2024-08-06 14:23:41,727 INFO [trainer.py:870] (2/8) Training started
2024-08-06 14:23:41,728 INFO [trainer.py:889] (2/8) Device: cuda:2
2024-08-06 14:23:41,728 INFO [trainer.py:890] (2/8) {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 100, 'reset_interval': 200, 'valid_interval': 2000, 'env_info': {'k2-version': '1.24.3', 'k2-build-type': 'Release', 'k2-with-cuda': True, 'k2-git-sha1': '279b0c87015a615b81b147251814d737a548f397', 'k2-git-date': 'Wed May 24 22:24:09 2023', 'lhotse-version': '1.26.0', 'torch-version': '2.0.1+cu118', 'torch-cuda-available': True, 'torch-cuda-version': '11.8', 'python-version': '3.10', 'icefall-git-branch': None, 'icefall-git-sha1': None, 'icefall-git-date': None, 'icefall-path': '/workspace/icefall_llm', 'k2-path': '/usr/local/lib/python3.10/dist-packages/k2/__init__.py', 'lhotse-path': '/usr/local/lib/python3.10/dist-packages/lhotse/__init__.py', 'hostname': '6867463', 'IP address': '0.104.202.7'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 40, 'start_epoch': 100, 'start_batch': 0, 'exp_dir': PosixPath('exp/valle'), 'optimizer_name': 'ScaledAdam', 'scheduler_name': 'Eden', 'base_lr': 0.03, 'warmup_steps': 200, 'seed': 42, 'inf_check': False, 'save_every_n': 100000, 'keep_last_k': 20, 'average_period': 0, 'accumulate_grad_steps': 2, 'dtype': 'float32', 'filter_min_duration': 0.5, 'filter_max_duration': 14.0, 'train_stage': 2, 'visualize': False, 'oom_check': False, 'model_name': 'valle', 'decoder_dim': 1024, 'nhead': 16, 'num_decoder_layers': 12, 'scale_factor': 1.0, 'norm_first': True, 'add_prenet': False, 'prefix_mode': 1, 'share_embedding': True, 'prepend_bos': False, 'num_quantizers': 8, 'scaling_xformers': False, 'manifest_dir': PosixPath('data/tokenized'), 'max_duration': 160, 'bucketing_sampler': True, 'num_buckets': 6, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 0.1, 'on_the_fly_feats': False, 'shuffle': True, 'buffer_size': 40000, 'shuffle_buffer_size': 100000, 'drop_last': False, 'return_cuts': True, 'num_workers': 8, 'enable_spec_aug': False, 'spec_aug_time_warp_factor': 80, 'input_strategy': 'PrecomputedFeatures', 'dataset': 'libritts', 'text_tokens': 'data/tokenized/unique_text_tokens.k2symbols', 'sampling_rate': 24000}
2024-08-06 14:23:41,728 INFO [trainer.py:892] (2/8) About to create model
2024-08-06 14:23:42,446 INFO [trainer.py:899] (2/8) Number of model parameters: 367386628
2024-08-06 14:23:42,446 INFO [checkpoint.py:112] (2/8) Loading checkpoint from exp/valle/epoch-99.pt
2024-08-06 14:23:47,398 INFO [trainer.py:914] (2/8) Using DDP
2024-08-06 14:23:49,639 INFO [datamodule.py:427] (2/8) About to get train cuts
2024-08-06 14:23:49,641 INFO [datamodule.py:434] (2/8) About to get dev cuts
2024-08-06 14:23:49,642 INFO [datamodule.py:292] (2/8) Disable SpecAugment
2024-08-06 14:23:49,643 INFO [datamodule.py:294] (2/8) About to create train dataset
2024-08-06 14:23:49,643 INFO [datamodule.py:323] (2/8) Using DynamicBucketingSampler
2024-08-06 14:23:50,257 INFO [datamodule.py:344] (2/8) About to create train dataloader
2024-08-06 14:23:50,257 INFO [datamodule.py:367] (2/8) About to create dev dataset
2024-08-06 14:23:50,585 INFO [datamodule.py:388] (2/8) About to create dev dataloader
2024-08-06 14:24:38,249 INFO [trainer.py:765] (2/8) Epoch 1, batch 100, train_loss[loss=105.9, NarTop10Accuracy=0.02382, over 7296.00 frames. ], tot_loss[loss=73.84, NarTop10Accuracy=0.04677, over 2381.79 frames. ], batch size: 31, lr: 2.25e-02
2024-08-06 14:25:07,518 INFO [trainer.py:765] (2/8) Epoch 1, batch 200, train_loss[loss=129.7, NarTop10Accuracy=0.01297, over 6786.00 frames. ], tot_loss[loss=97.4, NarTop10Accuracy=0.04128, over 3860.02 frames. ], batch size: 17, lr: 3.00e-02
2024-08-06 14:25:37,111 INFO [trainer.py:765] (2/8) Epoch 1, batch 300, train_loss[loss=113.5, NarTop10Accuracy=0.02626, over 7110.00 frames. ], tot_loss[loss=85.22, NarTop10Accuracy=0.04226, over 4663.73 frames. ], batch size: 22, lr: 3.00e-02
2024-08-06 14:26:07,483 INFO [trainer.py:765] (2/8) Epoch 1, batch 400, train_loss[loss=48.85, NarTop10Accuracy=0.02065, over 5205.00 frames. ], tot_loss[loss=67.92, NarTop10Accuracy=0.04664, over 5094.86 frames. ], batch size: 7, lr: 3.00e-02
2024-08-06 14:26:35,358 INFO [trainer.py:765] (2/8) Epoch 1, batch 500, train_loss[loss=14.61, NarTop10Accuracy=0.02276, over 6099.00 frames. ], tot_loss[loss=49.19, NarTop10Accuracy=0.04923, over 5350.99 frames. ], batch size: 11, lr: 2.99e-02
2024-08-06 14:27:04,001 INFO [trainer.py:765] (2/8) Epoch 1, batch 600, train_loss[loss=6.125, NarTop10Accuracy=0.201, over 5574.00 frames. ], tot_loss[loss=33.5, NarTop10Accuracy=0.05448, over 5625.48 frames. ], batch size: 9, lr: 2.99e-02
2024-08-06 14:27:39,490 INFO [trainer.py:765] (2/8) Epoch 1, batch 700, train_loss[loss=6.785, NarTop10Accuracy=0.1159, over 5076.00 frames. ], tot_loss[loss=23.45, NarTop10Accuracy=0.0634, over 5696.43 frames. ], batch size: 6, lr: 2.99e-02
2024-08-06 14:28:08,831 INFO [trainer.py:765] (2/8) Epoch 1, batch 800, train_loss[loss=6.402, NarTop10Accuracy=0.132, over 4344.00 frames. ], tot_loss[loss=17.17, NarTop10Accuracy=0.0844, over 5771.42 frames. ], batch size: 5, lr: 2.98e-02
2024-08-06 14:28:36,757 INFO [trainer.py:765] (2/8) Epoch 1, batch 900, train_loss[loss=5.68, NarTop10Accuracy=0.1962, over 6396.00 frames. ], tot_loss[loss=12.8, NarTop10Accuracy=0.1132, over 5780.55 frames. ], batch size: 13, lr: 2.98e-02
2024-08-06 14:29:12,587 INFO [trainer.py:765] (2/8) Epoch 1, batch 1000, train_loss[loss=5.633, NarTop10Accuracy=0.2054, over 6135.00 frames. ], tot_loss[loss=10.11, NarTop10Accuracy=0.1352, over 5886.64 frames. ], batch size: 13, lr: 2.97e-02
2024-08-06 14:29:42,825 INFO [trainer.py:765] (2/8) Epoch 1, batch 1100, train_loss[loss=5.767, NarTop10Accuracy=0.1733, over 7020.00 frames. ], tot_loss[loss=8.415, NarTop10Accuracy=0.1539, over 5922.01 frames. ], batch size: 17, lr: 2.96e-02
2024-08-06 14:30:11,468 INFO [trainer.py:765] (2/8) Epoch 1, batch 1200, train_loss[loss=5.946, NarTop10Accuracy=0.168, over 7062.00 frames. ], tot_loss[loss=7.35, NarTop10Accuracy=0.1716, over 5913.77 frames. ], batch size: 31, lr: 2.96e-02
2024-08-06 14:30:48,748 INFO [trainer.py:765] (2/8) Epoch 1, batch 1300, train_loss[loss=5.254, NarTop10Accuracy=0.2807, over 5016.00 frames. ], tot_loss[loss=6.684, NarTop10Accuracy=0.1861, over 5981.32 frames. ], batch size: 6, lr: 2.95e-02
2024-08-06 14:31:18,144 INFO [trainer.py:765] (2/8) Epoch 1, batch 1400, train_loss[loss=5.694, NarTop10Accuracy=0.1826, over 6111.00 frames. ], tot_loss[loss=6.256, NarTop10Accuracy=0.1961, over 5997.68 frames. ], batch size: 11, lr: 2.94e-02
2024-08-06 14:31:46,027 INFO [trainer.py:765] (2/8) Epoch 1, batch 1500, train_loss[loss=5.798, NarTop10Accuracy=0.1867, over 6036.00 frames. ], tot_loss[loss=5.968, NarTop10Accuracy=0.2095, over 5966.11 frames. ], batch size: 50, lr: 2.94e-02
2024-08-06 14:32:13,692 INFO [trainer.py:765] (2/8) Epoch 1, batch 1600, train_loss[loss=5.579, NarTop10Accuracy=0.2149, over 7053.00 frames. ], tot_loss[loss=5.784, NarTop10Accuracy=0.219, over 5944.76 frames. ], batch size: 22, lr: 2.93e-02
2024-08-06 14:32:40,199 INFO [trainer.py:765] (2/8) Epoch 1, batch 1700, train_loss[loss=5.472, NarTop10Accuracy=0.2443, over 6723.00 frames. ], tot_loss[loss=5.664, NarTop10Accuracy=0.2258, over 5918.97 frames. ], batch size: 14, lr: 2.92e-02
2024-08-06 14:33:06,500 INFO [trainer.py:765] (2/8) Epoch 1, batch 1800, train_loss[loss=5.539, NarTop10Accuracy=0.2244, over 7185.00 frames. ], tot_loss[loss=5.576, NarTop10Accuracy=0.2327, over 5974.83 frames. ], batch size: 22, lr: 2.91e-02
2024-08-06 14:33:32,625 INFO [trainer.py:765] (2/8) Epoch 1, batch 1900, train_loss[loss=5.709, NarTop10Accuracy=0.1936, over 6222.00 frames. ], tot_loss[loss=5.503, NarTop10Accuracy=0.2419, over 6025.19 frames. ], batch size: 55, lr: 2.90e-02
2024-08-06 14:33:58,015 INFO [trainer.py:765] (2/8) Epoch 1, batch 2000, train_loss[loss=5.51, NarTop10Accuracy=0.2418, over 6603.00 frames. ], tot_loss[loss=5.442, NarTop10Accuracy=0.2507, over 6000.52 frames. ], batch size: 52, lr: 2.89e-02
2024-08-06 14:33:58,016 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 14:34:06,103 INFO [trainer.py:811] (2/8) Epoch 1, validation: loss=5.397, NarTop10Accuracy=0.2581, over 1905321.00 frames. 
