2024-08-06 08:06:14,314 INFO [trainer.py:870] (1/8) Training started
2024-08-06 08:06:14,315 INFO [trainer.py:889] (1/8) Device: cuda:1
2024-08-06 08:06:14,315 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': 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 08:06:14,315 INFO [trainer.py:892] (1/8) About to create model
2024-08-06 08:06:15,030 INFO [trainer.py:899] (1/8) Number of model parameters: 367386628
2024-08-06 08:06:16,712 INFO [trainer.py:914] (1/8) Using DDP
2024-08-06 08:06:19,149 INFO [datamodule.py:427] (1/8) About to get train cuts
2024-08-06 08:06:19,151 INFO [datamodule.py:434] (1/8) About to get dev cuts
2024-08-06 08:06:19,152 INFO [datamodule.py:292] (1/8) Disable SpecAugment
2024-08-06 08:06:19,152 INFO [datamodule.py:294] (1/8) About to create train dataset
2024-08-06 08:06:19,153 INFO [datamodule.py:323] (1/8) Using DynamicBucketingSampler
2024-08-06 08:06:19,769 INFO [datamodule.py:344] (1/8) About to create train dataloader
2024-08-06 08:06:19,769 INFO [datamodule.py:367] (1/8) About to create dev dataset
2024-08-06 08:06:20,100 INFO [datamodule.py:388] (1/8) About to create dev dataloader
2024-08-06 08:08:02,125 INFO [trainer.py:765] (1/8) Epoch 1, batch 100, train_loss[loss=4.313, ArTop10Accuracy=0.499, over 14373.00 frames. ], tot_loss[loss=5.051, ArTop10Accuracy=0.3736, over 4747.16 frames. ], batch size: 63, lr: 2.25e-02
2024-08-06 08:09:28,831 INFO [trainer.py:765] (1/8) Epoch 1, batch 200, train_loss[loss=4.082, ArTop10Accuracy=0.5339, over 13701.00 frames. ], tot_loss[loss=4.494, ArTop10Accuracy=0.4669, over 7740.47 frames. ], batch size: 34, lr: 3.00e-02
2024-08-06 08:10:52,432 INFO [trainer.py:765] (1/8) Epoch 1, batch 300, train_loss[loss=3.827, ArTop10Accuracy=0.5819, over 14076.00 frames. ], tot_loss[loss=4.214, ArTop10Accuracy=0.5136, over 9378.41 frames. ], batch size: 44, lr: 3.00e-02
2024-08-06 08:12:12,703 INFO [trainer.py:765] (1/8) Epoch 1, batch 400, train_loss[loss=3.646, ArTop10Accuracy=0.6151, over 10353.00 frames. ], tot_loss[loss=4.028, ArTop10Accuracy=0.5453, over 10284.75 frames. ], batch size: 14, lr: 3.00e-02
2024-08-06 08:13:40,054 INFO [trainer.py:765] (1/8) Epoch 1, batch 500, train_loss[loss=3.622, ArTop10Accuracy=0.6179, over 12669.00 frames. ], tot_loss[loss=3.883, ArTop10Accuracy=0.5706, over 10856.75 frames. ], batch size: 23, lr: 2.99e-02
2024-08-06 08:15:00,247 INFO [trainer.py:765] (1/8) Epoch 1, batch 600, train_loss[loss=3.602, ArTop10Accuracy=0.6197, over 11541.00 frames. ], tot_loss[loss=3.77, ArTop10Accuracy=0.5906, over 11363.67 frames. ], batch size: 18, lr: 2.99e-02
2024-08-06 08:16:26,429 INFO [trainer.py:765] (1/8) Epoch 1, batch 700, train_loss[loss=3.496, ArTop10Accuracy=0.6398, over 10332.00 frames. ], tot_loss[loss=3.689, ArTop10Accuracy=0.6051, over 11510.86 frames. ], batch size: 12, lr: 2.99e-02
2024-08-06 08:17:43,022 INFO [trainer.py:765] (1/8) Epoch 1, batch 800, train_loss[loss=3.526, ArTop10Accuracy=0.635, over 10014.00 frames. ], tot_loss[loss=3.625, ArTop10Accuracy=0.6167, over 11655.02 frames. ], batch size: 12, lr: 2.98e-02
2024-08-06 08:18:56,155 INFO [trainer.py:765] (1/8) Epoch 1, batch 900, train_loss[loss=3.49, ArTop10Accuracy=0.6426, over 12882.00 frames. ], tot_loss[loss=3.567, ArTop10Accuracy=0.6274, over 11695.58 frames. ], batch size: 27, lr: 2.98e-02
2024-08-06 08:20:12,867 INFO [trainer.py:765] (1/8) Epoch 1, batch 1000, train_loss[loss=3.434, ArTop10Accuracy=0.6517, over 13002.00 frames. ], tot_loss[loss=3.525, ArTop10Accuracy=0.635, over 11887.94 frames. ], batch size: 27, lr: 2.97e-02
2024-08-06 08:20:13,547 INFO [optim.py:386] (1/8) 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 08:21:29,161 INFO [trainer.py:765] (1/8) Epoch 1, batch 1100, train_loss[loss=3.453, ArTop10Accuracy=0.6489, over 14007.00 frames. ], tot_loss[loss=3.488, ArTop10Accuracy=0.6419, over 11969.79 frames. ], batch size: 35, lr: 2.96e-02
2024-08-06 08:22:45,417 INFO [trainer.py:765] (1/8) Epoch 1, batch 1200, train_loss[loss=3.476, ArTop10Accuracy=0.644, over 12039.00 frames. ], tot_loss[loss=3.463, ArTop10Accuracy=0.6461, over 11878.23 frames. ], batch size: 101, lr: 2.96e-02
2024-08-06 08:23:45,310 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 08:25:36,244 INFO [trainer.py:765] (1/8) Epoch 2, batch 100, train_loss[loss=3.4, ArTop10Accuracy=0.6565, over 14508.00 frames. ], tot_loss[loss=3.423, ArTop10Accuracy=0.6528, over 4764.29 frames. ], batch size: 62, lr: 2.90e-02
2024-08-06 08:26:58,962 INFO [trainer.py:765] (1/8) Epoch 2, batch 200, train_loss[loss=3.323, ArTop10Accuracy=0.6679, over 13725.00 frames. ], tot_loss[loss=3.385, ArTop10Accuracy=0.6599, over 7749.22 frames. ], batch size: 34, lr: 2.89e-02
2024-08-06 08:28:25,539 INFO [trainer.py:765] (1/8) Epoch 2, batch 300, train_loss[loss=3.403, ArTop10Accuracy=0.6592, over 14277.00 frames. ], tot_loss[loss=3.366, ArTop10Accuracy=0.6635, over 9375.13 frames. ], batch size: 44, lr: 2.89e-02
2024-08-06 08:29:48,644 INFO [trainer.py:765] (1/8) Epoch 2, batch 400, train_loss[loss=3.391, ArTop10Accuracy=0.6543, over 11046.00 frames. ], tot_loss[loss=3.354, ArTop10Accuracy=0.666, over 10294.61 frames. ], batch size: 15, lr: 2.88e-02
2024-08-06 08:31:22,906 INFO [trainer.py:765] (1/8) Epoch 2, batch 500, train_loss[loss=3.266, ArTop10Accuracy=0.6837, over 12363.00 frames. ], tot_loss[loss=3.337, ArTop10Accuracy=0.6696, over 10867.29 frames. ], batch size: 22, lr: 2.87e-02
2024-08-06 08:32:45,694 INFO [trainer.py:765] (1/8) Epoch 2, batch 600, train_loss[loss=3.294, ArTop10Accuracy=0.6813, over 11376.00 frames. ], tot_loss[loss=3.327, ArTop10Accuracy=0.6714, over 11379.06 frames. ], batch size: 18, lr: 2.86e-02
2024-08-06 08:34:13,587 INFO [trainer.py:765] (1/8) Epoch 2, batch 700, train_loss[loss=3.278, ArTop10Accuracy=0.6789, over 10239.00 frames. ], tot_loss[loss=3.322, ArTop10Accuracy=0.6723, over 11515.89 frames. ], batch size: 12, lr: 2.85e-02
2024-08-06 08:34:31,179 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 08:34:40,887 INFO [trainer.py:811] (1/8) Epoch 2, validation: loss=3.277, ArTop10Accuracy=0.6803, over 1827537.00 frames. 
