2024-08-06 08:06:14,318 INFO [trainer.py:870] (4/8) Training started
2024-08-06 08:06:14,319 INFO [trainer.py:889] (4/8) Device: cuda:4
2024-08-06 08:06:14,319 INFO [trainer.py:890] (4/8) {'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 08:06:14,319 INFO [trainer.py:892] (4/8) About to create model
2024-08-06 08:06:15,010 INFO [trainer.py:899] (4/8) Number of model parameters: 367386628
2024-08-06 08:06:16,222 INFO [trainer.py:914] (4/8) Using DDP
2024-08-06 08:06:19,151 INFO [datamodule.py:427] (4/8) About to get train cuts
2024-08-06 08:06:19,153 INFO [datamodule.py:434] (4/8) About to get dev cuts
2024-08-06 08:06:19,155 INFO [datamodule.py:292] (4/8) Disable SpecAugment
2024-08-06 08:06:19,155 INFO [datamodule.py:294] (4/8) About to create train dataset
2024-08-06 08:06:19,155 INFO [datamodule.py:323] (4/8) Using DynamicBucketingSampler
2024-08-06 08:06:19,763 INFO [datamodule.py:344] (4/8) About to create train dataloader
2024-08-06 08:06:19,763 INFO [datamodule.py:367] (4/8) About to create dev dataset
2024-08-06 08:06:20,087 INFO [datamodule.py:388] (4/8) About to create dev dataloader
2024-08-06 08:08:02,120 INFO [trainer.py:765] (4/8) Epoch 1, batch 100, train_loss[loss=4.335, ArTop10Accuracy=0.4992, over 14349.00 frames. ], tot_loss[loss=5.058, ArTop10Accuracy=0.3727, over 4771.89 frames. ], batch size: 62, lr: 2.25e-02
2024-08-06 08:09:28,827 INFO [trainer.py:765] (4/8) Epoch 1, batch 200, train_loss[loss=4.111, ArTop10Accuracy=0.5308, over 13680.00 frames. ], tot_loss[loss=4.496, ArTop10Accuracy=0.4669, over 7746.35 frames. ], batch size: 34, lr: 3.00e-02
2024-08-06 08:10:52,430 INFO [trainer.py:765] (4/8) Epoch 1, batch 300, train_loss[loss=3.881, ArTop10Accuracy=0.5686, over 14085.00 frames. ], tot_loss[loss=4.218, ArTop10Accuracy=0.5129, over 9372.51 frames. ], batch size: 44, lr: 3.00e-02
2024-08-06 08:12:12,698 INFO [trainer.py:765] (4/8) Epoch 1, batch 400, train_loss[loss=3.738, ArTop10Accuracy=0.6, over 10314.00 frames. ], tot_loss[loss=4.027, ArTop10Accuracy=0.5454, over 10297.26 frames. ], batch size: 14, lr: 3.00e-02
2024-08-06 08:13:40,049 INFO [trainer.py:765] (4/8) Epoch 1, batch 500, train_loss[loss=3.696, ArTop10Accuracy=0.6047, over 12063.00 frames. ], tot_loss[loss=3.883, ArTop10Accuracy=0.5703, over 10855.34 frames. ], batch size: 22, lr: 2.99e-02
2024-08-06 08:15:00,242 INFO [trainer.py:765] (4/8) Epoch 1, batch 600, train_loss[loss=3.559, ArTop10Accuracy=0.6271, over 11481.00 frames. ], tot_loss[loss=3.773, ArTop10Accuracy=0.5898, over 11365.23 frames. ], batch size: 18, lr: 2.99e-02
2024-08-06 08:16:26,424 INFO [trainer.py:765] (4/8) Epoch 1, batch 700, train_loss[loss=3.57, ArTop10Accuracy=0.6244, over 10320.00 frames. ], tot_loss[loss=3.695, ArTop10Accuracy=0.6037, over 11513.99 frames. ], batch size: 12, lr: 2.99e-02
2024-08-06 08:17:43,017 INFO [trainer.py:765] (4/8) Epoch 1, batch 800, train_loss[loss=3.429, ArTop10Accuracy=0.6523, over 9978.00 frames. ], tot_loss[loss=3.627, ArTop10Accuracy=0.6163, over 11645.81 frames. ], batch size: 12, lr: 2.98e-02
2024-08-06 08:18:56,150 INFO [trainer.py:765] (4/8) Epoch 1, batch 900, train_loss[loss=3.458, ArTop10Accuracy=0.6464, over 12951.00 frames. ], tot_loss[loss=3.567, ArTop10Accuracy=0.6273, over 11687.10 frames. ], batch size: 27, lr: 2.98e-02
2024-08-06 08:20:12,862 INFO [trainer.py:765] (4/8) Epoch 1, batch 1000, train_loss[loss=3.476, ArTop10Accuracy=0.6408, over 13488.00 frames. ], tot_loss[loss=3.524, ArTop10Accuracy=0.635, over 11889.35 frames. ], batch size: 28, lr: 2.97e-02
2024-08-06 08:20:13,539 INFO [optim.py:386] (4/8) 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 08:21:29,154 INFO [trainer.py:765] (4/8) Epoch 1, batch 1100, train_loss[loss=3.469, ArTop10Accuracy=0.6412, over 13692.00 frames. ], tot_loss[loss=3.487, ArTop10Accuracy=0.6416, over 11959.37 frames. ], batch size: 34, lr: 2.96e-02
2024-08-06 08:22:45,410 INFO [trainer.py:765] (4/8) Epoch 1, batch 1200, train_loss[loss=3.468, ArTop10Accuracy=0.6428, over 11691.00 frames. ], tot_loss[loss=3.456, ArTop10Accuracy=0.6475, over 11856.20 frames. ], batch size: 101, lr: 2.96e-02
2024-08-06 08:23:45,262 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 08:25:36,236 INFO [trainer.py:765] (4/8) Epoch 2, batch 100, train_loss[loss=3.453, ArTop10Accuracy=0.6483, over 14559.00 frames. ], tot_loss[loss=3.419, ArTop10Accuracy=0.6533, over 4753.85 frames. ], batch size: 62, lr: 2.90e-02
2024-08-06 08:26:58,955 INFO [trainer.py:765] (4/8) Epoch 2, batch 200, train_loss[loss=3.27, ArTop10Accuracy=0.6853, over 13752.00 frames. ], tot_loss[loss=3.384, ArTop10Accuracy=0.6604, over 7757.10 frames. ], batch size: 34, lr: 2.89e-02
2024-08-06 08:28:25,533 INFO [trainer.py:765] (4/8) Epoch 2, batch 300, train_loss[loss=3.402, ArTop10Accuracy=0.6578, over 14046.00 frames. ], tot_loss[loss=3.371, ArTop10Accuracy=0.6631, over 9382.03 frames. ], batch size: 44, lr: 2.89e-02
2024-08-06 08:29:48,636 INFO [trainer.py:765] (4/8) Epoch 2, batch 400, train_loss[loss=3.355, ArTop10Accuracy=0.6619, over 10944.00 frames. ], tot_loss[loss=3.358, ArTop10Accuracy=0.6657, over 10312.86 frames. ], batch size: 15, lr: 2.88e-02
2024-08-06 08:31:22,902 INFO [trainer.py:765] (4/8) Epoch 2, batch 500, train_loss[loss=3.212, ArTop10Accuracy=0.6956, over 12171.00 frames. ], tot_loss[loss=3.339, ArTop10Accuracy=0.6692, over 10869.97 frames. ], batch size: 22, lr: 2.87e-02
2024-08-06 08:32:45,688 INFO [trainer.py:765] (4/8) Epoch 2, batch 600, train_loss[loss=3.308, ArTop10Accuracy=0.6743, over 11418.00 frames. ], tot_loss[loss=3.329, ArTop10Accuracy=0.671, over 11384.57 frames. ], batch size: 18, lr: 2.86e-02
2024-08-06 08:34:13,582 INFO [trainer.py:765] (4/8) Epoch 2, batch 700, train_loss[loss=3.313, ArTop10Accuracy=0.6793, over 9951.00 frames. ], tot_loss[loss=3.325, ArTop10Accuracy=0.6719, over 11534.00 frames. ], batch size: 12, lr: 2.85e-02
2024-08-06 08:34:31,175 INFO [trainer.py:803] (4/8) Computing validation loss
2024-08-06 08:34:40,888 INFO [trainer.py:811] (4/8) Epoch 2, validation: loss=3.277, ArTop10Accuracy=0.6803, over 1827537.00 frames. 