2024-08-06 14:34:06,104 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 26698MB
2024-08-06 14:34:06,612 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 4.749e+01 2.278e+02 7.300e+02 1.664e+04 7.177e+05, threshold=1.460e+03, percent-clipped=0.0
2024-08-06 14:34:32,062 INFO [trainer.py:765] (2/8) Epoch 1, batch 2100, train_loss[loss=5.372, NarTop10Accuracy=0.2644, over 4869.00 frames. ], tot_loss[loss=5.383, NarTop10Accuracy=0.2605, over 5977.59 frames. ], batch size: 5, lr: 2.88e-02
2024-08-06 14:34:57,304 INFO [trainer.py:765] (2/8) Epoch 1, batch 2200, train_loss[loss=5.348, NarTop10Accuracy=0.268, over 7281.00 frames. ], tot_loss[loss=5.344, NarTop10Accuracy=0.2661, over 6005.99 frames. ], batch size: 31, lr: 2.87e-02
2024-08-06 14:35:22,456 INFO [trainer.py:765] (2/8) Epoch 1, batch 2300, train_loss[loss=5.355, NarTop10Accuracy=0.2604, over 5811.00 frames. ], tot_loss[loss=5.333, NarTop10Accuracy=0.2676, over 6023.17 frames. ], batch size: 9, lr: 2.86e-02
2024-08-06 14:35:46,816 INFO [trainer.py:765] (2/8) Epoch 1, batch 2400, train_loss[loss=5.161, NarTop10Accuracy=0.2962, over 5100.00 frames. ], tot_loss[loss=5.286, NarTop10Accuracy=0.2763, over 5772.42 frames. ], batch size: 7, lr: 2.85e-02
2024-08-06 14:36:10,408 INFO [trainer.py:765] (2/8) Epoch 1, batch 2500, train_loss[loss=4.773, NarTop10Accuracy=0.3783, over 5310.00 frames. ], tot_loss[loss=5.22, NarTop10Accuracy=0.2884, over 5465.53 frames. ], batch size: 7, lr: 2.84e-02
2024-08-06 14:36:31,180 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 14:37:29,668 INFO [trainer.py:765] (2/8) Epoch 2, batch 100, train_loss[loss=5.064, NarTop10Accuracy=0.3203, over 7248.00 frames. ], tot_loss[loss=5.183, NarTop10Accuracy=0.2967, over 2367.36 frames. ], batch size: 31, lr: 2.77e-02
2024-08-06 14:38:10,015 INFO [trainer.py:765] (2/8) Epoch 2, batch 200, train_loss[loss=5.106, NarTop10Accuracy=0.3178, over 6894.00 frames. ], tot_loss[loss=5.148, NarTop10Accuracy=0.3024, over 3843.92 frames. ], batch size: 17, lr: 2.76e-02
2024-08-06 14:38:38,297 INFO [trainer.py:765] (2/8) Epoch 2, batch 300, train_loss[loss=5.21, NarTop10Accuracy=0.2845, over 7362.00 frames. ], tot_loss[loss=5.139, NarTop10Accuracy=0.3032, over 4662.87 frames. ], batch size: 23, lr: 2.75e-02
2024-08-06 14:39:06,998 INFO [trainer.py:765] (2/8) Epoch 2, batch 400, train_loss[loss=4.933, NarTop10Accuracy=0.3372, over 5157.00 frames. ], tot_loss[loss=5.112, NarTop10Accuracy=0.3081, over 5101.29 frames. ], batch size: 7, lr: 2.74e-02
2024-08-06 14:39:46,119 INFO [trainer.py:765] (2/8) Epoch 2, batch 500, train_loss[loss=4.893, NarTop10Accuracy=0.3482, over 6192.00 frames. ], tot_loss[loss=5.069, NarTop10Accuracy=0.3163, over 5377.24 frames. ], batch size: 11, lr: 2.73e-02
2024-08-06 14:40:15,083 INFO [trainer.py:765] (2/8) Epoch 2, batch 600, train_loss[loss=4.94, NarTop10Accuracy=0.3521, over 5772.00 frames. ], tot_loss[loss=5.044, NarTop10Accuracy=0.321, over 5648.45 frames. ], batch size: 9, lr: 2.71e-02
2024-08-06 14:40:44,589 INFO [trainer.py:765] (2/8) Epoch 2, batch 700, train_loss[loss=4.832, NarTop10Accuracy=0.3576, over 5094.00 frames. ], tot_loss[loss=5.024, NarTop10Accuracy=0.3245, over 5727.07 frames. ], batch size: 6, lr: 2.70e-02
2024-08-06 14:41:24,513 INFO [trainer.py:765] (2/8) Epoch 2, batch 800, train_loss[loss=5.213, NarTop10Accuracy=0.2888, over 4248.00 frames. ], tot_loss[loss=5.014, NarTop10Accuracy=0.3262, over 5775.62 frames. ], batch size: 5, lr: 2.69e-02
2024-08-06 14:41:54,404 INFO [trainer.py:765] (2/8) Epoch 2, batch 900, train_loss[loss=4.723, NarTop10Accuracy=0.3814, over 6540.00 frames. ], tot_loss[loss=4.982, NarTop10Accuracy=0.3324, over 5802.34 frames. ], batch size: 14, lr: 2.68e-02
2024-08-06 14:42:23,901 INFO [trainer.py:765] (2/8) Epoch 2, batch 1000, train_loss[loss=4.783, NarTop10Accuracy=0.3749, over 6732.00 frames. ], tot_loss[loss=4.952, NarTop10Accuracy=0.3379, over 5898.02 frames. ], batch size: 14, lr: 2.66e-02
2024-08-06 14:42:56,254 INFO [trainer.py:765] (2/8) Epoch 2, batch 1100, train_loss[loss=4.935, NarTop10Accuracy=0.3404, over 6933.00 frames. ], tot_loss[loss=4.932, NarTop10Accuracy=0.3415, over 5939.91 frames. ], batch size: 17, lr: 2.65e-02
2024-08-06 14:43:35,188 INFO [trainer.py:765] (2/8) Epoch 2, batch 1200, train_loss[loss=4.861, NarTop10Accuracy=0.3565, over 7323.00 frames. ], tot_loss[loss=4.909, NarTop10Accuracy=0.3462, over 5942.34 frames. ], batch size: 31, lr: 2.64e-02
2024-08-06 14:44:04,347 INFO [trainer.py:765] (2/8) Epoch 2, batch 1300, train_loss[loss=4.952, NarTop10Accuracy=0.3437, over 5115.00 frames. ], tot_loss[loss=4.871, NarTop10Accuracy=0.353, over 5993.17 frames. ], batch size: 6, lr: 2.63e-02
2024-08-06 14:44:33,728 INFO [trainer.py:765] (2/8) Epoch 2, batch 1400, train_loss[loss=5.119, NarTop10Accuracy=0.3063, over 6135.00 frames. ], tot_loss[loss=4.854, NarTop10Accuracy=0.3562, over 6013.65 frames. ], batch size: 11, lr: 2.61e-02
2024-08-06 14:44:40,442 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 14:44:48,506 INFO [trainer.py:811] (2/8) Epoch 2, validation: loss=4.808, NarTop10Accuracy=0.3642, over 1905321.00 frames. 
2024-08-06 14:44:48,506 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 27019MB
2024-08-06 14:44:49,204 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 6.328e+01 1.178e+02 1.410e+02 1.789e+02 6.269e+02, threshold=2.821e+02, percent-clipped=0.0
2024-08-06 14:45:09,806 INFO [trainer.py:765] (2/8) Epoch 2, batch 1500, train_loss[loss=4.715, NarTop10Accuracy=0.3803, over 6348.00 frames. ], tot_loss[loss=4.826, NarTop10Accuracy=0.3618, over 5953.46 frames. ], batch size: 50, lr: 2.60e-02
2024-08-06 14:45:37,659 INFO [trainer.py:765] (2/8) Epoch 2, batch 1600, train_loss[loss=4.74, NarTop10Accuracy=0.3797, over 6996.00 frames. ], tot_loss[loss=4.799, NarTop10Accuracy=0.3668, over 5926.73 frames. ], batch size: 22, lr: 2.59e-02
2024-08-06 14:46:04,368 INFO [trainer.py:765] (2/8) Epoch 2, batch 1700, train_loss[loss=4.924, NarTop10Accuracy=0.3345, over 6618.00 frames. ], tot_loss[loss=4.795, NarTop10Accuracy=0.3673, over 5916.99 frames. ], batch size: 14, lr: 2.58e-02
2024-08-06 14:46:31,034 INFO [trainer.py:765] (2/8) Epoch 2, batch 1800, train_loss[loss=4.717, NarTop10Accuracy=0.3814, over 7230.00 frames. ], tot_loss[loss=4.777, NarTop10Accuracy=0.3708, over 5990.76 frames. ], batch size: 22, lr: 2.56e-02
2024-08-06 14:46:57,532 INFO [trainer.py:765] (2/8) Epoch 2, batch 1900, train_loss[loss=4.814, NarTop10Accuracy=0.3632, over 6186.00 frames. ], tot_loss[loss=4.759, NarTop10Accuracy=0.3744, over 6009.76 frames. ], batch size: 50, lr: 2.55e-02
2024-08-06 14:47:23,234 INFO [trainer.py:765] (2/8) Epoch 2, batch 2000, train_loss[loss=4.783, NarTop10Accuracy=0.3749, over 6000.00 frames. ], tot_loss[loss=4.731, NarTop10Accuracy=0.3795, over 5984.04 frames. ], batch size: 51, lr: 2.54e-02
2024-08-06 14:47:48,589 INFO [trainer.py:765] (2/8) Epoch 2, batch 2100, train_loss[loss=4.766, NarTop10Accuracy=0.3765, over 4830.00 frames. ], tot_loss[loss=4.719, NarTop10Accuracy=0.3816, over 5974.86 frames. ], batch size: 5, lr: 2.53e-02
2024-08-06 14:48:13,765 INFO [trainer.py:765] (2/8) Epoch 2, batch 2200, train_loss[loss=4.762, NarTop10Accuracy=0.3754, over 7140.00 frames. ], tot_loss[loss=4.685, NarTop10Accuracy=0.3882, over 6017.07 frames. ], batch size: 31, lr: 2.51e-02
2024-08-06 14:48:38,951 INFO [trainer.py:765] (2/8) Epoch 2, batch 2300, train_loss[loss=4.663, NarTop10Accuracy=0.3922, over 5703.00 frames. ], tot_loss[loss=4.687, NarTop10Accuracy=0.388, over 6021.88 frames. ], batch size: 9, lr: 2.50e-02
2024-08-06 14:49:03,320 INFO [trainer.py:765] (2/8) Epoch 2, batch 2400, train_loss[loss=4.572, NarTop10Accuracy=0.4112, over 5121.00 frames. ], tot_loss[loss=4.651, NarTop10Accuracy=0.395, over 5760.93 frames. ], batch size: 7, lr: 2.49e-02
2024-08-06 14:49:26,867 INFO [trainer.py:765] (2/8) Epoch 2, batch 2500, train_loss[loss=4.654, NarTop10Accuracy=0.3908, over 5244.00 frames. ], tot_loss[loss=4.622, NarTop10Accuracy=0.4007, over 5470.90 frames. ], batch size: 7, lr: 2.48e-02
2024-08-06 14:49:46,767 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 14:50:51,117 INFO [trainer.py:765] (2/8) Epoch 3, batch 100, train_loss[loss=4.668, NarTop10Accuracy=0.3934, over 7326.00 frames. ], tot_loss[loss=4.576, NarTop10Accuracy=0.4099, over 2360.61 frames. ], batch size: 31, lr: 2.36e-02
2024-08-06 14:51:20,388 INFO [trainer.py:765] (2/8) Epoch 3, batch 200, train_loss[loss=4.653, NarTop10Accuracy=0.4051, over 6726.00 frames. ], tot_loss[loss=4.545, NarTop10Accuracy=0.416, over 3837.44 frames. ], batch size: 17, lr: 2.34e-02
2024-08-06 14:51:50,954 INFO [trainer.py:765] (2/8) Epoch 3, batch 300, train_loss[loss=4.691, NarTop10Accuracy=0.3874, over 7452.00 frames. ], tot_loss[loss=4.52, NarTop10Accuracy=0.4209, over 4638.88 frames. ], batch size: 24, lr: 2.33e-02
2024-08-06 14:52:32,359 INFO [trainer.py:765] (2/8) Epoch 3, batch 400, train_loss[loss=4.491, NarTop10Accuracy=0.4303, over 5124.00 frames. ], tot_loss[loss=4.495, NarTop10Accuracy=0.4258, over 5093.83 frames. ], batch size: 7, lr: 2.32e-02
2024-08-06 14:53:00,680 INFO [trainer.py:765] (2/8) Epoch 3, batch 500, train_loss[loss=4.336, NarTop10Accuracy=0.4529, over 6084.00 frames. ], tot_loss[loss=4.483, NarTop10Accuracy=0.4275, over 5400.75 frames. ], batch size: 11, lr: 2.31e-02
2024-08-06 14:53:29,552 INFO [trainer.py:765] (2/8) Epoch 3, batch 600, train_loss[loss=4.397, NarTop10Accuracy=0.445, over 5643.00 frames. ], tot_loss[loss=4.468, NarTop10Accuracy=0.4306, over 5663.01 frames. ], batch size: 9, lr: 2.30e-02
2024-08-06 14:54:12,466 INFO [trainer.py:765] (2/8) Epoch 3, batch 700, train_loss[loss=4.317, NarTop10Accuracy=0.4677, over 4362.00 frames. ], tot_loss[loss=4.446, NarTop10Accuracy=0.4351, over 5733.28 frames. ], batch size: 5, lr: 2.29e-02
2024-08-06 14:54:44,785 INFO [trainer.py:765] (2/8) Epoch 3, batch 800, train_loss[loss=3.943, NarTop10Accuracy=0.5424, over 5190.00 frames. ], tot_loss[loss=4.42, NarTop10Accuracy=0.4404, over 5784.32 frames. ], batch size: 6, lr: 2.28e-02
2024-08-06 14:54:58,684 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 14:55:06,655 INFO [trainer.py:811] (2/8) Epoch 3, validation: loss=4.276, NarTop10Accuracy=0.4689, over 1905321.00 frames. 