2024-08-06 08:34:40,888 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 31570MB
2024-08-06 08:34:41,706 INFO [optim.py:386] (1/8) 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 08:35:39,883 INFO [trainer.py:765] (1/8) Epoch 2, batch 800, train_loss[loss=3.314, ArTop10Accuracy=0.6699, over 9348.00 frames. ], tot_loss[loss=3.319, ArTop10Accuracy=0.673, over 11636.96 frames. ], batch size: 11, lr: 2.84e-02
2024-08-06 08:36:56,377 INFO [trainer.py:765] (1/8) Epoch 2, batch 900, train_loss[loss=3.373, ArTop10Accuracy=0.6616, over 12846.00 frames. ], tot_loss[loss=3.305, ArTop10Accuracy=0.6758, over 11683.18 frames. ], batch size: 27, lr: 2.83e-02
2024-08-06 08:38:10,518 INFO [trainer.py:765] (1/8) Epoch 2, batch 1000, train_loss[loss=3.233, ArTop10Accuracy=0.6893, over 12870.00 frames. ], tot_loss[loss=3.296, ArTop10Accuracy=0.6774, over 11873.81 frames. ], batch size: 27, lr: 2.82e-02
2024-08-06 08:39:25,065 INFO [trainer.py:765] (1/8) Epoch 2, batch 1100, train_loss[loss=3.28, ArTop10Accuracy=0.6837, over 13569.00 frames. ], tot_loss[loss=3.291, ArTop10Accuracy=0.6783, over 11963.75 frames. ], batch size: 34, lr: 2.81e-02
2024-08-06 08:40:38,225 INFO [trainer.py:765] (1/8) Epoch 2, batch 1200, train_loss[loss=3.337, ArTop10Accuracy=0.6672, over 12903.00 frames. ], tot_loss[loss=3.281, ArTop10Accuracy=0.6802, over 11861.92 frames. ], batch size: 101, lr: 2.80e-02
2024-08-06 08:41:38,205 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 08:43:36,655 INFO [trainer.py:765] (1/8) Epoch 3, batch 100, train_loss[loss=3.334, ArTop10Accuracy=0.6681, over 14691.00 frames. ], tot_loss[loss=3.254, ArTop10Accuracy=0.6846, over 4778.14 frames. ], batch size: 62, lr: 2.67e-02
2024-08-06 08:45:10,505 INFO [trainer.py:765] (1/8) Epoch 3, batch 200, train_loss[loss=3.187, ArTop10Accuracy=0.6983, over 13692.00 frames. ], tot_loss[loss=3.223, ArTop10Accuracy=0.6906, over 7780.48 frames. ], batch size: 34, lr: 2.66e-02
2024-08-06 08:46:29,264 INFO [trainer.py:765] (1/8) Epoch 3, batch 300, train_loss[loss=3.197, ArTop10Accuracy=0.7005, over 14133.00 frames. ], tot_loss[loss=3.206, ArTop10Accuracy=0.6938, over 9395.78 frames. ], batch size: 44, lr: 2.64e-02
2024-08-06 08:48:04,223 INFO [trainer.py:765] (1/8) Epoch 3, batch 400, train_loss[loss=3.106, ArTop10Accuracy=0.7194, over 10431.00 frames. ], tot_loss[loss=3.191, ArTop10Accuracy=0.6968, over 10278.07 frames. ], batch size: 14, lr: 2.63e-02
2024-08-06 08:48:40,887 INFO [optim.py:386] (1/8) 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 08:49:25,548 INFO [trainer.py:765] (1/8) Epoch 3, batch 500, train_loss[loss=3.143, ArTop10Accuracy=0.7066, over 12162.00 frames. ], tot_loss[loss=3.171, ArTop10Accuracy=0.7005, over 10856.70 frames. ], batch size: 22, lr: 2.62e-02
2024-08-06 08:51:00,483 INFO [trainer.py:765] (1/8) Epoch 3, batch 600, train_loss[loss=3.082, ArTop10Accuracy=0.723, over 11733.00 frames. ], tot_loss[loss=3.156, ArTop10Accuracy=0.7034, over 11384.37 frames. ], batch size: 18, lr: 2.61e-02
2024-08-06 08:52:31,624 INFO [trainer.py:765] (1/8) Epoch 3, batch 700, train_loss[loss=3.085, ArTop10Accuracy=0.721, over 10002.00 frames. ], tot_loss[loss=3.15, ArTop10Accuracy=0.7044, over 11517.63 frames. ], batch size: 12, lr: 2.60e-02
2024-08-06 08:53:57,395 INFO [trainer.py:765] (1/8) Epoch 3, batch 800, train_loss[loss=3.078, ArTop10Accuracy=0.7226, over 10086.00 frames. ], tot_loss[loss=3.142, ArTop10Accuracy=0.7064, over 11639.54 frames. ], batch size: 12, lr: 2.59e-02
2024-08-06 08:55:15,124 INFO [trainer.py:765] (1/8) Epoch 3, batch 900, train_loss[loss=3.066, ArTop10Accuracy=0.7258, over 12849.00 frames. ], tot_loss[loss=3.12, ArTop10Accuracy=0.7104, over 11684.21 frames. ], batch size: 27, lr: 2.57e-02
2024-08-06 08:56:31,564 INFO [trainer.py:765] (1/8) Epoch 3, batch 1000, train_loss[loss=3.051, ArTop10Accuracy=0.7245, over 12855.00 frames. ], tot_loss[loss=3.112, ArTop10Accuracy=0.7118, over 11895.25 frames. ], batch size: 27, lr: 2.56e-02
2024-08-06 08:57:46,510 INFO [trainer.py:765] (1/8) Epoch 3, batch 1100, train_loss[loss=3.066, ArTop10Accuracy=0.7182, over 13584.00 frames. ], tot_loss[loss=3.104, ArTop10Accuracy=0.7134, over 11977.87 frames. ], batch size: 34, lr: 2.55e-02
2024-08-06 08:59:01,403 INFO [trainer.py:765] (1/8) Epoch 3, batch 1200, train_loss[loss=3.159, ArTop10Accuracy=0.702, over 11196.00 frames. ], tot_loss[loss=3.095, ArTop10Accuracy=0.715, over 11868.07 frames. ], batch size: 103, lr: 2.54e-02
2024-08-06 09:00:01,941 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 09:01:50,745 INFO [trainer.py:765] (1/8) Epoch 4, batch 100, train_loss[loss=3.027, ArTop10Accuracy=0.7318, over 14526.00 frames. ], tot_loss[loss=3.07, ArTop10Accuracy=0.7198, over 4767.61 frames. ], batch size: 62, lr: 2.38e-02
2024-08-06 09:02:52,864 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 09:03:02,383 INFO [trainer.py:811] (1/8) Epoch 4, validation: loss=2.997, ArTop10Accuracy=0.7338, over 1827537.00 frames. 
2024-08-06 09:03:02,384 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 31570MB
2024-08-06 09:03:03,368 INFO [optim.py:386] (1/8) 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 09:03:29,277 INFO [trainer.py:765] (1/8) Epoch 4, batch 200, train_loss[loss=2.974, ArTop10Accuracy=0.7396, over 13569.00 frames. ], tot_loss[loss=3.051, ArTop10Accuracy=0.7232, over 7747.56 frames. ], batch size: 34, lr: 2.37e-02
2024-08-06 09:05:01,738 INFO [trainer.py:765] (1/8) Epoch 4, batch 300, train_loss[loss=3.089, ArTop10Accuracy=0.7124, over 14157.00 frames. ], tot_loss[loss=3.041, ArTop10Accuracy=0.7252, over 9375.36 frames. ], batch size: 44, lr: 2.36e-02
2024-08-06 09:06:28,155 INFO [trainer.py:765] (1/8) Epoch 4, batch 400, train_loss[loss=2.98, ArTop10Accuracy=0.7353, over 10224.00 frames. ], tot_loss[loss=3.034, ArTop10Accuracy=0.7266, over 10275.30 frames. ], batch size: 14, lr: 2.34e-02
2024-08-06 09:08:01,929 INFO [trainer.py:765] (1/8) Epoch 4, batch 500, train_loss[loss=2.934, ArTop10Accuracy=0.7454, over 12306.00 frames. ], tot_loss[loss=3.025, ArTop10Accuracy=0.7283, over 10830.06 frames. ], batch size: 22, lr: 2.33e-02
2024-08-06 09:09:28,546 INFO [trainer.py:765] (1/8) Epoch 4, batch 600, train_loss[loss=3.117, ArTop10Accuracy=0.7081, over 11433.00 frames. ], tot_loss[loss=3.018, ArTop10Accuracy=0.7296, over 11350.44 frames. ], batch size: 18, lr: 2.32e-02
2024-08-06 09:10:59,871 INFO [trainer.py:765] (1/8) Epoch 4, batch 700, train_loss[loss=3.038, ArTop10Accuracy=0.7271, over 10323.00 frames. ], tot_loss[loss=3.024, ArTop10Accuracy=0.7283, over 11501.78 frames. ], batch size: 12, lr: 2.31e-02
2024-08-06 09:12:17,518 INFO [trainer.py:765] (1/8) Epoch 4, batch 800, train_loss[loss=3.003, ArTop10Accuracy=0.7298, over 9342.00 frames. ], tot_loss[loss=3.023, ArTop10Accuracy=0.7284, over 11621.48 frames. ], batch size: 11, lr: 2.30e-02
2024-08-06 09:13:33,218 INFO [trainer.py:765] (1/8) Epoch 4, batch 900, train_loss[loss=3.1, ArTop10Accuracy=0.7141, over 12897.00 frames. ], tot_loss[loss=3.016, ArTop10Accuracy=0.7296, over 11659.32 frames. ], batch size: 27, lr: 2.29e-02
2024-08-06 09:14:47,526 INFO [trainer.py:765] (1/8) Epoch 4, batch 1000, train_loss[loss=3.042, ArTop10Accuracy=0.7206, over 12765.00 frames. ], tot_loss[loss=3.013, ArTop10Accuracy=0.7304, over 11873.50 frames. ], batch size: 27, lr: 2.28e-02
2024-08-06 09:16:02,987 INFO [trainer.py:765] (1/8) Epoch 4, batch 1100, train_loss[loss=3.001, ArTop10Accuracy=0.7331, over 13710.00 frames. ], tot_loss[loss=3.014, ArTop10Accuracy=0.7303, over 11946.58 frames. ], batch size: 34, lr: 2.26e-02
2024-08-06 09:16:53,297 INFO [optim.py:386] (1/8) 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 09:17:18,350 INFO [trainer.py:765] (1/8) Epoch 4, batch 1200, train_loss[loss=3.076, ArTop10Accuracy=0.7165, over 12258.00 frames. ], tot_loss[loss=3.011, ArTop10Accuracy=0.7307, over 11834.91 frames. ], batch size: 101, lr: 2.25e-02
2024-08-06 09:18:17,461 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 09:20:17,177 INFO [trainer.py:765] (1/8) Epoch 5, batch 100, train_loss[loss=2.968, ArTop10Accuracy=0.7418, over 14499.00 frames. ], tot_loss[loss=2.991, ArTop10Accuracy=0.7345, over 4753.20 frames. ], batch size: 62, lr: 2.10e-02
2024-08-06 09:21:52,300 INFO [trainer.py:765] (1/8) Epoch 5, batch 200, train_loss[loss=3.047, ArTop10Accuracy=0.7255, over 13533.00 frames. ], tot_loss[loss=2.983, ArTop10Accuracy=0.7362, over 7733.64 frames. ], batch size: 34, lr: 2.09e-02
2024-08-06 09:23:19,245 INFO [trainer.py:765] (1/8) Epoch 5, batch 300, train_loss[loss=3, ArTop10Accuracy=0.7324, over 14067.00 frames. ], tot_loss[loss=2.971, ArTop10Accuracy=0.7382, over 9372.02 frames. ], batch size: 44, lr: 2.08e-02
2024-08-06 09:24:53,543 INFO [trainer.py:765] (1/8) Epoch 5, batch 400, train_loss[loss=2.851, ArTop10Accuracy=0.7643, over 10191.00 frames. ], tot_loss[loss=2.965, ArTop10Accuracy=0.7392, over 10286.55 frames. ], batch size: 14, lr: 2.07e-02
2024-08-06 09:26:19,424 INFO [trainer.py:765] (1/8) Epoch 5, batch 500, train_loss[loss=2.986, ArTop10Accuracy=0.7376, over 12162.00 frames. ], tot_loss[loss=2.963, ArTop10Accuracy=0.7397, over 10872.84 frames. ], batch size: 22, lr: 2.06e-02
2024-08-06 09:27:49,543 INFO [trainer.py:765] (1/8) Epoch 5, batch 600, train_loss[loss=2.903, ArTop10Accuracy=0.7532, over 11931.00 frames. ], tot_loss[loss=2.964, ArTop10Accuracy=0.7397, over 11399.96 frames. ], batch size: 19, lr: 2.05e-02
2024-08-06 09:29:21,676 INFO [trainer.py:765] (1/8) Epoch 5, batch 700, train_loss[loss=2.898, ArTop10Accuracy=0.7536, over 9321.00 frames. ], tot_loss[loss=2.972, ArTop10Accuracy=0.7382, over 11531.87 frames. ], batch size: 11, lr: 2.04e-02
2024-08-06 09:30:44,699 INFO [trainer.py:765] (1/8) Epoch 5, batch 800, train_loss[loss=3.077, ArTop10Accuracy=0.7202, over 9351.00 frames. ], tot_loss[loss=2.974, ArTop10Accuracy=0.738, over 11643.11 frames. ], batch size: 11, lr: 2.03e-02
2024-08-06 09:31:51,245 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 09:32:00,761 INFO [trainer.py:811] (1/8) Epoch 5, validation: loss=2.926, ArTop10Accuracy=0.7466, over 1827537.00 frames. 