2024-08-06 08:34:40,889 INFO [trainer.py:814] (4/8) Maximum memory allocated so far is 28695MB
2024-08-06 08:34:41,699 INFO [optim.py:386] (4/8) 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] (4/8) Epoch 2, batch 800, train_loss[loss=3.2, ArTop10Accuracy=0.6972, over 9570.00 frames. ], tot_loss[loss=3.318, ArTop10Accuracy=0.6735, over 11652.56 frames. ], batch size: 11, lr: 2.84e-02
2024-08-06 08:36:56,371 INFO [trainer.py:765] (4/8) Epoch 2, batch 900, train_loss[loss=3.262, ArTop10Accuracy=0.6776, over 12861.00 frames. ], tot_loss[loss=3.305, ArTop10Accuracy=0.6758, over 11691.96 frames. ], batch size: 27, lr: 2.83e-02
2024-08-06 08:38:10,511 INFO [trainer.py:765] (4/8) Epoch 2, batch 1000, train_loss[loss=3.307, ArTop10Accuracy=0.6773, over 13053.00 frames. ], tot_loss[loss=3.299, ArTop10Accuracy=0.677, over 11892.14 frames. ], batch size: 27, lr: 2.82e-02
2024-08-06 08:39:25,059 INFO [trainer.py:765] (4/8) Epoch 2, batch 1100, train_loss[loss=3.159, ArTop10Accuracy=0.7048, over 13839.00 frames. ], tot_loss[loss=3.292, ArTop10Accuracy=0.6781, over 11930.52 frames. ], batch size: 34, lr: 2.81e-02
2024-08-06 08:40:38,219 INFO [trainer.py:765] (4/8) Epoch 2, batch 1200, train_loss[loss=3.333, ArTop10Accuracy=0.6674, over 13452.00 frames. ], tot_loss[loss=3.283, ArTop10Accuracy=0.6799, over 11836.01 frames. ], batch size: 101, lr: 2.80e-02
2024-08-06 08:41:38,601 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 08:43:36,649 INFO [trainer.py:765] (4/8) Epoch 3, batch 100, train_loss[loss=3.256, ArTop10Accuracy=0.6832, over 14394.00 frames. ], tot_loss[loss=3.244, ArTop10Accuracy=0.6866, over 4768.62 frames. ], batch size: 62, lr: 2.67e-02
2024-08-06 08:45:10,500 INFO [trainer.py:765] (4/8) Epoch 3, batch 200, train_loss[loss=3.201, ArTop10Accuracy=0.695, over 13674.00 frames. ], tot_loss[loss=3.221, ArTop10Accuracy=0.6908, over 7764.36 frames. ], batch size: 34, lr: 2.66e-02
2024-08-06 08:46:29,258 INFO [trainer.py:765] (4/8) Epoch 3, batch 300, train_loss[loss=3.233, ArTop10Accuracy=0.6863, over 14310.00 frames. ], tot_loss[loss=3.207, ArTop10Accuracy=0.6938, over 9365.66 frames. ], batch size: 44, lr: 2.64e-02
2024-08-06 08:48:04,219 INFO [trainer.py:765] (4/8) Epoch 3, batch 400, train_loss[loss=3.129, ArTop10Accuracy=0.7089, over 10473.00 frames. ], tot_loss[loss=3.192, ArTop10Accuracy=0.6969, over 10282.72 frames. ], batch size: 14, lr: 2.63e-02
2024-08-06 08:48:40,881 INFO [optim.py:386] (4/8) 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 08:49:25,541 INFO [trainer.py:765] (4/8) Epoch 3, batch 500, train_loss[loss=3.17, ArTop10Accuracy=0.7073, over 12351.00 frames. ], tot_loss[loss=3.172, ArTop10Accuracy=0.7009, over 10852.39 frames. ], batch size: 22, lr: 2.62e-02
2024-08-06 08:51:00,477 INFO [trainer.py:765] (4/8) Epoch 3, batch 600, train_loss[loss=3.056, ArTop10Accuracy=0.7223, over 11325.00 frames. ], tot_loss[loss=3.16, ArTop10Accuracy=0.7028, over 11381.83 frames. ], batch size: 18, lr: 2.61e-02
2024-08-06 08:52:31,618 INFO [trainer.py:765] (4/8) Epoch 3, batch 700, train_loss[loss=3.058, ArTop10Accuracy=0.7241, over 10176.00 frames. ], tot_loss[loss=3.143, ArTop10Accuracy=0.7062, over 11521.06 frames. ], batch size: 12, lr: 2.60e-02
2024-08-06 08:53:57,389 INFO [trainer.py:765] (4/8) Epoch 3, batch 800, train_loss[loss=3.078, ArTop10Accuracy=0.7212, over 9276.00 frames. ], tot_loss[loss=3.137, ArTop10Accuracy=0.7072, over 11622.44 frames. ], batch size: 11, lr: 2.59e-02
2024-08-06 08:55:15,119 INFO [trainer.py:765] (4/8) Epoch 3, batch 900, train_loss[loss=3.061, ArTop10Accuracy=0.7179, over 13047.00 frames. ], tot_loss[loss=3.123, ArTop10Accuracy=0.7099, over 11666.34 frames. ], batch size: 27, lr: 2.57e-02
2024-08-06 08:56:31,557 INFO [trainer.py:765] (4/8) Epoch 3, batch 1000, train_loss[loss=3.183, ArTop10Accuracy=0.6972, over 12882.00 frames. ], tot_loss[loss=3.112, ArTop10Accuracy=0.7119, over 11867.25 frames. ], batch size: 27, lr: 2.56e-02
2024-08-06 08:57:46,506 INFO [trainer.py:765] (4/8) Epoch 3, batch 1100, train_loss[loss=2.998, ArTop10Accuracy=0.7333, over 13554.00 frames. ], tot_loss[loss=3.105, ArTop10Accuracy=0.7132, over 11926.75 frames. ], batch size: 34, lr: 2.55e-02
2024-08-06 08:59:01,399 INFO [trainer.py:765] (4/8) Epoch 3, batch 1200, train_loss[loss=3.151, ArTop10Accuracy=0.7024, over 13326.00 frames. ], tot_loss[loss=3.097, ArTop10Accuracy=0.7145, over 11854.55 frames. ], batch size: 101, lr: 2.54e-02
2024-08-06 09:00:01,980 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 09:01:50,742 INFO [trainer.py:765] (4/8) Epoch 4, batch 100, train_loss[loss=3.127, ArTop10Accuracy=0.7081, over 14670.00 frames. ], tot_loss[loss=3.065, ArTop10Accuracy=0.7201, over 4761.72 frames. ], batch size: 64, lr: 2.38e-02
2024-08-06 09:02:52,859 INFO [trainer.py:803] (4/8) Computing validation loss
2024-08-06 09:03:02,384 INFO [trainer.py:811] (4/8) Epoch 4, validation: loss=2.997, ArTop10Accuracy=0.7338, over 1827537.00 frames. 
2024-08-06 09:03:02,385 INFO [trainer.py:814] (4/8) Maximum memory allocated so far is 29513MB
2024-08-06 09:03:03,364 INFO [optim.py:386] (4/8) 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 09:03:29,273 INFO [trainer.py:765] (4/8) Epoch 4, batch 200, train_loss[loss=3.069, ArTop10Accuracy=0.718, over 13527.00 frames. ], tot_loss[loss=3.041, ArTop10Accuracy=0.7249, over 7754.25 frames. ], batch size: 34, lr: 2.37e-02
2024-08-06 09:05:01,733 INFO [trainer.py:765] (4/8) Epoch 4, batch 300, train_loss[loss=3.133, ArTop10Accuracy=0.7066, over 14562.00 frames. ], tot_loss[loss=3.038, ArTop10Accuracy=0.7259, over 9353.08 frames. ], batch size: 45, lr: 2.36e-02
2024-08-06 09:06:28,151 INFO [trainer.py:765] (4/8) Epoch 4, batch 400, train_loss[loss=2.94, ArTop10Accuracy=0.7486, over 10116.00 frames. ], tot_loss[loss=3.034, ArTop10Accuracy=0.7265, over 10275.79 frames. ], batch size: 14, lr: 2.34e-02
2024-08-06 09:08:01,925 INFO [trainer.py:765] (4/8) Epoch 4, batch 500, train_loss[loss=3.045, ArTop10Accuracy=0.7286, over 12501.00 frames. ], tot_loss[loss=3.029, ArTop10Accuracy=0.7272, over 10828.04 frames. ], batch size: 23, lr: 2.33e-02
2024-08-06 09:09:28,540 INFO [trainer.py:765] (4/8) Epoch 4, batch 600, train_loss[loss=2.955, ArTop10Accuracy=0.7423, over 11589.00 frames. ], tot_loss[loss=3.024, ArTop10Accuracy=0.7284, over 11374.57 frames. ], batch size: 18, lr: 2.32e-02
2024-08-06 09:10:59,865 INFO [trainer.py:765] (4/8) Epoch 4, batch 700, train_loss[loss=3.009, ArTop10Accuracy=0.7394, over 10125.00 frames. ], tot_loss[loss=3.026, ArTop10Accuracy=0.7277, over 11515.59 frames. ], batch size: 12, lr: 2.31e-02
2024-08-06 09:12:17,513 INFO [trainer.py:765] (4/8) Epoch 4, batch 800, train_loss[loss=2.969, ArTop10Accuracy=0.7425, over 9366.00 frames. ], tot_loss[loss=3.022, ArTop10Accuracy=0.7288, over 11640.09 frames. ], batch size: 11, lr: 2.30e-02
2024-08-06 09:13:33,212 INFO [trainer.py:765] (4/8) Epoch 4, batch 900, train_loss[loss=2.992, ArTop10Accuracy=0.7306, over 12924.00 frames. ], tot_loss[loss=3.012, ArTop10Accuracy=0.7308, over 11686.06 frames. ], batch size: 27, lr: 2.29e-02
2024-08-06 09:14:47,520 INFO [trainer.py:765] (4/8) Epoch 4, batch 1000, train_loss[loss=2.935, ArTop10Accuracy=0.7421, over 12690.00 frames. ], tot_loss[loss=3.011, ArTop10Accuracy=0.7308, over 11873.84 frames. ], batch size: 27, lr: 2.28e-02
2024-08-06 09:16:02,982 INFO [trainer.py:765] (4/8) Epoch 4, batch 1100, train_loss[loss=2.965, ArTop10Accuracy=0.741, over 13602.00 frames. ], tot_loss[loss=3.011, ArTop10Accuracy=0.7308, over 11940.21 frames. ], batch size: 34, lr: 2.26e-02
2024-08-06 09:16:53,291 INFO [optim.py:386] (4/8) 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 09:17:18,344 INFO [trainer.py:765] (4/8) Epoch 4, batch 1200, train_loss[loss=3.053, ArTop10Accuracy=0.7237, over 12633.00 frames. ], tot_loss[loss=3.01, ArTop10Accuracy=0.7309, over 11854.12 frames. ], batch size: 101, lr: 2.25e-02
2024-08-06 09:18:17,349 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 09:20:17,170 INFO [trainer.py:765] (4/8) Epoch 5, batch 100, train_loss[loss=3.024, ArTop10Accuracy=0.725, over 14337.00 frames. ], tot_loss[loss=2.997, ArTop10Accuracy=0.7326, over 4765.65 frames. ], batch size: 62, lr: 2.10e-02
2024-08-06 09:21:52,295 INFO [trainer.py:765] (4/8) Epoch 5, batch 200, train_loss[loss=2.968, ArTop10Accuracy=0.7412, over 13647.00 frames. ], tot_loss[loss=2.972, ArTop10Accuracy=0.7375, over 7764.93 frames. ], batch size: 34, lr: 2.09e-02
2024-08-06 09:23:19,240 INFO [trainer.py:765] (4/8) Epoch 5, batch 300, train_loss[loss=3.021, ArTop10Accuracy=0.7283, over 14367.00 frames. ], tot_loss[loss=2.966, ArTop10Accuracy=0.7392, over 9381.01 frames. ], batch size: 45, lr: 2.08e-02
2024-08-06 09:24:53,536 INFO [trainer.py:765] (4/8) Epoch 5, batch 400, train_loss[loss=2.943, ArTop10Accuracy=0.7394, over 10296.00 frames. ], tot_loss[loss=2.963, ArTop10Accuracy=0.74, over 10297.28 frames. ], batch size: 14, lr: 2.07e-02
2024-08-06 09:26:19,417 INFO [trainer.py:765] (4/8) Epoch 5, batch 500, train_loss[loss=2.9, ArTop10Accuracy=0.7498, over 12066.00 frames. ], tot_loss[loss=2.961, ArTop10Accuracy=0.7404, over 10856.08 frames. ], batch size: 22, lr: 2.06e-02
2024-08-06 09:27:49,536 INFO [trainer.py:765] (4/8) Epoch 5, batch 600, train_loss[loss=3.014, ArTop10Accuracy=0.7307, over 11511.00 frames. ], tot_loss[loss=2.963, ArTop10Accuracy=0.7401, over 11385.83 frames. ], batch size: 18, lr: 2.05e-02
2024-08-06 09:29:21,669 INFO [trainer.py:765] (4/8) Epoch 5, batch 700, train_loss[loss=2.976, ArTop10Accuracy=0.733, over 9171.00 frames. ], tot_loss[loss=2.967, ArTop10Accuracy=0.7393, over 11512.86 frames. ], batch size: 11, lr: 2.04e-02
2024-08-06 09:30:44,692 INFO [trainer.py:765] (4/8) Epoch 5, batch 800, train_loss[loss=2.901, ArTop10Accuracy=0.7489, over 10170.00 frames. ], tot_loss[loss=2.971, ArTop10Accuracy=0.7385, over 11642.97 frames. ], batch size: 12, lr: 2.03e-02
2024-08-06 09:31:51,238 INFO [trainer.py:803] (4/8) Computing validation loss
2024-08-06 09:32:00,762 INFO [trainer.py:811] (4/8) Epoch 5, validation: loss=2.926, ArTop10Accuracy=0.7466, over 1827537.00 frames. 
