2024-08-06 08:06:14,316 INFO [trainer.py:870] (2/8) Training started
2024-08-06 08:06:14,317 INFO [trainer.py:889] (2/8) Device: cuda:2
2024-08-06 08:06:14,317 INFO [trainer.py:890] (2/8) {'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': 20, 'start_epoch': 1, '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': 20000, 'keep_last_k': 20, 'average_period': 0, 'accumulate_grad_steps': 1, 'dtype': 'bfloat16', 'filter_min_duration': 0.5, 'filter_max_duration': 14.0, 'train_stage': 1, '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': 320, '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 08:06:14,317 INFO [trainer.py:892] (2/8) About to create model
2024-08-06 08:06:15,078 INFO [trainer.py:899] (2/8) Number of model parameters: 367386628
2024-08-06 08:06:16,215 INFO [trainer.py:914] (2/8) Using DDP
2024-08-06 08:06:19,151 INFO [datamodule.py:427] (2/8) About to get train cuts
2024-08-06 08:06:19,153 INFO [datamodule.py:434] (2/8) About to get dev cuts
2024-08-06 08:06:19,155 INFO [datamodule.py:292] (2/8) Disable SpecAugment
2024-08-06 08:06:19,155 INFO [datamodule.py:294] (2/8) About to create train dataset
2024-08-06 08:06:19,156 INFO [datamodule.py:323] (2/8) Using DynamicBucketingSampler
2024-08-06 08:06:19,769 INFO [datamodule.py:344] (2/8) About to create train dataloader
2024-08-06 08:06:19,770 INFO [datamodule.py:367] (2/8) About to create dev dataset
2024-08-06 08:06:20,096 INFO [datamodule.py:388] (2/8) About to create dev dataloader
2024-08-06 08:08:02,122 INFO [trainer.py:765] (2/8) Epoch 1, batch 100, train_loss[loss=4.363, ArTop10Accuracy=0.494, over 14232.00 frames. ], tot_loss[loss=5.052, ArTop10Accuracy=0.3739, over 4752.73 frames. ], batch size: 62, lr: 2.25e-02
2024-08-06 08:09:28,827 INFO [trainer.py:765] (2/8) Epoch 1, batch 200, train_loss[loss=3.997, ArTop10Accuracy=0.554, over 13785.00 frames. ], tot_loss[loss=4.487, ArTop10Accuracy=0.4685, over 7750.12 frames. ], batch size: 34, lr: 3.00e-02
2024-08-06 08:10:52,428 INFO [trainer.py:765] (2/8) Epoch 1, batch 300, train_loss[loss=3.878, ArTop10Accuracy=0.5701, over 14358.00 frames. ], tot_loss[loss=4.217, ArTop10Accuracy=0.5127, over 9382.60 frames. ], batch size: 45, lr: 3.00e-02
2024-08-06 08:12:12,699 INFO [trainer.py:765] (2/8) Epoch 1, batch 400, train_loss[loss=3.715, ArTop10Accuracy=0.6059, over 10305.00 frames. ], tot_loss[loss=4.027, ArTop10Accuracy=0.5453, over 10290.17 frames. ], batch size: 14, lr: 3.00e-02
2024-08-06 08:13:40,050 INFO [trainer.py:765] (2/8) Epoch 1, batch 500, train_loss[loss=3.654, ArTop10Accuracy=0.6128, over 12216.00 frames. ], tot_loss[loss=3.879, ArTop10Accuracy=0.5711, over 10857.77 frames. ], batch size: 22, lr: 2.99e-02
2024-08-06 08:15:00,245 INFO [trainer.py:765] (2/8) Epoch 1, batch 600, train_loss[loss=3.641, ArTop10Accuracy=0.6103, over 11523.00 frames. ], tot_loss[loss=3.768, ArTop10Accuracy=0.5906, over 11362.99 frames. ], batch size: 18, lr: 2.99e-02
2024-08-06 08:16:26,425 INFO [trainer.py:765] (2/8) Epoch 1, batch 700, train_loss[loss=3.477, ArTop10Accuracy=0.6423, over 10293.00 frames. ], tot_loss[loss=3.69, ArTop10Accuracy=0.6047, over 11525.39 frames. ], batch size: 12, lr: 2.99e-02
2024-08-06 08:17:43,020 INFO [trainer.py:765] (2/8) Epoch 1, batch 800, train_loss[loss=3.488, ArTop10Accuracy=0.6468, over 10005.00 frames. ], tot_loss[loss=3.627, ArTop10Accuracy=0.6161, over 11644.65 frames. ], batch size: 12, lr: 2.98e-02
2024-08-06 08:18:56,151 INFO [trainer.py:765] (2/8) Epoch 1, batch 900, train_loss[loss=3.489, ArTop10Accuracy=0.6433, over 13104.00 frames. ], tot_loss[loss=3.569, ArTop10Accuracy=0.6268, over 11684.52 frames. ], batch size: 28, lr: 2.98e-02
2024-08-06 08:20:12,863 INFO [trainer.py:765] (2/8) Epoch 1, batch 1000, train_loss[loss=3.458, ArTop10Accuracy=0.6483, over 12945.00 frames. ], tot_loss[loss=3.525, ArTop10Accuracy=0.6349, over 11858.22 frames. ], batch size: 27, lr: 2.97e-02
2024-08-06 08:20:13,539 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 9.300e+01 1.871e+02 2.675e+02 4.030e+02 9.119e+03, threshold=5.351e+02, percent-clipped=0.0
2024-08-06 08:21:29,155 INFO [trainer.py:765] (2/8) Epoch 1, batch 1100, train_loss[loss=3.455, ArTop10Accuracy=0.6509, over 13734.00 frames. ], tot_loss[loss=3.489, ArTop10Accuracy=0.6414, over 11951.02 frames. ], batch size: 34, lr: 2.96e-02
2024-08-06 08:22:45,412 INFO [trainer.py:765] (2/8) Epoch 1, batch 1200, train_loss[loss=3.438, ArTop10Accuracy=0.6536, over 12531.00 frames. ], tot_loss[loss=3.463, ArTop10Accuracy=0.6462, over 11868.08 frames. ], batch size: 101, lr: 2.96e-02
2024-08-06 08:23:45,264 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 08:25:36,238 INFO [trainer.py:765] (2/8) Epoch 2, batch 100, train_loss[loss=3.4, ArTop10Accuracy=0.6547, over 14385.00 frames. ], tot_loss[loss=3.411, ArTop10Accuracy=0.6553, over 4753.26 frames. ], batch size: 62, lr: 2.90e-02
2024-08-06 08:26:58,956 INFO [trainer.py:765] (2/8) Epoch 2, batch 200, train_loss[loss=3.384, ArTop10Accuracy=0.6598, over 13692.00 frames. ], tot_loss[loss=3.387, ArTop10Accuracy=0.6599, over 7750.66 frames. ], batch size: 34, lr: 2.89e-02
2024-08-06 08:28:25,533 INFO [trainer.py:765] (2/8) Epoch 2, batch 300, train_loss[loss=3.337, ArTop10Accuracy=0.6695, over 14655.00 frames. ], tot_loss[loss=3.368, ArTop10Accuracy=0.6638, over 9401.76 frames. ], batch size: 45, lr: 2.89e-02
2024-08-06 08:29:48,637 INFO [trainer.py:765] (2/8) Epoch 2, batch 400, train_loss[loss=3.286, ArTop10Accuracy=0.6797, over 10335.00 frames. ], tot_loss[loss=3.354, ArTop10Accuracy=0.6663, over 10286.49 frames. ], batch size: 14, lr: 2.88e-02
2024-08-06 08:31:22,900 INFO [trainer.py:765] (2/8) Epoch 2, batch 500, train_loss[loss=3.357, ArTop10Accuracy=0.6681, over 12267.00 frames. ], tot_loss[loss=3.345, ArTop10Accuracy=0.6679, over 10860.51 frames. ], batch size: 22, lr: 2.87e-02
2024-08-06 08:32:45,689 INFO [trainer.py:765] (2/8) Epoch 2, batch 600, train_loss[loss=3.376, ArTop10Accuracy=0.6645, over 11415.00 frames. ], tot_loss[loss=3.334, ArTop10Accuracy=0.6704, over 11391.79 frames. ], batch size: 18, lr: 2.86e-02
2024-08-06 08:34:13,581 INFO [trainer.py:765] (2/8) Epoch 2, batch 700, train_loss[loss=3.356, ArTop10Accuracy=0.6722, over 9474.00 frames. ], tot_loss[loss=3.329, ArTop10Accuracy=0.6711, over 11540.34 frames. ], batch size: 11, lr: 2.85e-02
2024-08-06 08:34:31,173 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 08:34:40,887 INFO [trainer.py:811] (2/8) Epoch 2, validation: loss=3.277, ArTop10Accuracy=0.6803, over 1827537.00 frames. 