2024-08-06 09:32:00,761 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 31570MB
2024-08-06 09:32:01,712 INFO [optim.py:386] (1/8) 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 09:32:10,557 INFO [trainer.py:765] (1/8) Epoch 5, batch 900, train_loss[loss=2.939, ArTop10Accuracy=0.7484, over 12774.00 frames. ], tot_loss[loss=2.962, ArTop10Accuracy=0.7404, over 11677.07 frames. ], batch size: 27, lr: 2.02e-02
2024-08-06 09:33:27,329 INFO [trainer.py:765] (1/8) Epoch 5, batch 1000, train_loss[loss=3, ArTop10Accuracy=0.7307, over 13125.00 frames. ], tot_loss[loss=2.962, ArTop10Accuracy=0.7405, over 11870.34 frames. ], batch size: 28, lr: 2.01e-02
2024-08-06 09:34:42,306 INFO [trainer.py:765] (1/8) Epoch 5, batch 1100, train_loss[loss=2.929, ArTop10Accuracy=0.7503, over 13596.00 frames. ], tot_loss[loss=2.964, ArTop10Accuracy=0.7399, over 11943.56 frames. ], batch size: 34, lr: 2.00e-02
2024-08-06 09:35:56,339 INFO [trainer.py:765] (1/8) Epoch 5, batch 1200, train_loss[loss=3.058, ArTop10Accuracy=0.7186, over 13242.00 frames. ], tot_loss[loss=2.963, ArTop10Accuracy=0.7399, over 11871.80 frames. ], batch size: 101, lr: 1.99e-02
2024-08-06 09:36:55,360 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 09:38:52,668 INFO [trainer.py:765] (1/8) Epoch 6, batch 100, train_loss[loss=2.962, ArTop10Accuracy=0.7441, over 14187.00 frames. ], tot_loss[loss=2.946, ArTop10Accuracy=0.7427, over 4761.42 frames. ], batch size: 62, lr: 1.85e-02
2024-08-06 09:40:19,840 INFO [trainer.py:765] (1/8) Epoch 6, batch 200, train_loss[loss=2.889, ArTop10Accuracy=0.7544, over 13533.00 frames. ], tot_loss[loss=2.934, ArTop10Accuracy=0.7452, over 7753.64 frames. ], batch size: 34, lr: 1.84e-02
2024-08-06 09:41:52,971 INFO [trainer.py:765] (1/8) Epoch 6, batch 300, train_loss[loss=2.977, ArTop10Accuracy=0.7367, over 14202.00 frames. ], tot_loss[loss=2.928, ArTop10Accuracy=0.7462, over 9400.74 frames. ], batch size: 44, lr: 1.83e-02
2024-08-06 09:43:17,833 INFO [trainer.py:765] (1/8) Epoch 6, batch 400, train_loss[loss=2.822, ArTop10Accuracy=0.7726, over 10521.00 frames. ], tot_loss[loss=2.925, ArTop10Accuracy=0.747, over 10303.55 frames. ], batch size: 14, lr: 1.83e-02
2024-08-06 09:44:54,134 INFO [trainer.py:765] (1/8) Epoch 6, batch 500, train_loss[loss=2.937, ArTop10Accuracy=0.7418, over 12210.00 frames. ], tot_loss[loss=2.918, ArTop10Accuracy=0.7481, over 10854.68 frames. ], batch size: 22, lr: 1.82e-02
2024-08-06 09:46:22,879 INFO [trainer.py:765] (1/8) Epoch 6, batch 600, train_loss[loss=2.901, ArTop10Accuracy=0.7563, over 11883.00 frames. ], tot_loss[loss=2.925, ArTop10Accuracy=0.7468, over 11386.09 frames. ], batch size: 19, lr: 1.81e-02
2024-08-06 09:46:37,225 INFO [optim.py:386] (1/8) 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 09:47:57,875 INFO [trainer.py:765] (1/8) Epoch 6, batch 700, train_loss[loss=2.899, ArTop10Accuracy=0.7566, over 10038.00 frames. ], tot_loss[loss=2.929, ArTop10Accuracy=0.7462, over 11537.98 frames. ], batch size: 12, lr: 1.80e-02
2024-08-06 09:49:15,961 INFO [trainer.py:765] (1/8) Epoch 6, batch 800, train_loss[loss=2.845, ArTop10Accuracy=0.7569, over 9402.00 frames. ], tot_loss[loss=2.932, ArTop10Accuracy=0.7455, over 11662.00 frames. ], batch size: 11, lr: 1.79e-02
2024-08-06 09:50:32,141 INFO [trainer.py:765] (1/8) Epoch 6, batch 900, train_loss[loss=2.907, ArTop10Accuracy=0.748, over 12954.00 frames. ], tot_loss[loss=2.927, ArTop10Accuracy=0.7466, over 11709.57 frames. ], batch size: 27, lr: 1.78e-02
2024-08-06 09:51:47,303 INFO [trainer.py:765] (1/8) Epoch 6, batch 1000, train_loss[loss=2.976, ArTop10Accuracy=0.7375, over 12882.00 frames. ], tot_loss[loss=2.929, ArTop10Accuracy=0.7461, over 11880.37 frames. ], batch size: 27, lr: 1.77e-02
2024-08-06 09:53:00,927 INFO [trainer.py:765] (1/8) Epoch 6, batch 1100, train_loss[loss=2.896, ArTop10Accuracy=0.7569, over 13659.00 frames. ], tot_loss[loss=2.929, ArTop10Accuracy=0.7462, over 11936.22 frames. ], batch size: 34, lr: 1.77e-02
2024-08-06 09:54:14,343 INFO [trainer.py:765] (1/8) Epoch 6, batch 1200, train_loss[loss=3.025, ArTop10Accuracy=0.7304, over 12231.00 frames. ], tot_loss[loss=2.928, ArTop10Accuracy=0.7461, over 11865.74 frames. ], batch size: 101, lr: 1.76e-02
2024-08-06 09:55:13,177 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 09:57:06,705 INFO [trainer.py:765] (1/8) Epoch 7, batch 100, train_loss[loss=3.002, ArTop10Accuracy=0.7374, over 14385.00 frames. ], tot_loss[loss=2.913, ArTop10Accuracy=0.7486, over 4745.63 frames. ], batch size: 62, lr: 1.64e-02
2024-08-06 09:58:39,429 INFO [trainer.py:765] (1/8) Epoch 7, batch 200, train_loss[loss=2.902, ArTop10Accuracy=0.7502, over 13656.00 frames. ], tot_loss[loss=2.9, ArTop10Accuracy=0.7515, over 7751.20 frames. ], batch size: 34, lr: 1.64e-02
2024-08-06 10:00:06,090 INFO [trainer.py:765] (1/8) Epoch 7, batch 300, train_loss[loss=2.908, ArTop10Accuracy=0.755, over 14034.00 frames. ], tot_loss[loss=2.896, ArTop10Accuracy=0.7522, over 9344.26 frames. ], batch size: 44, lr: 1.63e-02
2024-08-06 10:00:40,514 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 10:00:50,245 INFO [trainer.py:811] (1/8) Epoch 7, validation: loss=2.88, ArTop10Accuracy=0.7554, over 1827537.00 frames. 
2024-08-06 10:00:50,246 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 31570MB
2024-08-06 10:00:50,983 INFO [optim.py:386] (1/8) 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 10:01:49,123 INFO [trainer.py:765] (1/8) Epoch 7, batch 400, train_loss[loss=2.808, ArTop10Accuracy=0.769, over 10485.00 frames. ], tot_loss[loss=2.893, ArTop10Accuracy=0.7531, over 10278.27 frames. ], batch size: 14, lr: 1.62e-02
2024-08-06 10:03:21,463 INFO [trainer.py:765] (1/8) Epoch 7, batch 500, train_loss[loss=2.828, ArTop10Accuracy=0.7612, over 12168.00 frames. ], tot_loss[loss=2.889, ArTop10Accuracy=0.754, over 10832.15 frames. ], batch size: 22, lr: 1.61e-02
2024-08-06 10:04:51,889 INFO [trainer.py:765] (1/8) Epoch 7, batch 600, train_loss[loss=2.795, ArTop10Accuracy=0.7731, over 11178.00 frames. ], tot_loss[loss=2.888, ArTop10Accuracy=0.7539, over 11361.58 frames. ], batch size: 18, lr: 1.61e-02
2024-08-06 10:06:25,117 INFO [trainer.py:765] (1/8) Epoch 7, batch 700, train_loss[loss=2.795, ArTop10Accuracy=0.766, over 9279.00 frames. ], tot_loss[loss=2.896, ArTop10Accuracy=0.7525, over 11491.31 frames. ], batch size: 11, lr: 1.60e-02
2024-08-06 10:07:46,955 INFO [trainer.py:765] (1/8) Epoch 7, batch 800, train_loss[loss=2.803, ArTop10Accuracy=0.7747, over 10359.00 frames. ], tot_loss[loss=2.896, ArTop10Accuracy=0.7525, over 11632.01 frames. ], batch size: 12, lr: 1.59e-02
2024-08-06 10:09:02,828 INFO [trainer.py:765] (1/8) Epoch 7, batch 900, train_loss[loss=2.792, ArTop10Accuracy=0.7744, over 12621.00 frames. ], tot_loss[loss=2.892, ArTop10Accuracy=0.7532, over 11686.51 frames. ], batch size: 27, lr: 1.59e-02
2024-08-06 10:10:19,642 INFO [trainer.py:765] (1/8) Epoch 7, batch 1000, train_loss[loss=2.938, ArTop10Accuracy=0.7412, over 13341.00 frames. ], tot_loss[loss=2.894, ArTop10Accuracy=0.7527, over 11857.32 frames. ], batch size: 28, lr: 1.58e-02
2024-08-06 10:11:35,214 INFO [trainer.py:765] (1/8) Epoch 7, batch 1100, train_loss[loss=2.966, ArTop10Accuracy=0.7316, over 13683.00 frames. ], tot_loss[loss=2.902, ArTop10Accuracy=0.7512, over 11942.87 frames. ], batch size: 34, lr: 1.57e-02
2024-08-06 10:12:48,210 INFO [trainer.py:765] (1/8) Epoch 7, batch 1200, train_loss[loss=3.03, ArTop10Accuracy=0.7313, over 12375.00 frames. ], tot_loss[loss=2.901, ArTop10Accuracy=0.7515, over 11863.93 frames. ], batch size: 101, lr: 1.57e-02
2024-08-06 10:13:46,697 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 10:15:03,607 INFO [optim.py:386] (1/8) 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 10:15:40,827 INFO [trainer.py:765] (1/8) Epoch 8, batch 100, train_loss[loss=2.922, ArTop10Accuracy=0.7479, over 14244.00 frames. ], tot_loss[loss=2.885, ArTop10Accuracy=0.7541, over 4746.16 frames. ], batch size: 62, lr: 1.47e-02
2024-08-06 10:17:12,868 INFO [trainer.py:765] (1/8) Epoch 8, batch 200, train_loss[loss=2.894, ArTop10Accuracy=0.7525, over 13881.00 frames. ], tot_loss[loss=2.873, ArTop10Accuracy=0.7565, over 7754.49 frames. ], batch size: 34, lr: 1.46e-02
2024-08-06 10:18:37,904 INFO [trainer.py:765] (1/8) Epoch 8, batch 300, train_loss[loss=2.901, ArTop10Accuracy=0.7532, over 14163.00 frames. ], tot_loss[loss=2.87, ArTop10Accuracy=0.7571, over 9382.60 frames. ], batch size: 44, lr: 1.46e-02
2024-08-06 10:20:06,348 INFO [trainer.py:765] (1/8) Epoch 8, batch 400, train_loss[loss=2.749, ArTop10Accuracy=0.7818, over 10323.00 frames. ], tot_loss[loss=2.864, ArTop10Accuracy=0.7585, over 10284.68 frames. ], batch size: 14, lr: 1.45e-02
2024-08-06 10:21:32,417 INFO [trainer.py:765] (1/8) Epoch 8, batch 500, train_loss[loss=2.842, ArTop10Accuracy=0.7659, over 12006.00 frames. ], tot_loss[loss=2.864, ArTop10Accuracy=0.7587, over 10864.33 frames. ], batch size: 22, lr: 1.45e-02
2024-08-06 10:23:00,980 INFO [trainer.py:765] (1/8) Epoch 8, batch 600, train_loss[loss=2.892, ArTop10Accuracy=0.7495, over 11358.00 frames. ], tot_loss[loss=2.867, ArTop10Accuracy=0.7579, over 11374.38 frames. ], batch size: 18, lr: 1.44e-02
2024-08-06 10:24:37,794 INFO [trainer.py:765] (1/8) Epoch 8, batch 700, train_loss[loss=2.749, ArTop10Accuracy=0.7816, over 10002.00 frames. ], tot_loss[loss=2.87, ArTop10Accuracy=0.7573, over 11528.07 frames. ], batch size: 12, lr: 1.43e-02
2024-08-06 10:25:56,091 INFO [trainer.py:765] (1/8) Epoch 8, batch 800, train_loss[loss=2.752, ArTop10Accuracy=0.775, over 9339.00 frames. ], tot_loss[loss=2.875, ArTop10Accuracy=0.7566, over 11620.96 frames. ], batch size: 11, lr: 1.43e-02
2024-08-06 10:27:12,249 INFO [trainer.py:765] (1/8) Epoch 8, batch 900, train_loss[loss=2.869, ArTop10Accuracy=0.7567, over 13035.00 frames. ], tot_loss[loss=2.867, ArTop10Accuracy=0.7579, over 11677.37 frames. ], batch size: 27, lr: 1.42e-02
2024-08-06 10:28:25,269 INFO [trainer.py:765] (1/8) Epoch 8, batch 1000, train_loss[loss=2.85, ArTop10Accuracy=0.7617, over 12864.00 frames. ], tot_loss[loss=2.872, ArTop10Accuracy=0.7572, over 11871.35 frames. ], batch size: 27, lr: 1.42e-02
2024-08-06 10:29:07,161 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 10:29:16,830 INFO [trainer.py:811] (1/8) Epoch 8, validation: loss=2.858, ArTop10Accuracy=0.7594, over 1827537.00 frames. 
