<5:14:18,  1.45s/it]
 79%|███████▉  | 48861/61904 [2:38:51<5:07:21,  1.41s/it]
 79%|███████▉  | 48862/61904 [2:38:52<5:01:51,  1.39s/it]
 79%|███████▉  | 48863/61904 [2:38:54<4:58:06,  1.37s/it]
 79%|███████▉  | 48864/61904 [2:38:55<4:53:00,  1.35s/it]
 79%|███████▉  | 48865/61904 [2:38:56<4:49:59,  1.33s/it]
 79%|███████▉  | 48866/61904 [2:38:58<4:54:58,  1.36s/it]
 79%|███████▉  | 48867/61904 [2:38:59<5:06:54,  1.41s/it]
 79%|███████▉  | 48868/61904 [2:39:01<5:19:46,  1.47s/it]
 79%|███████▉  | 48869/61904 [2:39:02<5:14:25,  1.45s/it]
 79%|███████▉  | 48870/61904 [2:39:04<5:11:04,  1.43s/it]
 79%|███████▉  | 48871/61904 [2:39:05<5:08:58,  1.42s/it]
 79%|███████▉  | 48872/61904 [2:39:06<5:00:45,  1.38s/it]
 79%|███████▉  | 48873/61904 [2:39:08<5:00:44,  1.38s/it]
 79%|███████▉  | 48874/61904 [2:39:09<4:57:38,  1.37s/it]
 79%|███████▉  | 48875/61904 [2:39:10<5:04:52,  1.40s/it]
 79%|███████▉  | 48876/61904 [2:39:12<4:50:58,  1.34s/it]
 79%|███████▉  | 48877/61904 [2:39:13<4:58:36,  1.38s/it]
 79%|███████▉  | 48878/61904 [2:39:15<4:59:20,  1.38s/it]
 79%|███████▉  | 48879/61904 [2:39:16<4:59:33,  1.38s/it]
 79%|███████▉  | 48880/61904 [2:39:17<4:52:56,  1.35s/it]
                                                         
{'loss': 2.4393, 'learning_rate': 1.2110722157396602e-07, 'epoch': 12.63}

 79%|███████▉  | 48880/61904 [2:39:17<4:52:56,  1.35s/it]
 79%|███████▉  | 48881/61904 [2:39:19<5:04:04,  1.40s/it]
 79%|███████▉  | 48882/61904 [2:39:20<5:02:21,  1.39s/it]
 79%|███████▉  | 48883/61904 [2:39:21<5:02:45,  1.40s/it]
 79%|███████▉  | 48884/61904 [2:39:23<4:55:16,  1.36s/it]
 79%|███████▉  | 48885/61904 [2:39:24<4:53:55,  1.35s/it]
 79%|███████▉  | 48886/61904 [2:39:25<4:54:11,  1.36s/it]
 79%|███████▉  | 48887/61904 [2:39:27<5:02:28,  1.39s/it]
 79%|███████▉  | 48888/61904 [2:39:28<5:03:57,  1.40s/it]
 79%|███████▉  | 48889/61904 [2:39:30<4:55:28,  1.36s/it]
 79%|███████▉  | 48890/61904 [2:39:31<5:08:04,  1.42s/it]
 79%|███████▉  | 48891/61904 [2:39:33<5:03:08,  1.40s/it]
 79%|███████▉  | 48892/61904 [2:39:34<5:05:56,  1.41s/it]
 79%|███████▉  | 48893/61904 [2:39:35<4:55:41,  1.36s/it]
 79%|███████▉  | 48894/61904 [2:39:37<5:05:33,  1.41s/it]
 79%|███████▉  | 48895/61904 [2:39:38<5:04:12,  1.40s/it]
 79%|███████▉  | 48896/61904 [2:39:40<5:14:25,  1.45s/it]
 79%|███████▉  | 48897/61904 [2:39:41<5:17:21,  1.46s/it]
 79%|███████▉  | 48898/61904 [2:39:43<5:10:51,  1.43s/it]
 79%|███████▉  | 48899/61904 [2:39:44<5:11:33,  1.44s/it]
 79%|███████▉  | 48900/61904 [2:39:45<5:06:56,  1.42s/it]
                                                         
{'loss': 2.4266, 'learning_rate': 1.2107480876442369e-07, 'epoch': 12.64}

 79%|███████▉  | 48900/61904 [2:39:45<5:06:56,  1.42s/it]
 79%|███████▉  | 48901/61904 [2:39:47<5:01:04,  1.39s/it]
 79%|███████▉  | 48902/61904 [2:39:48<5:03:04,  1.40s/it]
 79%|███████▉  | 48903/61904 [2:39:50<5:06:44,  1.42s/it]
 79%|███████▉  | 48904/61904 [2:39:51<5:05:27,  1.41s/it]
 79%|███████▉  | 48905/61904 [2:39:52<5:03:01,  1.40s/it]
 79%|███████▉  | 48906/61904 [2:39:54<5:05:15,  1.41s/it]
 79%|███████▉  | 48907/61904 [2:39:55<4:59:34,  1.38s/it]
 79%|███████▉  | 48908/61904 [2:39:56<5:02:15,  1.40s/it]
 79%|███████▉  | 48909/61904 [2:39:58<5:00:40,  1.39s/it]
 79%|███████▉  | 48910/61904 [2:39:59<5:05:07,  1.41s/it]
 79%|███████▉  | 48911/61904 [2:40:01<4:58:16,  1.38s/it]
 79%|███████▉  | 48912/61904 [2:40:02<4:58:47,  1.38s/it]
 79%|███████▉  | 48913/61904 [2:40:04<5:08:58,  1.43s/it]
 79%|███████▉  | 48914/61904 [2:40:05<5:09:12,  1.43s/it]
 79%|███████▉  | 48915/61904 [2:40:06<5:10:42,  1.44s/it]
 79%|███████▉  | 48916/61904 [2:40:08<5:08:18,  1.42s/it]
 79%|███████▉  | 48917/61904 [2:40:09<5:06:27,  1.42s/it]
 79%|███████▉  | 48918/61904 [2:40:11<5:06:43,  1.42s/it]
 79%|███████▉  | 48919/61904 [2:40:12<5:10:12,  1.43s/it]
 79%|███████▉  | 48920/61904 [2:40:14<5:10:26,  1.43s/it]
                                                         
{'loss': 2.4504, 'learning_rate': 1.2104239595488135e-07, 'epoch': 12.64}

 79%|███████▉  | 48920/61904 [2:40:14<5:10:26,  1.43s/it]
 79%|███████▉  | 48921/61904 [2:40:15<5:02:59,  1.40s/it]
 79%|███████▉  | 48922/61904 [2:40:16<4:57:11,  1.37s/it]
 79%|███████▉  | 48923/61904 [2:40:18<4:58:03,  1.38s/it]
 79%|███████▉  | 48924/61904 [2:40:19<4:53:30,  1.36s/it]
 79%|███████▉  | 48925/61904 [2:40:20<4:47:50,  1.33s/it]
 79%|███████▉  | 48926/61904 [2:40:22<4:50:28,  1.34s/it]
 79%|███████▉  | 48927/61904 [2:40:23<4:46:29,  1.32s/it]
 79%|███████▉  | 48928/61904 [2:40:24<4:48:55,  1.34s/it]
 79%|███████▉  | 48929/61904 [2:40:26<4:55:03,  1.36s/it]
 79%|███████▉  | 48930/61904 [2:40:27<4:57:06,  1.37s/it]
 79%|███████▉  | 48931/61904 [2:40:28<5:01:40,  1.40s/it]
 79%|███████▉  | 48932/61904 [2:40:30<4:57:05,  1.37s/it]
 79%|███████▉  | 48933/61904 [2:40:31<4:56:09,  1.37s/it]
 79%|███████▉  | 48934/61904 [2:40:33<5:02:14,  1.40s/it]
 79%|███████▉  | 48935/61904 [2:40:34<5:08:08,  1.43s/it]
 79%|███████▉  | 48936/61904 [2:40:35<5:04:52,  1.41s/it]
 79%|███████▉  | 48937/61904 [2:40:37<5:04:52,  1.41s/it]
 79%|███████▉  | 48938/61904 [2:40:38<4:57:30,  1.38s/it]
 79%|███████▉  | 48939/61904 [2:40:40<4:57:01,  1.37s/it]
 79%|███████▉  | 48940/61904 [2:40:41<5:01:08,  1.39s/it]
                                                         
{'loss': 2.4426, 'learning_rate': 1.2100998314533904e-07, 'epoch': 12.65}

 79%|███████▉  | 48940/61904 [2:40:41<5:01:08,  1.39s/it]
 79%|███████▉  | 48941/61904 [2:40:42<5:04:48,  1.41s/it]
 79%|███████▉  | 48942/61904 [2:40:44<5:00:41,  1.39s/it]
 79%|███████▉  | 48943/61904 [2:40:45<4:59:27,  1.39s/it]
 79%|███████▉  | 48944/61904 [2:40:47<5:08:06,  1.43s/it]
 79%|███████▉  | 48945/61904 [2:40:48<5:05:22,  1.41s/it]
 79%|███████▉  | 48946/61904 [2:40:50<5:12:13,  1.45s/it]
 79%|███████▉  | 48947/61904 [2:40:51<5:06:10,  1.42s/it]
 79%|███████▉  | 48948/61904 [2:40:52<5:06:15,  1.42s/it]
 79%|███████▉  | 48949/61904 [2:40:54<5:09:55,  1.44s/it]
 79%|███████▉  | 48950/61904 [2:40:55<5:04:40,  1.41s/it]
 79%|███████▉  | 48951/61904 [2:40:57<4:59:47,  1.39s/it]
 79%|███████▉  | 48952/61904 [2:40:58<4:55:56,  1.37s/it]
 79%|███████▉  | 48953/61904 [2:40:59<5:14:10,  1.46s/it]
 79%|███████▉  | 48954/61904 [2:41:01<5:03:05,  1.40s/it]
 79%|███████▉  | 48955/61904 [2:41:02<4:55:29,  1.37s/it]
 79%|███████▉  | 48956/61904 [2:41:04<5:01:26,  1.40s/it]
 79%|███████▉  | 48957/61904 [2:41:05<4:56:36,  1.37s/it]
 79%|███████▉  | 48958/61904 [2:41:06<5:01:49,  1.40s/it]
 79%|███████▉  | 48959/61904 [2:41:08<4:56:32,  1.37s/it]
 79%|███████▉  | 48960/61904 [2:41:09<4:56:47,  1.38s/it]
                                                         
{'loss': 2.4279, 'learning_rate': 1.209775703357967e-07, 'epoch': 12.65}

 79%|███████▉  | 48960/61904 [2:41:09<4:56:47,  1.38s/it]
 79%|███████▉  | 48961/61904 [2:41:10<4:59:06,  1.39s/it]
 79%|███████▉  | 48962/61904 [2:41:12<4:59:25,  1.39s/it]
 79%|███████▉  | 48963/61904 [2:41:13<5:17:25,  1.47s/it]
 79%|███████▉  | 48964/61904 [2:41:15<5:01:23,  1.40s/it]
 79%|███████▉  | 48965/61904 [2:41:16<5:03:03,  1.41s/it]
 79%|███████▉  | 48966/61904 [2:41:18<5:05:36,  1.42s/it]
 79%|███████▉  | 48967/61904 [2:41:19<4:56:30,  1.38s/it]
 79%|███████▉  | 48968/61904 [2:41:20<4:51:37,  1.35s/it]
 79%|███████▉  | 48969/61904 [2:41:22<4:58:21,  1.38s/it]
 79%|███████▉  | 48970/61904 [2:41:23<4:58:56,  1.39s/it]
 79%|███████▉  | 48971/61904 [2:41:25<5:11:31,  1.45s/it]
 79%|███████▉  | 48972/61904 [2:41:26<5:12:06,  1.45s/it]
 79%|███████▉  | 48973/61904 [2:41:27<5:10:09,  1.44s/it]
 79%|███████▉  | 48974/61904 [2:41:29<5:07:34,  1.43s/it]
 79%|███████▉  | 48975/61904 [2:41:30<5:03:36,  1.41s/it]
 79%|███████▉  | 48976/61904 [2:41:32<4:57:01,  1.38s/it]
 79%|███████▉  | 48977/61904 [2:41:33<4:48:46,  1.34s/it]
 79%|███████▉  | 48978/61904 [2:41:34<4:46:49,  1.33s/it]
 79%|███████▉  | 48979/61904 [2:41:35<4:42:53,  1.31s/it]
 79%|███████▉  | 48980/61904 [2:41:37<4:56:12,  1.38s/it]
                                                         
{'loss': 2.4973, 'learning_rate': 1.2094515752625436e-07, 'epoch': 12.66}

 79%|███████▉  | 48980/61904 [2:41:37<4:56:12,  1.38s/it]
 79%|███████▉  | 48981/61904 [2:41:38<5:00:18,  1.39s/it]
 79%|███████▉  | 48982/61904 [2:41:40<5:02:47,  1.41s/it]
 79%|███████▉  | 48983/61904 [2:41:41<4:59:42,  1.39s/it]
 79%|███████▉  | 48984/61904 [2:41:42<4:57:20,  1.38s/it]
 79%|███████▉  | 48985/61904 [2:41:44<5:00:51,  1.40s/it]
 79%|███████▉  | 48986/61904 [2:41:45<4:59:33,  1.39s/it]
 79%|███████▉  | 48987/61904 [2:41:47<5:03:20,  1.41s/it]
 79%|███████▉  | 48988/61904 [2:41:48<5:02:39,  1.41s/it]
 79%|███████▉  | 48989/61904 [2:41:49<4:51:42,  1.36s/it]
 79%|███████▉  | 48990/61904 [2:41:51<4:51:04,  1.35s/it]
 79%|███████▉  | 48991/61904 [2:41:52<4:49:28,  1.35s/it]
 79%|███████▉  | 48992/61904 [2:41:53<4:46:09,  1.33s/it]
 79%|███████▉  | 48993/61904 [2:41:55<4:41:37,  1.31s/it]
 79%|███████▉  | 48994/61904 [2:41:56<4:44:53,  1.32s/it]
 79%|███████▉  | 48995/61904 [2:41:57<4:41:22,  1.31s/it]
 79%|███████▉  | 48996/61904 [2:41:59<4:47:20,  1.34s/it]
 79%|███████▉  | 48997/61904 [2:42:00<4:55:17,  1.37s/it]
 79%|███████▉  | 48998/61904 [2:42:01<4:58:27,  1.39s/it]
 79%|███████▉  | 48999/61904 [2:42:03<5:07:30,  1.43s/it]
 79%|███████▉  | 49000/61904 [2:42:04<5:03:15,  1.41s/it]
                                                         
{'loss': 2.4447, 'learning_rate': 1.2091274471671205e-07, 'epoch': 12.66}

 79%|███████▉  | 49000/61904 [2:42:04<5:03:15,  1.41s/it]
 79%|███████▉  | 49001/61904 [2:42:06<4:59:25,  1.39s/it]
 79%|███████▉  | 49002/61904 [2:42:07<5:05:05,  1.42s/it]
 79%|███████▉  | 49003/61904 [2:42:09<5:15:39,  1.47s/it]
 79%|███████▉  | 49004/61904 [2:42:10<5:02:22,  1.41s/it]
 79%|███████▉  | 49005/61904 [2:42:11<4:56:25,  1.38s/it]
 79%|███████▉  | 49006/61904 [2:42:13<4:58:12,  1.39s/it]
 79%|███████▉  | 49007/61904 [2:42:14<4:50:27,  1.35s/it]
 79%|███████▉  | 49008/61904 [2:42:15<4:49:02,  1.34s/it]
 79%|███████▉  | 49009/61904 [2:42:17<4:44:42,  1.32s/it]
 79%|███████▉  | 49010/61904 [2:42:18<4:44:14,  1.32s/it]
 79%|███████▉  | 49011/61904 [2:42:19<4:50:53,  1.35s/it]
 79%|███████▉  | 49012/61904 [2:42:21<4:56:39,  1.38s/it]
 79%|███████▉  | 49013/61904 [2:42:22<4:55:22,  1.37s/it]
 79%|███████▉  | 49014/61904 [2:42:24<5:02:13,  1.41s/it]
 79%|███████▉  | 49015/61904 [2:42:25<5:02:29,  1.41s/it]
 79%|███████▉  | 49016/61904 [2:42:27<5:07:35,  1.43s/it]
 79%|███████▉  | 49017/61904 [2:42:28<4:57:23,  1.38s/it]
 79%|███████▉  | 49018/61904 [2:42:29<5:04:12,  1.42s/it]
 79%|███████▉  | 49019/61904 [2:42:31<4:59:14,  1.39s/it]
 79%|███████▉  | 49020/61904 [2:42:32<4:52:14,  1.36s/it]
                                                         
{'loss': 2.497, 'learning_rate': 1.208803319071697e-07, 'epoch': 12.67}

 79%|███████▉  | 49020/61904 [2:42:32<4:52:14,  1.36s/it]
 79%|███████▉  | 49021/61904 [2:42:33<4:55:54,  1.38s/it]
 79%|███████▉  | 49022/61904 [2:42:35<4:50:10,  1.35s/it]
 79%|███████▉  | 49023/61904 [2:42:36<4:58:37,  1.39s/it]
 79%|███████▉  | 49024/61904 [2:42:38<5:13:05,  1.46s/it]
 79%|███████▉  | 49025/61904 [2:42:39<5:07:49,  1.43s/it]
 79%|███████▉  | 49026/61904 [2:42:40<5:00:14,  1.40s/it]
 79%|███████▉  | 49027/61904 [2:42:42<5:04:06,  1.42s/it]
 79%|███████▉  | 49028/61904 [2:42:43<5:04:09,  1.42s/it]
 79%|███████▉  | 49029/61904 [2:42:45<5:03:35,  1.41s/it]
 79%|███████▉  | 49030/61904 [2:42:46<5:06:31,  1.43s/it]
 79%|███████▉  | 49031/61904 [2:42:48<5:02:15,  1.41s/it]
 79%|███████▉  | 49032/61904 [2:42:49<4:55:58,  1.38s/it]
 79%|███████▉  | 49033/61904 [2:42:50<4:52:40,  1.36s/it]
 79%|███████▉  | 49034/61904 [2:42:52<4:54:28,  1.37s/it]
 79%|███████▉  | 49035/61904 [2:42:53<4:58:41,  1.39s/it]
 79%|███████▉  | 49036/61904 [2:42:54<4:50:05,  1.35s/it]
 79%|███████▉  | 49037/61904 [2:42:56<4:45:56,  1.33s/it]
 79%|███████▉  | 49038/61904 [2:42:57<4:47:31,  1.34s/it]
 79%|███████▉  | 49039/61904 [2:42:58<4:50:50,  1.36s/it]
 79%|███████▉  | 49040/61904 [2:43:00<4:57:48,  1.39s/it]
                                                         
{'loss': 2.4223, 'learning_rate': 1.2084791909762737e-07, 'epoch': 12.67}

 79%|███████▉  | 49040/61904 [2:43:00<4:57:48,  1.39s/it]
 79%|███████▉  | 49041/61904 [2:43:01<4:54:38,  1.37s/it]
 79%|███████▉  | 49042/61904 [2:43:03<5:03:57,  1.42s/it]
 79%|███████▉  | 49043/61904 [2:43:04<4:56:50,  1.38s/it]
 79%|███████▉  | 49044/61904 [2:43:05<4:59:52,  1.40s/it]
 79%|███████▉  | 49045/61904 [2:43:07<5:04:15,  1.42s/it]
 79%|███████▉  | 49046/61904 [2:43:08<5:06:29,  1.43s/it]
 79%|███████▉  | 49047/61904 [2:43:10<4:57:57,  1.39s/it]
 79%|███████▉  | 49048/61904 [2:43:11<4:59:41,  1.40s/it]
 79%|███████▉  | 49049/61904 [2:43:12<4:54:01,  1.37s/it]
 79%|███████▉  | 49050/61904 [2:43:14<5:03:45,  1.42s/it]
 79%|███████▉  | 49051/61904 [2:43:15<4:58:32,  1.39s/it]
 79%|███████▉  | 49052/61904 [2:43:17<4:57:56,  1.39s/it]
 79%|███████▉  | 49053/61904 [2:43:18<5:11:26,  1.45s/it]
 79%|███████▉  | 49054/61904 [2:43:20<5:14:57,  1.47s/it]
 79%|███████▉  | 49055/61904 [2:43:21<5:04:06,  1.42s/it]
 79%|███████▉  | 49056/61904 [2:43:22<5:06:33,  1.43s/it]
 79%|███████▉  | 49057/61904 [2:43:24<5:00:18,  1.40s/it]
 79%|███████▉  | 49058/61904 [2:43:25<4:59:11,  1.40s/it]
 79%|███████▉  | 49059/61904 [2:43:27<4:56:46,  1.39s/it]
 79%|███████▉  | 49060/61904 [2:43:28<4:47:43,  1.34s/it]
                                                         
{'loss': 2.447, 'learning_rate': 1.2081550628808503e-07, 'epoch': 12.68}

 79%|███████▉  | 49060/61904 [2:43:28<4:47:43,  1.34s/it]
 79%|███████▉  | 49061/61904 [2:43:29<4:46:21,  1.34s/it]
 79%|███████▉  | 49062/61904 [2:43:30<4:46:03,  1.34s/it]
 79%|███████▉  | 49063/61904 [2:43:32<4:51:47,  1.36s/it]
 79%|███████▉  | 49064/61904 [2:43:33<4:51:23,  1.36s/it]
 79%|███████▉  | 49065/61904 [2:43:35<5:01:07,  1.41s/it]
 79%|███████▉  | 49066/61904 [2:43:36<4:52:41,  1.37s/it]
 79%|███████▉  | 49067/61904 [2:43:37<4:54:22,  1.38s/it]
 79%|███████▉  | 49068/61904 [2:43:39<4:54:47,  1.38s/it]
 79%|███████▉  | 49069/61904 [2:43:40<4:59:34,  1.40s/it]
 79%|███████▉  | 49070/61904 [2:43:42<5:00:41,  1.41s/it]
 79%|███████▉  | 49071/61904 [2:43:43<5:03:57,  1.42s/it]
 79%|███████▉  | 49072/61904 [2:43:45<5:03:32,  1.42s/it]
 79%|███████▉  | 49073/61904 [2:43:46<5:07:13,  1.44s/it]
 79%|███████▉  | 49074/61904 [2:43:47<4:59:25,  1.40s/it]
 79%|███████▉  | 49075/61904 [2:43:49<5:06:54,  1.44s/it]
 79%|███████▉  | 49076/61904 [2:43:50<5:02:40,  1.42s/it]
 79%|███████▉  | 49077/61904 [2:43:51<4:50:00,  1.36s/it]
 79%|███████▉  | 49078/61904 [2:43:53<4:47:18,  1.34s/it]
 79%|███████▉  | 49079/61904 [2:43:54<4:44:17,  1.33s/it]
 79%|███████▉  | 49080/61904 [2:43:55<4:43:45,  1.33s/it]
                                                         
{'loss': 2.4652, 'learning_rate': 1.2078309347854272e-07, 'epoch': 12.69}

 79%|███████▉  | 49080/61904 [2:43:55<4:43:45,  1.33s/it]
 79%|███████▉  | 49081/61904 [2:43:57<4:38:48,  1.30s/it]
 79%|███████▉  | 49082/61904 [2:43:58<4:41:39,  1.32s/it]
 79%|███████▉  | 49083/61904 [2:43:59<4:41:38,  1.32s/it]
 79%|███████▉  | 49084/61904 [2:44:01<4:46:52,  1.34s/it]
 79%|███████▉  | 49085/61904 [2:44:02<4:52:42,  1.37s/it]
 79%|███████▉  | 49086/61904 [2:44:03<4:46:24,  1.34s/it]
 79%|███████▉  | 49087/61904 [2:44:05<4:47:48,  1.35s/it]
 79%|███████▉  | 49088/61904 [2:44:06<4:53:10,  1.37s/it]
 79%|███████▉  | 49089/61904 [2:44:08<4:58:36,  1.40s/it]
 79%|███████▉  | 49090/61904 [2:44:09<4:54:16,  1.38s/it]
 79%|███████▉  | 49091/61904 [2:44:10<4:57:04,  1.39s/it]
 79%|███████▉  | 49092/61904 [2:44:12<4:57:00,  1.39s/it]
 79%|███████▉  | 49093/61904 [2:44:13<5:03:42,  1.42s/it]
 79%|███████▉  | 49094/61904 [2:44:15<5:00:20,  1.41s/it]
 79%|███████▉  | 49095/61904 [2:44:16<4:57:44,  1.39s/it]
 79%|███████▉  | 49096/61904 [2:44:17<4:51:15,  1.36s/it]
 79%|███████▉  | 49097/61904 [2:44:19<4:45:33,  1.34s/it]
 79%|███████▉  | 49098/61904 [2:44:20<4:47:36,  1.35s/it]
 79%|███████▉  | 49099/61904 [2:44:21<4:44:05,  1.33s/it]
 79%|███████▉  | 49100/61904 [2:44:23<4:45:49,  1.34s/it]
                                                         
{'loss': 2.4167, 'learning_rate': 1.2075068066900038e-07, 'epoch': 12.69}

 79%|███████▉  | 49100/61904 [2:44:23<4:45:49,  1.34s/it]
 79%|███████▉  | 49101/61904 [2:44:24<4:43:01,  1.33s/it]
 79%|███████▉  | 49102/61904 [2:44:25<4:42:32,  1.32s/it]
 79%|███████▉  | 49103/61904 [2:44:27<4:49:59,  1.36s/it]
 79%|███████▉  | 49104/61904 [2:44:28<4:56:01,  1.39s/it]
 79%|███████▉  | 49105/61904 [2:44:30<4:55:09,  1.38s/it]
 79%|███████▉  | 49106/61904 [2:44:31<4:45:09,  1.34s/it]
 79%|███████▉  | 49107/61904 [2:44:32<4:47:19,  1.35s/it]
 79%|███████▉  | 49108/61904 [2:44:33<4:48:41,  1.35s/it]
 79%|███████▉  | 49109/61904 [2:44:35<4:59:22,  1.40s/it]
 79%|███████▉  | 49110/61904 [2:44:36<4:50:54,  1.36s/it]
 79%|███████▉  | 49111/61904 [2:44:38<4:51:32,  1.37s/it]
 79%|███████▉  | 49112/61904 [2:44:39<4:48:02,  1.35s/it]
 79%|███████▉  | 49113/61904 [2:44:40<4:43:55,  1.33s/it]
 79%|███████▉  | 49114/61904 [2:44:42<4:45:29,  1.34s/it]
 79%|███████▉  | 49115/61904 [2:44:43<4:51:58,  1.37s/it]
 79%|███████▉  | 49116/61904 [2:44:44<4:54:01,  1.38s/it]
 79%|███████▉  | 49117/61904 [2:44:46<4:56:05,  1.39s/it]
 79%|███████▉  | 49118/61904 [2:44:47<4:54:17,  1.38s/it]
 79%|███████▉  | 49119/61904 [2:44:49<5:01:12,  1.41s/it]
 79%|███████▉  | 49120/61904 [2:44:50<4:56:11,  1.39s/it]
                                                         
{'loss': 2.4103, 'learning_rate': 1.2071826785945805e-07, 'epoch': 12.7}

 79%|███████▉  | 49120/61904 [2:44:50<4:56:11,  1.39s/it]
 79%|███████▉  | 49121/61904 [2:44:51<4:51:19,  1.37s/it]
 79%|███████▉  | 49122/61904 [2:44:53<4:44:32,  1.34s/it]
 79%|███████▉  | 49123/61904 [2:44:54<4:41:45,  1.32s/it]
 79%|███████▉  | 49124/61904 [2:44:55<4:44:06,  1.33s/it]
 79%|███████▉  | 49125/61904 [2:44:57<4:40:16,  1.32s/it]
 79%|███████▉  | 49126/61904 [2:44:58<4:40:01,  1.31s/it]
 79%|███████▉  | 49127/61904 [2:44:59<4:43:51,  1.33s/it]
 79%|███████▉  | 49128/61904 [2:45:01<4:50:06,  1.36s/it]
 79%|███████▉  | 49129/61904 [2:45:02<4:49:19,  1.36s/it]
 79%|███████▉  | 49130/61904 [2:45:03<4:50:18,  1.36s/it]
 79%|███████▉  | 49131/61904 [2:45:05<4:55:22,  1.39s/it]
 79%|███████▉  | 49132/61904 [2:45:06<4:57:47,  1.40s/it]
 79%|███████▉  | 49133/61904 [2:45:08<4:58:05,  1.40s/it]
 79%|███████▉  | 49134/61904 [2:45:09<4:50:35,  1.37s/it]
 79%|███████▉  | 49135/61904 [2:45:10<4:55:41,  1.39s/it]
 79%|███████▉  | 49136/61904 [2:45:12<4:53:41,  1.38s/it]
 79%|███████▉  | 49137/61904 [2:45:13<5:02:58,  1.42s/it]
 79%|███████▉  | 49138/61904 [2:45:15<5:06:23,  1.44s/it]
 79%|███████▉  | 49139/61904 [2:45:16<5:00:03,  1.41s/it]
 79%|███████▉  | 49140/61904 [2:45:17<4:50:23,  1.37s/it]
                                                         
{'loss': 2.4225, 'learning_rate': 1.206858550499157e-07, 'epoch': 12.7}

 79%|███████▉  | 49140/61904 [2:45:17<4:50:23,  1.37s/it]
 79%|███████▉  | 49141/61904 [2:45:19<4:43:17,  1.33s/it]
 79%|███████▉  | 49142/61904 [2:45:20<4:54:28,  1.38s/it]
 79%|███████▉  | 49143/61904 [2:45:22<5:02:36,  1.42s/it]
 79%|███████▉  | 49144/61904 [2:45:23<4:58:59,  1.41s/it]
 79%|███████▉  | 49145/61904 [2:45:24<4:51:35,  1.37s/it]
 79%|███████▉  | 49146/61904 [2:45:26<4:49:52,  1.36s/it]
 79%|███████▉  | 49147/61904 [2:45:27<4:50:08,  1.36s/it]
 79%|███████▉  | 49148/61904 [2:45:28<4:41:19,  1.32s/it]
 79%|███████▉  | 49149/61904 [2:45:30<5:00:38,  1.41s/it]
 79%|███████▉  | 49150/61904 [2:45:31<5:02:17,  1.42s/it]
 79%|███████▉  | 49151/61904 [2:45:33<4:56:48,  1.40s/it]
 79%|███████▉  | 49152/61904 [2:45:34<4:52:07,  1.37s/it]
 79%|███████▉  | 49153/61904 [2:45:35<4:58:21,  1.40s/it]
 79%|███████▉  | 49154/61904 [2:45:37<4:55:36,  1.39s/it]
 79%|███████▉  | 49155/61904 [2:45:38<5:00:14,  1.41s/it]
 79%|███████▉  | 49156/61904 [2:45:40<5:09:56,  1.46s/it]
 79%|███████▉  | 49157/61904 [2:45:41<4:57:56,  1.40s/it]
 79%|███████▉  | 49158/61904 [2:45:43<5:04:16,  1.43s/it]
 79%|███████▉  | 49159/61904 [2:45:44<5:04:00,  1.43s/it]
 79%|███████▉  | 49160/61904 [2:45:45<4:59:56,  1.41s/it]
                                                         
{'loss': 2.4668, 'learning_rate': 1.206534422403734e-07, 'epoch': 12.71}

 79%|███████▉  | 49160/61904 [2:45:45<4:59:56,  1.41s/it]
 79%|███████▉  | 49161/61904 [2:45:47<5:00:44,  1.42s/it]
 79%|███████▉  | 49162/61904 [2:45:48<4:56:09,  1.39s/it]
 79%|███████▉  | 49163/61904 [2:45:49<4:50:17,  1.37s/it]
 79%|███████▉  | 49164/61904 [2:45:51<4:51:36,  1.37s/it]
 79%|███████▉  | 49165/61904 [2:45:52<4:50:14,  1.37s/it]
 79%|███████▉  | 49166/61904 [2:45:54<4:48:18,  1.36s/it]
 79%|███████▉  | 49167/61904 [2:45:55<4:39:09,  1.32s/it]
 79%|███████▉  | 49168/61904 [2:45:56<4:44:45,  1.34s/it]
 79%|███████▉  | 49169/61904 [2:45:57<4:35:47,  1.30s/it]
 79%|███████▉  | 49170/61904 [2:45:59<4:40:05,  1.32s/it]
 79%|███████▉  | 49171/61904 [2:46:00<4:43:42,  1.34s/it]
 79%|███████▉  | 49172/61904 [2:46:02<4:51:13,  1.37s/it]
 79%|███████▉  | 49173/61904 [2:46:03<5:01:04,  1.42s/it]
 79%|███████▉  | 49174/61904 [2:46:04<4:52:26,  1.38s/it]
 79%|███████▉  | 49175/61904 [2:46:06<4:45:17,  1.34s/it]
 79%|███████▉  | 49176/61904 [2:46:07<4:45:38,  1.35s/it]
 79%|███████▉  | 49177/61904 [2:46:08<4:52:52,  1.38s/it]
 79%|███████▉  | 49178/61904 [2:46:10<5:05:57,  1.44s/it]
 79%|███████▉  | 49179/61904 [2:46:11<4:56:16,  1.40s/it]
 79%|███████▉  | 49180/61904 [2:46:13<4:58:57,  1.41s/it]
                                                         
{'loss': 2.4861, 'learning_rate': 1.2062102943083106e-07, 'epoch': 12.71}

 79%|███████▉  | 49180/61904 [2:46:13<4:58:57,  1.41s/it]
 79%|███████▉  | 49181/61904 [2:46:14<5:01:27,  1.42s/it]
 79%|███████▉  | 49182/61904 [2:46:16<4:58:15,  1.41s/it]
 79%|███████▉  | 49183/61904 [2:46:17<4:51:38,  1.38s/it]
 79%|███████▉  | 49184/61904 [2:46:18<4:51:18,  1.37s/it]
 79%|███████▉  | 49185/61904 [2:46:20<4:58:27,  1.41s/it]
 79%|███████▉  | 49186/61904 [2:46:21<4:51:41,  1.38s/it]
 79%|███████▉  | 49187/61904 [2:46:23<4:58:34,  1.41s/it]
 79%|███████▉  | 49188/61904 [2:46:24<5:05:53,  1.44s/it]
 79%|███████▉  | 49189/61904 [2:46:25<4:59:33,  1.41s/it]
 79%|███████▉  | 49190/61904 [2:46:27<5:04:02,  1.43s/it]
 79%|███████▉  | 49191/61904 [2:46:28<4:55:11,  1.39s/it]
 79%|███████▉  | 49192/61904 [2:46:30<5:03:43,  1.43s/it]
 79%|███████▉  | 49193/61904 [2:46:31<4:51:13,  1.37s/it]
 79%|███████▉  | 49194/61904 [2:46:32<4:56:57,  1.40s/it]
 79%|███████▉  | 49195/61904 [2:46:34<4:50:52,  1.37s/it]
 79%|███████▉  | 49196/61904 [2:46:35<4:52:56,  1.38s/it]
 79%|███████▉  | 49197/61904 [2:46:37<4:54:38,  1.39s/it]
 79%|███████▉  | 49198/61904 [2:46:38<5:09:08,  1.46s/it]
 79%|███████▉  | 49199/61904 [2:46:40<5:04:29,  1.44s/it]
 79%|███████▉  | 49200/61904 [2:46:41<5:01:58,  1.43s/it]
                                                         
{'loss': 2.433, 'learning_rate': 1.2058861662128872e-07, 'epoch': 12.72}

 79%|███████▉  | 49200/61904 [2:46:41<5:01:58,  1.43s/it]
 79%|███████▉  | 49201/61904 [2:46:42<5:00:51,  1.42s/it]
 79%|███████▉  | 49202/61904 [2:46:44<5:13:50,  1.48s/it]
 79%|███████▉  | 49203/61904 [2:46:45<5:03:54,  1.44s/it]
 79%|███████▉  | 49204/61904 [2:46:47<5:02:38,  1.43s/it]
 79%|███████▉  | 49205/61904 [2:46:48<4:55:37,  1.40s/it]
 79%|███████▉  | 49206/61904 [2:46:49<4:52:20,  1.38s/it]
 79%|███████▉  | 49207/61904 [2:46:51<4:58:41,  1.41s/it]
 79%|███████▉  | 49208/61904 [2:46:52<4:52:58,  1.38s/it]
 79%|███████▉  | 49209/61904 [2:46:54<4:53:35,  1.39s/it]
 79%|███████▉  | 49210/61904 [2:46:55<5:01:38,  1.43s/it]
 79%|███████▉  | 49211/61904 [2:46:56<4:50:56,  1.38s/it]
 79%|███████▉  | 49212/61904 [2:46:58<4:54:44,  1.39s/it]
 79%|███████▉  | 49213/61904 [2:46:59<4:51:08,  1.38s/it]
 80%|███████▉  | 49214/61904 [2:47:01<4:52:26,  1.38s/it]
 80%|███████▉  | 49215/61904 [2:47:02<4:56:54,  1.40s/it]
 80%|███████▉  | 49216/61904 [2:47:03<4:54:02,  1.39s/it]
 80%|███████▉  | 49217/61904 [2:47:05<4:56:01,  1.40s/it]
 80%|███████▉  | 49218/61904 [2:47:06<4:53:41,  1.39s/it]
 80%|███████▉  | 49219/61904 [2:47:08<4:57:17,  1.41s/it]
 80%|███████▉  | 49220/61904 [2:47:09<4:57:00,  1.40s/it]
                                                         
{'loss': 2.4395, 'learning_rate': 1.205562038117464e-07, 'epoch': 12.72}

 80%|███████▉  | 49220/61904 [2:47:09<4:57:00,  1.40s/it]
 80%|███████▉  | 49221/61904 [2:47:10<4:58:05,  1.41s/it]
 80%|███████▉  | 49222/61904 [2:47:12<4:55:01,  1.40s/it]
 80%|███████▉  | 49223/61904 [2:47:13<4:51:00,  1.38s/it]
 80%|███████▉  | 49224/61904 [2:47:15<4:57:39,  1.41s/it]
 80%|███████▉  | 49225/61904 [2:47:16<4:55:52,  1.40s/it]
 80%|███████▉  | 49226/61904 [2:47:17<4:47:17,  1.36s/it]
 80%|███████▉  | 49227/61904 [2:47:19<4:43:50,  1.34s/it]
 80%|███████▉  | 49228/61904 [2:47:20<4:44:36,  1.35s/it]
 80%|███████▉  | 49229/61904 [2:47:21<4:40:27,  1.33s/it]
 80%|███████▉  | 49230/61904 [2:47:23<4:42:58,  1.34s/it]
 80%|███████▉  | 49231/61904 [2:47:24<4:44:50,  1.35s/it]
 80%|███████▉  | 49232/61904 [2:47:25<4:48:29,  1.37s/it]
 80%|███████▉  | 49233/61904 [2:47:27<4:45:49,  1.35s/it]
 80%|███████▉  | 49234/61904 [2:47:28<4:51:56,  1.38s/it]
 80%|███████▉  | 49235/61904 [2:47:30<4:54:02,  1.39s/it]
 80%|███████▉  | 49236/61904 [2:47:31<4:46:51,  1.36s/it]
 80%|███████▉  | 49237/61904 [2:47:32<5:05:15,  1.45s/it]
 80%|███████▉  | 49238/61904 [2:47:34<4:52:28,  1.39s/it]
 80%|███████▉  | 49239/61904 [2:47:35<4:49:01,  1.37s/it]
 80%|███████▉  | 49240/61904 [2:47:36<4:42:35,  1.34s/it]
                                                         
{'loss': 2.4702, 'learning_rate': 1.2052379100220407e-07, 'epoch': 12.73}

 80%|███████▉  | 49240/61904 [2:47:36<4:42:35,  1.34s/it]
 80%|███████▉  | 49241/61904 [2:47:38<4:38:07,  1.32s/it]
 80%|███████▉  | 49242/61904 [2:47:39<4:49:45,  1.37s/it]
 80%|███████▉  | 49243/61904 [2:47:40<4:42:28,  1.34s/it]
 80%|███████▉  | 49244/61904 [2:47:42<4:43:05,  1.34s/it]
 80%|███████▉  | 49245/61904 [2:47:43<4:45:33,  1.35s/it]
 80%|███████▉  | 49246/61904 [2:47:44<4:50:02,  1.37s/it]
 80%|███████▉  | 49247/61904 [2:47:46<4:49:05,  1.37s/it]
 80%|███████▉  | 49248/61904 [2:47:47<4:48:29,  1.37s/it]
 80%|███████▉  | 49249/61904 [2:47:49<4:49:25,  1.37s/it]
 80%|███████▉  | 49250/61904 [2:47:50<4:56:29,  1.41s/it]
 80%|███████▉  | 49251/61904 [2:47:51<4:43:25,  1.34s/it]
 80%|███████▉  | 49252/61904 [2:47:53<4:43:31,  1.34s/it]
 80%|███████▉  | 49253/61904 [2:47:54<4:50:18,  1.38s/it]
 80%|███████▉  | 49254/61904 [2:47:55<4:48:21,  1.37s/it]
 80%|███████▉  | 49255/61904 [2:47:57<4:44:53,  1.35s/it]
 80%|███████▉  | 49256/61904 [2:47:58<4:57:28,  1.41s/it]
 80%|███████▉  | 49257/61904 [2:48:00<4:49:11,  1.37s/it]
 80%|███████▉  | 49258/61904 [2:48:01<4:58:16,  1.42s/it]
 80%|███████▉  | 49259/61904 [2:48:02<4:50:06,  1.38s/it]
 80%|███████▉  | 49260/61904 [2:48:04<4:47:44,  1.37s/it]
                                                         
{'loss': 2.4585, 'learning_rate': 1.2049137819266173e-07, 'epoch': 12.73}

 80%|███████▉  | 49260/61904 [2:48:04<4:47:44,  1.37s/it]
 80%|███████▉  | 49261/61904 [2:48:05<4:47:46,  1.37s/it]
 80%|███████▉  | 49262/61904 [2:48:06<4:47:48,  1.37s/it]
 80%|███████▉  | 49263/61904 [2:48:08<4:47:20,  1.36s/it]
 80%|███████▉  | 49264/61904 [2:48:09<4:46:02,  1.36s/it]
 80%|███████▉  | 49265/61904 [2:48:11<4:59:48,  1.42s/it]
 80%|███████▉  | 49266/61904 [2:48:12<4:56:26,  1.41s/it]
 80%|███████▉  | 49267/61904 [2:48:13<4:48:32,  1.37s/it]
 80%|███████▉  | 49268/61904 [2:48:15<4:46:09,  1.36s/it]
 80%|███████▉  | 49269/61904 [2:48:16<4:46:13,  1.36s/it]
 80%|███████▉  | 49270/61904 [2:48:17<4:44:05,  1.35s/it]
 80%|███████▉  | 49271/61904 [2:48:19<4:48:44,  1.37s/it]
 80%|███████▉  | 49272/61904 [2:48:20<4:43:38,  1.35s/it]
 80%|███████▉  | 49273/61904 [2:48:22<5:05:08,  1.45s/it]
 80%|███████▉  | 49274/61904 [2:48:23<5:06:18,  1.46s/it]
 80%|███████▉  | 49275/61904 [2:48:25<5:03:59,  1.44s/it]
 80%|███████▉  | 49276/61904 [2:48:26<4:53:18,  1.39s/it]
 80%|███████▉  | 49277/61904 [2:48:27<4:46:45,  1.36s/it]
 80%|███████▉  | 49278/61904 [2:48:29<4:54:35,  1.40s/it]
 80%|███████▉  | 49279/61904 [2:48:30<4:57:49,  1.42s/it]
 80%|███████▉  | 49280/61904 [2:48:32<5:09:48,  1.47s/it]
                                                         
{'loss': 2.414, 'learning_rate': 1.204589653831194e-07, 'epoch': 12.74}

 80%|███████▉  | 49280/61904 [2:48:32<5:09:48,  1.47s/it]
 80%|███████▉  | 49281/61904 [2:48:33<5:05:37,  1.45s/it]
 80%|███████▉  | 49282/61904 [2:48:35<5:03:20,  1.44s/it]
 80%|███████▉  | 49283/61904 [2:48:36<4:53:57,  1.40s/it]
 80%|███████▉  | 49284/61904 [2:48:37<4:46:16,  1.36s/it]
 80%|███████▉  | 49285/61904 [2:48:38<4:43:36,  1.35s/it]
 80%|███████▉  | 49286/61904 [2:48:40<4:36:15,  1.31s/it]
 80%|███████▉  | 49287/61904 [2:48:41<4:51:37,  1.39s/it]
 80%|███████▉  | 49288/61904 [2:48:43<5:03:48,  1.44s/it]
 80%|███████▉  | 49289/61904 [2:48:44<5:04:04,  1.45s/it]
 80%|███████▉  | 49290/61904 [2:48:46<4:53:50,  1.40s/it]
 80%|███████▉  | 49291/61904 [2:48:47<4:47:30,  1.37s/it]
 80%|███████▉  | 49292/61904 [2:48:48<4:45:19,  1.36s/it]
 80%|███████▉  | 49293/61904 [2:48:50<4:57:05,  1.41s/it]
 80%|███████▉  | 49294/61904 [2:48:51<4:52:19,  1.39s/it]
 80%|███████▉  | 49295/61904 [2:48:52<4:48:22,  1.37s/it]
 80%|███████▉  | 49296/61904 [2:48:54<4:49:33,  1.38s/it]
 80%|███████▉  | 49297/61904 [2:48:55<4:53:44,  1.40s/it]
 80%|███████▉  | 49298/61904 [2:48:57<4:53:50,  1.40s/it]
 80%|███████▉  | 49299/61904 [2:48:58<4:57:55,  1.42s/it]
 80%|███████▉  | 49300/61904 [2:48:59<4:49:16,  1.38s/it]
                                                         
{'loss': 2.4743, 'learning_rate': 1.2042655257357706e-07, 'epoch': 12.74}

 80%|███████▉  | 49300/61904 [2:48:59<4:49:16,  1.38s/it]
 80%|███████▉  | 49301/61904 [2:49:01<4:46:52,  1.37s/it]
 80%|███████▉  | 49302/61904 [2:49:02<4:47:18,  1.37s/it]
 80%|███████▉  | 49303/61904 [2:49:04<4:50:22,  1.38s/it]
 80%|███████▉  | 49304/61904 [2:49:05<4:53:14,  1.40s/it]
 80%|███████▉  | 49305/61904 [2:49:06<4:40:36,  1.34s/it]
 80%|███████▉  | 49306/61904 [2:49:07<4:33:30,  1.30s/it]
 80%|███████▉  | 49307/61904 [2:49:09<4:41:46,  1.34s/it]
 80%|███████▉  | 49308/61904 [2:49:10<4:43:20,  1.35s/it]
 80%|███████▉  | 49309/61904 [2:49:12<4:45:38,  1.36s/it]
 80%|███████▉  | 49310/61904 [2:49:13<4:45:27,  1.36s/it]
 80%|███████▉  | 49311/61904 [2:49:14<4:44:32,  1.36s/it]
 80%|███████▉  | 49312/61904 [2:49:16<4:48:06,  1.37s/it]
 80%|███████▉  | 49313/61904 [2:49:17<4:48:05,  1.37s/it]
 80%|███████▉  | 49314/61904 [2:49:18<4:41:59,  1.34s/it]
 80%|███████▉  | 49315/61904 [2:49:20<4:42:00,  1.34s/it]
 80%|███████▉  | 49316/61904 [2:49:21<4:36:21,  1.32s/it]
 80%|███████▉  | 49317/61904 [2:49:22<4:35:25,  1.31s/it]
 80%|███████▉  | 49318/61904 [2:49:24<4:39:58,  1.33s/it]
 80%|███████▉  | 49319/61904 [2:49:25<4:38:46,  1.33s/it]
 80%|███████▉  | 49320/61904 [2:49:26<4:42:56,  1.35s/it]
                                                         
{'loss': 2.4963, 'learning_rate': 1.2039413976403474e-07, 'epoch': 12.75}

 80%|███████▉  | 49320/61904 [2:49:26<4:42:56,  1.35s/it]
 80%|███████▉  | 49321/61904 [2:49:28<4:46:47,  1.37s/it]
 80%|███████▉  | 49322/61904 [2:49:29<4:47:43,  1.37s/it]
 80%|███████▉  | 49323/61904 [2:49:30<4:47:33,  1.37s/it]
 80%|███████▉  | 49324/61904 [2:49:32<4:58:25,  1.42s/it]
 80%|███████▉  | 49325/61904 [2:49:33<4:50:21,  1.38s/it]
 80%|███████▉  | 49326/61904 [2:49:35<4:53:21,  1.40s/it]
 80%|███████▉  | 49327/61904 [2:49:36<4:51:13,  1.39s/it]
 80%|███████▉  | 49328/61904 [2:49:37<4:45:11,  1.36s/it]
 80%|███████▉  | 49329/61904 [2:49:39<4:43:55,  1.35s/it]
 80%|███████▉  | 49330/61904 [2:49:40<4:39:41,  1.33s/it]
 80%|███████▉  | 49331/61904 [2:49:41<4:43:02,  1.35s/it]
 80%|███████▉  | 49332/61904 [2:49:43<4:37:22,  1.32s/it]
 80%|███████▉  | 49333/61904 [2:49:44<4:34:40,  1.31s/it]
 80%|███████▉  | 49334/61904 [2:49:45<4:39:52,  1.34s/it]
 80%|███████▉  | 49335/61904 [2:49:47<4:45:56,  1.36s/it]
 80%|███████▉  | 49336/61904 [2:49:48<4:38:57,  1.33s/it]
 80%|███████▉  | 49337/61904 [2:49:49<4:37:37,  1.33s/it]
 80%|███████▉  | 49338/61904 [2:49:51<4:38:50,  1.33s/it]
 80%|███████▉  | 49339/61904 [2:49:52<4:49:02,  1.38s/it]
 80%|███████▉  | 49340/61904 [2:49:54<4:51:57,  1.39s/it]
                                                         
{'loss': 2.4157, 'learning_rate': 1.203617269544924e-07, 'epoch': 12.75}

 80%|███████▉  | 49340/61904 [2:49:54<4:51:57,  1.39s/it]
 80%|███████▉  | 49341/61904 [2:49:55<4:55:12,  1.41s/it]
 80%|███████▉  | 49342/61904 [2:49:56<4:42:08,  1.35s/it]
 80%|███████▉  | 49343/61904 [2:49:58<4:43:15,  1.35s/it]
 80%|███████▉  | 49344/61904 [2:49:59<4:43:39,  1.36s/it]
 80%|███████▉  | 49345/61904 [2:50:00<4:45:03,  1.36s/it]
 80%|███████▉  | 49346/61904 [2:50:02<4:47:04,  1.37s/it]
 80%|███████▉  | 49347/61904 [2:50:03<4:46:01,  1.37s/it]
 80%|███████▉  | 49348/61904 [2:50:05<4:47:58,  1.38s/it]
 80%|███████▉  | 49349/61904 [2:50:06<4:43:14,  1.35s/it]
 80%|███████▉  | 49350/61904 [2:50:07<4:52:52,  1.40s/it]
 80%|███████▉  | 49351/61904 [2:50:09<4:44:41,  1.36s/it]
 80%|███████▉  | 49352/61904 [2:50:10<4:39:09,  1.33s/it]
 80%|███████▉  | 49353/61904 [2:50:11<4:43:02,  1.35s/it]
 80%|███████▉  | 49354/61904 [2:50:13<4:47:04,  1.37s/it]
 80%|███████▉  | 49355/61904 [2:50:14<4:41:41,  1.35s/it]
 80%|███████▉  | 49356/61904 [2:50:15<4:42:47,  1.35s/it]
 80%|███████▉  | 49357/61904 [2:50:17<4:44:43,  1.36s/it]
 80%|███████▉  | 49358/61904 [2:50:18<4:43:40,  1.36s/it]
 80%|███████▉  | 49359/61904 [2:50:19<4:43:48,  1.36s/it]
 80%|███████▉  | 49360/61904 [2:50:21<4:40:41,  1.34s/it]
                                                         
{'loss': 2.4355, 'learning_rate': 1.2032931414495007e-07, 'epoch': 12.76}

 80%|███████▉  | 49360/61904 [2:50:21<4:40:41,  1.34s/it]
 80%|███████▉  | 49361/61904 [2:50:22<4:39:44,  1.34s/it]
 80%|███████▉  | 49362/61904 [2:50:23<4:35:52,  1.32s/it]
 80%|███████▉  | 49363/61904 [2:50:25<4:39:22,  1.34s/it]
 80%|███████▉  | 49364/61904 [2:50:26<4:41:40,  1.35s/it]
 80%|███████▉  | 49365/61904 [2:50:27<4:43:54,  1.36s/it]
 80%|███████▉  | 49366/61904 [2:50:29<4:44:34,  1.36s/it]
 80%|███████▉  | 49367/61904 [2:50:30<4:48:39,  1.38s/it]
 80%|███████▉  | 49368/61904 [2:50:32<4:46:35,  1.37s/it]
 80%|███████▉  | 49369/61904 [2:50:33<4:43:03,  1.35s/it]
 80%|███████▉  | 49370/61904 [2:50:34<4:37:08,  1.33s/it]
 80%|███████▉  | 49371/61904 [2:50:36<4:40:39,  1.34s/it]
 80%|███████▉  | 49372/61904 [2:50:37<4:48:58,  1.38s/it]
 80%|███████▉  | 49373/61904 [2:50:38<4:45:55,  1.37s/it]
 80%|███████▉  | 49374/61904 [2:50:40<4:39:31,  1.34s/it]
 80%|███████▉  | 49375/61904 [2:50:41<4:39:01,  1.34s/it]
 80%|███████▉  | 49376/61904 [2:50:42<4:37:35,  1.33s/it]
 80%|███████▉  | 49377/61904 [2:50:44<4:38:23,  1.33s/it]
 80%|███████▉  | 49378/61904 [2:50:45<4:50:19,  1.39s/it]
 80%|███████▉  | 49379/61904 [2:50:47<4:49:27,  1.39s/it]
 80%|███████▉  | 49380/61904 [2:50:48<4:56:40,  1.42s/it]
                                                         
{'loss': 2.4174, 'learning_rate': 1.2029690133540776e-07, 'epoch': 12.76}

 80%|███████▉  | 49380/61904 [2:50:48<4:56:40,  1.42s/it]
 80%|███████▉  | 49381/61904 [2:50:49<4:56:13,  1.42s/it]
 80%|███████▉  | 49382/61904 [2:50:51<5:09:34,  1.48s/it]
 80%|███████▉  | 49383/61904 [2:50:52<4:58:07,  1.43s/it]
 80%|███████▉  | 49384/61904 [2:50:54<4:58:51,  1.43s/it]
 80%|███████▉  | 49385/61904 [2:50:55<4:47:59,  1.38s/it]
 80%|███████▉  | 49386/61904 [2:50:57<4:56:55,  1.42s/it]
 80%|███████▉  | 49387/61904 [2:50:58<5:00:55,  1.44s/it]
 80%|███████▉  | 49388/61904 [2:50:59<4:52:51,  1.40s/it]
 80%|███████▉  | 49389/61904 [2:51:01<4:56:24,  1.42s/it]
 80%|███████▉  | 49390/61904 [2:51:02<4:51:16,  1.40s/it]
 80%|███████▉  | 49391/61904 [2:51:04<5:07:11,  1.47s/it]
 80%|███████▉  | 49392/61904 [2:51:05<4:59:04,  1.43s/it]
 80%|███████▉  | 49393/61904 [2:51:07<5:05:32,  1.47s/it]
 80%|███████▉  | 49394/61904 [2:51:08<5:06:30,  1.47s/it]
 80%|███████▉  | 49395/61904 [2:51:10<4:56:31,  1.42s/it]
 80%|███████▉  | 49396/61904 [2:51:11<4:53:49,  1.41s/it]
 80%|███████▉  | 49397/61904 [2:51:13<5:04:48,  1.46s/it]
 80%|███████▉  | 49398/61904 [2:51:14<4:54:56,  1.42s/it]
 80%|███████▉  | 49399/61904 [2:51:15<4:50:27,  1.39s/it]
 80%|███████▉  | 49400/61904 [2:51:17<5:07:21,  1.47s/it]
                                                         
{'loss': 2.4903, 'learning_rate': 1.2026448852586542e-07, 'epoch': 12.77}

 80%|███████▉  | 49400/61904 [2:51:17<5:07:21,  1.47s/it]
 80%|███████▉  | 49401/61904 [2:51:18<5:01:19,  1.45s/it]
 80%|███████▉  | 49402/61904 [2:51:20<5:15:07,  1.51s/it]
 80%|███████▉  | 49403/61904 [2:51:21<5:10:56,  1.49s/it]
 80%|███████▉  | 49404/61904 [2:51:23<5:07:46,  1.48s/it]
 80%|███████▉  | 49405/61904 [2:51:24<4:57:07,  1.43s/it]
 80%|███████▉  | 49406/61904 [2:51:26<4:58:14,  1.43s/it]
 80%|███████▉  | 49407/61904 [2:51:27<4:44:39,  1.37s/it]
 80%|███████▉  | 49408/61904 [2:51:28<4:37:13,  1.33s/it]
 80%|███████▉  | 49409/61904 [2:51:29<4:36:09,  1.33s/it]
 80%|███████▉  | 49410/61904 [2:51:31<4:38:25,  1.34s/it]
 80%|███████▉  | 49411/61904 [2:51:32<4:35:36,  1.32s/it]
 80%|███████▉  | 49412/61904 [2:51:33<4:35:53,  1.33s/it]
 80%|███████▉  | 49413/61904 [2:51:35<4:42:29,  1.36s/it]
 80%|███████▉  | 49414/61904 [2:51:36<4:40:09,  1.35s/it]
 80%|███████▉  | 49415/61904 [2:51:37<4:35:20,  1.32s/it]
 80%|███████▉  | 49416/61904 [2:51:39<4:45:57,  1.37s/it]
 80%|███████▉  | 49417/61904 [2:51:40<4:47:56,  1.38s/it]
 80%|███████▉  | 49418/61904 [2:51:41<4:41:00,  1.35s/it]
 80%|███████▉  | 49419/61904 [2:51:43<4:44:16,  1.37s/it]
 80%|███████▉  | 49420/61904 [2:51:44<4:40:23,  1.35s/it]
                                                         
{'loss': 2.4285, 'learning_rate': 1.2023207571632308e-07, 'epoch': 12.77}

 80%|███████▉  | 49420/61904 [2:51:44<4:40:23,  1.35s/it]
 80%|███████▉  | 49421/61904 [2:51:45<4:35:11,  1.32s/it]
 80%|███████▉  | 49422/61904 [2:51:47<4:32:00,  1.31s/it]
 80%|███████▉  | 49423/61904 [2:51:48<4:44:28,  1.37s/it]
 80%|███████▉  | 49424/61904 [2:51:50<4:43:39,  1.36s/it]
 80%|███████▉  | 49425/61904 [2:51:51<4:45:39,  1.37s/it]
 80%|███████▉  | 49426/61904 [2:51:52<4:47:12,  1.38s/it]
 80%|███████▉  | 49427/61904 [2:51:54<4:48:20,  1.39s/it]
 80%|███████▉  | 49428/61904 [2:51:55<4:37:25,  1.33s/it]
 80%|███████▉  | 49429/61904 [2:51:56<4:35:37,  1.33s/it]
 80%|███████▉  | 49430/61904 [2:51:58<4:30:41,  1.30s/it]
 80%|███████▉  | 49431/61904 [2:51:59<4:45:00,  1.37s/it]
 80%|███████▉  | 49432/61904 [2:52:01<4:48:54,  1.39s/it]
 80%|███████▉  | 49433/61904 [2:52:02<4:43:22,  1.36s/it]
 80%|███████▉  | 49434/61904 [2:52:03<4:47:13,  1.38s/it]
 80%|███████▉  | 49435/61904 [2:52:05<4:41:50,  1.36s/it]
 80%|███████▉  | 49436/61904 [2:52:06<4:54:24,  1.42s/it]
 80%|███████▉  | 49437/61904 [2:52:07<4:51:28,  1.40s/it]
 80%|███████▉  | 49438/61904 [2:52:09<4:52:25,  1.41s/it]
 80%|███████▉  | 49439/61904 [2:52:10<4:49:01,  1.39s/it]
 80%|███████▉  | 49440/61904 [2:52:12<4:52:14,  1.41s/it]
                                                         
{'loss': 2.5139, 'learning_rate': 1.2019966290678074e-07, 'epoch': 12.78}

 80%|███████▉  | 49440/61904 [2:52:12<4:52:14,  1.41s/it]
 80%|███████▉  | 49441/61904 [2:52:13<5:01:09,  1.45s/it]
 80%|███████▉  | 49442/61904 [2:52:15<5:01:07,  1.45s/it]
 80%|███████▉  | 49443/61904 [2:52:16<5:01:45,  1.45s/it]
 80%|███████▉  | 49444/61904 [2:52:17<4:52:33,  1.41s/it]
 80%|███████▉  | 49445/61904 [2:52:19<4:51:04,  1.40s/it]
 80%|███████▉  | 49446/61904 [2:52:20<4:55:38,  1.42s/it]
 80%|███████▉  | 49447/61904 [2:52:22<4:57:21,  1.43s/it]
 80%|███████▉  | 49448/61904 [2:52:23<4:45:37,  1.38s/it]
 80%|███████▉  | 49449/61904 [2:52:24<4:41:08,  1.35s/it]
 80%|███████▉  | 49450/61904 [2:52:26<4:39:14,  1.35s/it]
 80%|███████▉  | 49451/61904 [2:52:27<4:40:24,  1.35s/it]
 80%|███████▉  | 49452/61904 [2:52:28<4:41:49,  1.36s/it]
 80%|███████▉  | 49453/61904 [2:52:30<4:38:14,  1.34s/it]
 80%|███████▉  | 49454/61904 [2:52:31<4:27:21,  1.29s/it]
 80%|███████▉  | 49455/61904 [2:52:32<4:24:42,  1.28s/it]
 80%|███████▉  | 49456/61904 [2:52:33<4:26:48,  1.29s/it]
 80%|███████▉  | 49457/61904 [2:52:35<4:45:44,  1.38s/it]
 80%|███████▉  | 49458/61904 [2:52:36<4:46:04,  1.38s/it]
 80%|███████▉  | 49459/61904 [2:52:38<4:42:21,  1.36s/it]
 80%|███████▉  | 49460/61904 [2:52:39<4:36:53,  1.34s/it]
                                                         
{'loss': 2.4306, 'learning_rate': 1.2016725009723843e-07, 'epoch': 12.78}

 80%|███████▉  | 49460/61904 [2:52:39<4:36:53,  1.34s/it]
 80%|███████▉  | 49461/61904 [2:52:40<4:44:05,  1.37s/it]
 80%|███████▉  | 49462/61904 [2:52:42<4:44:17,  1.37s/it]
 80%|███████▉  | 49463/61904 [2:52:44<5:09:30,  1.49s/it]
 80%|███████▉  | 49464/61904 [2:52:45<5:02:35,  1.46s/it]
 80%|███████▉  | 49465/61904 [2:52:46<5:01:14,  1.45s/it]
 80%|███████▉  | 49466/61904 [2:52:48<4:46:28,  1.38s/it]
 80%|███████▉  | 49467/61904 [2:52:49<4:45:08,  1.38s/it]
 80%|███████▉  | 49468/61904 [2:52:50<4:47:47,  1.39s/it]
 80%|███████▉  | 49469/61904 [2:52:52<4:42:22,  1.36s/it]
 80%|███████▉  | 49470/61904 [2:52:53<4:42:59,  1.37s/it]
 80%|███████▉  | 49471/61904 [2:52:54<4:41:02,  1.36s/it]
 80%|███████▉  | 49472/61904 [2:52:56<4:38:11,  1.34s/it]
 80%|███████▉  | 49473/61904 [2:52:57<4:35:40,  1.33s/it]
 80%|███████▉  | 49474/61904 [2:52:58<4:43:07,  1.37s/it]
 80%|███████▉  | 49475/61904 [2:53:00<4:47:58,  1.39s/it]
 80%|███████▉  | 49476/61904 [2:53:01<4:40:27,  1.35s/it]
 80%|███████▉  | 49477/61904 [2:53:03<4:40:58,  1.36s/it]
 80%|███████▉  | 49478/61904 [2:53:04<4:46:04,  1.38s/it]
 80%|███████▉  | 49479/61904 [2:53:05<4:47:05,  1.39s/it]
 80%|███████▉  | 49480/61904 [2:53:07<4:48:37,  1.39s/it]
                                                         
{'loss': 2.4208, 'learning_rate': 1.201348372876961e-07, 'epoch': 12.79}

 80%|███████▉  | 49480/61904 [2:53:07<4:48:37,  1.39s/it]
 80%|███████▉  | 49481/61904 [2:53:08<4:51:29,  1.41s/it]
 80%|███████▉  | 49482/61904 [2:53:10<4:59:10,  1.45s/it]
 80%|███████▉  | 49483/61904 [2:53:11<5:08:24,  1.49s/it]
 80%|███████▉  | 49484/61904 [2:53:13<5:13:14,  1.51s/it]
 80%|███████▉  | 49485/61904 [2:53:15<5:20:10,  1.55s/it]
 80%|███████▉  | 49486/61904 [2:53:16<5:01:54,  1.46s/it]
 80%|███████▉  | 49487/61904 [2:53:17<4:56:44,  1.43s/it]
 80%|███████▉  | 49488/61904 [2:53:18<4:44:55,  1.38s/it]
 80%|███████▉  | 49489/61904 [2:53:20<5:02:46,  1.46s/it]
 80%|███████▉  | 49490/61904 [2:53:22<5:00:57,  1.45s/it]
 80%|███████▉  | 49491/61904 [2:53:23<4:56:56,  1.44s/it]
 80%|███████▉  | 49492/61904 [2:53:24<5:02:10,  1.46s/it]
 80%|███████▉  | 49493/61904 [2:53:26<4:56:20,  1.43s/it]
 80%|███████▉  | 49494/61904 [2:53:27<4:51:19,  1.41s/it]
 80%|███████▉  | 49495/61904 [2:53:28<4:48:01,  1.39s/it]
 80%|███████▉  | 49496/61904 [2:53:30<4:45:11,  1.38s/it]
 80%|███████▉  | 49497/61904 [2:53:31<4:42:05,  1.36s/it]
 80%|███████▉  | 49498/61904 [2:53:33<4:46:26,  1.39s/it]
 80%|███████▉  | 49499/61904 [2:53:34<4:50:34,  1.41s/it]
 80%|███████▉  | 49500/61904 [2:53:35<4:50:00,  1.40s/it]
                                                         
{'loss': 2.4154, 'learning_rate': 1.2010242447815375e-07, 'epoch': 12.79}

 80%|███████▉  | 49500/61904 [2:53:35<4:50:00,  1.40s/it]
 80%|███████▉  | 49501/61904 [2:53:37<4:52:24,  1.41s/it]
 80%|███████▉  | 49502/61904 [2:53:38<4:46:21,  1.39s/it]
 80%|███████▉  | 49503/61904 [2:53:40<4:43:50,  1.37s/it]
 80%|███████▉  | 49504/61904 [2:53:41<4:41:10,  1.36s/it]
 80%|███████▉  | 49505/61904 [2:53:42<4:46:06,  1.38s/it]
 80%|███████▉  | 49506/61904 [2:53:44<4:42:06,  1.37s/it]
 80%|███████▉  | 49507/61904 [2:53:45<4:43:24,  1.37s/it]
 80%|███████▉  | 49508/61904 [2:53:47<4:55:05,  1.43s/it]
 80%|███████▉  | 49509/61904 [2:53:48<4:48:52,  1.40s/it]
 80%|███████▉  | 49510/61904 [2:53:49<4:51:54,  1.41s/it]
 80%|███████▉  | 49511/61904 [2:53:51<4:46:43,  1.39s/it]
 80%|███████▉  | 49512/61904 [2:53:52<4:39:53,  1.36s/it]
 80%|███████▉  | 49513/61904 [2:53:53<4:42:02,  1.37s/it]
 80%|███████▉  | 49514/61904 [2:53:55<4:49:44,  1.40s/it]
 80%|███████▉  | 49515/61904 [2:53:56<4:42:45,  1.37s/it]
 80%|███████▉  | 49516/61904 [2:53:57<4:34:57,  1.33s/it]
 80%|███████▉  | 49517/61904 [2:53:59<4:33:43,  1.33s/it]
 80%|███████▉  | 49518/61904 [2:54:00<4:44:19,  1.38s/it]
 80%|███████▉  | 49519/61904 [2:54:02<4:41:51,  1.37s/it]
 80%|███████▉  | 49520/61904 [2:54:03<4:35:38,  1.34s/it]
                                                         
{'loss': 2.4862, 'learning_rate': 1.2007001166861142e-07, 'epoch': 12.8}

 80%|███████▉  | 49520/61904 [2:54:03<4:35:38,  1.34s/it]
 80%|███████▉  | 49521/61904 [2:54:04<4:34:29,  1.33s/it]
 80%|███████▉  | 49522/61904 [2:54:05<4:33:25,  1.32s/it]
 80%|███████▉  | 49523/61904 [2:54:07<4:40:29,  1.36s/it]
 80%|████████  | 49524/61904 [2:54:08<4:36:14,  1.34s/it]
 80%|████████  | 49525/61904 [2:54:09<4:25:22,  1.29s/it]
 80%|████████  | 49526/61904 [2:54:11<4:24:38,  1.28s/it]
 80%|████████  | 49527/61904 [2:54:12<4:30:46,  1.31s/it]
 80%|████████  | 49528/61904 [2:54:13<4:28:27,  1.30s/it]
 80%|████████  | 49529/61904 [2:54:15<4:26:30,  1.29s/it]
 80%|████████  | 49530/61904 [2:54:16<4:28:43,  1.30s/it]
 80%|████████  | 49531/61904 [2:54:17<4:44:11,  1.38s/it]
 80%|████████  | 49532/61904 [2:54:19<4:50:13,  1.41s/it]
 80%|████████  | 49533/61904 [2:54:20<4:45:46,  1.39s/it]
 80%|████████  | 49534/61904 [2:54:22<4:48:55,  1.40s/it]
 80%|████████  | 49535/61904 [2:54:23<4:44:15,  1.38s/it]
 80%|████████  | 49536/61904 [2:54:24<4:43:06,  1.37s/it]
 80%|████████  | 49537/61904 [2:54:26<4:39:19,  1.36s/it]
 80%|████████  | 49538/61904 [2:54:27<4:34:53,  1.33s/it]
 80%|████████  | 49539/61904 [2:54:28<4:29:39,  1.31s/it]
 80%|████████  | 49540/61904 [2:54:30<4:30:23,  1.31s/it]
                                                         
{'loss': 2.4184, 'learning_rate': 1.200375988590691e-07, 'epoch': 12.8}

 80%|████████  | 49540/61904 [2:54:30<4:30:23,  1.31s/it]
 80%|████████  | 49541/61904 [2:54:31<4:33:16,  1.33s/it]
 80%|████████  | 49542/61904 [2:54:32<4:40:03,  1.36s/it]
 80%|████████  | 49543/61904 [2:54:34<4:35:08,  1.34s/it]
 80%|████████  | 49544/61904 [2:54:35<4:43:43,  1.38s/it]
 80%|████████  | 49545/61904 [2:54:36<4:45:08,  1.38s/it]
 80%|████████  | 49546/61904 [2:54:38<4:50:59,  1.41s/it]
 80%|████████  | 49547/61904 [2:54:39<4:48:10,  1.40s/it]
 80%|████████  | 49548/61904 [2:54:41<4:49:44,  1.41s/it]
 80%|████████  | 49549/61904 [2:54:42<4:44:39,  1.38s/it]
 80%|████████  | 49550/61904 [2:54:44<4:55:12,  1.43s/it]
 80%|████████  | 49551/61904 [2:54:45<5:07:06,  1.49s/it]
 80%|████████  | 49552/61904 [2:54:47<4:55:43,  1.44s/it]
 80%|████████  | 49553/61904 [2:54:48<4:52:43,  1.42s/it]
 80%|████████  | 49554/61904 [2:54:49<4:53:09,  1.42s/it]
 80%|████████  | 49555/61904 [2:54:51<4:53:01,  1.42s/it]
 80%|████████  | 49556/61904 [2:54:52<4:44:32,  1.38s/it]
 80%|████████  | 49557/61904 [2:54:53<4:41:44,  1.37s/it]
 80%|████████  | 49558/61904 [2:54:55<4:38:52,  1.36s/it]
 80%|████████  | 49559/61904 [2:54:56<4:39:50,  1.36s/it]
 80%|████████  | 49560/61904 [2:54:57<4:38:31,  1.35s/it]
                                                         
{'loss': 2.374, 'learning_rate': 1.2000518604952677e-07, 'epoch': 12.81}

 80%|████████  | 49560/61904 [2:54:57<4:38:31,  1.35s/it]
 80%|████████  | 49561/61904 [2:54:59<4:41:59,  1.37s/it]
 80%|████████  | 49562/61904 [2:55:00<4:42:34,  1.37s/it]
 80%|████████  | 49563/61904 [2:55:02<4:49:39,  1.41s/it]
 80%|████████  | 49564/61904 [2:55:03<4:49:52,  1.41s/it]
 80%|████████  | 49565/61904 [2:55:05<4:51:09,  1.42s/it]
 80%|████████  | 49566/61904 [2:55:06<4:45:05,  1.39s/it]
 80%|████████  | 49567/61904 [2:55:07<4:49:12,  1.41s/it]
 80%|████████  | 49568/61904 [2:55:09<4:43:52,  1.38s/it]
 80%|████████  | 49569/61904 [2:55:10<4:45:11,  1.39s/it]
 80%|████████  | 49570/61904 [2:55:11<4:40:42,  1.37s/it]
 80%|████████  | 49571/61904 [2:55:13<4:43:48,  1.38s/it]
 80%|████████  | 49572/61904 [2:55:14<4:38:26,  1.35s/it]
 80%|████████  | 49573/61904 [2:55:16<4:44:06,  1.38s/it]
 80%|████████  | 49574/61904 [2:55:17<4:41:57,  1.37s/it]
 80%|████████  | 49575/61904 [2:55:18<4:41:26,  1.37s/it]
 80%|████████  | 49576/61904 [2:55:20<4:37:22,  1.35s/it]
 80%|████████  | 49577/61904 [2:55:21<4:42:00,  1.37s/it]
 80%|████████  | 49578/61904 [2:55:22<4:43:07,  1.38s/it]
 80%|████████  | 49579/61904 [2:55:24<4:48:41,  1.41s/it]
 80%|████████  | 49580/61904 [2:55:25<4:51:28,  1.42s/it]
                                                         
{'loss': 2.4885, 'learning_rate': 1.1997277323998443e-07, 'epoch': 12.81}

 80%|████████  | 49580/61904 [2:55:25<4:51:28,  1.42s/it]
 80%|████████  | 49581/61904 [2:55:27<4:48:49,  1.41s/it]
 80%|████████  | 49582/61904 [2:55:28<4:41:01,  1.37s/it]
 80%|████████  | 49583/61904 [2:55:29<4:43:27,  1.38s/it]
 80%|████████  | 49584/61904 [2:55:31<4:54:11,  1.43s/it]
 80%|████████  | 49585/61904 [2:55:32<4:42:42,  1.38s/it]
 80%|████████  | 49586/61904 [2:55:34<4:45:38,  1.39s/it]
 80%|████████  | 49587/61904 [2:55:35<4:51:55,  1.42s/it]
 80%|████████  | 49588/61904 [2:55:36<4:49:12,  1.41s/it]
 80%|████████  | 49589/61904 [2:55:38<4:53:20,  1.43s/it]
 80%|████████  | 49590/61904 [2:55:39<4:45:59,  1.39s/it]
 80%|████████  | 49591/61904 [2:55:41<4:42:17,  1.38s/it]
 80%|████████  | 49592/61904 [2:55:42<4:33:47,  1.33s/it]
 80%|████████  | 49593/61904 [2:55:43<4:31:39,  1.32s/it]
 80%|████████  | 49594/61904 [2:55:45<4:39:44,  1.36s/it]
 80%|████████  | 49595/61904 [2:55:46<4:41:00,  1.37s/it]
 80%|████████  | 49596/61904 [2:55:47<4:42:17,  1.38s/it]
 80%|████████  | 49597/61904 [2:55:49<4:49:00,  1.41s/it]
 80%|████████  | 49598/61904 [2:55:50<4:49:40,  1.41s/it]
 80%|████████  | 49599/61904 [2:55:52<4:42:48,  1.38s/it]
 80%|████████  | 49600/61904 [2:55:53<4:51:57,  1.42s/it]
                                                         
{'loss': 2.4429, 'learning_rate': 1.199403604304421e-07, 'epoch': 12.82}

 80%|████████  | 49600/61904 [2:55:53<4:51:57,  1.42s/it]
 80%|████████  | 49601/61904 [2:55:55<5:01:58,  1.47s/it]
 80%|████████  | 49602/61904 [2:55:56<4:58:08,  1.45s/it]
 80%|████████  | 49603/61904 [2:55:57<4:48:14,  1.41s/it]
 80%|████████  | 49604/61904 [2:55:59<4:49:36,  1.41s/it]
 80%|████████  | 49605/61904 [2:56:00<4:48:37,  1.41s/it]
 80%|████████  | 49606/61904 [2:56:02<4:44:52,  1.39s/it]
 80%|████████  | 49607/61904 [2:56:03<4:51:44,  1.42s/it]
 80%|████████  | 49608/61904 [2:56:04<4:41:00,  1.37s/it]
 80%|████████  | 49609/61904 [2:56:06<4:44:00,  1.39s/it]
 80%|████████  | 49610/61904 [2:56:07<4:44:26,  1.39s/it]
 80%|████████  | 49611/61904 [2:56:09<4:49:46,  1.41s/it]
 80%|████████  | 49612/61904 [2:56:10<4:47:19,  1.40s/it]
 80%|████████  | 49613/61904 [2:56:11<4:41:52,  1.38s/it]
 80%|████████  | 49614/61904 [2:56:13<4:44:49,  1.39s/it]
 80%|████████  | 49615/61904 [2:56:14<4:52:34,  1.43s/it]
 80%|████████  | 49616/61904 [2:56:16<4:43:56,  1.39s/it]
 80%|████████  | 49617/61904 [2:56:17<4:44:59,  1.39s/it]
 80%|████████  | 49618/61904 [2:56:18<4:48:19,  1.41s/it]
 80%|████████  | 49619/61904 [2:56:20<4:39:35,  1.37s/it]
 80%|████████  | 49620/61904 [2:56:21<4:40:32,  1.37s/it]
                                                         
{'loss': 2.3834, 'learning_rate': 1.1990794762089978e-07, 'epoch': 12.82}

 80%|████████  | 49620/61904 [2:56:21<4:40:32,  1.37s/it]
 80%|████████  | 49621/61904 [2:56:22<4:42:46,  1.38s/it]
 80%|████████  | 49622/61904 [2:56:24<4:46:25,  1.40s/it]
 80%|████████  | 49623/61904 [2:56:25<4:49:53,  1.42s/it]
 80%|████████  | 49624/61904 [2:56:27<4:42:00,  1.38s/it]
 80%|████████  | 49625/61904 [2:56:28<4:36:22,  1.35s/it]
 80%|████████  | 49626/61904 [2:56:29<4:31:31,  1.33s/it]
 80%|████████  | 49627/61904 [2:56:31<4:33:26,  1.34s/it]
 80%|████████  | 49628/61904 [2:56:32<4:42:51,  1.38s/it]
 80%|████████  | 49629/61904 [2:56:33<4:36:25,  1.35s/it]
 80%|████████  | 49630/61904 [2:56:35<4:36:38,  1.35s/it]
 80%|████████  | 49631/61904 [2:56:36<4:42:19,  1.38s/it]
 80%|████████  | 49632/61904 [2:56:38<4:55:19,  1.44s/it]
 80%|████████  | 49633/61904 [2:56:39<4:44:30,  1.39s/it]
 80%|████████  | 49634/61904 [2:56:40<4:51:36,  1.43s/it]
 80%|████████  | 49635/61904 [2:56:42<4:50:15,  1.42s/it]
 80%|████████  | 49636/61904 [2:56:43<4:44:03,  1.39s/it]
 80%|████████  | 49637/61904 [2:56:45<4:40:58,  1.37s/it]
 80%|████████  | 49638/61904 [2:56:46<4:57:17,  1.45s/it]
 80%|████████  | 49639/61904 [2:56:47<4:46:50,  1.40s/it]
 80%|████████  | 49640/61904 [2:56:49<4:50:29,  1.42s/it]
                                                         
{'loss': 2.415, 'learning_rate': 1.1987553481135744e-07, 'epoch': 12.83}

 80%|████████  | 49640/61904 [2:56:49<4:50:29,  1.42s/it]
 80%|████████  | 49641/61904 [2:56:50<4:35:37,  1.35s/it]
 80%|████████  | 49642/61904 [2:56:52<4:42:25,  1.38s/it]
 80%|████████  | 49643/61904 [2:56:53<4:43:17,  1.39s/it]
 80%|████████  | 49644/61904 [2:56:54<4:33:10,  1.34s/it]
 80%|████████  | 49645/61904 [2:56:55<4:28:25,  1.31s/it]
 80%|████████  | 49646/61904 [2:56:57<4:34:11,  1.34s/it]
 80%|████████  | 49647/61904 [2:56:58<4:38:06,  1.36s/it]
 80%|████████  | 49648/61904 [2:57:00<4:42:55,  1.39s/it]
 80%|████████  | 49649/61904 [2:57:01<4:34:34,  1.34s/it]
 80%|████████  | 49650/61904 [2:57:02<4:35:52,  1.35s/it]
 80%|████████  | 49651/61904 [2:57:04<4:44:35,  1.39s/it]
 80%|████████  | 49652/61904 [2:57:05<4:43:36,  1.39s/it]
 80%|████████  | 49653/61904 [2:57:07<4:53:01,  1.44s/it]
 80%|████████  | 49654/61904 [2:57:08<4:46:09,  1.40s/it]
 80%|████████  | 49655/61904 [2:57:09<4:38:27,  1.36s/it]
 80%|████████  | 49656/61904 [2:57:11<4:30:37,  1.33s/it]
 80%|████████  | 49657/61904 [2:57:12<4:30:31,  1.33s/it]
 80%|████████  | 49658/61904 [2:57:13<4:28:25,  1.32s/it]
 80%|████████  | 49659/61904 [2:57:15<4:30:20,  1.32s/it]
 80%|████████  | 49660/61904 [2:57:16<4:29:24,  1.32s/it]
                                                         
{'loss': 2.5206, 'learning_rate': 1.198431220018151e-07, 'epoch': 12.84}

 80%|████████  | 49660/61904 [2:57:16<4:29:24,  1.32s/it]
 80%|████████  | 49661/61904 [2:57:17<4:26:28,  1.31s/it]
 80%|████████  | 49662/61904 [2:57:18<4:27:12,  1.31s/it]
 80%|████████  | 49663/61904 [2:57:20<4:32:51,  1.34s/it]
 80%|████████  | 49664/61904 [2:57:21<4:33:41,  1.34s/it]
 80%|████████  | 49665/61904 [2:57:22<4:30:34,  1.33s/it]
 80%|████████  | 49666/61904 [2:57:24<4:31:22,  1.33s/it]
 80%|████████  | 49667/61904 [2:57:25<4:34:22,  1.35s/it]
 80%|████████  | 49668/61904 [2:57:27<4:39:12,  1.37s/it]
 80%|████████  | 49669/61904 [2:57:28<4:43:01,  1.39s/it]
 80%|████████  | 49670/61904 [2:57:30<4:49:23,  1.42s/it]
 80%|████████  | 49671/61904 [2:57:31<4:48:08,  1.41s/it]
 80%|████████  | 49672/61904 [2:57:32<4:42:46,  1.39s/it]
 80%|████████  | 49673/61904 [2:57:34<4:42:27,  1.39s/it]
 80%|████████  | 49674/61904 [2:57:35<4:37:03,  1.36s/it]
 80%|████████  | 49675/61904 [2:57:36<4:38:11,  1.36s/it]
 80%|████████  | 49676/61904 [2:57:38<4:33:55,  1.34s/it]
 80%|████████  | 49677/61904 [2:57:39<4:28:31,  1.32s/it]
 80%|████████  | 49678/61904 [2:57:40<4:32:32,  1.34s/it]
 80%|████████  | 49679/61904 [2:57:42<4:30:33,  1.33s/it]
 80%|████████  | 49680/61904 [2:57:43<4:27:47,  1.31s/it]
                                                         
{'loss': 2.4883, 'learning_rate': 1.198107091922728e-07, 'epoch': 12.84}

 80%|████████  | 49680/61904 [2:57:43<4:27:47,  1.31s/it]
 80%|████████  | 49681/61904 [2:57:44<4:29:36,  1.32s/it]
 80%|████████  | 49682/61904 [2:57:46<4:41:30,  1.38s/it]
 80%|████████  | 49683/61904 [2:57:47<4:40:39,  1.38s/it]
 80%|████████  | 49684/61904 [2:57:48<4:37:34,  1.36s/it]
 80%|████████  | 49685/61904 [2:57:50<4:40:55,  1.38s/it]
 80%|████████  | 49686/61904 [2:57:51<4:32:51,  1.34s/it]
 80%|████████  | 49687/61904 [2:57:52<4:35:32,  1.35s/it]
 80%|████████  | 49688/61904 [2:57:54<4:34:08,  1.35s/it]
 80%|████████  | 49689/61904 [2:57:55<4:37:51,  1.36s/it]
 80%|████████  | 49690/61904 [2:57:56<4:32:03,  1.34s/it]
 80%|████████  | 49691/61904 [2:57:58<4:43:16,  1.39s/it]
 80%|████████  | 49692/61904 [2:57:59<4:37:34,  1.36s/it]
 80%|████████  | 49693/61904 [2:58:01<4:47:31,  1.41s/it]
 80%|████████  | 49694/61904 [2:58:02<4:40:31,  1.38s/it]
 80%|████████  | 49695/61904 [2:58:04<4:50:04,  1.43s/it]
 80%|████████  | 49696/61904 [2:58:05<4:44:13,  1.40s/it]
 80%|████████  | 49697/61904 [2:58:06<4:45:16,  1.40s/it]
 80%|████████  | 49698/61904 [2:58:08<4:41:43,  1.38s/it]
 80%|████████  | 49699/61904 [2:58:09<4:42:07,  1.39s/it]
 80%|████████  | 49700/61904 [2:58:10<4:37:21,  1.36s/it]
                                                         
{'loss': 2.4729, 'learning_rate': 1.1977829638273045e-07, 'epoch': 12.85}

 80%|████████  | 49700/61904 [2:58:10<4:37:21,  1.36s/it]
 80%|████████  | 49701/61904 [2:58:12<4:31:10,  1.33s/it]
 80%|████████  | 49702/61904 [2:58:13<4:32:35,  1.34s/it]
 80%|████████  | 49703/61904 [2:58:14<4:36:31,  1.36s/it]
 80%|████████  | 49704/61904 [2:58:16<4:38:46,  1.37s/it]
 80%|████████  | 49705/61904 [2:58:17<4:40:21,  1.38s/it]
 80%|████████  | 49706/61904 [2:58:18<4:31:01,  1.33s/it]
 80%|████████  | 49707/61904 [2:58:20<4:35:41,  1.36s/it]
 80%|████████  | 49708/61904 [2:58:21<4:39:29,  1.37s/it]
 80%|████████  | 49709/61904 [2:58:23<4:35:00,  1.35s/it]
 80%|████████  | 49710/61904 [2:58:24<4:33:35,  1.35s/it]
 80%|████████  | 49711/61904 [2:58:25<4:35:34,  1.36s/it]
 80%|████████  | 49712/61904 [2:58:27<4:33:53,  1.35s/it]
 80%|████████  | 49713/61904 [2:58:28<4:37:14,  1.36s/it]
 80%|████████  | 49714/61904 [2:58:29<4:31:28,  1.34s/it]
 80%|████████  | 49715/61904 [2:58:31<4:32:30,  1.34s/it]
 80%|████████  | 49716/61904 [2:58:32<4:35:55,  1.36s/it]
 80%|████████  | 49717/61904 [2:58:33<4:26:19,  1.31s/it]
 80%|████████  | 49718/61904 [2:58:35<4:36:36,  1.36s/it]
 80%|████████  | 49719/61904 [2:58:36<4:37:25,  1.37s/it]
 80%|████████  | 49720/61904 [2:58:38<4:42:34,  1.39s/it]
                                                         
{'loss': 2.3815, 'learning_rate': 1.1974588357318811e-07, 'epoch': 12.85}

 80%|████████  | 49720/61904 [2:58:38<4:42:34,  1.39s/it]
 80%|████████  | 49721/61904 [2:58:39<4:37:15,  1.37s/it]
 80%|████████  | 49722/61904 [2:58:40<4:39:09,  1.37s/it]
 80%|████████  | 49723/61904 [2:58:42<4:51:17,  1.43s/it]
 80%|████████  | 49724/61904 [2:58:43<4:44:14,  1.40s/it]
 80%|████████  | 49725/61904 [2:58:44<4:37:53,  1.37s/it]
 80%|████████  | 49726/61904 [2:58:46<4:38:05,  1.37s/it]
 80%|████████  | 49727/61904 [2:58:47<4:34:56,  1.35s/it]
 80%|████████  | 49728/61904 [2:58:48<4:29:55,  1.33s/it]
 80%|████████  | 49729/61904 [2:58:50<4:27:25,  1.32s/it]
 80%|████████  | 49730/61904 [2:58:51<4:34:43,  1.35s/it]
 80%|████████  | 49731/61904 [2:58:52<4:32:46,  1.34s/it]
 80%|████████  | 49732/61904 [2:58:54<4:36:10,  1.36s/it]
 80%|████████  | 49733/61904 [2:58:55<4:48:10,  1.42s/it]
 80%|████████  | 49734/61904 [2:58:57<4:44:06,  1.40s/it]
 80%|████████  | 49735/61904 [2:58:58<5:02:00,  1.49s/it]
 80%|████████  | 49736/61904 [2:59:00<4:53:36,  1.45s/it]
 80%|████████  | 49737/61904 [2:59:01<4:45:09,  1.41s/it]
 80%|████████  | 49738/61904 [2:59:03<4:50:25,  1.43s/it]
 80%|████████  | 49739/61904 [2:59:04<4:56:41,  1.46s/it]
 80%|████████  | 49740/61904 [2:59:05<4:47:18,  1.42s/it]
                                                         
{'loss': 2.453, 'learning_rate': 1.1971347076364578e-07, 'epoch': 12.86}

 80%|████████  | 49740/61904 [2:59:05<4:47:18,  1.42s/it]
 80%|████████  | 49741/61904 [2:59:07<4:53:44,  1.45s/it]
 80%|████████  | 49742/61904 [2:59:08<4:53:42,  1.45s/it]
 80%|████████  | 49743/61904 [2:59:10<4:39:26,  1.38s/it]
 80%|████████  | 49744/61904 [2:59:11<4:42:54,  1.40s/it]
 80%|████████  | 49745/61904 [2:59:12<4:37:09,  1.37s/it]
 80%|████████  | 49746/61904 [2:59:14<4:32:09,  1.34s/it]
 80%|████████  | 49747/61904 [2:59:15<4:38:55,  1.38s/it]
 80%|████████  | 49748/61904 [2:59:16<4:34:32,  1.36s/it]
 80%|████████  | 49749/61904 [2:59:18<4:44:10,  1.40s/it]
 80%|████████  | 49750/61904 [2:59:19<4:48:11,  1.42s/it]
 80%|████████  | 49751/61904 [2:59:21<4:39:05,  1.38s/it]
 80%|████████  | 49752/61904 [2:59:22<4:34:52,  1.36s/it]
 80%|████████  | 49753/61904 [2:59:23<4:29:25,  1.33s/it]
 80%|████████  | 49754/61904 [2:59:25<4:33:37,  1.35s/it]
 80%|████████  | 49755/61904 [2:59:26<4:26:04,  1.31s/it]
 80%|████████  | 49756/61904 [2:59:27<4:26:43,  1.32s/it]
 80%|████████  | 49757/61904 [2:59:29<4:32:14,  1.34s/it]
 80%|████████  | 49758/61904 [2:59:30<4:31:52,  1.34s/it]
 80%|████████  | 49759/61904 [2:59:31<4:42:00,  1.39s/it]
 80%|████████  | 49760/61904 [2:59:33<4:40:38,  1.39s/it]
                                                         
{'loss': 2.4414, 'learning_rate': 1.1968105795410346e-07, 'epoch': 12.86}

 80%|████████  | 49760/61904 [2:59:33<4:40:38,  1.39s/it]
 80%|████████  | 49761/61904 [2:59:34<4:33:14,  1.35s/it]
 80%|████████  | 49762/61904 [2:59:36<4:48:07,  1.42s/it]
 80%|████████  | 49763/61904 [2:59:37<4:50:49,  1.44s/it]
 80%|████████  | 49764/61904 [2:59:38<4:42:15,  1.40s/it]
 80%|████████  | 49765/61904 [2:59:40<4:31:01,  1.34s/it]
 80%|████████  | 49766/61904 [2:59:41<4:37:05,  1.37s/it]
 80%|████████  | 49767/61904 [2:59:42<4:30:25,  1.34s/it]
 80%|████████  | 49768/61904 [2:59:44<4:31:12,  1.34s/it]
 80%|████████  | 49769/61904 [2:59:45<4:31:10,  1.34s/it]
 80%|████████  | 49770/61904 [2:59:47<4:36:53,  1.37s/it]
 80%|████████  | 49771/61904 [2:59:48<4:34:26,  1.36s/it]
 80%|████████  | 49772/61904 [2:59:49<4:29:29,  1.33s/it]
 80%|████████  | 49773/61904 [2:59:51<4:37:44,  1.37s/it]
 80%|████████  | 49774/61904 [2:59:52<4:37:30,  1.37s/it]
 80%|████████  | 49775/61904 [2:59:53<4:42:15,  1.40s/it]
 80%|████████  | 49776/61904 [2:59:55<4:40:03,  1.39s/it]
 80%|████████  | 49777/61904 [2:59:56<4:45:52,  1.41s/it]
 80%|████████  | 49778/61904 [2:59:58<4:36:36,  1.37s/it]
 80%|████████  | 49779/61904 [2:59:59<4:36:53,  1.37s/it]
 80%|████████  | 49780/61904 [3:00:00<4:35:44,  1.36s/it]
                                                         
{'loss': 2.5048, 'learning_rate': 1.1964864514456113e-07, 'epoch': 12.87}

 80%|████████  | 49780/61904 [3:00:00<4:35:44,  1.36s/it]
 80%|████████  | 49781/61904 [3:00:02<4:46:08,  1.42s/it]
 80%|████████  | 49782/61904 [3:00:03<4:46:51,  1.42s/it]
 80%|████████  | 49783/61904 [3:00:05<4:40:08,  1.39s/it]
 80%|████████  | 49784/61904 [3:00:06<4:37:19,  1.37s/it]
 80%|████████  | 49785/61904 [3:00:07<4:37:17,  1.37s/it]
 80%|████████  | 49786/61904 [3:00:09<4:37:21,  1.37s/it]
 80%|████████  | 49787/61904 [3:00:10<4:40:39,  1.39s/it]
 80%|████████  | 49788/61904 [3:00:11<4:39:31,  1.38s/it]
 80%|████████  | 49789/61904 [3:00:13<4:32:18,  1.35s/it]
 80%|████████  | 49790/61904 [3:00:14<4:29:28,  1.33s/it]
 80%|████████  | 49791/61904 [3:00:15<4:32:02,  1.35s/it]
 80%|████████  | 49792/61904 [3:00:17<4:30:44,  1.34s/it]
 80%|████████  | 49793/61904 [3:00:18<4:26:47,  1.32s/it]
 80%|████████  | 49794/61904 [3:00:19<4:32:14,  1.35s/it]
 80%|████████  | 49795/61904 [3:00:21<4:38:31,  1.38s/it]
 80%|████████  | 49796/61904 [3:00:22<4:35:48,  1.37s/it]
 80%|████████  | 49797/61904 [3:00:23<4:32:05,  1.35s/it]
 80%|████████  | 49798/61904 [3:00:25<4:42:25,  1.40s/it]
 80%|████████  | 49799/61904 [3:00:26<4:29:37,  1.34s/it]
 80%|████████  | 49800/61904 [3:00:28<4:29:37,  1.34s/it]
                                                         
{'loss': 2.4836, 'learning_rate': 1.196162323350188e-07, 'epoch': 12.87}

 80%|████████  | 49800/61904 [3:00:28<4:29:37,  1.34s/it]
 80%|████████  | 49801/61904 [3:00:29<4:31:14,  1.34s/it]
 80%|████████  | 49802/61904 [3:00:30<4:32:01,  1.35s/it]
 80%|████████  | 49803/61904 [3:00:31<4:26:50,  1.32s/it]
 80%|████████  | 49804/61904 [3:00:33<4:34:36,  1.36s/it]
 80%|████████  | 49805/61904 [3:00:34<4:29:05,  1.33s/it]
 80%|████████  | 49806/61904 [3:00:36<4:28:38,  1.33s/it]
 80%|████████  | 49807/61904 [3:00:37<4:25:49,  1.32s/it]
 80%|████████  | 49808/61904 [3:00:38<4:32:06,  1.35s/it]
 80%|████████  | 49809/61904 [3:00:40<4:35:44,  1.37s/it]
 80%|████████  | 49810/61904 [3:00:41<4:45:06,  1.41s/it]
 80%|████████  | 49811/61904 [3:00:42<4:38:47,  1.38s/it]
 80%|████████  | 49812/61904 [3:00:44<4:37:21,  1.38s/it]
 80%|████████  | 49813/61904 [3:00:45<4:33:02,  1.35s/it]
 80%|████████  | 49814/61904 [3:00:47<4:36:16,  1.37s/it]
 80%|████████  | 49815/61904 [3:00:48<4:34:29,  1.36s/it]
 80%|████████  | 49816/61904 [3:00:49<4:34:20,  1.36s/it]
 80%|████████  | 49817/61904 [3:00:51<4:37:44,  1.38s/it]
 80%|████████  | 49818/61904 [3:00:52<4:40:04,  1.39s/it]
 80%|████████  | 49819/61904 [3:00:53<4:36:15,  1.37s/it]
 80%|████████  | 49820/61904 [3:00:55<4:40:36,  1.39s/it]
                                                         
{'loss': 2.4018, 'learning_rate': 1.1958381952547645e-07, 'epoch': 12.88}

 80%|████████  | 49820/61904 [3:00:55<4:40:36,  1.39s/it]
 80%|████████  | 49821/61904 [3:00:56<4:34:12,  1.36s/it]
 80%|████████  | 49822/61904 [3:00:58<4:32:29,  1.35s/it]
 80%|████████  | 49823/61904 [3:00:59<4:39:15,  1.39s/it]
 80%|████████  | 49824/61904 [3:01:00<4:29:39,  1.34s/it]
 80%|████████  | 49825/61904 [3:01:02<4:32:46,  1.35s/it]
 80%|████████  | 49826/61904 [3:01:03<4:29:38,  1.34s/it]
 80%|████████  | 49827/61904 [3:01:04<4:32:52,  1.36s/it]
 80%|████████  | 49828/61904 [3:01:06<4:37:55,  1.38s/it]
 80%|████████  | 49829/61904 [3:01:07<4:38:58,  1.39s/it]
 80%|████████  | 49830/61904 [3:01:09<4:38:27,  1.38s/it]
 80%|████████  | 49831/61904 [3:01:10<4:36:19,  1.37s/it]
 80%|████████  | 49832/61904 [3:01:11<4:44:31,  1.41s/it]
 81%|████████  | 49833/61904 [3:01:13<4:39:05,  1.39s/it]
 81%|████████  | 49834/61904 [3:01:14<4:33:25,  1.36s/it]
 81%|████████  | 49835/61904 [3:01:15<4:34:59,  1.37s/it]
 81%|████████  | 49836/61904 [3:01:17<4:35:00,  1.37s/it]
 81%|████████  | 49837/61904 [3:01:18<4:36:19,  1.37s/it]
 81%|████████  | 49838/61904 [3:01:20<4:39:01,  1.39s/it]
 81%|████████  | 49839/61904 [3:01:21<4:35:15,  1.37s/it]
 81%|████████  | 49840/61904 [3:01:22<4:30:54,  1.35s/it]
                                                         
{'loss': 2.4562, 'learning_rate': 1.1955140671593414e-07, 'epoch': 12.88}

 81%|████████  | 49840/61904 [3:01:22<4:30:54,  1.35s/it]
 81%|████████  | 49841/61904 [3:01:24<4:37:01,  1.38s/it]
 81%|████████  | 49842/61904 [3:01:25<4:47:36,  1.43s/it]
 81%|████████  | 49843/61904 [3:01:27<4:43:25,  1.41s/it]
 81%|████████  | 49844/61904 [3:01:28<4:44:28,  1.42s/it]
 81%|████████  | 49845/61904 [3:01:29<4:44:31,  1.42s/it]
 81%|████████  | 49846/61904 [3:01:31<4:37:14,  1.38s/it]
 81%|████████  | 49847/61904 [3:01:32<4:30:43,  1.35s/it]
 81%|████████  | 49848/61904 [3:01:33<4:28:43,  1.34s/it]
 81%|████████  | 49849/61904 [3:01:35<4:48:49,  1.44s/it]
 81%|████████  | 49850/61904 [3:01:36<4:39:03,  1.39s/it]
 81%|████████  | 49851/61904 [3:01:38<4:34:15,  1.37s/it]
 81%|████████  | 49852/61904 [3:01:39<4:32:19,  1.36s/it]
 81%|████████  | 49853/61904 [3:01:40<4:35:20,  1.37s/it]
 81%|████████  | 49854/61904 [3:01:42<4:37:02,  1.38s/it]
 81%|████████  | 49855/61904 [3:01:43<4:41:00,  1.40s/it]
 81%|████████  | 49856/61904 [3:01:44<4:32:04,  1.35s/it]
 81%|████████  | 49857/61904 [3:01:46<4:27:02,  1.33s/it]
 81%|████████  | 49858/61904 [3:01:47<4:36:48,  1.38s/it]
 81%|████████  | 49859/61904 [3:01:48<4:34:13,  1.37s/it]
 81%|████████  | 49860/61904 [3:01:50<4:31:54,  1.35s/it]
                                                         
{'loss': 2.4431, 'learning_rate': 1.195189939063918e-07, 'epoch': 12.89}

 81%|████████  | 49860/61904 [3:01:50<4:31:54,  1.35s/it]
 81%|████████  | 49861/61904 [3:01:51<4:37:07,  1.38s/it]
 81%|████████  | 49862/61904 [3:01:53<4:33:46,  1.36s/it]
 81%|████████  | 49863/61904 [3:01:54<4:34:06,  1.37s/it]
 81%|████████  | 49864/61904 [3:01:55<4:32:37,  1.36s/it]
 81%|████████  | 49865/61904 [3:01:57<4:39:00,  1.39s/it]
 81%|████████  | 49866/61904 [3:01:58<4:38:03,  1.39s/it]
 81%|████████  | 49867/61904 [3:02:00<4:39:59,  1.40s/it]
 81%|████████  | 49868/61904 [3:02:01<4:43:18,  1.41s/it]
 81%|████████  | 49869/61904 [3:02:02<4:40:29,  1.40s/it]
 81%|████████  | 49870/61904 [3:02:04<4:47:11,  1.43s/it]
 81%|████████  | 49871/61904 [3:02:05<4:39:49,  1.40s/it]
 81%|████████  | 49872/61904 [3:02:07<4:40:06,  1.40s/it]
 81%|████████  | 49873/61904 [3:02:08<4:44:56,  1.42s/it]
 81%|████████  | 49874/61904 [3:02:09<4:40:11,  1.40s/it]
 81%|████████  | 49875/61904 [3:02:11<4:40:41,  1.40s/it]
 81%|████████  | 49876/61904 [3:02:12<4:35:55,  1.38s/it]
 81%|████████  | 49877/61904 [3:02:14<4:50:57,  1.45s/it]
 81%|████████  | 49878/61904 [3:02:15<4:46:26,  1.43s/it]
 81%|████████  | 49879/61904 [3:02:17<4:50:38,  1.45s/it]
 81%|████████  | 49880/61904 [3:02:18<4:37:35,  1.39s/it]
                                                         
{'loss': 2.4554, 'learning_rate': 1.1948658109684946e-07, 'epoch': 12.89}

 81%|████████  | 49880/61904 [3:02:18<4:37:35,  1.39s/it]
 81%|████████  | 49881/61904 [3:02:19<4:33:50,  1.37s/it]
 81%|████████  | 49882/61904 [3:02:20<4:28:46,  1.34s/it]
 81%|████████  | 49883/61904 [3:02:22<4:29:51,  1.35s/it]
 81%|████████  | 49884/61904 [3:02:23<4:24:59,  1.32s/it]
 81%|████████  | 49885/61904 [3:02:24<4:26:54,  1.33s/it]
 81%|████████  | 49886/61904 [3:02:26<4:23:11,  1.31s/it]
 81%|████████  | 49887/61904 [3:02:27<4:24:44,  1.32s/it]
 81%|████████  | 49888/61904 [3:02:29<4:35:06,  1.37s/it]
 81%|████████  | 49889/61904 [3:02:30<4:36:36,  1.38s/it]
 81%|████████  | 49890/61904 [3:02:31<4:31:13,  1.35s/it]
 81%|████████  | 49891/61904 [3:02:32<4:25:20,  1.33s/it]
 81%|████████  | 49892/61904 [3:02:34<4:26:36,  1.33s/it]
 81%|████████  | 49893/61904 [3:02:35<4:38:27,  1.39s/it]
 81%|████████  | 49894/61904 [3:02:37<4:31:04,  1.35s/it]
 81%|████████  | 49895/61904 [3:02:38<4:38:47,  1.39s/it]
 81%|████████  | 49896/61904 [3:02:40<4:40:16,  1.40s/it]
 81%|████████  | 49897/61904 [3:02:41<4:34:49,  1.37s/it]
 81%|████████  | 49898/61904 [3:02:42<4:37:55,  1.39s/it]
 81%|████████  | 49899/61904 [3:02:44<4:37:41,  1.39s/it]
 81%|████████  | 49900/61904 [3:02:45<4:40:07,  1.40s/it]
                                                         
{'loss': 2.4341, 'learning_rate': 1.1945416828730712e-07, 'epoch': 12.9}

 81%|████████  | 49900/61904 [3:02:45<4:40:07,  1.40s/it]
 81%|████████  | 49901/61904 [3:02:46<4:33:31,  1.37s/it]
 81%|████████  | 49902/61904 [3:02:48<4:32:40,  1.36s/it]
 81%|████████  | 49903/61904 [3:02:49<4:39:39,  1.40s/it]
 81%|████████  | 49904/61904 [3:02:51<4:43:38,  1.42s/it]
 81%|████████  | 49905/61904 [3:02:52<4:35:40,  1.38s/it]
 81%|████████  | 49906/61904 [3:02:53<4:37:34,  1.39s/it]
 81%|████████  | 49907/61904 [3:02:55<4:50:49,  1.45s/it]
 81%|████████  | 49908/61904 [3:02:56<4:40:25,  1.40s/it]
 81%|████████  | 49909/61904 [3:02:58<4:37:19,  1.39s/it]
 81%|████████  | 49910/61904 [3:02:59<4:38:17,  1.39s/it]
 81%|████████  | 49911/61904 [3:03:00<4:37:21,  1.39s/it]
 81%|████████  | 49912/61904 [3:03:02<4:30:36,  1.35s/it]
 81%|████████  | 49913/61904 [3:03:03<4:31:53,  1.36s/it]
 81%|████████  | 49914/61904 [3:03:04<4:29:59,  1.35s/it]
 81%|████████  | 49915/61904 [3:03:06<4:29:35,  1.35s/it]
 81%|████████  | 49916/61904 [3:03:07<4:27:44,  1.34s/it]
 81%|████████  | 49917/61904 [3:03:08<4:26:40,  1.33s/it]
 81%|████████  | 49918/61904 [3:03:10<4:21:07,  1.31s/it]
 81%|████████  | 49919/61904 [3:03:11<4:16:23,  1.28s/it]
 81%|████████  | 49920/61904 [3:03:12<4:32:57,  1.37s/it]
                                                         
{'loss': 2.4189, 'learning_rate': 1.194217554777648e-07, 'epoch': 12.9}

 81%|████████  | 49920/61904 [3:03:12<4:32:57,  1.37s/it]
 81%|████████  | 49921/61904 [3:03:14<4:25:30,  1.33s/it]
 81%|████████  | 49922/61904 [3:03:15<4:32:48,  1.37s/it]
 81%|████████  | 49923/61904 [3:03:16<4:30:18,  1.35s/it]
 81%|████████  | 49924/61904 [3:03:18<4:34:37,  1.38s/it]
 81%|████████  | 49925/61904 [3:03:19<4:35:51,  1.38s/it]
 81%|████████  | 49926/61904 [3:03:21<4:34:23,  1.37s/it]
 81%|████████  | 49927/61904 [3:03:22<4:28:33,  1.35s/it]
 81%|████████  | 49928/61904 [3:03:23<4:28:31,  1.35s/it]
 81%|████████  | 49929/61904 [3:03:25<4:28:23,  1.34s/it]
 81%|████████  | 49930/61904 [3:03:26<4:30:22,  1.35s/it]
 81%|████████  | 49931/61904 [3:03:27<4:40:55,  1.41s/it]
 81%|████████  | 49932/61904 [3:03:29<4:44:19,  1.42s/it]
 81%|████████  | 49933/61904 [3:03:30<4:36:16,  1.38s/it]
 81%|████████  | 49934/61904 [3:03:32<4:41:59,  1.41s/it]
 81%|████████  | 49935/61904 [3:03:33<4:35:55,  1.38s/it]
 81%|████████  | 49936/61904 [3:03:35<4:44:07,  1.42s/it]
 81%|████████  | 49937/61904 [3:03:36<4:44:06,  1.42s/it]
 81%|████████  | 49938/61904 [3:03:37<4:41:31,  1.41s/it]
 81%|████████  | 49939/61904 [3:03:39<4:39:16,  1.40s/it]
 81%|████████  | 49940/61904 [3:03:40<4:43:48,  1.42s/it]
                                                         
{'loss': 2.4739, 'learning_rate': 1.1938934266822247e-07, 'epoch': 12.91}

 81%|████████  | 49940/61904 [3:03:40<4:43:48,  1.42s/it]
 81%|████████  | 49941/61904 [3:03:41<4:36:01,  1.38s/it]
 81%|████████  | 49942/61904 [3:03:43<4:47:05,  1.44s/it]
 81%|████████  | 49943/61904 [3:03:44<4:44:03,  1.42s/it]
 81%|████████  | 49944/61904 [3:03:46<4:45:56,  1.43s/it]
 81%|████████  | 49945/61904 [3:03:47<4:41:22,  1.41s/it]
 81%|████████  | 49946/61904 [3:03:49<4:36:54,  1.39s/it]
 81%|████████  | 49947/61904 [3:03:50<4:36:43,  1.39s/it]
 81%|████████  | 49948/61904 [3:03:51<4:37:21,  1.39s/it]
 81%|████████  | 49949/61904 [3:03:53<4:42:34,  1.42s/it]
 81%|████████  | 49950/61904 [3:03:54<4:33:51,  1.37s/it]
 81%|████████  | 49951/61904 [3:03:56<4:35:12,  1.38s/it]
 81%|████████  | 49952/61904 [3:03:57<4:25:43,  1.33s/it]
 81%|████████  | 49953/61904 [3:03:58<4:37:41,  1.39s/it]
 81%|████████  | 49954/61904 [3:04:00<4:40:35,  1.41s/it]
 81%|████████  | 49955/61904 [3:04:01<4:39:43,  1.40s/it]
 81%|████████  | 49956/61904 [3:04:03<4:41:10,  1.41s/it]
 81%|████████  | 49957/61904 [3:04:04<4:34:42,  1.38s/it]
 81%|████████  | 49958/61904 [3:04:05<4:25:49,  1.34s/it]
 81%|████████  | 49959/61904 [3:04:06<4:30:00,  1.36s/it]
 81%|████████  | 49960/61904 [3:04:08<4:25:45,  1.34s/it]
                                                         
{'loss': 2.3941, 'learning_rate': 1.1935692985868014e-07, 'epoch': 12.91}

 81%|████████  | 49960/61904 [3:04:08<4:25:45,  1.34s/it]
 81%|████████  | 49961/61904 [3:04:09<4:33:53,  1.38s/it]
 81%|████████  | 49962/61904 [3:04:11<4:34:08,  1.38s/it]
 81%|████████  | 49963/61904 [3:04:12<4:27:06,  1.34s/it]
 81%|████████  | 49964/61904 [3:04:13<4:38:04,  1.40s/it]
 81%|████████  | 49965/61904 [3:04:15<4:25:06,  1.33s/it]
 81%|████████  | 49966/61904 [3:04:16<4:29:04,  1.35s/it]
 81%|████████  | 49967/61904 [3:04:17<4:23:45,  1.33s/it]
 81%|████████  | 49968/61904 [3:04:19<4:28:35,  1.35s/it]
 81%|████████  | 49969/61904 [3:04:20<4:25:02,  1.33s/it]
 81%|████████  | 49970/61904 [3:04:21<4:28:18,  1.35s/it]
 81%|████████  | 49971/61904 [3:04:23<4:37:41,  1.40s/it]
 81%|████████  | 49972/61904 [3:04:24<4:45:18,  1.43s/it]
 81%|████████  | 49973/61904 [3:04:26<4:31:29,  1.37s/it]
 81%|████████  | 49974/61904 [3:04:27<4:29:37,  1.36s/it]
 81%|████████  | 49975/61904 [3:04:28<4:37:31,  1.40s/it]
 81%|████████  | 49976/61904 [3:04:30<4:25:45,  1.34s/it]
 81%|████████  | 49977/61904 [3:04:31<4:30:02,  1.36s/it]
 81%|████████  | 49978/61904 [3:04:32<4:31:04,  1.36s/it]
 81%|████████  | 49979/61904 [3:04:34<4:29:40,  1.36s/it]
 81%|████████  | 49980/61904 [3:04:35<4:27:53,  1.35s/it]
                                                         
{'loss': 2.4357, 'learning_rate': 1.1932451704913782e-07, 'epoch': 12.92}

 81%|████████  | 49980/61904 [3:04:35<4:27:53,  1.35s/it]
 81%|████████  | 49981/61904 [3:04:36<4:29:35,  1.36s/it]
 81%|████████  | 49982/61904 [3:04:38<4:30:27,  1.36s/it]
 81%|████████  | 49983/61904 [3:04:39<4:33:54,  1.38s/it]
 81%|████████  | 49984/61904 [3:04:40<4:25:46,  1.34s/it]
 81%|████████  | 49985/61904 [3:04:42<4:18:47,  1.30s/it]
 81%|████████  | 49986/61904 [3:04:43<4:26:04,  1.34s/it]
 81%|████████  | 49987/61904 [3:04:44<4:29:09,  1.36s/it]
 81%|████████  | 49988/61904 [3:04:46<4:39:27,  1.41s/it]
 81%|████████  | 49989/61904 [3:04:47<4:37:54,  1.40s/it]
 81%|████████  | 49990/61904 [3:04:49<4:33:44,  1.38s/it]
 81%|████████  | 49991/61904 [3:04:50<4:36:14,  1.39s/it]
 81%|████████  | 49992/61904 [3:04:52<4:37:24,  1.40s/it]
 81%|████████  | 49993/61904 [3:04:53<4:31:45,  1.37s/it]
 81%|████████  | 49994/61904 [3:04:54<4:26:59,  1.35s/it]
 81%|████████  | 49995/61904 [3:04:56<4:31:59,  1.37s/it]
 81%|████████  | 49996/61904 [3:04:57<4:26:45,  1.34s/it]
 81%|████████  | 49997/61904 [3:04:58<4:24:43,  1.33s/it]
 81%|████████  | 49998/61904 [3:04:59<4:20:01,  1.31s/it]
 81%|████████  | 49999/61904 [3:05:01<4:29:02,  1.36s/it]
 81%|████████  | 50000/61904 [3:05:02<4:31:36,  1.37s/it]
                                                         
{'loss': 2.4676, 'learning_rate': 1.1929210423959549e-07, 'epoch': 12.92}

 81%|████████  | 50000/61904 [3:05:02<4:31:36,  1.37s/it]
 81%|████████  | 50001/61904 [3:05:04<4:32:08,  1.37s/it]
 81%|████████  | 50002/61904 [3:05:05<4:31:15,  1.37s/it]
 81%|████████  | 50003/61904 [3:05:06<4:28:19,  1.35s/it]
 81%|████████  | 50004/61904 [3:05:08<4:34:15,  1.38s/it]
 81%|████████  | 50005/61904 [3:05:09<4:30:55,  1.37s/it]
 81%|████████  | 50006/61904 [3:05:11<4:33:51,  1.38s/it]
 81%|████████  | 50007/61904 [3:05:12<4:31:38,  1.37s/it]
 81%|████████  | 50008/61904 [3:05:13<4:29:00,  1.36s/it]
 81%|████████  | 50009/61904 [3:05:15<4:29:06,  1.36s/it]
 81%|████████  | 50010/61904 [3:05:16<4:23:35,  1.33s/it]
 81%|████████  | 50011/61904 [3:05:17<4:23:52,  1.33s/it]
 81%|████████  | 50012/61904 [3:05:19<4:27:53,  1.35s/it]
 81%|████████  | 50013/61904 [3:05:20<4:25:23,  1.34s/it]
 81%|████████  | 50014/61904 [3:05:21<4:25:10,  1.34s/it]
 81%|████████  | 50015/61904 [3:05:23<4:21:57,  1.32s/it]
 81%|████████  | 50016/61904 [3:05:24<4:28:53,  1.36s/it]
 81%|████████  | 50017/61904 [3:05:25<4:31:47,  1.37s/it]
 81%|████████  | 50018/61904 [3:05:27<4:28:53,  1.36s/it]
 81%|████████  | 50019/61904 [3:05:28<4:32:16,  1.37s/it]
 81%|████████  | 50020/61904 [3:05:29<4:27:30,  1.35s/it]
                                                         
{'loss': 2.4551, 'learning_rate': 1.1925969143005315e-07, 'epoch': 12.93}

 81%|████████  | 50020/61904 [3:05:29<4:27:30,  1.35s/it]
 81%|████████  | 50021/61904 [3:05:31<4:21:07,  1.32s/it]
 81%|████████  | 50022/61904 [3:05:32<4:17:31,  1.30s/it]
 81%|████████  | 50023/61904 [3:05:33<4:21:44,  1.32s/it]
 81%|████████  | 50024/61904 [3:05:35<4:20:34,  1.32s/it]
 81%|████████  | 50025/61904 [3:05:36<4:19:31,  1.31s/it]
 81%|████████  | 50026/61904 [3:05:37<4:18:46,  1.31s/it]
 81%|████████  | 50027/61904 [3:05:39<4:27:26,  1.35s/it]
 81%|████████  | 50028/61904 [3:05:40<4:18:25,  1.31s/it]
 81%|████████  | 50029/61904 [3:05:41<4:22:35,  1.33s/it]
 81%|████████  | 50030/61904 [3:05:43<4:30:29,  1.37s/it]
 81%|████████  | 50031/61904 [3:05:44<4:32:10,  1.38s/it]
 81%|████████  | 50032/61904 [3:05:45<4:28:40,  1.36s/it]
 81%|████████  | 50033/61904 [3:05:47<4:27:51,  1.35s/it]
 81%|████████  | 50034/61904 [3:05:48<4:29:17,  1.36s/it]
 81%|████████  | 50035/61904 [3:05:50<4:32:44,  1.38s/it]
 81%|████████  | 50036/61904 [3:05:51<4:33:11,  1.38s/it]
 81%|████████  | 50037/61904 [3:05:52<4:32:56,  1.38s/it]
 81%|████████  | 50038/61904 [3:05:54<4:32:29,  1.38s/it]
 81%|████████  | 50039/61904 [3:05:55<4:33:23,  1.38s/it]
 81%|████████  | 50040/61904 [3:05:56<4:26:32,  1.35s/it]
                                                         
{'loss': 2.4811, 'learning_rate': 1.192272786205108e-07, 'epoch': 12.93}

 81%|████████  | 50040/61904 [3:05:56<4:26:32,  1.35s/it]
 81%|████████  | 50041/61904 [3:05:58<4:28:36,  1.36s/it]
 81%|████████  | 50042/61904 [3:05:59<4:29:42,  1.36s/it]
 81%|████████  | 50043/61904 [3:06:00<4:33:21,  1.38s/it]
 81%|████████  | 50044/61904 [3:06:02<4:22:51,  1.33s/it]
 81%|████████  | 50045/61904 [3:06:03<4:33:12,  1.38s/it]
 81%|████████  | 50046/61904 [3:06:05<4:38:20,  1.41s/it]
 81%|████████  | 50047/61904 [3:06:06<4:23:47,  1.33s/it]
 81%|████████  | 50048/61904 [3:06:07<4:19:33,  1.31s/it]
 81%|████████  | 50049/61904 [3:06:08<4:16:24,  1.30s/it]
 81%|████████  | 50050/61904 [3:06:10<4:12:32,  1.28s/it]
 81%|████████  | 50051/61904 [3:06:11<4:15:30,  1.29s/it]
 81%|████████  | 50052/61904 [3:06:12<4:12:59,  1.28s/it]
 81%|████████  | 50053/61904 [3:06:13<4:13:18,  1.28s/it]
 81%|████████  | 50054/61904 [3:06:15<4:15:23,  1.29s/it]
 81%|████████  | 50055/61904 [3:06:16<4:13:20,  1.28s/it]
 81%|████████  | 50056/61904 [3:06:17<4:15:53,  1.30s/it]
 81%|████████  | 50057/61904 [3:06:19<4:22:59,  1.33s/it]
 81%|████████  | 50058/61904 [3:06:20<4:36:37,  1.40s/it]
 81%|████████  | 50059/61904 [3:06:22<4:46:12,  1.45s/it]
 81%|████████  | 50060/61904 [3:06:23<4:42:01,  1.43s/it]
                                                         
{'loss': 2.4513, 'learning_rate': 1.191948658109685e-07, 'epoch': 12.94}

 81%|████████  | 50060/61904 [3:06:23<4:42:01,  1.43s/it]
 81%|████████  | 50061/61904 [3:06:25<4:36:55,  1.40s/it]
 81%|████████  | 50062/61904 [3:06:26<4:25:51,  1.35s/it]
 81%|████████  | 50063/61904 [3:06:27<4:30:41,  1.37s/it]
 81%|████████  | 50064/61904 [3:06:29<4:36:09,  1.40s/it]
 81%|████████  | 50065/61904 [3:06:30<4:29:37,  1.37s/it]
 81%|████████  | 50066/61904 [3:06:32<4:40:31,  1.42s/it]
 81%|████████  | 50067/61904 [3:06:33<4:33:18,  1.39s/it]
 81%|████████  | 50068/61904 [3:06:34<4:35:34,  1.40s/it]
 81%|████████  | 50069/61904 [3:06:36<4:30:47,  1.37s/it]
 81%|████████  | 50070/61904 [3:06:37<4:36:40,  1.40s/it]
 81%|████████  | 50071/61904 [3:06:38<4:34:41,  1.39s/it]
 81%|████████  | 50072/61904 [3:06:40<4:33:05,  1.38s/it]
 81%|████████  | 50073/61904 [3:06:41<4:29:23,  1.37s/it]
 81%|████████  | 50074/61904 [3:06:42<4:24:54,  1.34s/it]
 81%|████████  | 50075/61904 [3:06:44<4:22:31,  1.33s/it]
 81%|████████  | 50076/61904 [3:06:45<4:30:06,  1.37s/it]
 81%|████████  | 50077/61904 [3:06:47<4:31:42,  1.38s/it]
 81%|████████  | 50078/61904 [3:06:48<4:24:37,  1.34s/it]
 81%|████████  | 50079/61904 [3:06:49<4:30:01,  1.37s/it]
 81%|████████  | 50080/61904 [3:06:51<4:24:18,  1.34s/it]
                                                         
{'loss': 2.4607, 'learning_rate': 1.1916245300142616e-07, 'epoch': 12.94}

 81%|████████  | 50080/61904 [3:06:51<4:24:18,  1.34s/it]
 81%|████████  | 50081/61904 [3:06:52<4:35:27,  1.40s/it]
 81%|████████  | 50082/61904 [3:06:54<4:39:58,  1.42s/it]
 81%|████████  | 50083/61904 [3:06:55<4:27:32,  1.36s/it]
 81%|████████  | 50084/61904 [3:06:56<4:23:11,  1.34s/it]
 81%|████████  | 50085/61904 [3:06:57<4:18:08,  1.31s/it]
 81%|████████  | 50086/61904 [3:06:59<4:21:21,  1.33s/it]
 81%|████████  | 50087/61904 [3:07:00<4:22:01,  1.33s/it]
 81%|████████  | 50088/61904 [3:07:01<4:25:39,  1.35s/it]
 81%|████████  | 50089/61904 [3:07:03<4:34:19,  1.39s/it]
 81%|████████  | 50090/61904 [3:07:04<4:34:36,  1.39s/it]
 81%|████████  | 50091/61904 [3:07:06<4:25:01,  1.35s/it]
 81%|████████  | 50092/61904 [3:07:07<4:33:19,  1.39s/it]
 81%|████████  | 50093/61904 [3:07:08<4:28:03,  1.36s/it]
 81%|████████  | 50094/61904 [3:07:10<4:37:03,  1.41s/it]
 81%|████████  | 50095/61904 [3:07:11<4:34:37,  1.40s/it]
 81%|████████  | 50096/61904 [3:07:12<4:23:41,  1.34s/it]
 81%|████████  | 50097/61904 [3:07:14<4:24:00,  1.34s/it]
 81%|████████  | 50098/61904 [3:07:15<4:27:49,  1.36s/it]
 81%|████████  | 50099/61904 [3:07:17<4:26:50,  1.36s/it]
 81%|████████  | 50100/61904 [3:07:18<4:30:54,  1.38s/it]
                                                         
{'loss': 2.482, 'learning_rate': 1.1913004019188382e-07, 'epoch': 12.95}

 81%|████████  | 50100/61904 [3:07:18<4:30:54,  1.38s/it]
 81%|████████  | 50101/61904 [3:07:19<4:19:59,  1.32s/it]
 81%|████████  | 50102/61904 [3:07:21<4:26:37,  1.36s/it]
 81%|████████  | 50103/61904 [3:07:22<4:21:28,  1.33s/it]
 81%|████████  | 50104/61904 [3:07:23<4:29:54,  1.37s/it]
 81%|████████  | 50105/61904 [3:07:25<4:30:08,  1.37s/it]
 81%|████████  | 50106/61904 [3:07:26<4:35:40,  1.40s/it]
 81%|████████  | 50107/61904 [3:07:28<4:34:40,  1.40s/it]
 81%|████████  | 50108/61904 [3:07:29<4:42:41,  1.44s/it]
 81%|████████  | 50109/61904 [3:07:31<4:44:44,  1.45s/it]
 81%|████████  | 50110/61904 [3:07:32<4:37:33,  1.41s/it]
 81%|████████  | 50111/61904 [3:07:33<4:39:50,  1.42s/it]
 81%|████████  | 50112/61904 [3:07:35<4:27:11,  1.36s/it]
 81%|████████  | 50113/61904 [3:07:36<4:28:07,  1.36s/it]
 81%|████████  | 50114/61904 [3:07:37<4:29:48,  1.37s/it]
 81%|████████  | 50115/61904 [3:07:39<4:19:55,  1.32s/it]
 81%|████████  | 50116/61904 [3:07:40<4:14:18,  1.29s/it]
 81%|████████  | 50117/61904 [3:07:41<4:17:09,  1.31s/it]
 81%|████████  | 50118/61904 [3:07:42<4:17:11,  1.31s/it]
 81%|████████  | 50119/61904 [3:07:44<4:15:30,  1.30s/it]
 81%|████████  | 50120/61904 [3:07:45<4:21:30,  1.33s/it]
                                                         
{'loss': 2.4465, 'learning_rate': 1.1909762738234151e-07, 'epoch': 12.95}

 81%|████████  | 50120/61904 [3:07:45<4:21:30,  1.33s/it]
 81%|████████  | 50121/61904 [3:07:47<4:30:49,  1.38s/it]
 81%|████████  | 50122/61904 [3:07:48<4:33:38,  1.39s/it]
 81%|████████  | 50123/61904 [3:07:49<4:30:57,  1.38s/it]
 81%|████████  | 50124/61904 [3:07:51<4:30:50,  1.38s/it]
 81%|████████  | 50125/61904 [3:07:52<4:28:14,  1.37s/it]
 81%|████████  | 50126/61904 [3:07:53<4:23:54,  1.34s/it]
 81%|████████  | 50127/61904 [3:07:55<4:24:38,  1.35s/it]
 81%|████████  | 50128/61904 [3:07:56<4:21:05,  1.33s/it]
 81%|████████  | 50129/61904 [3:07:57<4:24:09,  1.35s/it]
 81%|████████  | 50130/61904 [3:07:59<4:23:32,  1.34s/it]
 81%|████████  | 50131/61904 [3:08:00<4:21:49,  1.33s/it]
 81%|████████  | 50132/61904 [3:08:01<4:23:20,  1.34s/it]
 81%|████████  | 50133/61904 [3:08:03<4:25:52,  1.36s/it]
 81%|████████  | 50134/61904 [3:08:05<4:48:42,  1.47s/it]
 81%|████████  | 50135/61904 [3:08:06<4:47:45,  1.47s/it]
 81%|████████  | 50136/61904 [3:08:07<4:43:37,  1.45s/it]
 81%|████████  | 50137/61904 [3:08:09<4:30:35,  1.38s/it]
 81%|████████  | 50138/61904 [3:08:10<4:31:24,  1.38s/it]
 81%|████████  | 50139/61904 [3:08:11<4:30:37,  1.38s/it]
 81%|████████  | 50140/61904 [3:08:13<4:29:12,  1.37s/it]
                                                         
{'loss': 2.4672, 'learning_rate': 1.1906521457279917e-07, 'epoch': 12.96}

 81%|████████  | 50140/61904 [3:08:13<4:29:12,  1.37s/it]
 81%|████████  | 50141/61904 [3:08:14<4:29:43,  1.38s/it]
 81%|████████  | 50142/61904 [3:08:15<4:22:27,  1.34s/it]
 81%|████████  | 50143/61904 [3:08:17<4:23:18,  1.34s/it]
 81%|████████  | 50144/61904 [3:08:18<4:30:04,  1.38s/it]
 81%|████████  | 50145/61904 [3:08:20<4:31:00,  1.38s/it]
 81%|████████  | 50146/61904 [3:08:21<4:28:54,  1.37s/it]
 81%|████████  | 50147/61904 [3:08:22<4:26:59,  1.36s/it]
 81%|████████  | 50148/61904 [3:08:24<4:30:23,  1.38s/it]
 81%|████████  | 50149/61904 [3:08:25<4:33:24,  1.40s/it]
 81%|████████  | 50150/61904 [3:08:27<4:38:29,  1.42s/it]
 81%|████████  | 50151/61904 [3:08:28<4:32:17,  1.39s/it]
 81%|████████  | 50152/61904 [3:08:29<4:31:23,  1.39s/it]
 81%|████████  | 50153/61904 [3:08:31<4:41:04,  1.44s/it]
 81%|████████  | 50154/61904 [3:08:32<4:38:32,  1.42s/it]
 81%|████████  | 50155/61904 [3:08:34<4:36:29,  1.41s/it]
 81%|████████  | 50156/61904 [3:08:35<4:49:40,  1.48s/it]
 81%|████████  | 50157/61904 [3:08:37<4:37:42,  1.42s/it]
 81%|████████  | 50158/61904 [3:08:38<4:36:50,  1.41s/it]
 81%|████████  | 50159/61904 [3:08:39<4:31:17,  1.39s/it]
 81%|████████  | 50160/61904 [3:08:41<4:44:55,  1.46s/it]
                                                         
{'loss': 2.421, 'learning_rate': 1.1903280176325683e-07, 'epoch': 12.96}

 81%|████████  | 50160/61904 [3:08:41<4:44:55,  1.46s/it]
 81%|████████  | 50161/61904 [3:08:42<4:50:58,  1.49s/it]
 81%|████████  | 50162/61904 [3:08:44<4:42:59,  1.45s/it]
 81%|████████  | 50163/61904 [3:08:45<4:42:48,  1.45s/it]
 81%|████████  | 50164/61904 [3:08:47<4:45:57,  1.46s/it]
 81%|████████  | 50165/61904 [3:08:49<5:12:41,  1.60s/it]
 81%|████████  | 50166/61904 [3:08:50<4:58:55,  1.53s/it]
 81%|████████  | 50167/61904 [3:08:51<4:50:57,  1.49s/it]
 81%|████████  | 50168/61904 [3:08:53<4:45:02,  1.46s/it]
 81%|████████  | 50169/61904 [3:08:54<4:35:40,  1.41s/it]
 81%|████████  | 50170/61904 [3:08:55<4:22:24,  1.34s/it]
 81%|████████  | 50171/61904 [3:08:57<4:35:39,  1.41s/it]
 81%|████████  | 50172/61904 [3:08:58<4:27:58,  1.37s/it]
 81%|████████  | 50173/61904 [3:08:59<4:23:25,  1.35s/it]
 81%|████████  | 50174/61904 [3:09:01<4:21:15,  1.34s/it]
 81%|████████  | 50175/61904 [3:09:02<4:24:48,  1.35s/it]
 81%|████████  | 50176/61904 [3:09:04<4:29:28,  1.38s/it]
 81%|████████  | 50177/61904 [3:09:05<4:28:00,  1.37s/it]
 81%|████████  | 50178/61904 [3:09:06<4:28:51,  1.38s/it]
 81%|████████  | 50179/61904 [3:09:08<4:26:25,  1.36s/it]
 81%|████████  | 50180/61904 [3:09:09<4:30:24,  1.38s/it]
                                                         
{'loss': 2.4271, 'learning_rate': 1.190003889537145e-07, 'epoch': 12.97}

 81%|████████  | 50180/61904 [3:09:09<4:30:24,  1.38s/it]
 81%|████████  | 50181/61904 [3:09:10<4:31:21,  1.39s/it]
 81%|████████  | 50182/61904 [3:09:12<4:25:35,  1.36s/it]
 81%|████████  | 50183/61904 [3:09:13<4:28:45,  1.38s/it]
 81%|████████  | 50184/61904 [3:09:14<4:21:39,  1.34s/it]
 81%|████████  | 50185/61904 [3:09:16<4:20:20,  1.33s/it]
 81%|████████  | 50186/61904 [3:09:17<4:20:46,  1.34s/it]
 81%|████████  | 50187/61904 [3:09:18<4:25:24,  1.36s/it]
 81%|████████  | 50188/61904 [3:09:20<4:22:36,  1.34s/it]
 81%|████████  | 50189/61904 [3:09:21<4:21:55,  1.34s/it]
 81%|████████  | 50190/61904 [3:09:22<4:20:52,  1.34s/it]
 81%|████████  | 50191/61904 [3:09:24<4:25:09,  1.36s/it]
 81%|████████  | 50192/61904 [3:09:25<4:22:25,  1.34s/it]
 81%|████████  | 50193/61904 [3:09:27<4:32:32,  1.40s/it]
 81%|████████  | 50194/61904 [3:09:28<4:29:20,  1.38s/it]
 81%|████████  | 50195/61904 [3:09:29<4:22:57,  1.35s/it]
 81%|████████  | 50196/61904 [3:09:31<4:19:19,  1.33s/it]
 81%|████████  | 50197/61904 [3:09:32<4:32:32,  1.40s/it]
 81%|████████  | 50198/61904 [3:09:33<4:27:51,  1.37s/it]
 81%|████████  | 50199/61904 [3:09:35<4:29:14,  1.38s/it]
 81%|████████  | 50200/61904 [3:09:36<4:27:43,  1.37s/it]
                                                         
{'loss': 2.4226, 'learning_rate': 1.1896797614417218e-07, 'epoch': 12.97}

 81%|████████  | 50200/61904 [3:09:36<4:27:43,  1.37s/it]
 81%|████████  | 50201/61904 [3:09:38<4:33:35,  1.40s/it]
 81%|████████  | 50202/61904 [3:09:39<4:26:53,  1.37s/it]
 81%|████████  | 50203/61904 [3:09:40<4:20:08,  1.33s/it]
 81%|████████  | 50204/61904 [3:09:42<4:23:52,  1.35s/it]
 81%|████████  | 50205/61904 [3:09:43<4:22:28,  1.35s/it]
 81%|████████  | 50206/61904 [3:09:44<4:26:10,  1.37s/it]
 81%|████████  | 50207/61904 [3:09:46<4:23:59,  1.35s/it]
 81%|████████  | 50208/61904 [3:09:47<4:29:00,  1.38s/it]
 81%|████████  | 50209/61904 [3:09:49<4:28:28,  1.38s/it]
 81%|████████  | 50210/61904 [3:09:50<4:27:09,  1.37s/it]
 81%|████████  | 50211/61904 [3:09:51<4:31:26,  1.39s/it]
 81%|████████  | 50212/61904 [3:09:53<4:41:57,  1.45s/it]
 81%|████████  | 50213/61904 [3:09:54<4:41:48,  1.45s/it]
 81%|████████  | 50214/61904 [3:09:56<4:33:42,  1.40s/it]
 81%|████████  | 50215/61904 [3:09:57<4:41:20,  1.44s/it]
 81%|████████  | 50216/61904 [3:09:59<4:43:05,  1.45s/it]
 81%|████████  | 50217/61904 [3:10:00<4:40:14,  1.44s/it]
 81%|████████  | 50218/61904 [3:10:01<4:26:53,  1.37s/it]
 81%|████████  | 50219/61904 [3:10:03<4:26:30,  1.37s/it]
 81%|████████  | 50220/61904 [3:10:04<4:27:01,  1.37s/it]
                                                         
{'loss': 2.4162, 'learning_rate': 1.1893556333462985e-07, 'epoch': 12.98}

 81%|████████  | 50220/61904 [3:10:04<4:27:01,  1.37s/it]
 81%|████████  | 50221/61904 [3:10:05<4:30:49,  1.39s/it]
 81%|████████  | 50222/61904 [3:10:07<4:26:33,  1.37s/it]
 81%|████████  | 50223/61904 [3:10:08<4:32:39,  1.40s/it]
 81%|████████  | 50224/61904 [3:10:10<4:28:35,  1.38s/it]
 81%|████████  | 50225/61904 [3:10:11<4:31:24,  1.39s/it]
 81%|████████  | 50226/61904 [3:10:12<4:30:10,  1.39s/it]
 81%|████████  | 50227/61904 [3:10:14<4:33:04,  1.40s/it]
 81%|████████  | 50228/61904 [3:10:15<4:38:22,  1.43s/it]
 81%|████████  | 50229/61904 [3:10:17<4:41:36,  1.45s/it]
 81%|████████  | 50230/61904 [3:10:18<4:36:48,  1.42s/it]
 81%|████████  | 50231/61904 [3:10:20<4:37:00,  1.42s/it]
 81%|████████  | 50232/61904 [3:10:21<4:35:24,  1.42s/it]
 81%|████████  | 50233/61904 [3:10:22<4:30:04,  1.39s/it]
 81%|████████  | 50234/61904 [3:10:24<4:26:04,  1.37s/it]
 81%|████████  | 50235/61904 [3:10:25<4:26:01,  1.37s/it]
 81%|████████  | 50236/61904 [3:10:26<4:30:27,  1.39s/it]
 81%|████████  | 50237/61904 [3:10:28<4:41:57,  1.45s/it]
 81%|████████  | 50238/61904 [3:10:29<4:38:01,  1.43s/it]
 81%|████████  | 50239/61904 [3:10:31<4:24:50,  1.36s/it]
 81%|████████  | 50240/61904 [3:10:32<4:42:11,  1.45s/it]
                                                         
{'loss': 2.509, 'learning_rate': 1.1890315052508751e-07, 'epoch': 12.99}

 81%|████████  | 50240/61904 [3:10:32<4:42:11,  1.45s/it]
 81%|████████  | 50241/61904 [3:10:34<4:33:49,  1.41s/it]
 81%|████████  | 50242/61904 [3:10:35<4:31:44,  1.40s/it]
 81%|████████  | 50243/61904 [3:10:36<4:29:26,  1.39s/it]
 81%|████████  | 50244/61904 [3:10:38<4:27:33,  1.38s/it]
 81%|████████  | 50245/61904 [3:10:39<4:38:56,  1.44s/it]
 81%|████████  | 50246/61904 [3:10:41<4:32:11,  1.40s/it]
 81%|████████  | 50247/61904 [3:10:42<4:36:50,  1.42s/it]
 81%|████████  | 50248/61904 [3:10:43<4:35:00,  1.42s/it]
 81%|████████  | 50249/61904 [3:10:45<4:25:13,  1.37s/it]
 81%|████████  | 50250/61904 [3:10:46<4:21:37,  1.35s/it]
 81%|████████  | 50251/61904 [3:10:47<4:21:41,  1.35s/it]
 81%|████████  | 50252/61904 [3:10:49<4:22:15,  1.35s/it]
 81%|████████  | 50253/61904 [3:10:50<4:31:49,  1.40s/it]
 81%|████████  | 50254/61904 [3:10:51<4:25:38,  1.37s/it]
 81%|████████  | 50255/61904 [3:10:53<4:29:31,  1.39s/it]
 81%|████████  | 50256/61904 [3:10:54<4:38:35,  1.44s/it]
 81%|████████  | 50257/61904 [3:10:56<4:29:43,  1.39s/it]
 81%|████████  | 50258/61904 [3:10:57<4:35:47,  1.42s/it]
 81%|████████  | 50259/61904 [3:10:59<4:30:21,  1.39s/it]
 81%|████████  | 50260/61904 [3:11:00<4:26:02,  1.37s/it]
                                                         
{'loss': 2.4553, 'learning_rate': 1.1887073771554518e-07, 'epoch': 12.99}

 81%|████████  | 50260/61904 [3:11:00<4:26:02,  1.37s/it]
 81%|████████  | 50261/61904 [3:11:01<4:27:27,  1.38s/it]
 81%|████████  | 50262/61904 [3:11:03<4:31:11,  1.40s/it]
 81%|████████  | 50263/61904 [3:11:04<4:24:37,  1.36s/it]
 81%|████████  | 50264/61904 [3:11:06<4:33:11,  1.41s/it]
 81%|████████  | 50265/61904 [3:11:07<4:21:38,  1.35s/it]
 81%|████████  | 50266/61904 [3:11:08<4:30:51,  1.40s/it]
 81%|████████  | 50267/61904 [3:11:10<4:29:10,  1.39s/it]
 81%|████████  | 50268/61904 [3:11:11<4:38:12,  1.43s/it]
 81%|████████  | 50269/61904 [3:11:13<4:46:41,  1.48s/it]
 81%|████████  | 50270/61904 [3:11:14<4:40:25,  1.45s/it]
 81%|████████  | 50271/61904 [3:11:16<4:38:16,  1.44s/it]
 81%|████████  | 50272/61904 [3:11:17<4:28:34,  1.39s/it]
 81%|████████  | 50273/61904 [3:11:18<4:32:14,  1.40s/it]
 81%|████████  | 50274/61904 [3:11:20<4:30:32,  1.40s/it]
 81%|████████  | 50275/61904 [3:11:21<4:39:56,  1.44s/it]
 81%|████████  | 50276/61904 [3:11:22<4:29:56,  1.39s/it]
 81%|████████  | 50277/61904 [3:11:24<4:26:11,  1.37s/it]
 81%|████████  | 50278/61904 [3:11:25<4:22:31,  1.35s/it]
 81%|████████  | 50279/61904 [3:11:26<4:22:43,  1.36s/it]
 81%|████████  | 50280/61904 [3:11:28<4:40:49,  1.45s/it]
                                                         
{'loss': 2.4558, 'learning_rate': 1.1883832490600286e-07, 'epoch': 13.0}

 81%|████████  | 50280/61904 [3:11:28<4:40:49,  1.45s/it]
 81%|████████  | 50281/61904 [3:11:29<4:30:59,  1.40s/it]
 81%|████████  | 50282/61904 [3:11:31<4:35:58,  1.42s/it]
 81%|████████  | 50283/61904 [3:11:32<4:28:34,  1.39s/it]
 81%|████████  | 50284/61904 [3:11:34<4:25:46,  1.37s/it]
 81%|████████  | 50285/61904 [3:11:35<4:18:56,  1.34s/it]
 81%|████████  | 50286/61904 [3:11:36<4:18:29,  1.33s/it]
 81%|████████  | 50287/61904 [3:11:38<4:31:02,  1.40s/it]
 81%|████████  | 50288/61904 [3:11:39<4:30:42,  1.40s/it]
 81%|████████  | 50289/61904 [3:11:40<4:24:24,  1.37s/it]
 81%|████████  | 50290/61904 [3:11:42<4:23:29,  1.36s/it]
 81%|████████  | 50291/61904 [3:11:43<4:26:52,  1.38s/it]
 81%|████████  | 50292/61904 [3:11:45<4:31:56,  1.41s/it]
 81%|████████  | 50293/61904 [3:11:46<4:34:31,  1.42s/it]
 81%|████████  | 50294/61904 [3:11:48<4:39:07,  1.44s/it]
 81%|████████  | 50295/61904 [3:11:49<4:38:51,  1.44s/it]
 81%|████████  | 50296/61904 [3:11:50<4:35:51,  1.43s/it]
 81%|████████▏ | 50297/61904 [3:11:52<4:28:06,  1.39s/it]
 81%|████████▏ | 50298/61904 [3:11:53<4:26:24,  1.38s/it]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/861 [00:00<?, ?it/s]

  0%|          | 2/861 [00:01<08:30,  1.68it/s]

  0%|          | 3/861 [00:02<15:17,  1.07s/it]

  0%|          | 4/861 [00:03<14:05,  1.01it/s]

  1%|          | 5/861 [00:04<14:14,  1.00it/s]

  1%|          | 6/861 [00:06<15:30,  1.09s/it]

  1%|          | 7/861 [00:06<12:41,  1.12it/s]

  1%|          | 8/861 [00:07<11:56,  1.19it/s]

  1%|          | 9/861 [00:07<11:24,  1.24it/s]

  1%|          | 10/861 [00:08<11:21,  1.25it/s]

  1%|▏         | 11/861 [00:10<14:10,  1.00s/it]

  1%|▏         | 12/861 [00:11<15:12,  1.08s/it]

  2%|▏         | 13/861 [00:12<14:03,  1.01it/s]

  2%|▏         | 14/861 [00:12<11:03,  1.28it/s]

  2%|▏         | 15/861 [00:13<09:58,  1.41it/s]

  2%|▏         | 16/861 [00:13<08:25,  1.67it/s]

  2%|▏         | 17/861 [00:14<11:23,  1.23it/s]

  2%|▏         | 18/861 [00:15<09:18,  1.51it/s]

  2%|▏         | 19/861 [00:16<14:05,  1.00s/it]

  2%|▏         | 20/861 [00:18<14:33,  1.04s/it]

  2%|▏         | 21/861 [00:19<16:54,  1.21s/it]

  3%|▎         | 22/861 [00:21<17:47,  1.27s/it]

  3%|▎         | 23/861 [00:21<13:47,  1.01it/s]

  3%|▎         | 24/861 [00:22<16:13,  1.16s/it]

  3%|▎         | 25/861 [00:23<14:43,  1.06s/it]

  3%|▎         | 26/861 [00:24<15:10,  1.09s/it]

  3%|▎         | 27/861 [00:26<16:09,  1.16s/it]

  3%|▎         | 28/861 [00:28<20:58,  1.51s/it]

  3%|▎         | 29/861 [00:28<16:04,  1.16s/it]

  3%|▎         | 30/861 [00:30<16:30,  1.19s/it]

  4%|▎         | 31/861 [00:30<13:44,  1.01it/s]

  4%|▎         | 32/861 [00:31<11:17,  1.22it/s]

  4%|▍         | 33/861 [00:32<12:14,  1.13it/s]

  4%|▍         | 34/861 [00:33<12:14,  1.13it/s]

  4%|▍         | 35/861 [00:35<17:12,  1.25s/it]

  4%|▍         | 36/861 [00:35<15:19,  1.11s/it]

  4%|▍         | 37/861 [00:36<14:28,  1.05s/it]

  4%|▍         | 38/861 [00:38<15:20,  1.12s/it]

  5%|▍         | 39/861 [00:38<13:36,  1.01it/s]

  5%|▍         | 40/861 [00:39<12:29,  1.10it/s]

  5%|▍         | 41/861 [00:39<10:05,  1.35it/s]

  5%|▍         | 42/861 [00:41<11:47,  1.16it/s]

  5%|▍         | 43/861 [00:42<12:49,  1.06it/s]

  5%|▌         | 44/861 [00:42<12:23,  1.10it/s]

  5%|▌         | 45/861 [00:43<12:14,  1.11it/s]

  5%|▌         | 46/861 [00:45<16:34,  1.22s/it]

  5%|▌         | 47/861 [00:47<16:51,  1.24s/it]

  6%|▌         | 48/861 [00:48<18:24,  1.36s/it]

  6%|▌         | 49/861 [00:49<17:53,  1.32s/it]

  6%|▌         | 50/861 [00:50<13:13,  1.02it/s]

  6%|▌         | 51/861 [00:51<13:40,  1.01s/it]

  6%|▌         | 52/861 [00:51<12:23,  1.09it/s]

  6%|▌         | 53/861 [00:52<11:13,  1.20it/s]

  6%|▋         | 54/861 [00:52<08:47,  1.53it/s]

  6%|▋         | 55/861 [00:53<08:24,  1.60it/s]

  7%|▋         | 56/861 [00:54<09:18,  1.44it/s]

  7%|▋         | 57/861 [00:54<07:44,  1.73it/s]

  7%|▋         | 58/861 [00:54<06:35,  2.03it/s]

  7%|▋         | 59/861 [00:55<08:07,  1.65it/s]

  7%|▋         | 60/861 [00:56<07:46,  1.72it/s]

  7%|▋         | 61/861 [00:56<06:59,  1.91it/s]

  7%|▋         | 62/861 [00:57<06:21,  2.09it/s]

  7%|▋         | 63/861 [00:57<06:19,  2.10it/s]

  7%|▋         | 64/861 [00:57<06:08,  2.16it/s]

  8%|▊         | 65/861 [00:58<06:08,  2.16it/s]

  8%|▊         | 66/861 [00:58<06:14,  2.13it/s]

  8%|▊         | 67/861 [00:59<07:36,  1.74it/s]

  8%|▊         | 68/861 [01:00<09:02,  1.46it/s]

  8%|▊         | 69/861 [01:01<10:25,  1.27it/s]

  8%|▊         | 70/861 [01:03<12:57,  1.02it/s]

  8%|▊         | 71/861 [01:04<14:28,  1.10s/it]

  8%|▊         | 72/861 [01:05<13:37,  1.04s/it]

  8%|▊         | 73/861 [01:05<10:32,  1.25it/s]

  9%|▊         | 74/861 [01:06<09:31,  1.38it/s]

  9%|▊         | 75/861 [01:07<11:08,  1.18it/s]

  9%|▉         | 76/861 [01:07<09:43,  1.35it/s]

  9%|▉         | 77/861 [01:08<10:58,  1.19it/s]

  9%|▉         | 78/861 [01:09<10:32,  1.24it/s]

  9%|▉         | 79/861 [01:10<11:38,  1.12it/s]

  9%|▉         | 80/861 [01:11<10:14,  1.27it/s]

  9%|▉         | 81/861 [01:12<10:48,  1.20it/s]

 10%|▉         | 82/861 [01:12<09:21,  1.39it/s]

 10%|▉         | 83/861 [01:13<09:17,  1.39it/s]

 10%|▉         | 84/861 [01:14<11:13,  1.15it/s]

 10%|▉         | 85/861 [01:15<10:14,  1.26it/s]

 10%|▉         | 86/861 [01:15<09:02,  1.43it/s]

 10%|█         | 87/861 [01:16<10:46,  1.20it/s]

 10%|█         | 88/861 [01:16<08:14,  1.56it/s]

 10%|█         | 89/861 [01:17<08:15,  1.56it/s]

 10%|█         | 90/861 [01:19<13:49,  1.08s/it]

 11%|█         | 91/861 [01:20<11:58,  1.07it/s]

 11%|█         | 92/861 [01:21<11:46,  1.09it/s]

 11%|█         | 93/861 [01:22<12:03,  1.06it/s]

 11%|█         | 94/861 [01:22<09:28,  1.35it/s]

 11%|█         | 95/861 [01:23<09:12,  1.39it/s]

 11%|█         | 96/861 [01:24<10:11,  1.25it/s]

 11%|█▏        | 97/861 [01:25<11:57,  1.07it/s]

 11%|█▏        | 98/861 [01:26<12:02,  1.06it/s]

 11%|█▏        | 99/861 [01:28<14:43,  1.16s/it]

 12%|█▏        | 100/861 [01:28<12:23,  1.02it/s]

 12%|█▏        | 101/861 [01:29<10:38,  1.19it/s]

 12%|█▏        | 102/861 [01:29<09:26,  1.34it/s]

 12%|█▏        | 103/861 [01:29<08:03,  1.57it/s]

 12%|█▏        | 104/861 [01:31<11:39,  1.08it/s]

 12%|█▏        | 105/861 [01:32<12:12,  1.03it/s]

 12%|█▏        | 106/861 [01:33<10:44,  1.17it/s]

 12%|█▏        | 107/861 [01:33<09:26,  1.33it/s]

 13%|█▎        | 108/861 [01:33<07:31,  1.67it/s]

 13%|█▎        | 109/861 [01:34<06:12,  2.02it/s]

 13%|█▎        | 110/861 [01:35<07:22,  1.70it/s]

 13%|█▎        | 111/861 [01:36<09:41,  1.29it/s]

 13%|█▎        | 112/861 [01:36<07:54,  1.58it/s]

 13%|█▎        | 113/861 [01:37<08:15,  1.51it/s]

 13%|█▎        | 114/861 [01:38<08:36,  1.45it/s]

 13%|█▎        | 115/861 [01:38<07:40,  1.62it/s]

 13%|█▎        | 116/861 [01:38<06:38,  1.87it/s]

 14%|█▎        | 117/861 [01:40<09:30,  1.30it/s]

 14%|█▎        | 118/861 [01:40<09:31,  1.30it/s]

 14%|█▍        | 119/861 [01:41<08:55,  1.39it/s]

 14%|█▍        | 120/861 [01:41<07:00,  1.76it/s]

 14%|█▍        | 121/861 [01:42<08:38,  1.43it/s]

 14%|█▍        | 122/861 [01:43<10:35,  1.16it/s]

 14%|█▍        | 123/861 [01:44<10:02,  1.23it/s]

 14%|█▍        | 124/861 [01:46<12:43,  1.04s/it]

 15%|█▍        | 125/861 [01:46<11:29,  1.07it/s]

 15%|█▍        | 126/861 [01:48<12:32,  1.02s/it]

 15%|█▍        | 127/861 [01:49<13:10,  1.08s/it]

 15%|█▍        | 128/861 [01:49<11:02,  1.11it/s]

 15%|█▍        | 129/861 [01:50<11:39,  1.05it/s]

 15%|█▌        | 130/861 [01:51<11:17,  1.08it/s]

 15%|█▌        | 131/861 [01:52<10:38,  1.14it/s]

 15%|█▌        | 132/861 [01:53<10:45,  1.13it/s]

 15%|█▌        | 133/861 [01:54<10:49,  1.12it/s]

 16%|█▌        | 134/861 [01:54<08:16,  1.46it/s]

 16%|█▌        | 135/861 [01:54<07:16,  1.66it/s]

 16%|█▌        | 136/861 [01:55<07:08,  1.69it/s]

 16%|█▌        | 137/861 [01:55<06:17,  1.92it/s]

 16%|█▌        | 138/861 [01:56<05:59,  2.01it/s]

 16%|█▌        | 139/861 [01:56<05:28,  2.20it/s]

 16%|█▋        | 140/861 [01:57<05:12,  2.30it/s]

 16%|█▋        | 141/861 [01:57<05:01,  2.39it/s]

 16%|█▋        | 142/861 [01:57<04:58,  2.41it/s]

 17%|█▋        | 143/861 [01:59<08:23,  1.43it/s]

 17%|█▋        | 144/861 [02:00<09:53,  1.21it/s]

 17%|█▋        | 145/861 [02:00<08:39,  1.38it/s]

 17%|█▋        | 146/861 [02:01<08:22,  1.42it/s]

 17%|█▋        | 147/861 [02:02<08:43,  1.36it/s]

 17%|█▋        | 148/861 [02:02<06:56,  1.71it/s]

 17%|█▋        | 149/861 [02:02<06:13,  1.90it/s]

 17%|█▋        | 150/861 [02:04<10:06,  1.17it/s]

 18%|█▊        | 151/861 [02:06<12:52,  1.09s/it]

 18%|█▊        | 152/861 [02:07<12:48,  1.08s/it]

 18%|█▊        | 153/861 [02:08<12:10,  1.03s/it]

 18%|█▊        | 154/861 [02:08<09:49,  1.20it/s]

 18%|█▊        | 155/861 [02:10<12:32,  1.07s/it]

 18%|█▊        | 156/861 [02:11<12:50,  1.09s/it]

 18%|█▊        | 157/861 [02:12<11:32,  1.02it/s]

 18%|█▊        | 158/861 [02:12<11:16,  1.04it/s]

 18%|█▊        | 159/861 [02:13<09:59,  1.17it/s]

 19%|█▊        | 160/861 [02:14<09:48,  1.19it/s]

 19%|█▊        | 161/861 [02:16<13:35,  1.16s/it]

 19%|█▉        | 162/861 [02:16<10:25,  1.12it/s]

 19%|█▉        | 163/861 [02:16<08:08,  1.43it/s]

 19%|█▉        | 164/861 [02:18<10:13,  1.14it/s]

 19%|█▉        | 165/861 [02:18<09:43,  1.19it/s]

 19%|█▉        | 166/861 [02:19<09:44,  1.19it/s]

 19%|█▉        | 167/861 [02:19<07:25,  1.56it/s]

 20%|█▉        | 168/861 [02:20<06:51,  1.68it/s]

 20%|█▉        | 169/861 [02:21<08:01,  1.44it/s]

 20%|█▉        | 170/861 [02:22<08:22,  1.38it/s]

 20%|█▉        | 171/861 [02:22<08:15,  1.39it/s]

 20%|█▉        | 172/861 [02:23<07:24,  1.55it/s]

 20%|██        | 173/861 [02:23<07:32,  1.52it/s]

 20%|██        | 174/861 [02:25<10:56,  1.05it/s]

 20%|██        | 175/861 [02:26<10:21,  1.10it/s]

 20%|██        | 176/861 [02:26<07:56,  1.44it/s]

 21%|██        | 177/861 [02:27<07:51,  1.45it/s]

 21%|██        | 178/861 [02:28<08:38,  1.32it/s]

 21%|██        | 179/861 [02:28<08:32,  1.33it/s]

 21%|██        | 180/861 [02:29<08:09,  1.39it/s]

 21%|██        | 181/861 [02:29<07:01,  1.61it/s]

 21%|██        | 182/861 [02:30<06:20,  1.78it/s]

 21%|██▏       | 183/861 [02:31<07:29,  1.51it/s]

 21%|██▏       | 184/861 [02:32<08:56,  1.26it/s]

 21%|██▏       | 185/861 [02:32<07:55,  1.42it/s]

 22%|██▏       | 186/861 [02:33<06:47,  1.66it/s]

 22%|██▏       | 187/861 [02:34<07:57,  1.41it/s]

 22%|██▏       | 188/861 [02:35<08:37,  1.30it/s]

 22%|██▏       | 189/861 [02:36<11:08,  1.00it/s]

 22%|██▏       | 190/861 [02:38<12:43,  1.14s/it]

 22%|██▏       | 191/861 [02:38<10:25,  1.07it/s]

 22%|██▏       | 192/861 [02:39<09:51,  1.13it/s]

 22%|██▏       | 193/861 [02:40<10:59,  1.01it/s]

 23%|██▎       | 194/861 [02:41<09:23,  1.18it/s]

 23%|██▎       | 195/861 [02:41<08:00,  1.39it/s]

 23%|██▎       | 196/861 [02:41<07:08,  1.55it/s]

 23%|██▎       | 197/861 [02:42<06:35,  1.68it/s]

 23%|██▎       | 198/861 [02:42<05:45,  1.92it/s]

 23%|██▎       | 199/861 [02:44<08:16,  1.33it/s]

 23%|██▎       | 200/861 [02:45<09:10,  1.20it/s]

 23%|██▎       | 201/861 [02:46<09:53,  1.11it/s]

 23%|██▎       | 202/861 [02:47<10:31,  1.04it/s]

 24%|██▎       | 203/861 [02:47<08:17,  1.32it/s]

 24%|██▎       | 204/861 [02:47<06:22,  1.72it/s]

 24%|██▍       | 205/861 [02:48<05:48,  1.88it/s]

 24%|██▍       | 206/861 [02:48<06:20,  1.72it/s]

 24%|██▍       | 207/861 [02:49<07:01,  1.55it/s]

 24%|██▍       | 208/861 [02:50<07:13,  1.51it/s]

 24%|██▍       | 209/861 [02:50<06:59,  1.55it/s]

 24%|██▍       | 210/861 [02:51<07:29,  1.45it/s]

 25%|██▍       | 211/861 [02:53<09:52,  1.10it/s]

 25%|██▍       | 212/861 [02:54<09:48,  1.10it/s]

 25%|██▍       | 213/861 [02:54<08:27,  1.28it/s]

 25%|██▍       | 214/861 [02:55<07:43,  1.40it/s]

 25%|██▍       | 215/861 [02:55<08:16,  1.30it/s]

 25%|██▌       | 216/861 [02:56<07:10,  1.50it/s]

 25%|██▌       | 217/861 [02:56<05:53,  1.82it/s]

 25%|██▌       | 218/861 [02:57<05:20,  2.00it/s]

 25%|██▌       | 219/861 [02:58<06:54,  1.55it/s]

 26%|██▌       | 220/861 [02:58<07:06,  1.50it/s]

 26%|██▌       | 221/861 [02:59<06:30,  1.64it/s]

 26%|██▌       | 222/861 [03:00<08:36,  1.24it/s]

 26%|██▌       | 223/861 [03:01<09:13,  1.15it/s]

 26%|██▌       | 224/861 [03:02<08:20,  1.27it/s]

 26%|██▌       | 225/861 [03:03<10:08,  1.05it/s]

 26%|██▌       | 226/861 [03:05<11:57,  1.13s/it]

 26%|██▋       | 227/861 [03:05<10:59,  1.04s/it]

 26%|██▋       | 228/861 [03:06<10:49,  1.03s/it]

 27%|██▋       | 229/861 [03:07<09:18,  1.13it/s]

 27%|██▋       | 230/861 [03:08<09:36,  1.09it/s]

 27%|██▋       | 231/861 [03:10<14:43,  1.40s/it]

 27%|██▋       | 232/861 [03:11<10:50,  1.03s/it]

 27%|██▋       | 233/861 [03:11<09:52,  1.06it/s]

 27%|██▋       | 234/861 [03:12<08:42,  1.20it/s]

 27%|██▋       | 235/861 [03:13<08:54,  1.17it/s]

 27%|██▋       | 236/861 [03:13<08:23,  1.24it/s]

 28%|██▊       | 237/861 [03:14<08:08,  1.28it/s]

 28%|██▊       | 238/861 [03:15<06:39,  1.56it/s]

 28%|██▊       | 239/861 [03:16<08:07,  1.28it/s]

 28%|██▊       | 240/861 [03:16<08:07,  1.27it/s]

 28%|██▊       | 241/861 [03:18<10:05,  1.02it/s]

 28%|██▊       | 242/861 [03:18<08:42,  1.18it/s]

 28%|██▊       | 243/861 [03:20<09:36,  1.07it/s]

 28%|██▊       | 244/861 [03:20<09:03,  1.13it/s]

 28%|██▊       | 245/861 [03:22<10:32,  1.03s/it]

 29%|██▊       | 246/861 [03:23<10:07,  1.01it/s]

 29%|██▊       | 247/861 [03:23<08:09,  1.25it/s]

 29%|██▉       | 248/861 [03:23<06:14,  1.64it/s]

 29%|██▉       | 249/861 [03:24<05:59,  1.70it/s]

 29%|██▉       | 250/861 [03:25<07:14,  1.41it/s]

 29%|██▉       | 251/861 [03:25<07:36,  1.34it/s]

 29%|██▉       | 252/861 [03:26<07:23,  1.37it/s]

 29%|██▉       | 253/861 [03:27<06:51,  1.48it/s]

 30%|██▉       | 254/861 [03:27<05:37,  1.80it/s]

 30%|██▉       | 255/861 [03:28<06:13,  1.62it/s]

 30%|██▉       | 256/861 [03:29<08:21,  1.21it/s]

 30%|██▉       | 257/861 [03:30<09:04,  1.11it/s]

 30%|██▉       | 258/861 [03:31<09:28,  1.06it/s]

 30%|███       | 259/861 [03:32<10:04,  1.00s/it]

 30%|███       | 260/861 [03:33<09:32,  1.05it/s]

 30%|███       | 261/861 [03:36<13:45,  1.38s/it]

 30%|███       | 262/861 [03:36<11:26,  1.15s/it]

 31%|███       | 263/861 [03:36<08:30,  1.17it/s]

 31%|███       | 264/861 [03:37<08:13,  1.21it/s]

 31%|███       | 265/861 [03:38<07:07,  1.39it/s]

 31%|███       | 266/861 [03:38<05:54,  1.68it/s]

 31%|███       | 267/861 [03:38<05:38,  1.75it/s]

 31%|███       | 268/861 [03:39<05:59,  1.65it/s]

 31%|███       | 269/861 [03:40<06:07,  1.61it/s]

 31%|███▏      | 270/861 [03:40<06:40,  1.48it/s]

 31%|███▏      | 271/861 [03:41<06:55,  1.42it/s]

 32%|███▏      | 272/861 [03:42<08:30,  1.15it/s]

 32%|███▏      | 273/861 [03:43<08:46,  1.12it/s]

 32%|███▏      | 274/861 [03:45<10:18,  1.05s/it]

 32%|███▏      | 275/861 [03:45<07:43,  1.26it/s]

 32%|███▏      | 276/861 [03:46<08:16,  1.18it/s]

 32%|███▏      | 277/861 [03:47<09:52,  1.01s/it]

 32%|███▏      | 278/861 [03:49<10:41,  1.10s/it]

 32%|███▏      | 279/861 [03:50<09:55,  1.02s/it]

 33%|███▎      | 280/861 [03:51<09:53,  1.02s/it]

 33%|███▎      | 281/861 [03:52<10:57,  1.13s/it]

 33%|███▎      | 282/861 [03:53<09:58,  1.03s/it]

 33%|███▎      | 283/861 [03:54<08:58,  1.07it/s]

 33%|███▎      | 284/861 [03:54<07:24,  1.30it/s]

 33%|███▎      | 285/861 [03:55<06:58,  1.38it/s]

 33%|███▎      | 286/861 [03:57<11:11,  1.17s/it]

 33%|███▎      | 287/861 [03:59<13:06,  1.37s/it]

 33%|███▎      | 288/861 [04:00<11:53,  1.25s/it]

 34%|███▎      | 289/861 [04:00<09:21,  1.02it/s]

 34%|███▎      | 290/861 [04:01<08:19,  1.14it/s]

 34%|███▍      | 291/861 [04:01<07:59,  1.19it/s]

 34%|███▍      | 292/861 [04:02<08:55,  1.06it/s]

 34%|███▍      | 293/861 [04:03<08:53,  1.07it/s]

 34%|███▍      | 294/861 [04:05<09:24,  1.00it/s]

 34%|███▍      | 295/861 [04:05<07:12,  1.31it/s]

 34%|███▍      | 296/861 [04:05<06:53,  1.37it/s]

 34%|███▍      | 297/861 [04:07<08:37,  1.09it/s]

 35%|███▍      | 298/861 [04:08<09:32,  1.02s/it]

 35%|███▍      | 299/861 [04:10<12:15,  1.31s/it]

 35%|███▍      | 300/861 [04:11<10:27,  1.12s/it]

 35%|███▍      | 301/861 [04:13<13:53,  1.49s/it]

 35%|███▌      | 302/861 [04:13<10:24,  1.12s/it]

 35%|███▌      | 303/861 [04:15<11:16,  1.21s/it]

 35%|███▌      | 304/861 [04:16<10:45,  1.16s/it]

 35%|███▌      | 305/861 [04:17<11:46,  1.27s/it]

 36%|███▌      | 306/861 [04:19<12:40,  1.37s/it]

 36%|███▌      | 307/861 [04:21<14:14,  1.54s/it]

 36%|███▌      | 308/861 [04:21<10:27,  1.13s/it]

 36%|███▌      | 309/861 [04:21<08:13,  1.12it/s]

 36%|███▌      | 310/861 [04:22<07:31,  1.22it/s]

 36%|███▌      | 311/861 [04:23<07:56,  1.15it/s]

 36%|███▌      | 312/861 [04:24<08:29,  1.08it/s]

 36%|███▋      | 313/861 [04:26<10:14,  1.12s/it]

 36%|███▋      | 314/861 [04:27<09:48,  1.08s/it]

 37%|███▋      | 315/861 [04:27<08:29,  1.07it/s]

 37%|███▋      | 316/861 [04:28<09:08,  1.01s/it]

 37%|███▋      | 317/861 [04:29<06:59,  1.30it/s]

 37%|███▋      | 318/861 [04:29<05:36,  1.62it/s]

 37%|███▋      | 319/861 [04:31<08:31,  1.06it/s]

 37%|███▋      | 320/861 [04:31<08:03,  1.12it/s]

 37%|███▋      | 321/861 [04:33<09:28,  1.05s/it]

 37%|███▋      | 322/861 [04:35<11:36,  1.29s/it]

 38%|███▊      | 323/861 [04:35<10:15,  1.14s/it]

 38%|███▊      | 324/861 [04:37<10:55,  1.22s/it]

 38%|███▊      | 325/861 [04:38<11:06,  1.24s/it]

 38%|███▊      | 326/861 [04:38<08:13,  1.08it/s]

 38%|███▊      | 327/861 [04:39<08:22,  1.06it/s]

 38%|███▊      | 328/861 [04:40<08:32,  1.04it/s]

 38%|███▊      | 329/861 [04:41<08:08,  1.09it/s]

 38%|███▊      | 330/861 [04:42<07:36,  1.16it/s]

 38%|███▊      | 331/861 [04:45<13:48,  1.56s/it]

 39%|███▊      | 332/861 [04:46<11:59,  1.36s/it]

 39%|███▊      | 333/861 [04:47<12:22,  1.41s/it]

 39%|███▉      | 334/861 [04:49<12:22,  1.41s/it]

 39%|███▉      | 335/861 [04:50<11:00,  1.26s/it]

 39%|███▉      | 336/861 [04:51<11:36,  1.33s/it]

 39%|███▉      | 337/861 [04:52<09:42,  1.11s/it]

 39%|███▉      | 338/861 [04:54<12:16,  1.41s/it]

 39%|███▉      | 339/861 [04:55<11:04,  1.27s/it]

 39%|███▉      | 340/861 [04:55<08:45,  1.01s/it]

 40%|███▉      | 341/861 [04:56<06:52,  1.26it/s]

 40%|███▉      | 342/861 [04:56<06:33,  1.32it/s]

 40%|███▉      | 343/861 [04:57<06:52,  1.26it/s]

 40%|███▉      | 344/861 [04:58<06:01,  1.43it/s]

 40%|████      | 345/861 [04:59<07:00,  1.23it/s]

 40%|████      | 346/861 [05:00<07:24,  1.16it/s]

 40%|████      | 347/861 [05:00<06:15,  1.37it/s]

 40%|████      | 348/861 [05:01<05:56,  1.44it/s]

 41%|████      | 349/861 [05:01<05:59,  1.43it/s]

 41%|████      | 350/861 [05:02<06:38,  1.28it/s]

 41%|████      | 351/861 [05:03<06:19,  1.34it/s]

 41%|████      | 352/861 [05:04<06:24,  1.32it/s]

 41%|████      | 353/861 [05:04<06:13,  1.36it/s]

 41%|████      | 354/861 [05:05<05:56,  1.42it/s]

 41%|████      | 355/861 [05:06<05:14,  1.61it/s]

 41%|████▏     | 356/861 [05:06<04:44,  1.78it/s]

 41%|████▏     | 357/861 [05:06<04:02,  2.07it/s]

 42%|████▏     | 358/861 [05:07<04:47,  1.75it/s]

 42%|████▏     | 359/861 [05:09<07:31,  1.11it/s]

 42%|████▏     | 360/861 [05:10<08:04,  1.03it/s]

 42%|████▏     | 361/861 [05:11<07:45,  1.07it/s]

 42%|████▏     | 362/861 [05:12<08:06,  1.03it/s]

 42%|████▏     | 363/861 [05:12<07:11,  1.15it/s]

 42%|████▏     | 364/861 [05:13<06:36,  1.25it/s]

 42%|████▏     | 365/861 [05:15<09:36,  1.16s/it]

 43%|████▎     | 366/861 [05:16<09:08,  1.11s/it]

 43%|████▎     | 367/861 [05:18<10:35,  1.29s/it]

 43%|████▎     | 368/861 [05:19<09:36,  1.17s/it]

 43%|████▎     | 369/861 [05:19<08:29,  1.04s/it]

 43%|████▎     | 370/861 [05:20<07:28,  1.10it/s]

 43%|████▎     | 371/861 [05:21<07:06,  1.15it/s]

 43%|████▎     | 372/861 [05:22<07:35,  1.07it/s]

 43%|████▎     | 373/861 [05:22<06:49,  1.19it/s]

 43%|████▎     | 374/861 [05:25<10:05,  1.24s/it]

 44%|████▎     | 375/861 [05:26<11:18,  1.40s/it]

 44%|████▎     | 376/861 [05:27<09:36,  1.19s/it]

 44%|████▍     | 377/861 [05:29<11:06,  1.38s/it]

 44%|████▍     | 378/861 [05:31<12:31,  1.56s/it]

 44%|████▍     | 379/861 [05:31<09:10,  1.14s/it]

 44%|████▍     | 380/861 [05:32<08:42,  1.09s/it]

 44%|████▍     | 381/861 [05:33<08:23,  1.05s/it]

 44%|████▍     | 382/861 [05:34<07:25,  1.07it/s]

 44%|████▍     | 383/861 [05:35<07:35,  1.05it/s]

 45%|████▍     | 384/861 [05:35<07:08,  1.11it/s]

 45%|████▍     | 385/861 [05:36<05:49,  1.36it/s]

 45%|████▍     | 386/861 [05:37<07:29,  1.06it/s]

 45%|████▍     | 387/861 [05:39<08:36,  1.09s/it]

 45%|████▌     | 388/861 [05:39<07:42,  1.02it/s]

 45%|████▌     | 389/861 [05:40<06:25,  1.22it/s]

 45%|████▌     | 390/861 [05:40<05:59,  1.31it/s]

 45%|████▌     | 391/861 [05:41<06:12,  1.26it/s]

 46%|████▌     | 392/861 [05:42<06:25,  1.22it/s]

 46%|████▌     | 393/861 [05:43<07:28,  1.04it/s]

 46%|████▌     | 394/861 [05:45<08:08,  1.05s/it]

 46%|████▌     | 395/861 [05:45<07:01,  1.11it/s]

 46%|████▌     | 396/861 [05:46<05:56,  1.30it/s]

 46%|████▌     | 397/861 [05:46<04:35,  1.68it/s]

 46%|████▌     | 398/861 [05:47<04:48,  1.61it/s]

 46%|████▋     | 399/861 [05:48<05:42,  1.35it/s]

 46%|████▋     | 400/861 [05:49<06:23,  1.20it/s]

 47%|████▋     | 401/861 [05:49<05:28,  1.40it/s]

 47%|████▋     | 402/861 [05:50<05:41,  1.34it/s]

 47%|████▋     | 403/861 [05:51<05:33,  1.37it/s]

 47%|████▋     | 404/861 [05:52<06:16,  1.21it/s]

 47%|████▋     | 405/861 [05:52<05:13,  1.45it/s]

 47%|████▋     | 406/861 [05:53<06:11,  1.23it/s]

 47%|████▋     | 407/861 [05:54<06:37,  1.14it/s]

 47%|████▋     | 408/861 [05:55<06:03,  1.25it/s]

 48%|████▊     | 409/861 [05:55<05:23,  1.40it/s]

 48%|████▊     | 410/861 [05:56<05:26,  1.38it/s]

 48%|████▊     | 411/861 [05:56<04:34,  1.64it/s]

 48%|████▊     | 412/861 [05:57<05:23,  1.39it/s]

 48%|████▊     | 413/861 [05:58<05:22,  1.39it/s]

 48%|████▊     | 414/861 [05:59<04:53,  1.52it/s]

 48%|████▊     | 415/861 [05:59<04:19,  1.72it/s]

 48%|████▊     | 416/861 [06:00<04:14,  1.75it/s]

 48%|████▊     | 417/861 [06:00<04:36,  1.61it/s]

 49%|████▊     | 418/861 [06:01<04:16,  1.73it/s]

 49%|████▊     | 419/861 [06:02<04:58,  1.48it/s]

 49%|████▉     | 420/861 [06:02<04:53,  1.50it/s]

 49%|████▉     | 421/861 [06:03<04:31,  1.62it/s]

 49%|████▉     | 422/861 [06:03<03:50,  1.90it/s]

 49%|████▉     | 423/861 [06:04<04:47,  1.52it/s]

 49%|████▉     | 424/861 [06:05<04:24,  1.66it/s]

 49%|████▉     | 425/861 [06:05<04:39,  1.56it/s]

 49%|████▉     | 426/861 [06:07<05:58,  1.21it/s]

 50%|████▉     | 427/861 [06:07<05:56,  1.22it/s]

 50%|████▉     | 428/861 [06:08<05:38,  1.28it/s]

 50%|████▉     | 429/861 [06:09<06:01,  1.19it/s]

 50%|████▉     | 430/861 [06:10<06:17,  1.14it/s]

 50%|█████     | 431/861 [06:11<07:21,  1.03s/it]

 50%|█████     | 432/861 [06:13<08:12,  1.15s/it]

 50%|█████     | 433/861 [06:14<08:22,  1.17s/it]

 50%|█████     | 434/861 [06:14<06:51,  1.04it/s]

 51%|█████     | 435/861 [06:15<05:09,  1.37it/s]

 51%|█████     | 436/861 [06:15<04:12,  1.68it/s]

 51%|█████     | 437/861 [06:15<04:00,  1.76it/s]

 51%|█████     | 438/861 [06:16<03:29,  2.02it/s]

 51%|█████     | 439/861 [06:16<03:49,  1.84it/s]

 51%|█████     | 440/861 [06:17<03:18,  2.12it/s]

 51%|█████     | 441/861 [06:17<03:00,  2.33it/s]

 51%|█████▏    | 442/861 [06:18<03:14,  2.15it/s]

 51%|█████▏    | 443/861 [06:18<03:17,  2.11it/s]

 52%|█████▏    | 444/861 [06:19<03:32,  1.96it/s]

 52%|█████▏    | 445/861 [06:19<03:09,  2.20it/s]

 52%|█████▏    | 446/861 [06:19<02:59,  2.31it/s]

 52%|█████▏    | 447/861 [06:20<04:02,  1.71it/s]

 52%|█████▏    | 448/861 [06:22<05:19,  1.29it/s]

 52%|█████▏    | 449/861 [06:22<04:58,  1.38it/s]

 52%|█████▏    | 450/861 [06:23<05:42,  1.20it/s]

 52%|█████▏    | 451/861 [06:24<04:59,  1.37it/s]

 52%|█████▏    | 452/861 [06:24<04:48,  1.42it/s]

 53%|█████▎    | 453/861 [06:25<04:18,  1.58it/s]

 53%|█████▎    | 454/861 [06:26<04:21,  1.55it/s]

 53%|█████▎    | 455/861 [06:26<03:43,  1.82it/s]

 53%|█████▎    | 456/861 [06:26<03:42,  1.82it/s]

 53%|█████▎    | 457/861 [06:27<03:48,  1.77it/s]

 53%|█████▎    | 458/861 [06:28<04:16,  1.57it/s]

 53%|█████▎    | 459/861 [06:28<03:37,  1.85it/s]

 53%|█████▎    | 460/861 [06:29<04:07,  1.62it/s]

 54%|█████▎    | 461/861 [06:30<04:48,  1.38it/s]

 54%|█████▎    | 462/861 [06:30<04:21,  1.52it/s]

 54%|█████▍    | 463/861 [06:31<04:01,  1.65it/s]

 54%|█████▍    | 464/861 [06:31<03:37,  1.82it/s]

 54%|█████▍    | 465/861 [06:31<02:58,  2.22it/s]

 54%|█████▍    | 466/861 [06:32<03:08,  2.10it/s]

 54%|█████▍    | 467/861 [06:33<04:20,  1.51it/s]

 54%|█████▍    | 468/861 [06:33<03:38,  1.80it/s]

 54%|█████▍    | 469/861 [06:34<03:35,  1.82it/s]

 55%|█████▍    | 470/861 [06:34<03:00,  2.17it/s]

 55%|█████▍    | 471/861 [06:35<03:24,  1.91it/s]

 55%|█████▍    | 472/861 [06:35<03:19,  1.95it/s]

 55%|█████▍    | 473/861 [06:36<02:57,  2.18it/s]

 55%|█████▌    | 474/861 [06:36<02:39,  2.43it/s]

 55%|█████▌    | 475/861 [06:37<03:01,  2.13it/s]

 55%|█████▌    | 476/861 [06:37<02:49,  2.27it/s]

 55%|█████▌    | 477/861 [06:38<03:15,  1.96it/s]

 56%|█████▌    | 478/861 [06:38<03:09,  2.02it/s]

 56%|█████▌    | 479/861 [06:38<02:40,  2.38it/s]

 56%|█████▌    | 480/861 [06:39<03:11,  1.99it/s]

 56%|█████▌    | 481/861 [06:39<02:47,  2.27it/s]

 56%|█████▌    | 482/861 [06:40<02:31,  2.51it/s]

 56%|█████▌    | 483/861 [06:40<02:14,  2.81it/s]

 56%|█████▌    | 484/861 [06:40<02:18,  2.73it/s]

 56%|█████▋    | 485/861 [06:41<02:06,  2.97it/s]

 56%|█████▋    | 486/861 [06:41<01:55,  3.25it/s]

 57%|█████▋    | 487/861 [06:41<02:31,  2.47it/s]

 57%|█████▋    | 488/861 [06:42<02:12,  2.81it/s]

 57%|█████▋    | 489/861 [06:42<02:15,  2.74it/s]

 57%|█████▋    | 490/861 [06:42<02:03,  3.01it/s]

 57%|█████▋    | 491/861 [06:43<02:06,  2.92it/s]

 57%|█████▋    | 492/861 [06:43<02:18,  2.67it/s]

 57%|█████▋    | 493/861 [06:44<02:22,  2.58it/s]

 57%|█████▋    | 494/861 [06:44<02:09,  2.83it/s]

 57%|█████▋    | 495/861 [06:45<03:12,  1.90it/s]

 58%|█████▊    | 496/861 [06:46<03:46,  1.61it/s]

 58%|█████▊    | 497/861 [06:46<03:03,  1.98it/s]

 58%|█████▊    | 498/861 [06:46<02:56,  2.05it/s]

 58%|█████▊    | 499/861 [06:47<02:31,  2.39it/s]

 58%|█████▊    | 500/861 [06:47<02:43,  2.20it/s]

 58%|█████▊    | 501/861 [06:47<02:21,  2.55it/s]

 58%|█████▊    | 502/861 [06:48<02:51,  2.09it/s]

 58%|█████▊    | 503/861 [06:48<02:48,  2.12it/s]

 59%|█████▊    | 504/861 [06:49<02:48,  2.12it/s]

 59%|█████▊    | 505/861 [06:49<02:29,  2.39it/s]

 59%|█████▉    | 506/861 [06:50<02:13,  2.65it/s]

 59%|█████▉    | 507/861 [06:50<01:59,  2.95it/s]

 59%|█████▉    | 508/861 [06:51<02:51,  2.06it/s]

 59%|█████▉    | 509/861 [06:52<03:38,  1.61it/s]

 59%|█████▉    | 510/861 [06:52<03:27,  1.69it/s]

 59%|█████▉    | 511/861 [06:53<03:26,  1.70it/s]

 59%|█████▉    | 512/861 [06:53<03:25,  1.69it/s]

 60%|█████▉    | 513/861 [06:54<03:17,  1.76it/s]

 60%|█████▉    | 514/861 [06:54<03:06,  1.87it/s]

 60%|█████▉    | 515/861 [06:54<02:28,  2.34it/s]

 60%|█████▉    | 516/861 [06:55<02:04,  2.77it/s]

 60%|██████    | 517/861 [06:55<01:54,  3.01it/s]

 60%|██████    | 518/861 [06:55<02:11,  2.60it/s]

 60%|██████    | 519/861 [06:56<02:53,  1.97it/s]

 60%|██████    | 520/861 [06:57<03:06,  1.83it/s]

 61%|██████    | 521/861 [06:57<02:37,  2.16it/s]

 61%|██████    | 522/861 [06:58<02:54,  1.94it/s]

 61%|██████    | 523/861 [06:59<03:44,  1.51it/s]

 61%|██████    | 524/861 [07:00<04:45,  1.18it/s]

 61%|██████    | 525/861 [07:00<03:59,  1.40it/s]

 61%|██████    | 526/861 [07:01<03:51,  1.45it/s]

 61%|██████    | 527/861 [07:02<03:48,  1.46it/s]

 61%|██████▏   | 528/861 [07:02<03:42,  1.50it/s]

 61%|██████▏   | 529/861 [07:03<03:09,  1.75it/s]

 62%|██████▏   | 530/861 [07:03<02:47,  1.97it/s]

 62%|██████▏   | 531/861 [07:03<02:42,  2.03it/s]

 62%|██████▏   | 532/861 [07:04<02:56,  1.86it/s]

 62%|██████▏   | 533/861 [07:05<02:43,  2.00it/s]

 62%|██████▏   | 534/861 [07:05<02:49,  1.93it/s]

 62%|██████▏   | 535/861 [07:06<02:50,  1.92it/s]

 62%|██████▏   | 536/861 [07:06<03:02,  1.78it/s]

 62%|██████▏   | 537/861 [07:08<04:28,  1.21it/s]

 62%|██████▏   | 538/861 [07:08<03:45,  1.43it/s]

 63%|██████▎   | 539/861 [07:10<05:26,  1.01s/it]

 63%|██████▎   | 540/861 [07:11<05:15,  1.02it/s]

 63%|██████▎   | 541/861 [07:11<04:23,  1.21it/s]

 63%|██████▎   | 542/861 [07:11<03:28,  1.53it/s]

 63%|██████▎   | 543/861 [07:12<03:34,  1.49it/s]

 63%|██████▎   | 544/861 [07:13<03:20,  1.58it/s]

 63%|██████▎   | 545/861 [07:14<04:49,  1.09it/s]

 63%|██████▎   | 546/861 [07:15<05:07,  1.02it/s]

 64%|██████▎   | 547/861 [07:16<04:32,  1.15it/s]

 64%|██████▎   | 548/861 [07:17<05:14,  1.00s/it]

 64%|██████▍   | 549/861 [07:18<05:15,  1.01s/it]

 64%|██████▍   | 550/861 [07:19<04:49,  1.07it/s]

 64%|██████▍   | 551/861 [07:20<04:25,  1.17it/s]

 64%|██████▍   | 552/861 [07:21<04:10,  1.23it/s]

 64%|██████▍   | 553/861 [07:22<04:54,  1.05it/s]

 64%|██████▍   | 554/861 [07:23<04:57,  1.03it/s]

 64%|██████▍   | 555/861 [07:24<05:57,  1.17s/it]

 65%|██████▍   | 556/861 [07:26<06:05,  1.20s/it]

 65%|██████▍   | 557/861 [07:27<06:36,  1.30s/it]

 65%|██████▍   | 558/861 [07:29<06:56,  1.38s/it]

 65%|██████▍   | 559/861 [07:30<06:39,  1.32s/it]

 65%|██████▌   | 560/861 [07:31<06:36,  1.32s/it]

 65%|██████▌   | 561/861 [07:32<05:49,  1.16s/it]

 65%|██████▌   | 562/861 [07:33<05:35,  1.12s/it]

 65%|██████▌   | 563/861 [07:34<05:26,  1.10s/it]

 66%|██████▌   | 564/861 [07:35<05:02,  1.02s/it]

 66%|██████▌   | 565/861 [07:36<04:41,  1.05it/s]

 66%|██████▌   | 566/861 [07:37<05:22,  1.09s/it]

 66%|██████▌   | 567/861 [07:39<05:45,  1.18s/it]

 66%|██████▌   | 568/861 [07:40<05:52,  1.20s/it]

 66%|██████▌   | 569/861 [07:41<05:25,  1.12s/it]

 66%|██████▌   | 570/861 [07:41<04:47,  1.01it/s]

 66%|██████▋   | 571/861 [07:43<05:11,  1.07s/it]

 66%|██████▋   | 572/861 [07:44<05:13,  1.09s/it]

 67%|██████▋   | 573/861 [07:44<04:28,  1.07it/s]

 67%|██████▋   | 574/861 [07:46<05:05,  1.06s/it]

 67%|██████▋   | 575/861 [07:47<04:52,  1.02s/it]

 67%|██████▋   | 576/861 [07:49<06:05,  1.28s/it]

 67%|██████▋   | 577/861 [07:50<06:33,  1.39s/it]

 67%|██████▋   | 578/861 [07:52<06:40,  1.41s/it]

 67%|██████▋   | 579/861 [07:54<07:30,  1.60s/it]

 67%|██████▋   | 580/861 [07:55<06:54,  1.47s/it]

 67%|██████▋   | 581/861 [07:56<06:11,  1.33s/it]

 68%|██████▊   | 582/861 [07:58<07:12,  1.55s/it]

 68%|██████▊   | 583/861 [07:59<06:40,  1.44s/it]

 68%|██████▊   | 584/861 [08:00<05:54,  1.28s/it]

 68%|██████▊   | 585/861 [08:01<05:14,  1.14s/it]

 68%|██████▊   | 586/861 [08:02<04:29,  1.02it/s]

 68%|██████▊   | 587/861 [08:03<04:49,  1.06s/it]

 68%|██████▊   | 588/861 [08:04<04:39,  1.03s/it]

 68%|██████▊   | 589/861 [08:05<04:20,  1.04it/s]

 69%|██████▊   | 590/861 [08:06<05:03,  1.12s/it]

 69%|██████▊   | 591/861 [08:07<04:15,  1.06it/s]

 69%|██████▉   | 592/861 [08:08<04:25,  1.01it/s]

 69%|██████▉   | 593/861 [08:09<05:03,  1.13s/it]

 69%|██████▉   | 594/861 [08:10<05:18,  1.19s/it]

 69%|██████▉   | 595/861 [08:11<04:32,  1.02s/it]

 69%|██████▉   | 596/861 [08:11<03:42,  1.19it/s]

 69%|██████▉   | 597/861 [08:12<03:21,  1.31it/s]

 69%|██████▉   | 598/861 [08:13<03:14,  1.35it/s]

 70%|██████▉   | 599/861 [08:14<03:26,  1.27it/s]

 70%|██████▉   | 600/861 [08:14<03:15,  1.33it/s]

 70%|██████▉   | 601/861 [08:15<03:06,  1.39it/s]

 70%|██████▉   | 602/861 [08:17<04:25,  1.03s/it]

 70%|███████   | 603/861 [08:18<04:49,  1.12s/it]

 70%|███████   | 604/861 [08:19<04:38,  1.08s/it]

 70%|███████   | 605/861 [08:20<04:05,  1.04it/s]

 70%|███████   | 606/861 [08:21<04:01,  1.06it/s]

 70%|███████   | 607/861 [08:21<03:53,  1.09it/s]

 71%|███████   | 608/861 [08:22<03:28,  1.21it/s]

 71%|███████   | 609/861 [08:23<03:40,  1.15it/s]

 71%|███████   | 610/861 [08:25<04:58,  1.19s/it]

 71%|███████   | 611/861 [08:26<05:01,  1.20s/it]

 71%|███████   | 612/861 [08:27<04:38,  1.12s/it]

 71%|███████   | 613/861 [08:28<03:53,  1.06it/s]

 71%|███████▏  | 614/861 [08:29<04:24,  1.07s/it]

 71%|███████▏  | 615/861 [08:30<04:40,  1.14s/it]

 72%|███████▏  | 616/861 [08:33<06:07,  1.50s/it]

 72%|███████▏  | 617/861 [08:34<06:11,  1.52s/it]

 72%|███████▏  | 618/861 [08:35<05:45,  1.42s/it]

 72%|███████▏  | 619/861 [08:37<05:26,  1.35s/it]

 72%|███████▏  | 620/861 [08:39<06:03,  1.51s/it]

 72%|███████▏  | 621/861 [08:40<05:39,  1.41s/it]

 72%|███████▏  | 622/861 [08:40<04:31,  1.14s/it]

 72%|███████▏  | 623/861 [08:42<05:32,  1.40s/it]

 72%|███████▏  | 624/861 [08:43<04:35,  1.16s/it]

 73%|███████▎  | 625/861 [08:43<03:56,  1.00s/it]

 73%|███████▎  | 626/861 [08:44<03:39,  1.07it/s]

 73%|███████▎  | 627/861 [08:45<03:20,  1.17it/s]

 73%|███████▎  | 628/861 [08:46<03:52,  1.00it/s]

 73%|███████▎  | 629/861 [08:47<04:02,  1.05s/it]

 73%|███████▎  | 630/861 [08:48<03:31,  1.09it/s]

 73%|███████▎  | 631/861 [08:48<02:49,  1.36it/s]

 73%|███████▎  | 632/861 [08:50<04:04,  1.07s/it]

 74%|███████▎  | 633/861 [08:51<03:54,  1.03s/it]

 74%|███████▎  | 634/861 [08:53<04:50,  1.28s/it]

 74%|███████▍  | 635/861 [08:54<04:39,  1.24s/it]

 74%|███████▍  | 636/861 [08:55<04:05,  1.09s/it]

 74%|███████▍  | 637/861 [08:56<03:42,  1.01it/s]

 74%|███████▍  | 638/861 [08:57<03:35,  1.04it/s]

 74%|███████▍  | 639/861 [08:58<04:04,  1.10s/it]

 74%|███████▍  | 640/861 [08:59<03:41,  1.00s/it]

 74%|███████▍  | 641/861 [09:00<03:29,  1.05it/s]

 75%|███████▍  | 642/861 [09:01<03:46,  1.04s/it]

 75%|███████▍  | 643/861 [09:01<03:22,  1.08it/s]

 75%|███████▍  | 644/861 [09:02<03:22,  1.07it/s]

 75%|███████▍  | 645/861 [09:03<02:46,  1.30it/s]

 75%|███████▌  | 646/861 [09:03<02:33,  1.40it/s]

 75%|███████▌  | 647/861 [09:04<02:23,  1.49it/s]

 75%|███████▌  | 648/861 [09:05<02:37,  1.35it/s]

 75%|███████▌  | 649/861 [09:05<02:28,  1.43it/s]

 75%|███████▌  | 650/861 [09:06<02:10,  1.62it/s]

 76%|███████▌  | 651/861 [09:06<01:53,  1.84it/s]

 76%|███████▌  | 652/861 [09:07<02:14,  1.56it/s]

 76%|███████▌  | 653/861 [09:08<02:03,  1.69it/s]

 76%|███████▌  | 654/861 [09:08<02:05,  1.65it/s]

 76%|███████▌  | 655/861 [09:09<01:49,  1.88it/s]

 76%|███████▌  | 656/861 [09:09<01:37,  2.10it/s]

 76%|███████▋  | 657/861 [09:09<01:35,  2.14it/s]

 76%|███████▋  | 658/861 [09:10<02:12,  1.53it/s]

 77%|███████▋  | 659/861 [09:11<02:10,  1.55it/s]

 77%|███████▋  | 660/861 [09:12<02:23,  1.41it/s]

 77%|███████▋  | 661/861 [09:12<02:02,  1.63it/s]

 77%|███████▋  | 662/861 [09:13<02:16,  1.46it/s]

 77%|███████▋  | 663/861 [09:15<03:38,  1.10s/it]

 77%|███████▋  | 664/861 [09:16<03:03,  1.08it/s]

 77%|███████▋  | 665/861 [09:16<02:28,  1.32it/s]

 77%|███████▋  | 666/861 [09:16<01:59,  1.63it/s]

 77%|███████▋  | 667/861 [09:17<02:08,  1.50it/s]

 78%|███████▊  | 668/861 [09:18<01:58,  1.62it/s]

 78%|███████▊  | 669/861 [09:18<01:43,  1.86it/s]

 78%|███████▊  | 670/861 [09:19<01:51,  1.71it/s]

 78%|███████▊  | 671/861 [09:19<01:32,  2.05it/s]

 78%|███████▊  | 672/861 [09:20<02:26,  1.29it/s]

 78%|███████▊  | 673/861 [09:21<02:15,  1.39it/s]

 78%|███████▊  | 674/861 [09:21<01:48,  1.73it/s]

 78%|███████▊  | 675/861 [09:23<02:40,  1.16it/s]

 79%|███████▊  | 676/861 [09:23<02:14,  1.37it/s]

 79%|███████▊  | 677/861 [09:24<01:58,  1.55it/s]

 79%|███████▊  | 678/861 [09:24<01:46,  1.71it/s]

 79%|███████▉  | 679/861 [09:24<01:30,  2.00it/s]

 79%|███████▉  | 680/861 [09:25<01:16,  2.35it/s]

 79%|███████▉  | 681/861 [09:25<01:16,  2.34it/s]

 79%|███████▉  | 682/861 [09:26<01:37,  1.83it/s]

 79%|███████▉  | 683/861 [09:26<01:33,  1.91it/s]

 79%|███████▉  | 684/861 [09:27<01:46,  1.67it/s]

 80%|███████▉  | 685/861 [09:28<01:46,  1.66it/s]

 80%|███████▉  | 686/861 [09:28<01:37,  1.79it/s]

 80%|███████▉  | 687/861 [09:30<02:45,  1.05it/s]

 80%|███████▉  | 688/861 [09:30<02:12,  1.30it/s]

 80%|████████  | 689/861 [09:31<02:09,  1.32it/s]

 80%|████████  | 690/861 [09:32<01:50,  1.55it/s]

 80%|████████  | 691/861 [09:32<01:42,  1.65it/s]

 80%|████████  | 692/861 [09:33<01:32,  1.83it/s]

 80%|████████  | 693/861 [09:33<01:43,  1.62it/s]

 81%|████████  | 694/861 [09:34<01:30,  1.85it/s]

 81%|████████  | 695/861 [09:34<01:27,  1.90it/s]

 81%|████████  | 696/861 [09:34<01:13,  2.26it/s]

 81%|████████  | 697/861 [09:35<01:18,  2.10it/s]

 81%|████████  | 698/861 [09:36<01:36,  1.69it/s]

 81%|████████  | 699/861 [09:37<01:43,  1.56it/s]

 81%|████████▏ | 700/861 [09:37<01:49,  1.48it/s]

 81%|████████▏ | 701/861 [09:38<01:56,  1.38it/s]

 82%|████████▏ | 702/861 [09:39<01:55,  1.38it/s]

 82%|████████▏ | 703/861 [09:39<01:39,  1.59it/s]

 82%|████████▏ | 704/861 [09:40<01:35,  1.64it/s]

 82%|████████▏ | 705/861 [09:40<01:23,  1.87it/s]

 82%|████████▏ | 706/861 [09:41<01:18,  1.97it/s]

 82%|████████▏ | 707/861 [09:41<01:11,  2.15it/s]

 82%|████████▏ | 708/861 [09:41<01:04,  2.38it/s]

 82%|████████▏ | 709/861 [09:42<01:02,  2.43it/s]

 82%|████████▏ | 710/861 [09:43<01:36,  1.57it/s]

 83%|████████▎ | 711/861 [09:44<01:33,  1.60it/s]

 83%|████████▎ | 712/861 [09:44<01:21,  1.82it/s]

 83%|████████▎ | 713/861 [09:44<01:09,  2.12it/s]

 83%|████████▎ | 714/861 [09:45<01:20,  1.83it/s]

 83%|████████▎ | 715/861 [09:46<01:42,  1.43it/s]

 83%|████████▎ | 716/861 [09:47<01:55,  1.26it/s]

 83%|████████▎ | 717/861 [09:47<01:43,  1.39it/s]

 83%|████████▎ | 718/861 [09:49<02:03,  1.16it/s]

 84%|████████▎ | 719/861 [09:49<01:47,  1.32it/s]

 84%|████████▎ | 720/861 [09:50<01:35,  1.48it/s]

 84%|████████▎ | 721/861 [09:50<01:28,  1.58it/s]