2024-08-06 08:34:40,888 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 33008MB
2024-08-06 08:34:41,700 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 7.953e+01 1.592e+02 2.200e+02 3.344e+02 2.949e+03, threshold=4.400e+02, percent-clipped=8.6
2024-08-06 08:35:39,878 INFO [trainer.py:765] (2/8) Epoch 2, batch 800, train_loss[loss=3.26, ArTop10Accuracy=0.6839, over 10119.00 frames. ], tot_loss[loss=3.322, ArTop10Accuracy=0.6726, over 11672.83 frames. ], batch size: 12, lr: 2.84e-02
2024-08-06 08:36:56,371 INFO [trainer.py:765] (2/8) Epoch 2, batch 900, train_loss[loss=3.232, ArTop10Accuracy=0.6876, over 13044.00 frames. ], tot_loss[loss=3.31, ArTop10Accuracy=0.6749, over 11707.63 frames. ], batch size: 27, lr: 2.83e-02
2024-08-06 08:38:10,512 INFO [trainer.py:765] (2/8) Epoch 2, batch 1000, train_loss[loss=3.22, ArTop10Accuracy=0.6934, over 12762.00 frames. ], tot_loss[loss=3.302, ArTop10Accuracy=0.6761, over 11890.52 frames. ], batch size: 27, lr: 2.82e-02
2024-08-06 08:39:25,060 INFO [trainer.py:765] (2/8) Epoch 2, batch 1100, train_loss[loss=3.299, ArTop10Accuracy=0.6775, over 13686.00 frames. ], tot_loss[loss=3.296, ArTop10Accuracy=0.6772, over 11940.66 frames. ], batch size: 34, lr: 2.81e-02
2024-08-06 08:40:38,220 INFO [trainer.py:765] (2/8) Epoch 2, batch 1200, train_loss[loss=3.305, ArTop10Accuracy=0.6728, over 12009.00 frames. ], tot_loss[loss=3.285, ArTop10Accuracy=0.6794, over 11860.80 frames. ], batch size: 103, lr: 2.80e-02
2024-08-06 08:41:38,236 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 08:43:36,650 INFO [trainer.py:765] (2/8) Epoch 3, batch 100, train_loss[loss=3.299, ArTop10Accuracy=0.6755, over 14610.00 frames. ], tot_loss[loss=3.25, ArTop10Accuracy=0.6855, over 4768.32 frames. ], batch size: 62, lr: 2.67e-02
2024-08-06 08:45:10,499 INFO [trainer.py:765] (2/8) Epoch 3, batch 200, train_loss[loss=3.211, ArTop10Accuracy=0.6906, over 13572.00 frames. ], tot_loss[loss=3.222, ArTop10Accuracy=0.6906, over 7770.25 frames. ], batch size: 34, lr: 2.66e-02
2024-08-06 08:46:29,258 INFO [trainer.py:765] (2/8) Epoch 3, batch 300, train_loss[loss=3.181, ArTop10Accuracy=0.6992, over 14205.00 frames. ], tot_loss[loss=3.203, ArTop10Accuracy=0.6945, over 9392.67 frames. ], batch size: 44, lr: 2.64e-02
2024-08-06 08:48:04,217 INFO [trainer.py:765] (2/8) Epoch 3, batch 400, train_loss[loss=3.158, ArTop10Accuracy=0.7093, over 10824.00 frames. ], tot_loss[loss=3.188, ArTop10Accuracy=0.6974, over 10294.96 frames. ], batch size: 15, lr: 2.63e-02
2024-08-06 08:48:40,880 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 9.282e+01 1.561e+02 1.981e+02 2.686e+02 1.768e+03, threshold=3.962e+02, percent-clipped=7.6
2024-08-06 08:49:25,542 INFO [trainer.py:765] (2/8) Epoch 3, batch 500, train_loss[loss=3.09, ArTop10Accuracy=0.7159, over 12096.00 frames. ], tot_loss[loss=3.174, ArTop10Accuracy=0.7, over 10852.34 frames. ], batch size: 22, lr: 2.62e-02
2024-08-06 08:51:00,477 INFO [trainer.py:765] (2/8) Epoch 3, batch 600, train_loss[loss=3.165, ArTop10Accuracy=0.7016, over 11343.00 frames. ], tot_loss[loss=3.157, ArTop10Accuracy=0.7035, over 11365.70 frames. ], batch size: 18, lr: 2.61e-02
2024-08-06 08:52:31,618 INFO [trainer.py:765] (2/8) Epoch 3, batch 700, train_loss[loss=3.123, ArTop10Accuracy=0.7134, over 9264.00 frames. ], tot_loss[loss=3.15, ArTop10Accuracy=0.7048, over 11520.92 frames. ], batch size: 11, lr: 2.60e-02
2024-08-06 08:53:57,388 INFO [trainer.py:765] (2/8) Epoch 3, batch 800, train_loss[loss=3.136, ArTop10Accuracy=0.7107, over 9384.00 frames. ], tot_loss[loss=3.143, ArTop10Accuracy=0.706, over 11642.41 frames. ], batch size: 11, lr: 2.59e-02
2024-08-06 08:55:15,118 INFO [trainer.py:765] (2/8) Epoch 3, batch 900, train_loss[loss=3.106, ArTop10Accuracy=0.7141, over 12834.00 frames. ], tot_loss[loss=3.12, ArTop10Accuracy=0.7105, over 11681.59 frames. ], batch size: 27, lr: 2.57e-02
2024-08-06 08:56:31,557 INFO [trainer.py:765] (2/8) Epoch 3, batch 1000, train_loss[loss=3.044, ArTop10Accuracy=0.7252, over 12933.00 frames. ], tot_loss[loss=3.113, ArTop10Accuracy=0.7119, over 11876.26 frames. ], batch size: 27, lr: 2.56e-02
2024-08-06 08:57:46,505 INFO [trainer.py:765] (2/8) Epoch 3, batch 1100, train_loss[loss=3.112, ArTop10Accuracy=0.7162, over 13767.00 frames. ], tot_loss[loss=3.108, ArTop10Accuracy=0.7123, over 11954.94 frames. ], batch size: 34, lr: 2.55e-02
2024-08-06 08:59:01,398 INFO [trainer.py:765] (2/8) Epoch 3, batch 1200, train_loss[loss=3.103, ArTop10Accuracy=0.712, over 12045.00 frames. ], tot_loss[loss=3.097, ArTop10Accuracy=0.7148, over 11876.24 frames. ], batch size: 101, lr: 2.54e-02
2024-08-06 09:00:01,918 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 09:01:50,740 INFO [trainer.py:765] (2/8) Epoch 4, batch 100, train_loss[loss=3.141, ArTop10Accuracy=0.7039, over 14811.00 frames. ], tot_loss[loss=3.07, ArTop10Accuracy=0.7194, over 4779.88 frames. ], batch size: 62, lr: 2.38e-02
2024-08-06 09:02:52,859 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 09:03:02,383 INFO [trainer.py:811] (2/8) Epoch 4, validation: loss=2.997, ArTop10Accuracy=0.7338, over 1827537.00 frames. 
2024-08-06 09:03:02,384 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 33008MB
2024-08-06 09:03:03,362 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.072e+02 1.499e+02 1.782e+02 2.273e+02 1.100e+03, threshold=3.565e+02, percent-clipped=4.7
2024-08-06 09:03:29,271 INFO [trainer.py:765] (2/8) Epoch 4, batch 200, train_loss[loss=3.03, ArTop10Accuracy=0.7293, over 13884.00 frames. ], tot_loss[loss=3.046, ArTop10Accuracy=0.7239, over 7761.27 frames. ], batch size: 35, lr: 2.37e-02
2024-08-06 09:05:01,732 INFO [trainer.py:765] (2/8) Epoch 4, batch 300, train_loss[loss=3.033, ArTop10Accuracy=0.7252, over 14427.00 frames. ], tot_loss[loss=3.04, ArTop10Accuracy=0.7251, over 9404.39 frames. ], batch size: 44, lr: 2.36e-02
2024-08-06 09:06:28,149 INFO [trainer.py:765] (2/8) Epoch 4, batch 400, train_loss[loss=3.001, ArTop10Accuracy=0.7312, over 10125.00 frames. ], tot_loss[loss=3.034, ArTop10Accuracy=0.7263, over 10311.26 frames. ], batch size: 14, lr: 2.34e-02
2024-08-06 09:08:01,925 INFO [trainer.py:765] (2/8) Epoch 4, batch 500, train_loss[loss=2.926, ArTop10Accuracy=0.7474, over 12684.00 frames. ], tot_loss[loss=3.029, ArTop10Accuracy=0.7274, over 10875.39 frames. ], batch size: 23, lr: 2.33e-02
2024-08-06 09:09:28,540 INFO [trainer.py:765] (2/8) Epoch 4, batch 600, train_loss[loss=3.015, ArTop10Accuracy=0.7289, over 11412.00 frames. ], tot_loss[loss=3.027, ArTop10Accuracy=0.7277, over 11389.35 frames. ], batch size: 18, lr: 2.32e-02
2024-08-06 09:10:59,865 INFO [trainer.py:765] (2/8) Epoch 4, batch 700, train_loss[loss=3.008, ArTop10Accuracy=0.7289, over 10233.00 frames. ], tot_loss[loss=3.025, ArTop10Accuracy=0.728, over 11523.83 frames. ], batch size: 12, lr: 2.31e-02
2024-08-06 09:12:17,513 INFO [trainer.py:765] (2/8) Epoch 4, batch 800, train_loss[loss=2.89, ArTop10Accuracy=0.7544, over 10230.00 frames. ], tot_loss[loss=3.026, ArTop10Accuracy=0.7279, over 11647.88 frames. ], batch size: 12, lr: 2.30e-02
2024-08-06 09:13:33,212 INFO [trainer.py:765] (2/8) Epoch 4, batch 900, train_loss[loss=3.084, ArTop10Accuracy=0.7148, over 13032.00 frames. ], tot_loss[loss=3.014, ArTop10Accuracy=0.7303, over 11678.88 frames. ], batch size: 27, lr: 2.29e-02
2024-08-06 09:14:47,520 INFO [trainer.py:765] (2/8) Epoch 4, batch 1000, train_loss[loss=2.916, ArTop10Accuracy=0.7481, over 12747.00 frames. ], tot_loss[loss=3.013, ArTop10Accuracy=0.7304, over 11858.96 frames. ], batch size: 27, lr: 2.28e-02
2024-08-06 09:16:02,981 INFO [trainer.py:765] (2/8) Epoch 4, batch 1100, train_loss[loss=2.947, ArTop10Accuracy=0.7418, over 13398.00 frames. ], tot_loss[loss=3.014, ArTop10Accuracy=0.7302, over 11919.73 frames. ], batch size: 34, lr: 2.26e-02
2024-08-06 09:16:53,292 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.100e+02 1.440e+02 1.636e+02 1.968e+02 7.702e+02, threshold=3.273e+02, percent-clipped=1.3
2024-08-06 09:17:18,345 INFO [trainer.py:765] (2/8) Epoch 4, batch 1200, train_loss[loss=3.05, ArTop10Accuracy=0.722, over 11808.00 frames. ], tot_loss[loss=3.009, ArTop10Accuracy=0.7312, over 11852.81 frames. ], batch size: 101, lr: 2.25e-02
2024-08-06 09:18:17,314 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 09:20:17,171 INFO [trainer.py:765] (2/8) Epoch 5, batch 100, train_loss[loss=3.07, ArTop10Accuracy=0.7177, over 14298.00 frames. ], tot_loss[loss=2.987, ArTop10Accuracy=0.7348, over 4753.11 frames. ], batch size: 62, lr: 2.10e-02
2024-08-06 09:21:52,293 INFO [trainer.py:765] (2/8) Epoch 5, batch 200, train_loss[loss=2.957, ArTop10Accuracy=0.7421, over 13812.00 frames. ], tot_loss[loss=2.98, ArTop10Accuracy=0.7365, over 7752.56 frames. ], batch size: 34, lr: 2.09e-02
2024-08-06 09:23:19,239 INFO [trainer.py:765] (2/8) Epoch 5, batch 300, train_loss[loss=3.04, ArTop10Accuracy=0.7233, over 14325.00 frames. ], tot_loss[loss=2.972, ArTop10Accuracy=0.7381, over 9367.98 frames. ], batch size: 44, lr: 2.08e-02
2024-08-06 09:24:53,537 INFO [trainer.py:765] (2/8) Epoch 5, batch 400, train_loss[loss=2.909, ArTop10Accuracy=0.7522, over 10209.00 frames. ], tot_loss[loss=2.97, ArTop10Accuracy=0.7384, over 10284.90 frames. ], batch size: 14, lr: 2.07e-02
2024-08-06 09:26:19,418 INFO [trainer.py:765] (2/8) Epoch 5, batch 500, train_loss[loss=2.91, ArTop10Accuracy=0.7482, over 12159.00 frames. ], tot_loss[loss=2.961, ArTop10Accuracy=0.7404, over 10847.24 frames. ], batch size: 22, lr: 2.06e-02
2024-08-06 09:27:49,537 INFO [trainer.py:765] (2/8) Epoch 5, batch 600, train_loss[loss=2.969, ArTop10Accuracy=0.7339, over 11391.00 frames. ], tot_loss[loss=2.962, ArTop10Accuracy=0.74, over 11368.24 frames. ], batch size: 18, lr: 2.05e-02
2024-08-06 09:29:21,671 INFO [trainer.py:765] (2/8) Epoch 5, batch 700, train_loss[loss=2.931, ArTop10Accuracy=0.7457, over 10194.00 frames. ], tot_loss[loss=2.966, ArTop10Accuracy=0.7394, over 11518.22 frames. ], batch size: 12, lr: 2.04e-02
2024-08-06 09:30:44,692 INFO [trainer.py:765] (2/8) Epoch 5, batch 800, train_loss[loss=2.974, ArTop10Accuracy=0.7366, over 9222.00 frames. ], tot_loss[loss=2.97, ArTop10Accuracy=0.7384, over 11625.17 frames. ], batch size: 11, lr: 2.03e-02
2024-08-06 09:31:51,239 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 09:32:00,761 INFO [trainer.py:811] (2/8) Epoch 5, validation: loss=2.926, ArTop10Accuracy=0.7466, over 1827537.00 frames. 