2024-08-06 14:55:06,656 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 27019MB
2024-08-06 14:55:07,183 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 8.443e+01 1.396e+02 1.639e+02 2.017e+02 7.124e+02, threshold=3.277e+02, percent-clipped=4.5
2024-08-06 14:55:21,052 INFO [trainer.py:765] (2/8) Epoch 3, batch 900, train_loss[loss=4.042, NarTop10Accuracy=0.5151, over 6729.00 frames. ], tot_loss[loss=4.386, NarTop10Accuracy=0.4473, over 5824.38 frames. ], batch size: 14, lr: 2.26e-02
2024-08-06 14:56:04,958 INFO [trainer.py:765] (2/8) Epoch 3, batch 1000, train_loss[loss=4.403, NarTop10Accuracy=0.4427, over 6513.00 frames. ], tot_loss[loss=4.373, NarTop10Accuracy=0.4496, over 5912.61 frames. ], batch size: 14, lr: 2.25e-02
2024-08-06 14:56:37,300 INFO [trainer.py:765] (2/8) Epoch 3, batch 1100, train_loss[loss=4.483, NarTop10Accuracy=0.4238, over 6849.00 frames. ], tot_loss[loss=4.349, NarTop10Accuracy=0.4546, over 5930.93 frames. ], batch size: 17, lr: 2.24e-02
2024-08-06 14:57:06,377 INFO [trainer.py:765] (2/8) Epoch 3, batch 1200, train_loss[loss=4.36, NarTop10Accuracy=0.4487, over 7464.00 frames. ], tot_loss[loss=4.332, NarTop10Accuracy=0.4576, over 5927.51 frames. ], batch size: 31, lr: 2.23e-02
2024-08-06 14:57:51,630 INFO [trainer.py:765] (2/8) Epoch 3, batch 1300, train_loss[loss=4.333, NarTop10Accuracy=0.4592, over 5100.00 frames. ], tot_loss[loss=4.308, NarTop10Accuracy=0.4625, over 5997.09 frames. ], batch size: 6, lr: 2.22e-02
2024-08-06 14:58:22,900 INFO [trainer.py:765] (2/8) Epoch 3, batch 1400, train_loss[loss=4.303, NarTop10Accuracy=0.4694, over 6237.00 frames. ], tot_loss[loss=4.298, NarTop10Accuracy=0.4642, over 6004.07 frames. ], batch size: 11, lr: 2.21e-02
2024-08-06 14:58:50,855 INFO [trainer.py:765] (2/8) Epoch 3, batch 1500, train_loss[loss=4.374, NarTop10Accuracy=0.4456, over 6144.00 frames. ], tot_loss[loss=4.273, NarTop10Accuracy=0.469, over 5942.15 frames. ], batch size: 51, lr: 2.20e-02
2024-08-06 14:59:18,715 INFO [trainer.py:765] (2/8) Epoch 3, batch 1600, train_loss[loss=4.065, NarTop10Accuracy=0.5123, over 7098.00 frames. ], tot_loss[loss=4.251, NarTop10Accuracy=0.4734, over 5900.94 frames. ], batch size: 23, lr: 2.19e-02
2024-08-06 14:59:45,952 INFO [trainer.py:765] (2/8) Epoch 3, batch 1700, train_loss[loss=4.079, NarTop10Accuracy=0.51, over 6651.00 frames. ], tot_loss[loss=4.228, NarTop10Accuracy=0.4779, over 5887.70 frames. ], batch size: 14, lr: 2.18e-02
2024-08-06 15:00:12,498 INFO [trainer.py:765] (2/8) Epoch 3, batch 1800, train_loss[loss=4.021, NarTop10Accuracy=0.5186, over 7029.00 frames. ], tot_loss[loss=4.207, NarTop10Accuracy=0.4816, over 5959.05 frames. ], batch size: 22, lr: 2.17e-02
2024-08-06 15:00:38,948 INFO [trainer.py:765] (2/8) Epoch 3, batch 1900, train_loss[loss=4.671, NarTop10Accuracy=0.386, over 6285.00 frames. ], tot_loss[loss=4.187, NarTop10Accuracy=0.486, over 6018.85 frames. ], batch size: 50, lr: 2.16e-02
2024-08-06 15:01:04,606 INFO [trainer.py:765] (2/8) Epoch 3, batch 2000, train_loss[loss=4.419, NarTop10Accuracy=0.4369, over 6279.00 frames. ], tot_loss[loss=4.163, NarTop10Accuracy=0.4908, over 5984.78 frames. ], batch size: 50, lr: 2.15e-02
2024-08-06 15:01:29,898 INFO [trainer.py:765] (2/8) Epoch 3, batch 2100, train_loss[loss=3.764, NarTop10Accuracy=0.5761, over 4002.00 frames. ], tot_loss[loss=4.14, NarTop10Accuracy=0.4956, over 5966.17 frames. ], batch size: 4, lr: 2.14e-02
2024-08-06 15:01:55,182 INFO [trainer.py:765] (2/8) Epoch 3, batch 2200, train_loss[loss=3.964, NarTop10Accuracy=0.5353, over 7188.00 frames. ], tot_loss[loss=4.115, NarTop10Accuracy=0.501, over 6002.13 frames. ], batch size: 31, lr: 2.13e-02
2024-08-06 15:02:20,410 INFO [trainer.py:765] (2/8) Epoch 3, batch 2300, train_loss[loss=4.362, NarTop10Accuracy=0.4477, over 5820.00 frames. ], tot_loss[loss=4.131, NarTop10Accuracy=0.4974, over 6020.95 frames. ], batch size: 9, lr: 2.12e-02
2024-08-06 15:02:44,664 INFO [trainer.py:765] (2/8) Epoch 3, batch 2400, train_loss[loss=4.1, NarTop10Accuracy=0.4958, over 5139.00 frames. ], tot_loss[loss=4.097, NarTop10Accuracy=0.5047, over 5779.94 frames. ], batch size: 7, lr: 2.11e-02
2024-08-06 15:03:08,234 INFO [trainer.py:765] (2/8) Epoch 3, batch 2500, train_loss[loss=3.793, NarTop10Accuracy=0.5601, over 5133.00 frames. ], tot_loss[loss=4.042, NarTop10Accuracy=0.5157, over 5482.18 frames. ], batch size: 7, lr: 2.10e-02
2024-08-06 15:03:28,326 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 15:04:28,131 INFO [trainer.py:765] (2/8) Epoch 4, batch 100, train_loss[loss=3.906, NarTop10Accuracy=0.5521, over 7287.00 frames. ], tot_loss[loss=4.04, NarTop10Accuracy=0.5175, over 2347.95 frames. ], batch size: 31, lr: 1.97e-02
2024-08-06 15:04:59,842 INFO [trainer.py:765] (2/8) Epoch 4, batch 200, train_loss[loss=3.791, NarTop10Accuracy=0.5727, over 6831.00 frames. ], tot_loss[loss=4.02, NarTop10Accuracy=0.5211, over 3844.73 frames. ], batch size: 17, lr: 1.96e-02
2024-08-06 15:05:27,508 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 15:05:35,694 INFO [trainer.py:811] (2/8) Epoch 4, validation: loss=3.804, NarTop10Accuracy=0.5644, over 1905321.00 frames. 
2024-08-06 15:05:35,695 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 27023MB
2024-08-06 15:05:36,238 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.166e+02 1.765e+02 1.975e+02 2.270e+02 5.852e+02, threshold=3.949e+02, percent-clipped=2.8
2024-08-06 15:05:43,890 INFO [trainer.py:765] (2/8) Epoch 4, batch 300, train_loss[loss=3.804, NarTop10Accuracy=0.5716, over 7113.00 frames. ], tot_loss[loss=3.999, NarTop10Accuracy=0.5246, over 4650.35 frames. ], batch size: 22, lr: 1.95e-02
2024-08-06 15:06:16,124 INFO [trainer.py:765] (2/8) Epoch 4, batch 400, train_loss[loss=3.83, NarTop10Accuracy=0.5553, over 5184.00 frames. ], tot_loss[loss=4.007, NarTop10Accuracy=0.5232, over 5110.59 frames. ], batch size: 7, lr: 1.94e-02
2024-08-06 15:06:46,473 INFO [trainer.py:765] (2/8) Epoch 4, batch 500, train_loss[loss=3.924, NarTop10Accuracy=0.5267, over 5964.00 frames. ], tot_loss[loss=3.984, NarTop10Accuracy=0.5279, over 5378.83 frames. ], batch size: 11, lr: 1.93e-02
2024-08-06 15:07:23,818 INFO [trainer.py:765] (2/8) Epoch 4, batch 600, train_loss[loss=3.773, NarTop10Accuracy=0.578, over 5769.00 frames. ], tot_loss[loss=3.974, NarTop10Accuracy=0.53, over 5641.89 frames. ], batch size: 9, lr: 1.93e-02
2024-08-06 15:07:59,001 INFO [trainer.py:765] (2/8) Epoch 4, batch 700, train_loss[loss=4.092, NarTop10Accuracy=0.5078, over 5178.00 frames. ], tot_loss[loss=3.969, NarTop10Accuracy=0.5308, over 5715.03 frames. ], batch size: 6, lr: 1.92e-02
2024-08-06 15:08:32,429 INFO [trainer.py:765] (2/8) Epoch 4, batch 800, train_loss[loss=3.838, NarTop10Accuracy=0.5613, over 5070.00 frames. ], tot_loss[loss=3.957, NarTop10Accuracy=0.5332, over 5789.14 frames. ], batch size: 6, lr: 1.91e-02
2024-08-06 15:09:10,689 INFO [trainer.py:765] (2/8) Epoch 4, batch 900, train_loss[loss=3.722, NarTop10Accuracy=0.5882, over 6165.00 frames. ], tot_loss[loss=3.923, NarTop10Accuracy=0.5399, over 5811.26 frames. ], batch size: 13, lr: 1.90e-02
2024-08-06 15:09:46,075 INFO [trainer.py:765] (2/8) Epoch 4, batch 1000, train_loss[loss=3.619, NarTop10Accuracy=0.6008, over 6150.00 frames. ], tot_loss[loss=3.914, NarTop10Accuracy=0.5417, over 5905.05 frames. ], batch size: 13, lr: 1.89e-02
2024-08-06 15:10:18,139 INFO [trainer.py:765] (2/8) Epoch 4, batch 1100, train_loss[loss=3.686, NarTop10Accuracy=0.5895, over 6672.00 frames. ], tot_loss[loss=3.907, NarTop10Accuracy=0.5432, over 5929.93 frames. ], batch size: 17, lr: 1.88e-02
2024-08-06 15:10:55,075 INFO [trainer.py:765] (2/8) Epoch 4, batch 1200, train_loss[loss=4.237, NarTop10Accuracy=0.4721, over 7326.00 frames. ], tot_loss[loss=3.9, NarTop10Accuracy=0.5445, over 5941.01 frames. ], batch size: 31, lr: 1.88e-02
2024-08-06 15:11:32,074 INFO [trainer.py:765] (2/8) Epoch 4, batch 1300, train_loss[loss=3.754, NarTop10Accuracy=0.5817, over 4986.00 frames. ], tot_loss[loss=3.86, NarTop10Accuracy=0.5528, over 6001.22 frames. ], batch size: 6, lr: 1.87e-02
2024-08-06 15:12:05,688 INFO [trainer.py:765] (2/8) Epoch 4, batch 1400, train_loss[loss=3.615, NarTop10Accuracy=0.6008, over 6090.00 frames. ], tot_loss[loss=3.852, NarTop10Accuracy=0.5543, over 6005.11 frames. ], batch size: 11, lr: 1.86e-02
2024-08-06 15:12:33,695 INFO [trainer.py:765] (2/8) Epoch 4, batch 1500, train_loss[loss=3.88, NarTop10Accuracy=0.5543, over 6534.00 frames. ], tot_loss[loss=3.854, NarTop10Accuracy=0.5538, over 5956.29 frames. ], batch size: 51, lr: 1.85e-02
2024-08-06 15:13:01,510 INFO [trainer.py:765] (2/8) Epoch 4, batch 1600, train_loss[loss=3.772, NarTop10Accuracy=0.5715, over 6768.00 frames. ], tot_loss[loss=3.847, NarTop10Accuracy=0.5555, over 5918.16 frames. ], batch size: 22, lr: 1.84e-02
2024-08-06 15:13:28,133 INFO [trainer.py:765] (2/8) Epoch 4, batch 1700, train_loss[loss=3.904, NarTop10Accuracy=0.5408, over 6243.00 frames. ], tot_loss[loss=3.82, NarTop10Accuracy=0.5607, over 5919.66 frames. ], batch size: 13, lr: 1.84e-02
2024-08-06 15:13:54,557 INFO [trainer.py:765] (2/8) Epoch 4, batch 1800, train_loss[loss=3.75, NarTop10Accuracy=0.5765, over 7095.00 frames. ], tot_loss[loss=3.822, NarTop10Accuracy=0.5608, over 5993.54 frames. ], batch size: 22, lr: 1.83e-02
2024-08-06 15:14:20,998 INFO [trainer.py:765] (2/8) Epoch 4, batch 1900, train_loss[loss=3.765, NarTop10Accuracy=0.5707, over 5946.00 frames. ], tot_loss[loss=3.84, NarTop10Accuracy=0.5573, over 6040.09 frames. ], batch size: 50, lr: 1.82e-02
2024-08-06 15:14:46,672 INFO [trainer.py:765] (2/8) Epoch 4, batch 2000, train_loss[loss=3.784, NarTop10Accuracy=0.5663, over 5775.00 frames. ], tot_loss[loss=3.814, NarTop10Accuracy=0.5624, over 6017.69 frames. ], batch size: 50, lr: 1.81e-02
2024-08-06 15:15:11,859 INFO [trainer.py:765] (2/8) Epoch 4, batch 2100, train_loss[loss=3.603, NarTop10Accuracy=0.6047, over 4920.00 frames. ], tot_loss[loss=3.805, NarTop10Accuracy=0.5642, over 6005.44 frames. ], batch size: 5, lr: 1.81e-02
2024-08-06 15:15:37,089 INFO [trainer.py:765] (2/8) Epoch 4, batch 2200, train_loss[loss=3.721, NarTop10Accuracy=0.5906, over 7011.00 frames. ], tot_loss[loss=3.797, NarTop10Accuracy=0.5658, over 6034.74 frames. ], batch size: 31, lr: 1.80e-02
2024-08-06 15:15:55,090 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 15:16:03,243 INFO [trainer.py:811] (2/8) Epoch 4, validation: loss=3.665, NarTop10Accuracy=0.5912, over 1905321.00 frames. 