 84%|████████▍ | 722/861 [09:51<01:27,  1.59it/s]

 84%|████████▍ | 723/861 [09:51<01:15,  1.82it/s]

 84%|████████▍ | 724/861 [09:52<01:14,  1.85it/s]

 84%|████████▍ | 725/861 [09:52<01:13,  1.84it/s]

 84%|████████▍ | 726/861 [09:53<01:28,  1.53it/s]

 84%|████████▍ | 727/861 [09:55<01:58,  1.13it/s]

 85%|████████▍ | 728/861 [09:56<02:02,  1.09it/s]

 85%|████████▍ | 729/861 [09:56<01:44,  1.27it/s]

 85%|████████▍ | 730/861 [09:56<01:26,  1.52it/s]

 85%|████████▍ | 731/861 [09:58<02:15,  1.04s/it]

 85%|████████▌ | 732/861 [09:59<01:53,  1.14it/s]

 85%|████████▌ | 733/861 [10:00<01:43,  1.24it/s]

 85%|████████▌ | 734/861 [10:00<01:20,  1.57it/s]

 85%|████████▌ | 735/861 [10:00<01:13,  1.72it/s]

 85%|████████▌ | 736/861 [10:01<01:13,  1.70it/s]

 86%|████████▌ | 737/861 [10:01<01:13,  1.68it/s]

 86%|████████▌ | 738/861 [10:02<01:09,  1.77it/s]

 86%|████████▌ | 739/861 [10:02<01:02,  1.97it/s]

 86%|████████▌ | 740/861 [10:03<01:05,  1.85it/s]

 86%|████████▌ | 741/861 [10:03<01:03,  1.88it/s]

 86%|████████▌ | 742/861 [10:04<01:15,  1.57it/s]

 86%|████████▋ | 743/861 [10:05<01:13,  1.60it/s]

 86%|████████▋ | 744/861 [10:05<01:05,  1.77it/s]

 87%|████████▋ | 745/861 [10:06<01:18,  1.49it/s]

 87%|████████▋ | 746/861 [10:06<01:01,  1.86it/s]

 87%|████████▋ | 747/861 [10:07<01:08,  1.68it/s]

 87%|████████▋ | 748/861 [10:08<01:05,  1.74it/s]

 87%|████████▋ | 749/861 [10:09<01:20,  1.39it/s]

 87%|████████▋ | 750/861 [10:09<01:03,  1.75it/s]

 87%|████████▋ | 751/861 [10:09<00:51,  2.15it/s]

 87%|████████▋ | 752/861 [10:10<01:14,  1.46it/s]

 87%|████████▋ | 753/861 [10:11<01:12,  1.50it/s]

 88%|████████▊ | 754/861 [10:11<01:02,  1.71it/s]

 88%|████████▊ | 755/861 [10:12<00:56,  1.86it/s]

 88%|████████▊ | 756/861 [10:12<00:51,  2.06it/s]

 88%|████████▊ | 757/861 [10:13<01:05,  1.60it/s]

 88%|████████▊ | 758/861 [10:14<01:04,  1.59it/s]

 88%|████████▊ | 759/861 [10:14<01:00,  1.69it/s]

 88%|████████▊ | 760/861 [10:15<01:11,  1.42it/s]

 88%|████████▊ | 761/861 [10:17<01:32,  1.08it/s]

 89%|████████▊ | 762/861 [10:17<01:15,  1.31it/s]

 89%|████████▊ | 763/861 [10:18<01:09,  1.40it/s]

 89%|████████▊ | 764/861 [10:19<01:14,  1.29it/s]

 89%|████████▉ | 765/861 [10:19<01:12,  1.32it/s]

 89%|████████▉ | 766/861 [10:20<01:09,  1.37it/s]

 89%|████████▉ | 767/861 [10:24<02:36,  1.66s/it]

 89%|████████▉ | 768/861 [10:25<02:08,  1.38s/it]

 89%|████████▉ | 769/861 [10:26<01:56,  1.27s/it]

 89%|████████▉ | 770/861 [10:26<01:31,  1.00s/it]

 90%|████████▉ | 771/861 [10:26<01:16,  1.18it/s]

 90%|████████▉ | 772/861 [10:27<01:09,  1.29it/s]

 90%|████████▉ | 773/861 [10:29<01:47,  1.23s/it]

 90%|████████▉ | 774/861 [10:30<01:36,  1.11s/it]

 90%|█████████ | 775/861 [10:31<01:27,  1.01s/it]

 90%|█████████ | 776/861 [10:32<01:23,  1.02it/s]

 90%|█████████ | 777/861 [10:33<01:16,  1.09it/s]

 90%|█████████ | 778/861 [10:33<01:12,  1.14it/s]

 90%|█████████ | 779/861 [10:35<01:37,  1.19s/it]

 91%|█████████ | 780/861 [10:37<01:52,  1.39s/it]

 91%|█████████ | 781/861 [10:40<02:17,  1.72s/it]

 91%|█████████ | 782/861 [10:41<02:10,  1.65s/it]

 91%|█████████ | 783/861 [10:42<01:46,  1.37s/it]

 91%|█████████ | 784/861 [10:43<01:31,  1.18s/it]

 91%|█████████ | 785/861 [10:43<01:19,  1.04s/it]

 91%|█████████▏| 786/861 [10:44<01:13,  1.03it/s]

 91%|█████████▏| 787/861 [10:45<01:02,  1.18it/s]

 92%|█████████▏| 788/861 [10:45<00:59,  1.22it/s]

 92%|█████████▏| 789/861 [10:46<00:59,  1.21it/s]

 92%|█████████▏| 790/861 [10:47<00:57,  1.23it/s]

 92%|█████████▏| 791/861 [10:48<00:50,  1.37it/s]

 92%|█████████▏| 792/861 [10:48<00:49,  1.40it/s]

 92%|█████████▏| 793/861 [10:49<00:51,  1.31it/s]

 92%|█████████▏| 794/861 [10:50<00:48,  1.37it/s]

 92%|█████████▏| 795/861 [10:50<00:45,  1.45it/s]

 92%|█████████▏| 796/861 [10:51<00:37,  1.72it/s]

 93%|█████████▎| 797/861 [10:52<00:43,  1.49it/s]

 93%|█████████▎| 798/861 [10:52<00:37,  1.70it/s]

 93%|█████████▎| 799/861 [10:53<00:33,  1.82it/s]

 93%|█████████▎| 800/861 [10:53<00:35,  1.70it/s]

 93%|█████████▎| 801/861 [10:54<00:47,  1.26it/s]

 93%|█████████▎| 802/861 [10:55<00:40,  1.45it/s]

 93%|█████████▎| 803/861 [10:56<00:48,  1.19it/s]

 93%|█████████▎| 804/861 [10:58<00:58,  1.03s/it]

 93%|█████████▎| 805/861 [10:59<01:03,  1.13s/it]

 94%|█████████▎| 806/861 [10:59<00:49,  1.10it/s]

 94%|█████████▎| 807/861 [11:01<00:53,  1.01it/s]

 94%|█████████▍| 808/861 [11:02<00:59,  1.12s/it]

 94%|█████████▍| 809/861 [11:02<00:46,  1.13it/s]

 94%|█████████▍| 810/861 [11:03<00:38,  1.32it/s]

 94%|█████████▍| 811/861 [11:03<00:36,  1.38it/s]

 94%|█████████▍| 812/861 [11:04<00:33,  1.47it/s]

 94%|█████████▍| 813/861 [11:05<00:40,  1.17it/s]

 95%|█████████▍| 814/861 [11:06<00:43,  1.09it/s]

 95%|█████████▍| 815/861 [11:07<00:42,  1.08it/s]

 95%|█████████▍| 816/861 [11:08<00:37,  1.20it/s]

 95%|█████████▍| 817/861 [11:09<00:34,  1.27it/s]

 95%|█████████▌| 818/861 [11:10<00:37,  1.15it/s]

 95%|█████████▌| 819/861 [11:10<00:33,  1.27it/s]

 95%|█████████▌| 820/861 [11:11<00:34,  1.19it/s]

 95%|█████████▌| 821/861 [11:12<00:37,  1.07it/s]

 95%|█████████▌| 822/861 [11:14<00:43,  1.11s/it]

 96%|█████████▌| 823/861 [11:15<00:39,  1.04s/it]

 96%|█████████▌| 824/861 [11:15<00:31,  1.17it/s]

 96%|█████████▌| 825/861 [11:16<00:27,  1.29it/s]

 96%|█████████▌| 826/861 [11:17<00:37,  1.06s/it]

 96%|█████████▌| 827/861 [11:19<00:37,  1.10s/it]

 96%|█████████▌| 828/861 [11:19<00:28,  1.15it/s]

 96%|█████████▋| 829/861 [11:20<00:31,  1.02it/s]

 96%|█████████▋| 830/861 [11:21<00:31,  1.03s/it]

 97%|█████████▋| 831/861 [11:23<00:36,  1.20s/it]

 97%|█████████▋| 832/861 [11:24<00:29,  1.01s/it]

 97%|█████████▋| 833/861 [11:24<00:24,  1.14it/s]

 97%|█████████▋| 834/861 [11:25<00:24,  1.09it/s]

 97%|█████████▋| 835/861 [11:26<00:23,  1.11it/s]

 97%|█████████▋| 836/861 [11:27<00:22,  1.12it/s]

 97%|█████████▋| 837/861 [11:28<00:23,  1.04it/s]

 97%|█████████▋| 838/861 [11:29<00:23,  1.04s/it]

 97%|█████████▋| 839/861 [11:30<00:19,  1.12it/s]

 98%|█████████▊| 840/861 [11:30<00:15,  1.32it/s]

 98%|█████████▊| 841/861 [11:31<00:14,  1.33it/s]

 98%|█████████▊| 842/861 [11:31<00:13,  1.44it/s]

 98%|█████████▊| 843/861 [11:32<00:12,  1.42it/s]

 98%|█████████▊| 844/861 [11:33<00:11,  1.47it/s]

 98%|█████████▊| 845/861 [11:34<00:13,  1.17it/s]

 98%|█████████▊| 846/861 [11:35<00:11,  1.33it/s]

 98%|█████████▊| 847/861 [11:36<00:11,  1.23it/s]

 98%|█████████▊| 848/861 [11:37<00:12,  1.07it/s]

 99%|█████████▊| 849/861 [11:38<00:11,  1.00it/s]

 99%|█████████▊| 850/861 [11:39<00:09,  1.14it/s]

 99%|█████████▉| 851/861 [11:39<00:07,  1.26it/s]

 99%|█████████▉| 852/861 [11:40<00:06,  1.35it/s]

 99%|█████████▉| 853/861 [11:40<00:05,  1.38it/s]

 99%|█████████▉| 854/861 [11:41<00:04,  1.42it/s]

 99%|█████████▉| 855/861 [11:42<00:04,  1.27it/s]

 99%|█████████▉| 856/861 [11:43<00:04,  1.02it/s]

100%|█████████▉| 857/861 [11:44<00:03,  1.02it/s]

100%|█████████▉| 858/861 [11:45<00:02,  1.07it/s]

100%|█████████▉| 859/861 [11:46<00:01,  1.13it/s]

100%|█████████▉| 860/861 [11:47<00:00,  1.06it/s]

100%|██████████| 861/861 [11:48<00:00,  1.04it/s]{'score': 12.814386132355898, 'counts': [17920, 8355, 4270, 2172], 'totals': [50259, 48537, 46815, 45093], 'precisions': [35.65530551741976, 17.213672044007666, 9.121008223859874, 4.816712128268246], 'bp': 1.0, 'sys_len': 50259, 'ref_len': 32555}

                                                         

                                                 
{'eval_loss': 2.433004140853882, 'eval_bleu': 12.8144, 'eval_gen_len': 37.2979, 'eval_runtime': 806.1399, 'eval_samples_per_second': 2.136, 'eval_steps_per_second': 1.068, 'epoch': 13.0}

 81%|████████▏ | 50298/61904 [3:25:19<4:26:24,  1.38s/it]

100%|██████████| 861/861 [13:25<00:00,  1.04it/s]

                                                 [WARNING|configuration_utils.py:448] 2024-10-28 18:50:59,604 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 81%|████████▏ | 50299/61904 [3:25:39<801:28:38, 248.63s/it]
 81%|████████▏ | 50300/61904 [3:25:40<562:17:08, 174.44s/it]
                                                            
{'loss': 2.4458, 'learning_rate': 1.1880591209646052e-07, 'epoch': 13.0}

 81%|████████▏ | 50300/61904 [3:25:40<562:17:08, 174.44s/it]
 81%|████████▏ | 50301/61904 [3:25:41<395:00:00, 122.55s/it]
 81%|████████▏ | 50302/61904 [3:25:43<277:48:17, 86.20s/it] 
 81%|████████▏ | 50303/61904 [3:25:44<195:50:25, 60.77s/it]
 81%|████████▏ | 50304/61904 [3:25:46<138:34:48, 43.01s/it]
 81%|████████▏ | 50305/61904 [3:25:47<98:20:57, 30.52s/it] 
 81%|████████▏ | 50306/61904 [3:25:49<70:17:02, 21.82s/it]
 81%|████████▏ | 50307/61904 [3:25:50<50:36:28, 15.71s/it]
 81%|████████▏ | 50308/61904 [3:25:52<37:05:05, 11.51s/it]
 81%|████████▏ | 50309/61904 [3:25:53<27:20:55,  8.49s/it]
 81%|████████▏ | 50310/61904 [3:25:55<20:43:34,  6.44s/it]
 81%|████████▏ | 50311/61904 [3:25:56<15:51:23,  4.92s/it]
 81%|████████▏ | 50312/61904 [3:25:58<12:40:13,  3.93s/it]
 81%|████████▏ | 50313/61904 [3:25:59<10:05:09,  3.13s/it]
 81%|████████▏ | 50314/61904 [3:26:01<8:21:01,  2.59s/it] 
 81%|████████▏ | 50315/61904 [3:26:02<7:11:31,  2.23s/it]
 81%|████████▏ | 50316/61904 [3:26:03<6:28:10,  2.01s/it]
 81%|████████▏ | 50317/61904 [3:26:05<5:57:31,  1.85s/it]
 81%|████████▏ | 50318/61904 [3:26:06<5:26:54,  1.69s/it]
 81%|████████▏ | 50319/61904 [3:26:08<5:07:49,  1.59s/it]
 81%|████████▏ | 50320/61904 [3:26:09<4:54:45,  1.53s/it]
                                                         
{'loss': 2.4137, 'learning_rate': 1.1877349928691818e-07, 'epoch': 13.01}

 81%|████████▏ | 50320/61904 [3:26:09<4:54:45,  1.53s/it]
 81%|████████▏ | 50321/61904 [3:26:10<4:50:45,  1.51s/it]
 81%|████████▏ | 50322/61904 [3:26:12<4:58:52,  1.55s/it]
 81%|████████▏ | 50323/61904 [3:26:13<4:52:51,  1.52s/it]
 81%|████████▏ | 50324/61904 [3:26:15<4:43:36,  1.47s/it]
 81%|████████▏ | 50325/61904 [3:26:16<4:43:21,  1.47s/it]
 81%|████████▏ | 50326/61904 [3:26:18<4:30:04,  1.40s/it]
 81%|████████▏ | 50327/61904 [3:26:19<4:27:21,  1.39s/it]
 81%|████████▏ | 50328/61904 [3:26:20<4:33:28,  1.42s/it]
 81%|████████▏ | 50329/61904 [3:26:22<4:44:52,  1.48s/it]
 81%|████████▏ | 50330/61904 [3:26:23<4:39:17,  1.45s/it]
 81%|████████▏ | 50331/61904 [3:26:25<4:29:00,  1.39s/it]
 81%|████████▏ | 50332/61904 [3:26:26<4:35:12,  1.43s/it]
 81%|████████▏ | 50333/61904 [3:26:27<4:29:27,  1.40s/it]
 81%|████████▏ | 50334/61904 [3:26:29<4:30:29,  1.40s/it]
 81%|████████▏ | 50335/61904 [3:26:30<4:32:54,  1.42s/it]
 81%|████████▏ | 50336/61904 [3:26:32<4:30:00,  1.40s/it]
 81%|████████▏ | 50337/61904 [3:26:33<4:28:53,  1.39s/it]
 81%|████████▏ | 50338/61904 [3:26:34<4:28:09,  1.39s/it]
 81%|████████▏ | 50339/61904 [3:26:36<4:24:50,  1.37s/it]
 81%|████████▏ | 50340/61904 [3:26:37<4:30:35,  1.40s/it]
                                                         
{'loss': 2.4151, 'learning_rate': 1.1874108647737586e-07, 'epoch': 13.01}

 81%|████████▏ | 50340/61904 [3:26:37<4:30:35,  1.40s/it]
 81%|████████▏ | 50341/61904 [3:26:39<4:35:51,  1.43s/it]
 81%|████████▏ | 50342/61904 [3:26:40<4:39:49,  1.45s/it]
 81%|████████▏ | 50343/61904 [3:26:42<4:40:57,  1.46s/it]
 81%|████████▏ | 50344/61904 [3:26:43<4:39:15,  1.45s/it]
 81%|████████▏ | 50345/61904 [3:26:45<4:44:38,  1.48s/it]
 81%|████████▏ | 50346/61904 [3:26:46<4:39:47,  1.45s/it]
 81%|████████▏ | 50347/61904 [3:26:48<4:38:41,  1.45s/it]
 81%|████████▏ | 50348/61904 [3:26:49<4:39:41,  1.45s/it]
 81%|████████▏ | 50349/61904 [3:26:50<4:34:51,  1.43s/it]
 81%|████████▏ | 50350/61904 [3:26:52<4:43:31,  1.47s/it]
 81%|████████▏ | 50351/61904 [3:26:53<4:37:19,  1.44s/it]
 81%|████████▏ | 50352/61904 [3:26:55<4:37:09,  1.44s/it]
 81%|████████▏ | 50353/61904 [3:26:56<4:38:24,  1.45s/it]
 81%|████████▏ | 50354/61904 [3:26:58<4:35:26,  1.43s/it]
 81%|████████▏ | 50355/61904 [3:26:59<4:52:19,  1.52s/it]
 81%|████████▏ | 50356/61904 [3:27:01<4:40:38,  1.46s/it]
 81%|████████▏ | 50357/61904 [3:27:02<4:35:36,  1.43s/it]
 81%|████████▏ | 50358/61904 [3:27:03<4:33:32,  1.42s/it]
 81%|████████▏ | 50359/61904 [3:27:05<4:28:19,  1.39s/it]
 81%|████████▏ | 50360/61904 [3:27:06<4:33:39,  1.42s/it]
                                                         
{'loss': 2.4124, 'learning_rate': 1.1870867366783353e-07, 'epoch': 13.02}

 81%|████████▏ | 50360/61904 [3:27:06<4:33:39,  1.42s/it]
 81%|████████▏ | 50361/61904 [3:27:08<4:30:40,  1.41s/it]
 81%|████████▏ | 50362/61904 [3:27:09<4:33:33,  1.42s/it]
 81%|████████▏ | 50363/61904 [3:27:10<4:32:10,  1.41s/it]
 81%|████████▏ | 50364/61904 [3:27:12<4:28:37,  1.40s/it]
 81%|████████▏ | 50365/61904 [3:27:13<4:34:51,  1.43s/it]
 81%|████████▏ | 50366/61904 [3:27:15<4:34:22,  1.43s/it]
 81%|████████▏ | 50367/61904 [3:27:16<4:35:39,  1.43s/it]
 81%|████████▏ | 50368/61904 [3:27:18<4:31:43,  1.41s/it]
 81%|████████▏ | 50369/61904 [3:27:19<4:31:00,  1.41s/it]
 81%|████████▏ | 50370/61904 [3:27:20<4:25:28,  1.38s/it]
 81%|████████▏ | 50371/61904 [3:27:22<4:26:57,  1.39s/it]
 81%|████████▏ | 50372/61904 [3:27:23<4:34:03,  1.43s/it]
 81%|████████▏ | 50373/61904 [3:27:25<4:54:52,  1.53s/it]
 81%|████████▏ | 50374/61904 [3:27:26<4:52:11,  1.52s/it]
 81%|████████▏ | 50375/61904 [3:27:28<4:40:02,  1.46s/it]
 81%|████████▏ | 50376/61904 [3:27:29<4:34:29,  1.43s/it]
 81%|████████▏ | 50377/61904 [3:27:31<4:37:39,  1.45s/it]
 81%|████████▏ | 50378/61904 [3:27:32<4:36:36,  1.44s/it]
 81%|████████▏ | 50379/61904 [3:27:33<4:33:55,  1.43s/it]
 81%|████████▏ | 50380/61904 [3:27:35<4:30:47,  1.41s/it]
                                                         
{'loss': 2.4259, 'learning_rate': 1.1867626085829119e-07, 'epoch': 13.02}

 81%|████████▏ | 50380/61904 [3:27:35<4:30:47,  1.41s/it]
 81%|████████▏ | 50381/61904 [3:27:36<4:30:50,  1.41s/it]
 81%|████████▏ | 50382/61904 [3:27:38<4:31:55,  1.42s/it]
 81%|████████▏ | 50383/61904 [3:27:39<4:26:12,  1.39s/it]
 81%|████████▏ | 50384/61904 [3:27:40<4:32:18,  1.42s/it]
 81%|████████▏ | 50385/61904 [3:27:42<4:21:36,  1.36s/it]
 81%|████████▏ | 50386/61904 [3:27:43<4:28:13,  1.40s/it]
 81%|████████▏ | 50387/61904 [3:27:45<4:27:40,  1.39s/it]
 81%|████████▏ | 50388/61904 [3:27:46<4:31:16,  1.41s/it]
 81%|████████▏ | 50389/61904 [3:27:47<4:26:26,  1.39s/it]
 81%|████████▏ | 50390/61904 [3:27:49<4:26:18,  1.39s/it]
 81%|████████▏ | 50391/61904 [3:27:50<4:35:51,  1.44s/it]
 81%|████████▏ | 50392/61904 [3:27:52<4:26:39,  1.39s/it]
 81%|████████▏ | 50393/61904 [3:27:53<4:27:13,  1.39s/it]
 81%|████████▏ | 50394/61904 [3:27:54<4:28:32,  1.40s/it]
 81%|████████▏ | 50395/61904 [3:27:56<4:26:57,  1.39s/it]
 81%|████████▏ | 50396/61904 [3:27:57<4:37:07,  1.44s/it]
 81%|████████▏ | 50397/61904 [3:27:59<4:49:00,  1.51s/it]
 81%|████████▏ | 50398/61904 [3:28:00<4:46:41,  1.50s/it]
 81%|████████▏ | 50399/61904 [3:28:02<4:45:32,  1.49s/it]
 81%|████████▏ | 50400/61904 [3:28:03<4:38:01,  1.45s/it]
                                                         
{'loss': 2.4933, 'learning_rate': 1.1864384804874886e-07, 'epoch': 13.03}

 81%|████████▏ | 50400/61904 [3:28:03<4:38:01,  1.45s/it]
 81%|████████▏ | 50401/61904 [3:28:05<4:27:43,  1.40s/it]
 81%|████████▏ | 50402/61904 [3:28:06<4:44:53,  1.49s/it]
 81%|████████▏ | 50403/61904 [3:28:08<4:35:18,  1.44s/it]
 81%|████████▏ | 50404/61904 [3:28:09<4:33:34,  1.43s/it]
 81%|████████▏ | 50405/61904 [3:28:10<4:35:00,  1.43s/it]
 81%|████████▏ | 50406/61904 [3:28:12<4:34:16,  1.43s/it]
 81%|████████▏ | 50407/61904 [3:28:13<4:28:58,  1.40s/it]
 81%|████████▏ | 50408/61904 [3:28:15<4:30:22,  1.41s/it]
 81%|████████▏ | 50409/61904 [3:28:16<4:30:25,  1.41s/it]
 81%|████████▏ | 50410/61904 [3:28:17<4:29:13,  1.41s/it]
 81%|████████▏ | 50411/61904 [3:28:19<4:27:26,  1.40s/it]
 81%|████████▏ | 50412/61904 [3:28:20<4:22:51,  1.37s/it]
 81%|████████▏ | 50413/61904 [3:28:22<4:23:06,  1.37s/it]
 81%|████████▏ | 50414/61904 [3:28:23<4:15:02,  1.33s/it]
 81%|████████▏ | 50415/61904 [3:28:24<4:13:33,  1.32s/it]
 81%|████████▏ | 50416/61904 [3:28:25<4:20:31,  1.36s/it]
 81%|████████▏ | 50417/61904 [3:28:27<4:15:53,  1.34s/it]
 81%|████████▏ | 50418/61904 [3:28:28<4:25:00,  1.38s/it]
 81%|████████▏ | 50419/61904 [3:28:30<4:21:01,  1.36s/it]
 81%|████████▏ | 50420/61904 [3:28:31<4:26:18,  1.39s/it]
                                                         
{'loss': 2.4579, 'learning_rate': 1.1861143523920653e-07, 'epoch': 13.03}

 81%|████████▏ | 50420/61904 [3:28:31<4:26:18,  1.39s/it]
 81%|████████▏ | 50421/61904 [3:28:32<4:25:04,  1.39s/it]
 81%|████████▏ | 50422/61904 [3:28:34<4:28:09,  1.40s/it]
 81%|████████▏ | 50423/61904 [3:28:35<4:32:01,  1.42s/it]
 81%|████████▏ | 50424/61904 [3:28:37<4:24:02,  1.38s/it]
 81%|████████▏ | 50425/61904 [3:28:38<4:16:50,  1.34s/it]
 81%|████████▏ | 50426/61904 [3:28:39<4:12:23,  1.32s/it]
 81%|████████▏ | 50427/61904 [3:28:40<4:11:22,  1.31s/it]
 81%|████████▏ | 50428/61904 [3:28:42<4:19:59,  1.36s/it]
 81%|████████▏ | 50429/61904 [3:28:43<4:21:16,  1.37s/it]
 81%|████████▏ | 50430/61904 [3:28:45<4:27:05,  1.40s/it]
 81%|████████▏ | 50431/61904 [3:28:46<4:27:27,  1.40s/it]
 81%|████████▏ | 50432/61904 [3:28:47<4:20:55,  1.36s/it]
 81%|████████▏ | 50433/61904 [3:28:49<4:19:36,  1.36s/it]
 81%|████████▏ | 50434/61904 [3:28:50<4:18:14,  1.35s/it]
 81%|████████▏ | 50435/61904 [3:28:51<4:16:54,  1.34s/it]
 81%|████████▏ | 50436/61904 [3:28:53<4:18:20,  1.35s/it]
 81%|████████▏ | 50437/61904 [3:28:54<4:24:55,  1.39s/it]
 81%|████████▏ | 50438/61904 [3:28:56<4:22:04,  1.37s/it]
 81%|████████▏ | 50439/61904 [3:28:57<4:18:00,  1.35s/it]
 81%|████████▏ | 50440/61904 [3:28:58<4:10:35,  1.31s/it]
                                                         
{'loss': 2.4766, 'learning_rate': 1.185790224296642e-07, 'epoch': 13.04}

 81%|████████▏ | 50440/61904 [3:28:58<4:10:35,  1.31s/it]
 81%|████████▏ | 50441/61904 [3:28:59<4:13:15,  1.33s/it]
 81%|████████▏ | 50442/61904 [3:29:01<4:09:08,  1.30s/it]
 81%|████████▏ | 50443/61904 [3:29:02<4:18:44,  1.35s/it]
 81%|████████▏ | 50444/61904 [3:29:04<4:19:36,  1.36s/it]
 81%|████████▏ | 50445/61904 [3:29:05<4:24:10,  1.38s/it]
 81%|████████▏ | 50446/61904 [3:29:06<4:22:15,  1.37s/it]
 81%|████████▏ | 50447/61904 [3:29:08<4:24:12,  1.38s/it]
 81%|████████▏ | 50448/61904 [3:29:09<4:22:34,  1.38s/it]
 81%|████████▏ | 50449/61904 [3:29:10<4:20:02,  1.36s/it]
 81%|████████▏ | 50450/61904 [3:29:12<4:14:02,  1.33s/it]
 81%|████████▏ | 50451/61904 [3:29:13<4:15:07,  1.34s/it]
 82%|████████▏ | 50452/61904 [3:29:14<4:12:55,  1.33s/it]
 82%|████████▏ | 50453/61904 [3:29:16<4:16:30,  1.34s/it]
 82%|████████▏ | 50454/61904 [3:29:17<4:13:05,  1.33s/it]
 82%|████████▏ | 50455/61904 [3:29:18<4:16:44,  1.35s/it]
 82%|████████▏ | 50456/61904 [3:29:20<4:25:40,  1.39s/it]
 82%|████████▏ | 50457/61904 [3:29:21<4:26:46,  1.40s/it]
 82%|████████▏ | 50458/61904 [3:29:23<4:27:02,  1.40s/it]
 82%|████████▏ | 50459/61904 [3:29:24<4:21:21,  1.37s/it]
 82%|████████▏ | 50460/61904 [3:29:25<4:15:57,  1.34s/it]
                                                         
{'loss': 2.4438, 'learning_rate': 1.1854660962012187e-07, 'epoch': 13.04}

 82%|████████▏ | 50460/61904 [3:29:25<4:15:57,  1.34s/it]
 82%|████████▏ | 50461/61904 [3:29:27<4:20:21,  1.37s/it]
 82%|████████▏ | 50462/61904 [3:29:28<4:11:45,  1.32s/it]
 82%|████████▏ | 50463/61904 [3:29:29<4:23:53,  1.38s/it]
 82%|████████▏ | 50464/61904 [3:29:31<4:17:28,  1.35s/it]
 82%|████████▏ | 50465/61904 [3:29:32<4:18:09,  1.35s/it]
 82%|████████▏ | 50466/61904 [3:29:34<4:26:10,  1.40s/it]
 82%|████████▏ | 50467/61904 [3:29:35<4:27:14,  1.40s/it]
 82%|████████▏ | 50468/61904 [3:29:37<4:36:48,  1.45s/it]
 82%|████████▏ | 50469/61904 [3:29:38<4:38:58,  1.46s/it]
 82%|████████▏ | 50470/61904 [3:29:40<4:36:56,  1.45s/it]
 82%|████████▏ | 50471/61904 [3:29:41<4:29:31,  1.41s/it]
 82%|████████▏ | 50472/61904 [3:29:42<4:34:26,  1.44s/it]
 82%|████████▏ | 50473/61904 [3:29:44<4:28:42,  1.41s/it]
 82%|████████▏ | 50474/61904 [3:29:45<4:26:28,  1.40s/it]
 82%|████████▏ | 50475/61904 [3:29:46<4:19:57,  1.36s/it]
 82%|████████▏ | 50476/61904 [3:29:48<4:24:39,  1.39s/it]
 82%|████████▏ | 50477/61904 [3:29:49<4:19:10,  1.36s/it]
 82%|████████▏ | 50478/61904 [3:29:51<4:34:15,  1.44s/it]
 82%|████████▏ | 50479/61904 [3:29:52<4:35:03,  1.44s/it]
 82%|████████▏ | 50480/61904 [3:29:54<4:36:10,  1.45s/it]
                                                         
{'loss': 2.4372, 'learning_rate': 1.1851419681057953e-07, 'epoch': 13.05}

 82%|████████▏ | 50480/61904 [3:29:54<4:36:10,  1.45s/it]
 82%|████████▏ | 50481/61904 [3:29:55<4:26:58,  1.40s/it]
 82%|████████▏ | 50482/61904 [3:29:56<4:26:41,  1.40s/it]
 82%|████████▏ | 50483/61904 [3:29:58<4:21:45,  1.38s/it]
 82%|████████▏ | 50484/61904 [3:29:59<4:24:56,  1.39s/it]
 82%|████████▏ | 50485/61904 [3:30:01<4:43:22,  1.49s/it]
 82%|████████▏ | 50486/61904 [3:30:02<4:30:27,  1.42s/it]
 82%|████████▏ | 50487/61904 [3:30:03<4:29:15,  1.42s/it]
 82%|████████▏ | 50488/61904 [3:30:05<4:30:45,  1.42s/it]
 82%|████████▏ | 50489/61904 [3:30:06<4:28:18,  1.41s/it]
 82%|████████▏ | 50490/61904 [3:30:08<4:29:07,  1.41s/it]
 82%|████████▏ | 50491/61904 [3:30:09<4:30:02,  1.42s/it]
 82%|████████▏ | 50492/61904 [3:30:10<4:27:00,  1.40s/it]
 82%|████████▏ | 50493/61904 [3:30:12<4:30:43,  1.42s/it]
 82%|████████▏ | 50494/61904 [3:30:14<4:43:29,  1.49s/it]
 82%|████████▏ | 50495/61904 [3:30:15<4:30:53,  1.42s/it]
 82%|████████▏ | 50496/61904 [3:30:16<4:30:32,  1.42s/it]
 82%|████████▏ | 50497/61904 [3:30:18<4:23:49,  1.39s/it]
 82%|████████▏ | 50498/61904 [3:30:19<4:13:31,  1.33s/it]
 82%|████████▏ | 50499/61904 [3:30:20<4:11:32,  1.32s/it]
 82%|████████▏ | 50500/61904 [3:30:22<4:14:54,  1.34s/it]
                                                         
{'loss': 2.4097, 'learning_rate': 1.184817840010372e-07, 'epoch': 13.05}

 82%|████████▏ | 50500/61904 [3:30:22<4:14:54,  1.34s/it]
 82%|████████▏ | 50501/61904 [3:30:23<4:22:57,  1.38s/it]
 82%|████████▏ | 50502/61904 [3:30:25<4:32:16,  1.43s/it]
 82%|████████▏ | 50503/61904 [3:30:26<4:23:06,  1.38s/it]
 82%|████████▏ | 50504/61904 [3:30:27<4:26:45,  1.40s/it]
 82%|████████▏ | 50505/61904 [3:30:29<4:19:56,  1.37s/it]
 82%|████████▏ | 50506/61904 [3:30:30<4:29:43,  1.42s/it]
 82%|████████▏ | 50507/61904 [3:30:31<4:23:29,  1.39s/it]
 82%|████████▏ | 50508/61904 [3:30:33<4:27:32,  1.41s/it]
 82%|████████▏ | 50509/61904 [3:30:34<4:18:57,  1.36s/it]
 82%|████████▏ | 50510/61904 [3:30:35<4:15:48,  1.35s/it]
 82%|████████▏ | 50511/61904 [3:30:37<4:16:59,  1.35s/it]
 82%|████████▏ | 50512/61904 [3:30:38<4:11:41,  1.33s/it]
 82%|████████▏ | 50513/61904 [3:30:39<4:11:51,  1.33s/it]
 82%|████████▏ | 50514/61904 [3:30:41<4:09:29,  1.31s/it]
 82%|████████▏ | 50515/61904 [3:30:42<4:14:55,  1.34s/it]
 82%|████████▏ | 50516/61904 [3:30:43<4:15:57,  1.35s/it]
 82%|████████▏ | 50517/61904 [3:30:45<4:09:11,  1.31s/it]
 82%|████████▏ | 50518/61904 [3:30:46<4:18:14,  1.36s/it]
 82%|████████▏ | 50519/61904 [3:30:47<4:15:06,  1.34s/it]
 82%|████████▏ | 50520/61904 [3:30:49<4:16:19,  1.35s/it]
                                                         
{'loss': 2.4199, 'learning_rate': 1.1844937119149488e-07, 'epoch': 13.06}

 82%|████████▏ | 50520/61904 [3:30:49<4:16:19,  1.35s/it]
 82%|████████▏ | 50521/61904 [3:30:50<4:15:30,  1.35s/it]
 82%|████████▏ | 50522/61904 [3:30:52<4:22:36,  1.38s/it]
 82%|████████▏ | 50523/61904 [3:30:53<4:26:46,  1.41s/it]
 82%|████████▏ | 50524/61904 [3:30:54<4:19:42,  1.37s/it]
 82%|████████▏ | 50525/61904 [3:30:56<4:13:23,  1.34s/it]
 82%|████████▏ | 50526/61904 [3:30:57<4:19:14,  1.37s/it]
 82%|████████▏ | 50527/61904 [3:30:58<4:16:05,  1.35s/it]
 82%|████████▏ | 50528/61904 [3:31:00<4:12:56,  1.33s/it]
 82%|████████▏ | 50529/61904 [3:31:01<4:11:55,  1.33s/it]
 82%|████████▏ | 50530/61904 [3:31:02<4:09:10,  1.31s/it]
 82%|████████▏ | 50531/61904 [3:31:04<4:22:40,  1.39s/it]
 82%|████████▏ | 50532/61904 [3:31:05<4:23:14,  1.39s/it]
 82%|████████▏ | 50533/61904 [3:31:07<4:33:33,  1.44s/it]
 82%|████████▏ | 50534/61904 [3:31:08<4:32:00,  1.44s/it]
 82%|████████▏ | 50535/61904 [3:31:09<4:24:30,  1.40s/it]
 82%|████████▏ | 50536/61904 [3:31:11<4:28:12,  1.42s/it]
 82%|████████▏ | 50537/61904 [3:31:12<4:27:35,  1.41s/it]
 82%|████████▏ | 50538/61904 [3:31:14<4:25:43,  1.40s/it]
 82%|████████▏ | 50539/61904 [3:31:15<4:22:03,  1.38s/it]
 82%|████████▏ | 50540/61904 [3:31:16<4:21:02,  1.38s/it]
                                                         
{'loss': 2.477, 'learning_rate': 1.1841695838195254e-07, 'epoch': 13.06}

 82%|████████▏ | 50540/61904 [3:31:16<4:21:02,  1.38s/it]
 82%|████████▏ | 50541/61904 [3:31:18<4:15:12,  1.35s/it]
 82%|████████▏ | 50542/61904 [3:31:19<4:15:43,  1.35s/it]
 82%|████████▏ | 50543/61904 [3:31:21<4:25:45,  1.40s/it]
 82%|████████▏ | 50544/61904 [3:31:22<4:17:53,  1.36s/it]
 82%|████████▏ | 50545/61904 [3:31:23<4:15:49,  1.35s/it]
 82%|████████▏ | 50546/61904 [3:31:24<4:10:15,  1.32s/it]
 82%|████████▏ | 50547/61904 [3:31:26<4:11:46,  1.33s/it]
 82%|████████▏ | 50548/61904 [3:31:27<4:22:32,  1.39s/it]
 82%|████████▏ | 50549/61904 [3:31:29<4:17:33,  1.36s/it]
 82%|████████▏ | 50550/61904 [3:31:30<4:14:28,  1.34s/it]
 82%|████████▏ | 50551/61904 [3:31:31<4:16:51,  1.36s/it]
 82%|████████▏ | 50552/61904 [3:31:33<4:18:37,  1.37s/it]
 82%|████████▏ | 50553/61904 [3:31:34<4:14:15,  1.34s/it]
 82%|████████▏ | 50554/61904 [3:31:35<4:11:36,  1.33s/it]
 82%|████████▏ | 50555/61904 [3:31:37<4:05:29,  1.30s/it]
 82%|████████▏ | 50556/61904 [3:31:38<4:12:55,  1.34s/it]
 82%|████████▏ | 50557/61904 [3:31:39<4:17:17,  1.36s/it]
 82%|████████▏ | 50558/61904 [3:31:41<4:18:59,  1.37s/it]
 82%|████████▏ | 50559/61904 [3:31:42<4:17:35,  1.36s/it]
 82%|████████▏ | 50560/61904 [3:31:43<4:10:13,  1.32s/it]
                                                         
{'loss': 2.3863, 'learning_rate': 1.183845455724102e-07, 'epoch': 13.07}

 82%|████████▏ | 50560/61904 [3:31:43<4:10:13,  1.32s/it]
 82%|████████▏ | 50561/61904 [3:31:45<4:15:33,  1.35s/it]
 82%|████████▏ | 50562/61904 [3:31:46<4:23:20,  1.39s/it]
 82%|████████▏ | 50563/61904 [3:31:48<4:20:09,  1.38s/it]
 82%|████████▏ | 50564/61904 [3:31:49<4:22:24,  1.39s/it]
 82%|████████▏ | 50565/61904 [3:31:50<4:22:16,  1.39s/it]
 82%|████████▏ | 50566/61904 [3:31:52<4:22:20,  1.39s/it]
 82%|████████▏ | 50567/61904 [3:31:53<4:19:07,  1.37s/it]
 82%|████████▏ | 50568/61904 [3:31:54<4:15:11,  1.35s/it]
 82%|████████▏ | 50569/61904 [3:31:56<4:20:06,  1.38s/it]
 82%|████████▏ | 50570/61904 [3:31:57<4:15:01,  1.35s/it]
 82%|████████▏ | 50571/61904 [3:31:59<4:30:27,  1.43s/it]
 82%|████████▏ | 50572/61904 [3:32:00<4:17:07,  1.36s/it]
 82%|████████▏ | 50573/61904 [3:32:01<4:14:32,  1.35s/it]
 82%|████████▏ | 50574/61904 [3:32:03<4:23:07,  1.39s/it]
 82%|████████▏ | 50575/61904 [3:32:04<4:38:30,  1.47s/it]
 82%|████████▏ | 50576/61904 [3:32:06<4:31:31,  1.44s/it]
 82%|████████▏ | 50577/61904 [3:32:07<4:30:10,  1.43s/it]
 82%|████████▏ | 50578/61904 [3:32:09<4:25:21,  1.41s/it]
 82%|████████▏ | 50579/61904 [3:32:10<4:19:05,  1.37s/it]
 82%|████████▏ | 50580/61904 [3:32:11<4:24:53,  1.40s/it]
                                                         
{'loss': 2.4797, 'learning_rate': 1.1835213276286788e-07, 'epoch': 13.07}

 82%|████████▏ | 50580/61904 [3:32:11<4:24:53,  1.40s/it]
 82%|████████▏ | 50581/61904 [3:32:13<4:14:54,  1.35s/it]
 82%|████████▏ | 50582/61904 [3:32:14<4:14:26,  1.35s/it]
 82%|████████▏ | 50583/61904 [3:32:15<4:16:08,  1.36s/it]
 82%|████████▏ | 50584/61904 [3:32:17<4:18:11,  1.37s/it]
 82%|████████▏ | 50585/61904 [3:32:18<4:33:34,  1.45s/it]
 82%|████████▏ | 50586/61904 [3:32:20<4:26:58,  1.42s/it]
 82%|████████▏ | 50587/61904 [3:32:21<4:20:06,  1.38s/it]
 82%|████████▏ | 50588/61904 [3:32:22<4:13:43,  1.35s/it]
 82%|████████▏ | 50589/61904 [3:32:24<4:21:00,  1.38s/it]
 82%|████████▏ | 50590/61904 [3:32:25<4:21:15,  1.39s/it]
 82%|████████▏ | 50591/61904 [3:32:26<4:17:35,  1.37s/it]
 82%|████████▏ | 50592/61904 [3:32:28<4:17:52,  1.37s/it]
 82%|████████▏ | 50593/61904 [3:32:29<4:21:15,  1.39s/it]
 82%|████████▏ | 50594/61904 [3:32:30<4:17:31,  1.37s/it]
 82%|████████▏ | 50595/61904 [3:32:32<4:15:59,  1.36s/it]
 82%|████████▏ | 50596/61904 [3:32:33<4:13:42,  1.35s/it]
 82%|████████▏ | 50597/61904 [3:32:35<4:15:02,  1.35s/it]
 82%|████████▏ | 50598/61904 [3:32:36<4:13:13,  1.34s/it]
 82%|████████▏ | 50599/61904 [3:32:37<4:13:40,  1.35s/it]
 82%|████████▏ | 50600/61904 [3:32:39<4:22:28,  1.39s/it]
                                                         
{'loss': 2.4302, 'learning_rate': 1.1831971995332555e-07, 'epoch': 13.08}

 82%|████████▏ | 50600/61904 [3:32:39<4:22:28,  1.39s/it]
 82%|████████▏ | 50601/61904 [3:32:40<4:19:00,  1.37s/it]
 82%|████████▏ | 50602/61904 [3:32:41<4:21:18,  1.39s/it]
 82%|████████▏ | 50603/61904 [3:32:43<4:18:58,  1.38s/it]
 82%|████████▏ | 50604/61904 [3:32:44<4:26:47,  1.42s/it]
 82%|████████▏ | 50605/61904 [3:32:46<4:26:53,  1.42s/it]
 82%|████████▏ | 50606/61904 [3:32:47<4:30:55,  1.44s/it]
 82%|████████▏ | 50607/61904 [3:32:49<4:27:24,  1.42s/it]
 82%|████████▏ | 50608/61904 [3:32:50<4:22:43,  1.40s/it]
 82%|████████▏ | 50609/61904 [3:32:51<4:16:15,  1.36s/it]
 82%|████████▏ | 50610/61904 [3:32:52<4:10:14,  1.33s/it]
 82%|████████▏ | 50611/61904 [3:32:54<4:15:48,  1.36s/it]
 82%|████████▏ | 50612/61904 [3:32:55<4:16:54,  1.37s/it]
 82%|████████▏ | 50613/61904 [3:32:57<4:13:24,  1.35s/it]
 82%|████████▏ | 50614/61904 [3:32:58<4:06:05,  1.31s/it]
 82%|████████▏ | 50615/61904 [3:32:59<4:10:09,  1.33s/it]
 82%|████████▏ | 50616/61904 [3:33:01<4:10:05,  1.33s/it]
 82%|████████▏ | 50617/61904 [3:33:02<4:11:01,  1.33s/it]
 82%|████████▏ | 50618/61904 [3:33:03<4:18:05,  1.37s/it]
 82%|████████▏ | 50619/61904 [3:33:05<4:21:48,  1.39s/it]
 82%|████████▏ | 50620/61904 [3:33:06<4:21:12,  1.39s/it]
                                                         
{'loss': 2.4693, 'learning_rate': 1.1828730714378322e-07, 'epoch': 13.08}

 82%|████████▏ | 50620/61904 [3:33:06<4:21:12,  1.39s/it]
 82%|████████▏ | 50621/61904 [3:33:08<4:20:22,  1.38s/it]
 82%|████████▏ | 50622/61904 [3:33:09<4:24:20,  1.41s/it]
 82%|████████▏ | 50623/61904 [3:33:10<4:23:35,  1.40s/it]
 82%|████████▏ | 50624/61904 [3:33:12<4:18:38,  1.38s/it]
 82%|████████▏ | 50625/61904 [3:33:13<4:21:26,  1.39s/it]
 82%|████████▏ | 50626/61904 [3:33:14<4:21:55,  1.39s/it]
 82%|████████▏ | 50627/61904 [3:33:16<4:20:35,  1.39s/it]
 82%|████████▏ | 50628/61904 [3:33:17<4:33:50,  1.46s/it]
 82%|████████▏ | 50629/61904 [3:33:19<4:31:57,  1.45s/it]
 82%|████████▏ | 50630/61904 [3:33:20<4:29:01,  1.43s/it]
 82%|████████▏ | 50631/61904 [3:33:22<4:26:35,  1.42s/it]
 82%|████████▏ | 50632/61904 [3:33:23<4:35:17,  1.47s/it]
 82%|████████▏ | 50633/61904 [3:33:25<4:22:06,  1.40s/it]
 82%|████████▏ | 50634/61904 [3:33:26<4:33:20,  1.46s/it]
 82%|████████▏ | 50635/61904 [3:33:27<4:26:00,  1.42s/it]
 82%|████████▏ | 50636/61904 [3:33:29<4:19:26,  1.38s/it]
 82%|████████▏ | 50637/61904 [3:33:30<4:17:06,  1.37s/it]
 82%|████████▏ | 50638/61904 [3:33:31<4:19:14,  1.38s/it]
 82%|████████▏ | 50639/61904 [3:33:33<4:13:59,  1.35s/it]
 82%|████████▏ | 50640/61904 [3:33:34<4:19:06,  1.38s/it]
                                                         
{'loss': 2.5014, 'learning_rate': 1.1825489433424088e-07, 'epoch': 13.09}

 82%|████████▏ | 50640/61904 [3:33:34<4:19:06,  1.38s/it]
 82%|████████▏ | 50641/61904 [3:33:35<4:14:22,  1.36s/it]
 82%|████████▏ | 50642/61904 [3:33:37<4:21:31,  1.39s/it]
 82%|████████▏ | 50643/61904 [3:33:39<4:36:35,  1.47s/it]
 82%|████████▏ | 50644/61904 [3:33:40<4:27:41,  1.43s/it]
 82%|████████▏ | 50645/61904 [3:33:41<4:26:04,  1.42s/it]
 82%|████████▏ | 50646/61904 [3:33:43<4:26:24,  1.42s/it]
 82%|████████▏ | 50647/61904 [3:33:44<4:26:00,  1.42s/it]
 82%|████████▏ | 50648/61904 [3:33:45<4:18:27,  1.38s/it]
 82%|████████▏ | 50649/61904 [3:33:47<4:20:59,  1.39s/it]
 82%|████████▏ | 50650/61904 [3:33:49<4:33:59,  1.46s/it]
 82%|████████▏ | 50651/61904 [3:33:50<4:36:09,  1.47s/it]
 82%|████████▏ | 50652/61904 [3:33:52<4:45:35,  1.52s/it]
 82%|████████▏ | 50653/61904 [3:33:53<4:48:36,  1.54s/it]
 82%|████████▏ | 50654/61904 [3:33:55<4:36:39,  1.48s/it]
 82%|████████▏ | 50655/61904 [3:33:56<4:24:25,  1.41s/it]
 82%|████████▏ | 50656/61904 [3:33:57<4:18:57,  1.38s/it]
 82%|████████▏ | 50657/61904 [3:33:58<4:15:59,  1.37s/it]
 82%|████████▏ | 50658/61904 [3:34:00<4:18:29,  1.38s/it]
 82%|████████▏ | 50659/61904 [3:34:01<4:17:06,  1.37s/it]
 82%|████████▏ | 50660/61904 [3:34:03<4:30:46,  1.44s/it]
                                                         
{'loss': 2.4204, 'learning_rate': 1.1822248152469855e-07, 'epoch': 13.09}

 82%|████████▏ | 50660/61904 [3:34:03<4:30:46,  1.44s/it]
 82%|████████▏ | 50661/61904 [3:34:04<4:24:51,  1.41s/it]
 82%|████████▏ | 50662/61904 [3:34:06<4:28:39,  1.43s/it]
 82%|████████▏ | 50663/61904 [3:34:07<4:31:45,  1.45s/it]
 82%|████████▏ | 50664/61904 [3:34:09<4:33:58,  1.46s/it]
 82%|████████▏ | 50665/61904 [3:34:10<4:25:45,  1.42s/it]
 82%|████████▏ | 50666/61904 [3:34:11<4:18:47,  1.38s/it]
 82%|████████▏ | 50667/61904 [3:34:13<4:21:34,  1.40s/it]
 82%|████████▏ | 50668/61904 [3:34:14<4:10:57,  1.34s/it]
 82%|████████▏ | 50669/61904 [3:34:15<4:10:16,  1.34s/it]
 82%|████████▏ | 50670/61904 [3:34:16<4:04:58,  1.31s/it]
 82%|████████▏ | 50671/61904 [3:34:18<3:56:52,  1.27s/it]
 82%|████████▏ | 50672/61904 [3:34:19<3:59:17,  1.28s/it]
 82%|████████▏ | 50673/61904 [3:34:20<4:07:41,  1.32s/it]
 82%|████████▏ | 50674/61904 [3:34:22<4:07:33,  1.32s/it]
 82%|████████▏ | 50675/61904 [3:34:23<4:11:15,  1.34s/it]
 82%|████████▏ | 50676/61904 [3:34:24<4:09:52,  1.34s/it]
 82%|████████▏ | 50677/61904 [3:34:26<4:15:43,  1.37s/it]
 82%|████████▏ | 50678/61904 [3:34:27<4:10:54,  1.34s/it]
 82%|████████▏ | 50679/61904 [3:34:28<4:10:15,  1.34s/it]
 82%|████████▏ | 50680/61904 [3:34:30<4:07:15,  1.32s/it]
                                                         
{'loss': 2.4063, 'learning_rate': 1.1819006871515623e-07, 'epoch': 13.1}

 82%|████████▏ | 50680/61904 [3:34:30<4:07:15,  1.32s/it]
 82%|████████▏ | 50681/61904 [3:34:31<4:12:22,  1.35s/it]
 82%|████████▏ | 50682/61904 [3:34:33<4:13:12,  1.35s/it]
 82%|████████▏ | 50683/61904 [3:34:34<4:22:21,  1.40s/it]
 82%|████████▏ | 50684/61904 [3:34:35<4:13:37,  1.36s/it]
 82%|████████▏ | 50685/61904 [3:34:37<4:16:32,  1.37s/it]
 82%|████████▏ | 50686/61904 [3:34:38<4:14:20,  1.36s/it]
 82%|████████▏ | 50687/61904 [3:34:39<4:10:54,  1.34s/it]
 82%|████████▏ | 50688/61904 [3:34:41<4:09:33,  1.34s/it]
 82%|████████▏ | 50689/61904 [3:34:42<4:08:59,  1.33s/it]
 82%|████████▏ | 50690/61904 [3:34:43<4:18:24,  1.38s/it]
 82%|████████▏ | 50691/61904 [3:34:45<4:15:11,  1.37s/it]
 82%|████████▏ | 50692/61904 [3:34:46<4:11:15,  1.34s/it]
 82%|████████▏ | 50693/61904 [3:34:48<4:19:48,  1.39s/it]
 82%|████████▏ | 50694/61904 [3:34:49<4:22:56,  1.41s/it]
 82%|████████▏ | 50695/61904 [3:34:51<4:27:42,  1.43s/it]
 82%|████████▏ | 50696/61904 [3:34:52<4:27:47,  1.43s/it]
 82%|████████▏ | 50697/61904 [3:34:53<4:19:09,  1.39s/it]
 82%|████████▏ | 50698/61904 [3:34:55<4:22:27,  1.41s/it]
 82%|████████▏ | 50699/61904 [3:34:56<4:24:27,  1.42s/it]
 82%|████████▏ | 50700/61904 [3:34:58<4:22:38,  1.41s/it]
                                                         
{'loss': 2.4893, 'learning_rate': 1.1815765590561389e-07, 'epoch': 13.1}

 82%|████████▏ | 50700/61904 [3:34:58<4:22:38,  1.41s/it]
 82%|████████▏ | 50701/61904 [3:34:59<4:18:01,  1.38s/it]
 82%|████████▏ | 50702/61904 [3:35:00<4:16:22,  1.37s/it]
 82%|████████▏ | 50703/61904 [3:35:02<4:15:10,  1.37s/it]
 82%|████████▏ | 50704/61904 [3:35:03<4:13:07,  1.36s/it]
 82%|████████▏ | 50705/61904 [3:35:04<4:11:57,  1.35s/it]
 82%|████████▏ | 50706/61904 [3:35:06<4:14:10,  1.36s/it]
 82%|████████▏ | 50707/61904 [3:35:07<4:15:32,  1.37s/it]
 82%|████████▏ | 50708/61904 [3:35:08<4:14:36,  1.36s/it]
 82%|████████▏ | 50709/61904 [3:35:10<4:10:50,  1.34s/it]
 82%|████████▏ | 50710/61904 [3:35:11<4:06:03,  1.32s/it]
 82%|████████▏ | 50711/61904 [3:35:12<4:21:28,  1.40s/it]
 82%|████████▏ | 50712/61904 [3:35:14<4:18:58,  1.39s/it]
 82%|████████▏ | 50713/61904 [3:35:15<4:27:12,  1.43s/it]
 82%|████████▏ | 50714/61904 [3:35:17<4:46:12,  1.53s/it]
 82%|████████▏ | 50715/61904 [3:35:18<4:29:37,  1.45s/it]
 82%|████████▏ | 50716/61904 [3:35:20<4:25:39,  1.42s/it]
 82%|████████▏ | 50717/61904 [3:35:21<4:21:42,  1.40s/it]
 82%|████████▏ | 50718/61904 [3:35:22<4:13:27,  1.36s/it]
 82%|████████▏ | 50719/61904 [3:35:24<4:20:02,  1.39s/it]
 82%|████████▏ | 50720/61904 [3:35:25<4:23:39,  1.41s/it]
                                                         
{'loss': 2.4443, 'learning_rate': 1.1812524309607155e-07, 'epoch': 13.11}

 82%|████████▏ | 50720/61904 [3:35:25<4:23:39,  1.41s/it]
 82%|████████▏ | 50721/61904 [3:35:27<4:19:00,  1.39s/it]
 82%|████████▏ | 50722/61904 [3:35:28<4:14:44,  1.37s/it]
 82%|████████▏ | 50723/61904 [3:35:29<4:10:15,  1.34s/it]
 82%|████████▏ | 50724/61904 [3:35:31<4:24:41,  1.42s/it]
 82%|████████▏ | 50725/61904 [3:35:32<4:22:43,  1.41s/it]
 82%|████████▏ | 50726/61904 [3:35:34<4:25:51,  1.43s/it]
 82%|████████▏ | 50727/61904 [3:35:35<4:27:16,  1.43s/it]
 82%|████████▏ | 50728/61904 [3:35:36<4:18:19,  1.39s/it]
 82%|████████▏ | 50729/61904 [3:35:38<4:18:28,  1.39s/it]
 82%|████████▏ | 50730/61904 [3:35:39<4:09:55,  1.34s/it]
 82%|████████▏ | 50731/61904 [3:35:40<4:13:22,  1.36s/it]
 82%|████████▏ | 50732/61904 [3:35:42<4:11:03,  1.35s/it]
 82%|████████▏ | 50733/61904 [3:35:43<4:12:43,  1.36s/it]
 82%|████████▏ | 50734/61904 [3:35:45<4:14:19,  1.37s/it]
 82%|████████▏ | 50735/61904 [3:35:46<4:07:39,  1.33s/it]
 82%|████████▏ | 50736/61904 [3:35:47<4:04:34,  1.31s/it]
 82%|████████▏ | 50737/61904 [3:35:48<4:05:31,  1.32s/it]
 82%|████████▏ | 50738/61904 [3:35:50<4:11:13,  1.35s/it]
 82%|████████▏ | 50739/61904 [3:35:51<4:12:36,  1.36s/it]
 82%|████████▏ | 50740/61904 [3:35:53<4:10:53,  1.35s/it]
                                                         
{'loss': 2.4188, 'learning_rate': 1.1809283028652923e-07, 'epoch': 13.11}

 82%|████████▏ | 50740/61904 [3:35:53<4:10:53,  1.35s/it]
 82%|████████▏ | 50741/61904 [3:35:54<4:14:15,  1.37s/it]
 82%|████████▏ | 50742/61904 [3:35:55<4:20:43,  1.40s/it]
 82%|████████▏ | 50743/61904 [3:35:57<4:15:01,  1.37s/it]
 82%|████████▏ | 50744/61904 [3:35:58<4:12:48,  1.36s/it]
 82%|████████▏ | 50745/61904 [3:36:00<4:21:02,  1.40s/it]
 82%|████████▏ | 50746/61904 [3:36:01<4:22:15,  1.41s/it]
 82%|████████▏ | 50747/61904 [3:36:02<4:21:12,  1.40s/it]
 82%|████████▏ | 50748/61904 [3:36:04<4:15:02,  1.37s/it]
 82%|████████▏ | 50749/61904 [3:36:05<4:15:58,  1.38s/it]
 82%|████████▏ | 50750/61904 [3:36:06<4:09:42,  1.34s/it]
 82%|████████▏ | 50751/61904 [3:36:08<4:21:11,  1.41s/it]
 82%|████████▏ | 50752/61904 [3:36:09<4:14:06,  1.37s/it]
 82%|████████▏ | 50753/61904 [3:36:10<4:12:33,  1.36s/it]
 82%|████████▏ | 50754/61904 [3:36:12<4:11:51,  1.36s/it]
 82%|████████▏ | 50755/61904 [3:36:13<4:21:12,  1.41s/it]
 82%|████████▏ | 50756/61904 [3:36:15<4:20:11,  1.40s/it]
 82%|████████▏ | 50757/61904 [3:36:16<4:16:53,  1.38s/it]
 82%|████████▏ | 50758/61904 [3:36:17<4:13:49,  1.37s/it]
 82%|████████▏ | 50759/61904 [3:36:19<4:16:02,  1.38s/it]
 82%|████████▏ | 50760/61904 [3:36:20<4:15:22,  1.37s/it]
                                                         
{'loss': 2.4566, 'learning_rate': 1.180604174769869e-07, 'epoch': 13.12}

 82%|████████▏ | 50760/61904 [3:36:20<4:15:22,  1.37s/it]
 82%|████████▏ | 50761/61904 [3:36:21<4:06:41,  1.33s/it]
 82%|████████▏ | 50762/61904 [3:36:23<4:07:26,  1.33s/it]
 82%|████████▏ | 50763/61904 [3:36:24<4:09:28,  1.34s/it]
 82%|████████▏ | 50764/61904 [3:36:25<4:06:30,  1.33s/it]
 82%|████████▏ | 50765/61904 [3:36:27<4:14:56,  1.37s/it]
 82%|████████▏ | 50766/61904 [3:36:28<4:22:29,  1.41s/it]
 82%|████████▏ | 50767/61904 [3:36:30<4:16:32,  1.38s/it]
 82%|████████▏ | 50768/61904 [3:36:31<4:12:07,  1.36s/it]
 82%|████████▏ | 50769/61904 [3:36:32<4:15:41,  1.38s/it]
 82%|████████▏ | 50770/61904 [3:36:34<4:14:14,  1.37s/it]
 82%|████████▏ | 50771/61904 [3:36:35<4:13:01,  1.36s/it]
 82%|████████▏ | 50772/61904 [3:36:36<4:12:41,  1.36s/it]
 82%|████████▏ | 50773/61904 [3:36:38<4:15:23,  1.38s/it]
 82%|████████▏ | 50774/61904 [3:36:40<4:31:05,  1.46s/it]
 82%|████████▏ | 50775/61904 [3:36:41<4:22:27,  1.42s/it]
 82%|████████▏ | 50776/61904 [3:36:42<4:12:57,  1.36s/it]
 82%|████████▏ | 50777/61904 [3:36:44<4:24:42,  1.43s/it]
 82%|████████▏ | 50778/61904 [3:36:45<4:24:31,  1.43s/it]
 82%|████████▏ | 50779/61904 [3:36:46<4:21:14,  1.41s/it]
 82%|████████▏ | 50780/61904 [3:36:48<4:20:11,  1.40s/it]
                                                         
{'loss': 2.4187, 'learning_rate': 1.1802800466744456e-07, 'epoch': 13.12}

 82%|████████▏ | 50780/61904 [3:36:48<4:20:11,  1.40s/it]
 82%|████████▏ | 50781/61904 [3:36:49<4:26:24,  1.44s/it]
 82%|████████▏ | 50782/61904 [3:36:51<4:22:15,  1.41s/it]
 82%|████████▏ | 50783/61904 [3:36:52<4:29:29,  1.45s/it]
 82%|████████▏ | 50784/61904 [3:36:54<4:23:05,  1.42s/it]
 82%|████████▏ | 50785/61904 [3:36:55<4:22:21,  1.42s/it]
 82%|████████▏ | 50786/61904 [3:36:56<4:13:22,  1.37s/it]
 82%|████████▏ | 50787/61904 [3:36:58<4:11:10,  1.36s/it]
 82%|████████▏ | 50788/61904 [3:36:59<4:13:15,  1.37s/it]
 82%|████████▏ | 50789/61904 [3:37:00<4:18:07,  1.39s/it]
 82%|████████▏ | 50790/61904 [3:37:02<4:15:03,  1.38s/it]
 82%|████████▏ | 50791/61904 [3:37:03<4:28:01,  1.45s/it]
 82%|████████▏ | 50792/61904 [3:37:05<4:24:43,  1.43s/it]
 82%|████████▏ | 50793/61904 [3:37:06<4:17:53,  1.39s/it]
 82%|████████▏ | 50794/61904 [3:37:08<4:17:22,  1.39s/it]
 82%|████████▏ | 50795/61904 [3:37:09<4:19:54,  1.40s/it]
 82%|████████▏ | 50796/61904 [3:37:10<4:26:45,  1.44s/it]
 82%|████████▏ | 50797/61904 [3:37:12<4:26:55,  1.44s/it]
 82%|████████▏ | 50798/61904 [3:37:13<4:22:11,  1.42s/it]
 82%|████████▏ | 50799/61904 [3:37:15<4:17:34,  1.39s/it]
 82%|████████▏ | 50800/61904 [3:37:16<4:22:16,  1.42s/it]
                                                         
{'loss': 2.4418, 'learning_rate': 1.1799559185790222e-07, 'epoch': 13.13}

 82%|████████▏ | 50800/61904 [3:37:16<4:22:16,  1.42s/it]
 82%|████████▏ | 50801/61904 [3:37:17<4:21:20,  1.41s/it]
 82%|████████▏ | 50802/61904 [3:37:19<4:19:01,  1.40s/it]
 82%|████████▏ | 50803/61904 [3:37:20<4:17:35,  1.39s/it]
 82%|████████▏ | 50804/61904 [3:37:22<4:21:01,  1.41s/it]
 82%|████████▏ | 50805/61904 [3:37:23<4:20:15,  1.41s/it]
 82%|████████▏ | 50806/61904 [3:37:25<4:21:39,  1.41s/it]
 82%|████████▏ | 50807/61904 [3:37:26<4:21:40,  1.41s/it]
 82%|████████▏ | 50808/61904 [3:37:27<4:20:52,  1.41s/it]
 82%|████████▏ | 50809/61904 [3:37:29<4:19:11,  1.40s/it]
 82%|████████▏ | 50810/61904 [3:37:30<4:22:53,  1.42s/it]
 82%|████████▏ | 50811/61904 [3:37:32<4:24:04,  1.43s/it]
 82%|████████▏ | 50812/61904 [3:37:33<4:22:14,  1.42s/it]
 82%|████████▏ | 50813/61904 [3:37:34<4:16:15,  1.39s/it]
 82%|████████▏ | 50814/61904 [3:37:36<4:18:01,  1.40s/it]
 82%|████████▏ | 50815/61904 [3:37:37<4:17:26,  1.39s/it]
 82%|████████▏ | 50816/61904 [3:37:38<4:12:04,  1.36s/it]
 82%|████████▏ | 50817/61904 [3:37:40<4:19:24,  1.40s/it]
 82%|████████▏ | 50818/61904 [3:37:41<4:14:14,  1.38s/it]
 82%|████████▏ | 50819/61904 [3:37:43<4:15:46,  1.38s/it]
 82%|████████▏ | 50820/61904 [3:37:44<4:14:37,  1.38s/it]
                                                         
{'loss': 2.4705, 'learning_rate': 1.179631790483599e-07, 'epoch': 13.13}

 82%|████████▏ | 50820/61904 [3:37:44<4:14:37,  1.38s/it]
 82%|████████▏ | 50821/61904 [3:37:45<4:11:45,  1.36s/it]
 82%|████████▏ | 50822/61904 [3:37:47<4:04:35,  1.32s/it]
 82%|████████▏ | 50823/61904 [3:37:48<4:00:43,  1.30s/it]
 82%|████████▏ | 50824/61904 [3:37:49<4:08:17,  1.34s/it]
 82%|████████▏ | 50825/61904 [3:37:51<4:10:51,  1.36s/it]
 82%|████████▏ | 50826/61904 [3:37:52<4:03:17,  1.32s/it]
 82%|████████▏ | 50827/61904 [3:37:53<3:59:56,  1.30s/it]
 82%|████████▏ | 50828/61904 [3:37:55<4:11:52,  1.36s/it]
 82%|████████▏ | 50829/61904 [3:37:56<4:16:17,  1.39s/it]
 82%|████████▏ | 50830/61904 [3:37:57<4:06:56,  1.34s/it]
 82%|████████▏ | 50831/61904 [3:37:59<4:08:29,  1.35s/it]
 82%|████████▏ | 50832/61904 [3:38:00<4:08:37,  1.35s/it]
 82%|████████▏ | 50833/61904 [3:38:01<4:06:52,  1.34s/it]
 82%|████████▏ | 50834/61904 [3:38:03<4:10:29,  1.36s/it]
 82%|████████▏ | 50835/61904 [3:38:04<4:07:09,  1.34s/it]
 82%|████████▏ | 50836/61904 [3:38:06<4:14:57,  1.38s/it]
 82%|████████▏ | 50837/61904 [3:38:07<4:19:03,  1.40s/it]
 82%|████████▏ | 50838/61904 [3:38:08<4:20:12,  1.41s/it]
 82%|████████▏ | 50839/61904 [3:38:10<4:20:50,  1.41s/it]
 82%|████████▏ | 50840/61904 [3:38:11<4:19:31,  1.41s/it]
                                                         
{'loss': 2.4966, 'learning_rate': 1.1793076623881758e-07, 'epoch': 13.14}

 82%|████████▏ | 50840/61904 [3:38:11<4:19:31,  1.41s/it]
 82%|████████▏ | 50841/61904 [3:38:13<4:15:31,  1.39s/it]
 82%|████████▏ | 50842/61904 [3:38:14<4:18:57,  1.40s/it]
 82%|████████▏ | 50843/61904 [3:38:15<4:23:33,  1.43s/it]
 82%|████████▏ | 50844/61904 [3:38:17<4:32:38,  1.48s/it]
 82%|████████▏ | 50845/61904 [3:38:18<4:23:56,  1.43s/it]
 82%|████████▏ | 50846/61904 [3:38:20<4:20:07,  1.41s/it]
 82%|████████▏ | 50847/61904 [3:38:21<4:25:06,  1.44s/it]
 82%|████████▏ | 50848/61904 [3:38:23<4:30:10,  1.47s/it]
 82%|████████▏ | 50849/61904 [3:38:24<4:29:26,  1.46s/it]
 82%|████████▏ | 50850/61904 [3:38:26<4:26:52,  1.45s/it]
 82%|████████▏ | 50851/61904 [3:38:27<4:29:03,  1.46s/it]
 82%|████████▏ | 50852/61904 [3:38:29<4:33:04,  1.48s/it]
 82%|████████▏ | 50853/61904 [3:38:30<4:35:44,  1.50s/it]
 82%|████████▏ | 50854/61904 [3:38:32<4:32:16,  1.48s/it]
 82%|████████▏ | 50855/61904 [3:38:33<4:31:42,  1.48s/it]
 82%|████████▏ | 50856/61904 [3:38:34<4:21:43,  1.42s/it]
 82%|████████▏ | 50857/61904 [3:38:36<4:22:46,  1.43s/it]
 82%|████████▏ | 50858/61904 [3:38:37<4:16:21,  1.39s/it]
 82%|████████▏ | 50859/61904 [3:38:39<4:16:36,  1.39s/it]
 82%|████████▏ | 50860/61904 [3:38:40<4:13:49,  1.38s/it]
                                                         
{'loss': 2.4615, 'learning_rate': 1.1789835342927524e-07, 'epoch': 13.15}

 82%|████████▏ | 50860/61904 [3:38:40<4:13:49,  1.38s/it]
 82%|████████▏ | 50861/61904 [3:38:41<4:13:08,  1.38s/it]
 82%|████████▏ | 50862/61904 [3:38:43<4:13:02,  1.37s/it]
 82%|████████▏ | 50863/61904 [3:38:44<4:10:54,  1.36s/it]
 82%|████████▏ | 50864/61904 [3:38:45<4:10:14,  1.36s/it]
 82%|████████▏ | 50865/61904 [3:38:47<4:12:01,  1.37s/it]
 82%|████████▏ | 50866/61904 [3:38:48<4:10:45,  1.36s/it]
 82%|████████▏ | 50867/61904 [3:38:50<4:29:09,  1.46s/it]
 82%|████████▏ | 50868/61904 [3:38:51<4:22:12,  1.43s/it]
 82%|████████▏ | 50869/61904 [3:38:52<4:13:08,  1.38s/it]
 82%|████████▏ | 50870/61904 [3:38:54<4:16:04,  1.39s/it]
 82%|████████▏ | 50871/61904 [3:38:55<4:11:53,  1.37s/it]
 82%|████████▏ | 50872/61904 [3:38:56<4:07:27,  1.35s/it]
 82%|████████▏ | 50873/61904 [3:38:58<4:05:50,  1.34s/it]
 82%|████████▏ | 50874/61904 [3:38:59<4:18:15,  1.40s/it]
 82%|████████▏ | 50875/61904 [3:39:01<4:16:33,  1.40s/it]
 82%|████████▏ | 50876/61904 [3:39:02<4:19:16,  1.41s/it]
 82%|████████▏ | 50877/61904 [3:39:03<4:16:35,  1.40s/it]
 82%|████████▏ | 50878/61904 [3:39:05<4:10:41,  1.36s/it]
 82%|████████▏ | 50879/61904 [3:39:06<4:03:03,  1.32s/it]
 82%|████████▏ | 50880/61904 [3:39:08<4:16:06,  1.39s/it]
                                                         
{'loss': 2.4513, 'learning_rate': 1.1786594061973291e-07, 'epoch': 13.15}

 82%|████████▏ | 50880/61904 [3:39:08<4:16:06,  1.39s/it]
 82%|████████▏ | 50881/61904 [3:39:09<4:11:40,  1.37s/it]
 82%|████████▏ | 50882/61904 [3:39:10<4:19:10,  1.41s/it]
 82%|████████▏ | 50883/61904 [3:39:12<4:21:58,  1.43s/it]
 82%|████████▏ | 50884/61904 [3:39:13<4:15:56,  1.39s/it]
 82%|████████▏ | 50885/61904 [3:39:15<4:22:30,  1.43s/it]
 82%|████████▏ | 50886/61904 [3:39:16<4:18:13,  1.41s/it]
 82%|████████▏ | 50887/61904 [3:39:18<4:23:03,  1.43s/it]
 82%|████████▏ | 50888/61904 [3:39:19<4:23:17,  1.43s/it]
 82%|████████▏ | 50889/61904 [3:39:20<4:15:30,  1.39s/it]
 82%|████████▏ | 50890/61904 [3:39:22<4:09:45,  1.36s/it]
 82%|████████▏ | 50891/61904 [3:39:23<4:08:50,  1.36s/it]
 82%|████████▏ | 50892/61904 [3:39:24<4:10:11,  1.36s/it]
 82%|████████▏ | 50893/61904 [3:39:26<4:16:11,  1.40s/it]
 82%|████████▏ | 50894/61904 [3:39:27<4:15:19,  1.39s/it]
 82%|████████▏ | 50895/61904 [3:39:28<4:04:54,  1.33s/it]
 82%|████████▏ | 50896/61904 [3:39:30<4:08:20,  1.35s/it]
 82%|████████▏ | 50897/61904 [3:39:31<4:14:59,  1.39s/it]
 82%|████████▏ | 50898/61904 [3:39:33<4:18:03,  1.41s/it]
 82%|████████▏ | 50899/61904 [3:39:34<4:16:36,  1.40s/it]
 82%|████████▏ | 50900/61904 [3:39:35<4:19:09,  1.41s/it]
                                                         
{'loss': 2.4163, 'learning_rate': 1.1783352781019059e-07, 'epoch': 13.16}

 82%|████████▏ | 50900/61904 [3:39:35<4:19:09,  1.41s/it]
 82%|████████▏ | 50901/61904 [3:39:37<4:16:02,  1.40s/it]
 82%|████████▏ | 50902/61904 [3:39:38<4:08:58,  1.36s/it]
 82%|████████▏ | 50903/61904 [3:39:39<4:06:33,  1.34s/it]
 82%|████████▏ | 50904/61904 [3:39:41<4:18:02,  1.41s/it]
 82%|████████▏ | 50905/61904 [3:39:42<4:18:13,  1.41s/it]
 82%|████████▏ | 50906/61904 [3:39:44<4:23:09,  1.44s/it]
 82%|████████▏ | 50907/61904 [3:39:45<4:14:33,  1.39s/it]
 82%|████████▏ | 50908/61904 [3:39:47<4:14:38,  1.39s/it]
 82%|████████▏ | 50909/61904 [3:39:48<4:12:48,  1.38s/it]
 82%|████████▏ | 50910/61904 [3:39:49<4:20:10,  1.42s/it]
 82%|████████▏ | 50911/61904 [3:39:51<4:19:32,  1.42s/it]
 82%|████████▏ | 50912/61904 [3:39:52<4:20:25,  1.42s/it]
 82%|████████▏ | 50913/61904 [3:39:54<4:14:14,  1.39s/it]
 82%|████████▏ | 50914/61904 [3:39:55<4:14:23,  1.39s/it]
 82%|████████▏ | 50915/61904 [3:39:56<4:18:18,  1.41s/it]
 82%|████████▏ | 50916/61904 [3:39:58<4:16:30,  1.40s/it]
 82%|████████▏ | 50917/61904 [3:39:59<4:18:07,  1.41s/it]
 82%|████████▏ | 50918/61904 [3:40:01<4:23:54,  1.44s/it]
 82%|████████▏ | 50919/61904 [3:40:02<4:18:35,  1.41s/it]
 82%|████████▏ | 50920/61904 [3:40:04<4:20:15,  1.42s/it]
                                                         
{'loss': 2.457, 'learning_rate': 1.1780111500064825e-07, 'epoch': 13.16}

 82%|████████▏ | 50920/61904 [3:40:04<4:20:15,  1.42s/it]
 82%|████████▏ | 50921/61904 [3:40:05<4:12:26,  1.38s/it]
 82%|████████▏ | 50922/61904 [3:40:06<4:07:32,  1.35s/it]
 82%|████████▏ | 50923/61904 [3:40:07<4:09:47,  1.36s/it]
 82%|████████▏ | 50924/61904 [3:40:09<4:20:54,  1.43s/it]
 82%|████████▏ | 50925/61904 [3:40:10<4:19:09,  1.42s/it]
 82%|████████▏ | 50926/61904 [3:40:12<4:11:33,  1.37s/it]
 82%|████████▏ | 50927/61904 [3:40:13<4:11:07,  1.37s/it]
 82%|████████▏ | 50928/61904 [3:40:14<4:12:40,  1.38s/it]
 82%|████████▏ | 50929/61904 [3:40:16<4:11:39,  1.38s/it]
 82%|████████▏ | 50930/61904 [3:40:17<4:11:12,  1.37s/it]
 82%|████████▏ | 50931/61904 [3:40:19<4:16:37,  1.40s/it]
 82%|████████▏ | 50932/61904 [3:40:20<4:22:45,  1.44s/it]
 82%|████████▏ | 50933/61904 [3:40:22<4:21:53,  1.43s/it]
 82%|████████▏ | 50934/61904 [3:40:23<4:21:02,  1.43s/it]
 82%|████████▏ | 50935/61904 [3:40:25<4:23:10,  1.44s/it]
 82%|████████▏ | 50936/61904 [3:40:26<4:20:32,  1.43s/it]
 82%|████████▏ | 50937/61904 [3:40:27<4:12:35,  1.38s/it]
 82%|████████▏ | 50938/61904 [3:40:29<4:21:46,  1.43s/it]
 82%|████████▏ | 50939/61904 [3:40:30<4:20:36,  1.43s/it]
 82%|████████▏ | 50940/61904 [3:40:32<4:33:43,  1.50s/it]
                                                         
{'loss': 2.4637, 'learning_rate': 1.1776870219110591e-07, 'epoch': 13.17}

 82%|████████▏ | 50940/61904 [3:40:32<4:33:43,  1.50s/it]
 82%|████████▏ | 50941/61904 [3:40:33<4:24:18,  1.45s/it]
 82%|████████▏ | 50942/61904 [3:40:34<4:16:50,  1.41s/it]
 82%|████████▏ | 50943/61904 [3:40:36<4:17:38,  1.41s/it]
 82%|████████▏ | 50944/61904 [3:40:37<4:15:34,  1.40s/it]
 82%|████████▏ | 50945/61904 [3:40:39<4:23:40,  1.44s/it]
 82%|████████▏ | 50946/61904 [3:40:40<4:24:06,  1.45s/it]
 82%|████████▏ | 50947/61904 [3:40:42<4:19:53,  1.42s/it]
 82%|████████▏ | 50948/61904 [3:40:43<4:16:37,  1.41s/it]
 82%|████████▏ | 50949/61904 [3:40:44<4:14:01,  1.39s/it]
 82%|████████▏ | 50950/61904 [3:40:46<4:17:01,  1.41s/it]
 82%|████████▏ | 50951/61904 [3:40:47<4:18:45,  1.42s/it]
 82%|████████▏ | 50952/61904 [3:40:49<4:11:33,  1.38s/it]
 82%|████████▏ | 50953/61904 [3:40:50<4:14:34,  1.39s/it]
 82%|████████▏ | 50954/61904 [3:40:51<4:16:05,  1.40s/it]
 82%|████████▏ | 50955/61904 [3:40:53<4:26:02,  1.46s/it]
 82%|████████▏ | 50956/61904 [3:40:54<4:17:06,  1.41s/it]
 82%|████████▏ | 50957/61904 [3:40:55<4:07:42,  1.36s/it]
 82%|████████▏ | 50958/61904 [3:40:57<4:00:14,  1.32s/it]
 82%|████████▏ | 50959/61904 [3:40:58<4:03:46,  1.34s/it]
 82%|████████▏ | 50960/61904 [3:41:00<4:12:51,  1.39s/it]
                                                         
{'loss': 2.4972, 'learning_rate': 1.1773628938156359e-07, 'epoch': 13.17}

 82%|████████▏ | 50960/61904 [3:41:00<4:12:51,  1.39s/it]
 82%|████████▏ | 50961/61904 [3:41:01<4:07:02,  1.35s/it]
 82%|████████▏ | 50962/61904 [3:41:02<4:10:03,  1.37s/it]
 82%|████████▏ | 50963/61904 [3:41:04<4:12:34,  1.39s/it]
 82%|████████▏ | 50964/61904 [3:41:05<4:12:36,  1.39s/it]
 82%|████████▏ | 50965/61904 [3:41:07<4:16:04,  1.40s/it]
 82%|████████▏ | 50966/61904 [3:41:08<4:36:14,  1.52s/it]
 82%|████████▏ | 50967/61904 [3:41:10<4:31:05,  1.49s/it]
 82%|████████▏ | 50968/61904 [3:41:11<4:28:55,  1.48s/it]
 82%|████████▏ | 50969/61904 [3:41:12<4:14:26,  1.40s/it]
 82%|████████▏ | 50970/61904 [3:41:14<4:11:33,  1.38s/it]
 82%|████████▏ | 50971/61904 [3:41:15<4:16:23,  1.41s/it]
 82%|████████▏ | 50972/61904 [3:41:17<4:26:10,  1.46s/it]
 82%|████████▏ | 50973/61904 [3:41:18<4:21:13,  1.43s/it]
 82%|████████▏ | 50974/61904 [3:41:20<4:26:34,  1.46s/it]
 82%|████████▏ | 50975/61904 [3:41:21<4:24:44,  1.45s/it]
 82%|████████▏ | 50976/61904 [3:41:23<4:20:20,  1.43s/it]
 82%|████████▏ | 50977/61904 [3:41:24<4:20:54,  1.43s/it]
 82%|████████▏ | 50978/61904 [3:41:25<4:18:31,  1.42s/it]
 82%|████████▏ | 50979/61904 [3:41:27<4:17:51,  1.42s/it]
 82%|████████▏ | 50980/61904 [3:41:28<4:17:36,  1.41s/it]
                                                         
{'loss': 2.4628, 'learning_rate': 1.1770387657202126e-07, 'epoch': 13.18}

 82%|████████▏ | 50980/61904 [3:41:28<4:17:36,  1.41s/it]
 82%|████████▏ | 50981/61904 [3:41:30<4:19:54,  1.43s/it]
 82%|████████▏ | 50982/61904 [3:41:31<4:23:22,  1.45s/it]
 82%|████████▏ | 50983/61904 [3:41:32<4:19:57,  1.43s/it]
 82%|████████▏ | 50984/61904 [3:41:34<4:17:30,  1.41s/it]
 82%|████████▏ | 50985/61904 [3:41:35<4:25:23,  1.46s/it]
 82%|████████▏ | 50986/61904 [3:41:37<4:18:46,  1.42s/it]
 82%|████████▏ | 50987/61904 [3:41:38<4:18:13,  1.42s/it]
 82%|████████▏ | 50988/61904 [3:41:40<4:17:17,  1.41s/it]
 82%|████████▏ | 50989/61904 [3:41:41<4:13:32,  1.39s/it]
 82%|████████▏ | 50990/61904 [3:41:42<4:15:05,  1.40s/it]
 82%|████████▏ | 50991/61904 [3:41:44<4:19:21,  1.43s/it]
 82%|████████▏ | 50992/61904 [3:41:45<4:20:18,  1.43s/it]
 82%|████████▏ | 50993/61904 [3:41:47<4:13:45,  1.40s/it]
 82%|████████▏ | 50994/61904 [3:41:48<4:13:29,  1.39s/it]
 82%|████████▏ | 50995/61904 [3:41:49<4:11:43,  1.38s/it]
 82%|████████▏ | 50996/61904 [3:41:51<4:13:30,  1.39s/it]
 82%|████████▏ | 50997/61904 [3:41:52<4:10:06,  1.38s/it]
 82%|████████▏ | 50998/61904 [3:41:53<4:09:13,  1.37s/it]
 82%|████████▏ | 50999/61904 [3:41:55<4:24:44,  1.46s/it]
 82%|████████▏ | 51000/61904 [3:41:57<4:23:13,  1.45s/it]
                                                         
{'loss': 2.404, 'learning_rate': 1.1767146376247892e-07, 'epoch': 13.18}

 82%|████████▏ | 51000/61904 [3:41:57<4:23:13,  1.45s/it]
 82%|████████▏ | 51001/61904 [3:41:58<4:17:24,  1.42s/it]
 82%|████████▏ | 51002/61904 [3:41:59<4:15:01,  1.40s/it]
 82%|████████▏ | 51003/61904 [3:42:01<4:22:15,  1.44s/it]
 82%|████████▏ | 51004/61904 [3:42:02<4:11:46,  1.39s/it]
 82%|████████▏ | 51005/61904 [3:42:04<4:21:24,  1.44s/it]
 82%|████████▏ | 51006/61904 [3:42:05<4:13:59,  1.40s/it]
 82%|████████▏ | 51007/61904 [3:42:06<4:13:50,  1.40s/it]
 82%|████████▏ | 51008/61904 [3:42:08<4:19:14,  1.43s/it]
 82%|████████▏ | 51009/61904 [3:42:09<4:12:09,  1.39s/it]
 82%|████████▏ | 51010/61904 [3:42:10<4:11:31,  1.39s/it]
 82%|████████▏ | 51011/61904 [3:42:12<4:08:44,  1.37s/it]
 82%|████████▏ | 51012/61904 [3:42:13<4:07:42,  1.36s/it]
 82%|████████▏ | 51013/61904 [3:42:15<4:09:26,  1.37s/it]
 82%|████████▏ | 51014/61904 [3:42:16<4:02:57,  1.34s/it]
 82%|████████▏ | 51015/61904 [3:42:17<4:03:01,  1.34s/it]
 82%|████████▏ | 51016/61904 [3:42:18<4:01:32,  1.33s/it]
 82%|████████▏ | 51017/61904 [3:42:20<4:08:01,  1.37s/it]
 82%|████████▏ | 51018/61904 [3:42:21<4:08:40,  1.37s/it]
 82%|████████▏ | 51019/61904 [3:42:23<4:07:15,  1.36s/it]
 82%|████████▏ | 51020/61904 [3:42:24<4:09:00,  1.37s/it]
                                                         
{'loss': 2.4146, 'learning_rate': 1.1763905095293658e-07, 'epoch': 13.19}

 82%|████████▏ | 51020/61904 [3:42:24<4:09:00,  1.37s/it]
 82%|████████▏ | 51021/61904 [3:42:25<4:05:33,  1.35s/it]
 82%|████████▏ | 51022/61904 [3:42:27<4:04:48,  1.35s/it]
 82%|████████▏ | 51023/61904 [3:42:28<4:06:45,  1.36s/it]
 82%|████████▏ | 51024/61904 [3:42:30<4:11:46,  1.39s/it]
 82%|████████▏ | 51025/61904 [3:42:31<4:08:50,  1.37s/it]
 82%|████████▏ | 51026/61904 [3:42:32<4:10:16,  1.38s/it]
 82%|████████▏ | 51027/61904 [3:42:34<4:08:38,  1.37s/it]
 82%|████████▏ | 51028/61904 [3:42:35<4:04:20,  1.35s/it]
 82%|████████▏ | 51029/61904 [3:42:36<4:03:40,  1.34s/it]
 82%|████████▏ | 51030/61904 [3:42:38<4:09:54,  1.38s/it]
 82%|████████▏ | 51031/61904 [3:42:39<4:15:21,  1.41s/it]
 82%|████████▏ | 51032/61904 [3:42:41<4:12:39,  1.39s/it]
 82%|████████▏ | 51033/61904 [3:42:42<4:13:15,  1.40s/it]
 82%|████████▏ | 51034/61904 [3:42:43<4:10:33,  1.38s/it]
 82%|████████▏ | 51035/61904 [3:42:45<4:11:59,  1.39s/it]
 82%|████████▏ | 51036/61904 [3:42:46<4:08:01,  1.37s/it]
 82%|████████▏ | 51037/61904 [3:42:47<4:12:17,  1.39s/it]
 82%|████████▏ | 51038/61904 [3:42:49<4:07:41,  1.37s/it]
 82%|████████▏ | 51039/61904 [3:42:50<4:01:56,  1.34s/it]
 82%|████████▏ | 51040/61904 [3:42:52<4:14:37,  1.41s/it]
                                                         
{'loss': 2.4528, 'learning_rate': 1.1760663814339426e-07, 'epoch': 13.19}

 82%|████████▏ | 51040/61904 [3:42:52<4:14:37,  1.41s/it]
 82%|████████▏ | 51041/61904 [3:42:53<4:17:53,  1.42s/it]
 82%|████████▏ | 51042/61904 [3:42:54<4:14:40,  1.41s/it]
 82%|████████▏ | 51043/61904 [3:42:56<4:13:11,  1.40s/it]
 82%|████████▏ | 51044/61904 [3:42:57<4:13:01,  1.40s/it]
 82%|████████▏ | 51045/61904 [3:42:59<4:11:14,  1.39s/it]
 82%|████████▏ | 51046/61904 [3:43:00<4:08:50,  1.38s/it]
 82%|████████▏ | 51047/61904 [3:43:01<4:09:03,  1.38s/it]
 82%|████████▏ | 51048/61904 [3:43:03<4:04:59,  1.35s/it]
 82%|████████▏ | 51049/61904 [3:43:04<4:13:57,  1.40s/it]
 82%|████████▏ | 51050/61904 [3:43:06<4:16:45,  1.42s/it]
 82%|████████▏ | 51051/61904 [3:43:07<4:08:21,  1.37s/it]
 82%|████████▏ | 51052/61904 [3:43:08<4:03:07,  1.34s/it]
 82%|████████▏ | 51053/61904 [3:43:09<4:03:15,  1.35s/it]
 82%|████████▏ | 51054/61904 [3:43:11<4:03:18,  1.35s/it]
 82%|████████▏ | 51055/61904 [3:43:12<4:02:31,  1.34s/it]
 82%|████████▏ | 51056/61904 [3:43:14<4:11:07,  1.39s/it]
 82%|████████▏ | 51057/61904 [3:43:15<4:08:37,  1.38s/it]
 82%|████████▏ | 51058/61904 [3:43:16<4:08:49,  1.38s/it]
 82%|████████▏ | 51059/61904 [3:43:18<4:09:55,  1.38s/it]
 82%|████████▏ | 51060/61904 [3:43:19<4:10:53,  1.39s/it]
                                                         
{'loss': 2.4843, 'learning_rate': 1.1757422533385193e-07, 'epoch': 13.2}

 82%|████████▏ | 51060/61904 [3:43:19<4:10:53,  1.39s/it]
 82%|████████▏ | 51061/61904 [3:43:21<4:20:11,  1.44s/it]
 82%|████████▏ | 51062/61904 [3:43:22<4:15:29,  1.41s/it]
 82%|████████▏ | 51063/61904 [3:43:23<4:14:04,  1.41s/it]
 82%|████████▏ | 51064/61904 [3:43:25<4:09:08,  1.38s/it]
 82%|████████▏ | 51065/61904 [3:43:26<4:11:40,  1.39s/it]
 82%|████████▏ | 51066/61904 [3:43:27<4:05:32,  1.36s/it]
 82%|████████▏ | 51067/61904 [3:43:29<3:59:06,  1.32s/it]
 82%|████████▏ | 51068/61904 [3:43:30<3:57:40,  1.32s/it]
 82%|████████▏ | 51069/61904 [3:43:32<4:07:15,  1.37s/it]
 82%|████████▏ | 51070/61904 [3:43:33<4:00:20,  1.33s/it]
 83%|████████▎ | 51071/61904 [3:43:34<4:01:16,  1.34s/it]
 83%|████████▎ | 51072/61904 [3:43:35<3:58:10,  1.32s/it]
 83%|████████▎ | 51073/61904 [3:43:37<4:05:04,  1.36s/it]
 83%|████████▎ | 51074/61904 [3:43:38<4:10:03,  1.39s/it]
 83%|████████▎ | 51075/61904 [3:43:40<4:18:47,  1.43s/it]
 83%|████████▎ | 51076/61904 [3:43:41<4:11:42,  1.39s/it]
 83%|████████▎ | 51077/61904 [3:43:42<4:08:35,  1.38s/it]
 83%|████████▎ | 51078/61904 [3:43:44<4:03:19,  1.35s/it]
 83%|████████▎ | 51079/61904 [3:43:45<3:59:59,  1.33s/it]
 83%|████████▎ | 51080/61904 [3:43:46<3:59:25,  1.33s/it]
                                                         
{'loss': 2.4556, 'learning_rate': 1.175418125243096e-07, 'epoch': 13.2}

 83%|████████▎ | 51080/61904 [3:43:46<3:59:25,  1.33s/it]
 83%|████████▎ | 51081/61904 [3:43:48<4:08:49,  1.38s/it]
 83%|████████▎ | 51082/61904 [3:43:49<4:04:27,  1.36s/it]
 83%|████████▎ | 51083/61904 [3:43:51<4:07:05,  1.37s/it]
 83%|████████▎ | 51084/61904 [3:43:52<3:59:33,  1.33s/it]
 83%|████████▎ | 51085/61904 [3:43:53<4:02:29,  1.34s/it]
 83%|████████▎ | 51086/61904 [3:43:55<4:09:47,  1.39s/it]
 83%|████████▎ | 51087/61904 [3:43:56<4:16:08,  1.42s/it]
 83%|████████▎ | 51088/61904 [3:43:58<4:14:59,  1.41s/it]
 83%|████████▎ | 51089/61904 [3:43:59<4:09:24,  1.38s/it]
 83%|████████▎ | 51090/61904 [3:44:00<4:04:43,  1.36s/it]
 83%|████████▎ | 51091/61904 [3:44:02<4:09:03,  1.38s/it]
 83%|████████▎ | 51092/61904 [3:44:03<4:21:30,  1.45s/it]
 83%|████████▎ | 51093/61904 [3:44:05<4:15:21,  1.42s/it]
 83%|████████▎ | 51094/61904 [3:44:06<4:09:03,  1.38s/it]
 83%|████████▎ | 51095/61904 [3:44:07<4:04:26,  1.36s/it]
 83%|████████▎ | 51096/61904 [3:44:08<4:00:22,  1.33s/it]
 83%|████████▎ | 51097/61904 [3:44:10<3:59:21,  1.33s/it]
 83%|████████▎ | 51098/61904 [3:44:11<4:00:10,  1.33s/it]
 83%|████████▎ | 51099/61904 [3:44:13<4:10:06,  1.39s/it]
 83%|████████▎ | 51100/61904 [3:44:14<4:05:12,  1.36s/it]
                                                         
{'loss': 2.4307, 'learning_rate': 1.1750939971476726e-07, 'epoch': 13.21}

 83%|████████▎ | 51100/61904 [3:44:14<4:05:12,  1.36s/it]
 83%|████████▎ | 51101/61904 [3:44:15<3:58:50,  1.33s/it]
 83%|████████▎ | 51102/61904 [3:44:17<4:01:29,  1.34s/it]
 83%|████████▎ | 51103/61904 [3:44:18<3:59:09,  1.33s/it]
 83%|████████▎ | 51104/61904 [3:44:19<3:53:39,  1.30s/it]
 83%|████████▎ | 51105/61904 [3:44:21<4:05:23,  1.36s/it]
 83%|████████▎ | 51106/61904 [3:44:22<4:10:51,  1.39s/it]
 83%|████████▎ | 51107/61904 [3:44:23<4:07:46,  1.38s/it]
 83%|████████▎ | 51108/61904 [3:44:25<4:21:20,  1.45s/it]
 83%|████████▎ | 51109/61904 [3:44:26<4:10:48,  1.39s/it]
 83%|████████▎ | 51110/61904 [3:44:28<4:06:53,  1.37s/it]
 83%|████████▎ | 51111/61904 [3:44:29<4:04:19,  1.36s/it]
 83%|████████▎ | 51112/61904 [3:44:30<4:05:08,  1.36s/it]
 83%|████████▎ | 51113/61904 [3:44:32<4:04:13,  1.36s/it]
 83%|████████▎ | 51114/61904 [3:44:33<4:06:26,  1.37s/it]
 83%|████████▎ | 51115/61904 [3:44:34<4:03:31,  1.35s/it]
 83%|████████▎ | 51116/61904 [3:44:36<4:00:58,  1.34s/it]
 83%|████████▎ | 51117/61904 [3:44:37<4:10:42,  1.39s/it]
 83%|████████▎ | 51118/61904 [3:44:38<4:04:34,  1.36s/it]
 83%|████████▎ | 51119/61904 [3:44:40<4:04:56,  1.36s/it]
 83%|████████▎ | 51120/61904 [3:44:41<4:09:29,  1.39s/it]
                                                         
{'loss': 2.4733, 'learning_rate': 1.1747698690522493e-07, 'epoch': 13.21}

 83%|████████▎ | 51120/61904 [3:44:41<4:09:29,  1.39s/it]
 83%|████████▎ | 51121/61904 [3:44:43<4:10:45,  1.40s/it]
 83%|████████▎ | 51122/61904 [3:44:44<4:07:49,  1.38s/it]
 83%|████████▎ | 51123/61904 [3:44:46<4:13:04,  1.41s/it]
 83%|████████▎ | 51124/61904 [3:44:47<4:06:57,  1.37s/it]
 83%|████████▎ | 51125/61904 [3:44:48<4:07:34,  1.38s/it]
 83%|████████▎ | 51126/61904 [3:44:50<4:07:44,  1.38s/it]
 83%|████████▎ | 51127/61904 [3:44:51<4:08:12,  1.38s/it]
 83%|████████▎ | 51128/61904 [3:44:52<4:07:39,  1.38s/it]
 83%|████████▎ | 51129/61904 [3:44:54<4:07:20,  1.38s/it]
 83%|████████▎ | 51130/61904 [3:44:55<4:07:01,  1.38s/it]
 83%|████████▎ | 51131/61904 [3:44:56<4:00:31,  1.34s/it]
 83%|████████▎ | 51132/61904 [3:44:58<4:02:16,  1.35s/it]
 83%|████████▎ | 51133/61904 [3:44:59<4:01:54,  1.35s/it]
 83%|████████▎ | 51134/61904 [3:45:01<4:15:52,  1.43s/it]
 83%|████████▎ | 51135/61904 [3:45:02<4:11:06,  1.40s/it]
 83%|████████▎ | 51136/61904 [3:45:03<4:09:37,  1.39s/it]
 83%|████████▎ | 51137/61904 [3:45:05<4:08:20,  1.38s/it]
 83%|████████▎ | 51138/61904 [3:45:06<4:09:32,  1.39s/it]
 83%|████████▎ | 51139/61904 [3:45:07<4:02:57,  1.35s/it]
 83%|████████▎ | 51140/61904 [3:45:09<3:59:59,  1.34s/it]
                                                         
{'loss': 2.4003, 'learning_rate': 1.1744457409568261e-07, 'epoch': 13.22}

 83%|████████▎ | 51140/61904 [3:45:09<3:59:59,  1.34s/it]
 83%|████████▎ | 51141/61904 [3:45:10<4:04:17,  1.36s/it]
 83%|████████▎ | 51142/61904 [3:45:12<4:09:19,  1.39s/it]
 83%|████████▎ | 51143/61904 [3:45:13<4:04:30,  1.36s/it]
 83%|████████▎ | 51144/61904 [3:45:14<4:08:44,  1.39s/it]
 83%|████████▎ | 51145/61904 [3:45:16<4:01:13,  1.35s/it]
 83%|████████▎ | 51146/61904 [3:45:17<4:02:33,  1.35s/it]
 83%|████████▎ | 51147/61904 [3:45:18<3:55:32,  1.31s/it]
 83%|████████▎ | 51148/61904 [3:45:20<3:58:56,  1.33s/it]
 83%|████████▎ | 51149/61904 [3:45:21<4:06:17,  1.37s/it]
 83%|████████▎ | 51150/61904 [3:45:23<4:17:45,  1.44s/it]
 83%|████████▎ | 51151/61904 [3:45:24<4:20:00,  1.45s/it]
 83%|████████▎ | 51152/61904 [3:45:26<4:18:59,  1.45s/it]
 83%|████████▎ | 51153/61904 [3:45:27<4:17:20,  1.44s/it]
 83%|████████▎ | 51154/61904 [3:45:28<4:12:58,  1.41s/it]
 83%|████████▎ | 51155/61904 [3:45:30<4:04:51,  1.37s/it]
 83%|████████▎ | 51156/61904 [3:45:31<4:01:50,  1.35s/it]
 83%|████████▎ | 51157/61904 [3:45:32<4:08:30,  1.39s/it]
 83%|████████▎ | 51158/61904 [3:45:34<4:09:41,  1.39s/it]
 83%|████████▎ | 51159/61904 [3:45:35<4:10:25,  1.40s/it]
 83%|████████▎ | 51160/61904 [3:45:37<4:18:45,  1.45s/it]
                                                         
{'loss': 2.4786, 'learning_rate': 1.1741216128614027e-07, 'epoch': 13.22}

 83%|████████▎ | 51160/61904 [3:45:37<4:18:45,  1.45s/it]
 83%|████████▎ | 51161/61904 [3:45:38<4:13:35,  1.42s/it]
 83%|████████▎ | 51162/61904 [3:45:39<4:08:45,  1.39s/it]
 83%|████████▎ | 51163/61904 [3:45:41<4:05:42,  1.37s/it]
 83%|████████▎ | 51164/61904 [3:45:42<4:06:51,  1.38s/it]
 83%|████████▎ | 51165/61904 [3:45:43<4:04:02,  1.36s/it]
 83%|████████▎ | 51166/61904 [3:45:45<4:03:24,  1.36s/it]
 83%|████████▎ | 51167/61904 [3:45:46<4:09:06,  1.39s/it]
 83%|████████▎ | 51168/61904 [3:45:48<4:12:46,  1.41s/it]
 83%|████████▎ | 51169/61904 [3:45:49<4:12:49,  1.41s/it]
 83%|████████▎ | 51170/61904 [3:45:50<4:08:36,  1.39s/it]
 83%|████████▎ | 51171/61904 [3:45:52<4:08:07,  1.39s/it]
 83%|████████▎ | 51172/61904 [3:45:53<4:06:02,  1.38s/it]
 83%|████████▎ | 51173/61904 [3:45:55<4:04:45,  1.37s/it]
 83%|████████▎ | 51174/61904 [3:45:56<4:10:44,  1.40s/it]
 83%|████████▎ | 51175/61904 [3:45:57<4:06:25,  1.38s/it]
 83%|████████▎ | 51176/61904 [3:45:59<4:01:12,  1.35s/it]
 83%|████████▎ | 51177/61904 [3:46:00<4:13:08,  1.42s/it]
 83%|████████▎ | 51178/61904 [3:46:02<4:06:44,  1.38s/it]
 83%|████████▎ | 51179/61904 [3:46:03<4:08:17,  1.39s/it]
 83%|████████▎ | 51180/61904 [3:46:04<3:59:13,  1.34s/it]
                                                         
{'loss': 2.4754, 'learning_rate': 1.1737974847659795e-07, 'epoch': 13.23}

 83%|████████▎ | 51180/61904 [3:46:04<3:59:13,  1.34s/it]
 83%|████████▎ | 51181/61904 [3:46:06<4:00:29,  1.35s/it]
 83%|████████▎ | 51182/61904 [3:46:07<4:00:47,  1.35s/it]
 83%|████████▎ | 51183/61904 [3:46:08<4:02:12,  1.36s/it]
 83%|████████▎ | 51184/61904 [3:46:10<4:05:07,  1.37s/it]
 83%|████████▎ | 51185/61904 [3:46:11<3:58:59,  1.34s/it]
 83%|████████▎ | 51186/61904 [3:46:12<3:54:54,  1.32s/it]
 83%|████████▎ | 51187/61904 [3:46:13<3:54:43,  1.31s/it]
 83%|████████▎ | 51188/61904 [3:46:15<3:58:25,  1.34s/it]
 83%|████████▎ | 51189/61904 [3:46:16<3:55:22,  1.32s/it]
 83%|████████▎ | 51190/61904 [3:46:18<4:10:02,  1.40s/it]
 83%|████████▎ | 51191/61904 [3:46:19<4:08:41,  1.39s/it]
 83%|████████▎ | 51192/61904 [3:46:21<4:10:29,  1.40s/it]
 83%|████████▎ | 51193/61904 [3:46:22<4:08:20,  1.39s/it]
 83%|████████▎ | 51194/61904 [3:46:23<4:09:27,  1.40s/it]
 83%|████████▎ | 51195/61904 [3:46:25<4:05:28,  1.38s/it]
 83%|████████▎ | 51196/61904 [3:46:26<4:03:53,  1.37s/it]
 83%|████████▎ | 51197/61904 [3:46:27<4:09:03,  1.40s/it]
 83%|████████▎ | 51198/61904 [3:46:29<4:15:46,  1.43s/it]
 83%|████████▎ | 51199/61904 [3:46:30<4:17:57,  1.45s/it]
 83%|████████▎ | 51200/61904 [3:46:32<4:16:40,  1.44s/it]
                                                         
{'loss': 2.4504, 'learning_rate': 1.1734733566705561e-07, 'epoch': 13.23}

 83%|████████▎ | 51200/61904 [3:46:32<4:16:40,  1.44s/it]
 83%|████████▎ | 51201/61904 [3:46:33<4:27:09,  1.50s/it]
 83%|████████▎ | 51202/61904 [3:46:35<4:27:08,  1.50s/it]
 83%|████████▎ | 51203/61904 [3:46:36<4:15:43,  1.43s/it]
 83%|████████▎ | 51204/61904 [3:46:38<4:06:19,  1.38s/it]
 83%|████████▎ | 51205/61904 [3:46:39<4:05:34,  1.38s/it]
 83%|████████▎ | 51206/61904 [3:46:40<4:03:12,  1.36s/it]
 83%|████████▎ | 51207/61904 [3:46:42<4:03:54,  1.37s/it]
 83%|████████▎ | 51208/61904 [3:46:43<4:08:54,  1.40s/it]
 83%|████████▎ | 51209/61904 [3:46:44<4:07:51,  1.39s/it]
 83%|████████▎ | 51210/61904 [3:46:46<4:09:11,  1.40s/it]
 83%|████████▎ | 51211/61904 [3:46:47<3:59:20,  1.34s/it]
 83%|████████▎ | 51212/61904 [3:46:49<4:03:36,  1.37s/it]
 83%|████████▎ | 51213/61904 [3:46:50<3:57:11,  1.33s/it]
 83%|████████▎ | 51214/61904 [3:46:51<4:03:52,  1.37s/it]
 83%|████████▎ | 51215/61904 [3:46:53<4:08:42,  1.40s/it]
 83%|████████▎ | 51216/61904 [3:46:54<4:10:56,  1.41s/it]
 83%|████████▎ | 51217/61904 [3:46:55<4:04:38,  1.37s/it]
 83%|████████▎ | 51218/61904 [3:46:57<3:59:29,  1.34s/it]
 83%|████████▎ | 51219/61904 [3:46:58<4:01:05,  1.35s/it]
 83%|████████▎ | 51220/61904 [3:47:00<4:06:40,  1.39s/it]
                                                         
{'loss': 2.3622, 'learning_rate': 1.1731492285751328e-07, 'epoch': 13.24}

 83%|████████▎ | 51220/61904 [3:47:00<4:06:40,  1.39s/it]
 83%|████████▎ | 51221/61904 [3:47:01<4:04:22,  1.37s/it]
 83%|████████▎ | 51222/61904 [3:47:02<4:06:16,  1.38s/it]
 83%|████████▎ | 51223/61904 [3:47:04<4:03:53,  1.37s/it]
 83%|████████▎ | 51224/61904 [3:47:05<4:05:22,  1.38s/it]
 83%|████████▎ | 51225/61904 [3:47:06<4:03:04,  1.37s/it]
 83%|████████▎ | 51226/61904 [3:47:08<4:03:38,  1.37s/it]
 83%|████████▎ | 51227/61904 [3:47:09<4:09:22,  1.40s/it]
 83%|████████▎ | 51228/61904 [3:47:11<4:10:20,  1.41s/it]
 83%|████████▎ | 51229/61904 [3:47:12<4:04:23,  1.37s/it]
 83%|████████▎ | 51230/61904 [3:47:13<4:04:28,  1.37s/it]
 83%|████████▎ | 51231/61904 [3:47:15<3:58:57,  1.34s/it]
 83%|████████▎ | 51232/61904 [3:47:16<4:02:43,  1.36s/it]
 83%|████████▎ | 51233/61904 [3:47:18<4:15:30,  1.44s/it]
 83%|████████▎ | 51234/61904 [3:47:19<4:17:18,  1.45s/it]
 83%|████████▎ | 51235/61904 [3:47:20<4:08:00,  1.39s/it]
 83%|████████▎ | 51236/61904 [3:47:22<4:15:36,  1.44s/it]
 83%|████████▎ | 51237/61904 [3:47:23<4:09:40,  1.40s/it]
 83%|████████▎ | 51238/61904 [3:47:25<4:17:21,  1.45s/it]
 83%|████████▎ | 51239/61904 [3:47:26<4:11:29,  1.41s/it]
 83%|████████▎ | 51240/61904 [3:47:27<4:09:55,  1.41s/it]
                                                         
{'loss': 2.4765, 'learning_rate': 1.1728251004797094e-07, 'epoch': 13.24}

 83%|████████▎ | 51240/61904 [3:47:27<4:09:55,  1.41s/it]
 83%|████████▎ | 51241/61904 [3:47:29<4:02:53,  1.37s/it]
 83%|████████▎ | 51242/61904 [3:47:30<4:03:14,  1.37s/it]
 83%|████████▎ | 51243/61904 [3:47:31<4:02:11,  1.36s/it]
 83%|████████▎ | 51244/61904 [3:47:33<4:11:48,  1.42s/it]
 83%|████████▎ | 51245/61904 [3:47:34<4:11:00,  1.41s/it]
 83%|████████▎ | 51246/61904 [3:47:36<4:04:35,  1.38s/it]
 83%|████████▎ | 51247/61904 [3:47:37<4:04:07,  1.37s/it]
 83%|████████▎ | 51248/61904 [3:47:39<4:09:03,  1.40s/it]
 83%|████████▎ | 51249/61904 [3:47:40<4:04:15,  1.38s/it]
 83%|████████▎ | 51250/61904 [3:47:41<4:05:58,  1.39s/it]
 83%|████████▎ | 51251/61904 [3:47:43<4:06:33,  1.39s/it]
 83%|████████▎ | 51252/61904 [3:47:44<4:12:55,  1.42s/it]
 83%|████████▎ | 51253/61904 [3:47:46<4:18:08,  1.45s/it]
 83%|████████▎ | 51254/61904 [3:47:47<4:18:24,  1.46s/it]
 83%|████████▎ | 51255/61904 [3:47:49<4:19:15,  1.46s/it]
 83%|████████▎ | 51256/61904 [3:47:50<4:17:44,  1.45s/it]
 83%|████████▎ | 51257/61904 [3:47:51<4:15:49,  1.44s/it]
 83%|████████▎ | 51258/61904 [3:47:53<4:08:35,  1.40s/it]
 83%|████████▎ | 51259/61904 [3:47:54<4:15:11,  1.44s/it]
 83%|████████▎ | 51260/61904 [3:47:56<4:14:37,  1.44s/it]
                                                         
{'loss': 2.5202, 'learning_rate': 1.1725009723842862e-07, 'epoch': 13.25}

 83%|████████▎ | 51260/61904 [3:47:56<4:14:37,  1.44s/it]
 83%|████████▎ | 51261/61904 [3:47:57<4:07:17,  1.39s/it]
 83%|████████▎ | 51262/61904 [3:47:58<4:03:01,  1.37s/it]
 83%|████████▎ | 51263/61904 [3:48:00<3:59:14,  1.35s/it]
 83%|████████▎ | 51264/61904 [3:48:01<4:00:49,  1.36s/it]
 83%|████████▎ | 51265/61904 [3:48:03<4:10:24,  1.41s/it]
 83%|████████▎ | 51266/61904 [3:48:04<4:02:20,  1.37s/it]
 83%|████████▎ | 51267/61904 [3:48:05<4:06:59,  1.39s/it]
 83%|████████▎ | 51268/61904 [3:48:07<4:08:27,  1.40s/it]
 83%|████████▎ | 51269/61904 [3:48:08<4:01:15,  1.36s/it]
 83%|████████▎ | 51270/61904 [3:48:09<4:02:36,  1.37s/it]
 83%|████████▎ | 51271/61904 [3:48:11<4:03:02,  1.37s/it]
 83%|████████▎ | 51272/61904 [3:48:12<3:57:17,  1.34s/it]
 83%|████████▎ | 51273/61904 [3:48:13<3:58:28,  1.35s/it]
 83%|████████▎ | 51274/61904 [3:48:15<4:08:18,  1.40s/it]
 83%|████████▎ | 51275/61904 [3:48:16<4:00:44,  1.36s/it]
 83%|████████▎ | 51276/61904 [3:48:18<4:04:47,  1.38s/it]
 83%|████████▎ | 51277/61904 [3:48:19<4:11:25,  1.42s/it]
 83%|████████▎ | 51278/61904 [3:48:20<4:05:09,  1.38s/it]
 83%|████████▎ | 51279/61904 [3:48:22<4:13:40,  1.43s/it]
 83%|████████▎ | 51280/61904 [3:48:23<4:07:17,  1.40s/it]
                                                         
{'loss': 2.4383, 'learning_rate': 1.1721768442888628e-07, 'epoch': 13.25}

 83%|████████▎ | 51280/61904 [3:48:23<4:07:17,  1.40s/it]
 83%|████████▎ | 51281/61904 [3:48:25<4:02:12,  1.37s/it]
 83%|████████▎ | 51282/61904 [3:48:26<3:55:51,  1.33s/it]
 83%|████████▎ | 51283/61904 [3:48:27<3:55:55,  1.33s/it]
 83%|████████▎ | 51284/61904 [3:48:28<3:54:36,  1.33s/it]
 83%|████████▎ | 51285/61904 [3:48:30<3:58:29,  1.35s/it]
 83%|████████▎ | 51286/61904 [3:48:31<4:00:17,  1.36s/it]
 83%|████████▎ | 51287/61904 [3:48:33<3:58:05,  1.35s/it]
 83%|████████▎ | 51288/61904 [3:48:34<4:09:41,  1.41s/it]
 83%|████████▎ | 51289/61904 [3:48:35<4:04:42,  1.38s/it]
 83%|████████▎ | 51290/61904 [3:48:37<4:03:55,  1.38s/it]
 83%|████████▎ | 51291/61904 [3:48:38<4:00:36,  1.36s/it]
 83%|████████▎ | 51292/61904 [3:48:39<3:58:08,  1.35s/it]
 83%|████████▎ | 51293/61904 [3:48:41<4:02:57,  1.37s/it]
 83%|████████▎ | 51294/61904 [3:48:42<4:08:06,  1.40s/it]
 83%|████████▎ | 51295/61904 [3:48:44<4:02:43,  1.37s/it]
 83%|████████▎ | 51296/61904 [3:48:45<3:57:02,  1.34s/it]
 83%|████████▎ | 51297/61904 [3:48:46<3:58:31,  1.35s/it]
 83%|████████▎ | 51298/61904 [3:48:48<4:05:30,  1.39s/it]
 83%|████████▎ | 51299/61904 [3:48:49<4:08:07,  1.40s/it]
 83%|████████▎ | 51300/61904 [3:48:51<4:06:04,  1.39s/it]
                                                         
{'loss': 2.4267, 'learning_rate': 1.1718527161934396e-07, 'epoch': 13.26}

 83%|████████▎ | 51300/61904 [3:48:51<4:06:04,  1.39s/it]
 83%|████████▎ | 51301/61904 [3:48:52<4:04:14,  1.38s/it]
 83%|████████▎ | 51302/61904 [3:48:53<4:09:05,  1.41s/it]
 83%|████████▎ | 51303/61904 [3:48:55<4:15:56,  1.45s/it]
 83%|████████▎ | 51304/61904 [3:48:56<4:09:36,  1.41s/it]
 83%|████████▎ | 51305/61904 [3:48:58<4:04:30,  1.38s/it]
 83%|████████▎ | 51306/61904 [3:48:59<4:12:23,  1.43s/it]
 83%|████████▎ | 51307/61904 [3:49:00<4:06:21,  1.39s/it]
 83%|████████▎ | 51308/61904 [3:49:02<4:03:55,  1.38s/it]
 83%|████████▎ | 51309/61904 [3:49:03<4:15:46,  1.45s/it]
 83%|████████▎ | 51310/61904 [3:49:05<4:09:23,  1.41s/it]
 83%|████████▎ | 51311/61904 [3:49:06<4:16:46,  1.45s/it]
 83%|████████▎ | 51312/61904 [3:49:08<4:06:59,  1.40s/it]
 83%|████████▎ | 51313/61904 [3:49:09<4:05:04,  1.39s/it]
 83%|████████▎ | 51314/61904 [3:49:10<3:59:50,  1.36s/it]
 83%|████████▎ | 51315/61904 [3:49:12<4:00:42,  1.36s/it]
 83%|████████▎ | 51316/61904 [3:49:13<4:00:09,  1.36s/it]
 83%|████████▎ | 51317/61904 [3:49:14<3:59:13,  1.36s/it]
 83%|████████▎ | 51318/61904 [3:49:16<3:58:42,  1.35s/it]
 83%|████████▎ | 51319/61904 [3:49:17<3:56:27,  1.34s/it]
 83%|████████▎ | 51320/61904 [3:49:18<4:09:05,  1.41s/it]
                                                         
{'loss': 2.4442, 'learning_rate': 1.1715285880980162e-07, 'epoch': 13.26}

 83%|████████▎ | 51320/61904 [3:49:18<4:09:05,  1.41s/it]
 83%|████████▎ | 51321/61904 [3:49:20<4:05:27,  1.39s/it]
 83%|████████▎ | 51322/61904 [3:49:21<4:11:22,  1.43s/it]
 83%|████████▎ | 51323/61904 [3:49:23<4:09:19,  1.41s/it]
 83%|████████▎ | 51324/61904 [3:49:24<4:07:22,  1.40s/it]
 83%|████████▎ | 51325/61904 [3:49:25<3:56:41,  1.34s/it]
 83%|████████▎ | 51326/61904 [3:49:27<4:01:19,  1.37s/it]
 83%|████████▎ | 51327/61904 [3:49:28<4:03:19,  1.38s/it]
 83%|████████▎ | 51328/61904 [3:49:30<4:07:38,  1.40s/it]
 83%|████████▎ | 51329/61904 [3:49:31<4:03:05,  1.38s/it]
 83%|████████▎ | 51330/61904 [3:49:32<4:11:51,  1.43s/it]
 83%|████████▎ | 51331/61904 [3:49:34<4:05:59,  1.40s/it]
 83%|████████▎ | 51332/61904 [3:49:35<4:05:34,  1.39s/it]
 83%|████████▎ | 51333/61904 [3:49:37<4:10:55,  1.42s/it]
 83%|████████▎ | 51334/61904 [3:49:38<4:16:32,  1.46s/it]
 83%|████████▎ | 51335/61904 [3:49:40<4:13:30,  1.44s/it]
 83%|████████▎ | 51336/61904 [3:49:41<4:10:54,  1.42s/it]
 83%|████████▎ | 51337/61904 [3:49:42<4:02:47,  1.38s/it]
 83%|████████▎ | 51338/61904 [3:49:44<4:08:48,  1.41s/it]
 83%|████████▎ | 51339/61904 [3:49:45<4:03:18,  1.38s/it]
 83%|████████▎ | 51340/61904 [3:49:47<4:08:46,  1.41s/it]
                                                         
{'loss': 2.4723, 'learning_rate': 1.171204460002593e-07, 'epoch': 13.27}

 83%|████████▎ | 51340/61904 [3:49:47<4:08:46,  1.41s/it]
 83%|████████▎ | 51341/61904 [3:49:48<4:06:13,  1.40s/it]
 83%|████████▎ | 51342/61904 [3:49:49<4:06:56,  1.40s/it]
 83%|████████▎ | 51343/61904 [3:49:51<4:04:01,  1.39s/it]
 83%|████████▎ | 51344/61904 [3:49:52<4:02:40,  1.38s/it]
 83%|████████▎ | 51345/61904 [3:49:53<4:02:31,  1.38s/it]
 83%|████████▎ | 51346/61904 [3:49:55<3:58:41,  1.36s/it]
 83%|████████▎ | 51347/61904 [3:49:56<4:05:04,  1.39s/it]
 83%|████████▎ | 51348/61904 [3:49:57<3:57:07,  1.35s/it]
 83%|████████▎ | 51349/61904 [3:49:59<4:05:26,  1.40s/it]
 83%|████████▎ | 51350/61904 [3:50:00<4:01:42,  1.37s/it]
 83%|████████▎ | 51351/61904 [3:50:02<4:02:11,  1.38s/it]
 83%|████████▎ | 51352/61904 [3:50:03<4:07:56,  1.41s/it]
 83%|████████▎ | 51353/61904 [3:50:04<4:00:30,  1.37s/it]
 83%|████████▎ | 51354/61904 [3:50:06<4:00:18,  1.37s/it]
 83%|████████▎ | 51355/61904 [3:50:07<3:59:10,  1.36s/it]
 83%|████████▎ | 51356/61904 [3:50:08<3:55:02,  1.34s/it]
 83%|████████▎ | 51357/61904 [3:50:10<4:09:41,  1.42s/it]
 83%|████████▎ | 51358/61904 [3:50:11<4:03:02,  1.38s/it]
 83%|████████▎ | 51359/61904 [3:50:13<4:03:15,  1.38s/it]
 83%|████████▎ | 51360/61904 [3:50:14<4:08:27,  1.41s/it]
                                                         
{'loss': 2.4552, 'learning_rate': 1.1708803319071696e-07, 'epoch': 13.27}

 83%|████████▎ | 51360/61904 [3:50:14<4:08:27,  1.41s/it]
 83%|████████▎ | 51361/61904 [3:50:16<4:09:40,  1.42s/it]
 83%|████████▎ | 51362/61904 [3:50:17<4:02:26,  1.38s/it]
 83%|████████▎ | 51363/61904 [3:50:18<4:04:05,  1.39s/it]
 83%|████████▎ | 51364/61904 [3:50:20<4:00:53,  1.37s/it]
 83%|████████▎ | 51365/61904 [3:50:21<4:03:08,  1.38s/it]
 83%|████████▎ | 51366/61904 [3:50:22<4:01:39,  1.38s/it]
 83%|████████▎ | 51367/61904 [3:50:24<4:04:54,  1.39s/it]
 83%|████████▎ | 51368/61904 [3:50:25<3:58:49,  1.36s/it]
 83%|████████▎ | 51369/61904 [3:50:26<3:56:06,  1.34s/it]
 83%|████████▎ | 51370/61904 [3:50:28<3:52:36,  1.32s/it]
 83%|████████▎ | 51371/61904 [3:50:29<4:01:48,  1.38s/it]
 83%|████████▎ | 51372/61904 [3:50:31<4:00:15,  1.37s/it]
 83%|████████▎ | 51373/61904 [3:50:32<3:56:16,  1.35s/it]
 83%|████████▎ | 51374/61904 [3:50:33<4:04:00,  1.39s/it]
 83%|████████▎ | 51375/61904 [3:50:35<4:04:59,  1.40s/it]
 83%|████████▎ | 51376/61904 [3:50:36<3:58:39,  1.36s/it]
 83%|████████▎ | 51377/61904 [3:50:37<3:55:56,  1.34s/it]
 83%|████████▎ | 51378/61904 [3:50:39<3:51:47,  1.32s/it]
 83%|████████▎ | 51379/61904 [3:50:40<4:01:33,  1.38s/it]
 83%|████████▎ | 51380/61904 [3:50:42<4:05:28,  1.40s/it]
                                                         
{'loss': 2.4261, 'learning_rate': 1.1705562038117463e-07, 'epoch': 13.28}

 83%|████████▎ | 51380/61904 [3:50:42<4:05:28,  1.40s/it]
 83%|████████▎ | 51381/61904 [3:50:43<4:05:19,  1.40s/it]
 83%|████████▎ | 51382/61904 [3:50:44<4:11:21,  1.43s/it]
 83%|████████▎ | 51383/61904 [3:50:46<4:09:23,  1.42s/it]
 83%|████████▎ | 51384/61904 [3:50:47<4:06:06,  1.40s/it]
 83%|████████▎ | 51385/61904 [3:50:49<4:06:44,  1.41s/it]
 83%|████████▎ | 51386/61904 [3:50:50<4:02:40,  1.38s/it]
 83%|████████▎ | 51387/61904 [3:50:51<4:00:02,  1.37s/it]
 83%|████████▎ | 51388/61904 [3:50:53<4:03:40,  1.39s/it]
 83%|████████▎ | 51389/61904 [3:50:54<4:04:44,  1.40s/it]
 83%|████████▎ | 51390/61904 [3:50:55<4:00:13,  1.37s/it]
 83%|████████▎ | 51391/61904 [3:50:57<4:02:46,  1.39s/it]
 83%|████████▎ | 51392/61904 [3:50:58<3:58:24,  1.36s/it]
 83%|████████▎ | 51393/61904 [3:51:00<3:59:20,  1.37s/it]
 83%|████████▎ | 51394/61904 [3:51:01<4:02:10,  1.38s/it]
 83%|████████▎ | 51395/61904 [3:51:02<4:03:37,  1.39s/it]
 83%|████████▎ | 51396/61904 [3:51:04<4:06:05,  1.41s/it]
 83%|████████▎ | 51397/61904 [3:51:05<4:13:55,  1.45s/it]
 83%|████████▎ | 51398/61904 [3:51:07<4:11:55,  1.44s/it]
 83%|████████▎ | 51399/61904 [3:51:08<4:09:02,  1.42s/it]
 83%|████████▎ | 51400/61904 [3:51:09<4:02:16,  1.38s/it]
                                                         
{'loss': 2.3728, 'learning_rate': 1.1702320757163229e-07, 'epoch': 13.28}

 83%|████████▎ | 51400/61904 [3:51:09<4:02:16,  1.38s/it]
 83%|████████▎ | 51401/61904 [3:51:11<4:05:58,  1.41s/it]
 83%|████████▎ | 51402/61904 [3:51:12<4:01:15,  1.38s/it]
 83%|████████▎ | 51403/61904 [3:51:14<4:26:48,  1.52s/it]
 83%|████████▎ | 51404/61904 [3:51:15<4:18:29,  1.48s/it]
 83%|████████▎ | 51405/61904 [3:51:17<4:11:55,  1.44s/it]
 83%|████████▎ | 51406/61904 [3:51:18<4:09:52,  1.43s/it]
 83%|████████▎ | 51407/61904 [3:51:20<4:03:15,  1.39s/it]
 83%|████████▎ | 51408/61904 [3:51:21<4:06:51,  1.41s/it]
 83%|████████▎ | 51409/61904 [3:51:23<4:11:39,  1.44s/it]
 83%|████████▎ | 51410/61904 [3:51:24<4:05:49,  1.41s/it]
 83%|████████▎ | 51411/61904 [3:51:25<4:06:35,  1.41s/it]
 83%|████████▎ | 51412/61904 [3:51:27<4:06:21,  1.41s/it]
 83%|████████▎ | 51413/61904 [3:51:28<4:02:18,  1.39s/it]
 83%|████████▎ | 51414/61904 [3:51:29<4:05:36,  1.40s/it]
 83%|████████▎ | 51415/61904 [3:51:31<4:02:58,  1.39s/it]
 83%|████████▎ | 51416/61904 [3:51:32<3:58:23,  1.36s/it]
 83%|████████▎ | 51417/61904 [3:51:34<4:09:07,  1.43s/it]
 83%|████████▎ | 51418/61904 [3:51:35<4:16:14,  1.47s/it]
 83%|████████▎ | 51419/61904 [3:51:37<4:15:19,  1.46s/it]
 83%|████████▎ | 51420/61904 [3:51:38<4:26:12,  1.52s/it]
                                                         
{'loss': 2.4434, 'learning_rate': 1.1699079476208997e-07, 'epoch': 13.29}

 83%|████████▎ | 51420/61904 [3:51:38<4:26:12,  1.52s/it]
 83%|████████▎ | 51421/61904 [3:51:40<4:18:57,  1.48s/it]
 83%|████████▎ | 51422/61904 [3:51:41<4:12:13,  1.44s/it]
 83%|████████▎ | 51423/61904 [3:51:43<4:11:58,  1.44s/it]
 83%|████████▎ | 51424/61904 [3:51:44<4:13:55,  1.45s/it]
 83%|████████▎ | 51425/61904 [3:51:46<4:22:35,  1.50s/it]
 83%|████████▎ | 51426/61904 [3:51:47<4:15:32,  1.46s/it]
 83%|████████▎ | 51427/61904 [3:51:48<4:13:15,  1.45s/it]
 83%|████████▎ | 51428/61904 [3:51:50<4:09:51,  1.43s/it]
 83%|████████▎ | 51429/61904 [3:51:51<4:07:38,  1.42s/it]
 83%|████████▎ | 51430/61904 [3:51:53<4:05:29,  1.41s/it]
 83%|████████▎ | 51431/61904 [3:51:54<4:03:02,  1.39s/it]
 83%|████████▎ | 51432/61904 [3:51:55<3:58:56,  1.37s/it]
 83%|████████▎ | 51433/61904 [3:51:57<3:56:03,  1.35s/it]
 83%|████████▎ | 51434/61904 [3:51:58<3:57:53,  1.36s/it]
 83%|████████▎ | 51435/61904 [3:51:59<3:57:43,  1.36s/it]
 83%|████████▎ | 51436/61904 [3:52:01<3:57:45,  1.36s/it]
 83%|████████▎ | 51437/61904 [3:52:02<3:55:22,  1.35s/it]
 83%|████████▎ | 51438/61904 [3:52:03<3:54:51,  1.35s/it]
 83%|████████▎ | 51439/61904 [3:52:05<3:51:58,  1.33s/it]
 83%|████████▎ | 51440/61904 [3:52:06<3:53:02,  1.34s/it]
                                                         
{'loss': 2.433, 'learning_rate': 1.1695838195254763e-07, 'epoch': 13.3}

 83%|████████▎ | 51440/61904 [3:52:06<3:53:02,  1.34s/it]
 83%|████████▎ | 51441/61904 [3:52:07<3:56:17,  1.36s/it]
 83%|████████▎ | 51442/61904 [3:52:09<3:55:58,  1.35s/it]
 83%|████████▎ | 51443/61904 [3:52:10<4:01:35,  1.39s/it]
 83%|████████▎ | 51444/61904 [3:52:12<4:11:15,  1.44s/it]
 83%|████████▎ | 51445/61904 [3:52:13<3:59:53,  1.38s/it]
 83%|████████▎ | 51446/61904 [3:52:14<3:58:47,  1.37s/it]
 83%|████████▎ | 51447/61904 [3:52:16<3:57:43,  1.36s/it]
 83%|████████▎ | 51448/61904 [3:52:17<4:04:14,  1.40s/it]
 83%|████████▎ | 51449/61904 [3:52:19<4:04:04,  1.40s/it]
 83%|████████▎ | 51450/61904 [3:52:20<3:58:52,  1.37s/it]
 83%|████████▎ | 51451/61904 [3:52:21<4:03:33,  1.40s/it]
 83%|████████▎ | 51452/61904 [3:52:23<3:59:51,  1.38s/it]
 83%|████████▎ | 51453/61904 [3:52:24<4:06:58,  1.42s/it]
 83%|████████▎ | 51454/61904 [3:52:26<4:03:49,  1.40s/it]
 83%|████████▎ | 51455/61904 [3:52:27<4:03:32,  1.40s/it]
 83%|████████▎ | 51456/61904 [3:52:28<3:59:00,  1.37s/it]
 83%|████████▎ | 51457/61904 [3:52:30<4:04:14,  1.40s/it]
 83%|████████▎ | 51458/61904 [3:52:31<4:02:32,  1.39s/it]
 83%|████████▎ | 51459/61904 [3:52:32<3:58:56,  1.37s/it]
 83%|████████▎ | 51460/61904 [3:52:34<4:01:59,  1.39s/it]
                                                         
{'loss': 2.4091, 'learning_rate': 1.169259691430053e-07, 'epoch': 13.3}

 83%|████████▎ | 51460/61904 [3:52:34<4:01:59,  1.39s/it]
 83%|████████▎ | 51461/61904 [3:52:35<3:57:36,  1.37s/it]
 83%|████████▎ | 51462/61904 [3:52:37<4:07:16,  1.42s/it]
 83%|████████▎ | 51463/61904 [3:52:38<4:05:14,  1.41s/it]
 83%|████████▎ | 51464/61904 [3:52:39<3:58:35,  1.37s/it]
 83%|████████▎ | 51465/61904 [3:52:41<4:02:12,  1.39s/it]
 83%|████████▎ | 51466/61904 [3:52:42<4:02:08,  1.39s/it]
 83%|████████▎ | 51467/61904 [3:52:44<4:03:50,  1.40s/it]
 83%|████████▎ | 51468/61904 [3:52:45<4:01:13,  1.39s/it]
 83%|████████▎ | 51469/61904 [3:52:46<4:05:56,  1.41s/it]
 83%|████████▎ | 51470/61904 [3:52:48<4:04:07,  1.40s/it]
 83%|████████▎ | 51471/61904 [3:52:49<4:12:20,  1.45s/it]
 83%|████████▎ | 51472/61904 [3:52:51<4:01:14,  1.39s/it]
 83%|████████▎ | 51473/61904 [3:52:52<4:03:30,  1.40s/it]
 83%|████████▎ | 51474/61904 [3:52:53<3:56:12,  1.36s/it]
 83%|████████▎ | 51475/61904 [3:52:55<4:02:13,  1.39s/it]
 83%|████████▎ | 51476/61904 [3:52:56<3:54:24,  1.35s/it]
 83%|████████▎ | 51477/61904 [3:52:58<4:01:43,  1.39s/it]
 83%|████████▎ | 51478/61904 [3:52:59<4:01:17,  1.39s/it]
 83%|████████▎ | 51479/61904 [3:53:00<4:04:55,  1.41s/it]
 83%|████████▎ | 51480/61904 [3:53:02<4:01:11,  1.39s/it]
                                                         
{'loss': 2.418, 'learning_rate': 1.1689355633346298e-07, 'epoch': 13.31}

 83%|████████▎ | 51480/61904 [3:53:02<4:01:11,  1.39s/it]
 83%|████████▎ | 51481/61904 [3:53:03<3:56:34,  1.36s/it]
 83%|████████▎ | 51482/61904 [3:53:04<3:59:27,  1.38s/it]
 83%|████████▎ | 51483/61904 [3:53:06<4:03:06,  1.40s/it]
 83%|████████▎ | 51484/61904 [3:53:07<3:58:54,  1.38s/it]
 83%|████████▎ | 51485/61904 [3:53:08<3:53:06,  1.34s/it]
 83%|████████▎ | 51486/61904 [3:53:10<3:51:41,  1.33s/it]
 83%|████████▎ | 51487/61904 [3:53:11<3:48:28,  1.32s/it]
 83%|████████▎ | 51488/61904 [3:53:12<3:55:01,  1.35s/it]
 83%|████████▎ | 51489/61904 [3:53:14<3:50:19,  1.33s/it]
 83%|████████▎ | 51490/61904 [3:53:15<3:51:25,  1.33s/it]
 83%|████████▎ | 51491/61904 [3:53:16<3:52:37,  1.34s/it]
 83%|████████▎ | 51492/61904 [3:53:18<3:55:24,  1.36s/it]
 83%|████████▎ | 51493/61904 [3:53:19<3:58:17,  1.37s/it]
 83%|████████▎ | 51494/61904 [3:53:21<4:07:31,  1.43s/it]
 83%|████████▎ | 51495/61904 [3:53:22<4:07:45,  1.43s/it]
 83%|████████▎ | 51496/61904 [3:53:24<4:15:22,  1.47s/it]
 83%|████████▎ | 51497/61904 [3:53:25<4:14:09,  1.47s/it]
 83%|████████▎ | 51498/61904 [3:53:27<4:08:28,  1.43s/it]
 83%|████████▎ | 51499/61904 [3:53:28<4:12:19,  1.46s/it]
 83%|████████▎ | 51500/61904 [3:53:30<4:12:23,  1.46s/it]
                                                         
{'loss': 2.4226, 'learning_rate': 1.1686114352392064e-07, 'epoch': 13.31}

 83%|████████▎ | 51500/61904 [3:53:30<4:12:23,  1.46s/it]
 83%|████████▎ | 51501/61904 [3:53:31<4:09:58,  1.44s/it]
 83%|████████▎ | 51502/61904 [3:53:32<4:01:24,  1.39s/it]
 83%|████████▎ | 51503/61904 [3:53:34<3:59:23,  1.38s/it]
 83%|████████▎ | 51504/61904 [3:53:35<3:54:49,  1.35s/it]
 83%|████████▎ | 51505/61904 [3:53:36<3:55:23,  1.36s/it]
 83%|████████▎ | 51506/61904 [3:53:38<4:01:02,  1.39s/it]
 83%|████████▎ | 51507/61904 [3:53:39<3:55:05,  1.36s/it]
 83%|████████▎ | 51508/61904 [3:53:40<3:57:08,  1.37s/it]
 83%|████████▎ | 51509/61904 [3:53:42<4:05:42,  1.42s/it]
 83%|████████▎ | 51510/61904 [3:53:43<4:00:17,  1.39s/it]
 83%|████████▎ | 51511/61904 [3:53:45<3:57:20,  1.37s/it]
 83%|████████▎ | 51512/61904 [3:53:46<4:00:34,  1.39s/it]
 83%|████████▎ | 51513/61904 [3:53:48<4:06:00,  1.42s/it]
 83%|████████▎ | 51514/61904 [3:53:49<4:04:37,  1.41s/it]
 83%|████████▎ | 51515/61904 [3:53:50<4:09:20,  1.44s/it]
 83%|████████▎ | 51516/61904 [3:53:52<4:02:56,  1.40s/it]
 83%|████████▎ | 51517/61904 [3:53:53<4:14:42,  1.47s/it]
 83%|████████▎ | 51518/61904 [3:53:55<4:09:39,  1.44s/it]
 83%|████████▎ | 51519/61904 [3:53:56<4:08:40,  1.44s/it]
 83%|████████▎ | 51520/61904 [3:53:58<4:20:22,  1.50s/it]
                                                         
{'loss': 2.4603, 'learning_rate': 1.168287307143783e-07, 'epoch': 13.32}

 83%|████████▎ | 51520/61904 [3:53:58<4:20:22,  1.50s/it]
 83%|████████▎ | 51521/61904 [3:53:59<4:13:59,  1.47s/it]
 83%|████████▎ | 51522/61904 [3:54:01<4:03:53,  1.41s/it]
 83%|████████▎ | 51523/61904 [3:54:02<3:56:51,  1.37s/it]
 83%|████████▎ | 51524/61904 [3:54:03<3:54:05,  1.35s/it]
 83%|████████▎ | 51525/61904 [3:54:05<3:58:44,  1.38s/it]
 83%|████████▎ | 51526/61904 [3:54:06<4:06:03,  1.42s/it]
 83%|████████▎ | 51527/61904 [3:54:08<4:11:41,  1.46s/it]
 83%|████████▎ | 51528/61904 [3:54:09<4:09:58,  1.45s/it]
 83%|████████▎ | 51529/61904 [3:54:10<4:06:01,  1.42s/it]
 83%|████████▎ | 51530/61904 [3:54:12<3:54:55,  1.36s/it]
 83%|████████▎ | 51531/61904 [3:54:13<3:55:01,  1.36s/it]
 83%|████████▎ | 51532/61904 [3:54:14<3:58:42,  1.38s/it]
 83%|████████▎ | 51533/61904 [3:54:16<3:53:54,  1.35s/it]
 83%|████████▎ | 51534/61904 [3:54:17<3:51:55,  1.34s/it]
 83%|████████▎ | 51535/61904 [3:54:18<3:48:40,  1.32s/it]
 83%|████████▎ | 51536/61904 [3:54:20<3:46:30,  1.31s/it]
 83%|████████▎ | 51537/61904 [3:54:21<3:46:13,  1.31s/it]
 83%|████████▎ | 51538/61904 [3:54:22<3:53:44,  1.35s/it]
 83%|████████▎ | 51539/61904 [3:54:24<3:54:25,  1.36s/it]
 83%|████████▎ | 51540/61904 [3:54:25<3:58:23,  1.38s/it]
                                                         
{'loss': 2.4939, 'learning_rate': 1.1679631790483598e-07, 'epoch': 13.32}

 83%|████████▎ | 51540/61904 [3:54:25<3:58:23,  1.38s/it]
 83%|████████▎ | 51541/61904 [3:54:26<3:53:32,  1.35s/it]
 83%|████████▎ | 51542/61904 [3:54:28<4:05:13,  1.42s/it]
 83%|████████▎ | 51543/61904 [3:54:29<4:02:28,  1.40s/it]
 83%|████████▎ | 51544/61904 [3:54:31<4:06:35,  1.43s/it]
 83%|████████▎ | 51545/61904 [3:54:32<4:00:33,  1.39s/it]
 83%|████████▎ | 51546/61904 [3:54:34<4:00:59,  1.40s/it]
 83%|████████▎ | 51547/61904 [3:54:35<4:09:52,  1.45s/it]
 83%|████████▎ | 51548/61904 [3:54:36<4:06:02,  1.43s/it]
 83%|████████▎ | 51549/61904 [3:54:38<4:11:30,  1.46s/it]
 83%|████████▎ | 51550/61904 [3:54:39<4:06:13,  1.43s/it]
 83%|████████▎ | 51551/61904 [3:54:41<4:09:07,  1.44s/it]
 83%|████████▎ | 51552/61904 [3:54:42<3:59:29,  1.39s/it]
 83%|████████▎ | 51553/61904 [3:54:44<3:59:40,  1.39s/it]
 83%|████████▎ | 51554/61904 [3:54:45<3:57:03,  1.37s/it]
 83%|████████▎ | 51555/61904 [3:54:46<4:02:31,  1.41s/it]
 83%|████████▎ | 51556/61904 [3:54:48<3:58:34,  1.38s/it]
 83%|████████▎ | 51557/61904 [3:54:49<4:01:52,  1.40s/it]
 83%|████████▎ | 51558/61904 [3:54:50<4:00:45,  1.40s/it]
 83%|████████▎ | 51559/61904 [3:54:52<3:52:01,  1.35s/it]
 83%|████████▎ | 51560/61904 [3:54:53<3:52:50,  1.35s/it]
                                                         
{'loss': 2.444, 'learning_rate': 1.1676390509529365e-07, 'epoch': 13.33}

 83%|████████▎ | 51560/61904 [3:54:53<3:52:50,  1.35s/it]
 83%|████████▎ | 51561/61904 [3:54:54<3:51:12,  1.34s/it]
 83%|████████▎ | 51562/61904 [3:54:56<3:44:46,  1.30s/it]
 83%|████████▎ | 51563/61904 [3:54:57<4:06:03,  1.43s/it]
 83%|████████▎ | 51564/61904 [3:54:59<4:00:40,  1.40s/it]
 83%|████████▎ | 51565/61904 [3:55:00<3:58:07,  1.38s/it]
 83%|████████▎ | 51566/61904 [3:55:01<4:00:52,  1.40s/it]
 83%|████████▎ | 51567/61904 [3:55:03<3:58:33,  1.38s/it]
 83%|████████▎ | 51568/61904 [3:55:04<4:04:04,  1.42s/it]
 83%|████████▎ | 51569/61904 [3:55:06<4:05:22,  1.42s/it]
 83%|████████▎ | 51570/61904 [3:55:07<4:14:34,  1.48s/it]
 83%|████████▎ | 51571/61904 [3:55:09<4:03:55,  1.42s/it]
 83%|████████▎ | 51572/61904 [3:55:10<4:06:43,  1.43s/it]
 83%|████████▎ | 51573/61904 [3:55:11<4:04:51,  1.42s/it]
 83%|████████▎ | 51574/61904 [3:55:13<3:58:52,  1.39s/it]
 83%|████████▎ | 51575/61904 [3:55:14<4:07:26,  1.44s/it]
 83%|████████▎ | 51576/61904 [3:55:16<4:07:34,  1.44s/it]
 83%|████████▎ | 51577/61904 [3:55:17<3:57:00,  1.38s/it]
 83%|████████▎ | 51578/61904 [3:55:18<3:53:06,  1.35s/it]
 83%|████████▎ | 51579/61904 [3:55:20<3:52:30,  1.35s/it]
 83%|████████▎ | 51580/61904 [3:55:21<3:58:29,  1.39s/it]
                                                         
{'loss': 2.5078, 'learning_rate': 1.1673149228575132e-07, 'epoch': 13.33}

 83%|████████▎ | 51580/61904 [3:55:21<3:58:29,  1.39s/it]
 83%|████████▎ | 51581/61904 [3:55:22<3:58:33,  1.39s/it]
 83%|████████▎ | 51582/61904 [3:55:24<3:56:14,  1.37s/it]
 83%|████████▎ | 51583/61904 [3:55:25<3:56:38,  1.38s/it]
 83%|████████▎ | 51584/61904 [3:55:27<4:01:10,  1.40s/it]
 83%|████████▎ | 51585/61904 [3:55:28<3:55:01,  1.37s/it]
 83%|████████▎ | 51586/61904 [3:55:29<4:02:12,  1.41s/it]
 83%|████████▎ | 51587/61904 [3:55:31<3:55:00,  1.37s/it]
 83%|████████▎ | 51588/61904 [3:55:32<3:52:21,  1.35s/it]
 83%|████████▎ | 51589/61904 [3:55:33<3:55:20,  1.37s/it]
 83%|████████▎ | 51590/61904 [3:55:35<3:57:56,  1.38s/it]
 83%|████████▎ | 51591/61904 [3:55:36<3:59:05,  1.39s/it]
 83%|████████▎ | 51592/61904 [3:55:38<3:58:07,  1.39s/it]
 83%|████████▎ | 51593/61904 [3:55:39<3:56:19,  1.38s/it]
 83%|████████▎ | 51594/61904 [3:55:40<3:56:19,  1.38s/it]
 83%|████████▎ | 51595/61904 [3:55:42<4:02:38,  1.41s/it]
 83%|████████▎ | 51596/61904 [3:55:43<4:05:37,  1.43s/it]
 83%|████████▎ | 51597/61904 [3:55:45<4:10:20,  1.46s/it]
 83%|████████▎ | 51598/61904 [3:55:46<4:03:28,  1.42s/it]
 83%|████████▎ | 51599/61904 [3:55:47<3:56:17,  1.38s/it]
 83%|████████▎ | 51600/61904 [3:55:49<3:56:40,  1.38s/it]
                                                         
{'loss': 2.5158, 'learning_rate': 1.1669907947620898e-07, 'epoch': 13.34}

 83%|████████▎ | 51600/61904 [3:55:49<3:56:40,  1.38s/it]
 83%|████████▎ | 51601/61904 [3:55:50<3:49:18,  1.34s/it]
 83%|████████▎ | 51602/61904 [3:55:51<3:46:05,  1.32s/it]
 83%|████████▎ | 51603/61904 [3:55:53<3:41:00,  1.29s/it]
 83%|████████▎ | 51604/61904 [3:55:54<3:43:28,  1.30s/it]
 83%|████████▎ | 51605/61904 [3:55:55<3:41:47,  1.29s/it]
 83%|████████▎ | 51606/61904 [3:55:57<3:50:04,  1.34s/it]
 83%|████████▎ | 51607/61904 [3:55:58<3:53:06,  1.36s/it]
 83%|████████▎ | 51608/61904 [3:56:00<4:03:36,  1.42s/it]
 83%|████████▎ | 51609/61904 [3:56:01<4:09:50,  1.46s/it]
 83%|████████▎ | 51610/61904 [3:56:03<4:03:58,  1.42s/it]
 83%|████████▎ | 51611/61904 [3:56:04<4:05:10,  1.43s/it]
 83%|████████▎ | 51612/61904 [3:56:05<4:04:24,  1.42s/it]
 83%|████████▎ | 51613/61904 [3:56:07<3:59:22,  1.40s/it]
 83%|████████▎ | 51614/61904 [3:56:08<4:06:47,  1.44s/it]
 83%|████████▎ | 51615/61904 [3:56:10<4:05:00,  1.43s/it]
 83%|████████▎ | 51616/61904 [3:56:11<4:05:49,  1.43s/it]
 83%|████████▎ | 51617/61904 [3:56:12<3:56:46,  1.38s/it]
 83%|████████▎ | 51618/61904 [3:56:14<3:55:24,  1.37s/it]
 83%|████████▎ | 51619/61904 [3:56:15<4:05:27,  1.43s/it]
 83%|████████▎ | 51620/61904 [3:56:17<4:04:32,  1.43s/it]
                                                         
{'loss': 2.5183, 'learning_rate': 1.1666666666666665e-07, 'epoch': 13.34}

 83%|████████▎ | 51620/61904 [3:56:17<4:04:32,  1.43s/it]
 83%|████████▎ | 51621/61904 [3:56:18<4:03:04,  1.42s/it]
 83%|████████▎ | 51622/61904 [3:56:19<3:59:18,  1.40s/it]
 83%|████████▎ | 51623/61904 [3:56:21<3:56:18,  1.38s/it]
 83%|████████▎ | 51624/61904 [3:56:22<4:05:07,  1.43s/it]
 83%|████████▎ | 51625/61904 [3:56:24<4:03:37,  1.42s/it]
 83%|████████▎ | 51626/61904 [3:56:25<3:58:59,  1.40s/it]
 83%|████████▎ | 51627/61904 [3:56:26<3:55:30,  1.37s/it]
 83%|████████▎ | 51628/61904 [3:56:28<3:57:42,  1.39s/it]
 83%|████████▎ | 51629/61904 [3:56:29<3:55:06,  1.37s/it]
 83%|████████▎ | 51630/61904 [3:56:31<3:57:52,  1.39s/it]
 83%|████████▎ | 51631/61904 [3:56:32<4:02:36,  1.42s/it]
 83%|████████▎ | 51632/61904 [3:56:34<4:15:31,  1.49s/it]
 83%|████████▎ | 51633/61904 [3:56:35<4:07:42,  1.45s/it]
 83%|████████▎ | 51634/61904 [3:56:36<4:03:20,  1.42s/it]
 83%|████████▎ | 51635/61904 [3:56:38<3:59:04,  1.40s/it]
 83%|████████▎ | 51636/61904 [3:56:39<4:04:25,  1.43s/it]
 83%|████████▎ | 51637/61904 [3:56:41<4:06:53,  1.44s/it]
 83%|████████▎ | 51638/61904 [3:56:42<4:04:33,  1.43s/it]
 83%|████████▎ | 51639/61904 [3:56:44<4:05:03,  1.43s/it]
 83%|████████▎ | 51640/61904 [3:56:45<4:02:14,  1.42s/it]
                                                         
{'loss': 2.3932, 'learning_rate': 1.1663425385712433e-07, 'epoch': 13.35}

 83%|████████▎ | 51640/61904 [3:56:45<4:02:14,  1.42s/it]
 83%|████████▎ | 51641/61904 [3:56:46<3:56:53,  1.38s/it]
 83%|████████▎ | 51642/61904 [3:56:48<3:50:54,  1.35s/it]
 83%|████████▎ | 51643/61904 [3:56:49<3:50:52,  1.35s/it]
 83%|████████▎ | 51644/61904 [3:56:50<3:48:09,  1.33s/it]
 83%|████████▎ | 51645/61904 [3:56:51<3:46:27,  1.32s/it]
 83%|████████▎ | 51646/61904 [3:56:53<3:41:22,  1.29s/it]
 83%|████████▎ | 51647/61904 [3:56:54<3:46:25,  1.32s/it]
 83%|████████▎ | 51648/61904 [3:56:56<3:51:19,  1.35s/it]
 83%|████████▎ | 51649/61904 [3:56:57<3:51:42,  1.36s/it]
 83%|████████▎ | 51650/61904 [3:56:58<3:53:47,  1.37s/it]
 83%|████████▎ | 51651/61904 [3:57:00<4:01:40,  1.41s/it]
 83%|████████▎ | 51652/61904 [3:57:01<4:03:27,  1.42s/it]
 83%|████████▎ | 51653/61904 [3:57:03<4:04:22,  1.43s/it]
 83%|████████▎ | 51654/61904 [3:57:04<4:02:23,  1.42s/it]
 83%|████████▎ | 51655/61904 [3:57:05<4:01:43,  1.42s/it]
 83%|████████▎ | 51656/61904 [3:57:07<3:53:45,  1.37s/it]
 83%|████████▎ | 51657/61904 [3:57:08<3:54:58,  1.38s/it]
 83%|████████▎ | 51658/61904 [3:57:09<3:48:46,  1.34s/it]
 83%|████████▎ | 51659/61904 [3:57:11<3:47:21,  1.33s/it]
 83%|████████▎ | 51660/61904 [3:57:12<3:50:13,  1.35s/it]
                                                         
{'loss': 2.413, 'learning_rate': 1.1660184104758199e-07, 'epoch': 13.35}

 83%|████████▎ | 51660/61904 [3:57:12<3:50:13,  1.35s/it]
 83%|████████▎ | 51661/61904 [3:57:13<3:51:52,  1.36s/it]
 83%|████████▎ | 51662/61904 [3:57:15<3:54:32,  1.37s/it]
 83%|████████▎ | 51663/61904 [3:57:16<3:48:56,  1.34s/it]
 83%|████████▎ | 51664/61904 [3:57:18<3:49:52,  1.35s/it]
 83%|████████▎ | 51665/61904 [3:57:19<3:49:18,  1.34s/it]
 83%|████████▎ | 51666/61904 [3:57:20<3:46:18,  1.33s/it]
 83%|████████▎ | 51667/61904 [3:57:21<3:45:51,  1.32s/it]
 83%|████████▎ | 51668/61904 [3:57:23<3:49:38,  1.35s/it]
 83%|████████▎ | 51669/61904 [3:57:24<3:52:11,  1.36s/it]
 83%|████████▎ | 51670/61904 [3:57:26<3:49:58,  1.35s/it]
 83%|████████▎ | 51671/61904 [3:57:27<3:50:57,  1.35s/it]
 83%|████████▎ | 51672/61904 [3:57:28<3:55:36,  1.38s/it]
 83%|████████▎ | 51673/61904 [3:57:30<3:53:39,  1.37s/it]
 83%|████████▎ | 51674/61904 [3:57:31<3:53:47,  1.37s/it]
 83%|████████▎ | 51675/61904 [3:57:33<4:01:12,  1.41s/it]
 83%|████████▎ | 51676/61904 [3:57:34<3:59:10,  1.40s/it]
 83%|████████▎ | 51677/61904 [3:57:35<4:01:06,  1.41s/it]
 83%|████████▎ | 51678/61904 [3:57:37<3:58:19,  1.40s/it]
 83%|████████▎ | 51679/61904 [3:57:38<3:57:26,  1.39s/it]
 83%|████████▎ | 51680/61904 [3:57:40<3:57:18,  1.39s/it]
                                                         
{'loss': 2.4563, 'learning_rate': 1.1656942823803965e-07, 'epoch': 13.36}

 83%|████████▎ | 51680/61904 [3:57:40<3:57:18,  1.39s/it]
 83%|████████▎ | 51681/61904 [3:57:41<3:50:49,  1.35s/it]
 83%|████████▎ | 51682/61904 [3:57:42<3:50:44,  1.35s/it]
 83%|████████▎ | 51683/61904 [3:57:44<4:00:25,  1.41s/it]
 83%|████████▎ | 51684/61904 [3:57:45<3:57:55,  1.40s/it]
 83%|████████▎ | 51685/61904 [3:57:46<3:55:48,  1.38s/it]
 83%|████████▎ | 51686/61904 [3:57:48<3:57:46,  1.40s/it]
 83%|████████▎ | 51687/61904 [3:57:49<3:57:13,  1.39s/it]
 83%|████████▎ | 51688/61904 [3:57:51<3:56:54,  1.39s/it]
 83%|████████▎ | 51689/61904 [3:57:52<3:51:53,  1.36s/it]
 84%|████████▎ | 51690/61904 [3:57:53<3:59:25,  1.41s/it]
 84%|████████▎ | 51691/61904 [3:57:55<4:01:33,  1.42s/it]
 84%|████████▎ | 51692/61904 [3:57:56<3:53:42,  1.37s/it]
 84%|████████▎ | 51693/61904 [3:57:57<3:51:16,  1.36s/it]
 84%|████████▎ | 51694/61904 [3:57:59<3:48:19,  1.34s/it]
 84%|████████▎ | 51695/61904 [3:58:00<3:47:57,  1.34s/it]
 84%|████████▎ | 51696/61904 [3:58:01<3:49:21,  1.35s/it]
 84%|████████▎ | 51697/61904 [3:58:03<3:48:09,  1.34s/it]
 84%|████████▎ | 51698/61904 [3:58:04<3:51:57,  1.36s/it]
 84%|████████▎ | 51699/61904 [3:58:06<3:53:38,  1.37s/it]
 84%|████████▎ | 51700/61904 [3:58:07<3:58:38,  1.40s/it]
                                                         
{'loss': 2.4141, 'learning_rate': 1.1653701542849733e-07, 'epoch': 13.36}

 84%|████████▎ | 51700/61904 [3:58:07<3:58:38,  1.40s/it]
 84%|████████▎ | 51701/61904 [3:58:09<4:01:51,  1.42s/it]
 84%|████████▎ | 51702/61904 [3:58:10<4:06:08,  1.45s/it]
 84%|████████▎ | 51703/61904 [3:58:11<3:59:11,  1.41s/it]
 84%|████████▎ | 51704/61904 [3:58:13<3:56:41,  1.39s/it]
 84%|████████▎ | 51705/61904 [3:58:14<4:01:30,  1.42s/it]
 84%|████████▎ | 51706/61904 [3:58:16<4:01:07,  1.42s/it]
 84%|████████▎ | 51707/61904 [3:58:17<4:06:01,  1.45s/it]
 84%|████████▎ | 51708/61904 [3:58:19<4:02:51,  1.43s/it]
 84%|████████▎ | 51709/61904 [3:58:20<3:57:16,  1.40s/it]
 84%|████████▎ | 51710/61904 [3:58:21<4:05:01,  1.44s/it]
 84%|████████▎ | 51711/61904 [3:58:23<3:58:59,  1.41s/it]
 84%|████████▎ | 51712/61904 [3:58:24<3:57:58,  1.40s/it]
 84%|████████▎ | 51713/61904 [3:58:25<3:50:05,  1.35s/it]
 84%|████████▎ | 51714/61904 [3:58:27<3:46:21,  1.33s/it]
 84%|████████▎ | 51715/61904 [3:58:28<3:45:32,  1.33s/it]
 84%|████████▎ | 51716/61904 [3:58:29<3:44:28,  1.32s/it]
 84%|████████▎ | 51717/61904 [3:58:31<3:43:24,  1.32s/it]
 84%|████████▎ | 51718/61904 [3:58:32<3:53:43,  1.38s/it]
 84%|████████▎ | 51719/61904 [3:58:33<3:51:49,  1.37s/it]
 84%|████████▎ | 51720/61904 [3:58:35<3:47:26,  1.34s/it]
                                                         
{'loss': 2.486, 'learning_rate': 1.16504602618955e-07, 'epoch': 13.37}

 84%|████████▎ | 51720/61904 [3:58:35<3:47:26,  1.34s/it]
 84%|████████▎ | 51721/61904 [3:58:36<3:45:45,  1.33s/it]
 84%|████████▎ | 51722/61904 [3:58:37<3:42:37,  1.31s/it]
 84%|████████▎ | 51723/61904 [3:58:39<3:49:33,  1.35s/it]
 84%|████████▎ | 51724/61904 [3:58:40<3:54:05,  1.38s/it]
 84%|████████▎ | 51725/61904 [3:58:42<3:55:59,  1.39s/it]
 84%|████████▎ | 51726/61904 [3:58:43<3:55:43,  1.39s/it]
 84%|████████▎ | 51727/61904 [3:58:44<3:52:27,  1.37s/it]
 84%|████████▎ | 51728/61904 [3:58:46<3:50:22,  1.36s/it]
 84%|████████▎ | 51729/61904 [3:58:47<3:47:58,  1.34s/it]
 84%|████████▎ | 51730/61904 [3:58:48<3:44:30,  1.32s/it]
 84%|████████▎ | 51731/61904 [3:58:50<3:47:44,  1.34s/it]
 84%|████████▎ | 51732/61904 [3:58:51<3:48:21,  1.35s/it]
 84%|████████▎ | 51733/61904 [3:58:52<3:49:11,  1.35s/it]
 84%|████████▎ | 51734/61904 [3:58:54<3:48:22,  1.35s/it]
 84%|████████▎ | 51735/61904 [3:58:55<3:45:53,  1.33s/it]
 84%|████████▎ | 51736/61904 [3:58:56<3:51:54,  1.37s/it]
 84%|████████▎ | 51737/61904 [3:58:58<4:01:07,  1.42s/it]
 84%|████████▎ | 51738/61904 [3:58:59<3:56:34,  1.40s/it]
 84%|████████▎ | 51739/61904 [3:59:01<3:56:02,  1.39s/it]
 84%|████████▎ | 51740/61904 [3:59:02<3:54:03,  1.38s/it]
                                                         
{'loss': 2.444, 'learning_rate': 1.1647218980941266e-07, 'epoch': 13.37}

 84%|████████▎ | 51740/61904 [3:59:02<3:54:03,  1.38s/it]
 84%|████████▎ | 51741/61904 [3:59:04<4:03:16,  1.44s/it]
 84%|████████▎ | 51742/61904 [3:59:05<3:55:58,  1.39s/it]
 84%|████████▎ | 51743/61904 [3:59:06<3:47:03,  1.34s/it]
 84%|████████▎ | 51744/61904 [3:59:08<3:51:44,  1.37s/it]
 84%|████████▎ | 51745/61904 [3:59:09<3:54:14,  1.38s/it]
 84%|████████▎ | 51746/61904 [3:59:10<3:55:42,  1.39s/it]
 84%|████████▎ | 51747/61904 [3:59:12<3:59:46,  1.42s/it]
 84%|████████▎ | 51748/61904 [3:59:13<3:55:01,  1.39s/it]
 84%|████████▎ | 51749/61904 [3:59:15<3:58:54,  1.41s/it]
 84%|████████▎ | 51750/61904 [3:59:16<3:50:44,  1.36s/it]
 84%|████████▎ | 51751/61904 [3:59:17<3:43:25,  1.32s/it]
 84%|████████▎ | 51752/61904 [3:59:19<3:48:16,  1.35s/it]
 84%|████████▎ | 51753/61904 [3:59:20<3:50:00,  1.36s/it]
 84%|████████▎ | 51754/61904 [3:59:21<3:53:40,  1.38s/it]
 84%|████████▎ | 51755/61904 [3:59:23<3:51:38,  1.37s/it]
 84%|████████▎ | 51756/61904 [3:59:24<3:50:21,  1.36s/it]
 84%|████████▎ | 51757/61904 [3:59:25<3:52:55,  1.38s/it]
 84%|████████▎ | 51758/61904 [3:59:27<3:51:06,  1.37s/it]
 84%|████████▎ | 51759/61904 [3:59:28<3:47:48,  1.35s/it]
 84%|████████▎ | 51760/61904 [3:59:29<3:46:44,  1.34s/it]
                                                         
{'loss': 2.4608, 'learning_rate': 1.1643977699987033e-07, 'epoch': 13.38}

 84%|████████▎ | 51760/61904 [3:59:29<3:46:44,  1.34s/it]
 84%|████████▎ | 51761/61904 [3:59:31<3:41:41,  1.31s/it]
 84%|████████▎ | 51762/61904 [3:59:32<3:47:57,  1.35s/it]
 84%|████████▎ | 51763/61904 [3:59:33<3:45:40,  1.34s/it]
 84%|████████▎ | 51764/61904 [3:59:35<3:42:28,  1.32s/it]
 84%|████████▎ | 51765/61904 [3:59:36<3:48:33,  1.35s/it]
 84%|████████▎ | 51766/61904 [3:59:38<3:57:39,  1.41s/it]
 84%|████████▎ | 51767/61904 [3:59:39<3:55:26,  1.39s/it]
 84%|████████▎ | 51768/61904 [3:59:40<3:54:32,  1.39s/it]
 84%|████████▎ | 51769/61904 [3:59:42<3:58:00,  1.41s/it]
 84%|████████▎ | 51770/61904 [3:59:43<3:51:33,  1.37s/it]
 84%|████████▎ | 51771/61904 [3:59:45<3:55:37,  1.40s/it]
 84%|████████▎ | 51772/61904 [3:59:46<4:00:44,  1.43s/it]
 84%|████████▎ | 51773/61904 [3:59:47<3:57:52,  1.41s/it]
 84%|████████▎ | 51774/61904 [3:59:49<3:51:26,  1.37s/it]
 84%|████████▎ | 51775/61904 [3:59:50<3:50:21,  1.36s/it]
 84%|████████▎ | 51776/61904 [3:59:52<3:53:00,  1.38s/it]
 84%|████████▎ | 51777/61904 [3:59:53<3:55:53,  1.40s/it]
 84%|████████▎ | 51778/61904 [3:59:54<3:55:57,  1.40s/it]
 84%|████████▎ | 51779/61904 [3:59:56<3:55:22,  1.39s/it]
 84%|████████▎ | 51780/61904 [3:59:57<3:54:46,  1.39s/it]
                                                         
{'loss': 2.4173, 'learning_rate': 1.1640736419032801e-07, 'epoch': 13.38}

 84%|████████▎ | 51780/61904 [3:59:57<3:54:46,  1.39s/it]
 84%|████████▎ | 51781/61904 [3:59:59<4:01:39,  1.43s/it]
 84%|████████▎ | 51782/61904 [4:00:00<3:56:40,  1.40s/it]
 84%|████████▎ | 51783/61904 [4:00:01<3:52:36,  1.38s/it]
 84%|████████▎ | 51784/61904 [4:00:03<3:54:01,  1.39s/it]
 84%|████████▎ | 51785/61904 [4:00:04<3:53:13,  1.38s/it]
 84%|████████▎ | 51786/61904 [4:00:05<3:44:38,  1.33s/it]
 84%|████████▎ | 51787/61904 [4:00:07<3:49:24,  1.36s/it]
 84%|████████▎ | 51788/61904 [4:00:08<3:54:36,  1.39s/it]
 84%|████████▎ | 51789/61904 [4:00:10<3:54:20,  1.39s/it]
 84%|████████▎ | 51790/61904 [4:00:11<3:50:20,  1.37s/it]
 84%|████████▎ | 51791/61904 [4:00:12<3:52:05,  1.38s/it]
 84%|████████▎ | 51792/61904 [4:00:14<3:50:53,  1.37s/it]
 84%|████████▎ | 51793/61904 [4:00:15<3:55:56,  1.40s/it]
 84%|████████▎ | 51794/61904 [4:00:16<3:48:37,  1.36s/it]
 84%|████████▎ | 51795/61904 [4:00:18<3:46:05,  1.34s/it]
 84%|████████▎ | 51796/61904 [4:00:19<3:47:01,  1.35s/it]
 84%|████████▎ | 51797/61904 [4:00:20<3:47:22,  1.35s/it]
 84%|████████▎ | 51798/61904 [4:00:22<3:41:38,  1.32s/it]
 84%|████████▎ | 51799/61904 [4:00:23<3:46:50,  1.35s/it]
 84%|████████▎ | 51800/61904 [4:00:24<3:49:23,  1.36s/it]
                                                         
{'loss': 2.4247, 'learning_rate': 1.1637495138078568e-07, 'epoch': 13.39}

 84%|████████▎ | 51800/61904 [4:00:24<3:49:23,  1.36s/it]
 84%|████████▎ | 51801/61904 [4:00:26<3:44:06,  1.33s/it]
 84%|████████▎ | 51802/61904 [4:00:27<3:45:50,  1.34s/it]
 84%|████████▎ | 51803/61904 [4:00:28<3:49:27,  1.36s/it]
 84%|████████▎ | 51804/61904 [4:00:30<3:47:49,  1.35s/it]
 84%|████████▎ | 51805/61904 [4:00:31<3:45:49,  1.34s/it]
 84%|████████▎ | 51806/61904 [4:00:32<3:44:55,  1.34s/it]
 84%|████████▎ | 51807/61904 [4:00:34<3:44:14,  1.33s/it]
 84%|████████▎ | 51808/61904 [4:00:35<3:45:01,  1.34s/it]
 84%|████████▎ | 51809/61904 [4:00:37<3:48:22,  1.36s/it]
 84%|████████▎ | 51810/61904 [4:00:38<3:47:00,  1.35s/it]
 84%|████████▎ | 51811/61904 [4:00:39<3:45:56,  1.34s/it]
 84%|████████▎ | 51812/61904 [4:00:41<3:48:00,  1.36s/it]
 84%|████████▎ | 51813/61904 [4:00:42<3:48:20,  1.36s/it]
 84%|████████▎ | 51814/61904 [4:00:43<3:58:32,  1.42s/it]
 84%|████████▎ | 51815/61904 [4:00:45<3:59:39,  1.43s/it]
 84%|████████▎ | 51816/61904 [4:00:46<4:02:28,  1.44s/it]
 84%|████████▎ | 51817/61904 [4:00:48<3:58:52,  1.42s/it]
 84%|████████▎ | 51818/61904 [4:00:49<4:01:01,  1.43s/it]
 84%|████████▎ | 51819/61904 [4:00:51<3:54:33,  1.40s/it]
 84%|████████▎ | 51820/61904 [4:00:52<3:47:28,  1.35s/it]
                                                         
{'loss': 2.4383, 'learning_rate': 1.1634253857124334e-07, 'epoch': 13.39}

 84%|████████▎ | 51820/61904 [4:00:52<3:47:28,  1.35s/it]
 84%|████████▎ | 51821/61904 [4:00:53<3:47:47,  1.36s/it]
 84%|████████▎ | 51822/61904 [4:00:54<3:44:06,  1.33s/it]
 84%|████████▎ | 51823/61904 [4:00:56<3:40:39,  1.31s/it]
 84%|████████▎ | 51824/61904 [4:00:57<3:38:57,  1.30s/it]
 84%|████████▎ | 51825/61904 [4:00:58<3:44:10,  1.33s/it]
 84%|████████▎ | 51826/61904 [4:01:00<3:49:27,  1.37s/it]
 84%|████████▎ | 51827/61904 [4:01:01<3:56:06,  1.41s/it]
 84%|████████▎ | 51828/61904 [4:01:03<3:53:55,  1.39s/it]
 84%|████████▎ | 51829/61904 [4:01:04<3:51:41,  1.38s/it]
 84%|████████▎ | 51830/61904 [4:01:06<3:58:19,  1.42s/it]
 84%|████████▎ | 51831/61904 [4:01:07<3:47:28,  1.35s/it]
 84%|████████▎ | 51832/61904 [4:01:08<3:49:45,  1.37s/it]
 84%|████████▎ | 51833/61904 [4:01:10<3:53:57,  1.39s/it]
 84%|████████▎ | 51834/61904 [4:01:11<3:53:38,  1.39s/it]
 84%|████████▎ | 51835/61904 [4:01:13<4:01:45,  1.44s/it]
 84%|████████▎ | 51836/61904 [4:01:14<4:03:16,  1.45s/it]
 84%|████████▎ | 51837/61904 [4:01:15<4:01:29,  1.44s/it]
 84%|████████▎ | 51838/61904 [4:01:17<4:02:05,  1.44s/it]
 84%|████████▎ | 51839/61904 [4:01:18<3:55:38,  1.40s/it]
 84%|████████▎ | 51840/61904 [4:01:20<4:03:09,  1.45s/it]
                                                         
{'loss': 2.4455, 'learning_rate': 1.16310125761701e-07, 'epoch': 13.4}

 84%|████████▎ | 51840/61904 [4:01:20<4:03:09,  1.45s/it]
 84%|████████▎ | 51841/61904 [4:01:21<4:04:25,  1.46s/it]
 84%|████████▎ | 51842/61904 [4:01:23<3:57:10,  1.41s/it]
 84%|████████▎ | 51843/61904 [4:01:24<3:50:50,  1.38s/it]
 84%|████████▎ | 51844/61904 [4:01:25<3:48:49,  1.36s/it]
 84%|████████▍ | 51845/61904 [4:01:27<3:48:02,  1.36s/it]
 84%|████████▍ | 51846/61904 [4:01:28<3:53:56,  1.40s/it]
 84%|████████▍ | 51847/61904 [4:01:29<3:45:10,  1.34s/it]
 84%|████████▍ | 51848/61904 [4:01:31<3:43:58,  1.34s/it]
 84%|████████▍ | 51849/61904 [4:01:32<3:40:57,  1.32s/it]
 84%|████████▍ | 51850/61904 [4:01:33<3:37:11,  1.30s/it]
 84%|████████▍ | 51851/61904 [4:01:34<3:37:28,  1.30s/it]
 84%|████████▍ | 51852/61904 [4:01:36<3:37:34,  1.30s/it]
 84%|████████▍ | 51853/61904 [4:01:37<3:39:51,  1.31s/it]
 84%|████████▍ | 51854/61904 [4:01:39<3:50:27,  1.38s/it]
 84%|████████▍ | 51855/61904 [4:01:40<3:47:32,  1.36s/it]
 84%|████████▍ | 51856/61904 [4:01:41<3:48:11,  1.36s/it]
 84%|████████▍ | 51857/61904 [4:01:43<3:48:57,  1.37s/it]
 84%|████████▍ | 51858/61904 [4:01:44<3:47:23,  1.36s/it]
 84%|████████▍ | 51859/61904 [4:01:45<3:51:57,  1.39s/it]
 84%|████████▍ | 51860/61904 [4:01:47<3:50:39,  1.38s/it]
                                                         
{'loss': 2.4771, 'learning_rate': 1.1627771295215869e-07, 'epoch': 13.4}

 84%|████████▍ | 51860/61904 [4:01:47<3:50:39,  1.38s/it]
 84%|████████▍ | 51861/61904 [4:01:48<3:43:04,  1.33s/it]
 84%|████████▍ | 51862/61904 [4:01:49<3:42:30,  1.33s/it]
 84%|████████▍ | 51863/61904 [4:01:51<3:45:24,  1.35s/it]
 84%|████████▍ | 51864/61904 [4:01:52<3:43:26,  1.34s/it]
 84%|████████▍ | 51865/61904 [4:01:53<3:43:59,  1.34s/it]
 84%|████████▍ | 51866/61904 [4:01:55<3:50:41,  1.38s/it]
 84%|████████▍ | 51867/61904 [4:01:56<3:50:01,  1.38s/it]
 84%|████████▍ | 51868/61904 [4:01:58<3:51:17,  1.38s/it]
 84%|████████▍ | 51869/61904 [4:01:59<3:54:17,  1.40s/it]
 84%|████████▍ | 51870/61904 [4:02:01<3:57:37,  1.42s/it]
 84%|████████▍ | 51871/61904 [4:02:02<3:55:53,  1.41s/it]
 84%|████████▍ | 51872/61904 [4:02:03<3:59:26,  1.43s/it]
 84%|████████▍ | 51873/61904 [4:02:05<3:59:48,  1.43s/it]
 84%|████████▍ | 51874/61904 [4:02:06<4:06:10,  1.47s/it]
 84%|████████▍ | 51875/61904 [4:02:08<4:07:31,  1.48s/it]
 84%|████████▍ | 51876/61904 [4:02:09<4:00:12,  1.44s/it]
 84%|████████▍ | 51877/61904 [4:02:11<3:59:58,  1.44s/it]
 84%|████████▍ | 51878/61904 [4:02:12<4:00:05,  1.44s/it]
 84%|████████▍ | 51879/61904 [4:02:13<3:55:28,  1.41s/it]
 84%|████████▍ | 51880/61904 [4:02:15<3:54:18,  1.40s/it]
                                                         
{'loss': 2.4686, 'learning_rate': 1.1624530014261635e-07, 'epoch': 13.41}

 84%|████████▍ | 51880/61904 [4:02:15<3:54:18,  1.40s/it]
 84%|████████▍ | 51881/61904 [4:02:16<3:47:00,  1.36s/it]
 84%|████████▍ | 51882/61904 [4:02:17<3:44:56,  1.35s/it]
 84%|████████▍ | 51883/61904 [4:02:19<3:52:13,  1.39s/it]
 84%|████████▍ | 51884/61904 [4:02:20<3:46:04,  1.35s/it]
 84%|████████▍ | 51885/61904 [4:02:21<3:43:47,  1.34s/it]
 84%|████████▍ | 51886/61904 [4:02:23<3:53:17,  1.40s/it]
 84%|████████▍ | 51887/61904 [4:02:24<3:48:29,  1.37s/it]
 84%|████████▍ | 51888/61904 [4:02:26<3:46:51,  1.36s/it]
 84%|████████▍ | 51889/61904 [4:02:27<3:50:14,  1.38s/it]
 84%|████████▍ | 51890/61904 [4:02:28<3:49:20,  1.37s/it]
 84%|████████▍ | 51891/61904 [4:02:30<3:47:09,  1.36s/it]
 84%|████████▍ | 51892/61904 [4:02:31<3:46:16,  1.36s/it]
 84%|████████▍ | 51893/61904 [4:02:32<3:48:01,  1.37s/it]
 84%|████████▍ | 51894/61904 [4:02:34<3:45:48,  1.35s/it]
 84%|████████▍ | 51895/61904 [4:02:35<3:46:25,  1.36s/it]
 84%|████████▍ | 51896/61904 [4:02:36<3:44:16,  1.34s/it]
 84%|████████▍ | 51897/61904 [4:02:38<3:39:26,  1.32s/it]
 84%|████████▍ | 51898/61904 [4:02:39<3:49:26,  1.38s/it]
 84%|████████▍ | 51899/61904 [4:02:41<3:52:46,  1.40s/it]
 84%|████████▍ | 51900/61904 [4:02:42<3:57:02,  1.42s/it]
                                                         
{'loss': 2.4417, 'learning_rate': 1.1621288733307401e-07, 'epoch': 13.41}

 84%|████████▍ | 51900/61904 [4:02:42<3:57:02,  1.42s/it]
 84%|████████▍ | 51901/61904 [4:02:43<3:50:16,  1.38s/it]
 84%|████████▍ | 51902/61904 [4:02:45<3:54:23,  1.41s/it]
 84%|████████▍ | 51903/61904 [4:02:46<3:51:08,  1.39s/it]
 84%|████████▍ | 51904/61904 [4:02:48<3:49:41,  1.38s/it]
 84%|████████▍ | 51905/61904 [4:02:49<3:49:01,  1.37s/it]
 84%|████████▍ | 51906/61904 [4:02:50<3:46:54,  1.36s/it]
 84%|████████▍ | 51907/61904 [4:02:52<3:51:06,  1.39s/it]
 84%|████████▍ | 51908/61904 [4:02:53<3:57:01,  1.42s/it]
 84%|████████▍ | 51909/61904 [4:02:55<3:49:39,  1.38s/it]
 84%|████████▍ | 51910/61904 [4:02:56<3:51:31,  1.39s/it]
 84%|████████▍ | 51911/61904 [4:02:57<3:45:03,  1.35s/it]
 84%|████████▍ | 51912/61904 [4:02:59<3:43:33,  1.34s/it]
 84%|████████▍ | 51913/61904 [4:03:00<3:39:52,  1.32s/it]
 84%|████████▍ | 51914/61904 [4:03:01<3:41:01,  1.33s/it]
 84%|████████▍ | 51915/61904 [4:03:02<3:39:28,  1.32s/it]
 84%|████████▍ | 51916/61904 [4:03:04<3:34:40,  1.29s/it]
 84%|████████▍ | 51917/61904 [4:03:05<3:36:28,  1.30s/it]
 84%|████████▍ | 51918/61904 [4:03:06<3:37:14,  1.31s/it]
 84%|████████▍ | 51919/61904 [4:03:08<3:34:36,  1.29s/it]
 84%|████████▍ | 51920/61904 [4:03:09<3:46:04,  1.36s/it]
                                                         
{'loss': 2.4765, 'learning_rate': 1.1618047452353167e-07, 'epoch': 13.42}

 84%|████████▍ | 51920/61904 [4:03:09<3:46:04,  1.36s/it]
 84%|████████▍ | 51921/61904 [4:03:11<3:52:14,  1.40s/it]
 84%|████████▍ | 51922/61904 [4:03:12<3:45:43,  1.36s/it]
 84%|████████▍ | 51923/61904 [4:03:13<3:45:20,  1.35s/it]
 84%|████████▍ | 51924/61904 [4:03:15<3:51:35,  1.39s/it]
 84%|████████▍ | 51925/61904 [4:03:16<3:51:50,  1.39s/it]
 84%|████████▍ | 51926/61904 [4:03:17<3:48:04,  1.37s/it]
 84%|████████▍ | 51927/61904 [4:03:19<3:45:39,  1.36s/it]
 84%|████████▍ | 51928/61904 [4:03:20<3:45:40,  1.36s/it]
 84%|████████▍ | 51929/61904 [4:03:21<3:43:36,  1.35s/it]
 84%|████████▍ | 51930/61904 [4:03:23<3:43:44,  1.35s/it]
 84%|████████▍ | 51931/61904 [4:03:24<3:44:27,  1.35s/it]
 84%|████████▍ | 51932/61904 [4:03:25<3:43:51,  1.35s/it]
 84%|████████▍ | 51933/61904 [4:03:27<3:43:37,  1.35s/it]
 84%|████████▍ | 51934/61904 [4:03:28<3:44:30,  1.35s/it]
 84%|████████▍ | 51935/61904 [4:03:30<3:46:23,  1.36s/it]
 84%|████████▍ | 51936/61904 [4:03:31<3:43:57,  1.35s/it]
 84%|████████▍ | 51937/61904 [4:03:32<3:42:53,  1.34s/it]
 84%|████████▍ | 51938/61904 [4:03:34<3:44:09,  1.35s/it]
 84%|████████▍ | 51939/61904 [4:03:35<3:41:38,  1.33s/it]
 84%|████████▍ | 51940/61904 [4:03:36<3:43:01,  1.34s/it]
                                                         
{'loss': 2.4501, 'learning_rate': 1.1614806171398936e-07, 'epoch': 13.42}

 84%|████████▍ | 51940/61904 [4:03:36<3:43:01,  1.34s/it]
 84%|████████▍ | 51941/61904 [4:03:38<3:47:43,  1.37s/it]
 84%|████████▍ | 51942/61904 [4:03:39<3:43:49,  1.35s/it]
 84%|████████▍ | 51943/61904 [4:03:40<3:40:59,  1.33s/it]
 84%|████████▍ | 51944/61904 [4:03:42<3:43:10,  1.34s/it]
 84%|████████▍ | 51945/61904 [4:03:43<3:47:45,  1.37s/it]
 84%|████████▍ | 51946/61904 [4:03:44<3:48:35,  1.38s/it]
 84%|████████▍ | 51947/61904 [4:03:46<3:47:02,  1.37s/it]
 84%|████████▍ | 51948/61904 [4:03:47<3:46:04,  1.36s/it]
 84%|████████▍ | 51949/61904 [4:03:49<3:47:46,  1.37s/it]
 84%|████████▍ | 51950/61904 [4:03:50<3:43:30,  1.35s/it]
 84%|████████▍ | 51951/61904 [4:03:51<3:42:37,  1.34s/it]
 84%|████████▍ | 51952/61904 [4:03:52<3:38:20,  1.32s/it]
 84%|████████▍ | 51953/61904 [4:03:54<3:42:38,  1.34s/it]
 84%|████████▍ | 51954/61904 [4:03:55<3:42:08,  1.34s/it]
 84%|████████▍ | 51955/61904 [4:03:56<3:38:35,  1.32s/it]
 84%|████████▍ | 51956/61904 [4:03:58<3:43:15,  1.35s/it]
 84%|████████▍ | 51957/61904 [4:03:59<3:47:10,  1.37s/it]
 84%|████████▍ | 51958/61904 [4:04:01<3:48:16,  1.38s/it]
 84%|████████▍ | 51959/61904 [4:04:02<3:53:40,  1.41s/it]
 84%|████████▍ | 51960/61904 [4:04:04<3:53:50,  1.41s/it]
                                                         
{'loss': 2.467, 'learning_rate': 1.1611564890444702e-07, 'epoch': 13.43}

 84%|████████▍ | 51960/61904 [4:04:04<3:53:50,  1.41s/it]
 84%|████████▍ | 51961/61904 [4:04:05<3:50:30,  1.39s/it]
 84%|████████▍ | 51962/61904 [4:04:06<3:47:12,  1.37s/it]
 84%|████████▍ | 51963/61904 [4:04:08<3:46:30,  1.37s/it]
 84%|████████▍ | 51964/61904 [4:04:09<3:47:38,  1.37s/it]
 84%|████████▍ | 51965/61904 [4:04:10<3:40:53,  1.33s/it]
 84%|████████▍ | 51966/61904 [4:04:12<3:42:41,  1.34s/it]
 84%|████████▍ | 51967/61904 [4:04:13<3:46:29,  1.37s/it]
 84%|████████▍ | 51968/61904 [4:04:14<3:41:00,  1.33s/it]
 84%|████████▍ | 51969/61904 [4:04:16<3:40:04,  1.33s/it]
 84%|████████▍ | 51970/61904 [4:04:17<3:46:14,  1.37s/it]
 84%|████████▍ | 51971/61904 [4:04:18<3:50:29,  1.39s/it]
 84%|████████▍ | 51972/61904 [4:04:20<3:47:33,  1.37s/it]
 84%|████████▍ | 51973/61904 [4:04:21<3:55:22,  1.42s/it]
 84%|████████▍ | 51974/61904 [4:04:23<3:50:18,  1.39s/it]
 84%|████████▍ | 51975/61904 [4:04:24<3:40:44,  1.33s/it]
 84%|████████▍ | 51976/61904 [4:04:26<3:57:48,  1.44s/it]
 84%|████████▍ | 51977/61904 [4:04:27<3:55:23,  1.42s/it]
 84%|████████▍ | 51978/61904 [4:04:28<4:01:22,  1.46s/it]
 84%|████████▍ | 51979/61904 [4:04:30<3:56:30,  1.43s/it]
 84%|████████▍ | 51980/61904 [4:04:31<3:48:05,  1.38s/it]
                                                         
{'loss': 2.4404, 'learning_rate': 1.1608323609490469e-07, 'epoch': 13.43}

 84%|████████▍ | 51980/61904 [4:04:31<3:48:05,  1.38s/it]
 84%|████████▍ | 51981/61904 [4:04:33<3:51:57,  1.40s/it]
 84%|████████▍ | 51982/61904 [4:04:34<3:47:44,  1.38s/it]
 84%|████████▍ | 51983/61904 [4:04:35<3:38:49,  1.32s/it]
 84%|████████▍ | 51984/61904 [4:04:36<3:35:05,  1.30s/it]
 84%|████████▍ | 51985/61904 [4:04:38<3:45:51,  1.37s/it]
 84%|████████▍ | 51986/61904 [4:04:39<3:41:35,  1.34s/it]
 84%|████████▍ | 51987/61904 [4:04:40<3:41:30,  1.34s/it]
 84%|████████▍ | 51988/61904 [4:04:42<3:54:03,  1.42s/it]
 84%|████████▍ | 51989/61904 [4:04:44<4:04:00,  1.48s/it]
 84%|████████▍ | 51990/61904 [4:04:45<3:51:15,  1.40s/it]
 84%|████████▍ | 51991/61904 [4:04:46<3:49:16,  1.39s/it]
 84%|████████▍ | 51992/61904 [4:04:47<3:41:17,  1.34s/it]
 84%|████████▍ | 51993/61904 [4:04:49<3:43:40,  1.35s/it]
 84%|████████▍ | 51994/61904 [4:04:50<3:41:40,  1.34s/it]
 84%|████████▍ | 51995/61904 [4:04:51<3:34:22,  1.30s/it]
 84%|████████▍ | 51996/61904 [4:04:53<3:35:18,  1.30s/it]
 84%|████████▍ | 51997/61904 [4:04:54<3:45:56,  1.37s/it]
 84%|████████▍ | 51998/61904 [4:04:56<3:45:03,  1.36s/it]
 84%|████████▍ | 51999/61904 [4:04:57<3:49:39,  1.39s/it]
 84%|████████▍ | 52000/61904 [4:04:58<3:47:44,  1.38s/it]
                                                         
{'loss': 2.4413, 'learning_rate': 1.1605082328536235e-07, 'epoch': 13.44}

 84%|████████▍ | 52000/61904 [4:04:58<3:47:44,  1.38s/it]
 84%|████████▍ | 52001/61904 [4:05:00<3:46:11,  1.37s/it]
 84%|████████▍ | 52002/61904 [4:05:01<3:46:39,  1.37s/it]
 84%|████████▍ | 52003/61904 [4:05:02<3:46:40,  1.37s/it]
 84%|████████▍ | 52004/61904 [4:05:04<3:48:17,  1.38s/it]
 84%|████████▍ | 52005/61904 [4:05:05<3:48:11,  1.38s/it]
 84%|████████▍ | 52006/61904 [4:05:06<3:39:20,  1.33s/it]
 84%|████████▍ | 52007/61904 [4:05:08<3:39:53,  1.33s/it]
 84%|████████▍ | 52008/61904 [4:05:09<3:51:12,  1.40s/it]
 84%|████████▍ | 52009/61904 [4:05:11<3:51:43,  1.41s/it]
 84%|████████▍ | 52010/61904 [4:05:12<4:05:52,  1.49s/it]
 84%|████████▍ | 52011/61904 [4:05:14<3:57:08,  1.44s/it]
 84%|████████▍ | 52012/61904 [4:05:15<3:51:10,  1.40s/it]
 84%|████████▍ | 52013/61904 [4:05:16<3:44:14,  1.36s/it]
 84%|████████▍ | 52014/61904 [4:05:18<3:40:17,  1.34s/it]
 84%|████████▍ | 52015/61904 [4:05:19<3:40:04,  1.34s/it]
 84%|████████▍ | 52016/61904 [4:05:20<3:48:27,  1.39s/it]
 84%|████████▍ | 52017/61904 [4:05:22<3:45:53,  1.37s/it]
 84%|████████▍ | 52018/61904 [4:05:23<3:45:29,  1.37s/it]
 84%|████████▍ | 52019/61904 [4:05:25<3:46:53,  1.38s/it]
 84%|████████▍ | 52020/61904 [4:05:26<3:42:13,  1.35s/it]
                                                         
{'loss': 2.4529, 'learning_rate': 1.1601841047582004e-07, 'epoch': 13.45}

 84%|████████▍ | 52020/61904 [4:05:26<3:42:13,  1.35s/it]
 84%|████████▍ | 52021/61904 [4:05:27<3:39:39,  1.33s/it]
 84%|████████▍ | 52022/61904 [4:05:29<3:42:58,  1.35s/it]
 84%|████████▍ | 52023/61904 [4:05:30<3:41:12,  1.34s/it]
 84%|████████▍ | 52024/61904 [4:05:31<3:45:24,  1.37s/it]
 84%|████████▍ | 52025/61904 [4:05:33<3:43:17,  1.36s/it]
 84%|████████▍ | 52026/61904 [4:05:34<3:41:47,  1.35s/it]
 84%|████████▍ | 52027/61904 [4:05:35<3:38:17,  1.33s/it]
 84%|████████▍ | 52028/61904 [4:05:37<3:42:55,  1.35s/it]
 84%|████████▍ | 52029/61904 [4:05:38<3:45:24,  1.37s/it]
 84%|████████▍ | 52030/61904 [4:05:39<3:44:45,  1.37s/it]
 84%|████████▍ | 52031/61904 [4:05:41<3:41:35,  1.35s/it]
 84%|████████▍ | 52032/61904 [4:05:42<3:40:37,  1.34s/it]
 84%|████████▍ | 52033/61904 [4:05:44<3:46:59,  1.38s/it]
 84%|████████▍ | 52034/61904 [4:05:45<3:47:51,  1.39s/it]
 84%|████████▍ | 52035/61904 [4:05:46<3:39:30,  1.33s/it]
 84%|████████▍ | 52036/61904 [4:05:47<3:39:16,  1.33s/it]
 84%|████████▍ | 52037/61904 [4:05:49<3:46:54,  1.38s/it]
 84%|████████▍ | 52038/61904 [4:05:50<3:42:32,  1.35s/it]
 84%|████████▍ | 52039/61904 [4:05:52<3:38:55,  1.33s/it]
 84%|████████▍ | 52040/61904 [4:05:53<3:40:21,  1.34s/it]
                                                         
{'loss': 2.4719, 'learning_rate': 1.159859976662777e-07, 'epoch': 13.45}

 84%|████████▍ | 52040/61904 [4:05:53<3:40:21,  1.34s/it]
 84%|████████▍ | 52041/61904 [4:05:54<3:43:19,  1.36s/it]
 84%|████████▍ | 52042/61904 [4:05:56<3:43:43,  1.36s/it]
 84%|████████▍ | 52043/61904 [4:05:57<3:46:59,  1.38s/it]
 84%|████████▍ | 52044/61904 [4:05:59<3:51:15,  1.41s/it]
 84%|████████▍ | 52045/61904 [4:06:00<3:53:12,  1.42s/it]
 84%|████████▍ | 52046/61904 [4:06:01<3:48:34,  1.39s/it]
 84%|████████▍ | 52047/61904 [4:06:03<3:48:56,  1.39s/it]
 84%|████████▍ | 52048/61904 [4:06:04<3:51:17,  1.41s/it]
 84%|████████▍ | 52049/61904 [4:06:05<3:40:59,  1.35s/it]
 84%|████████▍ | 52050/61904 [4:06:07<3:37:37,  1.33s/it]
 84%|████████▍ | 52051/61904 [4:06:08<3:44:48,  1.37s/it]
 84%|████████▍ | 52052/61904 [4:06:09<3:42:38,  1.36s/it]
 84%|████████▍ | 52053/61904 [4:06:11<3:41:44,  1.35s/it]
 84%|████████▍ | 52054/61904 [4:06:12<3:41:38,  1.35s/it]
 84%|████████▍ | 52055/61904 [4:06:13<3:39:22,  1.34s/it]
 84%|████████▍ | 52056/61904 [4:06:15<3:38:07,  1.33s/it]
 84%|████████▍ | 52057/61904 [4:06:16<3:44:46,  1.37s/it]
 84%|████████▍ | 52058/61904 [4:06:18<3:42:17,  1.35s/it]
 84%|████████▍ | 52059/61904 [4:06:19<3:43:06,  1.36s/it]
 84%|████████▍ | 52060/61904 [4:06:20<3:38:01,  1.33s/it]
                                                         
{'loss': 2.3729, 'learning_rate': 1.1595358485673536e-07, 'epoch': 13.46}

 84%|████████▍ | 52060/61904 [4:06:20<3:38:01,  1.33s/it]
 84%|████████▍ | 52061/61904 [4:06:22<3:44:57,  1.37s/it]
 84%|████████▍ | 52062/61904 [4:06:23<3:49:00,  1.40s/it]
 84%|████████▍ | 52063/61904 [4:06:24<3:47:19,  1.39s/it]
 84%|████████▍ | 52064/61904 [4:06:26<3:46:58,  1.38s/it]
 84%|████████▍ | 52065/61904 [4:06:27<3:59:04,  1.46s/it]
 84%|████████▍ | 52066/61904 [4:06:29<3:51:43,  1.41s/it]
 84%|████████▍ | 52067/61904 [4:06:30<3:45:47,  1.38s/it]
 84%|████████▍ | 52068/61904 [4:06:31<3:46:57,  1.38s/it]
 84%|████████▍ | 52069/61904 [4:06:33<3:42:05,  1.35s/it]
 84%|████████▍ | 52070/61904 [4:06:34<3:45:13,  1.37s/it]
 84%|████████▍ | 52071/61904 [4:06:36<3:46:35,  1.38s/it]
 84%|████████▍ | 52072/61904 [4:06:37<3:45:22,  1.38s/it]
 84%|████████▍ | 52073/61904 [4:06:38<3:45:43,  1.38s/it]
 84%|████████▍ | 52074/61904 [4:06:40<3:46:12,  1.38s/it]
 84%|████████▍ | 52075/61904 [4:06:41<3:51:58,  1.42s/it]
 84%|████████▍ | 52076/61904 [4:06:42<3:46:56,  1.39s/it]
 84%|████████▍ | 52077/61904 [4:06:44<3:50:13,  1.41s/it]
 84%|████████▍ | 52078/61904 [4:06:45<3:47:49,  1.39s/it]
 84%|████████▍ | 52079/61904 [4:06:47<3:41:34,  1.35s/it]
 84%|████████▍ | 52080/61904 [4:06:48<3:45:53,  1.38s/it]
                                                         
{'loss': 2.4296, 'learning_rate': 1.1592117204719305e-07, 'epoch': 13.46}

 84%|████████▍ | 52080/61904 [4:06:48<3:45:53,  1.38s/it]
 84%|████████▍ | 52081/61904 [4:06:49<3:38:34,  1.34s/it]
 84%|████████▍ | 52082/61904 [4:06:51<3:40:39,  1.35s/it]
 84%|████████▍ | 52083/61904 [4:06:52<3:43:10,  1.36s/it]
 84%|████████▍ | 52084/61904 [4:06:53<3:48:08,  1.39s/it]
 84%|████████▍ | 52085/61904 [4:06:55<3:47:01,  1.39s/it]
 84%|████████▍ | 52086/61904 [4:06:56<3:46:56,  1.39s/it]
 84%|████████▍ | 52087/61904 [4:06:58<3:53:16,  1.43s/it]
 84%|████████▍ | 52088/61904 [4:06:59<3:48:27,  1.40s/it]
 84%|████████▍ | 52089/61904 [4:07:01<3:52:01,  1.42s/it]
 84%|████████▍ | 52090/61904 [4:07:02<3:48:19,  1.40s/it]
 84%|████████▍ | 52091/61904 [4:07:03<3:43:53,  1.37s/it]
 84%|████████▍ | 52092/61904 [4:07:04<3:39:30,  1.34s/it]
 84%|████████▍ | 52093/61904 [4:07:06<3:47:31,  1.39s/it]
 84%|████████▍ | 52094/61904 [4:07:07<3:50:40,  1.41s/it]
 84%|████████▍ | 52095/61904 [4:07:09<3:51:49,  1.42s/it]
 84%|████████▍ | 52096/61904 [4:07:10<3:48:25,  1.40s/it]
 84%|████████▍ | 52097/61904 [4:07:12<3:45:36,  1.38s/it]
 84%|████████▍ | 52098/61904 [4:07:13<3:46:40,  1.39s/it]
 84%|████████▍ | 52099/61904 [4:07:14<3:45:02,  1.38s/it]
 84%|████████▍ | 52100/61904 [4:07:16<3:44:53,  1.38s/it]
                                                         
{'loss': 2.4939, 'learning_rate': 1.1588875923765071e-07, 'epoch': 13.47}

 84%|████████▍ | 52100/61904 [4:07:16<3:44:53,  1.38s/it]
 84%|████████▍ | 52101/61904 [4:07:17<3:44:32,  1.37s/it]
 84%|████████▍ | 52102/61904 [4:07:18<3:46:01,  1.38s/it]
 84%|████████▍ | 52103/61904 [4:07:20<3:51:06,  1.41s/it]
 84%|████████▍ | 52104/61904 [4:07:21<3:42:19,  1.36s/it]
 84%|████████▍ | 52105/61904 [4:07:23<3:56:41,  1.45s/it]
 84%|████████▍ | 52106/61904 [4:07:24<3:57:52,  1.46s/it]
 84%|████████▍ | 52107/61904 [4:07:26<3:55:22,  1.44s/it]
 84%|████████▍ | 52108/61904 [4:07:27<3:48:48,  1.40s/it]
 84%|████████▍ | 52109/61904 [4:07:28<3:46:20,  1.39s/it]
 84%|████████▍ | 52110/61904 [4:07:30<3:43:54,  1.37s/it]
 84%|████████▍ | 52111/61904 [4:07:31<3:47:37,  1.39s/it]
 84%|████████▍ | 52112/61904 [4:07:32<3:42:39,  1.36s/it]
 84%|████████▍ | 52113/61904 [4:07:34<3:49:25,  1.41s/it]
 84%|████████▍ | 52114/61904 [4:07:35<3:49:32,  1.41s/it]
 84%|████████▍ | 52115/61904 [4:07:37<3:48:49,  1.40s/it]
 84%|████████▍ | 52116/61904 [4:07:38<3:45:31,  1.38s/it]
 84%|████████▍ | 52117/61904 [4:07:39<3:45:45,  1.38s/it]
 84%|████████▍ | 52118/61904 [4:07:41<3:41:34,  1.36s/it]
 84%|████████▍ | 52119/61904 [4:07:42<3:37:23,  1.33s/it]
 84%|████████▍ | 52120/61904 [4:07:43<3:38:02,  1.34s/it]
                                                         
