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 03:01:25.380111: 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 03:01:25.380212: 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 03:01:25.493275: 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: 922 examples [00:00, 6433.39 examples/s]
Generating train split: 2317 examples [00:00, 10185.32 examples/s]
Generating train split: 4128 examples [00:00, 13481.85 examples/s]
Generating train split: 6000 examples [00:00, 15323.47 examples/s]
Generating train split: 7909 examples [00:00, 16621.68 examples/s]
Generating train split: 9761 examples [00:00, 17248.98 examples/s]
Generating train split: 11574 examples [00:00, 17528.82 examples/s]
Generating train split: 13412 examples [00:00, 17795.49 examples/s]
Generating train split: 15290 examples [00:00, 18096.18 examples/s]
Generating train split: 17177 examples [00:01, 18329.44 examples/s]
Generating train split: 19041 examples [00:01, 18421.93 examples/s]
Generating train split: 21000 examples [00:01, 18616.35 examples/s]
Generating train split: 23000 examples [00:01, 18732.77 examples/s]
Generating train split: 25000 examples [00:01, 18806.84 examples/s]
Generating train split: 27000 examples [00:01, 18839.42 examples/s]
Generating train split: 29000 examples [00:01, 18855.58 examples/s]
Generating train split: 31000 examples [00:01, 18831.57 examples/s]
Generating train split: 32981 examples [00:01, 18892.67 examples/s]
Generating train split: 35778 examples [00:02, 18795.14 examples/s]
Generating train split: 38582 examples [00:02, 18756.45 examples/s]
Generating train split: 41305 examples [00:02, 18550.90 examples/s]
Generating train split: 43171 examples [00:02, 18575.52 examples/s]
Generating train split: 45033 examples [00:02, 18585.20 examples/s]
Generating train split: 47000 examples [00:02, 18595.53 examples/s]
Generating train split: 48939 examples [00:02, 18812.09 examples/s]
Generating train split: 51646 examples [00:02, 18525.60 examples/s]
Generating train split: 54403 examples [00:03, 18470.77 examples/s]
Generating train split: 57135 examples [00:03, 18380.09 examples/s]
Generating train split: 59000 examples [00:03, 18306.15 examples/s]
Generating train split: 61000 examples [00:03, 18480.43 examples/s]
Generating train split: 63000 examples [00:03, 18596.82 examples/s]
Generating train split: 65000 examples [00:03, 18704.17 examples/s]
Generating train split: 67000 examples [00:03, 18772.17 examples/s]
Generating train split: 69000 examples [00:03, 18842.38 examples/s]
Generating train split: 70939 examples [00:03, 18992.53 examples/s]
Generating train split: 73724 examples [00:04, 18828.57 examples/s]
Generating train split: 76504 examples [00:04, 18723.29 examples/s]
Generating train split: 79293 examples [00:04, 18677.35 examples/s]
Generating train split: 81806 examples [00:04, 18054.26 examples/s]
Generating train split: 84223 examples [00:04, 17439.43 examples/s]
Generating train split: 86002 examples [00:04, 17518.70 examples/s]
Generating train split: 88398 examples [00:04, 17003.26 examples/s]
Generating train split: 90198 examples [00:05, 17239.93 examples/s]
Generating train split: 92000 examples [00:05, 17413.15 examples/s]
Generating train split: 92867 examples [00:05, 17936.49 examples/s]

Generating validation split: 0 examples [00:00, ? examples/s]
Generating validation split: 1722 examples [00:00, 17696.62 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<02:31, 605.99 examples/s]
Running tokenizer on train dataset:   2%|▏         | 2000/92867 [00:02<01:52, 806.74 examples/s]
Running tokenizer on train dataset:   3%|▎         | 3000/92867 [00:04<02:05, 715.24 examples/s]
Running tokenizer on train dataset:   4%|▍         | 4000/92867 [00:06<02:22, 623.19 examples/s]
Running tokenizer on train dataset:   5%|▌         | 5000/92867 [00:07<02:26, 599.70 examples/s]
Running tokenizer on train dataset:   6%|▋         | 6000/92867 [00:09<02:29, 581.36 examples/s]
Running tokenizer on train dataset:   8%|▊         | 7000/92867 [00:11<02:30, 569.73 examples/s]
Running tokenizer on train dataset:   9%|▊         | 8000/92867 [00:13<02:30, 565.27 examples/s]
Running tokenizer on train dataset:  10%|▉         | 9000/92867 [00:14<02:25, 578.19 examples/s]
Running tokenizer on train dataset:  11%|█         | 10000/92867 [00:16<02:08, 643.84 examples/s]
Running tokenizer on train dataset:  12%|█▏        | 11000/92867 [00:17<01:57, 694.49 examples/s]
Running tokenizer on train dataset:  13%|█▎        | 12000/92867 [00:18<01:53, 712.20 examples/s]
Running tokenizer on train dataset:  14%|█▍        | 13000/92867 [00:19<01:50, 721.69 examples/s]
Running tokenizer on train dataset:  15%|█▌        | 14000/92867 [00:21<01:42, 770.25 examples/s]
Running tokenizer on train dataset:  16%|█▌        | 15000/92867 [00:22<01:37, 797.83 examples/s]
Running tokenizer on train dataset:  17%|█▋        | 16000/92867 [00:23<01:32, 827.12 examples/s]
Running tokenizer on train dataset:  18%|█▊        | 17000/92867 [00:24<01:30, 838.47 examples/s]
Running tokenizer on train dataset:  19%|█▉        | 18000/92867 [00:25<01:29, 837.94 examples/s]
Running tokenizer on train dataset:  20%|██        | 19000/92867 [00:27<01:31, 806.31 examples/s]
Running tokenizer on train dataset:  22%|██▏       | 20000/92867 [00:28<01:28, 819.03 examples/s]
Running tokenizer on train dataset:  23%|██▎       | 21000/92867 [00:29<01:26, 832.06 examples/s]
Running tokenizer on train dataset:  24%|██▎       | 22000/92867 [00:30<01:25, 827.69 examples/s]
Running tokenizer on train dataset:  25%|██▍       | 23000/92867 [00:31<01:27, 801.00 examples/s]
Running tokenizer on train dataset:  26%|██▌       | 24000/92867 [00:33<01:27, 785.71 examples/s]
Running tokenizer on train dataset:  27%|██▋       | 25000/92867 [00:34<01:26, 788.04 examples/s]
Running tokenizer on train dataset:  28%|██▊       | 26000/92867 [00:35<01:25, 779.05 examples/s]
Running tokenizer on train dataset:  29%|██▉       | 27000/92867 [00:37<01:24, 775.75 examples/s]
Running tokenizer on train dataset:  30%|███       | 28000/92867 [00:38<01:27, 740.93 examples/s]
Running tokenizer on train dataset:  31%|███       | 29000/92867 [00:40<01:28, 720.58 examples/s]
Running tokenizer on train dataset:  32%|███▏      | 30000/92867 [00:41<01:28, 713.83 examples/s]
Running tokenizer on train dataset:  33%|███▎      | 31000/92867 [00:43<01:28, 698.05 examples/s]
Running tokenizer on train dataset:  34%|███▍      | 32000/92867 [00:44<01:31, 666.30 examples/s]
Running tokenizer on train dataset:  36%|███▌      | 33000/92867 [00:46<01:30, 660.94 examples/s]
Running tokenizer on train dataset:  37%|███▋      | 34000/92867 [00:47<01:30, 649.72 examples/s]
Running tokenizer on train dataset:  38%|███▊      | 35000/92867 [00:49<01:30, 640.29 examples/s]
Running tokenizer on train dataset:  39%|███▉      | 36000/92867 [00:51<01:29, 633.33 examples/s]
Running tokenizer on train dataset:  40%|███▉      | 37000/92867 [00:52<01:25, 650.05 examples/s]
Running tokenizer on train dataset:  41%|████      | 38000/92867 [00:53<01:22, 663.41 examples/s]
Running tokenizer on train dataset:  42%|████▏     | 39000/92867 [00:55<01:21, 663.95 examples/s]
Running tokenizer on train dataset:  43%|████▎     | 40000/92867 [00:57<01:22, 638.83 examples/s]
Running tokenizer on train dataset:  44%|████▍     | 41000/92867 [00:59<01:34, 548.92 examples/s]
Running tokenizer on train dataset:  45%|████▌     | 42000/92867 [01:01<01:31, 553.97 examples/s]
Running tokenizer on train dataset:  46%|████▋     | 43000/92867 [01:02<01:27, 570.21 examples/s]
Running tokenizer on train dataset:  47%|████▋     | 44000/92867 [01:04<01:21, 596.21 examples/s]
Running tokenizer on train dataset:  48%|████▊     | 45000/92867 [01:06<01:20, 596.85 examples/s]
Running tokenizer on train dataset:  50%|████▉     | 46000/92867 [01:07<01:18, 593.77 examples/s]
Running tokenizer on train dataset:  51%|█████     | 47000/92867 [01:09<01:15, 607.94 examples/s]
Running tokenizer on train dataset:  52%|█████▏    | 48000/92867 [01:11<01:16, 588.34 examples/s]
Running tokenizer on train dataset:  53%|█████▎    | 49000/92867 [01:12<01:11, 611.58 examples/s]
Running tokenizer on train dataset:  54%|█████▍    | 50000/92867 [01:14<01:13, 579.86 examples/s]
Running tokenizer on train dataset:  55%|█████▍    | 51000/92867 [01:16<01:16, 550.83 examples/s]
Running tokenizer on train dataset:  56%|█████▌    | 52000/92867 [01:18<01:14, 548.63 examples/s]
Running tokenizer on train dataset:  57%|█████▋    | 53000/92867 [01:20<01:15, 529.32 examples/s]
Running tokenizer on train dataset:  58%|█████▊    | 54000/92867 [01:22<01:11, 543.76 examples/s]
Running tokenizer on train dataset:  59%|█████▉    | 55000/92867 [01:23<01:07, 556.96 examples/s]
Running tokenizer on train dataset:  60%|██████    | 56000/92867 [01:26<01:09, 527.35 examples/s]
Running tokenizer on train dataset:  61%|██████▏   | 57000/92867 [01:28<01:10, 511.75 examples/s]
Running tokenizer on train dataset:  62%|██████▏   | 58000/92867 [01:30<01:09, 502.06 examples/s]
Running tokenizer on train dataset:  64%|██████▎   | 59000/92867 [01:32<01:07, 501.65 examples/s]
Running tokenizer on train dataset:  65%|██████▍   | 60000/92867 [01:33<00:59, 556.71 examples/s]
Running tokenizer on train dataset:  66%|██████▌   | 61000/92867 [01:35<00:53, 596.34 examples/s]
Running tokenizer on train dataset:  67%|██████▋   | 62000/92867 [01:36<00:49, 619.32 examples/s]
Running tokenizer on train dataset:  68%|██████▊   | 63000/92867 [01:37<00:45, 658.08 examples/s]
Running tokenizer on train dataset:  69%|██████▉   | 64000/92867 [01:39<00:41, 697.27 examples/s]
Running tokenizer on train dataset:  70%|██████▉   | 65000/92867 [01:40<00:39, 708.97 examples/s]
Running tokenizer on train dataset:  71%|███████   | 66000/92867 [01:41<00:37, 718.53 examples/s]
Running tokenizer on train dataset:  72%|███████▏  | 67000/92867 [01:43<00:36, 709.33 examples/s]
Running tokenizer on train dataset:  73%|███████▎  | 68000/92867 [01:44<00:34, 720.09 examples/s]
Running tokenizer on train dataset:  74%|███████▍  | 69000/92867 [01:45<00:32, 726.27 examples/s]
Running tokenizer on train dataset:  75%|███████▌  | 70000/92867 [01:47<00:32, 704.84 examples/s]
Running tokenizer on train dataset:  76%|███████▋  | 71000/92867 [01:48<00:31, 697.32 examples/s]
Running tokenizer on train dataset:  78%|███████▊  | 72000/92867 [01:50<00:30, 682.87 examples/s]
Running tokenizer on train dataset:  79%|███████▊  | 73000/92867 [01:52<00:30, 659.59 examples/s]
Running tokenizer on train dataset:  80%|███████▉  | 74000/92867 [01:53<00:29, 640.25 examples/s]
Running tokenizer on train dataset:  81%|████████  | 75000/92867 [01:55<00:28, 631.43 examples/s]
Running tokenizer on train dataset:  82%|████████▏ | 76000/92867 [01:57<00:27, 602.84 examples/s]
Running tokenizer on train dataset:  83%|████████▎ | 77000/92867 [01:58<00:26, 594.84 examples/s]
Running tokenizer on train dataset:  84%|████████▍ | 78000/92867 [02:00<00:25, 580.37 examples/s]
Running tokenizer on train dataset:  85%|████████▌ | 79000/92867 [02:02<00:24, 577.02 examples/s]
Running tokenizer on train dataset:  86%|████████▌ | 80000/92867 [02:04<00:22, 575.19 examples/s]
Running tokenizer on train dataset:  87%|████████▋ | 81000/92867 [02:05<00:20, 583.40 examples/s]
Running tokenizer on train dataset:  88%|████████▊ | 82000/92867 [02:07<00:18, 599.78 examples/s]
Running tokenizer on train dataset:  89%|████████▉ | 83000/92867 [02:10<00:19, 515.76 examples/s]
Running tokenizer on train dataset:  90%|█████████ | 84000/92867 [02:11<00:17, 512.73 examples/s]
Running tokenizer on train dataset:  92%|█████████▏| 85000/92867 [02:13<00:14, 534.69 examples/s]
Running tokenizer on train dataset:  93%|█████████▎| 86000/92867 [02:15<00:12, 553.96 examples/s]
Running tokenizer on train dataset:  94%|█████████▎| 87000/92867 [02:17<00:10, 548.61 examples/s]
Running tokenizer on train dataset:  95%|█████████▍| 88000/92867 [02:18<00:08, 556.68 examples/s]
Running tokenizer on train dataset:  96%|█████████▌| 89000/92867 [02:20<00:07, 543.31 examples/s]
Running tokenizer on train dataset:  97%|█████████▋| 90000/92867 [02:22<00:05, 554.15 examples/s]
Running tokenizer on train dataset:  98%|█████████▊| 91000/92867 [02:24<00:03, 513.19 examples/s]
Running tokenizer on train dataset:  99%|█████████▉| 92000/92867 [02:26<00:01, 507.57 examples/s]
Running tokenizer on train dataset: 100%|██████████| 92867/92867 [02:28<00:00, 498.52 examples/s]
Running tokenizer on train dataset: 100%|██████████| 92867/92867 [02:28<00:00, 624.37 examples/s]
Saving cached train data ...

Saving the dataset (0/1 shards):   0%|          | 0/92867 [00:00<?, ? examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 92867/92867 [00:00<00:00, 965990.36 examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 92867/92867 [00:00<00:00, 963788.99 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, 553.59 examples/s]
Running tokenizer on validation dataset: 100%|██████████| 1722/1722 [00:03<00:00, 539.41 examples/s]
Running tokenizer on validation dataset: 100%|██████████| 1722/1722 [00:03<00:00, 541.08 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, 319033.15 examples/s]
Saving the dataset (1/1 shards): 100%|██████████| 1722/1722 [00:00<00:00, 308763.32 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, 19.9MB/s]
[WARNING|trainer.py:2764] 2024-10-28 03:04:19,967 >> 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_030425-uweeff6i
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/uweeff6i

  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)

 31%|███▏      | 19348/61904 [00:03<00:06, 6346.47it/s]
 31%|███▏      | 19359/61904 [00:19<00:06, 6346.47it/s]
 31%|███▏      | 19360/61904 [00:19<00:58, 727.78it/s] 
                                                      
{'loss': 2.6522, 'learning_rate': 1.6894852845844678e-07, 'epoch': 5.0}

 31%|███▏      | 19360/61904 [00:19<00:58, 727.78it/s]
 31%|███▏      | 19361/61904 [00:20<01:04, 654.84it/s]
 31%|███▏      | 19373/61904 [00:39<01:04, 654.84it/s]
 31%|███▏      | 19374/61904 [00:39<03:01, 234.11it/s]
 31%|███▏      | 19375/61904 [00:40<03:13, 219.89it/s]
                                                      
{'loss': 2.6008, 'learning_rate': 1.6891611564890445e-07, 'epoch': 5.01}

 31%|███▏      | 19380/61904 [00:47<03:13, 219.89it/s]
 31%|███▏      | 19388/61904 [00:59<03:13, 219.89it/s]
 31%|███▏      | 19389/61904 [01:00<07:27, 94.93it/s] 
 31%|███▏      | 19390/61904 [01:01<07:53, 89.80it/s]
                                                     
{'loss': 2.6294, 'learning_rate': 1.688837028393621e-07, 'epoch': 5.01}

 31%|███▏      | 19400/61904 [01:16<07:53, 89.80it/s]
 31%|███▏      | 19402/61904 [01:19<07:53, 89.80it/s]
 31%|███▏      | 19403/61904 [01:20<15:53, 44.57it/s]
 31%|███▏      | 19404/61904 [01:21<16:43, 42.36it/s]
 31%|███▏      | 19416/61904 [01:39<16:43, 42.36it/s]
 31%|███▏      | 19417/61904 [01:40<32:45, 21.62it/s]
 31%|███▏      | 19418/61904 [01:41<34:16, 20.66it/s]
                                                     
{'loss': 2.6519, 'learning_rate': 1.6885129002981977e-07, 'epoch': 5.02}

 31%|███▏      | 19420/61904 [01:44<34:16, 20.66it/s]
 31%|███▏      | 19430/61904 [01:59<34:15, 20.66it/s]
 31%|███▏      | 19431/61904 [01:59<1:04:25, 10.99it/s]
 31%|███▏      | 19432/61904 [02:00<1:07:45, 10.45it/s]
                                                       
{'loss': 2.6537, 'learning_rate': 1.6881887722027743e-07, 'epoch': 5.02}

 31%|███▏      | 19440/61904 [02:11<1:07:45, 10.45it/s]
 31%|███▏      | 19445/61904 [02:19<1:07:44, 10.45it/s]
 31%|███▏      | 19446/61904 [02:19<2:06:09,  5.61it/s]
 31%|███▏      | 19447/61904 [02:21<2:12:09,  5.35it/s]
 31%|███▏      | 19459/61904 [02:39<2:12:06,  5.35it/s]
 31%|███▏      | 19460/61904 [02:39<3:43:38,  3.16it/s]
                                                       
{'loss': 2.6256, 'learning_rate': 1.6878646441073512e-07, 'epoch': 5.03}

 31%|███▏      | 19460/61904 [02:39<3:43:38,  3.16it/s]
 31%|███▏      | 19461/61904 [02:40<3:53:15,  3.03it/s]
 31%|███▏      | 19473/61904 [02:57<5:59:54,  1.96it/s]
 31%|███▏      | 19474/61904 [02:58<6:10:46,  1.91it/s]
                                                       
{'loss': 2.6721, 'learning_rate': 1.6875405160119278e-07, 'epoch': 5.03}

 31%|███▏      | 19480/61904 [03:06<6:10:43,  1.91it/s]
 31%|███▏      | 19481/61904 [03:09<6:10:42,  1.91it/s]
 31%|███▏      | 19482/61904 [03:09<8:00:05,  1.47it/s]
 31%|███▏      | 19483/61904 [03:10<8:16:36,  1.42it/s]
 31%|███▏      | 19489/61904 [03:19<10:08:20,  1.16it/s]
 31%|███▏      | 19493/61904 [03:25<11:09:54,  1.06it/s]
 31%|███▏      | 19496/61904 [03:29<11:58:34,  1.02s/it]
 31%|███▏      | 19498/61904 [03:31<12:22:21,  1.05s/it]
 32%|███▏      | 19500/61904 [03:34<13:14:06,  1.12s/it]
                                                        
{'loss': 2.6894, 'learning_rate': 1.6872163879165044e-07, 'epoch': 5.04}

 32%|███▏      | 19500/61904 [03:34<13:14:06,  1.12s/it]
 32%|███▏      | 19501/61904 [03:36<13:27:17,  1.14s/it]
 32%|███▏      | 19502/61904 [03:37<13:41:55,  1.16s/it]
 32%|███▏      | 19503/61904 [03:38<14:02:35,  1.19s/it]
 32%|███▏      | 19504/61904 [03:40<14:30:03,  1.23s/it]
 32%|███▏      | 19505/61904 [03:41<15:08:06,  1.29s/it]
 32%|███▏      | 19506/61904 [03:43<15:28:17,  1.31s/it]
 32%|███▏      | 19507/61904 [03:44<15:52:21,  1.35s/it]
 32%|███▏      | 19508/61904 [03:46<16:00:16,  1.36s/it]
 32%|███▏      | 19509/61904 [03:47<15:53:15,  1.35s/it]
 32%|███▏      | 19510/61904 [03:48<15:35:45,  1.32s/it]
 32%|███▏      | 19511/61904 [03:50<15:53:27,  1.35s/it]
 32%|███▏      | 19512/61904 [03:51<16:04:14,  1.36s/it]
 32%|███▏      | 19513/61904 [03:52<16:01:41,  1.36s/it]
 32%|███▏      | 19514/61904 [03:54<15:55:47,  1.35s/it]
 32%|███▏      | 19515/61904 [03:55<16:09:03,  1.37s/it]
 32%|███▏      | 19516/61904 [03:56<15:41:56,  1.33s/it]
 32%|███▏      | 19517/61904 [03:58<16:03:42,  1.36s/it]
 32%|███▏      | 19518/61904 [03:59<15:51:14,  1.35s/it]
 32%|███▏      | 19519/61904 [04:00<16:05:31,  1.37s/it]
 32%|███▏      | 19520/61904 [04:02<16:34:30,  1.41s/it]
                                                        
{'loss': 2.6702, 'learning_rate': 1.6868922598210813e-07, 'epoch': 5.05}

 32%|███▏      | 19520/61904 [04:02<16:34:30,  1.41s/it]
 32%|███▏      | 19521/61904 [04:03<16:31:52,  1.40s/it]
 32%|███▏      | 19522/61904 [04:05<16:29:42,  1.40s/it]
 32%|███▏      | 19523/61904 [04:06<16:33:25,  1.41s/it]
 32%|███▏      | 19524/61904 [04:08<16:28:35,  1.40s/it]
 32%|███▏      | 19525/61904 [04:09<16:56:54,  1.44s/it]
 32%|███▏      | 19526/61904 [04:11<16:53:47,  1.44s/it]
 32%|███▏      | 19527/61904 [04:12<16:22:08,  1.39s/it]
 32%|███▏      | 19528/61904 [04:13<16:40:50,  1.42s/it]
 32%|███▏      | 19529/61904 [04:15<16:20:50,  1.39s/it]
 32%|███▏      | 19530/61904 [04:16<16:41:47,  1.42s/it]
 32%|███▏      | 19531/61904 [04:17<16:23:23,  1.39s/it]
 32%|███▏      | 19532/61904 [04:19<16:04:26,  1.37s/it]
 32%|███▏      | 19533/61904 [04:20<15:58:19,  1.36s/it]
 32%|███▏      | 19534/61904 [04:22<16:15:03,  1.38s/it]
 32%|███▏      | 19535/61904 [04:23<16:00:42,  1.36s/it]
 32%|███▏      | 19536/61904 [04:24<15:55:49,  1.35s/it]
 32%|███▏      | 19537/61904 [04:26<16:31:01,  1.40s/it]
 32%|███▏      | 19538/61904 [04:27<16:34:48,  1.41s/it]
 32%|███▏      | 19539/61904 [04:28<16:25:13,  1.40s/it]
 32%|███▏      | 19540/61904 [04:30<16:15:58,  1.38s/it]
                                                        
{'loss': 2.7041, 'learning_rate': 1.686568131725658e-07, 'epoch': 5.05}

 32%|███▏      | 19540/61904 [04:30<16:15:58,  1.38s/it]
 32%|███▏      | 19541/61904 [04:31<16:32:38,  1.41s/it]
 32%|███▏      | 19542/61904 [04:33<16:34:29,  1.41s/it]
 32%|███▏      | 19543/61904 [04:34<16:14:12,  1.38s/it]
 32%|███▏      | 19544/61904 [04:35<16:19:43,  1.39s/it]
 32%|███▏      | 19545/61904 [04:37<16:19:04,  1.39s/it]
 32%|███▏      | 19546/61904 [04:38<16:03:55,  1.37s/it]
 32%|███▏      | 19547/61904 [04:40<16:30:00,  1.40s/it]
 32%|███▏      | 19548/61904 [04:41<16:18:06,  1.39s/it]
 32%|███▏      | 19549/61904 [04:42<15:40:48,  1.33s/it]
 32%|███▏      | 19550/61904 [04:44<15:52:48,  1.35s/it]
 32%|███▏      | 19551/61904 [04:45<16:05:21,  1.37s/it]
 32%|███▏      | 19552/61904 [04:46<16:05:00,  1.37s/it]
 32%|███▏      | 19553/61904 [04:48<15:43:03,  1.34s/it]
 32%|███▏      | 19554/61904 [04:49<15:53:31,  1.35s/it]
 32%|███▏      | 19555/61904 [04:50<16:06:37,  1.37s/it]
 32%|███▏      | 19556/61904 [04:52<16:12:14,  1.38s/it]
 32%|███▏      | 19557/61904 [04:53<16:28:00,  1.40s/it]
 32%|███▏      | 19558/61904 [04:55<16:19:41,  1.39s/it]
 32%|███▏      | 19559/61904 [04:56<15:51:54,  1.35s/it]
 32%|███▏      | 19560/61904 [04:57<16:09:05,  1.37s/it]
                                                        
{'loss': 2.7243, 'learning_rate': 1.6862440036302346e-07, 'epoch': 5.06}

 32%|███▏      | 19560/61904 [04:57<16:09:05,  1.37s/it]
 32%|███▏      | 19561/61904 [04:59<16:00:45,  1.36s/it]
 32%|███▏      | 19562/61904 [05:00<16:42:38,  1.42s/it]
 32%|███▏      | 19563/61904 [05:02<16:23:30,  1.39s/it]
 32%|███▏      | 19564/61904 [05:03<16:25:41,  1.40s/it]
 32%|███▏      | 19565/61904 [05:04<16:02:37,  1.36s/it]
 32%|███▏      | 19566/61904 [05:06<16:22:33,  1.39s/it]
 32%|███▏      | 19567/61904 [05:07<16:22:00,  1.39s/it]
 32%|███▏      | 19568/61904 [05:08<16:18:03,  1.39s/it]
 32%|███▏      | 19569/61904 [05:10<16:37:35,  1.41s/it]
 32%|███▏      | 19570/61904 [05:11<16:48:15,  1.43s/it]
 32%|███▏      | 19571/61904 [05:13<16:53:03,  1.44s/it]
 32%|███▏      | 19572/61904 [05:14<16:57:06,  1.44s/it]
 32%|███▏      | 19573/61904 [05:16<16:51:07,  1.43s/it]
 32%|███▏      | 19574/61904 [05:17<16:41:40,  1.42s/it]
 32%|███▏      | 19575/61904 [05:19<17:02:11,  1.45s/it]
 32%|███▏      | 19576/61904 [05:20<16:40:03,  1.42s/it]
 32%|███▏      | 19577/61904 [05:21<16:29:08,  1.40s/it]
 32%|███▏      | 19578/61904 [05:23<16:26:48,  1.40s/it]
 32%|███▏      | 19579/61904 [05:24<16:43:06,  1.42s/it]
 32%|███▏      | 19580/61904 [05:25<16:22:13,  1.39s/it]
                                                        
{'loss': 2.7082, 'learning_rate': 1.6859198755348114e-07, 'epoch': 5.06}

 32%|███▏      | 19580/61904 [05:26<16:22:13,  1.39s/it]
 32%|███▏      | 19581/61904 [05:27<16:19:14,  1.39s/it]
 32%|███▏      | 19582/61904 [05:28<16:09:48,  1.37s/it]
 32%|███▏      | 19583/61904 [05:30<16:24:10,  1.40s/it]
 32%|███▏      | 19584/61904 [05:31<16:08:36,  1.37s/it]
 32%|███▏      | 19585/61904 [05:32<16:23:52,  1.39s/it]
 32%|███▏      | 19586/61904 [05:34<16:22:06,  1.39s/it]
 32%|███▏      | 19587/61904 [05:35<16:23:56,  1.40s/it]
 32%|███▏      | 19588/61904 [05:37<16:28:48,  1.40s/it]
 32%|███▏      | 19589/61904 [05:38<16:52:52,  1.44s/it]
 32%|███▏      | 19590/61904 [05:40<16:35:50,  1.41s/it]
 32%|███▏      | 19591/61904 [05:41<16:29:43,  1.40s/it]
 32%|███▏      | 19592/61904 [05:42<16:02:28,  1.36s/it]
 32%|███▏      | 19593/61904 [05:44<16:14:17,  1.38s/it]
 32%|███▏      | 19594/61904 [05:45<15:55:26,  1.35s/it]
 32%|███▏      | 19595/61904 [05:46<16:09:06,  1.37s/it]
 32%|███▏      | 19596/61904 [05:48<16:28:39,  1.40s/it]
 32%|███▏      | 19597/61904 [05:49<16:58:13,  1.44s/it]
 32%|███▏      | 19598/61904 [05:51<16:46:21,  1.43s/it]
 32%|███▏      | 19599/61904 [05:52<16:47:30,  1.43s/it]
 32%|███▏      | 19600/61904 [05:54<17:02:29,  1.45s/it]
                                                        
{'loss': 2.6755, 'learning_rate': 1.685595747439388e-07, 'epoch': 5.07}

 32%|███▏      | 19600/61904 [05:54<17:02:29,  1.45s/it]
 32%|███▏      | 19601/61904 [05:55<16:48:34,  1.43s/it]
 32%|███▏      | 19602/61904 [05:56<16:26:06,  1.40s/it]
 32%|███▏      | 19603/61904 [05:58<16:37:38,  1.42s/it]
 32%|███▏      | 19604/61904 [05:59<16:24:05,  1.40s/it]
 32%|███▏      | 19605/61904 [06:01<16:39:03,  1.42s/it]
 32%|███▏      | 19606/61904 [06:02<17:37:02,  1.50s/it]
 32%|███▏      | 19607/61904 [06:04<17:26:12,  1.48s/it]
 32%|███▏      | 19608/61904 [06:05<17:18:38,  1.47s/it]
 32%|███▏      | 19609/61904 [06:07<17:01:11,  1.45s/it]
 32%|███▏      | 19610/61904 [06:08<17:00:52,  1.45s/it]
 32%|███▏      | 19611/61904 [06:10<17:05:10,  1.45s/it]
 32%|███▏      | 19612/61904 [06:11<16:50:16,  1.43s/it]
 32%|███▏      | 19613/61904 [06:12<16:25:37,  1.40s/it]
 32%|███▏      | 19614/61904 [06:13<16:03:29,  1.37s/it]
 32%|███▏      | 19615/61904 [06:15<16:17:15,  1.39s/it]
 32%|███▏      | 19616/61904 [06:16<16:16:50,  1.39s/it]
 32%|███▏      | 19617/61904 [06:18<16:05:52,  1.37s/it]
 32%|███▏      | 19618/61904 [06:19<15:43:31,  1.34s/it]
 32%|███▏      | 19619/61904 [06:20<15:50:10,  1.35s/it]
 32%|███▏      | 19620/61904 [06:22<15:48:41,  1.35s/it]
                                                        
{'loss': 2.6075, 'learning_rate': 1.6852716193439647e-07, 'epoch': 5.07}

 32%|███▏      | 19620/61904 [06:22<15:48:41,  1.35s/it]
 32%|███▏      | 19621/61904 [06:23<16:46:52,  1.43s/it]
 32%|███▏      | 19622/61904 [06:25<16:33:54,  1.41s/it]
 32%|███▏      | 19623/61904 [06:26<16:53:10,  1.44s/it]
 32%|███▏      | 19624/61904 [06:27<16:35:54,  1.41s/it]
 32%|███▏      | 19625/61904 [06:29<16:23:31,  1.40s/it]
 32%|███▏      | 19626/61904 [06:30<15:49:07,  1.35s/it]
 32%|███▏      | 19627/61904 [06:31<15:34:36,  1.33s/it]
 32%|███▏      | 19628/61904 [06:33<15:27:40,  1.32s/it]
 32%|███▏      | 19629/61904 [06:34<16:02:42,  1.37s/it]
 32%|███▏      | 19630/61904 [06:35<16:02:48,  1.37s/it]
 32%|███▏      | 19631/61904 [06:37<16:06:01,  1.37s/it]
 32%|███▏      | 19632/61904 [06:38<16:13:33,  1.38s/it]
 32%|███▏      | 19633/61904 [06:40<16:15:18,  1.38s/it]
 32%|███▏      | 19634/61904 [06:41<16:21:05,  1.39s/it]
 32%|███▏      | 19635/61904 [06:42<16:21:15,  1.39s/it]
 32%|███▏      | 19636/61904 [06:44<16:12:06,  1.38s/it]
 32%|███▏      | 19637/61904 [06:45<16:27:03,  1.40s/it]
 32%|███▏      | 19638/61904 [06:47<16:29:57,  1.41s/it]
 32%|███▏      | 19639/61904 [06:48<16:18:17,  1.39s/it]
 32%|███▏      | 19640/61904 [06:49<16:28:25,  1.40s/it]
                                                        
{'loss': 2.6402, 'learning_rate': 1.6849474912485413e-07, 'epoch': 5.08}

 32%|███▏      | 19640/61904 [06:49<16:28:25,  1.40s/it]
 32%|███▏      | 19641/61904 [06:51<16:17:22,  1.39s/it]
 32%|███▏      | 19642/61904 [06:52<15:57:47,  1.36s/it]
 32%|███▏      | 19643/61904 [06:53<15:48:59,  1.35s/it]
 32%|███▏      | 19644/61904 [06:55<16:28:34,  1.40s/it]
 32%|███▏      | 19645/61904 [06:56<16:31:32,  1.41s/it]
 32%|███▏      | 19646/61904 [06:58<16:06:12,  1.37s/it]
 32%|███▏      | 19647/61904 [06:59<16:14:33,  1.38s/it]
 32%|███▏      | 19648/61904 [07:01<16:30:12,  1.41s/it]
 32%|███▏      | 19649/61904 [07:02<16:13:03,  1.38s/it]
 32%|███▏      | 19650/61904 [07:03<16:00:18,  1.36s/it]
 32%|███▏      | 19651/61904 [07:05<16:05:11,  1.37s/it]
 32%|███▏      | 19652/61904 [07:06<16:08:41,  1.38s/it]
 32%|███▏      | 19653/61904 [07:07<15:54:57,  1.36s/it]
 32%|███▏      | 19654/61904 [07:09<16:09:09,  1.38s/it]
 32%|███▏      | 19655/61904 [07:10<15:55:22,  1.36s/it]
 32%|███▏      | 19656/61904 [07:11<15:22:52,  1.31s/it]
 32%|███▏      | 19657/61904 [07:12<15:15:29,  1.30s/it]
 32%|███▏      | 19658/61904 [07:14<15:23:02,  1.31s/it]
 32%|███▏      | 19659/61904 [07:15<15:53:48,  1.35s/it]
 32%|███▏      | 19660/61904 [07:17<16:04:36,  1.37s/it]
                                                        
{'loss': 2.6928, 'learning_rate': 1.684623363153118e-07, 'epoch': 5.08}

 32%|███▏      | 19660/61904 [07:17<16:04:36,  1.37s/it]
 32%|███▏      | 19661/61904 [07:18<15:55:16,  1.36s/it]
 32%|███▏      | 19662/61904 [07:19<15:54:06,  1.36s/it]
 32%|███▏      | 19663/61904 [07:21<16:23:47,  1.40s/it]
 32%|███▏      | 19664/61904 [07:22<16:24:23,  1.40s/it]
 32%|███▏      | 19665/61904 [07:24<15:51:42,  1.35s/it]
 32%|███▏      | 19666/61904 [07:25<16:06:41,  1.37s/it]
 32%|███▏      | 19667/61904 [07:26<16:15:36,  1.39s/it]
 32%|███▏      | 19668/61904 [07:28<16:36:34,  1.42s/it]
 32%|███▏      | 19669/61904 [07:29<17:01:18,  1.45s/it]
 32%|███▏      | 19670/61904 [07:31<17:12:07,  1.47s/it]
 32%|███▏      | 19671/61904 [07:32<16:52:21,  1.44s/it]
 32%|███▏      | 19672/61904 [07:34<16:22:12,  1.40s/it]
 32%|███▏      | 19673/61904 [07:35<16:29:10,  1.41s/it]
 32%|███▏      | 19674/61904 [07:36<16:19:10,  1.39s/it]
 32%|███▏      | 19675/61904 [07:38<16:13:28,  1.38s/it]
 32%|███▏      | 19676/61904 [07:39<16:46:44,  1.43s/it]
 32%|███▏      | 19677/61904 [07:41<16:32:23,  1.41s/it]
 32%|███▏      | 19678/61904 [07:42<16:12:13,  1.38s/it]
 32%|███▏      | 19679/61904 [07:43<16:17:17,  1.39s/it]
 32%|███▏      | 19680/61904 [07:45<16:20:36,  1.39s/it]
                                                        
{'loss': 2.6689, 'learning_rate': 1.6842992350576948e-07, 'epoch': 5.09}

 32%|███▏      | 19680/61904 [07:45<16:20:36,  1.39s/it]
 32%|███▏      | 19681/61904 [07:46<16:05:11,  1.37s/it]
 32%|███▏      | 19682/61904 [07:47<15:39:45,  1.34s/it]
 32%|███▏      | 19683/61904 [07:49<16:30:33,  1.41s/it]
 32%|███▏      | 19684/61904 [07:50<16:21:19,  1.39s/it]
 32%|███▏      | 19685/61904 [07:52<16:25:15,  1.40s/it]
 32%|███▏      | 19686/61904 [07:53<16:54:31,  1.44s/it]
 32%|███▏      | 19687/61904 [07:55<16:49:11,  1.43s/it]
 32%|███▏      | 19688/61904 [07:56<16:23:38,  1.40s/it]
 32%|███▏      | 19689/61904 [07:57<16:37:31,  1.42s/it]
 32%|███▏      | 19690/61904 [07:59<16:42:24,  1.42s/it]
 32%|███▏      | 19691/61904 [08:00<16:41:07,  1.42s/it]
 32%|███▏      | 19692/61904 [08:02<16:30:45,  1.41s/it]
 32%|███▏      | 19693/61904 [08:03<16:40:05,  1.42s/it]
 32%|███▏      | 19694/61904 [08:04<16:20:43,  1.39s/it]
 32%|███▏      | 19695/61904 [08:06<16:22:47,  1.40s/it]
 32%|███▏      | 19696/61904 [08:07<16:09:47,  1.38s/it]
 32%|███▏      | 19697/61904 [08:08<15:54:56,  1.36s/it]
 32%|███▏      | 19698/61904 [08:10<16:02:16,  1.37s/it]
 32%|███▏      | 19699/61904 [08:11<16:04:28,  1.37s/it]
 32%|███▏      | 19700/61904 [08:13<15:59:52,  1.36s/it]
                                                        
{'loss': 2.6848, 'learning_rate': 1.6839751069622714e-07, 'epoch': 5.09}

 32%|███▏      | 19700/61904 [08:13<15:59:52,  1.36s/it]
 32%|███▏      | 19701/61904 [08:14<15:57:29,  1.36s/it]
 32%|███▏      | 19702/61904 [08:15<16:21:08,  1.39s/it]
 32%|███▏      | 19703/61904 [08:17<16:02:14,  1.37s/it]
 32%|███▏      | 19704/61904 [08:18<15:34:58,  1.33s/it]
 32%|███▏      | 19705/61904 [08:19<15:23:19,  1.31s/it]
 32%|███▏      | 19706/61904 [08:21<15:51:20,  1.35s/it]
 32%|███▏      | 19707/61904 [08:22<15:46:19,  1.35s/it]
 32%|███▏      | 19708/61904 [08:23<16:08:40,  1.38s/it]
 32%|███▏      | 19709/61904 [08:25<16:03:35,  1.37s/it]
 32%|███▏      | 19710/61904 [08:26<16:20:42,  1.39s/it]
 32%|███▏      | 19711/61904 [08:28<16:01:36,  1.37s/it]
 32%|███▏      | 19712/61904 [08:29<16:17:22,  1.39s/it]
 32%|███▏      | 19713/61904 [08:31<16:55:13,  1.44s/it]
 32%|███▏      | 19714/61904 [08:32<16:33:19,  1.41s/it]
 32%|███▏      | 19715/61904 [08:33<16:30:59,  1.41s/it]
 32%|███▏      | 19716/61904 [08:35<16:19:44,  1.39s/it]
 32%|███▏      | 19717/61904 [08:36<15:53:07,  1.36s/it]
 32%|███▏      | 19718/61904 [08:37<16:10:17,  1.38s/it]
 32%|███▏      | 19719/61904 [08:39<15:54:42,  1.36s/it]
 32%|███▏      | 19720/61904 [08:40<15:57:30,  1.36s/it]
                                                        
{'loss': 2.6315, 'learning_rate': 1.683650978866848e-07, 'epoch': 5.1}

 32%|███▏      | 19720/61904 [08:40<15:57:30,  1.36s/it]
 32%|███▏      | 19721/61904 [08:41<16:13:46,  1.39s/it]
 32%|███▏      | 19722/61904 [08:43<16:12:51,  1.38s/it]
 32%|███▏      | 19723/61904 [08:44<16:07:37,  1.38s/it]
 32%|███▏      | 19724/61904 [08:46<16:22:29,  1.40s/it]
 32%|███▏      | 19725/61904 [08:47<16:13:22,  1.38s/it]
 32%|███▏      | 19726/61904 [08:48<15:42:47,  1.34s/it]
 32%|███▏      | 19727/61904 [08:50<15:44:59,  1.34s/it]
 32%|███▏      | 19728/61904 [08:51<15:53:38,  1.36s/it]
 32%|███▏      | 19729/61904 [08:52<16:12:25,  1.38s/it]
 32%|███▏      | 19730/61904 [08:54<16:27:16,  1.40s/it]
 32%|███▏      | 19731/61904 [08:55<16:32:48,  1.41s/it]
 32%|███▏      | 19732/61904 [08:57<16:50:00,  1.44s/it]
 32%|███▏      | 19733/61904 [08:58<16:49:37,  1.44s/it]
 32%|███▏      | 19734/61904 [09:00<16:29:24,  1.41s/it]
 32%|███▏      | 19735/61904 [09:01<16:19:42,  1.39s/it]
 32%|███▏      | 19736/61904 [09:02<16:27:45,  1.41s/it]
 32%|███▏      | 19737/61904 [09:04<15:50:05,  1.35s/it]
 32%|███▏      | 19738/61904 [09:05<16:08:38,  1.38s/it]
 32%|███▏      | 19739/61904 [09:07<16:41:02,  1.42s/it]
 32%|███▏      | 19740/61904 [09:08<16:33:43,  1.41s/it]
                                                        
{'loss': 2.6936, 'learning_rate': 1.683326850771425e-07, 'epoch': 5.1}

 32%|███▏      | 19740/61904 [09:08<16:33:43,  1.41s/it]
 32%|███▏      | 19741/61904 [09:09<16:04:46,  1.37s/it]
 32%|███▏      | 19742/61904 [09:11<16:14:21,  1.39s/it]
 32%|███▏      | 19743/61904 [09:12<16:13:43,  1.39s/it]
 32%|███▏      | 19744/61904 [09:13<15:51:59,  1.35s/it]
 32%|███▏      | 19745/61904 [09:15<16:23:46,  1.40s/it]
 32%|███▏      | 19746/61904 [09:16<16:20:26,  1.40s/it]
 32%|███▏      | 19747/61904 [09:18<16:38:24,  1.42s/it]
 32%|███▏      | 19748/61904 [09:19<16:26:33,  1.40s/it]
 32%|███▏      | 19749/61904 [09:20<16:31:04,  1.41s/it]
 32%|███▏      | 19750/61904 [09:22<16:54:57,  1.44s/it]
 32%|███▏      | 19751/61904 [09:23<16:40:58,  1.42s/it]
 32%|███▏      | 19752/61904 [09:25<16:45:55,  1.43s/it]
 32%|███▏      | 19753/61904 [09:26<16:20:18,  1.40s/it]
 32%|███▏      | 19754/61904 [09:28<16:45:28,  1.43s/it]
 32%|███▏      | 19755/61904 [09:29<16:25:59,  1.40s/it]
 32%|███▏      | 19756/61904 [09:30<16:10:21,  1.38s/it]
 32%|███▏      | 19757/61904 [09:32<16:11:51,  1.38s/it]
 32%|███▏      | 19758/61904 [09:33<16:07:43,  1.38s/it]
 32%|███▏      | 19759/61904 [09:35<16:56:34,  1.45s/it]
 32%|███▏      | 19760/61904 [09:36<16:28:25,  1.41s/it]
                                                        
{'loss': 2.6354, 'learning_rate': 1.6830027226760015e-07, 'epoch': 5.11}

 32%|███▏      | 19760/61904 [09:36<16:28:25,  1.41s/it]
 32%|███▏      | 19761/61904 [09:38<16:53:32,  1.44s/it]
 32%|███▏      | 19762/61904 [09:39<16:42:02,  1.43s/it]
 32%|███▏      | 19763/61904 [09:40<16:47:37,  1.43s/it]
 32%|███▏      | 19764/61904 [09:42<16:37:57,  1.42s/it]
 32%|███▏      | 19765/61904 [09:43<16:16:48,  1.39s/it]
 32%|███▏      | 19766/61904 [09:44<16:04:46,  1.37s/it]
 32%|███▏      | 19767/61904 [09:46<15:50:39,  1.35s/it]
 32%|███▏      | 19768/61904 [09:47<15:39:34,  1.34s/it]
 32%|███▏      | 19769/61904 [09:48<15:35:37,  1.33s/it]
 32%|███▏      | 19770/61904 [09:50<16:23:07,  1.40s/it]
 32%|███▏      | 19771/61904 [09:51<16:22:04,  1.40s/it]
 32%|███▏      | 19772/61904 [09:53<16:34:51,  1.42s/it]
 32%|███▏      | 19773/61904 [09:54<17:11:19,  1.47s/it]
 32%|███▏      | 19774/61904 [09:56<16:43:10,  1.43s/it]
 32%|███▏      | 19775/61904 [09:57<17:05:15,  1.46s/it]
 32%|███▏      | 19776/61904 [09:59<17:19:30,  1.48s/it]
 32%|███▏      | 19777/61904 [10:00<17:08:40,  1.47s/it]
 32%|███▏      | 19778/61904 [10:02<16:40:09,  1.42s/it]
 32%|███▏      | 19779/61904 [10:03<16:29:43,  1.41s/it]
 32%|███▏      | 19780/61904 [10:05<17:17:49,  1.48s/it]
                                                        
{'loss': 2.6376, 'learning_rate': 1.6826785945805782e-07, 'epoch': 5.11}

 32%|███▏      | 19780/61904 [10:05<17:17:49,  1.48s/it]
 32%|███▏      | 19781/61904 [10:06<16:37:51,  1.42s/it]
 32%|███▏      | 19782/61904 [10:07<16:16:02,  1.39s/it]
 32%|███▏      | 19783/61904 [10:08<16:00:23,  1.37s/it]
 32%|███▏      | 19784/61904 [10:10<16:03:54,  1.37s/it]
 32%|███▏      | 19785/61904 [10:11<16:10:50,  1.38s/it]
 32%|███▏      | 19786/61904 [10:13<16:11:26,  1.38s/it]
 32%|███▏      | 19787/61904 [10:14<16:42:21,  1.43s/it]
 32%|███▏      | 19788/61904 [10:15<16:09:00,  1.38s/it]
 32%|███▏      | 19789/61904 [10:17<16:29:17,  1.41s/it]
 32%|███▏      | 19790/61904 [10:18<16:14:12,  1.39s/it]
 32%|███▏      | 19791/61904 [10:20<16:11:42,  1.38s/it]
 32%|███▏      | 19792/61904 [10:21<16:10:21,  1.38s/it]
 32%|███▏      | 19793/61904 [10:22<16:10:14,  1.38s/it]
 32%|███▏      | 19794/61904 [10:24<15:37:14,  1.34s/it]
 32%|███▏      | 19795/61904 [10:25<16:09:23,  1.38s/it]
 32%|███▏      | 19796/61904 [10:26<15:59:43,  1.37s/it]
 32%|███▏      | 19797/61904 [10:28<16:26:21,  1.41s/it]
 32%|███▏      | 19798/61904 [10:29<16:07:33,  1.38s/it]
 32%|███▏      | 19799/61904 [10:31<15:52:14,  1.36s/it]
 32%|███▏      | 19800/61904 [10:32<15:59:57,  1.37s/it]
                                                        
{'loss': 2.7595, 'learning_rate': 1.6823544664851548e-07, 'epoch': 5.12}

 32%|███▏      | 19800/61904 [10:32<15:59:57,  1.37s/it]
 32%|███▏      | 19801/61904 [10:33<15:38:10,  1.34s/it]
 32%|███▏      | 19802/61904 [10:35<16:04:38,  1.37s/it]
 32%|███▏      | 19803/61904 [10:36<15:45:35,  1.35s/it]
 32%|███▏      | 19804/61904 [10:37<16:26:40,  1.41s/it]
 32%|███▏      | 19805/61904 [10:39<16:43:53,  1.43s/it]
 32%|███▏      | 19806/61904 [10:40<16:26:39,  1.41s/it]
 32%|███▏      | 19807/61904 [10:42<16:10:04,  1.38s/it]
 32%|███▏      | 19808/61904 [10:43<15:59:34,  1.37s/it]
 32%|███▏      | 19809/61904 [10:44<15:57:27,  1.36s/it]
 32%|███▏      | 19810/61904 [10:46<15:49:49,  1.35s/it]
 32%|███▏      | 19811/61904 [10:47<15:45:50,  1.35s/it]
 32%|███▏      | 19812/61904 [10:48<16:13:27,  1.39s/it]
 32%|███▏      | 19813/61904 [10:50<15:55:01,  1.36s/it]
 32%|███▏      | 19814/61904 [10:51<16:00:22,  1.37s/it]
 32%|███▏      | 19815/61904 [10:52<15:50:10,  1.35s/it]
 32%|███▏      | 19816/61904 [10:54<16:04:17,  1.37s/it]
 32%|███▏      | 19817/61904 [10:55<16:00:06,  1.37s/it]
 32%|███▏      | 19818/61904 [10:57<16:18:55,  1.40s/it]
 32%|███▏      | 19819/61904 [10:58<16:45:18,  1.43s/it]
 32%|███▏      | 19820/61904 [11:00<16:22:00,  1.40s/it]
                                                        
{'loss': 2.5688, 'learning_rate': 1.6820303383897317e-07, 'epoch': 5.12}

 32%|███▏      | 19820/61904 [11:00<16:22:00,  1.40s/it]
 32%|███▏      | 19821/61904 [11:01<16:01:12,  1.37s/it]
 32%|███▏      | 19822/61904 [11:02<15:40:31,  1.34s/it]
 32%|███▏      | 19823/61904 [11:03<15:39:43,  1.34s/it]
 32%|███▏      | 19824/61904 [11:05<16:03:48,  1.37s/it]
 32%|███▏      | 19825/61904 [11:06<16:15:44,  1.39s/it]
 32%|███▏      | 19826/61904 [11:08<16:11:46,  1.39s/it]
 32%|███▏      | 19827/61904 [11:09<16:15:33,  1.39s/it]
 32%|███▏      | 19828/61904 [11:10<16:00:00,  1.37s/it]
 32%|███▏      | 19829/61904 [11:12<16:53:50,  1.45s/it]
 32%|███▏      | 19830/61904 [11:14<16:56:34,  1.45s/it]
 32%|███▏      | 19831/61904 [11:15<17:13:16,  1.47s/it]
 32%|███▏      | 19832/61904 [11:16<16:49:08,  1.44s/it]
 32%|███▏      | 19833/61904 [11:18<16:41:50,  1.43s/it]
 32%|███▏      | 19834/61904 [11:19<16:31:26,  1.41s/it]
 32%|███▏      | 19835/61904 [11:21<16:35:14,  1.42s/it]
 32%|███▏      | 19836/61904 [11:22<16:40:00,  1.43s/it]
 32%|███▏      | 19837/61904 [11:24<16:42:49,  1.43s/it]
 32%|███▏      | 19838/61904 [11:25<16:35:03,  1.42s/it]
 32%|███▏      | 19839/61904 [11:26<16:09:30,  1.38s/it]
 32%|███▏      | 19840/61904 [11:28<16:10:00,  1.38s/it]
                                                        
{'loss': 2.6504, 'learning_rate': 1.6817062102943083e-07, 'epoch': 5.13}

 32%|███▏      | 19840/61904 [11:28<16:10:00,  1.38s/it]
 32%|███▏      | 19841/61904 [11:29<15:50:22,  1.36s/it]
 32%|███▏      | 19842/61904 [11:30<16:11:01,  1.39s/it]
 32%|███▏      | 19843/61904 [11:32<16:25:56,  1.41s/it]
 32%|███▏      | 19844/61904 [11:33<16:25:48,  1.41s/it]
 32%|███▏      | 19845/61904 [11:35<16:29:21,  1.41s/it]
 32%|███▏      | 19846/61904 [11:36<15:53:45,  1.36s/it]
 32%|███▏      | 19847/61904 [11:37<16:15:30,  1.39s/it]
 32%|███▏      | 19848/61904 [11:39<16:09:18,  1.38s/it]
 32%|███▏      | 19849/61904 [11:40<16:10:11,  1.38s/it]
 32%|███▏      | 19850/61904 [11:41<15:43:41,  1.35s/it]
 32%|███▏      | 19851/61904 [11:43<16:16:36,  1.39s/it]
 32%|███▏      | 19852/61904 [11:44<16:42:56,  1.43s/it]
 32%|███▏      | 19853/61904 [11:46<16:20:12,  1.40s/it]
 32%|███▏      | 19854/61904 [11:47<15:56:26,  1.36s/it]
 32%|███▏      | 19855/61904 [11:48<15:45:02,  1.35s/it]
 32%|███▏      | 19856/61904 [11:50<16:03:33,  1.37s/it]
 32%|███▏      | 19857/61904 [11:51<15:55:47,  1.36s/it]
 32%|███▏      | 19858/61904 [11:52<16:07:16,  1.38s/it]
 32%|███▏      | 19859/61904 [11:54<15:59:21,  1.37s/it]
 32%|███▏      | 19860/61904 [11:55<15:36:09,  1.34s/it]
                                                        
{'loss': 2.701, 'learning_rate': 1.681382082198885e-07, 'epoch': 5.13}

 32%|███▏      | 19860/61904 [11:55<15:36:09,  1.34s/it]
 32%|███▏      | 19861/61904 [11:56<15:39:30,  1.34s/it]
 32%|███▏      | 19862/61904 [11:58<15:37:33,  1.34s/it]
 32%|███▏      | 19863/61904 [11:59<16:01:48,  1.37s/it]
 32%|███▏      | 19864/61904 [12:01<15:56:52,  1.37s/it]
 32%|███▏      | 19865/61904 [12:02<16:00:40,  1.37s/it]
 32%|███▏      | 19866/61904 [12:03<15:42:27,  1.35s/it]
 32%|███▏      | 19867/61904 [12:05<15:33:42,  1.33s/it]
 32%|███▏      | 19868/61904 [12:06<15:24:11,  1.32s/it]
 32%|███▏      | 19869/61904 [12:07<15:44:16,  1.35s/it]
 32%|███▏      | 19870/61904 [12:09<15:35:05,  1.33s/it]
 32%|███▏      | 19871/61904 [12:10<15:49:46,  1.36s/it]
 32%|███▏      | 19872/61904 [12:11<16:07:53,  1.38s/it]
 32%|███▏      | 19873/61904 [12:13<15:56:45,  1.37s/it]
 32%|███▏      | 19874/61904 [12:14<16:30:23,  1.41s/it]
 32%|███▏      | 19875/61904 [12:16<16:09:18,  1.38s/it]
 32%|███▏      | 19876/61904 [12:17<16:02:30,  1.37s/it]
 32%|███▏      | 19877/61904 [12:18<15:50:48,  1.36s/it]
 32%|███▏      | 19878/61904 [12:20<16:03:59,  1.38s/it]
 32%|███▏      | 19879/61904 [12:21<16:24:03,  1.40s/it]
 32%|███▏      | 19880/61904 [12:23<16:39:50,  1.43s/it]
                                                        
{'loss': 2.6691, 'learning_rate': 1.6810579541034615e-07, 'epoch': 5.14}

 32%|███▏      | 19880/61904 [12:23<16:39:50,  1.43s/it]
 32%|███▏      | 19881/61904 [12:24<16:18:13,  1.40s/it]
 32%|███▏      | 19882/61904 [12:25<16:24:50,  1.41s/it]
 32%|███▏      | 19883/61904 [12:27<16:28:41,  1.41s/it]
 32%|███▏      | 19884/61904 [12:28<16:25:07,  1.41s/it]
 32%|███▏      | 19885/61904 [12:30<16:39:03,  1.43s/it]
 32%|███▏      | 19886/61904 [12:31<16:21:26,  1.40s/it]
 32%|███▏      | 19887/61904 [12:33<16:42:06,  1.43s/it]
 32%|███▏      | 19888/61904 [12:34<16:42:06,  1.43s/it]
 32%|███▏      | 19889/61904 [12:35<16:20:35,  1.40s/it]
 32%|███▏      | 19890/61904 [12:37<15:49:09,  1.36s/it]
 32%|███▏      | 19891/61904 [12:38<16:23:00,  1.40s/it]
 32%|███▏      | 19892/61904 [12:40<16:49:15,  1.44s/it]
 32%|███▏      | 19893/61904 [12:41<16:40:23,  1.43s/it]
 32%|███▏      | 19894/61904 [12:42<17:02:12,  1.46s/it]
 32%|███▏      | 19895/61904 [12:44<16:17:43,  1.40s/it]
 32%|███▏      | 19896/61904 [12:45<15:48:07,  1.35s/it]
 32%|███▏      | 19897/61904 [12:46<15:50:20,  1.36s/it]
 32%|███▏      | 19898/61904 [12:48<15:53:59,  1.36s/it]
 32%|███▏      | 19899/61904 [12:49<16:15:04,  1.39s/it]
 32%|███▏      | 19900/61904 [12:50<15:46:18,  1.35s/it]
                                                        
{'loss': 2.6396, 'learning_rate': 1.6807338260080384e-07, 'epoch': 5.14}

 32%|███▏      | 19900/61904 [12:50<15:46:18,  1.35s/it]
 32%|███▏      | 19901/61904 [12:52<15:58:48,  1.37s/it]
 32%|███▏      | 19902/61904 [12:53<16:21:39,  1.40s/it]
 32%|███▏      | 19903/61904 [12:55<16:40:08,  1.43s/it]
 32%|███▏      | 19904/61904 [12:56<16:17:59,  1.40s/it]
 32%|███▏      | 19905/61904 [12:57<16:02:48,  1.38s/it]
 32%|███▏      | 19906/61904 [12:59<15:38:17,  1.34s/it]
 32%|███▏      | 19907/61904 [13:00<15:50:07,  1.36s/it]
 32%|███▏      | 19908/61904 [13:01<15:50:00,  1.36s/it]
 32%|███▏      | 19909/61904 [13:03<15:58:45,  1.37s/it]
 32%|███▏      | 19910/61904 [13:04<16:14:36,  1.39s/it]
 32%|███▏      | 19911/61904 [13:06<15:48:05,  1.35s/it]
 32%|███▏      | 19912/61904 [13:07<15:32:41,  1.33s/it]
 32%|███▏      | 19913/61904 [13:08<16:05:55,  1.38s/it]
 32%|███▏      | 19914/61904 [13:10<16:06:19,  1.38s/it]
 32%|███▏      | 19915/61904 [13:11<16:00:26,  1.37s/it]
 32%|███▏      | 19916/61904 [13:12<15:49:21,  1.36s/it]
 32%|███▏      | 19917/61904 [13:14<16:00:49,  1.37s/it]
 32%|███▏      | 19918/61904 [13:15<16:07:19,  1.38s/it]
 32%|███▏      | 19919/61904 [13:17<16:33:24,  1.42s/it]
 32%|███▏      | 19920/61904 [13:18<16:17:44,  1.40s/it]
                                                        
{'loss': 2.6752, 'learning_rate': 1.680409697912615e-07, 'epoch': 5.15}

 32%|███▏      | 19920/61904 [13:18<16:17:44,  1.40s/it]
 32%|███▏      | 19921/61904 [13:20<16:29:09,  1.41s/it]
 32%|███▏      | 19922/61904 [13:21<16:20:57,  1.40s/it]
 32%|███▏      | 19923/61904 [13:22<15:41:54,  1.35s/it]
 32%|███▏      | 19924/61904 [13:23<15:43:51,  1.35s/it]
 32%|███▏      | 19925/61904 [13:25<15:56:12,  1.37s/it]
 32%|███▏      | 19926/61904 [13:26<16:06:32,  1.38s/it]
 32%|███▏      | 19927/61904 [13:28<16:10:44,  1.39s/it]
 32%|███▏      | 19928/61904 [13:29<16:04:35,  1.38s/it]
 32%|███▏      | 19929/61904 [13:30<16:07:59,  1.38s/it]
 32%|███▏      | 19930/61904 [13:32<15:55:44,  1.37s/it]
 32%|███▏      | 19931/61904 [13:33<16:04:22,  1.38s/it]
 32%|███▏      | 19932/61904 [13:35<16:11:13,  1.39s/it]
 32%|███▏      | 19933/61904 [13:36<17:36:42,  1.51s/it]
 32%|███▏      | 19934/61904 [13:38<16:47:49,  1.44s/it]
 32%|███▏      | 19935/61904 [13:39<16:46:47,  1.44s/it]
 32%|███▏      | 19936/61904 [13:41<16:41:37,  1.43s/it]
 32%|███▏      | 19937/61904 [13:42<16:20:35,  1.40s/it]
 32%|███▏      | 19938/61904 [13:43<16:30:11,  1.42s/it]
 32%|███▏      | 19939/61904 [13:45<15:51:48,  1.36s/it]
 32%|███▏      | 19940/61904 [13:46<15:57:10,  1.37s/it]
                                                        
{'loss': 2.567, 'learning_rate': 1.6800855698171916e-07, 'epoch': 5.15}

 32%|███▏      | 19940/61904 [13:46<15:57:10,  1.37s/it]
 32%|███▏      | 19941/61904 [13:47<15:51:22,  1.36s/it]
 32%|███▏      | 19942/61904 [13:49<15:36:50,  1.34s/it]
 32%|███▏      | 19943/61904 [13:50<15:52:47,  1.36s/it]
 32%|███▏      | 19944/61904 [13:51<16:09:15,  1.39s/it]
 32%|███▏      | 19945/61904 [13:53<16:24:42,  1.41s/it]
 32%|███▏      | 19946/61904 [13:54<16:45:15,  1.44s/it]
 32%|███▏      | 19947/61904 [13:56<16:31:14,  1.42s/it]
 32%|███▏      | 19948/61904 [13:57<16:03:10,  1.38s/it]
 32%|███▏      | 19949/61904 [13:58<15:43:34,  1.35s/it]
 32%|███▏      | 19950/61904 [14:00<15:38:23,  1.34s/it]
 32%|███▏      | 19951/61904 [14:01<16:05:39,  1.38s/it]
 32%|███▏      | 19952/61904 [14:03<17:08:27,  1.47s/it]
 32%|███▏      | 19953/61904 [14:04<17:13:20,  1.48s/it]
 32%|███▏      | 19954/61904 [14:06<16:47:49,  1.44s/it]
 32%|███▏      | 19955/61904 [14:07<16:44:36,  1.44s/it]
 32%|███▏      | 19956/61904 [14:09<17:06:38,  1.47s/it]
 32%|███▏      | 19957/61904 [14:10<16:53:00,  1.45s/it]
 32%|███▏      | 19958/61904 [14:12<17:05:04,  1.47s/it]
 32%|███▏      | 19959/61904 [14:13<16:59:14,  1.46s/it]
 32%|███▏      | 19960/61904 [14:14<16:24:28,  1.41s/it]
                                                        
{'loss': 2.6691, 'learning_rate': 1.6797614417217685e-07, 'epoch': 5.16}

 32%|███▏      | 19960/61904 [14:14<16:24:28,  1.41s/it]
 32%|███▏      | 19961/61904 [14:16<16:20:12,  1.40s/it]
 32%|███▏      | 19962/61904 [14:17<16:11:33,  1.39s/it]
 32%|███▏      | 19963/61904 [14:18<15:58:51,  1.37s/it]
 32%|███▏      | 19964/61904 [14:20<16:27:17,  1.41s/it]
 32%|███▏      | 19965/61904 [14:21<17:03:58,  1.46s/it]
 32%|███▏      | 19966/61904 [14:23<16:41:06,  1.43s/it]
 32%|███▏      | 19967/61904 [14:24<16:58:19,  1.46s/it]
 32%|███▏      | 19968/61904 [14:26<16:33:22,  1.42s/it]
 32%|███▏      | 19969/61904 [14:27<17:00:20,  1.46s/it]
 32%|███▏      | 19970/61904 [14:29<17:02:47,  1.46s/it]
 32%|███▏      | 19971/61904 [14:30<17:15:12,  1.48s/it]
 32%|███▏      | 19972/61904 [14:32<17:28:43,  1.50s/it]
 32%|███▏      | 19973/61904 [14:33<17:05:17,  1.47s/it]
 32%|███▏      | 19974/61904 [14:34<16:43:08,  1.44s/it]
 32%|███▏      | 19975/61904 [14:36<16:18:53,  1.40s/it]
 32%|███▏      | 19976/61904 [14:37<16:30:23,  1.42s/it]
 32%|███▏      | 19977/61904 [14:39<16:53:58,  1.45s/it]
 32%|███▏      | 19978/61904 [14:40<16:40:52,  1.43s/it]
 32%|███▏      | 19979/61904 [14:42<16:21:29,  1.40s/it]
 32%|███▏      | 19980/61904 [14:43<16:06:39,  1.38s/it]
                                                        
{'loss': 2.6172, 'learning_rate': 1.6794373136263451e-07, 'epoch': 5.16}

 32%|███▏      | 19980/61904 [14:43<16:06:39,  1.38s/it]
 32%|███▏      | 19981/61904 [14:44<15:57:10,  1.37s/it]
 32%|███▏      | 19982/61904 [14:46<15:59:27,  1.37s/it]
 32%|███▏      | 19983/61904 [14:47<15:59:14,  1.37s/it]
 32%|███▏      | 19984/61904 [14:49<16:42:03,  1.43s/it]
 32%|███▏      | 19985/61904 [14:50<16:49:18,  1.44s/it]
 32%|███▏      | 19986/61904 [14:51<16:33:17,  1.42s/it]
 32%|███▏      | 19987/61904 [14:53<16:37:15,  1.43s/it]
 32%|███▏      | 19988/61904 [14:54<17:01:01,  1.46s/it]
 32%|███▏      | 19989/61904 [14:56<16:55:09,  1.45s/it]
 32%|███▏      | 19990/61904 [14:57<16:34:13,  1.42s/it]
 32%|███▏      | 19991/61904 [14:59<16:33:58,  1.42s/it]
 32%|███▏      | 19992/61904 [15:00<16:28:56,  1.42s/it]
 32%|███▏      | 19993/61904 [15:01<16:45:56,  1.44s/it]
 32%|███▏      | 19994/61904 [15:03<16:37:30,  1.43s/it]
 32%|███▏      | 19995/61904 [15:04<16:30:36,  1.42s/it]
 32%|███▏      | 19996/61904 [15:06<16:25:19,  1.41s/it]
 32%|███▏      | 19997/61904 [15:07<16:15:14,  1.40s/it]
 32%|███▏      | 19998/61904 [15:08<15:58:05,  1.37s/it]
 32%|███▏      | 19999/61904 [15:10<15:28:26,  1.33s/it]
 32%|███▏      | 20000/61904 [15:11<15:39:44,  1.35s/it]
                                                        
{'loss': 2.6856, 'learning_rate': 1.6791131855309218e-07, 'epoch': 5.17}

 32%|███▏      | 20000/61904 [15:11<15:39:44,  1.35s/it]
 32%|███▏      | 20001/61904 [15:12<15:26:11,  1.33s/it]
 32%|███▏      | 20002/61904 [15:14<15:38:34,  1.34s/it]
 32%|███▏      | 20003/61904 [15:15<15:58:21,  1.37s/it]
 32%|███▏      | 20004/61904 [15:16<15:21:20,  1.32s/it]
 32%|███▏      | 20005/61904 [15:18<15:29:27,  1.33s/it]
 32%|███▏      | 20006/61904 [15:19<15:48:49,  1.36s/it]
 32%|███▏      | 20007/61904 [15:20<15:43:02,  1.35s/it]
 32%|███▏      | 20008/61904 [15:22<15:58:32,  1.37s/it]
 32%|███▏      | 20009/61904 [15:23<16:21:32,  1.41s/it]
 32%|███▏      | 20010/61904 [15:25<17:00:53,  1.46s/it]
 32%|███▏      | 20011/61904 [15:26<16:51:45,  1.45s/it]
 32%|███▏      | 20012/61904 [15:28<16:27:03,  1.41s/it]
 32%|███▏      | 20013/61904 [15:29<16:17:27,  1.40s/it]
 32%|███▏      | 20014/61904 [15:30<16:19:14,  1.40s/it]
 32%|███▏      | 20015/61904 [15:32<16:18:57,  1.40s/it]
 32%|███▏      | 20016/61904 [15:33<16:28:26,  1.42s/it]
 32%|███▏      | 20017/61904 [15:35<16:39:03,  1.43s/it]
 32%|███▏      | 20018/61904 [15:36<16:13:02,  1.39s/it]
 32%|███▏      | 20019/61904 [15:37<15:55:02,  1.37s/it]
 32%|███▏      | 20020/61904 [15:39<16:37:57,  1.43s/it]
                                                        
{'loss': 2.6874, 'learning_rate': 1.6787890574354984e-07, 'epoch': 5.17}

 32%|███▏      | 20020/61904 [15:39<16:37:57,  1.43s/it]
 32%|███▏      | 20021/61904 [15:40<16:28:58,  1.42s/it]
 32%|███▏      | 20022/61904 [15:42<16:02:35,  1.38s/it]
 32%|███▏      | 20023/61904 [15:43<16:10:02,  1.39s/it]
 32%|███▏      | 20024/61904 [15:44<16:02:15,  1.38s/it]
 32%|███▏      | 20025/61904 [15:46<16:10:36,  1.39s/it]
 32%|███▏      | 20026/61904 [15:47<15:48:51,  1.36s/it]
 32%|███▏      | 20027/61904 [15:48<15:50:24,  1.36s/it]
 32%|███▏      | 20028/61904 [15:50<15:59:54,  1.38s/it]
 32%|███▏      | 20029/61904 [15:51<16:10:32,  1.39s/it]
 32%|███▏      | 20030/61904 [15:53<16:13:17,  1.39s/it]
 32%|███▏      | 20031/61904 [15:54<16:08:42,  1.39s/it]
 32%|███▏      | 20032/61904 [15:55<16:09:51,  1.39s/it]
 32%|███▏      | 20033/61904 [15:57<16:40:04,  1.43s/it]
 32%|███▏      | 20034/61904 [15:58<16:49:20,  1.45s/it]
 32%|███▏      | 20035/61904 [16:00<16:12:28,  1.39s/it]
 32%|███▏      | 20036/61904 [16:01<16:16:23,  1.40s/it]
 32%|███▏      | 20037/61904 [16:02<16:14:45,  1.40s/it]
 32%|███▏      | 20038/61904 [16:04<16:05:21,  1.38s/it]
 32%|███▏      | 20039/61904 [16:05<16:37:36,  1.43s/it]
 32%|███▏      | 20040/61904 [16:07<16:20:47,  1.41s/it]
                                                        
{'loss': 2.6737, 'learning_rate': 1.678464929340075e-07, 'epoch': 5.18}

 32%|███▏      | 20040/61904 [16:07<16:20:47,  1.41s/it]
 32%|███▏      | 20041/61904 [16:08<16:07:47,  1.39s/it]
 32%|███▏      | 20042/61904 [16:10<16:29:19,  1.42s/it]
 32%|███▏      | 20043/61904 [16:11<16:41:05,  1.43s/it]
 32%|███▏      | 20044/61904 [16:13<17:35:37,  1.51s/it]
 32%|███▏      | 20045/61904 [16:14<17:15:48,  1.48s/it]
 32%|███▏      | 20046/61904 [16:16<17:37:55,  1.52s/it]
 32%|███▏      | 20047/61904 [16:17<16:53:24,  1.45s/it]
 32%|███▏      | 20048/61904 [16:18<16:25:27,  1.41s/it]
 32%|███▏      | 20049/61904 [16:20<16:13:31,  1.40s/it]
 32%|███▏      | 20050/61904 [16:21<16:51:15,  1.45s/it]
 32%|███▏      | 20051/61904 [16:23<16:46:59,  1.44s/it]
 32%|███▏      | 20052/61904 [16:24<16:31:00,  1.42s/it]
 32%|███▏      | 20053/61904 [16:25<16:19:42,  1.40s/it]
 32%|███▏      | 20054/61904 [16:27<16:06:19,  1.39s/it]
 32%|███▏      | 20055/61904 [16:28<16:51:11,  1.45s/it]
 32%|███▏      | 20056/61904 [16:30<16:51:27,  1.45s/it]
 32%|███▏      | 20057/61904 [16:31<17:03:26,  1.47s/it]
 32%|███▏      | 20058/61904 [16:33<16:49:52,  1.45s/it]
 32%|███▏      | 20059/61904 [16:34<16:43:59,  1.44s/it]
 32%|███▏      | 20060/61904 [16:36<16:27:07,  1.42s/it]
                                                        
{'loss': 2.6503, 'learning_rate': 1.678140801244652e-07, 'epoch': 5.18}

 32%|███▏      | 20060/61904 [16:36<16:27:07,  1.42s/it]
 32%|███▏      | 20061/61904 [16:37<16:35:39,  1.43s/it]
 32%|███▏      | 20062/61904 [16:38<16:41:28,  1.44s/it]
 32%|███▏      | 20063/61904 [16:40<16:25:50,  1.41s/it]
 32%|███▏      | 20064/61904 [16:41<16:04:49,  1.38s/it]
 32%|███▏      | 20065/61904 [16:43<16:10:28,  1.39s/it]
 32%|███▏      | 20066/61904 [16:44<16:08:14,  1.39s/it]
 32%|███▏      | 20067/61904 [16:45<15:58:19,  1.37s/it]
 32%|███▏      | 20068/61904 [16:47<15:48:48,  1.36s/it]
 32%|███▏      | 20069/61904 [16:48<15:46:13,  1.36s/it]
 32%|███▏      | 20070/61904 [16:49<15:29:32,  1.33s/it]
 32%|███▏      | 20071/61904 [16:51<15:29:57,  1.33s/it]
 32%|███▏      | 20072/61904 [16:52<16:35:51,  1.43s/it]
 32%|███▏      | 20073/61904 [16:54<16:14:06,  1.40s/it]
 32%|███▏      | 20074/61904 [16:55<15:54:20,  1.37s/it]
 32%|███▏      | 20075/61904 [16:56<15:46:11,  1.36s/it]
 32%|███▏      | 20076/61904 [16:58<15:43:48,  1.35s/it]
 32%|███▏      | 20077/61904 [16:59<15:54:26,  1.37s/it]
 32%|███▏      | 20078/61904 [17:00<15:49:41,  1.36s/it]
 32%|███▏      | 20079/61904 [17:02<16:07:23,  1.39s/it]
 32%|███▏      | 20080/61904 [17:03<16:05:52,  1.39s/it]
                                                        
{'loss': 2.6155, 'learning_rate': 1.6778166731492285e-07, 'epoch': 5.19}

 32%|███▏      | 20080/61904 [17:03<16:05:52,  1.39s/it]
 32%|███▏      | 20081/61904 [17:05<16:37:15,  1.43s/it]
 32%|███▏      | 20082/61904 [17:06<16:29:37,  1.42s/it]
 32%|███▏      | 20083/61904 [17:07<16:15:39,  1.40s/it]
 32%|███▏      | 20084/61904 [17:09<16:08:29,  1.39s/it]
 32%|███▏      | 20085/61904 [17:10<16:16:36,  1.40s/it]
 32%|███▏      | 20086/61904 [17:12<16:08:28,  1.39s/it]
 32%|███▏      | 20087/61904 [17:13<16:19:10,  1.40s/it]
 32%|███▏      | 20088/61904 [17:14<16:36:28,  1.43s/it]
 32%|███▏      | 20089/61904 [17:16<16:27:06,  1.42s/it]
 32%|███▏      | 20090/61904 [17:17<16:04:19,  1.38s/it]
 32%|███▏      | 20091/61904 [17:19<16:14:30,  1.40s/it]
 32%|███▏      | 20092/61904 [17:20<15:52:47,  1.37s/it]
 32%|███▏      | 20093/61904 [17:21<15:56:13,  1.37s/it]
 32%|███▏      | 20094/61904 [17:23<16:50:04,  1.45s/it]
 32%|███▏      | 20095/61904 [17:24<16:40:58,  1.44s/it]
 32%|███▏      | 20096/61904 [17:26<16:15:43,  1.40s/it]
 32%|███▏      | 20097/61904 [17:27<16:31:59,  1.42s/it]
 32%|███▏      | 20098/61904 [17:28<16:04:37,  1.38s/it]
 32%|███▏      | 20099/61904 [17:30<16:03:48,  1.38s/it]
 32%|███▏      | 20100/61904 [17:31<16:43:45,  1.44s/it]
                                                        
{'loss': 2.7035, 'learning_rate': 1.677492545053805e-07, 'epoch': 5.2}

 32%|███▏      | 20100/61904 [17:31<16:43:45,  1.44s/it]
 32%|███▏      | 20101/61904 [17:33<17:01:59,  1.47s/it]
 32%|███▏      | 20102/61904 [17:34<16:29:03,  1.42s/it]
 32%|███▏      | 20103/61904 [17:36<16:55:00,  1.46s/it]
 32%|███▏      | 20104/61904 [17:37<16:34:34,  1.43s/it]
 32%|███▏      | 20105/61904 [17:38<16:25:20,  1.41s/it]
 32%|███▏      | 20106/61904 [17:40<16:21:39,  1.41s/it]
 32%|███▏      | 20107/61904 [17:41<16:29:13,  1.42s/it]
 32%|███▏      | 20108/61904 [17:43<16:58:54,  1.46s/it]
 32%|███▏      | 20109/61904 [17:44<16:36:48,  1.43s/it]
 32%|███▏      | 20110/61904 [17:46<16:26:33,  1.42s/it]
 32%|███▏      | 20111/61904 [17:47<16:48:07,  1.45s/it]
 32%|███▏      | 20112/61904 [17:49<16:50:04,  1.45s/it]
 32%|███▏      | 20113/61904 [17:50<16:18:05,  1.40s/it]
 32%|███▏      | 20114/61904 [17:51<16:19:14,  1.41s/it]
 32%|███▏      | 20115/61904 [17:53<15:57:31,  1.37s/it]
 32%|███▏      | 20116/61904 [17:54<16:00:35,  1.38s/it]
 32%|███▏      | 20117/61904 [17:55<16:03:40,  1.38s/it]
 32%|███▏      | 20118/61904 [17:57<16:02:18,  1.38s/it]
 33%|███▎      | 20119/61904 [17:58<16:30:05,  1.42s/it]
 33%|███▎      | 20120/61904 [18:00<16:17:11,  1.40s/it]
                                                        
{'loss': 2.6192, 'learning_rate': 1.677168416958382e-07, 'epoch': 5.2}

 33%|███▎      | 20120/61904 [18:00<16:17:11,  1.40s/it]
 33%|███▎      | 20121/61904 [18:01<17:11:08,  1.48s/it]
 33%|███▎      | 20122/61904 [18:03<17:10:15,  1.48s/it]
 33%|███▎      | 20123/61904 [18:04<16:30:12,  1.42s/it]
 33%|███▎      | 20124/61904 [18:05<16:05:35,  1.39s/it]
 33%|███▎      | 20125/61904 [18:07<15:43:09,  1.35s/it]
 33%|███▎      | 20126/61904 [18:08<15:36:47,  1.35s/it]
 33%|███▎      | 20127/61904 [18:09<15:44:25,  1.36s/it]
 33%|███▎      | 20128/61904 [18:11<15:35:28,  1.34s/it]
 33%|███▎      | 20129/61904 [18:12<15:38:21,  1.35s/it]
 33%|███▎      | 20130/61904 [18:13<15:35:39,  1.34s/it]
 33%|███▎      | 20131/61904 [18:15<15:36:08,  1.34s/it]
 33%|███▎      | 20132/61904 [18:16<15:26:11,  1.33s/it]
 33%|███▎      | 20133/61904 [18:17<15:41:19,  1.35s/it]
 33%|███▎      | 20134/61904 [18:19<15:45:58,  1.36s/it]
 33%|███▎      | 20135/61904 [18:20<15:33:15,  1.34s/it]
 33%|███▎      | 20136/61904 [18:21<15:41:10,  1.35s/it]
 33%|███▎      | 20137/61904 [18:23<15:28:27,  1.33s/it]
 33%|███▎      | 20138/61904 [18:24<15:52:46,  1.37s/it]
 33%|███▎      | 20139/61904 [18:26<16:04:05,  1.39s/it]
 33%|███▎      | 20140/61904 [18:27<16:03:23,  1.38s/it]
                                                        
{'loss': 2.5974, 'learning_rate': 1.6768442888629586e-07, 'epoch': 5.21}

 33%|███▎      | 20140/61904 [18:27<16:03:23,  1.38s/it]
 33%|███▎      | 20141/61904 [18:28<15:38:42,  1.35s/it]
 33%|███▎      | 20142/61904 [18:30<15:42:31,  1.35s/it]
 33%|███▎      | 20143/61904 [18:31<15:52:46,  1.37s/it]
 33%|███▎      | 20144/61904 [18:32<16:13:23,  1.40s/it]
 33%|███▎      | 20145/61904 [18:34<16:15:22,  1.40s/it]
 33%|███▎      | 20146/61904 [18:35<15:54:18,  1.37s/it]
 33%|███▎      | 20147/61904 [18:37<15:55:38,  1.37s/it]
 33%|███▎      | 20148/61904 [18:38<16:01:30,  1.38s/it]
 33%|███▎      | 20149/61904 [18:39<15:54:55,  1.37s/it]
 33%|███▎      | 20150/61904 [18:41<15:57:19,  1.38s/it]
 33%|███▎      | 20151/61904 [18:42<16:39:10,  1.44s/it]
 33%|███▎      | 20152/61904 [18:44<16:18:47,  1.41s/it]
 33%|███▎      | 20153/61904 [18:45<15:53:07,  1.37s/it]
 33%|███▎      | 20154/61904 [18:46<15:52:52,  1.37s/it]
 33%|███▎      | 20155/61904 [18:48<15:59:09,  1.38s/it]
 33%|███▎      | 20156/61904 [18:49<16:03:40,  1.38s/it]
 33%|███▎      | 20157/61904 [18:50<16:07:42,  1.39s/it]
 33%|███▎      | 20158/61904 [18:52<15:42:54,  1.36s/it]
 33%|███▎      | 20159/61904 [18:53<15:49:24,  1.36s/it]
 33%|███▎      | 20160/61904 [18:55<15:57:08,  1.38s/it]
                                                        
{'loss': 2.694, 'learning_rate': 1.6765201607675352e-07, 'epoch': 5.21}

 33%|███▎      | 20160/61904 [18:55<15:57:08,  1.38s/it]
 33%|███▎      | 20161/61904 [18:56<15:46:40,  1.36s/it]
 33%|███▎      | 20162/61904 [18:57<15:15:08,  1.32s/it]
 33%|███▎      | 20163/61904 [18:58<15:02:54,  1.30s/it]
 33%|███▎      | 20164/61904 [19:00<15:33:50,  1.34s/it]
 33%|███▎      | 20165/61904 [19:01<15:28:04,  1.33s/it]
 33%|███▎      | 20166/61904 [19:02<14:56:28,  1.29s/it]
 33%|███▎      | 20167/61904 [19:04<15:31:19,  1.34s/it]
 33%|███▎      | 20168/61904 [19:05<15:45:13,  1.36s/it]
 33%|███▎      | 20169/61904 [19:07<16:22:05,  1.41s/it]
 33%|███▎      | 20170/61904 [19:08<16:25:29,  1.42s/it]
 33%|███▎      | 20171/61904 [19:09<15:50:43,  1.37s/it]
 33%|███▎      | 20172/61904 [19:11<16:17:46,  1.41s/it]
 33%|███▎      | 20173/61904 [19:12<15:49:59,  1.37s/it]
 33%|███▎      | 20174/61904 [19:13<15:49:22,  1.37s/it]
 33%|███▎      | 20175/61904 [19:15<15:45:49,  1.36s/it]
 33%|███▎      | 20176/61904 [19:16<15:39:21,  1.35s/it]
 33%|███▎      | 20177/61904 [19:18<16:01:00,  1.38s/it]
 33%|███▎      | 20178/61904 [19:19<16:02:16,  1.38s/it]
 33%|███▎      | 20179/61904 [19:20<16:00:52,  1.38s/it]
 33%|███▎      | 20180/61904 [19:22<15:53:34,  1.37s/it]
                                                        
{'loss': 2.6391, 'learning_rate': 1.676196032672112e-07, 'epoch': 5.22}

 33%|███▎      | 20180/61904 [19:22<15:53:34,  1.37s/it]
 33%|███▎      | 20181/61904 [19:23<16:47:42,  1.45s/it]
 33%|███▎      | 20182/61904 [19:25<16:41:52,  1.44s/it]
 33%|███▎      | 20183/61904 [19:26<16:35:49,  1.43s/it]
 33%|███▎      | 20184/61904 [19:28<16:32:56,  1.43s/it]
 33%|███▎      | 20185/61904 [19:29<15:54:07,  1.37s/it]
 33%|███▎      | 20186/61904 [19:30<15:47:32,  1.36s/it]
 33%|███▎      | 20187/61904 [19:31<15:34:27,  1.34s/it]
 33%|███▎      | 20188/61904 [19:33<15:50:11,  1.37s/it]
 33%|███▎      | 20189/61904 [19:34<15:28:47,  1.34s/it]
 33%|███▎      | 20190/61904 [19:35<15:16:37,  1.32s/it]
 33%|███▎      | 20191/61904 [19:37<15:15:25,  1.32s/it]
 33%|███▎      | 20192/61904 [19:38<15:21:44,  1.33s/it]
 33%|███▎      | 20193/61904 [19:40<15:38:15,  1.35s/it]
 33%|███▎      | 20194/61904 [19:41<16:07:37,  1.39s/it]
 33%|███▎      | 20195/61904 [19:42<16:20:59,  1.41s/it]
 33%|███▎      | 20196/61904 [19:44<16:03:55,  1.39s/it]
 33%|███▎      | 20197/61904 [19:45<15:42:39,  1.36s/it]
 33%|███▎      | 20198/61904 [19:46<15:34:18,  1.34s/it]
 33%|███▎      | 20199/61904 [19:48<15:11:01,  1.31s/it]
 33%|███▎      | 20200/61904 [19:49<15:15:12,  1.32s/it]
                                                        
{'loss': 2.6428, 'learning_rate': 1.6758719045766887e-07, 'epoch': 5.22}

 33%|███▎      | 20200/61904 [19:49<15:15:12,  1.32s/it]
 33%|███▎      | 20201/61904 [19:50<15:35:13,  1.35s/it]
 33%|███▎      | 20202/61904 [19:52<15:34:41,  1.34s/it]
 33%|███▎      | 20203/61904 [19:53<16:15:34,  1.40s/it]
 33%|███▎      | 20204/61904 [19:55<16:09:49,  1.40s/it]
 33%|███▎      | 20205/61904 [19:56<16:10:20,  1.40s/it]
 33%|███▎      | 20206/61904 [19:57<15:56:00,  1.38s/it]
 33%|███▎      | 20207/61904 [19:59<15:44:29,  1.36s/it]
 33%|███▎      | 20208/61904 [20:00<15:23:57,  1.33s/it]
 33%|███▎      | 20209/61904 [20:01<15:19:46,  1.32s/it]
 33%|███▎      | 20210/61904 [20:03<15:27:56,  1.34s/it]
 33%|███▎      | 20211/61904 [20:04<15:40:40,  1.35s/it]
 33%|███▎      | 20212/61904 [20:05<15:22:11,  1.33s/it]
 33%|███▎      | 20213/61904 [20:07<15:23:17,  1.33s/it]
 33%|███▎      | 20214/61904 [20:08<15:20:27,  1.32s/it]
 33%|███▎      | 20215/61904 [20:09<15:52:40,  1.37s/it]
 33%|███▎      | 20216/61904 [20:11<15:47:10,  1.36s/it]
 33%|███▎      | 20217/61904 [20:12<16:07:59,  1.39s/it]
 33%|███▎      | 20218/61904 [20:14<16:49:30,  1.45s/it]
 33%|███▎      | 20219/61904 [20:15<17:02:59,  1.47s/it]
 33%|███▎      | 20220/61904 [20:17<17:12:57,  1.49s/it]
                                                        
{'loss': 2.6796, 'learning_rate': 1.6755477764812654e-07, 'epoch': 5.23}

 33%|███▎      | 20220/61904 [20:17<17:12:57,  1.49s/it]
 33%|███▎      | 20221/61904 [20:18<17:01:21,  1.47s/it]
 33%|███▎      | 20222/61904 [20:20<16:56:07,  1.46s/it]
 33%|███▎      | 20223/61904 [20:21<17:20:44,  1.50s/it]
 33%|███▎      | 20224/61904 [20:23<16:42:42,  1.44s/it]
 33%|███▎      | 20225/61904 [20:24<16:31:07,  1.43s/it]
 33%|███▎      | 20226/61904 [20:25<16:42:16,  1.44s/it]
 33%|███▎      | 20227/61904 [20:27<16:17:55,  1.41s/it]
 33%|███▎      | 20228/61904 [20:28<15:54:08,  1.37s/it]
 33%|███▎      | 20229/61904 [20:30<16:01:24,  1.38s/it]
 33%|███▎      | 20230/61904 [20:31<15:44:42,  1.36s/it]
 33%|███▎      | 20231/61904 [20:32<15:29:26,  1.34s/it]
 33%|███▎      | 20232/61904 [20:33<14:53:33,  1.29s/it]
 33%|███▎      | 20233/61904 [20:35<15:03:28,  1.30s/it]
 33%|███▎      | 20234/61904 [20:36<15:17:04,  1.32s/it]
 33%|███▎      | 20235/61904 [20:37<15:38:17,  1.35s/it]
 33%|███▎      | 20236/61904 [20:39<16:28:15,  1.42s/it]
 33%|███▎      | 20237/61904 [20:41<16:54:37,  1.46s/it]
 33%|███▎      | 20238/61904 [20:42<16:34:41,  1.43s/it]
 33%|███▎      | 20239/61904 [20:43<16:22:13,  1.41s/it]
 33%|███▎      | 20240/61904 [20:45<16:07:21,  1.39s/it]
                                                        
{'loss': 2.6819, 'learning_rate': 1.675223648385842e-07, 'epoch': 5.23}

 33%|███▎      | 20240/61904 [20:45<16:07:21,  1.39s/it]
 33%|███▎      | 20241/61904 [20:46<16:12:23,  1.40s/it]
 33%|███▎      | 20242/61904 [20:47<16:08:42,  1.40s/it]
 33%|███▎      | 20243/61904 [20:49<17:03:24,  1.47s/it]
 33%|███▎      | 20244/61904 [20:50<16:45:18,  1.45s/it]
 33%|███▎      | 20245/61904 [20:52<16:48:41,  1.45s/it]
 33%|███▎      | 20246/61904 [20:53<16:53:07,  1.46s/it]
 33%|███▎      | 20247/61904 [20:55<16:33:05,  1.43s/it]
 33%|███▎      | 20248/61904 [20:56<16:42:27,  1.44s/it]
 33%|███▎      | 20249/61904 [20:58<16:16:33,  1.41s/it]
 33%|███▎      | 20250/61904 [20:59<15:51:10,  1.37s/it]
 33%|███▎      | 20251/61904 [21:00<15:52:27,  1.37s/it]
 33%|███▎      | 20252/61904 [21:02<15:51:12,  1.37s/it]
 33%|███▎      | 20253/61904 [21:03<15:40:05,  1.35s/it]
 33%|███▎      | 20254/61904 [21:04<15:34:53,  1.35s/it]
 33%|███▎      | 20255/61904 [21:06<16:04:28,  1.39s/it]
 33%|███▎      | 20256/61904 [21:07<15:55:23,  1.38s/it]
 33%|███▎      | 20257/61904 [21:08<15:46:28,  1.36s/it]
 33%|███▎      | 20258/61904 [21:10<15:42:57,  1.36s/it]
 33%|███▎      | 20259/61904 [21:11<15:48:40,  1.37s/it]
 33%|███▎      | 20260/61904 [21:12<15:43:09,  1.36s/it]
                                                        
{'loss': 2.6714, 'learning_rate': 1.6748995202904186e-07, 'epoch': 5.24}

 33%|███▎      | 20260/61904 [21:12<15:43:09,  1.36s/it]
 33%|███▎      | 20261/61904 [21:14<15:29:10,  1.34s/it]
 33%|███▎      | 20262/61904 [21:15<16:04:27,  1.39s/it]
 33%|███▎      | 20263/61904 [21:17<15:49:14,  1.37s/it]
 33%|███▎      | 20264/61904 [21:18<15:41:33,  1.36s/it]
 33%|███▎      | 20265/61904 [21:19<16:17:17,  1.41s/it]
 33%|███▎      | 20266/61904 [21:21<15:59:03,  1.38s/it]
 33%|███▎      | 20267/61904 [21:22<15:55:30,  1.38s/it]
 33%|███▎      | 20268/61904 [21:24<16:14:36,  1.40s/it]
 33%|███▎      | 20269/61904 [21:25<16:25:12,  1.42s/it]
 33%|███▎      | 20270/61904 [21:26<16:11:47,  1.40s/it]
 33%|███▎      | 20271/61904 [21:28<15:55:27,  1.38s/it]
 33%|███▎      | 20272/61904 [21:29<16:19:48,  1.41s/it]
 33%|███▎      | 20273/61904 [21:31<16:23:03,  1.42s/it]
 33%|███▎      | 20274/61904 [21:32<16:21:26,  1.41s/it]
 33%|███▎      | 20275/61904 [21:33<15:45:46,  1.36s/it]
 33%|███▎      | 20276/61904 [21:35<16:06:37,  1.39s/it]
 33%|███▎      | 20277/61904 [21:36<15:45:47,  1.36s/it]
 33%|███▎      | 20278/61904 [21:37<15:49:21,  1.37s/it]
 33%|███▎      | 20279/61904 [21:39<15:36:51,  1.35s/it]
 33%|███▎      | 20280/61904 [21:40<16:02:41,  1.39s/it]
                                                        
{'loss': 2.6392, 'learning_rate': 1.6745753921949955e-07, 'epoch': 5.24}

 33%|███▎      | 20280/61904 [21:40<16:02:41,  1.39s/it]
 33%|███▎      | 20281/61904 [21:42<16:18:09,  1.41s/it]
 33%|███▎      | 20282/61904 [21:43<16:57:19,  1.47s/it]
 33%|███▎      | 20283/61904 [21:45<16:48:58,  1.45s/it]
 33%|███▎      | 20284/61904 [21:46<16:26:26,  1.42s/it]
 33%|███▎      | 20285/61904 [21:47<16:10:28,  1.40s/it]
 33%|███▎      | 20286/61904 [21:49<15:44:41,  1.36s/it]
 33%|███▎      | 20287/61904 [21:50<16:09:52,  1.40s/it]
 33%|███▎      | 20288/61904 [21:52<16:00:36,  1.38s/it]
 33%|███▎      | 20289/61904 [21:53<15:53:44,  1.38s/it]
 33%|███▎      | 20290/61904 [21:54<15:33:52,  1.35s/it]
 33%|███▎      | 20291/61904 [21:56<15:51:26,  1.37s/it]
 33%|███▎      | 20292/61904 [21:57<15:35:02,  1.35s/it]
 33%|███▎      | 20293/61904 [21:58<16:15:58,  1.41s/it]
 33%|███▎      | 20294/61904 [22:00<16:04:07,  1.39s/it]
 33%|███▎      | 20295/61904 [22:01<15:57:57,  1.38s/it]
 33%|███▎      | 20296/61904 [22:03<16:17:53,  1.41s/it]
 33%|███▎      | 20297/61904 [22:04<15:51:44,  1.37s/it]
 33%|███▎      | 20298/61904 [22:05<15:54:55,  1.38s/it]
 33%|███▎      | 20299/61904 [22:07<15:53:33,  1.38s/it]
 33%|███▎      | 20300/61904 [22:08<16:09:04,  1.40s/it]
                                                        
{'loss': 2.7057, 'learning_rate': 1.674251264099572e-07, 'epoch': 5.25}

 33%|███▎      | 20300/61904 [22:08<16:09:04,  1.40s/it]
 33%|███▎      | 20301/61904 [22:10<16:20:14,  1.41s/it]
 33%|███▎      | 20302/61904 [22:11<16:14:02,  1.40s/it]
 33%|███▎      | 20303/61904 [22:12<15:36:19,  1.35s/it]
 33%|███▎      | 20304/61904 [22:13<15:31:36,  1.34s/it]
 33%|███▎      | 20305/61904 [22:15<15:34:08,  1.35s/it]
 33%|███▎      | 20306/61904 [22:16<15:51:42,  1.37s/it]
 33%|███▎      | 20307/61904 [22:18<16:18:56,  1.41s/it]
 33%|███▎      | 20308/61904 [22:19<16:04:45,  1.39s/it]
 33%|███▎      | 20309/61904 [22:21<16:41:36,  1.44s/it]
 33%|███▎      | 20310/61904 [22:22<16:13:21,  1.40s/it]
 33%|███▎      | 20311/61904 [22:23<16:13:39,  1.40s/it]
 33%|███▎      | 20312/61904 [22:25<16:04:32,  1.39s/it]
 33%|███▎      | 20313/61904 [22:26<16:25:59,  1.42s/it]
 33%|███▎      | 20314/61904 [22:28<16:00:29,  1.39s/it]
 33%|███▎      | 20315/61904 [22:29<16:00:07,  1.39s/it]
 33%|███▎      | 20316/61904 [22:30<15:52:42,  1.37s/it]
 33%|███▎      | 20317/61904 [22:32<15:59:40,  1.38s/it]
 33%|███▎      | 20318/61904 [22:33<15:53:08,  1.38s/it]
 33%|███▎      | 20319/61904 [22:34<15:47:45,  1.37s/it]
 33%|███▎      | 20320/61904 [22:36<16:51:00,  1.46s/it]
                                                        
{'loss': 2.6676, 'learning_rate': 1.6739271360041487e-07, 'epoch': 5.25}

 33%|███▎      | 20320/61904 [22:36<16:51:00,  1.46s/it]
 33%|███▎      | 20321/61904 [22:37<16:29:42,  1.43s/it]
 33%|███▎      | 20322/61904 [22:39<16:55:25,  1.47s/it]
 33%|███▎      | 20323/61904 [22:40<16:50:14,  1.46s/it]
 33%|███▎      | 20324/61904 [22:42<16:23:36,  1.42s/it]
 33%|███▎      | 20325/61904 [22:43<15:54:58,  1.38s/it]
 33%|███▎      | 20326/61904 [22:44<15:58:04,  1.38s/it]
 33%|███▎      | 20327/61904 [22:46<15:38:48,  1.35s/it]
 33%|███▎      | 20328/61904 [22:47<15:43:23,  1.36s/it]
 33%|███▎      | 20329/61904 [22:49<16:13:24,  1.40s/it]
 33%|███▎      | 20330/61904 [22:50<16:03:03,  1.39s/it]
 33%|███▎      | 20331/61904 [22:51<15:45:26,  1.36s/it]
 33%|███▎      | 20332/61904 [22:53<16:25:50,  1.42s/it]
 33%|███▎      | 20333/61904 [22:54<16:11:37,  1.40s/it]
 33%|███▎      | 20334/61904 [22:55<15:52:22,  1.37s/it]
 33%|███▎      | 20335/61904 [22:57<15:28:50,  1.34s/it]
 33%|███▎      | 20336/61904 [22:58<15:58:00,  1.38s/it]
 33%|███▎      | 20337/61904 [23:00<16:02:56,  1.39s/it]
 33%|███▎      | 20338/61904 [23:01<15:55:51,  1.38s/it]
 33%|███▎      | 20339/61904 [23:02<15:44:32,  1.36s/it]
 33%|███▎      | 20340/61904 [23:04<15:39:28,  1.36s/it]
                                                        
{'loss': 2.7037, 'learning_rate': 1.6736030079087256e-07, 'epoch': 5.26}

 33%|███▎      | 20340/61904 [23:04<15:39:28,  1.36s/it]
 33%|███▎      | 20341/61904 [23:05<16:06:42,  1.40s/it]
 33%|███▎      | 20342/61904 [23:07<16:09:07,  1.40s/it]
 33%|███▎      | 20343/61904 [23:08<16:30:05,  1.43s/it]
 33%|███▎      | 20344/61904 [23:09<16:13:17,  1.41s/it]
 33%|███▎      | 20345/61904 [23:11<16:12:02,  1.40s/it]
 33%|███▎      | 20346/61904 [23:12<15:42:13,  1.36s/it]
 33%|███▎      | 20347/61904 [23:13<15:20:59,  1.33s/it]
 33%|███▎      | 20348/61904 [23:15<15:46:09,  1.37s/it]
 33%|███▎      | 20349/61904 [23:16<16:19:16,  1.41s/it]
 33%|███▎      | 20350/61904 [23:18<16:45:23,  1.45s/it]
 33%|███▎      | 20351/61904 [23:19<16:20:15,  1.42s/it]
 33%|███▎      | 20352/61904 [23:21<16:30:35,  1.43s/it]
 33%|███▎      | 20353/61904 [23:22<16:23:50,  1.42s/it]
 33%|███▎      | 20354/61904 [23:24<16:58:21,  1.47s/it]
 33%|███▎      | 20355/61904 [23:25<16:47:36,  1.46s/it]
 33%|███▎      | 20356/61904 [23:26<16:38:09,  1.44s/it]
 33%|███▎      | 20357/61904 [23:28<16:28:11,  1.43s/it]
 33%|███▎      | 20358/61904 [23:29<15:54:38,  1.38s/it]
 33%|███▎      | 20359/61904 [23:31<16:00:09,  1.39s/it]
 33%|███▎      | 20360/61904 [23:32<16:18:30,  1.41s/it]
                                                        
{'loss': 2.7595, 'learning_rate': 1.6732788798133022e-07, 'epoch': 5.26}

 33%|███▎      | 20360/61904 [23:32<16:18:30,  1.41s/it]
 33%|███▎      | 20361/61904 [23:33<15:44:04,  1.36s/it]
 33%|███▎      | 20362/61904 [23:35<15:52:14,  1.38s/it]
 33%|███▎      | 20363/61904 [23:36<16:21:27,  1.42s/it]
 33%|███▎      | 20364/61904 [23:38<16:07:51,  1.40s/it]
 33%|███▎      | 20365/61904 [23:39<16:08:15,  1.40s/it]
 33%|███▎      | 20366/61904 [23:40<16:18:34,  1.41s/it]
 33%|███▎      | 20367/61904 [23:42<16:10:59,  1.40s/it]
 33%|███▎      | 20368/61904 [23:43<15:51:06,  1.37s/it]
 33%|███▎      | 20369/61904 [23:45<16:09:10,  1.40s/it]
 33%|███▎      | 20370/61904 [23:46<15:32:43,  1.35s/it]
 33%|███▎      | 20371/61904 [23:47<15:15:09,  1.32s/it]
 33%|███▎      | 20372/61904 [23:48<15:33:16,  1.35s/it]
 33%|███▎      | 20373/61904 [23:50<15:36:35,  1.35s/it]
 33%|███▎      | 20374/61904 [23:51<15:53:00,  1.38s/it]
 33%|███▎      | 20375/61904 [23:52<15:34:25,  1.35s/it]
 33%|███▎      | 20376/61904 [23:54<15:44:52,  1.37s/it]
 33%|███▎      | 20377/61904 [23:55<15:34:54,  1.35s/it]
 33%|███▎      | 20378/61904 [23:57<16:07:44,  1.40s/it]
 33%|███▎      | 20379/61904 [23:58<16:03:47,  1.39s/it]
 33%|███▎      | 20380/61904 [24:00<16:20:18,  1.42s/it]
                                                        
{'loss': 2.6665, 'learning_rate': 1.6729547517178788e-07, 'epoch': 5.27}

 33%|███▎      | 20380/61904 [24:00<16:20:18,  1.42s/it]
 33%|███▎      | 20381/61904 [24:01<16:06:46,  1.40s/it]
 33%|███▎      | 20382/61904 [24:02<15:59:39,  1.39s/it]
 33%|███▎      | 20383/61904 [24:04<16:38:01,  1.44s/it]
 33%|███▎      | 20384/61904 [24:05<16:22:15,  1.42s/it]
 33%|███▎      | 20385/61904 [24:07<16:17:49,  1.41s/it]
 33%|███▎      | 20386/61904 [24:08<16:02:28,  1.39s/it]
 33%|███▎      | 20387/61904 [24:09<15:55:40,  1.38s/it]
 33%|███▎      | 20388/61904 [24:11<16:14:04,  1.41s/it]
 33%|███▎      | 20389/61904 [24:12<16:40:10,  1.45s/it]
 33%|███▎      | 20390/61904 [24:14<16:25:38,  1.42s/it]
 33%|███▎      | 20391/61904 [24:15<16:18:39,  1.41s/it]
 33%|███▎      | 20392/61904 [24:16<16:07:21,  1.40s/it]
 33%|███▎      | 20393/61904 [24:18<16:08:49,  1.40s/it]
 33%|███▎      | 20394/61904 [24:19<15:59:37,  1.39s/it]
 33%|███▎      | 20395/61904 [24:21<16:13:29,  1.41s/it]
 33%|███▎      | 20396/61904 [24:22<16:12:14,  1.41s/it]
 33%|███▎      | 20397/61904 [24:23<15:52:04,  1.38s/it]
 33%|███▎      | 20398/61904 [24:25<16:11:02,  1.40s/it]
 33%|███▎      | 20399/61904 [24:26<15:40:22,  1.36s/it]
 33%|███▎      | 20400/61904 [24:28<16:01:03,  1.39s/it]
                                                        
{'loss': 2.6281, 'learning_rate': 1.6726306236224554e-07, 'epoch': 5.27}

 33%|███▎      | 20400/61904 [24:28<16:01:03,  1.39s/it]
 33%|███▎      | 20401/61904 [24:29<15:51:51,  1.38s/it]
 33%|███▎      | 20402/61904 [24:30<15:46:09,  1.37s/it]
 33%|███▎      | 20403/61904 [24:32<15:55:57,  1.38s/it]
 33%|███▎      | 20404/61904 [24:33<15:33:17,  1.35s/it]
 33%|███▎      | 20405/61904 [24:34<15:49:24,  1.37s/it]
 33%|███▎      | 20406/61904 [24:36<15:34:50,  1.35s/it]
 33%|███▎      | 20407/61904 [24:37<15:56:39,  1.38s/it]
 33%|███▎      | 20408/61904 [24:38<15:41:31,  1.36s/it]
 33%|███▎      | 20409/61904 [24:40<16:22:45,  1.42s/it]
 33%|███▎      | 20410/61904 [24:41<15:55:17,  1.38s/it]
 33%|███▎      | 20411/61904 [24:43<15:56:06,  1.38s/it]
 33%|███▎      | 20412/61904 [24:44<15:55:52,  1.38s/it]
 33%|███▎      | 20413/61904 [24:46<16:30:16,  1.43s/it]
 33%|███▎      | 20414/61904 [24:47<16:50:40,  1.46s/it]
 33%|███▎      | 20415/61904 [24:48<16:20:20,  1.42s/it]
 33%|███▎      | 20416/61904 [24:50<16:23:16,  1.42s/it]
 33%|███▎      | 20417/61904 [24:51<17:01:42,  1.48s/it]
 33%|███▎      | 20418/61904 [24:53<17:18:23,  1.50s/it]
 33%|███▎      | 20419/61904 [24:55<17:36:10,  1.53s/it]
 33%|███▎      | 20420/61904 [24:56<17:17:42,  1.50s/it]
                                                        
{'loss': 2.6047, 'learning_rate': 1.6723064955270323e-07, 'epoch': 5.28}

 33%|███▎      | 20420/61904 [24:56<17:17:42,  1.50s/it]
 33%|███▎      | 20421/61904 [24:57<16:30:22,  1.43s/it]
 33%|███▎      | 20422/61904 [24:59<15:55:07,  1.38s/it]
 33%|███▎      | 20423/61904 [25:00<15:43:51,  1.37s/it]
 33%|███▎      | 20424/61904 [25:01<16:21:24,  1.42s/it]
 33%|███▎      | 20425/61904 [25:03<15:58:59,  1.39s/it]
 33%|███▎      | 20426/61904 [25:04<15:47:58,  1.37s/it]
 33%|███▎      | 20427/61904 [25:05<15:45:35,  1.37s/it]
 33%|███▎      | 20428/61904 [25:07<15:37:49,  1.36s/it]
 33%|███▎      | 20429/61904 [25:08<15:55:33,  1.38s/it]
 33%|███▎      | 20430/61904 [25:10<15:57:59,  1.39s/it]
 33%|███▎      | 20431/61904 [25:11<15:56:45,  1.38s/it]
 33%|███▎      | 20432/61904 [25:12<15:37:15,  1.36s/it]
 33%|███▎      | 20433/61904 [25:14<15:33:19,  1.35s/it]
 33%|███▎      | 20434/61904 [25:15<16:09:01,  1.40s/it]
 33%|███▎      | 20435/61904 [25:17<16:12:44,  1.41s/it]
 33%|███▎      | 20436/61904 [25:18<16:24:10,  1.42s/it]
 33%|███▎      | 20437/61904 [25:19<16:17:24,  1.41s/it]
 33%|███▎      | 20438/61904 [25:21<16:13:01,  1.41s/it]
 33%|███▎      | 20439/61904 [25:22<16:27:35,  1.43s/it]
 33%|███▎      | 20440/61904 [25:24<16:11:20,  1.41s/it]
                                                        
{'loss': 2.6466, 'learning_rate': 1.671982367431609e-07, 'epoch': 5.28}

 33%|███▎      | 20440/61904 [25:24<16:11:20,  1.41s/it]
 33%|███▎      | 20441/61904 [25:25<16:15:37,  1.41s/it]
 33%|███▎      | 20442/61904 [25:27<16:27:41,  1.43s/it]
 33%|███▎      | 20443/61904 [25:28<16:32:27,  1.44s/it]
 33%|███▎      | 20444/61904 [25:29<16:10:25,  1.40s/it]
 33%|███▎      | 20445/61904 [25:31<16:04:29,  1.40s/it]
 33%|███▎      | 20446/61904 [25:32<15:55:00,  1.38s/it]
 33%|███▎      | 20447/61904 [25:34<16:06:42,  1.40s/it]
 33%|███▎      | 20448/61904 [25:35<16:09:17,  1.40s/it]
 33%|███▎      | 20449/61904 [25:36<16:21:59,  1.42s/it]
 33%|███▎      | 20450/61904 [25:38<15:59:43,  1.39s/it]
 33%|███▎      | 20451/61904 [25:39<17:05:33,  1.48s/it]
 33%|███▎      | 20452/61904 [25:41<16:54:22,  1.47s/it]
 33%|███▎      | 20453/61904 [25:42<16:52:23,  1.47s/it]
 33%|███▎      | 20454/61904 [25:44<16:16:02,  1.41s/it]
 33%|███▎      | 20455/61904 [25:45<16:09:38,  1.40s/it]
 33%|███▎      | 20456/61904 [25:46<16:10:38,  1.41s/it]
 33%|███▎      | 20457/61904 [25:48<16:13:00,  1.41s/it]
 33%|███▎      | 20458/61904 [25:49<16:18:43,  1.42s/it]
 33%|███▎      | 20459/61904 [25:51<16:42:38,  1.45s/it]
 33%|███▎      | 20460/61904 [25:52<16:25:23,  1.43s/it]
                                                        
{'loss': 2.6026, 'learning_rate': 1.6716582393361856e-07, 'epoch': 5.29}

 33%|███▎      | 20460/61904 [25:52<16:25:23,  1.43s/it]
 33%|███▎      | 20461/61904 [25:54<16:23:00,  1.42s/it]
 33%|███▎      | 20462/61904 [25:55<16:20:10,  1.42s/it]
 33%|███▎      | 20463/61904 [25:56<15:59:23,  1.39s/it]
 33%|███▎      | 20464/61904 [25:58<15:41:21,  1.36s/it]
 33%|███▎      | 20465/61904 [25:59<15:49:40,  1.38s/it]
 33%|███▎      | 20466/61904 [26:00<15:57:33,  1.39s/it]
 33%|███▎      | 20467/61904 [26:02<16:02:04,  1.39s/it]
 33%|███▎      | 20468/61904 [26:03<16:32:29,  1.44s/it]
 33%|███▎      | 20469/61904 [26:05<16:45:48,  1.46s/it]
 33%|███▎      | 20470/61904 [26:06<16:25:20,  1.43s/it]
 33%|███▎      | 20471/61904 [26:08<16:04:29,  1.40s/it]
 33%|███▎      | 20472/61904 [26:09<16:32:22,  1.44s/it]
 33%|███▎      | 20473/61904 [26:11<16:34:04,  1.44s/it]
 33%|███▎      | 20474/61904 [26:12<16:26:53,  1.43s/it]
 33%|███▎      | 20475/61904 [26:13<16:27:58,  1.43s/it]
 33%|███▎      | 20476/61904 [26:15<16:07:19,  1.40s/it]
 33%|███▎      | 20477/61904 [26:16<16:07:51,  1.40s/it]
 33%|███▎      | 20478/61904 [26:17<16:03:53,  1.40s/it]
 33%|███▎      | 20479/61904 [26:19<15:54:23,  1.38s/it]
 33%|███▎      | 20480/61904 [26:20<16:07:18,  1.40s/it]
                                                        