2024-08-06 09:32:00,763 INFO [trainer.py:814] (4/8) Maximum memory allocated so far is 32729MB
2024-08-06 09:32:01,708 INFO [optim.py:386] (4/8) 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 09:32:10,553 INFO [trainer.py:765] (4/8) Epoch 5, batch 900, train_loss[loss=2.998, ArTop10Accuracy=0.7307, over 12870.00 frames. ], tot_loss[loss=2.961, ArTop10Accuracy=0.7404, over 11683.19 frames. ], batch size: 27, lr: 2.02e-02
2024-08-06 09:33:27,322 INFO [trainer.py:765] (4/8) Epoch 5, batch 1000, train_loss[loss=2.89, ArTop10Accuracy=0.7553, over 12822.00 frames. ], tot_loss[loss=2.963, ArTop10Accuracy=0.7399, over 11878.40 frames. ], batch size: 27, lr: 2.01e-02
2024-08-06 09:34:42,299 INFO [trainer.py:765] (4/8) Epoch 5, batch 1100, train_loss[loss=2.96, ArTop10Accuracy=0.7399, over 13461.00 frames. ], tot_loss[loss=2.961, ArTop10Accuracy=0.7402, over 11949.48 frames. ], batch size: 34, lr: 2.00e-02
2024-08-06 09:35:56,331 INFO [trainer.py:765] (4/8) Epoch 5, batch 1200, train_loss[loss=3.116, ArTop10Accuracy=0.7083, over 11610.00 frames. ], tot_loss[loss=2.957, ArTop10Accuracy=0.7409, over 11851.67 frames. ], batch size: 101, lr: 1.99e-02
2024-08-06 09:36:55,326 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 09:38:52,664 INFO [trainer.py:765] (4/8) Epoch 6, batch 100, train_loss[loss=3.011, ArTop10Accuracy=0.7297, over 14652.00 frames. ], tot_loss[loss=2.953, ArTop10Accuracy=0.7414, over 4763.22 frames. ], batch size: 63, lr: 1.85e-02
2024-08-06 09:40:19,833 INFO [trainer.py:765] (4/8) Epoch 6, batch 200, train_loss[loss=2.924, ArTop10Accuracy=0.749, over 13821.00 frames. ], tot_loss[loss=2.935, ArTop10Accuracy=0.7448, over 7747.45 frames. ], batch size: 34, lr: 1.84e-02
2024-08-06 09:41:52,964 INFO [trainer.py:765] (4/8) Epoch 6, batch 300, train_loss[loss=2.895, ArTop10Accuracy=0.7482, over 14133.00 frames. ], tot_loss[loss=2.931, ArTop10Accuracy=0.7456, over 9381.03 frames. ], batch size: 44, lr: 1.83e-02
2024-08-06 09:43:17,827 INFO [trainer.py:765] (4/8) Epoch 6, batch 400, train_loss[loss=2.934, ArTop10Accuracy=0.7428, over 10410.00 frames. ], tot_loss[loss=2.927, ArTop10Accuracy=0.7465, over 10294.73 frames. ], batch size: 14, lr: 1.83e-02
2024-08-06 09:44:54,127 INFO [trainer.py:765] (4/8) Epoch 6, batch 500, train_loss[loss=2.914, ArTop10Accuracy=0.7514, over 12327.00 frames. ], tot_loss[loss=2.916, ArTop10Accuracy=0.7488, over 10858.88 frames. ], batch size: 22, lr: 1.82e-02
2024-08-06 09:46:22,872 INFO [trainer.py:765] (4/8) Epoch 6, batch 600, train_loss[loss=2.957, ArTop10Accuracy=0.7467, over 11445.00 frames. ], tot_loss[loss=2.921, ArTop10Accuracy=0.7477, over 11366.12 frames. ], batch size: 18, lr: 1.81e-02
2024-08-06 09:46:37,219 INFO [optim.py:386] (4/8) 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 09:47:57,869 INFO [trainer.py:765] (4/8) Epoch 6, batch 700, train_loss[loss=2.881, ArTop10Accuracy=0.7528, over 10191.00 frames. ], tot_loss[loss=2.925, ArTop10Accuracy=0.7467, over 11534.85 frames. ], batch size: 12, lr: 1.80e-02
2024-08-06 09:49:15,954 INFO [trainer.py:765] (4/8) Epoch 6, batch 800, train_loss[loss=2.915, ArTop10Accuracy=0.7503, over 9345.00 frames. ], tot_loss[loss=2.927, ArTop10Accuracy=0.7465, over 11644.71 frames. ], batch size: 11, lr: 1.79e-02
2024-08-06 09:50:32,134 INFO [trainer.py:765] (4/8) Epoch 6, batch 900, train_loss[loss=2.904, ArTop10Accuracy=0.7514, over 13062.00 frames. ], tot_loss[loss=2.923, ArTop10Accuracy=0.7472, over 11680.49 frames. ], batch size: 27, lr: 1.78e-02
2024-08-06 09:51:47,298 INFO [trainer.py:765] (4/8) Epoch 6, batch 1000, train_loss[loss=2.913, ArTop10Accuracy=0.752, over 12957.00 frames. ], tot_loss[loss=2.925, ArTop10Accuracy=0.747, over 11873.10 frames. ], batch size: 27, lr: 1.77e-02
2024-08-06 09:53:00,920 INFO [trainer.py:765] (4/8) Epoch 6, batch 1100, train_loss[loss=2.91, ArTop10Accuracy=0.7514, over 13686.00 frames. ], tot_loss[loss=2.931, ArTop10Accuracy=0.7458, over 11944.91 frames. ], batch size: 34, lr: 1.77e-02
2024-08-06 09:54:14,336 INFO [trainer.py:765] (4/8) Epoch 6, batch 1200, train_loss[loss=3.056, ArTop10Accuracy=0.7208, over 12609.00 frames. ], tot_loss[loss=2.93, ArTop10Accuracy=0.7461, over 11868.14 frames. ], batch size: 101, lr: 1.76e-02
2024-08-06 09:55:13,263 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 09:57:06,699 INFO [trainer.py:765] (4/8) Epoch 7, batch 100, train_loss[loss=2.98, ArTop10Accuracy=0.7353, over 14310.00 frames. ], tot_loss[loss=2.918, ArTop10Accuracy=0.748, over 4748.26 frames. ], batch size: 62, lr: 1.64e-02
2024-08-06 09:58:39,426 INFO [trainer.py:765] (4/8) Epoch 7, batch 200, train_loss[loss=2.916, ArTop10Accuracy=0.7468, over 13752.00 frames. ], tot_loss[loss=2.906, ArTop10Accuracy=0.7504, over 7746.19 frames. ], batch size: 34, lr: 1.64e-02
2024-08-06 10:00:06,083 INFO [trainer.py:765] (4/8) Epoch 7, batch 300, train_loss[loss=2.979, ArTop10Accuracy=0.7354, over 13800.00 frames. ], tot_loss[loss=2.898, ArTop10Accuracy=0.7517, over 9374.86 frames. ], batch size: 44, lr: 1.63e-02
2024-08-06 10:00:40,509 INFO [trainer.py:803] (4/8) Computing validation loss
2024-08-06 10:00:50,245 INFO [trainer.py:811] (4/8) Epoch 7, validation: loss=2.88, ArTop10Accuracy=0.7554, over 1827537.00 frames. 
2024-08-06 10:00:50,246 INFO [trainer.py:814] (4/8) Maximum memory allocated so far is 32729MB
2024-08-06 10:00:50,977 INFO [optim.py:386] (4/8) 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 10:01:49,118 INFO [trainer.py:765] (4/8) Epoch 7, batch 400, train_loss[loss=2.852, ArTop10Accuracy=0.765, over 10215.00 frames. ], tot_loss[loss=2.896, ArTop10Accuracy=0.7524, over 10288.13 frames. ], batch size: 14, lr: 1.62e-02
2024-08-06 10:03:21,457 INFO [trainer.py:765] (4/8) Epoch 7, batch 500, train_loss[loss=2.888, ArTop10Accuracy=0.7599, over 12327.00 frames. ], tot_loss[loss=2.891, ArTop10Accuracy=0.7534, over 10853.35 frames. ], batch size: 22, lr: 1.61e-02
2024-08-06 10:04:51,882 INFO [trainer.py:765] (4/8) Epoch 7, batch 600, train_loss[loss=2.909, ArTop10Accuracy=0.7526, over 11847.00 frames. ], tot_loss[loss=2.895, ArTop10Accuracy=0.7529, over 11343.07 frames. ], batch size: 19, lr: 1.61e-02
2024-08-06 10:06:25,112 INFO [trainer.py:765] (4/8) Epoch 7, batch 700, train_loss[loss=2.939, ArTop10Accuracy=0.7475, over 9381.00 frames. ], tot_loss[loss=2.896, ArTop10Accuracy=0.7526, over 11502.86 frames. ], batch size: 11, lr: 1.60e-02
2024-08-06 10:07:46,948 INFO [trainer.py:765] (4/8) Epoch 7, batch 800, train_loss[loss=2.904, ArTop10Accuracy=0.7507, over 10071.00 frames. ], tot_loss[loss=2.902, ArTop10Accuracy=0.7514, over 11636.93 frames. ], batch size: 12, lr: 1.59e-02
2024-08-06 10:09:02,824 INFO [trainer.py:765] (4/8) Epoch 7, batch 900, train_loss[loss=2.835, ArTop10Accuracy=0.7591, over 12993.00 frames. ], tot_loss[loss=2.893, ArTop10Accuracy=0.753, over 11682.69 frames. ], batch size: 27, lr: 1.59e-02
2024-08-06 10:10:19,636 INFO [trainer.py:765] (4/8) Epoch 7, batch 1000, train_loss[loss=2.856, ArTop10Accuracy=0.7663, over 12762.00 frames. ], tot_loss[loss=2.898, ArTop10Accuracy=0.7523, over 11896.36 frames. ], batch size: 27, lr: 1.58e-02
2024-08-06 10:11:35,208 INFO [trainer.py:765] (4/8) Epoch 7, batch 1100, train_loss[loss=2.936, ArTop10Accuracy=0.7445, over 13755.00 frames. ], tot_loss[loss=2.902, ArTop10Accuracy=0.7512, over 11966.74 frames. ], batch size: 34, lr: 1.57e-02
2024-08-06 10:12:48,204 INFO [trainer.py:765] (4/8) Epoch 7, batch 1200, train_loss[loss=3.002, ArTop10Accuracy=0.7326, over 12930.00 frames. ], tot_loss[loss=2.898, ArTop10Accuracy=0.7519, over 11872.20 frames. ], batch size: 101, lr: 1.57e-02
2024-08-06 10:13:46,750 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 10:15:03,600 INFO [optim.py:386] (4/8) 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 10:15:40,820 INFO [trainer.py:765] (4/8) Epoch 8, batch 100, train_loss[loss=3.008, ArTop10Accuracy=0.7324, over 14205.00 frames. ], tot_loss[loss=2.887, ArTop10Accuracy=0.754, over 4763.79 frames. ], batch size: 62, lr: 1.47e-02
2024-08-06 10:17:12,861 INFO [trainer.py:765] (4/8) Epoch 8, batch 200, train_loss[loss=2.874, ArTop10Accuracy=0.7629, over 13785.00 frames. ], tot_loss[loss=2.872, ArTop10Accuracy=0.757, over 7763.58 frames. ], batch size: 34, lr: 1.46e-02
2024-08-06 10:18:37,897 INFO [trainer.py:765] (4/8) Epoch 8, batch 300, train_loss[loss=2.891, ArTop10Accuracy=0.7523, over 14205.00 frames. ], tot_loss[loss=2.865, ArTop10Accuracy=0.7584, over 9375.13 frames. ], batch size: 44, lr: 1.46e-02
2024-08-06 10:20:06,341 INFO [trainer.py:765] (4/8) Epoch 8, batch 400, train_loss[loss=2.892, ArTop10Accuracy=0.751, over 10953.00 frames. ], tot_loss[loss=2.865, ArTop10Accuracy=0.7583, over 10289.35 frames. ], batch size: 15, lr: 1.45e-02
2024-08-06 10:21:32,410 INFO [trainer.py:765] (4/8) Epoch 8, batch 500, train_loss[loss=2.888, ArTop10Accuracy=0.7557, over 12642.00 frames. ], tot_loss[loss=2.859, ArTop10Accuracy=0.7591, over 10849.37 frames. ], batch size: 23, lr: 1.45e-02
2024-08-06 10:23:00,973 INFO [trainer.py:765] (4/8) Epoch 8, batch 600, train_loss[loss=2.915, ArTop10Accuracy=0.7512, over 11388.00 frames. ], tot_loss[loss=2.862, ArTop10Accuracy=0.7587, over 11353.14 frames. ], batch size: 18, lr: 1.44e-02
2024-08-06 10:24:37,787 INFO [trainer.py:765] (4/8) Epoch 8, batch 700, train_loss[loss=2.855, ArTop10Accuracy=0.7624, over 10257.00 frames. ], tot_loss[loss=2.866, ArTop10Accuracy=0.7579, over 11516.65 frames. ], batch size: 12, lr: 1.43e-02
2024-08-06 10:25:56,086 INFO [trainer.py:765] (4/8) Epoch 8, batch 800, train_loss[loss=2.831, ArTop10Accuracy=0.7627, over 10239.00 frames. ], tot_loss[loss=2.873, ArTop10Accuracy=0.7568, over 11657.44 frames. ], batch size: 12, lr: 1.43e-02
2024-08-06 10:27:12,244 INFO [trainer.py:765] (4/8) Epoch 8, batch 900, train_loss[loss=2.981, ArTop10Accuracy=0.7387, over 13305.00 frames. ], tot_loss[loss=2.865, ArTop10Accuracy=0.7582, over 11699.99 frames. ], batch size: 28, lr: 1.42e-02
2024-08-06 10:28:25,262 INFO [trainer.py:765] (4/8) Epoch 8, batch 1000, train_loss[loss=2.895, ArTop10Accuracy=0.7544, over 13005.00 frames. ], tot_loss[loss=2.871, ArTop10Accuracy=0.7573, over 11892.93 frames. ], batch size: 27, lr: 1.42e-02
2024-08-06 10:29:07,154 INFO [trainer.py:803] (4/8) Computing validation loss
2024-08-06 10:29:16,831 INFO [trainer.py:811] (4/8) Epoch 8, validation: loss=2.858, ArTop10Accuracy=0.7594, over 1827537.00 frames. 