2024-08-06 10:29:16,831 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 31570MB
2024-08-06 10:29:17,496 INFO [optim.py:386] (1/8) 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 10:29:51,738 INFO [trainer.py:765] (1/8) Epoch 8, batch 1100, train_loss[loss=2.851, ArTop10Accuracy=0.7608, over 13545.00 frames. ], tot_loss[loss=2.88, ArTop10Accuracy=0.7554, over 11946.85 frames. ], batch size: 34, lr: 1.41e-02
2024-08-06 10:31:05,952 INFO [trainer.py:765] (1/8) Epoch 8, batch 1200, train_loss[loss=3.013, ArTop10Accuracy=0.7242, over 12375.00 frames. ], tot_loss[loss=2.878, ArTop10Accuracy=0.756, over 11877.61 frames. ], batch size: 101, lr: 1.40e-02
2024-08-06 10:32:05,554 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 10:34:01,262 INFO [trainer.py:765] (1/8) Epoch 9, batch 100, train_loss[loss=2.974, ArTop10Accuracy=0.7336, over 14712.00 frames. ], tot_loss[loss=2.854, ArTop10Accuracy=0.7598, over 4756.21 frames. ], batch size: 62, lr: 1.32e-02
2024-08-06 10:35:31,778 INFO [trainer.py:765] (1/8) Epoch 9, batch 200, train_loss[loss=2.743, ArTop10Accuracy=0.782, over 13812.00 frames. ], tot_loss[loss=2.845, ArTop10Accuracy=0.7618, over 7742.43 frames. ], batch size: 34, lr: 1.32e-02
2024-08-06 10:36:57,933 INFO [trainer.py:765] (1/8) Epoch 9, batch 300, train_loss[loss=2.905, ArTop10Accuracy=0.7537, over 14358.00 frames. ], tot_loss[loss=2.842, ArTop10Accuracy=0.7627, over 9372.16 frames. ], batch size: 45, lr: 1.31e-02
2024-08-06 10:38:32,702 INFO [trainer.py:765] (1/8) Epoch 9, batch 400, train_loss[loss=2.77, ArTop10Accuracy=0.7783, over 10809.00 frames. ], tot_loss[loss=2.843, ArTop10Accuracy=0.7625, over 10272.39 frames. ], batch size: 15, lr: 1.31e-02
2024-08-06 10:39:59,262 INFO [trainer.py:765] (1/8) Epoch 9, batch 500, train_loss[loss=2.804, ArTop10Accuracy=0.7676, over 12750.00 frames. ], tot_loss[loss=2.837, ArTop10Accuracy=0.7636, over 10841.66 frames. ], batch size: 23, lr: 1.30e-02
2024-08-06 10:41:29,694 INFO [trainer.py:765] (1/8) Epoch 9, batch 600, train_loss[loss=2.872, ArTop10Accuracy=0.7589, over 11277.00 frames. ], tot_loss[loss=2.837, ArTop10Accuracy=0.7634, over 11363.34 frames. ], batch size: 18, lr: 1.30e-02
2024-08-06 10:42:58,446 INFO [trainer.py:765] (1/8) Epoch 9, batch 700, train_loss[loss=2.794, ArTop10Accuracy=0.7749, over 10224.00 frames. ], tot_loss[loss=2.847, ArTop10Accuracy=0.7615, over 11506.27 frames. ], batch size: 12, lr: 1.29e-02
2024-08-06 10:44:02,958 INFO [optim.py:386] (1/8) 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 10:44:19,675 INFO [trainer.py:765] (1/8) Epoch 9, batch 800, train_loss[loss=2.758, ArTop10Accuracy=0.7845, over 9348.00 frames. ], tot_loss[loss=2.852, ArTop10Accuracy=0.7607, over 11633.24 frames. ], batch size: 11, lr: 1.29e-02
2024-08-06 10:45:35,725 INFO [trainer.py:765] (1/8) Epoch 9, batch 900, train_loss[loss=2.776, ArTop10Accuracy=0.7739, over 12975.00 frames. ], tot_loss[loss=2.847, ArTop10Accuracy=0.7616, over 11688.38 frames. ], batch size: 27, lr: 1.28e-02
2024-08-06 10:46:51,277 INFO [trainer.py:765] (1/8) Epoch 9, batch 1000, train_loss[loss=2.904, ArTop10Accuracy=0.7464, over 12858.00 frames. ], tot_loss[loss=2.852, ArTop10Accuracy=0.7605, over 11884.24 frames. ], batch size: 27, lr: 1.28e-02
2024-08-06 10:48:06,253 INFO [trainer.py:765] (1/8) Epoch 9, batch 1100, train_loss[loss=2.846, ArTop10Accuracy=0.7651, over 13599.00 frames. ], tot_loss[loss=2.856, ArTop10Accuracy=0.7598, over 11944.83 frames. ], batch size: 34, lr: 1.28e-02
2024-08-06 10:49:21,058 INFO [trainer.py:765] (1/8) Epoch 9, batch 1200, train_loss[loss=2.94, ArTop10Accuracy=0.7412, over 12285.00 frames. ], tot_loss[loss=2.852, ArTop10Accuracy=0.7606, over 11849.65 frames. ], batch size: 103, lr: 1.27e-02
2024-08-06 10:50:22,395 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 10:52:12,332 INFO [trainer.py:765] (1/8) Epoch 10, batch 100, train_loss[loss=2.84, ArTop10Accuracy=0.7599, over 14454.00 frames. ], tot_loss[loss=2.84, ArTop10Accuracy=0.7628, over 4762.71 frames. ], batch size: 62, lr: 1.20e-02
2024-08-06 10:53:44,591 INFO [trainer.py:765] (1/8) Epoch 10, batch 200, train_loss[loss=2.841, ArTop10Accuracy=0.7632, over 13776.00 frames. ], tot_loss[loss=2.832, ArTop10Accuracy=0.7643, over 7751.20 frames. ], batch size: 34, lr: 1.20e-02
2024-08-06 10:55:08,096 INFO [trainer.py:765] (1/8) Epoch 10, batch 300, train_loss[loss=2.908, ArTop10Accuracy=0.7502, over 13872.00 frames. ], tot_loss[loss=2.828, ArTop10Accuracy=0.765, over 9380.76 frames. ], batch size: 44, lr: 1.19e-02
2024-08-06 10:56:41,181 INFO [trainer.py:765] (1/8) Epoch 10, batch 400, train_loss[loss=2.775, ArTop10Accuracy=0.7748, over 10197.00 frames. ], tot_loss[loss=2.824, ArTop10Accuracy=0.7658, over 10286.84 frames. ], batch size: 14, lr: 1.19e-02
2024-08-06 10:58:04,944 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 10:58:14,557 INFO [trainer.py:811] (1/8) Epoch 10, validation: loss=2.842, ArTop10Accuracy=0.7624, over 1827537.00 frames. 
