2024-08-06 14:23:41,788 INFO [trainer.py:870] (1/8) Training started
2024-08-06 14:23:41,789 INFO [trainer.py:889] (1/8) Device: cuda:1
2024-08-06 14:23:41,789 INFO [trainer.py:890] (1/8) {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 100, 'reset_interval': 200, 'valid_interval': 2000, 'env_info': {'k2-version': '1.24.3', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '279b0c87015a615b81b147251814d737a548f397', 'k2-git-date': 'Wed May 24 22:24:09 2023', 'lhotse-version': '1.26.0', 'torch-version': '2.0.1+cu118', 'torch-cuda-available': True, 'torch-cuda-version': '11.8', 'python-version': '3.10', 'icefall-git-branch': None, 'icefall-git-sha1': None, 'icefall-git-date': None, 'icefall-path': '/workspace/icefall_llm', 'k2-path': '/usr/local/lib/python3.10/dist-packages/k2/__init__.py', 'lhotse-path': '/usr/local/lib/python3.10/dist-packages/lhotse/__init__.py', 'hostname': '6867463', 'IP address': '0.104.202.7'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 40, 'start_epoch': 100, 'start_batch': 0, 'exp_dir': PosixPath('exp/valle'), 'optimizer_name': 'ScaledAdam', 'scheduler_name': 'Eden', 'base_lr': 0.03, 'warmup_steps': 200, 'seed': 42, 'inf_check': False, 'save_every_n': 100000, 'keep_last_k': 20, 'average_period': 0, 'accumulate_grad_steps': 2, 'dtype': 'float32', 'filter_min_duration': 0.5, 'filter_max_duration': 14.0, 'train_stage': 2, 'visualize': False, 'oom_check': False, 'model_name': 'valle', 'decoder_dim': 1024, 'nhead': 16, 'num_decoder_layers': 12, 'scale_factor': 1.0, 'norm_first': True, 'add_prenet': False, 'prefix_mode': 1, 'share_embedding': True, 'prepend_bos': False, 'num_quantizers': 8, 'scaling_xformers': False, 'manifest_dir': PosixPath('data/tokenized'), 'max_duration': 160, 'bucketing_sampler': True, 'num_buckets': 6, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 0.1, 'on_the_fly_feats': False, 'shuffle': True, 'buffer_size': 40000, 'shuffle_buffer_size': 100000, 'drop_last': False, 'return_cuts': True, 'num_workers': 8, 'enable_spec_aug': False, 'spec_aug_time_warp_factor': 80, 'input_strategy': 'PrecomputedFeatures', 'dataset': 'libritts', 'text_tokens': 'data/tokenized/unique_text_tokens.k2symbols', 'sampling_rate': 24000}
2024-08-06 14:23:41,789 INFO [trainer.py:892] (1/8) About to create model
2024-08-06 14:23:42,552 INFO [trainer.py:899] (1/8) Number of model parameters: 367386628
2024-08-06 14:23:42,552 INFO [checkpoint.py:112] (1/8) Loading checkpoint from exp/valle/epoch-99.pt
2024-08-06 14:23:47,458 INFO [trainer.py:914] (1/8) Using DDP
2024-08-06 14:23:49,641 INFO [datamodule.py:427] (1/8) About to get train cuts
2024-08-06 14:23:49,643 INFO [datamodule.py:434] (1/8) About to get dev cuts
2024-08-06 14:23:49,644 INFO [datamodule.py:292] (1/8) Disable SpecAugment
2024-08-06 14:23:49,644 INFO [datamodule.py:294] (1/8) About to create train dataset
2024-08-06 14:23:49,645 INFO [datamodule.py:323] (1/8) Using DynamicBucketingSampler
2024-08-06 14:23:50,266 INFO [datamodule.py:344] (1/8) About to create train dataloader
2024-08-06 14:23:50,267 INFO [datamodule.py:367] (1/8) About to create dev dataset
2024-08-06 14:23:50,600 INFO [datamodule.py:388] (1/8) About to create dev dataloader
2024-08-06 14:24:38,249 INFO [trainer.py:765] (1/8) Epoch 1, batch 100, train_loss[loss=105.1, NarTop10Accuracy=0.01887, over 7386.00 frames. ], tot_loss[loss=74.58, NarTop10Accuracy=0.04796, over 2371.63 frames. ], batch size: 31, lr: 2.25e-02
2024-08-06 14:25:07,518 INFO [trainer.py:765] (1/8) Epoch 1, batch 200, train_loss[loss=136.9, NarTop10Accuracy=0.01535, over 6936.00 frames. ], tot_loss[loss=98, NarTop10Accuracy=0.04192, over 3863.19 frames. ], batch size: 17, lr: 3.00e-02
2024-08-06 14:25:37,111 INFO [trainer.py:765] (1/8) Epoch 1, batch 300, train_loss[loss=105.6, NarTop10Accuracy=0.02372, over 6975.00 frames. ], tot_loss[loss=85.32, NarTop10Accuracy=0.04288, over 4656.54 frames. ], batch size: 22, lr: 3.00e-02
2024-08-06 14:26:07,482 INFO [trainer.py:765] (1/8) Epoch 1, batch 400, train_loss[loss=53.59, NarTop10Accuracy=0.01745, over 5070.00 frames. ], tot_loss[loss=67.84, NarTop10Accuracy=0.04713, over 5111.55 frames. ], batch size: 7, lr: 3.00e-02
2024-08-06 14:26:35,357 INFO [trainer.py:765] (1/8) Epoch 1, batch 500, train_loss[loss=14.57, NarTop10Accuracy=0.02618, over 6162.00 frames. ], tot_loss[loss=49.03, NarTop10Accuracy=0.05107, over 5383.33 frames. ], batch size: 11, lr: 2.99e-02
2024-08-06 14:27:04,000 INFO [trainer.py:765] (1/8) Epoch 1, batch 600, train_loss[loss=6.264, NarTop10Accuracy=0.1547, over 6210.00 frames. ], tot_loss[loss=33.34, NarTop10Accuracy=0.05558, over 5666.53 frames. ], batch size: 10, lr: 2.99e-02
2024-08-06 14:27:39,490 INFO [trainer.py:765] (1/8) Epoch 1, batch 700, train_loss[loss=6.77, NarTop10Accuracy=0.1121, over 4221.00 frames. ], tot_loss[loss=23.38, NarTop10Accuracy=0.06406, over 5724.39 frames. ], batch size: 5, lr: 2.99e-02
2024-08-06 14:28:08,831 INFO [trainer.py:765] (1/8) Epoch 1, batch 800, train_loss[loss=6.379, NarTop10Accuracy=0.1529, over 5031.00 frames. ], tot_loss[loss=17.18, NarTop10Accuracy=0.08526, over 5761.81 frames. ], batch size: 6, lr: 2.98e-02
2024-08-06 14:28:36,758 INFO [trainer.py:765] (1/8) Epoch 1, batch 900, train_loss[loss=5.81, NarTop10Accuracy=0.1604, over 6342.00 frames. ], tot_loss[loss=12.78, NarTop10Accuracy=0.1119, over 5807.44 frames. ], batch size: 13, lr: 2.98e-02
2024-08-06 14:29:12,586 INFO [trainer.py:765] (1/8) Epoch 1, batch 1000, train_loss[loss=5.72, NarTop10Accuracy=0.1873, over 6681.00 frames. ], tot_loss[loss=10.09, NarTop10Accuracy=0.1341, over 5909.13 frames. ], batch size: 14, lr: 2.97e-02
2024-08-06 14:29:42,825 INFO [trainer.py:765] (1/8) Epoch 1, batch 1100, train_loss[loss=5.576, NarTop10Accuracy=0.2159, over 6795.00 frames. ], tot_loss[loss=8.411, NarTop10Accuracy=0.153, over 5934.85 frames. ], batch size: 17, lr: 2.96e-02
2024-08-06 14:30:11,468 INFO [trainer.py:765] (1/8) Epoch 1, batch 1200, train_loss[loss=5.92, NarTop10Accuracy=0.1551, over 7311.00 frames. ], tot_loss[loss=7.351, NarTop10Accuracy=0.1702, over 5922.73 frames. ], batch size: 32, lr: 2.96e-02
2024-08-06 14:30:48,747 INFO [trainer.py:765] (1/8) Epoch 1, batch 1300, train_loss[loss=5.12, NarTop10Accuracy=0.3, over 4455.00 frames. ], tot_loss[loss=6.673, NarTop10Accuracy=0.1875, over 6005.12 frames. ], batch size: 5, lr: 2.95e-02
2024-08-06 14:31:18,143 INFO [trainer.py:765] (1/8) Epoch 1, batch 1400, train_loss[loss=5.67, NarTop10Accuracy=0.1867, over 6117.00 frames. ], tot_loss[loss=6.248, NarTop10Accuracy=0.1975, over 6028.89 frames. ], batch size: 11, lr: 2.94e-02
2024-08-06 14:31:46,026 INFO [trainer.py:765] (1/8) Epoch 1, batch 1500, train_loss[loss=5.814, NarTop10Accuracy=0.1693, over 6342.00 frames. ], tot_loss[loss=5.973, NarTop10Accuracy=0.2081, over 5971.60 frames. ], batch size: 50, lr: 2.94e-02
2024-08-06 14:32:13,691 INFO [trainer.py:765] (1/8) Epoch 1, batch 1600, train_loss[loss=5.551, NarTop10Accuracy=0.2154, over 7086.00 frames. ], tot_loss[loss=5.791, NarTop10Accuracy=0.2173, over 5944.23 frames. ], batch size: 22, lr: 2.93e-02
2024-08-06 14:32:40,198 INFO [trainer.py:765] (1/8) Epoch 1, batch 1700, train_loss[loss=5.398, NarTop10Accuracy=0.2549, over 6663.00 frames. ], tot_loss[loss=5.672, NarTop10Accuracy=0.2242, over 5909.80 frames. ], batch size: 14, lr: 2.92e-02
2024-08-06 14:33:06,499 INFO [trainer.py:765] (1/8) Epoch 1, batch 1800, train_loss[loss=5.449, NarTop10Accuracy=0.2401, over 7149.00 frames. ], tot_loss[loss=5.579, NarTop10Accuracy=0.2326, over 5980.24 frames. ], batch size: 22, lr: 2.91e-02
2024-08-06 14:33:32,625 INFO [trainer.py:765] (1/8) Epoch 1, batch 1900, train_loss[loss=5.585, NarTop10Accuracy=0.2097, over 6150.00 frames. ], tot_loss[loss=5.514, NarTop10Accuracy=0.2396, over 6024.68 frames. ], batch size: 50, lr: 2.90e-02
2024-08-06 14:33:58,014 INFO [trainer.py:765] (1/8) Epoch 1, batch 2000, train_loss[loss=5.457, NarTop10Accuracy=0.2511, over 5736.00 frames. ], tot_loss[loss=5.446, NarTop10Accuracy=0.2498, over 6003.38 frames. ], batch size: 51, lr: 2.89e-02
2024-08-06 14:33:58,016 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 14:34:06,103 INFO [trainer.py:811] (1/8) Epoch 1, validation: loss=5.397, NarTop10Accuracy=0.2581, over 1905321.00 frames. 
2024-08-06 14:34:06,104 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 26863MB
2024-08-06 14:34:06,612 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 4.749e+01 2.278e+02 7.300e+02 1.664e+04 7.177e+05, threshold=1.460e+03, percent-clipped=0.0
2024-08-06 14:34:32,061 INFO [trainer.py:765] (1/8) Epoch 1, batch 2100, train_loss[loss=4.95, NarTop10Accuracy=0.3428, over 3948.00 frames. ], tot_loss[loss=5.382, NarTop10Accuracy=0.2605, over 5984.71 frames. ], batch size: 4, lr: 2.88e-02
2024-08-06 14:34:57,303 INFO [trainer.py:765] (1/8) Epoch 1, batch 2200, train_loss[loss=5.446, NarTop10Accuracy=0.2452, over 7416.00 frames. ], tot_loss[loss=5.349, NarTop10Accuracy=0.2652, over 6018.35 frames. ], batch size: 31, lr: 2.87e-02
2024-08-06 14:35:22,455 INFO [trainer.py:765] (1/8) Epoch 1, batch 2300, train_loss[loss=5.358, NarTop10Accuracy=0.2628, over 5661.00 frames. ], tot_loss[loss=5.336, NarTop10Accuracy=0.267, over 6004.60 frames. ], batch size: 9, lr: 2.86e-02
2024-08-06 14:35:46,815 INFO [trainer.py:765] (1/8) Epoch 1, batch 2400, train_loss[loss=5.225, NarTop10Accuracy=0.2812, over 5280.00 frames. ], tot_loss[loss=5.284, NarTop10Accuracy=0.2765, over 5772.29 frames. ], batch size: 7, lr: 2.85e-02
2024-08-06 14:36:10,408 INFO [trainer.py:765] (1/8) Epoch 1, batch 2500, train_loss[loss=5.069, NarTop10Accuracy=0.3156, over 5217.00 frames. ], tot_loss[loss=5.223, NarTop10Accuracy=0.2879, over 5476.61 frames. ], batch size: 7, lr: 2.84e-02
2024-08-06 14:36:31,006 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 14:37:29,669 INFO [trainer.py:765] (1/8) Epoch 2, batch 100, train_loss[loss=4.988, NarTop10Accuracy=0.3371, over 7368.00 frames. ], tot_loss[loss=5.188, NarTop10Accuracy=0.2946, over 2359.01 frames. ], batch size: 31, lr: 2.77e-02
2024-08-06 14:38:10,014 INFO [trainer.py:765] (1/8) Epoch 2, batch 200, train_loss[loss=5.279, NarTop10Accuracy=0.277, over 6852.00 frames. ], tot_loss[loss=5.169, NarTop10Accuracy=0.2976, over 3851.85 frames. ], batch size: 17, lr: 2.76e-02
2024-08-06 14:38:38,297 INFO [trainer.py:765] (1/8) Epoch 2, batch 300, train_loss[loss=4.977, NarTop10Accuracy=0.3384, over 7173.00 frames. ], tot_loss[loss=5.142, NarTop10Accuracy=0.3018, over 4637.45 frames. ], batch size: 22, lr: 2.75e-02
2024-08-06 14:39:06,999 INFO [trainer.py:765] (1/8) Epoch 2, batch 400, train_loss[loss=4.804, NarTop10Accuracy=0.378, over 5109.00 frames. ], tot_loss[loss=5.104, NarTop10Accuracy=0.3085, over 5104.14 frames. ], batch size: 7, lr: 2.74e-02
2024-08-06 14:39:46,119 INFO [trainer.py:765] (1/8) Epoch 2, batch 500, train_loss[loss=4.931, NarTop10Accuracy=0.3444, over 6087.00 frames. ], tot_loss[loss=5.068, NarTop10Accuracy=0.3162, over 5369.66 frames. ], batch size: 11, lr: 2.73e-02
2024-08-06 14:40:15,083 INFO [trainer.py:765] (1/8) Epoch 2, batch 600, train_loss[loss=4.953, NarTop10Accuracy=0.3566, over 5598.00 frames. ], tot_loss[loss=5.04, NarTop10Accuracy=0.3216, over 5637.00 frames. ], batch size: 9, lr: 2.71e-02
2024-08-06 14:40:44,589 INFO [trainer.py:765] (1/8) Epoch 2, batch 700, train_loss[loss=5.128, NarTop10Accuracy=0.2983, over 4293.00 frames. ], tot_loss[loss=5.023, NarTop10Accuracy=0.3245, over 5712.10 frames. ], batch size: 5, lr: 2.70e-02
2024-08-06 14:41:24,514 INFO [trainer.py:765] (1/8) Epoch 2, batch 800, train_loss[loss=5.058, NarTop10Accuracy=0.3157, over 5208.00 frames. ], tot_loss[loss=5.004, NarTop10Accuracy=0.3279, over 5769.80 frames. ], batch size: 6, lr: 2.69e-02
2024-08-06 14:41:54,404 INFO [trainer.py:765] (1/8) Epoch 2, batch 900, train_loss[loss=4.71, NarTop10Accuracy=0.3832, over 6624.00 frames. ], tot_loss[loss=4.966, NarTop10Accuracy=0.3353, over 5798.53 frames. ], batch size: 14, lr: 2.68e-02
2024-08-06 14:42:23,902 INFO [trainer.py:765] (1/8) Epoch 2, batch 1000, train_loss[loss=4.85, NarTop10Accuracy=0.3651, over 6837.00 frames. ], tot_loss[loss=4.938, NarTop10Accuracy=0.3408, over 5901.76 frames. ], batch size: 14, lr: 2.66e-02
2024-08-06 14:42:56,254 INFO [trainer.py:765] (1/8) Epoch 2, batch 1100, train_loss[loss=4.879, NarTop10Accuracy=0.3463, over 7116.00 frames. ], tot_loss[loss=4.934, NarTop10Accuracy=0.3416, over 5928.58 frames. ], batch size: 18, lr: 2.65e-02
2024-08-06 14:43:35,186 INFO [trainer.py:765] (1/8) Epoch 2, batch 1200, train_loss[loss=4.832, NarTop10Accuracy=0.3596, over 7599.00 frames. ], tot_loss[loss=4.901, NarTop10Accuracy=0.3476, over 5935.33 frames. ], batch size: 32, lr: 2.64e-02
2024-08-06 14:44:04,345 INFO [trainer.py:765] (1/8) Epoch 2, batch 1300, train_loss[loss=4.855, NarTop10Accuracy=0.3489, over 5085.00 frames. ], tot_loss[loss=4.864, NarTop10Accuracy=0.3546, over 6013.20 frames. ], batch size: 6, lr: 2.63e-02
2024-08-06 14:44:33,727 INFO [trainer.py:765] (1/8) Epoch 2, batch 1400, train_loss[loss=5.003, NarTop10Accuracy=0.3238, over 6114.00 frames. ], tot_loss[loss=4.852, NarTop10Accuracy=0.3567, over 6023.15 frames. ], batch size: 11, lr: 2.61e-02
2024-08-06 14:44:40,441 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 14:44:48,506 INFO [trainer.py:811] (1/8) Epoch 2, validation: loss=4.808, NarTop10Accuracy=0.3642, over 1905321.00 frames. 
2024-08-06 14:44:48,506 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 14:44:49,204 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 6.328e+01 1.178e+02 1.410e+02 1.789e+02 6.269e+02, threshold=2.821e+02, percent-clipped=0.0
2024-08-06 14:45:09,806 INFO [trainer.py:765] (1/8) Epoch 2, batch 1500, train_loss[loss=4.755, NarTop10Accuracy=0.3763, over 5796.00 frames. ], tot_loss[loss=4.825, NarTop10Accuracy=0.3618, over 5947.03 frames. ], batch size: 50, lr: 2.60e-02
2024-08-06 14:45:37,659 INFO [trainer.py:765] (1/8) Epoch 2, batch 1600, train_loss[loss=4.696, NarTop10Accuracy=0.3896, over 7335.00 frames. ], tot_loss[loss=4.804, NarTop10Accuracy=0.366, over 5921.42 frames. ], batch size: 22, lr: 2.59e-02
2024-08-06 14:46:04,368 INFO [trainer.py:765] (1/8) Epoch 2, batch 1700, train_loss[loss=4.844, NarTop10Accuracy=0.362, over 6141.00 frames. ], tot_loss[loss=4.798, NarTop10Accuracy=0.3665, over 5904.52 frames. ], batch size: 13, lr: 2.58e-02
2024-08-06 14:46:31,034 INFO [trainer.py:765] (1/8) Epoch 2, batch 1800, train_loss[loss=4.834, NarTop10Accuracy=0.3564, over 7107.00 frames. ], tot_loss[loss=4.773, NarTop10Accuracy=0.3713, over 5980.89 frames. ], batch size: 22, lr: 2.56e-02
2024-08-06 14:46:57,532 INFO [trainer.py:765] (1/8) Epoch 2, batch 1900, train_loss[loss=4.725, NarTop10Accuracy=0.3842, over 6390.00 frames. ], tot_loss[loss=4.749, NarTop10Accuracy=0.376, over 6019.87 frames. ], batch size: 50, lr: 2.55e-02
2024-08-06 14:47:23,233 INFO [trainer.py:765] (1/8) Epoch 2, batch 2000, train_loss[loss=4.865, NarTop10Accuracy=0.3492, over 6477.00 frames. ], tot_loss[loss=4.727, NarTop10Accuracy=0.3801, over 5993.84 frames. ], batch size: 50, lr: 2.54e-02
2024-08-06 14:47:48,589 INFO [trainer.py:765] (1/8) Epoch 2, batch 2100, train_loss[loss=4.816, NarTop10Accuracy=0.369, over 4008.00 frames. ], tot_loss[loss=4.718, NarTop10Accuracy=0.3819, over 5966.03 frames. ], batch size: 4, lr: 2.53e-02
2024-08-06 14:48:13,765 INFO [trainer.py:765] (1/8) Epoch 2, batch 2200, train_loss[loss=4.75, NarTop10Accuracy=0.3687, over 7398.00 frames. ], tot_loss[loss=4.681, NarTop10Accuracy=0.3893, over 5994.19 frames. ], batch size: 32, lr: 2.51e-02
2024-08-06 14:48:38,951 INFO [trainer.py:765] (1/8) Epoch 2, batch 2300, train_loss[loss=4.805, NarTop10Accuracy=0.3684, over 5784.00 frames. ], tot_loss[loss=4.686, NarTop10Accuracy=0.388, over 6019.97 frames. ], batch size: 9, lr: 2.50e-02
2024-08-06 14:49:03,320 INFO [trainer.py:765] (1/8) Epoch 2, batch 2400, train_loss[loss=4.233, NarTop10Accuracy=0.4782, over 4998.00 frames. ], tot_loss[loss=4.651, NarTop10Accuracy=0.3952, over 5784.93 frames. ], batch size: 7, lr: 2.49e-02
2024-08-06 14:49:26,867 INFO [trainer.py:765] (1/8) Epoch 2, batch 2500, train_loss[loss=4.84, NarTop10Accuracy=0.3573, over 5154.00 frames. ], tot_loss[loss=4.618, NarTop10Accuracy=0.4012, over 5491.63 frames. ], batch size: 7, lr: 2.48e-02
2024-08-06 14:49:46,729 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 14:50:51,117 INFO [trainer.py:765] (1/8) Epoch 3, batch 100, train_loss[loss=4.724, NarTop10Accuracy=0.3771, over 7014.00 frames. ], tot_loss[loss=4.584, NarTop10Accuracy=0.4074, over 2370.50 frames. ], batch size: 31, lr: 2.36e-02
2024-08-06 14:51:20,388 INFO [trainer.py:765] (1/8) Epoch 3, batch 200, train_loss[loss=4.609, NarTop10Accuracy=0.3925, over 6879.00 frames. ], tot_loss[loss=4.541, NarTop10Accuracy=0.4164, over 3860.05 frames. ], batch size: 17, lr: 2.34e-02
2024-08-06 14:51:50,954 INFO [trainer.py:765] (1/8) Epoch 3, batch 300, train_loss[loss=4.762, NarTop10Accuracy=0.3737, over 7164.00 frames. ], tot_loss[loss=4.514, NarTop10Accuracy=0.4217, over 4639.81 frames. ], batch size: 22, lr: 2.33e-02
2024-08-06 14:52:32,359 INFO [trainer.py:765] (1/8) Epoch 3, batch 400, train_loss[loss=4.558, NarTop10Accuracy=0.4129, over 4980.00 frames. ], tot_loss[loss=4.494, NarTop10Accuracy=0.4256, over 5076.60 frames. ], batch size: 7, lr: 2.32e-02
2024-08-06 14:53:00,680 INFO [trainer.py:765] (1/8) Epoch 3, batch 500, train_loss[loss=4.475, NarTop10Accuracy=0.4354, over 6501.00 frames. ], tot_loss[loss=4.489, NarTop10Accuracy=0.4262, over 5381.19 frames. ], batch size: 12, lr: 2.31e-02
2024-08-06 14:53:29,551 INFO [trainer.py:765] (1/8) Epoch 3, batch 600, train_loss[loss=4.167, NarTop10Accuracy=0.4923, over 5769.00 frames. ], tot_loss[loss=4.472, NarTop10Accuracy=0.4301, over 5647.48 frames. ], batch size: 9, lr: 2.30e-02
2024-08-06 14:54:12,466 INFO [trainer.py:765] (1/8) Epoch 3, batch 700, train_loss[loss=4.356, NarTop10Accuracy=0.4423, over 4893.00 frames. ], tot_loss[loss=4.451, NarTop10Accuracy=0.4341, over 5705.99 frames. ], batch size: 6, lr: 2.29e-02
2024-08-06 14:54:44,785 INFO [trainer.py:765] (1/8) Epoch 3, batch 800, train_loss[loss=4.314, NarTop10Accuracy=0.4638, over 4320.00 frames. ], tot_loss[loss=4.43, NarTop10Accuracy=0.4384, over 5770.15 frames. ], batch size: 5, lr: 2.28e-02
2024-08-06 14:54:58,684 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 14:55:06,655 INFO [trainer.py:811] (1/8) Epoch 3, validation: loss=4.276, NarTop10Accuracy=0.4689, over 1905321.00 frames. 
2024-08-06 14:55:06,656 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 14:55:07,183 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 8.443e+01 1.396e+02 1.639e+02 2.017e+02 7.124e+02, threshold=3.277e+02, percent-clipped=4.5
2024-08-06 14:55:21,051 INFO [trainer.py:765] (1/8) Epoch 3, batch 900, train_loss[loss=4.188, NarTop10Accuracy=0.4813, over 6279.00 frames. ], tot_loss[loss=4.404, NarTop10Accuracy=0.4437, over 5783.89 frames. ], batch size: 13, lr: 2.26e-02
2024-08-06 14:56:04,957 INFO [trainer.py:765] (1/8) Epoch 3, batch 1000, train_loss[loss=4.248, NarTop10Accuracy=0.4859, over 6522.00 frames. ], tot_loss[loss=4.381, NarTop10Accuracy=0.448, over 5901.79 frames. ], batch size: 14, lr: 2.25e-02
2024-08-06 14:56:37,300 INFO [trainer.py:765] (1/8) Epoch 3, batch 1100, train_loss[loss=4.577, NarTop10Accuracy=0.4033, over 6750.00 frames. ], tot_loss[loss=4.358, NarTop10Accuracy=0.4525, over 5938.30 frames. ], batch size: 17, lr: 2.24e-02
2024-08-06 14:57:06,377 INFO [trainer.py:765] (1/8) Epoch 3, batch 1200, train_loss[loss=4.429, NarTop10Accuracy=0.4404, over 7092.00 frames. ], tot_loss[loss=4.338, NarTop10Accuracy=0.4562, over 5923.78 frames. ], batch size: 31, lr: 2.23e-02
2024-08-06 14:57:51,630 INFO [trainer.py:765] (1/8) Epoch 3, batch 1300, train_loss[loss=4.184, NarTop10Accuracy=0.4836, over 4329.00 frames. ], tot_loss[loss=4.313, NarTop10Accuracy=0.4612, over 5981.83 frames. ], batch size: 5, lr: 2.22e-02
2024-08-06 14:58:22,899 INFO [trainer.py:765] (1/8) Epoch 3, batch 1400, train_loss[loss=4.058, NarTop10Accuracy=0.5129, over 6177.00 frames. ], tot_loss[loss=4.294, NarTop10Accuracy=0.4646, over 6012.60 frames. ], batch size: 11, lr: 2.21e-02
2024-08-06 14:58:50,854 INFO [trainer.py:765] (1/8) Epoch 3, batch 1500, train_loss[loss=4.312, NarTop10Accuracy=0.4692, over 6168.00 frames. ], tot_loss[loss=4.274, NarTop10Accuracy=0.4682, over 5953.88 frames. ], batch size: 50, lr: 2.20e-02
2024-08-06 14:59:18,714 INFO [trainer.py:765] (1/8) Epoch 3, batch 1600, train_loss[loss=4.011, NarTop10Accuracy=0.5185, over 7152.00 frames. ], tot_loss[loss=4.251, NarTop10Accuracy=0.4725, over 5925.80 frames. ], batch size: 22, lr: 2.19e-02
2024-08-06 14:59:45,952 INFO [trainer.py:765] (1/8) Epoch 3, batch 1700, train_loss[loss=4.066, NarTop10Accuracy=0.5119, over 6636.00 frames. ], tot_loss[loss=4.225, NarTop10Accuracy=0.478, over 5919.63 frames. ], batch size: 14, lr: 2.18e-02
2024-08-06 15:00:12,497 INFO [trainer.py:765] (1/8) Epoch 3, batch 1800, train_loss[loss=3.905, NarTop10Accuracy=0.541, over 7047.00 frames. ], tot_loss[loss=4.207, NarTop10Accuracy=0.4817, over 5976.05 frames. ], batch size: 22, lr: 2.17e-02
2024-08-06 15:00:38,948 INFO [trainer.py:765] (1/8) Epoch 3, batch 1900, train_loss[loss=4.59, NarTop10Accuracy=0.4064, over 5799.00 frames. ], tot_loss[loss=4.191, NarTop10Accuracy=0.4851, over 6008.77 frames. ], batch size: 50, lr: 2.16e-02
2024-08-06 15:01:04,605 INFO [trainer.py:765] (1/8) Epoch 3, batch 2000, train_loss[loss=4.395, NarTop10Accuracy=0.4384, over 6627.00 frames. ], tot_loss[loss=4.164, NarTop10Accuracy=0.4912, over 5989.30 frames. ], batch size: 50, lr: 2.15e-02
2024-08-06 15:01:29,898 INFO [trainer.py:765] (1/8) Epoch 3, batch 2100, train_loss[loss=3.841, NarTop10Accuracy=0.5557, over 3891.00 frames. ], tot_loss[loss=4.14, NarTop10Accuracy=0.4959, over 5959.90 frames. ], batch size: 4, lr: 2.14e-02
2024-08-06 15:01:55,181 INFO [trainer.py:765] (1/8) Epoch 3, batch 2200, train_loss[loss=3.948, NarTop10Accuracy=0.5378, over 7368.00 frames. ], tot_loss[loss=4.112, NarTop10Accuracy=0.5018, over 6001.30 frames. ], batch size: 31, lr: 2.13e-02
2024-08-06 15:02:20,409 INFO [trainer.py:765] (1/8) Epoch 3, batch 2300, train_loss[loss=4.186, NarTop10Accuracy=0.4891, over 5709.00 frames. ], tot_loss[loss=4.122, NarTop10Accuracy=0.4995, over 6017.42 frames. ], batch size: 9, lr: 2.12e-02
2024-08-06 15:02:44,663 INFO [trainer.py:765] (1/8) Epoch 3, batch 2400, train_loss[loss=4.255, NarTop10Accuracy=0.46, over 5064.00 frames. ], tot_loss[loss=4.099, NarTop10Accuracy=0.5041, over 5779.38 frames. ], batch size: 7, lr: 2.11e-02
2024-08-06 15:03:08,234 INFO [trainer.py:765] (1/8) Epoch 3, batch 2500, train_loss[loss=3.838, NarTop10Accuracy=0.558, over 5145.00 frames. ], tot_loss[loss=4.036, NarTop10Accuracy=0.5169, over 5477.61 frames. ], batch size: 7, lr: 2.10e-02
2024-08-06 15:03:28,311 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 15:04:28,130 INFO [trainer.py:765] (1/8) Epoch 4, batch 100, train_loss[loss=3.795, NarTop10Accuracy=0.5717, over 7302.00 frames. ], tot_loss[loss=4.031, NarTop10Accuracy=0.5177, over 2373.17 frames. ], batch size: 31, lr: 1.97e-02
2024-08-06 15:04:59,841 INFO [trainer.py:765] (1/8) Epoch 4, batch 200, train_loss[loss=3.884, NarTop10Accuracy=0.5462, over 6813.00 frames. ], tot_loss[loss=4.002, NarTop10Accuracy=0.5241, over 3861.09 frames. ], batch size: 17, lr: 1.96e-02
2024-08-06 15:05:27,507 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 15:05:35,694 INFO [trainer.py:811] (1/8) Epoch 4, validation: loss=3.804, NarTop10Accuracy=0.5644, over 1905321.00 frames. 
2024-08-06 15:05:35,695 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 15:05:36,237 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.166e+02 1.765e+02 1.975e+02 2.270e+02 5.852e+02, threshold=3.949e+02, percent-clipped=2.8
2024-08-06 15:05:43,888 INFO [trainer.py:765] (1/8) Epoch 4, batch 300, train_loss[loss=3.774, NarTop10Accuracy=0.5765, over 6966.00 frames. ], tot_loss[loss=3.992, NarTop10Accuracy=0.5258, over 4655.28 frames. ], batch size: 22, lr: 1.95e-02
2024-08-06 15:06:16,123 INFO [trainer.py:765] (1/8) Epoch 4, batch 400, train_loss[loss=3.768, NarTop10Accuracy=0.579, over 5055.00 frames. ], tot_loss[loss=4.006, NarTop10Accuracy=0.5232, over 5100.95 frames. ], batch size: 7, lr: 1.94e-02
2024-08-06 15:06:46,472 INFO [trainer.py:765] (1/8) Epoch 4, batch 500, train_loss[loss=4.167, NarTop10Accuracy=0.4816, over 6276.00 frames. ], tot_loss[loss=3.982, NarTop10Accuracy=0.5278, over 5377.94 frames. ], batch size: 11, lr: 1.93e-02
2024-08-06 15:07:23,817 INFO [trainer.py:765] (1/8) Epoch 4, batch 600, train_loss[loss=3.662, NarTop10Accuracy=0.6042, over 5709.00 frames. ], tot_loss[loss=3.968, NarTop10Accuracy=0.5307, over 5655.68 frames. ], batch size: 9, lr: 1.93e-02
2024-08-06 15:07:59,001 INFO [trainer.py:765] (1/8) Epoch 4, batch 700, train_loss[loss=4.256, NarTop10Accuracy=0.4754, over 4995.00 frames. ], tot_loss[loss=3.971, NarTop10Accuracy=0.5298, over 5736.67 frames. ], batch size: 6, lr: 1.92e-02
2024-08-06 15:08:32,429 INFO [trainer.py:765] (1/8) Epoch 4, batch 800, train_loss[loss=3.526, NarTop10Accuracy=0.6195, over 5058.00 frames. ], tot_loss[loss=3.96, NarTop10Accuracy=0.5323, over 5784.99 frames. ], batch size: 6, lr: 1.91e-02
2024-08-06 15:09:10,688 INFO [trainer.py:765] (1/8) Epoch 4, batch 900, train_loss[loss=3.608, NarTop10Accuracy=0.6022, over 6135.00 frames. ], tot_loss[loss=3.922, NarTop10Accuracy=0.54, over 5806.99 frames. ], batch size: 13, lr: 1.90e-02
2024-08-06 15:09:46,075 INFO [trainer.py:765] (1/8) Epoch 4, batch 1000, train_loss[loss=3.583, NarTop10Accuracy=0.6124, over 6258.00 frames. ], tot_loss[loss=3.915, NarTop10Accuracy=0.5416, over 5908.00 frames. ], batch size: 13, lr: 1.89e-02
2024-08-06 15:10:18,138 INFO [trainer.py:765] (1/8) Epoch 4, batch 1100, train_loss[loss=3.737, NarTop10Accuracy=0.5776, over 6810.00 frames. ], tot_loss[loss=3.91, NarTop10Accuracy=0.5427, over 5938.60 frames. ], batch size: 17, lr: 1.88e-02
2024-08-06 15:10:55,074 INFO [trainer.py:765] (1/8) Epoch 4, batch 1200, train_loss[loss=4.257, NarTop10Accuracy=0.4645, over 7092.00 frames. ], tot_loss[loss=3.9, NarTop10Accuracy=0.5442, over 5928.01 frames. ], batch size: 31, lr: 1.88e-02
2024-08-06 15:11:32,073 INFO [trainer.py:765] (1/8) Epoch 4, batch 1300, train_loss[loss=3.505, NarTop10Accuracy=0.6245, over 4977.00 frames. ], tot_loss[loss=3.856, NarTop10Accuracy=0.5532, over 5994.56 frames. ], batch size: 6, lr: 1.87e-02
2024-08-06 15:12:05,687 INFO [trainer.py:765] (1/8) Epoch 4, batch 1400, train_loss[loss=3.776, NarTop10Accuracy=0.5839, over 6087.00 frames. ], tot_loss[loss=3.857, NarTop10Accuracy=0.5534, over 6014.16 frames. ], batch size: 11, lr: 1.86e-02
2024-08-06 15:12:33,695 INFO [trainer.py:765] (1/8) Epoch 4, batch 1500, train_loss[loss=3.838, NarTop10Accuracy=0.5622, over 5802.00 frames. ], tot_loss[loss=3.857, NarTop10Accuracy=0.5532, over 5955.71 frames. ], batch size: 50, lr: 1.85e-02
2024-08-06 15:13:01,509 INFO [trainer.py:765] (1/8) Epoch 4, batch 1600, train_loss[loss=3.773, NarTop10Accuracy=0.5689, over 6972.00 frames. ], tot_loss[loss=3.848, NarTop10Accuracy=0.5554, over 5919.53 frames. ], batch size: 22, lr: 1.84e-02
2024-08-06 15:13:28,132 INFO [trainer.py:765] (1/8) Epoch 4, batch 1700, train_loss[loss=3.747, NarTop10Accuracy=0.5794, over 6333.00 frames. ], tot_loss[loss=3.829, NarTop10Accuracy=0.5597, over 5912.60 frames. ], batch size: 13, lr: 1.84e-02
2024-08-06 15:13:54,556 INFO [trainer.py:765] (1/8) Epoch 4, batch 1800, train_loss[loss=3.778, NarTop10Accuracy=0.5771, over 7107.00 frames. ], tot_loss[loss=3.835, NarTop10Accuracy=0.5582, over 5977.35 frames. ], batch size: 22, lr: 1.83e-02
2024-08-06 15:14:20,997 INFO [trainer.py:765] (1/8) Epoch 4, batch 1900, train_loss[loss=3.748, NarTop10Accuracy=0.5852, over 6405.00 frames. ], tot_loss[loss=3.856, NarTop10Accuracy=0.5536, over 6021.15 frames. ], batch size: 50, lr: 1.82e-02
2024-08-06 15:14:46,671 INFO [trainer.py:765] (1/8) Epoch 4, batch 2000, train_loss[loss=3.803, NarTop10Accuracy=0.5592, over 6174.00 frames. ], tot_loss[loss=3.828, NarTop10Accuracy=0.5593, over 5991.10 frames. ], batch size: 50, lr: 1.81e-02
2024-08-06 15:15:11,858 INFO [trainer.py:765] (1/8) Epoch 4, batch 2100, train_loss[loss=3.473, NarTop10Accuracy=0.6247, over 3804.00 frames. ], tot_loss[loss=3.815, NarTop10Accuracy=0.5618, over 5976.64 frames. ], batch size: 4, lr: 1.81e-02
2024-08-06 15:15:37,088 INFO [trainer.py:765] (1/8) Epoch 4, batch 2200, train_loss[loss=3.601, NarTop10Accuracy=0.6104, over 7656.00 frames. ], tot_loss[loss=3.806, NarTop10Accuracy=0.5636, over 6011.79 frames. ], batch size: 32, lr: 1.80e-02
2024-08-06 15:15:55,088 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 15:16:03,243 INFO [trainer.py:811] (1/8) Epoch 4, validation: loss=3.665, NarTop10Accuracy=0.5912, over 1905321.00 frames. 