2024-08-06 10:29:16,831 INFO [trainer.py:814] (4/8) Maximum memory allocated so far is 32729MB
2024-08-06 10:29:17,490 INFO [optim.py:386] (4/8) 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] (4/8) Epoch 8, batch 1100, train_loss[loss=2.842, ArTop10Accuracy=0.762, over 13689.00 frames. ], tot_loss[loss=2.873, ArTop10Accuracy=0.7568, over 11939.37 frames. ], batch size: 34, lr: 1.41e-02
2024-08-06 10:31:05,947 INFO [trainer.py:765] (4/8) Epoch 8, batch 1200, train_loss[loss=2.955, ArTop10Accuracy=0.743, over 12402.00 frames. ], tot_loss[loss=2.875, ArTop10Accuracy=0.7565, over 11857.03 frames. ], batch size: 101, lr: 1.40e-02
2024-08-06 10:32:05,791 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 10:34:01,255 INFO [trainer.py:765] (4/8) Epoch 9, batch 100, train_loss[loss=2.904, ArTop10Accuracy=0.7568, over 14307.00 frames. ], tot_loss[loss=2.863, ArTop10Accuracy=0.7586, over 4737.05 frames. ], batch size: 62, lr: 1.32e-02
2024-08-06 10:35:31,771 INFO [trainer.py:765] (4/8) Epoch 9, batch 200, train_loss[loss=2.822, ArTop10Accuracy=0.7641, over 13818.00 frames. ], tot_loss[loss=2.855, ArTop10Accuracy=0.76, over 7743.59 frames. ], batch size: 35, lr: 1.32e-02
2024-08-06 10:36:57,926 INFO [trainer.py:765] (4/8) Epoch 9, batch 300, train_loss[loss=2.909, ArTop10Accuracy=0.7482, over 13983.00 frames. ], tot_loss[loss=2.849, ArTop10Accuracy=0.7611, over 9372.82 frames. ], batch size: 44, lr: 1.31e-02
2024-08-06 10:38:32,696 INFO [trainer.py:765] (4/8) Epoch 9, batch 400, train_loss[loss=2.76, ArTop10Accuracy=0.7829, over 10272.00 frames. ], tot_loss[loss=2.849, ArTop10Accuracy=0.7612, over 10289.62 frames. ], batch size: 14, lr: 1.31e-02
2024-08-06 10:39:59,255 INFO [trainer.py:765] (4/8) Epoch 9, batch 500, train_loss[loss=2.807, ArTop10Accuracy=0.7688, over 12525.00 frames. ], tot_loss[loss=2.843, ArTop10Accuracy=0.7624, over 10855.66 frames. ], batch size: 23, lr: 1.30e-02
2024-08-06 10:41:29,689 INFO [trainer.py:765] (4/8) Epoch 9, batch 600, train_loss[loss=2.761, ArTop10Accuracy=0.7807, over 11481.00 frames. ], tot_loss[loss=2.846, ArTop10Accuracy=0.7619, over 11380.55 frames. ], batch size: 18, lr: 1.30e-02
2024-08-06 10:42:58,439 INFO [trainer.py:765] (4/8) Epoch 9, batch 700, train_loss[loss=2.828, ArTop10Accuracy=0.7617, over 10086.00 frames. ], tot_loss[loss=2.849, ArTop10Accuracy=0.7613, over 11524.13 frames. ], batch size: 12, lr: 1.29e-02
2024-08-06 10:44:02,952 INFO [optim.py:386] (4/8) 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 10:44:19,668 INFO [trainer.py:765] (4/8) Epoch 9, batch 800, train_loss[loss=2.768, ArTop10Accuracy=0.7773, over 10254.00 frames. ], tot_loss[loss=2.852, ArTop10Accuracy=0.7609, over 11649.42 frames. ], batch size: 12, lr: 1.29e-02
2024-08-06 10:45:35,718 INFO [trainer.py:765] (4/8) Epoch 9, batch 900, train_loss[loss=2.88, ArTop10Accuracy=0.753, over 13434.00 frames. ], tot_loss[loss=2.847, ArTop10Accuracy=0.7618, over 11670.68 frames. ], batch size: 28, lr: 1.28e-02
2024-08-06 10:46:51,270 INFO [trainer.py:765] (4/8) Epoch 9, batch 1000, train_loss[loss=2.869, ArTop10Accuracy=0.7541, over 12966.00 frames. ], tot_loss[loss=2.85, ArTop10Accuracy=0.761, over 11876.51 frames. ], batch size: 27, lr: 1.28e-02
2024-08-06 10:48:06,246 INFO [trainer.py:765] (4/8) Epoch 9, batch 1100, train_loss[loss=2.955, ArTop10Accuracy=0.7404, over 13590.00 frames. ], tot_loss[loss=2.856, ArTop10Accuracy=0.7598, over 11951.07 frames. ], batch size: 34, lr: 1.28e-02
2024-08-06 10:49:21,052 INFO [trainer.py:765] (4/8) Epoch 9, batch 1200, train_loss[loss=2.974, ArTop10Accuracy=0.7371, over 12891.00 frames. ], tot_loss[loss=2.854, ArTop10Accuracy=0.7605, over 11860.30 frames. ], batch size: 101, lr: 1.27e-02
2024-08-06 10:50:22,648 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 10:52:12,326 INFO [trainer.py:765] (4/8) Epoch 10, batch 100, train_loss[loss=2.903, ArTop10Accuracy=0.7494, over 14361.00 frames. ], tot_loss[loss=2.84, ArTop10Accuracy=0.7629, over 4760.61 frames. ], batch size: 62, lr: 1.20e-02
2024-08-06 10:53:44,585 INFO [trainer.py:765] (4/8) Epoch 10, batch 200, train_loss[loss=2.808, ArTop10Accuracy=0.7728, over 13860.00 frames. ], tot_loss[loss=2.832, ArTop10Accuracy=0.7645, over 7751.90 frames. ], batch size: 34, lr: 1.20e-02
2024-08-06 10:55:08,089 INFO [trainer.py:765] (4/8) Epoch 10, batch 300, train_loss[loss=2.899, ArTop10Accuracy=0.7537, over 14238.00 frames. ], tot_loss[loss=2.829, ArTop10Accuracy=0.765, over 9382.80 frames. ], batch size: 44, lr: 1.19e-02
2024-08-06 10:56:41,176 INFO [trainer.py:765] (4/8) Epoch 10, batch 400, train_loss[loss=2.607, ArTop10Accuracy=0.8052, over 10920.00 frames. ], tot_loss[loss=2.825, ArTop10Accuracy=0.7657, over 10285.01 frames. ], batch size: 15, lr: 1.19e-02
2024-08-06 10:58:04,937 INFO [trainer.py:803] (4/8) Computing validation loss
2024-08-06 10:58:14,559 INFO [trainer.py:811] (4/8) Epoch 10, validation: loss=2.842, ArTop10Accuracy=0.7624, over 1827537.00 frames. 