2024-08-06 09:32:00,762 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 33008MB
2024-08-06 09:32:01,706 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.060e+02 1.349e+02 1.525e+02 1.806e+02 1.007e+03, threshold=3.049e+02, percent-clipped=2.3
2024-08-06 09:32:10,550 INFO [trainer.py:765] (2/8) Epoch 5, batch 900, train_loss[loss=2.953, ArTop10Accuracy=0.7378, over 12915.00 frames. ], tot_loss[loss=2.961, ArTop10Accuracy=0.7405, over 11667.24 frames. ], batch size: 27, lr: 2.02e-02
2024-08-06 09:33:27,322 INFO [trainer.py:765] (2/8) Epoch 5, batch 1000, train_loss[loss=2.969, ArTop10Accuracy=0.7443, over 12915.00 frames. ], tot_loss[loss=2.963, ArTop10Accuracy=0.7401, over 11855.31 frames. ], batch size: 27, lr: 2.01e-02
2024-08-06 09:34:42,299 INFO [trainer.py:765] (2/8) Epoch 5, batch 1100, train_loss[loss=2.942, ArTop10Accuracy=0.7451, over 13662.00 frames. ], tot_loss[loss=2.962, ArTop10Accuracy=0.7403, over 11926.15 frames. ], batch size: 34, lr: 2.00e-02
2024-08-06 09:35:56,330 INFO [trainer.py:765] (2/8) Epoch 5, batch 1200, train_loss[loss=3.037, ArTop10Accuracy=0.7247, over 12591.00 frames. ], tot_loss[loss=2.96, ArTop10Accuracy=0.7405, over 11843.81 frames. ], batch size: 101, lr: 1.99e-02
2024-08-06 09:36:54,933 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 09:38:52,662 INFO [trainer.py:765] (2/8) Epoch 6, batch 100, train_loss[loss=3.01, ArTop10Accuracy=0.729, over 14643.00 frames. ], tot_loss[loss=2.948, ArTop10Accuracy=0.7425, over 4757.65 frames. ], batch size: 62, lr: 1.85e-02
2024-08-06 09:40:19,834 INFO [trainer.py:765] (2/8) Epoch 6, batch 200, train_loss[loss=2.891, ArTop10Accuracy=0.7547, over 13698.00 frames. ], tot_loss[loss=2.936, ArTop10Accuracy=0.7452, over 7750.83 frames. ], batch size: 34, lr: 1.84e-02
2024-08-06 09:41:52,964 INFO [trainer.py:765] (2/8) Epoch 6, batch 300, train_loss[loss=2.975, ArTop10Accuracy=0.7346, over 14988.00 frames. ], tot_loss[loss=2.934, ArTop10Accuracy=0.7453, over 9390.38 frames. ], batch size: 45, lr: 1.83e-02
2024-08-06 09:43:17,827 INFO [trainer.py:765] (2/8) Epoch 6, batch 400, train_loss[loss=2.765, ArTop10Accuracy=0.7792, over 10242.00 frames. ], tot_loss[loss=2.931, ArTop10Accuracy=0.746, over 10311.50 frames. ], batch size: 14, lr: 1.83e-02
2024-08-06 09:44:54,128 INFO [trainer.py:765] (2/8) Epoch 6, batch 500, train_loss[loss=2.926, ArTop10Accuracy=0.7468, over 12633.00 frames. ], tot_loss[loss=2.925, ArTop10Accuracy=0.7472, over 10873.26 frames. ], batch size: 23, lr: 1.82e-02
2024-08-06 09:46:22,873 INFO [trainer.py:765] (2/8) Epoch 6, batch 600, train_loss[loss=2.928, ArTop10Accuracy=0.7472, over 11355.00 frames. ], tot_loss[loss=2.924, ArTop10Accuracy=0.7471, over 11385.20 frames. ], batch size: 18, lr: 1.81e-02
2024-08-06 09:46:37,219 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.012e+02 1.339e+02 1.480e+02 1.701e+02 7.506e+02, threshold=2.959e+02, percent-clipped=1.1
2024-08-06 09:47:57,867 INFO [trainer.py:765] (2/8) Epoch 6, batch 700, train_loss[loss=2.878, ArTop10Accuracy=0.7607, over 10119.00 frames. ], tot_loss[loss=2.925, ArTop10Accuracy=0.7469, over 11525.26 frames. ], batch size: 12, lr: 1.80e-02
2024-08-06 09:49:15,954 INFO [trainer.py:765] (2/8) Epoch 6, batch 800, train_loss[loss=2.852, ArTop10Accuracy=0.7609, over 9819.00 frames. ], tot_loss[loss=2.928, ArTop10Accuracy=0.7466, over 11650.70 frames. ], batch size: 12, lr: 1.79e-02
2024-08-06 09:50:32,135 INFO [trainer.py:765] (2/8) Epoch 6, batch 900, train_loss[loss=2.791, ArTop10Accuracy=0.78, over 13071.00 frames. ], tot_loss[loss=2.924, ArTop10Accuracy=0.7474, over 11693.48 frames. ], batch size: 27, lr: 1.78e-02
2024-08-06 09:51:47,297 INFO [trainer.py:765] (2/8) Epoch 6, batch 1000, train_loss[loss=2.926, ArTop10Accuracy=0.7512, over 12903.00 frames. ], tot_loss[loss=2.926, ArTop10Accuracy=0.747, over 11887.13 frames. ], batch size: 27, lr: 1.77e-02
2024-08-06 09:53:00,921 INFO [trainer.py:765] (2/8) Epoch 6, batch 1100, train_loss[loss=2.984, ArTop10Accuracy=0.7382, over 13563.00 frames. ], tot_loss[loss=2.929, ArTop10Accuracy=0.7464, over 11928.49 frames. ], batch size: 34, lr: 1.77e-02
2024-08-06 09:54:14,336 INFO [trainer.py:765] (2/8) Epoch 6, batch 1200, train_loss[loss=3.008, ArTop10Accuracy=0.731, over 12219.00 frames. ], tot_loss[loss=2.926, ArTop10Accuracy=0.7471, over 11866.28 frames. ], batch size: 101, lr: 1.76e-02
2024-08-06 09:55:13,368 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 09:57:06,699 INFO [trainer.py:765] (2/8) Epoch 7, batch 100, train_loss[loss=2.987, ArTop10Accuracy=0.7334, over 14478.00 frames. ], tot_loss[loss=2.916, ArTop10Accuracy=0.7479, over 4762.83 frames. ], batch size: 62, lr: 1.64e-02
2024-08-06 09:58:39,425 INFO [trainer.py:765] (2/8) Epoch 7, batch 200, train_loss[loss=2.928, ArTop10Accuracy=0.7454, over 13437.00 frames. ], tot_loss[loss=2.902, ArTop10Accuracy=0.7509, over 7759.42 frames. ], batch size: 34, lr: 1.64e-02
2024-08-06 10:00:06,083 INFO [trainer.py:765] (2/8) Epoch 7, batch 300, train_loss[loss=2.956, ArTop10Accuracy=0.7386, over 14145.00 frames. ], tot_loss[loss=2.9, ArTop10Accuracy=0.7512, over 9375.25 frames. ], batch size: 44, lr: 1.63e-02
2024-08-06 10:00:40,509 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 10:00:50,245 INFO [trainer.py:811] (2/8) Epoch 7, validation: loss=2.88, ArTop10Accuracy=0.7554, over 1827537.00 frames. 
2024-08-06 10:00:50,246 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 33008MB
2024-08-06 10:00:50,977 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.002e+02 1.286e+02 1.429e+02 1.605e+02 1.020e+03, threshold=2.857e+02, percent-clipped=1.5
2024-08-06 10:01:49,116 INFO [trainer.py:765] (2/8) Epoch 7, batch 400, train_loss[loss=2.927, ArTop10Accuracy=0.7455, over 10119.00 frames. ], tot_loss[loss=2.897, ArTop10Accuracy=0.7518, over 10282.62 frames. ], batch size: 14, lr: 1.62e-02
2024-08-06 10:03:21,457 INFO [trainer.py:765] (2/8) Epoch 7, batch 500, train_loss[loss=2.883, ArTop10Accuracy=0.7547, over 12735.00 frames. ], tot_loss[loss=2.892, ArTop10Accuracy=0.7532, over 10853.66 frames. ], batch size: 23, lr: 1.61e-02
2024-08-06 10:04:51,883 INFO [trainer.py:765] (2/8) Epoch 7, batch 600, train_loss[loss=2.797, ArTop10Accuracy=0.7727, over 11964.00 frames. ], tot_loss[loss=2.891, ArTop10Accuracy=0.7535, over 11365.43 frames. ], batch size: 19, lr: 1.61e-02
2024-08-06 10:06:25,110 INFO [trainer.py:765] (2/8) Epoch 7, batch 700, train_loss[loss=2.876, ArTop10Accuracy=0.7522, over 10353.00 frames. ], tot_loss[loss=2.896, ArTop10Accuracy=0.7524, over 11504.87 frames. ], batch size: 12, lr: 1.60e-02
2024-08-06 10:07:46,949 INFO [trainer.py:765] (2/8) Epoch 7, batch 800, train_loss[loss=2.859, ArTop10Accuracy=0.7643, over 10203.00 frames. ], tot_loss[loss=2.897, ArTop10Accuracy=0.7524, over 11612.79 frames. ], batch size: 12, lr: 1.59e-02
2024-08-06 10:09:02,821 INFO [trainer.py:765] (2/8) Epoch 7, batch 900, train_loss[loss=2.795, ArTop10Accuracy=0.7766, over 12912.00 frames. ], tot_loss[loss=2.892, ArTop10Accuracy=0.7533, over 11666.77 frames. ], batch size: 27, lr: 1.59e-02
2024-08-06 10:10:19,636 INFO [trainer.py:765] (2/8) Epoch 7, batch 1000, train_loss[loss=2.902, ArTop10Accuracy=0.7527, over 12813.00 frames. ], tot_loss[loss=2.894, ArTop10Accuracy=0.7529, over 11861.16 frames. ], batch size: 27, lr: 1.58e-02
2024-08-06 10:11:35,208 INFO [trainer.py:765] (2/8) Epoch 7, batch 1100, train_loss[loss=2.863, ArTop10Accuracy=0.7594, over 13686.00 frames. ], tot_loss[loss=2.9, ArTop10Accuracy=0.7517, over 11940.68 frames. ], batch size: 34, lr: 1.57e-02
2024-08-06 10:12:48,204 INFO [trainer.py:765] (2/8) Epoch 7, batch 1200, train_loss[loss=3.009, ArTop10Accuracy=0.7302, over 11538.00 frames. ], tot_loss[loss=2.897, ArTop10Accuracy=0.7522, over 11860.24 frames. ], batch size: 103, lr: 1.57e-02
2024-08-06 10:13:46,381 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 10:15:03,601 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.017e+02 1.283e+02 1.410e+02 1.601e+02 1.017e+03, threshold=2.820e+02, percent-clipped=0.9
2024-08-06 10:15:40,821 INFO [trainer.py:765] (2/8) Epoch 8, batch 100, train_loss[loss=2.902, ArTop10Accuracy=0.7498, over 14082.00 frames. ], tot_loss[loss=2.885, ArTop10Accuracy=0.7545, over 4743.10 frames. ], batch size: 62, lr: 1.47e-02
2024-08-06 10:17:12,862 INFO [trainer.py:765] (2/8) Epoch 8, batch 200, train_loss[loss=2.889, ArTop10Accuracy=0.7539, over 13659.00 frames. ], tot_loss[loss=2.877, ArTop10Accuracy=0.7557, over 7747.35 frames. ], batch size: 34, lr: 1.46e-02
2024-08-06 10:18:37,898 INFO [trainer.py:765] (2/8) Epoch 8, batch 300, train_loss[loss=2.899, ArTop10Accuracy=0.7508, over 14328.00 frames. ], tot_loss[loss=2.872, ArTop10Accuracy=0.7569, over 9362.59 frames. ], batch size: 44, lr: 1.46e-02
2024-08-06 10:20:06,342 INFO [trainer.py:765] (2/8) Epoch 8, batch 400, train_loss[loss=2.801, ArTop10Accuracy=0.7699, over 10290.00 frames. ], tot_loss[loss=2.862, ArTop10Accuracy=0.7589, over 10271.46 frames. ], batch size: 14, lr: 1.45e-02
2024-08-06 10:21:32,411 INFO [trainer.py:765] (2/8) Epoch 8, batch 500, train_loss[loss=2.819, ArTop10Accuracy=0.7623, over 12291.00 frames. ], tot_loss[loss=2.859, ArTop10Accuracy=0.7595, over 10811.25 frames. ], batch size: 22, lr: 1.45e-02
2024-08-06 10:23:00,974 INFO [trainer.py:765] (2/8) Epoch 8, batch 600, train_loss[loss=2.875, ArTop10Accuracy=0.7605, over 11448.00 frames. ], tot_loss[loss=2.858, ArTop10Accuracy=0.7597, over 11342.02 frames. ], batch size: 18, lr: 1.44e-02
2024-08-06 10:24:37,788 INFO [trainer.py:765] (2/8) Epoch 8, batch 700, train_loss[loss=2.805, ArTop10Accuracy=0.7703, over 9375.00 frames. ], tot_loss[loss=2.865, ArTop10Accuracy=0.7582, over 11499.48 frames. ], batch size: 11, lr: 1.43e-02
2024-08-06 10:25:56,085 INFO [trainer.py:765] (2/8) Epoch 8, batch 800, train_loss[loss=2.802, ArTop10Accuracy=0.7732, over 9558.00 frames. ], tot_loss[loss=2.872, ArTop10Accuracy=0.7568, over 11628.09 frames. ], batch size: 11, lr: 1.43e-02
2024-08-06 10:27:12,244 INFO [trainer.py:765] (2/8) Epoch 8, batch 900, train_loss[loss=2.901, ArTop10Accuracy=0.7464, over 13362.00 frames. ], tot_loss[loss=2.873, ArTop10Accuracy=0.7566, over 11687.71 frames. ], batch size: 28, lr: 1.42e-02
2024-08-06 10:28:25,263 INFO [trainer.py:765] (2/8) Epoch 8, batch 1000, train_loss[loss=2.916, ArTop10Accuracy=0.7449, over 12993.00 frames. ], tot_loss[loss=2.877, ArTop10Accuracy=0.7559, over 11886.99 frames. ], batch size: 27, lr: 1.42e-02
2024-08-06 10:29:07,156 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 10:29:16,830 INFO [trainer.py:811] (2/8) Epoch 8, validation: loss=2.858, ArTop10Accuracy=0.7594, over 1827537.00 frames. 