{'loss': 2.4214, 'learning_rate': 1.1585634642810837e-07, 'epoch': 13.47}

 84%|████████▍ | 52120/61904 [4:07:43<3:38:02,  1.34s/it]
 84%|████████▍ | 52121/61904 [4:07:45<3:36:13,  1.33s/it]
 84%|████████▍ | 52122/61904 [4:07:46<3:34:15,  1.31s/it]
 84%|████████▍ | 52123/61904 [4:07:47<3:32:44,  1.31s/it]
 84%|████████▍ | 52124/61904 [4:07:49<3:39:50,  1.35s/it]
 84%|████████▍ | 52125/61904 [4:07:50<3:49:30,  1.41s/it]
 84%|████████▍ | 52126/61904 [4:07:51<3:39:39,  1.35s/it]
 84%|████████▍ | 52127/61904 [4:07:53<3:34:59,  1.32s/it]
 84%|████████▍ | 52128/61904 [4:07:54<3:37:41,  1.34s/it]
 84%|████████▍ | 52129/61904 [4:07:55<3:35:07,  1.32s/it]
 84%|████████▍ | 52130/61904 [4:07:57<3:43:45,  1.37s/it]
 84%|████████▍ | 52131/61904 [4:07:58<3:40:02,  1.35s/it]
 84%|████████▍ | 52132/61904 [4:08:00<3:42:28,  1.37s/it]
 84%|████████▍ | 52133/61904 [4:08:01<3:45:33,  1.39s/it]
 84%|████████▍ | 52134/61904 [4:08:02<3:41:26,  1.36s/it]
 84%|████████▍ | 52135/61904 [4:08:04<3:40:30,  1.35s/it]
 84%|████████▍ | 52136/61904 [4:08:05<3:45:28,  1.38s/it]
 84%|████████▍ | 52137/61904 [4:08:07<3:46:38,  1.39s/it]
 84%|████████▍ | 52138/61904 [4:08:08<3:46:23,  1.39s/it]
 84%|████████▍ | 52139/61904 [4:08:09<3:47:31,  1.40s/it]
 84%|████████▍ | 52140/61904 [4:08:11<3:44:18,  1.38s/it]
                                                         
{'loss': 2.4435, 'learning_rate': 1.1582393361856603e-07, 'epoch': 13.48}

 84%|████████▍ | 52140/61904 [4:08:11<3:44:18,  1.38s/it]
 84%|████████▍ | 52141/61904 [4:08:12<3:34:50,  1.32s/it]
 84%|████████▍ | 52142/61904 [4:08:13<3:43:52,  1.38s/it]
 84%|████████▍ | 52143/61904 [4:08:15<3:40:16,  1.35s/it]
 84%|████████▍ | 52144/61904 [4:08:16<3:47:42,  1.40s/it]
 84%|████████▍ | 52145/61904 [4:08:18<3:46:40,  1.39s/it]
 84%|████████▍ | 52146/61904 [4:08:19<3:40:41,  1.36s/it]
 84%|████████▍ | 52147/61904 [4:08:20<3:37:48,  1.34s/it]
 84%|████████▍ | 52148/61904 [4:08:21<3:37:19,  1.34s/it]
 84%|████████▍ | 52149/61904 [4:08:23<3:42:25,  1.37s/it]
 84%|████████▍ | 52150/61904 [4:08:24<3:35:50,  1.33s/it]
 84%|████████▍ | 52151/61904 [4:08:25<3:36:21,  1.33s/it]
 84%|████████▍ | 52152/61904 [4:08:27<3:36:46,  1.33s/it]
 84%|████████▍ | 52153/61904 [4:08:28<3:39:59,  1.35s/it]
 84%|████████▍ | 52154/61904 [4:08:30<3:39:57,  1.35s/it]
 84%|████████▍ | 52155/61904 [4:08:31<3:48:36,  1.41s/it]
 84%|████████▍ | 52156/61904 [4:08:32<3:45:59,  1.39s/it]
 84%|████████▍ | 52157/61904 [4:08:34<3:50:05,  1.42s/it]
 84%|████████▍ | 52158/61904 [4:08:35<3:43:15,  1.37s/it]
 84%|████████▍ | 52159/61904 [4:08:37<3:39:52,  1.35s/it]
 84%|████████▍ | 52160/61904 [4:08:38<3:40:51,  1.36s/it]
                                                         
{'loss': 2.4724, 'learning_rate': 1.1579152080902372e-07, 'epoch': 13.48}

 84%|████████▍ | 52160/61904 [4:08:38<3:40:51,  1.36s/it]
 84%|████████▍ | 52161/61904 [4:08:39<3:38:15,  1.34s/it]
 84%|████████▍ | 52162/61904 [4:08:41<3:53:06,  1.44s/it]
 84%|████████▍ | 52163/61904 [4:08:42<3:49:48,  1.42s/it]
 84%|████████▍ | 52164/61904 [4:08:44<3:48:25,  1.41s/it]
 84%|████████▍ | 52165/61904 [4:08:45<3:52:26,  1.43s/it]
 84%|████████▍ | 52166/61904 [4:08:47<4:05:13,  1.51s/it]
 84%|████████▍ | 52167/61904 [4:08:48<3:55:43,  1.45s/it]
 84%|████████▍ | 52168/61904 [4:08:49<3:51:29,  1.43s/it]
 84%|████████▍ | 52169/61904 [4:08:51<3:44:46,  1.39s/it]
 84%|████████▍ | 52170/61904 [4:08:52<3:52:14,  1.43s/it]
 84%|████████▍ | 52171/61904 [4:08:54<3:45:54,  1.39s/it]
 84%|████████▍ | 52172/61904 [4:08:55<3:45:56,  1.39s/it]
 84%|████████▍ | 52173/61904 [4:08:56<3:44:28,  1.38s/it]
 84%|████████▍ | 52174/61904 [4:08:58<3:42:47,  1.37s/it]
 84%|████████▍ | 52175/61904 [4:08:59<3:42:03,  1.37s/it]
 84%|████████▍ | 52176/61904 [4:09:00<3:42:50,  1.37s/it]
 84%|████████▍ | 52177/61904 [4:09:02<3:43:55,  1.38s/it]
 84%|████████▍ | 52178/61904 [4:09:03<3:42:25,  1.37s/it]
 84%|████████▍ | 52179/61904 [4:09:05<3:46:28,  1.40s/it]
 84%|████████▍ | 52180/61904 [4:09:06<3:45:41,  1.39s/it]
                                                         
{'loss': 2.4219, 'learning_rate': 1.1575910799948138e-07, 'epoch': 13.49}

 84%|████████▍ | 52180/61904 [4:09:06<3:45:41,  1.39s/it]
 84%|████████▍ | 52181/61904 [4:09:07<3:47:39,  1.40s/it]
 84%|████████▍ | 52182/61904 [4:09:09<3:48:11,  1.41s/it]
 84%|████████▍ | 52183/61904 [4:09:10<3:48:18,  1.41s/it]
 84%|████████▍ | 52184/61904 [4:09:12<3:46:16,  1.40s/it]
 84%|████████▍ | 52185/61904 [4:09:13<3:46:41,  1.40s/it]
 84%|████████▍ | 52186/61904 [4:09:14<3:45:11,  1.39s/it]
 84%|████████▍ | 52187/61904 [4:09:16<3:38:51,  1.35s/it]
 84%|████████▍ | 52188/61904 [4:09:17<3:37:33,  1.34s/it]
 84%|████████▍ | 52189/61904 [4:09:18<3:34:05,  1.32s/it]
 84%|████████▍ | 52190/61904 [4:09:20<3:37:49,  1.35s/it]
 84%|████████▍ | 52191/61904 [4:09:21<3:39:54,  1.36s/it]
 84%|████████▍ | 52192/61904 [4:09:23<3:44:50,  1.39s/it]
 84%|████████▍ | 52193/61904 [4:09:24<3:41:37,  1.37s/it]
 84%|████████▍ | 52194/61904 [4:09:25<3:41:31,  1.37s/it]
 84%|████████▍ | 52195/61904 [4:09:27<3:43:47,  1.38s/it]
 84%|████████▍ | 52196/61904 [4:09:28<3:40:56,  1.37s/it]
 84%|████████▍ | 52197/61904 [4:09:29<3:46:25,  1.40s/it]
 84%|████████▍ | 52198/61904 [4:09:31<3:48:21,  1.41s/it]
 84%|████████▍ | 52199/61904 [4:09:32<3:41:32,  1.37s/it]
 84%|████████▍ | 52200/61904 [4:09:33<3:34:50,  1.33s/it]
                                                         
{'loss': 2.4166, 'learning_rate': 1.1572669518993905e-07, 'epoch': 13.49}

 84%|████████▍ | 52200/61904 [4:09:33<3:34:50,  1.33s/it]
 84%|████████▍ | 52201/61904 [4:09:35<3:38:38,  1.35s/it]
 84%|████████▍ | 52202/61904 [4:09:36<3:37:41,  1.35s/it]
 84%|████████▍ | 52203/61904 [4:09:38<3:41:34,  1.37s/it]
 84%|████████▍ | 52204/61904 [4:09:39<3:40:47,  1.37s/it]
 84%|████████▍ | 52205/61904 [4:09:40<3:47:27,  1.41s/it]
 84%|████████▍ | 52206/61904 [4:09:42<3:48:09,  1.41s/it]
 84%|████████▍ | 52207/61904 [4:09:43<3:51:21,  1.43s/it]
 84%|████████▍ | 52208/61904 [4:09:45<3:48:45,  1.42s/it]
 84%|████████▍ | 52209/61904 [4:09:46<3:50:26,  1.43s/it]
 84%|████████▍ | 52210/61904 [4:09:47<3:43:26,  1.38s/it]
 84%|████████▍ | 52211/61904 [4:09:49<3:39:43,  1.36s/it]
 84%|████████▍ | 52212/61904 [4:09:50<3:39:48,  1.36s/it]
 84%|████████▍ | 52213/61904 [4:09:52<3:43:19,  1.38s/it]
 84%|████████▍ | 52214/61904 [4:09:53<3:43:41,  1.39s/it]
 84%|████████▍ | 52215/61904 [4:09:54<3:46:16,  1.40s/it]
 84%|████████▍ | 52216/61904 [4:09:56<3:37:22,  1.35s/it]
 84%|████████▍ | 52217/61904 [4:09:57<3:37:11,  1.35s/it]
 84%|████████▍ | 52218/61904 [4:09:58<3:46:27,  1.40s/it]
 84%|████████▍ | 52219/61904 [4:10:00<3:49:00,  1.42s/it]
 84%|████████▍ | 52220/61904 [4:10:01<3:42:59,  1.38s/it]
                                                         
{'loss': 2.456, 'learning_rate': 1.1569428238039671e-07, 'epoch': 13.5}

 84%|████████▍ | 52220/61904 [4:10:01<3:42:59,  1.38s/it]
 84%|████████▍ | 52221/61904 [4:10:03<3:39:45,  1.36s/it]
 84%|████████▍ | 52222/61904 [4:10:04<3:44:47,  1.39s/it]
 84%|████████▍ | 52223/61904 [4:10:05<3:43:59,  1.39s/it]
 84%|████████▍ | 52224/61904 [4:10:07<3:38:10,  1.35s/it]
 84%|████████▍ | 52225/61904 [4:10:08<3:35:10,  1.33s/it]
 84%|████████▍ | 52226/61904 [4:10:09<3:32:52,  1.32s/it]
 84%|████████▍ | 52227/61904 [4:10:11<3:33:19,  1.32s/it]
 84%|████████▍ | 52228/61904 [4:10:12<3:34:29,  1.33s/it]
 84%|████████▍ | 52229/61904 [4:10:13<3:38:33,  1.36s/it]
 84%|████████▍ | 52230/61904 [4:10:15<3:39:00,  1.36s/it]
 84%|████████▍ | 52231/61904 [4:10:16<3:38:47,  1.36s/it]
 84%|████████▍ | 52232/61904 [4:10:17<3:36:50,  1.35s/it]
 84%|████████▍ | 52233/61904 [4:10:19<3:42:42,  1.38s/it]
 84%|████████▍ | 52234/61904 [4:10:20<3:38:47,  1.36s/it]
 84%|████████▍ | 52235/61904 [4:10:22<3:40:49,  1.37s/it]
 84%|████████▍ | 52236/61904 [4:10:23<3:36:29,  1.34s/it]
 84%|████████▍ | 52237/61904 [4:10:24<3:34:41,  1.33s/it]
 84%|████████▍ | 52238/61904 [4:10:26<3:38:17,  1.36s/it]
 84%|████████▍ | 52239/61904 [4:10:27<3:41:53,  1.38s/it]
 84%|████████▍ | 52240/61904 [4:10:28<3:40:06,  1.37s/it]
                                                         
{'loss': 2.4335, 'learning_rate': 1.156618695708544e-07, 'epoch': 13.5}

 84%|████████▍ | 52240/61904 [4:10:28<3:40:06,  1.37s/it]
 84%|████████▍ | 52241/61904 [4:10:30<3:36:20,  1.34s/it]
 84%|████████▍ | 52242/61904 [4:10:31<3:35:47,  1.34s/it]
 84%|████████▍ | 52243/61904 [4:10:32<3:43:18,  1.39s/it]
 84%|████████▍ | 52244/61904 [4:10:34<3:42:24,  1.38s/it]
 84%|████████▍ | 52245/61904 [4:10:35<3:44:17,  1.39s/it]
 84%|████████▍ | 52246/61904 [4:10:36<3:38:29,  1.36s/it]
 84%|████████▍ | 52247/61904 [4:10:38<3:43:53,  1.39s/it]
 84%|████████▍ | 52248/61904 [4:10:39<3:45:46,  1.40s/it]
 84%|████████▍ | 52249/61904 [4:10:41<3:49:27,  1.43s/it]
 84%|████████▍ | 52250/61904 [4:10:42<3:48:08,  1.42s/it]
 84%|████████▍ | 52251/61904 [4:10:44<3:45:24,  1.40s/it]
 84%|████████▍ | 52252/61904 [4:10:45<3:46:44,  1.41s/it]
 84%|████████▍ | 52253/61904 [4:10:46<3:46:15,  1.41s/it]
 84%|████████▍ | 52254/61904 [4:10:48<3:43:45,  1.39s/it]
 84%|████████▍ | 52255/61904 [4:10:49<3:39:00,  1.36s/it]
 84%|████████▍ | 52256/61904 [4:10:50<3:41:14,  1.38s/it]
 84%|████████▍ | 52257/61904 [4:10:52<3:42:28,  1.38s/it]
 84%|████████▍ | 52258/61904 [4:10:53<3:45:53,  1.41s/it]
 84%|████████▍ | 52259/61904 [4:10:55<3:50:17,  1.43s/it]
 84%|████████▍ | 52260/61904 [4:10:56<3:42:51,  1.39s/it]
                                                         
{'loss': 2.4549, 'learning_rate': 1.1562945676131206e-07, 'epoch': 13.51}

 84%|████████▍ | 52260/61904 [4:10:56<3:42:51,  1.39s/it]
 84%|████████▍ | 52261/61904 [4:10:58<3:43:05,  1.39s/it]
 84%|████████▍ | 52262/61904 [4:10:59<3:39:02,  1.36s/it]
 84%|████████▍ | 52263/61904 [4:11:00<3:41:11,  1.38s/it]
 84%|████████▍ | 52264/61904 [4:11:02<3:37:28,  1.35s/it]
 84%|████████▍ | 52265/61904 [4:11:03<3:37:00,  1.35s/it]
 84%|████████▍ | 52266/61904 [4:11:04<3:41:57,  1.38s/it]
 84%|████████▍ | 52267/61904 [4:11:06<3:35:45,  1.34s/it]
 84%|████████▍ | 52268/61904 [4:11:07<3:41:32,  1.38s/it]
 84%|████████▍ | 52269/61904 [4:11:09<3:48:13,  1.42s/it]
 84%|████████▍ | 52270/61904 [4:11:10<3:50:23,  1.43s/it]
 84%|████████▍ | 52271/61904 [4:11:11<3:47:57,  1.42s/it]
 84%|████████▍ | 52272/61904 [4:11:13<3:48:55,  1.43s/it]
 84%|████████▍ | 52273/61904 [4:11:14<3:45:43,  1.41s/it]
 84%|████████▍ | 52274/61904 [4:11:16<3:45:30,  1.41s/it]
 84%|████████▍ | 52275/61904 [4:11:17<3:42:35,  1.39s/it]
 84%|████████▍ | 52276/61904 [4:11:18<3:41:41,  1.38s/it]
 84%|████████▍ | 52277/61904 [4:11:20<3:49:14,  1.43s/it]
 84%|████████▍ | 52278/61904 [4:11:21<3:47:35,  1.42s/it]
 84%|████████▍ | 52279/61904 [4:11:23<3:42:16,  1.39s/it]
 84%|████████▍ | 52280/61904 [4:11:24<3:47:27,  1.42s/it]
                                                         
{'loss': 2.4274, 'learning_rate': 1.1559704395176972e-07, 'epoch': 13.51}

 84%|████████▍ | 52280/61904 [4:11:24<3:47:27,  1.42s/it]
 84%|████████▍ | 52281/61904 [4:11:25<3:43:38,  1.39s/it]
 84%|████████▍ | 52282/61904 [4:11:27<3:40:26,  1.37s/it]
 84%|████████▍ | 52283/61904 [4:11:28<3:35:25,  1.34s/it]
 84%|████████▍ | 52284/61904 [4:11:29<3:33:03,  1.33s/it]
 84%|████████▍ | 52285/61904 [4:11:31<3:37:18,  1.36s/it]
 84%|████████▍ | 52286/61904 [4:11:32<3:41:51,  1.38s/it]
 84%|████████▍ | 52287/61904 [4:11:34<3:42:06,  1.39s/it]
 84%|████████▍ | 52288/61904 [4:11:35<3:42:35,  1.39s/it]
 84%|████████▍ | 52289/61904 [4:11:36<3:42:22,  1.39s/it]
 84%|████████▍ | 52290/61904 [4:11:38<3:41:01,  1.38s/it]
 84%|████████▍ | 52291/61904 [4:11:39<3:36:02,  1.35s/it]
 84%|████████▍ | 52292/61904 [4:11:40<3:32:46,  1.33s/it]
 84%|████████▍ | 52293/61904 [4:11:42<3:42:27,  1.39s/it]
 84%|████████▍ | 52294/61904 [4:11:43<3:34:43,  1.34s/it]
 84%|████████▍ | 52295/61904 [4:11:44<3:39:46,  1.37s/it]
 84%|████████▍ | 52296/61904 [4:11:46<3:35:52,  1.35s/it]
 84%|████████▍ | 52297/61904 [4:11:47<3:34:34,  1.34s/it]
 84%|████████▍ | 52298/61904 [4:11:49<3:39:18,  1.37s/it]
 84%|████████▍ | 52299/61904 [4:11:50<3:42:56,  1.39s/it]
 84%|████████▍ | 52300/61904 [4:11:51<3:34:57,  1.34s/it]
                                                         
{'loss': 2.4509, 'learning_rate': 1.1556463114222738e-07, 'epoch': 13.52}

 84%|████████▍ | 52300/61904 [4:11:51<3:34:57,  1.34s/it]
 84%|████████▍ | 52301/61904 [4:11:53<3:36:06,  1.35s/it]
 84%|████████▍ | 52302/61904 [4:11:54<3:41:47,  1.39s/it]
 84%|████████▍ | 52303/61904 [4:11:56<3:52:05,  1.45s/it]
 84%|████████▍ | 52304/61904 [4:11:57<3:48:51,  1.43s/it]
 84%|████████▍ | 52305/61904 [4:11:58<3:50:10,  1.44s/it]
 84%|████████▍ | 52306/61904 [4:12:00<3:41:45,  1.39s/it]
 84%|████████▍ | 52307/61904 [4:12:01<3:39:01,  1.37s/it]
 84%|████████▍ | 52308/61904 [4:12:03<3:52:05,  1.45s/it]
 85%|████████▍ | 52309/61904 [4:12:04<3:44:06,  1.40s/it]
 85%|████████▍ | 52310/61904 [4:12:05<3:37:19,  1.36s/it]
 85%|████████▍ | 52311/61904 [4:12:07<3:40:30,  1.38s/it]
 85%|████████▍ | 52312/61904 [4:12:08<3:34:38,  1.34s/it]
 85%|████████▍ | 52313/61904 [4:12:09<3:33:29,  1.34s/it]
 85%|████████▍ | 52314/61904 [4:12:11<3:30:26,  1.32s/it]
 85%|████████▍ | 52315/61904 [4:12:12<3:29:19,  1.31s/it]
 85%|████████▍ | 52316/61904 [4:12:13<3:34:06,  1.34s/it]
 85%|████████▍ | 52317/61904 [4:12:14<3:26:25,  1.29s/it]
 85%|████████▍ | 52318/61904 [4:12:16<3:33:31,  1.34s/it]
 85%|████████▍ | 52319/61904 [4:12:17<3:35:25,  1.35s/it]
 85%|████████▍ | 52320/61904 [4:12:19<3:39:31,  1.37s/it]
                                                         
{'loss': 2.4466, 'learning_rate': 1.1553221833268507e-07, 'epoch': 13.52}

 85%|████████▍ | 52320/61904 [4:12:19<3:39:31,  1.37s/it]
 85%|████████▍ | 52321/61904 [4:12:20<3:48:36,  1.43s/it]
 85%|████████▍ | 52322/61904 [4:12:22<3:47:05,  1.42s/it]
 85%|████████▍ | 52323/61904 [4:12:23<3:39:12,  1.37s/it]
 85%|████████▍ | 52324/61904 [4:12:24<3:40:53,  1.38s/it]
 85%|████████▍ | 52325/61904 [4:12:26<3:36:33,  1.36s/it]
 85%|████████▍ | 52326/61904 [4:12:27<3:39:22,  1.37s/it]
 85%|████████▍ | 52327/61904 [4:12:29<3:58:07,  1.49s/it]
 85%|████████▍ | 52328/61904 [4:12:30<3:51:06,  1.45s/it]
 85%|████████▍ | 52329/61904 [4:12:32<3:48:53,  1.43s/it]
 85%|████████▍ | 52330/61904 [4:12:33<3:51:14,  1.45s/it]
 85%|████████▍ | 52331/61904 [4:12:34<3:47:05,  1.42s/it]
 85%|████████▍ | 52332/61904 [4:12:36<3:38:00,  1.37s/it]
 85%|████████▍ | 52333/61904 [4:12:37<3:47:21,  1.43s/it]
 85%|████████▍ | 52334/61904 [4:12:39<3:45:21,  1.41s/it]
 85%|████████▍ | 52335/61904 [4:12:40<3:38:05,  1.37s/it]
 85%|████████▍ | 52336/61904 [4:12:41<3:36:37,  1.36s/it]
 85%|████████▍ | 52337/61904 [4:12:43<3:57:05,  1.49s/it]
 85%|████████▍ | 52338/61904 [4:12:44<3:52:06,  1.46s/it]
 85%|████████▍ | 52339/61904 [4:12:46<3:48:31,  1.43s/it]
 85%|████████▍ | 52340/61904 [4:12:47<3:49:48,  1.44s/it]
                                                         
{'loss': 2.486, 'learning_rate': 1.1549980552314273e-07, 'epoch': 13.53}

 85%|████████▍ | 52340/61904 [4:12:47<3:49:48,  1.44s/it]
 85%|████████▍ | 52341/61904 [4:12:49<3:52:42,  1.46s/it]
 85%|████████▍ | 52342/61904 [4:12:50<3:51:33,  1.45s/it]
 85%|████████▍ | 52343/61904 [4:12:51<3:45:25,  1.41s/it]
 85%|████████▍ | 52344/61904 [4:12:53<3:43:22,  1.40s/it]
 85%|████████▍ | 52345/61904 [4:12:54<3:41:15,  1.39s/it]
 85%|████████▍ | 52346/61904 [4:12:56<3:41:41,  1.39s/it]
 85%|████████▍ | 52347/61904 [4:12:57<3:45:46,  1.42s/it]
 85%|████████▍ | 52348/61904 [4:12:58<3:43:56,  1.41s/it]
 85%|████████▍ | 52349/61904 [4:13:00<3:43:13,  1.40s/it]
 85%|████████▍ | 52350/61904 [4:13:01<3:38:33,  1.37s/it]
 85%|████████▍ | 52351/61904 [4:13:02<3:35:56,  1.36s/it]
 85%|████████▍ | 52352/61904 [4:13:04<3:37:38,  1.37s/it]
 85%|████████▍ | 52353/61904 [4:13:05<3:41:07,  1.39s/it]
 85%|████████▍ | 52354/61904 [4:13:07<3:37:00,  1.36s/it]
 85%|████████▍ | 52355/61904 [4:13:08<3:38:42,  1.37s/it]
 85%|████████▍ | 52356/61904 [4:13:09<3:33:20,  1.34s/it]
 85%|████████▍ | 52357/61904 [4:13:11<3:33:50,  1.34s/it]
 85%|████████▍ | 52358/61904 [4:13:12<3:39:41,  1.38s/it]
 85%|████████▍ | 52359/61904 [4:13:13<3:35:17,  1.35s/it]
 85%|████████▍ | 52360/61904 [4:13:15<3:40:01,  1.38s/it]
                                                         
{'loss': 2.4423, 'learning_rate': 1.1546739271360039e-07, 'epoch': 13.53}

 85%|████████▍ | 52360/61904 [4:13:15<3:40:01,  1.38s/it]
 85%|████████▍ | 52361/61904 [4:13:16<3:37:45,  1.37s/it]
 85%|████████▍ | 52362/61904 [4:13:18<3:43:00,  1.40s/it]
 85%|████████▍ | 52363/61904 [4:13:19<3:39:43,  1.38s/it]
 85%|████████▍ | 52364/61904 [4:13:20<3:32:26,  1.34s/it]
 85%|████████▍ | 52365/61904 [4:13:22<3:33:10,  1.34s/it]
 85%|████████▍ | 52366/61904 [4:13:23<3:41:24,  1.39s/it]
 85%|████████▍ | 52367/61904 [4:13:24<3:40:13,  1.39s/it]
 85%|████████▍ | 52368/61904 [4:13:26<3:38:18,  1.37s/it]
 85%|████████▍ | 52369/61904 [4:13:27<3:37:08,  1.37s/it]
 85%|████████▍ | 52370/61904 [4:13:28<3:32:43,  1.34s/it]
 85%|████████▍ | 52371/61904 [4:13:30<3:37:17,  1.37s/it]
 85%|████████▍ | 52372/61904 [4:13:31<3:32:57,  1.34s/it]
 85%|████████▍ | 52373/61904 [4:13:32<3:28:41,  1.31s/it]
 85%|████████▍ | 52374/61904 [4:13:34<3:37:35,  1.37s/it]
 85%|████████▍ | 52375/61904 [4:13:35<3:39:51,  1.38s/it]
 85%|████████▍ | 52376/61904 [4:13:37<3:41:53,  1.40s/it]
 85%|████████▍ | 52377/61904 [4:13:38<3:41:38,  1.40s/it]
 85%|████████▍ | 52378/61904 [4:13:39<3:43:22,  1.41s/it]
 85%|████████▍ | 52379/61904 [4:13:41<3:35:33,  1.36s/it]
 85%|████████▍ | 52380/61904 [4:13:42<3:35:22,  1.36s/it]
                                                         
{'loss': 2.3907, 'learning_rate': 1.1543497990405808e-07, 'epoch': 13.54}

 85%|████████▍ | 52380/61904 [4:13:42<3:35:22,  1.36s/it]
 85%|████████▍ | 52381/61904 [4:13:43<3:34:31,  1.35s/it]
 85%|████████▍ | 52382/61904 [4:13:45<3:35:30,  1.36s/it]
 85%|████████▍ | 52383/61904 [4:13:46<3:43:32,  1.41s/it]
 85%|████████▍ | 52384/61904 [4:13:48<3:38:28,  1.38s/it]
 85%|████████▍ | 52385/61904 [4:13:49<3:37:01,  1.37s/it]
 85%|████████▍ | 52386/61904 [4:13:50<3:44:13,  1.41s/it]
 85%|████████▍ | 52387/61904 [4:13:52<3:43:53,  1.41s/it]
 85%|████████▍ | 52388/61904 [4:13:53<3:39:56,  1.39s/it]
 85%|████████▍ | 52389/61904 [4:13:55<3:50:11,  1.45s/it]
 85%|████████▍ | 52390/61904 [4:13:56<3:48:35,  1.44s/it]
 85%|████████▍ | 52391/61904 [4:13:58<3:39:24,  1.38s/it]
 85%|████████▍ | 52392/61904 [4:13:59<3:42:58,  1.41s/it]
 85%|████████▍ | 52393/61904 [4:14:00<3:44:03,  1.41s/it]
 85%|████████▍ | 52394/61904 [4:14:02<3:37:24,  1.37s/it]
 85%|████████▍ | 52395/61904 [4:14:03<3:37:06,  1.37s/it]
 85%|████████▍ | 52396/61904 [4:14:04<3:31:02,  1.33s/it]
 85%|████████▍ | 52397/61904 [4:14:06<3:29:36,  1.32s/it]
 85%|████████▍ | 52398/61904 [4:14:07<3:28:02,  1.31s/it]
 85%|████████▍ | 52399/61904 [4:14:08<3:30:49,  1.33s/it]
 85%|████████▍ | 52400/61904 [4:14:10<3:46:45,  1.43s/it]
                                                         
{'loss': 2.4323, 'learning_rate': 1.1540256709451574e-07, 'epoch': 13.54}

 85%|████████▍ | 52400/61904 [4:14:10<3:46:45,  1.43s/it]
 85%|████████▍ | 52401/61904 [4:14:11<3:39:37,  1.39s/it]
 85%|████████▍ | 52402/61904 [4:14:13<3:37:05,  1.37s/it]
 85%|████████▍ | 52403/61904 [4:14:14<3:39:08,  1.38s/it]
 85%|████████▍ | 52404/61904 [4:14:15<3:33:26,  1.35s/it]
 85%|████████▍ | 52405/61904 [4:14:17<3:36:29,  1.37s/it]
 85%|████████▍ | 52406/61904 [4:14:18<3:30:43,  1.33s/it]
 85%|████████▍ | 52407/61904 [4:14:19<3:32:56,  1.35s/it]
 85%|████████▍ | 52408/61904 [4:14:21<3:29:42,  1.32s/it]
 85%|████████▍ | 52409/61904 [4:14:22<3:27:59,  1.31s/it]
 85%|████████▍ | 52410/61904 [4:14:23<3:29:20,  1.32s/it]
 85%|████████▍ | 52411/61904 [4:14:24<3:29:22,  1.32s/it]
 85%|████████▍ | 52412/61904 [4:14:26<3:31:17,  1.34s/it]
 85%|████████▍ | 52413/61904 [4:14:27<3:38:40,  1.38s/it]
 85%|████████▍ | 52414/61904 [4:14:29<3:36:04,  1.37s/it]
 85%|████████▍ | 52415/61904 [4:14:30<3:36:01,  1.37s/it]
 85%|████████▍ | 52416/61904 [4:14:31<3:31:05,  1.33s/it]
 85%|████████▍ | 52417/61904 [4:14:33<3:32:54,  1.35s/it]
 85%|████████▍ | 52418/61904 [4:14:34<3:39:03,  1.39s/it]
 85%|████████▍ | 52419/61904 [4:14:35<3:33:30,  1.35s/it]
 85%|████████▍ | 52420/61904 [4:14:37<3:36:47,  1.37s/it]
                                                         
{'loss': 2.4375, 'learning_rate': 1.153701542849734e-07, 'epoch': 13.55}

 85%|████████▍ | 52420/61904 [4:14:37<3:36:47,  1.37s/it]
 85%|████████▍ | 52421/61904 [4:14:38<3:37:32,  1.38s/it]
 85%|████████▍ | 52422/61904 [4:14:40<3:39:43,  1.39s/it]
 85%|████████▍ | 52423/61904 [4:14:41<3:39:27,  1.39s/it]
 85%|████████▍ | 52424/61904 [4:14:43<3:44:11,  1.42s/it]
 85%|████████▍ | 52425/61904 [4:14:44<3:38:24,  1.38s/it]
 85%|████████▍ | 52426/61904 [4:14:45<3:39:50,  1.39s/it]
 85%|████████▍ | 52427/61904 [4:14:47<3:44:27,  1.42s/it]
 85%|████████▍ | 52428/61904 [4:14:48<3:48:22,  1.45s/it]
 85%|████████▍ | 52429/61904 [4:14:50<3:43:29,  1.42s/it]
 85%|████████▍ | 52430/61904 [4:14:51<3:43:30,  1.42s/it]
 85%|████████▍ | 52431/61904 [4:14:52<3:43:32,  1.42s/it]
 85%|████████▍ | 52432/61904 [4:14:54<3:45:28,  1.43s/it]
 85%|████████▍ | 52433/61904 [4:14:55<3:38:00,  1.38s/it]
 85%|████████▍ | 52434/61904 [4:14:56<3:36:21,  1.37s/it]
 85%|████████▍ | 52435/61904 [4:14:58<3:35:05,  1.36s/it]
 85%|████████▍ | 52436/61904 [4:14:59<3:33:22,  1.35s/it]
 85%|████████▍ | 52437/61904 [4:15:00<3:33:16,  1.35s/it]
 85%|████████▍ | 52438/61904 [4:15:02<3:30:41,  1.34s/it]
 85%|████████▍ | 52439/61904 [4:15:03<3:39:27,  1.39s/it]
 85%|████████▍ | 52440/61904 [4:15:05<3:33:08,  1.35s/it]
                                                         
{'loss': 2.4197, 'learning_rate': 1.1533774147543107e-07, 'epoch': 13.55}

 85%|████████▍ | 52440/61904 [4:15:05<3:33:08,  1.35s/it]
 85%|████████▍ | 52441/61904 [4:15:06<3:38:02,  1.38s/it]
 85%|████████▍ | 52442/61904 [4:15:07<3:36:06,  1.37s/it]
 85%|████████▍ | 52443/61904 [4:15:09<3:40:58,  1.40s/it]
 85%|████████▍ | 52444/61904 [4:15:10<3:44:10,  1.42s/it]
 85%|████████▍ | 52445/61904 [4:15:12<3:42:37,  1.41s/it]
 85%|████████▍ | 52446/61904 [4:15:13<3:41:49,  1.41s/it]
 85%|████████▍ | 52447/61904 [4:15:14<3:39:13,  1.39s/it]
 85%|████████▍ | 52448/61904 [4:15:16<3:41:29,  1.41s/it]
 85%|████████▍ | 52449/61904 [4:15:17<3:39:59,  1.40s/it]
 85%|████████▍ | 52450/61904 [4:15:19<3:40:51,  1.40s/it]
 85%|████████▍ | 52451/61904 [4:15:20<3:37:01,  1.38s/it]
 85%|████████▍ | 52452/61904 [4:15:21<3:33:01,  1.35s/it]
 85%|████████▍ | 52453/61904 [4:15:23<3:35:44,  1.37s/it]
 85%|████████▍ | 52454/61904 [4:15:24<3:41:34,  1.41s/it]
 85%|████████▍ | 52455/61904 [4:15:26<3:45:43,  1.43s/it]
 85%|████████▍ | 52456/61904 [4:15:27<3:45:00,  1.43s/it]
 85%|████████▍ | 52457/61904 [4:15:29<3:48:32,  1.45s/it]
 85%|████████▍ | 52458/61904 [4:15:30<3:52:23,  1.48s/it]
 85%|████████▍ | 52459/61904 [4:15:31<3:45:37,  1.43s/it]
 85%|████████▍ | 52460/61904 [4:15:33<3:39:10,  1.39s/it]
                                                         
{'loss': 2.4902, 'learning_rate': 1.1530532866588876e-07, 'epoch': 13.56}

 85%|████████▍ | 52460/61904 [4:15:33<3:39:10,  1.39s/it]
 85%|████████▍ | 52461/61904 [4:15:34<3:36:32,  1.38s/it]
 85%|████████▍ | 52462/61904 [4:15:35<3:31:21,  1.34s/it]
 85%|████████▍ | 52463/61904 [4:15:37<3:32:57,  1.35s/it]
 85%|████████▍ | 52464/61904 [4:15:38<3:36:19,  1.37s/it]
 85%|████████▍ | 52465/61904 [4:15:40<3:42:57,  1.42s/it]
 85%|████████▍ | 52466/61904 [4:15:41<3:40:53,  1.40s/it]
 85%|████████▍ | 52467/61904 [4:15:42<3:38:05,  1.39s/it]
 85%|████████▍ | 52468/61904 [4:15:44<3:41:09,  1.41s/it]
 85%|████████▍ | 52469/61904 [4:15:45<3:41:26,  1.41s/it]
 85%|████████▍ | 52470/61904 [4:15:47<3:44:24,  1.43s/it]
 85%|████████▍ | 52471/61904 [4:15:48<3:40:43,  1.40s/it]
 85%|████████▍ | 52472/61904 [4:15:50<3:42:16,  1.41s/it]
 85%|████████▍ | 52473/61904 [4:15:51<3:39:26,  1.40s/it]
 85%|████████▍ | 52474/61904 [4:15:52<3:44:32,  1.43s/it]
 85%|████████▍ | 52475/61904 [4:15:54<3:40:05,  1.40s/it]
 85%|████████▍ | 52476/61904 [4:15:55<3:37:35,  1.38s/it]
 85%|████████▍ | 52477/61904 [4:15:56<3:36:08,  1.38s/it]
 85%|████████▍ | 52478/61904 [4:15:58<3:26:59,  1.32s/it]
 85%|████████▍ | 52479/61904 [4:15:59<3:28:18,  1.33s/it]
 85%|████████▍ | 52480/61904 [4:16:00<3:29:45,  1.34s/it]
                                                         
{'loss': 2.4065, 'learning_rate': 1.1527291585634642e-07, 'epoch': 13.56}

 85%|████████▍ | 52480/61904 [4:16:00<3:29:45,  1.34s/it]
 85%|████████▍ | 52481/61904 [4:16:02<3:34:36,  1.37s/it]
 85%|████████▍ | 52482/61904 [4:16:03<3:38:23,  1.39s/it]
 85%|████████▍ | 52483/61904 [4:16:05<3:41:34,  1.41s/it]
 85%|████████▍ | 52484/61904 [4:16:06<3:35:08,  1.37s/it]
 85%|████████▍ | 52485/61904 [4:16:07<3:35:47,  1.37s/it]
 85%|████████▍ | 52486/61904 [4:16:09<3:34:49,  1.37s/it]
 85%|████████▍ | 52487/61904 [4:16:10<3:26:12,  1.31s/it]
 85%|████████▍ | 52488/61904 [4:16:11<3:30:43,  1.34s/it]
 85%|████████▍ | 52489/61904 [4:16:13<3:26:32,  1.32s/it]
 85%|████████▍ | 52490/61904 [4:16:14<3:24:58,  1.31s/it]
 85%|████████▍ | 52491/61904 [4:16:15<3:38:14,  1.39s/it]
 85%|████████▍ | 52492/61904 [4:16:17<3:34:37,  1.37s/it]
 85%|████████▍ | 52493/61904 [4:16:18<3:35:13,  1.37s/it]
 85%|████████▍ | 52494/61904 [4:16:20<3:42:06,  1.42s/it]
 85%|████████▍ | 52495/61904 [4:16:21<3:38:36,  1.39s/it]
 85%|████████▍ | 52496/61904 [4:16:22<3:40:36,  1.41s/it]
 85%|████████▍ | 52497/61904 [4:16:24<3:42:55,  1.42s/it]
 85%|████████▍ | 52498/61904 [4:16:25<3:37:13,  1.39s/it]
 85%|████████▍ | 52499/61904 [4:16:26<3:35:09,  1.37s/it]
 85%|████████▍ | 52500/61904 [4:16:28<3:36:52,  1.38s/it]
                                                         
{'loss': 2.4606, 'learning_rate': 1.1524050304680408e-07, 'epoch': 13.57}

 85%|████████▍ | 52500/61904 [4:16:28<3:36:52,  1.38s/it]
 85%|████████▍ | 52501/61904 [4:16:29<3:37:46,  1.39s/it]
 85%|████████▍ | 52502/61904 [4:16:31<3:36:48,  1.38s/it]
 85%|████████▍ | 52503/61904 [4:16:32<3:35:34,  1.38s/it]
 85%|████████▍ | 52504/61904 [4:16:33<3:39:02,  1.40s/it]
 85%|████████▍ | 52505/61904 [4:16:35<3:42:13,  1.42s/it]
 85%|████████▍ | 52506/61904 [4:16:36<3:35:46,  1.38s/it]
 85%|████████▍ | 52507/61904 [4:16:37<3:28:47,  1.33s/it]
 85%|████████▍ | 52508/61904 [4:16:39<3:28:27,  1.33s/it]
 85%|████████▍ | 52509/61904 [4:16:40<3:36:43,  1.38s/it]
 85%|████████▍ | 52510/61904 [4:16:42<3:45:56,  1.44s/it]
 85%|████████▍ | 52511/61904 [4:16:43<3:48:50,  1.46s/it]
 85%|████████▍ | 52512/61904 [4:16:45<3:54:32,  1.50s/it]
 85%|████████▍ | 52513/61904 [4:16:46<3:42:12,  1.42s/it]
 85%|████████▍ | 52514/61904 [4:16:47<3:32:08,  1.36s/it]
 85%|████████▍ | 52515/61904 [4:16:49<3:32:37,  1.36s/it]
 85%|████████▍ | 52516/61904 [4:16:50<3:35:19,  1.38s/it]
 85%|████████▍ | 52517/61904 [4:16:52<3:32:29,  1.36s/it]
 85%|████████▍ | 52518/61904 [4:16:53<3:36:43,  1.39s/it]
 85%|████████▍ | 52519/61904 [4:16:54<3:42:38,  1.42s/it]
 85%|████████▍ | 52520/61904 [4:16:56<3:41:02,  1.41s/it]
                                                         
{'loss': 2.4576, 'learning_rate': 1.1520809023726174e-07, 'epoch': 13.57}

 85%|████████▍ | 52520/61904 [4:16:56<3:41:02,  1.41s/it]
 85%|████████▍ | 52521/61904 [4:16:57<3:49:50,  1.47s/it]
 85%|████████▍ | 52522/61904 [4:16:59<3:43:23,  1.43s/it]
 85%|████████▍ | 52523/61904 [4:17:00<3:40:28,  1.41s/it]
 85%|████████▍ | 52524/61904 [4:17:02<3:38:23,  1.40s/it]
 85%|████████▍ | 52525/61904 [4:17:03<3:36:28,  1.38s/it]
 85%|████████▍ | 52526/61904 [4:17:04<3:42:07,  1.42s/it]
 85%|████████▍ | 52527/61904 [4:17:06<3:42:14,  1.42s/it]
 85%|████████▍ | 52528/61904 [4:17:07<3:37:47,  1.39s/it]
 85%|████████▍ | 52529/61904 [4:17:08<3:35:04,  1.38s/it]
 85%|████████▍ | 52530/61904 [4:17:10<3:29:18,  1.34s/it]
 85%|████████▍ | 52531/61904 [4:17:11<3:30:44,  1.35s/it]
 85%|████████▍ | 52532/61904 [4:17:12<3:29:05,  1.34s/it]
 85%|████████▍ | 52533/61904 [4:17:14<3:34:26,  1.37s/it]
 85%|████████▍ | 52534/61904 [4:17:15<3:33:57,  1.37s/it]
 85%|████████▍ | 52535/61904 [4:17:17<3:37:55,  1.40s/it]
 85%|████████▍ | 52536/61904 [4:17:18<3:34:37,  1.37s/it]
 85%|████████▍ | 52537/61904 [4:17:19<3:38:30,  1.40s/it]
 85%|████████▍ | 52538/61904 [4:17:21<3:38:44,  1.40s/it]
 85%|████████▍ | 52539/61904 [4:17:22<3:34:45,  1.38s/it]
 85%|████████▍ | 52540/61904 [4:17:23<3:31:12,  1.35s/it]
                                                         
{'loss': 2.4596, 'learning_rate': 1.1517567742771943e-07, 'epoch': 13.58}

 85%|████████▍ | 52540/61904 [4:17:23<3:31:12,  1.35s/it]
 85%|████████▍ | 52541/61904 [4:17:25<3:35:08,  1.38s/it]
 85%|████████▍ | 52542/61904 [4:17:26<3:29:57,  1.35s/it]
 85%|████████▍ | 52543/61904 [4:17:28<3:32:30,  1.36s/it]
 85%|████████▍ | 52544/61904 [4:17:29<3:36:34,  1.39s/it]
 85%|████████▍ | 52545/61904 [4:17:30<3:35:20,  1.38s/it]
 85%|████████▍ | 52546/61904 [4:17:32<3:42:48,  1.43s/it]
 85%|████████▍ | 52547/61904 [4:17:33<3:41:46,  1.42s/it]
 85%|████████▍ | 52548/61904 [4:17:35<3:34:43,  1.38s/it]
 85%|████████▍ | 52549/61904 [4:17:36<3:32:59,  1.37s/it]
 85%|████████▍ | 52550/61904 [4:17:37<3:31:59,  1.36s/it]
 85%|████████▍ | 52551/61904 [4:17:39<3:25:18,  1.32s/it]
 85%|████████▍ | 52552/61904 [4:17:40<3:32:25,  1.36s/it]
 85%|████████▍ | 52553/61904 [4:17:41<3:37:01,  1.39s/it]
 85%|████████▍ | 52554/61904 [4:17:43<3:36:13,  1.39s/it]
 85%|████████▍ | 52555/61904 [4:17:44<3:39:08,  1.41s/it]
 85%|████████▍ | 52556/61904 [4:17:46<3:41:16,  1.42s/it]
 85%|████████▍ | 52557/61904 [4:17:47<3:39:01,  1.41s/it]
 85%|████████▍ | 52558/61904 [4:17:49<3:38:33,  1.40s/it]
 85%|████████▍ | 52559/61904 [4:17:50<3:40:56,  1.42s/it]
 85%|████████▍ | 52560/61904 [4:17:51<3:41:35,  1.42s/it]
                                                         
{'loss': 2.4678, 'learning_rate': 1.1514326461817709e-07, 'epoch': 13.58}

 85%|████████▍ | 52560/61904 [4:17:51<3:41:35,  1.42s/it]
 85%|████████▍ | 52561/61904 [4:17:53<3:47:19,  1.46s/it]
 85%|████████▍ | 52562/61904 [4:17:54<3:44:46,  1.44s/it]
 85%|████████▍ | 52563/61904 [4:17:56<3:39:40,  1.41s/it]
 85%|████████▍ | 52564/61904 [4:17:57<3:41:01,  1.42s/it]
 85%|████████▍ | 52565/61904 [4:17:58<3:35:46,  1.39s/it]
 85%|████████▍ | 52566/61904 [4:18:00<3:36:47,  1.39s/it]
 85%|████████▍ | 52567/61904 [4:18:01<3:35:43,  1.39s/it]
 85%|████████▍ | 52568/61904 [4:18:03<3:37:34,  1.40s/it]
 85%|████████▍ | 52569/61904 [4:18:04<3:32:38,  1.37s/it]
 85%|████████▍ | 52570/61904 [4:18:05<3:41:43,  1.43s/it]
 85%|████████▍ | 52571/61904 [4:18:07<3:41:42,  1.43s/it]
 85%|████████▍ | 52572/61904 [4:18:08<3:37:21,  1.40s/it]
 85%|████████▍ | 52573/61904 [4:18:10<3:35:34,  1.39s/it]
 85%|████████▍ | 52574/61904 [4:18:11<3:41:13,  1.42s/it]
 85%|████████▍ | 52575/61904 [4:18:13<3:45:43,  1.45s/it]
 85%|████████▍ | 52576/61904 [4:18:14<3:52:40,  1.50s/it]
 85%|████████▍ | 52577/61904 [4:18:16<3:46:52,  1.46s/it]
 85%|████████▍ | 52578/61904 [4:18:17<3:47:34,  1.46s/it]
 85%|████████▍ | 52579/61904 [4:18:19<3:55:18,  1.51s/it]
 85%|████████▍ | 52580/61904 [4:18:20<3:50:26,  1.48s/it]
                                                         
{'loss': 2.4333, 'learning_rate': 1.1511085180863475e-07, 'epoch': 13.59}

 85%|████████▍ | 52580/61904 [4:18:20<3:50:26,  1.48s/it]
 85%|████████▍ | 52581/61904 [4:18:21<3:43:42,  1.44s/it]
 85%|████████▍ | 52582/61904 [4:18:23<3:35:38,  1.39s/it]
 85%|████████▍ | 52583/61904 [4:18:24<3:37:13,  1.40s/it]
 85%|████████▍ | 52584/61904 [4:18:26<3:36:11,  1.39s/it]
 85%|████████▍ | 52585/61904 [4:18:27<3:43:17,  1.44s/it]
 85%|████████▍ | 52586/61904 [4:18:29<3:46:05,  1.46s/it]
 85%|████████▍ | 52587/61904 [4:18:30<3:39:01,  1.41s/it]
 85%|████████▍ | 52588/61904 [4:18:31<3:37:10,  1.40s/it]
 85%|████████▍ | 52589/61904 [4:18:33<3:31:39,  1.36s/it]
 85%|████████▍ | 52590/61904 [4:18:34<3:32:21,  1.37s/it]
 85%|████████▍ | 52591/61904 [4:18:35<3:33:13,  1.37s/it]
 85%|████████▍ | 52592/61904 [4:18:37<3:31:00,  1.36s/it]
 85%|████████▍ | 52593/61904 [4:18:38<3:33:18,  1.37s/it]
 85%|████████▍ | 52594/61904 [4:18:40<3:43:00,  1.44s/it]
 85%|████████▍ | 52595/61904 [4:18:41<3:42:49,  1.44s/it]
 85%|████████▍ | 52596/61904 [4:18:42<3:39:30,  1.41s/it]
 85%|████████▍ | 52597/61904 [4:18:44<3:38:17,  1.41s/it]
 85%|████████▍ | 52598/61904 [4:18:45<3:34:40,  1.38s/it]
 85%|████████▍ | 52599/61904 [4:18:47<3:41:16,  1.43s/it]
 85%|████████▍ | 52600/61904 [4:18:48<3:38:53,  1.41s/it]
                                                         
{'loss': 2.4255, 'learning_rate': 1.1507843899909241e-07, 'epoch': 13.59}

 85%|████████▍ | 52600/61904 [4:18:48<3:38:53,  1.41s/it]
 85%|████████▍ | 52601/61904 [4:18:49<3:36:45,  1.40s/it]
 85%|████████▍ | 52602/61904 [4:18:51<3:39:25,  1.42s/it]
 85%|████████▍ | 52603/61904 [4:18:52<3:42:29,  1.44s/it]
 85%|████████▍ | 52604/61904 [4:18:54<3:41:54,  1.43s/it]
 85%|████████▍ | 52605/61904 [4:18:55<3:39:02,  1.41s/it]
 85%|████████▍ | 52606/61904 [4:18:57<3:39:09,  1.41s/it]
 85%|████████▍ | 52607/61904 [4:18:58<3:43:46,  1.44s/it]
 85%|████████▍ | 52608/61904 [4:18:59<3:41:08,  1.43s/it]
 85%|████████▍ | 52609/61904 [4:19:01<3:38:38,  1.41s/it]
 85%|████████▍ | 52610/61904 [4:19:02<3:49:15,  1.48s/it]
 85%|████████▍ | 52611/61904 [4:19:04<3:46:40,  1.46s/it]
 85%|████████▍ | 52612/61904 [4:19:05<3:46:08,  1.46s/it]
 85%|████████▍ | 52613/61904 [4:19:07<3:48:23,  1.47s/it]
 85%|████████▍ | 52614/61904 [4:19:08<3:45:37,  1.46s/it]
 85%|████████▍ | 52615/61904 [4:19:10<3:48:42,  1.48s/it]
 85%|████████▍ | 52616/61904 [4:19:11<3:51:26,  1.50s/it]
 85%|████████▍ | 52617/61904 [4:19:13<3:56:14,  1.53s/it]
 85%|████████▍ | 52618/61904 [4:19:14<3:46:33,  1.46s/it]
 85%|████████▌ | 52619/61904 [4:19:16<3:41:47,  1.43s/it]
 85%|████████▌ | 52620/61904 [4:19:17<3:47:37,  1.47s/it]
                                                         
{'loss': 2.414, 'learning_rate': 1.150460261895501e-07, 'epoch': 13.6}

 85%|████████▌ | 52620/61904 [4:19:17<3:47:37,  1.47s/it]
 85%|████████▌ | 52621/61904 [4:19:18<3:40:47,  1.43s/it]
 85%|████████▌ | 52622/61904 [4:19:20<3:38:34,  1.41s/it]
 85%|████████▌ | 52623/61904 [4:19:21<3:33:47,  1.38s/it]
 85%|████████▌ | 52624/61904 [4:19:23<3:34:53,  1.39s/it]
 85%|████████▌ | 52625/61904 [4:19:24<3:41:16,  1.43s/it]
 85%|████████▌ | 52626/61904 [4:19:26<3:40:44,  1.43s/it]
 85%|████████▌ | 52627/61904 [4:19:27<3:37:19,  1.41s/it]
 85%|████████▌ | 52628/61904 [4:19:28<3:39:48,  1.42s/it]
 85%|████████▌ | 52629/61904 [4:19:30<3:39:00,  1.42s/it]
 85%|████████▌ | 52630/61904 [4:19:31<3:45:47,  1.46s/it]
 85%|████████▌ | 52631/61904 [4:19:33<3:42:01,  1.44s/it]
 85%|████████▌ | 52632/61904 [4:19:34<3:41:21,  1.43s/it]
 85%|████████▌ | 52633/61904 [4:19:35<3:33:28,  1.38s/it]
 85%|████████▌ | 52634/61904 [4:19:37<3:40:59,  1.43s/it]
 85%|████████▌ | 52635/61904 [4:19:38<3:37:54,  1.41s/it]
 85%|████████▌ | 52636/61904 [4:19:40<3:33:00,  1.38s/it]
 85%|████████▌ | 52637/61904 [4:19:41<3:37:11,  1.41s/it]
 85%|████████▌ | 52638/61904 [4:19:43<3:41:19,  1.43s/it]
 85%|████████▌ | 52639/61904 [4:19:44<3:44:40,  1.46s/it]
 85%|████████▌ | 52640/61904 [4:19:45<3:41:08,  1.43s/it]
                                                         
{'loss': 2.4667, 'learning_rate': 1.1501361338000777e-07, 'epoch': 13.61}

 85%|████████▌ | 52640/61904 [4:19:45<3:41:08,  1.43s/it]
 85%|████████▌ | 52641/61904 [4:19:47<3:34:07,  1.39s/it]
 85%|████████▌ | 52642/61904 [4:19:48<3:35:06,  1.39s/it]
 85%|████████▌ | 52643/61904 [4:19:49<3:32:08,  1.37s/it]
 85%|████████▌ | 52644/61904 [4:19:51<3:29:39,  1.36s/it]
 85%|████████▌ | 52645/61904 [4:19:52<3:35:55,  1.40s/it]
 85%|████████▌ | 52646/61904 [4:19:54<3:33:54,  1.39s/it]
 85%|████████▌ | 52647/61904 [4:19:55<3:36:32,  1.40s/it]
 85%|████████▌ | 52648/61904 [4:19:57<3:36:54,  1.41s/it]
 85%|████████▌ | 52649/61904 [4:19:58<3:39:14,  1.42s/it]
 85%|████████▌ | 52650/61904 [4:19:59<3:42:01,  1.44s/it]
 85%|████████▌ | 52651/61904 [4:20:01<3:37:01,  1.41s/it]
 85%|████████▌ | 52652/61904 [4:20:02<3:32:29,  1.38s/it]
 85%|████████▌ | 52653/61904 [4:20:03<3:32:27,  1.38s/it]
 85%|████████▌ | 52654/61904 [4:20:05<3:28:59,  1.36s/it]
 85%|████████▌ | 52655/61904 [4:20:06<3:27:46,  1.35s/it]
 85%|████████▌ | 52656/61904 [4:20:07<3:29:25,  1.36s/it]
 85%|████████▌ | 52657/61904 [4:20:09<3:28:41,  1.35s/it]
 85%|████████▌ | 52658/61904 [4:20:10<3:33:48,  1.39s/it]
 85%|████████▌ | 52659/61904 [4:20:12<3:34:59,  1.40s/it]
 85%|████████▌ | 52660/61904 [4:20:13<3:31:39,  1.37s/it]
                                                         
{'loss': 2.4574, 'learning_rate': 1.1498120057046543e-07, 'epoch': 13.61}

 85%|████████▌ | 52660/61904 [4:20:13<3:31:39,  1.37s/it]
 85%|████████▌ | 52661/61904 [4:20:14<3:33:06,  1.38s/it]
 85%|████████▌ | 52662/61904 [4:20:16<3:34:33,  1.39s/it]
 85%|████████▌ | 52663/61904 [4:20:17<3:34:22,  1.39s/it]
 85%|████████▌ | 52664/61904 [4:20:19<3:35:33,  1.40s/it]
 85%|████████▌ | 52665/61904 [4:20:20<3:34:16,  1.39s/it]
 85%|████████▌ | 52666/61904 [4:20:21<3:34:45,  1.39s/it]
 85%|████████▌ | 52667/61904 [4:20:23<3:31:13,  1.37s/it]
 85%|████████▌ | 52668/61904 [4:20:24<3:31:37,  1.37s/it]
 85%|████████▌ | 52669/61904 [4:20:26<3:31:31,  1.37s/it]
 85%|████████▌ | 52670/61904 [4:20:27<3:30:53,  1.37s/it]
 85%|████████▌ | 52671/61904 [4:20:28<3:30:40,  1.37s/it]
 85%|████████▌ | 52672/61904 [4:20:29<3:25:48,  1.34s/it]
 85%|████████▌ | 52673/61904 [4:20:31<3:24:35,  1.33s/it]
 85%|████████▌ | 52674/61904 [4:20:32<3:26:34,  1.34s/it]
 85%|████████▌ | 52675/61904 [4:20:34<3:28:55,  1.36s/it]
 85%|████████▌ | 52676/61904 [4:20:35<3:30:56,  1.37s/it]
 85%|████████▌ | 52677/61904 [4:20:36<3:31:56,  1.38s/it]
 85%|████████▌ | 52678/61904 [4:20:38<3:29:27,  1.36s/it]
 85%|████████▌ | 52679/61904 [4:20:39<3:28:30,  1.36s/it]
 85%|████████▌ | 52680/61904 [4:20:40<3:32:15,  1.38s/it]
                                                         
{'loss': 2.4472, 'learning_rate': 1.1494878776092312e-07, 'epoch': 13.62}

 85%|████████▌ | 52680/61904 [4:20:40<3:32:15,  1.38s/it]
 85%|████████▌ | 52681/61904 [4:20:42<3:26:13,  1.34s/it]
 85%|████████▌ | 52682/61904 [4:20:43<3:26:22,  1.34s/it]
 85%|████████▌ | 52683/61904 [4:20:45<3:31:25,  1.38s/it]
 85%|████████▌ | 52684/61904 [4:20:46<3:34:55,  1.40s/it]
 85%|████████▌ | 52685/61904 [4:20:47<3:35:33,  1.40s/it]
 85%|████████▌ | 52686/61904 [4:20:49<3:38:38,  1.42s/it]
 85%|████████▌ | 52687/61904 [4:20:50<3:32:01,  1.38s/it]
 85%|████████▌ | 52688/61904 [4:20:52<3:33:37,  1.39s/it]
 85%|████████▌ | 52689/61904 [4:20:53<3:35:51,  1.41s/it]
 85%|████████▌ | 52690/61904 [4:20:54<3:39:08,  1.43s/it]
 85%|████████▌ | 52691/61904 [4:20:56<3:31:14,  1.38s/it]
 85%|████████▌ | 52692/61904 [4:20:57<3:30:21,  1.37s/it]
 85%|████████▌ | 52693/61904 [4:20:59<3:34:41,  1.40s/it]
 85%|████████▌ | 52694/61904 [4:21:00<3:34:54,  1.40s/it]
 85%|████████▌ | 52695/61904 [4:21:01<3:34:12,  1.40s/it]
 85%|████████▌ | 52696/61904 [4:21:03<3:35:09,  1.40s/it]
 85%|████████▌ | 52697/61904 [4:21:04<3:29:28,  1.37s/it]
 85%|████████▌ | 52698/61904 [4:21:05<3:28:51,  1.36s/it]
 85%|████████▌ | 52699/61904 [4:21:07<3:28:49,  1.36s/it]
 85%|████████▌ | 52700/61904 [4:21:08<3:27:58,  1.36s/it]
                                                         
{'loss': 2.4838, 'learning_rate': 1.1491637495138078e-07, 'epoch': 13.62}

 85%|████████▌ | 52700/61904 [4:21:08<3:27:58,  1.36s/it]
 85%|████████▌ | 52701/61904 [4:21:10<3:34:39,  1.40s/it]
 85%|████████▌ | 52702/61904 [4:21:11<3:36:24,  1.41s/it]
 85%|████████▌ | 52703/61904 [4:21:12<3:31:33,  1.38s/it]
 85%|████████▌ | 52704/61904 [4:21:14<3:34:26,  1.40s/it]
 85%|████████▌ | 52705/61904 [4:21:15<3:31:03,  1.38s/it]
 85%|████████▌ | 52706/61904 [4:21:16<3:28:50,  1.36s/it]
 85%|████████▌ | 52707/61904 [4:21:18<3:38:39,  1.43s/it]
 85%|████████▌ | 52708/61904 [4:21:19<3:33:04,  1.39s/it]
 85%|████████▌ | 52709/61904 [4:21:21<3:34:00,  1.40s/it]
 85%|████████▌ | 52710/61904 [4:21:22<3:39:11,  1.43s/it]
 85%|████████▌ | 52711/61904 [4:21:24<3:34:17,  1.40s/it]
 85%|████████▌ | 52712/61904 [4:21:25<3:34:08,  1.40s/it]
 85%|████████▌ | 52713/61904 [4:21:26<3:37:29,  1.42s/it]
 85%|████████▌ | 52714/61904 [4:21:28<3:34:05,  1.40s/it]
 85%|████████▌ | 52715/61904 [4:21:29<3:28:07,  1.36s/it]
 85%|████████▌ | 52716/61904 [4:21:30<3:27:40,  1.36s/it]
 85%|████████▌ | 52717/61904 [4:21:32<3:27:45,  1.36s/it]
 85%|████████▌ | 52718/61904 [4:21:33<3:27:12,  1.35s/it]
 85%|████████▌ | 52719/61904 [4:21:35<3:36:27,  1.41s/it]
 85%|████████▌ | 52720/61904 [4:21:36<3:31:59,  1.38s/it]
                                                         
{'loss': 2.4244, 'learning_rate': 1.1488396214183844e-07, 'epoch': 13.63}

 85%|████████▌ | 52720/61904 [4:21:36<3:31:59,  1.38s/it]
 85%|████████▌ | 52721/61904 [4:21:37<3:31:05,  1.38s/it]
 85%|████████▌ | 52722/61904 [4:21:39<3:29:24,  1.37s/it]
 85%|████████▌ | 52723/61904 [4:21:40<3:24:46,  1.34s/it]
 85%|████████▌ | 52724/61904 [4:21:41<3:23:38,  1.33s/it]
 85%|████████▌ | 52725/61904 [4:21:43<3:26:26,  1.35s/it]
 85%|████████▌ | 52726/61904 [4:21:44<3:33:15,  1.39s/it]
 85%|████████▌ | 52727/61904 [4:21:46<3:31:29,  1.38s/it]
 85%|████████▌ | 52728/61904 [4:21:47<3:35:04,  1.41s/it]
 85%|████████▌ | 52729/61904 [4:21:48<3:36:42,  1.42s/it]
 85%|████████▌ | 52730/61904 [4:21:50<3:36:54,  1.42s/it]
 85%|████████▌ | 52731/61904 [4:21:51<3:30:47,  1.38s/it]
 85%|████████▌ | 52732/61904 [4:21:52<3:29:27,  1.37s/it]
 85%|████████▌ | 52733/61904 [4:21:54<3:44:07,  1.47s/it]
 85%|████████▌ | 52734/61904 [4:21:56<3:38:27,  1.43s/it]
 85%|████████▌ | 52735/61904 [4:21:57<3:37:22,  1.42s/it]
 85%|████████▌ | 52736/61904 [4:21:58<3:31:29,  1.38s/it]
 85%|████████▌ | 52737/61904 [4:22:00<3:29:46,  1.37s/it]
 85%|████████▌ | 52738/61904 [4:22:01<3:26:54,  1.35s/it]
 85%|████████▌ | 52739/61904 [4:22:02<3:33:07,  1.40s/it]
 85%|████████▌ | 52740/61904 [4:22:04<3:44:54,  1.47s/it]
                                                         
{'loss': 2.4486, 'learning_rate': 1.148515493322961e-07, 'epoch': 13.63}

 85%|████████▌ | 52740/61904 [4:22:04<3:44:54,  1.47s/it]
 85%|████████▌ | 52741/61904 [4:22:05<3:45:55,  1.48s/it]
 85%|████████▌ | 52742/61904 [4:22:07<3:43:32,  1.46s/it]
 85%|████████▌ | 52743/61904 [4:22:08<3:44:14,  1.47s/it]
 85%|████████▌ | 52744/61904 [4:22:10<3:45:31,  1.48s/it]
 85%|████████▌ | 52745/61904 [4:22:11<3:36:19,  1.42s/it]
 85%|████████▌ | 52746/61904 [4:22:13<3:35:25,  1.41s/it]
 85%|████████▌ | 52747/61904 [4:22:14<3:33:23,  1.40s/it]
 85%|████████▌ | 52748/61904 [4:22:15<3:24:00,  1.34s/it]
 85%|████████▌ | 52749/61904 [4:22:16<3:20:45,  1.32s/it]
 85%|████████▌ | 52750/61904 [4:22:18<3:22:25,  1.33s/it]
 85%|████████▌ | 52751/61904 [4:22:19<3:24:53,  1.34s/it]
 85%|████████▌ | 52752/61904 [4:22:21<3:27:23,  1.36s/it]
 85%|████████▌ | 52753/61904 [4:22:22<3:25:51,  1.35s/it]
 85%|████████▌ | 52754/61904 [4:22:23<3:22:28,  1.33s/it]
 85%|████████▌ | 52755/61904 [4:22:25<3:28:05,  1.36s/it]
 85%|████████▌ | 52756/61904 [4:22:26<3:24:26,  1.34s/it]
 85%|████████▌ | 52757/61904 [4:22:27<3:24:39,  1.34s/it]
 85%|████████▌ | 52758/61904 [4:22:29<3:21:55,  1.32s/it]
 85%|████████▌ | 52759/61904 [4:22:30<3:23:40,  1.34s/it]
 85%|████████▌ | 52760/61904 [4:22:31<3:23:18,  1.33s/it]
                                                         
{'loss': 2.4595, 'learning_rate': 1.1481913652275379e-07, 'epoch': 13.64}

 85%|████████▌ | 52760/61904 [4:22:31<3:23:18,  1.33s/it]
 85%|████████▌ | 52761/61904 [4:22:33<3:21:55,  1.33s/it]
 85%|████████▌ | 52762/61904 [4:22:34<3:23:59,  1.34s/it]
 85%|████████▌ | 52763/61904 [4:22:35<3:24:54,  1.34s/it]
 85%|████████▌ | 52764/61904 [4:22:37<3:22:24,  1.33s/it]
 85%|████████▌ | 52765/61904 [4:22:38<3:30:55,  1.38s/it]
 85%|████████▌ | 52766/61904 [4:22:39<3:26:46,  1.36s/it]
 85%|████████▌ | 52767/61904 [4:22:41<3:30:06,  1.38s/it]
 85%|████████▌ | 52768/61904 [4:22:42<3:30:19,  1.38s/it]
 85%|████████▌ | 52769/61904 [4:22:44<3:32:12,  1.39s/it]
 85%|████████▌ | 52770/61904 [4:22:45<3:33:41,  1.40s/it]
 85%|████████▌ | 52771/61904 [4:22:46<3:35:33,  1.42s/it]
 85%|████████▌ | 52772/61904 [4:22:48<3:39:25,  1.44s/it]
 85%|████████▌ | 52773/61904 [4:22:49<3:35:44,  1.42s/it]
 85%|████████▌ | 52774/61904 [4:22:51<3:29:33,  1.38s/it]
 85%|████████▌ | 52775/61904 [4:22:52<3:30:15,  1.38s/it]
 85%|████████▌ | 52776/61904 [4:22:53<3:28:24,  1.37s/it]
 85%|████████▌ | 52777/61904 [4:22:55<3:29:02,  1.37s/it]
 85%|████████▌ | 52778/61904 [4:22:56<3:32:31,  1.40s/it]
 85%|████████▌ | 52779/61904 [4:22:58<3:32:43,  1.40s/it]
 85%|████████▌ | 52780/61904 [4:22:59<3:30:26,  1.38s/it]
                                                         
{'loss': 2.4267, 'learning_rate': 1.1478672371321145e-07, 'epoch': 13.64}

 85%|████████▌ | 52780/61904 [4:22:59<3:30:26,  1.38s/it]
 85%|████████▌ | 52781/61904 [4:23:00<3:35:49,  1.42s/it]
 85%|████████▌ | 52782/61904 [4:23:02<3:32:31,  1.40s/it]
 85%|████████▌ | 52783/61904 [4:23:03<3:29:43,  1.38s/it]
 85%|████████▌ | 52784/61904 [4:23:04<3:28:10,  1.37s/it]
 85%|████████▌ | 52785/61904 [4:23:06<3:28:33,  1.37s/it]
 85%|████████▌ | 52786/61904 [4:23:07<3:24:03,  1.34s/it]
 85%|████████▌ | 52787/61904 [4:23:08<3:26:28,  1.36s/it]
 85%|████████▌ | 52788/61904 [4:23:10<3:22:57,  1.34s/it]
 85%|████████▌ | 52789/61904 [4:23:11<3:34:36,  1.41s/it]
 85%|████████▌ | 52790/61904 [4:23:13<3:28:41,  1.37s/it]
 85%|████████▌ | 52791/61904 [4:23:14<3:27:52,  1.37s/it]
 85%|████████▌ | 52792/61904 [4:23:16<3:34:23,  1.41s/it]
 85%|████████▌ | 52793/61904 [4:23:17<3:34:07,  1.41s/it]
 85%|████████▌ | 52794/61904 [4:23:18<3:33:02,  1.40s/it]
 85%|████████▌ | 52795/61904 [4:23:20<3:34:20,  1.41s/it]
 85%|████████▌ | 52796/61904 [4:23:21<3:33:26,  1.41s/it]
 85%|████████▌ | 52797/61904 [4:23:23<3:35:50,  1.42s/it]
 85%|████████▌ | 52798/61904 [4:23:24<3:36:12,  1.42s/it]
 85%|████████▌ | 52799/61904 [4:23:25<3:31:09,  1.39s/it]
 85%|████████▌ | 52800/61904 [4:23:27<3:36:55,  1.43s/it]
                                                         
{'loss': 2.4348, 'learning_rate': 1.1475431090366911e-07, 'epoch': 13.65}

 85%|████████▌ | 52800/61904 [4:23:27<3:36:55,  1.43s/it]
 85%|████████▌ | 52801/61904 [4:23:28<3:28:07,  1.37s/it]
 85%|████████▌ | 52802/61904 [4:23:29<3:27:34,  1.37s/it]
 85%|████████▌ | 52803/61904 [4:23:31<3:26:59,  1.36s/it]
 85%|████████▌ | 52804/61904 [4:23:32<3:31:03,  1.39s/it]
 85%|████████▌ | 52805/61904 [4:23:34<3:39:34,  1.45s/it]
 85%|████████▌ | 52806/61904 [4:23:35<3:33:30,  1.41s/it]
 85%|████████▌ | 52807/61904 [4:23:37<3:38:23,  1.44s/it]
 85%|████████▌ | 52808/61904 [4:23:38<3:35:53,  1.42s/it]
 85%|████████▌ | 52809/61904 [4:23:39<3:35:53,  1.42s/it]
 85%|████████▌ | 52810/61904 [4:23:41<3:36:41,  1.43s/it]
 85%|████████▌ | 52811/61904 [4:23:42<3:31:59,  1.40s/it]
 85%|████████▌ | 52812/61904 [4:23:44<3:27:21,  1.37s/it]
 85%|████████▌ | 52813/61904 [4:23:45<3:32:43,  1.40s/it]
 85%|████████▌ | 52814/61904 [4:23:46<3:29:09,  1.38s/it]
 85%|████████▌ | 52815/61904 [4:23:48<3:31:48,  1.40s/it]
 85%|████████▌ | 52816/61904 [4:23:49<3:29:06,  1.38s/it]
 85%|████████▌ | 52817/61904 [4:23:50<3:25:48,  1.36s/it]
 85%|████████▌ | 52818/61904 [4:23:52<3:23:57,  1.35s/it]
 85%|████████▌ | 52819/61904 [4:23:53<3:24:33,  1.35s/it]
 85%|████████▌ | 52820/61904 [4:23:54<3:22:12,  1.34s/it]
                                                         
{'loss': 2.4963, 'learning_rate': 1.1472189809412677e-07, 'epoch': 13.65}

 85%|████████▌ | 52820/61904 [4:23:54<3:22:12,  1.34s/it]
 85%|████████▌ | 52821/61904 [4:23:56<3:30:38,  1.39s/it]
 85%|████████▌ | 52822/61904 [4:23:57<3:34:24,  1.42s/it]
 85%|████████▌ | 52823/61904 [4:23:59<3:33:44,  1.41s/it]
 85%|████████▌ | 52824/61904 [4:24:00<3:27:47,  1.37s/it]
 85%|████████▌ | 52825/61904 [4:24:02<3:33:43,  1.41s/it]
 85%|████████▌ | 52826/61904 [4:24:03<3:36:08,  1.43s/it]
 85%|████████▌ | 52827/61904 [4:24:04<3:33:41,  1.41s/it]
 85%|████████▌ | 52828/61904 [4:24:06<3:29:02,  1.38s/it]
 85%|████████▌ | 52829/61904 [4:24:07<3:35:08,  1.42s/it]
 85%|████████▌ | 52830/61904 [4:24:09<3:41:28,  1.46s/it]
 85%|████████▌ | 52831/61904 [4:24:10<3:38:38,  1.45s/it]
 85%|████████▌ | 52832/61904 [4:24:12<3:40:19,  1.46s/it]
 85%|████████▌ | 52833/61904 [4:24:13<3:35:49,  1.43s/it]
 85%|████████▌ | 52834/61904 [4:24:14<3:26:43,  1.37s/it]
 85%|████████▌ | 52835/61904 [4:24:16<3:24:50,  1.36s/it]
 85%|████████▌ | 52836/61904 [4:24:17<3:23:30,  1.35s/it]
 85%|████████▌ | 52837/61904 [4:24:18<3:19:08,  1.32s/it]
 85%|████████▌ | 52838/61904 [4:24:20<3:26:54,  1.37s/it]
 85%|████████▌ | 52839/61904 [4:24:21<3:26:57,  1.37s/it]
 85%|████████▌ | 52840/61904 [4:24:23<3:32:52,  1.41s/it]
                                                         
{'loss': 2.3726, 'learning_rate': 1.1468948528458446e-07, 'epoch': 13.66}

 85%|████████▌ | 52840/61904 [4:24:23<3:32:52,  1.41s/it]
 85%|████████▌ | 52841/61904 [4:24:24<3:34:42,  1.42s/it]
 85%|████████▌ | 52842/61904 [4:24:25<3:30:37,  1.39s/it]
 85%|████████▌ | 52843/61904 [4:24:27<3:27:28,  1.37s/it]
 85%|████████▌ | 52844/61904 [4:24:28<3:25:25,  1.36s/it]
 85%|████████▌ | 52845/61904 [4:24:29<3:27:04,  1.37s/it]
 85%|████████▌ | 52846/61904 [4:24:31<3:28:35,  1.38s/it]
 85%|████████▌ | 52847/61904 [4:24:32<3:33:13,  1.41s/it]
 85%|████████▌ | 52848/61904 [4:24:34<3:31:45,  1.40s/it]
 85%|████████▌ | 52849/61904 [4:24:35<3:26:32,  1.37s/it]
 85%|████████▌ | 52850/61904 [4:24:36<3:27:37,  1.38s/it]
 85%|████████▌ | 52851/61904 [4:24:38<3:29:11,  1.39s/it]
 85%|████████▌ | 52852/61904 [4:24:39<3:33:04,  1.41s/it]
 85%|████████▌ | 52853/61904 [4:24:41<3:31:35,  1.40s/it]
 85%|████████▌ | 52854/61904 [4:24:42<3:33:50,  1.42s/it]
 85%|████████▌ | 52855/61904 [4:24:43<3:33:09,  1.41s/it]
 85%|████████▌ | 52856/61904 [4:24:45<3:31:37,  1.40s/it]
 85%|████████▌ | 52857/61904 [4:24:46<3:31:22,  1.40s/it]
 85%|████████▌ | 52858/61904 [4:24:48<3:30:06,  1.39s/it]
 85%|████████▌ | 52859/61904 [4:24:49<3:23:58,  1.35s/it]
 85%|████████▌ | 52860/61904 [4:24:50<3:18:18,  1.32s/it]
                                                         
{'loss': 2.3944, 'learning_rate': 1.1465707247504213e-07, 'epoch': 13.66}

 85%|████████▌ | 52860/61904 [4:24:50<3:18:18,  1.32s/it]
 85%|████████▌ | 52861/61904 [4:24:52<3:23:16,  1.35s/it]
 85%|████████▌ | 52862/61904 [4:24:53<3:25:26,  1.36s/it]
 85%|████████▌ | 52863/61904 [4:24:54<3:28:36,  1.38s/it]
 85%|████████▌ | 52864/61904 [4:24:56<3:30:12,  1.40s/it]
 85%|████████▌ | 52865/61904 [4:24:57<3:25:33,  1.36s/it]
 85%|████████▌ | 52866/61904 [4:24:58<3:22:58,  1.35s/it]
 85%|████████▌ | 52867/61904 [4:25:00<3:26:26,  1.37s/it]
 85%|████████▌ | 52868/61904 [4:25:01<3:24:35,  1.36s/it]
 85%|████████▌ | 52869/61904 [4:25:02<3:22:20,  1.34s/it]
 85%|████████▌ | 52870/61904 [4:25:04<3:21:18,  1.34s/it]
 85%|████████▌ | 52871/61904 [4:25:05<3:31:23,  1.40s/it]
 85%|████████▌ | 52872/61904 [4:25:07<3:36:31,  1.44s/it]
 85%|████████▌ | 52873/61904 [4:25:08<3:37:42,  1.45s/it]
 85%|████████▌ | 52874/61904 [4:25:10<3:38:52,  1.45s/it]
 85%|████████▌ | 52875/61904 [4:25:11<3:41:25,  1.47s/it]
 85%|████████▌ | 52876/61904 [4:25:13<3:40:49,  1.47s/it]
 85%|████████▌ | 52877/61904 [4:25:14<3:36:12,  1.44s/it]
 85%|████████▌ | 52878/61904 [4:25:16<3:33:25,  1.42s/it]
 85%|████████▌ | 52879/61904 [4:25:17<3:32:19,  1.41s/it]
 85%|████████▌ | 52880/61904 [4:25:18<3:31:02,  1.40s/it]
                                                         
{'loss': 2.5007, 'learning_rate': 1.1462465966549979e-07, 'epoch': 13.67}

 85%|████████▌ | 52880/61904 [4:25:18<3:31:02,  1.40s/it]
 85%|████████▌ | 52881/61904 [4:25:20<3:36:09,  1.44s/it]
 85%|████████▌ | 52882/61904 [4:25:21<3:38:32,  1.45s/it]
 85%|████████▌ | 52883/61904 [4:25:23<3:37:15,  1.45s/it]
 85%|████████▌ | 52884/61904 [4:25:24<3:27:40,  1.38s/it]
 85%|████████▌ | 52885/61904 [4:25:25<3:20:24,  1.33s/it]
 85%|████████▌ | 52886/61904 [4:25:27<3:19:35,  1.33s/it]
 85%|████████▌ | 52887/61904 [4:25:28<3:15:34,  1.30s/it]
 85%|████████▌ | 52888/61904 [4:25:29<3:15:48,  1.30s/it]
 85%|████████▌ | 52889/61904 [4:25:30<3:20:51,  1.34s/it]
 85%|████████▌ | 52890/61904 [4:25:32<3:25:02,  1.36s/it]
 85%|████████▌ | 52891/61904 [4:25:33<3:25:21,  1.37s/it]
 85%|████████▌ | 52892/61904 [4:25:35<3:25:57,  1.37s/it]
 85%|████████▌ | 52893/61904 [4:25:36<3:26:47,  1.38s/it]
 85%|████████▌ | 52894/61904 [4:25:38<3:32:21,  1.41s/it]
 85%|████████▌ | 52895/61904 [4:25:39<3:24:30,  1.36s/it]
 85%|████████▌ | 52896/61904 [4:25:40<3:34:25,  1.43s/it]
 85%|████████▌ | 52897/61904 [4:25:42<3:30:10,  1.40s/it]
 85%|████████▌ | 52898/61904 [4:25:43<3:25:37,  1.37s/it]
 85%|████████▌ | 52899/61904 [4:25:45<3:33:08,  1.42s/it]
 85%|████████▌ | 52900/61904 [4:25:46<3:37:26,  1.45s/it]
                                                         
{'loss': 2.4834, 'learning_rate': 1.1459224685595745e-07, 'epoch': 13.67}

 85%|████████▌ | 52900/61904 [4:25:46<3:37:26,  1.45s/it]
 85%|████████▌ | 52901/61904 [4:25:47<3:28:42,  1.39s/it]
 85%|████████▌ | 52902/61904 [4:25:49<3:27:49,  1.39s/it]
 85%|████████▌ | 52903/61904 [4:25:50<3:26:22,  1.38s/it]
 85%|████████▌ | 52904/61904 [4:25:51<3:23:06,  1.35s/it]
 85%|████████▌ | 52905/61904 [4:25:53<3:19:55,  1.33s/it]
 85%|████████▌ | 52906/61904 [4:25:54<3:25:34,  1.37s/it]
 85%|████████▌ | 52907/61904 [4:25:55<3:26:12,  1.38s/it]
 85%|████████▌ | 52908/61904 [4:25:57<3:22:43,  1.35s/it]
 85%|████████▌ | 52909/61904 [4:25:58<3:24:46,  1.37s/it]
 85%|████████▌ | 52910/61904 [4:26:00<3:30:11,  1.40s/it]
 85%|████████▌ | 52911/61904 [4:26:01<3:29:12,  1.40s/it]
 85%|████████▌ | 52912/61904 [4:26:03<3:36:02,  1.44s/it]
 85%|████████▌ | 52913/61904 [4:26:04<3:40:08,  1.47s/it]
 85%|████████▌ | 52914/61904 [4:26:06<3:44:01,  1.50s/it]
 85%|████████▌ | 52915/61904 [4:26:07<3:44:53,  1.50s/it]
 85%|████████▌ | 52916/61904 [4:26:09<3:36:53,  1.45s/it]
 85%|████████▌ | 52917/61904 [4:26:10<3:30:55,  1.41s/it]
 85%|████████▌ | 52918/61904 [4:26:11<3:31:40,  1.41s/it]
 85%|████████▌ | 52919/61904 [4:26:13<3:35:36,  1.44s/it]
 85%|████████▌ | 52920/61904 [4:26:14<3:29:42,  1.40s/it]
                                                         
{'loss': 2.3963, 'learning_rate': 1.1455983404641514e-07, 'epoch': 13.68}

 85%|████████▌ | 52920/61904 [4:26:14<3:29:42,  1.40s/it]
 85%|████████▌ | 52921/61904 [4:26:15<3:25:14,  1.37s/it]
 85%|████████▌ | 52922/61904 [4:26:17<3:25:59,  1.38s/it]
 85%|████████▌ | 52923/61904 [4:26:18<3:21:52,  1.35s/it]
 85%|████████▌ | 52924/61904 [4:26:19<3:20:03,  1.34s/it]
 85%|████████▌ | 52925/61904 [4:26:21<3:19:36,  1.33s/it]
 85%|████████▌ | 52926/61904 [4:26:22<3:20:02,  1.34s/it]
 85%|████████▌ | 52927/61904 [4:26:23<3:18:36,  1.33s/it]
 86%|████████▌ | 52928/61904 [4:26:25<3:18:50,  1.33s/it]
 86%|████████▌ | 52929/61904 [4:26:26<3:23:03,  1.36s/it]
 86%|████████▌ | 52930/61904 [4:26:27<3:21:17,  1.35s/it]
 86%|████████▌ | 52931/61904 [4:26:29<3:19:48,  1.34s/it]
 86%|████████▌ | 52932/61904 [4:26:30<3:23:40,  1.36s/it]
 86%|████████▌ | 52933/61904 [4:26:32<3:28:27,  1.39s/it]
 86%|████████▌ | 52934/61904 [4:26:33<3:30:18,  1.41s/it]
 86%|████████▌ | 52935/61904 [4:26:34<3:31:27,  1.41s/it]
 86%|████████▌ | 52936/61904 [4:26:36<3:25:42,  1.38s/it]
 86%|████████▌ | 52937/61904 [4:26:37<3:24:55,  1.37s/it]
 86%|████████▌ | 52938/61904 [4:26:38<3:25:08,  1.37s/it]
 86%|████████▌ | 52939/61904 [4:26:40<3:25:08,  1.37s/it]
 86%|████████▌ | 52940/61904 [4:26:41<3:21:22,  1.35s/it]
                                                         
{'loss': 2.4304, 'learning_rate': 1.1452742123687283e-07, 'epoch': 13.68}

 86%|████████▌ | 52940/61904 [4:26:41<3:21:22,  1.35s/it]
 86%|████████▌ | 52941/61904 [4:26:43<3:30:28,  1.41s/it]
 86%|████████▌ | 52942/61904 [4:26:44<3:26:52,  1.39s/it]
 86%|████████▌ | 52943/61904 [4:26:45<3:26:47,  1.38s/it]
 86%|████████▌ | 52944/61904 [4:26:47<3:23:45,  1.36s/it]
 86%|████████▌ | 52945/61904 [4:26:48<3:22:21,  1.36s/it]
 86%|████████▌ | 52946/61904 [4:26:50<3:29:49,  1.41s/it]
 86%|████████▌ | 52947/61904 [4:26:51<3:26:47,  1.39s/it]
 86%|████████▌ | 52948/61904 [4:26:52<3:26:26,  1.38s/it]
 86%|████████▌ | 52949/61904 [4:26:54<3:24:48,  1.37s/it]
 86%|████████▌ | 52950/61904 [4:26:55<3:20:42,  1.34s/it]
 86%|████████▌ | 52951/61904 [4:26:56<3:24:28,  1.37s/it]
 86%|████████▌ | 52952/61904 [4:26:58<3:30:22,  1.41s/it]
 86%|████████▌ | 52953/61904 [4:26:59<3:31:07,  1.42s/it]
 86%|████████▌ | 52954/61904 [4:27:01<3:24:24,  1.37s/it]
 86%|████████▌ | 52955/61904 [4:27:02<3:21:34,  1.35s/it]
 86%|████████▌ | 52956/61904 [4:27:03<3:20:56,  1.35s/it]
 86%|████████▌ | 52957/61904 [4:27:05<3:30:52,  1.41s/it]
 86%|████████▌ | 52958/61904 [4:27:06<3:35:00,  1.44s/it]
 86%|████████▌ | 52959/61904 [4:27:08<3:33:04,  1.43s/it]
 86%|████████▌ | 52960/61904 [4:27:09<3:24:43,  1.37s/it]
                                                         
{'loss': 2.4219, 'learning_rate': 1.1449500842733046e-07, 'epoch': 13.69}

 86%|████████▌ | 52960/61904 [4:27:09<3:24:43,  1.37s/it]
 86%|████████▌ | 52961/61904 [4:27:10<3:23:19,  1.36s/it]
 86%|████████▌ | 52962/61904 [4:27:12<3:19:27,  1.34s/it]
 86%|████████▌ | 52963/61904 [4:27:13<3:17:44,  1.33s/it]
 86%|████████▌ | 52964/61904 [4:27:14<3:17:26,  1.33s/it]
 86%|████████▌ | 52965/61904 [4:27:16<3:19:54,  1.34s/it]
 86%|████████▌ | 52966/61904 [4:27:17<3:24:38,  1.37s/it]
 86%|████████▌ | 52967/61904 [4:27:18<3:20:23,  1.35s/it]
 86%|████████▌ | 52968/61904 [4:27:20<3:22:38,  1.36s/it]
 86%|████████▌ | 52969/61904 [4:27:21<3:21:14,  1.35s/it]
 86%|████████▌ | 52970/61904 [4:27:22<3:24:50,  1.38s/it]
 86%|████████▌ | 52971/61904 [4:27:24<3:21:51,  1.36s/it]
 86%|████████▌ | 52972/61904 [4:27:25<3:19:31,  1.34s/it]
 86%|████████▌ | 52973/61904 [4:27:26<3:23:15,  1.37s/it]
 86%|████████▌ | 52974/61904 [4:27:28<3:28:46,  1.40s/it]
 86%|████████▌ | 52975/61904 [4:27:30<3:35:49,  1.45s/it]
 86%|████████▌ | 52976/61904 [4:27:31<3:41:29,  1.49s/it]
 86%|████████▌ | 52977/61904 [4:27:32<3:34:21,  1.44s/it]
 86%|████████▌ | 52978/61904 [4:27:34<3:30:06,  1.41s/it]
 86%|████████▌ | 52979/61904 [4:27:35<3:26:00,  1.38s/it]
 86%|████████▌ | 52980/61904 [4:27:36<3:22:27,  1.36s/it]
                                                         
{'loss': 2.5008, 'learning_rate': 1.1446259561778815e-07, 'epoch': 13.69}

 86%|████████▌ | 52980/61904 [4:27:36<3:22:27,  1.36s/it]
 86%|████████▌ | 52981/61904 [4:27:38<3:22:12,  1.36s/it]
 86%|████████▌ | 52982/61904 [4:27:39<3:19:44,  1.34s/it]
 86%|████████▌ | 52983/61904 [4:27:40<3:22:38,  1.36s/it]
 86%|████████▌ | 52984/61904 [4:27:42<3:20:14,  1.35s/it]
 86%|████████▌ | 52985/61904 [4:27:43<3:19:19,  1.34s/it]
 86%|████████▌ | 52986/61904 [4:27:45<3:26:05,  1.39s/it]
 86%|████████▌ | 52987/61904 [4:27:46<3:27:00,  1.39s/it]
 86%|████████▌ | 52988/61904 [4:27:47<3:25:14,  1.38s/it]
 86%|████████▌ | 52989/61904 [4:27:49<3:23:47,  1.37s/it]
 86%|████████▌ | 52990/61904 [4:27:50<3:23:38,  1.37s/it]
 86%|████████▌ | 52991/61904 [4:27:51<3:21:25,  1.36s/it]
 86%|████████▌ | 52992/61904 [4:27:53<3:19:37,  1.34s/it]
 86%|████████▌ | 52993/61904 [4:27:54<3:24:05,  1.37s/it]
 86%|████████▌ | 52994/61904 [4:27:56<3:27:37,  1.40s/it]
 86%|████████▌ | 52995/61904 [4:27:57<3:27:01,  1.39s/it]
 86%|████████▌ | 52996/61904 [4:27:58<3:28:26,  1.40s/it]
 86%|████████▌ | 52997/61904 [4:28:00<3:24:35,  1.38s/it]
 86%|████████▌ | 52998/61904 [4:28:01<3:23:35,  1.37s/it]
 86%|████████▌ | 52999/61904 [4:28:02<3:20:57,  1.35s/it]
 86%|████████▌ | 53000/61904 [4:28:04<3:26:16,  1.39s/it]
                                                         
{'loss': 2.4243, 'learning_rate': 1.1443018280824581e-07, 'epoch': 13.7}

 86%|████████▌ | 53000/61904 [4:28:04<3:26:16,  1.39s/it]
 86%|████████▌ | 53001/61904 [4:28:05<3:27:01,  1.40s/it]
 86%|████████▌ | 53002/61904 [4:28:07<3:25:05,  1.38s/it]
 86%|████████▌ | 53003/61904 [4:28:08<3:23:25,  1.37s/it]
 86%|████████▌ | 53004/61904 [4:28:09<3:27:51,  1.40s/it]
 86%|████████▌ | 53005/61904 [4:28:11<3:31:48,  1.43s/it]
 86%|████████▌ | 53006/61904 [4:28:12<3:25:50,  1.39s/it]
 86%|████████▌ | 53007/61904 [4:28:14<3:23:20,  1.37s/it]
 86%|████████▌ | 53008/61904 [4:28:15<3:29:36,  1.41s/it]
 86%|████████▌ | 53009/61904 [4:28:16<3:27:54,  1.40s/it]
 86%|████████▌ | 53010/61904 [4:28:18<3:23:02,  1.37s/it]
 86%|████████▌ | 53011/61904 [4:28:19<3:32:10,  1.43s/it]
 86%|████████▌ | 53012/61904 [4:28:21<3:33:43,  1.44s/it]
 86%|████████▌ | 53013/61904 [4:28:22<3:30:07,  1.42s/it]
 86%|████████▌ | 53014/61904 [4:28:24<3:27:11,  1.40s/it]
 86%|████████▌ | 53015/61904 [4:28:25<3:27:09,  1.40s/it]
 86%|████████▌ | 53016/61904 [4:28:26<3:23:09,  1.37s/it]
 86%|████████▌ | 53017/61904 [4:28:28<3:23:46,  1.38s/it]
 86%|████████▌ | 53018/61904 [4:28:29<3:28:01,  1.40s/it]
 86%|████████▌ | 53019/61904 [4:28:30<3:26:46,  1.40s/it]
 86%|████████▌ | 53020/61904 [4:28:32<3:23:01,  1.37s/it]
                                                         
{'loss': 2.462, 'learning_rate': 1.143977699987035e-07, 'epoch': 13.7}

 86%|████████▌ | 53020/61904 [4:28:32<3:23:01,  1.37s/it]
 86%|████████▌ | 53021/61904 [4:28:33<3:21:29,  1.36s/it]
 86%|████████▌ | 53022/61904 [4:28:35<3:26:14,  1.39s/it]
 86%|████████▌ | 53023/61904 [4:28:36<3:27:39,  1.40s/it]
 86%|████████▌ | 53024/61904 [4:28:37<3:28:42,  1.41s/it]
 86%|████████▌ | 53025/61904 [4:28:39<3:26:08,  1.39s/it]
 86%|████████▌ | 53026/61904 [4:28:40<3:29:19,  1.41s/it]
 86%|████████▌ | 53027/61904 [4:28:42<3:22:44,  1.37s/it]
 86%|████████▌ | 53028/61904 [4:28:43<3:22:48,  1.37s/it]
 86%|████████▌ | 53029/61904 [4:28:44<3:31:02,  1.43s/it]
 86%|████████▌ | 53030/61904 [4:28:46<3:29:40,  1.42s/it]
 86%|████████▌ | 53031/61904 [4:28:47<3:24:30,  1.38s/it]
 86%|████████▌ | 53032/61904 [4:28:48<3:22:58,  1.37s/it]
 86%|████████▌ | 53033/61904 [4:28:50<3:28:04,  1.41s/it]
 86%|████████▌ | 53034/61904 [4:28:51<3:22:26,  1.37s/it]
 86%|████████▌ | 53035/61904 [4:28:53<3:28:31,  1.41s/it]
 86%|████████▌ | 53036/61904 [4:28:54<3:27:19,  1.40s/it]
 86%|████████▌ | 53037/61904 [4:28:56<3:25:15,  1.39s/it]
 86%|████████▌ | 53038/61904 [4:28:57<3:22:15,  1.37s/it]
 86%|████████▌ | 53039/61904 [4:28:58<3:31:37,  1.43s/it]
 86%|████████▌ | 53040/61904 [4:29:00<3:24:10,  1.38s/it]
                                                         
{'loss': 2.4512, 'learning_rate': 1.1436535718916113e-07, 'epoch': 13.71}

 86%|████████▌ | 53040/61904 [4:29:00<3:24:10,  1.38s/it]
 86%|████████▌ | 53041/61904 [4:29:01<3:19:41,  1.35s/it]
 86%|████████▌ | 53042/61904 [4:29:03<3:37:48,  1.47s/it]
 86%|████████▌ | 53043/61904 [4:29:04<3:31:18,  1.43s/it]
 86%|████████▌ | 53044/61904 [4:29:05<3:28:50,  1.41s/it]
 86%|████████▌ | 53045/61904 [4:29:07<3:30:36,  1.43s/it]
 86%|████████▌ | 53046/61904 [4:29:08<3:21:29,  1.36s/it]
 86%|████████▌ | 53047/61904 [4:29:09<3:20:09,  1.36s/it]
 86%|████████▌ | 53048/61904 [4:29:11<3:23:38,  1.38s/it]
 86%|████████▌ | 53049/61904 [4:29:12<3:32:45,  1.44s/it]
 86%|████████▌ | 53050/61904 [4:29:14<3:30:09,  1.42s/it]
 86%|████████▌ | 53051/61904 [4:29:15<3:25:57,  1.40s/it]
 86%|████████▌ | 53052/61904 [4:29:16<3:20:26,  1.36s/it]
 86%|████████▌ | 53053/61904 [4:29:18<3:31:16,  1.43s/it]
 86%|████████▌ | 53054/61904 [4:29:20<3:38:08,  1.48s/it]
 86%|████████▌ | 53055/61904 [4:29:21<3:36:57,  1.47s/it]
 86%|████████▌ | 53056/61904 [4:29:23<3:35:41,  1.46s/it]
 86%|████████▌ | 53057/61904 [4:29:24<3:44:54,  1.53s/it]
 86%|████████▌ | 53058/61904 [4:29:26<3:40:20,  1.49s/it]
 86%|████████▌ | 53059/61904 [4:29:27<3:37:19,  1.47s/it]
 86%|████████▌ | 53060/61904 [4:29:29<3:36:34,  1.47s/it]
                                                         
{'loss': 2.508, 'learning_rate': 1.1433294437961882e-07, 'epoch': 13.71}

 86%|████████▌ | 53060/61904 [4:29:29<3:36:34,  1.47s/it]
 86%|████████▌ | 53061/61904 [4:29:30<3:35:55,  1.47s/it]
 86%|████████▌ | 53062/61904 [4:29:31<3:35:02,  1.46s/it]
 86%|████████▌ | 53063/61904 [4:29:33<3:30:53,  1.43s/it]
 86%|████████▌ | 53064/61904 [4:29:34<3:29:07,  1.42s/it]
 86%|████████▌ | 53065/61904 [4:29:36<3:28:56,  1.42s/it]
 86%|████████▌ | 53066/61904 [4:29:37<3:32:00,  1.44s/it]
 86%|████████▌ | 53067/61904 [4:29:38<3:28:14,  1.41s/it]
 86%|████████▌ | 53068/61904 [4:29:40<3:25:45,  1.40s/it]
 86%|████████▌ | 53069/61904 [4:29:41<3:28:14,  1.41s/it]
 86%|████████▌ | 53070/61904 [4:29:43<3:23:53,  1.38s/it]
 86%|████████▌ | 53071/61904 [4:29:44<3:22:19,  1.37s/it]
 86%|████████▌ | 53072/61904 [4:29:45<3:20:59,  1.37s/it]
 86%|████████▌ | 53073/61904 [4:29:47<3:25:26,  1.40s/it]
 86%|████████▌ | 53074/61904 [4:29:48<3:25:52,  1.40s/it]
 86%|████████▌ | 53075/61904 [4:29:50<3:29:37,  1.42s/it]
 86%|████████▌ | 53076/61904 [4:29:51<3:21:15,  1.37s/it]
 86%|████████▌ | 53077/61904 [4:29:52<3:18:41,  1.35s/it]
 86%|████████▌ | 53078/61904 [4:29:53<3:17:33,  1.34s/it]
 86%|████████▌ | 53079/61904 [4:29:55<3:27:43,  1.41s/it]
 86%|████████▌ | 53080/61904 [4:29:56<3:28:05,  1.41s/it]
                                                         
{'loss': 2.4558, 'learning_rate': 1.1430053157007649e-07, 'epoch': 13.72}

 86%|████████▌ | 53080/61904 [4:29:56<3:28:05,  1.41s/it]
 86%|████████▌ | 53081/61904 [4:29:58<3:21:39,  1.37s/it]
 86%|████████▌ | 53082/61904 [4:29:59<3:19:33,  1.36s/it]
 86%|████████▌ | 53083/61904 [4:30:00<3:14:51,  1.33s/it]
 86%|████████▌ | 53084/61904 [4:30:02<3:12:00,  1.31s/it]
 86%|████████▌ | 53085/61904 [4:30:03<3:17:50,  1.35s/it]
 86%|████████▌ | 53086/61904 [4:30:04<3:17:13,  1.34s/it]
 86%|████████▌ | 53087/61904 [4:30:06<3:14:44,  1.33s/it]
 86%|████████▌ | 53088/61904 [4:30:07<3:20:36,  1.37s/it]
 86%|████████▌ | 53089/61904 [4:30:08<3:15:58,  1.33s/it]
 86%|████████▌ | 53090/61904 [4:30:10<3:14:55,  1.33s/it]
 86%|████████▌ | 53091/61904 [4:30:11<3:11:53,  1.31s/it]
 86%|████████▌ | 53092/61904 [4:30:12<3:16:09,  1.34s/it]
 86%|████████▌ | 53093/61904 [4:30:14<3:17:14,  1.34s/it]
 86%|████████▌ | 53094/61904 [4:30:15<3:21:34,  1.37s/it]
 86%|████████▌ | 53095/61904 [4:30:17<3:27:48,  1.42s/it]
 86%|████████▌ | 53096/61904 [4:30:18<3:20:38,  1.37s/it]
 86%|████████▌ | 53097/61904 [4:30:19<3:20:52,  1.37s/it]
 86%|████████▌ | 53098/61904 [4:30:21<3:23:24,  1.39s/it]
 86%|████████▌ | 53099/61904 [4:30:22<3:22:05,  1.38s/it]
 86%|████████▌ | 53100/61904 [4:30:23<3:22:02,  1.38s/it]
                                                         
{'loss': 2.4658, 'learning_rate': 1.1426811876053417e-07, 'epoch': 13.72}

 86%|████████▌ | 53100/61904 [4:30:23<3:22:02,  1.38s/it]
 86%|████████▌ | 53101/61904 [4:30:25<3:18:57,  1.36s/it]
 86%|████████▌ | 53102/61904 [4:30:26<3:13:36,  1.32s/it]
 86%|████████▌ | 53103/61904 [4:30:27<3:18:31,  1.35s/it]
 86%|████████▌ | 53104/61904 [4:30:29<3:17:16,  1.35s/it]
 86%|████████▌ | 53105/61904 [4:30:30<3:22:47,  1.38s/it]
 86%|████████▌ | 53106/61904 [4:30:32<3:23:55,  1.39s/it]
 86%|████████▌ | 53107/61904 [4:30:33<3:21:51,  1.38s/it]
 86%|████████▌ | 53108/61904 [4:30:34<3:27:30,  1.42s/it]
 86%|████████▌ | 53109/61904 [4:30:36<3:24:44,  1.40s/it]
 86%|████████▌ | 53110/61904 [4:30:37<3:20:11,  1.37s/it]
 86%|████████▌ | 53111/61904 [4:30:39<3:27:54,  1.42s/it]
 86%|████████▌ | 53112/61904 [4:30:40<3:23:05,  1.39s/it]
 86%|████████▌ | 53113/61904 [4:30:41<3:22:26,  1.38s/it]
 86%|████████▌ | 53114/61904 [4:30:43<3:21:47,  1.38s/it]
 86%|████████▌ | 53115/61904 [4:30:44<3:18:05,  1.35s/it]
 86%|████████▌ | 53116/61904 [4:30:45<3:14:55,  1.33s/it]
 86%|████████▌ | 53117/61904 [4:30:47<3:19:54,  1.37s/it]
 86%|████████▌ | 53118/61904 [4:30:48<3:22:33,  1.38s/it]
 86%|████████▌ | 53119/61904 [4:30:50<3:22:42,  1.38s/it]
 86%|████████▌ | 53120/61904 [4:30:51<3:20:22,  1.37s/it]
                                                         
{'loss': 2.3885, 'learning_rate': 1.1423570595099181e-07, 'epoch': 13.73}

 86%|████████▌ | 53120/61904 [4:30:51<3:20:22,  1.37s/it]
 86%|████████▌ | 53121/61904 [4:30:52<3:21:59,  1.38s/it]
 86%|████████▌ | 53122/61904 [4:30:54<3:19:44,  1.36s/it]
 86%|████████▌ | 53123/61904 [4:30:55<3:21:35,  1.38s/it]
 86%|████████▌ | 53124/61904 [4:30:56<3:20:01,  1.37s/it]
 86%|████████▌ | 53125/61904 [4:30:58<3:24:14,  1.40s/it]
 86%|████████▌ | 53126/61904 [4:30:59<3:26:22,  1.41s/it]
 86%|████████▌ | 53127/61904 [4:31:01<3:22:05,  1.38s/it]
 86%|████████▌ | 53128/61904 [4:31:02<3:19:00,  1.36s/it]
 86%|████████▌ | 53129/61904 [4:31:03<3:20:30,  1.37s/it]
 86%|████████▌ | 53130/61904 [4:31:04<3:13:27,  1.32s/it]
 86%|████████▌ | 53131/61904 [4:31:06<3:17:29,  1.35s/it]
 86%|████████▌ | 53132/61904 [4:31:07<3:20:44,  1.37s/it]
 86%|████████▌ | 53133/61904 [4:31:09<3:17:11,  1.35s/it]
 86%|████████▌ | 53134/61904 [4:31:10<3:25:21,  1.40s/it]
 86%|████████▌ | 53135/61904 [4:31:11<3:22:03,  1.38s/it]
 86%|████████▌ | 53136/61904 [4:31:13<3:25:28,  1.41s/it]
 86%|████████▌ | 53137/61904 [4:31:14<3:19:59,  1.37s/it]
 86%|████████▌ | 53138/61904 [4:31:16<3:22:53,  1.39s/it]
 86%|████████▌ | 53139/61904 [4:31:17<3:11:51,  1.31s/it]
 86%|████████▌ | 53140/61904 [4:31:18<3:18:12,  1.36s/it]
                                                         
{'loss': 2.44, 'learning_rate': 1.142032931414495e-07, 'epoch': 13.73}

 86%|████████▌ | 53140/61904 [4:31:18<3:18:12,  1.36s/it]
 86%|████████▌ | 53141/61904 [4:31:19<3:12:20,  1.32s/it]
 86%|████████▌ | 53142/61904 [4:31:21<3:09:55,  1.30s/it]
 86%|████████▌ | 53143/61904 [4:31:22<3:11:04,  1.31s/it]
 86%|████████▌ | 53144/61904 [4:31:24<3:18:16,  1.36s/it]
 86%|████████▌ | 53145/61904 [4:31:25<3:19:46,  1.37s/it]
 86%|████████▌ | 53146/61904 [4:31:26<3:19:41,  1.37s/it]
 86%|████████▌ | 53147/61904 [4:31:28<3:22:10,  1.39s/it]
 86%|████████▌ | 53148/61904 [4:31:29<3:16:42,  1.35s/it]
 86%|████████▌ | 53149/61904 [4:31:30<3:14:25,  1.33s/it]
 86%|████████▌ | 53150/61904 [4:31:32<3:18:52,  1.36s/it]
 86%|████████▌ | 53151/61904 [4:31:33<3:20:19,  1.37s/it]
 86%|████████▌ | 53152/61904 [4:31:34<3:19:02,  1.36s/it]
 86%|████████▌ | 53153/61904 [4:31:36<3:13:34,  1.33s/it]
 86%|████████▌ | 53154/61904 [4:31:37<3:18:47,  1.36s/it]
 86%|████████▌ | 53155/61904 [4:31:39<3:18:49,  1.36s/it]
 86%|████████▌ | 53156/61904 [4:31:40<3:18:57,  1.36s/it]
 86%|████████▌ | 53157/61904 [4:31:41<3:21:50,  1.38s/it]
 86%|████████▌ | 53158/61904 [4:31:43<3:22:12,  1.39s/it]
 86%|████████▌ | 53159/61904 [4:31:44<3:19:22,  1.37s/it]
 86%|████████▌ | 53160/61904 [4:31:45<3:19:48,  1.37s/it]
                                                         
{'loss': 2.4517, 'learning_rate': 1.1417088033190716e-07, 'epoch': 13.74}

 86%|████████▌ | 53160/61904 [4:31:45<3:19:48,  1.37s/it]
 86%|████████▌ | 53161/61904 [4:31:47<3:16:23,  1.35s/it]
 86%|████████▌ | 53162/61904 [4:31:48<3:21:04,  1.38s/it]
 86%|████████▌ | 53163/61904 [4:31:50<3:27:21,  1.42s/it]
 86%|████████▌ | 53164/61904 [4:31:51<3:20:46,  1.38s/it]
 86%|████████▌ | 53165/61904 [4:31:52<3:22:19,  1.39s/it]
 86%|████████▌ | 53166/61904 [4:31:54<3:23:20,  1.40s/it]
 86%|████████▌ | 53167/61904 [4:31:55<3:25:19,  1.41s/it]
 86%|████████▌ | 53168/61904 [4:31:57<3:19:40,  1.37s/it]
 86%|████████▌ | 53169/61904 [4:31:58<3:18:25,  1.36s/it]
 86%|████████▌ | 53170/61904 [4:31:59<3:15:18,  1.34s/it]
 86%|████████▌ | 53171/61904 [4:32:01<3:17:15,  1.36s/it]
 86%|████████▌ | 53172/61904 [4:32:02<3:15:34,  1.34s/it]
 86%|████████▌ | 53173/61904 [4:32:03<3:16:55,  1.35s/it]
 86%|████████▌ | 53174/61904 [4:32:05<3:15:41,  1.34s/it]
 86%|████████▌ | 53175/61904 [4:32:06<3:18:09,  1.36s/it]
 86%|████████▌ | 53176/61904 [4:32:07<3:22:26,  1.39s/it]
 86%|████████▌ | 53177/61904 [4:32:09<3:25:35,  1.41s/it]
 86%|████████▌ | 53178/61904 [4:32:10<3:28:36,  1.43s/it]
 86%|████████▌ | 53179/61904 [4:32:12<3:32:39,  1.46s/it]
 86%|████████▌ | 53180/61904 [4:32:13<3:23:50,  1.40s/it]
                                                         
{'loss': 2.4766, 'learning_rate': 1.1413846752236485e-07, 'epoch': 13.74}

 86%|████████▌ | 53180/61904 [4:32:13<3:23:50,  1.40s/it]
 86%|████████▌ | 53181/61904 [4:32:14<3:17:27,  1.36s/it]
 86%|████████▌ | 53182/61904 [4:32:16<3:19:36,  1.37s/it]
 86%|████████▌ | 53183/61904 [4:32:17<3:18:36,  1.37s/it]
 86%|████████▌ | 53184/61904 [4:32:19<3:23:49,  1.40s/it]
 86%|████████▌ | 53185/61904 [4:32:20<3:22:24,  1.39s/it]
 86%|████████▌ | 53186/61904 [4:32:21<3:22:05,  1.39s/it]
 86%|████████▌ | 53187/61904 [4:32:23<3:20:56,  1.38s/it]
 86%|████████▌ | 53188/61904 [4:32:24<3:16:36,  1.35s/it]
 86%|████████▌ | 53189/61904 [4:32:25<3:13:22,  1.33s/it]
 86%|████████▌ | 53190/61904 [4:32:27<3:11:34,  1.32s/it]
 86%|████████▌ | 53191/61904 [4:32:28<3:20:30,  1.38s/it]
 86%|████████▌ | 53192/61904 [4:32:30<3:26:52,  1.42s/it]
 86%|████████▌ | 53193/61904 [4:32:31<3:23:04,  1.40s/it]
 86%|████████▌ | 53194/61904 [4:32:32<3:21:17,  1.39s/it]
 86%|████████▌ | 53195/61904 [4:32:34<3:19:16,  1.37s/it]
 86%|████████▌ | 53196/61904 [4:32:35<3:23:40,  1.40s/it]
 86%|████████▌ | 53197/61904 [4:32:37<3:22:04,  1.39s/it]
 86%|████████▌ | 53198/61904 [4:32:38<3:19:28,  1.37s/it]
 86%|████████▌ | 53199/61904 [4:32:39<3:22:10,  1.39s/it]
 86%|████████▌ | 53200/61904 [4:32:41<3:12:57,  1.33s/it]
                                                         
{'loss': 2.447, 'learning_rate': 1.1410605471282248e-07, 'epoch': 13.75}

 86%|████████▌ | 53200/61904 [4:32:41<3:12:57,  1.33s/it]
 86%|████████▌ | 53201/61904 [4:32:42<3:08:43,  1.30s/it]
 86%|████████▌ | 53202/61904 [4:32:43<3:06:42,  1.29s/it]
 86%|████████▌ | 53203/61904 [4:32:44<3:07:18,  1.29s/it]
 86%|████████▌ | 53204/61904 [4:32:46<3:08:39,  1.30s/it]
 86%|████████▌ | 53205/61904 [4:32:47<3:13:17,  1.33s/it]
 86%|████████▌ | 53206/61904 [4:32:48<3:14:56,  1.34s/it]
 86%|████████▌ | 53207/61904 [4:32:50<3:18:11,  1.37s/it]
 86%|████████▌ | 53208/61904 [4:32:51<3:13:25,  1.33s/it]
 86%|████████▌ | 53209/61904 [4:32:53<3:20:34,  1.38s/it]
 86%|████████▌ | 53210/61904 [4:32:54<3:21:48,  1.39s/it]
 86%|████████▌ | 53211/61904 [4:32:55<3:19:49,  1.38s/it]
 86%|████████▌ | 53212/61904 [4:32:57<3:22:51,  1.40s/it]
 86%|████████▌ | 53213/61904 [4:32:58<3:23:17,  1.40s/it]
 86%|████████▌ | 53214/61904 [4:33:00<3:22:19,  1.40s/it]
 86%|████████▌ | 53215/61904 [4:33:01<3:15:54,  1.35s/it]
 86%|████████▌ | 53216/61904 [4:33:02<3:18:26,  1.37s/it]
 86%|████████▌ | 53217/61904 [4:33:04<3:15:09,  1.35s/it]
 86%|████████▌ | 53218/61904 [4:33:05<3:14:01,  1.34s/it]
 86%|████████▌ | 53219/61904 [4:33:06<3:13:32,  1.34s/it]
 86%|████████▌ | 53220/61904 [4:33:08<3:28:01,  1.44s/it]
                                                         
{'loss': 2.4432, 'learning_rate': 1.1407364190328017e-07, 'epoch': 13.76}

 86%|████████▌ | 53220/61904 [4:33:08<3:28:01,  1.44s/it]
 86%|████████▌ | 53221/61904 [4:33:09<3:23:01,  1.40s/it]
 86%|████████▌ | 53222/61904 [4:33:11<3:23:37,  1.41s/it]
 86%|████████▌ | 53223/61904 [4:33:12<3:20:46,  1.39s/it]
 86%|████████▌ | 53224/61904 [4:33:13<3:27:14,  1.43s/it]
 86%|████████▌ | 53225/61904 [4:33:15<3:24:35,  1.41s/it]
 86%|████████▌ | 53226/61904 [4:33:16<3:27:52,  1.44s/it]
 86%|████████▌ | 53227/61904 [4:33:18<3:19:20,  1.38s/it]
 86%|████████▌ | 53228/61904 [4:33:19<3:12:25,  1.33s/it]
 86%|████████▌ | 53229/61904 [4:33:20<3:16:59,  1.36s/it]
 86%|████████▌ | 53230/61904 [4:33:21<3:11:15,  1.32s/it]
 86%|████████▌ | 53231/61904 [4:33:23<3:15:54,  1.36s/it]
 86%|████████▌ | 53232/61904 [4:33:24<3:14:30,  1.35s/it]
 86%|████████▌ | 53233/61904 [4:33:26<3:15:52,  1.36s/it]
 86%|████████▌ | 53234/61904 [4:33:27<3:15:01,  1.35s/it]
 86%|████████▌ | 53235/61904 [4:33:28<3:12:46,  1.33s/it]
 86%|████████▌ | 53236/61904 [4:33:30<3:09:27,  1.31s/it]
 86%|████████▌ | 53237/61904 [4:33:31<3:12:23,  1.33s/it]
 86%|████████▌ | 53238/61904 [4:33:32<3:14:41,  1.35s/it]
 86%|████████▌ | 53239/61904 [4:33:34<3:11:33,  1.33s/it]
 86%|████████▌ | 53240/61904 [4:33:35<3:19:12,  1.38s/it]
                                                         
{'loss': 2.4773, 'learning_rate': 1.1404122909373786e-07, 'epoch': 13.76}

 86%|████████▌ | 53240/61904 [4:33:35<3:19:12,  1.38s/it]
 86%|████████▌ | 53241/61904 [4:33:37<3:36:28,  1.50s/it]
 86%|████████▌ | 53242/61904 [4:33:38<3:33:03,  1.48s/it]
 86%|████████▌ | 53243/61904 [4:33:40<3:30:27,  1.46s/it]
 86%|████████▌ | 53244/61904 [4:33:41<3:27:22,  1.44s/it]
 86%|████████▌ | 53245/61904 [4:33:43<3:29:46,  1.45s/it]
 86%|████████▌ | 53246/61904 [4:33:44<3:30:13,  1.46s/it]
 86%|████████▌ | 53247/61904 [4:33:45<3:24:38,  1.42s/it]
 86%|████████▌ | 53248/61904 [4:33:47<3:34:02,  1.48s/it]
 86%|████████▌ | 53249/61904 [4:33:48<3:23:08,  1.41s/it]
 86%|████████▌ | 53250/61904 [4:33:50<3:19:07,  1.38s/it]
 86%|████████▌ | 53251/61904 [4:33:51<3:20:14,  1.39s/it]
 86%|████████▌ | 53252/61904 [4:33:53<3:29:19,  1.45s/it]
 86%|████████▌ | 53253/61904 [4:33:54<3:25:09,  1.42s/it]
 86%|████████▌ | 53254/61904 [4:33:55<3:22:27,  1.40s/it]
 86%|████████▌ | 53255/61904 [4:33:57<3:26:15,  1.43s/it]
 86%|████████▌ | 53256/61904 [4:33:58<3:21:35,  1.40s/it]
 86%|████████▌ | 53257/61904 [4:33:59<3:15:26,  1.36s/it]
 86%|████████▌ | 53258/61904 [4:34:01<3:10:48,  1.32s/it]
 86%|████████▌ | 53259/61904 [4:34:02<3:14:36,  1.35s/it]
 86%|████████▌ | 53260/61904 [4:34:03<3:18:56,  1.38s/it]
                                                         
{'loss': 2.455, 'learning_rate': 1.140088162841955e-07, 'epoch': 13.77}

 86%|████████▌ | 53260/61904 [4:34:03<3:18:56,  1.38s/it]
 86%|████████▌ | 53261/61904 [4:34:05<3:21:31,  1.40s/it]
 86%|████████▌ | 53262/61904 [4:34:06<3:13:23,  1.34s/it]
 86%|████████▌ | 53263/61904 [4:34:07<3:12:45,  1.34s/it]
 86%|████████▌ | 53264/61904 [4:34:09<3:14:01,  1.35s/it]
 86%|████████▌ | 53265/61904 [4:34:10<3:15:48,  1.36s/it]
 86%|████████▌ | 53266/61904 [4:34:12<3:17:01,  1.37s/it]
 86%|████████▌ | 53267/61904 [4:34:13<3:17:58,  1.38s/it]
 86%|████████▌ | 53268/61904 [4:34:14<3:13:33,  1.34s/it]
 86%|████████▌ | 53269/61904 [4:34:16<3:20:52,  1.40s/it]
 86%|████████▌ | 53270/61904 [4:34:17<3:21:58,  1.40s/it]
 86%|████████▌ | 53271/61904 [4:34:18<3:15:51,  1.36s/it]
 86%|████████▌ | 53272/61904 [4:34:20<3:18:12,  1.38s/it]
 86%|████████▌ | 53273/61904 [4:34:21<3:16:09,  1.36s/it]
 86%|████████▌ | 53274/61904 [4:34:23<3:18:28,  1.38s/it]
 86%|████████▌ | 53275/61904 [4:34:24<3:17:08,  1.37s/it]
 86%|████████▌ | 53276/61904 [4:34:25<3:16:43,  1.37s/it]
 86%|████████▌ | 53277/61904 [4:34:27<3:16:17,  1.37s/it]
 86%|████████▌ | 53278/61904 [4:34:28<3:19:26,  1.39s/it]
 86%|████████▌ | 53279/61904 [4:34:29<3:15:37,  1.36s/it]
 86%|████████▌ | 53280/61904 [4:34:31<3:16:46,  1.37s/it]
                                                         
{'loss': 2.4651, 'learning_rate': 1.1397640347465318e-07, 'epoch': 13.77}

 86%|████████▌ | 53280/61904 [4:34:31<3:16:46,  1.37s/it]
 86%|████████▌ | 53281/61904 [4:34:32<3:20:22,  1.39s/it]
 86%|████████▌ | 53282/61904 [4:34:34<3:17:27,  1.37s/it]
 86%|████████▌ | 53283/61904 [4:34:35<3:17:11,  1.37s/it]
 86%|████████▌ | 53284/61904 [4:34:36<3:18:53,  1.38s/it]
 86%|████████▌ | 53285/61904 [4:34:38<3:12:04,  1.34s/it]
 86%|████████▌ | 53286/61904 [4:34:39<3:10:17,  1.32s/it]
 86%|████████▌ | 53287/61904 [4:34:40<3:16:01,  1.36s/it]
 86%|████████▌ | 53288/61904 [4:34:42<3:11:27,  1.33s/it]
 86%|████████▌ | 53289/61904 [4:34:43<3:23:29,  1.42s/it]
 86%|████████▌ | 53290/61904 [4:34:45<3:22:42,  1.41s/it]
 86%|████████▌ | 53291/61904 [4:34:46<3:18:54,  1.39s/it]
 86%|████████▌ | 53292/61904 [4:34:47<3:22:33,  1.41s/it]
 86%|████████▌ | 53293/61904 [4:34:49<3:21:01,  1.40s/it]
 86%|████████▌ | 53294/61904 [4:34:50<3:22:03,  1.41s/it]
 86%|████████▌ | 53295/61904 [4:34:51<3:15:12,  1.36s/it]
 86%|████████▌ | 53296/61904 [4:34:53<3:16:10,  1.37s/it]
 86%|████████▌ | 53297/61904 [4:34:54<3:18:23,  1.38s/it]
 86%|████████▌ | 53298/61904 [4:34:56<3:23:29,  1.42s/it]
 86%|████████▌ | 53299/61904 [4:34:57<3:16:34,  1.37s/it]
 86%|████████▌ | 53300/61904 [4:34:58<3:14:23,  1.36s/it]
                                                         
{'loss': 2.4309, 'learning_rate': 1.1394399066511085e-07, 'epoch': 13.78}

 86%|████████▌ | 53300/61904 [4:34:58<3:14:23,  1.36s/it]
 86%|████████▌ | 53301/61904 [4:35:00<3:14:41,  1.36s/it]
 86%|████████▌ | 53302/61904 [4:35:01<3:13:27,  1.35s/it]
 86%|████████▌ | 53303/61904 [4:35:02<3:11:33,  1.34s/it]
 86%|████████▌ | 53304/61904 [4:35:04<3:10:41,  1.33s/it]
 86%|████████▌ | 53305/61904 [4:35:05<3:13:53,  1.35s/it]
 86%|████████▌ | 53306/61904 [4:35:06<3:15:11,  1.36s/it]
 86%|████████▌ | 53307/61904 [4:35:08<3:14:50,  1.36s/it]
 86%|████████▌ | 53308/61904 [4:35:09<3:14:38,  1.36s/it]
 86%|████████▌ | 53309/61904 [4:35:11<3:24:29,  1.43s/it]
 86%|████████▌ | 53310/61904 [4:35:12<3:18:19,  1.38s/it]
 86%|████████▌ | 53311/61904 [4:35:13<3:10:10,  1.33s/it]
 86%|████████▌ | 53312/61904 [4:35:15<3:14:23,  1.36s/it]
 86%|████████▌ | 53313/61904 [4:35:16<3:15:11,  1.36s/it]
 86%|████████▌ | 53314/61904 [4:35:18<3:22:19,  1.41s/it]
 86%|████████▌ | 53315/61904 [4:35:19<3:12:25,  1.34s/it]
 86%|████████▌ | 53316/61904 [4:35:20<3:12:59,  1.35s/it]
 86%|████████▌ | 53317/61904 [4:35:21<3:09:43,  1.33s/it]
 86%|████████▌ | 53318/61904 [4:35:23<3:09:05,  1.32s/it]
 86%|████████▌ | 53319/61904 [4:35:24<3:10:44,  1.33s/it]
 86%|████████▌ | 53320/61904 [4:35:25<3:14:05,  1.36s/it]
                                                         
{'loss': 2.4539, 'learning_rate': 1.1391157785556853e-07, 'epoch': 13.78}

 86%|████████▌ | 53320/61904 [4:35:25<3:14:05,  1.36s/it]
 86%|████████▌ | 53321/61904 [4:35:27<3:10:10,  1.33s/it]
 86%|████████▌ | 53322/61904 [4:35:28<3:09:33,  1.33s/it]
 86%|████████▌ | 53323/61904 [4:35:29<3:10:17,  1.33s/it]
 86%|████████▌ | 53324/61904 [4:35:31<3:08:19,  1.32s/it]
 86%|████████▌ | 53325/61904 [4:35:32<3:12:32,  1.35s/it]
 86%|████████▌ | 53326/61904 [4:35:33<3:15:48,  1.37s/it]
 86%|████████▌ | 53327/61904 [4:35:35<3:19:41,  1.40s/it]
 86%|████████▌ | 53328/61904 [4:35:36<3:14:52,  1.36s/it]
 86%|████████▌ | 53329/61904 [4:35:38<3:13:40,  1.36s/it]
 86%|████████▌ | 53330/61904 [4:35:39<3:10:46,  1.34s/it]
 86%|████████▌ | 53331/61904 [4:35:40<3:09:20,  1.33s/it]
 86%|████████▌ | 53332/61904 [4:35:42<3:11:46,  1.34s/it]
 86%|████████▌ | 53333/61904 [4:35:43<3:15:03,  1.37s/it]
 86%|████████▌ | 53334/61904 [4:35:44<3:17:23,  1.38s/it]
 86%|████████▌ | 53335/61904 [4:35:46<3:18:26,  1.39s/it]
 86%|████████▌ | 53336/61904 [4:35:47<3:16:49,  1.38s/it]
 86%|████████▌ | 53337/61904 [4:35:48<3:15:12,  1.37s/it]
 86%|████████▌ | 53338/61904 [4:35:50<3:19:29,  1.40s/it]
 86%|████████▌ | 53339/61904 [4:35:51<3:15:14,  1.37s/it]
 86%|████████▌ | 53340/61904 [4:35:53<3:21:22,  1.41s/it]
                                                         
{'loss': 2.4259, 'learning_rate': 1.1387916504602617e-07, 'epoch': 13.79}

 86%|████████▌ | 53340/61904 [4:35:53<3:21:22,  1.41s/it]
 86%|████████▌ | 53341/61904 [4:35:54<3:19:53,  1.40s/it]
 86%|████████▌ | 53342/61904 [4:35:56<3:19:33,  1.40s/it]
 86%|████████▌ | 53343/61904 [4:35:57<3:17:49,  1.39s/it]
 86%|████████▌ | 53344/61904 [4:35:58<3:13:34,  1.36s/it]
 86%|████████▌ | 53345/61904 [4:36:00<3:15:50,  1.37s/it]
 86%|████████▌ | 53346/61904 [4:36:01<3:18:06,  1.39s/it]
 86%|████████▌ | 53347/61904 [4:36:03<3:22:30,  1.42s/it]
 86%|████████▌ | 53348/61904 [4:36:04<3:21:39,  1.41s/it]
 86%|████████▌ | 53349/61904 [4:36:05<3:15:51,  1.37s/it]
 86%|████████▌ | 53350/61904 [4:36:07<3:15:17,  1.37s/it]
 86%|████████▌ | 53351/61904 [4:36:08<3:14:08,  1.36s/it]
 86%|████████▌ | 53352/61904 [4:36:09<3:18:01,  1.39s/it]
 86%|████████▌ | 53353/61904 [4:36:11<3:24:50,  1.44s/it]
 86%|████████▌ | 53354/61904 [4:36:12<3:29:21,  1.47s/it]
 86%|████████▌ | 53355/61904 [4:36:14<3:24:13,  1.43s/it]
 86%|████████▌ | 53356/61904 [4:36:15<3:24:41,  1.44s/it]
 86%|████████▌ | 53357/61904 [4:36:17<3:21:42,  1.42s/it]
 86%|████████▌ | 53358/61904 [4:36:18<3:15:44,  1.37s/it]
 86%|████████▌ | 53359/61904 [4:36:19<3:14:19,  1.36s/it]
 86%|████████▌ | 53360/61904 [4:36:21<3:12:14,  1.35s/it]
                                                         
{'loss': 2.357, 'learning_rate': 1.1384675223648386e-07, 'epoch': 13.79}

 86%|████████▌ | 53360/61904 [4:36:21<3:12:14,  1.35s/it]
 86%|████████▌ | 53361/61904 [4:36:22<3:07:29,  1.32s/it]
 86%|████████▌ | 53362/61904 [4:36:23<3:11:22,  1.34s/it]
 86%|████████▌ | 53363/61904 [4:36:25<3:12:21,  1.35s/it]
 86%|████████▌ | 53364/61904 [4:36:26<3:11:34,  1.35s/it]
 86%|████████▌ | 53365/61904 [4:36:27<3:13:13,  1.36s/it]
 86%|████████▌ | 53366/61904 [4:36:29<3:15:10,  1.37s/it]
 86%|████████▌ | 53367/61904 [4:36:30<3:16:48,  1.38s/it]
 86%|████████▌ | 53368/61904 [4:36:31<3:13:11,  1.36s/it]
 86%|████████▌ | 53369/61904 [4:36:33<3:18:23,  1.39s/it]
 86%|████████▌ | 53370/61904 [4:36:34<3:23:17,  1.43s/it]
 86%|████████▌ | 53371/61904 [4:36:36<3:25:12,  1.44s/it]
 86%|████████▌ | 53372/61904 [4:36:37<3:33:34,  1.50s/it]
 86%|████████▌ | 53373/61904 [4:36:39<3:32:09,  1.49s/it]
 86%|████████▌ | 53374/61904 [4:36:40<3:31:30,  1.49s/it]
 86%|████████▌ | 53375/61904 [4:36:42<3:31:28,  1.49s/it]
 86%|████████▌ | 53376/61904 [4:36:43<3:22:29,  1.42s/it]
 86%|████████▌ | 53377/61904 [4:36:45<3:18:31,  1.40s/it]
 86%|████████▌ | 53378/61904 [4:36:46<3:16:34,  1.38s/it]
 86%|████████▌ | 53379/61904 [4:36:47<3:10:35,  1.34s/it]
 86%|████████▌ | 53380/61904 [4:36:49<3:15:15,  1.37s/it]
                                                         
{'loss': 2.4122, 'learning_rate': 1.1381433942694152e-07, 'epoch': 13.8}

 86%|████████▌ | 53380/61904 [4:36:49<3:15:15,  1.37s/it]
 86%|████████▌ | 53381/61904 [4:36:50<3:16:14,  1.38s/it]
 86%|████████▌ | 53382/61904 [4:36:51<3:15:56,  1.38s/it]
 86%|████████▌ | 53383/61904 [4:36:53<3:12:46,  1.36s/it]
 86%|████████▌ | 53384/61904 [4:36:54<3:13:57,  1.37s/it]
 86%|████████▌ | 53385/61904 [4:36:55<3:13:31,  1.36s/it]
 86%|████████▌ | 53386/61904 [4:36:57<3:08:22,  1.33s/it]
 86%|████████▌ | 53387/61904 [4:36:58<3:10:25,  1.34s/it]
 86%|████████▌ | 53388/61904 [4:36:59<3:15:33,  1.38s/it]
 86%|████████▌ | 53389/61904 [4:37:01<3:14:14,  1.37s/it]
 86%|████████▌ | 53390/61904 [4:37:02<3:19:36,  1.41s/it]
 86%|████████▌ | 53391/61904 [4:37:04<3:22:37,  1.43s/it]
 86%|████████▌ | 53392/61904 [4:37:05<3:25:52,  1.45s/it]
 86%|████████▋ | 53393/61904 [4:37:07<3:23:45,  1.44s/it]
 86%|████████▋ | 53394/61904 [4:37:08<3:17:08,  1.39s/it]
 86%|████████▋ | 53395/61904 [4:37:09<3:11:50,  1.35s/it]
 86%|████████▋ | 53396/61904 [4:37:11<3:15:18,  1.38s/it]
 86%|████████▋ | 53397/61904 [4:37:12<3:14:20,  1.37s/it]
 86%|████████▋ | 53398/61904 [4:37:13<3:16:09,  1.38s/it]
 86%|████████▋ | 53399/61904 [4:37:15<3:16:14,  1.38s/it]
 86%|████████▋ | 53400/61904 [4:37:16<3:20:57,  1.42s/it]
                                                         
{'loss': 2.435, 'learning_rate': 1.1378192661739921e-07, 'epoch': 13.8}

 86%|████████▋ | 53400/61904 [4:37:16<3:20:57,  1.42s/it]
 86%|████████▋ | 53401/61904 [4:37:18<3:17:23,  1.39s/it]
 86%|████████▋ | 53402/61904 [4:37:19<3:12:55,  1.36s/it]
 86%|████████▋ | 53403/61904 [4:37:21<3:24:27,  1.44s/it]
 86%|████████▋ | 53404/61904 [4:37:22<3:17:47,  1.40s/it]
 86%|████████▋ | 53405/61904 [4:37:23<3:14:14,  1.37s/it]
 86%|████████▋ | 53406/61904 [4:37:25<3:12:42,  1.36s/it]
 86%|████████▋ | 53407/61904 [4:37:26<3:10:48,  1.35s/it]
 86%|████████▋ | 53408/61904 [4:37:27<3:11:07,  1.35s/it]
 86%|████████▋ | 53409/61904 [4:37:29<3:10:55,  1.35s/it]
 86%|████████▋ | 53410/61904 [4:37:30<3:15:32,  1.38s/it]
 86%|████████▋ | 53411/61904 [4:37:31<3:13:51,  1.37s/it]
 86%|████████▋ | 53412/61904 [4:37:33<3:12:23,  1.36s/it]
 86%|████████▋ | 53413/61904 [4:37:34<3:10:06,  1.34s/it]
 86%|████████▋ | 53414/61904 [4:37:35<3:08:14,  1.33s/it]
 86%|████████▋ | 53415/61904 [4:37:37<3:12:24,  1.36s/it]
 86%|████████▋ | 53416/61904 [4:37:38<3:24:34,  1.45s/it]
 86%|████████▋ | 53417/61904 [4:37:40<3:23:51,  1.44s/it]
 86%|████████▋ | 53418/61904 [4:37:41<3:19:31,  1.41s/it]
 86%|████████▋ | 53419/61904 [4:37:43<3:21:36,  1.43s/it]
 86%|████████▋ | 53420/61904 [4:37:44<3:19:15,  1.41s/it]
                                                         
{'loss': 2.4501, 'learning_rate': 1.1374951380785684e-07, 'epoch': 13.81}

 86%|████████▋ | 53420/61904 [4:37:44<3:19:15,  1.41s/it]
 86%|████████▋ | 53421/61904 [4:37:45<3:16:08,  1.39s/it]
 86%|████████▋ | 53422/61904 [4:37:47<3:12:51,  1.36s/it]
 86%|████████▋ | 53423/61904 [4:37:48<3:15:56,  1.39s/it]
 86%|████████▋ | 53424/61904 [4:37:49<3:15:36,  1.38s/it]
 86%|████████▋ | 53425/61904 [4:37:51<3:17:07,  1.39s/it]
 86%|████████▋ | 53426/61904 [4:37:52<3:16:37,  1.39s/it]
 86%|████████▋ | 53427/61904 [4:37:54<3:18:34,  1.41s/it]
 86%|████████▋ | 53428/61904 [4:37:55<3:19:58,  1.42s/it]
 86%|████████▋ | 53429/61904 [4:37:57<3:20:06,  1.42s/it]
 86%|████████▋ | 53430/61904 [4:37:58<3:23:35,  1.44s/it]
 86%|████████▋ | 53431/61904 [4:37:59<3:14:58,  1.38s/it]
 86%|████████▋ | 53432/61904 [4:38:01<3:16:24,  1.39s/it]
 86%|████████▋ | 53433/61904 [4:38:02<3:14:57,  1.38s/it]
 86%|████████▋ | 53434/61904 [4:38:04<3:19:31,  1.41s/it]
 86%|████████▋ | 53435/61904 [4:38:05<3:23:25,  1.44s/it]
 86%|████████▋ | 53436/61904 [4:38:06<3:20:54,  1.42s/it]
 86%|████████▋ | 53437/61904 [4:38:08<3:18:05,  1.40s/it]
 86%|████████▋ | 53438/61904 [4:38:09<3:20:36,  1.42s/it]
 86%|████████▋ | 53439/61904 [4:38:11<3:19:49,  1.42s/it]
 86%|████████▋ | 53440/61904 [4:38:12<3:15:40,  1.39s/it]
                                                         
{'loss': 2.4191, 'learning_rate': 1.1371710099831453e-07, 'epoch': 13.81}

 86%|████████▋ | 53440/61904 [4:38:12<3:15:40,  1.39s/it]
 86%|████████▋ | 53441/61904 [4:38:13<3:20:18,  1.42s/it]
 86%|████████▋ | 53442/61904 [4:38:15<3:20:34,  1.42s/it]
 86%|████████▋ | 53443/61904 [4:38:16<3:26:47,  1.47s/it]
 86%|████████▋ | 53444/61904 [4:38:18<3:32:31,  1.51s/it]
 86%|████████▋ | 53445/61904 [4:38:20<3:30:08,  1.49s/it]
 86%|████████▋ | 53446/61904 [4:38:21<3:24:45,  1.45s/it]
 86%|████████▋ | 53447/61904 [4:38:22<3:18:03,  1.41s/it]
 86%|████████▋ | 53448/61904 [4:38:24<3:16:08,  1.39s/it]
 86%|████████▋ | 53449/61904 [4:38:25<3:15:39,  1.39s/it]
 86%|████████▋ | 53450/61904 [4:38:26<3:12:35,  1.37s/it]
 86%|████████▋ | 53451/61904 [4:38:28<3:15:26,  1.39s/it]
 86%|████████▋ | 53452/61904 [4:38:29<3:12:36,  1.37s/it]
 86%|████████▋ | 53453/61904 [4:38:30<3:11:04,  1.36s/it]
 86%|████████▋ | 53454/61904 [4:38:32<3:10:16,  1.35s/it]
 86%|████████▋ | 53455/61904 [4:38:33<3:15:20,  1.39s/it]
 86%|████████▋ | 53456/61904 [4:38:34<3:10:45,  1.35s/it]
 86%|████████▋ | 53457/61904 [4:38:36<3:14:55,  1.38s/it]
 86%|████████▋ | 53458/61904 [4:38:37<3:19:08,  1.41s/it]
 86%|████████▋ | 53459/61904 [4:38:39<3:12:03,  1.36s/it]
 86%|████████▋ | 53460/61904 [4:38:40<3:13:56,  1.38s/it]
                                                         
{'loss': 2.4168, 'learning_rate': 1.1368468818877219e-07, 'epoch': 13.82}

 86%|████████▋ | 53460/61904 [4:38:40<3:13:56,  1.38s/it]
 86%|████████▋ | 53461/61904 [4:38:41<3:15:28,  1.39s/it]
 86%|████████▋ | 53462/61904 [4:38:43<3:07:48,  1.33s/it]
 86%|████████▋ | 53463/61904 [4:38:44<3:07:31,  1.33s/it]
 86%|████████▋ | 53464/61904 [4:38:45<3:09:58,  1.35s/it]
 86%|████████▋ | 53465/61904 [4:38:47<3:11:55,  1.36s/it]
 86%|████████▋ | 53466/61904 [4:38:48<3:12:11,  1.37s/it]
 86%|████████▋ | 53467/61904 [4:38:50<3:14:05,  1.38s/it]
 86%|████████▋ | 53468/61904 [4:38:51<3:14:10,  1.38s/it]
 86%|████████▋ | 53469/61904 [4:38:52<3:20:50,  1.43s/it]
 86%|████████▋ | 53470/61904 [4:38:54<3:13:15,  1.37s/it]
 86%|████████▋ | 53471/61904 [4:38:55<3:19:05,  1.42s/it]
 86%|████████▋ | 53472/61904 [4:38:57<3:16:43,  1.40s/it]
 86%|████████▋ | 53473/61904 [4:38:58<3:12:54,  1.37s/it]
 86%|████████▋ | 53474/61904 [4:38:59<3:20:18,  1.43s/it]
 86%|████████▋ | 53475/61904 [4:39:01<3:17:20,  1.40s/it]
 86%|████████▋ | 53476/61904 [4:39:02<3:11:19,  1.36s/it]
 86%|████████▋ | 53477/61904 [4:39:04<3:15:53,  1.39s/it]
 86%|████████▋ | 53478/61904 [4:39:05<3:13:20,  1.38s/it]
 86%|████████▋ | 53479/61904 [4:39:06<3:09:22,  1.35s/it]
 86%|████████▋ | 53480/61904 [4:39:08<3:10:29,  1.36s/it]
                                                         
{'loss': 2.4114, 'learning_rate': 1.1365227537922988e-07, 'epoch': 13.82}

 86%|████████▋ | 53480/61904 [4:39:08<3:10:29,  1.36s/it]
 86%|████████▋ | 53481/61904 [4:39:09<3:04:22,  1.31s/it]
 86%|████████▋ | 53482/61904 [4:39:10<3:05:24,  1.32s/it]
 86%|████████▋ | 53483/61904 [4:39:12<3:10:32,  1.36s/it]
 86%|████████▋ | 53484/61904 [4:39:13<3:11:36,  1.37s/it]
 86%|████████▋ | 53485/61904 [4:39:14<3:17:49,  1.41s/it]
 86%|████████▋ | 53486/61904 [4:39:16<3:15:58,  1.40s/it]
 86%|████████▋ | 53487/61904 [4:39:17<3:11:04,  1.36s/it]
 86%|████████▋ | 53488/61904 [4:39:19<3:31:17,  1.51s/it]
 86%|████████▋ | 53489/61904 [4:39:20<3:24:32,  1.46s/it]
 86%|████████▋ | 53490/61904 [4:39:22<3:18:09,  1.41s/it]
 86%|████████▋ | 53491/61904 [4:39:23<3:19:04,  1.42s/it]
 86%|████████▋ | 53492/61904 [4:39:24<3:20:18,  1.43s/it]
 86%|████████▋ | 53493/61904 [4:39:26<3:18:49,  1.42s/it]
 86%|████████▋ | 53494/61904 [4:39:27<3:14:18,  1.39s/it]
 86%|████████▋ | 53495/61904 [4:39:29<3:14:21,  1.39s/it]
 86%|████████▋ | 53496/61904 [4:39:30<3:11:24,  1.37s/it]
 86%|████████▋ | 53497/61904 [4:39:31<3:14:03,  1.38s/it]
 86%|████████▋ | 53498/61904 [4:39:33<3:12:55,  1.38s/it]
 86%|████████▋ | 53499/61904 [4:39:34<3:16:18,  1.40s/it]
 86%|████████▋ | 53500/61904 [4:39:35<3:10:18,  1.36s/it]
                                                         
{'loss': 2.4437, 'learning_rate': 1.1361986256968752e-07, 'epoch': 13.83}

 86%|████████▋ | 53500/61904 [4:39:35<3:10:18,  1.36s/it]
 86%|████████▋ | 53501/61904 [4:39:37<3:09:15,  1.35s/it]
 86%|████████▋ | 53502/61904 [4:39:38<3:09:23,  1.35s/it]
 86%|████████▋ | 53503/61904 [4:39:39<3:10:58,  1.36s/it]
 86%|████████▋ | 53504/61904 [4:39:41<3:10:28,  1.36s/it]
 86%|████████▋ | 53505/61904 [4:39:42<3:07:04,  1.34s/it]
 86%|████████▋ | 53506/61904 [4:39:44<3:12:43,  1.38s/it]
 86%|████████▋ | 53507/61904 [4:39:45<3:14:04,  1.39s/it]
 86%|████████▋ | 53508/61904 [4:39:46<3:12:40,  1.38s/it]
 86%|████████▋ | 53509/61904 [4:39:48<3:13:24,  1.38s/it]
 86%|████████▋ | 53510/61904 [4:39:49<3:17:21,  1.41s/it]
 86%|████████▋ | 53511/61904 [4:39:51<3:15:47,  1.40s/it]
 86%|████████▋ | 53512/61904 [4:39:52<3:14:25,  1.39s/it]
 86%|████████▋ | 53513/61904 [4:39:53<3:12:32,  1.38s/it]
 86%|████████▋ | 53514/61904 [4:39:55<3:12:31,  1.38s/it]
 86%|████████▋ | 53515/61904 [4:39:56<3:08:58,  1.35s/it]
 86%|████████▋ | 53516/61904 [4:39:57<3:09:25,  1.35s/it]
 86%|████████▋ | 53517/61904 [4:39:59<3:11:39,  1.37s/it]
 86%|████████▋ | 53518/61904 [4:40:00<3:11:04,  1.37s/it]
 86%|████████▋ | 53519/61904 [4:40:01<3:07:12,  1.34s/it]
 86%|████████▋ | 53520/61904 [4:40:03<3:08:38,  1.35s/it]
                                                         
{'loss': 2.5263, 'learning_rate': 1.135874497601452e-07, 'epoch': 13.83}

 86%|████████▋ | 53520/61904 [4:40:03<3:08:38,  1.35s/it]
 86%|████████▋ | 53521/61904 [4:40:04<3:14:05,  1.39s/it]
 86%|████████▋ | 53522/61904 [4:40:05<3:07:41,  1.34s/it]
 86%|████████▋ | 53523/61904 [4:40:07<3:14:28,  1.39s/it]
 86%|████████▋ | 53524/61904 [4:40:08<3:07:39,  1.34s/it]
 86%|████████▋ | 53525/61904 [4:40:10<3:11:46,  1.37s/it]
 86%|████████▋ | 53526/61904 [4:40:11<3:14:21,  1.39s/it]
 86%|████████▋ | 53527/61904 [4:40:13<3:17:30,  1.41s/it]
 86%|████████▋ | 53528/61904 [4:40:14<3:21:26,  1.44s/it]
 86%|████████▋ | 53529/61904 [4:40:16<3:26:41,  1.48s/it]
 86%|████████▋ | 53530/61904 [4:40:17<3:19:11,  1.43s/it]
 86%|████████▋ | 53531/61904 [4:40:18<3:22:00,  1.45s/it]
 86%|████████▋ | 53532/61904 [4:40:20<3:25:15,  1.47s/it]
 86%|████████▋ | 53533/61904 [4:40:21<3:25:04,  1.47s/it]
 86%|████████▋ | 53534/61904 [4:40:23<3:13:01,  1.38s/it]
 86%|████████▋ | 53535/61904 [4:40:24<3:11:25,  1.37s/it]
 86%|████████▋ | 53536/61904 [4:40:25<3:19:23,  1.43s/it]
 86%|████████▋ | 53537/61904 [4:40:27<3:14:08,  1.39s/it]
 86%|████████▋ | 53538/61904 [4:40:28<3:11:22,  1.37s/it]
 86%|████████▋ | 53539/61904 [4:40:30<3:12:56,  1.38s/it]
 86%|████████▋ | 53540/61904 [4:40:31<3:15:51,  1.41s/it]
                                                         
{'loss': 2.3909, 'learning_rate': 1.1355503695060289e-07, 'epoch': 13.84}

 86%|████████▋ | 53540/61904 [4:40:31<3:15:51,  1.41s/it]
 86%|████████▋ | 53541/61904 [4:40:32<3:13:45,  1.39s/it]
 86%|████████▋ | 53542/61904 [4:40:34<3:14:41,  1.40s/it]
 86%|████████▋ | 53543/61904 [4:40:35<3:22:32,  1.45s/it]
 86%|████████▋ | 53544/61904 [4:40:37<3:19:31,  1.43s/it]
 86%|████████▋ | 53545/61904 [4:40:38<3:16:35,  1.41s/it]
 86%|████████▋ | 53546/61904 [4:40:39<3:12:54,  1.38s/it]
 87%|████████▋ | 53547/61904 [4:40:41<3:07:45,  1.35s/it]
 87%|████████▋ | 53548/61904 [4:40:42<3:06:31,  1.34s/it]
 87%|████████▋ | 53549/61904 [4:40:43<3:05:07,  1.33s/it]
 87%|████████▋ | 53550/61904 [4:40:45<3:05:43,  1.33s/it]
 87%|████████▋ | 53551/61904 [4:40:46<3:05:01,  1.33s/it]
 87%|████████▋ | 53552/61904 [4:40:47<3:12:50,  1.39s/it]
 87%|████████▋ | 53553/61904 [4:40:49<3:17:19,  1.42s/it]
 87%|████████▋ | 53554/61904 [4:40:50<3:12:17,  1.38s/it]
 87%|████████▋ | 53555/61904 [4:40:52<3:16:45,  1.41s/it]
 87%|████████▋ | 53556/61904 [4:40:53<3:18:07,  1.42s/it]
 87%|████████▋ | 53557/61904 [4:40:55<3:15:52,  1.41s/it]
 87%|████████▋ | 53558/61904 [4:40:56<3:11:10,  1.37s/it]
 87%|████████▋ | 53559/61904 [4:40:57<3:12:55,  1.39s/it]
 87%|████████▋ | 53560/61904 [4:40:59<3:22:42,  1.46s/it]
                                                         
{'loss': 2.4661, 'learning_rate': 1.1352262414106056e-07, 'epoch': 13.84}

 87%|████████▋ | 53560/61904 [4:40:59<3:22:42,  1.46s/it]
 87%|████████▋ | 53561/61904 [4:41:00<3:17:47,  1.42s/it]
 87%|████████▋ | 53562/61904 [4:41:02<3:15:36,  1.41s/it]
 87%|████████▋ | 53563/61904 [4:41:03<3:18:40,  1.43s/it]
 87%|████████▋ | 53564/61904 [4:41:04<3:16:09,  1.41s/it]
 87%|████████▋ | 53565/61904 [4:41:06<3:13:28,  1.39s/it]
 87%|████████▋ | 53566/61904 [4:41:07<3:24:23,  1.47s/it]
 87%|████████▋ | 53567/61904 [4:41:09<3:22:15,  1.46s/it]
 87%|████████▋ | 53568/61904 [4:41:10<3:18:19,  1.43s/it]
 87%|████████▋ | 53569/61904 [4:41:12<3:19:56,  1.44s/it]
 87%|████████▋ | 53570/61904 [4:41:13<3:18:43,  1.43s/it]
 87%|████████▋ | 53571/61904 [4:41:14<3:15:04,  1.40s/it]
 87%|████████▋ | 53572/61904 [4:41:16<3:10:24,  1.37s/it]
 87%|████████▋ | 53573/61904 [4:41:17<3:12:04,  1.38s/it]
 87%|████████▋ | 53574/61904 [4:41:19<3:14:11,  1.40s/it]
 87%|████████▋ | 53575/61904 [4:41:20<3:19:47,  1.44s/it]
 87%|████████▋ | 53576/61904 [4:41:21<3:13:09,  1.39s/it]
 87%|████████▋ | 53577/61904 [4:41:23<3:11:05,  1.38s/it]
 87%|████████▋ | 53578/61904 [4:41:24<3:15:46,  1.41s/it]
 87%|████████▋ | 53579/61904 [4:41:26<3:12:58,  1.39s/it]
 87%|████████▋ | 53580/61904 [4:41:27<3:14:21,  1.40s/it]
                                                         
{'loss': 2.3978, 'learning_rate': 1.1349021133151822e-07, 'epoch': 13.85}

 87%|████████▋ | 53580/61904 [4:41:27<3:14:21,  1.40s/it]
 87%|████████▋ | 53581/61904 [4:41:28<3:15:10,  1.41s/it]
 87%|████████▋ | 53582/61904 [4:41:30<3:10:31,  1.37s/it]
 87%|████████▋ | 53583/61904 [4:41:31<3:05:35,  1.34s/it]
 87%|████████▋ | 53584/61904 [4:41:32<3:09:20,  1.37s/it]
 87%|████████▋ | 53585/61904 [4:41:34<3:07:23,  1.35s/it]
 87%|████████▋ | 53586/61904 [4:41:35<3:11:09,  1.38s/it]
 87%|████████▋ | 53587/61904 [4:41:37<3:19:36,  1.44s/it]
 87%|████████▋ | 53588/61904 [4:41:38<3:19:12,  1.44s/it]
 87%|████████▋ | 53589/61904 [4:41:39<3:13:07,  1.39s/it]
 87%|████████▋ | 53590/61904 [4:41:41<3:07:43,  1.35s/it]
 87%|████████▋ | 53591/61904 [4:41:42<3:11:46,  1.38s/it]
 87%|████████▋ | 53592/61904 [4:41:44<3:09:03,  1.36s/it]
 87%|████████▋ | 53593/61904 [4:41:45<3:07:48,  1.36s/it]
 87%|████████▋ | 53594/61904 [4:41:46<3:06:19,  1.35s/it]
 87%|████████▋ | 53595/61904 [4:41:47<3:02:25,  1.32s/it]
 87%|████████▋ | 53596/61904 [4:41:49<3:05:46,  1.34s/it]
 87%|████████▋ | 53597/61904 [4:41:50<3:10:37,  1.38s/it]
 87%|████████▋ | 53598/61904 [4:41:52<3:06:24,  1.35s/it]
 87%|████████▋ | 53599/61904 [4:41:53<3:11:15,  1.38s/it]
 87%|████████▋ | 53600/61904 [4:41:54<3:10:42,  1.38s/it]
                                                         
{'loss': 2.4506, 'learning_rate': 1.1345779852197588e-07, 'epoch': 13.85}

 87%|████████▋ | 53600/61904 [4:41:54<3:10:42,  1.38s/it]
 87%|████████▋ | 53601/61904 [4:41:56<3:10:44,  1.38s/it]
 87%|████████▋ | 53602/61904 [4:41:57<3:07:22,  1.35s/it]
 87%|████████▋ | 53603/61904 [4:41:58<3:02:21,  1.32s/it]
 87%|████████▋ | 53604/61904 [4:42:00<3:02:23,  1.32s/it]
 87%|████████▋ | 53605/61904 [4:42:01<3:07:42,  1.36s/it]
 87%|████████▋ | 53606/61904 [4:42:02<3:10:24,  1.38s/it]
 87%|████████▋ | 53607/61904 [4:42:04<3:10:51,  1.38s/it]
 87%|████████▋ | 53608/61904 [4:42:06<3:21:24,  1.46s/it]
 87%|████████▋ | 53609/61904 [4:42:07<3:26:22,  1.49s/it]
 87%|████████▋ | 53610/61904 [4:42:08<3:15:06,  1.41s/it]
 87%|████████▋ | 53611/61904 [4:42:10<3:08:30,  1.36s/it]
 87%|████████▋ | 53612/61904 [4:42:11<3:14:12,  1.41s/it]
 87%|████████▋ | 53613/61904 [4:42:13<3:17:57,  1.43s/it]
 87%|████████▋ | 53614/61904 [4:42:14<3:19:05,  1.44s/it]
 87%|████████▋ | 53615/61904 [4:42:15<3:20:30,  1.45s/it]
 87%|████████▋ | 53616/61904 [4:42:17<3:15:56,  1.42s/it]
 87%|████████▋ | 53617/61904 [4:42:18<3:19:58,  1.45s/it]
 87%|████████▋ | 53618/61904 [4:42:20<3:15:58,  1.42s/it]
 87%|████████▋ | 53619/61904 [4:42:21<3:13:34,  1.40s/it]
 87%|████████▋ | 53620/61904 [4:42:22<3:13:21,  1.40s/it]
                                                         
{'loss': 2.4424, 'learning_rate': 1.1342538571243357e-07, 'epoch': 13.86}

 87%|████████▋ | 53620/61904 [4:42:22<3:13:21,  1.40s/it]
 87%|████████▋ | 53621/61904 [4:42:24<3:14:03,  1.41s/it]
 87%|████████▋ | 53622/61904 [4:42:26<3:25:29,  1.49s/it]
 87%|████████▋ | 53623/61904 [4:42:27<3:19:36,  1.45s/it]
 87%|████████▋ | 53624/61904 [4:42:28<3:16:02,  1.42s/it]
 87%|████████▋ | 53625/61904 [4:42:30<3:12:55,  1.40s/it]
 87%|████████▋ | 53626/61904 [4:42:31<3:11:36,  1.39s/it]
 87%|████████▋ | 53627/61904 [4:42:32<3:08:02,  1.36s/it]
 87%|████████▋ | 53628/61904 [4:42:34<3:16:43,  1.43s/it]
 87%|████████▋ | 53629/61904 [4:42:35<3:17:01,  1.43s/it]
 87%|████████▋ | 53630/61904 [4:42:37<3:16:50,  1.43s/it]
 87%|████████▋ | 53631/61904 [4:42:38<3:13:25,  1.40s/it]
 87%|████████▋ | 53632/61904 [4:42:40<3:18:24,  1.44s/it]
 87%|████████▋ | 53633/61904 [4:42:41<3:18:30,  1.44s/it]
 87%|████████▋ | 53634/61904 [4:42:43<3:21:28,  1.46s/it]
 87%|████████▋ | 53635/61904 [4:42:44<3:14:43,  1.41s/it]
 87%|████████▋ | 53636/61904 [4:42:45<3:14:01,  1.41s/it]
 87%|████████▋ | 53637/61904 [4:42:47<3:16:10,  1.42s/it]
 87%|████████▋ | 53638/61904 [4:42:48<3:11:15,  1.39s/it]
 87%|████████▋ | 53639/61904 [4:42:50<3:17:32,  1.43s/it]
 87%|████████▋ | 53640/61904 [4:42:51<3:17:17,  1.43s/it]
                                                         
{'loss': 2.4247, 'learning_rate': 1.1339297290289123e-07, 'epoch': 13.86}

 87%|████████▋ | 53640/61904 [4:42:51<3:17:17,  1.43s/it]
 87%|████████▋ | 53641/61904 [4:42:52<3:11:33,  1.39s/it]
 87%|████████▋ | 53642/61904 [4:42:54<3:17:10,  1.43s/it]
 87%|████████▋ | 53643/61904 [4:42:55<3:21:31,  1.46s/it]
 87%|████████▋ | 53644/61904 [4:42:57<3:22:04,  1.47s/it]
 87%|████████▋ | 53645/61904 [4:42:58<3:16:01,  1.42s/it]
 87%|████████▋ | 53646/61904 [4:42:59<3:13:38,  1.41s/it]
 87%|████████▋ | 53647/61904 [4:43:01<3:10:47,  1.39s/it]
 87%|████████▋ | 53648/61904 [4:43:02<3:09:28,  1.38s/it]
 87%|████████▋ | 53649/61904 [4:43:04<3:11:02,  1.39s/it]
 87%|████████▋ | 53650/61904 [4:43:05<3:06:01,  1.35s/it]
 87%|████████▋ | 53651/61904 [4:43:06<3:05:14,  1.35s/it]
 87%|████████▋ | 53652/61904 [4:43:08<3:03:57,  1.34s/it]
 87%|████████▋ | 53653/61904 [4:43:09<3:04:24,  1.34s/it]
 87%|████████▋ | 53654/61904 [4:43:10<3:11:29,  1.39s/it]
 87%|████████▋ | 53655/61904 [4:43:12<3:13:45,  1.41s/it]
 87%|████████▋ | 53656/61904 [4:43:13<3:13:46,  1.41s/it]
 87%|████████▋ | 53657/61904 [4:43:15<3:17:36,  1.44s/it]
 87%|████████▋ | 53658/61904 [4:43:16<3:14:14,  1.41s/it]
 87%|████████▋ | 53659/61904 [4:43:17<3:08:28,  1.37s/it]
 87%|████████▋ | 53660/61904 [4:43:19<3:11:21,  1.39s/it]
                                                         
{'loss': 2.4441, 'learning_rate': 1.1336056009334889e-07, 'epoch': 13.87}

 87%|████████▋ | 53660/61904 [4:43:19<3:11:21,  1.39s/it]
 87%|████████▋ | 53661/61904 [4:43:20<3:14:43,  1.42s/it]
 87%|████████▋ | 53662/61904 [4:43:22<3:13:14,  1.41s/it]
 87%|████████▋ | 53663/61904 [4:43:23<3:08:04,  1.37s/it]
 87%|████████▋ | 53664/61904 [4:43:24<3:05:32,  1.35s/it]
 87%|████████▋ | 53665/61904 [4:43:25<2:59:45,  1.31s/it]
 87%|████████▋ | 53666/61904 [4:43:27<2:57:39,  1.29s/it]
 87%|████████▋ | 53667/61904 [4:43:28<3:01:50,  1.32s/it]
 87%|████████▋ | 53668/61904 [4:43:30<3:09:27,  1.38s/it]
 87%|████████▋ | 53669/61904 [4:43:31<3:09:47,  1.38s/it]
 87%|████████▋ | 53670/61904 [4:43:32<3:10:24,  1.39s/it]
 87%|████████▋ | 53671/61904 [4:43:34<3:13:54,  1.41s/it]
 87%|████████▋ | 53672/61904 [4:43:35<3:09:13,  1.38s/it]
 87%|████████▋ | 53673/61904 [4:43:37<3:10:23,  1.39s/it]
 87%|████████▋ | 53674/61904 [4:43:38<3:12:26,  1.40s/it]
 87%|████████▋ | 53675/61904 [4:43:40<3:15:36,  1.43s/it]
 87%|████████▋ | 53676/61904 [4:43:41<3:11:27,  1.40s/it]
 87%|████████▋ | 53677/61904 [4:43:42<3:09:05,  1.38s/it]
 87%|████████▋ | 53678/61904 [4:43:44<3:08:45,  1.38s/it]
 87%|████████▋ | 53679/61904 [4:43:45<3:09:39,  1.38s/it]
 87%|████████▋ | 53680/61904 [4:43:46<3:11:43,  1.40s/it]
                                                         
{'loss': 2.4742, 'learning_rate': 1.1332814728380655e-07, 'epoch': 13.87}

 87%|████████▋ | 53680/61904 [4:43:46<3:11:43,  1.40s/it]
 87%|████████▋ | 53681/61904 [4:43:48<3:06:30,  1.36s/it]
 87%|████████▋ | 53682/61904 [4:43:49<3:07:31,  1.37s/it]
 87%|████████▋ | 53683/61904 [4:43:50<3:08:16,  1.37s/it]
 87%|████████▋ | 53684/61904 [4:43:52<3:07:30,  1.37s/it]
 87%|████████▋ | 53685/61904 [4:43:53<3:05:15,  1.35s/it]
 87%|████████▋ | 53686/61904 [4:43:54<3:06:13,  1.36s/it]
 87%|████████▋ | 53687/61904 [4:43:56<3:08:03,  1.37s/it]
 87%|████████▋ | 53688/61904 [4:43:57<3:06:09,  1.36s/it]
 87%|████████▋ | 53689/61904 [4:43:59<3:05:05,  1.35s/it]
 87%|████████▋ | 53690/61904 [4:44:00<3:03:35,  1.34s/it]
 87%|████████▋ | 53691/61904 [4:44:01<3:04:38,  1.35s/it]
 87%|████████▋ | 53692/61904 [4:44:03<3:03:11,  1.34s/it]
 87%|████████▋ | 53693/61904 [4:44:04<3:07:57,  1.37s/it]
 87%|████████▋ | 53694/61904 [4:44:05<3:07:37,  1.37s/it]
 87%|████████▋ | 53695/61904 [4:44:07<3:05:03,  1.35s/it]
 87%|████████▋ | 53696/61904 [4:44:08<3:01:44,  1.33s/it]
 87%|████████▋ | 53697/61904 [4:44:09<3:02:31,  1.33s/it]
 87%|████████▋ | 53698/61904 [4:44:11<3:07:09,  1.37s/it]
 87%|████████▋ | 53699/61904 [4:44:12<3:07:11,  1.37s/it]
 87%|████████▋ | 53700/61904 [4:44:14<3:08:03,  1.38s/it]
                                                         
{'loss': 2.4507, 'learning_rate': 1.1329573447426424e-07, 'epoch': 13.88}

 87%|████████▋ | 53700/61904 [4:44:14<3:08:03,  1.38s/it]
 87%|████████▋ | 53701/61904 [4:44:15<3:09:12,  1.38s/it]
 87%|████████▋ | 53702/61904 [4:44:16<3:10:18,  1.39s/it]
 87%|████████▋ | 53703/61904 [4:44:18<3:07:00,  1.37s/it]
 87%|████████▋ | 53704/61904 [4:44:19<3:06:15,  1.36s/it]
 87%|████████▋ | 53705/61904 [4:44:20<3:07:18,  1.37s/it]
 87%|████████▋ | 53706/61904 [4:44:22<3:07:47,  1.37s/it]
 87%|████████▋ | 53707/61904 [4:44:23<3:10:34,  1.40s/it]
 87%|████████▋ | 53708/61904 [4:44:25<3:10:45,  1.40s/it]
 87%|████████▋ | 53709/61904 [4:44:26<3:15:05,  1.43s/it]
 87%|████████▋ | 53710/61904 [4:44:28<3:17:00,  1.44s/it]
 87%|████████▋ | 53711/61904 [4:44:29<3:16:57,  1.44s/it]
 87%|████████▋ | 53712/61904 [4:44:30<3:11:42,  1.40s/it]
 87%|████████▋ | 53713/61904 [4:44:32<3:10:08,  1.39s/it]
 87%|████████▋ | 53714/61904 [4:44:33<3:10:17,  1.39s/it]
 87%|████████▋ | 53715/61904 [4:44:34<3:07:44,  1.38s/it]
 87%|████████▋ | 53716/61904 [4:44:36<3:04:47,  1.35s/it]
 87%|████████▋ | 53717/61904 [4:44:37<3:05:31,  1.36s/it]
 87%|████████▋ | 53718/61904 [4:44:38<3:01:13,  1.33s/it]
 87%|████████▋ | 53719/61904 [4:44:40<3:01:31,  1.33s/it]
 87%|████████▋ | 53720/61904 [4:44:41<2:59:28,  1.32s/it]
                                                         
{'loss': 2.4422, 'learning_rate': 1.132633216647219e-07, 'epoch': 13.88}

 87%|████████▋ | 53720/61904 [4:44:41<2:59:28,  1.32s/it]
 87%|████████▋ | 53721/61904 [4:44:42<3:03:05,  1.34s/it]
 87%|████████▋ | 53722/61904 [4:44:44<3:07:47,  1.38s/it]
 87%|████████▋ | 53723/61904 [4:44:45<3:09:32,  1.39s/it]
 87%|████████▋ | 53724/61904 [4:44:47<3:10:16,  1.40s/it]
 87%|████████▋ | 53725/61904 [4:44:48<3:09:56,  1.39s/it]
 87%|████████▋ | 53726/61904 [4:44:49<3:07:43,  1.38s/it]
 87%|████████▋ | 53727/61904 [4:44:51<3:08:47,  1.39s/it]
 87%|████████▋ | 53728/61904 [4:44:52<3:10:59,  1.40s/it]
 87%|████████▋ | 53729/61904 [4:44:54<3:08:05,  1.38s/it]
 87%|████████▋ | 53730/61904 [4:44:55<3:09:28,  1.39s/it]
 87%|████████▋ | 53731/61904 [4:44:56<3:01:49,  1.33s/it]
 87%|████████▋ | 53732/61904 [4:44:57<2:57:58,  1.31s/it]
 87%|████████▋ | 53733/61904 [4:44:59<3:07:56,  1.38s/it]
 87%|████████▋ | 53734/61904 [4:45:00<3:07:35,  1.38s/it]
 87%|████████▋ | 53735/61904 [4:45:02<3:03:51,  1.35s/it]
 87%|████████▋ | 53736/61904 [4:45:03<3:06:59,  1.37s/it]
 87%|████████▋ | 53737/61904 [4:45:05<3:09:17,  1.39s/it]
 87%|████████▋ | 53738/61904 [4:45:06<3:06:45,  1.37s/it]
 87%|████████▋ | 53739/61904 [4:45:07<3:05:21,  1.36s/it]
 87%|████████▋ | 53740/61904 [4:45:09<3:05:41,  1.36s/it]
                                                         
{'loss': 2.5032, 'learning_rate': 1.1323090885517956e-07, 'epoch': 13.89}

 87%|████████▋ | 53740/61904 [4:45:09<3:05:41,  1.36s/it]
 87%|████████▋ | 53741/61904 [4:45:10<3:06:45,  1.37s/it]
 87%|████████▋ | 53742/61904 [4:45:11<3:04:52,  1.36s/it]
 87%|████████▋ | 53743/61904 [4:45:13<3:01:59,  1.34s/it]
 87%|████████▋ | 53744/61904 [4:45:14<3:05:01,  1.36s/it]
 87%|████████▋ | 53745/61904 [4:45:15<3:03:20,  1.35s/it]
 87%|████████▋ | 53746/61904 [4:45:17<3:06:09,  1.37s/it]
 87%|████████▋ | 53747/61904 [4:45:18<3:05:37,  1.37s/it]
 87%|████████▋ | 53748/61904 [4:45:19<3:00:23,  1.33s/it]
 87%|████████▋ | 53749/61904 [4:45:21<3:01:48,  1.34s/it]
 87%|████████▋ | 53750/61904 [4:45:22<3:03:05,  1.35s/it]
 87%|████████▋ | 53751/61904 [4:45:24<3:10:19,  1.40s/it]
 87%|████████▋ | 53752/61904 [4:45:25<3:13:05,  1.42s/it]
 87%|████████▋ | 53753/61904 [4:45:27<3:16:51,  1.45s/it]
 87%|████████▋ | 53754/61904 [4:45:28<3:19:06,  1.47s/it]
 87%|████████▋ | 53755/61904 [4:45:29<3:13:27,  1.42s/it]
 87%|████████▋ | 53756/61904 [4:45:31<3:17:04,  1.45s/it]
 87%|████████▋ | 53757/61904 [4:45:32<3:11:18,  1.41s/it]
 87%|████████▋ | 53758/61904 [4:45:34<3:13:41,  1.43s/it]
 87%|████████▋ | 53759/61904 [4:45:35<3:13:45,  1.43s/it]
 87%|████████▋ | 53760/61904 [4:45:36<3:07:28,  1.38s/it]
                                                         
{'loss': 2.4601, 'learning_rate': 1.1319849604563723e-07, 'epoch': 13.89}

 87%|████████▋ | 53760/61904 [4:45:36<3:07:28,  1.38s/it]
 87%|████████▋ | 53761/61904 [4:45:38<3:01:36,  1.34s/it]
 87%|████████▋ | 53762/61904 [4:45:39<3:06:35,  1.38s/it]
 87%|████████▋ | 53763/61904 [4:45:40<3:05:31,  1.37s/it]
 87%|████████▋ | 53764/61904 [4:45:42<3:12:18,  1.42s/it]
 87%|████████▋ | 53765/61904 [4:45:43<3:06:35,  1.38s/it]
 87%|████████▋ | 53766/61904 [4:45:45<3:10:35,  1.41s/it]
 87%|████████▋ | 53767/61904 [4:45:46<3:12:20,  1.42s/it]
 87%|████████▋ | 53768/61904 [4:45:48<3:10:18,  1.40s/it]
 87%|████████▋ | 53769/61904 [4:45:49<3:10:29,  1.40s/it]
 87%|████████▋ | 53770/61904 [4:45:50<3:12:02,  1.42s/it]
 87%|████████▋ | 53771/61904 [4:45:52<3:13:33,  1.43s/it]
 87%|████████▋ | 53772/61904 [4:45:53<3:08:36,  1.39s/it]
 87%|████████▋ | 53773/61904 [4:45:55<3:14:50,  1.44s/it]
 87%|████████▋ | 53774/61904 [4:45:56<3:18:47,  1.47s/it]
 87%|████████▋ | 53775/61904 [4:45:57<3:09:57,  1.40s/it]
 87%|████████▋ | 53776/61904 [4:45:59<3:09:46,  1.40s/it]
 87%|████████▋ | 53777/61904 [4:46:00<3:06:27,  1.38s/it]
 87%|████████▋ | 53778/61904 [4:46:02<3:04:14,  1.36s/it]
 87%|████████▋ | 53779/61904 [4:46:03<3:09:00,  1.40s/it]
 87%|████████▋ | 53780/61904 [4:46:04<3:08:49,  1.39s/it]
                                                         
{'loss': 2.3983, 'learning_rate': 1.1316608323609492e-07, 'epoch': 13.9}

 87%|████████▋ | 53780/61904 [4:46:04<3:08:49,  1.39s/it]
 87%|████████▋ | 53781/61904 [4:46:06<3:06:12,  1.38s/it]
 87%|████████▋ | 53782/61904 [4:46:07<3:02:21,  1.35s/it]
 87%|████████▋ | 53783/61904 [4:46:08<3:06:41,  1.38s/it]
 87%|████████▋ | 53784/61904 [4:46:10<3:06:02,  1.37s/it]
 87%|████████▋ | 53785/61904 [4:46:11<3:09:59,  1.40s/it]
 87%|████████▋ | 53786/61904 [4:46:13<3:09:35,  1.40s/it]
 87%|████████▋ | 53787/61904 [4:46:14<3:08:20,  1.39s/it]
 87%|████████▋ | 53788/61904 [4:46:15<3:10:28,  1.41s/it]
 87%|████████▋ | 53789/61904 [4:46:17<3:05:32,  1.37s/it]
 87%|████████▋ | 53790/61904 [4:46:18<3:08:20,  1.39s/it]
 87%|████████▋ | 53791/61904 [4:46:20<3:04:15,  1.36s/it]
 87%|████████▋ | 53792/61904 [4:46:21<3:02:21,  1.35s/it]
 87%|████████▋ | 53793/61904 [4:46:22<3:06:21,  1.38s/it]
 87%|████████▋ | 53794/61904 [4:46:24<3:10:54,  1.41s/it]
 87%|████████▋ | 53795/61904 [4:46:25<3:07:04,  1.38s/it]
 87%|████████▋ | 53796/61904 [4:46:26<3:05:03,  1.37s/it]
 87%|████████▋ | 53797/61904 [4:46:28<3:06:45,  1.38s/it]
 87%|████████▋ | 53798/61904 [4:46:29<3:09:44,  1.40s/it]
 87%|████████▋ | 53799/61904 [4:46:31<3:10:51,  1.41s/it]
 87%|████████▋ | 53800/61904 [4:46:32<3:06:12,  1.38s/it]
                                                         
{'loss': 2.3913, 'learning_rate': 1.1313367042655258e-07, 'epoch': 13.91}

 87%|████████▋ | 53800/61904 [4:46:32<3:06:12,  1.38s/it]
 87%|████████▋ | 53801/61904 [4:46:33<3:06:20,  1.38s/it]
 87%|████████▋ | 53802/61904 [4:46:35<3:05:35,  1.37s/it]
 87%|████████▋ | 53803/61904 [4:46:36<3:01:36,  1.35s/it]
 87%|████████▋ | 53804/61904 [4:46:37<3:01:13,  1.34s/it]
 87%|████████▋ | 53805/61904 [4:46:39<3:00:45,  1.34s/it]
 87%|████████▋ | 53806/61904 [4:46:40<3:03:18,  1.36s/it]
 87%|████████▋ | 53807/61904 [4:46:41<3:02:31,  1.35s/it]
 87%|████████▋ | 53808/61904 [4:46:43<3:05:56,  1.38s/it]
 87%|████████▋ | 53809/61904 [4:46:44<3:03:47,  1.36s/it]
 87%|████████▋ | 53810/61904 [4:46:46<3:04:03,  1.36s/it]
 87%|████████▋ | 53811/61904 [4:46:47<3:06:21,  1.38s/it]
 87%|████████▋ | 53812/61904 [4:46:48<3:01:29,  1.35s/it]
 87%|████████▋ | 53813/61904 [4:46:50<2:58:19,  1.32s/it]
 87%|████████▋ | 53814/61904 [4:46:51<3:02:30,  1.35s/it]
 87%|████████▋ | 53815/61904 [4:46:52<3:02:52,  1.36s/it]
 87%|████████▋ | 53816/61904 [4:46:54<3:03:29,  1.36s/it]
 87%|████████▋ | 53817/61904 [4:46:55<3:01:08,  1.34s/it]
 87%|████████▋ | 53818/61904 [4:46:56<3:02:29,  1.35s/it]
 87%|████████▋ | 53819/61904 [4:46:58<3:07:24,  1.39s/it]
 87%|████████▋ | 53820/61904 [4:46:59<3:06:51,  1.39s/it]
                                                         
{'loss': 2.4417, 'learning_rate': 1.1310125761701024e-07, 'epoch': 13.91}

 87%|████████▋ | 53820/61904 [4:46:59<3:06:51,  1.39s/it]
 87%|████████▋ | 53821/61904 [4:47:01<3:05:02,  1.37s/it]
 87%|████████▋ | 53822/61904 [4:47:02<3:03:53,  1.37s/it]
 87%|████████▋ | 53823/61904 [4:47:03<2:58:08,  1.32s/it]
 87%|████████▋ | 53824/61904 [4:47:05<2:59:31,  1.33s/it]
 87%|████████▋ | 53825/61904 [4:47:06<2:57:24,  1.32s/it]
 87%|████████▋ | 53826/61904 [4:47:07<3:05:38,  1.38s/it]
 87%|████████▋ | 53827/61904 [4:47:09<3:10:44,  1.42s/it]
 87%|████████▋ | 53828/61904 [4:47:10<3:19:24,  1.48s/it]
 87%|████████▋ | 53829/61904 [4:47:12<3:10:43,  1.42s/it]
 87%|████████▋ | 53830/61904 [4:47:13<3:10:12,  1.41s/it]
 87%|████████▋ | 53831/61904 [4:47:14<3:05:22,  1.38s/it]
 87%|████████▋ | 53832/61904 [4:47:16<3:08:21,  1.40s/it]
 87%|████████▋ | 53833/61904 [4:47:17<3:02:27,  1.36s/it]
 87%|████████▋ | 53834/61904 [4:47:18<3:02:55,  1.36s/it]
 87%|████████▋ | 53835/61904 [4:47:20<3:08:36,  1.40s/it]
 87%|████████▋ | 53836/61904 [4:47:22<3:22:25,  1.51s/it]
 87%|████████▋ | 53837/61904 [4:47:23<3:16:57,  1.46s/it]
 87%|████████▋ | 53838/61904 [4:47:25<3:19:52,  1.49s/it]
 87%|████████▋ | 53839/61904 [4:47:26<3:11:39,  1.43s/it]
 87%|████████▋ | 53840/61904 [4:47:27<3:15:57,  1.46s/it]
                                                         
{'loss': 2.422, 'learning_rate': 1.1306884480746793e-07, 'epoch': 13.92}

 87%|████████▋ | 53840/61904 [4:47:27<3:15:57,  1.46s/it]
 87%|████████▋ | 53841/61904 [4:47:29<3:12:53,  1.44s/it]
 87%|████████▋ | 53842/61904 [4:47:30<3:10:37,  1.42s/it]
 87%|████████▋ | 53843/61904 [4:47:32<3:07:17,  1.39s/it]
 87%|████████▋ | 53844/61904 [4:47:33<3:07:49,  1.40s/it]
 87%|████████▋ | 53845/61904 [4:47:34<3:10:38,  1.42s/it]
 87%|████████▋ | 53846/61904 [4:47:36<3:04:17,  1.37s/it]
 87%|████████▋ | 53847/61904 [4:47:37<3:07:30,  1.40s/it]
 87%|████████▋ | 53848/61904 [4:47:39<3:05:56,  1.38s/it]
 87%|████████▋ | 53849/61904 [4:47:40<3:01:05,  1.35s/it]
 87%|████████▋ | 53850/61904 [4:47:41<3:02:55,  1.36s/it]
 87%|████████▋ | 53851/61904 [4:47:43<3:10:09,  1.42s/it]
 87%|████████▋ | 53852/61904 [4:47:44<3:11:47,  1.43s/it]
 87%|████████▋ | 53853/61904 [4:47:46<3:20:51,  1.50s/it]
 87%|████████▋ | 53854/61904 [4:47:47<3:11:34,  1.43s/it]
 87%|████████▋ | 53855/61904 [4:47:48<3:06:02,  1.39s/it]
 87%|████████▋ | 53856/61904 [4:47:50<3:03:56,  1.37s/it]
 87%|████████▋ | 53857/61904 [4:47:51<3:02:32,  1.36s/it]
 87%|████████▋ | 53858/61904 [4:47:52<3:03:44,  1.37s/it]
 87%|████████▋ | 53859/61904 [4:47:54<3:05:07,  1.38s/it]
 87%|████████▋ | 53860/61904 [4:47:55<3:01:58,  1.36s/it]
                                                         
{'loss': 2.4629, 'learning_rate': 1.1303643199792559e-07, 'epoch': 13.92}

 87%|████████▋ | 53860/61904 [4:47:55<3:01:58,  1.36s/it]
 87%|████████▋ | 53861/61904 [4:47:57<3:02:35,  1.36s/it]
 87%|████████▋ | 53862/61904 [4:47:58<3:03:09,  1.37s/it]
 87%|████████▋ | 53863/61904 [4:47:59<3:05:45,  1.39s/it]
 87%|████████▋ | 53864/61904 [4:48:01<3:09:47,  1.42s/it]
 87%|████████▋ | 53865/61904 [4:48:02<3:10:56,  1.43s/it]
 87%|████████▋ | 53866/61904 [4:48:04<3:11:24,  1.43s/it]
 87%|████████▋ | 53867/61904 [4:48:05<3:09:14,  1.41s/it]
 87%|████████▋ | 53868/61904 [4:48:06<3:03:35,  1.37s/it]
 87%|████████▋ | 53869/61904 [4:48:08<3:05:51,  1.39s/it]
 87%|████████▋ | 53870/61904 [4:48:09<3:05:37,  1.39s/it]
 87%|████████▋ | 53871/61904 [4:48:11<3:10:14,  1.42s/it]
 87%|████████▋ | 53872/61904 [4:48:12<3:15:02,  1.46s/it]
 87%|████████▋ | 53873/61904 [4:48:14<3:32:11,  1.59s/it]
 87%|████████▋ | 53874/61904 [4:48:15<3:20:42,  1.50s/it]
 87%|████████▋ | 53875/61904 [4:48:17<3:13:39,  1.45s/it]
 87%|████████▋ | 53876/61904 [4:48:18<3:07:25,  1.40s/it]
 87%|████████▋ | 53877/61904 [4:48:19<3:05:49,  1.39s/it]
 87%|████████▋ | 53878/61904 [4:48:21<3:00:39,  1.35s/it]
 87%|████████▋ | 53879/61904 [4:48:22<3:00:23,  1.35s/it]
 87%|████████▋ | 53880/61904 [4:48:23<3:03:42,  1.37s/it]
                                                         
{'loss': 2.4489, 'learning_rate': 1.1300401918838325e-07, 'epoch': 13.93}

 87%|████████▋ | 53880/61904 [4:48:23<3:03:42,  1.37s/it]
 87%|████████▋ | 53881/61904 [4:48:25<3:01:15,  1.36s/it]
 87%|████████▋ | 53882/61904 [4:48:26<2:59:53,  1.35s/it]
 87%|████████▋ | 53883/61904 [4:48:27<3:00:01,  1.35s/it]
 87%|████████▋ | 53884/61904 [4:48:29<3:00:44,  1.35s/it]
 87%|████████▋ | 53885/61904 [4:48:30<3:01:26,  1.36s/it]
 87%|████████▋ | 53886/61904 [4:48:32<3:03:00,  1.37s/it]
 87%|████████▋ | 53887/61904 [4:48:33<3:05:21,  1.39s/it]
 87%|████████▋ | 53888/61904 [4:48:34<3:04:44,  1.38s/it]
 87%|████████▋ | 53889/61904 [4:48:36<3:01:26,  1.36s/it]
 87%|████████▋ | 53890/61904 [4:48:37<3:01:48,  1.36s/it]
 87%|████████▋ | 53891/61904 [4:48:38<2:59:46,  1.35s/it]
 87%|████████▋ | 53892/61904 [4:48:40<2:58:33,  1.34s/it]
 87%|████████▋ | 53893/61904 [4:48:41<3:01:47,  1.36s/it]
 87%|████████▋ | 53894/61904 [4:48:42<2:59:26,  1.34s/it]
 87%|████████▋ | 53895/61904 [4:48:44<3:01:46,  1.36s/it]
 87%|████████▋ | 53896/61904 [4:48:45<3:04:44,  1.38s/it]
 87%|████████▋ | 53897/61904 [4:48:46<3:00:14,  1.35s/it]
 87%|████████▋ | 53898/61904 [4:48:48<3:01:01,  1.36s/it]
 87%|████████▋ | 53899/61904 [4:48:49<3:03:43,  1.38s/it]
 87%|████████▋ | 53900/61904 [4:48:51<3:02:29,  1.37s/it]
                                                         
{'loss': 2.4243, 'learning_rate': 1.1297160637884091e-07, 'epoch': 13.93}

 87%|████████▋ | 53900/61904 [4:48:51<3:02:29,  1.37s/it]
 87%|████████▋ | 53901/61904 [4:48:52<3:01:53,  1.36s/it]
 87%|████████▋ | 53902/61904 [4:48:53<3:01:40,  1.36s/it]
 87%|████████▋ | 53903/61904 [4:48:55<3:00:32,  1.35s/it]
 87%|████████▋ | 53904/61904 [4:48:56<3:11:28,  1.44s/it]
 87%|████████▋ | 53905/61904 [4:48:58<3:11:15,  1.43s/it]
 87%|████████▋ | 53906/61904 [4:48:59<3:08:36,  1.41s/it]
 87%|████████▋ | 53907/61904 [4:49:00<3:07:51,  1.41s/it]
 87%|████████▋ | 53908/61904 [4:49:02<3:13:50,  1.45s/it]
 87%|████████▋ | 53909/61904 [4:49:03<3:10:40,  1.43s/it]
 87%|████████▋ | 53910/61904 [4:49:05<3:05:52,  1.40s/it]
 87%|████████▋ | 53911/61904 [4:49:06<3:10:22,  1.43s/it]
 87%|████████▋ | 53912/61904 [4:49:08<3:06:29,  1.40s/it]
 87%|████████▋ | 53913/61904 [4:49:09<3:05:40,  1.39s/it]
 87%|████████▋ | 53914/61904 [4:49:10<3:04:49,  1.39s/it]
 87%|████████▋ | 53915/61904 [4:49:12<3:01:55,  1.37s/it]
 87%|████████▋ | 53916/61904 [4:49:13<2:58:40,  1.34s/it]
 87%|████████▋ | 53917/61904 [4:49:14<3:01:47,  1.37s/it]
 87%|████████▋ | 53918/61904 [4:49:16<2:59:09,  1.35s/it]
 87%|████████▋ | 53919/61904 [4:49:17<3:01:01,  1.36s/it]
 87%|████████▋ | 53920/61904 [4:49:18<2:58:17,  1.34s/it]
                                                         
{'loss': 2.4241, 'learning_rate': 1.129391935692986e-07, 'epoch': 13.94}

 87%|████████▋ | 53920/61904 [4:49:18<2:58:17,  1.34s/it]
 87%|████████▋ | 53921/61904 [4:49:20<2:55:46,  1.32s/it]
 87%|████████▋ | 53922/61904 [4:49:21<2:59:36,  1.35s/it]
 87%|████████▋ | 53923/61904 [4:49:22<3:00:02,  1.35s/it]
 87%|████████▋ | 53924/61904 [4:49:24<2:59:16,  1.35s/it]
 87%|████████▋ | 53925/61904 [4:49:25<2:59:13,  1.35s/it]
 87%|████████▋ | 53926/61904 [4:49:27<3:03:51,  1.38s/it]
 87%|████████▋ | 53927/61904 [4:49:28<3:07:22,  1.41s/it]
 87%|████████▋ | 53928/61904 [4:49:29<3:03:22,  1.38s/it]
 87%|████████▋ | 53929/61904 [4:49:31<3:03:43,  1.38s/it]
 87%|████████▋ | 53930/61904 [4:49:32<3:03:18,  1.38s/it]
 87%|████████▋ | 53931/61904 [4:49:33<3:03:30,  1.38s/it]
 87%|████████▋ | 53932/61904 [4:49:35<3:05:41,  1.40s/it]
 87%|████████▋ | 53933/61904 [4:49:36<3:00:36,  1.36s/it]
 87%|████████▋ | 53934/61904 [4:49:37<2:57:15,  1.33s/it]
 87%|████████▋ | 53935/61904 [4:49:39<2:58:31,  1.34s/it]
 87%|████████▋ | 53936/61904 [4:49:40<2:54:48,  1.32s/it]
 87%|████████▋ | 53937/61904 [4:49:41<2:54:32,  1.31s/it]
 87%|████████▋ | 53938/61904 [4:49:43<2:55:36,  1.32s/it]
 87%|████████▋ | 53939/61904 [4:49:44<2:57:13,  1.34s/it]
 87%|████████▋ | 53940/61904 [4:49:46<3:07:53,  1.42s/it]
                                                         
{'loss': 2.4386, 'learning_rate': 1.1290678075975626e-07, 'epoch': 13.94}

 87%|████████▋ | 53940/61904 [4:49:46<3:07:53,  1.42s/it]
 87%|████████▋ | 53941/61904 [4:49:47<3:07:45,  1.41s/it]
 87%|████████▋ | 53942/61904 [4:49:48<3:03:56,  1.39s/it]
 87%|████████▋ | 53943/61904 [4:49:50<3:04:28,  1.39s/it]
 87%|████████▋ | 53944/61904 [4:49:51<3:10:48,  1.44s/it]
 87%|████████▋ | 53945/61904 [4:49:53<3:06:45,  1.41s/it]
 87%|████████▋ | 53946/61904 [4:49:54<3:04:07,  1.39s/it]
 87%|████████▋ | 53947/61904 [4:49:56<3:11:52,  1.45s/it]
 87%|████████▋ | 53948/61904 [4:49:57<3:06:33,  1.41s/it]
 87%|████████▋ | 53949/61904 [4:49:58<3:08:04,  1.42s/it]
 87%|████████▋ | 53950/61904 [4:50:00<3:06:34,  1.41s/it]
 87%|████████▋ | 53951/61904 [4:50:01<3:08:27,  1.42s/it]
 87%|████████▋ | 53952/61904 [4:50:03<3:11:43,  1.45s/it]
 87%|████████▋ | 53953/61904 [4:50:04<3:06:37,  1.41s/it]
 87%|████████▋ | 53954/61904 [4:50:05<3:07:29,  1.41s/it]
 87%|████████▋ | 53955/61904 [4:50:07<3:07:19,  1.41s/it]
 87%|████████▋ | 53956/61904 [4:50:08<3:00:07,  1.36s/it]
 87%|████████▋ | 53957/61904 [4:50:10<3:10:08,  1.44s/it]
 87%|████████▋ | 53958/61904 [4:50:11<3:04:28,  1.39s/it]
 87%|████████▋ | 53959/61904 [4:50:12<3:01:00,  1.37s/it]
 87%|████████▋ | 53960/61904 [4:50:14<3:07:14,  1.41s/it]
                                                         
{'loss': 2.4117, 'learning_rate': 1.1287436795021392e-07, 'epoch': 13.95}

 87%|████████▋ | 53960/61904 [4:50:14<3:07:14,  1.41s/it]
 87%|████████▋ | 53961/61904 [4:50:15<3:07:28,  1.42s/it]
 87%|████████▋ | 53962/61904 [4:50:17<3:01:54,  1.37s/it]
 87%|████████▋ | 53963/61904 [4:50:18<3:04:52,  1.40s/it]
 87%|████████▋ | 53964/61904 [4:50:19<3:01:21,  1.37s/it]
 87%|████████▋ | 53965/61904 [4:50:21<3:00:42,  1.37s/it]
 87%|████████▋ | 53966/61904 [4:50:22<2:58:59,  1.35s/it]
 87%|████████▋ | 53967/61904 [4:50:23<2:54:38,  1.32s/it]
 87%|████████▋ | 53968/61904 [4:50:25<2:53:59,  1.32s/it]
 87%|████████▋ | 53969/61904 [4:50:26<2:51:40,  1.30s/it]
 87%|████████▋ | 53970/61904 [4:50:27<2:51:18,  1.30s/it]
 87%|████████▋ | 53971/61904 [4:50:28<2:56:09,  1.33s/it]
 87%|████████▋ | 53972/61904 [4:50:30<2:54:27,  1.32s/it]
 87%|████████▋ | 53973/61904 [4:50:31<2:49:49,  1.28s/it]
 87%|████████▋ | 53974/61904 [4:50:32<2:54:00,  1.32s/it]
 87%|████████▋ | 53975/61904 [4:50:34<3:03:14,  1.39s/it]
 87%|████████▋ | 53976/61904 [4:50:36<3:13:12,  1.46s/it]
 87%|████████▋ | 53977/61904 [4:50:37<3:14:00,  1.47s/it]
 87%|████████▋ | 53978/61904 [4:50:38<3:06:30,  1.41s/it]
 87%|████████▋ | 53979/61904 [4:50:40<3:09:45,  1.44s/it]
 87%|████████▋ | 53980/61904 [4:50:41<3:06:58,  1.42s/it]
                                                         
{'loss': 2.4356, 'learning_rate': 1.1284195514067159e-07, 'epoch': 13.95}

 87%|████████▋ | 53980/61904 [4:50:41<3:06:58,  1.42s/it]
 87%|████████▋ | 53981/61904 [4:50:43<3:02:55,  1.39s/it]
 87%|████████▋ | 53982/61904 [4:50:44<2:59:48,  1.36s/it]
 87%|████████▋ | 53983/61904 [4:50:45<3:04:17,  1.40s/it]
 87%|████████▋ | 53984/61904 [4:50:47<3:02:21,  1.38s/it]
 87%|████████▋ | 53985/61904 [4:50:48<2:59:07,  1.36s/it]
 87%|████████▋ | 53986/61904 [4:50:49<3:02:43,  1.38s/it]
 87%|████████▋ | 53987/61904 [4:50:51<3:04:20,  1.40s/it]
 87%|████████▋ | 53988/61904 [4:50:52<3:02:44,  1.39s/it]
 87%|████████▋ | 53989/61904 [4:50:54<3:04:23,  1.40s/it]
 87%|████████▋ | 53990/61904 [4:50:55<3:04:35,  1.40s/it]
 87%|████████▋ | 53991/61904 [4:50:56<3:03:12,  1.39s/it]
 87%|████████▋ | 53992/61904 [4:50:58<3:01:20,  1.38s/it]
 87%|████████▋ | 53993/61904 [4:50:59<3:06:06,  1.41s/it]
 87%|████████▋ | 53994/61904 [4:51:01<3:04:39,  1.40s/it]
 87%|████████▋ | 53995/61904 [4:51:02<3:01:00,  1.37s/it]
 87%|████████▋ | 53996/61904 [4:51:03<3:05:38,  1.41s/it]
 87%|████████▋ | 53997/61904 [4:51:05<3:05:35,  1.41s/it]
 87%|████████▋ | 53998/61904 [4:51:06<3:07:14,  1.42s/it]
 87%|████████▋ | 53999/61904 [4:51:08<3:01:30,  1.38s/it]
 87%|████████▋ | 54000/61904 [4:51:09<3:11:08,  1.45s/it]
                                                         
{'loss': 2.4823, 'learning_rate': 1.1280954233112928e-07, 'epoch': 13.96}

 87%|████████▋ | 54000/61904 [4:51:09<3:11:08,  1.45s/it]
 87%|████████▋ | 54001/61904 [4:51:11<3:10:31,  1.45s/it]
 87%|████████▋ | 54002/61904 [4:51:12<3:09:46,  1.44s/it]
 87%|████████▋ | 54003/61904 [4:51:13<3:03:30,  1.39s/it]
 87%|████████▋ | 54004/61904 [4:51:15<3:04:54,  1.40s/it]
 87%|████████▋ | 54005/61904 [4:51:16<3:05:47,  1.41s/it]
 87%|████████▋ | 54006/61904 [4:51:17<3:02:30,  1.39s/it]
 87%|████████▋ | 54007/61904 [4:51:19<3:04:40,  1.40s/it]
 87%|████████▋ | 54008/61904 [4:51:20<3:01:36,  1.38s/it]
 87%|████████▋ | 54009/61904 [4:51:22<2:58:08,  1.35s/it]
 87%|████████▋ | 54010/61904 [4:51:23<3:01:04,  1.38s/it]
 87%|████████▋ | 54011/61904 [4:51:24<3:02:46,  1.39s/it]
 87%|████████▋ | 54012/61904 [4:51:26<2:59:56,  1.37s/it]
 87%|████████▋ | 54013/61904 [4:51:27<2:55:34,  1.33s/it]
 87%|████████▋ | 54014/61904 [4:51:28<2:53:46,  1.32s/it]
 87%|████████▋ | 54015/61904 [4:51:30<2:55:00,  1.33s/it]
 87%|████████▋ | 54016/61904 [4:51:31<2:57:03,  1.35s/it]
 87%|████████▋ | 54017/61904 [4:51:32<2:59:57,  1.37s/it]
 87%|████████▋ | 54018/61904 [4:51:34<2:56:31,  1.34s/it]
 87%|████████▋ | 54019/61904 [4:51:35<3:02:25,  1.39s/it]
 87%|████████▋ | 54020/61904 [4:51:37<3:03:48,  1.40s/it]
                                                         
{'loss': 2.4368, 'learning_rate': 1.1277712952158694e-07, 'epoch': 13.96}

 87%|████████▋ | 54020/61904 [4:51:37<3:03:48,  1.40s/it]
 87%|████████▋ | 54021/61904 [4:51:38<3:05:41,  1.41s/it]
 87%|████████▋ | 54022/61904 [4:51:39<3:05:23,  1.41s/it]
 87%|████████▋ | 54023/61904 [4:51:41<3:07:13,  1.43s/it]
 87%|████████▋ | 54024/61904 [4:51:42<3:08:15,  1.43s/it]
 87%|████████▋ | 54025/61904 [4:51:44<3:04:38,  1.41s/it]
 87%|████████▋ | 54026/61904 [4:51:45<3:10:12,  1.45s/it]
 87%|████████▋ | 54027/61904 [4:51:47<3:05:43,  1.41s/it]
 87%|████████▋ | 54028/61904 [4:51:48<3:02:47,  1.39s/it]
 87%|████████▋ | 54029/61904 [4:51:49<3:02:01,  1.39s/it]
 87%|████████▋ | 54030/61904 [4:51:51<3:02:52,  1.39s/it]
 87%|████████▋ | 54031/61904 [4:51:52<3:03:18,  1.40s/it]
 87%|████████▋ | 54032/61904 [4:51:53<3:01:16,  1.38s/it]
 87%|████████▋ | 54033/61904 [4:51:55<2:58:20,  1.36s/it]
 87%|████████▋ | 54034/61904 [4:51:56<3:00:29,  1.38s/it]
 87%|████████▋ | 54035/61904 [4:51:57<2:55:34,  1.34s/it]
 87%|████████▋ | 54036/61904 [4:51:59<2:51:02,  1.30s/it]
 87%|████████▋ | 54037/61904 [4:52:00<2:57:15,  1.35s/it]
 87%|████████▋ | 54038/61904 [4:52:02<2:58:32,  1.36s/it]
 87%|████████▋ | 54039/61904 [4:52:03<2:57:35,  1.35s/it]
 87%|████████▋ | 54040/61904 [4:52:04<2:55:42,  1.34s/it]
                                                         