2024-08-06 10:58:14,560 INFO [trainer.py:814] (4/8) Maximum memory allocated so far is 32729MB
2024-08-06 10:58:15,573 INFO [optim.py:386] (4/8) 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 10:58:15,577 INFO [trainer.py:765] (4/8) Epoch 10, batch 500, train_loss[loss=2.741, ArTop10Accuracy=0.7833, over 12168.00 frames. ], tot_loss[loss=2.822, ArTop10Accuracy=0.7663, over 10832.02 frames. ], batch size: 22, lr: 1.19e-02
2024-08-06 10:59:42,814 INFO [trainer.py:765] (4/8) Epoch 10, batch 600, train_loss[loss=2.833, ArTop10Accuracy=0.7675, over 11478.00 frames. ], tot_loss[loss=2.822, ArTop10Accuracy=0.7663, over 11348.40 frames. ], batch size: 18, lr: 1.18e-02
2024-08-06 11:01:18,107 INFO [trainer.py:765] (4/8) Epoch 10, batch 700, train_loss[loss=2.833, ArTop10Accuracy=0.77, over 10155.00 frames. ], tot_loss[loss=2.831, ArTop10Accuracy=0.7646, over 11499.12 frames. ], batch size: 12, lr: 1.18e-02
2024-08-06 11:02:36,917 INFO [trainer.py:765] (4/8) Epoch 10, batch 800, train_loss[loss=2.736, ArTop10Accuracy=0.7802, over 9588.00 frames. ], tot_loss[loss=2.834, ArTop10Accuracy=0.764, over 11598.00 frames. ], batch size: 11, lr: 1.17e-02
2024-08-06 11:03:51,211 INFO [trainer.py:765] (4/8) Epoch 10, batch 900, train_loss[loss=2.81, ArTop10Accuracy=0.7674, over 12879.00 frames. ], tot_loss[loss=2.829, ArTop10Accuracy=0.7651, over 11668.20 frames. ], batch size: 27, lr: 1.17e-02
2024-08-06 11:05:06,351 INFO [trainer.py:765] (4/8) Epoch 10, batch 1000, train_loss[loss=2.774, ArTop10Accuracy=0.7766, over 13230.00 frames. ], tot_loss[loss=2.832, ArTop10Accuracy=0.7643, over 11870.10 frames. ], batch size: 28, lr: 1.17e-02
2024-08-06 11:06:21,722 INFO [trainer.py:765] (4/8) Epoch 10, batch 1100, train_loss[loss=2.834, ArTop10Accuracy=0.7654, over 14001.00 frames. ], tot_loss[loss=2.837, ArTop10Accuracy=0.7635, over 11949.67 frames. ], batch size: 34, lr: 1.16e-02
2024-08-06 11:07:34,771 INFO [trainer.py:765] (4/8) Epoch 10, batch 1200, train_loss[loss=2.926, ArTop10Accuracy=0.7422, over 12183.00 frames. ], tot_loss[loss=2.839, ArTop10Accuracy=0.7631, over 11860.35 frames. ], batch size: 101, lr: 1.16e-02
2024-08-06 11:08:33,545 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 11:10:29,955 INFO [trainer.py:765] (4/8) Epoch 11, batch 100, train_loss[loss=2.894, ArTop10Accuracy=0.7514, over 14163.00 frames. ], tot_loss[loss=2.822, ArTop10Accuracy=0.7656, over 4760.24 frames. ], batch size: 62, lr: 1.10e-02
2024-08-06 11:12:04,675 INFO [trainer.py:765] (4/8) Epoch 11, batch 200, train_loss[loss=2.819, ArTop10Accuracy=0.7616, over 13581.00 frames. ], tot_loss[loss=2.816, ArTop10Accuracy=0.7671, over 7747.57 frames. ], batch size: 34, lr: 1.10e-02
2024-08-06 11:12:22,826 INFO [optim.py:386] (4/8) 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 11:13:31,548 INFO [trainer.py:765] (4/8) Epoch 11, batch 300, train_loss[loss=2.827, ArTop10Accuracy=0.7685, over 14136.00 frames. ], tot_loss[loss=2.805, ArTop10Accuracy=0.7695, over 9352.68 frames. ], batch size: 44, lr: 1.09e-02
2024-08-06 11:15:03,269 INFO [trainer.py:765] (4/8) Epoch 11, batch 400, train_loss[loss=2.65, ArTop10Accuracy=0.7958, over 10311.00 frames. ], tot_loss[loss=2.805, ArTop10Accuracy=0.7695, over 10269.57 frames. ], batch size: 14, lr: 1.09e-02
2024-08-06 11:16:29,637 INFO [trainer.py:765] (4/8) Epoch 11, batch 500, train_loss[loss=2.803, ArTop10Accuracy=0.7683, over 12186.00 frames. ], tot_loss[loss=2.799, ArTop10Accuracy=0.7709, over 10871.11 frames. ], batch size: 22, lr: 1.09e-02
2024-08-06 11:18:00,517 INFO [trainer.py:765] (4/8) Epoch 11, batch 600, train_loss[loss=2.703, ArTop10Accuracy=0.7925, over 11367.00 frames. ], tot_loss[loss=2.802, ArTop10Accuracy=0.7702, over 11379.50 frames. ], batch size: 18, lr: 1.08e-02
2024-08-06 11:19:34,514 INFO [trainer.py:765] (4/8) Epoch 11, batch 700, train_loss[loss=2.706, ArTop10Accuracy=0.7954, over 10206.00 frames. ], tot_loss[loss=2.805, ArTop10Accuracy=0.7696, over 11531.85 frames. ], batch size: 12, lr: 1.08e-02
2024-08-06 11:20:55,484 INFO [trainer.py:765] (4/8) Epoch 11, batch 800, train_loss[loss=2.785, ArTop10Accuracy=0.7746, over 10131.00 frames. ], tot_loss[loss=2.812, ArTop10Accuracy=0.7683, over 11652.45 frames. ], batch size: 12, lr: 1.07e-02
2024-08-06 11:22:13,705 INFO [trainer.py:765] (4/8) Epoch 11, batch 900, train_loss[loss=2.852, ArTop10Accuracy=0.7595, over 12939.00 frames. ], tot_loss[loss=2.808, ArTop10Accuracy=0.7692, over 11699.34 frames. ], batch size: 27, lr: 1.07e-02
2024-08-06 11:23:31,799 INFO [trainer.py:765] (4/8) Epoch 11, batch 1000, train_loss[loss=2.784, ArTop10Accuracy=0.776, over 12765.00 frames. ], tot_loss[loss=2.811, ArTop10Accuracy=0.7685, over 11909.07 frames. ], batch size: 27, lr: 1.07e-02
2024-08-06 11:24:46,902 INFO [trainer.py:765] (4/8) Epoch 11, batch 1100, train_loss[loss=2.783, ArTop10Accuracy=0.7739, over 13785.00 frames. ], tot_loss[loss=2.82, ArTop10Accuracy=0.7666, over 11994.73 frames. ], batch size: 34, lr: 1.06e-02
2024-08-06 11:26:00,733 INFO [trainer.py:765] (4/8) Epoch 11, batch 1200, train_loss[loss=2.906, ArTop10Accuracy=0.7499, over 12528.00 frames. ], tot_loss[loss=2.821, ArTop10Accuracy=0.7665, over 11900.31 frames. ], batch size: 101, lr: 1.06e-02
2024-08-06 11:26:15,847 INFO [trainer.py:803] (4/8) Computing validation loss
2024-08-06 11:26:25,556 INFO [trainer.py:811] (4/8) Epoch 11, validation: loss=2.831, ArTop10Accuracy=0.7643, over 1827537.00 frames. 
2024-08-06 11:26:25,557 INFO [trainer.py:814] (4/8) Maximum memory allocated so far is 32729MB
2024-08-06 11:26:26,185 INFO [optim.py:386] (4/8) 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 11:27:09,520 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 11:29:03,450 INFO [trainer.py:765] (4/8) Epoch 12, batch 100, train_loss[loss=2.851, ArTop10Accuracy=0.7621, over 14574.00 frames. ], tot_loss[loss=2.803, ArTop10Accuracy=0.7693, over 4761.92 frames. ], batch size: 62, lr: 1.01e-02
2024-08-06 11:30:30,674 INFO [trainer.py:765] (4/8) Epoch 12, batch 200, train_loss[loss=2.84, ArTop10Accuracy=0.7634, over 13653.00 frames. ], tot_loss[loss=2.801, ArTop10Accuracy=0.7697, over 7757.17 frames. ], batch size: 34, lr: 1.01e-02
2024-08-06 11:31:57,655 INFO [trainer.py:765] (4/8) Epoch 12, batch 300, train_loss[loss=2.84, ArTop10Accuracy=0.7657, over 14268.00 frames. ], tot_loss[loss=2.795, ArTop10Accuracy=0.7713, over 9378.27 frames. ], batch size: 44, lr: 1.01e-02
2024-08-06 11:33:30,739 INFO [trainer.py:765] (4/8) Epoch 12, batch 400, train_loss[loss=2.648, ArTop10Accuracy=0.7979, over 10299.00 frames. ], tot_loss[loss=2.793, ArTop10Accuracy=0.7716, over 10283.00 frames. ], batch size: 14, lr: 1.00e-02
2024-08-06 11:34:55,733 INFO [trainer.py:765] (4/8) Epoch 12, batch 500, train_loss[loss=2.764, ArTop10Accuracy=0.7742, over 12129.00 frames. ], tot_loss[loss=2.79, ArTop10Accuracy=0.7722, over 10856.75 frames. ], batch size: 22, lr: 1.00e-02
2024-08-06 11:36:29,363 INFO [trainer.py:765] (4/8) Epoch 12, batch 600, train_loss[loss=2.737, ArTop10Accuracy=0.7859, over 11379.00 frames. ], tot_loss[loss=2.792, ArTop10Accuracy=0.7718, over 11376.60 frames. ], batch size: 18, lr: 9.97e-03
2024-08-06 11:38:00,343 INFO [trainer.py:765] (4/8) Epoch 12, batch 700, train_loss[loss=2.838, ArTop10Accuracy=0.7632, over 10191.00 frames. ], tot_loss[loss=2.796, ArTop10Accuracy=0.771, over 11525.72 frames. ], batch size: 12, lr: 9.93e-03
2024-08-06 11:39:23,610 INFO [trainer.py:765] (4/8) Epoch 12, batch 800, train_loss[loss=2.668, ArTop10Accuracy=0.7935, over 10128.00 frames. ], tot_loss[loss=2.799, ArTop10Accuracy=0.7706, over 11638.44 frames. ], batch size: 12, lr: 9.90e-03
2024-08-06 11:40:39,889 INFO [trainer.py:765] (4/8) Epoch 12, batch 900, train_loss[loss=2.768, ArTop10Accuracy=0.7778, over 12996.00 frames. ], tot_loss[loss=2.794, ArTop10Accuracy=0.7715, over 11692.40 frames. ], batch size: 27, lr: 9.87e-03
2024-08-06 11:41:13,995 INFO [optim.py:386] (4/8) 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 11:41:56,188 INFO [trainer.py:765] (4/8) Epoch 12, batch 1000, train_loss[loss=2.773, ArTop10Accuracy=0.7733, over 12681.00 frames. ], tot_loss[loss=2.797, ArTop10Accuracy=0.7706, over 11884.29 frames. ], batch size: 27, lr: 9.85e-03
2024-08-06 11:43:14,321 INFO [trainer.py:765] (4/8) Epoch 12, batch 1100, train_loss[loss=2.818, ArTop10Accuracy=0.7713, over 13422.00 frames. ], tot_loss[loss=2.804, ArTop10Accuracy=0.7694, over 11954.58 frames. ], batch size: 34, lr: 9.82e-03
2024-08-06 11:44:26,156 INFO [trainer.py:765] (4/8) Epoch 12, batch 1200, train_loss[loss=2.938, ArTop10Accuracy=0.7448, over 12807.00 frames. ], tot_loss[loss=2.805, ArTop10Accuracy=0.7695, over 11862.54 frames. ], batch size: 101, lr: 9.79e-03
2024-08-06 11:45:26,431 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 11:47:26,599 INFO [trainer.py:765] (4/8) Epoch 13, batch 100, train_loss[loss=2.825, ArTop10Accuracy=0.766, over 14238.00 frames. ], tot_loss[loss=2.792, ArTop10Accuracy=0.7713, over 4764.73 frames. ], batch size: 62, lr: 9.37e-03
2024-08-06 11:48:54,778 INFO [trainer.py:765] (4/8) Epoch 13, batch 200, train_loss[loss=2.834, ArTop10Accuracy=0.7646, over 13965.00 frames. ], tot_loss[loss=2.783, ArTop10Accuracy=0.773, over 7763.78 frames. ], batch size: 35, lr: 9.34e-03
2024-08-06 11:50:20,514 INFO [trainer.py:765] (4/8) Epoch 13, batch 300, train_loss[loss=2.807, ArTop10Accuracy=0.7683, over 14352.00 frames. ], tot_loss[loss=2.779, ArTop10Accuracy=0.7743, over 9392.08 frames. ], batch size: 44, lr: 9.31e-03
2024-08-06 11:51:48,764 INFO [trainer.py:765] (4/8) Epoch 13, batch 400, train_loss[loss=2.714, ArTop10Accuracy=0.785, over 10140.00 frames. ], tot_loss[loss=2.777, ArTop10Accuracy=0.7749, over 10285.29 frames. ], batch size: 14, lr: 9.28e-03
2024-08-06 11:53:13,406 INFO [trainer.py:765] (4/8) Epoch 13, batch 500, train_loss[loss=2.727, ArTop10Accuracy=0.7851, over 12174.00 frames. ], tot_loss[loss=2.769, ArTop10Accuracy=0.7765, over 10845.60 frames. ], batch size: 22, lr: 9.26e-03
2024-08-06 11:54:52,222 INFO [trainer.py:765] (4/8) Epoch 13, batch 600, train_loss[loss=2.715, ArTop10Accuracy=0.7804, over 11475.00 frames. ], tot_loss[loss=2.776, ArTop10Accuracy=0.775, over 11351.00 frames. ], batch size: 18, lr: 9.23e-03
2024-08-06 11:55:47,080 INFO [trainer.py:803] (4/8) Computing validation loss
2024-08-06 11:55:56,835 INFO [trainer.py:811] (4/8) Epoch 13, validation: loss=2.824, ArTop10Accuracy=0.7662, over 1827537.00 frames. 