2024-08-06 10:58:14,557 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 31570MB
2024-08-06 10:58:15,576 INFO [optim.py:386] (1/8) 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 10:58:15,583 INFO [trainer.py:765] (1/8) Epoch 10, batch 500, train_loss[loss=2.86, ArTop10Accuracy=0.7601, over 12069.00 frames. ], tot_loss[loss=2.822, ArTop10Accuracy=0.7664, over 10851.85 frames. ], batch size: 22, lr: 1.19e-02
2024-08-06 10:59:42,821 INFO [trainer.py:765] (1/8) Epoch 10, batch 600, train_loss[loss=2.747, ArTop10Accuracy=0.7847, over 11316.00 frames. ], tot_loss[loss=2.823, ArTop10Accuracy=0.7663, over 11362.02 frames. ], batch size: 18, lr: 1.18e-02
2024-08-06 11:01:18,113 INFO [trainer.py:765] (1/8) Epoch 10, batch 700, train_loss[loss=2.815, ArTop10Accuracy=0.7639, over 10041.00 frames. ], tot_loss[loss=2.828, ArTop10Accuracy=0.7651, over 11512.01 frames. ], batch size: 12, lr: 1.18e-02
2024-08-06 11:02:36,923 INFO [trainer.py:765] (1/8) Epoch 10, batch 800, train_loss[loss=2.721, ArTop10Accuracy=0.7851, over 9291.00 frames. ], tot_loss[loss=2.83, ArTop10Accuracy=0.7648, over 11633.61 frames. ], batch size: 11, lr: 1.17e-02
2024-08-06 11:03:51,218 INFO [trainer.py:765] (1/8) Epoch 10, batch 900, train_loss[loss=2.86, ArTop10Accuracy=0.7579, over 12807.00 frames. ], tot_loss[loss=2.825, ArTop10Accuracy=0.7657, over 11681.50 frames. ], batch size: 27, lr: 1.17e-02
2024-08-06 11:05:06,358 INFO [trainer.py:765] (1/8) Epoch 10, batch 1000, train_loss[loss=2.904, ArTop10Accuracy=0.7478, over 12924.00 frames. ], tot_loss[loss=2.832, ArTop10Accuracy=0.7645, over 11872.55 frames. ], batch size: 27, lr: 1.17e-02
2024-08-06 11:06:21,725 INFO [trainer.py:765] (1/8) Epoch 10, batch 1100, train_loss[loss=2.817, ArTop10Accuracy=0.7649, over 13518.00 frames. ], tot_loss[loss=2.839, ArTop10Accuracy=0.763, over 11926.81 frames. ], batch size: 34, lr: 1.16e-02
2024-08-06 11:07:34,778 INFO [trainer.py:765] (1/8) Epoch 10, batch 1200, train_loss[loss=2.922, ArTop10Accuracy=0.7471, over 12081.00 frames. ], tot_loss[loss=2.837, ArTop10Accuracy=0.7634, over 11849.57 frames. ], batch size: 101, lr: 1.16e-02
2024-08-06 11:08:33,905 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 11:10:29,960 INFO [trainer.py:765] (1/8) Epoch 11, batch 100, train_loss[loss=2.921, ArTop10Accuracy=0.7486, over 14277.00 frames. ], tot_loss[loss=2.819, ArTop10Accuracy=0.7666, over 4744.36 frames. ], batch size: 62, lr: 1.10e-02
2024-08-06 11:12:04,679 INFO [trainer.py:765] (1/8) Epoch 11, batch 200, train_loss[loss=2.759, ArTop10Accuracy=0.7787, over 13740.00 frames. ], tot_loss[loss=2.815, ArTop10Accuracy=0.7673, over 7726.69 frames. ], batch size: 34, lr: 1.10e-02
2024-08-06 11:12:22,831 INFO [optim.py:386] (1/8) 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 11:13:31,551 INFO [trainer.py:765] (1/8) Epoch 11, batch 300, train_loss[loss=2.949, ArTop10Accuracy=0.739, over 14226.00 frames. ], tot_loss[loss=2.811, ArTop10Accuracy=0.7683, over 9344.10 frames. ], batch size: 44, lr: 1.09e-02
2024-08-06 11:15:03,275 INFO [trainer.py:765] (1/8) Epoch 11, batch 400, train_loss[loss=2.758, ArTop10Accuracy=0.7821, over 11040.00 frames. ], tot_loss[loss=2.808, ArTop10Accuracy=0.7688, over 10269.43 frames. ], batch size: 15, lr: 1.09e-02
2024-08-06 11:16:29,642 INFO [trainer.py:765] (1/8) Epoch 11, batch 500, train_loss[loss=2.739, ArTop10Accuracy=0.7819, over 12315.00 frames. ], tot_loss[loss=2.8, ArTop10Accuracy=0.7704, over 10842.51 frames. ], batch size: 22, lr: 1.09e-02
2024-08-06 11:18:00,523 INFO [trainer.py:765] (1/8) Epoch 11, batch 600, train_loss[loss=2.793, ArTop10Accuracy=0.7793, over 11529.00 frames. ], tot_loss[loss=2.807, ArTop10Accuracy=0.7689, over 11373.43 frames. ], batch size: 18, lr: 1.08e-02
2024-08-06 11:19:34,516 INFO [trainer.py:765] (1/8) Epoch 11, batch 700, train_loss[loss=2.696, ArTop10Accuracy=0.7903, over 9396.00 frames. ], tot_loss[loss=2.813, ArTop10Accuracy=0.768, over 11509.70 frames. ], batch size: 11, lr: 1.08e-02
2024-08-06 11:20:55,487 INFO [trainer.py:765] (1/8) Epoch 11, batch 800, train_loss[loss=2.761, ArTop10Accuracy=0.7746, over 10377.00 frames. ], tot_loss[loss=2.815, ArTop10Accuracy=0.7673, over 11641.00 frames. ], batch size: 12, lr: 1.07e-02
2024-08-06 11:22:13,712 INFO [trainer.py:765] (1/8) Epoch 11, batch 900, train_loss[loss=2.919, ArTop10Accuracy=0.7417, over 13068.00 frames. ], tot_loss[loss=2.811, ArTop10Accuracy=0.7683, over 11682.77 frames. ], batch size: 27, lr: 1.07e-02
2024-08-06 11:23:31,805 INFO [trainer.py:765] (1/8) Epoch 11, batch 1000, train_loss[loss=2.768, ArTop10Accuracy=0.7785, over 12609.00 frames. ], tot_loss[loss=2.813, ArTop10Accuracy=0.768, over 11877.30 frames. ], batch size: 27, lr: 1.07e-02
2024-08-06 11:24:46,908 INFO [trainer.py:765] (1/8) Epoch 11, batch 1100, train_loss[loss=2.88, ArTop10Accuracy=0.7552, over 13635.00 frames. ], tot_loss[loss=2.818, ArTop10Accuracy=0.767, over 11958.09 frames. ], batch size: 34, lr: 1.06e-02
2024-08-06 11:26:00,739 INFO [trainer.py:765] (1/8) Epoch 11, batch 1200, train_loss[loss=2.993, ArTop10Accuracy=0.7277, over 12222.00 frames. ], tot_loss[loss=2.82, ArTop10Accuracy=0.7665, over 11887.81 frames. ], batch size: 101, lr: 1.06e-02
2024-08-06 11:26:15,853 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 11:26:25,556 INFO [trainer.py:811] (1/8) Epoch 11, validation: loss=2.831, ArTop10Accuracy=0.7643, over 1827537.00 frames. 
2024-08-06 11:26:25,557 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 31570MB
2024-08-06 11:26:26,191 INFO [optim.py:386] (1/8) 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 11:27:09,715 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 11:29:03,456 INFO [trainer.py:765] (1/8) Epoch 12, batch 100, train_loss[loss=2.881, ArTop10Accuracy=0.7566, over 14679.00 frames. ], tot_loss[loss=2.805, ArTop10Accuracy=0.769, over 4772.54 frames. ], batch size: 62, lr: 1.01e-02
2024-08-06 11:30:30,679 INFO [trainer.py:765] (1/8) Epoch 12, batch 200, train_loss[loss=2.779, ArTop10Accuracy=0.7758, over 13632.00 frames. ], tot_loss[loss=2.798, ArTop10Accuracy=0.7707, over 7752.01 frames. ], batch size: 34, lr: 1.01e-02
2024-08-06 11:31:57,661 INFO [trainer.py:765] (1/8) Epoch 12, batch 300, train_loss[loss=2.833, ArTop10Accuracy=0.7634, over 14193.00 frames. ], tot_loss[loss=2.785, ArTop10Accuracy=0.7732, over 9379.82 frames. ], batch size: 45, lr: 1.01e-02
2024-08-06 11:33:30,744 INFO [trainer.py:765] (1/8) Epoch 12, batch 400, train_loss[loss=2.727, ArTop10Accuracy=0.7805, over 10134.00 frames. ], tot_loss[loss=2.785, ArTop10Accuracy=0.7731, over 10292.35 frames. ], batch size: 14, lr: 1.00e-02
2024-08-06 11:34:55,737 INFO [trainer.py:765] (1/8) Epoch 12, batch 500, train_loss[loss=2.804, ArTop10Accuracy=0.7718, over 11982.00 frames. ], tot_loss[loss=2.781, ArTop10Accuracy=0.7739, over 10839.09 frames. ], batch size: 22, lr: 1.00e-02
2024-08-06 11:36:29,367 INFO [trainer.py:765] (1/8) Epoch 12, batch 600, train_loss[loss=2.87, ArTop10Accuracy=0.7539, over 11367.00 frames. ], tot_loss[loss=2.788, ArTop10Accuracy=0.7727, over 11335.89 frames. ], batch size: 18, lr: 9.97e-03
2024-08-06 11:38:00,349 INFO [trainer.py:765] (1/8) Epoch 12, batch 700, train_loss[loss=2.716, ArTop10Accuracy=0.7844, over 10320.00 frames. ], tot_loss[loss=2.794, ArTop10Accuracy=0.7717, over 11503.62 frames. ], batch size: 12, lr: 9.93e-03
2024-08-06 11:39:23,617 INFO [trainer.py:765] (1/8) Epoch 12, batch 800, train_loss[loss=2.846, ArTop10Accuracy=0.7584, over 10128.00 frames. ], tot_loss[loss=2.798, ArTop10Accuracy=0.7709, over 11629.35 frames. ], batch size: 12, lr: 9.90e-03
2024-08-06 11:40:39,895 INFO [trainer.py:765] (1/8) Epoch 12, batch 900, train_loss[loss=2.831, ArTop10Accuracy=0.7651, over 12711.00 frames. ], tot_loss[loss=2.793, ArTop10Accuracy=0.772, over 11677.66 frames. ], batch size: 27, lr: 9.87e-03
2024-08-06 11:41:13,999 INFO [optim.py:386] (1/8) 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 11:41:56,195 INFO [trainer.py:765] (1/8) Epoch 12, batch 1000, train_loss[loss=2.809, ArTop10Accuracy=0.7676, over 12882.00 frames. ], tot_loss[loss=2.797, ArTop10Accuracy=0.7709, over 11898.86 frames. ], batch size: 27, lr: 9.85e-03
2024-08-06 11:43:14,326 INFO [trainer.py:765] (1/8) Epoch 12, batch 1100, train_loss[loss=2.782, ArTop10Accuracy=0.7774, over 13779.00 frames. ], tot_loss[loss=2.805, ArTop10Accuracy=0.7695, over 11949.96 frames. ], batch size: 34, lr: 9.82e-03
2024-08-06 11:44:26,162 INFO [trainer.py:765] (1/8) Epoch 12, batch 1200, train_loss[loss=2.944, ArTop10Accuracy=0.7393, over 12054.00 frames. ], tot_loss[loss=2.803, ArTop10Accuracy=0.7701, over 11864.81 frames. ], batch size: 101, lr: 9.79e-03
2024-08-06 11:45:26,869 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 11:47:26,604 INFO [trainer.py:765] (1/8) Epoch 13, batch 100, train_loss[loss=2.844, ArTop10Accuracy=0.7621, over 14415.00 frames. ], tot_loss[loss=2.788, ArTop10Accuracy=0.7719, over 4772.92 frames. ], batch size: 62, lr: 9.37e-03
2024-08-06 11:48:54,785 INFO [trainer.py:765] (1/8) Epoch 13, batch 200, train_loss[loss=2.752, ArTop10Accuracy=0.7792, over 13590.00 frames. ], tot_loss[loss=2.782, ArTop10Accuracy=0.7732, over 7754.83 frames. ], batch size: 34, lr: 9.34e-03
2024-08-06 11:50:20,521 INFO [trainer.py:765] (1/8) Epoch 13, batch 300, train_loss[loss=2.766, ArTop10Accuracy=0.7763, over 14256.00 frames. ], tot_loss[loss=2.776, ArTop10Accuracy=0.7748, over 9373.21 frames. ], batch size: 44, lr: 9.31e-03
2024-08-06 11:51:48,771 INFO [trainer.py:765] (1/8) Epoch 13, batch 400, train_loss[loss=2.624, ArTop10Accuracy=0.8076, over 10278.00 frames. ], tot_loss[loss=2.773, ArTop10Accuracy=0.7757, over 10275.22 frames. ], batch size: 14, lr: 9.28e-03
2024-08-06 11:53:13,412 INFO [trainer.py:765] (1/8) Epoch 13, batch 500, train_loss[loss=2.676, ArTop10Accuracy=0.798, over 12201.00 frames. ], tot_loss[loss=2.769, ArTop10Accuracy=0.7763, over 10857.58 frames. ], batch size: 22, lr: 9.26e-03
2024-08-06 11:54:52,229 INFO [trainer.py:765] (1/8) Epoch 13, batch 600, train_loss[loss=2.698, ArTop10Accuracy=0.7882, over 11418.00 frames. ], tot_loss[loss=2.776, ArTop10Accuracy=0.7749, over 11355.82 frames. ], batch size: 18, lr: 9.23e-03
2024-08-06 11:55:47,086 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 11:55:56,834 INFO [trainer.py:811] (1/8) Epoch 13, validation: loss=2.824, ArTop10Accuracy=0.7662, over 1827537.00 frames. 