{'loss': 2.4806, 'learning_rate': 1.127447167120446e-07, 'epoch': 13.97}

 87%|████████▋ | 54040/61904 [4:52:04<2:55:42,  1.34s/it]
 87%|████████▋ | 54041/61904 [4:52:06<3:02:04,  1.39s/it]
 87%|████████▋ | 54042/61904 [4:52:07<2:58:25,  1.36s/it]
 87%|████████▋ | 54043/61904 [4:52:08<3:01:07,  1.38s/it]
 87%|████████▋ | 54044/61904 [4:52:10<2:58:40,  1.36s/it]
 87%|████████▋ | 54045/61904 [4:52:11<2:57:20,  1.35s/it]
 87%|████████▋ | 54046/61904 [4:52:13<3:03:54,  1.40s/it]
 87%|████████▋ | 54047/61904 [4:52:14<3:01:54,  1.39s/it]
 87%|████████▋ | 54048/61904 [4:52:15<3:00:23,  1.38s/it]
 87%|████████▋ | 54049/61904 [4:52:17<3:05:11,  1.41s/it]
 87%|████████▋ | 54050/61904 [4:52:18<3:07:03,  1.43s/it]
 87%|████████▋ | 54051/61904 [4:52:20<3:03:38,  1.40s/it]
 87%|████████▋ | 54052/61904 [4:52:21<3:10:31,  1.46s/it]
 87%|████████▋ | 54053/61904 [4:52:22<3:04:44,  1.41s/it]
 87%|████████▋ | 54054/61904 [4:52:24<3:06:25,  1.42s/it]
 87%|████████▋ | 54055/61904 [4:52:25<3:05:01,  1.41s/it]
 87%|████████▋ | 54056/61904 [4:52:27<3:02:42,  1.40s/it]
 87%|████████▋ | 54057/61904 [4:52:28<3:06:29,  1.43s/it]
 87%|████████▋ | 54058/61904 [4:52:30<3:05:34,  1.42s/it]
 87%|████████▋ | 54059/61904 [4:52:31<2:59:43,  1.37s/it]
 87%|████████▋ | 54060/61904 [4:52:32<3:02:04,  1.39s/it]
                                                         
{'loss': 2.3614, 'learning_rate': 1.1271230390250226e-07, 'epoch': 13.97}

 87%|████████▋ | 54060/61904 [4:52:32<3:02:04,  1.39s/it]
 87%|████████▋ | 54061/61904 [4:52:34<3:05:58,  1.42s/it]
 87%|████████▋ | 54062/61904 [4:52:35<3:03:06,  1.40s/it]
 87%|████████▋ | 54063/61904 [4:52:36<3:02:23,  1.40s/it]
 87%|████████▋ | 54064/61904 [4:52:38<3:01:02,  1.39s/it]
 87%|████████▋ | 54065/61904 [4:52:39<2:57:47,  1.36s/it]
 87%|████████▋ | 54066/61904 [4:52:40<2:56:51,  1.35s/it]
 87%|████████▋ | 54067/61904 [4:52:42<2:54:54,  1.34s/it]
 87%|████████▋ | 54068/61904 [4:52:43<2:56:15,  1.35s/it]
 87%|████████▋ | 54069/61904 [4:52:45<3:12:40,  1.48s/it]
 87%|████████▋ | 54070/61904 [4:52:46<3:13:26,  1.48s/it]
 87%|████████▋ | 54071/61904 [4:52:48<3:12:05,  1.47s/it]
 87%|████████▋ | 54072/61904 [4:52:49<3:04:48,  1.42s/it]
 87%|████████▋ | 54073/61904 [4:52:50<2:57:52,  1.36s/it]
 87%|████████▋ | 54074/61904 [4:52:52<2:57:16,  1.36s/it]
 87%|████████▋ | 54075/61904 [4:52:53<2:56:13,  1.35s/it]
 87%|████████▋ | 54076/61904 [4:52:55<3:02:51,  1.40s/it]
 87%|████████▋ | 54077/61904 [4:52:56<2:56:38,  1.35s/it]
 87%|████████▋ | 54078/61904 [4:52:57<3:00:06,  1.38s/it]
 87%|████████▋ | 54079/61904 [4:52:59<3:07:17,  1.44s/it]
 87%|████████▋ | 54080/61904 [4:53:00<2:58:14,  1.37s/it]
                                                         
{'loss': 2.4549, 'learning_rate': 1.1267989109295995e-07, 'epoch': 13.98}

 87%|████████▋ | 54080/61904 [4:53:00<2:58:14,  1.37s/it]
 87%|████████▋ | 54081/61904 [4:53:01<2:56:56,  1.36s/it]
 87%|████████▋ | 54082/61904 [4:53:03<3:01:29,  1.39s/it]
 87%|████████▋ | 54083/61904 [4:53:04<2:53:51,  1.33s/it]
 87%|████████▋ | 54084/61904 [4:53:05<2:53:55,  1.33s/it]
 87%|████████▋ | 54085/61904 [4:53:07<2:54:54,  1.34s/it]
 87%|████████▋ | 54086/61904 [4:53:08<2:54:58,  1.34s/it]
 87%|████████▋ | 54087/61904 [4:53:09<2:55:50,  1.35s/it]
 87%|████████▋ | 54088/61904 [4:53:11<2:55:26,  1.35s/it]
 87%|████████▋ | 54089/61904 [4:53:12<2:57:13,  1.36s/it]
 87%|████████▋ | 54090/61904 [4:53:13<2:53:18,  1.33s/it]
 87%|████████▋ | 54091/61904 [4:53:15<2:59:45,  1.38s/it]
 87%|████████▋ | 54092/61904 [4:53:16<3:02:59,  1.41s/it]
 87%|████████▋ | 54093/61904 [4:53:18<2:57:46,  1.37s/it]
 87%|████████▋ | 54094/61904 [4:53:19<3:03:46,  1.41s/it]
 87%|████████▋ | 54095/61904 [4:53:21<2:59:05,  1.38s/it]
 87%|████████▋ | 54096/61904 [4:53:22<2:58:43,  1.37s/it]
 87%|████████▋ | 54097/61904 [4:53:23<3:01:05,  1.39s/it]
 87%|████████▋ | 54098/61904 [4:53:25<3:01:59,  1.40s/it]
 87%|████████▋ | 54099/61904 [4:53:26<3:00:35,  1.39s/it]
 87%|████████▋ | 54100/61904 [4:53:27<2:53:42,  1.34s/it]
                                                         
{'loss': 2.4648, 'learning_rate': 1.1264747828341761e-07, 'epoch': 13.98}

 87%|████████▋ | 54100/61904 [4:53:27<2:53:42,  1.34s/it]
 87%|████████▋ | 54101/61904 [4:53:29<2:52:09,  1.32s/it]
 87%|████████▋ | 54102/61904 [4:53:30<2:53:00,  1.33s/it]
 87%|████████▋ | 54103/61904 [4:53:31<2:52:37,  1.33s/it]
 87%|████████▋ | 54104/61904 [4:53:33<2:59:36,  1.38s/it]
 87%|████████▋ | 54105/61904 [4:53:34<3:04:21,  1.42s/it]
 87%|████████▋ | 54106/61904 [4:53:36<3:00:08,  1.39s/it]
 87%|████████▋ | 54107/61904 [4:53:37<3:02:36,  1.41s/it]
 87%|████████▋ | 54108/61904 [4:53:38<2:59:42,  1.38s/it]
 87%|████████▋ | 54109/61904 [4:53:40<3:00:34,  1.39s/it]
 87%|████████▋ | 54110/61904 [4:53:41<2:56:01,  1.36s/it]
 87%|████████▋ | 54111/61904 [4:53:42<2:55:59,  1.35s/it]
 87%|████████▋ | 54112/61904 [4:53:44<2:54:21,  1.34s/it]
 87%|████████▋ | 54113/61904 [4:53:45<2:55:41,  1.35s/it]
 87%|████████▋ | 54114/61904 [4:53:47<3:00:00,  1.39s/it]
 87%|████████▋ | 54115/61904 [4:53:48<3:03:51,  1.42s/it]
 87%|████████▋ | 54116/61904 [4:53:49<2:58:26,  1.37s/it]
 87%|████████▋ | 54117/61904 [4:53:51<2:57:18,  1.37s/it]
 87%|████████▋ | 54118/61904 [4:53:52<2:55:55,  1.36s/it]
 87%|████████▋ | 54119/61904 [4:53:53<2:54:51,  1.35s/it]
 87%|████████▋ | 54120/61904 [4:53:55<2:55:53,  1.36s/it]
                                                         
{'loss': 2.482, 'learning_rate': 1.1261506547387527e-07, 'epoch': 13.99}

 87%|████████▋ | 54120/61904 [4:53:55<2:55:53,  1.36s/it]
 87%|████████▋ | 54121/61904 [4:53:56<2:58:24,  1.38s/it]
 87%|████████▋ | 54122/61904 [4:53:58<2:59:47,  1.39s/it]
 87%|████████▋ | 54123/61904 [4:53:59<2:58:55,  1.38s/it]
 87%|████████▋ | 54124/61904 [4:54:00<2:53:18,  1.34s/it]
 87%|████████▋ | 54125/61904 [4:54:02<2:59:21,  1.38s/it]
 87%|████████▋ | 54126/61904 [4:54:03<2:59:10,  1.38s/it]
 87%|████████▋ | 54127/61904 [4:54:04<2:57:55,  1.37s/it]
 87%|████████▋ | 54128/61904 [4:54:06<3:01:03,  1.40s/it]
 87%|████████▋ | 54129/61904 [4:54:07<3:00:44,  1.39s/it]
 87%|████████▋ | 54130/61904 [4:54:09<2:56:58,  1.37s/it]
 87%|████████▋ | 54131/61904 [4:54:10<2:52:59,  1.34s/it]
 87%|████████▋ | 54132/61904 [4:54:11<2:51:34,  1.32s/it]
 87%|████████▋ | 54133/61904 [4:54:12<2:48:58,  1.30s/it]
 87%|████████▋ | 54134/61904 [4:54:14<2:53:01,  1.34s/it]
 87%|████████▋ | 54135/61904 [4:54:15<2:57:50,  1.37s/it]
 87%|████████▋ | 54136/61904 [4:54:17<2:59:59,  1.39s/it]
 87%|████████▋ | 54137/61904 [4:54:18<2:55:50,  1.36s/it]
 87%|████████▋ | 54138/61904 [4:54:19<2:57:45,  1.37s/it]
 87%|████████▋ | 54139/61904 [4:54:21<2:54:21,  1.35s/it]
 87%|████████▋ | 54140/61904 [4:54:22<2:53:36,  1.34s/it]
                                                         
{'loss': 2.4405, 'learning_rate': 1.1258265266433296e-07, 'epoch': 13.99}

 87%|████████▋ | 54140/61904 [4:54:22<2:53:36,  1.34s/it]
 87%|████████▋ | 54141/61904 [4:54:23<2:53:02,  1.34s/it]
 87%|████████▋ | 54142/61904 [4:54:25<2:53:36,  1.34s/it]
 87%|████████▋ | 54143/61904 [4:54:26<2:51:01,  1.32s/it]
 87%|████████▋ | 54144/61904 [4:54:27<2:49:02,  1.31s/it]
 87%|████████▋ | 54145/61904 [4:54:29<2:53:25,  1.34s/it]
 87%|████████▋ | 54146/61904 [4:54:30<2:53:26,  1.34s/it]
 87%|████████▋ | 54147/61904 [4:54:31<2:57:44,  1.37s/it]
 87%|████████▋ | 54148/61904 [4:54:33<2:55:47,  1.36s/it]
 87%|████████▋ | 54149/61904 [4:54:34<2:58:12,  1.38s/it]
 87%|████████▋ | 54150/61904 [4:54:36<3:00:04,  1.39s/it]
 87%|████████▋ | 54151/61904 [4:54:37<2:56:18,  1.36s/it]
 87%|████████▋ | 54152/61904 [4:54:38<2:54:03,  1.35s/it]
 87%|████████▋ | 54153/61904 [4:54:40<2:55:03,  1.36s/it]
 87%|████████▋ | 54154/61904 [4:54:41<2:55:54,  1.36s/it]
 87%|████████▋ | 54155/61904 [4:54:42<2:57:20,  1.37s/it]
 87%|████████▋ | 54156/61904 [4:54:44<2:56:18,  1.37s/it]
 87%|████████▋ | 54157/61904 [4:54:45<2:53:19,  1.34s/it]
 87%|████████▋ | 54158/61904 [4:54:46<2:52:09,  1.33s/it]
 87%|████████▋ | 54159/61904 [4:54:48<2:52:16,  1.33s/it]
 87%|████████▋ | 54160/61904 [4:54:49<2:59:48,  1.39s/it]
                                                         
{'loss': 2.4125, 'learning_rate': 1.1255023985479062e-07, 'epoch': 14.0}

 87%|████████▋ | 54160/61904 [4:54:49<2:59:48,  1.39s/it]
 87%|████████▋ | 54161/61904 [4:54:51<3:02:34,  1.41s/it]
 87%|████████▋ | 54162/61904 [4:54:52<2:57:35,  1.38s/it]
 87%|████████▋ | 54163/61904 [4:54:53<2:56:21,  1.37s/it]
 87%|████████▋ | 54164/61904 [4:54:55<2:55:32,  1.36s/it]
 87%|████████▋ | 54165/61904 [4:54:56<2:54:50,  1.36s/it]
 88%|████████▊ | 54166/61904 [4:54:57<2:58:49,  1.39s/it]
 88%|████████▊ | 54167/61904 [4:54:59<3:04:07,  1.43s/it]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/861 [00:00<?, ?it/s]

  0%|          | 2/861 [00:01<07:28,  1.92it/s]

  0%|          | 3/861 [00:02<15:25,  1.08s/it]

  0%|          | 4/861 [00:03<14:13,  1.00it/s]

  1%|          | 5/861 [00:04<14:08,  1.01it/s]

  1%|          | 6/861 [00:05<13:17,  1.07it/s]

  1%|          | 7/861 [00:05<10:59,  1.30it/s]

  1%|          | 8/861 [00:07<12:45,  1.11it/s]

  1%|          | 9/861 [00:07<12:12,  1.16it/s]

  1%|          | 10/861 [00:08<11:54,  1.19it/s]

  1%|▏         | 11/861 [00:10<14:39,  1.03s/it]

  1%|▏         | 12/861 [00:11<15:12,  1.07s/it]

  2%|▏         | 13/861 [00:12<14:15,  1.01s/it]

  2%|▏         | 14/861 [00:12<10:47,  1.31it/s]

  2%|▏         | 15/861 [00:12<09:53,  1.43it/s]

  2%|▏         | 16/861 [00:13<08:18,  1.70it/s]

  2%|▏         | 17/861 [00:14<11:07,  1.26it/s]

  2%|▏         | 18/861 [00:14<09:00,  1.56it/s]

  2%|▏         | 19/861 [00:16<14:02,  1.00s/it]

  2%|▏         | 20/861 [00:17<14:16,  1.02s/it]

  2%|▏         | 21/861 [00:19<16:42,  1.19s/it]

  3%|▎         | 22/861 [00:20<17:20,  1.24s/it]

  3%|▎         | 23/861 [00:21<13:27,  1.04it/s]

  3%|▎         | 24/861 [00:22<16:09,  1.16s/it]

  3%|▎         | 25/861 [00:23<14:46,  1.06s/it]

  3%|▎         | 26/861 [00:24<14:44,  1.06s/it]

  3%|▎         | 27/861 [00:25<15:52,  1.14s/it]

  3%|▎         | 28/861 [00:28<20:45,  1.50s/it]

  3%|▎         | 29/861 [00:28<15:41,  1.13s/it]

  3%|▎         | 30/861 [00:29<16:20,  1.18s/it]

  4%|▎         | 31/861 [00:30<13:46,  1.00it/s]

  4%|▎         | 32/861 [00:30<11:26,  1.21it/s]

  4%|▍         | 33/861 [00:31<12:11,  1.13it/s]

  4%|▍         | 34/861 [00:32<12:20,  1.12it/s]

  4%|▍         | 35/861 [00:34<17:08,  1.25s/it]

  4%|▍         | 36/861 [00:35<15:30,  1.13s/it]

  4%|▍         | 37/861 [00:36<14:21,  1.05s/it]

  4%|▍         | 38/861 [00:37<15:23,  1.12s/it]

  5%|▍         | 39/861 [00:38<13:55,  1.02s/it]

  5%|▍         | 40/861 [00:39<12:27,  1.10it/s]

  5%|▍         | 41/861 [00:39<10:34,  1.29it/s]

  5%|▍         | 42/861 [00:40<12:39,  1.08it/s]

  5%|▍         | 43/861 [00:41<12:56,  1.05it/s]

  5%|▌         | 44/861 [00:42<12:33,  1.08it/s]

  5%|▌         | 45/861 [00:43<12:33,  1.08it/s]

  5%|▌         | 46/861 [00:45<17:29,  1.29s/it]

  5%|▌         | 47/861 [00:47<17:04,  1.26s/it]

  6%|▌         | 48/861 [00:48<19:06,  1.41s/it]

  6%|▌         | 49/861 [00:50<18:11,  1.34s/it]

  6%|▌         | 50/861 [00:50<13:26,  1.01it/s]

  6%|▌         | 51/861 [00:51<13:25,  1.01it/s]

  6%|▌         | 52/861 [00:51<12:11,  1.11it/s]

  6%|▌         | 53/861 [00:52<11:01,  1.22it/s]

  6%|▋         | 54/861 [00:52<08:40,  1.55it/s]

  6%|▋         | 55/861 [00:53<08:21,  1.61it/s]

  7%|▋         | 56/861 [00:54<08:59,  1.49it/s]

  7%|▋         | 57/861 [00:54<07:31,  1.78it/s]

  7%|▋         | 58/861 [00:54<06:26,  2.08it/s]

  7%|▋         | 59/861 [00:55<07:47,  1.71it/s]

  7%|▋         | 60/861 [00:56<07:27,  1.79it/s]

  7%|▋         | 61/861 [00:56<06:45,  1.97it/s]

  7%|▋         | 62/861 [00:56<05:47,  2.30it/s]

  7%|▋         | 63/861 [00:57<05:58,  2.23it/s]

  7%|▋         | 64/861 [00:57<06:26,  2.06it/s]

  8%|▊         | 65/861 [00:58<06:19,  2.09it/s]

  8%|▊         | 66/861 [00:58<06:12,  2.13it/s]

  8%|▊         | 67/861 [00:59<07:33,  1.75it/s]

  8%|▊         | 68/861 [01:00<09:04,  1.46it/s]

  8%|▊         | 69/861 [01:01<10:03,  1.31it/s]

  8%|▊         | 70/861 [01:02<12:31,  1.05it/s]

  8%|▊         | 71/861 [01:04<14:14,  1.08s/it]

  8%|▊         | 72/861 [01:04<13:17,  1.01s/it]

  8%|▊         | 73/861 [01:05<10:20,  1.27it/s]

  9%|▊         | 74/861 [01:05<09:49,  1.34it/s]

  9%|▊         | 75/861 [01:07<11:29,  1.14it/s]

  9%|▉         | 76/861 [01:07<09:53,  1.32it/s]

  9%|▉         | 77/861 [01:08<10:43,  1.22it/s]

  9%|▉         | 78/861 [01:09<10:15,  1.27it/s]

  9%|▉         | 79/861 [01:10<11:17,  1.15it/s]

  9%|▉         | 80/861 [01:10<09:59,  1.30it/s]

  9%|▉         | 81/861 [01:11<10:45,  1.21it/s]

 10%|▉         | 82/861 [01:12<09:18,  1.39it/s]

 10%|▉         | 83/861 [01:13<09:34,  1.35it/s]

 10%|▉         | 84/861 [01:14<11:17,  1.15it/s]

 10%|▉         | 85/861 [01:14<10:22,  1.25it/s]

 10%|▉         | 86/861 [01:15<09:07,  1.42it/s]

 10%|█         | 87/861 [01:16<10:58,  1.18it/s]

 10%|█         | 88/861 [01:16<08:21,  1.54it/s]

 10%|█         | 89/861 [01:17<08:13,  1.57it/s]

 10%|█         | 90/861 [01:19<12:59,  1.01s/it]

 11%|█         | 91/861 [01:19<11:40,  1.10it/s]

 11%|█         | 92/861 [01:20<11:33,  1.11it/s]

 11%|█         | 93/861 [01:21<12:24,  1.03it/s]

 11%|█         | 94/861 [01:22<09:38,  1.33it/s]

 11%|█         | 95/861 [01:22<09:13,  1.38it/s]

 11%|█         | 96/861 [01:23<10:03,  1.27it/s]

 11%|█▏        | 97/861 [01:24<11:25,  1.11it/s]

 11%|█▏        | 98/861 [01:25<11:26,  1.11it/s]

 11%|█▏        | 99/861 [01:27<14:06,  1.11s/it]

 12%|█▏        | 100/861 [01:27<12:04,  1.05it/s]

 12%|█▏        | 101/861 [01:28<10:16,  1.23it/s]

 12%|█▏        | 102/861 [01:29<09:21,  1.35it/s]

 12%|█▏        | 103/861 [01:29<07:59,  1.58it/s]

 12%|█▏        | 104/861 [01:30<10:45,  1.17it/s]

 12%|█▏        | 105/861 [01:31<12:13,  1.03it/s]

 12%|█▏        | 106/861 [01:32<11:03,  1.14it/s]

 12%|█▏        | 107/861 [01:33<09:39,  1.30it/s]

 13%|█▎        | 108/861 [01:33<07:50,  1.60it/s]

 13%|█▎        | 109/861 [01:33<06:36,  1.90it/s]

 13%|█▎        | 110/861 [01:34<07:32,  1.66it/s]

 13%|█▎        | 111/861 [01:35<09:42,  1.29it/s]

 13%|█▎        | 112/861 [01:36<07:58,  1.56it/s]

 13%|█▎        | 113/861 [01:36<08:16,  1.51it/s]

 13%|█▎        | 114/861 [01:37<10:10,  1.22it/s]

 13%|█▎        | 115/861 [01:38<08:44,  1.42it/s]

 13%|█▎        | 116/861 [01:38<07:25,  1.67it/s]

 14%|█▎        | 117/861 [01:39<09:19,  1.33it/s]

 14%|█▎        | 118/861 [01:40<09:07,  1.36it/s]

 14%|█▍        | 119/861 [01:41<08:41,  1.42it/s]

 14%|█▍        | 120/861 [01:41<06:50,  1.80it/s]

 14%|█▍        | 121/861 [01:42<08:50,  1.39it/s]

 14%|█▍        | 122/861 [01:43<10:11,  1.21it/s]

 14%|█▍        | 123/861 [01:44<09:50,  1.25it/s]

 14%|█▍        | 124/861 [01:46<13:28,  1.10s/it]

 15%|█▍        | 125/861 [01:46<12:04,  1.02it/s]

 15%|█▍        | 126/861 [01:47<12:34,  1.03s/it]

 15%|█▍        | 127/861 [01:49<13:12,  1.08s/it]

 15%|█▍        | 128/861 [01:49<11:04,  1.10it/s]

 15%|█▍        | 129/861 [01:50<11:27,  1.06it/s]

 15%|█▌        | 130/861 [01:51<11:04,  1.10it/s]

 15%|█▌        | 131/861 [01:52<10:37,  1.14it/s]

 15%|█▌        | 132/861 [01:53<11:25,  1.06it/s]

 15%|█▌        | 133/861 [01:54<11:17,  1.08it/s]

 16%|█▌        | 134/861 [01:54<08:35,  1.41it/s]

 16%|█▌        | 135/861 [01:54<07:25,  1.63it/s]

 16%|█▌        | 136/861 [01:55<07:18,  1.65it/s]

 16%|█▌        | 137/861 [01:55<06:25,  1.88it/s]

 16%|█▌        | 138/861 [01:56<06:03,  1.99it/s]

 16%|█▌        | 139/861 [01:56<05:35,  2.15it/s]

 16%|█▋        | 140/861 [01:56<05:17,  2.27it/s]

 16%|█▋        | 141/861 [01:57<05:03,  2.37it/s]

 16%|█▋        | 142/861 [01:57<04:48,  2.49it/s]

 17%|█▋        | 143/861 [01:58<07:41,  1.55it/s]

 17%|█▋        | 144/861 [02:00<10:21,  1.15it/s]

 17%|█▋        | 145/861 [02:00<08:56,  1.33it/s]

 17%|█▋        | 146/861 [02:01<08:33,  1.39it/s]

 17%|█▋        | 147/861 [02:02<08:52,  1.34it/s]

 17%|█▋        | 148/861 [02:02<07:06,  1.67it/s]

 17%|█▋        | 149/861 [02:02<06:19,  1.87it/s]

 17%|█▋        | 150/861 [02:04<10:09,  1.17it/s]

 18%|█▊        | 151/861 [02:06<13:06,  1.11s/it]

 18%|█▊        | 152/861 [02:06<11:34,  1.02it/s]

 18%|█▊        | 153/861 [02:07<11:17,  1.05it/s]

 18%|█▊        | 154/861 [02:08<09:12,  1.28it/s]

 18%|█▊        | 155/861 [02:09<11:57,  1.02s/it]

 18%|█▊        | 156/861 [02:10<12:33,  1.07s/it]

 18%|█▊        | 157/861 [02:11<11:20,  1.04it/s]

 18%|█▊        | 158/861 [02:13<14:38,  1.25s/it]

 18%|█▊        | 159/861 [02:14<12:22,  1.06s/it]

 19%|█▊        | 160/861 [02:15<11:42,  1.00s/it]

 19%|█▊        | 161/861 [02:16<14:55,  1.28s/it]

 19%|█▉        | 162/861 [02:17<11:21,  1.03it/s]

 19%|█▉        | 163/861 [02:17<08:48,  1.32it/s]

 19%|█▉        | 164/861 [02:18<10:27,  1.11it/s]

 19%|█▉        | 165/861 [02:19<10:26,  1.11it/s]

 19%|█▉        | 166/861 [02:20<10:12,  1.14it/s]

 19%|█▉        | 167/861 [02:20<07:44,  1.49it/s]

 20%|█▉        | 168/861 [02:21<08:17,  1.39it/s]

 20%|█▉        | 169/861 [02:22<09:03,  1.27it/s]

 20%|█▉        | 170/861 [02:23<09:13,  1.25it/s]

 20%|█▉        | 171/861 [02:23<08:48,  1.31it/s]

 20%|█▉        | 172/861 [02:24<07:48,  1.47it/s]

 20%|██        | 173/861 [02:25<07:40,  1.49it/s]

 20%|██        | 174/861 [02:26<09:54,  1.15it/s]

 20%|██        | 175/861 [02:27<09:27,  1.21it/s]

 20%|██        | 176/861 [02:27<07:18,  1.56it/s]

 21%|██        | 177/861 [02:28<07:40,  1.49it/s]

 21%|██        | 178/861 [02:28<08:35,  1.33it/s]

 21%|██        | 179/861 [02:29<08:26,  1.35it/s]

 21%|██        | 180/861 [02:30<08:03,  1.41it/s]

 21%|██        | 181/861 [02:30<06:58,  1.63it/s]

 21%|██        | 182/861 [02:31<06:16,  1.80it/s]

 21%|██▏       | 183/861 [02:32<07:41,  1.47it/s]

 21%|██▏       | 184/861 [02:33<09:34,  1.18it/s]

 21%|██▏       | 185/861 [02:33<08:22,  1.34it/s]

 22%|██▏       | 186/861 [02:34<07:04,  1.59it/s]

 22%|██▏       | 187/861 [02:35<08:02,  1.40it/s]

 22%|██▏       | 188/861 [02:35<07:59,  1.40it/s]

 22%|██▏       | 189/861 [02:37<10:44,  1.04it/s]

 22%|██▏       | 190/861 [02:38<12:07,  1.08s/it]

 22%|██▏       | 191/861 [02:39<09:52,  1.13it/s]

 22%|██▏       | 192/861 [02:39<08:59,  1.24it/s]

 22%|██▏       | 193/861 [02:40<10:11,  1.09it/s]

 23%|██▎       | 194/861 [02:41<08:53,  1.25it/s]

 23%|██▎       | 195/861 [02:41<07:43,  1.44it/s]

 23%|██▎       | 196/861 [02:42<07:02,  1.57it/s]

 23%|██▎       | 197/861 [02:42<06:32,  1.69it/s]

 23%|██▎       | 198/861 [02:43<05:45,  1.92it/s]

 23%|██▎       | 199/861 [02:44<06:33,  1.68it/s]

 23%|██▎       | 200/861 [02:45<08:08,  1.35it/s]

 23%|██▎       | 201/861 [02:46<09:15,  1.19it/s]

 23%|██▎       | 202/861 [02:47<09:59,  1.10it/s]

 24%|██▎       | 203/861 [02:47<07:57,  1.38it/s]

 24%|██▎       | 204/861 [02:47<06:08,  1.79it/s]

 24%|██▍       | 205/861 [02:48<05:37,  1.94it/s]

 24%|██▍       | 206/861 [02:48<06:12,  1.76it/s]

 24%|██▍       | 207/861 [02:49<06:50,  1.59it/s]

 24%|██▍       | 208/861 [02:50<06:56,  1.57it/s]

 24%|██▍       | 209/861 [02:50<06:48,  1.59it/s]

 24%|██▍       | 210/861 [02:51<07:01,  1.54it/s]

 25%|██▍       | 211/861 [02:53<09:36,  1.13it/s]

 25%|██▍       | 212/861 [02:53<09:38,  1.12it/s]

 25%|██▍       | 213/861 [02:54<08:20,  1.29it/s]

 25%|██▍       | 214/861 [02:54<07:25,  1.45it/s]

 25%|██▍       | 215/861 [02:55<07:42,  1.40it/s]

 25%|██▌       | 216/861 [02:56<06:45,  1.59it/s]

 25%|██▌       | 217/861 [02:56<05:33,  1.93it/s]

 25%|██▌       | 218/861 [02:56<05:02,  2.12it/s]

 25%|██▌       | 219/861 [02:57<06:53,  1.55it/s]

 26%|██▌       | 220/861 [02:58<07:24,  1.44it/s]

 26%|██▌       | 221/861 [02:59<06:37,  1.61it/s]

 26%|██▌       | 222/861 [03:00<08:28,  1.26it/s]

 26%|██▌       | 223/861 [03:01<09:06,  1.17it/s]

 26%|██▌       | 224/861 [03:01<08:17,  1.28it/s]

 26%|██▌       | 225/861 [03:03<10:36,  1.00s/it]

 26%|██▌       | 226/861 [03:04<12:06,  1.14s/it]

 26%|██▋       | 227/861 [03:05<11:00,  1.04s/it]

 26%|██▋       | 228/861 [03:06<10:46,  1.02s/it]

 27%|██▋       | 229/861 [03:07<09:16,  1.14it/s]

 27%|██▋       | 230/861 [03:08<09:39,  1.09it/s]

 27%|██▋       | 231/861 [03:10<14:49,  1.41s/it]

 27%|██▋       | 232/861 [03:10<10:54,  1.04s/it]

 27%|██▋       | 233/861 [03:11<10:03,  1.04it/s]

 27%|██▋       | 234/861 [03:12<08:55,  1.17it/s]

 27%|██▋       | 235/861 [03:13<09:01,  1.16it/s]

 27%|██▋       | 236/861 [03:13<08:23,  1.24it/s]

 28%|██▊       | 237/861 [03:14<08:00,  1.30it/s]

 28%|██▊       | 238/861 [03:14<06:32,  1.59it/s]

 28%|██▊       | 239/861 [03:16<09:32,  1.09it/s]

 28%|██▊       | 240/861 [03:16<08:02,  1.29it/s]

 28%|██▊       | 241/861 [03:18<09:38,  1.07it/s]

 28%|██▊       | 242/861 [03:18<08:21,  1.23it/s]

 28%|██▊       | 243/861 [03:19<09:36,  1.07it/s]

 28%|██▊       | 244/861 [03:20<09:04,  1.13it/s]

 28%|██▊       | 245/861 [03:22<10:25,  1.02s/it]

 29%|██▊       | 246/861 [03:22<10:08,  1.01it/s]

 29%|██▊       | 247/861 [03:23<08:10,  1.25it/s]

 29%|██▉       | 248/861 [03:23<06:16,  1.63it/s]

 29%|██▉       | 249/861 [03:24<06:15,  1.63it/s]

 29%|██▉       | 250/861 [03:25<07:47,  1.31it/s]

 29%|██▉       | 251/861 [03:26<07:56,  1.28it/s]

 29%|██▉       | 252/861 [03:26<07:50,  1.29it/s]

 29%|██▉       | 253/861 [03:27<07:13,  1.40it/s]

 30%|██▉       | 254/861 [03:27<05:49,  1.74it/s]

 30%|██▉       | 255/861 [03:28<06:29,  1.56it/s]

 30%|██▉       | 256/861 [03:29<08:11,  1.23it/s]

 30%|██▉       | 257/861 [03:30<08:49,  1.14it/s]

 30%|██▉       | 258/861 [03:31<09:33,  1.05it/s]

 30%|███       | 259/861 [03:32<10:08,  1.01s/it]

 30%|███       | 260/861 [03:34<10:18,  1.03s/it]

 30%|███       | 261/861 [03:36<13:38,  1.36s/it]

 30%|███       | 262/861 [03:36<11:20,  1.14s/it]

 31%|███       | 263/861 [03:36<08:26,  1.18it/s]

 31%|███       | 264/861 [03:37<08:11,  1.22it/s]

 31%|███       | 265/861 [03:38<06:58,  1.42it/s]

 31%|███       | 266/861 [03:38<05:48,  1.71it/s]

 31%|███       | 267/861 [03:38<05:32,  1.78it/s]

 31%|███       | 268/861 [03:39<05:18,  1.86it/s]

 31%|███       | 269/861 [03:40<05:43,  1.72it/s]

 31%|███▏      | 270/861 [03:40<06:05,  1.62it/s]

 31%|███▏      | 271/861 [03:41<06:26,  1.53it/s]

 32%|███▏      | 272/861 [03:42<08:16,  1.19it/s]

 32%|███▏      | 273/861 [03:43<08:37,  1.14it/s]

 32%|███▏      | 274/861 [03:45<09:57,  1.02s/it]

 32%|███▏      | 275/861 [03:45<07:28,  1.31it/s]

 32%|███▏      | 276/861 [03:46<08:12,  1.19it/s]

 32%|███▏      | 277/861 [03:47<10:04,  1.03s/it]

 32%|███▏      | 278/861 [03:49<10:46,  1.11s/it]

 32%|███▏      | 279/861 [03:49<10:04,  1.04s/it]

 33%|███▎      | 280/861 [03:50<09:47,  1.01s/it]

 33%|███▎      | 281/861 [03:52<10:28,  1.08s/it]

 33%|███▎      | 282/861 [03:52<09:33,  1.01it/s]

 33%|███▎      | 283/861 [03:53<08:41,  1.11it/s]

 33%|███▎      | 284/861 [03:53<07:04,  1.36it/s]

 33%|███▎      | 285/861 [03:54<06:39,  1.44it/s]

 33%|███▎      | 286/861 [03:56<11:05,  1.16s/it]

 33%|███▎      | 287/861 [03:58<13:03,  1.37s/it]

 33%|███▎      | 288/861 [03:59<11:43,  1.23s/it]

 34%|███▎      | 289/861 [03:59<09:08,  1.04it/s]

 34%|███▎      | 290/861 [04:00<08:24,  1.13it/s]

 34%|███▍      | 291/861 [04:01<07:57,  1.19it/s]

 34%|███▍      | 292/861 [04:02<09:20,  1.01it/s]

 34%|███▍      | 293/861 [04:03<08:46,  1.08it/s]

 34%|███▍      | 294/861 [04:04<09:31,  1.01s/it]

 34%|███▍      | 295/861 [04:04<07:16,  1.30it/s]

 34%|███▍      | 296/861 [04:05<06:55,  1.36it/s]

 34%|███▍      | 297/861 [04:07<09:01,  1.04it/s]

 35%|███▍      | 298/861 [04:08<09:47,  1.04s/it]

 35%|███▍      | 299/861 [04:10<11:54,  1.27s/it]

 35%|███▍      | 300/861 [04:10<10:14,  1.10s/it]

 35%|███▍      | 301/861 [04:13<13:48,  1.48s/it]

 35%|███▌      | 302/861 [04:13<10:20,  1.11s/it]

 35%|███▌      | 303/861 [04:14<11:22,  1.22s/it]

 35%|███▌      | 304/861 [04:15<10:46,  1.16s/it]

 35%|███▌      | 305/861 [04:17<11:47,  1.27s/it]

 36%|███▌      | 306/861 [04:18<11:41,  1.26s/it]

 36%|███▌      | 307/861 [04:20<13:38,  1.48s/it]

 36%|███▌      | 308/861 [04:20<10:00,  1.09s/it]

 36%|███▌      | 309/861 [04:21<07:54,  1.16it/s]

 36%|███▌      | 310/861 [04:21<07:19,  1.25it/s]

 36%|███▌      | 311/861 [04:22<07:48,  1.17it/s]

 36%|███▌      | 312/861 [04:23<08:30,  1.08it/s]

 36%|███▋      | 313/861 [04:25<10:25,  1.14s/it]

 36%|███▋      | 314/861 [04:26<09:50,  1.08s/it]

 37%|███▋      | 315/861 [04:27<08:34,  1.06it/s]

 37%|███▋      | 316/861 [04:28<09:38,  1.06s/it]

 37%|███▋      | 317/861 [04:28<07:15,  1.25it/s]

 37%|███▋      | 318/861 [04:28<05:47,  1.56it/s]

 37%|███▋      | 319/861 [04:30<08:24,  1.07it/s]

 37%|███▋      | 320/861 [04:31<07:49,  1.15it/s]

 37%|███▋      | 321/861 [04:32<09:15,  1.03s/it]

 37%|███▋      | 322/861 [04:34<11:35,  1.29s/it]

 38%|███▊      | 323/861 [04:35<10:30,  1.17s/it]

 38%|███▊      | 324/861 [04:36<10:55,  1.22s/it]

 38%|███▊      | 325/861 [04:37<10:52,  1.22s/it]

 38%|███▊      | 326/861 [04:38<08:02,  1.11it/s]

 38%|███▊      | 327/861 [04:39<09:44,  1.09s/it]

 38%|███▊      | 328/861 [04:40<08:53,  1.00s/it]

 38%|███▊      | 329/861 [04:41<08:21,  1.06it/s]

 38%|███▊      | 330/861 [04:41<07:37,  1.16it/s]

 38%|███▊      | 331/861 [04:44<13:01,  1.47s/it]

 39%|███▊      | 332/861 [04:45<11:35,  1.31s/it]

 39%|███▊      | 333/861 [04:47<12:25,  1.41s/it]

 39%|███▉      | 334/861 [04:48<12:09,  1.38s/it]

 39%|███▉      | 335/861 [04:49<09:56,  1.13s/it]

 39%|███▉      | 336/861 [04:50<10:50,  1.24s/it]

 39%|███▉      | 337/861 [04:51<09:02,  1.04s/it]

 39%|███▉      | 338/861 [04:53<12:01,  1.38s/it]

 39%|███▉      | 339/861 [04:54<11:11,  1.29s/it]

 39%|███▉      | 340/861 [04:54<08:50,  1.02s/it]

 40%|███▉      | 341/861 [04:55<06:54,  1.25it/s]

 40%|███▉      | 342/861 [04:55<06:33,  1.32it/s]

 40%|███▉      | 343/861 [04:56<06:47,  1.27it/s]

 40%|███▉      | 344/861 [04:57<05:53,  1.46it/s]

 40%|████      | 345/861 [04:58<06:46,  1.27it/s]

 40%|████      | 346/861 [04:59<07:19,  1.17it/s]

 40%|████      | 347/861 [04:59<06:09,  1.39it/s]

 40%|████      | 348/861 [05:00<05:55,  1.44it/s]

 41%|████      | 349/861 [05:01<06:01,  1.42it/s]

 41%|████      | 350/861 [05:01<06:36,  1.29it/s]

 41%|████      | 351/861 [05:02<06:21,  1.34it/s]

 41%|████      | 352/861 [05:03<06:09,  1.38it/s]

 41%|████      | 353/861 [05:03<05:59,  1.41it/s]

 41%|████      | 354/861 [05:04<05:51,  1.44it/s]

 41%|████      | 355/861 [05:05<05:09,  1.63it/s]

 41%|████▏     | 356/861 [05:05<04:49,  1.74it/s]

 41%|████▏     | 357/861 [05:05<04:06,  2.05it/s]

 42%|████▏     | 358/861 [05:06<04:41,  1.78it/s]

 42%|████▏     | 359/861 [05:08<07:16,  1.15it/s]

 42%|████▏     | 360/861 [05:09<08:12,  1.02it/s]

 42%|████▏     | 361/861 [05:10<07:50,  1.06it/s]

 42%|████▏     | 362/861 [05:11<08:19,  1.00s/it]

 42%|████▏     | 363/861 [05:12<08:19,  1.00s/it]

 42%|████▏     | 364/861 [05:13<07:26,  1.11it/s]

 42%|████▏     | 365/861 [05:15<10:35,  1.28s/it]

 43%|████▎     | 366/861 [05:16<09:30,  1.15s/it]

 43%|████▎     | 367/861 [05:18<11:52,  1.44s/it]

 43%|████▎     | 368/861 [05:19<11:46,  1.43s/it]

 43%|████▎     | 369/861 [05:20<09:59,  1.22s/it]

 43%|████▎     | 370/861 [05:20<08:39,  1.06s/it]

 43%|████▎     | 371/861 [05:22<08:34,  1.05s/it]

 43%|████▎     | 372/861 [05:23<08:54,  1.09s/it]

 43%|████▎     | 373/861 [05:23<07:50,  1.04it/s]

 43%|████▎     | 374/861 [05:26<10:55,  1.35s/it]

 44%|████▎     | 375/861 [05:27<11:27,  1.41s/it]

 44%|████▎     | 376/861 [05:28<09:33,  1.18s/it]

 44%|████▍     | 377/861 [05:30<11:04,  1.37s/it]

 44%|████▍     | 378/861 [05:32<12:19,  1.53s/it]

 44%|████▍     | 379/861 [05:32<09:06,  1.13s/it]

 44%|████▍     | 380/861 [05:33<08:29,  1.06s/it]

 44%|████▍     | 381/861 [05:34<08:01,  1.00s/it]

 44%|████▍     | 382/861 [05:35<08:14,  1.03s/it]

 44%|████▍     | 383/861 [05:36<08:00,  1.01s/it]

 45%|████▍     | 384/861 [05:36<07:27,  1.07it/s]

 45%|████▍     | 385/861 [05:37<06:02,  1.31it/s]

 45%|████▍     | 386/861 [05:38<06:10,  1.28it/s]

 45%|████▍     | 387/861 [05:39<07:32,  1.05it/s]

 45%|████▌     | 388/861 [05:40<06:55,  1.14it/s]

 45%|████▌     | 389/861 [05:40<05:48,  1.35it/s]

 45%|████▌     | 390/861 [05:41<05:41,  1.38it/s]

 45%|████▌     | 391/861 [05:42<05:59,  1.31it/s]

 46%|████▌     | 392/861 [05:42<06:04,  1.29it/s]

 46%|████▌     | 393/861 [05:44<07:30,  1.04it/s]

 46%|████▌     | 394/861 [05:45<08:09,  1.05s/it]

 46%|████▌     | 395/861 [05:46<07:08,  1.09it/s]

 46%|████▌     | 396/861 [05:46<06:03,  1.28it/s]

 46%|████▌     | 397/861 [05:46<04:40,  1.65it/s]

 46%|████▌     | 398/861 [05:47<04:58,  1.55it/s]

 46%|████▋     | 399/861 [05:48<05:52,  1.31it/s]

 46%|████▋     | 400/861 [05:49<06:30,  1.18it/s]

 47%|████▋     | 401/861 [05:50<05:34,  1.38it/s]

 47%|████▋     | 402/861 [05:50<05:41,  1.34it/s]

 47%|████▋     | 403/861 [05:51<05:38,  1.35it/s]

 47%|████▋     | 404/861 [05:52<06:10,  1.23it/s]

 47%|████▋     | 405/861 [05:52<05:06,  1.49it/s]

 47%|████▋     | 406/861 [05:54<06:10,  1.23it/s]

 47%|████▋     | 407/861 [05:54<06:33,  1.15it/s]

 47%|████▋     | 408/861 [05:55<06:18,  1.20it/s]

 48%|████▊     | 409/861 [05:56<05:37,  1.34it/s]

 48%|████▊     | 410/861 [05:57<05:37,  1.34it/s]

 48%|████▊     | 411/861 [05:57<04:42,  1.59it/s]

 48%|████▊     | 412/861 [05:58<05:40,  1.32it/s]

 48%|████▊     | 413/861 [05:59<05:33,  1.34it/s]

 48%|████▊     | 414/861 [05:59<05:18,  1.40it/s]

 48%|████▊     | 415/861 [06:00<04:37,  1.61it/s]

 48%|████▊     | 416/861 [06:00<04:29,  1.65it/s]

 48%|████▊     | 417/861 [06:01<04:46,  1.55it/s]

 49%|████▊     | 418/861 [06:01<04:22,  1.69it/s]

 49%|████▊     | 419/861 [06:02<05:02,  1.46it/s]

 49%|████▉     | 420/861 [06:03<04:58,  1.48it/s]

 49%|████▉     | 421/861 [06:04<04:33,  1.61it/s]

 49%|████▉     | 422/861 [06:04<03:58,  1.84it/s]

 49%|████▉     | 423/861 [06:05<04:58,  1.47it/s]

 49%|████▉     | 424/861 [06:05<04:31,  1.61it/s]

 49%|████▉     | 425/861 [06:06<04:46,  1.52it/s]

 49%|████▉     | 426/861 [06:07<05:59,  1.21it/s]

 50%|████▉     | 427/861 [06:08<06:03,  1.19it/s]

 50%|████▉     | 428/861 [06:09<05:35,  1.29it/s]

 50%|████▉     | 429/861 [06:10<05:33,  1.30it/s]

 50%|████▉     | 430/861 [06:11<06:27,  1.11it/s]

 50%|█████     | 431/861 [06:12<07:58,  1.11s/it]

 50%|█████     | 432/861 [06:14<08:29,  1.19s/it]

 50%|█████     | 433/861 [06:15<08:59,  1.26s/it]

 50%|█████     | 434/861 [06:16<07:20,  1.03s/it]

 51%|█████     | 435/861 [06:16<05:30,  1.29it/s]

 51%|█████     | 436/861 [06:16<04:26,  1.60it/s]

 51%|█████     | 437/861 [06:17<04:09,  1.70it/s]

 51%|█████     | 438/861 [06:17<03:38,  1.93it/s]

 51%|█████     | 439/861 [06:18<03:57,  1.77it/s]

 51%|█████     | 440/861 [06:18<03:22,  2.08it/s]

 51%|█████     | 441/861 [06:18<03:00,  2.32it/s]

 51%|█████▏    | 442/861 [06:19<03:17,  2.13it/s]

 51%|█████▏    | 443/861 [06:19<03:18,  2.10it/s]

 52%|█████▏    | 444/861 [06:20<03:30,  1.98it/s]

 52%|█████▏    | 445/861 [06:20<03:06,  2.24it/s]

 52%|█████▏    | 446/861 [06:21<02:59,  2.31it/s]

 52%|█████▏    | 447/861 [06:22<04:03,  1.70it/s]

 52%|█████▏    | 448/861 [06:22<04:28,  1.54it/s]

 52%|█████▏    | 449/861 [06:23<04:22,  1.57it/s]

 52%|█████▏    | 450/861 [06:24<05:11,  1.32it/s]

 52%|█████▏    | 451/861 [06:25<04:56,  1.38it/s]

 52%|█████▏    | 452/861 [06:25<04:46,  1.43it/s]

 53%|█████▎    | 453/861 [06:26<04:07,  1.65it/s]

 53%|█████▎    | 454/861 [06:26<04:08,  1.64it/s]

 53%|█████▎    | 455/861 [06:27<03:37,  1.87it/s]

 53%|█████▎    | 456/861 [06:27<03:36,  1.87it/s]

 53%|█████▎    | 457/861 [06:28<03:44,  1.80it/s]

 53%|█████▎    | 458/861 [06:29<04:17,  1.56it/s]

 53%|█████▎    | 459/861 [06:29<03:38,  1.84it/s]

 53%|█████▎    | 460/861 [06:30<03:52,  1.72it/s]

 54%|█████▎    | 461/861 [06:31<04:40,  1.43it/s]

 54%|█████▎    | 462/861 [06:31<04:18,  1.55it/s]

 54%|█████▍    | 463/861 [06:32<03:58,  1.67it/s]

 54%|█████▍    | 464/861 [06:32<03:35,  1.84it/s]

 54%|█████▍    | 465/861 [06:32<02:56,  2.24it/s]

 54%|█████▍    | 466/861 [06:33<03:10,  2.08it/s]

 54%|█████▍    | 467/861 [06:34<04:20,  1.51it/s]

 54%|█████▍    | 468/861 [06:34<03:36,  1.82it/s]

 54%|█████▍    | 469/861 [06:35<03:32,  1.85it/s]

 55%|█████▍    | 470/861 [06:35<03:00,  2.16it/s]

 55%|█████▍    | 471/861 [06:36<03:23,  1.91it/s]

 55%|█████▍    | 472/861 [06:36<03:23,  1.91it/s]

 55%|█████▍    | 473/861 [06:36<02:59,  2.16it/s]

 55%|█████▌    | 474/861 [06:37<02:34,  2.50it/s]

 55%|█████▌    | 475/861 [06:37<02:52,  2.24it/s]

 55%|█████▌    | 476/861 [06:38<02:45,  2.32it/s]

 55%|█████▌    | 477/861 [06:38<03:09,  2.03it/s]

 56%|█████▌    | 478/861 [06:39<03:04,  2.08it/s]

 56%|█████▌    | 479/861 [06:39<02:37,  2.43it/s]

 56%|█████▌    | 480/861 [06:40<03:04,  2.07it/s]

 56%|█████▌    | 481/861 [06:40<02:49,  2.24it/s]

 56%|█████▌    | 482/861 [06:40<02:32,  2.49it/s]

 56%|█████▌    | 483/861 [06:41<02:16,  2.77it/s]

 56%|█████▌    | 484/861 [06:41<02:19,  2.70it/s]

 56%|█████▋    | 485/861 [06:41<02:10,  2.89it/s]

 56%|█████▋    | 486/861 [06:42<01:55,  3.25it/s]

 57%|█████▋    | 487/861 [06:42<02:34,  2.42it/s]

 57%|█████▋    | 488/861 [06:42<02:14,  2.77it/s]

 57%|█████▋    | 489/861 [06:43<02:16,  2.72it/s]

 57%|█████▋    | 490/861 [06:43<02:04,  2.97it/s]

 57%|█████▋    | 491/861 [06:43<02:05,  2.96it/s]

 57%|█████▋    | 492/861 [06:44<02:06,  2.91it/s]

 57%|█████▋    | 493/861 [06:44<02:28,  2.48it/s]

 57%|█████▋    | 494/861 [06:45<02:13,  2.74it/s]

 57%|█████▋    | 495/861 [06:45<03:01,  2.01it/s]

 58%|█████▊    | 496/861 [06:46<03:40,  1.66it/s]

 58%|█████▊    | 497/861 [06:46<02:57,  2.05it/s]

 58%|█████▊    | 498/861 [06:47<02:49,  2.14it/s]

 58%|█████▊    | 499/861 [06:47<02:27,  2.46it/s]

 58%|█████▊    | 500/861 [06:48<02:40,  2.26it/s]

 58%|█████▊    | 501/861 [06:48<02:18,  2.60it/s]

 58%|█████▊    | 502/861 [06:49<02:48,  2.13it/s]

 58%|█████▊    | 503/861 [06:49<02:45,  2.16it/s]

 59%|█████▊    | 504/861 [06:50<02:47,  2.14it/s]

 59%|█████▊    | 505/861 [06:50<02:29,  2.39it/s]

 59%|█████▉    | 506/861 [06:50<02:13,  2.66it/s]

 59%|█████▉    | 507/861 [06:50<01:59,  2.97it/s]

 59%|█████▉    | 508/861 [06:51<02:54,  2.02it/s]

 59%|█████▉    | 509/861 [06:52<03:44,  1.57it/s]

 59%|█████▉    | 510/861 [06:53<03:22,  1.73it/s]

 59%|█████▉    | 511/861 [06:53<03:22,  1.73it/s]

 59%|█████▉    | 512/861 [06:54<03:06,  1.87it/s]

 60%|█████▉    | 513/861 [06:54<03:02,  1.91it/s]

 60%|█████▉    | 514/861 [06:55<02:54,  1.98it/s]

 60%|█████▉    | 515/861 [06:55<02:21,  2.44it/s]

 60%|█████▉    | 516/861 [06:55<02:00,  2.87it/s]

 60%|██████    | 517/861 [06:55<01:50,  3.10it/s]

 60%|██████    | 518/861 [06:56<02:11,  2.62it/s]

 60%|██████    | 519/861 [06:56<02:43,  2.09it/s]

 60%|██████    | 520/861 [06:57<03:08,  1.81it/s]

 61%|██████    | 521/861 [06:57<02:40,  2.12it/s]

 61%|██████    | 522/861 [06:58<02:58,  1.90it/s]

 61%|██████    | 523/861 [06:59<03:42,  1.52it/s]

 61%|██████    | 524/861 [07:00<04:32,  1.24it/s]

 61%|██████    | 525/861 [07:01<03:49,  1.47it/s]

 61%|██████    | 526/861 [07:01<03:40,  1.52it/s]

 61%|██████    | 527/861 [07:02<03:52,  1.44it/s]

 61%|██████▏   | 528/861 [07:03<03:45,  1.48it/s]

 61%|██████▏   | 529/861 [07:03<03:12,  1.73it/s]

 62%|██████▏   | 530/861 [07:03<02:49,  1.95it/s]

 62%|██████▏   | 531/861 [07:04<02:41,  2.04it/s]

 62%|██████▏   | 532/861 [07:04<02:54,  1.89it/s]

 62%|██████▏   | 533/861 [07:05<02:39,  2.06it/s]

 62%|██████▏   | 534/861 [07:05<02:47,  1.96it/s]

 62%|██████▏   | 535/861 [07:06<02:49,  1.92it/s]

 62%|██████▏   | 536/861 [07:07<02:55,  1.85it/s]

 62%|██████▏   | 537/861 [07:08<04:24,  1.22it/s]

 62%|██████▏   | 538/861 [07:08<03:43,  1.44it/s]

 63%|██████▎   | 539/861 [07:10<04:55,  1.09it/s]

 63%|██████▎   | 540/861 [07:11<04:50,  1.11it/s]

 63%|██████▎   | 541/861 [07:11<04:06,  1.30it/s]

 63%|██████▎   | 542/861 [07:11<03:17,  1.62it/s]

 63%|██████▎   | 543/861 [07:12<03:19,  1.60it/s]

 63%|██████▎   | 544/861 [07:13<03:09,  1.67it/s]

 63%|██████▎   | 545/861 [07:14<04:29,  1.17it/s]

 63%|██████▎   | 546/861 [07:15<04:55,  1.07it/s]

 64%|██████▎   | 547/861 [07:16<04:21,  1.20it/s]

 64%|██████▎   | 548/861 [07:17<05:07,  1.02it/s]

 64%|██████▍   | 549/861 [07:18<05:02,  1.03it/s]

 64%|██████▍   | 550/861 [07:19<04:38,  1.11it/s]

 64%|██████▍   | 551/861 [07:19<04:17,  1.20it/s]

 64%|██████▍   | 552/861 [07:20<04:17,  1.20it/s]

 64%|██████▍   | 553/861 [07:22<04:57,  1.04it/s]

 64%|██████▍   | 554/861 [07:23<05:04,  1.01it/s]

 64%|██████▍   | 555/861 [07:24<06:01,  1.18s/it]

 65%|██████▍   | 556/861 [07:25<06:06,  1.20s/it]

 65%|██████▍   | 557/861 [07:27<06:44,  1.33s/it]

 65%|██████▍   | 558/861 [07:28<06:37,  1.31s/it]

 65%|██████▍   | 559/861 [07:30<06:49,  1.36s/it]

 65%|██████▌   | 560/861 [07:31<06:45,  1.35s/it]

 65%|██████▌   | 561/861 [07:32<06:29,  1.30s/it]

 65%|██████▌   | 562/861 [07:33<05:44,  1.15s/it]

 65%|██████▌   | 563/861 [07:34<05:31,  1.11s/it]

 66%|██████▌   | 564/861 [07:35<05:21,  1.08s/it]

 66%|██████▌   | 565/861 [07:36<04:56,  1.00s/it]

 66%|██████▌   | 566/861 [07:37<05:29,  1.12s/it]

 66%|██████▌   | 567/861 [07:39<05:45,  1.18s/it]

 66%|██████▌   | 568/861 [07:40<05:45,  1.18s/it]

 66%|██████▌   | 569/861 [07:41<05:34,  1.14s/it]

 66%|██████▌   | 570/861 [07:42<04:55,  1.02s/it]

 66%|██████▋   | 571/861 [07:43<05:31,  1.14s/it]

 66%|██████▋   | 572/861 [07:44<05:30,  1.14s/it]

 67%|██████▋   | 573/861 [07:45<04:47,  1.00it/s]

 67%|██████▋   | 574/861 [07:46<05:02,  1.05s/it]

 67%|██████▋   | 575/861 [07:47<05:00,  1.05s/it]

 67%|██████▋   | 576/861 [07:49<06:00,  1.27s/it]

 67%|██████▋   | 577/861 [07:51<06:32,  1.38s/it]

 67%|██████▋   | 578/861 [07:52<06:26,  1.36s/it]

 67%|██████▋   | 579/861 [07:54<06:57,  1.48s/it]

 67%|██████▋   | 580/861 [07:55<06:27,  1.38s/it]

 67%|██████▋   | 581/861 [07:56<05:43,  1.23s/it]

 68%|██████▊   | 582/861 [07:58<07:08,  1.54s/it]

 68%|██████▊   | 583/861 [07:59<06:28,  1.40s/it]

 68%|██████▊   | 584/861 [08:00<06:01,  1.30s/it]

 68%|██████▊   | 585/861 [08:01<05:14,  1.14s/it]

 68%|██████▊   | 586/861 [08:01<04:28,  1.02it/s]

 68%|██████▊   | 587/861 [08:03<05:05,  1.12s/it]

 68%|██████▊   | 588/861 [08:04<04:58,  1.09s/it]

 68%|██████▊   | 589/861 [08:05<04:34,  1.01s/it]

 69%|██████▊   | 590/861 [08:06<05:14,  1.16s/it]

 69%|██████▊   | 591/861 [08:07<04:38,  1.03s/it]

 69%|██████▉   | 592/861 [08:08<04:33,  1.02s/it]

 69%|██████▉   | 593/861 [08:10<05:28,  1.22s/it]

 69%|██████▉   | 594/861 [08:11<05:34,  1.25s/it]

 69%|██████▉   | 595/861 [08:12<04:44,  1.07s/it]

 69%|██████▉   | 596/861 [08:12<03:53,  1.14it/s]

 69%|██████▉   | 597/861 [08:13<03:28,  1.26it/s]

 69%|██████▉   | 598/861 [08:14<03:40,  1.19it/s]

 70%|██████▉   | 599/861 [08:14<03:45,  1.16it/s]

 70%|██████▉   | 600/861 [08:15<03:31,  1.24it/s]

 70%|██████▉   | 601/861 [08:16<03:19,  1.30it/s]

 70%|██████▉   | 602/861 [08:18<04:29,  1.04s/it]

 70%|███████   | 603/861 [08:19<04:51,  1.13s/it]

 70%|███████   | 604/861 [08:20<04:24,  1.03s/it]

 70%|███████   | 605/861 [08:20<03:39,  1.17it/s]

 70%|███████   | 606/861 [08:21<03:42,  1.15it/s]

 70%|███████   | 607/861 [08:22<03:18,  1.28it/s]

 71%|███████   | 608/861 [08:22<03:06,  1.36it/s]

 71%|███████   | 609/861 [08:23<03:29,  1.21it/s]

 71%|███████   | 610/861 [08:25<04:30,  1.08s/it]

 71%|███████   | 611/861 [08:26<04:34,  1.10s/it]

 71%|███████   | 612/861 [08:27<04:39,  1.12s/it]

 71%|███████   | 613/861 [08:28<03:51,  1.07it/s]

 71%|███████▏  | 614/861 [08:29<04:07,  1.00s/it]

 71%|███████▏  | 615/861 [08:30<04:17,  1.05s/it]

 72%|███████▏  | 616/861 [08:32<05:38,  1.38s/it]

 72%|███████▏  | 617/861 [08:34<05:36,  1.38s/it]

 72%|███████▏  | 618/861 [08:35<05:14,  1.30s/it]

 72%|███████▏  | 619/861 [08:36<04:56,  1.23s/it]

 72%|███████▏  | 620/861 [08:37<05:33,  1.38s/it]

 72%|███████▏  | 621/861 [08:39<05:20,  1.33s/it]

 72%|███████▏  | 622/861 [08:39<04:17,  1.08s/it]

 72%|███████▏  | 623/861 [08:41<05:12,  1.31s/it]

 72%|███████▏  | 624/861 [08:42<04:23,  1.11s/it]

 73%|███████▎  | 625/861 [08:42<03:45,  1.05it/s]

 73%|███████▎  | 626/861 [08:43<03:35,  1.09it/s]

 73%|███████▎  | 627/861 [08:44<03:31,  1.11it/s]

 73%|███████▎  | 628/861 [08:45<03:58,  1.02s/it]

 73%|███████▎  | 629/861 [08:46<03:56,  1.02s/it]

 73%|███████▎  | 630/861 [08:47<03:27,  1.11it/s]

 73%|███████▎  | 631/861 [08:47<02:46,  1.38it/s]

 73%|███████▎  | 632/861 [08:49<04:00,  1.05s/it]

 74%|███████▎  | 633/861 [08:50<03:27,  1.10it/s]

 74%|███████▎  | 634/861 [08:51<04:24,  1.16s/it]

 74%|███████▍  | 635/861 [08:53<04:58,  1.32s/it]

 74%|███████▍  | 636/861 [08:54<04:18,  1.15s/it]

 74%|███████▍  | 637/861 [08:55<03:53,  1.04s/it]

 74%|███████▍  | 638/861 [08:56<03:42,  1.00it/s]

 74%|███████▍  | 639/861 [08:57<04:14,  1.15s/it]

 74%|███████▍  | 640/861 [08:58<03:43,  1.01s/it]

 74%|███████▍  | 641/861 [08:58<03:26,  1.07it/s]

 75%|███████▍  | 642/861 [09:00<03:36,  1.01it/s]

 75%|███████▍  | 643/861 [09:00<03:14,  1.12it/s]

 75%|███████▍  | 644/861 [09:01<03:02,  1.19it/s]

 75%|███████▍  | 645/861 [09:01<02:24,  1.50it/s]

 75%|███████▌  | 646/861 [09:02<02:22,  1.51it/s]

 75%|███████▌  | 647/861 [09:02<02:17,  1.56it/s]

 75%|███████▌  | 648/861 [09:03<02:33,  1.39it/s]

 75%|███████▌  | 649/861 [09:04<02:27,  1.44it/s]

 75%|███████▌  | 650/861 [09:05<02:16,  1.55it/s]

 76%|███████▌  | 651/861 [09:05<02:02,  1.72it/s]

 76%|███████▌  | 652/861 [09:06<02:22,  1.46it/s]

 76%|███████▌  | 653/861 [09:06<02:05,  1.66it/s]

 76%|███████▌  | 654/861 [09:07<02:06,  1.64it/s]

 76%|███████▌  | 655/861 [09:07<01:47,  1.92it/s]

 76%|███████▌  | 656/861 [09:08<01:36,  2.13it/s]

 76%|███████▋  | 657/861 [09:08<01:34,  2.16it/s]

 76%|███████▋  | 658/861 [09:09<02:12,  1.53it/s]

 77%|███████▋  | 659/861 [09:10<02:07,  1.58it/s]

 77%|███████▋  | 660/861 [09:10<02:09,  1.55it/s]

 77%|███████▋  | 661/861 [09:11<01:54,  1.75it/s]

 77%|███████▋  | 662/861 [09:12<02:10,  1.52it/s]

 77%|███████▋  | 663/861 [09:14<03:34,  1.09s/it]

 77%|███████▋  | 664/861 [09:14<03:01,  1.08it/s]

 77%|███████▋  | 665/861 [09:15<02:26,  1.33it/s]

 77%|███████▋  | 666/861 [09:15<01:59,  1.63it/s]

 77%|███████▋  | 667/861 [09:16<02:09,  1.50it/s]

 78%|███████▊  | 668/861 [09:16<01:58,  1.64it/s]

 78%|███████▊  | 669/861 [09:17<01:40,  1.91it/s]

 78%|███████▊  | 670/861 [09:17<01:50,  1.72it/s]

 78%|███████▊  | 671/861 [09:17<01:32,  2.06it/s]

 78%|███████▊  | 672/861 [09:19<02:26,  1.29it/s]

 78%|███████▊  | 673/861 [09:20<02:14,  1.40it/s]

 78%|███████▊  | 674/861 [09:20<01:48,  1.72it/s]

 78%|███████▊  | 675/861 [09:21<02:14,  1.38it/s]

 79%|███████▊  | 676/861 [09:21<01:56,  1.59it/s]

 79%|███████▊  | 677/861 [09:22<01:45,  1.74it/s]

 79%|███████▊  | 678/861 [09:22<01:39,  1.84it/s]

 79%|███████▉  | 679/861 [09:22<01:25,  2.12it/s]

 79%|███████▉  | 680/861 [09:23<01:13,  2.47it/s]

 79%|███████▉  | 681/861 [09:23<01:14,  2.40it/s]

 79%|███████▉  | 682/861 [09:24<01:38,  1.82it/s]

 79%|███████▉  | 683/861 [09:24<01:33,  1.90it/s]

 79%|███████▉  | 684/861 [09:25<01:46,  1.66it/s]

 80%|███████▉  | 685/861 [09:26<01:46,  1.66it/s]

 80%|███████▉  | 686/861 [09:26<01:39,  1.75it/s]

 80%|███████▉  | 687/861 [09:28<02:49,  1.02it/s]

 80%|███████▉  | 688/861 [09:29<02:16,  1.27it/s]

 80%|████████  | 689/861 [09:29<02:11,  1.30it/s]

 80%|████████  | 690/861 [09:30<01:51,  1.53it/s]

 80%|████████  | 691/861 [09:31<01:58,  1.43it/s]

 80%|████████  | 692/861 [09:31<01:42,  1.64it/s]

 80%|████████  | 693/861 [09:32<01:51,  1.51it/s]

 81%|████████  | 694/861 [09:32<01:38,  1.70it/s]

 81%|████████  | 695/861 [09:33<01:36,  1.72it/s]

 81%|████████  | 696/861 [09:33<01:19,  2.08it/s]

 81%|████████  | 697/861 [09:34<01:22,  1.98it/s]

 81%|████████  | 698/861 [09:34<01:40,  1.63it/s]

 81%|████████  | 699/861 [09:35<01:41,  1.60it/s]

 81%|████████▏ | 700/861 [09:36<01:44,  1.54it/s]

 81%|████████▏ | 701/861 [09:37<02:02,  1.31it/s]

 82%|████████▏ | 702/861 [09:38<02:04,  1.28it/s]

 82%|████████▏ | 703/861 [09:38<01:42,  1.54it/s]

 82%|████████▏ | 704/861 [09:38<01:36,  1.63it/s]

 82%|████████▏ | 705/861 [09:39<01:24,  1.86it/s]

 82%|████████▏ | 706/861 [09:39<01:19,  1.96it/s]

 82%|████████▏ | 707/861 [09:40<01:12,  2.13it/s]

 82%|████████▏ | 708/861 [09:40<01:04,  2.37it/s]

 82%|████████▏ | 709/861 [09:40<01:01,  2.46it/s]

 82%|████████▏ | 710/861 [09:42<01:38,  1.53it/s]

 83%|████████▎ | 711/861 [09:42<01:36,  1.56it/s]

 83%|████████▎ | 712/861 [09:43<01:22,  1.80it/s]

 83%|████████▎ | 713/861 [09:43<01:10,  2.10it/s]

 83%|████████▎ | 714/861 [09:44<01:20,  1.82it/s]

 83%|████████▎ | 715/861 [09:45<01:45,  1.38it/s]

 83%|████████▎ | 716/861 [09:46<01:53,  1.27it/s]

 83%|████████▎ | 717/861 [09:46<01:44,  1.37it/s]

 83%|████████▎ | 718/861 [09:47<02:03,  1.15it/s]

 84%|████████▎ | 719/861 [09:48<01:49,  1.30it/s]

 84%|████████▎ | 720/861 [09:48<01:36,  1.47it/s]

 84%|████████▎ | 721/861 [09:49<01:28,  1.59it/s]

 84%|████████▍ | 722/861 [09:50<01:28,  1.57it/s]

 84%|████████▍ | 723/861 [09:50<01:16,  1.79it/s]

 84%|████████▍ | 724/861 [09:50<01:13,  1.88it/s]

 84%|████████▍ | 725/861 [09:51<01:13,  1.85it/s]

 84%|████████▍ | 726/861 [09:52<01:26,  1.56it/s]

 84%|████████▍ | 727/861 [09:53<01:56,  1.15it/s]

 85%|████████▍ | 728/861 [09:54<02:02,  1.08it/s]

 85%|████████▍ | 729/861 [09:55<01:43,  1.27it/s]

 85%|████████▍ | 730/861 [09:55<01:26,  1.52it/s]

 85%|████████▍ | 731/861 [09:57<02:12,  1.02s/it]

 85%|████████▌ | 732/861 [09:57<01:50,  1.17it/s]

 85%|████████▌ | 733/861 [09:58<01:43,  1.23it/s]

 85%|████████▌ | 734/861 [09:58<01:20,  1.57it/s]

 85%|████████▌ | 735/861 [09:59<01:13,  1.72it/s]

 85%|████████▌ | 736/861 [09:59<01:13,  1.70it/s]

 86%|████████▌ | 737/861 [10:00<01:13,  1.69it/s]

 86%|████████▌ | 738/861 [10:01<01:08,  1.80it/s]

 86%|████████▌ | 739/861 [10:01<01:01,  1.99it/s]

 86%|████████▌ | 740/861 [10:02<01:04,  1.86it/s]

 86%|████████▌ | 741/861 [10:02<01:03,  1.90it/s]

 86%|████████▌ | 742/861 [10:03<01:15,  1.57it/s]

 86%|████████▋ | 743/861 [10:03<01:10,  1.67it/s]

 86%|████████▋ | 744/861 [10:04<01:03,  1.85it/s]

 87%|████████▋ | 745/861 [10:05<01:15,  1.53it/s]

 87%|████████▋ | 746/861 [10:05<01:00,  1.91it/s]

 87%|████████▋ | 747/861 [10:06<01:06,  1.72it/s]

 87%|████████▋ | 748/861 [10:06<01:03,  1.78it/s]

 87%|████████▋ | 749/861 [10:07<01:14,  1.50it/s]

 87%|████████▋ | 750/861 [10:07<00:59,  1.86it/s]

 87%|████████▋ | 751/861 [10:08<00:49,  2.22it/s]

 87%|████████▋ | 752/861 [10:09<01:12,  1.50it/s]

 87%|████████▋ | 753/861 [10:10<01:15,  1.43it/s]

 88%|████████▊ | 754/861 [10:10<01:05,  1.63it/s]

 88%|████████▊ | 755/861 [10:10<00:59,  1.77it/s]

 88%|████████▊ | 756/861 [10:11<00:53,  1.98it/s]

 88%|████████▊ | 757/861 [10:12<01:04,  1.62it/s]

 88%|████████▊ | 758/861 [10:12<01:06,  1.55it/s]

 88%|████████▊ | 759/861 [10:13<01:01,  1.65it/s]

 88%|████████▊ | 760/861 [10:14<01:11,  1.42it/s]

 88%|████████▊ | 761/861 [10:15<01:33,  1.07it/s]

 89%|████████▊ | 762/861 [10:16<01:16,  1.30it/s]

 89%|████████▊ | 763/861 [10:16<01:07,  1.46it/s]

 89%|████████▊ | 764/861 [10:17<01:05,  1.48it/s]

 89%|████████▉ | 765/861 [10:18<01:08,  1.40it/s]

 89%|████████▉ | 766/861 [10:18<01:02,  1.52it/s]

 89%|████████▉ | 767/861 [10:21<02:10,  1.39s/it]

 89%|████████▉ | 768/861 [10:22<01:52,  1.21s/it]

 89%|████████▉ | 769/861 [10:23<01:42,  1.12s/it]

 89%|████████▉ | 770/861 [10:23<01:21,  1.11it/s]

 90%|████████▉ | 771/861 [10:24<01:09,  1.30it/s]

 90%|████████▉ | 772/861 [10:24<01:02,  1.42it/s]

 90%|████████▉ | 773/861 [10:27<01:40,  1.15s/it]

 90%|████████▉ | 774/861 [10:27<01:21,  1.07it/s]

 90%|█████████ | 775/861 [10:28<01:22,  1.04it/s]

 90%|█████████ | 776/861 [10:29<01:20,  1.05it/s]

 90%|█████████ | 777/861 [10:30<01:19,  1.06it/s]

 90%|█████████ | 778/861 [10:31<01:15,  1.10it/s]

 90%|█████████ | 779/861 [10:32<01:23,  1.01s/it]

 91%|█████████ | 780/861 [10:34<01:42,  1.27s/it]

 91%|█████████ | 781/861 [10:36<02:11,  1.64s/it]

 91%|█████████ | 782/861 [10:38<02:04,  1.58s/it]

 91%|█████████ | 783/861 [10:38<01:40,  1.29s/it]

 91%|█████████ | 784/861 [10:39<01:26,  1.12s/it]

 91%|█████████ | 785/861 [10:40<01:15,  1.01it/s]

 91%|█████████▏| 786/861 [10:41<01:12,  1.04it/s]

 91%|█████████▏| 787/861 [10:41<01:01,  1.21it/s]

 92%|█████████▏| 788/861 [10:42<00:56,  1.29it/s]

 92%|█████████▏| 789/861 [10:43<00:56,  1.27it/s]

 92%|█████████▏| 790/861 [10:43<00:54,  1.29it/s]

 92%|█████████▏| 791/861 [10:44<00:49,  1.42it/s]

 92%|█████████▏| 792/861 [10:45<00:48,  1.42it/s]

 92%|█████████▏| 793/861 [10:46<00:51,  1.31it/s]

 92%|█████████▏| 794/861 [10:46<00:47,  1.41it/s]

 92%|█████████▏| 795/861 [10:47<00:54,  1.22it/s]

 92%|█████████▏| 796/861 [10:48<00:43,  1.49it/s]

 93%|█████████▎| 797/861 [10:48<00:45,  1.42it/s]

 93%|█████████▎| 798/861 [10:49<00:38,  1.62it/s]

 93%|█████████▎| 799/861 [10:49<00:35,  1.77it/s]

 93%|█████████▎| 800/861 [10:50<00:36,  1.65it/s]

 93%|█████████▎| 801/861 [10:51<00:50,  1.19it/s]

 93%|█████████▎| 802/861 [10:52<00:42,  1.38it/s]

 93%|█████████▎| 803/861 [10:53<00:50,  1.14it/s]

 93%|█████████▎| 804/861 [10:54<00:57,  1.01s/it]

 93%|█████████▎| 805/861 [10:56<01:01,  1.11s/it]

 94%|█████████▎| 806/861 [10:56<00:49,  1.12it/s]

 94%|█████████▎| 807/861 [10:57<00:52,  1.02it/s]

 94%|█████████▍| 808/861 [10:59<00:58,  1.10s/it]

 94%|█████████▍| 809/861 [10:59<00:46,  1.11it/s]

 94%|█████████▍| 810/861 [10:59<00:39,  1.29it/s]

 94%|█████████▍| 811/861 [11:00<00:38,  1.29it/s]

 94%|█████████▍| 812/861 [11:01<00:35,  1.38it/s]

 94%|█████████▍| 813/861 [11:02<00:44,  1.08it/s]

 95%|█████████▍| 814/861 [11:04<00:49,  1.06s/it]

 95%|█████████▍| 815/861 [11:05<00:46,  1.02s/it]

 95%|█████████▍| 816/861 [11:05<00:41,  1.09it/s]

 95%|█████████▍| 817/861 [11:06<00:39,  1.11it/s]

 95%|█████████▌| 818/861 [11:07<00:40,  1.06it/s]

 95%|█████████▌| 819/861 [11:08<00:35,  1.19it/s]

 95%|█████████▌| 820/861 [11:09<00:37,  1.10it/s]

 95%|█████████▌| 821/861 [11:10<00:37,  1.07it/s]

 95%|█████████▌| 822/861 [11:11<00:40,  1.05s/it]

 96%|█████████▌| 823/861 [11:13<00:48,  1.28s/it]

 96%|█████████▌| 824/861 [11:13<00:38,  1.03s/it]

 96%|█████████▌| 825/861 [11:14<00:32,  1.11it/s]

 96%|█████████▌| 826/861 [11:16<00:39,  1.12s/it]

 96%|█████████▌| 827/861 [11:17<00:36,  1.09s/it]

 96%|█████████▌| 828/861 [11:17<00:28,  1.16it/s]

 96%|█████████▋| 829/861 [11:18<00:31,  1.02it/s]

 96%|█████████▋| 830/861 [11:19<00:31,  1.00s/it]

 97%|█████████▋| 831/861 [11:21<00:34,  1.14s/it]

 97%|█████████▋| 832/861 [11:21<00:28,  1.00it/s]

 97%|█████████▋| 833/861 [11:22<00:24,  1.14it/s]

 97%|█████████▋| 834/861 [11:23<00:24,  1.11it/s]

 97%|█████████▋| 835/861 [11:24<00:23,  1.12it/s]

 97%|█████████▋| 836/861 [11:25<00:22,  1.12it/s]

 97%|█████████▋| 837/861 [11:26<00:24,  1.02s/it]

 97%|█████████▋| 838/861 [11:27<00:23,  1.03s/it]

 97%|█████████▋| 839/861 [11:28<00:19,  1.11it/s]

 98%|█████████▊| 840/861 [11:28<00:16,  1.31it/s]

 98%|█████████▊| 841/861 [11:29<00:14,  1.39it/s]

 98%|█████████▊| 842/861 [11:29<00:12,  1.48it/s]

 98%|█████████▊| 843/861 [11:30<00:12,  1.49it/s]

 98%|█████████▊| 844/861 [11:31<00:11,  1.54it/s]

 98%|█████████▊| 845/861 [11:32<00:13,  1.20it/s]

 98%|█████████▊| 846/861 [11:32<00:10,  1.37it/s]

 98%|█████████▊| 847/861 [11:33<00:11,  1.23it/s]

 98%|█████████▊| 848/861 [11:34<00:10,  1.29it/s]

 99%|█████████▊| 849/861 [11:35<00:10,  1.17it/s]

 99%|█████████▊| 850/861 [11:36<00:08,  1.30it/s]

 99%|█████████▉| 851/861 [11:36<00:07,  1.41it/s]

 99%|█████████▉| 852/861 [11:37<00:06,  1.48it/s]

 99%|█████████▉| 853/861 [11:37<00:05,  1.50it/s]

 99%|█████████▉| 854/861 [11:38<00:05,  1.31it/s]

 99%|█████████▉| 855/861 [11:39<00:04,  1.23it/s]

 99%|█████████▉| 856/861 [11:41<00:04,  1.03it/s]

100%|█████████▉| 857/861 [11:42<00:03,  1.03it/s]

100%|█████████▉| 858/861 [11:42<00:02,  1.18it/s]

100%|█████████▉| 859/861 [11:43<00:01,  1.23it/s]

100%|█████████▉| 860/861 [11:45<00:01,  1.06s/it]

100%|██████████| 861/861 [11:46<00:00,  1.04s/it]{'score': 13.077205386483644, 'counts': [17972, 8380, 4291, 2190], 'totals': [49525, 47803, 46081, 44359], 'precisions': [36.28874305906108, 17.5302805263268, 9.311863891842625, 4.936991365900945], 'bp': 1.0, 'sys_len': 49525, 'ref_len': 32555}

                                                         

                                                 
{'eval_loss': 2.4198501110076904, 'eval_bleu': 13.0772, 'eval_gen_len': 37.0436, 'eval_runtime': 802.9059, 'eval_samples_per_second': 2.145, 'eval_steps_per_second': 1.072, 'epoch': 14.0}

 88%|████████▊ | 54167/61904 [5:08:22<3:04:07,  1.43s/it]

100%|██████████| 861/861 [13:22<00:00,  1.04s/it]

                                                 [WARNING|configuration_utils.py:448] 2024-10-28 20:34:02,917 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 88%|████████▊ | 54168/61904 [5:08:44<534:04:07, 248.53s/it]
 88%|████████▊ | 54169/61904 [5:08:46<374:48:53, 174.45s/it]
 88%|████████▊ | 54170/61904 [5:08:47<263:14:41, 122.53s/it]
 88%|████████▊ | 54171/61904 [5:08:49<185:15:09, 86.24s/it] 
 88%|████████▊ | 54172/61904 [5:08:50<130:38:14, 60.82s/it]
 88%|████████▊ | 54173/61904 [5:08:51<92:19:45, 42.99s/it] 
 88%|████████▊ | 54174/61904 [5:08:53<65:32:20, 30.52s/it]
 88%|████████▊ | 54175/61904 [5:08:54<46:50:58, 21.82s/it]
 88%|████████▊ | 54176/61904 [5:08:56<33:38:28, 15.67s/it]
 88%|████████▊ | 54177/61904 [5:08:57<24:28:27, 11.40s/it]
 88%|████████▊ | 54178/61904 [5:08:59<18:07:15,  8.44s/it]
 88%|████████▊ | 54179/61904 [5:09:00<13:40:09,  6.37s/it]
 88%|████████▊ | 54180/61904 [5:09:02<10:42:22,  4.99s/it]
                                                          
{'loss': 2.497, 'learning_rate': 1.1251782704524828e-07, 'epoch': 14.0}

 88%|████████▊ | 54180/61904 [5:09:02<10:42:22,  4.99s/it]
 88%|████████▊ | 54181/61904 [5:09:03<8:25:20,  3.93s/it] 
 88%|████████▊ | 54182/61904 [5:09:05<6:49:32,  3.18s/it]
 88%|████████▊ | 54183/61904 [5:09:06<5:42:11,  2.66s/it]
 88%|████████▊ | 54184/61904 [5:09:08<5:06:09,  2.38s/it]
 88%|████████▊ | 54185/61904 [5:09:10<4:33:41,  2.13s/it]
 88%|████████▊ | 54186/61904 [5:09:11<4:11:36,  1.96s/it]
 88%|████████▊ | 54187/61904 [5:09:13<3:55:33,  1.83s/it]
 88%|████████▊ | 54188/61904 [5:09:14<3:39:33,  1.71s/it]
 88%|████████▊ | 54189/61904 [5:09:16<3:30:47,  1.64s/it]
 88%|████████▊ | 54190/61904 [5:09:17<3:27:39,  1.62s/it]
 88%|████████▊ | 54191/61904 [5:09:19<3:22:56,  1.58s/it]
 88%|████████▊ | 54192/61904 [5:09:20<3:15:02,  1.52s/it]
 88%|████████▊ | 54193/61904 [5:09:21<3:12:42,  1.50s/it]
 88%|████████▊ | 54194/61904 [5:09:23<3:09:46,  1.48s/it]
 88%|████████▊ | 54195/61904 [5:09:24<3:10:43,  1.48s/it]
 88%|████████▊ | 54196/61904 [5:09:26<3:18:27,  1.54s/it]
 88%|████████▊ | 54197/61904 [5:09:28<3:20:10,  1.56s/it]
 88%|████████▊ | 54198/61904 [5:09:29<3:14:42,  1.52s/it]
 88%|████████▊ | 54199/61904 [5:09:30<3:06:05,  1.45s/it]
 88%|████████▊ | 54200/61904 [5:09:32<3:05:54,  1.45s/it]
                                                         
{'loss': 2.4448, 'learning_rate': 1.1248541423570595e-07, 'epoch': 14.01}

 88%|████████▊ | 54200/61904 [5:09:32<3:05:54,  1.45s/it]
 88%|████████▊ | 54201/61904 [5:09:33<3:05:20,  1.44s/it]
 88%|████████▊ | 54202/61904 [5:09:35<3:03:01,  1.43s/it]
 88%|████████▊ | 54203/61904 [5:09:36<3:02:41,  1.42s/it]
 88%|████████▊ | 54204/61904 [5:09:38<3:05:54,  1.45s/it]
 88%|████████▊ | 54205/61904 [5:09:39<3:12:12,  1.50s/it]
 88%|████████▊ | 54206/61904 [5:09:41<3:05:05,  1.44s/it]
 88%|████████▊ | 54207/61904 [5:09:42<3:06:32,  1.45s/it]
 88%|████████▊ | 54208/61904 [5:09:43<3:07:56,  1.47s/it]
 88%|████████▊ | 54209/61904 [5:09:45<3:09:16,  1.48s/it]
 88%|████████▊ | 54210/61904 [5:09:47<3:11:24,  1.49s/it]
 88%|████████▊ | 54211/61904 [5:09:48<3:08:58,  1.47s/it]
 88%|████████▊ | 54212/61904 [5:09:49<3:08:25,  1.47s/it]
 88%|████████▊ | 54213/61904 [5:09:51<3:08:12,  1.47s/it]
 88%|████████▊ | 54214/61904 [5:09:52<3:09:40,  1.48s/it]
 88%|████████▊ | 54215/61904 [5:09:54<3:13:14,  1.51s/it]
 88%|████████▊ | 54216/61904 [5:09:55<3:06:52,  1.46s/it]
 88%|████████▊ | 54217/61904 [5:09:57<3:03:31,  1.43s/it]
 88%|████████▊ | 54218/61904 [5:09:58<3:04:59,  1.44s/it]
 88%|████████▊ | 54219/61904 [5:10:00<3:09:13,  1.48s/it]
 88%|████████▊ | 54220/61904 [5:10:01<3:15:25,  1.53s/it]
                                                         
{'loss': 2.4748, 'learning_rate': 1.1245300142616364e-07, 'epoch': 14.01}

 88%|████████▊ | 54220/61904 [5:10:01<3:15:25,  1.53s/it]
 88%|████████▊ | 54221/61904 [5:10:03<3:09:56,  1.48s/it]
 88%|████████▊ | 54222/61904 [5:10:04<3:03:43,  1.43s/it]
 88%|████████▊ | 54223/61904 [5:10:05<3:04:56,  1.44s/it]
 88%|████████▊ | 54224/61904 [5:10:07<3:00:51,  1.41s/it]
 88%|████████▊ | 54225/61904 [5:10:08<2:59:04,  1.40s/it]
 88%|████████▊ | 54226/61904 [5:10:10<3:03:49,  1.44s/it]
 88%|████████▊ | 54227/61904 [5:10:11<2:58:19,  1.39s/it]
 88%|████████▊ | 54228/61904 [5:10:12<2:56:55,  1.38s/it]
 88%|████████▊ | 54229/61904 [5:10:14<2:56:52,  1.38s/it]
 88%|████████▊ | 54230/61904 [5:10:15<3:03:36,  1.44s/it]
 88%|████████▊ | 54231/61904 [5:10:17<3:06:15,  1.46s/it]
 88%|████████▊ | 54232/61904 [5:10:18<3:06:11,  1.46s/it]
 88%|████████▊ | 54233/61904 [5:10:20<3:05:22,  1.45s/it]
 88%|████████▊ | 54234/61904 [5:10:21<3:12:19,  1.50s/it]
 88%|████████▊ | 54235/61904 [5:10:23<3:11:07,  1.50s/it]
 88%|████████▊ | 54236/61904 [5:10:24<3:16:52,  1.54s/it]
 88%|████████▊ | 54237/61904 [5:10:26<3:11:57,  1.50s/it]
 88%|████████▊ | 54238/61904 [5:10:27<3:07:04,  1.46s/it]
 88%|████████▊ | 54239/61904 [5:10:29<3:02:38,  1.43s/it]
 88%|████████▊ | 54240/61904 [5:10:30<3:04:32,  1.44s/it]
                                                         
{'loss': 2.5235, 'learning_rate': 1.124205886166213e-07, 'epoch': 14.02}

 88%|████████▊ | 54240/61904 [5:10:30<3:04:32,  1.44s/it]
 88%|████████▊ | 54241/61904 [5:10:32<3:09:05,  1.48s/it]
 88%|████████▊ | 54242/61904 [5:10:33<3:14:20,  1.52s/it]
 88%|████████▊ | 54243/61904 [5:10:35<3:10:56,  1.50s/it]
 88%|████████▊ | 54244/61904 [5:10:36<3:07:58,  1.47s/it]
 88%|████████▊ | 54245/61904 [5:10:38<3:06:29,  1.46s/it]
 88%|████████▊ | 54246/61904 [5:10:39<3:03:15,  1.44s/it]
 88%|████████▊ | 54247/61904 [5:10:40<3:06:41,  1.46s/it]
 88%|████████▊ | 54248/61904 [5:10:42<3:08:20,  1.48s/it]
 88%|████████▊ | 54249/61904 [5:10:43<3:03:42,  1.44s/it]
 88%|████████▊ | 54250/61904 [5:10:45<2:59:53,  1.41s/it]
 88%|████████▊ | 54251/61904 [5:10:46<3:00:03,  1.41s/it]
 88%|████████▊ | 54252/61904 [5:10:48<3:02:43,  1.43s/it]
 88%|████████▊ | 54253/61904 [5:10:49<2:58:15,  1.40s/it]
 88%|████████▊ | 54254/61904 [5:10:50<2:59:34,  1.41s/it]
 88%|████████▊ | 54255/61904 [5:10:52<3:04:02,  1.44s/it]
 88%|████████▊ | 54256/61904 [5:10:53<3:04:22,  1.45s/it]
 88%|████████▊ | 54257/61904 [5:10:55<3:02:24,  1.43s/it]
 88%|████████▊ | 54258/61904 [5:10:56<3:04:03,  1.44s/it]
 88%|████████▊ | 54259/61904 [5:10:58<3:07:49,  1.47s/it]
 88%|████████▊ | 54260/61904 [5:10:59<3:09:00,  1.48s/it]
                                                         
{'loss': 2.4309, 'learning_rate': 1.1238817580707896e-07, 'epoch': 14.02}

 88%|████████▊ | 54260/61904 [5:10:59<3:09:00,  1.48s/it]
 88%|████████▊ | 54261/61904 [5:11:01<3:06:33,  1.46s/it]
 88%|████████▊ | 54262/61904 [5:11:02<3:06:05,  1.46s/it]
 88%|████████▊ | 54263/61904 [5:11:04<3:09:08,  1.49s/it]
 88%|████████▊ | 54264/61904 [5:11:05<3:09:53,  1.49s/it]
 88%|████████▊ | 54265/61904 [5:11:07<3:05:26,  1.46s/it]
 88%|████████▊ | 54266/61904 [5:11:08<3:06:57,  1.47s/it]
 88%|████████▊ | 54267/61904 [5:11:09<3:04:28,  1.45s/it]
 88%|████████▊ | 54268/61904 [5:11:11<3:07:46,  1.48s/it]
 88%|████████▊ | 54269/61904 [5:11:12<3:06:04,  1.46s/it]
 88%|████████▊ | 54270/61904 [5:11:14<3:04:49,  1.45s/it]
 88%|████████▊ | 54271/61904 [5:11:15<3:06:04,  1.46s/it]
 88%|████████▊ | 54272/61904 [5:11:17<3:03:38,  1.44s/it]
 88%|████████▊ | 54273/61904 [5:11:18<3:01:53,  1.43s/it]
 88%|████████▊ | 54274/61904 [5:11:20<3:05:17,  1.46s/it]
 88%|████████▊ | 54275/61904 [5:11:21<2:58:46,  1.41s/it]
 88%|████████▊ | 54276/61904 [5:11:22<2:58:03,  1.40s/it]
 88%|████████▊ | 54277/61904 [5:11:24<2:55:22,  1.38s/it]
 88%|████████▊ | 54278/61904 [5:11:25<2:58:02,  1.40s/it]
 88%|████████▊ | 54279/61904 [5:11:26<2:56:36,  1.39s/it]
 88%|████████▊ | 54280/61904 [5:11:28<2:59:25,  1.41s/it]
                                                         
{'loss': 2.4434, 'learning_rate': 1.1235576299753662e-07, 'epoch': 14.03}

 88%|████████▊ | 54280/61904 [5:11:28<2:59:25,  1.41s/it]
 88%|████████▊ | 54281/61904 [5:11:29<2:57:54,  1.40s/it]
 88%|████████▊ | 54282/61904 [5:11:31<2:56:38,  1.39s/it]
 88%|████████▊ | 54283/61904 [5:11:32<2:53:16,  1.36s/it]
 88%|████████▊ | 54284/61904 [5:11:33<2:49:29,  1.33s/it]
 88%|████████▊ | 54285/61904 [5:11:35<2:54:01,  1.37s/it]
 88%|████████▊ | 54286/61904 [5:11:36<2:54:42,  1.38s/it]
 88%|████████▊ | 54287/61904 [5:11:37<2:57:32,  1.40s/it]
 88%|████████▊ | 54288/61904 [5:11:39<2:59:13,  1.41s/it]
 88%|████████▊ | 54289/61904 [5:11:40<2:59:12,  1.41s/it]
 88%|████████▊ | 54290/61904 [5:11:42<2:57:32,  1.40s/it]
 88%|████████▊ | 54291/61904 [5:11:43<2:53:47,  1.37s/it]
 88%|████████▊ | 54292/61904 [5:11:44<2:55:12,  1.38s/it]
 88%|████████▊ | 54293/61904 [5:11:46<2:57:40,  1.40s/it]
 88%|████████▊ | 54294/61904 [5:11:47<2:53:14,  1.37s/it]
 88%|████████▊ | 54295/61904 [5:11:49<2:57:25,  1.40s/it]
 88%|████████▊ | 54296/61904 [5:11:50<3:01:29,  1.43s/it]
 88%|████████▊ | 54297/61904 [5:11:52<2:59:32,  1.42s/it]
 88%|████████▊ | 54298/61904 [5:11:53<2:56:17,  1.39s/it]
 88%|████████▊ | 54299/61904 [5:11:54<2:53:20,  1.37s/it]
 88%|████████▊ | 54300/61904 [5:11:56<2:56:01,  1.39s/it]
                                                         
{'loss': 2.4613, 'learning_rate': 1.1232335018799431e-07, 'epoch': 14.03}

 88%|████████▊ | 54300/61904 [5:11:56<2:56:01,  1.39s/it]
 88%|████████▊ | 54301/61904 [5:11:57<2:52:15,  1.36s/it]
 88%|████████▊ | 54302/61904 [5:11:58<2:54:08,  1.37s/it]
 88%|████████▊ | 54303/61904 [5:12:00<2:51:10,  1.35s/it]
 88%|████████▊ | 54304/61904 [5:12:01<2:48:53,  1.33s/it]
 88%|████████▊ | 54305/61904 [5:12:02<2:50:00,  1.34s/it]
 88%|████████▊ | 54306/61904 [5:12:04<2:49:46,  1.34s/it]
 88%|████████▊ | 54307/61904 [5:12:05<2:47:01,  1.32s/it]
 88%|████████▊ | 54308/61904 [5:12:06<2:46:52,  1.32s/it]
 88%|████████▊ | 54309/61904 [5:12:08<2:47:38,  1.32s/it]
 88%|████████▊ | 54310/61904 [5:12:09<2:51:53,  1.36s/it]
 88%|████████▊ | 54311/61904 [5:12:10<2:50:24,  1.35s/it]
 88%|████████▊ | 54312/61904 [5:12:12<2:53:05,  1.37s/it]
 88%|████████▊ | 54313/61904 [5:12:13<3:00:33,  1.43s/it]
 88%|████████▊ | 54314/61904 [5:12:15<2:59:47,  1.42s/it]
 88%|████████▊ | 54315/61904 [5:12:16<2:56:30,  1.40s/it]
 88%|████████▊ | 54316/61904 [5:12:18<3:04:40,  1.46s/it]
 88%|████████▊ | 54317/61904 [5:12:19<3:04:13,  1.46s/it]
 88%|████████▊ | 54318/61904 [5:12:20<2:59:38,  1.42s/it]
 88%|████████▊ | 54319/61904 [5:12:22<3:10:22,  1.51s/it]
 88%|████████▊ | 54320/61904 [5:12:24<3:11:18,  1.51s/it]
                                                         
{'loss': 2.4494, 'learning_rate': 1.1229093737845197e-07, 'epoch': 14.04}

 88%|████████▊ | 54320/61904 [5:12:24<3:11:18,  1.51s/it]
 88%|████████▊ | 54321/61904 [5:12:25<3:05:35,  1.47s/it]
 88%|████████▊ | 54322/61904 [5:12:26<2:57:30,  1.40s/it]
 88%|████████▊ | 54323/61904 [5:12:28<2:58:43,  1.41s/it]
 88%|████████▊ | 54324/61904 [5:12:29<2:58:07,  1.41s/it]
 88%|████████▊ | 54325/61904 [5:12:30<2:55:43,  1.39s/it]
 88%|████████▊ | 54326/61904 [5:12:32<2:56:50,  1.40s/it]
 88%|████████▊ | 54327/61904 [5:12:33<2:59:43,  1.42s/it]
 88%|████████▊ | 54328/61904 [5:12:35<2:54:55,  1.39s/it]
 88%|████████▊ | 54329/61904 [5:12:36<2:56:22,  1.40s/it]
 88%|████████▊ | 54330/61904 [5:12:37<2:57:50,  1.41s/it]
 88%|████████▊ | 54331/61904 [5:12:39<2:54:26,  1.38s/it]
 88%|████████▊ | 54332/61904 [5:12:40<2:51:24,  1.36s/it]
 88%|████████▊ | 54333/61904 [5:12:41<2:52:18,  1.37s/it]
 88%|████████▊ | 54334/61904 [5:12:43<2:55:49,  1.39s/it]
 88%|████████▊ | 54335/61904 [5:12:44<2:50:50,  1.35s/it]
 88%|████████▊ | 54336/61904 [5:12:46<2:50:53,  1.35s/it]
 88%|████████▊ | 54337/61904 [5:12:47<2:54:38,  1.38s/it]
 88%|████████▊ | 54338/61904 [5:12:48<2:50:50,  1.35s/it]
 88%|████████▊ | 54339/61904 [5:12:50<2:50:05,  1.35s/it]
 88%|████████▊ | 54340/61904 [5:12:51<2:47:50,  1.33s/it]
                                                         
{'loss': 2.4625, 'learning_rate': 1.1225852456890963e-07, 'epoch': 14.04}

 88%|████████▊ | 54340/61904 [5:12:51<2:47:50,  1.33s/it]
 88%|████████▊ | 54341/61904 [5:12:52<2:47:05,  1.33s/it]
 88%|████████▊ | 54342/61904 [5:12:54<2:55:17,  1.39s/it]
 88%|████████▊ | 54343/61904 [5:12:55<2:51:14,  1.36s/it]
 88%|████████▊ | 54344/61904 [5:12:56<2:49:59,  1.35s/it]
 88%|████████▊ | 54345/61904 [5:12:58<3:04:43,  1.47s/it]
 88%|████████▊ | 54346/61904 [5:12:59<2:55:28,  1.39s/it]
 88%|████████▊ | 54347/61904 [5:13:01<2:56:19,  1.40s/it]
 88%|████████▊ | 54348/61904 [5:13:02<2:54:14,  1.38s/it]
 88%|████████▊ | 54349/61904 [5:13:04<2:58:41,  1.42s/it]
 88%|████████▊ | 54350/61904 [5:13:05<2:58:04,  1.41s/it]
 88%|████████▊ | 54351/61904 [5:13:06<2:54:53,  1.39s/it]
 88%|████████▊ | 54352/61904 [5:13:08<2:54:41,  1.39s/it]
 88%|████████▊ | 54353/61904 [5:13:09<2:55:51,  1.40s/it]
 88%|████████▊ | 54354/61904 [5:13:11<2:55:38,  1.40s/it]
 88%|████████▊ | 54355/61904 [5:13:12<2:52:46,  1.37s/it]
 88%|████████▊ | 54356/61904 [5:13:13<2:55:38,  1.40s/it]
 88%|████████▊ | 54357/61904 [5:13:15<2:49:33,  1.35s/it]
 88%|████████▊ | 54358/61904 [5:13:16<2:48:12,  1.34s/it]
 88%|████████▊ | 54359/61904 [5:13:17<2:48:12,  1.34s/it]
 88%|████████▊ | 54360/61904 [5:13:18<2:45:57,  1.32s/it]
                                                         
{'loss': 2.4266, 'learning_rate': 1.122261117593673e-07, 'epoch': 14.05}

 88%|████████▊ | 54360/61904 [5:13:18<2:45:57,  1.32s/it]
 88%|████████▊ | 54361/61904 [5:13:20<2:47:44,  1.33s/it]
 88%|████████▊ | 54362/61904 [5:13:21<2:46:15,  1.32s/it]
 88%|████████▊ | 54363/61904 [5:13:23<2:49:44,  1.35s/it]
 88%|████████▊ | 54364/61904 [5:13:24<2:50:38,  1.36s/it]
 88%|████████▊ | 54365/61904 [5:13:25<2:48:53,  1.34s/it]
 88%|████████▊ | 54366/61904 [5:13:27<2:57:50,  1.42s/it]
 88%|████████▊ | 54367/61904 [5:13:28<2:51:17,  1.36s/it]
 88%|████████▊ | 54368/61904 [5:13:30<2:53:40,  1.38s/it]
 88%|████████▊ | 54369/61904 [5:13:31<2:49:21,  1.35s/it]
 88%|████████▊ | 54370/61904 [5:13:32<2:51:32,  1.37s/it]
 88%|████████▊ | 54371/61904 [5:13:34<2:49:45,  1.35s/it]
 88%|████████▊ | 54372/61904 [5:13:35<2:50:21,  1.36s/it]
 88%|████████▊ | 54373/61904 [5:13:36<2:55:10,  1.40s/it]
 88%|████████▊ | 54374/61904 [5:13:38<2:53:54,  1.39s/it]
 88%|████████▊ | 54375/61904 [5:13:39<3:01:25,  1.45s/it]
 88%|████████▊ | 54376/61904 [5:13:41<3:00:52,  1.44s/it]
 88%|████████▊ | 54377/61904 [5:13:42<2:58:09,  1.42s/it]
 88%|████████▊ | 54378/61904 [5:13:44<2:58:37,  1.42s/it]
 88%|████████▊ | 54379/61904 [5:13:45<2:54:26,  1.39s/it]
 88%|████████▊ | 54380/61904 [5:13:46<2:57:26,  1.41s/it]
                                                         
{'loss': 2.4216, 'learning_rate': 1.1219369894982498e-07, 'epoch': 14.05}

 88%|████████▊ | 54380/61904 [5:13:46<2:57:26,  1.41s/it]
 88%|████████▊ | 54381/61904 [5:13:48<2:57:16,  1.41s/it]
 88%|████████▊ | 54382/61904 [5:13:49<2:58:40,  1.43s/it]
 88%|████████▊ | 54383/61904 [5:13:51<2:56:34,  1.41s/it]
 88%|████████▊ | 54384/61904 [5:13:52<2:56:37,  1.41s/it]
 88%|████████▊ | 54385/61904 [5:13:53<2:55:03,  1.40s/it]
 88%|████████▊ | 54386/61904 [5:13:55<2:54:01,  1.39s/it]
 88%|████████▊ | 54387/61904 [5:13:56<2:54:02,  1.39s/it]
 88%|████████▊ | 54388/61904 [5:13:58<2:58:01,  1.42s/it]
 88%|████████▊ | 54389/61904 [5:13:59<2:57:12,  1.41s/it]
 88%|████████▊ | 54390/61904 [5:14:00<2:55:22,  1.40s/it]
 88%|████████▊ | 54391/61904 [5:14:02<2:54:15,  1.39s/it]
 88%|████████▊ | 54392/61904 [5:14:03<2:55:49,  1.40s/it]
 88%|████████▊ | 54393/61904 [5:14:05<2:54:26,  1.39s/it]
 88%|████████▊ | 54394/61904 [5:14:06<2:54:13,  1.39s/it]
 88%|████████▊ | 54395/61904 [5:14:07<3:00:53,  1.45s/it]
 88%|████████▊ | 54396/61904 [5:14:09<3:00:50,  1.45s/it]
 88%|████████▊ | 54397/61904 [5:14:10<3:03:00,  1.46s/it]
 88%|████████▊ | 54398/61904 [5:14:12<3:03:01,  1.46s/it]
 88%|████████▊ | 54399/61904 [5:14:13<2:58:46,  1.43s/it]
 88%|████████▊ | 54400/61904 [5:14:15<2:53:26,  1.39s/it]
                                                         
{'loss': 2.4619, 'learning_rate': 1.1216128614028264e-07, 'epoch': 14.06}

 88%|████████▊ | 54400/61904 [5:14:15<2:53:26,  1.39s/it]
 88%|████████▊ | 54401/61904 [5:14:16<2:57:33,  1.42s/it]
 88%|████████▊ | 54402/61904 [5:14:17<2:53:17,  1.39s/it]
 88%|████████▊ | 54403/61904 [5:14:19<2:46:42,  1.33s/it]
 88%|████████▊ | 54404/61904 [5:14:20<2:47:38,  1.34s/it]
 88%|████████▊ | 54405/61904 [5:14:21<2:46:30,  1.33s/it]
 88%|████████▊ | 54406/61904 [5:14:23<2:50:41,  1.37s/it]
 88%|████████▊ | 54407/61904 [5:14:24<2:48:03,  1.35s/it]
 88%|████████▊ | 54408/61904 [5:14:25<2:49:15,  1.35s/it]
 88%|████████▊ | 54409/61904 [5:14:27<2:48:38,  1.35s/it]
 88%|████████▊ | 54410/61904 [5:14:28<2:52:19,  1.38s/it]
 88%|████████▊ | 54411/61904 [5:14:30<2:52:08,  1.38s/it]
 88%|████████▊ | 54412/61904 [5:14:31<2:55:27,  1.41s/it]
 88%|████████▊ | 54413/61904 [5:14:32<2:51:21,  1.37s/it]
 88%|████████▊ | 54414/61904 [5:14:34<2:52:21,  1.38s/it]
 88%|████████▊ | 54415/61904 [5:14:35<2:51:41,  1.38s/it]
 88%|████████▊ | 54416/61904 [5:14:36<2:54:36,  1.40s/it]
 88%|████████▊ | 54417/61904 [5:14:38<2:54:09,  1.40s/it]
 88%|████████▊ | 54418/61904 [5:14:39<2:49:50,  1.36s/it]
 88%|████████▊ | 54419/61904 [5:14:41<2:50:14,  1.36s/it]
 88%|████████▊ | 54420/61904 [5:14:42<2:50:49,  1.37s/it]
                                                         
{'loss': 2.4161, 'learning_rate': 1.1212887333074031e-07, 'epoch': 14.07}

 88%|████████▊ | 54420/61904 [5:14:42<2:50:49,  1.37s/it]
 88%|████████▊ | 54421/61904 [5:14:43<2:52:29,  1.38s/it]
 88%|████████▊ | 54422/61904 [5:14:45<2:56:20,  1.41s/it]
 88%|████████▊ | 54423/61904 [5:14:46<2:54:44,  1.40s/it]
 88%|████████▊ | 54424/61904 [5:14:48<3:00:55,  1.45s/it]
 88%|████████▊ | 54425/61904 [5:14:49<2:56:35,  1.42s/it]
 88%|████████▊ | 54426/61904 [5:14:50<2:54:02,  1.40s/it]
 88%|████████▊ | 54427/61904 [5:14:52<2:52:11,  1.38s/it]
 88%|████████▊ | 54428/61904 [5:14:53<2:52:56,  1.39s/it]
 88%|████████▊ | 54429/61904 [5:14:55<2:51:20,  1.38s/it]
 88%|████████▊ | 54430/61904 [5:14:56<2:55:16,  1.41s/it]
 88%|████████▊ | 54431/61904 [5:14:57<2:51:12,  1.37s/it]
 88%|████████▊ | 54432/61904 [5:14:59<2:50:34,  1.37s/it]
 88%|████████▊ | 54433/61904 [5:15:00<2:59:13,  1.44s/it]
 88%|████████▊ | 54434/61904 [5:15:02<2:56:31,  1.42s/it]
 88%|████████▊ | 54435/61904 [5:15:03<2:52:32,  1.39s/it]
 88%|████████▊ | 54436/61904 [5:15:04<2:51:29,  1.38s/it]
 88%|████████▊ | 54437/61904 [5:15:06<2:48:58,  1.36s/it]
 88%|████████▊ | 54438/61904 [5:15:07<2:52:01,  1.38s/it]
 88%|████████▊ | 54439/61904 [5:15:08<2:48:23,  1.35s/it]
 88%|████████▊ | 54440/61904 [5:15:10<2:55:07,  1.41s/it]
                                                         
{'loss': 2.4824, 'learning_rate': 1.12096460521198e-07, 'epoch': 14.07}

 88%|████████▊ | 54440/61904 [5:15:10<2:55:07,  1.41s/it]
 88%|████████▊ | 54441/61904 [5:15:11<2:55:06,  1.41s/it]
 88%|████████▊ | 54442/61904 [5:15:13<2:56:44,  1.42s/it]
 88%|████████▊ | 54443/61904 [5:15:14<2:53:13,  1.39s/it]
 88%|████████▊ | 54444/61904 [5:15:16<3:03:42,  1.48s/it]
 88%|████████▊ | 54445/61904 [5:15:17<2:59:05,  1.44s/it]
 88%|████████▊ | 54446/61904 [5:15:18<2:53:21,  1.39s/it]
 88%|████████▊ | 54447/61904 [5:15:20<2:55:47,  1.41s/it]
 88%|████████▊ | 54448/61904 [5:15:21<2:55:18,  1.41s/it]
 88%|████████▊ | 54449/61904 [5:15:23<2:54:02,  1.40s/it]
 88%|████████▊ | 54450/61904 [5:15:24<2:52:35,  1.39s/it]
 88%|████████▊ | 54451/61904 [5:15:25<2:52:47,  1.39s/it]
 88%|████████▊ | 54452/61904 [5:15:27<2:50:37,  1.37s/it]
 88%|████████▊ | 54453/61904 [5:15:28<2:51:49,  1.38s/it]
 88%|████████▊ | 54454/61904 [5:15:29<2:49:06,  1.36s/it]
 88%|████████▊ | 54455/61904 [5:15:31<2:49:59,  1.37s/it]
 88%|████████▊ | 54456/61904 [5:15:32<2:50:44,  1.38s/it]
 88%|████████▊ | 54457/61904 [5:15:33<2:46:50,  1.34s/it]
 88%|████████▊ | 54458/61904 [5:15:35<2:42:16,  1.31s/it]
 88%|████████▊ | 54459/61904 [5:15:36<2:46:04,  1.34s/it]
 88%|████████▊ | 54460/61904 [5:15:38<2:49:08,  1.36s/it]
                                                         
{'loss': 2.3989, 'learning_rate': 1.1206404771165566e-07, 'epoch': 14.08}

 88%|████████▊ | 54460/61904 [5:15:38<2:49:08,  1.36s/it]
 88%|████████▊ | 54461/61904 [5:15:39<2:47:12,  1.35s/it]
 88%|████████▊ | 54462/61904 [5:15:40<2:45:42,  1.34s/it]
 88%|████████▊ | 54463/61904 [5:15:41<2:44:43,  1.33s/it]
 88%|████████▊ | 54464/61904 [5:15:43<2:49:54,  1.37s/it]
 88%|████████▊ | 54465/61904 [5:15:44<2:53:18,  1.40s/it]
 88%|████████▊ | 54466/61904 [5:15:46<2:52:06,  1.39s/it]
 88%|████████▊ | 54467/61904 [5:15:47<2:46:48,  1.35s/it]
 88%|████████▊ | 54468/61904 [5:15:48<2:46:22,  1.34s/it]
 88%|████████▊ | 54469/61904 [5:15:50<2:47:20,  1.35s/it]
 88%|████████▊ | 54470/61904 [5:15:51<2:51:57,  1.39s/it]
 88%|████████▊ | 54471/61904 [5:15:53<2:54:09,  1.41s/it]
 88%|████████▊ | 54472/61904 [5:15:54<2:55:40,  1.42s/it]
 88%|████████▊ | 54473/61904 [5:15:55<2:51:40,  1.39s/it]
 88%|████████▊ | 54474/61904 [5:15:57<2:45:58,  1.34s/it]
 88%|████████▊ | 54475/61904 [5:15:58<2:48:07,  1.36s/it]
 88%|████████▊ | 54476/61904 [5:15:59<2:46:10,  1.34s/it]
 88%|████████▊ | 54477/61904 [5:16:01<2:49:50,  1.37s/it]
 88%|████████▊ | 54478/61904 [5:16:02<2:54:14,  1.41s/it]
 88%|████████▊ | 54479/61904 [5:16:04<2:54:14,  1.41s/it]
 88%|████████▊ | 54480/61904 [5:16:05<2:52:29,  1.39s/it]
                                                         
{'loss': 2.4347, 'learning_rate': 1.1203163490211332e-07, 'epoch': 14.08}

 88%|████████▊ | 54480/61904 [5:16:05<2:52:29,  1.39s/it]
 88%|████████▊ | 54481/61904 [5:16:06<2:47:10,  1.35s/it]
 88%|████████▊ | 54482/61904 [5:16:08<2:49:54,  1.37s/it]
 88%|████████▊ | 54483/61904 [5:16:09<2:53:31,  1.40s/it]
 88%|████████▊ | 54484/61904 [5:16:11<2:51:41,  1.39s/it]
 88%|████████▊ | 54485/61904 [5:16:12<2:54:04,  1.41s/it]
 88%|████████▊ | 54486/61904 [5:16:13<2:55:31,  1.42s/it]
 88%|████████▊ | 54487/61904 [5:16:15<2:56:28,  1.43s/it]
 88%|████████▊ | 54488/61904 [5:16:16<2:50:01,  1.38s/it]
 88%|████████▊ | 54489/61904 [5:16:18<2:51:41,  1.39s/it]
 88%|████████▊ | 54490/61904 [5:16:19<2:48:32,  1.36s/it]
 88%|████████▊ | 54491/61904 [5:16:20<2:44:32,  1.33s/it]
 88%|████████▊ | 54492/61904 [5:16:22<2:47:22,  1.35s/it]
 88%|████████▊ | 54493/61904 [5:16:23<2:50:24,  1.38s/it]
 88%|████████▊ | 54494/61904 [5:16:24<2:50:04,  1.38s/it]
 88%|████████▊ | 54495/61904 [5:16:26<2:48:56,  1.37s/it]
 88%|████████▊ | 54496/61904 [5:16:27<2:46:02,  1.34s/it]
 88%|████████▊ | 54497/61904 [5:16:28<2:45:28,  1.34s/it]
 88%|████████▊ | 54498/61904 [5:16:30<2:44:24,  1.33s/it]
 88%|████████▊ | 54499/61904 [5:16:31<2:44:35,  1.33s/it]
 88%|████████▊ | 54500/61904 [5:16:32<2:42:32,  1.32s/it]
                                                         
{'loss': 2.4447, 'learning_rate': 1.1199922209257098e-07, 'epoch': 14.09}

 88%|████████▊ | 54500/61904 [5:16:32<2:42:32,  1.32s/it]
 88%|████████▊ | 54501/61904 [5:16:34<2:43:30,  1.33s/it]
 88%|████████▊ | 54502/61904 [5:16:35<2:48:30,  1.37s/it]
 88%|████████▊ | 54503/61904 [5:16:36<2:47:24,  1.36s/it]
 88%|████████▊ | 54504/61904 [5:16:38<2:48:08,  1.36s/it]
 88%|████████▊ | 54505/61904 [5:16:39<2:44:06,  1.33s/it]
 88%|████████▊ | 54506/61904 [5:16:40<2:44:26,  1.33s/it]
 88%|████████▊ | 54507/61904 [5:16:42<2:43:26,  1.33s/it]
 88%|████████▊ | 54508/61904 [5:16:43<2:42:30,  1.32s/it]
 88%|████████▊ | 54509/61904 [5:16:44<2:46:40,  1.35s/it]
 88%|████████▊ | 54510/61904 [5:16:46<2:51:40,  1.39s/it]
 88%|████████▊ | 54511/61904 [5:16:47<2:54:29,  1.42s/it]
 88%|████████▊ | 54512/61904 [5:16:49<2:51:48,  1.39s/it]
 88%|████████▊ | 54513/61904 [5:16:50<2:50:48,  1.39s/it]
 88%|████████▊ | 54514/61904 [5:16:51<2:50:40,  1.39s/it]
 88%|████████▊ | 54515/61904 [5:16:53<2:50:16,  1.38s/it]
 88%|████████▊ | 54516/61904 [5:16:54<2:50:03,  1.38s/it]
 88%|████████▊ | 54517/61904 [5:16:56<2:49:04,  1.37s/it]
 88%|████████▊ | 54518/61904 [5:16:57<2:53:18,  1.41s/it]
 88%|████████▊ | 54519/61904 [5:16:58<2:53:43,  1.41s/it]
 88%|████████▊ | 54520/61904 [5:17:00<2:57:14,  1.44s/it]
                                                         
{'loss': 2.4, 'learning_rate': 1.1196680928302867e-07, 'epoch': 14.09}

 88%|████████▊ | 54520/61904 [5:17:00<2:57:14,  1.44s/it]
 88%|████████▊ | 54521/61904 [5:17:01<2:54:26,  1.42s/it]
 88%|████████▊ | 54522/61904 [5:17:03<2:48:18,  1.37s/it]
 88%|████████▊ | 54523/61904 [5:17:04<3:02:14,  1.48s/it]
 88%|████████▊ | 54524/61904 [5:17:06<2:59:31,  1.46s/it]
 88%|████████▊ | 54525/61904 [5:17:07<2:52:23,  1.40s/it]
 88%|████████▊ | 54526/61904 [5:17:08<2:47:30,  1.36s/it]
 88%|████████▊ | 54527/61904 [5:17:10<2:52:35,  1.40s/it]
 88%|████████▊ | 54528/61904 [5:17:11<2:52:38,  1.40s/it]
 88%|████████▊ | 54529/61904 [5:17:12<2:46:34,  1.36s/it]
 88%|████████▊ | 54530/61904 [5:17:14<2:51:53,  1.40s/it]
 88%|████████▊ | 54531/61904 [5:17:15<2:47:13,  1.36s/it]
 88%|████████▊ | 54532/61904 [5:17:17<2:47:10,  1.36s/it]
 88%|████████▊ | 54533/61904 [5:17:18<2:49:26,  1.38s/it]
 88%|████████▊ | 54534/61904 [5:17:19<2:45:30,  1.35s/it]
 88%|████████▊ | 54535/61904 [5:17:21<2:44:28,  1.34s/it]
 88%|████████▊ | 54536/61904 [5:17:22<2:42:26,  1.32s/it]
 88%|████████▊ | 54537/61904 [5:17:23<2:49:36,  1.38s/it]
 88%|████████▊ | 54538/61904 [5:17:25<2:48:00,  1.37s/it]
 88%|████████▊ | 54539/61904 [5:17:26<2:44:30,  1.34s/it]
 88%|████████▊ | 54540/61904 [5:17:27<2:48:01,  1.37s/it]
                                                         
{'loss': 2.421, 'learning_rate': 1.1193439647348633e-07, 'epoch': 14.1}

 88%|████████▊ | 54540/61904 [5:17:27<2:48:01,  1.37s/it]
 88%|████████▊ | 54541/61904 [5:17:29<2:48:58,  1.38s/it]
 88%|████████▊ | 54542/61904 [5:17:30<2:47:38,  1.37s/it]
 88%|████████▊ | 54543/61904 [5:17:32<2:50:52,  1.39s/it]
 88%|████████▊ | 54544/61904 [5:17:33<2:50:06,  1.39s/it]
 88%|████████▊ | 54545/61904 [5:17:34<2:44:30,  1.34s/it]
 88%|████████▊ | 54546/61904 [5:17:36<2:49:24,  1.38s/it]
 88%|████████▊ | 54547/61904 [5:17:37<2:45:19,  1.35s/it]
 88%|████████▊ | 54548/61904 [5:17:38<2:45:08,  1.35s/it]
 88%|████████▊ | 54549/61904 [5:17:40<2:46:29,  1.36s/it]
 88%|████████▊ | 54550/61904 [5:17:41<2:44:37,  1.34s/it]
 88%|████████▊ | 54551/61904 [5:17:43<2:51:24,  1.40s/it]
 88%|████████▊ | 54552/61904 [5:17:44<2:53:24,  1.42s/it]
 88%|████████▊ | 54553/61904 [5:17:45<2:56:06,  1.44s/it]
 88%|████████▊ | 54554/61904 [5:17:47<2:55:53,  1.44s/it]
 88%|████████▊ | 54555/61904 [5:17:48<2:58:01,  1.45s/it]
 88%|████████▊ | 54556/61904 [5:17:50<2:56:16,  1.44s/it]
 88%|████████▊ | 54557/61904 [5:17:51<2:58:10,  1.46s/it]
 88%|████████▊ | 54558/61904 [5:17:53<2:56:11,  1.44s/it]
 88%|████████▊ | 54559/61904 [5:17:54<2:56:44,  1.44s/it]
 88%|████████▊ | 54560/61904 [5:17:56<2:56:15,  1.44s/it]
                                                         
{'loss': 2.4029, 'learning_rate': 1.1190198366394399e-07, 'epoch': 14.1}

 88%|████████▊ | 54560/61904 [5:17:56<2:56:15,  1.44s/it]
 88%|████████▊ | 54561/61904 [5:17:57<3:00:41,  1.48s/it]
 88%|████████▊ | 54562/61904 [5:17:59<3:01:09,  1.48s/it]
 88%|████████▊ | 54563/61904 [5:18:00<3:00:02,  1.47s/it]
 88%|████████▊ | 54564/61904 [5:18:02<3:00:25,  1.47s/it]
 88%|████████▊ | 54565/61904 [5:18:03<3:01:07,  1.48s/it]
 88%|████████▊ | 54566/61904 [5:18:04<2:56:25,  1.44s/it]
 88%|████████▊ | 54567/61904 [5:18:06<2:57:41,  1.45s/it]
 88%|████████▊ | 54568/61904 [5:18:07<2:58:09,  1.46s/it]
 88%|████████▊ | 54569/61904 [5:18:09<2:55:08,  1.43s/it]
 88%|████████▊ | 54570/61904 [5:18:10<2:54:13,  1.43s/it]
 88%|████████▊ | 54571/61904 [5:18:12<2:51:41,  1.40s/it]
 88%|████████▊ | 54572/61904 [5:18:13<2:49:34,  1.39s/it]
 88%|████████▊ | 54573/61904 [5:18:14<2:49:32,  1.39s/it]
 88%|████████▊ | 54574/61904 [5:18:16<2:53:08,  1.42s/it]
 88%|████████▊ | 54575/61904 [5:18:17<2:48:05,  1.38s/it]
 88%|████████▊ | 54576/61904 [5:18:18<2:48:10,  1.38s/it]
 88%|████████▊ | 54577/61904 [5:18:20<2:46:38,  1.36s/it]
 88%|████████▊ | 54578/61904 [5:18:21<2:49:16,  1.39s/it]
 88%|████████▊ | 54579/61904 [5:18:23<2:51:34,  1.41s/it]
 88%|████████▊ | 54580/61904 [5:18:24<2:49:01,  1.38s/it]
                                                         
{'loss': 2.4102, 'learning_rate': 1.1186957085440165e-07, 'epoch': 14.11}

 88%|████████▊ | 54580/61904 [5:18:24<2:49:01,  1.38s/it]
 88%|████████▊ | 54581/61904 [5:18:25<2:47:00,  1.37s/it]
 88%|████████▊ | 54582/61904 [5:18:27<2:44:03,  1.34s/it]
 88%|████████▊ | 54583/61904 [5:18:28<2:44:46,  1.35s/it]
 88%|████████▊ | 54584/61904 [5:18:29<2:43:27,  1.34s/it]
 88%|████████▊ | 54585/61904 [5:18:31<2:40:33,  1.32s/it]
 88%|████████▊ | 54586/61904 [5:18:32<2:40:21,  1.31s/it]
 88%|████████▊ | 54587/61904 [5:18:33<2:44:33,  1.35s/it]
 88%|████████▊ | 54588/61904 [5:18:35<2:48:33,  1.38s/it]
 88%|████████▊ | 54589/61904 [5:18:36<2:49:38,  1.39s/it]
 88%|████████▊ | 54590/61904 [5:18:37<2:46:14,  1.36s/it]
 88%|████████▊ | 54591/61904 [5:18:39<2:43:58,  1.35s/it]
 88%|████████▊ | 54592/61904 [5:18:40<2:42:58,  1.34s/it]
 88%|████████▊ | 54593/61904 [5:18:42<2:47:09,  1.37s/it]
 88%|████████▊ | 54594/61904 [5:18:43<2:41:30,  1.33s/it]
 88%|████████▊ | 54595/61904 [5:18:44<2:45:33,  1.36s/it]
 88%|████████▊ | 54596/61904 [5:18:46<2:45:56,  1.36s/it]
 88%|████████▊ | 54597/61904 [5:18:47<2:43:00,  1.34s/it]
 88%|████████▊ | 54598/61904 [5:18:48<2:41:27,  1.33s/it]
 88%|████████▊ | 54599/61904 [5:18:49<2:42:05,  1.33s/it]
 88%|████████▊ | 54600/61904 [5:18:51<2:47:04,  1.37s/it]
                                                         
{'loss': 2.391, 'learning_rate': 1.1183715804485934e-07, 'epoch': 14.11}

 88%|████████▊ | 54600/61904 [5:18:51<2:47:04,  1.37s/it]
 88%|████████▊ | 54601/61904 [5:18:52<2:50:05,  1.40s/it]
 88%|████████▊ | 54602/61904 [5:18:54<2:45:23,  1.36s/it]
 88%|████████▊ | 54603/61904 [5:18:55<2:45:33,  1.36s/it]
 88%|████████▊ | 54604/61904 [5:18:56<2:46:15,  1.37s/it]
 88%|████████▊ | 54605/61904 [5:18:58<2:48:25,  1.38s/it]
 88%|████████▊ | 54606/61904 [5:18:59<2:53:10,  1.42s/it]
 88%|████████▊ | 54607/61904 [5:19:01<2:54:02,  1.43s/it]
 88%|████████▊ | 54608/61904 [5:19:02<2:50:05,  1.40s/it]
 88%|████████▊ | 54609/61904 [5:19:03<2:46:16,  1.37s/it]
 88%|████████▊ | 54610/61904 [5:19:05<2:41:25,  1.33s/it]
 88%|████████▊ | 54611/61904 [5:19:06<2:45:02,  1.36s/it]
 88%|████████▊ | 54612/61904 [5:19:07<2:47:14,  1.38s/it]
 88%|████████▊ | 54613/61904 [5:19:09<2:49:25,  1.39s/it]
 88%|████████▊ | 54614/61904 [5:19:10<2:45:08,  1.36s/it]
 88%|████████▊ | 54615/61904 [5:19:11<2:39:59,  1.32s/it]
 88%|████████▊ | 54616/61904 [5:19:13<2:40:28,  1.32s/it]
 88%|████████▊ | 54617/61904 [5:19:14<2:45:42,  1.36s/it]
 88%|████████▊ | 54618/61904 [5:19:16<2:43:37,  1.35s/it]
 88%|████████▊ | 54619/61904 [5:19:17<2:39:49,  1.32s/it]
 88%|████████▊ | 54620/61904 [5:19:18<2:37:43,  1.30s/it]
                                                         
{'loss': 2.4074, 'learning_rate': 1.11804745235317e-07, 'epoch': 14.12}

 88%|████████▊ | 54620/61904 [5:19:18<2:37:43,  1.30s/it]
 88%|████████▊ | 54621/61904 [5:19:20<2:45:11,  1.36s/it]
 88%|████████▊ | 54622/61904 [5:19:21<2:49:04,  1.39s/it]
 88%|████████▊ | 54623/61904 [5:19:22<2:49:08,  1.39s/it]
 88%|████████▊ | 54624/61904 [5:19:24<2:49:51,  1.40s/it]
 88%|████████▊ | 54625/61904 [5:19:25<2:50:33,  1.41s/it]
 88%|████████▊ | 54626/61904 [5:19:27<2:49:56,  1.40s/it]
 88%|████████▊ | 54627/61904 [5:19:28<2:55:40,  1.45s/it]
 88%|████████▊ | 54628/61904 [5:19:30<2:52:46,  1.42s/it]
 88%|████████▊ | 54629/61904 [5:19:31<2:53:29,  1.43s/it]
 88%|████████▊ | 54630/61904 [5:19:33<3:04:21,  1.52s/it]
 88%|████████▊ | 54631/61904 [5:19:34<2:57:25,  1.46s/it]
 88%|████████▊ | 54632/61904 [5:19:35<2:53:54,  1.43s/it]
 88%|████████▊ | 54633/61904 [5:19:37<2:50:25,  1.41s/it]
 88%|████████▊ | 54634/61904 [5:19:38<2:49:50,  1.40s/it]
 88%|████████▊ | 54635/61904 [5:19:40<2:51:34,  1.42s/it]
 88%|████████▊ | 54636/61904 [5:19:41<2:50:30,  1.41s/it]
 88%|████████▊ | 54637/61904 [5:19:42<2:44:13,  1.36s/it]
 88%|████████▊ | 54638/61904 [5:19:44<2:45:00,  1.36s/it]
 88%|████████▊ | 54639/61904 [5:19:45<2:48:09,  1.39s/it]
 88%|████████▊ | 54640/61904 [5:19:47<2:57:09,  1.46s/it]
                                                         
{'loss': 2.4133, 'learning_rate': 1.1177233242577467e-07, 'epoch': 14.12}

 88%|████████▊ | 54640/61904 [5:19:47<2:57:09,  1.46s/it]
 88%|████████▊ | 54641/61904 [5:19:48<2:51:38,  1.42s/it]
 88%|████████▊ | 54642/61904 [5:19:49<2:46:35,  1.38s/it]
 88%|████████▊ | 54643/61904 [5:19:51<2:49:58,  1.40s/it]
 88%|████████▊ | 54644/61904 [5:19:52<2:48:36,  1.39s/it]
 88%|████████▊ | 54645/61904 [5:19:53<2:44:01,  1.36s/it]
 88%|████████▊ | 54646/61904 [5:19:55<2:42:18,  1.34s/it]
 88%|████████▊ | 54647/61904 [5:19:56<2:44:34,  1.36s/it]
 88%|████████▊ | 54648/61904 [5:19:58<2:47:31,  1.39s/it]
 88%|████████▊ | 54649/61904 [5:19:59<2:47:23,  1.38s/it]
 88%|████████▊ | 54650/61904 [5:20:00<2:44:11,  1.36s/it]
 88%|████████▊ | 54651/61904 [5:20:02<2:42:42,  1.35s/it]
 88%|████████▊ | 54652/61904 [5:20:03<2:53:14,  1.43s/it]
 88%|████████▊ | 54653/61904 [5:20:05<2:50:10,  1.41s/it]
 88%|████████▊ | 54654/61904 [5:20:06<2:49:44,  1.40s/it]
 88%|████████▊ | 54655/61904 [5:20:07<2:51:35,  1.42s/it]
 88%|████████▊ | 54656/61904 [5:20:09<2:47:48,  1.39s/it]
 88%|████████▊ | 54657/61904 [5:20:10<2:43:00,  1.35s/it]
 88%|████████▊ | 54658/61904 [5:20:11<2:45:16,  1.37s/it]
 88%|████████▊ | 54659/61904 [5:20:13<2:43:08,  1.35s/it]
 88%|████████▊ | 54660/61904 [5:20:14<2:49:11,  1.40s/it]
                                                         
{'loss': 2.4479, 'learning_rate': 1.1173991961623233e-07, 'epoch': 14.13}

 88%|████████▊ | 54660/61904 [5:20:14<2:49:11,  1.40s/it]
 88%|████████▊ | 54661/61904 [5:20:15<2:45:38,  1.37s/it]
 88%|████████▊ | 54662/61904 [5:20:17<2:45:52,  1.37s/it]
 88%|████████▊ | 54663/61904 [5:20:18<2:43:27,  1.35s/it]
 88%|████████▊ | 54664/61904 [5:20:20<2:44:18,  1.36s/it]
 88%|████████▊ | 54665/61904 [5:20:21<2:42:10,  1.34s/it]
 88%|████████▊ | 54666/61904 [5:20:22<2:42:05,  1.34s/it]
 88%|████████▊ | 54667/61904 [5:20:24<2:41:02,  1.34s/it]
 88%|████████▊ | 54668/61904 [5:20:25<2:43:37,  1.36s/it]
 88%|████████▊ | 54669/61904 [5:20:26<2:47:02,  1.39s/it]
 88%|████████▊ | 54670/61904 [5:20:28<2:49:55,  1.41s/it]
 88%|████████▊ | 54671/61904 [5:20:29<2:56:34,  1.46s/it]
 88%|████████▊ | 54672/61904 [5:20:31<2:50:21,  1.41s/it]
 88%|████████▊ | 54673/61904 [5:20:32<2:49:08,  1.40s/it]
 88%|████████▊ | 54674/61904 [5:20:34<2:49:11,  1.40s/it]
 88%|████████▊ | 54675/61904 [5:20:35<2:52:38,  1.43s/it]
 88%|████████▊ | 54676/61904 [5:20:36<2:50:57,  1.42s/it]
 88%|████████▊ | 54677/61904 [5:20:38<2:49:26,  1.41s/it]
 88%|████████▊ | 54678/61904 [5:20:39<2:44:14,  1.36s/it]
 88%|████████▊ | 54679/61904 [5:20:40<2:42:32,  1.35s/it]
 88%|████████▊ | 54680/61904 [5:20:42<2:46:21,  1.38s/it]
                                                         
{'loss': 2.4476, 'learning_rate': 1.1170750680669002e-07, 'epoch': 14.13}

 88%|████████▊ | 54680/61904 [5:20:42<2:46:21,  1.38s/it]
 88%|████████▊ | 54681/61904 [5:20:43<2:45:26,  1.37s/it]
 88%|████████▊ | 54682/61904 [5:20:44<2:43:34,  1.36s/it]
 88%|████████▊ | 54683/61904 [5:20:46<2:41:21,  1.34s/it]
 88%|████████▊ | 54684/61904 [5:20:47<2:49:50,  1.41s/it]
 88%|████████▊ | 54685/61904 [5:20:49<2:44:46,  1.37s/it]
 88%|████████▊ | 54686/61904 [5:20:50<2:44:56,  1.37s/it]
 88%|████████▊ | 54687/61904 [5:20:52<2:51:17,  1.42s/it]
 88%|████████▊ | 54688/61904 [5:20:53<2:47:31,  1.39s/it]
 88%|████████▊ | 54689/61904 [5:20:54<2:46:25,  1.38s/it]
 88%|████████▊ | 54690/61904 [5:20:56<2:51:38,  1.43s/it]
 88%|████████▊ | 54691/61904 [5:20:57<2:45:07,  1.37s/it]
 88%|████████▊ | 54692/61904 [5:20:58<2:40:21,  1.33s/it]
 88%|████████▊ | 54693/61904 [5:21:00<2:40:33,  1.34s/it]
 88%|████████▊ | 54694/61904 [5:21:01<2:43:11,  1.36s/it]
 88%|████████▊ | 54695/61904 [5:21:02<2:41:08,  1.34s/it]
 88%|████████▊ | 54696/61904 [5:21:04<2:38:10,  1.32s/it]
 88%|████████▊ | 54697/61904 [5:21:05<2:38:29,  1.32s/it]
 88%|████████▊ | 54698/61904 [5:21:06<2:44:33,  1.37s/it]
 88%|████████▊ | 54699/61904 [5:21:08<2:47:41,  1.40s/it]
 88%|████████▊ | 54700/61904 [5:21:09<2:48:02,  1.40s/it]
                                                         
{'loss': 2.4295, 'learning_rate': 1.1167509399714768e-07, 'epoch': 14.14}

 88%|████████▊ | 54700/61904 [5:21:09<2:48:02,  1.40s/it]
 88%|████████▊ | 54701/61904 [5:21:11<2:47:15,  1.39s/it]
 88%|████████▊ | 54702/61904 [5:21:12<2:47:27,  1.40s/it]
 88%|████████▊ | 54703/61904 [5:21:13<2:49:35,  1.41s/it]
 88%|████████▊ | 54704/61904 [5:21:15<2:46:38,  1.39s/it]
 88%|████████▊ | 54705/61904 [5:21:16<2:46:42,  1.39s/it]
 88%|████████▊ | 54706/61904 [5:21:18<2:45:43,  1.38s/it]
 88%|████████▊ | 54707/61904 [5:21:19<2:45:36,  1.38s/it]
 88%|████████▊ | 54708/61904 [5:21:20<2:44:48,  1.37s/it]
 88%|████████▊ | 54709/61904 [5:21:22<2:46:37,  1.39s/it]
 88%|████████▊ | 54710/61904 [5:21:23<2:48:57,  1.41s/it]
 88%|████████▊ | 54711/61904 [5:21:24<2:43:38,  1.36s/it]
 88%|████████▊ | 54712/61904 [5:21:26<2:45:50,  1.38s/it]
 88%|████████▊ | 54713/61904 [5:21:27<2:44:10,  1.37s/it]
 88%|████████▊ | 54714/61904 [5:21:29<2:46:10,  1.39s/it]
 88%|████████▊ | 54715/61904 [5:21:30<2:44:24,  1.37s/it]
 88%|████████▊ | 54716/61904 [5:21:31<2:49:20,  1.41s/it]
 88%|████████▊ | 54717/61904 [5:21:33<2:47:20,  1.40s/it]
 88%|████████▊ | 54718/61904 [5:21:34<2:45:26,  1.38s/it]
 88%|████████▊ | 54719/61904 [5:21:35<2:40:42,  1.34s/it]
 88%|████████▊ | 54720/61904 [5:21:37<2:39:44,  1.33s/it]
                                                         
{'loss': 2.4715, 'learning_rate': 1.1164268118760534e-07, 'epoch': 14.14}

 88%|████████▊ | 54720/61904 [5:21:37<2:39:44,  1.33s/it]
 88%|████████▊ | 54721/61904 [5:21:38<2:38:51,  1.33s/it]
 88%|████████▊ | 54722/61904 [5:21:39<2:37:22,  1.31s/it]
 88%|████████▊ | 54723/61904 [5:21:41<2:38:45,  1.33s/it]
 88%|████████▊ | 54724/61904 [5:21:42<2:39:06,  1.33s/it]
 88%|████████▊ | 54725/61904 [5:21:43<2:37:53,  1.32s/it]
 88%|████████▊ | 54726/61904 [5:21:45<2:39:01,  1.33s/it]
 88%|████████▊ | 54727/61904 [5:21:46<2:38:54,  1.33s/it]
 88%|████████▊ | 54728/61904 [5:21:48<2:45:37,  1.38s/it]
 88%|████████▊ | 54729/61904 [5:21:49<2:47:18,  1.40s/it]
 88%|████████▊ | 54730/61904 [5:21:50<2:47:37,  1.40s/it]
 88%|████████▊ | 54731/61904 [5:21:52<2:45:17,  1.38s/it]
 88%|████████▊ | 54732/61904 [5:21:53<2:42:11,  1.36s/it]
 88%|████████▊ | 54733/61904 [5:21:54<2:40:38,  1.34s/it]
 88%|████████▊ | 54734/61904 [5:21:56<2:39:21,  1.33s/it]
 88%|████████▊ | 54735/61904 [5:21:57<2:42:28,  1.36s/it]
 88%|████████▊ | 54736/61904 [5:21:59<2:48:04,  1.41s/it]
 88%|████████▊ | 54737/61904 [5:22:00<2:53:54,  1.46s/it]
 88%|████████▊ | 54738/61904 [5:22:01<2:47:31,  1.40s/it]
 88%|████████▊ | 54739/61904 [5:22:03<2:46:56,  1.40s/it]
 88%|████████▊ | 54740/61904 [5:22:04<2:47:39,  1.40s/it]
                                                         
{'loss': 2.4425, 'learning_rate': 1.1161026837806302e-07, 'epoch': 14.15}

 88%|████████▊ | 54740/61904 [5:22:04<2:47:39,  1.40s/it]
 88%|████████▊ | 54741/61904 [5:22:06<2:53:35,  1.45s/it]
 88%|████████▊ | 54742/61904 [5:22:07<2:46:06,  1.39s/it]
 88%|████████▊ | 54743/61904 [5:22:09<2:48:21,  1.41s/it]
 88%|████████▊ | 54744/61904 [5:22:10<2:46:11,  1.39s/it]
 88%|████████▊ | 54745/61904 [5:22:11<2:47:12,  1.40s/it]
 88%|████████▊ | 54746/61904 [5:22:13<2:45:06,  1.38s/it]
 88%|████████▊ | 54747/61904 [5:22:14<2:44:04,  1.38s/it]
 88%|████████▊ | 54748/61904 [5:22:15<2:42:51,  1.37s/it]
 88%|████████▊ | 54749/61904 [5:22:17<2:46:28,  1.40s/it]
 88%|████████▊ | 54750/61904 [5:22:18<2:47:02,  1.40s/it]
 88%|████████▊ | 54751/61904 [5:22:20<2:47:04,  1.40s/it]
 88%|████████▊ | 54752/61904 [5:22:21<2:48:24,  1.41s/it]
 88%|████████▊ | 54753/61904 [5:22:22<2:49:38,  1.42s/it]
 88%|████████▊ | 54754/61904 [5:22:24<2:51:49,  1.44s/it]
 88%|████████▊ | 54755/61904 [5:22:25<2:50:22,  1.43s/it]
 88%|████████▊ | 54756/61904 [5:22:27<2:49:30,  1.42s/it]
 88%|████████▊ | 54757/61904 [5:22:28<2:51:15,  1.44s/it]
 88%|████████▊ | 54758/61904 [5:22:30<2:50:55,  1.44s/it]
 88%|████████▊ | 54759/61904 [5:22:31<2:52:09,  1.45s/it]
 88%|████████▊ | 54760/61904 [5:22:33<2:59:16,  1.51s/it]
                                                         
{'loss': 2.4664, 'learning_rate': 1.1157785556852069e-07, 'epoch': 14.15}

 88%|████████▊ | 54760/61904 [5:22:33<2:59:16,  1.51s/it]
 88%|████████▊ | 54761/61904 [5:22:34<3:00:58,  1.52s/it]
 88%|████████▊ | 54762/61904 [5:22:36<2:56:28,  1.48s/it]
 88%|████████▊ | 54763/61904 [5:22:37<2:52:45,  1.45s/it]
 88%|████████▊ | 54764/61904 [5:22:38<2:49:12,  1.42s/it]
 88%|████████▊ | 54765/61904 [5:22:40<2:52:29,  1.45s/it]
 88%|████████▊ | 54766/61904 [5:22:41<2:47:42,  1.41s/it]
 88%|████████▊ | 54767/61904 [5:22:43<2:47:36,  1.41s/it]
 88%|████████▊ | 54768/61904 [5:22:44<2:42:48,  1.37s/it]
 88%|████████▊ | 54769/61904 [5:22:45<2:43:32,  1.38s/it]
 88%|████████▊ | 54770/61904 [5:22:47<2:42:25,  1.37s/it]
 88%|████████▊ | 54771/61904 [5:22:48<2:43:30,  1.38s/it]
 88%|████████▊ | 54772/61904 [5:22:49<2:41:10,  1.36s/it]
 88%|████████▊ | 54773/61904 [5:22:51<2:38:57,  1.34s/it]
 88%|████████▊ | 54774/61904 [5:22:52<2:42:10,  1.36s/it]
 88%|████████▊ | 54775/61904 [5:22:54<2:42:32,  1.37s/it]
 88%|████████▊ | 54776/61904 [5:22:55<2:42:14,  1.37s/it]
 88%|████████▊ | 54777/61904 [5:22:56<2:39:19,  1.34s/it]
 88%|████████▊ | 54778/61904 [5:22:58<2:41:40,  1.36s/it]
 88%|████████▊ | 54779/61904 [5:22:59<2:36:28,  1.32s/it]
 88%|████████▊ | 54780/61904 [5:23:00<2:40:59,  1.36s/it]
                                                         
{'loss': 2.424, 'learning_rate': 1.1154544275897835e-07, 'epoch': 14.16}

 88%|████████▊ | 54780/61904 [5:23:00<2:40:59,  1.36s/it]
 88%|████████▊ | 54781/61904 [5:23:02<2:43:35,  1.38s/it]
 88%|████████▊ | 54782/61904 [5:23:03<2:43:38,  1.38s/it]
 88%|████████▊ | 54783/61904 [5:23:05<2:50:50,  1.44s/it]
 88%|████████▊ | 54784/61904 [5:23:06<2:42:36,  1.37s/it]
 88%|████████▊ | 54785/61904 [5:23:07<2:43:25,  1.38s/it]
 89%|████████▊ | 54786/61904 [5:23:09<2:43:11,  1.38s/it]
 89%|████████▊ | 54787/61904 [5:23:10<2:40:35,  1.35s/it]
 89%|████████▊ | 54788/61904 [5:23:11<2:39:07,  1.34s/it]
 89%|████████▊ | 54789/61904 [5:23:13<2:39:46,  1.35s/it]
 89%|████████▊ | 54790/61904 [5:23:14<2:47:45,  1.41s/it]
 89%|████████▊ | 54791/61904 [5:23:16<2:47:00,  1.41s/it]
 89%|████████▊ | 54792/61904 [5:23:17<2:40:30,  1.35s/it]
 89%|████████▊ | 54793/61904 [5:23:18<2:41:11,  1.36s/it]
 89%|████████▊ | 54794/61904 [5:23:19<2:38:41,  1.34s/it]
 89%|████████▊ | 54795/61904 [5:23:21<2:43:14,  1.38s/it]
 89%|████████▊ | 54796/61904 [5:23:22<2:42:25,  1.37s/it]
 89%|████████▊ | 54797/61904 [5:23:24<2:47:04,  1.41s/it]
 89%|████████▊ | 54798/61904 [5:23:25<2:46:25,  1.41s/it]
 89%|████████▊ | 54799/61904 [5:23:26<2:43:32,  1.38s/it]
 89%|████████▊ | 54800/61904 [5:23:28<2:46:51,  1.41s/it]
                                                         
{'loss': 2.4141, 'learning_rate': 1.1151302994943601e-07, 'epoch': 14.16}

 89%|████████▊ | 54800/61904 [5:23:28<2:46:51,  1.41s/it]
 89%|████████▊ | 54801/61904 [5:23:29<2:47:10,  1.41s/it]
 89%|████████▊ | 54802/61904 [5:23:31<2:43:34,  1.38s/it]
 89%|████████▊ | 54803/61904 [5:23:32<2:43:43,  1.38s/it]
 89%|████████▊ | 54804/61904 [5:23:33<2:42:45,  1.38s/it]
 89%|████████▊ | 54805/61904 [5:23:35<2:40:20,  1.36s/it]
 89%|████████▊ | 54806/61904 [5:23:36<2:41:18,  1.36s/it]
 89%|████████▊ | 54807/61904 [5:23:38<2:45:59,  1.40s/it]
 89%|████████▊ | 54808/61904 [5:23:39<2:42:40,  1.38s/it]
 89%|████████▊ | 54809/61904 [5:23:40<2:42:47,  1.38s/it]
 89%|████████▊ | 54810/61904 [5:23:42<2:39:22,  1.35s/it]
 89%|████████▊ | 54811/61904 [5:23:43<2:43:39,  1.38s/it]
 89%|████████▊ | 54812/61904 [5:23:45<2:46:46,  1.41s/it]
 89%|████████▊ | 54813/61904 [5:23:46<2:47:18,  1.42s/it]
 89%|████████▊ | 54814/61904 [5:23:47<2:43:21,  1.38s/it]
 89%|████████▊ | 54815/61904 [5:23:49<2:39:12,  1.35s/it]
 89%|████████▊ | 54816/61904 [5:23:50<2:34:32,  1.31s/it]
 89%|████████▊ | 54817/61904 [5:23:51<2:33:26,  1.30s/it]
 89%|████████▊ | 54818/61904 [5:23:52<2:33:55,  1.30s/it]
 89%|████████▊ | 54819/61904 [5:23:54<2:34:19,  1.31s/it]
 89%|████████▊ | 54820/61904 [5:23:55<2:37:23,  1.33s/it]
                                                         
{'loss': 2.4566, 'learning_rate': 1.1148061713989369e-07, 'epoch': 14.17}

 89%|████████▊ | 54820/61904 [5:23:55<2:37:23,  1.33s/it]
 89%|████████▊ | 54821/61904 [5:23:56<2:38:50,  1.35s/it]
 89%|████████▊ | 54822/61904 [5:23:58<2:41:04,  1.36s/it]
 89%|████████▊ | 54823/61904 [5:23:59<2:43:51,  1.39s/it]
 89%|████████▊ | 54824/61904 [5:24:01<2:43:57,  1.39s/it]
 89%|████████▊ | 54825/61904 [5:24:02<2:39:30,  1.35s/it]
 89%|████████▊ | 54826/61904 [5:24:03<2:39:41,  1.35s/it]
 89%|████████▊ | 54827/61904 [5:24:05<2:41:51,  1.37s/it]
 89%|████████▊ | 54828/61904 [5:24:06<2:42:29,  1.38s/it]
 89%|████████▊ | 54829/61904 [5:24:07<2:42:34,  1.38s/it]
 89%|████████▊ | 54830/61904 [5:24:09<2:40:21,  1.36s/it]
 89%|████████▊ | 54831/61904 [5:24:10<2:42:49,  1.38s/it]
 89%|████████▊ | 54832/61904 [5:24:12<2:41:54,  1.37s/it]
 89%|████████▊ | 54833/61904 [5:24:13<2:41:18,  1.37s/it]
 89%|████████▊ | 54834/61904 [5:24:14<2:40:31,  1.36s/it]
 89%|████████▊ | 54835/61904 [5:24:16<2:45:52,  1.41s/it]
 89%|████████▊ | 54836/61904 [5:24:17<2:44:05,  1.39s/it]
 89%|████████▊ | 54837/61904 [5:24:18<2:38:21,  1.34s/it]
 89%|████████▊ | 54838/61904 [5:24:20<2:41:25,  1.37s/it]
 89%|████████▊ | 54839/61904 [5:24:21<2:45:50,  1.41s/it]
 89%|████████▊ | 54840/61904 [5:24:23<2:42:49,  1.38s/it]
                                                         
{'loss': 2.4483, 'learning_rate': 1.1144820433035136e-07, 'epoch': 14.17}

 89%|████████▊ | 54840/61904 [5:24:23<2:42:49,  1.38s/it]
 89%|████████▊ | 54841/61904 [5:24:24<2:47:12,  1.42s/it]
 89%|████████▊ | 54842/61904 [5:24:26<2:44:47,  1.40s/it]
 89%|████████▊ | 54843/61904 [5:24:27<2:40:24,  1.36s/it]
 89%|████████▊ | 54844/61904 [5:24:28<2:39:17,  1.35s/it]
 89%|████████▊ | 54845/61904 [5:24:29<2:40:00,  1.36s/it]
 89%|████████▊ | 54846/61904 [5:24:31<2:42:10,  1.38s/it]
 89%|████████▊ | 54847/61904 [5:24:32<2:38:33,  1.35s/it]
 89%|████████▊ | 54848/61904 [5:24:34<2:39:20,  1.35s/it]
 89%|████████▊ | 54849/61904 [5:24:35<2:41:06,  1.37s/it]
 89%|████████▊ | 54850/61904 [5:24:36<2:38:12,  1.35s/it]
 89%|████████▊ | 54851/61904 [5:24:38<2:38:21,  1.35s/it]
 89%|████████▊ | 54852/61904 [5:24:39<2:36:59,  1.34s/it]
 89%|████████▊ | 54853/61904 [5:24:40<2:35:23,  1.32s/it]
 89%|████████▊ | 54854/61904 [5:24:42<2:39:06,  1.35s/it]
 89%|████████▊ | 54855/61904 [5:24:43<2:40:50,  1.37s/it]
 89%|████████▊ | 54856/61904 [5:24:44<2:43:04,  1.39s/it]
 89%|████████▊ | 54857/61904 [5:24:46<2:41:43,  1.38s/it]
 89%|████████▊ | 54858/61904 [5:24:47<2:41:18,  1.37s/it]
 89%|████████▊ | 54859/61904 [5:24:48<2:37:07,  1.34s/it]
 89%|████████▊ | 54860/61904 [5:24:50<2:53:38,  1.48s/it]
                                                         
{'loss': 2.4681, 'learning_rate': 1.1141579152080903e-07, 'epoch': 14.18}

 89%|████████▊ | 54860/61904 [5:24:50<2:53:38,  1.48s/it]
 89%|████████▊ | 54861/61904 [5:24:52<2:47:13,  1.42s/it]
 89%|████████▊ | 54862/61904 [5:24:53<2:51:26,  1.46s/it]
 89%|████████▊ | 54863/61904 [5:24:54<2:45:52,  1.41s/it]
 89%|████████▊ | 54864/61904 [5:24:56<2:43:22,  1.39s/it]
 89%|████████▊ | 54865/61904 [5:24:57<2:43:19,  1.39s/it]
 89%|████████▊ | 54866/61904 [5:24:58<2:40:57,  1.37s/it]
 89%|████████▊ | 54867/61904 [5:25:00<2:38:11,  1.35s/it]
 89%|████████▊ | 54868/61904 [5:25:01<2:41:08,  1.37s/it]
 89%|████████▊ | 54869/61904 [5:25:03<2:41:42,  1.38s/it]
 89%|████████▊ | 54870/61904 [5:25:04<2:43:39,  1.40s/it]
 89%|████████▊ | 54871/61904 [5:25:05<2:42:11,  1.38s/it]
 89%|████████▊ | 54872/61904 [5:25:07<2:45:32,  1.41s/it]
 89%|████████▊ | 54873/61904 [5:25:08<2:45:50,  1.42s/it]
 89%|████████▊ | 54874/61904 [5:25:10<2:43:42,  1.40s/it]
 89%|████████▊ | 54875/61904 [5:25:11<2:48:47,  1.44s/it]
 89%|████████▊ | 54876/61904 [5:25:13<2:44:55,  1.41s/it]
 89%|████████▊ | 54877/61904 [5:25:14<2:44:54,  1.41s/it]
 89%|████████▊ | 54878/61904 [5:25:15<2:48:40,  1.44s/it]
 89%|████████▊ | 54879/61904 [5:25:17<2:45:47,  1.42s/it]
 89%|████████▊ | 54880/61904 [5:25:18<2:44:49,  1.41s/it]
                                                         
{'loss': 2.4122, 'learning_rate': 1.1138337871126669e-07, 'epoch': 14.18}

 89%|████████▊ | 54880/61904 [5:25:18<2:44:49,  1.41s/it]
 89%|████████▊ | 54881/61904 [5:25:20<2:47:14,  1.43s/it]
 89%|████████▊ | 54882/61904 [5:25:21<2:43:13,  1.39s/it]
 89%|████████▊ | 54883/61904 [5:25:22<2:44:10,  1.40s/it]
 89%|████████▊ | 54884/61904 [5:25:24<2:39:08,  1.36s/it]
 89%|████████▊ | 54885/61904 [5:25:25<2:44:11,  1.40s/it]
 89%|████████▊ | 54886/61904 [5:25:27<2:50:33,  1.46s/it]
 89%|████████▊ | 54887/61904 [5:25:28<2:45:35,  1.42s/it]
 89%|████████▊ | 54888/61904 [5:25:29<2:45:37,  1.42s/it]
 89%|████████▊ | 54889/61904 [5:25:31<2:39:30,  1.36s/it]
 89%|████████▊ | 54890/61904 [5:25:32<2:44:05,  1.40s/it]
 89%|████████▊ | 54891/61904 [5:25:34<2:46:29,  1.42s/it]
 89%|████████▊ | 54892/61904 [5:25:35<2:43:49,  1.40s/it]
 89%|████████▊ | 54893/61904 [5:25:36<2:44:38,  1.41s/it]
 89%|████████▊ | 54894/61904 [5:25:38<2:41:54,  1.39s/it]
 89%|████████▊ | 54895/61904 [5:25:39<2:45:30,  1.42s/it]
 89%|████████▊ | 54896/61904 [5:25:41<2:49:50,  1.45s/it]
 89%|████████▊ | 54897/61904 [5:25:42<2:45:40,  1.42s/it]
 89%|████████▊ | 54898/61904 [5:25:44<2:44:04,  1.41s/it]
 89%|████████▊ | 54899/61904 [5:25:45<2:42:58,  1.40s/it]
 89%|████████▊ | 54900/61904 [5:25:46<2:39:16,  1.36s/it]
                                                         
{'loss': 2.4219, 'learning_rate': 1.1135096590172436e-07, 'epoch': 14.19}

 89%|████████▊ | 54900/61904 [5:25:46<2:39:16,  1.36s/it]
 89%|████████▊ | 54901/61904 [5:25:48<2:41:59,  1.39s/it]
 89%|████████▊ | 54902/61904 [5:25:49<2:47:47,  1.44s/it]
 89%|████████▊ | 54903/61904 [5:25:51<2:50:07,  1.46s/it]
 89%|████████▊ | 54904/61904 [5:25:52<2:44:08,  1.41s/it]
 89%|████████▊ | 54905/61904 [5:25:53<2:45:37,  1.42s/it]
 89%|████████▊ | 54906/61904 [5:25:55<2:43:48,  1.40s/it]
 89%|████████▊ | 54907/61904 [5:25:56<2:40:43,  1.38s/it]
 89%|████████▊ | 54908/61904 [5:25:57<2:39:10,  1.37s/it]
 89%|████████▊ | 54909/61904 [5:25:59<2:40:04,  1.37s/it]
 89%|████████▊ | 54910/61904 [5:26:00<2:41:36,  1.39s/it]
 89%|████████▊ | 54911/61904 [5:26:02<2:40:55,  1.38s/it]
 89%|████████▊ | 54912/61904 [5:26:03<2:40:17,  1.38s/it]
 89%|████████▊ | 54913/61904 [5:26:04<2:43:03,  1.40s/it]
 89%|████████▊ | 54914/61904 [5:26:06<2:43:11,  1.40s/it]
 89%|████████▊ | 54915/61904 [5:26:07<2:40:00,  1.37s/it]
 89%|████████▊ | 54916/61904 [5:26:09<2:43:12,  1.40s/it]
 89%|████████▊ | 54917/61904 [5:26:10<2:42:13,  1.39s/it]
 89%|████████▊ | 54918/61904 [5:26:11<2:45:26,  1.42s/it]
 89%|████████▊ | 54919/61904 [5:26:13<2:42:09,  1.39s/it]
 89%|████████▊ | 54920/61904 [5:26:14<2:44:31,  1.41s/it]
                                                         
{'loss': 2.398, 'learning_rate': 1.1131855309218204e-07, 'epoch': 14.19}

 89%|████████▊ | 54920/61904 [5:26:14<2:44:31,  1.41s/it]
 89%|████████▊ | 54921/61904 [5:26:16<2:39:48,  1.37s/it]
 89%|████████▊ | 54922/61904 [5:26:17<2:36:38,  1.35s/it]
 89%|████████▊ | 54923/61904 [5:26:18<2:34:18,  1.33s/it]
 89%|████████▊ | 54924/61904 [5:26:20<2:37:13,  1.35s/it]
 89%|████████▊ | 54925/61904 [5:26:21<2:40:38,  1.38s/it]
 89%|████████▊ | 54926/61904 [5:26:22<2:43:11,  1.40s/it]
 89%|████████▊ | 54927/61904 [5:26:24<2:46:02,  1.43s/it]
 89%|████████▊ | 54928/61904 [5:26:25<2:45:40,  1.42s/it]
 89%|████████▊ | 54929/61904 [5:26:27<2:45:31,  1.42s/it]
 89%|████████▊ | 54930/61904 [5:26:28<2:42:11,  1.40s/it]
 89%|████████▊ | 54931/61904 [5:26:30<2:48:35,  1.45s/it]
 89%|████████▊ | 54932/61904 [5:26:31<2:46:52,  1.44s/it]
 89%|████████▊ | 54933/61904 [5:26:32<2:38:45,  1.37s/it]
 89%|████████▊ | 54934/61904 [5:26:34<2:40:01,  1.38s/it]
 89%|████████▊ | 54935/61904 [5:26:35<2:40:37,  1.38s/it]
 89%|████████▊ | 54936/61904 [5:26:37<2:44:36,  1.42s/it]
 89%|████████▊ | 54937/61904 [5:26:38<2:44:22,  1.42s/it]
 89%|████████▊ | 54938/61904 [5:26:39<2:38:29,  1.37s/it]
 89%|████████▊ | 54939/61904 [5:26:41<2:42:20,  1.40s/it]
 89%|████████▉ | 54940/61904 [5:26:42<2:40:12,  1.38s/it]
                                                         
{'loss': 2.4346, 'learning_rate': 1.112861402826397e-07, 'epoch': 14.2}

 89%|████████▉ | 54940/61904 [5:26:42<2:40:12,  1.38s/it]
 89%|████████▉ | 54941/61904 [5:26:43<2:41:59,  1.40s/it]
 89%|████████▉ | 54942/61904 [5:26:45<2:40:27,  1.38s/it]
 89%|████████▉ | 54943/61904 [5:26:46<2:34:35,  1.33s/it]
 89%|████████▉ | 54944/61904 [5:26:47<2:35:07,  1.34s/it]
 89%|████████▉ | 54945/61904 [5:26:49<2:42:00,  1.40s/it]
 89%|████████▉ | 54946/61904 [5:26:50<2:44:41,  1.42s/it]
 89%|████████▉ | 54947/61904 [5:26:52<2:40:54,  1.39s/it]
 89%|████████▉ | 54948/61904 [5:26:53<2:36:52,  1.35s/it]
 89%|████████▉ | 54949/61904 [5:26:54<2:38:29,  1.37s/it]
 89%|████████▉ | 54950/61904 [5:26:56<2:38:14,  1.37s/it]
 89%|████████▉ | 54951/61904 [5:26:57<2:37:10,  1.36s/it]
 89%|████████▉ | 54952/61904 [5:26:58<2:32:43,  1.32s/it]
 89%|████████▉ | 54953/61904 [5:27:00<2:44:42,  1.42s/it]
 89%|████████▉ | 54954/61904 [5:27:01<2:41:33,  1.39s/it]
 89%|████████▉ | 54955/61904 [5:27:03<2:43:19,  1.41s/it]
 89%|████████▉ | 54956/61904 [5:27:04<2:43:52,  1.42s/it]
 89%|████████▉ | 54957/61904 [5:27:05<2:36:24,  1.35s/it]
 89%|████████▉ | 54958/61904 [5:27:07<2:43:54,  1.42s/it]
 89%|████████▉ | 54959/61904 [5:27:08<2:44:36,  1.42s/it]
 89%|████████▉ | 54960/61904 [5:27:10<2:44:06,  1.42s/it]
                                                         
{'loss': 2.477, 'learning_rate': 1.1125372747309736e-07, 'epoch': 14.2}

 89%|████████▉ | 54960/61904 [5:27:10<2:44:06,  1.42s/it]
 89%|████████▉ | 54961/61904 [5:27:11<2:45:55,  1.43s/it]
 89%|████████▉ | 54962/61904 [5:27:13<2:41:01,  1.39s/it]
 89%|████████▉ | 54963/61904 [5:27:14<2:38:36,  1.37s/it]
 89%|████████▉ | 54964/61904 [5:27:15<2:36:18,  1.35s/it]
 89%|████████▉ | 54965/61904 [5:27:17<2:35:09,  1.34s/it]
 89%|████████▉ | 54966/61904 [5:27:18<2:33:05,  1.32s/it]
 89%|████████▉ | 54967/61904 [5:27:19<2:31:38,  1.31s/it]
 89%|████████▉ | 54968/61904 [5:27:20<2:33:45,  1.33s/it]
 89%|████████▉ | 54969/61904 [5:27:22<2:41:57,  1.40s/it]
 89%|████████▉ | 54970/61904 [5:27:24<2:49:20,  1.47s/it]
 89%|████████▉ | 54971/61904 [5:27:25<2:46:21,  1.44s/it]
 89%|████████▉ | 54972/61904 [5:27:26<2:43:35,  1.42s/it]
 89%|████████▉ | 54973/61904 [5:27:28<2:41:42,  1.40s/it]
 89%|████████▉ | 54974/61904 [5:27:29<2:38:36,  1.37s/it]
 89%|████████▉ | 54975/61904 [5:27:31<2:42:38,  1.41s/it]
 89%|████████▉ | 54976/61904 [5:27:32<2:42:07,  1.40s/it]
 89%|████████▉ | 54977/61904 [5:27:33<2:42:07,  1.40s/it]
 89%|████████▉ | 54978/61904 [5:27:35<2:44:47,  1.43s/it]
 89%|████████▉ | 54979/61904 [5:27:36<2:46:02,  1.44s/it]
 89%|████████▉ | 54980/61904 [5:27:38<2:40:50,  1.39s/it]
                                                         
{'loss': 2.412, 'learning_rate': 1.1122131466355504e-07, 'epoch': 14.21}

 89%|████████▉ | 54980/61904 [5:27:38<2:40:50,  1.39s/it]
 89%|████████▉ | 54981/61904 [5:27:39<2:38:35,  1.37s/it]
 89%|████████▉ | 54982/61904 [5:27:40<2:44:46,  1.43s/it]
 89%|████████▉ | 54983/61904 [5:27:42<2:40:08,  1.39s/it]
 89%|████████▉ | 54984/61904 [5:27:43<2:36:51,  1.36s/it]
 89%|████████▉ | 54985/61904 [5:27:45<2:42:32,  1.41s/it]
 89%|████████▉ | 54986/61904 [5:27:46<2:40:11,  1.39s/it]
 89%|████████▉ | 54987/61904 [5:27:47<2:46:28,  1.44s/it]
 89%|████████▉ | 54988/61904 [5:27:49<2:47:06,  1.45s/it]
 89%|████████▉ | 54989/61904 [5:27:50<2:46:36,  1.45s/it]
 89%|████████▉ | 54990/61904 [5:27:52<2:44:48,  1.43s/it]
 89%|████████▉ | 54991/61904 [5:27:53<2:54:20,  1.51s/it]
 89%|████████▉ | 54992/61904 [5:27:55<2:54:22,  1.51s/it]
 89%|████████▉ | 54993/61904 [5:27:56<2:49:08,  1.47s/it]
 89%|████████▉ | 54994/61904 [5:27:58<2:47:05,  1.45s/it]
 89%|████████▉ | 54995/61904 [5:27:59<2:45:55,  1.44s/it]
 89%|████████▉ | 54996/61904 [5:28:00<2:41:25,  1.40s/it]
 89%|████████▉ | 54997/61904 [5:28:02<2:35:41,  1.35s/it]
 89%|████████▉ | 54998/61904 [5:28:03<2:36:11,  1.36s/it]
 89%|████████▉ | 54999/61904 [5:28:05<2:38:19,  1.38s/it]
 89%|████████▉ | 55000/61904 [5:28:06<2:40:17,  1.39s/it]
                                                         
{'loss': 2.4304, 'learning_rate': 1.1118890185401271e-07, 'epoch': 14.22}

 89%|████████▉ | 55000/61904 [5:28:06<2:40:17,  1.39s/it]
 89%|████████▉ | 55001/61904 [5:28:07<2:34:47,  1.35s/it]
 89%|████████▉ | 55002/61904 [5:28:09<2:35:43,  1.35s/it]
 89%|████████▉ | 55003/61904 [5:28:10<2:33:17,  1.33s/it]
 89%|████████▉ | 55004/61904 [5:28:11<2:35:00,  1.35s/it]
 89%|████████▉ | 55005/61904 [5:28:13<2:45:14,  1.44s/it]
 89%|████████▉ | 55006/61904 [5:28:14<2:43:33,  1.42s/it]
 89%|████████▉ | 55007/61904 [5:28:16<2:38:14,  1.38s/it]
 89%|████████▉ | 55008/61904 [5:28:17<2:40:26,  1.40s/it]
 89%|████████▉ | 55009/61904 [5:28:18<2:38:16,  1.38s/it]
 89%|████████▉ | 55010/61904 [5:28:20<2:37:47,  1.37s/it]
 89%|████████▉ | 55011/61904 [5:28:21<2:35:30,  1.35s/it]
 89%|████████▉ | 55012/61904 [5:28:22<2:36:00,  1.36s/it]
 89%|████████▉ | 55013/61904 [5:28:24<2:41:28,  1.41s/it]
 89%|████████▉ | 55014/61904 [5:28:25<2:37:06,  1.37s/it]
 89%|████████▉ | 55015/61904 [5:28:26<2:36:04,  1.36s/it]
 89%|████████▉ | 55016/61904 [5:28:28<2:35:13,  1.35s/it]
 89%|████████▉ | 55017/61904 [5:28:29<2:42:11,  1.41s/it]
 89%|████████▉ | 55018/61904 [5:28:31<2:45:09,  1.44s/it]
 89%|████████▉ | 55019/61904 [5:28:32<2:40:04,  1.39s/it]
 89%|████████▉ | 55020/61904 [5:28:34<2:38:07,  1.38s/it]
                                                         
{'loss': 2.4396, 'learning_rate': 1.1115648904447037e-07, 'epoch': 14.22}

 89%|████████▉ | 55020/61904 [5:28:34<2:38:07,  1.38s/it]
 89%|████████▉ | 55021/61904 [5:28:35<2:42:53,  1.42s/it]
 89%|████████▉ | 55022/61904 [5:28:36<2:40:56,  1.40s/it]
 89%|████████▉ | 55023/61904 [5:28:38<2:37:59,  1.38s/it]
 89%|████████▉ | 55024/61904 [5:28:39<2:36:54,  1.37s/it]
 89%|████████▉ | 55025/61904 [5:28:40<2:34:41,  1.35s/it]
 89%|████████▉ | 55026/61904 [5:28:42<2:40:17,  1.40s/it]
 89%|████████▉ | 55027/61904 [5:28:43<2:41:46,  1.41s/it]
 89%|████████▉ | 55028/61904 [5:28:45<2:50:42,  1.49s/it]
 89%|████████▉ | 55029/61904 [5:28:46<2:47:45,  1.46s/it]
 89%|████████▉ | 55030/61904 [5:28:48<2:47:18,  1.46s/it]
 89%|████████▉ | 55031/61904 [5:28:49<2:45:17,  1.44s/it]
 89%|████████▉ | 55032/61904 [5:28:51<2:40:12,  1.40s/it]
 89%|████████▉ | 55033/61904 [5:28:52<2:39:32,  1.39s/it]
 89%|████████▉ | 55034/61904 [5:28:53<2:43:49,  1.43s/it]
 89%|████████▉ | 55035/61904 [5:28:55<2:39:32,  1.39s/it]
 89%|████████▉ | 55036/61904 [5:28:56<2:39:30,  1.39s/it]
 89%|████████▉ | 55037/61904 [5:28:57<2:37:59,  1.38s/it]
 89%|████████▉ | 55038/61904 [5:28:59<2:36:45,  1.37s/it]
 89%|████████▉ | 55039/61904 [5:29:00<2:40:14,  1.40s/it]
 89%|████████▉ | 55040/61904 [5:29:02<2:37:48,  1.38s/it]
                                                         
{'loss': 2.4407, 'learning_rate': 1.1112407623492805e-07, 'epoch': 14.23}

 89%|████████▉ | 55040/61904 [5:29:02<2:37:48,  1.38s/it]
 89%|████████▉ | 55041/61904 [5:29:03<2:33:47,  1.34s/it]
 89%|████████▉ | 55042/61904 [5:29:04<2:32:28,  1.33s/it]
 89%|████████▉ | 55043/61904 [5:29:06<2:35:27,  1.36s/it]
 89%|████████▉ | 55044/61904 [5:29:07<2:40:45,  1.41s/it]
 89%|████████▉ | 55045/61904 [5:29:09<2:42:06,  1.42s/it]
 89%|████████▉ | 55046/61904 [5:29:10<2:40:12,  1.40s/it]
 89%|████████▉ | 55047/61904 [5:29:11<2:34:16,  1.35s/it]
 89%|████████▉ | 55048/61904 [5:29:13<2:38:30,  1.39s/it]
 89%|████████▉ | 55049/61904 [5:29:14<2:41:15,  1.41s/it]
 89%|████████▉ | 55050/61904 [5:29:16<2:45:10,  1.45s/it]
 89%|████████▉ | 55051/61904 [5:29:17<2:38:36,  1.39s/it]
 89%|████████▉ | 55052/61904 [5:29:18<2:36:44,  1.37s/it]
 89%|████████▉ | 55053/61904 [5:29:20<2:40:16,  1.40s/it]
 89%|████████▉ | 55054/61904 [5:29:21<2:39:37,  1.40s/it]
 89%|████████▉ | 55055/61904 [5:29:22<2:39:26,  1.40s/it]
 89%|████████▉ | 55056/61904 [5:29:24<2:39:33,  1.40s/it]
 89%|████████▉ | 55057/61904 [5:29:25<2:36:20,  1.37s/it]
 89%|████████▉ | 55058/61904 [5:29:27<2:39:12,  1.40s/it]
 89%|████████▉ | 55059/61904 [5:29:28<2:34:32,  1.35s/it]
 89%|████████▉ | 55060/61904 [5:29:29<2:33:11,  1.34s/it]
                                                         
{'loss': 2.3734, 'learning_rate': 1.1109166342538571e-07, 'epoch': 14.23}

 89%|████████▉ | 55060/61904 [5:29:29<2:33:11,  1.34s/it]
 89%|████████▉ | 55061/61904 [5:29:31<2:31:22,  1.33s/it]
 89%|████████▉ | 55062/61904 [5:29:32<2:30:47,  1.32s/it]
 89%|████████▉ | 55063/61904 [5:29:33<2:32:36,  1.34s/it]
 89%|████████▉ | 55064/61904 [5:29:35<2:34:05,  1.35s/it]
 89%|████████▉ | 55065/61904 [5:29:36<2:34:21,  1.35s/it]
 89%|████████▉ | 55066/61904 [5:29:37<2:35:04,  1.36s/it]
 89%|████████▉ | 55067/61904 [5:29:39<2:32:17,  1.34s/it]
 89%|████████▉ | 55068/61904 [5:29:40<2:33:02,  1.34s/it]
 89%|████████▉ | 55069/61904 [5:29:41<2:32:39,  1.34s/it]
 89%|████████▉ | 55070/61904 [5:29:43<2:33:41,  1.35s/it]
 89%|████████▉ | 55071/61904 [5:29:44<2:32:37,  1.34s/it]
 89%|████████▉ | 55072/61904 [5:29:45<2:30:35,  1.32s/it]
 89%|████████▉ | 55073/61904 [5:29:47<2:40:18,  1.41s/it]
 89%|████████▉ | 55074/61904 [5:29:48<2:39:12,  1.40s/it]
 89%|████████▉ | 55075/61904 [5:29:50<2:38:42,  1.39s/it]
 89%|████████▉ | 55076/61904 [5:29:51<2:38:39,  1.39s/it]
 89%|████████▉ | 55077/61904 [5:29:52<2:36:26,  1.37s/it]
 89%|████████▉ | 55078/61904 [5:29:54<2:35:30,  1.37s/it]
 89%|████████▉ | 55079/61904 [5:29:55<2:33:13,  1.35s/it]
 89%|████████▉ | 55080/61904 [5:29:57<2:42:19,  1.43s/it]
                                                         
{'loss': 2.4121, 'learning_rate': 1.1105925061584339e-07, 'epoch': 14.24}

 89%|████████▉ | 55080/61904 [5:29:57<2:42:19,  1.43s/it]
 89%|████████▉ | 55081/61904 [5:29:58<2:42:59,  1.43s/it]
 89%|████████▉ | 55082/61904 [5:29:59<2:36:58,  1.38s/it]
 89%|████████▉ | 55083/61904 [5:30:01<2:39:14,  1.40s/it]
 89%|████████▉ | 55084/61904 [5:30:02<2:39:04,  1.40s/it]
 89%|████████▉ | 55085/61904 [5:30:04<2:40:25,  1.41s/it]
 89%|████████▉ | 55086/61904 [5:30:05<2:43:32,  1.44s/it]
 89%|████████▉ | 55087/61904 [5:30:07<2:44:45,  1.45s/it]
 89%|████████▉ | 55088/61904 [5:30:08<2:47:03,  1.47s/it]
 89%|████████▉ | 55089/61904 [5:30:10<2:47:04,  1.47s/it]
 89%|████████▉ | 55090/61904 [5:30:11<2:39:52,  1.41s/it]
 89%|████████▉ | 55091/61904 [5:30:12<2:38:55,  1.40s/it]
 89%|████████▉ | 55092/61904 [5:30:14<2:38:34,  1.40s/it]
 89%|████████▉ | 55093/61904 [5:30:15<2:43:02,  1.44s/it]
 89%|████████▉ | 55094/61904 [5:30:17<2:45:13,  1.46s/it]
 89%|████████▉ | 55095/61904 [5:30:18<2:39:02,  1.40s/it]
 89%|████████▉ | 55096/61904 [5:30:19<2:40:46,  1.42s/it]
 89%|████████▉ | 55097/61904 [5:30:21<2:36:24,  1.38s/it]
 89%|████████▉ | 55098/61904 [5:30:22<2:36:51,  1.38s/it]
 89%|████████▉ | 55099/61904 [5:30:23<2:36:50,  1.38s/it]
 89%|████████▉ | 55100/61904 [5:30:25<2:34:31,  1.36s/it]
                                                         
{'loss': 2.4242, 'learning_rate': 1.1102683780630105e-07, 'epoch': 14.24}

 89%|████████▉ | 55100/61904 [5:30:25<2:34:31,  1.36s/it]
 89%|████████▉ | 55101/61904 [5:30:26<2:36:13,  1.38s/it]
 89%|████████▉ | 55102/61904 [5:30:28<2:36:52,  1.38s/it]
 89%|████████▉ | 55103/61904 [5:30:29<2:40:58,  1.42s/it]
 89%|████████▉ | 55104/61904 [5:30:30<2:39:02,  1.40s/it]
 89%|████████▉ | 55105/61904 [5:30:32<2:45:45,  1.46s/it]
 89%|████████▉ | 55106/61904 [5:30:33<2:44:38,  1.45s/it]
 89%|████████▉ | 55107/61904 [5:30:35<2:47:13,  1.48s/it]
 89%|████████▉ | 55108/61904 [5:30:36<2:45:24,  1.46s/it]
 89%|████████▉ | 55109/61904 [5:30:38<2:48:32,  1.49s/it]
 89%|████████▉ | 55110/61904 [5:30:39<2:42:17,  1.43s/it]
 89%|████████▉ | 55111/61904 [5:30:41<2:36:48,  1.38s/it]
 89%|████████▉ | 55112/61904 [5:30:42<2:35:10,  1.37s/it]
 89%|████████▉ | 55113/61904 [5:30:43<2:36:14,  1.38s/it]
 89%|████████▉ | 55114/61904 [5:30:45<2:34:38,  1.37s/it]
 89%|████████▉ | 55115/61904 [5:30:46<2:37:43,  1.39s/it]
 89%|████████▉ | 55116/61904 [5:30:48<2:41:12,  1.42s/it]
 89%|████████▉ | 55117/61904 [5:30:49<2:35:56,  1.38s/it]
 89%|████████▉ | 55118/61904 [5:30:50<2:37:44,  1.39s/it]
 89%|████████▉ | 55119/61904 [5:30:52<2:39:21,  1.41s/it]
 89%|████████▉ | 55120/61904 [5:30:53<2:40:12,  1.42s/it]
                                                         
{'loss': 2.446, 'learning_rate': 1.1099442499675872e-07, 'epoch': 14.25}

 89%|████████▉ | 55120/61904 [5:30:53<2:40:12,  1.42s/it]
 89%|████████▉ | 55121/61904 [5:30:55<2:40:17,  1.42s/it]
 89%|████████▉ | 55122/61904 [5:30:56<2:37:00,  1.39s/it]
 89%|████████▉ | 55123/61904 [5:30:57<2:31:08,  1.34s/it]
 89%|████████▉ | 55124/61904 [5:30:59<2:35:00,  1.37s/it]
 89%|████████▉ | 55125/61904 [5:31:00<2:40:11,  1.42s/it]
 89%|████████▉ | 55126/61904 [5:31:01<2:36:27,  1.39s/it]
 89%|████████▉ | 55127/61904 [5:31:03<2:34:03,  1.36s/it]
 89%|████████▉ | 55128/61904 [5:31:04<2:32:07,  1.35s/it]
 89%|████████▉ | 55129/61904 [5:31:05<2:31:29,  1.34s/it]
 89%|████████▉ | 55130/61904 [5:31:07<2:31:31,  1.34s/it]
 89%|████████▉ | 55131/61904 [5:31:08<2:34:54,  1.37s/it]
 89%|████████▉ | 55132/61904 [5:31:10<2:43:05,  1.45s/it]
 89%|████████▉ | 55133/61904 [5:31:11<2:38:27,  1.40s/it]
 89%|████████▉ | 55134/61904 [5:31:13<2:41:36,  1.43s/it]
 89%|████████▉ | 55135/61904 [5:31:14<2:38:59,  1.41s/it]
 89%|████████▉ | 55136/61904 [5:31:15<2:38:16,  1.40s/it]
 89%|████████▉ | 55137/61904 [5:31:17<2:32:27,  1.35s/it]
 89%|████████▉ | 55138/61904 [5:31:18<2:32:34,  1.35s/it]
 89%|████████▉ | 55139/61904 [5:31:19<2:33:26,  1.36s/it]
 89%|████████▉ | 55140/61904 [5:31:21<2:35:05,  1.38s/it]
                                                         
{'loss': 2.3918, 'learning_rate': 1.1096201218721639e-07, 'epoch': 14.25}

 89%|████████▉ | 55140/61904 [5:31:21<2:35:05,  1.38s/it]
 89%|████████▉ | 55141/61904 [5:31:22<2:37:55,  1.40s/it]
 89%|████████▉ | 55142/61904 [5:31:23<2:34:38,  1.37s/it]
 89%|████████▉ | 55143/61904 [5:31:25<2:38:01,  1.40s/it]
 89%|████████▉ | 55144/61904 [5:31:26<2:39:54,  1.42s/it]
 89%|████████▉ | 55145/61904 [5:31:28<2:36:50,  1.39s/it]
 89%|████████▉ | 55146/61904 [5:31:29<2:33:02,  1.36s/it]
 89%|████████▉ | 55147/61904 [5:31:30<2:33:31,  1.36s/it]
 89%|████████▉ | 55148/61904 [5:31:32<2:32:44,  1.36s/it]
 89%|████████▉ | 55149/61904 [5:31:33<2:29:50,  1.33s/it]
 89%|████████▉ | 55150/61904 [5:31:34<2:30:20,  1.34s/it]
 89%|████████▉ | 55151/61904 [5:31:36<2:30:06,  1.33s/it]
 89%|████████▉ | 55152/61904 [5:31:37<2:31:58,  1.35s/it]
 89%|████████▉ | 55153/61904 [5:31:38<2:33:14,  1.36s/it]
 89%|████████▉ | 55154/61904 [5:31:40<2:32:56,  1.36s/it]
 89%|████████▉ | 55155/61904 [5:31:41<2:34:56,  1.38s/it]
 89%|████████▉ | 55156/61904 [5:31:43<2:34:01,  1.37s/it]
 89%|████████▉ | 55157/61904 [5:31:44<2:38:45,  1.41s/it]
 89%|████████▉ | 55158/61904 [5:31:45<2:36:29,  1.39s/it]
 89%|████████▉ | 55159/61904 [5:31:47<2:41:29,  1.44s/it]
 89%|████████▉ | 55160/61904 [5:31:48<2:37:48,  1.40s/it]
                                                         
{'loss': 2.4142, 'learning_rate': 1.1092959937767406e-07, 'epoch': 14.26}

 89%|████████▉ | 55160/61904 [5:31:48<2:37:48,  1.40s/it]
 89%|████████▉ | 55161/61904 [5:31:50<2:40:08,  1.42s/it]
 89%|████████▉ | 55162/61904 [5:31:51<2:37:43,  1.40s/it]
 89%|████████▉ | 55163/61904 [5:31:52<2:35:34,  1.38s/it]
 89%|████████▉ | 55164/61904 [5:31:54<2:35:40,  1.39s/it]
 89%|████████▉ | 55165/61904 [5:31:55<2:33:54,  1.37s/it]
 89%|████████▉ | 55166/61904 [5:31:57<2:34:04,  1.37s/it]
 89%|████████▉ | 55167/61904 [5:31:58<2:35:49,  1.39s/it]
 89%|████████▉ | 55168/61904 [5:31:59<2:39:53,  1.42s/it]
 89%|████████▉ | 55169/61904 [5:32:01<2:33:19,  1.37s/it]
 89%|████████▉ | 55170/61904 [5:32:02<2:34:23,  1.38s/it]
 89%|████████▉ | 55171/61904 [5:32:04<2:37:30,  1.40s/it]
 89%|████████▉ | 55172/61904 [5:32:05<2:39:06,  1.42s/it]
 89%|████████▉ | 55173/61904 [5:32:06<2:38:28,  1.41s/it]
 89%|████████▉ | 55174/61904 [5:32:08<2:34:44,  1.38s/it]
 89%|████████▉ | 55175/61904 [5:32:09<2:37:23,  1.40s/it]
 89%|████████▉ | 55176/61904 [5:32:10<2:32:57,  1.36s/it]
 89%|████████▉ | 55177/61904 [5:32:12<2:29:23,  1.33s/it]
 89%|████████▉ | 55178/61904 [5:32:13<2:33:24,  1.37s/it]
 89%|████████▉ | 55179/61904 [5:32:15<2:33:55,  1.37s/it]
 89%|████████▉ | 55180/61904 [5:32:16<2:34:33,  1.38s/it]
                                                         
{'loss': 2.4401, 'learning_rate': 1.1089718656813172e-07, 'epoch': 14.26}

 89%|████████▉ | 55180/61904 [5:32:16<2:34:33,  1.38s/it]
 89%|████████▉ | 55181/61904 [5:32:17<2:36:56,  1.40s/it]
 89%|████████▉ | 55182/61904 [5:32:19<2:36:13,  1.39s/it]
 89%|████████▉ | 55183/61904 [5:32:20<2:38:53,  1.42s/it]
 89%|████████▉ | 55184/61904 [5:32:22<2:39:01,  1.42s/it]
 89%|████████▉ | 55185/61904 [5:32:23<2:34:43,  1.38s/it]
 89%|████████▉ | 55186/61904 [5:32:24<2:32:52,  1.37s/it]
 89%|████████▉ | 55187/61904 [5:32:26<2:32:39,  1.36s/it]
 89%|████████▉ | 55188/61904 [5:32:27<2:31:47,  1.36s/it]
 89%|████████▉ | 55189/61904 [5:32:28<2:35:05,  1.39s/it]
 89%|████████▉ | 55190/61904 [5:32:30<2:35:45,  1.39s/it]
 89%|████████▉ | 55191/61904 [5:32:31<2:33:25,  1.37s/it]
 89%|████████▉ | 55192/61904 [5:32:33<2:39:08,  1.42s/it]
 89%|████████▉ | 55193/61904 [5:32:34<2:37:28,  1.41s/it]
 89%|████████▉ | 55194/61904 [5:32:35<2:36:32,  1.40s/it]
 89%|████████▉ | 55195/61904 [5:32:37<2:39:37,  1.43s/it]
 89%|████████▉ | 55196/61904 [5:32:38<2:38:03,  1.41s/it]
 89%|████████▉ | 55197/61904 [5:32:40<2:36:53,  1.40s/it]
 89%|████████▉ | 55198/61904 [5:32:41<2:30:17,  1.34s/it]
 89%|████████▉ | 55199/61904 [5:32:42<2:35:18,  1.39s/it]
 89%|████████▉ | 55200/61904 [5:32:44<2:36:53,  1.40s/it]
                                                         
{'loss': 2.4477, 'learning_rate': 1.108647737585894e-07, 'epoch': 14.27}

 89%|████████▉ | 55200/61904 [5:32:44<2:36:53,  1.40s/it]
 89%|████████▉ | 55201/61904 [5:32:45<2:32:03,  1.36s/it]
 89%|████████▉ | 55202/61904 [5:32:46<2:31:46,  1.36s/it]
 89%|████████▉ | 55203/61904 [5:32:48<2:29:10,  1.34s/it]
 89%|████████▉ | 55204/61904 [5:32:49<2:28:22,  1.33s/it]
 89%|████████▉ | 55205/61904 [5:32:51<2:32:55,  1.37s/it]
 89%|████████▉ | 55206/61904 [5:32:52<2:34:16,  1.38s/it]
 89%|████████▉ | 55207/61904 [5:32:53<2:31:17,  1.36s/it]
 89%|████████▉ | 55208/61904 [5:32:55<2:32:46,  1.37s/it]
 89%|████████▉ | 55209/61904 [5:32:56<2:31:32,  1.36s/it]
 89%|████████▉ | 55210/61904 [5:32:57<2:34:36,  1.39s/it]
 89%|████████▉ | 55211/61904 [5:32:59<2:34:09,  1.38s/it]
 89%|████████▉ | 55212/61904 [5:33:00<2:29:18,  1.34s/it]
 89%|████████▉ | 55213/61904 [5:33:02<2:38:25,  1.42s/it]
 89%|████████▉ | 55214/61904 [5:33:03<2:36:59,  1.41s/it]
 89%|████████▉ | 55215/61904 [5:33:04<2:34:21,  1.38s/it]
 89%|████████▉ | 55216/61904 [5:33:06<2:40:16,  1.44s/it]
 89%|████████▉ | 55217/61904 [5:33:07<2:32:30,  1.37s/it]
 89%|████████▉ | 55218/61904 [5:33:09<2:37:17,  1.41s/it]
 89%|████████▉ | 55219/61904 [5:33:10<2:31:49,  1.36s/it]
 89%|████████▉ | 55220/61904 [5:33:11<2:31:09,  1.36s/it]
                                                         
{'loss': 2.434, 'learning_rate': 1.1083236094904706e-07, 'epoch': 14.27}

 89%|████████▉ | 55220/61904 [5:33:11<2:31:09,  1.36s/it]
 89%|████████▉ | 55221/61904 [5:33:13<2:29:53,  1.35s/it]
 89%|████████▉ | 55222/61904 [5:33:14<2:31:55,  1.36s/it]
 89%|████████▉ | 55223/61904 [5:33:15<2:37:08,  1.41s/it]
 89%|████████▉ | 55224/61904 [5:33:17<2:40:27,  1.44s/it]
 89%|████████▉ | 55225/61904 [5:33:18<2:39:52,  1.44s/it]
 89%|████████▉ | 55226/61904 [5:33:20<2:35:45,  1.40s/it]
 89%|████████▉ | 55227/61904 [5:33:21<2:32:53,  1.37s/it]
 89%|████████▉ | 55228/61904 [5:33:22<2:35:19,  1.40s/it]
 89%|████████▉ | 55229/61904 [5:33:24<2:31:28,  1.36s/it]
 89%|████████▉ | 55230/61904 [5:33:25<2:29:44,  1.35s/it]
 89%|████████▉ | 55231/61904 [5:33:26<2:30:03,  1.35s/it]
 89%|████████▉ | 55232/61904 [5:33:28<2:30:18,  1.35s/it]
 89%|████████▉ | 55233/61904 [5:33:29<2:31:34,  1.36s/it]
 89%|████████▉ | 55234/61904 [5:33:30<2:29:03,  1.34s/it]
 89%|████████▉ | 55235/61904 [5:33:32<2:27:37,  1.33s/it]
 89%|████████▉ | 55236/61904 [5:33:33<2:28:50,  1.34s/it]
 89%|████████▉ | 55237/61904 [5:33:34<2:26:32,  1.32s/it]
 89%|████████▉ | 55238/61904 [5:33:36<2:30:17,  1.35s/it]
 89%|████████▉ | 55239/61904 [5:33:37<2:29:24,  1.35s/it]
 89%|████████▉ | 55240/61904 [5:33:38<2:27:04,  1.32s/it]
                                                         
{'loss': 2.4021, 'learning_rate': 1.1079994813950473e-07, 'epoch': 14.28}

 89%|████████▉ | 55240/61904 [5:33:38<2:27:04,  1.32s/it]
 89%|████████▉ | 55241/61904 [5:33:40<2:25:00,  1.31s/it]
 89%|████████▉ | 55242/61904 [5:33:41<2:27:29,  1.33s/it]
 89%|████████▉ | 55243/61904 [5:33:42<2:28:47,  1.34s/it]
 89%|████████▉ | 55244/61904 [5:33:44<2:38:26,  1.43s/it]
 89%|████████▉ | 55245/61904 [5:33:45<2:37:30,  1.42s/it]
 89%|████████▉ | 55246/61904 [5:33:47<2:36:23,  1.41s/it]
 89%|████████▉ | 55247/61904 [5:33:48<2:33:48,  1.39s/it]
 89%|████████▉ | 55248/61904 [5:33:50<2:31:20,  1.36s/it]
 89%|████████▉ | 55249/61904 [5:33:51<2:29:28,  1.35s/it]
 89%|████████▉ | 55250/61904 [5:33:52<2:28:19,  1.34s/it]
 89%|████████▉ | 55251/61904 [5:33:54<2:33:42,  1.39s/it]
 89%|████████▉ | 55252/61904 [5:33:55<2:36:19,  1.41s/it]
 89%|████████▉ | 55253/61904 [5:33:56<2:34:48,  1.40s/it]
 89%|████████▉ | 55254/61904 [5:33:58<2:31:02,  1.36s/it]
 89%|████████▉ | 55255/61904 [5:33:59<2:28:21,  1.34s/it]
 89%|████████▉ | 55256/61904 [5:34:00<2:30:14,  1.36s/it]
 89%|████████▉ | 55257/61904 [5:34:02<2:35:10,  1.40s/it]
 89%|████████▉ | 55258/61904 [5:34:03<2:39:50,  1.44s/it]
 89%|████████▉ | 55259/61904 [5:34:05<2:41:10,  1.46s/it]
 89%|████████▉ | 55260/61904 [5:34:06<2:35:49,  1.41s/it]
                                                         
{'loss': 2.4173, 'learning_rate': 1.107675353299624e-07, 'epoch': 14.28}

 89%|████████▉ | 55260/61904 [5:34:06<2:35:49,  1.41s/it]
 89%|████████▉ | 55261/61904 [5:34:08<2:34:22,  1.39s/it]
 89%|████████▉ | 55262/61904 [5:34:09<2:30:30,  1.36s/it]
 89%|████████▉ | 55263/61904 [5:34:10<2:32:22,  1.38s/it]
 89%|████████▉ | 55264/61904 [5:34:12<2:34:12,  1.39s/it]
 89%|████████▉ | 55265/61904 [5:34:13<2:29:34,  1.35s/it]
 89%|████████▉ | 55266/61904 [5:34:14<2:32:32,  1.38s/it]
 89%|████████▉ | 55267/61904 [5:34:16<2:33:01,  1.38s/it]
 89%|████████▉ | 55268/61904 [5:34:17<2:33:09,  1.38s/it]
 89%|████████▉ | 55269/61904 [5:34:19<2:30:14,  1.36s/it]
 89%|████████▉ | 55270/61904 [5:34:20<2:31:58,  1.37s/it]
 89%|████████▉ | 55271/61904 [5:34:21<2:29:29,  1.35s/it]
 89%|████████▉ | 55272/61904 [5:34:23<2:28:26,  1.34s/it]
 89%|████████▉ | 55273/61904 [5:34:24<2:35:02,  1.40s/it]
 89%|████████▉ | 55274/61904 [5:34:26<2:36:31,  1.42s/it]
 89%|████████▉ | 55275/61904 [5:34:27<2:40:34,  1.45s/it]
 89%|████████▉ | 55276/61904 [5:34:29<2:42:14,  1.47s/it]
 89%|████████▉ | 55277/61904 [5:34:30<2:39:45,  1.45s/it]
 89%|████████▉ | 55278/61904 [5:34:31<2:38:41,  1.44s/it]
 89%|████████▉ | 55279/61904 [5:34:33<2:39:39,  1.45s/it]
 89%|████████▉ | 55280/61904 [5:34:34<2:38:46,  1.44s/it]
                                                         
{'loss': 2.4248, 'learning_rate': 1.1073512252042007e-07, 'epoch': 14.29}

 89%|████████▉ | 55280/61904 [5:34:34<2:38:46,  1.44s/it]
 89%|████████▉ | 55281/61904 [5:34:36<2:31:02,  1.37s/it]
 89%|████████▉ | 55282/61904 [5:34:37<2:35:08,  1.41s/it]
 89%|████████▉ | 55283/61904 [5:34:38<2:31:09,  1.37s/it]
 89%|████████▉ | 55284/61904 [5:34:40<2:30:08,  1.36s/it]
 89%|████████▉ | 55285/61904 [5:34:41<2:32:00,  1.38s/it]
 89%|████████▉ | 55286/61904 [5:34:42<2:33:07,  1.39s/it]
 89%|████████▉ | 55287/61904 [5:34:44<2:28:28,  1.35s/it]
 89%|████████▉ | 55288/61904 [5:34:45<2:41:46,  1.47s/it]
 89%|████████▉ | 55289/61904 [5:34:47<2:42:08,  1.47s/it]
 89%|████████▉ | 55290/61904 [5:34:48<2:39:04,  1.44s/it]
 89%|████████▉ | 55291/61904 [5:34:50<2:36:17,  1.42s/it]
 89%|████████▉ | 55292/61904 [5:34:51<2:38:20,  1.44s/it]
 89%|████████▉ | 55293/61904 [5:34:53<2:37:16,  1.43s/it]
 89%|████████▉ | 55294/61904 [5:34:54<2:39:58,  1.45s/it]
 89%|████████▉ | 55295/61904 [5:34:56<2:44:24,  1.49s/it]
 89%|████████▉ | 55296/61904 [5:34:57<2:39:46,  1.45s/it]
 89%|████████▉ | 55297/61904 [5:34:59<2:41:37,  1.47s/it]
 89%|████████▉ | 55298/61904 [5:35:00<2:36:03,  1.42s/it]
 89%|████████▉ | 55299/61904 [5:35:01<2:32:20,  1.38s/it]
 89%|████████▉ | 55300/61904 [5:35:02<2:31:26,  1.38s/it]
                                                         
{'loss': 2.449, 'learning_rate': 1.1070270971087773e-07, 'epoch': 14.29}

 89%|████████▉ | 55300/61904 [5:35:02<2:31:26,  1.38s/it]
 89%|████████▉ | 55301/61904 [5:35:04<2:35:37,  1.41s/it]
 89%|████████▉ | 55302/61904 [5:35:05<2:32:18,  1.38s/it]
 89%|████████▉ | 55303/61904 [5:35:07<2:36:49,  1.43s/it]
 89%|████████▉ | 55304/61904 [5:35:08<2:31:25,  1.38s/it]
 89%|████████▉ | 55305/61904 [5:35:09<2:31:14,  1.38s/it]
 89%|████████▉ | 55306/61904 [5:35:11<2:29:52,  1.36s/it]
 89%|████████▉ | 55307/61904 [5:35:12<2:32:02,  1.38s/it]
 89%|████████▉ | 55308/61904 [5:35:14<2:29:50,  1.36s/it]
 89%|████████▉ | 55309/61904 [5:35:15<2:33:08,  1.39s/it]
 89%|████████▉ | 55310/61904 [5:35:16<2:36:12,  1.42s/it]
 89%|████████▉ | 55311/61904 [5:35:18<2:34:01,  1.40s/it]
 89%|████████▉ | 55312/61904 [5:35:19<2:32:01,  1.38s/it]
 89%|████████▉ | 55313/61904 [5:35:21<2:32:05,  1.38s/it]
 89%|████████▉ | 55314/61904 [5:35:22<2:27:26,  1.34s/it]
 89%|████████▉ | 55315/61904 [5:35:23<2:27:29,  1.34s/it]
 89%|████████▉ | 55316/61904 [5:35:25<2:29:14,  1.36s/it]
 89%|████████▉ | 55317/61904 [5:35:26<2:27:05,  1.34s/it]
 89%|████████▉ | 55318/61904 [5:35:27<2:28:07,  1.35s/it]
 89%|████████▉ | 55319/61904 [5:35:29<2:26:27,  1.33s/it]
 89%|████████▉ | 55320/61904 [5:35:30<2:27:00,  1.34s/it]
                                                         
{'loss': 2.5167, 'learning_rate': 1.1067029690133541e-07, 'epoch': 14.3}

 89%|████████▉ | 55320/61904 [5:35:30<2:27:00,  1.34s/it]
 89%|████████▉ | 55321/61904 [5:35:31<2:26:24,  1.33s/it]
 89%|████████▉ | 55322/61904 [5:35:33<2:27:55,  1.35s/it]
 89%|████████▉ | 55323/61904 [5:35:34<2:27:23,  1.34s/it]
 89%|████████▉ | 55324/61904 [5:35:35<2:26:31,  1.34s/it]
 89%|████████▉ | 55325/61904 [5:35:36<2:21:17,  1.29s/it]
 89%|████████▉ | 55326/61904 [5:35:38<2:22:50,  1.30s/it]
 89%|████████▉ | 55327/61904 [5:35:39<2:28:43,  1.36s/it]
 89%|████████▉ | 55328/61904 [5:35:41<2:29:39,  1.37s/it]
 89%|████████▉ | 55329/61904 [5:35:42<2:27:59,  1.35s/it]
 89%|████████▉ | 55330/61904 [5:35:43<2:29:20,  1.36s/it]
 89%|████████▉ | 55331/61904 [5:35:45<2:28:06,  1.35s/it]
 89%|████████▉ | 55332/61904 [5:35:46<2:28:38,  1.36s/it]
 89%|████████▉ | 55333/61904 [5:35:47<2:27:08,  1.34s/it]
 89%|████████▉ | 55334/61904 [5:35:49<2:26:11,  1.34s/it]
 89%|████████▉ | 55335/61904 [5:35:50<2:23:17,  1.31s/it]
 89%|████████▉ | 55336/61904 [5:35:51<2:30:07,  1.37s/it]
 89%|████████▉ | 55337/61904 [5:35:53<2:28:15,  1.35s/it]
 89%|████████▉ | 55338/61904 [5:35:54<2:26:38,  1.34s/it]
 89%|████████▉ | 55339/61904 [5:35:55<2:27:51,  1.35s/it]
 89%|████████▉ | 55340/61904 [5:35:57<2:26:08,  1.34s/it]
                                                         