2024-08-06 15:16:03,243 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 15:16:03,740 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.414e+02 1.889e+02 2.096e+02 2.369e+02 1.168e+03, threshold=4.192e+02, percent-clipped=1.7
2024-08-06 15:16:10,347 INFO [trainer.py:765] (1/8) Epoch 4, batch 2300, train_loss[loss=3.68, NarTop10Accuracy=0.5964, over 5628.00 frames. ], tot_loss[loss=3.816, NarTop10Accuracy=0.5616, over 6014.31 frames. ], batch size: 9, lr: 1.79e-02
2024-08-06 15:16:34,840 INFO [trainer.py:765] (1/8) Epoch 4, batch 2400, train_loss[loss=3.425, NarTop10Accuracy=0.6501, over 5139.00 frames. ], tot_loss[loss=3.779, NarTop10Accuracy=0.5691, over 5757.92 frames. ], batch size: 7, lr: 1.79e-02
2024-08-06 15:16:58,534 INFO [trainer.py:765] (1/8) Epoch 4, batch 2500, train_loss[loss=3.52, NarTop10Accuracy=0.6293, over 5199.00 frames. ], tot_loss[loss=3.767, NarTop10Accuracy=0.5713, over 5480.65 frames. ], batch size: 7, lr: 1.78e-02
2024-08-06 15:17:18,901 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 15:18:24,101 INFO [trainer.py:765] (1/8) Epoch 5, batch 100, train_loss[loss=3.506, NarTop10Accuracy=0.6341, over 7452.00 frames. ], tot_loss[loss=3.777, NarTop10Accuracy=0.5702, over 2361.88 frames. ], batch size: 31, lr: 1.66e-02
2024-08-06 15:18:59,675 INFO [trainer.py:765] (1/8) Epoch 5, batch 200, train_loss[loss=4.102, NarTop10Accuracy=0.5003, over 6678.00 frames. ], tot_loss[loss=3.751, NarTop10Accuracy=0.5752, over 3846.93 frames. ], batch size: 17, lr: 1.65e-02
2024-08-06 15:19:32,888 INFO [trainer.py:765] (1/8) Epoch 5, batch 300, train_loss[loss=4.004, NarTop10Accuracy=0.522, over 6969.00 frames. ], tot_loss[loss=3.724, NarTop10Accuracy=0.5807, over 4653.09 frames. ], batch size: 22, lr: 1.65e-02
2024-08-06 15:20:01,656 INFO [trainer.py:765] (1/8) Epoch 5, batch 400, train_loss[loss=3.575, NarTop10Accuracy=0.6216, over 5151.00 frames. ], tot_loss[loss=3.712, NarTop10Accuracy=0.5825, over 5098.33 frames. ], batch size: 7, lr: 1.64e-02
2024-08-06 15:20:38,298 INFO [trainer.py:765] (1/8) Epoch 5, batch 500, train_loss[loss=3.957, NarTop10Accuracy=0.5258, over 6045.00 frames. ], tot_loss[loss=3.732, NarTop10Accuracy=0.5779, over 5373.97 frames. ], batch size: 11, lr: 1.63e-02
2024-08-06 15:21:13,711 INFO [trainer.py:765] (1/8) Epoch 5, batch 600, train_loss[loss=3.891, NarTop10Accuracy=0.5376, over 5703.00 frames. ], tot_loss[loss=3.719, NarTop10Accuracy=0.5803, over 5658.33 frames. ], batch size: 9, lr: 1.63e-02
2024-08-06 15:21:45,881 INFO [trainer.py:765] (1/8) Epoch 5, batch 700, train_loss[loss=3.362, NarTop10Accuracy=0.6607, over 4884.00 frames. ], tot_loss[loss=3.716, NarTop10Accuracy=0.5814, over 5730.89 frames. ], batch size: 6, lr: 1.62e-02
2024-08-06 15:22:24,499 INFO [trainer.py:765] (1/8) Epoch 5, batch 800, train_loss[loss=4.001, NarTop10Accuracy=0.5202, over 4941.00 frames. ], tot_loss[loss=3.705, NarTop10Accuracy=0.5839, over 5785.20 frames. ], batch size: 6, lr: 1.62e-02
2024-08-06 15:22:56,784 INFO [trainer.py:765] (1/8) Epoch 5, batch 900, train_loss[loss=3.622, NarTop10Accuracy=0.6063, over 6216.00 frames. ], tot_loss[loss=3.698, NarTop10Accuracy=0.5852, over 5819.06 frames. ], batch size: 13, lr: 1.61e-02
2024-08-06 15:23:31,914 INFO [trainer.py:765] (1/8) Epoch 5, batch 1000, train_loss[loss=3.672, NarTop10Accuracy=0.6, over 6234.00 frames. ], tot_loss[loss=3.683, NarTop10Accuracy=0.5883, over 5913.73 frames. ], batch size: 13, lr: 1.60e-02
2024-08-06 15:24:09,572 INFO [trainer.py:765] (1/8) Epoch 5, batch 1100, train_loss[loss=3.529, NarTop10Accuracy=0.6244, over 6906.00 frames. ], tot_loss[loss=3.681, NarTop10Accuracy=0.5887, over 5933.90 frames. ], batch size: 17, lr: 1.60e-02
2024-08-06 15:24:44,529 INFO [trainer.py:765] (1/8) Epoch 5, batch 1200, train_loss[loss=3.449, NarTop10Accuracy=0.6391, over 7329.00 frames. ], tot_loss[loss=3.678, NarTop10Accuracy=0.5893, over 5914.00 frames. ], batch size: 31, lr: 1.59e-02
2024-08-06 15:25:19,380 INFO [trainer.py:765] (1/8) Epoch 5, batch 1300, train_loss[loss=3.838, NarTop10Accuracy=0.5451, over 5118.00 frames. ], tot_loss[loss=3.665, NarTop10Accuracy=0.592, over 6003.15 frames. ], batch size: 6, lr: 1.59e-02
2024-08-06 15:25:51,694 INFO [trainer.py:765] (1/8) Epoch 5, batch 1400, train_loss[loss=3.901, NarTop10Accuracy=0.5419, over 6000.00 frames. ], tot_loss[loss=3.67, NarTop10Accuracy=0.5909, over 6018.90 frames. ], batch size: 11, lr: 1.58e-02
2024-08-06 15:26:26,195 INFO [trainer.py:765] (1/8) Epoch 5, batch 1500, train_loss[loss=3.593, NarTop10Accuracy=0.6177, over 6606.00 frames. ], tot_loss[loss=3.668, NarTop10Accuracy=0.5912, over 5952.64 frames. ], batch size: 53, lr: 1.58e-02
2024-08-06 15:26:54,130 INFO [trainer.py:765] (1/8) Epoch 5, batch 1600, train_loss[loss=3.494, NarTop10Accuracy=0.6325, over 7173.00 frames. ], tot_loss[loss=3.682, NarTop10Accuracy=0.5886, over 5929.80 frames. ], batch size: 22, lr: 1.57e-02
2024-08-06 15:27:19,603 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 15:27:27,821 INFO [trainer.py:811] (1/8) Epoch 5, validation: loss=3.552, NarTop10Accuracy=0.6147, over 1905321.00 frames. 
2024-08-06 15:27:27,822 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 15:27:28,341 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.340e+02 1.756e+02 1.962e+02 2.205e+02 5.880e+02, threshold=3.924e+02, percent-clipped=0.8
2024-08-06 15:27:29,131 INFO [trainer.py:765] (1/8) Epoch 5, batch 1700, train_loss[loss=3.653, NarTop10Accuracy=0.5954, over 6618.00 frames. ], tot_loss[loss=3.665, NarTop10Accuracy=0.5921, over 5921.38 frames. ], batch size: 14, lr: 1.56e-02
2024-08-06 15:27:55,652 INFO [trainer.py:765] (1/8) Epoch 5, batch 1800, train_loss[loss=3.762, NarTop10Accuracy=0.5703, over 7242.00 frames. ], tot_loss[loss=3.664, NarTop10Accuracy=0.5923, over 5967.37 frames. ], batch size: 22, lr: 1.56e-02
2024-08-06 15:28:22,172 INFO [trainer.py:765] (1/8) Epoch 5, batch 1900, train_loss[loss=3.704, NarTop10Accuracy=0.5872, over 5916.00 frames. ], tot_loss[loss=3.671, NarTop10Accuracy=0.5911, over 6017.91 frames. ], batch size: 50, lr: 1.55e-02
2024-08-06 15:28:47,893 INFO [trainer.py:765] (1/8) Epoch 5, batch 2000, train_loss[loss=3.626, NarTop10Accuracy=0.5978, over 5979.00 frames. ], tot_loss[loss=3.669, NarTop10Accuracy=0.5912, over 5990.51 frames. ], batch size: 50, lr: 1.55e-02
2024-08-06 15:29:13,770 INFO [trainer.py:765] (1/8) Epoch 5, batch 2100, train_loss[loss=3.435, NarTop10Accuracy=0.6453, over 3843.00 frames. ], tot_loss[loss=3.687, NarTop10Accuracy=0.5873, over 5961.66 frames. ], batch size: 4, lr: 1.54e-02
2024-08-06 15:29:39,177 INFO [trainer.py:765] (1/8) Epoch 5, batch 2200, train_loss[loss=4.104, NarTop10Accuracy=0.4974, over 7347.00 frames. ], tot_loss[loss=3.672, NarTop10Accuracy=0.5902, over 5995.22 frames. ], batch size: 31, lr: 1.54e-02
2024-08-06 15:30:04,430 INFO [trainer.py:765] (1/8) Epoch 5, batch 2300, train_loss[loss=3.461, NarTop10Accuracy=0.6269, over 5748.00 frames. ], tot_loss[loss=3.681, NarTop10Accuracy=0.5885, over 6015.65 frames. ], batch size: 9, lr: 1.53e-02
2024-08-06 15:30:28,862 INFO [trainer.py:765] (1/8) Epoch 5, batch 2400, train_loss[loss=3.327, NarTop10Accuracy=0.6591, over 5127.00 frames. ], tot_loss[loss=3.654, NarTop10Accuracy=0.5942, over 5764.05 frames. ], batch size: 7, lr: 1.53e-02
2024-08-06 15:30:52,502 INFO [trainer.py:765] (1/8) Epoch 5, batch 2500, train_loss[loss=3.349, NarTop10Accuracy=0.654, over 5037.00 frames. ], tot_loss[loss=3.611, NarTop10Accuracy=0.6026, over 5453.35 frames. ], batch size: 7, lr: 1.52e-02
2024-08-06 15:31:12,397 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 15:32:14,415 INFO [trainer.py:765] (1/8) Epoch 6, batch 100, train_loss[loss=3.505, NarTop10Accuracy=0.6322, over 7221.00 frames. ], tot_loss[loss=3.629, NarTop10Accuracy=0.5986, over 2359.27 frames. ], batch size: 32, lr: 1.42e-02
2024-08-06 15:32:46,016 INFO [trainer.py:765] (1/8) Epoch 6, batch 200, train_loss[loss=4.019, NarTop10Accuracy=0.505, over 7098.00 frames. ], tot_loss[loss=3.616, NarTop10Accuracy=0.6016, over 3859.41 frames. ], batch size: 18, lr: 1.42e-02
2024-08-06 15:33:21,243 INFO [trainer.py:765] (1/8) Epoch 6, batch 300, train_loss[loss=3.546, NarTop10Accuracy=0.6158, over 7278.00 frames. ], tot_loss[loss=3.613, NarTop10Accuracy=0.6022, over 4660.06 frames. ], batch size: 23, lr: 1.41e-02
2024-08-06 15:33:56,035 INFO [trainer.py:765] (1/8) Epoch 6, batch 400, train_loss[loss=3.453, NarTop10Accuracy=0.6373, over 5067.00 frames. ], tot_loss[loss=3.597, NarTop10Accuracy=0.6054, over 5096.56 frames. ], batch size: 7, lr: 1.41e-02
2024-08-06 15:34:26,759 INFO [trainer.py:765] (1/8) Epoch 6, batch 500, train_loss[loss=3.309, NarTop10Accuracy=0.6671, over 6117.00 frames. ], tot_loss[loss=3.582, NarTop10Accuracy=0.609, over 5385.10 frames. ], batch size: 11, lr: 1.40e-02
2024-08-06 15:35:01,458 INFO [trainer.py:765] (1/8) Epoch 6, batch 600, train_loss[loss=3.309, NarTop10Accuracy=0.6715, over 6198.00 frames. ], tot_loss[loss=3.581, NarTop10Accuracy=0.6088, over 5672.91 frames. ], batch size: 10, lr: 1.40e-02
2024-08-06 15:35:32,734 INFO [trainer.py:765] (1/8) Epoch 6, batch 700, train_loss[loss=3.355, NarTop10Accuracy=0.6594, over 4338.00 frames. ], tot_loss[loss=3.584, NarTop10Accuracy=0.6086, over 5721.21 frames. ], batch size: 5, lr: 1.39e-02
2024-08-06 15:36:06,844 INFO [trainer.py:765] (1/8) Epoch 6, batch 800, train_loss[loss=3.623, NarTop10Accuracy=0.5956, over 5079.00 frames. ], tot_loss[loss=3.593, NarTop10Accuracy=0.6064, over 5787.56 frames. ], batch size: 6, lr: 1.39e-02
2024-08-06 15:36:40,384 INFO [trainer.py:765] (1/8) Epoch 6, batch 900, train_loss[loss=3.934, NarTop10Accuracy=0.5359, over 6339.00 frames. ], tot_loss[loss=3.582, NarTop10Accuracy=0.6086, over 5792.08 frames. ], batch size: 13, lr: 1.38e-02
2024-08-06 15:37:15,272 INFO [trainer.py:765] (1/8) Epoch 6, batch 1000, train_loss[loss=3.364, NarTop10Accuracy=0.6451, over 6837.00 frames. ], tot_loss[loss=3.594, NarTop10Accuracy=0.6058, over 5898.09 frames. ], batch size: 14, lr: 1.38e-02
2024-08-06 15:37:50,508 INFO [trainer.py:765] (1/8) Epoch 6, batch 1100, train_loss[loss=3.419, NarTop10Accuracy=0.6495, over 6723.00 frames. ], tot_loss[loss=3.589, NarTop10Accuracy=0.6071, over 5932.45 frames. ], batch size: 17, lr: 1.38e-02
2024-08-06 15:37:55,828 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 15:38:04,436 INFO [trainer.py:811] (1/8) Epoch 6, validation: loss=3.421, NarTop10Accuracy=0.6418, over 1905321.00 frames. 
2024-08-06 15:38:04,437 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 15:38:04,965 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.415e+02 1.809e+02 1.991e+02 2.234e+02 5.215e+02, threshold=3.983e+02, percent-clipped=0.5
2024-08-06 15:38:36,168 INFO [trainer.py:765] (1/8) Epoch 6, batch 1200, train_loss[loss=3.422, NarTop10Accuracy=0.647, over 7536.00 frames. ], tot_loss[loss=3.571, NarTop10Accuracy=0.6108, over 5931.31 frames. ], batch size: 32, lr: 1.37e-02
2024-08-06 15:39:08,242 INFO [trainer.py:765] (1/8) Epoch 6, batch 1300, train_loss[loss=3.474, NarTop10Accuracy=0.6334, over 5013.00 frames. ], tot_loss[loss=3.57, NarTop10Accuracy=0.611, over 5989.57 frames. ], batch size: 6, lr: 1.37e-02
2024-08-06 15:39:44,069 INFO [trainer.py:765] (1/8) Epoch 6, batch 1400, train_loss[loss=3.372, NarTop10Accuracy=0.6546, over 6060.00 frames. ], tot_loss[loss=3.57, NarTop10Accuracy=0.6114, over 6008.00 frames. ], batch size: 11, lr: 1.36e-02
2024-08-06 15:40:15,383 INFO [trainer.py:765] (1/8) Epoch 6, batch 1500, train_loss[loss=4.034, NarTop10Accuracy=0.5213, over 6066.00 frames. ], tot_loss[loss=3.565, NarTop10Accuracy=0.6126, over 5948.07 frames. ], batch size: 50, lr: 1.36e-02
2024-08-06 15:40:43,105 INFO [trainer.py:765] (1/8) Epoch 6, batch 1600, train_loss[loss=3.456, NarTop10Accuracy=0.6325, over 6930.00 frames. ], tot_loss[loss=3.56, NarTop10Accuracy=0.6134, over 5917.39 frames. ], batch size: 22, lr: 1.35e-02
2024-08-06 15:41:09,788 INFO [trainer.py:765] (1/8) Epoch 6, batch 1700, train_loss[loss=3.526, NarTop10Accuracy=0.6194, over 6159.00 frames. ], tot_loss[loss=3.55, NarTop10Accuracy=0.6152, over 5917.20 frames. ], batch size: 13, lr: 1.35e-02
2024-08-06 15:41:36,316 INFO [trainer.py:765] (1/8) Epoch 6, batch 1800, train_loss[loss=3.454, NarTop10Accuracy=0.6394, over 7386.00 frames. ], tot_loss[loss=3.561, NarTop10Accuracy=0.6132, over 5996.07 frames. ], batch size: 22, lr: 1.35e-02
2024-08-06 15:42:02,720 INFO [trainer.py:765] (1/8) Epoch 6, batch 1900, train_loss[loss=3.804, NarTop10Accuracy=0.5647, over 6288.00 frames. ], tot_loss[loss=3.583, NarTop10Accuracy=0.6087, over 6033.13 frames. ], batch size: 51, lr: 1.34e-02
2024-08-06 15:42:28,319 INFO [trainer.py:765] (1/8) Epoch 6, batch 2000, train_loss[loss=3.504, NarTop10Accuracy=0.62, over 6582.00 frames. ], tot_loss[loss=3.576, NarTop10Accuracy=0.6097, over 6026.23 frames. ], batch size: 50, lr: 1.34e-02
2024-08-06 15:42:53,669 INFO [trainer.py:765] (1/8) Epoch 6, batch 2100, train_loss[loss=3.166, NarTop10Accuracy=0.6929, over 3990.00 frames. ], tot_loss[loss=3.557, NarTop10Accuracy=0.6133, over 5994.33 frames. ], batch size: 4, lr: 1.33e-02
2024-08-06 15:43:18,977 INFO [trainer.py:765] (1/8) Epoch 6, batch 2200, train_loss[loss=3.782, NarTop10Accuracy=0.566, over 7395.00 frames. ], tot_loss[loss=3.564, NarTop10Accuracy=0.6122, over 6025.15 frames. ], batch size: 31, lr: 1.33e-02
2024-08-06 15:43:44,105 INFO [trainer.py:765] (1/8) Epoch 6, batch 2300, train_loss[loss=3.327, NarTop10Accuracy=0.666, over 5712.00 frames. ], tot_loss[loss=3.561, NarTop10Accuracy=0.6126, over 6043.14 frames. ], batch size: 9, lr: 1.33e-02
2024-08-06 15:44:08,620 INFO [trainer.py:765] (1/8) Epoch 6, batch 2400, train_loss[loss=3.385, NarTop10Accuracy=0.6523, over 5031.00 frames. ], tot_loss[loss=3.533, NarTop10Accuracy=0.6183, over 5788.15 frames. ], batch size: 7, lr: 1.32e-02
2024-08-06 15:44:32,132 INFO [trainer.py:765] (1/8) Epoch 6, batch 2500, train_loss[loss=3.496, NarTop10Accuracy=0.6312, over 5154.00 frames. ], tot_loss[loss=3.52, NarTop10Accuracy=0.6211, over 5472.80 frames. ], batch size: 7, lr: 1.32e-02
2024-08-06 15:44:51,568 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 15:45:58,042 INFO [trainer.py:765] (1/8) Epoch 7, batch 100, train_loss[loss=3.382, NarTop10Accuracy=0.6544, over 7578.00 frames. ], tot_loss[loss=3.544, NarTop10Accuracy=0.6162, over 2370.00 frames. ], batch size: 31, lr: 1.24e-02
2024-08-06 15:46:33,613 INFO [trainer.py:765] (1/8) Epoch 7, batch 200, train_loss[loss=3.467, NarTop10Accuracy=0.6207, over 6849.00 frames. ], tot_loss[loss=3.524, NarTop10Accuracy=0.6201, over 3857.92 frames. ], batch size: 17, lr: 1.23e-02
2024-08-06 15:47:03,246 INFO [trainer.py:765] (1/8) Epoch 7, batch 300, train_loss[loss=3.847, NarTop10Accuracy=0.5556, over 7293.00 frames. ], tot_loss[loss=3.538, NarTop10Accuracy=0.6179, over 4649.38 frames. ], batch size: 23, lr: 1.23e-02
2024-08-06 15:47:34,494 INFO [trainer.py:765] (1/8) Epoch 7, batch 400, train_loss[loss=3.661, NarTop10Accuracy=0.5924, over 5658.00 frames. ], tot_loss[loss=3.533, NarTop10Accuracy=0.6188, over 5107.51 frames. ], batch size: 8, lr: 1.23e-02
2024-08-06 15:48:13,729 INFO [trainer.py:765] (1/8) Epoch 7, batch 500, train_loss[loss=3.611, NarTop10Accuracy=0.6036, over 6024.00 frames. ], tot_loss[loss=3.521, NarTop10Accuracy=0.621, over 5375.72 frames. ], batch size: 11, lr: 1.22e-02
2024-08-06 15:48:26,368 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 15:48:34,533 INFO [trainer.py:811] (1/8) Epoch 7, validation: loss=3.326, NarTop10Accuracy=0.6612, over 1905321.00 frames. 
2024-08-06 15:48:34,534 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 15:48:35,079 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.466e+02 1.860e+02 2.018e+02 2.241e+02 5.111e+02, threshold=4.035e+02, percent-clipped=0.3
2024-08-06 15:48:52,721 INFO [trainer.py:765] (1/8) Epoch 7, batch 600, train_loss[loss=3.204, NarTop10Accuracy=0.6898, over 5748.00 frames. ], tot_loss[loss=3.522, NarTop10Accuracy=0.6209, over 5634.24 frames. ], batch size: 9, lr: 1.22e-02
2024-08-06 15:49:24,911 INFO [trainer.py:765] (1/8) Epoch 7, batch 700, train_loss[loss=3.802, NarTop10Accuracy=0.5594, over 5118.00 frames. ], tot_loss[loss=3.516, NarTop10Accuracy=0.622, over 5700.01 frames. ], batch size: 6, lr: 1.21e-02
2024-08-06 15:50:04,380 INFO [trainer.py:765] (1/8) Epoch 7, batch 800, train_loss[loss=3.101, NarTop10Accuracy=0.7091, over 5028.00 frames. ], tot_loss[loss=3.502, NarTop10Accuracy=0.6253, over 5756.47 frames. ], batch size: 6, lr: 1.21e-02
2024-08-06 15:50:34,548 INFO [trainer.py:765] (1/8) Epoch 7, batch 900, train_loss[loss=3.269, NarTop10Accuracy=0.6767, over 6636.00 frames. ], tot_loss[loss=3.495, NarTop10Accuracy=0.6264, over 5791.30 frames. ], batch size: 14, lr: 1.21e-02
2024-08-06 15:51:07,154 INFO [trainer.py:765] (1/8) Epoch 7, batch 1000, train_loss[loss=3.312, NarTop10Accuracy=0.661, over 6072.00 frames. ], tot_loss[loss=3.49, NarTop10Accuracy=0.6274, over 5902.62 frames. ], batch size: 13, lr: 1.20e-02
2024-08-06 15:51:51,758 INFO [trainer.py:765] (1/8) Epoch 7, batch 1100, train_loss[loss=3.311, NarTop10Accuracy=0.6652, over 6777.00 frames. ], tot_loss[loss=3.492, NarTop10Accuracy=0.6272, over 5944.99 frames. ], batch size: 17, lr: 1.20e-02
2024-08-06 15:52:22,699 INFO [trainer.py:765] (1/8) Epoch 7, batch 1200, train_loss[loss=3.403, NarTop10Accuracy=0.6526, over 7455.00 frames. ], tot_loss[loss=3.492, NarTop10Accuracy=0.6272, over 5939.14 frames. ], batch size: 31, lr: 1.20e-02
2024-08-06 15:52:52,007 INFO [trainer.py:765] (1/8) Epoch 7, batch 1300, train_loss[loss=3.448, NarTop10Accuracy=0.6362, over 5046.00 frames. ], tot_loss[loss=3.495, NarTop10Accuracy=0.6262, over 5998.13 frames. ], batch size: 6, lr: 1.19e-02
2024-08-06 15:53:33,841 INFO [trainer.py:765] (1/8) Epoch 7, batch 1400, train_loss[loss=3.312, NarTop10Accuracy=0.6672, over 6219.00 frames. ], tot_loss[loss=3.496, NarTop10Accuracy=0.626, over 6031.75 frames. ], batch size: 11, lr: 1.19e-02
2024-08-06 15:54:04,599 INFO [trainer.py:765] (1/8) Epoch 7, batch 1500, train_loss[loss=3.615, NarTop10Accuracy=0.593, over 5625.00 frames. ], tot_loss[loss=3.475, NarTop10Accuracy=0.6305, over 5952.57 frames. ], batch size: 51, lr: 1.19e-02
2024-08-06 15:54:32,384 INFO [trainer.py:765] (1/8) Epoch 7, batch 1600, train_loss[loss=3.626, NarTop10Accuracy=0.5926, over 7023.00 frames. ], tot_loss[loss=3.477, NarTop10Accuracy=0.63, over 5930.83 frames. ], batch size: 22, lr: 1.19e-02
2024-08-06 15:54:59,054 INFO [trainer.py:765] (1/8) Epoch 7, batch 1700, train_loss[loss=3.524, NarTop10Accuracy=0.6189, over 6063.00 frames. ], tot_loss[loss=3.494, NarTop10Accuracy=0.626, over 5916.40 frames. ], batch size: 13, lr: 1.18e-02
2024-08-06 15:55:25,512 INFO [trainer.py:765] (1/8) Epoch 7, batch 1800, train_loss[loss=3.911, NarTop10Accuracy=0.5472, over 6942.00 frames. ], tot_loss[loss=3.492, NarTop10Accuracy=0.6263, over 5970.30 frames. ], batch size: 22, lr: 1.18e-02
2024-08-06 15:55:52,082 INFO [trainer.py:765] (1/8) Epoch 7, batch 1900, train_loss[loss=3.414, NarTop10Accuracy=0.6378, over 6087.00 frames. ], tot_loss[loss=3.509, NarTop10Accuracy=0.6232, over 6009.46 frames. ], batch size: 50, lr: 1.18e-02
2024-08-06 15:56:17,590 INFO [trainer.py:765] (1/8) Epoch 7, batch 2000, train_loss[loss=3.775, NarTop10Accuracy=0.569, over 6579.00 frames. ], tot_loss[loss=3.509, NarTop10Accuracy=0.6234, over 5991.80 frames. ], batch size: 51, lr: 1.17e-02
2024-08-06 15:56:42,856 INFO [trainer.py:765] (1/8) Epoch 7, batch 2100, train_loss[loss=3.93, NarTop10Accuracy=0.5233, over 4005.00 frames. ], tot_loss[loss=3.495, NarTop10Accuracy=0.6264, over 5969.26 frames. ], batch size: 4, lr: 1.17e-02
2024-08-06 15:57:08,078 INFO [trainer.py:765] (1/8) Epoch 7, batch 2200, train_loss[loss=3.475, NarTop10Accuracy=0.6246, over 7152.00 frames. ], tot_loss[loss=3.511, NarTop10Accuracy=0.6229, over 6005.32 frames. ], batch size: 31, lr: 1.17e-02
2024-08-06 15:57:33,178 INFO [trainer.py:765] (1/8) Epoch 7, batch 2300, train_loss[loss=3.14, NarTop10Accuracy=0.6927, over 5637.00 frames. ], tot_loss[loss=3.508, NarTop10Accuracy=0.6237, over 6018.05 frames. ], batch size: 9, lr: 1.16e-02
2024-08-06 15:57:57,618 INFO [trainer.py:765] (1/8) Epoch 7, batch 2400, train_loss[loss=3.174, NarTop10Accuracy=0.6874, over 5166.00 frames. ], tot_loss[loss=3.492, NarTop10Accuracy=0.627, over 5756.67 frames. ], batch size: 7, lr: 1.16e-02
2024-08-06 15:58:21,088 INFO [trainer.py:765] (1/8) Epoch 7, batch 2500, train_loss[loss=3.856, NarTop10Accuracy=0.5531, over 5229.00 frames. ], tot_loss[loss=3.467, NarTop10Accuracy=0.6317, over 5455.22 frames. ], batch size: 7, lr: 1.16e-02
2024-08-06 15:58:31,565 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 15:58:39,769 INFO [trainer.py:811] (1/8) Epoch 7, validation: loss=3.381, NarTop10Accuracy=0.6488, over 1905321.00 frames. 
2024-08-06 15:58:39,770 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 15:58:40,221 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.471e+02 1.831e+02 1.996e+02 2.207e+02 5.229e+02, threshold=3.992e+02, percent-clipped=0.2
2024-08-06 15:58:49,133 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 15:59:52,877 INFO [trainer.py:765] (1/8) Epoch 8, batch 100, train_loss[loss=3.632, NarTop10Accuracy=0.5922, over 7077.00 frames. ], tot_loss[loss=3.462, NarTop10Accuracy=0.6334, over 2376.28 frames. ], batch size: 31, lr: 1.09e-02
2024-08-06 16:00:27,880 INFO [trainer.py:765] (1/8) Epoch 8, batch 200, train_loss[loss=3.313, NarTop10Accuracy=0.6651, over 6924.00 frames. ], tot_loss[loss=3.481, NarTop10Accuracy=0.6297, over 3853.53 frames. ], batch size: 17, lr: 1.09e-02
2024-08-06 16:00:58,562 INFO [trainer.py:765] (1/8) Epoch 8, batch 300, train_loss[loss=3.303, NarTop10Accuracy=0.67, over 7332.00 frames. ], tot_loss[loss=3.471, NarTop10Accuracy=0.6314, over 4655.77 frames. ], batch size: 22, lr: 1.08e-02
2024-08-06 16:01:29,759 INFO [trainer.py:765] (1/8) Epoch 8, batch 400, train_loss[loss=3.715, NarTop10Accuracy=0.5725, over 5028.00 frames. ], tot_loss[loss=3.465, NarTop10Accuracy=0.6315, over 5099.67 frames. ], batch size: 7, lr: 1.08e-02
2024-08-06 16:02:04,065 INFO [trainer.py:765] (1/8) Epoch 8, batch 500, train_loss[loss=3.865, NarTop10Accuracy=0.5492, over 6093.00 frames. ], tot_loss[loss=3.452, NarTop10Accuracy=0.6342, over 5372.03 frames. ], batch size: 11, lr: 1.08e-02
2024-08-06 16:02:41,835 INFO [trainer.py:765] (1/8) Epoch 8, batch 600, train_loss[loss=3.158, NarTop10Accuracy=0.7052, over 5709.00 frames. ], tot_loss[loss=3.465, NarTop10Accuracy=0.6315, over 5640.03 frames. ], batch size: 9, lr: 1.08e-02
2024-08-06 16:03:11,499 INFO [trainer.py:765] (1/8) Epoch 8, batch 700, train_loss[loss=3.691, NarTop10Accuracy=0.5815, over 5190.00 frames. ], tot_loss[loss=3.47, NarTop10Accuracy=0.6304, over 5703.73 frames. ], batch size: 6, lr: 1.07e-02
2024-08-06 16:03:50,083 INFO [trainer.py:765] (1/8) Epoch 8, batch 800, train_loss[loss=3.372, NarTop10Accuracy=0.6531, over 5049.00 frames. ], tot_loss[loss=3.465, NarTop10Accuracy=0.6318, over 5772.34 frames. ], batch size: 6, lr: 1.07e-02
2024-08-06 16:04:27,587 INFO [trainer.py:765] (1/8) Epoch 8, batch 900, train_loss[loss=3.228, NarTop10Accuracy=0.6794, over 6150.00 frames. ], tot_loss[loss=3.448, NarTop10Accuracy=0.6356, over 5792.09 frames. ], batch size: 13, lr: 1.07e-02
2024-08-06 16:04:57,465 INFO [trainer.py:765] (1/8) Epoch 8, batch 1000, train_loss[loss=3.62, NarTop10Accuracy=0.5982, over 6234.00 frames. ], tot_loss[loss=3.442, NarTop10Accuracy=0.6371, over 5905.49 frames. ], batch size: 13, lr: 1.07e-02
2024-08-06 16:05:37,293 INFO [trainer.py:765] (1/8) Epoch 8, batch 1100, train_loss[loss=3.731, NarTop10Accuracy=0.5821, over 6822.00 frames. ], tot_loss[loss=3.437, NarTop10Accuracy=0.638, over 5924.46 frames. ], batch size: 17, lr: 1.06e-02
2024-08-06 16:06:15,860 INFO [trainer.py:765] (1/8) Epoch 8, batch 1200, train_loss[loss=3.448, NarTop10Accuracy=0.6366, over 7335.00 frames. ], tot_loss[loss=3.448, NarTop10Accuracy=0.6354, over 5936.03 frames. ], batch size: 31, lr: 1.06e-02
2024-08-06 16:06:45,186 INFO [trainer.py:765] (1/8) Epoch 8, batch 1300, train_loss[loss=3.417, NarTop10Accuracy=0.6429, over 5172.00 frames. ], tot_loss[loss=3.441, NarTop10Accuracy=0.6369, over 5999.03 frames. ], batch size: 6, lr: 1.06e-02
2024-08-06 16:07:24,234 INFO [trainer.py:765] (1/8) Epoch 8, batch 1400, train_loss[loss=3.425, NarTop10Accuracy=0.6314, over 5994.00 frames. ], tot_loss[loss=3.447, NarTop10Accuracy=0.6357, over 6011.16 frames. ], batch size: 11, lr: 1.05e-02
2024-08-06 16:07:52,168 INFO [trainer.py:765] (1/8) Epoch 8, batch 1500, train_loss[loss=3.398, NarTop10Accuracy=0.6525, over 6231.00 frames. ], tot_loss[loss=3.427, NarTop10Accuracy=0.6402, over 5954.22 frames. ], batch size: 50, lr: 1.05e-02
2024-08-06 16:08:19,948 INFO [trainer.py:765] (1/8) Epoch 8, batch 1600, train_loss[loss=3.24, NarTop10Accuracy=0.6776, over 6957.00 frames. ], tot_loss[loss=3.422, NarTop10Accuracy=0.6411, over 5930.53 frames. ], batch size: 22, lr: 1.05e-02
2024-08-06 16:08:46,617 INFO [trainer.py:765] (1/8) Epoch 8, batch 1700, train_loss[loss=3.247, NarTop10Accuracy=0.6727, over 6282.00 frames. ], tot_loss[loss=3.425, NarTop10Accuracy=0.6407, over 5907.85 frames. ], batch size: 13, lr: 1.05e-02
2024-08-06 16:09:13,105 INFO [trainer.py:765] (1/8) Epoch 8, batch 1800, train_loss[loss=3.252, NarTop10Accuracy=0.677, over 7209.00 frames. ], tot_loss[loss=3.414, NarTop10Accuracy=0.6427, over 5962.86 frames. ], batch size: 22, lr: 1.04e-02
2024-08-06 16:09:39,635 INFO [trainer.py:765] (1/8) Epoch 8, batch 1900, train_loss[loss=3.681, NarTop10Accuracy=0.5864, over 6495.00 frames. ], tot_loss[loss=3.411, NarTop10Accuracy=0.6436, over 6014.68 frames. ], batch size: 50, lr: 1.04e-02
2024-08-06 16:09:56,939 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 16:10:04,970 INFO [trainer.py:811] (1/8) Epoch 8, validation: loss=3.282, NarTop10Accuracy=0.6699, over 1905321.00 frames. 
2024-08-06 16:10:04,970 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 16:10:05,469 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.411e+02 1.814e+02 1.981e+02 2.158e+02 5.862e+02, threshold=3.962e+02, percent-clipped=0.1
2024-08-06 16:10:13,203 INFO [trainer.py:765] (1/8) Epoch 8, batch 2000, train_loss[loss=3.922, NarTop10Accuracy=0.5332, over 6243.00 frames. ], tot_loss[loss=3.416, NarTop10Accuracy=0.6421, over 5986.73 frames. ], batch size: 50, lr: 1.04e-02
2024-08-06 16:10:38,513 INFO [trainer.py:765] (1/8) Epoch 8, batch 2100, train_loss[loss=3.208, NarTop10Accuracy=0.6827, over 4014.00 frames. ], tot_loss[loss=3.406, NarTop10Accuracy=0.6443, over 5948.80 frames. ], batch size: 4, lr: 1.04e-02
2024-08-06 16:11:03,746 INFO [trainer.py:765] (1/8) Epoch 8, batch 2200, train_loss[loss=3.529, NarTop10Accuracy=0.6189, over 7368.00 frames. ], tot_loss[loss=3.422, NarTop10Accuracy=0.6413, over 6015.35 frames. ], batch size: 31, lr: 1.04e-02
2024-08-06 16:11:28,904 INFO [trainer.py:765] (1/8) Epoch 8, batch 2300, train_loss[loss=3.691, NarTop10Accuracy=0.5771, over 5745.00 frames. ], tot_loss[loss=3.439, NarTop10Accuracy=0.6376, over 6030.40 frames. ], batch size: 9, lr: 1.03e-02
2024-08-06 16:11:53,092 INFO [trainer.py:765] (1/8) Epoch 8, batch 2400, train_loss[loss=3.531, NarTop10Accuracy=0.6207, over 5628.00 frames. ], tot_loss[loss=3.425, NarTop10Accuracy=0.6404, over 5780.38 frames. ], batch size: 8, lr: 1.03e-02
2024-08-06 16:12:16,444 INFO [trainer.py:765] (1/8) Epoch 8, batch 2500, train_loss[loss=3.387, NarTop10Accuracy=0.6428, over 5010.00 frames. ], tot_loss[loss=3.416, NarTop10Accuracy=0.6421, over 5481.59 frames. ], batch size: 7, lr: 1.03e-02
2024-08-06 16:12:36,390 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 16:13:37,514 INFO [trainer.py:765] (1/8) Epoch 9, batch 100, train_loss[loss=3.164, NarTop10Accuracy=0.6948, over 7518.00 frames. ], tot_loss[loss=3.377, NarTop10Accuracy=0.651, over 2353.58 frames. ], batch size: 32, lr: 9.72e-03
2024-08-06 16:14:14,440 INFO [trainer.py:765] (1/8) Epoch 9, batch 200, train_loss[loss=3.681, NarTop10Accuracy=0.584, over 6714.00 frames. ], tot_loss[loss=3.37, NarTop10Accuracy=0.6524, over 3850.84 frames. ], batch size: 17, lr: 9.70e-03
2024-08-06 16:14:44,507 INFO [trainer.py:765] (1/8) Epoch 9, batch 300, train_loss[loss=3.388, NarTop10Accuracy=0.65, over 7182.00 frames. ], tot_loss[loss=3.381, NarTop10Accuracy=0.6496, over 4627.30 frames. ], batch size: 23, lr: 9.68e-03
2024-08-06 16:15:14,914 INFO [trainer.py:765] (1/8) Epoch 9, batch 400, train_loss[loss=3.133, NarTop10Accuracy=0.7052, over 5118.00 frames. ], tot_loss[loss=3.366, NarTop10Accuracy=0.6528, over 5084.01 frames. ], batch size: 7, lr: 9.65e-03
2024-08-06 16:15:50,336 INFO [trainer.py:765] (1/8) Epoch 9, batch 500, train_loss[loss=3.093, NarTop10Accuracy=0.7045, over 6126.00 frames. ], tot_loss[loss=3.354, NarTop10Accuracy=0.655, over 5356.33 frames. ], batch size: 11, lr: 9.63e-03
2024-08-06 16:16:23,972 INFO [trainer.py:765] (1/8) Epoch 9, batch 600, train_loss[loss=3.498, NarTop10Accuracy=0.6297, over 5520.00 frames. ], tot_loss[loss=3.344, NarTop10Accuracy=0.6573, over 5635.29 frames. ], batch size: 9, lr: 9.61e-03
2024-08-06 16:16:57,146 INFO [trainer.py:765] (1/8) Epoch 9, batch 700, train_loss[loss=3.212, NarTop10Accuracy=0.6791, over 4962.00 frames. ], tot_loss[loss=3.356, NarTop10Accuracy=0.6548, over 5701.42 frames. ], batch size: 6, lr: 9.59e-03
2024-08-06 16:17:32,051 INFO [trainer.py:765] (1/8) Epoch 9, batch 800, train_loss[loss=3.171, NarTop10Accuracy=0.698, over 4920.00 frames. ], tot_loss[loss=3.389, NarTop10Accuracy=0.6479, over 5759.41 frames. ], batch size: 6, lr: 9.57e-03
2024-08-06 16:18:07,815 INFO [trainer.py:765] (1/8) Epoch 9, batch 900, train_loss[loss=3.27, NarTop10Accuracy=0.6751, over 6672.00 frames. ], tot_loss[loss=3.382, NarTop10Accuracy=0.6491, over 5789.61 frames. ], batch size: 14, lr: 9.55e-03
2024-08-06 16:18:39,344 INFO [trainer.py:765] (1/8) Epoch 9, batch 1000, train_loss[loss=3.136, NarTop10Accuracy=0.6926, over 6231.00 frames. ], tot_loss[loss=3.4, NarTop10Accuracy=0.6456, over 5889.93 frames. ], batch size: 13, lr: 9.53e-03
2024-08-06 16:19:15,382 INFO [trainer.py:765] (1/8) Epoch 9, batch 1100, train_loss[loss=3.52, NarTop10Accuracy=0.6206, over 6855.00 frames. ], tot_loss[loss=3.396, NarTop10Accuracy=0.6462, over 5930.52 frames. ], batch size: 17, lr: 9.50e-03
2024-08-06 16:19:53,877 INFO [trainer.py:765] (1/8) Epoch 9, batch 1200, train_loss[loss=3.788, NarTop10Accuracy=0.5654, over 7419.00 frames. ], tot_loss[loss=3.406, NarTop10Accuracy=0.6444, over 5935.68 frames. ], batch size: 32, lr: 9.48e-03
2024-08-06 16:20:24,906 INFO [trainer.py:765] (1/8) Epoch 9, batch 1300, train_loss[loss=3.205, NarTop10Accuracy=0.674, over 5007.00 frames. ], tot_loss[loss=3.401, NarTop10Accuracy=0.6452, over 6002.64 frames. ], batch size: 6, lr: 9.46e-03
2024-08-06 16:20:56,579 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 16:21:04,483 INFO [trainer.py:811] (1/8) Epoch 9, validation: loss=3.266, NarTop10Accuracy=0.6725, over 1905321.00 frames. 