{'loss': 2.6714, 'learning_rate': 1.6713341112407622e-07, 'epoch': 5.29}

 33%|███▎      | 20480/61904 [26:20<16:07:18,  1.40s/it]
 33%|███▎      | 20481/61904 [26:22<15:57:59,  1.39s/it]
 33%|███▎      | 20482/61904 [26:23<15:49:16,  1.38s/it]
 33%|███▎      | 20483/61904 [26:24<15:43:27,  1.37s/it]
 33%|███▎      | 20484/61904 [26:26<15:37:06,  1.36s/it]
 33%|███▎      | 20485/61904 [26:27<15:39:40,  1.36s/it]
 33%|███▎      | 20486/61904 [26:29<16:13:43,  1.41s/it]
 33%|███▎      | 20487/61904 [26:30<16:11:48,  1.41s/it]
 33%|███▎      | 20488/61904 [26:31<16:08:41,  1.40s/it]
 33%|███▎      | 20489/61904 [26:33<16:07:17,  1.40s/it]
 33%|███▎      | 20490/61904 [26:34<16:05:15,  1.40s/it]
 33%|███▎      | 20491/61904 [26:36<16:15:58,  1.41s/it]
 33%|███▎      | 20492/61904 [26:37<16:19:43,  1.42s/it]
 33%|███▎      | 20493/61904 [26:38<16:33:27,  1.44s/it]
 33%|███▎      | 20494/61904 [26:40<16:38:23,  1.45s/it]
 33%|███▎      | 20495/61904 [26:41<16:04:01,  1.40s/it]
 33%|███▎      | 20496/61904 [26:43<15:51:34,  1.38s/it]
 33%|███▎      | 20497/61904 [26:44<15:49:23,  1.38s/it]
 33%|███▎      | 20498/61904 [26:45<15:57:13,  1.39s/it]
 33%|███▎      | 20499/61904 [26:47<15:48:37,  1.37s/it]
 33%|███▎      | 20500/61904 [26:48<16:14:58,  1.41s/it]
                                                        
{'loss': 2.6351, 'learning_rate': 1.671009983145339e-07, 'epoch': 5.3}

 33%|███▎      | 20500/61904 [26:48<16:14:58,  1.41s/it]
 33%|███▎      | 20501/61904 [26:49<15:35:09,  1.36s/it]
 33%|███▎      | 20502/61904 [26:51<15:25:44,  1.34s/it]
 33%|███▎      | 20503/61904 [26:52<15:39:53,  1.36s/it]
 33%|███▎      | 20504/61904 [26:54<15:47:12,  1.37s/it]
 33%|███▎      | 20505/61904 [26:55<15:27:28,  1.34s/it]
 33%|███▎      | 20506/61904 [26:56<15:32:24,  1.35s/it]
 33%|███▎      | 20507/61904 [26:58<15:36:36,  1.36s/it]
 33%|███▎      | 20508/61904 [26:59<16:03:41,  1.40s/it]
 33%|███▎      | 20509/61904 [27:01<16:18:32,  1.42s/it]
 33%|███▎      | 20510/61904 [27:02<16:16:07,  1.41s/it]
 33%|███▎      | 20511/61904 [27:03<16:03:48,  1.40s/it]
 33%|███▎      | 20512/61904 [27:05<16:02:27,  1.40s/it]
 33%|███▎      | 20513/61904 [27:06<16:20:21,  1.42s/it]
 33%|███▎      | 20514/61904 [27:08<16:43:59,  1.46s/it]
 33%|███▎      | 20515/61904 [27:09<16:34:45,  1.44s/it]
 33%|███▎      | 20516/61904 [27:11<16:45:56,  1.46s/it]
 33%|███▎      | 20517/61904 [27:12<16:31:18,  1.44s/it]
 33%|███▎      | 20518/61904 [27:13<16:38:32,  1.45s/it]
 33%|███▎      | 20519/61904 [27:15<16:02:23,  1.40s/it]
 33%|███▎      | 20520/61904 [27:16<16:22:00,  1.42s/it]
                                                        
{'loss': 2.6293, 'learning_rate': 1.6706858550499157e-07, 'epoch': 5.3}

 33%|███▎      | 20520/61904 [27:16<16:22:00,  1.42s/it]
 33%|███▎      | 20521/61904 [27:18<16:40:51,  1.45s/it]
 33%|███▎      | 20522/61904 [27:19<16:16:05,  1.42s/it]
 33%|███▎      | 20523/61904 [27:21<16:20:43,  1.42s/it]
 33%|███▎      | 20524/61904 [27:22<16:36:59,  1.45s/it]
 33%|███▎      | 20525/61904 [27:23<16:10:51,  1.41s/it]
 33%|███▎      | 20526/61904 [27:25<16:02:20,  1.40s/it]
 33%|███▎      | 20527/61904 [27:26<16:24:35,  1.43s/it]
 33%|███▎      | 20528/61904 [27:28<16:14:41,  1.41s/it]
 33%|███▎      | 20529/61904 [27:29<16:08:42,  1.40s/it]
 33%|███▎      | 20530/61904 [27:30<16:11:59,  1.41s/it]
 33%|███▎      | 20531/61904 [27:32<16:14:03,  1.41s/it]
 33%|███▎      | 20532/61904 [27:33<15:50:44,  1.38s/it]
 33%|███▎      | 20533/61904 [27:35<15:59:15,  1.39s/it]
 33%|███▎      | 20534/61904 [27:36<15:52:12,  1.38s/it]
 33%|███▎      | 20535/61904 [27:37<16:02:34,  1.40s/it]
 33%|███▎      | 20536/61904 [27:39<15:39:08,  1.36s/it]
 33%|███▎      | 20537/61904 [27:40<16:11:05,  1.41s/it]
 33%|███▎      | 20538/61904 [27:41<16:05:37,  1.40s/it]
 33%|███▎      | 20539/61904 [27:43<16:13:25,  1.41s/it]
 33%|███▎      | 20540/61904 [27:44<15:52:06,  1.38s/it]
                                                        
{'loss': 2.6368, 'learning_rate': 1.6703617269544923e-07, 'epoch': 5.31}

 33%|███▎      | 20540/61904 [27:44<15:52:06,  1.38s/it]
 33%|███▎      | 20541/61904 [27:46<16:03:30,  1.40s/it]
 33%|███▎      | 20542/61904 [27:47<16:16:02,  1.42s/it]
 33%|███▎      | 20543/61904 [27:49<17:00:46,  1.48s/it]
 33%|███▎      | 20544/61904 [27:50<17:44:03,  1.54s/it]
 33%|███▎      | 20545/61904 [27:52<17:11:30,  1.50s/it]
 33%|███▎      | 20546/61904 [27:53<16:42:55,  1.45s/it]
 33%|███▎      | 20547/61904 [27:55<16:12:33,  1.41s/it]
 33%|███▎      | 20548/61904 [27:56<15:54:18,  1.38s/it]
 33%|███▎      | 20549/61904 [27:57<15:43:58,  1.37s/it]
 33%|███▎      | 20550/61904 [27:59<16:03:51,  1.40s/it]
 33%|███▎      | 20551/61904 [28:00<16:29:26,  1.44s/it]
 33%|███▎      | 20552/61904 [28:02<16:17:59,  1.42s/it]
 33%|███▎      | 20553/61904 [28:03<16:18:08,  1.42s/it]
 33%|███▎      | 20554/61904 [28:04<16:07:25,  1.40s/it]
 33%|███▎      | 20555/61904 [28:06<16:28:52,  1.43s/it]
 33%|███▎      | 20556/61904 [28:07<16:37:02,  1.45s/it]
 33%|███▎      | 20557/61904 [28:09<16:10:09,  1.41s/it]
 33%|███▎      | 20558/61904 [28:10<15:55:05,  1.39s/it]
 33%|███▎      | 20559/61904 [28:12<16:29:40,  1.44s/it]
 33%|███▎      | 20560/61904 [28:13<15:54:56,  1.39s/it]
                                                        
{'loss': 2.6963, 'learning_rate': 1.6700375988590692e-07, 'epoch': 5.31}

 33%|███▎      | 20560/61904 [28:13<15:54:56,  1.39s/it]
 33%|███▎      | 20561/61904 [28:14<16:04:14,  1.40s/it]
 33%|███▎      | 20562/61904 [28:16<16:34:42,  1.44s/it]
 33%|███▎      | 20563/61904 [28:17<16:32:50,  1.44s/it]
 33%|███▎      | 20564/61904 [28:19<16:15:25,  1.42s/it]
 33%|███▎      | 20565/61904 [28:20<16:28:24,  1.43s/it]
 33%|███▎      | 20566/61904 [28:22<16:45:14,  1.46s/it]
 33%|███▎      | 20567/61904 [28:23<16:25:24,  1.43s/it]
 33%|███▎      | 20568/61904 [28:24<16:46:14,  1.46s/it]
 33%|███▎      | 20569/61904 [28:26<16:38:00,  1.45s/it]
 33%|███▎      | 20570/61904 [28:27<16:02:29,  1.40s/it]
 33%|███▎      | 20571/61904 [28:28<15:30:05,  1.35s/it]
 33%|███▎      | 20572/61904 [28:30<15:25:40,  1.34s/it]
 33%|███▎      | 20573/61904 [28:31<15:38:03,  1.36s/it]
 33%|███▎      | 20574/61904 [28:32<15:29:25,  1.35s/it]
 33%|███▎      | 20575/61904 [28:34<16:21:32,  1.42s/it]
 33%|███▎      | 20576/61904 [28:35<15:56:27,  1.39s/it]
 33%|███▎      | 20577/61904 [28:37<15:53:08,  1.38s/it]
 33%|███▎      | 20578/61904 [28:38<15:48:27,  1.38s/it]
 33%|███▎      | 20579/61904 [28:39<15:49:05,  1.38s/it]
 33%|███▎      | 20580/61904 [28:41<15:50:38,  1.38s/it]
                                                        
{'loss': 2.6401, 'learning_rate': 1.6697134707636458e-07, 'epoch': 5.32}

 33%|███▎      | 20580/61904 [28:41<15:50:38,  1.38s/it]
 33%|███▎      | 20581/61904 [28:42<15:25:54,  1.34s/it]
 33%|███▎      | 20582/61904 [28:44<16:05:25,  1.40s/it]
 33%|███▎      | 20583/61904 [28:45<16:05:50,  1.40s/it]
 33%|███▎      | 20584/61904 [28:46<15:51:50,  1.38s/it]
 33%|███▎      | 20585/61904 [28:48<16:01:35,  1.40s/it]
 33%|███▎      | 20586/61904 [28:49<15:44:12,  1.37s/it]
 33%|███▎      | 20587/61904 [28:50<15:46:36,  1.37s/it]
 33%|███▎      | 20588/61904 [28:52<15:52:33,  1.38s/it]
 33%|███▎      | 20589/61904 [28:53<16:23:54,  1.43s/it]
 33%|███▎      | 20590/61904 [28:55<16:06:41,  1.40s/it]
 33%|███▎      | 20591/61904 [28:56<16:05:46,  1.40s/it]
 33%|███▎      | 20592/61904 [28:58<16:32:40,  1.44s/it]
 33%|███▎      | 20593/61904 [28:59<16:12:30,  1.41s/it]
 33%|███▎      | 20594/61904 [29:00<16:15:04,  1.42s/it]
 33%|███▎      | 20595/61904 [29:02<16:34:16,  1.44s/it]
 33%|███▎      | 20596/61904 [29:04<16:53:48,  1.47s/it]
 33%|███▎      | 20597/61904 [29:05<17:19:04,  1.51s/it]
 33%|███▎      | 20598/61904 [29:06<16:36:59,  1.45s/it]
 33%|███▎      | 20599/61904 [29:08<16:24:44,  1.43s/it]
 33%|███▎      | 20600/61904 [29:09<15:59:20,  1.39s/it]
                                                        
{'loss': 2.669, 'learning_rate': 1.6693893426682224e-07, 'epoch': 5.32}

 33%|███▎      | 20600/61904 [29:09<15:59:20,  1.39s/it]
 33%|███▎      | 20601/61904 [29:10<15:51:51,  1.38s/it]
 33%|███▎      | 20602/61904 [29:12<15:49:50,  1.38s/it]
 33%|███▎      | 20603/61904 [29:13<15:35:07,  1.36s/it]
 33%|███▎      | 20604/61904 [29:15<15:57:23,  1.39s/it]
 33%|███▎      | 20605/61904 [29:16<15:38:55,  1.36s/it]
 33%|███▎      | 20606/61904 [29:17<16:14:25,  1.42s/it]
 33%|███▎      | 20607/61904 [29:19<15:46:57,  1.38s/it]
 33%|███▎      | 20608/61904 [29:20<15:23:40,  1.34s/it]
 33%|███▎      | 20609/61904 [29:21<15:38:03,  1.36s/it]
 33%|███▎      | 20610/61904 [29:23<15:36:18,  1.36s/it]
 33%|███▎      | 20611/61904 [29:24<15:57:39,  1.39s/it]
 33%|███▎      | 20612/61904 [29:26<15:46:04,  1.37s/it]
 33%|███▎      | 20613/61904 [29:27<16:07:09,  1.41s/it]
 33%|███▎      | 20614/61904 [29:28<16:08:28,  1.41s/it]
 33%|███▎      | 20615/61904 [29:30<15:45:47,  1.37s/it]
 33%|███▎      | 20616/61904 [29:31<15:50:23,  1.38s/it]
 33%|███▎      | 20617/61904 [29:33<15:53:45,  1.39s/it]
 33%|███▎      | 20618/61904 [29:34<16:06:18,  1.40s/it]
 33%|███▎      | 20619/61904 [29:35<15:43:27,  1.37s/it]
 33%|███▎      | 20620/61904 [29:37<15:30:09,  1.35s/it]
                                                        
{'loss': 2.6384, 'learning_rate': 1.669065214572799e-07, 'epoch': 5.33}

 33%|███▎      | 20620/61904 [29:37<15:30:09,  1.35s/it]
 33%|███▎      | 20621/61904 [29:38<15:19:56,  1.34s/it]
 33%|███▎      | 20622/61904 [29:39<15:16:44,  1.33s/it]
 33%|███▎      | 20623/61904 [29:41<15:09:38,  1.32s/it]
 33%|███▎      | 20624/61904 [29:42<15:14:24,  1.33s/it]
 33%|███▎      | 20625/61904 [29:43<16:02:51,  1.40s/it]
 33%|███▎      | 20626/61904 [29:45<15:58:59,  1.39s/it]
 33%|███▎      | 20627/61904 [29:46<15:59:58,  1.40s/it]
 33%|███▎      | 20628/61904 [29:48<15:49:10,  1.38s/it]
 33%|███▎      | 20629/61904 [29:49<15:27:32,  1.35s/it]
 33%|███▎      | 20630/61904 [29:50<15:19:47,  1.34s/it]
 33%|███▎      | 20631/61904 [29:51<15:14:07,  1.33s/it]
 33%|███▎      | 20632/61904 [29:53<15:24:48,  1.34s/it]
 33%|███▎      | 20633/61904 [29:54<15:24:25,  1.34s/it]
 33%|███▎      | 20634/61904 [29:55<14:56:25,  1.30s/it]
 33%|███▎      | 20635/61904 [29:57<15:07:27,  1.32s/it]
 33%|███▎      | 20636/61904 [29:58<15:31:27,  1.35s/it]
 33%|███▎      | 20637/61904 [29:59<15:12:11,  1.33s/it]
 33%|███▎      | 20638/61904 [30:01<15:10:20,  1.32s/it]
 33%|███▎      | 20639/61904 [30:02<15:10:10,  1.32s/it]
 33%|███▎      | 20640/61904 [30:03<14:54:01,  1.30s/it]
                                                        
{'loss': 2.7073, 'learning_rate': 1.6687410864773757e-07, 'epoch': 5.33}

 33%|███▎      | 20640/61904 [30:03<14:54:01,  1.30s/it]
 33%|███▎      | 20641/61904 [30:05<15:12:11,  1.33s/it]
 33%|███▎      | 20642/61904 [30:06<15:49:24,  1.38s/it]
 33%|███▎      | 20643/61904 [30:08<16:41:16,  1.46s/it]
 33%|███▎      | 20644/61904 [30:09<16:46:20,  1.46s/it]
 33%|███▎      | 20645/61904 [30:11<16:33:18,  1.44s/it]
 33%|███▎      | 20646/61904 [30:12<16:54:58,  1.48s/it]
 33%|███▎      | 20647/61904 [30:14<16:23:13,  1.43s/it]
 33%|███▎      | 20648/61904 [30:15<16:04:59,  1.40s/it]
 33%|███▎      | 20649/61904 [30:16<16:03:58,  1.40s/it]
 33%|███▎      | 20650/61904 [30:18<15:49:21,  1.38s/it]
 33%|███▎      | 20651/61904 [30:19<15:57:37,  1.39s/it]
 33%|███▎      | 20652/61904 [30:20<15:40:44,  1.37s/it]
 33%|███▎      | 20653/61904 [30:22<15:44:49,  1.37s/it]
 33%|███▎      | 20654/61904 [30:23<15:42:46,  1.37s/it]
 33%|███▎      | 20655/61904 [30:25<15:47:34,  1.38s/it]
 33%|███▎      | 20656/61904 [30:26<15:52:18,  1.39s/it]
 33%|███▎      | 20657/61904 [30:27<15:53:41,  1.39s/it]
 33%|███▎      | 20658/61904 [30:29<15:51:08,  1.38s/it]
 33%|███▎      | 20659/61904 [30:30<16:06:52,  1.41s/it]
 33%|███▎      | 20660/61904 [30:32<16:03:49,  1.40s/it]
                                                        
{'loss': 2.6507, 'learning_rate': 1.6684169583819526e-07, 'epoch': 5.34}

 33%|███▎      | 20660/61904 [30:32<16:03:49,  1.40s/it]
 33%|███▎      | 20661/61904 [30:33<16:30:23,  1.44s/it]
 33%|███▎      | 20662/61904 [30:35<16:21:04,  1.43s/it]
 33%|███▎      | 20663/61904 [30:36<15:53:40,  1.39s/it]
 33%|███▎      | 20664/61904 [30:37<16:01:32,  1.40s/it]
 33%|███▎      | 20665/61904 [30:39<15:59:00,  1.40s/it]
 33%|███▎      | 20666/61904 [30:40<16:13:28,  1.42s/it]
 33%|███▎      | 20667/61904 [30:41<16:12:01,  1.41s/it]
 33%|███▎      | 20668/61904 [30:43<15:53:35,  1.39s/it]
 33%|███▎      | 20669/61904 [30:44<15:34:35,  1.36s/it]
 33%|███▎      | 20670/61904 [30:45<15:40:43,  1.37s/it]
 33%|███▎      | 20671/61904 [30:47<15:48:07,  1.38s/it]
 33%|███▎      | 20672/61904 [30:48<15:45:34,  1.38s/it]
 33%|███▎      | 20673/61904 [30:50<15:39:31,  1.37s/it]
 33%|███▎      | 20674/61904 [30:51<15:46:07,  1.38s/it]
 33%|███▎      | 20675/61904 [30:52<15:43:22,  1.37s/it]
 33%|███▎      | 20676/61904 [30:54<15:55:52,  1.39s/it]
 33%|███▎      | 20677/61904 [30:55<16:09:12,  1.41s/it]
 33%|███▎      | 20678/61904 [30:57<16:14:09,  1.42s/it]
 33%|███▎      | 20679/61904 [30:58<16:15:56,  1.42s/it]
 33%|███▎      | 20680/61904 [30:59<15:41:15,  1.37s/it]
                                                        
{'loss': 2.6378, 'learning_rate': 1.6680928302865292e-07, 'epoch': 5.35}

 33%|███▎      | 20680/61904 [30:59<15:41:15,  1.37s/it]
 33%|███▎      | 20681/61904 [31:01<15:59:18,  1.40s/it]
 33%|███▎      | 20682/61904 [31:02<15:41:10,  1.37s/it]
 33%|███▎      | 20683/61904 [31:03<15:14:28,  1.33s/it]
 33%|███▎      | 20684/61904 [31:05<15:02:05,  1.31s/it]
 33%|███▎      | 20685/61904 [31:06<15:26:02,  1.35s/it]
 33%|███▎      | 20686/61904 [31:07<15:17:37,  1.34s/it]
 33%|███▎      | 20687/61904 [31:09<15:32:08,  1.36s/it]
 33%|███▎      | 20688/61904 [31:10<15:30:03,  1.35s/it]
 33%|███▎      | 20689/61904 [31:12<15:36:45,  1.36s/it]
 33%|███▎      | 20690/61904 [31:13<15:38:55,  1.37s/it]
 33%|███▎      | 20691/61904 [31:14<15:55:36,  1.39s/it]
 33%|███▎      | 20692/61904 [31:16<15:30:54,  1.36s/it]
 33%|███▎      | 20693/61904 [31:17<15:15:14,  1.33s/it]
 33%|███▎      | 20694/61904 [31:18<15:22:53,  1.34s/it]
 33%|███▎      | 20695/61904 [31:20<15:42:54,  1.37s/it]
 33%|███▎      | 20696/61904 [31:21<15:34:59,  1.36s/it]
 33%|███▎      | 20697/61904 [31:22<15:23:31,  1.34s/it]
 33%|███▎      | 20698/61904 [31:24<15:48:29,  1.38s/it]
 33%|███▎      | 20699/61904 [31:25<15:34:38,  1.36s/it]
 33%|███▎      | 20700/61904 [31:26<15:32:13,  1.36s/it]
                                                        
{'loss': 2.6756, 'learning_rate': 1.6677687021911058e-07, 'epoch': 5.35}

 33%|███▎      | 20700/61904 [31:26<15:32:13,  1.36s/it]
 33%|███▎      | 20701/61904 [31:28<15:25:35,  1.35s/it]
 33%|███▎      | 20702/61904 [31:29<15:13:42,  1.33s/it]
 33%|███▎      | 20703/61904 [31:30<15:26:09,  1.35s/it]
 33%|███▎      | 20704/61904 [31:32<15:20:40,  1.34s/it]
 33%|███▎      | 20705/61904 [31:33<15:24:27,  1.35s/it]
 33%|███▎      | 20706/61904 [31:35<15:46:14,  1.38s/it]
 33%|███▎      | 20707/61904 [31:36<15:30:35,  1.36s/it]
 33%|███▎      | 20708/61904 [31:37<15:23:21,  1.34s/it]
 33%|███▎      | 20709/61904 [31:39<15:52:08,  1.39s/it]
 33%|███▎      | 20710/61904 [31:40<15:50:38,  1.38s/it]
 33%|███▎      | 20711/61904 [31:41<15:37:10,  1.37s/it]
 33%|███▎      | 20712/61904 [31:43<15:49:09,  1.38s/it]
 33%|███▎      | 20713/61904 [31:44<15:47:19,  1.38s/it]
 33%|███▎      | 20714/61904 [31:46<15:25:36,  1.35s/it]
 33%|███▎      | 20715/61904 [31:47<15:44:43,  1.38s/it]
 33%|███▎      | 20716/61904 [31:48<16:00:50,  1.40s/it]
 33%|███▎      | 20717/61904 [31:50<16:30:08,  1.44s/it]
 33%|███▎      | 20718/61904 [31:51<16:33:58,  1.45s/it]
 33%|███▎      | 20719/61904 [31:53<16:38:40,  1.45s/it]
 33%|███▎      | 20720/61904 [31:54<16:27:08,  1.44s/it]
                                                        
{'loss': 2.6667, 'learning_rate': 1.6674445740956827e-07, 'epoch': 5.36}

 33%|███▎      | 20720/61904 [31:54<16:27:08,  1.44s/it]
 33%|███▎      | 20721/61904 [31:56<15:55:12,  1.39s/it]
 33%|███▎      | 20722/61904 [31:57<16:10:40,  1.41s/it]
 33%|███▎      | 20723/61904 [31:58<16:12:27,  1.42s/it]
 33%|███▎      | 20724/61904 [32:00<15:56:49,  1.39s/it]
 33%|███▎      | 20725/61904 [32:01<16:13:26,  1.42s/it]
 33%|███▎      | 20726/61904 [32:03<17:12:34,  1.50s/it]
 33%|███▎      | 20727/61904 [32:04<16:26:06,  1.44s/it]
 33%|███▎      | 20728/61904 [32:06<17:27:08,  1.53s/it]
 33%|███▎      | 20729/61904 [32:07<16:51:01,  1.47s/it]
 33%|███▎      | 20730/61904 [32:09<16:19:03,  1.43s/it]
 33%|███▎      | 20731/61904 [32:10<16:15:15,  1.42s/it]
 33%|███▎      | 20732/61904 [32:11<16:11:44,  1.42s/it]
 33%|███▎      | 20733/61904 [32:13<16:05:12,  1.41s/it]
 33%|███▎      | 20734/61904 [32:14<16:14:30,  1.42s/it]
 33%|███▎      | 20735/61904 [32:16<15:50:51,  1.39s/it]
 33%|███▎      | 20736/61904 [32:17<15:35:33,  1.36s/it]
 33%|███▎      | 20737/61904 [32:18<15:47:38,  1.38s/it]
 34%|███▎      | 20738/61904 [32:20<15:59:53,  1.40s/it]
 34%|███▎      | 20739/61904 [32:21<15:41:35,  1.37s/it]
 34%|███▎      | 20740/61904 [32:22<15:46:58,  1.38s/it]
                                                        
{'loss': 2.6714, 'learning_rate': 1.6671204460002593e-07, 'epoch': 5.36}

 34%|███▎      | 20740/61904 [32:22<15:46:58,  1.38s/it]
 34%|███▎      | 20741/61904 [32:24<15:06:01,  1.32s/it]
 34%|███▎      | 20742/61904 [32:25<15:24:49,  1.35s/it]
 34%|███▎      | 20743/61904 [32:27<15:39:42,  1.37s/it]
 34%|███▎      | 20744/61904 [32:28<15:41:16,  1.37s/it]
 34%|███▎      | 20745/61904 [32:29<15:25:04,  1.35s/it]
 34%|███▎      | 20746/61904 [32:31<15:30:20,  1.36s/it]
 34%|███▎      | 20747/61904 [32:32<16:01:13,  1.40s/it]
 34%|███▎      | 20748/61904 [32:33<16:00:15,  1.40s/it]
 34%|███▎      | 20749/61904 [32:35<16:15:37,  1.42s/it]
 34%|███▎      | 20750/61904 [32:36<15:55:57,  1.39s/it]
 34%|███▎      | 20751/61904 [32:38<16:57:43,  1.48s/it]
 34%|███▎      | 20752/61904 [32:39<16:50:24,  1.47s/it]
 34%|███▎      | 20753/61904 [32:41<16:45:42,  1.47s/it]
 34%|███▎      | 20754/61904 [32:42<16:30:48,  1.44s/it]
 34%|███▎      | 20755/61904 [32:44<16:25:10,  1.44s/it]
 34%|███▎      | 20756/61904 [32:45<16:14:41,  1.42s/it]
 34%|███▎      | 20757/61904 [32:46<16:18:32,  1.43s/it]
 34%|███▎      | 20758/61904 [32:48<15:52:12,  1.39s/it]
 34%|███▎      | 20759/61904 [32:49<15:53:02,  1.39s/it]
 34%|███▎      | 20760/61904 [32:51<16:00:31,  1.40s/it]
                                                        
{'loss': 2.6117, 'learning_rate': 1.666796317904836e-07, 'epoch': 5.37}

 34%|███▎      | 20760/61904 [32:51<16:00:31,  1.40s/it]
 34%|███▎      | 20761/61904 [32:52<16:37:29,  1.45s/it]
 34%|███▎      | 20762/61904 [32:53<16:05:25,  1.41s/it]
 34%|███▎      | 20763/61904 [32:55<16:01:24,  1.40s/it]
 34%|███▎      | 20764/61904 [32:56<15:48:47,  1.38s/it]
 34%|███▎      | 20765/61904 [32:58<15:37:16,  1.37s/it]
 34%|███▎      | 20766/61904 [32:59<15:56:27,  1.39s/it]
 34%|███▎      | 20767/61904 [33:00<15:57:49,  1.40s/it]
 34%|███▎      | 20768/61904 [33:02<15:39:44,  1.37s/it]
 34%|███▎      | 20769/61904 [33:03<15:11:16,  1.33s/it]
 34%|███▎      | 20770/61904 [33:04<14:55:18,  1.31s/it]
 34%|███▎      | 20771/61904 [33:06<15:29:30,  1.36s/it]
 34%|███▎      | 20772/61904 [33:07<15:12:12,  1.33s/it]
 34%|███▎      | 20773/61904 [33:08<15:08:39,  1.33s/it]
 34%|███▎      | 20774/61904 [33:10<15:11:16,  1.33s/it]
 34%|███▎      | 20775/61904 [33:11<15:14:45,  1.33s/it]
 34%|███▎      | 20776/61904 [33:12<15:19:13,  1.34s/it]
 34%|███▎      | 20777/61904 [33:14<15:41:35,  1.37s/it]
 34%|███▎      | 20778/61904 [33:15<15:30:27,  1.36s/it]
 34%|███▎      | 20779/61904 [33:16<15:35:41,  1.37s/it]
 34%|███▎      | 20780/61904 [33:18<16:18:27,  1.43s/it]
                                                        
{'loss': 2.6513, 'learning_rate': 1.6664721898094128e-07, 'epoch': 5.37}

 34%|███▎      | 20780/61904 [33:18<16:18:27,  1.43s/it]
 34%|███▎      | 20781/61904 [33:19<16:15:50,  1.42s/it]
 34%|███▎      | 20782/61904 [33:21<16:01:29,  1.40s/it]
 34%|███▎      | 20783/61904 [33:22<15:33:31,  1.36s/it]
 34%|███▎      | 20784/61904 [33:23<15:18:05,  1.34s/it]
 34%|███▎      | 20785/61904 [33:25<15:32:27,  1.36s/it]
 34%|███▎      | 20786/61904 [33:26<15:19:33,  1.34s/it]
 34%|███▎      | 20787/61904 [33:27<15:16:51,  1.34s/it]
 34%|███▎      | 20788/61904 [33:29<15:14:22,  1.33s/it]
 34%|███▎      | 20789/61904 [33:30<15:27:21,  1.35s/it]
 34%|███▎      | 20790/61904 [33:31<15:28:56,  1.36s/it]
 34%|███▎      | 20791/61904 [33:33<15:21:53,  1.35s/it]
 34%|███▎      | 20792/61904 [33:34<15:30:51,  1.36s/it]
 34%|███▎      | 20793/61904 [33:35<15:12:00,  1.33s/it]
 34%|███▎      | 20794/61904 [33:37<15:27:43,  1.35s/it]
 34%|███▎      | 20795/61904 [33:38<15:59:32,  1.40s/it]
 34%|███▎      | 20796/61904 [33:40<16:20:20,  1.43s/it]
 34%|███▎      | 20797/61904 [33:42<17:03:48,  1.49s/it]
 34%|███▎      | 20798/61904 [33:43<17:03:03,  1.49s/it]
 34%|███▎      | 20799/61904 [33:44<16:57:18,  1.48s/it]
 34%|███▎      | 20800/61904 [33:46<16:07:35,  1.41s/it]
                                                        
{'loss': 2.6997, 'learning_rate': 1.6661480617139894e-07, 'epoch': 5.38}

 34%|███▎      | 20800/61904 [33:46<16:07:35,  1.41s/it]
 34%|███▎      | 20801/61904 [33:47<16:19:22,  1.43s/it]
 34%|███▎      | 20802/61904 [33:48<15:57:16,  1.40s/it]
 34%|███▎      | 20803/61904 [33:50<16:11:07,  1.42s/it]
 34%|███▎      | 20804/61904 [33:52<16:47:12,  1.47s/it]
 34%|███▎      | 20805/61904 [33:53<16:22:40,  1.43s/it]
 34%|███▎      | 20806/61904 [33:54<16:05:01,  1.41s/it]
 34%|███▎      | 20807/61904 [33:56<15:54:48,  1.39s/it]
 34%|███▎      | 20808/61904 [33:57<15:38:20,  1.37s/it]
 34%|███▎      | 20809/61904 [33:58<15:47:10,  1.38s/it]
 34%|███▎      | 20810/61904 [34:00<15:38:12,  1.37s/it]
 34%|███▎      | 20811/61904 [34:01<15:47:26,  1.38s/it]
 34%|███▎      | 20812/61904 [34:03<16:12:09,  1.42s/it]
 34%|███▎      | 20813/61904 [34:04<16:16:36,  1.43s/it]
 34%|███▎      | 20814/61904 [34:05<16:10:45,  1.42s/it]
 34%|███▎      | 20815/61904 [34:07<16:14:00,  1.42s/it]
 34%|███▎      | 20816/61904 [34:08<15:46:04,  1.38s/it]
 34%|███▎      | 20817/61904 [34:10<16:00:21,  1.40s/it]
 34%|███▎      | 20818/61904 [34:11<15:55:10,  1.39s/it]
 34%|███▎      | 20819/61904 [34:12<15:52:26,  1.39s/it]
 34%|███▎      | 20820/61904 [34:14<16:02:13,  1.41s/it]
                                                        
{'loss': 2.6395, 'learning_rate': 1.665823933618566e-07, 'epoch': 5.38}

 34%|███▎      | 20820/61904 [34:14<16:02:13,  1.41s/it]
 34%|███▎      | 20821/61904 [34:15<15:39:02,  1.37s/it]
 34%|███▎      | 20822/61904 [34:16<15:19:01,  1.34s/it]
 34%|███▎      | 20823/61904 [34:18<15:27:43,  1.35s/it]
 34%|███▎      | 20824/61904 [34:19<15:23:32,  1.35s/it]
 34%|███▎      | 20825/61904 [34:21<15:41:13,  1.37s/it]
 34%|███▎      | 20826/61904 [34:22<15:37:58,  1.37s/it]
 34%|███▎      | 20827/61904 [34:23<15:14:00,  1.34s/it]
 34%|███▎      | 20828/61904 [34:25<15:26:41,  1.35s/it]
 34%|███▎      | 20829/61904 [34:26<15:37:51,  1.37s/it]
 34%|███▎      | 20830/61904 [34:27<15:47:18,  1.38s/it]
 34%|███▎      | 20831/61904 [34:29<15:30:37,  1.36s/it]
 34%|███▎      | 20832/61904 [34:30<15:48:56,  1.39s/it]
 34%|███▎      | 20833/61904 [34:32<15:50:07,  1.39s/it]
 34%|███▎      | 20834/61904 [34:33<16:20:57,  1.43s/it]
 34%|███▎      | 20835/61904 [34:34<16:08:14,  1.41s/it]
 34%|███▎      | 20836/61904 [34:36<15:41:47,  1.38s/it]
 34%|███▎      | 20837/61904 [34:37<15:26:54,  1.35s/it]
 34%|███▎      | 20838/61904 [34:38<15:56:03,  1.40s/it]
 34%|███▎      | 20839/61904 [34:40<15:58:08,  1.40s/it]
 34%|███▎      | 20840/61904 [34:41<16:08:15,  1.41s/it]
                                                        
{'loss': 2.6615, 'learning_rate': 1.6654998055231426e-07, 'epoch': 5.39}

 34%|███▎      | 20840/61904 [34:41<16:08:15,  1.41s/it]
 34%|███▎      | 20841/61904 [34:43<15:46:17,  1.38s/it]
 34%|███▎      | 20842/61904 [34:44<15:46:57,  1.38s/it]
 34%|███▎      | 20843/61904 [34:45<15:12:37,  1.33s/it]
 34%|███▎      | 20844/61904 [34:47<15:16:33,  1.34s/it]
 34%|███▎      | 20845/61904 [34:48<15:29:44,  1.36s/it]
 34%|███▎      | 20846/61904 [34:50<16:01:10,  1.40s/it]
 34%|███▎      | 20847/61904 [34:51<16:04:06,  1.41s/it]
 34%|███▎      | 20848/61904 [34:53<16:36:49,  1.46s/it]
 34%|███▎      | 20849/61904 [34:54<16:30:40,  1.45s/it]
 34%|███▎      | 20850/61904 [34:55<16:31:31,  1.45s/it]
 34%|███▎      | 20851/61904 [34:57<16:19:12,  1.43s/it]
 34%|███▎      | 20852/61904 [34:58<15:55:06,  1.40s/it]
 34%|███▎      | 20853/61904 [34:59<15:28:51,  1.36s/it]
 34%|███▎      | 20854/61904 [35:01<15:38:18,  1.37s/it]
 34%|███▎      | 20855/61904 [35:02<15:46:04,  1.38s/it]
 34%|███▎      | 20856/61904 [35:04<15:40:00,  1.37s/it]
 34%|███▎      | 20857/61904 [35:05<15:40:10,  1.37s/it]
 34%|███▎      | 20858/61904 [35:06<15:17:31,  1.34s/it]
 34%|███▎      | 20859/61904 [35:08<15:45:31,  1.38s/it]
 34%|███▎      | 20860/61904 [35:09<15:43:58,  1.38s/it]
                                                        
{'loss': 2.6915, 'learning_rate': 1.6651756774277193e-07, 'epoch': 5.39}

 34%|███▎      | 20860/61904 [35:09<15:43:58,  1.38s/it]
 34%|███▎      | 20861/61904 [35:10<15:48:56,  1.39s/it]
 34%|███▎      | 20862/61904 [35:12<15:22:15,  1.35s/it]
 34%|███▎      | 20863/61904 [35:13<16:03:00,  1.41s/it]
 34%|███▎      | 20864/61904 [35:15<16:19:39,  1.43s/it]
 34%|███▎      | 20865/61904 [35:16<16:09:15,  1.42s/it]
 34%|███▎      | 20866/61904 [35:17<15:58:25,  1.40s/it]
 34%|███▎      | 20867/61904 [35:19<15:52:23,  1.39s/it]
 34%|███▎      | 20868/61904 [35:20<16:06:14,  1.41s/it]
 34%|███▎      | 20869/61904 [35:22<16:03:52,  1.41s/it]
 34%|███▎      | 20870/61904 [35:23<15:58:56,  1.40s/it]
 34%|███▎      | 20871/61904 [35:24<15:51:21,  1.39s/it]
 34%|███▎      | 20872/61904 [35:26<15:31:18,  1.36s/it]
 34%|███▎      | 20873/61904 [35:27<15:23:43,  1.35s/it]
 34%|███▎      | 20874/61904 [35:28<15:10:39,  1.33s/it]
 34%|███▎      | 20875/61904 [35:30<15:15:09,  1.34s/it]
 34%|███▎      | 20876/61904 [35:31<15:06:49,  1.33s/it]
 34%|███▎      | 20877/61904 [35:32<15:14:00,  1.34s/it]
 34%|███▎      | 20878/61904 [35:34<15:42:27,  1.38s/it]
 34%|███▎      | 20879/61904 [35:35<16:24:58,  1.44s/it]
 34%|███▎      | 20880/61904 [35:37<15:52:32,  1.39s/it]
                                                        
{'loss': 2.6248, 'learning_rate': 1.6648515493322961e-07, 'epoch': 5.4}

 34%|███▎      | 20880/61904 [35:37<15:52:32,  1.39s/it]
 34%|███▎      | 20881/61904 [35:38<15:28:37,  1.36s/it]
 34%|███▎      | 20882/61904 [35:39<15:49:50,  1.39s/it]
 34%|███▎      | 20883/61904 [35:41<15:33:45,  1.37s/it]
 34%|███▎      | 20884/61904 [35:42<15:48:21,  1.39s/it]
 34%|███▎      | 20885/61904 [35:44<15:45:26,  1.38s/it]
 34%|███▎      | 20886/61904 [35:45<15:16:41,  1.34s/it]
 34%|███▎      | 20887/61904 [35:46<15:25:34,  1.35s/it]
 34%|███▎      | 20888/61904 [35:48<15:44:59,  1.38s/it]
 34%|███▎      | 20889/61904 [35:49<15:40:02,  1.38s/it]
 34%|███▎      | 20890/61904 [35:50<15:23:39,  1.35s/it]
 34%|███▎      | 20891/61904 [35:52<15:23:27,  1.35s/it]
 34%|███▎      | 20892/61904 [35:53<15:22:58,  1.35s/it]
 34%|███▍      | 20893/61904 [35:54<15:13:56,  1.34s/it]
 34%|███▍      | 20894/61904 [35:56<15:16:57,  1.34s/it]
 34%|███▍      | 20895/61904 [35:57<15:30:54,  1.36s/it]
 34%|███▍      | 20896/61904 [35:58<15:25:45,  1.35s/it]
 34%|███▍      | 20897/61904 [36:00<15:05:24,  1.32s/it]
 34%|███▍      | 20898/61904 [36:01<15:14:15,  1.34s/it]
 34%|███▍      | 20899/61904 [36:03<15:49:32,  1.39s/it]
 34%|███▍      | 20900/61904 [36:04<15:23:47,  1.35s/it]
                                                        
{'loss': 2.7061, 'learning_rate': 1.6645274212368728e-07, 'epoch': 5.4}

 34%|███▍      | 20900/61904 [36:04<15:23:47,  1.35s/it]
 34%|███▍      | 20901/61904 [36:05<15:33:16,  1.37s/it]
 34%|███▍      | 20902/61904 [36:07<16:27:24,  1.44s/it]
 34%|███▍      | 20903/61904 [36:08<16:26:06,  1.44s/it]
 34%|███▍      | 20904/61904 [36:10<15:49:40,  1.39s/it]
 34%|███▍      | 20905/61904 [36:11<15:46:32,  1.39s/it]
 34%|███▍      | 20906/61904 [36:12<16:16:42,  1.43s/it]
 34%|███▍      | 20907/61904 [36:14<16:05:49,  1.41s/it]
 34%|███▍      | 20908/61904 [36:15<16:41:51,  1.47s/it]
 34%|███▍      | 20909/61904 [36:17<16:35:18,  1.46s/it]
 34%|███▍      | 20910/61904 [36:18<16:24:50,  1.44s/it]
 34%|███▍      | 20911/61904 [36:20<16:03:55,  1.41s/it]
 34%|███▍      | 20912/61904 [36:21<16:11:31,  1.42s/it]
 34%|███▍      | 20913/61904 [36:23<16:36:09,  1.46s/it]
 34%|███▍      | 20914/61904 [36:24<16:17:37,  1.43s/it]
 34%|███▍      | 20915/61904 [36:25<16:04:34,  1.41s/it]
 34%|███▍      | 20916/61904 [36:27<16:25:19,  1.44s/it]
 34%|███▍      | 20917/61904 [36:28<16:29:01,  1.45s/it]
 34%|███▍      | 20918/61904 [36:30<16:33:48,  1.45s/it]
 34%|███▍      | 20919/61904 [36:31<16:31:57,  1.45s/it]
 34%|███▍      | 20920/61904 [36:33<16:31:05,  1.45s/it]
                                                        
{'loss': 2.642, 'learning_rate': 1.6642032931414494e-07, 'epoch': 5.41}

 34%|███▍      | 20920/61904 [36:33<16:31:05,  1.45s/it]
 34%|███▍      | 20921/61904 [36:34<16:25:29,  1.44s/it]
 34%|███▍      | 20922/61904 [36:35<15:58:00,  1.40s/it]
 34%|███▍      | 20923/61904 [36:37<15:36:04,  1.37s/it]
 34%|███▍      | 20924/61904 [36:38<16:53:16,  1.48s/it]
 34%|███▍      | 20925/61904 [36:40<16:40:52,  1.47s/it]
 34%|███▍      | 20926/61904 [36:41<16:02:17,  1.41s/it]
 34%|███▍      | 20927/61904 [36:42<15:38:09,  1.37s/it]
 34%|███▍      | 20928/61904 [36:44<15:36:56,  1.37s/it]
 34%|███▍      | 20929/61904 [36:45<16:03:15,  1.41s/it]
 34%|███▍      | 20930/61904 [36:47<16:06:23,  1.42s/it]
 34%|███▍      | 20931/61904 [36:48<15:48:36,  1.39s/it]
 34%|███▍      | 20932/61904 [36:49<15:33:14,  1.37s/it]
 34%|███▍      | 20933/61904 [36:51<15:38:39,  1.37s/it]
 34%|███▍      | 20934/61904 [36:52<16:26:28,  1.44s/it]
 34%|███▍      | 20935/61904 [36:54<15:46:06,  1.39s/it]
 34%|███▍      | 20936/61904 [36:55<15:38:12,  1.37s/it]
 34%|███▍      | 20937/61904 [36:56<15:33:30,  1.37s/it]
 34%|███▍      | 20938/61904 [36:58<15:48:13,  1.39s/it]
 34%|███▍      | 20939/61904 [36:59<16:03:50,  1.41s/it]
 34%|███▍      | 20940/61904 [37:01<16:23:15,  1.44s/it]
                                                        
{'loss': 2.6377, 'learning_rate': 1.6638791650460263e-07, 'epoch': 5.41}

 34%|███▍      | 20940/61904 [37:01<16:23:15,  1.44s/it]
 34%|███▍      | 20941/61904 [37:02<16:20:14,  1.44s/it]
 34%|███▍      | 20942/61904 [37:04<16:20:28,  1.44s/it]
 34%|███▍      | 20943/61904 [37:05<16:30:26,  1.45s/it]
 34%|███▍      | 20944/61904 [37:06<16:08:05,  1.42s/it]
 34%|███▍      | 20945/61904 [37:08<16:04:02,  1.41s/it]
 34%|███▍      | 20946/61904 [37:09<16:04:19,  1.41s/it]
 34%|███▍      | 20947/61904 [37:11<15:51:36,  1.39s/it]
 34%|███▍      | 20948/61904 [37:12<15:55:01,  1.40s/it]
 34%|███▍      | 20949/61904 [37:13<16:03:58,  1.41s/it]
 34%|███▍      | 20950/61904 [37:15<15:49:40,  1.39s/it]
 34%|███▍      | 20951/61904 [37:16<15:47:34,  1.39s/it]
 34%|███▍      | 20952/61904 [37:18<15:40:12,  1.38s/it]
 34%|███▍      | 20953/61904 [37:19<15:29:04,  1.36s/it]
 34%|███▍      | 20954/61904 [37:20<15:49:45,  1.39s/it]
 34%|███▍      | 20955/61904 [37:22<16:05:17,  1.41s/it]
 34%|███▍      | 20956/61904 [37:23<16:01:18,  1.41s/it]
 34%|███▍      | 20957/61904 [37:24<15:28:16,  1.36s/it]
 34%|███▍      | 20958/61904 [37:26<15:54:50,  1.40s/it]
 34%|███▍      | 20959/61904 [37:27<15:36:09,  1.37s/it]
 34%|███▍      | 20960/61904 [37:29<16:01:23,  1.41s/it]
                                                        
{'loss': 2.6452, 'learning_rate': 1.663555036950603e-07, 'epoch': 5.42}

 34%|███▍      | 20960/61904 [37:29<16:01:23,  1.41s/it]
 34%|███▍      | 20961/61904 [37:30<15:48:51,  1.39s/it]
 34%|███▍      | 20962/61904 [37:31<15:57:38,  1.40s/it]
 34%|███▍      | 20963/61904 [37:33<15:29:47,  1.36s/it]
 34%|███▍      | 20964/61904 [37:34<15:13:09,  1.34s/it]
 34%|███▍      | 20965/61904 [37:35<15:00:59,  1.32s/it]
 34%|███▍      | 20966/61904 [37:37<14:55:05,  1.31s/it]
 34%|███▍      | 20967/61904 [37:38<14:41:45,  1.29s/it]
 34%|███▍      | 20968/61904 [37:39<14:38:18,  1.29s/it]
 34%|███▍      | 20969/61904 [37:41<14:59:52,  1.32s/it]
 34%|███▍      | 20970/61904 [37:42<15:02:42,  1.32s/it]
 34%|███▍      | 20971/61904 [37:43<15:07:37,  1.33s/it]
 34%|███▍      | 20972/61904 [37:45<15:05:27,  1.33s/it]
 34%|███▍      | 20973/61904 [37:46<15:22:54,  1.35s/it]
 34%|███▍      | 20974/61904 [37:47<15:53:55,  1.40s/it]
 34%|███▍      | 20975/61904 [37:49<15:37:55,  1.37s/it]
 34%|███▍      | 20976/61904 [37:50<15:22:36,  1.35s/it]
 34%|███▍      | 20977/61904 [37:51<15:17:23,  1.34s/it]
 34%|███▍      | 20978/61904 [37:53<14:47:10,  1.30s/it]
 34%|███▍      | 20979/61904 [37:54<14:54:37,  1.31s/it]
 34%|███▍      | 20980/61904 [37:55<14:58:58,  1.32s/it]
                                                        
{'loss': 2.7206, 'learning_rate': 1.6632309088551795e-07, 'epoch': 5.42}

 34%|███▍      | 20980/61904 [37:55<14:58:58,  1.32s/it]
 34%|███▍      | 20981/61904 [37:57<15:17:01,  1.34s/it]
 34%|███▍      | 20982/61904 [37:58<16:03:09,  1.41s/it]
 34%|███▍      | 20983/61904 [38:00<17:09:09,  1.51s/it]
 34%|███▍      | 20984/61904 [38:01<16:54:41,  1.49s/it]
 34%|███▍      | 20985/61904 [38:03<16:51:45,  1.48s/it]
 34%|███▍      | 20986/61904 [38:04<16:34:01,  1.46s/it]
 34%|███▍      | 20987/61904 [38:06<16:50:38,  1.48s/it]
 34%|███▍      | 20988/61904 [38:07<16:40:13,  1.47s/it]
 34%|███▍      | 20989/61904 [38:09<16:36:33,  1.46s/it]
 34%|███▍      | 20990/61904 [38:10<16:09:02,  1.42s/it]
 34%|███▍      | 20991/61904 [38:11<15:56:57,  1.40s/it]
 34%|███▍      | 20992/61904 [38:13<15:32:55,  1.37s/it]
 34%|███▍      | 20993/61904 [38:14<15:45:16,  1.39s/it]
 34%|███▍      | 20994/61904 [38:16<15:57:44,  1.40s/it]
 34%|███▍      | 20995/61904 [38:17<15:48:56,  1.39s/it]
 34%|███▍      | 20996/61904 [38:18<15:50:41,  1.39s/it]
 34%|███▍      | 20997/61904 [38:20<15:45:25,  1.39s/it]
 34%|███▍      | 20998/61904 [38:21<15:17:31,  1.35s/it]
 34%|███▍      | 20999/61904 [38:22<15:54:58,  1.40s/it]
 34%|███▍      | 21000/61904 [38:24<16:08:29,  1.42s/it]
                                                        
{'loss': 2.6524, 'learning_rate': 1.662906780759756e-07, 'epoch': 5.43}

 34%|███▍      | 21000/61904 [38:24<16:08:29,  1.42s/it]
 34%|███▍      | 21001/61904 [38:25<16:16:01,  1.43s/it]
 34%|███▍      | 21002/61904 [38:27<15:54:43,  1.40s/it]
 34%|███▍      | 21003/61904 [38:28<15:55:10,  1.40s/it]
 34%|███▍      | 21004/61904 [38:30<16:12:15,  1.43s/it]
 34%|███▍      | 21005/61904 [38:31<16:06:06,  1.42s/it]
 34%|███▍      | 21006/61904 [38:32<15:27:09,  1.36s/it]
 34%|███▍      | 21007/61904 [38:34<15:38:30,  1.38s/it]
 34%|███▍      | 21008/61904 [38:35<15:11:34,  1.34s/it]
 34%|███▍      | 21009/61904 [38:36<15:11:48,  1.34s/it]
 34%|███▍      | 21010/61904 [38:37<14:45:07,  1.30s/it]
 34%|███▍      | 21011/61904 [38:39<15:13:33,  1.34s/it]
 34%|███▍      | 21012/61904 [38:40<15:19:56,  1.35s/it]
 34%|███▍      | 21013/61904 [38:42<15:34:25,  1.37s/it]
 34%|███▍      | 21014/61904 [38:43<15:41:10,  1.38s/it]
 34%|███▍      | 21015/61904 [38:44<15:18:32,  1.35s/it]
 34%|███▍      | 21016/61904 [38:46<15:09:41,  1.33s/it]
 34%|███▍      | 21017/61904 [38:47<15:41:25,  1.38s/it]
 34%|███▍      | 21018/61904 [38:49<15:44:20,  1.39s/it]
 34%|███▍      | 21019/61904 [38:50<16:05:38,  1.42s/it]
 34%|███▍      | 21020/61904 [38:51<16:18:06,  1.44s/it]
                                                        
{'loss': 2.6398, 'learning_rate': 1.662582652664333e-07, 'epoch': 5.43}

 34%|███▍      | 21020/61904 [38:51<16:18:06,  1.44s/it]
 34%|███▍      | 21021/61904 [38:53<16:02:52,  1.41s/it]
 34%|███▍      | 21022/61904 [38:54<16:17:17,  1.43s/it]
 34%|███▍      | 21023/61904 [38:56<16:18:38,  1.44s/it]
 34%|███▍      | 21024/61904 [38:57<15:42:23,  1.38s/it]
 34%|███▍      | 21025/61904 [38:58<15:34:48,  1.37s/it]
 34%|███▍      | 21026/61904 [39:00<16:07:50,  1.42s/it]
 34%|███▍      | 21027/61904 [39:01<15:37:31,  1.38s/it]
 34%|███▍      | 21028/61904 [39:03<15:27:49,  1.36s/it]
 34%|███▍      | 21029/61904 [39:04<15:36:02,  1.37s/it]
 34%|███▍      | 21030/61904 [39:06<16:23:02,  1.44s/it]
 34%|███▍      | 21031/61904 [39:07<16:10:39,  1.42s/it]
 34%|███▍      | 21032/61904 [39:08<16:16:16,  1.43s/it]
 34%|███▍      | 21033/61904 [39:10<16:07:17,  1.42s/it]
 34%|███▍      | 21034/61904 [39:11<16:32:46,  1.46s/it]
 34%|███▍      | 21035/61904 [39:13<16:09:28,  1.42s/it]
 34%|███▍      | 21036/61904 [39:14<16:43:56,  1.47s/it]
 34%|███▍      | 21037/61904 [39:16<16:57:31,  1.49s/it]
 34%|███▍      | 21038/61904 [39:17<16:16:55,  1.43s/it]
 34%|███▍      | 21039/61904 [39:18<15:55:20,  1.40s/it]
 34%|███▍      | 21040/61904 [39:20<15:52:18,  1.40s/it]
                                                        
{'loss': 2.6486, 'learning_rate': 1.6622585245689096e-07, 'epoch': 5.44}

 34%|███▍      | 21040/61904 [39:20<15:52:18,  1.40s/it]
 34%|███▍      | 21041/61904 [39:21<15:44:38,  1.39s/it]
 34%|███▍      | 21042/61904 [39:22<15:32:32,  1.37s/it]
 34%|███▍      | 21043/61904 [39:24<16:03:12,  1.41s/it]
 34%|███▍      | 21044/61904 [39:25<15:44:25,  1.39s/it]
 34%|███▍      | 21045/61904 [39:27<15:21:36,  1.35s/it]
 34%|███▍      | 21046/61904 [39:28<15:21:26,  1.35s/it]
 34%|███▍      | 21047/61904 [39:29<15:37:29,  1.38s/it]
 34%|███▍      | 21048/61904 [39:31<15:42:10,  1.38s/it]
 34%|███▍      | 21049/61904 [39:32<15:42:22,  1.38s/it]
 34%|███▍      | 21050/61904 [39:33<15:33:25,  1.37s/it]
 34%|███▍      | 21051/61904 [39:35<16:00:32,  1.41s/it]
 34%|███▍      | 21052/61904 [39:36<16:00:55,  1.41s/it]
 34%|███▍      | 21053/61904 [39:38<15:38:12,  1.38s/it]
 34%|███▍      | 21054/61904 [39:39<15:35:24,  1.37s/it]
 34%|███▍      | 21055/61904 [39:40<15:16:58,  1.35s/it]
 34%|███▍      | 21056/61904 [39:42<15:07:14,  1.33s/it]
 34%|███▍      | 21057/61904 [39:43<15:45:45,  1.39s/it]
 34%|███▍      | 21058/61904 [39:45<16:05:03,  1.42s/it]
 34%|███▍      | 21059/61904 [39:46<15:43:15,  1.39s/it]
 34%|███▍      | 21060/61904 [39:47<15:30:27,  1.37s/it]
                                                        
{'loss': 2.6466, 'learning_rate': 1.6619343964734862e-07, 'epoch': 5.44}

 34%|███▍      | 21060/61904 [39:47<15:30:27,  1.37s/it]
 34%|███▍      | 21061/61904 [39:49<15:22:03,  1.35s/it]
 34%|███▍      | 21062/61904 [39:50<14:54:09,  1.31s/it]
 34%|███▍      | 21063/61904 [39:51<14:57:16,  1.32s/it]
 34%|███▍      | 21064/61904 [39:52<15:01:38,  1.32s/it]
 34%|███▍      | 21065/61904 [39:54<15:28:59,  1.36s/it]
 34%|███▍      | 21066/61904 [39:55<15:37:26,  1.38s/it]
 34%|███▍      | 21067/61904 [39:57<15:43:58,  1.39s/it]
 34%|███▍      | 21068/61904 [39:58<15:46:23,  1.39s/it]
 34%|███▍      | 21069/61904 [39:59<15:29:42,  1.37s/it]
 34%|███▍      | 21070/61904 [40:01<15:33:53,  1.37s/it]
 34%|███▍      | 21071/61904 [40:02<15:29:05,  1.37s/it]
 34%|███▍      | 21072/61904 [40:04<15:29:20,  1.37s/it]
 34%|███▍      | 21073/61904 [40:05<15:58:12,  1.41s/it]
 34%|███▍      | 21074/61904 [40:07<16:10:42,  1.43s/it]
 34%|███▍      | 21075/61904 [40:08<15:52:35,  1.40s/it]
 34%|███▍      | 21076/61904 [40:09<15:51:47,  1.40s/it]
 34%|███▍      | 21077/61904 [40:11<15:44:22,  1.39s/it]
 34%|███▍      | 21078/61904 [40:12<15:55:39,  1.40s/it]
 34%|███▍      | 21079/61904 [40:13<15:21:49,  1.35s/it]
 34%|███▍      | 21080/61904 [40:15<15:24:27,  1.36s/it]
                                                        
{'loss': 2.6818, 'learning_rate': 1.6616102683780629e-07, 'epoch': 5.45}

 34%|███▍      | 21080/61904 [40:15<15:24:27,  1.36s/it]
 34%|███▍      | 21081/61904 [40:16<15:26:55,  1.36s/it]
 34%|███▍      | 21082/61904 [40:17<15:09:31,  1.34s/it]
 34%|███▍      | 21083/61904 [40:19<15:28:19,  1.36s/it]
 34%|███▍      | 21084/61904 [40:20<15:58:14,  1.41s/it]
 34%|███▍      | 21085/61904 [40:22<16:37:43,  1.47s/it]
 34%|███▍      | 21086/61904 [40:23<16:30:40,  1.46s/it]
 34%|███▍      | 21087/61904 [40:25<15:59:11,  1.41s/it]
 34%|███▍      | 21088/61904 [40:26<15:51:44,  1.40s/it]
 34%|███▍      | 21089/61904 [40:27<15:57:42,  1.41s/it]
 34%|███▍      | 21090/61904 [40:29<15:37:29,  1.38s/it]
 34%|███▍      | 21091/61904 [40:30<16:01:14,  1.41s/it]
 34%|███▍      | 21092/61904 [40:32<15:44:28,  1.39s/it]
 34%|███▍      | 21093/61904 [40:33<15:34:46,  1.37s/it]
 34%|███▍      | 21094/61904 [40:34<15:33:25,  1.37s/it]
 34%|███▍      | 21095/61904 [40:36<15:09:15,  1.34s/it]
 34%|███▍      | 21096/61904 [40:37<15:24:53,  1.36s/it]
 34%|███▍      | 21097/61904 [40:38<15:17:14,  1.35s/it]
 34%|███▍      | 21098/61904 [40:40<15:27:21,  1.36s/it]
 34%|███▍      | 21099/61904 [40:41<15:34:43,  1.37s/it]
 34%|███▍      | 21100/61904 [40:43<16:12:51,  1.43s/it]
                                                        
{'loss': 2.6826, 'learning_rate': 1.6612861402826397e-07, 'epoch': 5.45}

 34%|███▍      | 21100/61904 [40:43<16:12:51,  1.43s/it]
 34%|███▍      | 21101/61904 [40:44<16:20:17,  1.44s/it]
 34%|███▍      | 21102/61904 [40:45<15:56:09,  1.41s/it]
 34%|███▍      | 21103/61904 [40:47<15:27:31,  1.36s/it]
 34%|███▍      | 21104/61904 [40:48<16:03:00,  1.42s/it]
 34%|███▍      | 21105/61904 [40:50<16:01:46,  1.41s/it]
 34%|███▍      | 21106/61904 [40:51<15:40:54,  1.38s/it]
 34%|███▍      | 21107/61904 [40:52<15:28:10,  1.37s/it]
 34%|███▍      | 21108/61904 [40:54<15:14:57,  1.35s/it]
 34%|███▍      | 21109/61904 [40:55<15:22:57,  1.36s/it]
 34%|███▍      | 21110/61904 [40:56<15:11:28,  1.34s/it]
 34%|███▍      | 21111/61904 [40:58<15:15:13,  1.35s/it]
 34%|███▍      | 21112/61904 [40:59<15:36:54,  1.38s/it]
 34%|███▍      | 21113/61904 [41:00<15:34:53,  1.38s/it]
 34%|███▍      | 21114/61904 [41:02<16:10:27,  1.43s/it]
 34%|███▍      | 21115/61904 [41:03<15:53:32,  1.40s/it]
 34%|███▍      | 21116/61904 [41:05<16:13:07,  1.43s/it]
 34%|███▍      | 21117/61904 [41:06<15:57:40,  1.41s/it]
 34%|███▍      | 21118/61904 [41:08<15:46:59,  1.39s/it]
 34%|███▍      | 21119/61904 [41:09<16:21:27,  1.44s/it]
 34%|███▍      | 21120/61904 [41:10<15:57:14,  1.41s/it]
                                                        
{'loss': 2.665, 'learning_rate': 1.6609620121872164e-07, 'epoch': 5.46}

 34%|███▍      | 21120/61904 [41:10<15:57:14,  1.41s/it]
 34%|███▍      | 21121/61904 [41:12<16:39:56,  1.47s/it]
 34%|███▍      | 21122/61904 [41:13<16:16:22,  1.44s/it]
 34%|███▍      | 21123/61904 [41:15<16:17:20,  1.44s/it]
 34%|███▍      | 21124/61904 [41:16<15:41:48,  1.39s/it]
 34%|███▍      | 21125/61904 [41:18<16:01:01,  1.41s/it]
 34%|███▍      | 21126/61904 [41:19<16:23:59,  1.45s/it]
 34%|███▍      | 21127/61904 [41:21<16:30:11,  1.46s/it]
 34%|███▍      | 21128/61904 [41:22<16:02:15,  1.42s/it]
 34%|███▍      | 21129/61904 [41:23<16:23:53,  1.45s/it]
 34%|███▍      | 21130/61904 [41:25<16:22:37,  1.45s/it]
 34%|███▍      | 21131/61904 [41:26<16:57:19,  1.50s/it]
 34%|███▍      | 21132/61904 [41:28<16:40:50,  1.47s/it]
 34%|███▍      | 21133/61904 [41:29<16:35:03,  1.46s/it]
 34%|███▍      | 21134/61904 [41:31<17:41:19,  1.56s/it]
 34%|███▍      | 21135/61904 [41:33<17:25:05,  1.54s/it]
 34%|███▍      | 21136/61904 [41:34<17:05:37,  1.51s/it]
 34%|███▍      | 21137/61904 [41:36<17:19:01,  1.53s/it]
 34%|███▍      | 21138/61904 [41:37<16:41:19,  1.47s/it]
 34%|███▍      | 21139/61904 [41:38<16:22:38,  1.45s/it]
 34%|███▍      | 21140/61904 [41:40<16:07:48,  1.42s/it]
                                                        
{'loss': 2.6018, 'learning_rate': 1.660637884091793e-07, 'epoch': 5.46}

 34%|███▍      | 21140/61904 [41:40<16:07:48,  1.42s/it]
 34%|███▍      | 21141/61904 [41:41<15:58:46,  1.41s/it]
 34%|███▍      | 21142/61904 [41:43<16:11:03,  1.43s/it]
 34%|███▍      | 21143/61904 [41:44<15:37:06,  1.38s/it]
 34%|███▍      | 21144/61904 [41:45<15:27:47,  1.37s/it]
 34%|███▍      | 21145/61904 [41:47<15:30:20,  1.37s/it]
 34%|███▍      | 21146/61904 [41:48<15:49:05,  1.40s/it]
 34%|███▍      | 21147/61904 [41:49<15:59:28,  1.41s/it]
 34%|███▍      | 21148/61904 [41:51<15:38:02,  1.38s/it]
 34%|███▍      | 21149/61904 [41:52<15:33:19,  1.37s/it]
 34%|███▍      | 21150/61904 [41:54<15:55:27,  1.41s/it]
 34%|███▍      | 21151/61904 [41:55<15:38:11,  1.38s/it]
 34%|███▍      | 21152/61904 [41:56<15:14:47,  1.35s/it]
 34%|███▍      | 21153/61904 [41:58<15:04:34,  1.33s/it]
 34%|███▍      | 21154/61904 [41:59<15:39:46,  1.38s/it]
 34%|███▍      | 21155/61904 [42:00<16:00:54,  1.41s/it]
 34%|███▍      | 21156/61904 [42:02<15:55:46,  1.41s/it]
 34%|███▍      | 21157/61904 [42:03<15:25:02,  1.36s/it]
 34%|███▍      | 21158/61904 [42:04<15:02:40,  1.33s/it]
 34%|███▍      | 21159/61904 [42:06<15:13:05,  1.34s/it]
 34%|███▍      | 21160/61904 [42:07<15:05:42,  1.33s/it]
                                                        
{'loss': 2.6867, 'learning_rate': 1.66031375599637e-07, 'epoch': 5.47}

 34%|███▍      | 21160/61904 [42:07<15:05:42,  1.33s/it]
 34%|███▍      | 21161/61904 [42:08<15:03:16,  1.33s/it]
 34%|███▍      | 21162/61904 [42:10<14:54:59,  1.32s/it]
 34%|███▍      | 21163/61904 [42:11<15:00:44,  1.33s/it]
 34%|███▍      | 21164/61904 [42:13<15:34:19,  1.38s/it]
 34%|███▍      | 21165/61904 [42:14<15:28:09,  1.37s/it]
 34%|███▍      | 21166/61904 [42:15<15:42:44,  1.39s/it]
 34%|███▍      | 21167/61904 [42:17<15:45:01,  1.39s/it]
 34%|███▍      | 21168/61904 [42:18<15:48:53,  1.40s/it]
 34%|███▍      | 21169/61904 [42:20<15:43:03,  1.39s/it]
 34%|███▍      | 21170/61904 [42:21<15:54:40,  1.41s/it]
 34%|███▍      | 21171/61904 [42:22<15:55:24,  1.41s/it]
 34%|███▍      | 21172/61904 [42:24<15:38:06,  1.38s/it]
 34%|███▍      | 21173/61904 [42:25<15:10:02,  1.34s/it]
 34%|███▍      | 21174/61904 [42:26<14:54:55,  1.32s/it]
 34%|███▍      | 21175/61904 [42:28<15:56:31,  1.41s/it]
 34%|███▍      | 21176/61904 [42:29<15:31:13,  1.37s/it]
 34%|███▍      | 21177/61904 [42:30<15:28:53,  1.37s/it]
 34%|███▍      | 21178/61904 [42:32<15:20:28,  1.36s/it]
 34%|███▍      | 21179/61904 [42:33<15:17:29,  1.35s/it]
 34%|███▍      | 21180/61904 [42:34<15:14:18,  1.35s/it]
                                                        
{'loss': 2.6972, 'learning_rate': 1.6599896279009465e-07, 'epoch': 5.47}

 34%|███▍      | 21180/61904 [42:34<15:14:18,  1.35s/it]
 34%|███▍      | 21181/61904 [42:36<15:31:36,  1.37s/it]
 34%|███▍      | 21182/61904 [42:37<15:19:36,  1.35s/it]
 34%|███▍      | 21183/61904 [42:39<15:38:28,  1.38s/it]
 34%|███▍      | 21184/61904 [42:40<15:24:37,  1.36s/it]
 34%|███▍      | 21185/61904 [42:41<15:26:55,  1.37s/it]
 34%|███▍      | 21186/61904 [42:43<16:30:14,  1.46s/it]
 34%|███▍      | 21187/61904 [42:44<16:27:05,  1.45s/it]
 34%|███▍      | 21188/61904 [42:46<16:35:33,  1.47s/it]
 34%|███▍      | 21189/61904 [42:47<16:42:32,  1.48s/it]
 34%|███▍      | 21190/61904 [42:49<16:24:25,  1.45s/it]
 34%|███▍      | 21191/61904 [42:50<15:52:27,  1.40s/it]
 34%|███▍      | 21192/61904 [42:51<15:25:12,  1.36s/it]
 34%|███▍      | 21193/61904 [42:53<15:08:55,  1.34s/it]
 34%|███▍      | 21194/61904 [42:54<15:33:10,  1.38s/it]
 34%|███▍      | 21195/61904 [42:55<15:16:36,  1.35s/it]
 34%|███▍      | 21196/61904 [42:57<15:17:23,  1.35s/it]
 34%|███▍      | 21197/61904 [42:58<15:39:41,  1.39s/it]
 34%|███▍      | 21198/61904 [43:00<15:28:47,  1.37s/it]
 34%|███▍      | 21199/61904 [43:01<15:42:04,  1.39s/it]
 34%|███▍      | 21200/61904 [43:02<15:33:06,  1.38s/it]
                                                        
{'loss': 2.6775, 'learning_rate': 1.659665499805523e-07, 'epoch': 5.48}

 34%|███▍      | 21200/61904 [43:02<15:33:06,  1.38s/it]
 34%|███▍      | 21201/61904 [43:04<15:26:49,  1.37s/it]
 34%|███▍      | 21202/61904 [43:05<15:33:38,  1.38s/it]
 34%|███▍      | 21203/61904 [43:06<15:32:21,  1.37s/it]
 34%|███▍      | 21204/61904 [43:08<15:48:21,  1.40s/it]
 34%|███▍      | 21205/61904 [43:09<15:59:48,  1.41s/it]
 34%|███▍      | 21206/61904 [43:11<15:28:38,  1.37s/it]
 34%|███▍      | 21207/61904 [43:12<15:42:42,  1.39s/it]
 34%|███▍      | 21208/61904 [43:13<15:31:43,  1.37s/it]
 34%|███▍      | 21209/61904 [43:15<15:25:07,  1.36s/it]
 34%|███▍      | 21210/61904 [43:16<15:28:58,  1.37s/it]
 34%|███▍      | 21211/61904 [43:18<15:55:02,  1.41s/it]
 34%|███▍      | 21212/61904 [43:19<15:34:58,  1.38s/it]
 34%|███▍      | 21213/61904 [43:20<15:43:21,  1.39s/it]
 34%|███▍      | 21214/61904 [43:22<15:53:25,  1.41s/it]
 34%|███▍      | 21215/61904 [43:23<15:49:24,  1.40s/it]
 34%|███▍      | 21216/61904 [43:25<15:31:06,  1.37s/it]
 34%|███▍      | 21217/61904 [43:26<15:44:42,  1.39s/it]
 34%|███▍      | 21218/61904 [43:27<15:36:52,  1.38s/it]
 34%|███▍      | 21219/61904 [43:29<15:38:58,  1.38s/it]
 34%|███▍      | 21220/61904 [43:30<15:15:48,  1.35s/it]
                                                        
{'loss': 2.7239, 'learning_rate': 1.6593413717100997e-07, 'epoch': 5.48}

 34%|███▍      | 21220/61904 [43:30<15:15:48,  1.35s/it]
 34%|███▍      | 21221/61904 [43:31<15:01:50,  1.33s/it]
 34%|███▍      | 21222/61904 [43:33<15:38:47,  1.38s/it]
 34%|███▍      | 21223/61904 [43:34<15:33:10,  1.38s/it]
 34%|███▍      | 21224/61904 [43:36<16:07:38,  1.43s/it]
 34%|███▍      | 21225/61904 [43:37<15:44:13,  1.39s/it]
 34%|███▍      | 21226/61904 [43:38<15:52:03,  1.40s/it]
 34%|███▍      | 21227/61904 [43:40<15:53:21,  1.41s/it]
 34%|███▍      | 21228/61904 [43:41<15:50:12,  1.40s/it]
 34%|███▍      | 21229/61904 [43:43<15:48:56,  1.40s/it]
 34%|███▍      | 21230/61904 [43:44<15:42:51,  1.39s/it]
 34%|███▍      | 21231/61904 [43:45<15:24:48,  1.36s/it]
 34%|███▍      | 21232/61904 [43:47<15:46:16,  1.40s/it]
 34%|███▍      | 21233/61904 [43:48<15:28:19,  1.37s/it]
 34%|███▍      | 21234/61904 [43:49<15:21:28,  1.36s/it]
 34%|███▍      | 21235/61904 [43:51<15:53:48,  1.41s/it]
 34%|███▍      | 21236/61904 [43:52<15:42:48,  1.39s/it]
 34%|███▍      | 21237/61904 [43:54<15:43:03,  1.39s/it]
 34%|███▍      | 21238/61904 [43:55<15:57:42,  1.41s/it]
 34%|███▍      | 21239/61904 [43:56<15:25:07,  1.37s/it]
 34%|███▍      | 21240/61904 [43:58<15:36:31,  1.38s/it]
                                                        
{'loss': 2.6349, 'learning_rate': 1.6590172436146763e-07, 'epoch': 5.49}

 34%|███▍      | 21240/61904 [43:58<15:36:31,  1.38s/it]
 34%|███▍      | 21241/61904 [43:59<15:37:48,  1.38s/it]
 34%|███▍      | 21242/61904 [44:01<15:23:32,  1.36s/it]
 34%|███▍      | 21243/61904 [44:02<15:31:08,  1.37s/it]
 34%|███▍      | 21244/61904 [44:03<15:43:51,  1.39s/it]
 34%|███▍      | 21245/61904 [44:05<15:49:55,  1.40s/it]
 34%|███▍      | 21246/61904 [44:06<16:31:54,  1.46s/it]
 34%|███▍      | 21247/61904 [44:08<16:37:15,  1.47s/it]
 34%|███▍      | 21248/61904 [44:09<16:06:12,  1.43s/it]
 34%|███▍      | 21249/61904 [44:11<16:07:38,  1.43s/it]
 34%|███▍      | 21250/61904 [44:12<16:05:49,  1.43s/it]
 34%|███▍      | 21251/61904 [44:13<16:06:42,  1.43s/it]
 34%|███▍      | 21252/61904 [44:15<15:33:56,  1.38s/it]
 34%|███▍      | 21253/61904 [44:16<15:32:53,  1.38s/it]
 34%|███▍      | 21254/61904 [44:17<15:35:03,  1.38s/it]
 34%|███▍      | 21255/61904 [44:19<15:23:53,  1.36s/it]
 34%|███▍      | 21256/61904 [44:20<15:35:41,  1.38s/it]
 34%|███▍      | 21257/61904 [44:22<15:35:12,  1.38s/it]
 34%|███▍      | 21258/61904 [44:23<14:59:48,  1.33s/it]
 34%|███▍      | 21259/61904 [44:24<14:56:09,  1.32s/it]
 34%|███▍      | 21260/61904 [44:26<15:12:29,  1.35s/it]
                                                        
{'loss': 2.6607, 'learning_rate': 1.6586931155192532e-07, 'epoch': 5.49}

 34%|███▍      | 21260/61904 [44:26<15:12:29,  1.35s/it]
 34%|███▍      | 21261/61904 [44:27<15:10:51,  1.34s/it]
 34%|███▍      | 21262/61904 [44:28<15:16:08,  1.35s/it]
 34%|███▍      | 21263/61904 [44:30<15:14:37,  1.35s/it]
 34%|███▍      | 21264/61904 [44:31<15:16:50,  1.35s/it]
 34%|███▍      | 21265/61904 [44:32<15:28:56,  1.37s/it]
 34%|███▍      | 21266/61904 [44:34<15:36:28,  1.38s/it]
 34%|███▍      | 21267/61904 [44:35<15:50:15,  1.40s/it]
 34%|███▍      | 21268/61904 [44:37<15:41:29,  1.39s/it]
 34%|███▍      | 21269/61904 [44:38<15:42:17,  1.39s/it]
 34%|███▍      | 21270/61904 [44:39<15:44:44,  1.39s/it]
 34%|███▍      | 21271/61904 [44:41<15:43:15,  1.39s/it]
 34%|███▍      | 21272/61904 [44:42<15:34:57,  1.38s/it]
 34%|███▍      | 21273/61904 [44:43<15:29:59,  1.37s/it]
 34%|███▍      | 21274/61904 [44:45<15:17:00,  1.35s/it]
 34%|███▍      | 21275/61904 [44:46<15:39:57,  1.39s/it]
 34%|███▍      | 21276/61904 [44:48<15:36:46,  1.38s/it]
 34%|███▍      | 21277/61904 [44:49<15:57:34,  1.41s/it]
 34%|███▍      | 21278/61904 [44:51<15:55:20,  1.41s/it]
 34%|███▍      | 21279/61904 [44:52<15:33:10,  1.38s/it]
 34%|███▍      | 21280/61904 [44:53<15:53:14,  1.41s/it]
                                                        
{'loss': 2.6806, 'learning_rate': 1.6583689874238298e-07, 'epoch': 5.5}

 34%|███▍      | 21280/61904 [44:53<15:53:14,  1.41s/it]
 34%|███▍      | 21281/61904 [44:55<15:51:43,  1.41s/it]
 34%|███▍      | 21282/61904 [44:56<16:25:01,  1.45s/it]
 34%|███▍      | 21283/61904 [44:58<16:19:31,  1.45s/it]
 34%|███▍      | 21284/61904 [44:59<16:02:43,  1.42s/it]
 34%|███▍      | 21285/61904 [45:00<15:52:47,  1.41s/it]
 34%|███▍      | 21286/61904 [45:02<15:46:13,  1.40s/it]
 34%|███▍      | 21287/61904 [45:03<15:38:48,  1.39s/it]
 34%|███▍      | 21288/61904 [45:05<15:39:41,  1.39s/it]
 34%|███▍      | 21289/61904 [45:06<15:21:00,  1.36s/it]
 34%|███▍      | 21290/61904 [45:07<15:00:36,  1.33s/it]
 34%|███▍      | 21291/61904 [45:08<14:58:34,  1.33s/it]
 34%|███▍      | 21292/61904 [45:10<15:00:19,  1.33s/it]
 34%|███▍      | 21293/61904 [45:11<15:14:49,  1.35s/it]
 34%|███▍      | 21294/61904 [45:13<15:16:05,  1.35s/it]
 34%|███▍      | 21295/61904 [45:14<15:25:18,  1.37s/it]
 34%|███▍      | 21296/61904 [45:15<15:45:26,  1.40s/it]
 34%|███▍      | 21297/61904 [45:17<15:27:41,  1.37s/it]
 34%|███▍      | 21298/61904 [45:18<15:16:10,  1.35s/it]
 34%|███▍      | 21299/61904 [45:19<15:16:09,  1.35s/it]
 34%|███▍      | 21300/61904 [45:21<15:53:30,  1.41s/it]
                                                        
{'loss': 2.7212, 'learning_rate': 1.6580448593284065e-07, 'epoch': 5.51}

 34%|███▍      | 21300/61904 [45:21<15:53:30,  1.41s/it]
 34%|███▍      | 21301/61904 [45:22<15:25:00,  1.37s/it]
 34%|███▍      | 21302/61904 [45:24<15:20:45,  1.36s/it]
 34%|███▍      | 21303/61904 [45:25<15:36:53,  1.38s/it]
 34%|███▍      | 21304/61904 [45:26<15:21:52,  1.36s/it]
 34%|███▍      | 21305/61904 [45:28<15:39:17,  1.39s/it]
 34%|███▍      | 21306/61904 [45:29<16:02:07,  1.42s/it]
 34%|███▍      | 21307/61904 [45:31<15:58:52,  1.42s/it]
 34%|███▍      | 21308/61904 [45:32<15:47:47,  1.40s/it]
 34%|███▍      | 21309/61904 [45:33<15:27:07,  1.37s/it]
 34%|███▍      | 21310/61904 [45:35<15:25:23,  1.37s/it]
 34%|███▍      | 21311/61904 [45:36<15:15:52,  1.35s/it]
 34%|███▍      | 21312/61904 [45:37<15:09:39,  1.34s/it]
 34%|███▍      | 21313/61904 [45:39<15:27:44,  1.37s/it]
 34%|███▍      | 21314/61904 [45:40<15:27:00,  1.37s/it]
 34%|███▍      | 21315/61904 [45:42<15:36:55,  1.38s/it]
 34%|███▍      | 21316/61904 [45:43<15:26:16,  1.37s/it]
 34%|███▍      | 21317/61904 [45:44<15:40:52,  1.39s/it]
 34%|███▍      | 21318/61904 [45:46<15:40:55,  1.39s/it]
 34%|███▍      | 21319/61904 [45:47<15:23:11,  1.36s/it]
 34%|███▍      | 21320/61904 [45:48<15:33:00,  1.38s/it]
                                                        
{'loss': 2.6997, 'learning_rate': 1.6577207312329833e-07, 'epoch': 5.51}

 34%|███▍      | 21320/61904 [45:48<15:33:00,  1.38s/it]
 34%|███▍      | 21321/61904 [45:50<15:27:54,  1.37s/it]
 34%|███▍      | 21322/61904 [45:51<15:22:07,  1.36s/it]
 34%|███▍      | 21323/61904 [45:53<15:37:47,  1.39s/it]
 34%|███▍      | 21324/61904 [45:54<15:11:48,  1.35s/it]
 34%|███▍      | 21325/61904 [45:55<15:03:08,  1.34s/it]
 34%|███▍      | 21326/61904 [45:57<15:21:48,  1.36s/it]
 34%|███▍      | 21327/61904 [45:58<15:30:33,  1.38s/it]
 34%|███▍      | 21328/61904 [45:59<15:27:18,  1.37s/it]
 34%|███▍      | 21329/61904 [46:01<15:08:48,  1.34s/it]
 34%|███▍      | 21330/61904 [46:02<15:06:36,  1.34s/it]
 34%|███▍      | 21331/61904 [46:03<15:25:49,  1.37s/it]
 34%|███▍      | 21332/61904 [46:05<15:41:35,  1.39s/it]
 34%|███▍      | 21333/61904 [46:06<15:29:40,  1.37s/it]
 34%|███▍      | 21334/61904 [46:07<15:12:07,  1.35s/it]
 34%|███▍      | 21335/61904 [46:09<15:21:39,  1.36s/it]
 34%|███▍      | 21336/61904 [46:10<15:16:38,  1.36s/it]
 34%|███▍      | 21337/61904 [46:12<15:16:15,  1.36s/it]
 34%|███▍      | 21338/61904 [46:13<16:05:47,  1.43s/it]
 34%|███▍      | 21339/61904 [46:15<15:59:31,  1.42s/it]
 34%|███▍      | 21340/61904 [46:16<16:03:59,  1.43s/it]
                                                        
{'loss': 2.6277, 'learning_rate': 1.65739660313756e-07, 'epoch': 5.52}

 34%|███▍      | 21340/61904 [46:16<16:03:59,  1.43s/it]
 34%|███▍      | 21341/61904 [46:17<15:49:38,  1.40s/it]
 34%|███▍      | 21342/61904 [46:19<15:48:35,  1.40s/it]
 34%|███▍      | 21343/61904 [46:20<15:53:37,  1.41s/it]
 34%|███▍      | 21344/61904 [46:22<16:01:06,  1.42s/it]
 34%|███▍      | 21345/61904 [46:23<15:33:35,  1.38s/it]
 34%|███▍      | 21346/61904 [46:24<15:27:05,  1.37s/it]
 34%|███▍      | 21347/61904 [46:26<16:22:03,  1.45s/it]
 34%|███▍      | 21348/61904 [46:27<16:08:30,  1.43s/it]
 34%|███▍      | 21349/61904 [46:29<15:53:42,  1.41s/it]
 34%|███▍      | 21350/61904 [46:30<15:36:29,  1.39s/it]
 34%|███▍      | 21351/61904 [46:31<16:00:27,  1.42s/it]
 34%|███▍      | 21352/61904 [46:33<15:19:53,  1.36s/it]
 34%|███▍      | 21353/61904 [46:34<15:44:10,  1.40s/it]
 34%|███▍      | 21354/61904 [46:36<15:41:13,  1.39s/it]
 34%|███▍      | 21355/61904 [46:37<15:41:15,  1.39s/it]
 34%|███▍      | 21356/61904 [46:38<15:13:19,  1.35s/it]
 35%|███▍      | 21357/61904 [46:40<15:21:19,  1.36s/it]
 35%|███▍      | 21358/61904 [46:41<15:20:16,  1.36s/it]
 35%|███▍      | 21359/61904 [46:42<15:15:10,  1.35s/it]
 35%|███▍      | 21360/61904 [46:44<16:00:11,  1.42s/it]
                                                        
{'loss': 2.6953, 'learning_rate': 1.6570724750421366e-07, 'epoch': 5.52}

 35%|███▍      | 21360/61904 [46:44<16:00:11,  1.42s/it]
 35%|███▍      | 21361/61904 [46:45<15:55:32,  1.41s/it]
 35%|███▍      | 21362/61904 [46:47<15:50:06,  1.41s/it]
 35%|███▍      | 21363/61904 [46:48<15:20:50,  1.36s/it]
 35%|███▍      | 21364/61904 [46:49<15:19:57,  1.36s/it]
 35%|███▍      | 21365/61904 [46:51<15:34:16,  1.38s/it]
 35%|███▍      | 21366/61904 [46:52<15:27:39,  1.37s/it]
 35%|███▍      | 21367/61904 [46:53<15:02:09,  1.34s/it]
 35%|███▍      | 21368/61904 [46:55<15:00:46,  1.33s/it]
 35%|███▍      | 21369/61904 [46:56<14:41:54,  1.31s/it]
 35%|███▍      | 21370/61904 [46:57<14:50:36,  1.32s/it]
 35%|███▍      | 21371/61904 [46:59<15:00:59,  1.33s/it]
 35%|███▍      | 21372/61904 [47:00<15:25:21,  1.37s/it]
 35%|███▍      | 21373/61904 [47:01<15:00:18,  1.33s/it]
 35%|███▍      | 21374/61904 [47:03<15:10:02,  1.35s/it]
 35%|███▍      | 21375/61904 [47:04<15:16:16,  1.36s/it]
 35%|███▍      | 21376/61904 [47:05<15:09:08,  1.35s/it]
 35%|███▍      | 21377/61904 [47:07<15:18:32,  1.36s/it]
 35%|███▍      | 21378/61904 [47:08<15:26:17,  1.37s/it]
 35%|███▍      | 21379/61904 [47:09<15:04:01,  1.34s/it]
 35%|███▍      | 21380/61904 [47:11<15:00:08,  1.33s/it]
                                                        
{'loss': 2.7586, 'learning_rate': 1.6567483469467135e-07, 'epoch': 5.53}

 35%|███▍      | 21380/61904 [47:11<15:00:08,  1.33s/it]
 35%|███▍      | 21381/61904 [47:12<14:35:44,  1.30s/it]
 35%|███▍      | 21382/61904 [47:13<14:34:29,  1.29s/it]
 35%|███▍      | 21383/61904 [47:15<15:12:52,  1.35s/it]
 35%|███▍      | 21384/61904 [47:16<15:22:38,  1.37s/it]
 35%|███▍      | 21385/61904 [47:17<14:57:48,  1.33s/it]
 35%|███▍      | 21386/61904 [47:19<15:12:09,  1.35s/it]
 35%|███▍      | 21387/61904 [47:20<15:09:10,  1.35s/it]
 35%|███▍      | 21388/61904 [47:21<14:48:17,  1.32s/it]
 35%|███▍      | 21389/61904 [47:23<14:46:59,  1.31s/it]
 35%|███▍      | 21390/61904 [47:24<15:06:13,  1.34s/it]
 35%|███▍      | 21391/61904 [47:25<14:50:56,  1.32s/it]
 35%|███▍      | 21392/61904 [47:27<14:59:16,  1.33s/it]
 35%|███▍      | 21393/61904 [47:28<15:02:56,  1.34s/it]
 35%|███▍      | 21394/61904 [47:29<15:27:37,  1.37s/it]
 35%|███▍      | 21395/61904 [47:31<16:07:28,  1.43s/it]
 35%|███▍      | 21396/61904 [47:32<15:37:58,  1.39s/it]
 35%|███▍      | 21397/61904 [47:34<15:25:41,  1.37s/it]
 35%|███▍      | 21398/61904 [47:35<15:15:49,  1.36s/it]
 35%|███▍      | 21399/61904 [47:36<15:18:38,  1.36s/it]
 35%|███▍      | 21400/61904 [47:38<15:45:14,  1.40s/it]
                                                        
{'loss': 2.5887, 'learning_rate': 1.65642421885129e-07, 'epoch': 5.53}

 35%|███▍      | 21400/61904 [47:38<15:45:14,  1.40s/it]
 35%|███▍      | 21401/61904 [47:39<16:01:13,  1.42s/it]
 35%|███▍      | 21402/61904 [47:41<15:45:00,  1.40s/it]
 35%|███▍      | 21403/61904 [47:42<16:11:34,  1.44s/it]
 35%|███▍      | 21404/61904 [47:44<16:51:34,  1.50s/it]
 35%|███▍      | 21405/61904 [47:46<17:25:02,  1.55s/it]
 35%|███▍      | 21406/61904 [47:47<16:37:59,  1.48s/it]
 35%|███▍      | 21407/61904 [47:48<16:41:21,  1.48s/it]
 35%|███▍      | 21408/61904 [47:50<16:35:07,  1.47s/it]
 35%|███▍      | 21409/61904 [47:51<16:00:32,  1.42s/it]
 35%|███▍      | 21410/61904 [47:53<16:25:38,  1.46s/it]
 35%|███▍      | 21411/61904 [47:54<15:55:10,  1.42s/it]
 35%|███▍      | 21412/61904 [47:55<15:12:08,  1.35s/it]
 35%|███▍      | 21413/61904 [47:56<15:02:15,  1.34s/it]
 35%|███▍      | 21414/61904 [47:58<14:38:57,  1.30s/it]
 35%|███▍      | 21415/61904 [47:59<14:31:45,  1.29s/it]
 35%|███▍      | 21416/61904 [48:00<14:43:42,  1.31s/it]
 35%|███▍      | 21417/61904 [48:02<15:05:37,  1.34s/it]
 35%|███▍      | 21418/61904 [48:03<14:45:56,  1.31s/it]
 35%|███▍      | 21419/61904 [48:04<15:28:04,  1.38s/it]
 35%|███▍      | 21420/61904 [48:06<15:10:04,  1.35s/it]
                                                        
{'loss': 2.6364, 'learning_rate': 1.6561000907558667e-07, 'epoch': 5.54}

 35%|███▍      | 21420/61904 [48:06<15:10:04,  1.35s/it]
 35%|███▍      | 21421/61904 [48:07<15:56:17,  1.42s/it]
 35%|███▍      | 21422/61904 [48:09<15:51:38,  1.41s/it]
 35%|███▍      | 21423/61904 [48:10<15:55:30,  1.42s/it]
 35%|███▍      | 21424/61904 [48:12<15:56:18,  1.42s/it]
 35%|███▍      | 21425/61904 [48:13<15:55:15,  1.42s/it]
 35%|███▍      | 21426/61904 [48:14<15:21:31,  1.37s/it]
 35%|███▍      | 21427/61904 [48:16<15:25:42,  1.37s/it]
 35%|███▍      | 21428/61904 [48:17<15:44:33,  1.40s/it]
 35%|███▍      | 21429/61904 [48:18<15:17:52,  1.36s/it]
 35%|███▍      | 21430/61904 [48:20<15:34:41,  1.39s/it]
 35%|███▍      | 21431/61904 [48:21<16:27:41,  1.46s/it]
 35%|███▍      | 21432/61904 [48:23<16:12:30,  1.44s/it]
 35%|███▍      | 21433/61904 [48:24<16:20:47,  1.45s/it]
 35%|███▍      | 21434/61904 [48:26<16:09:49,  1.44s/it]
 35%|███▍      | 21435/61904 [48:27<15:42:23,  1.40s/it]
 35%|███▍      | 21436/61904 [48:28<15:46:22,  1.40s/it]
 35%|███▍      | 21437/61904 [48:30<15:19:39,  1.36s/it]
 35%|███▍      | 21438/61904 [48:31<14:59:31,  1.33s/it]
 35%|███▍      | 21439/61904 [48:32<14:45:46,  1.31s/it]
 35%|███▍      | 21440/61904 [48:34<14:48:57,  1.32s/it]
                                                        
{'loss': 2.5951, 'learning_rate': 1.6557759626604433e-07, 'epoch': 5.54}

 35%|███▍      | 21440/61904 [48:34<14:48:57,  1.32s/it]
 35%|███▍      | 21441/61904 [48:35<15:06:30,  1.34s/it]
 35%|███▍      | 21442/61904 [48:36<15:24:26,  1.37s/it]
 35%|███▍      | 21443/61904 [48:38<15:23:04,  1.37s/it]
 35%|███▍      | 21444/61904 [48:39<15:09:51,  1.35s/it]
 35%|███▍      | 21445/61904 [48:40<15:19:26,  1.36s/it]
 35%|███▍      | 21446/61904 [48:42<15:11:22,  1.35s/it]
 35%|███▍      | 21447/61904 [48:43<14:49:37,  1.32s/it]
 35%|███▍      | 21448/61904 [48:45<15:20:14,  1.36s/it]
 35%|███▍      | 21449/61904 [48:46<15:12:21,  1.35s/it]
 35%|███▍      | 21450/61904 [48:47<14:49:16,  1.32s/it]
 35%|███▍      | 21451/61904 [48:48<14:50:10,  1.32s/it]
 35%|███▍      | 21452/61904 [48:50<14:39:54,  1.31s/it]
 35%|███▍      | 21453/61904 [48:51<15:24:18,  1.37s/it]
 35%|███▍      | 21454/61904 [48:53<15:14:43,  1.36s/it]
 35%|███▍      | 21455/61904 [48:54<15:35:40,  1.39s/it]
 35%|███▍      | 21456/61904 [48:55<15:17:37,  1.36s/it]
 35%|███▍      | 21457/61904 [48:57<15:31:01,  1.38s/it]
 35%|███▍      | 21458/61904 [48:58<15:07:43,  1.35s/it]
 35%|███▍      | 21459/61904 [48:59<15:09:40,  1.35s/it]
 35%|███▍      | 21460/61904 [49:01<15:16:09,  1.36s/it]
                                                        
{'loss': 2.6595, 'learning_rate': 1.65545183456502e-07, 'epoch': 5.55}

 35%|███▍      | 21460/61904 [49:01<15:16:09,  1.36s/it]
 35%|███▍      | 21461/61904 [49:02<15:49:25,  1.41s/it]
 35%|███▍      | 21462/61904 [49:04<15:36:45,  1.39s/it]
 35%|███▍      | 21463/61904 [49:05<15:43:47,  1.40s/it]
 35%|███▍      | 21464/61904 [49:06<15:47:23,  1.41s/it]
 35%|███▍      | 21465/61904 [49:08<16:01:13,  1.43s/it]
 35%|███▍      | 21466/61904 [49:09<15:57:35,  1.42s/it]
 35%|███▍      | 21467/61904 [49:11<15:40:45,  1.40s/it]
 35%|███▍      | 21468/61904 [49:12<15:32:35,  1.38s/it]
 35%|███▍      | 21469/61904 [49:13<15:22:05,  1.37s/it]
 35%|███▍      | 21470/61904 [49:15<15:34:39,  1.39s/it]
 35%|███▍      | 21471/61904 [49:16<15:59:51,  1.42s/it]
 35%|███▍      | 21472/61904 [49:18<16:39:44,  1.48s/it]
 35%|███▍      | 21473/61904 [49:19<15:59:49,  1.42s/it]
 35%|███▍      | 21474/61904 [49:21<15:48:03,  1.41s/it]
 35%|███▍      | 21475/61904 [49:22<16:10:19,  1.44s/it]
 35%|███▍      | 21476/61904 [49:23<15:48:07,  1.41s/it]
 35%|███▍      | 21477/61904 [49:25<15:37:49,  1.39s/it]
 35%|███▍      | 21478/61904 [49:26<15:16:12,  1.36s/it]
 35%|███▍      | 21479/61904 [49:27<15:06:16,  1.35s/it]
 35%|███▍      | 21480/61904 [49:29<14:51:20,  1.32s/it]
                                                        
{'loss': 2.602, 'learning_rate': 1.6551277064695968e-07, 'epoch': 5.55}

 35%|███▍      | 21480/61904 [49:29<14:51:20,  1.32s/it]
 35%|███▍      | 21481/61904 [49:30<15:20:25,  1.37s/it]
 35%|███▍      | 21482/61904 [49:31<15:15:58,  1.36s/it]
 35%|███▍      | 21483/61904 [49:33<14:59:53,  1.34s/it]
 35%|███▍      | 21484/61904 [49:34<15:08:51,  1.35s/it]
 35%|███▍      | 21485/61904 [49:35<14:53:09,  1.33s/it]
 35%|███▍      | 21486/61904 [49:37<15:34:29,  1.39s/it]
 35%|███▍      | 21487/61904 [49:38<15:14:57,  1.36s/it]
 35%|███▍      | 21488/61904 [49:40<15:23:14,  1.37s/it]
 35%|███▍      | 21489/61904 [49:41<15:40:41,  1.40s/it]
 35%|███▍      | 21490/61904 [49:42<15:44:37,  1.40s/it]
 35%|███▍      | 21491/61904 [49:44<15:52:03,  1.41s/it]
 35%|███▍      | 21492/61904 [49:45<15:20:36,  1.37s/it]
 35%|███▍      | 21493/61904 [49:47<15:23:49,  1.37s/it]
 35%|███▍      | 21494/61904 [49:48<14:49:08,  1.32s/it]
 35%|███▍      | 21495/61904 [49:49<14:52:48,  1.33s/it]
 35%|███▍      | 21496/61904 [49:51<15:44:17,  1.40s/it]
 35%|███▍      | 21497/61904 [49:52<15:24:26,  1.37s/it]
 35%|███▍      | 21498/61904 [49:53<15:38:08,  1.39s/it]
 35%|███▍      | 21499/61904 [49:55<15:18:14,  1.36s/it]
 35%|███▍      | 21500/61904 [49:56<15:07:49,  1.35s/it]
                                                        
{'loss': 2.5996, 'learning_rate': 1.6548035783741734e-07, 'epoch': 5.56}

 35%|███▍      | 21500/61904 [49:56<15:07:49,  1.35s/it]
 35%|███▍      | 21501/61904 [49:57<15:15:05,  1.36s/it]
 35%|███▍      | 21502/61904 [49:59<15:44:49,  1.40s/it]
 35%|███▍      | 21503/61904 [50:00<16:13:27,  1.45s/it]
 35%|███▍      | 21504/61904 [50:02<15:35:40,  1.39s/it]
 35%|███▍      | 21505/61904 [50:03<15:31:37,  1.38s/it]
 35%|███▍      | 21506/61904 [50:05<15:59:27,  1.43s/it]
 35%|███▍      | 21507/61904 [50:06<15:51:27,  1.41s/it]
 35%|███▍      | 21508/61904 [50:07<16:10:58,  1.44s/it]
 35%|███▍      | 21509/61904 [50:09<15:48:54,  1.41s/it]
 35%|███▍      | 21510/61904 [50:10<15:28:01,  1.38s/it]
 35%|███▍      | 21511/61904 [50:11<15:16:26,  1.36s/it]
 35%|███▍      | 21512/61904 [50:13<14:56:46,  1.33s/it]
 35%|███▍      | 21513/61904 [50:14<14:40:30,  1.31s/it]
 35%|███▍      | 21514/61904 [50:15<14:43:06,  1.31s/it]
 35%|███▍      | 21515/61904 [50:16<14:21:09,  1.28s/it]
 35%|███▍      | 21516/61904 [50:18<14:48:54,  1.32s/it]
 35%|███▍      | 21517/61904 [50:19<14:49:21,  1.32s/it]
 35%|███▍      | 21518/61904 [50:21<15:07:39,  1.35s/it]
 35%|███▍      | 21519/61904 [50:22<15:10:30,  1.35s/it]
 35%|███▍      | 21520/61904 [50:23<15:20:40,  1.37s/it]
                                                        
{'loss': 2.6529, 'learning_rate': 1.65447945027875e-07, 'epoch': 5.56}

 35%|███▍      | 21520/61904 [50:23<15:20:40,  1.37s/it]
 35%|███▍      | 21521/61904 [50:25<15:33:46,  1.39s/it]
 35%|███▍      | 21522/61904 [50:26<15:22:37,  1.37s/it]
 35%|███▍      | 21523/61904 [50:28<15:33:30,  1.39s/it]
 35%|███▍      | 21524/61904 [50:29<14:52:19,  1.33s/it]
 35%|███▍      | 21525/61904 [50:30<14:47:34,  1.32s/it]
 35%|███▍      | 21526/61904 [50:31<14:57:24,  1.33s/it]
 35%|███▍      | 21527/61904 [50:33<14:47:22,  1.32s/it]
 35%|███▍      | 21528/61904 [50:34<14:52:08,  1.33s/it]
 35%|███▍      | 21529/61904 [50:35<15:03:29,  1.34s/it]
 35%|███▍      | 21530/61904 [50:37<15:43:44,  1.40s/it]
 35%|███▍      | 21531/61904 [50:38<15:36:39,  1.39s/it]
 35%|███▍      | 21532/61904 [50:40<15:40:56,  1.40s/it]
 35%|███▍      | 21533/61904 [50:41<15:25:21,  1.38s/it]
 35%|███▍      | 21534/61904 [50:42<15:03:18,  1.34s/it]
 35%|███▍      | 21535/61904 [50:44<15:01:31,  1.34s/it]
 35%|███▍      | 21536/61904 [50:45<15:30:44,  1.38s/it]
 35%|███▍      | 21537/61904 [50:47<15:49:36,  1.41s/it]
 35%|███▍      | 21538/61904 [50:48<15:53:23,  1.42s/it]
 35%|███▍      | 21539/61904 [50:49<15:37:19,  1.39s/it]
 35%|███▍      | 21540/61904 [50:51<15:20:23,  1.37s/it]
                                                        
{'loss': 2.6917, 'learning_rate': 1.654155322183327e-07, 'epoch': 5.57}

 35%|███▍      | 21540/61904 [50:51<15:20:23,  1.37s/it]
 35%|███▍      | 21541/61904 [50:52<15:03:58,  1.34s/it]
 35%|███▍      | 21542/61904 [50:53<15:00:22,  1.34s/it]
 35%|███▍      | 21543/61904 [50:55<14:55:30,  1.33s/it]
 35%|███▍      | 21544/61904 [50:56<15:15:56,  1.36s/it]
 35%|███▍      | 21545/61904 [50:58<15:30:48,  1.38s/it]
 35%|███▍      | 21546/61904 [50:59<15:23:06,  1.37s/it]
 35%|███▍      | 21547/61904 [51:00<15:10:55,  1.35s/it]
 35%|███▍      | 21548/61904 [51:01<14:54:16,  1.33s/it]
 35%|███▍      | 21549/61904 [51:03<14:50:59,  1.32s/it]
 35%|███▍      | 21550/61904 [51:04<15:08:13,  1.35s/it]
 35%|███▍      | 21551/61904 [51:06<15:05:45,  1.35s/it]
 35%|███▍      | 21552/61904 [51:07<14:41:19,  1.31s/it]
 35%|███▍      | 21553/61904 [51:08<15:39:45,  1.40s/it]
 35%|███▍      | 21554/61904 [51:10<15:29:19,  1.38s/it]
 35%|███▍      | 21555/61904 [51:11<15:48:40,  1.41s/it]
 35%|███▍      | 21556/61904 [51:12<15:21:59,  1.37s/it]
 35%|███▍      | 21557/61904 [51:14<15:03:03,  1.34s/it]
 35%|███▍      | 21558/61904 [51:15<15:00:40,  1.34s/it]
 35%|███▍      | 21559/61904 [51:17<15:27:41,  1.38s/it]
 35%|███▍      | 21560/61904 [51:18<15:45:04,  1.41s/it]
                                                        
{'loss': 2.6509, 'learning_rate': 1.6538311940879036e-07, 'epoch': 5.57}

 35%|███▍      | 21560/61904 [51:18<15:45:04,  1.41s/it]
 35%|███▍      | 21561/61904 [51:19<16:00:19,  1.43s/it]
 35%|███▍      | 21562/61904 [51:21<15:48:38,  1.41s/it]
 35%|███▍      | 21563/61904 [51:22<15:57:34,  1.42s/it]
 35%|███▍      | 21564/61904 [51:24<15:51:14,  1.41s/it]
 35%|███▍      | 21565/61904 [51:25<15:36:28,  1.39s/it]
 35%|███▍      | 21566/61904 [51:26<15:24:26,  1.38s/it]
 35%|███▍      | 21567/61904 [51:28<15:08:43,  1.35s/it]
 35%|███▍      | 21568/61904 [51:29<14:52:31,  1.33s/it]
 35%|███▍      | 21569/61904 [51:30<15:18:19,  1.37s/it]
 35%|███▍      | 21570/61904 [51:32<15:24:16,  1.37s/it]
 35%|███▍      | 21571/61904 [51:33<14:53:49,  1.33s/it]
 35%|███▍      | 21572/61904 [51:34<14:56:12,  1.33s/it]
 35%|███▍      | 21573/61904 [51:36<15:12:43,  1.36s/it]
 35%|███▍      | 21574/61904 [51:37<15:01:56,  1.34s/it]
 35%|███▍      | 21575/61904 [51:38<15:02:44,  1.34s/it]
 35%|███▍      | 21576/61904 [51:40<15:38:34,  1.40s/it]
 35%|███▍      | 21577/61904 [51:41<15:49:57,  1.41s/it]
 35%|███▍      | 21578/61904 [51:43<15:51:46,  1.42s/it]
 35%|███▍      | 21579/61904 [51:44<16:06:52,  1.44s/it]
 35%|███▍      | 21580/61904 [51:46<16:07:38,  1.44s/it]
                                                        
{'loss': 2.6524, 'learning_rate': 1.6535070659924802e-07, 'epoch': 5.58}

 35%|███▍      | 21580/61904 [51:46<16:07:38,  1.44s/it]
 35%|███▍      | 21581/61904 [51:47<15:46:17,  1.41s/it]
 35%|███▍      | 21582/61904 [51:48<15:36:44,  1.39s/it]
 35%|███▍      | 21583/61904 [51:50<15:23:59,  1.37s/it]
 35%|███▍      | 21584/61904 [51:51<15:38:28,  1.40s/it]
 35%|███▍      | 21585/61904 [51:53<16:33:16,  1.48s/it]
 35%|███▍      | 21586/61904 [51:54<16:14:14,  1.45s/it]
 35%|███▍      | 21587/61904 [51:56<15:57:49,  1.43s/it]
 35%|███▍      | 21588/61904 [51:57<16:03:58,  1.43s/it]
 35%|███▍      | 21589/61904 [51:59<16:08:48,  1.44s/it]
 35%|███▍      | 21590/61904 [52:00<15:41:13,  1.40s/it]
 35%|███▍      | 21591/61904 [52:01<15:25:44,  1.38s/it]
 35%|███▍      | 21592/61904 [52:03<15:26:33,  1.38s/it]
 35%|███▍      | 21593/61904 [52:04<15:40:36,  1.40s/it]
 35%|███▍      | 21594/61904 [52:05<15:19:52,  1.37s/it]
 35%|███▍      | 21595/61904 [52:07<15:04:32,  1.35s/it]
 35%|███▍      | 21596/61904 [52:08<15:12:52,  1.36s/it]
 35%|███▍      | 21597/61904 [52:09<14:49:39,  1.32s/it]
 35%|███▍      | 21598/61904 [52:11<15:13:27,  1.36s/it]
 35%|███▍      | 21599/61904 [52:12<15:40:15,  1.40s/it]
 35%|███▍      | 21600/61904 [52:14<16:01:44,  1.43s/it]
                                                        
{'loss': 2.6894, 'learning_rate': 1.6531829378970568e-07, 'epoch': 5.58}

 35%|███▍      | 21600/61904 [52:14<16:01:44,  1.43s/it]
 35%|███▍      | 21601/61904 [52:15<15:52:15,  1.42s/it]
 35%|███▍      | 21602/61904 [52:16<15:28:31,  1.38s/it]
 35%|███▍      | 21603/61904 [52:18<15:25:18,  1.38s/it]
 35%|███▍      | 21604/61904 [52:19<15:36:04,  1.39s/it]
 35%|███▍      | 21605/61904 [52:21<15:31:39,  1.39s/it]
 35%|███▍      | 21606/61904 [52:22<15:40:43,  1.40s/it]
 35%|███▍      | 21607/61904 [52:23<15:24:31,  1.38s/it]
 35%|███▍      | 21608/61904 [52:25<15:09:22,  1.35s/it]
 35%|███▍      | 21609/61904 [52:26<14:52:49,  1.33s/it]
 35%|███▍      | 21610/61904 [52:27<14:58:20,  1.34s/it]
 35%|███▍      | 21611/61904 [52:28<14:45:02,  1.32s/it]
 35%|███▍      | 21612/61904 [52:30<14:37:34,  1.31s/it]
 35%|███▍      | 21613/61904 [52:31<15:07:36,  1.35s/it]
 35%|███▍      | 21614/61904 [52:32<14:48:42,  1.32s/it]
 35%|███▍      | 21615/61904 [52:34<14:48:08,  1.32s/it]
 35%|███▍      | 21616/61904 [52:35<15:05:22,  1.35s/it]
 35%|███▍      | 21617/61904 [52:37<15:22:26,  1.37s/it]
 35%|███▍      | 21618/61904 [52:38<15:14:05,  1.36s/it]
 35%|███▍      | 21619/61904 [52:39<15:10:59,  1.36s/it]
 35%|███▍      | 21620/61904 [52:41<14:52:32,  1.33s/it]
                                                        
{'loss': 2.6451, 'learning_rate': 1.6528588098016334e-07, 'epoch': 5.59}

 35%|███▍      | 21620/61904 [52:41<14:52:32,  1.33s/it]
 35%|███▍      | 21621/61904 [52:42<15:27:46,  1.38s/it]
 35%|███▍      | 21622/61904 [52:44<16:48:11,  1.50s/it]
 35%|███▍      | 21623/61904 [52:45<16:06:46,  1.44s/it]
 35%|███▍      | 21624/61904 [52:47<16:44:34,  1.50s/it]
 35%|███▍      | 21625/61904 [52:48<16:24:02,  1.47s/it]
 35%|███▍      | 21626/61904 [52:50<16:11:49,  1.45s/it]
 35%|███▍      | 21627/61904 [52:51<15:22:24,  1.37s/it]
 35%|███▍      | 21628/61904 [52:52<15:21:35,  1.37s/it]
 35%|███▍      | 21629/61904 [52:53<15:02:14,  1.34s/it]
 35%|███▍      | 21630/61904 [52:55<15:08:38,  1.35s/it]
 35%|███▍      | 21631/61904 [52:56<16:03:57,  1.44s/it]
 35%|███▍      | 21632/61904 [52:58<15:55:50,  1.42s/it]
 35%|███▍      | 21633/61904 [52:59<15:42:57,  1.40s/it]
 35%|███▍      | 21634/61904 [53:01<15:40:41,  1.40s/it]
 35%|███▍      | 21635/61904 [53:02<15:20:19,  1.37s/it]
 35%|███▍      | 21636/61904 [53:03<15:19:37,  1.37s/it]
 35%|███▍      | 21637/61904 [53:05<15:27:17,  1.38s/it]
 35%|███▍      | 21638/61904 [53:06<15:13:39,  1.36s/it]
 35%|███▍      | 21639/61904 [53:07<15:10:56,  1.36s/it]
 35%|███▍      | 21640/61904 [53:09<15:05:45,  1.35s/it]
                                                        
{'loss': 2.6636, 'learning_rate': 1.6525346817062103e-07, 'epoch': 5.59}

 35%|███▍      | 21640/61904 [53:09<15:05:45,  1.35s/it]
 35%|███▍      | 21641/61904 [53:10<15:26:30,  1.38s/it]
 35%|███▍      | 21642/61904 [53:11<15:03:06,  1.35s/it]
 35%|███▍      | 21643/61904 [53:13<15:25:15,  1.38s/it]
 35%|███▍      | 21644/61904 [53:14<15:59:15,  1.43s/it]
 35%|███▍      | 21645/61904 [53:16<15:50:01,  1.42s/it]
 35%|███▍      | 21646/61904 [53:17<15:42:13,  1.40s/it]
 35%|███▍      | 21647/61904 [53:19<16:08:45,  1.44s/it]
 35%|███▍      | 21648/61904 [53:20<16:09:59,  1.45s/it]
 35%|███▍      | 21649/61904 [53:22<15:54:39,  1.42s/it]
 35%|███▍      | 21650/61904 [53:23<15:16:15,  1.37s/it]
 35%|███▍      | 21651/61904 [53:24<14:53:42,  1.33s/it]
 35%|███▍      | 21652/61904 [53:25<14:47:50,  1.32s/it]
 35%|███▍      | 21653/61904 [53:27<15:42:30,  1.40s/it]
 35%|███▍      | 21654/61904 [53:28<15:54:50,  1.42s/it]
 35%|███▍      | 21655/61904 [53:30<16:23:44,  1.47s/it]
 35%|███▍      | 21656/61904 [53:31<16:21:32,  1.46s/it]
 35%|███▍      | 21657/61904 [53:33<16:31:02,  1.48s/it]
 35%|███▍      | 21658/61904 [53:34<16:06:41,  1.44s/it]
 35%|███▍      | 21659/61904 [53:36<15:34:21,  1.39s/it]
 35%|███▍      | 21660/61904 [53:37<16:10:52,  1.45s/it]
                                                        