2024-08-06 15:16:03,243 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 27390MB
2024-08-06 15:16:03,740 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.414e+02 1.889e+02 2.096e+02 2.369e+02 1.168e+03, threshold=4.192e+02, percent-clipped=1.7
2024-08-06 15:16:10,347 INFO [trainer.py:765] (2/8) Epoch 4, batch 2300, train_loss[loss=3.603, NarTop10Accuracy=0.6202, over 5751.00 frames. ], tot_loss[loss=3.805, NarTop10Accuracy=0.5641, over 6025.74 frames. ], batch size: 9, lr: 1.79e-02
2024-08-06 15:16:34,840 INFO [trainer.py:765] (2/8) Epoch 4, batch 2400, train_loss[loss=3.347, NarTop10Accuracy=0.6635, over 5160.00 frames. ], tot_loss[loss=3.777, NarTop10Accuracy=0.5696, over 5787.17 frames. ], batch size: 7, lr: 1.79e-02
2024-08-06 15:16:58,534 INFO [trainer.py:765] (2/8) Epoch 4, batch 2500, train_loss[loss=3.476, NarTop10Accuracy=0.6374, over 5163.00 frames. ], tot_loss[loss=3.762, NarTop10Accuracy=0.5722, over 5482.39 frames. ], batch size: 7, lr: 1.78e-02
2024-08-06 15:17:18,339 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 15:18:24,101 INFO [trainer.py:765] (2/8) Epoch 5, batch 100, train_loss[loss=3.507, NarTop10Accuracy=0.6254, over 7317.00 frames. ], tot_loss[loss=3.778, NarTop10Accuracy=0.5688, over 2376.60 frames. ], batch size: 32, lr: 1.66e-02
2024-08-06 15:18:59,675 INFO [trainer.py:765] (2/8) Epoch 5, batch 200, train_loss[loss=4.102, NarTop10Accuracy=0.5063, over 6744.00 frames. ], tot_loss[loss=3.76, NarTop10Accuracy=0.573, over 3855.98 frames. ], batch size: 17, lr: 1.65e-02
2024-08-06 15:19:32,888 INFO [trainer.py:765] (2/8) Epoch 5, batch 300, train_loss[loss=4.03, NarTop10Accuracy=0.52, over 7206.00 frames. ], tot_loss[loss=3.734, NarTop10Accuracy=0.5787, over 4656.37 frames. ], batch size: 22, lr: 1.65e-02
2024-08-06 15:20:01,656 INFO [trainer.py:765] (2/8) Epoch 5, batch 400, train_loss[loss=3.585, NarTop10Accuracy=0.6116, over 5277.00 frames. ], tot_loss[loss=3.722, NarTop10Accuracy=0.5805, over 5102.01 frames. ], batch size: 7, lr: 1.64e-02
2024-08-06 15:20:38,298 INFO [trainer.py:765] (2/8) Epoch 5, batch 500, train_loss[loss=3.923, NarTop10Accuracy=0.5344, over 6045.00 frames. ], tot_loss[loss=3.735, NarTop10Accuracy=0.5779, over 5390.27 frames. ], batch size: 11, lr: 1.63e-02
2024-08-06 15:21:13,711 INFO [trainer.py:765] (2/8) Epoch 5, batch 600, train_loss[loss=3.936, NarTop10Accuracy=0.5464, over 5673.00 frames. ], tot_loss[loss=3.722, NarTop10Accuracy=0.5807, over 5658.39 frames. ], batch size: 9, lr: 1.63e-02
2024-08-06 15:21:45,881 INFO [trainer.py:765] (2/8) Epoch 5, batch 700, train_loss[loss=3.504, NarTop10Accuracy=0.6242, over 5208.00 frames. ], tot_loss[loss=3.717, NarTop10Accuracy=0.5818, over 5724.68 frames. ], batch size: 6, lr: 1.62e-02
2024-08-06 15:22:24,499 INFO [trainer.py:765] (2/8) Epoch 5, batch 800, train_loss[loss=3.954, NarTop10Accuracy=0.5239, over 5070.00 frames. ], tot_loss[loss=3.705, NarTop10Accuracy=0.584, over 5792.67 frames. ], batch size: 6, lr: 1.62e-02
2024-08-06 15:22:56,783 INFO [trainer.py:765] (2/8) Epoch 5, batch 900, train_loss[loss=3.649, NarTop10Accuracy=0.5919, over 6279.00 frames. ], tot_loss[loss=3.693, NarTop10Accuracy=0.5863, over 5813.85 frames. ], batch size: 13, lr: 1.61e-02
2024-08-06 15:23:31,914 INFO [trainer.py:765] (2/8) Epoch 5, batch 1000, train_loss[loss=3.596, NarTop10Accuracy=0.6069, over 6567.00 frames. ], tot_loss[loss=3.681, NarTop10Accuracy=0.5885, over 5911.91 frames. ], batch size: 14, lr: 1.60e-02
2024-08-06 15:24:09,572 INFO [trainer.py:765] (2/8) Epoch 5, batch 1100, train_loss[loss=3.45, NarTop10Accuracy=0.6364, over 6882.00 frames. ], tot_loss[loss=3.684, NarTop10Accuracy=0.5883, over 5940.84 frames. ], batch size: 17, lr: 1.60e-02
2024-08-06 15:24:44,529 INFO [trainer.py:765] (2/8) Epoch 5, batch 1200, train_loss[loss=3.522, NarTop10Accuracy=0.6223, over 7173.00 frames. ], tot_loss[loss=3.682, NarTop10Accuracy=0.5886, over 5931.78 frames. ], batch size: 31, lr: 1.59e-02
2024-08-06 15:25:19,380 INFO [trainer.py:765] (2/8) Epoch 5, batch 1300, train_loss[loss=3.93, NarTop10Accuracy=0.5343, over 5106.00 frames. ], tot_loss[loss=3.664, NarTop10Accuracy=0.5922, over 6005.58 frames. ], batch size: 6, lr: 1.59e-02
2024-08-06 15:25:51,694 INFO [trainer.py:765] (2/8) Epoch 5, batch 1400, train_loss[loss=3.84, NarTop10Accuracy=0.5533, over 6096.00 frames. ], tot_loss[loss=3.672, NarTop10Accuracy=0.5908, over 6018.64 frames. ], batch size: 11, lr: 1.58e-02
2024-08-06 15:26:26,196 INFO [trainer.py:765] (2/8) Epoch 5, batch 1500, train_loss[loss=3.637, NarTop10Accuracy=0.6032, over 5979.00 frames. ], tot_loss[loss=3.664, NarTop10Accuracy=0.5924, over 5950.07 frames. ], batch size: 50, lr: 1.58e-02
2024-08-06 15:26:54,130 INFO [trainer.py:765] (2/8) Epoch 5, batch 1600, train_loss[loss=3.451, NarTop10Accuracy=0.6374, over 7008.00 frames. ], tot_loss[loss=3.677, NarTop10Accuracy=0.5896, over 5934.19 frames. ], batch size: 22, lr: 1.57e-02
2024-08-06 15:27:19,604 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 15:27:27,821 INFO [trainer.py:811] (2/8) Epoch 5, validation: loss=3.552, NarTop10Accuracy=0.6147, over 1905321.00 frames. 