2024-08-06 16:21:04,484 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 16:21:05,035 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.473e+02 1.808e+02 1.967e+02 2.142e+02 6.126e+02, threshold=3.935e+02, percent-clipped=0.5
2024-08-06 16:21:06,691 INFO [trainer.py:765] (1/8) Epoch 9, batch 1400, train_loss[loss=3.557, NarTop10Accuracy=0.6095, over 6126.00 frames. ], tot_loss[loss=3.406, NarTop10Accuracy=0.644, over 6019.82 frames. ], batch size: 11, lr: 9.44e-03
2024-08-06 16:21:38,896 INFO [trainer.py:765] (1/8) Epoch 9, batch 1500, train_loss[loss=3.413, NarTop10Accuracy=0.6449, over 6402.00 frames. ], tot_loss[loss=3.378, NarTop10Accuracy=0.6501, over 5958.46 frames. ], batch size: 51, lr: 9.42e-03
2024-08-06 16:22:06,721 INFO [trainer.py:765] (1/8) Epoch 9, batch 1600, train_loss[loss=3.485, NarTop10Accuracy=0.6144, over 7287.00 frames. ], tot_loss[loss=3.374, NarTop10Accuracy=0.6509, over 5945.34 frames. ], batch size: 23, lr: 9.40e-03
2024-08-06 16:22:33,470 INFO [trainer.py:765] (1/8) Epoch 9, batch 1700, train_loss[loss=3.366, NarTop10Accuracy=0.6479, over 6660.00 frames. ], tot_loss[loss=3.391, NarTop10Accuracy=0.6474, over 5933.77 frames. ], batch size: 14, lr: 9.38e-03
2024-08-06 16:23:00,063 INFO [trainer.py:765] (1/8) Epoch 9, batch 1800, train_loss[loss=3.171, NarTop10Accuracy=0.697, over 7107.00 frames. ], tot_loss[loss=3.375, NarTop10Accuracy=0.6503, over 5982.72 frames. ], batch size: 22, lr: 9.36e-03
2024-08-06 16:23:26,782 INFO [trainer.py:765] (1/8) Epoch 9, batch 1900, train_loss[loss=3.329, NarTop10Accuracy=0.6645, over 5994.00 frames. ], tot_loss[loss=3.384, NarTop10Accuracy=0.6484, over 6022.73 frames. ], batch size: 50, lr: 9.34e-03
2024-08-06 16:23:52,485 INFO [trainer.py:765] (1/8) Epoch 9, batch 2000, train_loss[loss=3.886, NarTop10Accuracy=0.5414, over 5739.00 frames. ], tot_loss[loss=3.379, NarTop10Accuracy=0.6496, over 5972.24 frames. ], batch size: 50, lr: 9.32e-03
2024-08-06 16:24:17,962 INFO [trainer.py:765] (1/8) Epoch 9, batch 2100, train_loss[loss=3.105, NarTop10Accuracy=0.7065, over 4014.00 frames. ], tot_loss[loss=3.384, NarTop10Accuracy=0.6487, over 5956.90 frames. ], batch size: 4, lr: 9.30e-03
2024-08-06 16:24:43,421 INFO [trainer.py:765] (1/8) Epoch 9, batch 2200, train_loss[loss=3.635, NarTop10Accuracy=0.5943, over 7092.00 frames. ], tot_loss[loss=3.389, NarTop10Accuracy=0.6476, over 5994.87 frames. ], batch size: 31, lr: 9.28e-03
2024-08-06 16:25:08,721 INFO [trainer.py:765] (1/8) Epoch 9, batch 2300, train_loss[loss=3.385, NarTop10Accuracy=0.6484, over 5727.00 frames. ], tot_loss[loss=3.404, NarTop10Accuracy=0.6447, over 6032.79 frames. ], batch size: 9, lr: 9.26e-03
2024-08-06 16:25:33,164 INFO [trainer.py:765] (1/8) Epoch 9, batch 2400, train_loss[loss=3.318, NarTop10Accuracy=0.659, over 5139.00 frames. ], tot_loss[loss=3.4, NarTop10Accuracy=0.6455, over 5786.55 frames. ], batch size: 7, lr: 9.25e-03
2024-08-06 16:25:56,768 INFO [trainer.py:765] (1/8) Epoch 9, batch 2500, train_loss[loss=3.156, NarTop10Accuracy=0.6969, over 5250.00 frames. ], tot_loss[loss=3.358, NarTop10Accuracy=0.6537, over 5483.67 frames. ], batch size: 7, lr: 9.23e-03
2024-08-06 16:26:16,434 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 16:27:19,583 INFO [trainer.py:765] (1/8) Epoch 10, batch 100, train_loss[loss=3.325, NarTop10Accuracy=0.666, over 7575.00 frames. ], tot_loss[loss=3.378, NarTop10Accuracy=0.6492, over 2375.34 frames. ], batch size: 32, lr: 8.76e-03
2024-08-06 16:27:52,627 INFO [trainer.py:765] (1/8) Epoch 10, batch 200, train_loss[loss=2.999, NarTop10Accuracy=0.7327, over 6894.00 frames. ], tot_loss[loss=3.354, NarTop10Accuracy=0.6543, over 3855.59 frames. ], batch size: 17, lr: 8.74e-03
2024-08-06 16:28:23,056 INFO [trainer.py:765] (1/8) Epoch 10, batch 300, train_loss[loss=3.142, NarTop10Accuracy=0.7038, over 6864.00 frames. ], tot_loss[loss=3.353, NarTop10Accuracy=0.6546, over 4655.94 frames. ], batch size: 22, lr: 8.72e-03
2024-08-06 16:28:59,199 INFO [trainer.py:765] (1/8) Epoch 10, batch 400, train_loss[loss=3.279, NarTop10Accuracy=0.6744, over 5055.00 frames. ], tot_loss[loss=3.347, NarTop10Accuracy=0.6562, over 5103.85 frames. ], batch size: 7, lr: 8.71e-03
2024-08-06 16:29:29,217 INFO [trainer.py:765] (1/8) Epoch 10, batch 500, train_loss[loss=3.075, NarTop10Accuracy=0.7121, over 6126.00 frames. ], tot_loss[loss=3.341, NarTop10Accuracy=0.6578, over 5371.89 frames. ], batch size: 11, lr: 8.69e-03
2024-08-06 16:30:02,764 INFO [trainer.py:765] (1/8) Epoch 10, batch 600, train_loss[loss=3.541, NarTop10Accuracy=0.6196, over 5640.00 frames. ], tot_loss[loss=3.341, NarTop10Accuracy=0.6574, over 5640.01 frames. ], batch size: 9, lr: 8.67e-03
2024-08-06 16:30:34,264 INFO [trainer.py:765] (1/8) Epoch 10, batch 700, train_loss[loss=3.307, NarTop10Accuracy=0.6598, over 4326.00 frames. ], tot_loss[loss=3.35, NarTop10Accuracy=0.6557, over 5718.98 frames. ], batch size: 5, lr: 8.65e-03
2024-08-06 16:31:09,842 INFO [trainer.py:765] (1/8) Epoch 10, batch 800, train_loss[loss=3.529, NarTop10Accuracy=0.6213, over 5055.00 frames. ], tot_loss[loss=3.361, NarTop10Accuracy=0.6537, over 5782.66 frames. ], batch size: 6, lr: 8.64e-03
2024-08-06 16:31:16,256 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 16:31:24,565 INFO [trainer.py:811] (1/8) Epoch 10, validation: loss=3.184, NarTop10Accuracy=0.6898, over 1905321.00 frames. 
2024-08-06 16:31:24,566 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 16:31:25,154 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.434e+02 1.851e+02 2.012e+02 2.196e+02 4.599e+02, threshold=4.024e+02, percent-clipped=0.1
2024-08-06 16:31:50,345 INFO [trainer.py:765] (1/8) Epoch 10, batch 900, train_loss[loss=3.11, NarTop10Accuracy=0.7113, over 6378.00 frames. ], tot_loss[loss=3.331, NarTop10Accuracy=0.6598, over 5785.46 frames. ], batch size: 13, lr: 8.62e-03
2024-08-06 16:32:28,588 INFO [trainer.py:765] (1/8) Epoch 10, batch 1000, train_loss[loss=3.13, NarTop10Accuracy=0.7077, over 6141.00 frames. ], tot_loss[loss=3.337, NarTop10Accuracy=0.6585, over 5900.56 frames. ], batch size: 13, lr: 8.60e-03
2024-08-06 16:33:06,375 INFO [trainer.py:765] (1/8) Epoch 10, batch 1100, train_loss[loss=3.159, NarTop10Accuracy=0.7018, over 6798.00 frames. ], tot_loss[loss=3.343, NarTop10Accuracy=0.6573, over 5922.92 frames. ], batch size: 17, lr: 8.59e-03
2024-08-06 16:33:40,960 INFO [trainer.py:765] (1/8) Epoch 10, batch 1200, train_loss[loss=3.339, NarTop10Accuracy=0.6644, over 7458.00 frames. ], tot_loss[loss=3.342, NarTop10Accuracy=0.6574, over 5925.63 frames. ], batch size: 31, lr: 8.57e-03
2024-08-06 16:34:16,169 INFO [trainer.py:765] (1/8) Epoch 10, batch 1300, train_loss[loss=3.176, NarTop10Accuracy=0.681, over 5178.00 frames. ], tot_loss[loss=3.338, NarTop10Accuracy=0.6583, over 5999.31 frames. ], batch size: 6, lr: 8.55e-03
2024-08-06 16:34:51,200 INFO [trainer.py:765] (1/8) Epoch 10, batch 1400, train_loss[loss=3.4, NarTop10Accuracy=0.6499, over 6108.00 frames. ], tot_loss[loss=3.367, NarTop10Accuracy=0.6522, over 6022.66 frames. ], batch size: 11, lr: 8.54e-03
2024-08-06 16:35:22,158 INFO [trainer.py:765] (1/8) Epoch 10, batch 1500, train_loss[loss=3.624, NarTop10Accuracy=0.6046, over 6207.00 frames. ], tot_loss[loss=3.339, NarTop10Accuracy=0.658, over 5957.40 frames. ], batch size: 50, lr: 8.52e-03
2024-08-06 16:35:50,136 INFO [trainer.py:765] (1/8) Epoch 10, batch 1600, train_loss[loss=3.598, NarTop10Accuracy=0.6074, over 7212.00 frames. ], tot_loss[loss=3.329, NarTop10Accuracy=0.6601, over 5936.33 frames. ], batch size: 22, lr: 8.50e-03
2024-08-06 16:36:16,975 INFO [trainer.py:765] (1/8) Epoch 10, batch 1700, train_loss[loss=3.471, NarTop10Accuracy=0.6369, over 6342.00 frames. ], tot_loss[loss=3.343, NarTop10Accuracy=0.6571, over 5926.93 frames. ], batch size: 13, lr: 8.49e-03
2024-08-06 16:36:43,647 INFO [trainer.py:765] (1/8) Epoch 10, batch 1800, train_loss[loss=3.256, NarTop10Accuracy=0.6767, over 7206.00 frames. ], tot_loss[loss=3.33, NarTop10Accuracy=0.6596, over 5990.88 frames. ], batch size: 23, lr: 8.47e-03
2024-08-06 16:37:10,289 INFO [trainer.py:765] (1/8) Epoch 10, batch 1900, train_loss[loss=3.277, NarTop10Accuracy=0.6712, over 6051.00 frames. ], tot_loss[loss=3.33, NarTop10Accuracy=0.6601, over 6037.49 frames. ], batch size: 51, lr: 8.45e-03
2024-08-06 16:37:36,089 INFO [trainer.py:765] (1/8) Epoch 10, batch 2000, train_loss[loss=3.254, NarTop10Accuracy=0.6848, over 6348.00 frames. ], tot_loss[loss=3.329, NarTop10Accuracy=0.6602, over 6013.65 frames. ], batch size: 50, lr: 8.44e-03
2024-08-06 16:38:01,650 INFO [trainer.py:765] (1/8) Epoch 10, batch 2100, train_loss[loss=3.328, NarTop10Accuracy=0.6487, over 4851.00 frames. ], tot_loss[loss=3.347, NarTop10Accuracy=0.6566, over 5986.25 frames. ], batch size: 5, lr: 8.42e-03
2024-08-06 16:38:27,120 INFO [trainer.py:765] (1/8) Epoch 10, batch 2200, train_loss[loss=3.793, NarTop10Accuracy=0.5644, over 7050.00 frames. ], tot_loss[loss=3.35, NarTop10Accuracy=0.6558, over 6010.45 frames. ], batch size: 31, lr: 8.41e-03
2024-08-06 16:38:52,447 INFO [trainer.py:765] (1/8) Epoch 10, batch 2300, train_loss[loss=3.205, NarTop10Accuracy=0.6916, over 5628.00 frames. ], tot_loss[loss=3.358, NarTop10Accuracy=0.6544, over 6014.34 frames. ], batch size: 9, lr: 8.39e-03
2024-08-06 16:39:17,005 INFO [trainer.py:765] (1/8) Epoch 10, batch 2400, train_loss[loss=3.289, NarTop10Accuracy=0.6684, over 5211.00 frames. ], tot_loss[loss=3.327, NarTop10Accuracy=0.6605, over 5777.78 frames. ], batch size: 7, lr: 8.37e-03
2024-08-06 16:39:40,801 INFO [trainer.py:765] (1/8) Epoch 10, batch 2500, train_loss[loss=3.5, NarTop10Accuracy=0.6214, over 5151.00 frames. ], tot_loss[loss=3.301, NarTop10Accuracy=0.6658, over 5465.18 frames. ], batch size: 7, lr: 8.36e-03
2024-08-06 16:40:00,839 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 16:41:06,234 INFO [trainer.py:765] (1/8) Epoch 11, batch 100, train_loss[loss=3.593, NarTop10Accuracy=0.6093, over 7272.00 frames. ], tot_loss[loss=3.356, NarTop10Accuracy=0.6553, over 2361.87 frames. ], batch size: 31, lr: 7.97e-03
2024-08-06 16:41:39,020 INFO [trainer.py:765] (1/8) Epoch 11, batch 200, train_loss[loss=3.649, NarTop10Accuracy=0.5854, over 6897.00 frames. ], tot_loss[loss=3.338, NarTop10Accuracy=0.6586, over 3853.59 frames. ], batch size: 17, lr: 7.95e-03
2024-08-06 16:41:53,189 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 16:42:01,355 INFO [trainer.py:811] (1/8) Epoch 11, validation: loss=3.116, NarTop10Accuracy=0.7034, over 1905321.00 frames. 
2024-08-06 16:42:01,356 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 16:42:01,879 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.526e+02 1.889e+02 2.046e+02 2.249e+02 5.417e+02, threshold=4.093e+02, percent-clipped=0.2
2024-08-06 16:42:17,975 INFO [trainer.py:765] (1/8) Epoch 11, batch 300, train_loss[loss=3.073, NarTop10Accuracy=0.7081, over 7104.00 frames. ], tot_loss[loss=3.308, NarTop10Accuracy=0.6646, over 4655.64 frames. ], batch size: 22, lr: 7.94e-03
2024-08-06 16:42:55,154 INFO [trainer.py:765] (1/8) Epoch 11, batch 400, train_loss[loss=3.346, NarTop10Accuracy=0.6546, over 5226.00 frames. ], tot_loss[loss=3.298, NarTop10Accuracy=0.6657, over 5117.73 frames. ], batch size: 7, lr: 7.92e-03
2024-08-06 16:43:25,719 INFO [trainer.py:765] (1/8) Epoch 11, batch 500, train_loss[loss=3.06, NarTop10Accuracy=0.7167, over 6153.00 frames. ], tot_loss[loss=3.287, NarTop10Accuracy=0.6682, over 5389.60 frames. ], batch size: 11, lr: 7.91e-03
2024-08-06 16:44:02,242 INFO [trainer.py:765] (1/8) Epoch 11, batch 600, train_loss[loss=3.625, NarTop10Accuracy=0.5978, over 5685.00 frames. ], tot_loss[loss=3.297, NarTop10Accuracy=0.6662, over 5647.37 frames. ], batch size: 9, lr: 7.89e-03
2024-08-06 16:44:35,716 INFO [trainer.py:765] (1/8) Epoch 11, batch 700, train_loss[loss=3.56, NarTop10Accuracy=0.6041, over 4980.00 frames. ], tot_loss[loss=3.298, NarTop10Accuracy=0.6662, over 5708.29 frames. ], batch size: 6, lr: 7.88e-03
2024-08-06 16:45:10,468 INFO [trainer.py:765] (1/8) Epoch 11, batch 800, train_loss[loss=3.016, NarTop10Accuracy=0.7294, over 4986.00 frames. ], tot_loss[loss=3.307, NarTop10Accuracy=0.6641, over 5759.23 frames. ], batch size: 6, lr: 7.86e-03
2024-08-06 16:45:46,457 INFO [trainer.py:765] (1/8) Epoch 11, batch 900, train_loss[loss=3.531, NarTop10Accuracy=0.6127, over 6351.00 frames. ], tot_loss[loss=3.304, NarTop10Accuracy=0.6644, over 5784.54 frames. ], batch size: 13, lr: 7.85e-03
2024-08-06 16:46:20,311 INFO [trainer.py:765] (1/8) Epoch 11, batch 1000, train_loss[loss=3.318, NarTop10Accuracy=0.6599, over 6270.00 frames. ], tot_loss[loss=3.306, NarTop10Accuracy=0.6644, over 5882.70 frames. ], batch size: 13, lr: 7.84e-03
2024-08-06 16:46:53,456 INFO [trainer.py:765] (1/8) Epoch 11, batch 1100, train_loss[loss=3.075, NarTop10Accuracy=0.7152, over 6921.00 frames. ], tot_loss[loss=3.3, NarTop10Accuracy=0.6661, over 5889.58 frames. ], batch size: 17, lr: 7.82e-03
2024-08-06 16:47:33,030 INFO [trainer.py:765] (1/8) Epoch 11, batch 1200, train_loss[loss=3.43, NarTop10Accuracy=0.6398, over 7323.00 frames. ], tot_loss[loss=3.307, NarTop10Accuracy=0.6642, over 5918.35 frames. ], batch size: 31, lr: 7.81e-03
2024-08-06 16:48:06,482 INFO [trainer.py:765] (1/8) Epoch 11, batch 1300, train_loss[loss=3.101, NarTop10Accuracy=0.7111, over 5127.00 frames. ], tot_loss[loss=3.311, NarTop10Accuracy=0.6631, over 5983.10 frames. ], batch size: 6, lr: 7.79e-03
2024-08-06 16:48:41,356 INFO [trainer.py:765] (1/8) Epoch 11, batch 1400, train_loss[loss=3.429, NarTop10Accuracy=0.6382, over 6231.00 frames. ], tot_loss[loss=3.327, NarTop10Accuracy=0.6595, over 6003.59 frames. ], batch size: 11, lr: 7.78e-03
2024-08-06 16:49:09,344 INFO [trainer.py:765] (1/8) Epoch 11, batch 1500, train_loss[loss=3.213, NarTop10Accuracy=0.6838, over 5784.00 frames. ], tot_loss[loss=3.321, NarTop10Accuracy=0.6605, over 5943.35 frames. ], batch size: 50, lr: 7.77e-03
2024-08-06 16:49:37,103 INFO [trainer.py:765] (1/8) Epoch 11, batch 1600, train_loss[loss=3.306, NarTop10Accuracy=0.6588, over 7233.00 frames. ], tot_loss[loss=3.305, NarTop10Accuracy=0.6642, over 5906.35 frames. ], batch size: 22, lr: 7.75e-03
2024-08-06 16:50:03,792 INFO [trainer.py:765] (1/8) Epoch 11, batch 1700, train_loss[loss=3.376, NarTop10Accuracy=0.6382, over 6774.00 frames. ], tot_loss[loss=3.303, NarTop10Accuracy=0.6645, over 5914.30 frames. ], batch size: 14, lr: 7.74e-03
2024-08-06 16:50:30,352 INFO [trainer.py:765] (1/8) Epoch 11, batch 1800, train_loss[loss=3.317, NarTop10Accuracy=0.6616, over 6888.00 frames. ], tot_loss[loss=3.313, NarTop10Accuracy=0.6625, over 5978.58 frames. ], batch size: 22, lr: 7.72e-03
2024-08-06 16:50:56,821 INFO [trainer.py:765] (1/8) Epoch 11, batch 1900, train_loss[loss=3.838, NarTop10Accuracy=0.5612, over 5832.00 frames. ], tot_loss[loss=3.322, NarTop10Accuracy=0.6608, over 6012.19 frames. ], batch size: 50, lr: 7.71e-03
2024-08-06 16:51:22,404 INFO [trainer.py:765] (1/8) Epoch 11, batch 2000, train_loss[loss=3.944, NarTop10Accuracy=0.5317, over 5844.00 frames. ], tot_loss[loss=3.316, NarTop10Accuracy=0.6621, over 5994.67 frames. ], batch size: 50, lr: 7.70e-03
2024-08-06 16:51:47,794 INFO [trainer.py:765] (1/8) Epoch 11, batch 2100, train_loss[loss=2.96, NarTop10Accuracy=0.7239, over 4866.00 frames. ], tot_loss[loss=3.307, NarTop10Accuracy=0.6639, over 5979.62 frames. ], batch size: 5, lr: 7.68e-03
2024-08-06 16:52:13,118 INFO [trainer.py:765] (1/8) Epoch 11, batch 2200, train_loss[loss=3.28, NarTop10Accuracy=0.6728, over 7473.00 frames. ], tot_loss[loss=3.303, NarTop10Accuracy=0.6646, over 6017.56 frames. ], batch size: 32, lr: 7.67e-03
2024-08-06 16:52:23,898 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 16:52:32,079 INFO [trainer.py:811] (1/8) Epoch 11, validation: loss=3.101, NarTop10Accuracy=0.7058, over 1905321.00 frames. 
2024-08-06 16:52:32,080 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 16:52:32,593 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.491e+02 1.920e+02 2.088e+02 2.244e+02 3.599e+02, threshold=4.177e+02, percent-clipped=0.0
2024-08-06 16:52:46,445 INFO [trainer.py:765] (1/8) Epoch 11, batch 2300, train_loss[loss=3.168, NarTop10Accuracy=0.6956, over 5694.00 frames. ], tot_loss[loss=3.31, NarTop10Accuracy=0.6635, over 6008.73 frames. ], batch size: 9, lr: 7.66e-03
2024-08-06 16:53:10,887 INFO [trainer.py:765] (1/8) Epoch 11, batch 2400, train_loss[loss=3.484, NarTop10Accuracy=0.6263, over 5253.00 frames. ], tot_loss[loss=3.302, NarTop10Accuracy=0.6651, over 5764.12 frames. ], batch size: 7, lr: 7.64e-03
2024-08-06 16:53:34,371 INFO [trainer.py:765] (1/8) Epoch 11, batch 2500, train_loss[loss=3.653, NarTop10Accuracy=0.5834, over 5046.00 frames. ], tot_loss[loss=3.294, NarTop10Accuracy=0.6663, over 5480.73 frames. ], batch size: 7, lr: 7.63e-03
2024-08-06 16:53:54,404 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 16:54:58,524 INFO [trainer.py:765] (1/8) Epoch 12, batch 100, train_loss[loss=3.63, NarTop10Accuracy=0.5932, over 7413.00 frames. ], tot_loss[loss=3.298, NarTop10Accuracy=0.6662, over 2371.92 frames. ], batch size: 31, lr: 7.30e-03
2024-08-06 16:55:32,431 INFO [trainer.py:765] (1/8) Epoch 12, batch 200, train_loss[loss=3.195, NarTop10Accuracy=0.6852, over 6975.00 frames. ], tot_loss[loss=3.272, NarTop10Accuracy=0.6713, over 3864.48 frames. ], batch size: 17, lr: 7.29e-03
2024-08-06 16:56:05,095 INFO [trainer.py:765] (1/8) Epoch 12, batch 300, train_loss[loss=3.116, NarTop10Accuracy=0.709, over 6963.00 frames. ], tot_loss[loss=3.245, NarTop10Accuracy=0.6764, over 4655.60 frames. ], batch size: 22, lr: 7.27e-03
2024-08-06 16:56:36,425 INFO [trainer.py:765] (1/8) Epoch 12, batch 400, train_loss[loss=3.14, NarTop10Accuracy=0.7092, over 5103.00 frames. ], tot_loss[loss=3.261, NarTop10Accuracy=0.6741, over 5095.26 frames. ], batch size: 7, lr: 7.26e-03
2024-08-06 16:57:10,502 INFO [trainer.py:765] (1/8) Epoch 12, batch 500, train_loss[loss=3.563, NarTop10Accuracy=0.6086, over 6048.00 frames. ], tot_loss[loss=3.27, NarTop10Accuracy=0.6722, over 5374.91 frames. ], batch size: 11, lr: 7.25e-03
2024-08-06 16:57:45,482 INFO [trainer.py:765] (1/8) Epoch 12, batch 600, train_loss[loss=2.97, NarTop10Accuracy=0.7307, over 5694.00 frames. ], tot_loss[loss=3.275, NarTop10Accuracy=0.6712, over 5649.23 frames. ], batch size: 9, lr: 7.24e-03
2024-08-06 16:58:17,004 INFO [trainer.py:765] (1/8) Epoch 12, batch 700, train_loss[loss=3.541, NarTop10Accuracy=0.6147, over 5196.00 frames. ], tot_loss[loss=3.288, NarTop10Accuracy=0.6683, over 5716.45 frames. ], batch size: 6, lr: 7.22e-03
2024-08-06 16:58:53,468 INFO [trainer.py:765] (1/8) Epoch 12, batch 800, train_loss[loss=3.365, NarTop10Accuracy=0.6537, over 4308.00 frames. ], tot_loss[loss=3.291, NarTop10Accuracy=0.6676, over 5779.85 frames. ], batch size: 5, lr: 7.21e-03
2024-08-06 16:59:27,205 INFO [trainer.py:765] (1/8) Epoch 12, batch 900, train_loss[loss=3.137, NarTop10Accuracy=0.6972, over 6660.00 frames. ], tot_loss[loss=3.271, NarTop10Accuracy=0.6718, over 5792.80 frames. ], batch size: 14, lr: 7.20e-03
2024-08-06 17:00:01,573 INFO [trainer.py:765] (1/8) Epoch 12, batch 1000, train_loss[loss=2.988, NarTop10Accuracy=0.7309, over 6204.00 frames. ], tot_loss[loss=3.287, NarTop10Accuracy=0.6684, over 5894.14 frames. ], batch size: 13, lr: 7.19e-03
2024-08-06 17:00:39,188 INFO [trainer.py:765] (1/8) Epoch 12, batch 1100, train_loss[loss=3.632, NarTop10Accuracy=0.5964, over 6954.00 frames. ], tot_loss[loss=3.298, NarTop10Accuracy=0.6657, over 5927.51 frames. ], batch size: 17, lr: 7.18e-03
2024-08-06 17:01:13,963 INFO [trainer.py:765] (1/8) Epoch 12, batch 1200, train_loss[loss=3.162, NarTop10Accuracy=0.7001, over 7317.00 frames. ], tot_loss[loss=3.26, NarTop10Accuracy=0.6737, over 5933.76 frames. ], batch size: 31, lr: 7.17e-03
2024-08-06 17:01:48,107 INFO [trainer.py:765] (1/8) Epoch 12, batch 1300, train_loss[loss=3.202, NarTop10Accuracy=0.6923, over 4281.00 frames. ], tot_loss[loss=3.279, NarTop10Accuracy=0.6701, over 5996.81 frames. ], batch size: 5, lr: 7.15e-03
2024-08-06 17:02:22,322 INFO [trainer.py:765] (1/8) Epoch 12, batch 1400, train_loss[loss=3.479, NarTop10Accuracy=0.6256, over 6177.00 frames. ], tot_loss[loss=3.291, NarTop10Accuracy=0.6674, over 6015.08 frames. ], batch size: 11, lr: 7.14e-03
2024-08-06 17:02:52,876 INFO [trainer.py:765] (1/8) Epoch 12, batch 1500, train_loss[loss=3.411, NarTop10Accuracy=0.6422, over 5982.00 frames. ], tot_loss[loss=3.267, NarTop10Accuracy=0.6726, over 5967.32 frames. ], batch size: 50, lr: 7.13e-03
2024-08-06 17:03:20,690 INFO [trainer.py:765] (1/8) Epoch 12, batch 1600, train_loss[loss=3.23, NarTop10Accuracy=0.6801, over 7164.00 frames. ], tot_loss[loss=3.279, NarTop10Accuracy=0.67, over 5926.68 frames. ], batch size: 22, lr: 7.12e-03
2024-08-06 17:03:38,296 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 17:03:46,474 INFO [trainer.py:811] (1/8) Epoch 12, validation: loss=3.054, NarTop10Accuracy=0.7153, over 1905321.00 frames. 
2024-08-06 17:03:46,475 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 17:03:46,988 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.507e+02 1.899e+02 2.078e+02 2.276e+02 5.455e+02, threshold=4.157e+02, percent-clipped=0.1
2024-08-06 17:03:55,604 INFO [trainer.py:765] (1/8) Epoch 12, batch 1700, train_loss[loss=3.251, NarTop10Accuracy=0.6712, over 6678.00 frames. ], tot_loss[loss=3.283, NarTop10Accuracy=0.6689, over 5909.22 frames. ], batch size: 14, lr: 7.11e-03
2024-08-06 17:04:22,121 INFO [trainer.py:765] (1/8) Epoch 12, batch 1800, train_loss[loss=3.664, NarTop10Accuracy=0.5906, over 7416.00 frames. ], tot_loss[loss=3.287, NarTop10Accuracy=0.6684, over 5979.99 frames. ], batch size: 23, lr: 7.10e-03
2024-08-06 17:04:48,591 INFO [trainer.py:765] (1/8) Epoch 12, batch 1900, train_loss[loss=3.258, NarTop10Accuracy=0.6769, over 6306.00 frames. ], tot_loss[loss=3.278, NarTop10Accuracy=0.6706, over 6030.31 frames. ], batch size: 52, lr: 7.08e-03
2024-08-06 17:05:14,198 INFO [trainer.py:765] (1/8) Epoch 12, batch 2000, train_loss[loss=3.543, NarTop10Accuracy=0.6148, over 5364.00 frames. ], tot_loss[loss=3.269, NarTop10Accuracy=0.6728, over 6002.12 frames. ], batch size: 50, lr: 7.07e-03
2024-08-06 17:05:39,468 INFO [trainer.py:765] (1/8) Epoch 12, batch 2100, train_loss[loss=3.386, NarTop10Accuracy=0.652, over 3900.00 frames. ], tot_loss[loss=3.274, NarTop10Accuracy=0.6717, over 5968.27 frames. ], batch size: 4, lr: 7.06e-03
2024-08-06 17:06:04,691 INFO [trainer.py:765] (1/8) Epoch 12, batch 2200, train_loss[loss=3.558, NarTop10Accuracy=0.6142, over 7203.00 frames. ], tot_loss[loss=3.291, NarTop10Accuracy=0.6679, over 5991.19 frames. ], batch size: 31, lr: 7.05e-03
2024-08-06 17:06:29,847 INFO [trainer.py:765] (1/8) Epoch 12, batch 2300, train_loss[loss=3.496, NarTop10Accuracy=0.6185, over 5631.00 frames. ], tot_loss[loss=3.286, NarTop10Accuracy=0.6688, over 6010.09 frames. ], batch size: 9, lr: 7.04e-03
2024-08-06 17:06:54,200 INFO [trainer.py:765] (1/8) Epoch 12, batch 2400, train_loss[loss=3.33, NarTop10Accuracy=0.6618, over 5250.00 frames. ], tot_loss[loss=3.272, NarTop10Accuracy=0.6711, over 5782.81 frames. ], batch size: 7, lr: 7.03e-03
2024-08-06 17:07:17,646 INFO [trainer.py:765] (1/8) Epoch 12, batch 2500, train_loss[loss=3.281, NarTop10Accuracy=0.6653, over 5106.00 frames. ], tot_loss[loss=3.259, NarTop10Accuracy=0.6733, over 5465.81 frames. ], batch size: 7, lr: 7.02e-03
2024-08-06 17:07:37,701 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 17:08:40,078 INFO [trainer.py:765] (1/8) Epoch 13, batch 100, train_loss[loss=3.072, NarTop10Accuracy=0.7097, over 7296.00 frames. ], tot_loss[loss=3.288, NarTop10Accuracy=0.6676, over 2364.01 frames. ], batch size: 31, lr: 6.73e-03
2024-08-06 17:09:14,119 INFO [trainer.py:765] (1/8) Epoch 13, batch 200, train_loss[loss=3.01, NarTop10Accuracy=0.7333, over 6741.00 frames. ], tot_loss[loss=3.287, NarTop10Accuracy=0.6686, over 3855.06 frames. ], batch size: 17, lr: 6.72e-03
2024-08-06 17:09:46,275 INFO [trainer.py:765] (1/8) Epoch 13, batch 300, train_loss[loss=3.569, NarTop10Accuracy=0.6014, over 7038.00 frames. ], tot_loss[loss=3.267, NarTop10Accuracy=0.6724, over 4649.41 frames. ], batch size: 22, lr: 6.71e-03
2024-08-06 17:10:19,162 INFO [trainer.py:765] (1/8) Epoch 13, batch 400, train_loss[loss=2.977, NarTop10Accuracy=0.7303, over 5169.00 frames. ], tot_loss[loss=3.244, NarTop10Accuracy=0.6771, over 5120.46 frames. ], batch size: 7, lr: 6.70e-03
2024-08-06 17:10:49,334 INFO [trainer.py:765] (1/8) Epoch 13, batch 500, train_loss[loss=3.168, NarTop10Accuracy=0.6849, over 6069.00 frames. ], tot_loss[loss=3.237, NarTop10Accuracy=0.6788, over 5401.69 frames. ], batch size: 11, lr: 6.69e-03
2024-08-06 17:11:26,243 INFO [trainer.py:765] (1/8) Epoch 13, batch 600, train_loss[loss=3.01, NarTop10Accuracy=0.7236, over 5718.00 frames. ], tot_loss[loss=3.228, NarTop10Accuracy=0.6806, over 5664.18 frames. ], batch size: 9, lr: 6.68e-03
2024-08-06 17:11:57,381 INFO [trainer.py:765] (1/8) Epoch 13, batch 700, train_loss[loss=3.095, NarTop10Accuracy=0.7042, over 5211.00 frames. ], tot_loss[loss=3.235, NarTop10Accuracy=0.6788, over 5727.10 frames. ], batch size: 6, lr: 6.67e-03
2024-08-06 17:12:33,441 INFO [trainer.py:765] (1/8) Epoch 13, batch 800, train_loss[loss=2.972, NarTop10Accuracy=0.7368, over 5127.00 frames. ], tot_loss[loss=3.247, NarTop10Accuracy=0.676, over 5793.48 frames. ], batch size: 6, lr: 6.66e-03
2024-08-06 17:13:10,030 INFO [trainer.py:765] (1/8) Epoch 13, batch 900, train_loss[loss=3.199, NarTop10Accuracy=0.6902, over 6528.00 frames. ], tot_loss[loss=3.237, NarTop10Accuracy=0.6783, over 5807.22 frames. ], batch size: 14, lr: 6.65e-03
2024-08-06 17:13:41,442 INFO [trainer.py:765] (1/8) Epoch 13, batch 1000, train_loss[loss=3.55, NarTop10Accuracy=0.6111, over 6672.00 frames. ], tot_loss[loss=3.247, NarTop10Accuracy=0.6765, over 5896.95 frames. ], batch size: 14, lr: 6.64e-03
2024-08-06 17:14:15,536 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 17:14:23,644 INFO [trainer.py:811] (1/8) Epoch 13, validation: loss=3.099, NarTop10Accuracy=0.7062, over 1905321.00 frames. 
2024-08-06 17:14:23,645 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 17:14:24,471 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.548e+02 1.948e+02 2.091e+02 2.295e+02 3.353e+02, threshold=4.181e+02, percent-clipped=0.0
2024-08-06 17:14:26,696 INFO [trainer.py:765] (1/8) Epoch 13, batch 1100, train_loss[loss=3.439, NarTop10Accuracy=0.6359, over 6711.00 frames. ], tot_loss[loss=3.255, NarTop10Accuracy=0.6749, over 5933.24 frames. ], batch size: 17, lr: 6.63e-03
2024-08-06 17:15:03,474 INFO [trainer.py:765] (1/8) Epoch 13, batch 1200, train_loss[loss=3.397, NarTop10Accuracy=0.6512, over 7206.00 frames. ], tot_loss[loss=3.255, NarTop10Accuracy=0.6748, over 5938.95 frames. ], batch size: 31, lr: 6.62e-03
2024-08-06 17:15:35,513 INFO [trainer.py:765] (1/8) Epoch 13, batch 1300, train_loss[loss=2.753, NarTop10Accuracy=0.768, over 4980.00 frames. ], tot_loss[loss=3.254, NarTop10Accuracy=0.6749, over 5997.70 frames. ], batch size: 6, lr: 6.61e-03
2024-08-06 17:16:11,782 INFO [trainer.py:765] (1/8) Epoch 13, batch 1400, train_loss[loss=3.156, NarTop10Accuracy=0.6866, over 6180.00 frames. ], tot_loss[loss=3.259, NarTop10Accuracy=0.6739, over 6024.07 frames. ], batch size: 11, lr: 6.60e-03
2024-08-06 17:16:39,787 INFO [trainer.py:765] (1/8) Epoch 13, batch 1500, train_loss[loss=3.53, NarTop10Accuracy=0.617, over 5760.00 frames. ], tot_loss[loss=3.252, NarTop10Accuracy=0.6749, over 5948.28 frames. ], batch size: 50, lr: 6.59e-03
2024-08-06 17:17:07,602 INFO [trainer.py:765] (1/8) Epoch 13, batch 1600, train_loss[loss=2.942, NarTop10Accuracy=0.7379, over 7164.00 frames. ], tot_loss[loss=3.259, NarTop10Accuracy=0.6736, over 5930.97 frames. ], batch size: 22, lr: 6.58e-03
2024-08-06 17:17:34,258 INFO [trainer.py:765] (1/8) Epoch 13, batch 1700, train_loss[loss=3.214, NarTop10Accuracy=0.6813, over 6285.00 frames. ], tot_loss[loss=3.257, NarTop10Accuracy=0.6739, over 5917.87 frames. ], batch size: 13, lr: 6.57e-03
2024-08-06 17:18:00,761 INFO [trainer.py:765] (1/8) Epoch 13, batch 1800, train_loss[loss=3.084, NarTop10Accuracy=0.7037, over 7131.00 frames. ], tot_loss[loss=3.249, NarTop10Accuracy=0.6759, over 5987.25 frames. ], batch size: 22, lr: 6.56e-03
2024-08-06 17:18:27,243 INFO [trainer.py:765] (1/8) Epoch 13, batch 1900, train_loss[loss=3.463, NarTop10Accuracy=0.6329, over 5838.00 frames. ], tot_loss[loss=3.251, NarTop10Accuracy=0.6754, over 6031.57 frames. ], batch size: 50, lr: 6.55e-03
2024-08-06 17:18:52,776 INFO [trainer.py:765] (1/8) Epoch 13, batch 2000, train_loss[loss=3.533, NarTop10Accuracy=0.6199, over 6048.00 frames. ], tot_loss[loss=3.239, NarTop10Accuracy=0.6782, over 5994.36 frames. ], batch size: 50, lr: 6.54e-03
2024-08-06 17:19:18,147 INFO [trainer.py:765] (1/8) Epoch 13, batch 2100, train_loss[loss=2.944, NarTop10Accuracy=0.7397, over 4710.00 frames. ], tot_loss[loss=3.241, NarTop10Accuracy=0.6779, over 5966.51 frames. ], batch size: 5, lr: 6.53e-03
2024-08-06 17:19:43,411 INFO [trainer.py:765] (1/8) Epoch 13, batch 2200, train_loss[loss=3.434, NarTop10Accuracy=0.638, over 7269.00 frames. ], tot_loss[loss=3.247, NarTop10Accuracy=0.6766, over 5981.88 frames. ], batch size: 31, lr: 6.52e-03
2024-08-06 17:20:08,542 INFO [trainer.py:765] (1/8) Epoch 13, batch 2300, train_loss[loss=3.66, NarTop10Accuracy=0.5997, over 5745.00 frames. ], tot_loss[loss=3.263, NarTop10Accuracy=0.6731, over 6012.22 frames. ], batch size: 9, lr: 6.51e-03
2024-08-06 17:20:32,939 INFO [trainer.py:765] (1/8) Epoch 13, batch 2400, train_loss[loss=3.579, NarTop10Accuracy=0.6069, over 5097.00 frames. ], tot_loss[loss=3.231, NarTop10Accuracy=0.6796, over 5789.69 frames. ], batch size: 7, lr: 6.50e-03
2024-08-06 17:20:56,408 INFO [trainer.py:765] (1/8) Epoch 13, batch 2500, train_loss[loss=3.542, NarTop10Accuracy=0.6096, over 5130.00 frames. ], tot_loss[loss=3.218, NarTop10Accuracy=0.682, over 5485.03 frames. ], batch size: 7, lr: 6.49e-03
2024-08-06 17:21:16,341 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 17:22:19,315 INFO [trainer.py:765] (1/8) Epoch 14, batch 100, train_loss[loss=3.017, NarTop10Accuracy=0.7295, over 7179.00 frames. ], tot_loss[loss=3.225, NarTop10Accuracy=0.6821, over 2354.25 frames. ], batch size: 31, lr: 6.24e-03
2024-08-06 17:22:50,379 INFO [trainer.py:765] (1/8) Epoch 14, batch 200, train_loss[loss=3.16, NarTop10Accuracy=0.7008, over 6843.00 frames. ], tot_loss[loss=3.229, NarTop10Accuracy=0.681, over 3859.07 frames. ], batch size: 17, lr: 6.23e-03
2024-08-06 17:23:23,880 INFO [trainer.py:765] (1/8) Epoch 14, batch 300, train_loss[loss=3.01, NarTop10Accuracy=0.7253, over 7047.00 frames. ], tot_loss[loss=3.205, NarTop10Accuracy=0.6857, over 4665.20 frames. ], batch size: 22, lr: 6.22e-03
2024-08-06 17:23:57,485 INFO [trainer.py:765] (1/8) Epoch 14, batch 400, train_loss[loss=2.913, NarTop10Accuracy=0.7504, over 5310.00 frames. ], tot_loss[loss=3.221, NarTop10Accuracy=0.682, over 5130.13 frames. ], batch size: 7, lr: 6.22e-03
2024-08-06 17:24:32,114 INFO [trainer.py:765] (1/8) Epoch 14, batch 500, train_loss[loss=3.221, NarTop10Accuracy=0.6801, over 6138.00 frames. ], tot_loss[loss=3.232, NarTop10Accuracy=0.6796, over 5412.28 frames. ], batch size: 11, lr: 6.21e-03
2024-08-06 17:24:36,213 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 17:24:44,275 INFO [trainer.py:811] (1/8) Epoch 14, validation: loss=3.004, NarTop10Accuracy=0.726, over 1905321.00 frames. 