2024-08-06 11:55:56,835 INFO [trainer.py:814] (4/8) Maximum memory allocated so far is 32729MB
2024-08-06 11:55:57,711 INFO [optim.py:386] (4/8) 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 11:56:28,464 INFO [trainer.py:765] (4/8) Epoch 13, batch 700, train_loss[loss=2.75, ArTop10Accuracy=0.7831, over 10083.00 frames. ], tot_loss[loss=2.777, ArTop10Accuracy=0.7747, over 11501.17 frames. ], batch size: 12, lr: 9.20e-03
2024-08-06 11:57:46,682 INFO [trainer.py:765] (4/8) Epoch 13, batch 800, train_loss[loss=2.675, ArTop10Accuracy=0.7886, over 10248.00 frames. ], tot_loss[loss=2.779, ArTop10Accuracy=0.7744, over 11619.44 frames. ], batch size: 12, lr: 9.18e-03
2024-08-06 11:59:03,286 INFO [trainer.py:765] (4/8) Epoch 13, batch 900, train_loss[loss=2.771, ArTop10Accuracy=0.7767, over 12915.00 frames. ], tot_loss[loss=2.775, ArTop10Accuracy=0.7752, over 11675.58 frames. ], batch size: 27, lr: 9.15e-03
2024-08-06 12:00:19,173 INFO [trainer.py:765] (4/8) Epoch 13, batch 1000, train_loss[loss=2.828, ArTop10Accuracy=0.7686, over 12804.00 frames. ], tot_loss[loss=2.785, ArTop10Accuracy=0.7734, over 11872.36 frames. ], batch size: 27, lr: 9.13e-03
2024-08-06 12:01:34,880 INFO [trainer.py:765] (4/8) Epoch 13, batch 1100, train_loss[loss=2.804, ArTop10Accuracy=0.7651, over 13485.00 frames. ], tot_loss[loss=2.79, ArTop10Accuracy=0.7723, over 11951.26 frames. ], batch size: 34, lr: 9.10e-03
2024-08-06 12:02:48,662 INFO [trainer.py:765] (4/8) Epoch 13, batch 1200, train_loss[loss=2.902, ArTop10Accuracy=0.7484, over 12114.00 frames. ], tot_loss[loss=2.79, ArTop10Accuracy=0.7723, over 11865.52 frames. ], batch size: 101, lr: 9.08e-03
2024-08-06 12:03:48,339 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 12:05:45,333 INFO [trainer.py:765] (4/8) Epoch 14, batch 100, train_loss[loss=2.835, ArTop10Accuracy=0.762, over 14472.00 frames. ], tot_loss[loss=2.776, ArTop10Accuracy=0.7746, over 4782.62 frames. ], batch size: 62, lr: 8.71e-03
2024-08-06 12:07:16,602 INFO [trainer.py:765] (4/8) Epoch 14, batch 200, train_loss[loss=2.814, ArTop10Accuracy=0.7662, over 13683.00 frames. ], tot_loss[loss=2.773, ArTop10Accuracy=0.7753, over 7786.17 frames. ], batch size: 34, lr: 8.69e-03
2024-08-06 12:08:44,310 INFO [trainer.py:765] (4/8) Epoch 14, batch 300, train_loss[loss=2.756, ArTop10Accuracy=0.7761, over 14625.00 frames. ], tot_loss[loss=2.766, ArTop10Accuracy=0.7768, over 9408.24 frames. ], batch size: 45, lr: 8.66e-03
2024-08-06 12:10:01,130 INFO [optim.py:386] (4/8) 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 12:10:10,225 INFO [trainer.py:765] (4/8) Epoch 14, batch 400, train_loss[loss=2.663, ArTop10Accuracy=0.7999, over 10509.00 frames. ], tot_loss[loss=2.765, ArTop10Accuracy=0.7769, over 10317.67 frames. ], batch size: 14, lr: 8.64e-03
2024-08-06 12:11:36,149 INFO [trainer.py:765] (4/8) Epoch 14, batch 500, train_loss[loss=2.836, ArTop10Accuracy=0.7666, over 12150.00 frames. ], tot_loss[loss=2.764, ArTop10Accuracy=0.7771, over 10867.61 frames. ], batch size: 22, lr: 8.62e-03
2024-08-06 12:13:05,992 INFO [trainer.py:765] (4/8) Epoch 14, batch 600, train_loss[loss=2.737, ArTop10Accuracy=0.7799, over 11397.00 frames. ], tot_loss[loss=2.766, ArTop10Accuracy=0.777, over 11388.73 frames. ], batch size: 18, lr: 8.59e-03
2024-08-06 12:14:38,553 INFO [trainer.py:765] (4/8) Epoch 14, batch 700, train_loss[loss=2.761, ArTop10Accuracy=0.7818, over 9318.00 frames. ], tot_loss[loss=2.771, ArTop10Accuracy=0.7759, over 11531.31 frames. ], batch size: 11, lr: 8.57e-03
2024-08-06 12:15:58,068 INFO [trainer.py:765] (4/8) Epoch 14, batch 800, train_loss[loss=2.574, ArTop10Accuracy=0.8119, over 10068.00 frames. ], tot_loss[loss=2.774, ArTop10Accuracy=0.7752, over 11637.37 frames. ], batch size: 12, lr: 8.55e-03
2024-08-06 12:17:12,864 INFO [trainer.py:765] (4/8) Epoch 14, batch 900, train_loss[loss=2.758, ArTop10Accuracy=0.7791, over 13287.00 frames. ], tot_loss[loss=2.767, ArTop10Accuracy=0.7766, over 11696.62 frames. ], batch size: 28, lr: 8.52e-03
2024-08-06 12:18:29,613 INFO [trainer.py:765] (4/8) Epoch 14, batch 1000, train_loss[loss=2.746, ArTop10Accuracy=0.7813, over 12909.00 frames. ], tot_loss[loss=2.771, ArTop10Accuracy=0.7758, over 11892.84 frames. ], batch size: 27, lr: 8.50e-03
2024-08-06 12:19:45,375 INFO [trainer.py:765] (4/8) Epoch 14, batch 1100, train_loss[loss=2.739, ArTop10Accuracy=0.7804, over 13647.00 frames. ], tot_loss[loss=2.775, ArTop10Accuracy=0.7752, over 11926.48 frames. ], batch size: 34, lr: 8.48e-03
2024-08-06 12:20:59,277 INFO [trainer.py:765] (4/8) Epoch 14, batch 1200, train_loss[loss=2.904, ArTop10Accuracy=0.7477, over 12768.00 frames. ], tot_loss[loss=2.774, ArTop10Accuracy=0.7754, over 11863.44 frames. ], batch size: 101, lr: 8.46e-03
2024-08-06 12:21:58,313 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 12:23:51,961 INFO [trainer.py:765] (4/8) Epoch 15, batch 100, train_loss[loss=2.757, ArTop10Accuracy=0.7769, over 14058.00 frames. ], tot_loss[loss=2.763, ArTop10Accuracy=0.7767, over 4741.67 frames. ], batch size: 62, lr: 8.14e-03
2024-08-06 12:24:00,599 INFO [trainer.py:803] (4/8) Computing validation loss
2024-08-06 12:24:10,290 INFO [trainer.py:811] (4/8) Epoch 15, validation: loss=2.819, ArTop10Accuracy=0.7675, over 1827537.00 frames. 
2024-08-06 12:24:10,291 INFO [trainer.py:814] (4/8) Maximum memory allocated so far is 32729MB
2024-08-06 12:24:11,094 INFO [optim.py:386] (4/8) 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 12:25:29,988 INFO [trainer.py:765] (4/8) Epoch 15, batch 200, train_loss[loss=2.727, ArTop10Accuracy=0.7861, over 13497.00 frames. ], tot_loss[loss=2.756, ArTop10Accuracy=0.7786, over 7747.87 frames. ], batch size: 34, lr: 8.12e-03
2024-08-06 12:26:58,694 INFO [trainer.py:765] (4/8) Epoch 15, batch 300, train_loss[loss=2.79, ArTop10Accuracy=0.7734, over 14127.00 frames. ], tot_loss[loss=2.755, ArTop10Accuracy=0.7789, over 9366.22 frames. ], batch size: 44, lr: 8.09e-03
2024-08-06 12:28:28,533 INFO [trainer.py:765] (4/8) Epoch 15, batch 400, train_loss[loss=2.737, ArTop10Accuracy=0.7757, over 10197.00 frames. ], tot_loss[loss=2.75, ArTop10Accuracy=0.7798, over 10275.21 frames. ], batch size: 14, lr: 8.07e-03
2024-08-06 12:29:54,032 INFO [trainer.py:765] (4/8) Epoch 15, batch 500, train_loss[loss=2.684, ArTop10Accuracy=0.7923, over 11910.00 frames. ], tot_loss[loss=2.745, ArTop10Accuracy=0.7806, over 10839.43 frames. ], batch size: 22, lr: 8.05e-03
2024-08-06 12:31:23,292 INFO [trainer.py:765] (4/8) Epoch 15, batch 600, train_loss[loss=2.711, ArTop10Accuracy=0.7829, over 11328.00 frames. ], tot_loss[loss=2.751, ArTop10Accuracy=0.7795, over 11360.31 frames. ], batch size: 18, lr: 8.03e-03
2024-08-06 12:32:53,175 INFO [trainer.py:765] (4/8) Epoch 15, batch 700, train_loss[loss=2.798, ArTop10Accuracy=0.7657, over 9354.00 frames. ], tot_loss[loss=2.755, ArTop10Accuracy=0.7787, over 11509.82 frames. ], batch size: 11, lr: 8.01e-03
2024-08-06 12:34:18,254 INFO [trainer.py:765] (4/8) Epoch 15, batch 800, train_loss[loss=2.694, ArTop10Accuracy=0.7858, over 9429.00 frames. ], tot_loss[loss=2.759, ArTop10Accuracy=0.7778, over 11617.64 frames. ], batch size: 11, lr: 7.99e-03
2024-08-06 12:35:34,726 INFO [trainer.py:765] (4/8) Epoch 15, batch 900, train_loss[loss=2.779, ArTop10Accuracy=0.7811, over 13008.00 frames. ], tot_loss[loss=2.754, ArTop10Accuracy=0.7789, over 11663.27 frames. ], batch size: 27, lr: 7.97e-03
2024-08-06 12:36:50,540 INFO [trainer.py:765] (4/8) Epoch 15, batch 1000, train_loss[loss=2.755, ArTop10Accuracy=0.7811, over 12786.00 frames. ], tot_loss[loss=2.758, ArTop10Accuracy=0.7782, over 11867.55 frames. ], batch size: 27, lr: 7.95e-03
2024-08-06 12:38:05,179 INFO [trainer.py:765] (4/8) Epoch 15, batch 1100, train_loss[loss=2.727, ArTop10Accuracy=0.781, over 13656.00 frames. ], tot_loss[loss=2.765, ArTop10Accuracy=0.7768, over 11960.61 frames. ], batch size: 34, lr: 7.93e-03
2024-08-06 12:38:12,841 INFO [optim.py:386] (4/8) 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 12:39:18,788 INFO [trainer.py:765] (4/8) Epoch 15, batch 1200, train_loss[loss=2.875, ArTop10Accuracy=0.7581, over 12324.00 frames. ], tot_loss[loss=2.767, ArTop10Accuracy=0.7764, over 11867.43 frames. ], batch size: 101, lr: 7.91e-03
2024-08-06 12:40:18,729 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 12:42:17,617 INFO [trainer.py:765] (4/8) Epoch 16, batch 100, train_loss[loss=2.72, ArTop10Accuracy=0.7843, over 14628.00 frames. ], tot_loss[loss=2.754, ArTop10Accuracy=0.7785, over 4756.83 frames. ], batch size: 63, lr: 7.63e-03
2024-08-06 12:43:49,563 INFO [trainer.py:765] (4/8) Epoch 16, batch 200, train_loss[loss=2.772, ArTop10Accuracy=0.7808, over 13596.00 frames. ], tot_loss[loss=2.748, ArTop10Accuracy=0.7796, over 7758.14 frames. ], batch size: 34, lr: 7.61e-03
2024-08-06 12:45:18,501 INFO [trainer.py:765] (4/8) Epoch 16, batch 300, train_loss[loss=2.786, ArTop10Accuracy=0.7746, over 14376.00 frames. ], tot_loss[loss=2.742, ArTop10Accuracy=0.7808, over 9384.75 frames. ], batch size: 44, lr: 7.59e-03
2024-08-06 12:46:45,207 INFO [trainer.py:765] (4/8) Epoch 16, batch 400, train_loss[loss=2.673, ArTop10Accuracy=0.7931, over 10800.00 frames. ], tot_loss[loss=2.738, ArTop10Accuracy=0.7816, over 10273.40 frames. ], batch size: 15, lr: 7.58e-03
2024-08-06 12:48:16,309 INFO [trainer.py:765] (4/8) Epoch 16, batch 500, train_loss[loss=2.668, ArTop10Accuracy=0.7959, over 12543.00 frames. ], tot_loss[loss=2.733, ArTop10Accuracy=0.7828, over 10823.89 frames. ], batch size: 23, lr: 7.56e-03
2024-08-06 12:49:46,641 INFO [trainer.py:765] (4/8) Epoch 16, batch 600, train_loss[loss=2.696, ArTop10Accuracy=0.7945, over 11832.00 frames. ], tot_loss[loss=2.739, ArTop10Accuracy=0.7818, over 11356.77 frames. ], batch size: 19, lr: 7.54e-03
2024-08-06 12:51:23,681 INFO [trainer.py:765] (4/8) Epoch 16, batch 700, train_loss[loss=2.622, ArTop10Accuracy=0.8066, over 9279.00 frames. ], tot_loss[loss=2.742, ArTop10Accuracy=0.7812, over 11496.79 frames. ], batch size: 11, lr: 7.52e-03
2024-08-06 12:52:43,500 INFO [trainer.py:765] (4/8) Epoch 16, batch 800, train_loss[loss=2.665, ArTop10Accuracy=0.7968, over 9534.00 frames. ], tot_loss[loss=2.748, ArTop10Accuracy=0.7802, over 11622.91 frames. ], batch size: 11, lr: 7.51e-03
2024-08-06 12:53:06,015 INFO [trainer.py:803] (4/8) Computing validation loss
2024-08-06 12:53:15,497 INFO [trainer.py:811] (4/8) Epoch 16, validation: loss=2.816, ArTop10Accuracy=0.7678, over 1827537.00 frames. 