2024-08-06 10:29:16,831 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 33008MB
2024-08-06 10:29:17,491 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.032e+02 1.275e+02 1.390e+02 1.547e+02 3.717e+02, threshold=2.781e+02, percent-clipped=0.7
2024-08-06 10:29:51,731 INFO [trainer.py:765] (2/8) Epoch 8, batch 1100, train_loss[loss=2.966, ArTop10Accuracy=0.7374, over 13548.00 frames. ], tot_loss[loss=2.881, ArTop10Accuracy=0.7551, over 11952.90 frames. ], batch size: 34, lr: 1.41e-02
2024-08-06 10:31:05,946 INFO [trainer.py:765] (2/8) Epoch 8, batch 1200, train_loss[loss=2.996, ArTop10Accuracy=0.7329, over 12714.00 frames. ], tot_loss[loss=2.878, ArTop10Accuracy=0.7555, over 11867.75 frames. ], batch size: 103, lr: 1.40e-02
2024-08-06 10:32:05,631 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 10:34:01,257 INFO [trainer.py:765] (2/8) Epoch 9, batch 100, train_loss[loss=2.938, ArTop10Accuracy=0.7441, over 14586.00 frames. ], tot_loss[loss=2.864, ArTop10Accuracy=0.7581, over 4765.68 frames. ], batch size: 62, lr: 1.32e-02
2024-08-06 10:35:31,773 INFO [trainer.py:765] (2/8) Epoch 9, batch 200, train_loss[loss=2.9, ArTop10Accuracy=0.7475, over 13782.00 frames. ], tot_loss[loss=2.856, ArTop10Accuracy=0.7596, over 7752.54 frames. ], batch size: 34, lr: 1.32e-02
2024-08-06 10:36:57,928 INFO [trainer.py:765] (2/8) Epoch 9, batch 300, train_loss[loss=2.8, ArTop10Accuracy=0.7712, over 14121.00 frames. ], tot_loss[loss=2.849, ArTop10Accuracy=0.7611, over 9397.10 frames. ], batch size: 44, lr: 1.31e-02
2024-08-06 10:38:32,697 INFO [trainer.py:765] (2/8) Epoch 9, batch 400, train_loss[loss=2.738, ArTop10Accuracy=0.7828, over 10422.00 frames. ], tot_loss[loss=2.847, ArTop10Accuracy=0.7617, over 10292.77 frames. ], batch size: 14, lr: 1.31e-02
2024-08-06 10:39:59,258 INFO [trainer.py:765] (2/8) Epoch 9, batch 500, train_loss[loss=2.854, ArTop10Accuracy=0.7616, over 12159.00 frames. ], tot_loss[loss=2.842, ArTop10Accuracy=0.7626, over 10855.51 frames. ], batch size: 22, lr: 1.30e-02
2024-08-06 10:41:29,688 INFO [trainer.py:765] (2/8) Epoch 9, batch 600, train_loss[loss=2.898, ArTop10Accuracy=0.7517, over 11454.00 frames. ], tot_loss[loss=2.847, ArTop10Accuracy=0.7617, over 11360.35 frames. ], batch size: 18, lr: 1.30e-02
2024-08-06 10:42:58,441 INFO [trainer.py:765] (2/8) Epoch 9, batch 700, train_loss[loss=2.905, ArTop10Accuracy=0.7533, over 10239.00 frames. ], tot_loss[loss=2.848, ArTop10Accuracy=0.7615, over 11519.40 frames. ], batch size: 12, lr: 1.29e-02
2024-08-06 10:44:02,952 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.039e+02 1.253e+02 1.352e+02 1.493e+02 7.010e+02, threshold=2.704e+02, percent-clipped=0.6
2024-08-06 10:44:19,670 INFO [trainer.py:765] (2/8) Epoch 9, batch 800, train_loss[loss=2.826, ArTop10Accuracy=0.765, over 10275.00 frames. ], tot_loss[loss=2.849, ArTop10Accuracy=0.7612, over 11632.47 frames. ], batch size: 12, lr: 1.29e-02
2024-08-06 10:45:35,719 INFO [trainer.py:765] (2/8) Epoch 9, batch 900, train_loss[loss=2.826, ArTop10Accuracy=0.7678, over 12942.00 frames. ], tot_loss[loss=2.843, ArTop10Accuracy=0.7624, over 11680.07 frames. ], batch size: 27, lr: 1.28e-02
2024-08-06 10:46:51,272 INFO [trainer.py:765] (2/8) Epoch 9, batch 1000, train_loss[loss=2.815, ArTop10Accuracy=0.7701, over 12792.00 frames. ], tot_loss[loss=2.849, ArTop10Accuracy=0.7614, over 11876.81 frames. ], batch size: 27, lr: 1.28e-02
2024-08-06 10:48:06,247 INFO [trainer.py:765] (2/8) Epoch 9, batch 1100, train_loss[loss=2.844, ArTop10Accuracy=0.765, over 13515.00 frames. ], tot_loss[loss=2.854, ArTop10Accuracy=0.7605, over 11950.97 frames. ], batch size: 34, lr: 1.28e-02
2024-08-06 10:49:21,053 INFO [trainer.py:765] (2/8) Epoch 9, batch 1200, train_loss[loss=2.933, ArTop10Accuracy=0.7475, over 12606.00 frames. ], tot_loss[loss=2.854, ArTop10Accuracy=0.7604, over 11852.02 frames. ], batch size: 101, lr: 1.27e-02
2024-08-06 10:50:22,705 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 10:52:12,326 INFO [trainer.py:765] (2/8) Epoch 10, batch 100, train_loss[loss=2.848, ArTop10Accuracy=0.7638, over 14544.00 frames. ], tot_loss[loss=2.835, ArTop10Accuracy=0.7632, over 4772.41 frames. ], batch size: 62, lr: 1.20e-02
2024-08-06 10:53:44,586 INFO [trainer.py:765] (2/8) Epoch 10, batch 200, train_loss[loss=2.894, ArTop10Accuracy=0.7551, over 13695.00 frames. ], tot_loss[loss=2.83, ArTop10Accuracy=0.7647, over 7750.75 frames. ], batch size: 34, lr: 1.20e-02
2024-08-06 10:55:08,090 INFO [trainer.py:765] (2/8) Epoch 10, batch 300, train_loss[loss=2.908, ArTop10Accuracy=0.7534, over 14178.00 frames. ], tot_loss[loss=2.827, ArTop10Accuracy=0.7653, over 9377.29 frames. ], batch size: 44, lr: 1.19e-02
2024-08-06 10:56:41,175 INFO [trainer.py:765] (2/8) Epoch 10, batch 400, train_loss[loss=2.698, ArTop10Accuracy=0.7918, over 10212.00 frames. ], tot_loss[loss=2.826, ArTop10Accuracy=0.7655, over 10290.51 frames. ], batch size: 14, lr: 1.19e-02
2024-08-06 10:58:04,938 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 10:58:14,557 INFO [trainer.py:811] (2/8) Epoch 10, validation: loss=2.842, ArTop10Accuracy=0.7624, over 1827537.00 frames. 