2024-08-06 17:24:44,276 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 17:24:44,822 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.601e+02 1.969e+02 2.114e+02 2.287e+02 4.406e+02, threshold=4.227e+02, percent-clipped=0.1
2024-08-06 17:25:12,913 INFO [trainer.py:765] (1/8) Epoch 14, batch 600, train_loss[loss=2.903, NarTop10Accuracy=0.7441, over 5820.00 frames. ], tot_loss[loss=3.231, NarTop10Accuracy=0.6794, over 5659.32 frames. ], batch size: 9, lr: 6.20e-03
2024-08-06 17:25:48,547 INFO [trainer.py:765] (1/8) Epoch 14, batch 700, train_loss[loss=3.329, NarTop10Accuracy=0.6639, over 4338.00 frames. ], tot_loss[loss=3.22, NarTop10Accuracy=0.6817, over 5726.36 frames. ], batch size: 5, lr: 6.19e-03
2024-08-06 17:26:25,278 INFO [trainer.py:765] (1/8) Epoch 14, batch 800, train_loss[loss=2.804, NarTop10Accuracy=0.7605, over 5025.00 frames. ], tot_loss[loss=3.217, NarTop10Accuracy=0.6826, over 5787.83 frames. ], batch size: 6, lr: 6.18e-03
2024-08-06 17:26:57,658 INFO [trainer.py:765] (1/8) Epoch 14, batch 900, train_loss[loss=3.246, NarTop10Accuracy=0.6775, over 6192.00 frames. ], tot_loss[loss=3.207, NarTop10Accuracy=0.6843, over 5795.53 frames. ], batch size: 13, lr: 6.17e-03
2024-08-06 17:27:31,716 INFO [trainer.py:765] (1/8) Epoch 14, batch 1000, train_loss[loss=3.485, NarTop10Accuracy=0.638, over 6723.00 frames. ], tot_loss[loss=3.226, NarTop10Accuracy=0.6803, over 5900.30 frames. ], batch size: 14, lr: 6.16e-03
2024-08-06 17:28:11,596 INFO [trainer.py:765] (1/8) Epoch 14, batch 1100, train_loss[loss=3.006, NarTop10Accuracy=0.7303, over 6960.00 frames. ], tot_loss[loss=3.225, NarTop10Accuracy=0.6806, over 5924.91 frames. ], batch size: 17, lr: 6.15e-03
2024-08-06 17:28:40,732 INFO [trainer.py:765] (1/8) Epoch 14, batch 1200, train_loss[loss=3.433, NarTop10Accuracy=0.6351, over 7140.00 frames. ], tot_loss[loss=3.222, NarTop10Accuracy=0.6815, over 5925.45 frames. ], batch size: 31, lr: 6.15e-03
2024-08-06 17:29:16,213 INFO [trainer.py:765] (1/8) Epoch 14, batch 1300, train_loss[loss=3.382, NarTop10Accuracy=0.651, over 4278.00 frames. ], tot_loss[loss=3.224, NarTop10Accuracy=0.6809, over 5989.89 frames. ], batch size: 5, lr: 6.14e-03
2024-08-06 17:29:54,601 INFO [trainer.py:765] (1/8) Epoch 14, batch 1400, train_loss[loss=3.546, NarTop10Accuracy=0.6247, over 6066.00 frames. ], tot_loss[loss=3.231, NarTop10Accuracy=0.6795, over 6006.17 frames. ], batch size: 11, lr: 6.13e-03
2024-08-06 17:30:25,314 INFO [trainer.py:765] (1/8) Epoch 14, batch 1500, train_loss[loss=3.772, NarTop10Accuracy=0.574, over 6429.00 frames. ], tot_loss[loss=3.238, NarTop10Accuracy=0.6782, over 5946.50 frames. ], batch size: 50, lr: 6.12e-03
2024-08-06 17:30:53,042 INFO [trainer.py:765] (1/8) Epoch 14, batch 1600, train_loss[loss=2.901, NarTop10Accuracy=0.7509, over 6876.00 frames. ], tot_loss[loss=3.228, NarTop10Accuracy=0.6807, over 5945.92 frames. ], batch size: 22, lr: 6.11e-03
2024-08-06 17:31:19,727 INFO [trainer.py:765] (1/8) Epoch 14, batch 1700, train_loss[loss=3.073, NarTop10Accuracy=0.7175, over 6591.00 frames. ], tot_loss[loss=3.206, NarTop10Accuracy=0.6851, over 5928.04 frames. ], batch size: 14, lr: 6.10e-03
2024-08-06 17:31:46,288 INFO [trainer.py:765] (1/8) Epoch 14, batch 1800, train_loss[loss=3.001, NarTop10Accuracy=0.7314, over 7092.00 frames. ], tot_loss[loss=3.189, NarTop10Accuracy=0.6884, over 5995.16 frames. ], batch size: 22, lr: 6.09e-03
2024-08-06 17:32:12,727 INFO [trainer.py:765] (1/8) Epoch 14, batch 1900, train_loss[loss=3.655, NarTop10Accuracy=0.5896, over 6495.00 frames. ], tot_loss[loss=3.207, NarTop10Accuracy=0.685, over 6036.35 frames. ], batch size: 51, lr: 6.09e-03
2024-08-06 17:32:38,282 INFO [trainer.py:765] (1/8) Epoch 14, batch 2000, train_loss[loss=3.163, NarTop10Accuracy=0.6933, over 5760.00 frames. ], tot_loss[loss=3.209, NarTop10Accuracy=0.6843, over 6006.30 frames. ], batch size: 50, lr: 6.08e-03
2024-08-06 17:33:03,645 INFO [trainer.py:765] (1/8) Epoch 14, batch 2100, train_loss[loss=3.124, NarTop10Accuracy=0.7017, over 4839.00 frames. ], tot_loss[loss=3.213, NarTop10Accuracy=0.6835, over 5993.62 frames. ], batch size: 5, lr: 6.07e-03
2024-08-06 17:33:28,998 INFO [trainer.py:765] (1/8) Epoch 14, batch 2200, train_loss[loss=3.386, NarTop10Accuracy=0.6595, over 7281.00 frames. ], tot_loss[loss=3.215, NarTop10Accuracy=0.6836, over 6030.24 frames. ], batch size: 31, lr: 6.06e-03
2024-08-06 17:33:54,086 INFO [trainer.py:765] (1/8) Epoch 14, batch 2300, train_loss[loss=2.917, NarTop10Accuracy=0.7538, over 5667.00 frames. ], tot_loss[loss=3.231, NarTop10Accuracy=0.6801, over 6031.36 frames. ], batch size: 9, lr: 6.05e-03
2024-08-06 17:34:18,534 INFO [trainer.py:765] (1/8) Epoch 14, batch 2400, train_loss[loss=2.984, NarTop10Accuracy=0.736, over 5193.00 frames. ], tot_loss[loss=3.23, NarTop10Accuracy=0.6802, over 5788.98 frames. ], batch size: 7, lr: 6.04e-03
2024-08-06 17:34:42,116 INFO [trainer.py:765] (1/8) Epoch 14, batch 2500, train_loss[loss=2.971, NarTop10Accuracy=0.7358, over 5046.00 frames. ], tot_loss[loss=3.199, NarTop10Accuracy=0.6861, over 5482.29 frames. ], batch size: 7, lr: 6.04e-03
2024-08-06 17:34:45,394 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 17:34:53,209 INFO [trainer.py:811] (1/8) Epoch 14, validation: loss=3.062, NarTop10Accuracy=0.7136, over 1905321.00 frames. 
2024-08-06 17:34:53,209 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 17:34:53,679 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.574e+02 1.975e+02 2.132e+02 2.304e+02 3.875e+02, threshold=4.265e+02, percent-clipped=0.0
2024-08-06 17:35:09,873 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 17:36:11,738 INFO [trainer.py:765] (1/8) Epoch 15, batch 100, train_loss[loss=3.074, NarTop10Accuracy=0.7111, over 7344.00 frames. ], tot_loss[loss=3.218, NarTop10Accuracy=0.6821, over 2387.57 frames. ], batch size: 31, lr: 5.82e-03
2024-08-06 17:36:44,334 INFO [trainer.py:765] (1/8) Epoch 15, batch 200, train_loss[loss=3.423, NarTop10Accuracy=0.6349, over 6726.00 frames. ], tot_loss[loss=3.194, NarTop10Accuracy=0.6873, over 3876.23 frames. ], batch size: 17, lr: 5.81e-03
2024-08-06 17:37:17,714 INFO [trainer.py:765] (1/8) Epoch 15, batch 300, train_loss[loss=3.325, NarTop10Accuracy=0.6655, over 7131.00 frames. ], tot_loss[loss=3.201, NarTop10Accuracy=0.6861, over 4678.81 frames. ], batch size: 22, lr: 5.80e-03
2024-08-06 17:37:48,903 INFO [trainer.py:765] (1/8) Epoch 15, batch 400, train_loss[loss=2.877, NarTop10Accuracy=0.7488, over 5058.00 frames. ], tot_loss[loss=3.192, NarTop10Accuracy=0.6877, over 5130.09 frames. ], batch size: 7, lr: 5.80e-03
2024-08-06 17:38:22,353 INFO [trainer.py:765] (1/8) Epoch 15, batch 500, train_loss[loss=2.837, NarTop10Accuracy=0.7591, over 6042.00 frames. ], tot_loss[loss=3.189, NarTop10Accuracy=0.688, over 5397.69 frames. ], batch size: 11, lr: 5.79e-03
2024-08-06 17:38:53,093 INFO [trainer.py:765] (1/8) Epoch 15, batch 600, train_loss[loss=3.025, NarTop10Accuracy=0.736, over 5787.00 frames. ], tot_loss[loss=3.201, NarTop10Accuracy=0.6854, over 5662.99 frames. ], batch size: 9, lr: 5.78e-03
2024-08-06 17:39:27,922 INFO [trainer.py:765] (1/8) Epoch 15, batch 700, train_loss[loss=2.9, NarTop10Accuracy=0.7522, over 5043.00 frames. ], tot_loss[loss=3.204, NarTop10Accuracy=0.6851, over 5741.94 frames. ], batch size: 6, lr: 5.77e-03
2024-08-06 17:40:05,564 INFO [trainer.py:765] (1/8) Epoch 15, batch 800, train_loss[loss=3.265, NarTop10Accuracy=0.6675, over 5124.00 frames. ], tot_loss[loss=3.226, NarTop10Accuracy=0.6809, over 5805.10 frames. ], batch size: 6, lr: 5.76e-03
2024-08-06 17:40:35,790 INFO [trainer.py:765] (1/8) Epoch 15, batch 900, train_loss[loss=3.512, NarTop10Accuracy=0.6159, over 6243.00 frames. ], tot_loss[loss=3.207, NarTop10Accuracy=0.6847, over 5815.91 frames. ], batch size: 13, lr: 5.76e-03
2024-08-06 17:41:11,250 INFO [trainer.py:765] (1/8) Epoch 15, batch 1000, train_loss[loss=3.097, NarTop10Accuracy=0.7097, over 6711.00 frames. ], tot_loss[loss=3.192, NarTop10Accuracy=0.6877, over 5908.52 frames. ], batch size: 14, lr: 5.75e-03
2024-08-06 17:41:46,451 INFO [trainer.py:765] (1/8) Epoch 15, batch 1100, train_loss[loss=3.14, NarTop10Accuracy=0.6997, over 6789.00 frames. ], tot_loss[loss=3.194, NarTop10Accuracy=0.6873, over 5942.56 frames. ], batch size: 17, lr: 5.74e-03
2024-08-06 17:42:19,456 INFO [trainer.py:765] (1/8) Epoch 15, batch 1200, train_loss[loss=3.411, NarTop10Accuracy=0.6456, over 7470.00 frames. ], tot_loss[loss=3.222, NarTop10Accuracy=0.6809, over 5940.40 frames. ], batch size: 32, lr: 5.73e-03
2024-08-06 17:42:54,427 INFO [trainer.py:765] (1/8) Epoch 15, batch 1300, train_loss[loss=2.769, NarTop10Accuracy=0.7623, over 5082.00 frames. ], tot_loss[loss=3.203, NarTop10Accuracy=0.6849, over 6004.55 frames. ], batch size: 6, lr: 5.73e-03
2024-08-06 17:43:26,607 INFO [trainer.py:765] (1/8) Epoch 15, batch 1400, train_loss[loss=3.445, NarTop10Accuracy=0.6432, over 6246.00 frames. ], tot_loss[loss=3.216, NarTop10Accuracy=0.6823, over 6052.40 frames. ], batch size: 11, lr: 5.72e-03
2024-08-06 17:43:56,557 INFO [trainer.py:765] (1/8) Epoch 15, batch 1500, train_loss[loss=3.133, NarTop10Accuracy=0.7028, over 5895.00 frames. ], tot_loss[loss=3.222, NarTop10Accuracy=0.681, over 5958.59 frames. ], batch size: 51, lr: 5.71e-03
2024-08-06 17:44:24,241 INFO [trainer.py:765] (1/8) Epoch 15, batch 1600, train_loss[loss=3.493, NarTop10Accuracy=0.6128, over 7035.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6864, over 5916.91 frames. ], batch size: 22, lr: 5.70e-03
2024-08-06 17:44:50,855 INFO [trainer.py:765] (1/8) Epoch 15, batch 1700, train_loss[loss=3.107, NarTop10Accuracy=0.7083, over 6240.00 frames. ], tot_loss[loss=3.184, NarTop10Accuracy=0.6892, over 5918.92 frames. ], batch size: 13, lr: 5.70e-03
2024-08-06 17:45:17,293 INFO [trainer.py:765] (1/8) Epoch 15, batch 1800, train_loss[loss=3.226, NarTop10Accuracy=0.6794, over 7089.00 frames. ], tot_loss[loss=3.189, NarTop10Accuracy=0.6885, over 5986.19 frames. ], batch size: 22, lr: 5.69e-03
2024-08-06 17:45:43,678 INFO [trainer.py:765] (1/8) Epoch 15, batch 1900, train_loss[loss=3.093, NarTop10Accuracy=0.7051, over 6411.00 frames. ], tot_loss[loss=3.213, NarTop10Accuracy=0.6836, over 6020.29 frames. ], batch size: 51, lr: 5.68e-03
2024-08-06 17:45:53,539 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 17:46:01,742 INFO [trainer.py:811] (1/8) Epoch 15, validation: loss=3.006, NarTop10Accuracy=0.725, over 1905321.00 frames. 
2024-08-06 17:46:01,743 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 17:46:02,216 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.631e+02 2.004e+02 2.149e+02 2.324e+02 3.721e+02, threshold=4.298e+02, percent-clipped=0.0
2024-08-06 17:46:17,371 INFO [trainer.py:765] (1/8) Epoch 15, batch 2000, train_loss[loss=3.229, NarTop10Accuracy=0.6848, over 6093.00 frames. ], tot_loss[loss=3.205, NarTop10Accuracy=0.685, over 6008.38 frames. ], batch size: 50, lr: 5.67e-03
2024-08-06 17:46:42,773 INFO [trainer.py:765] (1/8) Epoch 15, batch 2100, train_loss[loss=3.102, NarTop10Accuracy=0.6973, over 4032.00 frames. ], tot_loss[loss=3.201, NarTop10Accuracy=0.6856, over 5990.29 frames. ], batch size: 4, lr: 5.67e-03
2024-08-06 17:47:08,033 INFO [trainer.py:765] (1/8) Epoch 15, batch 2200, train_loss[loss=3.023, NarTop10Accuracy=0.716, over 7311.00 frames. ], tot_loss[loss=3.206, NarTop10Accuracy=0.6844, over 6020.65 frames. ], batch size: 32, lr: 5.66e-03
2024-08-06 17:47:33,291 INFO [trainer.py:765] (1/8) Epoch 15, batch 2300, train_loss[loss=3.627, NarTop10Accuracy=0.5949, over 5739.00 frames. ], tot_loss[loss=3.213, NarTop10Accuracy=0.683, over 6037.34 frames. ], batch size: 9, lr: 5.65e-03
2024-08-06 17:47:57,640 INFO [trainer.py:765] (1/8) Epoch 15, batch 2400, train_loss[loss=3.272, NarTop10Accuracy=0.6752, over 5106.00 frames. ], tot_loss[loss=3.191, NarTop10Accuracy=0.6875, over 5798.45 frames. ], batch size: 7, lr: 5.65e-03
2024-08-06 17:48:21,161 INFO [trainer.py:765] (1/8) Epoch 15, batch 2500, train_loss[loss=2.956, NarTop10Accuracy=0.731, over 5118.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6928, over 5487.58 frames. ], batch size: 7, lr: 5.64e-03
2024-08-06 17:48:41,073 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 17:49:41,220 INFO [trainer.py:765] (1/8) Epoch 16, batch 100, train_loss[loss=3.328, NarTop10Accuracy=0.6614, over 7203.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6929, over 2363.19 frames. ], batch size: 31, lr: 5.45e-03
2024-08-06 17:50:12,157 INFO [trainer.py:765] (1/8) Epoch 16, batch 200, train_loss[loss=2.913, NarTop10Accuracy=0.7433, over 6840.00 frames. ], tot_loss[loss=3.203, NarTop10Accuracy=0.6854, over 3868.00 frames. ], batch size: 17, lr: 5.44e-03
2024-08-06 17:50:45,158 INFO [trainer.py:765] (1/8) Epoch 16, batch 300, train_loss[loss=3.115, NarTop10Accuracy=0.7049, over 7098.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.6883, over 4650.98 frames. ], batch size: 22, lr: 5.43e-03
2024-08-06 17:51:15,975 INFO [trainer.py:765] (1/8) Epoch 16, batch 400, train_loss[loss=3.613, NarTop10Accuracy=0.5999, over 5172.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6868, over 5104.33 frames. ], batch size: 7, lr: 5.43e-03
2024-08-06 17:51:50,323 INFO [trainer.py:765] (1/8) Epoch 16, batch 500, train_loss[loss=3.036, NarTop10Accuracy=0.7243, over 6042.00 frames. ], tot_loss[loss=3.188, NarTop10Accuracy=0.6882, over 5391.03 frames. ], batch size: 11, lr: 5.42e-03
2024-08-06 17:52:24,251 INFO [trainer.py:765] (1/8) Epoch 16, batch 600, train_loss[loss=2.925, NarTop10Accuracy=0.7424, over 5811.00 frames. ], tot_loss[loss=3.195, NarTop10Accuracy=0.6867, over 5654.88 frames. ], batch size: 9, lr: 5.41e-03
2024-08-06 17:52:55,386 INFO [trainer.py:765] (1/8) Epoch 16, batch 700, train_loss[loss=2.709, NarTop10Accuracy=0.786, over 4953.00 frames. ], tot_loss[loss=3.192, NarTop10Accuracy=0.6872, over 5743.94 frames. ], batch size: 6, lr: 5.41e-03
2024-08-06 17:53:33,815 INFO [trainer.py:765] (1/8) Epoch 16, batch 800, train_loss[loss=3.097, NarTop10Accuracy=0.7054, over 5172.00 frames. ], tot_loss[loss=3.184, NarTop10Accuracy=0.6889, over 5810.50 frames. ], batch size: 6, lr: 5.40e-03
2024-08-06 17:54:03,922 INFO [trainer.py:765] (1/8) Epoch 16, batch 900, train_loss[loss=3.523, NarTop10Accuracy=0.61, over 6309.00 frames. ], tot_loss[loss=3.175, NarTop10Accuracy=0.6908, over 5829.65 frames. ], batch size: 13, lr: 5.39e-03
2024-08-06 17:54:37,607 INFO [trainer.py:765] (1/8) Epoch 16, batch 1000, train_loss[loss=3.011, NarTop10Accuracy=0.7188, over 6717.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.6928, over 5927.61 frames. ], batch size: 14, lr: 5.39e-03
2024-08-06 17:55:17,196 INFO [trainer.py:765] (1/8) Epoch 16, batch 1100, train_loss[loss=3.119, NarTop10Accuracy=0.7024, over 6867.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6864, over 5947.83 frames. ], batch size: 17, lr: 5.38e-03
2024-08-06 17:55:46,209 INFO [trainer.py:765] (1/8) Epoch 16, batch 1200, train_loss[loss=3.474, NarTop10Accuracy=0.6289, over 7284.00 frames. ], tot_loss[loss=3.206, NarTop10Accuracy=0.6842, over 5947.59 frames. ], batch size: 32, lr: 5.37e-03
2024-08-06 17:56:22,774 INFO [trainer.py:765] (1/8) Epoch 16, batch 1300, train_loss[loss=3.653, NarTop10Accuracy=0.6036, over 4296.00 frames. ], tot_loss[loss=3.203, NarTop10Accuracy=0.685, over 5999.23 frames. ], batch size: 5, lr: 5.37e-03
2024-08-06 17:56:44,647 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 17:56:53,428 INFO [trainer.py:811] (1/8) Epoch 16, validation: loss=3.112, NarTop10Accuracy=0.703, over 1905321.00 frames. 
2024-08-06 17:56:53,429 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 17:56:54,007 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.620e+02 1.974e+02 2.136e+02 2.310e+02 5.351e+02, threshold=4.271e+02, percent-clipped=0.2
2024-08-06 17:57:06,171 INFO [trainer.py:765] (1/8) Epoch 16, batch 1400, train_loss[loss=3.124, NarTop10Accuracy=0.7051, over 6063.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6867, over 6030.86 frames. ], batch size: 11, lr: 5.36e-03
2024-08-06 17:57:34,033 INFO [trainer.py:765] (1/8) Epoch 16, batch 1500, train_loss[loss=3.404, NarTop10Accuracy=0.6554, over 6090.00 frames. ], tot_loss[loss=3.193, NarTop10Accuracy=0.6868, over 5945.41 frames. ], batch size: 51, lr: 5.35e-03
2024-08-06 17:58:01,775 INFO [trainer.py:765] (1/8) Epoch 16, batch 1600, train_loss[loss=2.969, NarTop10Accuracy=0.7391, over 7086.00 frames. ], tot_loss[loss=3.187, NarTop10Accuracy=0.6886, over 5931.44 frames. ], batch size: 22, lr: 5.35e-03
2024-08-06 17:58:28,475 INFO [trainer.py:765] (1/8) Epoch 16, batch 1700, train_loss[loss=2.997, NarTop10Accuracy=0.7299, over 6162.00 frames. ], tot_loss[loss=3.199, NarTop10Accuracy=0.6859, over 5925.87 frames. ], batch size: 13, lr: 5.34e-03
2024-08-06 17:58:54,976 INFO [trainer.py:765] (1/8) Epoch 16, batch 1800, train_loss[loss=3.005, NarTop10Accuracy=0.7232, over 7209.00 frames. ], tot_loss[loss=3.183, NarTop10Accuracy=0.6896, over 5980.67 frames. ], batch size: 22, lr: 5.33e-03
2024-08-06 17:59:21,360 INFO [trainer.py:765] (1/8) Epoch 16, batch 1900, train_loss[loss=3.542, NarTop10Accuracy=0.6178, over 6054.00 frames. ], tot_loss[loss=3.205, NarTop10Accuracy=0.6849, over 6027.51 frames. ], batch size: 50, lr: 5.33e-03
2024-08-06 17:59:46,857 INFO [trainer.py:765] (1/8) Epoch 16, batch 2000, train_loss[loss=3.138, NarTop10Accuracy=0.6946, over 6213.00 frames. ], tot_loss[loss=3.173, NarTop10Accuracy=0.6913, over 5992.06 frames. ], batch size: 51, lr: 5.32e-03
2024-08-06 18:00:12,117 INFO [trainer.py:765] (1/8) Epoch 16, batch 2100, train_loss[loss=3.376, NarTop10Accuracy=0.6416, over 3888.00 frames. ], tot_loss[loss=3.198, NarTop10Accuracy=0.6858, over 5960.54 frames. ], batch size: 4, lr: 5.32e-03
2024-08-06 18:00:37,333 INFO [trainer.py:765] (1/8) Epoch 16, batch 2200, train_loss[loss=3.215, NarTop10Accuracy=0.6842, over 7086.00 frames. ], tot_loss[loss=3.214, NarTop10Accuracy=0.6827, over 6008.73 frames. ], batch size: 31, lr: 5.31e-03
2024-08-06 18:01:02,502 INFO [trainer.py:765] (1/8) Epoch 16, batch 2300, train_loss[loss=3.008, NarTop10Accuracy=0.7289, over 6216.00 frames. ], tot_loss[loss=3.217, NarTop10Accuracy=0.6822, over 6012.61 frames. ], batch size: 10, lr: 5.30e-03
2024-08-06 18:01:26,883 INFO [trainer.py:765] (1/8) Epoch 16, batch 2400, train_loss[loss=2.958, NarTop10Accuracy=0.7352, over 5151.00 frames. ], tot_loss[loss=3.201, NarTop10Accuracy=0.6857, over 5790.77 frames. ], batch size: 7, lr: 5.30e-03
2024-08-06 18:01:50,405 INFO [trainer.py:765] (1/8) Epoch 16, batch 2500, train_loss[loss=2.919, NarTop10Accuracy=0.7405, over 5097.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6915, over 5477.19 frames. ], batch size: 7, lr: 5.29e-03
2024-08-06 18:02:10,742 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 18:03:08,531 INFO [trainer.py:765] (1/8) Epoch 17, batch 100, train_loss[loss=3.142, NarTop10Accuracy=0.693, over 7143.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.7017, over 2370.79 frames. ], batch size: 31, lr: 5.12e-03
2024-08-06 18:03:45,145 INFO [trainer.py:765] (1/8) Epoch 17, batch 200, train_loss[loss=3.494, NarTop10Accuracy=0.625, over 6792.00 frames. ], tot_loss[loss=3.142, NarTop10Accuracy=0.6981, over 3864.32 frames. ], batch size: 17, lr: 5.12e-03
2024-08-06 18:04:19,591 INFO [trainer.py:765] (1/8) Epoch 17, batch 300, train_loss[loss=3.284, NarTop10Accuracy=0.6668, over 7221.00 frames. ], tot_loss[loss=3.159, NarTop10Accuracy=0.6943, over 4675.44 frames. ], batch size: 22, lr: 5.11e-03
2024-08-06 18:04:48,402 INFO [trainer.py:765] (1/8) Epoch 17, batch 400, train_loss[loss=3.391, NarTop10Accuracy=0.645, over 4995.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6923, over 5113.08 frames. ], batch size: 7, lr: 5.10e-03
2024-08-06 18:05:24,680 INFO [trainer.py:765] (1/8) Epoch 17, batch 500, train_loss[loss=2.837, NarTop10Accuracy=0.7583, over 6051.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6956, over 5370.10 frames. ], batch size: 11, lr: 5.10e-03
2024-08-06 18:05:58,739 INFO [trainer.py:765] (1/8) Epoch 17, batch 600, train_loss[loss=3.163, NarTop10Accuracy=0.6813, over 5718.00 frames. ], tot_loss[loss=3.175, NarTop10Accuracy=0.6905, over 5650.56 frames. ], batch size: 9, lr: 5.09e-03
2024-08-06 18:06:32,475 INFO [trainer.py:765] (1/8) Epoch 17, batch 700, train_loss[loss=3.025, NarTop10Accuracy=0.7206, over 5097.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6921, over 5714.93 frames. ], batch size: 6, lr: 5.08e-03
2024-08-06 18:07:02,725 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 18:07:10,763 INFO [trainer.py:811] (1/8) Epoch 17, validation: loss=3.018, NarTop10Accuracy=0.7223, over 1905321.00 frames. 
2024-08-06 18:07:10,764 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 18:07:11,312 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.649e+02 2.005e+02 2.161e+02 2.341e+02 3.806e+02, threshold=4.323e+02, percent-clipped=0.0
2024-08-06 18:07:14,354 INFO [trainer.py:765] (1/8) Epoch 17, batch 800, train_loss[loss=3.006, NarTop10Accuracy=0.7224, over 4977.00 frames. ], tot_loss[loss=3.18, NarTop10Accuracy=0.6898, over 5785.16 frames. ], batch size: 6, lr: 5.08e-03
2024-08-06 18:07:49,721 INFO [trainer.py:765] (1/8) Epoch 17, batch 900, train_loss[loss=3.493, NarTop10Accuracy=0.6133, over 6345.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6944, over 5800.61 frames. ], batch size: 13, lr: 5.07e-03
2024-08-06 18:08:21,598 INFO [trainer.py:765] (1/8) Epoch 17, batch 1000, train_loss[loss=3.129, NarTop10Accuracy=0.6971, over 6396.00 frames. ], tot_loss[loss=3.167, NarTop10Accuracy=0.6925, over 5893.99 frames. ], batch size: 13, lr: 5.07e-03
2024-08-06 18:09:03,106 INFO [trainer.py:765] (1/8) Epoch 17, batch 1100, train_loss[loss=3.057, NarTop10Accuracy=0.7198, over 6591.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6914, over 5928.84 frames. ], batch size: 17, lr: 5.06e-03
2024-08-06 18:09:36,746 INFO [trainer.py:765] (1/8) Epoch 17, batch 1200, train_loss[loss=3.185, NarTop10Accuracy=0.692, over 7221.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.6925, over 5944.57 frames. ], batch size: 31, lr: 5.06e-03
2024-08-06 18:10:10,688 INFO [trainer.py:765] (1/8) Epoch 17, batch 1300, train_loss[loss=3.337, NarTop10Accuracy=0.6574, over 5145.00 frames. ], tot_loss[loss=3.172, NarTop10Accuracy=0.6913, over 6010.15 frames. ], batch size: 6, lr: 5.05e-03
2024-08-06 18:10:48,027 INFO [trainer.py:765] (1/8) Epoch 17, batch 1400, train_loss[loss=3.219, NarTop10Accuracy=0.686, over 6099.00 frames. ], tot_loss[loss=3.18, NarTop10Accuracy=0.6899, over 6026.07 frames. ], batch size: 11, lr: 5.04e-03
2024-08-06 18:11:19,106 INFO [trainer.py:765] (1/8) Epoch 17, batch 1500, train_loss[loss=3.473, NarTop10Accuracy=0.636, over 6171.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6914, over 5953.50 frames. ], batch size: 50, lr: 5.04e-03
2024-08-06 18:11:46,855 INFO [trainer.py:765] (1/8) Epoch 17, batch 1600, train_loss[loss=3.097, NarTop10Accuracy=0.7089, over 6921.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6947, over 5933.51 frames. ], batch size: 22, lr: 5.03e-03
2024-08-06 18:12:13,509 INFO [trainer.py:765] (1/8) Epoch 17, batch 1700, train_loss[loss=3.54, NarTop10Accuracy=0.6214, over 6783.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6912, over 5905.87 frames. ], batch size: 14, lr: 5.03e-03
2024-08-06 18:12:40,002 INFO [trainer.py:765] (1/8) Epoch 17, batch 1800, train_loss[loss=2.981, NarTop10Accuracy=0.7315, over 7032.00 frames. ], tot_loss[loss=3.181, NarTop10Accuracy=0.6894, over 5977.94 frames. ], batch size: 22, lr: 5.02e-03
2024-08-06 18:13:06,380 INFO [trainer.py:765] (1/8) Epoch 17, batch 1900, train_loss[loss=3.166, NarTop10Accuracy=0.6961, over 6189.00 frames. ], tot_loss[loss=3.195, NarTop10Accuracy=0.6868, over 6024.65 frames. ], batch size: 51, lr: 5.01e-03
2024-08-06 18:13:31,923 INFO [trainer.py:765] (1/8) Epoch 17, batch 2000, train_loss[loss=3.577, NarTop10Accuracy=0.6093, over 6270.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6921, over 6016.57 frames. ], batch size: 53, lr: 5.01e-03
2024-08-06 18:13:57,228 INFO [trainer.py:765] (1/8) Epoch 17, batch 2100, train_loss[loss=3.017, NarTop10Accuracy=0.7215, over 3930.00 frames. ], tot_loss[loss=3.179, NarTop10Accuracy=0.69, over 5983.52 frames. ], batch size: 4, lr: 5.00e-03
2024-08-06 18:14:22,435 INFO [trainer.py:765] (1/8) Epoch 17, batch 2200, train_loss[loss=2.997, NarTop10Accuracy=0.7295, over 7338.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.6876, over 6024.59 frames. ], batch size: 31, lr: 5.00e-03
2024-08-06 18:14:47,592 INFO [trainer.py:765] (1/8) Epoch 17, batch 2300, train_loss[loss=2.907, NarTop10Accuracy=0.7476, over 5700.00 frames. ], tot_loss[loss=3.195, NarTop10Accuracy=0.6869, over 6032.69 frames. ], batch size: 9, lr: 4.99e-03
2024-08-06 18:15:12,061 INFO [trainer.py:765] (1/8) Epoch 17, batch 2400, train_loss[loss=2.989, NarTop10Accuracy=0.7223, over 5859.00 frames. ], tot_loss[loss=3.184, NarTop10Accuracy=0.6889, over 5788.41 frames. ], batch size: 8, lr: 4.99e-03
2024-08-06 18:15:35,515 INFO [trainer.py:765] (1/8) Epoch 17, batch 2500, train_loss[loss=2.691, NarTop10Accuracy=0.7814, over 5211.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6911, over 5484.75 frames. ], batch size: 7, lr: 4.98e-03
2024-08-06 18:15:55,778 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 18:16:49,908 INFO [trainer.py:765] (1/8) Epoch 18, batch 100, train_loss[loss=3.094, NarTop10Accuracy=0.7083, over 7335.00 frames. ], tot_loss[loss=3.176, NarTop10Accuracy=0.6905, over 2365.54 frames. ], batch size: 31, lr: 4.83e-03
2024-08-06 18:17:24,749 INFO [trainer.py:765] (1/8) Epoch 18, batch 200, train_loss[loss=3.03, NarTop10Accuracy=0.7206, over 6744.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6946, over 3853.62 frames. ], batch size: 17, lr: 4.83e-03
2024-08-06 18:17:27,716 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 18:17:35,926 INFO [trainer.py:811] (1/8) Epoch 18, validation: loss=3.062, NarTop10Accuracy=0.7137, over 1905321.00 frames. 
2024-08-06 18:17:35,927 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 18:17:36,528 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.649e+02 2.024e+02 2.164e+02 2.334e+02 7.024e+02, threshold=4.329e+02, percent-clipped=0.1
2024-08-06 18:18:06,912 INFO [trainer.py:765] (1/8) Epoch 18, batch 300, train_loss[loss=3.362, NarTop10Accuracy=0.6515, over 7179.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6929, over 4654.49 frames. ], batch size: 22, lr: 4.82e-03
2024-08-06 18:18:38,183 INFO [trainer.py:765] (1/8) Epoch 18, batch 400, train_loss[loss=3.35, NarTop10Accuracy=0.6528, over 5106.00 frames. ], tot_loss[loss=3.159, NarTop10Accuracy=0.6938, over 5089.18 frames. ], batch size: 7, lr: 4.81e-03
2024-08-06 18:19:13,599 INFO [trainer.py:765] (1/8) Epoch 18, batch 500, train_loss[loss=3.058, NarTop10Accuracy=0.7189, over 6126.00 frames. ], tot_loss[loss=3.159, NarTop10Accuracy=0.6938, over 5364.59 frames. ], batch size: 11, lr: 4.81e-03
2024-08-06 18:19:48,151 INFO [trainer.py:765] (1/8) Epoch 18, batch 600, train_loss[loss=3.305, NarTop10Accuracy=0.6662, over 5721.00 frames. ], tot_loss[loss=3.156, NarTop10Accuracy=0.6944, over 5638.63 frames. ], batch size: 9, lr: 4.80e-03
2024-08-06 18:20:23,869 INFO [trainer.py:765] (1/8) Epoch 18, batch 700, train_loss[loss=3.485, NarTop10Accuracy=0.6303, over 5118.00 frames. ], tot_loss[loss=3.162, NarTop10Accuracy=0.6933, over 5695.99 frames. ], batch size: 6, lr: 4.80e-03
2024-08-06 18:21:01,026 INFO [trainer.py:765] (1/8) Epoch 18, batch 800, train_loss[loss=2.712, NarTop10Accuracy=0.7956, over 5043.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6916, over 5759.12 frames. ], batch size: 6, lr: 4.79e-03
2024-08-06 18:21:32,408 INFO [trainer.py:765] (1/8) Epoch 18, batch 900, train_loss[loss=2.949, NarTop10Accuracy=0.7402, over 6780.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6965, over 5788.79 frames. ], batch size: 14, lr: 4.79e-03
2024-08-06 18:22:11,191 INFO [trainer.py:765] (1/8) Epoch 18, batch 1000, train_loss[loss=2.951, NarTop10Accuracy=0.7363, over 6219.00 frames. ], tot_loss[loss=3.162, NarTop10Accuracy=0.6936, over 5894.05 frames. ], batch size: 13, lr: 4.78e-03
2024-08-06 18:22:46,969 INFO [trainer.py:765] (1/8) Epoch 18, batch 1100, train_loss[loss=3.28, NarTop10Accuracy=0.6623, over 6825.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.6935, over 5939.43 frames. ], batch size: 17, lr: 4.78e-03
2024-08-06 18:23:18,605 INFO [trainer.py:765] (1/8) Epoch 18, batch 1200, train_loss[loss=3.734, NarTop10Accuracy=0.5641, over 7515.00 frames. ], tot_loss[loss=3.177, NarTop10Accuracy=0.6901, over 5935.71 frames. ], batch size: 32, lr: 4.77e-03
2024-08-06 18:24:00,099 INFO [trainer.py:765] (1/8) Epoch 18, batch 1300, train_loss[loss=2.894, NarTop10Accuracy=0.7434, over 5049.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6952, over 5984.17 frames. ], batch size: 6, lr: 4.77e-03
2024-08-06 18:24:29,574 INFO [trainer.py:765] (1/8) Epoch 18, batch 1400, train_loss[loss=2.959, NarTop10Accuracy=0.7383, over 6162.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6945, over 6002.66 frames. ], batch size: 11, lr: 4.76e-03
2024-08-06 18:25:00,307 INFO [trainer.py:765] (1/8) Epoch 18, batch 1500, train_loss[loss=3.1, NarTop10Accuracy=0.708, over 6138.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6955, over 5935.01 frames. ], batch size: 50, lr: 4.76e-03
2024-08-06 18:25:28,085 INFO [trainer.py:765] (1/8) Epoch 18, batch 1600, train_loss[loss=3.131, NarTop10Accuracy=0.7006, over 7089.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6933, over 5917.57 frames. ], batch size: 22, lr: 4.75e-03
2024-08-06 18:25:54,688 INFO [trainer.py:765] (1/8) Epoch 18, batch 1700, train_loss[loss=3.071, NarTop10Accuracy=0.7189, over 6588.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6925, over 5891.77 frames. ], batch size: 14, lr: 4.75e-03
2024-08-06 18:26:21,196 INFO [trainer.py:765] (1/8) Epoch 18, batch 1800, train_loss[loss=3.522, NarTop10Accuracy=0.6257, over 7014.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.6933, over 5951.22 frames. ], batch size: 22, lr: 4.74e-03
2024-08-06 18:26:47,567 INFO [trainer.py:765] (1/8) Epoch 18, batch 1900, train_loss[loss=3.191, NarTop10Accuracy=0.6869, over 6066.00 frames. ], tot_loss[loss=3.177, NarTop10Accuracy=0.6905, over 6007.98 frames. ], batch size: 51, lr: 4.74e-03
2024-08-06 18:27:13,176 INFO [trainer.py:765] (1/8) Epoch 18, batch 2000, train_loss[loss=3.116, NarTop10Accuracy=0.7008, over 6195.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6935, over 5991.07 frames. ], batch size: 50, lr: 4.73e-03
2024-08-06 18:27:38,529 INFO [trainer.py:765] (1/8) Epoch 18, batch 2100, train_loss[loss=3.239, NarTop10Accuracy=0.6781, over 3864.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.694, over 5973.91 frames. ], batch size: 4, lr: 4.73e-03
2024-08-06 18:28:03,812 INFO [trainer.py:765] (1/8) Epoch 18, batch 2200, train_loss[loss=2.979, NarTop10Accuracy=0.7309, over 7236.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6932, over 5999.28 frames. ], batch size: 31, lr: 4.72e-03
2024-08-06 18:28:06,571 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 18:28:14,649 INFO [trainer.py:811] (1/8) Epoch 18, validation: loss=3.028, NarTop10Accuracy=0.7201, over 1905321.00 frames. 