{'loss': 2.6696, 'learning_rate': 1.652210553610787e-07, 'epoch': 5.6}

 35%|███▍      | 21660/61904 [53:37<16:10:52,  1.45s/it]
 35%|███▍      | 21661/61904 [53:39<16:02:51,  1.44s/it]
 35%|███▍      | 21662/61904 [53:40<15:33:43,  1.39s/it]
 35%|███▍      | 21663/61904 [53:41<15:27:05,  1.38s/it]
 35%|███▍      | 21664/61904 [53:42<15:11:28,  1.36s/it]
 35%|███▍      | 21665/61904 [53:44<15:04:13,  1.35s/it]
 35%|███▍      | 21666/61904 [53:45<16:00:17,  1.43s/it]
 35%|███▌      | 21667/61904 [53:47<15:44:18,  1.41s/it]
 35%|███▌      | 21668/61904 [53:48<15:41:55,  1.40s/it]
 35%|███▌      | 21669/61904 [53:50<15:33:54,  1.39s/it]
 35%|███▌      | 21670/61904 [53:51<15:32:55,  1.39s/it]
 35%|███▌      | 21671/61904 [53:52<16:03:03,  1.44s/it]
 35%|███▌      | 21672/61904 [53:54<15:03:13,  1.35s/it]
 35%|███▌      | 21673/61904 [53:55<15:15:24,  1.37s/it]
 35%|███▌      | 21674/61904 [53:56<15:24:51,  1.38s/it]
 35%|███▌      | 21675/61904 [53:58<15:29:54,  1.39s/it]
 35%|███▌      | 21676/61904 [53:59<15:31:13,  1.39s/it]
 35%|███▌      | 21677/61904 [54:01<15:24:37,  1.38s/it]
 35%|███▌      | 21678/61904 [54:02<16:05:50,  1.44s/it]
 35%|███▌      | 21679/61904 [54:04<16:31:15,  1.48s/it]
 35%|███▌      | 21680/61904 [54:05<15:58:21,  1.43s/it]
                                                        
{'loss': 2.6577, 'learning_rate': 1.6518864255153635e-07, 'epoch': 5.6}

 35%|███▌      | 21680/61904 [54:05<15:58:21,  1.43s/it]
 35%|███▌      | 21681/61904 [54:06<15:51:12,  1.42s/it]
 35%|███▌      | 21682/61904 [54:08<15:20:36,  1.37s/it]
 35%|███▌      | 21683/61904 [54:09<14:45:29,  1.32s/it]
 35%|███▌      | 21684/61904 [54:10<15:15:57,  1.37s/it]
 35%|███▌      | 21685/61904 [54:12<15:53:10,  1.42s/it]
 35%|███▌      | 21686/61904 [54:13<15:12:05,  1.36s/it]
 35%|███▌      | 21687/61904 [54:15<15:52:50,  1.42s/it]
 35%|███▌      | 21688/61904 [54:16<15:56:10,  1.43s/it]
 35%|███▌      | 21689/61904 [54:18<15:59:24,  1.43s/it]
 35%|███▌      | 21690/61904 [54:19<15:41:41,  1.41s/it]
 35%|███▌      | 21691/61904 [54:20<15:39:29,  1.40s/it]
 35%|███▌      | 21692/61904 [54:22<15:28:50,  1.39s/it]
 35%|███▌      | 21693/61904 [54:23<15:20:54,  1.37s/it]
 35%|███▌      | 21694/61904 [54:24<15:25:15,  1.38s/it]
 35%|███▌      | 21695/61904 [54:26<15:00:39,  1.34s/it]
 35%|███▌      | 21696/61904 [54:27<15:32:45,  1.39s/it]
 35%|███▌      | 21697/61904 [54:29<15:51:20,  1.42s/it]
 35%|███▌      | 21698/61904 [54:30<15:36:05,  1.40s/it]
 35%|███▌      | 21699/61904 [54:31<15:40:50,  1.40s/it]
 35%|███▌      | 21700/61904 [54:33<15:18:24,  1.37s/it]
                                                        
{'loss': 2.5968, 'learning_rate': 1.6515622974199404e-07, 'epoch': 5.61}

 35%|███▌      | 21700/61904 [54:33<15:18:24,  1.37s/it]
 35%|███▌      | 21701/61904 [54:34<15:23:45,  1.38s/it]
 35%|███▌      | 21702/61904 [54:35<15:20:33,  1.37s/it]
 35%|███▌      | 21703/61904 [54:37<15:35:04,  1.40s/it]
 35%|███▌      | 21704/61904 [54:38<15:04:59,  1.35s/it]
 35%|███▌      | 21705/61904 [54:40<15:39:11,  1.40s/it]
 35%|███▌      | 21706/61904 [54:41<15:12:21,  1.36s/it]
 35%|███▌      | 21707/61904 [54:42<15:37:32,  1.40s/it]
 35%|███▌      | 21708/61904 [54:44<15:39:48,  1.40s/it]
 35%|███▌      | 21709/61904 [54:45<15:38:35,  1.40s/it]
 35%|███▌      | 21710/61904 [54:47<15:55:22,  1.43s/it]
 35%|███▌      | 21711/61904 [54:48<15:36:10,  1.40s/it]
 35%|███▌      | 21712/61904 [54:49<15:14:09,  1.36s/it]
 35%|███▌      | 21713/61904 [54:51<15:05:08,  1.35s/it]
 35%|███▌      | 21714/61904 [54:52<15:17:21,  1.37s/it]
 35%|███▌      | 21715/61904 [54:53<15:16:34,  1.37s/it]
 35%|███▌      | 21716/61904 [54:55<15:24:47,  1.38s/it]
 35%|███▌      | 21717/61904 [54:56<15:13:01,  1.36s/it]
 35%|███▌      | 21718/61904 [54:58<15:00:42,  1.34s/it]
 35%|███▌      | 21719/61904 [54:59<15:17:46,  1.37s/it]
 35%|███▌      | 21720/61904 [55:00<15:31:48,  1.39s/it]
                                                        
{'loss': 2.6492, 'learning_rate': 1.651238169324517e-07, 'epoch': 5.61}

 35%|███▌      | 21720/61904 [55:00<15:31:48,  1.39s/it]
 35%|███▌      | 21721/61904 [55:02<15:46:01,  1.41s/it]
 35%|███▌      | 21722/61904 [55:03<15:31:35,  1.39s/it]
 35%|███▌      | 21723/61904 [55:04<15:10:36,  1.36s/it]
 35%|███▌      | 21724/61904 [55:06<15:00:06,  1.34s/it]
 35%|███▌      | 21725/61904 [55:07<15:26:49,  1.38s/it]
 35%|███▌      | 21726/61904 [55:09<15:17:44,  1.37s/it]
 35%|███▌      | 21727/61904 [55:10<15:59:22,  1.43s/it]
 35%|███▌      | 21728/61904 [55:12<16:04:18,  1.44s/it]
 35%|███▌      | 21729/61904 [55:13<15:43:28,  1.41s/it]
 35%|███▌      | 21730/61904 [55:14<15:11:07,  1.36s/it]
 35%|███▌      | 21731/61904 [55:16<15:02:36,  1.35s/it]
 35%|███▌      | 21732/61904 [55:17<15:03:24,  1.35s/it]
 35%|███▌      | 21733/61904 [55:18<15:11:06,  1.36s/it]
 35%|███▌      | 21734/61904 [55:20<15:20:32,  1.37s/it]
 35%|███▌      | 21735/61904 [55:21<15:11:17,  1.36s/it]
 35%|███▌      | 21736/61904 [55:22<15:32:09,  1.39s/it]
 35%|███▌      | 21737/61904 [55:24<15:27:22,  1.39s/it]
 35%|███▌      | 21738/61904 [55:25<15:19:31,  1.37s/it]
 35%|███▌      | 21739/61904 [55:26<15:05:57,  1.35s/it]
 35%|███▌      | 21740/61904 [55:28<15:14:43,  1.37s/it]
                                                        
{'loss': 2.6357, 'learning_rate': 1.6509140412290937e-07, 'epoch': 5.62}

 35%|███▌      | 21740/61904 [55:28<15:14:43,  1.37s/it]
 35%|███▌      | 21741/61904 [55:29<15:22:14,  1.38s/it]
 35%|███▌      | 21742/61904 [55:31<15:29:00,  1.39s/it]
 35%|███▌      | 21743/61904 [55:32<15:09:57,  1.36s/it]
 35%|███▌      | 21744/61904 [55:33<14:29:36,  1.30s/it]
 35%|███▌      | 21745/61904 [55:34<14:13:34,  1.28s/it]
 35%|███▌      | 21746/61904 [55:36<14:21:52,  1.29s/it]
 35%|███▌      | 21747/61904 [55:37<14:57:25,  1.34s/it]
 35%|███▌      | 21748/61904 [55:39<15:05:57,  1.35s/it]
 35%|███▌      | 21749/61904 [55:40<15:17:51,  1.37s/it]
 35%|███▌      | 21750/61904 [55:41<14:40:55,  1.32s/it]
 35%|███▌      | 21751/61904 [55:42<14:46:00,  1.32s/it]
 35%|███▌      | 21752/61904 [55:44<14:54:33,  1.34s/it]
 35%|███▌      | 21753/61904 [55:45<15:33:08,  1.39s/it]
 35%|███▌      | 21754/61904 [55:47<16:38:37,  1.49s/it]
 35%|███▌      | 21755/61904 [55:49<16:32:58,  1.48s/it]
 35%|███▌      | 21756/61904 [55:50<16:01:19,  1.44s/it]
 35%|███▌      | 21757/61904 [55:51<15:52:30,  1.42s/it]
 35%|███▌      | 21758/61904 [55:53<15:24:27,  1.38s/it]
 35%|███▌      | 21759/61904 [55:54<15:02:55,  1.35s/it]
 35%|███▌      | 21760/61904 [55:55<15:14:34,  1.37s/it]
                                                        
{'loss': 2.6401, 'learning_rate': 1.6505899131336705e-07, 'epoch': 5.62}

 35%|███▌      | 21760/61904 [55:55<15:14:34,  1.37s/it]
 35%|███▌      | 21761/61904 [55:57<15:07:44,  1.36s/it]
 35%|███▌      | 21762/61904 [55:58<15:09:36,  1.36s/it]
 35%|███▌      | 21763/61904 [55:59<15:13:18,  1.37s/it]
 35%|███▌      | 21764/61904 [56:01<16:04:51,  1.44s/it]
 35%|███▌      | 21765/61904 [56:02<15:43:46,  1.41s/it]
 35%|███▌      | 21766/61904 [56:04<15:37:04,  1.40s/it]
 35%|███▌      | 21767/61904 [56:05<15:11:02,  1.36s/it]
 35%|███▌      | 21768/61904 [56:06<15:15:26,  1.37s/it]
 35%|███▌      | 21769/61904 [56:08<15:44:36,  1.41s/it]
 35%|███▌      | 21770/61904 [56:09<15:26:26,  1.39s/it]
 35%|███▌      | 21771/61904 [56:10<15:12:39,  1.36s/it]
 35%|███▌      | 21772/61904 [56:12<14:47:52,  1.33s/it]
 35%|███▌      | 21773/61904 [56:13<15:11:08,  1.36s/it]
 35%|███▌      | 21774/61904 [56:14<15:00:27,  1.35s/it]
 35%|███▌      | 21775/61904 [56:16<15:25:24,  1.38s/it]
 35%|███▌      | 21776/61904 [56:17<15:12:06,  1.36s/it]
 35%|███▌      | 21777/61904 [56:19<14:57:26,  1.34s/it]
 35%|███▌      | 21778/61904 [56:20<14:58:14,  1.34s/it]
 35%|███▌      | 21779/61904 [56:21<15:00:17,  1.35s/it]
 35%|███▌      | 21780/61904 [56:23<14:56:28,  1.34s/it]
                                                        
{'loss': 2.5984, 'learning_rate': 1.650265785038247e-07, 'epoch': 5.63}

 35%|███▌      | 21780/61904 [56:23<14:56:28,  1.34s/it]
 35%|███▌      | 21781/61904 [56:24<14:49:31,  1.33s/it]
 35%|███▌      | 21782/61904 [56:25<15:17:48,  1.37s/it]
 35%|███▌      | 21783/61904 [56:27<15:37:28,  1.40s/it]
 35%|███▌      | 21784/61904 [56:28<16:11:18,  1.45s/it]
 35%|███▌      | 21785/61904 [56:30<15:54:49,  1.43s/it]
 35%|███▌      | 21786/61904 [56:31<15:41:09,  1.41s/it]
 35%|███▌      | 21787/61904 [56:32<15:04:30,  1.35s/it]
 35%|███▌      | 21788/61904 [56:34<14:55:24,  1.34s/it]
 35%|███▌      | 21789/61904 [56:35<14:23:49,  1.29s/it]
 35%|███▌      | 21790/61904 [56:36<14:47:19,  1.33s/it]
 35%|███▌      | 21791/61904 [56:38<15:06:44,  1.36s/it]
 35%|███▌      | 21792/61904 [56:39<15:18:41,  1.37s/it]
 35%|███▌      | 21793/61904 [56:40<15:13:51,  1.37s/it]
 35%|███▌      | 21794/61904 [56:42<15:33:14,  1.40s/it]
 35%|███▌      | 21795/61904 [56:43<15:29:38,  1.39s/it]
 35%|███▌      | 21796/61904 [56:45<16:04:08,  1.44s/it]
 35%|███▌      | 21797/61904 [56:46<15:43:09,  1.41s/it]
 35%|███▌      | 21798/61904 [56:48<15:28:12,  1.39s/it]
 35%|███▌      | 21799/61904 [56:49<15:35:53,  1.40s/it]
 35%|███▌      | 21800/61904 [56:50<15:08:04,  1.36s/it]
                                                        
{'loss': 2.6678, 'learning_rate': 1.6499416569428238e-07, 'epoch': 5.63}

 35%|███▌      | 21800/61904 [56:50<15:08:04,  1.36s/it]
 35%|███▌      | 21801/61904 [56:52<15:03:23,  1.35s/it]
 35%|███▌      | 21802/61904 [56:53<15:33:00,  1.40s/it]
 35%|███▌      | 21803/61904 [56:54<15:36:41,  1.40s/it]
 35%|███▌      | 21804/61904 [56:56<15:05:01,  1.35s/it]
 35%|███▌      | 21805/61904 [56:57<14:56:44,  1.34s/it]
 35%|███▌      | 21806/61904 [56:58<15:18:47,  1.37s/it]
 35%|███▌      | 21807/61904 [57:00<15:13:32,  1.37s/it]
 35%|███▌      | 21808/61904 [57:01<15:19:49,  1.38s/it]
 35%|███▌      | 21809/61904 [57:03<15:08:19,  1.36s/it]
 35%|███▌      | 21810/61904 [57:04<15:07:04,  1.36s/it]
 35%|███▌      | 21811/61904 [57:05<15:29:54,  1.39s/it]
 35%|███▌      | 21812/61904 [57:07<15:48:34,  1.42s/it]
 35%|███▌      | 21813/61904 [57:08<16:13:19,  1.46s/it]
 35%|███▌      | 21814/61904 [57:10<15:46:50,  1.42s/it]
 35%|███▌      | 21815/61904 [57:11<15:19:29,  1.38s/it]
 35%|███▌      | 21816/61904 [57:13<15:52:02,  1.42s/it]
 35%|███▌      | 21817/61904 [57:14<15:41:03,  1.41s/it]
 35%|███▌      | 21818/61904 [57:15<16:05:12,  1.44s/it]
 35%|███▌      | 21819/61904 [57:17<15:46:54,  1.42s/it]
 35%|███▌      | 21820/61904 [57:18<15:21:45,  1.38s/it]
                                                        
{'loss': 2.6161, 'learning_rate': 1.6496175288474004e-07, 'epoch': 5.64}

 35%|███▌      | 21820/61904 [57:18<15:21:45,  1.38s/it]
 35%|███▌      | 21821/61904 [57:19<15:29:34,  1.39s/it]
 35%|███▌      | 21822/61904 [57:21<15:17:42,  1.37s/it]
 35%|███▌      | 21823/61904 [57:22<15:11:54,  1.37s/it]
 35%|███▌      | 21824/61904 [57:23<14:36:01,  1.31s/it]
 35%|███▌      | 21825/61904 [57:25<15:09:14,  1.36s/it]
 35%|███▌      | 21826/61904 [57:26<15:39:57,  1.41s/it]
 35%|███▌      | 21827/61904 [57:28<15:17:44,  1.37s/it]
 35%|███▌      | 21828/61904 [57:29<15:01:56,  1.35s/it]
 35%|███▌      | 21829/61904 [57:30<15:23:09,  1.38s/it]
 35%|███▌      | 21830/61904 [57:32<15:33:51,  1.40s/it]
 35%|███▌      | 21831/61904 [57:33<15:40:00,  1.41s/it]
 35%|███▌      | 21832/61904 [57:35<15:49:46,  1.42s/it]
 35%|███▌      | 21833/61904 [57:36<15:49:52,  1.42s/it]
 35%|███▌      | 21834/61904 [57:38<15:44:50,  1.41s/it]
 35%|███▌      | 21835/61904 [57:39<15:57:34,  1.43s/it]
 35%|███▌      | 21836/61904 [57:40<15:39:31,  1.41s/it]
 35%|███▌      | 21837/61904 [57:42<15:11:23,  1.36s/it]
 35%|███▌      | 21838/61904 [57:43<15:10:05,  1.36s/it]
 35%|███▌      | 21839/61904 [57:44<15:05:01,  1.36s/it]
 35%|███▌      | 21840/61904 [57:46<15:16:04,  1.37s/it]
                                                        
{'loss': 2.6262, 'learning_rate': 1.649293400751977e-07, 'epoch': 5.64}

 35%|███▌      | 21840/61904 [57:46<15:16:04,  1.37s/it]
 35%|███▌      | 21841/61904 [57:47<15:29:18,  1.39s/it]
 35%|███▌      | 21842/61904 [57:48<15:00:32,  1.35s/it]
 35%|███▌      | 21843/61904 [57:50<16:23:18,  1.47s/it]
 35%|███▌      | 21844/61904 [57:51<15:32:51,  1.40s/it]
 35%|███▌      | 21845/61904 [57:53<16:00:46,  1.44s/it]
 35%|███▌      | 21846/61904 [57:54<16:00:27,  1.44s/it]
 35%|███▌      | 21847/61904 [57:56<16:23:26,  1.47s/it]
 35%|███▌      | 21848/61904 [57:57<16:13:39,  1.46s/it]
 35%|███▌      | 21849/61904 [57:59<15:44:04,  1.41s/it]
 35%|███▌      | 21850/61904 [58:00<15:49:25,  1.42s/it]
 35%|███▌      | 21851/61904 [58:02<15:48:06,  1.42s/it]
 35%|███▌      | 21852/61904 [58:03<15:53:12,  1.43s/it]
 35%|███▌      | 21853/61904 [58:04<15:11:43,  1.37s/it]
 35%|███▌      | 21854/61904 [58:05<14:45:44,  1.33s/it]
 35%|███▌      | 21855/61904 [58:07<14:48:44,  1.33s/it]
 35%|███▌      | 21856/61904 [58:08<15:00:45,  1.35s/it]
 35%|███▌      | 21857/61904 [58:09<14:58:39,  1.35s/it]
 35%|███▌      | 21858/61904 [58:11<15:16:40,  1.37s/it]
 35%|███▌      | 21859/61904 [58:12<15:35:45,  1.40s/it]
 35%|███▌      | 21860/61904 [58:14<15:37:00,  1.40s/it]
                                                        
{'loss': 2.6514, 'learning_rate': 1.648969272656554e-07, 'epoch': 5.65}

 35%|███▌      | 21860/61904 [58:14<15:37:00,  1.40s/it]
 35%|███▌      | 21861/61904 [58:15<15:21:48,  1.38s/it]
 35%|███▌      | 21862/61904 [58:17<15:59:17,  1.44s/it]
 35%|███▌      | 21863/61904 [58:18<15:13:21,  1.37s/it]
 35%|███▌      | 21864/61904 [58:19<15:18:08,  1.38s/it]
 35%|███▌      | 21865/61904 [58:21<15:31:52,  1.40s/it]
 35%|███▌      | 21866/61904 [58:22<15:11:40,  1.37s/it]
 35%|███▌      | 21867/61904 [58:23<15:15:46,  1.37s/it]
 35%|███▌      | 21868/61904 [58:25<14:54:39,  1.34s/it]
 35%|███▌      | 21869/61904 [58:26<14:57:45,  1.35s/it]
 35%|███▌      | 21870/61904 [58:27<15:02:06,  1.35s/it]
 35%|███▌      | 21871/61904 [58:29<15:28:06,  1.39s/it]
 35%|███▌      | 21872/61904 [58:30<14:56:23,  1.34s/it]
 35%|███▌      | 21873/61904 [58:31<14:42:46,  1.32s/it]
 35%|███▌      | 21874/61904 [58:33<15:06:56,  1.36s/it]
 35%|███▌      | 21875/61904 [58:34<15:23:23,  1.38s/it]
 35%|███▌      | 21876/61904 [58:36<15:15:19,  1.37s/it]
 35%|███▌      | 21877/61904 [58:37<16:06:33,  1.45s/it]
 35%|███▌      | 21878/61904 [58:39<15:37:41,  1.41s/it]
 35%|███▌      | 21879/61904 [58:40<15:21:57,  1.38s/it]
 35%|███▌      | 21880/61904 [58:41<14:55:37,  1.34s/it]
                                                        
{'loss': 2.6629, 'learning_rate': 1.6486451445611305e-07, 'epoch': 5.66}

 35%|███▌      | 21880/61904 [58:41<14:55:37,  1.34s/it]
 35%|███▌      | 21881/61904 [58:43<15:01:21,  1.35s/it]
 35%|███▌      | 21882/61904 [58:44<15:01:17,  1.35s/it]
 35%|███▌      | 21883/61904 [58:45<14:52:28,  1.34s/it]
 35%|███▌      | 21884/61904 [58:47<15:01:17,  1.35s/it]
 35%|███▌      | 21885/61904 [58:48<15:01:44,  1.35s/it]
 35%|███▌      | 21886/61904 [58:49<15:33:49,  1.40s/it]
 35%|███▌      | 21887/61904 [58:51<15:23:58,  1.39s/it]
 35%|███▌      | 21888/61904 [58:52<15:17:46,  1.38s/it]
 35%|███▌      | 21889/61904 [58:53<15:08:59,  1.36s/it]
 35%|███▌      | 21890/61904 [58:55<14:27:50,  1.30s/it]
 35%|███▌      | 21891/61904 [58:56<14:38:01,  1.32s/it]
 35%|███▌      | 21892/61904 [58:57<14:48:16,  1.33s/it]
 35%|███▌      | 21893/61904 [58:59<15:11:11,  1.37s/it]
 35%|███▌      | 21894/61904 [59:00<15:55:13,  1.43s/it]
 35%|███▌      | 21895/61904 [59:02<15:41:17,  1.41s/it]
 35%|███▌      | 21896/61904 [59:03<15:20:07,  1.38s/it]
 35%|███▌      | 21897/61904 [59:04<14:59:36,  1.35s/it]
 35%|███▌      | 21898/61904 [59:06<15:21:54,  1.38s/it]
 35%|███▌      | 21899/61904 [59:07<15:20:48,  1.38s/it]
 35%|███▌      | 21900/61904 [59:08<15:00:45,  1.35s/it]
                                                        
{'loss': 2.6764, 'learning_rate': 1.6483210164657071e-07, 'epoch': 5.66}

 35%|███▌      | 21900/61904 [59:08<15:00:45,  1.35s/it]
 35%|███▌      | 21901/61904 [59:10<15:01:52,  1.35s/it]
 35%|███▌      | 21902/61904 [59:11<14:43:12,  1.32s/it]
 35%|███▌      | 21903/61904 [59:13<15:08:02,  1.36s/it]
 35%|███▌      | 21904/61904 [59:14<15:11:57,  1.37s/it]
 35%|███▌      | 21905/61904 [59:16<16:06:29,  1.45s/it]
 35%|███▌      | 21906/61904 [59:17<15:35:56,  1.40s/it]
 35%|███▌      | 21907/61904 [59:18<15:55:10,  1.43s/it]
 35%|███▌      | 21908/61904 [59:20<15:57:17,  1.44s/it]
 35%|███▌      | 21909/61904 [59:21<15:47:57,  1.42s/it]
 35%|███▌      | 21910/61904 [59:22<15:29:41,  1.39s/it]
 35%|███▌      | 21911/61904 [59:24<14:54:03,  1.34s/it]
 35%|███▌      | 21912/61904 [59:25<14:46:59,  1.33s/it]
 35%|███▌      | 21913/61904 [59:26<14:44:47,  1.33s/it]
 35%|███▌      | 21914/61904 [59:28<14:35:24,  1.31s/it]
 35%|███▌      | 21915/61904 [59:29<14:37:48,  1.32s/it]
 35%|███▌      | 21916/61904 [59:30<14:56:27,  1.35s/it]
 35%|███▌      | 21917/61904 [59:32<14:46:50,  1.33s/it]
 35%|███▌      | 21918/61904 [59:33<14:32:27,  1.31s/it]
 35%|███▌      | 21919/61904 [59:34<14:33:01,  1.31s/it]
 35%|███▌      | 21920/61904 [59:36<14:33:17,  1.31s/it]
                                                        
{'loss': 2.6414, 'learning_rate': 1.647996888370284e-07, 'epoch': 5.67}

 35%|███▌      | 21920/61904 [59:36<14:33:17,  1.31s/it]
 35%|███▌      | 21921/61904 [59:37<14:58:00,  1.35s/it]
 35%|███▌      | 21922/61904 [59:38<14:55:57,  1.34s/it]
 35%|███▌      | 21923/61904 [59:40<14:49:54,  1.34s/it]
 35%|███▌      | 21924/61904 [59:41<14:53:59,  1.34s/it]
 35%|███▌      | 21925/61904 [59:42<14:26:55,  1.30s/it]
 35%|███▌      | 21926/61904 [59:44<14:38:28,  1.32s/it]
 35%|███▌      | 21927/61904 [59:45<14:44:19,  1.33s/it]
 35%|███▌      | 21928/61904 [59:46<15:04:36,  1.36s/it]
 35%|███▌      | 21929/61904 [59:48<14:54:24,  1.34s/it]
 35%|███▌      | 21930/61904 [59:49<14:38:33,  1.32s/it]
 35%|███▌      | 21931/61904 [59:50<14:27:36,  1.30s/it]
 35%|███▌      | 21932/61904 [59:52<15:00:09,  1.35s/it]
 35%|███▌      | 21933/61904 [59:53<15:10:23,  1.37s/it]
 35%|███▌      | 21934/61904 [59:54<14:54:12,  1.34s/it]
 35%|███▌      | 21935/61904 [59:56<14:48:03,  1.33s/it]
 35%|███▌      | 21936/61904 [59:57<14:55:04,  1.34s/it]
 35%|███▌      | 21937/61904 [59:59<15:33:08,  1.40s/it]
 35%|███▌      | 21938/61904 [1:00:00<15:10:22,  1.37s/it]
 35%|███▌      | 21939/61904 [1:00:01<15:28:12,  1.39s/it]
 35%|███▌      | 21940/61904 [1:00:03<15:21:34,  1.38s/it]
                                                          
{'loss': 2.5379, 'learning_rate': 1.6476727602748604e-07, 'epoch': 5.67}

 35%|███▌      | 21940/61904 [1:00:03<15:21:34,  1.38s/it]
 35%|███▌      | 21941/61904 [1:00:04<15:28:16,  1.39s/it]
 35%|███▌      | 21942/61904 [1:00:05<15:08:33,  1.36s/it]
 35%|███▌      | 21943/61904 [1:00:07<15:27:23,  1.39s/it]
 35%|███▌      | 21944/61904 [1:00:08<15:26:18,  1.39s/it]
 35%|███▌      | 21945/61904 [1:00:09<15:00:44,  1.35s/it]
 35%|███▌      | 21946/61904 [1:00:11<15:05:44,  1.36s/it]
 35%|███▌      | 21947/61904 [1:00:12<14:41:19,  1.32s/it]
 35%|███▌      | 21948/61904 [1:00:13<15:02:50,  1.36s/it]
 35%|███▌      | 21949/61904 [1:00:15<15:09:30,  1.37s/it]
 35%|███▌      | 21950/61904 [1:00:16<15:19:37,  1.38s/it]
 35%|███▌      | 21951/61904 [1:00:18<15:44:10,  1.42s/it]
 35%|███▌      | 21952/61904 [1:00:19<15:29:33,  1.40s/it]
 35%|███▌      | 21953/61904 [1:00:21<15:23:29,  1.39s/it]
 35%|███▌      | 21954/61904 [1:00:22<15:01:54,  1.35s/it]
 35%|███▌      | 21955/61904 [1:00:23<14:53:06,  1.34s/it]
 35%|███▌      | 21956/61904 [1:00:25<15:06:27,  1.36s/it]
 35%|███▌      | 21957/61904 [1:00:26<15:10:26,  1.37s/it]
 35%|███▌      | 21958/61904 [1:00:27<15:31:54,  1.40s/it]
 35%|███▌      | 21959/61904 [1:00:29<15:12:45,  1.37s/it]
 35%|███▌      | 21960/61904 [1:00:30<15:11:17,  1.37s/it]
                                                          
{'loss': 2.6744, 'learning_rate': 1.6473486321794373e-07, 'epoch': 5.68}

 35%|███▌      | 21960/61904 [1:00:30<15:11:17,  1.37s/it]
 35%|███▌      | 21961/61904 [1:00:31<15:09:21,  1.37s/it]
 35%|███▌      | 21962/61904 [1:00:33<15:36:21,  1.41s/it]
 35%|███▌      | 21963/61904 [1:00:34<15:15:34,  1.38s/it]
 35%|███▌      | 21964/61904 [1:00:36<15:33:28,  1.40s/it]
 35%|███▌      | 21965/61904 [1:00:37<15:21:39,  1.38s/it]
 35%|███▌      | 21966/61904 [1:00:38<15:12:59,  1.37s/it]
 35%|███▌      | 21967/61904 [1:00:40<15:24:37,  1.39s/it]
 35%|███▌      | 21968/61904 [1:00:41<15:25:21,  1.39s/it]
 35%|███▌      | 21969/61904 [1:00:43<15:20:46,  1.38s/it]
 35%|███▌      | 21970/61904 [1:00:44<15:15:56,  1.38s/it]
 35%|███▌      | 21971/61904 [1:00:45<15:30:25,  1.40s/it]
 35%|███▌      | 21972/61904 [1:00:47<15:37:20,  1.41s/it]
 35%|███▌      | 21973/61904 [1:00:48<15:36:06,  1.41s/it]
 35%|███▌      | 21974/61904 [1:00:50<15:46:39,  1.42s/it]
 35%|███▌      | 21975/61904 [1:00:51<15:41:06,  1.41s/it]
 36%|███▌      | 21976/61904 [1:00:52<15:31:31,  1.40s/it]
 36%|███▌      | 21977/61904 [1:00:54<16:02:07,  1.45s/it]
 36%|███▌      | 21978/61904 [1:00:55<15:36:27,  1.41s/it]
 36%|███▌      | 21979/61904 [1:00:57<16:17:38,  1.47s/it]
 36%|███▌      | 21980/61904 [1:00:58<15:45:17,  1.42s/it]
                                                          
{'loss': 2.7254, 'learning_rate': 1.647024504084014e-07, 'epoch': 5.68}

 36%|███▌      | 21980/61904 [1:00:58<15:45:17,  1.42s/it]
 36%|███▌      | 21981/61904 [1:01:00<16:02:14,  1.45s/it]
 36%|███▌      | 21982/61904 [1:01:01<16:01:36,  1.45s/it]
 36%|███▌      | 21983/61904 [1:01:03<15:50:34,  1.43s/it]
 36%|███▌      | 21984/61904 [1:01:04<15:40:18,  1.41s/it]
 36%|███▌      | 21985/61904 [1:01:05<15:25:34,  1.39s/it]
 36%|███▌      | 21986/61904 [1:01:07<15:42:08,  1.42s/it]
 36%|███▌      | 21987/61904 [1:01:08<15:28:59,  1.40s/it]
 36%|███▌      | 21988/61904 [1:01:09<15:26:13,  1.39s/it]
 36%|███▌      | 21989/61904 [1:01:11<15:48:45,  1.43s/it]
 36%|███▌      | 21990/61904 [1:01:12<15:50:00,  1.43s/it]
 36%|███▌      | 21991/61904 [1:01:14<15:42:15,  1.42s/it]
 36%|███▌      | 21992/61904 [1:01:15<15:08:14,  1.37s/it]
 36%|███▌      | 21993/61904 [1:01:16<14:57:37,  1.35s/it]
 36%|███▌      | 21994/61904 [1:01:18<15:52:42,  1.43s/it]
 36%|███▌      | 21995/61904 [1:01:19<15:44:53,  1.42s/it]
 36%|███▌      | 21996/61904 [1:01:21<15:10:56,  1.37s/it]
 36%|███▌      | 21997/61904 [1:01:22<14:46:35,  1.33s/it]
 36%|███▌      | 21998/61904 [1:01:23<15:05:50,  1.36s/it]
 36%|███▌      | 21999/61904 [1:01:25<14:57:06,  1.35s/it]
 36%|███▌      | 22000/61904 [1:01:26<14:51:15,  1.34s/it]
                                                          
{'loss': 2.6408, 'learning_rate': 1.6467003759885905e-07, 'epoch': 5.69}

 36%|███▌      | 22000/61904 [1:01:26<14:51:15,  1.34s/it]
 36%|███▌      | 22001/61904 [1:01:27<15:23:46,  1.39s/it]
 36%|███▌      | 22002/61904 [1:01:29<15:17:46,  1.38s/it]
 36%|███▌      | 22003/61904 [1:01:30<15:14:27,  1.38s/it]
 36%|███▌      | 22004/61904 [1:01:31<14:56:11,  1.35s/it]
 36%|███▌      | 22005/61904 [1:01:33<14:55:45,  1.35s/it]
 36%|███▌      | 22006/61904 [1:01:34<14:53:01,  1.34s/it]
 36%|███▌      | 22007/61904 [1:01:35<15:01:35,  1.36s/it]
 36%|███▌      | 22008/61904 [1:01:37<14:57:26,  1.35s/it]
 36%|███▌      | 22009/61904 [1:01:38<15:08:50,  1.37s/it]
 36%|███▌      | 22010/61904 [1:01:40<15:01:15,  1.36s/it]
 36%|███▌      | 22011/61904 [1:01:41<15:01:15,  1.36s/it]
 36%|███▌      | 22012/61904 [1:01:42<14:54:43,  1.35s/it]
 36%|███▌      | 22013/61904 [1:01:44<14:46:31,  1.33s/it]
 36%|███▌      | 22014/61904 [1:01:45<14:29:24,  1.31s/it]
 36%|███▌      | 22015/61904 [1:01:46<14:45:07,  1.33s/it]
 36%|███▌      | 22016/61904 [1:01:47<14:38:28,  1.32s/it]
 36%|███▌      | 22017/61904 [1:01:49<15:05:50,  1.36s/it]
 36%|███▌      | 22018/61904 [1:01:50<15:03:19,  1.36s/it]
 36%|███▌      | 22019/61904 [1:01:52<15:39:33,  1.41s/it]
 36%|███▌      | 22020/61904 [1:01:53<15:00:56,  1.36s/it]
                                                          
{'loss': 2.6751, 'learning_rate': 1.6463762478931674e-07, 'epoch': 5.69}

 36%|███▌      | 22020/61904 [1:01:53<15:00:56,  1.36s/it]
 36%|███▌      | 22021/61904 [1:01:54<15:04:20,  1.36s/it]
 36%|███▌      | 22022/61904 [1:01:56<14:40:32,  1.32s/it]
 36%|███▌      | 22023/61904 [1:01:57<15:06:03,  1.36s/it]
 36%|███▌      | 22024/61904 [1:01:59<15:17:23,  1.38s/it]
 36%|███▌      | 22025/61904 [1:02:00<15:12:32,  1.37s/it]
 36%|███▌      | 22026/61904 [1:02:01<15:13:05,  1.37s/it]
 36%|███▌      | 22027/61904 [1:02:03<16:01:26,  1.45s/it]
 36%|███▌      | 22028/61904 [1:02:04<15:53:43,  1.44s/it]
 36%|███▌      | 22029/61904 [1:02:06<15:45:44,  1.42s/it]
 36%|███▌      | 22030/61904 [1:02:07<15:37:53,  1.41s/it]
 36%|███▌      | 22031/61904 [1:02:08<15:41:28,  1.42s/it]
 36%|███▌      | 22032/61904 [1:02:10<15:27:29,  1.40s/it]
 36%|███▌      | 22033/61904 [1:02:11<15:36:57,  1.41s/it]
 36%|███▌      | 22034/61904 [1:02:13<15:44:41,  1.42s/it]
 36%|███▌      | 22035/61904 [1:02:14<15:42:38,  1.42s/it]
 36%|███▌      | 22036/61904 [1:02:16<15:38:29,  1.41s/it]
 36%|███▌      | 22037/61904 [1:02:17<15:44:25,  1.42s/it]
 36%|███▌      | 22038/61904 [1:02:18<15:47:46,  1.43s/it]
 36%|███▌      | 22039/61904 [1:02:20<15:40:17,  1.42s/it]
 36%|███▌      | 22040/61904 [1:02:21<15:34:44,  1.41s/it]
                                                          
{'loss': 2.6391, 'learning_rate': 1.646052119797744e-07, 'epoch': 5.7}

 36%|███▌      | 22040/61904 [1:02:21<15:34:44,  1.41s/it]
 36%|███▌      | 22041/61904 [1:02:23<15:22:38,  1.39s/it]
 36%|███▌      | 22042/61904 [1:02:24<15:04:23,  1.36s/it]
 36%|███▌      | 22043/61904 [1:02:25<15:12:20,  1.37s/it]
 36%|███▌      | 22044/61904 [1:02:27<15:05:55,  1.36s/it]
 36%|███▌      | 22045/61904 [1:02:28<14:48:58,  1.34s/it]
 36%|███▌      | 22046/61904 [1:02:29<15:06:07,  1.36s/it]
 36%|███▌      | 22047/61904 [1:02:31<15:31:28,  1.40s/it]
 36%|███▌      | 22048/61904 [1:02:32<15:10:50,  1.37s/it]
 36%|███▌      | 22049/61904 [1:02:33<15:03:17,  1.36s/it]
 36%|███▌      | 22050/61904 [1:02:35<15:02:46,  1.36s/it]
 36%|███▌      | 22051/61904 [1:02:36<15:18:15,  1.38s/it]
 36%|███▌      | 22052/61904 [1:02:38<15:17:08,  1.38s/it]
 36%|███▌      | 22053/61904 [1:02:39<14:53:02,  1.34s/it]
 36%|███▌      | 22054/61904 [1:02:40<14:47:12,  1.34s/it]
 36%|███▌      | 22055/61904 [1:02:42<14:50:26,  1.34s/it]
 36%|███▌      | 22056/61904 [1:02:43<14:43:57,  1.33s/it]
 36%|███▌      | 22057/61904 [1:02:44<15:02:28,  1.36s/it]
 36%|███▌      | 22058/61904 [1:02:46<14:54:30,  1.35s/it]
 36%|███▌      | 22059/61904 [1:02:47<15:07:10,  1.37s/it]
 36%|███▌      | 22060/61904 [1:02:48<15:08:00,  1.37s/it]
                                                          
{'loss': 2.625, 'learning_rate': 1.6457279917023206e-07, 'epoch': 5.7}

 36%|███▌      | 22060/61904 [1:02:48<15:08:00,  1.37s/it]
 36%|███▌      | 22061/61904 [1:02:50<15:05:13,  1.36s/it]
 36%|███▌      | 22062/61904 [1:02:51<15:52:37,  1.43s/it]
 36%|███▌      | 22063/61904 [1:02:53<16:05:19,  1.45s/it]
 36%|███▌      | 22064/61904 [1:02:54<16:04:53,  1.45s/it]
 36%|███▌      | 22065/61904 [1:02:56<15:24:08,  1.39s/it]
 36%|███▌      | 22066/61904 [1:02:57<15:42:12,  1.42s/it]
 36%|███▌      | 22067/61904 [1:02:58<15:00:34,  1.36s/it]
 36%|███▌      | 22068/61904 [1:03:00<15:25:54,  1.39s/it]
 36%|███▌      | 22069/61904 [1:03:01<15:05:44,  1.36s/it]
 36%|███▌      | 22070/61904 [1:03:02<14:54:38,  1.35s/it]
 36%|███▌      | 22071/61904 [1:03:04<14:37:13,  1.32s/it]
 36%|███▌      | 22072/61904 [1:03:05<14:35:55,  1.32s/it]
 36%|███▌      | 22073/61904 [1:03:06<15:22:57,  1.39s/it]
 36%|███▌      | 22074/61904 [1:03:08<15:50:56,  1.43s/it]
 36%|███▌      | 22075/61904 [1:03:09<15:42:00,  1.42s/it]
 36%|███▌      | 22076/61904 [1:03:11<16:13:26,  1.47s/it]
 36%|███▌      | 22077/61904 [1:03:12<16:20:14,  1.48s/it]
 36%|███▌      | 22078/61904 [1:03:14<16:21:46,  1.48s/it]
 36%|███▌      | 22079/61904 [1:03:15<15:47:56,  1.43s/it]
 36%|███▌      | 22080/61904 [1:03:17<16:17:41,  1.47s/it]
                                                          
{'loss': 2.607, 'learning_rate': 1.6454038636068975e-07, 'epoch': 5.71}

 36%|███▌      | 22080/61904 [1:03:17<16:17:41,  1.47s/it]
 36%|███▌      | 22081/61904 [1:03:18<16:30:48,  1.49s/it]
 36%|███▌      | 22082/61904 [1:03:20<15:54:15,  1.44s/it]
 36%|███▌      | 22083/61904 [1:03:21<15:52:21,  1.43s/it]
 36%|███▌      | 22084/61904 [1:03:23<15:54:12,  1.44s/it]
 36%|███▌      | 22085/61904 [1:03:24<15:28:00,  1.40s/it]
 36%|███▌      | 22086/61904 [1:03:25<15:12:23,  1.37s/it]
 36%|███▌      | 22087/61904 [1:03:27<15:29:45,  1.40s/it]
 36%|███▌      | 22088/61904 [1:03:28<15:31:10,  1.40s/it]
 36%|███▌      | 22089/61904 [1:03:29<15:44:50,  1.42s/it]
 36%|███▌      | 22090/61904 [1:03:31<15:14:49,  1.38s/it]
 36%|███▌      | 22091/61904 [1:03:32<14:59:23,  1.36s/it]
 36%|███▌      | 22092/61904 [1:03:33<14:53:41,  1.35s/it]
 36%|███▌      | 22093/61904 [1:03:35<14:50:28,  1.34s/it]
 36%|███▌      | 22094/61904 [1:03:36<14:35:03,  1.32s/it]
 36%|███▌      | 22095/61904 [1:03:37<14:50:26,  1.34s/it]
 36%|███▌      | 22096/61904 [1:03:39<14:57:30,  1.35s/it]
 36%|███▌      | 22097/61904 [1:03:40<15:11:15,  1.37s/it]
 36%|███▌      | 22098/61904 [1:03:41<14:40:54,  1.33s/it]
 36%|███▌      | 22099/61904 [1:03:43<14:32:09,  1.31s/it]
 36%|███▌      | 22100/61904 [1:03:44<14:40:05,  1.33s/it]
                                                          
{'loss': 2.6629, 'learning_rate': 1.6450797355114739e-07, 'epoch': 5.71}

 36%|███▌      | 22100/61904 [1:03:44<14:40:05,  1.33s/it]
 36%|███▌      | 22101/61904 [1:03:45<14:16:27,  1.29s/it]
 36%|███▌      | 22102/61904 [1:03:47<14:19:12,  1.30s/it]
 36%|███▌      | 22103/61904 [1:03:48<14:29:00,  1.31s/it]
 36%|███▌      | 22104/61904 [1:03:49<14:57:11,  1.35s/it]
 36%|███▌      | 22105/61904 [1:03:51<15:15:30,  1.38s/it]
 36%|███▌      | 22106/61904 [1:03:52<15:10:06,  1.37s/it]
 36%|███▌      | 22107/61904 [1:03:54<15:34:38,  1.41s/it]
 36%|███▌      | 22108/61904 [1:03:55<15:02:13,  1.36s/it]
 36%|███▌      | 22109/61904 [1:03:56<14:45:42,  1.34s/it]
 36%|███▌      | 22110/61904 [1:03:58<15:04:58,  1.36s/it]
 36%|███▌      | 22111/61904 [1:03:59<14:47:03,  1.34s/it]
 36%|███▌      | 22112/61904 [1:04:00<14:50:24,  1.34s/it]
 36%|███▌      | 22113/61904 [1:04:02<15:00:52,  1.36s/it]
 36%|███▌      | 22114/61904 [1:04:03<15:03:50,  1.36s/it]
 36%|███▌      | 22115/61904 [1:04:04<14:35:38,  1.32s/it]
 36%|███▌      | 22116/61904 [1:04:06<15:23:58,  1.39s/it]
 36%|███▌      | 22117/61904 [1:04:07<14:49:04,  1.34s/it]
 36%|███▌      | 22118/61904 [1:04:08<15:07:09,  1.37s/it]
 36%|███▌      | 22119/61904 [1:04:10<14:47:53,  1.34s/it]
 36%|███▌      | 22120/61904 [1:04:11<14:57:12,  1.35s/it]
                                                          
{'loss': 2.6358, 'learning_rate': 1.6447556074160507e-07, 'epoch': 5.72}

 36%|███▌      | 22120/61904 [1:04:11<14:57:12,  1.35s/it]
 36%|███▌      | 22121/61904 [1:04:12<14:58:42,  1.36s/it]
 36%|███▌      | 22122/61904 [1:04:14<14:55:28,  1.35s/it]
 36%|███▌      | 22123/61904 [1:04:15<14:30:17,  1.31s/it]
 36%|███▌      | 22124/61904 [1:04:16<14:13:40,  1.29s/it]
 36%|███▌      | 22125/61904 [1:04:17<14:11:19,  1.28s/it]
 36%|███▌      | 22126/61904 [1:04:19<14:21:18,  1.30s/it]
 36%|███▌      | 22127/61904 [1:04:20<14:58:23,  1.36s/it]
 36%|███▌      | 22128/61904 [1:04:22<15:15:52,  1.38s/it]
 36%|███▌      | 22129/61904 [1:04:23<14:50:43,  1.34s/it]
 36%|███▌      | 22130/61904 [1:04:24<14:47:31,  1.34s/it]
 36%|███▌      | 22131/61904 [1:04:26<15:29:46,  1.40s/it]
 36%|███▌      | 22132/61904 [1:04:27<15:49:28,  1.43s/it]
 36%|███▌      | 22133/61904 [1:04:29<15:11:07,  1.37s/it]
 36%|███▌      | 22134/61904 [1:04:30<14:59:36,  1.36s/it]
 36%|███▌      | 22135/61904 [1:04:31<15:01:56,  1.36s/it]
 36%|███▌      | 22136/61904 [1:04:33<14:56:07,  1.35s/it]
 36%|███▌      | 22137/61904 [1:04:34<15:25:45,  1.40s/it]
 36%|███▌      | 22138/61904 [1:04:36<15:29:54,  1.40s/it]
 36%|███▌      | 22139/61904 [1:04:37<15:17:27,  1.38s/it]
 36%|███▌      | 22140/61904 [1:04:38<14:48:52,  1.34s/it]
                                                          
{'loss': 2.6962, 'learning_rate': 1.6444314793206274e-07, 'epoch': 5.72}

 36%|███▌      | 22140/61904 [1:04:38<14:48:52,  1.34s/it]
 36%|███▌      | 22141/61904 [1:04:40<14:50:56,  1.34s/it]
 36%|███▌      | 22142/61904 [1:04:41<15:13:40,  1.38s/it]
 36%|███▌      | 22143/61904 [1:04:42<15:32:08,  1.41s/it]
 36%|███▌      | 22144/61904 [1:04:44<15:13:36,  1.38s/it]
 36%|███▌      | 22145/61904 [1:04:45<15:08:44,  1.37s/it]
 36%|███▌      | 22146/61904 [1:04:46<15:12:21,  1.38s/it]
 36%|███▌      | 22147/61904 [1:04:48<15:06:17,  1.37s/it]
 36%|███▌      | 22148/61904 [1:04:49<14:43:51,  1.33s/it]
 36%|███▌      | 22149/61904 [1:04:51<15:19:09,  1.39s/it]
 36%|███▌      | 22150/61904 [1:04:52<15:15:23,  1.38s/it]
 36%|███▌      | 22151/61904 [1:04:53<15:39:15,  1.42s/it]
 36%|███▌      | 22152/61904 [1:04:55<15:15:54,  1.38s/it]
 36%|███▌      | 22153/61904 [1:04:56<15:33:07,  1.41s/it]
 36%|███▌      | 22154/61904 [1:04:58<15:30:27,  1.40s/it]
 36%|███▌      | 22155/61904 [1:04:59<15:45:59,  1.43s/it]
 36%|███▌      | 22156/61904 [1:05:00<15:32:07,  1.41s/it]
 36%|███▌      | 22157/61904 [1:05:02<15:33:10,  1.41s/it]
 36%|███▌      | 22158/61904 [1:05:03<15:50:12,  1.43s/it]
 36%|███▌      | 22159/61904 [1:05:05<15:44:03,  1.43s/it]
 36%|███▌      | 22160/61904 [1:05:06<15:33:00,  1.41s/it]
                                                          
{'loss': 2.6403, 'learning_rate': 1.644107351225204e-07, 'epoch': 5.73}

 36%|███▌      | 22160/61904 [1:05:06<15:33:00,  1.41s/it]
 36%|███▌      | 22161/61904 [1:05:07<15:12:28,  1.38s/it]
 36%|███▌      | 22162/61904 [1:05:09<15:01:45,  1.36s/it]
 36%|███▌      | 22163/61904 [1:05:10<14:52:07,  1.35s/it]
 36%|███▌      | 22164/61904 [1:05:11<14:28:34,  1.31s/it]
 36%|███▌      | 22165/61904 [1:05:13<14:33:41,  1.32s/it]
 36%|███▌      | 22166/61904 [1:05:14<15:09:00,  1.37s/it]
 36%|███▌      | 22167/61904 [1:05:16<15:24:04,  1.40s/it]
 36%|███▌      | 22168/61904 [1:05:17<15:19:51,  1.39s/it]
 36%|███▌      | 22169/61904 [1:05:18<15:08:53,  1.37s/it]
 36%|███▌      | 22170/61904 [1:05:20<15:06:41,  1.37s/it]
 36%|███▌      | 22171/61904 [1:05:21<15:18:59,  1.39s/it]
 36%|███▌      | 22172/61904 [1:05:22<14:54:24,  1.35s/it]
 36%|███▌      | 22173/61904 [1:05:24<14:41:19,  1.33s/it]
 36%|███▌      | 22174/61904 [1:05:25<15:07:13,  1.37s/it]
 36%|███▌      | 22175/61904 [1:05:27<15:10:53,  1.38s/it]
 36%|███▌      | 22176/61904 [1:05:28<15:22:08,  1.39s/it]
 36%|███▌      | 22177/61904 [1:05:29<15:25:31,  1.40s/it]
 36%|███▌      | 22178/61904 [1:05:31<15:37:50,  1.42s/it]
 36%|███▌      | 22179/61904 [1:05:32<15:27:32,  1.40s/it]
 36%|███▌      | 22180/61904 [1:05:34<15:21:35,  1.39s/it]
                                                          
{'loss': 2.641, 'learning_rate': 1.6437832231297809e-07, 'epoch': 5.73}

 36%|███▌      | 22180/61904 [1:05:34<15:21:35,  1.39s/it]
 36%|███▌      | 22181/61904 [1:05:35<15:24:09,  1.40s/it]
 36%|███▌      | 22182/61904 [1:05:36<15:07:54,  1.37s/it]
 36%|███▌      | 22183/61904 [1:05:38<14:45:44,  1.34s/it]
 36%|███▌      | 22184/61904 [1:05:39<14:11:48,  1.29s/it]
 36%|███▌      | 22185/61904 [1:05:40<14:45:28,  1.34s/it]
 36%|███▌      | 22186/61904 [1:05:41<14:33:06,  1.32s/it]
 36%|███▌      | 22187/61904 [1:05:43<14:40:29,  1.33s/it]
 36%|███▌      | 22188/61904 [1:05:44<15:06:06,  1.37s/it]
 36%|███▌      | 22189/61904 [1:05:46<14:43:22,  1.33s/it]
 36%|███▌      | 22190/61904 [1:05:47<14:56:01,  1.35s/it]
 36%|███▌      | 22191/61904 [1:05:48<14:39:25,  1.33s/it]
 36%|███▌      | 22192/61904 [1:05:50<15:00:57,  1.36s/it]
 36%|███▌      | 22193/61904 [1:05:51<14:49:15,  1.34s/it]
 36%|███▌      | 22194/61904 [1:05:52<15:07:15,  1.37s/it]
 36%|███▌      | 22195/61904 [1:05:54<14:52:11,  1.35s/it]
 36%|███▌      | 22196/61904 [1:05:55<15:10:56,  1.38s/it]
 36%|███▌      | 22197/61904 [1:05:56<15:14:12,  1.38s/it]
 36%|███▌      | 22198/61904 [1:05:58<15:07:00,  1.37s/it]
 36%|███▌      | 22199/61904 [1:05:59<15:21:00,  1.39s/it]
 36%|███▌      | 22200/61904 [1:06:01<15:24:28,  1.40s/it]
                                                          
{'loss': 2.6213, 'learning_rate': 1.6434590950343575e-07, 'epoch': 5.74}

 36%|███▌      | 22200/61904 [1:06:01<15:24:28,  1.40s/it]
 36%|███▌      | 22201/61904 [1:06:02<15:36:29,  1.42s/it]
 36%|███▌      | 22202/61904 [1:06:03<15:20:12,  1.39s/it]
 36%|███▌      | 22203/61904 [1:06:05<15:35:07,  1.41s/it]
 36%|███▌      | 22204/61904 [1:06:06<14:57:37,  1.36s/it]
 36%|███▌      | 22205/61904 [1:06:08<15:12:15,  1.38s/it]
 36%|███▌      | 22206/61904 [1:06:09<15:02:57,  1.36s/it]
 36%|███▌      | 22207/61904 [1:06:10<14:48:33,  1.34s/it]
 36%|███▌      | 22208/61904 [1:06:12<14:39:29,  1.33s/it]
 36%|███▌      | 22209/61904 [1:06:13<15:03:08,  1.37s/it]
 36%|███▌      | 22210/61904 [1:06:14<15:17:49,  1.39s/it]
 36%|███▌      | 22211/61904 [1:06:16<15:31:40,  1.41s/it]
 36%|███▌      | 22212/61904 [1:06:17<15:17:30,  1.39s/it]
 36%|███▌      | 22213/61904 [1:06:19<15:06:39,  1.37s/it]
 36%|███▌      | 22214/61904 [1:06:20<15:04:30,  1.37s/it]
 36%|███▌      | 22215/61904 [1:06:21<14:58:32,  1.36s/it]
 36%|███▌      | 22216/61904 [1:06:23<14:45:24,  1.34s/it]
 36%|███▌      | 22217/61904 [1:06:24<14:33:32,  1.32s/it]
 36%|███▌      | 22218/61904 [1:06:25<14:46:39,  1.34s/it]
 36%|███▌      | 22219/61904 [1:06:27<14:57:52,  1.36s/it]
 36%|███▌      | 22220/61904 [1:06:28<15:02:38,  1.36s/it]
                                                          
{'loss': 2.6508, 'learning_rate': 1.643134966938934e-07, 'epoch': 5.74}

 36%|███▌      | 22220/61904 [1:06:28<15:02:38,  1.36s/it]
 36%|███▌      | 22221/61904 [1:06:29<15:17:45,  1.39s/it]
 36%|███▌      | 22222/61904 [1:06:31<15:06:39,  1.37s/it]
 36%|███▌      | 22223/61904 [1:06:32<14:56:22,  1.36s/it]
 36%|███▌      | 22224/61904 [1:06:33<15:03:17,  1.37s/it]
 36%|███▌      | 22225/61904 [1:06:35<15:41:04,  1.42s/it]
 36%|███▌      | 22226/61904 [1:06:36<15:16:01,  1.39s/it]
 36%|███▌      | 22227/61904 [1:06:38<15:27:57,  1.40s/it]
 36%|███▌      | 22228/61904 [1:06:39<15:15:43,  1.38s/it]
 36%|███▌      | 22229/61904 [1:06:40<14:39:44,  1.33s/it]
 36%|███▌      | 22230/61904 [1:06:42<14:56:05,  1.36s/it]
 36%|███▌      | 22231/61904 [1:06:43<14:57:22,  1.36s/it]
 36%|███▌      | 22232/61904 [1:06:44<14:46:43,  1.34s/it]
 36%|███▌      | 22233/61904 [1:06:46<14:57:10,  1.36s/it]
 36%|███▌      | 22234/61904 [1:06:47<14:46:07,  1.34s/it]
 36%|███▌      | 22235/61904 [1:06:48<14:36:50,  1.33s/it]
 36%|███▌      | 22236/61904 [1:06:50<14:47:30,  1.34s/it]
 36%|███▌      | 22237/61904 [1:06:51<15:00:03,  1.36s/it]
 36%|███▌      | 22238/61904 [1:06:53<15:08:18,  1.37s/it]
 36%|███▌      | 22239/61904 [1:06:54<14:44:28,  1.34s/it]
 36%|███▌      | 22240/61904 [1:06:55<14:42:12,  1.33s/it]
                                                          
{'loss': 2.6528, 'learning_rate': 1.642810838843511e-07, 'epoch': 5.75}

 36%|███▌      | 22240/61904 [1:06:55<14:42:12,  1.33s/it]
 36%|███▌      | 22241/61904 [1:06:57<15:18:12,  1.39s/it]
 36%|███▌      | 22242/61904 [1:06:58<15:15:28,  1.38s/it]
 36%|███▌      | 22243/61904 [1:07:00<15:44:52,  1.43s/it]
 36%|███▌      | 22244/61904 [1:07:01<15:16:59,  1.39s/it]
 36%|███▌      | 22245/61904 [1:07:02<15:15:12,  1.38s/it]
 36%|███▌      | 22246/61904 [1:07:04<15:25:52,  1.40s/it]
 36%|███▌      | 22247/61904 [1:07:05<15:31:07,  1.41s/it]
 36%|███▌      | 22248/61904 [1:07:06<15:09:29,  1.38s/it]
 36%|███▌      | 22249/61904 [1:07:08<14:46:54,  1.34s/it]
 36%|███▌      | 22250/61904 [1:07:09<14:57:59,  1.36s/it]
 36%|███▌      | 22251/61904 [1:07:10<14:31:04,  1.32s/it]
 36%|███▌      | 22252/61904 [1:07:12<14:53:09,  1.35s/it]
 36%|███▌      | 22253/61904 [1:07:13<15:03:46,  1.37s/it]
 36%|███▌      | 22254/61904 [1:07:14<14:58:03,  1.36s/it]
 36%|███▌      | 22255/61904 [1:07:16<14:53:48,  1.35s/it]
 36%|███▌      | 22256/61904 [1:07:17<14:57:14,  1.36s/it]
 36%|███▌      | 22257/61904 [1:07:18<14:47:02,  1.34s/it]
 36%|███▌      | 22258/61904 [1:07:20<14:39:12,  1.33s/it]
 36%|███▌      | 22259/61904 [1:07:21<14:22:56,  1.31s/it]
 36%|███▌      | 22260/61904 [1:07:23<15:03:14,  1.37s/it]
                                                          
{'loss': 2.5921, 'learning_rate': 1.6424867107480873e-07, 'epoch': 5.75}

 36%|███▌      | 22260/61904 [1:07:23<15:03:14,  1.37s/it]
 36%|███▌      | 22261/61904 [1:07:24<14:55:02,  1.35s/it]
 36%|███▌      | 22262/61904 [1:07:25<15:04:41,  1.37s/it]
 36%|███▌      | 22263/61904 [1:07:27<15:15:29,  1.39s/it]
 36%|███▌      | 22264/61904 [1:07:28<15:05:51,  1.37s/it]
 36%|███▌      | 22265/61904 [1:07:29<14:53:37,  1.35s/it]
 36%|███▌      | 22266/61904 [1:07:31<15:05:23,  1.37s/it]
 36%|███▌      | 22267/61904 [1:07:32<14:46:38,  1.34s/it]
 36%|███▌      | 22268/61904 [1:07:33<15:06:13,  1.37s/it]
 36%|███▌      | 22269/61904 [1:07:35<15:31:13,  1.41s/it]
 36%|███▌      | 22270/61904 [1:07:36<15:20:37,  1.39s/it]
 36%|███▌      | 22271/61904 [1:07:38<14:55:33,  1.36s/it]
 36%|███▌      | 22272/61904 [1:07:39<15:03:55,  1.37s/it]
 36%|███▌      | 22273/61904 [1:07:40<15:04:39,  1.37s/it]
 36%|███▌      | 22274/61904 [1:07:42<15:13:36,  1.38s/it]
 36%|███▌      | 22275/61904 [1:07:43<14:49:02,  1.35s/it]
 36%|███▌      | 22276/61904 [1:07:44<14:39:24,  1.33s/it]
 36%|███▌      | 22277/61904 [1:07:46<14:52:48,  1.35s/it]
 36%|███▌      | 22278/61904 [1:07:47<14:33:01,  1.32s/it]
 36%|███▌      | 22279/61904 [1:07:48<15:06:08,  1.37s/it]
 36%|███▌      | 22280/61904 [1:07:50<14:58:45,  1.36s/it]
                                                          
{'loss': 2.6379, 'learning_rate': 1.6421625826526642e-07, 'epoch': 5.76}

 36%|███▌      | 22280/61904 [1:07:50<14:58:45,  1.36s/it]
 36%|███▌      | 22281/61904 [1:07:51<15:52:30,  1.44s/it]
 36%|███▌      | 22282/61904 [1:07:53<15:24:58,  1.40s/it]
 36%|███▌      | 22283/61904 [1:07:54<15:53:00,  1.44s/it]
 36%|███▌      | 22284/61904 [1:07:56<15:25:39,  1.40s/it]
 36%|███▌      | 22285/61904 [1:07:57<14:58:41,  1.36s/it]
 36%|███▌      | 22286/61904 [1:07:58<14:54:15,  1.35s/it]
 36%|███▌      | 22287/61904 [1:08:00<15:04:29,  1.37s/it]
 36%|███▌      | 22288/61904 [1:08:01<15:43:07,  1.43s/it]
 36%|███▌      | 22289/61904 [1:08:02<15:28:29,  1.41s/it]
 36%|███▌      | 22290/61904 [1:08:04<15:12:42,  1.38s/it]
 36%|███▌      | 22291/61904 [1:08:05<15:01:14,  1.37s/it]
 36%|███▌      | 22292/61904 [1:08:07<15:26:45,  1.40s/it]
 36%|███▌      | 22293/61904 [1:08:08<16:05:44,  1.46s/it]
 36%|███▌      | 22294/61904 [1:08:10<16:10:19,  1.47s/it]
 36%|███▌      | 22295/61904 [1:08:11<15:49:16,  1.44s/it]
 36%|███▌      | 22296/61904 [1:08:12<15:30:15,  1.41s/it]
 36%|███▌      | 22297/61904 [1:08:14<15:21:44,  1.40s/it]
 36%|███▌      | 22298/61904 [1:08:15<15:14:34,  1.39s/it]
 36%|███▌      | 22299/61904 [1:08:16<14:46:09,  1.34s/it]
 36%|███▌      | 22300/61904 [1:08:18<15:11:01,  1.38s/it]
                                                          
{'loss': 2.6838, 'learning_rate': 1.641838454557241e-07, 'epoch': 5.76}

 36%|███▌      | 22300/61904 [1:08:18<15:11:01,  1.38s/it]
 36%|███▌      | 22301/61904 [1:08:19<14:42:43,  1.34s/it]
 36%|███▌      | 22302/61904 [1:08:20<14:34:36,  1.33s/it]
 36%|███▌      | 22303/61904 [1:08:22<14:18:03,  1.30s/it]
 36%|███▌      | 22304/61904 [1:08:23<14:27:45,  1.31s/it]
 36%|███▌      | 22305/61904 [1:08:24<14:40:27,  1.33s/it]
 36%|███▌      | 22306/61904 [1:08:26<14:56:17,  1.36s/it]
 36%|███▌      | 22307/61904 [1:08:27<14:30:05,  1.32s/it]
 36%|███▌      | 22308/61904 [1:08:28<14:57:27,  1.36s/it]
 36%|███▌      | 22309/61904 [1:08:30<14:42:27,  1.34s/it]
 36%|███▌      | 22310/61904 [1:08:31<14:56:18,  1.36s/it]
 36%|███▌      | 22311/61904 [1:08:33<14:58:27,  1.36s/it]
 36%|███▌      | 22312/61904 [1:08:34<15:25:54,  1.40s/it]
 36%|███▌      | 22313/61904 [1:08:35<15:34:56,  1.42s/it]
 36%|███▌      | 22314/61904 [1:08:37<15:41:54,  1.43s/it]
 36%|███▌      | 22315/61904 [1:08:38<15:19:39,  1.39s/it]
 36%|███▌      | 22316/61904 [1:08:39<14:48:00,  1.35s/it]
 36%|███▌      | 22317/61904 [1:08:41<14:57:59,  1.36s/it]
 36%|███▌      | 22318/61904 [1:08:42<14:55:23,  1.36s/it]
 36%|███▌      | 22319/61904 [1:08:44<14:43:30,  1.34s/it]
 36%|███▌      | 22320/61904 [1:08:45<15:03:48,  1.37s/it]
                                                          
{'loss': 2.6511, 'learning_rate': 1.6415143264618175e-07, 'epoch': 5.77}

 36%|███▌      | 22320/61904 [1:08:45<15:03:48,  1.37s/it]
 36%|███▌      | 22321/61904 [1:08:46<15:03:51,  1.37s/it]
 36%|███▌      | 22322/61904 [1:08:48<15:12:46,  1.38s/it]
 36%|███▌      | 22323/61904 [1:08:49<14:53:14,  1.35s/it]
 36%|███▌      | 22324/61904 [1:08:50<15:02:16,  1.37s/it]
 36%|███▌      | 22325/61904 [1:08:52<14:58:06,  1.36s/it]
 36%|███▌      | 22326/61904 [1:08:53<15:04:46,  1.37s/it]
 36%|███▌      | 22327/61904 [1:08:55<15:19:10,  1.39s/it]
 36%|███▌      | 22328/61904 [1:08:56<14:44:59,  1.34s/it]
 36%|███▌      | 22329/61904 [1:08:57<14:51:16,  1.35s/it]
 36%|███▌      | 22330/61904 [1:08:59<14:54:03,  1.36s/it]
 36%|███▌      | 22331/61904 [1:09:00<14:51:35,  1.35s/it]
 36%|███▌      | 22332/61904 [1:09:01<14:38:16,  1.33s/it]
 36%|███▌      | 22333/61904 [1:09:03<15:04:01,  1.37s/it]
 36%|███▌      | 22334/61904 [1:09:04<15:01:00,  1.37s/it]
 36%|███▌      | 22335/61904 [1:09:05<14:49:51,  1.35s/it]
 36%|███▌      | 22336/61904 [1:09:07<14:56:31,  1.36s/it]
 36%|███▌      | 22337/61904 [1:09:08<14:55:18,  1.36s/it]
 36%|███▌      | 22338/61904 [1:09:09<14:40:05,  1.33s/it]
 36%|███▌      | 22339/61904 [1:09:11<14:58:59,  1.36s/it]
 36%|███▌      | 22340/61904 [1:09:12<15:10:35,  1.38s/it]
                                                          
{'loss': 2.6547, 'learning_rate': 1.6411901983663943e-07, 'epoch': 5.77}

 36%|███▌      | 22340/61904 [1:09:12<15:10:35,  1.38s/it]
 36%|███▌      | 22341/61904 [1:09:14<15:21:04,  1.40s/it]
 36%|███▌      | 22342/61904 [1:09:15<15:37:54,  1.42s/it]
 36%|███▌      | 22343/61904 [1:09:17<15:44:26,  1.43s/it]
 36%|███▌      | 22344/61904 [1:09:18<15:19:18,  1.39s/it]
 36%|███▌      | 22345/61904 [1:09:19<15:32:56,  1.42s/it]
 36%|███▌      | 22346/61904 [1:09:21<15:24:04,  1.40s/it]
 36%|███▌      | 22347/61904 [1:09:22<15:23:24,  1.40s/it]
 36%|███▌      | 22348/61904 [1:09:23<15:05:03,  1.37s/it]
 36%|███▌      | 22349/61904 [1:09:25<15:27:06,  1.41s/it]
 36%|███▌      | 22350/61904 [1:09:26<15:41:12,  1.43s/it]
 36%|███▌      | 22351/61904 [1:09:28<15:17:53,  1.39s/it]
 36%|███▌      | 22352/61904 [1:09:29<15:23:09,  1.40s/it]
 36%|███▌      | 22353/61904 [1:09:31<15:31:38,  1.41s/it]
 36%|███▌      | 22354/61904 [1:09:32<15:27:13,  1.41s/it]
 36%|███▌      | 22355/61904 [1:09:33<15:06:30,  1.38s/it]
 36%|███▌      | 22356/61904 [1:09:35<15:27:00,  1.41s/it]
 36%|███▌      | 22357/61904 [1:09:36<15:27:19,  1.41s/it]
 36%|███▌      | 22358/61904 [1:09:37<15:17:37,  1.39s/it]
 36%|███▌      | 22359/61904 [1:09:39<15:16:58,  1.39s/it]
 36%|███▌      | 22360/61904 [1:09:40<15:01:27,  1.37s/it]
                                                          
{'loss': 2.5962, 'learning_rate': 1.640866070270971e-07, 'epoch': 5.78}

 36%|███▌      | 22360/61904 [1:09:40<15:01:27,  1.37s/it]
 36%|███▌      | 22361/61904 [1:09:42<14:49:18,  1.35s/it]
 36%|███▌      | 22362/61904 [1:09:43<15:18:42,  1.39s/it]
 36%|███▌      | 22363/61904 [1:09:44<14:54:42,  1.36s/it]
 36%|███▌      | 22364/61904 [1:09:46<15:08:37,  1.38s/it]
 36%|███▌      | 22365/61904 [1:09:47<15:10:21,  1.38s/it]
 36%|███▌      | 22366/61904 [1:09:48<15:05:01,  1.37s/it]
 36%|███▌      | 22367/61904 [1:09:50<14:54:19,  1.36s/it]
 36%|███▌      | 22368/61904 [1:09:51<14:47:34,  1.35s/it]
 36%|███▌      | 22369/61904 [1:09:52<14:29:17,  1.32s/it]
 36%|███▌      | 22370/61904 [1:09:54<15:25:55,  1.41s/it]
 36%|███▌      | 22371/61904 [1:09:55<15:31:59,  1.41s/it]
 36%|███▌      | 22372/61904 [1:09:57<15:38:24,  1.42s/it]
 36%|███▌      | 22373/61904 [1:09:58<16:07:17,  1.47s/it]
 36%|███▌      | 22374/61904 [1:10:00<16:17:47,  1.48s/it]
 36%|███▌      | 22375/61904 [1:10:01<16:13:56,  1.48s/it]
 36%|███▌      | 22376/61904 [1:10:03<16:13:36,  1.48s/it]
 36%|███▌      | 22377/61904 [1:10:04<16:05:52,  1.47s/it]
 36%|███▌      | 22378/61904 [1:10:06<15:31:10,  1.41s/it]
 36%|███▌      | 22379/61904 [1:10:07<15:30:25,  1.41s/it]
 36%|███▌      | 22380/61904 [1:10:08<15:35:24,  1.42s/it]
                                                          
{'loss': 2.6074, 'learning_rate': 1.6405419421755476e-07, 'epoch': 5.78}

 36%|███▌      | 22380/61904 [1:10:08<15:35:24,  1.42s/it]
 36%|███▌      | 22381/61904 [1:10:10<15:23:18,  1.40s/it]
 36%|███▌      | 22382/61904 [1:10:11<15:19:33,  1.40s/it]
 36%|███▌      | 22383/61904 [1:10:12<15:01:02,  1.37s/it]
 36%|███▌      | 22384/61904 [1:10:14<15:54:44,  1.45s/it]
 36%|███▌      | 22385/61904 [1:10:16<15:46:53,  1.44s/it]
 36%|███▌      | 22386/61904 [1:10:17<15:12:14,  1.39s/it]
 36%|███▌      | 22387/61904 [1:10:18<15:43:40,  1.43s/it]
 36%|███▌      | 22388/61904 [1:10:20<15:32:49,  1.42s/it]
 36%|███▌      | 22389/61904 [1:10:21<15:27:32,  1.41s/it]
 36%|███▌      | 22390/61904 [1:10:23<15:45:46,  1.44s/it]
 36%|███▌      | 22391/61904 [1:10:24<15:39:34,  1.43s/it]
 36%|███▌      | 22392/61904 [1:10:26<16:00:16,  1.46s/it]
 36%|███▌      | 22393/61904 [1:10:27<16:17:27,  1.48s/it]
 36%|███▌      | 22394/61904 [1:10:29<16:17:47,  1.48s/it]
 36%|███▌      | 22395/61904 [1:10:30<15:53:19,  1.45s/it]
 36%|███▌      | 22396/61904 [1:10:31<15:54:24,  1.45s/it]
 36%|███▌      | 22397/61904 [1:10:33<15:11:34,  1.38s/it]
 36%|███▌      | 22398/61904 [1:10:34<14:53:44,  1.36s/it]
 36%|███▌      | 22399/61904 [1:10:35<14:57:16,  1.36s/it]
 36%|███▌      | 22400/61904 [1:10:37<15:01:59,  1.37s/it]
                                                          
{'loss': 2.5927, 'learning_rate': 1.6402178140801245e-07, 'epoch': 5.79}

 36%|███▌      | 22400/61904 [1:10:37<15:01:59,  1.37s/it]
 36%|███▌      | 22401/61904 [1:10:38<15:24:51,  1.40s/it]
 36%|███▌      | 22402/61904 [1:10:39<15:00:08,  1.37s/it]
 36%|███▌      | 22403/61904 [1:10:41<14:31:07,  1.32s/it]
 36%|███▌      | 22404/61904 [1:10:42<14:38:17,  1.33s/it]
 36%|███▌      | 22405/61904 [1:10:43<14:45:44,  1.35s/it]
 36%|███▌      | 22406/61904 [1:10:45<14:45:05,  1.34s/it]
 36%|███▌      | 22407/61904 [1:10:46<14:45:59,  1.35s/it]
 36%|███▌      | 22408/61904 [1:10:47<14:34:41,  1.33s/it]
 36%|███▌      | 22409/61904 [1:10:49<14:19:25,  1.31s/it]
 36%|███▌      | 22410/61904 [1:10:50<14:22:18,  1.31s/it]
 36%|███▌      | 22411/61904 [1:10:51<14:32:44,  1.33s/it]
 36%|███▌      | 22412/61904 [1:10:53<14:56:01,  1.36s/it]
 36%|███▌      | 22413/61904 [1:10:54<15:07:14,  1.38s/it]
 36%|███▌      | 22414/61904 [1:10:56<14:58:09,  1.36s/it]
 36%|███▌      | 22415/61904 [1:10:57<15:15:02,  1.39s/it]
 36%|███▌      | 22416/61904 [1:10:58<15:10:40,  1.38s/it]
 36%|███▌      | 22417/61904 [1:11:00<14:50:47,  1.35s/it]
 36%|███▌      | 22418/61904 [1:11:01<14:59:38,  1.37s/it]
 36%|███▌      | 22419/61904 [1:11:02<14:52:58,  1.36s/it]
 36%|███▌      | 22420/61904 [1:11:04<15:57:55,  1.46s/it]
                                                          
{'loss': 2.6697, 'learning_rate': 1.6398936859847008e-07, 'epoch': 5.79}

 36%|███▌      | 22420/61904 [1:11:04<15:57:55,  1.46s/it]
 36%|███▌      | 22421/61904 [1:11:05<15:34:36,  1.42s/it]
 36%|███▌      | 22422/61904 [1:11:07<15:24:49,  1.41s/it]
 36%|███▌      | 22423/61904 [1:11:08<14:56:04,  1.36s/it]
 36%|███▌      | 22424/61904 [1:11:09<14:58:42,  1.37s/it]
 36%|███▌      | 22425/61904 [1:11:11<15:34:51,  1.42s/it]
 36%|███▌      | 22426/61904 [1:11:12<15:05:59,  1.38s/it]
 36%|███▌      | 22427/61904 [1:11:14<14:53:06,  1.36s/it]
 36%|███▌      | 22428/61904 [1:11:15<15:06:34,  1.38s/it]
 36%|███▌      | 22429/61904 [1:11:16<15:02:34,  1.37s/it]
 36%|███▌      | 22430/61904 [1:11:18<15:06:31,  1.38s/it]
 36%|███▌      | 22431/61904 [1:11:19<15:16:05,  1.39s/it]
 36%|███▌      | 22432/61904 [1:11:21<15:22:54,  1.40s/it]
 36%|███▌      | 22433/61904 [1:11:22<15:14:15,  1.39s/it]
 36%|███▌      | 22434/61904 [1:11:23<15:04:31,  1.38s/it]
 36%|███▌      | 22435/61904 [1:11:24<14:38:40,  1.34s/it]
 36%|███▌      | 22436/61904 [1:11:26<14:57:24,  1.36s/it]
 36%|███▌      | 22437/61904 [1:11:27<14:57:48,  1.36s/it]
 36%|███▌      | 22438/61904 [1:11:29<14:44:23,  1.34s/it]
 36%|███▌      | 22439/61904 [1:11:30<14:38:31,  1.34s/it]
 36%|███▌      | 22440/61904 [1:11:31<15:07:55,  1.38s/it]
                                                          
{'loss': 2.6267, 'learning_rate': 1.6395695578892777e-07, 'epoch': 5.8}

 36%|███▌      | 22440/61904 [1:11:31<15:07:55,  1.38s/it]
 36%|███▋      | 22441/61904 [1:11:33<14:46:05,  1.35s/it]
 36%|███▋      | 22442/61904 [1:11:34<15:00:26,  1.37s/it]
 36%|███▋      | 22443/61904 [1:11:35<14:59:00,  1.37s/it]
 36%|███▋      | 22444/61904 [1:11:37<15:18:37,  1.40s/it]
 36%|███▋      | 22445/61904 [1:11:39<16:06:03,  1.47s/it]
 36%|███▋      | 22446/61904 [1:11:40<15:44:17,  1.44s/it]
 36%|███▋      | 22447/61904 [1:11:41<15:17:30,  1.40s/it]
 36%|███▋      | 22448/61904 [1:11:43<15:49:52,  1.44s/it]
 36%|███▋      | 22449/61904 [1:11:44<15:27:36,  1.41s/it]
 36%|███▋      | 22450/61904 [1:11:46<15:46:22,  1.44s/it]
 36%|███▋      | 22451/61904 [1:11:47<15:39:37,  1.43s/it]
 36%|███▋      | 22452/61904 [1:11:48<15:33:30,  1.42s/it]
 36%|███▋      | 22453/61904 [1:11:50<15:18:29,  1.40s/it]
 36%|███▋      | 22454/61904 [1:11:51<14:59:28,  1.37s/it]
 36%|███▋      | 22455/61904 [1:11:52<15:09:15,  1.38s/it]
 36%|███▋      | 22456/61904 [1:11:54<14:54:03,  1.36s/it]
 36%|███▋      | 22457/61904 [1:11:55<15:17:15,  1.40s/it]
 36%|███▋      | 22458/61904 [1:11:57<15:27:56,  1.41s/it]
 36%|███▋      | 22459/61904 [1:11:58<15:34:07,  1.42s/it]
 36%|███▋      | 22460/61904 [1:11:59<15:08:57,  1.38s/it]
                                                          
{'loss': 2.6833, 'learning_rate': 1.6392454297938546e-07, 'epoch': 5.81}

 36%|███▋      | 22460/61904 [1:11:59<15:08:57,  1.38s/it]
 36%|███▋      | 22461/61904 [1:12:01<15:36:51,  1.43s/it]
 36%|███▋      | 22462/61904 [1:12:02<15:37:06,  1.43s/it]
 36%|███▋      | 22463/61904 [1:12:04<15:57:18,  1.46s/it]
 36%|███▋      | 22464/61904 [1:12:05<15:28:32,  1.41s/it]
 36%|███▋      | 22465/61904 [1:12:07<15:38:12,  1.43s/it]
 36%|███▋      | 22466/61904 [1:12:08<16:55:37,  1.55s/it]
 36%|███▋      | 22467/61904 [1:12:10<16:45:26,  1.53s/it]
 36%|███▋      | 22468/61904 [1:12:11<16:22:59,  1.50s/it]
 36%|███▋      | 22469/61904 [1:12:13<15:48:50,  1.44s/it]
 36%|███▋      | 22470/61904 [1:12:14<15:48:49,  1.44s/it]
 36%|███▋      | 22471/61904 [1:12:16<15:58:19,  1.46s/it]
 36%|███▋      | 22472/61904 [1:12:17<15:44:11,  1.44s/it]
 36%|███▋      | 22473/61904 [1:12:19<15:50:37,  1.45s/it]
 36%|███▋      | 22474/61904 [1:12:20<16:00:27,  1.46s/it]
 36%|███▋      | 22475/61904 [1:12:21<15:37:58,  1.43s/it]
 36%|███▋      | 22476/61904 [1:12:23<15:15:59,  1.39s/it]
 36%|███▋      | 22477/61904 [1:12:24<14:56:11,  1.36s/it]
 36%|███▋      | 22478/61904 [1:12:25<14:58:28,  1.37s/it]
 36%|███▋      | 22479/61904 [1:12:27<14:35:03,  1.33s/it]
 36%|███▋      | 22480/61904 [1:12:28<14:37:17,  1.34s/it]
                                                          
{'loss': 2.6647, 'learning_rate': 1.638921301698431e-07, 'epoch': 5.81}

 36%|███▋      | 22480/61904 [1:12:28<14:37:17,  1.34s/it]
 36%|███▋      | 22481/61904 [1:12:29<14:57:32,  1.37s/it]
 36%|███▋      | 22482/61904 [1:12:31<15:39:50,  1.43s/it]
 36%|███▋      | 22483/61904 [1:12:32<15:21:30,  1.40s/it]
 36%|███▋      | 22484/61904 [1:12:34<15:06:11,  1.38s/it]
 36%|███▋      | 22485/61904 [1:12:35<14:46:52,  1.35s/it]
 36%|███▋      | 22486/61904 [1:12:36<14:30:30,  1.33s/it]
 36%|███▋      | 22487/61904 [1:12:38<15:05:47,  1.38s/it]
 36%|███▋      | 22488/61904 [1:12:39<14:43:33,  1.34s/it]
 36%|███▋      | 22489/61904 [1:12:40<15:09:47,  1.38s/it]
 36%|███▋      | 22490/61904 [1:12:42<15:24:02,  1.41s/it]
 36%|███▋      | 22491/61904 [1:12:43<15:56:17,  1.46s/it]
 36%|███▋      | 22492/61904 [1:12:45<15:59:12,  1.46s/it]
 36%|███▋      | 22493/61904 [1:12:46<15:59:01,  1.46s/it]
 36%|███▋      | 22494/61904 [1:12:48<15:30:08,  1.42s/it]
 36%|███▋      | 22495/61904 [1:12:49<15:38:29,  1.43s/it]
 36%|███▋      | 22496/61904 [1:12:51<15:25:06,  1.41s/it]
 36%|███▋      | 22497/61904 [1:12:52<14:57:01,  1.37s/it]
 36%|███▋      | 22498/61904 [1:12:53<14:55:57,  1.36s/it]
 36%|███▋      | 22499/61904 [1:12:55<15:17:52,  1.40s/it]
 36%|███▋      | 22500/61904 [1:12:56<15:08:51,  1.38s/it]
                                                          
{'loss': 2.6619, 'learning_rate': 1.6385971736030078e-07, 'epoch': 5.82}

 36%|███▋      | 22500/61904 [1:12:56<15:08:51,  1.38s/it]
 36%|███▋      | 22501/61904 [1:12:57<15:08:58,  1.38s/it]
 36%|███▋      | 22502/61904 [1:12:59<15:12:59,  1.39s/it]
 36%|███▋      | 22503/61904 [1:13:00<15:13:17,  1.39s/it]
 36%|███▋      | 22504/61904 [1:13:01<15:00:41,  1.37s/it]
 36%|███▋      | 22505/61904 [1:13:03<14:49:49,  1.36s/it]
 36%|███▋      | 22506/61904 [1:13:04<14:51:51,  1.36s/it]
 36%|███▋      | 22507/61904 [1:13:05<14:45:31,  1.35s/it]
 36%|███▋      | 22508/61904 [1:13:07<14:53:46,  1.36s/it]
 36%|███▋      | 22509/61904 [1:13:08<14:51:19,  1.36s/it]
 36%|███▋      | 22510/61904 [1:13:10<15:28:38,  1.41s/it]
 36%|███▋      | 22511/61904 [1:13:11<15:26:10,  1.41s/it]
 36%|███▋      | 22512/61904 [1:13:13<15:37:57,  1.43s/it]
 36%|███▋      | 22513/61904 [1:13:14<15:29:45,  1.42s/it]
 36%|███▋      | 22514/61904 [1:13:15<15:16:25,  1.40s/it]
 36%|███▋      | 22515/61904 [1:13:17<15:37:51,  1.43s/it]
 36%|███▋      | 22516/61904 [1:13:18<15:08:40,  1.38s/it]
 36%|███▋      | 22517/61904 [1:13:19<14:59:11,  1.37s/it]
 36%|███▋      | 22518/61904 [1:13:21<14:51:40,  1.36s/it]
 36%|███▋      | 22519/61904 [1:13:22<14:40:28,  1.34s/it]
 36%|███▋      | 22520/61904 [1:13:23<14:28:54,  1.32s/it]
                                                          
{'loss': 2.6341, 'learning_rate': 1.6382730455075847e-07, 'epoch': 5.82}

 36%|███▋      | 22520/61904 [1:13:23<14:28:54,  1.32s/it]
 36%|███▋      | 22521/61904 [1:13:25<14:59:36,  1.37s/it]
 36%|███▋      | 22522/61904 [1:13:26<14:50:42,  1.36s/it]
 36%|███▋      | 22523/61904 [1:13:28<14:40:44,  1.34s/it]
 36%|███▋      | 22524/61904 [1:13:29<15:02:54,  1.38s/it]
 36%|███▋      | 22525/61904 [1:13:30<15:10:17,  1.39s/it]
 36%|███▋      | 22526/61904 [1:13:32<15:27:06,  1.41s/it]
 36%|███▋      | 22527/61904 [1:13:33<15:18:11,  1.40s/it]
 36%|███▋      | 22528/61904 [1:13:35<15:05:58,  1.38s/it]
 36%|███▋      | 22529/61904 [1:13:36<14:53:41,  1.36s/it]
 36%|███▋      | 22530/61904 [1:13:37<14:27:42,  1.32s/it]
 36%|███▋      | 22531/61904 [1:13:38<14:39:59,  1.34s/it]
 36%|███▋      | 22532/61904 [1:13:40<14:54:03,  1.36s/it]
 36%|███▋      | 22533/61904 [1:13:41<14:49:27,  1.36s/it]
 36%|███▋      | 22534/61904 [1:13:43<14:45:11,  1.35s/it]
 36%|███▋      | 22535/61904 [1:13:44<15:06:28,  1.38s/it]
 36%|███▋      | 22536/61904 [1:13:45<14:54:33,  1.36s/it]
 36%|███▋      | 22537/61904 [1:13:47<15:08:26,  1.38s/it]
 36%|███▋      | 22538/61904 [1:13:48<15:11:08,  1.39s/it]
 36%|███▋      | 22539/61904 [1:13:50<15:32:06,  1.42s/it]
 36%|███▋      | 22540/61904 [1:13:51<15:15:04,  1.39s/it]
                                                          
{'loss': 2.604, 'learning_rate': 1.637948917412161e-07, 'epoch': 5.83}

 36%|███▋      | 22540/61904 [1:13:51<15:15:04,  1.39s/it]
 36%|███▋      | 22541/61904 [1:13:52<15:18:36,  1.40s/it]
 36%|███▋      | 22542/61904 [1:13:54<14:54:47,  1.36s/it]
 36%|███▋      | 22543/61904 [1:13:55<14:47:21,  1.35s/it]
 36%|███▋      | 22544/61904 [1:13:56<14:50:51,  1.36s/it]
 36%|███▋      | 22545/61904 [1:13:58<14:58:52,  1.37s/it]
 36%|███▋      | 22546/61904 [1:13:59<14:52:17,  1.36s/it]
 36%|███▋      | 22547/61904 [1:14:01<14:54:20,  1.36s/it]
 36%|███▋      | 22548/61904 [1:14:02<15:16:58,  1.40s/it]
 36%|███▋      | 22549/61904 [1:14:03<15:18:35,  1.40s/it]
 36%|███▋      | 22550/61904 [1:14:05<15:08:23,  1.38s/it]
 36%|███▋      | 22551/61904 [1:14:06<15:12:00,  1.39s/it]
 36%|███▋      | 22552/61904 [1:14:08<15:14:46,  1.39s/it]
 36%|███▋      | 22553/61904 [1:14:09<15:12:18,  1.39s/it]
 36%|███▋      | 22554/61904 [1:14:10<15:08:35,  1.39s/it]
 36%|███▋      | 22555/61904 [1:14:12<14:54:11,  1.36s/it]
 36%|███▋      | 22556/61904 [1:14:13<14:53:47,  1.36s/it]
 36%|███▋      | 22557/61904 [1:14:14<14:54:44,  1.36s/it]
 36%|███▋      | 22558/61904 [1:14:16<14:58:33,  1.37s/it]
 36%|███▋      | 22559/61904 [1:14:17<14:45:15,  1.35s/it]
 36%|███▋      | 22560/61904 [1:14:18<15:01:07,  1.37s/it]
                                                          
{'loss': 2.6344, 'learning_rate': 1.637624789316738e-07, 'epoch': 5.83}

 36%|███▋      | 22560/61904 [1:14:18<15:01:07,  1.37s/it]
 36%|███▋      | 22561/61904 [1:14:20<15:47:57,  1.45s/it]
 36%|███▋      | 22562/61904 [1:14:21<15:32:15,  1.42s/it]
 36%|███▋      | 22563/61904 [1:14:23<15:38:28,  1.43s/it]
 36%|███▋      | 22564/61904 [1:14:24<15:15:39,  1.40s/it]
 36%|███▋      | 22565/61904 [1:14:26<15:01:02,  1.37s/it]
 36%|███▋      | 22566/61904 [1:14:27<15:49:40,  1.45s/it]
 36%|███▋      | 22567/61904 [1:14:29<15:33:48,  1.42s/it]
 36%|███▋      | 22568/61904 [1:14:30<15:48:47,  1.45s/it]
 36%|███▋      | 22569/61904 [1:14:31<15:42:27,  1.44s/it]
 36%|███▋      | 22570/61904 [1:14:33<15:40:49,  1.44s/it]
 36%|███▋      | 22571/61904 [1:14:34<15:47:05,  1.44s/it]
 36%|███▋      | 22572/61904 [1:14:36<15:54:51,  1.46s/it]
 36%|███▋      | 22573/61904 [1:14:37<15:54:33,  1.46s/it]
 36%|███▋      | 22574/61904 [1:14:39<16:04:57,  1.47s/it]
 36%|███▋      | 22575/61904 [1:14:40<15:41:20,  1.44s/it]
 36%|███▋      | 22576/61904 [1:14:42<15:44:07,  1.44s/it]
 36%|███▋      | 22577/61904 [1:14:43<15:49:11,  1.45s/it]
 36%|███▋      | 22578/61904 [1:14:45<16:11:43,  1.48s/it]
 36%|███▋      | 22579/61904 [1:14:46<15:40:41,  1.44s/it]
 36%|███▋      | 22580/61904 [1:14:47<15:28:52,  1.42s/it]
                                                          
{'loss': 2.6453, 'learning_rate': 1.6373006612213146e-07, 'epoch': 5.84}

 36%|███▋      | 22580/61904 [1:14:47<15:28:52,  1.42s/it]
 36%|███▋      | 22581/61904 [1:14:49<15:15:30,  1.40s/it]
 36%|███▋      | 22582/61904 [1:14:50<14:46:06,  1.35s/it]
 36%|███▋      | 22583/61904 [1:14:51<14:29:26,  1.33s/it]
 36%|███▋      | 22584/61904 [1:14:53<15:27:01,  1.41s/it]
 36%|███▋      | 22585/61904 [1:14:54<15:11:23,  1.39s/it]
 36%|███▋      | 22586/61904 [1:14:55<14:48:48,  1.36s/it]
 36%|███▋      | 22587/61904 [1:14:57<14:30:12,  1.33s/it]
 36%|███▋      | 22588/61904 [1:14:58<14:40:31,  1.34s/it]
 36%|███▋      | 22589/61904 [1:15:00<15:11:48,  1.39s/it]
 36%|███▋      | 22590/61904 [1:15:01<15:09:11,  1.39s/it]
 36%|███▋      | 22591/61904 [1:15:02<15:24:06,  1.41s/it]
 36%|███▋      | 22592/61904 [1:15:04<15:25:03,  1.41s/it]
 36%|███▋      | 22593/61904 [1:15:05<15:18:32,  1.40s/it]
 36%|███▋      | 22594/61904 [1:15:07<15:34:54,  1.43s/it]
 37%|███▋      | 22595/61904 [1:15:08<15:36:12,  1.43s/it]
 37%|███▋      | 22596/61904 [1:15:09<15:07:28,  1.39s/it]
 37%|███▋      | 22597/61904 [1:15:11<14:49:58,  1.36s/it]
 37%|███▋      | 22598/61904 [1:15:12<14:38:07,  1.34s/it]
 37%|███▋      | 22599/61904 [1:15:13<14:49:35,  1.36s/it]
 37%|███▋      | 22600/61904 [1:15:15<15:21:52,  1.41s/it]
                                                          
{'loss': 2.6433, 'learning_rate': 1.6369765331258912e-07, 'epoch': 5.84}

 37%|███▋      | 22600/61904 [1:15:15<15:21:52,  1.41s/it]
 37%|███▋      | 22601/61904 [1:15:16<15:09:42,  1.39s/it]
 37%|███▋      | 22602/61904 [1:15:18<14:46:30,  1.35s/it]
 37%|███▋      | 22603/61904 [1:15:19<14:53:35,  1.36s/it]
 37%|███▋      | 22604/61904 [1:15:20<14:41:35,  1.35s/it]
 37%|███▋      | 22605/61904 [1:15:22<14:50:15,  1.36s/it]
 37%|███▋      | 22606/61904 [1:15:23<15:22:51,  1.41s/it]
 37%|███▋      | 22607/61904 [1:15:25<15:34:34,  1.43s/it]
 37%|███▋      | 22608/61904 [1:15:26<15:43:27,  1.44s/it]
 37%|███▋      | 22609/61904 [1:15:27<15:06:34,  1.38s/it]
 37%|███▋      | 22610/61904 [1:15:29<15:22:04,  1.41s/it]
 37%|███▋      | 22611/61904 [1:15:30<15:01:00,  1.38s/it]
 37%|███▋      | 22612/61904 [1:15:32<15:52:03,  1.45s/it]
 37%|███▋      | 22613/61904 [1:15:33<15:32:37,  1.42s/it]
 37%|███▋      | 22614/61904 [1:15:34<15:08:28,  1.39s/it]
 37%|███▋      | 22615/61904 [1:15:36<14:50:51,  1.36s/it]
 37%|███▋      | 22616/61904 [1:15:37<15:06:28,  1.38s/it]
 37%|███▋      | 22617/61904 [1:15:38<15:01:15,  1.38s/it]
 37%|███▋      | 22618/61904 [1:15:40<14:43:23,  1.35s/it]
 37%|███▋      | 22619/61904 [1:15:41<14:28:42,  1.33s/it]
 37%|███▋      | 22620/61904 [1:15:43<15:09:30,  1.39s/it]
                                                          
{'loss': 2.5673, 'learning_rate': 1.636652405030468e-07, 'epoch': 5.85}

 37%|███▋      | 22620/61904 [1:15:43<15:09:30,  1.39s/it]
 37%|███▋      | 22621/61904 [1:15:44<15:54:22,  1.46s/it]
 37%|███▋      | 22622/61904 [1:15:46<15:52:31,  1.45s/it]
 37%|███▋      | 22623/61904 [1:15:47<15:29:08,  1.42s/it]
 37%|███▋      | 22624/61904 [1:15:48<15:39:10,  1.43s/it]
 37%|███▋      | 22625/61904 [1:15:50<15:38:46,  1.43s/it]
 37%|███▋      | 22626/61904 [1:15:51<15:43:02,  1.44s/it]
 37%|███▋      | 22627/61904 [1:15:53<15:25:02,  1.41s/it]
 37%|███▋      | 22628/61904 [1:15:54<15:14:01,  1.40s/it]
 37%|███▋      | 22629/61904 [1:15:56<15:43:23,  1.44s/it]
 37%|███▋      | 22630/61904 [1:15:57<15:51:43,  1.45s/it]
 37%|███▋      | 22631/61904 [1:15:59<15:57:19,  1.46s/it]
 37%|███▋      | 22632/61904 [1:16:00<15:32:53,  1.43s/it]
 37%|███▋      | 22633/61904 [1:16:01<15:16:28,  1.40s/it]
 37%|███▋      | 22634/61904 [1:16:03<14:55:59,  1.37s/it]
 37%|███▋      | 22635/61904 [1:16:04<14:35:32,  1.34s/it]
 37%|███▋      | 22636/61904 [1:16:05<14:19:46,  1.31s/it]
 37%|███▋      | 22637/61904 [1:16:06<14:19:09,  1.31s/it]
 37%|███▋      | 22638/61904 [1:16:08<14:44:54,  1.35s/it]
 37%|███▋      | 22639/61904 [1:16:09<14:34:31,  1.34s/it]
 37%|███▋      | 22640/61904 [1:16:10<14:25:00,  1.32s/it]
                                                          
{'loss': 2.6455, 'learning_rate': 1.6363282769350444e-07, 'epoch': 5.85}

 37%|███▋      | 22640/61904 [1:16:10<14:25:00,  1.32s/it]
 37%|███▋      | 22641/61904 [1:16:12<15:29:33,  1.42s/it]
 37%|███▋      | 22642/61904 [1:16:13<15:22:15,  1.41s/it]
 37%|███▋      | 22643/61904 [1:16:15<15:20:25,  1.41s/it]
 37%|███▋      | 22644/61904 [1:16:16<15:23:33,  1.41s/it]
 37%|███▋      | 22645/61904 [1:16:18<15:08:20,  1.39s/it]
 37%|███▋      | 22646/61904 [1:16:19<14:52:31,  1.36s/it]
 37%|███▋      | 22647/61904 [1:16:20<14:54:17,  1.37s/it]
 37%|███▋      | 22648/61904 [1:16:22<15:01:47,  1.38s/it]
 37%|███▋      | 22649/61904 [1:16:23<14:53:33,  1.37s/it]
 37%|███▋      | 22650/61904 [1:16:24<15:05:02,  1.38s/it]
 37%|███▋      | 22651/61904 [1:16:26<15:22:32,  1.41s/it]
 37%|███▋      | 22652/61904 [1:16:27<15:13:23,  1.40s/it]
 37%|███▋      | 22653/61904 [1:16:29<15:44:00,  1.44s/it]
 37%|███▋      | 22654/61904 [1:16:30<15:13:33,  1.40s/it]
 37%|███▋      | 22655/61904 [1:16:31<14:59:38,  1.38s/it]
 37%|███▋      | 22656/61904 [1:16:33<15:15:34,  1.40s/it]
 37%|███▋      | 22657/61904 [1:16:34<14:47:33,  1.36s/it]
 37%|███▋      | 22658/61904 [1:16:35<14:41:00,  1.35s/it]
 37%|███▋      | 22659/61904 [1:16:37<15:08:49,  1.39s/it]
 37%|███▋      | 22660/61904 [1:16:38<15:00:51,  1.38s/it]
                                                          
{'loss': 2.6617, 'learning_rate': 1.6360041488396213e-07, 'epoch': 5.86}

 37%|███▋      | 22660/61904 [1:16:38<15:00:51,  1.38s/it]
 37%|███▋      | 22661/61904 [1:16:40<14:53:56,  1.37s/it]
 37%|███▋      | 22662/61904 [1:16:41<15:29:45,  1.42s/it]
 37%|███▋      | 22663/61904 [1:16:43<15:16:47,  1.40s/it]
 37%|███▋      | 22664/61904 [1:16:44<15:11:59,  1.39s/it]
 37%|███▋      | 22665/61904 [1:16:45<15:10:27,  1.39s/it]
 37%|███▋      | 22666/61904 [1:16:47<14:59:37,  1.38s/it]
 37%|███▋      | 22667/61904 [1:16:48<15:11:58,  1.39s/it]
 37%|███▋      | 22668/61904 [1:16:49<15:01:37,  1.38s/it]
 37%|███▋      | 22669/61904 [1:16:51<14:51:05,  1.36s/it]
 37%|███▋      | 22670/61904 [1:16:52<14:49:03,  1.36s/it]
 37%|███▋      | 22671/61904 [1:16:53<14:49:47,  1.36s/it]
 37%|███▋      | 22672/61904 [1:16:55<15:14:56,  1.40s/it]
 37%|███▋      | 22673/61904 [1:16:56<15:14:25,  1.40s/it]
 37%|███▋      | 22674/61904 [1:16:58<14:59:47,  1.38s/it]
 37%|███▋      | 22675/61904 [1:16:59<14:58:20,  1.37s/it]
 37%|███▋      | 22676/61904 [1:17:01<15:21:54,  1.41s/it]
 37%|███▋      | 22677/61904 [1:17:02<15:05:19,  1.38s/it]
 37%|███▋      | 22678/61904 [1:17:03<14:58:50,  1.37s/it]
 37%|███▋      | 22679/61904 [1:17:05<14:53:40,  1.37s/it]
 37%|███▋      | 22680/61904 [1:17:06<15:07:15,  1.39s/it]
                                                          
{'loss': 2.6395, 'learning_rate': 1.6356800207441982e-07, 'epoch': 5.86}

 37%|███▋      | 22680/61904 [1:17:06<15:07:15,  1.39s/it]
 37%|███▋      | 22681/61904 [1:17:07<15:08:29,  1.39s/it]
 37%|███▋      | 22682/61904 [1:17:09<15:38:10,  1.44s/it]
 37%|███▋      | 22683/61904 [1:17:10<15:38:39,  1.44s/it]
 37%|███▋      | 22684/61904 [1:17:12<15:17:58,  1.40s/it]
 37%|███▋      | 22685/61904 [1:17:13<15:00:17,  1.38s/it]
 37%|███▋      | 22686/61904 [1:17:14<14:50:08,  1.36s/it]
 37%|███▋      | 22687/61904 [1:17:16<15:13:43,  1.40s/it]
 37%|███▋      | 22688/61904 [1:17:17<14:48:42,  1.36s/it]
 37%|███▋      | 22689/61904 [1:17:19<15:10:26,  1.39s/it]
 37%|███▋      | 22690/61904 [1:17:20<15:11:24,  1.39s/it]
 37%|███▋      | 22691/61904 [1:17:21<15:21:00,  1.41s/it]
 37%|███▋      | 22692/61904 [1:17:23<15:11:30,  1.39s/it]
 37%|███▋      | 22693/61904 [1:17:24<15:29:08,  1.42s/it]
 37%|███▋      | 22694/61904 [1:17:26<14:51:45,  1.36s/it]
 37%|███▋      | 22695/61904 [1:17:27<15:08:05,  1.39s/it]
 37%|███▋      | 22696/61904 [1:17:28<15:23:03,  1.41s/it]
 37%|███▋      | 22697/61904 [1:17:30<15:08:54,  1.39s/it]
 37%|███▋      | 22698/61904 [1:17:31<15:15:10,  1.40s/it]
 37%|███▋      | 22699/61904 [1:17:33<15:08:19,  1.39s/it]
 37%|███▋      | 22700/61904 [1:17:34<14:39:04,  1.35s/it]
                                                          
{'loss': 2.6358, 'learning_rate': 1.6353558926487745e-07, 'epoch': 5.87}

 37%|███▋      | 22700/61904 [1:17:34<14:39:04,  1.35s/it]
 37%|███▋      | 22701/61904 [1:17:35<15:10:30,  1.39s/it]
 37%|███▋      | 22702/61904 [1:17:37<15:25:34,  1.42s/it]
 37%|███▋      | 22703/61904 [1:17:38<15:22:18,  1.41s/it]
 37%|███▋      | 22704/61904 [1:17:39<14:45:27,  1.36s/it]
 37%|███▋      | 22705/61904 [1:17:41<15:04:28,  1.38s/it]
 37%|███▋      | 22706/61904 [1:17:42<15:18:59,  1.41s/it]
 37%|███▋      | 22707/61904 [1:17:44<15:05:52,  1.39s/it]
 37%|███▋      | 22708/61904 [1:17:45<14:57:47,  1.37s/it]
 37%|███▋      | 22709/61904 [1:17:46<14:47:41,  1.36s/it]
 37%|███▋      | 22710/61904 [1:17:48<14:49:07,  1.36s/it]
 37%|███▋      | 22711/61904 [1:17:49<14:51:13,  1.36s/it]
 37%|███▋      | 22712/61904 [1:17:50<14:48:23,  1.36s/it]
 37%|███▋      | 22713/61904 [1:17:52<14:45:21,  1.36s/it]
 37%|███▋      | 22714/61904 [1:17:53<15:09:51,  1.39s/it]
 37%|███▋      | 22715/61904 [1:17:55<15:07:36,  1.39s/it]
 37%|███▋      | 22716/61904 [1:17:56<15:28:38,  1.42s/it]
 37%|███▋      | 22717/61904 [1:17:57<15:15:40,  1.40s/it]
 37%|███▋      | 22718/61904 [1:17:59<15:27:27,  1.42s/it]
 37%|███▋      | 22719/61904 [1:18:00<15:32:28,  1.43s/it]
 37%|███▋      | 22720/61904 [1:18:02<15:17:46,  1.41s/it]
                                                          
{'loss': 2.618, 'learning_rate': 1.6350317645533514e-07, 'epoch': 5.87}

 37%|███▋      | 22720/61904 [1:18:02<15:17:46,  1.41s/it]
 37%|███▋      | 22721/61904 [1:18:03<15:14:20,  1.40s/it]
 37%|███▋      | 22722/61904 [1:18:05<15:26:35,  1.42s/it]
 37%|███▋      | 22723/61904 [1:18:06<14:54:48,  1.37s/it]
 37%|███▋      | 22724/61904 [1:18:07<14:58:51,  1.38s/it]
 37%|███▋      | 22725/61904 [1:18:09<15:11:58,  1.40s/it]
 37%|███▋      | 22726/61904 [1:18:10<15:17:58,  1.41s/it]
 37%|███▋      | 22727/61904 [1:18:12<15:17:50,  1.41s/it]
 37%|███▋      | 22728/61904 [1:18:13<15:14:44,  1.40s/it]
 37%|███▋      | 22729/61904 [1:18:14<14:58:39,  1.38s/it]
 37%|███▋      | 22730/61904 [1:18:16<15:33:50,  1.43s/it]
 37%|███▋      | 22731/61904 [1:18:17<15:18:52,  1.41s/it]
 37%|███▋      | 22732/61904 [1:18:18<14:55:14,  1.37s/it]
 37%|███▋      | 22733/61904 [1:18:20<15:14:32,  1.40s/it]
 37%|███▋      | 22734/61904 [1:18:21<15:17:03,  1.40s/it]
 37%|███▋      | 22735/61904 [1:18:23<15:25:28,  1.42s/it]
 37%|███▋      | 22736/61904 [1:18:24<14:52:10,  1.37s/it]
 37%|███▋      | 22737/61904 [1:18:25<14:34:01,  1.34s/it]
 37%|███▋      | 22738/61904 [1:18:27<14:30:26,  1.33s/it]
 37%|███▋      | 22739/61904 [1:18:28<14:42:37,  1.35s/it]
 37%|███▋      | 22740/61904 [1:18:29<14:43:17,  1.35s/it]
                                                          
{'loss': 2.6219, 'learning_rate': 1.634707636457928e-07, 'epoch': 5.88}

 37%|███▋      | 22740/61904 [1:18:29<14:43:17,  1.35s/it]
 37%|███▋      | 22741/61904 [1:18:31<14:45:14,  1.36s/it]
 37%|███▋      | 22742/61904 [1:18:32<15:15:24,  1.40s/it]
 37%|███▋      | 22743/61904 [1:18:34<15:06:36,  1.39s/it]
 37%|███▋      | 22744/61904 [1:18:35<14:40:37,  1.35s/it]
 37%|███▋      | 22745/61904 [1:18:36<14:40:24,  1.35s/it]
 37%|███▋      | 22746/61904 [1:18:38<14:57:21,  1.37s/it]
 37%|███▋      | 22747/61904 [1:18:39<15:11:21,  1.40s/it]
 37%|███▋      | 22748/61904 [1:18:41<15:31:55,  1.43s/it]
 37%|███▋      | 22749/61904 [1:18:42<15:36:53,  1.44s/it]
 37%|███▋      | 22750/61904 [1:18:43<15:31:01,  1.43s/it]
 37%|███▋      | 22751/61904 [1:18:45<15:28:09,  1.42s/it]
 37%|███▋      | 22752/61904 [1:18:46<15:06:03,  1.39s/it]
 37%|███▋      | 22753/61904 [1:18:47<14:42:10,  1.35s/it]
 37%|███▋      | 22754/61904 [1:18:49<15:05:20,  1.39s/it]
 37%|███▋      | 22755/61904 [1:18:50<14:56:23,  1.37s/it]
 37%|███▋      | 22756/61904 [1:18:52<14:51:04,  1.37s/it]
 37%|███▋      | 22757/61904 [1:18:53<15:05:03,  1.39s/it]
 37%|███▋      | 22758/61904 [1:18:54<14:51:02,  1.37s/it]
 37%|███▋      | 22759/61904 [1:18:56<15:16:10,  1.40s/it]
 37%|███▋      | 22760/61904 [1:18:57<15:29:59,  1.43s/it]
                                                          
{'loss': 2.6028, 'learning_rate': 1.6343835083625047e-07, 'epoch': 5.88}

 37%|███▋      | 22760/61904 [1:18:57<15:29:59,  1.43s/it]
 37%|███▋      | 22761/61904 [1:18:59<15:29:28,  1.42s/it]
 37%|███▋      | 22762/61904 [1:19:00<14:46:48,  1.36s/it]
 37%|███▋      | 22763/61904 [1:19:01<15:18:44,  1.41s/it]
 37%|███▋      | 22764/61904 [1:19:03<15:02:42,  1.38s/it]
 37%|███▋      | 22765/61904 [1:19:04<15:14:55,  1.40s/it]
 37%|███▋      | 22766/61904 [1:19:06<14:54:06,  1.37s/it]
 37%|███▋      | 22767/61904 [1:19:07<15:00:24,  1.38s/it]
 37%|███▋      | 22768/61904 [1:19:08<14:43:50,  1.36s/it]
 37%|███▋      | 22769/61904 [1:19:10<14:44:02,  1.36s/it]
 37%|███▋      | 22770/61904 [1:19:11<14:45:43,  1.36s/it]
 37%|███▋      | 22771/61904 [1:19:12<15:13:33,  1.40s/it]
 37%|███▋      | 22772/61904 [1:19:14<14:46:39,  1.36s/it]
 37%|███▋      | 22773/61904 [1:19:15<14:58:51,  1.38s/it]
 37%|███▋      | 22774/61904 [1:19:16<14:47:54,  1.36s/it]
 37%|███▋      | 22775/61904 [1:19:18<15:41:40,  1.44s/it]
 37%|███▋      | 22776/61904 [1:19:20<16:13:39,  1.49s/it]
 37%|███▋      | 22777/61904 [1:19:21<15:53:55,  1.46s/it]
 37%|███▋      | 22778/61904 [1:19:22<15:38:07,  1.44s/it]
 37%|███▋      | 22779/61904 [1:19:24<15:50:57,  1.46s/it]
 37%|███▋      | 22780/61904 [1:19:25<16:01:49,  1.48s/it]
                                                          
{'loss': 2.599, 'learning_rate': 1.6340593802670815e-07, 'epoch': 5.89}

 37%|███▋      | 22780/61904 [1:19:25<16:01:49,  1.48s/it]
 37%|███▋      | 22781/61904 [1:19:27<15:46:08,  1.45s/it]
 37%|███▋      | 22782/61904 [1:19:28<15:31:33,  1.43s/it]
 37%|███▋      | 22783/61904 [1:19:30<15:22:15,  1.41s/it]
 37%|███▋      | 22784/61904 [1:19:31<15:21:43,  1.41s/it]
 37%|███▋      | 22785/61904 [1:19:33<15:33:32,  1.43s/it]
 37%|███▋      | 22786/61904 [1:19:34<15:09:56,  1.40s/it]
 37%|███▋      | 22787/61904 [1:19:35<14:48:30,  1.36s/it]
 37%|███▋      | 22788/61904 [1:19:37<15:07:05,  1.39s/it]
 37%|███▋      | 22789/61904 [1:19:38<15:06:28,  1.39s/it]
 37%|███▋      | 22790/61904 [1:19:39<14:45:49,  1.36s/it]
 37%|███▋      | 22791/61904 [1:19:41<15:05:05,  1.39s/it]
 37%|███▋      | 22792/61904 [1:19:42<14:58:24,  1.38s/it]
 37%|███▋      | 22793/61904 [1:19:43<14:50:07,  1.37s/it]
 37%|███▋      | 22794/61904 [1:19:45<14:48:17,  1.36s/it]
 37%|███▋      | 22795/61904 [1:19:46<14:29:25,  1.33s/it]
 37%|███▋      | 22796/61904 [1:19:47<14:50:31,  1.37s/it]
 37%|███▋      | 22797/61904 [1:19:49<14:42:27,  1.35s/it]
 37%|███▋      | 22798/61904 [1:19:50<14:52:52,  1.37s/it]
 37%|███▋      | 22799/61904 [1:19:52<15:02:07,  1.38s/it]
 37%|███▋      | 22800/61904 [1:19:53<15:06:42,  1.39s/it]
                                                          