2024-08-06 10:58:14,558 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 33008MB
2024-08-06 10:58:15,570 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.035e+02 1.228e+02 1.320e+02 1.458e+02 6.096e+02, threshold=2.641e+02, percent-clipped=0.6
2024-08-06 10:58:15,575 INFO [trainer.py:765] (2/8) Epoch 10, batch 500, train_loss[loss=2.761, ArTop10Accuracy=0.7821, over 12861.00 frames. ], tot_loss[loss=2.821, ArTop10Accuracy=0.7663, over 10857.40 frames. ], batch size: 23, lr: 1.19e-02
2024-08-06 10:59:42,814 INFO [trainer.py:765] (2/8) Epoch 10, batch 600, train_loss[loss=2.725, ArTop10Accuracy=0.7842, over 11610.00 frames. ], tot_loss[loss=2.82, ArTop10Accuracy=0.7667, over 11367.33 frames. ], batch size: 18, lr: 1.18e-02
2024-08-06 11:01:18,107 INFO [trainer.py:765] (2/8) Epoch 10, batch 700, train_loss[loss=2.806, ArTop10Accuracy=0.7697, over 9408.00 frames. ], tot_loss[loss=2.827, ArTop10Accuracy=0.7654, over 11509.69 frames. ], batch size: 11, lr: 1.18e-02
2024-08-06 11:02:36,917 INFO [trainer.py:765] (2/8) Epoch 10, batch 800, train_loss[loss=2.718, ArTop10Accuracy=0.7886, over 9372.00 frames. ], tot_loss[loss=2.832, ArTop10Accuracy=0.7645, over 11622.04 frames. ], batch size: 11, lr: 1.17e-02
2024-08-06 11:03:51,212 INFO [trainer.py:765] (2/8) Epoch 10, batch 900, train_loss[loss=2.789, ArTop10Accuracy=0.7745, over 12852.00 frames. ], tot_loss[loss=2.825, ArTop10Accuracy=0.7658, over 11675.50 frames. ], batch size: 27, lr: 1.17e-02
2024-08-06 11:05:06,352 INFO [trainer.py:765] (2/8) Epoch 10, batch 1000, train_loss[loss=2.797, ArTop10Accuracy=0.7696, over 13302.00 frames. ], tot_loss[loss=2.829, ArTop10Accuracy=0.7649, over 11874.18 frames. ], batch size: 28, lr: 1.17e-02
2024-08-06 11:06:21,720 INFO [trainer.py:765] (2/8) Epoch 10, batch 1100, train_loss[loss=2.756, ArTop10Accuracy=0.7815, over 13491.00 frames. ], tot_loss[loss=2.832, ArTop10Accuracy=0.7642, over 11941.88 frames. ], batch size: 34, lr: 1.16e-02
2024-08-06 11:07:34,772 INFO [trainer.py:765] (2/8) Epoch 10, batch 1200, train_loss[loss=2.953, ArTop10Accuracy=0.7409, over 12528.00 frames. ], tot_loss[loss=2.837, ArTop10Accuracy=0.7635, over 11862.54 frames. ], batch size: 101, lr: 1.16e-02
2024-08-06 11:08:33,717 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 11:10:29,954 INFO [trainer.py:765] (2/8) Epoch 11, batch 100, train_loss[loss=2.905, ArTop10Accuracy=0.7495, over 14376.00 frames. ], tot_loss[loss=2.823, ArTop10Accuracy=0.766, over 4753.26 frames. ], batch size: 62, lr: 1.10e-02
2024-08-06 11:12:04,673 INFO [trainer.py:765] (2/8) Epoch 11, batch 200, train_loss[loss=2.831, ArTop10Accuracy=0.7636, over 13989.00 frames. ], tot_loss[loss=2.814, ArTop10Accuracy=0.7677, over 7754.04 frames. ], batch size: 35, lr: 1.10e-02
2024-08-06 11:12:22,825 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 9.884e+01 1.240e+02 1.333e+02 1.457e+02 6.939e+02, threshold=2.667e+02, percent-clipped=0.1
2024-08-06 11:13:31,545 INFO [trainer.py:765] (2/8) Epoch 11, batch 300, train_loss[loss=2.864, ArTop10Accuracy=0.7564, over 14175.00 frames. ], tot_loss[loss=2.807, ArTop10Accuracy=0.7691, over 9363.48 frames. ], batch size: 44, lr: 1.09e-02
2024-08-06 11:15:03,269 INFO [trainer.py:765] (2/8) Epoch 11, batch 400, train_loss[loss=2.861, ArTop10Accuracy=0.7604, over 10101.00 frames. ], tot_loss[loss=2.804, ArTop10Accuracy=0.7696, over 10275.08 frames. ], batch size: 14, lr: 1.09e-02
2024-08-06 11:16:29,637 INFO [trainer.py:765] (2/8) Epoch 11, batch 500, train_loss[loss=2.773, ArTop10Accuracy=0.7726, over 12708.00 frames. ], tot_loss[loss=2.805, ArTop10Accuracy=0.7693, over 10826.48 frames. ], batch size: 23, lr: 1.09e-02
2024-08-06 11:18:00,517 INFO [trainer.py:765] (2/8) Epoch 11, batch 600, train_loss[loss=2.764, ArTop10Accuracy=0.7791, over 11493.00 frames. ], tot_loss[loss=2.806, ArTop10Accuracy=0.7693, over 11350.63 frames. ], batch size: 18, lr: 1.08e-02
2024-08-06 11:19:34,511 INFO [trainer.py:765] (2/8) Epoch 11, batch 700, train_loss[loss=2.662, ArTop10Accuracy=0.7939, over 9405.00 frames. ], tot_loss[loss=2.809, ArTop10Accuracy=0.7687, over 11500.78 frames. ], batch size: 11, lr: 1.08e-02
2024-08-06 11:20:55,480 INFO [trainer.py:765] (2/8) Epoch 11, batch 800, train_loss[loss=2.791, ArTop10Accuracy=0.7738, over 10173.00 frames. ], tot_loss[loss=2.812, ArTop10Accuracy=0.7684, over 11644.67 frames. ], batch size: 12, lr: 1.07e-02
2024-08-06 11:22:13,705 INFO [trainer.py:765] (2/8) Epoch 11, batch 900, train_loss[loss=2.791, ArTop10Accuracy=0.7762, over 13308.00 frames. ], tot_loss[loss=2.81, ArTop10Accuracy=0.7689, over 11696.54 frames. ], batch size: 28, lr: 1.07e-02
2024-08-06 11:23:31,799 INFO [trainer.py:765] (2/8) Epoch 11, batch 1000, train_loss[loss=2.792, ArTop10Accuracy=0.766, over 12885.00 frames. ], tot_loss[loss=2.812, ArTop10Accuracy=0.7682, over 11886.02 frames. ], batch size: 27, lr: 1.07e-02
2024-08-06 11:24:46,902 INFO [trainer.py:765] (2/8) Epoch 11, batch 1100, train_loss[loss=2.821, ArTop10Accuracy=0.7629, over 13929.00 frames. ], tot_loss[loss=2.821, ArTop10Accuracy=0.7664, over 11966.48 frames. ], batch size: 35, lr: 1.06e-02
2024-08-06 11:26:00,733 INFO [trainer.py:765] (2/8) Epoch 11, batch 1200, train_loss[loss=2.978, ArTop10Accuracy=0.7354, over 11682.00 frames. ], tot_loss[loss=2.819, ArTop10Accuracy=0.7667, over 11862.92 frames. ], batch size: 101, lr: 1.06e-02
2024-08-06 11:26:15,847 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 11:26:25,556 INFO [trainer.py:811] (2/8) Epoch 11, validation: loss=2.831, ArTop10Accuracy=0.7643, over 1827537.00 frames. 
2024-08-06 11:26:25,557 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 33008MB
2024-08-06 11:26:26,185 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.029e+02 1.251e+02 1.335e+02 1.441e+02 2.942e+02, threshold=2.669e+02, percent-clipped=0.1
2024-08-06 11:27:09,617 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 11:29:03,450 INFO [trainer.py:765] (2/8) Epoch 12, batch 100, train_loss[loss=2.878, ArTop10Accuracy=0.755, over 14742.00 frames. ], tot_loss[loss=2.809, ArTop10Accuracy=0.7682, over 4789.07 frames. ], batch size: 62, lr: 1.01e-02
2024-08-06 11:30:30,672 INFO [trainer.py:765] (2/8) Epoch 12, batch 200, train_loss[loss=2.788, ArTop10Accuracy=0.7703, over 13956.00 frames. ], tot_loss[loss=2.802, ArTop10Accuracy=0.7696, over 7759.42 frames. ], batch size: 34, lr: 1.01e-02
2024-08-06 11:31:57,655 INFO [trainer.py:765] (2/8) Epoch 12, batch 300, train_loss[loss=2.867, ArTop10Accuracy=0.7579, over 14355.00 frames. ], tot_loss[loss=2.799, ArTop10Accuracy=0.7703, over 9398.69 frames. ], batch size: 45, lr: 1.01e-02
2024-08-06 11:33:30,738 INFO [trainer.py:765] (2/8) Epoch 12, batch 400, train_loss[loss=2.621, ArTop10Accuracy=0.8039, over 10920.00 frames. ], tot_loss[loss=2.795, ArTop10Accuracy=0.7713, over 10284.91 frames. ], batch size: 15, lr: 1.00e-02
2024-08-06 11:34:55,731 INFO [trainer.py:765] (2/8) Epoch 12, batch 500, train_loss[loss=2.757, ArTop10Accuracy=0.7775, over 12078.00 frames. ], tot_loss[loss=2.789, ArTop10Accuracy=0.7725, over 10826.63 frames. ], batch size: 22, lr: 1.00e-02
2024-08-06 11:36:29,362 INFO [trainer.py:765] (2/8) Epoch 12, batch 600, train_loss[loss=2.762, ArTop10Accuracy=0.7754, over 11370.00 frames. ], tot_loss[loss=2.79, ArTop10Accuracy=0.7722, over 11358.90 frames. ], batch size: 18, lr: 9.97e-03
2024-08-06 11:38:00,343 INFO [trainer.py:765] (2/8) Epoch 12, batch 700, train_loss[loss=2.66, ArTop10Accuracy=0.7981, over 10167.00 frames. ], tot_loss[loss=2.794, ArTop10Accuracy=0.7716, over 11498.68 frames. ], batch size: 12, lr: 9.93e-03
2024-08-06 11:39:23,610 INFO [trainer.py:765] (2/8) Epoch 12, batch 800, train_loss[loss=2.768, ArTop10Accuracy=0.7754, over 10056.00 frames. ], tot_loss[loss=2.796, ArTop10Accuracy=0.7714, over 11621.85 frames. ], batch size: 12, lr: 9.90e-03
2024-08-06 11:40:39,889 INFO [trainer.py:765] (2/8) Epoch 12, batch 900, train_loss[loss=2.752, ArTop10Accuracy=0.7747, over 13314.00 frames. ], tot_loss[loss=2.794, ArTop10Accuracy=0.7718, over 11684.35 frames. ], batch size: 28, lr: 9.87e-03
2024-08-06 11:41:13,993 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.041e+02 1.248e+02 1.348e+02 1.459e+02 5.540e+02, threshold=2.695e+02, percent-clipped=0.3
2024-08-06 11:41:56,189 INFO [trainer.py:765] (2/8) Epoch 12, batch 1000, train_loss[loss=2.823, ArTop10Accuracy=0.7637, over 13404.00 frames. ], tot_loss[loss=2.799, ArTop10Accuracy=0.7708, over 11891.06 frames. ], batch size: 28, lr: 9.85e-03
2024-08-06 11:43:14,320 INFO [trainer.py:765] (2/8) Epoch 12, batch 1100, train_loss[loss=2.808, ArTop10Accuracy=0.7702, over 13656.00 frames. ], tot_loss[loss=2.805, ArTop10Accuracy=0.7695, over 11941.91 frames. ], batch size: 34, lr: 9.82e-03
2024-08-06 11:44:26,155 INFO [trainer.py:765] (2/8) Epoch 12, batch 1200, train_loss[loss=2.945, ArTop10Accuracy=0.7388, over 12102.00 frames. ], tot_loss[loss=2.804, ArTop10Accuracy=0.7694, over 11857.94 frames. ], batch size: 101, lr: 9.79e-03
2024-08-06 11:45:26,863 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 11:47:26,600 INFO [trainer.py:765] (2/8) Epoch 13, batch 100, train_loss[loss=2.827, ArTop10Accuracy=0.7635, over 14637.00 frames. ], tot_loss[loss=2.793, ArTop10Accuracy=0.7713, over 4744.99 frames. ], batch size: 62, lr: 9.37e-03
2024-08-06 11:48:54,778 INFO [trainer.py:765] (2/8) Epoch 13, batch 200, train_loss[loss=2.797, ArTop10Accuracy=0.7655, over 13446.00 frames. ], tot_loss[loss=2.785, ArTop10Accuracy=0.7728, over 7731.58 frames. ], batch size: 34, lr: 9.34e-03
2024-08-06 11:50:20,515 INFO [trainer.py:765] (2/8) Epoch 13, batch 300, train_loss[loss=2.8, ArTop10Accuracy=0.7724, over 14124.00 frames. ], tot_loss[loss=2.782, ArTop10Accuracy=0.7733, over 9354.51 frames. ], batch size: 44, lr: 9.31e-03
2024-08-06 11:51:48,764 INFO [trainer.py:765] (2/8) Epoch 13, batch 400, train_loss[loss=2.705, ArTop10Accuracy=0.7874, over 10371.00 frames. ], tot_loss[loss=2.777, ArTop10Accuracy=0.7745, over 10278.47 frames. ], batch size: 14, lr: 9.28e-03
2024-08-06 11:53:13,405 INFO [trainer.py:765] (2/8) Epoch 13, batch 500, train_loss[loss=2.679, ArTop10Accuracy=0.7927, over 12141.00 frames. ], tot_loss[loss=2.772, ArTop10Accuracy=0.7756, over 10843.83 frames. ], batch size: 22, lr: 9.26e-03
2024-08-06 11:54:52,223 INFO [trainer.py:765] (2/8) Epoch 13, batch 600, train_loss[loss=2.73, ArTop10Accuracy=0.7851, over 11412.00 frames. ], tot_loss[loss=2.774, ArTop10Accuracy=0.7752, over 11366.55 frames. ], batch size: 18, lr: 9.23e-03
2024-08-06 11:55:47,081 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 11:55:56,835 INFO [trainer.py:811] (2/8) Epoch 13, validation: loss=2.824, ArTop10Accuracy=0.7662, over 1827537.00 frames. 