2024-08-06 12:53:15,497 INFO [trainer.py:814] (4/8) Maximum memory allocated so far is 32729MB
2024-08-06 12:53:16,186 INFO [optim.py:386] (4/8) 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 12:54:06,480 INFO [trainer.py:765] (4/8) Epoch 16, batch 900, train_loss[loss=2.758, ArTop10Accuracy=0.7755, over 12792.00 frames. ], tot_loss[loss=2.743, ArTop10Accuracy=0.7814, over 11673.14 frames. ], batch size: 27, lr: 7.49e-03
2024-08-06 12:55:19,790 INFO [trainer.py:765] (4/8) Epoch 16, batch 1000, train_loss[loss=2.729, ArTop10Accuracy=0.7823, over 12786.00 frames. ], tot_loss[loss=2.748, ArTop10Accuracy=0.7803, over 11883.80 frames. ], batch size: 27, lr: 7.47e-03
2024-08-06 12:56:33,162 INFO [trainer.py:765] (4/8) Epoch 16, batch 1100, train_loss[loss=2.841, ArTop10Accuracy=0.761, over 13731.00 frames. ], tot_loss[loss=2.755, ArTop10Accuracy=0.7788, over 11965.31 frames. ], batch size: 34, lr: 7.45e-03
2024-08-06 12:57:48,484 INFO [trainer.py:765] (4/8) Epoch 16, batch 1200, train_loss[loss=2.889, ArTop10Accuracy=0.7509, over 13242.00 frames. ], tot_loss[loss=2.758, ArTop10Accuracy=0.7784, over 11864.74 frames. ], batch size: 101, lr: 7.44e-03
2024-08-06 12:58:48,452 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 13:00:47,899 INFO [trainer.py:765] (4/8) Epoch 17, batch 100, train_loss[loss=2.808, ArTop10Accuracy=0.7735, over 14139.00 frames. ], tot_loss[loss=2.737, ArTop10Accuracy=0.782, over 4762.26 frames. ], batch size: 62, lr: 7.18e-03
2024-08-06 13:02:19,301 INFO [trainer.py:765] (4/8) Epoch 17, batch 200, train_loss[loss=2.696, ArTop10Accuracy=0.7905, over 13575.00 frames. ], tot_loss[loss=2.731, ArTop10Accuracy=0.783, over 7754.67 frames. ], batch size: 34, lr: 7.17e-03
2024-08-06 13:03:45,516 INFO [trainer.py:765] (4/8) Epoch 17, batch 300, train_loss[loss=2.778, ArTop10Accuracy=0.774, over 14085.00 frames. ], tot_loss[loss=2.728, ArTop10Accuracy=0.7836, over 9361.00 frames. ], batch size: 44, lr: 7.15e-03
2024-08-06 13:05:21,759 INFO [trainer.py:765] (4/8) Epoch 17, batch 400, train_loss[loss=2.697, ArTop10Accuracy=0.7889, over 10224.00 frames. ], tot_loss[loss=2.729, ArTop10Accuracy=0.7835, over 10286.59 frames. ], batch size: 14, lr: 7.14e-03
2024-08-06 13:06:47,020 INFO [trainer.py:765] (4/8) Epoch 17, batch 500, train_loss[loss=2.703, ArTop10Accuracy=0.7954, over 12390.00 frames. ], tot_loss[loss=2.722, ArTop10Accuracy=0.7849, over 10860.98 frames. ], batch size: 23, lr: 7.12e-03
2024-08-06 13:07:39,878 INFO [optim.py:386] (4/8) 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 13:08:22,687 INFO [trainer.py:765] (4/8) Epoch 17, batch 600, train_loss[loss=2.644, ArTop10Accuracy=0.8019, over 11319.00 frames. ], tot_loss[loss=2.725, ArTop10Accuracy=0.7842, over 11399.75 frames. ], batch size: 18, lr: 7.10e-03
2024-08-06 13:09:54,835 INFO [trainer.py:765] (4/8) Epoch 17, batch 700, train_loss[loss=2.647, ArTop10Accuracy=0.7977, over 9441.00 frames. ], tot_loss[loss=2.732, ArTop10Accuracy=0.7829, over 11531.09 frames. ], batch size: 11, lr: 7.09e-03
2024-08-06 13:11:19,480 INFO [trainer.py:765] (4/8) Epoch 17, batch 800, train_loss[loss=2.671, ArTop10Accuracy=0.7933, over 9414.00 frames. ], tot_loss[loss=2.736, ArTop10Accuracy=0.7824, over 11649.00 frames. ], batch size: 11, lr: 7.07e-03
2024-08-06 13:12:35,669 INFO [trainer.py:765] (4/8) Epoch 17, batch 900, train_loss[loss=2.667, ArTop10Accuracy=0.7941, over 12930.00 frames. ], tot_loss[loss=2.731, ArTop10Accuracy=0.7833, over 11681.78 frames. ], batch size: 27, lr: 7.06e-03
2024-08-06 13:13:53,061 INFO [trainer.py:765] (4/8) Epoch 17, batch 1000, train_loss[loss=2.74, ArTop10Accuracy=0.7801, over 13290.00 frames. ], tot_loss[loss=2.738, ArTop10Accuracy=0.7819, over 11875.05 frames. ], batch size: 28, lr: 7.04e-03
2024-08-06 13:15:08,483 INFO [trainer.py:765] (4/8) Epoch 17, batch 1100, train_loss[loss=2.772, ArTop10Accuracy=0.7688, over 13890.00 frames. ], tot_loss[loss=2.746, ArTop10Accuracy=0.7805, over 11955.85 frames. ], batch size: 34, lr: 7.02e-03
2024-08-06 13:16:22,387 INFO [trainer.py:765] (4/8) Epoch 17, batch 1200, train_loss[loss=2.87, ArTop10Accuracy=0.7565, over 12078.00 frames. ], tot_loss[loss=2.745, ArTop10Accuracy=0.7806, over 11841.53 frames. ], batch size: 101, lr: 7.01e-03
2024-08-06 13:17:21,505 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 13:19:15,993 INFO [trainer.py:765] (4/8) Epoch 18, batch 100, train_loss[loss=2.768, ArTop10Accuracy=0.7747, over 14724.00 frames. ], tot_loss[loss=2.726, ArTop10Accuracy=0.7841, over 4762.63 frames. ], batch size: 62, lr: 6.78e-03
2024-08-06 13:20:46,601 INFO [trainer.py:765] (4/8) Epoch 18, batch 200, train_loss[loss=2.718, ArTop10Accuracy=0.7839, over 13710.00 frames. ], tot_loss[loss=2.72, ArTop10Accuracy=0.7852, over 7740.19 frames. ], batch size: 34, lr: 6.77e-03
2024-08-06 13:21:55,104 INFO [trainer.py:803] (4/8) Computing validation loss
2024-08-06 13:22:04,751 INFO [trainer.py:811] (4/8) Epoch 18, validation: loss=2.817, ArTop10Accuracy=0.768, over 1827537.00 frames. 