{'loss': 2.439, 'learning_rate': 1.1063788409179308e-07, 'epoch': 14.3}

 89%|████████▉ | 55340/61904 [5:35:57<2:26:08,  1.34s/it]
 89%|████████▉ | 55341/61904 [5:35:58<2:24:48,  1.32s/it]
 89%|████████▉ | 55342/61904 [5:35:59<2:30:08,  1.37s/it]
 89%|████████▉ | 55343/61904 [5:36:01<2:23:36,  1.31s/it]
 89%|████████▉ | 55344/61904 [5:36:02<2:26:24,  1.34s/it]
 89%|████████▉ | 55345/61904 [5:36:03<2:27:33,  1.35s/it]
 89%|████████▉ | 55346/61904 [5:36:05<2:32:52,  1.40s/it]
 89%|████████▉ | 55347/61904 [5:36:06<2:30:29,  1.38s/it]
 89%|████████▉ | 55348/61904 [5:36:08<2:31:29,  1.39s/it]
 89%|████████▉ | 55349/61904 [5:36:09<2:31:48,  1.39s/it]
 89%|████████▉ | 55350/61904 [5:36:11<2:33:11,  1.40s/it]
 89%|████████▉ | 55351/61904 [5:36:12<2:31:28,  1.39s/it]
 89%|████████▉ | 55352/61904 [5:36:13<2:32:20,  1.40s/it]
 89%|████████▉ | 55353/61904 [5:36:15<2:30:22,  1.38s/it]
 89%|████████▉ | 55354/61904 [5:36:16<2:29:44,  1.37s/it]
 89%|████████▉ | 55355/61904 [5:36:17<2:28:51,  1.36s/it]
 89%|████████▉ | 55356/61904 [5:36:19<2:36:17,  1.43s/it]
 89%|████████▉ | 55357/61904 [5:36:20<2:36:15,  1.43s/it]
 89%|████████▉ | 55358/61904 [5:36:22<2:30:51,  1.38s/it]
 89%|████████▉ | 55359/61904 [5:36:23<2:30:47,  1.38s/it]
 89%|████████▉ | 55360/61904 [5:36:24<2:26:55,  1.35s/it]
                                                         
{'loss': 2.4282, 'learning_rate': 1.1060547128225075e-07, 'epoch': 14.31}

 89%|████████▉ | 55360/61904 [5:36:24<2:26:55,  1.35s/it]
 89%|████████▉ | 55361/61904 [5:36:26<2:26:12,  1.34s/it]
 89%|████████▉ | 55362/61904 [5:36:27<2:31:20,  1.39s/it]
 89%|████████▉ | 55363/61904 [5:36:28<2:29:23,  1.37s/it]
 89%|████████▉ | 55364/61904 [5:36:30<2:28:19,  1.36s/it]
 89%|████████▉ | 55365/61904 [5:36:31<2:30:19,  1.38s/it]
 89%|████████▉ | 55366/61904 [5:36:33<2:30:30,  1.38s/it]
 89%|████████▉ | 55367/61904 [5:36:34<2:35:14,  1.42s/it]
 89%|████████▉ | 55368/61904 [5:36:35<2:32:23,  1.40s/it]
 89%|████████▉ | 55369/61904 [5:36:37<2:29:53,  1.38s/it]
 89%|████████▉ | 55370/61904 [5:36:38<2:35:47,  1.43s/it]
 89%|████████▉ | 55371/61904 [5:36:40<2:32:11,  1.40s/it]
 89%|████████▉ | 55372/61904 [5:36:41<2:32:49,  1.40s/it]
 89%|████████▉ | 55373/61904 [5:36:42<2:32:56,  1.41s/it]
 89%|████████▉ | 55374/61904 [5:36:44<2:32:03,  1.40s/it]
 89%|████████▉ | 55375/61904 [5:36:45<2:36:07,  1.43s/it]
 89%|████████▉ | 55376/61904 [5:36:47<2:30:32,  1.38s/it]
 89%|████████▉ | 55377/61904 [5:36:48<2:33:36,  1.41s/it]
 89%|████████▉ | 55378/61904 [5:36:50<2:34:02,  1.42s/it]
 89%|████████▉ | 55379/61904 [5:36:51<2:30:42,  1.39s/it]
 89%|████████▉ | 55380/61904 [5:36:52<2:29:15,  1.37s/it]
                                                         
{'loss': 2.4502, 'learning_rate': 1.1057305847270841e-07, 'epoch': 14.31}

 89%|████████▉ | 55380/61904 [5:36:52<2:29:15,  1.37s/it]
 89%|████████▉ | 55381/61904 [5:36:54<2:30:57,  1.39s/it]
 89%|████████▉ | 55382/61904 [5:36:55<2:31:21,  1.39s/it]
 89%|████████▉ | 55383/61904 [5:36:56<2:31:29,  1.39s/it]
 89%|████████▉ | 55384/61904 [5:36:58<2:36:37,  1.44s/it]
 89%|████████▉ | 55385/61904 [5:36:59<2:38:06,  1.46s/it]
 89%|████████▉ | 55386/61904 [5:37:01<2:31:19,  1.39s/it]
 89%|████████▉ | 55387/61904 [5:37:02<2:32:04,  1.40s/it]
 89%|████████▉ | 55388/61904 [5:37:03<2:31:34,  1.40s/it]
 89%|████████▉ | 55389/61904 [5:37:05<2:27:06,  1.35s/it]
 89%|████████▉ | 55390/61904 [5:37:06<2:26:10,  1.35s/it]
 89%|████████▉ | 55391/61904 [5:37:07<2:24:32,  1.33s/it]
 89%|████████▉ | 55392/61904 [5:37:09<2:26:43,  1.35s/it]
 89%|████████▉ | 55393/61904 [5:37:10<2:29:32,  1.38s/it]
 89%|████████▉ | 55394/61904 [5:37:12<2:34:54,  1.43s/it]
 89%|████████▉ | 55395/61904 [5:37:13<2:38:00,  1.46s/it]
 89%|████████▉ | 55396/61904 [5:37:15<2:32:03,  1.40s/it]
 89%|████████▉ | 55397/61904 [5:37:16<2:29:42,  1.38s/it]
 89%|████████▉ | 55398/61904 [5:37:17<2:25:57,  1.35s/it]
 89%|████████▉ | 55399/61904 [5:37:19<2:29:40,  1.38s/it]
 89%|████████▉ | 55400/61904 [5:37:20<2:27:22,  1.36s/it]
                                                         
{'loss': 2.4245, 'learning_rate': 1.1054064566316608e-07, 'epoch': 14.32}

 89%|████████▉ | 55400/61904 [5:37:20<2:27:22,  1.36s/it]
 89%|████████▉ | 55401/61904 [5:37:21<2:33:10,  1.41s/it]
 89%|████████▉ | 55402/61904 [5:37:23<2:32:15,  1.41s/it]
 89%|████████▉ | 55403/61904 [5:37:24<2:39:46,  1.47s/it]
 89%|████████▉ | 55404/61904 [5:37:26<2:38:59,  1.47s/it]
 90%|████████▉ | 55405/61904 [5:37:27<2:39:51,  1.48s/it]
 90%|████████▉ | 55406/61904 [5:37:29<2:40:16,  1.48s/it]
 90%|████████▉ | 55407/61904 [5:37:30<2:38:57,  1.47s/it]
 90%|████████▉ | 55408/61904 [5:37:32<2:38:00,  1.46s/it]
 90%|████████▉ | 55409/61904 [5:37:33<2:40:35,  1.48s/it]
 90%|████████▉ | 55410/61904 [5:37:35<2:39:28,  1.47s/it]
 90%|████████▉ | 55411/61904 [5:37:36<2:34:26,  1.43s/it]
 90%|████████▉ | 55412/61904 [5:37:37<2:31:07,  1.40s/it]
 90%|████████▉ | 55413/61904 [5:37:39<2:29:08,  1.38s/it]
 90%|████████▉ | 55414/61904 [5:37:40<2:26:01,  1.35s/it]
 90%|████████▉ | 55415/61904 [5:37:41<2:28:01,  1.37s/it]
 90%|████████▉ | 55416/61904 [5:37:43<2:31:52,  1.40s/it]
 90%|████████▉ | 55417/61904 [5:37:44<2:31:59,  1.41s/it]
 90%|████████▉ | 55418/61904 [5:37:46<2:33:17,  1.42s/it]
 90%|████████▉ | 55419/61904 [5:37:47<2:31:06,  1.40s/it]
 90%|████████▉ | 55420/61904 [5:37:48<2:28:34,  1.37s/it]
                                                         
{'loss': 2.4192, 'learning_rate': 1.1050823285362376e-07, 'epoch': 14.32}

 90%|████████▉ | 55420/61904 [5:37:48<2:28:34,  1.37s/it]
 90%|████████▉ | 55421/61904 [5:37:50<2:34:09,  1.43s/it]
 90%|████████▉ | 55422/61904 [5:37:51<2:32:39,  1.41s/it]
 90%|████████▉ | 55423/61904 [5:37:53<2:37:22,  1.46s/it]
 90%|████████▉ | 55424/61904 [5:37:54<2:36:29,  1.45s/it]
 90%|████████▉ | 55425/61904 [5:37:56<2:33:16,  1.42s/it]
 90%|████████▉ | 55426/61904 [5:37:57<2:31:18,  1.40s/it]
 90%|████████▉ | 55427/61904 [5:37:58<2:27:11,  1.36s/it]
 90%|████████▉ | 55428/61904 [5:38:00<2:25:04,  1.34s/it]
 90%|████████▉ | 55429/61904 [5:38:01<2:21:47,  1.31s/it]
 90%|████████▉ | 55430/61904 [5:38:02<2:28:25,  1.38s/it]
 90%|████████▉ | 55431/61904 [5:38:04<2:29:37,  1.39s/it]
 90%|████████▉ | 55432/61904 [5:38:05<2:30:04,  1.39s/it]
 90%|████████▉ | 55433/61904 [5:38:07<2:28:25,  1.38s/it]
 90%|████████▉ | 55434/61904 [5:38:08<2:36:48,  1.45s/it]
 90%|████████▉ | 55435/61904 [5:38:10<2:34:27,  1.43s/it]
 90%|████████▉ | 55436/61904 [5:38:11<2:34:00,  1.43s/it]
 90%|████████▉ | 55437/61904 [5:38:12<2:29:47,  1.39s/it]
 90%|████████▉ | 55438/61904 [5:38:14<2:31:36,  1.41s/it]
 90%|████████▉ | 55439/61904 [5:38:15<2:31:30,  1.41s/it]
 90%|████████▉ | 55440/61904 [5:38:17<2:34:55,  1.44s/it]
                                                         
{'loss': 2.4461, 'learning_rate': 1.1047582004408142e-07, 'epoch': 14.33}

 90%|████████▉ | 55440/61904 [5:38:17<2:34:55,  1.44s/it]
 90%|████████▉ | 55441/61904 [5:38:18<2:38:48,  1.47s/it]
 90%|████████▉ | 55442/61904 [5:38:20<2:34:35,  1.44s/it]
 90%|████████▉ | 55443/61904 [5:38:21<2:28:01,  1.37s/it]
 90%|████████▉ | 55444/61904 [5:38:22<2:26:59,  1.37s/it]
 90%|████████▉ | 55445/61904 [5:38:24<2:32:18,  1.41s/it]
 90%|████████▉ | 55446/61904 [5:38:25<2:25:14,  1.35s/it]
 90%|████████▉ | 55447/61904 [5:38:26<2:31:23,  1.41s/it]
 90%|████████▉ | 55448/61904 [5:38:28<2:29:28,  1.39s/it]
 90%|████████▉ | 55449/61904 [5:38:29<2:34:40,  1.44s/it]
 90%|████████▉ | 55450/61904 [5:38:31<2:34:42,  1.44s/it]
 90%|████████▉ | 55451/61904 [5:38:32<2:35:49,  1.45s/it]
 90%|████████▉ | 55452/61904 [5:38:34<2:37:43,  1.47s/it]
 90%|████████▉ | 55453/61904 [5:38:35<2:37:30,  1.46s/it]
 90%|████████▉ | 55454/61904 [5:38:36<2:28:46,  1.38s/it]
 90%|████████▉ | 55455/61904 [5:38:38<2:28:08,  1.38s/it]
 90%|████████▉ | 55456/61904 [5:38:39<2:25:39,  1.36s/it]
 90%|████████▉ | 55457/61904 [5:38:40<2:23:51,  1.34s/it]
 90%|████████▉ | 55458/61904 [5:38:42<2:24:59,  1.35s/it]
 90%|████████▉ | 55459/61904 [5:38:43<2:24:17,  1.34s/it]
 90%|████████▉ | 55460/61904 [5:38:44<2:25:24,  1.35s/it]
                                                         
{'loss': 2.3875, 'learning_rate': 1.1044340723453908e-07, 'epoch': 14.33}

 90%|████████▉ | 55460/61904 [5:38:44<2:25:24,  1.35s/it]
 90%|████████▉ | 55461/61904 [5:38:46<2:27:34,  1.37s/it]
 90%|████████▉ | 55462/61904 [5:38:47<2:27:47,  1.38s/it]
 90%|████████▉ | 55463/61904 [5:38:49<2:26:16,  1.36s/it]
 90%|████████▉ | 55464/61904 [5:38:50<2:24:33,  1.35s/it]
 90%|████████▉ | 55465/61904 [5:38:51<2:25:35,  1.36s/it]
 90%|████████▉ | 55466/61904 [5:38:53<2:29:59,  1.40s/it]
 90%|████████▉ | 55467/61904 [5:38:54<2:25:33,  1.36s/it]
 90%|████████▉ | 55468/61904 [5:38:55<2:27:09,  1.37s/it]
 90%|████████▉ | 55469/61904 [5:38:57<2:31:11,  1.41s/it]
 90%|████████▉ | 55470/61904 [5:38:58<2:29:06,  1.39s/it]
 90%|████████▉ | 55471/61904 [5:39:00<2:38:51,  1.48s/it]
 90%|████████▉ | 55472/61904 [5:39:02<2:42:38,  1.52s/it]
 90%|████████▉ | 55473/61904 [5:39:03<2:36:05,  1.46s/it]
 90%|████████▉ | 55474/61904 [5:39:04<2:31:32,  1.41s/it]
 90%|████████▉ | 55475/61904 [5:39:05<2:26:51,  1.37s/it]
 90%|████████▉ | 55476/61904 [5:39:07<2:21:50,  1.32s/it]
 90%|████████▉ | 55477/61904 [5:39:08<2:22:38,  1.33s/it]
 90%|████████▉ | 55478/61904 [5:39:09<2:23:41,  1.34s/it]
 90%|████████▉ | 55479/61904 [5:39:11<2:23:56,  1.34s/it]
 90%|████████▉ | 55480/61904 [5:39:12<2:22:07,  1.33s/it]
                                                         
{'loss': 2.3687, 'learning_rate': 1.1041099442499676e-07, 'epoch': 14.34}

 90%|████████▉ | 55480/61904 [5:39:12<2:22:07,  1.33s/it]
 90%|████████▉ | 55481/61904 [5:39:14<2:26:42,  1.37s/it]
 90%|████████▉ | 55482/61904 [5:39:15<2:23:19,  1.34s/it]
 90%|████████▉ | 55483/61904 [5:39:16<2:24:38,  1.35s/it]
 90%|████████▉ | 55484/61904 [5:39:18<2:28:01,  1.38s/it]
 90%|████████▉ | 55485/61904 [5:39:19<2:28:16,  1.39s/it]
 90%|████████▉ | 55486/61904 [5:39:20<2:24:06,  1.35s/it]
 90%|████████▉ | 55487/61904 [5:39:22<2:28:12,  1.39s/it]
 90%|████████▉ | 55488/61904 [5:39:23<2:27:17,  1.38s/it]
 90%|████████▉ | 55489/61904 [5:39:25<2:28:25,  1.39s/it]
 90%|████████▉ | 55490/61904 [5:39:26<2:33:11,  1.43s/it]
 90%|████████▉ | 55491/61904 [5:39:28<2:34:18,  1.44s/it]
 90%|████████▉ | 55492/61904 [5:39:29<2:29:14,  1.40s/it]
 90%|████████▉ | 55493/61904 [5:39:30<2:25:19,  1.36s/it]
 90%|████████▉ | 55494/61904 [5:39:31<2:25:28,  1.36s/it]
 90%|████████▉ | 55495/61904 [5:39:33<2:29:23,  1.40s/it]
 90%|████████▉ | 55496/61904 [5:39:34<2:27:39,  1.38s/it]
 90%|████████▉ | 55497/61904 [5:39:36<2:25:32,  1.36s/it]
 90%|████████▉ | 55498/61904 [5:39:37<2:25:50,  1.37s/it]
 90%|████████▉ | 55499/61904 [5:39:38<2:25:43,  1.37s/it]
 90%|████████▉ | 55500/61904 [5:39:40<2:25:58,  1.37s/it]
                                                         
{'loss': 2.5006, 'learning_rate': 1.1037858161545443e-07, 'epoch': 14.34}

 90%|████████▉ | 55500/61904 [5:39:40<2:25:58,  1.37s/it]
 90%|████████▉ | 55501/61904 [5:39:41<2:23:55,  1.35s/it]
 90%|████████▉ | 55502/61904 [5:39:42<2:22:10,  1.33s/it]
 90%|████████▉ | 55503/61904 [5:39:44<2:22:53,  1.34s/it]
 90%|████████▉ | 55504/61904 [5:39:45<2:20:50,  1.32s/it]
 90%|████████▉ | 55505/61904 [5:39:46<2:22:17,  1.33s/it]
 90%|████████▉ | 55506/61904 [5:39:48<2:19:33,  1.31s/it]
 90%|████████▉ | 55507/61904 [5:39:49<2:23:02,  1.34s/it]
 90%|████████▉ | 55508/61904 [5:39:50<2:23:40,  1.35s/it]
 90%|████████▉ | 55509/61904 [5:39:52<2:21:00,  1.32s/it]
 90%|████████▉ | 55510/61904 [5:39:53<2:20:49,  1.32s/it]
 90%|████████▉ | 55511/61904 [5:39:54<2:22:53,  1.34s/it]
 90%|████████▉ | 55512/61904 [5:39:56<2:21:22,  1.33s/it]
 90%|████████▉ | 55513/61904 [5:39:57<2:23:14,  1.34s/it]
 90%|████████▉ | 55514/61904 [5:39:58<2:24:55,  1.36s/it]
 90%|████████▉ | 55515/61904 [5:40:00<2:25:16,  1.36s/it]
 90%|████████▉ | 55516/61904 [5:40:01<2:24:32,  1.36s/it]
 90%|████████▉ | 55517/61904 [5:40:03<2:33:23,  1.44s/it]
 90%|████████▉ | 55518/61904 [5:40:04<2:35:41,  1.46s/it]
 90%|████████▉ | 55519/61904 [5:40:06<2:28:52,  1.40s/it]
 90%|████████▉ | 55520/61904 [5:40:07<2:31:43,  1.43s/it]
                                                         
{'loss': 2.4207, 'learning_rate': 1.1034616880591209e-07, 'epoch': 14.35}

 90%|████████▉ | 55520/61904 [5:40:07<2:31:43,  1.43s/it]
 90%|████████▉ | 55521/61904 [5:40:08<2:27:51,  1.39s/it]
 90%|████████▉ | 55522/61904 [5:40:10<2:24:01,  1.35s/it]
 90%|████████▉ | 55523/61904 [5:40:11<2:22:40,  1.34s/it]
 90%|████████▉ | 55524/61904 [5:40:12<2:26:15,  1.38s/it]
 90%|████████▉ | 55525/61904 [5:40:14<2:23:13,  1.35s/it]
 90%|████████▉ | 55526/61904 [5:40:15<2:24:51,  1.36s/it]
 90%|████████▉ | 55527/61904 [5:40:17<2:31:56,  1.43s/it]
 90%|████████▉ | 55528/61904 [5:40:18<2:27:51,  1.39s/it]
 90%|████████▉ | 55529/61904 [5:40:19<2:30:19,  1.41s/it]
 90%|████████▉ | 55530/61904 [5:40:21<2:30:04,  1.41s/it]
 90%|████████▉ | 55531/61904 [5:40:22<2:32:43,  1.44s/it]
 90%|████████▉ | 55532/61904 [5:40:24<2:28:47,  1.40s/it]
 90%|████████▉ | 55533/61904 [5:40:25<2:29:50,  1.41s/it]
 90%|████████▉ | 55534/61904 [5:40:26<2:31:22,  1.43s/it]
 90%|████████▉ | 55535/61904 [5:40:28<2:30:36,  1.42s/it]
 90%|████████▉ | 55536/61904 [5:40:29<2:32:03,  1.43s/it]
 90%|████████▉ | 55537/61904 [5:40:31<2:31:55,  1.43s/it]
 90%|████████▉ | 55538/61904 [5:40:32<2:33:52,  1.45s/it]
 90%|████████▉ | 55539/61904 [5:40:34<2:31:51,  1.43s/it]
 90%|████████▉ | 55540/61904 [5:40:35<2:28:23,  1.40s/it]
                                                         
{'loss': 2.4137, 'learning_rate': 1.1031375599636977e-07, 'epoch': 14.35}

 90%|████████▉ | 55540/61904 [5:40:35<2:28:23,  1.40s/it]
 90%|████████▉ | 55541/61904 [5:40:36<2:27:31,  1.39s/it]
 90%|████████▉ | 55542/61904 [5:40:38<2:29:24,  1.41s/it]
 90%|████████▉ | 55543/61904 [5:40:39<2:32:00,  1.43s/it]
 90%|████████▉ | 55544/61904 [5:40:41<2:30:56,  1.42s/it]
 90%|████████▉ | 55545/61904 [5:40:42<2:34:34,  1.46s/it]
 90%|████████▉ | 55546/61904 [5:40:44<2:32:29,  1.44s/it]
 90%|████████▉ | 55547/61904 [5:40:45<2:31:47,  1.43s/it]
 90%|████████▉ | 55548/61904 [5:40:46<2:29:41,  1.41s/it]
 90%|████████▉ | 55549/61904 [5:40:48<2:25:45,  1.38s/it]
 90%|████████▉ | 55550/61904 [5:40:49<2:26:43,  1.39s/it]
 90%|████████▉ | 55551/61904 [5:40:51<2:27:13,  1.39s/it]
 90%|████████▉ | 55552/61904 [5:40:52<2:27:15,  1.39s/it]
 90%|████████▉ | 55553/61904 [5:40:53<2:27:12,  1.39s/it]
 90%|████████▉ | 55554/61904 [5:40:55<2:22:51,  1.35s/it]
 90%|████████▉ | 55555/61904 [5:40:56<2:22:12,  1.34s/it]
 90%|████████▉ | 55556/61904 [5:40:57<2:24:56,  1.37s/it]
 90%|████████▉ | 55557/61904 [5:40:59<2:30:46,  1.43s/it]
 90%|████████▉ | 55558/61904 [5:41:00<2:28:39,  1.41s/it]
 90%|████████▉ | 55559/61904 [5:41:01<2:23:55,  1.36s/it]
 90%|████████▉ | 55560/61904 [5:41:03<2:24:40,  1.37s/it]
                                                         
{'loss': 2.4323, 'learning_rate': 1.1028134318682743e-07, 'epoch': 14.36}

 90%|████████▉ | 55560/61904 [5:41:03<2:24:40,  1.37s/it]
 90%|████████▉ | 55561/61904 [5:41:04<2:28:00,  1.40s/it]
 90%|████████▉ | 55562/61904 [5:41:06<2:26:02,  1.38s/it]
 90%|████████▉ | 55563/61904 [5:41:07<2:29:21,  1.41s/it]
 90%|████████▉ | 55564/61904 [5:41:09<2:30:51,  1.43s/it]
 90%|████████▉ | 55565/61904 [5:41:10<2:29:44,  1.42s/it]
 90%|████████▉ | 55566/61904 [5:41:11<2:30:28,  1.42s/it]
 90%|████████▉ | 55567/61904 [5:41:13<2:25:59,  1.38s/it]
 90%|████████▉ | 55568/61904 [5:41:14<2:28:03,  1.40s/it]
 90%|████████▉ | 55569/61904 [5:41:16<2:30:13,  1.42s/it]
 90%|████████▉ | 55570/61904 [5:41:17<2:26:50,  1.39s/it]
 90%|████████▉ | 55571/61904 [5:41:18<2:24:43,  1.37s/it]
 90%|████████▉ | 55572/61904 [5:41:20<2:21:41,  1.34s/it]
 90%|████████▉ | 55573/61904 [5:41:21<2:21:15,  1.34s/it]
 90%|████████▉ | 55574/61904 [5:41:22<2:22:17,  1.35s/it]
 90%|████████▉ | 55575/61904 [5:41:24<2:23:02,  1.36s/it]
 90%|████████▉ | 55576/61904 [5:41:25<2:21:25,  1.34s/it]
 90%|████████▉ | 55577/61904 [5:41:26<2:21:04,  1.34s/it]
 90%|████████▉ | 55578/61904 [5:41:28<2:27:03,  1.39s/it]
 90%|████████▉ | 55579/61904 [5:41:29<2:22:25,  1.35s/it]
 90%|████████▉ | 55580/61904 [5:41:30<2:21:45,  1.34s/it]
                                                         
{'loss': 2.3947, 'learning_rate': 1.102489303772851e-07, 'epoch': 14.37}

 90%|████████▉ | 55580/61904 [5:41:30<2:21:45,  1.34s/it]
 90%|████████▉ | 55581/61904 [5:41:32<2:21:14,  1.34s/it]
 90%|████████▉ | 55582/61904 [5:41:33<2:26:28,  1.39s/it]
 90%|████████▉ | 55583/61904 [5:41:35<2:23:23,  1.36s/it]
 90%|████████▉ | 55584/61904 [5:41:36<2:21:50,  1.35s/it]
 90%|████████▉ | 55585/61904 [5:41:37<2:27:15,  1.40s/it]
 90%|████████▉ | 55586/61904 [5:41:39<2:23:20,  1.36s/it]
 90%|████████▉ | 55587/61904 [5:41:40<2:23:07,  1.36s/it]
 90%|████████▉ | 55588/61904 [5:41:41<2:23:24,  1.36s/it]
 90%|████████▉ | 55589/61904 [5:41:43<2:25:39,  1.38s/it]
 90%|████████▉ | 55590/61904 [5:41:44<2:26:19,  1.39s/it]
 90%|████████▉ | 55591/61904 [5:41:46<2:33:39,  1.46s/it]
 90%|████████▉ | 55592/61904 [5:41:47<2:29:21,  1.42s/it]
 90%|████████▉ | 55593/61904 [5:41:49<2:26:54,  1.40s/it]
 90%|████████▉ | 55594/61904 [5:41:50<2:29:04,  1.42s/it]
 90%|████████▉ | 55595/61904 [5:41:51<2:27:40,  1.40s/it]
 90%|████████▉ | 55596/61904 [5:41:53<2:27:06,  1.40s/it]
 90%|████████▉ | 55597/61904 [5:41:54<2:26:36,  1.39s/it]
 90%|████████▉ | 55598/61904 [5:41:56<2:28:06,  1.41s/it]
 90%|████████▉ | 55599/61904 [5:41:57<2:28:06,  1.41s/it]
 90%|████████▉ | 55600/61904 [5:41:58<2:28:47,  1.42s/it]
                                                         
{'loss': 2.4286, 'learning_rate': 1.1021651756774277e-07, 'epoch': 14.37}

 90%|████████▉ | 55600/61904 [5:41:58<2:28:47,  1.42s/it]
 90%|████████▉ | 55601/61904 [5:42:00<2:39:49,  1.52s/it]
 90%|████████▉ | 55602/61904 [5:42:02<2:35:15,  1.48s/it]
 90%|████████▉ | 55603/61904 [5:42:03<2:35:51,  1.48s/it]
 90%|████████▉ | 55604/61904 [5:42:04<2:34:14,  1.47s/it]
 90%|████████▉ | 55605/61904 [5:42:06<2:33:02,  1.46s/it]
 90%|████████▉ | 55606/61904 [5:42:07<2:31:34,  1.44s/it]
 90%|████████▉ | 55607/61904 [5:42:09<2:29:39,  1.43s/it]
 90%|████████▉ | 55608/61904 [5:42:10<2:32:21,  1.45s/it]
 90%|████████▉ | 55609/61904 [5:42:12<2:31:35,  1.44s/it]
 90%|████████▉ | 55610/61904 [5:42:13<2:29:51,  1.43s/it]
 90%|████████▉ | 55611/61904 [5:42:14<2:24:46,  1.38s/it]
 90%|████████▉ | 55612/61904 [5:42:16<2:22:50,  1.36s/it]
 90%|████████▉ | 55613/61904 [5:42:17<2:25:00,  1.38s/it]
 90%|████████▉ | 55614/61904 [5:42:19<2:27:19,  1.41s/it]
 90%|████████▉ | 55615/61904 [5:42:20<2:27:54,  1.41s/it]
 90%|████████▉ | 55616/61904 [5:42:21<2:26:48,  1.40s/it]
 90%|████████▉ | 55617/61904 [5:42:23<2:28:16,  1.42s/it]
 90%|████████▉ | 55618/61904 [5:42:24<2:21:59,  1.36s/it]
 90%|████████▉ | 55619/61904 [5:42:25<2:20:09,  1.34s/it]
 90%|████████▉ | 55620/61904 [5:42:27<2:25:31,  1.39s/it]
                                                         
{'loss': 2.3842, 'learning_rate': 1.1018410475820044e-07, 'epoch': 14.38}

 90%|████████▉ | 55620/61904 [5:42:27<2:25:31,  1.39s/it]
 90%|████████▉ | 55621/61904 [5:42:28<2:22:10,  1.36s/it]
 90%|████████▉ | 55622/61904 [5:42:29<2:19:31,  1.33s/it]
 90%|████████▉ | 55623/61904 [5:42:31<2:19:58,  1.34s/it]
 90%|████████▉ | 55624/61904 [5:42:32<2:17:36,  1.31s/it]
 90%|████████▉ | 55625/61904 [5:42:33<2:22:54,  1.37s/it]
 90%|████████▉ | 55626/61904 [5:42:35<2:19:14,  1.33s/it]
 90%|████████▉ | 55627/61904 [5:42:36<2:19:27,  1.33s/it]
 90%|████████▉ | 55628/61904 [5:42:38<2:25:34,  1.39s/it]
 90%|████████▉ | 55629/61904 [5:42:39<2:32:48,  1.46s/it]
 90%|████████▉ | 55630/61904 [5:42:41<2:30:57,  1.44s/it]
 90%|████████▉ | 55631/61904 [5:42:42<2:25:37,  1.39s/it]
 90%|████████▉ | 55632/61904 [5:42:43<2:24:12,  1.38s/it]
 90%|████████▉ | 55633/61904 [5:42:44<2:20:31,  1.34s/it]
 90%|████████▉ | 55634/61904 [5:42:46<2:20:39,  1.35s/it]
 90%|████████▉ | 55635/61904 [5:42:47<2:20:03,  1.34s/it]
 90%|████████▉ | 55636/61904 [5:42:48<2:18:12,  1.32s/it]
 90%|████████▉ | 55637/61904 [5:42:50<2:17:58,  1.32s/it]
 90%|████████▉ | 55638/61904 [5:42:51<2:21:30,  1.36s/it]
 90%|████████▉ | 55639/61904 [5:42:53<2:26:14,  1.40s/it]
 90%|████████▉ | 55640/61904 [5:42:54<2:24:41,  1.39s/it]
                                                         
{'loss': 2.4287, 'learning_rate': 1.101516919486581e-07, 'epoch': 14.38}

 90%|████████▉ | 55640/61904 [5:42:54<2:24:41,  1.39s/it]
 90%|████████▉ | 55641/61904 [5:42:55<2:22:29,  1.37s/it]
 90%|████████▉ | 55642/61904 [5:42:57<2:24:41,  1.39s/it]
 90%|████████▉ | 55643/61904 [5:42:58<2:26:15,  1.40s/it]
 90%|████████▉ | 55644/61904 [5:43:00<2:24:34,  1.39s/it]
 90%|████████▉ | 55645/61904 [5:43:01<2:22:11,  1.36s/it]
 90%|████████▉ | 55646/61904 [5:43:02<2:23:01,  1.37s/it]
 90%|████████▉ | 55647/61904 [5:43:04<2:21:29,  1.36s/it]
 90%|████████▉ | 55648/61904 [5:43:05<2:22:21,  1.37s/it]
 90%|████████▉ | 55649/61904 [5:43:06<2:20:41,  1.35s/it]
 90%|████████▉ | 55650/61904 [5:43:08<2:18:25,  1.33s/it]
 90%|████████▉ | 55651/61904 [5:43:09<2:19:06,  1.33s/it]
 90%|████████▉ | 55652/61904 [5:43:10<2:21:01,  1.35s/it]
 90%|████████▉ | 55653/61904 [5:43:12<2:19:24,  1.34s/it]
 90%|████████▉ | 55654/61904 [5:43:13<2:21:31,  1.36s/it]
 90%|████████▉ | 55655/61904 [5:43:15<2:26:07,  1.40s/it]
 90%|████████▉ | 55656/61904 [5:43:16<2:23:07,  1.37s/it]
 90%|████████▉ | 55657/61904 [5:43:17<2:20:28,  1.35s/it]
 90%|████████▉ | 55658/61904 [5:43:19<2:21:12,  1.36s/it]
 90%|████████▉ | 55659/61904 [5:43:20<2:23:00,  1.37s/it]
 90%|████████▉ | 55660/61904 [5:43:21<2:22:27,  1.37s/it]
                                                         
{'loss': 2.441, 'learning_rate': 1.1011927913911578e-07, 'epoch': 14.39}

 90%|████████▉ | 55660/61904 [5:43:21<2:22:27,  1.37s/it]
 90%|████████▉ | 55661/61904 [5:43:23<2:23:20,  1.38s/it]
 90%|████████▉ | 55662/61904 [5:43:24<2:26:56,  1.41s/it]
 90%|████████▉ | 55663/61904 [5:43:26<2:29:29,  1.44s/it]
 90%|████████▉ | 55664/61904 [5:43:27<2:28:37,  1.43s/it]
 90%|████████▉ | 55665/61904 [5:43:28<2:27:39,  1.42s/it]
 90%|████████▉ | 55666/61904 [5:43:30<2:28:47,  1.43s/it]
 90%|████████▉ | 55667/61904 [5:43:31<2:26:27,  1.41s/it]
 90%|████████▉ | 55668/61904 [5:43:33<2:26:36,  1.41s/it]
 90%|████████▉ | 55669/61904 [5:43:34<2:25:36,  1.40s/it]
 90%|████████▉ | 55670/61904 [5:43:36<2:26:42,  1.41s/it]
 90%|████████▉ | 55671/61904 [5:43:37<2:27:24,  1.42s/it]
 90%|████████▉ | 55672/61904 [5:43:38<2:28:06,  1.43s/it]
 90%|████████▉ | 55673/61904 [5:43:40<2:26:29,  1.41s/it]
 90%|████████▉ | 55674/61904 [5:43:41<2:24:12,  1.39s/it]
 90%|████████▉ | 55675/61904 [5:43:42<2:22:13,  1.37s/it]
 90%|████████▉ | 55676/61904 [5:43:44<2:22:14,  1.37s/it]
 90%|████████▉ | 55677/61904 [5:43:45<2:23:51,  1.39s/it]
 90%|████████▉ | 55678/61904 [5:43:47<2:24:46,  1.40s/it]
 90%|████████▉ | 55679/61904 [5:43:48<2:22:01,  1.37s/it]
 90%|████████▉ | 55680/61904 [5:43:49<2:25:29,  1.40s/it]
                                                         
{'loss': 2.467, 'learning_rate': 1.1008686632957344e-07, 'epoch': 14.39}

 90%|████████▉ | 55680/61904 [5:43:49<2:25:29,  1.40s/it]
 90%|████████▉ | 55681/61904 [5:43:51<2:28:53,  1.44s/it]
 90%|████████▉ | 55682/61904 [5:43:52<2:24:03,  1.39s/it]
 90%|████████▉ | 55683/61904 [5:43:54<2:22:38,  1.38s/it]
 90%|████████▉ | 55684/61904 [5:43:55<2:24:37,  1.40s/it]
 90%|████████▉ | 55685/61904 [5:43:57<2:27:43,  1.43s/it]
 90%|████████▉ | 55686/61904 [5:43:58<2:26:16,  1.41s/it]
 90%|████████▉ | 55687/61904 [5:43:59<2:23:37,  1.39s/it]
 90%|████████▉ | 55688/61904 [5:44:01<2:27:29,  1.42s/it]
 90%|████████▉ | 55689/61904 [5:44:02<2:27:14,  1.42s/it]
 90%|████████▉ | 55690/61904 [5:44:04<2:26:05,  1.41s/it]
 90%|████████▉ | 55691/61904 [5:44:05<2:27:24,  1.42s/it]
 90%|████████▉ | 55692/61904 [5:44:06<2:23:04,  1.38s/it]
 90%|████████▉ | 55693/61904 [5:44:08<2:26:37,  1.42s/it]
 90%|████████▉ | 55694/61904 [5:44:09<2:27:18,  1.42s/it]
 90%|████████▉ | 55695/61904 [5:44:11<2:27:20,  1.42s/it]
 90%|████████▉ | 55696/61904 [5:44:12<2:24:00,  1.39s/it]
 90%|████████▉ | 55697/61904 [5:44:13<2:26:37,  1.42s/it]
 90%|████████▉ | 55698/61904 [5:44:15<2:28:21,  1.43s/it]
 90%|████████▉ | 55699/61904 [5:44:16<2:25:24,  1.41s/it]
 90%|████████▉ | 55700/61904 [5:44:18<2:22:11,  1.38s/it]
                                                         
{'loss': 2.4228, 'learning_rate': 1.1005445352003112e-07, 'epoch': 14.4}

 90%|████████▉ | 55700/61904 [5:44:18<2:22:11,  1.38s/it]
 90%|████████▉ | 55701/61904 [5:44:19<2:21:56,  1.37s/it]
 90%|████████▉ | 55702/61904 [5:44:20<2:25:36,  1.41s/it]
 90%|████████▉ | 55703/61904 [5:44:22<2:21:20,  1.37s/it]
 90%|████████▉ | 55704/61904 [5:44:23<2:27:14,  1.42s/it]
 90%|████████▉ | 55705/61904 [5:44:25<2:26:00,  1.41s/it]
 90%|████████▉ | 55706/61904 [5:44:26<2:23:41,  1.39s/it]
 90%|████████▉ | 55707/61904 [5:44:27<2:20:57,  1.36s/it]
 90%|████████▉ | 55708/61904 [5:44:29<2:21:46,  1.37s/it]
 90%|████████▉ | 55709/61904 [5:44:30<2:21:16,  1.37s/it]
 90%|████████▉ | 55710/61904 [5:44:32<2:28:56,  1.44s/it]
 90%|████████▉ | 55711/61904 [5:44:33<2:29:38,  1.45s/it]
 90%|████████▉ | 55712/61904 [5:44:35<2:29:05,  1.44s/it]
 90%|████████▉ | 55713/61904 [5:44:36<2:29:34,  1.45s/it]
 90%|█████████ | 55714/61904 [5:44:37<2:23:18,  1.39s/it]
 90%|█████████ | 55715/61904 [5:44:39<2:22:25,  1.38s/it]
 90%|█████████ | 55716/61904 [5:44:40<2:20:11,  1.36s/it]
 90%|█████████ | 55717/61904 [5:44:41<2:25:09,  1.41s/it]
 90%|█████████ | 55718/61904 [5:44:43<2:26:10,  1.42s/it]
 90%|█████████ | 55719/61904 [5:44:44<2:30:36,  1.46s/it]
 90%|█████████ | 55720/61904 [5:44:46<2:28:46,  1.44s/it]
                                                         
{'loss': 2.4338, 'learning_rate': 1.1002204071048878e-07, 'epoch': 14.4}

 90%|█████████ | 55720/61904 [5:44:46<2:28:46,  1.44s/it]
 90%|█████████ | 55721/61904 [5:44:47<2:33:23,  1.49s/it]
 90%|█████████ | 55722/61904 [5:44:49<2:28:25,  1.44s/it]
 90%|█████████ | 55723/61904 [5:44:50<2:25:39,  1.41s/it]
 90%|█████████ | 55724/61904 [5:44:51<2:21:01,  1.37s/it]
 90%|█████████ | 55725/61904 [5:44:53<2:22:40,  1.39s/it]
 90%|█████████ | 55726/61904 [5:44:54<2:21:45,  1.38s/it]
 90%|█████████ | 55727/61904 [5:44:55<2:20:28,  1.36s/it]
 90%|█████████ | 55728/61904 [5:44:57<2:20:04,  1.36s/it]
 90%|█████████ | 55729/61904 [5:44:58<2:21:47,  1.38s/it]
 90%|█████████ | 55730/61904 [5:45:00<2:24:08,  1.40s/it]
 90%|█████████ | 55731/61904 [5:45:01<2:21:58,  1.38s/it]
 90%|█████████ | 55732/61904 [5:45:02<2:23:19,  1.39s/it]
 90%|█████████ | 55733/61904 [5:45:04<2:23:00,  1.39s/it]
 90%|█████████ | 55734/61904 [5:45:05<2:25:39,  1.42s/it]
 90%|█████████ | 55735/61904 [5:45:07<2:22:39,  1.39s/it]
 90%|█████████ | 55736/61904 [5:45:08<2:18:57,  1.35s/it]
 90%|█████████ | 55737/61904 [5:45:09<2:24:23,  1.40s/it]
 90%|█████████ | 55738/61904 [5:45:11<2:24:28,  1.41s/it]
 90%|█████████ | 55739/61904 [5:45:12<2:22:35,  1.39s/it]
 90%|█████████ | 55740/61904 [5:45:14<2:26:15,  1.42s/it]
                                                         
{'loss': 2.4264, 'learning_rate': 1.0998962790094645e-07, 'epoch': 14.41}

 90%|█████████ | 55740/61904 [5:45:14<2:26:15,  1.42s/it]
 90%|█████████ | 55741/61904 [5:45:15<2:26:08,  1.42s/it]
 90%|█████████ | 55742/61904 [5:45:17<2:25:13,  1.41s/it]
 90%|█████████ | 55743/61904 [5:45:18<2:24:03,  1.40s/it]
 90%|█████████ | 55744/61904 [5:45:19<2:27:02,  1.43s/it]
 90%|█████████ | 55745/61904 [5:45:21<2:21:40,  1.38s/it]
 90%|█████████ | 55746/61904 [5:45:22<2:21:51,  1.38s/it]
 90%|█████████ | 55747/61904 [5:45:23<2:23:17,  1.40s/it]
 90%|█████████ | 55748/61904 [5:45:25<2:21:37,  1.38s/it]
 90%|█████████ | 55749/61904 [5:45:26<2:20:07,  1.37s/it]
 90%|█████████ | 55750/61904 [5:45:28<2:22:10,  1.39s/it]
 90%|█████████ | 55751/61904 [5:45:29<2:20:17,  1.37s/it]
 90%|█████████ | 55752/61904 [5:45:30<2:20:09,  1.37s/it]
 90%|█████████ | 55753/61904 [5:45:32<2:23:25,  1.40s/it]
 90%|█████████ | 55754/61904 [5:45:33<2:26:31,  1.43s/it]
 90%|█████████ | 55755/61904 [5:45:35<2:24:39,  1.41s/it]
 90%|█████████ | 55756/61904 [5:45:36<2:25:09,  1.42s/it]
 90%|█████████ | 55757/61904 [5:45:38<2:27:09,  1.44s/it]
 90%|█████████ | 55758/61904 [5:45:39<2:26:42,  1.43s/it]
 90%|█████████ | 55759/61904 [5:45:40<2:24:23,  1.41s/it]
 90%|█████████ | 55760/61904 [5:45:42<2:19:15,  1.36s/it]
                                                         
{'loss': 2.3694, 'learning_rate': 1.0995721509140412e-07, 'epoch': 14.41}

 90%|█████████ | 55760/61904 [5:45:42<2:19:15,  1.36s/it]
 90%|█████████ | 55761/61904 [5:45:43<2:24:28,  1.41s/it]
 90%|█████████ | 55762/61904 [5:45:45<2:25:05,  1.42s/it]
 90%|█████████ | 55763/61904 [5:45:46<2:24:33,  1.41s/it]
 90%|█████████ | 55764/61904 [5:45:47<2:21:24,  1.38s/it]
 90%|█████████ | 55765/61904 [5:45:49<2:25:51,  1.43s/it]
 90%|█████████ | 55766/61904 [5:45:50<2:25:14,  1.42s/it]
 90%|█████████ | 55767/61904 [5:45:51<2:22:19,  1.39s/it]
 90%|█████████ | 55768/61904 [5:45:53<2:19:52,  1.37s/it]
 90%|█████████ | 55769/61904 [5:45:54<2:17:46,  1.35s/it]
 90%|█████████ | 55770/61904 [5:45:55<2:16:11,  1.33s/it]
 90%|█████████ | 55771/61904 [5:45:57<2:15:54,  1.33s/it]
 90%|█████████ | 55772/61904 [5:45:58<2:17:29,  1.35s/it]
 90%|█████████ | 55773/61904 [5:45:59<2:16:43,  1.34s/it]
 90%|█████████ | 55774/61904 [5:46:01<2:20:54,  1.38s/it]
 90%|█████████ | 55775/61904 [5:46:02<2:22:27,  1.39s/it]
 90%|█████████ | 55776/61904 [5:46:04<2:25:37,  1.43s/it]
 90%|█████████ | 55777/61904 [5:46:05<2:23:14,  1.40s/it]
 90%|█████████ | 55778/61904 [5:46:07<2:23:08,  1.40s/it]
 90%|█████████ | 55779/61904 [5:46:08<2:25:14,  1.42s/it]
 90%|█████████ | 55780/61904 [5:46:10<2:27:04,  1.44s/it]
                                                         
{'loss': 2.4507, 'learning_rate': 1.0992480228186179e-07, 'epoch': 14.42}

 90%|█████████ | 55780/61904 [5:46:10<2:27:04,  1.44s/it]
 90%|█████████ | 55781/61904 [5:46:11<2:29:44,  1.47s/it]
 90%|█████████ | 55782/61904 [5:46:12<2:26:30,  1.44s/it]
 90%|█████████ | 55783/61904 [5:46:14<2:24:55,  1.42s/it]
 90%|█████████ | 55784/61904 [5:46:15<2:25:06,  1.42s/it]
 90%|█████████ | 55785/61904 [5:46:17<2:22:27,  1.40s/it]
 90%|█████████ | 55786/61904 [5:46:18<2:25:10,  1.42s/it]
 90%|█████████ | 55787/61904 [5:46:19<2:25:16,  1.42s/it]
 90%|█████████ | 55788/61904 [5:46:21<2:25:52,  1.43s/it]
 90%|█████████ | 55789/61904 [5:46:22<2:23:18,  1.41s/it]
 90%|█████████ | 55790/61904 [5:46:24<2:20:05,  1.37s/it]
 90%|█████████ | 55791/61904 [5:46:25<2:23:21,  1.41s/it]
 90%|█████████ | 55792/61904 [5:46:26<2:24:18,  1.42s/it]
 90%|█████████ | 55793/61904 [5:46:28<2:29:54,  1.47s/it]
 90%|█████████ | 55794/61904 [5:46:30<2:33:48,  1.51s/it]
 90%|█████████ | 55795/61904 [5:46:31<2:27:19,  1.45s/it]
 90%|█████████ | 55796/61904 [5:46:32<2:22:20,  1.40s/it]
 90%|█████████ | 55797/61904 [5:46:34<2:24:52,  1.42s/it]
 90%|█████████ | 55798/61904 [5:46:35<2:20:04,  1.38s/it]
 90%|█████████ | 55799/61904 [5:46:36<2:20:15,  1.38s/it]
 90%|█████████ | 55800/61904 [5:46:38<2:22:50,  1.40s/it]
                                                         
{'loss': 2.4463, 'learning_rate': 1.0989238947231945e-07, 'epoch': 14.42}

 90%|█████████ | 55800/61904 [5:46:38<2:22:50,  1.40s/it]
 90%|█████████ | 55801/61904 [5:46:39<2:19:27,  1.37s/it]
 90%|█████████ | 55802/61904 [5:46:40<2:17:51,  1.36s/it]
 90%|█████████ | 55803/61904 [5:46:42<2:18:44,  1.36s/it]
 90%|█████████ | 55804/61904 [5:46:43<2:24:55,  1.43s/it]
 90%|█████████ | 55805/61904 [5:46:45<2:25:05,  1.43s/it]
 90%|█████████ | 55806/61904 [5:46:46<2:29:53,  1.47s/it]
 90%|█████████ | 55807/61904 [5:46:48<2:27:32,  1.45s/it]
 90%|█████████ | 55808/61904 [5:46:49<2:24:03,  1.42s/it]
 90%|█████████ | 55809/61904 [5:46:51<2:24:39,  1.42s/it]
 90%|█████████ | 55810/61904 [5:46:52<2:21:17,  1.39s/it]
 90%|█████████ | 55811/61904 [5:46:53<2:22:24,  1.40s/it]
 90%|█████████ | 55812/61904 [5:46:55<2:24:17,  1.42s/it]
 90%|█████████ | 55813/61904 [5:46:56<2:24:05,  1.42s/it]
 90%|█████████ | 55814/61904 [5:46:58<2:27:59,  1.46s/it]
 90%|█████████ | 55815/61904 [5:46:59<2:27:46,  1.46s/it]
 90%|█████████ | 55816/61904 [5:47:01<2:28:25,  1.46s/it]
 90%|█████████ | 55817/61904 [5:47:02<2:32:46,  1.51s/it]
 90%|█████████ | 55818/61904 [5:47:04<2:29:16,  1.47s/it]
 90%|█████████ | 55819/61904 [5:47:05<2:25:43,  1.44s/it]
 90%|█████████ | 55820/61904 [5:47:06<2:24:13,  1.42s/it]
                                                         
{'loss': 2.4241, 'learning_rate': 1.0985997666277713e-07, 'epoch': 14.43}

 90%|█████████ | 55820/61904 [5:47:06<2:24:13,  1.42s/it]
 90%|█████████ | 55821/61904 [5:47:08<2:22:06,  1.40s/it]
 90%|█████████ | 55822/61904 [5:47:09<2:19:03,  1.37s/it]
 90%|█████████ | 55823/61904 [5:47:11<2:21:02,  1.39s/it]
 90%|█████████ | 55824/61904 [5:47:12<2:20:45,  1.39s/it]
 90%|█████████ | 55825/61904 [5:47:13<2:23:56,  1.42s/it]
 90%|█████████ | 55826/61904 [5:47:15<2:26:56,  1.45s/it]
 90%|█████████ | 55827/61904 [5:47:16<2:24:36,  1.43s/it]
 90%|█████████ | 55828/61904 [5:47:18<2:21:40,  1.40s/it]
 90%|█████████ | 55829/61904 [5:47:19<2:17:33,  1.36s/it]
 90%|█████████ | 55830/61904 [5:47:20<2:17:51,  1.36s/it]
 90%|█████████ | 55831/61904 [5:47:22<2:19:45,  1.38s/it]
 90%|█████████ | 55832/61904 [5:47:23<2:22:02,  1.40s/it]
 90%|█████████ | 55833/61904 [5:47:25<2:23:28,  1.42s/it]
 90%|█████████ | 55834/61904 [5:47:26<2:22:56,  1.41s/it]
 90%|█████████ | 55835/61904 [5:47:27<2:22:07,  1.41s/it]
 90%|█████████ | 55836/61904 [5:47:29<2:24:31,  1.43s/it]
 90%|█████████ | 55837/61904 [5:47:30<2:20:36,  1.39s/it]
 90%|█████████ | 55838/61904 [5:47:31<2:16:37,  1.35s/it]
 90%|█████████ | 55839/61904 [5:47:33<2:21:15,  1.40s/it]
 90%|█████████ | 55840/61904 [5:47:34<2:22:03,  1.41s/it]
                                                         
{'loss': 2.4437, 'learning_rate': 1.0982756385323479e-07, 'epoch': 14.43}

 90%|█████████ | 55840/61904 [5:47:34<2:22:03,  1.41s/it]
 90%|█████████ | 55841/61904 [5:47:36<2:20:01,  1.39s/it]
 90%|█████████ | 55842/61904 [5:47:37<2:20:28,  1.39s/it]
 90%|█████████ | 55843/61904 [5:47:39<2:21:11,  1.40s/it]
 90%|█████████ | 55844/61904 [5:47:40<2:23:04,  1.42s/it]
 90%|█████████ | 55845/61904 [5:47:41<2:20:13,  1.39s/it]
 90%|█████████ | 55846/61904 [5:47:43<2:20:15,  1.39s/it]
 90%|█████████ | 55847/61904 [5:47:44<2:27:00,  1.46s/it]
 90%|█████████ | 55848/61904 [5:47:46<2:25:13,  1.44s/it]
 90%|█████████ | 55849/61904 [5:47:47<2:24:42,  1.43s/it]
 90%|█████████ | 55850/61904 [5:47:48<2:20:12,  1.39s/it]
 90%|█████████ | 55851/61904 [5:47:50<2:18:14,  1.37s/it]
 90%|█████████ | 55852/61904 [5:47:52<2:28:59,  1.48s/it]
 90%|█████████ | 55853/61904 [5:47:53<2:25:25,  1.44s/it]
 90%|█████████ | 55854/61904 [5:47:54<2:21:51,  1.41s/it]
 90%|█████████ | 55855/61904 [5:47:56<2:23:22,  1.42s/it]
 90%|█████████ | 55856/61904 [5:47:57<2:19:11,  1.38s/it]
 90%|█████████ | 55857/61904 [5:47:58<2:21:05,  1.40s/it]
 90%|█████████ | 55858/61904 [5:48:00<2:22:10,  1.41s/it]
 90%|█████████ | 55859/61904 [5:48:01<2:20:33,  1.40s/it]
 90%|█████████ | 55860/61904 [5:48:03<2:24:33,  1.43s/it]
                                                         
{'loss': 2.4293, 'learning_rate': 1.0979515104369246e-07, 'epoch': 14.44}

 90%|█████████ | 55860/61904 [5:48:03<2:24:33,  1.43s/it]
 90%|█████████ | 55861/61904 [5:48:04<2:20:58,  1.40s/it]
 90%|█████████ | 55862/61904 [5:48:05<2:19:43,  1.39s/it]
 90%|█████████ | 55863/61904 [5:48:07<2:23:04,  1.42s/it]
 90%|█████████ | 55864/61904 [5:48:08<2:19:31,  1.39s/it]
 90%|█████████ | 55865/61904 [5:48:10<2:17:38,  1.37s/it]
 90%|█████████ | 55866/61904 [5:48:11<2:18:59,  1.38s/it]
 90%|█████████ | 55867/61904 [5:48:12<2:21:14,  1.40s/it]
 90%|█████████ | 55868/61904 [5:48:14<2:22:57,  1.42s/it]
 90%|█████████ | 55869/61904 [5:48:15<2:24:59,  1.44s/it]
 90%|█████████ | 55870/61904 [5:48:17<2:23:06,  1.42s/it]
 90%|█████████ | 55871/61904 [5:48:18<2:21:51,  1.41s/it]
 90%|█████████ | 55872/61904 [5:48:19<2:19:20,  1.39s/it]
 90%|█████████ | 55873/61904 [5:48:21<2:20:04,  1.39s/it]
 90%|█████████ | 55874/61904 [5:48:22<2:20:00,  1.39s/it]
 90%|█████████ | 55875/61904 [5:48:24<2:20:11,  1.40s/it]
 90%|█████████ | 55876/61904 [5:48:25<2:19:42,  1.39s/it]
 90%|█████████ | 55877/61904 [5:48:27<2:24:48,  1.44s/it]
 90%|█████████ | 55878/61904 [5:48:28<2:22:07,  1.42s/it]
 90%|█████████ | 55879/61904 [5:48:29<2:24:47,  1.44s/it]
 90%|█████████ | 55880/61904 [5:48:31<2:24:10,  1.44s/it]
                                                         
{'loss': 2.4539, 'learning_rate': 1.0976273823415014e-07, 'epoch': 14.44}

 90%|█████████ | 55880/61904 [5:48:31<2:24:10,  1.44s/it]
 90%|█████████ | 55881/61904 [5:48:32<2:25:26,  1.45s/it]
 90%|█████████ | 55882/61904 [5:48:34<2:22:02,  1.42s/it]
 90%|█████████ | 55883/61904 [5:48:35<2:19:30,  1.39s/it]
 90%|█████████ | 55884/61904 [5:48:36<2:18:21,  1.38s/it]
 90%|█████████ | 55885/61904 [5:48:38<2:17:10,  1.37s/it]
 90%|█████████ | 55886/61904 [5:48:39<2:15:39,  1.35s/it]
 90%|█████████ | 55887/61904 [5:48:40<2:18:00,  1.38s/it]
 90%|█████████ | 55888/61904 [5:48:42<2:22:46,  1.42s/it]
 90%|█████████ | 55889/61904 [5:48:44<2:26:20,  1.46s/it]
 90%|█████████ | 55890/61904 [5:48:45<2:25:58,  1.46s/it]
 90%|█████████ | 55891/61904 [5:48:46<2:27:15,  1.47s/it]
 90%|█████████ | 55892/61904 [5:48:48<2:20:04,  1.40s/it]
 90%|█████████ | 55893/61904 [5:48:49<2:20:52,  1.41s/it]
 90%|█████████ | 55894/61904 [5:48:50<2:19:59,  1.40s/it]
 90%|█████████ | 55895/61904 [5:48:52<2:16:55,  1.37s/it]
 90%|█████████ | 55896/61904 [5:48:53<2:20:27,  1.40s/it]
 90%|█████████ | 55897/61904 [5:48:55<2:21:18,  1.41s/it]
 90%|█████████ | 55898/61904 [5:48:56<2:18:09,  1.38s/it]
 90%|█████████ | 55899/61904 [5:48:58<2:22:33,  1.42s/it]
 90%|█████████ | 55900/61904 [5:48:59<2:21:54,  1.42s/it]
                                                         
{'loss': 2.444, 'learning_rate': 1.097303254246078e-07, 'epoch': 14.45}

 90%|█████████ | 55900/61904 [5:48:59<2:21:54,  1.42s/it]
 90%|█████████ | 55901/61904 [5:49:00<2:22:02,  1.42s/it]
 90%|█████████ | 55902/61904 [5:49:02<2:21:05,  1.41s/it]
 90%|█████████ | 55903/61904 [5:49:03<2:23:37,  1.44s/it]
 90%|█████████ | 55904/61904 [5:49:05<2:19:31,  1.40s/it]
 90%|█████████ | 55905/61904 [5:49:06<2:21:18,  1.41s/it]
 90%|█████████ | 55906/61904 [5:49:07<2:23:25,  1.43s/it]
 90%|█████████ | 55907/61904 [5:49:09<2:23:33,  1.44s/it]
 90%|█████████ | 55908/61904 [5:49:10<2:24:54,  1.45s/it]
 90%|█████████ | 55909/61904 [5:49:12<2:22:57,  1.43s/it]
 90%|█████████ | 55910/61904 [5:49:13<2:19:41,  1.40s/it]
 90%|█████████ | 55911/61904 [5:49:15<2:19:39,  1.40s/it]
 90%|█████████ | 55912/61904 [5:49:16<2:19:13,  1.39s/it]
 90%|█████████ | 55913/61904 [5:49:17<2:21:09,  1.41s/it]
 90%|█████████ | 55914/61904 [5:49:19<2:21:13,  1.41s/it]
 90%|█████████ | 55915/61904 [5:49:20<2:22:04,  1.42s/it]
 90%|█████████ | 55916/61904 [5:49:22<2:20:42,  1.41s/it]
 90%|█████████ | 55917/61904 [5:49:23<2:19:00,  1.39s/it]
 90%|█████████ | 55918/61904 [5:49:25<2:23:44,  1.44s/it]
 90%|█████████ | 55919/61904 [5:49:26<2:18:41,  1.39s/it]
 90%|█████████ | 55920/61904 [5:49:27<2:14:56,  1.35s/it]
                                                         
{'loss': 2.4366, 'learning_rate': 1.0969791261506546e-07, 'epoch': 14.45}

 90%|█████████ | 55920/61904 [5:49:27<2:14:56,  1.35s/it]
 90%|█████████ | 55921/61904 [5:49:28<2:12:15,  1.33s/it]
 90%|█████████ | 55922/61904 [5:49:30<2:18:21,  1.39s/it]
 90%|█████████ | 55923/61904 [5:49:31<2:14:47,  1.35s/it]
 90%|█████████ | 55924/61904 [5:49:33<2:17:26,  1.38s/it]
 90%|█████████ | 55925/61904 [5:49:34<2:17:45,  1.38s/it]
 90%|█████████ | 55926/61904 [5:49:35<2:14:54,  1.35s/it]
 90%|█████████ | 55927/61904 [5:49:37<2:18:24,  1.39s/it]
 90%|█████████ | 55928/61904 [5:49:38<2:21:35,  1.42s/it]
 90%|█████████ | 55929/61904 [5:49:40<2:21:35,  1.42s/it]
 90%|█████████ | 55930/61904 [5:49:41<2:19:06,  1.40s/it]
 90%|█████████ | 55931/61904 [5:49:42<2:21:27,  1.42s/it]
 90%|█████████ | 55932/61904 [5:49:44<2:19:42,  1.40s/it]
 90%|█████████ | 55933/61904 [5:49:45<2:19:48,  1.40s/it]
 90%|█████████ | 55934/61904 [5:49:47<2:18:50,  1.40s/it]
 90%|█████████ | 55935/61904 [5:49:48<2:17:29,  1.38s/it]
 90%|█████████ | 55936/61904 [5:49:50<2:25:28,  1.46s/it]
 90%|█████████ | 55937/61904 [5:49:51<2:22:52,  1.44s/it]
 90%|█████████ | 55938/61904 [5:49:52<2:18:48,  1.40s/it]
 90%|█████████ | 55939/61904 [5:49:54<2:19:21,  1.40s/it]
 90%|█████████ | 55940/61904 [5:49:55<2:21:57,  1.43s/it]
                                                         
{'loss': 2.3765, 'learning_rate': 1.0966549980552314e-07, 'epoch': 14.46}

 90%|█████████ | 55940/61904 [5:49:55<2:21:57,  1.43s/it]
 90%|█████████ | 55941/61904 [5:49:57<2:24:01,  1.45s/it]
 90%|█████████ | 55942/61904 [5:49:58<2:23:10,  1.44s/it]
 90%|█████████ | 55943/61904 [5:50:00<2:22:51,  1.44s/it]
 90%|█████████ | 55944/61904 [5:50:01<2:18:11,  1.39s/it]
 90%|█████████ | 55945/61904 [5:50:02<2:16:58,  1.38s/it]
 90%|█████████ | 55946/61904 [5:50:04<2:20:47,  1.42s/it]
 90%|█████████ | 55947/61904 [5:50:05<2:20:16,  1.41s/it]
 90%|█████████ | 55948/61904 [5:50:07<2:22:03,  1.43s/it]
 90%|█████████ | 55949/61904 [5:50:08<2:21:20,  1.42s/it]
 90%|█████████ | 55950/61904 [5:50:09<2:23:49,  1.45s/it]
 90%|█████████ | 55951/61904 [5:50:11<2:18:10,  1.39s/it]
 90%|█████████ | 55952/61904 [5:50:12<2:17:06,  1.38s/it]
 90%|█████████ | 55953/61904 [5:50:14<2:19:45,  1.41s/it]
 90%|█████████ | 55954/61904 [5:50:15<2:15:23,  1.37s/it]
 90%|█████████ | 55955/61904 [5:50:16<2:16:56,  1.38s/it]
 90%|█████████ | 55956/61904 [5:50:17<2:12:03,  1.33s/it]
 90%|█████████ | 55957/61904 [5:50:19<2:12:12,  1.33s/it]
 90%|█████████ | 55958/61904 [5:50:20<2:13:01,  1.34s/it]
 90%|█████████ | 55959/61904 [5:50:22<2:15:23,  1.37s/it]
 90%|█████████ | 55960/61904 [5:50:23<2:16:17,  1.38s/it]
                                                         
{'loss': 2.4172, 'learning_rate': 1.0963308699598081e-07, 'epoch': 14.46}

 90%|█████████ | 55960/61904 [5:50:23<2:16:17,  1.38s/it]
 90%|█████████ | 55961/61904 [5:50:24<2:17:27,  1.39s/it]
 90%|█████████ | 55962/61904 [5:50:26<2:16:11,  1.38s/it]
 90%|█████████ | 55963/61904 [5:50:27<2:15:49,  1.37s/it]
 90%|█████████ | 55964/61904 [5:50:28<2:15:56,  1.37s/it]
 90%|█████████ | 55965/61904 [5:50:30<2:12:36,  1.34s/it]
 90%|█████████ | 55966/61904 [5:50:31<2:19:30,  1.41s/it]
 90%|█████████ | 55967/61904 [5:50:33<2:16:21,  1.38s/it]
 90%|█████████ | 55968/61904 [5:50:34<2:21:01,  1.43s/it]
 90%|█████████ | 55969/61904 [5:50:36<2:21:58,  1.44s/it]
 90%|█████████ | 55970/61904 [5:50:37<2:17:19,  1.39s/it]
 90%|█████████ | 55971/61904 [5:50:38<2:16:17,  1.38s/it]
 90%|█████████ | 55972/61904 [5:50:40<2:16:50,  1.38s/it]
 90%|█████████ | 55973/61904 [5:50:41<2:15:28,  1.37s/it]
 90%|█████████ | 55974/61904 [5:50:42<2:14:57,  1.37s/it]
 90%|█████████ | 55975/61904 [5:50:44<2:17:25,  1.39s/it]
 90%|█████████ | 55976/61904 [5:50:45<2:15:02,  1.37s/it]
 90%|█████████ | 55977/61904 [5:50:46<2:15:35,  1.37s/it]
 90%|█████████ | 55978/61904 [5:50:48<2:19:20,  1.41s/it]
 90%|█████████ | 55979/61904 [5:50:49<2:16:09,  1.38s/it]
 90%|█████████ | 55980/61904 [5:50:51<2:18:14,  1.40s/it]
                                                         
{'loss': 2.4072, 'learning_rate': 1.0960067418643847e-07, 'epoch': 14.47}

 90%|█████████ | 55980/61904 [5:50:51<2:18:14,  1.40s/it]
 90%|█████████ | 55981/61904 [5:50:52<2:17:58,  1.40s/it]
 90%|█████████ | 55982/61904 [5:50:53<2:16:44,  1.39s/it]
 90%|█████████ | 55983/61904 [5:50:55<2:15:44,  1.38s/it]
 90%|█████████ | 55984/61904 [5:50:56<2:13:19,  1.35s/it]
 90%|█████████ | 55985/61904 [5:50:57<2:13:10,  1.35s/it]
 90%|█████████ | 55986/61904 [5:50:59<2:15:18,  1.37s/it]
 90%|█████████ | 55987/61904 [5:51:00<2:15:02,  1.37s/it]
 90%|█████████ | 55988/61904 [5:51:02<2:11:55,  1.34s/it]
 90%|█████████ | 55989/61904 [5:51:03<2:16:24,  1.38s/it]
 90%|█████████ | 55990/61904 [5:51:04<2:13:32,  1.35s/it]
 90%|█████████ | 55991/61904 [5:51:06<2:16:11,  1.38s/it]
 90%|█████████ | 55992/61904 [5:51:07<2:14:14,  1.36s/it]
 90%|█████████ | 55993/61904 [5:51:08<2:14:49,  1.37s/it]
 90%|█████████ | 55994/61904 [5:51:10<2:16:23,  1.38s/it]
 90%|█████████ | 55995/61904 [5:51:11<2:14:24,  1.36s/it]
 90%|█████████ | 55996/61904 [5:51:13<2:15:14,  1.37s/it]
 90%|█████████ | 55997/61904 [5:51:14<2:20:00,  1.42s/it]
 90%|█████████ | 55998/61904 [5:51:15<2:18:06,  1.40s/it]
 90%|█████████ | 55999/61904 [5:51:17<2:13:53,  1.36s/it]
 90%|█████████ | 56000/61904 [5:51:18<2:14:11,  1.36s/it]
                                                         
{'loss': 2.4183, 'learning_rate': 1.0956826137689614e-07, 'epoch': 14.47}

 90%|█████████ | 56000/61904 [5:51:18<2:14:11,  1.36s/it]
 90%|█████████ | 56001/61904 [5:51:20<2:20:23,  1.43s/it]
 90%|█████████ | 56002/61904 [5:51:21<2:16:27,  1.39s/it]
 90%|█████████ | 56003/61904 [5:51:22<2:13:50,  1.36s/it]
 90%|█████████ | 56004/61904 [5:51:24<2:14:11,  1.36s/it]
 90%|█████████ | 56005/61904 [5:51:25<2:14:16,  1.37s/it]
 90%|█████████ | 56006/61904 [5:51:26<2:13:39,  1.36s/it]
 90%|█████████ | 56007/61904 [5:51:28<2:10:49,  1.33s/it]
 90%|█████████ | 56008/61904 [5:51:29<2:13:39,  1.36s/it]
 90%|█████████ | 56009/61904 [5:51:31<2:19:57,  1.42s/it]
 90%|█████████ | 56010/61904 [5:51:32<2:17:26,  1.40s/it]
 90%|█████████ | 56011/61904 [5:51:33<2:16:09,  1.39s/it]
 90%|█████████ | 56012/61904 [5:51:35<2:12:56,  1.35s/it]
 90%|█████████ | 56013/61904 [5:51:36<2:08:29,  1.31s/it]
 90%|█████████ | 56014/61904 [5:51:37<2:07:02,  1.29s/it]
 90%|█████████ | 56015/61904 [5:51:39<2:14:15,  1.37s/it]
 90%|█████████ | 56016/61904 [5:51:40<2:14:50,  1.37s/it]
 90%|█████████ | 56017/61904 [5:51:42<2:20:31,  1.43s/it]
 90%|█████████ | 56018/61904 [5:51:43<2:25:07,  1.48s/it]
 90%|█████████ | 56019/61904 [5:51:45<2:24:20,  1.47s/it]
 90%|█████████ | 56020/61904 [5:51:46<2:27:24,  1.50s/it]
                                                         
{'loss': 2.4149, 'learning_rate': 1.0953584856735381e-07, 'epoch': 14.48}

 90%|█████████ | 56020/61904 [5:51:46<2:27:24,  1.50s/it]
 90%|█████████ | 56021/61904 [5:51:48<2:29:09,  1.52s/it]
 90%|█████████ | 56022/61904 [5:51:49<2:24:02,  1.47s/it]
 90%|█████████ | 56023/61904 [5:51:50<2:20:45,  1.44s/it]
 91%|█████████ | 56024/61904 [5:51:52<2:23:40,  1.47s/it]
 91%|█████████ | 56025/61904 [5:51:53<2:21:44,  1.45s/it]
 91%|█████████ | 56026/61904 [5:51:55<2:20:50,  1.44s/it]
 91%|█████████ | 56027/61904 [5:51:56<2:21:08,  1.44s/it]
 91%|█████████ | 56028/61904 [5:51:58<2:18:30,  1.41s/it]
 91%|█████████ | 56029/61904 [5:51:59<2:16:33,  1.39s/it]
 91%|█████████ | 56030/61904 [5:52:00<2:15:09,  1.38s/it]
 91%|█████████ | 56031/61904 [5:52:02<2:17:59,  1.41s/it]
 91%|█████████ | 56032/61904 [5:52:03<2:14:30,  1.37s/it]
 91%|█████████ | 56033/61904 [5:52:04<2:13:40,  1.37s/it]
 91%|█████████ | 56034/61904 [5:52:06<2:14:23,  1.37s/it]
 91%|█████████ | 56035/61904 [5:52:07<2:12:45,  1.36s/it]
 91%|█████████ | 56036/61904 [5:52:08<2:12:58,  1.36s/it]
 91%|█████████ | 56037/61904 [5:52:10<2:13:30,  1.37s/it]
 91%|█████████ | 56038/61904 [5:52:11<2:09:17,  1.32s/it]
 91%|█████████ | 56039/61904 [5:52:12<2:08:38,  1.32s/it]
 91%|█████████ | 56040/61904 [5:52:14<2:19:57,  1.43s/it]
                                                         
{'loss': 2.4087, 'learning_rate': 1.0950343575781149e-07, 'epoch': 14.48}

 91%|█████████ | 56040/61904 [5:52:14<2:19:57,  1.43s/it]
 91%|█████████ | 56041/61904 [5:52:15<2:18:27,  1.42s/it]
 91%|█████████ | 56042/61904 [5:52:17<2:17:02,  1.40s/it]
 91%|█████████ | 56043/61904 [5:52:18<2:17:09,  1.40s/it]
 91%|█████████ | 56044/61904 [5:52:20<2:16:37,  1.40s/it]
 91%|█████████ | 56045/61904 [5:52:21<2:20:24,  1.44s/it]
 91%|█████████ | 56046/61904 [5:52:23<2:17:38,  1.41s/it]
 91%|█████████ | 56047/61904 [5:52:24<2:23:43,  1.47s/it]
 91%|█████████ | 56048/61904 [5:52:25<2:20:26,  1.44s/it]
 91%|█████████ | 56049/61904 [5:52:27<2:22:27,  1.46s/it]
 91%|█████████ | 56050/61904 [5:52:28<2:21:47,  1.45s/it]
 91%|█████████ | 56051/61904 [5:52:30<2:21:03,  1.45s/it]
 91%|█████████ | 56052/61904 [5:52:31<2:16:43,  1.40s/it]
 91%|█████████ | 56053/61904 [5:52:33<2:15:49,  1.39s/it]
 91%|█████████ | 56054/61904 [5:52:34<2:14:32,  1.38s/it]
 91%|█████████ | 56055/61904 [5:52:35<2:14:14,  1.38s/it]
 91%|█████████ | 56056/61904 [5:52:37<2:10:43,  1.34s/it]
 91%|█████████ | 56057/61904 [5:52:38<2:11:40,  1.35s/it]
 91%|█████████ | 56058/61904 [5:52:39<2:10:19,  1.34s/it]
 91%|█████████ | 56059/61904 [5:52:41<2:13:24,  1.37s/it]
 91%|█████████ | 56060/61904 [5:52:42<2:18:40,  1.42s/it]
                                                         
{'loss': 2.4551, 'learning_rate': 1.0947102294826915e-07, 'epoch': 14.49}

 91%|█████████ | 56060/61904 [5:52:42<2:18:40,  1.42s/it]
 91%|█████████ | 56061/61904 [5:52:44<2:16:39,  1.40s/it]
 91%|█████████ | 56062/61904 [5:52:45<2:16:18,  1.40s/it]
 91%|█████████ | 56063/61904 [5:52:46<2:17:46,  1.42s/it]
 91%|█████████ | 56064/61904 [5:52:48<2:11:49,  1.35s/it]
 91%|█████████ | 56065/61904 [5:52:49<2:12:59,  1.37s/it]
 91%|█████████ | 56066/61904 [5:52:51<2:19:14,  1.43s/it]
 91%|█████████ | 56067/61904 [5:52:52<2:15:13,  1.39s/it]
 91%|█████████ | 56068/61904 [5:52:53<2:19:35,  1.44s/it]
 91%|█████████ | 56069/61904 [5:52:55<2:18:48,  1.43s/it]
 91%|█████████ | 56070/61904 [5:52:56<2:18:57,  1.43s/it]
 91%|█████████ | 56071/61904 [5:52:58<2:20:58,  1.45s/it]
 91%|█████████ | 56072/61904 [5:52:59<2:21:56,  1.46s/it]
 91%|█████████ | 56073/61904 [5:53:01<2:19:09,  1.43s/it]
 91%|█████████ | 56074/61904 [5:53:02<2:19:35,  1.44s/it]
 91%|█████████ | 56075/61904 [5:53:03<2:17:01,  1.41s/it]
 91%|█████████ | 56076/61904 [5:53:05<2:16:39,  1.41s/it]
 91%|█████████ | 56077/61904 [5:53:06<2:22:31,  1.47s/it]
 91%|█████████ | 56078/61904 [5:53:08<2:18:55,  1.43s/it]
 91%|█████████ | 56079/61904 [5:53:09<2:17:12,  1.41s/it]
 91%|█████████ | 56080/61904 [5:53:11<2:22:19,  1.47s/it]
                                                         
{'loss': 2.431, 'learning_rate': 1.0943861013872681e-07, 'epoch': 14.49}

 91%|█████████ | 56080/61904 [5:53:11<2:22:19,  1.47s/it]
 91%|█████████ | 56081/61904 [5:53:12<2:22:50,  1.47s/it]
 91%|█████████ | 56082/61904 [5:53:14<2:20:03,  1.44s/it]
 91%|█████████ | 56083/61904 [5:53:15<2:19:28,  1.44s/it]
 91%|█████████ | 56084/61904 [5:53:16<2:15:40,  1.40s/it]
 91%|█████████ | 56085/61904 [5:53:18<2:17:55,  1.42s/it]
 91%|█████████ | 56086/61904 [5:53:19<2:15:23,  1.40s/it]
 91%|█████████ | 56087/61904 [5:53:20<2:13:11,  1.37s/it]
 91%|█████████ | 56088/61904 [5:53:22<2:15:50,  1.40s/it]
 91%|█████████ | 56089/61904 [5:53:23<2:12:36,  1.37s/it]
 91%|█████████ | 56090/61904 [5:53:25<2:15:27,  1.40s/it]
 91%|█████████ | 56091/61904 [5:53:26<2:17:21,  1.42s/it]
 91%|█████████ | 56092/61904 [5:53:27<2:12:22,  1.37s/it]
 91%|█████████ | 56093/61904 [5:53:29<2:13:14,  1.38s/it]
 91%|█████████ | 56094/61904 [5:53:30<2:17:12,  1.42s/it]
 91%|█████████ | 56095/61904 [5:53:32<2:20:35,  1.45s/it]
 91%|█████████ | 56096/61904 [5:53:33<2:18:13,  1.43s/it]
 91%|█████████ | 56097/61904 [5:53:34<2:14:39,  1.39s/it]
 91%|█████████ | 56098/61904 [5:53:36<2:15:20,  1.40s/it]
 91%|█████████ | 56099/61904 [5:53:37<2:14:14,  1.39s/it]
 91%|█████████ | 56100/61904 [5:53:39<2:13:07,  1.38s/it]
                                                         
{'loss': 2.4769, 'learning_rate': 1.0940619732918449e-07, 'epoch': 14.5}

 91%|█████████ | 56100/61904 [5:53:39<2:13:07,  1.38s/it]
 91%|█████████ | 56101/61904 [5:53:40<2:16:02,  1.41s/it]
 91%|█████████ | 56102/61904 [5:53:41<2:14:36,  1.39s/it]
 91%|█████████ | 56103/61904 [5:53:43<2:18:30,  1.43s/it]
 91%|█████████ | 56104/61904 [5:53:44<2:15:15,  1.40s/it]
 91%|█████████ | 56105/61904 [5:53:46<2:14:10,  1.39s/it]
 91%|█████████ | 56106/61904 [5:53:47<2:15:08,  1.40s/it]
 91%|█████████ | 56107/61904 [5:53:48<2:15:03,  1.40s/it]
 91%|█████████ | 56108/61904 [5:53:50<2:12:18,  1.37s/it]
 91%|█████████ | 56109/61904 [5:53:51<2:09:05,  1.34s/it]
 91%|█████████ | 56110/61904 [5:53:52<2:11:55,  1.37s/it]
 91%|█████████ | 56111/61904 [5:53:54<2:10:22,  1.35s/it]
 91%|█████████ | 56112/61904 [5:53:55<2:10:00,  1.35s/it]
 91%|█████████ | 56113/61904 [5:53:57<2:13:38,  1.38s/it]
 91%|█████████ | 56114/61904 [5:53:58<2:15:30,  1.40s/it]
 91%|█████████ | 56115/61904 [5:54:00<2:16:55,  1.42s/it]
 91%|█████████ | 56116/61904 [5:54:01<2:17:04,  1.42s/it]
 91%|█████████ | 56117/61904 [5:54:02<2:15:29,  1.40s/it]
 91%|█████████ | 56118/61904 [5:54:04<2:17:29,  1.43s/it]
 91%|█████████ | 56119/61904 [5:54:05<2:16:42,  1.42s/it]
 91%|█████████ | 56120/61904 [5:54:06<2:12:23,  1.37s/it]
                                                         
{'loss': 2.4141, 'learning_rate': 1.0937378451964216e-07, 'epoch': 14.5}

 91%|█████████ | 56120/61904 [5:54:06<2:12:23,  1.37s/it]
 91%|█████████ | 56121/61904 [5:54:08<2:12:17,  1.37s/it]
 91%|█████████ | 56122/61904 [5:54:09<2:13:21,  1.38s/it]
 91%|█████████ | 56123/61904 [5:54:11<2:14:15,  1.39s/it]
 91%|█████████ | 56124/61904 [5:54:12<2:10:31,  1.35s/it]
 91%|█████████ | 56125/61904 [5:54:13<2:15:21,  1.41s/it]
 91%|█████████ | 56126/61904 [5:54:15<2:17:31,  1.43s/it]
 91%|█████████ | 56127/61904 [5:54:16<2:13:36,  1.39s/it]
 91%|█████████ | 56128/61904 [5:54:18<2:12:23,  1.38s/it]
 91%|█████████ | 56129/61904 [5:54:19<2:15:22,  1.41s/it]
 91%|█████████ | 56130/61904 [5:54:21<2:21:20,  1.47s/it]
 91%|█████████ | 56131/61904 [5:54:22<2:17:48,  1.43s/it]
 91%|█████████ | 56132/61904 [5:54:23<2:18:25,  1.44s/it]
 91%|█████████ | 56133/61904 [5:54:25<2:16:53,  1.42s/it]
 91%|█████████ | 56134/61904 [5:54:26<2:11:14,  1.36s/it]
 91%|█████████ | 56135/61904 [5:54:27<2:08:58,  1.34s/it]
 91%|█████████ | 56136/61904 [5:54:29<2:08:21,  1.34s/it]
 91%|█████████ | 56137/61904 [5:54:30<2:11:43,  1.37s/it]
 91%|█████████ | 56138/61904 [5:54:32<2:15:26,  1.41s/it]
 91%|█████████ | 56139/61904 [5:54:33<2:14:51,  1.40s/it]
 91%|█████████ | 56140/61904 [5:54:35<2:17:35,  1.43s/it]
                                                         
{'loss': 2.4434, 'learning_rate': 1.0934137171009982e-07, 'epoch': 14.51}

 91%|█████████ | 56140/61904 [5:54:35<2:17:35,  1.43s/it]
 91%|█████████ | 56141/61904 [5:54:36<2:15:29,  1.41s/it]
 91%|█████████ | 56142/61904 [5:54:37<2:18:04,  1.44s/it]
 91%|█████████ | 56143/61904 [5:54:39<2:15:31,  1.41s/it]
 91%|█████████ | 56144/61904 [5:54:40<2:11:24,  1.37s/it]
 91%|█████████ | 56145/61904 [5:54:41<2:12:45,  1.38s/it]
 91%|█████████ | 56146/61904 [5:54:43<2:11:23,  1.37s/it]
 91%|█████████ | 56147/61904 [5:54:44<2:09:12,  1.35s/it]
 91%|█████████ | 56148/61904 [5:54:46<2:12:40,  1.38s/it]
 91%|█████████ | 56149/61904 [5:54:47<2:10:21,  1.36s/it]
 91%|█████████ | 56150/61904 [5:54:48<2:12:58,  1.39s/it]
 91%|█████████ | 56151/61904 [5:54:50<2:11:30,  1.37s/it]
 91%|█████████ | 56152/61904 [5:54:51<2:11:14,  1.37s/it]
 91%|█████████ | 56153/61904 [5:54:52<2:14:20,  1.40s/it]
 91%|█████████ | 56154/61904 [5:54:54<2:17:48,  1.44s/it]
 91%|█████████ | 56155/61904 [5:54:55<2:14:06,  1.40s/it]
 91%|█████████ | 56156/61904 [5:54:57<2:14:42,  1.41s/it]
 91%|█████████ | 56157/61904 [5:54:58<2:18:22,  1.44s/it]
 91%|█████████ | 56158/61904 [5:55:00<2:13:25,  1.39s/it]
 91%|█████████ | 56159/61904 [5:55:01<2:13:20,  1.39s/it]
 91%|█████████ | 56160/61904 [5:55:02<2:13:11,  1.39s/it]
                                                         
{'loss': 2.4858, 'learning_rate': 1.0930895890055748e-07, 'epoch': 14.51}

 91%|█████████ | 56160/61904 [5:55:02<2:13:11,  1.39s/it]
 91%|█████████ | 56161/61904 [5:55:04<2:12:15,  1.38s/it]
 91%|█████████ | 56162/61904 [5:55:05<2:15:12,  1.41s/it]
 91%|█████████ | 56163/61904 [5:55:07<2:14:19,  1.40s/it]
 91%|█████████ | 56164/61904 [5:55:08<2:15:03,  1.41s/it]
 91%|█████████ | 56165/61904 [5:55:09<2:15:02,  1.41s/it]
 91%|█████████ | 56166/61904 [5:55:11<2:15:50,  1.42s/it]
 91%|█████████ | 56167/61904 [5:55:12<2:21:04,  1.48s/it]
 91%|█████████ | 56168/61904 [5:55:14<2:23:13,  1.50s/it]
 91%|█████████ | 56169/61904 [5:55:15<2:21:54,  1.48s/it]
 91%|█████████ | 56170/61904 [5:55:17<2:19:19,  1.46s/it]
 91%|█████████ | 56171/61904 [5:55:18<2:15:38,  1.42s/it]
 91%|█████████ | 56172/61904 [5:55:19<2:12:27,  1.39s/it]
 91%|█████████ | 56173/61904 [5:55:21<2:08:39,  1.35s/it]
 91%|█████████ | 56174/61904 [5:55:22<2:05:22,  1.31s/it]
 91%|█████████ | 56175/61904 [5:55:23<2:11:48,  1.38s/it]
 91%|█████████ | 56176/61904 [5:55:25<2:08:15,  1.34s/it]
 91%|█████████ | 56177/61904 [5:55:26<2:12:05,  1.38s/it]
 91%|█████████ | 56178/61904 [5:55:27<2:09:02,  1.35s/it]
 91%|█████████ | 56179/61904 [5:55:29<2:08:13,  1.34s/it]
 91%|█████████ | 56180/61904 [5:55:30<2:12:32,  1.39s/it]
                                                         
{'loss': 2.4497, 'learning_rate': 1.0927654609101516e-07, 'epoch': 14.52}

 91%|█████████ | 56180/61904 [5:55:30<2:12:32,  1.39s/it]
 91%|█████████ | 56181/61904 [5:55:32<2:10:13,  1.37s/it]
 91%|█████████ | 56182/61904 [5:55:33<2:13:28,  1.40s/it]
 91%|█████████ | 56183/61904 [5:55:34<2:12:24,  1.39s/it]
 91%|█████████ | 56184/61904 [5:55:36<2:11:26,  1.38s/it]
 91%|█████████ | 56185/61904 [5:55:37<2:14:53,  1.42s/it]
 91%|█████████ | 56186/61904 [5:55:39<2:10:08,  1.37s/it]
 91%|█████████ | 56187/61904 [5:55:40<2:11:26,  1.38s/it]
 91%|█████████ | 56188/61904 [5:55:41<2:10:22,  1.37s/it]
 91%|█████████ | 56189/61904 [5:55:43<2:10:50,  1.37s/it]
 91%|█████████ | 56190/61904 [5:55:44<2:16:44,  1.44s/it]
 91%|█████████ | 56191/61904 [5:55:46<2:14:20,  1.41s/it]
 91%|█████████ | 56192/61904 [5:55:47<2:16:34,  1.43s/it]
 91%|█████████ | 56193/61904 [5:55:49<2:15:07,  1.42s/it]
 91%|█████████ | 56194/61904 [5:55:50<2:13:29,  1.40s/it]
 91%|█████████ | 56195/61904 [5:55:52<2:23:05,  1.50s/it]
 91%|█████████ | 56196/61904 [5:55:53<2:21:52,  1.49s/it]
 91%|█████████ | 56197/61904 [5:55:54<2:16:35,  1.44s/it]
 91%|█████████ | 56198/61904 [5:55:56<2:15:52,  1.43s/it]
 91%|█████████ | 56199/61904 [5:55:57<2:14:07,  1.41s/it]
 91%|█████████ | 56200/61904 [5:55:59<2:14:59,  1.42s/it]
                                                         
{'loss': 2.3597, 'learning_rate': 1.0924413328147283e-07, 'epoch': 14.53}

 91%|█████████ | 56200/61904 [5:55:59<2:14:59,  1.42s/it]
 91%|█████████ | 56201/61904 [5:56:00<2:16:39,  1.44s/it]
 91%|█████████ | 56202/61904 [5:56:02<2:16:24,  1.44s/it]
 91%|█████████ | 56203/61904 [5:56:03<2:14:19,  1.41s/it]
 91%|█████████ | 56204/61904 [5:56:04<2:10:55,  1.38s/it]
 91%|█████████ | 56205/61904 [5:56:06<2:12:09,  1.39s/it]
 91%|█████████ | 56206/61904 [5:56:07<2:18:44,  1.46s/it]
 91%|█████████ | 56207/61904 [5:56:09<2:18:13,  1.46s/it]
 91%|█████████ | 56208/61904 [5:56:10<2:15:03,  1.42s/it]
 91%|█████████ | 56209/61904 [5:56:11<2:09:44,  1.37s/it]
 91%|█████████ | 56210/61904 [5:56:13<2:07:53,  1.35s/it]
 91%|█████████ | 56211/61904 [5:56:14<2:08:32,  1.35s/it]
 91%|█████████ | 56212/61904 [5:56:15<2:09:01,  1.36s/it]
 91%|█████████ | 56213/61904 [5:56:17<2:06:42,  1.34s/it]
 91%|█████████ | 56214/61904 [5:56:18<2:10:19,  1.37s/it]
 91%|█████████ | 56215/61904 [5:56:20<2:18:38,  1.46s/it]
 91%|█████████ | 56216/61904 [5:56:21<2:12:27,  1.40s/it]
 91%|█████████ | 56217/61904 [5:56:22<2:12:17,  1.40s/it]
 91%|█████████ | 56218/61904 [5:56:24<2:12:58,  1.40s/it]
 91%|█████████ | 56219/61904 [5:56:25<2:10:05,  1.37s/it]
 91%|█████████ | 56220/61904 [5:56:26<2:11:18,  1.39s/it]
                                                         
{'loss': 2.4058, 'learning_rate': 1.092117204719305e-07, 'epoch': 14.53}

 91%|█████████ | 56220/61904 [5:56:26<2:11:18,  1.39s/it]
 91%|█████████ | 56221/61904 [5:56:28<2:08:56,  1.36s/it]
 91%|█████████ | 56222/61904 [5:56:29<2:09:12,  1.36s/it]
 91%|█████████ | 56223/61904 [5:56:31<2:10:18,  1.38s/it]
 91%|█████████ | 56224/61904 [5:56:32<2:09:57,  1.37s/it]
 91%|█████████ | 56225/61904 [5:56:33<2:08:10,  1.35s/it]
 91%|█████████ | 56226/61904 [5:56:35<2:06:45,  1.34s/it]
 91%|█████████ | 56227/61904 [5:56:36<2:05:41,  1.33s/it]
 91%|█████████ | 56228/61904 [5:56:37<2:07:36,  1.35s/it]
 91%|█████████ | 56229/61904 [5:56:39<2:11:39,  1.39s/it]
 91%|█████████ | 56230/61904 [5:56:40<2:11:02,  1.39s/it]
 91%|█████████ | 56231/61904 [5:56:41<2:10:55,  1.38s/it]
 91%|█████████ | 56232/61904 [5:56:43<2:12:08,  1.40s/it]
 91%|█████████ | 56233/61904 [5:56:44<2:12:01,  1.40s/it]
 91%|█████████ | 56234/61904 [5:56:46<2:09:45,  1.37s/it]
 91%|█████████ | 56235/61904 [5:56:47<2:13:35,  1.41s/it]
 91%|█████████ | 56236/61904 [5:56:49<2:12:59,  1.41s/it]
 91%|█████████ | 56237/61904 [5:56:50<2:13:27,  1.41s/it]
 91%|█████████ | 56238/61904 [5:56:51<2:09:27,  1.37s/it]
 91%|█████████ | 56239/61904 [5:56:53<2:08:32,  1.36s/it]
 91%|█████████ | 56240/61904 [5:56:54<2:07:58,  1.36s/it]
                                                         
{'loss': 2.4425, 'learning_rate': 1.0917930766238816e-07, 'epoch': 14.54}

 91%|█████████ | 56240/61904 [5:56:54<2:07:58,  1.36s/it]
 91%|█████████ | 56241/61904 [5:56:55<2:07:42,  1.35s/it]
 91%|█████████ | 56242/61904 [5:56:57<2:13:44,  1.42s/it]
 91%|█████████ | 56243/61904 [5:56:58<2:12:15,  1.40s/it]
 91%|█████████ | 56244/61904 [5:57:00<2:17:05,  1.45s/it]
 91%|█████████ | 56245/61904 [5:57:01<2:17:23,  1.46s/it]
 91%|█████████ | 56246/61904 [5:57:03<2:17:27,  1.46s/it]
 91%|█████████ | 56247/61904 [5:57:04<2:14:48,  1.43s/it]
 91%|█████████ | 56248/61904 [5:57:05<2:10:50,  1.39s/it]
 91%|█████████ | 56249/61904 [5:57:07<2:09:10,  1.37s/it]
 91%|█████████ | 56250/61904 [5:57:08<2:12:49,  1.41s/it]
 91%|█████████ | 56251/61904 [5:57:10<2:23:04,  1.52s/it]
 91%|█████████ | 56252/61904 [5:57:11<2:20:33,  1.49s/it]
 91%|█████████ | 56253/61904 [5:57:13<2:15:26,  1.44s/it]
 91%|█████████ | 56254/61904 [5:57:14<2:13:15,  1.42s/it]
 91%|█████████ | 56255/61904 [5:57:15<2:09:26,  1.37s/it]
 91%|█████████ | 56256/61904 [5:57:17<2:08:20,  1.36s/it]
 91%|█████████ | 56257/61904 [5:57:18<2:08:52,  1.37s/it]
 91%|█████████ | 56258/61904 [5:57:19<2:08:48,  1.37s/it]
 91%|█████████ | 56259/61904 [5:57:21<2:11:26,  1.40s/it]
 91%|█████████ | 56260/61904 [5:57:22<2:10:56,  1.39s/it]
                                                         
{'loss': 2.4314, 'learning_rate': 1.0914689485284583e-07, 'epoch': 14.54}

 91%|█████████ | 56260/61904 [5:57:22<2:10:56,  1.39s/it]
 91%|█████████ | 56261/61904 [5:57:24<2:13:49,  1.42s/it]
 91%|█████████ | 56262/61904 [5:57:25<2:13:37,  1.42s/it]
 91%|█████████ | 56263/61904 [5:57:27<2:12:24,  1.41s/it]
 91%|█████████ | 56264/61904 [5:57:28<2:11:28,  1.40s/it]
 91%|█████████ | 56265/61904 [5:57:29<2:12:02,  1.40s/it]
 91%|█████████ | 56266/61904 [5:57:31<2:10:33,  1.39s/it]
 91%|█████████ | 56267/61904 [5:57:32<2:08:30,  1.37s/it]
 91%|█████████ | 56268/61904 [5:57:33<2:08:47,  1.37s/it]
 91%|█████████ | 56269/61904 [5:57:35<2:10:22,  1.39s/it]
 91%|█████████ | 56270/61904 [5:57:36<2:07:53,  1.36s/it]
 91%|█████████ | 56271/61904 [5:57:38<2:08:53,  1.37s/it]
 91%|█████████ | 56272/61904 [5:57:39<2:08:03,  1.36s/it]
 91%|█████████ | 56273/61904 [5:57:40<2:09:54,  1.38s/it]
 91%|█████████ | 56274/61904 [5:57:42<2:05:41,  1.34s/it]
 91%|█████████ | 56275/61904 [5:57:43<2:09:14,  1.38s/it]
 91%|█████████ | 56276/61904 [5:57:45<2:27:02,  1.57s/it]
 91%|█████████ | 56277/61904 [5:57:46<2:17:11,  1.46s/it]
 91%|█████████ | 56278/61904 [5:57:48<2:13:05,  1.42s/it]
 91%|█████████ | 56279/61904 [5:57:49<2:15:00,  1.44s/it]
 91%|█████████ | 56280/61904 [5:57:51<2:16:01,  1.45s/it]
                                                         
{'loss': 2.4842, 'learning_rate': 1.0911448204330351e-07, 'epoch': 14.55}

 91%|█████████ | 56280/61904 [5:57:51<2:16:01,  1.45s/it]
 91%|█████████ | 56281/61904 [5:57:52<2:13:00,  1.42s/it]
 91%|█████████ | 56282/61904 [5:57:53<2:10:17,  1.39s/it]
 91%|█████████ | 56283/61904 [5:57:55<2:13:17,  1.42s/it]
 91%|█████████ | 56284/61904 [5:57:56<2:09:03,  1.38s/it]
 91%|█████████ | 56285/61904 [5:57:57<2:10:02,  1.39s/it]
 91%|█████████ | 56286/61904 [5:57:59<2:11:35,  1.41s/it]
 91%|█████████ | 56287/61904 [5:58:00<2:10:25,  1.39s/it]
 91%|█████████ | 56288/61904 [5:58:02<2:08:57,  1.38s/it]
 91%|█████████ | 56289/61904 [5:58:03<2:15:31,  1.45s/it]
 91%|█████████ | 56290/61904 [5:58:05<2:15:19,  1.45s/it]
 91%|█████████ | 56291/61904 [5:58:06<2:11:38,  1.41s/it]
 91%|█████████ | 56292/61904 [5:58:07<2:12:58,  1.42s/it]
 91%|█████████ | 56293/61904 [5:58:09<2:09:17,  1.38s/it]
 91%|█████████ | 56294/61904 [5:58:10<2:08:06,  1.37s/it]
 91%|█████████ | 56295/61904 [5:58:11<2:07:07,  1.36s/it]
 91%|█████████ | 56296/61904 [5:58:13<2:06:25,  1.35s/it]
 91%|█████████ | 56297/61904 [5:58:14<2:09:01,  1.38s/it]
 91%|█████████ | 56298/61904 [5:58:15<2:07:49,  1.37s/it]
 91%|█████████ | 56299/61904 [5:58:17<2:07:54,  1.37s/it]
 91%|█████████ | 56300/61904 [5:58:18<2:05:59,  1.35s/it]
                                                         
{'loss': 2.4116, 'learning_rate': 1.0908206923376117e-07, 'epoch': 14.55}

 91%|█████████ | 56300/61904 [5:58:18<2:05:59,  1.35s/it]
 91%|█████████ | 56301/61904 [5:58:20<2:09:50,  1.39s/it]
 91%|█████████ | 56302/61904 [5:58:21<2:06:09,  1.35s/it]
 91%|█████████ | 56303/61904 [5:58:22<2:04:28,  1.33s/it]
 91%|█████████ | 56304/61904 [5:58:23<2:04:04,  1.33s/it]
 91%|█████████ | 56305/61904 [5:58:25<2:06:30,  1.36s/it]
 91%|█████████ | 56306/61904 [5:58:26<2:02:54,  1.32s/it]
 91%|█████████ | 56307/61904 [5:58:27<2:04:01,  1.33s/it]
 91%|█████████ | 56308/61904 [5:58:29<2:04:56,  1.34s/it]
 91%|█████████ | 56309/61904 [5:58:30<2:06:16,  1.35s/it]
 91%|█████████ | 56310/61904 [5:58:32<2:05:24,  1.35s/it]
 91%|█████████ | 56311/61904 [5:58:33<2:12:21,  1.42s/it]
 91%|█████████ | 56312/61904 [5:58:34<2:09:00,  1.38s/it]
 91%|█████████ | 56313/61904 [5:58:36<2:08:49,  1.38s/it]
 91%|█████████ | 56314/61904 [5:58:37<2:08:06,  1.38s/it]
 91%|█████████ | 56315/61904 [5:58:38<2:06:32,  1.36s/it]
 91%|█████████ | 56316/61904 [5:58:40<2:05:19,  1.35s/it]
 91%|█████████ | 56317/61904 [5:58:41<2:05:32,  1.35s/it]
 91%|█████████ | 56318/61904 [5:58:43<2:08:25,  1.38s/it]
 91%|█████████ | 56319/61904 [5:58:44<2:08:00,  1.38s/it]
 91%|█████████ | 56320/61904 [5:58:45<2:05:22,  1.35s/it]
                                                         
{'loss': 2.4123, 'learning_rate': 1.0904965642421883e-07, 'epoch': 14.56}

 91%|█████████ | 56320/61904 [5:58:45<2:05:22,  1.35s/it]
 91%|█████████ | 56321/61904 [5:58:47<2:10:04,  1.40s/it]
 91%|█████████ | 56322/61904 [5:58:48<2:07:29,  1.37s/it]
 91%|█████████ | 56323/61904 [5:58:50<2:09:19,  1.39s/it]
 91%|█████████ | 56324/61904 [5:58:51<2:12:04,  1.42s/it]
 91%|█████████ | 56325/61904 [5:58:52<2:11:02,  1.41s/it]
 91%|█████████ | 56326/61904 [5:58:54<2:12:25,  1.42s/it]
 91%|█████████ | 56327/61904 [5:58:55<2:10:32,  1.40s/it]
 91%|█████████ | 56328/61904 [5:58:57<2:07:55,  1.38s/it]
 91%|█████████ | 56329/61904 [5:58:58<2:08:57,  1.39s/it]
 91%|█████████ | 56330/61904 [5:58:59<2:11:34,  1.42s/it]
 91%|█████████ | 56331/61904 [5:59:01<2:07:14,  1.37s/it]
 91%|█████████ | 56332/61904 [5:59:02<2:06:12,  1.36s/it]
 91%|█████████ | 56333/61904 [5:59:03<2:05:38,  1.35s/it]
 91%|█████████ | 56334/61904 [5:59:05<2:10:22,  1.40s/it]
 91%|█████████ | 56335/61904 [5:59:06<2:10:36,  1.41s/it]
 91%|█████████ | 56336/61904 [5:59:08<2:08:39,  1.39s/it]
 91%|█████████ | 56337/61904 [5:59:09<2:15:01,  1.46s/it]
 91%|█████████ | 56338/61904 [5:59:11<2:13:13,  1.44s/it]
 91%|█████████ | 56339/61904 [5:59:12<2:10:10,  1.40s/it]
 91%|█████████ | 56340/61904 [5:59:13<2:10:04,  1.40s/it]
                                                         
{'loss': 2.4266, 'learning_rate': 1.0901724361467651e-07, 'epoch': 14.56}

 91%|█████████ | 56340/61904 [5:59:13<2:10:04,  1.40s/it]
 91%|█████████ | 56341/61904 [5:59:15<2:11:24,  1.42s/it]
 91%|█████████ | 56342/61904 [5:59:16<2:09:08,  1.39s/it]
 91%|█████████ | 56343/61904 [5:59:17<2:05:10,  1.35s/it]
 91%|█████████ | 56344/61904 [5:59:19<2:02:42,  1.32s/it]
 91%|█████████ | 56345/61904 [5:59:20<2:05:55,  1.36s/it]
 91%|█████████ | 56346/61904 [5:59:22<2:11:28,  1.42s/it]
 91%|█████████ | 56347/61904 [5:59:23<2:08:53,  1.39s/it]
 91%|█████████ | 56348/61904 [5:59:24<2:09:48,  1.40s/it]
 91%|█████████ | 56349/61904 [5:59:26<2:07:53,  1.38s/it]
 91%|█████████ | 56350/61904 [5:59:27<2:07:44,  1.38s/it]
 91%|█████████ | 56351/61904 [5:59:29<2:08:13,  1.39s/it]
 91%|█████████ | 56352/61904 [5:59:30<2:07:48,  1.38s/it]
 91%|█████████ | 56353/61904 [5:59:31<2:07:40,  1.38s/it]
 91%|█████████ | 56354/61904 [5:59:33<2:08:26,  1.39s/it]
 91%|█████████ | 56355/61904 [5:59:34<2:09:36,  1.40s/it]
 91%|█████████ | 56356/61904 [5:59:35<2:07:18,  1.38s/it]
 91%|█████████ | 56357/61904 [5:59:37<2:08:21,  1.39s/it]
 91%|█████████ | 56358/61904 [5:59:38<2:11:06,  1.42s/it]
 91%|█████████ | 56359/61904 [5:59:40<2:08:22,  1.39s/it]
 91%|█████████ | 56360/61904 [5:59:41<2:08:17,  1.39s/it]
                                                         
{'loss': 2.4135, 'learning_rate': 1.0898483080513418e-07, 'epoch': 14.57}

 91%|█████████ | 56360/61904 [5:59:41<2:08:17,  1.39s/it]
 91%|█████████ | 56361/61904 [5:59:42<2:06:37,  1.37s/it]
 91%|█████████ | 56362/61904 [5:59:44<2:05:32,  1.36s/it]
 91%|█████████ | 56363/61904 [5:59:45<2:07:20,  1.38s/it]
 91%|█████████ | 56364/61904 [5:59:47<2:10:39,  1.42s/it]
 91%|█████████ | 56365/61904 [5:59:48<2:10:20,  1.41s/it]
 91%|█████████ | 56366/61904 [5:59:50<2:13:08,  1.44s/it]
 91%|█████████ | 56367/61904 [5:59:51<2:15:21,  1.47s/it]
 91%|█████████ | 56368/61904 [5:59:52<2:12:43,  1.44s/it]
 91%|█████████ | 56369/61904 [5:59:54<2:13:25,  1.45s/it]
 91%|█████████ | 56370/61904 [5:59:55<2:13:14,  1.44s/it]
 91%|█████████ | 56371/61904 [5:59:57<2:10:07,  1.41s/it]
 91%|█████████ | 56372/61904 [5:59:58<2:05:48,  1.36s/it]
 91%|█████████ | 56373/61904 [5:59:59<2:04:29,  1.35s/it]
 91%|█████████ | 56374/61904 [6:00:01<2:01:51,  1.32s/it]
 91%|█████████ | 56375/61904 [6:00:02<2:02:17,  1.33s/it]
 91%|█████████ | 56376/61904 [6:00:03<2:04:03,  1.35s/it]
 91%|█████████ | 56377/61904 [6:00:05<2:04:56,  1.36s/it]
 91%|█████████ | 56378/61904 [6:00:06<2:08:02,  1.39s/it]
 91%|█████████ | 56379/61904 [6:00:07<2:04:32,  1.35s/it]
 91%|█████████ | 56380/61904 [6:00:09<2:04:39,  1.35s/it]
                                                         
{'loss': 2.4508, 'learning_rate': 1.0895241799559184e-07, 'epoch': 14.57}

 91%|█████████ | 56380/61904 [6:00:09<2:04:39,  1.35s/it]
 91%|█████████ | 56381/61904 [6:00:10<2:03:20,  1.34s/it]
 91%|█████████ | 56382/61904 [6:00:11<2:06:14,  1.37s/it]
 91%|█████████ | 56383/61904 [6:00:13<2:06:36,  1.38s/it]
 91%|█████████ | 56384/61904 [6:00:14<2:05:19,  1.36s/it]
 91%|█████████ | 56385/61904 [6:00:16<2:05:43,  1.37s/it]
 91%|█████████ | 56386/61904 [6:00:17<2:07:21,  1.38s/it]
 91%|█████████ | 56387/61904 [6:00:18<2:05:50,  1.37s/it]
 91%|█████████ | 56388/61904 [6:00:20<2:06:06,  1.37s/it]
 91%|█████████ | 56389/61904 [6:00:21<2:03:34,  1.34s/it]
 91%|█████████ | 56390/61904 [6:00:22<2:03:48,  1.35s/it]
 91%|█████████ | 56391/61904 [6:00:24<2:03:49,  1.35s/it]
 91%|█████████ | 56392/61904 [6:00:25<2:05:02,  1.36s/it]
 91%|█████████ | 56393/61904 [6:00:26<2:04:32,  1.36s/it]
 91%|█████████ | 56394/61904 [6:00:28<2:03:35,  1.35s/it]
 91%|█████████ | 56395/61904 [6:00:29<2:05:47,  1.37s/it]
 91%|█████████ | 56396/61904 [6:00:31<2:08:38,  1.40s/it]
 91%|█████████ | 56397/61904 [6:00:32<2:12:01,  1.44s/it]
 91%|█████████ | 56398/61904 [6:00:34<2:09:56,  1.42s/it]
 91%|█████████ | 56399/61904 [6:00:35<2:08:25,  1.40s/it]
 91%|█████████ | 56400/61904 [6:00:36<2:07:32,  1.39s/it]
                                                         
{'loss': 2.4001, 'learning_rate': 1.089200051860495e-07, 'epoch': 14.58}

 91%|█████████ | 56400/61904 [6:00:36<2:07:32,  1.39s/it]
 91%|█████████ | 56401/61904 [6:00:38<2:05:14,  1.37s/it]
 91%|█████████ | 56402/61904 [6:00:39<2:02:34,  1.34s/it]
 91%|█████████ | 56403/61904 [6:00:40<2:02:19,  1.33s/it]
 91%|█████████ | 56404/61904 [6:00:42<2:06:44,  1.38s/it]
 91%|█████████ | 56405/61904 [6:00:43<2:07:24,  1.39s/it]
 91%|█████████ | 56406/61904 [6:00:45<2:09:25,  1.41s/it]
 91%|█████████ | 56407/61904 [6:00:46<2:06:52,  1.38s/it]
 91%|█████████ | 56408/61904 [6:00:47<2:05:22,  1.37s/it]
 91%|█████████ | 56409/61904 [6:00:49<2:04:12,  1.36s/it]
 91%|█████████ | 56410/61904 [6:00:50<2:02:42,  1.34s/it]
 91%|█████████ | 56411/61904 [6:00:51<2:01:10,  1.32s/it]
 91%|█████████ | 56412/61904 [6:00:53<2:05:08,  1.37s/it]
 91%|█████████ | 56413/61904 [6:00:54<2:05:19,  1.37s/it]
 91%|█████████ | 56414/61904 [6:00:55<2:06:14,  1.38s/it]
 91%|█████████ | 56415/61904 [6:00:57<2:06:04,  1.38s/it]
 91%|█████████ | 56416/61904 [6:00:58<2:06:56,  1.39s/it]
 91%|█████████ | 56417/61904 [6:01:00<2:06:32,  1.38s/it]
 91%|█████████ | 56418/61904 [6:01:01<2:12:18,  1.45s/it]
 91%|█████████ | 56419/61904 [6:01:03<2:17:11,  1.50s/it]
 91%|█████████ | 56420/61904 [6:01:04<2:16:22,  1.49s/it]
                                                         
{'loss': 2.3891, 'learning_rate': 1.0888759237650718e-07, 'epoch': 14.58}

 91%|█████████ | 56420/61904 [6:01:04<2:16:22,  1.49s/it]
 91%|█████████ | 56421/61904 [6:01:05<2:11:08,  1.44s/it]
 91%|█████████ | 56422/61904 [6:01:07<2:10:40,  1.43s/it]
 91%|█████████ | 56423/61904 [6:01:08<2:08:43,  1.41s/it]
 91%|█████████ | 56424/61904 [6:01:10<2:09:34,  1.42s/it]
 91%|█████████ | 56425/61904 [6:01:11<2:06:37,  1.39s/it]
 91%|█████████ | 56426/61904 [6:01:13<2:11:49,  1.44s/it]
 91%|█████████ | 56427/61904 [6:01:14<2:12:44,  1.45s/it]
 91%|█████████ | 56428/61904 [6:01:15<2:10:56,  1.43s/it]
 91%|█████████ | 56429/61904 [6:01:17<2:08:05,  1.40s/it]
 91%|█████████ | 56430/61904 [6:01:18<2:15:22,  1.48s/it]
 91%|█████████ | 56431/61904 [6:01:20<2:11:56,  1.45s/it]
 91%|█████████ | 56432/61904 [6:01:21<2:11:36,  1.44s/it]
 91%|█████████ | 56433/61904 [6:01:23<2:10:25,  1.43s/it]
 91%|█████████ | 56434/61904 [6:01:24<2:07:33,  1.40s/it]
 91%|█████████ | 56435/61904 [6:01:25<2:07:17,  1.40s/it]
 91%|█████████ | 56436/61904 [6:01:27<2:07:30,  1.40s/it]
 91%|█████████ | 56437/61904 [6:01:28<2:09:43,  1.42s/it]
 91%|█████████ | 56438/61904 [6:01:30<2:07:03,  1.39s/it]
 91%|█████████ | 56439/61904 [6:01:31<2:05:12,  1.37s/it]
 91%|█████████ | 56440/61904 [6:01:32<2:03:09,  1.35s/it]
                                                         
{'loss': 2.4768, 'learning_rate': 1.0885517956696486e-07, 'epoch': 14.59}

 91%|█████████ | 56440/61904 [6:01:32<2:03:09,  1.35s/it]
 91%|█████████ | 56441/61904 [6:01:33<1:58:57,  1.31s/it]
 91%|█████████ | 56442/61904 [6:01:35<2:00:20,  1.32s/it]
 91%|█████████ | 56443/61904 [6:01:36<2:03:00,  1.35s/it]
 91%|█████████ | 56444/61904 [6:01:37<2:00:24,  1.32s/it]
 91%|█████████ | 56445/61904 [6:01:39<2:03:09,  1.35s/it]
 91%|█████████ | 56446/61904 [6:01:40<2:05:30,  1.38s/it]
 91%|█████████ | 56447/61904 [6:01:42<2:02:36,  1.35s/it]
 91%|█████████ | 56448/61904 [6:01:43<2:02:43,  1.35s/it]
 91%|█████████ | 56449/61904 [6:01:44<2:07:51,  1.41s/it]
 91%|█████████ | 56450/61904 [6:01:46<2:10:22,  1.43s/it]
 91%|█████████ | 56451/61904 [6:01:47<2:06:03,  1.39s/it]
 91%|█████████ | 56452/61904 [6:01:49<2:03:50,  1.36s/it]
 91%|█████████ | 56453/61904 [6:01:50<2:03:50,  1.36s/it]
 91%|█████████ | 56454/61904 [6:01:51<2:01:25,  1.34s/it]
 91%|█████████ | 56455/61904 [6:01:53<2:12:02,  1.45s/it]
 91%|█████████ | 56456/61904 [6:01:54<2:09:54,  1.43s/it]
 91%|█████████ | 56457/61904 [6:01:56<2:12:24,  1.46s/it]
 91%|█████████ | 56458/61904 [6:01:57<2:10:09,  1.43s/it]
 91%|█████████ | 56459/61904 [6:01:59<2:12:29,  1.46s/it]
 91%|█████████ | 56460/61904 [6:02:00<2:08:48,  1.42s/it]
                                                         
{'loss': 2.4198, 'learning_rate': 1.0882276675742252e-07, 'epoch': 14.59}

 91%|█████████ | 56460/61904 [6:02:00<2:08:48,  1.42s/it]
 91%|█████████ | 56461/61904 [6:02:01<2:08:44,  1.42s/it]
 91%|█████████ | 56462/61904 [6:02:03<2:07:07,  1.40s/it]
 91%|█████████ | 56463/61904 [6:02:04<2:07:09,  1.40s/it]
 91%|█████████ | 56464/61904 [6:02:06<2:06:21,  1.39s/it]
 91%|█████████ | 56465/61904 [6:02:07<2:03:30,  1.36s/it]
 91%|█████████ | 56466/61904 [6:02:08<2:04:11,  1.37s/it]
 91%|█████████ | 56467/61904 [6:02:10<2:02:53,  1.36s/it]
 91%|█████████ | 56468/61904 [6:02:11<2:01:46,  1.34s/it]
 91%|█████████ | 56469/61904 [6:02:12<1:58:59,  1.31s/it]
 91%|█████████ | 56470/61904 [6:02:14<2:03:12,  1.36s/it]
 91%|█████████ | 56471/61904 [6:02:15<2:05:57,  1.39s/it]
 91%|█████████ | 56472/61904 [6:02:16<2:02:38,  1.35s/it]
 91%|█████████ | 56473/61904 [6:02:18<2:02:44,  1.36s/it]
 91%|█████████ | 56474/61904 [6:02:19<2:02:43,  1.36s/it]
 91%|█████████ | 56475/61904 [6:02:20<2:02:29,  1.35s/it]
 91%|█████████ | 56476/61904 [6:02:22<1:59:03,  1.32s/it]
 91%|█████████ | 56477/61904 [6:02:23<1:59:43,  1.32s/it]
 91%|█████████ | 56478/61904 [6:02:24<1:59:56,  1.33s/it]
 91%|█████████ | 56479/61904 [6:02:26<2:00:49,  1.34s/it]
 91%|█████████ | 56480/61904 [6:02:27<1:59:49,  1.33s/it]
                                                         
{'loss': 2.404, 'learning_rate': 1.0879035394788018e-07, 'epoch': 14.6}

 91%|█████████ | 56480/61904 [6:02:27<1:59:49,  1.33s/it]
 91%|█████████ | 56481/61904 [6:02:29<2:06:13,  1.40s/it]
 91%|█████████ | 56482/61904 [6:02:30<2:03:22,  1.37s/it]
 91%|█████████ | 56483/61904 [6:02:31<2:04:25,  1.38s/it]
 91%|█████████ | 56484/61904 [6:02:33<2:04:19,  1.38s/it]
 91%|█████████ | 56485/61904 [6:02:34<2:06:37,  1.40s/it]
 91%|█████████ | 56486/61904 [6:02:36<2:07:33,  1.41s/it]
 91%|█████████ | 56487/61904 [6:02:37<2:09:21,  1.43s/it]
 91%|█████████▏| 56488/61904 [6:02:39<2:15:54,  1.51s/it]
 91%|█████████▏| 56489/61904 [6:02:40<2:12:11,  1.46s/it]
 91%|█████████▏| 56490/61904 [6:02:41<2:05:46,  1.39s/it]
 91%|█████████▏| 56491/61904 [6:02:43<2:03:40,  1.37s/it]
 91%|█████████▏| 56492/61904 [6:02:44<2:09:23,  1.43s/it]
 91%|█████████▏| 56493/61904 [6:02:46<2:08:27,  1.42s/it]
 91%|█████████▏| 56494/61904 [6:02:47<2:05:03,  1.39s/it]
 91%|█████████▏| 56495/61904 [6:02:48<2:03:29,  1.37s/it]
 91%|█████████▏| 56496/61904 [6:02:50<2:09:43,  1.44s/it]
 91%|█████████▏| 56497/61904 [6:02:51<2:05:48,  1.40s/it]
 91%|█████████▏| 56498/61904 [6:02:53<2:06:26,  1.40s/it]
 91%|█████████▏| 56499/61904 [6:02:54<2:02:21,  1.36s/it]
 91%|█████████▏| 56500/61904 [6:02:55<2:02:42,  1.36s/it]
                                                         
{'loss': 2.4938, 'learning_rate': 1.0875794113833786e-07, 'epoch': 14.6}

 91%|█████████▏| 56500/61904 [6:02:55<2:02:42,  1.36s/it]
 91%|█████████▏| 56501/61904 [6:02:57<2:04:34,  1.38s/it]
 91%|█████████▏| 56502/61904 [6:02:58<2:06:36,  1.41s/it]
 91%|█████████▏| 56503/61904 [6:02:59<2:06:01,  1.40s/it]
 91%|█████████▏| 56504/61904 [6:03:01<2:03:17,  1.37s/it]
 91%|█████████▏| 56505/61904 [6:03:02<2:03:15,  1.37s/it]
 91%|█████████▏| 56506/61904 [6:03:03<2:00:29,  1.34s/it]
 91%|█████████▏| 56507/61904 [6:03:05<1:58:43,  1.32s/it]
 91%|█████████▏| 56508/61904 [6:03:06<1:59:24,  1.33s/it]
 91%|█████████▏| 56509/61904 [6:03:07<1:59:15,  1.33s/it]
 91%|█████████▏| 56510/61904 [6:03:09<2:01:49,  1.36s/it]
 91%|█████████▏| 56511/61904 [6:03:10<1:58:50,  1.32s/it]
 91%|█████████▏| 56512/61904 [6:03:11<1:59:47,  1.33s/it]
 91%|█████████▏| 56513/61904 [6:03:13<2:02:19,  1.36s/it]
 91%|█████████▏| 56514/61904 [6:03:14<2:01:35,  1.35s/it]
 91%|█████████▏| 56515/61904 [6:03:16<2:03:21,  1.37s/it]
 91%|█████████▏| 56516/61904 [6:03:17<2:01:27,  1.35s/it]
 91%|█████████▏| 56517/61904 [6:03:18<1:59:44,  1.33s/it]
 91%|█████████▏| 56518/61904 [6:03:19<1:57:01,  1.30s/it]
 91%|█████████▏| 56519/61904 [6:03:21<2:04:46,  1.39s/it]
 91%|█████████▏| 56520/61904 [6:03:22<2:01:50,  1.36s/it]
                                                         
{'loss': 2.4509, 'learning_rate': 1.0872552832879553e-07, 'epoch': 14.61}

 91%|█████████▏| 56520/61904 [6:03:22<2:01:50,  1.36s/it]
 91%|█████████▏| 56521/61904 [6:03:24<2:01:35,  1.36s/it]
 91%|█████████▏| 56522/61904 [6:03:25<2:01:14,  1.35s/it]
 91%|█████████▏| 56523/61904 [6:03:26<2:03:08,  1.37s/it]
 91%|█████████▏| 56524/61904 [6:03:28<2:05:50,  1.40s/it]
 91%|█████████▏| 56525/61904 [6:03:29<2:07:18,  1.42s/it]
 91%|█████████▏| 56526/61904 [6:03:31<2:05:57,  1.41s/it]
 91%|█████████▏| 56527/61904 [6:03:32<2:10:02,  1.45s/it]
 91%|█████████▏| 56528/61904 [6:03:34<2:08:06,  1.43s/it]
 91%|█████████▏| 56529/61904 [6:03:35<2:10:55,  1.46s/it]
 91%|█████████▏| 56530/61904 [6:03:37<2:08:42,  1.44s/it]
 91%|█████████▏| 56531/61904 [6:03:38<2:08:10,  1.43s/it]
 91%|█████████▏| 56532/61904 [6:03:39<2:09:38,  1.45s/it]
 91%|█████████▏| 56533/61904 [6:03:41<2:08:46,  1.44s/it]
 91%|█████████▏| 56534/61904 [6:03:42<2:08:29,  1.44s/it]
 91%|█████████▏| 56535/61904 [6:03:44<2:04:14,  1.39s/it]
 91%|█████████▏| 56536/61904 [6:03:45<2:03:07,  1.38s/it]
 91%|█████████▏| 56537/61904 [6:03:46<2:02:21,  1.37s/it]
 91%|█████████▏| 56538/61904 [6:03:48<2:02:18,  1.37s/it]
 91%|█████████▏| 56539/61904 [6:03:49<2:00:06,  1.34s/it]
 91%|█████████▏| 56540/61904 [6:03:50<2:02:32,  1.37s/it]
                                                         
{'loss': 2.4481, 'learning_rate': 1.0869311551925319e-07, 'epoch': 14.61}

 91%|█████████▏| 56540/61904 [6:03:50<2:02:32,  1.37s/it]
 91%|█████████▏| 56541/61904 [6:03:52<2:04:11,  1.39s/it]
 91%|█████████▏| 56542/61904 [6:03:53<2:06:08,  1.41s/it]
 91%|█████████▏| 56543/61904 [6:03:54<2:02:05,  1.37s/it]
 91%|█████████▏| 56544/61904 [6:03:56<2:03:03,  1.38s/it]
 91%|█████████▏| 56545/61904 [6:03:57<1:59:43,  1.34s/it]
 91%|█████████▏| 56546/61904 [6:03:59<2:02:47,  1.38s/it]
 91%|█████████▏| 56547/61904 [6:04:00<2:01:35,  1.36s/it]
 91%|█████████▏| 56548/61904 [6:04:01<1:59:19,  1.34s/it]
 91%|█████████▏| 56549/61904 [6:04:03<2:02:08,  1.37s/it]
 91%|█████████▏| 56550/61904 [6:04:04<2:02:43,  1.38s/it]
 91%|█████████▏| 56551/61904 [6:04:05<2:04:56,  1.40s/it]
 91%|█████████▏| 56552/61904 [6:04:07<2:04:58,  1.40s/it]
 91%|█████████▏| 56553/61904 [6:04:08<2:03:43,  1.39s/it]
 91%|█████████▏| 56554/61904 [6:04:10<2:03:37,  1.39s/it]
 91%|█████████▏| 56555/61904 [6:04:11<2:02:44,  1.38s/it]
 91%|█████████▏| 56556/61904 [6:04:12<2:04:03,  1.39s/it]
 91%|█████████▏| 56557/61904 [6:04:14<2:04:44,  1.40s/it]
 91%|█████████▏| 56558/61904 [6:04:15<2:05:01,  1.40s/it]
 91%|█████████▏| 56559/61904 [6:04:17<2:02:23,  1.37s/it]
 91%|█████████▏| 56560/61904 [6:04:18<2:05:48,  1.41s/it]
                                                         
{'loss': 2.4265, 'learning_rate': 1.0866070270971085e-07, 'epoch': 14.62}

 91%|█████████▏| 56560/61904 [6:04:18<2:05:48,  1.41s/it]
 91%|█████████▏| 56561/61904 [6:04:20<2:07:00,  1.43s/it]
 91%|█████████▏| 56562/61904 [6:04:21<2:13:49,  1.50s/it]
 91%|█████████▏| 56563/61904 [6:04:23<2:10:22,  1.46s/it]
 91%|█████████▏| 56564/61904 [6:04:24<2:11:59,  1.48s/it]
 91%|█████████▏| 56565/61904 [6:04:26<2:15:35,  1.52s/it]
 91%|█████████▏| 56566/61904 [6:04:27<2:09:10,  1.45s/it]
 91%|█████████▏| 56567/61904 [6:04:28<2:07:28,  1.43s/it]
 91%|█████████▏| 56568/61904 [6:04:30<2:06:30,  1.42s/it]
 91%|█████████▏| 56569/61904 [6:04:31<2:05:32,  1.41s/it]
 91%|█████████▏| 56570/61904 [6:04:33<2:09:25,  1.46s/it]
 91%|█████████▏| 56571/61904 [6:04:34<2:05:18,  1.41s/it]
 91%|█████████▏| 56572/61904 [6:04:35<2:04:34,  1.40s/it]
 91%|█████████▏| 56573/61904 [6:04:37<2:02:16,  1.38s/it]
 91%|█████████▏| 56574/61904 [6:04:38<2:01:55,  1.37s/it]
 91%|█████████▏| 56575/61904 [6:04:39<2:01:14,  1.37s/it]
 91%|█████████▏| 56576/61904 [6:04:41<1:58:31,  1.33s/it]
 91%|█████████▏| 56577/61904 [6:04:42<1:57:45,  1.33s/it]
 91%|█████████▏| 56578/61904 [6:04:43<2:00:22,  1.36s/it]
 91%|█████████▏| 56579/61904 [6:04:45<2:02:00,  1.37s/it]
 91%|█████████▏| 56580/61904 [6:04:46<2:01:58,  1.37s/it]
                                                         
{'loss': 2.4469, 'learning_rate': 1.0862828990016854e-07, 'epoch': 14.62}

 91%|█████████▏| 56580/61904 [6:04:46<2:01:58,  1.37s/it]
 91%|█████████▏| 56581/61904 [6:04:48<2:00:10,  1.35s/it]
 91%|█████████▏| 56582/61904 [6:04:49<2:02:06,  1.38s/it]
 91%|█████████▏| 56583/61904 [6:04:50<2:00:40,  1.36s/it]
 91%|█████████▏| 56584/61904 [6:04:52<2:12:39,  1.50s/it]
 91%|█████████▏| 56585/61904 [6:04:54<2:12:40,  1.50s/it]
 91%|█████████▏| 56586/61904 [6:04:55<2:09:41,  1.46s/it]
 91%|█████████▏| 56587/61904 [6:04:56<2:06:53,  1.43s/it]
 91%|█████████▏| 56588/61904 [6:04:58<2:06:37,  1.43s/it]
 91%|█████████▏| 56589/61904 [6:04:59<2:06:37,  1.43s/it]
 91%|█████████▏| 56590/61904 [6:05:01<2:04:46,  1.41s/it]
 91%|█████████▏| 56591/61904 [6:05:02<2:04:29,  1.41s/it]
 91%|█████████▏| 56592/61904 [6:05:03<2:04:17,  1.40s/it]
 91%|█████████▏| 56593/61904 [6:05:05<2:02:39,  1.39s/it]
 91%|█████████▏| 56594/61904 [6:05:06<2:02:57,  1.39s/it]
 91%|█████████▏| 56595/61904 [6:05:07<2:01:30,  1.37s/it]
 91%|█████████▏| 56596/61904 [6:05:09<2:02:12,  1.38s/it]
 91%|█████████▏| 56597/61904 [6:05:10<2:02:09,  1.38s/it]
 91%|█████████▏| 56598/61904 [6:05:12<2:05:33,  1.42s/it]
 91%|█████████▏| 56599/61904 [6:05:13<2:01:29,  1.37s/it]
 91%|█████████▏| 56600/61904 [6:05:14<2:01:11,  1.37s/it]
                                                         
{'loss': 2.4133, 'learning_rate': 1.085958770906262e-07, 'epoch': 14.63}

 91%|█████████▏| 56600/61904 [6:05:14<2:01:11,  1.37s/it]
 91%|█████████▏| 56601/61904 [6:05:16<2:01:49,  1.38s/it]
 91%|█████████▏| 56602/61904 [6:05:17<2:01:56,  1.38s/it]
 91%|█████████▏| 56603/61904 [6:05:18<1:59:56,  1.36s/it]
 91%|█████████▏| 56604/61904 [6:05:20<1:57:02,  1.33s/it]
 91%|█████████▏| 56605/61904 [6:05:21<1:57:31,  1.33s/it]
 91%|█████████▏| 56606/61904 [6:05:22<1:56:07,  1.32s/it]
 91%|█████████▏| 56607/61904 [6:05:24<2:03:00,  1.39s/it]
 91%|█████████▏| 56608/61904 [6:05:26<2:13:54,  1.52s/it]
 91%|█████████▏| 56609/61904 [6:05:27<2:08:57,  1.46s/it]
 91%|█████████▏| 56610/61904 [6:05:28<2:06:17,  1.43s/it]
 91%|█████████▏| 56611/61904 [6:05:30<2:07:34,  1.45s/it]
 91%|█████████▏| 56612/61904 [6:05:31<2:05:15,  1.42s/it]
 91%|█████████▏| 56613/61904 [6:05:33<2:04:06,  1.41s/it]
 91%|█████████▏| 56614/61904 [6:05:34<2:00:46,  1.37s/it]
 91%|█████████▏| 56615/61904 [6:05:35<2:02:36,  1.39s/it]
 91%|█████████▏| 56616/61904 [6:05:37<1:58:21,  1.34s/it]
 91%|█████████▏| 56617/61904 [6:05:38<1:59:31,  1.36s/it]
 91%|█████████▏| 56618/61904 [6:05:39<2:01:54,  1.38s/it]
 91%|█████████▏| 56619/61904 [6:05:41<1:59:53,  1.36s/it]
 91%|█████████▏| 56620/61904 [6:05:42<1:57:39,  1.34s/it]
                                                         
{'loss': 2.4522, 'learning_rate': 1.0856346428108387e-07, 'epoch': 14.63}

 91%|█████████▏| 56620/61904 [6:05:42<1:57:39,  1.34s/it]
 91%|█████████▏| 56621/61904 [6:05:43<1:59:23,  1.36s/it]
 91%|█████████▏| 56622/61904 [6:05:45<2:02:38,  1.39s/it]
 91%|█████████▏| 56623/61904 [6:05:46<2:03:46,  1.41s/it]
 91%|█████████▏| 56624/61904 [6:05:48<2:02:30,  1.39s/it]
 91%|█████████▏| 56625/61904 [6:05:49<2:00:40,  1.37s/it]
 91%|█████████▏| 56626/61904 [6:05:50<2:04:09,  1.41s/it]
 91%|█████████▏| 56627/61904 [6:05:52<2:03:04,  1.40s/it]
 91%|█████████▏| 56628/61904 [6:05:53<2:02:20,  1.39s/it]
 91%|█████████▏| 56629/61904 [6:05:55<1:59:29,  1.36s/it]
 91%|█████████▏| 56630/61904 [6:05:56<2:01:16,  1.38s/it]
 91%|█████████▏| 56631/61904 [6:05:57<2:01:07,  1.38s/it]
 91%|█████████▏| 56632/61904 [6:05:59<2:01:48,  1.39s/it]
 91%|█████████▏| 56633/61904 [6:06:00<1:58:53,  1.35s/it]
 91%|█████████▏| 56634/61904 [6:06:01<1:58:54,  1.35s/it]
 91%|█████████▏| 56635/61904 [6:06:03<1:57:29,  1.34s/it]
 91%|█████████▏| 56636/61904 [6:06:04<1:58:46,  1.35s/it]
 91%|█████████▏| 56637/61904 [6:06:05<1:56:23,  1.33s/it]
 91%|█████████▏| 56638/61904 [6:06:07<1:55:17,  1.31s/it]
 91%|█████████▏| 56639/61904 [6:06:08<1:54:58,  1.31s/it]
 91%|█████████▏| 56640/61904 [6:06:09<1:57:32,  1.34s/it]
                                                         
{'loss': 2.4041, 'learning_rate': 1.0853105147154153e-07, 'epoch': 14.64}

 91%|█████████▏| 56640/61904 [6:06:09<1:57:32,  1.34s/it]
 91%|█████████▏| 56641/61904 [6:06:11<1:57:59,  1.35s/it]
 91%|█████████▏| 56642/61904 [6:06:12<1:56:36,  1.33s/it]
 92%|█████████▏| 56643/61904 [6:06:13<1:54:03,  1.30s/it]
 92%|█████████▏| 56644/61904 [6:06:15<1:55:19,  1.32s/it]
 92%|█████████▏| 56645/61904 [6:06:16<1:59:38,  1.37s/it]
 92%|█████████▏| 56646/61904 [6:06:17<1:58:24,  1.35s/it]
 92%|█████████▏| 56647/61904 [6:06:19<1:59:13,  1.36s/it]
 92%|█████████▏| 56648/61904 [6:06:20<2:03:55,  1.41s/it]
 92%|█████████▏| 56649/61904 [6:06:22<2:03:54,  1.41s/it]
 92%|█████████▏| 56650/61904 [6:06:23<2:04:21,  1.42s/it]
 92%|█████████▏| 56651/61904 [6:06:24<2:01:50,  1.39s/it]
 92%|█████████▏| 56652/61904 [6:06:26<1:59:17,  1.36s/it]
 92%|█████████▏| 56653/61904 [6:06:27<1:57:35,  1.34s/it]
 92%|█████████▏| 56654/61904 [6:06:29<2:03:49,  1.42s/it]
 92%|█████████▏| 56655/61904 [6:06:30<1:59:57,  1.37s/it]
 92%|█████████▏| 56656/61904 [6:06:31<2:03:18,  1.41s/it]
 92%|█████████▏| 56657/61904 [6:06:33<2:05:18,  1.43s/it]
 92%|█████████▏| 56658/61904 [6:06:34<2:03:55,  1.42s/it]
 92%|█████████▏| 56659/61904 [6:06:36<2:02:50,  1.41s/it]
 92%|█████████▏| 56660/61904 [6:06:37<2:04:25,  1.42s/it]
                                                         
{'loss': 2.4375, 'learning_rate': 1.0849863866199922e-07, 'epoch': 14.64}

 92%|█████████▏| 56660/61904 [6:06:37<2:04:25,  1.42s/it]
 92%|█████████▏| 56661/61904 [6:06:39<2:04:12,  1.42s/it]
 92%|█████████▏| 56662/61904 [6:06:40<2:03:11,  1.41s/it]
 92%|█████████▏| 56663/61904 [6:06:41<2:02:50,  1.41s/it]
 92%|█████████▏| 56664/61904 [6:06:43<2:04:11,  1.42s/it]
 92%|█████████▏| 56665/61904 [6:06:44<2:06:15,  1.45s/it]
 92%|█████████▏| 56666/61904 [6:06:46<2:05:52,  1.44s/it]
 92%|█████████▏| 56667/61904 [6:06:47<2:03:46,  1.42s/it]
 92%|█████████▏| 56668/61904 [6:06:48<2:03:06,  1.41s/it]
 92%|█████████▏| 56669/61904 [6:06:50<1:58:16,  1.36s/it]
 92%|█████████▏| 56670/61904 [6:06:51<2:00:33,  1.38s/it]
 92%|█████████▏| 56671/61904 [6:06:52<1:59:07,  1.37s/it]
 92%|█████████▏| 56672/61904 [6:06:54<2:00:00,  1.38s/it]
 92%|█████████▏| 56673/61904 [6:06:55<2:01:07,  1.39s/it]
 92%|█████████▏| 56674/61904 [6:06:57<2:02:22,  1.40s/it]
 92%|█████████▏| 56675/61904 [6:06:58<2:00:58,  1.39s/it]
 92%|█████████▏| 56676/61904 [6:06:59<1:57:26,  1.35s/it]
 92%|█████████▏| 56677/61904 [6:07:01<1:55:48,  1.33s/it]
 92%|█████████▏| 56678/61904 [6:07:02<1:54:39,  1.32s/it]
 92%|█████████▏| 56679/61904 [6:07:03<1:53:09,  1.30s/it]
 92%|█████████▏| 56680/61904 [6:07:04<1:54:39,  1.32s/it]
                                                         
{'loss': 2.4063, 'learning_rate': 1.0846622585245688e-07, 'epoch': 14.65}

 92%|█████████▏| 56680/61904 [6:07:04<1:54:39,  1.32s/it]
 92%|█████████▏| 56681/61904 [6:07:06<1:57:50,  1.35s/it]
 92%|█████████▏| 56682/61904 [6:07:07<1:59:11,  1.37s/it]
 92%|█████████▏| 56683/61904 [6:07:09<1:59:30,  1.37s/it]
 92%|█████████▏| 56684/61904 [6:07:10<1:58:02,  1.36s/it]
 92%|█████████▏| 56685/61904 [6:07:11<1:59:54,  1.38s/it]
 92%|█████████▏| 56686/61904 [6:07:13<2:00:48,  1.39s/it]
 92%|█████████▏| 56687/61904 [6:07:14<1:58:20,  1.36s/it]
 92%|█████████▏| 56688/61904 [6:07:16<1:58:47,  1.37s/it]
 92%|█████████▏| 56689/61904 [6:07:17<1:58:21,  1.36s/it]
 92%|█████████▏| 56690/61904 [6:07:18<1:55:27,  1.33s/it]
 92%|█████████▏| 56691/61904 [6:07:20<1:58:03,  1.36s/it]
 92%|█████████▏| 56692/61904 [6:07:21<1:59:13,  1.37s/it]
 92%|█████████▏| 56693/61904 [6:07:22<1:56:28,  1.34s/it]
 92%|█████████▏| 56694/61904 [6:07:24<1:58:35,  1.37s/it]
 92%|█████████▏| 56695/61904 [6:07:25<1:59:06,  1.37s/it]
 92%|█████████▏| 56696/61904 [6:07:26<1:54:56,  1.32s/it]
 92%|█████████▏| 56697/61904 [6:07:28<1:57:15,  1.35s/it]
 92%|█████████▏| 56698/61904 [6:07:29<1:59:34,  1.38s/it]
 92%|█████████▏| 56699/61904 [6:07:31<2:00:40,  1.39s/it]
 92%|█████████▏| 56700/61904 [6:07:32<1:59:42,  1.38s/it]
                                                         
{'loss': 2.4281, 'learning_rate': 1.0843381304291454e-07, 'epoch': 14.65}

 92%|█████████▏| 56700/61904 [6:07:32<1:59:42,  1.38s/it]
 92%|█████████▏| 56701/61904 [6:07:33<2:03:09,  1.42s/it]
 92%|█████████▏| 56702/61904 [6:07:35<2:00:29,  1.39s/it]
 92%|█████████▏| 56703/61904 [6:07:36<1:57:21,  1.35s/it]
 92%|█████████▏| 56704/61904 [6:07:37<1:57:09,  1.35s/it]
 92%|█████████▏| 56705/61904 [6:07:39<1:59:31,  1.38s/it]
 92%|█████████▏| 56706/61904 [6:07:40<1:58:14,  1.36s/it]
 92%|█████████▏| 56707/61904 [6:07:42<1:58:44,  1.37s/it]
 92%|█████████▏| 56708/61904 [6:07:43<1:58:38,  1.37s/it]
 92%|█████████▏| 56709/61904 [6:07:44<2:03:28,  1.43s/it]
 92%|█████████▏| 56710/61904 [6:07:46<2:00:09,  1.39s/it]
 92%|█████████▏| 56711/61904 [6:07:47<1:58:54,  1.37s/it]
 92%|█████████▏| 56712/61904 [6:07:48<1:58:01,  1.36s/it]
 92%|█████████▏| 56713/61904 [6:07:50<2:00:39,  1.39s/it]
 92%|█████████▏| 56714/61904 [6:07:51<2:01:18,  1.40s/it]
 92%|█████████▏| 56715/61904 [6:07:53<1:59:32,  1.38s/it]
 92%|█████████▏| 56716/61904 [6:07:54<1:58:17,  1.37s/it]
 92%|█████████▏| 56717/61904 [6:07:55<1:59:08,  1.38s/it]
 92%|█████████▏| 56718/61904 [6:07:57<2:00:52,  1.40s/it]
 92%|█████████▏| 56719/61904 [6:07:58<2:00:54,  1.40s/it]
 92%|█████████▏| 56720/61904 [6:08:00<2:06:50,  1.47s/it]
                                                         
{'loss': 2.3715, 'learning_rate': 1.084014002333722e-07, 'epoch': 14.66}

 92%|█████████▏| 56720/61904 [6:08:00<2:06:50,  1.47s/it]
 92%|█████████▏| 56721/61904 [6:08:01<2:05:32,  1.45s/it]
 92%|█████████▏| 56722/61904 [6:08:03<2:04:49,  1.45s/it]
 92%|█████████▏| 56723/61904 [6:08:04<1:59:58,  1.39s/it]
 92%|█████████▏| 56724/61904 [6:08:05<2:02:24,  1.42s/it]
 92%|█████████▏| 56725/61904 [6:08:07<2:06:35,  1.47s/it]
 92%|█████████▏| 56726/61904 [6:08:08<2:05:51,  1.46s/it]
 92%|█████████▏| 56727/61904 [6:08:10<2:03:37,  1.43s/it]
 92%|█████████▏| 56728/61904 [6:08:11<1:59:33,  1.39s/it]
 92%|█████████▏| 56729/61904 [6:08:13<1:59:24,  1.38s/it]
 92%|█████████▏| 56730/61904 [6:08:14<2:03:45,  1.44s/it]
 92%|█████████▏| 56731/61904 [6:08:16<2:04:52,  1.45s/it]
 92%|█████████▏| 56732/61904 [6:08:17<2:04:00,  1.44s/it]
 92%|█████████▏| 56733/61904 [6:08:18<2:03:02,  1.43s/it]
 92%|█████████▏| 56734/61904 [6:08:20<2:04:44,  1.45s/it]
 92%|█████████▏| 56735/61904 [6:08:21<2:02:08,  1.42s/it]
 92%|█████████▏| 56736/61904 [6:08:22<1:58:33,  1.38s/it]
 92%|█████████▏| 56737/61904 [6:08:24<1:56:40,  1.35s/it]
 92%|█████████▏| 56738/61904 [6:08:25<1:57:18,  1.36s/it]
 92%|█████████▏| 56739/61904 [6:08:26<1:54:56,  1.34s/it]
 92%|█████████▏| 56740/61904 [6:08:28<1:57:21,  1.36s/it]
                                                         
{'loss': 2.4447, 'learning_rate': 1.0836898742382989e-07, 'epoch': 14.66}

 92%|█████████▏| 56740/61904 [6:08:28<1:57:21,  1.36s/it]
 92%|█████████▏| 56741/61904 [6:08:29<2:04:07,  1.44s/it]
 92%|█████████▏| 56742/61904 [6:08:31<2:03:08,  1.43s/it]
 92%|█████████▏| 56743/61904 [6:08:32<2:01:36,  1.41s/it]
 92%|█████████▏| 56744/61904 [6:08:34<2:00:27,  1.40s/it]
 92%|█████████▏| 56745/61904 [6:08:35<1:57:52,  1.37s/it]
 92%|█████████▏| 56746/61904 [6:08:36<2:01:05,  1.41s/it]
 92%|█████████▏| 56747/61904 [6:08:38<2:01:03,  1.41s/it]
 92%|█████████▏| 56748/61904 [6:08:39<1:56:59,  1.36s/it]
 92%|█████████▏| 56749/61904 [6:08:40<1:56:49,  1.36s/it]
 92%|█████████▏| 56750/61904 [6:08:42<1:56:58,  1.36s/it]
 92%|█████████▏| 56751/61904 [6:08:43<2:01:55,  1.42s/it]
 92%|█████████▏| 56752/61904 [6:08:45<2:02:32,  1.43s/it]
 92%|█████████▏| 56753/61904 [6:08:46<2:01:37,  1.42s/it]
 92%|█████████▏| 56754/61904 [6:08:48<2:00:44,  1.41s/it]
 92%|█████████▏| 56755/61904 [6:08:49<2:02:32,  1.43s/it]
 92%|█████████▏| 56756/61904 [6:08:51<2:08:42,  1.50s/it]
 92%|█████████▏| 56757/61904 [6:08:52<2:04:11,  1.45s/it]
 92%|█████████▏| 56758/61904 [6:08:53<2:02:00,  1.42s/it]
 92%|█████████▏| 56759/61904 [6:08:55<1:58:37,  1.38s/it]
 92%|█████████▏| 56760/61904 [6:08:56<1:54:21,  1.33s/it]
                                                         
{'loss': 2.4509, 'learning_rate': 1.0833657461428755e-07, 'epoch': 14.67}

 92%|█████████▏| 56760/61904 [6:08:56<1:54:21,  1.33s/it]
 92%|█████████▏| 56761/61904 [6:08:57<1:52:56,  1.32s/it]
 92%|█████████▏| 56762/61904 [6:08:59<1:54:59,  1.34s/it]
 92%|█████████▏| 56763/61904 [6:09:00<2:00:41,  1.41s/it]
 92%|█████████▏| 56764/61904 [6:09:01<1:57:46,  1.37s/it]
 92%|█████████▏| 56765/61904 [6:09:03<1:58:59,  1.39s/it]
 92%|█████████▏| 56766/61904 [6:09:04<2:00:54,  1.41s/it]
 92%|█████████▏| 56767/61904 [6:09:06<2:04:18,  1.45s/it]
 92%|█████████▏| 56768/61904 [6:09:07<2:02:56,  1.44s/it]
 92%|█████████▏| 56769/61904 [6:09:09<2:01:56,  1.42s/it]
 92%|█████████▏| 56770/61904 [6:09:10<1:58:20,  1.38s/it]
 92%|█████████▏| 56771/61904 [6:09:11<1:56:53,  1.37s/it]
 92%|█████████▏| 56772/61904 [6:09:13<1:55:55,  1.36s/it]
 92%|█████████▏| 56773/61904 [6:09:14<1:58:44,  1.39s/it]
 92%|█████████▏| 56774/61904 [6:09:16<1:59:09,  1.39s/it]
 92%|█████████▏| 56775/61904 [6:09:17<1:58:10,  1.38s/it]
 92%|█████████▏| 56776/61904 [6:09:18<1:59:36,  1.40s/it]
 92%|█████████▏| 56777/61904 [6:09:20<2:00:52,  1.41s/it]
 92%|█████████▏| 56778/61904 [6:09:21<2:01:48,  1.43s/it]
 92%|█████████▏| 56779/61904 [6:09:23<2:01:07,  1.42s/it]
 92%|█████████▏| 56780/61904 [6:09:24<1:58:58,  1.39s/it]
                                                         
{'loss': 2.4565, 'learning_rate': 1.0830416180474521e-07, 'epoch': 14.68}

 92%|█████████▏| 56780/61904 [6:09:24<1:58:58,  1.39s/it]
 92%|█████████▏| 56781/61904 [6:09:25<1:58:08,  1.38s/it]
 92%|█████████▏| 56782/61904 [6:09:27<2:00:51,  1.42s/it]
 92%|█████████▏| 56783/61904 [6:09:28<1:57:48,  1.38s/it]
 92%|█████████▏| 56784/61904 [6:09:30<1:58:58,  1.39s/it]
 92%|█████████▏| 56785/61904 [6:09:31<1:54:17,  1.34s/it]
 92%|█████████▏| 56786/61904 [6:09:32<1:54:40,  1.34s/it]
 92%|█████████▏| 56787/61904 [6:09:33<1:53:15,  1.33s/it]
 92%|█████████▏| 56788/61904 [6:09:35<1:57:32,  1.38s/it]
 92%|█████████▏| 56789/61904 [6:09:36<1:59:35,  1.40s/it]
 92%|█████████▏| 56790/61904 [6:09:38<1:58:41,  1.39s/it]
 92%|█████████▏| 56791/61904 [6:09:39<1:57:12,  1.38s/it]
 92%|█████████▏| 56792/61904 [6:09:40<1:55:20,  1.35s/it]
 92%|█████████▏| 56793/61904 [6:09:42<1:58:27,  1.39s/it]
 92%|█████████▏| 56794/61904 [6:09:43<2:00:56,  1.42s/it]
 92%|█████████▏| 56795/61904 [6:09:45<2:00:05,  1.41s/it]
 92%|█████████▏| 56796/61904 [6:09:46<1:57:18,  1.38s/it]
 92%|█████████▏| 56797/61904 [6:09:47<1:57:00,  1.37s/it]
 92%|█████████▏| 56798/61904 [6:09:49<1:56:08,  1.36s/it]
 92%|█████████▏| 56799/61904 [6:09:50<1:56:58,  1.37s/it]
 92%|█████████▏| 56800/61904 [6:09:52<1:58:30,  1.39s/it]
                                                         
{'loss': 2.4184, 'learning_rate': 1.0827174899520288e-07, 'epoch': 14.68}

 92%|█████████▏| 56800/61904 [6:09:52<1:58:30,  1.39s/it]
 92%|█████████▏| 56801/61904 [6:09:53<1:56:34,  1.37s/it]
 92%|█████████▏| 56802/61904 [6:09:54<1:54:05,  1.34s/it]
 92%|█████████▏| 56803/61904 [6:09:55<1:54:08,  1.34s/it]
 92%|█████████▏| 56804/61904 [6:09:57<1:59:51,  1.41s/it]
 92%|█████████▏| 56805/61904 [6:09:58<1:58:07,  1.39s/it]
 92%|█████████▏| 56806/61904 [6:10:00<1:56:26,  1.37s/it]
 92%|█████████▏| 56807/61904 [6:10:01<1:59:01,  1.40s/it]
 92%|█████████▏| 56808/61904 [6:10:03<2:00:00,  1.41s/it]
 92%|█████████▏| 56809/61904 [6:10:04<2:02:01,  1.44s/it]
 92%|█████████▏| 56810/61904 [6:10:05<1:59:53,  1.41s/it]
 92%|█████████▏| 56811/61904 [6:10:07<2:00:04,  1.41s/it]
 92%|█████████▏| 56812/61904 [6:10:08<2:00:19,  1.42s/it]
 92%|█████████▏| 56813/61904 [6:10:10<1:58:02,  1.39s/it]
 92%|█████████▏| 56814/61904 [6:10:11<2:00:03,  1.42s/it]
 92%|█████████▏| 56815/61904 [6:10:13<1:59:51,  1.41s/it]
 92%|█████████▏| 56816/61904 [6:10:14<2:00:51,  1.43s/it]
 92%|█████████▏| 56817/61904 [6:10:16<2:03:52,  1.46s/it]
 92%|█████████▏| 56818/61904 [6:10:17<2:00:07,  1.42s/it]
 92%|█████████▏| 56819/61904 [6:10:18<2:00:23,  1.42s/it]
 92%|█████████▏| 56820/61904 [6:10:20<1:57:43,  1.39s/it]
                                                         
{'loss': 2.3964, 'learning_rate': 1.0823933618566056e-07, 'epoch': 14.69}

 92%|█████████▏| 56820/61904 [6:10:20<1:57:43,  1.39s/it]
 92%|█████████▏| 56821/61904 [6:10:21<2:03:05,  1.45s/it]
 92%|█████████▏| 56822/61904 [6:10:23<2:00:21,  1.42s/it]
 92%|█████████▏| 56823/61904 [6:10:24<1:56:57,  1.38s/it]
 92%|█████████▏| 56824/61904 [6:10:25<1:57:37,  1.39s/it]
 92%|█████████▏| 56825/61904 [6:10:27<1:56:02,  1.37s/it]
 92%|█████████▏| 56826/61904 [6:10:28<2:02:13,  1.44s/it]
 92%|█████████▏| 56827/61904 [6:10:30<2:01:11,  1.43s/it]
 92%|█████████▏| 56828/61904 [6:10:31<2:02:00,  1.44s/it]
 92%|█████████▏| 56829/61904 [6:10:32<2:00:35,  1.43s/it]
 92%|█████████▏| 56830/61904 [6:10:34<1:59:26,  1.41s/it]
 92%|█████████▏| 56831/61904 [6:10:35<1:58:11,  1.40s/it]
 92%|█████████▏| 56832/61904 [6:10:37<1:58:46,  1.40s/it]
 92%|█████████▏| 56833/61904 [6:10:38<2:01:10,  1.43s/it]
 92%|█████████▏| 56834/61904 [6:10:40<2:01:43,  1.44s/it]
 92%|█████████▏| 56835/61904 [6:10:41<2:02:11,  1.45s/it]
 92%|█████████▏| 56836/61904 [6:10:42<1:59:12,  1.41s/it]
 92%|█████████▏| 56837/61904 [6:10:44<1:57:49,  1.40s/it]
 92%|█████████▏| 56838/61904 [6:10:45<1:57:25,  1.39s/it]
 92%|█████████▏| 56839/61904 [6:10:46<1:57:33,  1.39s/it]
 92%|█████████▏| 56840/61904 [6:10:48<1:57:25,  1.39s/it]
                                                         
{'loss': 2.3597, 'learning_rate': 1.0820692337611823e-07, 'epoch': 14.69}

 92%|█████████▏| 56840/61904 [6:10:48<1:57:25,  1.39s/it]
 92%|█████████▏| 56841/61904 [6:10:49<1:57:06,  1.39s/it]
 92%|█████████▏| 56842/61904 [6:10:51<1:54:52,  1.36s/it]
 92%|█████████▏| 56843/61904 [6:10:52<1:54:40,  1.36s/it]
 92%|█████████▏| 56844/61904 [6:10:53<1:55:08,  1.37s/it]
 92%|█████████▏| 56845/61904 [6:10:55<1:55:23,  1.37s/it]
 92%|█████████▏| 56846/61904 [6:10:56<1:55:02,  1.36s/it]
 92%|█████████▏| 56847/61904 [6:10:58<1:59:07,  1.41s/it]
 92%|█████████▏| 56848/61904 [6:10:59<1:55:19,  1.37s/it]
 92%|█████████▏| 56849/61904 [6:11:00<1:54:43,  1.36s/it]
 92%|█████████▏| 56850/61904 [6:11:01<1:52:10,  1.33s/it]
 92%|█████████▏| 56851/61904 [6:11:03<1:55:01,  1.37s/it]
 92%|█████████▏| 56852/61904 [6:11:04<1:54:33,  1.36s/it]
 92%|█████████▏| 56853/61904 [6:11:06<1:57:58,  1.40s/it]
 92%|█████████▏| 56854/61904 [6:11:07<1:56:18,  1.38s/it]
 92%|█████████▏| 56855/61904 [6:11:09<1:59:00,  1.41s/it]
 92%|█████████▏| 56856/61904 [6:11:10<1:55:17,  1.37s/it]
 92%|█████████▏| 56857/61904 [6:11:11<1:55:58,  1.38s/it]
 92%|█████████▏| 56858/61904 [6:11:13<1:55:10,  1.37s/it]
 92%|█████████▏| 56859/61904 [6:11:14<1:54:33,  1.36s/it]
 92%|█████████▏| 56860/61904 [6:11:15<1:56:02,  1.38s/it]
                                                         
{'loss': 2.4697, 'learning_rate': 1.0817451056657589e-07, 'epoch': 14.7}

 92%|█████████▏| 56860/61904 [6:11:15<1:56:02,  1.38s/it]
 92%|█████████▏| 56861/61904 [6:11:17<1:55:54,  1.38s/it]
 92%|█████████▏| 56862/61904 [6:11:18<1:52:48,  1.34s/it]
 92%|█████████▏| 56863/61904 [6:11:19<1:57:24,  1.40s/it]
 92%|█████████▏| 56864/61904 [6:11:21<1:56:18,  1.38s/it]
 92%|█████████▏| 56865/61904 [6:11:22<1:55:50,  1.38s/it]
 92%|█████████▏| 56866/61904 [6:11:24<2:03:43,  1.47s/it]
 92%|█████████▏| 56867/61904 [6:11:25<2:02:33,  1.46s/it]
 92%|█████████▏| 56868/61904 [6:11:27<2:01:01,  1.44s/it]
 92%|█████████▏| 56869/61904 [6:11:28<1:57:57,  1.41s/it]
 92%|█████████▏| 56870/61904 [6:11:30<1:59:35,  1.43s/it]
 92%|█████████▏| 56871/61904 [6:11:31<1:57:07,  1.40s/it]
 92%|█████████▏| 56872/61904 [6:11:32<1:56:08,  1.38s/it]
 92%|█████████▏| 56873/61904 [6:11:34<1:56:24,  1.39s/it]
 92%|█████████▏| 56874/61904 [6:11:35<1:55:18,  1.38s/it]
 92%|█████████▏| 56875/61904 [6:11:36<1:59:41,  1.43s/it]
 92%|█████████▏| 56876/61904 [6:11:38<2:02:17,  1.46s/it]
 92%|█████████▏| 56877/61904 [6:11:39<1:59:20,  1.42s/it]
 92%|█████████▏| 56878/61904 [6:11:41<2:07:03,  1.52s/it]
 92%|█████████▏| 56879/61904 [6:11:42<2:01:50,  1.45s/it]
 92%|█████████▏| 56880/61904 [6:11:44<1:59:19,  1.43s/it]
                                                         
{'loss': 2.4048, 'learning_rate': 1.0814209775703358e-07, 'epoch': 14.7}

 92%|█████████▏| 56880/61904 [6:11:44<1:59:19,  1.43s/it]
 92%|█████████▏| 56881/61904 [6:11:45<2:02:24,  1.46s/it]
 92%|█████████▏| 56882/61904 [6:11:47<1:57:57,  1.41s/it]
 92%|█████████▏| 56883/61904 [6:11:48<1:56:05,  1.39s/it]
 92%|█████████▏| 56884/61904 [6:11:49<1:57:00,  1.40s/it]
 92%|█████████▏| 56885/61904 [6:11:51<1:52:20,  1.34s/it]
 92%|█████████▏| 56886/61904 [6:11:52<1:51:53,  1.34s/it]
 92%|█████████▏| 56887/61904 [6:11:53<1:54:31,  1.37s/it]
 92%|█████████▏| 56888/61904 [6:11:55<1:53:03,  1.35s/it]
 92%|█████████▏| 56889/61904 [6:11:56<1:57:34,  1.41s/it]
 92%|█████████▏| 56890/61904 [6:11:57<1:55:07,  1.38s/it]
 92%|█████████▏| 56891/61904 [6:11:59<1:53:11,  1.35s/it]
 92%|█████████▏| 56892/61904 [6:12:00<1:56:21,  1.39s/it]
 92%|█████████▏| 56893/61904 [6:12:02<1:56:55,  1.40s/it]
 92%|█████████▏| 56894/61904 [6:12:03<1:56:12,  1.39s/it]
 92%|█████████▏| 56895/61904 [6:12:04<1:55:08,  1.38s/it]
 92%|█████████▏| 56896/61904 [6:12:06<1:54:51,  1.38s/it]
 92%|█████████▏| 56897/61904 [6:12:07<1:54:03,  1.37s/it]
 92%|█████████▏| 56898/61904 [6:12:09<1:55:15,  1.38s/it]
 92%|█████████▏| 56899/61904 [6:12:10<1:52:35,  1.35s/it]
 92%|█████████▏| 56900/61904 [6:12:11<1:55:44,  1.39s/it]
                                                         
{'loss': 2.3896, 'learning_rate': 1.0810968494749124e-07, 'epoch': 14.71}

 92%|█████████▏| 56900/61904 [6:12:11<1:55:44,  1.39s/it]
 92%|█████████▏| 56901/61904 [6:12:13<2:01:20,  1.46s/it]
 92%|█████████▏| 56902/61904 [6:12:14<1:58:44,  1.42s/it]
 92%|█████████▏| 56903/61904 [6:12:16<1:57:15,  1.41s/it]
 92%|█████████▏| 56904/61904 [6:12:17<1:58:59,  1.43s/it]
 92%|█████████▏| 56905/61904 [6:12:18<1:58:00,  1.42s/it]
 92%|█████████▏| 56906/61904 [6:12:20<1:56:00,  1.39s/it]
 92%|█████████▏| 56907/61904 [6:12:21<1:55:14,  1.38s/it]
 92%|█████████▏| 56908/61904 [6:12:23<1:54:46,  1.38s/it]
 92%|█████████▏| 56909/61904 [6:12:24<1:57:04,  1.41s/it]
 92%|█████████▏| 56910/61904 [6:12:25<1:55:26,  1.39s/it]
 92%|█████████▏| 56911/61904 [6:12:27<1:55:09,  1.38s/it]
 92%|█████████▏| 56912/61904 [6:12:28<1:56:55,  1.41s/it]
 92%|█████████▏| 56913/61904 [6:12:30<1:57:15,  1.41s/it]
 92%|█████████▏| 56914/61904 [6:12:31<1:56:37,  1.40s/it]
 92%|█████████▏| 56915/61904 [6:12:32<1:55:01,  1.38s/it]
 92%|█████████▏| 56916/61904 [6:12:34<1:54:24,  1.38s/it]
 92%|█████████▏| 56917/61904 [6:12:35<1:52:45,  1.36s/it]
 92%|█████████▏| 56918/61904 [6:12:36<1:55:04,  1.38s/it]
 92%|█████████▏| 56919/61904 [6:12:38<2:01:44,  1.47s/it]
 92%|█████████▏| 56920/61904 [6:12:39<1:56:44,  1.41s/it]
                                                         
{'loss': 2.4108, 'learning_rate': 1.080772721379489e-07, 'epoch': 14.71}

 92%|█████████▏| 56920/61904 [6:12:39<1:56:44,  1.41s/it]
 92%|█████████▏| 56921/61904 [6:12:41<1:55:17,  1.39s/it]
 92%|█████████▏| 56922/61904 [6:12:42<1:58:04,  1.42s/it]
 92%|█████████▏| 56923/61904 [6:12:44<1:57:58,  1.42s/it]
 92%|█████████▏| 56924/61904 [6:12:45<1:58:09,  1.42s/it]
 92%|█████████▏| 56925/61904 [6:12:46<1:53:54,  1.37s/it]
 92%|█████████▏| 56926/61904 [6:12:48<1:57:06,  1.41s/it]
 92%|█████████▏| 56927/61904 [6:12:49<1:55:15,  1.39s/it]
 92%|█████████▏| 56928/61904 [6:12:51<1:54:40,  1.38s/it]
 92%|█████████▏| 56929/61904 [6:12:52<1:51:21,  1.34s/it]
 92%|█████████▏| 56930/61904 [6:12:53<1:50:10,  1.33s/it]
 92%|█████████▏| 56931/61904 [6:12:55<1:53:09,  1.37s/it]
 92%|█████████▏| 56932/61904 [6:12:56<1:53:51,  1.37s/it]
 92%|█████████▏| 56933/61904 [6:12:57<1:49:32,  1.32s/it]
 92%|█████████▏| 56934/61904 [6:12:59<1:50:54,  1.34s/it]
 92%|█████████▏| 56935/61904 [6:13:00<1:55:50,  1.40s/it]
 92%|█████████▏| 56936/61904 [6:13:01<1:56:13,  1.40s/it]
 92%|█████████▏| 56937/61904 [6:13:03<1:56:34,  1.41s/it]
 92%|█████████▏| 56938/61904 [6:13:04<1:55:25,  1.39s/it]
 92%|█████████▏| 56939/61904 [6:13:06<1:57:03,  1.41s/it]
 92%|█████████▏| 56940/61904 [6:13:07<1:59:02,  1.44s/it]
                                                         
{'loss': 2.3934, 'learning_rate': 1.0804485932840656e-07, 'epoch': 14.72}

 92%|█████████▏| 56940/61904 [6:13:07<1:59:02,  1.44s/it]
 92%|█████████▏| 56941/61904 [6:13:09<1:56:17,  1.41s/it]
 92%|█████████▏| 56942/61904 [6:13:10<1:57:04,  1.42s/it]
 92%|█████████▏| 56943/61904 [6:13:11<1:56:52,  1.41s/it]
 92%|█████████▏| 56944/61904 [6:13:13<1:59:16,  1.44s/it]
 92%|█████████▏| 56945/61904 [6:13:14<1:58:29,  1.43s/it]
 92%|█████████▏| 56946/61904 [6:13:16<1:55:22,  1.40s/it]
 92%|█████████▏| 56947/61904 [6:13:17<1:55:37,  1.40s/it]
 92%|█████████▏| 56948/61904 [6:13:19<1:58:07,  1.43s/it]
 92%|█████████▏| 56949/61904 [6:13:20<1:58:55,  1.44s/it]
 92%|█████████▏| 56950/61904 [6:13:21<1:59:17,  1.44s/it]
 92%|█████████▏| 56951/61904 [6:13:23<1:57:59,  1.43s/it]
 92%|█████████▏| 56952/61904 [6:13:24<1:56:31,  1.41s/it]
 92%|█████████▏| 56953/61904 [6:13:26<1:57:09,  1.42s/it]
 92%|█████████▏| 56954/61904 [6:13:27<1:54:34,  1.39s/it]
 92%|█████████▏| 56955/61904 [6:13:28<1:54:24,  1.39s/it]
 92%|█████████▏| 56956/61904 [6:13:30<1:55:14,  1.40s/it]
 92%|█████████▏| 56957/61904 [6:13:31<1:53:48,  1.38s/it]
 92%|█████████▏| 56958/61904 [6:13:32<1:52:53,  1.37s/it]
 92%|█████████▏| 56959/61904 [6:13:34<1:51:48,  1.36s/it]
 92%|█████████▏| 56960/61904 [6:13:35<1:51:45,  1.36s/it]
                                                         
{'loss': 2.3797, 'learning_rate': 1.0801244651886425e-07, 'epoch': 14.72}

 92%|█████████▏| 56960/61904 [6:13:35<1:51:45,  1.36s/it]
 92%|█████████▏| 56961/61904 [6:13:36<1:51:47,  1.36s/it]
 92%|█████████▏| 56962/61904 [6:13:38<1:51:13,  1.35s/it]
 92%|█████████▏| 56963/61904 [6:13:39<1:51:36,  1.36s/it]
 92%|█████████▏| 56964/61904 [6:13:41<1:57:06,  1.42s/it]
 92%|█████████▏| 56965/61904 [6:13:42<1:54:42,  1.39s/it]
 92%|█████████▏| 56966/61904 [6:13:43<1:52:21,  1.37s/it]
 92%|█████████▏| 56967/61904 [6:13:45<1:51:44,  1.36s/it]
 92%|█████████▏| 56968/61904 [6:13:46<1:53:27,  1.38s/it]
 92%|█████████▏| 56969/61904 [6:13:48<1:54:35,  1.39s/it]
 92%|█████████▏| 56970/61904 [6:13:49<1:53:36,  1.38s/it]
 92%|█████████▏| 56971/61904 [6:13:50<1:57:34,  1.43s/it]
 92%|█████████▏| 56972/61904 [6:13:52<1:59:21,  1.45s/it]
 92%|█████████▏| 56973/61904 [6:13:53<1:55:47,  1.41s/it]
 92%|█████████▏| 56974/61904 [6:13:55<1:55:59,  1.41s/it]
 92%|█████████▏| 56975/61904 [6:13:56<1:52:02,  1.36s/it]
 92%|█████████▏| 56976/61904 [6:13:57<1:50:18,  1.34s/it]
 92%|█████████▏| 56977/61904 [6:13:59<1:50:41,  1.35s/it]
 92%|█████████▏| 56978/61904 [6:14:00<1:56:55,  1.42s/it]
 92%|█████████▏| 56979/61904 [6:14:01<1:51:49,  1.36s/it]
 92%|█████████▏| 56980/61904 [6:14:03<1:58:38,  1.45s/it]
                                                         
{'loss': 2.3676, 'learning_rate': 1.0798003370932191e-07, 'epoch': 14.73}

 92%|█████████▏| 56980/61904 [6:14:03<1:58:38,  1.45s/it]
 92%|█████████▏| 56981/61904 [6:14:05<2:02:28,  1.49s/it]
 92%|█████████▏| 56982/61904 [6:14:06<1:58:42,  1.45s/it]
 92%|█████████▏| 56983/61904 [6:14:08<2:00:13,  1.47s/it]
 92%|█████████▏| 56984/61904 [6:14:09<1:57:17,  1.43s/it]
 92%|█████████▏| 56985/61904 [6:14:10<1:57:18,  1.43s/it]
 92%|█████████▏| 56986/61904 [6:14:12<1:57:28,  1.43s/it]
 92%|█████████▏| 56987/61904 [6:14:13<1:57:17,  1.43s/it]
 92%|█████████▏| 56988/61904 [6:14:15<1:59:02,  1.45s/it]
 92%|█████████▏| 56989/61904 [6:14:16<1:56:47,  1.43s/it]
 92%|█████████▏| 56990/61904 [6:14:17<1:56:15,  1.42s/it]
 92%|█████████▏| 56991/61904 [6:14:19<1:53:48,  1.39s/it]
 92%|█████████▏| 56992/61904 [6:14:20<1:55:19,  1.41s/it]
 92%|█████████▏| 56993/61904 [6:14:22<1:53:44,  1.39s/it]
 92%|█████████▏| 56994/61904 [6:14:23<1:51:28,  1.36s/it]
 92%|█████████▏| 56995/61904 [6:14:24<1:51:54,  1.37s/it]
 92%|█████████▏| 56996/61904 [6:14:26<1:53:28,  1.39s/it]
 92%|█████████▏| 56997/61904 [6:14:27<1:52:29,  1.38s/it]
 92%|█████████▏| 56998/61904 [6:14:28<1:53:38,  1.39s/it]
 92%|█████████▏| 56999/61904 [6:14:30<1:50:19,  1.35s/it]
 92%|█████████▏| 57000/61904 [6:14:31<1:50:32,  1.35s/it]
                                                         
{'loss': 2.426, 'learning_rate': 1.0794762089977957e-07, 'epoch': 14.73}

 92%|█████████▏| 57000/61904 [6:14:31<1:50:32,  1.35s/it]
 92%|█████████▏| 57001/61904 [6:14:33<1:52:42,  1.38s/it]
 92%|█████████▏| 57002/61904 [6:14:34<1:56:09,  1.42s/it]
 92%|█████████▏| 57003/61904 [6:14:35<1:56:07,  1.42s/it]
 92%|█████████▏| 57004/61904 [6:14:37<1:53:15,  1.39s/it]
 92%|█████████▏| 57005/61904 [6:14:38<1:54:53,  1.41s/it]
 92%|█████████▏| 57006/61904 [6:14:40<1:56:11,  1.42s/it]
 92%|█████████▏| 57007/61904 [6:14:41<1:56:10,  1.42s/it]
 92%|█████████▏| 57008/61904 [6:14:43<1:59:14,  1.46s/it]
 92%|█████████▏| 57009/61904 [6:14:44<1:56:44,  1.43s/it]
 92%|█████████▏| 57010/61904 [6:14:45<1:55:29,  1.42s/it]
 92%|█████████▏| 57011/61904 [6:14:47<1:53:07,  1.39s/it]
 92%|█████████▏| 57012/61904 [6:14:48<1:53:52,  1.40s/it]
 92%|█████████▏| 57013/61904 [6:14:50<1:54:06,  1.40s/it]
 92%|█████████▏| 57014/61904 [6:14:51<1:52:51,  1.38s/it]
 92%|█████████▏| 57015/61904 [6:14:52<1:52:35,  1.38s/it]
 92%|█████████▏| 57016/61904 [6:14:54<1:54:02,  1.40s/it]
 92%|█████████▏| 57017/61904 [6:14:55<1:52:05,  1.38s/it]
 92%|█████████▏| 57018/61904 [6:14:57<1:54:33,  1.41s/it]
 92%|█████████▏| 57019/61904 [6:14:58<1:58:06,  1.45s/it]
 92%|█████████▏| 57020/61904 [6:15:00<1:57:55,  1.45s/it]
                                                         
{'loss': 2.4503, 'learning_rate': 1.0791520809023724e-07, 'epoch': 14.74}

 92%|█████████▏| 57020/61904 [6:15:00<1:57:55,  1.45s/it]
 92%|█████████▏| 57021/61904 [6:15:01<1:59:46,  1.47s/it]
 92%|█████████▏| 57022/61904 [6:15:02<1:56:17,  1.43s/it]
 92%|█████████▏| 57023/61904 [6:15:04<1:50:50,  1.36s/it]
 92%|█████████▏| 57024/61904 [6:15:05<1:50:41,  1.36s/it]
 92%|█████████▏| 57025/61904 [6:15:06<1:48:14,  1.33s/it]
 92%|█████████▏| 57026/61904 [6:15:08<1:48:30,  1.33s/it]
 92%|█████████▏| 57027/61904 [6:15:09<1:45:38,  1.30s/it]
 92%|█████████▏| 57028/61904 [6:15:10<1:52:22,  1.38s/it]
 92%|█████████▏| 57029/61904 [6:15:12<1:53:03,  1.39s/it]
 92%|█████████▏| 57030/61904 [6:15:13<1:59:32,  1.47s/it]
 92%|█████████▏| 57031/61904 [6:15:15<1:58:00,  1.45s/it]
 92%|█████████▏| 57032/61904 [6:15:16<1:55:13,  1.42s/it]
 92%|█████████▏| 57033/61904 [6:15:18<1:54:32,  1.41s/it]
 92%|█████████▏| 57034/61904 [6:15:19<1:55:26,  1.42s/it]
 92%|█████████▏| 57035/61904 [6:15:20<1:54:01,  1.41s/it]
 92%|█████████▏| 57036/61904 [6:15:22<1:54:13,  1.41s/it]
 92%|█████████▏| 57037/61904 [6:15:23<1:52:58,  1.39s/it]
 92%|█████████▏| 57038/61904 [6:15:25<1:54:04,  1.41s/it]
 92%|█████████▏| 57039/61904 [6:15:26<1:52:43,  1.39s/it]
 92%|█████████▏| 57040/61904 [6:15:27<1:50:09,  1.36s/it]
                                                         
{'loss': 2.449, 'learning_rate': 1.0788279528069492e-07, 'epoch': 14.74}

 92%|█████████▏| 57040/61904 [6:15:27<1:50:09,  1.36s/it]
 92%|█████████▏| 57041/61904 [6:15:29<1:51:56,  1.38s/it]
 92%|█████████▏| 57042/61904 [6:15:30<1:53:50,  1.40s/it]
 92%|█████████▏| 57043/61904 [6:15:31<1:53:36,  1.40s/it]
 92%|█████████▏| 57044/61904 [6:15:33<1:53:52,  1.41s/it]
 92%|█████████▏| 57045/61904 [6:15:34<1:54:48,  1.42s/it]
 92%|█████████▏| 57046/61904 [6:15:36<1:50:49,  1.37s/it]
 92%|█████████▏| 57047/61904 [6:15:37<1:53:01,  1.40s/it]
 92%|█████████▏| 57048/61904 [6:15:38<1:52:29,  1.39s/it]
 92%|█████████▏| 57049/61904 [6:15:40<1:52:48,  1.39s/it]
 92%|█████████▏| 57050/61904 [6:15:41<1:49:38,  1.36s/it]
 92%|█████████▏| 57051/61904 [6:15:43<1:51:44,  1.38s/it]
 92%|█████████▏| 57052/61904 [6:15:44<1:53:28,  1.40s/it]
 92%|█████████▏| 57053/61904 [6:15:45<1:51:29,  1.38s/it]
 92%|█████████▏| 57054/61904 [6:15:47<1:50:49,  1.37s/it]
 92%|█████████▏| 57055/61904 [6:15:48<1:49:35,  1.36s/it]
 92%|█████████▏| 57056/61904 [6:15:49<1:49:33,  1.36s/it]
 92%|█████████▏| 57057/61904 [6:15:51<1:46:12,  1.31s/it]
 92%|█████████▏| 57058/61904 [6:15:52<1:52:30,  1.39s/it]
 92%|█████████▏| 57059/61904 [6:15:54<1:51:31,  1.38s/it]
 92%|█████████▏| 57060/61904 [6:15:55<1:52:54,  1.40s/it]
                                                         
{'loss': 2.4417, 'learning_rate': 1.0785038247115259e-07, 'epoch': 14.75}

 92%|█████████▏| 57060/61904 [6:15:55<1:52:54,  1.40s/it]
 92%|█████████▏| 57061/61904 [6:15:56<1:53:45,  1.41s/it]
 92%|█████████▏| 57062/61904 [6:15:58<1:53:08,  1.40s/it]
 92%|█████████▏| 57063/61904 [6:15:59<1:53:04,  1.40s/it]
 92%|█████████▏| 57064/61904 [6:16:00<1:50:50,  1.37s/it]
 92%|█████████▏| 57065/61904 [6:16:02<1:48:42,  1.35s/it]
 92%|█████████▏| 57066/61904 [6:16:03<1:51:20,  1.38s/it]
 92%|█████████▏| 57067/61904 [6:16:04<1:48:18,  1.34s/it]
 92%|█████████▏| 57068/61904 [6:16:06<1:49:54,  1.36s/it]
 92%|█████████▏| 57069/61904 [6:16:07<1:48:22,  1.34s/it]
 92%|█████████▏| 57070/61904 [6:16:09<1:48:44,  1.35s/it]
 92%|█████████▏| 57071/61904 [6:16:10<1:48:20,  1.35s/it]
 92%|█████████▏| 57072/61904 [6:16:11<1:50:52,  1.38s/it]
 92%|█████████▏| 57073/61904 [6:16:13<1:55:18,  1.43s/it]
 92%|█████████▏| 57074/61904 [6:16:14<1:56:41,  1.45s/it]
 92%|█████████▏| 57075/61904 [6:16:16<1:54:39,  1.42s/it]
 92%|█████████▏| 57076/61904 [6:16:17<1:55:48,  1.44s/it]
 92%|█████████▏| 57077/61904 [6:16:19<1:52:43,  1.40s/it]
 92%|█████████▏| 57078/61904 [6:16:20<1:52:57,  1.40s/it]
 92%|█████████▏| 57079/61904 [6:16:21<1:54:35,  1.42s/it]
 92%|█████████▏| 57080/61904 [6:16:23<1:53:39,  1.41s/it]
                                                         
{'loss': 2.4536, 'learning_rate': 1.0781796966161025e-07, 'epoch': 14.75}

 92%|█████████▏| 57080/61904 [6:16:23<1:53:39,  1.41s/it]
 92%|█████████▏| 57081/61904 [6:16:24<1:52:49,  1.40s/it]
 92%|█████████▏| 57082/61904 [6:16:26<1:56:24,  1.45s/it]
 92%|█████████▏| 57083/61904 [6:16:27<1:52:59,  1.41s/it]
 92%|█████████▏| 57084/61904 [6:16:28<1:50:13,  1.37s/it]
 92%|█████████▏| 57085/61904 [6:16:30<1:54:37,  1.43s/it]
 92%|█████████▏| 57086/61904 [6:16:31<1:51:32,  1.39s/it]
 92%|█████████▏| 57087/61904 [6:16:33<1:49:48,  1.37s/it]
 92%|█████████▏| 57088/61904 [6:16:34<1:46:22,  1.33s/it]
 92%|█████████▏| 57089/61904 [6:16:35<1:51:51,  1.39s/it]
 92%|█████████▏| 57090/61904 [6:16:37<1:52:16,  1.40s/it]
 92%|█████████▏| 57091/61904 [6:16:38<1:51:29,  1.39s/it]
 92%|█████████▏| 57092/61904 [6:16:39<1:49:40,  1.37s/it]
 92%|█████████▏| 57093/61904 [6:16:41<1:49:18,  1.36s/it]
 92%|█████████▏| 57094/61904 [6:16:42<1:50:00,  1.37s/it]
 92%|█████████▏| 57095/61904 [6:16:43<1:47:29,  1.34s/it]
 92%|█████████▏| 57096/61904 [6:16:45<1:50:24,  1.38s/it]
 92%|█████████▏| 57097/61904 [6:16:46<1:46:31,  1.33s/it]
 92%|█████████▏| 57098/61904 [6:16:47<1:48:28,  1.35s/it]
 92%|█████████▏| 57099/61904 [6:16:49<1:51:11,  1.39s/it]
 92%|█████████▏| 57100/61904 [6:16:50<1:49:29,  1.37s/it]
                                                         
{'loss': 2.4133, 'learning_rate': 1.0778555685206791e-07, 'epoch': 14.76}

 92%|█████████▏| 57100/61904 [6:16:50<1:49:29,  1.37s/it]
 92%|█████████▏| 57101/61904 [6:16:52<1:47:08,  1.34s/it]
 92%|█████████▏| 57102/61904 [6:16:53<1:55:33,  1.44s/it]
 92%|█████████▏| 57103/61904 [6:16:55<1:52:39,  1.41s/it]
 92%|█████████▏| 57104/61904 [6:16:56<1:50:29,  1.38s/it]
 92%|█████████▏| 57105/61904 [6:16:57<1:49:05,  1.36s/it]
 92%|█████████▏| 57106/61904 [6:16:58<1:47:09,  1.34s/it]
 92%|█████████▏| 57107/61904 [6:17:00<1:49:40,  1.37s/it]
 92%|█████████▏| 57108/61904 [6:17:01<1:49:54,  1.38s/it]
 92%|█████████▏| 57109/61904 [6:17:03<1:47:43,  1.35s/it]
 92%|█████████▏| 57110/61904 [6:17:04<1:52:48,  1.41s/it]
 92%|█████████▏| 57111/61904 [6:17:05<1:49:15,  1.37s/it]
 92%|█████████▏| 57112/61904 [6:17:07<1:47:06,  1.34s/it]
 92%|█████████▏| 57113/61904 [6:17:08<1:52:18,  1.41s/it]
 92%|█████████▏| 57114/61904 [6:17:10<1:53:25,  1.42s/it]
 92%|█████████▏| 57115/61904 [6:17:11<1:50:40,  1.39s/it]
 92%|█████████▏| 57116/61904 [6:17:12<1:50:08,  1.38s/it]
 92%|█████████▏| 57117/61904 [6:17:14<1:53:08,  1.42s/it]
 92%|█████████▏| 57118/61904 [6:17:15<1:52:02,  1.40s/it]
 92%|█████████▏| 57119/61904 [6:17:17<1:50:34,  1.39s/it]
 92%|█████████▏| 57120/61904 [6:17:18<1:49:43,  1.38s/it]
                                                         
{'loss': 2.4921, 'learning_rate': 1.077531440425256e-07, 'epoch': 14.76}

 92%|█████████▏| 57120/61904 [6:17:18<1:49:43,  1.38s/it]
 92%|█████████▏| 57121/61904 [6:17:19<1:52:07,  1.41s/it]
 92%|█████████▏| 57122/61904 [6:17:21<1:50:06,  1.38s/it]
 92%|█████████▏| 57123/61904 [6:17:22<1:53:23,  1.42s/it]
 92%|█████████▏| 57124/61904 [6:17:24<1:53:50,  1.43s/it]
 92%|█████████▏| 57125/61904 [6:17:25<1:50:46,  1.39s/it]
 92%|█████████▏| 57126/61904 [6:17:26<1:50:48,  1.39s/it]
 92%|█████████▏| 57127/61904 [6:17:28<1:49:20,  1.37s/it]
 92%|█████████▏| 57128/61904 [6:17:29<1:46:50,  1.34s/it]
 92%|█████████▏| 57129/61904 [6:17:30<1:46:08,  1.33s/it]
 92%|█████████▏| 57130/61904 [6:17:32<1:46:13,  1.34s/it]
 92%|█████████▏| 57131/61904 [6:17:33<1:43:32,  1.30s/it]
 92%|█████████▏| 57132/61904 [6:17:34<1:44:21,  1.31s/it]
 92%|█████████▏| 57133/61904 [6:17:36<1:50:10,  1.39s/it]
 92%|█████████▏| 57134/61904 [6:17:37<1:49:40,  1.38s/it]
 92%|█████████▏| 57135/61904 [6:17:39<1:49:53,  1.38s/it]
 92%|█████████▏| 57136/61904 [6:17:40<1:47:44,  1.36s/it]
 92%|█████████▏| 57137/61904 [6:17:41<1:47:08,  1.35s/it]
 92%|█████████▏| 57138/61904 [6:17:43<1:50:36,  1.39s/it]
 92%|█████████▏| 57139/61904 [6:17:44<1:53:48,  1.43s/it]
 92%|█████████▏| 57140/61904 [6:17:46<1:54:53,  1.45s/it]
                                                         
{'loss': 2.4226, 'learning_rate': 1.0772073123298326e-07, 'epoch': 14.77}

 92%|█████████▏| 57140/61904 [6:17:46<1:54:53,  1.45s/it]
 92%|█████████▏| 57141/61904 [6:17:47<1:55:21,  1.45s/it]
 92%|█████████▏| 57142/61904 [6:17:48<1:50:44,  1.40s/it]
 92%|█████████▏| 57143/61904 [6:17:50<1:49:20,  1.38s/it]
 92%|█████████▏| 57144/61904 [6:17:51<1:50:22,  1.39s/it]
 92%|█████████▏| 57145/61904 [6:17:52<1:48:16,  1.37s/it]
 92%|█████████▏| 57146/61904 [6:17:54<1:47:25,  1.35s/it]
 92%|█████████▏| 57147/61904 [6:17:55<1:46:34,  1.34s/it]
 92%|█████████▏| 57148/61904 [6:17:56<1:44:42,  1.32s/it]
 92%|█████████▏| 57149/61904 [6:17:58<1:45:45,  1.33s/it]
 92%|█████████▏| 57150/61904 [6:17:59<1:48:36,  1.37s/it]
 92%|█████████▏| 57151/61904 [6:18:01<1:48:43,  1.37s/it]
 92%|█████████▏| 57152/61904 [6:18:02<1:47:19,  1.36s/it]
 92%|█████████▏| 57153/61904 [6:18:03<1:50:55,  1.40s/it]
 92%|█████████▏| 57154/61904 [6:18:05<1:50:54,  1.40s/it]
 92%|█████████▏| 57155/61904 [6:18:06<1:47:10,  1.35s/it]
 92%|█████████▏| 57156/61904 [6:18:07<1:48:35,  1.37s/it]
 92%|█████████▏| 57157/61904 [6:18:09<1:49:25,  1.38s/it]
 92%|█████████▏| 57158/61904 [6:18:10<1:46:26,  1.35s/it]
 92%|█████████▏| 57159/61904 [6:18:11<1:43:57,  1.31s/it]
 92%|█████████▏| 57160/61904 [6:18:13<1:45:50,  1.34s/it]
                                                         
{'loss': 2.4188, 'learning_rate': 1.0768831842344092e-07, 'epoch': 14.77}

 92%|█████████▏| 57160/61904 [6:18:13<1:45:50,  1.34s/it]
 92%|█████████▏| 57161/61904 [6:18:14<1:46:46,  1.35s/it]
 92%|█████████▏| 57162/61904 [6:18:16<1:48:34,  1.37s/it]
 92%|█████████▏| 57163/61904 [6:18:17<1:48:50,  1.38s/it]
 92%|█████████▏| 57164/61904 [6:18:18<1:49:50,  1.39s/it]
 92%|█████████▏| 57165/61904 [6:18:20<1:49:26,  1.39s/it]
 92%|█████████▏| 57166/61904 [6:18:21<1:45:18,  1.33s/it]
 92%|█████████▏| 57167/61904 [6:18:22<1:44:26,  1.32s/it]
 92%|█████████▏| 57168/61904 [6:18:24<1:44:43,  1.33s/it]
 92%|█████████▏| 57169/61904 [6:18:25<1:49:19,  1.39s/it]
 92%|█████████▏| 57170/61904 [6:18:26<1:45:32,  1.34s/it]
 92%|█████████▏| 57171/61904 [6:18:28<1:48:05,  1.37s/it]
 92%|█████████▏| 57172/61904 [6:18:29<1:47:35,  1.36s/it]
 92%|█████████▏| 57173/61904 [6:18:31<1:47:09,  1.36s/it]
 92%|█████████▏| 57174/61904 [6:18:32<1:45:56,  1.34s/it]
 92%|█████████▏| 57175/61904 [6:18:33<1:47:36,  1.37s/it]
 92%|█████████▏| 57176/61904 [6:18:35<1:45:42,  1.34s/it]
 92%|█████████▏| 57177/61904 [6:18:36<1:44:05,  1.32s/it]
 92%|█████████▏| 57178/61904 [6:18:37<1:44:57,  1.33s/it]
 92%|█████████▏| 57179/61904 [6:18:39<1:47:19,  1.36s/it]
 92%|█████████▏| 57180/61904 [6:18:40<1:46:17,  1.35s/it]
                                                         
{'loss': 2.4282, 'learning_rate': 1.0765590561389861e-07, 'epoch': 14.78}

 92%|█████████▏| 57180/61904 [6:18:40<1:46:17,  1.35s/it]
 92%|█████████▏| 57181/61904 [6:18:41<1:46:50,  1.36s/it]
 92%|█████████▏| 57182/61904 [6:18:43<1:46:48,  1.36s/it]
 92%|█████████▏| 57183/61904 [6:18:44<1:47:47,  1.37s/it]
 92%|█████████▏| 57184/61904 [6:18:45<1:45:22,  1.34s/it]
 92%|█████████▏| 57185/61904 [6:18:47<1:46:13,  1.35s/it]
 92%|█████████▏| 57186/61904 [6:18:48<1:44:32,  1.33s/it]
 92%|█████████▏| 57187/61904 [6:18:49<1:47:49,  1.37s/it]
 92%|█████████▏| 57188/61904 [6:18:51<1:47:02,  1.36s/it]
 92%|█████████▏| 57189/61904 [6:18:52<1:46:44,  1.36s/it]
 92%|█████████▏| 57190/61904 [6:18:54<1:48:28,  1.38s/it]
 92%|█████████▏| 57191/61904 [6:18:55<1:49:33,  1.39s/it]
 92%|█████████▏| 57192/61904 [6:18:56<1:47:48,  1.37s/it]
 92%|█████████▏| 57193/61904 [6:18:58<1:50:24,  1.41s/it]
 92%|█████████▏| 57194/61904 [6:18:59<1:48:48,  1.39s/it]
 92%|█████████▏| 57195/61904 [6:19:00<1:47:29,  1.37s/it]
 92%|█████████▏| 57196/61904 [6:19:02<1:47:54,  1.38s/it]
 92%|█████████▏| 57197/61904 [6:19:03<1:47:04,  1.36s/it]
 92%|█████████▏| 57198/61904 [6:19:05<1:47:35,  1.37s/it]
 92%|█████████▏| 57199/61904 [6:19:06<1:45:15,  1.34s/it]
 92%|█████████▏| 57200/61904 [6:19:07<1:46:57,  1.36s/it]
                                                         
{'loss': 2.4692, 'learning_rate': 1.0762349280435627e-07, 'epoch': 14.78}

 92%|█████████▏| 57200/61904 [6:19:07<1:46:57,  1.36s/it]
 92%|█████████▏| 57201/61904 [6:19:09<1:48:07,  1.38s/it]
 92%|█████████▏| 57202/61904 [6:19:10<1:46:55,  1.36s/it]
 92%|█████████▏| 57203/61904 [6:19:11<1:44:04,  1.33s/it]
 92%|█████████▏| 57204/61904 [6:19:13<1:44:08,  1.33s/it]
 92%|█████████▏| 57205/61904 [6:19:14<1:45:29,  1.35s/it]
 92%|█████████▏| 57206/61904 [6:19:15<1:46:47,  1.36s/it]
 92%|█████████▏| 57207/61904 [6:19:17<1:44:46,  1.34s/it]
 92%|█████████▏| 57208/61904 [6:19:18<1:48:20,  1.38s/it]
 92%|█████████▏| 57209/61904 [6:19:20<1:51:32,  1.43s/it]
 92%|█████████▏| 57210/61904 [6:19:21<1:49:22,  1.40s/it]
 92%|█████████▏| 57211/61904 [6:19:22<1:49:26,  1.40s/it]
 92%|█████████▏| 57212/61904 [6:19:24<1:50:14,  1.41s/it]
 92%|█████████▏| 57213/61904 [6:19:25<1:47:22,  1.37s/it]
 92%|█████████▏| 57214/61904 [6:19:26<1:46:22,  1.36s/it]
 92%|█████████▏| 57215/61904 [6:19:28<1:50:26,  1.41s/it]
 92%|█████████▏| 57216/61904 [6:19:29<1:48:00,  1.38s/it]
 92%|█████████▏| 57217/61904 [6:19:31<1:47:30,  1.38s/it]
 92%|█████████▏| 57218/61904 [6:19:32<1:48:12,  1.39s/it]
 92%|█████████▏| 57219/61904 [6:19:33<1:46:23,  1.36s/it]
 92%|█████████▏| 57220/61904 [6:19:35<1:44:59,  1.34s/it]
                                                         
{'loss': 2.394, 'learning_rate': 1.0759107999481393e-07, 'epoch': 14.79}

 92%|█████████▏| 57220/61904 [6:19:35<1:44:59,  1.34s/it]
 92%|█████████▏| 57221/61904 [6:19:36<1:46:42,  1.37s/it]
 92%|█████████▏| 57222/61904 [6:19:38<1:49:24,  1.40s/it]
 92%|█████████▏| 57223/61904 [6:19:39<1:47:57,  1.38s/it]
 92%|█████████▏| 57224/61904 [6:19:40<1:46:15,  1.36s/it]
 92%|█████████▏| 57225/61904 [6:19:42<1:46:28,  1.37s/it]
 92%|█████████▏| 57226/61904 [6:19:43<1:47:27,  1.38s/it]
 92%|█████████▏| 57227/61904 [6:19:44<1:46:02,  1.36s/it]
 92%|█████████▏| 57228/61904 [6:19:46<1:47:22,  1.38s/it]
 92%|█████████▏| 57229/61904 [6:19:47<1:44:55,  1.35s/it]
 92%|█████████▏| 57230/61904 [6:19:48<1:47:38,  1.38s/it]
 92%|█████████▏| 57231/61904 [6:19:50<1:48:43,  1.40s/it]
 92%|█████████▏| 57232/61904 [6:19:51<1:49:03,  1.40s/it]
 92%|█████████▏| 57233/61904 [6:19:53<1:51:54,  1.44s/it]
 92%|█████████▏| 57234/61904 [6:19:54<1:50:09,  1.42s/it]
 92%|█████████▏| 57235/61904 [6:19:56<1:53:05,  1.45s/it]
 92%|█████████▏| 57236/61904 [6:19:57<1:50:43,  1.42s/it]
 92%|█████████▏| 57237/61904 [6:19:59<1:50:31,  1.42s/it]
 92%|█████████▏| 57238/61904 [6:20:00<1:47:10,  1.38s/it]
 92%|█████████▏| 57239/61904 [6:20:01<1:50:24,  1.42s/it]
 92%|█████████▏| 57240/61904 [6:20:03<1:48:17,  1.39s/it]
                                                         
{'loss': 2.4628, 'learning_rate': 1.075586671852716e-07, 'epoch': 14.79}

 92%|█████████▏| 57240/61904 [6:20:03<1:48:17,  1.39s/it]
 92%|█████████▏| 57241/61904 [6:20:04<1:46:28,  1.37s/it]
 92%|█████████▏| 57242/61904 [6:20:05<1:43:46,  1.34s/it]
 92%|█████████▏| 57243/61904 [6:20:07<1:43:48,  1.34s/it]
 92%|█████████▏| 57244/61904 [6:20:08<1:44:06,  1.34s/it]
 92%|█████████▏| 57245/61904 [6:20:09<1:45:33,  1.36s/it]
 92%|█████████▏| 57246/61904 [6:20:11<1:43:59,  1.34s/it]
 92%|█████████▏| 57247/61904 [6:20:12<1:43:31,  1.33s/it]
 92%|█████████▏| 57248/61904 [6:20:13<1:42:25,  1.32s/it]
 92%|█████████▏| 57249/61904 [6:20:15<1:43:55,  1.34s/it]
 92%|█████████▏| 57250/61904 [6:20:16<1:47:50,  1.39s/it]
 92%|█████████▏| 57251/61904 [6:20:17<1:46:43,  1.38s/it]
 92%|█████████▏| 57252/61904 [6:20:19<1:49:19,  1.41s/it]
 92%|█████████▏| 57253/61904 [6:20:20<1:51:05,  1.43s/it]
 92%|█████████▏| 57254/61904 [6:20:22<1:51:56,  1.44s/it]
 92%|█████████▏| 57255/61904 [6:20:23<1:48:26,  1.40s/it]
 92%|█████████▏| 57256/61904 [6:20:25<1:48:34,  1.40s/it]
 92%|█████████▏| 57257/61904 [6:20:26<1:48:46,  1.40s/it]
 92%|█████████▏| 57258/61904 [6:20:27<1:45:53,  1.37s/it]
 92%|█████████▏| 57259/61904 [6:20:29<1:43:30,  1.34s/it]
 92%|█████████▏| 57260/61904 [6:20:30<1:43:16,  1.33s/it]
                                                         
{'loss': 2.4294, 'learning_rate': 1.0752625437572928e-07, 'epoch': 14.8}

 92%|█████████▏| 57260/61904 [6:20:30<1:43:16,  1.33s/it]
 92%|█████████▏| 57261/61904 [6:20:31<1:44:39,  1.35s/it]
 93%|█████████▎| 57262/61904 [6:20:33<1:45:35,  1.36s/it]
 93%|█████████▎| 57263/61904 [6:20:34<1:48:45,  1.41s/it]
 93%|█████████▎| 57264/61904 [6:20:36<1:47:35,  1.39s/it]
 93%|█████████▎| 57265/61904 [6:20:37<1:48:26,  1.40s/it]
 93%|█████████▎| 57266/61904 [6:20:38<1:48:02,  1.40s/it]
 93%|█████████▎| 57267/61904 [6:20:40<1:48:59,  1.41s/it]
 93%|█████████▎| 57268/61904 [6:20:41<1:48:25,  1.40s/it]
 93%|█████████▎| 57269/61904 [6:20:43<1:48:26,  1.40s/it]
 93%|█████████▎| 57270/61904 [6:20:44<1:48:03,  1.40s/it]
 93%|█████████▎| 57271/61904 [6:20:45<1:49:40,  1.42s/it]
 93%|█████████▎| 57272/61904 [6:20:47<1:46:10,  1.38s/it]
 93%|█████████▎| 57273/61904 [6:20:48<1:48:43,  1.41s/it]
 93%|█████████▎| 57274/61904 [6:20:50<1:48:20,  1.40s/it]
 93%|█████████▎| 57275/61904 [6:20:51<1:45:31,  1.37s/it]
 93%|█████████▎| 57276/61904 [6:20:52<1:43:40,  1.34s/it]
 93%|█████████▎| 57277/61904 [6:20:54<1:44:26,  1.35s/it]
 93%|█████████▎| 57278/61904 [6:20:55<1:44:35,  1.36s/it]
 93%|█████████▎| 57279/61904 [6:20:56<1:43:08,  1.34s/it]
 93%|█████████▎| 57280/61904 [6:20:58<1:47:08,  1.39s/it]
                                                         