2024-08-06 11:55:56,835 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 33008MB
2024-08-06 11:55:57,711 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.064e+02 1.255e+02 1.343e+02 1.452e+02 4.888e+02, threshold=2.687e+02, percent-clipped=0.1
2024-08-06 11:56:28,465 INFO [trainer.py:765] (2/8) Epoch 13, batch 700, train_loss[loss=2.789, ArTop10Accuracy=0.7731, over 10020.00 frames. ], tot_loss[loss=2.78, ArTop10Accuracy=0.7741, over 11510.09 frames. ], batch size: 12, lr: 9.20e-03
2024-08-06 11:57:46,683 INFO [trainer.py:765] (2/8) Epoch 13, batch 800, train_loss[loss=2.646, ArTop10Accuracy=0.8021, over 10278.00 frames. ], tot_loss[loss=2.783, ArTop10Accuracy=0.7736, over 11638.26 frames. ], batch size: 12, lr: 9.18e-03
2024-08-06 11:59:03,284 INFO [trainer.py:765] (2/8) Epoch 13, batch 900, train_loss[loss=2.749, ArTop10Accuracy=0.7827, over 12804.00 frames. ], tot_loss[loss=2.778, ArTop10Accuracy=0.7745, over 11690.54 frames. ], batch size: 27, lr: 9.15e-03
2024-08-06 12:00:19,175 INFO [trainer.py:765] (2/8) Epoch 13, batch 1000, train_loss[loss=2.778, ArTop10Accuracy=0.7769, over 12894.00 frames. ], tot_loss[loss=2.785, ArTop10Accuracy=0.7733, over 11902.64 frames. ], batch size: 27, lr: 9.13e-03
2024-08-06 12:01:34,879 INFO [trainer.py:765] (2/8) Epoch 13, batch 1100, train_loss[loss=2.878, ArTop10Accuracy=0.7554, over 13428.00 frames. ], tot_loss[loss=2.794, ArTop10Accuracy=0.7717, over 11968.13 frames. ], batch size: 34, lr: 9.10e-03
2024-08-06 12:02:48,662 INFO [trainer.py:765] (2/8) Epoch 13, batch 1200, train_loss[loss=2.927, ArTop10Accuracy=0.7453, over 12432.00 frames. ], tot_loss[loss=2.795, ArTop10Accuracy=0.7716, over 11888.02 frames. ], batch size: 101, lr: 9.08e-03
2024-08-06 12:03:48,159 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 12:05:45,332 INFO [trainer.py:765] (2/8) Epoch 14, batch 100, train_loss[loss=2.837, ArTop10Accuracy=0.7623, over 14376.00 frames. ], tot_loss[loss=2.777, ArTop10Accuracy=0.7738, over 4767.97 frames. ], batch size: 62, lr: 8.71e-03
2024-08-06 12:07:16,602 INFO [trainer.py:765] (2/8) Epoch 14, batch 200, train_loss[loss=2.785, ArTop10Accuracy=0.7733, over 13857.00 frames. ], tot_loss[loss=2.769, ArTop10Accuracy=0.7755, over 7753.86 frames. ], batch size: 34, lr: 8.69e-03
2024-08-06 12:08:44,311 INFO [trainer.py:765] (2/8) Epoch 14, batch 300, train_loss[loss=2.779, ArTop10Accuracy=0.772, over 14271.00 frames. ], tot_loss[loss=2.764, ArTop10Accuracy=0.7764, over 9384.04 frames. ], batch size: 44, lr: 8.66e-03
2024-08-06 12:10:01,129 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.072e+02 1.266e+02 1.374e+02 1.483e+02 6.480e+02, threshold=2.748e+02, percent-clipped=0.2
2024-08-06 12:10:10,227 INFO [trainer.py:765] (2/8) Epoch 14, batch 400, train_loss[loss=2.689, ArTop10Accuracy=0.7941, over 11049.00 frames. ], tot_loss[loss=2.764, ArTop10Accuracy=0.7769, over 10302.72 frames. ], batch size: 15, lr: 8.64e-03
2024-08-06 12:11:36,151 INFO [trainer.py:765] (2/8) Epoch 14, batch 500, train_loss[loss=2.766, ArTop10Accuracy=0.7788, over 12171.00 frames. ], tot_loss[loss=2.759, ArTop10Accuracy=0.778, over 10839.36 frames. ], batch size: 22, lr: 8.62e-03
2024-08-06 12:13:05,995 INFO [trainer.py:765] (2/8) Epoch 14, batch 600, train_loss[loss=2.759, ArTop10Accuracy=0.7802, over 11607.00 frames. ], tot_loss[loss=2.764, ArTop10Accuracy=0.7772, over 11352.46 frames. ], batch size: 18, lr: 8.59e-03
2024-08-06 12:14:38,554 INFO [trainer.py:765] (2/8) Epoch 14, batch 700, train_loss[loss=2.653, ArTop10Accuracy=0.7979, over 10074.00 frames. ], tot_loss[loss=2.767, ArTop10Accuracy=0.7766, over 11499.27 frames. ], batch size: 12, lr: 8.57e-03
2024-08-06 12:15:58,072 INFO [trainer.py:765] (2/8) Epoch 14, batch 800, train_loss[loss=2.697, ArTop10Accuracy=0.7895, over 9354.00 frames. ], tot_loss[loss=2.771, ArTop10Accuracy=0.7758, over 11630.13 frames. ], batch size: 11, lr: 8.55e-03
2024-08-06 12:17:12,866 INFO [trainer.py:765] (2/8) Epoch 14, batch 900, train_loss[loss=2.692, ArTop10Accuracy=0.7951, over 12969.00 frames. ], tot_loss[loss=2.767, ArTop10Accuracy=0.7764, over 11672.33 frames. ], batch size: 27, lr: 8.52e-03
2024-08-06 12:18:29,612 INFO [trainer.py:765] (2/8) Epoch 14, batch 1000, train_loss[loss=2.764, ArTop10Accuracy=0.7829, over 12813.00 frames. ], tot_loss[loss=2.772, ArTop10Accuracy=0.7754, over 11880.22 frames. ], batch size: 27, lr: 8.50e-03
2024-08-06 12:19:45,377 INFO [trainer.py:765] (2/8) Epoch 14, batch 1100, train_loss[loss=2.763, ArTop10Accuracy=0.7783, over 13455.00 frames. ], tot_loss[loss=2.777, ArTop10Accuracy=0.7746, over 11943.84 frames. ], batch size: 34, lr: 8.48e-03
2024-08-06 12:20:59,279 INFO [trainer.py:765] (2/8) Epoch 14, batch 1200, train_loss[loss=2.902, ArTop10Accuracy=0.7476, over 11772.00 frames. ], tot_loss[loss=2.78, ArTop10Accuracy=0.774, over 11847.85 frames. ], batch size: 101, lr: 8.46e-03
2024-08-06 12:21:58,162 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 12:23:51,961 INFO [trainer.py:765] (2/8) Epoch 15, batch 100, train_loss[loss=2.847, ArTop10Accuracy=0.7598, over 14640.00 frames. ], tot_loss[loss=2.77, ArTop10Accuracy=0.7752, over 4775.25 frames. ], batch size: 62, lr: 8.14e-03
2024-08-06 12:24:00,598 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 12:24:10,290 INFO [trainer.py:811] (2/8) Epoch 15, validation: loss=2.819, ArTop10Accuracy=0.7675, over 1827537.00 frames. 
2024-08-06 12:24:10,291 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 33008MB
2024-08-06 12:24:11,094 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.080e+02 1.284e+02 1.371e+02 1.488e+02 4.667e+02, threshold=2.743e+02, percent-clipped=0.2
2024-08-06 12:25:29,986 INFO [trainer.py:765] (2/8) Epoch 15, batch 200, train_loss[loss=2.764, ArTop10Accuracy=0.7793, over 13491.00 frames. ], tot_loss[loss=2.755, ArTop10Accuracy=0.7786, over 7767.90 frames. ], batch size: 34, lr: 8.12e-03
2024-08-06 12:26:58,695 INFO [trainer.py:765] (2/8) Epoch 15, batch 300, train_loss[loss=2.755, ArTop10Accuracy=0.7769, over 14298.00 frames. ], tot_loss[loss=2.751, ArTop10Accuracy=0.7791, over 9413.88 frames. ], batch size: 44, lr: 8.09e-03
2024-08-06 12:28:28,533 INFO [trainer.py:765] (2/8) Epoch 15, batch 400, train_loss[loss=2.735, ArTop10Accuracy=0.7841, over 10920.00 frames. ], tot_loss[loss=2.75, ArTop10Accuracy=0.7793, over 10302.96 frames. ], batch size: 15, lr: 8.07e-03
2024-08-06 12:29:54,031 INFO [trainer.py:765] (2/8) Epoch 15, batch 500, train_loss[loss=2.659, ArTop10Accuracy=0.7957, over 12117.00 frames. ], tot_loss[loss=2.746, ArTop10Accuracy=0.7804, over 10858.01 frames. ], batch size: 22, lr: 8.05e-03
2024-08-06 12:31:23,293 INFO [trainer.py:765] (2/8) Epoch 15, batch 600, train_loss[loss=2.7, ArTop10Accuracy=0.7888, over 11391.00 frames. ], tot_loss[loss=2.75, ArTop10Accuracy=0.7795, over 11375.98 frames. ], batch size: 18, lr: 8.03e-03
2024-08-06 12:32:53,174 INFO [trainer.py:765] (2/8) Epoch 15, batch 700, train_loss[loss=2.552, ArTop10Accuracy=0.8162, over 9945.00 frames. ], tot_loss[loss=2.755, ArTop10Accuracy=0.7785, over 11508.10 frames. ], batch size: 12, lr: 8.01e-03
2024-08-06 12:34:18,254 INFO [trainer.py:765] (2/8) Epoch 15, batch 800, train_loss[loss=2.783, ArTop10Accuracy=0.773, over 10314.00 frames. ], tot_loss[loss=2.758, ArTop10Accuracy=0.7781, over 11629.59 frames. ], batch size: 12, lr: 7.99e-03
2024-08-06 12:35:34,728 INFO [trainer.py:765] (2/8) Epoch 15, batch 900, train_loss[loss=2.818, ArTop10Accuracy=0.7685, over 12936.00 frames. ], tot_loss[loss=2.752, ArTop10Accuracy=0.7794, over 11669.12 frames. ], batch size: 27, lr: 7.97e-03
2024-08-06 12:36:50,541 INFO [trainer.py:765] (2/8) Epoch 15, batch 1000, train_loss[loss=2.774, ArTop10Accuracy=0.7705, over 12861.00 frames. ], tot_loss[loss=2.758, ArTop10Accuracy=0.7781, over 11870.57 frames. ], batch size: 27, lr: 7.95e-03
2024-08-06 12:38:05,177 INFO [trainer.py:765] (2/8) Epoch 15, batch 1100, train_loss[loss=2.838, ArTop10Accuracy=0.763, over 13584.00 frames. ], tot_loss[loss=2.765, ArTop10Accuracy=0.7767, over 11923.60 frames. ], batch size: 34, lr: 7.93e-03
2024-08-06 12:38:12,841 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.080e+02 1.293e+02 1.379e+02 1.467e+02 2.824e+02, threshold=2.759e+02, percent-clipped=0.1
2024-08-06 12:39:18,789 INFO [trainer.py:765] (2/8) Epoch 15, batch 1200, train_loss[loss=2.862, ArTop10Accuracy=0.7544, over 12441.00 frames. ], tot_loss[loss=2.764, ArTop10Accuracy=0.777, over 11837.70 frames. ], batch size: 101, lr: 7.91e-03
2024-08-06 12:40:18,530 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 12:42:17,617 INFO [trainer.py:765] (2/8) Epoch 16, batch 100, train_loss[loss=2.803, ArTop10Accuracy=0.7697, over 14316.00 frames. ], tot_loss[loss=2.754, ArTop10Accuracy=0.7784, over 4759.65 frames. ], batch size: 63, lr: 7.63e-03
2024-08-06 12:43:49,563 INFO [trainer.py:765] (2/8) Epoch 16, batch 200, train_loss[loss=2.635, ArTop10Accuracy=0.799, over 13557.00 frames. ], tot_loss[loss=2.748, ArTop10Accuracy=0.7797, over 7747.42 frames. ], batch size: 34, lr: 7.61e-03
2024-08-06 12:45:18,502 INFO [trainer.py:765] (2/8) Epoch 16, batch 300, train_loss[loss=2.834, ArTop10Accuracy=0.7625, over 13779.00 frames. ], tot_loss[loss=2.741, ArTop10Accuracy=0.781, over 9373.27 frames. ], batch size: 44, lr: 7.59e-03
2024-08-06 12:46:45,207 INFO [trainer.py:765] (2/8) Epoch 16, batch 400, train_loss[loss=2.708, ArTop10Accuracy=0.7908, over 10155.00 frames. ], tot_loss[loss=2.735, ArTop10Accuracy=0.7825, over 10260.65 frames. ], batch size: 14, lr: 7.58e-03
2024-08-06 12:48:16,310 INFO [trainer.py:765] (2/8) Epoch 16, batch 500, train_loss[loss=2.684, ArTop10Accuracy=0.7932, over 12183.00 frames. ], tot_loss[loss=2.731, ArTop10Accuracy=0.7832, over 10821.97 frames. ], batch size: 22, lr: 7.56e-03
2024-08-06 12:49:46,642 INFO [trainer.py:765] (2/8) Epoch 16, batch 600, train_loss[loss=2.672, ArTop10Accuracy=0.7957, over 11847.00 frames. ], tot_loss[loss=2.734, ArTop10Accuracy=0.7826, over 11354.91 frames. ], batch size: 19, lr: 7.54e-03
2024-08-06 12:51:23,681 INFO [trainer.py:765] (2/8) Epoch 16, batch 700, train_loss[loss=2.805, ArTop10Accuracy=0.7707, over 9318.00 frames. ], tot_loss[loss=2.744, ArTop10Accuracy=0.7808, over 11503.01 frames. ], batch size: 11, lr: 7.52e-03
2024-08-06 12:52:43,501 INFO [trainer.py:765] (2/8) Epoch 16, batch 800, train_loss[loss=2.669, ArTop10Accuracy=0.793, over 10242.00 frames. ], tot_loss[loss=2.752, ArTop10Accuracy=0.7792, over 11612.27 frames. ], batch size: 12, lr: 7.51e-03
2024-08-06 12:53:06,014 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 12:53:15,496 INFO [trainer.py:811] (2/8) Epoch 16, validation: loss=2.816, ArTop10Accuracy=0.7678, over 1827537.00 frames. 