2024-08-06 18:28:14,650 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 18:28:15,147 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.654e+02 2.054e+02 2.220e+02 2.384e+02 3.992e+02, threshold=4.441e+02, percent-clipped=0.0
2024-08-06 18:28:37,096 INFO [trainer.py:765] (1/8) Epoch 18, batch 2300, train_loss[loss=2.895, NarTop10Accuracy=0.7373, over 5616.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6905, over 6026.83 frames. ], batch size: 9, lr: 4.72e-03
2024-08-06 18:29:01,592 INFO [trainer.py:765] (1/8) Epoch 18, batch 2400, train_loss[loss=2.93, NarTop10Accuracy=0.7374, over 5166.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.695, over 5788.00 frames. ], batch size: 7, lr: 4.71e-03
2024-08-06 18:29:25,027 INFO [trainer.py:765] (1/8) Epoch 18, batch 2500, train_loss[loss=2.908, NarTop10Accuracy=0.7391, over 5109.00 frames. ], tot_loss[loss=3.13, NarTop10Accuracy=0.6993, over 5490.18 frames. ], batch size: 7, lr: 4.71e-03
2024-08-06 18:29:45,357 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 18:30:41,232 INFO [trainer.py:765] (1/8) Epoch 19, batch 100, train_loss[loss=2.978, NarTop10Accuracy=0.7321, over 7623.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6945, over 2361.05 frames. ], batch size: 32, lr: 4.57e-03
2024-08-06 18:31:15,603 INFO [trainer.py:765] (1/8) Epoch 19, batch 200, train_loss[loss=2.906, NarTop10Accuracy=0.7475, over 6864.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6966, over 3836.37 frames. ], batch size: 17, lr: 4.57e-03
2024-08-06 18:31:47,468 INFO [trainer.py:765] (1/8) Epoch 19, batch 300, train_loss[loss=3.387, NarTop10Accuracy=0.6395, over 7059.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.6993, over 4649.19 frames. ], batch size: 22, lr: 4.56e-03
2024-08-06 18:32:20,355 INFO [trainer.py:765] (1/8) Epoch 19, batch 400, train_loss[loss=3.125, NarTop10Accuracy=0.7073, over 5091.00 frames. ], tot_loss[loss=3.133, NarTop10Accuracy=0.6997, over 5113.86 frames. ], batch size: 7, lr: 4.56e-03
2024-08-06 18:32:50,335 INFO [trainer.py:765] (1/8) Epoch 19, batch 500, train_loss[loss=3.048, NarTop10Accuracy=0.7215, over 6081.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.6991, over 5405.19 frames. ], batch size: 11, lr: 4.55e-03
2024-08-06 18:33:29,610 INFO [trainer.py:765] (1/8) Epoch 19, batch 600, train_loss[loss=3.076, NarTop10Accuracy=0.7108, over 5748.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6965, over 5659.12 frames. ], batch size: 9, lr: 4.55e-03
2024-08-06 18:34:03,592 INFO [trainer.py:765] (1/8) Epoch 19, batch 700, train_loss[loss=2.974, NarTop10Accuracy=0.7304, over 5052.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6969, over 5721.90 frames. ], batch size: 6, lr: 4.54e-03
2024-08-06 18:34:35,179 INFO [trainer.py:765] (1/8) Epoch 19, batch 800, train_loss[loss=3.24, NarTop10Accuracy=0.6688, over 4359.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6957, over 5804.02 frames. ], batch size: 5, lr: 4.54e-03
2024-08-06 18:35:10,263 INFO [trainer.py:765] (1/8) Epoch 19, batch 900, train_loss[loss=2.889, NarTop10Accuracy=0.7559, over 6174.00 frames. ], tot_loss[loss=3.14, NarTop10Accuracy=0.6976, over 5822.47 frames. ], batch size: 13, lr: 4.53e-03
2024-08-06 18:35:48,637 INFO [trainer.py:765] (1/8) Epoch 19, batch 1000, train_loss[loss=3.396, NarTop10Accuracy=0.6538, over 6288.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6967, over 5929.18 frames. ], batch size: 13, lr: 4.53e-03
2024-08-06 18:36:20,939 INFO [trainer.py:765] (1/8) Epoch 19, batch 1100, train_loss[loss=2.997, NarTop10Accuracy=0.7282, over 6675.00 frames. ], tot_loss[loss=3.159, NarTop10Accuracy=0.6942, over 5927.63 frames. ], batch size: 17, lr: 4.52e-03
2024-08-06 18:36:57,130 INFO [trainer.py:765] (1/8) Epoch 19, batch 1200, train_loss[loss=3.034, NarTop10Accuracy=0.7212, over 7215.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6912, over 5936.76 frames. ], batch size: 31, lr: 4.52e-03
2024-08-06 18:37:35,315 INFO [trainer.py:765] (1/8) Epoch 19, batch 1300, train_loss[loss=2.953, NarTop10Accuracy=0.7441, over 5133.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6915, over 5997.63 frames. ], batch size: 6, lr: 4.51e-03
2024-08-06 18:38:04,680 INFO [trainer.py:765] (1/8) Epoch 19, batch 1400, train_loss[loss=2.794, NarTop10Accuracy=0.7588, over 6003.00 frames. ], tot_loss[loss=3.17, NarTop10Accuracy=0.6917, over 6020.70 frames. ], batch size: 11, lr: 4.51e-03
2024-08-06 18:38:34,550 INFO [trainer.py:765] (1/8) Epoch 19, batch 1500, train_loss[loss=3.394, NarTop10Accuracy=0.6409, over 5859.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6955, over 5958.68 frames. ], batch size: 50, lr: 4.50e-03
2024-08-06 18:39:02,312 INFO [trainer.py:765] (1/8) Epoch 19, batch 1600, train_loss[loss=3.423, NarTop10Accuracy=0.6444, over 7047.00 frames. ], tot_loss[loss=3.147, NarTop10Accuracy=0.6963, over 5942.06 frames. ], batch size: 22, lr: 4.50e-03
2024-08-06 18:39:11,591 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 18:39:19,795 INFO [trainer.py:811] (1/8) Epoch 19, validation: loss=2.958, NarTop10Accuracy=0.7345, over 1905321.00 frames. 
2024-08-06 18:39:19,796 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 18:39:20,378 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.633e+02 2.040e+02 2.194e+02 2.364e+02 6.410e+02, threshold=4.387e+02, percent-clipped=0.2
2024-08-06 18:39:37,192 INFO [trainer.py:765] (1/8) Epoch 19, batch 1700, train_loss[loss=3.467, NarTop10Accuracy=0.6241, over 6663.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6961, over 5933.68 frames. ], batch size: 14, lr: 4.49e-03
2024-08-06 18:40:03,789 INFO [trainer.py:765] (1/8) Epoch 19, batch 1800, train_loss[loss=3.477, NarTop10Accuracy=0.6231, over 7392.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.696, over 5982.11 frames. ], batch size: 23, lr: 4.49e-03
2024-08-06 18:40:30,217 INFO [trainer.py:765] (1/8) Epoch 19, batch 1900, train_loss[loss=3.149, NarTop10Accuracy=0.7025, over 5715.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6963, over 6014.38 frames. ], batch size: 51, lr: 4.49e-03
2024-08-06 18:40:55,793 INFO [trainer.py:765] (1/8) Epoch 19, batch 2000, train_loss[loss=3.26, NarTop10Accuracy=0.6766, over 6228.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6973, over 5987.62 frames. ], batch size: 51, lr: 4.48e-03
2024-08-06 18:41:21,183 INFO [trainer.py:765] (1/8) Epoch 19, batch 2100, train_loss[loss=3.086, NarTop10Accuracy=0.7126, over 4869.00 frames. ], tot_loss[loss=3.139, NarTop10Accuracy=0.6982, over 5977.69 frames. ], batch size: 5, lr: 4.48e-03
2024-08-06 18:41:46,455 INFO [trainer.py:765] (1/8) Epoch 19, batch 2200, train_loss[loss=3.232, NarTop10Accuracy=0.6791, over 6987.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6955, over 6000.34 frames. ], batch size: 31, lr: 4.47e-03
2024-08-06 18:42:11,559 INFO [trainer.py:765] (1/8) Epoch 19, batch 2300, train_loss[loss=3.24, NarTop10Accuracy=0.6706, over 5748.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6921, over 6028.71 frames. ], batch size: 9, lr: 4.47e-03
2024-08-06 18:42:35,987 INFO [trainer.py:765] (1/8) Epoch 19, batch 2400, train_loss[loss=3.035, NarTop10Accuracy=0.7166, over 5703.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6961, over 5788.06 frames. ], batch size: 8, lr: 4.46e-03
2024-08-06 18:42:59,690 INFO [trainer.py:765] (1/8) Epoch 19, batch 2500, train_loss[loss=2.921, NarTop10Accuracy=0.7419, over 5166.00 frames. ], tot_loss[loss=3.132, NarTop10Accuracy=0.6994, over 5496.78 frames. ], batch size: 7, lr: 4.46e-03
2024-08-06 18:43:19,586 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 18:44:22,974 INFO [trainer.py:765] (1/8) Epoch 20, batch 100, train_loss[loss=3.279, NarTop10Accuracy=0.6712, over 7320.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.6935, over 2364.09 frames. ], batch size: 31, lr: 4.34e-03
2024-08-06 18:44:58,379 INFO [trainer.py:765] (1/8) Epoch 20, batch 200, train_loss[loss=3.474, NarTop10Accuracy=0.629, over 6756.00 frames. ], tot_loss[loss=3.131, NarTop10Accuracy=0.6999, over 3842.50 frames. ], batch size: 17, lr: 4.33e-03
2024-08-06 18:45:32,279 INFO [trainer.py:765] (1/8) Epoch 20, batch 300, train_loss[loss=3.381, NarTop10Accuracy=0.655, over 7362.00 frames. ], tot_loss[loss=3.124, NarTop10Accuracy=0.7012, over 4651.97 frames. ], batch size: 23, lr: 4.33e-03
2024-08-06 18:46:05,128 INFO [trainer.py:765] (1/8) Epoch 20, batch 400, train_loss[loss=2.816, NarTop10Accuracy=0.7688, over 5247.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.7005, over 5117.92 frames. ], batch size: 7, lr: 4.32e-03
2024-08-06 18:46:35,770 INFO [trainer.py:765] (1/8) Epoch 20, batch 500, train_loss[loss=2.914, NarTop10Accuracy=0.7416, over 6027.00 frames. ], tot_loss[loss=3.13, NarTop10Accuracy=0.6996, over 5391.44 frames. ], batch size: 11, lr: 4.32e-03
2024-08-06 18:47:13,255 INFO [trainer.py:765] (1/8) Epoch 20, batch 600, train_loss[loss=2.953, NarTop10Accuracy=0.7363, over 5901.00 frames. ], tot_loss[loss=3.129, NarTop10Accuracy=0.7005, over 5642.81 frames. ], batch size: 9, lr: 4.31e-03
2024-08-06 18:47:44,481 INFO [trainer.py:765] (1/8) Epoch 20, batch 700, train_loss[loss=2.669, NarTop10Accuracy=0.7839, over 5145.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7025, over 5703.63 frames. ], batch size: 6, lr: 4.31e-03
2024-08-06 18:48:21,016 INFO [trainer.py:765] (1/8) Epoch 20, batch 800, train_loss[loss=2.821, NarTop10Accuracy=0.7697, over 4203.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.699, over 5789.05 frames. ], batch size: 5, lr: 4.31e-03
2024-08-06 18:48:56,535 INFO [trainer.py:765] (1/8) Epoch 20, batch 900, train_loss[loss=2.894, NarTop10Accuracy=0.7528, over 6561.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7016, over 5813.04 frames. ], batch size: 14, lr: 4.30e-03
2024-08-06 18:49:29,805 INFO [trainer.py:765] (1/8) Epoch 20, batch 1000, train_loss[loss=3.372, NarTop10Accuracy=0.6527, over 6597.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6953, over 5908.46 frames. ], batch size: 14, lr: 4.30e-03
2024-08-06 18:49:52,237 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 18:50:00,327 INFO [trainer.py:811] (1/8) Epoch 20, validation: loss=2.962, NarTop10Accuracy=0.7336, over 1905321.00 frames. 
2024-08-06 18:50:00,327 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 18:50:00,875 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.681e+02 2.061e+02 2.223e+02 2.401e+02 3.871e+02, threshold=4.447e+02, percent-clipped=0.0
2024-08-06 18:50:15,428 INFO [trainer.py:765] (1/8) Epoch 20, batch 1100, train_loss[loss=3.296, NarTop10Accuracy=0.6683, over 6981.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.6952, over 5944.50 frames. ], batch size: 17, lr: 4.29e-03
2024-08-06 18:50:53,776 INFO [trainer.py:765] (1/8) Epoch 20, batch 1200, train_loss[loss=2.981, NarTop10Accuracy=0.7278, over 7227.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6957, over 5928.93 frames. ], batch size: 31, lr: 4.29e-03
2024-08-06 18:51:25,130 INFO [trainer.py:765] (1/8) Epoch 20, batch 1300, train_loss[loss=3.195, NarTop10Accuracy=0.6823, over 4380.00 frames. ], tot_loss[loss=3.14, NarTop10Accuracy=0.6972, over 5983.71 frames. ], batch size: 5, lr: 4.29e-03
2024-08-06 18:51:59,314 INFO [trainer.py:765] (1/8) Epoch 20, batch 1400, train_loss[loss=2.985, NarTop10Accuracy=0.7357, over 6141.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.6985, over 6000.85 frames. ], batch size: 11, lr: 4.28e-03
2024-08-06 18:52:32,806 INFO [trainer.py:765] (1/8) Epoch 20, batch 1500, train_loss[loss=3.193, NarTop10Accuracy=0.6826, over 5952.00 frames. ], tot_loss[loss=3.142, NarTop10Accuracy=0.6974, over 5953.68 frames. ], batch size: 50, lr: 4.28e-03
2024-08-06 18:53:00,635 INFO [trainer.py:765] (1/8) Epoch 20, batch 1600, train_loss[loss=2.989, NarTop10Accuracy=0.74, over 7146.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6966, over 5933.47 frames. ], batch size: 22, lr: 4.27e-03
2024-08-06 18:53:27,328 INFO [trainer.py:765] (1/8) Epoch 20, batch 1700, train_loss[loss=3.605, NarTop10Accuracy=0.602, over 6696.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6965, over 5924.38 frames. ], batch size: 14, lr: 4.27e-03
2024-08-06 18:53:53,851 INFO [trainer.py:765] (1/8) Epoch 20, batch 1800, train_loss[loss=3.037, NarTop10Accuracy=0.7239, over 7203.00 frames. ], tot_loss[loss=3.137, NarTop10Accuracy=0.6985, over 5995.74 frames. ], batch size: 22, lr: 4.26e-03
2024-08-06 18:54:20,316 INFO [trainer.py:765] (1/8) Epoch 20, batch 1900, train_loss[loss=3.162, NarTop10Accuracy=0.6976, over 5580.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6926, over 6016.18 frames. ], batch size: 50, lr: 4.26e-03
2024-08-06 18:54:45,891 INFO [trainer.py:765] (1/8) Epoch 20, batch 2000, train_loss[loss=3.541, NarTop10Accuracy=0.6184, over 5985.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.693, over 5997.72 frames. ], batch size: 51, lr: 4.26e-03
2024-08-06 18:55:11,182 INFO [trainer.py:765] (1/8) Epoch 20, batch 2100, train_loss[loss=3.21, NarTop10Accuracy=0.6642, over 4791.00 frames. ], tot_loss[loss=3.156, NarTop10Accuracy=0.6947, over 5965.04 frames. ], batch size: 5, lr: 4.25e-03
2024-08-06 18:55:36,414 INFO [trainer.py:765] (1/8) Epoch 20, batch 2200, train_loss[loss=2.878, NarTop10Accuracy=0.7514, over 7329.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.6953, over 6014.34 frames. ], batch size: 31, lr: 4.25e-03
2024-08-06 18:56:01,635 INFO [trainer.py:765] (1/8) Epoch 20, batch 2300, train_loss[loss=3.135, NarTop10Accuracy=0.6986, over 5622.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6919, over 6016.30 frames. ], batch size: 9, lr: 4.24e-03
2024-08-06 18:56:26,050 INFO [trainer.py:765] (1/8) Epoch 20, batch 2400, train_loss[loss=2.999, NarTop10Accuracy=0.7293, over 5217.00 frames. ], tot_loss[loss=3.156, NarTop10Accuracy=0.694, over 5779.05 frames. ], batch size: 7, lr: 4.24e-03
2024-08-06 18:56:49,566 INFO [trainer.py:765] (1/8) Epoch 20, batch 2500, train_loss[loss=2.938, NarTop10Accuracy=0.7477, over 5118.00 frames. ], tot_loss[loss=3.119, NarTop10Accuracy=0.7018, over 5481.39 frames. ], batch size: 7, lr: 4.24e-03
2024-08-06 18:57:09,563 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 18:58:09,585 INFO [trainer.py:765] (1/8) Epoch 21, batch 100, train_loss[loss=3.356, NarTop10Accuracy=0.6517, over 6987.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7057, over 2350.65 frames. ], batch size: 31, lr: 4.13e-03
2024-08-06 18:58:40,417 INFO [trainer.py:765] (1/8) Epoch 21, batch 200, train_loss[loss=2.869, NarTop10Accuracy=0.7556, over 6837.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.701, over 3841.29 frames. ], batch size: 17, lr: 4.12e-03
2024-08-06 18:59:13,333 INFO [trainer.py:765] (1/8) Epoch 21, batch 300, train_loss[loss=2.82, NarTop10Accuracy=0.7671, over 7014.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7004, over 4651.97 frames. ], batch size: 22, lr: 4.12e-03
2024-08-06 18:59:48,150 INFO [trainer.py:765] (1/8) Epoch 21, batch 400, train_loss[loss=2.907, NarTop10Accuracy=0.7491, over 5043.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7026, over 5094.16 frames. ], batch size: 7, lr: 4.11e-03
2024-08-06 19:00:16,839 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 19:00:25,075 INFO [trainer.py:811] (1/8) Epoch 21, validation: loss=2.992, NarTop10Accuracy=0.7268, over 1905321.00 frames. 
2024-08-06 19:00:25,076 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 19:00:25,622 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.727e+02 2.071e+02 2.224e+02 2.387e+02 3.839e+02, threshold=4.447e+02, percent-clipped=0.0
2024-08-06 19:00:29,890 INFO [trainer.py:765] (1/8) Epoch 21, batch 500, train_loss[loss=2.816, NarTop10Accuracy=0.7608, over 6234.00 frames. ], tot_loss[loss=3.123, NarTop10Accuracy=0.7012, over 5371.94 frames. ], batch size: 11, lr: 4.11e-03
2024-08-06 19:01:03,328 INFO [trainer.py:765] (1/8) Epoch 21, batch 600, train_loss[loss=3.4, NarTop10Accuracy=0.648, over 5718.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7041, over 5655.48 frames. ], batch size: 9, lr: 4.11e-03
2024-08-06 19:01:39,388 INFO [trainer.py:765] (1/8) Epoch 21, batch 700, train_loss[loss=2.86, NarTop10Accuracy=0.7529, over 5037.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7034, over 5733.66 frames. ], batch size: 6, lr: 4.10e-03
2024-08-06 19:02:18,047 INFO [trainer.py:765] (1/8) Epoch 21, batch 800, train_loss[loss=3.031, NarTop10Accuracy=0.7285, over 5088.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.7002, over 5792.60 frames. ], batch size: 6, lr: 4.10e-03
2024-08-06 19:02:48,663 INFO [trainer.py:765] (1/8) Epoch 21, batch 900, train_loss[loss=2.937, NarTop10Accuracy=0.7349, over 6174.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.7002, over 5824.58 frames. ], batch size: 13, lr: 4.09e-03
2024-08-06 19:03:25,800 INFO [trainer.py:765] (1/8) Epoch 21, batch 1000, train_loss[loss=3.063, NarTop10Accuracy=0.7184, over 6306.00 frames. ], tot_loss[loss=3.131, NarTop10Accuracy=0.6993, over 5925.82 frames. ], batch size: 13, lr: 4.09e-03
2024-08-06 19:04:07,206 INFO [trainer.py:765] (1/8) Epoch 21, batch 1100, train_loss[loss=3.482, NarTop10Accuracy=0.635, over 6765.00 frames. ], tot_loss[loss=3.153, NarTop10Accuracy=0.6951, over 5956.81 frames. ], batch size: 17, lr: 4.09e-03
2024-08-06 19:04:38,462 INFO [trainer.py:765] (1/8) Epoch 21, batch 1200, train_loss[loss=3.34, NarTop10Accuracy=0.6581, over 7443.00 frames. ], tot_loss[loss=3.132, NarTop10Accuracy=0.6991, over 5937.19 frames. ], batch size: 31, lr: 4.08e-03
2024-08-06 19:05:15,315 INFO [trainer.py:765] (1/8) Epoch 21, batch 1300, train_loss[loss=2.89, NarTop10Accuracy=0.7419, over 4224.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7039, over 5996.59 frames. ], batch size: 5, lr: 4.08e-03
2024-08-06 19:05:55,559 INFO [trainer.py:765] (1/8) Epoch 21, batch 1400, train_loss[loss=3.428, NarTop10Accuracy=0.6336, over 6039.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7032, over 6001.79 frames. ], batch size: 11, lr: 4.07e-03
2024-08-06 19:06:23,599 INFO [trainer.py:765] (1/8) Epoch 21, batch 1500, train_loss[loss=3.223, NarTop10Accuracy=0.6841, over 6408.00 frames. ], tot_loss[loss=3.129, NarTop10Accuracy=0.6999, over 5938.86 frames. ], batch size: 50, lr: 4.07e-03
2024-08-06 19:06:51,461 INFO [trainer.py:765] (1/8) Epoch 21, batch 1600, train_loss[loss=2.945, NarTop10Accuracy=0.7447, over 6960.00 frames. ], tot_loss[loss=3.133, NarTop10Accuracy=0.6991, over 5924.21 frames. ], batch size: 22, lr: 4.07e-03
2024-08-06 19:07:18,211 INFO [trainer.py:765] (1/8) Epoch 21, batch 1700, train_loss[loss=3.201, NarTop10Accuracy=0.6919, over 6585.00 frames. ], tot_loss[loss=3.139, NarTop10Accuracy=0.6981, over 5920.20 frames. ], batch size: 14, lr: 4.06e-03
2024-08-06 19:07:44,809 INFO [trainer.py:765] (1/8) Epoch 21, batch 1800, train_loss[loss=2.836, NarTop10Accuracy=0.7518, over 7119.00 frames. ], tot_loss[loss=3.133, NarTop10Accuracy=0.6992, over 5972.93 frames. ], batch size: 22, lr: 4.06e-03
2024-08-06 19:08:11,369 INFO [trainer.py:765] (1/8) Epoch 21, batch 1900, train_loss[loss=3.657, NarTop10Accuracy=0.595, over 5958.00 frames. ], tot_loss[loss=3.147, NarTop10Accuracy=0.6968, over 6019.77 frames. ], batch size: 50, lr: 4.06e-03
2024-08-06 19:08:37,105 INFO [trainer.py:765] (1/8) Epoch 21, batch 2000, train_loss[loss=3.498, NarTop10Accuracy=0.6294, over 6138.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6962, over 5997.44 frames. ], batch size: 50, lr: 4.05e-03
2024-08-06 19:09:02,507 INFO [trainer.py:765] (1/8) Epoch 21, batch 2100, train_loss[loss=2.758, NarTop10Accuracy=0.7782, over 4827.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6959, over 5970.84 frames. ], batch size: 5, lr: 4.05e-03
2024-08-06 19:09:27,891 INFO [trainer.py:765] (1/8) Epoch 21, batch 2200, train_loss[loss=2.907, NarTop10Accuracy=0.742, over 7119.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6948, over 6018.16 frames. ], batch size: 31, lr: 4.04e-03
2024-08-06 19:09:53,222 INFO [trainer.py:765] (1/8) Epoch 21, batch 2300, train_loss[loss=3.111, NarTop10Accuracy=0.6958, over 5769.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.692, over 6030.19 frames. ], batch size: 9, lr: 4.04e-03
2024-08-06 19:10:17,596 INFO [trainer.py:765] (1/8) Epoch 21, batch 2400, train_loss[loss=3.34, NarTop10Accuracy=0.6507, over 5205.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6962, over 5771.95 frames. ], batch size: 7, lr: 4.04e-03
2024-08-06 19:10:37,228 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 19:10:45,275 INFO [trainer.py:811] (1/8) Epoch 21, validation: loss=2.971, NarTop10Accuracy=0.7316, over 1905321.00 frames. 
2024-08-06 19:10:45,276 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 19:10:45,741 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.703e+02 2.100e+02 2.242e+02 2.407e+02 6.546e+02, threshold=4.484e+02, percent-clipped=0.1
2024-08-06 19:10:49,272 INFO [trainer.py:765] (1/8) Epoch 21, batch 2500, train_loss[loss=3.387, NarTop10Accuracy=0.6533, over 5091.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.704, over 5460.11 frames. ], batch size: 7, lr: 4.03e-03
2024-08-06 19:11:08,908 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 19:12:09,053 INFO [trainer.py:765] (1/8) Epoch 22, batch 100, train_loss[loss=3.055, NarTop10Accuracy=0.7234, over 7206.00 frames. ], tot_loss[loss=3.107, NarTop10Accuracy=0.7045, over 2370.31 frames. ], batch size: 31, lr: 3.93e-03
2024-08-06 19:12:44,462 INFO [trainer.py:765] (1/8) Epoch 22, batch 200, train_loss[loss=3.176, NarTop10Accuracy=0.6876, over 6807.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7037, over 3856.56 frames. ], batch size: 17, lr: 3.93e-03
2024-08-06 19:13:14,533 INFO [trainer.py:765] (1/8) Epoch 22, batch 300, train_loss[loss=2.954, NarTop10Accuracy=0.7362, over 6885.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.706, over 4651.70 frames. ], batch size: 22, lr: 3.93e-03
2024-08-06 19:13:49,228 INFO [trainer.py:765] (1/8) Epoch 22, batch 400, train_loss[loss=2.989, NarTop10Accuracy=0.7363, over 5109.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.707, over 5103.93 frames. ], batch size: 7, lr: 3.92e-03
2024-08-06 19:14:24,850 INFO [trainer.py:765] (1/8) Epoch 22, batch 500, train_loss[loss=3.132, NarTop10Accuracy=0.6949, over 6126.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.706, over 5388.78 frames. ], batch size: 11, lr: 3.92e-03
2024-08-06 19:14:55,701 INFO [trainer.py:765] (1/8) Epoch 22, batch 600, train_loss[loss=3.114, NarTop10Accuracy=0.7082, over 5706.00 frames. ], tot_loss[loss=3.132, NarTop10Accuracy=0.6994, over 5650.35 frames. ], batch size: 9, lr: 3.92e-03
2024-08-06 19:15:30,867 INFO [trainer.py:765] (1/8) Epoch 22, batch 700, train_loss[loss=3.467, NarTop10Accuracy=0.6349, over 4377.00 frames. ], tot_loss[loss=3.13, NarTop10Accuracy=0.7, over 5708.94 frames. ], batch size: 5, lr: 3.91e-03
2024-08-06 19:16:10,664 INFO [trainer.py:765] (1/8) Epoch 22, batch 800, train_loss[loss=2.882, NarTop10Accuracy=0.7503, over 5046.00 frames. ], tot_loss[loss=3.117, NarTop10Accuracy=0.7025, over 5791.66 frames. ], batch size: 6, lr: 3.91e-03
2024-08-06 19:16:40,952 INFO [trainer.py:765] (1/8) Epoch 22, batch 900, train_loss[loss=3.061, NarTop10Accuracy=0.7137, over 6177.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7022, over 5818.86 frames. ], batch size: 13, lr: 3.90e-03
2024-08-06 19:17:16,433 INFO [trainer.py:765] (1/8) Epoch 22, batch 1000, train_loss[loss=3.161, NarTop10Accuracy=0.6928, over 6546.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7035, over 5913.57 frames. ], batch size: 14, lr: 3.90e-03
2024-08-06 19:17:52,085 INFO [trainer.py:765] (1/8) Epoch 22, batch 1100, train_loss[loss=2.969, NarTop10Accuracy=0.7367, over 6831.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7024, over 5950.03 frames. ], batch size: 17, lr: 3.90e-03
2024-08-06 19:18:25,926 INFO [trainer.py:765] (1/8) Epoch 22, batch 1200, train_loss[loss=2.927, NarTop10Accuracy=0.745, over 7056.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7061, over 5946.95 frames. ], batch size: 31, lr: 3.89e-03
2024-08-06 19:19:01,252 INFO [trainer.py:765] (1/8) Epoch 22, batch 1300, train_loss[loss=2.944, NarTop10Accuracy=0.7418, over 5172.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7073, over 6005.49 frames. ], batch size: 6, lr: 3.89e-03
2024-08-06 19:19:33,316 INFO [trainer.py:765] (1/8) Epoch 22, batch 1400, train_loss[loss=2.845, NarTop10Accuracy=0.7641, over 6036.00 frames. ], tot_loss[loss=3.106, NarTop10Accuracy=0.7047, over 6026.15 frames. ], batch size: 11, lr: 3.89e-03
2024-08-06 19:20:03,830 INFO [trainer.py:765] (1/8) Epoch 22, batch 1500, train_loss[loss=3.512, NarTop10Accuracy=0.6193, over 5880.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7043, over 5960.43 frames. ], batch size: 50, lr: 3.88e-03
2024-08-06 19:20:31,646 INFO [trainer.py:765] (1/8) Epoch 22, batch 1600, train_loss[loss=3.14, NarTop10Accuracy=0.7018, over 7041.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7008, over 5935.41 frames. ], batch size: 22, lr: 3.88e-03
2024-08-06 19:20:58,417 INFO [trainer.py:765] (1/8) Epoch 22, batch 1700, train_loss[loss=3.299, NarTop10Accuracy=0.6676, over 6633.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7006, over 5926.97 frames. ], batch size: 14, lr: 3.88e-03
2024-08-06 19:21:25,010 INFO [trainer.py:765] (1/8) Epoch 22, batch 1800, train_loss[loss=2.885, NarTop10Accuracy=0.7433, over 7203.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7016, over 5991.64 frames. ], batch size: 22, lr: 3.87e-03
2024-08-06 19:21:51,372 INFO [trainer.py:765] (1/8) Epoch 22, batch 1900, train_loss[loss=3.092, NarTop10Accuracy=0.7117, over 6291.00 frames. ], tot_loss[loss=3.142, NarTop10Accuracy=0.6972, over 6045.79 frames. ], batch size: 52, lr: 3.87e-03
2024-08-06 19:21:53,109 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 19:22:01,088 INFO [trainer.py:811] (1/8) Epoch 22, validation: loss=3.009, NarTop10Accuracy=0.7241, over 1905321.00 frames. 
2024-08-06 19:22:01,089 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 19:22:01,575 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.670e+02 2.114e+02 2.276e+02 2.445e+02 4.438e+02, threshold=4.551e+02, percent-clipped=0.0
2024-08-06 19:22:24,819 INFO [trainer.py:765] (1/8) Epoch 22, batch 2000, train_loss[loss=3.576, NarTop10Accuracy=0.6102, over 6270.00 frames. ], tot_loss[loss=3.119, NarTop10Accuracy=0.7019, over 6016.48 frames. ], batch size: 51, lr: 3.87e-03
2024-08-06 19:22:50,041 INFO [trainer.py:765] (1/8) Epoch 22, batch 2100, train_loss[loss=3.399, NarTop10Accuracy=0.6428, over 4767.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7032, over 5990.87 frames. ], batch size: 5, lr: 3.86e-03
2024-08-06 19:23:15,230 INFO [trainer.py:765] (1/8) Epoch 22, batch 2200, train_loss[loss=3.043, NarTop10Accuracy=0.7208, over 7224.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7034, over 6016.39 frames. ], batch size: 31, lr: 3.86e-03
2024-08-06 19:23:40,315 INFO [trainer.py:765] (1/8) Epoch 22, batch 2300, train_loss[loss=3.022, NarTop10Accuracy=0.7237, over 5655.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.7001, over 6039.75 frames. ], batch size: 9, lr: 3.86e-03
2024-08-06 19:24:04,602 INFO [trainer.py:765] (1/8) Epoch 22, batch 2400, train_loss[loss=3.122, NarTop10Accuracy=0.7047, over 5130.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7026, over 5805.11 frames. ], batch size: 7, lr: 3.85e-03
2024-08-06 19:24:28,024 INFO [trainer.py:765] (1/8) Epoch 22, batch 2500, train_loss[loss=3.125, NarTop10Accuracy=0.6888, over 5145.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7055, over 5512.87 frames. ], batch size: 7, lr: 3.85e-03
2024-08-06 19:24:47,564 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 19:25:45,385 INFO [trainer.py:765] (1/8) Epoch 23, batch 100, train_loss[loss=3.058, NarTop10Accuracy=0.7229, over 7374.00 frames. ], tot_loss[loss=3.124, NarTop10Accuracy=0.7013, over 2372.04 frames. ], batch size: 31, lr: 3.76e-03
2024-08-06 19:26:21,309 INFO [trainer.py:765] (1/8) Epoch 23, batch 200, train_loss[loss=3.468, NarTop10Accuracy=0.6343, over 6771.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7019, over 3868.22 frames. ], batch size: 17, lr: 3.76e-03
2024-08-06 19:26:57,603 INFO [trainer.py:765] (1/8) Epoch 23, batch 300, train_loss[loss=3.019, NarTop10Accuracy=0.7282, over 7212.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7053, over 4667.14 frames. ], batch size: 22, lr: 3.75e-03
2024-08-06 19:27:26,540 INFO [trainer.py:765] (1/8) Epoch 23, batch 400, train_loss[loss=3.385, NarTop10Accuracy=0.6527, over 5214.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7038, over 5126.27 frames. ], batch size: 7, lr: 3.75e-03
2024-08-06 19:27:59,712 INFO [trainer.py:765] (1/8) Epoch 23, batch 500, train_loss[loss=3.421, NarTop10Accuracy=0.6277, over 6048.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7033, over 5403.53 frames. ], batch size: 11, lr: 3.75e-03
2024-08-06 19:28:35,883 INFO [trainer.py:765] (1/8) Epoch 23, batch 600, train_loss[loss=3.399, NarTop10Accuracy=0.6422, over 5739.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7047, over 5651.03 frames. ], batch size: 9, lr: 3.74e-03
2024-08-06 19:29:11,366 INFO [trainer.py:765] (1/8) Epoch 23, batch 700, train_loss[loss=3.398, NarTop10Accuracy=0.6473, over 4230.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7067, over 5711.68 frames. ], batch size: 5, lr: 3.74e-03
2024-08-06 19:29:43,613 INFO [trainer.py:765] (1/8) Epoch 23, batch 800, train_loss[loss=2.653, NarTop10Accuracy=0.7858, over 5145.00 frames. ], tot_loss[loss=3.106, NarTop10Accuracy=0.7045, over 5768.72 frames. ], batch size: 6, lr: 3.74e-03
2024-08-06 19:30:19,390 INFO [trainer.py:765] (1/8) Epoch 23, batch 900, train_loss[loss=3.332, NarTop10Accuracy=0.653, over 6147.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7067, over 5791.29 frames. ], batch size: 13, lr: 3.73e-03
2024-08-06 19:30:58,195 INFO [trainer.py:765] (1/8) Epoch 23, batch 1000, train_loss[loss=3.007, NarTop10Accuracy=0.7231, over 6204.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7083, over 5898.84 frames. ], batch size: 13, lr: 3.73e-03
2024-08-06 19:31:31,520 INFO [trainer.py:765] (1/8) Epoch 23, batch 1100, train_loss[loss=3.074, NarTop10Accuracy=0.7172, over 6867.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.708, over 5940.40 frames. ], batch size: 17, lr: 3.73e-03
2024-08-06 19:32:08,518 INFO [trainer.py:765] (1/8) Epoch 23, batch 1200, train_loss[loss=3.009, NarTop10Accuracy=0.726, over 7377.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7042, over 5941.10 frames. ], batch size: 31, lr: 3.72e-03
2024-08-06 19:32:46,937 INFO [trainer.py:765] (1/8) Epoch 23, batch 1300, train_loss[loss=3.185, NarTop10Accuracy=0.6892, over 4983.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7039, over 6004.13 frames. ], batch size: 6, lr: 3.72e-03
2024-08-06 19:32:56,402 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 19:33:04,722 INFO [trainer.py:811] (1/8) Epoch 23, validation: loss=2.893, NarTop10Accuracy=0.7468, over 1905321.00 frames. 
2024-08-06 19:33:04,723 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 19:33:05,262 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.759e+02 2.108e+02 2.273e+02 2.457e+02 3.966e+02, threshold=4.546e+02, percent-clipped=0.0
2024-08-06 19:33:27,409 INFO [trainer.py:765] (1/8) Epoch 23, batch 1400, train_loss[loss=2.746, NarTop10Accuracy=0.7811, over 5997.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7033, over 6024.74 frames. ], batch size: 11, lr: 3.72e-03
2024-08-06 19:33:58,215 INFO [trainer.py:765] (1/8) Epoch 23, batch 1500, train_loss[loss=3.28, NarTop10Accuracy=0.6757, over 5889.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7062, over 5970.50 frames. ], batch size: 50, lr: 3.71e-03
2024-08-06 19:34:26,015 INFO [trainer.py:765] (1/8) Epoch 23, batch 1600, train_loss[loss=2.895, NarTop10Accuracy=0.7442, over 7212.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7046, over 5968.89 frames. ], batch size: 23, lr: 3.71e-03
2024-08-06 19:34:52,783 INFO [trainer.py:765] (1/8) Epoch 23, batch 1700, train_loss[loss=3.234, NarTop10Accuracy=0.6801, over 6606.00 frames. ], tot_loss[loss=3.124, NarTop10Accuracy=0.7005, over 5935.44 frames. ], batch size: 14, lr: 3.71e-03
2024-08-06 19:35:19,262 INFO [trainer.py:765] (1/8) Epoch 23, batch 1800, train_loss[loss=2.949, NarTop10Accuracy=0.7328, over 7092.00 frames. ], tot_loss[loss=3.121, NarTop10Accuracy=0.7011, over 5977.04 frames. ], batch size: 22, lr: 3.70e-03
2024-08-06 19:35:45,596 INFO [trainer.py:765] (1/8) Epoch 23, batch 1900, train_loss[loss=3.342, NarTop10Accuracy=0.6545, over 5679.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.7001, over 6018.39 frames. ], batch size: 50, lr: 3.70e-03
2024-08-06 19:36:11,170 INFO [trainer.py:765] (1/8) Epoch 23, batch 2000, train_loss[loss=3.567, NarTop10Accuracy=0.6056, over 6429.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7041, over 5984.40 frames. ], batch size: 50, lr: 3.70e-03
2024-08-06 19:36:36,518 INFO [trainer.py:765] (1/8) Epoch 23, batch 2100, train_loss[loss=3.205, NarTop10Accuracy=0.6827, over 3954.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.703, over 5987.74 frames. ], batch size: 4, lr: 3.69e-03
2024-08-06 19:37:01,908 INFO [trainer.py:765] (1/8) Epoch 23, batch 2200, train_loss[loss=3.089, NarTop10Accuracy=0.7006, over 7269.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.6998, over 6033.60 frames. ], batch size: 31, lr: 3.69e-03
2024-08-06 19:37:27,060 INFO [trainer.py:765] (1/8) Epoch 23, batch 2300, train_loss[loss=3.015, NarTop10Accuracy=0.7236, over 5622.00 frames. ], tot_loss[loss=3.117, NarTop10Accuracy=0.702, over 6047.55 frames. ], batch size: 9, lr: 3.69e-03
2024-08-06 19:37:51,425 INFO [trainer.py:765] (1/8) Epoch 23, batch 2400, train_loss[loss=3.007, NarTop10Accuracy=0.7298, over 5106.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.701, over 5795.55 frames. ], batch size: 7, lr: 3.69e-03
2024-08-06 19:38:15,053 INFO [trainer.py:765] (1/8) Epoch 23, batch 2500, train_loss[loss=3.442, NarTop10Accuracy=0.6356, over 5175.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7057, over 5484.39 frames. ], batch size: 7, lr: 3.68e-03
2024-08-06 19:38:35,059 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 19:39:37,631 INFO [trainer.py:765] (1/8) Epoch 24, batch 100, train_loss[loss=3.417, NarTop10Accuracy=0.6408, over 7416.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7029, over 2363.83 frames. ], batch size: 32, lr: 3.60e-03
2024-08-06 19:40:10,189 INFO [trainer.py:765] (1/8) Epoch 24, batch 200, train_loss[loss=2.839, NarTop10Accuracy=0.7602, over 6840.00 frames. ], tot_loss[loss=3.107, NarTop10Accuracy=0.7046, over 3868.16 frames. ], batch size: 17, lr: 3.60e-03
2024-08-06 19:40:40,554 INFO [trainer.py:765] (1/8) Epoch 24, batch 300, train_loss[loss=2.846, NarTop10Accuracy=0.7675, over 7092.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7059, over 4667.96 frames. ], batch size: 22, lr: 3.59e-03
2024-08-06 19:41:18,233 INFO [trainer.py:765] (1/8) Epoch 24, batch 400, train_loss[loss=2.834, NarTop10Accuracy=0.7418, over 5220.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7067, over 5114.44 frames. ], batch size: 7, lr: 3.59e-03
2024-08-06 19:41:50,321 INFO [trainer.py:765] (1/8) Epoch 24, batch 500, train_loss[loss=2.966, NarTop10Accuracy=0.7388, over 6150.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7097, over 5379.61 frames. ], batch size: 11, lr: 3.59e-03
2024-08-06 19:42:21,451 INFO [trainer.py:765] (1/8) Epoch 24, batch 600, train_loss[loss=2.852, NarTop10Accuracy=0.7545, over 5742.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7082, over 5646.78 frames. ], batch size: 9, lr: 3.58e-03
2024-08-06 19:42:52,842 INFO [trainer.py:765] (1/8) Epoch 24, batch 700, train_loss[loss=2.904, NarTop10Accuracy=0.7497, over 5130.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7069, over 5724.88 frames. ], batch size: 6, lr: 3.58e-03
2024-08-06 19:43:17,380 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 19:43:25,410 INFO [trainer.py:811] (1/8) Epoch 24, validation: loss=3.021, NarTop10Accuracy=0.7204, over 1905321.00 frames. 