{'loss': 2.6062, 'learning_rate': 1.633735252171658e-07, 'epoch': 5.89}

 37%|███▋      | 22800/61904 [1:19:53<15:06:42,  1.39s/it]
 37%|███▋      | 22801/61904 [1:19:55<15:29:19,  1.43s/it]
 37%|███▋      | 22802/61904 [1:19:56<15:31:47,  1.43s/it]
 37%|███▋      | 22803/61904 [1:19:57<15:13:31,  1.40s/it]
 37%|███▋      | 22804/61904 [1:19:59<14:52:35,  1.37s/it]
 37%|███▋      | 22805/61904 [1:20:00<14:51:27,  1.37s/it]
 37%|███▋      | 22806/61904 [1:20:01<14:48:07,  1.36s/it]
 37%|███▋      | 22807/61904 [1:20:03<14:45:54,  1.36s/it]
 37%|███▋      | 22808/61904 [1:20:04<14:57:26,  1.38s/it]
 37%|███▋      | 22809/61904 [1:20:05<14:37:24,  1.35s/it]
 37%|███▋      | 22810/61904 [1:20:07<15:04:04,  1.39s/it]
 37%|███▋      | 22811/61904 [1:20:08<15:07:41,  1.39s/it]
 37%|███▋      | 22812/61904 [1:20:10<14:48:04,  1.36s/it]
 37%|███▋      | 22813/61904 [1:20:11<14:46:56,  1.36s/it]
 37%|███▋      | 22814/61904 [1:20:12<14:53:30,  1.37s/it]
 37%|███▋      | 22815/61904 [1:20:14<14:38:38,  1.35s/it]
 37%|███▋      | 22816/61904 [1:20:15<14:46:34,  1.36s/it]
 37%|███▋      | 22817/61904 [1:20:16<14:44:28,  1.36s/it]
 37%|███▋      | 22818/61904 [1:20:18<15:02:07,  1.38s/it]
 37%|███▋      | 22819/61904 [1:20:19<15:21:37,  1.41s/it]
 37%|███▋      | 22820/61904 [1:20:21<15:10:01,  1.40s/it]
                                                          
{'loss': 2.5854, 'learning_rate': 1.6334111240762348e-07, 'epoch': 5.9}

 37%|███▋      | 22820/61904 [1:20:21<15:10:01,  1.40s/it]
 37%|███▋      | 22821/61904 [1:20:22<15:46:35,  1.45s/it]
 37%|███▋      | 22822/61904 [1:20:24<15:26:17,  1.42s/it]
 37%|███▋      | 22823/61904 [1:20:25<15:11:18,  1.40s/it]
 37%|███▋      | 22824/61904 [1:20:26<15:18:34,  1.41s/it]
 37%|███▋      | 22825/61904 [1:20:28<15:11:58,  1.40s/it]
 37%|███▋      | 22826/61904 [1:20:29<15:20:53,  1.41s/it]
 37%|███▋      | 22827/61904 [1:20:31<15:15:56,  1.41s/it]
 37%|███▋      | 22828/61904 [1:20:32<15:38:08,  1.44s/it]
 37%|███▋      | 22829/61904 [1:20:33<15:22:35,  1.42s/it]
 37%|███▋      | 22830/61904 [1:20:35<15:15:56,  1.41s/it]
 37%|███▋      | 22831/61904 [1:20:36<15:09:30,  1.40s/it]
 37%|███▋      | 22832/61904 [1:20:38<15:12:15,  1.40s/it]
 37%|███▋      | 22833/61904 [1:20:39<15:35:09,  1.44s/it]
 37%|███▋      | 22834/61904 [1:20:41<15:36:27,  1.44s/it]
 37%|███▋      | 22835/61904 [1:20:42<15:18:37,  1.41s/it]
 37%|███▋      | 22836/61904 [1:20:43<15:00:21,  1.38s/it]
 37%|███▋      | 22837/61904 [1:20:45<15:58:18,  1.47s/it]
 37%|███▋      | 22838/61904 [1:20:47<16:34:48,  1.53s/it]
 37%|███▋      | 22839/61904 [1:20:48<16:13:58,  1.50s/it]
 37%|███▋      | 22840/61904 [1:20:49<15:55:38,  1.47s/it]
                                                          
{'loss': 2.5416, 'learning_rate': 1.6330869959808117e-07, 'epoch': 5.9}

 37%|███▋      | 22840/61904 [1:20:49<15:55:38,  1.47s/it]
 37%|███▋      | 22841/61904 [1:20:51<15:54:32,  1.47s/it]
 37%|███▋      | 22842/61904 [1:20:52<15:29:24,  1.43s/it]
 37%|███▋      | 22843/61904 [1:20:53<14:51:33,  1.37s/it]
 37%|███▋      | 22844/61904 [1:20:55<14:29:16,  1.34s/it]
 37%|███▋      | 22845/61904 [1:20:56<15:20:55,  1.41s/it]
 37%|███▋      | 22846/61904 [1:20:58<15:06:28,  1.39s/it]
 37%|███▋      | 22847/61904 [1:20:59<15:11:28,  1.40s/it]
 37%|███▋      | 22848/61904 [1:21:00<14:55:16,  1.38s/it]
 37%|███▋      | 22849/61904 [1:21:02<15:15:57,  1.41s/it]
 37%|███▋      | 22850/61904 [1:21:03<14:53:10,  1.37s/it]
 37%|███▋      | 22851/61904 [1:21:04<14:54:06,  1.37s/it]
 37%|███▋      | 22852/61904 [1:21:06<14:51:03,  1.37s/it]
 37%|███▋      | 22853/61904 [1:21:07<14:46:01,  1.36s/it]
 37%|███▋      | 22854/61904 [1:21:08<14:36:28,  1.35s/it]
 37%|███▋      | 22855/61904 [1:21:10<14:51:48,  1.37s/it]
 37%|███▋      | 22856/61904 [1:21:11<14:56:10,  1.38s/it]
 37%|███▋      | 22857/61904 [1:21:13<15:18:21,  1.41s/it]
 37%|███▋      | 22858/61904 [1:21:14<15:20:23,  1.41s/it]
 37%|███▋      | 22859/61904 [1:21:16<15:06:59,  1.39s/it]
 37%|███▋      | 22860/61904 [1:21:17<14:49:53,  1.37s/it]
                                                          
{'loss': 2.6731, 'learning_rate': 1.632762867885388e-07, 'epoch': 5.91}

 37%|███▋      | 22860/61904 [1:21:17<14:49:53,  1.37s/it]
 37%|███▋      | 22861/61904 [1:21:18<14:49:31,  1.37s/it]
 37%|███▋      | 22862/61904 [1:21:20<14:54:40,  1.37s/it]
 37%|███▋      | 22863/61904 [1:21:21<15:05:10,  1.39s/it]
 37%|███▋      | 22864/61904 [1:21:23<15:22:55,  1.42s/it]
 37%|███▋      | 22865/61904 [1:21:24<15:37:21,  1.44s/it]
 37%|███▋      | 22866/61904 [1:21:26<15:50:55,  1.46s/it]
 37%|███▋      | 22867/61904 [1:21:27<15:48:27,  1.46s/it]
 37%|███▋      | 22868/61904 [1:21:29<16:01:28,  1.48s/it]
 37%|███▋      | 22869/61904 [1:21:30<15:39:56,  1.44s/it]
 37%|███▋      | 22870/61904 [1:21:31<15:32:10,  1.43s/it]
 37%|███▋      | 22871/61904 [1:21:33<15:10:48,  1.40s/it]
 37%|███▋      | 22872/61904 [1:21:34<14:48:45,  1.37s/it]
 37%|███▋      | 22873/61904 [1:21:35<14:26:22,  1.33s/it]
 37%|███▋      | 22874/61904 [1:21:36<14:25:34,  1.33s/it]
 37%|███▋      | 22875/61904 [1:21:38<14:26:10,  1.33s/it]
 37%|███▋      | 22876/61904 [1:21:39<14:48:47,  1.37s/it]
 37%|███▋      | 22877/61904 [1:21:41<14:39:06,  1.35s/it]
 37%|███▋      | 22878/61904 [1:21:42<14:33:19,  1.34s/it]
 37%|███▋      | 22879/61904 [1:21:43<15:17:52,  1.41s/it]
 37%|███▋      | 22880/61904 [1:21:45<14:55:11,  1.38s/it]
                                                          
{'loss': 2.6271, 'learning_rate': 1.632438739789965e-07, 'epoch': 5.91}

 37%|███▋      | 22880/61904 [1:21:45<14:55:11,  1.38s/it]
 37%|███▋      | 22881/61904 [1:21:46<15:39:09,  1.44s/it]
 37%|███▋      | 22882/61904 [1:21:48<15:17:45,  1.41s/it]
 37%|███▋      | 22883/61904 [1:21:49<14:57:03,  1.38s/it]
 37%|███▋      | 22884/61904 [1:21:50<14:55:13,  1.38s/it]
 37%|███▋      | 22885/61904 [1:21:52<15:10:39,  1.40s/it]
 37%|███▋      | 22886/61904 [1:21:53<15:22:24,  1.42s/it]
 37%|███▋      | 22887/61904 [1:21:55<15:25:40,  1.42s/it]
 37%|███▋      | 22888/61904 [1:21:56<15:45:22,  1.45s/it]
 37%|███▋      | 22889/61904 [1:21:58<15:35:07,  1.44s/it]
 37%|███▋      | 22890/61904 [1:21:59<15:09:13,  1.40s/it]
 37%|███▋      | 22891/61904 [1:22:00<14:30:02,  1.34s/it]
 37%|███▋      | 22892/61904 [1:22:01<14:20:56,  1.32s/it]
 37%|███▋      | 22893/61904 [1:22:03<14:25:59,  1.33s/it]
 37%|███▋      | 22894/61904 [1:22:04<14:48:38,  1.37s/it]
 37%|███▋      | 22895/61904 [1:22:06<14:35:36,  1.35s/it]
 37%|███▋      | 22896/61904 [1:22:07<14:46:31,  1.36s/it]
 37%|███▋      | 22897/61904 [1:22:08<14:55:57,  1.38s/it]
 37%|███▋      | 22898/61904 [1:22:10<15:11:41,  1.40s/it]
 37%|███▋      | 22899/61904 [1:22:11<15:11:12,  1.40s/it]
 37%|███▋      | 22900/61904 [1:22:13<15:05:28,  1.39s/it]
                                                          
{'loss': 2.5896, 'learning_rate': 1.6321146116945418e-07, 'epoch': 5.92}

 37%|███▋      | 22900/61904 [1:22:13<15:05:28,  1.39s/it]
 37%|███▋      | 22901/61904 [1:22:14<15:03:10,  1.39s/it]
 37%|███▋      | 22902/61904 [1:22:16<15:32:18,  1.43s/it]
 37%|███▋      | 22903/61904 [1:22:17<15:22:12,  1.42s/it]
 37%|███▋      | 22904/61904 [1:22:18<15:19:55,  1.42s/it]
 37%|███▋      | 22905/61904 [1:22:20<15:40:13,  1.45s/it]
 37%|███▋      | 22906/61904 [1:22:21<15:23:26,  1.42s/it]
 37%|███▋      | 22907/61904 [1:22:23<15:14:55,  1.41s/it]
 37%|███▋      | 22908/61904 [1:22:24<14:57:41,  1.38s/it]
 37%|███▋      | 22909/61904 [1:22:25<14:42:22,  1.36s/it]
 37%|███▋      | 22910/61904 [1:22:27<14:36:28,  1.35s/it]
 37%|███▋      | 22911/61904 [1:22:28<14:38:02,  1.35s/it]
 37%|███▋      | 22912/61904 [1:22:29<14:37:06,  1.35s/it]
 37%|███▋      | 22913/61904 [1:22:30<14:20:12,  1.32s/it]
 37%|███▋      | 22914/61904 [1:22:32<14:22:35,  1.33s/it]
 37%|███▋      | 22915/61904 [1:22:33<14:22:08,  1.33s/it]
 37%|███▋      | 22916/61904 [1:22:35<14:36:19,  1.35s/it]
 37%|███▋      | 22917/61904 [1:22:36<14:54:15,  1.38s/it]
 37%|███▋      | 22918/61904 [1:22:37<14:53:18,  1.37s/it]
 37%|███▋      | 22919/61904 [1:22:39<14:37:38,  1.35s/it]
 37%|███▋      | 22920/61904 [1:22:40<14:55:55,  1.38s/it]
                                                          
{'loss': 2.6794, 'learning_rate': 1.6317904835991181e-07, 'epoch': 5.92}

 37%|███▋      | 22920/61904 [1:22:40<14:55:55,  1.38s/it]
 37%|███▋      | 22921/61904 [1:22:41<14:47:38,  1.37s/it]
 37%|███▋      | 22922/61904 [1:22:43<14:33:52,  1.35s/it]
 37%|███▋      | 22923/61904 [1:22:44<15:22:38,  1.42s/it]
 37%|███▋      | 22924/61904 [1:22:46<15:14:01,  1.41s/it]
 37%|███▋      | 22925/61904 [1:22:47<15:20:59,  1.42s/it]
 37%|███▋      | 22926/61904 [1:22:49<16:48:42,  1.55s/it]
 37%|███▋      | 22927/61904 [1:22:50<16:29:26,  1.52s/it]
 37%|███▋      | 22928/61904 [1:22:52<16:11:21,  1.50s/it]
 37%|███▋      | 22929/61904 [1:22:53<15:56:30,  1.47s/it]
 37%|███▋      | 22930/61904 [1:22:55<15:22:44,  1.42s/it]
 37%|███▋      | 22931/61904 [1:22:56<15:23:45,  1.42s/it]
 37%|███▋      | 22932/61904 [1:22:57<15:21:02,  1.42s/it]
 37%|███▋      | 22933/61904 [1:22:59<16:11:22,  1.50s/it]
 37%|███▋      | 22934/61904 [1:23:01<16:10:27,  1.49s/it]
 37%|███▋      | 22935/61904 [1:23:02<16:25:01,  1.52s/it]
 37%|███▋      | 22936/61904 [1:23:04<15:52:06,  1.47s/it]
 37%|███▋      | 22937/61904 [1:23:05<15:28:33,  1.43s/it]
 37%|███▋      | 22938/61904 [1:23:06<15:35:05,  1.44s/it]
 37%|███▋      | 22939/61904 [1:23:08<15:06:54,  1.40s/it]
 37%|███▋      | 22940/61904 [1:23:09<15:12:02,  1.40s/it]
                                                          
{'loss': 2.6051, 'learning_rate': 1.631466355503695e-07, 'epoch': 5.93}

 37%|███▋      | 22940/61904 [1:23:09<15:12:02,  1.40s/it]
 37%|███▋      | 22941/61904 [1:23:10<14:57:35,  1.38s/it]
 37%|███▋      | 22942/61904 [1:23:12<15:16:39,  1.41s/it]
 37%|███▋      | 22943/61904 [1:23:13<14:55:59,  1.38s/it]
 37%|███▋      | 22944/61904 [1:23:15<14:46:01,  1.36s/it]
 37%|███▋      | 22945/61904 [1:23:16<16:11:16,  1.50s/it]
 37%|███▋      | 22946/61904 [1:23:18<15:42:39,  1.45s/it]
 37%|███▋      | 22947/61904 [1:23:19<15:39:56,  1.45s/it]
 37%|███▋      | 22948/61904 [1:23:21<15:43:57,  1.45s/it]
 37%|███▋      | 22949/61904 [1:23:22<15:41:39,  1.45s/it]
 37%|███▋      | 22950/61904 [1:23:23<15:09:28,  1.40s/it]
 37%|███▋      | 22951/61904 [1:23:25<14:50:12,  1.37s/it]
 37%|███▋      | 22952/61904 [1:23:26<14:31:51,  1.34s/it]
 37%|███▋      | 22953/61904 [1:23:27<14:18:39,  1.32s/it]
 37%|███▋      | 22954/61904 [1:23:29<14:32:41,  1.34s/it]
 37%|███▋      | 22955/61904 [1:23:30<14:24:43,  1.33s/it]
 37%|███▋      | 22956/61904 [1:23:31<14:49:58,  1.37s/it]
 37%|███▋      | 22957/61904 [1:23:33<15:14:35,  1.41s/it]
 37%|███▋      | 22958/61904 [1:23:34<15:09:00,  1.40s/it]
 37%|███▋      | 22959/61904 [1:23:35<14:45:15,  1.36s/it]
 37%|███▋      | 22960/61904 [1:23:37<14:44:17,  1.36s/it]
                                                          
{'loss': 2.6901, 'learning_rate': 1.6311422274082716e-07, 'epoch': 5.93}

 37%|███▋      | 22960/61904 [1:23:37<14:44:17,  1.36s/it]
 37%|███▋      | 22961/61904 [1:23:38<14:46:40,  1.37s/it]
 37%|███▋      | 22962/61904 [1:23:40<14:38:37,  1.35s/it]
 37%|███▋      | 22963/61904 [1:23:41<14:57:37,  1.38s/it]
 37%|███▋      | 22964/61904 [1:23:42<15:17:04,  1.41s/it]
 37%|███▋      | 22965/61904 [1:23:44<14:54:26,  1.38s/it]
 37%|███▋      | 22966/61904 [1:23:45<14:51:11,  1.37s/it]
 37%|███▋      | 22967/61904 [1:23:47<14:59:42,  1.39s/it]
 37%|███▋      | 22968/61904 [1:23:48<15:04:40,  1.39s/it]
 37%|███▋      | 22969/61904 [1:23:49<15:12:16,  1.41s/it]
 37%|███▋      | 22970/61904 [1:23:51<14:40:42,  1.36s/it]
 37%|███▋      | 22971/61904 [1:23:52<15:14:54,  1.41s/it]
 37%|███▋      | 22972/61904 [1:23:53<14:40:51,  1.36s/it]
 37%|███▋      | 22973/61904 [1:23:55<14:27:16,  1.34s/it]
 37%|███▋      | 22974/61904 [1:23:56<14:18:16,  1.32s/it]
 37%|███▋      | 22975/61904 [1:23:57<14:19:58,  1.33s/it]
 37%|███▋      | 22976/61904 [1:23:59<14:10:03,  1.31s/it]
 37%|███▋      | 22977/61904 [1:24:00<14:33:05,  1.35s/it]
 37%|███▋      | 22978/61904 [1:24:01<14:36:20,  1.35s/it]
 37%|███▋      | 22979/61904 [1:24:03<15:52:37,  1.47s/it]
 37%|███▋      | 22980/61904 [1:24:04<15:31:13,  1.44s/it]
                                                          
{'loss': 2.6288, 'learning_rate': 1.6308180993128483e-07, 'epoch': 5.94}

 37%|███▋      | 22980/61904 [1:24:04<15:31:13,  1.44s/it]
 37%|███▋      | 22981/61904 [1:24:06<15:28:02,  1.43s/it]
 37%|███▋      | 22982/61904 [1:24:07<15:26:21,  1.43s/it]
 37%|███▋      | 22983/61904 [1:24:09<15:46:31,  1.46s/it]
 37%|███▋      | 22984/61904 [1:24:10<15:19:15,  1.42s/it]
 37%|███▋      | 22985/61904 [1:24:11<14:57:06,  1.38s/it]
 37%|███▋      | 22986/61904 [1:24:13<14:38:41,  1.35s/it]
 37%|███▋      | 22987/61904 [1:24:14<14:36:49,  1.35s/it]
 37%|███▋      | 22988/61904 [1:24:15<14:36:12,  1.35s/it]
 37%|███▋      | 22989/61904 [1:24:17<14:16:57,  1.32s/it]
 37%|███▋      | 22990/61904 [1:24:18<14:33:07,  1.35s/it]
 37%|███▋      | 22991/61904 [1:24:20<14:50:59,  1.37s/it]
 37%|███▋      | 22992/61904 [1:24:21<14:48:07,  1.37s/it]
 37%|███▋      | 22993/61904 [1:24:22<14:50:36,  1.37s/it]
 37%|███▋      | 22994/61904 [1:24:24<15:11:21,  1.41s/it]
 37%|███▋      | 22995/61904 [1:24:25<14:47:29,  1.37s/it]
 37%|███▋      | 22996/61904 [1:24:26<15:01:41,  1.39s/it]
 37%|███▋      | 22997/61904 [1:24:28<15:00:34,  1.39s/it]
 37%|███▋      | 22998/61904 [1:24:29<15:03:33,  1.39s/it]
 37%|███▋      | 22999/61904 [1:24:31<15:41:51,  1.45s/it]
 37%|███▋      | 23000/61904 [1:24:33<16:24:13,  1.52s/it]
                                                          
{'loss': 2.6806, 'learning_rate': 1.6304939712174251e-07, 'epoch': 5.94}

 37%|███▋      | 23000/61904 [1:24:33<16:24:13,  1.52s/it]
 37%|███▋      | 23001/61904 [1:24:34<16:02:11,  1.48s/it]
 37%|███▋      | 23002/61904 [1:24:35<15:33:09,  1.44s/it]
 37%|███▋      | 23003/61904 [1:24:37<14:58:17,  1.39s/it]
 37%|███▋      | 23004/61904 [1:24:38<15:03:53,  1.39s/it]
 37%|███▋      | 23005/61904 [1:24:40<15:40:29,  1.45s/it]
 37%|███▋      | 23006/61904 [1:24:41<15:29:01,  1.43s/it]
 37%|███▋      | 23007/61904 [1:24:42<15:31:45,  1.44s/it]
 37%|███▋      | 23008/61904 [1:24:44<15:36:58,  1.45s/it]
 37%|███▋      | 23009/61904 [1:24:45<15:43:17,  1.46s/it]
 37%|███▋      | 23010/61904 [1:24:47<15:47:27,  1.46s/it]
 37%|███▋      | 23011/61904 [1:24:48<15:41:01,  1.45s/it]
 37%|███▋      | 23012/61904 [1:24:50<15:43:18,  1.46s/it]
 37%|███▋      | 23013/61904 [1:24:51<15:42:00,  1.45s/it]
 37%|███▋      | 23014/61904 [1:24:53<15:47:33,  1.46s/it]
 37%|███▋      | 23015/61904 [1:24:54<15:36:46,  1.45s/it]
 37%|███▋      | 23016/61904 [1:24:55<15:36:56,  1.45s/it]
 37%|███▋      | 23017/61904 [1:24:57<15:26:34,  1.43s/it]
 37%|███▋      | 23018/61904 [1:24:58<15:30:06,  1.44s/it]
 37%|███▋      | 23019/61904 [1:25:00<14:57:54,  1.39s/it]
 37%|███▋      | 23020/61904 [1:25:01<14:52:30,  1.38s/it]
                                                          
{'loss': 2.6003, 'learning_rate': 1.6301698431220015e-07, 'epoch': 5.95}

 37%|███▋      | 23020/61904 [1:25:01<14:52:30,  1.38s/it]
 37%|███▋      | 23021/61904 [1:25:02<15:05:21,  1.40s/it]
 37%|███▋      | 23022/61904 [1:25:04<15:01:52,  1.39s/it]
 37%|███▋      | 23023/61904 [1:25:05<15:02:32,  1.39s/it]
 37%|███▋      | 23024/61904 [1:25:07<14:54:19,  1.38s/it]
 37%|███▋      | 23025/61904 [1:25:08<14:30:11,  1.34s/it]
 37%|███▋      | 23026/61904 [1:25:09<14:33:39,  1.35s/it]
 37%|███▋      | 23027/61904 [1:25:11<14:40:28,  1.36s/it]
 37%|███▋      | 23028/61904 [1:25:12<15:02:56,  1.39s/it]
 37%|███▋      | 23029/61904 [1:25:13<14:35:28,  1.35s/it]
 37%|███▋      | 23030/61904 [1:25:15<14:58:51,  1.39s/it]
 37%|███▋      | 23031/61904 [1:25:16<14:48:31,  1.37s/it]
 37%|███▋      | 23032/61904 [1:25:18<15:17:20,  1.42s/it]
 37%|███▋      | 23033/61904 [1:25:19<15:24:42,  1.43s/it]
 37%|███▋      | 23034/61904 [1:25:20<15:30:29,  1.44s/it]
 37%|███▋      | 23035/61904 [1:25:22<14:41:12,  1.36s/it]
 37%|███▋      | 23036/61904 [1:25:23<15:35:12,  1.44s/it]
 37%|███▋      | 23037/61904 [1:25:25<15:11:40,  1.41s/it]
 37%|███▋      | 23038/61904 [1:25:26<14:50:38,  1.37s/it]
 37%|███▋      | 23039/61904 [1:25:27<14:39:25,  1.36s/it]
 37%|███▋      | 23040/61904 [1:25:29<14:23:29,  1.33s/it]
                                                          
{'loss': 2.6595, 'learning_rate': 1.6298457150265784e-07, 'epoch': 5.95}

 37%|███▋      | 23040/61904 [1:25:29<14:23:29,  1.33s/it]
 37%|███▋      | 23041/61904 [1:25:30<14:27:07,  1.34s/it]
 37%|███▋      | 23042/61904 [1:25:31<14:26:39,  1.34s/it]
 37%|███▋      | 23043/61904 [1:25:33<14:45:42,  1.37s/it]
 37%|███▋      | 23044/61904 [1:25:34<15:12:29,  1.41s/it]
 37%|███▋      | 23045/61904 [1:25:35<14:43:51,  1.36s/it]
 37%|███▋      | 23046/61904 [1:25:37<14:50:00,  1.37s/it]
 37%|███▋      | 23047/61904 [1:25:38<14:32:21,  1.35s/it]
 37%|███▋      | 23048/61904 [1:25:40<14:51:43,  1.38s/it]
 37%|███▋      | 23049/61904 [1:25:41<14:53:08,  1.38s/it]
 37%|███▋      | 23050/61904 [1:25:42<14:39:53,  1.36s/it]
 37%|███▋      | 23051/61904 [1:25:44<14:31:34,  1.35s/it]
 37%|███▋      | 23052/61904 [1:25:45<14:37:31,  1.36s/it]
 37%|███▋      | 23053/61904 [1:25:46<14:36:59,  1.35s/it]
 37%|███▋      | 23054/61904 [1:25:48<14:38:03,  1.36s/it]
 37%|███▋      | 23055/61904 [1:25:49<14:47:40,  1.37s/it]
 37%|███▋      | 23056/61904 [1:25:50<14:47:46,  1.37s/it]
 37%|███▋      | 23057/61904 [1:25:52<15:08:21,  1.40s/it]
 37%|███▋      | 23058/61904 [1:25:53<15:08:51,  1.40s/it]
 37%|███▋      | 23059/61904 [1:25:55<15:27:18,  1.43s/it]
 37%|███▋      | 23060/61904 [1:25:56<15:00:40,  1.39s/it]
                                                          
{'loss': 2.6563, 'learning_rate': 1.6295215869311553e-07, 'epoch': 5.96}

 37%|███▋      | 23060/61904 [1:25:56<15:00:40,  1.39s/it]
 37%|███▋      | 23061/61904 [1:25:57<14:56:37,  1.39s/it]
 37%|███▋      | 23062/61904 [1:25:59<15:24:40,  1.43s/it]
 37%|███▋      | 23063/61904 [1:26:00<15:07:01,  1.40s/it]
 37%|███▋      | 23064/61904 [1:26:02<15:10:00,  1.41s/it]
 37%|███▋      | 23065/61904 [1:26:03<14:50:24,  1.38s/it]
 37%|███▋      | 23066/61904 [1:26:04<14:51:41,  1.38s/it]
 37%|███▋      | 23067/61904 [1:26:06<14:34:13,  1.35s/it]
 37%|███▋      | 23068/61904 [1:26:07<14:27:11,  1.34s/it]
 37%|███▋      | 23069/61904 [1:26:09<15:03:40,  1.40s/it]
 37%|███▋      | 23070/61904 [1:26:10<15:07:01,  1.40s/it]
 37%|███▋      | 23071/61904 [1:26:11<14:49:26,  1.37s/it]
 37%|███▋      | 23072/61904 [1:26:13<15:01:32,  1.39s/it]
 37%|███▋      | 23073/61904 [1:26:14<15:05:56,  1.40s/it]
 37%|███▋      | 23074/61904 [1:26:16<15:10:06,  1.41s/it]
 37%|███▋      | 23075/61904 [1:26:17<14:49:03,  1.37s/it]
 37%|███▋      | 23076/61904 [1:26:18<15:06:44,  1.40s/it]
 37%|███▋      | 23077/61904 [1:26:20<14:57:40,  1.39s/it]
 37%|███▋      | 23078/61904 [1:26:21<14:48:30,  1.37s/it]
 37%|███▋      | 23079/61904 [1:26:22<15:10:59,  1.41s/it]
 37%|███▋      | 23080/61904 [1:26:24<15:24:13,  1.43s/it]
                                                          
{'loss': 2.6499, 'learning_rate': 1.6291974588357316e-07, 'epoch': 5.97}

 37%|███▋      | 23080/61904 [1:26:24<15:24:13,  1.43s/it]
 37%|███▋      | 23081/61904 [1:26:25<15:25:55,  1.43s/it]
 37%|███▋      | 23082/61904 [1:26:27<15:47:41,  1.46s/it]
 37%|███▋      | 23083/61904 [1:26:28<15:20:39,  1.42s/it]
 37%|███▋      | 23084/61904 [1:26:30<14:57:09,  1.39s/it]
 37%|███▋      | 23085/61904 [1:26:31<14:44:42,  1.37s/it]
 37%|███▋      | 23086/61904 [1:26:32<14:55:25,  1.38s/it]
 37%|███▋      | 23087/61904 [1:26:34<15:12:06,  1.41s/it]
 37%|███▋      | 23088/61904 [1:26:35<15:13:49,  1.41s/it]
 37%|███▋      | 23089/61904 [1:26:37<15:21:14,  1.42s/it]
 37%|███▋      | 23090/61904 [1:26:38<15:32:28,  1.44s/it]
 37%|███▋      | 23091/61904 [1:26:40<15:49:57,  1.47s/it]
 37%|███▋      | 23092/61904 [1:26:41<16:09:24,  1.50s/it]
 37%|███▋      | 23093/61904 [1:26:43<15:31:41,  1.44s/it]
 37%|███▋      | 23094/61904 [1:26:44<15:24:14,  1.43s/it]
 37%|███▋      | 23095/61904 [1:26:45<15:26:36,  1.43s/it]
 37%|███▋      | 23096/61904 [1:26:47<14:53:58,  1.38s/it]
 37%|███▋      | 23097/61904 [1:26:48<15:12:49,  1.41s/it]
 37%|███▋      | 23098/61904 [1:26:49<14:55:17,  1.38s/it]
 37%|███▋      | 23099/61904 [1:26:51<15:46:41,  1.46s/it]
 37%|███▋      | 23100/61904 [1:26:52<15:33:17,  1.44s/it]
                                                          
{'loss': 2.6836, 'learning_rate': 1.6288733307403085e-07, 'epoch': 5.97}

 37%|███▋      | 23100/61904 [1:26:53<15:33:17,  1.44s/it]
 37%|███▋      | 23101/61904 [1:26:54<15:21:55,  1.43s/it]
 37%|███▋      | 23102/61904 [1:26:55<14:43:31,  1.37s/it]
 37%|███▋      | 23103/61904 [1:26:56<14:25:16,  1.34s/it]
 37%|███▋      | 23104/61904 [1:26:58<14:24:09,  1.34s/it]
 37%|███▋      | 23105/61904 [1:26:59<14:22:33,  1.33s/it]
 37%|███▋      | 23106/61904 [1:27:00<14:40:33,  1.36s/it]
 37%|███▋      | 23107/61904 [1:27:02<14:12:29,  1.32s/it]
 37%|███▋      | 23108/61904 [1:27:03<14:24:10,  1.34s/it]
 37%|███▋      | 23109/61904 [1:27:04<14:35:40,  1.35s/it]
 37%|███▋      | 23110/61904 [1:27:06<14:36:57,  1.36s/it]
 37%|███▋      | 23111/61904 [1:27:07<14:31:13,  1.35s/it]
 37%|███▋      | 23112/61904 [1:27:08<14:26:53,  1.34s/it]
 37%|███▋      | 23113/61904 [1:27:10<14:19:07,  1.33s/it]
 37%|███▋      | 23114/61904 [1:27:11<15:12:39,  1.41s/it]
 37%|███▋      | 23115/61904 [1:27:13<15:20:42,  1.42s/it]
 37%|███▋      | 23116/61904 [1:27:14<15:20:23,  1.42s/it]
 37%|███▋      | 23117/61904 [1:27:16<15:28:49,  1.44s/it]
 37%|███▋      | 23118/61904 [1:27:17<15:06:26,  1.40s/it]
 37%|███▋      | 23119/61904 [1:27:18<15:08:53,  1.41s/it]
 37%|███▋      | 23120/61904 [1:27:20<14:55:14,  1.38s/it]
                                                          
{'loss': 2.6193, 'learning_rate': 1.6285492026448854e-07, 'epoch': 5.98}

 37%|███▋      | 23120/61904 [1:27:20<14:55:14,  1.38s/it]
 37%|███▋      | 23121/61904 [1:27:21<15:16:47,  1.42s/it]
 37%|███▋      | 23122/61904 [1:27:23<15:39:36,  1.45s/it]
 37%|███▋      | 23123/61904 [1:27:24<15:17:56,  1.42s/it]
 37%|███▋      | 23124/61904 [1:27:26<15:25:58,  1.43s/it]
 37%|███▋      | 23125/61904 [1:27:27<15:28:20,  1.44s/it]
 37%|███▋      | 23126/61904 [1:27:28<15:07:37,  1.40s/it]
 37%|███▋      | 23127/61904 [1:27:30<15:07:21,  1.40s/it]
 37%|███▋      | 23128/61904 [1:27:31<15:15:57,  1.42s/it]
 37%|███▋      | 23129/61904 [1:27:33<15:21:20,  1.43s/it]
 37%|███▋      | 23130/61904 [1:27:34<15:22:29,  1.43s/it]
 37%|███▋      | 23131/61904 [1:27:36<15:18:42,  1.42s/it]
 37%|███▋      | 23132/61904 [1:27:37<15:02:47,  1.40s/it]
 37%|███▋      | 23133/61904 [1:27:38<15:05:16,  1.40s/it]
 37%|███▋      | 23134/61904 [1:27:40<14:45:28,  1.37s/it]
 37%|███▋      | 23135/61904 [1:27:41<14:33:44,  1.35s/it]
 37%|███▋      | 23136/61904 [1:27:42<14:49:28,  1.38s/it]
 37%|███▋      | 23137/61904 [1:27:44<14:44:07,  1.37s/it]
 37%|███▋      | 23138/61904 [1:27:45<15:33:37,  1.45s/it]
 37%|███▋      | 23139/61904 [1:27:47<15:29:25,  1.44s/it]
 37%|███▋      | 23140/61904 [1:27:48<15:19:58,  1.42s/it]
                                                          
{'loss': 2.6293, 'learning_rate': 1.6282250745494617e-07, 'epoch': 5.98}

 37%|███▋      | 23140/61904 [1:27:48<15:19:58,  1.42s/it]
 37%|███▋      | 23141/61904 [1:27:50<15:21:42,  1.43s/it]
 37%|███▋      | 23142/61904 [1:27:51<15:05:42,  1.40s/it]
 37%|███▋      | 23143/61904 [1:27:52<15:16:28,  1.42s/it]
 37%|███▋      | 23144/61904 [1:27:54<15:38:44,  1.45s/it]
 37%|███▋      | 23145/61904 [1:27:55<15:12:57,  1.41s/it]
 37%|███▋      | 23146/61904 [1:27:57<15:05:17,  1.40s/it]
 37%|███▋      | 23147/61904 [1:27:58<15:11:24,  1.41s/it]
 37%|███▋      | 23148/61904 [1:27:59<15:17:07,  1.42s/it]
 37%|███▋      | 23149/61904 [1:28:01<15:55:08,  1.48s/it]
 37%|███▋      | 23150/61904 [1:28:02<15:39:31,  1.45s/it]
 37%|███▋      | 23151/61904 [1:28:04<15:25:25,  1.43s/it]
 37%|███▋      | 23152/61904 [1:28:05<15:04:05,  1.40s/it]
 37%|███▋      | 23153/61904 [1:28:07<15:35:34,  1.45s/it]
 37%|███▋      | 23154/61904 [1:28:08<15:16:48,  1.42s/it]
 37%|███▋      | 23155/61904 [1:28:10<15:43:18,  1.46s/it]
 37%|███▋      | 23156/61904 [1:28:11<15:58:09,  1.48s/it]
 37%|███▋      | 23157/61904 [1:28:12<15:20:51,  1.43s/it]
 37%|███▋      | 23158/61904 [1:28:14<15:07:38,  1.41s/it]
 37%|███▋      | 23159/61904 [1:28:15<15:08:53,  1.41s/it]
 37%|███▋      | 23160/61904 [1:28:17<14:38:34,  1.36s/it]
                                                          
{'loss': 2.7275, 'learning_rate': 1.6279009464540386e-07, 'epoch': 5.99}

 37%|███▋      | 23160/61904 [1:28:17<14:38:34,  1.36s/it]
 37%|███▋      | 23161/61904 [1:28:18<14:55:10,  1.39s/it]
 37%|███▋      | 23162/61904 [1:28:19<14:56:32,  1.39s/it]
 37%|███▋      | 23163/61904 [1:28:21<14:41:08,  1.36s/it]
 37%|███▋      | 23164/61904 [1:28:22<14:16:56,  1.33s/it]
 37%|███▋      | 23165/61904 [1:28:23<14:18:58,  1.33s/it]
 37%|███▋      | 23166/61904 [1:28:25<14:56:09,  1.39s/it]
 37%|███▋      | 23167/61904 [1:28:26<14:59:50,  1.39s/it]
 37%|███▋      | 23168/61904 [1:28:28<15:04:35,  1.40s/it]
 37%|███▋      | 23169/61904 [1:28:29<14:53:00,  1.38s/it]
 37%|███▋      | 23170/61904 [1:28:31<15:41:05,  1.46s/it]
 37%|███▋      | 23171/61904 [1:28:32<16:07:31,  1.50s/it]
 37%|███▋      | 23172/61904 [1:28:33<15:19:27,  1.42s/it]
 37%|███▋      | 23173/61904 [1:28:35<15:00:11,  1.39s/it]
 37%|███▋      | 23174/61904 [1:28:36<14:55:04,  1.39s/it]
 37%|███▋      | 23175/61904 [1:28:37<14:49:30,  1.38s/it]
 37%|███▋      | 23176/61904 [1:28:39<14:36:24,  1.36s/it]
 37%|███▋      | 23177/61904 [1:28:40<14:53:45,  1.38s/it]
 37%|███▋      | 23178/61904 [1:28:42<15:21:20,  1.43s/it]
 37%|███▋      | 23179/61904 [1:28:43<15:21:35,  1.43s/it]
 37%|███▋      | 23180/61904 [1:28:45<15:16:31,  1.42s/it]
                                                          
{'loss': 2.6021, 'learning_rate': 1.6275768183586152e-07, 'epoch': 5.99}

 37%|███▋      | 23180/61904 [1:28:45<15:16:31,  1.42s/it]
 37%|███▋      | 23181/61904 [1:28:46<15:15:03,  1.42s/it]
 37%|███▋      | 23182/61904 [1:28:47<15:00:29,  1.40s/it]
 37%|███▋      | 23183/61904 [1:28:49<15:08:06,  1.41s/it]
 37%|███▋      | 23184/61904 [1:28:50<14:48:32,  1.38s/it]
 37%|███▋      | 23185/61904 [1:28:51<14:58:57,  1.39s/it]
 37%|███▋      | 23186/61904 [1:28:53<15:02:23,  1.40s/it]
 37%|███▋      | 23187/61904 [1:28:54<15:18:19,  1.42s/it]
 37%|███▋      | 23188/61904 [1:28:56<15:10:19,  1.41s/it]
 37%|███▋      | 23189/61904 [1:28:57<15:17:14,  1.42s/it]
 37%|███▋      | 23190/61904 [1:28:59<14:55:50,  1.39s/it]
 37%|███▋      | 23191/61904 [1:29:00<14:43:19,  1.37s/it]
 37%|███▋      | 23192/61904 [1:29:01<14:25:35,  1.34s/it]
 37%|███▋      | 23193/61904 [1:29:02<14:21:57,  1.34s/it]
 37%|███▋      | 23194/61904 [1:29:04<14:46:49,  1.37s/it]
 37%|███▋      | 23195/61904 [1:29:05<14:36:05,  1.36s/it]
 37%|███▋      | 23196/61904 [1:29:07<14:39:22,  1.36s/it]
 37%|███▋      | 23197/61904 [1:29:08<14:37:28,  1.36s/it]
 37%|███▋      | 23198/61904 [1:29:09<14:25:58,  1.34s/it]
 37%|███▋      | 23199/61904 [1:29:11<14:28:53,  1.35s/it]
 37%|███▋      | 23200/61904 [1:29:12<14:36:11,  1.36s/it]
                                                          
{'loss': 2.6331, 'learning_rate': 1.6272526902631919e-07, 'epoch': 6.0}

 37%|███▋      | 23200/61904 [1:29:12<14:36:11,  1.36s/it]
 37%|███▋      | 23201/61904 [1:29:13<14:37:08,  1.36s/it]
 37%|███▋      | 23202/61904 [1:29:15<14:28:00,  1.35s/it]
 37%|███▋      | 23203/61904 [1:29:16<14:45:22,  1.37s/it]
 37%|███▋      | 23204/61904 [1:29:18<15:06:48,  1.41s/it]
 37%|███▋      | 23205/61904 [1:29:19<15:27:28,  1.44s/it]
 37%|███▋      | 23206/61904 [1:29:21<16:16:15,  1.51s/it]
 37%|███▋      | 23207/61904 [1:29:22<15:52:02,  1.48s/it]
 37%|███▋      | 23208/61904 [1:29:24<15:35:06,  1.45s/it]
 37%|███▋      | 23209/61904 [1:29:25<15:00:17,  1.40s/it]
 37%|███▋      | 23210/61904 [1:29:26<14:58:50,  1.39s/it]
 37%|███▋      | 23211/61904 [1:29:28<14:59:14,  1.39s/it]
 37%|███▋      | 23212/61904 [1:29:29<14:54:46,  1.39s/it]
 37%|███▋      | 23213/61904 [1:29:30<14:45:11,  1.37s/it]
 38%|███▊      | 23214/61904 [1:29:32<15:10:34,  1.41s/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<07:50,  1.83it/s]

  0%|          | 3/861 [00:02<12:23,  1.15it/s]

  0%|          | 4/861 [00:04<20:26,  1.43s/it]

  1%|          | 5/861 [00:06<20:54,  1.47s/it]

  1%|          | 6/861 [00:07<21:33,  1.51s/it]

  1%|          | 7/861 [00:08<18:15,  1.28s/it]

  1%|          | 8/861 [00:10<21:12,  1.49s/it]

  1%|          | 9/861 [00:11<19:57,  1.41s/it]

  1%|          | 10/861 [00:13<19:43,  1.39s/it]

  1%|▏         | 11/861 [00:15<25:18,  1.79s/it]

  1%|▏         | 12/861 [00:16<21:15,  1.50s/it]

  2%|▏         | 13/861 [00:18<22:40,  1.60s/it]

  2%|▏         | 14/861 [00:19<19:22,  1.37s/it]

  2%|▏         | 15/861 [00:20<18:24,  1.31s/it]

  2%|▏         | 16/861 [00:21<17:21,  1.23s/it]

  2%|▏         | 17/861 [00:23<18:55,  1.35s/it]

  2%|▏         | 18/861 [00:24<17:04,  1.22s/it]

  2%|▏         | 19/861 [00:26<20:02,  1.43s/it]

  2%|▏         | 20/861 [00:28<24:25,  1.74s/it]

  2%|▏         | 21/861 [00:30<24:11,  1.73s/it]

  3%|▎         | 22/861 [00:31<21:25,  1.53s/it]

  3%|▎         | 23/861 [00:32<19:09,  1.37s/it]

  3%|▎         | 24/861 [00:35<25:00,  1.79s/it]

  3%|▎         | 25/861 [00:36<23:49,  1.71s/it]

  3%|▎         | 26/861 [00:37<22:08,  1.59s/it]

  3%|▎         | 27/861 [00:39<23:31,  1.69s/it]

  3%|▎         | 28/861 [00:41<22:30,  1.62s/it]

  3%|▎         | 29/861 [00:42<19:15,  1.39s/it]

  3%|▎         | 30/861 [00:43<18:14,  1.32s/it]

  4%|▎         | 31/861 [00:43<14:21,  1.04s/it]

  4%|▎         | 32/861 [00:44<11:45,  1.18it/s]

  4%|▍         | 33/861 [00:46<16:52,  1.22s/it]

  4%|▍         | 34/861 [00:47<17:16,  1.25s/it]

  4%|▍         | 35/861 [00:49<20:08,  1.46s/it]

  4%|▍         | 36/861 [00:50<20:10,  1.47s/it]

  4%|▍         | 37/861 [00:52<21:39,  1.58s/it]

  4%|▍         | 38/861 [00:54<20:38,  1.50s/it]

  5%|▍         | 39/861 [00:56<22:23,  1.63s/it]

  5%|▍         | 40/861 [00:56<18:59,  1.39s/it]

  5%|▍         | 41/861 [00:57<14:46,  1.08s/it]

  5%|▍         | 42/861 [00:58<14:21,  1.05s/it]

  5%|▍         | 43/861 [01:00<19:08,  1.40s/it]

  5%|▌         | 44/861 [01:01<17:04,  1.25s/it]

  5%|▌         | 45/861 [01:02<15:46,  1.16s/it]

  5%|▌         | 46/861 [01:03<16:51,  1.24s/it]

  5%|▌         | 47/861 [01:05<16:58,  1.25s/it]

  6%|▌         | 48/861 [01:07<20:36,  1.52s/it]

  6%|▌         | 49/861 [01:09<22:32,  1.67s/it]

  6%|▌         | 50/861 [01:09<16:49,  1.24s/it]

  6%|▌         | 51/861 [01:10<15:33,  1.15s/it]

  6%|▌         | 52/861 [01:11<13:39,  1.01s/it]

  6%|▌         | 53/861 [01:11<12:27,  1.08it/s]

  6%|▋         | 54/861 [01:12<10:35,  1.27it/s]

  6%|▋         | 55/861 [01:13<12:03,  1.11it/s]

  7%|▋         | 56/861 [01:14<11:52,  1.13it/s]

  7%|▋         | 57/861 [01:15<11:55,  1.12it/s]

  7%|▋         | 58/861 [01:15<09:41,  1.38it/s]

  7%|▋         | 59/861 [01:16<11:06,  1.20it/s]

  7%|▋         | 60/861 [01:18<15:05,  1.13s/it]

  7%|▋         | 61/861 [01:19<15:08,  1.14s/it]

  7%|▋         | 62/861 [01:20<13:40,  1.03s/it]

  7%|▋         | 63/861 [01:21<15:37,  1.17s/it]

  7%|▋         | 64/861 [01:22<15:21,  1.16s/it]

  8%|▊         | 65/861 [01:23<13:56,  1.05s/it]

  8%|▊         | 66/861 [01:24<11:40,  1.13it/s]

  8%|▊         | 67/861 [01:26<16:29,  1.25s/it]

  8%|▊         | 68/861 [01:29<22:51,  1.73s/it]

  8%|▊         | 69/861 [01:30<20:58,  1.59s/it]

  8%|▊         | 70/861 [01:32<21:02,  1.60s/it]

  8%|▊         | 71/861 [01:34<24:02,  1.83s/it]

  8%|▊         | 72/861 [01:35<20:44,  1.58s/it]

  8%|▊         | 73/861 [01:35<15:46,  1.20s/it]

  9%|▊         | 74/861 [01:38<21:20,  1.63s/it]

  9%|▊         | 75/861 [01:39<19:50,  1.51s/it]

  9%|▉         | 76/861 [01:41<20:07,  1.54s/it]

  9%|▉         | 77/861 [01:44<25:25,  1.95s/it]

  9%|▉         | 78/861 [01:45<23:32,  1.80s/it]

  9%|▉         | 79/861 [01:46<19:11,  1.47s/it]

  9%|▉         | 80/861 [01:46<15:23,  1.18s/it]

  9%|▉         | 81/861 [01:48<17:54,  1.38s/it]

 10%|▉         | 82/861 [01:49<16:24,  1.26s/it]

 10%|▉         | 83/861 [01:51<18:40,  1.44s/it]

 10%|▉         | 84/861 [01:53<20:26,  1.58s/it]

 10%|▉         | 85/861 [01:54<16:58,  1.31s/it]

 10%|▉         | 86/861 [01:54<14:26,  1.12s/it]

 10%|█         | 87/861 [01:57<20:26,  1.59s/it]

 10%|█         | 88/861 [01:57<15:16,  1.19s/it]

 10%|█         | 89/861 [01:59<17:14,  1.34s/it]

 10%|█         | 90/861 [02:03<28:25,  2.21s/it]

 11%|█         | 91/861 [02:05<26:25,  2.06s/it]

 11%|█         | 92/861 [02:07<25:19,  1.98s/it]

 11%|█         | 93/861 [02:10<30:08,  2.36s/it]

 11%|█         | 94/861 [02:10<22:06,  1.73s/it]

 11%|█         | 95/861 [02:11<17:20,  1.36s/it]

 11%|█         | 96/861 [02:13<19:43,  1.55s/it]

 11%|█▏        | 97/861 [02:14<20:08,  1.58s/it]

 11%|█▏        | 98/861 [02:16<19:56,  1.57s/it]

 11%|█▏        | 99/861 [02:17<19:01,  1.50s/it]

 12%|█▏        | 100/861 [02:18<15:32,  1.23s/it]

 12%|█▏        | 101/861 [02:19<14:49,  1.17s/it]

 12%|█▏        | 102/861 [02:20<15:35,  1.23s/it]

 12%|█▏        | 103/861 [02:21<12:29,  1.01it/s]

 12%|█▏        | 104/861 [02:21<11:48,  1.07it/s]

 12%|█▏        | 105/861 [02:22<10:17,  1.22it/s]

 12%|█▏        | 106/861 [02:23<09:26,  1.33it/s]

 12%|█▏        | 107/861 [02:23<08:41,  1.45it/s]

 13%|█▎        | 108/861 [02:23<07:06,  1.76it/s]

 13%|█▎        | 109/861 [02:24<06:02,  2.07it/s]

 13%|█▎        | 110/861 [02:25<11:10,  1.12it/s]

 13%|█▎        | 111/861 [02:27<11:56,  1.05it/s]

 13%|█▎        | 112/861 [02:27<11:23,  1.10it/s]

 13%|█▎        | 113/861 [02:29<13:35,  1.09s/it]

 13%|█▎        | 114/861 [02:31<19:02,  1.53s/it]

 13%|█▎        | 115/861 [02:32<17:08,  1.38s/it]

 13%|█▎        | 116/861 [02:33<15:45,  1.27s/it]

 14%|█▎        | 117/861 [02:37<23:00,  1.86s/it]

 14%|█▎        | 118/861 [02:37<18:08,  1.46s/it]

 14%|█▍        | 119/861 [02:38<15:06,  1.22s/it]

 14%|█▍        | 120/861 [02:38<11:26,  1.08it/s]

 14%|█▍        | 121/861 [02:40<14:47,  1.20s/it]

 14%|█▍        | 122/861 [02:41<14:12,  1.15s/it]

 14%|█▍        | 123/861 [02:42<15:02,  1.22s/it]

 14%|█▍        | 124/861 [02:44<16:25,  1.34s/it]

 15%|█▍        | 125/861 [02:46<19:41,  1.60s/it]

 15%|█▍        | 126/861 [02:48<19:43,  1.61s/it]

 15%|█▍        | 127/861 [02:50<21:11,  1.73s/it]

 15%|█▍        | 128/861 [02:52<20:43,  1.70s/it]

 15%|█▍        | 129/861 [02:53<19:36,  1.61s/it]

 15%|█▌        | 130/861 [02:55<20:09,  1.65s/it]

 15%|█▌        | 131/861 [02:56<20:26,  1.68s/it]

 15%|█▌        | 132/861 [02:57<17:33,  1.44s/it]

 15%|█▌        | 133/861 [03:00<20:31,  1.69s/it]

 16%|█▌        | 134/861 [03:00<15:17,  1.26s/it]

 16%|█▌        | 135/861 [03:01<13:41,  1.13s/it]

 16%|█▌        | 136/861 [03:02<14:05,  1.17s/it]

 16%|█▌        | 137/861 [03:03<14:47,  1.23s/it]

 16%|█▌        | 138/861 [03:05<14:54,  1.24s/it]

 16%|█▌        | 139/861 [03:06<14:19,  1.19s/it]

 16%|█▋        | 140/861 [03:07<13:26,  1.12s/it]

 16%|█▋        | 141/861 [03:08<14:24,  1.20s/it]

 16%|█▋        | 142/861 [03:08<11:25,  1.05it/s]

 17%|█▋        | 143/861 [03:14<29:35,  2.47s/it]

 17%|█▋        | 144/861 [03:17<30:29,  2.55s/it]

 17%|█▋        | 145/861 [03:18<25:50,  2.17s/it]

 17%|█▋        | 146/861 [03:20<24:29,  2.06s/it]

 17%|█▋        | 147/861 [03:21<20:14,  1.70s/it]

 17%|█▋        | 148/861 [03:22<16:07,  1.36s/it]

 17%|█▋        | 149/861 [03:22<12:34,  1.06s/it]

 17%|█▋        | 150/861 [03:25<18:03,  1.52s/it]

 18%|█▊        | 151/861 [03:26<18:46,  1.59s/it]

 18%|█▊        | 152/861 [03:28<17:36,  1.49s/it]

 18%|█▊        | 153/861 [03:30<19:42,  1.67s/it]

 18%|█▊        | 154/861 [03:32<20:21,  1.73s/it]

 18%|█▊        | 155/861 [03:34<24:32,  2.09s/it]

 18%|█▊        | 156/861 [03:37<25:49,  2.20s/it]

 18%|█▊        | 157/861 [03:38<21:55,  1.87s/it]

 18%|█▊        | 158/861 [03:42<27:43,  2.37s/it]

 18%|█▊        | 159/861 [03:43<25:29,  2.18s/it]

 19%|█▊        | 160/861 [03:45<23:29,  2.01s/it]

 19%|█▊        | 161/861 [03:47<23:31,  2.02s/it]

 19%|█▉        | 162/861 [03:47<17:25,  1.50s/it]

 19%|█▉        | 163/861 [03:47<13:04,  1.12s/it]

 19%|█▉        | 164/861 [03:50<17:40,  1.52s/it]

 19%|█▉        | 165/861 [03:53<21:59,  1.90s/it]

 19%|█▉        | 166/861 [03:55<23:57,  2.07s/it]

 19%|█▉        | 167/861 [03:55<17:46,  1.54s/it]

 20%|█▉        | 168/861 [03:56<13:35,  1.18s/it]

 20%|█▉        | 169/861 [03:57<14:39,  1.27s/it]

 20%|█▉        | 170/861 [03:58<13:25,  1.17s/it]

 20%|█▉        | 171/861 [03:59<13:40,  1.19s/it]

 20%|█▉        | 172/861 [04:00<12:59,  1.13s/it]

 20%|██        | 173/861 [04:03<17:37,  1.54s/it]

 20%|██        | 174/861 [04:05<20:08,  1.76s/it]

 20%|██        | 175/861 [04:07<20:21,  1.78s/it]

 20%|██        | 176/861 [04:07<15:05,  1.32s/it]

 21%|██        | 177/861 [04:08<13:04,  1.15s/it]

 21%|██        | 178/861 [04:09<12:12,  1.07s/it]

 21%|██        | 179/861 [04:11<15:06,  1.33s/it]

 21%|██        | 180/861 [04:12<16:05,  1.42s/it]

 21%|██        | 181/861 [04:13<12:51,  1.13s/it]

 21%|██        | 182/861 [04:13<10:10,  1.11it/s]

 21%|██▏       | 183/861 [04:15<13:28,  1.19s/it]

 21%|██▏       | 184/861 [04:17<14:49,  1.31s/it]

 21%|██▏       | 185/861 [04:18<15:36,  1.39s/it]

 22%|██▏       | 186/861 [04:19<13:15,  1.18s/it]

 22%|██▏       | 187/861 [04:21<15:45,  1.40s/it]

 22%|██▏       | 188/861 [04:23<19:23,  1.73s/it]

 22%|██▏       | 189/861 [04:25<18:12,  1.63s/it]

 22%|██▏       | 190/861 [04:26<15:45,  1.41s/it]

 22%|██▏       | 191/861 [04:26<12:31,  1.12s/it]

 22%|██▏       | 192/861 [04:28<15:18,  1.37s/it]

 22%|██▏       | 193/861 [04:30<15:40,  1.41s/it]

 23%|██▎       | 194/861 [04:30<13:47,  1.24s/it]

 23%|██▎       | 195/861 [04:31<10:54,  1.02it/s]

 23%|██▎       | 196/861 [04:31<09:22,  1.18it/s]

 23%|██▎       | 197/861 [04:33<11:08,  1.01s/it]

 23%|██▎       | 198/861 [04:34<12:22,  1.12s/it]

 23%|██▎       | 199/861 [04:36<15:37,  1.42s/it]

 23%|██▎       | 200/861 [04:38<16:39,  1.51s/it]

 23%|██▎       | 201/861 [04:39<16:04,  1.46s/it]

 23%|██▎       | 202/861 [04:40<14:34,  1.33s/it]

 24%|██▎       | 203/861 [04:42<15:58,  1.46s/it]

 24%|██▎       | 204/861 [04:42<11:56,  1.09s/it]

 24%|██▍       | 205/861 [04:43<11:19,  1.04s/it]

 24%|██▍       | 206/861 [04:44<11:11,  1.02s/it]

 24%|██▍       | 207/861 [04:45<10:20,  1.05it/s]

 24%|██▍       | 208/861 [04:46<12:03,  1.11s/it]

 24%|██▍       | 209/861 [04:47<11:36,  1.07s/it]

 24%|██▍       | 210/861 [04:49<12:42,  1.17s/it]

 25%|██▍       | 211/861 [04:50<13:28,  1.24s/it]

 25%|██▍       | 212/861 [04:52<14:54,  1.38s/it]

 25%|██▍       | 213/861 [04:53<14:44,  1.37s/it]

 25%|██▍       | 214/861 [04:55<14:48,  1.37s/it]

 25%|██▍       | 215/861 [04:56<13:37,  1.27s/it]

 25%|██▌       | 216/861 [04:56<11:17,  1.05s/it]

 25%|██▌       | 217/861 [04:57<10:34,  1.02it/s]

 25%|██▌       | 218/861 [04:57<08:33,  1.25it/s]

 25%|██▌       | 219/861 [04:58<09:16,  1.15it/s]

 26%|██▌       | 220/861 [05:00<11:53,  1.11s/it]

 26%|██▌       | 221/861 [05:01<11:42,  1.10s/it]

 26%|██▌       | 222/861 [05:03<15:11,  1.43s/it]

 26%|██▌       | 223/861 [05:05<15:36,  1.47s/it]

 26%|██▌       | 224/861 [05:06<13:19,  1.25s/it]

 26%|██▌       | 225/861 [05:08<17:07,  1.61s/it]

 26%|██▌       | 226/861 [05:11<19:51,  1.88s/it]

 26%|██▋       | 227/861 [05:12<18:04,  1.71s/it]

 26%|██▋       | 228/861 [05:13<15:21,  1.46s/it]

 27%|██▋       | 229/861 [05:14<14:08,  1.34s/it]

 27%|██▋       | 230/861 [05:16<16:45,  1.59s/it]

 27%|██▋       | 231/861 [05:19<19:18,  1.84s/it]

 27%|██▋       | 232/861 [05:19<14:14,  1.36s/it]

 27%|██▋       | 233/861 [05:19<12:12,  1.17s/it]

 27%|██▋       | 234/861 [05:20<11:03,  1.06s/it]

 27%|██▋       | 235/861 [05:21<11:00,  1.05s/it]

 27%|██▋       | 236/861 [05:22<10:50,  1.04s/it]

 28%|██▊       | 237/861 [05:23<11:00,  1.06s/it]

 28%|██▊       | 238/861 [05:24<08:38,  1.20it/s]

 28%|██▊       | 239/861 [05:27<15:48,  1.53s/it]

 28%|██▊       | 240/861 [05:28<14:38,  1.41s/it]

 28%|██▊       | 241/861 [05:31<18:56,  1.83s/it]

 28%|██▊       | 242/861 [05:33<18:50,  1.83s/it]

 28%|██▊       | 243/861 [05:35<19:13,  1.87s/it]

 28%|██▊       | 244/861 [05:35<15:50,  1.54s/it]

 28%|██▊       | 245/861 [05:37<14:31,  1.42s/it]

 29%|██▊       | 246/861 [05:37<12:45,  1.25s/it]

 29%|██▊       | 247/861 [05:39<13:06,  1.28s/it]

 29%|██▉       | 248/861 [05:39<09:50,  1.04it/s]

 29%|██▉       | 249/861 [05:41<12:04,  1.18s/it]

 29%|██▉       | 250/861 [05:43<15:26,  1.52s/it]

 29%|██▉       | 251/861 [05:45<15:50,  1.56s/it]

 29%|██▉       | 252/861 [05:45<13:13,  1.30s/it]

 29%|██▉       | 253/861 [05:47<13:48,  1.36s/it]

 30%|██▉       | 254/861 [05:47<10:36,  1.05s/it]

 30%|██▉       | 255/861 [05:49<12:21,  1.22s/it]

 30%|██▉       | 256/861 [05:50<12:17,  1.22s/it]

 30%|██▉       | 257/861 [05:51<10:58,  1.09s/it]

 30%|██▉       | 258/861 [05:52<12:32,  1.25s/it]

 30%|███       | 259/861 [05:55<15:59,  1.59s/it]

 30%|███       | 260/861 [05:57<16:23,  1.64s/it]

 30%|███       | 261/861 [06:01<23:40,  2.37s/it]

 30%|███       | 262/861 [06:02<20:32,  2.06s/it]

 31%|███       | 263/861 [06:02<14:55,  1.50s/it]

 31%|███       | 264/861 [06:04<15:56,  1.60s/it]

 31%|███       | 265/861 [06:05<14:19,  1.44s/it]

 31%|███       | 266/861 [06:06<11:38,  1.17s/it]

 31%|███       | 267/861 [06:06<10:35,  1.07s/it]

 31%|███       | 268/861 [06:07<10:13,  1.04s/it]

 31%|███       | 269/861 [06:08<10:07,  1.03s/it]

 31%|███▏      | 270/861 [06:10<10:26,  1.06s/it]

 31%|███▏      | 271/861 [06:10<09:32,  1.03it/s]

 32%|███▏      | 272/861 [06:12<11:55,  1.22s/it]

 32%|███▏      | 273/861 [06:14<13:04,  1.33s/it]

 32%|███▏      | 274/861 [06:16<15:36,  1.60s/it]

 32%|███▏      | 275/861 [06:16<11:38,  1.19s/it]

 32%|███▏      | 276/861 [06:18<14:59,  1.54s/it]

 32%|███▏      | 277/861 [06:21<18:25,  1.89s/it]

 32%|███▏      | 278/861 [06:23<18:33,  1.91s/it]

 32%|███▏      | 279/861 [06:25<17:36,  1.81s/it]

 33%|███▎      | 280/861 [06:27<19:38,  2.03s/it]

 33%|███▎      | 281/861 [06:28<16:10,  1.67s/it]

 33%|███▎      | 282/861 [06:30<16:54,  1.75s/it]

 33%|███▎      | 283/861 [06:31<15:35,  1.62s/it]

 33%|███▎      | 284/861 [06:32<11:58,  1.25s/it]

 33%|███▎      | 285/861 [06:33<12:45,  1.33s/it]

 33%|███▎      | 286/861 [06:36<16:26,  1.72s/it]

 33%|███▎      | 287/861 [06:37<15:29,  1.62s/it]

 33%|███▎      | 288/861 [06:40<17:36,  1.84s/it]

 34%|███▎      | 289/861 [06:40<14:10,  1.49s/it]

 34%|███▎      | 290/861 [06:41<12:35,  1.32s/it]

 34%|███▍      | 291/861 [06:44<16:03,  1.69s/it]

 34%|███▍      | 292/861 [06:47<20:36,  2.17s/it]

 34%|███▍      | 293/861 [06:48<18:05,  1.91s/it]

 34%|███▍      | 294/861 [06:51<20:43,  2.19s/it]

 34%|███▍      | 295/861 [06:52<15:17,  1.62s/it]

 34%|███▍      | 296/861 [06:52<12:40,  1.35s/it]

 34%|███▍      | 297/861 [06:55<16:58,  1.81s/it]

 35%|███▍      | 298/861 [06:57<17:15,  1.84s/it]

 35%|███▍      | 299/861 [06:59<19:02,  2.03s/it]

 35%|███▍      | 300/861 [07:01<17:27,  1.87s/it]

 35%|███▍      | 301/861 [07:04<20:15,  2.17s/it]

 35%|███▌      | 302/861 [07:04<15:04,  1.62s/it]

 35%|███▌      | 303/861 [07:08<21:12,  2.28s/it]

 35%|███▌      | 304/861 [07:12<24:40,  2.66s/it]

 35%|███▌      | 305/861 [07:14<24:59,  2.70s/it]

 36%|███▌      | 306/861 [07:18<26:46,  2.89s/it]

 36%|███▌      | 307/861 [07:19<23:23,  2.53s/it]

 36%|███▌      | 308/861 [07:20<17:09,  1.86s/it]

 36%|███▌      | 309/861 [07:22<17:05,  1.86s/it]

 36%|███▌      | 310/861 [07:23<17:01,  1.85s/it]

 36%|███▌      | 311/861 [07:25<16:21,  1.79s/it]

 36%|███▌      | 312/861 [07:28<19:15,  2.10s/it]

 36%|███▋      | 313/861 [07:32<24:34,  2.69s/it]

 36%|███▋      | 314/861 [07:33<21:27,  2.35s/it]

 37%|███▋      | 315/861 [07:35<17:58,  1.97s/it]

 37%|███▋      | 316/861 [07:36<17:29,  1.93s/it]

 37%|███▋      | 317/861 [07:37<13:01,  1.44s/it]

 37%|███▋      | 318/861 [07:39<14:14,  1.57s/it]

 37%|███▋      | 319/861 [07:40<14:23,  1.59s/it]

 37%|███▋      | 320/861 [07:41<12:42,  1.41s/it]

 37%|███▋      | 321/861 [07:44<15:31,  1.72s/it]

 37%|███▋      | 322/861 [07:46<16:03,  1.79s/it]

 38%|███▊      | 323/861 [07:47<14:36,  1.63s/it]

 38%|███▊      | 324/861 [07:52<25:05,  2.80s/it]

 38%|███▊      | 325/861 [07:55<23:38,  2.65s/it]

 38%|███▊      | 326/861 [07:55<17:12,  1.93s/it]

 38%|███▊      | 327/861 [07:56<15:27,  1.74s/it]

 38%|███▊      | 328/861 [07:58<15:05,  1.70s/it]

 38%|███▊      | 329/861 [07:59<13:40,  1.54s/it]

 38%|███▊      | 330/861 [08:01<15:44,  1.78s/it]

 38%|███▊      | 331/861 [08:07<24:47,  2.81s/it]

 39%|███▊      | 332/861 [08:09<23:33,  2.67s/it]

 39%|███▊      | 333/861 [08:10<19:53,  2.26s/it]

 39%|███▉      | 334/861 [08:12<18:32,  2.11s/it]

 39%|███▉      | 335/861 [08:14<18:38,  2.13s/it]

 39%|███▉      | 336/861 [08:15<16:38,  1.90s/it]

 39%|███▉      | 337/861 [08:17<15:28,  1.77s/it]

 39%|███▉      | 338/861 [08:18<12:51,  1.48s/it]

 39%|███▉      | 339/861 [08:20<15:19,  1.76s/it]

 39%|███▉      | 340/861 [08:22<15:03,  1.73s/it]

 40%|███▉      | 341/861 [08:22<11:32,  1.33s/it]

 40%|███▉      | 342/861 [08:24<12:25,  1.44s/it]

 40%|███▉      | 343/861 [08:24<10:05,  1.17s/it]

 40%|███▉      | 344/861 [08:26<12:03,  1.40s/it]

 40%|████      | 345/861 [08:28<13:42,  1.59s/it]

 40%|████      | 346/861 [08:31<15:59,  1.86s/it]

 40%|████      | 347/861 [08:32<14:45,  1.72s/it]

 40%|████      | 348/861 [08:34<14:09,  1.66s/it]

 41%|████      | 349/861 [08:34<11:24,  1.34s/it]

 41%|████      | 350/861 [08:35<10:15,  1.20s/it]

 41%|████      | 351/861 [08:37<11:43,  1.38s/it]

 41%|████      | 352/861 [08:38<11:39,  1.37s/it]

 41%|████      | 353/861 [08:40<12:24,  1.47s/it]

 41%|████      | 354/861 [08:41<10:34,  1.25s/it]

 41%|████      | 355/861 [08:41<08:51,  1.05s/it]

 41%|████▏     | 356/861 [08:42<07:20,  1.15it/s]

 41%|████▏     | 357/861 [08:42<06:30,  1.29it/s]

 42%|████▏     | 358/861 [08:43<06:21,  1.32it/s]

 42%|████▏     | 359/861 [08:45<08:02,  1.04it/s]

 42%|████▏     | 360/861 [08:48<13:23,  1.60s/it]

 42%|████▏     | 361/861 [08:49<12:10,  1.46s/it]

 42%|████▏     | 362/861 [08:50<11:30,  1.38s/it]

 42%|████▏     | 363/861 [08:53<14:46,  1.78s/it]

 42%|████▏     | 364/861 [08:53<12:00,  1.45s/it]

 42%|████▏     | 365/861 [08:57<17:16,  2.09s/it]

 43%|████▎     | 366/861 [08:58<14:24,  1.75s/it]

 43%|████▎     | 367/861 [09:00<15:36,  1.90s/it]

 43%|████▎     | 368/861 [09:05<22:08,  2.69s/it]

 43%|████▎     | 369/861 [09:06<19:05,  2.33s/it]

 43%|████▎     | 370/861 [09:07<15:11,  1.86s/it]

 43%|████▎     | 371/861 [09:08<12:43,  1.56s/it]

 43%|████▎     | 372/861 [09:11<15:17,  1.88s/it]

 43%|████▎     | 373/861 [09:13<16:03,  1.97s/it]

 43%|████▎     | 374/861 [09:15<16:53,  2.08s/it]

 44%|████▎     | 375/861 [09:19<21:40,  2.68s/it]

 44%|████▎     | 376/861 [09:20<17:41,  2.19s/it]

 44%|████▍     | 377/861 [09:22<17:21,  2.15s/it]

 44%|████▍     | 378/861 [09:27<22:54,  2.85s/it]

 44%|████▍     | 379/861 [09:27<16:43,  2.08s/it]

 44%|████▍     | 380/861 [09:29<16:15,  2.03s/it]

 44%|████▍     | 381/861 [09:31<15:43,  1.97s/it]

 44%|████▍     | 382/861 [09:31<12:16,  1.54s/it]

 44%|████▍     | 383/861 [09:33<12:37,  1.58s/it]

 45%|████▍     | 384/861 [09:34<11:16,  1.42s/it]

 45%|████▍     | 385/861 [09:34<08:31,  1.07s/it]

 45%|████▍     | 386/861 [09:37<12:03,  1.52s/it]

 45%|████▍     | 387/861 [09:39<12:42,  1.61s/it]

 45%|████▌     | 388/861 [09:39<10:37,  1.35s/it]

 45%|████▌     | 389/861 [09:40<09:38,  1.22s/it]

 45%|████▌     | 390/861 [09:42<10:46,  1.37s/it]

 45%|████▌     | 391/861 [09:43<09:40,  1.24s/it]

 46%|████▌     | 392/861 [09:45<10:34,  1.35s/it]

 46%|████▌     | 393/861 [09:46<10:07,  1.30s/it]

 46%|████▌     | 394/861 [09:47<09:15,  1.19s/it]

 46%|████▌     | 395/861 [09:48<09:06,  1.17s/it]

 46%|████▌     | 396/861 [09:49<08:53,  1.15s/it]

 46%|████▌     | 397/861 [09:49<06:46,  1.14it/s]

 46%|████▌     | 398/861 [09:51<09:31,  1.24s/it]

 46%|████▋     | 399/861 [09:53<11:42,  1.52s/it]

 46%|████▋     | 400/861 [09:55<11:32,  1.50s/it]

 47%|████▋     | 401/861 [09:56<10:09,  1.33s/it]

 47%|████▋     | 402/861 [09:57<09:38,  1.26s/it]

 47%|████▋     | 403/861 [09:58<08:55,  1.17s/it]

 47%|████▋     | 404/861 [09:59<09:48,  1.29s/it]

 47%|████▋     | 405/861 [10:00<07:50,  1.03s/it]

 47%|████▋     | 406/861 [10:01<08:08,  1.07s/it]

 47%|████▋     | 407/861 [10:02<07:38,  1.01s/it]

 47%|████▋     | 408/861 [10:04<09:25,  1.25s/it]

 48%|████▊     | 409/861 [10:05<10:03,  1.34s/it]

 48%|████▊     | 410/861 [10:07<10:28,  1.39s/it]

 48%|████▊     | 411/861 [10:07<08:52,  1.18s/it]

 48%|████▊     | 412/861 [10:10<12:31,  1.67s/it]

 48%|████▊     | 413/861 [10:12<11:37,  1.56s/it]

 48%|████▊     | 414/861 [10:12<09:17,  1.25s/it]

 48%|████▊     | 415/861 [10:13<07:56,  1.07s/it]

 48%|████▊     | 416/861 [10:14<08:02,  1.08s/it]

 48%|████▊     | 417/861 [10:15<07:48,  1.06s/it]

 49%|████▊     | 418/861 [10:17<09:19,  1.26s/it]

 49%|████▊     | 419/861 [10:18<10:37,  1.44s/it]

 49%|████▉     | 420/861 [10:20<11:15,  1.53s/it]

 49%|████▉     | 421/861 [10:21<08:54,  1.22s/it]

 49%|████▉     | 422/861 [10:22<08:33,  1.17s/it]

 49%|████▉     | 423/861 [10:24<10:19,  1.42s/it]

 49%|████▉     | 424/861 [10:25<10:55,  1.50s/it]

 49%|████▉     | 425/861 [10:27<11:03,  1.52s/it]

 49%|████▉     | 426/861 [10:28<10:32,  1.45s/it]

 50%|████▉     | 427/861 [10:30<11:17,  1.56s/it]

 50%|████▉     | 428/861 [10:32<11:28,  1.59s/it]

 50%|████▉     | 429/861 [10:34<12:41,  1.76s/it]

 50%|████▉     | 430/861 [10:36<13:12,  1.84s/it]

 50%|█████     | 431/861 [10:39<15:20,  2.14s/it]

 50%|█████     | 432/861 [10:40<13:39,  1.91s/it]

 50%|█████     | 433/861 [10:42<14:00,  1.96s/it]

 50%|█████     | 434/861 [10:44<12:43,  1.79s/it]

 51%|█████     | 435/861 [10:44<09:21,  1.32s/it]

 51%|█████     | 436/861 [10:44<07:40,  1.08s/it]

 51%|█████     | 437/861 [10:46<08:49,  1.25s/it]

 51%|█████     | 438/861 [10:47<07:44,  1.10s/it]

 51%|█████     | 439/861 [10:48<08:02,  1.14s/it]

 51%|█████     | 440/861 [10:48<06:20,  1.11it/s]

 51%|█████     | 441/861 [10:49<05:40,  1.23it/s]

 51%|█████▏    | 442/861 [10:50<06:25,  1.09it/s]

 51%|█████▏    | 443/861 [10:51<06:05,  1.15it/s]

 52%|█████▏    | 444/861 [10:52<06:38,  1.05it/s]

 52%|█████▏    | 445/861 [10:53<06:10,  1.12it/s]

 52%|█████▏    | 446/861 [10:54<06:24,  1.08it/s]

 52%|█████▏    | 447/861 [10:56<09:21,  1.36s/it]

 52%|█████▏    | 448/861 [10:59<11:31,  1.67s/it]

 52%|█████▏    | 449/861 [11:01<13:06,  1.91s/it]

 52%|█████▏    | 450/861 [11:03<13:52,  2.03s/it]

 52%|█████▏    | 451/861 [11:05<13:10,  1.93s/it]

 52%|█████▏    | 452/861 [11:06<10:33,  1.55s/it]

 53%|█████▎    | 453/861 [11:07<09:40,  1.42s/it]

 53%|█████▎    | 454/861 [11:08<09:42,  1.43s/it]

 53%|█████▎    | 455/861 [11:09<08:38,  1.28s/it]

 53%|█████▎    | 456/861 [11:10<08:01,  1.19s/it]

 53%|█████▎    | 457/861 [11:12<09:30,  1.41s/it]

 53%|█████▎    | 458/861 [11:13<08:51,  1.32s/it]

 53%|█████▎    | 459/861 [11:14<08:36,  1.28s/it]

 53%|█████▎    | 460/861 [11:15<07:49,  1.17s/it]

 54%|█████▎    | 461/861 [11:17<09:13,  1.38s/it]

 54%|█████▎    | 462/861 [11:18<07:51,  1.18s/it]

 54%|█████▍    | 463/861 [11:19<07:49,  1.18s/it]

 54%|█████▍    | 464/861 [11:20<06:51,  1.04s/it]

 54%|█████▍    | 465/861 [11:20<05:36,  1.18it/s]

 54%|█████▍    | 466/861 [11:21<04:54,  1.34it/s]

 54%|█████▍    | 467/861 [11:22<06:21,  1.03it/s]

 54%|█████▍    | 468/861 [11:23<05:26,  1.20it/s]

 54%|█████▍    | 469/861 [11:24<06:20,  1.03it/s]

 55%|█████▍    | 470/861 [11:25<05:59,  1.09it/s]

 55%|█████▍    | 471/861 [11:26<06:39,  1.02s/it]

 55%|█████▍    | 472/861 [11:27<05:59,  1.08it/s]

 55%|█████▍    | 473/861 [11:28<06:15,  1.03it/s]

 55%|█████▌    | 474/861 [11:28<05:16,  1.22it/s]

 55%|█████▌    | 475/861 [11:29<06:01,  1.07it/s]

 55%|█████▌    | 476/861 [11:30<05:25,  1.18it/s]

 55%|█████▌    | 477/861 [11:31<05:32,  1.15it/s]

 56%|█████▌    | 478/861 [11:32<06:16,  1.02it/s]

 56%|█████▌    | 479/861 [11:33<05:02,  1.26it/s]

 56%|█████▌    | 480/861 [11:33<05:08,  1.24it/s]

 56%|█████▌    | 481/861 [11:34<04:59,  1.27it/s]

 56%|█████▌    | 482/861 [11:34<04:05,  1.55it/s]

 56%|█████▌    | 483/861 [11:35<04:13,  1.49it/s]

 56%|█████▌    | 484/861 [11:36<04:47,  1.31it/s]

 56%|█████▋    | 485/861 [11:37<04:11,  1.50it/s]

 56%|█████▋    | 486/861 [11:37<03:41,  1.69it/s]

 57%|█████▋    | 487/861 [11:38<03:53,  1.60it/s]

 57%|█████▋    | 488/861 [11:38<03:25,  1.81it/s]

 57%|█████▋    | 489/861 [11:39<03:10,  1.95it/s]

 57%|█████▋    | 490/861 [11:39<02:47,  2.21it/s]

 57%|█████▋    | 491/861 [11:40<03:22,  1.83it/s]

 57%|█████▋    | 492/861 [11:40<03:10,  1.94it/s]

 57%|█████▋    | 493/861 [11:41<04:00,  1.53it/s]

 57%|█████▋    | 494/861 [11:42<03:37,  1.68it/s]

 57%|█████▋    | 495/861 [11:43<05:46,  1.06it/s]

 58%|█████▊    | 496/861 [11:44<05:30,  1.10it/s]

 58%|█████▊    | 497/861 [11:44<04:28,  1.36it/s]

 58%|█████▊    | 498/861 [11:45<03:54,  1.55it/s]

 58%|█████▊    | 499/861 [11:45<03:25,  1.76it/s]

 58%|█████▊    | 500/861 [11:46<03:41,  1.63it/s]

 58%|█████▊    | 501/861 [11:46<03:04,  1.95it/s]

 58%|█████▊    | 502/861 [11:47<03:24,  1.76it/s]

 58%|█████▊    | 503/861 [11:48<03:57,  1.51it/s]

 59%|█████▊    | 504/861 [11:49<04:07,  1.44it/s]

 59%|█████▊    | 505/861 [11:49<03:58,  1.49it/s]

 59%|█████▉    | 506/861 [11:50<03:50,  1.54it/s]

 59%|█████▉    | 507/861 [11:50<03:21,  1.75it/s]

 59%|█████▉    | 508/861 [11:52<05:06,  1.15it/s]

 59%|█████▉    | 509/861 [11:53<05:33,  1.05it/s]

 59%|█████▉    | 510/861 [11:53<04:55,  1.19it/s]

 59%|█████▉    | 511/861 [11:56<06:59,  1.20s/it]

 59%|█████▉    | 512/861 [11:57<06:56,  1.19s/it]

 60%|█████▉    | 513/861 [11:57<06:05,  1.05s/it]

 60%|█████▉    | 514/861 [11:59<06:19,  1.09s/it]

 60%|█████▉    | 515/861 [11:59<05:16,  1.09it/s]

 60%|█████▉    | 516/861 [11:59<04:15,  1.35it/s]

 60%|██████    | 517/861 [12:00<03:33,  1.61it/s]

 60%|██████    | 518/861 [12:00<03:23,  1.69it/s]

 60%|██████    | 519/861 [12:01<03:36,  1.58it/s]

 60%|██████    | 520/861 [12:03<05:36,  1.01it/s]

 61%|██████    | 521/861 [12:04<05:50,  1.03s/it]

 61%|██████    | 522/861 [12:06<07:43,  1.37s/it]

 61%|██████    | 523/861 [12:07<06:57,  1.23s/it]

 61%|██████    | 524/861 [12:10<09:45,  1.74s/it]

 61%|██████    | 525/861 [12:11<08:23,  1.50s/it]

 61%|██████    | 526/861 [12:12<08:21,  1.50s/it]

 61%|██████    | 527/861 [12:13<06:53,  1.24s/it]

 61%|██████▏   | 528/861 [12:15<08:18,  1.50s/it]

 61%|██████▏   | 529/861 [12:16<07:06,  1.29s/it]

 62%|██████▏   | 530/861 [12:17<06:10,  1.12s/it]

 62%|██████▏   | 531/861 [12:18<05:40,  1.03s/it]

 62%|██████▏   | 532/861 [12:18<05:06,  1.07it/s]

 62%|██████▏   | 533/861 [12:19<04:50,  1.13it/s]

 62%|██████▏   | 534/861 [12:20<05:28,  1.01s/it]

 62%|██████▏   | 535/861 [12:21<05:12,  1.04it/s]

 62%|██████▏   | 536/861 [12:22<04:44,  1.14it/s]

 62%|██████▏   | 537/861 [12:23<05:41,  1.05s/it]

 62%|██████▏   | 538/861 [12:24<04:39,  1.16it/s]

 63%|██████▎   | 539/861 [12:27<08:39,  1.61s/it]

 63%|██████▎   | 540/861 [12:29<08:44,  1.63s/it]

 63%|██████▎   | 541/861 [12:29<06:46,  1.27s/it]

 63%|██████▎   | 542/861 [12:30<06:09,  1.16s/it]

 63%|██████▎   | 543/861 [12:31<05:26,  1.03s/it]

 63%|██████▎   | 544/861 [12:31<04:50,  1.09it/s]

 63%|██████▎   | 545/861 [12:33<05:30,  1.04s/it]

 63%|██████▎   | 546/861 [12:34<05:42,  1.09s/it]

 64%|██████▎   | 547/861 [12:36<07:03,  1.35s/it]

 64%|██████▎   | 548/861 [12:37<06:46,  1.30s/it]

 64%|██████▍   | 549/861 [12:39<08:14,  1.59s/it]

 64%|██████▍   | 550/861 [12:40<07:02,  1.36s/it]

 64%|██████▍   | 551/861 [12:42<07:51,  1.52s/it]

 64%|██████▍   | 552/861 [12:43<07:34,  1.47s/it]

 64%|██████▍   | 553/861 [12:47<10:21,  2.02s/it]

 64%|██████▍   | 554/861 [12:49<11:11,  2.19s/it]

 64%|██████▍   | 555/861 [12:51<10:26,  2.05s/it]

 65%|██████▍   | 556/861 [12:53<09:51,  1.94s/it]

 65%|██████▍   | 557/861 [12:54<08:29,  1.68s/it]

 65%|██████▍   | 558/861 [12:56<08:46,  1.74s/it]

 65%|██████▍   | 559/861 [12:57<07:38,  1.52s/it]

 65%|██████▌   | 560/861 [12:57<06:25,  1.28s/it]

 65%|██████▌   | 561/861 [12:59<06:25,  1.29s/it]

 65%|██████▌   | 562/861 [13:03<10:47,  2.16s/it]

 65%|██████▌   | 563/861 [13:05<11:17,  2.27s/it]

 66%|██████▌   | 564/861 [13:06<09:20,  1.89s/it]

 66%|██████▌   | 565/861 [13:08<08:49,  1.79s/it]

 66%|██████▌   | 566/861 [13:10<08:24,  1.71s/it]

 66%|██████▌   | 567/861 [13:12<09:33,  1.95s/it]

 66%|██████▌   | 568/861 [13:13<08:09,  1.67s/it]

 66%|██████▌   | 569/861 [13:15<09:04,  1.86s/it]

 66%|██████▌   | 570/861 [13:16<07:37,  1.57s/it]

 66%|██████▋   | 571/861 [13:18<08:00,  1.66s/it]

 66%|██████▋   | 572/861 [13:19<07:29,  1.56s/it]

 67%|██████▋   | 573/861 [13:20<06:04,  1.27s/it]

 67%|██████▋   | 574/861 [13:21<06:11,  1.30s/it]

 67%|██████▋   | 575/861 [13:22<05:48,  1.22s/it]

 67%|██████▋   | 576/861 [13:24<06:05,  1.28s/it]

 67%|██████▋   | 577/861 [13:26<06:37,  1.40s/it]

 67%|██████▋   | 578/861 [13:27<06:25,  1.36s/it]

 67%|██████▋   | 579/861 [13:28<05:36,  1.19s/it]

 67%|██████▋   | 580/861 [13:34<12:13,  2.61s/it]

 67%|██████▋   | 581/861 [13:36<12:17,  2.63s/it]

 68%|██████▊   | 582/861 [13:40<13:48,  2.97s/it]

 68%|██████▊   | 583/861 [13:42<12:48,  2.76s/it]

 68%|██████▊   | 584/861 [13:44<11:29,  2.49s/it]

 68%|██████▊   | 585/861 [13:45<09:49,  2.14s/it]

 68%|██████▊   | 586/861 [13:47<08:56,  1.95s/it]

 68%|██████▊   | 587/861 [13:50<11:04,  2.43s/it]

 68%|██████▊   | 588/861 [13:53<11:11,  2.46s/it]

 68%|██████▊   | 589/861 [13:54<09:21,  2.06s/it]

 69%|██████▊   | 590/861 [13:55<07:56,  1.76s/it]

 69%|██████▊   | 591/861 [13:58<08:54,  1.98s/it]

 69%|██████▉   | 592/861 [14:01<10:56,  2.44s/it]

 69%|██████▉   | 593/861 [14:03<09:32,  2.14s/it]

 69%|██████▉   | 594/861 [14:04<08:21,  1.88s/it]

 69%|██████▉   | 595/861 [14:06<08:21,  1.88s/it]

 69%|██████▉   | 596/861 [14:07<06:55,  1.57s/it]

 69%|██████▉   | 597/861 [14:08<06:43,  1.53s/it]

 69%|██████▉   | 598/861 [14:10<06:45,  1.54s/it]

 70%|██████▉   | 599/861 [14:12<07:14,  1.66s/it]

 70%|██████▉   | 600/861 [14:13<06:43,  1.55s/it]

 70%|██████▉   | 601/861 [14:15<07:04,  1.63s/it]

 70%|██████▉   | 602/861 [14:17<07:19,  1.70s/it]

 70%|███████   | 603/861 [14:19<08:42,  2.03s/it]

 70%|███████   | 604/861 [14:22<09:35,  2.24s/it]

 70%|███████   | 605/861 [14:23<07:25,  1.74s/it]

 70%|███████   | 606/861 [14:24<06:31,  1.53s/it]

 70%|███████   | 607/861 [14:25<06:38,  1.57s/it]

 71%|███████   | 608/861 [14:26<05:58,  1.42s/it]

 71%|███████   | 609/861 [14:29<07:48,  1.86s/it]

 71%|███████   | 610/861 [14:32<08:45,  2.10s/it]

 71%|███████   | 611/861 [14:33<07:31,  1.81s/it]

 71%|███████   | 612/861 [14:34<06:39,  1.61s/it]

 71%|███████   | 613/861 [14:35<05:06,  1.24s/it]

 71%|███████▏  | 614/861 [14:37<06:28,  1.57s/it]

 71%|███████▏  | 615/861 [14:40<08:02,  1.96s/it]

 72%|███████▏  | 616/861 [14:43<09:03,  2.22s/it]

 72%|███████▏  | 617/861 [14:44<08:13,  2.02s/it]

 72%|███████▏  | 618/861 [14:45<07:05,  1.75s/it]

 72%|███████▏  | 619/861 [14:46<06:04,  1.51s/it]

 72%|███████▏  | 620/861 [14:48<06:15,  1.56s/it]

 72%|███████▏  | 621/861 [14:49<05:53,  1.47s/it]

 72%|███████▏  | 622/861 [14:50<04:59,  1.25s/it]

 72%|███████▏  | 623/861 [14:51<04:45,  1.20s/it]

 72%|███████▏  | 624/861 [14:52<04:02,  1.02s/it]

 73%|███████▎  | 625/861 [14:52<03:49,  1.03it/s]

 73%|███████▎  | 626/861 [14:54<04:47,  1.22s/it]

 73%|███████▎  | 627/861 [14:56<05:39,  1.45s/it]

 73%|███████▎  | 628/861 [14:59<06:34,  1.69s/it]

 73%|███████▎  | 629/861 [15:01<06:54,  1.79s/it]

 73%|███████▎  | 630/861 [15:01<05:28,  1.42s/it]

 73%|███████▎  | 631/861 [15:01<04:12,  1.10s/it]

 73%|███████▎  | 632/861 [15:03<04:18,  1.13s/it]

 74%|███████▎  | 633/861 [15:03<03:58,  1.05s/it]

 74%|███████▎  | 634/861 [15:05<04:14,  1.12s/it]

 74%|███████▍  | 635/861 [15:06<04:43,  1.25s/it]

 74%|███████▍  | 636/861 [15:08<04:43,  1.26s/it]

 74%|███████▍  | 637/861 [15:09<04:34,  1.22s/it]

 74%|███████▍  | 638/861 [15:11<05:09,  1.39s/it]

 74%|███████▍  | 639/861 [15:13<05:55,  1.60s/it]

 74%|███████▍  | 640/861 [15:14<05:51,  1.59s/it]

 74%|███████▍  | 641/861 [15:16<05:46,  1.58s/it]

 75%|███████▍  | 642/861 [15:17<05:57,  1.63s/it]

 75%|███████▍  | 643/861 [15:18<05:04,  1.40s/it]

 75%|███████▍  | 644/861 [15:19<04:40,  1.29s/it]

 75%|███████▍  | 645/861 [15:20<04:10,  1.16s/it]

 75%|███████▌  | 646/861 [15:22<04:27,  1.24s/it]

 75%|███████▌  | 647/861 [15:23<04:05,  1.15s/it]

 75%|███████▌  | 648/861 [15:24<04:41,  1.32s/it]

 75%|███████▌  | 649/861 [15:26<05:02,  1.43s/it]

 75%|███████▌  | 650/861 [15:27<04:58,  1.42s/it]

 76%|███████▌  | 651/861 [15:28<04:22,  1.25s/it]

 76%|███████▌  | 652/861 [15:29<04:03,  1.16s/it]

 76%|███████▌  | 653/861 [15:30<04:00,  1.16s/it]

 76%|███████▌  | 654/861 [15:31<03:34,  1.04s/it]

 76%|███████▌  | 655/861 [15:31<02:51,  1.20it/s]

 76%|███████▌  | 656/861 [15:32<02:40,  1.28it/s]

 76%|███████▋  | 657/861 [15:33<02:34,  1.32it/s]

 76%|███████▋  | 658/861 [15:34<02:46,  1.22it/s]

 77%|███████▋  | 659/861 [15:35<03:04,  1.09it/s]

 77%|███████▋  | 660/861 [15:36<03:42,  1.11s/it]

 77%|███████▋  | 661/861 [15:38<04:06,  1.23s/it]

 77%|███████▋  | 662/861 [15:39<03:43,  1.12s/it]

 77%|███████▋  | 663/861 [15:40<03:27,  1.05s/it]

 77%|███████▋  | 664/861 [15:40<02:59,  1.10it/s]

 77%|███████▋  | 665/861 [15:41<02:44,  1.19it/s]

 77%|███████▋  | 666/861 [15:42<02:38,  1.23it/s]

 77%|███████▋  | 667/861 [15:43<02:42,  1.19it/s]

 78%|███████▊  | 668/861 [15:44<03:03,  1.05it/s]

 78%|███████▊  | 669/861 [15:45<02:46,  1.15it/s]

 78%|███████▊  | 670/861 [15:45<02:36,  1.22it/s]

 78%|███████▊  | 671/861 [15:46<02:10,  1.46it/s]

 78%|███████▊  | 672/861 [15:47<02:44,  1.15it/s]

 78%|███████▊  | 673/861 [15:48<02:41,  1.17it/s]

 78%|███████▊  | 674/861 [15:49<03:01,  1.03it/s]

 78%|███████▊  | 675/861 [15:50<02:37,  1.18it/s]

 79%|███████▊  | 676/861 [15:51<02:57,  1.04it/s]

 79%|███████▊  | 677/861 [15:53<03:39,  1.19s/it]

 79%|███████▊  | 678/861 [15:53<03:23,  1.11s/it]

 79%|███████▉  | 679/861 [15:54<03:14,  1.07s/it]

 79%|███████▉  | 680/861 [15:55<02:58,  1.01it/s]

 79%|███████▉  | 681/861 [15:56<02:45,  1.09it/s]

 79%|███████▉  | 682/861 [15:57<02:37,  1.13it/s]

 79%|███████▉  | 683/861 [15:58<03:08,  1.06s/it]

 79%|███████▉  | 684/861 [16:00<03:51,  1.31s/it]

 80%|███████▉  | 685/861 [16:01<03:28,  1.18s/it]

 80%|███████▉  | 686/861 [16:02<03:19,  1.14s/it]

 80%|███████▉  | 687/861 [16:05<05:04,  1.75s/it]

 80%|███████▉  | 688/861 [16:06<04:26,  1.54s/it]

 80%|████████  | 689/861 [16:08<04:24,  1.54s/it]

 80%|████████  | 690/861 [16:09<04:22,  1.54s/it]

 80%|████████  | 691/861 [16:10<03:52,  1.37s/it]

 80%|████████  | 692/861 [16:12<04:07,  1.46s/it]

 80%|████████  | 693/861 [16:13<03:55,  1.40s/it]

 81%|████████  | 694/861 [16:14<03:27,  1.24s/it]

 81%|████████  | 695/861 [16:15<03:06,  1.12s/it]

 81%|████████  | 696/861 [16:15<02:24,  1.15it/s]

 81%|████████  | 697/861 [16:16<02:39,  1.03it/s]

 81%|████████  | 698/861 [16:17<02:35,  1.05it/s]

 81%|████████  | 699/861 [16:20<03:56,  1.46s/it]

 81%|████████▏ | 700/861 [16:23<05:07,  1.91s/it]

 81%|████████▏ | 701/861 [16:25<04:54,  1.84s/it]

 82%|████████▏ | 702/861 [16:26<04:07,  1.56s/it]

 82%|████████▏ | 703/861 [16:26<03:26,  1.30s/it]

 82%|████████▏ | 704/861 [16:28<03:21,  1.28s/it]

 82%|████████▏ | 705/861 [16:29<03:38,  1.40s/it]

 82%|████████▏ | 706/861 [16:30<03:17,  1.27s/it]

 82%|████████▏ | 707/861 [16:31<02:50,  1.11s/it]

 82%|████████▏ | 708/861 [16:32<02:49,  1.11s/it]

 82%|████████▏ | 709/861 [16:33<02:50,  1.12s/it]

 82%|████████▏ | 710/861 [16:35<03:36,  1.43s/it]

 83%|████████▎ | 711/861 [16:37<03:51,  1.54s/it]

 83%|████████▎ | 712/861 [16:38<03:35,  1.45s/it]

 83%|████████▎ | 713/861 [16:39<02:51,  1.16s/it]

 83%|████████▎ | 714/861 [16:40<02:57,  1.20s/it]

 83%|████████▎ | 715/861 [16:43<03:56,  1.62s/it]

 83%|████████▎ | 716/861 [16:44<03:26,  1.42s/it]

 83%|████████▎ | 717/861 [16:45<03:15,  1.35s/it]

 83%|████████▎ | 718/861 [16:46<03:09,  1.32s/it]

 84%|████████▎ | 719/861 [16:47<02:58,  1.26s/it]

 84%|████████▎ | 720/861 [16:48<02:46,  1.18s/it]

 84%|████████▎ | 721/861 [16:49<02:42,  1.16s/it]

 84%|████████▍ | 722/861 [16:50<02:23,  1.03s/it]

 84%|████████▍ | 723/861 [16:51<02:21,  1.03s/it]

 84%|████████▍ | 724/861 [16:52<02:27,  1.08s/it]

 84%|████████▍ | 725/861 [16:53<02:07,  1.07it/s]

 84%|████████▍ | 726/861 [16:54<02:07,  1.06it/s]

 84%|████████▍ | 727/861 [16:56<02:49,  1.26s/it]

 85%|████████▍ | 728/861 [16:58<03:08,  1.42s/it]

 85%|████████▍ | 729/861 [16:59<02:58,  1.35s/it]

 85%|████████▍ | 730/861 [16:59<02:27,  1.13s/it]

 85%|████████▍ | 731/861 [17:01<02:22,  1.10s/it]

 85%|████████▌ | 732/861 [17:02<02:20,  1.09s/it]

 85%|████████▌ | 733/861 [17:03<02:30,  1.17s/it]

 85%|████████▌ | 734/861 [17:03<01:55,  1.10it/s]

 85%|████████▌ | 735/861 [17:04<01:52,  1.12it/s]

 85%|████████▌ | 736/861 [17:06<02:11,  1.05s/it]

 86%|████████▌ | 737/861 [17:07<02:41,  1.30s/it]

 86%|████████▌ | 738/861 [17:08<02:24,  1.17s/it]

 86%|████████▌ | 739/861 [17:09<02:18,  1.13s/it]

 86%|████████▌ | 740/861 [17:10<01:54,  1.06it/s]

 86%|████████▌ | 741/861 [17:12<02:21,  1.18s/it]

 86%|████████▌ | 742/861 [17:13<02:38,  1.33s/it]

 86%|████████▋ | 743/861 [17:14<02:21,  1.20s/it]

 86%|████████▋ | 744/861 [17:15<02:13,  1.14s/it]

 87%|████████▋ | 745/861 [17:17<02:41,  1.39s/it]

 87%|████████▋ | 746/861 [17:18<02:29,  1.30s/it]

 87%|████████▋ | 747/861 [17:19<02:26,  1.29s/it]

 87%|████████▋ | 748/861 [17:21<02:50,  1.51s/it]

 87%|████████▋ | 749/861 [17:23<02:51,  1.54s/it]

 87%|████████▋ | 750/861 [17:24<02:28,  1.34s/it]

 87%|████████▋ | 751/861 [17:24<01:51,  1.01s/it]

 87%|████████▋ | 752/861 [17:26<02:06,  1.16s/it]

 87%|████████▋ | 753/861 [17:27<01:58,  1.10s/it]

 88%|████████▊ | 754/861 [17:28<01:50,  1.03s/it]

 88%|████████▊ | 755/861 [17:28<01:43,  1.02it/s]

 88%|████████▊ | 756/861 [17:29<01:22,  1.27it/s]

 88%|████████▊ | 757/861 [17:30<01:31,  1.14it/s]

 88%|████████▊ | 758/861 [17:31<01:45,  1.02s/it]

 88%|████████▊ | 759/861 [17:32<01:37,  1.05it/s]

 88%|████████▊ | 760/861 [17:34<02:13,  1.32s/it]

 88%|████████▊ | 761/861 [17:36<02:33,  1.54s/it]

 89%|████████▊ | 762/861 [17:37<02:06,  1.28s/it]

 89%|████████▊ | 763/861 [17:37<01:42,  1.04s/it]

 89%|████████▊ | 764/861 [17:38<01:34,  1.03it/s]

 89%|████████▉ | 765/861 [17:39<01:23,  1.16it/s]

 89%|████████▉ | 766/861 [17:41<01:54,  1.21s/it]

 89%|████████▉ | 767/861 [17:47<04:08,  2.65s/it]

 89%|████████▉ | 768/861 [17:48<03:13,  2.08s/it]

 89%|████████▉ | 769/861 [17:49<02:44,  1.78s/it]

 89%|████████▉ | 770/861 [17:50<02:23,  1.57s/it]

 90%|████████▉ | 771/861 [17:51<02:04,  1.39s/it]

 90%|████████▉ | 772/861 [17:53<02:21,  1.59s/it]

 90%|████████▉ | 773/861 [17:55<02:42,  1.84s/it]

 90%|████████▉ | 774/861 [17:57<02:40,  1.84s/it]

 90%|█████████ | 775/861 [17:59<02:53,  2.02s/it]

 90%|█████████ | 776/861 [18:02<02:59,  2.11s/it]

 90%|█████████ | 777/861 [18:03<02:42,  1.94s/it]

 90%|█████████ | 778/861 [18:05<02:41,  1.94s/it]

 90%|█████████ | 779/861 [18:08<03:01,  2.22s/it]

 91%|█████████ | 780/861 [18:10<02:54,  2.16s/it]

 91%|█████████ | 781/861 [18:12<02:37,  1.97s/it]

 91%|█████████ | 782/861 [18:13<02:09,  1.64s/it]

 91%|█████████ | 783/861 [18:14<02:12,  1.70s/it]

 91%|█████████ | 784/861 [18:17<02:40,  2.08s/it]

 91%|█████████ | 785/861 [18:19<02:30,  1.97s/it]

 91%|█████████▏| 786/861 [18:21<02:18,  1.84s/it]

 91%|█████████▏| 787/861 [18:22<02:08,  1.74s/it]

 92%|█████████▏| 788/861 [18:26<02:59,  2.46s/it]

 92%|█████████▏| 789/861 [18:29<02:58,  2.48s/it]

 92%|█████████▏| 790/861 [18:30<02:39,  2.25s/it]

 92%|█████████▏| 791/861 [18:32<02:32,  2.18s/it]

 92%|█████████▏| 792/861 [18:34<02:15,  1.97s/it]

 92%|█████████▏| 793/861 [18:37<02:28,  2.19s/it]

 92%|█████████▏| 794/861 [18:38<02:05,  1.88s/it]

 92%|█████████▏| 795/861 [18:42<02:58,  2.70s/it]

 92%|█████████▏| 796/861 [18:43<02:09,  1.99s/it]

 93%|█████████▎| 797/861 [18:45<02:04,  1.95s/it]

 93%|█████████▎| 798/861 [18:48<02:22,  2.27s/it]

 93%|█████████▎| 799/861 [18:50<02:17,  2.23s/it]

 93%|█████████▎| 800/861 [18:51<01:52,  1.84s/it]

 93%|█████████▎| 801/861 [18:53<01:56,  1.95s/it]

 93%|█████████▎| 802/861 [18:54<01:31,  1.56s/it]

 93%|█████████▎| 803/861 [18:56<01:47,  1.85s/it]

 93%|█████████▎| 804/861 [19:02<02:53,  3.05s/it]

 93%|█████████▎| 805/861 [19:07<03:22,  3.62s/it]

 94%|█████████▎| 806/861 [19:08<02:30,  2.73s/it]

 94%|█████████▎| 807/861 [19:09<02:08,  2.37s/it]

 94%|█████████▍| 808/861 [19:11<02:00,  2.27s/it]

 94%|█████████▍| 809/861 [19:12<01:32,  1.78s/it]

 94%|█████████▍| 810/861 [19:13<01:30,  1.77s/it]

 94%|█████████▍| 811/861 [19:15<01:24,  1.69s/it]

 94%|█████████▍| 812/861 [19:17<01:21,  1.66s/it]

 94%|█████████▍| 813/861 [19:22<02:19,  2.92s/it]

 95%|█████████▍| 814/861 [19:24<01:59,  2.54s/it]

 95%|█████████▍| 815/861 [19:27<01:58,  2.57s/it]

 95%|█████████▍| 816/861 [19:28<01:41,  2.26s/it]

 95%|█████████▍| 817/861 [19:30<01:26,  1.96s/it]

 95%|█████████▌| 818/861 [19:32<01:31,  2.13s/it]

 95%|█████████▌| 819/861 [19:33<01:18,  1.87s/it]

 95%|█████████▌| 820/861 [19:34<01:06,  1.63s/it]

 95%|█████████▌| 821/861 [19:38<01:24,  2.11s/it]

 95%|█████████▌| 822/861 [19:39<01:12,  1.87s/it]

 96%|█████████▌| 823/861 [19:40<00:58,  1.55s/it]

 96%|█████████▌| 824/861 [19:41<00:54,  1.46s/it]

 96%|█████████▌| 825/861 [19:42<00:45,  1.27s/it]

 96%|█████████▌| 826/861 [19:44<00:50,  1.44s/it]

 96%|█████████▌| 827/861 [19:45<00:45,  1.33s/it]

 96%|█████████▌| 828/861 [19:46<00:41,  1.27s/it]

 96%|█████████▋| 829/861 [19:48<00:49,  1.56s/it]

 96%|█████████▋| 830/861 [19:49<00:45,  1.48s/it]

 97%|█████████▋| 831/861 [19:52<00:55,  1.85s/it]

 97%|█████████▋| 832/861 [19:54<00:52,  1.79s/it]

 97%|█████████▋| 833/861 [19:55<00:45,  1.62s/it]

 97%|█████████▋| 834/861 [19:56<00:39,  1.46s/it]

 97%|█████████▋| 835/861 [19:57<00:34,  1.31s/it]

 97%|█████████▋| 836/861 [20:00<00:42,  1.70s/it]

 97%|█████████▋| 837/861 [20:02<00:47,  1.97s/it]

 97%|█████████▋| 838/861 [20:05<00:48,  2.09s/it]

 97%|█████████▋| 839/861 [20:06<00:41,  1.87s/it]

 98%|█████████▊| 840/861 [20:08<00:37,  1.78s/it]

 98%|█████████▊| 841/861 [20:09<00:36,  1.81s/it]

 98%|█████████▊| 842/861 [20:11<00:34,  1.84s/it]

 98%|█████████▊| 843/861 [20:13<00:32,  1.79s/it]

 98%|█████████▊| 844/861 [20:15<00:30,  1.79s/it]

 98%|█████████▊| 845/861 [20:17<00:31,  1.98s/it]

 98%|█████████▊| 846/861 [20:19<00:27,  1.85s/it]

 98%|█████████▊| 847/861 [20:21<00:27,  1.95s/it]

 98%|█████████▊| 848/861 [20:23<00:27,  2.11s/it]

 99%|█████████▊| 849/861 [20:25<00:22,  1.89s/it]

 99%|█████████▊| 850/861 [20:26<00:17,  1.63s/it]

 99%|█████████▉| 851/861 [20:27<00:14,  1.48s/it]

 99%|█████████▉| 852/861 [20:28<00:12,  1.38s/it]

 99%|█████████▉| 853/861 [20:33<00:18,  2.37s/it]

 99%|█████████▉| 854/861 [20:34<00:14,  2.06s/it]

 99%|█████████▉| 855/861 [20:35<00:10,  1.73s/it]

 99%|█████████▉| 856/861 [20:38<00:10,  2.15s/it]

100%|█████████▉| 857/861 [20:40<00:08,  2.05s/it]

100%|█████████▉| 858/861 [20:41<00:05,  1.77s/it]

100%|█████████▉| 859/861 [20:42<00:02,  1.49s/it]

100%|█████████▉| 860/861 [20:43<00:01,  1.35s/it]

100%|██████████| 861/861 [20:45<00:00,  1.51s/it]{'score': 1.6990924408151828, 'counts': [13158, 4103, 1802, 804], 'totals': [177622, 175900, 174178, 172456], 'precisions': [7.407866142707547, 2.3325753268902787, 1.0345738267749085, 0.466205872802338], 'bp': 1.0, 'sys_len': 177622, 'ref_len': 32555}

                                                          

                                                 
{'eval_loss': 2.596095085144043, 'eval_bleu': 1.6991, 'eval_gen_len': 66.9245, 'eval_runtime': 1347.5897, 'eval_samples_per_second': 1.278, 'eval_steps_per_second': 0.639, 'epoch': 6.0}

 38%|███▊      | 23214/61904 [1:52:00<15:10:34,  1.41s/it]

100%|██████████| 861/861 [22:25<00:00,  1.51s/it]

                                                 [WARNING|configuration_utils.py:448] 2024-10-28 04:56:43,093 >> 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()

 38%|███▊      | 23215/61904 [1:52:23<4432:28:40, 412.44s/it]
 38%|███▊      | 23216/61904 [1:52:25<3107:09:47, 289.13s/it]
 38%|███▊      | 23217/61904 [1:52:26<2179:36:43, 202.82s/it]
 38%|███▊      | 23218/61904 [1:52:28<1530:10:56, 142.39s/it]
 38%|███▊      | 23219/61904 [1:52:29<1076:08:05, 100.14s/it]
 38%|███▊      | 23220/61904 [1:52:31<757:58:32, 70.54s/it]  
                                                           
{'loss': 2.6423, 'learning_rate': 1.6269285621677687e-07, 'epoch': 6.0}

 38%|███▊      | 23220/61904 [1:52:31<757:58:32, 70.54s/it]
 38%|███▊      | 23221/61904 [1:52:32<535:11:14, 49.81s/it]
 38%|███▊      | 23222/61904 [1:52:33<379:02:15, 35.28s/it]
 38%|███▊      | 23223/61904 [1:52:35<270:01:36, 25.13s/it]
 38%|███▊      | 23224/61904 [1:52:36<193:20:17, 17.99s/it]
 38%|███▊      | 23225/61904 [1:52:38<140:12:55, 13.05s/it]
 38%|███▊      | 23226/61904 [1:52:39<103:13:21,  9.61s/it]
 38%|███▊      | 23227/61904 [1:52:41<77:28:15,  7.21s/it] 
 38%|███▊      | 23228/61904 [1:52:43<59:33:25,  5.54s/it]
 38%|███▊      | 23229/61904 [1:52:44<46:30:55,  4.33s/it]
 38%|███▊      | 23230/61904 [1:52:46<37:26:12,  3.48s/it]
 38%|███▊      | 23231/61904 [1:52:47<30:43:22,  2.86s/it]
 38%|███▊      | 23232/61904 [1:52:48<25:36:27,  2.38s/it]
 38%|███▊      | 23233/61904 [1:52:50<22:13:13,  2.07s/it]
 38%|███▊      | 23234/61904 [1:52:51<20:02:45,  1.87s/it]
 38%|███▊      | 23235/61904 [1:52:52<18:26:00,  1.72s/it]
 38%|███▊      | 23236/61904 [1:52:54<17:09:32,  1.60s/it]
 38%|███▊      | 23237/61904 [1:52:55<16:30:01,  1.54s/it]
 38%|███▊      | 23238/61904 [1:52:56<16:00:59,  1.49s/it]
 38%|███▊      | 23239/61904 [1:52:58<15:14:50,  1.42s/it]
 38%|███▊      | 23240/61904 [1:52:59<15:19:20,  1.43s/it]
                                                          
{'loss': 2.667, 'learning_rate': 1.626604434072345e-07, 'epoch': 6.01}

 38%|███▊      | 23240/61904 [1:52:59<15:19:20,  1.43s/it]
 38%|███▊      | 23241/61904 [1:53:01<15:12:08,  1.42s/it]
 38%|███▊      | 23242/61904 [1:53:02<15:15:24,  1.42s/it]
 38%|███▊      | 23243/61904 [1:53:03<15:28:55,  1.44s/it]
 38%|███▊      | 23244/61904 [1:53:05<15:30:06,  1.44s/it]
 38%|███▊      | 23245/61904 [1:53:06<15:36:16,  1.45s/it]
 38%|███▊      | 23246/61904 [1:53:08<15:25:43,  1.44s/it]
 38%|███▊      | 23247/61904 [1:53:09<15:26:21,  1.44s/it]
 38%|███▊      | 23248/61904 [1:53:11<15:42:16,  1.46s/it]
 38%|███▊      | 23249/61904 [1:53:12<15:34:55,  1.45s/it]
 38%|███▊      | 23250/61904 [1:53:14<15:33:19,  1.45s/it]
 38%|███▊      | 23251/61904 [1:53:15<15:25:00,  1.44s/it]
 38%|███▊      | 23252/61904 [1:53:16<15:18:03,  1.43s/it]
 38%|███▊      | 23253/61904 [1:53:18<15:01:18,  1.40s/it]
 38%|███▊      | 23254/61904 [1:53:19<14:53:57,  1.39s/it]
 38%|███▊      | 23255/61904 [1:53:21<15:04:07,  1.40s/it]
 38%|███▊      | 23256/61904 [1:53:22<15:29:34,  1.44s/it]
 38%|███▊      | 23257/61904 [1:53:23<15:18:44,  1.43s/it]
 38%|███▊      | 23258/61904 [1:53:25<15:32:15,  1.45s/it]
 38%|███▊      | 23259/61904 [1:53:27<15:56:10,  1.48s/it]
 38%|███▊      | 23260/61904 [1:53:28<15:51:28,  1.48s/it]
                                                          