2024-08-06 12:53:15,497 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 33008MB
2024-08-06 12:53:16,186 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.112e+02 1.291e+02 1.391e+02 1.487e+02 3.459e+02, threshold=2.783e+02, percent-clipped=0.1
2024-08-06 12:54:06,481 INFO [trainer.py:765] (2/8) Epoch 16, batch 900, train_loss[loss=2.798, ArTop10Accuracy=0.7704, over 12786.00 frames. ], tot_loss[loss=2.747, ArTop10Accuracy=0.78, over 11657.17 frames. ], batch size: 27, lr: 7.49e-03
2024-08-06 12:55:19,792 INFO [trainer.py:765] (2/8) Epoch 16, batch 1000, train_loss[loss=2.778, ArTop10Accuracy=0.7748, over 12894.00 frames. ], tot_loss[loss=2.751, ArTop10Accuracy=0.7795, over 11860.56 frames. ], batch size: 27, lr: 7.47e-03
2024-08-06 12:56:33,162 INFO [trainer.py:765] (2/8) Epoch 16, batch 1100, train_loss[loss=2.797, ArTop10Accuracy=0.7688, over 13869.00 frames. ], tot_loss[loss=2.758, ArTop10Accuracy=0.7783, over 11950.02 frames. ], batch size: 35, lr: 7.45e-03
2024-08-06 12:57:48,485 INFO [trainer.py:765] (2/8) Epoch 16, batch 1200, train_loss[loss=2.856, ArTop10Accuracy=0.7589, over 12633.00 frames. ], tot_loss[loss=2.757, ArTop10Accuracy=0.7783, over 11848.50 frames. ], batch size: 103, lr: 7.44e-03
2024-08-06 12:58:48,362 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 13:00:47,898 INFO [trainer.py:765] (2/8) Epoch 17, batch 100, train_loss[loss=2.763, ArTop10Accuracy=0.7751, over 14601.00 frames. ], tot_loss[loss=2.736, ArTop10Accuracy=0.7817, over 4750.76 frames. ], batch size: 63, lr: 7.18e-03
2024-08-06 13:02:19,302 INFO [trainer.py:765] (2/8) Epoch 17, batch 200, train_loss[loss=2.645, ArTop10Accuracy=0.7961, over 13347.00 frames. ], tot_loss[loss=2.732, ArTop10Accuracy=0.7829, over 7753.52 frames. ], batch size: 34, lr: 7.17e-03
2024-08-06 13:03:45,517 INFO [trainer.py:765] (2/8) Epoch 17, batch 300, train_loss[loss=2.766, ArTop10Accuracy=0.7765, over 14475.00 frames. ], tot_loss[loss=2.73, ArTop10Accuracy=0.7835, over 9368.92 frames. ], batch size: 45, lr: 7.15e-03
2024-08-06 13:05:21,761 INFO [trainer.py:765] (2/8) Epoch 17, batch 400, train_loss[loss=2.698, ArTop10Accuracy=0.7876, over 10851.00 frames. ], tot_loss[loss=2.728, ArTop10Accuracy=0.7838, over 10285.68 frames. ], batch size: 15, lr: 7.14e-03
2024-08-06 13:06:47,021 INFO [trainer.py:765] (2/8) Epoch 17, batch 500, train_loss[loss=2.613, ArTop10Accuracy=0.8077, over 12156.00 frames. ], tot_loss[loss=2.72, ArTop10Accuracy=0.7855, over 10849.34 frames. ], batch size: 22, lr: 7.12e-03
2024-08-06 13:07:39,876 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.140e+02 1.293e+02 1.386e+02 1.488e+02 3.253e+02, threshold=2.772e+02, percent-clipped=0.1
2024-08-06 13:08:22,688 INFO [trainer.py:765] (2/8) Epoch 17, batch 600, train_loss[loss=2.731, ArTop10Accuracy=0.783, over 11442.00 frames. ], tot_loss[loss=2.726, ArTop10Accuracy=0.7841, over 11370.60 frames. ], batch size: 18, lr: 7.10e-03
2024-08-06 13:09:54,836 INFO [trainer.py:765] (2/8) Epoch 17, batch 700, train_loss[loss=2.633, ArTop10Accuracy=0.807, over 10050.00 frames. ], tot_loss[loss=2.732, ArTop10Accuracy=0.7831, over 11529.16 frames. ], batch size: 12, lr: 7.09e-03
2024-08-06 13:11:19,480 INFO [trainer.py:765] (2/8) Epoch 17, batch 800, train_loss[loss=2.641, ArTop10Accuracy=0.8067, over 9264.00 frames. ], tot_loss[loss=2.733, ArTop10Accuracy=0.7829, over 11639.94 frames. ], batch size: 11, lr: 7.07e-03
2024-08-06 13:12:35,670 INFO [trainer.py:765] (2/8) Epoch 17, batch 900, train_loss[loss=2.787, ArTop10Accuracy=0.7766, over 13002.00 frames. ], tot_loss[loss=2.73, ArTop10Accuracy=0.7836, over 11693.45 frames. ], batch size: 27, lr: 7.06e-03
2024-08-06 13:13:53,061 INFO [trainer.py:765] (2/8) Epoch 17, batch 1000, train_loss[loss=2.69, ArTop10Accuracy=0.7868, over 12726.00 frames. ], tot_loss[loss=2.739, ArTop10Accuracy=0.7817, over 11891.49 frames. ], batch size: 27, lr: 7.04e-03
2024-08-06 13:15:08,484 INFO [trainer.py:765] (2/8) Epoch 17, batch 1100, train_loss[loss=2.742, ArTop10Accuracy=0.7813, over 13857.00 frames. ], tot_loss[loss=2.744, ArTop10Accuracy=0.7807, over 11966.62 frames. ], batch size: 34, lr: 7.02e-03
2024-08-06 13:16:22,388 INFO [trainer.py:765] (2/8) Epoch 17, batch 1200, train_loss[loss=2.858, ArTop10Accuracy=0.7581, over 12147.00 frames. ], tot_loss[loss=2.747, ArTop10Accuracy=0.7801, over 11878.52 frames. ], batch size: 103, lr: 7.01e-03
2024-08-06 13:17:21,657 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 13:19:15,994 INFO [trainer.py:765] (2/8) Epoch 18, batch 100, train_loss[loss=2.798, ArTop10Accuracy=0.7686, over 14166.00 frames. ], tot_loss[loss=2.727, ArTop10Accuracy=0.7833, over 4761.06 frames. ], batch size: 62, lr: 6.78e-03
2024-08-06 13:20:46,598 INFO [trainer.py:765] (2/8) Epoch 18, batch 200, train_loss[loss=2.716, ArTop10Accuracy=0.7841, over 13710.00 frames. ], tot_loss[loss=2.728, ArTop10Accuracy=0.7835, over 7760.09 frames. ], batch size: 34, lr: 6.77e-03
2024-08-06 13:21:55,105 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 13:22:04,751 INFO [trainer.py:811] (2/8) Epoch 18, validation: loss=2.817, ArTop10Accuracy=0.768, over 1827537.00 frames. 