2024-08-06 19:43:25,411 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29066MB
2024-08-06 19:43:28,562 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.744e+02 2.113e+02 2.282e+02 2.472e+02 2.357e+03, threshold=4.564e+02, percent-clipped=0.2
2024-08-06 19:43:40,814 INFO [trainer.py:765] (1/8) Epoch 24, batch 800, train_loss[loss=2.874, NarTop10Accuracy=0.7516, over 5025.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7077, over 5785.12 frames. ], batch size: 6, lr: 3.58e-03
2024-08-06 19:44:11,409 INFO [trainer.py:765] (1/8) Epoch 24, batch 900, train_loss[loss=2.878, NarTop10Accuracy=0.7496, over 6723.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7082, over 5801.37 frames. ], batch size: 14, lr: 3.57e-03
2024-08-06 19:44:47,489 INFO [trainer.py:765] (1/8) Epoch 24, batch 1000, train_loss[loss=3.253, NarTop10Accuracy=0.6691, over 6399.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.706, over 5905.91 frames. ], batch size: 13, lr: 3.57e-03
2024-08-06 19:45:27,107 INFO [trainer.py:765] (1/8) Epoch 24, batch 1100, train_loss[loss=3.452, NarTop10Accuracy=0.6292, over 6828.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7035, over 5940.87 frames. ], batch size: 17, lr: 3.57e-03
2024-08-06 19:45:58,437 INFO [trainer.py:765] (1/8) Epoch 24, batch 1200, train_loss[loss=2.948, NarTop10Accuracy=0.7416, over 7578.00 frames. ], tot_loss[loss=3.105, NarTop10Accuracy=0.7046, over 5957.79 frames. ], batch size: 32, lr: 3.57e-03
2024-08-06 19:46:30,293 INFO [trainer.py:765] (1/8) Epoch 24, batch 1300, train_loss[loss=3.217, NarTop10Accuracy=0.6698, over 4293.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7056, over 6007.72 frames. ], batch size: 5, lr: 3.56e-03
2024-08-06 19:47:07,859 INFO [trainer.py:765] (1/8) Epoch 24, batch 1400, train_loss[loss=3.314, NarTop10Accuracy=0.6644, over 6150.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7033, over 6017.20 frames. ], batch size: 11, lr: 3.56e-03
2024-08-06 19:47:40,956 INFO [trainer.py:765] (1/8) Epoch 24, batch 1500, train_loss[loss=3.402, NarTop10Accuracy=0.6479, over 5919.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7016, over 5965.35 frames. ], batch size: 50, lr: 3.56e-03
2024-08-06 19:48:08,675 INFO [trainer.py:765] (1/8) Epoch 24, batch 1600, train_loss[loss=3.447, NarTop10Accuracy=0.6357, over 7071.00 frames. ], tot_loss[loss=3.123, NarTop10Accuracy=0.7003, over 5935.28 frames. ], batch size: 22, lr: 3.55e-03
2024-08-06 19:48:35,266 INFO [trainer.py:765] (1/8) Epoch 24, batch 1700, train_loss[loss=2.858, NarTop10Accuracy=0.7612, over 6531.00 frames. ], tot_loss[loss=3.121, NarTop10Accuracy=0.7012, over 5911.94 frames. ], batch size: 14, lr: 3.55e-03
2024-08-06 19:49:01,637 INFO [trainer.py:765] (1/8) Epoch 24, batch 1800, train_loss[loss=2.983, NarTop10Accuracy=0.7313, over 7191.00 frames. ], tot_loss[loss=3.124, NarTop10Accuracy=0.6999, over 5963.22 frames. ], batch size: 22, lr: 3.55e-03
2024-08-06 19:49:28,041 INFO [trainer.py:765] (1/8) Epoch 24, batch 1900, train_loss[loss=3.613, NarTop10Accuracy=0.6023, over 6222.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.6998, over 6027.63 frames. ], batch size: 50, lr: 3.55e-03
2024-08-06 19:49:53,533 INFO [trainer.py:765] (1/8) Epoch 24, batch 2000, train_loss[loss=3.506, NarTop10Accuracy=0.6242, over 6528.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.705, over 6007.38 frames. ], batch size: 51, lr: 3.54e-03
2024-08-06 19:50:18,819 INFO [trainer.py:765] (1/8) Epoch 24, batch 2100, train_loss[loss=3.024, NarTop10Accuracy=0.7188, over 3912.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7049, over 5991.68 frames. ], batch size: 4, lr: 3.54e-03
2024-08-06 19:50:43,942 INFO [trainer.py:765] (1/8) Epoch 24, batch 2200, train_loss[loss=3.458, NarTop10Accuracy=0.6324, over 6984.00 frames. ], tot_loss[loss=3.104, NarTop10Accuracy=0.7045, over 6027.63 frames. ], batch size: 31, lr: 3.54e-03
2024-08-06 19:51:09,024 INFO [trainer.py:765] (1/8) Epoch 24, batch 2300, train_loss[loss=2.743, NarTop10Accuracy=0.7729, over 5751.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7039, over 6042.53 frames. ], batch size: 9, lr: 3.53e-03
2024-08-06 19:51:33,348 INFO [trainer.py:765] (1/8) Epoch 24, batch 2400, train_loss[loss=3.02, NarTop10Accuracy=0.717, over 5229.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.7052, over 5789.93 frames. ], batch size: 7, lr: 3.53e-03
2024-08-06 19:51:56,782 INFO [trainer.py:765] (1/8) Epoch 24, batch 2500, train_loss[loss=2.914, NarTop10Accuracy=0.7413, over 5724.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7087, over 5501.58 frames. ], batch size: 8, lr: 3.53e-03
2024-08-06 19:52:17,153 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 19:53:22,196 INFO [trainer.py:765] (1/8) Epoch 25, batch 100, train_loss[loss=3.403, NarTop10Accuracy=0.6454, over 7251.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.709, over 2357.72 frames. ], batch size: 31, lr: 3.45e-03
2024-08-06 19:53:47,261 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 19:53:55,329 INFO [trainer.py:811] (1/8) Epoch 25, validation: loss=2.96, NarTop10Accuracy=0.7332, over 1905321.00 frames. 
2024-08-06 19:53:55,329 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29627MB
2024-08-06 19:53:55,916 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.693e+02 2.155e+02 2.306e+02 2.475e+02 6.485e+02, threshold=4.611e+02, percent-clipped=0.1
2024-08-06 19:54:01,176 INFO [trainer.py:765] (1/8) Epoch 25, batch 200, train_loss[loss=2.845, NarTop10Accuracy=0.7592, over 6822.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.708, over 3831.60 frames. ], batch size: 17, lr: 3.45e-03
2024-08-06 19:54:35,647 INFO [trainer.py:765] (1/8) Epoch 25, batch 300, train_loss[loss=3.238, NarTop10Accuracy=0.6804, over 6972.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7092, over 4644.72 frames. ], batch size: 22, lr: 3.45e-03
2024-08-06 19:55:12,958 INFO [trainer.py:765] (1/8) Epoch 25, batch 400, train_loss[loss=2.96, NarTop10Accuracy=0.7419, over 4977.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.709, over 5086.95 frames. ], batch size: 7, lr: 3.44e-03
2024-08-06 19:55:43,737 INFO [trainer.py:765] (1/8) Epoch 25, batch 500, train_loss[loss=2.744, NarTop10Accuracy=0.7707, over 6129.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7104, over 5374.66 frames. ], batch size: 11, lr: 3.44e-03
2024-08-06 19:56:14,814 INFO [trainer.py:765] (1/8) Epoch 25, batch 600, train_loss[loss=2.823, NarTop10Accuracy=0.761, over 5652.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.71, over 5643.53 frames. ], batch size: 9, lr: 3.44e-03
2024-08-06 19:56:55,496 INFO [trainer.py:765] (1/8) Epoch 25, batch 700, train_loss[loss=2.708, NarTop10Accuracy=0.7881, over 5016.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7123, over 5709.97 frames. ], batch size: 6, lr: 3.43e-03
2024-08-06 19:57:30,135 INFO [trainer.py:765] (1/8) Epoch 25, batch 800, train_loss[loss=2.694, NarTop10Accuracy=0.7819, over 4224.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.71, over 5774.10 frames. ], batch size: 5, lr: 3.43e-03
2024-08-06 19:58:00,678 INFO [trainer.py:765] (1/8) Epoch 25, batch 900, train_loss[loss=3.19, NarTop10Accuracy=0.6804, over 6588.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7107, over 5796.09 frames. ], batch size: 14, lr: 3.43e-03
2024-08-06 19:58:37,638 INFO [trainer.py:765] (1/8) Epoch 25, batch 1000, train_loss[loss=2.916, NarTop10Accuracy=0.7413, over 6729.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7073, over 5890.63 frames. ], batch size: 14, lr: 3.43e-03
2024-08-06 19:59:14,854 INFO [trainer.py:765] (1/8) Epoch 25, batch 1100, train_loss[loss=3.427, NarTop10Accuracy=0.635, over 6840.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7077, over 5939.78 frames. ], batch size: 17, lr: 3.42e-03
2024-08-06 19:59:49,038 INFO [trainer.py:765] (1/8) Epoch 25, batch 1200, train_loss[loss=3.434, NarTop10Accuracy=0.6298, over 7062.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7085, over 5940.64 frames. ], batch size: 31, lr: 3.42e-03
2024-08-06 20:00:25,598 INFO [trainer.py:765] (1/8) Epoch 25, batch 1300, train_loss[loss=2.923, NarTop10Accuracy=0.7507, over 5193.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7083, over 6003.16 frames. ], batch size: 6, lr: 3.42e-03
2024-08-06 20:01:02,015 INFO [trainer.py:765] (1/8) Epoch 25, batch 1400, train_loss[loss=2.905, NarTop10Accuracy=0.7481, over 6207.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7087, over 6017.69 frames. ], batch size: 11, lr: 3.42e-03
2024-08-06 20:01:32,822 INFO [trainer.py:765] (1/8) Epoch 25, batch 1500, train_loss[loss=3.226, NarTop10Accuracy=0.6806, over 5853.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7078, over 5945.36 frames. ], batch size: 50, lr: 3.41e-03
2024-08-06 20:02:00,624 INFO [trainer.py:765] (1/8) Epoch 25, batch 1600, train_loss[loss=2.794, NarTop10Accuracy=0.767, over 7497.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7084, over 5938.76 frames. ], batch size: 23, lr: 3.41e-03
2024-08-06 20:02:27,358 INFO [trainer.py:765] (1/8) Epoch 25, batch 1700, train_loss[loss=2.919, NarTop10Accuracy=0.736, over 6270.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7076, over 5923.81 frames. ], batch size: 13, lr: 3.41e-03
2024-08-06 20:02:53,853 INFO [trainer.py:765] (1/8) Epoch 25, batch 1800, train_loss[loss=3.393, NarTop10Accuracy=0.6453, over 6903.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7053, over 5973.77 frames. ], batch size: 22, lr: 3.40e-03
2024-08-06 20:03:20,340 INFO [trainer.py:765] (1/8) Epoch 25, batch 1900, train_loss[loss=3.149, NarTop10Accuracy=0.701, over 6087.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.703, over 6008.05 frames. ], batch size: 50, lr: 3.40e-03
2024-08-06 20:03:45,934 INFO [trainer.py:765] (1/8) Epoch 25, batch 2000, train_loss[loss=3.441, NarTop10Accuracy=0.6421, over 6300.00 frames. ], tot_loss[loss=3.123, NarTop10Accuracy=0.7007, over 5986.77 frames. ], batch size: 50, lr: 3.40e-03
2024-08-06 20:04:11,245 INFO [trainer.py:765] (1/8) Epoch 25, batch 2100, train_loss[loss=2.728, NarTop10Accuracy=0.7843, over 3825.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7031, over 5962.89 frames. ], batch size: 4, lr: 3.40e-03
2024-08-06 20:04:31,408 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 20:04:39,343 INFO [trainer.py:811] (1/8) Epoch 25, validation: loss=2.999, NarTop10Accuracy=0.7251, over 1905321.00 frames. 
2024-08-06 20:04:39,344 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29627MB
2024-08-06 20:04:39,840 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.755e+02 2.185e+02 2.339e+02 2.507e+02 3.640e+02, threshold=4.678e+02, percent-clipped=0.0
2024-08-06 20:04:44,513 INFO [trainer.py:765] (1/8) Epoch 25, batch 2200, train_loss[loss=3.221, NarTop10Accuracy=0.6766, over 6921.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7021, over 6023.20 frames. ], batch size: 31, lr: 3.39e-03
2024-08-06 20:05:09,645 INFO [trainer.py:765] (1/8) Epoch 25, batch 2300, train_loss[loss=3.037, NarTop10Accuracy=0.7228, over 5676.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7019, over 6018.11 frames. ], batch size: 9, lr: 3.39e-03
2024-08-06 20:05:34,141 INFO [trainer.py:765] (1/8) Epoch 25, batch 2400, train_loss[loss=2.842, NarTop10Accuracy=0.7537, over 5127.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.7053, over 5796.04 frames. ], batch size: 7, lr: 3.39e-03
2024-08-06 20:05:57,846 INFO [trainer.py:765] (1/8) Epoch 25, batch 2500, train_loss[loss=2.85, NarTop10Accuracy=0.7566, over 5037.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7108, over 5495.33 frames. ], batch size: 7, lr: 3.39e-03
2024-08-06 20:06:18,019 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 20:07:19,303 INFO [trainer.py:765] (1/8) Epoch 26, batch 100, train_loss[loss=3.017, NarTop10Accuracy=0.7207, over 7428.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.7051, over 2364.42 frames. ], batch size: 31, lr: 3.32e-03
2024-08-06 20:07:52,381 INFO [trainer.py:765] (1/8) Epoch 26, batch 200, train_loss[loss=2.764, NarTop10Accuracy=0.7701, over 6828.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7069, over 3861.79 frames. ], batch size: 17, lr: 3.31e-03
2024-08-06 20:08:24,732 INFO [trainer.py:765] (1/8) Epoch 26, batch 300, train_loss[loss=2.942, NarTop10Accuracy=0.7344, over 6837.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.708, over 4660.03 frames. ], batch size: 22, lr: 3.31e-03
2024-08-06 20:08:58,184 INFO [trainer.py:765] (1/8) Epoch 26, batch 400, train_loss[loss=3.077, NarTop10Accuracy=0.7163, over 5043.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7077, over 5087.19 frames. ], batch size: 7, lr: 3.31e-03
2024-08-06 20:09:33,146 INFO [trainer.py:765] (1/8) Epoch 26, batch 500, train_loss[loss=2.809, NarTop10Accuracy=0.7651, over 6024.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7074, over 5369.65 frames. ], batch size: 11, lr: 3.30e-03
2024-08-06 20:10:03,890 INFO [trainer.py:765] (1/8) Epoch 26, batch 600, train_loss[loss=2.744, NarTop10Accuracy=0.7745, over 5748.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7115, over 5633.52 frames. ], batch size: 9, lr: 3.30e-03
2024-08-06 20:10:39,872 INFO [trainer.py:765] (1/8) Epoch 26, batch 700, train_loss[loss=3.022, NarTop10Accuracy=0.7263, over 5217.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.707, over 5710.08 frames. ], batch size: 6, lr: 3.30e-03
2024-08-06 20:11:19,060 INFO [trainer.py:765] (1/8) Epoch 26, batch 800, train_loss[loss=2.958, NarTop10Accuracy=0.7281, over 4347.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.707, over 5762.91 frames. ], batch size: 5, lr: 3.30e-03
2024-08-06 20:11:49,314 INFO [trainer.py:765] (1/8) Epoch 26, batch 900, train_loss[loss=2.927, NarTop10Accuracy=0.7427, over 6777.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7079, over 5797.55 frames. ], batch size: 14, lr: 3.29e-03
2024-08-06 20:12:25,972 INFO [trainer.py:765] (1/8) Epoch 26, batch 1000, train_loss[loss=2.713, NarTop10Accuracy=0.7789, over 6609.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7072, over 5918.45 frames. ], batch size: 14, lr: 3.29e-03
2024-08-06 20:13:06,376 INFO [trainer.py:765] (1/8) Epoch 26, batch 1100, train_loss[loss=3.37, NarTop10Accuracy=0.6495, over 6744.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7059, over 5926.57 frames. ], batch size: 17, lr: 3.29e-03
2024-08-06 20:13:37,535 INFO [trainer.py:765] (1/8) Epoch 26, batch 1200, train_loss[loss=3.404, NarTop10Accuracy=0.6437, over 7311.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7085, over 5933.32 frames. ], batch size: 31, lr: 3.29e-03
2024-08-06 20:14:13,694 INFO [trainer.py:765] (1/8) Epoch 26, batch 1300, train_loss[loss=2.861, NarTop10Accuracy=0.7464, over 5187.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7089, over 5991.39 frames. ], batch size: 6, lr: 3.28e-03
2024-08-06 20:14:50,538 INFO [trainer.py:765] (1/8) Epoch 26, batch 1400, train_loss[loss=2.788, NarTop10Accuracy=0.7674, over 6060.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7077, over 6017.15 frames. ], batch size: 11, lr: 3.28e-03
2024-08-06 20:15:21,154 INFO [trainer.py:765] (1/8) Epoch 26, batch 1500, train_loss[loss=3.19, NarTop10Accuracy=0.6817, over 5979.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7083, over 5937.23 frames. ], batch size: 51, lr: 3.28e-03
2024-08-06 20:15:48,978 INFO [trainer.py:765] (1/8) Epoch 26, batch 1600, train_loss[loss=3.035, NarTop10Accuracy=0.7225, over 7158.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.71, over 5921.08 frames. ], batch size: 22, lr: 3.28e-03
2024-08-06 20:15:50,001 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 20:15:58,239 INFO [trainer.py:811] (1/8) Epoch 26, validation: loss=2.899, NarTop10Accuracy=0.7457, over 1905321.00 frames. 
2024-08-06 20:15:58,239 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29627MB
2024-08-06 20:15:58,779 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.752e+02 2.166e+02 2.322e+02 2.511e+02 3.952e+02, threshold=4.644e+02, percent-clipped=0.0
2024-08-06 20:16:23,951 INFO [trainer.py:765] (1/8) Epoch 26, batch 1700, train_loss[loss=3.19, NarTop10Accuracy=0.6956, over 6252.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7122, over 5921.63 frames. ], batch size: 13, lr: 3.28e-03
2024-08-06 20:16:50,426 INFO [trainer.py:765] (1/8) Epoch 26, batch 1800, train_loss[loss=2.76, NarTop10Accuracy=0.7709, over 7245.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7117, over 5990.87 frames. ], batch size: 22, lr: 3.27e-03
2024-08-06 20:17:16,839 INFO [trainer.py:765] (1/8) Epoch 26, batch 1900, train_loss[loss=3.022, NarTop10Accuracy=0.7265, over 6249.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7098, over 6019.41 frames. ], batch size: 50, lr: 3.27e-03
2024-08-06 20:17:42,379 INFO [trainer.py:765] (1/8) Epoch 26, batch 2000, train_loss[loss=3.582, NarTop10Accuracy=0.6093, over 6162.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7086, over 5996.24 frames. ], batch size: 50, lr: 3.27e-03
2024-08-06 20:18:07,563 INFO [trainer.py:765] (1/8) Epoch 26, batch 2100, train_loss[loss=3.133, NarTop10Accuracy=0.71, over 3900.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7058, over 5979.96 frames. ], batch size: 4, lr: 3.27e-03
2024-08-06 20:18:32,776 INFO [trainer.py:765] (1/8) Epoch 26, batch 2200, train_loss[loss=2.943, NarTop10Accuracy=0.7337, over 7506.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7067, over 6004.32 frames. ], batch size: 31, lr: 3.26e-03
2024-08-06 20:18:57,897 INFO [trainer.py:765] (1/8) Epoch 26, batch 2300, train_loss[loss=3.165, NarTop10Accuracy=0.6968, over 5604.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7061, over 6019.15 frames. ], batch size: 9, lr: 3.26e-03
2024-08-06 20:19:22,205 INFO [trainer.py:765] (1/8) Epoch 26, batch 2400, train_loss[loss=2.718, NarTop10Accuracy=0.7829, over 5019.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.711, over 5773.32 frames. ], batch size: 7, lr: 3.26e-03
2024-08-06 20:19:45,651 INFO [trainer.py:765] (1/8) Epoch 26, batch 2500, train_loss[loss=2.731, NarTop10Accuracy=0.7799, over 5124.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7149, over 5477.79 frames. ], batch size: 7, lr: 3.26e-03
2024-08-06 20:20:06,240 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 20:21:04,873 INFO [trainer.py:765] (1/8) Epoch 27, batch 100, train_loss[loss=3.232, NarTop10Accuracy=0.6787, over 7218.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7088, over 2366.36 frames. ], batch size: 31, lr: 3.19e-03
2024-08-06 20:21:39,783 INFO [trainer.py:765] (1/8) Epoch 27, batch 200, train_loss[loss=2.765, NarTop10Accuracy=0.7621, over 6684.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7084, over 3856.79 frames. ], batch size: 17, lr: 3.19e-03
2024-08-06 20:22:13,049 INFO [trainer.py:765] (1/8) Epoch 27, batch 300, train_loss[loss=2.893, NarTop10Accuracy=0.7462, over 7431.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7106, over 4652.56 frames. ], batch size: 23, lr: 3.18e-03
2024-08-06 20:22:43,556 INFO [trainer.py:765] (1/8) Epoch 27, batch 400, train_loss[loss=2.898, NarTop10Accuracy=0.7441, over 5043.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7111, over 5109.12 frames. ], batch size: 7, lr: 3.18e-03
2024-08-06 20:23:18,083 INFO [trainer.py:765] (1/8) Epoch 27, batch 500, train_loss[loss=2.798, NarTop10Accuracy=0.7589, over 6042.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7145, over 5370.90 frames. ], batch size: 11, lr: 3.18e-03
2024-08-06 20:23:51,434 INFO [trainer.py:765] (1/8) Epoch 27, batch 600, train_loss[loss=3.244, NarTop10Accuracy=0.6771, over 5760.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7153, over 5646.03 frames. ], batch size: 9, lr: 3.18e-03
2024-08-06 20:24:24,975 INFO [trainer.py:765] (1/8) Epoch 27, batch 700, train_loss[loss=2.833, NarTop10Accuracy=0.7664, over 5091.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7151, over 5705.19 frames. ], batch size: 6, lr: 3.18e-03
2024-08-06 20:25:03,407 INFO [trainer.py:765] (1/8) Epoch 27, batch 800, train_loss[loss=3.146, NarTop10Accuracy=0.6959, over 5142.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7108, over 5775.74 frames. ], batch size: 6, lr: 3.17e-03
2024-08-06 20:25:34,176 INFO [trainer.py:765] (1/8) Epoch 27, batch 900, train_loss[loss=3.209, NarTop10Accuracy=0.6807, over 6120.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7104, over 5797.37 frames. ], batch size: 13, lr: 3.17e-03
2024-08-06 20:26:10,096 INFO [trainer.py:765] (1/8) Epoch 27, batch 1000, train_loss[loss=2.721, NarTop10Accuracy=0.787, over 6681.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7089, over 5902.93 frames. ], batch size: 14, lr: 3.17e-03
2024-08-06 20:26:18,313 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 20:26:26,346 INFO [trainer.py:811] (1/8) Epoch 27, validation: loss=2.95, NarTop10Accuracy=0.735, over 1905321.00 frames. 
2024-08-06 20:26:26,347 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29627MB
2024-08-06 20:26:26,878 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.789e+02 2.166e+02 2.331e+02 2.512e+02 4.284e+02, threshold=4.663e+02, percent-clipped=0.0
2024-08-06 20:26:50,899 INFO [trainer.py:765] (1/8) Epoch 27, batch 1100, train_loss[loss=2.985, NarTop10Accuracy=0.7321, over 6867.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7092, over 5939.25 frames. ], batch size: 17, lr: 3.17e-03
2024-08-06 20:27:24,545 INFO [trainer.py:765] (1/8) Epoch 27, batch 1200, train_loss[loss=2.813, NarTop10Accuracy=0.7674, over 7578.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7109, over 5934.02 frames. ], batch size: 32, lr: 3.16e-03
2024-08-06 20:27:58,568 INFO [trainer.py:765] (1/8) Epoch 27, batch 1300, train_loss[loss=2.733, NarTop10Accuracy=0.7733, over 4305.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.712, over 5994.31 frames. ], batch size: 5, lr: 3.16e-03
2024-08-06 20:28:36,745 INFO [trainer.py:765] (1/8) Epoch 27, batch 1400, train_loss[loss=3.16, NarTop10Accuracy=0.6856, over 6168.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7083, over 6023.75 frames. ], batch size: 11, lr: 3.16e-03
2024-08-06 20:29:04,633 INFO [trainer.py:765] (1/8) Epoch 27, batch 1500, train_loss[loss=3.08, NarTop10Accuracy=0.7068, over 5673.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7091, over 5958.39 frames. ], batch size: 50, lr: 3.16e-03
2024-08-06 20:29:32,362 INFO [trainer.py:765] (1/8) Epoch 27, batch 1600, train_loss[loss=2.917, NarTop10Accuracy=0.7447, over 7251.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.708, over 5935.62 frames. ], batch size: 23, lr: 3.15e-03
2024-08-06 20:29:58,977 INFO [trainer.py:765] (1/8) Epoch 27, batch 1700, train_loss[loss=3.149, NarTop10Accuracy=0.6894, over 6324.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7092, over 5917.51 frames. ], batch size: 13, lr: 3.15e-03
2024-08-06 20:30:25,463 INFO [trainer.py:765] (1/8) Epoch 27, batch 1800, train_loss[loss=3.496, NarTop10Accuracy=0.6237, over 7089.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7085, over 5977.84 frames. ], batch size: 22, lr: 3.15e-03
2024-08-06 20:30:51,845 INFO [trainer.py:765] (1/8) Epoch 27, batch 1900, train_loss[loss=3.059, NarTop10Accuracy=0.7159, over 5550.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7084, over 6027.87 frames. ], batch size: 50, lr: 3.15e-03
2024-08-06 20:31:17,390 INFO [trainer.py:765] (1/8) Epoch 27, batch 2000, train_loss[loss=3.059, NarTop10Accuracy=0.7229, over 5751.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7115, over 5994.08 frames. ], batch size: 50, lr: 3.15e-03
2024-08-06 20:31:42,660 INFO [trainer.py:765] (1/8) Epoch 27, batch 2100, train_loss[loss=2.796, NarTop10Accuracy=0.7666, over 3843.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.711, over 5946.01 frames. ], batch size: 4, lr: 3.14e-03
2024-08-06 20:32:07,804 INFO [trainer.py:765] (1/8) Epoch 27, batch 2200, train_loss[loss=3.378, NarTop10Accuracy=0.6448, over 7332.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7088, over 6003.89 frames. ], batch size: 32, lr: 3.14e-03
2024-08-06 20:32:32,942 INFO [trainer.py:765] (1/8) Epoch 27, batch 2300, train_loss[loss=2.695, NarTop10Accuracy=0.7814, over 5745.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7081, over 6007.16 frames. ], batch size: 9, lr: 3.14e-03
2024-08-06 20:32:57,246 INFO [trainer.py:765] (1/8) Epoch 27, batch 2400, train_loss[loss=2.76, NarTop10Accuracy=0.7708, over 5175.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7068, over 5769.21 frames. ], batch size: 7, lr: 3.14e-03
2024-08-06 20:33:20,615 INFO [trainer.py:765] (1/8) Epoch 27, batch 2500, train_loss[loss=3.403, NarTop10Accuracy=0.6476, over 5133.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7136, over 5470.51 frames. ], batch size: 7, lr: 3.13e-03
2024-08-06 20:33:40,626 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 20:34:35,830 INFO [trainer.py:765] (1/8) Epoch 28, batch 100, train_loss[loss=2.793, NarTop10Accuracy=0.7599, over 7290.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7094, over 2363.08 frames. ], batch size: 31, lr: 3.07e-03
2024-08-06 20:35:07,393 INFO [trainer.py:765] (1/8) Epoch 28, batch 200, train_loss[loss=2.816, NarTop10Accuracy=0.7642, over 6717.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.709, over 3865.88 frames. ], batch size: 17, lr: 3.07e-03
2024-08-06 20:35:45,422 INFO [trainer.py:765] (1/8) Epoch 28, batch 300, train_loss[loss=3.156, NarTop10Accuracy=0.6934, over 7011.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7108, over 4673.68 frames. ], batch size: 22, lr: 3.07e-03
2024-08-06 20:36:15,865 INFO [trainer.py:765] (1/8) Epoch 28, batch 400, train_loss[loss=3.197, NarTop10Accuracy=0.6757, over 5118.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7082, over 5116.48 frames. ], batch size: 7, lr: 3.07e-03
2024-08-06 20:36:32,407 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 20:36:40,530 INFO [trainer.py:811] (1/8) Epoch 28, validation: loss=2.963, NarTop10Accuracy=0.7327, over 1905321.00 frames. 
2024-08-06 20:36:40,531 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29627MB
2024-08-06 20:36:41,102 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.761e+02 2.179e+02 2.348e+02 2.536e+02 3.573e+02, threshold=4.696e+02, percent-clipped=0.0
2024-08-06 20:36:56,664 INFO [trainer.py:765] (1/8) Epoch 28, batch 500, train_loss[loss=3.25, NarTop10Accuracy=0.6723, over 6114.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7104, over 5406.14 frames. ], batch size: 11, lr: 3.06e-03
2024-08-06 20:37:29,463 INFO [trainer.py:765] (1/8) Epoch 28, batch 600, train_loss[loss=3.005, NarTop10Accuracy=0.719, over 5748.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7099, over 5663.72 frames. ], batch size: 9, lr: 3.06e-03
2024-08-06 20:38:08,891 INFO [trainer.py:765] (1/8) Epoch 28, batch 700, train_loss[loss=3.103, NarTop10Accuracy=0.7026, over 4938.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.709, over 5733.50 frames. ], batch size: 6, lr: 3.06e-03
2024-08-06 20:38:42,489 INFO [trainer.py:765] (1/8) Epoch 28, batch 800, train_loss[loss=2.913, NarTop10Accuracy=0.7445, over 5037.00 frames. ], tot_loss[loss=3.062, NarTop10Accuracy=0.7133, over 5801.39 frames. ], batch size: 6, lr: 3.06e-03
2024-08-06 20:39:15,507 INFO [trainer.py:765] (1/8) Epoch 28, batch 900, train_loss[loss=3.259, NarTop10Accuracy=0.6739, over 6153.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7136, over 5803.08 frames. ], batch size: 13, lr: 3.06e-03
2024-08-06 20:39:53,241 INFO [trainer.py:765] (1/8) Epoch 28, batch 1000, train_loss[loss=3.139, NarTop10Accuracy=0.7096, over 6618.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.714, over 5909.67 frames. ], batch size: 14, lr: 3.05e-03
2024-08-06 20:40:25,868 INFO [trainer.py:765] (1/8) Epoch 28, batch 1100, train_loss[loss=2.772, NarTop10Accuracy=0.781, over 6804.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7105, over 5955.71 frames. ], batch size: 17, lr: 3.05e-03
2024-08-06 20:40:59,419 INFO [trainer.py:765] (1/8) Epoch 28, batch 1200, train_loss[loss=3.186, NarTop10Accuracy=0.6822, over 7374.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.71, over 5962.09 frames. ], batch size: 31, lr: 3.05e-03
2024-08-06 20:41:38,681 INFO [trainer.py:765] (1/8) Epoch 28, batch 1300, train_loss[loss=3.107, NarTop10Accuracy=0.7032, over 4242.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7104, over 6009.63 frames. ], batch size: 5, lr: 3.05e-03
2024-08-06 20:42:13,048 INFO [trainer.py:765] (1/8) Epoch 28, batch 1400, train_loss[loss=3.049, NarTop10Accuracy=0.7225, over 5970.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7085, over 6039.80 frames. ], batch size: 11, lr: 3.04e-03
2024-08-06 20:42:43,171 INFO [trainer.py:765] (1/8) Epoch 28, batch 1500, train_loss[loss=3.411, NarTop10Accuracy=0.6474, over 6228.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7107, over 5950.63 frames. ], batch size: 50, lr: 3.04e-03
2024-08-06 20:43:11,081 INFO [trainer.py:765] (1/8) Epoch 28, batch 1600, train_loss[loss=2.918, NarTop10Accuracy=0.7464, over 7365.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.711, over 5944.98 frames. ], batch size: 23, lr: 3.04e-03
2024-08-06 20:43:37,786 INFO [trainer.py:765] (1/8) Epoch 28, batch 1700, train_loss[loss=2.968, NarTop10Accuracy=0.7396, over 6294.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7097, over 5923.97 frames. ], batch size: 13, lr: 3.04e-03
2024-08-06 20:44:04,326 INFO [trainer.py:765] (1/8) Epoch 28, batch 1800, train_loss[loss=3.15, NarTop10Accuracy=0.6911, over 6960.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7109, over 5994.42 frames. ], batch size: 22, lr: 3.04e-03
2024-08-06 20:44:30,757 INFO [trainer.py:765] (1/8) Epoch 28, batch 1900, train_loss[loss=3.051, NarTop10Accuracy=0.7198, over 5928.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7108, over 6025.63 frames. ], batch size: 50, lr: 3.03e-03
2024-08-06 20:44:56,329 INFO [trainer.py:765] (1/8) Epoch 28, batch 2000, train_loss[loss=3.04, NarTop10Accuracy=0.721, over 5979.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7127, over 5987.64 frames. ], batch size: 50, lr: 3.03e-03
2024-08-06 20:45:21,651 INFO [trainer.py:765] (1/8) Epoch 28, batch 2100, train_loss[loss=2.983, NarTop10Accuracy=0.7398, over 3990.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7134, over 5988.67 frames. ], batch size: 4, lr: 3.03e-03
2024-08-06 20:45:47,077 INFO [trainer.py:765] (1/8) Epoch 28, batch 2200, train_loss[loss=2.893, NarTop10Accuracy=0.7515, over 7257.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7121, over 6014.21 frames. ], batch size: 31, lr: 3.03e-03
2024-08-06 20:46:12,308 INFO [trainer.py:765] (1/8) Epoch 28, batch 2300, train_loss[loss=3.527, NarTop10Accuracy=0.6145, over 5718.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7073, over 6025.74 frames. ], batch size: 9, lr: 3.03e-03
2024-08-06 20:46:36,807 INFO [trainer.py:765] (1/8) Epoch 28, batch 2400, train_loss[loss=2.931, NarTop10Accuracy=0.7389, over 5103.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7074, over 5777.83 frames. ], batch size: 7, lr: 3.02e-03
2024-08-06 20:46:48,595 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 20:46:56,604 INFO [trainer.py:811] (1/8) Epoch 28, validation: loss=2.931, NarTop10Accuracy=0.7396, over 1905321.00 frames. 
2024-08-06 20:46:56,605 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29627MB
2024-08-06 20:46:57,081 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.745e+02 2.201e+02 2.381e+02 2.551e+02 4.872e+02, threshold=4.762e+02, percent-clipped=0.1
2024-08-06 20:47:08,292 INFO [trainer.py:765] (1/8) Epoch 28, batch 2500, train_loss[loss=3.093, NarTop10Accuracy=0.7008, over 5115.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7117, over 5470.36 frames. ], batch size: 7, lr: 3.02e-03
2024-08-06 20:47:28,310 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 20:48:21,052 INFO [trainer.py:765] (1/8) Epoch 29, batch 100, train_loss[loss=3.016, NarTop10Accuracy=0.7261, over 7410.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7096, over 2351.97 frames. ], batch size: 31, lr: 2.96e-03
2024-08-06 20:48:53,405 INFO [trainer.py:765] (1/8) Epoch 29, batch 200, train_loss[loss=3.125, NarTop10Accuracy=0.7001, over 6945.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7165, over 3838.68 frames. ], batch size: 17, lr: 2.96e-03
2024-08-06 20:49:27,476 INFO [trainer.py:765] (1/8) Epoch 29, batch 300, train_loss[loss=3.059, NarTop10Accuracy=0.7137, over 7059.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7181, over 4645.34 frames. ], batch size: 22, lr: 2.96e-03
2024-08-06 20:49:56,052 INFO [trainer.py:765] (1/8) Epoch 29, batch 400, train_loss[loss=3.373, NarTop10Accuracy=0.6456, over 5778.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7125, over 5110.65 frames. ], batch size: 8, lr: 2.96e-03
2024-08-06 20:50:29,435 INFO [trainer.py:765] (1/8) Epoch 29, batch 500, train_loss[loss=3.174, NarTop10Accuracy=0.6909, over 6147.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7152, over 5401.59 frames. ], batch size: 11, lr: 2.96e-03
2024-08-06 20:51:00,023 INFO [trainer.py:765] (1/8) Epoch 29, batch 600, train_loss[loss=2.79, NarTop10Accuracy=0.7774, over 5664.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7153, over 5641.89 frames. ], batch size: 9, lr: 2.95e-03
2024-08-06 20:51:35,677 INFO [trainer.py:765] (1/8) Epoch 29, batch 700, train_loss[loss=2.822, NarTop10Accuracy=0.7551, over 5001.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7099, over 5709.05 frames. ], batch size: 6, lr: 2.95e-03
2024-08-06 20:52:10,724 INFO [trainer.py:765] (1/8) Epoch 29, batch 800, train_loss[loss=2.679, NarTop10Accuracy=0.7864, over 4230.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7105, over 5754.37 frames. ], batch size: 5, lr: 2.95e-03
2024-08-06 20:52:40,742 INFO [trainer.py:765] (1/8) Epoch 29, batch 900, train_loss[loss=2.813, NarTop10Accuracy=0.7644, over 6693.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7094, over 5790.76 frames. ], batch size: 14, lr: 2.95e-03
2024-08-06 20:53:16,861 INFO [trainer.py:765] (1/8) Epoch 29, batch 1000, train_loss[loss=3.434, NarTop10Accuracy=0.6325, over 6654.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7073, over 5895.51 frames. ], batch size: 14, lr: 2.95e-03
2024-08-06 20:53:52,902 INFO [trainer.py:765] (1/8) Epoch 29, batch 1100, train_loss[loss=3.037, NarTop10Accuracy=0.706, over 6696.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7067, over 5928.11 frames. ], batch size: 17, lr: 2.94e-03
2024-08-06 20:54:23,690 INFO [trainer.py:765] (1/8) Epoch 29, batch 1200, train_loss[loss=3.007, NarTop10Accuracy=0.7228, over 7437.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.708, over 5912.68 frames. ], batch size: 31, lr: 2.94e-03
2024-08-06 20:55:01,428 INFO [trainer.py:765] (1/8) Epoch 29, batch 1300, train_loss[loss=3.088, NarTop10Accuracy=0.7082, over 5055.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.709, over 5985.53 frames. ], batch size: 6, lr: 2.94e-03
2024-08-06 20:55:32,557 INFO [trainer.py:765] (1/8) Epoch 29, batch 1400, train_loss[loss=3.294, NarTop10Accuracy=0.6515, over 6039.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7089, over 6016.89 frames. ], batch size: 11, lr: 2.94e-03
2024-08-06 20:56:04,359 INFO [trainer.py:765] (1/8) Epoch 29, batch 1500, train_loss[loss=3.367, NarTop10Accuracy=0.6511, over 6114.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7093, over 5941.46 frames. ], batch size: 50, lr: 2.94e-03
2024-08-06 20:56:32,040 INFO [trainer.py:765] (1/8) Epoch 29, batch 1600, train_loss[loss=3.35, NarTop10Accuracy=0.6634, over 6897.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7085, over 5935.42 frames. ], batch size: 22, lr: 2.93e-03
2024-08-06 20:56:58,639 INFO [trainer.py:765] (1/8) Epoch 29, batch 1700, train_loss[loss=2.859, NarTop10Accuracy=0.7583, over 6612.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7106, over 5928.18 frames. ], batch size: 14, lr: 2.93e-03
2024-08-06 20:57:25,000 INFO [trainer.py:765] (1/8) Epoch 29, batch 1800, train_loss[loss=3.14, NarTop10Accuracy=0.6906, over 7020.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7118, over 5981.88 frames. ], batch size: 22, lr: 2.93e-03
2024-08-06 20:57:44,621 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 20:57:52,863 INFO [trainer.py:811] (1/8) Epoch 29, validation: loss=2.897, NarTop10Accuracy=0.7458, over 1905321.00 frames. 