{'loss': 2.4667, 'learning_rate': 1.0749384156618695e-07, 'epoch': 14.8}

 93%|█████████▎| 57280/61904 [6:20:58<1:47:08,  1.39s/it]
 93%|█████████▎| 57281/61904 [6:20:59<1:44:31,  1.36s/it]
 93%|█████████▎| 57282/61904 [6:21:00<1:47:04,  1.39s/it]
 93%|█████████▎| 57283/61904 [6:21:02<1:44:06,  1.35s/it]
 93%|█████████▎| 57284/61904 [6:21:03<1:47:32,  1.40s/it]
 93%|█████████▎| 57285/61904 [6:21:05<1:47:26,  1.40s/it]
 93%|█████████▎| 57286/61904 [6:21:06<1:48:54,  1.41s/it]
 93%|█████████▎| 57287/61904 [6:21:07<1:46:18,  1.38s/it]
 93%|█████████▎| 57288/61904 [6:21:09<1:45:18,  1.37s/it]
 93%|█████████▎| 57289/61904 [6:21:10<1:48:23,  1.41s/it]
 93%|█████████▎| 57290/61904 [6:21:12<1:47:02,  1.39s/it]
 93%|█████████▎| 57291/61904 [6:21:13<1:50:15,  1.43s/it]
 93%|█████████▎| 57292/61904 [6:21:14<1:46:53,  1.39s/it]
 93%|█████████▎| 57293/61904 [6:21:16<1:46:26,  1.39s/it]
 93%|█████████▎| 57294/61904 [6:21:17<1:47:37,  1.40s/it]
 93%|█████████▎| 57295/61904 [6:21:19<1:45:36,  1.37s/it]
 93%|█████████▎| 57296/61904 [6:21:20<1:49:20,  1.42s/it]
 93%|█████████▎| 57297/61904 [6:21:22<1:50:21,  1.44s/it]
 93%|█████████▎| 57298/61904 [6:21:23<1:50:23,  1.44s/it]
 93%|█████████▎| 57299/61904 [6:21:24<1:50:07,  1.43s/it]
 93%|█████████▎| 57300/61904 [6:21:26<1:48:15,  1.41s/it]
                                                         
{'loss': 2.4368, 'learning_rate': 1.0746142875664461e-07, 'epoch': 14.81}

 93%|█████████▎| 57300/61904 [6:21:26<1:48:15,  1.41s/it]
 93%|█████████▎| 57301/61904 [6:21:27<1:50:56,  1.45s/it]
 93%|█████████▎| 57302/61904 [6:21:29<1:48:40,  1.42s/it]
 93%|█████████▎| 57303/61904 [6:21:30<1:48:07,  1.41s/it]
 93%|█████████▎| 57304/61904 [6:21:31<1:48:31,  1.42s/it]
 93%|█████████▎| 57305/61904 [6:21:33<1:46:52,  1.39s/it]
 93%|█████████▎| 57306/61904 [6:21:34<1:44:58,  1.37s/it]
 93%|█████████▎| 57307/61904 [6:21:36<1:47:56,  1.41s/it]
 93%|█████████▎| 57308/61904 [6:21:37<1:46:42,  1.39s/it]
 93%|█████████▎| 57309/61904 [6:21:38<1:46:44,  1.39s/it]
 93%|█████████▎| 57310/61904 [6:21:40<1:46:02,  1.38s/it]
 93%|█████████▎| 57311/61904 [6:21:41<1:47:22,  1.40s/it]
 93%|█████████▎| 57312/61904 [6:21:43<1:48:39,  1.42s/it]
 93%|█████████▎| 57313/61904 [6:21:44<1:47:30,  1.41s/it]
 93%|█████████▎| 57314/61904 [6:21:45<1:49:44,  1.43s/it]
 93%|█████████▎| 57315/61904 [6:21:47<1:47:47,  1.41s/it]
 93%|█████████▎| 57316/61904 [6:21:48<1:46:05,  1.39s/it]
 93%|█████████▎| 57317/61904 [6:21:50<1:46:50,  1.40s/it]
 93%|█████████▎| 57318/61904 [6:21:51<1:46:26,  1.39s/it]
 93%|█████████▎| 57319/61904 [6:21:52<1:47:20,  1.40s/it]
 93%|█████████▎| 57320/61904 [6:21:54<1:48:32,  1.42s/it]
                                                         
{'loss': 2.3656, 'learning_rate': 1.0742901594710227e-07, 'epoch': 14.81}

 93%|█████████▎| 57320/61904 [6:21:54<1:48:32,  1.42s/it]
 93%|█████████▎| 57321/61904 [6:21:55<1:48:00,  1.41s/it]
 93%|█████████▎| 57322/61904 [6:21:56<1:43:34,  1.36s/it]
 93%|█████████▎| 57323/61904 [6:21:58<1:39:26,  1.30s/it]
 93%|█████████▎| 57324/61904 [6:21:59<1:44:00,  1.36s/it]
 93%|█████████▎| 57325/61904 [6:22:00<1:41:52,  1.33s/it]
 93%|█████████▎| 57326/61904 [6:22:02<1:41:53,  1.34s/it]
 93%|█████████▎| 57327/61904 [6:22:03<1:41:23,  1.33s/it]
 93%|█████████▎| 57328/61904 [6:22:04<1:42:21,  1.34s/it]
 93%|█████████▎| 57329/61904 [6:22:06<1:42:38,  1.35s/it]
 93%|█████████▎| 57330/61904 [6:22:07<1:42:39,  1.35s/it]
 93%|█████████▎| 57331/61904 [6:22:09<1:42:58,  1.35s/it]
 93%|█████████▎| 57332/61904 [6:22:10<1:42:23,  1.34s/it]
 93%|█████████▎| 57333/61904 [6:22:11<1:44:14,  1.37s/it]
 93%|█████████▎| 57334/61904 [6:22:13<1:43:58,  1.37s/it]
 93%|█████████▎| 57335/61904 [6:22:14<1:42:29,  1.35s/it]
 93%|█████████▎| 57336/61904 [6:22:15<1:42:38,  1.35s/it]
 93%|█████████▎| 57337/61904 [6:22:17<1:43:10,  1.36s/it]
 93%|█████████▎| 57338/61904 [6:22:18<1:44:58,  1.38s/it]
 93%|█████████▎| 57339/61904 [6:22:20<1:45:31,  1.39s/it]
 93%|█████████▎| 57340/61904 [6:22:21<1:43:37,  1.36s/it]
                                                         
{'loss': 2.4152, 'learning_rate': 1.0739660313755996e-07, 'epoch': 14.82}

 93%|█████████▎| 57340/61904 [6:22:21<1:43:37,  1.36s/it]
 93%|█████████▎| 57341/61904 [6:22:22<1:43:07,  1.36s/it]
 93%|█████████▎| 57342/61904 [6:22:23<1:40:28,  1.32s/it]
 93%|█████████▎| 57343/61904 [6:22:25<1:43:22,  1.36s/it]
 93%|█████████▎| 57344/61904 [6:22:26<1:48:15,  1.42s/it]
 93%|█████████▎| 57345/61904 [6:22:28<1:47:16,  1.41s/it]
 93%|█████████▎| 57346/61904 [6:22:29<1:46:38,  1.40s/it]
 93%|█████████▎| 57347/61904 [6:22:31<1:49:48,  1.45s/it]
 93%|█████████▎| 57348/61904 [6:22:32<1:49:37,  1.44s/it]
 93%|█████████▎| 57349/61904 [6:22:34<1:49:21,  1.44s/it]
 93%|█████████▎| 57350/61904 [6:22:35<1:50:37,  1.46s/it]
 93%|█████████▎| 57351/61904 [6:22:36<1:49:05,  1.44s/it]
 93%|█████████▎| 57352/61904 [6:22:38<1:49:19,  1.44s/it]
 93%|█████████▎| 57353/61904 [6:22:39<1:47:00,  1.41s/it]
 93%|█████████▎| 57354/61904 [6:22:41<1:46:36,  1.41s/it]
 93%|█████████▎| 57355/61904 [6:22:42<1:45:03,  1.39s/it]
 93%|█████████▎| 57356/61904 [6:22:43<1:43:04,  1.36s/it]
 93%|█████████▎| 57357/61904 [6:22:45<1:42:41,  1.36s/it]
 93%|█████████▎| 57358/61904 [6:22:46<1:41:47,  1.34s/it]
 93%|█████████▎| 57359/61904 [6:22:47<1:40:15,  1.32s/it]
 93%|█████████▎| 57360/61904 [6:22:49<1:38:53,  1.31s/it]
                                                         
{'loss': 2.4619, 'learning_rate': 1.0736419032801762e-07, 'epoch': 14.83}

 93%|█████████▎| 57360/61904 [6:22:49<1:38:53,  1.31s/it]
 93%|█████████▎| 57361/61904 [6:22:50<1:40:05,  1.32s/it]
 93%|█████████▎| 57362/61904 [6:22:51<1:39:26,  1.31s/it]
 93%|█████████▎| 57363/61904 [6:22:52<1:37:59,  1.29s/it]
 93%|█████████▎| 57364/61904 [6:22:54<1:39:23,  1.31s/it]
 93%|█████████▎| 57365/61904 [6:22:55<1:38:35,  1.30s/it]
 93%|█████████▎| 57366/61904 [6:22:56<1:40:13,  1.33s/it]
 93%|█████████▎| 57367/61904 [6:22:58<1:44:26,  1.38s/it]
 93%|█████████▎| 57368/61904 [6:22:59<1:44:08,  1.38s/it]
 93%|█████████▎| 57369/61904 [6:23:01<1:46:30,  1.41s/it]
 93%|█████████▎| 57370/61904 [6:23:02<1:45:11,  1.39s/it]
 93%|█████████▎| 57371/61904 [6:23:04<1:44:40,  1.39s/it]
 93%|█████████▎| 57372/61904 [6:23:05<1:44:31,  1.38s/it]
 93%|█████████▎| 57373/61904 [6:23:06<1:43:10,  1.37s/it]
 93%|█████████▎| 57374/61904 [6:23:08<1:41:42,  1.35s/it]
 93%|█████████▎| 57375/61904 [6:23:09<1:41:58,  1.35s/it]
 93%|█████████▎| 57376/61904 [6:23:10<1:44:28,  1.38s/it]
 93%|█████████▎| 57377/61904 [6:23:12<1:47:26,  1.42s/it]
 93%|█████████▎| 57378/61904 [6:23:13<1:47:23,  1.42s/it]
 93%|█████████▎| 57379/61904 [6:23:15<1:47:48,  1.43s/it]
 93%|█████████▎| 57380/61904 [6:23:16<1:46:28,  1.41s/it]
                                                         
{'loss': 2.4696, 'learning_rate': 1.0733177751847528e-07, 'epoch': 14.83}

 93%|█████████▎| 57380/61904 [6:23:16<1:46:28,  1.41s/it]
 93%|█████████▎| 57381/61904 [6:23:17<1:44:49,  1.39s/it]
 93%|█████████▎| 57382/61904 [6:23:19<1:44:36,  1.39s/it]
 93%|█████████▎| 57383/61904 [6:23:20<1:40:56,  1.34s/it]
 93%|█████████▎| 57384/61904 [6:23:21<1:42:31,  1.36s/it]
 93%|█████████▎| 57385/61904 [6:23:23<1:39:22,  1.32s/it]
 93%|█████████▎| 57386/61904 [6:23:24<1:39:10,  1.32s/it]
 93%|█████████▎| 57387/61904 [6:23:25<1:42:02,  1.36s/it]
 93%|█████████▎| 57388/61904 [6:23:27<1:45:47,  1.41s/it]
 93%|█████████▎| 57389/61904 [6:23:28<1:45:21,  1.40s/it]
 93%|█████████▎| 57390/61904 [6:23:30<1:46:04,  1.41s/it]
 93%|█████████▎| 57391/61904 [6:23:31<1:44:21,  1.39s/it]
 93%|█████████▎| 57392/61904 [6:23:32<1:42:41,  1.37s/it]
 93%|█████████▎| 57393/61904 [6:23:34<1:52:43,  1.50s/it]
 93%|█████████▎| 57394/61904 [6:23:36<1:50:16,  1.47s/it]
 93%|█████████▎| 57395/61904 [6:23:37<1:48:09,  1.44s/it]
 93%|█████████▎| 57396/61904 [6:23:38<1:47:26,  1.43s/it]
 93%|█████████▎| 57397/61904 [6:23:40<1:44:49,  1.40s/it]
 93%|█████████▎| 57398/61904 [6:23:41<1:47:43,  1.43s/it]
 93%|█████████▎| 57399/61904 [6:23:43<1:46:12,  1.41s/it]
 93%|█████████▎| 57400/61904 [6:23:44<1:43:38,  1.38s/it]
                                                         
{'loss': 2.4359, 'learning_rate': 1.0729936470893294e-07, 'epoch': 14.84}

 93%|█████████▎| 57400/61904 [6:23:44<1:43:38,  1.38s/it]
 93%|█████████▎| 57401/61904 [6:23:45<1:44:47,  1.40s/it]
 93%|█████████▎| 57402/61904 [6:23:47<1:43:02,  1.37s/it]
 93%|█████████▎| 57403/61904 [6:23:48<1:41:08,  1.35s/it]
 93%|█████████▎| 57404/61904 [6:23:49<1:42:12,  1.36s/it]
 93%|█████████▎| 57405/61904 [6:23:51<1:43:35,  1.38s/it]
 93%|█████████▎| 57406/61904 [6:23:52<1:41:41,  1.36s/it]
 93%|█████████▎| 57407/61904 [6:23:54<1:43:08,  1.38s/it]
 93%|█████████▎| 57408/61904 [6:23:55<1:41:57,  1.36s/it]
 93%|█████████▎| 57409/61904 [6:23:56<1:39:51,  1.33s/it]
 93%|█████████▎| 57410/61904 [6:23:57<1:39:46,  1.33s/it]
 93%|█████████▎| 57411/61904 [6:23:59<1:41:18,  1.35s/it]
 93%|█████████▎| 57412/61904 [6:24:00<1:42:04,  1.36s/it]
 93%|█████████▎| 57413/61904 [6:24:02<1:45:44,  1.41s/it]
 93%|█████████▎| 57414/61904 [6:24:03<1:45:49,  1.41s/it]
 93%|█████████▎| 57415/61904 [6:24:05<1:50:48,  1.48s/it]
 93%|█████████▎| 57416/61904 [6:24:06<1:47:28,  1.44s/it]
 93%|█████████▎| 57417/61904 [6:24:07<1:45:15,  1.41s/it]
 93%|█████████▎| 57418/61904 [6:24:09<1:42:58,  1.38s/it]
 93%|█████████▎| 57419/61904 [6:24:10<1:45:27,  1.41s/it]
 93%|█████████▎| 57420/61904 [6:24:12<1:44:45,  1.40s/it]
                                                         
{'loss': 2.4534, 'learning_rate': 1.0726695189939063e-07, 'epoch': 14.84}

 93%|█████████▎| 57420/61904 [6:24:12<1:44:45,  1.40s/it]
 93%|█████████▎| 57421/61904 [6:24:13<1:43:53,  1.39s/it]
 93%|█████████▎| 57422/61904 [6:24:14<1:43:47,  1.39s/it]
 93%|█████████▎| 57423/61904 [6:24:16<1:42:22,  1.37s/it]
 93%|█████████▎| 57424/61904 [6:24:17<1:46:19,  1.42s/it]
 93%|█████████▎| 57425/61904 [6:24:19<1:45:02,  1.41s/it]
 93%|█████████▎| 57426/61904 [6:24:20<1:43:42,  1.39s/it]
 93%|█████████▎| 57427/61904 [6:24:21<1:42:56,  1.38s/it]
 93%|█████████▎| 57428/61904 [6:24:23<1:41:18,  1.36s/it]
 93%|█████████▎| 57429/61904 [6:24:24<1:40:26,  1.35s/it]
 93%|█████████▎| 57430/61904 [6:24:25<1:38:15,  1.32s/it]
 93%|█████████▎| 57431/61904 [6:24:27<1:38:18,  1.32s/it]
 93%|█████████▎| 57432/61904 [6:24:28<1:37:09,  1.30s/it]
 93%|█████████▎| 57433/61904 [6:24:29<1:39:47,  1.34s/it]
 93%|█████████▎| 57434/61904 [6:24:31<1:40:30,  1.35s/it]
 93%|█████████▎| 57435/61904 [6:24:32<1:39:13,  1.33s/it]
 93%|█████████▎| 57436/61904 [6:24:33<1:39:00,  1.33s/it]
 93%|█████████▎| 57437/61904 [6:24:35<1:41:28,  1.36s/it]
 93%|█████████▎| 57438/61904 [6:24:36<1:44:50,  1.41s/it]
 93%|█████████▎| 57439/61904 [6:24:38<1:45:21,  1.42s/it]
 93%|█████████▎| 57440/61904 [6:24:39<1:43:28,  1.39s/it]
                                                         
{'loss': 2.4296, 'learning_rate': 1.072345390898483e-07, 'epoch': 14.85}

 93%|█████████▎| 57440/61904 [6:24:39<1:43:28,  1.39s/it]
 93%|█████████▎| 57441/61904 [6:24:40<1:43:52,  1.40s/it]
 93%|█████████▎| 57442/61904 [6:24:42<1:44:44,  1.41s/it]
 93%|█████████▎| 57443/61904 [6:24:43<1:40:38,  1.35s/it]
 93%|█████████▎| 57444/61904 [6:24:45<1:43:40,  1.39s/it]
 93%|█████████▎| 57445/61904 [6:24:46<1:43:02,  1.39s/it]
 93%|█████████▎| 57446/61904 [6:24:47<1:44:15,  1.40s/it]
 93%|█████████▎| 57447/61904 [6:24:49<1:42:56,  1.39s/it]
 93%|█████████▎| 57448/61904 [6:24:50<1:41:50,  1.37s/it]
 93%|█████████▎| 57449/61904 [6:24:51<1:40:22,  1.35s/it]
 93%|█████████▎| 57450/61904 [6:24:53<1:38:40,  1.33s/it]
 93%|█████████▎| 57451/61904 [6:24:54<1:42:34,  1.38s/it]
 93%|█████████▎| 57452/61904 [6:24:55<1:41:53,  1.37s/it]
 93%|█████████▎| 57453/61904 [6:24:57<1:40:11,  1.35s/it]
 93%|█████████▎| 57454/61904 [6:24:58<1:39:01,  1.34s/it]
 93%|█████████▎| 57455/61904 [6:24:59<1:36:25,  1.30s/it]
 93%|█████████▎| 57456/61904 [6:25:01<1:38:44,  1.33s/it]
 93%|█████████▎| 57457/61904 [6:25:02<1:37:52,  1.32s/it]
 93%|█████████▎| 57458/61904 [6:25:03<1:37:44,  1.32s/it]
 93%|█████████▎| 57459/61904 [6:25:05<1:37:12,  1.31s/it]
 93%|█████████▎| 57460/61904 [6:25:06<1:40:43,  1.36s/it]
                                                         
{'loss': 2.4417, 'learning_rate': 1.0720212628030596e-07, 'epoch': 14.85}

 93%|█████████▎| 57460/61904 [6:25:06<1:40:43,  1.36s/it]
 93%|█████████▎| 57461/61904 [6:25:07<1:40:15,  1.35s/it]
 93%|█████████▎| 57462/61904 [6:25:09<1:39:47,  1.35s/it]
 93%|█████████▎| 57463/61904 [6:25:10<1:37:48,  1.32s/it]
 93%|█████████▎| 57464/61904 [6:25:11<1:38:32,  1.33s/it]
 93%|█████████▎| 57465/61904 [6:25:13<1:38:17,  1.33s/it]
 93%|█████████▎| 57466/61904 [6:25:14<1:40:18,  1.36s/it]
 93%|█████████▎| 57467/61904 [6:25:15<1:40:42,  1.36s/it]
 93%|█████████▎| 57468/61904 [6:25:17<1:39:36,  1.35s/it]
 93%|█████████▎| 57469/61904 [6:25:18<1:41:39,  1.38s/it]
 93%|█████████▎| 57470/61904 [6:25:20<1:46:54,  1.45s/it]
 93%|█████████▎| 57471/61904 [6:25:21<1:45:13,  1.42s/it]
 93%|█████████▎| 57472/61904 [6:25:22<1:41:47,  1.38s/it]
 93%|█████████▎| 57473/61904 [6:25:24<1:41:05,  1.37s/it]
 93%|█████████▎| 57474/61904 [6:25:25<1:38:43,  1.34s/it]
 93%|█████████▎| 57475/61904 [6:25:26<1:39:19,  1.35s/it]
 93%|█████████▎| 57476/61904 [6:25:28<1:40:35,  1.36s/it]
 93%|█████████▎| 57477/61904 [6:25:29<1:42:44,  1.39s/it]
 93%|█████████▎| 57478/61904 [6:25:31<1:42:49,  1.39s/it]
 93%|█████████▎| 57479/61904 [6:25:32<1:42:21,  1.39s/it]
 93%|█████████▎| 57480/61904 [6:25:33<1:41:32,  1.38s/it]
                                                         
{'loss': 2.4688, 'learning_rate': 1.0716971347076364e-07, 'epoch': 14.86}

 93%|█████████▎| 57480/61904 [6:25:33<1:41:32,  1.38s/it]
 93%|█████████▎| 57481/61904 [6:25:35<1:40:31,  1.36s/it]
 93%|█████████▎| 57482/61904 [6:25:36<1:41:41,  1.38s/it]
 93%|█████████▎| 57483/61904 [6:25:38<1:43:56,  1.41s/it]
 93%|█████████▎| 57484/61904 [6:25:39<1:48:56,  1.48s/it]
 93%|█████████▎| 57485/61904 [6:25:41<1:48:48,  1.48s/it]
 93%|█████████▎| 57486/61904 [6:25:42<1:47:43,  1.46s/it]
 93%|█████████▎| 57487/61904 [6:25:44<1:48:16,  1.47s/it]
 93%|█████████▎| 57488/61904 [6:25:45<1:45:55,  1.44s/it]
 93%|█████████▎| 57489/61904 [6:25:46<1:41:04,  1.37s/it]
 93%|█████████▎| 57490/61904 [6:25:48<1:42:29,  1.39s/it]
 93%|█████████▎| 57491/61904 [6:25:49<1:41:42,  1.38s/it]
 93%|█████████▎| 57492/61904 [6:25:50<1:39:22,  1.35s/it]
 93%|█████████▎| 57493/61904 [6:25:52<1:38:33,  1.34s/it]
 93%|█████████▎| 57494/61904 [6:25:53<1:37:32,  1.33s/it]
 93%|█████████▎| 57495/61904 [6:25:54<1:38:18,  1.34s/it]
 93%|█████████▎| 57496/61904 [6:25:56<1:41:46,  1.39s/it]
 93%|█████████▎| 57497/61904 [6:25:57<1:44:03,  1.42s/it]
 93%|█████████▎| 57498/61904 [6:25:59<1:44:51,  1.43s/it]
 93%|█████████▎| 57499/61904 [6:26:00<1:40:21,  1.37s/it]
 93%|█████████▎| 57500/61904 [6:26:01<1:41:30,  1.38s/it]
                                                         
{'loss': 2.4566, 'learning_rate': 1.071373006612213e-07, 'epoch': 14.86}

 93%|█████████▎| 57500/61904 [6:26:01<1:41:30,  1.38s/it]
 93%|█████████▎| 57501/61904 [6:26:03<1:38:54,  1.35s/it]
 93%|█████████▎| 57502/61904 [6:26:04<1:37:55,  1.33s/it]
 93%|█████████▎| 57503/61904 [6:26:05<1:38:02,  1.34s/it]
 93%|█████████▎| 57504/61904 [6:26:07<1:39:21,  1.35s/it]
 93%|█████████▎| 57505/61904 [6:26:08<1:38:50,  1.35s/it]
 93%|█████████▎| 57506/61904 [6:26:10<1:41:47,  1.39s/it]
 93%|█████████▎| 57507/61904 [6:26:11<1:44:11,  1.42s/it]
 93%|█████████▎| 57508/61904 [6:26:12<1:42:33,  1.40s/it]
 93%|█████████▎| 57509/61904 [6:26:14<1:40:56,  1.38s/it]
 93%|█████████▎| 57510/61904 [6:26:15<1:38:04,  1.34s/it]
 93%|█████████▎| 57511/61904 [6:26:16<1:38:11,  1.34s/it]
 93%|█████████▎| 57512/61904 [6:26:18<1:40:10,  1.37s/it]
 93%|█████████▎| 57513/61904 [6:26:19<1:40:46,  1.38s/it]
 93%|█████████▎| 57514/61904 [6:26:21<1:42:45,  1.40s/it]
 93%|█████████▎| 57515/61904 [6:26:22<1:41:21,  1.39s/it]
 93%|█████████▎| 57516/61904 [6:26:23<1:42:19,  1.40s/it]
 93%|█████████▎| 57517/61904 [6:26:25<1:40:34,  1.38s/it]
 93%|█████████▎| 57518/61904 [6:26:26<1:39:22,  1.36s/it]
 93%|█████████▎| 57519/61904 [6:26:27<1:39:02,  1.36s/it]
 93%|█████████▎| 57520/61904 [6:26:29<1:38:52,  1.35s/it]
                                                         
{'loss': 2.4179, 'learning_rate': 1.0710488785167897e-07, 'epoch': 14.87}

 93%|█████████▎| 57520/61904 [6:26:29<1:38:52,  1.35s/it]
 93%|█████████▎| 57521/61904 [6:26:30<1:37:30,  1.33s/it]
 93%|█████████▎| 57522/61904 [6:26:31<1:36:32,  1.32s/it]
 93%|█████████▎| 57523/61904 [6:26:33<1:36:27,  1.32s/it]
 93%|█████████▎| 57524/61904 [6:26:34<1:41:58,  1.40s/it]
 93%|█████████▎| 57525/61904 [6:26:35<1:39:13,  1.36s/it]
 93%|█████████▎| 57526/61904 [6:26:37<1:39:11,  1.36s/it]
 93%|█████████▎| 57527/61904 [6:26:38<1:37:35,  1.34s/it]
 93%|█████████▎| 57528/61904 [6:26:40<1:39:52,  1.37s/it]
 93%|█████████▎| 57529/61904 [6:26:41<1:39:54,  1.37s/it]
 93%|█████████▎| 57530/61904 [6:26:42<1:41:26,  1.39s/it]
 93%|█████████▎| 57531/61904 [6:26:44<1:46:06,  1.46s/it]
 93%|█████████▎| 57532/61904 [6:26:45<1:42:37,  1.41s/it]
 93%|█████████▎| 57533/61904 [6:26:46<1:38:07,  1.35s/it]
 93%|█████████▎| 57534/61904 [6:26:48<1:38:05,  1.35s/it]
 93%|█████████▎| 57535/61904 [6:26:49<1:35:43,  1.31s/it]
 93%|█████████▎| 57536/61904 [6:26:50<1:35:57,  1.32s/it]
 93%|█████████▎| 57537/61904 [6:26:52<1:34:43,  1.30s/it]
 93%|█████████▎| 57538/61904 [6:26:53<1:36:09,  1.32s/it]
 93%|█████████▎| 57539/61904 [6:26:54<1:36:18,  1.32s/it]
 93%|█████████▎| 57540/61904 [6:26:56<1:41:27,  1.39s/it]
                                                         
{'loss': 2.4653, 'learning_rate': 1.0707247504213663e-07, 'epoch': 14.87}

 93%|█████████▎| 57540/61904 [6:26:56<1:41:27,  1.39s/it]
 93%|█████████▎| 57541/61904 [6:26:57<1:40:16,  1.38s/it]
 93%|█████████▎| 57542/61904 [6:26:59<1:39:19,  1.37s/it]
 93%|█████████▎| 57543/61904 [6:27:00<1:38:22,  1.35s/it]
 93%|█████████▎| 57544/61904 [6:27:01<1:39:11,  1.37s/it]
 93%|█████████▎| 57545/61904 [6:27:03<1:39:59,  1.38s/it]
 93%|█████████▎| 57546/61904 [6:27:04<1:37:44,  1.35s/it]
 93%|█████████▎| 57547/61904 [6:27:05<1:38:52,  1.36s/it]
 93%|█████████▎| 57548/61904 [6:27:07<1:36:45,  1.33s/it]
 93%|█████████▎| 57549/61904 [6:27:08<1:36:46,  1.33s/it]
 93%|█████████▎| 57550/61904 [6:27:09<1:36:17,  1.33s/it]
 93%|█████████▎| 57551/61904 [6:27:11<1:34:23,  1.30s/it]
 93%|█████████▎| 57552/61904 [6:27:12<1:36:11,  1.33s/it]
 93%|█████████▎| 57553/61904 [6:27:13<1:38:51,  1.36s/it]
 93%|█████████▎| 57554/61904 [6:27:15<1:46:29,  1.47s/it]
 93%|█████████▎| 57555/61904 [6:27:16<1:43:49,  1.43s/it]
 93%|█████████▎| 57556/61904 [6:27:18<1:41:46,  1.40s/it]
 93%|█████████▎| 57557/61904 [6:27:19<1:40:50,  1.39s/it]
 93%|█████████▎| 57558/61904 [6:27:21<1:40:20,  1.39s/it]
 93%|█████████▎| 57559/61904 [6:27:22<1:41:45,  1.41s/it]
 93%|█████████▎| 57560/61904 [6:27:23<1:41:34,  1.40s/it]
                                                         
{'loss': 2.4089, 'learning_rate': 1.0704006223259432e-07, 'epoch': 14.88}

 93%|█████████▎| 57560/61904 [6:27:23<1:41:34,  1.40s/it]
 93%|█████████▎| 57561/61904 [6:27:25<1:39:24,  1.37s/it]
 93%|█████████▎| 57562/61904 [6:27:26<1:37:19,  1.34s/it]
 93%|█████████▎| 57563/61904 [6:27:27<1:38:33,  1.36s/it]
 93%|█████████▎| 57564/61904 [6:27:29<1:38:49,  1.37s/it]
 93%|█████████▎| 57565/61904 [6:27:30<1:40:57,  1.40s/it]
 93%|█████████▎| 57566/61904 [6:27:31<1:39:02,  1.37s/it]
 93%|█████████▎| 57567/61904 [6:27:33<1:38:02,  1.36s/it]
 93%|█████████▎| 57568/61904 [6:27:34<1:37:16,  1.35s/it]
 93%|█████████▎| 57569/61904 [6:27:35<1:34:55,  1.31s/it]
 93%|█████████▎| 57570/61904 [6:27:37<1:36:16,  1.33s/it]
 93%|█████████▎| 57571/61904 [6:27:39<1:49:45,  1.52s/it]
 93%|█████████▎| 57572/61904 [6:27:40<1:44:10,  1.44s/it]
 93%|█████████▎| 57573/61904 [6:27:41<1:43:55,  1.44s/it]
 93%|█████████▎| 57574/61904 [6:27:43<1:43:54,  1.44s/it]
 93%|█████████▎| 57575/61904 [6:27:44<1:40:01,  1.39s/it]
 93%|█████████▎| 57576/61904 [6:27:45<1:38:31,  1.37s/it]
 93%|█████████▎| 57577/61904 [6:27:47<1:41:58,  1.41s/it]
 93%|█████████▎| 57578/61904 [6:27:48<1:40:11,  1.39s/it]
 93%|█████████▎| 57579/61904 [6:27:50<1:39:28,  1.38s/it]
 93%|█████████▎| 57580/61904 [6:27:51<1:39:52,  1.39s/it]
                                                         
{'loss': 2.4813, 'learning_rate': 1.0700764942305198e-07, 'epoch': 14.88}

 93%|█████████▎| 57580/61904 [6:27:51<1:39:52,  1.39s/it]
 93%|█████████▎| 57581/61904 [6:27:52<1:40:25,  1.39s/it]
 93%|█████████▎| 57582/61904 [6:27:54<1:41:06,  1.40s/it]
 93%|█████████▎| 57583/61904 [6:27:55<1:40:35,  1.40s/it]
 93%|█████████▎| 57584/61904 [6:27:57<1:37:19,  1.35s/it]
 93%|█████████▎| 57585/61904 [6:27:58<1:37:12,  1.35s/it]
 93%|█████████▎| 57586/61904 [6:27:59<1:38:54,  1.37s/it]
 93%|█████████▎| 57587/61904 [6:28:01<1:39:18,  1.38s/it]
 93%|█████████▎| 57588/61904 [6:28:02<1:39:24,  1.38s/it]
 93%|█████████▎| 57589/61904 [6:28:03<1:36:35,  1.34s/it]
 93%|█████████▎| 57590/61904 [6:28:05<1:39:10,  1.38s/it]
 93%|█████████▎| 57591/61904 [6:28:06<1:38:57,  1.38s/it]
 93%|█████████▎| 57592/61904 [6:28:08<1:40:34,  1.40s/it]
 93%|█████████▎| 57593/61904 [6:28:09<1:40:20,  1.40s/it]
 93%|█████████▎| 57594/61904 [6:28:10<1:37:58,  1.36s/it]
 93%|█████████▎| 57595/61904 [6:28:11<1:34:38,  1.32s/it]
 93%|█████████▎| 57596/61904 [6:28:13<1:35:52,  1.34s/it]
 93%|█████████▎| 57597/61904 [6:28:14<1:39:07,  1.38s/it]
 93%|█████████▎| 57598/61904 [6:28:16<1:38:28,  1.37s/it]
 93%|█████████▎| 57599/61904 [6:28:17<1:37:54,  1.36s/it]
 93%|█████████▎| 57600/61904 [6:28:18<1:38:37,  1.37s/it]
                                                         
{'loss': 2.3872, 'learning_rate': 1.0697523661350964e-07, 'epoch': 14.89}

 93%|█████████▎| 57600/61904 [6:28:18<1:38:37,  1.37s/it]
 93%|█████████▎| 57601/61904 [6:28:20<1:44:29,  1.46s/it]
 93%|█████████▎| 57602/61904 [6:28:22<1:44:53,  1.46s/it]
 93%|█████████▎| 57603/61904 [6:28:23<1:44:33,  1.46s/it]
 93%|█████████▎| 57604/61904 [6:28:24<1:44:50,  1.46s/it]
 93%|█████████▎| 57605/61904 [6:28:26<1:43:35,  1.45s/it]
 93%|█████████▎| 57606/61904 [6:28:27<1:42:36,  1.43s/it]
 93%|█████████▎| 57607/61904 [6:28:29<1:44:48,  1.46s/it]
 93%|█████████▎| 57608/61904 [6:28:30<1:40:56,  1.41s/it]
 93%|█████████▎| 57609/61904 [6:28:31<1:38:56,  1.38s/it]
 93%|█████████▎| 57610/61904 [6:28:33<1:37:38,  1.36s/it]
 93%|█████████▎| 57611/61904 [6:28:34<1:39:59,  1.40s/it]
 93%|█████████▎| 57612/61904 [6:28:36<1:42:13,  1.43s/it]
 93%|█████████▎| 57613/61904 [6:28:37<1:40:54,  1.41s/it]
 93%|█████████▎| 57614/61904 [6:28:38<1:39:48,  1.40s/it]
 93%|█████████▎| 57615/61904 [6:28:40<1:39:58,  1.40s/it]
 93%|█████████▎| 57616/61904 [6:28:41<1:42:53,  1.44s/it]
 93%|█████████▎| 57617/61904 [6:28:43<1:41:10,  1.42s/it]
 93%|█████████▎| 57618/61904 [6:28:44<1:41:05,  1.42s/it]
 93%|█████████▎| 57619/61904 [6:28:46<1:39:37,  1.39s/it]
 93%|█████████▎| 57620/61904 [6:28:47<1:37:05,  1.36s/it]
                                                         
{'loss': 2.4628, 'learning_rate': 1.069428238039673e-07, 'epoch': 14.89}

 93%|█████████▎| 57620/61904 [6:28:47<1:37:05,  1.36s/it]
 93%|█████████▎| 57621/61904 [6:28:48<1:38:40,  1.38s/it]
 93%|█████████▎| 57622/61904 [6:28:50<1:37:15,  1.36s/it]
 93%|█████████▎| 57623/61904 [6:28:51<1:42:17,  1.43s/it]
 93%|█████████▎| 57624/61904 [6:28:53<1:42:40,  1.44s/it]
 93%|█████████▎| 57625/61904 [6:28:54<1:43:55,  1.46s/it]
 93%|█████████▎| 57626/61904 [6:28:56<1:45:44,  1.48s/it]
 93%|█████████▎| 57627/61904 [6:28:57<1:45:35,  1.48s/it]
 93%|█████████▎| 57628/61904 [6:28:59<1:44:52,  1.47s/it]
 93%|█████████▎| 57629/61904 [6:29:00<1:43:06,  1.45s/it]
 93%|█████████▎| 57630/61904 [6:29:01<1:40:50,  1.42s/it]
 93%|█████████▎| 57631/61904 [6:29:03<1:40:43,  1.41s/it]
 93%|█████████▎| 57632/61904 [6:29:04<1:41:19,  1.42s/it]
 93%|█████████▎| 57633/61904 [6:29:06<1:41:30,  1.43s/it]
 93%|█████████▎| 57634/61904 [6:29:07<1:40:12,  1.41s/it]
 93%|█████████▎| 57635/61904 [6:29:08<1:39:03,  1.39s/it]
 93%|█████████▎| 57636/61904 [6:29:10<1:40:27,  1.41s/it]
 93%|█████████▎| 57637/61904 [6:29:11<1:41:25,  1.43s/it]
 93%|█████████▎| 57638/61904 [6:29:13<1:40:08,  1.41s/it]
 93%|█████████▎| 57639/61904 [6:29:14<1:39:04,  1.39s/it]
 93%|█████████▎| 57640/61904 [6:29:15<1:39:01,  1.39s/it]
                                                         
{'loss': 2.3651, 'learning_rate': 1.0691041099442499e-07, 'epoch': 14.9}

 93%|█████████▎| 57640/61904 [6:29:15<1:39:01,  1.39s/it]
 93%|█████████▎| 57641/61904 [6:29:17<1:38:32,  1.39s/it]
 93%|█████████▎| 57642/61904 [6:29:18<1:39:17,  1.40s/it]
 93%|█████████▎| 57643/61904 [6:29:20<1:39:07,  1.40s/it]
 93%|█████████▎| 57644/61904 [6:29:21<1:37:55,  1.38s/it]
 93%|█████████▎| 57645/61904 [6:29:22<1:39:31,  1.40s/it]
 93%|█████████▎| 57646/61904 [6:29:24<1:40:20,  1.41s/it]
 93%|█████████▎| 57647/61904 [6:29:25<1:39:52,  1.41s/it]
 93%|█████████▎| 57648/61904 [6:29:26<1:37:48,  1.38s/it]
 93%|█████████▎| 57649/61904 [6:29:28<1:37:31,  1.38s/it]
 93%|█████████▎| 57650/61904 [6:29:29<1:41:15,  1.43s/it]
 93%|█████████▎| 57651/61904 [6:29:31<1:42:13,  1.44s/it]
 93%|█████████▎| 57652/61904 [6:29:32<1:41:50,  1.44s/it]
 93%|█████████▎| 57653/61904 [6:29:34<1:42:07,  1.44s/it]
 93%|█████████▎| 57654/61904 [6:29:35<1:37:45,  1.38s/it]
 93%|█████████▎| 57655/61904 [6:29:36<1:36:31,  1.36s/it]
 93%|█████████▎| 57656/61904 [6:29:38<1:36:08,  1.36s/it]
 93%|█████████▎| 57657/61904 [6:29:39<1:35:01,  1.34s/it]
 93%|█████████▎| 57658/61904 [6:29:40<1:37:45,  1.38s/it]
 93%|█████████▎| 57659/61904 [6:29:42<1:35:23,  1.35s/it]
 93%|█████████▎| 57660/61904 [6:29:43<1:39:56,  1.41s/it]
                                                         
{'loss': 2.4236, 'learning_rate': 1.0687799818488265e-07, 'epoch': 14.9}

 93%|█████████▎| 57660/61904 [6:29:43<1:39:56,  1.41s/it]
 93%|█████████▎| 57661/61904 [6:29:45<1:38:35,  1.39s/it]
 93%|█████████▎| 57662/61904 [6:29:46<1:40:30,  1.42s/it]
 93%|█████████▎| 57663/61904 [6:29:48<1:40:10,  1.42s/it]
 93%|█████████▎| 57664/61904 [6:29:49<1:37:56,  1.39s/it]
 93%|█████████▎| 57665/61904 [6:29:50<1:39:53,  1.41s/it]
 93%|█████████▎| 57666/61904 [6:29:52<1:36:39,  1.37s/it]
 93%|█████████▎| 57667/61904 [6:29:53<1:37:04,  1.37s/it]
 93%|█████████▎| 57668/61904 [6:29:55<1:41:04,  1.43s/it]
 93%|█████████▎| 57669/61904 [6:29:56<1:43:31,  1.47s/it]
 93%|█████████▎| 57670/61904 [6:29:58<1:47:17,  1.52s/it]
 93%|█████████▎| 57671/61904 [6:29:59<1:46:57,  1.52s/it]
 93%|█████████▎| 57672/61904 [6:30:01<1:44:24,  1.48s/it]
 93%|█████████▎| 57673/61904 [6:30:02<1:43:02,  1.46s/it]
 93%|█████████▎| 57674/61904 [6:30:03<1:41:09,  1.43s/it]
 93%|█████████▎| 57675/61904 [6:30:05<1:38:54,  1.40s/it]
 93%|█████████▎| 57676/61904 [6:30:06<1:40:21,  1.42s/it]
 93%|█████████▎| 57677/61904 [6:30:08<1:38:40,  1.40s/it]
 93%|█████████▎| 57678/61904 [6:30:09<1:37:01,  1.38s/it]
 93%|█████████▎| 57679/61904 [6:30:10<1:38:51,  1.40s/it]
 93%|█████████▎| 57680/61904 [6:30:12<1:36:04,  1.36s/it]
                                                         
{'loss': 2.4099, 'learning_rate': 1.0684558537534032e-07, 'epoch': 14.91}

 93%|█████████▎| 57680/61904 [6:30:12<1:36:04,  1.36s/it]
 93%|█████████▎| 57681/61904 [6:30:13<1:34:50,  1.35s/it]
 93%|█████████▎| 57682/61904 [6:30:14<1:36:31,  1.37s/it]
 93%|█████████▎| 57683/61904 [6:30:16<1:37:43,  1.39s/it]
 93%|█████████▎| 57684/61904 [6:30:17<1:38:27,  1.40s/it]
 93%|█████████▎| 57685/61904 [6:30:19<1:39:42,  1.42s/it]
 93%|█████████▎| 57686/61904 [6:30:20<1:38:32,  1.40s/it]
 93%|█████████▎| 57687/61904 [6:30:21<1:37:08,  1.38s/it]
 93%|█████████▎| 57688/61904 [6:30:23<1:36:58,  1.38s/it]
 93%|█████████▎| 57689/61904 [6:30:24<1:35:08,  1.35s/it]
 93%|█████████▎| 57690/61904 [6:30:25<1:33:47,  1.34s/it]
 93%|█████████▎| 57691/61904 [6:30:27<1:32:22,  1.32s/it]
 93%|█████████▎| 57692/61904 [6:30:28<1:33:19,  1.33s/it]
 93%|█████████▎| 57693/61904 [6:30:30<1:38:12,  1.40s/it]
 93%|█████████▎| 57694/61904 [6:30:31<1:36:04,  1.37s/it]
 93%|█████████▎| 57695/61904 [6:30:32<1:34:00,  1.34s/it]
 93%|█████████▎| 57696/61904 [6:30:34<1:38:03,  1.40s/it]
 93%|█████████▎| 57697/61904 [6:30:35<1:37:26,  1.39s/it]
 93%|█████████▎| 57698/61904 [6:30:36<1:35:17,  1.36s/it]
 93%|█████████▎| 57699/61904 [6:30:38<1:34:35,  1.35s/it]
 93%|█████████▎| 57700/61904 [6:30:39<1:33:55,  1.34s/it]
                                                         
{'loss': 2.4265, 'learning_rate': 1.0681317256579798e-07, 'epoch': 14.91}

 93%|█████████▎| 57700/61904 [6:30:39<1:33:55,  1.34s/it]
 93%|█████████▎| 57701/61904 [6:30:40<1:37:15,  1.39s/it]
 93%|█████████▎| 57702/61904 [6:30:42<1:37:44,  1.40s/it]
 93%|█████████▎| 57703/61904 [6:30:43<1:37:04,  1.39s/it]
 93%|█████████▎| 57704/61904 [6:30:45<1:42:58,  1.47s/it]
 93%|█████████▎| 57705/61904 [6:30:46<1:39:09,  1.42s/it]
 93%|█████████▎| 57706/61904 [6:30:48<1:44:52,  1.50s/it]
 93%|█████████▎| 57707/61904 [6:30:49<1:39:44,  1.43s/it]
 93%|█████████▎| 57708/61904 [6:30:51<1:40:29,  1.44s/it]
 93%|█████████▎| 57709/61904 [6:30:52<1:37:09,  1.39s/it]
 93%|█████████▎| 57710/61904 [6:30:53<1:36:32,  1.38s/it]
 93%|█████████▎| 57711/61904 [6:30:55<1:36:51,  1.39s/it]
 93%|█████████▎| 57712/61904 [6:30:56<1:34:49,  1.36s/it]
 93%|█████████▎| 57713/61904 [6:30:57<1:35:06,  1.36s/it]
 93%|█████████▎| 57714/61904 [6:30:59<1:38:10,  1.41s/it]
 93%|█████████▎| 57715/61904 [6:31:00<1:38:47,  1.42s/it]
 93%|█████████▎| 57716/61904 [6:31:01<1:35:29,  1.37s/it]
 93%|█████████▎| 57717/61904 [6:31:03<1:35:50,  1.37s/it]
 93%|█████████▎| 57718/61904 [6:31:04<1:37:26,  1.40s/it]
 93%|█████████▎| 57719/61904 [6:31:06<1:38:56,  1.42s/it]
 93%|█████████▎| 57720/61904 [6:31:07<1:34:41,  1.36s/it]
                                                         
{'loss': 2.4424, 'learning_rate': 1.0678075975625567e-07, 'epoch': 14.92}

 93%|█████████▎| 57720/61904 [6:31:07<1:34:41,  1.36s/it]
 93%|█████████▎| 57721/61904 [6:31:08<1:35:45,  1.37s/it]
 93%|█████████▎| 57722/61904 [6:31:10<1:34:52,  1.36s/it]
 93%|█████████▎| 57723/61904 [6:31:11<1:33:26,  1.34s/it]
 93%|█████████▎| 57724/61904 [6:31:12<1:33:59,  1.35s/it]
 93%|█████████▎| 57725/61904 [6:31:14<1:32:40,  1.33s/it]
 93%|█████████▎| 57726/61904 [6:31:15<1:35:34,  1.37s/it]
 93%|█████████▎| 57727/61904 [6:31:17<1:35:17,  1.37s/it]
 93%|█████████▎| 57728/61904 [6:31:18<1:42:38,  1.47s/it]
 93%|█████████▎| 57729/61904 [6:31:20<1:42:03,  1.47s/it]
 93%|█████████▎| 57730/61904 [6:31:21<1:39:24,  1.43s/it]
 93%|█████████▎| 57731/61904 [6:31:22<1:37:17,  1.40s/it]
 93%|█████████▎| 57732/61904 [6:31:24<1:34:25,  1.36s/it]
 93%|█████████▎| 57733/61904 [6:31:25<1:39:35,  1.43s/it]
 93%|█████████▎| 57734/61904 [6:31:27<1:38:15,  1.41s/it]
 93%|█████████▎| 57735/61904 [6:31:28<1:38:33,  1.42s/it]
 93%|█████████▎| 57736/61904 [6:31:29<1:36:57,  1.40s/it]
 93%|█████████▎| 57737/61904 [6:31:31<1:34:19,  1.36s/it]
 93%|█████████▎| 57738/61904 [6:31:32<1:36:22,  1.39s/it]
 93%|█████████▎| 57739/61904 [6:31:34<1:39:23,  1.43s/it]
 93%|█████████▎| 57740/61904 [6:31:35<1:40:01,  1.44s/it]
                                                         
{'loss': 2.3981, 'learning_rate': 1.0674834694671335e-07, 'epoch': 14.92}

 93%|█████████▎| 57740/61904 [6:31:35<1:40:01,  1.44s/it]
 93%|█████████▎| 57741/61904 [6:31:37<1:40:20,  1.45s/it]
 93%|█████████▎| 57742/61904 [6:31:38<1:37:13,  1.40s/it]
 93%|█████████▎| 57743/61904 [6:31:39<1:37:18,  1.40s/it]
 93%|█████████▎| 57744/61904 [6:31:41<1:38:18,  1.42s/it]
 93%|█████████▎| 57745/61904 [6:31:42<1:35:59,  1.38s/it]
 93%|█████████▎| 57746/61904 [6:31:43<1:35:54,  1.38s/it]
 93%|█████████▎| 57747/61904 [6:31:45<1:34:12,  1.36s/it]
 93%|█████████▎| 57748/61904 [6:31:46<1:32:17,  1.33s/it]
 93%|█████████▎| 57749/61904 [6:31:47<1:33:21,  1.35s/it]
 93%|█████████▎| 57750/61904 [6:31:49<1:33:57,  1.36s/it]
 93%|█████████▎| 57751/61904 [6:31:50<1:33:22,  1.35s/it]
 93%|█████████▎| 57752/61904 [6:31:51<1:34:25,  1.36s/it]
 93%|█████████▎| 57753/61904 [6:31:53<1:34:33,  1.37s/it]
 93%|█████████▎| 57754/61904 [6:31:54<1:37:45,  1.41s/it]
 93%|█████████▎| 57755/61904 [6:31:56<1:39:06,  1.43s/it]
 93%|█████████▎| 57756/61904 [6:31:57<1:38:44,  1.43s/it]
 93%|█████████▎| 57757/61904 [6:31:59<1:37:49,  1.42s/it]
 93%|█████████▎| 57758/61904 [6:32:00<1:37:29,  1.41s/it]
 93%|█████████▎| 57759/61904 [6:32:01<1:36:53,  1.40s/it]
 93%|█████████▎| 57760/61904 [6:32:03<1:36:19,  1.39s/it]
                                                         
{'loss': 2.4498, 'learning_rate': 1.0671593413717099e-07, 'epoch': 14.93}

 93%|█████████▎| 57760/61904 [6:32:03<1:36:19,  1.39s/it]
 93%|█████████▎| 57761/61904 [6:32:04<1:33:31,  1.35s/it]
 93%|█████████▎| 57762/61904 [6:32:05<1:32:53,  1.35s/it]
 93%|█████████▎| 57763/61904 [6:32:07<1:34:01,  1.36s/it]
 93%|█████████▎| 57764/61904 [6:32:08<1:39:21,  1.44s/it]
 93%|█████████▎| 57765/61904 [6:32:10<1:40:15,  1.45s/it]
 93%|█████████▎| 57766/61904 [6:32:11<1:38:25,  1.43s/it]
 93%|█████████▎| 57767/61904 [6:32:13<1:36:11,  1.40s/it]
 93%|█████████▎| 57768/61904 [6:32:14<1:39:55,  1.45s/it]
 93%|█████████▎| 57769/61904 [6:32:16<1:43:48,  1.51s/it]
 93%|█████████▎| 57770/61904 [6:32:17<1:39:00,  1.44s/it]
 93%|█████████▎| 57771/61904 [6:32:18<1:36:56,  1.41s/it]
 93%|█████████▎| 57772/61904 [6:32:20<1:36:30,  1.40s/it]
 93%|█████████▎| 57773/61904 [6:32:21<1:35:35,  1.39s/it]
 93%|█████████▎| 57774/61904 [6:32:22<1:33:17,  1.36s/it]
 93%|█████████▎| 57775/61904 [6:32:24<1:33:24,  1.36s/it]
 93%|█████████▎| 57776/61904 [6:32:25<1:32:50,  1.35s/it]
 93%|█████████▎| 57777/61904 [6:32:26<1:31:17,  1.33s/it]
 93%|█████████▎| 57778/61904 [6:32:28<1:34:02,  1.37s/it]
 93%|█████████▎| 57779/61904 [6:32:29<1:35:36,  1.39s/it]
 93%|█████████▎| 57780/61904 [6:32:31<1:35:17,  1.39s/it]
                                                         
{'loss': 2.4153, 'learning_rate': 1.0668352132762868e-07, 'epoch': 14.93}

 93%|█████████▎| 57780/61904 [6:32:31<1:35:17,  1.39s/it]
 93%|█████████▎| 57781/61904 [6:32:32<1:37:03,  1.41s/it]
 93%|█████████▎| 57782/61904 [6:32:33<1:34:59,  1.38s/it]
 93%|█████████▎| 57783/61904 [6:32:35<1:37:39,  1.42s/it]
 93%|█████████▎| 57784/61904 [6:32:36<1:37:23,  1.42s/it]
 93%|█████████▎| 57785/61904 [6:32:38<1:36:21,  1.40s/it]
 93%|█████████▎| 57786/61904 [6:32:39<1:35:06,  1.39s/it]
 93%|█████████▎| 57787/61904 [6:32:40<1:34:07,  1.37s/it]
 93%|█████████▎| 57788/61904 [6:32:42<1:31:42,  1.34s/it]
 93%|█████████▎| 57789/61904 [6:32:43<1:34:43,  1.38s/it]
 93%|█████████▎| 57790/61904 [6:32:44<1:32:10,  1.34s/it]
 93%|█████████▎| 57791/61904 [6:32:46<1:32:51,  1.35s/it]
 93%|█████████▎| 57792/61904 [6:32:47<1:33:37,  1.37s/it]
 93%|█████████▎| 57793/61904 [6:32:49<1:33:30,  1.36s/it]
 93%|█████████▎| 57794/61904 [6:32:50<1:34:20,  1.38s/it]
 93%|█████████▎| 57795/61904 [6:32:52<1:39:00,  1.45s/it]
 93%|█████████▎| 57796/61904 [6:32:53<1:36:26,  1.41s/it]
 93%|█████████▎| 57797/61904 [6:32:54<1:31:40,  1.34s/it]
 93%|█████████▎| 57798/61904 [6:32:55<1:30:51,  1.33s/it]
 93%|█████████▎| 57799/61904 [6:32:57<1:29:33,  1.31s/it]
 93%|█████████▎| 57800/61904 [6:32:58<1:26:35,  1.27s/it]
                                                         
{'loss': 2.4706, 'learning_rate': 1.0665110851808634e-07, 'epoch': 14.94}

 93%|█████████▎| 57800/61904 [6:32:58<1:26:35,  1.27s/it]
 93%|█████████▎| 57801/61904 [6:32:59<1:28:32,  1.29s/it]
 93%|█████████▎| 57802/61904 [6:33:01<1:29:02,  1.30s/it]
 93%|█████████▎| 57803/61904 [6:33:02<1:28:22,  1.29s/it]
 93%|█████████▎| 57804/61904 [6:33:03<1:29:43,  1.31s/it]
 93%|█████████▎| 57805/61904 [6:33:05<1:33:22,  1.37s/it]
 93%|█████████▎| 57806/61904 [6:33:06<1:36:22,  1.41s/it]
 93%|█████████▎| 57807/61904 [6:33:08<1:37:49,  1.43s/it]
 93%|█████████▎| 57808/61904 [6:33:09<1:37:44,  1.43s/it]
 93%|█████████▎| 57809/61904 [6:33:10<1:36:30,  1.41s/it]
 93%|█████████▎| 57810/61904 [6:33:12<1:40:01,  1.47s/it]
 93%|█████████▎| 57811/61904 [6:33:13<1:36:14,  1.41s/it]
 93%|█████████▎| 57812/61904 [6:33:15<1:35:36,  1.40s/it]
 93%|█████████▎| 57813/61904 [6:33:16<1:36:17,  1.41s/it]
 93%|█████████▎| 57814/61904 [6:33:18<1:36:42,  1.42s/it]
 93%|█████████▎| 57815/61904 [6:33:19<1:34:13,  1.38s/it]
 93%|█████████▎| 57816/61904 [6:33:20<1:32:07,  1.35s/it]
 93%|█████████▎| 57817/61904 [6:33:21<1:29:46,  1.32s/it]
 93%|█████████▎| 57818/61904 [6:33:23<1:30:16,  1.33s/it]
 93%|█████████▎| 57819/61904 [6:33:24<1:32:50,  1.36s/it]
 93%|█████████▎| 57820/61904 [6:33:26<1:34:40,  1.39s/it]
                                                         
{'loss': 2.4511, 'learning_rate': 1.0661869570854403e-07, 'epoch': 14.94}

 93%|█████████▎| 57820/61904 [6:33:26<1:34:40,  1.39s/it]
 93%|█████████▎| 57821/61904 [6:33:27<1:32:11,  1.35s/it]
 93%|█████████▎| 57822/61904 [6:33:28<1:30:51,  1.34s/it]
 93%|█████████▎| 57823/61904 [6:33:30<1:31:47,  1.35s/it]
 93%|█████████▎| 57824/61904 [6:33:31<1:32:25,  1.36s/it]
 93%|█████████▎| 57825/61904 [6:33:32<1:31:57,  1.35s/it]
 93%|█████████▎| 57826/61904 [6:33:34<1:32:50,  1.37s/it]
 93%|█████████▎| 57827/61904 [6:33:35<1:35:51,  1.41s/it]
 93%|█████████▎| 57828/61904 [6:33:37<1:34:21,  1.39s/it]
 93%|█████████▎| 57829/61904 [6:33:38<1:35:05,  1.40s/it]
 93%|█████████▎| 57830/61904 [6:33:39<1:35:03,  1.40s/it]
 93%|█████████▎| 57831/61904 [6:33:41<1:36:26,  1.42s/it]
 93%|█████████▎| 57832/61904 [6:33:42<1:35:32,  1.41s/it]
 93%|█████████▎| 57833/61904 [6:33:44<1:35:12,  1.40s/it]
 93%|█████████▎| 57834/61904 [6:33:45<1:33:57,  1.39s/it]
 93%|█████████▎| 57835/61904 [6:33:46<1:31:46,  1.35s/it]
 93%|█████████▎| 57836/61904 [6:33:48<1:33:15,  1.38s/it]
 93%|█████████▎| 57837/61904 [6:33:49<1:32:57,  1.37s/it]
 93%|█████████▎| 57838/61904 [6:33:50<1:30:33,  1.34s/it]
 93%|█████████▎| 57839/61904 [6:33:52<1:29:34,  1.32s/it]
 93%|█████████▎| 57840/61904 [6:33:53<1:31:27,  1.35s/it]
                                                         
{'loss': 2.4389, 'learning_rate': 1.0658628289900166e-07, 'epoch': 14.95}

 93%|█████████▎| 57840/61904 [6:33:53<1:31:27,  1.35s/it]
 93%|█████████▎| 57841/61904 [6:33:54<1:31:36,  1.35s/it]
 93%|█████████▎| 57842/61904 [6:33:56<1:29:10,  1.32s/it]
 93%|█████████▎| 57843/61904 [6:33:57<1:32:33,  1.37s/it]
 93%|█████████▎| 57844/61904 [6:33:58<1:31:52,  1.36s/it]
 93%|█████████▎| 57845/61904 [6:34:00<1:31:17,  1.35s/it]
 93%|█████████▎| 57846/61904 [6:34:01<1:33:41,  1.39s/it]
 93%|█████████▎| 57847/61904 [6:34:02<1:30:36,  1.34s/it]
 93%|█████████▎| 57848/61904 [6:34:04<1:31:47,  1.36s/it]
 93%|█████████▎| 57849/61904 [6:34:05<1:31:44,  1.36s/it]
 93%|█████████▎| 57850/61904 [6:34:07<1:33:15,  1.38s/it]
 93%|█████████▎| 57851/61904 [6:34:08<1:34:17,  1.40s/it]
 93%|█████████▎| 57852/61904 [6:34:09<1:34:03,  1.39s/it]
 93%|█████████▎| 57853/61904 [6:34:11<1:36:52,  1.43s/it]
 93%|█████████▎| 57854/61904 [6:34:12<1:33:32,  1.39s/it]
 93%|█████████▎| 57855/61904 [6:34:14<1:34:14,  1.40s/it]
 93%|█████████▎| 57856/61904 [6:34:15<1:33:36,  1.39s/it]
 93%|█████████▎| 57857/61904 [6:34:16<1:34:18,  1.40s/it]
 93%|█████████▎| 57858/61904 [6:34:18<1:38:42,  1.46s/it]
 93%|█████████▎| 57859/61904 [6:34:19<1:36:47,  1.44s/it]
 93%|█████████▎| 57860/61904 [6:34:21<1:38:53,  1.47s/it]
                                                         
{'loss': 2.4287, 'learning_rate': 1.0655387008945935e-07, 'epoch': 14.95}

 93%|█████████▎| 57860/61904 [6:34:21<1:38:53,  1.47s/it]
 93%|█████████▎| 57861/61904 [6:34:22<1:36:26,  1.43s/it]
 93%|█████████▎| 57862/61904 [6:34:24<1:33:13,  1.38s/it]
 93%|█████████▎| 57863/61904 [6:34:25<1:34:45,  1.41s/it]
 93%|█████████▎| 57864/61904 [6:34:26<1:32:53,  1.38s/it]
 93%|█████████▎| 57865/61904 [6:34:28<1:32:30,  1.37s/it]
 93%|█████████▎| 57866/61904 [6:34:29<1:31:28,  1.36s/it]
 93%|█████████▎| 57867/61904 [6:34:30<1:29:29,  1.33s/it]
 93%|█████████▎| 57868/61904 [6:34:32<1:29:25,  1.33s/it]
 93%|█████████▎| 57869/61904 [6:34:33<1:29:36,  1.33s/it]
 93%|█████████▎| 57870/61904 [6:34:34<1:29:40,  1.33s/it]
 93%|█████████▎| 57871/61904 [6:34:36<1:33:02,  1.38s/it]
 93%|█████████▎| 57872/61904 [6:34:37<1:35:34,  1.42s/it]
 93%|█████████▎| 57873/61904 [6:34:39<1:35:24,  1.42s/it]
 93%|█████████▎| 57874/61904 [6:34:40<1:36:53,  1.44s/it]
 93%|█████████▎| 57875/61904 [6:34:42<1:36:05,  1.43s/it]
 93%|█████████▎| 57876/61904 [6:34:43<1:36:12,  1.43s/it]
 93%|█████████▎| 57877/61904 [6:34:45<1:36:03,  1.43s/it]
 93%|█████████▎| 57878/61904 [6:34:46<1:31:36,  1.37s/it]
 93%|█████████▎| 57879/61904 [6:34:47<1:32:33,  1.38s/it]
 93%|█████████▎| 57880/61904 [6:34:49<1:32:06,  1.37s/it]
                                                         
{'loss': 2.4765, 'learning_rate': 1.0652145727991701e-07, 'epoch': 14.96}

 93%|█████████▎| 57880/61904 [6:34:49<1:32:06,  1.37s/it]
 94%|█████████▎| 57881/61904 [6:34:50<1:35:07,  1.42s/it]
 94%|█████████▎| 57882/61904 [6:34:51<1:31:41,  1.37s/it]
 94%|█████████▎| 57883/61904 [6:34:53<1:29:03,  1.33s/it]
 94%|█████████▎| 57884/61904 [6:34:54<1:31:46,  1.37s/it]
 94%|█████████▎| 57885/61904 [6:34:55<1:30:09,  1.35s/it]
 94%|█████████▎| 57886/61904 [6:34:57<1:29:29,  1.34s/it]
 94%|█████████▎| 57887/61904 [6:34:58<1:27:26,  1.31s/it]
 94%|█████████▎| 57888/61904 [6:34:59<1:28:53,  1.33s/it]
 94%|█████████▎| 57889/61904 [6:35:01<1:30:13,  1.35s/it]
 94%|█████████▎| 57890/61904 [6:35:02<1:28:47,  1.33s/it]
 94%|█████████▎| 57891/61904 [6:35:03<1:27:49,  1.31s/it]
 94%|█████████▎| 57892/61904 [6:35:05<1:29:02,  1.33s/it]
 94%|█████████▎| 57893/61904 [6:35:06<1:28:30,  1.32s/it]
 94%|█████████▎| 57894/61904 [6:35:07<1:31:37,  1.37s/it]
 94%|█████████▎| 57895/61904 [6:35:09<1:31:48,  1.37s/it]
 94%|█████████▎| 57896/61904 [6:35:10<1:33:24,  1.40s/it]
 94%|█████████▎| 57897/61904 [6:35:11<1:32:15,  1.38s/it]
 94%|█████████▎| 57898/61904 [6:35:13<1:32:02,  1.38s/it]
 94%|█████████▎| 57899/61904 [6:35:14<1:33:00,  1.39s/it]
 94%|█████████▎| 57900/61904 [6:35:16<1:31:51,  1.38s/it]
                                                         
{'loss': 2.4132, 'learning_rate': 1.0648904447037468e-07, 'epoch': 14.96}

 94%|█████████▎| 57900/61904 [6:35:16<1:31:51,  1.38s/it]
 94%|█████████▎| 57901/61904 [6:35:17<1:32:31,  1.39s/it]
 94%|█████████▎| 57902/61904 [6:35:19<1:35:03,  1.43s/it]
 94%|█████████▎| 57903/61904 [6:35:20<1:32:16,  1.38s/it]
 94%|█████████▎| 57904/61904 [6:35:21<1:30:48,  1.36s/it]
 94%|█████████▎| 57905/61904 [6:35:22<1:29:56,  1.35s/it]
 94%|█████████▎| 57906/61904 [6:35:24<1:28:14,  1.32s/it]
 94%|█████████▎| 57907/61904 [6:35:25<1:29:01,  1.34s/it]
 94%|█████████▎| 57908/61904 [6:35:26<1:28:12,  1.32s/it]
 94%|█████████▎| 57909/61904 [6:35:28<1:26:31,  1.30s/it]
 94%|█████████▎| 57910/61904 [6:35:29<1:30:21,  1.36s/it]
 94%|█████████▎| 57911/61904 [6:35:31<1:32:08,  1.38s/it]
 94%|█████████▎| 57912/61904 [6:35:32<1:31:33,  1.38s/it]
 94%|█████████▎| 57913/61904 [6:35:33<1:29:05,  1.34s/it]
 94%|█████████▎| 57914/61904 [6:35:34<1:28:01,  1.32s/it]
 94%|█████████▎| 57915/61904 [6:35:36<1:28:47,  1.34s/it]
 94%|█████████▎| 57916/61904 [6:35:37<1:30:16,  1.36s/it]
 94%|█████████▎| 57917/61904 [6:35:39<1:30:27,  1.36s/it]
 94%|█████████▎| 57918/61904 [6:35:40<1:31:10,  1.37s/it]
 94%|█████████▎| 57919/61904 [6:35:41<1:30:55,  1.37s/it]
 94%|█████████▎| 57920/61904 [6:35:43<1:35:47,  1.44s/it]
                                                         
{'loss': 2.4539, 'learning_rate': 1.0645663166083234e-07, 'epoch': 14.97}

 94%|█████████▎| 57920/61904 [6:35:43<1:35:47,  1.44s/it]
 94%|█████████▎| 57921/61904 [6:35:44<1:33:15,  1.40s/it]
 94%|█████████▎| 57922/61904 [6:35:46<1:33:46,  1.41s/it]
 94%|█████████▎| 57923/61904 [6:35:47<1:30:02,  1.36s/it]
 94%|█████████▎| 57924/61904 [6:35:48<1:30:26,  1.36s/it]
 94%|█████████▎| 57925/61904 [6:35:50<1:31:29,  1.38s/it]
 94%|█████████▎| 57926/61904 [6:35:51<1:28:30,  1.33s/it]
 94%|█████████▎| 57927/61904 [6:35:52<1:29:08,  1.34s/it]
 94%|█████████▎| 57928/61904 [6:35:54<1:28:40,  1.34s/it]
 94%|█████████▎| 57929/61904 [6:35:55<1:29:28,  1.35s/it]
 94%|█████████▎| 57930/61904 [6:35:56<1:29:36,  1.35s/it]
 94%|█████████▎| 57931/61904 [6:35:58<1:28:27,  1.34s/it]
 94%|█████████▎| 57932/61904 [6:35:59<1:27:55,  1.33s/it]
 94%|█████████▎| 57933/61904 [6:36:00<1:27:40,  1.32s/it]
 94%|█████████▎| 57934/61904 [6:36:02<1:29:28,  1.35s/it]
 94%|█████████▎| 57935/61904 [6:36:03<1:28:28,  1.34s/it]
 94%|█████████▎| 57936/61904 [6:36:04<1:30:03,  1.36s/it]
 94%|█████████▎| 57937/61904 [6:36:06<1:29:15,  1.35s/it]
 94%|█████████▎| 57938/61904 [6:36:07<1:28:09,  1.33s/it]
 94%|█████████▎| 57939/61904 [6:36:09<1:31:33,  1.39s/it]
 94%|█████████▎| 57940/61904 [6:36:10<1:32:37,  1.40s/it]
                                                         
{'loss': 2.4428, 'learning_rate': 1.0642421885129003e-07, 'epoch': 14.97}

 94%|█████████▎| 57940/61904 [6:36:10<1:32:37,  1.40s/it]
 94%|█████████▎| 57941/61904 [6:36:11<1:31:36,  1.39s/it]
 94%|█████████▎| 57942/61904 [6:36:13<1:32:13,  1.40s/it]
 94%|█████████▎| 57943/61904 [6:36:14<1:33:30,  1.42s/it]
 94%|█████████▎| 57944/61904 [6:36:16<1:33:33,  1.42s/it]
 94%|█████████▎| 57945/61904 [6:36:17<1:30:46,  1.38s/it]
 94%|█████████▎| 57946/61904 [6:36:18<1:28:44,  1.35s/it]
 94%|█████████▎| 57947/61904 [6:36:20<1:29:49,  1.36s/it]
 94%|█████████▎| 57948/61904 [6:36:21<1:31:45,  1.39s/it]
 94%|█████████▎| 57949/61904 [6:36:23<1:33:10,  1.41s/it]
 94%|█████████▎| 57950/61904 [6:36:24<1:31:50,  1.39s/it]
 94%|█████████▎| 57951/61904 [6:36:25<1:31:12,  1.38s/it]
 94%|█████████▎| 57952/61904 [6:36:27<1:31:26,  1.39s/it]
 94%|█████████▎| 57953/61904 [6:36:28<1:28:24,  1.34s/it]
 94%|█████████▎| 57954/61904 [6:36:29<1:28:01,  1.34s/it]
 94%|█████████▎| 57955/61904 [6:36:31<1:33:23,  1.42s/it]
 94%|█████████▎| 57956/61904 [6:36:32<1:32:42,  1.41s/it]
 94%|█████████▎| 57957/61904 [6:36:34<1:31:01,  1.38s/it]
 94%|█████████▎| 57958/61904 [6:36:35<1:28:55,  1.35s/it]
 94%|█████████▎| 57959/61904 [6:36:36<1:28:48,  1.35s/it]
 94%|█████████▎| 57960/61904 [6:36:37<1:25:22,  1.30s/it]
                                                         
{'loss': 2.3815, 'learning_rate': 1.0639180604174769e-07, 'epoch': 14.98}

 94%|█████████▎| 57960/61904 [6:36:37<1:25:22,  1.30s/it]
 94%|█████████▎| 57961/61904 [6:36:39<1:25:18,  1.30s/it]
 94%|█████████▎| 57962/61904 [6:36:40<1:26:40,  1.32s/it]
 94%|█████████▎| 57963/61904 [6:36:41<1:25:32,  1.30s/it]
 94%|█████████▎| 57964/61904 [6:36:43<1:27:17,  1.33s/it]
 94%|█████████▎| 57965/61904 [6:36:44<1:30:45,  1.38s/it]
 94%|█████████▎| 57966/61904 [6:36:45<1:28:21,  1.35s/it]
 94%|█████████▎| 57967/61904 [6:36:47<1:28:53,  1.35s/it]
 94%|█████████▎| 57968/61904 [6:36:48<1:32:37,  1.41s/it]
 94%|█████████▎| 57969/61904 [6:36:50<1:31:25,  1.39s/it]
 94%|█████████▎| 57970/61904 [6:36:51<1:30:17,  1.38s/it]
 94%|█████████▎| 57971/61904 [6:36:52<1:30:20,  1.38s/it]
 94%|█████████▎| 57972/61904 [6:36:54<1:30:36,  1.38s/it]
 94%|█████████▎| 57973/61904 [6:36:55<1:30:36,  1.38s/it]
 94%|█████████▎| 57974/61904 [6:36:57<1:31:23,  1.40s/it]
 94%|█████████▎| 57975/61904 [6:36:58<1:29:30,  1.37s/it]
 94%|█████████▎| 57976/61904 [6:36:59<1:32:44,  1.42s/it]
 94%|█████████▎| 57977/61904 [6:37:01<1:30:49,  1.39s/it]
 94%|█████████▎| 57978/61904 [6:37:02<1:30:05,  1.38s/it]
 94%|█████████▎| 57979/61904 [6:37:03<1:28:52,  1.36s/it]
 94%|█████████▎| 57980/61904 [6:37:05<1:26:18,  1.32s/it]
                                                         
{'loss': 2.4527, 'learning_rate': 1.0635939323220535e-07, 'epoch': 14.99}

 94%|█████████▎| 57980/61904 [6:37:05<1:26:18,  1.32s/it]
 94%|█████████▎| 57981/61904 [6:37:06<1:27:33,  1.34s/it]
 94%|█████████▎| 57982/61904 [6:37:08<1:29:20,  1.37s/it]
 94%|█████████▎| 57983/61904 [6:37:09<1:31:43,  1.40s/it]
 94%|█████████▎| 57984/61904 [6:37:10<1:28:11,  1.35s/it]
 94%|█████████▎| 57985/61904 [6:37:11<1:25:44,  1.31s/it]
 94%|█████████▎| 57986/61904 [6:37:13<1:25:42,  1.31s/it]
 94%|█████████▎| 57987/61904 [6:37:14<1:25:27,  1.31s/it]
 94%|█████████▎| 57988/61904 [6:37:15<1:27:14,  1.34s/it]
 94%|█████████▎| 57989/61904 [6:37:17<1:24:42,  1.30s/it]
 94%|█████████▎| 57990/61904 [6:37:18<1:26:00,  1.32s/it]
 94%|█████████▎| 57991/61904 [6:37:19<1:25:58,  1.32s/it]
 94%|█████████▎| 57992/61904 [6:37:21<1:27:55,  1.35s/it]
 94%|█████████▎| 57993/61904 [6:37:22<1:24:45,  1.30s/it]
 94%|█████████▎| 57994/61904 [6:37:23<1:25:23,  1.31s/it]
 94%|█████████▎| 57995/61904 [6:37:25<1:26:46,  1.33s/it]
 94%|█████████▎| 57996/61904 [6:37:26<1:26:49,  1.33s/it]
 94%|█████████▎| 57997/61904 [6:37:27<1:26:20,  1.33s/it]
 94%|█████████▎| 57998/61904 [6:37:29<1:24:59,  1.31s/it]
 94%|█████████▎| 57999/61904 [6:37:30<1:24:24,  1.30s/it]
 94%|█████████▎| 58000/61904 [6:37:31<1:26:49,  1.33s/it]
                                                         
{'loss': 2.4376, 'learning_rate': 1.0632698042266301e-07, 'epoch': 14.99}

 94%|█████████▎| 58000/61904 [6:37:31<1:26:49,  1.33s/it]
 94%|█████████▎| 58001/61904 [6:37:33<1:27:16,  1.34s/it]
 94%|█████████▎| 58002/61904 [6:37:34<1:28:21,  1.36s/it]
 94%|█████████▎| 58003/61904 [6:37:35<1:28:56,  1.37s/it]
 94%|█████████▎| 58004/61904 [6:37:37<1:28:15,  1.36s/it]
 94%|█████████▎| 58005/61904 [6:37:38<1:28:17,  1.36s/it]
 94%|█████████▎| 58006/61904 [6:37:40<1:29:05,  1.37s/it]
 94%|█████████▎| 58007/61904 [6:37:41<1:27:30,  1.35s/it]
 94%|█████████▎| 58008/61904 [6:37:42<1:27:43,  1.35s/it]
 94%|█████████▎| 58009/61904 [6:37:44<1:27:36,  1.35s/it]
 94%|█████████▎| 58010/61904 [6:37:45<1:27:26,  1.35s/it]
 94%|█████████▎| 58011/61904 [6:37:46<1:29:42,  1.38s/it]
 94%|█████████▎| 58012/61904 [6:37:48<1:29:20,  1.38s/it]
 94%|█████████▎| 58013/61904 [6:37:49<1:29:32,  1.38s/it]
 94%|█████████▎| 58014/61904 [6:37:50<1:29:52,  1.39s/it]
 94%|█████████▎| 58015/61904 [6:37:52<1:28:55,  1.37s/it]
 94%|█████████▎| 58016/61904 [6:37:53<1:29:23,  1.38s/it]
 94%|█████████▎| 58017/61904 [6:37:55<1:29:56,  1.39s/it]
 94%|█████████▎| 58018/61904 [6:37:56<1:29:31,  1.38s/it]
 94%|█████████▎| 58019/61904 [6:37:57<1:29:12,  1.38s/it]
 94%|█████████▎| 58020/61904 [6:37:59<1:29:38,  1.38s/it]
                                                         
{'loss': 2.4053, 'learning_rate': 1.062945676131207e-07, 'epoch': 15.0}

 94%|█████████▎| 58020/61904 [6:37:59<1:29:38,  1.38s/it]
 94%|█████████▎| 58021/61904 [6:38:00<1:30:43,  1.40s/it]
 94%|█████████▎| 58022/61904 [6:38:02<1:30:23,  1.40s/it]
 94%|█████████▎| 58023/61904 [6:38:03<1:33:04,  1.44s/it]
 94%|█████████▎| 58024/61904 [6:38:05<1:32:39,  1.43s/it]
 94%|█████████▎| 58025/61904 [6:38:06<1:34:08,  1.46s/it]
 94%|█████████▎| 58026/61904 [6:38:07<1:33:21,  1.44s/it]
 94%|█████████▎| 58027/61904 [6:38:09<1:32:01,  1.42s/it]
 94%|█████████▎| 58028/61904 [6:38:10<1:32:10,  1.43s/it]
 94%|█████████▎| 58029/61904 [6:38:12<1:30:48,  1.41s/it]
 94%|█████████▎| 58030/61904 [6:38:13<1:31:49,  1.42s/it]
 94%|█████████▎| 58031/61904 [6:38:14<1:28:35,  1.37s/it]
 94%|█████████▎| 58032/61904 [6:38:16<1:27:21,  1.35s/it]
 94%|█████████▎| 58033/61904 [6:38:17<1:25:36,  1.33s/it]
 94%|█████████▎| 58034/61904 [6:38:18<1:29:32,  1.39s/it]
 94%|█████████▍| 58035/61904 [6:38:20<1:33:02,  1.44s/it]
 94%|█████████▍| 58036/61904 [6:38:21<1:30:57,  1.41s/it]
 94%|█████████▍| 58037/61904 [6:38:23<1:29:09,  1.38s/it]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


  0%|          | 0/861 [00:00<?, ?it/s]

  0%|          | 2/861 [00:01<07:34,  1.89it/s]

  0%|          | 3/861 [00:02<14:38,  1.02s/it]

  0%|          | 4/861 [00:03<13:41,  1.04it/s]

  1%|          | 5/861 [00:04<13:54,  1.03it/s]

  1%|          | 6/861 [00:05<14:31,  1.02s/it]

  1%|          | 7/861 [00:06<11:50,  1.20it/s]

  1%|          | 8/861 [00:06<11:27,  1.24it/s]

  1%|          | 9/861 [00:07<11:10,  1.27it/s]

  1%|          | 10/861 [00:08<11:10,  1.27it/s]

  1%|▏         | 11/861 [00:09<14:25,  1.02s/it]

  1%|▏         | 12/861 [00:11<14:58,  1.06s/it]

  2%|▏         | 13/861 [00:11<14:01,  1.01it/s]

  2%|▏         | 14/861 [00:12<11:02,  1.28it/s]

  2%|▏         | 15/861 [00:12<10:03,  1.40it/s]

  2%|▏         | 16/861 [00:13<08:13,  1.71it/s]

  2%|▏         | 17/861 [00:14<11:06,  1.27it/s]

  2%|▏         | 18/861 [00:14<09:01,  1.56it/s]

  2%|▏         | 19/861 [00:16<14:30,  1.03s/it]

  2%|▏         | 20/861 [00:17<14:40,  1.05s/it]

  2%|▏         | 21/861 [00:18<12:27,  1.12it/s]

  3%|▎         | 22/861 [00:19<14:22,  1.03s/it]

  3%|▎         | 23/861 [00:19<11:24,  1.22it/s]

  3%|▎         | 24/861 [00:21<14:03,  1.01s/it]

  3%|▎         | 25/861 [00:22<14:36,  1.05s/it]

  3%|▎         | 26/861 [00:23<14:28,  1.04s/it]

  3%|▎         | 27/861 [00:24<15:40,  1.13s/it]

  3%|▎         | 28/861 [00:27<23:03,  1.66s/it]

  3%|▎         | 29/861 [00:28<17:18,  1.25s/it]

  3%|▎         | 30/861 [00:29<17:08,  1.24s/it]

  4%|▎         | 31/861 [00:29<13:58,  1.01s/it]

  4%|▎         | 32/861 [00:30<11:26,  1.21it/s]

  4%|▍         | 33/861 [00:31<12:03,  1.14it/s]

  4%|▍         | 34/861 [00:32<12:10,  1.13it/s]

  4%|▍         | 35/861 [00:34<16:49,  1.22s/it]

  4%|▍         | 36/861 [00:34<15:25,  1.12s/it]

  4%|▍         | 37/861 [00:35<14:25,  1.05s/it]

  4%|▍         | 38/861 [00:37<15:14,  1.11s/it]

  5%|▍         | 39/861 [00:37<13:13,  1.04it/s]

  5%|▍         | 40/861 [00:38<11:59,  1.14it/s]

  5%|▍         | 41/861 [00:38<10:16,  1.33it/s]

  5%|▍         | 42/861 [00:40<12:24,  1.10it/s]

  5%|▍         | 43/861 [00:41<13:05,  1.04it/s]

  5%|▌         | 44/861 [00:41<12:19,  1.11it/s]

  5%|▌         | 45/861 [00:42<12:17,  1.11it/s]

  5%|▌         | 46/861 [00:44<16:30,  1.22s/it]

  5%|▌         | 47/861 [00:45<16:23,  1.21s/it]

  6%|▌         | 48/861 [00:47<17:55,  1.32s/it]

  6%|▌         | 49/861 [00:48<17:39,  1.30s/it]

  6%|▌         | 50/861 [00:49<13:03,  1.03it/s]

  6%|▌         | 51/861 [00:49<13:01,  1.04it/s]

  6%|▌         | 52/861 [00:50<11:56,  1.13it/s]

  6%|▌         | 53/861 [00:51<10:46,  1.25it/s]

  6%|▋         | 54/861 [00:51<08:29,  1.58it/s]

  6%|▋         | 55/861 [00:52<07:52,  1.71it/s]

  7%|▋         | 56/861 [00:52<08:40,  1.55it/s]

  7%|▋         | 57/861 [00:53<07:19,  1.83it/s]

  7%|▋         | 58/861 [00:53<06:22,  2.10it/s]

  7%|▋         | 59/861 [00:54<07:56,  1.68it/s]

  7%|▋         | 60/861 [00:54<08:21,  1.60it/s]

  7%|▋         | 61/861 [00:55<07:24,  1.80it/s]

  7%|▋         | 62/861 [00:55<06:18,  2.11it/s]

  7%|▋         | 63/861 [00:56<06:22,  2.08it/s]

  7%|▋         | 64/861 [00:56<06:43,  1.98it/s]

  8%|▊         | 65/861 [00:57<06:33,  2.02it/s]

  8%|▊         | 66/861 [00:57<06:16,  2.11it/s]

  8%|▊         | 67/861 [00:58<07:42,  1.71it/s]

  8%|▊         | 68/861 [00:59<09:04,  1.46it/s]

  8%|▊         | 69/861 [01:00<10:01,  1.32it/s]

  8%|▊         | 70/861 [01:01<11:52,  1.11it/s]

  8%|▊         | 71/861 [01:02<12:57,  1.02it/s]

  8%|▊         | 72/861 [01:03<12:30,  1.05it/s]

  8%|▊         | 73/861 [01:03<09:53,  1.33it/s]

  9%|▊         | 74/861 [01:04<09:26,  1.39it/s]

  9%|▊         | 75/861 [01:05<11:11,  1.17it/s]

  9%|▉         | 76/861 [01:06<09:35,  1.36it/s]

  9%|▉         | 77/861 [01:07<10:32,  1.24it/s]

  9%|▉         | 78/861 [01:07<10:11,  1.28it/s]

  9%|▉         | 79/861 [01:08<11:11,  1.16it/s]

  9%|▉         | 80/861 [01:09<09:53,  1.32it/s]

  9%|▉         | 81/861 [01:10<09:53,  1.31it/s]

 10%|▉         | 82/861 [01:10<08:44,  1.48it/s]

 10%|▉         | 83/861 [01:11<09:27,  1.37it/s]

 10%|▉         | 84/861 [01:12<11:14,  1.15it/s]

 10%|▉         | 85/861 [01:13<10:16,  1.26it/s]

 10%|▉         | 86/861 [01:13<09:07,  1.41it/s]

 10%|█         | 87/861 [01:14<10:44,  1.20it/s]

 10%|█         | 88/861 [01:15<08:13,  1.57it/s]

 10%|█         | 89/861 [01:15<08:09,  1.58it/s]

 10%|█         | 90/861 [01:17<13:10,  1.03s/it]

 11%|█         | 91/861 [01:18<11:46,  1.09it/s]

 11%|█         | 92/861 [01:19<11:03,  1.16it/s]

 11%|█         | 93/861 [01:20<11:47,  1.09it/s]

 11%|█         | 94/861 [01:20<09:09,  1.40it/s]

 11%|█         | 95/861 [01:21<08:49,  1.45it/s]

 11%|█         | 96/861 [01:21<09:35,  1.33it/s]

 11%|█▏        | 97/861 [01:23<11:59,  1.06it/s]

 11%|█▏        | 98/861 [01:24<11:52,  1.07it/s]

 11%|█▏        | 99/861 [01:25<14:19,  1.13s/it]

 12%|█▏        | 100/861 [01:26<12:09,  1.04it/s]

 12%|█▏        | 101/861 [01:26<10:19,  1.23it/s]

 12%|█▏        | 102/861 [01:27<09:26,  1.34it/s]

 12%|█▏        | 103/861 [01:27<08:00,  1.58it/s]

 12%|█▏        | 104/861 [01:29<10:38,  1.19it/s]

 12%|█▏        | 105/861 [01:30<11:30,  1.10it/s]

 12%|█▏        | 106/861 [01:30<09:52,  1.27it/s]

 12%|█▏        | 107/861 [01:31<08:50,  1.42it/s]

 13%|█▎        | 108/861 [01:31<07:16,  1.73it/s]

 13%|█▎        | 109/861 [01:31<06:03,  2.07it/s]

 13%|█▎        | 110/861 [01:32<05:54,  2.12it/s]

 13%|█▎        | 111/861 [01:33<08:29,  1.47it/s]

 13%|█▎        | 112/861 [01:33<07:04,  1.77it/s]

 13%|█▎        | 113/861 [01:34<07:34,  1.64it/s]

 13%|█▎        | 114/861 [01:35<08:15,  1.51it/s]

 13%|█▎        | 115/861 [01:35<07:20,  1.69it/s]

 13%|█▎        | 116/861 [01:35<06:24,  1.94it/s]

 14%|█▎        | 117/861 [01:37<08:43,  1.42it/s]

 14%|█▎        | 118/861 [01:37<08:40,  1.43it/s]

 14%|█▍        | 119/861 [01:38<08:22,  1.48it/s]

 14%|█▍        | 120/861 [01:38<06:41,  1.85it/s]

 14%|█▍        | 121/861 [01:39<08:04,  1.53it/s]

 14%|█▍        | 122/861 [01:40<09:53,  1.24it/s]

 14%|█▍        | 123/861 [01:41<09:33,  1.29it/s]

 14%|█▍        | 124/861 [01:43<13:15,  1.08s/it]

 15%|█▍        | 125/861 [01:43<11:48,  1.04it/s]

 15%|█▍        | 126/861 [01:45<12:26,  1.02s/it]

 15%|█▍        | 127/861 [01:46<12:45,  1.04s/it]

 15%|█▍        | 128/861 [01:46<10:46,  1.13it/s]

 15%|█▍        | 129/861 [01:47<10:38,  1.15it/s]

 15%|█▌        | 130/861 [01:48<10:34,  1.15it/s]

 15%|█▌        | 131/861 [01:49<10:06,  1.20it/s]

 15%|█▌        | 132/861 [01:49<10:19,  1.18it/s]

 15%|█▌        | 133/861 [01:50<10:35,  1.15it/s]

 16%|█▌        | 134/861 [01:51<08:06,  1.50it/s]

 16%|█▌        | 135/861 [01:51<07:10,  1.69it/s]

 16%|█▌        | 136/861 [01:52<07:10,  1.68it/s]

 16%|█▌        | 137/861 [01:52<06:19,  1.91it/s]

 16%|█▌        | 138/861 [01:52<05:54,  2.04it/s]

 16%|█▌        | 139/861 [01:53<05:25,  2.22it/s]

 16%|█▋        | 140/861 [01:53<05:10,  2.32it/s]

 16%|█▋        | 141/861 [01:53<04:53,  2.46it/s]

 16%|█▋        | 142/861 [01:54<04:49,  2.48it/s]

 17%|█▋        | 143/861 [01:55<08:03,  1.48it/s]

 17%|█▋        | 144/861 [01:56<09:40,  1.24it/s]

 17%|█▋        | 145/861 [01:57<08:29,  1.41it/s]

 17%|█▋        | 146/861 [01:57<08:14,  1.45it/s]

 17%|█▋        | 147/861 [01:58<08:21,  1.42it/s]

 17%|█▋        | 148/861 [01:58<06:40,  1.78it/s]

 17%|█▋        | 149/861 [01:59<06:00,  1.97it/s]

 17%|█▋        | 150/861 [02:00<09:59,  1.19it/s]

 18%|█▊        | 151/861 [02:02<13:29,  1.14s/it]

 18%|█▊        | 152/861 [02:03<13:14,  1.12s/it]

 18%|█▊        | 153/861 [02:04<12:36,  1.07s/it]

 18%|█▊        | 154/861 [02:05<12:27,  1.06s/it]

 18%|█▊        | 155/861 [02:07<14:51,  1.26s/it]

 18%|█▊        | 156/861 [02:08<14:41,  1.25s/it]

 18%|█▊        | 157/861 [02:09<12:58,  1.11s/it]

 18%|█▊        | 158/861 [02:10<12:01,  1.03s/it]

 18%|█▊        | 159/861 [02:11<10:54,  1.07it/s]

 19%|█▊        | 160/861 [02:11<10:08,  1.15it/s]

 19%|█▊        | 161/861 [02:13<13:58,  1.20s/it]

 19%|█▉        | 162/861 [02:14<10:41,  1.09it/s]

 19%|█▉        | 163/861 [02:14<08:26,  1.38it/s]

 19%|█▉        | 164/861 [02:15<10:32,  1.10it/s]

 19%|█▉        | 165/861 [02:16<10:05,  1.15it/s]

 19%|█▉        | 166/861 [02:17<10:08,  1.14it/s]

 19%|█▉        | 167/861 [02:17<07:42,  1.50it/s]

 20%|█▉        | 168/861 [02:18<07:47,  1.48it/s]

 20%|█▉        | 169/861 [02:19<08:40,  1.33it/s]

 20%|█▉        | 170/861 [02:19<08:50,  1.30it/s]

 20%|█▉        | 171/861 [02:20<08:33,  1.34it/s]

 20%|█▉        | 172/861 [02:21<07:49,  1.47it/s]

 20%|██        | 173/861 [02:21<07:37,  1.50it/s]

 20%|██        | 174/861 [02:23<10:09,  1.13it/s]

 20%|██        | 175/861 [02:23<09:34,  1.19it/s]

 20%|██        | 176/861 [02:24<07:24,  1.54it/s]

 21%|██        | 177/861 [02:24<07:44,  1.47it/s]

 21%|██        | 178/861 [02:25<08:02,  1.42it/s]

 21%|██        | 179/861 [02:26<08:03,  1.41it/s]

 21%|██        | 180/861 [02:26<07:18,  1.55it/s]

 21%|██        | 181/861 [02:27<06:26,  1.76it/s]

 21%|██        | 182/861 [02:27<05:56,  1.90it/s]

 21%|██▏       | 183/861 [02:28<06:59,  1.62it/s]

 21%|██▏       | 184/861 [02:29<09:01,  1.25it/s]

 21%|██▏       | 185/861 [02:30<07:59,  1.41it/s]

 22%|██▏       | 186/861 [02:30<07:01,  1.60it/s]

 22%|██▏       | 187/861 [02:31<08:04,  1.39it/s]

 22%|██▏       | 188/861 [02:32<08:06,  1.38it/s]

 22%|██▏       | 189/861 [02:33<10:38,  1.05it/s]

 22%|██▏       | 190/861 [02:34<11:08,  1.00it/s]

 22%|██▏       | 191/861 [02:35<09:10,  1.22it/s]

 22%|██▏       | 192/861 [02:35<08:35,  1.30it/s]

 22%|██▏       | 193/861 [02:36<09:14,  1.20it/s]

 23%|██▎       | 194/861 [02:37<08:08,  1.37it/s]

 23%|██▎       | 195/861 [02:37<07:09,  1.55it/s]

 23%|██▎       | 196/861 [02:38<06:32,  1.69it/s]

 23%|██▎       | 197/861 [02:38<06:10,  1.79it/s]

 23%|██▎       | 198/861 [02:39<05:30,  2.01it/s]

 23%|██▎       | 199/861 [02:39<06:00,  1.84it/s]

 23%|██▎       | 200/861 [02:40<07:40,  1.43it/s]

 23%|██▎       | 201/861 [02:41<08:57,  1.23it/s]

 23%|██▎       | 202/861 [02:43<09:49,  1.12it/s]

 24%|██▎       | 203/861 [02:43<07:51,  1.40it/s]

 24%|██▎       | 204/861 [02:43<06:02,  1.81it/s]

 24%|██▍       | 205/861 [02:43<05:31,  1.98it/s]

 24%|██▍       | 206/861 [02:44<06:09,  1.77it/s]

 24%|██▍       | 207/861 [02:45<06:37,  1.65it/s]

 24%|██▍       | 208/861 [02:45<06:45,  1.61it/s]

 24%|██▍       | 209/861 [02:46<06:42,  1.62it/s]

 24%|██▍       | 210/861 [02:47<07:00,  1.55it/s]

 25%|██▍       | 211/861 [02:48<09:29,  1.14it/s]

 25%|██▍       | 212/861 [02:49<09:50,  1.10it/s]

 25%|██▍       | 213/861 [02:50<08:31,  1.27it/s]

 25%|██▍       | 214/861 [02:50<07:41,  1.40it/s]

 25%|██▍       | 215/861 [02:51<08:11,  1.31it/s]

 25%|██▌       | 216/861 [02:52<07:07,  1.51it/s]

 25%|██▌       | 217/861 [02:52<05:51,  1.83it/s]

 25%|██▌       | 218/861 [02:52<05:15,  2.04it/s]

 25%|██▌       | 219/861 [02:53<06:46,  1.58it/s]

 26%|██▌       | 220/861 [02:54<07:10,  1.49it/s]

 26%|██▌       | 221/861 [02:54<06:28,  1.65it/s]

 26%|██▌       | 222/861 [02:56<08:21,  1.27it/s]

 26%|██▌       | 223/861 [02:57<08:52,  1.20it/s]

 26%|██▌       | 224/861 [02:57<08:09,  1.30it/s]

 26%|██▌       | 225/861 [02:58<09:57,  1.07it/s]

 26%|██▌       | 226/861 [03:00<11:40,  1.10s/it]

 26%|██▋       | 227/861 [03:01<10:47,  1.02s/it]

 26%|██▋       | 228/861 [03:02<10:35,  1.00s/it]

 27%|██▋       | 229/861 [03:02<09:13,  1.14it/s]

 27%|██▋       | 230/861 [03:03<09:32,  1.10it/s]

 27%|██▋       | 231/861 [03:06<15:20,  1.46s/it]

 27%|██▋       | 232/861 [03:06<11:16,  1.07s/it]

 27%|██▋       | 233/861 [03:07<10:18,  1.02it/s]

 27%|██▋       | 234/861 [03:08<09:01,  1.16it/s]

 27%|██▋       | 235/861 [03:08<09:04,  1.15it/s]

 27%|██▋       | 236/861 [03:09<08:17,  1.26it/s]

 28%|██▊       | 237/861 [03:10<08:01,  1.30it/s]

 28%|██▊       | 238/861 [03:10<06:31,  1.59it/s]

 28%|██▊       | 239/861 [03:12<09:47,  1.06it/s]

 28%|██▊       | 240/861 [03:12<08:44,  1.18it/s]

 28%|██▊       | 241/861 [03:14<10:28,  1.01s/it]

 28%|██▊       | 242/861 [03:14<08:56,  1.15it/s]

 28%|██▊       | 243/861 [03:15<09:50,  1.05it/s]

 28%|██▊       | 244/861 [03:16<09:14,  1.11it/s]

 28%|██▊       | 245/861 [03:17<09:48,  1.05it/s]

 29%|██▊       | 246/861 [03:18<09:40,  1.06it/s]

 29%|██▊       | 247/861 [03:19<07:50,  1.31it/s]

 29%|██▉       | 248/861 [03:19<06:00,  1.70it/s]

 29%|██▉       | 249/861 [03:19<06:21,  1.61it/s]

 29%|██▉       | 250/861 [03:21<07:56,  1.28it/s]

 29%|██▉       | 251/861 [03:21<08:12,  1.24it/s]

 29%|██▉       | 252/861 [03:22<07:57,  1.27it/s]

 29%|██▉       | 253/861 [03:23<07:07,  1.42it/s]

 30%|██▉       | 254/861 [03:23<05:51,  1.73it/s]

 30%|██▉       | 255/861 [03:24<05:55,  1.70it/s]

 30%|██▉       | 256/861 [03:25<07:59,  1.26it/s]

 30%|██▉       | 257/861 [03:26<08:05,  1.24it/s]

 30%|██▉       | 258/861 [03:27<09:11,  1.09it/s]

 30%|███       | 259/861 [03:28<11:00,  1.10s/it]

 30%|███       | 260/861 [03:30<10:56,  1.09s/it]

 30%|███       | 261/861 [03:32<14:11,  1.42s/it]

 30%|███       | 262/861 [03:32<11:43,  1.17s/it]

 31%|███       | 263/861 [03:32<08:42,  1.14it/s]

 31%|███       | 264/861 [03:33<08:32,  1.16it/s]

 31%|███       | 265/861 [03:34<07:21,  1.35it/s]

 31%|███       | 266/861 [03:34<06:05,  1.63it/s]

 31%|███       | 267/861 [03:35<05:50,  1.69it/s]

 31%|███       | 268/861 [03:35<05:18,  1.86it/s]

 31%|███       | 269/861 [03:36<05:52,  1.68it/s]

 31%|███▏      | 270/861 [03:37<06:44,  1.46it/s]

 31%|███▏      | 271/861 [03:37<06:38,  1.48it/s]

 32%|███▏      | 272/861 [03:39<08:20,  1.18it/s]

 32%|███▏      | 273/861 [03:39<08:34,  1.14it/s]

 32%|███▏      | 274/861 [03:41<09:52,  1.01s/it]

 32%|███▏      | 275/861 [03:41<07:24,  1.32it/s]

 32%|███▏      | 276/861 [03:42<08:06,  1.20it/s]

 32%|███▏      | 277/861 [03:44<10:13,  1.05s/it]

 32%|███▏      | 278/861 [03:45<10:49,  1.11s/it]

 32%|███▏      | 279/861 [03:46<10:03,  1.04s/it]

 33%|███▎      | 280/861 [03:47<09:49,  1.01s/it]

 33%|███▎      | 281/861 [03:48<10:30,  1.09s/it]

 33%|███▎      | 282/861 [03:49<09:42,  1.01s/it]

 33%|███▎      | 283/861 [03:49<08:45,  1.10it/s]

 33%|███▎      | 284/861 [03:50<07:07,  1.35it/s]

 33%|███▎      | 285/861 [03:50<06:49,  1.41it/s]

 33%|███▎      | 286/861 [03:52<10:50,  1.13s/it]

 33%|███▎      | 287/861 [03:54<13:15,  1.39s/it]

 33%|███▎      | 288/861 [03:55<11:48,  1.24s/it]

 34%|███▎      | 289/861 [03:56<09:11,  1.04it/s]

 34%|███▎      | 290/861 [03:56<08:22,  1.14it/s]

 34%|███▍      | 291/861 [03:57<07:41,  1.23it/s]

 34%|███▍      | 292/861 [03:59<10:06,  1.07s/it]

 34%|███▍      | 293/861 [03:59<09:19,  1.02it/s]

 34%|███▍      | 294/861 [04:01<09:54,  1.05s/it]

 34%|███▍      | 295/861 [04:01<07:33,  1.25it/s]

 34%|███▍      | 296/861 [04:02<07:09,  1.32it/s]

 34%|███▍      | 297/861 [04:03<08:30,  1.10it/s]

 35%|███▍      | 298/861 [04:04<09:27,  1.01s/it]

 35%|███▍      | 299/861 [04:06<11:43,  1.25s/it]

 35%|███▍      | 300/861 [04:07<10:06,  1.08s/it]

 35%|███▍      | 301/861 [04:07<09:10,  1.02it/s]

 35%|███▌      | 302/861 [04:08<07:04,  1.32it/s]

 35%|███▌      | 303/861 [04:09<09:03,  1.03it/s]

 35%|███▌      | 304/861 [04:10<09:12,  1.01it/s]

 35%|███▌      | 305/861 [04:12<10:37,  1.15s/it]

 36%|███▌      | 306/861 [04:13<11:53,  1.29s/it]

 36%|███▌      | 307/861 [04:15<13:04,  1.42s/it]

 36%|███▌      | 308/861 [04:15<09:37,  1.04s/it]

 36%|███▌      | 309/861 [04:15<07:37,  1.21it/s]

 36%|███▌      | 310/861 [04:16<07:13,  1.27it/s]

 36%|███▌      | 311/861 [04:17<07:43,  1.19it/s]

 36%|███▌      | 312/861 [04:18<08:23,  1.09it/s]

 36%|███▋      | 313/861 [04:20<10:03,  1.10s/it]

 36%|███▋      | 314/861 [04:21<09:36,  1.05s/it]

 37%|███▋      | 315/861 [04:21<08:26,  1.08it/s]

 37%|███▋      | 316/861 [04:23<09:30,  1.05s/it]

 37%|███▋      | 317/861 [04:23<07:10,  1.26it/s]

 37%|███▋      | 318/861 [04:23<06:04,  1.49it/s]

 37%|███▋      | 319/861 [04:25<08:38,  1.04it/s]

 37%|███▋      | 320/861 [04:26<08:00,  1.13it/s]

 37%|███▋      | 321/861 [04:27<09:37,  1.07s/it]

 37%|███▋      | 322/861 [04:29<11:52,  1.32s/it]

 38%|███▊      | 323/861 [04:30<10:27,  1.17s/it]

 38%|███▊      | 324/861 [04:31<10:50,  1.21s/it]

 38%|███▊      | 325/861 [04:32<10:49,  1.21s/it]

 38%|███▊      | 326/861 [04:32<08:02,  1.11it/s]

 38%|███▊      | 327/861 [04:34<09:44,  1.09s/it]

 38%|███▊      | 328/861 [04:35<08:46,  1.01it/s]

 38%|███▊      | 329/861 [04:36<08:17,  1.07it/s]

 38%|███▊      | 330/861 [04:36<07:34,  1.17it/s]

 38%|███▊      | 331/861 [04:39<13:23,  1.52s/it]

 39%|███▊      | 332/861 [04:40<11:54,  1.35s/it]

 39%|███▊      | 333/861 [04:42<12:13,  1.39s/it]

 39%|███▉      | 334/861 [04:43<12:16,  1.40s/it]

 39%|███▉      | 335/861 [04:44<10:21,  1.18s/it]

 39%|███▉      | 336/861 [04:45<10:24,  1.19s/it]

 39%|███▉      | 337/861 [04:46<08:42,  1.00it/s]

 39%|███▉      | 338/861 [04:47<11:01,  1.26s/it]

 39%|███▉      | 339/861 [04:48<10:21,  1.19s/it]

 39%|███▉      | 340/861 [04:49<08:16,  1.05it/s]

 40%|███▉      | 341/861 [04:49<06:32,  1.32it/s]

 40%|███▉      | 342/861 [04:50<06:20,  1.36it/s]

 40%|███▉      | 343/861 [04:51<06:39,  1.30it/s]

 40%|███▉      | 344/861 [04:51<05:57,  1.45it/s]

 40%|████      | 345/861 [04:52<06:47,  1.27it/s]

 40%|████      | 346/861 [04:53<07:14,  1.18it/s]

 40%|████      | 347/861 [04:54<06:11,  1.38it/s]

 40%|████      | 348/861 [04:54<05:46,  1.48it/s]

 41%|████      | 349/861 [04:55<05:55,  1.44it/s]

 41%|████      | 350/861 [04:56<06:36,  1.29it/s]

 41%|████      | 351/861 [04:57<06:25,  1.32it/s]

 41%|████      | 352/861 [04:57<05:59,  1.42it/s]

 41%|████      | 353/861 [04:58<05:50,  1.45it/s]

 41%|████      | 354/861 [04:58<05:42,  1.48it/s]

 41%|████      | 355/861 [04:59<05:04,  1.66it/s]

 41%|████▏     | 356/861 [04:59<04:46,  1.77it/s]

 41%|████▏     | 357/861 [05:00<04:08,  2.03it/s]

 42%|████▏     | 358/861 [05:00<04:42,  1.78it/s]

 42%|████▏     | 359/861 [05:02<07:03,  1.19it/s]

 42%|████▏     | 360/861 [05:03<07:54,  1.06it/s]

 42%|████▏     | 361/861 [05:04<07:30,  1.11it/s]

 42%|████▏     | 362/861 [05:05<08:09,  1.02it/s]

 42%|████▏     | 363/861 [05:06<08:14,  1.01it/s]

 42%|████▏     | 364/861 [05:07<07:24,  1.12it/s]

 42%|████▏     | 365/861 [05:09<10:41,  1.29s/it]

 43%|████▎     | 366/861 [05:10<09:59,  1.21s/it]

 43%|████▎     | 367/861 [05:12<11:28,  1.39s/it]

 43%|████▎     | 368/861 [05:13<10:07,  1.23s/it]

 43%|████▎     | 369/861 [05:13<08:47,  1.07s/it]

 43%|████▎     | 370/861 [05:14<07:50,  1.04it/s]

 43%|████▎     | 371/861 [05:15<07:41,  1.06it/s]

 43%|████▎     | 372/861 [05:16<08:16,  1.01s/it]

 43%|████▎     | 373/861 [05:17<07:29,  1.09it/s]

 43%|████▎     | 374/861 [05:19<10:20,  1.27s/it]

 44%|████▎     | 375/861 [05:21<11:53,  1.47s/it]

 44%|████▎     | 376/861 [05:22<09:51,  1.22s/it]

 44%|████▍     | 377/861 [05:23<10:46,  1.33s/it]

 44%|████▍     | 378/861 [05:25<12:29,  1.55s/it]

 44%|████▍     | 379/861 [05:25<09:10,  1.14s/it]

 44%|████▍     | 380/861 [05:26<08:32,  1.07s/it]

 44%|████▍     | 381/861 [05:27<08:04,  1.01s/it]

 44%|████▍     | 382/861 [05:28<08:10,  1.02s/it]

 44%|████▍     | 383/861 [05:29<07:54,  1.01it/s]

 45%|████▍     | 384/861 [05:30<07:15,  1.10it/s]

 45%|████▍     | 385/861 [05:30<05:53,  1.34it/s]

 45%|████▍     | 386/861 [05:31<06:04,  1.30it/s]

 45%|████▍     | 387/861 [05:32<07:08,  1.11it/s]

 45%|████▌     | 388/861 [05:33<06:47,  1.16it/s]

 45%|████▌     | 389/861 [05:33<05:45,  1.36it/s]

 45%|████▌     | 390/861 [05:34<05:35,  1.41it/s]

 45%|████▌     | 391/861 [05:35<05:59,  1.31it/s]

 46%|████▌     | 392/861 [05:36<06:23,  1.22it/s]

 46%|████▌     | 393/861 [05:37<07:36,  1.03it/s]

 46%|████▌     | 394/861 [05:38<08:03,  1.04s/it]

 46%|████▌     | 395/861 [05:39<06:56,  1.12it/s]

 46%|████▌     | 396/861 [05:39<05:56,  1.31it/s]

 46%|████▌     | 397/861 [05:40<04:35,  1.68it/s]

 46%|████▌     | 398/861 [05:40<04:55,  1.57it/s]

 46%|████▋     | 399/861 [05:42<06:19,  1.22it/s]

 46%|████▋     | 400/861 [05:43<07:16,  1.06it/s]

 47%|████▋     | 401/861 [05:43<06:08,  1.25it/s]

 47%|████▋     | 402/861 [05:44<06:06,  1.25it/s]

 47%|████▋     | 403/861 [05:45<05:59,  1.28it/s]

 47%|████▋     | 404/861 [05:46<06:25,  1.18it/s]

 47%|████▋     | 405/861 [05:46<05:19,  1.43it/s]

 47%|████▋     | 406/861 [05:47<06:20,  1.20it/s]

 47%|████▋     | 407/861 [05:48<06:43,  1.12it/s]

 47%|████▋     | 408/861 [05:49<06:23,  1.18it/s]

 48%|████▊     | 409/861 [05:50<05:50,  1.29it/s]

 48%|████▊     | 410/861 [05:51<06:01,  1.25it/s]

 48%|████▊     | 411/861 [05:51<04:59,  1.50it/s]

 48%|████▊     | 412/861 [05:52<06:13,  1.20it/s]

 48%|████▊     | 413/861 [05:53<05:57,  1.25it/s]

 48%|████▊     | 414/861 [05:54<05:35,  1.33it/s]

 48%|████▊     | 415/861 [05:54<04:51,  1.53it/s]

 48%|████▊     | 416/861 [05:55<04:42,  1.58it/s]

 48%|████▊     | 417/861 [05:55<04:56,  1.50it/s]

 49%|████▊     | 418/861 [05:56<04:36,  1.60it/s]

 49%|████▊     | 419/861 [05:57<05:04,  1.45it/s]

 49%|████▉     | 420/861 [05:57<05:02,  1.46it/s]

 49%|████▉     | 421/861 [05:58<04:33,  1.61it/s]

 49%|████▉     | 422/861 [05:58<03:53,  1.88it/s]

 49%|████▉     | 423/861 [05:59<04:34,  1.60it/s]

 49%|████▉     | 424/861 [06:00<04:28,  1.63it/s]

 49%|████▉     | 425/861 [06:00<04:38,  1.57it/s]

 49%|████▉     | 426/861 [06:01<05:40,  1.28it/s]

 50%|████▉     | 427/861 [06:02<05:55,  1.22it/s]

 50%|████▉     | 428/861 [06:03<05:28,  1.32it/s]

 50%|████▉     | 429/861 [06:04<05:28,  1.31it/s]

 50%|████▉     | 430/861 [06:05<06:29,  1.11it/s]

 50%|█████     | 431/861 [06:06<07:44,  1.08s/it]

 50%|█████     | 432/861 [06:08<08:33,  1.20s/it]

 50%|█████     | 433/861 [06:09<08:30,  1.19s/it]

 50%|█████     | 434/861 [06:10<06:57,  1.02it/s]

 51%|█████     | 435/861 [06:10<05:15,  1.35it/s]

 51%|█████     | 436/861 [06:10<04:18,  1.65it/s]

 51%|█████     | 437/861 [06:11<04:06,  1.72it/s]

 51%|█████     | 438/861 [06:11<03:33,  1.98it/s]

 51%|█████     | 439/861 [06:12<03:50,  1.83it/s]

 51%|█████     | 440/861 [06:12<03:17,  2.13it/s]

 51%|█████     | 441/861 [06:12<02:49,  2.48it/s]

 51%|█████▏    | 442/861 [06:13<03:09,  2.21it/s]

 51%|█████▏    | 443/861 [06:13<03:21,  2.07it/s]

 52%|█████▏    | 444/861 [06:14<03:14,  2.14it/s]

 52%|█████▏    | 445/861 [06:14<02:56,  2.36it/s]

 52%|█████▏    | 446/861 [06:14<02:55,  2.37it/s]

 52%|█████▏    | 447/861 [06:15<04:15,  1.62it/s]

 52%|█████▏    | 448/861 [06:16<04:31,  1.52it/s]

 52%|█████▏    | 449/861 [06:17<04:39,  1.47it/s]

 52%|█████▏    | 450/861 [06:18<05:21,  1.28it/s]

 52%|█████▏    | 451/861 [06:19<05:04,  1.35it/s]

 52%|█████▏    | 452/861 [06:19<04:50,  1.41it/s]

 53%|█████▎    | 453/861 [06:20<04:19,  1.57it/s]

 53%|█████▎    | 454/861 [06:20<04:08,  1.64it/s]

 53%|█████▎    | 455/861 [06:21<03:37,  1.87it/s]

 53%|█████▎    | 456/861 [06:21<03:42,  1.82it/s]

 53%|█████▎    | 457/861 [06:22<03:48,  1.77it/s]

 53%|█████▎    | 458/861 [06:23<04:21,  1.54it/s]

 53%|█████▎    | 459/861 [06:23<03:41,  1.82it/s]

 53%|█████▎    | 460/861 [06:24<04:03,  1.65it/s]

 54%|█████▎    | 461/861 [06:25<04:54,  1.36it/s]

 54%|█████▎    | 462/861 [06:25<04:26,  1.49it/s]

 54%|█████▍    | 463/861 [06:26<04:04,  1.63it/s]

 54%|█████▍    | 464/861 [06:26<03:37,  1.83it/s]

 54%|█████▍    | 465/861 [06:26<02:57,  2.23it/s]

 54%|█████▍    | 466/861 [06:27<03:08,  2.10it/s]

 54%|█████▍    | 467/861 [06:28<04:13,  1.55it/s]

 54%|█████▍    | 468/861 [06:28<03:32,  1.85it/s]

 54%|█████▍    | 469/861 [06:29<03:30,  1.86it/s]

 55%|█████▍    | 470/861 [06:29<03:00,  2.17it/s]

 55%|█████▍    | 471/861 [06:30<03:03,  2.12it/s]

 55%|█████▍    | 472/861 [06:30<02:58,  2.18it/s]

 55%|█████▍    | 473/861 [06:30<02:40,  2.42it/s]

 55%|█████▌    | 474/861 [06:31<02:20,  2.75it/s]

 55%|█████▌    | 475/861 [06:31<02:35,  2.48it/s]

 55%|█████▌    | 476/861 [06:31<02:28,  2.58it/s]

 55%|█████▌    | 477/861 [06:32<02:55,  2.19it/s]

 56%|█████▌    | 478/861 [06:32<02:54,  2.19it/s]

 56%|█████▌    | 479/861 [06:33<02:27,  2.59it/s]

 56%|█████▌    | 480/861 [06:33<02:57,  2.14it/s]

 56%|█████▌    | 481/861 [06:34<02:44,  2.31it/s]

 56%|█████▌    | 482/861 [06:34<02:29,  2.54it/s]

 56%|█████▌    | 483/861 [06:34<02:16,  2.78it/s]

 56%|█████▌    | 484/861 [06:35<02:20,  2.69it/s]

 56%|█████▋    | 485/861 [06:35<02:12,  2.84it/s]

 56%|█████▋    | 486/861 [06:35<01:58,  3.16it/s]

 57%|█████▋    | 487/861 [06:36<02:35,  2.40it/s]

 57%|█████▋    | 488/861 [06:36<02:15,  2.76it/s]

 57%|█████▋    | 489/861 [06:36<02:16,  2.72it/s]

 57%|█████▋    | 490/861 [06:37<02:05,  2.96it/s]

 57%|█████▋    | 491/861 [06:37<02:09,  2.86it/s]

 57%|█████▋    | 492/861 [06:37<02:08,  2.86it/s]

 57%|█████▋    | 493/861 [06:38<02:27,  2.50it/s]

 57%|█████▋    | 494/861 [06:38<02:13,  2.75it/s]

 57%|█████▋    | 495/861 [06:39<03:11,  1.92it/s]

 58%|█████▊    | 496/861 [06:40<03:45,  1.62it/s]

 58%|█████▊    | 497/861 [06:40<02:59,  2.03it/s]

 58%|█████▊    | 498/861 [06:41<02:49,  2.14it/s]

 58%|█████▊    | 499/861 [06:41<02:27,  2.45it/s]

 58%|█████▊    | 500/861 [06:41<02:39,  2.26it/s]

 58%|█████▊    | 501/861 [06:42<02:16,  2.64it/s]

 58%|█████▊    | 502/861 [06:42<02:41,  2.23it/s]

 58%|█████▊    | 503/861 [06:43<02:38,  2.26it/s]

 59%|█████▊    | 504/861 [06:43<02:41,  2.21it/s]

 59%|█████▊    | 505/861 [06:43<02:22,  2.49it/s]

 59%|█████▉    | 506/861 [06:44<02:09,  2.74it/s]

 59%|█████▉    | 507/861 [06:44<01:57,  3.01it/s]

 59%|█████▉    | 508/861 [06:45<03:05,  1.91it/s]

 59%|█████▉    | 509/861 [06:46<03:54,  1.50it/s]

 59%|█████▉    | 510/861 [06:46<03:29,  1.68it/s]

 59%|█████▉    | 511/861 [06:47<03:26,  1.69it/s]

 59%|█████▉    | 512/861 [06:47<03:10,  1.83it/s]

 60%|█████▉    | 513/861 [06:48<03:08,  1.85it/s]

 60%|█████▉    | 514/861 [06:48<02:59,  1.93it/s]

 60%|█████▉    | 515/861 [06:49<02:23,  2.41it/s]

 60%|█████▉    | 516/861 [06:49<02:01,  2.83it/s]

 60%|██████    | 517/861 [06:49<01:52,  3.06it/s]

 60%|██████    | 518/861 [06:50<02:12,  2.60it/s]

 60%|██████    | 519/861 [06:50<02:50,  2.01it/s]

 60%|██████    | 520/861 [06:51<03:08,  1.81it/s]

 61%|██████    | 521/861 [06:51<02:41,  2.10it/s]

 61%|██████    | 522/861 [06:52<03:06,  1.81it/s]

 61%|██████    | 523/861 [06:53<03:50,  1.47it/s]

 61%|██████    | 524/861 [06:54<04:30,  1.25it/s]

 61%|██████    | 525/861 [06:54<03:50,  1.46it/s]

 61%|██████    | 526/861 [06:55<03:43,  1.50it/s]

 61%|██████    | 527/861 [06:56<03:47,  1.47it/s]

 61%|██████▏   | 528/861 [06:57<04:20,  1.28it/s]

 61%|██████▏   | 529/861 [06:57<03:37,  1.52it/s]

 62%|██████▏   | 530/861 [06:58<03:07,  1.77it/s]

 62%|██████▏   | 531/861 [06:58<02:53,  1.90it/s]

 62%|██████▏   | 532/861 [06:59<03:02,  1.80it/s]

 62%|██████▏   | 533/861 [06:59<02:46,  1.97it/s]

 62%|██████▏   | 534/861 [07:00<02:53,  1.89it/s]

 62%|██████▏   | 535/861 [07:00<02:53,  1.88it/s]

 62%|██████▏   | 536/861 [07:01<03:05,  1.75it/s]

 62%|██████▏   | 537/861 [07:02<04:07,  1.31it/s]

 62%|██████▏   | 538/861 [07:02<03:30,  1.53it/s]

 63%|██████▎   | 539/861 [07:04<04:53,  1.10it/s]

 63%|██████▎   | 540/861 [07:05<04:55,  1.09it/s]

 63%|██████▎   | 541/861 [07:05<04:09,  1.28it/s]

 63%|██████▎   | 542/861 [07:06<03:19,  1.60it/s]

 63%|██████▎   | 543/861 [07:06<03:38,  1.46it/s]

 63%|██████▎   | 544/861 [07:07<03:24,  1.55it/s]

 63%|██████▎   | 545/861 [07:08<03:57,  1.33it/s]

 63%|██████▎   | 546/861 [07:09<04:30,  1.17it/s]

 64%|██████▎   | 547/861 [07:10<04:08,  1.26it/s]

 64%|██████▎   | 548/861 [07:11<05:00,  1.04it/s]

 64%|██████▍   | 549/861 [07:12<04:57,  1.05it/s]

 64%|██████▍   | 550/861 [07:13<04:35,  1.13it/s]

 64%|██████▍   | 551/861 [07:13<04:14,  1.22it/s]

 64%|██████▍   | 552/861 [07:14<04:23,  1.17it/s]

 64%|██████▍   | 553/861 [07:15<04:44,  1.08it/s]

 64%|██████▍   | 554/861 [07:17<05:17,  1.03s/it]

 64%|██████▍   | 555/861 [07:18<05:56,  1.17s/it]

 65%|██████▍   | 556/861 [07:19<06:04,  1.19s/it]

 65%|██████▍   | 557/861 [07:21<06:35,  1.30s/it]

 65%|██████▍   | 558/861 [07:22<05:50,  1.16s/it]

 65%|██████▍   | 559/861 [07:23<05:55,  1.18s/it]

 65%|██████▌   | 560/861 [07:24<06:03,  1.21s/it]

 65%|██████▌   | 561/861 [07:25<06:00,  1.20s/it]

 65%|██████▌   | 562/861 [07:26<05:37,  1.13s/it]

 65%|██████▌   | 563/861 [07:27<05:28,  1.10s/it]

 66%|██████▌   | 564/861 [07:28<05:18,  1.07s/it]

 66%|██████▌   | 565/861 [07:29<04:58,  1.01s/it]

 66%|██████▌   | 566/861 [07:31<05:30,  1.12s/it]

 66%|██████▌   | 567/861 [07:32<05:42,  1.16s/it]

 66%|██████▌   | 568/861 [07:33<05:45,  1.18s/it]

 66%|██████▌   | 569/861 [07:34<05:20,  1.10s/it]

 66%|██████▌   | 570/861 [07:35<04:48,  1.01it/s]

 66%|██████▋   | 571/861 [07:36<05:22,  1.11s/it]

 66%|██████▋   | 572/861 [07:37<05:24,  1.12s/it]

 67%|██████▋   | 573/861 [07:38<04:43,  1.02it/s]

 67%|██████▋   | 574/861 [07:39<05:03,  1.06s/it]

 67%|██████▋   | 575/861 [07:40<05:02,  1.06s/it]

 67%|██████▋   | 576/861 [07:42<06:06,  1.29s/it]

 67%|██████▋   | 577/861 [07:43<05:33,  1.18s/it]

 67%|██████▋   | 578/861 [07:45<05:57,  1.26s/it]

 67%|██████▋   | 579/861 [07:46<06:39,  1.42s/it]

 67%|██████▋   | 580/861 [07:47<06:15,  1.34s/it]

 67%|██████▋   | 581/861 [07:48<05:39,  1.21s/it]

 68%|██████▊   | 582/861 [07:51<07:12,  1.55s/it]

 68%|██████▊   | 583/861 [07:52<06:32,  1.41s/it]

 68%|██████▊   | 584/861 [07:53<06:01,  1.31s/it]

 68%|██████▊   | 585/861 [07:54<05:15,  1.14s/it]

 68%|██████▊   | 586/861 [07:54<04:31,  1.01it/s]

 68%|██████▊   | 587/861 [07:56<04:53,  1.07s/it]

 68%|██████▊   | 588/861 [07:56<04:39,  1.03s/it]

 68%|██████▊   | 589/861 [07:57<04:19,  1.05it/s]

 69%|██████▊   | 590/861 [07:59<05:06,  1.13s/it]

 69%|██████▊   | 591/861 [07:59<04:25,  1.02it/s]

 69%|██████▉   | 592/861 [08:00<04:25,  1.01it/s]

 69%|██████▉   | 593/861 [08:02<04:53,  1.09s/it]

 69%|██████▉   | 594/861 [08:03<05:07,  1.15s/it]

 69%|██████▉   | 595/861 [08:04<04:23,  1.01it/s]

 69%|██████▉   | 596/861 [08:04<03:37,  1.22it/s]

 69%|██████▉   | 597/861 [08:05<03:19,  1.33it/s]

 69%|██████▉   | 598/861 [08:05<03:08,  1.39it/s]

 70%|██████▉   | 599/861 [08:06<03:20,  1.31it/s]

 70%|██████▉   | 600/861 [08:07<03:14,  1.34it/s]

 70%|██████▉   | 601/861 [08:08<03:20,  1.29it/s]

 70%|██████▉   | 602/861 [08:09<04:30,  1.04s/it]

 70%|███████   | 603/861 [08:11<04:59,  1.16s/it]

 70%|███████   | 604/861 [08:12<04:46,  1.11s/it]

 70%|███████   | 605/861 [08:12<03:57,  1.08it/s]

 70%|███████   | 606/861 [08:13<03:55,  1.08it/s]

 70%|███████   | 607/861 [08:14<03:30,  1.21it/s]

 71%|███████   | 608/861 [08:14<03:11,  1.32it/s]

 71%|███████   | 609/861 [08:15<03:23,  1.24it/s]

 71%|███████   | 610/861 [08:17<04:11,  1.00s/it]

 71%|███████   | 611/861 [08:18<04:15,  1.02s/it]

 71%|███████   | 612/861 [08:19<04:01,  1.03it/s]

 71%|███████   | 613/861 [08:19<03:26,  1.20it/s]

 71%|███████▏  | 614/861 [08:20<03:53,  1.06it/s]

 71%|███████▏  | 615/861 [08:22<04:20,  1.06s/it]

 72%|███████▏  | 616/861 [08:24<05:35,  1.37s/it]

 72%|███████▏  | 617/861 [08:25<05:35,  1.37s/it]

 72%|███████▏  | 618/861 [08:26<05:13,  1.29s/it]

 72%|███████▏  | 619/861 [08:27<04:39,  1.15s/it]

 72%|███████▏  | 620/861 [08:29<05:11,  1.29s/it]

 72%|███████▏  | 621/861 [08:30<04:47,  1.20s/it]

 72%|███████▏  | 622/861 [08:30<03:56,  1.01it/s]

 72%|███████▏  | 623/861 [08:32<05:10,  1.31s/it]

 72%|███████▏  | 624/861 [08:33<04:23,  1.11s/it]

 73%|███████▎  | 625/861 [08:34<03:40,  1.07it/s]

 73%|███████▎  | 626/861 [08:34<03:30,  1.12it/s]

 73%|███████▎  | 627/861 [08:35<03:26,  1.13it/s]

 73%|███████▎  | 628/861 [08:36<03:45,  1.03it/s]

 73%|███████▎  | 629/861 [08:37<03:48,  1.02it/s]

 73%|███████▎  | 630/861 [08:38<03:21,  1.15it/s]

 73%|███████▎  | 631/861 [08:38<02:42,  1.42it/s]

 73%|███████▎  | 632/861 [08:40<03:51,  1.01s/it]

 74%|███████▎  | 633/861 [08:41<03:35,  1.06it/s]

 74%|███████▎  | 634/861 [08:42<04:21,  1.15s/it]

 74%|███████▍  | 635/861 [08:44<04:31,  1.20s/it]

 74%|███████▍  | 636/861 [08:45<04:03,  1.08s/it]

 74%|███████▍  | 637/861 [08:45<03:42,  1.00it/s]

 74%|███████▍  | 638/861 [08:46<03:35,  1.04it/s]

 74%|███████▍  | 639/861 [08:47<03:23,  1.09it/s]

 74%|███████▍  | 640/861 [08:48<03:04,  1.20it/s]

 74%|███████▍  | 641/861 [08:48<03:00,  1.22it/s]

 75%|███████▍  | 642/861 [08:50<03:30,  1.04it/s]

 75%|███████▍  | 643/861 [08:51<03:30,  1.04it/s]

 75%|███████▍  | 644/861 [08:52<03:34,  1.01it/s]

 75%|███████▍  | 645/861 [08:52<02:48,  1.28it/s]

 75%|███████▌  | 646/861 [08:53<02:36,  1.37it/s]

 75%|███████▌  | 647/861 [08:53<02:24,  1.48it/s]

 75%|███████▌  | 648/861 [08:54<02:44,  1.29it/s]

 75%|███████▌  | 649/861 [08:55<02:33,  1.38it/s]

 75%|███████▌  | 650/861 [08:55<02:14,  1.57it/s]

 76%|███████▌  | 651/861 [08:56<01:56,  1.80it/s]

 76%|███████▌  | 652/861 [08:57<02:18,  1.51it/s]

 76%|███████▌  | 653/861 [08:57<02:05,  1.66it/s]

 76%|███████▌  | 654/861 [08:58<02:06,  1.63it/s]

 76%|███████▌  | 655/861 [08:58<01:48,  1.90it/s]

 76%|███████▌  | 656/861 [08:58<01:37,  2.10it/s]

 76%|███████▋  | 657/861 [08:59<01:35,  2.14it/s]

 76%|███████▋  | 658/861 [09:00<02:09,  1.57it/s]

 77%|███████▋  | 659/861 [09:00<02:09,  1.56it/s]

 77%|███████▋  | 660/861 [09:01<02:11,  1.53it/s]

 77%|███████▋  | 661/861 [09:02<01:55,  1.73it/s]

 77%|███████▋  | 662/861 [09:02<02:10,  1.52it/s]

 77%|███████▋  | 663/861 [09:04<03:32,  1.07s/it]

 77%|███████▋  | 664/861 [09:05<02:57,  1.11it/s]

 77%|███████▋  | 665/861 [09:05<02:24,  1.35it/s]

 77%|███████▋  | 666/861 [09:06<01:57,  1.66it/s]

 77%|███████▋  | 667/861 [09:06<02:07,  1.53it/s]

 78%|███████▊  | 668/861 [09:07<01:56,  1.65it/s]

 78%|███████▊  | 669/861 [09:07<01:39,  1.92it/s]

 78%|███████▊  | 670/861 [09:08<01:46,  1.80it/s]

 78%|███████▊  | 671/861 [09:08<01:28,  2.14it/s]

 78%|███████▊  | 672/861 [09:09<02:21,  1.34it/s]

 78%|███████▊  | 673/861 [09:10<02:10,  1.44it/s]

 78%|███████▊  | 674/861 [09:10<01:45,  1.77it/s]

 78%|███████▊  | 675/861 [09:11<02:12,  1.41it/s]

 79%|███████▊  | 676/861 [09:12<01:55,  1.60it/s]

 79%|███████▊  | 677/861 [09:12<01:44,  1.75it/s]

 79%|███████▊  | 678/861 [09:13<01:36,  1.90it/s]

 79%|███████▉  | 679/861 [09:13<01:23,  2.18it/s]

 79%|███████▉  | 680/861 [09:13<01:11,  2.52it/s]

 79%|███████▉  | 681/861 [09:14<01:12,  2.50it/s]

 79%|███████▉  | 682/861 [09:14<01:26,  2.07it/s]

 79%|███████▉  | 683/861 [09:15<01:31,  1.95it/s]

 79%|███████▉  | 684/861 [09:16<01:45,  1.69it/s]

 80%|███████▉  | 685/861 [09:16<01:44,  1.68it/s]

 80%|███████▉  | 686/861 [09:17<01:35,  1.83it/s]

 80%|███████▉  | 687/861 [09:18<02:39,  1.09it/s]

 80%|███████▉  | 688/861 [09:19<02:09,  1.34it/s]

 80%|████████  | 689/861 [09:20<02:06,  1.36it/s]

 80%|████████  | 690/861 [09:20<01:51,  1.54it/s]

 80%|████████  | 691/861 [09:21<01:44,  1.62it/s]

 80%|████████  | 692/861 [09:21<01:33,  1.81it/s]

 80%|████████  | 693/861 [09:22<01:44,  1.61it/s]

 81%|████████  | 694/861 [09:22<01:28,  1.88it/s]

 81%|████████  | 695/861 [09:23<01:27,  1.89it/s]

 81%|████████  | 696/861 [09:23<01:13,  2.25it/s]

 81%|████████  | 697/861 [09:23<01:19,  2.07it/s]

 81%|████████  | 698/861 [09:24<01:34,  1.72it/s]

 81%|████████  | 699/861 [09:25<01:40,  1.62it/s]

 81%|████████▏ | 700/861 [09:26<01:41,  1.59it/s]

 81%|████████▏ | 701/861 [09:26<01:54,  1.40it/s]

 82%|████████▏ | 702/861 [09:27<01:58,  1.34it/s]

 82%|████████▏ | 703/861 [09:28<01:38,  1.60it/s]

 82%|████████▏ | 704/861 [09:28<01:32,  1.69it/s]

 82%|████████▏ | 705/861 [09:29<01:21,  1.91it/s]

 82%|████████▏ | 706/861 [09:29<01:18,  1.99it/s]

 82%|████████▏ | 707/861 [09:29<01:10,  2.17it/s]

 82%|████████▏ | 708/861 [09:30<01:02,  2.43it/s]

 82%|████████▏ | 709/861 [09:30<01:00,  2.51it/s]

 82%|████████▏ | 710/861 [09:31<01:35,  1.58it/s]

 83%|████████▎ | 711/861 [09:32<01:28,  1.70it/s]

 83%|████████▎ | 712/861 [09:32<01:17,  1.92it/s]

 83%|████████▎ | 713/861 [09:32<01:06,  2.22it/s]

 83%|████████▎ | 714/861 [09:33<01:18,  1.88it/s]

 83%|████████▎ | 715/861 [09:34<01:43,  1.41it/s]

 83%|████████▎ | 716/861 [09:35<01:54,  1.27it/s]

 83%|████████▎ | 717/861 [09:36<01:43,  1.39it/s]

 83%|████████▎ | 718/861 [09:37<02:02,  1.17it/s]

 84%|████████▎ | 719/861 [09:37<01:50,  1.29it/s]

 84%|████████▎ | 720/861 [09:38<01:34,  1.48it/s]

 84%|████████▎ | 721/861 [09:38<01:27,  1.61it/s]

 84%|████████▍ | 722/861 [09:39<01:26,  1.60it/s]

 84%|████████▍ | 723/861 [09:39<01:15,  1.82it/s]

 84%|████████▍ | 724/861 [09:40<01:12,  1.89it/s]

 84%|████████▍ | 725/861 [09:40<01:12,  1.87it/s]

 84%|████████▍ | 726/861 [09:41<01:24,  1.60it/s]

 84%|████████▍ | 727/861 [09:43<01:53,  1.18it/s]

 85%|████████▍ | 728/861 [09:44<01:55,  1.15it/s]

 85%|████████▍ | 729/861 [09:44<01:39,  1.33it/s]

 85%|████████▍ | 730/861 [09:44<01:24,  1.54it/s]

 85%|████████▍ | 731/861 [09:46<02:13,  1.02s/it]

 85%|████████▌ | 732/861 [09:47<01:45,  1.22it/s]

 85%|████████▌ | 733/861 [09:47<01:37,  1.31it/s]

 85%|████████▌ | 734/861 [09:48<01:16,  1.66it/s]

 85%|████████▌ | 735/861 [09:48<01:10,  1.78it/s]

 85%|████████▌ | 736/861 [09:49<01:12,  1.73it/s]

 86%|████████▌ | 737/861 [09:49<01:12,  1.71it/s]

 86%|████████▌ | 738/861 [09:50<01:08,  1.80it/s]

 86%|████████▌ | 739/861 [09:50<01:01,  1.97it/s]

 86%|████████▌ | 740/861 [09:51<01:05,  1.84it/s]

 86%|████████▌ | 741/861 [09:51<01:03,  1.88it/s]

 86%|████████▌ | 742/861 [09:52<01:16,  1.56it/s]

 86%|████████▋ | 743/861 [09:53<01:10,  1.67it/s]

 86%|████████▋ | 744/861 [09:53<01:02,  1.86it/s]

 87%|████████▋ | 745/861 [09:54<01:18,  1.48it/s]

 87%|████████▋ | 746/861 [09:54<01:03,  1.82it/s]

 87%|████████▋ | 747/861 [09:55<01:23,  1.36it/s]

 87%|████████▋ | 748/861 [09:56<01:15,  1.50it/s]

 87%|████████▋ | 749/861 [09:57<01:25,  1.31it/s]

 87%|████████▋ | 750/861 [09:57<01:06,  1.67it/s]

 87%|████████▋ | 751/861 [09:57<00:54,  2.02it/s]

 87%|████████▋ | 752/861 [09:59<01:15,  1.45it/s]

 87%|████████▋ | 753/861 [09:59<01:15,  1.42it/s]

 88%|████████▊ | 754/861 [10:00<01:06,  1.62it/s]

 88%|████████▊ | 755/861 [10:00<01:00,  1.76it/s]

 88%|████████▊ | 756/861 [10:01<00:53,  1.97it/s]

 88%|████████▊ | 757/861 [10:01<01:04,  1.61it/s]

 88%|████████▊ | 758/861 [10:02<01:04,  1.59it/s]

 88%|████████▊ | 759/861 [10:03<01:00,  1.67it/s]

 88%|████████▊ | 760/861 [10:03<01:06,  1.51it/s]

 88%|████████▊ | 761/861 [10:05<01:31,  1.10it/s]

 89%|████████▊ | 762/861 [10:05<01:15,  1.32it/s]

 89%|████████▊ | 763/861 [10:06<01:06,  1.48it/s]

 89%|████████▊ | 764/861 [10:07<01:09,  1.40it/s]

 89%|████████▉ | 765/861 [10:07<01:11,  1.35it/s]

 89%|████████▉ | 766/861 [10:08<01:03,  1.49it/s]

 89%|████████▉ | 767/861 [10:09<01:16,  1.23it/s]

 89%|████████▉ | 768/861 [10:10<01:11,  1.29it/s]

 89%|████████▉ | 769/861 [10:11<01:17,  1.18it/s]

 89%|████████▉ | 770/861 [10:11<01:04,  1.41it/s]

 90%|████████▉ | 771/861 [10:12<00:57,  1.57it/s]

 90%|████████▉ | 772/861 [10:12<00:54,  1.63it/s]

 90%|████████▉ | 773/861 [10:13<01:02,  1.40it/s]

 90%|████████▉ | 774/861 [10:14<00:54,  1.59it/s]

 90%|█████████ | 775/861 [10:15<01:05,  1.31it/s]

 90%|█████████ | 776/861 [10:15<01:07,  1.27it/s]

 90%|█████████ | 777/861 [10:16<01:04,  1.29it/s]

 90%|█████████ | 778/861 [10:17<01:06,  1.25it/s]

 90%|█████████ | 779/861 [10:18<01:10,  1.16it/s]

 91%|█████████ | 780/861 [10:20<01:35,  1.18s/it]

 91%|█████████ | 781/861 [10:22<02:06,  1.58s/it]

 91%|█████████ | 782/861 [10:24<02:00,  1.53s/it]

 91%|█████████ | 783/861 [10:25<01:38,  1.26s/it]

 91%|█████████ | 784/861 [10:25<01:25,  1.11s/it]

 91%|█████████ | 785/861 [10:26<01:16,  1.01s/it]

 91%|█████████▏| 786/861 [10:27<01:10,  1.07it/s]

 91%|█████████▏| 787/861 [10:27<01:00,  1.23it/s]

 92%|█████████▏| 788/861 [10:28<00:56,  1.29it/s]

 92%|█████████▏| 789/861 [10:29<00:56,  1.26it/s]

 92%|█████████▏| 790/861 [10:30<00:55,  1.29it/s]

 92%|█████████▏| 791/861 [10:30<00:47,  1.47it/s]

 92%|█████████▏| 792/861 [10:31<00:46,  1.48it/s]

 92%|█████████▏| 793/861 [10:31<00:45,  1.50it/s]

 92%|█████████▏| 794/861 [10:32<00:42,  1.59it/s]

 92%|█████████▏| 795/861 [10:33<00:43,  1.50it/s]

 92%|█████████▏| 796/861 [10:33<00:36,  1.76it/s]

 93%|█████████▎| 797/861 [10:34<00:40,  1.59it/s]

 93%|█████████▎| 798/861 [10:34<00:34,  1.83it/s]

 93%|█████████▎| 799/861 [10:35<00:32,  1.89it/s]

 93%|█████████▎| 800/861 [10:35<00:35,  1.73it/s]

 93%|█████████▎| 801/861 [10:37<00:49,  1.22it/s]

 93%|█████████▎| 802/861 [10:37<00:41,  1.41it/s]

 93%|█████████▎| 803/861 [10:38<00:50,  1.16it/s]

 93%|█████████▎| 804/861 [10:40<00:58,  1.03s/it]

 93%|█████████▎| 805/861 [10:41<01:01,  1.09s/it]

 94%|█████████▎| 806/861 [10:41<00:48,  1.12it/s]

 94%|█████████▎| 807/861 [10:43<00:52,  1.03it/s]

 94%|█████████▍| 808/861 [10:44<00:58,  1.11s/it]

 94%|█████████▍| 809/861 [10:44<00:47,  1.10it/s]

 94%|█████████▍| 810/861 [10:45<00:39,  1.30it/s]

 94%|█████████▍| 811/861 [10:46<00:38,  1.29it/s]

 94%|█████████▍| 812/861 [10:46<00:35,  1.40it/s]

 94%|█████████▍| 813/861 [10:47<00:37,  1.27it/s]

 95%|█████████▍| 814/861 [10:48<00:40,  1.15it/s]

 95%|█████████▍| 815/861 [10:49<00:40,  1.12it/s]

 95%|█████████▍| 816/861 [10:50<00:36,  1.23it/s]

 95%|█████████▍| 817/861 [10:51<00:36,  1.20it/s]

 95%|█████████▌| 818/861 [10:52<00:38,  1.12it/s]

 95%|█████████▌| 819/861 [10:52<00:34,  1.23it/s]

 95%|█████████▌| 820/861 [10:53<00:35,  1.15it/s]

 95%|█████████▌| 821/861 [10:55<00:37,  1.07it/s]

 95%|█████████▌| 822/861 [10:56<00:38,  1.00it/s]

 96%|█████████▌| 823/861 [10:58<00:47,  1.26s/it]

 96%|█████████▌| 824/861 [10:58<00:37,  1.02s/it]

 96%|█████████▌| 825/861 [10:59<00:31,  1.13it/s]

 96%|█████████▌| 826/861 [11:00<00:39,  1.12s/it]

 96%|█████████▌| 827/861 [11:01<00:37,  1.09s/it]

 96%|█████████▌| 828/861 [11:02<00:28,  1.16it/s]

 96%|█████████▋| 829/861 [11:03<00:31,  1.01it/s]

 96%|█████████▋| 830/861 [11:04<00:31,  1.01s/it]

 97%|█████████▋| 831/861 [11:05<00:35,  1.18s/it]

 97%|█████████▋| 832/861 [11:06<00:29,  1.03s/it]

 97%|█████████▋| 833/861 [11:07<00:24,  1.13it/s]

 97%|█████████▋| 834/861 [11:08<00:24,  1.11it/s]

 97%|█████████▋| 835/861 [11:08<00:22,  1.14it/s]

 97%|█████████▋| 836/861 [11:09<00:21,  1.17it/s]

 97%|█████████▋| 837/861 [11:11<00:23,  1.03it/s]

 97%|█████████▋| 838/861 [11:12<00:23,  1.03s/it]

 97%|█████████▋| 839/861 [11:12<00:19,  1.12it/s]

 98%|█████████▊| 840/861 [11:13<00:15,  1.32it/s]

 98%|█████████▊| 841/861 [11:13<00:14,  1.37it/s]

 98%|█████████▊| 842/861 [11:14<00:13,  1.46it/s]

 98%|█████████▊| 843/861 [11:15<00:12,  1.46it/s]

 98%|█████████▊| 844/861 [11:15<00:11,  1.53it/s]

 98%|█████████▊| 845/861 [11:16<00:13,  1.23it/s]

 98%|█████████▊| 846/861 [11:17<00:10,  1.41it/s]

 98%|█████████▊| 847/861 [11:18<00:10,  1.29it/s]

 98%|█████████▊| 848/861 [11:19<00:11,  1.18it/s]

 99%|█████████▊| 849/861 [11:20<00:10,  1.11it/s]

 99%|█████████▊| 850/861 [11:20<00:08,  1.24it/s]

 99%|█████████▉| 851/861 [11:21<00:07,  1.32it/s]

 99%|█████████▉| 852/861 [11:22<00:06,  1.42it/s]

 99%|█████████▉| 853/861 [11:22<00:05,  1.47it/s]

 99%|█████████▉| 854/861 [11:23<00:04,  1.55it/s]

 99%|█████████▉| 855/861 [11:24<00:04,  1.34it/s]

 99%|█████████▉| 856/861 [11:25<00:04,  1.05it/s]

100%|█████████▉| 857/861 [11:26<00:03,  1.04it/s]

100%|█████████▉| 858/861 [11:27<00:02,  1.20it/s]

100%|█████████▉| 859/861 [11:28<00:01,  1.24it/s]

100%|█████████▉| 860/861 [11:29<00:01,  1.06s/it]

100%|██████████| 861/861 [11:30<00:00,  1.01it/s]{'score': 13.576419919185327, 'counts': [17863, 8397, 4341, 2204], 'totals': [47959, 46237, 44515, 42793], 'precisions': [37.24639796492838, 18.16078032744339, 9.751769066606762, 5.1503750613418084], 'bp': 1.0, 'sys_len': 47959, 'ref_len': 32555}

                                                         

                                                 
{'eval_loss': 2.4080686569213867, 'eval_bleu': 13.5764, 'eval_gen_len': 36.1492, 'eval_runtime': 787.1528, 'eval_samples_per_second': 2.188, 'eval_steps_per_second': 1.094, 'epoch': 15.0}

 94%|█████████▍| 58037/61904 [6:51:30<1:29:09,  1.38s/it]

100%|██████████| 861/861 [13:06<00:00,  1.01it/s]

                                                 [WARNING|configuration_utils.py:448] 2024-10-28 22:17:10,319 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()

 94%|█████████▍| 58038/61904 [6:51:58<263:42:12, 245.56s/it]
 94%|█████████▍| 58039/61904 [6:52:00<185:05:43, 172.40s/it]
 94%|█████████▍| 58040/61904 [6:52:01<130:00:51, 121.13s/it]
                                                            
{'loss': 2.3623, 'learning_rate': 1.0626215480357839e-07, 'epoch': 15.0}

 94%|█████████▍| 58040/61904 [6:52:01<130:00:51, 121.13s/it]
 94%|█████████▍| 58041/61904 [6:52:03<91:25:26, 85.20s/it]  
 94%|█████████▍| 58042/61904 [6:52:04<64:27:30, 60.09s/it]
 94%|█████████▍| 58043/61904 [6:52:05<45:33:52, 42.48s/it]
 94%|█████████▍| 58044/61904 [6:52:07<32:17:39, 30.12s/it]
 94%|█████████▍| 58045/61904 [6:52:08<23:05:40, 21.54s/it]
 94%|█████████▍| 58046/61904 [6:52:10<16:35:55, 15.49s/it]
 94%|█████████▍| 58047/61904 [6:52:11<12:05:57, 11.29s/it]
 94%|█████████▍| 58048/61904 [6:52:13<8:55:45,  8.34s/it] 
 94%|█████████▍| 58049/61904 [6:52:14<6:40:02,  6.23s/it]
 94%|█████████▍| 58050/61904 [6:52:15<5:07:04,  4.78s/it]
 94%|█████████▍| 58051/61904 [6:52:17<4:00:57,  3.75s/it]
 94%|█████████▍| 58052/61904 [6:52:18<3:17:53,  3.08s/it]
 94%|█████████▍| 58053/61904 [6:52:19<2:43:33,  2.55s/it]
 94%|█████████▍| 58054/61904 [6:52:21<2:23:37,  2.24s/it]
 94%|█████████▍| 58055/61904 [6:52:22<2:05:49,  1.96s/it]
 94%|█████████▍| 58056/61904 [6:52:24<1:57:00,  1.82s/it]
 94%|█████████▍| 58057/61904 [6:52:25<1:49:34,  1.71s/it]
 94%|█████████▍| 58058/61904 [6:52:27<1:47:06,  1.67s/it]
 94%|█████████▍| 58059/61904 [6:52:28<1:41:16,  1.58s/it]
 94%|█████████▍| 58060/61904 [6:52:30<1:37:57,  1.53s/it]
                                                         
{'loss': 2.4089, 'learning_rate': 1.0622974199403602e-07, 'epoch': 15.01}

 94%|█████████▍| 58060/61904 [6:52:30<1:37:57,  1.53s/it]
 94%|█████████▍| 58061/61904 [6:52:31<1:36:47,  1.51s/it]
 94%|█████████▍| 58062/61904 [6:52:33<1:36:46,  1.51s/it]
 94%|█████████▍| 58063/61904 [6:52:34<1:34:30,  1.48s/it]
 94%|█████████▍| 58064/61904 [6:52:35<1:31:46,  1.43s/it]
 94%|█████████▍| 58065/61904 [6:52:37<1:32:08,  1.44s/it]
 94%|█████████▍| 58066/61904 [6:52:38<1:30:39,  1.42s/it]
 94%|█████████▍| 58067/61904 [6:52:40<1:30:13,  1.41s/it]
 94%|█████████▍| 58068/61904 [6:52:41<1:30:02,  1.41s/it]
 94%|█████████▍| 58069/61904 [6:52:42<1:29:53,  1.41s/it]
 94%|█████████▍| 58070/61904 [6:52:44<1:27:39,  1.37s/it]
 94%|█████████▍| 58071/61904 [6:52:45<1:28:05,  1.38s/it]
 94%|█████████▍| 58072/61904 [6:52:46<1:28:15,  1.38s/it]
 94%|█████████▍| 58073/61904 [6:52:48<1:32:08,  1.44s/it]
 94%|█████████▍| 58074/61904 [6:52:50<1:34:27,  1.48s/it]
 94%|█████████▍| 58075/61904 [6:52:51<1:32:20,  1.45s/it]
 94%|█████████▍| 58076/61904 [6:52:52<1:31:03,  1.43s/it]
 94%|█████████▍| 58077/61904 [6:52:54<1:30:43,  1.42s/it]
 94%|█████████▍| 58078/61904 [6:52:55<1:32:26,  1.45s/it]
 94%|█████████▍| 58079/61904 [6:52:57<1:31:47,  1.44s/it]
 94%|█████████▍| 58080/61904 [6:52:58<1:33:14,  1.46s/it]
                                                         
{'loss': 2.5134, 'learning_rate': 1.0619732918449371e-07, 'epoch': 15.01}

 94%|█████████▍| 58080/61904 [6:52:58<1:33:14,  1.46s/it]
 94%|█████████▍| 58081/61904 [6:52:59<1:30:58,  1.43s/it]
 94%|█████████▍| 58082/61904 [6:53:01<1:31:26,  1.44s/it]
 94%|█████████▍| 58083/61904 [6:53:02<1:29:29,  1.41s/it]
 94%|█████████▍| 58084/61904 [6:53:04<1:32:36,  1.45s/it]
 94%|█████████▍| 58085/61904 [6:53:05<1:31:08,  1.43s/it]
 94%|█████████▍| 58086/61904 [6:53:07<1:31:40,  1.44s/it]
 94%|█████████▍| 58087/61904 [6:53:08<1:33:56,  1.48s/it]
 94%|█████████▍| 58088/61904 [6:53:10<1:36:58,  1.52s/it]
 94%|█████████▍| 58089/61904 [6:53:11<1:35:10,  1.50s/it]
 94%|█████████▍| 58090/61904 [6:53:13<1:35:07,  1.50s/it]
 94%|█████████▍| 58091/61904 [6:53:14<1:31:54,  1.45s/it]
 94%|█████████▍| 58092/61904 [6:53:16<1:31:36,  1.44s/it]
 94%|█████████▍| 58093/61904 [6:53:17<1:34:30,  1.49s/it]
 94%|█████████▍| 58094/61904 [6:53:19<1:36:05,  1.51s/it]
 94%|█████████▍| 58095/61904 [6:53:20<1:34:33,  1.49s/it]
 94%|█████████▍| 58096/61904 [6:53:22<1:31:53,  1.45s/it]
 94%|█████████▍| 58097/61904 [6:53:23<1:30:05,  1.42s/it]
 94%|█████████▍| 58098/61904 [6:53:24<1:29:31,  1.41s/it]
 94%|█████████▍| 58099/61904 [6:53:26<1:31:08,  1.44s/it]
 94%|█████████▍| 58100/61904 [6:53:27<1:28:36,  1.40s/it]
                                                         
{'loss': 2.4379, 'learning_rate': 1.0616491637495137e-07, 'epoch': 15.02}

 94%|█████████▍| 58100/61904 [6:53:27<1:28:36,  1.40s/it]
 94%|█████████▍| 58101/61904 [6:53:29<1:30:46,  1.43s/it]
 94%|█████████▍| 58102/61904 [6:53:30<1:33:15,  1.47s/it]
 94%|█████████▍| 58103/61904 [6:53:31<1:29:58,  1.42s/it]
 94%|█████████▍| 58104/61904 [6:53:33<1:31:09,  1.44s/it]
 94%|█████████▍| 58105/61904 [6:53:34<1:26:14,  1.36s/it]
 94%|█████████▍| 58106/61904 [6:53:36<1:28:20,  1.40s/it]
 94%|█████████▍| 58107/61904 [6:53:37<1:26:38,  1.37s/it]
 94%|█████████▍| 58108/61904 [6:53:39<1:33:07,  1.47s/it]
 94%|█████████▍| 58109/61904 [6:53:40<1:34:13,  1.49s/it]
 94%|█████████▍| 58110/61904 [6:53:42<1:32:19,  1.46s/it]
 94%|█████████▍| 58111/61904 [6:53:43<1:33:23,  1.48s/it]
 94%|█████████▍| 58112/61904 [6:53:45<1:38:26,  1.56s/it]
 94%|█████████▍| 58113/61904 [6:53:46<1:39:17,  1.57s/it]
 94%|█████████▍| 58114/61904 [6:53:48<1:37:03,  1.54s/it]
 94%|█████████▍| 58115/61904 [6:53:49<1:34:55,  1.50s/it]
 94%|█████████▍| 58116/61904 [6:53:51<1:33:54,  1.49s/it]
 94%|█████████▍| 58117/61904 [6:53:52<1:32:40,  1.47s/it]
 94%|█████████▍| 58118/61904 [6:53:54<1:31:42,  1.45s/it]
 94%|█████████▍| 58119/61904 [6:53:55<1:29:44,  1.42s/it]
 94%|█████████▍| 58120/61904 [6:53:56<1:29:01,  1.41s/it]
                                                         
{'loss': 2.4265, 'learning_rate': 1.0613250356540906e-07, 'epoch': 15.02}

 94%|█████████▍| 58120/61904 [6:53:56<1:29:01,  1.41s/it]
 94%|█████████▍| 58121/61904 [6:53:58<1:29:38,  1.42s/it]
 94%|█████████▍| 58122/61904 [6:53:59<1:29:53,  1.43s/it]
 94%|█████████▍| 58123/61904 [6:54:01<1:29:16,  1.42s/it]
 94%|█████████▍| 58124/61904 [6:54:02<1:29:07,  1.41s/it]
 94%|█████████▍| 58125/61904 [6:54:03<1:28:51,  1.41s/it]
 94%|█████████▍| 58126/61904 [6:54:05<1:28:48,  1.41s/it]
 94%|█████████▍| 58127/61904 [6:54:07<1:34:00,  1.49s/it]
 94%|█████████▍| 58128/61904 [6:54:08<1:34:40,  1.50s/it]
 94%|█████████▍| 58129/61904 [6:54:10<1:37:43,  1.55s/it]
 94%|█████████▍| 58130/61904 [6:54:11<1:35:00,  1.51s/it]
 94%|█████████▍| 58131/61904 [6:54:13<1:32:43,  1.47s/it]
 94%|█████████▍| 58132/61904 [6:54:14<1:30:49,  1.44s/it]
 94%|█████████▍| 58133/61904 [6:54:15<1:31:34,  1.46s/it]
 94%|█████████▍| 58134/61904 [6:54:17<1:30:37,  1.44s/it]
 94%|█████████▍| 58135/61904 [6:54:18<1:30:26,  1.44s/it]
 94%|█████████▍| 58136/61904 [6:54:20<1:31:49,  1.46s/it]
 94%|█████████▍| 58137/61904 [6:54:21<1:32:47,  1.48s/it]
 94%|█████████▍| 58138/61904 [6:54:23<1:31:51,  1.46s/it]
 94%|█████████▍| 58139/61904 [6:54:24<1:33:38,  1.49s/it]
 94%|█████████▍| 58140/61904 [6:54:26<1:30:37,  1.44s/it]
                                                         
{'loss': 2.438, 'learning_rate': 1.061000907558667e-07, 'epoch': 15.03}

 94%|█████████▍| 58140/61904 [6:54:26<1:30:37,  1.44s/it]
 94%|█████████▍| 58141/61904 [6:54:27<1:30:28,  1.44s/it]
 94%|█████████▍| 58142/61904 [6:54:28<1:30:51,  1.45s/it]
 94%|█████████▍| 58143/61904 [6:54:30<1:31:02,  1.45s/it]
 94%|█████████▍| 58144/61904 [6:54:31<1:31:46,  1.46s/it]
 94%|█████████▍| 58145/61904 [6:54:33<1:29:34,  1.43s/it]
 94%|█████████▍| 58146/61904 [6:54:34<1:26:23,  1.38s/it]
 94%|█████████▍| 58147/61904 [6:54:35<1:28:11,  1.41s/it]
 94%|█████████▍| 58148/61904 [6:54:37<1:28:44,  1.42s/it]
 94%|█████████▍| 58149/61904 [6:54:38<1:28:34,  1.42s/it]
 94%|█████████▍| 58150/61904 [6:54:40<1:30:00,  1.44s/it]
 94%|█████████▍| 58151/61904 [6:54:41<1:29:44,  1.43s/it]
 94%|█████████▍| 58152/61904 [6:54:43<1:30:09,  1.44s/it]
 94%|█████████▍| 58153/61904 [6:54:44<1:29:35,  1.43s/it]
 94%|█████████▍| 58154/61904 [6:54:45<1:28:12,  1.41s/it]
 94%|█████████▍| 58155/61904 [6:54:47<1:27:11,  1.40s/it]
 94%|█████████▍| 58156/61904 [6:54:48<1:28:37,  1.42s/it]
 94%|█████████▍| 58157/61904 [6:54:50<1:27:08,  1.40s/it]
 94%|█████████▍| 58158/61904 [6:54:51<1:29:58,  1.44s/it]
 94%|█████████▍| 58159/61904 [6:54:53<1:32:32,  1.48s/it]
 94%|█████████▍| 58160/61904 [6:54:54<1:29:31,  1.43s/it]
                                                         
{'loss': 2.4204, 'learning_rate': 1.0606767794632439e-07, 'epoch': 15.03}

 94%|█████████▍| 58160/61904 [6:54:54<1:29:31,  1.43s/it]
 94%|█████████▍| 58161/61904 [6:54:55<1:27:30,  1.40s/it]
 94%|█████████▍| 58162/61904 [6:54:57<1:27:10,  1.40s/it]
 94%|█████████▍| 58163/61904 [6:54:58<1:25:22,  1.37s/it]
 94%|█████████▍| 58164/61904 [6:54:59<1:25:08,  1.37s/it]
 94%|█████████▍| 58165/61904 [6:55:01<1:27:09,  1.40s/it]
 94%|█████████▍| 58166/61904 [6:55:02<1:27:49,  1.41s/it]
 94%|█████████▍| 58167/61904 [6:55:04<1:27:35,  1.41s/it]
 94%|█████████▍| 58168/61904 [6:55:05<1:25:59,  1.38s/it]
 94%|█████████▍| 58169/61904 [6:55:07<1:25:53,  1.38s/it]
 94%|█████████▍| 58170/61904 [6:55:08<1:26:23,  1.39s/it]
 94%|█████████▍| 58171/61904 [6:55:09<1:25:00,  1.37s/it]
 94%|█████████▍| 58172/61904 [6:55:11<1:25:28,  1.37s/it]
 94%|█████████▍| 58173/61904 [6:55:12<1:25:04,  1.37s/it]
 94%|█████████▍| 58174/61904 [6:55:13<1:22:42,  1.33s/it]
 94%|█████████▍| 58175/61904 [6:55:15<1:23:01,  1.34s/it]
 94%|█████████▍| 58176/61904 [6:55:16<1:24:17,  1.36s/it]
 94%|█████████▍| 58177/61904 [6:55:17<1:26:07,  1.39s/it]
 94%|█████████▍| 58178/61904 [6:55:19<1:26:18,  1.39s/it]
 94%|█████████▍| 58179/61904 [6:55:20<1:25:59,  1.39s/it]
 94%|█████████▍| 58180/61904 [6:55:22<1:26:37,  1.40s/it]
                                                         
{'loss': 2.4318, 'learning_rate': 1.0603526513678205e-07, 'epoch': 15.04}

 94%|█████████▍| 58180/61904 [6:55:22<1:26:37,  1.40s/it]
 94%|█████████▍| 58181/61904 [6:55:23<1:27:55,  1.42s/it]
 94%|█████████▍| 58182/61904 [6:55:24<1:26:04,  1.39s/it]
 94%|█████████▍| 58183/61904 [6:55:26<1:25:32,  1.38s/it]
 94%|█████████▍| 58184/61904 [6:55:27<1:25:14,  1.37s/it]
 94%|█████████▍| 58185/61904 [6:55:28<1:22:42,  1.33s/it]
 94%|█████████▍| 58186/61904 [6:55:30<1:23:58,  1.36s/it]
 94%|█████████▍| 58187/61904 [6:55:31<1:22:15,  1.33s/it]
 94%|█████████▍| 58188/61904 [6:55:32<1:23:44,  1.35s/it]
 94%|█████████▍| 58189/61904 [6:55:34<1:21:32,  1.32s/it]
 94%|█████████▍| 58190/61904 [6:55:35<1:20:23,  1.30s/it]
 94%|█████████▍| 58191/61904 [6:55:36<1:21:42,  1.32s/it]
 94%|█████████▍| 58192/61904 [6:55:38<1:24:06,  1.36s/it]
 94%|█████████▍| 58193/61904 [6:55:39<1:22:50,  1.34s/it]
 94%|█████████▍| 58194/61904 [6:55:40<1:22:00,  1.33s/it]
 94%|█████████▍| 58195/61904 [6:55:42<1:21:51,  1.32s/it]
 94%|█████████▍| 58196/61904 [6:55:43<1:24:32,  1.37s/it]
 94%|█████████▍| 58197/61904 [6:55:44<1:24:26,  1.37s/it]
 94%|█████████▍| 58198/61904 [6:55:46<1:21:51,  1.33s/it]
 94%|█████████▍| 58199/61904 [6:55:47<1:23:26,  1.35s/it]
 94%|█████████▍| 58200/61904 [6:55:49<1:27:46,  1.42s/it]
                                                         
{'loss': 2.4512, 'learning_rate': 1.0600285232723974e-07, 'epoch': 15.04}

 94%|█████████▍| 58200/61904 [6:55:49<1:27:46,  1.42s/it]
 94%|█████████▍| 58201/61904 [6:55:50<1:27:37,  1.42s/it]
 94%|█████████▍| 58202/61904 [6:55:51<1:26:03,  1.39s/it]
 94%|█████████▍| 58203/61904 [6:55:53<1:27:03,  1.41s/it]
 94%|█████████▍| 58204/61904 [6:55:54<1:24:58,  1.38s/it]
 94%|█████████▍| 58205/61904 [6:55:55<1:22:54,  1.34s/it]
 94%|█████████▍| 58206/61904 [6:55:57<1:23:05,  1.35s/it]
 94%|█████████▍| 58207/61904 [6:55:58<1:23:15,  1.35s/it]
 94%|█████████▍| 58208/61904 [6:56:00<1:23:17,  1.35s/it]
 94%|█████████▍| 58209/61904 [6:56:01<1:25:01,  1.38s/it]
 94%|█████████▍| 58210/61904 [6:56:02<1:24:55,  1.38s/it]
 94%|█████████▍| 58211/61904 [6:56:04<1:25:25,  1.39s/it]
 94%|█████████▍| 58212/61904 [6:56:05<1:26:05,  1.40s/it]
 94%|█████████▍| 58213/61904 [6:56:07<1:24:35,  1.38s/it]
 94%|█████████▍| 58214/61904 [6:56:08<1:21:55,  1.33s/it]
 94%|█████████▍| 58215/61904 [6:56:09<1:23:03,  1.35s/it]
 94%|█████████▍| 58216/61904 [6:56:10<1:22:34,  1.34s/it]
 94%|█████████▍| 58217/61904 [6:56:12<1:24:55,  1.38s/it]
 94%|█████████▍| 58218/61904 [6:56:14<1:27:54,  1.43s/it]
 94%|█████████▍| 58219/61904 [6:56:15<1:26:05,  1.40s/it]
 94%|█████████▍| 58220/61904 [6:56:16<1:26:30,  1.41s/it]
                                                         
{'loss': 2.4247, 'learning_rate': 1.0597043951769737e-07, 'epoch': 15.05}

 94%|█████████▍| 58220/61904 [6:56:16<1:26:30,  1.41s/it]
 94%|█████████▍| 58221/61904 [6:56:18<1:24:59,  1.38s/it]
 94%|█████████▍| 58222/61904 [6:56:19<1:25:09,  1.39s/it]
 94%|█████████▍| 58223/61904 [6:56:20<1:22:43,  1.35s/it]
 94%|█████████▍| 58224/61904 [6:56:22<1:23:22,  1.36s/it]
 94%|█████████▍| 58225/61904 [6:56:23<1:24:50,  1.38s/it]
 94%|█████████▍| 58226/61904 [6:56:24<1:25:34,  1.40s/it]
 94%|█████████▍| 58227/61904 [6:56:26<1:27:09,  1.42s/it]
 94%|█████████▍| 58228/61904 [6:56:27<1:26:03,  1.40s/it]
 94%|█████████▍| 58229/61904 [6:56:29<1:26:34,  1.41s/it]
 94%|█████████▍| 58230/61904 [6:56:30<1:24:40,  1.38s/it]
 94%|█████████▍| 58231/61904 [6:56:32<1:25:57,  1.40s/it]
 94%|█████████▍| 58232/61904 [6:56:33<1:25:31,  1.40s/it]
 94%|█████████▍| 58233/61904 [6:56:34<1:22:50,  1.35s/it]
 94%|█████████▍| 58234/61904 [6:56:36<1:22:58,  1.36s/it]
 94%|█████████▍| 58235/61904 [6:56:37<1:23:01,  1.36s/it]
 94%|█████████▍| 58236/61904 [6:56:38<1:23:06,  1.36s/it]
 94%|█████████▍| 58237/61904 [6:56:40<1:24:28,  1.38s/it]
 94%|█████████▍| 58238/61904 [6:56:41<1:25:22,  1.40s/it]
 94%|█████████▍| 58239/61904 [6:56:43<1:28:07,  1.44s/it]
 94%|█████████▍| 58240/61904 [6:56:44<1:27:25,  1.43s/it]
                                                         
{'loss': 2.4195, 'learning_rate': 1.0593802670815506e-07, 'epoch': 15.05}

 94%|█████████▍| 58240/61904 [6:56:44<1:27:25,  1.43s/it]
 94%|█████████▍| 58241/61904 [6:56:46<1:27:29,  1.43s/it]
 94%|█████████▍| 58242/61904 [6:56:47<1:28:02,  1.44s/it]
 94%|█████████▍| 58243/61904 [6:56:48<1:26:59,  1.43s/it]
 94%|█████████▍| 58244/61904 [6:56:50<1:29:26,  1.47s/it]
 94%|█████████▍| 58245/61904 [6:56:51<1:25:09,  1.40s/it]
 94%|█████████▍| 58246/61904 [6:56:53<1:25:54,  1.41s/it]
 94%|█████████▍| 58247/61904 [6:56:54<1:25:33,  1.40s/it]
 94%|█████████▍| 58248/61904 [6:56:55<1:24:46,  1.39s/it]
 94%|█████████▍| 58249/61904 [6:56:57<1:20:46,  1.33s/it]
 94%|█████████▍| 58250/61904 [6:56:58<1:21:20,  1.34s/it]
 94%|█████████▍| 58251/61904 [6:56:59<1:19:53,  1.31s/it]
 94%|█████████▍| 58252/61904 [6:57:00<1:19:23,  1.30s/it]
 94%|█████████▍| 58253/61904 [6:57:02<1:19:55,  1.31s/it]
 94%|█████████▍| 58254/61904 [6:57:03<1:19:43,  1.31s/it]
 94%|█████████▍| 58255/61904 [6:57:04<1:19:09,  1.30s/it]
 94%|█████████▍| 58256/61904 [6:57:06<1:19:49,  1.31s/it]
 94%|█████████▍| 58257/61904 [6:57:07<1:23:29,  1.37s/it]
 94%|█████████▍| 58258/61904 [6:57:09<1:24:50,  1.40s/it]
 94%|█████████▍| 58259/61904 [6:57:10<1:25:16,  1.40s/it]
 94%|█████████▍| 58260/61904 [6:57:11<1:23:56,  1.38s/it]
                                                         
{'loss': 2.4264, 'learning_rate': 1.0590561389861272e-07, 'epoch': 15.06}

 94%|█████████▍| 58260/61904 [6:57:11<1:23:56,  1.38s/it]
 94%|█████████▍| 58261/61904 [6:57:13<1:23:02,  1.37s/it]
 94%|█████████▍| 58262/61904 [6:57:14<1:23:08,  1.37s/it]
 94%|█████████▍| 58263/61904 [6:57:15<1:21:52,  1.35s/it]
 94%|█████████▍| 58264/61904 [6:57:17<1:22:23,  1.36s/it]
 94%|█████████▍| 58265/61904 [6:57:18<1:22:50,  1.37s/it]
 94%|█████████▍| 58266/61904 [6:57:20<1:23:51,  1.38s/it]
 94%|█████████▍| 58267/61904 [6:57:21<1:21:37,  1.35s/it]
 94%|█████████▍| 58268/61904 [6:57:22<1:19:54,  1.32s/it]
 94%|█████████▍| 58269/61904 [6:57:24<1:21:12,  1.34s/it]
 94%|█████████▍| 58270/61904 [6:57:25<1:22:18,  1.36s/it]
 94%|█████████▍| 58271/61904 [6:57:26<1:22:36,  1.36s/it]
 94%|█████████▍| 58272/61904 [6:57:28<1:21:04,  1.34s/it]
 94%|█████████▍| 58273/61904 [6:57:29<1:21:17,  1.34s/it]
 94%|█████████▍| 58274/61904 [6:57:30<1:22:08,  1.36s/it]
 94%|█████████▍| 58275/61904 [6:57:32<1:25:58,  1.42s/it]
 94%|█████████▍| 58276/61904 [6:57:33<1:23:02,  1.37s/it]
 94%|█████████▍| 58277/61904 [6:57:34<1:22:19,  1.36s/it]
 94%|█████████▍| 58278/61904 [6:57:36<1:23:23,  1.38s/it]
 94%|█████████▍| 58279/61904 [6:57:37<1:26:22,  1.43s/it]
 94%|█████████▍| 58280/61904 [6:57:39<1:23:37,  1.38s/it]
                                                         
{'loss': 2.4425, 'learning_rate': 1.0587320108907041e-07, 'epoch': 15.06}

 94%|█████████▍| 58280/61904 [6:57:39<1:23:37,  1.38s/it]
 94%|█████████▍| 58281/61904 [6:57:40<1:24:07,  1.39s/it]
 94%|█████████▍| 58282/61904 [6:57:42<1:25:01,  1.41s/it]
 94%|█████████▍| 58283/61904 [6:57:43<1:23:00,  1.38s/it]
 94%|█████████▍| 58284/61904 [6:57:44<1:21:20,  1.35s/it]
 94%|█████████▍| 58285/61904 [6:57:46<1:21:57,  1.36s/it]
 94%|█████████▍| 58286/61904 [6:57:47<1:23:34,  1.39s/it]
 94%|█████████▍| 58287/61904 [6:57:48<1:25:09,  1.41s/it]
 94%|█████████▍| 58288/61904 [6:57:50<1:26:27,  1.43s/it]
 94%|█████████▍| 58289/61904 [6:57:51<1:24:53,  1.41s/it]
 94%|█████████▍| 58290/61904 [6:57:53<1:24:08,  1.40s/it]
 94%|█████████▍| 58291/61904 [6:57:54<1:23:53,  1.39s/it]
 94%|█████████▍| 58292/61904 [6:57:56<1:26:54,  1.44s/it]
 94%|█████████▍| 58293/61904 [6:57:57<1:25:50,  1.43s/it]
 94%|█████████▍| 58294/61904 [6:57:58<1:23:22,  1.39s/it]
 94%|█████████▍| 58295/61904 [6:58:00<1:21:17,  1.35s/it]
 94%|█████████▍| 58296/61904 [6:58:01<1:22:33,  1.37s/it]
 94%|█████████▍| 58297/61904 [6:58:02<1:23:01,  1.38s/it]
 94%|█████████▍| 58298/61904 [6:58:04<1:24:17,  1.40s/it]
 94%|█████████▍| 58299/61904 [6:58:05<1:24:50,  1.41s/it]
 94%|█████████▍| 58300/61904 [6:58:07<1:23:57,  1.40s/it]
                                                         
{'loss': 2.3938, 'learning_rate': 1.0584078827952805e-07, 'epoch': 15.07}

 94%|█████████▍| 58300/61904 [6:58:07<1:23:57,  1.40s/it]
 94%|█████████▍| 58301/61904 [6:58:08<1:20:28,  1.34s/it]
 94%|█████████▍| 58302/61904 [6:58:09<1:19:54,  1.33s/it]
 94%|█████████▍| 58303/61904 [6:58:11<1:21:08,  1.35s/it]
 94%|█████████▍| 58304/61904 [6:58:12<1:22:28,  1.37s/it]
 94%|█████████▍| 58305/61904 [6:58:13<1:22:53,  1.38s/it]
 94%|█████████▍| 58306/61904 [6:58:15<1:21:26,  1.36s/it]
 94%|█████████▍| 58307/61904 [6:58:16<1:20:16,  1.34s/it]
 94%|█████████▍| 58308/61904 [6:58:17<1:20:18,  1.34s/it]
 94%|█████████▍| 58309/61904 [6:58:19<1:24:50,  1.42s/it]
 94%|█████████▍| 58310/61904 [6:58:20<1:25:51,  1.43s/it]
 94%|█████████▍| 58311/61904 [6:58:22<1:28:00,  1.47s/it]
 94%|█████████▍| 58312/61904 [6:58:23<1:28:11,  1.47s/it]
 94%|█████████▍| 58313/61904 [6:58:25<1:25:42,  1.43s/it]
 94%|█████████▍| 58314/61904 [6:58:26<1:24:59,  1.42s/it]
 94%|█████████▍| 58315/61904 [6:58:28<1:28:38,  1.48s/it]
 94%|█████████▍| 58316/61904 [6:58:29<1:26:01,  1.44s/it]
 94%|█████████▍| 58317/61904 [6:58:31<1:27:21,  1.46s/it]
 94%|█████████▍| 58318/61904 [6:58:32<1:25:10,  1.43s/it]
 94%|█████████▍| 58319/61904 [6:58:33<1:23:34,  1.40s/it]
 94%|█████████▍| 58320/61904 [6:58:35<1:24:26,  1.41s/it]
                                                         
{'loss': 2.4447, 'learning_rate': 1.0580837546998573e-07, 'epoch': 15.07}

 94%|█████████▍| 58320/61904 [6:58:35<1:24:26,  1.41s/it]
 94%|█████████▍| 58321/61904 [6:58:36<1:23:00,  1.39s/it]
 94%|█████████▍| 58322/61904 [6:58:38<1:25:27,  1.43s/it]
 94%|█████████▍| 58323/61904 [6:58:39<1:24:28,  1.42s/it]
 94%|█████████▍| 58324/61904 [6:58:40<1:20:49,  1.35s/it]
 94%|█████████▍| 58325/61904 [6:58:42<1:22:17,  1.38s/it]
 94%|█████████▍| 58326/61904 [6:58:43<1:22:41,  1.39s/it]
 94%|█████████▍| 58327/61904 [6:58:45<1:24:09,  1.41s/it]
 94%|█████████▍| 58328/61904 [6:58:46<1:28:15,  1.48s/it]
 94%|█████████▍| 58329/61904 [6:58:47<1:24:41,  1.42s/it]
 94%|█████████▍| 58330/61904 [6:58:49<1:23:26,  1.40s/it]
 94%|█████████▍| 58331/61904 [6:58:50<1:23:21,  1.40s/it]
 94%|█████████▍| 58332/61904 [6:58:52<1:24:22,  1.42s/it]
 94%|█████████▍| 58333/61904 [6:58:53<1:24:20,  1.42s/it]
 94%|█████████▍| 58334/61904 [6:58:54<1:23:58,  1.41s/it]
 94%|█████████▍| 58335/61904 [6:58:56<1:26:12,  1.45s/it]
 94%|█████████▍| 58336/61904 [6:58:57<1:23:06,  1.40s/it]
 94%|█████████▍| 58337/61904 [6:58:59<1:23:08,  1.40s/it]
 94%|█████████▍| 58338/61904 [6:59:00<1:22:35,  1.39s/it]
 94%|█████████▍| 58339/61904 [6:59:01<1:22:01,  1.38s/it]
 94%|█████████▍| 58340/61904 [6:59:03<1:21:46,  1.38s/it]
                                                         
{'loss': 2.3923, 'learning_rate': 1.0577596266044342e-07, 'epoch': 15.08}

 94%|█████████▍| 58340/61904 [6:59:03<1:21:46,  1.38s/it]
 94%|█████████▍| 58341/61904 [6:59:04<1:22:38,  1.39s/it]
 94%|█████████▍| 58342/61904 [6:59:06<1:21:04,  1.37s/it]
 94%|█████████▍| 58343/61904 [6:59:07<1:20:06,  1.35s/it]
 94%|█████████▍| 58344/61904 [6:59:08<1:18:53,  1.33s/it]
 94%|█████████▍| 58345/61904 [6:59:09<1:19:25,  1.34s/it]
 94%|█████████▍| 58346/61904 [6:59:11<1:21:44,  1.38s/it]
 94%|█████████▍| 58347/61904 [6:59:12<1:19:37,  1.34s/it]
 94%|█████████▍| 58348/61904 [6:59:14<1:18:47,  1.33s/it]
 94%|█████████▍| 58349/61904 [6:59:15<1:19:33,  1.34s/it]
 94%|█████████▍| 58350/61904 [6:59:16<1:20:37,  1.36s/it]
 94%|█████████▍| 58351/61904 [6:59:18<1:19:22,  1.34s/it]
 94%|█████████▍| 58352/61904 [6:59:19<1:23:03,  1.40s/it]
 94%|█████████▍| 58353/61904 [6:59:20<1:22:00,  1.39s/it]
 94%|█████████▍| 58354/61904 [6:59:22<1:21:07,  1.37s/it]
 94%|█████████▍| 58355/61904 [6:59:23<1:23:22,  1.41s/it]
 94%|█████████▍| 58356/61904 [6:59:25<1:23:24,  1.41s/it]
 94%|█████████▍| 58357/61904 [6:59:26<1:22:07,  1.39s/it]
 94%|█████████▍| 58358/61904 [6:59:27<1:22:17,  1.39s/it]
 94%|█████████▍| 58359/61904 [6:59:29<1:20:17,  1.36s/it]
 94%|█████████▍| 58360/61904 [6:59:30<1:20:24,  1.36s/it]
                                                         
{'loss': 2.4065, 'learning_rate': 1.0574354985090108e-07, 'epoch': 15.08}

 94%|█████████▍| 58360/61904 [6:59:30<1:20:24,  1.36s/it]
 94%|█████████▍| 58361/61904 [6:59:31<1:20:03,  1.36s/it]
 94%|█████████▍| 58362/61904 [6:59:33<1:20:35,  1.37s/it]
 94%|█████████▍| 58363/61904 [6:59:34<1:23:55,  1.42s/it]
 94%|█████████▍| 58364/61904 [6:59:36<1:21:47,  1.39s/it]
 94%|█████████▍| 58365/61904 [6:59:37<1:21:07,  1.38s/it]
 94%|█████████▍| 58366/61904 [6:59:38<1:19:16,  1.34s/it]
 94%|█████████▍| 58367/61904 [6:59:40<1:18:50,  1.34s/it]
 94%|█████████▍| 58368/61904 [6:59:41<1:17:29,  1.31s/it]
 94%|█████████▍| 58369/61904 [6:59:42<1:18:48,  1.34s/it]
 94%|█████████▍| 58370/61904 [6:59:44<1:19:22,  1.35s/it]
 94%|█████████▍| 58371/61904 [6:59:45<1:17:13,  1.31s/it]
 94%|█████████▍| 58372/61904 [6:59:46<1:17:59,  1.32s/it]
 94%|█████████▍| 58373/61904 [6:59:48<1:17:09,  1.31s/it]
 94%|█████████▍| 58374/61904 [6:59:49<1:17:35,  1.32s/it]
 94%|█████████▍| 58375/61904 [6:59:50<1:17:38,  1.32s/it]
 94%|█████████▍| 58376/61904 [6:59:52<1:21:01,  1.38s/it]
 94%|█████████▍| 58377/61904 [6:59:53<1:20:32,  1.37s/it]
 94%|█████████▍| 58378/61904 [6:59:54<1:20:35,  1.37s/it]
 94%|█████████▍| 58379/61904 [6:59:56<1:22:11,  1.40s/it]
 94%|█████████▍| 58380/61904 [6:59:57<1:20:34,  1.37s/it]
                                                         
{'loss': 2.4171, 'learning_rate': 1.0571113704135875e-07, 'epoch': 15.09}

 94%|█████████▍| 58380/61904 [6:59:57<1:20:34,  1.37s/it]
 94%|█████████▍| 58381/61904 [6:59:59<1:19:55,  1.36s/it]
 94%|█████████▍| 58382/61904 [7:00:00<1:20:55,  1.38s/it]
 94%|█████████▍| 58383/61904 [7:00:01<1:20:38,  1.37s/it]
 94%|█████████▍| 58384/61904 [7:00:03<1:22:51,  1.41s/it]
 94%|█████████▍| 58385/61904 [7:00:04<1:22:03,  1.40s/it]
 94%|█████████▍| 58386/61904 [7:00:06<1:21:21,  1.39s/it]
 94%|█████████▍| 58387/61904 [7:00:07<1:21:37,  1.39s/it]
 94%|█████████▍| 58388/61904 [7:00:08<1:20:43,  1.38s/it]
 94%|█████████▍| 58389/61904 [7:00:10<1:21:40,  1.39s/it]
 94%|█████████▍| 58390/61904 [7:00:11<1:19:48,  1.36s/it]
 94%|█████████▍| 58391/61904 [7:00:12<1:20:24,  1.37s/it]
 94%|█████████▍| 58392/61904 [7:00:14<1:23:07,  1.42s/it]
 94%|█████████▍| 58393/61904 [7:00:16<1:25:55,  1.47s/it]
 94%|█████████▍| 58394/61904 [7:00:17<1:24:21,  1.44s/it]
 94%|█████████▍| 58395/61904 [7:00:18<1:22:31,  1.41s/it]
 94%|█████████▍| 58396/61904 [7:00:20<1:22:34,  1.41s/it]
 94%|█████████▍| 58397/61904 [7:00:21<1:20:48,  1.38s/it]
 94%|█████████▍| 58398/61904 [7:00:22<1:20:20,  1.37s/it]
 94%|█████████▍| 58399/61904 [7:00:24<1:24:34,  1.45s/it]
 94%|█████████▍| 58400/61904 [7:00:25<1:23:50,  1.44s/it]
                                                         
{'loss': 2.4148, 'learning_rate': 1.0567872423181641e-07, 'epoch': 15.09}

 94%|█████████▍| 58400/61904 [7:00:25<1:23:50,  1.44s/it]
 94%|█████████▍| 58401/61904 [7:00:27<1:26:28,  1.48s/it]
 94%|█████████▍| 58402/61904 [7:00:28<1:23:31,  1.43s/it]
 94%|█████████▍| 58403/61904 [7:00:30<1:21:22,  1.39s/it]
 94%|█████████▍| 58404/61904 [7:00:31<1:20:19,  1.38s/it]
 94%|█████████▍| 58405/61904 [7:00:32<1:18:51,  1.35s/it]
 94%|█████████▍| 58406/61904 [7:00:34<1:19:51,  1.37s/it]
 94%|█████████▍| 58407/61904 [7:00:35<1:22:28,  1.42s/it]
 94%|█████████▍| 58408/61904 [7:00:36<1:20:21,  1.38s/it]
 94%|█████████▍| 58409/61904 [7:00:38<1:18:42,  1.35s/it]
 94%|█████████▍| 58410/61904 [7:00:39<1:20:06,  1.38s/it]
 94%|█████████▍| 58411/61904 [7:00:40<1:16:40,  1.32s/it]
 94%|█████████▍| 58412/61904 [7:00:42<1:19:09,  1.36s/it]
 94%|█████████▍| 58413/61904 [7:00:43<1:20:24,  1.38s/it]
 94%|█████████▍| 58414/61904 [7:00:45<1:23:18,  1.43s/it]
 94%|█████████▍| 58415/61904 [7:00:46<1:21:25,  1.40s/it]
 94%|█████████▍| 58416/61904 [7:00:47<1:19:34,  1.37s/it]
 94%|█████████▍| 58417/61904 [7:00:49<1:18:18,  1.35s/it]
 94%|█████████▍| 58418/61904 [7:00:50<1:20:18,  1.38s/it]
 94%|█████████▍| 58419/61904 [7:00:51<1:19:08,  1.36s/it]
 94%|█████████▍| 58420/61904 [7:00:53<1:18:41,  1.36s/it]
                                                         
{'loss': 2.4317, 'learning_rate': 1.056463114222741e-07, 'epoch': 15.1}

 94%|█████████▍| 58420/61904 [7:00:53<1:18:41,  1.36s/it]
 94%|█████████▍| 58421/61904 [7:00:54<1:17:43,  1.34s/it]
 94%|█████████▍| 58422/61904 [7:00:55<1:16:29,  1.32s/it]
 94%|█████████▍| 58423/61904 [7:00:57<1:17:16,  1.33s/it]
 94%|█████████▍| 58424/61904 [7:00:58<1:18:25,  1.35s/it]
 94%|█████████▍| 58425/61904 [7:00:59<1:17:52,  1.34s/it]
 94%|█████████▍| 58426/61904 [7:01:01<1:20:15,  1.38s/it]
 94%|█████████▍| 58427/61904 [7:01:02<1:18:27,  1.35s/it]
 94%|█████████▍| 58428/61904 [7:01:04<1:22:56,  1.43s/it]
 94%|█████████▍| 58429/61904 [7:01:05<1:23:26,  1.44s/it]
 94%|█████████▍| 58430/61904 [7:01:07<1:22:11,  1.42s/it]
 94%|█████████▍| 58431/61904 [7:01:08<1:21:31,  1.41s/it]
 94%|█████████▍| 58432/61904 [7:01:10<1:23:09,  1.44s/it]
 94%|█████████▍| 58433/61904 [7:01:11<1:20:15,  1.39s/it]
 94%|█████████▍| 58434/61904 [7:01:12<1:19:37,  1.38s/it]
 94%|█████████▍| 58435/61904 [7:01:14<1:18:42,  1.36s/it]
 94%|█████████▍| 58436/61904 [7:01:15<1:17:12,  1.34s/it]
 94%|█████████▍| 58437/61904 [7:01:16<1:19:21,  1.37s/it]
 94%|█████████▍| 58438/61904 [7:01:18<1:19:41,  1.38s/it]
 94%|█████████▍| 58439/61904 [7:01:19<1:18:14,  1.35s/it]
 94%|█████████▍| 58440/61904 [7:01:20<1:18:02,  1.35s/it]
                                                         
{'loss': 2.3749, 'learning_rate': 1.0561389861273176e-07, 'epoch': 15.1}

 94%|█████████▍| 58440/61904 [7:01:20<1:18:02,  1.35s/it]
 94%|█████████▍| 58441/61904 [7:01:22<1:16:53,  1.33s/it]
 94%|█████████▍| 58442/61904 [7:01:23<1:17:16,  1.34s/it]
 94%|█████████▍| 58443/61904 [7:01:24<1:16:04,  1.32s/it]
 94%|█████████▍| 58444/61904 [7:01:26<1:16:04,  1.32s/it]
 94%|█████████▍| 58445/61904 [7:01:27<1:15:58,  1.32s/it]
 94%|█████████▍| 58446/61904 [7:01:28<1:14:41,  1.30s/it]
 94%|█████████▍| 58447/61904 [7:01:30<1:17:48,  1.35s/it]
 94%|█████████▍| 58448/61904 [7:01:31<1:19:01,  1.37s/it]
 94%|█████████▍| 58449/61904 [7:01:32<1:18:06,  1.36s/it]
 94%|█████████▍| 58450/61904 [7:01:34<1:19:03,  1.37s/it]
 94%|█████████▍| 58451/61904 [7:01:35<1:16:33,  1.33s/it]
 94%|█████████▍| 58452/61904 [7:01:36<1:16:50,  1.34s/it]
 94%|█████████▍| 58453/61904 [7:01:38<1:18:39,  1.37s/it]
 94%|█████████▍| 58454/61904 [7:01:39<1:22:01,  1.43s/it]
 94%|█████████▍| 58455/61904 [7:01:41<1:19:16,  1.38s/it]
 94%|█████████▍| 58456/61904 [7:01:42<1:18:46,  1.37s/it]
 94%|█████████▍| 58457/61904 [7:01:43<1:18:25,  1.37s/it]
 94%|█████████▍| 58458/61904 [7:01:45<1:19:35,  1.39s/it]
 94%|█████████▍| 58459/61904 [7:01:46<1:21:37,  1.42s/it]
 94%|█████████▍| 58460/61904 [7:01:47<1:17:40,  1.35s/it]
                                                         
{'loss': 2.3947, 'learning_rate': 1.0558148580318942e-07, 'epoch': 15.11}

 94%|█████████▍| 58460/61904 [7:01:47<1:17:40,  1.35s/it]
 94%|█████████▍| 58461/61904 [7:01:49<1:15:57,  1.32s/it]
 94%|█████████▍| 58462/61904 [7:01:50<1:17:42,  1.35s/it]
 94%|█████████▍| 58463/61904 [7:01:52<1:19:19,  1.38s/it]
 94%|█████████▍| 58464/61904 [7:01:53<1:19:10,  1.38s/it]
 94%|█████████▍| 58465/61904 [7:01:54<1:17:03,  1.34s/it]
 94%|█████████▍| 58466/61904 [7:01:55<1:16:08,  1.33s/it]
 94%|█████████▍| 58467/61904 [7:01:57<1:16:53,  1.34s/it]
 94%|█████████▍| 58468/61904 [7:01:58<1:18:53,  1.38s/it]
 94%|█████████▍| 58469/61904 [7:02:00<1:19:34,  1.39s/it]
 94%|█████████▍| 58470/61904 [7:02:01<1:21:44,  1.43s/it]
 94%|█████████▍| 58471/61904 [7:02:03<1:20:17,  1.40s/it]
 94%|█████████▍| 58472/61904 [7:02:04<1:18:31,  1.37s/it]
 94%|█████████▍| 58473/61904 [7:02:05<1:17:16,  1.35s/it]
 94%|█████████▍| 58474/61904 [7:02:06<1:16:21,  1.34s/it]
 94%|█████████▍| 58475/61904 [7:02:08<1:14:45,  1.31s/it]
 94%|█████████▍| 58476/61904 [7:02:09<1:17:02,  1.35s/it]
 94%|█████████▍| 58477/61904 [7:02:11<1:18:50,  1.38s/it]
 94%|█████████▍| 58478/61904 [7:02:12<1:17:32,  1.36s/it]
 94%|█████████▍| 58479/61904 [7:02:13<1:19:31,  1.39s/it]
 94%|█████████▍| 58480/61904 [7:02:15<1:20:34,  1.41s/it]
                                                         
{'loss': 2.3908, 'learning_rate': 1.0554907299364708e-07, 'epoch': 15.11}

 94%|█████████▍| 58480/61904 [7:02:15<1:20:34,  1.41s/it]
 94%|█████████▍| 58481/61904 [7:02:16<1:21:24,  1.43s/it]
 94%|█████████▍| 58482/61904 [7:02:18<1:20:51,  1.42s/it]
 94%|█████████▍| 58483/61904 [7:02:19<1:22:05,  1.44s/it]
 94%|█████████▍| 58484/61904 [7:02:21<1:20:02,  1.40s/it]
 94%|█████████▍| 58485/61904 [7:02:22<1:21:47,  1.44s/it]
 94%|█████████▍| 58486/61904 [7:02:23<1:21:49,  1.44s/it]
 94%|█████████▍| 58487/61904 [7:02:25<1:18:49,  1.38s/it]
 94%|█████████▍| 58488/61904 [7:02:26<1:18:12,  1.37s/it]
 94%|█████████▍| 58489/61904 [7:02:27<1:17:31,  1.36s/it]
 94%|█████████▍| 58490/61904 [7:02:29<1:17:19,  1.36s/it]
 94%|█████████▍| 58491/61904 [7:02:30<1:15:57,  1.34s/it]
 94%|█████████▍| 58492/61904 [7:02:31<1:15:54,  1.33s/it]
 94%|█████████▍| 58493/61904 [7:02:33<1:17:59,  1.37s/it]
 94%|█████████▍| 58494/61904 [7:02:34<1:17:24,  1.36s/it]
 94%|█████████▍| 58495/61904 [7:02:36<1:25:07,  1.50s/it]
 94%|█████████▍| 58496/61904 [7:02:37<1:22:02,  1.44s/it]
 94%|█████████▍| 58497/61904 [7:02:39<1:24:33,  1.49s/it]
 94%|█████████▍| 58498/61904 [7:02:40<1:22:01,  1.45s/it]
 94%|█████████▍| 58499/61904 [7:02:42<1:20:01,  1.41s/it]
 95%|█████████▍| 58500/61904 [7:02:43<1:19:47,  1.41s/it]
                                                         
{'loss': 2.3965, 'learning_rate': 1.0551666018410477e-07, 'epoch': 15.12}

 95%|█████████▍| 58500/61904 [7:02:43<1:19:47,  1.41s/it]
 95%|█████████▍| 58501/61904 [7:02:44<1:18:57,  1.39s/it]
 95%|█████████▍| 58502/61904 [7:02:46<1:18:23,  1.38s/it]
 95%|█████████▍| 58503/61904 [7:02:47<1:17:12,  1.36s/it]
 95%|█████████▍| 58504/61904 [7:02:48<1:15:59,  1.34s/it]
 95%|█████████▍| 58505/61904 [7:02:50<1:16:50,  1.36s/it]
 95%|█████████▍| 58506/61904 [7:02:51<1:18:35,  1.39s/it]
 95%|█████████▍| 58507/61904 [7:02:52<1:17:30,  1.37s/it]
 95%|█████████▍| 58508/61904 [7:02:54<1:16:41,  1.35s/it]
 95%|█████████▍| 58509/61904 [7:02:55<1:17:47,  1.37s/it]
 95%|█████████▍| 58510/61904 [7:02:57<1:17:59,  1.38s/it]
 95%|█████████▍| 58511/61904 [7:02:58<1:17:28,  1.37s/it]
 95%|█████████▍| 58512/61904 [7:02:59<1:17:21,  1.37s/it]
 95%|█████████▍| 58513/61904 [7:03:01<1:17:27,  1.37s/it]
 95%|█████████▍| 58514/61904 [7:03:02<1:19:22,  1.40s/it]
 95%|█████████▍| 58515/61904 [7:03:04<1:18:04,  1.38s/it]
 95%|█████████▍| 58516/61904 [7:03:05<1:18:14,  1.39s/it]
 95%|█████████▍| 58517/61904 [7:03:06<1:17:19,  1.37s/it]
 95%|█████████▍| 58518/61904 [7:03:08<1:20:19,  1.42s/it]
 95%|█████████▍| 58519/61904 [7:03:09<1:21:52,  1.45s/it]
 95%|█████████▍| 58520/61904 [7:03:11<1:21:59,  1.45s/it]
                                                         
{'loss': 2.4536, 'learning_rate': 1.0548424737456243e-07, 'epoch': 15.12}

 95%|█████████▍| 58520/61904 [7:03:11<1:21:59,  1.45s/it]
 95%|█████████▍| 58521/61904 [7:03:12<1:20:14,  1.42s/it]
 95%|█████████▍| 58522/61904 [7:03:13<1:18:14,  1.39s/it]
 95%|█████████▍| 58523/61904 [7:03:15<1:21:22,  1.44s/it]
 95%|█████████▍| 58524/61904 [7:03:16<1:19:51,  1.42s/it]
 95%|█████████▍| 58525/61904 [7:03:18<1:17:50,  1.38s/it]
 95%|█████████▍| 58526/61904 [7:03:19<1:17:41,  1.38s/it]
 95%|█████████▍| 58527/61904 [7:03:20<1:16:44,  1.36s/it]
 95%|█████████▍| 58528/61904 [7:03:22<1:16:54,  1.37s/it]
 95%|█████████▍| 58529/61904 [7:03:23<1:17:06,  1.37s/it]
 95%|█████████▍| 58530/61904 [7:03:25<1:19:26,  1.41s/it]
 95%|█████████▍| 58531/61904 [7:03:26<1:18:38,  1.40s/it]
 95%|█████████▍| 58532/61904 [7:03:27<1:16:37,  1.36s/it]
 95%|█████████▍| 58533/61904 [7:03:28<1:14:23,  1.32s/it]
 95%|█████████▍| 58534/61904 [7:03:30<1:18:10,  1.39s/it]
 95%|█████████▍| 58535/61904 [7:03:31<1:17:01,  1.37s/it]
 95%|█████████▍| 58536/61904 [7:03:33<1:17:24,  1.38s/it]
 95%|█████████▍| 58537/61904 [7:03:34<1:15:59,  1.35s/it]
 95%|█████████▍| 58538/61904 [7:03:36<1:18:51,  1.41s/it]
 95%|█████████▍| 58539/61904 [7:03:37<1:17:58,  1.39s/it]
 95%|█████████▍| 58540/61904 [7:03:38<1:20:26,  1.43s/it]
                                                         
{'loss': 2.4602, 'learning_rate': 1.054518345650201e-07, 'epoch': 15.13}

 95%|█████████▍| 58540/61904 [7:03:38<1:20:26,  1.43s/it]
 95%|█████████▍| 58541/61904 [7:03:40<1:18:48,  1.41s/it]
 95%|█████████▍| 58542/61904 [7:03:41<1:20:21,  1.43s/it]
 95%|█████████▍| 58543/61904 [7:03:43<1:19:02,  1.41s/it]
 95%|█████████▍| 58544/61904 [7:03:44<1:18:45,  1.41s/it]
 95%|█████████▍| 58545/61904 [7:03:46<1:19:58,  1.43s/it]
 95%|█████████▍| 58546/61904 [7:03:47<1:18:20,  1.40s/it]
 95%|█████████▍| 58547/61904 [7:03:48<1:18:41,  1.41s/it]
 95%|█████████▍| 58548/61904 [7:03:50<1:19:36,  1.42s/it]
 95%|█████████▍| 58549/61904 [7:03:51<1:17:11,  1.38s/it]
 95%|█████████▍| 58550/61904 [7:03:52<1:15:16,  1.35s/it]
 95%|█████████▍| 58551/61904 [7:03:54<1:16:56,  1.38s/it]
 95%|█████████▍| 58552/61904 [7:03:55<1:19:46,  1.43s/it]
 95%|█████████▍| 58553/61904 [7:03:57<1:19:48,  1.43s/it]
 95%|█████████▍| 58554/61904 [7:03:58<1:21:00,  1.45s/it]
 95%|█████████▍| 58555/61904 [7:04:00<1:20:21,  1.44s/it]
 95%|█████████▍| 58556/61904 [7:04:01<1:16:37,  1.37s/it]
 95%|█████████▍| 58557/61904 [7:04:02<1:18:00,  1.40s/it]
 95%|█████████▍| 58558/61904 [7:04:04<1:18:59,  1.42s/it]
 95%|█████████▍| 58559/61904 [7:04:05<1:19:24,  1.42s/it]
 95%|█████████▍| 58560/61904 [7:04:07<1:17:06,  1.38s/it]
                                                         