{'loss': 2.6741, 'learning_rate': 1.626280305976922e-07, 'epoch': 6.01}

 38%|███▊      | 23260/61904 [1:53:28<15:51:28,  1.48s/it]
 38%|███▊      | 23261/61904 [1:53:29<15:42:01,  1.46s/it]
 38%|███▊      | 23262/61904 [1:53:31<16:02:32,  1.49s/it]
 38%|███▊      | 23263/61904 [1:53:33<16:03:29,  1.50s/it]
 38%|███▊      | 23264/61904 [1:53:34<15:45:25,  1.47s/it]
 38%|███▊      | 23265/61904 [1:53:35<15:29:03,  1.44s/it]
 38%|███▊      | 23266/61904 [1:53:37<15:29:09,  1.44s/it]
 38%|███▊      | 23267/61904 [1:53:38<15:34:57,  1.45s/it]
 38%|███▊      | 23268/61904 [1:53:40<15:52:53,  1.48s/it]
 38%|███▊      | 23269/61904 [1:53:41<15:47:18,  1.47s/it]
 38%|███▊      | 23270/61904 [1:53:43<15:42:39,  1.46s/it]
 38%|███▊      | 23271/61904 [1:53:44<15:38:03,  1.46s/it]
 38%|███▊      | 23272/61904 [1:53:45<15:15:23,  1.42s/it]
 38%|███▊      | 23273/61904 [1:53:47<16:05:16,  1.50s/it]
 38%|███▊      | 23274/61904 [1:53:49<15:50:56,  1.48s/it]
 38%|███▊      | 23275/61904 [1:53:50<15:51:03,  1.48s/it]
 38%|███▊      | 23276/61904 [1:53:51<15:39:08,  1.46s/it]
 38%|███▊      | 23277/61904 [1:53:53<15:14:06,  1.42s/it]
 38%|███▊      | 23278/61904 [1:53:54<15:25:50,  1.44s/it]
 38%|███▊      | 23279/61904 [1:53:56<14:54:19,  1.39s/it]
 38%|███▊      | 23280/61904 [1:53:57<15:38:47,  1.46s/it]
                                                          
{'loss': 2.6269, 'learning_rate': 1.6259561778814989e-07, 'epoch': 6.02}

 38%|███▊      | 23280/61904 [1:53:57<15:38:47,  1.46s/it]
 38%|███▊      | 23281/61904 [1:53:59<15:26:03,  1.44s/it]
 38%|███▊      | 23282/61904 [1:54:00<15:15:37,  1.42s/it]
 38%|███▊      | 23283/61904 [1:54:01<15:06:25,  1.41s/it]
 38%|███▊      | 23284/61904 [1:54:03<15:23:26,  1.43s/it]
 38%|███▊      | 23285/61904 [1:54:04<15:10:12,  1.41s/it]
 38%|███▊      | 23286/61904 [1:54:06<15:06:08,  1.41s/it]
 38%|███▊      | 23287/61904 [1:54:07<15:11:46,  1.42s/it]
 38%|███▊      | 23288/61904 [1:54:08<15:28:14,  1.44s/it]
 38%|███▊      | 23289/61904 [1:54:10<15:22:24,  1.43s/it]
 38%|███▊      | 23290/61904 [1:54:11<15:41:23,  1.46s/it]
 38%|███▊      | 23291/61904 [1:54:13<15:34:48,  1.45s/it]
 38%|███▊      | 23292/61904 [1:54:14<15:25:49,  1.44s/it]
 38%|███▊      | 23293/61904 [1:54:16<15:06:21,  1.41s/it]
 38%|███▊      | 23294/61904 [1:54:17<15:35:58,  1.45s/it]
 38%|███▊      | 23295/61904 [1:54:19<16:11:40,  1.51s/it]
 38%|███▊      | 23296/61904 [1:54:20<16:09:44,  1.51s/it]
 38%|███▊      | 23297/61904 [1:54:22<16:10:10,  1.51s/it]
 38%|███▊      | 23298/61904 [1:54:23<16:14:22,  1.51s/it]
 38%|███▊      | 23299/61904 [1:54:25<16:15:50,  1.52s/it]
 38%|███▊      | 23300/61904 [1:54:26<16:29:29,  1.54s/it]
                                                          
{'loss': 2.6817, 'learning_rate': 1.6256320497860752e-07, 'epoch': 6.02}

 38%|███▊      | 23300/61904 [1:54:26<16:29:29,  1.54s/it]
 38%|███▊      | 23301/61904 [1:54:28<16:28:25,  1.54s/it]
 38%|███▊      | 23302/61904 [1:54:30<16:27:41,  1.54s/it]
 38%|███▊      | 23303/61904 [1:54:31<16:17:42,  1.52s/it]
 38%|███▊      | 23304/61904 [1:54:33<16:19:28,  1.52s/it]
 38%|███▊      | 23305/61904 [1:54:34<16:01:48,  1.50s/it]
 38%|███▊      | 23306/61904 [1:54:35<15:47:48,  1.47s/it]
 38%|███▊      | 23307/61904 [1:54:37<15:46:46,  1.47s/it]
 38%|███▊      | 23308/61904 [1:54:38<15:33:59,  1.45s/it]
 38%|███▊      | 23309/61904 [1:54:40<15:07:11,  1.41s/it]
 38%|███▊      | 23310/61904 [1:54:41<15:26:52,  1.44s/it]
 38%|███▊      | 23311/61904 [1:54:42<15:13:01,  1.42s/it]
 38%|███▊      | 23312/61904 [1:54:44<15:32:48,  1.45s/it]
 38%|███▊      | 23313/61904 [1:54:45<15:22:29,  1.43s/it]
 38%|███▊      | 23314/61904 [1:54:47<15:11:40,  1.42s/it]
 38%|███▊      | 23315/61904 [1:54:48<15:10:27,  1.42s/it]
 38%|███▊      | 23316/61904 [1:54:49<14:53:23,  1.39s/it]
 38%|███▊      | 23317/61904 [1:54:51<14:59:55,  1.40s/it]
 38%|███▊      | 23318/61904 [1:54:52<15:01:54,  1.40s/it]
 38%|███▊      | 23319/61904 [1:54:54<14:44:15,  1.38s/it]
 38%|███▊      | 23320/61904 [1:54:55<14:58:46,  1.40s/it]
                                                          
{'loss': 2.6804, 'learning_rate': 1.625307921690652e-07, 'epoch': 6.03}

 38%|███▊      | 23320/61904 [1:54:55<14:58:46,  1.40s/it]
 38%|███▊      | 23321/61904 [1:54:56<14:49:54,  1.38s/it]
 38%|███▊      | 23322/61904 [1:54:58<15:09:09,  1.41s/it]
 38%|███▊      | 23323/61904 [1:54:59<15:14:16,  1.42s/it]
 38%|███▊      | 23324/61904 [1:55:01<15:13:31,  1.42s/it]
 38%|███▊      | 23325/61904 [1:55:02<15:12:31,  1.42s/it]
 38%|███▊      | 23326/61904 [1:55:04<15:09:29,  1.41s/it]
 38%|███▊      | 23327/61904 [1:55:05<15:28:30,  1.44s/it]
 38%|███▊      | 23328/61904 [1:55:07<15:27:19,  1.44s/it]
 38%|███▊      | 23329/61904 [1:55:08<15:59:01,  1.49s/it]
 38%|███▊      | 23330/61904 [1:55:10<15:48:57,  1.48s/it]
 38%|███▊      | 23331/61904 [1:55:11<15:46:19,  1.47s/it]
 38%|███▊      | 23332/61904 [1:55:13<16:06:32,  1.50s/it]
 38%|███▊      | 23333/61904 [1:55:14<15:44:21,  1.47s/it]
 38%|███▊      | 23334/61904 [1:55:16<16:02:33,  1.50s/it]
 38%|███▊      | 23335/61904 [1:55:17<15:49:49,  1.48s/it]
 38%|███▊      | 23336/61904 [1:55:18<15:37:08,  1.46s/it]
 38%|███▊      | 23337/61904 [1:55:20<15:18:18,  1.43s/it]
 38%|███▊      | 23338/61904 [1:55:21<15:25:55,  1.44s/it]
 38%|███▊      | 23339/61904 [1:55:23<15:06:11,  1.41s/it]
 38%|███▊      | 23340/61904 [1:55:24<15:09:11,  1.41s/it]
                                                          
{'loss': 2.6283, 'learning_rate': 1.6249837935952287e-07, 'epoch': 6.03}

 38%|███▊      | 23340/61904 [1:55:24<15:09:11,  1.41s/it]
 38%|███▊      | 23341/61904 [1:55:25<15:17:14,  1.43s/it]
 38%|███▊      | 23342/61904 [1:55:27<15:06:58,  1.41s/it]
 38%|███▊      | 23343/61904 [1:55:28<15:13:22,  1.42s/it]
 38%|███▊      | 23344/61904 [1:55:30<14:54:18,  1.39s/it]
 38%|███▊      | 23345/61904 [1:55:31<14:43:45,  1.38s/it]
 38%|███▊      | 23346/61904 [1:55:32<15:04:07,  1.41s/it]
 38%|███▊      | 23347/61904 [1:55:34<15:19:35,  1.43s/it]
 38%|███▊      | 23348/61904 [1:55:35<15:35:30,  1.46s/it]
 38%|███▊      | 23349/61904 [1:55:37<15:42:52,  1.47s/it]
 38%|███▊      | 23350/61904 [1:55:38<15:21:13,  1.43s/it]
 38%|███▊      | 23351/61904 [1:55:40<15:00:26,  1.40s/it]
 38%|███▊      | 23352/61904 [1:55:41<15:15:22,  1.42s/it]
 38%|███▊      | 23353/61904 [1:55:43<15:23:21,  1.44s/it]
 38%|███▊      | 23354/61904 [1:55:44<15:11:47,  1.42s/it]
 38%|███▊      | 23355/61904 [1:55:45<15:19:45,  1.43s/it]
 38%|███▊      | 23356/61904 [1:55:47<15:05:45,  1.41s/it]
 38%|███▊      | 23357/61904 [1:55:48<14:42:00,  1.37s/it]
 38%|███▊      | 23358/61904 [1:55:49<14:34:15,  1.36s/it]
 38%|███▊      | 23359/61904 [1:55:51<14:44:17,  1.38s/it]
 38%|███▊      | 23360/61904 [1:55:52<15:05:25,  1.41s/it]
                                                          
{'loss': 2.6344, 'learning_rate': 1.6246596654998053e-07, 'epoch': 6.04}

 38%|███▊      | 23360/61904 [1:55:52<15:05:25,  1.41s/it]
 38%|███▊      | 23361/61904 [1:55:54<15:23:18,  1.44s/it]
 38%|███▊      | 23362/61904 [1:55:55<15:19:55,  1.43s/it]
 38%|███▊      | 23363/61904 [1:55:57<15:29:38,  1.45s/it]
 38%|███▊      | 23364/61904 [1:55:58<15:26:29,  1.44s/it]
 38%|███▊      | 23365/61904 [1:55:59<15:02:07,  1.40s/it]
 38%|███▊      | 23366/61904 [1:56:01<15:34:19,  1.45s/it]
 38%|███▊      | 23367/61904 [1:56:02<15:02:40,  1.41s/it]
 38%|███▊      | 23368/61904 [1:56:04<15:11:26,  1.42s/it]
 38%|███▊      | 23369/61904 [1:56:05<15:08:48,  1.42s/it]
 38%|███▊      | 23370/61904 [1:56:07<15:02:40,  1.41s/it]
 38%|███▊      | 23371/61904 [1:56:08<14:49:51,  1.39s/it]
 38%|███▊      | 23372/61904 [1:56:09<14:55:12,  1.39s/it]
 38%|███▊      | 23373/61904 [1:56:11<15:11:14,  1.42s/it]
 38%|███▊      | 23374/61904 [1:56:12<15:07:10,  1.41s/it]
 38%|███▊      | 23375/61904 [1:56:14<15:09:03,  1.42s/it]
 38%|███▊      | 23376/61904 [1:56:15<14:57:06,  1.40s/it]
 38%|███▊      | 23377/61904 [1:56:16<14:28:45,  1.35s/it]
 38%|███▊      | 23378/61904 [1:56:18<14:43:17,  1.38s/it]
 38%|███▊      | 23379/61904 [1:56:19<14:34:56,  1.36s/it]
 38%|███▊      | 23380/61904 [1:56:20<15:10:28,  1.42s/it]
                                                          
{'loss': 2.6453, 'learning_rate': 1.6243355374043822e-07, 'epoch': 6.04}

 38%|███▊      | 23380/61904 [1:56:20<15:10:28,  1.42s/it]
 38%|███▊      | 23381/61904 [1:56:22<15:00:48,  1.40s/it]
 38%|███▊      | 23382/61904 [1:56:23<15:25:35,  1.44s/it]
 38%|███▊      | 23383/61904 [1:56:25<15:12:22,  1.42s/it]
 38%|███▊      | 23384/61904 [1:56:26<15:02:19,  1.41s/it]
 38%|███▊      | 23385/61904 [1:56:27<14:28:20,  1.35s/it]
 38%|███▊      | 23386/61904 [1:56:29<15:43:42,  1.47s/it]
 38%|███▊      | 23387/61904 [1:56:31<15:53:28,  1.49s/it]
 38%|███▊      | 23388/61904 [1:56:32<15:20:09,  1.43s/it]
 38%|███▊      | 23389/61904 [1:56:33<15:02:12,  1.41s/it]
 38%|███▊      | 23390/61904 [1:56:35<15:13:53,  1.42s/it]
 38%|███▊      | 23391/61904 [1:56:36<14:50:40,  1.39s/it]
 38%|███▊      | 23392/61904 [1:56:38<15:23:51,  1.44s/it]
 38%|███▊      | 23393/61904 [1:56:39<15:09:47,  1.42s/it]
 38%|███▊      | 23394/61904 [1:56:40<15:28:42,  1.45s/it]
 38%|███▊      | 23395/61904 [1:56:42<15:22:46,  1.44s/it]
 38%|███▊      | 23396/61904 [1:56:43<14:55:54,  1.40s/it]
 38%|███▊      | 23397/61904 [1:56:45<15:02:15,  1.41s/it]
 38%|███▊      | 23398/61904 [1:56:46<14:35:13,  1.36s/it]
 38%|███▊      | 23399/61904 [1:56:47<14:41:02,  1.37s/it]
 38%|███▊      | 23400/61904 [1:56:49<14:36:03,  1.37s/it]
                                                          
{'loss': 2.5926, 'learning_rate': 1.6240114093089586e-07, 'epoch': 6.05}

 38%|███▊      | 23400/61904 [1:56:49<14:36:03,  1.37s/it]
 38%|███▊      | 23401/61904 [1:56:50<14:49:05,  1.39s/it]
 38%|███▊      | 23402/61904 [1:56:52<15:08:41,  1.42s/it]
 38%|███▊      | 23403/61904 [1:56:53<14:51:06,  1.39s/it]
 38%|███▊      | 23404/61904 [1:56:54<14:59:08,  1.40s/it]
 38%|███▊      | 23405/61904 [1:56:56<14:51:33,  1.39s/it]
 38%|███▊      | 23406/61904 [1:56:57<15:40:10,  1.47s/it]
 38%|███▊      | 23407/61904 [1:56:59<15:21:54,  1.44s/it]
 38%|███▊      | 23408/61904 [1:57:00<15:33:10,  1.45s/it]
 38%|███▊      | 23409/61904 [1:57:02<16:34:58,  1.55s/it]
 38%|███▊      | 23410/61904 [1:57:03<16:17:58,  1.52s/it]
 38%|███▊      | 23411/61904 [1:57:05<16:11:17,  1.51s/it]
 38%|███▊      | 23412/61904 [1:57:06<15:33:51,  1.46s/it]
 38%|███▊      | 23413/61904 [1:57:07<14:55:29,  1.40s/it]
 38%|███▊      | 23414/61904 [1:57:09<14:47:16,  1.38s/it]
 38%|███▊      | 23415/61904 [1:57:10<14:19:09,  1.34s/it]
 38%|███▊      | 23416/61904 [1:57:11<14:26:39,  1.35s/it]
 38%|███▊      | 23417/61904 [1:57:13<14:28:53,  1.35s/it]
 38%|███▊      | 23418/61904 [1:57:14<14:27:41,  1.35s/it]
 38%|███▊      | 23419/61904 [1:57:16<14:31:43,  1.36s/it]
 38%|███▊      | 23420/61904 [1:57:17<14:46:47,  1.38s/it]
                                                          
{'loss': 2.6709, 'learning_rate': 1.6236872812135355e-07, 'epoch': 6.05}

 38%|███▊      | 23420/61904 [1:57:17<14:46:47,  1.38s/it]
 38%|███▊      | 23421/61904 [1:57:18<14:26:21,  1.35s/it]
 38%|███▊      | 23422/61904 [1:57:19<14:02:32,  1.31s/it]
 38%|███▊      | 23423/61904 [1:57:21<14:07:15,  1.32s/it]
 38%|███▊      | 23424/61904 [1:57:22<14:33:27,  1.36s/it]
 38%|███▊      | 23425/61904 [1:57:24<14:34:58,  1.36s/it]
 38%|███▊      | 23426/61904 [1:57:25<15:03:02,  1.41s/it]
 38%|███▊      | 23427/61904 [1:57:26<14:36:50,  1.37s/it]
 38%|███▊      | 23428/61904 [1:57:28<14:54:04,  1.39s/it]
 38%|███▊      | 23429/61904 [1:57:29<14:55:54,  1.40s/it]
 38%|███▊      | 23430/61904 [1:57:31<15:03:56,  1.41s/it]
 38%|███▊      | 23431/61904 [1:57:32<15:24:19,  1.44s/it]
 38%|███▊      | 23432/61904 [1:57:34<15:42:26,  1.47s/it]
 38%|███▊      | 23433/61904 [1:57:35<16:02:13,  1.50s/it]
 38%|███▊      | 23434/61904 [1:57:37<15:42:45,  1.47s/it]
 38%|███▊      | 23435/61904 [1:57:38<15:47:01,  1.48s/it]
 38%|███▊      | 23436/61904 [1:57:40<15:27:02,  1.45s/it]
 38%|███▊      | 23437/61904 [1:57:41<15:21:52,  1.44s/it]
 38%|███▊      | 23438/61904 [1:57:43<15:31:28,  1.45s/it]
 38%|███▊      | 23439/61904 [1:57:44<15:21:40,  1.44s/it]
 38%|███▊      | 23440/61904 [1:57:45<14:41:20,  1.37s/it]
                                                          
{'loss': 2.6228, 'learning_rate': 1.6233631531181123e-07, 'epoch': 6.06}

 38%|███▊      | 23440/61904 [1:57:45<14:41:20,  1.37s/it]
 38%|███▊      | 23441/61904 [1:57:47<14:42:45,  1.38s/it]
 38%|███▊      | 23442/61904 [1:57:48<15:12:16,  1.42s/it]
 38%|███▊      | 23443/61904 [1:57:50<15:17:07,  1.43s/it]
 38%|███▊      | 23444/61904 [1:57:51<15:12:48,  1.42s/it]
 38%|███▊      | 23445/61904 [1:57:52<15:30:04,  1.45s/it]
 38%|███▊      | 23446/61904 [1:57:54<15:38:09,  1.46s/it]
 38%|███▊      | 23447/61904 [1:57:56<16:09:13,  1.51s/it]
 38%|███▊      | 23448/61904 [1:57:57<15:58:15,  1.50s/it]
 38%|███▊      | 23449/61904 [1:57:58<15:46:22,  1.48s/it]
 38%|███▊      | 23450/61904 [1:58:00<15:35:37,  1.46s/it]
 38%|███▊      | 23451/61904 [1:58:01<15:13:54,  1.43s/it]
 38%|███▊      | 23452/61904 [1:58:03<15:07:32,  1.42s/it]
 38%|███▊      | 23453/61904 [1:58:04<14:49:20,  1.39s/it]
 38%|███▊      | 23454/61904 [1:58:05<14:10:13,  1.33s/it]
 38%|███▊      | 23455/61904 [1:58:06<14:14:35,  1.33s/it]
 38%|███▊      | 23456/61904 [1:58:08<14:17:11,  1.34s/it]
 38%|███▊      | 23457/61904 [1:58:09<14:24:14,  1.35s/it]
 38%|███▊      | 23458/61904 [1:58:11<14:34:27,  1.36s/it]
 38%|███▊      | 23459/61904 [1:58:12<14:33:47,  1.36s/it]
 38%|███▊      | 23460/61904 [1:58:13<14:25:04,  1.35s/it]
                                                          
{'loss': 2.6006, 'learning_rate': 1.6230390250226887e-07, 'epoch': 6.06}

 38%|███▊      | 23460/61904 [1:58:13<14:25:04,  1.35s/it]
 38%|███▊      | 23461/61904 [1:58:15<14:36:45,  1.37s/it]
 38%|███▊      | 23462/61904 [1:58:16<14:44:16,  1.38s/it]
 38%|███▊      | 23463/61904 [1:58:18<14:59:57,  1.40s/it]
 38%|███▊      | 23464/61904 [1:58:19<14:48:42,  1.39s/it]
 38%|███▊      | 23465/61904 [1:58:20<14:31:14,  1.36s/it]
 38%|███▊      | 23466/61904 [1:58:22<14:45:06,  1.38s/it]
 38%|███▊      | 23467/61904 [1:58:23<15:15:32,  1.43s/it]
 38%|███▊      | 23468/61904 [1:58:25<15:46:57,  1.48s/it]
 38%|███▊      | 23469/61904 [1:58:26<15:45:02,  1.48s/it]
 38%|███▊      | 23470/61904 [1:58:28<15:25:29,  1.44s/it]
 38%|███▊      | 23471/61904 [1:58:29<15:14:29,  1.43s/it]
 38%|███▊      | 23472/61904 [1:58:30<15:12:47,  1.43s/it]
 38%|███▊      | 23473/61904 [1:58:32<15:20:28,  1.44s/it]
 38%|███▊      | 23474/61904 [1:58:33<15:16:41,  1.43s/it]
 38%|███▊      | 23475/61904 [1:58:35<15:07:16,  1.42s/it]
 38%|███▊      | 23476/61904 [1:58:36<14:55:59,  1.40s/it]
 38%|███▊      | 23477/61904 [1:58:38<15:27:11,  1.45s/it]
 38%|███▊      | 23478/61904 [1:58:39<14:50:43,  1.39s/it]
 38%|███▊      | 23479/61904 [1:58:40<14:38:40,  1.37s/it]
 38%|███▊      | 23480/61904 [1:58:42<14:38:30,  1.37s/it]
                                                          
{'loss': 2.6179, 'learning_rate': 1.6227148969272656e-07, 'epoch': 6.07}

 38%|███▊      | 23480/61904 [1:58:42<14:38:30,  1.37s/it]
 38%|███▊      | 23481/61904 [1:58:43<15:00:22,  1.41s/it]
 38%|███▊      | 23482/61904 [1:58:44<14:54:05,  1.40s/it]
 38%|███▊      | 23483/61904 [1:58:46<14:35:48,  1.37s/it]
 38%|███▊      | 23484/61904 [1:58:47<14:56:54,  1.40s/it]
 38%|███▊      | 23485/61904 [1:58:49<14:57:07,  1.40s/it]
 38%|███▊      | 23486/61904 [1:58:50<14:29:31,  1.36s/it]
 38%|███▊      | 23487/61904 [1:58:51<14:39:55,  1.37s/it]
 38%|███▊      | 23488/61904 [1:58:53<14:26:14,  1.35s/it]
 38%|███▊      | 23489/61904 [1:58:54<14:47:39,  1.39s/it]
 38%|███▊      | 23490/61904 [1:58:55<14:51:30,  1.39s/it]
 38%|███▊      | 23491/61904 [1:58:57<14:48:46,  1.39s/it]
 38%|███▊      | 23492/61904 [1:58:58<14:38:34,  1.37s/it]
 38%|███▊      | 23493/61904 [1:58:59<14:25:32,  1.35s/it]
 38%|███▊      | 23494/61904 [1:59:01<15:14:11,  1.43s/it]
 38%|███▊      | 23495/61904 [1:59:03<15:30:29,  1.45s/it]
 38%|███▊      | 23496/61904 [1:59:04<15:42:23,  1.47s/it]
 38%|███▊      | 23497/61904 [1:59:06<16:06:38,  1.51s/it]
 38%|███▊      | 23498/61904 [1:59:07<15:45:04,  1.48s/it]
 38%|███▊      | 23499/61904 [1:59:09<15:48:30,  1.48s/it]
 38%|███▊      | 23500/61904 [1:59:10<15:53:41,  1.49s/it]
                                                          
{'loss': 2.63, 'learning_rate': 1.6223907688318425e-07, 'epoch': 6.07}

 38%|███▊      | 23500/61904 [1:59:10<15:53:41,  1.49s/it]
 38%|███▊      | 23501/61904 [1:59:11<15:27:58,  1.45s/it]
 38%|███▊      | 23502/61904 [1:59:13<15:14:23,  1.43s/it]
 38%|███▊      | 23503/61904 [1:59:14<14:43:29,  1.38s/it]
 38%|███▊      | 23504/61904 [1:59:15<14:48:58,  1.39s/it]
 38%|███▊      | 23505/61904 [1:59:17<14:49:33,  1.39s/it]
 38%|███▊      | 23506/61904 [1:59:18<14:50:14,  1.39s/it]
 38%|███▊      | 23507/61904 [1:59:20<14:29:18,  1.36s/it]
 38%|███▊      | 23508/61904 [1:59:21<14:33:19,  1.36s/it]
 38%|███▊      | 23509/61904 [1:59:22<14:25:08,  1.35s/it]
 38%|███▊      | 23510/61904 [1:59:24<14:20:01,  1.34s/it]
 38%|███▊      | 23511/61904 [1:59:25<14:40:00,  1.38s/it]
 38%|███▊      | 23512/61904 [1:59:26<14:45:09,  1.38s/it]
 38%|███▊      | 23513/61904 [1:59:28<14:20:33,  1.34s/it]
 38%|███▊      | 23514/61904 [1:59:29<14:24:34,  1.35s/it]
 38%|███▊      | 23515/61904 [1:59:30<14:37:57,  1.37s/it]
 38%|███▊      | 23516/61904 [1:59:32<14:29:31,  1.36s/it]
 38%|███▊      | 23517/61904 [1:59:33<14:56:17,  1.40s/it]
 38%|███▊      | 23518/61904 [1:59:35<14:49:26,  1.39s/it]
 38%|███▊      | 23519/61904 [1:59:36<14:32:30,  1.36s/it]
 38%|███▊      | 23520/61904 [1:59:37<14:35:46,  1.37s/it]
                                                          
{'loss': 2.653, 'learning_rate': 1.6220666407364188e-07, 'epoch': 6.08}

 38%|███▊      | 23520/61904 [1:59:37<14:35:46,  1.37s/it]
 38%|███▊      | 23521/61904 [1:59:39<15:06:08,  1.42s/it]
 38%|███▊      | 23522/61904 [1:59:40<14:44:01,  1.38s/it]
 38%|███▊      | 23523/61904 [1:59:42<14:32:36,  1.36s/it]
 38%|███▊      | 23524/61904 [1:59:43<14:26:13,  1.35s/it]
 38%|███▊      | 23525/61904 [1:59:44<14:48:38,  1.39s/it]
 38%|███▊      | 23526/61904 [1:59:46<15:50:13,  1.49s/it]
 38%|███▊      | 23527/61904 [1:59:47<15:46:04,  1.48s/it]
 38%|███▊      | 23528/61904 [1:59:49<15:41:28,  1.47s/it]
 38%|███▊      | 23529/61904 [1:59:50<15:46:46,  1.48s/it]
 38%|███▊      | 23530/61904 [1:59:52<15:29:49,  1.45s/it]
 38%|███▊      | 23531/61904 [1:59:53<15:31:32,  1.46s/it]
 38%|███▊      | 23532/61904 [1:59:55<15:41:23,  1.47s/it]
 38%|███▊      | 23533/61904 [1:59:56<16:11:44,  1.52s/it]
 38%|███▊      | 23534/61904 [1:59:58<16:36:21,  1.56s/it]
 38%|███▊      | 23535/61904 [1:59:59<15:46:02,  1.48s/it]
 38%|███▊      | 23536/61904 [2:00:01<15:09:15,  1.42s/it]
 38%|███▊      | 23537/61904 [2:00:02<15:06:34,  1.42s/it]
 38%|███▊      | 23538/61904 [2:00:04<15:13:43,  1.43s/it]
 38%|███▊      | 23539/61904 [2:00:05<15:28:09,  1.45s/it]
 38%|███▊      | 23540/61904 [2:00:07<15:35:51,  1.46s/it]
                                                          
{'loss': 2.6129, 'learning_rate': 1.6217425126409957e-07, 'epoch': 6.08}

 38%|███▊      | 23540/61904 [2:00:07<15:35:51,  1.46s/it]
 38%|███▊      | 23541/61904 [2:00:08<15:30:22,  1.46s/it]
 38%|███▊      | 23542/61904 [2:00:09<15:11:23,  1.43s/it]
 38%|███▊      | 23543/61904 [2:00:11<15:03:52,  1.41s/it]
 38%|███▊      | 23544/61904 [2:00:12<15:25:15,  1.45s/it]
 38%|███▊      | 23545/61904 [2:00:14<15:12:39,  1.43s/it]
 38%|███▊      | 23546/61904 [2:00:15<15:01:04,  1.41s/it]
 38%|███▊      | 23547/61904 [2:00:16<14:38:36,  1.37s/it]
 38%|███▊      | 23548/61904 [2:00:18<14:41:06,  1.38s/it]
 38%|███▊      | 23549/61904 [2:00:19<14:45:34,  1.39s/it]
 38%|███▊      | 23550/61904 [2:00:20<14:51:10,  1.39s/it]
 38%|███▊      | 23551/61904 [2:00:22<15:29:33,  1.45s/it]
 38%|███▊      | 23552/61904 [2:00:23<15:09:54,  1.42s/it]
 38%|███▊      | 23553/61904 [2:00:25<15:15:00,  1.43s/it]
 38%|███▊      | 23554/61904 [2:00:26<14:49:47,  1.39s/it]
 38%|███▊      | 23555/61904 [2:00:28<15:14:00,  1.43s/it]
 38%|███▊      | 23556/61904 [2:00:29<15:03:43,  1.41s/it]
 38%|███▊      | 23557/61904 [2:00:30<14:54:44,  1.40s/it]
 38%|███▊      | 23558/61904 [2:00:32<14:57:09,  1.40s/it]
 38%|███▊      | 23559/61904 [2:00:33<14:56:55,  1.40s/it]
 38%|███▊      | 23560/61904 [2:00:35<14:56:21,  1.40s/it]
                                                          
{'loss': 2.6008, 'learning_rate': 1.6214183845455723e-07, 'epoch': 6.09}

 38%|███▊      | 23560/61904 [2:00:35<14:56:21,  1.40s/it]
 38%|███▊      | 23561/61904 [2:00:36<14:47:53,  1.39s/it]
 38%|███▊      | 23562/61904 [2:00:38<15:08:09,  1.42s/it]
 38%|███▊      | 23563/61904 [2:00:39<15:20:11,  1.44s/it]
 38%|███▊      | 23564/61904 [2:00:40<15:18:23,  1.44s/it]
 38%|███▊      | 23565/61904 [2:00:42<15:20:42,  1.44s/it]
 38%|███▊      | 23566/61904 [2:00:43<15:51:57,  1.49s/it]
 38%|███▊      | 23567/61904 [2:00:45<15:21:59,  1.44s/it]
 38%|███▊      | 23568/61904 [2:00:46<15:37:36,  1.47s/it]
 38%|███▊      | 23569/61904 [2:00:48<15:35:17,  1.46s/it]
 38%|███▊      | 23570/61904 [2:00:49<15:37:06,  1.47s/it]
 38%|███▊      | 23571/61904 [2:00:51<15:19:06,  1.44s/it]
 38%|███▊      | 23572/61904 [2:00:52<15:25:38,  1.45s/it]
 38%|███▊      | 23573/61904 [2:00:54<15:30:08,  1.46s/it]
 38%|███▊      | 23574/61904 [2:00:55<15:19:02,  1.44s/it]
 38%|███▊      | 23575/61904 [2:00:56<15:16:35,  1.43s/it]
 38%|███▊      | 23576/61904 [2:00:58<15:14:43,  1.43s/it]
 38%|███▊      | 23577/61904 [2:00:59<15:30:42,  1.46s/it]
 38%|███▊      | 23578/61904 [2:01:01<14:57:54,  1.41s/it]
 38%|███▊      | 23579/61904 [2:01:02<15:26:58,  1.45s/it]
 38%|███▊      | 23580/61904 [2:01:04<15:11:07,  1.43s/it]
                                                          
{'loss': 2.6594, 'learning_rate': 1.621094256450149e-07, 'epoch': 6.09}

 38%|███▊      | 23580/61904 [2:01:04<15:11:07,  1.43s/it]
 38%|███▊      | 23581/61904 [2:01:05<15:00:04,  1.41s/it]
 38%|███▊      | 23582/61904 [2:01:06<15:04:31,  1.42s/it]
 38%|███▊      | 23583/61904 [2:01:08<14:54:04,  1.40s/it]
 38%|███▊      | 23584/61904 [2:01:09<15:08:52,  1.42s/it]
 38%|███▊      | 23585/61904 [2:01:11<15:01:43,  1.41s/it]
 38%|███▊      | 23586/61904 [2:01:12<15:15:58,  1.43s/it]
 38%|███▊      | 23587/61904 [2:01:14<15:21:25,  1.44s/it]
 38%|███▊      | 23588/61904 [2:01:15<15:40:09,  1.47s/it]
 38%|███▊      | 23589/61904 [2:01:17<15:33:49,  1.46s/it]
 38%|███▊      | 23590/61904 [2:01:18<15:01:07,  1.41s/it]
 38%|███▊      | 23591/61904 [2:01:19<15:08:45,  1.42s/it]
 38%|███▊      | 23592/61904 [2:01:21<15:06:30,  1.42s/it]
 38%|███▊      | 23593/61904 [2:01:22<15:05:13,  1.42s/it]
 38%|███▊      | 23594/61904 [2:01:23<15:03:12,  1.41s/it]
 38%|███▊      | 23595/61904 [2:01:25<14:55:08,  1.40s/it]
 38%|███▊      | 23596/61904 [2:01:26<15:07:54,  1.42s/it]
 38%|███▊      | 23597/61904 [2:01:28<14:53:50,  1.40s/it]
 38%|███▊      | 23598/61904 [2:01:29<14:44:37,  1.39s/it]
 38%|███▊      | 23599/61904 [2:01:30<14:54:00,  1.40s/it]
 38%|███▊      | 23600/61904 [2:01:32<14:37:13,  1.37s/it]
                                                          
{'loss': 2.617, 'learning_rate': 1.6207701283547258e-07, 'epoch': 6.1}

 38%|███▊      | 23600/61904 [2:01:32<14:37:13,  1.37s/it]
 38%|███▊      | 23601/61904 [2:01:33<14:44:37,  1.39s/it]
 38%|███▊      | 23602/61904 [2:01:35<15:04:40,  1.42s/it]
 38%|███▊      | 23603/61904 [2:01:36<14:47:29,  1.39s/it]
 38%|███▊      | 23604/61904 [2:01:37<15:00:17,  1.41s/it]
 38%|███▊      | 23605/61904 [2:01:39<15:15:42,  1.43s/it]
 38%|███▊      | 23606/61904 [2:01:41<15:51:39,  1.49s/it]
 38%|███▊      | 23607/61904 [2:01:42<14:54:43,  1.40s/it]
 38%|███▊      | 23608/61904 [2:01:43<14:56:10,  1.40s/it]
 38%|███▊      | 23609/61904 [2:01:45<15:13:52,  1.43s/it]
 38%|███▊      | 23610/61904 [2:01:46<14:42:36,  1.38s/it]
 38%|███▊      | 23611/61904 [2:01:47<14:54:09,  1.40s/it]
 38%|███▊      | 23612/61904 [2:01:49<14:50:37,  1.40s/it]
 38%|███▊      | 23613/61904 [2:01:50<14:53:41,  1.40s/it]
 38%|███▊      | 23614/61904 [2:01:52<15:00:53,  1.41s/it]
 38%|███▊      | 23615/61904 [2:01:53<15:20:52,  1.44s/it]
 38%|███▊      | 23616/61904 [2:01:54<15:03:36,  1.42s/it]
 38%|███▊      | 23617/61904 [2:01:56<15:00:31,  1.41s/it]
 38%|███▊      | 23618/61904 [2:01:57<15:02:21,  1.41s/it]
 38%|███▊      | 23619/61904 [2:01:59<15:04:35,  1.42s/it]
 38%|███▊      | 23620/61904 [2:02:00<14:59:45,  1.41s/it]
                                                          
{'loss': 2.6392, 'learning_rate': 1.6204460002593022e-07, 'epoch': 6.1}

 38%|███▊      | 23620/61904 [2:02:00<14:59:45,  1.41s/it]
 38%|███▊      | 23621/61904 [2:02:01<14:47:30,  1.39s/it]
 38%|███▊      | 23622/61904 [2:02:03<14:25:32,  1.36s/it]
 38%|███▊      | 23623/61904 [2:02:04<14:33:49,  1.37s/it]
 38%|███▊      | 23624/61904 [2:02:06<14:43:38,  1.39s/it]
 38%|███▊      | 23625/61904 [2:02:07<14:19:00,  1.35s/it]
 38%|███▊      | 23626/61904 [2:02:08<14:43:25,  1.38s/it]
 38%|███▊      | 23627/61904 [2:02:10<14:56:11,  1.40s/it]
 38%|███▊      | 23628/61904 [2:02:11<14:57:16,  1.41s/it]
 38%|███▊      | 23629/61904 [2:02:13<14:56:33,  1.41s/it]
 38%|███▊      | 23630/61904 [2:02:14<14:33:46,  1.37s/it]
 38%|███▊      | 23631/61904 [2:02:15<14:40:08,  1.38s/it]
 38%|███▊      | 23632/61904 [2:02:17<14:38:48,  1.38s/it]
 38%|███▊      | 23633/61904 [2:02:18<14:42:28,  1.38s/it]
 38%|███▊      | 23634/61904 [2:02:19<14:26:36,  1.36s/it]
 38%|███▊      | 23635/61904 [2:02:21<14:25:34,  1.36s/it]
 38%|███▊      | 23636/61904 [2:02:22<14:38:54,  1.38s/it]
 38%|███▊      | 23637/61904 [2:02:24<14:52:31,  1.40s/it]
 38%|███▊      | 23638/61904 [2:02:25<14:51:26,  1.40s/it]
 38%|███▊      | 23639/61904 [2:02:26<14:17:28,  1.34s/it]
 38%|███▊      | 23640/61904 [2:02:27<14:08:51,  1.33s/it]
                                                          
{'loss': 2.6315, 'learning_rate': 1.620121872163879e-07, 'epoch': 6.11}

 38%|███▊      | 23640/61904 [2:02:27<14:08:51,  1.33s/it]
 38%|███▊      | 23641/61904 [2:02:29<14:09:53,  1.33s/it]
 38%|███▊      | 23642/61904 [2:02:30<14:44:55,  1.39s/it]
 38%|███▊      | 23643/61904 [2:02:32<14:46:12,  1.39s/it]
 38%|███▊      | 23644/61904 [2:02:33<14:49:37,  1.40s/it]
 38%|███▊      | 23645/61904 [2:02:34<14:43:38,  1.39s/it]
 38%|███▊      | 23646/61904 [2:02:36<14:38:07,  1.38s/it]
 38%|███▊      | 23647/61904 [2:02:37<14:25:11,  1.36s/it]
 38%|███▊      | 23648/61904 [2:02:39<14:52:49,  1.40s/it]
 38%|███▊      | 23649/61904 [2:02:40<14:29:51,  1.36s/it]
 38%|███▊      | 23650/61904 [2:02:41<14:34:42,  1.37s/it]
 38%|███▊      | 23651/61904 [2:02:43<15:00:07,  1.41s/it]
 38%|███▊      | 23652/61904 [2:02:45<15:52:02,  1.49s/it]
 38%|███▊      | 23653/61904 [2:02:46<15:03:46,  1.42s/it]
 38%|███▊      | 23654/61904 [2:02:47<14:47:26,  1.39s/it]
 38%|███▊      | 23655/61904 [2:02:48<14:49:02,  1.39s/it]
 38%|███▊      | 23656/61904 [2:02:50<15:10:48,  1.43s/it]
 38%|███▊      | 23657/61904 [2:02:51<14:41:01,  1.38s/it]
 38%|███▊      | 23658/61904 [2:02:53<14:51:15,  1.40s/it]
 38%|███▊      | 23659/61904 [2:02:54<14:56:12,  1.41s/it]
 38%|███▊      | 23660/61904 [2:02:55<14:47:22,  1.39s/it]
                                                          
{'loss': 2.6131, 'learning_rate': 1.619797744068456e-07, 'epoch': 6.12}

 38%|███▊      | 23660/61904 [2:02:55<14:47:22,  1.39s/it]
 38%|███▊      | 23661/61904 [2:02:57<15:14:35,  1.43s/it]
 38%|███▊      | 23662/61904 [2:02:59<15:29:50,  1.46s/it]
 38%|███▊      | 23663/61904 [2:03:00<15:16:33,  1.44s/it]
 38%|███▊      | 23664/61904 [2:03:01<15:22:08,  1.45s/it]
 38%|███▊      | 23665/61904 [2:03:03<14:41:26,  1.38s/it]
 38%|███▊      | 23666/61904 [2:03:04<14:33:28,  1.37s/it]
 38%|███▊      | 23667/61904 [2:03:05<14:48:25,  1.39s/it]
 38%|███▊      | 23668/61904 [2:03:07<15:04:53,  1.42s/it]
 38%|███▊      | 23669/61904 [2:03:08<14:58:58,  1.41s/it]
 38%|███▊      | 23670/61904 [2:03:10<14:31:00,  1.37s/it]
 38%|███▊      | 23671/61904 [2:03:11<14:33:43,  1.37s/it]
 38%|███▊      | 23672/61904 [2:03:12<14:17:08,  1.35s/it]
 38%|███▊      | 23673/61904 [2:03:14<14:18:12,  1.35s/it]
 38%|███▊      | 23674/61904 [2:03:15<14:46:11,  1.39s/it]
 38%|███▊      | 23675/61904 [2:03:16<14:39:43,  1.38s/it]
 38%|███▊      | 23676/61904 [2:03:18<15:09:43,  1.43s/it]
 38%|███▊      | 23677/61904 [2:03:19<14:54:08,  1.40s/it]
 38%|███▊      | 23678/61904 [2:03:21<14:48:08,  1.39s/it]
 38%|███▊      | 23679/61904 [2:03:22<14:51:04,  1.40s/it]
 38%|███▊      | 23680/61904 [2:03:24<15:02:06,  1.42s/it]
                                                          
{'loss': 2.6512, 'learning_rate': 1.6194736159730323e-07, 'epoch': 6.12}

 38%|███▊      | 23680/61904 [2:03:24<15:02:06,  1.42s/it]
 38%|███▊      | 23681/61904 [2:03:25<14:47:33,  1.39s/it]
 38%|███▊      | 23682/61904 [2:03:26<14:57:07,  1.41s/it]
 38%|███▊      | 23683/61904 [2:03:28<15:36:09,  1.47s/it]
 38%|███▊      | 23684/61904 [2:03:29<15:18:09,  1.44s/it]
 38%|███▊      | 23685/61904 [2:03:31<15:28:46,  1.46s/it]
 38%|███▊      | 23686/61904 [2:03:32<15:54:16,  1.50s/it]
 38%|███▊      | 23687/61904 [2:03:34<15:46:45,  1.49s/it]
 38%|███▊      | 23688/61904 [2:03:35<15:54:44,  1.50s/it]
 38%|███▊      | 23689/61904 [2:03:37<15:29:18,  1.46s/it]
 38%|███▊      | 23690/61904 [2:03:38<15:56:42,  1.50s/it]
 38%|███▊      | 23691/61904 [2:03:40<15:40:18,  1.48s/it]
 38%|███▊      | 23692/61904 [2:03:41<15:47:14,  1.49s/it]
 38%|███▊      | 23693/61904 [2:03:43<15:06:07,  1.42s/it]
 38%|███▊      | 23694/61904 [2:03:44<15:37:31,  1.47s/it]
 38%|███▊      | 23695/61904 [2:03:46<15:35:44,  1.47s/it]
 38%|███▊      | 23696/61904 [2:03:47<15:24:12,  1.45s/it]
 38%|███▊      | 23697/61904 [2:03:48<15:10:13,  1.43s/it]
 38%|███▊      | 23698/61904 [2:03:50<14:44:20,  1.39s/it]
 38%|███▊      | 23699/61904 [2:03:51<14:49:17,  1.40s/it]
 38%|███▊      | 23700/61904 [2:03:53<15:12:54,  1.43s/it]
                                                          
{'loss': 2.6196, 'learning_rate': 1.6191494878776092e-07, 'epoch': 6.13}

 38%|███▊      | 23700/61904 [2:03:53<15:12:54,  1.43s/it]
 38%|███▊      | 23701/61904 [2:03:54<14:58:30,  1.41s/it]
 38%|███▊      | 23702/61904 [2:03:55<14:35:05,  1.37s/it]
 38%|███▊      | 23703/61904 [2:03:57<14:16:59,  1.35s/it]
 38%|███▊      | 23704/61904 [2:03:58<14:32:13,  1.37s/it]
 38%|███▊      | 23705/61904 [2:03:59<14:28:51,  1.36s/it]
 38%|███▊      | 23706/61904 [2:04:01<14:35:02,  1.37s/it]
 38%|███▊      | 23707/61904 [2:04:02<14:30:33,  1.37s/it]
 38%|███▊      | 23708/61904 [2:04:03<14:19:28,  1.35s/it]
 38%|███▊      | 23709/61904 [2:04:05<14:33:34,  1.37s/it]
 38%|███▊      | 23710/61904 [2:04:06<14:32:12,  1.37s/it]
 38%|███▊      | 23711/61904 [2:04:08<14:37:23,  1.38s/it]
 38%|███▊      | 23712/61904 [2:04:09<14:27:34,  1.36s/it]
 38%|███▊      | 23713/61904 [2:04:10<14:25:48,  1.36s/it]
 38%|███▊      | 23714/61904 [2:04:12<14:33:02,  1.37s/it]
 38%|███▊      | 23715/61904 [2:04:13<14:25:05,  1.36s/it]
 38%|███▊      | 23716/61904 [2:04:14<14:53:29,  1.40s/it]
 38%|███▊      | 23717/61904 [2:04:16<14:46:31,  1.39s/it]
 38%|███▊      | 23718/61904 [2:04:17<15:11:27,  1.43s/it]
 38%|███▊      | 23719/61904 [2:04:19<15:32:17,  1.46s/it]
 38%|███▊      | 23720/61904 [2:04:20<15:37:21,  1.47s/it]
                                                          
{'loss': 2.6234, 'learning_rate': 1.618825359782186e-07, 'epoch': 6.13}

 38%|███▊      | 23720/61904 [2:04:20<15:37:21,  1.47s/it]
 38%|███▊      | 23721/61904 [2:04:22<15:20:15,  1.45s/it]
 38%|███▊      | 23722/61904 [2:04:23<15:52:09,  1.50s/it]
 38%|███▊      | 23723/61904 [2:04:25<15:30:58,  1.46s/it]
 38%|███▊      | 23724/61904 [2:04:26<15:38:04,  1.47s/it]
 38%|███▊      | 23725/61904 [2:04:28<15:17:21,  1.44s/it]
 38%|███▊      | 23726/61904 [2:04:29<15:17:11,  1.44s/it]
 38%|███▊      | 23727/61904 [2:04:31<15:11:11,  1.43s/it]
 38%|███▊      | 23728/61904 [2:04:32<15:07:00,  1.43s/it]
 38%|███▊      | 23729/61904 [2:04:33<15:03:15,  1.42s/it]
 38%|███▊      | 23730/61904 [2:04:35<14:38:30,  1.38s/it]
 38%|███▊      | 23731/61904 [2:04:36<14:18:48,  1.35s/it]
 38%|███▊      | 23732/61904 [2:04:37<14:50:33,  1.40s/it]
 38%|███▊      | 23733/61904 [2:04:39<14:47:26,  1.39s/it]
 38%|███▊      | 23734/61904 [2:04:40<14:47:27,  1.39s/it]
 38%|███▊      | 23735/61904 [2:04:42<14:57:43,  1.41s/it]
 38%|███▊      | 23736/61904 [2:04:43<14:54:13,  1.41s/it]
 38%|███▊      | 23737/61904 [2:04:44<14:50:05,  1.40s/it]
 38%|███▊      | 23738/61904 [2:04:46<14:40:27,  1.38s/it]
 38%|███▊      | 23739/61904 [2:04:47<14:29:26,  1.37s/it]
 38%|███▊      | 23740/61904 [2:04:49<14:49:24,  1.40s/it]
                                                          
{'loss': 2.5817, 'learning_rate': 1.6185012316867624e-07, 'epoch': 6.14}

 38%|███▊      | 23740/61904 [2:04:49<14:49:24,  1.40s/it]
 38%|███▊      | 23741/61904 [2:04:50<14:42:37,  1.39s/it]
 38%|███▊      | 23742/61904 [2:04:51<15:04:54,  1.42s/it]
 38%|███▊      | 23743/61904 [2:04:53<14:58:57,  1.41s/it]
 38%|███▊      | 23744/61904 [2:04:54<15:09:14,  1.43s/it]
 38%|███▊      | 23745/61904 [2:04:56<15:03:37,  1.42s/it]
 38%|███▊      | 23746/61904 [2:04:57<15:09:12,  1.43s/it]
 38%|███▊      | 23747/61904 [2:04:59<15:15:19,  1.44s/it]
 38%|███▊      | 23748/61904 [2:05:00<15:21:37,  1.45s/it]
 38%|███▊      | 23749/61904 [2:05:01<15:13:17,  1.44s/it]
 38%|███▊      | 23750/61904 [2:05:03<15:15:14,  1.44s/it]
 38%|███▊      | 23751/61904 [2:05:04<15:09:21,  1.43s/it]
 38%|███▊      | 23752/61904 [2:05:06<15:05:43,  1.42s/it]
 38%|███▊      | 23753/61904 [2:05:07<15:04:48,  1.42s/it]
 38%|███▊      | 23754/61904 [2:05:08<14:39:29,  1.38s/it]
 38%|███▊      | 23755/61904 [2:05:10<14:41:10,  1.39s/it]
 38%|███▊      | 23756/61904 [2:05:11<14:35:22,  1.38s/it]
 38%|███▊      | 23757/61904 [2:05:13<14:36:38,  1.38s/it]
 38%|███▊      | 23758/61904 [2:05:14<14:58:46,  1.41s/it]
 38%|███▊      | 23759/61904 [2:05:15<14:33:18,  1.37s/it]
 38%|███▊      | 23760/61904 [2:05:17<14:36:06,  1.38s/it]
                                                          
{'loss': 2.5873, 'learning_rate': 1.6181771035913393e-07, 'epoch': 6.14}

 38%|███▊      | 23760/61904 [2:05:17<14:36:06,  1.38s/it]
 38%|███▊      | 23761/61904 [2:05:18<14:47:56,  1.40s/it]
 38%|███▊      | 23762/61904 [2:05:20<14:39:46,  1.38s/it]
 38%|███▊      | 23763/61904 [2:05:21<14:43:44,  1.39s/it]
 38%|███▊      | 23764/61904 [2:05:22<15:03:33,  1.42s/it]
 38%|███▊      | 23765/61904 [2:05:24<15:03:00,  1.42s/it]
 38%|███▊      | 23766/61904 [2:05:25<14:24:36,  1.36s/it]
 38%|███▊      | 23767/61904 [2:05:26<14:20:33,  1.35s/it]
 38%|███▊      | 23768/61904 [2:05:28<14:24:12,  1.36s/it]
 38%|███▊      | 23769/61904 [2:05:29<14:37:34,  1.38s/it]
 38%|███▊      | 23770/61904 [2:05:31<14:26:21,  1.36s/it]
 38%|███▊      | 23771/61904 [2:05:32<14:23:18,  1.36s/it]
 38%|███▊      | 23772/61904 [2:05:33<14:47:03,  1.40s/it]
 38%|███▊      | 23773/61904 [2:05:35<14:40:21,  1.39s/it]
 38%|███▊      | 23774/61904 [2:05:36<14:36:24,  1.38s/it]
 38%|███▊      | 23775/61904 [2:05:38<14:42:32,  1.39s/it]
 38%|███▊      | 23776/61904 [2:05:39<14:30:31,  1.37s/it]
 38%|███▊      | 23777/61904 [2:05:40<14:46:24,  1.39s/it]
 38%|███▊      | 23778/61904 [2:05:42<15:01:08,  1.42s/it]
 38%|███▊      | 23779/61904 [2:05:43<14:55:24,  1.41s/it]
 38%|███▊      | 23780/61904 [2:05:45<14:58:13,  1.41s/it]
                                                          
{'loss': 2.5957, 'learning_rate': 1.617852975495916e-07, 'epoch': 6.15}

 38%|███▊      | 23780/61904 [2:05:45<14:58:13,  1.41s/it]
 38%|███▊      | 23781/61904 [2:05:46<14:37:56,  1.38s/it]
 38%|███▊      | 23782/61904 [2:05:47<14:21:43,  1.36s/it]
 38%|███▊      | 23783/61904 [2:05:49<14:29:14,  1.37s/it]
 38%|███▊      | 23784/61904 [2:05:50<14:01:42,  1.32s/it]
 38%|███▊      | 23785/61904 [2:05:51<14:26:43,  1.36s/it]
 38%|███▊      | 23786/61904 [2:05:53<14:24:15,  1.36s/it]
 38%|███▊      | 23787/61904 [2:05:54<14:14:30,  1.35s/it]
 38%|███▊      | 23788/61904 [2:05:55<14:29:54,  1.37s/it]
 38%|███▊      | 23789/61904 [2:05:57<14:43:21,  1.39s/it]
 38%|███▊      | 23790/61904 [2:05:58<14:56:27,  1.41s/it]
 38%|███▊      | 23791/61904 [2:06:00<14:58:30,  1.41s/it]
 38%|███▊      | 23792/61904 [2:06:01<15:21:12,  1.45s/it]
 38%|███▊      | 23793/61904 [2:06:03<15:08:23,  1.43s/it]
 38%|███▊      | 23794/61904 [2:06:04<14:40:52,  1.39s/it]
 38%|███▊      | 23795/61904 [2:06:05<14:28:03,  1.37s/it]
 38%|███▊      | 23796/61904 [2:06:07<14:27:45,  1.37s/it]
 38%|███▊      | 23797/61904 [2:06:08<14:24:14,  1.36s/it]
 38%|███▊      | 23798/61904 [2:06:09<14:18:05,  1.35s/it]
 38%|███▊      | 23799/61904 [2:06:11<14:45:29,  1.39s/it]
 38%|███▊      | 23800/61904 [2:06:12<14:28:56,  1.37s/it]
                                                          
{'loss': 2.613, 'learning_rate': 1.6175288474004925e-07, 'epoch': 6.15}

 38%|███▊      | 23800/61904 [2:06:12<14:28:56,  1.37s/it]
 38%|███▊      | 23801/61904 [2:06:14<14:47:50,  1.40s/it]
 38%|███▊      | 23802/61904 [2:06:15<14:58:44,  1.42s/it]
 38%|███▊      | 23803/61904 [2:06:16<14:42:42,  1.39s/it]
 38%|███▊      | 23804/61904 [2:06:18<14:49:31,  1.40s/it]
 38%|███▊      | 23805/61904 [2:06:19<14:56:44,  1.41s/it]
 38%|███▊      | 23806/61904 [2:06:21<15:17:56,  1.45s/it]
 38%|███▊      | 23807/61904 [2:06:22<14:53:10,  1.41s/it]
 38%|███▊      | 23808/61904 [2:06:24<15:16:30,  1.44s/it]
 38%|███▊      | 23809/61904 [2:06:25<14:54:21,  1.41s/it]
 38%|███▊      | 23810/61904 [2:06:26<15:02:00,  1.42s/it]
 38%|███▊      | 23811/61904 [2:06:28<15:00:48,  1.42s/it]
 38%|███▊      | 23812/61904 [2:06:29<15:23:25,  1.45s/it]
 38%|███▊      | 23813/61904 [2:06:31<15:27:48,  1.46s/it]
 38%|███▊      | 23814/61904 [2:06:32<14:56:24,  1.41s/it]
 38%|███▊      | 23815/61904 [2:06:33<14:28:45,  1.37s/it]
 38%|███▊      | 23816/61904 [2:06:35<14:24:30,  1.36s/it]
 38%|███▊      | 23817/61904 [2:06:36<14:13:12,  1.34s/it]
 38%|███▊      | 23818/61904 [2:06:37<14:39:18,  1.39s/it]
 38%|███▊      | 23819/61904 [2:06:39<14:34:25,  1.38s/it]
 38%|███▊      | 23820/61904 [2:06:40<14:16:14,  1.35s/it]
                                                          
{'loss': 2.5577, 'learning_rate': 1.6172047193050694e-07, 'epoch': 6.16}

 38%|███▊      | 23820/61904 [2:06:40<14:16:14,  1.35s/it]
 38%|███▊      | 23821/61904 [2:06:42<14:39:45,  1.39s/it]
 38%|███▊      | 23822/61904 [2:06:43<14:31:24,  1.37s/it]
 38%|███▊      | 23823/61904 [2:06:44<14:37:37,  1.38s/it]
 38%|███▊      | 23824/61904 [2:06:46<14:45:46,  1.40s/it]
 38%|███▊      | 23825/61904 [2:06:47<14:30:51,  1.37s/it]
 38%|███▊      | 23826/61904 [2:06:48<14:28:52,  1.37s/it]
 38%|███▊      | 23827/61904 [2:06:50<14:50:00,  1.40s/it]
 38%|███▊      | 23828/61904 [2:06:51<14:54:44,  1.41s/it]
 38%|███▊      | 23829/61904 [2:06:53<14:41:56,  1.39s/it]
 38%|███▊      | 23830/61904 [2:06:54<14:18:32,  1.35s/it]
 38%|███▊      | 23831/61904 [2:06:55<14:34:16,  1.38s/it]
 38%|███▊      | 23832/61904 [2:06:57<14:08:51,  1.34s/it]
 38%|███▊      | 23833/61904 [2:06:58<14:46:07,  1.40s/it]
 39%|███▊      | 23834/61904 [2:07:00<14:44:28,  1.39s/it]
 39%|███▊      | 23835/61904 [2:07:01<14:35:10,  1.38s/it]
 39%|███▊      | 23836/61904 [2:07:02<14:31:32,  1.37s/it]
 39%|███▊      | 23837/61904 [2:07:04<14:37:43,  1.38s/it]
 39%|███▊      | 23838/61904 [2:07:05<14:27:23,  1.37s/it]
 39%|███▊      | 23839/61904 [2:07:06<14:32:07,  1.37s/it]
 39%|███▊      | 23840/61904 [2:07:08<15:12:00,  1.44s/it]
                                                          
{'loss': 2.6101, 'learning_rate': 1.6168805912096458e-07, 'epoch': 6.16}

 39%|███▊      | 23840/61904 [2:07:08<15:12:00,  1.44s/it]
 39%|███▊      | 23841/61904 [2:07:09<15:10:32,  1.44s/it]
 39%|███▊      | 23842/61904 [2:07:11<14:58:12,  1.42s/it]
 39%|███▊      | 23843/61904 [2:07:12<14:45:10,  1.40s/it]
 39%|███▊      | 23844/61904 [2:07:14<14:50:52,  1.40s/it]
 39%|███▊      | 23845/61904 [2:07:15<14:53:45,  1.41s/it]
 39%|███▊      | 23846/61904 [2:07:16<14:42:17,  1.39s/it]
 39%|███▊      | 23847/61904 [2:07:18<14:36:48,  1.38s/it]
 39%|███▊      | 23848/61904 [2:07:19<14:42:17,  1.39s/it]
 39%|███▊      | 23849/61904 [2:07:20<14:34:11,  1.38s/it]
 39%|███▊      | 23850/61904 [2:07:22<14:46:19,  1.40s/it]
 39%|███▊      | 23851/61904 [2:07:23<14:47:49,  1.40s/it]
 39%|███▊      | 23852/61904 [2:07:25<14:51:55,  1.41s/it]
 39%|███▊      | 23853/61904 [2:07:26<14:58:47,  1.42s/it]
 39%|███▊      | 23854/61904 [2:07:28<15:12:09,  1.44s/it]
 39%|███▊      | 23855/61904 [2:07:29<15:07:27,  1.43s/it]
 39%|███▊      | 23856/61904 [2:07:30<14:37:06,  1.38s/it]
 39%|███▊      | 23857/61904 [2:07:32<14:52:56,  1.41s/it]
 39%|███▊      | 23858/61904 [2:07:33<14:50:25,  1.40s/it]
 39%|███▊      | 23859/61904 [2:07:35<14:46:50,  1.40s/it]
 39%|███▊      | 23860/61904 [2:07:36<14:39:46,  1.39s/it]
                                                          
{'loss': 2.5553, 'learning_rate': 1.6165564631142227e-07, 'epoch': 6.17}

 39%|███▊      | 23860/61904 [2:07:36<14:39:46,  1.39s/it]
 39%|███▊      | 23861/61904 [2:07:37<15:01:19,  1.42s/it]
 39%|███▊      | 23862/61904 [2:07:39<14:55:51,  1.41s/it]
 39%|███▊      | 23863/61904 [2:07:40<15:16:14,  1.45s/it]
 39%|███▊      | 23864/61904 [2:07:42<15:09:40,  1.43s/it]
 39%|███▊      | 23865/61904 [2:07:43<14:55:52,  1.41s/it]
 39%|███▊      | 23866/61904 [2:07:44<14:52:03,  1.41s/it]
 39%|███▊      | 23867/61904 [2:07:46<15:03:36,  1.43s/it]
 39%|███▊      | 23868/61904 [2:07:47<14:55:27,  1.41s/it]
 39%|███▊      | 23869/61904 [2:07:49<15:10:56,  1.44s/it]
 39%|███▊      | 23870/61904 [2:07:50<15:21:47,  1.45s/it]
 39%|███▊      | 23871/61904 [2:07:52<15:03:06,  1.42s/it]
 39%|███▊      | 23872/61904 [2:07:53<14:53:19,  1.41s/it]
 39%|███▊      | 23873/61904 [2:07:54<14:56:21,  1.41s/it]
 39%|███▊      | 23874/61904 [2:07:56<14:57:40,  1.42s/it]
 39%|███▊      | 23875/61904 [2:07:57<14:43:07,  1.39s/it]
 39%|███▊      | 23876/61904 [2:07:59<14:31:16,  1.37s/it]
 39%|███▊      | 23877/61904 [2:08:00<14:33:03,  1.38s/it]
 39%|███▊      | 23878/61904 [2:08:02<15:28:32,  1.47s/it]
 39%|███▊      | 23879/61904 [2:08:03<15:06:26,  1.43s/it]
 39%|███▊      | 23880/61904 [2:08:04<15:03:59,  1.43s/it]
                                                          
{'loss': 2.6326, 'learning_rate': 1.6162323350187995e-07, 'epoch': 6.17}

 39%|███▊      | 23880/61904 [2:08:04<15:03:59,  1.43s/it]
 39%|███▊      | 23881/61904 [2:08:06<14:54:49,  1.41s/it]
 39%|███▊      | 23882/61904 [2:08:07<14:36:30,  1.38s/it]
 39%|███▊      | 23883/61904 [2:08:08<14:19:05,  1.36s/it]
 39%|███▊      | 23884/61904 [2:08:10<14:46:58,  1.40s/it]
 39%|███▊      | 23885/61904 [2:08:11<14:50:50,  1.41s/it]
 39%|███▊      | 23886/61904 [2:08:13<14:41:25,  1.39s/it]
 39%|███▊      | 23887/61904 [2:08:14<15:04:08,  1.43s/it]
 39%|███▊      | 23888/61904 [2:08:15<14:33:38,  1.38s/it]
 39%|███▊      | 23889/61904 [2:08:17<14:43:54,  1.40s/it]
 39%|███▊      | 23890/61904 [2:08:18<14:06:20,  1.34s/it]
 39%|███▊      | 23891/61904 [2:08:19<13:46:13,  1.30s/it]
 39%|███▊      | 23892/61904 [2:08:21<13:55:29,  1.32s/it]
 39%|███▊      | 23893/61904 [2:08:22<14:13:14,  1.35s/it]
 39%|███▊      | 23894/61904 [2:08:23<14:19:08,  1.36s/it]
 39%|███▊      | 23895/61904 [2:08:25<14:33:27,  1.38s/it]
 39%|███▊      | 23896/61904 [2:08:26<14:21:13,  1.36s/it]
 39%|███▊      | 23897/61904 [2:08:28<14:30:47,  1.37s/it]
 39%|███▊      | 23898/61904 [2:08:29<14:24:17,  1.36s/it]
 39%|███▊      | 23899/61904 [2:08:30<14:54:42,  1.41s/it]
 39%|███▊      | 23900/61904 [2:08:32<14:42:49,  1.39s/it]
                                                          
{'loss': 2.5922, 'learning_rate': 1.615908206923376e-07, 'epoch': 6.18}

 39%|███▊      | 23900/61904 [2:08:32<14:42:49,  1.39s/it]
 39%|███▊      | 23901/61904 [2:08:33<14:31:05,  1.38s/it]
 39%|███▊      | 23902/61904 [2:08:34<14:26:17,  1.37s/it]
 39%|███▊      | 23903/61904 [2:08:36<14:11:47,  1.34s/it]
 39%|███▊      | 23904/61904 [2:08:37<14:20:32,  1.36s/it]
 39%|███▊      | 23905/61904 [2:08:39<14:59:10,  1.42s/it]
 39%|███▊      | 23906/61904 [2:08:40<14:45:12,  1.40s/it]
 39%|███▊      | 23907/61904 [2:08:41<14:47:49,  1.40s/it]
 39%|███▊      | 23908/61904 [2:08:43<14:58:51,  1.42s/it]
 39%|███▊      | 23909/61904 [2:08:44<14:56:27,  1.42s/it]
 39%|███▊      | 23910/61904 [2:08:46<14:40:05,  1.39s/it]
 39%|███▊      | 23911/61904 [2:08:47<14:34:00,  1.38s/it]
 39%|███▊      | 23912/61904 [2:08:49<15:00:07,  1.42s/it]
 39%|███▊      | 23913/61904 [2:08:50<14:50:47,  1.41s/it]
 39%|███▊      | 23914/61904 [2:08:51<14:51:19,  1.41s/it]
 39%|███▊      | 23915/61904 [2:08:53<14:29:20,  1.37s/it]
 39%|███▊      | 23916/61904 [2:08:54<15:08:27,  1.43s/it]
 39%|███▊      | 23917/61904 [2:08:56<15:00:11,  1.42s/it]
 39%|███▊      | 23918/61904 [2:08:57<14:40:11,  1.39s/it]
 39%|███▊      | 23919/61904 [2:08:58<14:26:51,  1.37s/it]
 39%|███▊      | 23920/61904 [2:09:00<14:41:41,  1.39s/it]
                                                          
{'loss': 2.5913, 'learning_rate': 1.6155840788279528e-07, 'epoch': 6.18}

 39%|███▊      | 23920/61904 [2:09:00<14:41:41,  1.39s/it]
 39%|███▊      | 23921/61904 [2:09:01<14:42:15,  1.39s/it]
 39%|███▊      | 23922/61904 [2:09:03<14:49:57,  1.41s/it]
 39%|███▊      | 23923/61904 [2:09:04<15:01:30,  1.42s/it]
 39%|███▊      | 23924/61904 [2:09:05<14:51:41,  1.41s/it]
 39%|███▊      | 23925/61904 [2:09:07<15:02:41,  1.43s/it]
 39%|███▊      | 23926/61904 [2:09:08<14:41:05,  1.39s/it]
 39%|███▊      | 23927/61904 [2:09:09<14:18:20,  1.36s/it]
 39%|███▊      | 23928/61904 [2:09:11<14:49:40,  1.41s/it]
 39%|███▊      | 23929/61904 [2:09:12<14:37:29,  1.39s/it]
 39%|███▊      | 23930/61904 [2:09:14<15:10:37,  1.44s/it]
 39%|███▊      | 23931/61904 [2:09:15<14:59:33,  1.42s/it]
 39%|███▊      | 23932/61904 [2:09:17<15:00:58,  1.42s/it]
 39%|███▊      | 23933/61904 [2:09:18<14:43:46,  1.40s/it]
 39%|███▊      | 23934/61904 [2:09:19<14:47:44,  1.40s/it]
 39%|███▊      | 23935/61904 [2:09:21<14:46:29,  1.40s/it]
 39%|███▊      | 23936/61904 [2:09:22<14:37:08,  1.39s/it]
 39%|███▊      | 23937/61904 [2:09:24<14:46:38,  1.40s/it]
 39%|███▊      | 23938/61904 [2:09:25<14:49:23,  1.41s/it]
 39%|███▊      | 23939/61904 [2:09:26<14:35:37,  1.38s/it]
 39%|███▊      | 23940/61904 [2:09:28<14:44:36,  1.40s/it]
                                                          
{'loss': 2.6378, 'learning_rate': 1.6152599507325294e-07, 'epoch': 6.19}

 39%|███▊      | 23940/61904 [2:09:28<14:44:36,  1.40s/it]
 39%|███▊      | 23941/61904 [2:09:29<14:32:13,  1.38s/it]
 39%|███▊      | 23942/61904 [2:09:30<14:12:31,  1.35s/it]
 39%|███▊      | 23943/61904 [2:09:32<14:09:24,  1.34s/it]
 39%|███▊      | 23944/61904 [2:09:33<14:15:59,  1.35s/it]
 39%|███▊      | 23945/61904 [2:09:34<14:11:53,  1.35s/it]
 39%|███▊      | 23946/61904 [2:09:36<14:26:45,  1.37s/it]
 39%|███▊      | 23947/61904 [2:09:37<14:51:38,  1.41s/it]
 39%|███▊      | 23948/61904 [2:09:39<14:47:53,  1.40s/it]
 39%|███▊      | 23949/61904 [2:09:40<14:47:41,  1.40s/it]
 39%|███▊      | 23950/61904 [2:09:42<15:13:11,  1.44s/it]
 39%|███▊      | 23951/61904 [2:09:43<15:23:14,  1.46s/it]
 39%|███▊      | 23952/61904 [2:09:45<15:37:09,  1.48s/it]
 39%|███▊      | 23953/61904 [2:09:46<15:30:27,  1.47s/it]
 39%|███▊      | 23954/61904 [2:09:48<15:12:43,  1.44s/it]
 39%|███▊      | 23955/61904 [2:09:49<15:22:41,  1.46s/it]
 39%|███▊      | 23956/61904 [2:09:50<15:04:24,  1.43s/it]
 39%|███▊      | 23957/61904 [2:09:52<14:39:13,  1.39s/it]
 39%|███▊      | 23958/61904 [2:09:53<14:31:31,  1.38s/it]
 39%|███▊      | 23959/61904 [2:09:54<14:39:23,  1.39s/it]
 39%|███▊      | 23960/61904 [2:09:56<14:36:48,  1.39s/it]
                                                          
{'loss': 2.5969, 'learning_rate': 1.614935822637106e-07, 'epoch': 6.19}

 39%|███▊      | 23960/61904 [2:09:56<14:36:48,  1.39s/it]
 39%|███▊      | 23961/61904 [2:09:57<14:44:34,  1.40s/it]
 39%|███▊      | 23962/61904 [2:09:59<14:18:26,  1.36s/it]
 39%|███▊      | 23963/61904 [2:10:00<14:11:37,  1.35s/it]
 39%|███▊      | 23964/61904 [2:10:01<14:24:44,  1.37s/it]
 39%|███▊      | 23965/61904 [2:10:03<14:40:27,  1.39s/it]
 39%|███▊      | 23966/61904 [2:10:04<14:31:29,  1.38s/it]
 39%|███▊      | 23967/61904 [2:10:05<14:25:36,  1.37s/it]
 39%|███▊      | 23968/61904 [2:10:07<14:21:45,  1.36s/it]
 39%|███▊      | 23969/61904 [2:10:08<14:56:05,  1.42s/it]
 39%|███▊      | 23970/61904 [2:10:10<14:25:03,  1.37s/it]
 39%|███▊      | 23971/61904 [2:10:11<14:42:43,  1.40s/it]
 39%|███▊      | 23972/61904 [2:10:12<14:56:44,  1.42s/it]
 39%|███▊      | 23973/61904 [2:10:14<14:56:28,  1.42s/it]
 39%|███▊      | 23974/61904 [2:10:15<14:33:35,  1.38s/it]
 39%|███▊      | 23975/61904 [2:10:17<14:47:35,  1.40s/it]
 39%|███▊      | 23976/61904 [2:10:18<14:32:35,  1.38s/it]
 39%|███▊      | 23977/61904 [2:10:19<14:16:51,  1.36s/it]
 39%|███▊      | 23978/61904 [2:10:21<14:08:00,  1.34s/it]
 39%|███▊      | 23979/61904 [2:10:22<14:02:31,  1.33s/it]
 39%|███▊      | 23980/61904 [2:10:23<14:15:16,  1.35s/it]
                                                          
{'loss': 2.5971, 'learning_rate': 1.614611694541683e-07, 'epoch': 6.2}

 39%|███▊      | 23980/61904 [2:10:23<14:15:16,  1.35s/it]
 39%|███▊      | 23981/61904 [2:10:25<14:21:35,  1.36s/it]
 39%|███▊      | 23982/61904 [2:10:26<14:13:54,  1.35s/it]
 39%|███▊      | 23983/61904 [2:10:27<14:11:19,  1.35s/it]
 39%|███▊      | 23984/61904 [2:10:29<14:37:59,  1.39s/it]
 39%|███▊      | 23985/61904 [2:10:30<14:53:42,  1.41s/it]
 39%|███▊      | 23986/61904 [2:10:32<15:20:09,  1.46s/it]
 39%|███▊      | 23987/61904 [2:10:33<14:53:33,  1.41s/it]
 39%|███▉      | 23988/61904 [2:10:35<15:07:57,  1.44s/it]
 39%|███▉      | 23989/61904 [2:10:36<15:15:48,  1.45s/it]
 39%|███▉      | 23990/61904 [2:10:37<14:54:36,  1.42s/it]
 39%|███▉      | 23991/61904 [2:10:39<14:23:07,  1.37s/it]
 39%|███▉      | 23992/61904 [2:10:40<14:14:03,  1.35s/it]
 39%|███▉      | 23993/61904 [2:10:42<14:44:40,  1.40s/it]
 39%|███▉      | 23994/61904 [2:10:43<14:48:00,  1.41s/it]
 39%|███▉      | 23995/61904 [2:10:44<15:05:05,  1.43s/it]
 39%|███▉      | 23996/61904 [2:10:46<15:22:51,  1.46s/it]
 39%|███▉      | 23997/61904 [2:10:47<15:21:50,  1.46s/it]
 39%|███▉      | 23998/61904 [2:10:49<15:21:52,  1.46s/it]
 39%|███▉      | 23999/61904 [2:10:50<15:19:24,  1.46s/it]
 39%|███▉      | 24000/61904 [2:10:52<14:57:54,  1.42s/it]
                                                          
{'loss': 2.616, 'learning_rate': 1.6142875664462593e-07, 'epoch': 6.2}

 39%|███▉      | 24000/61904 [2:10:52<14:57:54,  1.42s/it]
 39%|███▉      | 24001/61904 [2:10:53<15:05:50,  1.43s/it]
 39%|███▉      | 24002/61904 [2:10:54<14:36:42,  1.39s/it]
 39%|███▉      | 24003/61904 [2:10:56<14:26:16,  1.37s/it]
 39%|███▉      | 24004/61904 [2:10:57<14:35:30,  1.39s/it]
 39%|███▉      | 24005/61904 [2:10:59<14:44:44,  1.40s/it]
 39%|███▉      | 24006/61904 [2:11:00<14:22:07,  1.36s/it]
 39%|███▉      | 24007/61904 [2:11:01<14:04:07,  1.34s/it]
 39%|███▉      | 24008/61904 [2:11:03<14:06:18,  1.34s/it]
 39%|███▉      | 24009/61904 [2:11:04<14:29:16,  1.38s/it]
 39%|███▉      | 24010/61904 [2:11:05<14:54:03,  1.42s/it]
 39%|███▉      | 24011/61904 [2:11:07<15:11:50,  1.44s/it]
 39%|███▉      | 24012/61904 [2:11:08<15:17:51,  1.45s/it]
 39%|███▉      | 24013/61904 [2:11:10<15:51:52,  1.51s/it]
 39%|███▉      | 24014/61904 [2:11:11<15:19:51,  1.46s/it]
 39%|███▉      | 24015/61904 [2:11:13<15:31:54,  1.48s/it]
 39%|███▉      | 24016/61904 [2:11:15<16:05:01,  1.53s/it]
 39%|███▉      | 24017/61904 [2:11:16<15:36:30,  1.48s/it]
 39%|███▉      | 24018/61904 [2:11:17<15:14:23,  1.45s/it]
 39%|███▉      | 24019/61904 [2:11:19<14:45:50,  1.40s/it]
 39%|███▉      | 24020/61904 [2:11:20<15:04:51,  1.43s/it]
                                                          
{'loss': 2.6352, 'learning_rate': 1.6139634383508361e-07, 'epoch': 6.21}

 39%|███▉      | 24020/61904 [2:11:20<15:04:51,  1.43s/it]
 39%|███▉      | 24021/61904 [2:11:21<14:31:23,  1.38s/it]
 39%|███▉      | 24022/61904 [2:11:23<14:26:25,  1.37s/it]
 39%|███▉      | 24023/61904 [2:11:24<14:14:06,  1.35s/it]
 39%|███▉      | 24024/61904 [2:11:25<14:13:28,  1.35s/it]
 39%|███▉      | 24025/61904 [2:11:27<14:22:29,  1.37s/it]
 39%|███▉      | 24026/61904 [2:11:28<14:40:30,  1.39s/it]
 39%|███▉      | 24027/61904 [2:11:30<14:30:10,  1.38s/it]
 39%|███▉      | 24028/61904 [2:11:31<14:29:58,  1.38s/it]
 39%|███▉      | 24029/61904 [2:11:32<14:35:36,  1.39s/it]
 39%|███▉      | 24030/61904 [2:11:34<14:13:17,  1.35s/it]
 39%|███▉      | 24031/61904 [2:11:35<14:27:40,  1.37s/it]
 39%|███▉      | 24032/61904 [2:11:37<14:45:37,  1.40s/it]
 39%|███▉      | 24033/61904 [2:11:38<14:31:31,  1.38s/it]
 39%|███▉      | 24034/61904 [2:11:39<15:00:51,  1.43s/it]
 39%|███▉      | 24035/61904 [2:11:41<15:00:34,  1.43s/it]
 39%|███▉      | 24036/61904 [2:11:42<14:55:28,  1.42s/it]
 39%|███▉      | 24037/61904 [2:11:44<15:05:40,  1.44s/it]
 39%|███▉      | 24038/61904 [2:11:45<14:47:57,  1.41s/it]
 39%|███▉      | 24039/61904 [2:11:46<14:37:40,  1.39s/it]
 39%|███▉      | 24040/61904 [2:11:48<14:44:25,  1.40s/it]
                                                          
{'loss': 2.6371, 'learning_rate': 1.613639310255413e-07, 'epoch': 6.21}

 39%|███▉      | 24040/61904 [2:11:48<14:44:25,  1.40s/it]
 39%|███▉      | 24041/61904 [2:11:49<14:35:51,  1.39s/it]
 39%|███▉      | 24042/61904 [2:11:51<14:39:37,  1.39s/it]
 39%|███▉      | 24043/61904 [2:11:52<14:33:24,  1.38s/it]
 39%|███▉      | 24044/61904 [2:11:53<14:23:46,  1.37s/it]
 39%|███▉      | 24045/61904 [2:11:55<14:11:02,  1.35s/it]
 39%|███▉      | 24046/61904 [2:11:56<14:27:54,  1.38s/it]
 39%|███▉      | 24047/61904 [2:11:57<14:20:12,  1.36s/it]
 39%|███▉      | 24048/61904 [2:11:59<14:39:26,  1.39s/it]
 39%|███▉      | 24049/61904 [2:12:00<14:45:49,  1.40s/it]
 39%|███▉      | 24050/61904 [2:12:02<14:47:40,  1.41s/it]
 39%|███▉      | 24051/61904 [2:12:03<14:44:41,  1.40s/it]
 39%|███▉      | 24052/61904 [2:12:04<14:34:24,  1.39s/it]
 39%|███▉      | 24053/61904 [2:12:06<14:10:33,  1.35s/it]
 39%|███▉      | 24054/61904 [2:12:07<14:39:20,  1.39s/it]
 39%|███▉      | 24055/61904 [2:12:09<14:21:21,  1.37s/it]
 39%|███▉      | 24056/61904 [2:12:10<14:07:42,  1.34s/it]
 39%|███▉      | 24057/61904 [2:12:11<14:42:43,  1.40s/it]
 39%|███▉      | 24058/61904 [2:12:13<14:37:51,  1.39s/it]
 39%|███▉      | 24059/61904 [2:12:14<15:02:38,  1.43s/it]
 39%|███▉      | 24060/61904 [2:12:16<14:59:35,  1.43s/it]
                                                          
{'loss': 2.5946, 'learning_rate': 1.6133151821599894e-07, 'epoch': 6.22}

 39%|███▉      | 24060/61904 [2:12:16<14:59:35,  1.43s/it]
 39%|███▉      | 24061/61904 [2:12:17<14:17:08,  1.36s/it]
 39%|███▉      | 24062/61904 [2:12:18<14:26:53,  1.37s/it]
 39%|███▉      | 24063/61904 [2:12:20<14:03:03,  1.34s/it]
 39%|███▉      | 24064/61904 [2:12:21<14:29:22,  1.38s/it]
 39%|███▉      | 24065/61904 [2:12:22<14:55:57,  1.42s/it]
 39%|███▉      | 24066/61904 [2:12:24<14:44:50,  1.40s/it]
 39%|███▉      | 24067/61904 [2:12:25<14:24:56,  1.37s/it]
 39%|███▉      | 24068/61904 [2:12:26<14:15:33,  1.36s/it]
 39%|███▉      | 24069/61904 [2:12:28<14:07:10,  1.34s/it]
 39%|███▉      | 24070/61904 [2:12:29<14:26:18,  1.37s/it]
 39%|███▉      | 24071/61904 [2:12:31<14:11:54,  1.35s/it]
 39%|███▉      | 24072/61904 [2:12:32<14:14:02,  1.35s/it]
 39%|███▉      | 24073/61904 [2:12:33<14:08:46,  1.35s/it]
 39%|███▉      | 24074/61904 [2:12:35<14:20:57,  1.37s/it]
 39%|███▉      | 24075/61904 [2:12:36<14:35:37,  1.39s/it]
 39%|███▉      | 24076/61904 [2:12:37<14:13:42,  1.35s/it]
 39%|███▉      | 24077/61904 [2:12:39<14:14:23,  1.36s/it]
 39%|███▉      | 24078/61904 [2:12:40<14:10:12,  1.35s/it]
 39%|███▉      | 24079/61904 [2:12:42<14:59:30,  1.43s/it]
 39%|███▉      | 24080/61904 [2:12:43<14:46:21,  1.41s/it]
                                                          
{'loss': 2.6379, 'learning_rate': 1.6129910540645663e-07, 'epoch': 6.22}

 39%|███▉      | 24080/61904 [2:12:43<14:46:21,  1.41s/it]
 39%|███▉      | 24081/61904 [2:12:44<14:50:32,  1.41s/it]
 39%|███▉      | 24082/61904 [2:12:46<14:49:14,  1.41s/it]
 39%|███▉      | 24083/61904 [2:12:47<15:03:29,  1.43s/it]
 39%|███▉      | 24084/61904 [2:12:49<14:57:51,  1.42s/it]
 39%|███▉      | 24085/61904 [2:12:50<14:43:39,  1.40s/it]
 39%|███▉      | 24086/61904 [2:12:52<14:50:19,  1.41s/it]
 39%|███▉      | 24087/61904 [2:12:53<15:28:29,  1.47s/it]
 39%|███▉      | 24088/61904 [2:12:54<14:54:29,  1.42s/it]
 39%|███▉      | 24089/61904 [2:12:56<14:40:02,  1.40s/it]
 39%|███▉      | 24090/61904 [2:12:57<14:13:06,  1.35s/it]
 39%|███▉      | 24091/61904 [2:12:59<14:37:11,  1.39s/it]
 39%|███▉      | 24092/61904 [2:13:00<14:47:38,  1.41s/it]
 39%|███▉      | 24093/61904 [2:13:02<15:15:29,  1.45s/it]
 39%|███▉      | 24094/61904 [2:13:03<15:09:00,  1.44s/it]
 39%|███▉      | 24095/61904 [2:13:04<14:50:26,  1.41s/it]
 39%|███▉      | 24096/61904 [2:13:06<14:50:10,  1.41s/it]
 39%|███▉      | 24097/61904 [2:13:07<14:13:19,  1.35s/it]
 39%|███▉      | 24098/61904 [2:13:08<14:16:27,  1.36s/it]
 39%|███▉      | 24099/61904 [2:13:10<14:04:11,  1.34s/it]
 39%|███▉      | 24100/61904 [2:13:11<14:06:40,  1.34s/it]
                                                          
{'loss': 2.6046, 'learning_rate': 1.6126669259691431e-07, 'epoch': 6.23}

 39%|███▉      | 24100/61904 [2:13:11<14:06:40,  1.34s/it]
 39%|███▉      | 24101/61904 [2:13:12<14:25:02,  1.37s/it]
 39%|███▉      | 24102/61904 [2:13:14<14:18:45,  1.36s/it]
 39%|███▉      | 24103/61904 [2:13:15<14:43:03,  1.40s/it]
 39%|███▉      | 24104/61904 [2:13:17<15:18:19,  1.46s/it]
 39%|███▉      | 24105/61904 [2:13:18<15:25:56,  1.47s/it]
 39%|███▉      | 24106/61904 [2:13:20<15:01:34,  1.43s/it]
 39%|███▉      | 24107/61904 [2:13:21<14:43:37,  1.40s/it]
 39%|███▉      | 24108/61904 [2:13:22<14:46:03,  1.41s/it]
 39%|███▉      | 24109/61904 [2:13:24<14:27:21,  1.38s/it]
 39%|███▉      | 24110/61904 [2:13:25<14:37:19,  1.39s/it]
 39%|███▉      | 24111/61904 [2:13:27<14:40:26,  1.40s/it]
 39%|███▉      | 24112/61904 [2:13:28<14:22:11,  1.37s/it]
 39%|███▉      | 24113/61904 [2:13:29<14:02:11,  1.34s/it]
 39%|███▉      | 24114/61904 [2:13:31<14:29:19,  1.38s/it]
 39%|███▉      | 24115/61904 [2:13:32<14:33:39,  1.39s/it]
 39%|███▉      | 24116/61904 [2:13:34<15:13:06,  1.45s/it]
 39%|███▉      | 24117/61904 [2:13:35<14:47:26,  1.41s/it]
 39%|███▉      | 24118/61904 [2:13:36<14:33:37,  1.39s/it]
 39%|███▉      | 24119/61904 [2:13:38<14:15:50,  1.36s/it]
 39%|███▉      | 24120/61904 [2:13:39<14:08:51,  1.35s/it]
                                                          
{'loss': 2.653, 'learning_rate': 1.6123427978737195e-07, 'epoch': 6.23}

 39%|███▉      | 24120/61904 [2:13:39<14:08:51,  1.35s/it]
 39%|███▉      | 24121/61904 [2:13:40<14:18:20,  1.36s/it]
 39%|███▉      | 24122/61904 [2:13:42<14:27:54,  1.38s/it]
 39%|███▉      | 24123/61904 [2:13:43<14:36:31,  1.39s/it]
 39%|███▉      | 24124/61904 [2:13:44<14:23:03,  1.37s/it]
 39%|███▉      | 24125/61904 [2:13:46<14:15:31,  1.36s/it]
 39%|███▉      | 24126/61904 [2:13:47<14:53:48,  1.42s/it]
 39%|███▉      | 24127/61904 [2:13:49<14:37:06,  1.39s/it]
 39%|███▉      | 24128/61904 [2:13:50<14:20:23,  1.37s/it]
 39%|███▉      | 24129/61904 [2:13:51<14:22:29,  1.37s/it]
 39%|███▉      | 24130/61904 [2:13:53<14:27:20,  1.38s/it]
 39%|███▉      | 24131/61904 [2:13:54<14:46:04,  1.41s/it]
 39%|███▉      | 24132/61904 [2:13:56<14:34:15,  1.39s/it]
 39%|███▉      | 24133/61904 [2:13:57<14:50:06,  1.41s/it]
 39%|███▉      | 24134/61904 [2:13:58<14:39:24,  1.40s/it]
 39%|███▉      | 24135/61904 [2:14:00<14:35:38,  1.39s/it]
 39%|███▉      | 24136/61904 [2:14:01<14:32:02,  1.39s/it]
 39%|███▉      | 24137/61904 [2:14:03<15:32:13,  1.48s/it]
 39%|███▉      | 24138/61904 [2:14:04<14:51:31,  1.42s/it]
 39%|███▉      | 24139/61904 [2:14:05<14:39:05,  1.40s/it]
 39%|███▉      | 24140/61904 [2:14:07<14:18:00,  1.36s/it]
                                                          
{'loss': 2.6409, 'learning_rate': 1.6120186697782964e-07, 'epoch': 6.24}

 39%|███▉      | 24140/61904 [2:14:07<14:18:00,  1.36s/it]
 39%|███▉      | 24141/61904 [2:14:08<14:42:30,  1.40s/it]
 39%|███▉      | 24142/61904 [2:14:09<14:22:31,  1.37s/it]
 39%|███▉      | 24143/61904 [2:14:11<14:07:29,  1.35s/it]
 39%|███▉      | 24144/61904 [2:14:12<14:02:45,  1.34s/it]
 39%|███▉      | 24145/61904 [2:14:13<14:09:04,  1.35s/it]
 39%|███▉      | 24146/61904 [2:14:15<14:01:00,  1.34s/it]
 39%|███▉      | 24147/61904 [2:14:16<13:57:21,  1.33s/it]
 39%|███▉      | 24148/61904 [2:14:17<14:11:44,  1.35s/it]
 39%|███▉      | 24149/61904 [2:14:19<14:11:45,  1.35s/it]
 39%|███▉      | 24150/61904 [2:14:20<13:57:12,  1.33s/it]
 39%|███▉      | 24151/61904 [2:14:21<13:38:43,  1.30s/it]
 39%|███▉      | 24152/61904 [2:14:23<13:52:56,  1.32s/it]
 39%|███▉      | 24153/61904 [2:14:24<14:06:11,  1.34s/it]
 39%|███▉      | 24154/61904 [2:14:26<14:29:16,  1.38s/it]
 39%|███▉      | 24155/61904 [2:14:27<14:26:25,  1.38s/it]
 39%|███▉      | 24156/61904 [2:14:28<14:25:12,  1.38s/it]
 39%|███▉      | 24157/61904 [2:14:30<14:13:31,  1.36s/it]
 39%|███▉      | 24158/61904 [2:14:31<14:12:44,  1.36s/it]
 39%|███▉      | 24159/61904 [2:14:32<14:01:42,  1.34s/it]
 39%|███▉      | 24160/61904 [2:14:34<14:02:44,  1.34s/it]
                                                          
{'loss': 2.6077, 'learning_rate': 1.611694541682873e-07, 'epoch': 6.24}

 39%|███▉      | 24160/61904 [2:14:34<14:02:44,  1.34s/it]
 39%|███▉      | 24161/61904 [2:14:35<14:06:59,  1.35s/it]
 39%|███▉      | 24162/61904 [2:14:36<14:13:31,  1.36s/it]
 39%|███▉      | 24163/61904 [2:14:38<13:59:12,  1.33s/it]
 39%|███▉      | 24164/61904 [2:14:39<14:22:37,  1.37s/it]
 39%|███▉      | 24165/61904 [2:14:40<14:19:23,  1.37s/it]
 39%|███▉      | 24166/61904 [2:14:42<14:32:47,  1.39s/it]
 39%|███▉      | 24167/61904 [2:14:43<14:49:58,  1.42s/it]
 39%|███▉      | 24168/61904 [2:14:45<14:47:22,  1.41s/it]
 39%|███▉      | 24169/61904 [2:14:46<14:33:45,  1.39s/it]
 39%|███▉      | 24170/61904 [2:14:48<14:31:04,  1.39s/it]
 39%|███▉      | 24171/61904 [2:14:49<14:38:07,  1.40s/it]
 39%|███▉      | 24172/61904 [2:14:50<14:38:59,  1.40s/it]
 39%|███▉      | 24173/61904 [2:14:52<14:18:23,  1.37s/it]
 39%|███▉      | 24174/61904 [2:14:53<14:25:49,  1.38s/it]
 39%|███▉      | 24175/61904 [2:14:54<14:23:23,  1.37s/it]
 39%|███▉      | 24176/61904 [2:14:56<14:04:39,  1.34s/it]
 39%|███▉      | 24177/61904 [2:14:57<14:21:32,  1.37s/it]
 39%|███▉      | 24178/61904 [2:14:58<14:15:32,  1.36s/it]
 39%|███▉      | 24179/61904 [2:15:00<14:26:04,  1.38s/it]
 39%|███▉      | 24180/61904 [2:15:01<14:25:32,  1.38s/it]
                                                          
{'loss': 2.5993, 'learning_rate': 1.6113704135874496e-07, 'epoch': 6.25}

 39%|███▉      | 24180/61904 [2:15:01<14:25:32,  1.38s/it]
 39%|███▉      | 24181/61904 [2:15:03<14:16:29,  1.36s/it]
 39%|███▉      | 24182/61904 [2:15:04<14:19:50,  1.37s/it]
 39%|███▉      | 24183/61904 [2:15:05<14:10:10,  1.35s/it]
 39%|███▉      | 24184/61904 [2:15:07<14:24:54,  1.38s/it]
 39%|███▉      | 24185/61904 [2:15:08<14:15:07,  1.36s/it]
 39%|███▉      | 24186/61904 [2:15:09<14:33:44,  1.39s/it]
 39%|███▉      | 24187/61904 [2:15:11<14:54:38,  1.42s/it]
 39%|███▉      | 24188/61904 [2:15:12<14:38:17,  1.40s/it]
 39%|███▉      | 24189/61904 [2:15:14<14:40:41,  1.40s/it]
 39%|███▉      | 24190/61904 [2:15:15<14:38:48,  1.40s/it]
 39%|███▉      | 24191/61904 [2:15:17<15:16:24,  1.46s/it]
 39%|███▉      | 24192/61904 [2:15:18<14:50:26,  1.42s/it]
 39%|███▉      | 24193/61904 [2:15:19<14:17:46,  1.36s/it]
 39%|███▉      | 24194/61904 [2:15:21<14:39:47,  1.40s/it]
 39%|███▉      | 24195/61904 [2:15:22<14:22:02,  1.37s/it]
 39%|███▉      | 24196/61904 [2:15:23<14:16:13,  1.36s/it]
 39%|███▉      | 24197/61904 [2:15:25<14:27:12,  1.38s/it]
 39%|███▉      | 24198/61904 [2:15:26<14:37:18,  1.40s/it]
 39%|███▉      | 24199/61904 [2:15:28<14:49:05,  1.41s/it]
 39%|███▉      | 24200/61904 [2:15:29<14:41:49,  1.40s/it]
                                                          
{'loss': 2.6326, 'learning_rate': 1.6110462854920265e-07, 'epoch': 6.25}

 39%|███▉      | 24200/61904 [2:15:29<14:41:49,  1.40s/it]
 39%|███▉      | 24201/61904 [2:15:31<14:50:58,  1.42s/it]
 39%|███▉      | 24202/61904 [2:15:32<14:41:11,  1.40s/it]
 39%|███▉      | 24203/61904 [2:15:33<14:40:30,  1.40s/it]
 39%|███▉      | 24204/61904 [2:15:35<15:04:30,  1.44s/it]
 39%|███▉      | 24205/61904 [2:15:36<14:51:59,  1.42s/it]
 39%|███▉      | 24206/61904 [2:15:37<14:24:50,  1.38s/it]
 39%|███▉      | 24207/61904 [2:15:39<14:38:23,  1.40s/it]
 39%|███▉      | 24208/61904 [2:15:40<14:33:49,  1.39s/it]
 39%|███▉      | 24209/61904 [2:15:42<14:49:32,  1.42s/it]
 39%|███▉      | 24210/61904 [2:15:43<14:49:23,  1.42s/it]
 39%|███▉      | 24211/61904 [2:15:45<14:49:44,  1.42s/it]
 39%|███▉      | 24212/61904 [2:15:46<14:22:39,  1.37s/it]
 39%|███▉      | 24213/61904 [2:15:47<14:10:50,  1.35s/it]
 39%|███▉      | 24214/61904 [2:15:49<14:54:54,  1.42s/it]
 39%|███▉      | 24215/61904 [2:15:50<14:33:05,  1.39s/it]
 39%|███▉      | 24216/61904 [2:15:52<15:05:30,  1.44s/it]
 39%|███▉      | 24217/61904 [2:15:53<14:40:32,  1.40s/it]
 39%|███▉      | 24218/61904 [2:15:54<14:37:06,  1.40s/it]
 39%|███▉      | 24219/61904 [2:15:56<14:35:48,  1.39s/it]
 39%|███▉      | 24220/61904 [2:15:57<14:08:34,  1.35s/it]
                                                          
{'loss': 2.612, 'learning_rate': 1.6107221573966029e-07, 'epoch': 6.26}

 39%|███▉      | 24220/61904 [2:15:57<14:08:34,  1.35s/it]
 39%|███▉      | 24221/61904 [2:15:59<14:40:33,  1.40s/it]
 39%|███▉      | 24222/61904 [2:16:00<14:37:17,  1.40s/it]
 39%|███▉      | 24223/61904 [2:16:01<14:40:39,  1.40s/it]
 39%|███▉      | 24224/61904 [2:16:03<14:43:21,  1.41s/it]
 39%|███▉      | 24225/61904 [2:16:04<14:39:22,  1.40s/it]
 39%|███▉      | 24226/61904 [2:16:06<16:10:21,  1.55s/it]
 39%|███▉      | 24227/61904 [2:16:07<15:38:37,  1.49s/it]
 39%|███▉      | 24228/61904 [2:16:09<15:22:44,  1.47s/it]
 39%|███▉      | 24229/61904 [2:16:10<14:53:56,  1.42s/it]
 39%|███▉      | 24230/61904 [2:16:11<14:42:14,  1.41s/it]
 39%|███▉      | 24231/61904 [2:16:13<14:54:16,  1.42s/it]
 39%|███▉      | 24232/61904 [2:16:14<14:43:20,  1.41s/it]
 39%|███▉      | 24233/61904 [2:16:16<14:15:10,  1.36s/it]
 39%|███▉      | 24234/61904 [2:16:17<14:25:14,  1.38s/it]
 39%|███▉      | 24235/61904 [2:16:18<14:18:56,  1.37s/it]
 39%|███▉      | 24236/61904 [2:16:20<14:19:54,  1.37s/it]
 39%|███▉      | 24237/61904 [2:16:21<14:22:25,  1.37s/it]
 39%|███▉      | 24238/61904 [2:16:22<14:04:56,  1.35s/it]
 39%|███▉      | 24239/61904 [2:16:24<14:12:10,  1.36s/it]
 39%|███▉      | 24240/61904 [2:16:25<14:40:22,  1.40s/it]
                                                          
{'loss': 2.662, 'learning_rate': 1.6103980293011797e-07, 'epoch': 6.27}

 39%|███▉      | 24240/61904 [2:16:25<14:40:22,  1.40s/it]
 39%|███▉      | 24241/61904 [2:16:27<14:43:50,  1.41s/it]
 39%|███▉      | 24242/61904 [2:16:28<14:36:34,  1.40s/it]
 39%|███▉      | 24243/61904 [2:16:29<14:06:46,  1.35s/it]
 39%|███▉      | 24244/61904 [2:16:31<14:28:44,  1.38s/it]
 39%|███▉      | 24245/61904 [2:16:32<14:23:34,  1.38s/it]
 39%|███▉      | 24246/61904 [2:16:33<14:03:48,  1.34s/it]
 39%|███▉      | 24247/61904 [2:16:35<14:01:28,  1.34s/it]
 39%|███▉      | 24248/61904 [2:16:36<14:14:36,  1.36s/it]
 39%|███▉      | 24249/61904 [2:16:37<14:13:27,  1.36s/it]
 39%|███▉      | 24250/61904 [2:16:39<14:15:42,  1.36s/it]
 39%|███▉      | 24251/61904 [2:16:40<14:19:21,  1.37s/it]
 39%|███▉      | 24252/61904 [2:16:42<14:34:45,  1.39s/it]
 39%|███▉      | 24253/61904 [2:16:43<14:30:40,  1.39s/it]
 39%|███▉      | 24254/61904 [2:16:44<14:33:22,  1.39s/it]
 39%|███▉      | 24255/61904 [2:16:46<14:36:09,  1.40s/it]
 39%|███▉      | 24256/61904 [2:16:47<14:27:20,  1.38s/it]
 39%|███▉      | 24257/61904 [2:16:49<14:23:31,  1.38s/it]
 39%|███▉      | 24258/61904 [2:16:50<14:09:13,  1.35s/it]
 39%|███▉      | 24259/61904 [2:16:51<14:17:35,  1.37s/it]
 39%|███▉      | 24260/61904 [2:16:53<14:09:10,  1.35s/it]
                                                          
{'loss': 2.6377, 'learning_rate': 1.6100739012057566e-07, 'epoch': 6.27}

 39%|███▉      | 24260/61904 [2:16:53<14:09:10,  1.35s/it]
 39%|███▉      | 24261/61904 [2:16:54<14:48:11,  1.42s/it]
 39%|███▉      | 24262/61904 [2:16:56<15:07:41,  1.45s/it]
 39%|███▉      | 24263/61904 [2:16:57<14:47:08,  1.41s/it]
 39%|███▉      | 24264/61904 [2:16:58<14:49:42,  1.42s/it]
 39%|███▉      | 24265/61904 [2:17:00<14:50:42,  1.42s/it]
 39%|███▉      | 24266/61904 [2:17:01<14:54:55,  1.43s/it]
 39%|███▉      | 24267/61904 [2:17:03<15:34:17,  1.49s/it]
 39%|███▉      | 24268/61904 [2:17:04<15:10:41,  1.45s/it]
 39%|███▉      | 24269/61904 [2:17:06<15:17:56,  1.46s/it]
 39%|███▉      | 24270/61904 [2:17:07<15:09:40,  1.45s/it]
 39%|███▉      | 24271/61904 [2:17:09<15:10:39,  1.45s/it]
 39%|███▉      | 24272/61904 [2:17:10<14:57:30,  1.43s/it]
 39%|███▉      | 24273/61904 [2:17:11<14:56:16,  1.43s/it]
 39%|███▉      | 24274/61904 [2:17:13<14:37:19,  1.40s/it]
 39%|███▉      | 24275/61904 [2:17:14<15:16:26,  1.46s/it]
 39%|███▉      | 24276/61904 [2:17:16<15:31:21,  1.49s/it]
 39%|███▉      | 24277/61904 [2:17:17<14:50:56,  1.42s/it]
 39%|███▉      | 24278/61904 [2:17:19<14:38:56,  1.40s/it]
 39%|███▉      | 24279/61904 [2:17:20<14:34:15,  1.39s/it]
 39%|███▉      | 24280/61904 [2:17:21<14:44:15,  1.41s/it]
                                                          
{'loss': 2.6113, 'learning_rate': 1.609749773110333e-07, 'epoch': 6.28}

 39%|███▉      | 24280/61904 [2:17:21<14:44:15,  1.41s/it]
 39%|███▉      | 24281/61904 [2:17:23<14:24:37,  1.38s/it]
 39%|███▉      | 24282/61904 [2:17:24<14:07:18,  1.35s/it]
 39%|███▉      | 24283/61904 [2:17:26<14:46:40,  1.41s/it]
 39%|███▉      | 24284/61904 [2:17:27<14:47:03,  1.41s/it]
 39%|███▉      | 24285/61904 [2:17:28<14:28:27,  1.39s/it]
 39%|███▉      | 24286/61904 [2:17:30<14:28:21,  1.39s/it]
 39%|███▉      | 24287/61904 [2:17:31<14:12:29,  1.36s/it]
 39%|███▉      | 24288/61904 [2:17:32<14:28:05,  1.38s/it]
 39%|███▉      | 24289/61904 [2:17:34<14:49:35,  1.42s/it]
 39%|███▉      | 24290/61904 [2:17:35<14:55:40,  1.43s/it]
 39%|███▉      | 24291/61904 [2:17:37<14:48:38,  1.42s/it]
 39%|███▉      | 24292/61904 [2:17:38<14:30:54,  1.39s/it]
 39%|███▉      | 24293/61904 [2:17:39<14:22:16,  1.38s/it]
 39%|███▉      | 24294/61904 [2:17:41<14:02:48,  1.34s/it]
 39%|███▉      | 24295/61904 [2:17:42<14:05:13,  1.35s/it]
 39%|███▉      | 24296/61904 [2:17:43<14:02:25,  1.34s/it]
 39%|███▉      | 24297/61904 [2:17:45<14:25:53,  1.38s/it]
 39%|███▉      | 24298/61904 [2:17:46<14:07:52,  1.35s/it]
 39%|███▉      | 24299/61904 [2:17:47<14:05:55,  1.35s/it]
 39%|███▉      | 24300/61904 [2:17:49<14:38:07,  1.40s/it]
                                                          
{'loss': 2.6094, 'learning_rate': 1.6094256450149099e-07, 'epoch': 6.28}

 39%|███▉      | 24300/61904 [2:17:49<14:38:07,  1.40s/it]
 39%|███▉      | 24301/61904 [2:17:50<14:16:36,  1.37s/it]
 39%|███▉      | 24302/61904 [2:17:52<14:37:25,  1.40s/it]
 39%|███▉      | 24303/61904 [2:17:53<14:18:42,  1.37s/it]
 39%|███▉      | 24304/61904 [2:17:54<14:05:31,  1.35s/it]
 39%|███▉      | 24305/61904 [2:17:56<13:54:30,  1.33s/it]
 39%|███▉      | 24306/61904 [2:17:57<14:05:58,  1.35s/it]
 39%|███▉      | 24307/61904 [2:17:59<14:25:28,  1.38s/it]
 39%|███▉      | 24308/61904 [2:18:00<15:19:00,  1.47s/it]
 39%|███▉      | 24309/61904 [2:18:02<15:16:02,  1.46s/it]
 39%|███▉      | 24310/61904 [2:18:03<14:55:22,  1.43s/it]
 39%|███▉      | 24311/61904 [2:18:04<15:04:49,  1.44s/it]
 39%|███▉      | 24312/61904 [2:18:06<14:57:37,  1.43s/it]
 39%|███▉      | 24313/61904 [2:18:07<14:38:55,  1.40s/it]
 39%|███▉      | 24314/61904 [2:18:09<14:28:05,  1.39s/it]
 39%|███▉      | 24315/61904 [2:18:10<14:31:26,  1.39s/it]
 39%|███▉      | 24316/61904 [2:18:11<14:06:21,  1.35s/it]
 39%|███▉      | 24317/61904 [2:18:13<14:24:14,  1.38s/it]
 39%|███▉      | 24318/61904 [2:18:14<14:03:51,  1.35s/it]
 39%|███▉      | 24319/61904 [2:18:15<14:14:30,  1.36s/it]
 39%|███▉      | 24320/61904 [2:18:17<14:46:46,  1.42s/it]
                                                          
{'loss': 2.6185, 'learning_rate': 1.6091015169194867e-07, 'epoch': 6.29}

 39%|███▉      | 24320/61904 [2:18:17<14:46:46,  1.42s/it]
 39%|███▉      | 24321/61904 [2:18:18<15:01:53,  1.44s/it]
 39%|███▉      | 24322/61904 [2:18:20<14:44:37,  1.41s/it]
 39%|███▉      | 24323/61904 [2:18:21<15:11:40,  1.46s/it]
 39%|███▉      | 24324/61904 [2:18:23<15:24:20,  1.48s/it]
 39%|███▉      | 24325/61904 [2:18:24<15:20:26,  1.47s/it]
 39%|███▉      | 24326/61904 [2:18:26<15:23:06,  1.47s/it]
 39%|███▉      | 24327/61904 [2:18:27<14:59:52,  1.44s/it]
 39%|███▉      | 24328/61904 [2:18:29<15:12:45,  1.46s/it]
 39%|███▉      | 24329/61904 [2:18:30<15:25:40,  1.48s/it]
 39%|███▉      | 24330/61904 [2:18:32<15:24:58,  1.48s/it]
 39%|███▉      | 24331/61904 [2:18:33<15:08:20,  1.45s/it]
 39%|███▉      | 24332/61904 [2:18:34<15:00:03,  1.44s/it]
 39%|███▉      | 24333/61904 [2:18:36<15:19:34,  1.47s/it]
 39%|███▉      | 24334/61904 [2:18:37<14:47:27,  1.42s/it]
 39%|███▉      | 24335/61904 [2:18:39<14:43:58,  1.41s/it]
 39%|███▉      | 24336/61904 [2:18:40<15:00:10,  1.44s/it]
 39%|███▉      | 24337/61904 [2:18:42<15:02:36,  1.44s/it]
 39%|███▉      | 24338/61904 [2:18:43<14:27:26,  1.39s/it]
 39%|███▉      | 24339/61904 [2:18:44<14:42:30,  1.41s/it]
 39%|███▉      | 24340/61904 [2:18:46<14:34:59,  1.40s/it]
                                                          
{'loss': 2.6523, 'learning_rate': 1.608777388824063e-07, 'epoch': 6.29}

 39%|███▉      | 24340/61904 [2:18:46<14:34:59,  1.40s/it]
 39%|███▉      | 24341/61904 [2:18:47<15:10:14,  1.45s/it]
 39%|███▉      | 24342/61904 [2:18:49<14:46:09,  1.42s/it]
 39%|███▉      | 24343/61904 [2:18:50<14:37:44,  1.40s/it]
 39%|███▉      | 24344/61904 [2:18:51<14:56:50,  1.43s/it]
 39%|███▉      | 24345/61904 [2:18:53<15:16:28,  1.46s/it]
 39%|███▉      | 24346/61904 [2:18:54<15:20:28,  1.47s/it]
 39%|███▉      | 24347/61904 [2:18:56<15:21:54,  1.47s/it]
 39%|███▉      | 24348/61904 [2:18:57<15:13:58,  1.46s/it]
 39%|███▉      | 24349/61904 [2:18:59<14:48:16,  1.42s/it]
 39%|███▉      | 24350/61904 [2:19:00<14:30:26,  1.39s/it]
 39%|███▉      | 24351/61904 [2:19:01<14:25:54,  1.38s/it]
 39%|███▉      | 24352/61904 [2:19:03<14:38:05,  1.40s/it]
 39%|███▉      | 24353/61904 [2:19:04<14:16:57,  1.37s/it]
 39%|███▉      | 24354/61904 [2:19:06<14:43:01,  1.41s/it]
 39%|███▉      | 24355/61904 [2:19:07<14:33:35,  1.40s/it]
 39%|███▉      | 24356/61904 [2:19:08<14:47:29,  1.42s/it]
 39%|███▉      | 24357/61904 [2:19:10<14:43:08,  1.41s/it]
 39%|███▉      | 24358/61904 [2:19:11<14:51:27,  1.42s/it]
 39%|███▉      | 24359/61904 [2:19:13<15:12:50,  1.46s/it]
 39%|███▉      | 24360/61904 [2:19:14<15:20:30,  1.47s/it]
                                                          
{'loss': 2.6458, 'learning_rate': 1.60845326072864e-07, 'epoch': 6.3}

 39%|███▉      | 24360/61904 [2:19:14<15:20:30,  1.47s/it]
 39%|███▉      | 24361/61904 [2:19:16<15:32:11,  1.49s/it]
 39%|███▉      | 24362/61904 [2:19:17<15:06:58,  1.45s/it]
 39%|███▉      | 24363/61904 [2:19:18<14:31:45,  1.39s/it]
 39%|███▉      | 24364/61904 [2:19:20<14:23:43,  1.38s/it]
 39%|███▉      | 24365/61904 [2:19:21<14:12:09,  1.36s/it]
 39%|███▉      | 24366/61904 [2:19:23<14:52:50,  1.43s/it]
 39%|███▉      | 24367/61904 [2:19:24<14:28:26,  1.39s/it]
 39%|███▉      | 24368/61904 [2:19:26<15:03:40,  1.44s/it]
 39%|███▉      | 24369/61904 [2:19:27<14:39:11,  1.41s/it]
 39%|███▉      | 24370/61904 [2:19:28<14:39:44,  1.41s/it]
 39%|███▉      | 24371/61904 [2:19:30<14:29:43,  1.39s/it]
 39%|███▉      | 24372/61904 [2:19:31<14:56:16,  1.43s/it]
 39%|███▉      | 24373/61904 [2:19:33<14:33:22,  1.40s/it]
 39%|███▉      | 24374/61904 [2:19:34<14:00:59,  1.34s/it]
 39%|███▉      | 24375/61904 [2:19:35<14:17:09,  1.37s/it]
 39%|███▉      | 24376/61904 [2:19:37<14:27:21,  1.39s/it]
 39%|███▉      | 24377/61904 [2:19:38<14:14:21,  1.37s/it]
 39%|███▉      | 24378/61904 [2:19:40<15:03:04,  1.44s/it]
 39%|███▉      | 24379/61904 [2:19:41<15:11:08,  1.46s/it]
 39%|███▉      | 24380/61904 [2:19:42<14:44:20,  1.41s/it]
                                                          