2024-08-06 15:27:27,822 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 27390MB
2024-08-06 15:27:28,341 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.340e+02 1.756e+02 1.962e+02 2.205e+02 5.880e+02, threshold=3.924e+02, percent-clipped=0.8
2024-08-06 15:27:29,131 INFO [trainer.py:765] (2/8) Epoch 5, batch 1700, train_loss[loss=3.849, NarTop10Accuracy=0.5533, over 6747.00 frames. ], tot_loss[loss=3.664, NarTop10Accuracy=0.5923, over 5925.87 frames. ], batch size: 14, lr: 1.56e-02
2024-08-06 15:27:55,652 INFO [trainer.py:765] (2/8) Epoch 5, batch 1800, train_loss[loss=3.884, NarTop10Accuracy=0.5403, over 7101.00 frames. ], tot_loss[loss=3.663, NarTop10Accuracy=0.5928, over 5983.42 frames. ], batch size: 22, lr: 1.56e-02
2024-08-06 15:28:22,171 INFO [trainer.py:765] (2/8) Epoch 5, batch 1900, train_loss[loss=3.747, NarTop10Accuracy=0.5814, over 5859.00 frames. ], tot_loss[loss=3.663, NarTop10Accuracy=0.5927, over 6030.47 frames. ], batch size: 51, lr: 1.55e-02
2024-08-06 15:28:47,893 INFO [trainer.py:765] (2/8) Epoch 5, batch 2000, train_loss[loss=3.623, NarTop10Accuracy=0.603, over 6315.00 frames. ], tot_loss[loss=3.665, NarTop10Accuracy=0.5924, over 5990.18 frames. ], batch size: 50, lr: 1.55e-02
2024-08-06 15:29:13,769 INFO [trainer.py:765] (2/8) Epoch 5, batch 2100, train_loss[loss=3.383, NarTop10Accuracy=0.6379, over 3888.00 frames. ], tot_loss[loss=3.682, NarTop10Accuracy=0.5878, over 5970.52 frames. ], batch size: 4, lr: 1.54e-02
2024-08-06 15:29:39,177 INFO [trainer.py:765] (2/8) Epoch 5, batch 2200, train_loss[loss=4.095, NarTop10Accuracy=0.5082, over 7203.00 frames. ], tot_loss[loss=3.66, NarTop10Accuracy=0.5921, over 6011.53 frames. ], batch size: 32, lr: 1.54e-02
2024-08-06 15:30:04,429 INFO [trainer.py:765] (2/8) Epoch 5, batch 2300, train_loss[loss=3.479, NarTop10Accuracy=0.6296, over 5667.00 frames. ], tot_loss[loss=3.671, NarTop10Accuracy=0.5901, over 6026.91 frames. ], batch size: 9, lr: 1.53e-02
2024-08-06 15:30:28,862 INFO [trainer.py:765] (2/8) Epoch 5, batch 2400, train_loss[loss=3.327, NarTop10Accuracy=0.6434, over 5052.00 frames. ], tot_loss[loss=3.644, NarTop10Accuracy=0.5959, over 5785.53 frames. ], batch size: 7, lr: 1.53e-02
2024-08-06 15:30:52,502 INFO [trainer.py:765] (2/8) Epoch 5, batch 2500, train_loss[loss=3.324, NarTop10Accuracy=0.6611, over 5190.00 frames. ], tot_loss[loss=3.615, NarTop10Accuracy=0.602, over 5491.34 frames. ], batch size: 7, lr: 1.52e-02
2024-08-06 15:31:12,342 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 15:32:14,415 INFO [trainer.py:765] (2/8) Epoch 6, batch 100, train_loss[loss=3.551, NarTop10Accuracy=0.6109, over 7386.00 frames. ], tot_loss[loss=3.646, NarTop10Accuracy=0.596, over 2383.31 frames. ], batch size: 31, lr: 1.42e-02
2024-08-06 15:32:46,015 INFO [trainer.py:765] (2/8) Epoch 6, batch 200, train_loss[loss=3.879, NarTop10Accuracy=0.5421, over 6636.00 frames. ], tot_loss[loss=3.619, NarTop10Accuracy=0.6013, over 3878.68 frames. ], batch size: 17, lr: 1.42e-02
2024-08-06 15:33:21,242 INFO [trainer.py:765] (2/8) Epoch 6, batch 300, train_loss[loss=3.438, NarTop10Accuracy=0.6432, over 7230.00 frames. ], tot_loss[loss=3.615, NarTop10Accuracy=0.602, over 4671.74 frames. ], batch size: 23, lr: 1.41e-02
2024-08-06 15:33:56,035 INFO [trainer.py:765] (2/8) Epoch 6, batch 400, train_loss[loss=3.423, NarTop10Accuracy=0.6355, over 5103.00 frames. ], tot_loss[loss=3.601, NarTop10Accuracy=0.6052, over 5112.41 frames. ], batch size: 7, lr: 1.41e-02
2024-08-06 15:34:26,759 INFO [trainer.py:765] (2/8) Epoch 6, batch 500, train_loss[loss=3.321, NarTop10Accuracy=0.6619, over 6051.00 frames. ], tot_loss[loss=3.583, NarTop10Accuracy=0.6093, over 5388.35 frames. ], batch size: 11, lr: 1.40e-02
2024-08-06 15:35:01,458 INFO [trainer.py:765] (2/8) Epoch 6, batch 600, train_loss[loss=3.279, NarTop10Accuracy=0.6755, over 5790.00 frames. ], tot_loss[loss=3.576, NarTop10Accuracy=0.6105, over 5647.15 frames. ], batch size: 9, lr: 1.40e-02
2024-08-06 15:35:32,734 INFO [trainer.py:765] (2/8) Epoch 6, batch 700, train_loss[loss=3.562, NarTop10Accuracy=0.6091, over 4254.00 frames. ], tot_loss[loss=3.581, NarTop10Accuracy=0.6095, over 5716.97 frames. ], batch size: 5, lr: 1.39e-02
2024-08-06 15:36:06,844 INFO [trainer.py:765] (2/8) Epoch 6, batch 800, train_loss[loss=3.745, NarTop10Accuracy=0.5615, over 5001.00 frames. ], tot_loss[loss=3.587, NarTop10Accuracy=0.6076, over 5768.63 frames. ], batch size: 6, lr: 1.39e-02
2024-08-06 15:36:40,384 INFO [trainer.py:765] (2/8) Epoch 6, batch 900, train_loss[loss=3.984, NarTop10Accuracy=0.5259, over 6231.00 frames. ], tot_loss[loss=3.572, NarTop10Accuracy=0.6105, over 5790.46 frames. ], batch size: 13, lr: 1.38e-02
2024-08-06 15:37:15,272 INFO [trainer.py:765] (2/8) Epoch 6, batch 1000, train_loss[loss=3.545, NarTop10Accuracy=0.6167, over 6549.00 frames. ], tot_loss[loss=3.592, NarTop10Accuracy=0.6059, over 5901.73 frames. ], batch size: 14, lr: 1.38e-02
2024-08-06 15:37:50,508 INFO [trainer.py:765] (2/8) Epoch 6, batch 1100, train_loss[loss=3.332, NarTop10Accuracy=0.6621, over 6951.00 frames. ], tot_loss[loss=3.589, NarTop10Accuracy=0.6067, over 5946.70 frames. ], batch size: 17, lr: 1.38e-02
2024-08-06 15:37:55,828 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 15:38:04,436 INFO [trainer.py:811] (2/8) Epoch 6, validation: loss=3.421, NarTop10Accuracy=0.6418, over 1905321.00 frames. 
2024-08-06 15:38:04,437 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 27390MB
2024-08-06 15:38:04,966 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.415e+02 1.809e+02 1.991e+02 2.234e+02 5.215e+02, threshold=3.983e+02, percent-clipped=0.5
2024-08-06 15:38:36,168 INFO [trainer.py:765] (2/8) Epoch 6, batch 1200, train_loss[loss=3.364, NarTop10Accuracy=0.6521, over 7218.00 frames. ], tot_loss[loss=3.577, NarTop10Accuracy=0.6096, over 5957.40 frames. ], batch size: 31, lr: 1.37e-02
2024-08-06 15:39:08,242 INFO [trainer.py:765] (2/8) Epoch 6, batch 1300, train_loss[loss=3.367, NarTop10Accuracy=0.6573, over 5085.00 frames. ], tot_loss[loss=3.571, NarTop10Accuracy=0.6106, over 6013.27 frames. ], batch size: 6, lr: 1.37e-02
2024-08-06 15:39:44,070 INFO [trainer.py:765] (2/8) Epoch 6, batch 1400, train_loss[loss=3.354, NarTop10Accuracy=0.662, over 6126.00 frames. ], tot_loss[loss=3.571, NarTop10Accuracy=0.6112, over 6041.26 frames. ], batch size: 11, lr: 1.36e-02
2024-08-06 15:40:15,383 INFO [trainer.py:765] (2/8) Epoch 6, batch 1500, train_loss[loss=3.972, NarTop10Accuracy=0.5319, over 5790.00 frames. ], tot_loss[loss=3.574, NarTop10Accuracy=0.6105, over 5976.62 frames. ], batch size: 52, lr: 1.36e-02
2024-08-06 15:40:43,106 INFO [trainer.py:765] (2/8) Epoch 6, batch 1600, train_loss[loss=3.291, NarTop10Accuracy=0.6706, over 6993.00 frames. ], tot_loss[loss=3.563, NarTop10Accuracy=0.6124, over 5925.58 frames. ], batch size: 22, lr: 1.35e-02
2024-08-06 15:41:09,789 INFO [trainer.py:765] (2/8) Epoch 6, batch 1700, train_loss[loss=3.467, NarTop10Accuracy=0.6368, over 6321.00 frames. ], tot_loss[loss=3.555, NarTop10Accuracy=0.6142, over 5909.49 frames. ], batch size: 13, lr: 1.35e-02
2024-08-06 15:41:36,317 INFO [trainer.py:765] (2/8) Epoch 6, batch 1800, train_loss[loss=3.24, NarTop10Accuracy=0.6849, over 6975.00 frames. ], tot_loss[loss=3.565, NarTop10Accuracy=0.6125, over 5995.00 frames. ], batch size: 22, lr: 1.35e-02
2024-08-06 15:42:02,720 INFO [trainer.py:765] (2/8) Epoch 6, batch 1900, train_loss[loss=3.791, NarTop10Accuracy=0.5599, over 5976.00 frames. ], tot_loss[loss=3.581, NarTop10Accuracy=0.6092, over 6017.54 frames. ], batch size: 51, lr: 1.34e-02
2024-08-06 15:42:28,319 INFO [trainer.py:765] (2/8) Epoch 6, batch 2000, train_loss[loss=3.591, NarTop10Accuracy=0.6123, over 6147.00 frames. ], tot_loss[loss=3.583, NarTop10Accuracy=0.6086, over 5986.07 frames. ], batch size: 51, lr: 1.34e-02
2024-08-06 15:42:53,669 INFO [trainer.py:765] (2/8) Epoch 6, batch 2100, train_loss[loss=3.335, NarTop10Accuracy=0.6677, over 4935.00 frames. ], tot_loss[loss=3.576, NarTop10Accuracy=0.61, over 5988.71 frames. ], batch size: 5, lr: 1.33e-02
2024-08-06 15:43:18,978 INFO [trainer.py:765] (2/8) Epoch 6, batch 2200, train_loss[loss=3.826, NarTop10Accuracy=0.5588, over 7410.00 frames. ], tot_loss[loss=3.571, NarTop10Accuracy=0.6107, over 6021.80 frames. ], batch size: 31, lr: 1.33e-02
2024-08-06 15:43:44,105 INFO [trainer.py:765] (2/8) Epoch 6, batch 2300, train_loss[loss=3.416, NarTop10Accuracy=0.6425, over 5784.00 frames. ], tot_loss[loss=3.569, NarTop10Accuracy=0.6112, over 6016.38 frames. ], batch size: 9, lr: 1.33e-02
2024-08-06 15:44:08,620 INFO [trainer.py:765] (2/8) Epoch 6, batch 2400, train_loss[loss=3.412, NarTop10Accuracy=0.6444, over 5118.00 frames. ], tot_loss[loss=3.545, NarTop10Accuracy=0.6163, over 5782.93 frames. ], batch size: 7, lr: 1.32e-02
2024-08-06 15:44:32,132 INFO [trainer.py:765] (2/8) Epoch 6, batch 2500, train_loss[loss=3.5, NarTop10Accuracy=0.616, over 5727.00 frames. ], tot_loss[loss=3.52, NarTop10Accuracy=0.621, over 5485.14 frames. ], batch size: 8, lr: 1.32e-02
2024-08-06 15:44:51,803 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 15:45:58,043 INFO [trainer.py:765] (2/8) Epoch 7, batch 100, train_loss[loss=3.201, NarTop10Accuracy=0.6889, over 7209.00 frames. ], tot_loss[loss=3.544, NarTop10Accuracy=0.6164, over 2377.07 frames. ], batch size: 31, lr: 1.24e-02
2024-08-06 15:46:33,614 INFO [trainer.py:765] (2/8) Epoch 7, batch 200, train_loss[loss=3.371, NarTop10Accuracy=0.6507, over 6720.00 frames. ], tot_loss[loss=3.533, NarTop10Accuracy=0.6188, over 3856.40 frames. ], batch size: 17, lr: 1.23e-02
2024-08-06 15:47:03,247 INFO [trainer.py:765] (2/8) Epoch 7, batch 300, train_loss[loss=3.685, NarTop10Accuracy=0.5859, over 7095.00 frames. ], tot_loss[loss=3.544, NarTop10Accuracy=0.6166, over 4663.41 frames. ], batch size: 22, lr: 1.23e-02
2024-08-06 15:47:34,495 INFO [trainer.py:765] (2/8) Epoch 7, batch 400, train_loss[loss=3.595, NarTop10Accuracy=0.6045, over 5073.00 frames. ], tot_loss[loss=3.531, NarTop10Accuracy=0.6192, over 5111.09 frames. ], batch size: 7, lr: 1.23e-02
2024-08-06 15:48:13,730 INFO [trainer.py:765] (2/8) Epoch 7, batch 500, train_loss[loss=3.574, NarTop10Accuracy=0.6112, over 6189.00 frames. ], tot_loss[loss=3.522, NarTop10Accuracy=0.621, over 5389.93 frames. ], batch size: 11, lr: 1.22e-02
2024-08-06 15:48:26,369 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 15:48:34,533 INFO [trainer.py:811] (2/8) Epoch 7, validation: loss=3.326, NarTop10Accuracy=0.6612, over 1905321.00 frames. 