{'loss': 2.4214, 'learning_rate': 1.0541942175547776e-07, 'epoch': 15.14}

 95%|█████████▍| 58560/61904 [7:04:07<1:17:06,  1.38s/it]
 95%|█████████▍| 58561/61904 [7:04:08<1:20:11,  1.44s/it]
 95%|█████████▍| 58562/61904 [7:04:10<1:21:44,  1.47s/it]
 95%|█████████▍| 58563/61904 [7:04:11<1:18:14,  1.41s/it]
 95%|█████████▍| 58564/61904 [7:04:12<1:16:47,  1.38s/it]
 95%|█████████▍| 58565/61904 [7:04:14<1:16:55,  1.38s/it]
 95%|█████████▍| 58566/61904 [7:04:15<1:19:18,  1.43s/it]
 95%|█████████▍| 58567/61904 [7:04:17<1:19:13,  1.42s/it]
 95%|█████████▍| 58568/61904 [7:04:18<1:22:39,  1.49s/it]
 95%|█████████▍| 58569/61904 [7:04:20<1:21:48,  1.47s/it]
 95%|█████████▍| 58570/61904 [7:04:21<1:18:11,  1.41s/it]
 95%|█████████▍| 58571/61904 [7:04:22<1:17:17,  1.39s/it]
 95%|█████████▍| 58572/61904 [7:04:24<1:16:24,  1.38s/it]
 95%|█████████▍| 58573/61904 [7:04:25<1:15:03,  1.35s/it]
 95%|█████████▍| 58574/61904 [7:04:26<1:14:40,  1.35s/it]
 95%|█████████▍| 58575/61904 [7:04:28<1:14:11,  1.34s/it]
 95%|█████████▍| 58576/61904 [7:04:29<1:14:32,  1.34s/it]
 95%|█████████▍| 58577/61904 [7:04:30<1:15:32,  1.36s/it]
 95%|█████████▍| 58578/61904 [7:04:32<1:13:58,  1.33s/it]
 95%|█████████▍| 58579/61904 [7:04:33<1:12:14,  1.30s/it]
 95%|█████████▍| 58580/61904 [7:04:34<1:13:07,  1.32s/it]
                                                         
{'loss': 2.4254, 'learning_rate': 1.0538700894593544e-07, 'epoch': 15.14}

 95%|█████████▍| 58580/61904 [7:04:34<1:13:07,  1.32s/it]
 95%|█████████▍| 58581/61904 [7:04:35<1:12:42,  1.31s/it]
 95%|█████████▍| 58582/61904 [7:04:37<1:12:59,  1.32s/it]
 95%|█████████▍| 58583/61904 [7:04:38<1:12:12,  1.30s/it]
 95%|█████████▍| 58584/61904 [7:04:40<1:17:18,  1.40s/it]
 95%|█████████▍| 58585/61904 [7:04:41<1:16:29,  1.38s/it]
 95%|█████████▍| 58586/61904 [7:04:42<1:14:48,  1.35s/it]
 95%|█████████▍| 58587/61904 [7:04:43<1:12:24,  1.31s/it]
 95%|█████████▍| 58588/61904 [7:04:45<1:13:58,  1.34s/it]
 95%|█████████▍| 58589/61904 [7:04:46<1:11:53,  1.30s/it]
 95%|█████████▍| 58590/61904 [7:04:47<1:11:18,  1.29s/it]
 95%|█████████▍| 58591/61904 [7:04:49<1:14:20,  1.35s/it]
 95%|█████████▍| 58592/61904 [7:04:50<1:15:57,  1.38s/it]
 95%|█████████▍| 58593/61904 [7:04:52<1:15:47,  1.37s/it]
 95%|█████████▍| 58594/61904 [7:04:53<1:15:20,  1.37s/it]
 95%|█████████▍| 58595/61904 [7:04:54<1:13:43,  1.34s/it]
 95%|█████████▍| 58596/61904 [7:04:56<1:13:08,  1.33s/it]
 95%|█████████▍| 58597/61904 [7:04:57<1:15:49,  1.38s/it]
 95%|█████████▍| 58598/61904 [7:04:58<1:16:18,  1.38s/it]
 95%|█████████▍| 58599/61904 [7:05:00<1:16:03,  1.38s/it]
 95%|█████████▍| 58600/61904 [7:05:01<1:17:40,  1.41s/it]
                                                         
{'loss': 2.446, 'learning_rate': 1.053545961363931e-07, 'epoch': 15.15}

 95%|█████████▍| 58600/61904 [7:05:01<1:17:40,  1.41s/it]
 95%|█████████▍| 58601/61904 [7:05:03<1:16:39,  1.39s/it]
 95%|█████████▍| 58602/61904 [7:05:04<1:18:14,  1.42s/it]
 95%|█████████▍| 58603/61904 [7:05:05<1:15:12,  1.37s/it]
 95%|█████████▍| 58604/61904 [7:05:07<1:14:09,  1.35s/it]
 95%|█████████▍| 58605/61904 [7:05:08<1:16:47,  1.40s/it]
 95%|█████████▍| 58606/61904 [7:05:10<1:19:14,  1.44s/it]
 95%|█████████▍| 58607/61904 [7:05:11<1:17:47,  1.42s/it]
 95%|█████████▍| 58608/61904 [7:05:12<1:16:26,  1.39s/it]
 95%|█████████▍| 58609/61904 [7:05:14<1:14:54,  1.36s/it]
 95%|█████████▍| 58610/61904 [7:05:15<1:13:08,  1.33s/it]
 95%|█████████▍| 58611/61904 [7:05:16<1:13:47,  1.34s/it]
 95%|█████████▍| 58612/61904 [7:05:18<1:13:10,  1.33s/it]
 95%|█████████▍| 58613/61904 [7:05:19<1:13:31,  1.34s/it]
 95%|█████████▍| 58614/61904 [7:05:21<1:15:49,  1.38s/it]
 95%|█████████▍| 58615/61904 [7:05:22<1:17:23,  1.41s/it]
 95%|█████████▍| 58616/61904 [7:05:23<1:16:36,  1.40s/it]
 95%|█████████▍| 58617/61904 [7:05:25<1:15:30,  1.38s/it]
 95%|█████████▍| 58618/61904 [7:05:26<1:14:57,  1.37s/it]
 95%|█████████▍| 58619/61904 [7:05:27<1:14:42,  1.36s/it]
 95%|█████████▍| 58620/61904 [7:05:29<1:15:19,  1.38s/it]
                                                         
{'loss': 2.4541, 'learning_rate': 1.0532218332685077e-07, 'epoch': 15.15}

 95%|█████████▍| 58620/61904 [7:05:29<1:15:19,  1.38s/it]
 95%|█████████▍| 58621/61904 [7:05:30<1:12:49,  1.33s/it]
 95%|█████████▍| 58622/61904 [7:05:31<1:11:27,  1.31s/it]
 95%|█████████▍| 58623/61904 [7:05:33<1:14:17,  1.36s/it]
 95%|█████████▍| 58624/61904 [7:05:34<1:14:20,  1.36s/it]
 95%|█████████▍| 58625/61904 [7:05:36<1:14:57,  1.37s/it]
 95%|█████████▍| 58626/61904 [7:05:37<1:13:59,  1.35s/it]
 95%|█████████▍| 58627/61904 [7:05:38<1:15:41,  1.39s/it]
 95%|█████████▍| 58628/61904 [7:05:40<1:14:01,  1.36s/it]
 95%|█████████▍| 58629/61904 [7:05:41<1:15:53,  1.39s/it]
 95%|█████████▍| 58630/61904 [7:05:42<1:15:08,  1.38s/it]
 95%|█████████▍| 58631/61904 [7:05:44<1:14:51,  1.37s/it]
 95%|█████████▍| 58632/61904 [7:05:45<1:15:48,  1.39s/it]
 95%|█████████▍| 58633/61904 [7:05:47<1:16:35,  1.40s/it]
 95%|█████████▍| 58634/61904 [7:05:48<1:16:22,  1.40s/it]
 95%|█████████▍| 58635/61904 [7:05:50<1:18:25,  1.44s/it]
 95%|█████████▍| 58636/61904 [7:05:51<1:17:18,  1.42s/it]
 95%|█████████▍| 58637/61904 [7:05:52<1:16:59,  1.41s/it]
 95%|█████████▍| 58638/61904 [7:05:54<1:16:02,  1.40s/it]
 95%|█████████▍| 58639/61904 [7:05:55<1:16:01,  1.40s/it]
 95%|█████████▍| 58640/61904 [7:05:56<1:14:31,  1.37s/it]
                                                         
{'loss': 2.4487, 'learning_rate': 1.0528977051730846e-07, 'epoch': 15.16}

 95%|█████████▍| 58640/61904 [7:05:56<1:14:31,  1.37s/it]
 95%|█████████▍| 58641/61904 [7:05:58<1:15:52,  1.40s/it]
 95%|█████████▍| 58642/61904 [7:05:59<1:15:40,  1.39s/it]
 95%|█████████▍| 58643/61904 [7:06:01<1:15:18,  1.39s/it]
 95%|█████████▍| 58644/61904 [7:06:02<1:14:37,  1.37s/it]
 95%|█████████▍| 58645/61904 [7:06:03<1:13:30,  1.35s/it]
 95%|█████████▍| 58646/61904 [7:06:05<1:14:07,  1.36s/it]
 95%|█████████▍| 58647/61904 [7:06:06<1:12:37,  1.34s/it]
 95%|█████████▍| 58648/61904 [7:06:07<1:11:15,  1.31s/it]
 95%|█████████▍| 58649/61904 [7:06:09<1:13:46,  1.36s/it]
 95%|█████████▍| 58650/61904 [7:06:10<1:16:58,  1.42s/it]
 95%|█████████▍| 58651/61904 [7:06:11<1:14:00,  1.37s/it]
 95%|█████████▍| 58652/61904 [7:06:13<1:13:15,  1.35s/it]
 95%|█████████▍| 58653/61904 [7:06:14<1:16:45,  1.42s/it]
 95%|█████████▍| 58654/61904 [7:06:16<1:15:23,  1.39s/it]
 95%|█████████▍| 58655/61904 [7:06:17<1:15:35,  1.40s/it]
 95%|█████████▍| 58656/61904 [7:06:19<1:16:42,  1.42s/it]
 95%|█████████▍| 58657/61904 [7:06:20<1:19:13,  1.46s/it]
 95%|█████████▍| 58658/61904 [7:06:22<1:18:13,  1.45s/it]
 95%|█████████▍| 58659/61904 [7:06:23<1:17:47,  1.44s/it]
 95%|█████████▍| 58660/61904 [7:06:24<1:15:35,  1.40s/it]
                                                         
{'loss': 2.3776, 'learning_rate': 1.0525735770776612e-07, 'epoch': 15.16}

 95%|█████████▍| 58660/61904 [7:06:24<1:15:35,  1.40s/it]
 95%|█████████▍| 58661/61904 [7:06:26<1:14:54,  1.39s/it]
 95%|█████████▍| 58662/61904 [7:06:27<1:12:52,  1.35s/it]
 95%|█████████▍| 58663/61904 [7:06:28<1:12:41,  1.35s/it]
 95%|█████████▍| 58664/61904 [7:06:30<1:12:15,  1.34s/it]
 95%|█████████▍| 58665/61904 [7:06:31<1:11:58,  1.33s/it]
 95%|█████████▍| 58666/61904 [7:06:32<1:12:05,  1.34s/it]
 95%|█████████▍| 58667/61904 [7:06:34<1:14:00,  1.37s/it]
 95%|█████████▍| 58668/61904 [7:06:35<1:14:30,  1.38s/it]
 95%|█████████▍| 58669/61904 [7:06:36<1:14:21,  1.38s/it]
 95%|█████████▍| 58670/61904 [7:06:38<1:13:49,  1.37s/it]
 95%|█████████▍| 58671/61904 [7:06:39<1:15:34,  1.40s/it]
 95%|█████████▍| 58672/61904 [7:06:41<1:17:00,  1.43s/it]
 95%|█████████▍| 58673/61904 [7:06:42<1:19:42,  1.48s/it]
 95%|█████████▍| 58674/61904 [7:06:44<1:18:41,  1.46s/it]
 95%|█████████▍| 58675/61904 [7:06:45<1:17:32,  1.44s/it]
 95%|█████████▍| 58676/61904 [7:06:47<1:17:03,  1.43s/it]
 95%|█████████▍| 58677/61904 [7:06:48<1:15:29,  1.40s/it]
 95%|█████████▍| 58678/61904 [7:06:49<1:15:58,  1.41s/it]
 95%|█████████▍| 58679/61904 [7:06:51<1:17:09,  1.44s/it]
 95%|█████████▍| 58680/61904 [7:06:52<1:17:21,  1.44s/it]
                                                         
{'loss': 2.3837, 'learning_rate': 1.0522494489822378e-07, 'epoch': 15.17}

 95%|█████████▍| 58680/61904 [7:06:52<1:17:21,  1.44s/it]
 95%|█████████▍| 58681/61904 [7:06:54<1:15:04,  1.40s/it]
 95%|█████████▍| 58682/61904 [7:06:55<1:13:42,  1.37s/it]
 95%|█████████▍| 58683/61904 [7:06:56<1:12:20,  1.35s/it]
 95%|█████████▍| 58684/61904 [7:06:58<1:12:17,  1.35s/it]
 95%|█████████▍| 58685/61904 [7:06:59<1:10:58,  1.32s/it]
 95%|█████████▍| 58686/61904 [7:07:00<1:10:30,  1.31s/it]
 95%|█████████▍| 58687/61904 [7:07:01<1:12:05,  1.34s/it]
 95%|█████████▍| 58688/61904 [7:07:03<1:11:06,  1.33s/it]
 95%|█████████▍| 58689/61904 [7:07:04<1:13:55,  1.38s/it]
 95%|█████████▍| 58690/61904 [7:07:06<1:16:23,  1.43s/it]
 95%|█████████▍| 58691/61904 [7:07:07<1:14:55,  1.40s/it]
 95%|█████████▍| 58692/61904 [7:07:09<1:15:07,  1.40s/it]
 95%|█████████▍| 58693/61904 [7:07:10<1:13:45,  1.38s/it]
 95%|█████████▍| 58694/61904 [7:07:11<1:14:09,  1.39s/it]
 95%|█████████▍| 58695/61904 [7:07:13<1:13:15,  1.37s/it]
 95%|█████████▍| 58696/61904 [7:07:14<1:12:36,  1.36s/it]
 95%|█████████▍| 58697/61904 [7:07:15<1:12:59,  1.37s/it]
 95%|█████████▍| 58698/61904 [7:07:17<1:12:41,  1.36s/it]
 95%|█████████▍| 58699/61904 [7:07:18<1:14:14,  1.39s/it]
 95%|█████████▍| 58700/61904 [7:07:19<1:12:35,  1.36s/it]
                                                         
{'loss': 2.3505, 'learning_rate': 1.0519253208868144e-07, 'epoch': 15.17}

 95%|█████████▍| 58700/61904 [7:07:19<1:12:35,  1.36s/it]
 95%|█████████▍| 58701/61904 [7:07:21<1:10:45,  1.33s/it]
 95%|█████████▍| 58702/61904 [7:07:22<1:09:18,  1.30s/it]
 95%|█████████▍| 58703/61904 [7:07:23<1:12:17,  1.35s/it]
 95%|█████████▍| 58704/61904 [7:07:25<1:12:52,  1.37s/it]
 95%|█████████▍| 58705/61904 [7:07:26<1:11:27,  1.34s/it]
 95%|█████████▍| 58706/61904 [7:07:27<1:11:19,  1.34s/it]
 95%|█████████▍| 58707/61904 [7:07:29<1:13:53,  1.39s/it]
 95%|█████████▍| 58708/61904 [7:07:30<1:16:30,  1.44s/it]
 95%|█████████▍| 58709/61904 [7:07:32<1:13:46,  1.39s/it]
 95%|█████████▍| 58710/61904 [7:07:33<1:15:08,  1.41s/it]
 95%|█████████▍| 58711/61904 [7:07:34<1:12:26,  1.36s/it]
 95%|█████████▍| 58712/61904 [7:07:36<1:11:45,  1.35s/it]
 95%|█████████▍| 58713/61904 [7:07:37<1:14:15,  1.40s/it]
 95%|█████████▍| 58714/61904 [7:07:39<1:12:41,  1.37s/it]
 95%|█████████▍| 58715/61904 [7:07:40<1:14:23,  1.40s/it]
 95%|█████████▍| 58716/61904 [7:07:41<1:14:28,  1.40s/it]
 95%|█████████▍| 58717/61904 [7:07:43<1:13:51,  1.39s/it]
 95%|█████████▍| 58718/61904 [7:07:44<1:11:36,  1.35s/it]
 95%|█████████▍| 58719/61904 [7:07:45<1:11:58,  1.36s/it]
 95%|█████████▍| 58720/61904 [7:07:47<1:09:31,  1.31s/it]
                                                         
{'loss': 2.4518, 'learning_rate': 1.0516011927913913e-07, 'epoch': 15.18}

 95%|█████████▍| 58720/61904 [7:07:47<1:09:31,  1.31s/it]
 95%|█████████▍| 58721/61904 [7:07:48<1:09:37,  1.31s/it]
 95%|█████████▍| 58722/61904 [7:07:50<1:14:51,  1.41s/it]
 95%|█████████▍| 58723/61904 [7:07:51<1:13:47,  1.39s/it]
 95%|█████████▍| 58724/61904 [7:07:52<1:12:02,  1.36s/it]
 95%|█████████▍| 58725/61904 [7:07:53<1:10:17,  1.33s/it]
 95%|█████████▍| 58726/61904 [7:07:55<1:08:51,  1.30s/it]
 95%|█████████▍| 58727/61904 [7:07:56<1:08:50,  1.30s/it]
 95%|█████████▍| 58728/61904 [7:07:57<1:08:37,  1.30s/it]
 95%|█████████▍| 58729/61904 [7:07:59<1:10:21,  1.33s/it]
 95%|█████████▍| 58730/61904 [7:08:00<1:11:25,  1.35s/it]
 95%|█████████▍| 58731/61904 [7:08:01<1:09:49,  1.32s/it]
 95%|█████████▍| 58732/61904 [7:08:03<1:10:03,  1.33s/it]
 95%|█████████▍| 58733/61904 [7:08:04<1:12:31,  1.37s/it]
 95%|█████████▍| 58734/61904 [7:08:06<1:11:38,  1.36s/it]
 95%|█████████▍| 58735/61904 [7:08:07<1:12:04,  1.36s/it]
 95%|█████████▍| 58736/61904 [7:08:08<1:14:49,  1.42s/it]
 95%|█████████▍| 58737/61904 [7:08:10<1:14:17,  1.41s/it]
 95%|█████████▍| 58738/61904 [7:08:11<1:16:39,  1.45s/it]
 95%|█████████▍| 58739/61904 [7:08:13<1:15:16,  1.43s/it]
 95%|█████████▍| 58740/61904 [7:08:14<1:14:16,  1.41s/it]
                                                         
{'loss': 2.3862, 'learning_rate': 1.0512770646959679e-07, 'epoch': 15.18}

 95%|█████████▍| 58740/61904 [7:08:14<1:14:16,  1.41s/it]
 95%|█████████▍| 58741/61904 [7:08:15<1:12:10,  1.37s/it]
 95%|█████████▍| 58742/61904 [7:08:17<1:11:15,  1.35s/it]
 95%|█████████▍| 58743/61904 [7:08:18<1:10:50,  1.34s/it]
 95%|█████████▍| 58744/61904 [7:08:19<1:12:55,  1.38s/it]
 95%|█████████▍| 58745/61904 [7:08:21<1:14:24,  1.41s/it]
 95%|█████████▍| 58746/61904 [7:08:22<1:12:30,  1.38s/it]
 95%|█████████▍| 58747/61904 [7:08:24<1:12:33,  1.38s/it]
 95%|█████████▍| 58748/61904 [7:08:25<1:11:40,  1.36s/it]
 95%|█████████▍| 58749/61904 [7:08:26<1:12:20,  1.38s/it]
 95%|█████████▍| 58750/61904 [7:08:28<1:08:59,  1.31s/it]
 95%|█████████▍| 58751/61904 [7:08:29<1:09:45,  1.33s/it]
 95%|█████████▍| 58752/61904 [7:08:30<1:08:57,  1.31s/it]
 95%|█████████▍| 58753/61904 [7:08:32<1:11:09,  1.35s/it]
 95%|█████████▍| 58754/61904 [7:08:33<1:10:42,  1.35s/it]
 95%|█████████▍| 58755/61904 [7:08:34<1:10:07,  1.34s/it]
 95%|█████████▍| 58756/61904 [7:08:36<1:08:43,  1.31s/it]
 95%|█████████▍| 58757/61904 [7:08:37<1:11:06,  1.36s/it]
 95%|█████████▍| 58758/61904 [7:08:39<1:13:38,  1.40s/it]
 95%|█████████▍| 58759/61904 [7:08:40<1:12:01,  1.37s/it]
 95%|█████████▍| 58760/61904 [7:08:41<1:15:15,  1.44s/it]
                                                         
{'loss': 2.3564, 'learning_rate': 1.0509529366005445e-07, 'epoch': 15.19}

 95%|█████████▍| 58760/61904 [7:08:41<1:15:15,  1.44s/it]
 95%|█████████▍| 58761/61904 [7:08:43<1:14:33,  1.42s/it]
 95%|█████████▍| 58762/61904 [7:08:44<1:12:28,  1.38s/it]
 95%|█████████▍| 58763/61904 [7:08:45<1:11:28,  1.37s/it]
 95%|█████████▍| 58764/61904 [7:08:47<1:12:09,  1.38s/it]
 95%|█████████▍| 58765/61904 [7:08:48<1:10:12,  1.34s/it]
 95%|█████████▍| 58766/61904 [7:08:49<1:09:01,  1.32s/it]
 95%|█████████▍| 58767/61904 [7:08:51<1:09:25,  1.33s/it]
 95%|█████████▍| 58768/61904 [7:08:52<1:11:11,  1.36s/it]
 95%|█████████▍| 58769/61904 [7:08:53<1:10:16,  1.35s/it]
 95%|█████████▍| 58770/61904 [7:08:55<1:10:58,  1.36s/it]
 95%|█████████▍| 58771/61904 [7:08:56<1:10:24,  1.35s/it]
 95%|█████████▍| 58772/61904 [7:08:58<1:11:52,  1.38s/it]
 95%|█████████▍| 58773/61904 [7:08:59<1:11:47,  1.38s/it]
 95%|█████████▍| 58774/61904 [7:09:00<1:13:01,  1.40s/it]
 95%|█████████▍| 58775/61904 [7:09:02<1:11:15,  1.37s/it]
 95%|█████████▍| 58776/61904 [7:09:03<1:12:42,  1.39s/it]
 95%|█████████▍| 58777/61904 [7:09:05<1:14:06,  1.42s/it]
 95%|█████████▍| 58778/61904 [7:09:06<1:13:13,  1.41s/it]
 95%|█████████▍| 58779/61904 [7:09:07<1:11:16,  1.37s/it]
 95%|█████████▍| 58780/61904 [7:09:09<1:12:50,  1.40s/it]
                                                         
{'loss': 2.3832, 'learning_rate': 1.0506288085051212e-07, 'epoch': 15.19}

 95%|█████████▍| 58780/61904 [7:09:09<1:12:50,  1.40s/it]
 95%|█████████▍| 58781/61904 [7:09:10<1:14:26,  1.43s/it]
 95%|█████████▍| 58782/61904 [7:09:12<1:12:16,  1.39s/it]
 95%|█████████▍| 58783/61904 [7:09:13<1:14:05,  1.42s/it]
 95%|█████████▍| 58784/61904 [7:09:14<1:12:58,  1.40s/it]
 95%|█████████▍| 58785/61904 [7:09:16<1:12:24,  1.39s/it]
 95%|█████████▍| 58786/61904 [7:09:17<1:11:10,  1.37s/it]
 95%|█████████▍| 58787/61904 [7:09:18<1:10:55,  1.37s/it]
 95%|█████████▍| 58788/61904 [7:09:20<1:11:19,  1.37s/it]
 95%|█████████▍| 58789/61904 [7:09:21<1:11:46,  1.38s/it]
 95%|█████████▍| 58790/61904 [7:09:23<1:11:13,  1.37s/it]
 95%|█████████▍| 58791/61904 [7:09:24<1:14:41,  1.44s/it]
 95%|█████████▍| 58792/61904 [7:09:26<1:13:56,  1.43s/it]
 95%|█████████▍| 58793/61904 [7:09:27<1:11:36,  1.38s/it]
 95%|█████████▍| 58794/61904 [7:09:28<1:12:04,  1.39s/it]
 95%|█████████▍| 58795/61904 [7:09:30<1:13:05,  1.41s/it]
 95%|█████████▍| 58796/61904 [7:09:31<1:14:02,  1.43s/it]
 95%|█████████▍| 58797/61904 [7:09:33<1:12:51,  1.41s/it]
 95%|█████████▍| 58798/61904 [7:09:34<1:12:48,  1.41s/it]
 95%|█████████▍| 58799/61904 [7:09:35<1:12:41,  1.40s/it]
 95%|█████████▍| 58800/61904 [7:09:37<1:11:11,  1.38s/it]
                                                         
{'loss': 2.4699, 'learning_rate': 1.050304680409698e-07, 'epoch': 15.2}

 95%|█████████▍| 58800/61904 [7:09:37<1:11:11,  1.38s/it]
 95%|█████████▍| 58801/61904 [7:09:38<1:10:30,  1.36s/it]
 95%|█████████▍| 58802/61904 [7:09:40<1:13:09,  1.41s/it]
 95%|█████████▍| 58803/61904 [7:09:41<1:11:51,  1.39s/it]
 95%|█████████▍| 58804/61904 [7:09:42<1:11:20,  1.38s/it]
 95%|█████████▍| 58805/61904 [7:09:44<1:11:58,  1.39s/it]
 95%|█████████▍| 58806/61904 [7:09:45<1:13:23,  1.42s/it]
 95%|█████████▍| 58807/61904 [7:09:46<1:11:31,  1.39s/it]
 95%|█████████▍| 58808/61904 [7:09:48<1:09:56,  1.36s/it]
 95%|█████████▌| 58809/61904 [7:09:49<1:11:46,  1.39s/it]
 95%|█████████▌| 58810/61904 [7:09:51<1:12:43,  1.41s/it]
 95%|█████████▌| 58811/61904 [7:09:52<1:11:08,  1.38s/it]
 95%|█████████▌| 58812/61904 [7:09:53<1:11:38,  1.39s/it]
 95%|█████████▌| 58813/61904 [7:09:55<1:11:04,  1.38s/it]
 95%|█████████▌| 58814/61904 [7:09:56<1:14:46,  1.45s/it]
 95%|█████████▌| 58815/61904 [7:09:58<1:12:06,  1.40s/it]
 95%|█████████▌| 58816/61904 [7:09:59<1:10:51,  1.38s/it]
 95%|█████████▌| 58817/61904 [7:10:00<1:08:36,  1.33s/it]
 95%|█████████▌| 58818/61904 [7:10:02<1:08:58,  1.34s/it]
 95%|█████████▌| 58819/61904 [7:10:03<1:08:21,  1.33s/it]
 95%|█████████▌| 58820/61904 [7:10:04<1:10:47,  1.38s/it]
                                                         
{'loss': 2.4436, 'learning_rate': 1.0499805523142747e-07, 'epoch': 15.2}

 95%|█████████▌| 58820/61904 [7:10:04<1:10:47,  1.38s/it]
 95%|█████████▌| 58821/61904 [7:10:06<1:10:12,  1.37s/it]
 95%|█████████▌| 58822/61904 [7:10:07<1:10:27,  1.37s/it]
 95%|█████████▌| 58823/61904 [7:10:09<1:12:30,  1.41s/it]
 95%|█████████▌| 58824/61904 [7:10:10<1:11:09,  1.39s/it]
 95%|█████████▌| 58825/61904 [7:10:11<1:10:28,  1.37s/it]
 95%|█████████▌| 58826/61904 [7:10:13<1:08:36,  1.34s/it]
 95%|█████████▌| 58827/61904 [7:10:14<1:10:35,  1.38s/it]
 95%|█████████▌| 58828/61904 [7:10:16<1:14:50,  1.46s/it]
 95%|█████████▌| 58829/61904 [7:10:17<1:13:17,  1.43s/it]
 95%|█████████▌| 58830/61904 [7:10:18<1:12:29,  1.41s/it]
 95%|█████████▌| 58831/61904 [7:10:20<1:12:28,  1.42s/it]
 95%|█████████▌| 58832/61904 [7:10:21<1:10:54,  1.38s/it]
 95%|█████████▌| 58833/61904 [7:10:22<1:10:33,  1.38s/it]
 95%|█████████▌| 58834/61904 [7:10:24<1:08:11,  1.33s/it]
 95%|█████████▌| 58835/61904 [7:10:25<1:08:42,  1.34s/it]
 95%|█████████▌| 58836/61904 [7:10:26<1:08:21,  1.34s/it]
 95%|█████████▌| 58837/61904 [7:10:28<1:11:56,  1.41s/it]
 95%|█████████▌| 58838/61904 [7:10:29<1:11:14,  1.39s/it]
 95%|█████████▌| 58839/61904 [7:10:31<1:11:09,  1.39s/it]
 95%|█████████▌| 58840/61904 [7:10:32<1:11:08,  1.39s/it]
                                                         
{'loss': 2.3911, 'learning_rate': 1.0496564242188513e-07, 'epoch': 15.21}

 95%|█████████▌| 58840/61904 [7:10:32<1:11:08,  1.39s/it]
 95%|█████████▌| 58841/61904 [7:10:33<1:10:51,  1.39s/it]
 95%|█████████▌| 58842/61904 [7:10:35<1:10:06,  1.37s/it]
 95%|█████████▌| 58843/61904 [7:10:36<1:08:33,  1.34s/it]
 95%|█████████▌| 58844/61904 [7:10:37<1:09:21,  1.36s/it]
 95%|█████████▌| 58845/61904 [7:10:39<1:09:58,  1.37s/it]
 95%|█████████▌| 58846/61904 [7:10:40<1:08:40,  1.35s/it]
 95%|█████████▌| 58847/61904 [7:10:42<1:10:21,  1.38s/it]
 95%|█████████▌| 58848/61904 [7:10:43<1:10:43,  1.39s/it]
 95%|█████████▌| 58849/61904 [7:10:44<1:10:03,  1.38s/it]
 95%|█████████▌| 58850/61904 [7:10:46<1:09:40,  1.37s/it]
 95%|█████████▌| 58851/61904 [7:10:47<1:09:27,  1.37s/it]
 95%|█████████▌| 58852/61904 [7:10:48<1:08:58,  1.36s/it]
 95%|█████████▌| 58853/61904 [7:10:50<1:12:02,  1.42s/it]
 95%|█████████▌| 58854/61904 [7:10:51<1:12:45,  1.43s/it]
 95%|█████████▌| 58855/61904 [7:10:53<1:14:39,  1.47s/it]
 95%|█████████▌| 58856/61904 [7:10:55<1:15:14,  1.48s/it]
 95%|█████████▌| 58857/61904 [7:10:56<1:12:47,  1.43s/it]
 95%|█████████▌| 58858/61904 [7:10:57<1:13:07,  1.44s/it]
 95%|█████████▌| 58859/61904 [7:10:59<1:13:24,  1.45s/it]
 95%|█████████▌| 58860/61904 [7:11:00<1:11:40,  1.41s/it]
                                                         
{'loss': 2.3914, 'learning_rate': 1.0493322961234279e-07, 'epoch': 15.21}

 95%|█████████▌| 58860/61904 [7:11:00<1:11:40,  1.41s/it]
 95%|█████████▌| 58861/61904 [7:11:01<1:10:46,  1.40s/it]
 95%|█████████▌| 58862/61904 [7:11:03<1:10:10,  1.38s/it]
 95%|█████████▌| 58863/61904 [7:11:04<1:09:31,  1.37s/it]
 95%|█████████▌| 58864/61904 [7:11:06<1:12:20,  1.43s/it]
 95%|█████████▌| 58865/61904 [7:11:07<1:12:01,  1.42s/it]
 95%|█████████▌| 58866/61904 [7:11:08<1:11:11,  1.41s/it]
 95%|█████████▌| 58867/61904 [7:11:10<1:09:54,  1.38s/it]
 95%|█████████▌| 58868/61904 [7:11:11<1:08:16,  1.35s/it]
 95%|█████████▌| 58869/61904 [7:11:13<1:10:12,  1.39s/it]
 95%|█████████▌| 58870/61904 [7:11:14<1:10:25,  1.39s/it]
 95%|█████████▌| 58871/61904 [7:11:15<1:09:06,  1.37s/it]
 95%|█████████▌| 58872/61904 [7:11:17<1:09:11,  1.37s/it]
 95%|█████████▌| 58873/61904 [7:11:18<1:09:30,  1.38s/it]
 95%|█████████▌| 58874/61904 [7:11:19<1:10:26,  1.39s/it]
 95%|█████████▌| 58875/61904 [7:11:21<1:11:04,  1.41s/it]
 95%|█████████▌| 58876/61904 [7:11:22<1:10:11,  1.39s/it]
 95%|█████████▌| 58877/61904 [7:11:24<1:11:31,  1.42s/it]
 95%|█████████▌| 58878/61904 [7:11:25<1:09:42,  1.38s/it]
 95%|█████████▌| 58879/61904 [7:11:26<1:08:23,  1.36s/it]
 95%|█████████▌| 58880/61904 [7:11:28<1:09:23,  1.38s/it]
                                                         
{'loss': 2.454, 'learning_rate': 1.0490081680280048e-07, 'epoch': 15.22}

 95%|█████████▌| 58880/61904 [7:11:28<1:09:23,  1.38s/it]
 95%|█████████▌| 58881/61904 [7:11:29<1:07:16,  1.34s/it]
 95%|█████████▌| 58882/61904 [7:11:30<1:07:23,  1.34s/it]
 95%|█████████▌| 58883/61904 [7:11:32<1:06:53,  1.33s/it]
 95%|█████████▌| 58884/61904 [7:11:33<1:05:34,  1.30s/it]
 95%|█████████▌| 58885/61904 [7:11:34<1:06:12,  1.32s/it]
 95%|█████████▌| 58886/61904 [7:11:36<1:06:51,  1.33s/it]
 95%|█████████▌| 58887/61904 [7:11:37<1:06:01,  1.31s/it]
 95%|█████████▌| 58888/61904 [7:11:38<1:07:27,  1.34s/it]
 95%|█████████▌| 58889/61904 [7:11:40<1:06:51,  1.33s/it]
 95%|█████████▌| 58890/61904 [7:11:41<1:05:54,  1.31s/it]
 95%|█████████▌| 58891/61904 [7:11:42<1:09:10,  1.38s/it]
 95%|█████████▌| 58892/61904 [7:11:44<1:09:34,  1.39s/it]
 95%|█████████▌| 58893/61904 [7:11:45<1:08:49,  1.37s/it]
 95%|█████████▌| 58894/61904 [7:11:46<1:07:26,  1.34s/it]
 95%|█████████▌| 58895/61904 [7:11:48<1:08:38,  1.37s/it]
 95%|█████████▌| 58896/61904 [7:11:49<1:06:49,  1.33s/it]
 95%|█████████▌| 58897/61904 [7:11:50<1:06:12,  1.32s/it]
 95%|█████████▌| 58898/61904 [7:11:52<1:08:35,  1.37s/it]
 95%|█████████▌| 58899/61904 [7:11:53<1:09:26,  1.39s/it]
 95%|█████████▌| 58900/61904 [7:11:55<1:07:48,  1.35s/it]
                                                         
{'loss': 2.424, 'learning_rate': 1.0486840399325814e-07, 'epoch': 15.22}

 95%|█████████▌| 58900/61904 [7:11:55<1:07:48,  1.35s/it]
 95%|█████████▌| 58901/61904 [7:11:56<1:05:47,  1.31s/it]
 95%|█████████▌| 58902/61904 [7:11:57<1:06:13,  1.32s/it]
 95%|█████████▌| 58903/61904 [7:11:59<1:06:35,  1.33s/it]
 95%|█████████▌| 58904/61904 [7:12:00<1:09:09,  1.38s/it]
 95%|█████████▌| 58905/61904 [7:12:01<1:07:02,  1.34s/it]
 95%|█████████▌| 58906/61904 [7:12:03<1:09:02,  1.38s/it]
 95%|█████████▌| 58907/61904 [7:12:04<1:07:49,  1.36s/it]
 95%|█████████▌| 58908/61904 [7:12:06<1:10:16,  1.41s/it]
 95%|█████████▌| 58909/61904 [7:12:07<1:08:41,  1.38s/it]
 95%|█████████▌| 58910/61904 [7:12:08<1:08:13,  1.37s/it]
 95%|█████████▌| 58911/61904 [7:12:10<1:07:31,  1.35s/it]
 95%|█████████▌| 58912/61904 [7:12:11<1:07:17,  1.35s/it]
 95%|█████████▌| 58913/61904 [7:12:12<1:10:43,  1.42s/it]
 95%|█████████▌| 58914/61904 [7:12:14<1:09:41,  1.40s/it]
 95%|█████████▌| 58915/61904 [7:12:15<1:12:27,  1.45s/it]
 95%|█████████▌| 58916/61904 [7:12:17<1:13:41,  1.48s/it]
 95%|█████████▌| 58917/61904 [7:12:18<1:12:50,  1.46s/it]
 95%|█████████▌| 58918/61904 [7:12:20<1:10:31,  1.42s/it]
 95%|█████████▌| 58919/61904 [7:12:21<1:09:20,  1.39s/it]
 95%|█████████▌| 58920/61904 [7:12:22<1:07:23,  1.36s/it]
                                                         
{'loss': 2.4053, 'learning_rate': 1.048359911837158e-07, 'epoch': 15.23}

 95%|█████████▌| 58920/61904 [7:12:22<1:07:23,  1.36s/it]
 95%|█████████▌| 58921/61904 [7:12:24<1:07:03,  1.35s/it]
 95%|█████████▌| 58922/61904 [7:12:25<1:07:01,  1.35s/it]
 95%|█████████▌| 58923/61904 [7:12:26<1:08:15,  1.37s/it]
 95%|█████████▌| 58924/61904 [7:12:28<1:08:36,  1.38s/it]
 95%|█████████▌| 58925/61904 [7:12:29<1:06:32,  1.34s/it]
 95%|█████████▌| 58926/61904 [7:12:30<1:08:27,  1.38s/it]
 95%|█████████▌| 58927/61904 [7:12:32<1:07:09,  1.35s/it]
 95%|█████████▌| 58928/61904 [7:12:33<1:06:30,  1.34s/it]
 95%|█████████▌| 58929/61904 [7:12:34<1:07:04,  1.35s/it]
 95%|█████████▌| 58930/61904 [7:12:36<1:07:41,  1.37s/it]
 95%|█████████▌| 58931/61904 [7:12:37<1:08:03,  1.37s/it]
 95%|█████████▌| 58932/61904 [7:12:39<1:09:46,  1.41s/it]
 95%|█████████▌| 58933/61904 [7:12:40<1:08:17,  1.38s/it]
 95%|█████████▌| 58934/61904 [7:12:41<1:08:59,  1.39s/it]
 95%|█████████▌| 58935/61904 [7:12:43<1:08:10,  1.38s/it]
 95%|█████████▌| 58936/61904 [7:12:44<1:08:32,  1.39s/it]
 95%|█████████▌| 58937/61904 [7:12:46<1:08:42,  1.39s/it]
 95%|█████████▌| 58938/61904 [7:12:47<1:06:19,  1.34s/it]
 95%|█████████▌| 58939/61904 [7:12:48<1:06:23,  1.34s/it]
 95%|█████████▌| 58940/61904 [7:12:50<1:07:57,  1.38s/it]
                                                         
{'loss': 2.41, 'learning_rate': 1.0480357837417349e-07, 'epoch': 15.23}

 95%|█████████▌| 58940/61904 [7:12:50<1:07:57,  1.38s/it]
 95%|█████████▌| 58941/61904 [7:12:51<1:07:49,  1.37s/it]
 95%|█████████▌| 58942/61904 [7:12:52<1:07:25,  1.37s/it]
 95%|█████████▌| 58943/61904 [7:12:54<1:07:57,  1.38s/it]
 95%|█████████▌| 58944/61904 [7:12:55<1:06:27,  1.35s/it]
 95%|█████████▌| 58945/61904 [7:12:56<1:06:57,  1.36s/it]
 95%|█████████▌| 58946/61904 [7:12:58<1:07:17,  1.36s/it]
 95%|█████████▌| 58947/61904 [7:12:59<1:06:53,  1.36s/it]
 95%|█████████▌| 58948/61904 [7:13:00<1:05:44,  1.33s/it]
 95%|█████████▌| 58949/61904 [7:13:02<1:07:21,  1.37s/it]
 95%|█████████▌| 58950/61904 [7:13:03<1:05:54,  1.34s/it]
 95%|█████████▌| 58951/61904 [7:13:05<1:09:21,  1.41s/it]
 95%|█████████▌| 58952/61904 [7:13:06<1:08:15,  1.39s/it]
 95%|█████████▌| 58953/61904 [7:13:07<1:07:51,  1.38s/it]
 95%|█████████▌| 58954/61904 [7:13:09<1:10:34,  1.44s/it]
 95%|█████████▌| 58955/61904 [7:13:10<1:08:36,  1.40s/it]
 95%|█████████▌| 58956/61904 [7:13:12<1:07:37,  1.38s/it]
 95%|█████████▌| 58957/61904 [7:13:13<1:07:31,  1.37s/it]
 95%|█████████▌| 58958/61904 [7:13:14<1:07:19,  1.37s/it]
 95%|█████████▌| 58959/61904 [7:13:16<1:08:02,  1.39s/it]
 95%|█████████▌| 58960/61904 [7:13:17<1:06:07,  1.35s/it]
                                                         
{'loss': 2.4504, 'learning_rate': 1.0477116556463115e-07, 'epoch': 15.24}

 95%|█████████▌| 58960/61904 [7:13:17<1:06:07,  1.35s/it]
 95%|█████████▌| 58961/61904 [7:13:18<1:07:03,  1.37s/it]
 95%|█████████▌| 58962/61904 [7:13:20<1:05:55,  1.34s/it]
 95%|█████████▌| 58963/61904 [7:13:21<1:05:58,  1.35s/it]
 95%|█████████▌| 58964/61904 [7:13:23<1:07:12,  1.37s/it]
 95%|█████████▌| 58965/61904 [7:13:24<1:07:38,  1.38s/it]
 95%|█████████▌| 58966/61904 [7:13:25<1:08:03,  1.39s/it]
 95%|█████████▌| 58967/61904 [7:13:27<1:07:33,  1.38s/it]
 95%|█████████▌| 58968/61904 [7:13:28<1:05:28,  1.34s/it]
 95%|█████████▌| 58969/61904 [7:13:29<1:07:06,  1.37s/it]
 95%|█████████▌| 58970/61904 [7:13:31<1:06:16,  1.36s/it]
 95%|█████████▌| 58971/61904 [7:13:32<1:06:21,  1.36s/it]
 95%|█████████▌| 58972/61904 [7:13:33<1:07:03,  1.37s/it]
 95%|█████████▌| 58973/61904 [7:13:35<1:07:53,  1.39s/it]
 95%|█████████▌| 58974/61904 [7:13:36<1:06:39,  1.37s/it]
 95%|█████████▌| 58975/61904 [7:13:38<1:09:55,  1.43s/it]
 95%|█████████▌| 58976/61904 [7:13:39<1:08:12,  1.40s/it]
 95%|█████████▌| 58977/61904 [7:13:41<1:09:53,  1.43s/it]
 95%|█████████▌| 58978/61904 [7:13:42<1:08:02,  1.40s/it]
 95%|█████████▌| 58979/61904 [7:13:43<1:07:19,  1.38s/it]
 95%|█████████▌| 58980/61904 [7:13:45<1:05:08,  1.34s/it]
                                                         
{'loss': 2.4132, 'learning_rate': 1.0473875275508881e-07, 'epoch': 15.24}

 95%|█████████▌| 58980/61904 [7:13:45<1:05:08,  1.34s/it]
 95%|█████████▌| 58981/61904 [7:13:46<1:05:03,  1.34s/it]
 95%|█████████▌| 58982/61904 [7:13:47<1:07:52,  1.39s/it]
 95%|█████████▌| 58983/61904 [7:13:49<1:06:55,  1.37s/it]
 95%|█████████▌| 58984/61904 [7:13:50<1:07:22,  1.38s/it]
 95%|█████████▌| 58985/61904 [7:13:51<1:06:53,  1.37s/it]
 95%|█████████▌| 58986/61904 [7:13:53<1:05:02,  1.34s/it]
 95%|█████████▌| 58987/61904 [7:13:54<1:03:14,  1.30s/it]
 95%|█████████▌| 58988/61904 [7:13:55<1:03:56,  1.32s/it]
 95%|█████████▌| 58989/61904 [7:13:57<1:04:50,  1.33s/it]
 95%|█████████▌| 58990/61904 [7:13:58<1:05:00,  1.34s/it]
 95%|█████████▌| 58991/61904 [7:13:59<1:05:38,  1.35s/it]
 95%|█████████▌| 58992/61904 [7:14:01<1:04:46,  1.33s/it]
 95%|█████████▌| 58993/61904 [7:14:02<1:04:22,  1.33s/it]
 95%|█████████▌| 58994/61904 [7:14:03<1:05:20,  1.35s/it]
 95%|█████████▌| 58995/61904 [7:14:05<1:04:15,  1.33s/it]
 95%|█████████▌| 58996/61904 [7:14:06<1:06:49,  1.38s/it]
 95%|█████████▌| 58997/61904 [7:14:07<1:05:56,  1.36s/it]
 95%|█████████▌| 58998/61904 [7:14:09<1:06:44,  1.38s/it]
 95%|█████████▌| 58999/61904 [7:14:10<1:05:18,  1.35s/it]
 95%|█████████▌| 59000/61904 [7:14:12<1:06:00,  1.36s/it]
                                                         
{'loss': 2.4664, 'learning_rate': 1.0470633994554648e-07, 'epoch': 15.25}

 95%|█████████▌| 59000/61904 [7:14:12<1:06:00,  1.36s/it]
 95%|█████████▌| 59001/61904 [7:14:13<1:05:50,  1.36s/it]
 95%|█████████▌| 59002/61904 [7:14:14<1:05:09,  1.35s/it]
 95%|█████████▌| 59003/61904 [7:14:16<1:07:35,  1.40s/it]
 95%|█████████▌| 59004/61904 [7:14:17<1:04:50,  1.34s/it]
 95%|█████████▌| 59005/61904 [7:14:18<1:06:07,  1.37s/it]
 95%|█████████▌| 59006/61904 [7:14:20<1:06:37,  1.38s/it]
 95%|█████████▌| 59007/61904 [7:14:21<1:04:44,  1.34s/it]
 95%|█████████▌| 59008/61904 [7:14:22<1:03:39,  1.32s/it]
 95%|█████████▌| 59009/61904 [7:14:24<1:06:12,  1.37s/it]
 95%|█████████▌| 59010/61904 [7:14:25<1:08:57,  1.43s/it]
 95%|█████████▌| 59011/61904 [7:14:27<1:07:39,  1.40s/it]
 95%|█████████▌| 59012/61904 [7:14:28<1:07:59,  1.41s/it]
 95%|█████████▌| 59013/61904 [7:14:30<1:07:10,  1.39s/it]
 95%|█████████▌| 59014/61904 [7:14:31<1:06:45,  1.39s/it]
 95%|█████████▌| 59015/61904 [7:14:32<1:06:39,  1.38s/it]
 95%|█████████▌| 59016/61904 [7:14:34<1:08:18,  1.42s/it]
 95%|█████████▌| 59017/61904 [7:14:35<1:05:50,  1.37s/it]
 95%|█████████▌| 59018/61904 [7:14:36<1:05:58,  1.37s/it]
 95%|█████████▌| 59019/61904 [7:14:38<1:04:28,  1.34s/it]
 95%|█████████▌| 59020/61904 [7:14:39<1:07:04,  1.40s/it]
                                                         
{'loss': 2.4222, 'learning_rate': 1.0467392713600416e-07, 'epoch': 15.25}

 95%|█████████▌| 59020/61904 [7:14:39<1:07:04,  1.40s/it]
 95%|█████████▌| 59021/61904 [7:14:40<1:05:09,  1.36s/it]
 95%|█████████▌| 59022/61904 [7:14:42<1:05:01,  1.35s/it]
 95%|█████████▌| 59023/61904 [7:14:43<1:06:41,  1.39s/it]
 95%|█████████▌| 59024/61904 [7:14:45<1:05:36,  1.37s/it]
 95%|█████████▌| 59025/61904 [7:14:46<1:06:56,  1.39s/it]
 95%|█████████▌| 59026/61904 [7:14:47<1:07:29,  1.41s/it]
 95%|█████████▌| 59027/61904 [7:14:49<1:08:31,  1.43s/it]
 95%|█████████▌| 59028/61904 [7:14:50<1:06:02,  1.38s/it]
 95%|█████████▌| 59029/61904 [7:14:52<1:05:32,  1.37s/it]
 95%|█████████▌| 59030/61904 [7:14:53<1:04:49,  1.35s/it]
 95%|█████████▌| 59031/61904 [7:14:54<1:06:07,  1.38s/it]
 95%|█████████▌| 59032/61904 [7:14:56<1:06:07,  1.38s/it]
 95%|█████████▌| 59033/61904 [7:14:57<1:04:49,  1.35s/it]
 95%|█████████▌| 59034/61904 [7:14:58<1:05:46,  1.38s/it]
 95%|█████████▌| 59035/61904 [7:15:00<1:04:35,  1.35s/it]
 95%|█████████▌| 59036/61904 [7:15:01<1:05:37,  1.37s/it]
 95%|█████████▌| 59037/61904 [7:15:03<1:07:41,  1.42s/it]
 95%|█████████▌| 59038/61904 [7:15:04<1:07:45,  1.42s/it]
 95%|█████████▌| 59039/61904 [7:15:06<1:08:44,  1.44s/it]
 95%|█████████▌| 59040/61904 [7:15:07<1:07:43,  1.42s/it]
                                                         
{'loss': 2.4471, 'learning_rate': 1.0464151432646183e-07, 'epoch': 15.26}

 95%|█████████▌| 59040/61904 [7:15:07<1:07:43,  1.42s/it]
 95%|█████████▌| 59041/61904 [7:15:08<1:08:07,  1.43s/it]
 95%|█████████▌| 59042/61904 [7:15:10<1:07:53,  1.42s/it]
 95%|█████████▌| 59043/61904 [7:15:11<1:08:39,  1.44s/it]
 95%|█████████▌| 59044/61904 [7:15:13<1:09:52,  1.47s/it]
 95%|█████████▌| 59045/61904 [7:15:14<1:08:06,  1.43s/it]
 95%|█████████▌| 59046/61904 [7:15:15<1:06:28,  1.40s/it]
 95%|█████████▌| 59047/61904 [7:15:17<1:05:53,  1.38s/it]
 95%|█████████▌| 59048/61904 [7:15:18<1:06:16,  1.39s/it]
 95%|█████████▌| 59049/61904 [7:15:20<1:04:56,  1.36s/it]
 95%|█████████▌| 59050/61904 [7:15:21<1:03:57,  1.34s/it]
 95%|█████████▌| 59051/61904 [7:15:22<1:04:02,  1.35s/it]
 95%|█████████▌| 59052/61904 [7:15:23<1:02:58,  1.32s/it]
 95%|█████████▌| 59053/61904 [7:15:25<1:07:08,  1.41s/it]
 95%|█████████▌| 59054/61904 [7:15:26<1:05:14,  1.37s/it]
 95%|█████████▌| 59055/61904 [7:15:28<1:03:11,  1.33s/it]
 95%|█████████▌| 59056/61904 [7:15:29<1:05:02,  1.37s/it]
 95%|█████████▌| 59057/61904 [7:15:30<1:05:10,  1.37s/it]
 95%|█████████▌| 59058/61904 [7:15:32<1:06:44,  1.41s/it]
 95%|█████████▌| 59059/61904 [7:15:33<1:04:25,  1.36s/it]
 95%|█████████▌| 59060/61904 [7:15:34<1:03:13,  1.33s/it]
                                                         
{'loss': 2.402, 'learning_rate': 1.0460910151691949e-07, 'epoch': 15.26}

 95%|█████████▌| 59060/61904 [7:15:34<1:03:13,  1.33s/it]
 95%|█████████▌| 59061/61904 [7:15:36<1:02:33,  1.32s/it]
 95%|█████████▌| 59062/61904 [7:15:37<1:03:41,  1.34s/it]
 95%|█████████▌| 59063/61904 [7:15:39<1:06:58,  1.41s/it]
 95%|█████████▌| 59064/61904 [7:15:40<1:05:32,  1.38s/it]
 95%|█████████▌| 59065/61904 [7:15:41<1:04:35,  1.36s/it]
 95%|█████████▌| 59066/61904 [7:15:43<1:03:26,  1.34s/it]
 95%|█████████▌| 59067/61904 [7:15:44<1:05:24,  1.38s/it]
 95%|█████████▌| 59068/61904 [7:15:45<1:04:43,  1.37s/it]
 95%|█████████▌| 59069/61904 [7:15:47<1:03:25,  1.34s/it]
 95%|█████████▌| 59070/61904 [7:15:48<1:04:12,  1.36s/it]
 95%|█████████▌| 59071/61904 [7:15:50<1:05:18,  1.38s/it]
 95%|█████████▌| 59072/61904 [7:15:51<1:02:37,  1.33s/it]
 95%|█████████▌| 59073/61904 [7:15:52<1:04:38,  1.37s/it]
 95%|█████████▌| 59074/61904 [7:15:54<1:06:52,  1.42s/it]
 95%|█████████▌| 59075/61904 [7:15:55<1:04:27,  1.37s/it]
 95%|█████████▌| 59076/61904 [7:15:56<1:03:33,  1.35s/it]
 95%|█████████▌| 59077/61904 [7:15:58<1:06:35,  1.41s/it]
 95%|█████████▌| 59078/61904 [7:15:59<1:06:50,  1.42s/it]
 95%|█████████▌| 59079/61904 [7:16:01<1:06:13,  1.41s/it]
 95%|█████████▌| 59080/61904 [7:16:02<1:04:26,  1.37s/it]
                                                         
{'loss': 2.3928, 'learning_rate': 1.0457668870737715e-07, 'epoch': 15.27}

 95%|█████████▌| 59080/61904 [7:16:02<1:04:26,  1.37s/it]
 95%|█████████▌| 59081/61904 [7:16:03<1:06:18,  1.41s/it]
 95%|█████████▌| 59082/61904 [7:16:05<1:06:12,  1.41s/it]
 95%|█████████▌| 59083/61904 [7:16:06<1:05:43,  1.40s/it]
 95%|█████████▌| 59084/61904 [7:16:08<1:04:53,  1.38s/it]
 95%|█████████▌| 59085/61904 [7:16:09<1:03:26,  1.35s/it]
 95%|█████████▌| 59086/61904 [7:16:10<1:04:22,  1.37s/it]
 95%|█████████▌| 59087/61904 [7:16:12<1:06:25,  1.41s/it]
 95%|█████████▌| 59088/61904 [7:16:13<1:04:49,  1.38s/it]
 95%|█████████▌| 59089/61904 [7:16:14<1:04:16,  1.37s/it]
 95%|█████████▌| 59090/61904 [7:16:16<1:03:40,  1.36s/it]
 95%|█████████▌| 59091/61904 [7:16:17<1:04:01,  1.37s/it]
 95%|█████████▌| 59092/61904 [7:16:19<1:06:50,  1.43s/it]
 95%|█████████▌| 59093/61904 [7:16:20<1:04:53,  1.39s/it]
 95%|█████████▌| 59094/61904 [7:16:21<1:04:13,  1.37s/it]
 95%|█████████▌| 59095/61904 [7:16:23<1:04:47,  1.38s/it]
 95%|█████████▌| 59096/61904 [7:16:24<1:04:14,  1.37s/it]
 95%|█████████▌| 59097/61904 [7:16:25<1:03:22,  1.35s/it]
 95%|█████████▌| 59098/61904 [7:16:27<1:05:35,  1.40s/it]
 95%|█████████▌| 59099/61904 [7:16:28<1:03:50,  1.37s/it]
 95%|█████████▌| 59100/61904 [7:16:30<1:03:09,  1.35s/it]
                                                         
{'loss': 2.3765, 'learning_rate': 1.0454427589783484e-07, 'epoch': 15.27}

 95%|█████████▌| 59100/61904 [7:16:30<1:03:09,  1.35s/it]
 95%|█████████▌| 59101/61904 [7:16:31<1:05:14,  1.40s/it]
 95%|█████████▌| 59102/61904 [7:16:32<1:04:51,  1.39s/it]
 95%|█████████▌| 59103/61904 [7:16:34<1:04:46,  1.39s/it]
 95%|█████████▌| 59104/61904 [7:16:35<1:05:46,  1.41s/it]
 95%|█████████▌| 59105/61904 [7:16:37<1:04:32,  1.38s/it]
 95%|█████████▌| 59106/61904 [7:16:38<1:05:34,  1.41s/it]
 95%|█████████▌| 59107/61904 [7:16:39<1:03:13,  1.36s/it]
 95%|█████████▌| 59108/61904 [7:16:41<1:05:05,  1.40s/it]
 95%|█████████▌| 59109/61904 [7:16:42<1:06:19,  1.42s/it]
 95%|█████████▌| 59110/61904 [7:16:44<1:05:58,  1.42s/it]
 95%|█████████▌| 59111/61904 [7:16:45<1:05:01,  1.40s/it]
 95%|█████████▌| 59112/61904 [7:16:46<1:03:53,  1.37s/it]
 95%|█████████▌| 59113/61904 [7:16:48<1:05:18,  1.40s/it]
 95%|█████████▌| 59114/61904 [7:16:49<1:04:36,  1.39s/it]
 95%|█████████▌| 59115/61904 [7:16:51<1:03:39,  1.37s/it]
 95%|█████████▌| 59116/61904 [7:16:52<1:05:18,  1.41s/it]
 95%|█████████▌| 59117/61904 [7:16:53<1:04:28,  1.39s/it]
 95%|█████████▌| 59118/61904 [7:16:55<1:04:26,  1.39s/it]
 96%|█████████▌| 59119/61904 [7:16:56<1:05:43,  1.42s/it]
 96%|█████████▌| 59120/61904 [7:16:58<1:05:31,  1.41s/it]
                                                         
{'loss': 2.3731, 'learning_rate': 1.045118630882925e-07, 'epoch': 15.28}

 96%|█████████▌| 59120/61904 [7:16:58<1:05:31,  1.41s/it]
 96%|█████████▌| 59121/61904 [7:16:59<1:05:03,  1.40s/it]
 96%|█████████▌| 59122/61904 [7:17:00<1:05:28,  1.41s/it]
 96%|█████████▌| 59123/61904 [7:17:02<1:07:16,  1.45s/it]
 96%|█████████▌| 59124/61904 [7:17:03<1:07:53,  1.47s/it]
 96%|█████████▌| 59125/61904 [7:17:05<1:08:26,  1.48s/it]
 96%|█████████▌| 59126/61904 [7:17:06<1:06:53,  1.44s/it]
 96%|█████████▌| 59127/61904 [7:17:08<1:05:18,  1.41s/it]
 96%|█████████▌| 59128/61904 [7:17:09<1:03:46,  1.38s/it]
 96%|█████████▌| 59129/61904 [7:17:10<1:04:19,  1.39s/it]
 96%|█████████▌| 59130/61904 [7:17:12<1:04:34,  1.40s/it]
 96%|█████████▌| 59131/61904 [7:17:13<1:04:34,  1.40s/it]
 96%|█████████▌| 59132/61904 [7:17:14<1:02:18,  1.35s/it]
 96%|█████████▌| 59133/61904 [7:17:16<1:03:01,  1.36s/it]
 96%|█████████▌| 59134/61904 [7:17:17<1:03:25,  1.37s/it]
 96%|█████████▌| 59135/61904 [7:17:19<1:05:06,  1.41s/it]
 96%|█████████▌| 59136/61904 [7:17:20<1:04:07,  1.39s/it]
 96%|█████████▌| 59137/61904 [7:17:21<1:04:12,  1.39s/it]
 96%|█████████▌| 59138/61904 [7:17:23<1:03:18,  1.37s/it]
 96%|█████████▌| 59139/61904 [7:17:24<1:04:40,  1.40s/it]
 96%|█████████▌| 59140/61904 [7:17:26<1:04:34,  1.40s/it]
                                                         
{'loss': 2.4251, 'learning_rate': 1.0447945027875016e-07, 'epoch': 15.29}

 96%|█████████▌| 59140/61904 [7:17:26<1:04:34,  1.40s/it]
 96%|█████████▌| 59141/61904 [7:17:27<1:05:11,  1.42s/it]
 96%|█████████▌| 59142/61904 [7:17:29<1:05:35,  1.43s/it]
 96%|█████████▌| 59143/61904 [7:17:30<1:05:06,  1.41s/it]
 96%|█████████▌| 59144/61904 [7:17:31<1:03:32,  1.38s/it]
 96%|█████████▌| 59145/61904 [7:17:33<1:01:51,  1.35s/it]
 96%|█████████▌| 59146/61904 [7:17:34<1:00:02,  1.31s/it]
 96%|█████████▌| 59147/61904 [7:17:35<1:02:05,  1.35s/it]
 96%|█████████▌| 59148/61904 [7:17:37<1:01:26,  1.34s/it]
 96%|█████████▌| 59149/61904 [7:17:38<1:02:03,  1.35s/it]
 96%|█████████▌| 59150/61904 [7:17:39<1:01:48,  1.35s/it]
 96%|█████████▌| 59151/61904 [7:17:41<1:02:14,  1.36s/it]
 96%|█████████▌| 59152/61904 [7:17:42<1:03:04,  1.38s/it]
 96%|█████████▌| 59153/61904 [7:17:43<1:04:17,  1.40s/it]
 96%|█████████▌| 59154/61904 [7:17:45<1:03:53,  1.39s/it]
 96%|█████████▌| 59155/61904 [7:17:46<1:02:20,  1.36s/it]
 96%|█████████▌| 59156/61904 [7:17:48<1:05:02,  1.42s/it]
 96%|█████████▌| 59157/61904 [7:17:49<1:02:13,  1.36s/it]
 96%|█████████▌| 59158/61904 [7:17:50<1:04:40,  1.41s/it]
 96%|█████████▌| 59159/61904 [7:17:52<1:02:21,  1.36s/it]
 96%|█████████▌| 59160/61904 [7:17:53<1:04:11,  1.40s/it]
                                                         
{'loss': 2.4078, 'learning_rate': 1.0444703746920782e-07, 'epoch': 15.29}

 96%|█████████▌| 59160/61904 [7:17:53<1:04:11,  1.40s/it]
 96%|█████████▌| 59161/61904 [7:17:55<1:05:08,  1.42s/it]
 96%|█████████▌| 59162/61904 [7:17:56<1:07:08,  1.47s/it]
 96%|█████████▌| 59163/61904 [7:17:58<1:04:31,  1.41s/it]
 96%|█████████▌| 59164/61904 [7:17:59<1:05:17,  1.43s/it]
 96%|█████████▌| 59165/61904 [7:18:00<1:03:03,  1.38s/it]
 96%|█████████▌| 59166/61904 [7:18:02<1:02:21,  1.37s/it]
 96%|█████████▌| 59167/61904 [7:18:03<1:03:40,  1.40s/it]
 96%|█████████▌| 59168/61904 [7:18:04<1:02:40,  1.37s/it]
 96%|█████████▌| 59169/61904 [7:18:06<1:01:11,  1.34s/it]
 96%|█████████▌| 59170/61904 [7:18:07<1:03:00,  1.38s/it]
 96%|█████████▌| 59171/61904 [7:18:08<1:02:33,  1.37s/it]
 96%|█████████▌| 59172/61904 [7:18:10<1:01:14,  1.34s/it]
 96%|█████████▌| 59173/61904 [7:18:11<1:01:07,  1.34s/it]
 96%|█████████▌| 59174/61904 [7:18:12<1:00:43,  1.33s/it]
 96%|█████████▌| 59175/61904 [7:18:14<1:02:32,  1.37s/it]
 96%|█████████▌| 59176/61904 [7:18:15<1:04:10,  1.41s/it]
 96%|█████████▌| 59177/61904 [7:18:17<1:03:26,  1.40s/it]
 96%|█████████▌| 59178/61904 [7:18:18<1:03:07,  1.39s/it]
 96%|█████████▌| 59179/61904 [7:18:19<1:02:59,  1.39s/it]
 96%|█████████▌| 59180/61904 [7:18:21<1:03:05,  1.39s/it]
                                                         
{'loss': 2.3711, 'learning_rate': 1.0441462465966551e-07, 'epoch': 15.3}

 96%|█████████▌| 59180/61904 [7:18:21<1:03:05,  1.39s/it]
 96%|█████████▌| 59181/61904 [7:18:22<1:02:34,  1.38s/it]
 96%|█████████▌| 59182/61904 [7:18:24<1:01:44,  1.36s/it]
 96%|█████████▌| 59183/61904 [7:18:25<1:02:54,  1.39s/it]
 96%|█████████▌| 59184/61904 [7:18:26<1:01:37,  1.36s/it]
 96%|█████████▌| 59185/61904 [7:18:28<1:03:57,  1.41s/it]
 96%|█████████▌| 59186/61904 [7:18:29<1:02:59,  1.39s/it]
 96%|█████████▌| 59187/61904 [7:18:31<1:03:23,  1.40s/it]
 96%|█████████▌| 59188/61904 [7:18:32<1:02:09,  1.37s/it]
 96%|█████████▌| 59189/61904 [7:18:33<1:02:06,  1.37s/it]
 96%|█████████▌| 59190/61904 [7:18:35<1:02:20,  1.38s/it]
 96%|█████████▌| 59191/61904 [7:18:36<1:01:23,  1.36s/it]
 96%|█████████▌| 59192/61904 [7:18:37<1:00:55,  1.35s/it]
 96%|█████████▌| 59193/61904 [7:18:39<1:02:54,  1.39s/it]
 96%|█████████▌| 59194/61904 [7:18:40<1:02:55,  1.39s/it]
 96%|█████████▌| 59195/61904 [7:18:41<1:01:18,  1.36s/it]
 96%|█████████▌| 59196/61904 [7:18:43<1:01:33,  1.36s/it]
 96%|█████████▌| 59197/61904 [7:18:44<1:01:49,  1.37s/it]
 96%|█████████▌| 59198/61904 [7:18:46<1:02:51,  1.39s/it]
 96%|█████████▌| 59199/61904 [7:18:47<1:03:12,  1.40s/it]
 96%|█████████▌| 59200/61904 [7:18:48<1:02:38,  1.39s/it]
                                                         
{'loss': 2.4432, 'learning_rate': 1.0438221185012317e-07, 'epoch': 15.3}

 96%|█████████▌| 59200/61904 [7:18:48<1:02:38,  1.39s/it]
 96%|█████████▌| 59201/61904 [7:18:50<1:02:48,  1.39s/it]
 96%|█████████▌| 59202/61904 [7:18:51<1:05:33,  1.46s/it]
 96%|█████████▌| 59203/61904 [7:18:53<1:05:37,  1.46s/it]
 96%|█████████▌| 59204/61904 [7:18:54<1:04:23,  1.43s/it]
 96%|█████████▌| 59205/61904 [7:18:56<1:03:14,  1.41s/it]
 96%|█████████▌| 59206/61904 [7:18:57<1:02:34,  1.39s/it]
 96%|█████████▌| 59207/61904 [7:18:58<1:00:55,  1.36s/it]
 96%|█████████▌| 59208/61904 [7:19:00<1:01:40,  1.37s/it]
 96%|█████████▌| 59209/61904 [7:19:01<1:00:56,  1.36s/it]
 96%|█████████▌| 59210/61904 [7:19:02<1:00:29,  1.35s/it]
 96%|█████████▌| 59211/61904 [7:19:04<1:00:43,  1.35s/it]
 96%|█████████▌| 59212/61904 [7:19:05<1:00:33,  1.35s/it]
 96%|█████████▌| 59213/61904 [7:19:06<59:20,  1.32s/it]  
 96%|█████████▌| 59214/61904 [7:19:08<1:00:55,  1.36s/it]
 96%|█████████▌| 59215/61904 [7:19:09<1:00:18,  1.35s/it]
 96%|█████████▌| 59216/61904 [7:19:11<1:01:43,  1.38s/it]
 96%|█████████▌| 59217/61904 [7:19:12<59:54,  1.34s/it]  
 96%|█████████▌| 59218/61904 [7:19:13<59:03,  1.32s/it]
 96%|█████████▌| 59219/61904 [7:19:14<59:05,  1.32s/it]
 96%|█████████▌| 59220/61904 [7:19:16<58:17,  1.30s/it]
                                                       
{'loss': 2.4697, 'learning_rate': 1.0434979904058084e-07, 'epoch': 15.31}

 96%|█████████▌| 59220/61904 [7:19:16<58:17,  1.30s/it]
 96%|█████████▌| 59221/61904 [7:19:17<1:00:20,  1.35s/it]
 96%|█████████▌| 59222/61904 [7:19:18<1:00:32,  1.35s/it]
 96%|█████████▌| 59223/61904 [7:19:20<1:00:55,  1.36s/it]
 96%|█████████▌| 59224/61904 [7:19:21<1:00:04,  1.34s/it]
 96%|█████████▌| 59225/61904 [7:19:23<1:01:41,  1.38s/it]
 96%|█████████▌| 59226/61904 [7:19:24<1:01:14,  1.37s/it]
 96%|█████████▌| 59227/61904 [7:19:25<1:02:53,  1.41s/it]
 96%|█████████▌| 59228/61904 [7:19:27<1:01:28,  1.38s/it]
 96%|█████████▌| 59229/61904 [7:19:28<1:02:45,  1.41s/it]
 96%|█████████▌| 59230/61904 [7:19:30<1:07:55,  1.52s/it]
 96%|█████████▌| 59231/61904 [7:19:31<1:04:30,  1.45s/it]
 96%|█████████▌| 59232/61904 [7:19:33<1:03:01,  1.42s/it]
 96%|█████████▌| 59233/61904 [7:19:34<1:01:57,  1.39s/it]
 96%|█████████▌| 59234/61904 [7:19:35<1:01:25,  1.38s/it]
 96%|█████████▌| 59235/61904 [7:19:37<1:02:47,  1.41s/it]
 96%|█████████▌| 59236/61904 [7:19:38<1:02:02,  1.40s/it]
 96%|█████████▌| 59237/61904 [7:19:40<1:01:33,  1.38s/it]
 96%|█████████▌| 59238/61904 [7:19:41<1:05:08,  1.47s/it]
 96%|█████████▌| 59239/61904 [7:19:42<1:02:57,  1.42s/it]
 96%|█████████▌| 59240/61904 [7:19:44<1:05:24,  1.47s/it]
                                                         
{'loss': 2.4792, 'learning_rate': 1.0431738623103852e-07, 'epoch': 15.31}

 96%|█████████▌| 59240/61904 [7:19:44<1:05:24,  1.47s/it]
 96%|█████████▌| 59241/61904 [7:19:46<1:05:28,  1.48s/it]
 96%|█████████▌| 59242/61904 [7:19:47<1:03:22,  1.43s/it]
 96%|█████████▌| 59243/61904 [7:19:48<1:03:16,  1.43s/it]
 96%|█████████▌| 59244/61904 [7:19:50<1:05:01,  1.47s/it]
 96%|█████████▌| 59245/61904 [7:19:51<1:04:48,  1.46s/it]
 96%|█████████▌| 59246/61904 [7:19:53<1:03:11,  1.43s/it]
 96%|█████████▌| 59247/61904 [7:19:54<1:00:27,  1.37s/it]
 96%|█████████▌| 59248/61904 [7:19:55<59:30,  1.34s/it]  
 96%|█████████▌| 59249/61904 [7:19:57<1:00:40,  1.37s/it]
 96%|█████████▌| 59250/61904 [7:19:58<59:23,  1.34s/it]  
 96%|█████████▌| 59251/61904 [7:19:59<59:55,  1.36s/it]
 96%|█████████▌| 59252/61904 [7:20:01<1:01:55,  1.40s/it]
 96%|█████████▌| 59253/61904 [7:20:02<59:47,  1.35s/it]  
 96%|█████████▌| 59254/61904 [7:20:03<59:57,  1.36s/it]
 96%|█████████▌| 59255/61904 [7:20:05<1:00:29,  1.37s/it]
 96%|█████████▌| 59256/61904 [7:20:06<1:01:18,  1.39s/it]
 96%|█████████▌| 59257/61904 [7:20:08<1:01:33,  1.40s/it]
 96%|█████████▌| 59258/61904 [7:20:09<1:01:30,  1.39s/it]
 96%|█████████▌| 59259/61904 [7:20:10<59:25,  1.35s/it]  
 96%|█████████▌| 59260/61904 [7:20:12<59:41,  1.35s/it]
                                                       
{'loss': 2.4445, 'learning_rate': 1.0428497342149619e-07, 'epoch': 15.32}

 96%|█████████▌| 59260/61904 [7:20:12<59:41,  1.35s/it]
 96%|█████████▌| 59261/61904 [7:20:13<1:01:47,  1.40s/it]
 96%|█████████▌| 59262/61904 [7:20:15<1:03:55,  1.45s/it]
 96%|█████████▌| 59263/61904 [7:20:16<1:02:43,  1.43s/it]
 96%|█████████▌| 59264/61904 [7:20:18<1:02:54,  1.43s/it]
 96%|█████████▌| 59265/61904 [7:20:19<1:02:09,  1.41s/it]
 96%|█████████▌| 59266/61904 [7:20:20<1:02:38,  1.42s/it]
 96%|█████████▌| 59267/61904 [7:20:22<1:02:46,  1.43s/it]
 96%|█████████▌| 59268/61904 [7:20:23<1:04:07,  1.46s/it]
 96%|█████████▌| 59269/61904 [7:20:25<1:03:09,  1.44s/it]
 96%|█████████▌| 59270/61904 [7:20:26<1:02:16,  1.42s/it]
 96%|█████████▌| 59271/61904 [7:20:27<1:01:27,  1.40s/it]
 96%|█████████▌| 59272/61904 [7:20:29<1:02:24,  1.42s/it]
 96%|█████████▌| 59273/61904 [7:20:30<1:00:52,  1.39s/it]
 96%|█████████▌| 59274/61904 [7:20:32<1:02:48,  1.43s/it]
 96%|█████████▌| 59275/61904 [7:20:33<1:02:03,  1.42s/it]
 96%|█████████▌| 59276/61904 [7:20:34<59:25,  1.36s/it]  
 96%|█████████▌| 59277/61904 [7:20:36<1:01:39,  1.41s/it]
 96%|█████████▌| 59278/61904 [7:20:37<1:01:21,  1.40s/it]
 96%|█████████▌| 59279/61904 [7:20:39<1:00:06,  1.37s/it]
 96%|█████████▌| 59280/61904 [7:20:40<59:32,  1.36s/it]  
                                                       
{'loss': 2.4796, 'learning_rate': 1.0425256061195385e-07, 'epoch': 15.32}

 96%|█████████▌| 59280/61904 [7:20:40<59:32,  1.36s/it]
 96%|█████████▌| 59281/61904 [7:20:41<59:52,  1.37s/it]
 96%|█████████▌| 59282/61904 [7:20:43<59:44,  1.37s/it]
 96%|█████████▌| 59283/61904 [7:20:44<58:51,  1.35s/it]
 96%|█████████▌| 59284/61904 [7:20:45<58:08,  1.33s/it]
 96%|█████████▌| 59285/61904 [7:20:47<1:02:32,  1.43s/it]
 96%|█████████▌| 59286/61904 [7:20:48<1:03:23,  1.45s/it]
 96%|█████████▌| 59287/61904 [7:20:50<1:01:34,  1.41s/it]
 96%|█████████▌| 59288/61904 [7:20:51<59:37,  1.37s/it]  
 96%|█████████▌| 59289/61904 [7:20:52<59:24,  1.36s/it]
 96%|█████████▌| 59290/61904 [7:20:54<58:10,  1.34s/it]
 96%|█████████▌| 59291/61904 [7:20:55<1:00:36,  1.39s/it]
 96%|█████████▌| 59292/61904 [7:20:56<59:29,  1.37s/it]  
 96%|█████████▌| 59293/61904 [7:20:58<58:45,  1.35s/it]
 96%|█████████▌| 59294/61904 [7:20:59<58:38,  1.35s/it]
 96%|█████████▌| 59295/61904 [7:21:00<58:31,  1.35s/it]
 96%|█████████▌| 59296/61904 [7:21:02<57:32,  1.32s/it]
 96%|█████████▌| 59297/61904 [7:21:03<56:49,  1.31s/it]
 96%|█████████▌| 59298/61904 [7:21:04<57:52,  1.33s/it]
 96%|█████████▌| 59299/61904 [7:21:06<58:36,  1.35s/it]
 96%|█████████▌| 59300/61904 [7:21:07<58:14,  1.34s/it]
                                                       
{'loss': 2.4082, 'learning_rate': 1.0422014780241151e-07, 'epoch': 15.33}

 96%|█████████▌| 59300/61904 [7:21:07<58:14,  1.34s/it]
 96%|█████████▌| 59301/61904 [7:21:09<58:56,  1.36s/it]
 96%|█████████▌| 59302/61904 [7:21:10<58:27,  1.35s/it]
 96%|█████████▌| 59303/61904 [7:21:11<57:40,  1.33s/it]
 96%|█████████▌| 59304/61904 [7:21:12<58:00,  1.34s/it]
 96%|█████████▌| 59305/61904 [7:21:14<58:46,  1.36s/it]
 96%|█████████▌| 59306/61904 [7:21:15<58:09,  1.34s/it]
 96%|█████████▌| 59307/61904 [7:21:17<58:18,  1.35s/it]
 96%|█████████▌| 59308/61904 [7:21:18<1:00:54,  1.41s/it]
 96%|█████████▌| 59309/61904 [7:21:20<1:02:27,  1.44s/it]
 96%|█████████▌| 59310/61904 [7:21:21<1:01:26,  1.42s/it]
 96%|█████████▌| 59311/61904 [7:21:22<1:00:00,  1.39s/it]
 96%|█████████▌| 59312/61904 [7:21:24<1:01:13,  1.42s/it]
 96%|█████████▌| 59313/61904 [7:21:25<1:00:35,  1.40s/it]
 96%|█████████▌| 59314/61904 [7:21:27<1:00:39,  1.41s/it]
 96%|█████████▌| 59315/61904 [7:21:28<1:00:44,  1.41s/it]
 96%|█████████▌| 59316/61904 [7:21:29<1:00:59,  1.41s/it]
 96%|█████████▌| 59317/61904 [7:21:31<1:00:41,  1.41s/it]
 96%|█████████▌| 59318/61904 [7:21:32<59:49,  1.39s/it]  
 96%|█████████▌| 59319/61904 [7:21:33<58:45,  1.36s/it]
 96%|█████████▌| 59320/61904 [7:21:35<1:00:21,  1.40s/it]
                                                         
{'loss': 2.4877, 'learning_rate': 1.041877349928692e-07, 'epoch': 15.33}

 96%|█████████▌| 59320/61904 [7:21:35<1:00:21,  1.40s/it]
 96%|█████████▌| 59321/61904 [7:21:36<1:01:07,  1.42s/it]
 96%|█████████▌| 59322/61904 [7:21:38<1:00:05,  1.40s/it]
 96%|█████████▌| 59323/61904 [7:21:39<1:00:58,  1.42s/it]
 96%|█████████▌| 59324/61904 [7:21:41<1:00:54,  1.42s/it]
 96%|█████████▌| 59325/61904 [7:21:42<59:47,  1.39s/it]  
 96%|█████████▌| 59326/61904 [7:21:43<1:00:13,  1.40s/it]
 96%|█████████▌| 59327/61904 [7:21:45<1:03:07,  1.47s/it]
 96%|█████████▌| 59328/61904 [7:21:46<1:01:29,  1.43s/it]
 96%|█████████▌| 59329/61904 [7:21:48<59:23,  1.38s/it]  
 96%|█████████▌| 59330/61904 [7:21:49<1:00:06,  1.40s/it]
 96%|█████████▌| 59331/61904 [7:21:50<59:59,  1.40s/it]  
 96%|█████████▌| 59332/61904 [7:21:52<1:00:03,  1.40s/it]
 96%|█████████▌| 59333/61904 [7:21:53<59:30,  1.39s/it]  
 96%|█████████▌| 59334/61904 [7:21:55<1:01:20,  1.43s/it]
 96%|█████████▌| 59335/61904 [7:21:56<1:01:27,  1.44s/it]
 96%|█████████▌| 59336/61904 [7:21:58<1:01:56,  1.45s/it]
 96%|█████████▌| 59337/61904 [7:21:59<1:02:27,  1.46s/it]
 96%|█████████▌| 59338/61904 [7:22:01<1:02:27,  1.46s/it]
 96%|█████████▌| 59339/61904 [7:22:02<1:03:20,  1.48s/it]
 96%|█████████▌| 59340/61904 [7:22:03<1:01:24,  1.44s/it]
                                                         
{'loss': 2.3853, 'learning_rate': 1.0415532218332686e-07, 'epoch': 15.34}

 96%|█████████▌| 59340/61904 [7:22:03<1:01:24,  1.44s/it]
 96%|█████████▌| 59341/61904 [7:22:05<59:34,  1.39s/it]  
 96%|█████████▌| 59342/61904 [7:22:06<57:45,  1.35s/it]
 96%|█████████▌| 59343/61904 [7:22:07<58:23,  1.37s/it]
 96%|█████████▌| 59344/61904 [7:22:09<58:56,  1.38s/it]
 96%|█████████▌| 59345/61904 [7:22:10<1:01:02,  1.43s/it]
 96%|█████████▌| 59346/61904 [7:22:12<1:00:10,  1.41s/it]
 96%|█████████▌| 59347/61904 [7:22:13<59:25,  1.39s/it]  
 96%|█████████▌| 59348/61904 [7:22:14<57:49,  1.36s/it]
 96%|█████████▌| 59349/61904 [7:22:16<58:21,  1.37s/it]
 96%|█████████▌| 59350/61904 [7:22:17<57:54,  1.36s/it]
 96%|█████████▌| 59351/61904 [7:22:18<57:25,  1.35s/it]
 96%|█████████▌| 59352/61904 [7:22:20<56:27,  1.33s/it]
 96%|█████████▌| 59353/61904 [7:22:21<57:28,  1.35s/it]
 96%|█████████▌| 59354/61904 [7:22:22<57:14,  1.35s/it]
 96%|█████████▌| 59355/61904 [7:22:24<56:17,  1.33s/it]
 96%|█████████▌| 59356/61904 [7:22:25<56:12,  1.32s/it]
 96%|█████████▌| 59357/61904 [7:22:26<55:56,  1.32s/it]
 96%|█████████▌| 59358/61904 [7:22:28<58:30,  1.38s/it]
 96%|█████████▌| 59359/61904 [7:22:29<58:31,  1.38s/it]
 96%|█████████▌| 59360/61904 [7:22:31<59:17,  1.40s/it]
                                                       
{'loss': 2.4456, 'learning_rate': 1.0412290937378452e-07, 'epoch': 15.34}

 96%|█████████▌| 59360/61904 [7:22:31<59:17,  1.40s/it]
 96%|█████████▌| 59361/61904 [7:22:32<57:05,  1.35s/it]
 96%|█████████▌| 59362/61904 [7:22:33<58:43,  1.39s/it]
 96%|█████████▌| 59363/61904 [7:22:35<59:09,  1.40s/it]
 96%|█████████▌| 59364/61904 [7:22:36<58:11,  1.37s/it]
 96%|█████████▌| 59365/61904 [7:22:38<59:49,  1.41s/it]
 96%|█████████▌| 59366/61904 [7:22:39<1:02:23,  1.48s/it]
 96%|█████████▌| 59367/61904 [7:22:41<1:00:58,  1.44s/it]
 96%|█████████▌| 59368/61904 [7:22:42<58:30,  1.38s/it]  
 96%|█████████▌| 59369/61904 [7:22:43<59:57,  1.42s/it]
 96%|█████████▌| 59370/61904 [7:22:45<59:24,  1.41s/it]
 96%|█████████▌| 59371/61904 [7:22:46<58:59,  1.40s/it]
 96%|█████████▌| 59372/61904 [7:22:48<59:37,  1.41s/it]
 96%|█████████▌| 59373/61904 [7:22:49<59:22,  1.41s/it]
 96%|█████████▌| 59374/61904 [7:22:50<59:08,  1.40s/it]
 96%|█████████▌| 59375/61904 [7:22:52<57:26,  1.36s/it]
 96%|█████████▌| 59376/61904 [7:22:53<58:49,  1.40s/it]
 96%|█████████▌| 59377/61904 [7:22:55<1:00:41,  1.44s/it]
 96%|█████████▌| 59378/61904 [7:22:56<1:00:17,  1.43s/it]
 96%|█████████▌| 59379/61904 [7:22:58<1:00:31,  1.44s/it]
 96%|█████████▌| 59380/61904 [7:22:59<59:49,  1.42s/it]  
                                                       
{'loss': 2.3743, 'learning_rate': 1.0409049656424218e-07, 'epoch': 15.35}

 96%|█████████▌| 59380/61904 [7:22:59<59:49,  1.42s/it]
 96%|█████████▌| 59381/61904 [7:23:00<1:00:05,  1.43s/it]
 96%|█████████▌| 59382/61904 [7:23:02<1:00:41,  1.44s/it]
 96%|█████████▌| 59383/61904 [7:23:03<1:00:58,  1.45s/it]
 96%|█████████▌| 59384/61904 [7:23:05<1:00:41,  1.45s/it]
 96%|█████████▌| 59385/61904 [7:23:06<59:50,  1.43s/it]  
 96%|█████████▌| 59386/61904 [7:23:07<57:48,  1.38s/it]
 96%|█████████▌| 59387/61904 [7:23:09<56:26,  1.35s/it]
 96%|█████████▌| 59388/61904 [7:23:10<55:16,  1.32s/it]
 96%|█████████▌| 59389/61904 [7:23:11<55:09,  1.32s/it]
 96%|█████████▌| 59390/61904 [7:23:13<55:32,  1.33s/it]
 96%|█████████▌| 59391/61904 [7:23:14<54:13,  1.29s/it]
 96%|█████████▌| 59392/61904 [7:23:15<53:14,  1.27s/it]
 96%|█████████▌| 59393/61904 [7:23:16<53:58,  1.29s/it]
 96%|█████████▌| 59394/61904 [7:23:18<57:07,  1.37s/it]
 96%|█████████▌| 59395/61904 [7:23:19<58:08,  1.39s/it]
 96%|█████████▌| 59396/61904 [7:23:21<56:49,  1.36s/it]
 96%|█████████▌| 59397/61904 [7:23:22<56:21,  1.35s/it]
 96%|█████████▌| 59398/61904 [7:23:23<55:42,  1.33s/it]
 96%|█████████▌| 59399/61904 [7:23:25<56:27,  1.35s/it]
 96%|█████████▌| 59400/61904 [7:23:26<56:48,  1.36s/it]
                                                       
{'loss': 2.4828, 'learning_rate': 1.0405808375469987e-07, 'epoch': 15.35}

 96%|█████████▌| 59400/61904 [7:23:26<56:48,  1.36s/it]
 96%|█████████▌| 59401/61904 [7:23:27<57:25,  1.38s/it]
 96%|█████████▌| 59402/61904 [7:23:29<57:38,  1.38s/it]
 96%|█████████▌| 59403/61904 [7:23:30<57:55,  1.39s/it]
 96%|█████████▌| 59404/61904 [7:23:32<57:19,  1.38s/it]
 96%|█████████▌| 59405/61904 [7:23:33<58:39,  1.41s/it]
 96%|█████████▌| 59406/61904 [7:23:34<57:29,  1.38s/it]
 96%|█████████▌| 59407/61904 [7:23:36<56:20,  1.35s/it]
 96%|█████████▌| 59408/61904 [7:23:37<55:38,  1.34s/it]
 96%|█████████▌| 59409/61904 [7:23:39<58:08,  1.40s/it]
 96%|█████████▌| 59410/61904 [7:23:40<57:06,  1.37s/it]
 96%|█████████▌| 59411/61904 [7:23:41<56:09,  1.35s/it]
 96%|█████████▌| 59412/61904 [7:23:43<57:31,  1.39s/it]
 96%|█████████▌| 59413/61904 [7:23:44<58:18,  1.40s/it]
 96%|█████████▌| 59414/61904 [7:23:45<56:40,  1.37s/it]
 96%|█████████▌| 59415/61904 [7:23:47<54:40,  1.32s/it]
 96%|█████████▌| 59416/61904 [7:23:48<53:29,  1.29s/it]
 96%|█████████▌| 59417/61904 [7:23:49<54:14,  1.31s/it]
 96%|█████████▌| 59418/61904 [7:23:50<54:05,  1.31s/it]
 96%|█████████▌| 59419/61904 [7:23:52<53:05,  1.28s/it]
 96%|█████████▌| 59420/61904 [7:23:53<55:51,  1.35s/it]
                                                       
{'loss': 2.4157, 'learning_rate': 1.0402567094515753e-07, 'epoch': 15.36}

 96%|█████████▌| 59420/61904 [7:23:53<55:51,  1.35s/it]
 96%|█████████▌| 59421/61904 [7:23:55<59:03,  1.43s/it]
 96%|█████████▌| 59422/61904 [7:23:56<58:49,  1.42s/it]
 96%|█████████▌| 59423/61904 [7:23:58<59:07,  1.43s/it]
 96%|█████████▌| 59424/61904 [7:23:59<57:21,  1.39s/it]
 96%|█████████▌| 59425/61904 [7:24:00<56:37,  1.37s/it]
 96%|█████████▌| 59426/61904 [7:24:02<57:33,  1.39s/it]
 96%|█████████▌| 59427/61904 [7:24:03<57:34,  1.39s/it]
 96%|█████████▌| 59428/61904 [7:24:04<57:21,  1.39s/it]
 96%|█████████▌| 59429/61904 [7:24:06<58:41,  1.42s/it]
 96%|█████████▌| 59430/61904 [7:24:07<58:50,  1.43s/it]
 96%|█████████▌| 59431/61904 [7:24:09<59:06,  1.43s/it]
 96%|█████████▌| 59432/61904 [7:24:10<1:00:03,  1.46s/it]
 96%|█████████▌| 59433/61904 [7:24:12<59:53,  1.45s/it]  
 96%|█████████▌| 59434/61904 [7:24:13<58:15,  1.42s/it]
 96%|█████████▌| 59435/61904 [7:24:15<58:28,  1.42s/it]
 96%|█████████▌| 59436/61904 [7:24:16<57:23,  1.40s/it]
 96%|█████████▌| 59437/61904 [7:24:17<56:14,  1.37s/it]
 96%|█████████▌| 59438/61904 [7:24:19<57:07,  1.39s/it]
 96%|█████████▌| 59439/61904 [7:24:20<57:03,  1.39s/it]
 96%|█████████▌| 59440/61904 [7:24:21<57:39,  1.40s/it]
                                                       
{'loss': 2.4593, 'learning_rate': 1.039932581356152e-07, 'epoch': 15.36}

 96%|█████████▌| 59440/61904 [7:24:21<57:39,  1.40s/it]
 96%|█████████▌| 59441/61904 [7:24:23<56:00,  1.36s/it]
 96%|█████████▌| 59442/61904 [7:24:24<56:18,  1.37s/it]
 96%|█████████▌| 59443/61904 [7:24:25<54:40,  1.33s/it]
 96%|█████████▌| 59444/61904 [7:24:27<54:48,  1.34s/it]
 96%|█████████▌| 59445/61904 [7:24:28<54:23,  1.33s/it]
 96%|█████████▌| 59446/61904 [7:24:29<54:27,  1.33s/it]
 96%|█████████▌| 59447/61904 [7:24:31<52:58,  1.29s/it]
 96%|█████████▌| 59448/61904 [7:24:32<53:46,  1.31s/it]
 96%|█████████▌| 59449/61904 [7:24:33<54:52,  1.34s/it]
 96%|█████████▌| 59450/61904 [7:24:35<55:03,  1.35s/it]
 96%|█████████▌| 59451/61904 [7:24:36<56:23,  1.38s/it]
 96%|█████████▌| 59452/61904 [7:24:38<56:27,  1.38s/it]
 96%|█████████▌| 59453/61904 [7:24:39<55:56,  1.37s/it]
 96%|█████████▌| 59454/61904 [7:24:40<54:30,  1.33s/it]
 96%|█████████▌| 59455/61904 [7:24:42<55:02,  1.35s/it]
 96%|█████████▌| 59456/61904 [7:24:43<53:56,  1.32s/it]
 96%|█████████▌| 59457/61904 [7:24:44<55:24,  1.36s/it]
 96%|█████████▌| 59458/61904 [7:24:46<55:39,  1.37s/it]
 96%|█████████▌| 59459/61904 [7:24:47<55:20,  1.36s/it]
 96%|█████████▌| 59460/61904 [7:24:48<56:54,  1.40s/it]
                                                       
{'loss': 2.3706, 'learning_rate': 1.0396084532607286e-07, 'epoch': 15.37}

 96%|█████████▌| 59460/61904 [7:24:48<56:54,  1.40s/it]
 96%|█████████▌| 59461/61904 [7:24:50<57:14,  1.41s/it]
 96%|█████████▌| 59462/61904 [7:24:51<55:47,  1.37s/it]
 96%|█████████▌| 59463/61904 [7:24:52<54:27,  1.34s/it]
 96%|█████████▌| 59464/61904 [7:24:54<54:44,  1.35s/it]
 96%|█████████▌| 59465/61904 [7:24:55<55:10,  1.36s/it]
 96%|█████████▌| 59466/61904 [7:24:57<56:43,  1.40s/it]
 96%|█████████▌| 59467/61904 [7:24:58<57:29,  1.42s/it]
 96%|█████████▌| 59468/61904 [7:24:59<55:55,  1.38s/it]
 96%|█████████▌| 59469/61904 [7:25:01<56:30,  1.39s/it]
 96%|█████████▌| 59470/61904 [7:25:02<55:07,  1.36s/it]
 96%|█████████▌| 59471/61904 [7:25:04<57:58,  1.43s/it]
 96%|█████████▌| 59472/61904 [7:25:05<58:01,  1.43s/it]
 96%|█████████▌| 59473/61904 [7:25:06<55:54,  1.38s/it]
 96%|█████████▌| 59474/61904 [7:25:08<54:29,  1.35s/it]
 96%|█████████▌| 59475/61904 [7:25:09<54:36,  1.35s/it]
 96%|█████████▌| 59476/61904 [7:25:10<54:28,  1.35s/it]
 96%|█████████▌| 59477/61904 [7:25:12<54:15,  1.34s/it]
 96%|█████████▌| 59478/61904 [7:25:13<56:55,  1.41s/it]
 96%|█████████▌| 59479/61904 [7:25:15<57:15,  1.42s/it]
 96%|█████████▌| 59480/61904 [7:25:16<58:09,  1.44s/it]
                                                       
{'loss': 2.4284, 'learning_rate': 1.0392843251653055e-07, 'epoch': 15.37}

 96%|█████████▌| 59480/61904 [7:25:16<58:09,  1.44s/it]
 96%|█████████▌| 59481/61904 [7:25:18<56:56,  1.41s/it]
 96%|█████████▌| 59482/61904 [7:25:19<55:41,  1.38s/it]
 96%|█████████▌| 59483/61904 [7:25:20<56:15,  1.39s/it]
 96%|█████████▌| 59484/61904 [7:25:22<55:54,  1.39s/it]
 96%|█████████▌| 59485/61904 [7:25:23<56:32,  1.40s/it]
 96%|█████████▌| 59486/61904 [7:25:25<57:19,  1.42s/it]
 96%|█████████▌| 59487/61904 [7:25:26<56:09,  1.39s/it]
 96%|█████████▌| 59488/61904 [7:25:27<56:39,  1.41s/it]
 96%|█████████▌| 59489/61904 [7:25:29<56:32,  1.40s/it]
 96%|█████████▌| 59490/61904 [7:25:30<54:02,  1.34s/it]
 96%|█████████▌| 59491/61904 [7:25:31<53:18,  1.33s/it]
 96%|█████████▌| 59492/61904 [7:25:32<53:02,  1.32s/it]
 96%|█████████▌| 59493/61904 [7:25:34<52:08,  1.30s/it]
 96%|█████████▌| 59494/61904 [7:25:35<52:56,  1.32s/it]
 96%|█████████▌| 59495/61904 [7:25:36<53:46,  1.34s/it]
 96%|█████████▌| 59496/61904 [7:25:38<54:00,  1.35s/it]
 96%|█████████▌| 59497/61904 [7:25:39<54:54,  1.37s/it]
 96%|█████████▌| 59498/61904 [7:25:41<54:46,  1.37s/it]
 96%|█████████▌| 59499/61904 [7:25:42<54:40,  1.36s/it]
 96%|█████████▌| 59500/61904 [7:25:44<59:24,  1.48s/it]
                                                       
{'loss': 2.4174, 'learning_rate': 1.0389601970698821e-07, 'epoch': 15.38}

 96%|█████████▌| 59500/61904 [7:25:44<59:24,  1.48s/it]
 96%|█████████▌| 59501/61904 [7:25:45<58:59,  1.47s/it]
 96%|█████████▌| 59502/61904 [7:25:47<59:39,  1.49s/it]
 96%|█████████▌| 59503/61904 [7:25:48<57:33,  1.44s/it]
 96%|█████████▌| 59504/61904 [7:25:49<57:19,  1.43s/it]
 96%|█████████▌| 59505/61904 [7:25:51<55:23,  1.39s/it]
 96%|█████████▌| 59506/61904 [7:25:52<55:41,  1.39s/it]
 96%|█████████▌| 59507/61904 [7:25:54<55:09,  1.38s/it]
 96%|█████████▌| 59508/61904 [7:25:55<54:45,  1.37s/it]
 96%|█████████▌| 59509/61904 [7:25:56<56:34,  1.42s/it]
 96%|█████████▌| 59510/61904 [7:25:58<54:26,  1.36s/it]
 96%|█████████▌| 59511/61904 [7:25:59<54:56,  1.38s/it]
 96%|█████████▌| 59512/61904 [7:26:00<53:34,  1.34s/it]
 96%|█████████▌| 59513/61904 [7:26:02<52:34,  1.32s/it]
 96%|█████████▌| 59514/61904 [7:26:03<52:55,  1.33s/it]
 96%|█████████▌| 59515/61904 [7:26:04<54:14,  1.36s/it]
 96%|█████████▌| 59516/61904 [7:26:06<54:26,  1.37s/it]
 96%|█████████▌| 59517/61904 [7:26:07<53:52,  1.35s/it]
 96%|█████████▌| 59518/61904 [7:26:09<55:27,  1.39s/it]
 96%|█████████▌| 59519/61904 [7:26:10<57:00,  1.43s/it]
 96%|█████████▌| 59520/61904 [7:26:12<57:10,  1.44s/it]
                                                       
{'loss': 2.3777, 'learning_rate': 1.0386360689744587e-07, 'epoch': 15.38}

 96%|█████████▌| 59520/61904 [7:26:12<57:10,  1.44s/it]
 96%|█████████▌| 59521/61904 [7:26:13<55:33,  1.40s/it]
 96%|█████████▌| 59522/61904 [7:26:14<54:43,  1.38s/it]
 96%|█████████▌| 59523/61904 [7:26:16<56:28,  1.42s/it]
 96%|█████████▌| 59524/61904 [7:26:17<57:30,  1.45s/it]
 96%|█████████▌| 59525/61904 [7:26:19<56:33,  1.43s/it]
 96%|█████████▌| 59526/61904 [7:26:20<54:49,  1.38s/it]
 96%|█████████▌| 59527/61904 [7:26:21<54:29,  1.38s/it]
 96%|█████████▌| 59528/61904 [7:26:22<52:37,  1.33s/it]
 96%|█████████▌| 59529/61904 [7:26:24<54:35,  1.38s/it]
 96%|█████████▌| 59530/61904 [7:26:25<54:59,  1.39s/it]
 96%|█████████▌| 59531/61904 [7:26:27<53:52,  1.36s/it]
 96%|█████████▌| 59532/61904 [7:26:28<54:24,  1.38s/it]
 96%|█████████▌| 59533/61904 [7:26:30<56:35,  1.43s/it]
 96%|█████████▌| 59534/61904 [7:26:31<55:01,  1.39s/it]
 96%|█████████▌| 59535/61904 [7:26:32<54:01,  1.37s/it]
 96%|█████████▌| 59536/61904 [7:26:34<53:22,  1.35s/it]
 96%|█████████▌| 59537/61904 [7:26:35<53:35,  1.36s/it]
 96%|█████████▌| 59538/61904 [7:26:36<54:09,  1.37s/it]
 96%|█████████▌| 59539/61904 [7:26:38<54:35,  1.39s/it]
 96%|█████████▌| 59540/61904 [7:26:39<53:57,  1.37s/it]
                                                       
{'loss': 2.3894, 'learning_rate': 1.0383119408790354e-07, 'epoch': 15.39}

 96%|█████████▌| 59540/61904 [7:26:39<53:57,  1.37s/it]
 96%|█████████▌| 59541/61904 [7:26:40<54:17,  1.38s/it]
 96%|█████████▌| 59542/61904 [7:26:42<52:45,  1.34s/it]
 96%|█████████▌| 59543/61904 [7:26:43<53:11,  1.35s/it]
 96%|█████████▌| 59544/61904 [7:26:45<55:05,  1.40s/it]
 96%|█████████▌| 59545/61904 [7:26:46<53:31,  1.36s/it]
 96%|█████████▌| 59546/61904 [7:26:47<54:42,  1.39s/it]
 96%|█████████▌| 59547/61904 [7:26:49<54:00,  1.37s/it]
 96%|█████████▌| 59548/61904 [7:26:50<54:48,  1.40s/it]
 96%|█████████▌| 59549/61904 [7:26:52<55:59,  1.43s/it]
 96%|█████████▌| 59550/61904 [7:26:53<55:46,  1.42s/it]
 96%|█████████▌| 59551/61904 [7:26:54<55:38,  1.42s/it]
 96%|█████████▌| 59552/61904 [7:26:56<55:04,  1.41s/it]
 96%|█████████▌| 59553/61904 [7:26:57<55:15,  1.41s/it]
 96%|█████████▌| 59554/61904 [7:26:59<54:48,  1.40s/it]
 96%|█████████▌| 59555/61904 [7:27:00<56:33,  1.44s/it]
 96%|█████████▌| 59556/61904 [7:27:02<56:23,  1.44s/it]
 96%|█████████▌| 59557/61904 [7:27:03<55:06,  1.41s/it]
 96%|█████████▌| 59558/61904 [7:27:04<53:31,  1.37s/it]
 96%|█████████▌| 59559/61904 [7:27:05<52:09,  1.33s/it]
 96%|█████████▌| 59560/61904 [7:27:07<51:34,  1.32s/it]
                                                       
{'loss': 2.4183, 'learning_rate': 1.0379878127836122e-07, 'epoch': 15.39}

 96%|█████████▌| 59560/61904 [7:27:07<51:34,  1.32s/it]
 96%|█████████▌| 59561/61904 [7:27:08<51:32,  1.32s/it]
 96%|█████████▌| 59562/61904 [7:27:09<51:36,  1.32s/it]
 96%|█████████▌| 59563/61904 [7:27:11<52:07,  1.34s/it]
 96%|█████████▌| 59564/61904 [7:27:12<55:44,  1.43s/it]
 96%|█████████▌| 59565/61904 [7:27:14<55:15,  1.42s/it]
 96%|█████████▌| 59566/61904 [7:27:15<54:10,  1.39s/it]
 96%|█████████▌| 59567/61904 [7:27:16<53:41,  1.38s/it]
 96%|█████████▌| 59568/61904 [7:27:18<54:10,  1.39s/it]
 96%|█████████▌| 59569/61904 [7:27:20<56:46,  1.46s/it]
 96%|█████████▌| 59570/61904 [7:27:21<55:45,  1.43s/it]
 96%|█████████▌| 59571/61904 [7:27:22<54:07,  1.39s/it]
 96%|█████████▌| 59572/61904 [7:27:24<53:19,  1.37s/it]
 96%|█████████▌| 59573/61904 [7:27:25<54:21,  1.40s/it]
 96%|█████████▌| 59574/61904 [7:27:26<53:21,  1.37s/it]
 96%|█████████▌| 59575/61904 [7:27:28<52:44,  1.36s/it]
 96%|█████████▌| 59576/61904 [7:27:29<54:53,  1.41s/it]
 96%|█████████▌| 59577/61904 [7:27:31<54:31,  1.41s/it]
 96%|█████████▌| 59578/61904 [7:27:32<53:47,  1.39s/it]
 96%|█████████▌| 59579/61904 [7:27:33<53:03,  1.37s/it]
 96%|█████████▌| 59580/61904 [7:27:35<54:33,  1.41s/it]
                                                       
{'loss': 2.3614, 'learning_rate': 1.0376636846881888e-07, 'epoch': 15.4}

 96%|█████████▌| 59580/61904 [7:27:35<54:33,  1.41s/it]
 96%|█████████▌| 59581/61904 [7:27:36<54:55,  1.42s/it]
 96%|█████████▌| 59582/61904 [7:27:37<53:28,  1.38s/it]
 96%|█████████▋| 59583/61904 [7:27:39<53:44,  1.39s/it]
 96%|█████████▋| 59584/61904 [7:27:40<54:45,  1.42s/it]
 96%|█████████▋| 59585/61904 [7:27:42<53:49,  1.39s/it]
 96%|█████████▋| 59586/61904 [7:27:43<57:35,  1.49s/it]
 96%|█████████▋| 59587/61904 [7:27:45<54:30,  1.41s/it]
 96%|█████████▋| 59588/61904 [7:27:46<53:53,  1.40s/it]
 96%|█████████▋| 59589/61904 [7:27:47<52:10,  1.35s/it]
 96%|█████████▋| 59590/61904 [7:27:49<52:21,  1.36s/it]
 96%|█████████▋| 59591/61904 [7:27:50<52:28,  1.36s/it]
 96%|█████████▋| 59592/61904 [7:27:51<53:25,  1.39s/it]
 96%|█████████▋| 59593/61904 [7:27:53<53:08,  1.38s/it]
 96%|█████████▋| 59594/61904 [7:27:54<54:40,  1.42s/it]
 96%|█████████▋| 59595/61904 [7:27:56<54:27,  1.41s/it]
 96%|█████████▋| 59596/61904 [7:27:57<53:22,  1.39s/it]
 96%|█████████▋| 59597/61904 [7:27:58<52:35,  1.37s/it]
 96%|█████████▋| 59598/61904 [7:28:00<52:23,  1.36s/it]
 96%|█████████▋| 59599/61904 [7:28:01<54:04,  1.41s/it]
 96%|█████████▋| 59600/61904 [7:28:02<52:32,  1.37s/it]
                                                       
{'loss': 2.4399, 'learning_rate': 1.0373395565927654e-07, 'epoch': 15.4}

 96%|█████████▋| 59600/61904 [7:28:02<52:32,  1.37s/it]
 96%|█████████▋| 59601/61904 [7:28:04<51:13,  1.33s/it]
 96%|█████████▋| 59602/61904 [7:28:05<50:50,  1.33s/it]
 96%|█████████▋| 59603/61904 [7:28:06<52:09,  1.36s/it]
 96%|█████████▋| 59604/61904 [7:28:08<52:40,  1.37s/it]
 96%|█████████▋| 59605/61904 [7:28:09<52:11,  1.36s/it]
 96%|█████████▋| 59606/61904 [7:28:10<50:53,  1.33s/it]
 96%|█████████▋| 59607/61904 [7:28:12<50:58,  1.33s/it]
 96%|█████████▋| 59608/61904 [7:28:13<52:51,  1.38s/it]
 96%|█████████▋| 59609/61904 [7:28:15<52:07,  1.36s/it]
 96%|█████████▋| 59610/61904 [7:28:16<50:20,  1.32s/it]
 96%|█████████▋| 59611/61904 [7:28:17<50:10,  1.31s/it]
 96%|█████████▋| 59612/61904 [7:28:18<49:36,  1.30s/it]
 96%|█████████▋| 59613/61904 [7:28:20<50:33,  1.32s/it]
 96%|█████████▋| 59614/61904 [7:28:21<52:20,  1.37s/it]
 96%|█████████▋| 59615/61904 [7:28:23<54:21,  1.42s/it]
 96%|█████████▋| 59616/61904 [7:28:24<53:42,  1.41s/it]
 96%|█████████▋| 59617/61904 [7:28:26<55:32,  1.46s/it]
 96%|█████████▋| 59618/61904 [7:28:27<55:38,  1.46s/it]
 96%|█████████▋| 59619/61904 [7:28:29<55:22,  1.45s/it]
 96%|█████████▋| 59620/61904 [7:28:30<54:11,  1.42s/it]
                                                       
{'loss': 2.3998, 'learning_rate': 1.0370154284973422e-07, 'epoch': 15.41}

 96%|█████████▋| 59620/61904 [7:28:30<54:11,  1.42s/it]
 96%|█████████▋| 59621/61904 [7:28:31<54:08,  1.42s/it]
 96%|█████████▋| 59622/61904 [7:28:33<53:12,  1.40s/it]
 96%|█████████▋| 59623/61904 [7:28:34<54:03,  1.42s/it]
 96%|█████████▋| 59624/61904 [7:28:36<52:35,  1.38s/it]
 96%|█████████▋| 59625/61904 [7:28:37<51:45,  1.36s/it]
 96%|█████████▋| 59626/61904 [7:28:38<51:24,  1.35s/it]
 96%|█████████▋| 59627/61904 [7:28:40<51:26,  1.36s/it]
 96%|█████████▋| 59628/61904 [7:28:41<51:40,  1.36s/it]
 96%|█████████▋| 59629/61904 [7:28:42<51:17,  1.35s/it]
 96%|█████████▋| 59630/61904 [7:28:44<50:49,  1.34s/it]
 96%|█████████▋| 59631/61904 [7:28:45<50:43,  1.34s/it]
 96%|█████████▋| 59632/61904 [7:28:46<52:53,  1.40s/it]
 96%|█████████▋| 59633/61904 [7:28:48<52:05,  1.38s/it]
 96%|█████████▋| 59634/61904 [7:28:49<50:41,  1.34s/it]
 96%|█████████▋| 59635/61904 [7:28:50<50:31,  1.34s/it]
 96%|█████████▋| 59636/61904 [7:28:52<50:22,  1.33s/it]
 96%|█████████▋| 59637/61904 [7:28:53<53:35,  1.42s/it]
 96%|█████████▋| 59638/61904 [7:28:55<52:55,  1.40s/it]
 96%|█████████▋| 59639/61904 [7:28:56<51:37,  1.37s/it]
 96%|█████████▋| 59640/61904 [7:28:57<51:36,  1.37s/it]
                                                       
{'loss': 2.4962, 'learning_rate': 1.036691300401919e-07, 'epoch': 15.41}

 96%|█████████▋| 59640/61904 [7:28:57<51:36,  1.37s/it]
 96%|█████████▋| 59641/61904 [7:28:59<50:03,  1.33s/it]
 96%|█████████▋| 59642/61904 [7:29:00<50:24,  1.34s/it]
 96%|█████████▋| 59643/61904 [7:29:01<51:04,  1.36s/it]
 96%|█████████▋| 59644/61904 [7:29:03<51:46,  1.37s/it]
 96%|█████████▋| 59645/61904 [7:29:04<52:08,  1.38s/it]
 96%|█████████▋| 59646/61904 [7:29:05<51:25,  1.37s/it]
 96%|█████████▋| 59647/61904 [7:29:07<52:46,  1.40s/it]
 96%|█████████▋| 59648/61904 [7:29:08<52:14,  1.39s/it]
 96%|█████████▋| 59649/61904 [7:29:10<55:15,  1.47s/it]
 96%|█████████▋| 59650/61904 [7:29:11<53:56,  1.44s/it]
 96%|█████████▋| 59651/61904 [7:29:13<51:33,  1.37s/it]
 96%|█████████▋| 59652/61904 [7:29:14<51:14,  1.37s/it]
 96%|█████████▋| 59653/61904 [7:29:15<50:46,  1.35s/it]
 96%|█████████▋| 59654/61904 [7:29:17<52:26,  1.40s/it]
 96%|█████████▋| 59655/61904 [7:29:18<52:59,  1.41s/it]
 96%|█████████▋| 59656/61904 [7:29:20<52:15,  1.39s/it]
 96%|█████████▋| 59657/61904 [7:29:21<51:02,  1.36s/it]
 96%|█████████▋| 59658/61904 [7:29:22<50:39,  1.35s/it]
 96%|█████████▋| 59659/61904 [7:29:24<51:59,  1.39s/it]
 96%|█████████▋| 59660/61904 [7:29:25<51:42,  1.38s/it]
                                                       
{'loss': 2.3728, 'learning_rate': 1.0363671723064956e-07, 'epoch': 15.42}

 96%|█████████▋| 59660/61904 [7:29:25<51:42,  1.38s/it]
 96%|█████████▋| 59661/61904 [7:29:26<52:17,  1.40s/it]
 96%|█████████▋| 59662/61904 [7:29:28<52:15,  1.40s/it]
 96%|█████████▋| 59663/61904 [7:29:29<52:03,  1.39s/it]
 96%|█████████▋| 59664/61904 [7:29:31<51:02,  1.37s/it]
 96%|█████████▋| 59665/61904 [7:29:32<52:46,  1.41s/it]
 96%|█████████▋| 59666/61904 [7:29:33<52:30,  1.41s/it]
 96%|█████████▋| 59667/61904 [7:29:35<52:43,  1.41s/it]
 96%|█████████▋| 59668/61904 [7:29:36<53:51,  1.45s/it]
 96%|█████████▋| 59669/61904 [7:29:38<53:47,  1.44s/it]
 96%|█████████▋| 59670/61904 [7:29:39<51:37,  1.39s/it]
 96%|█████████▋| 59671/61904 [7:29:40<51:28,  1.38s/it]
 96%|█████████▋| 59672/61904 [7:29:42<50:38,  1.36s/it]
 96%|█████████▋| 59673/61904 [7:29:43<49:04,  1.32s/it]
 96%|█████████▋| 59674/61904 [7:29:44<50:14,  1.35s/it]
 96%|█████████▋| 59675/61904 [7:29:46<50:28,  1.36s/it]
 96%|█████████▋| 59676/61904 [7:29:47<49:20,  1.33s/it]
 96%|█████████▋| 59677/61904 [7:29:48<49:09,  1.32s/it]
 96%|█████████▋| 59678/61904 [7:29:50<50:04,  1.35s/it]
 96%|█████████▋| 59679/61904 [7:29:51<50:01,  1.35s/it]
 96%|█████████▋| 59680/61904 [7:29:52<49:39,  1.34s/it]
                                                       
{'loss': 2.4273, 'learning_rate': 1.0360430442110722e-07, 'epoch': 15.42}

 96%|█████████▋| 59680/61904 [7:29:52<49:39,  1.34s/it]
 96%|█████████▋| 59681/61904 [7:29:54<49:44,  1.34s/it]
 96%|█████████▋| 59682/61904 [7:29:55<50:56,  1.38s/it]
 96%|█████████▋| 59683/61904 [7:29:57<51:05,  1.38s/it]
 96%|█████████▋| 59684/61904 [7:29:58<50:06,  1.35s/it]
 96%|█████████▋| 59685/61904 [7:29:59<50:50,  1.37s/it]
 96%|█████████▋| 59686/61904 [7:30:01<52:14,  1.41s/it]
 96%|█████████▋| 59687/61904 [7:30:02<51:35,  1.40s/it]
 96%|█████████▋| 59688/61904 [7:30:04<53:11,  1.44s/it]
 96%|█████████▋| 59689/61904 [7:30:05<53:53,  1.46s/it]
 96%|█████████▋| 59690/61904 [7:30:07<53:23,  1.45s/it]
 96%|█████████▋| 59691/61904 [7:30:08<53:22,  1.45s/it]
 96%|█████████▋| 59692/61904 [7:30:09<51:16,  1.39s/it]
 96%|█████████▋| 59693/61904 [7:30:11<50:44,  1.38s/it]
 96%|█████████▋| 59694/61904 [7:30:12<50:02,  1.36s/it]
 96%|█████████▋| 59695/61904 [7:30:13<50:30,  1.37s/it]
 96%|█████████▋| 59696/61904 [7:30:15<51:59,  1.41s/it]
 96%|█████████▋| 59697/61904 [7:30:16<50:53,  1.38s/it]
 96%|█████████▋| 59698/61904 [7:30:18<51:32,  1.40s/it]
 96%|█████████▋| 59699/61904 [7:30:19<51:34,  1.40s/it]
 96%|█████████▋| 59700/61904 [7:30:20<50:53,  1.39s/it]
                                                       
{'loss': 2.4366, 'learning_rate': 1.0357189161156489e-07, 'epoch': 15.43}

 96%|█████████▋| 59700/61904 [7:30:20<50:53,  1.39s/it]
 96%|█████████▋| 59701/61904 [7:30:22<49:18,  1.34s/it]
 96%|█████████▋| 59702/61904 [7:30:23<50:26,  1.37s/it]
 96%|█████████▋| 59703/61904 [7:30:24<48:46,  1.33s/it]
 96%|█████████▋| 59704/61904 [7:30:26<49:32,  1.35s/it]
 96%|█████████▋| 59705/61904 [7:30:27<52:16,  1.43s/it]
 96%|█████████▋| 59706/61904 [7:30:29<52:41,  1.44s/it]
 96%|█████████▋| 59707/61904 [7:30:30<52:11,  1.43s/it]
 96%|█████████▋| 59708/61904 [7:30:32<52:30,  1.43s/it]
 96%|█████████▋| 59709/61904 [7:30:33<52:25,  1.43s/it]
 96%|█████████▋| 59710/61904 [7:30:34<51:25,  1.41s/it]
 96%|█████████▋| 59711/61904 [7:30:36<50:25,  1.38s/it]
 96%|█████████▋| 59712/61904 [7:30:37<49:08,  1.34s/it]
 96%|█████████▋| 59713/61904 [7:30:38<48:57,  1.34s/it]
 96%|█████████▋| 59714/61904 [7:30:40<49:14,  1.35s/it]
 96%|█████████▋| 59715/61904 [7:30:41<49:29,  1.36s/it]
 96%|█████████▋| 59716/61904 [7:30:42<49:15,  1.35s/it]
 96%|█████████▋| 59717/61904 [7:30:44<50:26,  1.38s/it]
 96%|█████████▋| 59718/61904 [7:30:45<50:43,  1.39s/it]
 96%|█████████▋| 59719/61904 [7:30:47<50:29,  1.39s/it]
 96%|█████████▋| 59720/61904 [7:30:48<51:23,  1.41s/it]
                                                       
{'loss': 2.4697, 'learning_rate': 1.0353947880202257e-07, 'epoch': 15.43}

 96%|█████████▋| 59720/61904 [7:30:48<51:23,  1.41s/it]
 96%|█████████▋| 59721/61904 [7:30:50<51:11,  1.41s/it]
 96%|█████████▋| 59722/61904 [7:30:51<51:16,  1.41s/it]
 96%|█████████▋| 59723/61904 [7:30:52<51:01,  1.40s/it]
 96%|█████████▋| 59724/61904 [7:30:54<50:04,  1.38s/it]
 96%|█████████▋| 59725/61904 [7:30:55<50:51,  1.40s/it]
 96%|█████████▋| 59726/61904 [7:30:56<49:49,  1.37s/it]
 96%|█████████▋| 59727/61904 [7:30:58<51:11,  1.41s/it]
 96%|█████████▋| 59728/61904 [7:30:59<52:05,  1.44s/it]
 96%|█████████▋| 59729/61904 [7:31:01<50:45,  1.40s/it]
 96%|█████████▋| 59730/61904 [7:31:02<50:38,  1.40s/it]
 96%|█████████▋| 59731/61904 [7:31:03<49:58,  1.38s/it]
 96%|█████████▋| 59732/61904 [7:31:05<48:43,  1.35s/it]
 96%|█████████▋| 59733/61904 [7:31:06<49:39,  1.37s/it]
 96%|█████████▋| 59734/61904 [7:31:08<50:39,  1.40s/it]
 96%|█████████▋| 59735/61904 [7:31:09<51:52,  1.43s/it]
 96%|█████████▋| 59736/61904 [7:31:11<54:16,  1.50s/it]
 96%|█████████▋| 59737/61904 [7:31:12<52:54,  1.46s/it]
 97%|█████████▋| 59738/61904 [7:31:13<50:32,  1.40s/it]
 97%|█████████▋| 59739/61904 [7:31:15<49:01,  1.36s/it]
 97%|█████████▋| 59740/61904 [7:31:16<50:00,  1.39s/it]
                                                       
{'loss': 2.3705, 'learning_rate': 1.0350706599248023e-07, 'epoch': 15.44}

 97%|█████████▋| 59740/61904 [7:31:16<50:00,  1.39s/it]
 97%|█████████▋| 59741/61904 [7:31:18<50:10,  1.39s/it]
 97%|█████████▋| 59742/61904 [7:31:19<49:04,  1.36s/it]
 97%|█████████▋| 59743/61904 [7:31:20<48:47,  1.35s/it]
 97%|█████████▋| 59744/61904 [7:31:22<49:31,  1.38s/it]
 97%|█████████▋| 59745/61904 [7:31:23<49:35,  1.38s/it]
 97%|█████████▋| 59746/61904 [7:31:25<52:18,  1.45s/it]
 97%|█████████▋| 59747/61904 [7:31:26<50:04,  1.39s/it]
 97%|█████████▋| 59748/61904 [7:31:27<49:57,  1.39s/it]
 97%|█████████▋| 59749/61904 [7:31:29<49:24,  1.38s/it]
 97%|█████████▋| 59750/61904 [7:31:30<47:53,  1.33s/it]
 97%|█████████▋| 59751/61904 [7:31:31<49:24,  1.38s/it]
 97%|█████████▋| 59752/61904 [7:31:33<49:30,  1.38s/it]
 97%|█████████▋| 59753/61904 [7:31:34<48:58,  1.37s/it]
 97%|█████████▋| 59754/61904 [7:31:35<49:22,  1.38s/it]
 97%|█████████▋| 59755/61904 [7:31:37<48:40,  1.36s/it]
 97%|█████████▋| 59756/61904 [7:31:38<47:59,  1.34s/it]
 97%|█████████▋| 59757/61904 [7:31:39<48:02,  1.34s/it]
 97%|█████████▋| 59758/61904 [7:31:41<49:54,  1.40s/it]
 97%|█████████▋| 59759/61904 [7:31:42<48:57,  1.37s/it]
 97%|█████████▋| 59760/61904 [7:31:44<49:14,  1.38s/it]
                                                       
{'loss': 2.4004, 'learning_rate': 1.0347465318293789e-07, 'epoch': 15.45}

 97%|█████████▋| 59760/61904 [7:31:44<49:14,  1.38s/it]
 97%|█████████▋| 59761/61904 [7:31:45<49:17,  1.38s/it]
 97%|█████████▋| 59762/61904 [7:31:46<48:10,  1.35s/it]
 97%|█████████▋| 59763/61904 [7:31:48<49:26,  1.39s/it]
 97%|█████████▋| 59764/61904 [7:31:49<50:30,  1.42s/it]
 97%|█████████▋| 59765/61904 [7:31:51<50:12,  1.41s/it]
 97%|█████████▋| 59766/61904 [7:31:52<50:01,  1.40s/it]
 97%|█████████▋| 59767/61904 [7:31:53<49:38,  1.39s/it]
 97%|█████████▋| 59768/61904 [7:31:55<49:06,  1.38s/it]
 97%|█████████▋| 59769/61904 [7:31:56<49:54,  1.40s/it]
 97%|█████████▋| 59770/61904 [7:31:58<50:33,  1.42s/it]
 97%|█████████▋| 59771/61904 [7:31:59<50:47,  1.43s/it]
 97%|█████████▋| 59772/61904 [7:32:00<50:04,  1.41s/it]
 97%|█████████▋| 59773/61904 [7:32:02<49:55,  1.41s/it]
 97%|█████████▋| 59774/61904 [7:32:03<50:41,  1.43s/it]
 97%|█████████▋| 59775/61904 [7:32:05<49:44,  1.40s/it]
 97%|█████████▋| 59776/61904 [7:32:06<49:27,  1.39s/it]
 97%|█████████▋| 59777/61904 [7:32:08<49:49,  1.41s/it]
 97%|█████████▋| 59778/61904 [7:32:09<49:02,  1.38s/it]
 97%|█████████▋| 59779/61904 [7:32:10<48:46,  1.38s/it]
 97%|█████████▋| 59780/61904 [7:32:12<48:44,  1.38s/it]
                                                       
{'loss': 2.4214, 'learning_rate': 1.0344224037339557e-07, 'epoch': 15.45}

 97%|█████████▋| 59780/61904 [7:32:12<48:44,  1.38s/it]
 97%|█████████▋| 59781/61904 [7:32:13<47:21,  1.34s/it]
 97%|█████████▋| 59782/61904 [7:32:14<47:17,  1.34s/it]
 97%|█████████▋| 59783/61904 [7:32:16<47:51,  1.35s/it]
 97%|█████████▋| 59784/61904 [7:32:17<48:50,  1.38s/it]
 97%|█████████▋| 59785/61904 [7:32:18<48:24,  1.37s/it]
 97%|█████████▋| 59786/61904 [7:32:20<48:36,  1.38s/it]
 97%|█████████▋| 59787/61904 [7:32:21<48:17,  1.37s/it]
 97%|█████████▋| 59788/61904 [7:32:22<48:11,  1.37s/it]
 97%|█████████▋| 59789/61904 [7:32:24<50:44,  1.44s/it]
 97%|█████████▋| 59790/61904 [7:32:26<52:03,  1.48s/it]
 97%|█████████▋| 59791/61904 [7:32:27<50:37,  1.44s/it]
 97%|█████████▋| 59792/61904 [7:32:28<48:56,  1.39s/it]
 97%|█████████▋| 59793/61904 [7:32:30<48:39,  1.38s/it]
 97%|█████████▋| 59794/61904 [7:32:31<47:40,  1.36s/it]
 97%|█████████▋| 59795/61904 [7:32:32<48:06,  1.37s/it]
 97%|█████████▋| 59796/61904 [7:32:34<47:29,  1.35s/it]
 97%|█████████▋| 59797/61904 [7:32:35<48:23,  1.38s/it]
 97%|█████████▋| 59798/61904 [7:32:37<49:23,  1.41s/it]
 97%|█████████▋| 59799/61904 [7:32:38<49:06,  1.40s/it]
 97%|█████████▋| 59800/61904 [7:32:39<48:45,  1.39s/it]
                                                       
{'loss': 2.4458, 'learning_rate': 1.0340982756385324e-07, 'epoch': 15.46}

 97%|█████████▋| 59800/61904 [7:32:39<48:45,  1.39s/it]
 97%|█████████▋| 59801/61904 [7:32:41<48:36,  1.39s/it]
 97%|█████████▋| 59802/61904 [7:32:42<46:32,  1.33s/it]
 97%|█████████▋| 59803/61904 [7:32:43<45:57,  1.31s/it]
 97%|█████████▋| 59804/61904 [7:32:45<46:36,  1.33s/it]
 97%|█████████▋| 59805/61904 [7:32:46<47:42,  1.36s/it]
 97%|█████████▋| 59806/61904 [7:32:47<48:09,  1.38s/it]
 97%|█████████▋| 59807/61904 [7:32:49<49:23,  1.41s/it]
 97%|█████████▋| 59808/61904 [7:32:50<51:08,  1.46s/it]
 97%|█████████▋| 59809/61904 [7:32:52<48:46,  1.40s/it]
 97%|█████████▋| 59810/61904 [7:32:53<47:29,  1.36s/it]
 97%|█████████▋| 59811/61904 [7:32:54<49:14,  1.41s/it]
 97%|█████████▋| 59812/61904 [7:32:56<49:00,  1.41s/it]
 97%|█████████▋| 59813/61904 [7:32:57<47:40,  1.37s/it]
 97%|█████████▋| 59814/61904 [7:32:59<47:26,  1.36s/it]
 97%|█████████▋| 59815/61904 [7:33:00<47:22,  1.36s/it]
 97%|█████████▋| 59816/61904 [7:33:01<47:42,  1.37s/it]
 97%|█████████▋| 59817/61904 [7:33:03<47:50,  1.38s/it]
 97%|█████████▋| 59818/61904 [7:33:04<46:58,  1.35s/it]
 97%|█████████▋| 59819/61904 [7:33:05<47:30,  1.37s/it]
 97%|█████████▋| 59820/61904 [7:33:07<49:38,  1.43s/it]
                                                       
{'loss': 2.4129, 'learning_rate': 1.033774147543109e-07, 'epoch': 15.46}

 97%|█████████▋| 59820/61904 [7:33:07<49:38,  1.43s/it]
 97%|█████████▋| 59821/61904 [7:33:08<48:58,  1.41s/it]
 97%|█████████▋| 59822/61904 [7:33:10<47:29,  1.37s/it]
 97%|█████████▋| 59823/61904 [7:33:11<45:57,  1.33s/it]
 97%|█████████▋| 59824/61904 [7:33:12<45:32,  1.31s/it]
 97%|█████████▋| 59825/61904 [7:33:13<46:13,  1.33s/it]
 97%|█████████▋| 59826/61904 [7:33:15<45:42,  1.32s/it]
 97%|█████████▋| 59827/61904 [7:33:16<45:14,  1.31s/it]
 97%|█████████▋| 59828/61904 [7:33:17<45:24,  1.31s/it]
 97%|█████████▋| 59829/61904 [7:33:19<46:03,  1.33s/it]
 97%|█████████▋| 59830/61904 [7:33:20<46:29,  1.35s/it]
 97%|█████████▋| 59831/61904 [7:33:21<45:56,  1.33s/it]
 97%|█████████▋| 59832/61904 [7:33:23<45:27,  1.32s/it]
 97%|█████████▋| 59833/61904 [7:33:24<43:46,  1.27s/it]
 97%|█████████▋| 59834/61904 [7:33:25<45:16,  1.31s/it]
 97%|█████████▋| 59835/61904 [7:33:26<44:24,  1.29s/it]
 97%|█████████▋| 59836/61904 [7:33:28<47:09,  1.37s/it]
 97%|█████████▋| 59837/61904 [7:33:29<48:01,  1.39s/it]
 97%|█████████▋| 59838/61904 [7:33:31<47:26,  1.38s/it]
 97%|█████████▋| 59839/61904 [7:33:32<47:32,  1.38s/it]
 97%|█████████▋| 59840/61904 [7:33:34<48:27,  1.41s/it]
                                                       
{'loss': 2.3648, 'learning_rate': 1.0334500194476858e-07, 'epoch': 15.47}

 97%|█████████▋| 59840/61904 [7:33:34<48:27,  1.41s/it]
 97%|█████████▋| 59841/61904 [7:33:35<48:07,  1.40s/it]
 97%|█████████▋| 59842/61904 [7:33:36<46:31,  1.35s/it]
 97%|█████████▋| 59843/61904 [7:33:38<48:56,  1.42s/it]
 97%|█████████▋| 59844/61904 [7:33:39<48:05,  1.40s/it]
 97%|█████████▋| 59845/61904 [7:33:41<46:34,  1.36s/it]
 97%|█████████▋| 59846/61904 [7:33:42<46:58,  1.37s/it]
 97%|█████████▋| 59847/61904 [7:33:43<46:53,  1.37s/it]
 97%|█████████▋| 59848/61904 [7:33:45<46:32,  1.36s/it]
 97%|█████████▋| 59849/61904 [7:33:46<46:06,  1.35s/it]
 97%|█████████▋| 59850/61904 [7:33:47<47:39,  1.39s/it]
 97%|█████████▋| 59851/61904 [7:33:49<46:58,  1.37s/it]
 97%|█████████▋| 59852/61904 [7:33:50<47:27,  1.39s/it]
 97%|█████████▋| 59853/61904 [7:33:52<47:24,  1.39s/it]
 97%|█████████▋| 59854/61904 [7:33:53<47:38,  1.39s/it]
 97%|█████████▋| 59855/61904 [7:33:54<48:01,  1.41s/it]
 97%|█████████▋| 59856/61904 [7:33:56<46:28,  1.36s/it]
 97%|█████████▋| 59857/61904 [7:33:57<45:26,  1.33s/it]
 97%|█████████▋| 59858/61904 [7:33:58<46:54,  1.38s/it]
 97%|█████████▋| 59859/61904 [7:34:00<47:27,  1.39s/it]
 97%|█████████▋| 59860/61904 [7:34:01<47:01,  1.38s/it]
                                                       
{'loss': 2.3726, 'learning_rate': 1.0331258913522624e-07, 'epoch': 15.47}

 97%|█████████▋| 59860/61904 [7:34:01<47:01,  1.38s/it]
 97%|█████████▋| 59861/61904 [7:34:02<46:16,  1.36s/it]
 97%|█████████▋| 59862/61904 [7:34:04<46:57,  1.38s/it]
 97%|█████████▋| 59863/61904 [7:34:05<46:57,  1.38s/it]
 97%|█████████▋| 59864/61904 [7:34:07<46:03,  1.35s/it]
 97%|█████████▋| 59865/61904 [7:34:08<46:14,  1.36s/it]
 97%|█████████▋| 59866/61904 [7:34:09<46:04,  1.36s/it]
 97%|█████████▋| 59867/61904 [7:34:11<45:26,  1.34s/it]
 97%|█████████▋| 59868/61904 [7:34:12<45:04,  1.33s/it]
 97%|█████████▋| 59869/61904 [7:34:13<45:18,  1.34s/it]
 97%|█████████▋| 59870/61904 [7:34:15<46:18,  1.37s/it]
 97%|█████████▋| 59871/61904 [7:34:16<45:39,  1.35s/it]
 97%|█████████▋| 59872/61904 [7:34:17<45:28,  1.34s/it]
 97%|█████████▋| 59873/61904 [7:34:19<46:29,  1.37s/it]
 97%|█████████▋| 59874/61904 [7:34:20<46:18,  1.37s/it]
 97%|█████████▋| 59875/61904 [7:34:22<46:39,  1.38s/it]
 97%|█████████▋| 59876/61904 [7:34:23<46:18,  1.37s/it]
 97%|█████████▋| 59877/61904 [7:34:24<46:29,  1.38s/it]
 97%|█████████▋| 59878/61904 [7:34:26<47:23,  1.40s/it]
 97%|█████████▋| 59879/61904 [7:34:27<47:02,  1.39s/it]
 97%|█████████▋| 59880/61904 [7:34:29<47:33,  1.41s/it]
                                                       
{'loss': 2.4154, 'learning_rate': 1.0328017632568392e-07, 'epoch': 15.48}

 97%|█████████▋| 59880/61904 [7:34:29<47:33,  1.41s/it]
 97%|█████████▋| 59881/61904 [7:34:30<46:52,  1.39s/it]
 97%|█████████▋| 59882/61904 [7:34:31<46:22,  1.38s/it]
 97%|█████████▋| 59883/61904 [7:34:33<45:43,  1.36s/it]
 97%|█████████▋| 59884/61904 [7:34:34<45:19,  1.35s/it]
 97%|█████████▋| 59885/61904 [7:34:35<47:40,  1.42s/it]
 97%|█████████▋| 59886/61904 [7:34:37<47:30,  1.41s/it]
 97%|█████████▋| 59887/61904 [7:34:38<47:31,  1.41s/it]
 97%|█████████▋| 59888/61904 [7:34:40<46:59,  1.40s/it]
 97%|█████████▋| 59889/61904 [7:34:41<47:09,  1.40s/it]
 97%|█████████▋| 59890/61904 [7:34:42<46:28,  1.38s/it]
 97%|█████████▋| 59891/61904 [7:34:44<46:32,  1.39s/it]
 97%|█████████▋| 59892/61904 [7:34:45<46:51,  1.40s/it]
 97%|█████████▋| 59893/61904 [7:34:47<47:49,  1.43s/it]
 97%|█████████▋| 59894/61904 [7:34:48<48:40,  1.45s/it]
 97%|█████████▋| 59895/61904 [7:34:50<48:47,  1.46s/it]
 97%|█████████▋| 59896/61904 [7:34:51<46:57,  1.40s/it]
 97%|█████████▋| 59897/61904 [7:34:52<46:56,  1.40s/it]
 97%|█████████▋| 59898/61904 [7:34:54<46:21,  1.39s/it]
 97%|█████████▋| 59899/61904 [7:34:55<47:01,  1.41s/it]
 97%|█████████▋| 59900/61904 [7:34:56<45:36,  1.37s/it]
                                                       
{'loss': 2.41, 'learning_rate': 1.0324776351614158e-07, 'epoch': 15.48}

 97%|█████████▋| 59900/61904 [7:34:56<45:36,  1.37s/it]
 97%|█████████▋| 59901/61904 [7:34:58<46:19,  1.39s/it]
 97%|█████████▋| 59902/61904 [7:34:59<46:59,  1.41s/it]
 97%|█████████▋| 59903/61904 [7:35:01<45:58,  1.38s/it]
 97%|█████████▋| 59904/61904 [7:35:02<47:11,  1.42s/it]
 97%|█████████▋| 59905/61904 [7:35:03<45:51,  1.38s/it]
 97%|█████████▋| 59906/61904 [7:35:05<45:02,  1.35s/it]
 97%|█████████▋| 59907/61904 [7:35:06<45:37,  1.37s/it]
 97%|█████████▋| 59908/61904 [7:35:07<45:11,  1.36s/it]
 97%|█████████▋| 59909/61904 [7:35:09<44:39,  1.34s/it]
 97%|█████████▋| 59910/61904 [7:35:10<44:32,  1.34s/it]
 97%|█████████▋| 59911/61904 [7:35:11<44:04,  1.33s/it]
 97%|█████████▋| 59912/61904 [7:35:13<45:23,  1.37s/it]
 97%|█████████▋| 59913/61904 [7:35:14<45:56,  1.38s/it]
 97%|█████████▋| 59914/61904 [7:35:16<46:56,  1.42s/it]
 97%|█████████▋| 59915/61904 [7:35:17<46:52,  1.41s/it]
 97%|█████████▋| 59916/61904 [7:35:19<47:22,  1.43s/it]
 97%|█████████▋| 59917/61904 [7:35:20<47:42,  1.44s/it]
 97%|█████████▋| 59918/61904 [7:35:22<47:51,  1.45s/it]
 97%|█████████▋| 59919/61904 [7:35:23<45:44,  1.38s/it]
 97%|█████████▋| 59920/61904 [7:35:24<44:52,  1.36s/it]
                                                       
{'loss': 2.4175, 'learning_rate': 1.0321535070659925e-07, 'epoch': 15.49}

 97%|█████████▋| 59920/61904 [7:35:24<44:52,  1.36s/it]
 97%|█████████▋| 59921/61904 [7:35:25<44:41,  1.35s/it]
 97%|█████████▋| 59922/61904 [7:35:27<44:23,  1.34s/it]
 97%|█████████▋| 59923/61904 [7:35:28<44:27,  1.35s/it]
 97%|█████████▋| 59924/61904 [7:35:30<44:54,  1.36s/it]
 97%|█████████▋| 59925/61904 [7:35:31<45:03,  1.37s/it]
 97%|█████████▋| 59926/61904 [7:35:32<44:34,  1.35s/it]
 97%|█████████▋| 59927/61904 [7:35:33<43:24,  1.32s/it]
 97%|█████████▋| 59928/61904 [7:35:35<42:25,  1.29s/it]
 97%|█████████▋| 59929/61904 [7:35:36<44:29,  1.35s/it]
 97%|█████████▋| 59930/61904 [7:35:37<43:08,  1.31s/it]
 97%|█████████▋| 59931/61904 [7:35:39<42:58,  1.31s/it]
 97%|█████████▋| 59932/61904 [7:35:40<43:39,  1.33s/it]
 97%|█████████▋| 59933/61904 [7:35:41<43:05,  1.31s/it]
 97%|█████████▋| 59934/61904 [7:35:43<44:05,  1.34s/it]
 97%|█████████▋| 59935/61904 [7:35:44<44:17,  1.35s/it]
 97%|█████████▋| 59936/61904 [7:35:45<44:02,  1.34s/it]
 97%|█████████▋| 59937/61904 [7:35:47<43:16,  1.32s/it]
 97%|█████████▋| 59938/61904 [7:35:48<43:26,  1.33s/it]
 97%|█████████▋| 59939/61904 [7:35:49<43:39,  1.33s/it]
 97%|█████████▋| 59940/61904 [7:35:51<43:30,  1.33s/it]
                                                       
{'loss': 2.4498, 'learning_rate': 1.0318293789705691e-07, 'epoch': 15.49}

 97%|█████████▋| 59940/61904 [7:35:51<43:30,  1.33s/it]
 97%|█████████▋| 59941/61904 [7:35:52<43:29,  1.33s/it]
 97%|█████████▋| 59942/61904 [7:35:53<43:49,  1.34s/it]
 97%|█████████▋| 59943/61904 [7:35:55<44:21,  1.36s/it]
 97%|█████████▋| 59944/61904 [7:35:56<44:41,  1.37s/it]
 97%|█████████▋| 59945/61904 [7:35:58<45:12,  1.38s/it]
 97%|█████████▋| 59946/61904 [7:35:59<44:51,  1.37s/it]
 97%|█████████▋| 59947/61904 [7:36:00<45:47,  1.40s/it]
 97%|█████████▋| 59948/61904 [7:36:02<45:24,  1.39s/it]
 97%|█████████▋| 59949/61904 [7:36:03<46:03,  1.41s/it]
 97%|█████████▋| 59950/61904 [7:36:05<46:57,  1.44s/it]
 97%|█████████▋| 59951/61904 [7:36:06<45:28,  1.40s/it]
 97%|█████████▋| 59952/61904 [7:36:07<44:24,  1.37s/it]
 97%|█████████▋| 59953/61904 [7:36:09<45:52,  1.41s/it]
 97%|█████████▋| 59954/61904 [7:36:10<47:12,  1.45s/it]
 97%|█████████▋| 59955/61904 [7:36:12<46:17,  1.42s/it]
 97%|█████████▋| 59956/61904 [7:36:13<45:16,  1.39s/it]
 97%|█████████▋| 59957/61904 [7:36:14<43:32,  1.34s/it]
 97%|█████████▋| 59958/61904 [7:36:16<45:10,  1.39s/it]
 97%|█████████▋| 59959/61904 [7:36:17<44:06,  1.36s/it]
 97%|█████████▋| 59960/61904 [7:36:19<44:21,  1.37s/it]
                                                       
{'loss': 2.4872, 'learning_rate': 1.0315052508751459e-07, 'epoch': 15.5}

 97%|█████████▋| 59960/61904 [7:36:19<44:21,  1.37s/it]
 97%|█████████▋| 59961/61904 [7:36:20<44:27,  1.37s/it]
 97%|█████████▋| 59962/61904 [7:36:21<44:02,  1.36s/it]
 97%|█████████▋| 59963/61904 [7:36:23<44:31,  1.38s/it]
 97%|█████████▋| 59964/61904 [7:36:24<44:30,  1.38s/it]
 97%|█████████▋| 59965/61904 [7:36:25<44:55,  1.39s/it]
 97%|█████████▋| 59966/61904 [7:36:27<44:20,  1.37s/it]
 97%|█████████▋| 59967/61904 [7:36:28<43:38,  1.35s/it]
 97%|█████████▋| 59968/61904 [7:36:30<44:20,  1.37s/it]
 97%|█████████▋| 59969/61904 [7:36:31<44:18,  1.37s/it]
 97%|█████████▋| 59970/61904 [7:36:32<43:49,  1.36s/it]
 97%|█████████▋| 59971/61904 [7:36:33<41:57,  1.30s/it]
 97%|█████████▋| 59972/61904 [7:36:35<43:35,  1.35s/it]
 97%|█████████▋| 59973/61904 [7:36:36<45:02,  1.40s/it]
 97%|█████████▋| 59974/61904 [7:36:38<44:54,  1.40s/it]
 97%|█████████▋| 59975/61904 [7:36:39<45:20,  1.41s/it]
 97%|█████████▋| 59976/61904 [7:36:41<45:14,  1.41s/it]
 97%|█████████▋| 59977/61904 [7:36:42<45:26,  1.41s/it]
 97%|█████████▋| 59978/61904 [7:36:43<44:27,  1.38s/it]
 97%|█████████▋| 59979/61904 [7:36:45<45:49,  1.43s/it]
 97%|█████████▋| 59980/61904 [7:36:46<44:35,  1.39s/it]
                                                       
{'loss': 2.3658, 'learning_rate': 1.0311811227797225e-07, 'epoch': 15.5}

 97%|█████████▋| 59980/61904 [7:36:46<44:35,  1.39s/it]
 97%|█████████▋| 59981/61904 [7:36:48<44:52,  1.40s/it]
 97%|█████████▋| 59982/61904 [7:36:49<45:14,  1.41s/it]
 97%|█████████▋| 59983/61904 [7:36:51<45:51,  1.43s/it]
 97%|█████████▋| 59984/61904 [7:36:52<46:40,  1.46s/it]
 97%|█████████▋| 59985/61904 [7:36:54<46:40,  1.46s/it]
 97%|█████████▋| 59986/61904 [7:36:55<47:16,  1.48s/it]
 97%|█████████▋| 59987/61904 [7:36:56<45:25,  1.42s/it]
 97%|█████████▋| 59988/61904 [7:36:58<45:09,  1.41s/it]
 97%|█████████▋| 59989/61904 [7:36:59<44:57,  1.41s/it]
 97%|█████████▋| 59990/61904 [7:37:01<45:19,  1.42s/it]
 97%|█████████▋| 59991/61904 [7:37:02<45:51,  1.44s/it]
 97%|█████████▋| 59992/61904 [7:37:04<46:16,  1.45s/it]
 97%|█████████▋| 59993/61904 [7:37:05<45:43,  1.44s/it]
 97%|█████████▋| 59994/61904 [7:37:06<46:29,  1.46s/it]
 97%|█████████▋| 59995/61904 [7:37:08<46:35,  1.46s/it]
 97%|█████████▋| 59996/61904 [7:37:09<46:14,  1.45s/it]
 97%|█████████▋| 59997/61904 [7:37:11<44:39,  1.40s/it]
 97%|█████████▋| 59998/61904 [7:37:12<43:57,  1.38s/it]
 97%|█████████▋| 59999/61904 [7:37:13<44:03,  1.39s/it]
 97%|█████████▋| 60000/61904 [7:37:15<43:07,  1.36s/it]
                                                       
{'loss': 2.4036, 'learning_rate': 1.0308569946842993e-07, 'epoch': 15.51}

 97%|█████████▋| 60000/61904 [7:37:15<43:07,  1.36s/it]
 97%|█████████▋| 60001/61904 [7:37:16<43:07,  1.36s/it]
 97%|█████████▋| 60002/61904 [7:37:17<42:12,  1.33s/it]
 97%|█████████▋| 60003/61904 [7:37:19<46:01,  1.45s/it]
 97%|█████████▋| 60004/61904 [7:37:21<46:16,  1.46s/it]
 97%|█████████▋| 60005/61904 [7:37:22<45:04,  1.42s/it]
 97%|█████████▋| 60006/61904 [7:37:23<44:39,  1.41s/it]
 97%|█████████▋| 60007/61904 [7:37:25<43:25,  1.37s/it]
 97%|█████████▋| 60008/61904 [7:37:26<42:20,  1.34s/it]
 97%|█████████▋| 60009/61904 [7:37:27<44:08,  1.40s/it]
 97%|█████████▋| 60010/61904 [7:37:29<44:31,  1.41s/it]
 97%|█████████▋| 60011/61904 [7:37:30<43:50,  1.39s/it]
 97%|█████████▋| 60012/61904 [7:37:32<45:33,  1.44s/it]
 97%|█████████▋| 60013/61904 [7:37:33<45:12,  1.43s/it]
 97%|█████████▋| 60014/61904 [7:37:34<43:23,  1.38s/it]
 97%|█████████▋| 60015/61904 [7:37:36<42:14,  1.34s/it]
 97%|█████████▋| 60016/61904 [7:37:37<42:35,  1.35s/it]
 97%|█████████▋| 60017/61904 [7:37:38<41:46,  1.33s/it]
 97%|█████████▋| 60018/61904 [7:37:40<42:56,  1.37s/it]
 97%|█████████▋| 60019/61904 [7:37:41<42:53,  1.37s/it]
 97%|█████████▋| 60020/61904 [7:37:43<43:48,  1.40s/it]
                                                       
{'loss': 2.4134, 'learning_rate': 1.0305328665888759e-07, 'epoch': 15.51}

 97%|█████████▋| 60020/61904 [7:37:43<43:48,  1.40s/it]
 97%|█████████▋| 60021/61904 [7:37:44<43:32,  1.39s/it]
 97%|█████████▋| 60022/61904 [7:37:45<44:41,  1.43s/it]
 97%|█████████▋| 60023/61904 [7:37:47<43:06,  1.37s/it]
 97%|█████████▋| 60024/61904 [7:37:48<43:48,  1.40s/it]
 97%|█████████▋| 60025/61904 [7:37:49<42:47,  1.37s/it]
 97%|█████████▋| 60026/61904 [7:37:51<43:42,  1.40s/it]
 97%|█████████▋| 60027/61904 [7:37:52<43:21,  1.39s/it]
 97%|█████████▋| 60028/61904 [7:37:54<42:19,  1.35s/it]
 97%|█████████▋| 60029/61904 [7:37:55<42:23,  1.36s/it]
 97%|█████████▋| 60030/61904 [7:37:56<41:50,  1.34s/it]
 97%|█████████▋| 60031/61904 [7:37:58<42:50,  1.37s/it]
 97%|█████████▋| 60032/61904 [7:37:59<42:52,  1.37s/it]
 97%|█████████▋| 60033/61904 [7:38:00<41:26,  1.33s/it]
 97%|█████████▋| 60034/61904 [7:38:02<41:51,  1.34s/it]
 97%|█████████▋| 60035/61904 [7:38:03<42:36,  1.37s/it]
 97%|█████████▋| 60036/61904 [7:38:04<43:02,  1.38s/it]
 97%|█████████▋| 60037/61904 [7:38:06<44:32,  1.43s/it]
 97%|█████████▋| 60038/61904 [7:38:07<44:13,  1.42s/it]
 97%|█████████▋| 60039/61904 [7:38:09<43:45,  1.41s/it]
 97%|█████████▋| 60040/61904 [7:38:10<43:34,  1.40s/it]
                                                       
{'loss': 2.4383, 'learning_rate': 1.0302087384934526e-07, 'epoch': 15.52}

 97%|█████████▋| 60040/61904 [7:38:10<43:34,  1.40s/it]
 97%|█████████▋| 60041/61904 [7:38:11<42:34,  1.37s/it]
 97%|█████████▋| 60042/61904 [7:38:13<43:34,  1.40s/it]
 97%|█████████▋| 60043/61904 [7:38:14<42:27,  1.37s/it]
 97%|█████████▋| 60044/61904 [7:38:16<43:06,  1.39s/it]
 97%|█████████▋| 60045/61904 [7:38:17<43:25,  1.40s/it]
 97%|█████████▋| 60046/61904 [7:38:18<42:23,  1.37s/it]
 97%|█████████▋| 60047/61904 [7:38:20<42:55,  1.39s/it]
 97%|█████████▋| 60048/61904 [7:38:21<44:12,  1.43s/it]
 97%|█████████▋| 60049/61904 [7:38:23<44:00,  1.42s/it]
 97%|█████████▋| 60050/61904 [7:38:24<43:10,  1.40s/it]
 97%|█████████▋| 60051/61904 [7:38:25<43:01,  1.39s/it]
 97%|█████████▋| 60052/61904 [7:38:27<43:41,  1.42s/it]
 97%|█████████▋| 60053/61904 [7:38:28<43:41,  1.42s/it]
 97%|█████████▋| 60054/61904 [7:38:30<44:37,  1.45s/it]
 97%|█████████▋| 60055/61904 [7:38:31<44:05,  1.43s/it]
 97%|█████████▋| 60056/61904 [7:38:33<43:13,  1.40s/it]
 97%|█████████▋| 60057/61904 [7:38:34<42:56,  1.40s/it]
 97%|█████████▋| 60058/61904 [7:38:35<43:30,  1.41s/it]
 97%|█████████▋| 60059/61904 [7:38:37<43:18,  1.41s/it]
 97%|█████████▋| 60060/61904 [7:38:38<42:37,  1.39s/it]
                                                       
{'loss': 2.3699, 'learning_rate': 1.0298846103980293e-07, 'epoch': 15.52}

 97%|█████████▋| 60060/61904 [7:38:38<42:37,  1.39s/it]
 97%|█████████▋| 60061/61904 [7:38:40<43:41,  1.42s/it]
 97%|█████████▋| 60062/61904 [7:38:41<42:55,  1.40s/it]
 97%|█████████▋| 60063/61904 [7:38:43<44:18,  1.44s/it]
 97%|█████████▋| 60064/61904 [7:38:44<42:33,  1.39s/it]
 97%|█████████▋| 60065/61904 [7:38:45<44:07,  1.44s/it]
 97%|█████████▋| 60066/61904 [7:38:47<43:57,  1.43s/it]
 97%|█████████▋| 60067/61904 [7:38:48<42:22,  1.38s/it]
 97%|█████████▋| 60068/61904 [7:38:50<42:41,  1.39s/it]
 97%|█████████▋| 60069/61904 [7:38:51<43:13,  1.41s/it]
 97%|█████████▋| 60070/61904 [7:38:52<42:43,  1.40s/it]
 97%|█████████▋| 60071/61904 [7:38:54<43:05,  1.41s/it]
 97%|█████████▋| 60072/61904 [7:38:55<42:35,  1.39s/it]
 97%|█████████▋| 60073/61904 [7:38:56<41:47,  1.37s/it]
 97%|█████████▋| 60074/61904 [7:38:58<42:47,  1.40s/it]
 97%|█████████▋| 60075/61904 [7:38:59<43:40,  1.43s/it]
 97%|█████████▋| 60076/61904 [7:39:01<42:53,  1.41s/it]
 97%|█████████▋| 60077/61904 [7:39:02<42:48,  1.41s/it]
 97%|█████████▋| 60078/61904 [7:39:04<42:24,  1.39s/it]
 97%|█████████▋| 60079/61904 [7:39:05<42:21,  1.39s/it]
 97%|█████████▋| 60080/61904 [7:39:06<43:25,  1.43s/it]
                                                       
{'loss': 2.3865, 'learning_rate': 1.029560482302606e-07, 'epoch': 15.53}

 97%|█████████▋| 60080/61904 [7:39:06<43:25,  1.43s/it]
 97%|█████████▋| 60081/61904 [7:39:08<44:46,  1.47s/it]
 97%|█████████▋| 60082/61904 [7:39:09<43:43,  1.44s/it]
 97%|█████████▋| 60083/61904 [7:39:11<43:58,  1.45s/it]
 97%|█████████▋| 60084/61904 [7:39:12<43:42,  1.44s/it]
 97%|█████████▋| 60085/61904 [7:39:14<42:36,  1.41s/it]
 97%|█████████▋| 60086/61904 [7:39:15<42:11,  1.39s/it]
 97%|█████████▋| 60087/61904 [7:39:16<42:33,  1.41s/it]
 97%|█████████▋| 60088/61904 [7:39:18<43:54,  1.45s/it]
 97%|█████████▋| 60089/61904 [7:39:19<43:37,  1.44s/it]
 97%|█████████▋| 60090/61904 [7:39:21<44:30,  1.47s/it]
 97%|█████████▋| 60091/61904 [7:39:22<43:00,  1.42s/it]
 97%|█████████▋| 60092/61904 [7:39:24<42:56,  1.42s/it]
 97%|█████████▋| 60093/61904 [7:39:25<42:55,  1.42s/it]
 97%|█████████▋| 60094/61904 [7:39:26<42:04,  1.39s/it]
 97%|█████████▋| 60095/61904 [7:39:28<42:17,  1.40s/it]
 97%|█████████▋| 60096/61904 [7:39:29<42:27,  1.41s/it]
 97%|█████████▋| 60097/61904 [7:39:31<42:07,  1.40s/it]
 97%|█████████▋| 60098/61904 [7:39:32<41:19,  1.37s/it]
 97%|█████████▋| 60099/61904 [7:39:33<41:25,  1.38s/it]
 97%|█████████▋| 60100/61904 [7:39:35<40:48,  1.36s/it]
                                                       
{'loss': 2.3725, 'learning_rate': 1.0292363542071826e-07, 'epoch': 15.53}

 97%|█████████▋| 60100/61904 [7:39:35<40:48,  1.36s/it]
 97%|█████████▋| 60101/61904 [7:39:36<41:12,  1.37s/it]
 97%|█████████▋| 60102/61904 [7:39:37<40:46,  1.36s/it]
 97%|█████████▋| 60103/61904 [7:39:39<42:45,  1.42s/it]
 97%|█████████▋| 60104/61904 [7:39:40<42:21,  1.41s/it]
 97%|█████████▋| 60105/61904 [7:39:42<42:00,  1.40s/it]
 97%|█████████▋| 60106/61904 [7:39:43<40:26,  1.35s/it]
 97%|█████████▋| 60107/61904 [7:39:44<40:47,  1.36s/it]
 97%|█████████▋| 60108/61904 [7:39:46<40:12,  1.34s/it]
 97%|█████████▋| 60109/61904 [7:39:47<40:43,  1.36s/it]
 97%|█████████▋| 60110/61904 [7:39:48<41:24,  1.39s/it]
 97%|█████████▋| 60111/61904 [7:39:50<41:32,  1.39s/it]
 97%|█████████▋| 60112/61904 [7:39:51<41:05,  1.38s/it]
 97%|█████████▋| 60113/61904 [7:39:53<45:49,  1.54s/it]
 97%|█████████▋| 60114/61904 [7:39:55<44:47,  1.50s/it]
 97%|█████████▋| 60115/61904 [7:39:56<43:45,  1.47s/it]
 97%|█████████▋| 60116/61904 [7:39:57<42:21,  1.42s/it]
 97%|█████████▋| 60117/61904 [7:39:59<41:47,  1.40s/it]
 97%|█████████▋| 60118/61904 [7:40:00<41:47,  1.40s/it]
 97%|█████████▋| 60119/61904 [7:40:02<43:06,  1.45s/it]
 97%|█████████▋| 60120/61904 [7:40:03<42:52,  1.44s/it]
                                                       
{'loss': 2.3363, 'learning_rate': 1.0289122261117594e-07, 'epoch': 15.54}

 97%|█████████▋| 60120/61904 [7:40:03<42:52,  1.44s/it]
 97%|█████████▋| 60121/61904 [7:40:04<41:39,  1.40s/it]
 97%|█████████▋| 60122/61904 [7:40:06<41:05,  1.38s/it]
 97%|█████████▋| 60123/61904 [7:40:07<40:06,  1.35s/it]
 97%|█████████▋| 60124/61904 [7:40:09<42:49,  1.44s/it]
 97%|█████████▋| 60125/61904 [7:40:10<42:08,  1.42s/it]
 97%|█████████▋| 60126/61904 [7:40:11<41:39,  1.41s/it]
 97%|█████████▋| 60127/61904 [7:40:13<42:03,  1.42s/it]
 97%|█████████▋| 60128/61904 [7:40:14<40:45,  1.38s/it]
 97%|█████████▋| 60129/61904 [7:40:16<41:54,  1.42s/it]
 97%|█████████▋| 60130/61904 [7:40:17<40:23,  1.37s/it]
 97%|█████████▋| 60131/61904 [7:40:18<40:20,  1.37s/it]
 97%|█████████▋| 60132/61904 [7:40:20<40:26,  1.37s/it]
 97%|█████████▋| 60133/61904 [7:40:21<40:31,  1.37s/it]
 97%|█████████▋| 60134/61904 [7:40:22<42:09,  1.43s/it]
 97%|█████████▋| 60135/61904 [7:40:24<41:17,  1.40s/it]
 97%|█████████▋| 60136/61904 [7:40:25<41:03,  1.39s/it]
 97%|█████████▋| 60137/61904 [7:40:27<41:22,  1.40s/it]
 97%|█████████▋| 60138/61904 [7:40:28<41:21,  1.41s/it]
 97%|█████████▋| 60139/61904 [7:40:29<41:35,  1.41s/it]
 97%|█████████▋| 60140/61904 [7:40:31<41:37,  1.42s/it]
                                                       
{'loss': 2.3921, 'learning_rate': 1.028588098016336e-07, 'epoch': 15.54}

 97%|█████████▋| 60140/61904 [7:40:31<41:37,  1.42s/it]
 97%|█████████▋| 60141/61904 [7:40:32<40:57,  1.39s/it]
 97%|█████████▋| 60142/61904 [7:40:34<40:13,  1.37s/it]
 97%|█████████▋| 60143/61904 [7:40:35<42:09,  1.44s/it]
 97%|█████████▋| 60144/61904 [7:40:36<41:08,  1.40s/it]
 97%|█████████▋| 60145/61904 [7:40:38<41:31,  1.42s/it]
 97%|█████████▋| 60146/61904 [7:40:39<40:05,  1.37s/it]
 97%|█████████▋| 60147/61904 [7:40:41<40:13,  1.37s/it]
 97%|█████████▋| 60148/61904 [7:40:42<41:23,  1.41s/it]
 97%|█████████▋| 60149/61904 [7:40:43<39:49,  1.36s/it]
 97%|█████████▋| 60150/61904 [7:40:45<41:10,  1.41s/it]
 97%|█████████▋| 60151/61904 [7:40:46<40:00,  1.37s/it]
 97%|█████████▋| 60152/61904 [7:40:47<39:24,  1.35s/it]
 97%|█████████▋| 60153/61904 [7:40:49<41:03,  1.41s/it]
 97%|█████████▋| 60154/61904 [7:40:50<39:43,  1.36s/it]
 97%|█████████▋| 60155/61904 [7:40:52<40:02,  1.37s/it]
 97%|█████████▋| 60156/61904 [7:40:53<39:31,  1.36s/it]
 97%|█████████▋| 60157/61904 [7:40:54<39:17,  1.35s/it]
 97%|█████████▋| 60158/61904 [7:40:56<38:46,  1.33s/it]
 97%|█████████▋| 60159/61904 [7:40:57<38:27,  1.32s/it]
 97%|█████████▋| 60160/61904 [7:40:58<38:34,  1.33s/it]
                                                       
{'loss': 2.4028, 'learning_rate': 1.0282639699209127e-07, 'epoch': 15.55}

 97%|█████████▋| 60160/61904 [7:40:58<38:34,  1.33s/it]
 97%|█████████▋| 60161/61904 [7:41:00<40:10,  1.38s/it]
 97%|█████████▋| 60162/61904 [7:41:01<40:15,  1.39s/it]
 97%|█████████▋| 60163/61904 [7:41:02<38:49,  1.34s/it]
 97%|█████████▋| 60164/61904 [7:41:04<38:53,  1.34s/it]
 97%|█████████▋| 60165/61904 [7:41:05<39:14,  1.35s/it]
 97%|█████████▋| 60166/61904 [7:41:06<38:56,  1.34s/it]
 97%|█████████▋| 60167/61904 [7:41:08<40:18,  1.39s/it]
 97%|█████████▋| 60168/61904 [7:41:09<39:23,  1.36s/it]
 97%|█████████▋| 60169/61904 [7:41:11<39:46,  1.38s/it]
 97%|█████████▋| 60170/61904 [7:41:12<39:15,  1.36s/it]
 97%|█████████▋| 60171/61904 [7:41:13<39:12,  1.36s/it]
 97%|█████████▋| 60172/61904 [7:41:15<38:37,  1.34s/it]
 97%|█████████▋| 60173/61904 [7:41:16<41:30,  1.44s/it]
 97%|█████████▋| 60174/61904 [7:41:17<40:18,  1.40s/it]
 97%|█████████▋| 60175/61904 [7:41:19<40:16,  1.40s/it]
 97%|█████████▋| 60176/61904 [7:41:20<40:10,  1.39s/it]
 97%|█████████▋| 60177/61904 [7:41:22<40:26,  1.41s/it]
 97%|█████████▋| 60178/61904 [7:41:23<40:13,  1.40s/it]
 97%|█████████▋| 60179/61904 [7:41:25<41:48,  1.45s/it]
 97%|█████████▋| 60180/61904 [7:41:26<41:01,  1.43s/it]
                                                       
{'loss': 2.4546, 'learning_rate': 1.0279398418254894e-07, 'epoch': 15.55}

 97%|█████████▋| 60180/61904 [7:41:26<41:01,  1.43s/it]
 97%|█████████▋| 60181/61904 [7:41:27<39:45,  1.38s/it]
 97%|█████████▋| 60182/61904 [7:41:29<40:53,  1.42s/it]
 97%|█████████▋| 60183/61904 [7:41:30<40:16,  1.40s/it]
 97%|█████████▋| 60184/61904 [7:41:32<41:15,  1.44s/it]
 97%|█████████▋| 60185/61904 [7:41:33<40:13,  1.40s/it]
 97%|█████████▋| 60186/61904 [7:41:34<40:06,  1.40s/it]
 97%|█████████▋| 60187/61904 [7:41:36<39:25,  1.38s/it]
 97%|█████████▋| 60188/61904 [7:41:37<39:05,  1.37s/it]
 97%|█████████▋| 60189/61904 [7:41:39<39:59,  1.40s/it]
 97%|█████████▋| 60190/61904 [7:41:40<39:26,  1.38s/it]
 97%|█████████▋| 60191/61904 [7:41:41<39:12,  1.37s/it]
 97%|█████████▋| 60192/61904 [7:41:43<39:01,  1.37s/it]
 97%|█████████▋| 60193/61904 [7:41:44<38:36,  1.35s/it]
 97%|█████████▋| 60194/61904 [7:41:45<37:29,  1.32s/it]
 97%|█████████▋| 60195/61904 [7:41:47<37:44,  1.33s/it]
 97%|█████████▋| 60196/61904 [7:41:48<37:10,  1.31s/it]
 97%|█████████▋| 60197/61904 [7:41:49<36:58,  1.30s/it]
 97%|█████████▋| 60198/61904 [7:41:50<37:13,  1.31s/it]
 97%|█████████▋| 60199/61904 [7:41:52<38:29,  1.35s/it]
 97%|█████████▋| 60200/61904 [7:41:53<40:22,  1.42s/it]
                                                       
{'loss': 2.3757, 'learning_rate': 1.0276157137300661e-07, 'epoch': 15.56}

 97%|█████████▋| 60200/61904 [7:41:53<40:22,  1.42s/it]
 97%|█████████▋| 60201/61904 [7:41:55<40:07,  1.41s/it]
 97%|█████████▋| 60202/61904 [7:41:56<39:04,  1.38s/it]
 97%|█████████▋| 60203/61904 [7:41:57<38:18,  1.35s/it]
 97%|█████████▋| 60204/61904 [7:41:59<38:12,  1.35s/it]
 97%|█████████▋| 60205/61904 [7:42:00<37:55,  1.34s/it]
 97%|█████████▋| 60206/61904 [7:42:01<37:27,  1.32s/it]
 97%|█████████▋| 60207/61904 [7:42:03<37:45,  1.34s/it]
 97%|█████████▋| 60208/61904 [7:42:04<40:47,  1.44s/it]
 97%|█████████▋| 60209/61904 [7:42:06<40:12,  1.42s/it]
 97%|█████████▋| 60210/61904 [7:42:07<40:14,  1.43s/it]
 97%|█████████▋| 60211/61904 [7:42:09<40:03,  1.42s/it]
 97%|█████████▋| 60212/61904 [7:42:10<39:31,  1.40s/it]
 97%|█████████▋| 60213/61904 [7:42:11<38:59,  1.38s/it]
 97%|█████████▋| 60214/61904 [7:42:13<38:27,  1.37s/it]
 97%|█████████▋| 60215/61904 [7:42:14<39:21,  1.40s/it]
 97%|█████████▋| 60216/61904 [7:42:16<41:16,  1.47s/it]
 97%|█████████▋| 60217/61904 [7:42:17<40:33,  1.44s/it]
 97%|█████████▋| 60218/61904 [7:42:19<40:42,  1.45s/it]
 97%|█████████▋| 60219/61904 [7:42:20<39:29,  1.41s/it]
 97%|█████████▋| 60220/61904 [7:42:21<40:15,  1.43s/it]
                                                       
{'loss': 2.3857, 'learning_rate': 1.0272915856346427e-07, 'epoch': 15.56}

 97%|█████████▋| 60220/61904 [7:42:21<40:15,  1.43s/it]
 97%|█████████▋| 60221/61904 [7:42:23<40:08,  1.43s/it]
 97%|█████████▋| 60222/61904 [7:42:24<40:14,  1.44s/it]
 97%|█████████▋| 60223/61904 [7:42:26<40:17,  1.44s/it]
 97%|█████████▋| 60224/61904 [7:42:27<40:31,  1.45s/it]
 97%|█████████▋| 60225/61904 [7:42:29<40:46,  1.46s/it]
 97%|█████████▋| 60226/61904 [7:42:30<41:25,  1.48s/it]
 97%|█████████▋| 60227/61904 [7:42:32<41:46,  1.49s/it]
 97%|█████████▋| 60228/61904 [7:42:33<41:45,  1.50s/it]
 97%|█████████▋| 60229/61904 [7:42:35<40:08,  1.44s/it]
 97%|█████████▋| 60230/61904 [7:42:36<39:35,  1.42s/it]
 97%|█████████▋| 60231/61904 [7:42:37<38:56,  1.40s/it]
 97%|█████████▋| 60232/61904 [7:42:39<39:02,  1.40s/it]
 97%|█████████▋| 60233/61904 [7:42:40<39:33,  1.42s/it]
 97%|█████████▋| 60234/61904 [7:42:41<38:30,  1.38s/it]
 97%|█████████▋| 60235/61904 [7:42:43<37:30,  1.35s/it]
 97%|█████████▋| 60236/61904 [7:42:44<36:47,  1.32s/it]
 97%|█████████▋| 60237/61904 [7:42:45<38:03,  1.37s/it]
 97%|█████████▋| 60238/61904 [7:42:47<37:26,  1.35s/it]
 97%|█████████▋| 60239/61904 [7:42:48<37:02,  1.33s/it]
 97%|█████████▋| 60240/61904 [7:42:49<37:48,  1.36s/it]
                                                       
{'loss': 2.4224, 'learning_rate': 1.0269674575392195e-07, 'epoch': 15.57}

 97%|█████████▋| 60240/61904 [7:42:49<37:48,  1.36s/it]
 97%|█████████▋| 60241/61904 [7:42:51<38:08,  1.38s/it]
 97%|█████████▋| 60242/61904 [7:42:52<38:12,  1.38s/it]
 97%|█████████▋| 60243/61904 [7:42:54<40:11,  1.45s/it]
 97%|█████████▋| 60244/61904 [7:42:56<41:42,  1.51s/it]
 97%|█████████▋| 60245/61904 [7:42:57<41:01,  1.48s/it]
 97%|█████████▋| 60246/61904 [7:42:59<41:55,  1.52s/it]
 97%|█████████▋| 60247/61904 [7:43:00<41:23,  1.50s/it]
 97%|█████████▋| 60248/61904 [7:43:01<39:30,  1.43s/it]
 97%|█████████▋| 60249/61904 [7:43:03<39:01,  1.41s/it]
 97%|█████████▋| 60250/61904 [7:43:04<37:54,  1.38s/it]
 97%|█████████▋| 60251/61904 [7:43:05<37:09,  1.35s/it]
 97%|█████████▋| 60252/61904 [7:43:07<36:56,  1.34s/it]
 97%|█████████▋| 60253/61904 [7:43:08<37:58,  1.38s/it]
 97%|█████████▋| 60254/61904 [7:43:09<38:12,  1.39s/it]
 97%|█████████▋| 60255/61904 [7:43:11<37:24,  1.36s/it]
 97%|█████████▋| 60256/61904 [7:43:12<37:27,  1.36s/it]
 97%|█████████▋| 60257/61904 [7:43:13<36:52,  1.34s/it]
 97%|█████████▋| 60258/61904 [7:43:15<37:46,  1.38s/it]
 97%|█████████▋| 60259/61904 [7:43:16<38:41,  1.41s/it]
 97%|█████████▋| 60260/61904 [7:43:18<38:48,  1.42s/it]
                                                       
{'loss': 2.4753, 'learning_rate': 1.0266433294437962e-07, 'epoch': 15.57}

 97%|█████████▋| 60260/61904 [7:43:18<38:48,  1.42s/it]
 97%|█████████▋| 60261/61904 [7:43:19<37:53,  1.38s/it]
 97%|█████████▋| 60262/61904 [7:43:21<38:47,  1.42s/it]
 97%|█████████▋| 60263/61904 [7:43:22<37:06,  1.36s/it]
 97%|█████████▋| 60264/61904 [7:43:23<38:06,  1.39s/it]
 97%|█████████▋| 60265/61904 [7:43:25<37:30,  1.37s/it]
 97%|█████████▋| 60266/61904 [7:43:26<36:58,  1.35s/it]
 97%|█████████▋| 60267/61904 [7:43:27<37:19,  1.37s/it]
 97%|█████████▋| 60268/61904 [7:43:29<37:39,  1.38s/it]
 97%|█████████▋| 60269/61904 [7:43:30<37:15,  1.37s/it]
 97%|█████████▋| 60270/61904 [7:43:32<38:53,  1.43s/it]
 97%|█████████▋| 60271/61904 [7:43:33<37:58,  1.40s/it]
 97%|█████████▋| 60272/61904 [7:43:34<38:18,  1.41s/it]
 97%|█████████▋| 60273/61904 [7:43:36<38:54,  1.43s/it]
 97%|█████████▋| 60274/61904 [7:43:37<38:33,  1.42s/it]
 97%|█████████▋| 60275/61904 [7:43:39<38:52,  1.43s/it]
 97%|█████████▋| 60276/61904 [7:43:40<38:23,  1.42s/it]
 97%|█████████▋| 60277/61904 [7:43:41<37:12,  1.37s/it]
 97%|█████████▋| 60278/61904 [7:43:43<37:02,  1.37s/it]
 97%|█████████▋| 60279/61904 [7:43:44<39:29,  1.46s/it]
 97%|█████████▋| 60280/61904 [7:43:46<38:38,  1.43s/it]
                                                       
{'loss': 2.3691, 'learning_rate': 1.0263192013483729e-07, 'epoch': 15.58}

 97%|█████████▋| 60280/61904 [7:43:46<38:38,  1.43s/it]
 97%|█████████▋| 60281/61904 [7:43:47<37:35,  1.39s/it]
 97%|█████████▋| 60282/61904 [7:43:49<39:59,  1.48s/it]
 97%|█████████▋| 60283/61904 [7:43:50<40:04,  1.48s/it]
 97%|█████████▋| 60284/61904 [7:43:52<41:06,  1.52s/it]
 97%|█████████▋| 60285/61904 [7:43:53<39:32,  1.47s/it]
 97%|█████████▋| 60286/61904 [7:43:55<39:25,  1.46s/it]
 97%|█████████▋| 60287/61904 [7:43:56<38:54,  1.44s/it]
 97%|█████████▋| 60288/61904 [7:43:58<40:12,  1.49s/it]
 97%|█████████▋| 60289/61904 [7:43:59<39:06,  1.45s/it]
 97%|█████████▋| 60290/61904 [7:44:01<39:40,  1.48s/it]
 97%|█████████▋| 60291/61904 [7:44:02<39:20,  1.46s/it]
 97%|█████████▋| 60292/61904 [7:44:03<39:05,  1.46s/it]
 97%|█████████▋| 60293/61904 [7:44:05<39:46,  1.48s/it]
 97%|█████████▋| 60294/61904 [7:44:06<39:54,  1.49s/it]
 97%|█████████▋| 60295/61904 [7:44:08<38:47,  1.45s/it]
 97%|█████████▋| 60296/61904 [7:44:09<38:43,  1.45s/it]
 97%|█████████▋| 60297/61904 [7:44:11<39:20,  1.47s/it]
 97%|█████████▋| 60298/61904 [7:44:12<38:10,  1.43s/it]
 97%|█████████▋| 60299/61904 [7:44:14<40:29,  1.51s/it]
 97%|█████████▋| 60300/61904 [7:44:15<39:56,  1.49s/it]
                                                       
{'loss': 2.363, 'learning_rate': 1.0259950732529495e-07, 'epoch': 15.58}

 97%|█████████▋| 60300/61904 [7:44:15<39:56,  1.49s/it]
 97%|█████████▋| 60301/61904 [7:44:17<38:18,  1.43s/it]
 97%|█████████▋| 60302/61904 [7:44:18<38:06,  1.43s/it]
 97%|█████████▋| 60303/61904 [7:44:19<38:51,  1.46s/it]
 97%|█████████▋| 60304/61904 [7:44:21<37:48,  1.42s/it]
 97%|█████████▋| 60305/61904 [7:44:22<37:00,  1.39s/it]
 97%|█████████▋| 60306/61904 [7:44:23<36:05,  1.36s/it]
 97%|█████████▋| 60307/61904 [7:44:25<37:13,  1.40s/it]
 97%|█████████▋| 60308/61904 [7:44:26<37:52,  1.42s/it]
 97%|█████████▋| 60309/61904 [7:44:28<38:15,  1.44s/it]
 97%|█████████▋| 60310/61904 [7:44:30<40:14,  1.51s/it]
 97%|█████████▋| 60311/61904 [7:44:31<38:17,  1.44s/it]
 97%|█████████▋| 60312/61904 [7:44:32<38:01,  1.43s/it]
 97%|█████████▋| 60313/61904 [7:44:34<36:55,  1.39s/it]
 97%|█████████▋| 60314/61904 [7:44:35<36:22,  1.37s/it]
 97%|█████████▋| 60315/61904 [7:44:36<37:11,  1.40s/it]
 97%|█████████▋| 60316/61904 [7:44:38<36:45,  1.39s/it]
 97%|█████████▋| 60317/61904 [7:44:39<36:34,  1.38s/it]
 97%|█████████▋| 60318/61904 [7:44:40<36:47,  1.39s/it]
 97%|█████████▋| 60319/61904 [7:44:42<39:53,  1.51s/it]
 97%|█████████▋| 60320/61904 [7:44:44<39:03,  1.48s/it]
                                                       
{'loss': 2.4099, 'learning_rate': 1.0256709451575262e-07, 'epoch': 15.59}

 97%|█████████▋| 60320/61904 [7:44:44<39:03,  1.48s/it]
 97%|█████████▋| 60321/61904 [7:44:45<38:27,  1.46s/it]
 97%|█████████▋| 60322/61904 [7:44:47<38:51,  1.47s/it]
 97%|█████████▋| 60323/61904 [7:44:48<40:32,  1.54s/it]
 97%|█████████▋| 60324/61904 [7:44:50<39:11,  1.49s/it]
 97%|█████████▋| 60325/61904 [7:44:51<38:39,  1.47s/it]
 97%|█████████▋| 60326/61904 [7:44:53<38:58,  1.48s/it]
 97%|█████████▋| 60327/61904 [7:44:54<37:51,  1.44s/it]
 97%|█████████▋| 60328/61904 [7:44:55<37:41,  1.43s/it]
 97%|█████████▋| 60329/61904 [7:44:57<36:13,  1.38s/it]
 97%|█████████▋| 60330/61904 [7:44:58<35:53,  1.37s/it]
 97%|█████████▋| 60331/61904 [7:44:59<36:13,  1.38s/it]
 97%|█████████▋| 60332/61904 [7:45:01<36:13,  1.38s/it]
 97%|█████████▋| 60333/61904 [7:45:02<36:12,  1.38s/it]
 97%|█████████▋| 60334/61904 [7:45:03<35:43,  1.37s/it]
 97%|█████████▋| 60335/61904 [7:45:05<34:59,  1.34s/it]
 97%|█████████▋| 60336/61904 [7:45:06<35:11,  1.35s/it]
 97%|█████████▋| 60337/61904 [7:45:07<35:25,  1.36s/it]
 97%|█████████▋| 60338/61904 [7:45:09<35:27,  1.36s/it]
 97%|█████████▋| 60339/61904 [7:45:10<35:54,  1.38s/it]
 97%|█████████▋| 60340/61904 [7:45:12<36:08,  1.39s/it]
                                                       
{'loss': 2.4276, 'learning_rate': 1.025346817062103e-07, 'epoch': 15.6}

 97%|█████████▋| 60340/61904 [7:45:12<36:08,  1.39s/it]
 97%|█████████▋| 60341/61904 [7:45:13<35:12,  1.35s/it]
 97%|█████████▋| 60342/61904 [7:45:14<35:34,  1.37s/it]
 97%|█████████▋| 60343/61904 [7:45:16<34:55,  1.34s/it]
 97%|█████████▋| 60344/61904 [7:45:17<35:49,  1.38s/it]
 97%|█████████▋| 60345/61904 [7:45:18<35:27,  1.36s/it]
 97%|█████████▋| 60346/61904 [7:45:20<36:42,  1.41s/it]
 97%|█████████▋| 60347/61904 [7:45:21<36:44,  1.42s/it]
 97%|█████████▋| 60348/61904 [7:45:23<36:23,  1.40s/it]
 97%|█████████▋| 60349/61904 [7:45:24<37:35,  1.45s/it]
 97%|█████████▋| 60350/61904 [7:45:26<36:58,  1.43s/it]
 97%|█████████▋| 60351/61904 [7:45:27<36:12,  1.40s/it]
 97%|█████████▋| 60352/61904 [7:45:28<36:37,  1.42s/it]
 97%|█████████▋| 60353/61904 [7:45:30<35:39,  1.38s/it]
 97%|█████████▋| 60354/61904 [7:45:31<35:16,  1.37s/it]
 97%|█████████▋| 60355/61904 [7:45:32<34:16,  1.33s/it]
 97%|█████████▋| 60356/61904 [7:45:34<34:01,  1.32s/it]
 98%|█████████▊| 60357/61904 [7:45:35<35:34,  1.38s/it]
 98%|█████████▊| 60358/61904 [7:45:37<36:15,  1.41s/it]
 98%|█████████▊| 60359/61904 [7:45:38<36:05,  1.40s/it]
 98%|█████████▊| 60360/61904 [7:45:39<35:40,  1.39s/it]
                                                       
{'loss': 2.4374, 'learning_rate': 1.0250226889666796e-07, 'epoch': 15.6}

 98%|█████████▊| 60360/61904 [7:45:39<35:40,  1.39s/it]
 98%|█████████▊| 60361/61904 [7:45:41<36:35,  1.42s/it]
 98%|█████████▊| 60362/61904 [7:45:42<35:40,  1.39s/it]
 98%|█████████▊| 60363/61904 [7:45:43<35:13,  1.37s/it]
 98%|█████████▊| 60364/61904 [7:45:45<35:05,  1.37s/it]
 98%|█████████▊| 60365/61904 [7:45:46<35:18,  1.38s/it]
 98%|█████████▊| 60366/61904 [7:45:48<35:17,  1.38s/it]
 98%|█████████▊| 60367/61904 [7:45:49<35:12,  1.37s/it]
 98%|█████████▊| 60368/61904 [7:45:50<34:51,  1.36s/it]
 98%|█████████▊| 60369/61904 [7:45:52<36:33,  1.43s/it]
 98%|█████████▊| 60370/61904 [7:45:53<36:04,  1.41s/it]
 98%|█████████▊| 60371/61904 [7:45:55<37:47,  1.48s/it]
 98%|█████████▊| 60372/61904 [7:45:56<36:52,  1.44s/it]
 98%|█████████▊| 60373/61904 [7:45:58<35:46,  1.40s/it]
 98%|█████████▊| 60374/61904 [7:45:59<34:50,  1.37s/it]
 98%|█████████▊| 60375/61904 [7:46:00<34:50,  1.37s/it]
 98%|█████████▊| 60376/61904 [7:46:02<35:20,  1.39s/it]
 98%|█████████▊| 60377/61904 [7:46:03<35:34,  1.40s/it]
 98%|█████████▊| 60378/61904 [7:46:04<35:31,  1.40s/it]
 98%|█████████▊| 60379/61904 [7:46:06<35:57,  1.41s/it]
 98%|█████████▊| 60380/61904 [7:46:07<34:40,  1.36s/it]
                                                       
{'loss': 2.426, 'learning_rate': 1.0246985608712562e-07, 'epoch': 15.61}

 98%|█████████▊| 60380/61904 [7:46:07<34:40,  1.36s/it]
 98%|█████████▊| 60381/61904 [7:46:08<33:58,  1.34s/it]
 98%|█████████▊| 60382/61904 [7:46:10<35:58,  1.42s/it]
 98%|█████████▊| 60383/61904 [7:46:11<35:16,  1.39s/it]
 98%|█████████▊| 60384/61904 [7:46:13<35:11,  1.39s/it]
 98%|█████████▊| 60385/61904 [7:46:14<35:03,  1.38s/it]
 98%|█████████▊| 60386/61904 [7:46:15<34:05,  1.35s/it]
 98%|█████████▊| 60387/61904 [7:46:17<34:19,  1.36s/it]
 98%|█████████▊| 60388/61904 [7:46:18<35:08,  1.39s/it]
 98%|█████████▊| 60389/61904 [7:46:20<35:59,  1.43s/it]
 98%|█████████▊| 60390/61904 [7:46:21<34:59,  1.39s/it]
 98%|█████████▊| 60391/61904 [7:46:23<36:23,  1.44s/it]
 98%|█████████▊| 60392/61904 [7:46:24<36:24,  1.44s/it]
 98%|█████████▊| 60393/61904 [7:46:25<35:30,  1.41s/it]
 98%|█████████▊| 60394/61904 [7:46:27<35:06,  1.39s/it]
 98%|█████████▊| 60395/61904 [7:46:28<35:35,  1.41s/it]
 98%|█████████▊| 60396/61904 [7:46:30<35:39,  1.42s/it]
 98%|█████████▊| 60397/61904 [7:46:31<35:32,  1.42s/it]
 98%|█████████▊| 60398/61904 [7:46:32<34:57,  1.39s/it]
 98%|█████████▊| 60399/61904 [7:46:34<35:10,  1.40s/it]
 98%|█████████▊| 60400/61904 [7:46:35<34:44,  1.39s/it]
                                                       
{'loss': 2.4147, 'learning_rate': 1.024374432775833e-07, 'epoch': 15.61}

 98%|█████████▊| 60400/61904 [7:46:35<34:44,  1.39s/it]
 98%|█████████▊| 60401/61904 [7:46:37<34:11,  1.37s/it]
 98%|█████████▊| 60402/61904 [7:46:38<34:36,  1.38s/it]
 98%|█████████▊| 60403/61904 [7:46:39<34:21,  1.37s/it]
 98%|█████████▊| 60404/61904 [7:46:41<33:52,  1.35s/it]
 98%|█████████▊| 60405/61904 [7:46:42<34:16,  1.37s/it]
 98%|█████████▊| 60406/61904 [7:46:43<34:23,  1.38s/it]
 98%|█████████▊| 60407/61904 [7:46:45<33:22,  1.34s/it]
 98%|█████████▊| 60408/61904 [7:46:46<33:43,  1.35s/it]
 98%|█████████▊| 60409/61904 [7:46:47<32:52,  1.32s/it]
 98%|█████████▊| 60410/61904 [7:46:49<33:46,  1.36s/it]
 98%|█████████▊| 60411/61904 [7:46:50<34:06,  1.37s/it]
 98%|█████████▊| 60412/61904 [7:46:51<33:11,  1.33s/it]
 98%|█████████▊| 60413/61904 [7:46:53<34:04,  1.37s/it]
 98%|█████████▊| 60414/61904 [7:46:54<33:34,  1.35s/it]
 98%|█████████▊| 60415/61904 [7:46:56<34:28,  1.39s/it]
 98%|█████████▊| 60416/61904 [7:46:57<34:31,  1.39s/it]
 98%|█████████▊| 60417/61904 [7:46:58<33:49,  1.37s/it]
 98%|█████████▊| 60418/61904 [7:47:00<33:46,  1.36s/it]
 98%|█████████▊| 60419/61904 [7:47:01<35:07,  1.42s/it]
 98%|█████████▊| 60420/61904 [7:47:03<35:02,  1.42s/it]
                                                       
{'loss': 2.4362, 'learning_rate': 1.0240503046804097e-07, 'epoch': 15.62}

 98%|█████████▊| 60420/61904 [7:47:03<35:02,  1.42s/it]
 98%|█████████▊| 60421/61904 [7:47:04<34:38,  1.40s/it]
 98%|█████████▊| 60422/61904 [7:47:05<34:04,  1.38s/it]
 98%|█████████▊| 60423/61904 [7:47:07<35:30,  1.44s/it]
 98%|█████████▊| 60424/61904 [7:47:08<35:49,  1.45s/it]
 98%|█████████▊| 60425/61904 [7:47:10<34:53,  1.42s/it]
 98%|█████████▊| 60426/61904 [7:47:11<34:19,  1.39s/it]
 98%|█████████▊| 60427/61904 [7:47:12<33:56,  1.38s/it]
 98%|█████████▊| 60428/61904 [7:47:14<32:54,  1.34s/it]
 98%|█████████▊| 60429/61904 [7:47:15<32:29,  1.32s/it]
 98%|█████████▊| 60430/61904 [7:47:16<32:19,  1.32s/it]
 98%|█████████▊| 60431/61904 [7:47:18<32:41,  1.33s/it]
 98%|█████████▊| 60432/61904 [7:47:19<32:59,  1.34s/it]
 98%|█████████▊| 60433/61904 [7:47:20<33:58,  1.39s/it]
 98%|█████████▊| 60434/61904 [7:47:22<33:09,  1.35s/it]
 98%|█████████▊| 60435/61904 [7:47:23<34:11,  1.40s/it]
 98%|█████████▊| 60436/61904 [7:47:25<34:16,  1.40s/it]
 98%|█████████▊| 60437/61904 [7:47:26<34:08,  1.40s/it]
 98%|█████████▊| 60438/61904 [7:47:27<33:11,  1.36s/it]
 98%|█████████▊| 60439/61904 [7:47:29<34:39,  1.42s/it]
 98%|█████████▊| 60440/61904 [7:47:30<33:47,  1.38s/it]
                                                       
{'loss': 2.4182, 'learning_rate': 1.0237261765849863e-07, 'epoch': 15.62}

 98%|█████████▊| 60440/61904 [7:47:30<33:47,  1.38s/it]
 98%|█████████▊| 60441/61904 [7:47:32<34:04,  1.40s/it]
 98%|█████████▊| 60442/61904 [7:47:33<34:28,  1.42s/it]
 98%|█████████▊| 60443/61904 [7:47:35<35:02,  1.44s/it]
 98%|█████████▊| 60444/61904 [7:47:36<33:53,  1.39s/it]
 98%|█████████▊| 60445/61904 [7:47:37<34:08,  1.40s/it]
 98%|█████████▊| 60446/61904 [7:47:39<33:26,  1.38s/it]
 98%|█████████▊| 60447/61904 [7:47:40<32:48,  1.35s/it]
 98%|█████████▊| 60448/61904 [7:47:41<32:49,  1.35s/it]
 98%|█████████▊| 60449/61904 [7:47:43<32:54,  1.36s/it]
 98%|█████████▊| 60450/61904 [7:47:44<32:57,  1.36s/it]
 98%|█████████▊| 60451/61904 [7:47:45<33:16,  1.37s/it]
 98%|█████████▊| 60452/61904 [7:47:47<32:57,  1.36s/it]
 98%|█████████▊| 60453/61904 [7:47:48<33:43,  1.39s/it]
 98%|█████████▊| 60454/61904 [7:47:50<33:58,  1.41s/it]
 98%|█████████▊| 60455/61904 [7:47:51<33:46,  1.40s/it]
 98%|█████████▊| 60456/61904 [7:47:52<33:34,  1.39s/it]
 98%|█████████▊| 60457/61904 [7:47:54<32:57,  1.37s/it]
 98%|█████████▊| 60458/61904 [7:47:55<32:59,  1.37s/it]
 98%|█████████▊| 60459/61904 [7:47:56<32:41,  1.36s/it]
 98%|█████████▊| 60460/61904 [7:47:58<32:27,  1.35s/it]
                                                       
{'loss': 2.389, 'learning_rate': 1.023402048489563e-07, 'epoch': 15.63}

 98%|█████████▊| 60460/61904 [7:47:58<32:27,  1.35s/it]
 98%|█████████▊| 60461/61904 [7:47:59<32:31,  1.35s/it]
 98%|█████████▊| 60462/61904 [7:48:01<33:10,  1.38s/it]
 98%|█████████▊| 60463/61904 [7:48:02<33:14,  1.38s/it]
 98%|█████████▊| 60464/61904 [7:48:03<33:46,  1.41s/it]
 98%|█████████▊| 60465/61904 [7:48:05<34:40,  1.45s/it]
 98%|█████████▊| 60466/61904 [7:48:07<36:28,  1.52s/it]
 98%|█████████▊| 60467/61904 [7:48:08<35:37,  1.49s/it]
 98%|█████████▊| 60468/61904 [7:48:09<34:54,  1.46s/it]
 98%|█████████▊| 60469/61904 [7:48:11<34:20,  1.44s/it]
 98%|█████████▊| 60470/61904 [7:48:12<33:57,  1.42s/it]
 98%|█████████▊| 60471/61904 [7:48:14<33:30,  1.40s/it]
 98%|█████████▊| 60472/61904 [7:48:15<33:04,  1.39s/it]
 98%|█████████▊| 60473/61904 [7:48:16<33:25,  1.40s/it]
 98%|█████████▊| 60474/61904 [7:48:18<33:09,  1.39s/it]
 98%|█████████▊| 60475/61904 [7:48:19<33:31,  1.41s/it]
 98%|█████████▊| 60476/61904 [7:48:21<34:36,  1.45s/it]
 98%|█████████▊| 60477/61904 [7:48:22<34:07,  1.44s/it]
 98%|█████████▊| 60478/61904 [7:48:24<34:30,  1.45s/it]
 98%|█████████▊| 60479/61904 [7:48:25<33:41,  1.42s/it]
 98%|█████████▊| 60480/61904 [7:48:26<32:58,  1.39s/it]
                                                       
{'loss': 2.4295, 'learning_rate': 1.0230779203941397e-07, 'epoch': 15.63}

 98%|█████████▊| 60480/61904 [7:48:26<32:58,  1.39s/it]
 98%|█████████▊| 60481/61904 [7:48:28<32:25,  1.37s/it]
 98%|█████████▊| 60482/61904 [7:48:29<32:46,  1.38s/it]
 98%|█████████▊| 60483/61904 [7:48:30<32:32,  1.37s/it]
 98%|█████████▊| 60484/61904 [7:48:32<32:26,  1.37s/it]
 98%|█████████▊| 60485/61904 [7:48:33<32:18,  1.37s/it]
 98%|█████████▊| 60486/61904 [7:48:34<32:12,  1.36s/it]
 98%|█████████▊| 60487/61904 [7:48:36<31:50,  1.35s/it]
 98%|█████████▊| 60488/61904 [7:48:37<31:41,  1.34s/it]
 98%|█████████▊| 60489/61904 [7:48:39<32:36,  1.38s/it]
 98%|█████████▊| 60490/61904 [7:48:40<31:44,  1.35s/it]
 98%|█████████▊| 60491/61904 [7:48:41<32:03,  1.36s/it]
 98%|█████████▊| 60492/61904 [7:48:43<32:46,  1.39s/it]
 98%|█████████▊| 60493/61904 [7:48:44<33:27,  1.42s/it]
 98%|█████████▊| 60494/61904 [7:48:46<33:12,  1.41s/it]
 98%|█████████▊| 60495/61904 [7:48:47<33:01,  1.41s/it]
 98%|█████████▊| 60496/61904 [7:48:48<32:25,  1.38s/it]
 98%|█████████▊| 60497/61904 [7:48:50<31:48,  1.36s/it]
 98%|█████████▊| 60498/61904 [7:48:51<31:49,  1.36s/it]
 98%|█████████▊| 60499/61904 [7:48:52<31:37,  1.35s/it]
 98%|█████████▊| 60500/61904 [7:48:54<32:18,  1.38s/it]
                                                       
{'loss': 2.4227, 'learning_rate': 1.0227537922987165e-07, 'epoch': 15.64}

 98%|█████████▊| 60500/61904 [7:48:54<32:18,  1.38s/it]
 98%|█████████▊| 60501/61904 [7:48:55<32:23,  1.39s/it]
 98%|█████████▊| 60502/61904 [7:48:56<32:23,  1.39s/it]
 98%|█████████▊| 60503/61904 [7:48:58<31:44,  1.36s/it]
 98%|█████████▊| 60504/61904 [7:48:59<32:31,  1.39s/it]
 98%|█████████▊| 60505/61904 [7:49:01<32:21,  1.39s/it]
 98%|█████████▊| 60506/61904 [7:49:02<32:16,  1.39s/it]
 98%|█████████▊| 60507/61904 [7:49:03<32:15,  1.39s/it]
 98%|█████████▊| 60508/61904 [7:49:05<32:13,  1.38s/it]
 98%|█████████▊| 60509/61904 [7:49:06<31:21,  1.35s/it]
 98%|█████████▊| 60510/61904 [7:49:07<31:55,  1.37s/it]
 98%|█████████▊| 60511/61904 [7:49:09<31:31,  1.36s/it]
 98%|█████████▊| 60512/61904 [7:49:10<31:56,  1.38s/it]
 98%|█████████▊| 60513/61904 [7:49:11<31:03,  1.34s/it]
 98%|█████████▊| 60514/61904 [7:49:13<30:51,  1.33s/it]
 98%|█████████▊| 60515/61904 [7:49:14<31:35,  1.36s/it]
 98%|█████████▊| 60516/61904 [7:49:16<31:07,  1.35s/it]
 98%|█████████▊| 60517/61904 [7:49:17<31:55,  1.38s/it]
 98%|█████████▊| 60518/61904 [7:49:18<31:29,  1.36s/it]
 98%|█████████▊| 60519/61904 [7:49:20<31:54,  1.38s/it]
 98%|█████████▊| 60520/61904 [7:49:21<31:52,  1.38s/it]
                                                       
{'loss': 2.4355, 'learning_rate': 1.0224296642032931e-07, 'epoch': 15.64}

 98%|█████████▊| 60520/61904 [7:49:21<31:52,  1.38s/it]
 98%|█████████▊| 60521/61904 [7:49:22<31:29,  1.37s/it]
 98%|█████████▊| 60522/61904 [7:49:24<31:24,  1.36s/it]
 98%|█████████▊| 60523/61904 [7:49:25<32:46,  1.42s/it]
 98%|█████████▊| 60524/61904 [7:49:27<32:23,  1.41s/it]
 98%|█████████▊| 60525/61904 [7:49:28<31:53,  1.39s/it]
 98%|█████████▊| 60526/61904 [7:49:29<31:49,  1.39s/it]
 98%|█████████▊| 60527/61904 [7:49:31<31:02,  1.35s/it]
 98%|█████████▊| 60528/61904 [7:49:32<31:43,  1.38s/it]
 98%|█████████▊| 60529/61904 [7:49:34<33:00,  1.44s/it]
 98%|█████████▊| 60530/61904 [7:49:35<32:52,  1.44s/it]
 98%|█████████▊| 60531/61904 [7:49:36<31:54,  1.39s/it]
 98%|█████████▊| 60532/61904 [7:49:38<33:16,  1.46s/it]
 98%|█████████▊| 60533/61904 [7:49:39<32:00,  1.40s/it]
 98%|█████████▊| 60534/61904 [7:49:41<31:33,  1.38s/it]
 98%|█████████▊| 60535/61904 [7:49:42<31:50,  1.40s/it]
 98%|█████████▊| 60536/61904 [7:49:43<31:24,  1.38s/it]
 98%|█████████▊| 60537/61904 [7:49:45<31:01,  1.36s/it]
 98%|█████████▊| 60538/61904 [7:49:46<30:50,  1.35s/it]
 98%|█████████▊| 60539/61904 [7:49:47<30:06,  1.32s/it]
 98%|█████████▊| 60540/61904 [7:49:49<30:15,  1.33s/it]
                                                       
{'loss': 2.3482, 'learning_rate': 1.0221055361078698e-07, 'epoch': 15.65}

 98%|█████████▊| 60540/61904 [7:49:49<30:15,  1.33s/it]
 98%|█████████▊| 60541/61904 [7:49:50<30:49,  1.36s/it]
 98%|█████████▊| 60542/61904 [7:49:51<30:44,  1.35s/it]
 98%|█████████▊| 60543/61904 [7:49:53<30:10,  1.33s/it]
 98%|█████████▊| 60544/61904 [7:49:54<30:05,  1.33s/it]
 98%|█████████▊| 60545/61904 [7:49:55<30:17,  1.34s/it]
 98%|█████████▊| 60546/61904 [7:49:57<30:01,  1.33s/it]
 98%|█████████▊| 60547/61904 [7:49:58<30:21,  1.34s/it]
 98%|█████████▊| 60548/61904 [7:50:00<30:54,  1.37s/it]
 98%|█████████▊| 60549/61904 [7:50:01<31:02,  1.37s/it]
 98%|█████████▊| 60550/61904 [7:50:02<31:32,  1.40s/it]
 98%|█████████▊| 60551/61904 [7:50:04<30:52,  1.37s/it]
 98%|█████████▊| 60552/61904 [7:50:05<31:12,  1.39s/it]
 98%|█████████▊| 60553/61904 [7:50:07<31:22,  1.39s/it]
 98%|█████████▊| 60554/61904 [7:50:08<30:30,  1.36s/it]
 98%|█████████▊| 60555/61904 [7:50:09<30:06,  1.34s/it]
 98%|█████████▊| 60556/61904 [7:50:11<31:48,  1.42s/it]
 98%|█████████▊| 60557/61904 [7:50:12<31:02,  1.38s/it]
 98%|█████████▊| 60558/61904 [7:50:13<30:41,  1.37s/it]
 98%|█████████▊| 60559/61904 [7:50:15<30:37,  1.37s/it]
 98%|█████████▊| 60560/61904 [7:50:16<29:47,  1.33s/it]
                                                       