{'loss': 2.5826, 'learning_rate': 1.6081291326332166e-07, 'epoch': 6.3}

 39%|███▉      | 24380/61904 [2:19:42<14:44:20,  1.41s/it]
 39%|███▉      | 24381/61904 [2:19:44<14:27:04,  1.39s/it]
 39%|███▉      | 24382/61904 [2:19:45<14:31:16,  1.39s/it]
 39%|███▉      | 24383/61904 [2:19:46<14:25:07,  1.38s/it]
 39%|███▉      | 24384/61904 [2:19:48<14:02:17,  1.35s/it]
 39%|███▉      | 24385/61904 [2:19:49<14:12:30,  1.36s/it]
 39%|███▉      | 24386/61904 [2:19:50<13:52:20,  1.33s/it]
 39%|███▉      | 24387/61904 [2:19:52<13:45:11,  1.32s/it]
 39%|███▉      | 24388/61904 [2:19:53<13:59:15,  1.34s/it]
 39%|███▉      | 24389/61904 [2:19:54<14:09:23,  1.36s/it]
 39%|███▉      | 24390/61904 [2:19:56<14:28:31,  1.39s/it]
 39%|███▉      | 24391/61904 [2:19:57<14:24:40,  1.38s/it]
 39%|███▉      | 24392/61904 [2:19:59<14:14:26,  1.37s/it]
 39%|███▉      | 24393/61904 [2:20:00<14:10:00,  1.36s/it]
 39%|███▉      | 24394/61904 [2:20:01<14:05:43,  1.35s/it]
 39%|███▉      | 24395/61904 [2:20:03<14:38:42,  1.41s/it]
 39%|███▉      | 24396/61904 [2:20:04<14:47:27,  1.42s/it]
 39%|███▉      | 24397/61904 [2:20:06<14:47:22,  1.42s/it]
 39%|███▉      | 24398/61904 [2:20:07<14:55:16,  1.43s/it]
 39%|███▉      | 24399/61904 [2:20:09<15:17:19,  1.47s/it]
 39%|███▉      | 24400/61904 [2:20:10<15:17:22,  1.47s/it]
                                                          
{'loss': 2.6395, 'learning_rate': 1.6078050045377932e-07, 'epoch': 6.31}

 39%|███▉      | 24400/61904 [2:20:10<15:17:22,  1.47s/it]
 39%|███▉      | 24401/61904 [2:20:12<15:10:02,  1.46s/it]
 39%|███▉      | 24402/61904 [2:20:13<14:51:00,  1.43s/it]
 39%|███▉      | 24403/61904 [2:20:14<14:45:10,  1.42s/it]
 39%|███▉      | 24404/61904 [2:20:16<14:36:18,  1.40s/it]
 39%|███▉      | 24405/61904 [2:20:17<14:36:30,  1.40s/it]
 39%|███▉      | 24406/61904 [2:20:18<14:30:40,  1.39s/it]
 39%|███▉      | 24407/61904 [2:20:20<14:44:46,  1.42s/it]
 39%|███▉      | 24408/61904 [2:20:21<15:00:37,  1.44s/it]
 39%|███▉      | 24409/61904 [2:20:23<14:42:02,  1.41s/it]
 39%|███▉      | 24410/61904 [2:20:24<14:27:33,  1.39s/it]
 39%|███▉      | 24411/61904 [2:20:26<14:29:53,  1.39s/it]
 39%|███▉      | 24412/61904 [2:20:27<14:01:46,  1.35s/it]
 39%|███▉      | 24413/61904 [2:20:28<14:04:33,  1.35s/it]
 39%|███▉      | 24414/61904 [2:20:30<14:11:40,  1.36s/it]
 39%|███▉      | 24415/61904 [2:20:31<14:21:31,  1.38s/it]
 39%|███▉      | 24416/61904 [2:20:32<14:17:51,  1.37s/it]
 39%|███▉      | 24417/61904 [2:20:34<14:40:03,  1.41s/it]
 39%|███▉      | 24418/61904 [2:20:35<14:37:32,  1.40s/it]
 39%|███▉      | 24419/61904 [2:20:37<14:58:35,  1.44s/it]
 39%|███▉      | 24420/61904 [2:20:38<14:57:29,  1.44s/it]
                                                          
{'loss': 2.6305, 'learning_rate': 1.60748087644237e-07, 'epoch': 6.31}

 39%|███▉      | 24420/61904 [2:20:38<14:57:29,  1.44s/it]
 39%|███▉      | 24421/61904 [2:20:39<14:32:26,  1.40s/it]
 39%|███▉      | 24422/61904 [2:20:41<14:31:46,  1.40s/it]
 39%|███▉      | 24423/61904 [2:20:42<14:17:18,  1.37s/it]
 39%|███▉      | 24424/61904 [2:20:44<14:14:30,  1.37s/it]
 39%|███▉      | 24425/61904 [2:20:45<14:02:25,  1.35s/it]
 39%|███▉      | 24426/61904 [2:20:46<14:09:41,  1.36s/it]
 39%|███▉      | 24427/61904 [2:20:48<14:49:27,  1.42s/it]
 39%|███▉      | 24428/61904 [2:20:49<15:02:22,  1.44s/it]
 39%|███▉      | 24429/61904 [2:20:51<14:55:31,  1.43s/it]
 39%|███▉      | 24430/61904 [2:20:52<15:05:49,  1.45s/it]
 39%|███▉      | 24431/61904 [2:20:54<15:00:27,  1.44s/it]
 39%|███▉      | 24432/61904 [2:20:55<14:50:10,  1.43s/it]
 39%|███▉      | 24433/61904 [2:20:56<14:34:33,  1.40s/it]
 39%|███▉      | 24434/61904 [2:20:58<14:35:17,  1.40s/it]
 39%|███▉      | 24435/61904 [2:20:59<14:34:36,  1.40s/it]
 39%|███▉      | 24436/61904 [2:21:01<14:37:15,  1.40s/it]
 39%|███▉      | 24437/61904 [2:21:02<15:04:27,  1.45s/it]
 39%|███▉      | 24438/61904 [2:21:03<14:46:04,  1.42s/it]
 39%|███▉      | 24439/61904 [2:21:05<14:39:44,  1.41s/it]
 39%|███▉      | 24440/61904 [2:21:06<14:59:20,  1.44s/it]
                                                          
{'loss': 2.6493, 'learning_rate': 1.6071567483469465e-07, 'epoch': 6.32}

 39%|███▉      | 24440/61904 [2:21:06<14:59:20,  1.44s/it]
 39%|███▉      | 24441/61904 [2:21:08<14:46:15,  1.42s/it]
 39%|███▉      | 24442/61904 [2:21:09<14:48:52,  1.42s/it]
 39%|███▉      | 24443/61904 [2:21:10<14:33:18,  1.40s/it]
 39%|███▉      | 24444/61904 [2:21:12<14:41:31,  1.41s/it]
 39%|███▉      | 24445/61904 [2:21:13<14:29:10,  1.39s/it]
 39%|███▉      | 24446/61904 [2:21:15<14:24:57,  1.39s/it]
 39%|███▉      | 24447/61904 [2:21:16<14:52:36,  1.43s/it]
 39%|███▉      | 24448/61904 [2:21:18<14:40:07,  1.41s/it]
 39%|███▉      | 24449/61904 [2:21:19<14:55:04,  1.43s/it]
 39%|███▉      | 24450/61904 [2:21:20<14:40:23,  1.41s/it]
 39%|███▉      | 24451/61904 [2:21:22<14:35:10,  1.40s/it]
 39%|███▉      | 24452/61904 [2:21:23<14:26:20,  1.39s/it]
 40%|███▉      | 24453/61904 [2:21:24<14:21:39,  1.38s/it]
 40%|███▉      | 24454/61904 [2:21:26<14:43:27,  1.42s/it]
 40%|███▉      | 24455/61904 [2:21:27<14:13:57,  1.37s/it]
 40%|███▉      | 24456/61904 [2:21:29<14:07:55,  1.36s/it]
 40%|███▉      | 24457/61904 [2:21:30<14:11:36,  1.36s/it]
 40%|███▉      | 24458/61904 [2:21:31<14:15:03,  1.37s/it]
 40%|███▉      | 24459/61904 [2:21:33<13:56:49,  1.34s/it]
 40%|███▉      | 24460/61904 [2:21:34<14:23:21,  1.38s/it]
                                                          
{'loss': 2.6198, 'learning_rate': 1.6068326202515233e-07, 'epoch': 6.32}

 40%|███▉      | 24460/61904 [2:21:34<14:23:21,  1.38s/it]
 40%|███▉      | 24461/61904 [2:21:36<14:51:02,  1.43s/it]
 40%|███▉      | 24462/61904 [2:21:37<15:22:16,  1.48s/it]
 40%|███▉      | 24463/61904 [2:21:39<14:52:21,  1.43s/it]
 40%|███▉      | 24464/61904 [2:21:40<14:57:59,  1.44s/it]
 40%|███▉      | 24465/61904 [2:21:41<14:25:43,  1.39s/it]
 40%|███▉      | 24466/61904 [2:21:43<14:38:44,  1.41s/it]
 40%|███▉      | 24467/61904 [2:21:44<14:18:14,  1.38s/it]
 40%|███▉      | 24468/61904 [2:21:45<14:16:36,  1.37s/it]
 40%|███▉      | 24469/61904 [2:21:47<14:56:42,  1.44s/it]
 40%|███▉      | 24470/61904 [2:21:48<14:54:17,  1.43s/it]
 40%|███▉      | 24471/61904 [2:21:50<14:34:25,  1.40s/it]
 40%|███▉      | 24472/61904 [2:21:51<14:30:20,  1.40s/it]
 40%|███▉      | 24473/61904 [2:21:52<14:28:21,  1.39s/it]
 40%|███▉      | 24474/61904 [2:21:54<14:25:23,  1.39s/it]
 40%|███▉      | 24475/61904 [2:21:55<14:24:59,  1.39s/it]
 40%|███▉      | 24476/61904 [2:21:57<14:12:11,  1.37s/it]
 40%|███▉      | 24477/61904 [2:21:58<14:39:23,  1.41s/it]
 40%|███▉      | 24478/61904 [2:22:00<14:42:16,  1.41s/it]
 40%|███▉      | 24479/61904 [2:22:01<14:31:53,  1.40s/it]
 40%|███▉      | 24480/61904 [2:22:02<14:13:30,  1.37s/it]
                                                          
{'loss': 2.5705, 'learning_rate': 1.6065084921561002e-07, 'epoch': 6.33}

 40%|███▉      | 24480/61904 [2:22:02<14:13:30,  1.37s/it]
 40%|███▉      | 24481/61904 [2:22:04<15:04:54,  1.45s/it]
 40%|███▉      | 24482/61904 [2:22:05<14:44:38,  1.42s/it]
 40%|███▉      | 24483/61904 [2:22:06<14:26:25,  1.39s/it]
 40%|███▉      | 24484/61904 [2:22:08<13:58:28,  1.34s/it]
 40%|███▉      | 24485/61904 [2:22:09<13:44:43,  1.32s/it]
 40%|███▉      | 24486/61904 [2:22:11<14:23:23,  1.38s/it]
 40%|███▉      | 24487/61904 [2:22:12<14:35:40,  1.40s/it]
 40%|███▉      | 24488/61904 [2:22:14<15:01:11,  1.45s/it]
 40%|███▉      | 24489/61904 [2:22:15<15:15:40,  1.47s/it]
 40%|███▉      | 24490/61904 [2:22:16<15:13:27,  1.46s/it]
 40%|███▉      | 24491/61904 [2:22:18<14:29:39,  1.39s/it]
 40%|███▉      | 24492/61904 [2:22:19<14:29:12,  1.39s/it]
 40%|███▉      | 24493/61904 [2:22:20<14:18:50,  1.38s/it]
 40%|███▉      | 24494/61904 [2:22:22<14:41:02,  1.41s/it]
 40%|███▉      | 24495/61904 [2:22:23<14:41:06,  1.41s/it]
 40%|███▉      | 24496/61904 [2:22:25<14:37:30,  1.41s/it]
 40%|███▉      | 24497/61904 [2:22:26<14:36:43,  1.41s/it]
 40%|███▉      | 24498/61904 [2:22:28<14:51:39,  1.43s/it]
 40%|███▉      | 24499/61904 [2:22:29<14:26:35,  1.39s/it]
 40%|███▉      | 24500/61904 [2:22:30<14:54:33,  1.43s/it]
                                                          
{'loss': 2.5797, 'learning_rate': 1.6061843640606766e-07, 'epoch': 6.33}

 40%|███▉      | 24500/61904 [2:22:30<14:54:33,  1.43s/it]
 40%|███▉      | 24501/61904 [2:22:32<15:07:20,  1.46s/it]
 40%|███▉      | 24502/61904 [2:22:33<15:17:41,  1.47s/it]
 40%|███▉      | 24503/61904 [2:22:35<14:49:05,  1.43s/it]
 40%|███▉      | 24504/61904 [2:22:36<14:52:07,  1.43s/it]
 40%|███▉      | 24505/61904 [2:22:38<15:12:44,  1.46s/it]
 40%|███▉      | 24506/61904 [2:22:39<14:59:14,  1.44s/it]
 40%|███▉      | 24507/61904 [2:22:41<15:10:52,  1.46s/it]
 40%|███▉      | 24508/61904 [2:22:42<14:49:55,  1.43s/it]
 40%|███▉      | 24509/61904 [2:22:43<14:48:44,  1.43s/it]
 40%|███▉      | 24510/61904 [2:22:45<14:41:12,  1.41s/it]
 40%|███▉      | 24511/61904 [2:22:46<14:16:15,  1.37s/it]
 40%|███▉      | 24512/61904 [2:22:47<13:42:18,  1.32s/it]
 40%|███▉      | 24513/61904 [2:22:49<13:33:54,  1.31s/it]
 40%|███▉      | 24514/61904 [2:22:50<13:38:22,  1.31s/it]
 40%|███▉      | 24515/61904 [2:22:51<13:43:43,  1.32s/it]
 40%|███▉      | 24516/61904 [2:22:53<13:45:15,  1.32s/it]
 40%|███▉      | 24517/61904 [2:22:54<14:04:41,  1.36s/it]
 40%|███▉      | 24518/61904 [2:22:55<14:12:58,  1.37s/it]
 40%|███▉      | 24519/61904 [2:22:57<14:15:56,  1.37s/it]
 40%|███▉      | 24520/61904 [2:22:58<13:53:35,  1.34s/it]
                                                          
{'loss': 2.6152, 'learning_rate': 1.6058602359652535e-07, 'epoch': 6.34}

 40%|███▉      | 24520/61904 [2:22:58<13:53:35,  1.34s/it]
 40%|███▉      | 24521/61904 [2:22:59<14:02:08,  1.35s/it]
 40%|███▉      | 24522/61904 [2:23:01<14:07:56,  1.36s/it]
 40%|███▉      | 24523/61904 [2:23:02<13:52:21,  1.34s/it]
 40%|███▉      | 24524/61904 [2:23:03<13:44:25,  1.32s/it]
 40%|███▉      | 24525/61904 [2:23:05<14:22:57,  1.39s/it]
 40%|███▉      | 24526/61904 [2:23:06<14:48:29,  1.43s/it]
 40%|███▉      | 24527/61904 [2:23:08<14:18:03,  1.38s/it]
 40%|███▉      | 24528/61904 [2:23:09<14:19:27,  1.38s/it]
 40%|███▉      | 24529/61904 [2:23:11<14:45:26,  1.42s/it]
 40%|███▉      | 24530/61904 [2:23:12<14:42:09,  1.42s/it]
 40%|███▉      | 24531/61904 [2:23:13<14:45:36,  1.42s/it]
 40%|███▉      | 24532/61904 [2:23:15<14:09:43,  1.36s/it]
 40%|███▉      | 24533/61904 [2:23:16<14:33:01,  1.40s/it]
 40%|███▉      | 24534/61904 [2:23:18<14:30:59,  1.40s/it]
 40%|███▉      | 24535/61904 [2:23:19<14:10:40,  1.37s/it]
 40%|███▉      | 24536/61904 [2:23:20<14:33:03,  1.40s/it]
 40%|███▉      | 24537/61904 [2:23:22<14:36:59,  1.41s/it]
 40%|███▉      | 24538/61904 [2:23:23<14:07:58,  1.36s/it]
 40%|███▉      | 24539/61904 [2:23:24<14:13:12,  1.37s/it]
 40%|███▉      | 24540/61904 [2:23:26<14:14:22,  1.37s/it]
                                                          
{'loss': 2.6075, 'learning_rate': 1.60553610786983e-07, 'epoch': 6.34}

 40%|███▉      | 24540/61904 [2:23:26<14:14:22,  1.37s/it]
 40%|███▉      | 24541/61904 [2:23:27<14:32:06,  1.40s/it]
 40%|███▉      | 24542/61904 [2:23:29<14:28:55,  1.40s/it]
 40%|███▉      | 24543/61904 [2:23:30<14:00:19,  1.35s/it]
 40%|███▉      | 24544/61904 [2:23:31<14:18:46,  1.38s/it]
 40%|███▉      | 24545/61904 [2:23:33<14:06:15,  1.36s/it]
 40%|███▉      | 24546/61904 [2:23:34<14:19:16,  1.38s/it]
 40%|███▉      | 24547/61904 [2:23:35<14:11:30,  1.37s/it]
 40%|███▉      | 24548/61904 [2:23:37<13:45:20,  1.33s/it]
 40%|███▉      | 24549/61904 [2:23:38<13:54:47,  1.34s/it]
 40%|███▉      | 24550/61904 [2:23:40<14:22:03,  1.38s/it]
 40%|███▉      | 24551/61904 [2:23:41<14:12:34,  1.37s/it]
 40%|███▉      | 24552/61904 [2:23:42<14:26:24,  1.39s/it]
 40%|███▉      | 24553/61904 [2:23:44<14:19:54,  1.38s/it]
 40%|███▉      | 24554/61904 [2:23:45<14:19:33,  1.38s/it]
 40%|███▉      | 24555/61904 [2:23:46<14:19:31,  1.38s/it]
 40%|███▉      | 24556/61904 [2:23:48<14:13:39,  1.37s/it]
 40%|███▉      | 24557/61904 [2:23:49<14:22:49,  1.39s/it]
 40%|███▉      | 24558/61904 [2:23:50<14:06:45,  1.36s/it]
 40%|███▉      | 24559/61904 [2:23:52<14:03:23,  1.36s/it]
 40%|███▉      | 24560/61904 [2:23:53<14:08:26,  1.36s/it]
                                                          
{'loss': 2.6446, 'learning_rate': 1.6052119797744067e-07, 'epoch': 6.35}

 40%|███▉      | 24560/61904 [2:23:53<14:08:26,  1.36s/it]
 40%|███▉      | 24561/61904 [2:23:55<14:35:22,  1.41s/it]
 40%|███▉      | 24562/61904 [2:23:56<14:08:14,  1.36s/it]
 40%|███▉      | 24563/61904 [2:23:57<14:27:52,  1.39s/it]
 40%|███▉      | 24564/61904 [2:23:59<14:47:21,  1.43s/it]
 40%|███▉      | 24565/61904 [2:24:00<14:34:37,  1.41s/it]
 40%|███▉      | 24566/61904 [2:24:02<14:55:31,  1.44s/it]
 40%|███▉      | 24567/61904 [2:24:03<14:18:16,  1.38s/it]
 40%|███▉      | 24568/61904 [2:24:05<14:37:20,  1.41s/it]
 40%|███▉      | 24569/61904 [2:24:06<14:39:24,  1.41s/it]
 40%|███▉      | 24570/61904 [2:24:07<14:25:23,  1.39s/it]
 40%|███▉      | 24571/61904 [2:24:09<14:16:42,  1.38s/it]
 40%|███▉      | 24572/61904 [2:24:10<14:24:25,  1.39s/it]
 40%|███▉      | 24573/61904 [2:24:11<14:11:16,  1.37s/it]
 40%|███▉      | 24574/61904 [2:24:13<14:45:02,  1.42s/it]
 40%|███▉      | 24575/61904 [2:24:14<14:39:25,  1.41s/it]
 40%|███▉      | 24576/61904 [2:24:16<14:37:44,  1.41s/it]
 40%|███▉      | 24577/61904 [2:24:17<14:46:45,  1.43s/it]
 40%|███▉      | 24578/61904 [2:24:18<14:13:42,  1.37s/it]
 40%|███▉      | 24579/61904 [2:24:20<14:09:55,  1.37s/it]
 40%|███▉      | 24580/61904 [2:24:21<14:41:16,  1.42s/it]
                                                          
{'loss': 2.6204, 'learning_rate': 1.6048878516789836e-07, 'epoch': 6.35}

 40%|███▉      | 24580/61904 [2:24:21<14:41:16,  1.42s/it]
 40%|███▉      | 24581/61904 [2:24:23<14:20:06,  1.38s/it]
 40%|███▉      | 24582/61904 [2:24:24<14:04:18,  1.36s/it]
 40%|███▉      | 24583/61904 [2:24:25<14:32:49,  1.40s/it]
 40%|███▉      | 24584/61904 [2:24:27<14:43:49,  1.42s/it]
 40%|███▉      | 24585/61904 [2:24:28<14:39:24,  1.41s/it]
 40%|███▉      | 24586/61904 [2:24:30<14:40:58,  1.42s/it]
 40%|███▉      | 24587/61904 [2:24:31<15:23:48,  1.49s/it]
 40%|███▉      | 24588/61904 [2:24:33<15:07:25,  1.46s/it]
 40%|███▉      | 24589/61904 [2:24:34<15:04:43,  1.45s/it]
 40%|███▉      | 24590/61904 [2:24:36<15:16:09,  1.47s/it]
 40%|███▉      | 24591/61904 [2:24:37<14:51:32,  1.43s/it]
 40%|███▉      | 24592/61904 [2:24:38<14:13:31,  1.37s/it]
 40%|███▉      | 24593/61904 [2:24:40<14:13:06,  1.37s/it]
 40%|███▉      | 24594/61904 [2:24:41<13:54:31,  1.34s/it]
 40%|███▉      | 24595/61904 [2:24:42<14:22:48,  1.39s/it]
 40%|███▉      | 24596/61904 [2:24:44<14:07:53,  1.36s/it]
 40%|███▉      | 24597/61904 [2:24:45<14:07:05,  1.36s/it]
 40%|███▉      | 24598/61904 [2:24:47<14:25:25,  1.39s/it]
 40%|███▉      | 24599/61904 [2:24:48<14:15:41,  1.38s/it]
 40%|███▉      | 24600/61904 [2:24:49<14:11:57,  1.37s/it]
                                                          
{'loss': 2.6079, 'learning_rate': 1.60456372358356e-07, 'epoch': 6.36}

 40%|███▉      | 24600/61904 [2:24:49<14:11:57,  1.37s/it]
 40%|███▉      | 24601/61904 [2:24:51<13:54:35,  1.34s/it]
 40%|███▉      | 24602/61904 [2:24:52<13:37:49,  1.32s/it]
 40%|███▉      | 24603/61904 [2:24:53<13:54:20,  1.34s/it]
 40%|███▉      | 24604/61904 [2:24:55<14:33:32,  1.41s/it]
 40%|███▉      | 24605/61904 [2:24:56<14:26:26,  1.39s/it]
 40%|███▉      | 24606/61904 [2:24:57<14:09:30,  1.37s/it]
 40%|███▉      | 24607/61904 [2:24:59<13:32:24,  1.31s/it]
 40%|███▉      | 24608/61904 [2:25:00<14:03:08,  1.36s/it]
 40%|███▉      | 24609/61904 [2:25:01<14:06:30,  1.36s/it]
 40%|███▉      | 24610/61904 [2:25:03<13:44:38,  1.33s/it]
 40%|███▉      | 24611/61904 [2:25:04<14:02:04,  1.35s/it]
 40%|███▉      | 24612/61904 [2:25:06<14:34:53,  1.41s/it]
 40%|███▉      | 24613/61904 [2:25:07<14:03:28,  1.36s/it]
 40%|███▉      | 24614/61904 [2:25:08<13:49:20,  1.33s/it]
 40%|███▉      | 24615/61904 [2:25:10<14:03:50,  1.36s/it]
 40%|███▉      | 24616/61904 [2:25:11<14:09:50,  1.37s/it]
 40%|███▉      | 24617/61904 [2:25:12<14:01:20,  1.35s/it]
 40%|███▉      | 24618/61904 [2:25:14<14:07:21,  1.36s/it]
 40%|███▉      | 24619/61904 [2:25:15<14:06:58,  1.36s/it]
 40%|███▉      | 24620/61904 [2:25:16<14:02:41,  1.36s/it]
                                                          
{'loss': 2.59, 'learning_rate': 1.6042395954881368e-07, 'epoch': 6.36}

 40%|███▉      | 24620/61904 [2:25:16<14:02:41,  1.36s/it]
 40%|███▉      | 24621/61904 [2:25:18<13:52:22,  1.34s/it]
 40%|███▉      | 24622/61904 [2:25:19<13:49:36,  1.34s/it]
 40%|███▉      | 24623/61904 [2:25:20<14:21:05,  1.39s/it]
 40%|███▉      | 24624/61904 [2:25:22<14:24:41,  1.39s/it]
 40%|███▉      | 24625/61904 [2:25:23<14:26:42,  1.39s/it]
 40%|███▉      | 24626/61904 [2:25:25<13:54:58,  1.34s/it]
 40%|███▉      | 24627/61904 [2:25:26<13:58:40,  1.35s/it]
 40%|███▉      | 24628/61904 [2:25:27<13:39:31,  1.32s/it]
 40%|███▉      | 24629/61904 [2:25:28<13:29:11,  1.30s/it]
 40%|███▉      | 24630/61904 [2:25:30<14:00:26,  1.35s/it]
 40%|███▉      | 24631/61904 [2:25:31<14:01:20,  1.35s/it]
 40%|███▉      | 24632/61904 [2:25:33<14:15:44,  1.38s/it]
 40%|███▉      | 24633/61904 [2:25:34<14:52:37,  1.44s/it]
 40%|███▉      | 24634/61904 [2:25:36<14:47:00,  1.43s/it]
 40%|███▉      | 24635/61904 [2:25:37<14:41:18,  1.42s/it]
 40%|███▉      | 24636/61904 [2:25:38<14:49:36,  1.43s/it]
 40%|███▉      | 24637/61904 [2:25:40<14:31:55,  1.40s/it]
 40%|███▉      | 24638/61904 [2:25:41<14:10:53,  1.37s/it]
 40%|███▉      | 24639/61904 [2:25:42<14:01:18,  1.35s/it]
 40%|███▉      | 24640/61904 [2:25:44<13:54:03,  1.34s/it]
                                                          
{'loss': 2.6417, 'learning_rate': 1.6039154673927137e-07, 'epoch': 6.37}

 40%|███▉      | 24640/61904 [2:25:44<13:54:03,  1.34s/it]
 40%|███▉      | 24641/61904 [2:25:45<14:04:48,  1.36s/it]
 40%|███▉      | 24642/61904 [2:25:47<14:11:14,  1.37s/it]
 40%|███▉      | 24643/61904 [2:25:48<14:09:54,  1.37s/it]
 40%|███▉      | 24644/61904 [2:25:49<14:31:33,  1.40s/it]
 40%|███▉      | 24645/61904 [2:25:51<14:20:47,  1.39s/it]
 40%|███▉      | 24646/61904 [2:25:52<14:37:10,  1.41s/it]
 40%|███▉      | 24647/61904 [2:25:54<14:32:30,  1.41s/it]
 40%|███▉      | 24648/61904 [2:25:55<14:07:38,  1.37s/it]
 40%|███▉      | 24649/61904 [2:25:56<14:20:52,  1.39s/it]
 40%|███▉      | 24650/61904 [2:25:58<14:13:10,  1.37s/it]
 40%|███▉      | 24651/61904 [2:25:59<14:25:25,  1.39s/it]
 40%|███▉      | 24652/61904 [2:26:00<14:27:34,  1.40s/it]
 40%|███▉      | 24653/61904 [2:26:02<13:56:03,  1.35s/it]
 40%|███▉      | 24654/61904 [2:26:03<13:52:32,  1.34s/it]
 40%|███▉      | 24655/61904 [2:26:04<13:52:43,  1.34s/it]
 40%|███▉      | 24656/61904 [2:26:06<13:36:11,  1.31s/it]
 40%|███▉      | 24657/61904 [2:26:07<13:48:57,  1.34s/it]
 40%|███▉      | 24658/61904 [2:26:08<13:47:40,  1.33s/it]
 40%|███▉      | 24659/61904 [2:26:10<13:59:29,  1.35s/it]
 40%|███▉      | 24660/61904 [2:26:11<13:59:26,  1.35s/it]
                                                          
{'loss': 2.6426, 'learning_rate': 1.60359133929729e-07, 'epoch': 6.37}

 40%|███▉      | 24660/61904 [2:26:11<13:59:26,  1.35s/it]
 40%|███▉      | 24661/61904 [2:26:13<14:14:55,  1.38s/it]
 40%|███▉      | 24662/61904 [2:26:14<14:27:37,  1.40s/it]
 40%|███▉      | 24663/61904 [2:26:15<14:15:20,  1.38s/it]
 40%|███▉      | 24664/61904 [2:26:17<14:04:40,  1.36s/it]
 40%|███▉      | 24665/61904 [2:26:18<13:52:27,  1.34s/it]
 40%|███▉      | 24666/61904 [2:26:19<13:43:43,  1.33s/it]
 40%|███▉      | 24667/61904 [2:26:21<13:56:50,  1.35s/it]
 40%|███▉      | 24668/61904 [2:26:22<14:14:07,  1.38s/it]
 40%|███▉      | 24669/61904 [2:26:23<14:04:45,  1.36s/it]
 40%|███▉      | 24670/61904 [2:26:25<13:50:27,  1.34s/it]
 40%|███▉      | 24671/61904 [2:26:26<13:54:27,  1.34s/it]
 40%|███▉      | 24672/61904 [2:26:27<13:52:59,  1.34s/it]
 40%|███▉      | 24673/61904 [2:26:29<13:49:14,  1.34s/it]
 40%|███▉      | 24674/61904 [2:26:30<13:37:59,  1.32s/it]
 40%|███▉      | 24675/61904 [2:26:31<13:55:05,  1.35s/it]
 40%|███▉      | 24676/61904 [2:26:33<14:25:19,  1.39s/it]
 40%|███▉      | 24677/61904 [2:26:34<14:27:53,  1.40s/it]
 40%|███▉      | 24678/61904 [2:26:36<14:18:35,  1.38s/it]
 40%|███▉      | 24679/61904 [2:26:37<14:09:39,  1.37s/it]
 40%|███▉      | 24680/61904 [2:26:38<13:46:10,  1.33s/it]
                                                          
{'loss': 2.6004, 'learning_rate': 1.603267211201867e-07, 'epoch': 6.38}

 40%|███▉      | 24680/61904 [2:26:38<13:46:10,  1.33s/it]
 40%|███▉      | 24681/61904 [2:26:40<13:35:06,  1.31s/it]
 40%|███▉      | 24682/61904 [2:26:41<13:51:08,  1.34s/it]
 40%|███▉      | 24683/61904 [2:26:42<13:57:43,  1.35s/it]
 40%|███▉      | 24684/61904 [2:26:44<13:42:01,  1.33s/it]
 40%|███▉      | 24685/61904 [2:26:45<13:42:08,  1.33s/it]
 40%|███▉      | 24686/61904 [2:26:46<14:11:10,  1.37s/it]
 40%|███▉      | 24687/61904 [2:26:48<13:59:08,  1.35s/it]
 40%|███▉      | 24688/61904 [2:26:49<14:10:08,  1.37s/it]
 40%|███▉      | 24689/61904 [2:26:50<13:50:18,  1.34s/it]
 40%|███▉      | 24690/61904 [2:26:52<14:10:40,  1.37s/it]
 40%|███▉      | 24691/61904 [2:26:53<14:10:53,  1.37s/it]
 40%|███▉      | 24692/61904 [2:26:55<14:05:47,  1.36s/it]
 40%|███▉      | 24693/61904 [2:26:56<13:39:22,  1.32s/it]
 40%|███▉      | 24694/61904 [2:26:57<13:35:22,  1.31s/it]
 40%|███▉      | 24695/61904 [2:26:58<13:46:13,  1.33s/it]
 40%|███▉      | 24696/61904 [2:27:00<13:44:13,  1.33s/it]
 40%|███▉      | 24697/61904 [2:27:01<13:49:12,  1.34s/it]
 40%|███▉      | 24698/61904 [2:27:02<13:50:54,  1.34s/it]
 40%|███▉      | 24699/61904 [2:27:04<13:37:06,  1.32s/it]
 40%|███▉      | 24700/61904 [2:27:05<14:03:24,  1.36s/it]
                                                          
{'loss': 2.6422, 'learning_rate': 1.6029430831064438e-07, 'epoch': 6.38}

 40%|███▉      | 24700/61904 [2:27:05<14:03:24,  1.36s/it]
 40%|███▉      | 24701/61904 [2:27:06<13:59:17,  1.35s/it]
 40%|███▉      | 24702/61904 [2:27:08<14:25:28,  1.40s/it]
 40%|███▉      | 24703/61904 [2:27:09<14:41:37,  1.42s/it]
 40%|███▉      | 24704/61904 [2:27:11<14:12:23,  1.37s/it]
 40%|███▉      | 24705/61904 [2:27:12<14:24:03,  1.39s/it]
 40%|███▉      | 24706/61904 [2:27:14<14:29:52,  1.40s/it]
 40%|███▉      | 24707/61904 [2:27:15<14:26:45,  1.40s/it]
 40%|███▉      | 24708/61904 [2:27:17<14:56:41,  1.45s/it]
 40%|███▉      | 24709/61904 [2:27:18<15:14:00,  1.47s/it]
 40%|███▉      | 24710/61904 [2:27:19<14:47:31,  1.43s/it]
 40%|███▉      | 24711/61904 [2:27:21<15:04:07,  1.46s/it]
 40%|███▉      | 24712/61904 [2:27:22<14:29:01,  1.40s/it]
 40%|███▉      | 24713/61904 [2:27:24<14:58:11,  1.45s/it]
 40%|███▉      | 24714/61904 [2:27:25<15:08:37,  1.47s/it]
 40%|███▉      | 24715/61904 [2:27:27<15:07:31,  1.46s/it]
 40%|███▉      | 24716/61904 [2:27:28<14:54:36,  1.44s/it]
 40%|███▉      | 24717/61904 [2:27:30<14:44:51,  1.43s/it]
 40%|███▉      | 24718/61904 [2:27:31<15:13:45,  1.47s/it]
 40%|███▉      | 24719/61904 [2:27:32<14:42:56,  1.42s/it]
 40%|███▉      | 24720/61904 [2:27:34<14:26:27,  1.40s/it]
                                                          
{'loss': 2.595, 'learning_rate': 1.6026189550110202e-07, 'epoch': 6.39}

 40%|███▉      | 24720/61904 [2:27:34<14:26:27,  1.40s/it]
 40%|███▉      | 24721/61904 [2:27:35<14:10:32,  1.37s/it]
 40%|███▉      | 24722/61904 [2:27:36<13:43:36,  1.33s/it]
 40%|███▉      | 24723/61904 [2:27:38<13:23:36,  1.30s/it]
 40%|███▉      | 24724/61904 [2:27:39<13:40:44,  1.32s/it]
 40%|███▉      | 24725/61904 [2:27:40<13:47:21,  1.34s/it]
 40%|███▉      | 24726/61904 [2:27:41<13:31:24,  1.31s/it]
 40%|███▉      | 24727/61904 [2:27:43<13:27:40,  1.30s/it]
 40%|███▉      | 24728/61904 [2:27:44<13:10:54,  1.28s/it]
 40%|███▉      | 24729/61904 [2:27:45<13:41:03,  1.33s/it]
 40%|███▉      | 24730/61904 [2:27:47<13:42:47,  1.33s/it]
 40%|███▉      | 24731/61904 [2:27:48<13:48:46,  1.34s/it]
 40%|███▉      | 24732/61904 [2:27:49<13:39:11,  1.32s/it]
 40%|███▉      | 24733/61904 [2:27:51<13:34:48,  1.32s/it]
 40%|███▉      | 24734/61904 [2:27:52<13:52:23,  1.34s/it]
 40%|███▉      | 24735/61904 [2:27:53<13:42:26,  1.33s/it]
 40%|███▉      | 24736/61904 [2:27:55<13:28:06,  1.30s/it]
 40%|███▉      | 24737/61904 [2:27:56<13:51:29,  1.34s/it]
 40%|███▉      | 24738/61904 [2:27:57<13:55:35,  1.35s/it]
 40%|███▉      | 24739/61904 [2:27:59<14:02:10,  1.36s/it]
 40%|███▉      | 24740/61904 [2:28:00<13:36:09,  1.32s/it]
                                                          
{'loss': 2.6091, 'learning_rate': 1.602294826915597e-07, 'epoch': 6.39}

 40%|███▉      | 24740/61904 [2:28:00<13:36:09,  1.32s/it]
 40%|███▉      | 24741/61904 [2:28:01<13:43:18,  1.33s/it]
 40%|███▉      | 24742/61904 [2:28:03<13:30:29,  1.31s/it]
 40%|███▉      | 24743/61904 [2:28:04<13:24:23,  1.30s/it]
 40%|███▉      | 24744/61904 [2:28:05<13:31:35,  1.31s/it]
 40%|███▉      | 24745/61904 [2:28:07<14:15:46,  1.38s/it]
 40%|███▉      | 24746/61904 [2:28:08<13:56:08,  1.35s/it]
 40%|███▉      | 24747/61904 [2:28:10<14:13:33,  1.38s/it]
 40%|███▉      | 24748/61904 [2:28:11<14:06:03,  1.37s/it]
 40%|███▉      | 24749/61904 [2:28:12<13:57:30,  1.35s/it]
 40%|███▉      | 24750/61904 [2:28:14<13:45:55,  1.33s/it]
 40%|███▉      | 24751/61904 [2:28:15<14:27:43,  1.40s/it]
 40%|███▉      | 24752/61904 [2:28:16<14:28:32,  1.40s/it]
 40%|███▉      | 24753/61904 [2:28:18<14:21:40,  1.39s/it]
 40%|███▉      | 24754/61904 [2:28:19<14:30:56,  1.41s/it]
 40%|███▉      | 24755/61904 [2:28:21<14:46:59,  1.43s/it]
 40%|███▉      | 24756/61904 [2:28:22<14:24:06,  1.40s/it]
 40%|███▉      | 24757/61904 [2:28:23<14:24:17,  1.40s/it]
 40%|███▉      | 24758/61904 [2:28:25<14:22:54,  1.39s/it]
 40%|███▉      | 24759/61904 [2:28:26<14:09:05,  1.37s/it]
 40%|███▉      | 24760/61904 [2:28:28<14:02:01,  1.36s/it]
                                                          
{'loss': 2.5978, 'learning_rate': 1.6019706988201737e-07, 'epoch': 6.4}

 40%|███▉      | 24760/61904 [2:28:28<14:02:01,  1.36s/it]
 40%|███▉      | 24761/61904 [2:28:29<15:18:20,  1.48s/it]
 40%|████      | 24762/61904 [2:28:31<15:03:00,  1.46s/it]
 40%|████      | 24763/61904 [2:28:32<14:40:49,  1.42s/it]
 40%|████      | 24764/61904 [2:28:33<14:41:47,  1.42s/it]
 40%|████      | 24765/61904 [2:28:35<14:39:55,  1.42s/it]
 40%|████      | 24766/61904 [2:28:36<13:59:22,  1.36s/it]
 40%|████      | 24767/61904 [2:28:37<13:47:28,  1.34s/it]
 40%|████      | 24768/61904 [2:28:39<13:42:21,  1.33s/it]
 40%|████      | 24769/61904 [2:28:40<13:56:29,  1.35s/it]
 40%|████      | 24770/61904 [2:28:41<13:52:20,  1.34s/it]
 40%|████      | 24771/61904 [2:28:43<13:35:48,  1.32s/it]
 40%|████      | 24772/61904 [2:28:44<13:53:16,  1.35s/it]
 40%|████      | 24773/61904 [2:28:45<13:47:29,  1.34s/it]
 40%|████      | 24774/61904 [2:28:47<13:46:01,  1.33s/it]
 40%|████      | 24775/61904 [2:28:48<13:41:38,  1.33s/it]
 40%|████      | 24776/61904 [2:28:49<13:59:45,  1.36s/it]
 40%|████      | 24777/61904 [2:28:51<13:47:16,  1.34s/it]
 40%|████      | 24778/61904 [2:28:52<13:45:29,  1.33s/it]
 40%|████      | 24779/61904 [2:28:53<13:56:13,  1.35s/it]
 40%|████      | 24780/61904 [2:28:55<13:55:08,  1.35s/it]
                                                          
{'loss': 2.5525, 'learning_rate': 1.6016465707247503e-07, 'epoch': 6.4}

 40%|████      | 24780/61904 [2:28:55<13:55:08,  1.35s/it]
 40%|████      | 24781/61904 [2:28:56<13:30:16,  1.31s/it]
 40%|████      | 24782/61904 [2:28:57<13:22:30,  1.30s/it]
 40%|████      | 24783/61904 [2:28:59<13:36:17,  1.32s/it]
 40%|████      | 24784/61904 [2:29:00<14:25:45,  1.40s/it]
 40%|████      | 24785/61904 [2:29:02<13:58:16,  1.36s/it]
 40%|████      | 24786/61904 [2:29:03<14:12:03,  1.38s/it]
 40%|████      | 24787/61904 [2:29:04<13:44:47,  1.33s/it]
 40%|████      | 24788/61904 [2:29:06<13:53:31,  1.35s/it]
 40%|████      | 24789/61904 [2:29:07<13:56:23,  1.35s/it]
 40%|████      | 24790/61904 [2:29:08<13:48:32,  1.34s/it]
 40%|████      | 24791/61904 [2:29:10<14:18:37,  1.39s/it]
 40%|████      | 24792/61904 [2:29:11<14:27:20,  1.40s/it]
 40%|████      | 24793/61904 [2:29:13<14:14:49,  1.38s/it]
 40%|████      | 24794/61904 [2:29:14<14:03:54,  1.36s/it]
 40%|████      | 24795/61904 [2:29:15<14:29:10,  1.41s/it]
 40%|████      | 24796/61904 [2:29:17<14:36:43,  1.42s/it]
 40%|████      | 24797/61904 [2:29:18<14:19:49,  1.39s/it]
 40%|████      | 24798/61904 [2:29:20<14:26:02,  1.40s/it]
 40%|████      | 24799/61904 [2:29:21<14:24:07,  1.40s/it]
 40%|████      | 24800/61904 [2:29:22<14:25:16,  1.40s/it]
                                                          
{'loss': 2.6011, 'learning_rate': 1.6013224426293272e-07, 'epoch': 6.41}

 40%|████      | 24800/61904 [2:29:22<14:25:16,  1.40s/it]
 40%|████      | 24801/61904 [2:29:24<13:59:37,  1.36s/it]
 40%|████      | 24802/61904 [2:29:25<13:42:34,  1.33s/it]
 40%|████      | 24803/61904 [2:29:26<13:52:33,  1.35s/it]
 40%|████      | 24804/61904 [2:29:28<14:40:43,  1.42s/it]
 40%|████      | 24805/61904 [2:29:29<14:33:10,  1.41s/it]
 40%|████      | 24806/61904 [2:29:31<14:44:25,  1.43s/it]
 40%|████      | 24807/61904 [2:29:32<14:52:47,  1.44s/it]
 40%|████      | 24808/61904 [2:29:34<14:31:20,  1.41s/it]
 40%|████      | 24809/61904 [2:29:35<13:56:21,  1.35s/it]
 40%|████      | 24810/61904 [2:29:36<13:36:30,  1.32s/it]
 40%|████      | 24811/61904 [2:29:37<13:58:11,  1.36s/it]
 40%|████      | 24812/61904 [2:29:39<13:49:47,  1.34s/it]
 40%|████      | 24813/61904 [2:29:40<14:07:41,  1.37s/it]
 40%|████      | 24814/61904 [2:29:42<14:28:42,  1.41s/it]
 40%|████      | 24815/61904 [2:29:43<14:16:19,  1.39s/it]
 40%|████      | 24816/61904 [2:29:44<14:12:44,  1.38s/it]
 40%|████      | 24817/61904 [2:29:46<14:32:34,  1.41s/it]
 40%|████      | 24818/61904 [2:29:47<14:49:02,  1.44s/it]
 40%|████      | 24819/61904 [2:29:49<14:26:49,  1.40s/it]
 40%|████      | 24820/61904 [2:29:50<14:42:41,  1.43s/it]
                                                          
{'loss': 2.5727, 'learning_rate': 1.6009983145339035e-07, 'epoch': 6.41}

 40%|████      | 24820/61904 [2:29:50<14:42:41,  1.43s/it]
 40%|████      | 24821/61904 [2:29:51<14:24:43,  1.40s/it]
 40%|████      | 24822/61904 [2:29:53<14:18:48,  1.39s/it]
 40%|████      | 24823/61904 [2:29:54<14:32:30,  1.41s/it]
 40%|████      | 24824/61904 [2:29:56<14:28:46,  1.41s/it]
 40%|████      | 24825/61904 [2:29:57<14:31:57,  1.41s/it]
 40%|████      | 24826/61904 [2:29:58<14:18:18,  1.39s/it]
 40%|████      | 24827/61904 [2:30:00<13:40:16,  1.33s/it]
 40%|████      | 24828/61904 [2:30:01<13:51:30,  1.35s/it]
 40%|████      | 24829/61904 [2:30:02<13:25:20,  1.30s/it]
 40%|████      | 24830/61904 [2:30:04<13:31:04,  1.31s/it]
 40%|████      | 24831/61904 [2:30:05<13:53:49,  1.35s/it]
 40%|████      | 24832/61904 [2:30:06<14:09:18,  1.37s/it]
 40%|████      | 24833/61904 [2:30:08<14:16:50,  1.39s/it]
 40%|████      | 24834/61904 [2:30:09<14:37:24,  1.42s/it]
 40%|████      | 24835/61904 [2:30:11<13:59:29,  1.36s/it]
 40%|████      | 24836/61904 [2:30:12<14:11:35,  1.38s/it]
 40%|████      | 24837/61904 [2:30:13<14:00:24,  1.36s/it]
 40%|████      | 24838/61904 [2:30:15<13:57:00,  1.35s/it]
 40%|████      | 24839/61904 [2:30:16<13:47:28,  1.34s/it]
 40%|████      | 24840/61904 [2:30:17<13:36:18,  1.32s/it]
                                                          
{'loss': 2.6214, 'learning_rate': 1.6006741864384804e-07, 'epoch': 6.42}

 40%|████      | 24840/61904 [2:30:17<13:36:18,  1.32s/it]
 40%|████      | 24841/61904 [2:30:19<13:56:13,  1.35s/it]
 40%|████      | 24842/61904 [2:30:20<13:45:23,  1.34s/it]
 40%|████      | 24843/61904 [2:30:21<13:50:42,  1.34s/it]
 40%|████      | 24844/61904 [2:30:23<14:08:08,  1.37s/it]
 40%|████      | 24845/61904 [2:30:24<14:03:27,  1.37s/it]
 40%|████      | 24846/61904 [2:30:26<14:15:11,  1.38s/it]
 40%|████      | 24847/61904 [2:30:27<14:34:55,  1.42s/it]
 40%|████      | 24848/61904 [2:30:29<14:53:22,  1.45s/it]
 40%|████      | 24849/61904 [2:30:30<14:18:12,  1.39s/it]
 40%|████      | 24850/61904 [2:30:31<14:12:17,  1.38s/it]
 40%|████      | 24851/61904 [2:30:32<13:59:30,  1.36s/it]
 40%|████      | 24852/61904 [2:30:34<13:27:35,  1.31s/it]
 40%|████      | 24853/61904 [2:30:35<14:14:23,  1.38s/it]
 40%|████      | 24854/61904 [2:30:37<14:16:47,  1.39s/it]
 40%|████      | 24855/61904 [2:30:38<14:18:54,  1.39s/it]
 40%|████      | 24856/61904 [2:30:39<14:05:44,  1.37s/it]
 40%|████      | 24857/61904 [2:30:41<14:08:24,  1.37s/it]
 40%|████      | 24858/61904 [2:30:42<14:43:55,  1.43s/it]
 40%|████      | 24859/61904 [2:30:44<14:21:30,  1.40s/it]
 40%|████      | 24860/61904 [2:30:45<14:15:22,  1.39s/it]
                                                          
{'loss': 2.6492, 'learning_rate': 1.6003500583430573e-07, 'epoch': 6.43}

 40%|████      | 24860/61904 [2:30:45<14:15:22,  1.39s/it]
 40%|████      | 24861/61904 [2:30:46<14:17:45,  1.39s/it]
 40%|████      | 24862/61904 [2:30:48<14:27:24,  1.41s/it]
 40%|████      | 24863/61904 [2:30:49<14:07:34,  1.37s/it]
 40%|████      | 24864/61904 [2:30:50<14:05:16,  1.37s/it]
 40%|████      | 24865/61904 [2:30:52<14:02:33,  1.36s/it]
 40%|████      | 24866/61904 [2:30:53<14:25:42,  1.40s/it]
 40%|████      | 24867/61904 [2:30:55<14:10:44,  1.38s/it]
 40%|████      | 24868/61904 [2:30:56<13:56:16,  1.35s/it]
 40%|████      | 24869/61904 [2:30:57<13:41:41,  1.33s/it]
 40%|████      | 24870/61904 [2:30:58<13:27:46,  1.31s/it]
 40%|████      | 24871/61904 [2:31:00<13:31:59,  1.32s/it]
 40%|████      | 24872/61904 [2:31:01<13:33:43,  1.32s/it]
 40%|████      | 24873/61904 [2:31:02<13:38:59,  1.33s/it]
 40%|████      | 24874/61904 [2:31:04<13:42:07,  1.33s/it]
 40%|████      | 24875/61904 [2:31:05<13:55:15,  1.35s/it]
 40%|████      | 24876/61904 [2:31:07<14:37:08,  1.42s/it]
 40%|████      | 24877/61904 [2:31:08<14:24:15,  1.40s/it]
 40%|████      | 24878/61904 [2:31:10<14:36:18,  1.42s/it]
 40%|████      | 24879/61904 [2:31:11<15:17:51,  1.49s/it]
 40%|████      | 24880/61904 [2:31:13<14:47:29,  1.44s/it]
                                                          
{'loss': 2.628, 'learning_rate': 1.6000259302476336e-07, 'epoch': 6.43}

 40%|████      | 24880/61904 [2:31:13<14:47:29,  1.44s/it]
 40%|████      | 24881/61904 [2:31:14<14:47:49,  1.44s/it]
 40%|████      | 24882/61904 [2:31:16<15:23:32,  1.50s/it]
 40%|████      | 24883/61904 [2:31:17<14:52:15,  1.45s/it]
 40%|████      | 24884/61904 [2:31:18<15:01:29,  1.46s/it]
 40%|████      | 24885/61904 [2:31:20<14:34:31,  1.42s/it]
 40%|████      | 24886/61904 [2:31:21<14:08:04,  1.37s/it]
 40%|████      | 24887/61904 [2:31:22<14:10:49,  1.38s/it]
 40%|████      | 24888/61904 [2:31:24<14:16:24,  1.39s/it]
 40%|████      | 24889/61904 [2:31:25<13:47:36,  1.34s/it]
 40%|████      | 24890/61904 [2:31:26<13:42:47,  1.33s/it]
 40%|████      | 24891/61904 [2:31:28<13:32:19,  1.32s/it]
 40%|████      | 24892/61904 [2:31:29<13:54:22,  1.35s/it]
 40%|████      | 24893/61904 [2:31:31<14:13:10,  1.38s/it]
 40%|████      | 24894/61904 [2:31:32<13:58:00,  1.36s/it]
 40%|████      | 24895/61904 [2:31:33<13:49:38,  1.35s/it]
 40%|████      | 24896/61904 [2:31:35<14:08:12,  1.38s/it]
 40%|████      | 24897/61904 [2:31:36<13:54:54,  1.35s/it]
 40%|████      | 24898/61904 [2:31:37<13:38:41,  1.33s/it]
 40%|████      | 24899/61904 [2:31:39<14:11:00,  1.38s/it]
 40%|████      | 24900/61904 [2:31:40<14:08:45,  1.38s/it]
                                                          
{'loss': 2.6282, 'learning_rate': 1.5997018021522105e-07, 'epoch': 6.44}

 40%|████      | 24900/61904 [2:31:40<14:08:45,  1.38s/it]
 40%|████      | 24901/61904 [2:31:42<14:25:25,  1.40s/it]
 40%|████      | 24902/61904 [2:31:43<14:24:34,  1.40s/it]
 40%|████      | 24903/61904 [2:31:44<14:10:39,  1.38s/it]
 40%|████      | 24904/61904 [2:31:46<13:48:27,  1.34s/it]
 40%|████      | 24905/61904 [2:31:47<13:37:11,  1.33s/it]
 40%|████      | 24906/61904 [2:31:48<13:38:51,  1.33s/it]
 40%|████      | 24907/61904 [2:31:49<13:42:28,  1.33s/it]
 40%|████      | 24908/61904 [2:31:51<13:56:04,  1.36s/it]
 40%|████      | 24909/61904 [2:31:52<13:40:05,  1.33s/it]
 40%|████      | 24910/61904 [2:31:53<13:27:25,  1.31s/it]
 40%|████      | 24911/61904 [2:31:55<13:21:39,  1.30s/it]
 40%|████      | 24912/61904 [2:31:56<13:58:58,  1.36s/it]
 40%|████      | 24913/61904 [2:31:58<13:51:55,  1.35s/it]
 40%|████      | 24914/61904 [2:31:59<13:19:10,  1.30s/it]
 40%|████      | 24915/61904 [2:32:00<13:45:01,  1.34s/it]
 40%|████      | 24916/61904 [2:32:02<13:53:45,  1.35s/it]
 40%|████      | 24917/61904 [2:32:03<13:44:07,  1.34s/it]
 40%|████      | 24918/61904 [2:32:04<14:43:21,  1.43s/it]
 40%|████      | 24919/61904 [2:32:06<14:28:30,  1.41s/it]
 40%|████      | 24920/61904 [2:32:07<14:16:00,  1.39s/it]
                                                          
{'loss': 2.6483, 'learning_rate': 1.5993776740567874e-07, 'epoch': 6.44}

 40%|████      | 24920/61904 [2:32:07<14:16:00,  1.39s/it]
 40%|████      | 24921/61904 [2:32:09<14:09:01,  1.38s/it]
 40%|████      | 24922/61904 [2:32:10<14:37:47,  1.42s/it]
 40%|████      | 24923/61904 [2:32:12<14:43:52,  1.43s/it]
 40%|████      | 24924/61904 [2:32:13<14:56:59,  1.46s/it]
 40%|████      | 24925/61904 [2:32:14<14:28:04,  1.41s/it]
 40%|████      | 24926/61904 [2:32:16<14:48:29,  1.44s/it]
 40%|████      | 24927/61904 [2:32:17<14:59:45,  1.46s/it]
 40%|████      | 24928/61904 [2:32:19<14:29:51,  1.41s/it]
 40%|████      | 24929/61904 [2:32:20<13:48:58,  1.35s/it]
 40%|████      | 24930/61904 [2:32:21<13:34:44,  1.32s/it]
 40%|████      | 24931/61904 [2:32:22<13:40:04,  1.33s/it]
 40%|████      | 24932/61904 [2:32:24<13:30:01,  1.31s/it]
 40%|████      | 24933/61904 [2:32:25<13:27:08,  1.31s/it]
 40%|████      | 24934/61904 [2:32:26<13:43:15,  1.34s/it]
 40%|████      | 24935/61904 [2:32:28<13:49:41,  1.35s/it]
 40%|████      | 24936/61904 [2:32:29<14:00:45,  1.36s/it]
 40%|████      | 24937/61904 [2:32:31<14:28:56,  1.41s/it]
 40%|████      | 24938/61904 [2:32:32<14:08:05,  1.38s/it]
 40%|████      | 24939/61904 [2:32:33<13:58:49,  1.36s/it]
 40%|████      | 24940/61904 [2:32:35<13:50:46,  1.35s/it]
                                                          
{'loss': 2.6026, 'learning_rate': 1.5990535459613638e-07, 'epoch': 6.45}

 40%|████      | 24940/61904 [2:32:35<13:50:46,  1.35s/it]
 40%|████      | 24941/61904 [2:32:36<13:37:07,  1.33s/it]
 40%|████      | 24942/61904 [2:32:37<14:06:30,  1.37s/it]
 40%|████      | 24943/61904 [2:32:39<14:18:16,  1.39s/it]
 40%|████      | 24944/61904 [2:32:40<14:00:34,  1.36s/it]
 40%|████      | 24945/61904 [2:32:42<14:17:41,  1.39s/it]
 40%|████      | 24946/61904 [2:32:43<14:14:39,  1.39s/it]
 40%|████      | 24947/61904 [2:32:44<13:52:46,  1.35s/it]
 40%|████      | 24948/61904 [2:32:46<14:17:23,  1.39s/it]
 40%|████      | 24949/61904 [2:32:47<14:06:21,  1.37s/it]
 40%|████      | 24950/61904 [2:32:49<14:21:42,  1.40s/it]
 40%|████      | 24951/61904 [2:32:50<14:32:15,  1.42s/it]
 40%|████      | 24952/61904 [2:32:51<14:02:57,  1.37s/it]
 40%|████      | 24953/61904 [2:32:53<14:41:37,  1.43s/it]
 40%|████      | 24954/61904 [2:32:54<14:19:48,  1.40s/it]
 40%|████      | 24955/61904 [2:32:56<14:27:18,  1.41s/it]
 40%|████      | 24956/61904 [2:32:57<14:17:31,  1.39s/it]
 40%|████      | 24957/61904 [2:32:58<13:43:43,  1.34s/it]
 40%|████      | 24958/61904 [2:32:59<13:41:58,  1.33s/it]
 40%|████      | 24959/61904 [2:33:01<14:10:57,  1.38s/it]
 40%|████      | 24960/61904 [2:33:02<14:25:42,  1.41s/it]
                                                          
{'loss': 2.6324, 'learning_rate': 1.5987294178659407e-07, 'epoch': 6.45}

 40%|████      | 24960/61904 [2:33:02<14:25:42,  1.41s/it]
 40%|████      | 24961/61904 [2:33:04<14:15:25,  1.39s/it]
 40%|████      | 24962/61904 [2:33:05<14:04:58,  1.37s/it]
 40%|████      | 24963/61904 [2:33:07<14:32:58,  1.42s/it]
 40%|████      | 24964/61904 [2:33:08<14:28:14,  1.41s/it]
 40%|████      | 24965/61904 [2:33:09<14:10:55,  1.38s/it]
 40%|████      | 24966/61904 [2:33:11<13:54:07,  1.35s/it]
 40%|████      | 24967/61904 [2:33:12<13:59:03,  1.36s/it]
 40%|████      | 24968/61904 [2:33:13<13:59:13,  1.36s/it]
 40%|████      | 24969/61904 [2:33:15<14:05:00,  1.37s/it]
 40%|████      | 24970/61904 [2:33:16<13:51:38,  1.35s/it]
 40%|████      | 24971/61904 [2:33:17<13:36:41,  1.33s/it]
 40%|████      | 24972/61904 [2:33:19<13:53:09,  1.35s/it]
 40%|████      | 24973/61904 [2:33:20<13:54:45,  1.36s/it]
 40%|████      | 24974/61904 [2:33:21<13:51:59,  1.35s/it]
 40%|████      | 24975/61904 [2:33:23<13:58:56,  1.36s/it]
 40%|████      | 24976/61904 [2:33:24<13:49:32,  1.35s/it]
 40%|████      | 24977/61904 [2:33:26<13:50:10,  1.35s/it]
 40%|████      | 24978/61904 [2:33:27<14:24:05,  1.40s/it]
 40%|████      | 24979/61904 [2:33:28<14:09:45,  1.38s/it]
 40%|████      | 24980/61904 [2:33:30<14:09:21,  1.38s/it]
                                                          
{'loss': 2.5601, 'learning_rate': 1.5984052897705173e-07, 'epoch': 6.46}

 40%|████      | 24980/61904 [2:33:30<14:09:21,  1.38s/it]
 40%|████      | 24981/61904 [2:33:31<14:08:31,  1.38s/it]
 40%|████      | 24982/61904 [2:33:32<14:06:03,  1.37s/it]
 40%|████      | 24983/61904 [2:33:34<14:10:02,  1.38s/it]
 40%|████      | 24984/61904 [2:33:35<14:30:45,  1.42s/it]
 40%|████      | 24985/61904 [2:33:37<15:01:58,  1.47s/it]
 40%|████      | 24986/61904 [2:33:38<15:08:46,  1.48s/it]
 40%|████      | 24987/61904 [2:33:40<14:31:02,  1.42s/it]
 40%|████      | 24988/61904 [2:33:41<14:23:40,  1.40s/it]
 40%|████      | 24989/61904 [2:33:42<14:13:04,  1.39s/it]
 40%|████      | 24990/61904 [2:33:44<14:25:27,  1.41s/it]
 40%|████      | 24991/61904 [2:33:45<14:00:57,  1.37s/it]
 40%|████      | 24992/61904 [2:33:47<13:52:10,  1.35s/it]
 40%|████      | 24993/61904 [2:33:48<14:21:28,  1.40s/it]
 40%|████      | 24994/61904 [2:33:49<14:22:02,  1.40s/it]
 40%|████      | 24995/61904 [2:33:51<14:28:06,  1.41s/it]
 40%|████      | 24996/61904 [2:33:52<14:02:16,  1.37s/it]
 40%|████      | 24997/61904 [2:33:53<13:59:50,  1.37s/it]
 40%|████      | 24998/61904 [2:33:55<13:51:51,  1.35s/it]
 40%|████      | 24999/61904 [2:33:56<13:28:48,  1.31s/it]
 40%|████      | 25000/61904 [2:33:57<13:49:56,  1.35s/it]
                                                          
{'loss': 2.6437, 'learning_rate': 1.598081161675094e-07, 'epoch': 6.46}

 40%|████      | 25000/61904 [2:33:57<13:49:56,  1.35s/it]
 40%|████      | 25001/61904 [2:33:59<14:10:17,  1.38s/it]
 40%|████      | 25002/61904 [2:34:00<14:16:27,  1.39s/it]
 40%|████      | 25003/61904 [2:34:02<14:17:08,  1.39s/it]
 40%|████      | 25004/61904 [2:34:03<14:18:10,  1.40s/it]
 40%|████      | 25005/61904 [2:34:05<14:13:38,  1.39s/it]
 40%|████      | 25006/61904 [2:34:06<14:36:13,  1.42s/it]
 40%|████      | 25007/61904 [2:34:08<14:51:03,  1.45s/it]
 40%|████      | 25008/61904 [2:34:09<14:42:23,  1.43s/it]
 40%|████      | 25009/61904 [2:34:10<15:01:43,  1.47s/it]
 40%|████      | 25010/61904 [2:34:12<14:46:53,  1.44s/it]
 40%|████      | 25011/61904 [2:34:13<14:14:26,  1.39s/it]
 40%|████      | 25012/61904 [2:34:15<14:14:35,  1.39s/it]
 40%|████      | 25013/61904 [2:34:16<14:08:04,  1.38s/it]
 40%|████      | 25014/61904 [2:34:17<13:49:11,  1.35s/it]
 40%|████      | 25015/61904 [2:34:18<13:30:59,  1.32s/it]
 40%|████      | 25016/61904 [2:34:20<13:33:26,  1.32s/it]
 40%|████      | 25017/61904 [2:34:21<13:46:53,  1.35s/it]
 40%|████      | 25018/61904 [2:34:23<13:53:07,  1.36s/it]
 40%|████      | 25019/61904 [2:34:24<13:48:17,  1.35s/it]
 40%|████      | 25020/61904 [2:34:25<13:45:58,  1.34s/it]
                                                          
{'loss': 2.6326, 'learning_rate': 1.5977570335796708e-07, 'epoch': 6.47}

 40%|████      | 25020/61904 [2:34:25<13:45:58,  1.34s/it]
 40%|████      | 25021/61904 [2:34:27<14:17:04,  1.39s/it]
 40%|████      | 25022/61904 [2:34:28<14:02:35,  1.37s/it]
 40%|████      | 25023/61904 [2:34:29<13:55:07,  1.36s/it]
 40%|████      | 25024/61904 [2:34:31<14:25:07,  1.41s/it]
 40%|████      | 25025/61904 [2:34:32<14:16:10,  1.39s/it]
 40%|████      | 25026/61904 [2:34:34<14:16:22,  1.39s/it]
 40%|████      | 25027/61904 [2:34:35<14:15:01,  1.39s/it]
 40%|████      | 25028/61904 [2:34:36<14:28:25,  1.41s/it]
 40%|████      | 25029/61904 [2:34:38<14:03:11,  1.37s/it]
 40%|████      | 25030/61904 [2:34:39<14:02:23,  1.37s/it]
 40%|████      | 25031/61904 [2:34:40<13:58:11,  1.36s/it]
 40%|████      | 25032/61904 [2:34:42<13:51:28,  1.35s/it]
 40%|████      | 25033/61904 [2:34:43<14:00:27,  1.37s/it]
 40%|████      | 25034/61904 [2:34:44<13:35:51,  1.33s/it]
 40%|████      | 25035/61904 [2:34:46<13:41:57,  1.34s/it]
 40%|████      | 25036/61904 [2:34:47<13:32:42,  1.32s/it]
 40%|████      | 25037/61904 [2:34:48<13:39:14,  1.33s/it]
 40%|████      | 25038/61904 [2:34:50<13:26:46,  1.31s/it]
 40%|████      | 25039/61904 [2:34:51<13:49:41,  1.35s/it]
 40%|████      | 25040/61904 [2:34:53<14:02:47,  1.37s/it]
                                                          
{'loss': 2.6664, 'learning_rate': 1.597432905484247e-07, 'epoch': 6.47}

 40%|████      | 25040/61904 [2:34:53<14:02:47,  1.37s/it]
 40%|████      | 25041/61904 [2:34:54<13:38:42,  1.33s/it]
 40%|████      | 25042/61904 [2:34:55<13:32:52,  1.32s/it]
 40%|████      | 25043/61904 [2:34:57<13:54:04,  1.36s/it]
 40%|████      | 25044/61904 [2:34:58<13:52:35,  1.36s/it]
 40%|████      | 25045/61904 [2:34:59<14:02:04,  1.37s/it]
 40%|████      | 25046/61904 [2:35:01<14:07:21,  1.38s/it]
 40%|████      | 25047/61904 [2:35:02<14:03:55,  1.37s/it]
 40%|████      | 25048/61904 [2:35:04<14:30:47,  1.42s/it]
 40%|████      | 25049/61904 [2:35:05<14:37:58,  1.43s/it]
 40%|████      | 25050/61904 [2:35:06<14:28:23,  1.41s/it]
 40%|████      | 25051/61904 [2:35:08<14:18:50,  1.40s/it]
 40%|████      | 25052/61904 [2:35:09<14:14:14,  1.39s/it]
 40%|████      | 25053/61904 [2:35:10<14:08:47,  1.38s/it]
 40%|████      | 25054/61904 [2:35:12<14:13:08,  1.39s/it]
 40%|████      | 25055/61904 [2:35:13<14:15:47,  1.39s/it]
 40%|████      | 25056/61904 [2:35:15<13:51:57,  1.35s/it]
 40%|████      | 25057/61904 [2:35:16<14:04:06,  1.37s/it]
 40%|████      | 25058/61904 [2:35:17<13:39:40,  1.33s/it]
 40%|████      | 25059/61904 [2:35:18<13:19:46,  1.30s/it]
 40%|████      | 25060/61904 [2:35:20<13:24:31,  1.31s/it]
                                                          
{'loss': 2.6057, 'learning_rate': 1.597108777388824e-07, 'epoch': 6.48}

 40%|████      | 25060/61904 [2:35:20<13:24:31,  1.31s/it]
 40%|████      | 25061/61904 [2:35:21<13:29:16,  1.32s/it]
 40%|████      | 25062/61904 [2:35:22<13:36:44,  1.33s/it]
 40%|████      | 25063/61904 [2:35:24<13:39:03,  1.33s/it]
 40%|████      | 25064/61904 [2:35:25<13:15:12,  1.30s/it]
 40%|████      | 25065/61904 [2:35:26<13:31:26,  1.32s/it]
 40%|████      | 25066/61904 [2:35:28<13:30:09,  1.32s/it]
 40%|████      | 25067/61904 [2:35:29<13:59:58,  1.37s/it]
 40%|████      | 25068/61904 [2:35:30<13:45:45,  1.35s/it]
 40%|████      | 25069/61904 [2:35:32<14:06:34,  1.38s/it]
 40%|████      | 25070/61904 [2:35:33<13:57:17,  1.36s/it]
 40%|████      | 25071/61904 [2:35:35<13:34:23,  1.33s/it]
 41%|████      | 25072/61904 [2:35:36<13:31:00,  1.32s/it]
 41%|████      | 25073/61904 [2:35:37<13:22:08,  1.31s/it]
 41%|████      | 25074/61904 [2:35:39<14:01:56,  1.37s/it]
 41%|████      | 25075/61904 [2:35:40<14:03:28,  1.37s/it]
 41%|████      | 25076/61904 [2:35:41<14:05:14,  1.38s/it]
 41%|████      | 25077/61904 [2:35:43<13:52:52,  1.36s/it]
 41%|████      | 25078/61904 [2:35:44<14:10:57,  1.39s/it]
 41%|████      | 25079/61904 [2:35:46<14:11:28,  1.39s/it]
 41%|████      | 25080/61904 [2:35:47<14:16:25,  1.40s/it]
                                                          
{'loss': 2.6007, 'learning_rate': 1.596784649293401e-07, 'epoch': 6.48}

 41%|████      | 25080/61904 [2:35:47<14:16:25,  1.40s/it]
 41%|████      | 25081/61904 [2:35:48<14:25:05,  1.41s/it]
 41%|████      | 25082/61904 [2:35:50<14:43:33,  1.44s/it]
 41%|████      | 25083/61904 [2:35:51<14:41:15,  1.44s/it]
 41%|████      | 25084/61904 [2:35:53<14:19:39,  1.40s/it]
 41%|████      | 25085/61904 [2:35:54<14:03:19,  1.37s/it]
 41%|████      | 25086/61904 [2:35:55<14:21:11,  1.40s/it]
 41%|████      | 25087/61904 [2:35:57<14:01:52,  1.37s/it]
 41%|████      | 25088/61904 [2:35:58<14:08:48,  1.38s/it]
 41%|████      | 25089/61904 [2:36:00<14:22:16,  1.41s/it]
 41%|████      | 25090/61904 [2:36:01<13:53:03,  1.36s/it]
 41%|████      | 25091/61904 [2:36:02<14:35:55,  1.43s/it]
 41%|████      | 25092/61904 [2:36:04<14:05:54,  1.38s/it]
 41%|████      | 25093/61904 [2:36:05<14:00:36,  1.37s/it]
 41%|████      | 25094/61904 [2:36:06<13:37:48,  1.33s/it]
 41%|████      | 25095/61904 [2:36:08<13:39:32,  1.34s/it]
 41%|████      | 25096/61904 [2:36:09<13:24:19,  1.31s/it]
 41%|████      | 25097/61904 [2:36:10<13:12:34,  1.29s/it]
 41%|████      | 25098/61904 [2:36:12<13:27:59,  1.32s/it]
 41%|████      | 25099/61904 [2:36:13<13:31:18,  1.32s/it]
 41%|████      | 25100/61904 [2:36:14<13:44:41,  1.34s/it]
                                                          
{'loss': 2.5935, 'learning_rate': 1.5964605211979772e-07, 'epoch': 6.49}

 41%|████      | 25100/61904 [2:36:14<13:44:41,  1.34s/it]
 41%|████      | 25101/61904 [2:36:16<14:03:46,  1.38s/it]
 41%|████      | 25102/61904 [2:36:17<13:51:33,  1.36s/it]
 41%|████      | 25103/61904 [2:36:18<13:42:37,  1.34s/it]
 41%|████      | 25104/61904 [2:36:20<13:37:48,  1.33s/it]
 41%|████      | 25105/61904 [2:36:21<13:23:53,  1.31s/it]
 41%|████      | 25106/61904 [2:36:22<13:42:23,  1.34s/it]
 41%|████      | 25107/61904 [2:36:24<14:22:18,  1.41s/it]
 41%|████      | 25108/61904 [2:36:25<14:37:36,  1.43s/it]
 41%|████      | 25109/61904 [2:36:27<14:23:14,  1.41s/it]
 41%|████      | 25110/61904 [2:36:28<14:35:42,  1.43s/it]
 41%|████      | 25111/61904 [2:36:29<14:06:20,  1.38s/it]
 41%|████      | 25112/61904 [2:36:31<14:34:12,  1.43s/it]
 41%|████      | 25113/61904 [2:36:32<14:26:18,  1.41s/it]
 41%|████      | 25114/61904 [2:36:34<14:38:21,  1.43s/it]
 41%|████      | 25115/61904 [2:36:35<14:03:21,  1.38s/it]
 41%|████      | 25116/61904 [2:36:36<13:51:41,  1.36s/it]
 41%|████      | 25117/61904 [2:36:38<13:58:36,  1.37s/it]
 41%|████      | 25118/61904 [2:36:39<13:53:55,  1.36s/it]
 41%|████      | 25119/61904 [2:36:41<13:58:19,  1.37s/it]
 41%|████      | 25120/61904 [2:36:42<14:24:30,  1.41s/it]
                                                          
{'loss': 2.5344, 'learning_rate': 1.5961363931025541e-07, 'epoch': 6.49}

 41%|████      | 25120/61904 [2:36:42<14:24:30,  1.41s/it]
 41%|████      | 25121/61904 [2:36:43<14:05:34,  1.38s/it]
 41%|████      | 25122/61904 [2:36:45<14:14:07,  1.39s/it]
 41%|████      | 25123/61904 [2:36:46<14:00:50,  1.37s/it]
 41%|████      | 25124/61904 [2:36:47<13:48:46,  1.35s/it]
 41%|████      | 25125/61904 [2:36:49<13:46:50,  1.35s/it]
 41%|████      | 25126/61904 [2:36:50<13:59:37,  1.37s/it]
 41%|████      | 25127/61904 [2:36:52<14:07:41,  1.38s/it]
 41%|████      | 25128/61904 [2:36:53<14:08:33,  1.38s/it]
 41%|████      | 25129/61904 [2:36:54<13:55:17,  1.36s/it]
 41%|████      | 25130/61904 [2:36:56<13:55:31,  1.36s/it]
 41%|████      | 25131/61904 [2:36:57<14:15:01,  1.40s/it]
 41%|████      | 25132/61904 [2:36:58<14:15:44,  1.40s/it]
 41%|████      | 25133/61904 [2:37:00<14:37:45,  1.43s/it]
 41%|████      | 25134/61904 [2:37:01<14:13:36,  1.39s/it]
 41%|████      | 25135/61904 [2:37:03<14:40:20,  1.44s/it]
 41%|████      | 25136/61904 [2:37:04<14:50:50,  1.45s/it]
 41%|████      | 25137/61904 [2:37:06<14:57:54,  1.47s/it]
 41%|████      | 25138/61904 [2:37:07<14:37:08,  1.43s/it]
 41%|████      | 25139/61904 [2:37:09<14:23:47,  1.41s/it]
 41%|████      | 25140/61904 [2:37:10<13:57:33,  1.37s/it]
                                                          
{'loss': 2.6249, 'learning_rate': 1.5958122650071308e-07, 'epoch': 6.5}

 41%|████      | 25140/61904 [2:37:10<13:57:33,  1.37s/it]
 41%|████      | 25141/61904 [2:37:11<14:05:27,  1.38s/it]
 41%|████      | 25142/61904 [2:37:13<13:47:16,  1.35s/it]
 41%|████      | 25143/61904 [2:37:14<13:37:35,  1.33s/it]
 41%|████      | 25144/61904 [2:37:15<13:44:05,  1.35s/it]
 41%|████      | 25145/61904 [2:37:16<13:36:21,  1.33s/it]
 41%|████      | 25146/61904 [2:37:18<13:52:47,  1.36s/it]
 41%|████      | 25147/61904 [2:37:19<13:24:23,  1.31s/it]
 41%|████      | 25148/61904 [2:37:21<13:44:24,  1.35s/it]
 41%|████      | 25149/61904 [2:37:22<13:33:41,  1.33s/it]
 41%|████      | 25150/61904 [2:37:23<13:39:35,  1.34s/it]
 41%|████      | 25151/61904 [2:37:25<14:15:55,  1.40s/it]
 41%|████      | 25152/61904 [2:37:26<14:28:29,  1.42s/it]
 41%|████      | 25153/61904 [2:37:28<14:35:17,  1.43s/it]
 41%|████      | 25154/61904 [2:37:29<14:53:49,  1.46s/it]
 41%|████      | 25155/61904 [2:37:31<14:54:23,  1.46s/it]
 41%|████      | 25156/61904 [2:37:32<14:42:27,  1.44s/it]
 41%|████      | 25157/61904 [2:37:33<14:43:12,  1.44s/it]
 41%|████      | 25158/61904 [2:37:35<14:27:13,  1.42s/it]
 41%|████      | 25159/61904 [2:37:36<14:25:35,  1.41s/it]
 41%|████      | 25160/61904 [2:37:38<14:29:36,  1.42s/it]
                                                          
{'loss': 2.5882, 'learning_rate': 1.5954881369117074e-07, 'epoch': 6.5}

 41%|████      | 25160/61904 [2:37:38<14:29:36,  1.42s/it]
 41%|████      | 25161/61904 [2:37:39<14:07:12,  1.38s/it]
 41%|████      | 25162/61904 [2:37:41<14:38:42,  1.43s/it]
 41%|████      | 25163/61904 [2:37:42<14:16:00,  1.40s/it]
 41%|████      | 25164/61904 [2:37:43<13:48:43,  1.35s/it]
 41%|████      | 25165/61904 [2:37:45<14:05:05,  1.38s/it]
 41%|████      | 25166/61904 [2:37:46<14:26:27,  1.42s/it]
 41%|████      | 25167/61904 [2:37:47<13:55:56,  1.37s/it]
 41%|████      | 25168/61904 [2:37:49<13:35:38,  1.33s/it]
 41%|████      | 25169/61904 [2:37:50<13:45:48,  1.35s/it]
 41%|████      | 25170/61904 [2:37:51<13:44:54,  1.35s/it]
 41%|████      | 25171/61904 [2:37:52<13:17:29,  1.30s/it]
 41%|████      | 25172/61904 [2:37:54<14:33:48,  1.43s/it]
 41%|████      | 25173/61904 [2:37:55<13:54:19,  1.36s/it]
 41%|████      | 25174/61904 [2:37:57<13:50:32,  1.36s/it]
 41%|████      | 25175/61904 [2:37:58<14:37:06,  1.43s/it]
 41%|████      | 25176/61904 [2:38:00<14:12:41,  1.39s/it]
 41%|████      | 25177/61904 [2:38:01<14:06:18,  1.38s/it]
 41%|████      | 25178/61904 [2:38:02<13:48:48,  1.35s/it]
 41%|████      | 25179/61904 [2:38:04<13:58:48,  1.37s/it]
 41%|████      | 25180/61904 [2:38:05<13:47:08,  1.35s/it]
                                                          
{'loss': 2.6219, 'learning_rate': 1.5951640088162843e-07, 'epoch': 6.51}

 41%|████      | 25180/61904 [2:38:05<13:47:08,  1.35s/it]
 41%|████      | 25181/61904 [2:38:07<15:01:15,  1.47s/it]
 41%|████      | 25182/61904 [2:38:08<14:40:37,  1.44s/it]
 41%|████      | 25183/61904 [2:38:09<14:11:47,  1.39s/it]
 41%|████      | 25184/61904 [2:38:11<14:16:30,  1.40s/it]
 41%|████      | 25185/61904 [2:38:12<14:11:53,  1.39s/it]
 41%|████      | 25186/61904 [2:38:13<13:56:37,  1.37s/it]
 41%|████      | 25187/61904 [2:38:15<14:15:10,  1.40s/it]
 41%|████      | 25188/61904 [2:38:16<13:59:15,  1.37s/it]
 41%|████      | 25189/61904 [2:38:18<13:33:40,  1.33s/it]
 41%|████      | 25190/61904 [2:38:19<13:39:03,  1.34s/it]
 41%|████      | 25191/61904 [2:38:20<14:02:01,  1.38s/it]
 41%|████      | 25192/61904 [2:38:22<14:07:49,  1.39s/it]
 41%|████      | 25193/61904 [2:38:23<14:19:25,  1.40s/it]
 41%|████      | 25194/61904 [2:38:24<14:01:04,  1.37s/it]
 41%|████      | 25195/61904 [2:38:26<14:06:27,  1.38s/it]
 41%|████      | 25196/61904 [2:38:27<13:53:13,  1.36s/it]
 41%|████      | 25197/61904 [2:38:29<14:01:10,  1.37s/it]
 41%|████      | 25198/61904 [2:38:30<13:44:54,  1.35s/it]
 41%|████      | 25199/61904 [2:38:31<14:05:26,  1.38s/it]
 41%|████      | 25200/61904 [2:38:33<13:57:39,  1.37s/it]
                                                          
{'loss': 2.5838, 'learning_rate': 1.5948398807208606e-07, 'epoch': 6.51}

 41%|████      | 25200/61904 [2:38:33<13:57:39,  1.37s/it]
 41%|████      | 25201/61904 [2:38:34<13:57:47,  1.37s/it]
 41%|████      | 25202/61904 [2:38:35<13:56:26,  1.37s/it]
 41%|████      | 25203/61904 [2:38:37<14:22:52,  1.41s/it]
 41%|████      | 25204/61904 [2:38:38<14:01:13,  1.38s/it]
 41%|████      | 25205/61904 [2:38:40<14:12:41,  1.39s/it]
 41%|████      | 25206/61904 [2:38:41<14:22:33,  1.41s/it]
 41%|████      | 25207/61904 [2:38:43<14:36:49,  1.43s/it]
 41%|████      | 25208/61904 [2:38:44<14:08:48,  1.39s/it]
 41%|████      | 25209/61904 [2:38:45<13:31:00,  1.33s/it]
 41%|████      | 25210/61904 [2:38:46<13:29:22,  1.32s/it]
 41%|████      | 25211/61904 [2:38:48<13:59:18,  1.37s/it]
 41%|████      | 25212/61904 [2:38:49<13:58:19,  1.37s/it]
 41%|████      | 25213/61904 [2:38:51<13:50:01,  1.36s/it]
 41%|████      | 25214/61904 [2:38:52<13:50:26,  1.36s/it]
 41%|████      | 25215/61904 [2:38:54<14:39:14,  1.44s/it]
 41%|████      | 25216/61904 [2:38:55<14:52:17,  1.46s/it]
 41%|████      | 25217/61904 [2:38:56<14:33:48,  1.43s/it]
 41%|████      | 25218/61904 [2:38:58<14:06:24,  1.38s/it]
 41%|████      | 25219/61904 [2:38:59<13:45:31,  1.35s/it]
 41%|████      | 25220/61904 [2:39:00<13:58:32,  1.37s/it]
                                                          
{'loss': 2.5943, 'learning_rate': 1.5945157526254375e-07, 'epoch': 6.52}

 41%|████      | 25220/61904 [2:39:00<13:58:32,  1.37s/it]
 41%|████      | 25221/61904 [2:39:02<14:00:44,  1.38s/it]
 41%|████      | 25222/61904 [2:39:03<14:08:23,  1.39s/it]
 41%|████      | 25223/61904 [2:39:04<13:53:50,  1.36s/it]
 41%|████      | 25224/61904 [2:39:06<14:11:47,  1.39s/it]
 41%|████      | 25225/61904 [2:39:07<14:09:24,  1.39s/it]
 41%|████      | 25226/61904 [2:39:09<14:02:15,  1.38s/it]
 41%|████      | 25227/61904 [2:39:10<14:00:48,  1.38s/it]
 41%|████      | 25228/61904 [2:39:12<14:18:37,  1.40s/it]
 41%|████      | 25229/61904 [2:39:13<14:20:22,  1.41s/it]
 41%|████      | 25230/61904 [2:39:15<14:47:37,  1.45s/it]
 41%|████      | 25231/61904 [2:39:16<14:20:25,  1.41s/it]
 41%|████      | 25232/61904 [2:39:17<14:52:20,  1.46s/it]
 41%|████      | 25233/61904 [2:39:19<14:50:40,  1.46s/it]
 41%|████      | 25234/61904 [2:39:20<14:14:10,  1.40s/it]
 41%|████      | 25235/61904 [2:39:21<14:03:53,  1.38s/it]
 41%|████      | 25236/61904 [2:39:23<14:09:59,  1.39s/it]
 41%|████      | 25237/61904 [2:39:24<13:55:17,  1.37s/it]
 41%|████      | 25238/61904 [2:39:25<13:48:44,  1.36s/it]
 41%|████      | 25239/61904 [2:39:27<13:46:36,  1.35s/it]
 41%|████      | 25240/61904 [2:39:28<13:30:33,  1.33s/it]
                                                          
{'loss': 2.6468, 'learning_rate': 1.5941916245300144e-07, 'epoch': 6.52}

 41%|████      | 25240/61904 [2:39:28<13:30:33,  1.33s/it]
 41%|████      | 25241/61904 [2:39:30<13:44:05,  1.35s/it]
 41%|████      | 25242/61904 [2:39:31<13:40:37,  1.34s/it]
 41%|████      | 25243/61904 [2:39:32<14:03:08,  1.38s/it]
 41%|████      | 25244/61904 [2:39:34<13:35:31,  1.33s/it]
 41%|████      | 25245/61904 [2:39:35<13:59:12,  1.37s/it]
 41%|████      | 25246/61904 [2:39:36<13:55:10,  1.37s/it]
 41%|████      | 25247/61904 [2:39:38<13:57:35,  1.37s/it]
 41%|████      | 25248/61904 [2:39:39<14:01:23,  1.38s/it]
 41%|████      | 25249/61904 [2:39:40<13:56:13,  1.37s/it]
 41%|████      | 25250/61904 [2:39:42<13:54:31,  1.37s/it]
 41%|████      | 25251/61904 [2:39:43<13:39:46,  1.34s/it]
 41%|████      | 25252/61904 [2:39:45<14:00:27,  1.38s/it]
 41%|████      | 25253/61904 [2:39:46<14:11:39,  1.39s/it]
 41%|████      | 25254/61904 [2:39:47<14:09:23,  1.39s/it]
 41%|████      | 25255/61904 [2:39:49<13:59:26,  1.37s/it]
 41%|████      | 25256/61904 [2:39:50<14:23:33,  1.41s/it]
 41%|████      | 25257/61904 [2:39:52<14:27:00,  1.42s/it]
 41%|████      | 25258/61904 [2:39:53<14:44:36,  1.45s/it]
 41%|████      | 25259/61904 [2:39:55<14:27:35,  1.42s/it]
 41%|████      | 25260/61904 [2:39:56<13:56:05,  1.37s/it]
                                                          
{'loss': 2.6726, 'learning_rate': 1.5938674964345907e-07, 'epoch': 6.53}

 41%|████      | 25260/61904 [2:39:56<13:56:05,  1.37s/it]
 41%|████      | 25261/61904 [2:39:57<14:04:15,  1.38s/it]
 41%|████      | 25262/61904 [2:39:59<13:56:13,  1.37s/it]
 41%|████      | 25263/61904 [2:40:00<13:58:13,  1.37s/it]
 41%|████      | 25264/61904 [2:40:01<14:02:21,  1.38s/it]
 41%|████      | 25265/61904 [2:40:03<14:35:01,  1.43s/it]
 41%|████      | 25266/61904 [2:40:04<14:26:02,  1.42s/it]
 41%|████      | 25267/61904 [2:40:06<14:06:37,  1.39s/it]
 41%|████      | 25268/61904 [2:40:07<14:19:37,  1.41s/it]
 41%|████      | 25269/61904 [2:40:08<14:03:35,  1.38s/it]
 41%|████      | 25270/61904 [2:40:10<14:22:07,  1.41s/it]
 41%|████      | 25271/61904 [2:40:11<14:02:37,  1.38s/it]
 41%|████      | 25272/61904 [2:40:12<13:59:36,  1.38s/it]
 41%|████      | 25273/61904 [2:40:14<13:26:07,  1.32s/it]
 41%|████      | 25274/61904 [2:40:15<13:42:49,  1.35s/it]
 41%|████      | 25275/61904 [2:40:16<13:44:34,  1.35s/it]
 41%|████      | 25276/61904 [2:40:18<13:23:24,  1.32s/it]
 41%|████      | 25277/61904 [2:40:19<13:26:33,  1.32s/it]
 41%|████      | 25278/61904 [2:40:20<13:18:17,  1.31s/it]
 41%|████      | 25279/61904 [2:40:22<13:47:16,  1.36s/it]
 41%|████      | 25280/61904 [2:40:23<13:41:46,  1.35s/it]
                                                          
{'loss': 2.5732, 'learning_rate': 1.5935433683391676e-07, 'epoch': 6.53}

 41%|████      | 25280/61904 [2:40:23<13:41:46,  1.35s/it]
 41%|████      | 25281/61904 [2:40:24<13:33:49,  1.33s/it]
 41%|████      | 25282/61904 [2:40:26<13:28:31,  1.32s/it]
 41%|████      | 25283/61904 [2:40:27<13:23:57,  1.32s/it]
 41%|████      | 25284/61904 [2:40:28<13:23:24,  1.32s/it]
 41%|████      | 25285/61904 [2:40:30<13:29:07,  1.33s/it]
 41%|████      | 25286/61904 [2:40:31<13:51:15,  1.36s/it]
 41%|████      | 25287/61904 [2:40:33<14:09:17,  1.39s/it]
 41%|████      | 25288/61904 [2:40:34<13:46:42,  1.35s/it]
 41%|████      | 25289/61904 [2:40:35<14:09:55,  1.39s/it]
 41%|████      | 25290/61904 [2:40:37<14:03:33,  1.38s/it]
 41%|████      | 25291/61904 [2:40:38<14:18:44,  1.41s/it]
 41%|████      | 25292/61904 [2:40:40<14:10:47,  1.39s/it]
 41%|████      | 25293/61904 [2:40:41<14:39:14,  1.44s/it]
 41%|████      | 25294/61904 [2:40:42<14:18:12,  1.41s/it]
 41%|████      | 25295/61904 [2:40:44<14:16:47,  1.40s/it]
 41%|████      | 25296/61904 [2:40:45<13:47:23,  1.36s/it]
 41%|████      | 25297/61904 [2:40:46<14:01:43,  1.38s/it]
 41%|████      | 25298/61904 [2:40:48<13:58:33,  1.37s/it]
 41%|████      | 25299/61904 [2:40:49<13:40:30,  1.34s/it]
 41%|████      | 25300/61904 [2:40:50<13:23:43,  1.32s/it]
                                                          
{'loss': 2.5739, 'learning_rate': 1.5932192402437442e-07, 'epoch': 6.54}

 41%|████      | 25300/61904 [2:40:50<13:23:43,  1.32s/it]
 41%|████      | 25301/61904 [2:40:52<13:25:11,  1.32s/it]
 41%|████      | 25302/61904 [2:40:53<13:38:04,  1.34s/it]
 41%|████      | 25303/61904 [2:40:55<13:55:23,  1.37s/it]
 41%|████      | 25304/61904 [2:40:56<13:58:20,  1.37s/it]
 41%|████      | 25305/61904 [2:40:57<13:49:32,  1.36s/it]
 41%|████      | 25306/61904 [2:40:59<14:33:30,  1.43s/it]
 41%|████      | 25307/61904 [2:41:00<14:16:49,  1.40s/it]
 41%|████      | 25308/61904 [2:41:01<13:59:33,  1.38s/it]
 41%|████      | 25309/61904 [2:41:03<13:52:11,  1.36s/it]
 41%|████      | 25310/61904 [2:41:04<13:52:04,  1.36s/it]
 41%|████      | 25311/61904 [2:41:05<13:42:50,  1.35s/it]
 41%|████      | 25312/61904 [2:41:07<13:30:56,  1.33s/it]
 41%|████      | 25313/61904 [2:41:08<13:56:40,  1.37s/it]
 41%|████      | 25314/61904 [2:41:10<14:04:23,  1.38s/it]
 41%|████      | 25315/61904 [2:41:11<13:39:57,  1.34s/it]
 41%|████      | 25316/61904 [2:41:12<14:10:52,  1.40s/it]
 41%|████      | 25317/61904 [2:41:14<13:50:33,  1.36s/it]
 41%|████      | 25318/61904 [2:41:15<15:00:37,  1.48s/it]
 41%|████      | 25319/61904 [2:41:17<14:33:59,  1.43s/it]
 41%|████      | 25320/61904 [2:41:18<14:03:11,  1.38s/it]
                                                          
{'loss': 2.5914, 'learning_rate': 1.5928951121483208e-07, 'epoch': 6.54}

 41%|████      | 25320/61904 [2:41:18<14:03:11,  1.38s/it]
 41%|████      | 25321/61904 [2:41:19<13:54:16,  1.37s/it]
 41%|████      | 25322/61904 [2:41:21<13:39:26,  1.34s/it]
 41%|████      | 25323/61904 [2:41:22<13:26:14,  1.32s/it]
 41%|████      | 25324/61904 [2:41:23<13:42:24,  1.35s/it]
 41%|████      | 25325/61904 [2:41:25<13:11:49,  1.30s/it]
 41%|████      | 25326/61904 [2:41:26<13:05:14,  1.29s/it]
 41%|████      | 25327/61904 [2:41:27<13:20:51,  1.31s/it]
 41%|████      | 25328/61904 [2:41:29<13:52:05,  1.36s/it]
 41%|████      | 25329/61904 [2:41:30<14:11:07,  1.40s/it]
 41%|████      | 25330/61904 [2:41:31<14:05:28,  1.39s/it]
 41%|████      | 25331/61904 [2:41:33<13:57:01,  1.37s/it]
 41%|████      | 25332/61904 [2:41:34<13:55:00,  1.37s/it]
 41%|████      | 25333/61904 [2:41:35<13:31:53,  1.33s/it]
 41%|████      | 25334/61904 [2:41:37<13:28:03,  1.33s/it]
 41%|████      | 25335/61904 [2:41:38<13:46:58,  1.36s/it]
 41%|████      | 25336/61904 [2:41:39<13:38:24,  1.34s/it]
 41%|████      | 25337/61904 [2:41:41<13:51:04,  1.36s/it]
 41%|████      | 25338/61904 [2:41:42<13:56:08,  1.37s/it]
 41%|████      | 25339/61904 [2:41:44<13:53:39,  1.37s/it]
 41%|████      | 25340/61904 [2:41:45<14:36:45,  1.44s/it]
                                                          
{'loss': 2.6142, 'learning_rate': 1.5925709840528977e-07, 'epoch': 6.55}

 41%|████      | 25340/61904 [2:41:45<14:36:45,  1.44s/it]
 41%|████      | 25341/61904 [2:41:47<14:25:40,  1.42s/it]
 41%|████      | 25342/61904 [2:41:48<14:39:32,  1.44s/it]
 41%|████      | 25343/61904 [2:41:50<15:20:12,  1.51s/it]
 41%|████      | 25344/61904 [2:41:51<14:41:41,  1.45s/it]
 41%|████      | 25345/61904 [2:41:52<14:22:22,  1.42s/it]
 41%|████      | 25346/61904 [2:41:54<14:11:36,  1.40s/it]
 41%|████      | 25347/61904 [2:41:55<13:54:48,  1.37s/it]
 41%|████      | 25348/61904 [2:41:56<13:37:09,  1.34s/it]
 41%|████      | 25349/61904 [2:41:58<13:21:11,  1.32s/it]
 41%|████      | 25350/61904 [2:41:59<13:47:13,  1.36s/it]
 41%|████      | 25351/61904 [2:42:00<13:53:39,  1.37s/it]
 41%|████      | 25352/61904 [2:42:02<13:58:06,  1.38s/it]
 41%|████      | 25353/61904 [2:42:03<14:06:03,  1.39s/it]
 41%|████      | 25354/61904 [2:42:05<14:13:34,  1.40s/it]
 41%|████      | 25355/61904 [2:42:06<14:30:14,  1.43s/it]
 41%|████      | 25356/61904 [2:42:08<14:11:17,  1.40s/it]
 41%|████      | 25357/61904 [2:42:09<13:49:21,  1.36s/it]
 41%|████      | 25358/61904 [2:42:10<13:35:20,  1.34s/it]
 41%|████      | 25359/61904 [2:42:12<13:48:26,  1.36s/it]
 41%|████      | 25360/61904 [2:42:13<14:09:49,  1.40s/it]
                                                          
{'loss': 2.6145, 'learning_rate': 1.5922468559574744e-07, 'epoch': 6.55}

 41%|████      | 25360/61904 [2:42:13<14:09:49,  1.40s/it]
 41%|████      | 25361/61904 [2:42:14<13:57:48,  1.38s/it]
 41%|████      | 25362/61904 [2:42:16<14:14:06,  1.40s/it]
 41%|████      | 25363/61904 [2:42:17<14:24:52,  1.42s/it]
 41%|████      | 25364/61904 [2:42:18<13:49:24,  1.36s/it]
 41%|████      | 25365/61904 [2:42:20<13:26:06,  1.32s/it]
 41%|████      | 25366/61904 [2:42:21<13:28:13,  1.33s/it]
 41%|████      | 25367/61904 [2:42:22<13:16:32,  1.31s/it]
 41%|████      | 25368/61904 [2:42:24<13:28:08,  1.33s/it]
 41%|████      | 25369/61904 [2:42:25<13:31:40,  1.33s/it]
 41%|████      | 25370/61904 [2:42:26<13:15:45,  1.31s/it]
 41%|████      | 25371/61904 [2:42:28<13:25:14,  1.32s/it]
 41%|████      | 25372/61904 [2:42:29<14:02:09,  1.38s/it]
 41%|████      | 25373/61904 [2:42:31<14:15:27,  1.41s/it]
 41%|████      | 25374/61904 [2:42:32<14:31:12,  1.43s/it]
 41%|████      | 25375/61904 [2:42:33<14:14:30,  1.40s/it]
 41%|████      | 25376/61904 [2:42:35<13:59:00,  1.38s/it]
 41%|████      | 25377/61904 [2:42:36<14:24:19,  1.42s/it]
 41%|████      | 25378/61904 [2:42:38<13:57:37,  1.38s/it]
 41%|████      | 25379/61904 [2:42:39<13:31:49,  1.33s/it]
 41%|████      | 25380/61904 [2:42:40<13:24:49,  1.32s/it]
                                                          
{'loss': 2.6449, 'learning_rate': 1.591922727862051e-07, 'epoch': 6.56}

 41%|████      | 25380/61904 [2:42:40<13:24:49,  1.32s/it]
 41%|████      | 25381/61904 [2:42:42<13:46:22,  1.36s/it]
 41%|████      | 25382/61904 [2:42:43<13:46:26,  1.36s/it]
 41%|████      | 25383/61904 [2:42:44<13:44:53,  1.36s/it]
 41%|████      | 25384/61904 [2:42:46<13:51:12,  1.37s/it]
 41%|████      | 25385/61904 [2:42:47<13:56:27,  1.37s/it]
 41%|████      | 25386/61904 [2:42:48<14:14:15,  1.40s/it]
 41%|████      | 25387/61904 [2:42:50<13:52:23,  1.37s/it]
 41%|████      | 25388/61904 [2:42:51<13:50:54,  1.37s/it]
 41%|████      | 25389/61904 [2:42:52<13:47:17,  1.36s/it]
 41%|████      | 25390/61904 [2:42:54<13:21:00,  1.32s/it]
 41%|████      | 25391/61904 [2:42:55<13:23:33,  1.32s/it]
 41%|████      | 25392/61904 [2:42:56<13:30:42,  1.33s/it]
 41%|████      | 25393/61904 [2:42:58<13:25:38,  1.32s/it]
 41%|████      | 25394/61904 [2:42:59<13:51:37,  1.37s/it]
 41%|████      | 25395/61904 [2:43:00<13:41:09,  1.35s/it]
 41%|████      | 25396/61904 [2:43:02<13:35:51,  1.34s/it]
 41%|████      | 25397/61904 [2:43:03<13:26:56,  1.33s/it]
 41%|████      | 25398/61904 [2:43:04<13:31:30,  1.33s/it]
 41%|████      | 25399/61904 [2:43:06<13:26:32,  1.33s/it]
 41%|████      | 25400/61904 [2:43:07<13:23:39,  1.32s/it]
                                                          
{'loss': 2.586, 'learning_rate': 1.5915985997666279e-07, 'epoch': 6.56}

 41%|████      | 25400/61904 [2:43:07<13:23:39,  1.32s/it]
 41%|████      | 25401/61904 [2:43:08<13:40:20,  1.35s/it]
 41%|████      | 25402/61904 [2:43:10<13:42:47,  1.35s/it]
 41%|████      | 25403/61904 [2:43:11<13:42:54,  1.35s/it]
 41%|████      | 25404/61904 [2:43:13<13:56:02,  1.37s/it]
 41%|████      | 25405/61904 [2:43:14<14:01:44,  1.38s/it]
 41%|████      | 25406/61904 [2:43:15<13:55:58,  1.37s/it]
 41%|████      | 25407/61904 [2:43:17<13:48:25,  1.36s/it]
 41%|████      | 25408/61904 [2:43:18<14:12:36,  1.40s/it]
 41%|████      | 25409/61904 [2:43:20<14:03:04,  1.39s/it]
 41%|████      | 25410/61904 [2:43:21<13:54:57,  1.37s/it]
 41%|████      | 25411/61904 [2:43:22<14:01:17,  1.38s/it]
 41%|████      | 25412/61904 [2:43:24<13:57:33,  1.38s/it]
 41%|████      | 25413/61904 [2:43:25<13:37:38,  1.34s/it]
 41%|████      | 25414/61904 [2:43:26<13:42:16,  1.35s/it]
 41%|████      | 25415/61904 [2:43:28<13:51:37,  1.37s/it]
 41%|████      | 25416/61904 [2:43:29<13:44:56,  1.36s/it]
 41%|████      | 25417/61904 [2:43:30<13:31:26,  1.33s/it]
 41%|████      | 25418/61904 [2:43:31<12:57:33,  1.28s/it]
 41%|████      | 25419/61904 [2:43:33<13:22:28,  1.32s/it]
 41%|████      | 25420/61904 [2:43:34<13:06:53,  1.29s/it]
                                                          
{'loss': 2.6136, 'learning_rate': 1.5912744716712042e-07, 'epoch': 6.57}

 41%|████      | 25420/61904 [2:43:34<13:06:53,  1.29s/it]
 41%|████      | 25421/61904 [2:43:36<13:53:18,  1.37s/it]
 41%|████      | 25422/61904 [2:43:37<13:53:22,  1.37s/it]
 41%|████      | 25423/61904 [2:43:38<13:49:32,  1.36s/it]
 41%|████      | 25424/61904 [2:43:40<13:53:55,  1.37s/it]
 41%|████      | 25425/61904 [2:43:41<14:08:43,  1.40s/it]
 41%|████      | 25426/61904 [2:43:43<13:52:48,  1.37s/it]
 41%|████      | 25427/61904 [2:43:44<14:20:05,  1.41s/it]
 41%|████      | 25428/61904 [2:43:45<14:11:30,  1.40s/it]
 41%|████      | 25429/61904 [2:43:47<13:42:15,  1.35s/it]
 41%|████      | 25430/61904 [2:43:48<13:49:39,  1.36s/it]
 41%|████      | 25431/61904 [2:43:49<13:53:18,  1.37s/it]
 41%|████      | 25432/61904 [2:43:51<13:57:57,  1.38s/it]
 41%|████      | 25433/61904 [2:43:52<13:45:23,  1.36s/it]
 41%|████      | 25434/61904 [2:43:53<13:40:16,  1.35s/it]
 41%|████      | 25435/61904 [2:43:55<13:35:57,  1.34s/it]
 41%|████      | 25436/61904 [2:43:56<13:17:37,  1.31s/it]
 41%|████      | 25437/61904 [2:43:57<13:14:23,  1.31s/it]
 41%|████      | 25438/61904 [2:43:59<13:40:40,  1.35s/it]
 41%|████      | 25439/61904 [2:44:00<14:03:01,  1.39s/it]
 41%|████      | 25440/61904 [2:44:02<13:59:16,  1.38s/it]
                                                          
{'loss': 2.6556, 'learning_rate': 1.590950343575781e-07, 'epoch': 6.58}

 41%|████      | 25440/61904 [2:44:02<13:59:16,  1.38s/it]
 41%|████      | 25441/61904 [2:44:03<14:07:59,  1.40s/it]
 41%|████      | 25442/61904 [2:44:04<13:59:32,  1.38s/it]
 41%|████      | 25443/61904 [2:44:06<13:45:29,  1.36s/it]
 41%|████      | 25444/61904 [2:44:07<13:53:21,  1.37s/it]
 41%|████      | 25445/61904 [2:44:09<14:27:19,  1.43s/it]
 41%|████      | 25446/61904 [2:44:10<14:02:56,  1.39s/it]
 41%|████      | 25447/61904 [2:44:11<13:55:09,  1.37s/it]
 41%|████      | 25448/61904 [2:44:13<13:35:33,  1.34s/it]
 41%|████      | 25449/61904 [2:44:14<13:51:24,  1.37s/it]
 41%|████      | 25450/61904 [2:44:15<13:25:01,  1.33s/it]
 41%|████      | 25451/61904 [2:44:17<13:32:36,  1.34s/it]
 41%|████      | 25452/61904 [2:44:18<13:39:04,  1.35s/it]
 41%|████      | 25453/61904 [2:44:19<14:05:24,  1.39s/it]
 41%|████      | 25454/61904 [2:44:21<14:03:02,  1.39s/it]
 41%|████      | 25455/61904 [2:44:22<13:52:23,  1.37s/it]
 41%|████      | 25456/61904 [2:44:24<14:05:36,  1.39s/it]
 41%|████      | 25457/61904 [2:44:25<14:09:04,  1.40s/it]
 41%|████      | 25458/61904 [2:44:26<13:58:47,  1.38s/it]
 41%|████      | 25459/61904 [2:44:28<14:16:39,  1.41s/it]
 41%|████      | 25460/61904 [2:44:29<14:01:33,  1.39s/it]
                                                          
{'loss': 2.6557, 'learning_rate': 1.5906262154803577e-07, 'epoch': 6.58}

 41%|████      | 25460/61904 [2:44:29<14:01:33,  1.39s/it]
 41%|████      | 25461/61904 [2:44:31<13:56:26,  1.38s/it]
 41%|████      | 25462/61904 [2:44:32<14:07:28,  1.40s/it]
 41%|████      | 25463/61904 [2:44:33<13:26:41,  1.33s/it]
 41%|████      | 25464/61904 [2:44:35<13:41:27,  1.35s/it]
 41%|████      | 25465/61904 [2:44:36<13:44:57,  1.36s/it]
 41%|████      | 25466/61904 [2:44:37<13:23:40,  1.32s/it]
 41%|████      | 25467/61904 [2:44:39<13:45:57,  1.36s/it]
 41%|████      | 25468/61904 [2:44:40<13:57:23,  1.38s/it]
 41%|████      | 25469/61904 [2:44:41<13:42:53,  1.36s/it]
 41%|████      | 25470/61904 [2:44:43<14:03:57,  1.39s/it]
 41%|████      | 25471/61904 [2:44:44<13:43:39,  1.36s/it]
 41%|████      | 25472/61904 [2:44:45<13:56:50,  1.38s/it]
 41%|████      | 25473/61904 [2:44:47<13:56:36,  1.38s/it]
 41%|████      | 25474/61904 [2:44:48<13:36:06,  1.34s/it]
 41%|████      | 25475/61904 [2:44:49<13:14:24,  1.31s/it]
 41%|████      | 25476/61904 [2:44:51<13:27:12,  1.33s/it]
 41%|████      | 25477/61904 [2:44:52<13:44:54,  1.36s/it]
 41%|████      | 25478/61904 [2:44:54<13:50:18,  1.37s/it]
 41%|████      | 25479/61904 [2:44:55<13:45:26,  1.36s/it]
 41%|████      | 25480/61904 [2:44:56<14:03:17,  1.39s/it]
                                                          
{'loss': 2.5518, 'learning_rate': 1.5903020873849343e-07, 'epoch': 6.59}

 41%|████      | 25480/61904 [2:44:56<14:03:17,  1.39s/it]
 41%|████      | 25481/61904 [2:44:58<13:39:57,  1.35s/it]
 41%|████      | 25482/61904 [2:44:59<13:27:43,  1.33s/it]
 41%|████      | 25483/61904 [2:45:00<13:29:40,  1.33s/it]
 41%|████      | 25484/61904 [2:45:02<13:19:38,  1.32s/it]
 41%|████      | 25485/61904 [2:45:03<13:20:46,  1.32s/it]
 41%|████      | 25486/61904 [2:45:04<14:00:25,  1.38s/it]
 41%|████      | 25487/61904 [2:45:06<14:01:11,  1.39s/it]
 41%|████      | 25488/61904 [2:45:07<13:47:24,  1.36s/it]
 41%|████      | 25489/61904 [2:45:08<13:43:01,  1.36s/it]
 41%|████      | 25490/61904 [2:45:10<13:20:39,  1.32s/it]
 41%|████      | 25491/61904 [2:45:11<13:52:54,  1.37s/it]
 41%|████      | 25492/61904 [2:45:13<14:04:25,  1.39s/it]
 41%|████      | 25493/61904 [2:45:14<13:27:15,  1.33s/it]
 41%|████      | 25494/61904 [2:45:15<13:39:42,  1.35s/it]
 41%|████      | 25495/61904 [2:45:16<13:36:06,  1.34s/it]
 41%|████      | 25496/61904 [2:45:18<13:39:55,  1.35s/it]
 41%|████      | 25497/61904 [2:45:19<13:54:55,  1.38s/it]
 41%|████      | 25498/61904 [2:45:21<14:26:02,  1.43s/it]
 41%|████      | 25499/61904 [2:45:22<14:09:21,  1.40s/it]
 41%|████      | 25500/61904 [2:45:24<14:15:21,  1.41s/it]
                                                          
{'loss': 2.6054, 'learning_rate': 1.5899779592895112e-07, 'epoch': 6.59}

 41%|████      | 25500/61904 [2:45:24<14:15:21,  1.41s/it]
 41%|████      | 25501/61904 [2:45:25<13:45:43,  1.36s/it]
 41%|████      | 25502/61904 [2:45:26<13:53:28,  1.37s/it]
 41%|████      | 25503/61904 [2:45:28<14:38:15,  1.45s/it]
 41%|████      | 25504/61904 [2:45:29<14:06:29,  1.40s/it]
 41%|████      | 25505/61904 [2:45:31<14:12:33,  1.41s/it]
 41%|████      | 25506/61904 [2:45:32<14:02:25,  1.39s/it]
 41%|████      | 25507/61904 [2:45:33<13:29:31,  1.33s/it]
 41%|████      | 25508/61904 [2:45:34<13:32:27,  1.34s/it]
 41%|████      | 25509/61904 [2:45:36<13:46:19,  1.36s/it]
 41%|████      | 25510/61904 [2:45:37<13:49:35,  1.37s/it]
 41%|████      | 25511/61904 [2:45:39<14:09:23,  1.40s/it]
 41%|████      | 25512/61904 [2:45:40<13:47:44,  1.36s/it]
 41%|████      | 25513/61904 [2:45:41<13:46:36,  1.36s/it]
 41%|████      | 25514/61904 [2:45:43<14:00:33,  1.39s/it]
 41%|████      | 25515/61904 [2:45:44<14:04:03,  1.39s/it]
 41%|████      | 25516/61904 [2:45:46<14:38:36,  1.45s/it]
 41%|████      | 25517/61904 [2:45:47<14:24:10,  1.42s/it]
 41%|████      | 25518/61904 [2:45:49<14:15:00,  1.41s/it]
 41%|████      | 25519/61904 [2:45:50<13:50:15,  1.37s/it]
 41%|████      | 25520/61904 [2:45:51<13:57:47,  1.38s/it]
                                                          
{'loss': 2.5766, 'learning_rate': 1.5896538311940878e-07, 'epoch': 6.6}

 41%|████      | 25520/61904 [2:45:51<13:57:47,  1.38s/it]
 41%|████      | 25521/61904 [2:45:53<13:48:35,  1.37s/it]
 41%|████      | 25522/61904 [2:45:54<13:42:30,  1.36s/it]
 41%|████      | 25523/61904 [2:45:55<14:11:49,  1.40s/it]
 41%|████      | 25524/61904 [2:45:57<14:20:17,  1.42s/it]
 41%|████      | 25525/61904 [2:45:59<15:08:31,  1.50s/it]
 41%|████      | 25526/61904 [2:46:00<14:57:33,  1.48s/it]
 41%|████      | 25527/61904 [2:46:01<14:12:24,  1.41s/it]
 41%|████      | 25528/61904 [2:46:03<14:13:38,  1.41s/it]
 41%|████      | 25529/61904 [2:46:04<14:05:11,  1.39s/it]
 41%|████      | 25530/61904 [2:46:05<13:48:28,  1.37s/it]
 41%|████      | 25531/61904 [2:46:07<13:58:45,  1.38s/it]
 41%|████      | 25532/61904 [2:46:08<14:39:28,  1.45s/it]
 41%|████      | 25533/61904 [2:46:10<14:33:35,  1.44s/it]
 41%|████      | 25534/61904 [2:46:11<15:03:47,  1.49s/it]
 41%|████      | 25535/61904 [2:46:13<14:43:45,  1.46s/it]
 41%|████▏     | 25536/61904 [2:46:14<14:27:10,  1.43s/it]
 41%|████▏     | 25537/61904 [2:46:15<14:15:22,  1.41s/it]
 41%|████▏     | 25538/61904 [2:46:17<13:57:56,  1.38s/it]
 41%|████▏     | 25539/61904 [2:46:18<13:48:00,  1.37s/it]
 41%|████▏     | 25540/61904 [2:46:19<13:43:32,  1.36s/it]
                                                          