2024-08-06 13:22:04,752 INFO [trainer.py:814] (4/8) Maximum memory allocated so far is 32729MB
2024-08-06 13:22:05,473 INFO [optim.py:386] (4/8) 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 13:22:26,580 INFO [trainer.py:765] (4/8) Epoch 18, batch 300, train_loss[loss=2.816, ArTop10Accuracy=0.7642, over 14331.00 frames. ], tot_loss[loss=2.719, ArTop10Accuracy=0.7853, over 9360.96 frames. ], batch size: 45, lr: 6.76e-03
2024-08-06 13:23:57,929 INFO [trainer.py:765] (4/8) Epoch 18, batch 400, train_loss[loss=2.63, ArTop10Accuracy=0.8021, over 10269.00 frames. ], tot_loss[loss=2.719, ArTop10Accuracy=0.7853, over 10295.59 frames. ], batch size: 14, lr: 6.74e-03
2024-08-06 13:25:34,012 INFO [trainer.py:765] (4/8) Epoch 18, batch 500, train_loss[loss=2.756, ArTop10Accuracy=0.7784, over 12132.00 frames. ], tot_loss[loss=2.718, ArTop10Accuracy=0.7855, over 10847.92 frames. ], batch size: 22, lr: 6.73e-03
2024-08-06 13:27:00,633 INFO [trainer.py:765] (4/8) Epoch 18, batch 600, train_loss[loss=2.646, ArTop10Accuracy=0.8065, over 11325.00 frames. ], tot_loss[loss=2.719, ArTop10Accuracy=0.7854, over 11377.58 frames. ], batch size: 18, lr: 6.71e-03
2024-08-06 13:28:33,581 INFO [trainer.py:765] (4/8) Epoch 18, batch 700, train_loss[loss=2.732, ArTop10Accuracy=0.7826, over 10032.00 frames. ], tot_loss[loss=2.721, ArTop10Accuracy=0.785, over 11521.88 frames. ], batch size: 12, lr: 6.70e-03
2024-08-06 13:29:54,984 INFO [trainer.py:765] (4/8) Epoch 18, batch 800, train_loss[loss=2.64, ArTop10Accuracy=0.804, over 9444.00 frames. ], tot_loss[loss=2.725, ArTop10Accuracy=0.7844, over 11624.46 frames. ], batch size: 11, lr: 6.68e-03
2024-08-06 13:31:12,518 INFO [trainer.py:765] (4/8) Epoch 18, batch 900, train_loss[loss=2.733, ArTop10Accuracy=0.7867, over 13254.00 frames. ], tot_loss[loss=2.722, ArTop10Accuracy=0.7851, over 11690.93 frames. ], batch size: 28, lr: 6.67e-03
2024-08-06 13:32:26,550 INFO [trainer.py:765] (4/8) Epoch 18, batch 1000, train_loss[loss=2.754, ArTop10Accuracy=0.7792, over 12873.00 frames. ], tot_loss[loss=2.729, ArTop10Accuracy=0.7838, over 11892.74 frames. ], batch size: 27, lr: 6.66e-03
2024-08-06 13:33:41,496 INFO [trainer.py:765] (4/8) Epoch 18, batch 1100, train_loss[loss=2.731, ArTop10Accuracy=0.7878, over 13854.00 frames. ], tot_loss[loss=2.734, ArTop10Accuracy=0.7828, over 11966.56 frames. ], batch size: 34, lr: 6.64e-03
2024-08-06 13:34:54,673 INFO [trainer.py:765] (4/8) Epoch 18, batch 1200, train_loss[loss=2.876, ArTop10Accuracy=0.755, over 11688.00 frames. ], tot_loss[loss=2.733, ArTop10Accuracy=0.7828, over 11879.62 frames. ], batch size: 103, lr: 6.63e-03
2024-08-06 13:35:51,064 INFO [optim.py:386] (4/8) 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 13:35:54,218 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 13:37:48,623 INFO [trainer.py:765] (4/8) Epoch 19, batch 100, train_loss[loss=2.786, ArTop10Accuracy=0.773, over 14562.00 frames. ], tot_loss[loss=2.709, ArTop10Accuracy=0.7871, over 4763.34 frames. ], batch size: 62, lr: 6.43e-03
2024-08-06 13:39:23,256 INFO [trainer.py:765] (4/8) Epoch 19, batch 200, train_loss[loss=2.706, ArTop10Accuracy=0.782, over 13527.00 frames. ], tot_loss[loss=2.711, ArTop10Accuracy=0.7867, over 7744.85 frames. ], batch size: 34, lr: 6.41e-03
2024-08-06 13:40:48,358 INFO [trainer.py:765] (4/8) Epoch 19, batch 300, train_loss[loss=2.735, ArTop10Accuracy=0.7868, over 14472.00 frames. ], tot_loss[loss=2.71, ArTop10Accuracy=0.7871, over 9377.25 frames. ], batch size: 46, lr: 6.40e-03
2024-08-06 13:42:21,067 INFO [trainer.py:765] (4/8) Epoch 19, batch 400, train_loss[loss=2.586, ArTop10Accuracy=0.8117, over 10197.00 frames. ], tot_loss[loss=2.703, ArTop10Accuracy=0.7883, over 10290.26 frames. ], batch size: 14, lr: 6.39e-03
2024-08-06 13:43:44,954 INFO [trainer.py:765] (4/8) Epoch 19, batch 500, train_loss[loss=2.667, ArTop10Accuracy=0.7974, over 12102.00 frames. ], tot_loss[loss=2.697, ArTop10Accuracy=0.7896, over 10853.44 frames. ], batch size: 22, lr: 6.37e-03
2024-08-06 13:45:16,681 INFO [trainer.py:765] (4/8) Epoch 19, batch 600, train_loss[loss=2.625, ArTop10Accuracy=0.8068, over 11361.00 frames. ], tot_loss[loss=2.703, ArTop10Accuracy=0.7886, over 11367.34 frames. ], batch size: 18, lr: 6.36e-03
2024-08-06 13:46:48,324 INFO [trainer.py:765] (4/8) Epoch 19, batch 700, train_loss[loss=2.687, ArTop10Accuracy=0.7831, over 10386.00 frames. ], tot_loss[loss=2.713, ArTop10Accuracy=0.7867, over 11508.06 frames. ], batch size: 12, lr: 6.35e-03
2024-08-06 13:48:11,883 INFO [trainer.py:765] (4/8) Epoch 19, batch 800, train_loss[loss=2.696, ArTop10Accuracy=0.7907, over 10185.00 frames. ], tot_loss[loss=2.717, ArTop10Accuracy=0.7858, over 11635.75 frames. ], batch size: 12, lr: 6.34e-03
2024-08-06 13:49:27,258 INFO [trainer.py:765] (4/8) Epoch 19, batch 900, train_loss[loss=2.68, ArTop10Accuracy=0.7937, over 12957.00 frames. ], tot_loss[loss=2.711, ArTop10Accuracy=0.7868, over 11686.07 frames. ], batch size: 27, lr: 6.32e-03
2024-08-06 13:50:40,653 INFO [trainer.py:803] (4/8) Computing validation loss
2024-08-06 13:50:50,537 INFO [trainer.py:811] (4/8) Epoch 19, validation: loss=2.818, ArTop10Accuracy=0.7679, over 1827537.00 frames. 
2024-08-06 13:50:50,537 INFO [trainer.py:814] (4/8) Maximum memory allocated so far is 32729MB
2024-08-06 13:50:51,489 INFO [optim.py:386] (4/8) 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 13:50:52,915 INFO [trainer.py:765] (4/8) Epoch 19, batch 1000, train_loss[loss=2.761, ArTop10Accuracy=0.7747, over 12699.00 frames. ], tot_loss[loss=2.72, ArTop10Accuracy=0.7853, over 11884.10 frames. ], batch size: 27, lr: 6.31e-03
2024-08-06 13:52:08,265 INFO [trainer.py:765] (4/8) Epoch 19, batch 1100, train_loss[loss=2.701, ArTop10Accuracy=0.7904, over 13695.00 frames. ], tot_loss[loss=2.724, ArTop10Accuracy=0.7845, over 11953.71 frames. ], batch size: 34, lr: 6.30e-03
2024-08-06 13:53:22,313 INFO [trainer.py:765] (4/8) Epoch 19, batch 1200, train_loss[loss=2.831, ArTop10Accuracy=0.7577, over 12249.00 frames. ], tot_loss[loss=2.726, ArTop10Accuracy=0.7842, over 11861.23 frames. ], batch size: 101, lr: 6.28e-03
2024-08-06 13:54:21,708 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 13:56:12,907 INFO [trainer.py:765] (4/8) Epoch 20, batch 100, train_loss[loss=2.789, ArTop10Accuracy=0.7679, over 14760.00 frames. ], tot_loss[loss=2.713, ArTop10Accuracy=0.7857, over 4756.56 frames. ], batch size: 62, lr: 6.10e-03
2024-08-06 13:57:42,497 INFO [trainer.py:765] (4/8) Epoch 20, batch 200, train_loss[loss=2.639, ArTop10Accuracy=0.8007, over 13737.00 frames. ], tot_loss[loss=2.705, ArTop10Accuracy=0.7879, over 7746.44 frames. ], batch size: 34, lr: 6.09e-03
2024-08-06 13:59:15,430 INFO [trainer.py:765] (4/8) Epoch 20, batch 300, train_loss[loss=2.762, ArTop10Accuracy=0.7798, over 14253.00 frames. ], tot_loss[loss=2.699, ArTop10Accuracy=0.789, over 9366.73 frames. ], batch size: 45, lr: 6.08e-03
2024-08-06 14:00:44,356 INFO [trainer.py:765] (4/8) Epoch 20, batch 400, train_loss[loss=2.555, ArTop10Accuracy=0.8139, over 10905.00 frames. ], tot_loss[loss=2.696, ArTop10Accuracy=0.7895, over 10302.20 frames. ], batch size: 15, lr: 6.07e-03
2024-08-06 14:02:14,855 INFO [trainer.py:765] (4/8) Epoch 20, batch 500, train_loss[loss=2.66, ArTop10Accuracy=0.7958, over 12114.00 frames. ], tot_loss[loss=2.692, ArTop10Accuracy=0.7904, over 10858.12 frames. ], batch size: 22, lr: 6.06e-03
2024-08-06 14:03:40,856 INFO [trainer.py:765] (4/8) Epoch 20, batch 600, train_loss[loss=2.597, ArTop10Accuracy=0.8091, over 11571.00 frames. ], tot_loss[loss=2.695, ArTop10Accuracy=0.7899, over 11385.90 frames. ], batch size: 18, lr: 6.04e-03
2024-08-06 14:05:13,864 INFO [trainer.py:765] (4/8) Epoch 20, batch 700, train_loss[loss=2.717, ArTop10Accuracy=0.7839, over 9984.00 frames. ], tot_loss[loss=2.699, ArTop10Accuracy=0.7892, over 11521.50 frames. ], batch size: 12, lr: 6.03e-03
2024-08-06 14:05:30,791 INFO [optim.py:386] (4/8) 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 14:06:34,509 INFO [trainer.py:765] (4/8) Epoch 20, batch 800, train_loss[loss=2.721, ArTop10Accuracy=0.7837, over 10083.00 frames. ], tot_loss[loss=2.705, ArTop10Accuracy=0.7881, over 11637.46 frames. ], batch size: 12, lr: 6.02e-03
2024-08-06 14:07:50,944 INFO [trainer.py:765] (4/8) Epoch 20, batch 900, train_loss[loss=2.635, ArTop10Accuracy=0.8005, over 12861.00 frames. ], tot_loss[loss=2.704, ArTop10Accuracy=0.7881, over 11700.37 frames. ], batch size: 27, lr: 6.01e-03
2024-08-06 14:09:07,173 INFO [trainer.py:765] (4/8) Epoch 20, batch 1000, train_loss[loss=2.693, ArTop10Accuracy=0.7967, over 12675.00 frames. ], tot_loss[loss=2.708, ArTop10Accuracy=0.7876, over 11883.15 frames. ], batch size: 27, lr: 6.00e-03
2024-08-06 14:10:21,210 INFO [trainer.py:765] (4/8) Epoch 20, batch 1100, train_loss[loss=2.709, ArTop10Accuracy=0.7851, over 13629.00 frames. ], tot_loss[loss=2.714, ArTop10Accuracy=0.7864, over 11931.12 frames. ], batch size: 34, lr: 5.99e-03
2024-08-06 14:11:37,813 INFO [trainer.py:765] (4/8) Epoch 20, batch 1200, train_loss[loss=2.855, ArTop10Accuracy=0.7594, over 11973.00 frames. ], tot_loss[loss=2.714, ArTop10Accuracy=0.7863, over 11830.00 frames. ], batch size: 105, lr: 5.98e-03
2024-08-06 14:12:37,299 INFO [trainer.py:650] (4/8) Reaches end of dataloader.
2024-08-06 14:12:37,301 INFO [trainer.py:1069] (4/8) Done!