2024-08-06 13:22:04,752 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 33008MB
2024-08-06 13:22:05,473 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.131e+02 1.323e+02 1.409e+02 1.514e+02 3.209e+02, threshold=2.818e+02, percent-clipped=0.1
2024-08-06 13:22:26,581 INFO [trainer.py:765] (2/8) Epoch 18, batch 300, train_loss[loss=2.701, ArTop10Accuracy=0.7888, over 14001.00 frames. ], tot_loss[loss=2.721, ArTop10Accuracy=0.7847, over 9379.73 frames. ], batch size: 44, lr: 6.76e-03
2024-08-06 13:23:57,930 INFO [trainer.py:765] (2/8) Epoch 18, batch 400, train_loss[loss=2.628, ArTop10Accuracy=0.8027, over 10353.00 frames. ], tot_loss[loss=2.72, ArTop10Accuracy=0.785, over 10253.95 frames. ], batch size: 14, lr: 6.74e-03
2024-08-06 13:25:34,014 INFO [trainer.py:765] (2/8) Epoch 18, batch 500, train_loss[loss=2.724, ArTop10Accuracy=0.7832, over 12105.00 frames. ], tot_loss[loss=2.715, ArTop10Accuracy=0.7862, over 10832.76 frames. ], batch size: 22, lr: 6.73e-03
2024-08-06 13:27:00,634 INFO [trainer.py:765] (2/8) Epoch 18, batch 600, train_loss[loss=2.664, ArTop10Accuracy=0.7917, over 11499.00 frames. ], tot_loss[loss=2.715, ArTop10Accuracy=0.7864, over 11359.21 frames. ], batch size: 18, lr: 6.71e-03
2024-08-06 13:28:33,581 INFO [trainer.py:765] (2/8) Epoch 18, batch 700, train_loss[loss=2.679, ArTop10Accuracy=0.7905, over 10233.00 frames. ], tot_loss[loss=2.723, ArTop10Accuracy=0.7849, over 11509.88 frames. ], batch size: 12, lr: 6.70e-03
2024-08-06 13:29:54,984 INFO [trainer.py:765] (2/8) Epoch 18, batch 800, train_loss[loss=2.624, ArTop10Accuracy=0.8056, over 10095.00 frames. ], tot_loss[loss=2.727, ArTop10Accuracy=0.7841, over 11633.45 frames. ], batch size: 12, lr: 6.68e-03
2024-08-06 13:31:12,519 INFO [trainer.py:765] (2/8) Epoch 18, batch 900, train_loss[loss=2.763, ArTop10Accuracy=0.7727, over 12981.00 frames. ], tot_loss[loss=2.724, ArTop10Accuracy=0.7846, over 11688.74 frames. ], batch size: 27, lr: 6.67e-03
2024-08-06 13:32:26,552 INFO [trainer.py:765] (2/8) Epoch 18, batch 1000, train_loss[loss=2.712, ArTop10Accuracy=0.7877, over 12930.00 frames. ], tot_loss[loss=2.728, ArTop10Accuracy=0.7838, over 11878.51 frames. ], batch size: 27, lr: 6.66e-03
2024-08-06 13:33:41,497 INFO [trainer.py:765] (2/8) Epoch 18, batch 1100, train_loss[loss=2.725, ArTop10Accuracy=0.7836, over 13770.00 frames. ], tot_loss[loss=2.732, ArTop10Accuracy=0.7829, over 11933.41 frames. ], batch size: 34, lr: 6.64e-03
2024-08-06 13:34:54,675 INFO [trainer.py:765] (2/8) Epoch 18, batch 1200, train_loss[loss=2.849, ArTop10Accuracy=0.7605, over 12456.00 frames. ], tot_loss[loss=2.736, ArTop10Accuracy=0.7823, over 11823.99 frames. ], batch size: 101, lr: 6.63e-03
2024-08-06 13:35:51,064 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.124e+02 1.340e+02 1.433e+02 1.533e+02 2.444e+02, threshold=2.867e+02, percent-clipped=0.0
2024-08-06 13:35:54,276 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 13:37:48,623 INFO [trainer.py:765] (2/8) Epoch 19, batch 100, train_loss[loss=2.829, ArTop10Accuracy=0.7638, over 14544.00 frames. ], tot_loss[loss=2.721, ArTop10Accuracy=0.7847, over 4759.09 frames. ], batch size: 63, lr: 6.43e-03
2024-08-06 13:39:23,258 INFO [trainer.py:765] (2/8) Epoch 19, batch 200, train_loss[loss=2.664, ArTop10Accuracy=0.7977, over 13635.00 frames. ], tot_loss[loss=2.712, ArTop10Accuracy=0.7865, over 7744.99 frames. ], batch size: 34, lr: 6.41e-03
2024-08-06 13:40:48,361 INFO [trainer.py:765] (2/8) Epoch 19, batch 300, train_loss[loss=2.759, ArTop10Accuracy=0.7783, over 14727.00 frames. ], tot_loss[loss=2.708, ArTop10Accuracy=0.7873, over 9362.71 frames. ], batch size: 45, lr: 6.40e-03
2024-08-06 13:42:21,067 INFO [trainer.py:765] (2/8) Epoch 19, batch 400, train_loss[loss=2.777, ArTop10Accuracy=0.7715, over 10257.00 frames. ], tot_loss[loss=2.708, ArTop10Accuracy=0.7875, over 10289.48 frames. ], batch size: 14, lr: 6.39e-03
2024-08-06 13:43:44,954 INFO [trainer.py:765] (2/8) Epoch 19, batch 500, train_loss[loss=2.716, ArTop10Accuracy=0.7888, over 12099.00 frames. ], tot_loss[loss=2.706, ArTop10Accuracy=0.7879, over 10829.04 frames. ], batch size: 22, lr: 6.37e-03
2024-08-06 13:45:16,681 INFO [trainer.py:765] (2/8) Epoch 19, batch 600, train_loss[loss=2.644, ArTop10Accuracy=0.7979, over 11373.00 frames. ], tot_loss[loss=2.708, ArTop10Accuracy=0.7875, over 11342.18 frames. ], batch size: 18, lr: 6.36e-03
2024-08-06 13:46:48,321 INFO [trainer.py:765] (2/8) Epoch 19, batch 700, train_loss[loss=2.622, ArTop10Accuracy=0.8048, over 9222.00 frames. ], tot_loss[loss=2.712, ArTop10Accuracy=0.7868, over 11489.32 frames. ], batch size: 11, lr: 6.35e-03
2024-08-06 13:48:11,883 INFO [trainer.py:765] (2/8) Epoch 19, batch 800, train_loss[loss=2.682, ArTop10Accuracy=0.7907, over 9537.00 frames. ], tot_loss[loss=2.714, ArTop10Accuracy=0.7861, over 11598.77 frames. ], batch size: 11, lr: 6.34e-03
2024-08-06 13:49:27,258 INFO [trainer.py:765] (2/8) Epoch 19, batch 900, train_loss[loss=2.691, ArTop10Accuracy=0.7925, over 13038.00 frames. ], tot_loss[loss=2.709, ArTop10Accuracy=0.7874, over 11650.51 frames. ], batch size: 28, lr: 6.32e-03
2024-08-06 13:50:40,652 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 13:50:50,536 INFO [trainer.py:811] (2/8) Epoch 19, validation: loss=2.818, ArTop10Accuracy=0.7679, over 1827537.00 frames. 
2024-08-06 13:50:50,536 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 33008MB
2024-08-06 13:50:51,488 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.161e+02 1.371e+02 1.455e+02 1.550e+02 3.697e+02, threshold=2.909e+02, percent-clipped=0.2
2024-08-06 13:50:52,917 INFO [trainer.py:765] (2/8) Epoch 19, batch 1000, train_loss[loss=2.821, ArTop10Accuracy=0.7719, over 13188.00 frames. ], tot_loss[loss=2.718, ArTop10Accuracy=0.7857, over 11863.63 frames. ], batch size: 28, lr: 6.31e-03
2024-08-06 13:52:08,266 INFO [trainer.py:765] (2/8) Epoch 19, batch 1100, train_loss[loss=2.794, ArTop10Accuracy=0.7726, over 13524.00 frames. ], tot_loss[loss=2.727, ArTop10Accuracy=0.7837, over 11957.72 frames. ], batch size: 34, lr: 6.30e-03
2024-08-06 13:53:22,313 INFO [trainer.py:765] (2/8) Epoch 19, batch 1200, train_loss[loss=2.808, ArTop10Accuracy=0.7734, over 12612.00 frames. ], tot_loss[loss=2.729, ArTop10Accuracy=0.7834, over 11877.42 frames. ], batch size: 101, lr: 6.28e-03
2024-08-06 13:54:22,076 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 13:56:12,905 INFO [trainer.py:765] (2/8) Epoch 20, batch 100, train_loss[loss=2.786, ArTop10Accuracy=0.7693, over 14730.00 frames. ], tot_loss[loss=2.709, ArTop10Accuracy=0.7874, over 4769.30 frames. ], batch size: 63, lr: 6.10e-03
2024-08-06 13:57:42,493 INFO [trainer.py:765] (2/8) Epoch 20, batch 200, train_loss[loss=2.748, ArTop10Accuracy=0.7818, over 13584.00 frames. ], tot_loss[loss=2.7, ArTop10Accuracy=0.789, over 7782.09 frames. ], batch size: 34, lr: 6.09e-03
2024-08-06 13:59:15,430 INFO [trainer.py:765] (2/8) Epoch 20, batch 300, train_loss[loss=2.791, ArTop10Accuracy=0.7734, over 14217.00 frames. ], tot_loss[loss=2.699, ArTop10Accuracy=0.7891, over 9382.25 frames. ], batch size: 44, lr: 6.08e-03
2024-08-06 14:00:44,356 INFO [trainer.py:765] (2/8) Epoch 20, batch 400, train_loss[loss=2.715, ArTop10Accuracy=0.7895, over 10272.00 frames. ], tot_loss[loss=2.698, ArTop10Accuracy=0.7893, over 10264.93 frames. ], batch size: 14, lr: 6.07e-03
2024-08-06 14:02:14,854 INFO [trainer.py:765] (2/8) Epoch 20, batch 500, train_loss[loss=2.714, ArTop10Accuracy=0.7842, over 12114.00 frames. ], tot_loss[loss=2.694, ArTop10Accuracy=0.79, over 10835.01 frames. ], batch size: 22, lr: 6.06e-03
2024-08-06 14:03:40,853 INFO [trainer.py:765] (2/8) Epoch 20, batch 600, train_loss[loss=2.604, ArTop10Accuracy=0.8084, over 11556.00 frames. ], tot_loss[loss=2.7, ArTop10Accuracy=0.789, over 11368.42 frames. ], batch size: 18, lr: 6.04e-03
2024-08-06 14:05:13,864 INFO [trainer.py:765] (2/8) Epoch 20, batch 700, train_loss[loss=2.532, ArTop10Accuracy=0.8161, over 9213.00 frames. ], tot_loss[loss=2.704, ArTop10Accuracy=0.7882, over 11519.69 frames. ], batch size: 11, lr: 6.03e-03
2024-08-06 14:05:30,789 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.180e+02 1.365e+02 1.456e+02 1.550e+02 3.525e+02, threshold=2.913e+02, percent-clipped=0.1
2024-08-06 14:06:34,508 INFO [trainer.py:765] (2/8) Epoch 20, batch 800, train_loss[loss=2.548, ArTop10Accuracy=0.8172, over 10098.00 frames. ], tot_loss[loss=2.707, ArTop10Accuracy=0.7874, over 11627.31 frames. ], batch size: 12, lr: 6.02e-03
2024-08-06 14:07:50,944 INFO [trainer.py:765] (2/8) Epoch 20, batch 900, train_loss[loss=2.708, ArTop10Accuracy=0.7879, over 12912.00 frames. ], tot_loss[loss=2.703, ArTop10Accuracy=0.7883, over 11679.18 frames. ], batch size: 27, lr: 6.01e-03
2024-08-06 14:09:07,173 INFO [trainer.py:765] (2/8) Epoch 20, batch 1000, train_loss[loss=2.672, ArTop10Accuracy=0.7979, over 13386.00 frames. ], tot_loss[loss=2.706, ArTop10Accuracy=0.7883, over 11867.63 frames. ], batch size: 28, lr: 6.00e-03
2024-08-06 14:10:21,210 INFO [trainer.py:765] (2/8) Epoch 20, batch 1100, train_loss[loss=2.742, ArTop10Accuracy=0.7785, over 13809.00 frames. ], tot_loss[loss=2.715, ArTop10Accuracy=0.7864, over 11939.19 frames. ], batch size: 34, lr: 5.99e-03
2024-08-06 14:11:37,813 INFO [trainer.py:765] (2/8) Epoch 20, batch 1200, train_loss[loss=2.899, ArTop10Accuracy=0.7505, over 12645.00 frames. ], tot_loss[loss=2.718, ArTop10Accuracy=0.7857, over 11855.77 frames. ], batch size: 101, lr: 5.98e-03
2024-08-06 14:12:37,479 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 14:12:37,481 INFO [trainer.py:1069] (2/8) Done!