{'loss': 2.5573, 'learning_rate': 1.5893297030986644e-07, 'epoch': 6.6}

 41%|████▏     | 25540/61904 [2:46:19<13:43:32,  1.36s/it]
 41%|████▏     | 25541/61904 [2:46:21<14:02:15,  1.39s/it]
 41%|████▏     | 25542/61904 [2:46:22<14:01:56,  1.39s/it]
 41%|████▏     | 25543/61904 [2:46:24<14:00:31,  1.39s/it]
 41%|████▏     | 25544/61904 [2:46:25<13:39:51,  1.35s/it]
 41%|████▏     | 25545/61904 [2:46:26<13:37:57,  1.35s/it]
 41%|████▏     | 25546/61904 [2:46:28<13:55:29,  1.38s/it]
 41%|████▏     | 25547/61904 [2:46:29<14:19:52,  1.42s/it]
 41%|████▏     | 25548/61904 [2:46:31<14:23:20,  1.42s/it]
 41%|████▏     | 25549/61904 [2:46:32<14:04:22,  1.39s/it]
 41%|████▏     | 25550/61904 [2:46:33<13:36:03,  1.35s/it]
 41%|████▏     | 25551/61904 [2:46:34<12:58:25,  1.28s/it]
 41%|████▏     | 25552/61904 [2:46:36<13:20:07,  1.32s/it]
 41%|████▏     | 25553/61904 [2:46:37<13:12:52,  1.31s/it]
 41%|████▏     | 25554/61904 [2:46:39<14:40:02,  1.45s/it]
 41%|████▏     | 25555/61904 [2:46:40<14:32:48,  1.44s/it]
 41%|████▏     | 25556/61904 [2:46:42<14:06:10,  1.40s/it]
 41%|████▏     | 25557/61904 [2:46:43<14:39:20,  1.45s/it]
 41%|████▏     | 25558/61904 [2:46:45<14:22:48,  1.42s/it]
 41%|████▏     | 25559/61904 [2:46:46<14:07:58,  1.40s/it]
 41%|████▏     | 25560/61904 [2:46:47<14:09:50,  1.40s/it]
                                                          
{'loss': 2.6429, 'learning_rate': 1.5890055750032413e-07, 'epoch': 6.61}

 41%|████▏     | 25560/61904 [2:46:47<14:09:50,  1.40s/it]
 41%|████▏     | 25561/61904 [2:46:48<13:31:05,  1.34s/it]
 41%|████▏     | 25562/61904 [2:46:50<13:13:32,  1.31s/it]
 41%|████▏     | 25563/61904 [2:46:51<13:11:30,  1.31s/it]
 41%|████▏     | 25564/61904 [2:46:52<13:02:10,  1.29s/it]
 41%|████▏     | 25565/61904 [2:46:54<13:07:22,  1.30s/it]
 41%|████▏     | 25566/61904 [2:46:55<13:28:22,  1.33s/it]
 41%|████▏     | 25567/61904 [2:46:56<13:26:27,  1.33s/it]
 41%|████▏     | 25568/61904 [2:46:58<13:50:39,  1.37s/it]
 41%|████▏     | 25569/61904 [2:46:59<13:48:03,  1.37s/it]
 41%|████▏     | 25570/61904 [2:47:01<13:59:39,  1.39s/it]
 41%|████▏     | 25571/61904 [2:47:02<13:57:41,  1.38s/it]
 41%|████▏     | 25572/61904 [2:47:03<13:42:46,  1.36s/it]
 41%|████▏     | 25573/61904 [2:47:05<13:24:20,  1.33s/it]
 41%|████▏     | 25574/61904 [2:47:06<13:28:28,  1.34s/it]
 41%|████▏     | 25575/61904 [2:47:07<13:28:53,  1.34s/it]
 41%|████▏     | 25576/61904 [2:47:09<13:26:35,  1.33s/it]
 41%|████▏     | 25577/61904 [2:47:10<13:47:02,  1.37s/it]
 41%|████▏     | 25578/61904 [2:47:11<14:05:36,  1.40s/it]
 41%|████▏     | 25579/61904 [2:47:13<14:12:17,  1.41s/it]
 41%|████▏     | 25580/61904 [2:47:14<13:48:53,  1.37s/it]
                                                          
{'loss': 2.6795, 'learning_rate': 1.588681446907818e-07, 'epoch': 6.61}

 41%|████▏     | 25580/61904 [2:47:14<13:48:53,  1.37s/it]
 41%|████▏     | 25581/61904 [2:47:16<13:49:48,  1.37s/it]
 41%|████▏     | 25582/61904 [2:47:17<13:43:37,  1.36s/it]
 41%|████▏     | 25583/61904 [2:47:18<13:54:12,  1.38s/it]
 41%|████▏     | 25584/61904 [2:47:20<13:34:29,  1.35s/it]
 41%|████▏     | 25585/61904 [2:47:21<13:31:23,  1.34s/it]
 41%|████▏     | 25586/61904 [2:47:22<13:23:29,  1.33s/it]
 41%|████▏     | 25587/61904 [2:47:23<13:10:05,  1.31s/it]
 41%|████▏     | 25588/61904 [2:47:25<13:35:36,  1.35s/it]
 41%|████▏     | 25589/61904 [2:47:26<13:41:20,  1.36s/it]
 41%|████▏     | 25590/61904 [2:47:28<13:35:46,  1.35s/it]
 41%|████▏     | 25591/61904 [2:47:29<13:37:09,  1.35s/it]
 41%|████▏     | 25592/61904 [2:47:30<13:47:04,  1.37s/it]
 41%|████▏     | 25593/61904 [2:47:32<13:37:31,  1.35s/it]
 41%|████▏     | 25594/61904 [2:47:33<13:22:02,  1.33s/it]
 41%|████▏     | 25595/61904 [2:47:34<13:38:53,  1.35s/it]
 41%|████▏     | 25596/61904 [2:47:36<13:37:52,  1.35s/it]
 41%|████▏     | 25597/61904 [2:47:37<13:40:10,  1.36s/it]
 41%|████▏     | 25598/61904 [2:47:38<13:36:47,  1.35s/it]
 41%|████▏     | 25599/61904 [2:47:40<13:55:30,  1.38s/it]
 41%|████▏     | 25600/61904 [2:47:41<13:46:41,  1.37s/it]
                                                          
{'loss': 2.6573, 'learning_rate': 1.5883573188123946e-07, 'epoch': 6.62}

 41%|████▏     | 25600/61904 [2:47:41<13:46:41,  1.37s/it]
 41%|████▏     | 25601/61904 [2:47:43<13:58:04,  1.39s/it]
 41%|████▏     | 25602/61904 [2:47:44<13:52:34,  1.38s/it]
 41%|████▏     | 25603/61904 [2:47:45<13:31:57,  1.34s/it]
 41%|████▏     | 25604/61904 [2:47:47<13:47:38,  1.37s/it]
 41%|████▏     | 25605/61904 [2:47:48<13:36:04,  1.35s/it]
 41%|████▏     | 25606/61904 [2:47:49<13:27:05,  1.33s/it]
 41%|████▏     | 25607/61904 [2:47:51<13:20:38,  1.32s/it]
 41%|████▏     | 25608/61904 [2:47:52<13:07:16,  1.30s/it]
 41%|████▏     | 25609/61904 [2:47:53<13:00:12,  1.29s/it]
 41%|████▏     | 25610/61904 [2:47:55<13:29:11,  1.34s/it]
 41%|████▏     | 25611/61904 [2:47:56<13:25:21,  1.33s/it]
 41%|████▏     | 25612/61904 [2:47:57<13:33:22,  1.34s/it]
 41%|████▏     | 25613/61904 [2:47:59<13:22:30,  1.33s/it]
 41%|████▏     | 25614/61904 [2:48:00<13:19:15,  1.32s/it]
 41%|████▏     | 25615/61904 [2:48:01<13:41:57,  1.36s/it]
 41%|████▏     | 25616/61904 [2:48:03<13:33:54,  1.35s/it]
 41%|████▏     | 25617/61904 [2:48:04<13:34:06,  1.35s/it]
 41%|████▏     | 25618/61904 [2:48:05<13:27:41,  1.34s/it]
 41%|████▏     | 25619/61904 [2:48:07<13:29:49,  1.34s/it]
 41%|████▏     | 25620/61904 [2:48:08<13:52:11,  1.38s/it]
                                                          
{'loss': 2.5762, 'learning_rate': 1.5880331907169712e-07, 'epoch': 6.62}

 41%|████▏     | 25620/61904 [2:48:08<13:52:11,  1.38s/it]
 41%|████▏     | 25621/61904 [2:48:09<13:43:34,  1.36s/it]
 41%|████▏     | 25622/61904 [2:48:11<13:45:46,  1.37s/it]
 41%|████▏     | 25623/61904 [2:48:12<13:56:09,  1.38s/it]
 41%|████▏     | 25624/61904 [2:48:14<13:57:08,  1.38s/it]
 41%|████▏     | 25625/61904 [2:48:15<13:27:05,  1.33s/it]
 41%|████▏     | 25626/61904 [2:48:16<13:45:55,  1.37s/it]
 41%|████▏     | 25627/61904 [2:48:18<13:41:06,  1.36s/it]
 41%|████▏     | 25628/61904 [2:48:19<13:41:50,  1.36s/it]
 41%|████▏     | 25629/61904 [2:48:20<14:09:21,  1.40s/it]
 41%|████▏     | 25630/61904 [2:48:22<14:10:34,  1.41s/it]
 41%|████▏     | 25631/61904 [2:48:23<13:48:46,  1.37s/it]
 41%|████▏     | 25632/61904 [2:48:24<13:31:20,  1.34s/it]
 41%|████▏     | 25633/61904 [2:48:26<13:35:23,  1.35s/it]
 41%|████▏     | 25634/61904 [2:48:27<13:28:24,  1.34s/it]
 41%|████▏     | 25635/61904 [2:48:29<13:53:21,  1.38s/it]
 41%|████▏     | 25636/61904 [2:48:30<13:54:09,  1.38s/it]
 41%|████▏     | 25637/61904 [2:48:31<13:58:52,  1.39s/it]
 41%|████▏     | 25638/61904 [2:48:33<13:32:41,  1.34s/it]
 41%|████▏     | 25639/61904 [2:48:34<13:17:13,  1.32s/it]
 41%|████▏     | 25640/61904 [2:48:35<13:20:51,  1.33s/it]
                                                          
{'loss': 2.6336, 'learning_rate': 1.5877090626215478e-07, 'epoch': 6.63}

 41%|████▏     | 25640/61904 [2:48:35<13:20:51,  1.33s/it]
 41%|████▏     | 25641/61904 [2:48:37<13:19:05,  1.32s/it]
 41%|████▏     | 25642/61904 [2:48:38<13:32:11,  1.34s/it]
 41%|████▏     | 25643/61904 [2:48:39<13:21:10,  1.33s/it]
 41%|████▏     | 25644/61904 [2:48:40<13:19:19,  1.32s/it]
 41%|████▏     | 25645/61904 [2:48:42<13:26:31,  1.33s/it]
 41%|████▏     | 25646/61904 [2:48:43<13:16:50,  1.32s/it]
 41%|████▏     | 25647/61904 [2:48:45<13:36:58,  1.35s/it]
 41%|████▏     | 25648/61904 [2:48:46<14:16:46,  1.42s/it]
 41%|████▏     | 25649/61904 [2:48:47<14:02:23,  1.39s/it]
 41%|████▏     | 25650/61904 [2:48:49<13:54:30,  1.38s/it]
 41%|████▏     | 25651/61904 [2:48:50<13:56:36,  1.38s/it]
 41%|████▏     | 25652/61904 [2:48:52<14:02:08,  1.39s/it]
 41%|████▏     | 25653/61904 [2:48:53<13:51:58,  1.38s/it]
 41%|████▏     | 25654/61904 [2:48:54<13:31:41,  1.34s/it]
 41%|████▏     | 25655/61904 [2:48:56<13:34:41,  1.35s/it]
 41%|████▏     | 25656/61904 [2:48:57<13:39:39,  1.36s/it]
 41%|████▏     | 25657/61904 [2:48:58<13:31:23,  1.34s/it]
 41%|████▏     | 25658/61904 [2:49:00<13:36:26,  1.35s/it]
 41%|████▏     | 25659/61904 [2:49:01<13:37:22,  1.35s/it]
 41%|████▏     | 25660/61904 [2:49:02<13:34:05,  1.35s/it]
                                                          
{'loss': 2.5999, 'learning_rate': 1.5873849345261247e-07, 'epoch': 6.63}

 41%|████▏     | 25660/61904 [2:49:02<13:34:05,  1.35s/it]
 41%|████▏     | 25661/61904 [2:49:04<13:09:16,  1.31s/it]
 41%|████▏     | 25662/61904 [2:49:05<13:01:35,  1.29s/it]
 41%|████▏     | 25663/61904 [2:49:06<13:19:56,  1.32s/it]
 41%|████▏     | 25664/61904 [2:49:08<13:31:15,  1.34s/it]
 41%|████▏     | 25665/61904 [2:49:09<13:20:20,  1.33s/it]
 41%|████▏     | 25666/61904 [2:49:10<13:23:50,  1.33s/it]
 41%|████▏     | 25667/61904 [2:49:12<13:34:58,  1.35s/it]
 41%|████▏     | 25668/61904 [2:49:13<13:27:16,  1.34s/it]
 41%|████▏     | 25669/61904 [2:49:14<13:16:23,  1.32s/it]
 41%|████▏     | 25670/61904 [2:49:15<12:58:57,  1.29s/it]
 41%|████▏     | 25671/61904 [2:49:17<13:18:43,  1.32s/it]
 41%|████▏     | 25672/61904 [2:49:18<13:21:08,  1.33s/it]
 41%|████▏     | 25673/61904 [2:49:19<13:20:21,  1.33s/it]
 41%|████▏     | 25674/61904 [2:49:21<14:13:05,  1.41s/it]
 41%|████▏     | 25675/61904 [2:49:22<13:52:44,  1.38s/it]
 41%|████▏     | 25676/61904 [2:49:24<13:58:38,  1.39s/it]
 41%|████▏     | 25677/61904 [2:49:25<13:45:39,  1.37s/it]
 41%|████▏     | 25678/61904 [2:49:26<13:39:24,  1.36s/it]
 41%|████▏     | 25679/61904 [2:49:28<13:31:53,  1.34s/it]
 41%|████▏     | 25680/61904 [2:49:29<13:58:48,  1.39s/it]
                                                          
{'loss': 2.6625, 'learning_rate': 1.5870608064307013e-07, 'epoch': 6.64}

 41%|████▏     | 25680/61904 [2:49:29<13:58:48,  1.39s/it]
 41%|████▏     | 25681/61904 [2:49:31<14:05:47,  1.40s/it]
 41%|████▏     | 25682/61904 [2:49:32<14:09:08,  1.41s/it]
 41%|████▏     | 25683/61904 [2:49:33<13:50:51,  1.38s/it]
 41%|████▏     | 25684/61904 [2:49:35<14:25:46,  1.43s/it]
 41%|████▏     | 25685/61904 [2:49:36<14:12:08,  1.41s/it]
 41%|████▏     | 25686/61904 [2:49:38<14:10:17,  1.41s/it]
 41%|████▏     | 25687/61904 [2:49:39<14:28:03,  1.44s/it]
 41%|████▏     | 25688/61904 [2:49:41<14:18:28,  1.42s/it]
 41%|████▏     | 25689/61904 [2:49:42<14:16:40,  1.42s/it]
 41%|████▏     | 25690/61904 [2:49:43<14:16:18,  1.42s/it]
 42%|████▏     | 25691/61904 [2:49:45<14:08:55,  1.41s/it]
 42%|████▏     | 25692/61904 [2:49:46<14:16:53,  1.42s/it]
 42%|████▏     | 25693/61904 [2:49:48<14:07:01,  1.40s/it]
 42%|████▏     | 25694/61904 [2:49:49<13:51:57,  1.38s/it]
 42%|████▏     | 25695/61904 [2:49:50<13:41:26,  1.36s/it]
 42%|████▏     | 25696/61904 [2:49:52<13:47:52,  1.37s/it]
 42%|████▏     | 25697/61904 [2:49:53<13:41:33,  1.36s/it]
 42%|████▏     | 25698/61904 [2:49:54<13:38:42,  1.36s/it]
 42%|████▏     | 25699/61904 [2:49:56<13:42:04,  1.36s/it]
 42%|████▏     | 25700/61904 [2:49:57<13:49:33,  1.37s/it]
                                                          
{'loss': 2.5277, 'learning_rate': 1.586736678335278e-07, 'epoch': 6.64}

 42%|████▏     | 25700/61904 [2:49:57<13:49:33,  1.37s/it]
 42%|████▏     | 25701/61904 [2:49:59<13:50:38,  1.38s/it]
 42%|████▏     | 25702/61904 [2:50:00<13:51:33,  1.38s/it]
 42%|████▏     | 25703/61904 [2:50:01<13:42:54,  1.36s/it]
 42%|████▏     | 25704/61904 [2:50:03<13:59:05,  1.39s/it]
 42%|████▏     | 25705/61904 [2:50:04<13:55:46,  1.39s/it]
 42%|████▏     | 25706/61904 [2:50:05<13:49:23,  1.37s/it]
 42%|████▏     | 25707/61904 [2:50:07<13:33:22,  1.35s/it]
 42%|████▏     | 25708/61904 [2:50:08<13:38:51,  1.36s/it]
 42%|████▏     | 25709/61904 [2:50:09<13:17:57,  1.32s/it]
 42%|████▏     | 25710/61904 [2:50:11<13:06:38,  1.30s/it]
 42%|████▏     | 25711/61904 [2:50:12<13:14:21,  1.32s/it]
 42%|████▏     | 25712/61904 [2:50:13<13:34:44,  1.35s/it]
 42%|████▏     | 25713/61904 [2:50:15<13:40:58,  1.36s/it]
 42%|████▏     | 25714/61904 [2:50:16<13:24:49,  1.33s/it]
 42%|████▏     | 25715/61904 [2:50:17<13:37:35,  1.36s/it]
 42%|████▏     | 25716/61904 [2:50:19<13:42:55,  1.36s/it]
 42%|████▏     | 25717/61904 [2:50:20<14:04:15,  1.40s/it]
 42%|████▏     | 25718/61904 [2:50:22<13:46:42,  1.37s/it]
 42%|████▏     | 25719/61904 [2:50:23<14:08:35,  1.41s/it]
 42%|████▏     | 25720/61904 [2:50:24<14:03:25,  1.40s/it]
                                                          
{'loss': 2.5688, 'learning_rate': 1.5864125502398548e-07, 'epoch': 6.65}

 42%|████▏     | 25720/61904 [2:50:24<14:03:25,  1.40s/it]
 42%|████▏     | 25721/61904 [2:50:26<13:40:13,  1.36s/it]
 42%|████▏     | 25722/61904 [2:50:27<13:53:00,  1.38s/it]
 42%|████▏     | 25723/61904 [2:50:28<13:29:31,  1.34s/it]
 42%|████▏     | 25724/61904 [2:50:30<13:17:32,  1.32s/it]
 42%|████▏     | 25725/61904 [2:50:31<13:22:37,  1.33s/it]
 42%|████▏     | 25726/61904 [2:50:32<13:12:18,  1.31s/it]
 42%|████▏     | 25727/61904 [2:50:34<13:15:33,  1.32s/it]
 42%|████▏     | 25728/61904 [2:50:35<13:44:59,  1.37s/it]
 42%|████▏     | 25729/61904 [2:50:37<14:17:29,  1.42s/it]
 42%|████▏     | 25730/61904 [2:50:38<14:25:07,  1.43s/it]
 42%|████▏     | 25731/61904 [2:50:40<14:11:17,  1.41s/it]
 42%|████▏     | 25732/61904 [2:50:41<13:51:45,  1.38s/it]
 42%|████▏     | 25733/61904 [2:50:42<14:22:19,  1.43s/it]
 42%|████▏     | 25734/61904 [2:50:44<14:00:59,  1.40s/it]
 42%|████▏     | 25735/61904 [2:50:45<13:39:30,  1.36s/it]
 42%|████▏     | 25736/61904 [2:50:46<13:40:41,  1.36s/it]
 42%|████▏     | 25737/61904 [2:50:48<13:32:33,  1.35s/it]
 42%|████▏     | 25738/61904 [2:50:49<13:43:41,  1.37s/it]
 42%|████▏     | 25739/61904 [2:50:50<13:22:48,  1.33s/it]
 42%|████▏     | 25740/61904 [2:50:52<13:02:53,  1.30s/it]
                                                          
{'loss': 2.5813, 'learning_rate': 1.5860884221444314e-07, 'epoch': 6.65}

 42%|████▏     | 25740/61904 [2:50:52<13:02:53,  1.30s/it]
 42%|████▏     | 25741/61904 [2:50:53<13:15:31,  1.32s/it]
 42%|████▏     | 25742/61904 [2:50:54<13:22:40,  1.33s/it]
 42%|████▏     | 25743/61904 [2:50:56<13:52:37,  1.38s/it]
 42%|████▏     | 25744/61904 [2:50:57<13:58:34,  1.39s/it]
 42%|████▏     | 25745/61904 [2:50:58<13:40:26,  1.36s/it]
 42%|████▏     | 25746/61904 [2:51:00<13:58:09,  1.39s/it]
 42%|████▏     | 25747/61904 [2:51:01<14:07:05,  1.41s/it]
 42%|████▏     | 25748/61904 [2:51:03<13:45:32,  1.37s/it]
 42%|████▏     | 25749/61904 [2:51:04<13:43:07,  1.37s/it]
 42%|████▏     | 25750/61904 [2:51:05<13:05:34,  1.30s/it]
 42%|████▏     | 25751/61904 [2:51:07<13:10:04,  1.31s/it]
 42%|████▏     | 25752/61904 [2:51:08<13:45:54,  1.37s/it]
 42%|████▏     | 25753/61904 [2:51:09<13:47:40,  1.37s/it]
 42%|████▏     | 25754/61904 [2:51:11<13:38:13,  1.36s/it]
 42%|████▏     | 25755/61904 [2:51:12<13:33:34,  1.35s/it]
 42%|████▏     | 25756/61904 [2:51:13<13:35:52,  1.35s/it]
 42%|████▏     | 25757/61904 [2:51:15<13:45:49,  1.37s/it]
 42%|████▏     | 25758/61904 [2:51:16<14:22:54,  1.43s/it]
 42%|████▏     | 25759/61904 [2:51:18<13:49:37,  1.38s/it]
 42%|████▏     | 25760/61904 [2:51:19<13:54:47,  1.39s/it]
                                                          
{'loss': 2.622, 'learning_rate': 1.585764294049008e-07, 'epoch': 6.66}

 42%|████▏     | 25760/61904 [2:51:19<13:54:47,  1.39s/it]
 42%|████▏     | 25761/61904 [2:51:20<14:00:29,  1.40s/it]
 42%|████▏     | 25762/61904 [2:51:22<14:20:21,  1.43s/it]
 42%|████▏     | 25763/61904 [2:51:23<14:12:26,  1.42s/it]
 42%|████▏     | 25764/61904 [2:51:25<13:45:32,  1.37s/it]
 42%|████▏     | 25765/61904 [2:51:26<13:33:28,  1.35s/it]
 42%|████▏     | 25766/61904 [2:51:27<13:32:29,  1.35s/it]
 42%|████▏     | 25767/61904 [2:51:29<13:50:29,  1.38s/it]
 42%|████▏     | 25768/61904 [2:51:30<13:44:19,  1.37s/it]
 42%|████▏     | 25769/61904 [2:51:31<13:32:30,  1.35s/it]
 42%|████▏     | 25770/61904 [2:51:33<13:32:48,  1.35s/it]
 42%|████▏     | 25771/61904 [2:51:34<13:12:34,  1.32s/it]
 42%|████▏     | 25772/61904 [2:51:35<13:25:29,  1.34s/it]
 42%|████▏     | 25773/61904 [2:51:37<13:45:58,  1.37s/it]
 42%|████▏     | 25774/61904 [2:51:38<13:31:25,  1.35s/it]
 42%|████▏     | 25775/61904 [2:51:39<13:39:47,  1.36s/it]
 42%|████▏     | 25776/61904 [2:51:41<13:39:04,  1.36s/it]
 42%|████▏     | 25777/61904 [2:51:42<13:26:52,  1.34s/it]
 42%|████▏     | 25778/61904 [2:51:43<13:23:16,  1.33s/it]
 42%|████▏     | 25779/61904 [2:51:45<13:13:18,  1.32s/it]
 42%|████▏     | 25780/61904 [2:51:46<13:34:48,  1.35s/it]
                                                          
{'loss': 2.5956, 'learning_rate': 1.5854401659535847e-07, 'epoch': 6.66}

 42%|████▏     | 25780/61904 [2:51:46<13:34:48,  1.35s/it]
 42%|████▏     | 25781/61904 [2:51:48<13:33:47,  1.35s/it]
 42%|████▏     | 25782/61904 [2:51:49<13:12:40,  1.32s/it]
 42%|████▏     | 25783/61904 [2:51:50<13:23:19,  1.33s/it]
 42%|████▏     | 25784/61904 [2:51:52<13:38:04,  1.36s/it]
 42%|████▏     | 25785/61904 [2:51:53<13:22:15,  1.33s/it]
 42%|████▏     | 25786/61904 [2:51:54<13:51:18,  1.38s/it]
 42%|████▏     | 25787/61904 [2:51:56<13:57:38,  1.39s/it]
 42%|████▏     | 25788/61904 [2:51:57<13:45:55,  1.37s/it]
 42%|████▏     | 25789/61904 [2:51:58<13:39:28,  1.36s/it]
 42%|████▏     | 25790/61904 [2:52:00<13:34:18,  1.35s/it]
 42%|████▏     | 25791/61904 [2:52:01<13:24:44,  1.34s/it]
 42%|████▏     | 25792/61904 [2:52:02<13:28:38,  1.34s/it]
 42%|████▏     | 25793/61904 [2:52:04<13:26:04,  1.34s/it]
 42%|████▏     | 25794/61904 [2:52:05<13:12:56,  1.32s/it]
 42%|████▏     | 25795/61904 [2:52:06<13:02:31,  1.30s/it]
 42%|████▏     | 25796/61904 [2:52:08<13:29:07,  1.34s/it]
 42%|████▏     | 25797/61904 [2:52:09<13:18:46,  1.33s/it]
 42%|████▏     | 25798/61904 [2:52:11<13:58:43,  1.39s/it]
 42%|████▏     | 25799/61904 [2:52:12<13:56:36,  1.39s/it]
 42%|████▏     | 25800/61904 [2:52:13<13:36:42,  1.36s/it]
                                                          
{'loss': 2.5834, 'learning_rate': 1.5851160378581613e-07, 'epoch': 6.67}

 42%|████▏     | 25800/61904 [2:52:13<13:36:42,  1.36s/it]
 42%|████▏     | 25801/61904 [2:52:15<13:40:52,  1.36s/it]
 42%|████▏     | 25802/61904 [2:52:16<13:50:32,  1.38s/it]
 42%|████▏     | 25803/61904 [2:52:17<13:53:38,  1.39s/it]
 42%|████▏     | 25804/61904 [2:52:19<13:33:09,  1.35s/it]
 42%|████▏     | 25805/61904 [2:52:20<14:13:47,  1.42s/it]
 42%|████▏     | 25806/61904 [2:52:22<14:03:58,  1.40s/it]
 42%|████▏     | 25807/61904 [2:52:23<14:05:57,  1.41s/it]
 42%|████▏     | 25808/61904 [2:52:24<13:47:34,  1.38s/it]
 42%|████▏     | 25809/61904 [2:52:26<13:35:13,  1.36s/it]
 42%|████▏     | 25810/61904 [2:52:27<13:24:05,  1.34s/it]
 42%|████▏     | 25811/61904 [2:52:28<13:30:57,  1.35s/it]
 42%|████▏     | 25812/61904 [2:52:30<13:24:30,  1.34s/it]
 42%|████▏     | 25813/61904 [2:52:31<13:07:00,  1.31s/it]
 42%|████▏     | 25814/61904 [2:52:32<13:06:04,  1.31s/it]
 42%|████▏     | 25815/61904 [2:52:34<13:22:33,  1.33s/it]
 42%|████▏     | 25816/61904 [2:52:35<13:38:57,  1.36s/it]
 42%|████▏     | 25817/61904 [2:52:36<13:58:12,  1.39s/it]
 42%|████▏     | 25818/61904 [2:52:38<13:27:27,  1.34s/it]
 42%|████▏     | 25819/61904 [2:52:39<13:16:32,  1.32s/it]
 42%|████▏     | 25820/61904 [2:52:40<13:35:47,  1.36s/it]
                                                          
{'loss': 2.5737, 'learning_rate': 1.5847919097627382e-07, 'epoch': 6.67}

 42%|████▏     | 25820/61904 [2:52:40<13:35:47,  1.36s/it]
 42%|████▏     | 25821/61904 [2:52:42<14:20:33,  1.43s/it]
 42%|████▏     | 25822/61904 [2:52:43<13:58:31,  1.39s/it]
 42%|████▏     | 25823/61904 [2:52:45<13:56:08,  1.39s/it]
 42%|████▏     | 25824/61904 [2:52:46<13:52:45,  1.38s/it]
 42%|████▏     | 25825/61904 [2:52:47<13:34:28,  1.35s/it]
 42%|████▏     | 25826/61904 [2:52:49<13:29:01,  1.35s/it]
 42%|████▏     | 25827/61904 [2:52:50<13:25:17,  1.34s/it]
 42%|████▏     | 25828/61904 [2:52:51<13:39:25,  1.36s/it]
 42%|████▏     | 25829/61904 [2:52:53<13:37:33,  1.36s/it]
 42%|████▏     | 25830/61904 [2:52:54<13:44:32,  1.37s/it]
 42%|████▏     | 25831/61904 [2:52:55<13:33:31,  1.35s/it]
 42%|████▏     | 25832/61904 [2:52:57<13:24:58,  1.34s/it]
 42%|████▏     | 25833/61904 [2:52:58<13:25:32,  1.34s/it]
 42%|████▏     | 25834/61904 [2:52:59<13:13:37,  1.32s/it]
 42%|████▏     | 25835/61904 [2:53:01<13:23:16,  1.34s/it]
 42%|████▏     | 25836/61904 [2:53:02<13:35:43,  1.36s/it]
 42%|████▏     | 25837/61904 [2:53:03<13:09:03,  1.31s/it]
 42%|████▏     | 25838/61904 [2:53:05<12:53:50,  1.29s/it]
 42%|████▏     | 25839/61904 [2:53:06<13:15:51,  1.32s/it]
 42%|████▏     | 25840/61904 [2:53:07<13:21:55,  1.33s/it]
                                                          
{'loss': 2.5815, 'learning_rate': 1.5844677816673148e-07, 'epoch': 6.68}

 42%|████▏     | 25840/61904 [2:53:07<13:21:55,  1.33s/it]
 42%|████▏     | 25841/61904 [2:53:09<13:12:28,  1.32s/it]
 42%|████▏     | 25842/61904 [2:53:10<12:50:58,  1.28s/it]
 42%|████▏     | 25843/61904 [2:53:11<13:13:08,  1.32s/it]
 42%|████▏     | 25844/61904 [2:53:13<13:36:44,  1.36s/it]
 42%|████▏     | 25845/61904 [2:53:14<14:05:04,  1.41s/it]
 42%|████▏     | 25846/61904 [2:53:16<14:02:30,  1.40s/it]
 42%|████▏     | 25847/61904 [2:53:17<13:23:04,  1.34s/it]
 42%|████▏     | 25848/61904 [2:53:18<13:55:08,  1.39s/it]
 42%|████▏     | 25849/61904 [2:53:20<13:58:02,  1.39s/it]
 42%|████▏     | 25850/61904 [2:53:21<14:19:27,  1.43s/it]
 42%|████▏     | 25851/61904 [2:53:23<14:21:28,  1.43s/it]
 42%|████▏     | 25852/61904 [2:53:24<14:17:20,  1.43s/it]
 42%|████▏     | 25853/61904 [2:53:25<13:53:45,  1.39s/it]
 42%|████▏     | 25854/61904 [2:53:27<14:04:34,  1.41s/it]
 42%|████▏     | 25855/61904 [2:53:28<13:47:31,  1.38s/it]
 42%|████▏     | 25856/61904 [2:53:30<13:48:59,  1.38s/it]
 42%|████▏     | 25857/61904 [2:53:31<13:59:29,  1.40s/it]
 42%|████▏     | 25858/61904 [2:53:32<14:10:28,  1.42s/it]
 42%|████▏     | 25859/61904 [2:53:34<13:48:08,  1.38s/it]
 42%|████▏     | 25860/61904 [2:53:35<13:22:29,  1.34s/it]
                                                          
{'loss': 2.5868, 'learning_rate': 1.5841436535718914e-07, 'epoch': 6.68}

 42%|████▏     | 25860/61904 [2:53:35<13:22:29,  1.34s/it]
 42%|████▏     | 25861/61904 [2:53:36<13:06:30,  1.31s/it]
 42%|████▏     | 25862/61904 [2:53:38<13:25:34,  1.34s/it]
 42%|████▏     | 25863/61904 [2:53:39<13:24:37,  1.34s/it]
 42%|████▏     | 25864/61904 [2:53:40<13:49:18,  1.38s/it]
 42%|████▏     | 25865/61904 [2:53:42<13:51:57,  1.39s/it]
 42%|████▏     | 25866/61904 [2:53:43<14:05:02,  1.41s/it]
 42%|████▏     | 25867/61904 [2:53:45<14:14:17,  1.42s/it]
 42%|████▏     | 25868/61904 [2:53:46<14:01:30,  1.40s/it]
 42%|████▏     | 25869/61904 [2:53:47<13:54:39,  1.39s/it]
 42%|████▏     | 25870/61904 [2:53:49<13:31:01,  1.35s/it]
 42%|████▏     | 25871/61904 [2:53:50<13:26:04,  1.34s/it]
 42%|████▏     | 25872/61904 [2:53:51<13:35:23,  1.36s/it]
 42%|████▏     | 25873/61904 [2:53:53<13:31:43,  1.35s/it]
 42%|████▏     | 25874/61904 [2:53:54<13:14:18,  1.32s/it]
 42%|████▏     | 25875/61904 [2:53:55<13:11:03,  1.32s/it]
 42%|████▏     | 25876/61904 [2:53:57<12:59:21,  1.30s/it]
 42%|████▏     | 25877/61904 [2:53:58<13:18:50,  1.33s/it]
 42%|████▏     | 25878/61904 [2:53:59<13:21:23,  1.33s/it]
 42%|████▏     | 25879/61904 [2:54:01<13:08:13,  1.31s/it]
 42%|████▏     | 25880/61904 [2:54:02<13:10:52,  1.32s/it]
                                                          
{'loss': 2.6376, 'learning_rate': 1.5838195254764683e-07, 'epoch': 6.69}

 42%|████▏     | 25880/61904 [2:54:02<13:10:52,  1.32s/it]
 42%|████▏     | 25881/61904 [2:54:03<13:16:44,  1.33s/it]
 42%|████▏     | 25882/61904 [2:54:05<13:50:45,  1.38s/it]
 42%|████▏     | 25883/61904 [2:54:06<13:43:46,  1.37s/it]
 42%|████▏     | 25884/61904 [2:54:07<13:38:11,  1.36s/it]
 42%|████▏     | 25885/61904 [2:54:09<13:23:15,  1.34s/it]
 42%|████▏     | 25886/61904 [2:54:10<13:26:39,  1.34s/it]
 42%|████▏     | 25887/61904 [2:54:12<13:42:12,  1.37s/it]
 42%|████▏     | 25888/61904 [2:54:13<13:31:40,  1.35s/it]
 42%|████▏     | 25889/61904 [2:54:14<13:28:13,  1.35s/it]
 42%|████▏     | 25890/61904 [2:54:16<13:28:12,  1.35s/it]
 42%|████▏     | 25891/61904 [2:54:17<13:31:02,  1.35s/it]
 42%|████▏     | 25892/61904 [2:54:18<13:13:47,  1.32s/it]
 42%|████▏     | 25893/61904 [2:54:19<13:16:24,  1.33s/it]
 42%|████▏     | 25894/61904 [2:54:21<13:15:21,  1.33s/it]
 42%|████▏     | 25895/61904 [2:54:22<13:00:47,  1.30s/it]
 42%|████▏     | 25896/61904 [2:54:23<13:05:07,  1.31s/it]
 42%|████▏     | 25897/61904 [2:54:25<13:32:46,  1.35s/it]
 42%|████▏     | 25898/61904 [2:54:26<13:20:29,  1.33s/it]
 42%|████▏     | 25899/61904 [2:54:27<13:09:28,  1.32s/it]
 42%|████▏     | 25900/61904 [2:54:29<13:18:02,  1.33s/it]
                                                          
{'loss': 2.5857, 'learning_rate': 1.583495397381045e-07, 'epoch': 6.69}

 42%|████▏     | 25900/61904 [2:54:29<13:18:02,  1.33s/it]
 42%|████▏     | 25901/61904 [2:54:30<13:32:44,  1.35s/it]
 42%|████▏     | 25902/61904 [2:54:31<13:23:58,  1.34s/it]
 42%|████▏     | 25903/61904 [2:54:33<14:03:19,  1.41s/it]
 42%|████▏     | 25904/61904 [2:54:34<13:26:05,  1.34s/it]
 42%|████▏     | 25905/61904 [2:54:36<13:43:17,  1.37s/it]
 42%|████▏     | 25906/61904 [2:54:37<13:12:16,  1.32s/it]
 42%|████▏     | 25907/61904 [2:54:38<13:00:33,  1.30s/it]
 42%|████▏     | 25908/61904 [2:54:40<13:38:22,  1.36s/it]
 42%|████▏     | 25909/61904 [2:54:41<14:02:33,  1.40s/it]
 42%|████▏     | 25910/61904 [2:54:42<13:48:23,  1.38s/it]
 42%|████▏     | 25911/61904 [2:54:44<13:21:02,  1.34s/it]
 42%|████▏     | 25912/61904 [2:54:45<13:30:43,  1.35s/it]
 42%|████▏     | 25913/61904 [2:54:46<13:31:49,  1.35s/it]
 42%|████▏     | 25914/61904 [2:54:48<14:25:01,  1.44s/it]
 42%|████▏     | 25915/61904 [2:54:50<14:36:45,  1.46s/it]
 42%|████▏     | 25916/61904 [2:54:51<14:24:55,  1.44s/it]
 42%|████▏     | 25917/61904 [2:54:52<14:11:36,  1.42s/it]
 42%|████▏     | 25918/61904 [2:54:54<14:00:36,  1.40s/it]
 42%|████▏     | 25919/61904 [2:54:55<13:37:18,  1.36s/it]
 42%|████▏     | 25920/61904 [2:54:57<14:17:52,  1.43s/it]
                                                          
{'loss': 2.6078, 'learning_rate': 1.5831712692856215e-07, 'epoch': 6.7}

 42%|████▏     | 25920/61904 [2:54:57<14:17:52,  1.43s/it]
 42%|████▏     | 25921/61904 [2:54:58<14:45:40,  1.48s/it]
 42%|████▏     | 25922/61904 [2:54:59<13:56:47,  1.40s/it]
 42%|████▏     | 25923/61904 [2:55:01<13:58:41,  1.40s/it]
 42%|████▏     | 25924/61904 [2:55:02<13:26:50,  1.35s/it]
 42%|████▏     | 25925/61904 [2:55:03<13:23:30,  1.34s/it]
 42%|████▏     | 25926/61904 [2:55:05<13:27:51,  1.35s/it]
 42%|████▏     | 25927/61904 [2:55:06<13:45:24,  1.38s/it]
 42%|████▏     | 25928/61904 [2:55:07<13:28:32,  1.35s/it]
 42%|████▏     | 25929/61904 [2:55:09<13:46:59,  1.38s/it]
 42%|████▏     | 25930/61904 [2:55:10<13:54:32,  1.39s/it]
 42%|████▏     | 25931/61904 [2:55:12<13:32:22,  1.35s/it]
 42%|████▏     | 25932/61904 [2:55:13<13:21:54,  1.34s/it]
 42%|████▏     | 25933/61904 [2:55:14<13:40:47,  1.37s/it]
 42%|████▏     | 25934/61904 [2:55:16<13:38:28,  1.37s/it]
 42%|████▏     | 25935/61904 [2:55:17<13:31:52,  1.35s/it]
 42%|████▏     | 25936/61904 [2:55:18<13:28:24,  1.35s/it]
 42%|████▏     | 25937/61904 [2:55:20<13:15:32,  1.33s/it]
 42%|████▏     | 25938/61904 [2:55:21<13:25:08,  1.34s/it]
 42%|████▏     | 25939/61904 [2:55:22<13:24:01,  1.34s/it]
 42%|████▏     | 25940/61904 [2:55:24<13:40:05,  1.37s/it]
                                                          
{'loss': 2.6262, 'learning_rate': 1.5828471411901981e-07, 'epoch': 6.7}

 42%|████▏     | 25940/61904 [2:55:24<13:40:05,  1.37s/it]
 42%|████▏     | 25941/61904 [2:55:25<13:22:02,  1.34s/it]
 42%|████▏     | 25942/61904 [2:55:26<13:34:15,  1.36s/it]
 42%|████▏     | 25943/61904 [2:55:28<13:29:09,  1.35s/it]
 42%|████▏     | 25944/61904 [2:55:29<13:40:37,  1.37s/it]
 42%|████▏     | 25945/61904 [2:55:31<13:39:32,  1.37s/it]
 42%|████▏     | 25946/61904 [2:55:32<13:20:39,  1.34s/it]
 42%|████▏     | 25947/61904 [2:55:33<13:07:25,  1.31s/it]
 42%|████▏     | 25948/61904 [2:55:34<13:14:02,  1.33s/it]
 42%|████▏     | 25949/61904 [2:55:36<13:22:28,  1.34s/it]
 42%|████▏     | 25950/61904 [2:55:37<13:08:28,  1.32s/it]
 42%|████▏     | 25951/61904 [2:55:38<13:18:08,  1.33s/it]
 42%|████▏     | 25952/61904 [2:55:40<13:04:25,  1.31s/it]
 42%|████▏     | 25953/61904 [2:55:41<13:04:40,  1.31s/it]
 42%|████▏     | 25954/61904 [2:55:42<12:56:10,  1.30s/it]
 42%|████▏     | 25955/61904 [2:55:44<13:16:11,  1.33s/it]
 42%|████▏     | 25956/61904 [2:55:45<13:35:00,  1.36s/it]
 42%|████▏     | 25957/61904 [2:55:47<14:02:04,  1.41s/it]
 42%|████▏     | 25958/61904 [2:55:48<14:00:36,  1.40s/it]
 42%|████▏     | 25959/61904 [2:55:49<13:55:28,  1.39s/it]
 42%|████▏     | 25960/61904 [2:55:51<13:44:03,  1.38s/it]
                                                          
{'loss': 2.5676, 'learning_rate': 1.582523013094775e-07, 'epoch': 6.71}

 42%|████▏     | 25960/61904 [2:55:51<13:44:03,  1.38s/it]
 42%|████▏     | 25961/61904 [2:55:52<14:16:43,  1.43s/it]
 42%|████▏     | 25962/61904 [2:55:54<13:50:25,  1.39s/it]
 42%|████▏     | 25963/61904 [2:55:55<13:57:11,  1.40s/it]
 42%|████▏     | 25964/61904 [2:55:56<14:19:15,  1.43s/it]
 42%|████▏     | 25965/61904 [2:55:58<14:26:44,  1.45s/it]
 42%|████▏     | 25966/61904 [2:55:59<14:22:07,  1.44s/it]
 42%|████▏     | 25967/61904 [2:56:01<14:24:46,  1.44s/it]
 42%|████▏     | 25968/61904 [2:56:02<14:15:39,  1.43s/it]
 42%|████▏     | 25969/61904 [2:56:04<14:11:01,  1.42s/it]
 42%|████▏     | 25970/61904 [2:56:05<13:50:45,  1.39s/it]
 42%|████▏     | 25971/61904 [2:56:06<13:45:59,  1.38s/it]
 42%|████▏     | 25972/61904 [2:56:08<13:30:06,  1.35s/it]
 42%|████▏     | 25973/61904 [2:56:09<13:24:55,  1.34s/it]
 42%|████▏     | 25974/61904 [2:56:10<13:07:29,  1.32s/it]
 42%|████▏     | 25975/61904 [2:56:12<13:22:31,  1.34s/it]
 42%|████▏     | 25976/61904 [2:56:13<14:00:28,  1.40s/it]
 42%|████▏     | 25977/61904 [2:56:14<13:57:04,  1.40s/it]
 42%|████▏     | 25978/61904 [2:56:16<13:51:18,  1.39s/it]
 42%|████▏     | 25979/61904 [2:56:17<13:56:29,  1.40s/it]
 42%|████▏     | 25980/61904 [2:56:19<13:49:38,  1.39s/it]
                                                          
{'loss': 2.6036, 'learning_rate': 1.5821988849993516e-07, 'epoch': 6.71}

 42%|████▏     | 25980/61904 [2:56:19<13:49:38,  1.39s/it]
 42%|████▏     | 25981/61904 [2:56:20<13:42:52,  1.37s/it]
 42%|████▏     | 25982/61904 [2:56:21<13:43:40,  1.38s/it]
 42%|████▏     | 25983/61904 [2:56:23<13:29:37,  1.35s/it]
 42%|████▏     | 25984/61904 [2:56:24<13:34:41,  1.36s/it]
 42%|████▏     | 25985/61904 [2:56:25<13:27:40,  1.35s/it]
 42%|████▏     | 25986/61904 [2:56:27<13:15:58,  1.33s/it]
 42%|████▏     | 25987/61904 [2:56:28<13:21:09,  1.34s/it]
 42%|████▏     | 25988/61904 [2:56:29<13:16:51,  1.33s/it]
 42%|████▏     | 25989/61904 [2:56:31<13:25:30,  1.35s/it]
 42%|████▏     | 25990/61904 [2:56:32<13:31:40,  1.36s/it]
 42%|████▏     | 25991/61904 [2:56:33<13:30:31,  1.35s/it]
 42%|████▏     | 25992/61904 [2:56:35<13:18:31,  1.33s/it]
 42%|████▏     | 25993/61904 [2:56:36<13:23:52,  1.34s/it]
 42%|████▏     | 25994/61904 [2:56:37<13:19:18,  1.34s/it]
 42%|████▏     | 25995/61904 [2:56:39<13:44:07,  1.38s/it]
 42%|████▏     | 25996/61904 [2:56:40<14:19:36,  1.44s/it]
 42%|████▏     | 25997/61904 [2:56:42<14:10:05,  1.42s/it]
 42%|████▏     | 25998/61904 [2:56:43<13:49:21,  1.39s/it]
 42%|████▏     | 25999/61904 [2:56:44<13:34:50,  1.36s/it]
 42%|████▏     | 26000/61904 [2:56:46<13:18:10,  1.33s/it]
                                                          
{'loss': 2.5575, 'learning_rate': 1.5818747569039283e-07, 'epoch': 6.72}

 42%|████▏     | 26000/61904 [2:56:46<13:18:10,  1.33s/it]
 42%|████▏     | 26001/61904 [2:56:47<13:59:52,  1.40s/it]
 42%|████▏     | 26002/61904 [2:56:49<13:58:42,  1.40s/it]
 42%|████▏     | 26003/61904 [2:56:50<13:53:07,  1.39s/it]
 42%|████▏     | 26004/61904 [2:56:51<13:47:52,  1.38s/it]
 42%|████▏     | 26005/61904 [2:56:53<13:35:47,  1.36s/it]
 42%|████▏     | 26006/61904 [2:56:54<13:36:49,  1.37s/it]
 42%|████▏     | 26007/61904 [2:56:56<13:51:23,  1.39s/it]
 42%|████▏     | 26008/61904 [2:56:57<13:23:23,  1.34s/it]
 42%|████▏     | 26009/61904 [2:56:58<13:14:55,  1.33s/it]
 42%|████▏     | 26010/61904 [2:56:59<13:26:31,  1.35s/it]
 42%|████▏     | 26011/61904 [2:57:01<13:35:44,  1.36s/it]
 42%|████▏     | 26012/61904 [2:57:02<13:31:40,  1.36s/it]
 42%|████▏     | 26013/61904 [2:57:04<13:27:13,  1.35s/it]
 42%|████▏     | 26014/61904 [2:57:05<13:10:31,  1.32s/it]
 42%|████▏     | 26015/61904 [2:57:06<12:55:45,  1.30s/it]
 42%|████▏     | 26016/61904 [2:57:07<13:24:23,  1.34s/it]
 42%|████▏     | 26017/61904 [2:57:09<13:39:07,  1.37s/it]
 42%|████▏     | 26018/61904 [2:57:10<14:18:41,  1.44s/it]
 42%|████▏     | 26019/61904 [2:57:12<14:46:31,  1.48s/it]
 42%|████▏     | 26020/61904 [2:57:14<14:49:03,  1.49s/it]
                                                          
{'loss': 2.5708, 'learning_rate': 1.581550628808505e-07, 'epoch': 6.73}

 42%|████▏     | 26020/61904 [2:57:14<14:49:03,  1.49s/it]
 42%|████▏     | 26021/61904 [2:57:15<14:20:53,  1.44s/it]
 42%|████▏     | 26022/61904 [2:57:16<13:54:05,  1.39s/it]
 42%|████▏     | 26023/61904 [2:57:18<13:52:59,  1.39s/it]
 42%|████▏     | 26024/61904 [2:57:19<13:57:42,  1.40s/it]
 42%|████▏     | 26025/61904 [2:57:20<13:53:47,  1.39s/it]
 42%|████▏     | 26026/61904 [2:57:22<13:36:33,  1.37s/it]
 42%|████▏     | 26027/61904 [2:57:23<13:50:04,  1.39s/it]
 42%|████▏     | 26028/61904 [2:57:24<13:46:38,  1.38s/it]
 42%|████▏     | 26029/61904 [2:57:26<13:36:43,  1.37s/it]
 42%|████▏     | 26030/61904 [2:57:27<13:52:17,  1.39s/it]
 42%|████▏     | 26031/61904 [2:57:29<13:43:50,  1.38s/it]
 42%|████▏     | 26032/61904 [2:57:30<13:42:00,  1.37s/it]
 42%|████▏     | 26033/61904 [2:57:31<13:43:25,  1.38s/it]
 42%|████▏     | 26034/61904 [2:57:33<13:58:26,  1.40s/it]
 42%|████▏     | 26035/61904 [2:57:34<13:34:36,  1.36s/it]
 42%|████▏     | 26036/61904 [2:57:35<13:32:07,  1.36s/it]
 42%|████▏     | 26037/61904 [2:57:37<13:20:56,  1.34s/it]
 42%|████▏     | 26038/61904 [2:57:38<13:38:11,  1.37s/it]
 42%|████▏     | 26039/61904 [2:57:39<13:11:46,  1.32s/it]
 42%|████▏     | 26040/61904 [2:57:41<13:08:16,  1.32s/it]
                                                          
{'loss': 2.6489, 'learning_rate': 1.5812265007130818e-07, 'epoch': 6.73}

 42%|████▏     | 26040/61904 [2:57:41<13:08:16,  1.32s/it]
 42%|████▏     | 26041/61904 [2:57:42<13:18:05,  1.34s/it]
 42%|████▏     | 26042/61904 [2:57:43<13:22:28,  1.34s/it]
 42%|████▏     | 26043/61904 [2:57:45<13:14:17,  1.33s/it]
 42%|████▏     | 26044/61904 [2:57:46<13:03:27,  1.31s/it]
 42%|████▏     | 26045/61904 [2:57:47<13:04:18,  1.31s/it]
 42%|████▏     | 26046/61904 [2:57:49<13:16:44,  1.33s/it]
 42%|████▏     | 26047/61904 [2:57:50<13:01:45,  1.31s/it]
 42%|████▏     | 26048/61904 [2:57:51<13:28:18,  1.35s/it]
 42%|████▏     | 26049/61904 [2:57:53<13:26:02,  1.35s/it]
 42%|████▏     | 26050/61904 [2:57:54<13:28:18,  1.35s/it]
 42%|████▏     | 26051/61904 [2:57:56<13:45:58,  1.38s/it]
 42%|████▏     | 26052/61904 [2:57:57<13:27:35,  1.35s/it]
 42%|████▏     | 26053/61904 [2:57:58<13:25:57,  1.35s/it]
 42%|████▏     | 26054/61904 [2:58:00<13:39:09,  1.37s/it]
 42%|████▏     | 26055/61904 [2:58:01<13:18:05,  1.34s/it]
 42%|████▏     | 26056/61904 [2:58:02<13:14:04,  1.33s/it]
 42%|████▏     | 26057/61904 [2:58:04<13:14:49,  1.33s/it]
 42%|████▏     | 26058/61904 [2:58:05<13:18:21,  1.34s/it]
 42%|████▏     | 26059/61904 [2:58:06<13:56:32,  1.40s/it]
 42%|████▏     | 26060/61904 [2:58:08<13:48:25,  1.39s/it]
                                                          
{'loss': 2.6338, 'learning_rate': 1.5809023726176584e-07, 'epoch': 6.74}

 42%|████▏     | 26060/61904 [2:58:08<13:48:25,  1.39s/it]
 42%|████▏     | 26061/61904 [2:58:09<13:33:07,  1.36s/it]
 42%|████▏     | 26062/61904 [2:58:10<13:30:33,  1.36s/it]
 42%|████▏     | 26063/61904 [2:58:12<13:34:34,  1.36s/it]
 42%|████▏     | 26064/61904 [2:58:13<13:32:53,  1.36s/it]
 42%|████▏     | 26065/61904 [2:58:15<13:42:22,  1.38s/it]
 42%|████▏     | 26066/61904 [2:58:16<13:24:38,  1.35s/it]
 42%|████▏     | 26067/61904 [2:58:17<14:08:14,  1.42s/it]
 42%|████▏     | 26068/61904 [2:58:19<13:57:03,  1.40s/it]
 42%|████▏     | 26069/61904 [2:58:20<13:39:01,  1.37s/it]
 42%|████▏     | 26070/61904 [2:58:22<13:49:18,  1.39s/it]
 42%|████▏     | 26071/61904 [2:58:23<13:52:45,  1.39s/it]
 42%|████▏     | 26072/61904 [2:58:24<13:59:18,  1.41s/it]
 42%|████▏     | 26073/61904 [2:58:26<13:56:30,  1.40s/it]
 42%|████▏     | 26074/61904 [2:58:27<13:40:57,  1.37s/it]
 42%|████▏     | 26075/61904 [2:58:28<13:21:14,  1.34s/it]
 42%|████▏     | 26076/61904 [2:58:30<13:42:58,  1.38s/it]
 42%|████▏     | 26077/61904 [2:58:31<13:52:57,  1.39s/it]
 42%|████▏     | 26078/61904 [2:58:32<13:28:45,  1.35s/it]
 42%|████▏     | 26079/61904 [2:58:34<13:14:53,  1.33s/it]
 42%|████▏     | 26080/61904 [2:58:35<13:16:39,  1.33s/it]
                                                          
{'loss': 2.6506, 'learning_rate': 1.580578244522235e-07, 'epoch': 6.74}

 42%|████▏     | 26080/61904 [2:58:35<13:16:39,  1.33s/it]
 42%|████▏     | 26081/61904 [2:58:37<13:46:06,  1.38s/it]
 42%|████▏     | 26082/61904 [2:58:38<13:38:24,  1.37s/it]
 42%|████▏     | 26083/61904 [2:58:39<13:55:08,  1.40s/it]
 42%|████▏     | 26084/61904 [2:58:41<13:42:41,  1.38s/it]
 42%|████▏     | 26085/61904 [2:58:42<13:27:04,  1.35s/it]
 42%|████▏     | 26086/61904 [2:58:43<13:13:42,  1.33s/it]
 42%|████▏     | 26087/61904 [2:58:45<13:05:18,  1.32s/it]
 42%|████▏     | 26088/61904 [2:58:46<13:12:16,  1.33s/it]
 42%|████▏     | 26089/61904 [2:58:47<12:52:11,  1.29s/it]
 42%|████▏     | 26090/61904 [2:58:48<12:59:49,  1.31s/it]
 42%|████▏     | 26091/61904 [2:58:50<12:43:13,  1.28s/it]
 42%|████▏     | 26092/61904 [2:58:51<13:01:23,  1.31s/it]
 42%|████▏     | 26093/61904 [2:58:52<13:17:09,  1.34s/it]
 42%|████▏     | 26094/61904 [2:58:54<13:24:37,  1.35s/it]
 42%|████▏     | 26095/61904 [2:58:55<13:28:50,  1.36s/it]
 42%|████▏     | 26096/61904 [2:58:57<13:29:19,  1.36s/it]
 42%|████▏     | 26097/61904 [2:58:58<13:51:40,  1.39s/it]
 42%|████▏     | 26098/61904 [2:58:59<13:47:42,  1.39s/it]
 42%|████▏     | 26099/61904 [2:59:01<13:39:02,  1.37s/it]
 42%|████▏     | 26100/61904 [2:59:02<13:29:24,  1.36s/it]
                                                          
{'loss': 2.541, 'learning_rate': 1.5802541164268116e-07, 'epoch': 6.75}

 42%|████▏     | 26100/61904 [2:59:02<13:29:24,  1.36s/it]
 42%|████▏     | 26101/61904 [2:59:03<13:17:26,  1.34s/it]
 42%|████▏     | 26102/61904 [2:59:05<13:20:01,  1.34s/it]
 42%|████▏     | 26103/61904 [2:59:06<13:29:01,  1.36s/it]
 42%|████▏     | 26104/61904 [2:59:08<13:40:25,  1.38s/it]
 42%|████▏     | 26105/61904 [2:59:09<13:31:29,  1.36s/it]
 42%|████▏     | 26106/61904 [2:59:10<13:29:34,  1.36s/it]
 42%|████▏     | 26107/61904 [2:59:12<13:26:43,  1.35s/it]
 42%|████▏     | 26108/61904 [2:59:13<13:25:54,  1.35s/it]
 42%|████▏     | 26109/61904 [2:59:14<13:28:51,  1.36s/it]
 42%|████▏     | 26110/61904 [2:59:16<13:26:26,  1.35s/it]
 42%|████▏     | 26111/61904 [2:59:17<13:25:15,  1.35s/it]
 42%|████▏     | 26112/61904 [2:59:18<13:32:07,  1.36s/it]
 42%|████▏     | 26113/61904 [2:59:20<13:35:25,  1.37s/it]
 42%|████▏     | 26114/61904 [2:59:21<13:44:34,  1.38s/it]
 42%|████▏     | 26115/61904 [2:59:23<13:57:43,  1.40s/it]
 42%|████▏     | 26116/61904 [2:59:24<14:00:56,  1.41s/it]
 42%|████▏     | 26117/61904 [2:59:25<13:56:31,  1.40s/it]
 42%|████▏     | 26118/61904 [2:59:27<13:46:16,  1.39s/it]
 42%|████▏     | 26119/61904 [2:59:28<14:06:10,  1.42s/it]
 42%|████▏     | 26120/61904 [2:59:30<14:15:15,  1.43s/it]
                                                          
{'loss': 2.5367, 'learning_rate': 1.5799299883313885e-07, 'epoch': 6.75}

 42%|████▏     | 26120/61904 [2:59:30<14:15:15,  1.43s/it]
 42%|████▏     | 26121/61904 [2:59:31<14:29:24,  1.46s/it]
 42%|████▏     | 26122/61904 [2:59:33<14:13:54,  1.43s/it]
 42%|████▏     | 26123/61904 [2:59:34<14:05:19,  1.42s/it]
 42%|████▏     | 26124/61904 [2:59:35<13:53:24,  1.40s/it]
 42%|████▏     | 26125/61904 [2:59:37<13:46:13,  1.39s/it]
 42%|████▏     | 26126/61904 [2:59:38<13:29:22,  1.36s/it]
 42%|████▏     | 26127/61904 [2:59:39<13:38:52,  1.37s/it]
 42%|████▏     | 26128/61904 [2:59:41<13:31:09,  1.36s/it]
 42%|████▏     | 26129/61904 [2:59:42<13:27:01,  1.35s/it]
 42%|████▏     | 26130/61904 [2:59:43<13:12:07,  1.33s/it]
 42%|████▏     | 26131/61904 [2:59:45<12:59:57,  1.31s/it]
 42%|████▏     | 26132/61904 [2:59:46<13:28:21,  1.36s/it]
 42%|████▏     | 26133/61904 [2:59:47<13:37:17,  1.37s/it]
 42%|████▏     | 26134/61904 [2:59:49<13:53:32,  1.40s/it]
 42%|████▏     | 26135/61904 [2:59:50<13:51:23,  1.39s/it]
 42%|████▏     | 26136/61904 [2:59:52<13:25:35,  1.35s/it]
 42%|████▏     | 26137/61904 [2:59:53<13:23:16,  1.35s/it]
 42%|████▏     | 26138/61904 [2:59:54<13:11:38,  1.33s/it]
 42%|████▏     | 26139/61904 [2:59:56<13:18:19,  1.34s/it]
 42%|████▏     | 26140/61904 [2:59:57<13:17:14,  1.34s/it]
                                                          
{'loss': 2.5891, 'learning_rate': 1.579605860235965e-07, 'epoch': 6.76}

 42%|████▏     | 26140/61904 [2:59:57<13:17:14,  1.34s/it]
 42%|████▏     | 26141/61904 [2:59:58<13:30:07,  1.36s/it]
 42%|████▏     | 26142/61904 [3:00:00<13:40:13,  1.38s/it]
 42%|████▏     | 26143/61904 [3:00:01<13:44:27,  1.38s/it]
 42%|████▏     | 26144/61904 [3:00:03<14:13:01,  1.43s/it]
 42%|████▏     | 26145/61904 [3:00:04<14:33:11,  1.47s/it]
 42%|████▏     | 26146/61904 [3:00:06<14:16:28,  1.44s/it]
 42%|████▏     | 26147/61904 [3:00:07<14:05:29,  1.42s/it]
 42%|████▏     | 26148/61904 [3:00:08<14:08:43,  1.42s/it]
 42%|████▏     | 26149/61904 [3:00:10<14:10:42,  1.43s/it]
 42%|████▏     | 26150/61904 [3:00:11<14:06:26,  1.42s/it]
 42%|████▏     | 26151/61904 [3:00:13<13:49:15,  1.39s/it]
 42%|████▏     | 26152/61904 [3:00:14<14:21:02,  1.45s/it]
 42%|████▏     | 26153/61904 [3:00:16<14:23:14,  1.45s/it]
 42%|████▏     | 26154/61904 [3:00:17<13:56:37,  1.40s/it]
 42%|████▏     | 26155/61904 [3:00:18<14:30:40,  1.46s/it]
 42%|████▏     | 26156/61904 [3:00:20<13:59:15,  1.41s/it]
 42%|████▏     | 26157/61904 [3:00:21<13:46:49,  1.39s/it]
 42%|████▏     | 26158/61904 [3:00:22<13:44:37,  1.38s/it]
 42%|████▏     | 26159/61904 [3:00:24<13:41:25,  1.38s/it]
 42%|████▏     | 26160/61904 [3:00:25<14:26:03,  1.45s/it]
                                                          
{'loss': 2.6226, 'learning_rate': 1.5792817321405417e-07, 'epoch': 6.76}

 42%|████▏     | 26160/61904 [3:00:25<14:26:03,  1.45s/it]
 42%|████▏     | 26161/61904 [3:00:27<14:17:13,  1.44s/it]
 42%|████▏     | 26162/61904 [3:00:28<13:50:01,  1.39s/it]
 42%|████▏     | 26163/61904 [3:00:29<13:31:28,  1.36s/it]
 42%|████▏     | 26164/61904 [3:00:31<13:21:04,  1.34s/it]
 42%|████▏     | 26165/61904 [3:00:32<13:43:33,  1.38s/it]
 42%|████▏     | 26166/61904 [3:00:34<13:33:56,  1.37s/it]
 42%|████▏     | 26167/61904 [3:00:35<13:40:43,  1.38s/it]
 42%|████▏     | 26168/61904 [3:00:37<14:36:22,  1.47s/it]
 42%|████▏     | 26169/61904 [3:00:38<14:23:16,  1.45s/it]
 42%|████▏     | 26170/61904 [3:00:39<13:53:00,  1.40s/it]
 42%|████▏     | 26171/61904 [3:00:40<13:07:28,  1.32s/it]
 42%|████▏     | 26172/61904 [3:00:42<13:10:44,  1.33s/it]
 42%|████▏     | 26173/61904 [3:00:43<13:06:01,  1.32s/it]
 42%|████▏     | 26174/61904 [3:00:45<13:20:19,  1.34s/it]
 42%|████▏     | 26175/61904 [3:00:46<13:40:31,  1.38s/it]
 42%|████▏     | 26176/61904 [3:00:47<13:22:45,  1.35s/it]
 42%|████▏     | 26177/61904 [3:00:49<13:25:11,  1.35s/it]
 42%|████▏     | 26178/61904 [3:00:50<13:25:52,  1.35s/it]
 42%|████▏     | 26179/61904 [3:00:51<13:26:22,  1.35s/it]
 42%|████▏     | 26180/61904 [3:00:53<13:36:33,  1.37s/it]
                                                          
{'loss': 2.6313, 'learning_rate': 1.5789576040451186e-07, 'epoch': 6.77}

 42%|████▏     | 26180/61904 [3:00:53<13:36:33,  1.37s/it]
 42%|████▏     | 26181/61904 [3:00:54<13:42:30,  1.38s/it]
 42%|████▏     | 26182/61904 [3:00:56<13:38:56,  1.38s/it]
 42%|████▏     | 26183/61904 [3:00:57<13:48:07,  1.39s/it]
 42%|████▏     | 26184/61904 [3:00:58<13:38:04,  1.37s/it]
 42%|████▏     | 26185/61904 [3:01:00<14:06:28,  1.42s/it]
 42%|████▏     | 26186/61904 [3:01:01<13:48:45,  1.39s/it]
 42%|████▏     | 26187/61904 [3:01:03<13:58:02,  1.41s/it]
 42%|████▏     | 26188/61904 [3:01:04<13:42:17,  1.38s/it]
 42%|████▏     | 26189/61904 [3:01:05<13:40:52,  1.38s/it]
 42%|████▏     | 26190/61904 [3:01:07<14:11:48,  1.43s/it]
 42%|████▏     | 26191/61904 [3:01:08<13:59:20,  1.41s/it]
 42%|████▏     | 26192/61904 [3:01:09<13:36:42,  1.37s/it]
 42%|████▏     | 26193/61904 [3:01:11<13:53:38,  1.40s/it]
 42%|████▏     | 26194/61904 [3:01:12<14:05:16,  1.42s/it]
 42%|████▏     | 26195/61904 [3:01:14<14:17:41,  1.44s/it]
 42%|████▏     | 26196/61904 [3:01:15<13:49:30,  1.39s/it]
 42%|████▏     | 26197/61904 [3:01:17<14:11:07,  1.43s/it]
 42%|████▏     | 26198/61904 [3:01:18<13:57:18,  1.41s/it]
 42%|████▏     | 26199/61904 [3:01:19<13:50:02,  1.39s/it]
 42%|████▏     | 26200/61904 [3:01:21<13:44:25,  1.39s/it]
                                                          
{'loss': 2.5891, 'learning_rate': 1.5786334759496952e-07, 'epoch': 6.77}

 42%|████▏     | 26200/61904 [3:01:21<13:44:25,  1.39s/it]
 42%|████▏     | 26201/61904 [3:01:22<13:29:27,  1.36s/it]
 42%|████▏     | 26202/61904 [3:01:23<13:40:27,  1.38s/it]
 42%|████▏     | 26203/61904 [3:01:25<13:48:47,  1.39s/it]
 42%|████▏     | 26204/61904 [3:01:26<13:38:34,  1.38s/it]
 42%|████▏     | 26205/61904 [3:01:28<13:35:30,  1.37s/it]
 42%|████▏     | 26206/61904 [3:01:29<13:39:54,  1.38s/it]
 42%|████▏     | 26207/61904 [3:01:30<13:50:36,  1.40s/it]
 42%|████▏     | 26208/61904 [3:01:32<13:52:24,  1.40s/it]
 42%|████▏     | 26209/61904 [3:01:33<13:40:13,  1.38s/it]
 42%|████▏     | 26210/61904 [3:01:34<13:17:01,  1.34s/it]
 42%|████▏     | 26211/61904 [3:01:36<13:23:17,  1.35s/it]
 42%|████▏     | 26212/61904 [3:01:37<13:25:39,  1.35s/it]
 42%|████▏     | 26213/61904 [3:01:39<13:40:42,  1.38s/it]
 42%|████▏     | 26214/61904 [3:01:40<14:07:47,  1.43s/it]
 42%|████▏     | 26215/61904 [3:01:41<13:52:04,  1.40s/it]
 42%|████▏     | 26216/61904 [3:01:43<13:53:53,  1.40s/it]
 42%|████▏     | 26217/61904 [3:01:44<13:49:52,  1.40s/it]
 42%|████▏     | 26218/61904 [3:01:46<13:38:18,  1.38s/it]
 42%|████▏     | 26219/61904 [3:01:47<13:32:26,  1.37s/it]
 42%|████▏     | 26220/61904 [3:01:48<13:40:35,  1.38s/it]
                                                          
{'loss': 2.5806, 'learning_rate': 1.5783093478542719e-07, 'epoch': 6.78}

 42%|████▏     | 26220/61904 [3:01:48<13:40:35,  1.38s/it]
 42%|████▏     | 26221/61904 [3:01:50<13:43:26,  1.38s/it]
 42%|████▏     | 26222/61904 [3:01:51<13:46:01,  1.39s/it]
 42%|████▏     | 26223/61904 [3:01:53<13:58:27,  1.41s/it]
 42%|████▏     | 26224/61904 [3:01:54<13:41:50,  1.38s/it]
 42%|████▏     | 26225/61904 [3:01:55<13:58:20,  1.41s/it]
 42%|████▏     | 26226/61904 [3:01:57<13:58:52,  1.41s/it]
 42%|████▏     | 26227/61904 [3:01:58<13:57:26,  1.41s/it]
 42%|████▏     | 26228/61904 [3:02:00<13:36:03,  1.37s/it]
 42%|████▏     | 26229/61904 [3:02:01<13:48:14,  1.39s/it]
 42%|████▏     | 26230/61904 [3:02:02<13:59:34,  1.41s/it]
 42%|████▏     | 26231/61904 [3:02:04<13:29:16,  1.36s/it]
 42%|████▏     | 26232/61904 [3:02:05<13:26:20,  1.36s/it]
 42%|████▏     | 26233/61904 [3:02:06<13:20:50,  1.35s/it]
 42%|████▏     | 26234/61904 [3:02:08<13:23:47,  1.35s/it]
 42%|████▏     | 26235/61904 [3:02:09<13:22:02,  1.35s/it]
 42%|████▏     | 26236/61904 [3:02:11<13:45:15,  1.39s/it]
 42%|████▏     | 26237/61904 [3:02:12<13:40:38,  1.38s/it]
 42%|████▏     | 26238/61904 [3:02:13<13:38:19,  1.38s/it]
 42%|████▏     | 26239/61904 [3:02:15<13:40:33,  1.38s/it]
 42%|████▏     | 26240/61904 [3:02:16<13:32:57,  1.37s/it]
                                                          
{'loss': 2.5518, 'learning_rate': 1.5779852197588485e-07, 'epoch': 6.78}

 42%|████▏     | 26240/61904 [3:02:16<13:32:57,  1.37s/it]
 42%|████▏     | 26241/61904 [3:02:17<13:33:53,  1.37s/it]
 42%|████▏     | 26242/61904 [3:02:19<13:33:58,  1.37s/it]
 42%|████▏     | 26243/61904 [3:02:20<14:20:14,  1.45s/it]
 42%|████▏     | 26244/61904 [3:02:22<14:36:06,  1.47s/it]
 42%|████▏     | 26245/61904 [3:02:23<14:22:25,  1.45s/it]
 42%|████▏     | 26246/61904 [3:02:25<13:53:30,  1.40s/it]
 42%|████▏     | 26247/61904 [3:02:26<13:44:41,  1.39s/it]
 42%|████▏     | 26248/61904 [3:02:27<14:07:31,  1.43s/it]
 42%|████▏     | 26249/61904 [3:02:29<14:12:10,  1.43s/it]
 42%|████▏     | 26250/61904 [3:02:30<14:20:02,  1.45s/it]
 42%|████▏     | 26251/61904 [3:02:32<14:13:13,  1.44s/it]
 42%|████▏     | 26252/61904 [3:02:33<14:14:54,  1.44s/it]
 42%|████▏     | 26253/61904 [3:02:35<14:10:42,  1.43s/it]
 42%|████▏     | 26254/61904 [3:02:36<14:44:35,  1.49s/it]
 42%|████▏     | 26255/61904 [3:02:38<15:11:08,  1.53s/it]
 42%|████▏     | 26256/61904 [3:02:39<14:23:30,  1.45s/it]
 42%|████▏     | 26257/61904 [3:02:41<14:27:07,  1.46s/it]
 42%|████▏     | 26258/61904 [3:02:42<14:12:36,  1.44s/it]
 42%|████▏     | 26259/61904 [3:02:43<13:59:38,  1.41s/it]
 42%|████▏     | 26260/61904 [3:02:45<14:06:08,  1.42s/it]
                                                          
{'loss': 2.6104, 'learning_rate': 1.5776610916634254e-07, 'epoch': 6.79}

 42%|████▏     | 26260/61904 [3:02:45<14:06:08,  1.42s/it]
 42%|████▏     | 26261/61904 [3:02:46<13:37:04,  1.38s/it]
 42%|████▏     | 26262/61904 [3:02:48<13:59:57,  1.41s/it]
 42%|████▏     | 26263/61904 [3:02:49<13:42:12,  1.38s/it]
 42%|████▏     | 26264/61904 [3:02:50<13:19:35,  1.35s/it]
 42%|████▏     | 26265/61904 [3:02:52<13:30:54,  1.37s/it]
 42%|████▏     | 26266/61904 [3:02:53<13:13:11,  1.34s/it]
 42%|████▏     | 26267/61904 [3:02:54<13:14:55,  1.34s/it]
 42%|████▏     | 26268/61904 [3:02:55<13:10:09,  1.33s/it]
 42%|████▏     | 26269/61904 [3:02:57<13:47:04,  1.39s/it]
 42%|████▏     | 26270/61904 [3:02:58<13:28:21,  1.36s/it]
 42%|████▏     | 26271/61904 [3:03:00<13:25:46,  1.36s/it]
 42%|████▏     | 26272/61904 [3:03:01<13:19:22,  1.35s/it]
 42%|████▏     | 26273/61904 [3:03:02<13:07:50,  1.33s/it]
 42%|████▏     | 26274/61904 [3:03:04<13:14:51,  1.34s/it]
 42%|████▏     | 26275/61904 [3:03:05<13:03:13,  1.32s/it]
 42%|████▏     | 26276/61904 [3:03:06<13:09:24,  1.33s/it]
 42%|████▏     | 26277/61904 [3:03:08<13:12:33,  1.33s/it]
 42%|████▏     | 26278/61904 [3:03:09<13:17:22,  1.34s/it]
 42%|████▏     | 26279/61904 [3:03:10<13:24:00,  1.35s/it]
 42%|████▏     | 26280/61904 [3:03:12<13:14:09,  1.34s/it]
                                                          
{'loss': 2.6052, 'learning_rate': 1.577336963568002e-07, 'epoch': 6.79}

 42%|████▏     | 26280/61904 [3:03:12<13:14:09,  1.34s/it]
 42%|████▏     | 26281/61904 [3:03:13<13:01:11,  1.32s/it]
 42%|████▏     | 26282/61904 [3:03:14<12:48:08,  1.29s/it]
 42%|████▏     | 26283/61904 [3:03:15<12:48:29,  1.29s/it]
 42%|████▏     | 26284/61904 [3:03:17<12:56:47,  1.31s/it]
 42%|████▏     | 26285/61904 [3:03:18<13:05:29,  1.32s/it]
 42%|████▏     | 26286/61904 [3:03:20<13:36:29,  1.38s/it]
 42%|████▏     | 26287/61904 [3:03:21<13:37:11,  1.38s/it]
 42%|████▏     | 26288/61904 [3:03:22<13:25:34,  1.36s/it]
 42%|████▏     | 26289/61904 [3:03:24<13:09:27,  1.33s/it]
 42%|████▏     | 26290/61904 [3:03:25<13:03:33,  1.32s/it]
 42%|████▏     | 26291/61904 [3:03:26<13:17:37,  1.34s/it]
 42%|████▏     | 26292/61904 [3:03:28<13:37:48,  1.38s/it]
 42%|████▏     | 26293/61904 [3:03:29<13:28:44,  1.36s/it]
 42%|████▏     | 26294/61904 [3:03:31<13:40:32,  1.38s/it]
 42%|████▏     | 26295/61904 [3:03:32<13:45:48,  1.39s/it]
 42%|████▏     | 26296/61904 [3:03:33<13:38:33,  1.38s/it]
 42%|████▏     | 26297/61904 [3:03:35<13:27:25,  1.36s/it]
 42%|████▏     | 26298/61904 [3:03:36<13:30:31,  1.37s/it]
 42%|████▏     | 26299/61904 [3:03:37<13:20:08,  1.35s/it]
 42%|████▏     | 26300/61904 [3:03:39<13:11:44,  1.33s/it]
                                                          
{'loss': 2.5845, 'learning_rate': 1.5770128354725786e-07, 'epoch': 6.8}

 42%|████▏     | 26300/61904 [3:03:39<13:11:44,  1.33s/it]
 42%|████▏     | 26301/61904 [3:03:40<13:19:52,  1.35s/it]
 42%|████▏     | 26302/61904 [3:03:41<13:33:36,  1.37s/it]
 42%|████▏     | 26303/61904 [3:03:43<13:35:27,  1.37s/it]
 42%|████▏     | 26304/61904 [3:03:44<13:22:41,  1.35s/it]
 42%|████▏     | 26305/61904 [3:03:46<13:44:27,  1.39s/it]
 42%|████▏     | 26306/61904 [3:03:47<14:06:50,  1.43s/it]
 42%|████▏     | 26307/61904 [3:03:48<13:41:59,  1.39s/it]
 42%|████▏     | 26308/61904 [3:03:50<13:41:47,  1.39s/it]
 42%|████▏     | 26309/61904 [3:03:51<13:49:36,  1.40s/it]
 43%|████▎     | 26310/61904 [3:03:52<13:38:29,  1.38s/it]
 43%|████▎     | 26311/61904 [3:03:54<14:05:00,  1.42s/it]
 43%|████▎     | 26312/61904 [3:03:55<13:53:16,  1.40s/it]
 43%|████▎     | 26313/61904 [3:03:57<13:29:41,  1.36s/it]
 43%|████▎     | 26314/61904 [3:03:58<13:43:50,  1.39s/it]
 43%|████▎     | 26315/61904 [3:04:00<13:51:06,  1.40s/it]
 43%|████▎     | 26316/61904 [3:04:01<14:04:21,  1.42s/it]
 43%|████▎     | 26317/61904 [3:04:03<14:19:10,  1.45s/it]
 43%|████▎     | 26318/61904 [3:04:04<14:22:04,  1.45s/it]
 43%|████▎     | 26319/61904 [3:04:05<14:23:50,  1.46s/it]
 43%|████▎     | 26320/61904 [3:04:07<14:22:15,  1.45s/it]
                                                          
{'loss': 2.6096, 'learning_rate': 1.5766887073771552e-07, 'epoch': 6.8}

 43%|████▎     | 26320/61904 [3:04:07<14:22:15,  1.45s/it]
 43%|████▎     | 26321/61904 [3:04:08<14:13:16,  1.44s/it]
 43%|████▎     | 26322/61904 [3:04:10<14:09:58,  1.43s/it]
 43%|████▎     | 26323/61904 [3:04:11<14:02:16,  1.42s/it]
 43%|████▎     | 26324/61904 [3:04:13<14:14:32,  1.44s/it]
 43%|████▎     | 26325/61904 [3:04:14<14:33:09,  1.47s/it]
 43%|████▎     | 26326/61904 [3:04:16<14:24:58,  1.46s/it]
 43%|████▎     | 26327/61904 [3:04:17<14:28:01,  1.46s/it]
 43%|████▎     | 26328/61904 [3:04:18<14:22:54,  1.46s/it]
 43%|████▎     | 26329/61904 [3:04:20<14:25:23,  1.46s/it]
 43%|████▎     | 26330/61904 [3:04:21<14:27:44,  1.46s/it]
 43%|████▎     | 26331/61904 [3:04:23<14:21:22,  1.45s/it]
 43%|████▎     | 26332/61904 [3:04:24<14:03:35,  1.42s/it]
 43%|████▎     | 26333/61904 [3:04:26<14:20:35,  1.45s/it]
 43%|████▎     | 26334/61904 [3:04:27<13:53:20,  1.41s/it]
 43%|████▎     | 26335/61904 [3:04:28<13:39:24,  1.38s/it]
 43%|████▎     | 26336/61904 [3:04:30<14:23:54,  1.46s/it]
 43%|████▎     | 26337/61904 [3:04:31<14:11:44,  1.44s/it]
 43%|████▎     | 26338/61904 [3:04:33<13:40:04,  1.38s/it]
 43%|████▎     | 26339/61904 [3:04:34<13:18:57,  1.35s/it]
 43%|████▎     | 26340/61904 [3:04:35<13:16:12,  1.34s/it]
                                                          
{'loss': 2.5916, 'learning_rate': 1.576364579281732e-07, 'epoch': 6.81}

 43%|████▎     | 26340/61904 [3:04:35<13:16:12,  1.34s/it]
 43%|████▎     | 26341/61904 [3:04:37<13:40:32,  1.38s/it]
 43%|████▎     | 26342/61904 [3:04:38<13:22:14,  1.35s/it]
 43%|████▎     | 26343/61904 [3:04:39<13:13:15,  1.34s/it]
 43%|████▎     | 26344/61904 [3:04:41<13:27:53,  1.36s/it]
 43%|████▎     | 26345/61904 [3:04:42<13:04:08,  1.32s/it]
 43%|████▎     | 26346/61904 [3:04:43<12:55:14,  1.31s/it]
 43%|████▎     | 26347/61904 [3:04:45<13:16:52,  1.34s/it]
 43%|████▎     | 26348/61904 [3:04:46<13:39:13,  1.38s/it]
 43%|████▎     | 26349/61904 [3:04:47<13:33:42,  1.37s/it]
 43%|████▎     | 26350/61904 [3:04:49<13:50:40,  1.40s/it]
 43%|████▎     | 26351/61904 [3:04:50<14:03:26,  1.42s/it]
 43%|████▎     | 26352/61904 [3:04:52<13:44:12,  1.39s/it]
 43%|████▎     | 26353/61904 [3:04:53<13:52:20,  1.40s/it]
 43%|████▎     | 26354/61904 [3:04:54<13:33:56,  1.37s/it]
 43%|████▎     | 26355/61904 [3:04:56<13:21:13,  1.35s/it]
 43%|████▎     | 26356/61904 [3:04:57<13:00:41,  1.32s/it]
 43%|████▎     | 26357/61904 [3:04:58<12:57:25,  1.31s/it]
 43%|████▎     | 26358/61904 [3:05:00<13:05:39,  1.33s/it]
 43%|████▎     | 26359/61904 [3:05:01<13:02:49,  1.32s/it]
 43%|████▎     | 26360/61904 [3:05:02<13:17:49,  1.35s/it]
                                                          
{'loss': 2.584, 'learning_rate': 1.5760404511863087e-07, 'epoch': 6.81}

 43%|████▎     | 26360/61904 [3:05:02<13:17:49,  1.35s/it]
 43%|████▎     | 26361/61904 [3:05:04<14:00:47,  1.42s/it]
 43%|████▎     | 26362/61904 [3:05:05<14:19:13,  1.45s/it]
 43%|████▎     | 26363/61904 [3:05:07<14:12:59,  1.44s/it]
 43%|████▎     | 26364/61904 [3:05:08<14:32:16,  1.47s/it]
 43%|████▎     | 26365/61904 [3:05:10<14:16:46,  1.45s/it]
 43%|████▎     | 26366/61904 [3:05:11<14:05:07,  1.43s/it]
 43%|████▎     | 26367/61904 [3:05:13<14:08:03,  1.43s/it]
 43%|████▎     | 26368/61904 [3:05:14<14:03:20,  1.42s/it]
 43%|████▎     | 26369/61904 [3:05:15<13:41:37,  1.39s/it]
 43%|████▎     | 26370/61904 [3:05:17<13:48:35,  1.40s/it]
 43%|████▎     | 26371/61904 [3:05:18<13:29:09,  1.37s/it]
 43%|████▎     | 26372/61904 [3:05:20<13:46:31,  1.40s/it]
 43%|████▎     | 26373/61904 [3:05:21<13:19:42,  1.35s/it]
 43%|████▎     | 26374/61904 [3:05:22<13:37:46,  1.38s/it]
 43%|████▎     | 26375/61904 [3:05:24<13:58:00,  1.42s/it]
 43%|████▎     | 26376/61904 [3:05:25<13:55:02,  1.41s/it]
 43%|████▎     | 26377/61904 [3:05:27<13:55:28,  1.41s/it]
 43%|████▎     | 26378/61904 [3:05:28<14:04:26,  1.43s/it]
 43%|████▎     | 26379/61904 [3:05:29<13:38:25,  1.38s/it]
 43%|████▎     | 26380/61904 [3:05:31<13:12:56,  1.34s/it]
                                                          
{'loss': 2.6194, 'learning_rate': 1.5757163230908853e-07, 'epoch': 6.82}

 43%|████▎     | 26380/61904 [3:05:31<13:12:56,  1.34s/it]
 43%|████▎     | 26381/61904 [3:05:32<12:56:56,  1.31s/it]
 43%|████▎     | 26382/61904 [3:05:33<12:49:50,  1.30s/it]
 43%|████▎     | 26383/61904 [3:05:34<13:00:43,  1.32s/it]
 43%|████▎     | 26384/61904 [3:05:36<12:39:50,  1.28s/it]
 43%|████▎     | 26385/61904 [3:05:37<12:27:44,  1.26s/it]
 43%|████▎     | 26386/61904 [3:05:38<12:41:02,  1.29s/it]
 43%|████▎     | 26387/61904 [3:05:39<12:43:30,  1.29s/it]
 43%|████▎     | 26388/61904 [3:05:41<12:45:09,  1.29s/it]
 43%|████▎     | 26389/61904 [3:05:42<12:40:45,  1.29s/it]
 43%|████▎     | 26390/61904 [3:05:43<12:54:39,  1.31s/it]
 43%|████▎     | 26391/61904 [3:05:45<12:58:34,  1.32s/it]
 43%|████▎     | 26392/61904 [3:05:46<13:11:17,  1.34s/it]
 43%|████▎     | 26393/61904 [3:05:47<13:09:42,  1.33s/it]
 43%|████▎     | 26394/61904 [3:05:49<12:58:06,  1.31s/it]
 43%|████▎     | 26395/61904 [3:05:50<13:13:22,  1.34s/it]
 43%|████▎     | 26396/61904 [3:05:52<13:38:46,  1.38s/it]
 43%|████▎     | 26397/61904 [3:05:53<13:41:21,  1.39s/it]
 43%|████▎     | 26398/61904 [3:05:54<14:00:00,  1.42s/it]
 43%|████▎     | 26399/61904 [3:05:56<13:31:27,  1.37s/it]
 43%|████▎     | 26400/61904 [3:05:57<13:21:16,  1.35s/it]
                                                          
{'loss': 2.6581, 'learning_rate': 1.575392194995462e-07, 'epoch': 6.82}

 43%|████▎     | 26400/61904 [3:05:57<13:21:16,  1.35s/it]
 43%|████▎     | 26401/61904 [3:05:58<13:18:22,  1.35s/it]
 43%|████▎     | 26402/61904 [3:06:00<13:33:28,  1.37s/it]
 43%|████▎     | 26403/61904 [3:06:01<13:20:47,  1.35s/it]
 43%|████▎     | 26404/61904 [3:06:02<12:56:40,  1.31s/it]
 43%|████▎     | 26405/61904 [3:06:04<12:52:57,  1.31s/it]
 43%|████▎     | 26406/61904 [3:06:05<12:55:09,  1.31s/it]
 43%|████▎     | 26407/61904 [3:06:06<12:46:50,  1.30s/it]
 43%|████▎     | 26408/61904 [3:06:08<13:00:04,  1.32s/it]
 43%|████▎     | 26409/61904 [3:06:09<12:53:45,  1.31s/it]
 43%|████▎     | 26410/61904 [3:06:10<13:01:39,  1.32s/it]
 43%|████▎     | 26411/61904 [3:06:12<13:04:07,  1.33s/it]
 43%|████▎     | 26412/61904 [3:06:13<13:43:04,  1.39s/it]
 43%|████▎     | 26413/61904 [3:06:14<13:06:21,  1.33s/it]
 43%|████▎     | 26414/61904 [3:06:16<13:25:06,  1.36s/it]
 43%|████▎     | 26415/61904 [3:06:17<13:23:25,  1.36s/it]
 43%|████▎     | 26416/61904 [3:06:18<13:02:48,  1.32s/it]
 43%|████▎     | 26417/61904 [3:06:20<13:09:06,  1.33s/it]
 43%|████▎     | 26418/61904 [3:06:21<13:44:30,  1.39s/it]
 43%|████▎     | 26419/61904 [3:06:23<13:33:46,  1.38s/it]
 43%|████▎     | 26420/61904 [3:06:24<13:22:09,  1.36s/it]
                                                          
{'loss': 2.6636, 'learning_rate': 1.5750680669000388e-07, 'epoch': 6.83}

 43%|████▎     | 26420/61904 [3:06:24<13:22:09,  1.36s/it]
 43%|████▎     | 26421/61904 [3:06:25<14:10:18,  1.44s/it]
 43%|████▎     | 26422/61904 [3:06:27<13:57:08,  1.42s/it]
 43%|████▎     | 26423/61904 [3:06:28<13:59:59,  1.42s/it]
 43%|████▎     | 26424/61904 [3:06:30<13:34:25,  1.38s/it]
 43%|████▎     | 26425/61904 [3:06:31<13:06:08,  1.33s/it]
 43%|████▎     | 26426/61904 [3:06:32<13:31:16,  1.37s/it]
 43%|████▎     | 26427/61904 [3:06:33<13:01:29,  1.32s/it]
 43%|████▎     | 26428/61904 [3:06:35<12:46:26,  1.30s/it]
 43%|████▎     | 26429/61904 [3:06:36<13:38:10,  1.38s/it]
 43%|████▎     | 26430/61904 [3:06:38<13:20:07,  1.35s/it]
 43%|████▎     | 26431/61904 [3:06:39<13:10:45,  1.34s/it]
 43%|████▎     | 26432/61904 [3:06:40<13:13:53,  1.34s/it]
 43%|████▎     | 26433/61904 [3:06:42<13:06:13,  1.33s/it]
 43%|████▎     | 26434/61904 [3:06:43<12:56:20,  1.31s/it]
 43%|████▎     | 26435/61904 [3:06:44<13:19:01,  1.35s/it]
 43%|████▎     | 26436/61904 [3:06:46<13:17:41,  1.35s/it]
 43%|████▎     | 26437/61904 [3:06:47<13:18:27,  1.35s/it]
 43%|████▎     | 26438/61904 [3:06:48<12:53:43,  1.31s/it]
 43%|████▎     | 26439/61904 [3:06:49<12:34:49,  1.28s/it]
 43%|████▎     | 26440/61904 [3:06:51<12:51:43,  1.31s/it]
                                                          
{'loss': 2.6135, 'learning_rate': 1.5747439388046155e-07, 'epoch': 6.83}

 43%|████▎     | 26440/61904 [3:06:51<12:51:43,  1.31s/it]
 43%|████▎     | 26441/61904 [3:06:52<13:24:44,  1.36s/it]
 43%|████▎     | 26442/61904 [3:06:54<13:29:35,  1.37s/it]
 43%|████▎     | 26443/61904 [3:06:55<13:45:33,  1.40s/it]
 43%|████▎     | 26444/61904 [3:06:56<13:42:02,  1.39s/it]
 43%|████▎     | 26445/61904 [3:06:58<13:19:50,  1.35s/it]
 43%|████▎     | 26446/61904 [3:06:59<13:18:22,  1.35s/it]
 43%|████▎     | 26447/61904 [3:07:00<13:10:57,  1.34s/it]
 43%|████▎     | 26448/61904 [3:07:02<13:32:25,  1.37s/it]
 43%|████▎     | 26449/61904 [3:07:03<13:17:26,  1.35s/it]
 43%|████▎     | 26450/61904 [3:07:05<13:50:23,  1.41s/it]
 43%|████▎     | 26451/61904 [3:07:06<13:46:05,  1.40s/it]
 43%|████▎     | 26452/61904 [3:07:07<13:48:18,  1.40s/it]
 43%|████▎     | 26453/61904 [3:07:09<13:23:37,  1.36s/it]
 43%|████▎     | 26454/61904 [3:07:10<13:49:36,  1.40s/it]
 43%|████▎     | 26455/61904 [3:07:12<13:34:26,  1.38s/it]
 43%|████▎     | 26456/61904 [3:07:13<13:42:58,  1.39s/it]
 43%|████▎     | 26457/61904 [3:07:14<13:44:43,  1.40s/it]
 43%|████▎     | 26458/61904 [3:07:16<13:31:26,  1.37s/it]
 43%|████▎     | 26459/61904 [3:07:17<13:31:35,  1.37s/it]
 43%|████▎     | 26460/61904 [3:07:18<13:22:02,  1.36s/it]
                                                          
{'loss': 2.609, 'learning_rate': 1.574419810709192e-07, 'epoch': 6.84}

 43%|████▎     | 26460/61904 [3:07:18<13:22:02,  1.36s/it]
 43%|████▎     | 26461/61904 [3:07:20<13:12:58,  1.34s/it]
 43%|████▎     | 26462/61904 [3:07:21<13:39:48,  1.39s/it]
 43%|████▎     | 26463/61904 [3:07:22<13:20:53,  1.36s/it]
 43%|████▎     | 26464/61904 [3:07:24<13:26:19,  1.37s/it]
 43%|████▎     | 26465/61904 [3:07:25<13:13:02,  1.34s/it]
 43%|████▎     | 26466/61904 [3:07:26<13:16:08,  1.35s/it]
 43%|████▎     | 26467/61904 [3:07:28<13:21:46,  1.36s/it]
 43%|████▎     | 26468/61904 [3:07:29<13:40:29,  1.39s/it]
 43%|████▎     | 26469/61904 [3:07:31<13:22:52,  1.36s/it]
 43%|████▎     | 26470/61904 [3:07:32<13:14:40,  1.35s/it]
 43%|████▎     | 26471/61904 [3:07:33<13:32:40,  1.38s/it]
 43%|████▎     | 26472/61904 [3:07:35<13:28:37,  1.37s/it]
 43%|████▎     | 26473/61904 [3:07:36<13:35:22,  1.38s/it]
 43%|████▎     | 26474/61904 [3:07:38<13:53:41,  1.41s/it]
 43%|████▎     | 26475/61904 [3:07:39<13:41:08,  1.39s/it]
 43%|████▎     | 26476/61904 [3:07:40<13:45:44,  1.40s/it]
 43%|████▎     | 26477/61904 [3:07:42<13:10:46,  1.34s/it]
 43%|████▎     | 26478/61904 [3:07:43<13:14:45,  1.35s/it]
 43%|████▎     | 26479/61904 [3:07:44<13:26:43,  1.37s/it]
 43%|████▎     | 26480/61904 [3:07:46<13:24:08,  1.36s/it]
                                                          
{'loss': 2.6168, 'learning_rate': 1.574095682613769e-07, 'epoch': 6.84}

 43%|████▎     | 26480/61904 [3:07:46<13:24:08,  1.36s/it]
 43%|████▎     | 26481/61904 [3:07:47<13:27:47,  1.37s/it]
 43%|████▎     | 26482/61904 [3:07:48<13:24:02,  1.36s/it]
 43%|████▎     | 26483/61904 [3:07:50<13:18:35,  1.35s/it]
 43%|████▎     | 26484/61904 [3:07:51<13:08:26,  1.34s/it]
 43%|████▎     | 26485/61904 [3:07:52<13:22:41,  1.36s/it]
 43%|████▎     | 26486/61904 [3:07:54<13:32:53,  1.38s/it]
 43%|████▎     | 26487/61904 [3:07:55<13:49:26,  1.41s/it]
 43%|████▎     | 26488/61904 [3:07:57<13:58:33,  1.42s/it]
 43%|████▎     | 26489/61904 [3:07:58<13:41:32,  1.39s/it]
 43%|████▎     | 26490/61904 [3:08:00<13:52:40,  1.41s/it]
 43%|████▎     | 26491/61904 [3:08:01<14:09:18,  1.44s/it]
 43%|████▎     | 26492/61904 [3:08:02<13:48:07,  1.40s/it]
 43%|████▎     | 26493/61904 [3:08:04<14:14:52,  1.45s/it]
 43%|████▎     | 26494/61904 [3:08:05<14:23:25,  1.46s/it]
 43%|████▎     | 26495/61904 [3:08:07<14:14:49,  1.45s/it]
 43%|████▎     | 26496/61904 [3:08:08<13:52:55,  1.41s/it]
 43%|████▎     | 26497/61904 [3:08:10<13:32:46,  1.38s/it]
 43%|████▎     | 26498/61904 [3:08:11<13:19:54,  1.36s/it]
 43%|████▎     | 26499/61904 [3:08:12<13:13:45,  1.35s/it]
 43%|████▎     | 26500/61904 [3:08:13<13:04:54,  1.33s/it]
                                                          
{'loss': 2.5408, 'learning_rate': 1.5737715545183456e-07, 'epoch': 6.85}

 43%|████▎     | 26500/61904 [3:08:13<13:04:54,  1.33s/it]
 43%|████▎     | 26501/61904 [3:08:15<12:38:07,  1.28s/it]
 43%|████▎     | 26502/61904 [3:08:16<12:51:22,  1.31s/it]
 43%|████▎     | 26503/61904 [3:08:17<12:34:08,  1.28s/it]
 43%|████▎     | 26504/61904 [3:08:19<12:40:34,  1.29s/it]
 43%|████▎     | 26505/61904 [3:08:20<12:41:45,  1.29s/it]
 43%|████▎     | 26506/61904 [3:08:21<12:22:02,  1.26s/it]
 43%|████▎     | 26507/61904 [3:08:22<12:47:36,  1.30s/it]
 43%|████▎     | 26508/61904 [3:08:24<13:38:16,  1.39s/it]
 43%|████▎     | 26509/61904 [3:08:25<13:31:21,  1.38s/it]
 43%|████▎     | 26510/61904 [3:08:27<13:26:46,  1.37s/it]
 43%|████▎     | 26511/61904 [3:08:28<13:13:33,  1.35s/it]
 43%|████▎     | 26512/61904 [3:08:29<13:27:06,  1.37s/it]
 43%|████▎     | 26513/61904 [3:08:31<13:29:03,  1.37s/it]
 43%|████▎     | 26514/61904 [3:08:32<13:51:21,  1.41s/it]
 43%|████▎     | 26515/61904 [3:08:34<13:45:40,  1.40s/it]
 43%|████▎     | 26516/61904 [3:08:35<13:48:59,  1.41s/it]
 43%|████▎     | 26517/61904 [3:08:37<14:07:50,  1.44s/it]
 43%|████▎     | 26518/61904 [3:08:38<13:41:34,  1.39s/it]
 43%|████▎     | 26519/61904 [3:08:40<14:46:55,  1.50s/it]
 43%|████▎     | 26520/61904 [3:08:41<14:48:28,  1.51s/it]
                                                          
{'loss': 2.6252, 'learning_rate': 1.5734474264229222e-07, 'epoch': 6.85}

 43%|████▎     | 26520/61904 [3:08:41<14:48:28,  1.51s/it]
 43%|████▎     | 26521/61904 [3:08:42<14:20:26,  1.46s/it]
 43%|████▎     | 26522/61904 [3:08:44<14:04:03,  1.43s/it]
 43%|████▎     | 26523/61904 [3:08:45<14:03:59,  1.43s/it]
 43%|████▎     | 26524/61904 [3:08:47<13:49:54,  1.41s/it]
 43%|████▎     | 26525/61904 [3:08:48<13:30:24,  1.37s/it]
 43%|████▎     | 26526/61904 [3:08:49<13:32:56,  1.38s/it]
 43%|████▎     | 26527/61904 [3:08:51<13:20:55,  1.36s/it]
 43%|████▎     | 26528/61904 [3:08:52<13:30:17,  1.37s/it]
 43%|████▎     | 26529/61904 [3:08:53<13:02:56,  1.33s/it]
 43%|████▎     | 26530/61904 [3:08:55<12:47:10,  1.30s/it]
 43%|████▎     | 26531/61904 [3:08:56<12:44:43,  1.30s/it]
 43%|████▎     | 26532/61904 [3:08:57<12:33:02,  1.28s/it]
 43%|████▎     | 26533/61904 [3:08:58<12:47:05,  1.30s/it]
 43%|████▎     | 26534/61904 [3:09:00<13:13:57,  1.35s/it]
 43%|████▎     | 26535/61904 [3:09:01<13:32:16,  1.38s/it]
 43%|████▎     | 26536/61904 [3:09:03<13:27:58,  1.37s/it]
 43%|████▎     | 26537/61904 [3:09:04<13:12:29,  1.34s/it]
 43%|████▎     | 26538/61904 [3:09:05<13:02:33,  1.33s/it]
 43%|████▎     | 26539/61904 [3:09:06<12:36:40,  1.28s/it]
 43%|████▎     | 26540/61904 [3:09:08<13:04:06,  1.33s/it]
                                                          
{'loss': 2.5935, 'learning_rate': 1.5731232983274988e-07, 'epoch': 6.86}

 43%|████▎     | 26540/61904 [3:09:08<13:04:06,  1.33s/it]
 43%|████▎     | 26541/61904 [3:09:09<13:37:32,  1.39s/it]
 43%|████▎     | 26542/61904 [3:09:11<13:17:29,  1.35s/it]
 43%|████▎     | 26543/61904 [3:09:12<13:33:54,  1.38s/it]
 43%|████▎     | 26544/61904 [3:09:13<13:38:11,  1.39s/it]
 43%|████▎     | 26545/61904 [3:09:15<13:31:38,  1.38s/it]
 43%|████▎     | 26546/61904 [3:09:16<13:30:12,  1.37s/it]
 43%|████▎     | 26547/61904 [3:09:18<13:43:55,  1.40s/it]
 43%|████▎     | 26548/61904 [3:09:19<13:46:40,  1.40s/it]
 43%|████▎     | 26549/61904 [3:09:20<13:32:43,  1.38s/it]
 43%|████▎     | 26550/61904 [3:09:22<13:22:41,  1.36s/it]
 43%|████▎     | 26551/61904 [3:09:23<13:05:24,  1.33s/it]
 43%|████▎     | 26552/61904 [3:09:24<13:07:43,  1.34s/it]
 43%|████▎     | 26553/61904 [3:09:26<13:13:16,  1.35s/it]
 43%|████▎     | 26554/61904 [3:09:27<13:20:43,  1.36s/it]
 43%|████▎     | 26555/61904 [3:09:28<13:05:23,  1.33s/it]
 43%|████▎     | 26556/61904 [3:09:30<13:41:37,  1.39s/it]
 43%|████▎     | 26557/61904 [3:09:31<13:53:53,  1.42s/it]
 43%|████▎     | 26558/61904 [3:09:33<13:52:00,  1.41s/it]
 43%|████▎     | 26559/61904 [3:09:34<14:00:20,  1.43s/it]
 43%|████▎     | 26560/61904 [3:09:36<14:20:27,  1.46s/it]
                                                          
{'loss': 2.5767, 'learning_rate': 1.5727991702320757e-07, 'epoch': 6.86}

 43%|████▎     | 26560/61904 [3:09:36<14:20:27,  1.46s/it]
 43%|████▎     | 26561/61904 [3:09:37<13:52:00,  1.41s/it]
 43%|████▎     | 26562/61904 [3:09:38<13:28:07,  1.37s/it]
 43%|████▎     | 26563/61904 [3:09:40<13:23:27,  1.36s/it]
 43%|████▎     | 26564/61904 [3:09:41<13:27:05,  1.37s/it]
 43%|████▎     | 26565/61904 [3:09:42<13:04:24,  1.33s/it]
 43%|████▎     | 26566/61904 [3:09:44<13:03:16,  1.33s/it]
 43%|████▎     | 26567/61904 [3:09:45<13:32:20,  1.38s/it]
 43%|████▎     | 26568/61904 [3:09:47<13:35:21,  1.38s/it]
 43%|████▎     | 26569/61904 [3:09:48<13:30:02,  1.38s/it]
 43%|████▎     | 26570/61904 [3:09:49<13:48:15,  1.41s/it]
 43%|████▎     | 26571/61904 [3:09:51<13:48:17,  1.41s/it]
 43%|████▎     | 26572/61904 [3:09:52<13:06:04,  1.33s/it]
 43%|████▎     | 26573/61904 [3:09:53<13:08:45,  1.34s/it]
 43%|████▎     | 26574/61904 [3:09:54<12:41:16,  1.29s/it]
 43%|████▎     | 26575/61904 [3:09:56<13:01:56,  1.33s/it]
 43%|████▎     | 26576/61904 [3:09:57<12:57:12,  1.32s/it]
 43%|████▎     | 26577/61904 [3:09:59<13:34:40,  1.38s/it]
 43%|████▎     | 26578/61904 [3:10:00<13:16:21,  1.35s/it]
 43%|████▎     | 26579/61904 [3:10:01<13:14:00,  1.35s/it]
 43%|████▎     | 26580/61904 [3:10:03<13:05:43,  1.33s/it]
                                                          
{'loss': 2.6351, 'learning_rate': 1.5724750421366523e-07, 'epoch': 6.87}

 43%|████▎     | 26580/61904 [3:10:03<13:05:43,  1.33s/it]
 43%|████▎     | 26581/61904 [3:10:04<12:41:31,  1.29s/it]
 43%|████▎     | 26582/61904 [3:10:05<12:53:40,  1.31s/it]
 43%|████▎     | 26583/61904 [3:10:07<13:13:22,  1.35s/it]
 43%|████▎     | 26584/61904 [3:10:08<13:16:05,  1.35s/it]
 43%|████▎     | 26585/61904 [3:10:09<13:08:47,  1.34s/it]
 43%|████▎     | 26586/61904 [3:10:11<13:21:02,  1.36s/it]
 43%|████▎     | 26587/61904 [3:10:12<13:23:56,  1.37s/it]
 43%|████▎     | 26588/61904 [3:10:13<13:12:57,  1.35s/it]
 43%|████▎     | 26589/61904 [3:10:15<13:08:24,  1.34s/it]
 43%|████▎     | 26590/61904 [3:10:16<13:01:03,  1.33s/it]
 43%|████▎     | 26591/61904 [3:10:17<12:41:24,  1.29s/it]
 43%|████▎     | 26592/61904 [3:10:19<13:00:35,  1.33s/it]
 43%|████▎     | 26593/61904 [3:10:20<12:48:16,  1.31s/it]
 43%|████▎     | 26594/61904 [3:10:21<12:36:39,  1.29s/it]
 43%|████▎     | 26595/61904 [3:10:23<12:57:16,  1.32s/it]
 43%|████▎     | 26596/61904 [3:10:24<13:04:55,  1.33s/it]
 43%|████▎     | 26597/61904 [3:10:25<13:09:35,  1.34s/it]
 43%|████▎     | 26598/61904 [3:10:27<13:21:16,  1.36s/it]
 43%|████▎     | 26599/61904 [3:10:28<13:33:33,  1.38s/it]
 43%|████▎     | 26600/61904 [3:10:30<13:43:31,  1.40s/it]
                                                          
{'loss': 2.5793, 'learning_rate': 1.572150914041229e-07, 'epoch': 6.87}

 43%|████▎     | 26600/61904 [3:10:30<13:43:31,  1.40s/it]
 43%|████▎     | 26601/61904 [3:10:31<13:31:50,  1.38s/it]
 43%|████▎     | 26602/61904 [3:10:32<14:03:06,  1.43s/it]
 43%|████▎     | 26603/61904 [3:10:34<14:03:45,  1.43s/it]
 43%|████▎     | 26604/61904 [3:10:35<13:50:50,  1.41s/it]
 43%|████▎     | 26605/61904 [3:10:37<13:48:40,  1.41s/it]
 43%|████▎     | 26606/61904 [3:10:38<14:15:53,  1.45s/it]
 43%|████▎     | 26607/61904 [3:10:40<13:57:57,  1.42s/it]
 43%|████▎     | 26608/61904 [3:10:41<13:55:46,  1.42s/it]
 43%|████▎     | 26609/61904 [3:10:42<13:42:16,  1.40s/it]
 43%|████▎     | 26610/61904 [3:10:44<13:21:17,  1.36s/it]
 43%|████▎     | 26611/61904 [3:10:45<13:29:59,  1.38s/it]
 43%|████▎     | 26612/61904 [3:10:46<13:13:16,  1.35s/it]
 43%|████▎     | 26613/61904 [3:10:48<13:17:11,  1.36s/it]
 43%|████▎     | 26614/61904 [3:10:49<13:21:58,  1.36s/it]
 43%|████▎     | 26615/61904 [3:10:50<13:30:48,  1.38s/it]
 43%|████▎     | 26616/61904 [3:10:52<13:24:50,  1.37s/it]
 43%|████▎     | 26617/61904 [3:10:53<13:39:10,  1.39s/it]
 43%|████▎     | 26618/61904 [3:10:54<13:14:48,  1.35s/it]
 43%|████▎     | 26619/61904 [3:10:56<13:29:25,  1.38s/it]
 43%|████▎     | 26620/61904 [3:10:57<13:12:20,  1.35s/it]
                                                          
{'loss': 2.6026, 'learning_rate': 1.5718267859458056e-07, 'epoch': 6.88}

 43%|████▎     | 26620/61904 [3:10:57<13:12:20,  1.35s/it]
 43%|████▎     | 26621/61904 [3:10:59<13:16:26,  1.35s/it]
 43%|████▎     | 26622/61904 [3:11:00<13:12:58,  1.35s/it]
 43%|████▎     | 26623/61904 [3:11:01<13:38:04,  1.39s/it]
 43%|████▎     | 26624/61904 [3:11:03<13:28:57,  1.38s/it]
 43%|████▎     | 26625/61904 [3:11:04<14:13:25,  1.45s/it]
 43%|████▎     | 26626/61904 [3:11:06<13:44:05,  1.40s/it]
 43%|████▎     | 26627/61904 [3:11:07<13:33:09,  1.38s/it]
 43%|████▎     | 26628/61904 [3:11:09<14:06:33,  1.44s/it]
 43%|████▎     | 26629/61904 [3:11:10<13:48:41,  1.41s/it]
 43%|████▎     | 26630/61904 [3:11:11<13:48:47,  1.41s/it]
 43%|████▎     | 26631/61904 [3:11:13<13:30:33,  1.38s/it]
 43%|████▎     | 26632/61904 [3:11:14<13:26:49,  1.37s/it]
 43%|████▎     | 26633/61904 [3:11:15<12:53:11,  1.32s/it]
 43%|████▎     | 26634/61904 [3:11:16<12:58:37,  1.32s/it]
 43%|████▎     | 26635/61904 [3:11:18<13:30:49,  1.38s/it]
 43%|████▎     | 26636/61904 [3:11:19<13:18:16,  1.36s/it]
 43%|████▎     | 26637/61904 [3:11:21<13:07:19,  1.34s/it]
 43%|████▎     | 26638/61904 [3:11:22<13:31:15,  1.38s/it]
 43%|████▎     | 26639/61904 [3:11:23<13:27:38,  1.37s/it]
 43%|████▎     | 26640/61904 [3:11:25<13:08:41,  1.34s/it]
                                                          
{'loss': 2.5796, 'learning_rate': 1.5715026578503824e-07, 'epoch': 6.89}

 43%|████▎     | 26640/61904 [3:11:25<13:08:41,  1.34s/it]
 43%|████▎     | 26641/61904 [3:11:26<13:55:23,  1.42s/it]
 43%|████▎     | 26642/61904 [3:11:28<13:51:05,  1.41s/it]
 43%|████▎     | 26643/61904 [3:11:29<13:45:27,  1.40s/it]
 43%|████▎     | 26644/61904 [3:11:30<13:34:04,  1.39s/it]
 43%|████▎     | 26645/61904 [3:11:32<13:35:48,  1.39s/it]
 43%|████▎     | 26646/61904 [3:11:33<13:27:05,  1.37s/it]
 43%|████▎     | 26647/61904 [3:11:34<13:07:35,  1.34s/it]
 43%|████▎     | 26648/61904 [3:11:36<13:30:19,  1.38s/it]
 43%|████▎     | 26649/61904 [3:11:37<13:27:50,  1.37s/it]
 43%|████▎     | 26650/61904 [3:11:39<13:16:27,  1.36s/it]
 43%|████▎     | 26651/61904 [3:11:40<13:17:57,  1.36s/it]
 43%|████▎     | 26652/61904 [3:11:41<13:21:36,  1.36s/it]
 43%|████▎     | 26653/61904 [3:11:43<14:07:47,  1.44s/it]
 43%|████▎     | 26654/61904 [3:11:44<13:57:35,  1.43s/it]
 43%|████▎     | 26655/61904 [3:11:46<13:39:04,  1.39s/it]
 43%|████▎     | 26656/61904 [3:11:47<13:43:24,  1.40s/it]
 43%|████▎     | 26657/61904 [3:11:48<13:10:15,  1.35s/it]
 43%|████▎     | 26658/61904 [3:11:50<13:00:36,  1.33s/it]
 43%|████▎     | 26659/61904 [3:11:51<12:48:01,  1.31s/it]
 43%|████▎     | 26660/61904 [3:11:52<12:39:02,  1.29s/it]
                                                          