2024-08-06 15:48:34,534 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29439MB
2024-08-06 15:48:35,078 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.466e+02 1.860e+02 2.018e+02 2.241e+02 5.111e+02, threshold=4.035e+02, percent-clipped=0.3
2024-08-06 15:48:52,719 INFO [trainer.py:765] (2/8) Epoch 7, batch 600, train_loss[loss=3.291, NarTop10Accuracy=0.6684, over 5583.00 frames. ], tot_loss[loss=3.525, NarTop10Accuracy=0.6202, over 5649.61 frames. ], batch size: 9, lr: 1.22e-02
2024-08-06 15:49:24,911 INFO [trainer.py:765] (2/8) Epoch 7, batch 700, train_loss[loss=3.847, NarTop10Accuracy=0.5536, over 5091.00 frames. ], tot_loss[loss=3.518, NarTop10Accuracy=0.6214, over 5729.10 frames. ], batch size: 6, lr: 1.21e-02
2024-08-06 15:50:04,380 INFO [trainer.py:765] (2/8) Epoch 7, batch 800, train_loss[loss=3.133, NarTop10Accuracy=0.6999, over 4341.00 frames. ], tot_loss[loss=3.501, NarTop10Accuracy=0.6247, over 5774.88 frames. ], batch size: 5, lr: 1.21e-02
2024-08-06 15:50:34,547 INFO [trainer.py:765] (2/8) Epoch 7, batch 900, train_loss[loss=3.368, NarTop10Accuracy=0.6589, over 6291.00 frames. ], tot_loss[loss=3.493, NarTop10Accuracy=0.6267, over 5799.57 frames. ], batch size: 13, lr: 1.21e-02
2024-08-06 15:51:07,154 INFO [trainer.py:765] (2/8) Epoch 7, batch 1000, train_loss[loss=3.289, NarTop10Accuracy=0.6801, over 6672.00 frames. ], tot_loss[loss=3.486, NarTop10Accuracy=0.6279, over 5910.37 frames. ], batch size: 14, lr: 1.20e-02
2024-08-06 15:51:51,757 INFO [trainer.py:765] (2/8) Epoch 7, batch 1100, train_loss[loss=3.368, NarTop10Accuracy=0.6537, over 6801.00 frames. ], tot_loss[loss=3.496, NarTop10Accuracy=0.6262, over 5941.90 frames. ], batch size: 17, lr: 1.20e-02
2024-08-06 15:52:22,699 INFO [trainer.py:765] (2/8) Epoch 7, batch 1200, train_loss[loss=3.452, NarTop10Accuracy=0.6371, over 7476.00 frames. ], tot_loss[loss=3.487, NarTop10Accuracy=0.6279, over 5936.90 frames. ], batch size: 31, lr: 1.20e-02
2024-08-06 15:52:52,006 INFO [trainer.py:765] (2/8) Epoch 7, batch 1300, train_loss[loss=3.473, NarTop10Accuracy=0.6316, over 5223.00 frames. ], tot_loss[loss=3.489, NarTop10Accuracy=0.6277, over 5996.03 frames. ], batch size: 6, lr: 1.19e-02
2024-08-06 15:53:33,841 INFO [trainer.py:765] (2/8) Epoch 7, batch 1400, train_loss[loss=3.398, NarTop10Accuracy=0.6558, over 5988.00 frames. ], tot_loss[loss=3.498, NarTop10Accuracy=0.6256, over 6025.01 frames. ], batch size: 11, lr: 1.19e-02
2024-08-06 15:54:04,599 INFO [trainer.py:765] (2/8) Epoch 7, batch 1500, train_loss[loss=3.743, NarTop10Accuracy=0.5684, over 6297.00 frames. ], tot_loss[loss=3.475, NarTop10Accuracy=0.6303, over 5963.36 frames. ], batch size: 50, lr: 1.19e-02
2024-08-06 15:54:32,384 INFO [trainer.py:765] (2/8) Epoch 7, batch 1600, train_loss[loss=3.704, NarTop10Accuracy=0.5812, over 7071.00 frames. ], tot_loss[loss=3.472, NarTop10Accuracy=0.6312, over 5937.90 frames. ], batch size: 22, lr: 1.19e-02
2024-08-06 15:54:59,054 INFO [trainer.py:765] (2/8) Epoch 7, batch 1700, train_loss[loss=3.787, NarTop10Accuracy=0.5661, over 6210.00 frames. ], tot_loss[loss=3.491, NarTop10Accuracy=0.6271, over 5914.91 frames. ], batch size: 13, lr: 1.18e-02
2024-08-06 15:55:25,511 INFO [trainer.py:765] (2/8) Epoch 7, batch 1800, train_loss[loss=3.855, NarTop10Accuracy=0.55, over 6987.00 frames. ], tot_loss[loss=3.486, NarTop10Accuracy=0.6277, over 5961.14 frames. ], batch size: 22, lr: 1.18e-02
2024-08-06 15:55:52,081 INFO [trainer.py:765] (2/8) Epoch 7, batch 1900, train_loss[loss=3.394, NarTop10Accuracy=0.6572, over 5796.00 frames. ], tot_loss[loss=3.504, NarTop10Accuracy=0.624, over 6009.36 frames. ], batch size: 52, lr: 1.18e-02
2024-08-06 15:56:17,590 INFO [trainer.py:765] (2/8) Epoch 7, batch 2000, train_loss[loss=3.698, NarTop10Accuracy=0.5891, over 5979.00 frames. ], tot_loss[loss=3.505, NarTop10Accuracy=0.6241, over 5982.85 frames. ], batch size: 51, lr: 1.17e-02
2024-08-06 15:56:42,855 INFO [trainer.py:765] (2/8) Epoch 7, batch 2100, train_loss[loss=3.648, NarTop10Accuracy=0.5912, over 3870.00 frames. ], tot_loss[loss=3.489, NarTop10Accuracy=0.6276, over 5962.24 frames. ], batch size: 4, lr: 1.17e-02
2024-08-06 15:57:08,078 INFO [trainer.py:765] (2/8) Epoch 7, batch 2200, train_loss[loss=3.461, NarTop10Accuracy=0.632, over 7194.00 frames. ], tot_loss[loss=3.504, NarTop10Accuracy=0.6244, over 5993.34 frames. ], batch size: 31, lr: 1.17e-02
2024-08-06 15:57:33,177 INFO [trainer.py:765] (2/8) Epoch 7, batch 2300, train_loss[loss=3.245, NarTop10Accuracy=0.6782, over 5703.00 frames. ], tot_loss[loss=3.503, NarTop10Accuracy=0.6245, over 6010.10 frames. ], batch size: 9, lr: 1.16e-02
2024-08-06 15:57:57,618 INFO [trainer.py:765] (2/8) Epoch 7, batch 2400, train_loss[loss=3.212, NarTop10Accuracy=0.6778, over 5178.00 frames. ], tot_loss[loss=3.49, NarTop10Accuracy=0.627, over 5791.00 frames. ], batch size: 7, lr: 1.16e-02
2024-08-06 15:58:21,087 INFO [trainer.py:765] (2/8) Epoch 7, batch 2500, train_loss[loss=3.8, NarTop10Accuracy=0.5652, over 5271.00 frames. ], tot_loss[loss=3.466, NarTop10Accuracy=0.6318, over 5486.17 frames. ], batch size: 7, lr: 1.16e-02
2024-08-06 15:58:31,564 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 15:58:39,769 INFO [trainer.py:811] (2/8) Epoch 7, validation: loss=3.381, NarTop10Accuracy=0.6488, over 1905321.00 frames. 
2024-08-06 15:58:39,770 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29439MB
2024-08-06 15:58:40,220 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.471e+02 1.831e+02 1.996e+02 2.207e+02 5.229e+02, threshold=3.992e+02, percent-clipped=0.2
2024-08-06 15:58:49,130 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 15:59:52,876 INFO [trainer.py:765] (2/8) Epoch 8, batch 100, train_loss[loss=3.65, NarTop10Accuracy=0.5927, over 7314.00 frames. ], tot_loss[loss=3.447, NarTop10Accuracy=0.6361, over 2357.64 frames. ], batch size: 31, lr: 1.09e-02
2024-08-06 16:00:27,881 INFO [trainer.py:765] (2/8) Epoch 8, batch 200, train_loss[loss=3.318, NarTop10Accuracy=0.67, over 6930.00 frames. ], tot_loss[loss=3.471, NarTop10Accuracy=0.6318, over 3842.62 frames. ], batch size: 17, lr: 1.09e-02
2024-08-06 16:00:58,562 INFO [trainer.py:765] (2/8) Epoch 8, batch 300, train_loss[loss=3.236, NarTop10Accuracy=0.6792, over 7137.00 frames. ], tot_loss[loss=3.464, NarTop10Accuracy=0.6334, over 4636.31 frames. ], batch size: 22, lr: 1.08e-02
2024-08-06 16:01:29,759 INFO [trainer.py:765] (2/8) Epoch 8, batch 400, train_loss[loss=3.733, NarTop10Accuracy=0.5707, over 5076.00 frames. ], tot_loss[loss=3.471, NarTop10Accuracy=0.6319, over 5096.96 frames. ], batch size: 7, lr: 1.08e-02
2024-08-06 16:02:04,065 INFO [trainer.py:765] (2/8) Epoch 8, batch 500, train_loss[loss=3.877, NarTop10Accuracy=0.5398, over 6189.00 frames. ], tot_loss[loss=3.458, NarTop10Accuracy=0.6343, over 5397.83 frames. ], batch size: 11, lr: 1.08e-02
2024-08-06 16:02:41,836 INFO [trainer.py:765] (2/8) Epoch 8, batch 600, train_loss[loss=3.282, NarTop10Accuracy=0.6803, over 5697.00 frames. ], tot_loss[loss=3.475, NarTop10Accuracy=0.6303, over 5662.16 frames. ], batch size: 9, lr: 1.08e-02
2024-08-06 16:03:11,499 INFO [trainer.py:765] (2/8) Epoch 8, batch 700, train_loss[loss=3.653, NarTop10Accuracy=0.5788, over 5208.00 frames. ], tot_loss[loss=3.481, NarTop10Accuracy=0.6289, over 5749.77 frames. ], batch size: 6, lr: 1.07e-02
2024-08-06 16:03:50,084 INFO [trainer.py:765] (2/8) Epoch 8, batch 800, train_loss[loss=3.522, NarTop10Accuracy=0.6176, over 4368.00 frames. ], tot_loss[loss=3.472, NarTop10Accuracy=0.6308, over 5786.35 frames. ], batch size: 5, lr: 1.07e-02
2024-08-06 16:04:27,587 INFO [trainer.py:765] (2/8) Epoch 8, batch 900, train_loss[loss=3.259, NarTop10Accuracy=0.6728, over 6252.00 frames. ], tot_loss[loss=3.457, NarTop10Accuracy=0.6337, over 5794.24 frames. ], batch size: 13, lr: 1.07e-02
2024-08-06 16:04:57,466 INFO [trainer.py:765] (2/8) Epoch 8, batch 1000, train_loss[loss=3.846, NarTop10Accuracy=0.5503, over 6768.00 frames. ], tot_loss[loss=3.443, NarTop10Accuracy=0.6364, over 5896.25 frames. ], batch size: 14, lr: 1.07e-02
2024-08-06 16:05:37,293 INFO [trainer.py:765] (2/8) Epoch 8, batch 1100, train_loss[loss=3.587, NarTop10Accuracy=0.6102, over 6732.00 frames. ], tot_loss[loss=3.433, NarTop10Accuracy=0.6387, over 5933.18 frames. ], batch size: 17, lr: 1.06e-02
2024-08-06 16:06:15,859 INFO [trainer.py:765] (2/8) Epoch 8, batch 1200, train_loss[loss=3.393, NarTop10Accuracy=0.6447, over 7011.00 frames. ], tot_loss[loss=3.445, NarTop10Accuracy=0.6361, over 5919.75 frames. ], batch size: 31, lr: 1.06e-02
2024-08-06 16:06:45,187 INFO [trainer.py:765] (2/8) Epoch 8, batch 1300, train_loss[loss=3.268, NarTop10Accuracy=0.6839, over 5061.00 frames. ], tot_loss[loss=3.432, NarTop10Accuracy=0.6384, over 5984.27 frames. ], batch size: 6, lr: 1.06e-02
2024-08-06 16:07:24,235 INFO [trainer.py:765] (2/8) Epoch 8, batch 1400, train_loss[loss=3.407, NarTop10Accuracy=0.6464, over 6024.00 frames. ], tot_loss[loss=3.438, NarTop10Accuracy=0.6372, over 6008.49 frames. ], batch size: 11, lr: 1.05e-02
2024-08-06 16:07:52,168 INFO [trainer.py:765] (2/8) Epoch 8, batch 1500, train_loss[loss=3.41, NarTop10Accuracy=0.6464, over 6423.00 frames. ], tot_loss[loss=3.425, NarTop10Accuracy=0.64, over 5941.71 frames. ], batch size: 50, lr: 1.05e-02
2024-08-06 16:08:19,948 INFO [trainer.py:765] (2/8) Epoch 8, batch 1600, train_loss[loss=3.213, NarTop10Accuracy=0.6815, over 7410.00 frames. ], tot_loss[loss=3.426, NarTop10Accuracy=0.6404, over 5928.69 frames. ], batch size: 23, lr: 1.05e-02
2024-08-06 16:08:46,617 INFO [trainer.py:765] (2/8) Epoch 8, batch 1700, train_loss[loss=3.392, NarTop10Accuracy=0.6457, over 6189.00 frames. ], tot_loss[loss=3.43, NarTop10Accuracy=0.6394, over 5917.59 frames. ], batch size: 13, lr: 1.05e-02
2024-08-06 16:09:13,105 INFO [trainer.py:765] (2/8) Epoch 8, batch 1800, train_loss[loss=3.384, NarTop10Accuracy=0.6599, over 7194.00 frames. ], tot_loss[loss=3.423, NarTop10Accuracy=0.6412, over 5977.79 frames. ], batch size: 22, lr: 1.04e-02
2024-08-06 16:09:39,635 INFO [trainer.py:765] (2/8) Epoch 8, batch 1900, train_loss[loss=3.787, NarTop10Accuracy=0.563, over 6129.00 frames. ], tot_loss[loss=3.418, NarTop10Accuracy=0.6423, over 6035.17 frames. ], batch size: 54, lr: 1.04e-02
2024-08-06 16:09:56,939 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 16:10:04,970 INFO [trainer.py:811] (2/8) Epoch 8, validation: loss=3.282, NarTop10Accuracy=0.6699, over 1905321.00 frames. 