2024-08-06 20:57:52,864 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29627MB
2024-08-06 20:57:53,424 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.772e+02 2.206e+02 2.380e+02 2.554e+02 4.464e+02, threshold=4.759e+02, percent-clipped=0.0
2024-08-06 20:57:59,756 INFO [trainer.py:765] (1/8) Epoch 29, batch 1900, train_loss[loss=2.99, NarTop10Accuracy=0.7323, over 6405.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7086, over 6030.95 frames. ], batch size: 52, lr: 2.93e-03
2024-08-06 20:58:25,308 INFO [trainer.py:765] (1/8) Epoch 29, batch 2000, train_loss[loss=3.412, NarTop10Accuracy=0.6483, over 6471.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7086, over 6005.66 frames. ], batch size: 50, lr: 2.93e-03
2024-08-06 20:58:50,629 INFO [trainer.py:765] (1/8) Epoch 29, batch 2100, train_loss[loss=2.941, NarTop10Accuracy=0.7425, over 3921.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7082, over 5965.43 frames. ], batch size: 4, lr: 2.92e-03
2024-08-06 20:59:15,805 INFO [trainer.py:765] (1/8) Epoch 29, batch 2200, train_loss[loss=2.943, NarTop10Accuracy=0.7411, over 7131.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7096, over 6002.47 frames. ], batch size: 31, lr: 2.92e-03
2024-08-06 20:59:40,910 INFO [trainer.py:765] (1/8) Epoch 29, batch 2300, train_loss[loss=2.899, NarTop10Accuracy=0.7417, over 5823.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.706, over 6023.72 frames. ], batch size: 9, lr: 2.92e-03
2024-08-06 21:00:05,155 INFO [trainer.py:765] (1/8) Epoch 29, batch 2400, train_loss[loss=2.693, NarTop10Accuracy=0.7854, over 5172.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7094, over 5804.51 frames. ], batch size: 7, lr: 2.92e-03
2024-08-06 21:00:28,741 INFO [trainer.py:765] (1/8) Epoch 29, batch 2500, train_loss[loss=3.316, NarTop10Accuracy=0.6561, over 5178.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7137, over 5501.74 frames. ], batch size: 7, lr: 2.92e-03
2024-08-06 21:00:48,843 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 21:01:41,717 INFO [trainer.py:765] (1/8) Epoch 30, batch 100, train_loss[loss=2.863, NarTop10Accuracy=0.747, over 7194.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.721, over 2365.50 frames. ], batch size: 31, lr: 2.86e-03
2024-08-06 21:02:17,014 INFO [trainer.py:765] (1/8) Epoch 30, batch 200, train_loss[loss=3.029, NarTop10Accuracy=0.7179, over 6816.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7229, over 3853.40 frames. ], batch size: 17, lr: 2.86e-03
2024-08-06 21:02:51,343 INFO [trainer.py:765] (1/8) Epoch 30, batch 300, train_loss[loss=3.072, NarTop10Accuracy=0.7135, over 6987.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7237, over 4656.20 frames. ], batch size: 22, lr: 2.86e-03
2024-08-06 21:03:21,643 INFO [trainer.py:765] (1/8) Epoch 30, batch 400, train_loss[loss=2.692, NarTop10Accuracy=0.7895, over 5085.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.721, over 5112.05 frames. ], batch size: 7, lr: 2.86e-03
2024-08-06 21:03:58,546 INFO [trainer.py:765] (1/8) Epoch 30, batch 500, train_loss[loss=3.161, NarTop10Accuracy=0.6833, over 5961.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7186, over 5385.74 frames. ], batch size: 11, lr: 2.86e-03
2024-08-06 21:04:31,657 INFO [trainer.py:765] (1/8) Epoch 30, batch 600, train_loss[loss=3.038, NarTop10Accuracy=0.7222, over 5751.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7173, over 5640.07 frames. ], batch size: 9, lr: 2.85e-03
2024-08-06 21:05:03,526 INFO [trainer.py:765] (1/8) Epoch 30, batch 700, train_loss[loss=3.027, NarTop10Accuracy=0.728, over 5085.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7197, over 5710.99 frames. ], batch size: 6, lr: 2.85e-03
2024-08-06 21:05:44,132 INFO [trainer.py:765] (1/8) Epoch 30, batch 800, train_loss[loss=2.914, NarTop10Accuracy=0.7315, over 4962.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7199, over 5753.61 frames. ], batch size: 6, lr: 2.85e-03
2024-08-06 21:06:14,844 INFO [trainer.py:765] (1/8) Epoch 30, batch 900, train_loss[loss=2.883, NarTop10Accuracy=0.7548, over 6579.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7202, over 5772.61 frames. ], batch size: 14, lr: 2.85e-03
2024-08-06 21:06:48,952 INFO [trainer.py:765] (1/8) Epoch 30, batch 1000, train_loss[loss=2.953, NarTop10Accuracy=0.7338, over 6741.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7129, over 5870.92 frames. ], batch size: 14, lr: 2.85e-03
2024-08-06 21:07:25,937 INFO [trainer.py:765] (1/8) Epoch 30, batch 1100, train_loss[loss=3.476, NarTop10Accuracy=0.6357, over 6942.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7106, over 5905.53 frames. ], batch size: 17, lr: 2.84e-03
2024-08-06 21:08:02,381 INFO [trainer.py:765] (1/8) Epoch 30, batch 1200, train_loss[loss=2.989, NarTop10Accuracy=0.7295, over 7317.00 frames. ], tot_loss[loss=3.062, NarTop10Accuracy=0.7122, over 5915.49 frames. ], batch size: 33, lr: 2.84e-03
2024-08-06 21:08:35,371 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 21:08:43,457 INFO [trainer.py:811] (1/8) Epoch 30, validation: loss=2.93, NarTop10Accuracy=0.7391, over 1905321.00 frames. 
2024-08-06 21:08:43,458 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29627MB
2024-08-06 21:08:44,197 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.770e+02 2.209e+02 2.377e+02 2.553e+02 3.956e+02, threshold=4.754e+02, percent-clipped=0.0
2024-08-06 21:08:44,203 INFO [trainer.py:765] (1/8) Epoch 30, batch 1300, train_loss[loss=3.077, NarTop10Accuracy=0.7174, over 4239.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7125, over 5988.54 frames. ], batch size: 5, lr: 2.84e-03
2024-08-06 21:09:22,397 INFO [trainer.py:765] (1/8) Epoch 30, batch 1400, train_loss[loss=2.89, NarTop10Accuracy=0.7472, over 6174.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7109, over 6024.67 frames. ], batch size: 11, lr: 2.84e-03
2024-08-06 21:09:52,373 INFO [trainer.py:765] (1/8) Epoch 30, batch 1500, train_loss[loss=3.036, NarTop10Accuracy=0.7172, over 6102.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7114, over 5959.65 frames. ], batch size: 50, lr: 2.84e-03
2024-08-06 21:10:20,084 INFO [trainer.py:765] (1/8) Epoch 30, batch 1600, train_loss[loss=2.993, NarTop10Accuracy=0.7313, over 6945.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7117, over 5945.51 frames. ], batch size: 22, lr: 2.84e-03
2024-08-06 21:10:46,680 INFO [trainer.py:765] (1/8) Epoch 30, batch 1700, train_loss[loss=3.203, NarTop10Accuracy=0.6805, over 6147.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7093, over 5908.89 frames. ], batch size: 13, lr: 2.83e-03
2024-08-06 21:11:13,059 INFO [trainer.py:765] (1/8) Epoch 30, batch 1800, train_loss[loss=3.403, NarTop10Accuracy=0.6375, over 7062.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7098, over 5979.15 frames. ], batch size: 22, lr: 2.83e-03
2024-08-06 21:11:39,419 INFO [trainer.py:765] (1/8) Epoch 30, batch 1900, train_loss[loss=3.049, NarTop10Accuracy=0.7167, over 6333.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7097, over 6032.95 frames. ], batch size: 50, lr: 2.83e-03
2024-08-06 21:12:04,826 INFO [trainer.py:765] (1/8) Epoch 30, batch 2000, train_loss[loss=3.375, NarTop10Accuracy=0.6458, over 6231.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7119, over 6009.01 frames. ], batch size: 50, lr: 2.83e-03
2024-08-06 21:12:30,088 INFO [trainer.py:765] (1/8) Epoch 30, batch 2100, train_loss[loss=2.919, NarTop10Accuracy=0.7476, over 4794.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7103, over 5986.02 frames. ], batch size: 5, lr: 2.83e-03
2024-08-06 21:12:55,225 INFO [trainer.py:765] (1/8) Epoch 30, batch 2200, train_loss[loss=3.046, NarTop10Accuracy=0.7249, over 7359.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7111, over 6018.75 frames. ], batch size: 31, lr: 2.82e-03
2024-08-06 21:13:20,298 INFO [trainer.py:765] (1/8) Epoch 30, batch 2300, train_loss[loss=2.75, NarTop10Accuracy=0.7806, over 5688.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7073, over 6031.16 frames. ], batch size: 9, lr: 2.82e-03
2024-08-06 21:13:44,491 INFO [trainer.py:765] (1/8) Epoch 30, batch 2400, train_loss[loss=2.812, NarTop10Accuracy=0.7672, over 5097.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7145, over 5776.45 frames. ], batch size: 7, lr: 2.82e-03
2024-08-06 21:14:07,988 INFO [trainer.py:765] (1/8) Epoch 30, batch 2500, train_loss[loss=2.899, NarTop10Accuracy=0.7382, over 5070.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7157, over 5486.72 frames. ], batch size: 7, lr: 2.82e-03
2024-08-06 21:14:27,907 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 21:15:23,633 INFO [trainer.py:765] (1/8) Epoch 31, batch 100, train_loss[loss=3.531, NarTop10Accuracy=0.61, over 7197.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.713, over 2372.72 frames. ], batch size: 31, lr: 2.77e-03
2024-08-06 21:15:55,127 INFO [trainer.py:765] (1/8) Epoch 31, batch 200, train_loss[loss=2.941, NarTop10Accuracy=0.7436, over 6756.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.717, over 3857.65 frames. ], batch size: 17, lr: 2.77e-03
2024-08-06 21:16:31,215 INFO [trainer.py:765] (1/8) Epoch 31, batch 300, train_loss[loss=2.917, NarTop10Accuracy=0.7462, over 7092.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7175, over 4663.60 frames. ], batch size: 22, lr: 2.77e-03
2024-08-06 21:17:01,624 INFO [trainer.py:765] (1/8) Epoch 31, batch 400, train_loss[loss=3.268, NarTop10Accuracy=0.6745, over 5142.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7156, over 5107.84 frames. ], batch size: 7, lr: 2.76e-03
2024-08-06 21:17:35,724 INFO [trainer.py:765] (1/8) Epoch 31, batch 500, train_loss[loss=2.705, NarTop10Accuracy=0.7835, over 6180.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7179, over 5390.94 frames. ], batch size: 11, lr: 2.76e-03
2024-08-06 21:18:07,083 INFO [trainer.py:765] (1/8) Epoch 31, batch 600, train_loss[loss=2.812, NarTop10Accuracy=0.7733, over 5643.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7147, over 5668.89 frames. ], batch size: 9, lr: 2.76e-03
2024-08-06 21:18:44,610 INFO [trainer.py:765] (1/8) Epoch 31, batch 700, train_loss[loss=3.418, NarTop10Accuracy=0.632, over 4242.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7135, over 5725.38 frames. ], batch size: 5, lr: 2.76e-03
2024-08-06 21:18:51,095 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 21:18:59,276 INFO [trainer.py:811] (1/8) Epoch 31, validation: loss=2.984, NarTop10Accuracy=0.7279, over 1905321.00 frames. 
2024-08-06 21:18:59,277 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29627MB
2024-08-06 21:18:59,985 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.824e+02 2.222e+02 2.378e+02 2.557e+02 4.306e+02, threshold=4.755e+02, percent-clipped=0.0
2024-08-06 21:19:24,246 INFO [trainer.py:765] (1/8) Epoch 31, batch 800, train_loss[loss=2.804, NarTop10Accuracy=0.7754, over 4290.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7161, over 5789.20 frames. ], batch size: 5, lr: 2.76e-03
2024-08-06 21:19:56,951 INFO [trainer.py:765] (1/8) Epoch 31, batch 900, train_loss[loss=3.306, NarTop10Accuracy=0.6609, over 6273.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7166, over 5799.88 frames. ], batch size: 13, lr: 2.76e-03
2024-08-06 21:20:33,311 INFO [trainer.py:765] (1/8) Epoch 31, batch 1000, train_loss[loss=3.327, NarTop10Accuracy=0.649, over 6264.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7172, over 5889.69 frames. ], batch size: 13, lr: 2.75e-03
2024-08-06 21:21:10,216 INFO [trainer.py:765] (1/8) Epoch 31, batch 1100, train_loss[loss=3.268, NarTop10Accuracy=0.6685, over 7131.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.716, over 5921.24 frames. ], batch size: 18, lr: 2.75e-03
2024-08-06 21:21:41,120 INFO [trainer.py:765] (1/8) Epoch 31, batch 1200, train_loss[loss=3.002, NarTop10Accuracy=0.7267, over 7077.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7193, over 5927.86 frames. ], batch size: 31, lr: 2.75e-03
2024-08-06 21:22:19,742 INFO [trainer.py:765] (1/8) Epoch 31, batch 1300, train_loss[loss=2.976, NarTop10Accuracy=0.7312, over 5040.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7143, over 6003.52 frames. ], batch size: 6, lr: 2.75e-03
2024-08-06 21:22:53,534 INFO [trainer.py:765] (1/8) Epoch 31, batch 1400, train_loss[loss=2.959, NarTop10Accuracy=0.7401, over 6069.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7124, over 6020.16 frames. ], batch size: 11, lr: 2.75e-03
2024-08-06 21:23:21,270 INFO [trainer.py:765] (1/8) Epoch 31, batch 1500, train_loss[loss=3.226, NarTop10Accuracy=0.6751, over 6294.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7148, over 5938.40 frames. ], batch size: 50, lr: 2.74e-03
2024-08-06 21:23:49,005 INFO [trainer.py:765] (1/8) Epoch 31, batch 1600, train_loss[loss=3.309, NarTop10Accuracy=0.671, over 7026.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7156, over 5927.50 frames. ], batch size: 22, lr: 2.74e-03
2024-08-06 21:24:15,512 INFO [trainer.py:765] (1/8) Epoch 31, batch 1700, train_loss[loss=3.379, NarTop10Accuracy=0.6475, over 6276.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7151, over 5922.32 frames. ], batch size: 13, lr: 2.74e-03
2024-08-06 21:24:41,996 INFO [trainer.py:765] (1/8) Epoch 31, batch 1800, train_loss[loss=2.769, NarTop10Accuracy=0.7694, over 7038.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7168, over 5980.70 frames. ], batch size: 22, lr: 2.74e-03
2024-08-06 21:25:08,357 INFO [trainer.py:765] (1/8) Epoch 31, batch 1900, train_loss[loss=3.292, NarTop10Accuracy=0.6711, over 6291.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7129, over 6015.76 frames. ], batch size: 50, lr: 2.74e-03
2024-08-06 21:25:33,773 INFO [trainer.py:765] (1/8) Epoch 31, batch 2000, train_loss[loss=3.05, NarTop10Accuracy=0.7222, over 6060.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7136, over 5987.22 frames. ], batch size: 50, lr: 2.74e-03
2024-08-06 21:25:59,107 INFO [trainer.py:765] (1/8) Epoch 31, batch 2100, train_loss[loss=2.685, NarTop10Accuracy=0.7822, over 3903.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7146, over 5959.52 frames. ], batch size: 4, lr: 2.73e-03
2024-08-06 21:26:24,238 INFO [trainer.py:765] (1/8) Epoch 31, batch 2200, train_loss[loss=3.009, NarTop10Accuracy=0.7215, over 7503.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7181, over 5986.93 frames. ], batch size: 32, lr: 2.73e-03
2024-08-06 21:26:49,322 INFO [trainer.py:765] (1/8) Epoch 31, batch 2300, train_loss[loss=2.766, NarTop10Accuracy=0.7748, over 5637.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7146, over 6002.60 frames. ], batch size: 9, lr: 2.73e-03
2024-08-06 21:27:13,608 INFO [trainer.py:765] (1/8) Epoch 31, batch 2400, train_loss[loss=2.835, NarTop10Accuracy=0.7563, over 5169.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.716, over 5759.94 frames. ], batch size: 7, lr: 2.73e-03
2024-08-06 21:27:37,028 INFO [trainer.py:765] (1/8) Epoch 31, batch 2500, train_loss[loss=2.88, NarTop10Accuracy=0.741, over 5766.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7183, over 5488.49 frames. ], batch size: 8, lr: 2.73e-03
2024-08-06 21:27:57,345 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 21:28:49,392 INFO [trainer.py:765] (1/8) Epoch 32, batch 100, train_loss[loss=2.843, NarTop10Accuracy=0.7575, over 7167.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7143, over 2342.23 frames. ], batch size: 31, lr: 2.68e-03
2024-08-06 21:29:08,160 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 21:29:16,392 INFO [trainer.py:811] (1/8) Epoch 32, validation: loss=2.919, NarTop10Accuracy=0.7409, over 1905321.00 frames. 
2024-08-06 21:29:16,393 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 29627MB
2024-08-06 21:29:16,939 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.842e+02 2.253e+02 2.413e+02 2.600e+02 5.680e+02, threshold=4.826e+02, percent-clipped=0.1
2024-08-06 21:29:32,273 INFO [trainer.py:765] (1/8) Epoch 32, batch 200, train_loss[loss=3.234, NarTop10Accuracy=0.6721, over 6909.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.714, over 3830.65 frames. ], batch size: 17, lr: 2.68e-03
2024-08-06 21:30:05,279 INFO [trainer.py:765] (1/8) Epoch 32, batch 300, train_loss[loss=3.115, NarTop10Accuracy=0.7094, over 7050.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7156, over 4652.07 frames. ], batch size: 22, lr: 2.68e-03
2024-08-06 21:30:34,103 INFO [trainer.py:765] (1/8) Epoch 32, batch 400, train_loss[loss=2.793, NarTop10Accuracy=0.7577, over 5202.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.712, over 5107.57 frames. ], batch size: 7, lr: 2.68e-03
2024-08-06 21:31:13,530 INFO [trainer.py:765] (1/8) Epoch 32, batch 500, train_loss[loss=2.959, NarTop10Accuracy=0.7305, over 6072.00 frames. ], tot_loss[loss=3.062, NarTop10Accuracy=0.7128, over 5385.92 frames. ], batch size: 11, lr: 2.67e-03
2024-08-06 21:31:42,487 INFO [trainer.py:765] (1/8) Epoch 32, batch 600, train_loss[loss=3.297, NarTop10Accuracy=0.6635, over 5661.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7138, over 5653.09 frames. ], batch size: 9, lr: 2.67e-03
2024-08-06 21:32:17,029 INFO [trainer.py:765] (1/8) Epoch 32, batch 700, train_loss[loss=2.622, NarTop10Accuracy=0.8059, over 5178.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7164, over 5723.50 frames. ], batch size: 6, lr: 2.67e-03
2024-08-06 21:33:00,647 INFO [trainer.py:765] (1/8) Epoch 32, batch 800, train_loss[loss=3.13, NarTop10Accuracy=0.6861, over 4257.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7176, over 5774.54 frames. ], batch size: 5, lr: 2.67e-03
2024-08-06 21:33:28,992 INFO [trainer.py:765] (1/8) Epoch 32, batch 900, train_loss[loss=2.749, NarTop10Accuracy=0.7818, over 6702.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.719, over 5804.66 frames. ], batch size: 14, lr: 2.67e-03
2024-08-06 21:34:04,050 INFO [trainer.py:765] (1/8) Epoch 32, batch 1000, train_loss[loss=3.311, NarTop10Accuracy=0.6666, over 6651.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7156, over 5908.19 frames. ], batch size: 14, lr: 2.67e-03
2024-08-06 21:34:46,674 INFO [trainer.py:765] (1/8) Epoch 32, batch 1100, train_loss[loss=3.127, NarTop10Accuracy=0.6957, over 6861.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7151, over 5932.45 frames. ], batch size: 17, lr: 2.66e-03
2024-08-06 21:35:18,171 INFO [trainer.py:765] (1/8) Epoch 32, batch 1200, train_loss[loss=3.267, NarTop10Accuracy=0.6681, over 7449.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7134, over 5940.49 frames. ], batch size: 32, lr: 2.66e-03
2024-08-06 21:35:52,802 INFO [trainer.py:765] (1/8) Epoch 32, batch 1300, train_loss[loss=3.049, NarTop10Accuracy=0.7154, over 5088.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7131, over 6000.88 frames. ], batch size: 6, lr: 2.66e-03
2024-08-06 21:36:29,479 INFO [trainer.py:765] (1/8) Epoch 32, batch 1400, train_loss[loss=3.37, NarTop10Accuracy=0.6451, over 6084.00 frames. ], tot_loss[loss=3.062, NarTop10Accuracy=0.713, over 6003.27 frames. ], batch size: 11, lr: 2.66e-03
2024-08-06 21:37:04,734 INFO [trainer.py:765] (1/8) Epoch 32, batch 1500, train_loss[loss=3.439, NarTop10Accuracy=0.6385, over 5769.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7141, over 5933.33 frames. ], batch size: 51, lr: 2.66e-03
2024-08-06 21:37:32,522 INFO [trainer.py:765] (1/8) Epoch 32, batch 1600, train_loss[loss=2.989, NarTop10Accuracy=0.7298, over 7230.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7147, over 5929.27 frames. ], batch size: 23, lr: 2.66e-03
2024-08-06 21:37:59,161 INFO [trainer.py:765] (1/8) Epoch 32, batch 1700, train_loss[loss=3.098, NarTop10Accuracy=0.7112, over 6705.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7148, over 5916.64 frames. ], batch size: 14, lr: 2.65e-03
2024-08-06 21:38:25,702 INFO [trainer.py:765] (1/8) Epoch 32, batch 1800, train_loss[loss=3.136, NarTop10Accuracy=0.6958, over 7065.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7141, over 5982.39 frames. ], batch size: 22, lr: 2.65e-03
2024-08-06 21:38:52,169 INFO [trainer.py:765] (1/8) Epoch 32, batch 1900, train_loss[loss=2.992, NarTop10Accuracy=0.7239, over 6120.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7106, over 6028.11 frames. ], batch size: 50, lr: 2.65e-03
2024-08-06 21:39:17,769 INFO [trainer.py:765] (1/8) Epoch 32, batch 2000, train_loss[loss=3.439, NarTop10Accuracy=0.6379, over 5517.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7138, over 5992.15 frames. ], batch size: 51, lr: 2.65e-03
2024-08-06 21:39:43,178 INFO [trainer.py:765] (1/8) Epoch 32, batch 2100, train_loss[loss=2.584, NarTop10Accuracy=0.8135, over 4911.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7154, over 5982.38 frames. ], batch size: 5, lr: 2.65e-03
2024-08-06 21:39:54,782 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 21:40:02,941 INFO [trainer.py:811] (1/8) Epoch 32, validation: loss=2.886, NarTop10Accuracy=0.7482, over 1905321.00 frames. 
2024-08-06 21:40:02,942 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 30116MB
2024-08-06 21:40:03,423 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.874e+02 2.278e+02 2.449e+02 2.609e+02 8.207e+02, threshold=4.898e+02, percent-clipped=0.3
2024-08-06 21:40:16,628 INFO [trainer.py:765] (1/8) Epoch 32, batch 2200, train_loss[loss=3.113, NarTop10Accuracy=0.7031, over 7389.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7152, over 6010.75 frames. ], batch size: 32, lr: 2.65e-03
2024-08-06 21:40:41,717 INFO [trainer.py:765] (1/8) Epoch 32, batch 2300, train_loss[loss=3.383, NarTop10Accuracy=0.6527, over 5736.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7107, over 6019.40 frames. ], batch size: 9, lr: 2.65e-03
2024-08-06 21:41:06,072 INFO [trainer.py:765] (1/8) Epoch 32, batch 2400, train_loss[loss=3.375, NarTop10Accuracy=0.6587, over 5103.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7144, over 5775.44 frames. ], batch size: 7, lr: 2.64e-03
2024-08-06 21:41:29,537 INFO [trainer.py:765] (1/8) Epoch 32, batch 2500, train_loss[loss=2.725, NarTop10Accuracy=0.7899, over 5154.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7211, over 5479.79 frames. ], batch size: 7, lr: 2.64e-03
2024-08-06 21:41:49,800 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 21:42:47,615 INFO [trainer.py:765] (1/8) Epoch 33, batch 100, train_loss[loss=3.158, NarTop10Accuracy=0.694, over 6972.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7218, over 2374.33 frames. ], batch size: 31, lr: 2.60e-03
2024-08-06 21:43:22,368 INFO [trainer.py:765] (1/8) Epoch 33, batch 200, train_loss[loss=2.782, NarTop10Accuracy=0.7654, over 6738.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7198, over 3872.61 frames. ], batch size: 17, lr: 2.60e-03
2024-08-06 21:43:56,513 INFO [trainer.py:765] (1/8) Epoch 33, batch 300, train_loss[loss=3.383, NarTop10Accuracy=0.648, over 7056.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7183, over 4670.50 frames. ], batch size: 22, lr: 2.60e-03
2024-08-06 21:44:30,315 INFO [trainer.py:765] (1/8) Epoch 33, batch 400, train_loss[loss=2.803, NarTop10Accuracy=0.7642, over 5124.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7173, over 5123.61 frames. ], batch size: 7, lr: 2.59e-03
2024-08-06 21:45:02,870 INFO [trainer.py:765] (1/8) Epoch 33, batch 500, train_loss[loss=2.752, NarTop10Accuracy=0.776, over 5991.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.72, over 5384.11 frames. ], batch size: 11, lr: 2.59e-03
2024-08-06 21:45:36,226 INFO [trainer.py:765] (1/8) Epoch 33, batch 600, train_loss[loss=3.395, NarTop10Accuracy=0.6427, over 5802.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7151, over 5635.83 frames. ], batch size: 9, lr: 2.59e-03
2024-08-06 21:46:11,316 INFO [trainer.py:765] (1/8) Epoch 33, batch 700, train_loss[loss=2.844, NarTop10Accuracy=0.7563, over 4989.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7149, over 5716.88 frames. ], batch size: 6, lr: 2.59e-03
2024-08-06 21:46:46,169 INFO [trainer.py:765] (1/8) Epoch 33, batch 800, train_loss[loss=2.704, NarTop10Accuracy=0.7778, over 5085.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7156, over 5763.28 frames. ], batch size: 6, lr: 2.59e-03
2024-08-06 21:47:18,908 INFO [trainer.py:765] (1/8) Epoch 33, batch 900, train_loss[loss=3.197, NarTop10Accuracy=0.6866, over 6681.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7148, over 5780.59 frames. ], batch size: 14, lr: 2.59e-03
2024-08-06 21:47:57,316 INFO [trainer.py:765] (1/8) Epoch 33, batch 1000, train_loss[loss=3.032, NarTop10Accuracy=0.7224, over 6117.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7148, over 5901.28 frames. ], batch size: 13, lr: 2.58e-03
2024-08-06 21:48:30,908 INFO [trainer.py:765] (1/8) Epoch 33, batch 1100, train_loss[loss=2.782, NarTop10Accuracy=0.7746, over 6822.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7106, over 5923.68 frames. ], batch size: 17, lr: 2.58e-03
2024-08-06 21:49:06,659 INFO [trainer.py:765] (1/8) Epoch 33, batch 1200, train_loss[loss=2.875, NarTop10Accuracy=0.7559, over 7359.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7111, over 5911.66 frames. ], batch size: 31, lr: 2.58e-03
2024-08-06 21:49:42,815 INFO [trainer.py:765] (1/8) Epoch 33, batch 1300, train_loss[loss=2.983, NarTop10Accuracy=0.7321, over 5112.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7119, over 5972.87 frames. ], batch size: 6, lr: 2.58e-03
2024-08-06 21:50:17,310 INFO [trainer.py:765] (1/8) Epoch 33, batch 1400, train_loss[loss=3.199, NarTop10Accuracy=0.6784, over 6141.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7103, over 5997.27 frames. ], batch size: 11, lr: 2.58e-03
2024-08-06 21:50:45,370 INFO [trainer.py:765] (1/8) Epoch 33, batch 1500, train_loss[loss=3.076, NarTop10Accuracy=0.7109, over 6231.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7133, over 5944.18 frames. ], batch size: 51, lr: 2.58e-03
2024-08-06 21:51:04,606 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 21:51:12,661 INFO [trainer.py:811] (1/8) Epoch 33, validation: loss=2.938, NarTop10Accuracy=0.7372, over 1905321.00 frames. 
2024-08-06 21:51:12,662 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 30116MB
2024-08-06 21:51:13,180 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.834e+02 2.250e+02 2.409e+02 2.586e+02 3.975e+02, threshold=4.818e+02, percent-clipped=0.0
2024-08-06 21:51:21,261 INFO [trainer.py:765] (1/8) Epoch 33, batch 1600, train_loss[loss=3.163, NarTop10Accuracy=0.6932, over 7086.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7153, over 5924.12 frames. ], batch size: 22, lr: 2.57e-03
2024-08-06 21:51:47,922 INFO [trainer.py:765] (1/8) Epoch 33, batch 1700, train_loss[loss=2.855, NarTop10Accuracy=0.7612, over 6135.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7145, over 5924.06 frames. ], batch size: 13, lr: 2.57e-03
2024-08-06 21:52:14,392 INFO [trainer.py:765] (1/8) Epoch 33, batch 1800, train_loss[loss=2.838, NarTop10Accuracy=0.7573, over 7200.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.716, over 5998.44 frames. ], batch size: 22, lr: 2.57e-03
2024-08-06 21:52:40,856 INFO [trainer.py:765] (1/8) Epoch 33, batch 1900, train_loss[loss=3.408, NarTop10Accuracy=0.6435, over 5955.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7121, over 6042.75 frames. ], batch size: 50, lr: 2.57e-03
2024-08-06 21:53:06,352 INFO [trainer.py:765] (1/8) Epoch 33, batch 2000, train_loss[loss=3.44, NarTop10Accuracy=0.6413, over 6015.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7179, over 6004.14 frames. ], batch size: 50, lr: 2.57e-03
2024-08-06 21:53:31,658 INFO [trainer.py:765] (1/8) Epoch 33, batch 2100, train_loss[loss=3.297, NarTop10Accuracy=0.6633, over 3891.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7151, over 5975.34 frames. ], batch size: 4, lr: 2.57e-03
2024-08-06 21:53:56,890 INFO [trainer.py:765] (1/8) Epoch 33, batch 2200, train_loss[loss=3.448, NarTop10Accuracy=0.6313, over 7080.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7131, over 6000.95 frames. ], batch size: 31, lr: 2.57e-03
2024-08-06 21:54:21,990 INFO [trainer.py:765] (1/8) Epoch 33, batch 2300, train_loss[loss=2.841, NarTop10Accuracy=0.7688, over 5796.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7148, over 6015.26 frames. ], batch size: 9, lr: 2.56e-03
2024-08-06 21:54:46,430 INFO [trainer.py:765] (1/8) Epoch 33, batch 2400, train_loss[loss=2.728, NarTop10Accuracy=0.7779, over 5190.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7171, over 5774.43 frames. ], batch size: 7, lr: 2.56e-03
2024-08-06 21:55:09,862 INFO [trainer.py:765] (1/8) Epoch 33, batch 2500, train_loss[loss=2.772, NarTop10Accuracy=0.7841, over 5142.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7209, over 5465.95 frames. ], batch size: 7, lr: 2.56e-03
2024-08-06 21:55:29,641 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 21:56:24,721 INFO [trainer.py:765] (1/8) Epoch 34, batch 100, train_loss[loss=3.414, NarTop10Accuracy=0.6407, over 7278.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7194, over 2368.66 frames. ], batch size: 31, lr: 2.52e-03
2024-08-06 21:56:55,613 INFO [trainer.py:765] (1/8) Epoch 34, batch 200, train_loss[loss=3.149, NarTop10Accuracy=0.693, over 7053.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7229, over 3861.51 frames. ], batch size: 17, lr: 2.52e-03
2024-08-06 21:57:31,776 INFO [trainer.py:765] (1/8) Epoch 34, batch 300, train_loss[loss=2.919, NarTop10Accuracy=0.7412, over 7077.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7201, over 4649.06 frames. ], batch size: 22, lr: 2.52e-03
2024-08-06 21:58:02,724 INFO [trainer.py:765] (1/8) Epoch 34, batch 400, train_loss[loss=3.109, NarTop10Accuracy=0.7002, over 5007.00 frames. ], tot_loss[loss=3.008, NarTop10Accuracy=0.7236, over 5114.74 frames. ], batch size: 7, lr: 2.52e-03
2024-08-06 21:58:34,690 INFO [trainer.py:765] (1/8) Epoch 34, batch 500, train_loss[loss=3.215, NarTop10Accuracy=0.6779, over 6600.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.72, over 5389.13 frames. ], batch size: 12, lr: 2.51e-03
2024-08-06 21:59:09,616 INFO [trainer.py:765] (1/8) Epoch 34, batch 600, train_loss[loss=2.923, NarTop10Accuracy=0.7348, over 5802.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7186, over 5647.21 frames. ], batch size: 9, lr: 2.51e-03
2024-08-06 21:59:46,056 INFO [trainer.py:765] (1/8) Epoch 34, batch 700, train_loss[loss=3.018, NarTop10Accuracy=0.7168, over 5199.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7174, over 5733.83 frames. ], batch size: 6, lr: 2.51e-03
2024-08-06 22:00:17,575 INFO [trainer.py:765] (1/8) Epoch 34, batch 800, train_loss[loss=2.974, NarTop10Accuracy=0.7305, over 5034.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7192, over 5786.69 frames. ], batch size: 6, lr: 2.51e-03
2024-08-06 22:00:49,874 INFO [trainer.py:765] (1/8) Epoch 34, batch 900, train_loss[loss=2.929, NarTop10Accuracy=0.7442, over 6723.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7189, over 5796.92 frames. ], batch size: 14, lr: 2.51e-03
2024-08-06 22:01:25,338 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 22:01:33,386 INFO [trainer.py:811] (1/8) Epoch 34, validation: loss=2.9, NarTop10Accuracy=0.7444, over 1905321.00 frames. 
2024-08-06 22:01:33,387 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 30116MB
2024-08-06 22:01:34,091 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.819e+02 2.259e+02 2.434e+02 2.615e+02 5.125e+02, threshold=4.868e+02, percent-clipped=0.1
2024-08-06 22:01:35,624 INFO [trainer.py:765] (1/8) Epoch 34, batch 1000, train_loss[loss=3.354, NarTop10Accuracy=0.655, over 6207.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7162, over 5896.67 frames. ], batch size: 13, lr: 2.51e-03
2024-08-06 22:02:10,829 INFO [trainer.py:765] (1/8) Epoch 34, batch 1100, train_loss[loss=3.254, NarTop10Accuracy=0.671, over 6882.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7161, over 5939.47 frames. ], batch size: 17, lr: 2.51e-03
2024-08-06 22:02:46,786 INFO [trainer.py:765] (1/8) Epoch 34, batch 1200, train_loss[loss=2.776, NarTop10Accuracy=0.7676, over 7290.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7172, over 5940.91 frames. ], batch size: 31, lr: 2.50e-03
2024-08-06 22:03:20,813 INFO [trainer.py:765] (1/8) Epoch 34, batch 1300, train_loss[loss=2.827, NarTop10Accuracy=0.7615, over 4299.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7166, over 5984.44 frames. ], batch size: 5, lr: 2.50e-03
2024-08-06 22:03:52,949 INFO [trainer.py:765] (1/8) Epoch 34, batch 1400, train_loss[loss=3.218, NarTop10Accuracy=0.673, over 6531.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7165, over 5996.67 frames. ], batch size: 12, lr: 2.50e-03
2024-08-06 22:04:20,822 INFO [trainer.py:765] (1/8) Epoch 34, batch 1500, train_loss[loss=3.028, NarTop10Accuracy=0.7248, over 5766.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7158, over 5932.28 frames. ], batch size: 50, lr: 2.50e-03
2024-08-06 22:04:48,599 INFO [trainer.py:765] (1/8) Epoch 34, batch 1600, train_loss[loss=2.889, NarTop10Accuracy=0.7512, over 6912.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7151, over 5920.24 frames. ], batch size: 22, lr: 2.50e-03
2024-08-06 22:05:15,241 INFO [trainer.py:765] (1/8) Epoch 34, batch 1700, train_loss[loss=3.141, NarTop10Accuracy=0.7046, over 6132.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7166, over 5917.76 frames. ], batch size: 13, lr: 2.50e-03
2024-08-06 22:05:41,720 INFO [trainer.py:765] (1/8) Epoch 34, batch 1800, train_loss[loss=3.417, NarTop10Accuracy=0.6488, over 6744.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7167, over 5993.45 frames. ], batch size: 22, lr: 2.50e-03
2024-08-06 22:06:08,206 INFO [trainer.py:765] (1/8) Epoch 34, batch 1900, train_loss[loss=3.019, NarTop10Accuracy=0.721, over 6213.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7128, over 6033.37 frames. ], batch size: 50, lr: 2.49e-03
2024-08-06 22:06:33,769 INFO [trainer.py:765] (1/8) Epoch 34, batch 2000, train_loss[loss=2.979, NarTop10Accuracy=0.7383, over 6504.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7155, over 5991.79 frames. ], batch size: 50, lr: 2.49e-03
2024-08-06 22:06:59,126 INFO [trainer.py:765] (1/8) Epoch 34, batch 2100, train_loss[loss=3.309, NarTop10Accuracy=0.6634, over 4821.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7133, over 5948.76 frames. ], batch size: 5, lr: 2.49e-03
2024-08-06 22:07:24,398 INFO [trainer.py:765] (1/8) Epoch 34, batch 2200, train_loss[loss=2.996, NarTop10Accuracy=0.7294, over 7296.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7135, over 5984.42 frames. ], batch size: 32, lr: 2.49e-03
2024-08-06 22:07:49,535 INFO [trainer.py:765] (1/8) Epoch 34, batch 2300, train_loss[loss=2.872, NarTop10Accuracy=0.76, over 5766.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7136, over 6011.30 frames. ], batch size: 9, lr: 2.49e-03
2024-08-06 22:08:14,059 INFO [trainer.py:765] (1/8) Epoch 34, batch 2400, train_loss[loss=3.357, NarTop10Accuracy=0.6603, over 5178.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7146, over 5777.19 frames. ], batch size: 7, lr: 2.49e-03
2024-08-06 22:08:37,648 INFO [trainer.py:765] (1/8) Epoch 34, batch 2500, train_loss[loss=2.688, NarTop10Accuracy=0.787, over 5214.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7218, over 5467.06 frames. ], batch size: 7, lr: 2.49e-03
2024-08-06 22:08:57,272 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 22:09:52,640 INFO [trainer.py:765] (1/8) Epoch 35, batch 100, train_loss[loss=3.017, NarTop10Accuracy=0.7252, over 7185.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7177, over 2386.35 frames. ], batch size: 31, lr: 2.45e-03
2024-08-06 22:10:29,697 INFO [trainer.py:765] (1/8) Epoch 35, batch 200, train_loss[loss=3.17, NarTop10Accuracy=0.692, over 6816.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7144, over 3868.92 frames. ], batch size: 17, lr: 2.45e-03
2024-08-06 22:11:04,942 INFO [trainer.py:765] (1/8) Epoch 35, batch 300, train_loss[loss=2.877, NarTop10Accuracy=0.758, over 7008.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7206, over 4661.35 frames. ], batch size: 22, lr: 2.44e-03
2024-08-06 22:11:35,333 INFO [trainer.py:765] (1/8) Epoch 35, batch 400, train_loss[loss=2.877, NarTop10Accuracy=0.7516, over 5259.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7201, over 5108.22 frames. ], batch size: 7, lr: 2.44e-03
2024-08-06 22:11:40,047 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 22:11:48,129 INFO [trainer.py:811] (1/8) Epoch 35, validation: loss=2.84, NarTop10Accuracy=0.7576, over 1905321.00 frames. 