{'loss': 2.6488, 'learning_rate': 1.571178529754959e-07, 'epoch': 6.89}

 43%|████▎     | 26660/61904 [3:11:52<12:39:02,  1.29s/it]
 43%|████▎     | 26661/61904 [3:11:53<12:44:05,  1.30s/it]
 43%|████▎     | 26662/61904 [3:11:55<12:51:52,  1.31s/it]
 43%|████▎     | 26663/61904 [3:11:56<13:13:00,  1.35s/it]
 43%|████▎     | 26664/61904 [3:11:58<13:07:05,  1.34s/it]
 43%|████▎     | 26665/61904 [3:11:59<13:13:24,  1.35s/it]
 43%|████▎     | 26666/61904 [3:12:00<12:54:56,  1.32s/it]
 43%|████▎     | 26667/61904 [3:12:01<12:43:41,  1.30s/it]
 43%|████▎     | 26668/61904 [3:12:03<13:13:02,  1.35s/it]
 43%|████▎     | 26669/61904 [3:12:04<13:12:28,  1.35s/it]
 43%|████▎     | 26670/61904 [3:12:06<13:40:27,  1.40s/it]
 43%|████▎     | 26671/61904 [3:12:07<13:21:49,  1.37s/it]
 43%|████▎     | 26672/61904 [3:12:08<13:21:54,  1.37s/it]
 43%|████▎     | 26673/61904 [3:12:10<12:55:23,  1.32s/it]
 43%|████▎     | 26674/61904 [3:12:11<13:00:38,  1.33s/it]
 43%|████▎     | 26675/61904 [3:12:13<14:24:01,  1.47s/it]
 43%|████▎     | 26676/61904 [3:12:14<14:12:14,  1.45s/it]
 43%|████▎     | 26677/61904 [3:12:15<13:48:27,  1.41s/it]
 43%|████▎     | 26678/61904 [3:12:17<13:34:31,  1.39s/it]
 43%|████▎     | 26679/61904 [3:12:18<13:00:28,  1.33s/it]
 43%|████▎     | 26680/61904 [3:12:19<13:07:20,  1.34s/it]
                                                          
{'loss': 2.6461, 'learning_rate': 1.5708544016595357e-07, 'epoch': 6.9}

 43%|████▎     | 26680/61904 [3:12:19<13:07:20,  1.34s/it]
 43%|████▎     | 26681/61904 [3:12:21<13:06:13,  1.34s/it]
 43%|████▎     | 26682/61904 [3:12:22<13:02:14,  1.33s/it]
 43%|████▎     | 26683/61904 [3:12:23<13:18:56,  1.36s/it]
 43%|████▎     | 26684/61904 [3:12:25<13:20:03,  1.36s/it]
 43%|████▎     | 26685/61904 [3:12:26<13:10:32,  1.35s/it]
 43%|████▎     | 26686/61904 [3:12:28<13:45:02,  1.41s/it]
 43%|████▎     | 26687/61904 [3:12:29<13:43:57,  1.40s/it]
 43%|████▎     | 26688/61904 [3:12:31<14:06:42,  1.44s/it]
 43%|████▎     | 26689/61904 [3:12:32<13:48:58,  1.41s/it]
 43%|████▎     | 26690/61904 [3:12:33<13:31:35,  1.38s/it]
 43%|████▎     | 26691/61904 [3:12:35<13:41:25,  1.40s/it]
 43%|████▎     | 26692/61904 [3:12:36<13:51:34,  1.42s/it]
 43%|████▎     | 26693/61904 [3:12:38<13:45:32,  1.41s/it]
 43%|████▎     | 26694/61904 [3:12:39<13:22:10,  1.37s/it]
 43%|████▎     | 26695/61904 [3:12:40<13:39:45,  1.40s/it]
 43%|████▎     | 26696/61904 [3:12:42<13:42:44,  1.40s/it]
 43%|████▎     | 26697/61904 [3:12:43<13:28:26,  1.38s/it]
 43%|████▎     | 26698/61904 [3:12:44<13:17:45,  1.36s/it]
 43%|████▎     | 26699/61904 [3:12:46<13:34:27,  1.39s/it]
 43%|████▎     | 26700/61904 [3:12:47<13:39:40,  1.40s/it]
                                                          
{'loss': 2.5738, 'learning_rate': 1.5705302735641123e-07, 'epoch': 6.9}

 43%|████▎     | 26700/61904 [3:12:47<13:39:40,  1.40s/it]
 43%|████▎     | 26701/61904 [3:12:48<13:00:18,  1.33s/it]
 43%|████▎     | 26702/61904 [3:12:50<13:27:24,  1.38s/it]
 43%|████▎     | 26703/61904 [3:12:51<13:27:35,  1.38s/it]
 43%|████▎     | 26704/61904 [3:12:53<13:34:44,  1.39s/it]
 43%|████▎     | 26705/61904 [3:12:54<13:21:27,  1.37s/it]
 43%|████▎     | 26706/61904 [3:12:55<13:24:47,  1.37s/it]
 43%|████▎     | 26707/61904 [3:12:57<13:07:17,  1.34s/it]
 43%|████▎     | 26708/61904 [3:12:58<13:16:20,  1.36s/it]
 43%|████▎     | 26709/61904 [3:12:59<13:36:22,  1.39s/it]
 43%|████▎     | 26710/61904 [3:13:01<13:33:47,  1.39s/it]
 43%|████▎     | 26711/61904 [3:13:02<13:24:59,  1.37s/it]
 43%|████▎     | 26712/61904 [3:13:04<13:21:34,  1.37s/it]
 43%|████▎     | 26713/61904 [3:13:05<13:34:47,  1.39s/it]
 43%|████▎     | 26714/61904 [3:13:06<13:50:34,  1.42s/it]
 43%|████▎     | 26715/61904 [3:13:08<13:06:19,  1.34s/it]
 43%|████▎     | 26716/61904 [3:13:09<13:23:05,  1.37s/it]
 43%|████▎     | 26717/61904 [3:13:10<13:19:16,  1.36s/it]
 43%|████▎     | 26718/61904 [3:13:12<13:24:02,  1.37s/it]
 43%|████▎     | 26719/61904 [3:13:13<13:24:25,  1.37s/it]
 43%|████▎     | 26720/61904 [3:13:14<13:07:46,  1.34s/it]
                                                          
{'loss': 2.5407, 'learning_rate': 1.5702061454686892e-07, 'epoch': 6.91}

 43%|████▎     | 26720/61904 [3:13:14<13:07:46,  1.34s/it]
 43%|████▎     | 26721/61904 [3:13:16<13:03:26,  1.34s/it]
 43%|████▎     | 26722/61904 [3:13:17<12:53:17,  1.32s/it]
 43%|████▎     | 26723/61904 [3:13:19<13:19:41,  1.36s/it]
 43%|████▎     | 26724/61904 [3:13:20<13:17:52,  1.36s/it]
 43%|████▎     | 26725/61904 [3:13:21<13:19:58,  1.36s/it]
 43%|████▎     | 26726/61904 [3:13:23<13:35:59,  1.39s/it]
 43%|████▎     | 26727/61904 [3:13:24<13:13:31,  1.35s/it]
 43%|████▎     | 26728/61904 [3:13:25<13:38:36,  1.40s/it]
 43%|████▎     | 26729/61904 [3:13:27<13:22:04,  1.37s/it]
 43%|████▎     | 26730/61904 [3:13:28<12:57:21,  1.33s/it]
 43%|████▎     | 26731/61904 [3:13:29<13:18:59,  1.36s/it]
 43%|████▎     | 26732/61904 [3:13:31<13:04:59,  1.34s/it]
 43%|████▎     | 26733/61904 [3:13:32<13:05:49,  1.34s/it]
 43%|████▎     | 26734/61904 [3:13:33<13:00:33,  1.33s/it]
 43%|████▎     | 26735/61904 [3:13:35<12:54:33,  1.32s/it]
 43%|████▎     | 26736/61904 [3:13:36<13:15:03,  1.36s/it]
 43%|████▎     | 26737/61904 [3:13:37<13:03:36,  1.34s/it]
 43%|████▎     | 26738/61904 [3:13:39<12:52:40,  1.32s/it]
 43%|████▎     | 26739/61904 [3:13:40<12:43:12,  1.30s/it]
 43%|████▎     | 26740/61904 [3:13:41<13:10:55,  1.35s/it]
                                                          
{'loss': 2.6304, 'learning_rate': 1.5698820173732658e-07, 'epoch': 6.91}

 43%|████▎     | 26740/61904 [3:13:41<13:10:55,  1.35s/it]
 43%|████▎     | 26741/61904 [3:13:43<13:21:52,  1.37s/it]
 43%|████▎     | 26742/61904 [3:13:44<13:32:39,  1.39s/it]
 43%|████▎     | 26743/61904 [3:13:46<14:56:26,  1.53s/it]
 43%|████▎     | 26744/61904 [3:13:47<14:16:33,  1.46s/it]
 43%|████▎     | 26745/61904 [3:13:49<13:42:58,  1.40s/it]
 43%|████▎     | 26746/61904 [3:13:50<13:57:02,  1.43s/it]
 43%|████▎     | 26747/61904 [3:13:52<13:51:05,  1.42s/it]
 43%|████▎     | 26748/61904 [3:13:53<13:47:21,  1.41s/it]
 43%|████▎     | 26749/61904 [3:13:54<13:29:56,  1.38s/it]
 43%|████▎     | 26750/61904 [3:13:56<13:18:34,  1.36s/it]
 43%|████▎     | 26751/61904 [3:13:57<13:29:24,  1.38s/it]
 43%|████▎     | 26752/61904 [3:13:58<13:21:03,  1.37s/it]
 43%|████▎     | 26753/61904 [3:14:00<12:58:45,  1.33s/it]
 43%|████▎     | 26754/61904 [3:14:01<12:58:45,  1.33s/it]
 43%|████▎     | 26755/61904 [3:14:02<13:10:24,  1.35s/it]
 43%|████▎     | 26756/61904 [3:14:04<13:45:52,  1.41s/it]
 43%|████▎     | 26757/61904 [3:14:05<13:49:15,  1.42s/it]
 43%|████▎     | 26758/61904 [3:14:07<13:38:30,  1.40s/it]
 43%|████▎     | 26759/61904 [3:14:08<13:54:35,  1.42s/it]
 43%|████▎     | 26760/61904 [3:14:09<13:25:09,  1.37s/it]
                                                          
{'loss': 2.576, 'learning_rate': 1.5695578892778424e-07, 'epoch': 6.92}

 43%|████▎     | 26760/61904 [3:14:09<13:25:09,  1.37s/it]
 43%|████▎     | 26761/61904 [3:14:11<12:53:07,  1.32s/it]
 43%|████▎     | 26762/61904 [3:14:12<12:43:16,  1.30s/it]
 43%|████▎     | 26763/61904 [3:14:13<12:47:48,  1.31s/it]
 43%|████▎     | 26764/61904 [3:14:15<13:05:40,  1.34s/it]
 43%|████▎     | 26765/61904 [3:14:16<12:43:04,  1.30s/it]
 43%|████▎     | 26766/61904 [3:14:17<13:36:09,  1.39s/it]
 43%|████▎     | 26767/61904 [3:14:19<13:20:37,  1.37s/it]
 43%|████▎     | 26768/61904 [3:14:20<12:56:02,  1.33s/it]
 43%|████▎     | 26769/61904 [3:14:21<12:58:05,  1.33s/it]
 43%|████▎     | 26770/61904 [3:14:22<12:32:09,  1.28s/it]
 43%|████▎     | 26771/61904 [3:14:24<12:35:17,  1.29s/it]
 43%|████▎     | 26772/61904 [3:14:25<12:51:39,  1.32s/it]
 43%|████▎     | 26773/61904 [3:14:27<13:19:39,  1.37s/it]
 43%|████▎     | 26774/61904 [3:14:28<13:10:42,  1.35s/it]
 43%|████▎     | 26775/61904 [3:14:29<13:14:54,  1.36s/it]
 43%|████▎     | 26776/61904 [3:14:31<13:23:31,  1.37s/it]
 43%|████▎     | 26777/61904 [3:14:32<13:33:18,  1.39s/it]
 43%|████▎     | 26778/61904 [3:14:33<13:22:23,  1.37s/it]
 43%|████▎     | 26779/61904 [3:14:35<13:53:24,  1.42s/it]
 43%|████▎     | 26780/61904 [3:14:36<13:38:07,  1.40s/it]
                                                          
{'loss': 2.5784, 'learning_rate': 1.5692337611824193e-07, 'epoch': 6.92}

 43%|████▎     | 26780/61904 [3:14:36<13:38:07,  1.40s/it]
 43%|████▎     | 26781/61904 [3:14:38<13:51:16,  1.42s/it]
 43%|████▎     | 26782/61904 [3:14:39<13:37:39,  1.40s/it]
 43%|████▎     | 26783/61904 [3:14:41<13:49:08,  1.42s/it]
 43%|████▎     | 26784/61904 [3:14:42<13:51:12,  1.42s/it]
 43%|████▎     | 26785/61904 [3:14:43<13:31:44,  1.39s/it]
 43%|████▎     | 26786/61904 [3:14:45<13:16:16,  1.36s/it]
 43%|████▎     | 26787/61904 [3:14:46<13:19:42,  1.37s/it]
 43%|████▎     | 26788/61904 [3:14:47<13:22:19,  1.37s/it]
 43%|████▎     | 26789/61904 [3:14:49<13:22:58,  1.37s/it]
 43%|████▎     | 26790/61904 [3:14:50<13:36:15,  1.39s/it]
 43%|████▎     | 26791/61904 [3:14:51<12:59:59,  1.33s/it]
 43%|████▎     | 26792/61904 [3:14:53<12:52:34,  1.32s/it]
 43%|████▎     | 26793/61904 [3:14:54<12:53:24,  1.32s/it]
 43%|████▎     | 26794/61904 [3:14:55<12:56:40,  1.33s/it]
 43%|████▎     | 26795/61904 [3:14:57<13:09:53,  1.35s/it]
 43%|████▎     | 26796/61904 [3:14:58<13:34:22,  1.39s/it]
 43%|████▎     | 26797/61904 [3:15:00<13:21:40,  1.37s/it]
 43%|████▎     | 26798/61904 [3:15:01<13:04:51,  1.34s/it]
 43%|████▎     | 26799/61904 [3:15:02<12:50:23,  1.32s/it]
 43%|████▎     | 26800/61904 [3:15:04<13:13:09,  1.36s/it]
                                                          
{'loss': 2.6124, 'learning_rate': 1.568909633086996e-07, 'epoch': 6.93}

 43%|████▎     | 26800/61904 [3:15:04<13:13:09,  1.36s/it]
 43%|████▎     | 26801/61904 [3:15:05<13:19:34,  1.37s/it]
 43%|████▎     | 26802/61904 [3:15:07<14:24:21,  1.48s/it]
 43%|████▎     | 26803/61904 [3:15:08<14:05:36,  1.45s/it]
 43%|████▎     | 26804/61904 [3:15:09<13:35:12,  1.39s/it]
 43%|████▎     | 26805/61904 [3:15:11<13:07:55,  1.35s/it]
 43%|████▎     | 26806/61904 [3:15:12<13:11:52,  1.35s/it]
 43%|████▎     | 26807/61904 [3:15:13<12:47:22,  1.31s/it]
 43%|████▎     | 26808/61904 [3:15:14<12:43:03,  1.30s/it]
 43%|████▎     | 26809/61904 [3:15:16<12:47:30,  1.31s/it]
 43%|████▎     | 26810/61904 [3:15:17<12:44:27,  1.31s/it]
 43%|████▎     | 26811/61904 [3:15:19<13:04:07,  1.34s/it]
 43%|████▎     | 26812/61904 [3:15:20<13:22:06,  1.37s/it]
 43%|████▎     | 26813/61904 [3:15:21<13:37:49,  1.40s/it]
 43%|████▎     | 26814/61904 [3:15:23<13:27:48,  1.38s/it]
 43%|████▎     | 26815/61904 [3:15:24<13:07:33,  1.35s/it]
 43%|████▎     | 26816/61904 [3:15:25<13:24:52,  1.38s/it]
 43%|████▎     | 26817/61904 [3:15:27<13:10:29,  1.35s/it]
 43%|████▎     | 26818/61904 [3:15:28<13:08:23,  1.35s/it]
 43%|████▎     | 26819/61904 [3:15:29<12:52:50,  1.32s/it]
 43%|████▎     | 26820/61904 [3:15:31<13:03:41,  1.34s/it]
                                                          
{'loss': 2.5992, 'learning_rate': 1.5685855049915725e-07, 'epoch': 6.93}

 43%|████▎     | 26820/61904 [3:15:31<13:03:41,  1.34s/it]
 43%|████▎     | 26821/61904 [3:15:32<12:56:25,  1.33s/it]
 43%|████▎     | 26822/61904 [3:15:33<12:42:28,  1.30s/it]
 43%|████▎     | 26823/61904 [3:15:35<12:59:29,  1.33s/it]
 43%|████▎     | 26824/61904 [3:15:36<13:23:31,  1.37s/it]
 43%|████▎     | 26825/61904 [3:15:38<13:16:42,  1.36s/it]
 43%|████▎     | 26826/61904 [3:15:39<13:17:10,  1.36s/it]
 43%|████▎     | 26827/61904 [3:15:40<13:01:39,  1.34s/it]
 43%|████▎     | 26828/61904 [3:15:42<13:05:00,  1.34s/it]
 43%|████▎     | 26829/61904 [3:15:43<12:59:40,  1.33s/it]
 43%|████▎     | 26830/61904 [3:15:44<13:17:39,  1.36s/it]
 43%|████▎     | 26831/61904 [3:15:46<13:49:52,  1.42s/it]
 43%|████▎     | 26832/61904 [3:15:47<13:40:14,  1.40s/it]
 43%|████▎     | 26833/61904 [3:15:49<13:51:04,  1.42s/it]
 43%|████▎     | 26834/61904 [3:15:50<13:49:38,  1.42s/it]
 43%|████▎     | 26835/61904 [3:15:52<14:12:53,  1.46s/it]
 43%|████▎     | 26836/61904 [3:15:53<14:19:06,  1.47s/it]
 43%|████▎     | 26837/61904 [3:15:54<13:52:08,  1.42s/it]
 43%|████▎     | 26838/61904 [3:15:56<13:20:10,  1.37s/it]
 43%|████▎     | 26839/61904 [3:15:57<13:14:47,  1.36s/it]
 43%|████▎     | 26840/61904 [3:15:58<13:15:05,  1.36s/it]
                                                          
{'loss': 2.5961, 'learning_rate': 1.5682613768961492e-07, 'epoch': 6.94}

 43%|████▎     | 26840/61904 [3:15:58<13:15:05,  1.36s/it]
 43%|████▎     | 26841/61904 [3:16:00<13:05:54,  1.34s/it]
 43%|████▎     | 26842/61904 [3:16:01<13:13:03,  1.36s/it]
 43%|████▎     | 26843/61904 [3:16:02<13:07:59,  1.35s/it]
 43%|████▎     | 26844/61904 [3:16:04<13:12:26,  1.36s/it]
 43%|████▎     | 26845/61904 [3:16:05<12:48:22,  1.31s/it]
 43%|████▎     | 26846/61904 [3:16:06<13:22:34,  1.37s/it]
 43%|████▎     | 26847/61904 [3:16:08<13:38:59,  1.40s/it]
 43%|████▎     | 26848/61904 [3:16:09<13:38:29,  1.40s/it]
 43%|████▎     | 26849/61904 [3:16:11<13:19:28,  1.37s/it]
 43%|████▎     | 26850/61904 [3:16:12<13:00:38,  1.34s/it]
 43%|████▎     | 26851/61904 [3:16:13<13:11:33,  1.35s/it]
 43%|████▎     | 26852/61904 [3:16:15<13:15:38,  1.36s/it]
 43%|████▎     | 26853/61904 [3:16:16<13:09:30,  1.35s/it]
 43%|████▎     | 26854/61904 [3:16:17<12:56:12,  1.33s/it]
 43%|████▎     | 26855/61904 [3:16:19<13:14:39,  1.36s/it]
 43%|████▎     | 26856/61904 [3:16:20<13:11:24,  1.35s/it]
 43%|████▎     | 26857/61904 [3:16:21<13:14:35,  1.36s/it]
 43%|████▎     | 26858/61904 [3:16:23<13:09:42,  1.35s/it]
 43%|████▎     | 26859/61904 [3:16:24<13:35:54,  1.40s/it]
 43%|████▎     | 26860/61904 [3:16:26<13:29:48,  1.39s/it]
                                                          
{'loss': 2.5989, 'learning_rate': 1.567937248800726e-07, 'epoch': 6.94}

 43%|████▎     | 26860/61904 [3:16:26<13:29:48,  1.39s/it]
 43%|████▎     | 26861/61904 [3:16:27<13:33:16,  1.39s/it]
 43%|████▎     | 26862/61904 [3:16:28<13:09:38,  1.35s/it]
 43%|████▎     | 26863/61904 [3:16:30<13:05:24,  1.34s/it]
 43%|████▎     | 26864/61904 [3:16:31<13:13:44,  1.36s/it]
 43%|████▎     | 26865/61904 [3:16:32<13:07:46,  1.35s/it]
 43%|████▎     | 26866/61904 [3:16:34<12:59:47,  1.34s/it]
 43%|████▎     | 26867/61904 [3:16:35<13:17:03,  1.36s/it]
 43%|████▎     | 26868/61904 [3:16:37<13:34:06,  1.39s/it]
 43%|████▎     | 26869/61904 [3:16:38<14:07:52,  1.45s/it]
 43%|████▎     | 26870/61904 [3:16:40<14:25:47,  1.48s/it]
 43%|████▎     | 26871/61904 [3:16:41<13:53:33,  1.43s/it]
 43%|████▎     | 26872/61904 [3:16:42<13:55:51,  1.43s/it]
 43%|████▎     | 26873/61904 [3:16:44<13:19:58,  1.37s/it]
 43%|████▎     | 26874/61904 [3:16:45<13:06:11,  1.35s/it]
 43%|████▎     | 26875/61904 [3:16:46<13:04:08,  1.34s/it]
 43%|████▎     | 26876/61904 [3:16:48<13:11:01,  1.35s/it]
 43%|████▎     | 26877/61904 [3:16:49<13:11:17,  1.36s/it]
 43%|████▎     | 26878/61904 [3:16:50<13:07:05,  1.35s/it]
 43%|████▎     | 26879/61904 [3:16:52<13:06:01,  1.35s/it]
 43%|████▎     | 26880/61904 [3:16:53<13:21:00,  1.37s/it]
                                                          
{'loss': 2.6514, 'learning_rate': 1.5676131207053027e-07, 'epoch': 6.95}

 43%|████▎     | 26880/61904 [3:16:53<13:21:00,  1.37s/it]
 43%|████▎     | 26881/61904 [3:16:54<13:15:45,  1.36s/it]
 43%|████▎     | 26882/61904 [3:16:56<13:14:28,  1.36s/it]
 43%|████▎     | 26883/61904 [3:16:57<13:14:04,  1.36s/it]
 43%|████▎     | 26884/61904 [3:16:59<13:48:01,  1.42s/it]
 43%|████▎     | 26885/61904 [3:17:00<13:45:29,  1.41s/it]
 43%|████▎     | 26886/61904 [3:17:02<13:49:30,  1.42s/it]
 43%|████▎     | 26887/61904 [3:17:03<13:30:05,  1.39s/it]
 43%|████▎     | 26888/61904 [3:17:04<13:31:10,  1.39s/it]
 43%|████▎     | 26889/61904 [3:17:06<13:37:27,  1.40s/it]
 43%|████▎     | 26890/61904 [3:17:07<13:14:46,  1.36s/it]
 43%|████▎     | 26891/61904 [3:17:08<13:23:46,  1.38s/it]
 43%|████▎     | 26892/61904 [3:17:10<13:39:57,  1.41s/it]
 43%|████▎     | 26893/61904 [3:17:11<13:10:13,  1.35s/it]
 43%|████▎     | 26894/61904 [3:17:13<13:31:03,  1.39s/it]
 43%|████▎     | 26895/61904 [3:17:14<13:38:13,  1.40s/it]
 43%|████▎     | 26896/61904 [3:17:15<13:19:44,  1.37s/it]
 43%|████▎     | 26897/61904 [3:17:17<13:36:39,  1.40s/it]
 43%|████▎     | 26898/61904 [3:17:18<13:26:52,  1.38s/it]
 43%|████▎     | 26899/61904 [3:17:19<12:53:55,  1.33s/it]
 43%|████▎     | 26900/61904 [3:17:21<13:08:53,  1.35s/it]
                                                          
{'loss': 2.5921, 'learning_rate': 1.5672889926098793e-07, 'epoch': 6.95}

 43%|████▎     | 26900/61904 [3:17:21<13:08:53,  1.35s/it]
 43%|████▎     | 26901/61904 [3:17:22<13:06:51,  1.35s/it]
 43%|████▎     | 26902/61904 [3:17:23<13:20:20,  1.37s/it]
 43%|████▎     | 26903/61904 [3:17:25<13:20:26,  1.37s/it]
 43%|████▎     | 26904/61904 [3:17:26<13:29:55,  1.39s/it]
 43%|████▎     | 26905/61904 [3:17:28<13:29:11,  1.39s/it]
 43%|████▎     | 26906/61904 [3:17:29<13:23:08,  1.38s/it]
 43%|████▎     | 26907/61904 [3:17:30<13:33:39,  1.39s/it]
 43%|████▎     | 26908/61904 [3:17:32<13:14:17,  1.36s/it]
 43%|████▎     | 26909/61904 [3:17:33<12:56:27,  1.33s/it]
 43%|████▎     | 26910/61904 [3:17:34<13:24:24,  1.38s/it]
 43%|████▎     | 26911/61904 [3:17:36<13:30:44,  1.39s/it]
 43%|████▎     | 26912/61904 [3:17:37<13:21:07,  1.37s/it]
 43%|████▎     | 26913/61904 [3:17:38<12:57:26,  1.33s/it]
 43%|████▎     | 26914/61904 [3:17:40<12:42:18,  1.31s/it]
 43%|████▎     | 26915/61904 [3:17:41<12:52:12,  1.32s/it]
 43%|████▎     | 26916/61904 [3:17:42<12:50:49,  1.32s/it]
 43%|████▎     | 26917/61904 [3:17:44<12:37:46,  1.30s/it]
 43%|████▎     | 26918/61904 [3:17:45<12:35:19,  1.30s/it]
 43%|████▎     | 26919/61904 [3:17:46<13:00:21,  1.34s/it]
 43%|████▎     | 26920/61904 [3:17:48<12:54:13,  1.33s/it]
                                                          
{'loss': 2.5907, 'learning_rate': 1.566964864514456e-07, 'epoch': 6.96}

 43%|████▎     | 26920/61904 [3:17:48<12:54:13,  1.33s/it]
 43%|████▎     | 26921/61904 [3:17:49<12:57:02,  1.33s/it]
 43%|████▎     | 26922/61904 [3:17:51<13:27:40,  1.39s/it]
 43%|████▎     | 26923/61904 [3:17:52<13:25:07,  1.38s/it]
 43%|████▎     | 26924/61904 [3:17:53<13:33:23,  1.40s/it]
 43%|████▎     | 26925/61904 [3:17:55<13:29:39,  1.39s/it]
 43%|████▎     | 26926/61904 [3:17:56<13:14:01,  1.36s/it]
 43%|████▎     | 26927/61904 [3:17:57<13:10:04,  1.36s/it]
 43%|████▎     | 26928/61904 [3:17:59<13:17:53,  1.37s/it]
 44%|████▎     | 26929/61904 [3:18:00<13:16:36,  1.37s/it]
 44%|████▎     | 26930/61904 [3:18:01<13:09:48,  1.35s/it]
 44%|████▎     | 26931/61904 [3:18:03<13:19:32,  1.37s/it]
 44%|████▎     | 26932/61904 [3:18:04<13:13:40,  1.36s/it]
 44%|████▎     | 26933/61904 [3:18:06<13:28:16,  1.39s/it]
 44%|████▎     | 26934/61904 [3:18:07<13:34:24,  1.40s/it]
 44%|████▎     | 26935/61904 [3:18:08<13:33:32,  1.40s/it]
 44%|████▎     | 26936/61904 [3:18:10<13:12:30,  1.36s/it]
 44%|████▎     | 26937/61904 [3:18:11<13:15:31,  1.37s/it]
 44%|████▎     | 26938/61904 [3:18:13<13:28:49,  1.39s/it]
 44%|████▎     | 26939/61904 [3:18:14<13:35:39,  1.40s/it]
 44%|████▎     | 26940/61904 [3:18:15<13:48:19,  1.42s/it]
                                                          
{'loss': 2.5183, 'learning_rate': 1.5666407364190328e-07, 'epoch': 6.96}

 44%|████▎     | 26940/61904 [3:18:15<13:48:19,  1.42s/it]
 44%|████▎     | 26941/61904 [3:18:17<13:07:47,  1.35s/it]
 44%|████▎     | 26942/61904 [3:18:18<12:45:08,  1.31s/it]
 44%|████▎     | 26943/61904 [3:18:19<12:49:32,  1.32s/it]
 44%|████▎     | 26944/61904 [3:18:21<13:12:42,  1.36s/it]
 44%|████▎     | 26945/61904 [3:18:22<12:58:22,  1.34s/it]
 44%|████▎     | 26946/61904 [3:18:23<13:08:59,  1.35s/it]
 44%|████▎     | 26947/61904 [3:18:25<13:13:24,  1.36s/it]
 44%|████▎     | 26948/61904 [3:18:26<13:07:26,  1.35s/it]
 44%|████▎     | 26949/61904 [3:18:27<12:58:03,  1.34s/it]
 44%|████▎     | 26950/61904 [3:18:29<13:14:52,  1.36s/it]
 44%|████▎     | 26951/61904 [3:18:30<13:16:41,  1.37s/it]
 44%|████▎     | 26952/61904 [3:18:31<12:56:29,  1.33s/it]
 44%|████▎     | 26953/61904 [3:18:33<12:45:52,  1.31s/it]
 44%|████▎     | 26954/61904 [3:18:34<13:03:08,  1.34s/it]
 44%|████▎     | 26955/61904 [3:18:35<13:02:01,  1.34s/it]
 44%|████▎     | 26956/61904 [3:18:37<13:10:54,  1.36s/it]
 44%|████▎     | 26957/61904 [3:18:38<13:12:06,  1.36s/it]
 44%|████▎     | 26958/61904 [3:18:40<13:13:22,  1.36s/it]
 44%|████▎     | 26959/61904 [3:18:41<13:31:12,  1.39s/it]
 44%|████▎     | 26960/61904 [3:18:42<13:30:45,  1.39s/it]
                                                          
{'loss': 2.6151, 'learning_rate': 1.5663166083236094e-07, 'epoch': 6.97}

 44%|████▎     | 26960/61904 [3:18:42<13:30:45,  1.39s/it]
 44%|████▎     | 26961/61904 [3:18:44<14:13:20,  1.47s/it]
 44%|████▎     | 26962/61904 [3:18:45<13:55:52,  1.44s/it]
 44%|████▎     | 26963/61904 [3:18:47<13:24:56,  1.38s/it]
 44%|████▎     | 26964/61904 [3:18:48<13:30:07,  1.39s/it]
 44%|████▎     | 26965/61904 [3:18:49<13:12:47,  1.36s/it]
 44%|████▎     | 26966/61904 [3:18:51<13:08:45,  1.35s/it]
 44%|████▎     | 26967/61904 [3:18:52<13:18:16,  1.37s/it]
 44%|████▎     | 26968/61904 [3:18:54<13:32:03,  1.39s/it]
 44%|████▎     | 26969/61904 [3:18:55<13:38:52,  1.41s/it]
 44%|████▎     | 26970/61904 [3:18:56<13:53:57,  1.43s/it]
 44%|████▎     | 26971/61904 [3:18:58<14:01:41,  1.45s/it]
 44%|████▎     | 26972/61904 [3:18:59<13:44:40,  1.42s/it]
 44%|████▎     | 26973/61904 [3:19:01<13:57:40,  1.44s/it]
 44%|████▎     | 26974/61904 [3:19:02<13:51:26,  1.43s/it]
 44%|████▎     | 26975/61904 [3:19:03<13:27:12,  1.39s/it]
 44%|████▎     | 26976/61904 [3:19:05<13:10:06,  1.36s/it]
 44%|████▎     | 26977/61904 [3:19:06<12:47:13,  1.32s/it]
 44%|████▎     | 26978/61904 [3:19:07<13:04:53,  1.35s/it]
 44%|████▎     | 26979/61904 [3:19:09<13:07:01,  1.35s/it]
 44%|████▎     | 26980/61904 [3:19:10<13:04:28,  1.35s/it]
                                                          
{'loss': 2.5454, 'learning_rate': 1.565992480228186e-07, 'epoch': 6.97}

 44%|████▎     | 26980/61904 [3:19:10<13:04:28,  1.35s/it]
 44%|████▎     | 26981/61904 [3:19:11<12:59:44,  1.34s/it]
 44%|████▎     | 26982/61904 [3:19:13<12:54:19,  1.33s/it]
 44%|████▎     | 26983/61904 [3:19:14<13:04:18,  1.35s/it]
 44%|████▎     | 26984/61904 [3:19:15<13:03:25,  1.35s/it]
 44%|████▎     | 26985/61904 [3:19:17<13:03:22,  1.35s/it]
 44%|████▎     | 26986/61904 [3:19:18<13:24:49,  1.38s/it]
 44%|████▎     | 26987/61904 [3:19:20<13:16:55,  1.37s/it]
 44%|████▎     | 26988/61904 [3:19:21<13:35:43,  1.40s/it]
 44%|████▎     | 26989/61904 [3:19:22<13:32:15,  1.40s/it]
 44%|████▎     | 26990/61904 [3:19:24<13:31:57,  1.40s/it]
 44%|████▎     | 26991/61904 [3:19:25<14:00:56,  1.45s/it]
 44%|████▎     | 26992/61904 [3:19:27<13:29:03,  1.39s/it]
 44%|████▎     | 26993/61904 [3:19:28<13:10:57,  1.36s/it]
 44%|████▎     | 26994/61904 [3:19:29<12:58:57,  1.34s/it]
 44%|████▎     | 26995/61904 [3:19:31<12:42:07,  1.31s/it]
 44%|████▎     | 26996/61904 [3:19:32<12:38:20,  1.30s/it]
 44%|████▎     | 26997/61904 [3:19:33<12:56:41,  1.34s/it]
 44%|████▎     | 26998/61904 [3:19:35<12:53:16,  1.33s/it]
 44%|████▎     | 26999/61904 [3:19:36<13:09:12,  1.36s/it]
 44%|████▎     | 27000/61904 [3:19:37<13:01:32,  1.34s/it]
                                                          
{'loss': 2.5349, 'learning_rate': 1.5656683521327626e-07, 'epoch': 6.98}

 44%|████▎     | 27000/61904 [3:19:37<13:01:32,  1.34s/it]
 44%|████▎     | 27001/61904 [3:19:39<13:03:07,  1.35s/it]
 44%|████▎     | 27002/61904 [3:19:40<12:52:22,  1.33s/it]
 44%|████▎     | 27003/61904 [3:19:41<12:56:44,  1.34s/it]
 44%|████▎     | 27004/61904 [3:19:43<12:57:13,  1.34s/it]
 44%|████▎     | 27005/61904 [3:19:44<13:09:38,  1.36s/it]
 44%|████▎     | 27006/61904 [3:19:45<13:06:35,  1.35s/it]
 44%|████▎     | 27007/61904 [3:19:47<13:12:12,  1.36s/it]
 44%|████▎     | 27008/61904 [3:19:48<13:23:55,  1.38s/it]
 44%|████▎     | 27009/61904 [3:19:50<13:34:48,  1.40s/it]
 44%|████▎     | 27010/61904 [3:19:51<13:19:55,  1.38s/it]
 44%|████▎     | 27011/61904 [3:19:52<13:00:39,  1.34s/it]
 44%|████▎     | 27012/61904 [3:19:54<13:07:49,  1.35s/it]
 44%|████▎     | 27013/61904 [3:19:55<13:11:22,  1.36s/it]
 44%|████▎     | 27014/61904 [3:19:56<12:59:55,  1.34s/it]
 44%|████▎     | 27015/61904 [3:19:58<13:20:11,  1.38s/it]
 44%|████▎     | 27016/61904 [3:19:59<12:52:23,  1.33s/it]
 44%|████▎     | 27017/61904 [3:20:00<13:06:05,  1.35s/it]
 44%|████▎     | 27018/61904 [3:20:02<13:11:41,  1.36s/it]
 44%|████▎     | 27019/61904 [3:20:03<13:11:01,  1.36s/it]
 44%|████▎     | 27020/61904 [3:20:04<13:02:45,  1.35s/it]
                                                          
{'loss': 2.6422, 'learning_rate': 1.5653442240373395e-07, 'epoch': 6.98}

 44%|████▎     | 27020/61904 [3:20:04<13:02:45,  1.35s/it]
 44%|████▎     | 27021/61904 [3:20:06<13:12:11,  1.36s/it]
 44%|████▎     | 27022/61904 [3:20:07<13:05:08,  1.35s/it]
 44%|████▎     | 27023/61904 [3:20:08<13:01:15,  1.34s/it]
 44%|████▎     | 27024/61904 [3:20:10<13:49:46,  1.43s/it]
 44%|████▎     | 27025/61904 [3:20:11<13:48:41,  1.43s/it]
 44%|████▎     | 27026/61904 [3:20:13<13:42:07,  1.41s/it]
 44%|████▎     | 27027/61904 [3:20:14<13:35:33,  1.40s/it]
 44%|████▎     | 27028/61904 [3:20:15<13:00:06,  1.34s/it]
 44%|████▎     | 27029/61904 [3:20:17<12:53:06,  1.33s/it]
 44%|████▎     | 27030/61904 [3:20:18<13:06:40,  1.35s/it]
 44%|████▎     | 27031/61904 [3:20:19<13:01:37,  1.34s/it]
 44%|████▎     | 27032/61904 [3:20:21<12:49:53,  1.32s/it]
 44%|████▎     | 27033/61904 [3:20:22<12:54:17,  1.33s/it]
 44%|████▎     | 27034/61904 [3:20:23<13:01:05,  1.34s/it]
 44%|████▎     | 27035/61904 [3:20:25<13:06:51,  1.35s/it]
 44%|████▎     | 27036/61904 [3:20:26<13:14:55,  1.37s/it]
 44%|████▎     | 27037/61904 [3:20:28<13:07:59,  1.36s/it]
 44%|████▎     | 27038/61904 [3:20:29<13:16:09,  1.37s/it]
 44%|████▎     | 27039/61904 [3:20:30<13:16:08,  1.37s/it]
 44%|████▎     | 27040/61904 [3:20:32<12:49:24,  1.32s/it]
                                                          
{'loss': 2.6273, 'learning_rate': 1.5650200959419161e-07, 'epoch': 6.99}

 44%|████▎     | 27040/61904 [3:20:32<12:49:24,  1.32s/it]
 44%|████▎     | 27041/61904 [3:20:33<12:54:50,  1.33s/it]
 44%|████▎     | 27042/61904 [3:20:34<12:58:48,  1.34s/it]
 44%|████▎     | 27043/61904 [3:20:36<13:03:49,  1.35s/it]
 44%|████▎     | 27044/61904 [3:20:37<13:17:42,  1.37s/it]
 44%|████▎     | 27045/61904 [3:20:38<13:20:44,  1.38s/it]
 44%|████▎     | 27046/61904 [3:20:40<13:23:06,  1.38s/it]
 44%|████▎     | 27047/61904 [3:20:41<13:31:23,  1.40s/it]
 44%|████▎     | 27048/61904 [3:20:43<13:34:02,  1.40s/it]
 44%|████▎     | 27049/61904 [3:20:44<13:07:12,  1.36s/it]
 44%|████▎     | 27050/61904 [3:20:45<13:26:55,  1.39s/it]
 44%|████▎     | 27051/61904 [3:20:47<13:04:15,  1.35s/it]
 44%|████▎     | 27052/61904 [3:20:48<13:40:36,  1.41s/it]
 44%|████▎     | 27053/61904 [3:20:50<13:20:15,  1.38s/it]
 44%|████▎     | 27054/61904 [3:20:51<13:18:27,  1.37s/it]
 44%|████▎     | 27055/61904 [3:20:52<13:16:21,  1.37s/it]
 44%|████▎     | 27056/61904 [3:20:54<13:24:21,  1.38s/it]
 44%|████▎     | 27057/61904 [3:20:55<13:12:26,  1.36s/it]
 44%|████▎     | 27058/61904 [3:20:56<12:52:45,  1.33s/it]
 44%|████▎     | 27059/61904 [3:20:57<12:35:33,  1.30s/it]
 44%|████▎     | 27060/61904 [3:20:59<12:42:13,  1.31s/it]
                                                          
{'loss': 2.5851, 'learning_rate': 1.5646959678464928e-07, 'epoch': 6.99}

 44%|████▎     | 27060/61904 [3:20:59<12:42:13,  1.31s/it]
 44%|████▎     | 27061/61904 [3:21:00<12:26:42,  1.29s/it]
 44%|████▎     | 27062/61904 [3:21:01<12:30:02,  1.29s/it]
 44%|████▎     | 27063/61904 [3:21:03<12:48:25,  1.32s/it]
 44%|████▎     | 27064/61904 [3:21:04<12:41:24,  1.31s/it]
 44%|████▎     | 27065/61904 [3:21:05<13:01:38,  1.35s/it]
 44%|████▎     | 27066/61904 [3:21:07<12:56:59,  1.34s/it]
 44%|████▎     | 27067/61904 [3:21:08<13:06:04,  1.35s/it]
 44%|████▎     | 27068/61904 [3:21:09<12:52:26,  1.33s/it]
 44%|████▎     | 27069/61904 [3:21:11<12:55:37,  1.34s/it]
 44%|████▎     | 27070/61904 [3:21:12<12:47:46,  1.32s/it]
 44%|████▎     | 27071/61904 [3:21:13<13:03:38,  1.35s/it]
 44%|████▎     | 27072/61904 [3:21:15<12:38:23,  1.31s/it]
 44%|████▎     | 27073/61904 [3:21:16<12:53:31,  1.33s/it]
 44%|████▎     | 27074/61904 [3:21:17<12:35:54,  1.30s/it]
 44%|████▎     | 27075/61904 [3:21:19<13:07:03,  1.36s/it]
 44%|████▎     | 27076/61904 [3:21:20<13:18:44,  1.38s/it]
 44%|████▎     | 27077/61904 [3:21:22<13:13:51,  1.37s/it]
 44%|████▎     | 27078/61904 [3:21:23<14:13:24,  1.47s/it]
 44%|████▎     | 27079/61904 [3:21:25<13:43:57,  1.42s/it]
 44%|████▎     | 27080/61904 [3:21:26<13:48:38,  1.43s/it]
                                                          
{'loss': 2.5716, 'learning_rate': 1.5643718397510696e-07, 'epoch': 7.0}

 44%|████▎     | 27080/61904 [3:21:26<13:48:38,  1.43s/it]
 44%|████▎     | 27081/61904 [3:21:27<13:33:51,  1.40s/it]
 44%|████▎     | 27082/61904 [3:21:29<13:36:15,  1.41s/it]
 44%|████▍     | 27083/61904 [3:21:30<13:10:55,  1.36s/it]
 44%|████▍     | 27084/61904 [3:21:31<13:17:20,  1.37s/it]Generation Kwargs:
{'max_length': 384, 'max_gen_length': 380, 'num_beams': 5}


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

  0%|          | 2/861 [00:00<04:25,  3.23it/s]

  0%|          | 3/861 [00:02<12:15,  1.17it/s]

  0%|          | 4/861 [00:04<20:29,  1.43s/it]

  1%|          | 5/861 [00:05<19:09,  1.34s/it]

  1%|          | 6/861 [00:07<19:31,  1.37s/it]

  1%|          | 7/861 [00:08<17:06,  1.20s/it]

  1%|          | 8/861 [00:09<17:58,  1.26s/it]

  1%|          | 9/861 [00:10<15:12,  1.07s/it]

  1%|          | 10/861 [00:10<14:04,  1.01it/s]

  1%|▏         | 11/861 [00:12<15:41,  1.11s/it]

  1%|▏         | 12/861 [00:13<15:14,  1.08s/it]

  2%|▏         | 13/861 [00:14<14:05,  1.00it/s]

  2%|▏         | 14/861 [00:14<11:32,  1.22it/s]

  2%|▏         | 15/861 [00:15<11:17,  1.25it/s]

  2%|▏         | 16/861 [00:15<09:51,  1.43it/s]

  2%|▏         | 17/861 [00:17<12:40,  1.11it/s]

  2%|▏         | 18/861 [00:17<10:15,  1.37it/s]

  2%|▏         | 19/861 [00:18<09:37,  1.46it/s]

  2%|▏         | 20/861 [00:20<16:07,  1.15s/it]

  2%|▏         | 21/861 [00:22<19:20,  1.38s/it]

  3%|▎         | 22/861 [00:23<17:49,  1.27s/it]

  3%|▎         | 23/861 [00:23<13:52,  1.01it/s]

  3%|▎         | 24/861 [00:24<12:33,  1.11it/s]

  3%|▎         | 25/861 [00:25<13:02,  1.07it/s]

  3%|▎         | 26/861 [00:26<13:46,  1.01it/s]

  3%|▎         | 27/861 [00:27<14:35,  1.05s/it]

  3%|▎         | 28/861 [00:30<20:21,  1.47s/it]

  3%|▎         | 29/861 [00:30<16:35,  1.20s/it]

  3%|▎         | 30/861 [00:31<16:21,  1.18s/it]

  4%|▎         | 31/861 [00:32<13:11,  1.05it/s]

  4%|▎         | 32/861 [00:32<10:58,  1.26it/s]

  4%|▍         | 33/861 [00:33<12:34,  1.10it/s]

  4%|▍         | 34/861 [00:34<12:40,  1.09it/s]

  4%|▍         | 35/861 [00:36<15:21,  1.12s/it]

  4%|▍         | 36/861 [00:37<13:49,  1.01s/it]

  4%|▍         | 37/861 [00:37<12:49,  1.07it/s]

  4%|▍         | 38/861 [00:39<14:26,  1.05s/it]

  5%|▍         | 39/861 [00:39<13:44,  1.00s/it]

  5%|▍         | 40/861 [00:40<12:39,  1.08it/s]

  5%|▍         | 41/861 [00:41<10:22,  1.32it/s]

  5%|▍         | 42/861 [00:42<11:22,  1.20it/s]

  5%|▍         | 43/861 [00:43<12:22,  1.10it/s]

  5%|▌         | 44/861 [00:43<11:37,  1.17it/s]

  5%|▌         | 45/861 [00:44<11:27,  1.19it/s]

  5%|▌         | 46/861 [00:50<31:26,  2.31s/it]

  5%|▌         | 47/861 [00:51<26:54,  1.98s/it]

  6%|▌         | 48/861 [00:53<25:52,  1.91s/it]

  6%|▌         | 49/861 [00:54<23:49,  1.76s/it]

  6%|▌         | 50/861 [00:55<17:35,  1.30s/it]

  6%|▌         | 51/861 [00:55<15:38,  1.16s/it]

  6%|▌         | 52/861 [00:56<13:27,  1.00it/s]

  6%|▌         | 53/861 [00:57<11:44,  1.15it/s]

  6%|▋         | 54/861 [00:57<09:58,  1.35it/s]

  6%|▋         | 55/861 [00:58<09:25,  1.43it/s]

  7%|▋         | 56/861 [00:59<10:11,  1.32it/s]

  7%|▋         | 57/861 [00:59<08:40,  1.54it/s]

  7%|▋         | 58/861 [00:59<07:28,  1.79it/s]

  7%|▋         | 59/861 [01:00<08:26,  1.58it/s]

  7%|▋         | 60/861 [01:01<08:01,  1.66it/s]

  7%|▋         | 61/861 [01:01<08:42,  1.53it/s]

  7%|▋         | 62/861 [01:02<07:19,  1.82it/s]

  7%|▋         | 63/861 [01:02<07:04,  1.88it/s]

  7%|▋         | 64/861 [01:03<09:28,  1.40it/s]

  8%|▊         | 65/861 [01:04<10:17,  1.29it/s]

  8%|▊         | 66/861 [01:05<08:58,  1.48it/s]

  8%|▊         | 67/861 [01:05<09:19,  1.42it/s]

  8%|▊         | 68/861 [01:07<11:00,  1.20it/s]

  8%|▊         | 69/861 [01:08<12:50,  1.03it/s]

  8%|▊         | 70/861 [01:09<14:22,  1.09s/it]

  8%|▊         | 71/861 [01:11<16:07,  1.23s/it]

  8%|▊         | 72/861 [01:12<14:39,  1.12s/it]

  8%|▊         | 73/861 [01:12<11:17,  1.16it/s]

  9%|▊         | 74/861 [01:13<10:20,  1.27it/s]

  9%|▊         | 75/861 [01:14<11:54,  1.10it/s]

  9%|▉         | 76/861 [01:15<12:47,  1.02it/s]

  9%|▉         | 77/861 [01:16<12:27,  1.05it/s]

  9%|▉         | 78/861 [01:17<11:40,  1.12it/s]

  9%|▉         | 79/861 [01:17<11:09,  1.17it/s]

  9%|▉         | 80/861 [01:18<10:20,  1.26it/s]

  9%|▉         | 81/861 [01:19<11:03,  1.18it/s]

 10%|▉         | 82/861 [01:20<10:04,  1.29it/s]

 10%|▉         | 83/861 [01:20<10:19,  1.26it/s]

 10%|▉         | 84/861 [01:22<12:12,  1.06it/s]

 10%|▉         | 85/861 [01:22<10:51,  1.19it/s]

 10%|▉         | 86/861 [01:23<09:48,  1.32it/s]

 10%|█         | 87/861 [01:24<11:03,  1.17it/s]

 10%|█         | 88/861 [01:24<08:37,  1.49it/s]

 10%|█         | 89/861 [01:26<11:24,  1.13it/s]

 10%|█         | 90/861 [01:26<11:01,  1.17it/s]

 11%|█         | 91/861 [01:28<13:39,  1.06s/it]

 11%|█         | 92/861 [01:29<14:27,  1.13s/it]

 11%|█         | 93/861 [01:31<16:25,  1.28s/it]

 11%|█         | 94/861 [01:31<12:23,  1.03it/s]

 11%|█         | 95/861 [01:32<10:28,  1.22it/s]

 11%|█         | 96/861 [01:32<10:43,  1.19it/s]

 11%|█▏        | 97/861 [01:34<12:02,  1.06it/s]

 11%|█▏        | 98/861 [01:35<12:23,  1.03it/s]

 11%|█▏        | 99/861 [01:37<16:14,  1.28s/it]

 12%|█▏        | 100/861 [01:37<13:30,  1.06s/it]

 12%|█▏        | 101/861 [01:38<11:49,  1.07it/s]

 12%|█▏        | 102/861 [01:39<10:59,  1.15it/s]

 12%|█▏        | 103/861 [01:39<08:57,  1.41it/s]

 12%|█▏        | 104/861 [01:40<10:48,  1.17it/s]

 12%|█▏        | 105/861 [01:41<11:11,  1.13it/s]

 12%|█▏        | 106/861 [01:42<09:51,  1.28it/s]

 12%|█▏        | 107/861 [01:42<09:10,  1.37it/s]

 13%|█▎        | 108/861 [01:42<07:18,  1.72it/s]

 13%|█▎        | 109/861 [01:43<06:08,  2.04it/s]

 13%|█▎        | 110/861 [01:44<08:00,  1.56it/s]

 13%|█▎        | 111/861 [01:45<09:38,  1.30it/s]

 13%|█▎        | 112/861 [01:46<09:43,  1.28it/s]

 13%|█▎        | 113/861 [01:47<11:10,  1.12it/s]

 13%|█▎        | 114/861 [01:48<12:16,  1.01it/s]

 13%|█▎        | 115/861 [01:49<12:09,  1.02it/s]

 13%|█▎        | 116/861 [01:49<09:54,  1.25it/s]

 14%|█▎        | 117/861 [01:51<15:00,  1.21s/it]

 14%|█▎        | 118/861 [01:52<13:42,  1.11s/it]

 14%|█▍        | 119/861 [01:53<11:37,  1.06it/s]

 14%|█▍        | 120/861 [01:53<08:56,  1.38it/s]

 14%|█▍        | 121/861 [01:55<14:20,  1.16s/it]

 14%|█▍        | 122/861 [01:56<13:48,  1.12s/it]

 14%|█▍        | 123/861 [01:57<13:59,  1.14s/it]

 14%|█▍        | 124/861 [01:58<13:04,  1.06s/it]

 15%|█▍        | 125/861 [01:59<11:50,  1.04it/s]

 15%|█▍        | 126/861 [02:00<12:00,  1.02it/s]

 15%|█▍        | 127/861 [02:02<14:28,  1.18s/it]

 15%|█▍        | 128/861 [02:02<12:39,  1.04s/it]

 15%|█▍        | 129/861 [02:03<12:33,  1.03s/it]

 15%|█▌        | 130/861 [02:04<11:43,  1.04it/s]

 15%|█▌        | 131/861 [02:05<12:12,  1.00s/it]

 15%|█▌        | 132/861 [02:06<11:45,  1.03it/s]

 15%|█▌        | 133/861 [02:07<12:19,  1.02s/it]

 16%|█▌        | 134/861 [02:08<09:31,  1.27it/s]

 16%|█▌        | 135/861 [02:08<08:14,  1.47it/s]

 16%|█▌        | 136/861 [02:09<08:52,  1.36it/s]

 16%|█▌        | 137/861 [02:09<07:24,  1.63it/s]

 16%|█▌        | 138/861 [02:10<07:51,  1.53it/s]

 16%|█▌        | 139/861 [02:11<08:26,  1.43it/s]

 16%|█▋        | 140/861 [02:11<07:16,  1.65it/s]

 16%|█▋        | 141/861 [02:12<07:38,  1.57it/s]

 16%|█▋        | 142/861 [02:12<06:43,  1.78it/s]

 17%|█▋        | 143/861 [02:14<12:11,  1.02s/it]

 17%|█▋        | 144/861 [02:16<12:44,  1.07s/it]

 17%|█▋        | 145/861 [02:16<10:34,  1.13it/s]

 17%|█▋        | 146/861 [02:17<10:52,  1.10it/s]

 17%|█▋        | 147/861 [02:18<10:41,  1.11it/s]

 17%|█▋        | 148/861 [02:18<09:11,  1.29it/s]

 17%|█▋        | 149/861 [02:19<07:41,  1.54it/s]

 17%|█▋        | 150/861 [02:20<10:45,  1.10it/s]

 18%|█▊        | 151/861 [02:22<13:29,  1.14s/it]

 18%|█▊        | 152/861 [02:23<12:53,  1.09s/it]

 18%|█▊        | 153/861 [02:24<13:15,  1.12s/it]

 18%|█▊        | 154/861 [02:25<11:51,  1.01s/it]

 18%|█▊        | 155/861 [02:26<13:19,  1.13s/it]

 18%|█▊        | 156/861 [02:28<14:13,  1.21s/it]

 18%|█▊        | 157/861 [02:28<12:56,  1.10s/it]

 18%|█▊        | 158/861 [02:31<16:13,  1.38s/it]

 18%|█▊        | 159/861 [02:32<16:47,  1.43s/it]

 19%|█▊        | 160/861 [02:33<14:23,  1.23s/it]

 19%|█▊        | 161/861 [02:35<17:07,  1.47s/it]

 19%|█▉        | 162/861 [02:35<12:53,  1.11s/it]

 19%|█▉        | 163/861 [02:35<09:54,  1.17it/s]

 19%|█▉        | 164/861 [02:37<10:55,  1.06it/s]

 19%|█▉        | 165/861 [02:38<12:53,  1.11s/it]

 19%|█▉        | 166/861 [02:39<12:16,  1.06s/it]

 19%|█▉        | 167/861 [02:39<09:26,  1.23it/s]

 20%|█▉        | 168/861 [02:40<07:44,  1.49it/s]

 20%|█▉        | 169/861 [02:40<07:54,  1.46it/s]

 20%|█▉        | 170/861 [02:41<08:19,  1.38it/s]

 20%|█▉        | 171/861 [02:42<09:14,  1.24it/s]

 20%|█▉        | 172/861 [02:43<10:01,  1.15it/s]

 20%|██        | 173/861 [02:44<11:43,  1.02s/it]

 20%|██        | 174/861 [02:46<14:36,  1.28s/it]

 20%|██        | 175/861 [02:47<12:02,  1.05s/it]

 20%|██        | 176/861 [02:47<09:15,  1.23it/s]

 21%|██        | 177/861 [02:48<09:04,  1.26it/s]

 21%|██        | 178/861 [02:49<09:20,  1.22it/s]

 21%|██        | 179/861 [02:50<09:08,  1.24it/s]

 21%|██        | 180/861 [02:50<08:39,  1.31it/s]

 21%|██        | 181/861 [02:51<07:25,  1.53it/s]

 21%|██        | 182/861 [02:51<06:21,  1.78it/s]

 21%|██▏       | 183/861 [02:52<07:18,  1.55it/s]

 21%|██▏       | 184/861 [02:53<10:13,  1.10it/s]

 21%|██▏       | 185/861 [02:54<08:48,  1.28it/s]

 22%|██▏       | 186/861 [02:54<07:52,  1.43it/s]

 22%|██▏       | 187/861 [02:55<08:03,  1.39it/s]

 22%|██▏       | 188/861 [02:56<08:59,  1.25it/s]

 22%|██▏       | 189/861 [02:57<10:44,  1.04it/s]

 22%|██▏       | 190/861 [02:58<10:22,  1.08it/s]

 22%|██▏       | 191/861 [02:59<08:54,  1.25it/s]

 22%|██▏       | 192/861 [03:00<11:10,  1.00s/it]

 22%|██▏       | 193/861 [03:01<11:53,  1.07s/it]

 23%|██▎       | 194/861 [03:02<11:09,  1.00s/it]

 23%|██▎       | 195/861 [03:03<09:05,  1.22it/s]

 23%|██▎       | 196/861 [03:03<07:50,  1.41it/s]

 23%|██▎       | 197/861 [03:04<09:50,  1.12it/s]

 23%|██▎       | 198/861 [03:05<08:09,  1.36it/s]

 23%|██▎       | 199/861 [03:06<08:04,  1.37it/s]

 23%|██▎       | 200/861 [03:08<12:18,  1.12s/it]

 23%|██▎       | 201/861 [03:09<12:08,  1.10s/it]

 23%|██▎       | 202/861 [03:09<11:19,  1.03s/it]

 24%|██▎       | 203/861 [03:11<12:17,  1.12s/it]

 24%|██▎       | 204/861 [03:11<09:21,  1.17it/s]

 24%|██▍       | 205/861 [03:11<07:47,  1.40it/s]

 24%|██▍       | 206/861 [03:12<07:46,  1.40it/s]

 24%|██▍       | 207/861 [03:13<07:37,  1.43it/s]

 24%|██▍       | 208/861 [03:13<07:04,  1.54it/s]

 24%|██▍       | 209/861 [03:14<07:55,  1.37it/s]

 24%|██▍       | 210/861 [03:16<10:11,  1.07it/s]

 25%|██▍       | 211/861 [03:17<11:30,  1.06s/it]

 25%|██▍       | 212/861 [03:19<13:18,  1.23s/it]

 25%|██▍       | 213/861 [03:20<13:30,  1.25s/it]

 25%|██▍       | 214/861 [03:20<11:08,  1.03s/it]

 25%|██▍       | 215/861 [03:21<10:28,  1.03it/s]

 25%|██▌       | 216/861 [03:22<08:41,  1.24it/s]

 25%|██▌       | 217/861 [03:22<06:55,  1.55it/s]

 25%|██▌       | 218/861 [03:22<06:03,  1.77it/s]

 25%|██▌       | 219/861 [03:23<07:50,  1.36it/s]

 26%|██▌       | 220/861 [03:25<11:10,  1.05s/it]

 26%|██▌       | 221/861 [03:26<11:31,  1.08s/it]

 26%|██▌       | 222/861 [03:28<12:32,  1.18s/it]

 26%|██▌       | 223/861 [03:29<11:58,  1.13s/it]

 26%|██▌       | 224/861 [03:29<10:03,  1.06it/s]

 26%|██▌       | 225/861 [03:30<10:25,  1.02it/s]

 26%|██▌       | 226/861 [03:32<12:17,  1.16s/it]

 26%|██▋       | 227/861 [03:33<11:30,  1.09s/it]

 26%|██▋       | 228/861 [03:34<10:32,  1.00it/s]

 27%|██▋       | 229/861 [03:34<09:12,  1.14it/s]

 27%|██▋       | 230/861 [03:35<09:58,  1.05it/s]

 27%|██▋       | 231/861 [03:38<13:41,  1.30s/it]

 27%|██▋       | 232/861 [03:38<10:18,  1.02it/s]

 27%|██▋       | 233/861 [03:38<09:24,  1.11it/s]

 27%|██▋       | 234/861 [03:39<08:31,  1.23it/s]

 27%|██▋       | 235/861 [03:40<07:18,  1.43it/s]

 27%|██▋       | 236/861 [03:41<08:09,  1.28it/s]

 28%|██▊       | 237/861 [03:41<08:23,  1.24it/s]

 28%|██▊       | 238/861 [03:42<06:46,  1.53it/s]

 28%|██▊       | 239/861 [03:44<11:53,  1.15s/it]

 28%|██▊       | 240/861 [03:45<11:35,  1.12s/it]

 28%|██▊       | 241/861 [03:46<12:29,  1.21s/it]

 28%|██▊       | 242/861 [03:48<12:49,  1.24s/it]

 28%|██▊       | 243/861 [03:48<11:06,  1.08s/it]

 28%|██▊       | 244/861 [03:49<10:18,  1.00s/it]

 28%|██▊       | 245/861 [03:50<10:24,  1.01s/it]

 29%|██▊       | 246/861 [03:51<09:46,  1.05it/s]

 29%|██▊       | 247/861 [03:52<08:36,  1.19it/s]

 29%|██▉       | 248/861 [03:52<06:38,  1.54it/s]

 29%|██▉       | 249/861 [03:53<06:57,  1.46it/s]

 29%|██▉       | 250/861 [03:53<06:13,  1.64it/s]

 29%|██▉       | 251/861 [03:55<09:04,  1.12it/s]

 29%|██▉       | 252/861 [03:55<08:12,  1.24it/s]

 29%|██▉       | 253/861 [03:56<07:09,  1.42it/s]

 30%|██▉       | 254/861 [03:56<05:50,  1.73it/s]

 30%|██▉       | 255/861 [03:57<06:37,  1.52it/s]

 30%|██▉       | 256/861 [03:58<08:30,  1.18it/s]

 30%|██▉       | 257/861 [03:59<08:24,  1.20it/s]

 30%|██▉       | 258/861 [04:01<10:47,  1.07s/it]

 30%|███       | 259/861 [04:02<12:19,  1.23s/it]

 30%|███       | 260/861 [04:04<13:21,  1.33s/it]

 30%|███       | 261/861 [04:06<15:15,  1.53s/it]

 30%|███       | 262/861 [04:06<12:41,  1.27s/it]

 31%|███       | 263/861 [04:07<09:26,  1.06it/s]

 31%|███       | 264/861 [04:08<10:03,  1.01s/it]

 31%|███       | 265/861 [04:08<08:36,  1.15it/s]

 31%|███       | 266/861 [04:09<07:33,  1.31it/s]

 31%|███       | 267/861 [04:10<07:43,  1.28it/s]

 31%|███       | 268/861 [04:11<08:06,  1.22it/s]

 31%|███       | 269/861 [04:12<08:39,  1.14it/s]

 31%|███▏      | 270/861 [04:12<08:09,  1.21it/s]

 31%|███▏      | 271/861 [04:13<07:34,  1.30it/s]

 32%|███▏      | 272/861 [04:14<08:47,  1.12it/s]

 32%|███▏      | 273/861 [04:16<10:25,  1.06s/it]

 32%|███▏      | 274/861 [04:17<11:41,  1.20s/it]

 32%|███▏      | 275/861 [04:17<09:02,  1.08it/s]

 32%|███▏      | 276/861 [04:18<08:07,  1.20it/s]

 32%|███▏      | 277/861 [04:20<11:38,  1.20s/it]

 32%|███▏      | 278/861 [04:21<11:04,  1.14s/it]

 32%|███▏      | 279/861 [04:22<09:59,  1.03s/it]

 33%|███▎      | 280/861 [04:23<10:05,  1.04s/it]

 33%|███▎      | 281/861 [04:24<09:53,  1.02s/it]

 33%|███▎      | 282/861 [04:26<12:12,  1.27s/it]

 33%|███▎      | 283/861 [04:26<10:24,  1.08s/it]

 33%|███▎      | 284/861 [04:27<08:18,  1.16it/s]

 33%|███▎      | 285/861 [04:28<09:34,  1.00it/s]

 33%|███▎      | 286/861 [04:30<11:59,  1.25s/it]

 33%|███▎      | 287/861 [04:31<12:42,  1.33s/it]

 33%|███▎      | 288/861 [04:32<11:30,  1.20s/it]

 34%|███▎      | 289/861 [04:33<10:16,  1.08s/it]

 34%|███▎      | 290/861 [04:34<08:59,  1.06it/s]

 34%|███▍      | 291/861 [04:34<07:56,  1.20it/s]

 34%|███▍      | 292/861 [04:35<08:49,  1.07it/s]

 34%|███▍      | 293/861 [04:36<08:10,  1.16it/s]

 34%|███▍      | 294/861 [04:37<08:20,  1.13it/s]

 34%|███▍      | 295/861 [04:37<06:39,  1.42it/s]

 34%|███▍      | 296/861 [04:38<06:17,  1.50it/s]

 34%|███▍      | 297/861 [04:39<06:59,  1.34it/s]

 35%|███▍      | 298/861 [04:41<10:42,  1.14s/it]

 35%|███▍      | 299/861 [04:43<12:25,  1.33s/it]

 35%|███▍      | 300/861 [04:43<10:50,  1.16s/it]

 35%|███▍      | 301/861 [04:46<13:45,  1.47s/it]

 35%|███▌      | 302/861 [04:46<10:16,  1.10s/it]

 35%|███▌      | 303/861 [04:48<13:13,  1.42s/it]

 35%|███▌      | 304/861 [04:49<13:00,  1.40s/it]

 35%|███▌      | 305/861 [04:51<13:54,  1.50s/it]

 36%|███▌      | 306/861 [04:52<13:23,  1.45s/it]

 36%|███▌      | 307/861 [04:54<14:32,  1.57s/it]

 36%|███▌      | 308/861 [04:55<10:48,  1.17s/it]

 36%|███▌      | 309/861 [04:56<12:21,  1.34s/it]

 36%|███▌      | 310/861 [04:58<13:28,  1.47s/it]

 36%|███▌      | 311/861 [05:00<13:42,  1.49s/it]

 36%|███▌      | 312/861 [05:02<15:26,  1.69s/it]

 36%|███▋      | 313/861 [05:03<13:29,  1.48s/it]

 36%|███▋      | 314/861 [05:04<13:45,  1.51s/it]

 37%|███▋      | 315/861 [05:05<12:10,  1.34s/it]

 37%|███▋      | 316/861 [05:07<13:40,  1.51s/it]

 37%|███▋      | 317/861 [05:07<10:16,  1.13s/it]

 37%|███▋      | 318/861 [05:10<12:51,  1.42s/it]

 37%|███▋      | 319/861 [05:11<13:58,  1.55s/it]

 37%|███▋      | 320/861 [05:12<12:10,  1.35s/it]

 37%|███▋      | 321/861 [05:14<12:40,  1.41s/it]

 37%|███▋      | 322/861 [05:16<14:27,  1.61s/it]

 38%|███▊      | 323/861 [05:17<13:15,  1.48s/it]

 38%|███▊      | 324/861 [05:19<13:11,  1.47s/it]

 38%|███▊      | 325/861 [05:21<14:30,  1.62s/it]

 38%|███▊      | 326/861 [05:21<10:50,  1.22s/it]

 38%|███▊      | 327/861 [05:22<09:57,  1.12s/it]

 38%|███▊      | 328/861 [05:23<09:26,  1.06s/it]

 38%|███▊      | 329/861 [05:24<09:31,  1.07s/it]

 38%|███▊      | 330/861 [05:26<13:00,  1.47s/it]

 38%|███▊      | 331/861 [05:30<19:19,  2.19s/it]

 39%|███▊      | 332/861 [05:31<15:39,  1.78s/it]

 39%|███▊      | 333/861 [05:32<14:20,  1.63s/it]

 39%|███▉      | 334/861 [05:34<14:22,  1.64s/it]

 39%|███▉      | 335/861 [05:35<12:24,  1.42s/it]

 39%|███▉      | 336/861 [05:36<12:14,  1.40s/it]

 39%|███▉      | 337/861 [05:37<11:24,  1.31s/it]

 39%|███▉      | 338/861 [05:38<09:44,  1.12s/it]

 39%|███▉      | 339/861 [05:40<11:49,  1.36s/it]

 39%|███▉      | 340/861 [05:41<12:32,  1.44s/it]

 40%|███▉      | 341/861 [05:42<09:44,  1.12s/it]

 40%|███▉      | 342/861 [05:43<09:22,  1.08s/it]

 40%|███▉      | 343/861 [05:44<08:50,  1.02s/it]

 40%|███▉      | 344/861 [05:44<07:43,  1.12it/s]

 40%|████      | 345/861 [05:45<08:49,  1.03s/it]

 40%|████      | 346/861 [05:47<08:59,  1.05s/it]

 40%|████      | 347/861 [05:48<09:54,  1.16s/it]

 40%|████      | 348/861 [05:49<08:20,  1.02it/s]

 41%|████      | 349/861 [05:49<07:21,  1.16it/s]

 41%|████      | 350/861 [05:50<07:33,  1.13it/s]

 41%|████      | 351/861 [05:52<09:23,  1.11s/it]

 41%|████      | 352/861 [05:53<10:12,  1.20s/it]

 41%|████      | 353/861 [05:54<10:22,  1.23s/it]

 41%|████      | 354/861 [05:55<08:58,  1.06s/it]

 41%|████      | 355/861 [05:56<07:25,  1.13it/s]

 41%|████▏     | 356/861 [05:56<07:03,  1.19it/s]

 41%|████▏     | 357/861 [05:57<06:01,  1.39it/s]

 42%|████▏     | 358/861 [05:57<06:02,  1.39it/s]

 42%|████▏     | 359/861 [05:59<07:56,  1.05it/s]

 42%|████▏     | 360/861 [06:00<08:14,  1.01it/s]

 42%|████▏     | 361/861 [06:01<08:05,  1.03it/s]

 42%|████▏     | 362/861 [06:02<08:14,  1.01it/s]

 42%|████▏     | 363/861 [06:03<07:59,  1.04it/s]

 42%|████▏     | 364/861 [06:04<07:16,  1.14it/s]

 42%|████▏     | 365/861 [06:07<13:25,  1.62s/it]

 43%|████▎     | 366/861 [06:08<11:35,  1.41s/it]

 43%|████▎     | 367/861 [06:09<11:31,  1.40s/it]

 43%|████▎     | 368/861 [06:10<10:59,  1.34s/it]

 43%|████▎     | 369/861 [06:11<10:21,  1.26s/it]

 43%|████▎     | 370/861 [06:12<09:02,  1.10s/it]

 43%|████▎     | 371/861 [06:13<08:19,  1.02s/it]

 43%|████▎     | 372/861 [06:16<11:54,  1.46s/it]

 43%|████▎     | 373/861 [06:16<10:31,  1.29s/it]

 43%|████▎     | 374/861 [06:19<13:28,  1.66s/it]

 44%|████▎     | 375/861 [06:21<14:23,  1.78s/it]

 44%|████▎     | 376/861 [06:22<11:32,  1.43s/it]

 44%|████▍     | 377/861 [06:23<11:58,  1.48s/it]

 44%|████▍     | 378/861 [06:25<11:50,  1.47s/it]

 44%|████▍     | 379/861 [06:25<08:48,  1.10s/it]

 44%|████▍     | 380/861 [06:26<08:34,  1.07s/it]

 44%|████▍     | 381/861 [06:27<08:22,  1.05s/it]

 44%|████▍     | 382/861 [06:27<07:14,  1.10it/s]

 44%|████▍     | 383/861 [06:28<07:12,  1.10it/s]

 45%|████▍     | 384/861 [06:29<07:07,  1.12it/s]

 45%|████▍     | 385/861 [06:29<05:34,  1.42it/s]

 45%|████▍     | 386/861 [06:31<07:04,  1.12it/s]

 45%|████▍     | 387/861 [06:32<08:14,  1.04s/it]

 45%|████▌     | 388/861 [06:33<07:20,  1.07it/s]

 45%|████▌     | 389/861 [06:33<06:28,  1.22it/s]

 45%|████▌     | 390/861 [06:34<05:55,  1.32it/s]

 45%|████▌     | 391/861 [06:35<06:40,  1.17it/s]

 46%|████▌     | 392/861 [06:36<06:24,  1.22it/s]

 46%|████▌     | 393/861 [06:37<07:33,  1.03it/s]

 46%|████▌     | 394/861 [06:38<07:44,  1.01it/s]

 46%|████▌     | 395/861 [06:39<07:52,  1.01s/it]

 46%|████▌     | 396/861 [06:40<08:04,  1.04s/it]

 46%|████▌     | 397/861 [06:41<06:08,  1.26it/s]

 46%|████▌     | 398/861 [06:41<06:03,  1.27it/s]

 46%|████▋     | 399/861 [06:42<06:44,  1.14it/s]

 46%|████▋     | 400/861 [06:44<07:15,  1.06it/s]

 47%|████▋     | 401/861 [06:44<06:52,  1.12it/s]

 47%|████▋     | 402/861 [06:45<07:06,  1.08it/s]

 47%|████▋     | 403/861 [06:46<06:50,  1.12it/s]

 47%|████▋     | 404/861 [06:47<07:06,  1.07it/s]

 47%|████▋     | 405/861 [06:48<05:54,  1.29it/s]

 47%|████▋     | 406/861 [06:49<06:41,  1.13it/s]

 47%|████▋     | 407/861 [06:50<06:43,  1.12it/s]

 47%|████▋     | 408/861 [06:50<06:08,  1.23it/s]

 48%|████▊     | 409/861 [06:52<07:02,  1.07it/s]

 48%|████▊     | 410/861 [06:52<07:04,  1.06it/s]

 48%|████▊     | 411/861 [06:53<06:27,  1.16it/s]

 48%|████▊     | 412/861 [06:55<09:02,  1.21s/it]

 48%|████▊     | 413/861 [06:56<07:34,  1.01s/it]

 48%|████▊     | 414/861 [06:56<06:17,  1.18it/s]

 48%|████▊     | 415/861 [06:57<05:19,  1.40it/s]

 48%|████▊     | 416/861 [06:58<06:09,  1.20it/s]

 48%|████▊     | 417/861 [06:59<06:29,  1.14it/s]

 49%|████▊     | 418/861 [07:00<08:00,  1.08s/it]

 49%|████▊     | 419/861 [07:02<08:41,  1.18s/it]

 49%|████▉     | 420/861 [07:02<07:44,  1.05s/it]

 49%|████▉     | 421/861 [07:03<06:27,  1.14it/s]

 49%|████▉     | 422/861 [07:04<06:15,  1.17it/s]

 49%|████▉     | 423/861 [07:05<07:23,  1.01s/it]

 49%|████▉     | 424/861 [07:06<06:22,  1.14it/s]

 49%|████▉     | 425/861 [07:07<07:17,  1.00s/it]

 49%|████▉     | 426/861 [07:08<07:25,  1.02s/it]

 50%|████▉     | 427/861 [07:09<07:14,  1.00s/it]

 50%|████▉     | 428/861 [07:10<08:24,  1.16s/it]

 50%|████▉     | 429/861 [07:13<10:35,  1.47s/it]

 50%|████▉     | 430/861 [07:14<10:06,  1.41s/it]

 50%|█████     | 431/861 [07:16<11:13,  1.57s/it]

 50%|█████     | 432/861 [07:17<10:35,  1.48s/it]

 50%|█████     | 433/861 [07:19<10:26,  1.46s/it]

 50%|█████     | 434/861 [07:19<08:38,  1.21s/it]

 51%|█████     | 435/861 [07:19<06:30,  1.09it/s]

 51%|█████     | 436/861 [07:20<05:37,  1.26it/s]

 51%|█████     | 437/861 [07:21<05:15,  1.34it/s]

 51%|█████     | 438/861 [07:21<05:11,  1.36it/s]

 51%|█████     | 439/861 [07:22<04:40,  1.50it/s]

 51%|█████     | 440/861 [07:22<03:58,  1.76it/s]

 51%|█████     | 441/861 [07:23<03:44,  1.87it/s]

 51%|█████▏    | 442/861 [07:23<03:54,  1.79it/s]

 51%|█████▏    | 443/861 [07:24<04:06,  1.69it/s]

 52%|█████▏    | 444/861 [07:25<04:35,  1.51it/s]

 52%|█████▏    | 445/861 [07:25<04:20,  1.60it/s]

 52%|█████▏    | 446/861 [07:26<05:06,  1.36it/s]

 52%|█████▏    | 447/861 [07:28<08:15,  1.20s/it]

 52%|█████▏    | 448/861 [07:30<08:07,  1.18s/it]

 52%|█████▏    | 449/861 [07:31<07:52,  1.15s/it]

 52%|█████▏    | 450/861 [07:32<07:33,  1.10s/it]

 52%|█████▏    | 451/861 [07:32<06:23,  1.07it/s]

 52%|█████▏    | 452/861 [07:33<05:40,  1.20it/s]

 53%|█████▎    | 453/861 [07:33<04:27,  1.53it/s]

 53%|█████▎    | 454/861 [07:34<05:57,  1.14it/s]

 53%|█████▎    | 455/861 [07:35<05:58,  1.13it/s]

 53%|█████▎    | 456/861 [07:36<05:51,  1.15it/s]

 53%|█████▎    | 457/861 [07:38<07:47,  1.16s/it]

 53%|█████▎    | 458/861 [07:39<07:28,  1.11s/it]

 53%|█████▎    | 459/861 [07:39<06:02,  1.11it/s]

 53%|█████▎    | 460/861 [07:40<05:39,  1.18it/s]

 54%|█████▎    | 461/861 [07:41<06:04,  1.10it/s]

 54%|█████▎    | 462/861 [07:42<05:17,  1.25it/s]

 54%|█████▍    | 463/861 [07:43<05:15,  1.26it/s]

 54%|█████▍    | 464/861 [07:43<04:31,  1.46it/s]

 54%|█████▍    | 465/861 [07:43<03:57,  1.67it/s]

 54%|█████▍    | 466/861 [07:44<03:44,  1.76it/s]

 54%|█████▍    | 467/861 [07:45<05:17,  1.24it/s]

 54%|█████▍    | 468/861 [07:46<04:41,  1.40it/s]

 54%|█████▍    | 469/861 [07:47<05:47,  1.13it/s]

 55%|█████▍    | 470/861 [07:48<05:39,  1.15it/s]

 55%|█████▍    | 471/861 [07:49<05:37,  1.16it/s]

 55%|█████▍    | 472/861 [07:49<04:57,  1.31it/s]

 55%|█████▍    | 473/861 [07:50<05:40,  1.14it/s]

 55%|█████▌    | 474/861 [07:51<04:51,  1.33it/s]

 55%|█████▌    | 475/861 [07:52<04:50,  1.33it/s]

 55%|█████▌    | 476/861 [07:52<04:24,  1.46it/s]

 55%|█████▌    | 477/861 [07:53<04:51,  1.32it/s]

 56%|█████▌    | 478/861 [07:54<04:59,  1.28it/s]

 56%|█████▌    | 479/861 [07:54<04:07,  1.55it/s]

 56%|█████▌    | 480/861 [07:55<04:42,  1.35it/s]

 56%|█████▌    | 481/861 [07:56<04:41,  1.35it/s]

 56%|█████▌    | 482/861 [07:56<03:52,  1.63it/s]

 56%|█████▌    | 483/861 [07:57<03:18,  1.90it/s]

 56%|█████▌    | 484/861 [07:58<04:07,  1.52it/s]

 56%|█████▋    | 485/861 [07:58<03:31,  1.78it/s]

 56%|█████▋    | 486/861 [07:58<03:19,  1.88it/s]

 57%|█████▋    | 487/861 [07:59<03:36,  1.73it/s]

 57%|█████▋    | 488/861 [07:59<03:06,  2.00it/s]

 57%|█████▋    | 489/861 [08:00<02:59,  2.08it/s]

 57%|█████▋    | 490/861 [08:00<02:35,  2.38it/s]

 57%|█████▋    | 491/861 [08:00<02:27,  2.50it/s]

 57%|█████▋    | 492/861 [08:01<02:29,  2.47it/s]

 57%|█████▋    | 493/861 [08:01<02:44,  2.24it/s]

 57%|█████▋    | 494/861 [08:02<02:37,  2.33it/s]

 57%|█████▋    | 495/861 [08:04<05:21,  1.14it/s]

 58%|█████▊    | 496/861 [08:04<05:14,  1.16it/s]

 58%|█████▊    | 497/861 [08:05<04:14,  1.43it/s]

 58%|█████▊    | 498/861 [08:05<03:42,  1.63it/s]

 58%|█████▊    | 499/861 [08:06<03:11,  1.89it/s]

 58%|█████▊    | 500/861 [08:06<03:25,  1.76it/s]

 58%|█████▊    | 501/861 [08:07<02:53,  2.07it/s]

 58%|█████▊    | 502/861 [08:07<03:18,  1.81it/s]

 58%|█████▊    | 503/861 [08:08<03:13,  1.85it/s]

 59%|█████▊    | 504/861 [08:08<03:09,  1.88it/s]

 59%|█████▊    | 505/861 [08:09<02:45,  2.15it/s]

 59%|█████▉    | 506/861 [08:09<02:27,  2.41it/s]

 59%|█████▉    | 507/861 [08:09<02:18,  2.55it/s]

 59%|█████▉    | 508/861 [08:10<03:25,  1.72it/s]

 59%|█████▉    | 509/861 [08:11<04:24,  1.33it/s]

 59%|█████▉    | 510/861 [08:12<04:06,  1.42it/s]

 59%|█████▉    | 511/861 [08:13<04:19,  1.35it/s]

 59%|█████▉    | 512/861 [08:14<04:38,  1.26it/s]

 60%|█████▉    | 513/861 [08:14<04:17,  1.35it/s]

 60%|█████▉    | 514/861 [08:15<03:56,  1.47it/s]

 60%|█████▉    | 515/861 [08:15<03:02,  1.89it/s]

 60%|█████▉    | 516/861 [08:15<02:30,  2.29it/s]

 60%|██████    | 517/861 [08:16<02:10,  2.63it/s]

 60%|██████    | 518/861 [08:16<02:22,  2.40it/s]

 60%|██████    | 519/861 [08:17<03:00,  1.90it/s]

 60%|██████    | 520/861 [08:18<04:21,  1.31it/s]

 61%|██████    | 521/861 [08:18<03:32,  1.60it/s]

 61%|██████    | 522/861 [08:20<04:57,  1.14it/s]

 61%|██████    | 523/861 [08:21<04:55,  1.14it/s]

 61%|██████    | 524/861 [08:22<05:29,  1.02it/s]

 61%|██████    | 525/861 [08:22<04:34,  1.22it/s]

 61%|██████    | 526/861 [08:23<04:18,  1.30it/s]

 61%|██████    | 527/861 [08:24<04:00,  1.39it/s]

 61%|██████▏   | 528/861 [08:25<04:28,  1.24it/s]

 61%|██████▏   | 529/861 [08:25<04:15,  1.30it/s]

 62%|██████▏   | 530/861 [08:26<04:05,  1.35it/s]

 62%|██████▏   | 531/861 [08:26<03:33,  1.55it/s]

 62%|██████▏   | 532/861 [08:27<03:30,  1.57it/s]

 62%|██████▏   | 533/861 [08:27<03:02,  1.80it/s]

 62%|██████▏   | 534/861 [08:29<03:54,  1.40it/s]

 62%|██████▏   | 535/861 [08:29<03:36,  1.50it/s]

 62%|██████▏   | 536/861 [08:30<03:33,  1.52it/s]

 62%|██████▏   | 537/861 [08:31<04:52,  1.11it/s]

 62%|██████▏   | 538/861 [08:32<03:55,  1.37it/s]

 63%|██████▎   | 539/861 [08:33<05:45,  1.07s/it]

 63%|██████▎   | 540/861 [08:35<06:18,  1.18s/it]

 63%|██████▎   | 541/861 [08:35<05:04,  1.05it/s]

 63%|██████▎   | 542/861 [08:35<03:56,  1.35it/s]

 63%|██████▎   | 543/861 [08:36<03:56,  1.34it/s]

 63%|██████▎   | 544/861 [08:37<03:46,  1.40it/s]

 63%|██████▎   | 545/861 [08:38<04:45,  1.10it/s]

 63%|██████▎   | 546/861 [08:39<05:01,  1.05it/s]

 64%|██████▎   | 547/861 [08:41<06:17,  1.20s/it]

 64%|██████▎   | 548/861 [08:42<06:12,  1.19s/it]

 64%|██████▍   | 549/861 [08:44<06:27,  1.24s/it]

 64%|██████▍   | 550/861 [08:44<05:39,  1.09s/it]

 64%|██████▍   | 551/861 [08:45<05:15,  1.02s/it]

 64%|██████▍   | 552/861 [08:46<04:48,  1.07it/s]

 64%|██████▍   | 553/861 [08:47<05:23,  1.05s/it]

 64%|██████▍   | 554/861 [08:49<06:42,  1.31s/it]

 64%|██████▍   | 555/861 [08:50<06:30,  1.28s/it]

 65%|██████▍   | 556/861 [08:52<06:29,  1.28s/it]

 65%|██████▍   | 557/861 [08:53<06:11,  1.22s/it]

 65%|██████▍   | 558/861 [08:54<05:33,  1.10s/it]

 65%|██████▍   | 559/861 [08:55<05:41,  1.13s/it]

 65%|██████▌   | 560/861 [08:56<05:07,  1.02s/it]

 65%|██████▌   | 561/861 [08:56<04:57,  1.01it/s]

 65%|██████▌   | 562/861 [09:00<09:11,  1.84s/it]

 65%|██████▌   | 563/861 [09:02<09:28,  1.91s/it]

 66%|██████▌   | 564/861 [09:03<08:03,  1.63s/it]

 66%|██████▌   | 565/861 [09:04<06:48,  1.38s/it]

 66%|██████▌   | 566/861 [09:05<06:31,  1.33s/it]

 66%|██████▌   | 567/861 [09:07<06:30,  1.33s/it]

 66%|██████▌   | 568/861 [09:08<06:05,  1.25s/it]

 66%|██████▌   | 569/861 [09:10<07:33,  1.55s/it]

 66%|██████▌   | 570/861 [09:11<06:34,  1.36s/it]

 66%|██████▋   | 571/861 [09:12<06:27,  1.34s/it]

 66%|██████▋   | 572/861 [09:13<06:00,  1.25s/it]

 67%|██████▋   | 573/861 [09:14<05:03,  1.05s/it]

 67%|██████▋   | 574/861 [09:15<05:30,  1.15s/it]

 67%|██████▋   | 575/861 [09:16<05:12,  1.09s/it]

 67%|██████▋   | 576/861 [09:18<05:58,  1.26s/it]

 67%|██████▋   | 577/861 [09:20<07:00,  1.48s/it]

 67%|██████▋   | 578/861 [09:21<06:32,  1.39s/it]

 67%|██████▋   | 579/861 [09:23<06:47,  1.44s/it]

 67%|██████▋   | 580/861 [09:24<06:11,  1.32s/it]

 67%|██████▋   | 581/861 [09:25<05:47,  1.24s/it]

 68%|██████▊   | 582/861 [09:27<07:58,  1.72s/it]

 68%|██████▊   | 583/861 [09:29<07:07,  1.54s/it]

 68%|██████▊   | 584/861 [09:30<06:32,  1.42s/it]

 68%|██████▊   | 585/861 [09:31<05:59,  1.30s/it]

 68%|██████▊   | 586/861 [09:32<05:42,  1.25s/it]

 68%|██████▊   | 587/861 [09:33<05:32,  1.21s/it]

 68%|██████▊   | 588/861 [09:34<05:19,  1.17s/it]

 68%|██████▊   | 589/861 [09:35<04:53,  1.08s/it]

 69%|██████▊   | 590/861 [09:37<05:33,  1.23s/it]

 69%|██████▊   | 591/861 [09:37<04:44,  1.05s/it]

 69%|██████▉   | 592/861 [09:39<05:50,  1.30s/it]

 69%|██████▉   | 593/861 [09:41<06:05,  1.36s/it]

 69%|██████▉   | 594/861 [09:42<06:05,  1.37s/it]

 69%|██████▉   | 595/861 [09:44<06:31,  1.47s/it]

 69%|██████▉   | 596/861 [09:44<05:35,  1.27s/it]

 69%|██████▉   | 597/861 [09:46<05:49,  1.32s/it]

 69%|██████▉   | 598/861 [09:47<05:11,  1.19s/it]

 70%|██████▉   | 599/861 [09:48<05:18,  1.22s/it]

 70%|██████▉   | 600/861 [09:49<04:43,  1.09s/it]

 70%|██████▉   | 601/861 [09:50<04:28,  1.03s/it]

 70%|██████▉   | 602/861 [09:51<05:14,  1.21s/it]

 70%|███████   | 603/861 [09:53<05:07,  1.19s/it]

 70%|███████   | 604/861 [09:55<06:10,  1.44s/it]

 70%|███████   | 605/861 [09:55<05:03,  1.19s/it]

 70%|███████   | 606/861 [09:56<04:45,  1.12s/it]

 70%|███████   | 607/861 [09:57<04:13,  1.00it/s]

 71%|███████   | 608/861 [09:58<04:13,  1.00s/it]

 71%|███████   | 609/861 [09:59<04:10,  1.01it/s]

 71%|███████   | 610/861 [10:00<04:54,  1.17s/it]

 71%|███████   | 611/861 [10:01<04:48,  1.16s/it]

 71%|███████   | 612/861 [10:03<04:50,  1.17s/it]

 71%|███████   | 613/861 [10:03<03:49,  1.08it/s]

 71%|███████▏  | 614/861 [10:04<04:04,  1.01it/s]

 71%|███████▏  | 615/861 [10:05<03:49,  1.07it/s]

 72%|███████▏  | 616/861 [10:07<04:45,  1.17s/it]

 72%|███████▏  | 617/861 [10:08<05:03,  1.24s/it]

 72%|███████▏  | 618/861 [10:09<04:56,  1.22s/it]

 72%|███████▏  | 619/861 [10:10<04:42,  1.17s/it]

 72%|███████▏  | 620/861 [10:12<05:08,  1.28s/it]

 72%|███████▏  | 621/861 [10:13<05:16,  1.32s/it]

 72%|███████▏  | 622/861 [10:14<04:15,  1.07s/it]

 72%|███████▏  | 623/861 [10:14<03:32,  1.12it/s]

 72%|███████▏  | 624/861 [10:15<03:23,  1.17it/s]

 73%|███████▎  | 625/861 [10:16<03:06,  1.27it/s]

 73%|███████▎  | 626/861 [10:16<03:00,  1.31it/s]

 73%|███████▎  | 627/861 [10:17<02:49,  1.38it/s]

 73%|███████▎  | 628/861 [10:18<03:26,  1.13it/s]

 73%|███████▎  | 629/861 [10:20<04:04,  1.05s/it]

 73%|███████▎  | 630/861 [10:20<03:31,  1.09it/s]

 73%|███████▎  | 631/861 [10:21<02:51,  1.34it/s]

 73%|███████▎  | 632/861 [10:22<03:21,  1.14it/s]

 74%|███████▎  | 633/861 [10:23<03:15,  1.17it/s]

 74%|███████▎  | 634/861 [10:24<03:56,  1.04s/it]

 74%|███████▍  | 635/861 [10:26<04:26,  1.18s/it]

 74%|███████▍  | 636/861 [10:26<03:58,  1.06s/it]

 74%|███████▍  | 637/861 [10:27<03:47,  1.02s/it]

 74%|███████▍  | 638/861 [10:28<03:48,  1.03s/it]

 74%|███████▍  | 639/861 [10:30<04:12,  1.14s/it]

 74%|███████▍  | 640/861 [10:30<03:40,  1.00it/s]

 74%|███████▍  | 641/861 [10:32<03:49,  1.04s/it]

 75%|███████▍  | 642/861 [10:33<04:18,  1.18s/it]

 75%|███████▍  | 643/861 [10:34<03:45,  1.04s/it]

 75%|███████▍  | 644/861 [10:35<03:53,  1.07s/it]

 75%|███████▍  | 645/861 [10:35<03:13,  1.11it/s]

 75%|███████▌  | 646/861 [10:36<03:11,  1.12it/s]

 75%|███████▌  | 647/861 [10:37<03:00,  1.19it/s]

 75%|███████▌  | 648/861 [10:38<03:13,  1.10it/s]

 75%|███████▌  | 649/861 [10:39<03:05,  1.14it/s]

 75%|███████▌  | 650/861 [10:39<02:45,  1.27it/s]

 76%|███████▌  | 651/861 [10:40<02:52,  1.22it/s]

 76%|███████▌  | 652/861 [10:41<02:53,  1.20it/s]

 76%|███████▌  | 653/861 [10:42<03:09,  1.10it/s]

 76%|███████▌  | 654/861 [10:43<02:47,  1.24it/s]

 76%|███████▌  | 655/861 [10:43<02:17,  1.50it/s]

 76%|███████▌  | 656/861 [10:44<01:58,  1.72it/s]

 76%|███████▋  | 657/861 [10:44<02:06,  1.61it/s]

 76%|███████▋  | 658/861 [10:45<02:25,  1.39it/s]

 77%|███████▋  | 659/861 [10:46<02:37,  1.28it/s]

 77%|███████▋  | 660/861 [10:47<03:04,  1.09it/s]

 77%|███████▋  | 661/861 [10:48<02:39,  1.26it/s]

 77%|███████▋  | 662/861 [10:49<02:42,  1.23it/s]

 77%|███████▋  | 663/861 [10:50<02:41,  1.23it/s]

 77%|███████▋  | 664/861 [10:50<02:26,  1.34it/s]

 77%|███████▋  | 665/861 [10:51<02:10,  1.50it/s]

 77%|███████▋  | 666/861 [10:51<02:04,  1.57it/s]

 77%|███████▋  | 667/861 [10:52<02:23,  1.35it/s]

 78%|███████▊  | 668/861 [10:53<02:07,  1.51it/s]

 78%|███████▊  | 669/861 [10:53<02:06,  1.52it/s]

 78%|███████▊  | 670/861 [10:54<02:02,  1.56it/s]

 78%|███████▊  | 671/861 [10:54<01:43,  1.84it/s]

 78%|███████▊  | 672/861 [10:55<02:03,  1.52it/s]

 78%|███████▊  | 673/861 [10:56<02:04,  1.51it/s]

 78%|███████▊  | 674/861 [10:57<02:28,  1.26it/s]

 78%|███████▊  | 675/861 [10:59<03:41,  1.19s/it]

 79%|███████▊  | 676/861 [11:00<03:30,  1.14s/it]

 79%|███████▊  | 677/861 [11:01<03:40,  1.20s/it]

 79%|███████▊  | 678/861 [11:02<03:12,  1.05s/it]

 79%|███████▉  | 679/861 [11:02<02:32,  1.20it/s]

 79%|███████▉  | 680/861 [11:03<02:25,  1.25it/s]

 79%|███████▉  | 681/861 [11:04<02:10,  1.38it/s]

 79%|███████▉  | 682/861 [11:04<02:09,  1.38it/s]

 79%|███████▉  | 683/861 [11:05<01:57,  1.52it/s]

 79%|███████▉  | 684/861 [11:06<02:08,  1.38it/s]

 80%|███████▉  | 685/861 [11:07<02:15,  1.29it/s]

 80%|███████▉  | 686/861 [11:08<02:25,  1.21it/s]

 80%|███████▉  | 687/861 [11:09<02:49,  1.03it/s]

 80%|███████▉  | 688/861 [11:09<02:17,  1.26it/s]

 80%|████████  | 689/861 [11:10<02:28,  1.16it/s]

 80%|████████  | 690/861 [11:12<02:57,  1.04s/it]

 80%|████████  | 691/861 [11:13<02:42,  1.05it/s]

 80%|████████  | 692/861 [11:13<02:26,  1.15it/s]

 80%|████████  | 693/861 [11:15<02:43,  1.03it/s]

 81%|████████  | 694/861 [11:15<02:28,  1.13it/s]

 81%|████████  | 695/861 [11:16<02:17,  1.21it/s]

 81%|████████  | 696/861 [11:16<01:49,  1.51it/s]

 81%|████████  | 697/861 [11:17<01:46,  1.54it/s]

 81%|████████  | 698/861 [11:18<01:56,  1.40it/s]

 81%|████████  | 699/861 [11:18<01:54,  1.41it/s]

 81%|████████▏ | 700/861 [11:19<01:58,  1.36it/s]

 81%|████████▏ | 701/861 [11:20<02:20,  1.14it/s]

 82%|████████▏ | 702/861 [11:21<02:18,  1.15it/s]

 82%|████████▏ | 703/861 [11:22<01:55,  1.37it/s]

 82%|████████▏ | 704/861 [11:22<01:46,  1.48it/s]

 82%|████████▏ | 705/861 [11:24<02:19,  1.12it/s]

 82%|████████▏ | 706/861 [11:24<02:07,  1.21it/s]

 82%|████████▏ | 707/861 [11:25<01:47,  1.43it/s]

 82%|████████▏ | 708/861 [11:26<01:56,  1.31it/s]

 82%|████████▏ | 709/861 [11:27<02:06,  1.20it/s]

 82%|████████▏ | 710/861 [11:28<02:35,  1.03s/it]

 83%|████████▎ | 711/861 [11:29<02:53,  1.16s/it]

 83%|████████▎ | 712/861 [11:30<02:20,  1.06it/s]

 83%|████████▎ | 713/861 [11:30<01:56,  1.27it/s]

 83%|████████▎ | 714/861 [11:31<01:56,  1.26it/s]

 83%|████████▎ | 715/861 [11:32<02:00,  1.21it/s]

 83%|████████▎ | 716/861 [11:33<02:04,  1.16it/s]

 83%|████████▎ | 717/861 [11:34<02:14,  1.07it/s]

 83%|████████▎ | 718/861 [11:35<02:27,  1.03s/it]

 84%|████████▎ | 719/861 [11:36<02:23,  1.01s/it]

 84%|████████▎ | 720/861 [11:37<02:14,  1.05it/s]

 84%|████████▎ | 721/861 [11:38<01:56,  1.20it/s]

 84%|████████▍ | 722/861 [11:38<01:48,  1.29it/s]

 84%|████████▍ | 723/861 [11:39<01:57,  1.17it/s]

 84%|████████▍ | 724/861 [11:40<01:47,  1.27it/s]

 84%|████████▍ | 725/861 [11:41<01:39,  1.37it/s]

 84%|████████▍ | 726/861 [11:41<01:40,  1.34it/s]

 84%|████████▍ | 727/861 [11:43<02:27,  1.10s/it]

 85%|████████▍ | 728/861 [11:44<02:17,  1.04s/it]

 85%|████████▍ | 729/861 [11:45<02:21,  1.07s/it]

 85%|████████▍ | 730/861 [11:46<01:53,  1.16it/s]

 85%|████████▍ | 731/861 [11:46<01:44,  1.24it/s]

 85%|████████▌ | 732/861 [11:48<01:56,  1.11it/s]

 85%|████████▌ | 733/861 [11:49<02:02,  1.04it/s]

 85%|████████▌ | 734/861 [11:49<01:35,  1.33it/s]

 85%|████████▌ | 735/861 [11:49<01:25,  1.48it/s]

 85%|████████▌ | 736/861 [11:50<01:23,  1.50it/s]

 86%|████████▌ | 737/861 [11:51<01:27,  1.42it/s]

 86%|████████▌ | 738/861 [11:52<01:31,  1.34it/s]

 86%|████████▌ | 739/861 [11:53<01:39,  1.23it/s]

 86%|████████▌ | 740/861 [11:53<01:28,  1.37it/s]

 86%|████████▌ | 741/861 [11:54<01:18,  1.52it/s]

 86%|████████▌ | 742/861 [11:55<01:34,  1.26it/s]

 86%|████████▋ | 743/861 [11:55<01:28,  1.34it/s]

 86%|████████▋ | 744/861 [11:56<01:35,  1.22it/s]

 87%|████████▋ | 745/861 [11:58<01:53,  1.02it/s]

 87%|████████▋ | 746/861 [11:59<01:55,  1.00s/it]

 87%|████████▋ | 747/861 [12:00<01:57,  1.03s/it]

 87%|████████▋ | 748/861 [12:01<01:59,  1.06s/it]

 87%|████████▋ | 749/861 [12:03<02:17,  1.23s/it]

 87%|████████▋ | 750/861 [12:03<02:03,  1.11s/it]

 87%|████████▋ | 751/861 [12:04<01:33,  1.18it/s]

 87%|████████▋ | 752/861 [12:05<01:46,  1.02it/s]

 87%|████████▋ | 753/861 [12:06<01:35,  1.13it/s]

 88%|████████▊ | 754/861 [12:06<01:32,  1.16it/s]

 88%|████████▊ | 755/861 [12:07<01:29,  1.18it/s]

 88%|████████▊ | 756/861 [12:08<01:15,  1.38it/s]

 88%|████████▊ | 757/861 [12:08<01:16,  1.37it/s]

 88%|████████▊ | 758/861 [12:10<01:28,  1.16it/s]

 88%|████████▊ | 759/861 [12:10<01:19,  1.28it/s]

 88%|████████▊ | 760/861 [12:12<02:02,  1.21s/it]

 88%|████████▊ | 761/861 [12:14<02:18,  1.38s/it]

 89%|████████▊ | 762/861 [12:15<01:52,  1.13s/it]

 89%|████████▊ | 763/861 [12:15<01:35,  1.03it/s]

 89%|████████▊ | 764/861 [12:16<01:30,  1.07it/s]

 89%|████████▉ | 765/861 [12:17<01:23,  1.15it/s]

 89%|████████▉ | 766/861 [12:18<01:30,  1.05it/s]

 89%|████████▉ | 767/861 [12:23<03:20,  2.14s/it]

 89%|████████▉ | 768/861 [12:24<02:39,  1.72s/it]

 89%|████████▉ | 769/861 [12:25<02:22,  1.55s/it]

 89%|████████▉ | 770/861 [12:26<01:55,  1.27s/it]

 90%|████████▉ | 771/861 [12:26<01:30,  1.01s/it]

 90%|████████▉ | 772/861 [12:27<01:33,  1.05s/it]

 90%|████████▉ | 773/861 [12:29<02:06,  1.44s/it]

 90%|████████▉ | 774/861 [12:31<02:12,  1.52s/it]

 90%|█████████ | 775/861 [12:33<02:21,  1.65s/it]

 90%|█████████ | 776/861 [12:35<02:32,  1.79s/it]

 90%|█████████ | 777/861 [12:36<02:09,  1.54s/it]

 90%|█████████ | 778/861 [12:37<01:54,  1.38s/it]

 90%|█████████ | 779/861 [12:39<02:04,  1.52s/it]

 91%|█████████ | 780/861 [12:41<02:11,  1.63s/it]

 91%|█████████ | 781/861 [12:43<02:13,  1.67s/it]

 91%|█████████ | 782/861 [12:43<01:52,  1.42s/it]

 91%|█████████ | 783/861 [12:45<01:59,  1.53s/it]

 91%|█████████ | 784/861 [12:48<02:35,  2.01s/it]

 91%|█████████ | 785/861 [12:50<02:19,  1.83s/it]

 91%|█████████▏| 786/861 [12:51<01:54,  1.52s/it]

 91%|█████████▏| 787/861 [12:51<01:36,  1.30s/it]

 92%|█████████▏| 788/861 [12:52<01:28,  1.21s/it]

 92%|█████████▏| 789/861 [12:53<01:24,  1.18s/it]

 92%|█████████▏| 790/861 [12:54<01:19,  1.12s/it]

 92%|█████████▏| 791/861 [12:56<01:26,  1.23s/it]

 92%|█████████▏| 792/861 [12:57<01:24,  1.22s/it]

 92%|█████████▏| 793/861 [12:59<01:42,  1.51s/it]

 92%|█████████▏| 794/861 [13:00<01:29,  1.33s/it]

 92%|█████████▏| 795/861 [13:02<01:36,  1.47s/it]

 92%|█████████▏| 796/861 [13:02<01:13,  1.12s/it]

 93%|█████████▎| 797/861 [13:03<01:07,  1.05s/it]

 93%|█████████▎| 798/861 [13:06<01:38,  1.56s/it]

 93%|█████████▎| 799/861 [13:08<01:45,  1.70s/it]

 93%|█████████▎| 800/861 [13:09<01:29,  1.47s/it]

 93%|█████████▎| 801/861 [13:11<01:31,  1.52s/it]

 93%|█████████▎| 802/861 [13:11<01:13,  1.25s/it]

 93%|█████████▎| 803/861 [13:12<01:08,  1.18s/it]

 93%|█████████▎| 804/861 [13:14<01:15,  1.32s/it]

 93%|█████████▎| 805/861 [13:15<01:12,  1.29s/it]

 94%|█████████▎| 806/861 [13:16<01:00,  1.09s/it]

 94%|█████████▎| 807/861 [13:17<01:03,  1.17s/it]

 94%|█████████▍| 808/861 [13:19<01:13,  1.38s/it]

 94%|█████████▍| 809/861 [13:19<00:55,  1.08s/it]

 94%|█████████▍| 810/861 [13:20<00:48,  1.05it/s]

 94%|█████████▍| 811/861 [13:21<00:53,  1.07s/it]

 94%|█████████▍| 812/861 [13:23<00:54,  1.12s/it]

 94%|█████████▍| 813/861 [13:23<00:49,  1.04s/it]

 95%|█████████▍| 814/861 [13:25<00:57,  1.23s/it]

 95%|█████████▍| 815/861 [13:27<01:11,  1.56s/it]

 95%|█████████▍| 816/861 [13:28<00:57,  1.28s/it]

 95%|█████████▍| 817/861 [13:29<00:50,  1.15s/it]

 95%|█████████▌| 818/861 [13:31<00:55,  1.30s/it]

 95%|█████████▌| 819/861 [13:32<00:53,  1.28s/it]

 95%|█████████▌| 820/861 [13:33<00:47,  1.15s/it]

 95%|█████████▌| 821/861 [13:34<00:43,  1.10s/it]

 95%|█████████▌| 822/861 [13:35<00:45,  1.17s/it]

 96%|█████████▌| 823/861 [13:36<00:41,  1.08s/it]

 96%|█████████▌| 824/861 [13:37<00:39,  1.06s/it]

 96%|█████████▌| 825/861 [13:37<00:32,  1.12it/s]

 96%|█████████▌| 826/861 [13:39<00:40,  1.15s/it]

 96%|█████████▌| 827/861 [13:40<00:36,  1.07s/it]

 96%|█████████▌| 828/861 [13:40<00:30,  1.09it/s]

 96%|█████████▋| 829/861 [13:42<00:31,  1.02it/s]

 96%|█████████▋| 830/861 [13:43<00:32,  1.06s/it]

 97%|█████████▋| 831/861 [13:44<00:33,  1.12s/it]

 97%|█████████▋| 832/861 [13:45<00:30,  1.07s/it]

 97%|█████████▋| 833/861 [13:46<00:30,  1.10s/it]

 97%|█████████▋| 834/861 [13:47<00:28,  1.06s/it]

 97%|█████████▋| 835/861 [13:48<00:24,  1.04it/s]

 97%|█████████▋| 836/861 [13:50<00:34,  1.38s/it]

 97%|█████████▋| 837/861 [13:52<00:32,  1.37s/it]

 97%|█████████▋| 838/861 [13:54<00:35,  1.54s/it]

 97%|█████████▋| 839/861 [13:54<00:27,  1.27s/it]

 98%|█████████▊| 840/861 [13:55<00:22,  1.06s/it]

 98%|█████████▊| 841/861 [13:56<00:22,  1.11s/it]

 98%|█████████▊| 842/861 [13:57<00:20,  1.07s/it]

 98%|█████████▊| 843/861 [13:59<00:22,  1.23s/it]

 98%|█████████▊| 844/861 [14:00<00:22,  1.33s/it]

 98%|█████████▊| 845/861 [14:02<00:26,  1.63s/it]

 98%|█████████▊| 846/861 [14:04<00:23,  1.57s/it]

 98%|█████████▊| 847/861 [14:05<00:20,  1.48s/it]

 98%|█████████▊| 848/861 [14:06<00:17,  1.38s/it]

 99%|█████████▊| 849/861 [14:07<00:15,  1.29s/it]

 99%|█████████▊| 850/861 [14:08<00:12,  1.12s/it]

 99%|█████████▉| 851/861 [14:09<00:10,  1.10s/it]

 99%|█████████▉| 852/861 [14:10<00:08,  1.05it/s]

 99%|█████████▉| 853/861 [14:13<00:12,  1.53s/it]

 99%|█████████▉| 854/861 [14:14<00:10,  1.50s/it]

 99%|█████████▉| 855/861 [14:15<00:07,  1.29s/it]

 99%|█████████▉| 856/861 [14:16<00:06,  1.28s/it]

100%|█████████▉| 857/861 [14:17<00:04,  1.17s/it]

100%|█████████▉| 858/861 [14:18<00:03,  1.06s/it]

100%|█████████▉| 859/861 [14:19<00:01,  1.02it/s]

100%|█████████▉| 860/861 [14:20<00:00,  1.02it/s]

100%|██████████| 861/861 [14:21<00:00,  1.04it/s]{'score': 5.220083135583361, 'counts': [15847, 6350, 2984, 1408], 'totals': [89471, 87749, 86027, 84305], 'precisions': [17.711884297705403, 7.236549704270134, 3.4686784381647624, 1.6701263270268667], 'bp': 1.0, 'sys_len': 89471, 'ref_len': 32555}

                                                          

                                                 
{'eval_loss': 2.561117172241211, 'eval_bleu': 5.2201, 'eval_gen_len': 46.1405, 'eval_runtime': 958.6568, 'eval_samples_per_second': 1.796, 'eval_steps_per_second': 0.898, 'epoch': 7.0}

 44%|████▍     | 27084/61904 [3:37:30<13:17:20,  1.37s/it]

100%|██████████| 861/861 [15:57<00:00,  1.04it/s]

                                                 [WARNING|configuration_utils.py:448] 2024-10-28 06:42:13,060 >> 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()

 44%|████▍     | 27085/61904 [3:37:53<2857:28:59, 295.44s/it]
 44%|████▍     | 27086/61904 [3:37:55<2004:28:46, 207.25s/it]
 44%|████▍     | 27087/61904 [3:37:56<1407:50:39, 145.57s/it]
 44%|████▍     | 27088/61904 [3:37:58<989:26:33, 102.31s/it] 
 44%|████▍     | 27089/61904 [3:37:59<696:22:38, 72.01s/it] 
 44%|████▍     | 27090/61904 [3:38:00<491:43:59, 50.85s/it]
 44%|████▍     | 27091/61904 [3:38:02<348:18:32, 36.02s/it]
 44%|████▍     | 27092/61904 [3:38:03<248:10:32, 25.66s/it]
 44%|████▍     | 27093/61904 [3:38:05<178:13:52, 18.43s/it]
 44%|████▍     | 27094/61904 [3:38:06<129:21:49, 13.38s/it]
 44%|████▍     | 27095/61904 [3:38:08<94:16:47,  9.75s/it] 
 44%|████▍     | 27096/61904 [3:38:09<69:56:48,  7.23s/it]
 44%|████▍     | 27097/61904 [3:38:10<52:56:02,  5.47s/it]
 44%|████▍     | 27098/61904 [3:38:12<41:11:24,  4.26s/it]
 44%|████▍     | 27099/61904 [3:38:13<32:54:53,  3.40s/it]
 44%|████▍     | 27100/61904 [3:38:15<26:57:11,  2.79s/it]
                                                          
{'loss': 2.5946, 'learning_rate': 1.5640477116556463e-07, 'epoch': 7.0}

 44%|████▍     | 27100/61904 [3:38:15<26:57:11,  2.79s/it]
 44%|████▍     | 27101/61904 [3:38:16<23:16:18,  2.41s/it]
 44%|████▍     | 27102/61904 [3:38:18<20:31:31,  2.12s/it]
 44%|████▍     | 27103/61904 [3:38:19<18:15:45,  1.89s/it]
 44%|████▍     | 27104/61904 [3:38:20<16:56:09,  1.75s/it]
 44%|████▍     | 27105/61904 [3:38:22<15:39:52,  1.62s/it]
 44%|████▍     | 27106/61904 [3:38:23<15:14:02,  1.58s/it]
 44%|████▍     | 27107/61904 [3:38:25<15:10:19,  1.57s/it]
 44%|████▍     | 27108/61904 [3:38:26<14:57:27,  1.55s/it]
 44%|████▍     | 27109/61904 [3:38:28<14:45:04,  1.53s/it]
 44%|████▍     | 27110/61904 [3:38:29<14:49:20,  1.53s/it]
 44%|████▍     | 27111/61904 [3:38:31<14:20:05,  1.48s/it]
 44%|████▍     | 27112/61904 [3:38:32<14:52:46,  1.54s/it]
 44%|████▍     | 27113/61904 [3:38:34<14:52:45,  1.54s/it]
 44%|████▍     | 27114/61904 [3:38:35<14:38:30,  1.52s/it]
 44%|████▍     | 27115/61904 [3:38:37<14:13:24,  1.47s/it]
 44%|████▍     | 27116/61904 [3:38:38<13:48:49,  1.43s/it]
 44%|████▍     | 27117/61904 [3:38:39<14:09:28,  1.47s/it]
 44%|████▍     | 27118/61904 [3:38:41<14:01:29,  1.45s/it]
 44%|████▍     | 27119/61904 [3:38:42<14:17:23,  1.48s/it]
 44%|████▍     | 27120/61904 [3:38:44<14:35:04,  1.51s/it]
                                                          
{'loss': 2.5941, 'learning_rate': 1.563723583560223e-07, 'epoch': 7.01}

 44%|████▍     | 27120/61904 [3:38:44<14:35:04,  1.51s/it]
 44%|████▍     | 27121/61904 [3:38:45<14:09:07,  1.46s/it]
 44%|████▍     | 27122/61904 [3:38:47<13:57:14,  1.44s/it]
 44%|████▍     | 27123/61904 [3:38:48<13:34:48,  1.41s/it]
 44%|████▍     | 27124/61904 [3:38:50<13:38:20,  1.41s/it]
 44%|████▍     | 27125/61904 [3:38:51<13:40:00,  1.41s/it]
 44%|████▍     | 27126/61904 [3:38:52<13:49:56,  1.43s/it]
 44%|████▍     | 27127/61904 [3:38:54<13:45:40,  1.42s/it]