2024-08-06 16:10:04,970 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29439MB
2024-08-06 16:10:05,469 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.411e+02 1.814e+02 1.981e+02 2.158e+02 5.862e+02, threshold=3.962e+02, percent-clipped=0.1
2024-08-06 16:10:13,202 INFO [trainer.py:765] (2/8) Epoch 8, batch 2000, train_loss[loss=4, NarTop10Accuracy=0.5311, over 6636.00 frames. ], tot_loss[loss=3.424, NarTop10Accuracy=0.6414, over 6001.51 frames. ], batch size: 51, lr: 1.04e-02
2024-08-06 16:10:38,513 INFO [trainer.py:765] (2/8) Epoch 8, batch 2100, train_loss[loss=3.04, NarTop10Accuracy=0.701, over 3867.00 frames. ], tot_loss[loss=3.414, NarTop10Accuracy=0.6431, over 5985.20 frames. ], batch size: 4, lr: 1.04e-02
2024-08-06 16:11:03,746 INFO [trainer.py:765] (2/8) Epoch 8, batch 2200, train_loss[loss=3.519, NarTop10Accuracy=0.6214, over 7326.00 frames. ], tot_loss[loss=3.422, NarTop10Accuracy=0.641, over 6019.75 frames. ], batch size: 31, lr: 1.04e-02
2024-08-06 16:11:28,903 INFO [trainer.py:765] (2/8) Epoch 8, batch 2300, train_loss[loss=3.761, NarTop10Accuracy=0.565, over 5745.00 frames. ], tot_loss[loss=3.443, NarTop10Accuracy=0.637, over 6012.04 frames. ], batch size: 9, lr: 1.03e-02
2024-08-06 16:11:53,091 INFO [trainer.py:765] (2/8) Epoch 8, batch 2400, train_loss[loss=3.303, NarTop10Accuracy=0.6556, over 5181.00 frames. ], tot_loss[loss=3.425, NarTop10Accuracy=0.6408, over 5771.45 frames. ], batch size: 7, lr: 1.03e-02
2024-08-06 16:12:16,443 INFO [trainer.py:765] (2/8) Epoch 8, batch 2500, train_loss[loss=3.398, NarTop10Accuracy=0.6403, over 5295.00 frames. ], tot_loss[loss=3.412, NarTop10Accuracy=0.6427, over 5463.72 frames. ], batch size: 7, lr: 1.03e-02
2024-08-06 16:12:36,206 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 16:13:37,514 INFO [trainer.py:765] (2/8) Epoch 9, batch 100, train_loss[loss=3.098, NarTop10Accuracy=0.7039, over 7470.00 frames. ], tot_loss[loss=3.375, NarTop10Accuracy=0.6514, over 2364.57 frames. ], batch size: 32, lr: 9.72e-03
2024-08-06 16:14:14,440 INFO [trainer.py:765] (2/8) Epoch 9, batch 200, train_loss[loss=3.614, NarTop10Accuracy=0.5992, over 6843.00 frames. ], tot_loss[loss=3.372, NarTop10Accuracy=0.6522, over 3846.38 frames. ], batch size: 17, lr: 9.70e-03
2024-08-06 16:14:44,507 INFO [trainer.py:765] (2/8) Epoch 9, batch 300, train_loss[loss=3.404, NarTop10Accuracy=0.6464, over 6966.00 frames. ], tot_loss[loss=3.375, NarTop10Accuracy=0.6509, over 4649.89 frames. ], batch size: 22, lr: 9.68e-03
2024-08-06 16:15:14,914 INFO [trainer.py:765] (2/8) Epoch 9, batch 400, train_loss[loss=3.147, NarTop10Accuracy=0.6944, over 5256.00 frames. ], tot_loss[loss=3.366, NarTop10Accuracy=0.6524, over 5096.10 frames. ], batch size: 7, lr: 9.65e-03
2024-08-06 16:15:50,335 INFO [trainer.py:765] (2/8) Epoch 9, batch 500, train_loss[loss=2.965, NarTop10Accuracy=0.7181, over 6213.00 frames. ], tot_loss[loss=3.353, NarTop10Accuracy=0.655, over 5388.85 frames. ], batch size: 11, lr: 9.63e-03
2024-08-06 16:16:23,972 INFO [trainer.py:765] (2/8) Epoch 9, batch 600, train_loss[loss=3.688, NarTop10Accuracy=0.5887, over 5703.00 frames. ], tot_loss[loss=3.347, NarTop10Accuracy=0.6567, over 5652.41 frames. ], batch size: 9, lr: 9.61e-03
2024-08-06 16:16:57,145 INFO [trainer.py:765] (2/8) Epoch 9, batch 700, train_loss[loss=3.254, NarTop10Accuracy=0.6749, over 5097.00 frames. ], tot_loss[loss=3.355, NarTop10Accuracy=0.6548, over 5715.28 frames. ], batch size: 6, lr: 9.59e-03
2024-08-06 16:17:32,051 INFO [trainer.py:765] (2/8) Epoch 9, batch 800, train_loss[loss=2.937, NarTop10Accuracy=0.7324, over 4335.00 frames. ], tot_loss[loss=3.381, NarTop10Accuracy=0.649, over 5761.00 frames. ], batch size: 5, lr: 9.57e-03
2024-08-06 16:18:07,815 INFO [trainer.py:765] (2/8) Epoch 9, batch 900, train_loss[loss=3.21, NarTop10Accuracy=0.6927, over 6300.00 frames. ], tot_loss[loss=3.373, NarTop10Accuracy=0.6512, over 5778.08 frames. ], batch size: 13, lr: 9.55e-03
2024-08-06 16:18:39,344 INFO [trainer.py:765] (2/8) Epoch 9, batch 1000, train_loss[loss=3.237, NarTop10Accuracy=0.6778, over 6663.00 frames. ], tot_loss[loss=3.389, NarTop10Accuracy=0.6476, over 5886.77 frames. ], batch size: 14, lr: 9.53e-03
2024-08-06 16:19:15,381 INFO [trainer.py:765] (2/8) Epoch 9, batch 1100, train_loss[loss=3.446, NarTop10Accuracy=0.6364, over 6930.00 frames. ], tot_loss[loss=3.398, NarTop10Accuracy=0.6459, over 5927.57 frames. ], batch size: 17, lr: 9.50e-03
2024-08-06 16:19:53,877 INFO [trainer.py:765] (2/8) Epoch 9, batch 1200, train_loss[loss=3.873, NarTop10Accuracy=0.5367, over 7119.00 frames. ], tot_loss[loss=3.401, NarTop10Accuracy=0.6453, over 5930.61 frames. ], batch size: 31, lr: 9.48e-03
2024-08-06 16:20:24,906 INFO [trainer.py:765] (2/8) Epoch 9, batch 1300, train_loss[loss=3.075, NarTop10Accuracy=0.7022, over 4956.00 frames. ], tot_loss[loss=3.399, NarTop10Accuracy=0.6457, over 5992.94 frames. ], batch size: 6, lr: 9.46e-03
2024-08-06 16:20:56,579 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 16:21:04,483 INFO [trainer.py:811] (2/8) Epoch 9, validation: loss=3.266, NarTop10Accuracy=0.6725, over 1905321.00 frames. 