2024-08-06 22:11:48,129 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 30116MB
2024-08-06 22:11:48,701 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.898e+02 2.275e+02 2.426e+02 2.615e+02 4.095e+02, threshold=4.852e+02, percent-clipped=0.0
2024-08-06 22:12:17,722 INFO [trainer.py:765] (1/8) Epoch 35, batch 500, train_loss[loss=2.7, NarTop10Accuracy=0.7897, over 6111.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7212, over 5403.17 frames. ], batch size: 11, lr: 2.44e-03
2024-08-06 22:12:51,424 INFO [trainer.py:765] (1/8) Epoch 35, batch 600, train_loss[loss=3.299, NarTop10Accuracy=0.6689, over 5679.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7182, over 5664.54 frames. ], batch size: 9, lr: 2.44e-03
2024-08-06 22:13:24,940 INFO [trainer.py:765] (1/8) Epoch 35, batch 700, train_loss[loss=2.711, NarTop10Accuracy=0.7898, over 4947.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7179, over 5732.83 frames. ], batch size: 6, lr: 2.44e-03
2024-08-06 22:14:01,383 INFO [trainer.py:765] (1/8) Epoch 35, batch 800, train_loss[loss=2.649, NarTop10Accuracy=0.7961, over 5229.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7164, over 5779.22 frames. ], batch size: 6, lr: 2.44e-03
2024-08-06 22:14:34,372 INFO [trainer.py:765] (1/8) Epoch 35, batch 900, train_loss[loss=3.161, NarTop10Accuracy=0.6825, over 6249.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7189, over 5808.41 frames. ], batch size: 13, lr: 2.44e-03
2024-08-06 22:15:09,371 INFO [trainer.py:765] (1/8) Epoch 35, batch 1000, train_loss[loss=2.916, NarTop10Accuracy=0.7417, over 6324.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7186, over 5917.06 frames. ], batch size: 13, lr: 2.43e-03
2024-08-06 22:15:48,494 INFO [trainer.py:765] (1/8) Epoch 35, batch 1100, train_loss[loss=3.05, NarTop10Accuracy=0.712, over 6765.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7178, over 5932.42 frames. ], batch size: 17, lr: 2.43e-03
2024-08-06 22:16:22,483 INFO [trainer.py:765] (1/8) Epoch 35, batch 1200, train_loss[loss=2.979, NarTop10Accuracy=0.7341, over 7287.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7195, over 5929.48 frames. ], batch size: 31, lr: 2.43e-03
2024-08-06 22:16:57,060 INFO [trainer.py:765] (1/8) Epoch 35, batch 1300, train_loss[loss=2.863, NarTop10Accuracy=0.754, over 4992.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7214, over 5984.46 frames. ], batch size: 6, lr: 2.43e-03
2024-08-06 22:17:31,060 INFO [trainer.py:765] (1/8) Epoch 35, batch 1400, train_loss[loss=3.082, NarTop10Accuracy=0.6973, over 6072.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7197, over 6011.17 frames. ], batch size: 11, lr: 2.43e-03
2024-08-06 22:18:03,062 INFO [trainer.py:765] (1/8) Epoch 35, batch 1500, train_loss[loss=3.047, NarTop10Accuracy=0.719, over 6441.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7177, over 5968.52 frames. ], batch size: 53, lr: 2.43e-03
2024-08-06 22:18:30,727 INFO [trainer.py:765] (1/8) Epoch 35, batch 1600, train_loss[loss=3, NarTop10Accuracy=0.7341, over 7080.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7157, over 5939.21 frames. ], batch size: 22, lr: 2.43e-03
2024-08-06 22:18:57,319 INFO [trainer.py:765] (1/8) Epoch 35, batch 1700, train_loss[loss=2.87, NarTop10Accuracy=0.7589, over 6207.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7147, over 5930.11 frames. ], batch size: 13, lr: 2.42e-03
2024-08-06 22:19:23,702 INFO [trainer.py:765] (1/8) Epoch 35, batch 1800, train_loss[loss=3.417, NarTop10Accuracy=0.6379, over 7047.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7163, over 5989.33 frames. ], batch size: 22, lr: 2.42e-03
2024-08-06 22:19:50,201 INFO [trainer.py:765] (1/8) Epoch 35, batch 1900, train_loss[loss=3.176, NarTop10Accuracy=0.6895, over 5655.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7152, over 6026.24 frames. ], batch size: 50, lr: 2.42e-03
2024-08-06 22:20:15,761 INFO [trainer.py:765] (1/8) Epoch 35, batch 2000, train_loss[loss=3.065, NarTop10Accuracy=0.7166, over 6540.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7167, over 5996.93 frames. ], batch size: 51, lr: 2.42e-03
2024-08-06 22:20:41,044 INFO [trainer.py:765] (1/8) Epoch 35, batch 2100, train_loss[loss=2.746, NarTop10Accuracy=0.7786, over 3894.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.716, over 5984.78 frames. ], batch size: 4, lr: 2.42e-03
2024-08-06 22:21:06,226 INFO [trainer.py:765] (1/8) Epoch 35, batch 2200, train_loss[loss=2.859, NarTop10Accuracy=0.7511, over 7359.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7149, over 6003.72 frames. ], batch size: 31, lr: 2.42e-03
2024-08-06 22:21:31,285 INFO [trainer.py:765] (1/8) Epoch 35, batch 2300, train_loss[loss=2.99, NarTop10Accuracy=0.7205, over 5850.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7134, over 6014.74 frames. ], batch size: 9, lr: 2.42e-03
2024-08-06 22:21:55,647 INFO [trainer.py:765] (1/8) Epoch 35, batch 2400, train_loss[loss=3.293, NarTop10Accuracy=0.6765, over 5664.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7145, over 5770.25 frames. ], batch size: 8, lr: 2.42e-03
2024-08-06 22:21:59,680 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 22:22:07,656 INFO [trainer.py:811] (1/8) Epoch 35, validation: loss=2.905, NarTop10Accuracy=0.7437, over 1905321.00 frames. 
2024-08-06 22:22:07,657 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 30116MB
2024-08-06 22:22:08,116 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.895e+02 2.316e+02 2.462e+02 2.653e+02 5.566e+02, threshold=4.923e+02, percent-clipped=0.1
2024-08-06 22:22:27,128 INFO [trainer.py:765] (1/8) Epoch 35, batch 2500, train_loss[loss=2.966, NarTop10Accuracy=0.7238, over 5043.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7186, over 5468.43 frames. ], batch size: 7, lr: 2.41e-03
2024-08-06 22:22:47,022 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 22:23:47,171 INFO [trainer.py:765] (1/8) Epoch 36, batch 100, train_loss[loss=3.163, NarTop10Accuracy=0.6913, over 7287.00 frames. ], tot_loss[loss=2.989, NarTop10Accuracy=0.7282, over 2368.39 frames. ], batch size: 31, lr: 2.38e-03
2024-08-06 22:24:22,494 INFO [trainer.py:765] (1/8) Epoch 36, batch 200, train_loss[loss=2.765, NarTop10Accuracy=0.7785, over 6660.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7221, over 3858.56 frames. ], batch size: 17, lr: 2.38e-03
2024-08-06 22:24:54,720 INFO [trainer.py:765] (1/8) Epoch 36, batch 300, train_loss[loss=3.212, NarTop10Accuracy=0.6889, over 6996.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7189, over 4658.35 frames. ], batch size: 22, lr: 2.37e-03
2024-08-06 22:25:29,275 INFO [trainer.py:765] (1/8) Epoch 36, batch 400, train_loss[loss=2.873, NarTop10Accuracy=0.7535, over 5103.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.722, over 5128.39 frames. ], batch size: 7, lr: 2.37e-03
2024-08-06 22:26:01,818 INFO [trainer.py:765] (1/8) Epoch 36, batch 500, train_loss[loss=3.301, NarTop10Accuracy=0.6548, over 6195.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7213, over 5402.84 frames. ], batch size: 11, lr: 2.37e-03
2024-08-06 22:26:35,025 INFO [trainer.py:765] (1/8) Epoch 36, batch 600, train_loss[loss=2.92, NarTop10Accuracy=0.7441, over 5706.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.722, over 5666.60 frames. ], batch size: 9, lr: 2.37e-03
2024-08-06 22:27:10,990 INFO [trainer.py:765] (1/8) Epoch 36, batch 700, train_loss[loss=3.18, NarTop10Accuracy=0.6918, over 5097.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7212, over 5720.92 frames. ], batch size: 6, lr: 2.37e-03
2024-08-06 22:27:44,914 INFO [trainer.py:765] (1/8) Epoch 36, batch 800, train_loss[loss=3.187, NarTop10Accuracy=0.6901, over 4278.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7172, over 5771.46 frames. ], batch size: 5, lr: 2.37e-03
2024-08-06 22:28:17,811 INFO [trainer.py:765] (1/8) Epoch 36, batch 900, train_loss[loss=2.84, NarTop10Accuracy=0.7544, over 6201.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7201, over 5802.23 frames. ], batch size: 13, lr: 2.37e-03
2024-08-06 22:28:56,983 INFO [trainer.py:765] (1/8) Epoch 36, batch 1000, train_loss[loss=3.294, NarTop10Accuracy=0.6547, over 6714.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.72, over 5889.04 frames. ], batch size: 14, lr: 2.37e-03
2024-08-06 22:29:29,364 INFO [trainer.py:765] (1/8) Epoch 36, batch 1100, train_loss[loss=2.855, NarTop10Accuracy=0.7572, over 7167.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7196, over 5949.02 frames. ], batch size: 18, lr: 2.36e-03
2024-08-06 22:30:05,680 INFO [trainer.py:765] (1/8) Epoch 36, batch 1200, train_loss[loss=3.055, NarTop10Accuracy=0.7109, over 7419.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7204, over 5933.11 frames. ], batch size: 32, lr: 2.36e-03
2024-08-06 22:30:42,575 INFO [trainer.py:765] (1/8) Epoch 36, batch 1300, train_loss[loss=2.857, NarTop10Accuracy=0.7486, over 5010.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7184, over 5991.17 frames. ], batch size: 6, lr: 2.36e-03
2024-08-06 22:31:15,938 INFO [trainer.py:765] (1/8) Epoch 36, batch 1400, train_loss[loss=3.118, NarTop10Accuracy=0.7092, over 6147.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7211, over 5999.12 frames. ], batch size: 11, lr: 2.36e-03
2024-08-06 22:31:43,748 INFO [trainer.py:765] (1/8) Epoch 36, batch 1500, train_loss[loss=3.427, NarTop10Accuracy=0.6409, over 6435.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7201, over 5959.06 frames. ], batch size: 50, lr: 2.36e-03
2024-08-06 22:32:11,459 INFO [trainer.py:765] (1/8) Epoch 36, batch 1600, train_loss[loss=3.409, NarTop10Accuracy=0.6425, over 7299.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7196, over 5937.19 frames. ], batch size: 22, lr: 2.36e-03
2024-08-06 22:32:38,108 INFO [trainer.py:765] (1/8) Epoch 36, batch 1700, train_loss[loss=3.401, NarTop10Accuracy=0.6473, over 6120.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.717, over 5928.55 frames. ], batch size: 13, lr: 2.36e-03
2024-08-06 22:33:04,554 INFO [trainer.py:765] (1/8) Epoch 36, batch 1800, train_loss[loss=3.178, NarTop10Accuracy=0.6892, over 7308.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7171, over 6003.88 frames. ], batch size: 23, lr: 2.36e-03
2024-08-06 22:33:15,169 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 22:33:23,567 INFO [trainer.py:811] (1/8) Epoch 36, validation: loss=2.897, NarTop10Accuracy=0.7457, over 1905321.00 frames. 
2024-08-06 22:33:23,568 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 30116MB
2024-08-06 22:33:24,096 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.876e+02 2.309e+02 2.476e+02 2.664e+02 4.811e+02, threshold=4.951e+02, percent-clipped=0.0
2024-08-06 22:33:39,456 INFO [trainer.py:765] (1/8) Epoch 36, batch 1900, train_loss[loss=2.947, NarTop10Accuracy=0.7387, over 6345.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7171, over 6047.23 frames. ], batch size: 50, lr: 2.35e-03
2024-08-06 22:34:05,077 INFO [trainer.py:765] (1/8) Epoch 36, batch 2000, train_loss[loss=3.138, NarTop10Accuracy=0.7048, over 6033.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7183, over 6003.53 frames. ], batch size: 51, lr: 2.35e-03
2024-08-06 22:34:30,514 INFO [trainer.py:765] (1/8) Epoch 36, batch 2100, train_loss[loss=2.645, NarTop10Accuracy=0.7958, over 4890.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7195, over 5969.45 frames. ], batch size: 5, lr: 2.35e-03
2024-08-06 22:34:55,939 INFO [trainer.py:765] (1/8) Epoch 36, batch 2200, train_loss[loss=3.466, NarTop10Accuracy=0.6293, over 7311.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7156, over 6005.98 frames. ], batch size: 31, lr: 2.35e-03
2024-08-06 22:35:21,145 INFO [trainer.py:765] (1/8) Epoch 36, batch 2300, train_loss[loss=3.494, NarTop10Accuracy=0.6161, over 5643.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7143, over 6021.92 frames. ], batch size: 9, lr: 2.35e-03
2024-08-06 22:35:45,601 INFO [trainer.py:765] (1/8) Epoch 36, batch 2400, train_loss[loss=3.03, NarTop10Accuracy=0.6994, over 5124.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7173, over 5779.77 frames. ], batch size: 7, lr: 2.35e-03
2024-08-06 22:36:09,182 INFO [trainer.py:765] (1/8) Epoch 36, batch 2500, train_loss[loss=2.782, NarTop10Accuracy=0.757, over 5283.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7201, over 5491.16 frames. ], batch size: 7, lr: 2.35e-03
2024-08-06 22:36:28,928 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 22:37:29,725 INFO [trainer.py:765] (1/8) Epoch 37, batch 100, train_loss[loss=2.889, NarTop10Accuracy=0.7457, over 7434.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7144, over 2372.27 frames. ], batch size: 32, lr: 2.31e-03
2024-08-06 22:38:01,272 INFO [trainer.py:765] (1/8) Epoch 37, batch 200, train_loss[loss=2.828, NarTop10Accuracy=0.7692, over 6864.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7188, over 3856.27 frames. ], batch size: 17, lr: 2.31e-03
2024-08-06 22:38:35,956 INFO [trainer.py:765] (1/8) Epoch 37, batch 300, train_loss[loss=3.165, NarTop10Accuracy=0.6978, over 7137.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7209, over 4653.78 frames. ], batch size: 22, lr: 2.31e-03
2024-08-06 22:39:09,307 INFO [trainer.py:765] (1/8) Epoch 37, batch 400, train_loss[loss=2.631, NarTop10Accuracy=0.8044, over 5199.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7227, over 5111.60 frames. ], batch size: 7, lr: 2.31e-03
2024-08-06 22:39:43,861 INFO [trainer.py:765] (1/8) Epoch 37, batch 500, train_loss[loss=3.299, NarTop10Accuracy=0.6695, over 6084.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7228, over 5402.65 frames. ], batch size: 11, lr: 2.31e-03
2024-08-06 22:40:17,333 INFO [trainer.py:765] (1/8) Epoch 37, batch 600, train_loss[loss=2.762, NarTop10Accuracy=0.7777, over 5745.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7218, over 5673.63 frames. ], batch size: 9, lr: 2.31e-03
2024-08-06 22:40:51,615 INFO [trainer.py:765] (1/8) Epoch 37, batch 700, train_loss[loss=3.263, NarTop10Accuracy=0.6702, over 5277.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7172, over 5736.42 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:41:30,564 INFO [trainer.py:765] (1/8) Epoch 37, batch 800, train_loss[loss=2.799, NarTop10Accuracy=0.7656, over 4947.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.717, over 5789.08 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:41:59,083 INFO [trainer.py:765] (1/8) Epoch 37, batch 900, train_loss[loss=2.854, NarTop10Accuracy=0.7586, over 6243.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7205, over 5808.77 frames. ], batch size: 13, lr: 2.30e-03
2024-08-06 22:42:38,267 INFO [trainer.py:765] (1/8) Epoch 37, batch 1000, train_loss[loss=3.155, NarTop10Accuracy=0.6893, over 6231.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7175, over 5913.32 frames. ], batch size: 13, lr: 2.30e-03
2024-08-06 22:43:15,907 INFO [trainer.py:765] (1/8) Epoch 37, batch 1100, train_loss[loss=3.046, NarTop10Accuracy=0.7221, over 6858.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7175, over 5948.12 frames. ], batch size: 17, lr: 2.30e-03
2024-08-06 22:43:47,740 INFO [trainer.py:765] (1/8) Epoch 37, batch 1200, train_loss[loss=2.929, NarTop10Accuracy=0.7468, over 7137.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7167, over 5940.17 frames. ], batch size: 31, lr: 2.30e-03
2024-08-06 22:44:11,754 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 22:44:20,075 INFO [trainer.py:811] (1/8) Epoch 37, validation: loss=2.92, NarTop10Accuracy=0.7407, over 1905321.00 frames. 
2024-08-06 22:44:20,076 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 30116MB
2024-08-06 22:44:20,606 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.887e+02 2.309e+02 2.481e+02 2.647e+02 8.766e+02, threshold=4.961e+02, percent-clipped=0.1
2024-08-06 22:44:32,784 INFO [trainer.py:765] (1/8) Epoch 37, batch 1300, train_loss[loss=2.83, NarTop10Accuracy=0.7631, over 5073.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7189, over 5994.57 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:45:10,388 INFO [trainer.py:765] (1/8) Epoch 37, batch 1400, train_loss[loss=2.72, NarTop10Accuracy=0.7787, over 6150.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7193, over 6019.87 frames. ], batch size: 11, lr: 2.30e-03
2024-08-06 22:45:40,512 INFO [trainer.py:765] (1/8) Epoch 37, batch 1500, train_loss[loss=2.893, NarTop10Accuracy=0.746, over 6375.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7171, over 5946.75 frames. ], batch size: 50, lr: 2.29e-03
2024-08-06 22:46:08,438 INFO [trainer.py:765] (1/8) Epoch 37, batch 1600, train_loss[loss=3.387, NarTop10Accuracy=0.6486, over 7110.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7144, over 5919.61 frames. ], batch size: 22, lr: 2.29e-03
2024-08-06 22:46:35,187 INFO [trainer.py:765] (1/8) Epoch 37, batch 1700, train_loss[loss=3.37, NarTop10Accuracy=0.6437, over 6828.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7164, over 5896.41 frames. ], batch size: 14, lr: 2.29e-03
2024-08-06 22:47:01,793 INFO [trainer.py:765] (1/8) Epoch 37, batch 1800, train_loss[loss=2.787, NarTop10Accuracy=0.779, over 7182.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7172, over 5974.21 frames. ], batch size: 23, lr: 2.29e-03
2024-08-06 22:47:28,312 INFO [trainer.py:765] (1/8) Epoch 37, batch 1900, train_loss[loss=3.077, NarTop10Accuracy=0.7134, over 6084.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.717, over 6031.91 frames. ], batch size: 51, lr: 2.29e-03
2024-08-06 22:47:53,925 INFO [trainer.py:765] (1/8) Epoch 37, batch 2000, train_loss[loss=3.3, NarTop10Accuracy=0.6694, over 6489.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7176, over 5999.71 frames. ], batch size: 50, lr: 2.29e-03
2024-08-06 22:48:19,326 INFO [trainer.py:765] (1/8) Epoch 37, batch 2100, train_loss[loss=2.951, NarTop10Accuracy=0.7315, over 3876.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7155, over 5980.42 frames. ], batch size: 4, lr: 2.29e-03
2024-08-06 22:48:44,707 INFO [trainer.py:765] (1/8) Epoch 37, batch 2200, train_loss[loss=2.965, NarTop10Accuracy=0.7388, over 7395.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7155, over 6003.23 frames. ], batch size: 31, lr: 2.29e-03
2024-08-06 22:49:09,913 INFO [trainer.py:765] (1/8) Epoch 37, batch 2300, train_loss[loss=2.64, NarTop10Accuracy=0.7994, over 5718.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7163, over 6018.26 frames. ], batch size: 9, lr: 2.29e-03
2024-08-06 22:49:34,318 INFO [trainer.py:765] (1/8) Epoch 37, batch 2400, train_loss[loss=3.332, NarTop10Accuracy=0.657, over 4998.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7207, over 5787.32 frames. ], batch size: 7, lr: 2.28e-03
2024-08-06 22:49:57,861 INFO [trainer.py:765] (1/8) Epoch 37, batch 2500, train_loss[loss=3.371, NarTop10Accuracy=0.6483, over 5109.00 frames. ], tot_loss[loss=2.991, NarTop10Accuracy=0.727, over 5471.62 frames. ], batch size: 7, lr: 2.28e-03
2024-08-06 22:50:18,265 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 22:51:16,152 INFO [trainer.py:765] (1/8) Epoch 38, batch 100, train_loss[loss=3.099, NarTop10Accuracy=0.7136, over 7227.00 frames. ], tot_loss[loss=3.011, NarTop10Accuracy=0.7244, over 2358.38 frames. ], batch size: 31, lr: 2.25e-03
2024-08-06 22:51:53,015 INFO [trainer.py:765] (1/8) Epoch 38, batch 200, train_loss[loss=3.296, NarTop10Accuracy=0.6639, over 6876.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7229, over 3855.26 frames. ], batch size: 17, lr: 2.25e-03
2024-08-06 22:52:25,203 INFO [trainer.py:765] (1/8) Epoch 38, batch 300, train_loss[loss=2.878, NarTop10Accuracy=0.7447, over 7266.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7187, over 4655.09 frames. ], batch size: 22, lr: 2.25e-03
2024-08-06 22:52:55,627 INFO [trainer.py:765] (1/8) Epoch 38, batch 400, train_loss[loss=3.13, NarTop10Accuracy=0.6933, over 4992.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7214, over 5122.48 frames. ], batch size: 7, lr: 2.25e-03
2024-08-06 22:53:32,229 INFO [trainer.py:765] (1/8) Epoch 38, batch 500, train_loss[loss=2.714, NarTop10Accuracy=0.7871, over 6258.00 frames. ], tot_loss[loss=2.992, NarTop10Accuracy=0.7275, over 5405.28 frames. ], batch size: 11, lr: 2.25e-03
2024-08-06 22:54:05,498 INFO [trainer.py:765] (1/8) Epoch 38, batch 600, train_loss[loss=3.346, NarTop10Accuracy=0.6578, over 5619.00 frames. ], tot_loss[loss=3.003, NarTop10Accuracy=0.7253, over 5665.62 frames. ], batch size: 9, lr: 2.24e-03
2024-08-06 22:54:36,003 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 22:54:43,918 INFO [trainer.py:811] (1/8) Epoch 38, validation: loss=2.939, NarTop10Accuracy=0.7369, over 1905321.00 frames. 
2024-08-06 22:54:43,919 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 30116MB
2024-08-06 22:54:44,427 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.880e+02 2.313e+02 2.478e+02 2.663e+02 7.254e+02, threshold=4.957e+02, percent-clipped=0.3
2024-08-06 22:54:46,658 INFO [trainer.py:765] (1/8) Epoch 38, batch 700, train_loss[loss=2.73, NarTop10Accuracy=0.7727, over 4989.00 frames. ], tot_loss[loss=3.008, NarTop10Accuracy=0.724, over 5723.28 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:55:24,937 INFO [trainer.py:765] (1/8) Epoch 38, batch 800, train_loss[loss=3.183, NarTop10Accuracy=0.6865, over 5037.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7204, over 5781.24 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:55:59,703 INFO [trainer.py:765] (1/8) Epoch 38, batch 900, train_loss[loss=2.848, NarTop10Accuracy=0.7505, over 6318.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7212, over 5803.13 frames. ], batch size: 13, lr: 2.24e-03
2024-08-06 22:56:32,091 INFO [trainer.py:765] (1/8) Epoch 38, batch 1000, train_loss[loss=3.537, NarTop10Accuracy=0.6205, over 6603.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7207, over 5891.11 frames. ], batch size: 14, lr: 2.24e-03
2024-08-06 22:57:08,990 INFO [trainer.py:765] (1/8) Epoch 38, batch 1100, train_loss[loss=3.044, NarTop10Accuracy=0.7128, over 6888.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7185, over 5919.93 frames. ], batch size: 17, lr: 2.24e-03
2024-08-06 22:57:42,661 INFO [trainer.py:765] (1/8) Epoch 38, batch 1200, train_loss[loss=2.873, NarTop10Accuracy=0.7594, over 7200.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7181, over 5921.70 frames. ], batch size: 31, lr: 2.24e-03
2024-08-06 22:58:16,546 INFO [trainer.py:765] (1/8) Epoch 38, batch 1300, train_loss[loss=3.19, NarTop10Accuracy=0.6812, over 5067.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7181, over 5984.97 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:58:49,810 INFO [trainer.py:765] (1/8) Epoch 38, batch 1400, train_loss[loss=2.888, NarTop10Accuracy=0.7442, over 6192.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7133, over 6018.42 frames. ], batch size: 11, lr: 2.23e-03
2024-08-06 22:59:22,853 INFO [trainer.py:765] (1/8) Epoch 38, batch 1500, train_loss[loss=3.554, NarTop10Accuracy=0.6097, over 6144.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7176, over 5961.66 frames. ], batch size: 51, lr: 2.23e-03
2024-08-06 22:59:50,643 INFO [trainer.py:765] (1/8) Epoch 38, batch 1600, train_loss[loss=3.32, NarTop10Accuracy=0.6646, over 7038.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7183, over 5950.61 frames. ], batch size: 22, lr: 2.23e-03
2024-08-06 23:00:17,314 INFO [trainer.py:765] (1/8) Epoch 38, batch 1700, train_loss[loss=2.884, NarTop10Accuracy=0.7471, over 6741.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7158, over 5930.01 frames. ], batch size: 14, lr: 2.23e-03
2024-08-06 23:00:43,763 INFO [trainer.py:765] (1/8) Epoch 38, batch 1800, train_loss[loss=3.241, NarTop10Accuracy=0.6727, over 7029.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7155, over 5989.18 frames. ], batch size: 22, lr: 2.23e-03
2024-08-06 23:01:10,191 INFO [trainer.py:765] (1/8) Epoch 38, batch 1900, train_loss[loss=3.445, NarTop10Accuracy=0.6377, over 6180.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7151, over 6026.57 frames. ], batch size: 50, lr: 2.23e-03
2024-08-06 23:01:35,681 INFO [trainer.py:765] (1/8) Epoch 38, batch 2000, train_loss[loss=3.37, NarTop10Accuracy=0.6469, over 6147.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7139, over 6003.63 frames. ], batch size: 54, lr: 2.23e-03
2024-08-06 23:02:01,050 INFO [trainer.py:765] (1/8) Epoch 38, batch 2100, train_loss[loss=2.992, NarTop10Accuracy=0.7168, over 3909.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7157, over 5987.03 frames. ], batch size: 4, lr: 2.23e-03
2024-08-06 23:02:26,313 INFO [trainer.py:765] (1/8) Epoch 38, batch 2200, train_loss[loss=2.838, NarTop10Accuracy=0.7588, over 7224.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.716, over 6017.54 frames. ], batch size: 31, lr: 2.23e-03
2024-08-06 23:02:51,419 INFO [trainer.py:765] (1/8) Epoch 38, batch 2300, train_loss[loss=2.887, NarTop10Accuracy=0.7491, over 5673.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7162, over 6036.88 frames. ], batch size: 9, lr: 2.22e-03
2024-08-06 23:03:16,347 INFO [trainer.py:765] (1/8) Epoch 38, batch 2400, train_loss[loss=2.656, NarTop10Accuracy=0.8005, over 5196.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7184, over 5785.54 frames. ], batch size: 7, lr: 2.22e-03
2024-08-06 23:03:39,823 INFO [trainer.py:765] (1/8) Epoch 38, batch 2500, train_loss[loss=3.318, NarTop10Accuracy=0.6563, over 5670.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7218, over 5494.44 frames. ], batch size: 8, lr: 2.22e-03
2024-08-06 23:03:59,763 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 23:04:58,940 INFO [trainer.py:765] (1/8) Epoch 39, batch 100, train_loss[loss=3.229, NarTop10Accuracy=0.6741, over 7188.00 frames. ], tot_loss[loss=3, NarTop10Accuracy=0.7263, over 2381.99 frames. ], batch size: 31, lr: 2.19e-03
2024-08-06 23:05:03,467 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 23:05:11,563 INFO [trainer.py:811] (1/8) Epoch 39, validation: loss=2.9, NarTop10Accuracy=0.7445, over 1905321.00 frames. 
2024-08-06 23:05:11,564 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 30116MB
2024-08-06 23:05:12,137 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.911e+02 2.316e+02 2.500e+02 2.688e+02 4.683e+02, threshold=5.001e+02, percent-clipped=0.0
2024-08-06 23:05:40,163 INFO [trainer.py:765] (1/8) Epoch 39, batch 200, train_loss[loss=2.737, NarTop10Accuracy=0.7811, over 6915.00 frames. ], tot_loss[loss=3.003, NarTop10Accuracy=0.7256, over 3866.31 frames. ], batch size: 17, lr: 2.19e-03
2024-08-06 23:06:17,293 INFO [trainer.py:765] (1/8) Epoch 39, batch 300, train_loss[loss=3.059, NarTop10Accuracy=0.7202, over 7155.00 frames. ], tot_loss[loss=2.988, NarTop10Accuracy=0.7281, over 4638.63 frames. ], batch size: 22, lr: 2.19e-03
2024-08-06 23:06:48,275 INFO [trainer.py:765] (1/8) Epoch 39, batch 400, train_loss[loss=2.889, NarTop10Accuracy=0.7537, over 5250.00 frames. ], tot_loss[loss=2.991, NarTop10Accuracy=0.7274, over 5080.26 frames. ], batch size: 7, lr: 2.19e-03
2024-08-06 23:07:19,175 INFO [trainer.py:765] (1/8) Epoch 39, batch 500, train_loss[loss=3.215, NarTop10Accuracy=0.6754, over 6093.00 frames. ], tot_loss[loss=2.995, NarTop10Accuracy=0.7262, over 5368.60 frames. ], batch size: 11, lr: 2.19e-03
2024-08-06 23:07:52,563 INFO [trainer.py:765] (1/8) Epoch 39, batch 600, train_loss[loss=2.841, NarTop10Accuracy=0.7618, over 5745.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7225, over 5637.39 frames. ], batch size: 9, lr: 2.19e-03
2024-08-06 23:08:33,695 INFO [trainer.py:765] (1/8) Epoch 39, batch 700, train_loss[loss=3.121, NarTop10Accuracy=0.7037, over 4203.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7209, over 5705.41 frames. ], batch size: 5, lr: 2.18e-03
2024-08-06 23:09:05,861 INFO [trainer.py:765] (1/8) Epoch 39, batch 800, train_loss[loss=2.754, NarTop10Accuracy=0.7759, over 4257.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7202, over 5765.94 frames. ], batch size: 5, lr: 2.18e-03
2024-08-06 23:09:38,865 INFO [trainer.py:765] (1/8) Epoch 39, batch 900, train_loss[loss=3.321, NarTop10Accuracy=0.6568, over 6648.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7204, over 5784.69 frames. ], batch size: 14, lr: 2.18e-03
2024-08-06 23:10:18,460 INFO [trainer.py:765] (1/8) Epoch 39, batch 1000, train_loss[loss=2.847, NarTop10Accuracy=0.7511, over 6411.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7223, over 5884.64 frames. ], batch size: 13, lr: 2.18e-03
2024-08-06 23:10:53,934 INFO [trainer.py:765] (1/8) Epoch 39, batch 1100, train_loss[loss=2.858, NarTop10Accuracy=0.7592, over 6951.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7194, over 5919.87 frames. ], batch size: 17, lr: 2.18e-03
2024-08-06 23:11:27,822 INFO [trainer.py:765] (1/8) Epoch 39, batch 1200, train_loss[loss=2.93, NarTop10Accuracy=0.7359, over 7560.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7207, over 5918.66 frames. ], batch size: 31, lr: 2.18e-03
2024-08-06 23:12:07,253 INFO [trainer.py:765] (1/8) Epoch 39, batch 1300, train_loss[loss=2.749, NarTop10Accuracy=0.7686, over 5172.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7218, over 5998.24 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:12:39,302 INFO [trainer.py:765] (1/8) Epoch 39, batch 1400, train_loss[loss=3.042, NarTop10Accuracy=0.718, over 6075.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7215, over 6024.36 frames. ], batch size: 11, lr: 2.18e-03
2024-08-06 23:13:09,756 INFO [trainer.py:765] (1/8) Epoch 39, batch 1500, train_loss[loss=3.552, NarTop10Accuracy=0.6169, over 6252.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7216, over 5954.91 frames. ], batch size: 50, lr: 2.18e-03
2024-08-06 23:13:37,586 INFO [trainer.py:765] (1/8) Epoch 39, batch 1600, train_loss[loss=2.873, NarTop10Accuracy=0.7518, over 7278.00 frames. ], tot_loss[loss=3.003, NarTop10Accuracy=0.7248, over 5938.00 frames. ], batch size: 23, lr: 2.17e-03
2024-08-06 23:14:04,220 INFO [trainer.py:765] (1/8) Epoch 39, batch 1700, train_loss[loss=3.448, NarTop10Accuracy=0.6306, over 6198.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7182, over 5914.15 frames. ], batch size: 13, lr: 2.17e-03
2024-08-06 23:14:30,767 INFO [trainer.py:765] (1/8) Epoch 39, batch 1800, train_loss[loss=2.828, NarTop10Accuracy=0.7639, over 7185.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7181, over 5975.55 frames. ], batch size: 22, lr: 2.17e-03
2024-08-06 23:14:57,180 INFO [trainer.py:765] (1/8) Epoch 39, batch 1900, train_loss[loss=2.951, NarTop10Accuracy=0.7409, over 5865.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7161, over 6008.73 frames. ], batch size: 53, lr: 2.17e-03
2024-08-06 23:15:22,751 INFO [trainer.py:765] (1/8) Epoch 39, batch 2000, train_loss[loss=3.354, NarTop10Accuracy=0.6579, over 5220.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7205, over 5988.24 frames. ], batch size: 50, lr: 2.17e-03
2024-08-06 23:15:48,060 INFO [trainer.py:765] (1/8) Epoch 39, batch 2100, train_loss[loss=3.191, NarTop10Accuracy=0.6839, over 3969.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7206, over 5972.63 frames. ], batch size: 4, lr: 2.17e-03
2024-08-06 23:15:51,871 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 23:16:02,156 INFO [trainer.py:811] (1/8) Epoch 39, validation: loss=2.85, NarTop10Accuracy=0.7552, over 1905321.00 frames. 
2024-08-06 23:16:02,156 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 30116MB
2024-08-06 23:16:02,645 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.940e+02 2.369e+02 2.530e+02 2.720e+02 6.127e+02, threshold=5.059e+02, percent-clipped=0.2
2024-08-06 23:16:23,652 INFO [trainer.py:765] (1/8) Epoch 39, batch 2200, train_loss[loss=3.224, NarTop10Accuracy=0.6782, over 7119.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7206, over 6009.57 frames. ], batch size: 31, lr: 2.17e-03
2024-08-06 23:16:48,847 INFO [trainer.py:765] (1/8) Epoch 39, batch 2300, train_loss[loss=2.669, NarTop10Accuracy=0.7945, over 5700.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7188, over 6017.63 frames. ], batch size: 9, lr: 2.17e-03
2024-08-06 23:17:13,136 INFO [trainer.py:765] (1/8) Epoch 39, batch 2400, train_loss[loss=2.836, NarTop10Accuracy=0.7596, over 5178.00 frames. ], tot_loss[loss=3.01, NarTop10Accuracy=0.7232, over 5763.36 frames. ], batch size: 7, lr: 2.17e-03
2024-08-06 23:17:36,712 INFO [trainer.py:765] (1/8) Epoch 39, batch 2500, train_loss[loss=3.115, NarTop10Accuracy=0.7056, over 5016.00 frames. ], tot_loss[loss=2.989, NarTop10Accuracy=0.727, over 5484.33 frames. ], batch size: 7, lr: 2.16e-03
2024-08-06 23:17:56,631 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 23:18:48,946 INFO [trainer.py:765] (1/8) Epoch 40, batch 100, train_loss[loss=3.065, NarTop10Accuracy=0.7184, over 7212.00 frames. ], tot_loss[loss=2.998, NarTop10Accuracy=0.7262, over 2350.66 frames. ], batch size: 31, lr: 2.14e-03
2024-08-06 23:19:23,035 INFO [trainer.py:765] (1/8) Epoch 40, batch 200, train_loss[loss=2.751, NarTop10Accuracy=0.7752, over 6765.00 frames. ], tot_loss[loss=2.992, NarTop10Accuracy=0.7268, over 3838.66 frames. ], batch size: 17, lr: 2.13e-03
2024-08-06 23:19:57,188 INFO [trainer.py:765] (1/8) Epoch 40, batch 300, train_loss[loss=2.772, NarTop10Accuracy=0.7693, over 6993.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7225, over 4663.44 frames. ], batch size: 22, lr: 2.13e-03
2024-08-06 23:20:30,182 INFO [trainer.py:765] (1/8) Epoch 40, batch 400, train_loss[loss=2.814, NarTop10Accuracy=0.766, over 5238.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7227, over 5106.63 frames. ], batch size: 7, lr: 2.13e-03
2024-08-06 23:21:00,251 INFO [trainer.py:765] (1/8) Epoch 40, batch 500, train_loss[loss=2.749, NarTop10Accuracy=0.7735, over 6126.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7233, over 5377.65 frames. ], batch size: 11, lr: 2.13e-03
2024-08-06 23:21:34,882 INFO [trainer.py:765] (1/8) Epoch 40, batch 600, train_loss[loss=2.977, NarTop10Accuracy=0.7332, over 5751.00 frames. ], tot_loss[loss=2.996, NarTop10Accuracy=0.7261, over 5639.65 frames. ], batch size: 9, lr: 2.13e-03
2024-08-06 23:22:11,097 INFO [trainer.py:765] (1/8) Epoch 40, batch 700, train_loss[loss=2.851, NarTop10Accuracy=0.7473, over 5010.00 frames. ], tot_loss[loss=3.006, NarTop10Accuracy=0.7239, over 5722.59 frames. ], batch size: 6, lr: 2.13e-03
2024-08-06 23:22:44,754 INFO [trainer.py:765] (1/8) Epoch 40, batch 800, train_loss[loss=2.669, NarTop10Accuracy=0.794, over 5025.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.722, over 5779.67 frames. ], batch size: 6, lr: 2.13e-03
2024-08-06 23:23:16,636 INFO [trainer.py:765] (1/8) Epoch 40, batch 900, train_loss[loss=3.358, NarTop10Accuracy=0.6545, over 6606.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7214, over 5805.59 frames. ], batch size: 14, lr: 2.13e-03
2024-08-06 23:23:55,591 INFO [trainer.py:765] (1/8) Epoch 40, batch 1000, train_loss[loss=3.432, NarTop10Accuracy=0.6425, over 6705.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7192, over 5906.34 frames. ], batch size: 14, lr: 2.13e-03
2024-08-06 23:24:30,208 INFO [trainer.py:765] (1/8) Epoch 40, batch 1100, train_loss[loss=2.733, NarTop10Accuracy=0.7781, over 6999.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7202, over 5934.80 frames. ], batch size: 17, lr: 2.12e-03
2024-08-06 23:25:03,090 INFO [trainer.py:765] (1/8) Epoch 40, batch 1200, train_loss[loss=2.938, NarTop10Accuracy=0.7295, over 7176.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7217, over 5945.80 frames. ], batch size: 31, lr: 2.12e-03
2024-08-06 23:25:41,843 INFO [trainer.py:765] (1/8) Epoch 40, batch 1300, train_loss[loss=2.829, NarTop10Accuracy=0.7619, over 5163.00 frames. ], tot_loss[loss=3.008, NarTop10Accuracy=0.7234, over 6006.28 frames. ], batch size: 6, lr: 2.12e-03
2024-08-06 23:26:13,385 INFO [trainer.py:765] (1/8) Epoch 40, batch 1400, train_loss[loss=2.863, NarTop10Accuracy=0.7556, over 5994.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.721, over 6025.68 frames. ], batch size: 11, lr: 2.12e-03
2024-08-06 23:26:43,377 INFO [trainer.py:765] (1/8) Epoch 40, batch 1500, train_loss[loss=3.386, NarTop10Accuracy=0.644, over 5655.00 frames. ], tot_loss[loss=3.005, NarTop10Accuracy=0.7244, over 5967.31 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:26:54,419 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 23:27:02,676 INFO [trainer.py:811] (1/8) Epoch 40, validation: loss=2.86, NarTop10Accuracy=0.7522, over 1905321.00 frames. 
2024-08-06 23:27:02,677 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 30116MB
2024-08-06 23:27:03,156 INFO [optim.py:386] (1/8) Clipping_scale=2.0, grad-norm quartiles 1.941e+02 2.329e+02 2.511e+02 2.723e+02 1.241e+03, threshold=5.022e+02, percent-clipped=0.2
2024-08-06 23:27:19,381 INFO [trainer.py:765] (1/8) Epoch 40, batch 1600, train_loss[loss=3.044, NarTop10Accuracy=0.7196, over 7164.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7227, over 5936.13 frames. ], batch size: 22, lr: 2.12e-03
2024-08-06 23:27:46,056 INFO [trainer.py:765] (1/8) Epoch 40, batch 1700, train_loss[loss=3.362, NarTop10Accuracy=0.6507, over 6606.00 frames. ], tot_loss[loss=3.011, NarTop10Accuracy=0.7227, over 5913.10 frames. ], batch size: 14, lr: 2.12e-03
2024-08-06 23:28:12,578 INFO [trainer.py:765] (1/8) Epoch 40, batch 1800, train_loss[loss=2.914, NarTop10Accuracy=0.7408, over 7299.00 frames. ], tot_loss[loss=2.995, NarTop10Accuracy=0.7264, over 5986.41 frames. ], batch size: 22, lr: 2.12e-03
2024-08-06 23:28:38,908 INFO [trainer.py:765] (1/8) Epoch 40, batch 1900, train_loss[loss=3.249, NarTop10Accuracy=0.6772, over 6153.00 frames. ], tot_loss[loss=3, NarTop10Accuracy=0.7254, over 6031.59 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:29:04,444 INFO [trainer.py:765] (1/8) Epoch 40, batch 2000, train_loss[loss=3.534, NarTop10Accuracy=0.6074, over 6039.00 frames. ], tot_loss[loss=3.004, NarTop10Accuracy=0.7243, over 5988.20 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:29:29,749 INFO [trainer.py:765] (1/8) Epoch 40, batch 2100, train_loss[loss=2.974, NarTop10Accuracy=0.7417, over 4005.00 frames. ], tot_loss[loss=3.01, NarTop10Accuracy=0.7236, over 5973.04 frames. ], batch size: 4, lr: 2.11e-03
2024-08-06 23:29:54,938 INFO [trainer.py:765] (1/8) Epoch 40, batch 2200, train_loss[loss=3.165, NarTop10Accuracy=0.6909, over 7509.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7206, over 6004.97 frames. ], batch size: 32, lr: 2.11e-03
2024-08-06 23:30:20,012 INFO [trainer.py:765] (1/8) Epoch 40, batch 2300, train_loss[loss=2.933, NarTop10Accuracy=0.7422, over 5757.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7188, over 6018.47 frames. ], batch size: 9, lr: 2.11e-03
2024-08-06 23:30:44,295 INFO [trainer.py:765] (1/8) Epoch 40, batch 2400, train_loss[loss=2.925, NarTop10Accuracy=0.7431, over 5070.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7207, over 5770.23 frames. ], batch size: 7, lr: 2.11e-03
2024-08-06 23:31:07,738 INFO [trainer.py:765] (1/8) Epoch 40, batch 2500, train_loss[loss=2.992, NarTop10Accuracy=0.7198, over 5283.00 frames. ], tot_loss[loss=2.989, NarTop10Accuracy=0.7272, over 5470.32 frames. ], batch size: 7, lr: 2.11e-03
2024-08-06 23:31:27,218 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 23:31:27,221 INFO [trainer.py:1069] (1/8) Done!