2024-08-06 11:55:56,835 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 33972MB
2024-08-06 11:55:57,718 INFO [optim.py:386] (1/8) 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 11:56:28,471 INFO [trainer.py:765] (1/8) Epoch 13, batch 700, train_loss[loss=2.772, ArTop10Accuracy=0.7774, over 9309.00 frames. ], tot_loss[loss=2.783, ArTop10Accuracy=0.7735, over 11488.70 frames. ], batch size: 11, lr: 9.20e-03
2024-08-06 11:57:46,690 INFO [trainer.py:765] (1/8) Epoch 13, batch 800, train_loss[loss=2.713, ArTop10Accuracy=0.7875, over 10161.00 frames. ], tot_loss[loss=2.786, ArTop10Accuracy=0.773, over 11619.65 frames. ], batch size: 12, lr: 9.18e-03
2024-08-06 11:59:03,290 INFO [trainer.py:765] (1/8) Epoch 13, batch 900, train_loss[loss=2.756, ArTop10Accuracy=0.7807, over 13041.00 frames. ], tot_loss[loss=2.782, ArTop10Accuracy=0.7737, over 11686.03 frames. ], batch size: 27, lr: 9.15e-03
2024-08-06 12:00:19,180 INFO [trainer.py:765] (1/8) Epoch 13, batch 1000, train_loss[loss=2.81, ArTop10Accuracy=0.7706, over 12786.00 frames. ], tot_loss[loss=2.786, ArTop10Accuracy=0.773, over 11890.74 frames. ], batch size: 27, lr: 9.13e-03
2024-08-06 12:01:34,885 INFO [trainer.py:765] (1/8) Epoch 13, batch 1100, train_loss[loss=2.775, ArTop10Accuracy=0.7717, over 13575.00 frames. ], tot_loss[loss=2.797, ArTop10Accuracy=0.7709, over 11954.47 frames. ], batch size: 34, lr: 9.10e-03
2024-08-06 12:02:48,669 INFO [trainer.py:765] (1/8) Epoch 13, batch 1200, train_loss[loss=2.981, ArTop10Accuracy=0.7357, over 12087.00 frames. ], tot_loss[loss=2.795, ArTop10Accuracy=0.7714, over 11877.57 frames. ], batch size: 101, lr: 9.08e-03
2024-08-06 12:03:48,616 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 12:05:45,337 INFO [trainer.py:765] (1/8) Epoch 14, batch 100, train_loss[loss=2.83, ArTop10Accuracy=0.766, over 14226.00 frames. ], tot_loss[loss=2.772, ArTop10Accuracy=0.7751, over 4764.55 frames. ], batch size: 62, lr: 8.71e-03
2024-08-06 12:07:16,607 INFO [trainer.py:765] (1/8) Epoch 14, batch 200, train_loss[loss=2.838, ArTop10Accuracy=0.7595, over 13674.00 frames. ], tot_loss[loss=2.762, ArTop10Accuracy=0.7773, over 7749.81 frames. ], batch size: 34, lr: 8.69e-03
2024-08-06 12:08:44,317 INFO [trainer.py:765] (1/8) Epoch 14, batch 300, train_loss[loss=2.832, ArTop10Accuracy=0.7616, over 14316.00 frames. ], tot_loss[loss=2.762, ArTop10Accuracy=0.777, over 9372.28 frames. ], batch size: 44, lr: 8.66e-03
2024-08-06 12:10:01,135 INFO [optim.py:386] (1/8) 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 12:10:10,232 INFO [trainer.py:765] (1/8) Epoch 14, batch 400, train_loss[loss=2.79, ArTop10Accuracy=0.7714, over 10845.00 frames. ], tot_loss[loss=2.761, ArTop10Accuracy=0.7776, over 10295.62 frames. ], batch size: 15, lr: 8.64e-03
2024-08-06 12:11:36,157 INFO [trainer.py:765] (1/8) Epoch 14, batch 500, train_loss[loss=2.754, ArTop10Accuracy=0.7758, over 11991.00 frames. ], tot_loss[loss=2.759, ArTop10Accuracy=0.778, over 10856.86 frames. ], batch size: 22, lr: 8.62e-03
2024-08-06 12:13:06,000 INFO [trainer.py:765] (1/8) Epoch 14, batch 600, train_loss[loss=2.779, ArTop10Accuracy=0.7749, over 11514.00 frames. ], tot_loss[loss=2.762, ArTop10Accuracy=0.7771, over 11376.97 frames. ], batch size: 18, lr: 8.59e-03
2024-08-06 12:14:38,559 INFO [trainer.py:765] (1/8) Epoch 14, batch 700, train_loss[loss=2.725, ArTop10Accuracy=0.7884, over 9402.00 frames. ], tot_loss[loss=2.768, ArTop10Accuracy=0.776, over 11521.69 frames. ], batch size: 11, lr: 8.57e-03
2024-08-06 12:15:58,076 INFO [trainer.py:765] (1/8) Epoch 14, batch 800, train_loss[loss=2.679, ArTop10Accuracy=0.795, over 9294.00 frames. ], tot_loss[loss=2.771, ArTop10Accuracy=0.7755, over 11635.91 frames. ], batch size: 11, lr: 8.55e-03
2024-08-06 12:17:12,872 INFO [trainer.py:765] (1/8) Epoch 14, batch 900, train_loss[loss=2.759, ArTop10Accuracy=0.7819, over 13014.00 frames. ], tot_loss[loss=2.768, ArTop10Accuracy=0.7764, over 11670.90 frames. ], batch size: 27, lr: 8.52e-03
2024-08-06 12:18:29,618 INFO [trainer.py:765] (1/8) Epoch 14, batch 1000, train_loss[loss=2.777, ArTop10Accuracy=0.7752, over 13023.00 frames. ], tot_loss[loss=2.771, ArTop10Accuracy=0.7758, over 11869.41 frames. ], batch size: 27, lr: 8.50e-03
2024-08-06 12:19:45,382 INFO [trainer.py:765] (1/8) Epoch 14, batch 1100, train_loss[loss=2.772, ArTop10Accuracy=0.7752, over 13365.00 frames. ], tot_loss[loss=2.781, ArTop10Accuracy=0.7738, over 11956.46 frames. ], batch size: 34, lr: 8.48e-03
2024-08-06 12:20:59,284 INFO [trainer.py:765] (1/8) Epoch 14, batch 1200, train_loss[loss=2.913, ArTop10Accuracy=0.749, over 11832.00 frames. ], tot_loss[loss=2.779, ArTop10Accuracy=0.7742, over 11850.00 frames. ], batch size: 101, lr: 8.46e-03
2024-08-06 12:21:57,643 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 12:23:51,968 INFO [trainer.py:765] (1/8) Epoch 15, batch 100, train_loss[loss=2.838, ArTop10Accuracy=0.7632, over 14451.00 frames. ], tot_loss[loss=2.759, ArTop10Accuracy=0.7777, over 4747.89 frames. ], batch size: 62, lr: 8.14e-03
2024-08-06 12:24:00,605 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 12:24:10,290 INFO [trainer.py:811] (1/8) Epoch 15, validation: loss=2.819, ArTop10Accuracy=0.7675, over 1827537.00 frames. 
2024-08-06 12:24:10,290 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 33972MB
2024-08-06 12:24:11,100 INFO [optim.py:386] (1/8) 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 12:25:29,992 INFO [trainer.py:765] (1/8) Epoch 15, batch 200, train_loss[loss=2.771, ArTop10Accuracy=0.7773, over 13839.00 frames. ], tot_loss[loss=2.76, ArTop10Accuracy=0.7774, over 7753.74 frames. ], batch size: 35, lr: 8.12e-03
2024-08-06 12:26:58,701 INFO [trainer.py:765] (1/8) Epoch 15, batch 300, train_loss[loss=2.794, ArTop10Accuracy=0.7749, over 13956.00 frames. ], tot_loss[loss=2.756, ArTop10Accuracy=0.7783, over 9373.07 frames. ], batch size: 44, lr: 8.09e-03
2024-08-06 12:28:28,538 INFO [trainer.py:765] (1/8) Epoch 15, batch 400, train_loss[loss=2.758, ArTop10Accuracy=0.777, over 10365.00 frames. ], tot_loss[loss=2.752, ArTop10Accuracy=0.7793, over 10266.45 frames. ], batch size: 14, lr: 8.07e-03
2024-08-06 12:29:54,036 INFO [trainer.py:765] (1/8) Epoch 15, batch 500, train_loss[loss=2.73, ArTop10Accuracy=0.7861, over 12609.00 frames. ], tot_loss[loss=2.748, ArTop10Accuracy=0.7801, over 10847.41 frames. ], batch size: 23, lr: 8.05e-03
2024-08-06 12:31:23,297 INFO [trainer.py:765] (1/8) Epoch 15, batch 600, train_loss[loss=2.736, ArTop10Accuracy=0.7852, over 11271.00 frames. ], tot_loss[loss=2.746, ArTop10Accuracy=0.7805, over 11369.05 frames. ], batch size: 18, lr: 8.03e-03
2024-08-06 12:32:53,180 INFO [trainer.py:765] (1/8) Epoch 15, batch 700, train_loss[loss=2.627, ArTop10Accuracy=0.8074, over 10299.00 frames. ], tot_loss[loss=2.752, ArTop10Accuracy=0.7793, over 11529.74 frames. ], batch size: 12, lr: 8.01e-03
2024-08-06 12:34:18,260 INFO [trainer.py:765] (1/8) Epoch 15, batch 800, train_loss[loss=2.647, ArTop10Accuracy=0.8006, over 9471.00 frames. ], tot_loss[loss=2.759, ArTop10Accuracy=0.7781, over 11626.40 frames. ], batch size: 11, lr: 7.99e-03
2024-08-06 12:35:34,733 INFO [trainer.py:765] (1/8) Epoch 15, batch 900, train_loss[loss=2.757, ArTop10Accuracy=0.7784, over 12828.00 frames. ], tot_loss[loss=2.753, ArTop10Accuracy=0.7794, over 11678.28 frames. ], batch size: 27, lr: 7.97e-03
2024-08-06 12:36:50,547 INFO [trainer.py:765] (1/8) Epoch 15, batch 1000, train_loss[loss=2.76, ArTop10Accuracy=0.7799, over 12825.00 frames. ], tot_loss[loss=2.76, ArTop10Accuracy=0.7781, over 11871.63 frames. ], batch size: 27, lr: 7.95e-03
2024-08-06 12:38:05,183 INFO [trainer.py:765] (1/8) Epoch 15, batch 1100, train_loss[loss=2.717, ArTop10Accuracy=0.785, over 13494.00 frames. ], tot_loss[loss=2.769, ArTop10Accuracy=0.7765, over 11950.15 frames. ], batch size: 34, lr: 7.93e-03
2024-08-06 12:38:12,847 INFO [optim.py:386] (1/8) 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 12:39:18,795 INFO [trainer.py:765] (1/8) Epoch 15, batch 1200, train_loss[loss=2.892, ArTop10Accuracy=0.7571, over 12477.00 frames. ], tot_loss[loss=2.769, ArTop10Accuracy=0.7762, over 11866.65 frames. ], batch size: 101, lr: 7.91e-03
2024-08-06 12:40:18,961 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 12:42:17,623 INFO [trainer.py:765] (1/8) Epoch 16, batch 100, train_loss[loss=2.815, ArTop10Accuracy=0.765, over 14853.00 frames. ], tot_loss[loss=2.743, ArTop10Accuracy=0.781, over 4763.41 frames. ], batch size: 62, lr: 7.63e-03
2024-08-06 12:43:49,569 INFO [trainer.py:765] (1/8) Epoch 16, batch 200, train_loss[loss=2.731, ArTop10Accuracy=0.7824, over 13905.00 frames. ], tot_loss[loss=2.739, ArTop10Accuracy=0.7817, over 7738.07 frames. ], batch size: 35, lr: 7.61e-03
2024-08-06 12:45:18,507 INFO [trainer.py:765] (1/8) Epoch 16, batch 300, train_loss[loss=2.766, ArTop10Accuracy=0.7766, over 14256.00 frames. ], tot_loss[loss=2.735, ArTop10Accuracy=0.7825, over 9366.92 frames. ], batch size: 44, lr: 7.59e-03
2024-08-06 12:46:45,212 INFO [trainer.py:765] (1/8) Epoch 16, batch 400, train_loss[loss=2.789, ArTop10Accuracy=0.7706, over 10821.00 frames. ], tot_loss[loss=2.733, ArTop10Accuracy=0.7829, over 10278.07 frames. ], batch size: 15, lr: 7.58e-03
2024-08-06 12:48:16,316 INFO [trainer.py:765] (1/8) Epoch 16, batch 500, train_loss[loss=2.804, ArTop10Accuracy=0.771, over 12237.00 frames. ], tot_loss[loss=2.731, ArTop10Accuracy=0.7833, over 10829.44 frames. ], batch size: 22, lr: 7.56e-03
2024-08-06 12:49:46,648 INFO [trainer.py:765] (1/8) Epoch 16, batch 600, train_loss[loss=2.69, ArTop10Accuracy=0.794, over 11436.00 frames. ], tot_loss[loss=2.736, ArTop10Accuracy=0.7824, over 11359.23 frames. ], batch size: 18, lr: 7.54e-03
2024-08-06 12:51:23,687 INFO [trainer.py:765] (1/8) Epoch 16, batch 700, train_loss[loss=2.575, ArTop10Accuracy=0.8169, over 10113.00 frames. ], tot_loss[loss=2.737, ArTop10Accuracy=0.7824, over 11499.13 frames. ], batch size: 12, lr: 7.52e-03
2024-08-06 12:52:43,507 INFO [trainer.py:765] (1/8) Epoch 16, batch 800, train_loss[loss=2.739, ArTop10Accuracy=0.7811, over 9315.00 frames. ], tot_loss[loss=2.743, ArTop10Accuracy=0.7812, over 11618.42 frames. ], batch size: 11, lr: 7.51e-03
2024-08-06 12:53:06,020 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 12:53:15,496 INFO [trainer.py:811] (1/8) Epoch 16, validation: loss=2.816, ArTop10Accuracy=0.7678, over 1827537.00 frames. 