{'loss': 2.4117, 'learning_rate': 1.0217814080124464e-07, 'epoch': 15.65}

 98%|█████████▊| 60560/61904 [7:50:16<29:47,  1.33s/it]
 98%|█████████▊| 60561/61904 [7:50:17<31:09,  1.39s/it]
 98%|█████████▊| 60562/61904 [7:50:19<31:16,  1.40s/it]
 98%|█████████▊| 60563/61904 [7:50:20<31:40,  1.42s/it]
 98%|█████████▊| 60564/61904 [7:50:22<30:40,  1.37s/it]
 98%|█████████▊| 60565/61904 [7:50:23<30:49,  1.38s/it]
 98%|█████████▊| 60566/61904 [7:50:24<30:40,  1.38s/it]
 98%|█████████▊| 60567/61904 [7:50:26<30:27,  1.37s/it]
 98%|█████████▊| 60568/61904 [7:50:27<30:09,  1.35s/it]
 98%|█████████▊| 60569/61904 [7:50:28<30:53,  1.39s/it]
 98%|█████████▊| 60570/61904 [7:50:30<31:24,  1.41s/it]
 98%|█████████▊| 60571/61904 [7:50:31<31:28,  1.42s/it]
 98%|█████████▊| 60572/61904 [7:50:33<30:41,  1.38s/it]
 98%|█████████▊| 60573/61904 [7:50:34<31:12,  1.41s/it]
 98%|█████████▊| 60574/61904 [7:50:36<31:13,  1.41s/it]
 98%|█████████▊| 60575/61904 [7:50:37<31:24,  1.42s/it]
 98%|█████████▊| 60576/61904 [7:50:38<31:00,  1.40s/it]
 98%|█████████▊| 60577/61904 [7:50:40<30:37,  1.38s/it]
 98%|█████████▊| 60578/61904 [7:50:41<30:17,  1.37s/it]
 98%|█████████▊| 60579/61904 [7:50:42<30:36,  1.39s/it]
 98%|█████████▊| 60580/61904 [7:50:44<30:26,  1.38s/it]
                                                       
{'loss': 2.3671, 'learning_rate': 1.0214572799170232e-07, 'epoch': 15.66}

 98%|█████████▊| 60580/61904 [7:50:44<30:26,  1.38s/it]
 98%|█████████▊| 60581/61904 [7:50:45<29:25,  1.33s/it]
 98%|█████████▊| 60582/61904 [7:50:47<30:18,  1.38s/it]
 98%|█████████▊| 60583/61904 [7:50:48<30:00,  1.36s/it]
 98%|█████████▊| 60584/61904 [7:50:49<29:23,  1.34s/it]
 98%|█████████▊| 60585/61904 [7:50:51<29:46,  1.35s/it]
 98%|█████████▊| 60586/61904 [7:50:52<29:45,  1.35s/it]
 98%|█████████▊| 60587/61904 [7:50:53<30:26,  1.39s/it]
 98%|█████████▊| 60588/61904 [7:50:55<29:59,  1.37s/it]
 98%|█████████▊| 60589/61904 [7:50:56<29:08,  1.33s/it]
 98%|█████████▊| 60590/61904 [7:50:57<29:02,  1.33s/it]
 98%|█████████▊| 60591/61904 [7:50:59<29:35,  1.35s/it]
 98%|█████████▊| 60592/61904 [7:51:00<29:27,  1.35s/it]
 98%|█████████▊| 60593/61904 [7:51:01<29:24,  1.35s/it]
 98%|█████████▊| 60594/61904 [7:51:03<29:03,  1.33s/it]
 98%|█████████▊| 60595/61904 [7:51:04<29:52,  1.37s/it]
 98%|█████████▊| 60596/61904 [7:51:05<29:52,  1.37s/it]
 98%|█████████▊| 60597/61904 [7:51:07<30:01,  1.38s/it]
 98%|█████████▊| 60598/61904 [7:51:08<29:29,  1.36s/it]
 98%|█████████▊| 60599/61904 [7:51:09<29:01,  1.33s/it]
 98%|█████████▊| 60600/61904 [7:51:11<28:26,  1.31s/it]
                                                       
{'loss': 2.44, 'learning_rate': 1.0211331518215998e-07, 'epoch': 15.66}

 98%|█████████▊| 60600/61904 [7:51:11<28:26,  1.31s/it]
 98%|█████████▊| 60601/61904 [7:51:12<28:31,  1.31s/it]
 98%|█████████▊| 60602/61904 [7:51:13<28:16,  1.30s/it]
 98%|█████████▊| 60603/61904 [7:51:15<28:37,  1.32s/it]
 98%|█████████▊| 60604/61904 [7:51:16<29:23,  1.36s/it]
 98%|█████████▊| 60605/61904 [7:51:18<30:10,  1.39s/it]
 98%|█████████▊| 60606/61904 [7:51:19<29:56,  1.38s/it]
 98%|█████████▊| 60607/61904 [7:51:20<29:00,  1.34s/it]
 98%|█████████▊| 60608/61904 [7:51:22<29:14,  1.35s/it]
 98%|█████████▊| 60609/61904 [7:51:23<29:27,  1.37s/it]
 98%|█████████▊| 60610/61904 [7:51:24<29:01,  1.35s/it]
 98%|█████████▊| 60611/61904 [7:51:26<28:49,  1.34s/it]
 98%|█████████▊| 60612/61904 [7:51:27<28:41,  1.33s/it]
 98%|█████████▊| 60613/61904 [7:51:28<28:37,  1.33s/it]
 98%|█████████▊| 60614/61904 [7:51:30<29:14,  1.36s/it]
 98%|█████████▊| 60615/61904 [7:51:31<30:16,  1.41s/it]
 98%|█████████▊| 60616/61904 [7:51:33<29:43,  1.38s/it]
 98%|█████████▊| 60617/61904 [7:51:34<29:45,  1.39s/it]
 98%|█████████▊| 60618/61904 [7:51:35<29:39,  1.38s/it]
 98%|█████████▊| 60619/61904 [7:51:37<28:56,  1.35s/it]
 98%|█████████▊| 60620/61904 [7:51:38<29:03,  1.36s/it]
                                                       
{'loss': 2.4273, 'learning_rate': 1.0208090237261766e-07, 'epoch': 15.67}

 98%|█████████▊| 60620/61904 [7:51:38<29:03,  1.36s/it]
 98%|█████████▊| 60621/61904 [7:51:39<28:52,  1.35s/it]
 98%|█████████▊| 60622/61904 [7:51:41<28:49,  1.35s/it]
 98%|█████████▊| 60623/61904 [7:51:42<28:45,  1.35s/it]
 98%|█████████▊| 60624/61904 [7:51:43<29:28,  1.38s/it]
 98%|█████████▊| 60625/61904 [7:51:45<29:08,  1.37s/it]
 98%|█████████▊| 60626/61904 [7:51:46<29:56,  1.41s/it]
 98%|█████████▊| 60627/61904 [7:51:48<30:23,  1.43s/it]
 98%|█████████▊| 60628/61904 [7:51:49<29:42,  1.40s/it]
 98%|█████████▊| 60629/61904 [7:51:51<30:57,  1.46s/it]
 98%|█████████▊| 60630/61904 [7:51:52<30:17,  1.43s/it]
 98%|█████████▊| 60631/61904 [7:51:53<29:03,  1.37s/it]
 98%|█████████▊| 60632/61904 [7:51:55<29:32,  1.39s/it]
 98%|█████████▊| 60633/61904 [7:51:56<30:25,  1.44s/it]
 98%|█████████▊| 60634/61904 [7:51:58<29:54,  1.41s/it]
 98%|█████████▊| 60635/61904 [7:51:59<29:35,  1.40s/it]
 98%|█████████▊| 60636/61904 [7:52:00<29:45,  1.41s/it]
 98%|█████████▊| 60637/61904 [7:52:02<29:18,  1.39s/it]
 98%|█████████▊| 60638/61904 [7:52:03<28:32,  1.35s/it]
 98%|█████████▊| 60639/61904 [7:52:04<28:46,  1.36s/it]
 98%|█████████▊| 60640/61904 [7:52:06<28:22,  1.35s/it]
                                                       
{'loss': 2.4038, 'learning_rate': 1.0204848956307532e-07, 'epoch': 15.67}

 98%|█████████▊| 60640/61904 [7:52:06<28:22,  1.35s/it]
 98%|█████████▊| 60641/61904 [7:52:07<28:35,  1.36s/it]
 98%|█████████▊| 60642/61904 [7:52:08<27:57,  1.33s/it]
 98%|█████████▊| 60643/61904 [7:52:10<28:24,  1.35s/it]
 98%|█████████▊| 60644/61904 [7:52:11<28:18,  1.35s/it]
 98%|█████████▊| 60645/61904 [7:52:12<27:40,  1.32s/it]
 98%|█████████▊| 60646/61904 [7:52:14<27:22,  1.31s/it]
 98%|█████████▊| 60647/61904 [7:52:15<28:54,  1.38s/it]
 98%|█████████▊| 60648/61904 [7:52:17<28:57,  1.38s/it]
 98%|█████████▊| 60649/61904 [7:52:18<30:24,  1.45s/it]
 98%|█████████▊| 60650/61904 [7:52:19<29:32,  1.41s/it]
 98%|█████████▊| 60651/61904 [7:52:21<30:00,  1.44s/it]
 98%|█████████▊| 60652/61904 [7:52:22<29:29,  1.41s/it]
 98%|█████████▊| 60653/61904 [7:52:24<28:34,  1.37s/it]
 98%|█████████▊| 60654/61904 [7:52:25<28:58,  1.39s/it]
 98%|█████████▊| 60655/61904 [7:52:26<28:35,  1.37s/it]
 98%|█████████▊| 60656/61904 [7:52:28<28:15,  1.36s/it]
 98%|█████████▊| 60657/61904 [7:52:29<29:04,  1.40s/it]
 98%|█████████▊| 60658/61904 [7:52:30<28:12,  1.36s/it]
 98%|█████████▊| 60659/61904 [7:52:32<29:45,  1.43s/it]
 98%|█████████▊| 60660/61904 [7:52:34<30:06,  1.45s/it]
                                                       
{'loss': 2.4434, 'learning_rate': 1.0201607675353299e-07, 'epoch': 15.68}

 98%|█████████▊| 60660/61904 [7:52:34<30:06,  1.45s/it]
 98%|█████████▊| 60661/61904 [7:52:35<29:36,  1.43s/it]
 98%|█████████▊| 60662/61904 [7:52:36<29:19,  1.42s/it]
 98%|█████████▊| 60663/61904 [7:52:38<28:05,  1.36s/it]
 98%|█████████▊| 60664/61904 [7:52:39<28:34,  1.38s/it]
 98%|█████████▊| 60665/61904 [7:52:40<28:33,  1.38s/it]
 98%|█████████▊| 60666/61904 [7:52:42<28:22,  1.38s/it]
 98%|█████████▊| 60667/61904 [7:52:43<28:36,  1.39s/it]
 98%|█████████▊| 60668/61904 [7:52:44<28:05,  1.36s/it]
 98%|█████████▊| 60669/61904 [7:52:46<28:43,  1.40s/it]
 98%|█████████▊| 60670/61904 [7:52:47<28:26,  1.38s/it]
 98%|█████████▊| 60671/61904 [7:52:49<27:58,  1.36s/it]
 98%|█████████▊| 60672/61904 [7:52:50<28:16,  1.38s/it]
 98%|█████████▊| 60673/61904 [7:52:51<28:28,  1.39s/it]
 98%|█████████▊| 60674/61904 [7:52:53<28:21,  1.38s/it]
 98%|█████████▊| 60675/61904 [7:52:54<27:35,  1.35s/it]
 98%|█████████▊| 60676/61904 [7:52:55<27:46,  1.36s/it]
 98%|█████████▊| 60677/61904 [7:52:57<28:25,  1.39s/it]
 98%|█████████▊| 60678/61904 [7:52:58<28:54,  1.41s/it]
 98%|█████████▊| 60679/61904 [7:53:00<28:09,  1.38s/it]
 98%|█████████▊| 60680/61904 [7:53:01<28:16,  1.39s/it]
                                                       
{'loss': 2.3874, 'learning_rate': 1.0198366394399066e-07, 'epoch': 15.68}

 98%|█████████▊| 60680/61904 [7:53:01<28:16,  1.39s/it]
 98%|█████████▊| 60681/61904 [7:53:02<28:03,  1.38s/it]
 98%|█████████▊| 60682/61904 [7:53:04<27:56,  1.37s/it]
 98%|█████████▊| 60683/61904 [7:53:05<28:13,  1.39s/it]
 98%|█████████▊| 60684/61904 [7:53:07<27:41,  1.36s/it]
 98%|█████████▊| 60685/61904 [7:53:08<27:46,  1.37s/it]
 98%|█████████▊| 60686/61904 [7:53:09<27:57,  1.38s/it]
 98%|█████████▊| 60687/61904 [7:53:11<28:47,  1.42s/it]
 98%|█████████▊| 60688/61904 [7:53:12<28:34,  1.41s/it]
 98%|█████████▊| 60689/61904 [7:53:14<28:42,  1.42s/it]
 98%|█████████▊| 60690/61904 [7:53:15<28:48,  1.42s/it]
 98%|█████████▊| 60691/61904 [7:53:17<29:25,  1.46s/it]
 98%|█████████▊| 60692/61904 [7:53:18<28:38,  1.42s/it]
 98%|█████████▊| 60693/61904 [7:53:19<28:50,  1.43s/it]
 98%|█████████▊| 60694/61904 [7:53:21<28:34,  1.42s/it]
 98%|█████████▊| 60695/61904 [7:53:22<28:25,  1.41s/it]
 98%|█████████▊| 60696/61904 [7:53:24<28:16,  1.40s/it]
 98%|█████████▊| 60697/61904 [7:53:25<27:29,  1.37s/it]
 98%|█████████▊| 60698/61904 [7:53:26<27:38,  1.38s/it]
 98%|█████████▊| 60699/61904 [7:53:27<26:52,  1.34s/it]
 98%|█████████▊| 60700/61904 [7:53:29<27:43,  1.38s/it]
                                                       
{'loss': 2.4237, 'learning_rate': 1.0195125113444833e-07, 'epoch': 15.69}

 98%|█████████▊| 60700/61904 [7:53:29<27:43,  1.38s/it]
 98%|█████████▊| 60701/61904 [7:53:30<27:19,  1.36s/it]
 98%|█████████▊| 60702/61904 [7:53:32<27:00,  1.35s/it]
 98%|█████████▊| 60703/61904 [7:53:33<27:44,  1.39s/it]
 98%|█████████▊| 60704/61904 [7:53:35<28:08,  1.41s/it]
 98%|█████████▊| 60705/61904 [7:53:36<28:15,  1.41s/it]
 98%|█████████▊| 60706/61904 [7:53:37<27:53,  1.40s/it]
 98%|█████████▊| 60707/61904 [7:53:39<28:00,  1.40s/it]
 98%|█████████▊| 60708/61904 [7:53:40<27:33,  1.38s/it]
 98%|█████████▊| 60709/61904 [7:53:41<27:41,  1.39s/it]
 98%|█████████▊| 60710/61904 [7:53:43<27:13,  1.37s/it]
 98%|█████████▊| 60711/61904 [7:53:44<27:41,  1.39s/it]
 98%|█████████▊| 60712/61904 [7:53:46<27:52,  1.40s/it]
 98%|█████████▊| 60713/61904 [7:53:47<27:24,  1.38s/it]
 98%|█████████▊| 60714/61904 [7:53:48<27:58,  1.41s/it]
 98%|█████████▊| 60715/61904 [7:53:50<27:14,  1.37s/it]
 98%|█████████▊| 60716/61904 [7:53:51<26:37,  1.35s/it]
 98%|█████████▊| 60717/61904 [7:53:52<26:41,  1.35s/it]
 98%|█████████▊| 60718/61904 [7:53:54<26:27,  1.34s/it]
 98%|█████████▊| 60719/61904 [7:53:55<26:16,  1.33s/it]
 98%|█████████▊| 60720/61904 [7:53:56<25:46,  1.31s/it]
                                                       
{'loss': 2.3947, 'learning_rate': 1.0191883832490599e-07, 'epoch': 15.69}

 98%|█████████▊| 60720/61904 [7:53:56<25:46,  1.31s/it]
 98%|█████████▊| 60721/61904 [7:53:58<25:46,  1.31s/it]
 98%|█████████▊| 60722/61904 [7:53:59<25:46,  1.31s/it]
 98%|█████████▊| 60723/61904 [7:54:00<25:22,  1.29s/it]
 98%|█████████▊| 60724/61904 [7:54:01<25:00,  1.27s/it]
 98%|█████████▊| 60725/61904 [7:54:03<25:04,  1.28s/it]
 98%|█████████▊| 60726/61904 [7:54:04<27:10,  1.38s/it]
 98%|█████████▊| 60727/61904 [7:54:06<27:16,  1.39s/it]
 98%|█████████▊| 60728/61904 [7:54:07<27:05,  1.38s/it]
 98%|█████████▊| 60729/61904 [7:54:08<26:40,  1.36s/it]
 98%|█████████▊| 60730/61904 [7:54:10<26:14,  1.34s/it]
 98%|█████████▊| 60731/61904 [7:54:11<26:42,  1.37s/it]
 98%|█████████▊| 60732/61904 [7:54:12<26:25,  1.35s/it]
 98%|█████████▊| 60733/61904 [7:54:14<25:42,  1.32s/it]
 98%|█████████▊| 60734/61904 [7:54:15<26:01,  1.33s/it]
 98%|█████████▊| 60735/61904 [7:54:16<25:52,  1.33s/it]
 98%|█████████▊| 60736/61904 [7:54:18<26:50,  1.38s/it]
 98%|█████████▊| 60737/61904 [7:54:19<26:47,  1.38s/it]
 98%|█████████▊| 60738/61904 [7:54:21<26:19,  1.35s/it]
 98%|█████████▊| 60739/61904 [7:54:22<27:13,  1.40s/it]
 98%|█████████▊| 60740/61904 [7:54:23<26:54,  1.39s/it]
                                                       
{'loss': 2.4482, 'learning_rate': 1.0188642551536367e-07, 'epoch': 15.7}

 98%|█████████▊| 60740/61904 [7:54:23<26:54,  1.39s/it]
 98%|█████████▊| 60741/61904 [7:54:25<26:41,  1.38s/it]
 98%|█████████▊| 60742/61904 [7:54:26<26:48,  1.38s/it]
 98%|█████████▊| 60743/61904 [7:54:27<26:36,  1.38s/it]
 98%|█████████▊| 60744/61904 [7:54:29<26:20,  1.36s/it]
 98%|█████████▊| 60745/61904 [7:54:30<26:17,  1.36s/it]
 98%|█████████▊| 60746/61904 [7:54:31<25:31,  1.32s/it]
 98%|█████████▊| 60747/61904 [7:54:33<25:48,  1.34s/it]
 98%|█████████▊| 60748/61904 [7:54:34<27:34,  1.43s/it]
 98%|█████████▊| 60749/61904 [7:54:36<26:51,  1.40s/it]
 98%|█████████▊| 60750/61904 [7:54:37<26:11,  1.36s/it]
 98%|█████████▊| 60751/61904 [7:54:38<25:28,  1.33s/it]
 98%|█████████▊| 60752/61904 [7:54:40<26:22,  1.37s/it]
 98%|█████████▊| 60753/61904 [7:54:41<27:25,  1.43s/it]
 98%|█████████▊| 60754/61904 [7:54:43<27:11,  1.42s/it]
 98%|█████████▊| 60755/61904 [7:54:44<27:47,  1.45s/it]
 98%|█████████▊| 60756/61904 [7:54:45<26:30,  1.39s/it]
 98%|█████████▊| 60757/61904 [7:54:47<25:55,  1.36s/it]
 98%|█████████▊| 60758/61904 [7:54:48<26:36,  1.39s/it]
 98%|█████████▊| 60759/61904 [7:54:50<27:01,  1.42s/it]
 98%|█████████▊| 60760/61904 [7:54:51<26:53,  1.41s/it]
                                                       
{'loss': 2.4592, 'learning_rate': 1.0185401270582133e-07, 'epoch': 15.7}

 98%|█████████▊| 60760/61904 [7:54:51<26:53,  1.41s/it]
 98%|█████████▊| 60761/61904 [7:54:52<26:05,  1.37s/it]
 98%|█████████▊| 60762/61904 [7:54:54<26:07,  1.37s/it]
 98%|█████████▊| 60763/61904 [7:54:55<25:43,  1.35s/it]
 98%|█████████▊| 60764/61904 [7:54:56<25:08,  1.32s/it]
 98%|█████████▊| 60765/61904 [7:54:58<24:42,  1.30s/it]
 98%|█████████▊| 60766/61904 [7:54:59<25:04,  1.32s/it]
 98%|█████████▊| 60767/61904 [7:55:00<25:03,  1.32s/it]
 98%|█████████▊| 60768/61904 [7:55:02<25:05,  1.33s/it]
 98%|█████████▊| 60769/61904 [7:55:03<25:31,  1.35s/it]
 98%|█████████▊| 60770/61904 [7:55:04<26:14,  1.39s/it]
 98%|█████████▊| 60771/61904 [7:55:06<25:23,  1.34s/it]
 98%|█████████▊| 60772/61904 [7:55:07<26:12,  1.39s/it]
 98%|█████████▊| 60773/61904 [7:55:09<25:56,  1.38s/it]
 98%|█████████▊| 60774/61904 [7:55:10<26:07,  1.39s/it]
 98%|█████████▊| 60775/61904 [7:55:11<25:36,  1.36s/it]
 98%|█████████▊| 60776/61904 [7:55:13<25:51,  1.38s/it]
 98%|█████████▊| 60777/61904 [7:55:14<26:27,  1.41s/it]
 98%|█████████▊| 60778/61904 [7:55:16<26:33,  1.42s/it]
 98%|█████████▊| 60779/61904 [7:55:17<26:06,  1.39s/it]
 98%|█████████▊| 60780/61904 [7:55:18<26:24,  1.41s/it]
                                                       
{'loss': 2.4356, 'learning_rate': 1.01821599896279e-07, 'epoch': 15.71}

 98%|█████████▊| 60780/61904 [7:55:18<26:24,  1.41s/it]
 98%|█████████▊| 60781/61904 [7:55:20<26:19,  1.41s/it]
 98%|█████████▊| 60782/61904 [7:55:21<27:09,  1.45s/it]
 98%|█████████▊| 60783/61904 [7:55:23<27:33,  1.48s/it]
 98%|█████████▊| 60784/61904 [7:55:24<27:57,  1.50s/it]
 98%|█████████▊| 60785/61904 [7:55:26<26:51,  1.44s/it]
 98%|█████████▊| 60786/61904 [7:55:27<26:36,  1.43s/it]
 98%|█████████▊| 60787/61904 [7:55:28<26:05,  1.40s/it]
 98%|█████████▊| 60788/61904 [7:55:30<25:20,  1.36s/it]
 98%|█████████▊| 60789/61904 [7:55:31<25:08,  1.35s/it]
 98%|█████████▊| 60790/61904 [7:55:32<24:46,  1.33s/it]
 98%|█████████▊| 60791/61904 [7:55:34<25:22,  1.37s/it]
 98%|█████████▊| 60792/61904 [7:55:35<24:09,  1.30s/it]
 98%|█████████▊| 60793/61904 [7:55:36<25:15,  1.36s/it]
 98%|█████████▊| 60794/61904 [7:55:38<24:43,  1.34s/it]
 98%|█████████▊| 60795/61904 [7:55:39<25:30,  1.38s/it]
 98%|█████████▊| 60796/61904 [7:55:40<24:43,  1.34s/it]
 98%|█████████▊| 60797/61904 [7:55:42<24:18,  1.32s/it]
 98%|█████████▊| 60798/61904 [7:55:43<24:11,  1.31s/it]
 98%|█████████▊| 60799/61904 [7:55:44<24:46,  1.35s/it]
 98%|█████████▊| 60800/61904 [7:55:46<24:53,  1.35s/it]
                                                       
{'loss': 2.3921, 'learning_rate': 1.0178918708673667e-07, 'epoch': 15.71}

 98%|█████████▊| 60800/61904 [7:55:46<24:53,  1.35s/it]
 98%|█████████▊| 60801/61904 [7:55:47<26:01,  1.42s/it]
 98%|█████████▊| 60802/61904 [7:55:49<25:06,  1.37s/it]
 98%|█████████▊| 60803/61904 [7:55:50<25:38,  1.40s/it]
 98%|█████████▊| 60804/61904 [7:55:52<25:40,  1.40s/it]
 98%|█████████▊| 60805/61904 [7:55:53<25:13,  1.38s/it]
 98%|█████████▊| 60806/61904 [7:55:54<25:47,  1.41s/it]
 98%|█████████▊| 60807/61904 [7:55:56<25:33,  1.40s/it]
 98%|█████████▊| 60808/61904 [7:55:57<25:09,  1.38s/it]
 98%|█████████▊| 60809/61904 [7:55:58<25:17,  1.39s/it]
 98%|█████████▊| 60810/61904 [7:56:00<25:27,  1.40s/it]
 98%|█████████▊| 60811/61904 [7:56:01<24:52,  1.37s/it]
 98%|█████████▊| 60812/61904 [7:56:03<24:57,  1.37s/it]
 98%|█████████▊| 60813/61904 [7:56:04<25:05,  1.38s/it]
 98%|█████████▊| 60814/61904 [7:56:05<25:36,  1.41s/it]
 98%|█████████▊| 60815/61904 [7:56:07<24:54,  1.37s/it]
 98%|█████████▊| 60816/61904 [7:56:08<24:55,  1.37s/it]
 98%|█████████▊| 60817/61904 [7:56:09<25:02,  1.38s/it]
 98%|█████████▊| 60818/61904 [7:56:11<25:26,  1.41s/it]
 98%|█████████▊| 60819/61904 [7:56:12<24:51,  1.37s/it]
 98%|█████████▊| 60820/61904 [7:56:14<24:28,  1.35s/it]
                                                       
{'loss': 2.4722, 'learning_rate': 1.0175677427719434e-07, 'epoch': 15.72}

 98%|█████████▊| 60820/61904 [7:56:14<24:28,  1.35s/it]
 98%|█████████▊| 60821/61904 [7:56:15<25:27,  1.41s/it]
 98%|█████████▊| 60822/61904 [7:56:16<24:39,  1.37s/it]
 98%|█████████▊| 60823/61904 [7:56:18<24:28,  1.36s/it]
 98%|█████████▊| 60824/61904 [7:56:19<25:01,  1.39s/it]
 98%|█████████▊| 60825/61904 [7:56:21<25:08,  1.40s/it]
 98%|█████████▊| 60826/61904 [7:56:22<25:12,  1.40s/it]
 98%|█████████▊| 60827/61904 [7:56:24<25:58,  1.45s/it]
 98%|█████████▊| 60828/61904 [7:56:25<25:32,  1.42s/it]
 98%|█████████▊| 60829/61904 [7:56:26<24:55,  1.39s/it]
 98%|█████████▊| 60830/61904 [7:56:28<24:46,  1.38s/it]
 98%|█████████▊| 60831/61904 [7:56:29<24:03,  1.35s/it]
 98%|█████████▊| 60832/61904 [7:56:30<24:28,  1.37s/it]
 98%|█████████▊| 60833/61904 [7:56:32<25:07,  1.41s/it]
 98%|█████████▊| 60834/61904 [7:56:33<25:01,  1.40s/it]
 98%|█████████▊| 60835/61904 [7:56:35<26:01,  1.46s/it]
 98%|█████████▊| 60836/61904 [7:56:36<25:40,  1.44s/it]
 98%|█████████▊| 60837/61904 [7:56:38<25:31,  1.44s/it]
 98%|█████████▊| 60838/61904 [7:56:39<25:23,  1.43s/it]
 98%|█████████▊| 60839/61904 [7:56:40<24:41,  1.39s/it]
 98%|█████████▊| 60840/61904 [7:56:42<23:52,  1.35s/it]
                                                       
{'loss': 2.3778, 'learning_rate': 1.01724361467652e-07, 'epoch': 15.72}

 98%|█████████▊| 60840/61904 [7:56:42<23:52,  1.35s/it]
 98%|█████████▊| 60841/61904 [7:56:43<23:59,  1.35s/it]
 98%|█████████▊| 60842/61904 [7:56:44<24:15,  1.37s/it]
 98%|█████████▊| 60843/61904 [7:56:46<24:52,  1.41s/it]
 98%|█████████▊| 60844/61904 [7:56:47<24:29,  1.39s/it]
 98%|█████████▊| 60845/61904 [7:56:49<25:27,  1.44s/it]
 98%|█████████▊| 60846/61904 [7:56:50<25:19,  1.44s/it]
 98%|█████████▊| 60847/61904 [7:56:52<25:24,  1.44s/it]
 98%|█████████▊| 60848/61904 [7:56:53<25:15,  1.44s/it]
 98%|█████████▊| 60849/61904 [7:56:54<24:26,  1.39s/it]
 98%|█████████▊| 60850/61904 [7:56:56<25:28,  1.45s/it]
 98%|█████████▊| 60851/61904 [7:56:57<24:31,  1.40s/it]
 98%|█████████▊| 60852/61904 [7:56:59<25:22,  1.45s/it]
 98%|█████████▊| 60853/61904 [7:57:00<25:14,  1.44s/it]
 98%|█████████▊| 60854/61904 [7:57:01<24:42,  1.41s/it]
 98%|█████████▊| 60855/61904 [7:57:03<25:00,  1.43s/it]
 98%|█████████▊| 60856/61904 [7:57:04<24:43,  1.42s/it]
 98%|█████████▊| 60857/61904 [7:57:06<23:57,  1.37s/it]
 98%|█████████▊| 60858/61904 [7:57:07<24:11,  1.39s/it]
 98%|█████████▊| 60859/61904 [7:57:09<24:48,  1.42s/it]
 98%|█████████▊| 60860/61904 [7:57:10<24:50,  1.43s/it]
                                                       
{'loss': 2.4242, 'learning_rate': 1.0169194865810968e-07, 'epoch': 15.73}

 98%|█████████▊| 60860/61904 [7:57:10<24:50,  1.43s/it]
 98%|█████████▊| 60861/61904 [7:57:11<24:26,  1.41s/it]
 98%|█████████▊| 60862/61904 [7:57:13<24:29,  1.41s/it]
 98%|█████████▊| 60863/61904 [7:57:14<23:57,  1.38s/it]
 98%|█████████▊| 60864/61904 [7:57:16<24:24,  1.41s/it]
 98%|█████████▊| 60865/61904 [7:57:17<24:18,  1.40s/it]
 98%|█████████▊| 60866/61904 [7:57:18<24:19,  1.41s/it]
 98%|█████████▊| 60867/61904 [7:57:20<24:34,  1.42s/it]
 98%|█████████▊| 60868/61904 [7:57:21<23:58,  1.39s/it]
 98%|█████████▊| 60869/61904 [7:57:22<23:31,  1.36s/it]
 98%|█████████▊| 60870/61904 [7:57:24<23:22,  1.36s/it]
 98%|█████████▊| 60871/61904 [7:57:25<23:30,  1.37s/it]
 98%|█████████▊| 60872/61904 [7:57:26<23:19,  1.36s/it]
 98%|█████████▊| 60873/61904 [7:57:28<23:11,  1.35s/it]
 98%|█████████▊| 60874/61904 [7:57:29<23:00,  1.34s/it]
 98%|█████████▊| 60875/61904 [7:57:31<23:08,  1.35s/it]
 98%|█████████▊| 60876/61904 [7:57:32<22:49,  1.33s/it]
 98%|█████████▊| 60877/61904 [7:57:33<23:03,  1.35s/it]
 98%|█████████▊| 60878/61904 [7:57:34<22:45,  1.33s/it]
 98%|█████████▊| 60879/61904 [7:57:36<23:10,  1.36s/it]
 98%|█████████▊| 60880/61904 [7:57:37<22:56,  1.34s/it]
                                                       
{'loss': 2.4437, 'learning_rate': 1.0165953584856734e-07, 'epoch': 15.73}

 98%|█████████▊| 60880/61904 [7:57:37<22:56,  1.34s/it]
 98%|█████████▊| 60881/61904 [7:57:39<22:59,  1.35s/it]
 98%|█████████▊| 60882/61904 [7:57:40<23:28,  1.38s/it]
 98%|█████████▊| 60883/61904 [7:57:41<23:36,  1.39s/it]
 98%|█████████▊| 60884/61904 [7:57:43<23:04,  1.36s/it]
 98%|█████████▊| 60885/61904 [7:57:44<23:22,  1.38s/it]
 98%|█████████▊| 60886/61904 [7:57:45<22:57,  1.35s/it]
 98%|█████████▊| 60887/61904 [7:57:47<23:19,  1.38s/it]
 98%|█████████▊| 60888/61904 [7:57:48<23:25,  1.38s/it]
 98%|█████████▊| 60889/61904 [7:57:50<22:58,  1.36s/it]
 98%|█████████▊| 60890/61904 [7:57:51<23:01,  1.36s/it]
 98%|█████████▊| 60891/61904 [7:57:52<22:45,  1.35s/it]
 98%|█████████▊| 60892/61904 [7:57:54<22:52,  1.36s/it]
 98%|█████████▊| 60893/61904 [7:57:55<22:49,  1.35s/it]
 98%|█████████▊| 60894/61904 [7:57:56<22:19,  1.33s/it]
 98%|█████████▊| 60895/61904 [7:57:58<23:59,  1.43s/it]
 98%|█████████▊| 60896/61904 [7:57:59<24:12,  1.44s/it]
 98%|█████████▊| 60897/61904 [7:58:01<23:21,  1.39s/it]
 98%|█████████▊| 60898/61904 [7:58:02<23:36,  1.41s/it]
 98%|█████████▊| 60899/61904 [7:58:04<23:46,  1.42s/it]
 98%|█████████▊| 60900/61904 [7:58:05<22:46,  1.36s/it]
                                                       
{'loss': 2.4182, 'learning_rate': 1.0162712303902502e-07, 'epoch': 15.74}

 98%|█████████▊| 60900/61904 [7:58:05<22:46,  1.36s/it]
 98%|█████████▊| 60901/61904 [7:58:06<23:21,  1.40s/it]
 98%|█████████▊| 60902/61904 [7:58:08<23:42,  1.42s/it]
 98%|█████████▊| 60903/61904 [7:58:09<23:56,  1.44s/it]
 98%|█████████▊| 60904/61904 [7:58:11<23:29,  1.41s/it]
 98%|█████████▊| 60905/61904 [7:58:12<22:58,  1.38s/it]
 98%|█████████▊| 60906/61904 [7:58:13<22:47,  1.37s/it]
 98%|█████████▊| 60907/61904 [7:58:15<22:41,  1.37s/it]
 98%|█████████▊| 60908/61904 [7:58:16<23:06,  1.39s/it]
 98%|█████████▊| 60909/61904 [7:58:17<23:08,  1.40s/it]
 98%|█████████▊| 60910/61904 [7:58:19<23:01,  1.39s/it]
 98%|█████████▊| 60911/61904 [7:58:20<22:20,  1.35s/it]
 98%|█████████▊| 60912/61904 [7:58:21<22:15,  1.35s/it]
 98%|█████████▊| 60913/61904 [7:58:23<23:06,  1.40s/it]
 98%|█████████▊| 60914/61904 [7:58:24<22:55,  1.39s/it]
 98%|█████████▊| 60915/61904 [7:58:26<22:31,  1.37s/it]
 98%|█████████▊| 60916/61904 [7:58:27<23:20,  1.42s/it]
 98%|█████████▊| 60917/61904 [7:58:28<22:32,  1.37s/it]
 98%|█████████▊| 60918/61904 [7:58:30<22:08,  1.35s/it]
 98%|█████████▊| 60919/61904 [7:58:31<22:19,  1.36s/it]
 98%|█████████▊| 60920/61904 [7:58:33<23:06,  1.41s/it]
                                                       
{'loss': 2.3767, 'learning_rate': 1.0159471022948268e-07, 'epoch': 15.75}

 98%|█████████▊| 60920/61904 [7:58:33<23:06,  1.41s/it]
 98%|█████████▊| 60921/61904 [7:58:34<23:14,  1.42s/it]
 98%|█████████▊| 60922/61904 [7:58:35<23:07,  1.41s/it]
 98%|█████████▊| 60923/61904 [7:58:37<22:44,  1.39s/it]
 98%|█████████▊| 60924/61904 [7:58:38<22:47,  1.40s/it]
 98%|█████████▊| 60925/61904 [7:58:39<22:20,  1.37s/it]
 98%|█████████▊| 60926/61904 [7:58:41<22:40,  1.39s/it]
 98%|█████████▊| 60927/61904 [7:58:42<22:15,  1.37s/it]
 98%|█████████▊| 60928/61904 [7:58:44<22:01,  1.35s/it]
 98%|█████████▊| 60929/61904 [7:58:45<22:34,  1.39s/it]
 98%|█████████▊| 60930/61904 [7:58:46<22:23,  1.38s/it]
 98%|█████████▊| 60931/61904 [7:58:48<21:52,  1.35s/it]
 98%|█████████▊| 60932/61904 [7:58:49<21:50,  1.35s/it]
 98%|█████████▊| 60933/61904 [7:58:50<21:50,  1.35s/it]
 98%|█████████▊| 60934/61904 [7:58:52<21:27,  1.33s/it]
 98%|█████████▊| 60935/61904 [7:58:53<21:48,  1.35s/it]
 98%|█████████▊| 60936/61904 [7:58:54<22:16,  1.38s/it]
 98%|█████████▊| 60937/61904 [7:58:56<22:19,  1.38s/it]
 98%|█████████▊| 60938/61904 [7:58:57<22:33,  1.40s/it]
 98%|█████████▊| 60939/61904 [7:58:59<22:02,  1.37s/it]
 98%|█████████▊| 60940/61904 [7:59:00<21:56,  1.37s/it]
                                                       
{'loss': 2.4421, 'learning_rate': 1.0156229741994035e-07, 'epoch': 15.75}

 98%|█████████▊| 60940/61904 [7:59:00<21:56,  1.37s/it]
 98%|█████████▊| 60941/61904 [7:59:01<21:55,  1.37s/it]
 98%|█████████▊| 60942/61904 [7:59:03<22:34,  1.41s/it]
 98%|█████████▊| 60943/61904 [7:59:04<22:37,  1.41s/it]
 98%|█████████▊| 60944/61904 [7:59:06<22:05,  1.38s/it]
 98%|█████████▊| 60945/61904 [7:59:07<22:02,  1.38s/it]
 98%|█████████▊| 60946/61904 [7:59:08<22:13,  1.39s/it]
 98%|█████████▊| 60947/61904 [7:59:10<21:54,  1.37s/it]
 98%|█████████▊| 60948/61904 [7:59:11<21:49,  1.37s/it]
 98%|█████████▊| 60949/61904 [7:59:12<21:53,  1.37s/it]
 98%|█████████▊| 60950/61904 [7:59:14<21:44,  1.37s/it]
 98%|█████████▊| 60951/61904 [7:59:15<21:37,  1.36s/it]
 98%|█████████▊| 60952/61904 [7:59:16<20:58,  1.32s/it]
 98%|█████████▊| 60953/61904 [7:59:18<21:13,  1.34s/it]
 98%|█████████▊| 60954/61904 [7:59:19<21:34,  1.36s/it]
 98%|█████████▊| 60955/61904 [7:59:21<21:32,  1.36s/it]
 98%|█████████▊| 60956/61904 [7:59:22<21:24,  1.35s/it]
 98%|█████████▊| 60957/61904 [7:59:23<21:01,  1.33s/it]
 98%|█████████▊| 60958/61904 [7:59:25<21:46,  1.38s/it]
 98%|█████████▊| 60959/61904 [7:59:26<21:15,  1.35s/it]
 98%|█████████▊| 60960/61904 [7:59:27<21:32,  1.37s/it]
                                                       
{'loss': 2.4444, 'learning_rate': 1.0152988461039801e-07, 'epoch': 15.76}

 98%|█████████▊| 60960/61904 [7:59:27<21:32,  1.37s/it]
 98%|█████████▊| 60961/61904 [7:59:29<23:02,  1.47s/it]
 98%|█████████▊| 60962/61904 [7:59:30<22:24,  1.43s/it]
 98%|█████████▊| 60963/61904 [7:59:32<21:48,  1.39s/it]
 98%|█████████▊| 60964/61904 [7:59:33<21:55,  1.40s/it]
 98%|█████████▊| 60965/61904 [7:59:34<21:53,  1.40s/it]
 98%|█████████▊| 60966/61904 [7:59:36<22:15,  1.42s/it]
 98%|█████████▊| 60967/61904 [7:59:37<21:43,  1.39s/it]
 98%|█████████▊| 60968/61904 [7:59:39<21:06,  1.35s/it]
 98%|█████████▊| 60969/61904 [7:59:40<21:00,  1.35s/it]
 98%|█████████▊| 60970/61904 [7:59:41<20:46,  1.33s/it]
 98%|█████████▊| 60971/61904 [7:59:43<21:25,  1.38s/it]
 98%|█████████▊| 60972/61904 [7:59:44<20:56,  1.35s/it]
 98%|█████████▊| 60973/61904 [7:59:45<21:32,  1.39s/it]
 98%|█████████▊| 60974/61904 [7:59:47<21:26,  1.38s/it]
 98%|█████████▊| 60975/61904 [7:59:48<21:06,  1.36s/it]
 99%|█████████▊| 60976/61904 [7:59:49<20:53,  1.35s/it]
 99%|█████████▊| 60977/61904 [7:59:51<20:18,  1.31s/it]
 99%|█████████▊| 60978/61904 [7:59:52<21:26,  1.39s/it]
 99%|█████████▊| 60979/61904 [7:59:54<21:17,  1.38s/it]
 99%|█████████▊| 60980/61904 [7:59:55<20:45,  1.35s/it]
                                                       
{'loss': 2.4428, 'learning_rate': 1.0149747180085569e-07, 'epoch': 15.76}

 99%|█████████▊| 60980/61904 [7:59:55<20:45,  1.35s/it]
 99%|█████████▊| 60981/61904 [7:59:56<20:21,  1.32s/it]
 99%|█████████▊| 60982/61904 [7:59:57<20:26,  1.33s/it]
 99%|█████████▊| 60983/61904 [7:59:59<20:54,  1.36s/it]
 99%|█████████▊| 60984/61904 [8:00:00<21:16,  1.39s/it]
 99%|█████████▊| 60985/61904 [8:00:02<21:21,  1.39s/it]
 99%|█████████▊| 60986/61904 [8:00:03<21:16,  1.39s/it]
 99%|█████████▊| 60987/61904 [8:00:04<20:59,  1.37s/it]
 99%|█████████▊| 60988/61904 [8:00:06<20:26,  1.34s/it]
 99%|█████████▊| 60989/61904 [8:00:07<21:24,  1.40s/it]
 99%|█████████▊| 60990/61904 [8:00:09<20:56,  1.38s/it]
 99%|█████████▊| 60991/61904 [8:00:10<21:29,  1.41s/it]
 99%|█████████▊| 60992/61904 [8:00:12<21:47,  1.43s/it]
 99%|█████████▊| 60993/61904 [8:00:13<21:20,  1.41s/it]
 99%|█████████▊| 60994/61904 [8:00:14<21:19,  1.41s/it]
 99%|█████████▊| 60995/61904 [8:00:16<21:28,  1.42s/it]
 99%|█████████▊| 60996/61904 [8:00:17<22:11,  1.47s/it]
 99%|█████████▊| 60997/61904 [8:00:19<21:36,  1.43s/it]
 99%|█████████▊| 60998/61904 [8:00:20<21:08,  1.40s/it]
 99%|█████████▊| 60999/61904 [8:00:21<21:21,  1.42s/it]
 99%|█████████▊| 61000/61904 [8:00:23<20:25,  1.36s/it]
                                                       
{'loss': 2.4303, 'learning_rate': 1.0146505899131335e-07, 'epoch': 15.77}

 99%|█████████▊| 61000/61904 [8:00:23<20:25,  1.36s/it]
 99%|█████████▊| 61001/61904 [8:00:24<20:31,  1.36s/it]
 99%|█████████▊| 61002/61904 [8:00:25<20:25,  1.36s/it]
 99%|█████████▊| 61003/61904 [8:00:27<20:46,  1.38s/it]
 99%|█████████▊| 61004/61904 [8:00:28<21:11,  1.41s/it]
 99%|█████████▊| 61005/61904 [8:00:30<21:05,  1.41s/it]
 99%|█████████▊| 61006/61904 [8:00:31<21:02,  1.41s/it]
 99%|█████████▊| 61007/61904 [8:00:33<20:47,  1.39s/it]
 99%|█████████▊| 61008/61904 [8:00:34<21:17,  1.43s/it]
 99%|█████████▊| 61009/61904 [8:00:36<21:45,  1.46s/it]
 99%|█████████▊| 61010/61904 [8:00:37<21:14,  1.43s/it]
 99%|█████████▊| 61011/61904 [8:00:38<21:34,  1.45s/it]
 99%|█████████▊| 61012/61904 [8:00:40<20:51,  1.40s/it]
 99%|█████████▊| 61013/61904 [8:00:41<20:04,  1.35s/it]
 99%|█████████▊| 61014/61904 [8:00:42<20:19,  1.37s/it]
 99%|█████████▊| 61015/61904 [8:00:44<19:51,  1.34s/it]
 99%|█████████▊| 61016/61904 [8:00:45<19:56,  1.35s/it]
 99%|█████████▊| 61017/61904 [8:00:46<19:33,  1.32s/it]
 99%|█████████▊| 61018/61904 [8:00:48<20:51,  1.41s/it]
 99%|█████████▊| 61019/61904 [8:00:49<20:23,  1.38s/it]
 99%|█████████▊| 61020/61904 [8:00:50<19:44,  1.34s/it]
                                                       
{'loss': 2.385, 'learning_rate': 1.0143264618177103e-07, 'epoch': 15.77}

 99%|█████████▊| 61020/61904 [8:00:50<19:44,  1.34s/it]
 99%|█████████▊| 61021/61904 [8:00:52<19:37,  1.33s/it]
 99%|█████████▊| 61022/61904 [8:00:53<20:22,  1.39s/it]
 99%|█████████▊| 61023/61904 [8:00:55<19:52,  1.35s/it]
 99%|█████████▊| 61024/61904 [8:00:56<19:37,  1.34s/it]
 99%|█████████▊| 61025/61904 [8:00:57<19:15,  1.31s/it]
 99%|█████████▊| 61026/61904 [8:00:58<19:28,  1.33s/it]
 99%|█████████▊| 61027/61904 [8:01:00<19:47,  1.35s/it]
 99%|█████████▊| 61028/61904 [8:01:01<20:16,  1.39s/it]
 99%|█████████▊| 61029/61904 [8:01:03<20:31,  1.41s/it]
 99%|█████████▊| 61030/61904 [8:01:04<20:49,  1.43s/it]
 99%|█████████▊| 61031/61904 [8:01:06<20:18,  1.40s/it]
 99%|█████████▊| 61032/61904 [8:01:07<20:12,  1.39s/it]
 99%|█████████▊| 61033/61904 [8:01:08<20:25,  1.41s/it]
 99%|█████████▊| 61034/61904 [8:01:10<19:34,  1.35s/it]
 99%|█████████▊| 61035/61904 [8:01:11<19:40,  1.36s/it]
 99%|█████████▊| 61036/61904 [8:01:12<19:27,  1.34s/it]
 99%|█████████▊| 61037/61904 [8:01:14<19:55,  1.38s/it]
 99%|█████████▊| 61038/61904 [8:01:15<20:51,  1.45s/it]
 99%|█████████▊| 61039/61904 [8:01:17<20:08,  1.40s/it]
 99%|█████████▊| 61040/61904 [8:01:18<20:06,  1.40s/it]
                                                       
{'loss': 2.4281, 'learning_rate': 1.0140023337222869e-07, 'epoch': 15.78}

 99%|█████████▊| 61040/61904 [8:01:18<20:06,  1.40s/it]
 99%|█████████▊| 61041/61904 [8:01:19<19:44,  1.37s/it]
 99%|█████████▊| 61042/61904 [8:01:21<20:21,  1.42s/it]
 99%|█████████▊| 61043/61904 [8:01:22<20:38,  1.44s/it]
 99%|█████████▊| 61044/61904 [8:01:24<20:24,  1.42s/it]
 99%|█████████▊| 61045/61904 [8:01:25<20:11,  1.41s/it]
 99%|█████████▊| 61046/61904 [8:01:26<19:45,  1.38s/it]
 99%|█████████▊| 61047/61904 [8:01:28<19:54,  1.39s/it]
 99%|█████████▊| 61048/61904 [8:01:29<20:09,  1.41s/it]
 99%|█████████▊| 61049/61904 [8:01:31<19:43,  1.38s/it]
 99%|█████████▊| 61050/61904 [8:01:32<19:39,  1.38s/it]
 99%|█████████▊| 61051/61904 [8:01:33<19:09,  1.35s/it]
 99%|█████████▊| 61052/61904 [8:01:35<19:20,  1.36s/it]
 99%|█████████▊| 61053/61904 [8:01:36<19:12,  1.35s/it]
 99%|█████████▊| 61054/61904 [8:01:37<19:11,  1.36s/it]
 99%|█████████▊| 61055/61904 [8:01:39<19:11,  1.36s/it]
 99%|█████████▊| 61056/61904 [8:01:40<18:49,  1.33s/it]
 99%|█████████▊| 61057/61904 [8:01:41<18:50,  1.33s/it]
 99%|█████████▊| 61058/61904 [8:01:43<19:46,  1.40s/it]
 99%|█████████▊| 61059/61904 [8:01:44<19:16,  1.37s/it]
 99%|█████████▊| 61060/61904 [8:01:46<19:32,  1.39s/it]
                                                       
{'loss': 2.4551, 'learning_rate': 1.0136782056268636e-07, 'epoch': 15.78}

 99%|█████████▊| 61060/61904 [8:01:46<19:32,  1.39s/it]
 99%|█████████▊| 61061/61904 [8:01:47<18:53,  1.34s/it]
 99%|█████████▊| 61062/61904 [8:01:48<18:28,  1.32s/it]
 99%|█████████▊| 61063/61904 [8:01:49<18:12,  1.30s/it]
 99%|█████████▊| 61064/61904 [8:01:51<18:28,  1.32s/it]
 99%|█████████▊| 61065/61904 [8:01:52<18:53,  1.35s/it]
 99%|█████████▊| 61066/61904 [8:01:53<18:27,  1.32s/it]
 99%|█████████▊| 61067/61904 [8:01:55<18:22,  1.32s/it]
 99%|█████████▊| 61068/61904 [8:01:56<18:18,  1.31s/it]
 99%|█████████▊| 61069/61904 [8:01:57<18:20,  1.32s/it]
 99%|█████████▊| 61070/61904 [8:01:59<18:29,  1.33s/it]
 99%|█████████▊| 61071/61904 [8:02:00<18:16,  1.32s/it]
 99%|█████████▊| 61072/61904 [8:02:01<18:36,  1.34s/it]
 99%|█████████▊| 61073/61904 [8:02:03<18:22,  1.33s/it]
 99%|█████████▊| 61074/61904 [8:02:04<18:22,  1.33s/it]
 99%|█████████▊| 61075/61904 [8:02:05<18:39,  1.35s/it]
 99%|█████████▊| 61076/61904 [8:02:07<18:45,  1.36s/it]
 99%|█████████▊| 61077/61904 [8:02:08<18:27,  1.34s/it]
 99%|█████████▊| 61078/61904 [8:02:09<18:19,  1.33s/it]
 99%|█████████▊| 61079/61904 [8:02:11<18:38,  1.36s/it]
 99%|█████████▊| 61080/61904 [8:02:12<18:18,  1.33s/it]
                                                       
{'loss': 2.4592, 'learning_rate': 1.0133540775314404e-07, 'epoch': 15.79}

 99%|█████████▊| 61080/61904 [8:02:12<18:18,  1.33s/it]
 99%|█████████▊| 61081/61904 [8:02:14<18:32,  1.35s/it]
 99%|█████████▊| 61082/61904 [8:02:15<18:01,  1.32s/it]
 99%|█████████▊| 61083/61904 [8:02:16<17:53,  1.31s/it]
 99%|█████████▊| 61084/61904 [8:02:17<18:09,  1.33s/it]
 99%|█████████▊| 61085/61904 [8:02:19<19:02,  1.40s/it]
 99%|█████████▊| 61086/61904 [8:02:20<18:55,  1.39s/it]
 99%|█████████▊| 61087/61904 [8:02:22<19:08,  1.41s/it]
 99%|█████████▊| 61088/61904 [8:02:23<19:03,  1.40s/it]
 99%|█████████▊| 61089/61904 [8:02:25<19:18,  1.42s/it]
 99%|█████████▊| 61090/61904 [8:02:26<19:13,  1.42s/it]
 99%|█████████▊| 61091/61904 [8:02:27<18:56,  1.40s/it]
 99%|█████████▊| 61092/61904 [8:02:29<18:40,  1.38s/it]
 99%|█████████▊| 61093/61904 [8:02:30<18:27,  1.37s/it]
 99%|█████████▊| 61094/61904 [8:02:31<18:23,  1.36s/it]
 99%|█████████▊| 61095/61904 [8:02:33<18:36,  1.38s/it]
 99%|█████████▊| 61096/61904 [8:02:34<18:03,  1.34s/it]
 99%|█████████▊| 61097/61904 [8:02:35<17:51,  1.33s/it]
 99%|█████████▊| 61098/61904 [8:02:37<17:36,  1.31s/it]
 99%|█████████▊| 61099/61904 [8:02:38<17:39,  1.32s/it]
 99%|█████████▊| 61100/61904 [8:02:39<17:45,  1.32s/it]
                                                       
{'loss': 2.4028, 'learning_rate': 1.013029949436017e-07, 'epoch': 15.79}

 99%|█████████▊| 61100/61904 [8:02:39<17:45,  1.32s/it]
 99%|█████████▊| 61101/61904 [8:02:41<17:46,  1.33s/it]
 99%|█████████▊| 61102/61904 [8:02:42<17:50,  1.33s/it]
 99%|█████████▊| 61103/61904 [8:02:43<17:59,  1.35s/it]
 99%|█████████▊| 61104/61904 [8:02:45<17:46,  1.33s/it]
 99%|█████████▊| 61105/61904 [8:02:46<17:36,  1.32s/it]
 99%|█████████▊| 61106/61904 [8:02:47<17:44,  1.33s/it]
 99%|█████████▊| 61107/61904 [8:02:49<17:40,  1.33s/it]
 99%|█████████▊| 61108/61904 [8:02:50<17:54,  1.35s/it]
 99%|█████████▊| 61109/61904 [8:02:51<17:50,  1.35s/it]
 99%|█████████▊| 61110/61904 [8:02:53<18:16,  1.38s/it]
 99%|█████████▊| 61111/61904 [8:02:54<18:26,  1.39s/it]
 99%|█████████▊| 61112/61904 [8:02:56<18:47,  1.42s/it]
 99%|█████████▊| 61113/61904 [8:02:57<18:45,  1.42s/it]
 99%|█████████▊| 61114/61904 [8:02:59<18:10,  1.38s/it]
 99%|█████████▊| 61115/61904 [8:03:00<18:14,  1.39s/it]
 99%|█████████▊| 61116/61904 [8:03:01<18:11,  1.38s/it]
 99%|█████████▊| 61117/61904 [8:03:03<17:57,  1.37s/it]
 99%|█████████▊| 61118/61904 [8:03:04<17:42,  1.35s/it]
 99%|█████████▊| 61119/61904 [8:03:05<17:45,  1.36s/it]
 99%|█████████▊| 61120/61904 [8:03:07<17:16,  1.32s/it]
                                                       
{'loss': 2.466, 'learning_rate': 1.0127058213405936e-07, 'epoch': 15.8}

 99%|█████████▊| 61120/61904 [8:03:07<17:16,  1.32s/it]
 99%|█████████▊| 61121/61904 [8:03:08<17:24,  1.33s/it]
 99%|█████████▊| 61122/61904 [8:03:09<17:56,  1.38s/it]
 99%|█████████▊| 61123/61904 [8:03:11<18:05,  1.39s/it]
 99%|█████████▊| 61124/61904 [8:03:12<18:20,  1.41s/it]
 99%|█████████▊| 61125/61904 [8:03:14<18:07,  1.40s/it]
 99%|█████████▊| 61126/61904 [8:03:15<18:04,  1.39s/it]
 99%|█████████▊| 61127/61904 [8:03:16<17:43,  1.37s/it]
 99%|█████████▊| 61128/61904 [8:03:18<17:32,  1.36s/it]
 99%|█████████▊| 61129/61904 [8:03:19<18:06,  1.40s/it]
 99%|█████████▊| 61130/61904 [8:03:21<17:46,  1.38s/it]
 99%|█████████▉| 61131/61904 [8:03:22<18:30,  1.44s/it]
 99%|█████████▉| 61132/61904 [8:03:23<18:05,  1.41s/it]
 99%|█████████▉| 61133/61904 [8:03:25<18:12,  1.42s/it]
 99%|█████████▉| 61134/61904 [8:03:26<18:29,  1.44s/it]
 99%|█████████▉| 61135/61904 [8:03:28<18:05,  1.41s/it]
 99%|█████████▉| 61136/61904 [8:03:29<18:28,  1.44s/it]
 99%|█████████▉| 61137/61904 [8:03:31<18:21,  1.44s/it]
 99%|█████████▉| 61138/61904 [8:03:32<17:46,  1.39s/it]
 99%|█████████▉| 61139/61904 [8:03:33<17:38,  1.38s/it]
 99%|█████████▉| 61140/61904 [8:03:35<17:47,  1.40s/it]
                                                       
{'loss': 2.4135, 'learning_rate': 1.0123816932451704e-07, 'epoch': 15.8}

 99%|█████████▉| 61140/61904 [8:03:35<17:47,  1.40s/it]
 99%|█████████▉| 61141/61904 [8:03:36<17:26,  1.37s/it]
 99%|█████████▉| 61142/61904 [8:03:37<16:57,  1.33s/it]
 99%|█████████▉| 61143/61904 [8:03:39<17:17,  1.36s/it]
 99%|█████████▉| 61144/61904 [8:03:40<17:30,  1.38s/it]
 99%|█████████▉| 61145/61904 [8:03:42<17:40,  1.40s/it]
 99%|█████████▉| 61146/61904 [8:03:43<17:02,  1.35s/it]
 99%|█████████▉| 61147/61904 [8:03:44<17:00,  1.35s/it]
 99%|█████████▉| 61148/61904 [8:03:46<17:02,  1.35s/it]
 99%|█████████▉| 61149/61904 [8:03:47<17:09,  1.36s/it]
 99%|█████████▉| 61150/61904 [8:03:48<17:42,  1.41s/it]
 99%|█████████▉| 61151/61904 [8:03:50<16:59,  1.35s/it]
 99%|█████████▉| 61152/61904 [8:03:51<16:22,  1.31s/it]
 99%|█████████▉| 61153/61904 [8:03:52<16:23,  1.31s/it]
 99%|█████████▉| 61154/61904 [8:03:53<16:21,  1.31s/it]
 99%|█████████▉| 61155/61904 [8:03:55<16:22,  1.31s/it]
 99%|█████████▉| 61156/61904 [8:03:56<16:57,  1.36s/it]
 99%|█████████▉| 61157/61904 [8:03:58<16:40,  1.34s/it]
 99%|█████████▉| 61158/61904 [8:03:59<16:56,  1.36s/it]
 99%|█████████▉| 61159/61904 [8:04:00<16:32,  1.33s/it]
 99%|█████████▉| 61160/61904 [8:04:02<16:21,  1.32s/it]
                                                       
{'loss': 2.3495, 'learning_rate': 1.0120575651497471e-07, 'epoch': 15.81}

 99%|█████████▉| 61160/61904 [8:04:02<16:21,  1.32s/it]
 99%|█████████▉| 61161/61904 [8:04:03<16:06,  1.30s/it]
 99%|█████████▉| 61162/61904 [8:04:04<16:18,  1.32s/it]
 99%|█████████▉| 61163/61904 [8:04:05<16:10,  1.31s/it]
 99%|█████████▉| 61164/61904 [8:04:07<15:57,  1.29s/it]
 99%|█████████▉| 61165/61904 [8:04:08<15:55,  1.29s/it]
 99%|█████████▉| 61166/61904 [8:04:09<16:17,  1.32s/it]
 99%|█████████▉| 61167/61904 [8:04:11<16:44,  1.36s/it]
 99%|█████████▉| 61168/61904 [8:04:12<16:35,  1.35s/it]
 99%|█████████▉| 61169/61904 [8:04:14<16:46,  1.37s/it]
 99%|█████████▉| 61170/61904 [8:04:15<16:56,  1.39s/it]
 99%|█████████▉| 61171/61904 [8:04:16<16:42,  1.37s/it]
 99%|█████████▉| 61172/61904 [8:04:18<16:34,  1.36s/it]
 99%|█████████▉| 61173/61904 [8:04:19<16:20,  1.34s/it]
 99%|█████████▉| 61174/61904 [8:04:20<16:22,  1.35s/it]
 99%|█████████▉| 61175/61904 [8:04:22<16:14,  1.34s/it]
 99%|█████████▉| 61176/61904 [8:04:23<16:33,  1.36s/it]
 99%|█████████▉| 61177/61904 [8:04:24<16:20,  1.35s/it]
 99%|█████████▉| 61178/61904 [8:04:26<16:39,  1.38s/it]
 99%|█████████▉| 61179/61904 [8:04:27<16:23,  1.36s/it]
 99%|█████████▉| 61180/61904 [8:04:28<16:16,  1.35s/it]
                                                       
{'loss': 2.435, 'learning_rate': 1.0117334370543237e-07, 'epoch': 15.81}

 99%|█████████▉| 61180/61904 [8:04:28<16:16,  1.35s/it]
 99%|█████████▉| 61181/61904 [8:04:30<16:57,  1.41s/it]
 99%|█████████▉| 61182/61904 [8:04:31<16:42,  1.39s/it]
 99%|█████████▉| 61183/61904 [8:04:33<17:12,  1.43s/it]
 99%|█████████▉| 61184/61904 [8:04:34<16:42,  1.39s/it]
 99%|█████████▉| 61185/61904 [8:04:36<16:59,  1.42s/it]
 99%|█████████▉| 61186/61904 [8:04:37<16:33,  1.38s/it]
 99%|█████████▉| 61187/61904 [8:04:38<16:18,  1.36s/it]
 99%|█████████▉| 61188/61904 [8:04:40<16:10,  1.35s/it]
 99%|█████████▉| 61189/61904 [8:04:41<16:00,  1.34s/it]
 99%|█████████▉| 61190/61904 [8:04:43<17:15,  1.45s/it]
 99%|█████████▉| 61191/61904 [8:04:44<16:58,  1.43s/it]
 99%|█████████▉| 61192/61904 [8:04:45<16:35,  1.40s/it]
 99%|█████████▉| 61193/61904 [8:04:47<16:42,  1.41s/it]
 99%|█████████▉| 61194/61904 [8:04:48<17:05,  1.44s/it]
 99%|█████████▉| 61195/61904 [8:04:50<16:32,  1.40s/it]
 99%|█████████▉| 61196/61904 [8:04:51<16:10,  1.37s/it]
 99%|█████████▉| 61197/61904 [8:04:52<16:11,  1.37s/it]
 99%|█████████▉| 61198/61904 [8:04:54<16:17,  1.38s/it]
 99%|█████████▉| 61199/61904 [8:04:55<16:13,  1.38s/it]
 99%|█████████▉| 61200/61904 [8:04:56<16:01,  1.37s/it]
                                                       
{'loss': 2.4339, 'learning_rate': 1.0114093089589004e-07, 'epoch': 15.82}

 99%|█████████▉| 61200/61904 [8:04:56<16:01,  1.37s/it]
 99%|█████████▉| 61201/61904 [8:04:58<15:39,  1.34s/it]
 99%|█████████▉| 61202/61904 [8:04:59<15:44,  1.35s/it]
 99%|█████████▉| 61203/61904 [8:05:00<15:21,  1.31s/it]
 99%|█████████▉| 61204/61904 [8:05:01<15:08,  1.30s/it]
 99%|█████████▉| 61205/61904 [8:05:03<15:00,  1.29s/it]
 99%|█████████▉| 61206/61904 [8:05:04<15:24,  1.32s/it]
 99%|█████████▉| 61207/61904 [8:05:06<16:14,  1.40s/it]
 99%|█████████▉| 61208/61904 [8:05:07<16:00,  1.38s/it]
 99%|█████████▉| 61209/61904 [8:05:09<16:46,  1.45s/it]
 99%|█████████▉| 61210/61904 [8:05:10<16:49,  1.46s/it]
 99%|█████████▉| 61211/61904 [8:05:11<16:07,  1.40s/it]
 99%|█████████▉| 61212/61904 [8:05:13<16:03,  1.39s/it]
 99%|█████████▉| 61213/61904 [8:05:14<15:55,  1.38s/it]
 99%|█████████▉| 61214/61904 [8:05:15<15:40,  1.36s/it]
 99%|█████████▉| 61215/61904 [8:05:17<15:38,  1.36s/it]
 99%|█████████▉| 61216/61904 [8:05:18<15:25,  1.34s/it]
 99%|█████████▉| 61217/61904 [8:05:20<15:39,  1.37s/it]
 99%|█████████▉| 61218/61904 [8:05:21<15:47,  1.38s/it]
 99%|█████████▉| 61219/61904 [8:05:22<15:31,  1.36s/it]
 99%|█████████▉| 61220/61904 [8:05:24<15:50,  1.39s/it]
                                                       
{'loss': 2.4557, 'learning_rate': 1.0110851808634771e-07, 'epoch': 15.82}

 99%|█████████▉| 61220/61904 [8:05:24<15:50,  1.39s/it]
 99%|█████████▉| 61221/61904 [8:05:25<15:33,  1.37s/it]
 99%|█████████▉| 61222/61904 [8:05:27<16:00,  1.41s/it]
 99%|█████████▉| 61223/61904 [8:05:28<16:25,  1.45s/it]
 99%|█████████▉| 61224/61904 [8:05:29<15:58,  1.41s/it]
 99%|█████████▉| 61225/61904 [8:05:31<15:38,  1.38s/it]
 99%|█████████▉| 61226/61904 [8:05:32<15:30,  1.37s/it]
 99%|█████████▉| 61227/61904 [8:05:33<15:17,  1.35s/it]
 99%|█████████▉| 61228/61904 [8:05:35<15:49,  1.40s/it]
 99%|█████████▉| 61229/61904 [8:05:36<15:41,  1.39s/it]
 99%|█████████▉| 61230/61904 [8:05:38<15:44,  1.40s/it]
 99%|█████████▉| 61231/61904 [8:05:39<15:26,  1.38s/it]
 99%|█████████▉| 61232/61904 [8:05:40<14:59,  1.34s/it]
 99%|█████████▉| 61233/61904 [8:05:42<15:10,  1.36s/it]
 99%|█████████▉| 61234/61904 [8:05:43<15:25,  1.38s/it]
 99%|█████████▉| 61235/61904 [8:05:44<15:19,  1.37s/it]
 99%|█████████▉| 61236/61904 [8:05:46<15:19,  1.38s/it]
 99%|█████████▉| 61237/61904 [8:05:47<15:34,  1.40s/it]
 99%|█████████▉| 61238/61904 [8:05:49<15:37,  1.41s/it]
 99%|█████████▉| 61239/61904 [8:05:50<15:46,  1.42s/it]
 99%|█████████▉| 61240/61904 [8:05:52<16:13,  1.47s/it]
                                                       
{'loss': 2.4107, 'learning_rate': 1.0107610527680539e-07, 'epoch': 15.83}

 99%|█████████▉| 61240/61904 [8:05:52<16:13,  1.47s/it]
 99%|█████████▉| 61241/61904 [8:05:53<15:44,  1.42s/it]
 99%|█████████▉| 61242/61904 [8:05:54<15:34,  1.41s/it]
 99%|█████████▉| 61243/61904 [8:05:56<14:52,  1.35s/it]
 99%|█████████▉| 61244/61904 [8:05:57<15:01,  1.37s/it]
 99%|█████████▉| 61245/61904 [8:05:58<15:03,  1.37s/it]
 99%|█████████▉| 61246/61904 [8:06:00<14:44,  1.34s/it]
 99%|█████████▉| 61247/61904 [8:06:01<14:26,  1.32s/it]
 99%|█████████▉| 61248/61904 [8:06:02<14:33,  1.33s/it]
 99%|█████████▉| 61249/61904 [8:06:04<14:49,  1.36s/it]
 99%|█████████▉| 61250/61904 [8:06:05<14:54,  1.37s/it]
 99%|█████████▉| 61251/61904 [8:06:06<14:38,  1.35s/it]
 99%|█████████▉| 61252/61904 [8:06:08<14:52,  1.37s/it]
 99%|█████████▉| 61253/61904 [8:06:09<15:17,  1.41s/it]
 99%|█████████▉| 61254/61904 [8:06:11<15:03,  1.39s/it]
 99%|█████████▉| 61255/61904 [8:06:12<14:51,  1.37s/it]
 99%|█████████▉| 61256/61904 [8:06:14<15:20,  1.42s/it]
 99%|█████████▉| 61257/61904 [8:06:15<15:17,  1.42s/it]
 99%|█████████▉| 61258/61904 [8:06:16<15:25,  1.43s/it]
 99%|█████████▉| 61259/61904 [8:06:18<15:47,  1.47s/it]
 99%|█████████▉| 61260/61904 [8:06:19<15:22,  1.43s/it]
                                                       
{'loss': 2.424, 'learning_rate': 1.0104369246726305e-07, 'epoch': 15.83}

 99%|█████████▉| 61260/61904 [8:06:19<15:22,  1.43s/it]
 99%|█████████▉| 61261/61904 [8:06:21<15:15,  1.42s/it]
 99%|█████████▉| 61262/61904 [8:06:22<14:49,  1.39s/it]
 99%|█████████▉| 61263/61904 [8:06:23<14:29,  1.36s/it]
 99%|█████████▉| 61264/61904 [8:06:25<14:05,  1.32s/it]
 99%|█████████▉| 61265/61904 [8:06:26<14:10,  1.33s/it]
 99%|█████████▉| 61266/61904 [8:06:27<14:08,  1.33s/it]
 99%|█████████▉| 61267/61904 [8:06:29<14:04,  1.33s/it]
 99%|█████████▉| 61268/61904 [8:06:30<13:49,  1.30s/it]
 99%|█████████▉| 61269/61904 [8:06:31<14:08,  1.34s/it]
 99%|█████████▉| 61270/61904 [8:06:33<14:22,  1.36s/it]
 99%|█████████▉| 61271/61904 [8:06:34<14:46,  1.40s/it]
 99%|█████████▉| 61272/61904 [8:06:36<14:36,  1.39s/it]
 99%|█████████▉| 61273/61904 [8:06:37<15:14,  1.45s/it]
 99%|█████████▉| 61274/61904 [8:06:38<14:36,  1.39s/it]
 99%|█████████▉| 61275/61904 [8:06:40<14:37,  1.40s/it]
 99%|█████████▉| 61276/61904 [8:06:41<14:03,  1.34s/it]
 99%|█████████▉| 61277/61904 [8:06:43<14:26,  1.38s/it]
 99%|█████████▉| 61278/61904 [8:06:44<14:37,  1.40s/it]
 99%|█████████▉| 61279/61904 [8:06:45<14:18,  1.37s/it]
 99%|█████████▉| 61280/61904 [8:06:47<14:33,  1.40s/it]
                                                       
{'loss': 2.3895, 'learning_rate': 1.0101127965772071e-07, 'epoch': 15.84}

 99%|█████████▉| 61280/61904 [8:06:47<14:33,  1.40s/it]
 99%|█████████▉| 61281/61904 [8:06:48<14:20,  1.38s/it]
 99%|█████████▉| 61282/61904 [8:06:49<14:27,  1.39s/it]
 99%|█████████▉| 61283/61904 [8:06:51<14:45,  1.43s/it]
 99%|█████████▉| 61284/61904 [8:06:52<14:36,  1.41s/it]
 99%|█████████▉| 61285/61904 [8:06:54<14:22,  1.39s/it]
 99%|█████████▉| 61286/61904 [8:06:55<14:12,  1.38s/it]
 99%|█████████▉| 61287/61904 [8:06:56<13:57,  1.36s/it]
 99%|█████████▉| 61288/61904 [8:06:58<13:57,  1.36s/it]
 99%|█████████▉| 61289/61904 [8:06:59<13:55,  1.36s/it]
 99%|█████████▉| 61290/61904 [8:07:00<14:03,  1.37s/it]
 99%|█████████▉| 61291/61904 [8:07:02<14:13,  1.39s/it]
 99%|█████████▉| 61292/61904 [8:07:03<14:08,  1.39s/it]
 99%|█████████▉| 61293/61904 [8:07:05<14:18,  1.40s/it]
 99%|█████████▉| 61294/61904 [8:07:06<13:52,  1.36s/it]
 99%|█████████▉| 61295/61904 [8:07:07<13:42,  1.35s/it]
 99%|█████████▉| 61296/61904 [8:07:09<13:52,  1.37s/it]
 99%|█████████▉| 61297/61904 [8:07:10<13:44,  1.36s/it]
 99%|█████████▉| 61298/61904 [8:07:12<13:57,  1.38s/it]
 99%|█████████▉| 61299/61904 [8:07:13<13:59,  1.39s/it]
 99%|█████████▉| 61300/61904 [8:07:14<13:59,  1.39s/it]
                                                       
{'loss': 2.3533, 'learning_rate': 1.0097886684817838e-07, 'epoch': 15.84}

 99%|█████████▉| 61300/61904 [8:07:14<13:59,  1.39s/it]
 99%|█████████▉| 61301/61904 [8:07:16<13:46,  1.37s/it]
 99%|█████████▉| 61302/61904 [8:07:17<13:45,  1.37s/it]
 99%|█████████▉| 61303/61904 [8:07:19<14:11,  1.42s/it]
 99%|█████████▉| 61304/61904 [8:07:20<13:54,  1.39s/it]
 99%|█████████▉| 61305/61904 [8:07:21<13:55,  1.39s/it]
 99%|█████████▉| 61306/61904 [8:07:23<13:38,  1.37s/it]
 99%|█████████▉| 61307/61904 [8:07:24<13:09,  1.32s/it]
 99%|█████████▉| 61308/61904 [8:07:25<13:35,  1.37s/it]
 99%|█████████▉| 61309/61904 [8:07:27<13:17,  1.34s/it]
 99%|█████████▉| 61310/61904 [8:07:28<13:05,  1.32s/it]
 99%|█████████▉| 61311/61904 [8:07:29<13:15,  1.34s/it]
 99%|█████████▉| 61312/61904 [8:07:30<12:59,  1.32s/it]
 99%|█████████▉| 61313/61904 [8:07:32<12:54,  1.31s/it]
 99%|█████████▉| 61314/61904 [8:07:33<12:40,  1.29s/it]
 99%|█████████▉| 61315/61904 [8:07:34<12:58,  1.32s/it]
 99%|█████████▉| 61316/61904 [8:07:36<13:12,  1.35s/it]
 99%|█████████▉| 61317/61904 [8:07:37<13:44,  1.40s/it]
 99%|█████████▉| 61318/61904 [8:07:39<13:28,  1.38s/it]
 99%|█████████▉| 61319/61904 [8:07:40<13:44,  1.41s/it]
 99%|█████████▉| 61320/61904 [8:07:41<13:10,  1.35s/it]
                                                       
{'loss': 2.4579, 'learning_rate': 1.0094645403863606e-07, 'epoch': 15.85}

 99%|█████████▉| 61320/61904 [8:07:41<13:10,  1.35s/it]
 99%|█████████▉| 61321/61904 [8:07:43<13:21,  1.37s/it]
 99%|█████████▉| 61322/61904 [8:07:44<13:04,  1.35s/it]
 99%|█████████▉| 61323/61904 [8:07:45<13:08,  1.36s/it]
 99%|█████████▉| 61324/61904 [8:07:47<13:23,  1.38s/it]
 99%|█████████▉| 61325/61904 [8:07:48<13:35,  1.41s/it]
 99%|█████████▉| 61326/61904 [8:07:50<13:48,  1.43s/it]
 99%|█████████▉| 61327/61904 [8:07:51<13:40,  1.42s/it]
 99%|█████████▉| 61328/61904 [8:07:53<13:55,  1.45s/it]
 99%|█████████▉| 61329/61904 [8:07:54<13:38,  1.42s/it]
 99%|█████████▉| 61330/61904 [8:07:55<13:14,  1.38s/it]
 99%|█████████▉| 61331/61904 [8:07:57<13:32,  1.42s/it]
 99%|█████████▉| 61332/61904 [8:07:58<13:26,  1.41s/it]
 99%|█████████▉| 61333/61904 [8:08:00<12:59,  1.37s/it]
 99%|█████████▉| 61334/61904 [8:08:01<12:41,  1.34s/it]
 99%|█████████▉| 61335/61904 [8:08:02<12:54,  1.36s/it]
 99%|█████████▉| 61336/61904 [8:08:04<12:52,  1.36s/it]
 99%|█████████▉| 61337/61904 [8:08:05<12:53,  1.36s/it]
 99%|█████████▉| 61338/61904 [8:08:06<13:11,  1.40s/it]
 99%|█████████▉| 61339/61904 [8:08:08<13:06,  1.39s/it]
 99%|█████████▉| 61340/61904 [8:08:09<12:56,  1.38s/it]
                                                       
{'loss': 2.4648, 'learning_rate': 1.0091404122909372e-07, 'epoch': 15.85}

 99%|█████████▉| 61340/61904 [8:08:09<12:56,  1.38s/it]
 99%|█████████▉| 61341/61904 [8:08:10<12:34,  1.34s/it]
 99%|█████████▉| 61342/61904 [8:08:12<12:38,  1.35s/it]
 99%|█████████▉| 61343/61904 [8:08:13<12:50,  1.37s/it]
 99%|█████████▉| 61344/61904 [8:08:15<12:58,  1.39s/it]
 99%|█████████▉| 61345/61904 [8:08:16<13:16,  1.42s/it]
 99%|█████████▉| 61346/61904 [8:08:18<13:19,  1.43s/it]
 99%|█████████▉| 61347/61904 [8:08:19<13:05,  1.41s/it]
 99%|█████████▉| 61348/61904 [8:08:20<12:40,  1.37s/it]
 99%|█████████▉| 61349/61904 [8:08:22<12:36,  1.36s/it]
 99%|█████████▉| 61350/61904 [8:08:23<12:33,  1.36s/it]
 99%|█████████▉| 61351/61904 [8:08:24<12:32,  1.36s/it]
 99%|█████████▉| 61352/61904 [8:08:26<12:57,  1.41s/it]
 99%|█████████▉| 61353/61904 [8:08:27<12:38,  1.38s/it]
 99%|█████████▉| 61354/61904 [8:08:29<12:34,  1.37s/it]
 99%|█████████▉| 61355/61904 [8:08:30<12:28,  1.36s/it]
 99%|█████████▉| 61356/61904 [8:08:31<12:27,  1.36s/it]
 99%|█████████▉| 61357/61904 [8:08:33<12:25,  1.36s/it]
 99%|█████████▉| 61358/61904 [8:08:34<12:21,  1.36s/it]
 99%|█████████▉| 61359/61904 [8:08:35<12:20,  1.36s/it]
 99%|█████████▉| 61360/61904 [8:08:37<12:25,  1.37s/it]
                                                       
{'loss': 2.4004, 'learning_rate': 1.0088162841955138e-07, 'epoch': 15.86}

 99%|█████████▉| 61360/61904 [8:08:37<12:25,  1.37s/it]
 99%|█████████▉| 61361/61904 [8:08:38<11:56,  1.32s/it]
 99%|█████████▉| 61362/61904 [8:08:39<12:03,  1.34s/it]
 99%|█████████▉| 61363/61904 [8:08:41<12:28,  1.38s/it]
 99%|█████████▉| 61364/61904 [8:08:42<13:11,  1.47s/it]
 99%|█████████▉| 61365/61904 [8:08:44<12:43,  1.42s/it]
 99%|█████████▉| 61366/61904 [8:08:45<13:04,  1.46s/it]
 99%|█████████▉| 61367/61904 [8:08:47<12:37,  1.41s/it]
 99%|█████████▉| 61368/61904 [8:08:48<12:30,  1.40s/it]
 99%|█████████▉| 61369/61904 [8:08:49<12:17,  1.38s/it]
 99%|█████████▉| 61370/61904 [8:08:51<12:20,  1.39s/it]
 99%|█████████▉| 61371/61904 [8:08:52<12:38,  1.42s/it]
 99%|█████████▉| 61372/61904 [8:08:54<12:39,  1.43s/it]
 99%|█████████▉| 61373/61904 [8:08:55<12:29,  1.41s/it]
 99%|█████████▉| 61374/61904 [8:08:56<12:21,  1.40s/it]
 99%|█████████▉| 61375/61904 [8:08:58<12:33,  1.42s/it]
 99%|█████████▉| 61376/61904 [8:08:59<12:18,  1.40s/it]
 99%|█████████▉| 61377/61904 [8:09:01<12:15,  1.40s/it]
 99%|█████████▉| 61378/61904 [8:09:02<12:14,  1.40s/it]
 99%|█████████▉| 61379/61904 [8:09:03<11:46,  1.35s/it]
 99%|█████████▉| 61380/61904 [8:09:04<11:27,  1.31s/it]
                                                       
{'loss': 2.4231, 'learning_rate': 1.0084921561000907e-07, 'epoch': 15.86}

 99%|█████████▉| 61380/61904 [8:09:04<11:27,  1.31s/it]
 99%|█████████▉| 61381/61904 [8:09:06<11:42,  1.34s/it]
 99%|█████████▉| 61382/61904 [8:09:07<11:59,  1.38s/it]
 99%|█████████▉| 61383/61904 [8:09:09<12:19,  1.42s/it]
 99%|█████████▉| 61384/61904 [8:09:10<12:26,  1.44s/it]
 99%|█████████▉| 61385/61904 [8:09:12<12:15,  1.42s/it]
 99%|█████████▉| 61386/61904 [8:09:13<12:01,  1.39s/it]
 99%|█████████▉| 61387/61904 [8:09:14<11:46,  1.37s/it]
 99%|█████████▉| 61388/61904 [8:09:16<11:55,  1.39s/it]
 99%|█████████▉| 61389/61904 [8:09:17<11:59,  1.40s/it]
 99%|█████████▉| 61390/61904 [8:09:19<11:56,  1.39s/it]
 99%|█████████▉| 61391/61904 [8:09:20<12:14,  1.43s/it]
 99%|█████████▉| 61392/61904 [8:09:22<12:26,  1.46s/it]
 99%|█████████▉| 61393/61904 [8:09:23<12:11,  1.43s/it]
 99%|█████████▉| 61394/61904 [8:09:24<11:57,  1.41s/it]
 99%|█████████▉| 61395/61904 [8:09:26<11:55,  1.41s/it]
 99%|█████████▉| 61396/61904 [8:09:27<11:40,  1.38s/it]
 99%|█████████▉| 61397/61904 [8:09:29<12:15,  1.45s/it]
 99%|█████████▉| 61398/61904 [8:09:30<11:55,  1.41s/it]
 99%|█████████▉| 61399/61904 [8:09:31<11:27,  1.36s/it]
 99%|█████████▉| 61400/61904 [8:09:33<11:32,  1.37s/it]
                                                       
{'loss': 2.4427, 'learning_rate': 1.0081680280046673e-07, 'epoch': 15.87}

 99%|█████████▉| 61400/61904 [8:09:33<11:32,  1.37s/it]
 99%|█████████▉| 61401/61904 [8:09:34<11:16,  1.35s/it]
 99%|█████████▉| 61402/61904 [8:09:35<11:24,  1.36s/it]
 99%|█████████▉| 61403/61904 [8:09:37<11:17,  1.35s/it]
 99%|█████████▉| 61404/61904 [8:09:38<11:37,  1.39s/it]
 99%|█████████▉| 61405/61904 [8:09:40<11:40,  1.40s/it]
 99%|█████████▉| 61406/61904 [8:09:41<11:19,  1.36s/it]
 99%|█████████▉| 61407/61904 [8:09:42<11:39,  1.41s/it]
 99%|█████████▉| 61408/61904 [8:09:44<11:37,  1.41s/it]
 99%|█████████▉| 61409/61904 [8:09:45<11:26,  1.39s/it]
 99%|█████████▉| 61410/61904 [8:09:46<11:18,  1.37s/it]
 99%|█████████▉| 61411/61904 [8:09:48<11:25,  1.39s/it]
 99%|█████████▉| 61412/61904 [8:09:49<11:13,  1.37s/it]
 99%|█████████▉| 61413/61904 [8:09:51<11:05,  1.36s/it]
 99%|█████████▉| 61414/61904 [8:09:52<10:54,  1.34s/it]
 99%|█████████▉| 61415/61904 [8:09:53<11:20,  1.39s/it]
 99%|█████████▉| 61416/61904 [8:09:55<11:14,  1.38s/it]
 99%|█████████▉| 61417/61904 [8:09:56<11:23,  1.40s/it]
 99%|█████████▉| 61418/61904 [8:09:57<11:15,  1.39s/it]
 99%|█████████▉| 61419/61904 [8:09:59<11:37,  1.44s/it]
 99%|█████████▉| 61420/61904 [8:10:01<11:58,  1.48s/it]
                                                       
{'loss': 2.4253, 'learning_rate': 1.007843899909244e-07, 'epoch': 15.87}

 99%|█████████▉| 61420/61904 [8:10:01<11:58,  1.48s/it]
 99%|█████████▉| 61421/61904 [8:10:02<11:50,  1.47s/it]
 99%|█████████▉| 61422/61904 [8:10:04<11:43,  1.46s/it]
 99%|█████████▉| 61423/61904 [8:10:05<11:33,  1.44s/it]
 99%|█████████▉| 61424/61904 [8:10:06<11:26,  1.43s/it]
 99%|█████████▉| 61425/61904 [8:10:08<11:17,  1.41s/it]
 99%|█████████▉| 61426/61904 [8:10:09<11:29,  1.44s/it]
 99%|█████████▉| 61427/61904 [8:10:11<11:34,  1.46s/it]
 99%|█████████▉| 61428/61904 [8:10:12<11:14,  1.42s/it]
 99%|█████████▉| 61429/61904 [8:10:13<11:17,  1.43s/it]
 99%|█████████▉| 61430/61904 [8:10:15<10:59,  1.39s/it]
 99%|█████████▉| 61431/61904 [8:10:16<11:13,  1.42s/it]
 99%|█████████▉| 61432/61904 [8:10:18<10:47,  1.37s/it]
 99%|█████████▉| 61433/61904 [8:10:19<10:50,  1.38s/it]
 99%|█████████▉| 61434/61904 [8:10:20<10:36,  1.35s/it]
 99%|█████████▉| 61435/61904 [8:10:22<10:27,  1.34s/it]
 99%|█████████▉| 61436/61904 [8:10:23<10:20,  1.33s/it]
 99%|█████████▉| 61437/61904 [8:10:24<10:09,  1.30s/it]
 99%|█████████▉| 61438/61904 [8:10:25<10:08,  1.31s/it]
 99%|█████████▉| 61439/61904 [8:10:27<10:32,  1.36s/it]
 99%|█████████▉| 61440/61904 [8:10:28<10:43,  1.39s/it]
                                                       
{'loss': 2.3745, 'learning_rate': 1.0075197718138206e-07, 'epoch': 15.88}

 99%|█████████▉| 61440/61904 [8:10:28<10:43,  1.39s/it]
 99%|█████████▉| 61441/61904 [8:10:30<10:41,  1.39s/it]
 99%|█████████▉| 61442/61904 [8:10:31<11:05,  1.44s/it]
 99%|█████████▉| 61443/61904 [8:10:33<11:19,  1.47s/it]
 99%|█████████▉| 61444/61904 [8:10:34<11:05,  1.45s/it]
 99%|█████████▉| 61445/61904 [8:10:36<10:54,  1.43s/it]
 99%|█████████▉| 61446/61904 [8:10:37<10:51,  1.42s/it]
 99%|█████████▉| 61447/61904 [8:10:38<10:53,  1.43s/it]
 99%|█████████▉| 61448/61904 [8:10:40<10:53,  1.43s/it]
 99%|█████████▉| 61449/61904 [8:10:41<10:50,  1.43s/it]
 99%|█████████▉| 61450/61904 [8:10:43<10:49,  1.43s/it]
 99%|█████████▉| 61451/61904 [8:10:44<10:34,  1.40s/it]
 99%|█████████▉| 61452/61904 [8:10:45<10:25,  1.38s/it]
 99%|█████████▉| 61453/61904 [8:10:47<10:04,  1.34s/it]
 99%|█████████▉| 61454/61904 [8:10:48<09:52,  1.32s/it]
 99%|█████████▉| 61455/61904 [8:10:49<10:11,  1.36s/it]
 99%|█████████▉| 61456/61904 [8:10:51<10:06,  1.35s/it]
 99%|█████████▉| 61457/61904 [8:10:52<10:01,  1.35s/it]
 99%|█████████▉| 61458/61904 [8:10:54<10:34,  1.42s/it]
 99%|█████████▉| 61459/61904 [8:10:55<10:26,  1.41s/it]
 99%|█████████▉| 61460/61904 [8:10:56<10:30,  1.42s/it]
                                                       
{'loss': 2.4168, 'learning_rate': 1.0071956437183975e-07, 'epoch': 15.88}

 99%|█████████▉| 61460/61904 [8:10:56<10:30,  1.42s/it]
 99%|█████████▉| 61461/61904 [8:10:58<10:48,  1.46s/it]
 99%|█████████▉| 61462/61904 [8:11:00<10:53,  1.48s/it]
 99%|█████████▉| 61463/61904 [8:11:01<10:24,  1.42s/it]
 99%|█████████▉| 61464/61904 [8:11:02<10:04,  1.37s/it]
 99%|█████████▉| 61465/61904 [8:11:03<09:54,  1.36s/it]
 99%|█████████▉| 61466/61904 [8:11:05<09:47,  1.34s/it]
 99%|█████████▉| 61467/61904 [8:11:06<09:53,  1.36s/it]
 99%|█████████▉| 61468/61904 [8:11:07<09:55,  1.37s/it]
 99%|█████████▉| 61469/61904 [8:11:09<10:05,  1.39s/it]
 99%|█████████▉| 61470/61904 [8:11:10<09:53,  1.37s/it]
 99%|█████████▉| 61471/61904 [8:11:12<09:45,  1.35s/it]
 99%|█████████▉| 61472/61904 [8:11:13<09:47,  1.36s/it]
 99%|█████████▉| 61473/61904 [8:11:14<09:45,  1.36s/it]
 99%|█████████▉| 61474/61904 [8:11:16<10:00,  1.40s/it]
 99%|█████████▉| 61475/61904 [8:11:17<10:11,  1.42s/it]
 99%|█████████▉| 61476/61904 [8:11:19<10:01,  1.40s/it]
 99%|█████████▉| 61477/61904 [8:11:20<09:53,  1.39s/it]
 99%|█████████▉| 61478/61904 [8:11:21<09:56,  1.40s/it]
 99%|█████████▉| 61479/61904 [8:11:23<09:41,  1.37s/it]
 99%|█████████▉| 61480/61904 [8:11:24<09:52,  1.40s/it]
                                                       
{'loss': 2.4033, 'learning_rate': 1.0068715156229741e-07, 'epoch': 15.89}

 99%|█████████▉| 61480/61904 [8:11:24<09:52,  1.40s/it]
 99%|█████████▉| 61481/61904 [8:11:25<09:35,  1.36s/it]
 99%|█████████▉| 61482/61904 [8:11:27<09:55,  1.41s/it]
 99%|█████████▉| 61483/61904 [8:11:28<09:37,  1.37s/it]
 99%|█████████▉| 61484/61904 [8:11:30<09:34,  1.37s/it]
 99%|█████████▉| 61485/61904 [8:11:31<09:12,  1.32s/it]
 99%|█████████▉| 61486/61904 [8:11:32<09:23,  1.35s/it]
 99%|█████████▉| 61487/61904 [8:11:34<09:29,  1.37s/it]
 99%|█████████▉| 61488/61904 [8:11:35<09:42,  1.40s/it]
 99%|█████████▉| 61489/61904 [8:11:37<09:42,  1.40s/it]
 99%|█████████▉| 61490/61904 [8:11:38<09:31,  1.38s/it]
 99%|█████████▉| 61491/61904 [8:11:39<09:20,  1.36s/it]
 99%|█████████▉| 61492/61904 [8:11:41<09:40,  1.41s/it]
 99%|█████████▉| 61493/61904 [8:11:42<09:46,  1.43s/it]
 99%|█████████▉| 61494/61904 [8:11:44<09:50,  1.44s/it]
 99%|█████████▉| 61495/61904 [8:11:45<09:32,  1.40s/it]
 99%|█████████▉| 61496/61904 [8:11:46<09:41,  1.43s/it]
 99%|█████████▉| 61497/61904 [8:11:48<09:43,  1.43s/it]
 99%|█████████▉| 61498/61904 [8:11:49<09:32,  1.41s/it]
 99%|█████████▉| 61499/61904 [8:11:51<09:50,  1.46s/it]
 99%|█████████▉| 61500/61904 [8:11:52<09:26,  1.40s/it]
                                                       
{'loss': 2.3622, 'learning_rate': 1.0065473875275507e-07, 'epoch': 15.89}

 99%|█████████▉| 61500/61904 [8:11:52<09:26,  1.40s/it]
 99%|█████████▉| 61501/61904 [8:11:53<09:16,  1.38s/it]
 99%|█████████▉| 61502/61904 [8:11:55<09:12,  1.37s/it]
 99%|█████████▉| 61503/61904 [8:11:56<09:08,  1.37s/it]
 99%|█████████▉| 61504/61904 [8:11:57<09:05,  1.36s/it]
 99%|█████████▉| 61505/61904 [8:11:59<09:11,  1.38s/it]
 99%|█████████▉| 61506/61904 [8:12:00<09:08,  1.38s/it]
 99%|█████████▉| 61507/61904 [8:12:02<09:25,  1.42s/it]
 99%|█████████▉| 61508/61904 [8:12:03<09:37,  1.46s/it]
 99%|█████████▉| 61509/61904 [8:12:05<09:21,  1.42s/it]
 99%|█████████▉| 61510/61904 [8:12:06<09:05,  1.38s/it]
 99%|█████████▉| 61511/61904 [8:12:07<08:59,  1.37s/it]
 99%|█████████▉| 61512/61904 [8:12:09<09:02,  1.38s/it]
 99%|█████████▉| 61513/61904 [8:12:10<09:05,  1.39s/it]
 99%|█████████▉| 61514/61904 [8:12:12<09:08,  1.41s/it]
 99%|█████████▉| 61515/61904 [8:12:13<09:07,  1.41s/it]
 99%|█████████▉| 61516/61904 [8:12:14<09:01,  1.39s/it]
 99%|█████████▉| 61517/61904 [8:12:16<08:58,  1.39s/it]
 99%|█████████▉| 61518/61904 [8:12:17<08:59,  1.40s/it]
 99%|█████████▉| 61519/61904 [8:12:18<08:51,  1.38s/it]
 99%|█████████▉| 61520/61904 [8:12:20<08:54,  1.39s/it]
                                                       
{'loss': 2.4244, 'learning_rate': 1.0062232594321273e-07, 'epoch': 15.9}

 99%|█████████▉| 61520/61904 [8:12:20<08:54,  1.39s/it]
 99%|█████████▉| 61521/61904 [8:12:22<09:17,  1.45s/it]
 99%|█████████▉| 61522/61904 [8:12:23<09:01,  1.42s/it]
 99%|█████████▉| 61523/61904 [8:12:24<08:46,  1.38s/it]
 99%|█████████▉| 61524/61904 [8:12:25<08:28,  1.34s/it]
 99%|█████████▉| 61525/61904 [8:12:27<08:50,  1.40s/it]
 99%|█████████▉| 61526/61904 [8:12:28<09:03,  1.44s/it]
 99%|█████████▉| 61527/61904 [8:12:30<08:49,  1.41s/it]
 99%|█████████▉| 61528/61904 [8:12:31<08:46,  1.40s/it]
 99%|█████████▉| 61529/61904 [8:12:32<08:35,  1.38s/it]
 99%|█████████▉| 61530/61904 [8:12:34<08:48,  1.41s/it]
 99%|█████████▉| 61531/61904 [8:12:36<09:01,  1.45s/it]
 99%|█████████▉| 61532/61904 [8:12:37<09:25,  1.52s/it]
 99%|█████████▉| 61533/61904 [8:12:39<09:13,  1.49s/it]
 99%|█████████▉| 61534/61904 [8:12:40<09:02,  1.47s/it]
 99%|█████████▉| 61535/61904 [8:12:42<09:02,  1.47s/it]
 99%|█████████▉| 61536/61904 [8:12:43<08:52,  1.45s/it]
 99%|█████████▉| 61537/61904 [8:12:44<08:36,  1.41s/it]
 99%|█████████▉| 61538/61904 [8:12:46<08:41,  1.43s/it]
 99%|█████████▉| 61539/61904 [8:12:47<08:40,  1.43s/it]
 99%|█████████▉| 61540/61904 [8:12:49<08:44,  1.44s/it]
                                                       
{'loss': 2.3934, 'learning_rate': 1.0058991313367042e-07, 'epoch': 15.91}

 99%|█████████▉| 61540/61904 [8:12:49<08:44,  1.44s/it]
 99%|█████████▉| 61541/61904 [8:12:50<08:49,  1.46s/it]
 99%|█████████▉| 61542/61904 [8:12:51<08:34,  1.42s/it]
 99%|█████████▉| 61543/61904 [8:12:53<08:36,  1.43s/it]
 99%|█████████▉| 61544/61904 [8:12:54<08:29,  1.41s/it]
 99%|█████████▉| 61545/61904 [8:12:56<08:14,  1.38s/it]
 99%|█████████▉| 61546/61904 [8:12:57<08:22,  1.40s/it]
 99%|█████████▉| 61547/61904 [8:12:58<08:16,  1.39s/it]
 99%|█████████▉| 61548/61904 [8:13:00<08:53,  1.50s/it]
 99%|█████████▉| 61549/61904 [8:13:02<08:43,  1.47s/it]
 99%|█████████▉| 61550/61904 [8:13:03<08:24,  1.42s/it]
 99%|█████████▉| 61551/61904 [8:13:04<08:25,  1.43s/it]
 99%|█████████▉| 61552/61904 [8:13:06<08:08,  1.39s/it]
 99%|█████████▉| 61553/61904 [8:13:07<08:15,  1.41s/it]
 99%|█████████▉| 61554/61904 [8:13:08<08:11,  1.40s/it]
 99%|█████████▉| 61555/61904 [8:13:10<08:07,  1.40s/it]
 99%|█████████▉| 61556/61904 [8:13:11<08:02,  1.39s/it]
 99%|█████████▉| 61557/61904 [8:13:13<08:07,  1.41s/it]
 99%|█████████▉| 61558/61904 [8:13:14<08:07,  1.41s/it]
 99%|█████████▉| 61559/61904 [8:13:15<07:52,  1.37s/it]
 99%|█████████▉| 61560/61904 [8:13:17<07:48,  1.36s/it]
                                                       
{'loss': 2.4082, 'learning_rate': 1.0055750032412808e-07, 'epoch': 15.91}

 99%|█████████▉| 61560/61904 [8:13:17<07:48,  1.36s/it]
 99%|█████████▉| 61561/61904 [8:13:18<07:52,  1.38s/it]
 99%|█████████▉| 61562/61904 [8:13:19<07:45,  1.36s/it]
 99%|█████████▉| 61563/61904 [8:13:21<07:46,  1.37s/it]
 99%|█████████▉| 61564/61904 [8:13:22<07:48,  1.38s/it]
 99%|█████████▉| 61565/61904 [8:13:24<07:55,  1.40s/it]
 99%|█████████▉| 61566/61904 [8:13:25<07:52,  1.40s/it]
 99%|█████████▉| 61567/61904 [8:13:26<07:42,  1.37s/it]
 99%|█████████▉| 61568/61904 [8:13:28<07:30,  1.34s/it]
 99%|█████████▉| 61569/61904 [8:13:29<07:41,  1.38s/it]
 99%|█████████▉| 61570/61904 [8:13:30<07:42,  1.39s/it]
 99%|█████████▉| 61571/61904 [8:13:32<07:27,  1.35s/it]
 99%|█████████▉| 61572/61904 [8:13:33<07:20,  1.33s/it]
 99%|█████████▉| 61573/61904 [8:13:35<07:38,  1.39s/it]
 99%|█████████▉| 61574/61904 [8:13:36<07:37,  1.39s/it]
 99%|█████████▉| 61575/61904 [8:13:37<07:37,  1.39s/it]
 99%|█████████▉| 61576/61904 [8:13:39<07:32,  1.38s/it]
 99%|█████████▉| 61577/61904 [8:13:40<07:36,  1.40s/it]
 99%|█████████▉| 61578/61904 [8:13:42<07:46,  1.43s/it]
 99%|█████████▉| 61579/61904 [8:13:43<07:34,  1.40s/it]
 99%|█████████▉| 61580/61904 [8:13:44<07:28,  1.38s/it]
                                                       
{'loss': 2.4445, 'learning_rate': 1.0052508751458574e-07, 'epoch': 15.92}

 99%|█████████▉| 61580/61904 [8:13:44<07:28,  1.38s/it]
 99%|█████████▉| 61581/61904 [8:13:46<07:19,  1.36s/it]
 99%|█████████▉| 61582/61904 [8:13:47<07:29,  1.40s/it]
 99%|█████████▉| 61583/61904 [8:13:48<07:27,  1.39s/it]
 99%|█████████▉| 61584/61904 [8:13:50<07:33,  1.42s/it]
 99%|█████████▉| 61585/61904 [8:13:51<07:33,  1.42s/it]
 99%|█████████▉| 61586/61904 [8:13:53<07:14,  1.37s/it]
 99%|█████████▉| 61587/61904 [8:13:54<07:16,  1.38s/it]
 99%|█████████▉| 61588/61904 [8:13:55<07:14,  1.37s/it]
 99%|█████████▉| 61589/61904 [8:13:57<07:11,  1.37s/it]
 99%|█████████▉| 61590/61904 [8:13:58<07:20,  1.40s/it]
 99%|█████████▉| 61591/61904 [8:14:00<07:17,  1.40s/it]
 99%|█████████▉| 61592/61904 [8:14:01<07:11,  1.38s/it]
 99%|█████████▉| 61593/61904 [8:14:02<07:05,  1.37s/it]
 99%|█████████▉| 61594/61904 [8:14:04<07:00,  1.36s/it]
100%|█████████▉| 61595/61904 [8:14:05<06:54,  1.34s/it]
100%|█████████▉| 61596/61904 [8:14:06<07:08,  1.39s/it]
100%|█████████▉| 61597/61904 [8:14:08<07:02,  1.37s/it]
100%|█████████▉| 61598/61904 [8:14:09<07:21,  1.44s/it]
100%|█████████▉| 61599/61904 [8:14:11<07:08,  1.41s/it]
100%|█████████▉| 61600/61904 [8:14:12<07:16,  1.44s/it]
                                                       
{'loss': 2.4324, 'learning_rate': 1.0049267470504342e-07, 'epoch': 15.92}

100%|█████████▉| 61600/61904 [8:14:12<07:16,  1.44s/it]
100%|█████████▉| 61601/61904 [8:14:14<07:08,  1.41s/it]
100%|█████████▉| 61602/61904 [8:14:15<07:01,  1.40s/it]
100%|█████████▉| 61603/61904 [8:14:16<06:54,  1.38s/it]
100%|█████████▉| 61604/61904 [8:14:18<06:45,  1.35s/it]
100%|█████████▉| 61605/61904 [8:14:19<06:41,  1.34s/it]
100%|█████████▉| 61606/61904 [8:14:20<06:54,  1.39s/it]
100%|█████████▉| 61607/61904 [8:14:22<06:49,  1.38s/it]
100%|█████████▉| 61608/61904 [8:14:23<06:39,  1.35s/it]
100%|█████████▉| 61609/61904 [8:14:24<06:50,  1.39s/it]
100%|█████████▉| 61610/61904 [8:14:26<06:46,  1.38s/it]
100%|█████████▉| 61611/61904 [8:14:27<06:44,  1.38s/it]
100%|█████████▉| 61612/61904 [8:14:29<06:44,  1.38s/it]
100%|█████████▉| 61613/61904 [8:14:30<06:37,  1.37s/it]
100%|█████████▉| 61614/61904 [8:14:31<06:38,  1.37s/it]
100%|█████████▉| 61615/61904 [8:14:33<06:36,  1.37s/it]
100%|█████████▉| 61616/61904 [8:14:34<06:27,  1.34s/it]
100%|█████████▉| 61617/61904 [8:14:35<06:25,  1.34s/it]
100%|█████████▉| 61618/61904 [8:14:37<06:47,  1.42s/it]
100%|█████████▉| 61619/61904 [8:14:38<06:39,  1.40s/it]
100%|█████████▉| 61620/61904 [8:14:40<06:36,  1.40s/it]
                                                       
{'loss': 2.3891, 'learning_rate': 1.004602618955011e-07, 'epoch': 15.93}

100%|█████████▉| 61620/61904 [8:14:40<06:36,  1.40s/it]
100%|█████████▉| 61621/61904 [8:14:41<06:40,  1.41s/it]
100%|█████████▉| 61622/61904 [8:14:42<06:34,  1.40s/it]
100%|█████████▉| 61623/61904 [8:14:44<06:36,  1.41s/it]
100%|█████████▉| 61624/61904 [8:14:45<06:33,  1.41s/it]
100%|█████████▉| 61625/61904 [8:14:46<06:12,  1.33s/it]
100%|█████████▉| 61626/61904 [8:14:48<06:22,  1.38s/it]
100%|█████████▉| 61627/61904 [8:14:49<06:21,  1.38s/it]
100%|█████████▉| 61628/61904 [8:14:51<06:21,  1.38s/it]
100%|█████████▉| 61629/61904 [8:14:52<06:27,  1.41s/it]
100%|█████████▉| 61630/61904 [8:14:54<06:23,  1.40s/it]
100%|█████████▉| 61631/61904 [8:14:55<06:23,  1.41s/it]
100%|█████████▉| 61632/61904 [8:14:57<06:32,  1.44s/it]
100%|█████████▉| 61633/61904 [8:14:58<06:27,  1.43s/it]
100%|█████████▉| 61634/61904 [8:14:59<06:24,  1.42s/it]
100%|█████████▉| 61635/61904 [8:15:01<06:13,  1.39s/it]
100%|█████████▉| 61636/61904 [8:15:02<06:06,  1.37s/it]
100%|█████████▉| 61637/61904 [8:15:03<06:07,  1.38s/it]
100%|█████████▉| 61638/61904 [8:15:05<06:08,  1.39s/it]
100%|█████████▉| 61639/61904 [8:15:06<06:09,  1.40s/it]
100%|█████████▉| 61640/61904 [8:15:07<06:00,  1.37s/it]
                                                       
{'loss': 2.4304, 'learning_rate': 1.0042784908595876e-07, 'epoch': 15.93}

100%|█████████▉| 61640/61904 [8:15:07<06:00,  1.37s/it]
100%|█████████▉| 61641/61904 [8:15:09<06:09,  1.41s/it]
100%|█████████▉| 61642/61904 [8:15:10<06:10,  1.41s/it]
100%|█████████▉| 61643/61904 [8:15:12<06:02,  1.39s/it]
100%|█████████▉| 61644/61904 [8:15:13<06:00,  1.39s/it]
100%|█████████▉| 61645/61904 [8:15:14<05:50,  1.35s/it]
100%|█████████▉| 61646/61904 [8:15:16<05:50,  1.36s/it]
100%|█████████▉| 61647/61904 [8:15:17<05:49,  1.36s/it]
100%|█████████▉| 61648/61904 [8:15:19<05:54,  1.38s/it]
100%|█████████▉| 61649/61904 [8:15:20<05:42,  1.34s/it]
100%|█████████▉| 61650/61904 [8:15:21<05:54,  1.40s/it]
100%|█████████▉| 61651/61904 [8:15:23<05:58,  1.42s/it]
100%|█████████▉| 61652/61904 [8:15:24<05:45,  1.37s/it]
100%|█████████▉| 61653/61904 [8:15:25<05:39,  1.35s/it]
100%|█████████▉| 61654/61904 [8:15:27<05:47,  1.39s/it]
100%|█████████▉| 61655/61904 [8:15:28<05:46,  1.39s/it]
100%|█████████▉| 61656/61904 [8:15:30<05:40,  1.37s/it]
100%|█████████▉| 61657/61904 [8:15:31<05:38,  1.37s/it]
100%|█████████▉| 61658/61904 [8:15:32<05:45,  1.40s/it]
100%|█████████▉| 61659/61904 [8:15:34<05:55,  1.45s/it]
100%|█████████▉| 61660/61904 [8:15:35<05:48,  1.43s/it]
                                                       
{'loss': 2.4452, 'learning_rate': 1.0039543627641642e-07, 'epoch': 15.94}

100%|█████████▉| 61660/61904 [8:15:35<05:48,  1.43s/it]
100%|█████████▉| 61661/61904 [8:15:37<05:41,  1.40s/it]
100%|█████████▉| 61662/61904 [8:15:38<05:40,  1.41s/it]
100%|█████████▉| 61663/61904 [8:15:39<05:33,  1.38s/it]
100%|█████████▉| 61664/61904 [8:15:41<05:25,  1.36s/it]
100%|█████████▉| 61665/61904 [8:15:42<05:35,  1.40s/it]
100%|█████████▉| 61666/61904 [8:15:44<05:23,  1.36s/it]
100%|█████████▉| 61667/61904 [8:15:45<05:26,  1.38s/it]
100%|█████████▉| 61668/61904 [8:15:46<05:23,  1.37s/it]
100%|█████████▉| 61669/61904 [8:15:48<05:40,  1.45s/it]
100%|█████████▉| 61670/61904 [8:15:49<05:37,  1.44s/it]
100%|█████████▉| 61671/61904 [8:15:51<05:28,  1.41s/it]
100%|█████████▉| 61672/61904 [8:15:52<05:18,  1.37s/it]
100%|█████████▉| 61673/61904 [8:15:53<05:14,  1.36s/it]
100%|█████████▉| 61674/61904 [8:15:55<05:15,  1.37s/it]
100%|█████████▉| 61675/61904 [8:15:56<05:14,  1.37s/it]
100%|█████████▉| 61676/61904 [8:15:58<05:25,  1.43s/it]
100%|█████████▉| 61677/61904 [8:15:59<05:21,  1.42s/it]
100%|█████████▉| 61678/61904 [8:16:00<05:15,  1.40s/it]
100%|█████████▉| 61679/61904 [8:16:02<05:10,  1.38s/it]
100%|█████████▉| 61680/61904 [8:16:03<05:08,  1.38s/it]
                                                       
{'loss': 2.4355, 'learning_rate': 1.003630234668741e-07, 'epoch': 15.94}

100%|█████████▉| 61680/61904 [8:16:03<05:08,  1.38s/it]
100%|█████████▉| 61681/61904 [8:16:04<05:00,  1.35s/it]
100%|█████████▉| 61682/61904 [8:16:06<05:14,  1.42s/it]
100%|█████████▉| 61683/61904 [8:16:07<05:14,  1.42s/it]
100%|█████████▉| 61684/61904 [8:16:09<05:13,  1.42s/it]
100%|█████████▉| 61685/61904 [8:16:10<05:05,  1.39s/it]
100%|█████████▉| 61686/61904 [8:16:12<05:07,  1.41s/it]
100%|█████████▉| 61687/61904 [8:16:13<05:10,  1.43s/it]
100%|█████████▉| 61688/61904 [8:16:14<05:05,  1.41s/it]
100%|█████████▉| 61689/61904 [8:16:16<04:51,  1.35s/it]
100%|█████████▉| 61690/61904 [8:16:17<04:56,  1.39s/it]
100%|█████████▉| 61691/61904 [8:16:19<05:03,  1.43s/it]
100%|█████████▉| 61692/61904 [8:16:20<04:52,  1.38s/it]
100%|█████████▉| 61693/61904 [8:16:21<04:52,  1.38s/it]
100%|█████████▉| 61694/61904 [8:16:23<04:55,  1.41s/it]
100%|█████████▉| 61695/61904 [8:16:24<04:55,  1.41s/it]
100%|█████████▉| 61696/61904 [8:16:26<04:49,  1.39s/it]
100%|█████████▉| 61697/61904 [8:16:27<04:47,  1.39s/it]
100%|█████████▉| 61698/61904 [8:16:28<04:50,  1.41s/it]
100%|█████████▉| 61699/61904 [8:16:30<04:50,  1.42s/it]
100%|█████████▉| 61700/61904 [8:16:31<04:55,  1.45s/it]
                                                       
{'loss': 2.3643, 'learning_rate': 1.0033061065733177e-07, 'epoch': 15.95}

100%|█████████▉| 61700/61904 [8:16:31<04:55,  1.45s/it]
100%|█████████▉| 61701/61904 [8:16:33<04:53,  1.45s/it]
100%|█████████▉| 61702/61904 [8:16:34<04:39,  1.38s/it]
100%|█████████▉| 61703/61904 [8:16:35<04:37,  1.38s/it]
100%|█████████▉| 61704/61904 [8:16:37<04:31,  1.36s/it]
100%|█████████▉| 61705/61904 [8:16:38<04:34,  1.38s/it]
100%|█████████▉| 61706/61904 [8:16:39<04:32,  1.38s/it]
100%|█████████▉| 61707/61904 [8:16:41<04:28,  1.36s/it]
100%|█████████▉| 61708/61904 [8:16:42<04:26,  1.36s/it]
100%|█████████▉| 61709/61904 [8:16:44<04:27,  1.37s/it]
100%|█████████▉| 61710/61904 [8:16:45<04:27,  1.38s/it]
100%|█████████▉| 61711/61904 [8:16:46<04:23,  1.37s/it]
100%|█████████▉| 61712/61904 [8:16:48<04:17,  1.34s/it]
100%|█████████▉| 61713/61904 [8:16:49<04:14,  1.33s/it]
100%|█████████▉| 61714/61904 [8:16:50<04:11,  1.32s/it]
100%|█████████▉| 61715/61904 [8:16:52<04:14,  1.35s/it]
100%|█████████▉| 61716/61904 [8:16:53<04:18,  1.37s/it]
100%|█████████▉| 61717/61904 [8:16:55<04:24,  1.41s/it]
100%|█████████▉| 61718/61904 [8:16:56<04:23,  1.42s/it]
100%|█████████▉| 61719/61904 [8:16:57<04:17,  1.39s/it]
100%|█████████▉| 61720/61904 [8:16:59<04:19,  1.41s/it]
                                                       
{'loss': 2.3778, 'learning_rate': 1.0029819784778943e-07, 'epoch': 15.95}

100%|█████████▉| 61720/61904 [8:16:59<04:19,  1.41s/it]
100%|█████████▉| 61721/61904 [8:17:00<04:21,  1.43s/it]
100%|█████████▉| 61722/61904 [8:17:02<04:15,  1.40s/it]
100%|█████████▉| 61723/61904 [8:17:03<04:08,  1.37s/it]
100%|█████████▉| 61724/61904 [8:17:04<04:13,  1.41s/it]
100%|█████████▉| 61725/61904 [8:17:06<04:06,  1.38s/it]
100%|█████████▉| 61726/61904 [8:17:07<04:03,  1.37s/it]
100%|█████████▉| 61727/61904 [8:17:08<04:07,  1.40s/it]
100%|█████████▉| 61728/61904 [8:17:10<04:06,  1.40s/it]
100%|█████████▉| 61729/61904 [8:17:11<04:03,  1.39s/it]
100%|█████████▉| 61730/61904 [8:17:13<04:08,  1.43s/it]
100%|█████████▉| 61731/61904 [8:17:14<04:05,  1.42s/it]
100%|█████████▉| 61732/61904 [8:17:16<04:08,  1.44s/it]
100%|█████████▉| 61733/61904 [8:17:17<04:04,  1.43s/it]
100%|█████████▉| 61734/61904 [8:17:18<03:56,  1.39s/it]
100%|█████████▉| 61735/61904 [8:17:20<03:53,  1.38s/it]
100%|█████████▉| 61736/61904 [8:17:21<03:52,  1.39s/it]
100%|█████████▉| 61737/61904 [8:17:23<04:03,  1.46s/it]
100%|█████████▉| 61738/61904 [8:17:24<03:58,  1.44s/it]
100%|█████████▉| 61739/61904 [8:17:26<03:55,  1.42s/it]
100%|█████████▉| 61740/61904 [8:17:27<03:55,  1.44s/it]
                                                       
{'loss': 2.4225, 'learning_rate': 1.0026578503824709e-07, 'epoch': 15.96}

100%|█████████▉| 61740/61904 [8:17:27<03:55,  1.44s/it]
100%|█████████▉| 61741/61904 [8:17:28<03:48,  1.40s/it]
100%|█████████▉| 61742/61904 [8:17:30<03:50,  1.42s/it]
100%|█████████▉| 61743/61904 [8:17:31<03:46,  1.40s/it]
100%|█████████▉| 61744/61904 [8:17:33<03:48,  1.43s/it]
100%|█████████▉| 61745/61904 [8:17:34<04:02,  1.52s/it]
100%|█████████▉| 61746/61904 [8:17:36<04:01,  1.53s/it]
100%|█████████▉| 61747/61904 [8:17:37<03:55,  1.50s/it]
100%|█████████▉| 61748/61904 [8:17:39<03:44,  1.44s/it]
100%|█████████▉| 61749/61904 [8:17:40<03:35,  1.39s/it]
100%|█████████▉| 61750/61904 [8:17:41<03:33,  1.39s/it]
100%|█████████▉| 61751/61904 [8:17:43<03:32,  1.39s/it]
100%|█████████▉| 61752/61904 [8:17:44<03:31,  1.39s/it]
100%|█████████▉| 61753/61904 [8:17:45<03:26,  1.37s/it]
100%|█████████▉| 61754/61904 [8:17:47<03:24,  1.36s/it]
100%|█████████▉| 61755/61904 [8:17:48<03:26,  1.39s/it]
100%|█████████▉| 61756/61904 [8:17:50<03:22,  1.37s/it]
100%|█████████▉| 61757/61904 [8:17:51<03:21,  1.37s/it]
100%|█████████▉| 61758/61904 [8:17:52<03:27,  1.42s/it]
100%|█████████▉| 61759/61904 [8:17:54<03:21,  1.39s/it]
100%|█████████▉| 61760/61904 [8:17:55<03:19,  1.38s/it]
                                                       
{'loss': 2.374, 'learning_rate': 1.0023337222870478e-07, 'epoch': 15.96}

100%|█████████▉| 61760/61904 [8:17:55<03:19,  1.38s/it]
100%|█████████▉| 61761/61904 [8:17:56<03:14,  1.36s/it]
100%|█████████▉| 61762/61904 [8:17:58<03:17,  1.39s/it]
100%|█████████▉| 61763/61904 [8:17:59<03:20,  1.42s/it]
100%|█████████▉| 61764/61904 [8:18:01<03:13,  1.38s/it]
100%|█████████▉| 61765/61904 [8:18:02<03:08,  1.36s/it]
100%|█████████▉| 61766/61904 [8:18:03<03:11,  1.39s/it]
100%|█████████▉| 61767/61904 [8:18:05<03:03,  1.34s/it]
100%|█████████▉| 61768/61904 [8:18:06<03:03,  1.35s/it]
100%|█████████▉| 61769/61904 [8:18:07<03:03,  1.36s/it]
100%|█████████▉| 61770/61904 [8:18:09<03:02,  1.36s/it]
100%|█████████▉| 61771/61904 [8:18:10<02:57,  1.34s/it]
100%|█████████▉| 61772/61904 [8:18:12<03:01,  1.37s/it]
100%|█████████▉| 61773/61904 [8:18:13<02:58,  1.36s/it]
100%|█████████▉| 61774/61904 [8:18:14<02:56,  1.36s/it]
100%|█████████▉| 61775/61904 [8:18:16<02:55,  1.36s/it]
100%|█████████▉| 61776/61904 [8:18:17<02:56,  1.38s/it]
100%|█████████▉| 61777/61904 [8:18:19<03:00,  1.42s/it]
100%|█████████▉| 61778/61904 [8:18:20<02:57,  1.41s/it]
100%|█████████▉| 61779/61904 [8:18:21<02:54,  1.40s/it]
100%|█████████▉| 61780/61904 [8:18:23<02:46,  1.34s/it]
                                                       
{'loss': 2.4335, 'learning_rate': 1.0020095941916244e-07, 'epoch': 15.97}

100%|█████████▉| 61780/61904 [8:18:23<02:46,  1.34s/it]
100%|█████████▉| 61781/61904 [8:18:24<02:52,  1.40s/it]
100%|█████████▉| 61782/61904 [8:18:25<02:51,  1.41s/it]
100%|█████████▉| 61783/61904 [8:18:27<02:47,  1.38s/it]
100%|█████████▉| 61784/61904 [8:18:28<02:43,  1.36s/it]
100%|█████████▉| 61785/61904 [8:18:30<02:45,  1.39s/it]
100%|█████████▉| 61786/61904 [8:18:31<02:41,  1.37s/it]
100%|█████████▉| 61787/61904 [8:18:32<02:39,  1.36s/it]
100%|█████████▉| 61788/61904 [8:18:34<02:38,  1.37s/it]
100%|█████████▉| 61789/61904 [8:18:35<02:35,  1.35s/it]
100%|█████████▉| 61790/61904 [8:18:36<02:33,  1.34s/it]
100%|█████████▉| 61791/61904 [8:18:38<02:32,  1.35s/it]
100%|█████████▉| 61792/61904 [8:18:39<02:30,  1.35s/it]
100%|█████████▉| 61793/61904 [8:18:40<02:30,  1.35s/it]
100%|█████████▉| 61794/61904 [8:18:42<02:36,  1.42s/it]
100%|█████████▉| 61795/61904 [8:18:43<02:38,  1.46s/it]
100%|█████████▉| 61796/61904 [8:18:45<02:38,  1.46s/it]
100%|█████████▉| 61797/61904 [8:18:46<02:34,  1.45s/it]
100%|█████████▉| 61798/61904 [8:18:48<02:31,  1.43s/it]
100%|█████████▉| 61799/61904 [8:18:49<02:24,  1.37s/it]
100%|█████████▉| 61800/61904 [8:18:50<02:18,  1.33s/it]
                                                       
{'loss': 2.4207, 'learning_rate': 1.001685466096201e-07, 'epoch': 15.97}

100%|█████████▉| 61800/61904 [8:18:50<02:18,  1.33s/it]
100%|█████████▉| 61801/61904 [8:18:52<02:28,  1.45s/it]
100%|█████████▉| 61802/61904 [8:18:53<02:28,  1.45s/it]
100%|█████████▉| 61803/61904 [8:18:55<02:31,  1.50s/it]
100%|█████████▉| 61804/61904 [8:18:56<02:23,  1.44s/it]
100%|█████████▉| 61805/61904 [8:18:58<02:24,  1.46s/it]
100%|█████████▉| 61806/61904 [8:18:59<02:18,  1.42s/it]
100%|█████████▉| 61807/61904 [8:19:00<02:16,  1.41s/it]
100%|█████████▉| 61808/61904 [8:19:02<02:16,  1.42s/it]
100%|█████████▉| 61809/61904 [8:19:03<02:19,  1.47s/it]
100%|█████████▉| 61810/61904 [8:19:05<02:14,  1.43s/it]
100%|█████████▉| 61811/61904 [8:19:06<02:09,  1.39s/it]
100%|█████████▉| 61812/61904 [8:19:07<02:06,  1.37s/it]
100%|█████████▉| 61813/61904 [8:19:09<02:02,  1.35s/it]
100%|█████████▉| 61814/61904 [8:19:10<02:01,  1.35s/it]
100%|█████████▉| 61815/61904 [8:19:11<01:57,  1.32s/it]
100%|█████████▉| 61816/61904 [8:19:13<02:00,  1.36s/it]
100%|█████████▉| 61817/61904 [8:19:14<02:01,  1.40s/it]
100%|█████████▉| 61818/61904 [8:19:16<01:57,  1.37s/it]
100%|█████████▉| 61819/61904 [8:19:17<01:54,  1.34s/it]
100%|█████████▉| 61820/61904 [8:19:18<01:57,  1.39s/it]
                                                       
{'loss': 2.3516, 'learning_rate': 1.0013613380007777e-07, 'epoch': 15.98}

100%|█████████▉| 61820/61904 [8:19:18<01:57,  1.39s/it]
100%|█████████▉| 61821/61904 [8:19:20<01:57,  1.42s/it]
100%|█████████▉| 61822/61904 [8:19:21<01:54,  1.39s/it]
100%|█████████▉| 61823/61904 [8:19:23<01:55,  1.43s/it]
100%|█████████▉| 61824/61904 [8:19:24<01:52,  1.40s/it]
100%|█████████▉| 61825/61904 [8:19:26<01:52,  1.42s/it]
100%|█████████▉| 61826/61904 [8:19:27<01:50,  1.41s/it]
100%|█████████▉| 61827/61904 [8:19:28<01:49,  1.42s/it]
100%|█████████▉| 61828/61904 [8:19:30<01:46,  1.40s/it]
100%|█████████▉| 61829/61904 [8:19:31<01:45,  1.40s/it]
100%|█████████▉| 61830/61904 [8:19:33<01:43,  1.40s/it]
100%|█████████▉| 61831/61904 [8:19:34<01:42,  1.41s/it]
100%|█████████▉| 61832/61904 [8:19:35<01:41,  1.41s/it]
100%|█████████▉| 61833/61904 [8:19:37<01:40,  1.41s/it]
100%|█████████▉| 61834/61904 [8:19:38<01:34,  1.36s/it]
100%|█████████▉| 61835/61904 [8:19:39<01:32,  1.34s/it]
100%|█████████▉| 61836/61904 [8:19:41<01:33,  1.38s/it]
100%|█████████▉| 61837/61904 [8:19:42<01:31,  1.37s/it]
100%|█████████▉| 61838/61904 [8:19:43<01:30,  1.37s/it]
100%|█████████▉| 61839/61904 [8:19:45<01:26,  1.34s/it]
100%|█████████▉| 61840/61904 [8:19:46<01:29,  1.40s/it]
                                                       
{'loss': 2.4139, 'learning_rate': 1.0010372099053545e-07, 'epoch': 15.98}

100%|█████████▉| 61840/61904 [8:19:46<01:29,  1.40s/it]
100%|█████████▉| 61841/61904 [8:19:48<01:25,  1.36s/it]
100%|█████████▉| 61842/61904 [8:19:49<01:28,  1.43s/it]
100%|█████████▉| 61843/61904 [8:19:51<01:26,  1.42s/it]
100%|█████████▉| 61844/61904 [8:19:52<01:25,  1.43s/it]
100%|█████████▉| 61845/61904 [8:19:53<01:22,  1.40s/it]
100%|█████████▉| 61846/61904 [8:19:55<01:21,  1.40s/it]
100%|█████████▉| 61847/61904 [8:19:56<01:18,  1.38s/it]
100%|█████████▉| 61848/61904 [8:19:58<01:18,  1.39s/it]
100%|█████████▉| 61849/61904 [8:19:59<01:14,  1.35s/it]
100%|█████████▉| 61850/61904 [8:20:00<01:15,  1.39s/it]
100%|█████████▉| 61851/61904 [8:20:02<01:15,  1.42s/it]
100%|█████████▉| 61852/61904 [8:20:03<01:12,  1.39s/it]
100%|█████████▉| 61853/61904 [8:20:04<01:10,  1.37s/it]
100%|█████████▉| 61854/61904 [8:20:06<01:13,  1.47s/it]
100%|█████████▉| 61855/61904 [8:20:07<01:09,  1.41s/it]
100%|█████████▉| 61856/61904 [8:20:09<01:07,  1.40s/it]
100%|█████████▉| 61857/61904 [8:20:10<01:04,  1.38s/it]
100%|█████████▉| 61858/61904 [8:20:11<01:02,  1.35s/it]
100%|█████████▉| 61859/61904 [8:20:13<00:59,  1.33s/it]
100%|█████████▉| 61860/61904 [8:20:14<01:01,  1.40s/it]
                                                       
{'loss': 2.4381, 'learning_rate': 1.0007130818099312e-07, 'epoch': 15.99}

100%|█████████▉| 61860/61904 [8:20:14<01:01,  1.40s/it]
100%|█████████▉| 61861/61904 [8:20:15<00:58,  1.35s/it]
100%|█████████▉| 61862/61904 [8:20:17<00:56,  1.35s/it]
100%|█████████▉| 61863/61904 [8:20:18<00:56,  1.37s/it]
100%|█████████▉| 61864/61904 [8:20:20<00:54,  1.37s/it]
100%|█████████▉| 61865/61904 [8:20:21<00:54,  1.39s/it]
100%|█████████▉| 61866/61904 [8:20:22<00:53,  1.40s/it]
100%|█████████▉| 61867/61904 [8:20:24<00:52,  1.42s/it]
100%|█████████▉| 61868/61904 [8:20:25<00:50,  1.41s/it]
100%|█████████▉| 61869/61904 [8:20:27<00:48,  1.38s/it]
100%|█████████▉| 61870/61904 [8:20:28<00:46,  1.38s/it]
100%|█████████▉| 61871/61904 [8:20:29<00:44,  1.35s/it]
100%|█████████▉| 61872/61904 [8:20:31<00:44,  1.39s/it]
100%|█████████▉| 61873/61904 [8:20:32<00:43,  1.39s/it]
100%|█████████▉| 61874/61904 [8:20:33<00:41,  1.37s/it]
100%|█████████▉| 61875/61904 [8:20:35<00:40,  1.40s/it]
100%|█████████▉| 61876/61904 [8:20:36<00:38,  1.38s/it]
100%|█████████▉| 61877/61904 [8:20:38<00:37,  1.40s/it]
100%|█████████▉| 61878/61904 [8:20:39<00:36,  1.42s/it]
100%|█████████▉| 61879/61904 [8:20:41<00:35,  1.42s/it]
100%|█████████▉| 61880/61904 [8:20:42<00:33,  1.38s/it]
                                                       
{'loss': 2.4053, 'learning_rate': 1.0003889537145078e-07, 'epoch': 15.99}

100%|█████████▉| 61880/61904 [8:20:42<00:33,  1.38s/it]
100%|█████████▉| 61881/61904 [8:20:43<00:32,  1.41s/it]
100%|█████████▉| 61882/61904 [8:20:45<00:30,  1.40s/it]
100%|█████████▉| 61883/61904 [8:20:46<00:28,  1.37s/it]
100%|█████████▉| 61884/61904 [8:20:47<00:26,  1.35s/it]
100%|█████████▉| 61885/61904 [8:20:49<00:25,  1.33s/it]
100%|█████████▉| 61886/61904 [8:20:50<00:24,  1.35s/it]
100%|█████████▉| 61887/61904 [8:20:51<00:22,  1.32s/it]
100%|█████████▉| 61888/61904 [8:20:53<00:22,  1.40s/it]
100%|█████████▉| 61889/61904 [8:20:54<00:21,  1.41s/it]
100%|█████████▉| 61890/61904 [8:20:56<00:19,  1.42s/it]
100%|█████████▉| 61891/61904 [8:20:57<00:18,  1.43s/it]
100%|█████████▉| 61892/61904 [8:20:59<00:17,  1.44s/it]
100%|█████████▉| 61893/61904 [8:21:00<00:15,  1.44s/it]
100%|█████████▉| 61894/61904 [8:21:01<00:14,  1.42s/it]
100%|█████████▉| 61895/61904 [8:21:03<00:12,  1.44s/it]
100%|█████████▉| 61896/61904 [8:21:04<00:11,  1.43s/it]
100%|█████████▉| 61897/61904 [8:21:06<00:10,  1.49s/it]
100%|█████████▉| 61898/61904 [8:21:07<00:08,  1.44s/it]
100%|█████████▉| 61899/61904 [8:21:09<00:07,  1.44s/it]
100%|█████████▉| 61900/61904 [8:21:10<00:05,  1.40s/it]
                                                       
{'loss': 2.439, 'learning_rate': 1.0000648256190844e-07, 'epoch': 16.0}

100%|█████████▉| 61900/61904 [8:21:10<00:05,  1.40s/it]
100%|█████████▉| 61901/61904 [8:21:11<00:04,  1.41s/it]
100%|█████████▉| 61902/61904 [8:21:13<00:02,  1.40s/it]
100%|█████████▉| 61903/61904 [8:21:14<00:01,  1.36s/it]
100%|██████████| 61904/61904 [8:21:15<00:00,  1.35s/it][WARNING|configuration_utils.py:448] 2024-10-28 23:46:55,902 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}
/opt/conda/lib/python3.10/multiprocessing/popen_fork.py:66: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.
  self.pid = os.fork()


  0%|          | 0/861 [00:00<?, ?it/s]

  0%|          | 2/861 [00:01<10:09,  1.41it/s]

  0%|          | 3/861 [00:03<18:10,  1.27s/it]

  0%|          | 4/861 [00:04<15:54,  1.11s/it]

  1%|          | 5/861 [00:05<15:28,  1.09s/it]

  1%|          | 6/861 [00:06<15:18,  1.07s/it]

  1%|          | 7/861 [00:06<12:27,  1.14it/s]

  1%|          | 8/861 [00:07<12:11,  1.17it/s]

  1%|          | 9/861 [00:08<11:29,  1.24it/s]

  1%|          | 10/861 [00:09<10:43,  1.32it/s]

  1%|▏         | 11/861 [00:10<14:54,  1.05s/it]

  1%|▏         | 12/861 [00:11<15:11,  1.07s/it]

  2%|▏         | 13/861 [00:12<14:21,  1.02s/it]

  2%|▏         | 14/861 [00:13<11:28,  1.23it/s]

  2%|▏         | 15/861 [00:13<11:24,  1.24it/s]

  2%|▏         | 16/861 [00:14<09:33,  1.47it/s]

  2%|▏         | 17/861 [00:15<12:25,  1.13it/s]

  2%|▏         | 18/861 [00:15<10:04,  1.39it/s]

  2%|▏         | 19/861 [00:18<16:36,  1.18s/it]

  2%|▏         | 20/861 [00:19<15:37,  1.11s/it]

  2%|▏         | 21/861 [00:20<16:28,  1.18s/it]

  3%|▎         | 22/861 [00:22<19:12,  1.37s/it]

  3%|▎         | 23/861 [00:22<14:57,  1.07s/it]

  3%|▎         | 24/861 [00:24<17:34,  1.26s/it]

  3%|▎         | 25/861 [00:25<16:59,  1.22s/it]

  3%|▎         | 26/861 [00:26<16:39,  1.20s/it]

  3%|▎         | 27/861 [00:28<17:43,  1.28s/it]

  3%|▎         | 28/861 [00:31<25:57,  1.87s/it]

  3%|▎         | 29/861 [00:31<19:28,  1.40s/it]

  3%|▎         | 30/861 [00:33<19:22,  1.40s/it]

  4%|▎         | 31/861 [00:33<16:15,  1.18s/it]

  4%|▎         | 32/861 [00:34<13:11,  1.05it/s]

  4%|▍         | 33/861 [00:35<13:45,  1.00it/s]

  4%|▍         | 34/861 [00:36<13:47,  1.00s/it]

  4%|▍         | 35/861 [00:38<17:21,  1.26s/it]

  4%|▍         | 36/861 [00:39<16:03,  1.17s/it]

  4%|▍         | 37/861 [00:40<15:22,  1.12s/it]

  4%|▍         | 38/861 [00:41<16:45,  1.22s/it]

  5%|▍         | 39/861 [00:42<14:16,  1.04s/it]

  5%|▍         | 40/861 [00:42<12:43,  1.08it/s]

  5%|▍         | 41/861 [00:43<10:47,  1.27it/s]

  5%|▍         | 42/861 [00:44<12:51,  1.06it/s]

  5%|▍         | 43/861 [00:45<13:06,  1.04it/s]

  5%|▌         | 44/861 [00:46<11:56,  1.14it/s]

  5%|▌         | 45/861 [00:47<12:04,  1.13it/s]

  5%|▌         | 46/861 [00:49<17:42,  1.30s/it]

  5%|▌         | 47/861 [00:50<17:42,  1.31s/it]

  6%|▌         | 48/861 [00:52<20:29,  1.51s/it]

  6%|▌         | 49/861 [00:54<19:24,  1.43s/it]

  6%|▌         | 50/861 [00:54<14:23,  1.06s/it]

  6%|▌         | 51/861 [00:55<14:28,  1.07s/it]

  6%|▌         | 52/861 [00:56<13:27,  1.00it/s]

  6%|▌         | 53/861 [00:56<12:32,  1.07it/s]

  6%|▋         | 54/861 [00:57<09:46,  1.37it/s]

  6%|▋         | 55/861 [00:57<08:45,  1.53it/s]

  7%|▋         | 56/861 [00:58<09:22,  1.43it/s]

  7%|▋         | 57/861 [00:58<07:52,  1.70it/s]

  7%|▋         | 58/861 [00:59<06:43,  1.99it/s]

  7%|▋         | 59/861 [00:59<07:10,  1.86it/s]

  7%|▋         | 60/861 [01:00<07:41,  1.74it/s]

  7%|▋         | 61/861 [01:00<07:04,  1.88it/s]

  7%|▋         | 62/861 [01:01<06:07,  2.17it/s]

  7%|▋         | 63/861 [01:01<06:35,  2.02it/s]

  7%|▋         | 64/861 [01:02<07:05,  1.88it/s]

  8%|▊         | 65/861 [01:02<07:27,  1.78it/s]

  8%|▊         | 66/861 [01:03<07:17,  1.82it/s]

  8%|▊         | 67/861 [01:04<08:22,  1.58it/s]

  8%|▊         | 68/861 [01:05<11:28,  1.15it/s]

  8%|▊         | 69/861 [01:07<13:17,  1.01s/it]

  8%|▊         | 70/861 [01:08<15:01,  1.14s/it]

  8%|▊         | 71/861 [01:09<15:33,  1.18s/it]

  8%|▊         | 72/861 [01:10<14:48,  1.13s/it]

  8%|▊         | 73/861 [01:11<11:33,  1.14it/s]

  9%|▊         | 74/861 [01:11<10:33,  1.24it/s]

  9%|▊         | 75/861 [01:12<12:25,  1.06it/s]

  9%|▉         | 76/861 [01:13<10:39,  1.23it/s]

  9%|▉         | 77/861 [01:14<11:07,  1.17it/s]

  9%|▉         | 78/861 [01:15<11:17,  1.15it/s]

  9%|▉         | 79/861 [01:16<12:19,  1.06it/s]

  9%|▉         | 80/861 [01:17<10:53,  1.20it/s]

  9%|▉         | 81/861 [01:18<11:57,  1.09it/s]

 10%|▉         | 82/861 [01:18<10:20,  1.25it/s]

 10%|▉         | 83/861 [01:19<10:40,  1.21it/s]

 10%|▉         | 84/861 [01:20<12:41,  1.02it/s]

 10%|▉         | 85/861 [01:21<11:26,  1.13it/s]

 10%|▉         | 86/861 [01:22<10:24,  1.24it/s]

 10%|█         | 87/861 [01:23<12:28,  1.03it/s]

 10%|█         | 88/861 [01:23<09:35,  1.34it/s]

 10%|█         | 89/861 [01:24<09:27,  1.36it/s]

 10%|█         | 90/861 [01:26<13:36,  1.06s/it]

 11%|█         | 91/861 [01:27<12:18,  1.04it/s]

 11%|█         | 92/861 [01:27<11:27,  1.12it/s]

 11%|█         | 93/861 [01:28<12:12,  1.05it/s]

 11%|█         | 94/861 [01:29<09:35,  1.33it/s]

 11%|█         | 95/861 [01:29<09:17,  1.37it/s]

 11%|█         | 96/861 [01:30<09:52,  1.29it/s]

 11%|█▏        | 97/861 [01:32<12:49,  1.01s/it]

 11%|█▏        | 98/861 [01:33<12:49,  1.01s/it]

 11%|█▏        | 99/861 [01:35<16:27,  1.30s/it]

 12%|█▏        | 100/861 [01:35<13:49,  1.09s/it]

 12%|█▏        | 101/861 [01:36<11:37,  1.09it/s]

 12%|█▏        | 102/861 [01:37<10:40,  1.18it/s]

 12%|█▏        | 103/861 [01:37<09:02,  1.40it/s]

 12%|█▏        | 104/861 [01:39<12:17,  1.03it/s]

 12%|█▏        | 105/861 [01:40<13:55,  1.11s/it]

 12%|█▏        | 106/861 [01:40<11:47,  1.07it/s]

 12%|█▏        | 107/861 [01:41<10:30,  1.20it/s]

 13%|█▎        | 108/861 [01:41<08:33,  1.47it/s]

 13%|█▎        | 109/861 [01:42<07:07,  1.76it/s]

 13%|█▎        | 110/861 [01:42<06:49,  1.83it/s]

 13%|█▎        | 111/861 [01:43<09:36,  1.30it/s]

 13%|█▎        | 112/861 [01:44<08:04,  1.54it/s]

 13%|█▎        | 113/861 [01:45<08:47,  1.42it/s]

 13%|█▎        | 114/861 [01:46<09:26,  1.32it/s]

 13%|█▎        | 115/861 [01:46<08:26,  1.47it/s]

 13%|█▎        | 116/861 [01:46<07:18,  1.70it/s]

 14%|█▎        | 117/861 [01:48<09:36,  1.29it/s]

 14%|█▎        | 118/861 [01:48<09:54,  1.25it/s]

 14%|█▍        | 119/861 [01:49<09:44,  1.27it/s]

 14%|█▍        | 120/861 [01:50<07:47,  1.58it/s]

 14%|█▍        | 121/861 [01:51<09:50,  1.25it/s]

 14%|█▍        | 122/861 [01:52<11:55,  1.03it/s]

 14%|█▍        | 123/861 [01:53<11:16,  1.09it/s]

 14%|█▍        | 124/861 [01:55<15:05,  1.23s/it]

 15%|█▍        | 125/861 [01:56<13:19,  1.09s/it]

 15%|█▍        | 126/861 [01:57<14:09,  1.16s/it]

 15%|█▍        | 127/861 [01:58<14:05,  1.15s/it]

 15%|█▍        | 128/861 [01:59<11:51,  1.03it/s]

 15%|█▍        | 129/861 [02:00<12:09,  1.00it/s]

 15%|█▌        | 130/861 [02:01<11:49,  1.03it/s]

 15%|█▌        | 131/861 [02:01<11:22,  1.07it/s]

 15%|█▌        | 132/861 [02:03<12:25,  1.02s/it]

 15%|█▌        | 133/861 [02:04<12:14,  1.01s/it]

 16%|█▌        | 134/861 [02:04<09:16,  1.31it/s]

 16%|█▌        | 135/861 [02:04<07:59,  1.51it/s]

 16%|█▌        | 136/861 [02:05<08:25,  1.43it/s]

 16%|█▌        | 137/861 [02:05<07:40,  1.57it/s]

 16%|█▌        | 138/861 [02:06<07:08,  1.69it/s]

 16%|█▌        | 139/861 [02:06<06:31,  1.84it/s]

 16%|█▋        | 140/861 [02:07<06:22,  1.88it/s]

 16%|█▋        | 141/861 [02:07<05:52,  2.04it/s]

 16%|█▋        | 142/861 [02:08<05:35,  2.14it/s]

 17%|█▋        | 143/861 [02:09<09:17,  1.29it/s]

 17%|█▋        | 144/861 [02:10<10:07,  1.18it/s]

 17%|█▋        | 145/861 [02:11<09:25,  1.27it/s]

 17%|█▋        | 146/861 [02:12<09:18,  1.28it/s]

 17%|█▋        | 147/861 [02:12<09:18,  1.28it/s]

 17%|█▋        | 148/861 [02:13<07:26,  1.60it/s]

 17%|█▋        | 149/861 [02:13<06:40,  1.78it/s]

 17%|█▋        | 150/861 [02:15<10:59,  1.08it/s]

 18%|█▊        | 151/861 [02:17<13:34,  1.15s/it]

 18%|█▊        | 152/861 [02:18<13:18,  1.13s/it]

 18%|█▊        | 153/861 [02:19<13:02,  1.11s/it]

 18%|█▊        | 154/861 [02:20<12:48,  1.09s/it]

 18%|█▊        | 155/861 [02:21<15:02,  1.28s/it]

 18%|█▊        | 156/861 [02:23<14:54,  1.27s/it]

 18%|█▊        | 157/861 [02:23<12:52,  1.10s/it]

 18%|█▊        | 158/861 [02:25<14:35,  1.25s/it]

 18%|█▊        | 159/861 [02:26<12:38,  1.08s/it]

 19%|█▊        | 160/861 [02:26<11:16,  1.04it/s]

 19%|█▊        | 161/861 [02:28<14:42,  1.26s/it]

 19%|█▉        | 162/861 [02:29<11:13,  1.04it/s]

 19%|█▉        | 163/861 [02:29<08:45,  1.33it/s]

 19%|█▉        | 164/861 [02:30<10:28,  1.11it/s]

 19%|█▉        | 165/861 [02:31<10:30,  1.10it/s]

 19%|█▉        | 166/861 [02:32<09:46,  1.19it/s]

 19%|█▉        | 167/861 [02:32<07:26,  1.55it/s]

 20%|█▉        | 168/861 [02:32<07:10,  1.61it/s]

 20%|█▉        | 169/861 [02:33<08:12,  1.41it/s]

 20%|█▉        | 170/861 [02:34<08:43,  1.32it/s]

 20%|█▉        | 171/861 [02:35<08:29,  1.35it/s]

 20%|█▉        | 172/861 [02:35<07:15,  1.58it/s]

 20%|██        | 173/861 [02:36<07:05,  1.62it/s]

 20%|██        | 174/861 [02:37<09:26,  1.21it/s]

 20%|██        | 175/861 [02:38<09:07,  1.25it/s]

 20%|██        | 176/861 [02:38<07:05,  1.61it/s]

 21%|██        | 177/861 [02:39<07:27,  1.53it/s]

 21%|██        | 178/861 [02:40<08:05,  1.41it/s]

 21%|██        | 179/861 [02:40<08:08,  1.40it/s]

 21%|██        | 180/861 [02:41<07:24,  1.53it/s]

 21%|██        | 181/861 [02:41<06:35,  1.72it/s]

 21%|██        | 182/861 [02:42<06:02,  1.87it/s]

 21%|██▏       | 183/861 [02:43<07:03,  1.60it/s]

 21%|██▏       | 184/861 [02:44<09:05,  1.24it/s]

 21%|██▏       | 185/861 [02:44<08:03,  1.40it/s]

 22%|██▏       | 186/861 [02:45<07:04,  1.59it/s]

 22%|██▏       | 187/861 [02:46<07:58,  1.41it/s]

 22%|██▏       | 188/861 [02:46<08:02,  1.39it/s]

 22%|██▏       | 189/861 [02:48<10:19,  1.09it/s]

 22%|██▏       | 190/861 [02:49<10:43,  1.04it/s]

 22%|██▏       | 191/861 [02:49<08:52,  1.26it/s]

 22%|██▏       | 192/861 [02:50<07:54,  1.41it/s]

 22%|██▏       | 193/861 [02:51<08:48,  1.26it/s]

 23%|██▎       | 194/861 [02:51<08:01,  1.39it/s]

 23%|██▎       | 195/861 [02:52<07:14,  1.53it/s]

 23%|██▎       | 196/861 [02:52<06:37,  1.67it/s]

 23%|██▎       | 197/861 [02:53<06:13,  1.78it/s]

 23%|██▎       | 198/861 [02:53<05:32,  2.00it/s]

 23%|██▎       | 199/861 [02:54<06:06,  1.81it/s]

 23%|██▎       | 200/861 [02:55<07:43,  1.43it/s]

 23%|██▎       | 201/861 [02:56<09:02,  1.22it/s]

 23%|██▎       | 202/861 [02:57<09:52,  1.11it/s]

 24%|██▎       | 203/861 [02:57<07:52,  1.39it/s]

 24%|██▎       | 204/861 [02:58<06:02,  1.81it/s]

 24%|██▍       | 205/861 [02:58<05:39,  1.93it/s]

 24%|██▍       | 206/861 [02:59<06:15,  1.74it/s]

 24%|██▍       | 207/861 [02:59<06:33,  1.66it/s]

 24%|██▍       | 208/861 [03:00<07:01,  1.55it/s]

 24%|██▍       | 209/861 [03:01<06:54,  1.57it/s]

 24%|██▍       | 210/861 [03:01<07:17,  1.49it/s]

 25%|██▍       | 211/861 [03:03<10:08,  1.07it/s]

 25%|██▍       | 212/861 [03:04<10:31,  1.03it/s]

 25%|██▍       | 213/861 [03:05<08:58,  1.20it/s]

 25%|██▍       | 214/861 [03:05<07:52,  1.37it/s]

 25%|██▍       | 215/861 [03:06<08:07,  1.32it/s]

 25%|██▌       | 216/861 [03:06<07:03,  1.52it/s]

 25%|██▌       | 217/861 [03:07<05:47,  1.85it/s]

 25%|██▌       | 218/861 [03:07<05:12,  2.06it/s]

 25%|██▌       | 219/861 [03:08<07:42,  1.39it/s]

 26%|██▌       | 220/861 [03:09<07:36,  1.40it/s]

 26%|██▌       | 221/861 [03:09<06:34,  1.62it/s]

 26%|██▌       | 222/861 [03:10<07:50,  1.36it/s]

 26%|██▌       | 223/861 [03:11<08:46,  1.21it/s]

 26%|██▌       | 224/861 [03:12<07:56,  1.34it/s]

 26%|██▌       | 225/861 [03:13<09:41,  1.09it/s]

 26%|██▌       | 226/861 [03:15<11:47,  1.11s/it]

 26%|██▋       | 227/861 [03:16<10:36,  1.00s/it]

 26%|██▋       | 228/861 [03:16<10:29,  1.00it/s]

 27%|██▋       | 229/861 [03:17<09:11,  1.15it/s]

 27%|██▋       | 230/861 [03:18<09:19,  1.13it/s]

 27%|██▋       | 231/861 [03:21<14:29,  1.38s/it]

 27%|██▋       | 232/861 [03:21<10:42,  1.02s/it]

 27%|██▋       | 233/861 [03:22<09:58,  1.05it/s]

 27%|██▋       | 234/861 [03:22<08:47,  1.19it/s]

 27%|██▋       | 235/861 [03:23<08:13,  1.27it/s]

 27%|██▋       | 236/861 [03:23<07:32,  1.38it/s]

 28%|██▊       | 237/861 [03:24<07:24,  1.40it/s]

 28%|██▊       | 238/861 [03:24<06:05,  1.71it/s]

 28%|██▊       | 239/861 [03:26<09:31,  1.09it/s]

 28%|██▊       | 240/861 [03:27<08:38,  1.20it/s]

 28%|██▊       | 241/861 [03:28<10:53,  1.05s/it]

 28%|██▊       | 242/861 [03:29<09:12,  1.12it/s]

 28%|██▊       | 243/861 [03:30<10:10,  1.01it/s]

 28%|██▊       | 244/861 [03:31<09:28,  1.08it/s]

 28%|██▊       | 245/861 [03:32<10:46,  1.05s/it]

 29%|██▊       | 246/861 [03:33<10:18,  1.01s/it]

 29%|██▊       | 247/861 [03:33<08:17,  1.23it/s]

 29%|██▉       | 248/861 [03:33<06:20,  1.61it/s]

 29%|██▉       | 249/861 [03:34<06:28,  1.58it/s]

 29%|██▉       | 250/861 [03:35<07:59,  1.27it/s]

 29%|██▉       | 251/861 [03:36<08:10,  1.24it/s]

 29%|██▉       | 252/861 [03:37<08:09,  1.24it/s]

 29%|██▉       | 253/861 [03:37<07:14,  1.40it/s]

 30%|██▉       | 254/861 [03:38<05:57,  1.70it/s]

 30%|██▉       | 255/861 [03:38<06:00,  1.68it/s]

 30%|██▉       | 256/861 [03:40<07:54,  1.27it/s]

 30%|██▉       | 257/861 [03:40<07:48,  1.29it/s]

 30%|██▉       | 258/861 [03:42<09:07,  1.10it/s]

 30%|███       | 259/861 [03:43<11:23,  1.13s/it]

 30%|███       | 260/861 [03:44<10:34,  1.06s/it]

 30%|███       | 261/861 [03:46<13:57,  1.40s/it]

 30%|███       | 262/861 [03:47<11:32,  1.16s/it]

 31%|███       | 263/861 [03:47<08:33,  1.17it/s]

 31%|███       | 264/861 [03:48<07:37,  1.30it/s]

 31%|███       | 265/861 [03:48<06:47,  1.46it/s]

 31%|███       | 266/861 [03:48<05:40,  1.75it/s]

 31%|███       | 267/861 [03:49<05:24,  1.83it/s]

 31%|███       | 268/861 [03:50<05:45,  1.72it/s]

 31%|███       | 269/861 [03:50<05:54,  1.67it/s]

 31%|███▏      | 270/861 [03:51<06:42,  1.47it/s]

 31%|███▏      | 271/861 [03:52<06:53,  1.43it/s]

 32%|███▏      | 272/861 [03:53<08:31,  1.15it/s]

 32%|███▏      | 273/861 [03:54<08:50,  1.11it/s]

 32%|███▏      | 274/861 [03:55<10:06,  1.03s/it]

 32%|███▏      | 275/861 [03:56<07:34,  1.29it/s]

 32%|███▏      | 276/861 [03:57<08:09,  1.19it/s]

 32%|███▏      | 277/861 [03:58<09:40,  1.01it/s]

 32%|███▏      | 278/861 [03:59<10:20,  1.06s/it]

 32%|███▏      | 279/861 [04:00<09:34,  1.01it/s]

 33%|███▎      | 280/861 [04:01<09:37,  1.01it/s]

 33%|███▎      | 281/861 [04:02<10:26,  1.08s/it]

 33%|███▎      | 282/861 [04:03<09:39,  1.00s/it]

 33%|███▎      | 283/861 [04:04<08:42,  1.11it/s]

 33%|███▎      | 284/861 [04:04<07:12,  1.33it/s]

 33%|███▎      | 285/861 [04:05<06:52,  1.40it/s]

 33%|███▎      | 286/861 [04:07<10:50,  1.13s/it]

 33%|███▎      | 287/861 [04:09<12:54,  1.35s/it]

 33%|███▎      | 288/861 [04:10<11:30,  1.21s/it]

 34%|███▎      | 289/861 [04:10<09:02,  1.05it/s]

 34%|███▎      | 290/861 [04:11<08:25,  1.13it/s]

 34%|███▍      | 291/861 [04:11<08:04,  1.18it/s]

 34%|███▍      | 292/861 [04:13<09:19,  1.02it/s]

 34%|███▍      | 293/861 [04:14<09:08,  1.04it/s]

 34%|███▍      | 294/861 [04:15<09:45,  1.03s/it]

 34%|███▍      | 295/861 [04:15<07:26,  1.27it/s]

 34%|███▍      | 296/861 [04:16<06:50,  1.38it/s]

 34%|███▍      | 297/861 [04:17<08:53,  1.06it/s]

 35%|███▍      | 298/861 [04:18<09:35,  1.02s/it]

 35%|███▍      | 299/861 [04:20<11:52,  1.27s/it]

 35%|███▍      | 300/861 [04:21<10:11,  1.09s/it]

 35%|███▍      | 301/861 [04:22<09:13,  1.01it/s]

 35%|███▌      | 302/861 [04:22<07:06,  1.31it/s]

 35%|███▌      | 303/861 [04:23<09:07,  1.02it/s]

 35%|███▌      | 304/861 [04:25<09:55,  1.07s/it]

 35%|███▌      | 305/861 [04:26<11:09,  1.20s/it]

 36%|███▌      | 306/861 [04:28<12:11,  1.32s/it]

 36%|███▌      | 307/861 [04:30<13:40,  1.48s/it]

 36%|███▌      | 308/861 [04:30<10:03,  1.09s/it]

 36%|███▌      | 309/861 [04:30<07:53,  1.17it/s]

 36%|███▌      | 310/861 [04:31<07:26,  1.23it/s]

 36%|███▌      | 311/861 [04:32<07:56,  1.15it/s]

 36%|███▌      | 312/861 [04:33<08:25,  1.09it/s]

 36%|███▋      | 313/861 [04:34<10:14,  1.12s/it]

 36%|███▋      | 314/861 [04:35<09:41,  1.06s/it]

 37%|███▋      | 315/861 [04:36<08:24,  1.08it/s]

 37%|███▋      | 316/861 [04:37<09:33,  1.05s/it]

 37%|███▋      | 317/861 [04:37<07:12,  1.26it/s]

 37%|███▋      | 318/861 [04:39<09:01,  1.00it/s]

 37%|███▋      | 319/861 [04:41<10:40,  1.18s/it]

 37%|███▋      | 320/861 [04:41<09:31,  1.06s/it]

 37%|███▋      | 321/861 [04:43<10:17,  1.14s/it]

 37%|███▋      | 322/861 [04:44<11:41,  1.30s/it]

 38%|███▊      | 323/861 [04:45<10:25,  1.16s/it]

 38%|███▊      | 324/861 [04:46<10:56,  1.22s/it]

 38%|███▊      | 325/861 [04:48<10:54,  1.22s/it]

 38%|███▊      | 326/861 [04:48<08:06,  1.10it/s]

 38%|███▊      | 327/861 [04:49<09:51,  1.11s/it]

 38%|███▊      | 328/861 [04:50<08:44,  1.02it/s]

 38%|███▊      | 329/861 [04:51<08:13,  1.08it/s]

 38%|███▊      | 330/861 [04:52<07:37,  1.16it/s]

 38%|███▊      | 331/861 [04:55<12:57,  1.47s/it]

 39%|███▊      | 332/861 [04:56<11:41,  1.33s/it]

 39%|███▊      | 333/861 [04:57<12:48,  1.46s/it]

 39%|███▉      | 334/861 [04:59<12:50,  1.46s/it]

 39%|███▉      | 335/861 [05:00<11:19,  1.29s/it]

 39%|███▉      | 336/861 [05:01<11:11,  1.28s/it]

 39%|███▉      | 337/861 [05:02<09:27,  1.08s/it]

 39%|███▉      | 338/861 [05:04<12:16,  1.41s/it]

 39%|███▉      | 339/861 [05:05<11:14,  1.29s/it]

 39%|███▉      | 340/861 [05:05<08:52,  1.02s/it]

 40%|███▉      | 341/861 [05:05<06:55,  1.25it/s]

 40%|███▉      | 342/861 [05:06<06:19,  1.37it/s]

 40%|███▉      | 343/861 [05:07<06:32,  1.32it/s]

 40%|███▉      | 344/861 [05:07<05:47,  1.49it/s]

 40%|████      | 345/861 [05:08<06:32,  1.31it/s]

 40%|████      | 346/861 [05:09<07:03,  1.22it/s]

 40%|████      | 347/861 [05:10<06:04,  1.41it/s]

 40%|████      | 348/861 [05:10<05:50,  1.46it/s]

 41%|████      | 349/861 [05:11<05:55,  1.44it/s]

 41%|████      | 350/861 [05:12<06:40,  1.28it/s]

 41%|████      | 351/861 [05:13<06:27,  1.32it/s]

 41%|████      | 352/861 [05:13<05:42,  1.48it/s]

 41%|████      | 353/861 [05:14<05:36,  1.51it/s]

 41%|████      | 354/861 [05:14<05:41,  1.48it/s]

 41%|████      | 355/861 [05:15<05:03,  1.67it/s]

 41%|████▏     | 356/861 [05:15<04:44,  1.78it/s]

 41%|████▏     | 357/861 [05:16<04:05,  2.06it/s]

 42%|████▏     | 358/861 [05:16<04:19,  1.94it/s]

 42%|████▏     | 359/861 [05:18<06:19,  1.32it/s]

 42%|████▏     | 360/861 [05:19<07:24,  1.13it/s]

 42%|████▏     | 361/861 [05:20<07:09,  1.17it/s]

 42%|████▏     | 362/861 [05:21<07:46,  1.07it/s]

 42%|████▏     | 363/861 [05:22<07:59,  1.04it/s]

 42%|████▏     | 364/861 [05:22<07:17,  1.14it/s]

 42%|████▏     | 365/861 [05:24<09:39,  1.17s/it]

 43%|████▎     | 366/861 [05:25<08:58,  1.09s/it]

 43%|████▎     | 367/861 [05:27<10:20,  1.26s/it]

 43%|████▎     | 368/861 [05:28<09:20,  1.14s/it]

 43%|████▎     | 369/861 [05:28<08:11,  1.00it/s]

 43%|████▎     | 370/861 [05:29<07:32,  1.09it/s]

 43%|████▎     | 371/861 [05:30<07:53,  1.04it/s]

 43%|████▎     | 372/861 [05:31<08:30,  1.04s/it]

 43%|████▎     | 373/861 [05:32<07:42,  1.06it/s]

 43%|████▎     | 374/861 [05:34<10:17,  1.27s/it]

 44%|████▎     | 375/861 [05:36<11:10,  1.38s/it]

 44%|████▎     | 376/861 [05:36<09:19,  1.15s/it]

 44%|████▍     | 377/861 [05:38<10:54,  1.35s/it]

 44%|████▍     | 378/861 [05:40<12:02,  1.50s/it]

 44%|████▍     | 379/861 [05:40<08:53,  1.11s/it]

 44%|████▍     | 380/861 [05:41<08:43,  1.09s/it]

 44%|████▍     | 381/861 [05:42<08:28,  1.06s/it]

 44%|████▍     | 382/861 [05:43<08:18,  1.04s/it]

 44%|████▍     | 383/861 [05:44<07:58,  1.00s/it]

 45%|████▍     | 384/861 [05:45<07:17,  1.09it/s]

 45%|████▍     | 385/861 [05:45<05:56,  1.34it/s]

 45%|████▍     | 386/861 [05:46<06:18,  1.25it/s]

 45%|████▍     | 387/861 [05:47<07:30,  1.05it/s]

 45%|████▌     | 388/861 [05:48<06:49,  1.16it/s]

 45%|████▌     | 389/861 [05:49<05:46,  1.36it/s]

 45%|████▌     | 390/861 [05:49<05:24,  1.45it/s]

 45%|████▌     | 391/861 [05:50<05:48,  1.35it/s]

 46%|████▌     | 392/861 [05:51<06:17,  1.24it/s]

 46%|████▌     | 393/861 [05:52<07:24,  1.05it/s]

 46%|████▌     | 394/861 [05:54<09:22,  1.20s/it]

 46%|████▌     | 395/861 [05:55<07:54,  1.02s/it]

 46%|████▌     | 396/861 [05:55<06:34,  1.18it/s]

 46%|████▌     | 397/861 [05:55<05:02,  1.54it/s]

 46%|████▌     | 398/861 [05:56<05:16,  1.46it/s]

 46%|████▋     | 399/861 [05:57<06:28,  1.19it/s]

 46%|████▋     | 400/861 [05:58<07:18,  1.05it/s]

 47%|████▋     | 401/861 [05:59<06:08,  1.25it/s]

 47%|████▋     | 402/861 [06:00<06:11,  1.24it/s]

 47%|████▋     | 403/861 [06:00<05:57,  1.28it/s]

 47%|████▋     | 404/861 [06:01<06:35,  1.15it/s]

 47%|████▋     | 405/861 [06:02<05:28,  1.39it/s]

 47%|████▋     | 406/861 [06:03<06:19,  1.20it/s]

 47%|████▋     | 407/861 [06:04<06:44,  1.12it/s]

 47%|████▋     | 408/861 [06:05<06:26,  1.17it/s]

 48%|████▊     | 409/861 [06:06<06:28,  1.16it/s]

 48%|████▊     | 410/861 [06:06<06:10,  1.22it/s]

 48%|████▊     | 411/861 [06:07<05:05,  1.47it/s]

 48%|████▊     | 412/861 [06:08<05:34,  1.34it/s]

 48%|████▊     | 413/861 [06:08<05:33,  1.34it/s]

 48%|████▊     | 414/861 [06:09<04:58,  1.50it/s]

 48%|████▊     | 415/861 [06:09<04:23,  1.69it/s]

 48%|████▊     | 416/861 [06:10<04:21,  1.70it/s]

 48%|████▊     | 417/861 [06:10<04:13,  1.75it/s]

 49%|████▊     | 418/861 [06:11<04:06,  1.80it/s]

 49%|████▊     | 419/861 [06:12<04:52,  1.51it/s]

 49%|████▉     | 420/861 [06:12<04:29,  1.64it/s]

 49%|████▉     | 421/861 [06:13<04:11,  1.75it/s]

 49%|████▉     | 422/861 [06:13<03:38,  2.01it/s]

 49%|████▉     | 423/861 [06:14<04:24,  1.66it/s]

 49%|████▉     | 424/861 [06:14<04:07,  1.76it/s]

 49%|████▉     | 425/861 [06:15<04:19,  1.68it/s]

 49%|████▉     | 426/861 [06:16<05:26,  1.33it/s]

 50%|████▉     | 427/861 [06:17<05:44,  1.26it/s]

 50%|████▉     | 428/861 [06:18<05:29,  1.31it/s]

 50%|████▉     | 429/861 [06:19<05:28,  1.31it/s]

 50%|████▉     | 430/861 [06:20<06:25,  1.12it/s]

 50%|█████     | 431/861 [06:21<07:56,  1.11s/it]

 50%|█████     | 432/861 [06:23<08:33,  1.20s/it]

 50%|█████     | 433/861 [06:24<09:00,  1.26s/it]

 50%|█████     | 434/861 [06:25<07:22,  1.04s/it]

 51%|█████     | 435/861 [06:25<05:31,  1.28it/s]

 51%|█████     | 436/861 [06:25<04:32,  1.56it/s]

 51%|█████     | 437/861 [06:26<04:21,  1.62it/s]

 51%|█████     | 438/861 [06:26<03:42,  1.90it/s]

 51%|█████     | 439/861 [06:27<03:54,  1.80it/s]

 51%|█████     | 440/861 [06:27<03:18,  2.12it/s]

 51%|█████     | 441/861 [06:27<02:50,  2.46it/s]

 51%|█████▏    | 442/861 [06:28<03:01,  2.31it/s]

 51%|█████▏    | 443/861 [06:28<03:09,  2.20it/s]

 52%|█████▏    | 444/861 [06:29<03:04,  2.26it/s]

 52%|█████▏    | 445/861 [06:29<02:48,  2.47it/s]

 52%|█████▏    | 446/861 [06:29<02:46,  2.50it/s]

 52%|█████▏    | 447/861 [06:30<04:10,  1.65it/s]

 52%|█████▏    | 448/861 [06:31<04:31,  1.52it/s]

 52%|█████▏    | 449/861 [06:32<04:54,  1.40it/s]

 52%|█████▏    | 450/861 [06:33<05:33,  1.23it/s]

 52%|█████▏    | 451/861 [06:34<05:15,  1.30it/s]

 52%|█████▏    | 452/861 [06:34<05:00,  1.36it/s]

 53%|█████▎    | 453/861 [06:35<04:08,  1.64it/s]

 53%|█████▎    | 454/861 [06:35<03:57,  1.71it/s]

 53%|█████▎    | 455/861 [06:36<03:29,  1.93it/s]

 53%|█████▎    | 456/861 [06:36<03:31,  1.92it/s]

 53%|█████▎    | 457/861 [06:37<03:59,  1.68it/s]

 53%|█████▎    | 458/861 [06:38<04:33,  1.47it/s]

 53%|█████▎    | 459/861 [06:38<03:50,  1.75it/s]

 53%|█████▎    | 460/861 [06:39<04:03,  1.65it/s]

 54%|█████▎    | 461/861 [06:40<04:52,  1.37it/s]

 54%|█████▎    | 462/861 [06:40<04:24,  1.51it/s]

 54%|█████▍    | 463/861 [06:41<04:03,  1.63it/s]

 54%|█████▍    | 464/861 [06:41<03:38,  1.82it/s]

 54%|█████▍    | 465/861 [06:41<02:55,  2.25it/s]

 54%|█████▍    | 466/861 [06:42<03:09,  2.09it/s]

 54%|█████▍    | 467/861 [06:43<04:13,  1.55it/s]

 54%|█████▍    | 468/861 [06:43<03:33,  1.84it/s]

 54%|█████▍    | 469/861 [06:44<03:30,  1.86it/s]

 55%|█████▍    | 470/861 [06:44<03:00,  2.17it/s]

 55%|█████▍    | 471/861 [06:45<03:06,  2.09it/s]

 55%|█████▍    | 472/861 [06:45<02:46,  2.34it/s]

 55%|█████▍    | 473/861 [06:45<02:32,  2.55it/s]

 55%|█████▌    | 474/861 [06:46<02:17,  2.82it/s]

 55%|█████▌    | 475/861 [06:46<02:33,  2.52it/s]

 55%|█████▌    | 476/861 [06:46<02:41,  2.38it/s]

 55%|█████▌    | 477/861 [06:47<03:00,  2.13it/s]

 56%|█████▌    | 478/861 [06:48<02:58,  2.15it/s]

 56%|█████▌    | 479/861 [06:48<02:30,  2.55it/s]

 56%|█████▌    | 480/861 [06:48<02:50,  2.23it/s]

 56%|█████▌    | 481/861 [06:49<02:39,  2.38it/s]

 56%|█████▌    | 482/861 [06:49<02:28,  2.55it/s]

 56%|█████▌    | 483/861 [06:49<02:16,  2.78it/s]

 56%|█████▌    | 484/861 [06:50<02:10,  2.88it/s]

 56%|█████▋    | 485/861 [06:50<02:02,  3.07it/s]

 56%|█████▋    | 486/861 [06:50<01:50,  3.39it/s]

 57%|█████▋    | 487/861 [06:51<02:07,  2.94it/s]

 57%|█████▋    | 488/861 [06:51<01:55,  3.22it/s]

 57%|█████▋    | 489/861 [06:51<02:05,  2.95it/s]

 57%|█████▋    | 490/861 [06:51<01:58,  3.14it/s]

 57%|█████▋    | 491/861 [06:52<02:02,  3.01it/s]

 57%|█████▋    | 492/861 [06:52<02:10,  2.82it/s]

 57%|█████▋    | 493/861 [06:53<02:28,  2.48it/s]

 57%|█████▋    | 494/861 [06:53<02:13,  2.75it/s]

 57%|█████▋    | 495/861 [06:54<03:00,  2.03it/s]

 58%|█████▊    | 496/861 [06:55<03:42,  1.64it/s]

 58%|█████▊    | 497/861 [06:55<02:57,  2.05it/s]

 58%|█████▊    | 498/861 [06:55<02:50,  2.13it/s]

 58%|█████▊    | 499/861 [06:56<02:33,  2.36it/s]

 58%|█████▊    | 500/861 [06:56<02:43,  2.20it/s]

 58%|█████▊    | 501/861 [06:56<02:19,  2.57it/s]

 58%|█████▊    | 502/861 [06:57<02:44,  2.18it/s]

 58%|█████▊    | 503/861 [06:57<02:40,  2.23it/s]

 59%|█████▊    | 504/861 [06:58<02:35,  2.30it/s]

 59%|█████▊    | 505/861 [06:58<02:19,  2.55it/s]

 59%|█████▉    | 506/861 [06:58<02:07,  2.79it/s]

 59%|█████▉    | 507/861 [06:59<01:53,  3.11it/s]

 59%|█████▉    | 508/861 [06:59<02:40,  2.19it/s]

 59%|█████▉    | 509/861 [07:00<03:27,  1.70it/s]

 59%|█████▉    | 510/861 [07:01<03:10,  1.84it/s]

 59%|█████▉    | 511/861 [07:01<03:28,  1.68it/s]

 59%|█████▉    | 512/861 [07:02<03:11,  1.82it/s]

 60%|█████▉    | 513/861 [07:02<03:07,  1.86it/s]

 60%|█████▉    | 514/861 [07:03<02:57,  1.96it/s]

 60%|█████▉    | 515/861 [07:03<02:22,  2.43it/s]

 60%|█████▉    | 516/861 [07:03<02:00,  2.87it/s]

 60%|██████    | 517/861 [07:04<01:51,  3.09it/s]

 60%|██████    | 518/861 [07:04<02:18,  2.47it/s]

 60%|██████    | 519/861 [07:05<02:55,  1.95it/s]

 60%|██████    | 520/861 [07:06<03:11,  1.78it/s]

 61%|██████    | 521/861 [07:06<02:42,  2.09it/s]

 61%|██████    | 522/861 [07:07<03:11,  1.77it/s]

 61%|██████    | 523/861 [07:08<03:51,  1.46it/s]

 61%|██████    | 524/861 [07:09<04:35,  1.22it/s]

 61%|██████    | 525/861 [07:09<03:50,  1.46it/s]

 61%|██████    | 526/861 [07:10<03:36,  1.55it/s]

 61%|██████    | 527/861 [07:10<03:47,  1.47it/s]

 61%|██████▏   | 528/861 [07:11<04:04,  1.36it/s]

 61%|██████▏   | 529/861 [07:12<03:27,  1.60it/s]

 62%|██████▏   | 530/861 [07:12<03:00,  1.84it/s]

 62%|██████▏   | 531/861 [07:12<02:47,  1.97it/s]

 62%|██████▏   | 532/861 [07:13<02:41,  2.04it/s]

 62%|██████▏   | 533/861 [07:13<02:32,  2.14it/s]

 62%|██████▏   | 534/861 [07:14<02:43,  2.00it/s]

 62%|██████▏   | 535/861 [07:14<02:45,  1.96it/s]

 62%|██████▏   | 536/861 [07:15<03:02,  1.78it/s]

 62%|██████▏   | 537/861 [07:17<04:40,  1.15it/s]

 62%|██████▏   | 538/861 [07:17<03:54,  1.38it/s]

 63%|██████▎   | 539/861 [07:19<05:15,  1.02it/s]

 63%|██████▎   | 540/861 [07:20<05:05,  1.05it/s]

 63%|██████▎   | 541/861 [07:20<04:17,  1.24it/s]

 63%|██████▎   | 542/861 [07:20<03:24,  1.56it/s]

 63%|██████▎   | 543/861 [07:21<03:32,  1.50it/s]

 63%|██████▎   | 544/861 [07:22<03:23,  1.56it/s]

 63%|██████▎   | 545/861 [07:23<04:43,  1.12it/s]

 63%|██████▎   | 546/861 [07:24<04:58,  1.05it/s]

 64%|██████▎   | 547/861 [07:25<04:29,  1.16it/s]

 64%|██████▎   | 548/861 [07:26<05:12,  1.00it/s]

 64%|██████▍   | 549/861 [07:27<05:13,  1.00s/it]

 64%|██████▍   | 550/861 [07:28<04:53,  1.06it/s]

 64%|██████▍   | 551/861 [07:29<04:27,  1.16it/s]

 64%|██████▍   | 552/861 [07:29<04:30,  1.14it/s]

 64%|██████▍   | 553/861 [07:31<05:06,  1.01it/s]

 64%|██████▍   | 554/861 [07:32<05:31,  1.08s/it]

 64%|██████▍   | 555/861 [07:34<06:20,  1.24s/it]

 65%|██████▍   | 556/861 [07:35<06:19,  1.25s/it]

 65%|██████▍   | 557/861 [07:36<06:37,  1.31s/it]

 65%|██████▍   | 558/861 [07:37<05:35,  1.11s/it]

 65%|██████▍   | 559/861 [07:38<06:03,  1.20s/it]

 65%|██████▌   | 560/861 [07:40<06:04,  1.21s/it]

 65%|██████▌   | 561/861 [07:40<05:28,  1.10s/it]

 65%|██████▌   | 562/861 [07:41<05:15,  1.05s/it]

 65%|██████▌   | 563/861 [07:43<05:16,  1.06s/it]

 66%|██████▌   | 564/861 [07:43<05:01,  1.01s/it]

 66%|██████▌   | 565/861 [07:45<05:23,  1.09s/it]

 66%|██████▌   | 566/861 [07:46<05:46,  1.17s/it]

 66%|██████▌   | 567/861 [07:47<05:53,  1.20s/it]

 66%|██████▌   | 568/861 [07:49<05:51,  1.20s/it]

 66%|██████▌   | 569/861 [07:50<05:44,  1.18s/it]

 66%|██████▌   | 570/861 [07:50<05:01,  1.04s/it]

 66%|██████▋   | 571/861 [07:52<05:25,  1.12s/it]

 66%|██████▋   | 572/861 [07:53<05:23,  1.12s/it]

 67%|██████▋   | 573/861 [07:53<04:38,  1.03it/s]

 67%|██████▋   | 574/861 [07:55<04:58,  1.04s/it]

 67%|██████▋   | 575/861 [07:56<05:07,  1.08s/it]

 67%|██████▋   | 576/861 [07:58<06:15,  1.32s/it]

 67%|██████▋   | 577/861 [07:59<06:58,  1.48s/it]

 67%|██████▋   | 578/861 [08:01<07:27,  1.58s/it]

 67%|██████▋   | 579/861 [08:03<07:04,  1.51s/it]

 67%|██████▋   | 580/861 [08:04<06:31,  1.39s/it]

 67%|██████▋   | 581/861 [08:05<05:44,  1.23s/it]

 68%|██████▊   | 582/861 [08:07<06:59,  1.51s/it]

 68%|██████▊   | 583/861 [08:08<06:28,  1.40s/it]

 68%|██████▊   | 584/861 [08:09<06:02,  1.31s/it]

 68%|██████▊   | 585/861 [08:10<05:18,  1.16s/it]

 68%|██████▊   | 586/861 [08:10<04:31,  1.01it/s]

 68%|██████▊   | 587/861 [08:12<04:45,  1.04s/it]

 68%|██████▊   | 588/861 [08:13<04:43,  1.04s/it]

 68%|██████▊   | 589/861 [08:13<04:19,  1.05it/s]

 69%|██████▊   | 590/861 [08:15<04:59,  1.10s/it]

 69%|██████▊   | 591/861 [08:15<04:17,  1.05it/s]

 69%|██████▉   | 592/861 [08:16<04:18,  1.04it/s]

 69%|██████▉   | 593/861 [08:18<04:47,  1.07s/it]

 69%|██████▉   | 594/861 [08:19<04:57,  1.11s/it]

 69%|██████▉   | 595/861 [08:20<04:15,  1.04it/s]

 69%|██████▉   | 596/861 [08:20<03:31,  1.25it/s]

 69%|██████▉   | 597/861 [08:21<03:13,  1.36it/s]

 69%|██████▉   | 598/861 [08:22<03:34,  1.22it/s]

 70%|██████▉   | 599/861 [08:22<03:39,  1.19it/s]

 70%|██████▉   | 600/861 [08:23<03:25,  1.27it/s]

 70%|██████▉   | 601/861 [08:24<03:14,  1.33it/s]

 70%|██████▉   | 602/861 [08:25<04:27,  1.03s/it]

 70%|███████   | 603/861 [08:27<04:48,  1.12s/it]

 70%|███████   | 604/861 [08:28<04:36,  1.08s/it]

 70%|███████   | 605/861 [08:28<03:56,  1.08it/s]

 70%|███████   | 606/861 [08:29<03:51,  1.10it/s]

 70%|███████   | 607/861 [08:30<03:35,  1.18it/s]

 71%|███████   | 608/861 [08:31<03:20,  1.26it/s]

 71%|███████   | 609/861 [08:31<03:21,  1.25it/s]

 71%|███████   | 610/861 [08:33<04:15,  1.02s/it]

 71%|███████   | 611/861 [08:34<04:16,  1.03s/it]

 71%|███████   | 612/861 [08:35<04:06,  1.01it/s]

 71%|███████   | 613/861 [08:35<03:30,  1.18it/s]

 71%|███████▏  | 614/861 [08:37<04:08,  1.00s/it]

 71%|███████▏  | 615/861 [08:38<04:24,  1.07s/it]

 72%|███████▏  | 616/861 [08:40<05:59,  1.47s/it]

 72%|███████▏  | 617/861 [08:42<05:42,  1.40s/it]

 72%|███████▏  | 618/861 [08:43<05:26,  1.35s/it]

 72%|███████▏  | 619/861 [08:44<05:18,  1.32s/it]

 72%|███████▏  | 620/861 [08:46<05:38,  1.40s/it]

 72%|███████▏  | 621/861 [08:47<05:18,  1.33s/it]

 72%|███████▏  | 622/861 [08:47<04:17,  1.08s/it]

 72%|███████▏  | 623/861 [08:49<04:58,  1.25s/it]

 72%|███████▏  | 624/861 [08:50<04:12,  1.07s/it]

 73%|███████▎  | 625/861 [08:50<03:37,  1.09it/s]

 73%|███████▎  | 626/861 [08:51<03:25,  1.15it/s]

 73%|███████▎  | 627/861 [08:52<03:31,  1.11it/s]

 73%|███████▎  | 628/861 [08:53<03:43,  1.04it/s]

 73%|███████▎  | 629/861 [08:54<03:56,  1.02s/it]

 73%|███████▎  | 630/861 [08:55<03:27,  1.12it/s]

 73%|███████▎  | 631/861 [08:55<02:48,  1.36it/s]

 73%|███████▎  | 632/861 [08:57<04:01,  1.06s/it]

 74%|███████▎  | 633/861 [08:58<03:42,  1.03it/s]

 74%|███████▎  | 634/861 [08:59<04:31,  1.20s/it]

 74%|███████▍  | 635/861 [09:01<04:38,  1.23s/it]

 74%|███████▍  | 636/861 [09:02<04:05,  1.09s/it]

 74%|███████▍  | 637/861 [09:02<03:41,  1.01it/s]

 74%|███████▍  | 638/861 [09:03<03:33,  1.04it/s]

 74%|███████▍  | 639/861 [09:05<04:12,  1.14s/it]

 74%|███████▍  | 640/861 [09:05<03:43,  1.01s/it]

 74%|███████▍  | 641/861 [09:06<03:25,  1.07it/s]

 75%|███████▍  | 642/861 [09:07<03:34,  1.02it/s]

 75%|███████▍  | 643/861 [09:08<03:40,  1.01s/it]

 75%|███████▍  | 644/861 [09:09<03:38,  1.01s/it]

 75%|███████▍  | 645/861 [09:10<02:54,  1.24it/s]

 75%|███████▌  | 646/861 [09:10<02:39,  1.35it/s]

 75%|███████▌  | 647/861 [09:11<02:31,  1.42it/s]

 75%|███████▌  | 648/861 [09:12<02:48,  1.26it/s]

 75%|███████▌  | 649/861 [09:13<02:35,  1.37it/s]

 75%|███████▌  | 650/861 [09:13<02:14,  1.57it/s]

 76%|███████▌  | 651/861 [09:13<01:56,  1.80it/s]

 76%|███████▌  | 652/861 [09:14<02:18,  1.51it/s]

 76%|███████▌  | 653/861 [09:15<02:06,  1.64it/s]

 76%|███████▌  | 654/861 [09:15<02:08,  1.61it/s]

 76%|███████▌  | 655/861 [09:16<01:49,  1.88it/s]

 76%|███████▌  | 656/861 [09:16<01:39,  2.07it/s]

 76%|███████▋  | 657/861 [09:17<01:38,  2.08it/s]

 76%|███████▋  | 658/861 [09:18<02:12,  1.53it/s]

 77%|███████▋  | 659/861 [09:18<02:01,  1.66it/s]

 77%|███████▋  | 660/861 [09:19<02:06,  1.59it/s]

 77%|███████▋  | 661/861 [09:19<01:51,  1.80it/s]

 77%|███████▋  | 662/861 [09:20<02:07,  1.56it/s]

 77%|███████▋  | 663/861 [09:22<03:31,  1.07s/it]

 77%|███████▋  | 664/861 [09:23<02:57,  1.11it/s]

 77%|███████▋  | 665/861 [09:23<02:23,  1.36it/s]

 77%|███████▋  | 666/861 [09:23<01:56,  1.68it/s]

 77%|███████▋  | 667/861 [09:24<02:08,  1.51it/s]

 78%|███████▊  | 668/861 [09:24<01:58,  1.64it/s]

 78%|███████▊  | 669/861 [09:25<01:40,  1.90it/s]

 78%|███████▊  | 670/861 [09:25<01:46,  1.79it/s]

 78%|███████▊  | 671/861 [09:26<01:28,  2.14it/s]

 78%|███████▊  | 672/861 [09:27<02:27,  1.28it/s]

 78%|███████▊  | 673/861 [09:28<02:13,  1.41it/s]

 78%|███████▊  | 674/861 [09:28<01:45,  1.77it/s]

 78%|███████▊  | 675/861 [09:29<02:09,  1.43it/s]

 79%|███████▊  | 676/861 [09:29<01:55,  1.60it/s]

 79%|███████▊  | 677/861 [09:30<01:48,  1.70it/s]

 79%|███████▊  | 678/861 [09:30<01:39,  1.85it/s]

 79%|███████▉  | 679/861 [09:31<01:25,  2.12it/s]

 79%|███████▉  | 680/861 [09:31<01:13,  2.46it/s]

 79%|███████▉  | 681/861 [09:31<01:15,  2.39it/s]

 79%|███████▉  | 682/861 [09:32<01:37,  1.83it/s]

 79%|███████▉  | 683/861 [09:33<01:36,  1.84it/s]

 79%|███████▉  | 684/861 [09:33<01:34,  1.88it/s]

 80%|███████▉  | 685/861 [09:34<01:37,  1.80it/s]

 80%|███████▉  | 686/861 [09:34<01:30,  1.93it/s]

 80%|███████▉  | 687/861 [09:36<02:40,  1.08it/s]

 80%|███████▉  | 688/861 [09:37<02:08,  1.34it/s]

 80%|████████  | 689/861 [09:37<02:03,  1.39it/s]

 80%|████████  | 690/861 [09:38<01:48,  1.57it/s]

 80%|████████  | 691/861 [09:38<01:46,  1.59it/s]

 80%|████████  | 692/861 [09:39<01:34,  1.79it/s]

 80%|████████  | 693/861 [09:39<01:33,  1.80it/s]

 81%|████████  | 694/861 [09:39<01:20,  2.07it/s]

 81%|████████  | 695/861 [09:40<01:18,  2.12it/s]

 81%|████████  | 696/861 [09:40<01:07,  2.44it/s]

 81%|████████  | 697/861 [09:41<01:15,  2.18it/s]

 81%|████████  | 698/861 [09:42<01:32,  1.76it/s]

 81%|████████  | 699/861 [09:42<01:36,  1.68it/s]

 81%|████████▏ | 700/861 [09:43<01:40,  1.61it/s]

 81%|████████▏ | 701/861 [09:44<01:47,  1.49it/s]

 82%|████████▏ | 702/861 [09:44<01:45,  1.51it/s]

 82%|████████▏ | 703/861 [09:45<01:29,  1.77it/s]

 82%|████████▏ | 704/861 [09:45<01:26,  1.82it/s]

 82%|████████▏ | 705/861 [09:46<01:16,  2.03it/s]

 82%|████████▏ | 706/861 [09:46<01:14,  2.09it/s]

 82%|████████▏ | 707/861 [09:46<01:07,  2.26it/s]

 82%|████████▏ | 708/861 [09:47<01:02,  2.46it/s]

 82%|████████▏ | 709/861 [09:47<01:00,  2.50it/s]

 82%|████████▏ | 710/861 [09:48<01:19,  1.91it/s]

 83%|████████▎ | 711/861 [09:48<01:17,  1.94it/s]

 83%|████████▎ | 712/861 [09:49<01:09,  2.14it/s]

 83%|████████▎ | 713/861 [09:49<01:01,  2.42it/s]

 83%|████████▎ | 714/861 [09:50<01:12,  2.03it/s]

 83%|████████▎ | 715/861 [09:51<01:41,  1.44it/s]

 83%|████████▎ | 716/861 [09:52<01:52,  1.28it/s]

 83%|████████▎ | 717/861 [09:52<01:45,  1.37it/s]

 83%|████████▎ | 718/861 [09:53<01:57,  1.22it/s]

 84%|████████▎ | 719/861 [09:54<01:43,  1.37it/s]

 84%|████████▎ | 720/861 [09:54<01:29,  1.57it/s]

 84%|████████▎ | 721/861 [09:55<01:24,  1.65it/s]

 84%|████████▍ | 722/861 [09:56<01:26,  1.60it/s]

 84%|████████▍ | 723/861 [09:56<01:15,  1.83it/s]

 84%|████████▍ | 724/861 [09:57<01:14,  1.85it/s]

 84%|████████▍ | 725/861 [09:57<01:13,  1.84it/s]

 84%|████████▍ | 726/861 [09:58<01:24,  1.60it/s]

 84%|████████▍ | 727/861 [09:59<01:44,  1.28it/s]

 85%|████████▍ | 728/861 [10:00<01:43,  1.28it/s]

 85%|████████▍ | 729/861 [10:00<01:31,  1.45it/s]

 85%|████████▍ | 730/861 [10:01<01:18,  1.67it/s]

 85%|████████▍ | 731/861 [10:02<02:03,  1.05it/s]

 85%|████████▌ | 732/861 [10:03<01:45,  1.23it/s]

 85%|████████▌ | 733/861 [10:04<01:41,  1.26it/s]

 85%|████████▌ | 734/861 [10:04<01:19,  1.59it/s]

 85%|████████▌ | 735/861 [10:04<01:12,  1.74it/s]

 85%|████████▌ | 736/861 [10:05<01:10,  1.77it/s]

 86%|████████▌ | 737/861 [10:06<01:18,  1.58it/s]

 86%|████████▌ | 738/861 [10:06<01:12,  1.69it/s]

 86%|████████▌ | 739/861 [10:07<01:04,  1.89it/s]

 86%|████████▌ | 740/861 [10:07<01:07,  1.78it/s]

 86%|████████▌ | 741/861 [10:08<01:06,  1.82it/s]

 86%|████████▌ | 742/861 [10:09<01:17,  1.53it/s]

 86%|████████▋ | 743/861 [10:09<01:15,  1.56it/s]

 86%|████████▋ | 744/861 [10:10<01:05,  1.78it/s]

 87%|████████▋ | 745/861 [10:10<01:10,  1.64it/s]

 87%|████████▋ | 746/861 [10:11<00:56,  2.03it/s]

 87%|████████▋ | 747/861 [10:12<01:14,  1.52it/s]

 87%|████████▋ | 748/861 [10:12<01:09,  1.63it/s]

 87%|████████▋ | 749/861 [10:13<01:14,  1.50it/s]

 87%|████████▋ | 750/861 [10:13<00:59,  1.87it/s]

 87%|████████▋ | 751/861 [10:13<00:47,  2.30it/s]

 87%|████████▋ | 752/861 [10:14<01:10,  1.55it/s]

 87%|████████▋ | 753/861 [10:15<01:10,  1.54it/s]

 88%|████████▊ | 754/861 [10:16<01:02,  1.72it/s]

 88%|████████▊ | 755/861 [10:16<00:58,  1.81it/s]

 88%|████████▊ | 756/861 [10:16<00:52,  2.00it/s]

 88%|████████▊ | 757/861 [10:17<01:04,  1.62it/s]

 88%|████████▊ | 758/861 [10:18<01:04,  1.60it/s]

 88%|████████▊ | 759/861 [10:18<01:00,  1.69it/s]

 88%|████████▊ | 760/861 [10:19<01:07,  1.50it/s]

 88%|████████▊ | 761/861 [10:22<01:53,  1.14s/it]

 89%|████████▊ | 762/861 [10:22<01:30,  1.09it/s]

 89%|████████▊ | 763/861 [10:23<01:19,  1.23it/s]

 89%|████████▊ | 764/861 [10:23<01:18,  1.23it/s]

 89%|████████▉ | 765/861 [10:24<01:18,  1.23it/s]

 89%|████████▉ | 766/861 [10:25<01:08,  1.39it/s]

 89%|████████▉ | 767/861 [10:26<01:28,  1.07it/s]

 89%|████████▉ | 768/861 [10:27<01:25,  1.09it/s]

 89%|████████▉ | 769/861 [10:28<01:24,  1.09it/s]

 89%|████████▉ | 770/861 [10:28<01:09,  1.30it/s]

 90%|████████▉ | 771/861 [10:29<01:01,  1.46it/s]

 90%|████████▉ | 772/861 [10:29<00:55,  1.60it/s]

 90%|████████▉ | 773/861 [10:31<01:22,  1.07it/s]

 90%|████████▉ | 774/861 [10:32<01:15,  1.15it/s]

 90%|█████████ | 775/861 [10:33<01:18,  1.09it/s]

 90%|█████████ | 776/861 [10:34<01:16,  1.10it/s]

 90%|█████████ | 777/861 [10:34<01:14,  1.13it/s]

 90%|█████████ | 778/861 [10:35<01:13,  1.14it/s]

 90%|█████████ | 779/861 [10:37<01:20,  1.01it/s]

 91%|█████████ | 780/861 [10:38<01:40,  1.24s/it]

 91%|█████████ | 781/861 [10:41<02:05,  1.56s/it]

 91%|█████████ | 782/861 [10:42<01:57,  1.48s/it]

 91%|█████████ | 783/861 [10:43<01:35,  1.22s/it]

 91%|█████████ | 784/861 [10:43<01:22,  1.07s/it]

 91%|█████████ | 785/861 [10:44<01:12,  1.04it/s]

 91%|█████████▏| 786/861 [10:45<01:09,  1.08it/s]

 91%|█████████▏| 787/861 [10:45<00:59,  1.24it/s]

 92%|█████████▏| 788/861 [10:46<00:55,  1.31it/s]

 92%|█████████▏| 789/861 [10:47<00:56,  1.27it/s]

 92%|█████████▏| 790/861 [10:48<00:55,  1.29it/s]

 92%|█████████▏| 791/861 [10:48<00:46,  1.52it/s]

 92%|█████████▏| 792/861 [10:49<00:45,  1.52it/s]

 92%|█████████▏| 793/861 [10:49<00:44,  1.52it/s]

 92%|█████████▏| 794/861 [10:50<00:41,  1.60it/s]

 92%|█████████▏| 795/861 [10:51<00:43,  1.51it/s]

 92%|█████████▏| 796/861 [10:51<00:36,  1.78it/s]

 93%|█████████▎| 797/861 [10:52<00:42,  1.52it/s]

 93%|█████████▎| 798/861 [10:52<00:35,  1.77it/s]

 93%|█████████▎| 799/861 [10:53<00:32,  1.88it/s]

 93%|█████████▎| 800/861 [10:53<00:35,  1.73it/s]

 93%|█████████▎| 801/861 [10:55<00:47,  1.26it/s]

 93%|█████████▎| 802/861 [10:55<00:40,  1.44it/s]

 93%|█████████▎| 803/861 [10:56<00:52,  1.11it/s]

 93%|█████████▎| 804/861 [10:58<00:59,  1.05s/it]

 93%|█████████▎| 805/861 [10:59<01:01,  1.10s/it]

 94%|█████████▎| 806/861 [11:00<00:49,  1.11it/s]

 94%|█████████▎| 807/861 [11:01<00:51,  1.04it/s]

 94%|█████████▍| 808/861 [11:02<00:59,  1.12s/it]

 94%|█████████▍| 809/861 [11:03<00:47,  1.08it/s]

 94%|█████████▍| 810/861 [11:03<00:39,  1.29it/s]

 94%|█████████▍| 811/861 [11:04<00:39,  1.28it/s]

 94%|█████████▍| 812/861 [11:04<00:36,  1.35it/s]

 94%|█████████▍| 813/861 [11:06<00:42,  1.13it/s]

 95%|█████████▍| 814/861 [11:07<00:43,  1.07it/s]

 95%|█████████▍| 815/861 [11:08<00:43,  1.05it/s]

 95%|█████████▍| 816/861 [11:08<00:38,  1.17it/s]

 95%|█████████▍| 817/861 [11:09<00:37,  1.16it/s]

 95%|█████████▌| 818/861 [11:10<00:39,  1.08it/s]

 95%|█████████▌| 819/861 [11:11<00:34,  1.21it/s]

 95%|█████████▌| 820/861 [11:12<00:35,  1.15it/s]

 95%|█████████▌| 821/861 [11:13<00:36,  1.10it/s]

 95%|█████████▌| 822/861 [11:14<00:40,  1.04s/it]

 96%|█████████▌| 823/861 [11:16<00:49,  1.29s/it]

 96%|█████████▌| 824/861 [11:16<00:38,  1.03s/it]

 96%|█████████▌| 825/861 [11:17<00:31,  1.13it/s]

 96%|█████████▌| 826/861 [11:19<00:37,  1.08s/it]

 96%|█████████▌| 827/861 [11:20<00:36,  1.06s/it]

 96%|█████████▌| 828/861 [11:20<00:28,  1.17it/s]

 96%|█████████▋| 829/861 [11:21<00:31,  1.03it/s]

 96%|█████████▋| 830/861 [11:22<00:30,  1.01it/s]

 97%|█████████▋| 831/861 [11:24<00:33,  1.11s/it]

 97%|█████████▋| 832/861 [11:24<00:27,  1.06it/s]

 97%|█████████▋| 833/861 [11:25<00:23,  1.21it/s]

 97%|█████████▋| 834/861 [11:26<00:23,  1.14it/s]

 97%|█████████▋| 835/861 [11:27<00:22,  1.18it/s]

 97%|█████████▋| 836/861 [11:27<00:21,  1.18it/s]

 97%|█████████▋| 837/861 [11:28<00:22,  1.09it/s]

 97%|█████████▋| 838/861 [11:30<00:23,  1.00s/it]

 97%|█████████▋| 839/861 [11:30<00:19,  1.13it/s]

 98%|█████████▊| 840/861 [11:31<00:15,  1.32it/s]

 98%|█████████▊| 841/861 [11:31<00:14,  1.37it/s]

 98%|█████████▊| 842/861 [11:32<00:12,  1.47it/s]

 98%|█████████▊| 843/861 [11:33<00:12,  1.48it/s]

 98%|█████████▊| 844/861 [11:33<00:11,  1.49it/s]

 98%|█████████▊| 845/861 [11:35<00:13,  1.18it/s]

 98%|█████████▊| 846/861 [11:35<00:11,  1.35it/s]

 98%|█████████▊| 847/861 [11:36<00:11,  1.24it/s]

 98%|█████████▊| 848/861 [11:37<00:11,  1.15it/s]

 99%|█████████▊| 849/861 [11:38<00:10,  1.15it/s]

 99%|█████████▊| 850/861 [11:38<00:08,  1.30it/s]

 99%|█████████▉| 851/861 [11:39<00:07,  1.38it/s]

 99%|█████████▉| 852/861 [11:40<00:06,  1.48it/s]

 99%|█████████▉| 853/861 [11:40<00:05,  1.47it/s]

 99%|█████████▉| 854/861 [11:41<00:04,  1.55it/s]

 99%|█████████▉| 855/861 [11:42<00:04,  1.33it/s]

 99%|█████████▉| 856/861 [11:43<00:04,  1.10it/s]

100%|█████████▉| 857/861 [11:44<00:03,  1.14it/s]

100%|█████████▉| 858/861 [11:44<00:02,  1.30it/s]

100%|█████████▉| 859/861 [11:45<00:01,  1.32it/s]

100%|█████████▉| 860/861 [11:47<00:01,  1.09s/it]

100%|██████████| 861/861 [11:48<00:00,  1.01s/it]{'score': 13.717038040616565, 'counts': [18096, 8507, 4411, 2272], 'totals': [48313, 46591, 44869, 43147], 'precisions': [37.455757249601554, 18.258891202163507, 9.830840892375582, 5.265719517000023], 'bp': 1.0, 'sys_len': 48313, 'ref_len': 32555}

                                                       

                                                 
{'eval_loss': 2.397350311279297, 'eval_bleu': 13.717, 'eval_gen_len': 36.5221, 'eval_runtime': 805.5427, 'eval_samples_per_second': 2.138, 'eval_steps_per_second': 1.069, 'epoch': 16.0}

100%|██████████| 61904/61904 [8:35:01<00:00,  1.35s/it]

100%|██████████| 861/861 [13:24<00:00,  1.01s/it]

                                                 [WARNING|configuration_utils.py:448] 2024-10-29 00:00:41,433 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
[WARNING|trainer.py:2764] 2024-10-29 00:01:14,086 >> There were missing keys in the checkpoint model loaded: ['model.encoder.embed_tokens.weight', 'model.decoder.embed_tokens.weight', 'lm_head.weight'].

                                                       
{'train_runtime': 30950.9119, 'train_samples_per_second': 48.007, 'train_steps_per_second': 2.0, 'train_loss': 0.7644494936952421, 'epoch': 16.0}

100%|██████████| 61904/61904 [8:35:34<00:00,  1.35s/it]
100%|██████████| 61904/61904 [8:35:34<00:00,  2.00it/s]