2024-08-06 12:53:15,496 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 33972MB
2024-08-06 12:53:16,191 INFO [optim.py:386] (1/8) 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 12:54:06,487 INFO [trainer.py:765] (1/8) Epoch 16, batch 900, train_loss[loss=2.656, ArTop10Accuracy=0.7962, over 12948.00 frames. ], tot_loss[loss=2.738, ArTop10Accuracy=0.7822, over 11658.62 frames. ], batch size: 27, lr: 7.49e-03
2024-08-06 12:55:19,797 INFO [trainer.py:765] (1/8) Epoch 16, batch 1000, train_loss[loss=2.713, ArTop10Accuracy=0.7918, over 12969.00 frames. ], tot_loss[loss=2.746, ArTop10Accuracy=0.7808, over 11870.63 frames. ], batch size: 27, lr: 7.47e-03
2024-08-06 12:56:33,168 INFO [trainer.py:765] (1/8) Epoch 16, batch 1100, train_loss[loss=2.718, ArTop10Accuracy=0.7869, over 13368.00 frames. ], tot_loss[loss=2.757, ArTop10Accuracy=0.7786, over 11929.12 frames. ], batch size: 34, lr: 7.45e-03
2024-08-06 12:57:48,491 INFO [trainer.py:765] (1/8) Epoch 16, batch 1200, train_loss[loss=2.885, ArTop10Accuracy=0.7546, over 12060.00 frames. ], tot_loss[loss=2.755, ArTop10Accuracy=0.7789, over 11851.65 frames. ], batch size: 101, lr: 7.44e-03
2024-08-06 12:58:48,499 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 13:00:47,904 INFO [trainer.py:765] (1/8) Epoch 17, batch 100, train_loss[loss=2.817, ArTop10Accuracy=0.7671, over 14796.00 frames. ], tot_loss[loss=2.734, ArTop10Accuracy=0.7833, over 4759.58 frames. ], batch size: 62, lr: 7.18e-03
2024-08-06 13:02:19,308 INFO [trainer.py:765] (1/8) Epoch 17, batch 200, train_loss[loss=2.825, ArTop10Accuracy=0.7651, over 13587.00 frames. ], tot_loss[loss=2.733, ArTop10Accuracy=0.7833, over 7743.12 frames. ], batch size: 34, lr: 7.17e-03
2024-08-06 13:03:45,523 INFO [trainer.py:765] (1/8) Epoch 17, batch 300, train_loss[loss=2.757, ArTop10Accuracy=0.7768, over 14088.00 frames. ], tot_loss[loss=2.726, ArTop10Accuracy=0.7844, over 9362.71 frames. ], batch size: 44, lr: 7.15e-03
2024-08-06 13:05:21,767 INFO [trainer.py:765] (1/8) Epoch 17, batch 400, train_loss[loss=2.723, ArTop10Accuracy=0.7856, over 10410.00 frames. ], tot_loss[loss=2.725, ArTop10Accuracy=0.7844, over 10281.41 frames. ], batch size: 14, lr: 7.14e-03
2024-08-06 13:06:47,027 INFO [trainer.py:765] (1/8) Epoch 17, batch 500, train_loss[loss=2.711, ArTop10Accuracy=0.7892, over 12222.00 frames. ], tot_loss[loss=2.724, ArTop10Accuracy=0.7845, over 10840.39 frames. ], batch size: 22, lr: 7.12e-03
2024-08-06 13:07:39,882 INFO [optim.py:386] (1/8) 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 13:08:22,694 INFO [trainer.py:765] (1/8) Epoch 17, batch 600, train_loss[loss=2.759, ArTop10Accuracy=0.779, over 11331.00 frames. ], tot_loss[loss=2.728, ArTop10Accuracy=0.7837, over 11352.01 frames. ], batch size: 18, lr: 7.10e-03
2024-08-06 13:09:54,842 INFO [trainer.py:765] (1/8) Epoch 17, batch 700, train_loss[loss=2.614, ArTop10Accuracy=0.8014, over 10098.00 frames. ], tot_loss[loss=2.734, ArTop10Accuracy=0.7825, over 11507.09 frames. ], batch size: 12, lr: 7.09e-03
2024-08-06 13:11:19,487 INFO [trainer.py:765] (1/8) Epoch 17, batch 800, train_loss[loss=2.756, ArTop10Accuracy=0.7715, over 10443.00 frames. ], tot_loss[loss=2.739, ArTop10Accuracy=0.7816, over 11651.32 frames. ], batch size: 12, lr: 7.07e-03
2024-08-06 13:12:35,676 INFO [trainer.py:765] (1/8) Epoch 17, batch 900, train_loss[loss=2.768, ArTop10Accuracy=0.7783, over 12885.00 frames. ], tot_loss[loss=2.733, ArTop10Accuracy=0.7827, over 11681.22 frames. ], batch size: 27, lr: 7.06e-03
2024-08-06 13:13:53,068 INFO [trainer.py:765] (1/8) Epoch 17, batch 1000, train_loss[loss=2.674, ArTop10Accuracy=0.7989, over 12906.00 frames. ], tot_loss[loss=2.738, ArTop10Accuracy=0.782, over 11879.24 frames. ], batch size: 27, lr: 7.04e-03
2024-08-06 13:15:08,490 INFO [trainer.py:765] (1/8) Epoch 17, batch 1100, train_loss[loss=2.717, ArTop10Accuracy=0.7841, over 13662.00 frames. ], tot_loss[loss=2.745, ArTop10Accuracy=0.7807, over 11971.73 frames. ], batch size: 34, lr: 7.02e-03
2024-08-06 13:16:22,394 INFO [trainer.py:765] (1/8) Epoch 17, batch 1200, train_loss[loss=2.911, ArTop10Accuracy=0.7513, over 11856.00 frames. ], tot_loss[loss=2.748, ArTop10Accuracy=0.7802, over 11884.24 frames. ], batch size: 103, lr: 7.01e-03
2024-08-06 13:17:21,749 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 13:19:16,000 INFO [trainer.py:765] (1/8) Epoch 18, batch 100, train_loss[loss=2.769, ArTop10Accuracy=0.7795, over 14613.00 frames. ], tot_loss[loss=2.722, ArTop10Accuracy=0.7849, over 4769.80 frames. ], batch size: 63, lr: 6.78e-03
2024-08-06 13:20:46,604 INFO [trainer.py:765] (1/8) Epoch 18, batch 200, train_loss[loss=2.692, ArTop10Accuracy=0.7902, over 13776.00 frames. ], tot_loss[loss=2.72, ArTop10Accuracy=0.7853, over 7773.05 frames. ], batch size: 34, lr: 6.77e-03
2024-08-06 13:21:55,111 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 13:22:04,751 INFO [trainer.py:811] (1/8) Epoch 18, validation: loss=2.817, ArTop10Accuracy=0.768, over 1827537.00 frames. 
2024-08-06 13:22:04,752 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 33972MB
2024-08-06 13:22:05,479 INFO [optim.py:386] (1/8) 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 13:22:26,587 INFO [trainer.py:765] (1/8) Epoch 18, batch 300, train_loss[loss=2.765, ArTop10Accuracy=0.7781, over 14328.00 frames. ], tot_loss[loss=2.717, ArTop10Accuracy=0.7859, over 9385.66 frames. ], batch size: 44, lr: 6.76e-03
2024-08-06 13:23:57,935 INFO [trainer.py:765] (1/8) Epoch 18, batch 400, train_loss[loss=2.545, ArTop10Accuracy=0.8139, over 10287.00 frames. ], tot_loss[loss=2.717, ArTop10Accuracy=0.7857, over 10291.69 frames. ], batch size: 14, lr: 6.74e-03
2024-08-06 13:25:34,019 INFO [trainer.py:765] (1/8) Epoch 18, batch 500, train_loss[loss=2.681, ArTop10Accuracy=0.7954, over 12234.00 frames. ], tot_loss[loss=2.713, ArTop10Accuracy=0.7866, over 10834.26 frames. ], batch size: 22, lr: 6.73e-03
2024-08-06 13:27:00,640 INFO [trainer.py:765] (1/8) Epoch 18, batch 600, train_loss[loss=2.674, ArTop10Accuracy=0.794, over 11292.00 frames. ], tot_loss[loss=2.717, ArTop10Accuracy=0.7857, over 11355.11 frames. ], batch size: 18, lr: 6.71e-03
2024-08-06 13:28:33,588 INFO [trainer.py:765] (1/8) Epoch 18, batch 700, train_loss[loss=2.683, ArTop10Accuracy=0.7953, over 10089.00 frames. ], tot_loss[loss=2.721, ArTop10Accuracy=0.7849, over 11511.68 frames. ], batch size: 12, lr: 6.70e-03
2024-08-06 13:29:54,989 INFO [trainer.py:765] (1/8) Epoch 18, batch 800, train_loss[loss=2.677, ArTop10Accuracy=0.7978, over 10206.00 frames. ], tot_loss[loss=2.725, ArTop10Accuracy=0.7842, over 11652.90 frames. ], batch size: 12, lr: 6.68e-03
2024-08-06 13:31:12,525 INFO [trainer.py:765] (1/8) Epoch 18, batch 900, train_loss[loss=2.734, ArTop10Accuracy=0.7881, over 12990.00 frames. ], tot_loss[loss=2.721, ArTop10Accuracy=0.7853, over 11691.99 frames. ], batch size: 27, lr: 6.67e-03
2024-08-06 13:32:26,557 INFO [trainer.py:765] (1/8) Epoch 18, batch 1000, train_loss[loss=2.804, ArTop10Accuracy=0.77, over 12660.00 frames. ], tot_loss[loss=2.727, ArTop10Accuracy=0.7841, over 11895.92 frames. ], batch size: 27, lr: 6.66e-03
2024-08-06 13:33:41,503 INFO [trainer.py:765] (1/8) Epoch 18, batch 1100, train_loss[loss=2.752, ArTop10Accuracy=0.7808, over 13716.00 frames. ], tot_loss[loss=2.736, ArTop10Accuracy=0.7824, over 11960.66 frames. ], batch size: 35, lr: 6.64e-03
2024-08-06 13:34:54,680 INFO [trainer.py:765] (1/8) Epoch 18, batch 1200, train_loss[loss=2.896, ArTop10Accuracy=0.753, over 12399.00 frames. ], tot_loss[loss=2.737, ArTop10Accuracy=0.7821, over 11856.69 frames. ], batch size: 101, lr: 6.63e-03
2024-08-06 13:35:51,070 INFO [optim.py:386] (1/8) 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 13:35:54,948 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 13:37:48,630 INFO [trainer.py:765] (1/8) Epoch 19, batch 100, train_loss[loss=2.699, ArTop10Accuracy=0.7911, over 14262.00 frames. ], tot_loss[loss=2.715, ArTop10Accuracy=0.7858, over 4758.72 frames. ], batch size: 63, lr: 6.43e-03
2024-08-06 13:39:23,263 INFO [trainer.py:765] (1/8) Epoch 19, batch 200, train_loss[loss=2.776, ArTop10Accuracy=0.7724, over 13521.00 frames. ], tot_loss[loss=2.709, ArTop10Accuracy=0.7868, over 7762.49 frames. ], batch size: 34, lr: 6.41e-03
2024-08-06 13:40:48,365 INFO [trainer.py:765] (1/8) Epoch 19, batch 300, train_loss[loss=2.801, ArTop10Accuracy=0.768, over 13980.00 frames. ], tot_loss[loss=2.712, ArTop10Accuracy=0.7867, over 9377.16 frames. ], batch size: 44, lr: 6.40e-03
2024-08-06 13:42:21,073 INFO [trainer.py:765] (1/8) Epoch 19, batch 400, train_loss[loss=2.678, ArTop10Accuracy=0.7925, over 10728.00 frames. ], tot_loss[loss=2.705, ArTop10Accuracy=0.7881, over 10287.82 frames. ], batch size: 15, lr: 6.39e-03
2024-08-06 13:43:44,961 INFO [trainer.py:765] (1/8) Epoch 19, batch 500, train_loss[loss=2.629, ArTop10Accuracy=0.8012, over 12252.00 frames. ], tot_loss[loss=2.701, ArTop10Accuracy=0.7885, over 10839.43 frames. ], batch size: 22, lr: 6.37e-03
2024-08-06 13:45:16,687 INFO [trainer.py:765] (1/8) Epoch 19, batch 600, train_loss[loss=2.795, ArTop10Accuracy=0.7709, over 11283.00 frames. ], tot_loss[loss=2.704, ArTop10Accuracy=0.7882, over 11371.27 frames. ], batch size: 18, lr: 6.36e-03
2024-08-06 13:46:48,328 INFO [trainer.py:765] (1/8) Epoch 19, batch 700, train_loss[loss=2.647, ArTop10Accuracy=0.7986, over 10188.00 frames. ], tot_loss[loss=2.712, ArTop10Accuracy=0.7867, over 11507.32 frames. ], batch size: 12, lr: 6.35e-03
2024-08-06 13:48:11,890 INFO [trainer.py:765] (1/8) Epoch 19, batch 800, train_loss[loss=2.643, ArTop10Accuracy=0.8003, over 10218.00 frames. ], tot_loss[loss=2.715, ArTop10Accuracy=0.7864, over 11619.30 frames. ], batch size: 12, lr: 6.34e-03
2024-08-06 13:49:27,263 INFO [trainer.py:765] (1/8) Epoch 19, batch 900, train_loss[loss=2.758, ArTop10Accuracy=0.777, over 13005.00 frames. ], tot_loss[loss=2.712, ArTop10Accuracy=0.7869, over 11663.49 frames. ], batch size: 27, lr: 6.32e-03
2024-08-06 13:50:40,658 INFO [trainer.py:803] (1/8) Computing validation loss
2024-08-06 13:50:50,535 INFO [trainer.py:811] (1/8) Epoch 19, validation: loss=2.818, ArTop10Accuracy=0.7679, over 1827537.00 frames. 
2024-08-06 13:50:50,536 INFO [trainer.py:814] (1/8) Maximum memory allocated so far is 33972MB
2024-08-06 13:50:51,493 INFO [optim.py:386] (1/8) 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 13:50:52,923 INFO [trainer.py:765] (1/8) Epoch 19, batch 1000, train_loss[loss=2.812, ArTop10Accuracy=0.7639, over 12567.00 frames. ], tot_loss[loss=2.718, ArTop10Accuracy=0.7857, over 11873.45 frames. ], batch size: 27, lr: 6.31e-03
2024-08-06 13:52:08,273 INFO [trainer.py:765] (1/8) Epoch 19, batch 1100, train_loss[loss=2.733, ArTop10Accuracy=0.7851, over 13866.00 frames. ], tot_loss[loss=2.727, ArTop10Accuracy=0.7839, over 11972.86 frames. ], batch size: 34, lr: 6.30e-03
2024-08-06 13:53:22,319 INFO [trainer.py:765] (1/8) Epoch 19, batch 1200, train_loss[loss=2.845, ArTop10Accuracy=0.7572, over 12054.00 frames. ], tot_loss[loss=2.728, ArTop10Accuracy=0.7836, over 11871.82 frames. ], batch size: 101, lr: 6.28e-03
2024-08-06 13:54:21,985 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 13:56:12,911 INFO [trainer.py:765] (1/8) Epoch 20, batch 100, train_loss[loss=2.773, ArTop10Accuracy=0.7772, over 14652.00 frames. ], tot_loss[loss=2.711, ArTop10Accuracy=0.7862, over 4761.24 frames. ], batch size: 62, lr: 6.10e-03
2024-08-06 13:57:42,499 INFO [trainer.py:765] (1/8) Epoch 20, batch 200, train_loss[loss=2.695, ArTop10Accuracy=0.7874, over 13536.00 frames. ], tot_loss[loss=2.704, ArTop10Accuracy=0.7882, over 7748.16 frames. ], batch size: 34, lr: 6.09e-03
2024-08-06 13:59:15,436 INFO [trainer.py:765] (1/8) Epoch 20, batch 300, train_loss[loss=2.737, ArTop10Accuracy=0.779, over 14100.00 frames. ], tot_loss[loss=2.7, ArTop10Accuracy=0.7891, over 9381.75 frames. ], batch size: 44, lr: 6.08e-03
2024-08-06 14:00:44,362 INFO [trainer.py:765] (1/8) Epoch 20, batch 400, train_loss[loss=2.589, ArTop10Accuracy=0.8097, over 10383.00 frames. ], tot_loss[loss=2.698, ArTop10Accuracy=0.7892, over 10302.26 frames. ], batch size: 14, lr: 6.07e-03
2024-08-06 14:02:14,860 INFO [trainer.py:765] (1/8) Epoch 20, batch 500, train_loss[loss=2.766, ArTop10Accuracy=0.7745, over 12717.00 frames. ], tot_loss[loss=2.697, ArTop10Accuracy=0.7896, over 10858.59 frames. ], batch size: 23, lr: 6.06e-03
2024-08-06 14:03:40,860 INFO [trainer.py:765] (1/8) Epoch 20, batch 600, train_loss[loss=2.662, ArTop10Accuracy=0.7981, over 11499.00 frames. ], tot_loss[loss=2.699, ArTop10Accuracy=0.7891, over 11367.87 frames. ], batch size: 18, lr: 6.04e-03
2024-08-06 14:05:13,872 INFO [trainer.py:765] (1/8) Epoch 20, batch 700, train_loss[loss=2.667, ArTop10Accuracy=0.7949, over 10287.00 frames. ], tot_loss[loss=2.706, ArTop10Accuracy=0.7879, over 11530.59 frames. ], batch size: 12, lr: 6.03e-03
2024-08-06 14:05:30,795 INFO [optim.py:386] (1/8) 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 14:06:34,515 INFO [trainer.py:765] (1/8) Epoch 20, batch 800, train_loss[loss=2.604, ArTop10Accuracy=0.8108, over 9273.00 frames. ], tot_loss[loss=2.713, ArTop10Accuracy=0.7865, over 11640.77 frames. ], batch size: 11, lr: 6.02e-03
2024-08-06 14:07:50,950 INFO [trainer.py:765] (1/8) Epoch 20, batch 900, train_loss[loss=2.748, ArTop10Accuracy=0.7846, over 12843.00 frames. ], tot_loss[loss=2.704, ArTop10Accuracy=0.7883, over 11683.45 frames. ], batch size: 27, lr: 6.01e-03
2024-08-06 14:09:07,180 INFO [trainer.py:765] (1/8) Epoch 20, batch 1000, train_loss[loss=2.718, ArTop10Accuracy=0.7892, over 12714.00 frames. ], tot_loss[loss=2.706, ArTop10Accuracy=0.7881, over 11882.84 frames. ], batch size: 27, lr: 6.00e-03
2024-08-06 14:10:21,216 INFO [trainer.py:765] (1/8) Epoch 20, batch 1100, train_loss[loss=2.752, ArTop10Accuracy=0.7788, over 14235.00 frames. ], tot_loss[loss=2.712, ArTop10Accuracy=0.7871, over 11959.70 frames. ], batch size: 35, lr: 5.99e-03
2024-08-06 14:11:37,820 INFO [trainer.py:765] (1/8) Epoch 20, batch 1200, train_loss[loss=2.856, ArTop10Accuracy=0.758, over 12105.00 frames. ], tot_loss[loss=2.715, ArTop10Accuracy=0.7866, over 11876.99 frames. ], batch size: 101, lr: 5.98e-03
2024-08-06 14:12:36,847 INFO [trainer.py:650] (1/8) Reaches end of dataloader.
2024-08-06 14:12:36,850 INFO [trainer.py:1069] (1/8) Done!