2024-08-06 16:21:04,484 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29439MB
2024-08-06 16:21:05,035 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.473e+02 1.808e+02 1.967e+02 2.142e+02 6.126e+02, threshold=3.935e+02, percent-clipped=0.5
2024-08-06 16:21:06,690 INFO [trainer.py:765] (2/8) Epoch 9, batch 1400, train_loss[loss=3.605, NarTop10Accuracy=0.5912, over 6102.00 frames. ], tot_loss[loss=3.401, NarTop10Accuracy=0.6453, over 6017.86 frames. ], batch size: 11, lr: 9.44e-03
2024-08-06 16:21:38,895 INFO [trainer.py:765] (2/8) Epoch 9, batch 1500, train_loss[loss=3.331, NarTop10Accuracy=0.6623, over 5991.00 frames. ], tot_loss[loss=3.383, NarTop10Accuracy=0.6493, over 5947.74 frames. ], batch size: 50, lr: 9.42e-03
2024-08-06 16:22:06,720 INFO [trainer.py:765] (2/8) Epoch 9, batch 1600, train_loss[loss=3.272, NarTop10Accuracy=0.667, over 7158.00 frames. ], tot_loss[loss=3.373, NarTop10Accuracy=0.6514, over 5947.62 frames. ], batch size: 22, lr: 9.40e-03
2024-08-06 16:22:33,470 INFO [trainer.py:765] (2/8) Epoch 9, batch 1700, train_loss[loss=3.573, NarTop10Accuracy=0.6074, over 6597.00 frames. ], tot_loss[loss=3.389, NarTop10Accuracy=0.6475, over 5928.31 frames. ], batch size: 14, lr: 9.38e-03
2024-08-06 16:23:00,063 INFO [trainer.py:765] (2/8) Epoch 9, batch 1800, train_loss[loss=3.124, NarTop10Accuracy=0.7072, over 7044.00 frames. ], tot_loss[loss=3.378, NarTop10Accuracy=0.6498, over 5995.89 frames. ], batch size: 22, lr: 9.36e-03
2024-08-06 16:23:26,783 INFO [trainer.py:765] (2/8) Epoch 9, batch 1900, train_loss[loss=3.476, NarTop10Accuracy=0.6356, over 5694.00 frames. ], tot_loss[loss=3.388, NarTop10Accuracy=0.6478, over 6030.93 frames. ], batch size: 51, lr: 9.34e-03
2024-08-06 16:23:52,485 INFO [trainer.py:765] (2/8) Epoch 9, batch 2000, train_loss[loss=3.901, NarTop10Accuracy=0.5528, over 6429.00 frames. ], tot_loss[loss=3.387, NarTop10Accuracy=0.6479, over 6003.25 frames. ], batch size: 50, lr: 9.32e-03
2024-08-06 16:24:17,965 INFO [trainer.py:765] (2/8) Epoch 9, batch 2100, train_loss[loss=3.114, NarTop10Accuracy=0.7111, over 4794.00 frames. ], tot_loss[loss=3.391, NarTop10Accuracy=0.6474, over 5984.90 frames. ], batch size: 5, lr: 9.30e-03
2024-08-06 16:24:43,421 INFO [trainer.py:765] (2/8) Epoch 9, batch 2200, train_loss[loss=3.563, NarTop10Accuracy=0.6062, over 7080.00 frames. ], tot_loss[loss=3.397, NarTop10Accuracy=0.6457, over 6017.63 frames. ], batch size: 31, lr: 9.28e-03
2024-08-06 16:25:08,720 INFO [trainer.py:765] (2/8) Epoch 9, batch 2300, train_loss[loss=3.284, NarTop10Accuracy=0.6664, over 5733.00 frames. ], tot_loss[loss=3.407, NarTop10Accuracy=0.6438, over 6031.20 frames. ], batch size: 9, lr: 9.26e-03
2024-08-06 16:25:33,163 INFO [trainer.py:765] (2/8) Epoch 9, batch 2400, train_loss[loss=3.178, NarTop10Accuracy=0.6843, over 5025.00 frames. ], tot_loss[loss=3.396, NarTop10Accuracy=0.6457, over 5789.17 frames. ], batch size: 7, lr: 9.25e-03
2024-08-06 16:25:56,767 INFO [trainer.py:765] (2/8) Epoch 9, batch 2500, train_loss[loss=3.166, NarTop10Accuracy=0.6887, over 5109.00 frames. ], tot_loss[loss=3.366, NarTop10Accuracy=0.6517, over 5483.12 frames. ], batch size: 7, lr: 9.23e-03
2024-08-06 16:26:16,445 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 16:27:19,583 INFO [trainer.py:765] (2/8) Epoch 10, batch 100, train_loss[loss=3.171, NarTop10Accuracy=0.6944, over 7434.00 frames. ], tot_loss[loss=3.361, NarTop10Accuracy=0.6531, over 2376.66 frames. ], batch size: 31, lr: 8.76e-03
2024-08-06 16:27:52,627 INFO [trainer.py:765] (2/8) Epoch 10, batch 200, train_loss[loss=3.176, NarTop10Accuracy=0.6932, over 6945.00 frames. ], tot_loss[loss=3.346, NarTop10Accuracy=0.6563, over 3863.17 frames. ], batch size: 17, lr: 8.74e-03
2024-08-06 16:28:23,056 INFO [trainer.py:765] (2/8) Epoch 10, batch 300, train_loss[loss=3.096, NarTop10Accuracy=0.7083, over 7011.00 frames. ], tot_loss[loss=3.348, NarTop10Accuracy=0.6565, over 4655.11 frames. ], batch size: 22, lr: 8.72e-03
2024-08-06 16:28:59,199 INFO [trainer.py:765] (2/8) Epoch 10, batch 400, train_loss[loss=3.303, NarTop10Accuracy=0.6667, over 5241.00 frames. ], tot_loss[loss=3.341, NarTop10Accuracy=0.6581, over 5093.26 frames. ], batch size: 7, lr: 8.71e-03
2024-08-06 16:29:29,217 INFO [trainer.py:765] (2/8) Epoch 10, batch 500, train_loss[loss=3.024, NarTop10Accuracy=0.7325, over 6192.00 frames. ], tot_loss[loss=3.338, NarTop10Accuracy=0.6587, over 5384.92 frames. ], batch size: 11, lr: 8.69e-03
2024-08-06 16:30:02,764 INFO [trainer.py:765] (2/8) Epoch 10, batch 600, train_loss[loss=3.473, NarTop10Accuracy=0.6288, over 5679.00 frames. ], tot_loss[loss=3.345, NarTop10Accuracy=0.657, over 5656.91 frames. ], batch size: 9, lr: 8.67e-03
2024-08-06 16:30:34,264 INFO [trainer.py:765] (2/8) Epoch 10, batch 700, train_loss[loss=3.377, NarTop10Accuracy=0.6489, over 5127.00 frames. ], tot_loss[loss=3.352, NarTop10Accuracy=0.6557, over 5718.01 frames. ], batch size: 6, lr: 8.65e-03
2024-08-06 16:31:09,842 INFO [trainer.py:765] (2/8) Epoch 10, batch 800, train_loss[loss=3.482, NarTop10Accuracy=0.6228, over 4317.00 frames. ], tot_loss[loss=3.361, NarTop10Accuracy=0.6538, over 5791.86 frames. ], batch size: 5, lr: 8.64e-03
2024-08-06 16:31:16,256 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 16:31:24,565 INFO [trainer.py:811] (2/8) Epoch 10, validation: loss=3.184, NarTop10Accuracy=0.6898, over 1905321.00 frames. 
2024-08-06 16:31:24,566 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29440MB
2024-08-06 16:31:25,154 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.434e+02 1.851e+02 2.012e+02 2.196e+02 4.599e+02, threshold=4.024e+02, percent-clipped=0.1
2024-08-06 16:31:50,345 INFO [trainer.py:765] (2/8) Epoch 10, batch 900, train_loss[loss=3.262, NarTop10Accuracy=0.6703, over 6225.00 frames. ], tot_loss[loss=3.335, NarTop10Accuracy=0.659, over 5797.12 frames. ], batch size: 13, lr: 8.62e-03
2024-08-06 16:32:28,589 INFO [trainer.py:765] (2/8) Epoch 10, batch 1000, train_loss[loss=3.139, NarTop10Accuracy=0.7036, over 6198.00 frames. ], tot_loss[loss=3.346, NarTop10Accuracy=0.6571, over 5882.64 frames. ], batch size: 13, lr: 8.60e-03
2024-08-06 16:33:06,376 INFO [trainer.py:765] (2/8) Epoch 10, batch 1100, train_loss[loss=3.122, NarTop10Accuracy=0.7081, over 6675.00 frames. ], tot_loss[loss=3.352, NarTop10Accuracy=0.656, over 5931.93 frames. ], batch size: 17, lr: 8.59e-03
2024-08-06 16:33:40,960 INFO [trainer.py:765] (2/8) Epoch 10, batch 1200, train_loss[loss=3.218, NarTop10Accuracy=0.6755, over 7344.00 frames. ], tot_loss[loss=3.34, NarTop10Accuracy=0.6582, over 5937.65 frames. ], batch size: 31, lr: 8.57e-03
2024-08-06 16:34:16,170 INFO [trainer.py:765] (2/8) Epoch 10, batch 1300, train_loss[loss=3.144, NarTop10Accuracy=0.6946, over 5193.00 frames. ], tot_loss[loss=3.335, NarTop10Accuracy=0.6588, over 6000.12 frames. ], batch size: 6, lr: 8.55e-03
2024-08-06 16:34:51,201 INFO [trainer.py:765] (2/8) Epoch 10, batch 1400, train_loss[loss=3.408, NarTop10Accuracy=0.6516, over 6084.00 frames. ], tot_loss[loss=3.364, NarTop10Accuracy=0.6528, over 6006.16 frames. ], batch size: 11, lr: 8.54e-03
2024-08-06 16:35:22,159 INFO [trainer.py:765] (2/8) Epoch 10, batch 1500, train_loss[loss=3.641, NarTop10Accuracy=0.5921, over 5775.00 frames. ], tot_loss[loss=3.349, NarTop10Accuracy=0.6561, over 5956.58 frames. ], batch size: 50, lr: 8.52e-03
2024-08-06 16:35:50,136 INFO [trainer.py:765] (2/8) Epoch 10, batch 1600, train_loss[loss=3.681, NarTop10Accuracy=0.5796, over 7044.00 frames. ], tot_loss[loss=3.337, NarTop10Accuracy=0.6588, over 5920.95 frames. ], batch size: 22, lr: 8.50e-03
2024-08-06 16:36:16,976 INFO [trainer.py:765] (2/8) Epoch 10, batch 1700, train_loss[loss=3.409, NarTop10Accuracy=0.6385, over 6246.00 frames. ], tot_loss[loss=3.344, NarTop10Accuracy=0.657, over 5915.52 frames. ], batch size: 13, lr: 8.49e-03
2024-08-06 16:36:43,647 INFO [trainer.py:765] (2/8) Epoch 10, batch 1800, train_loss[loss=3.193, NarTop10Accuracy=0.6854, over 7140.00 frames. ], tot_loss[loss=3.334, NarTop10Accuracy=0.6591, over 5976.02 frames. ], batch size: 22, lr: 8.47e-03
2024-08-06 16:37:10,290 INFO [trainer.py:765] (2/8) Epoch 10, batch 1900, train_loss[loss=3.274, NarTop10Accuracy=0.6773, over 5433.00 frames. ], tot_loss[loss=3.331, NarTop10Accuracy=0.6599, over 6021.99 frames. ], batch size: 50, lr: 8.45e-03
2024-08-06 16:37:36,089 INFO [trainer.py:765] (2/8) Epoch 10, batch 2000, train_loss[loss=3.182, NarTop10Accuracy=0.696, over 6018.00 frames. ], tot_loss[loss=3.318, NarTop10Accuracy=0.6622, over 5993.82 frames. ], batch size: 50, lr: 8.44e-03
2024-08-06 16:38:01,650 INFO [trainer.py:765] (2/8) Epoch 10, batch 2100, train_loss[loss=3.488, NarTop10Accuracy=0.6282, over 4068.00 frames. ], tot_loss[loss=3.331, NarTop10Accuracy=0.6597, over 5958.03 frames. ], batch size: 4, lr: 8.42e-03
2024-08-06 16:38:27,120 INFO [trainer.py:765] (2/8) Epoch 10, batch 2200, train_loss[loss=3.714, NarTop10Accuracy=0.5809, over 7443.00 frames. ], tot_loss[loss=3.337, NarTop10Accuracy=0.6583, over 5999.22 frames. ], batch size: 31, lr: 8.41e-03
2024-08-06 16:38:52,447 INFO [trainer.py:765] (2/8) Epoch 10, batch 2300, train_loss[loss=3.281, NarTop10Accuracy=0.6707, over 5625.00 frames. ], tot_loss[loss=3.347, NarTop10Accuracy=0.6567, over 6011.96 frames. ], batch size: 9, lr: 8.39e-03
2024-08-06 16:39:17,005 INFO [trainer.py:765] (2/8) Epoch 10, batch 2400, train_loss[loss=3.314, NarTop10Accuracy=0.6661, over 5082.00 frames. ], tot_loss[loss=3.32, NarTop10Accuracy=0.6618, over 5761.29 frames. ], batch size: 7, lr: 8.37e-03
2024-08-06 16:39:40,801 INFO [trainer.py:765] (2/8) Epoch 10, batch 2500, train_loss[loss=3.776, NarTop10Accuracy=0.5644, over 5172.00 frames. ], tot_loss[loss=3.292, NarTop10Accuracy=0.6669, over 5455.58 frames. ], batch size: 7, lr: 8.36e-03
2024-08-06 16:40:00,680 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 16:41:06,234 INFO [trainer.py:765] (2/8) Epoch 11, batch 100, train_loss[loss=3.64, NarTop10Accuracy=0.5948, over 7401.00 frames. ], tot_loss[loss=3.362, NarTop10Accuracy=0.6542, over 2357.55 frames. ], batch size: 32, lr: 7.97e-03
2024-08-06 16:41:39,020 INFO [trainer.py:765] (2/8) Epoch 11, batch 200, train_loss[loss=3.69, NarTop10Accuracy=0.5708, over 6924.00 frames. ], tot_loss[loss=3.335, NarTop10Accuracy=0.6589, over 3842.15 frames. ], batch size: 17, lr: 7.95e-03
2024-08-06 16:41:53,189 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 16:42:01,355 INFO [trainer.py:811] (2/8) Epoch 11, validation: loss=3.116, NarTop10Accuracy=0.7034, over 1905321.00 frames. 
2024-08-06 16:42:01,356 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29440MB
2024-08-06 16:42:01,879 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.526e+02 1.889e+02 2.046e+02 2.249e+02 5.417e+02, threshold=4.093e+02, percent-clipped=0.2
2024-08-06 16:42:17,975 INFO [trainer.py:765] (2/8) Epoch 11, batch 300, train_loss[loss=3.142, NarTop10Accuracy=0.7099, over 7149.00 frames. ], tot_loss[loss=3.307, NarTop10Accuracy=0.6646, over 4661.17 frames. ], batch size: 22, lr: 7.94e-03
2024-08-06 16:42:55,153 INFO [trainer.py:765] (2/8) Epoch 11, batch 400, train_loss[loss=3.284, NarTop10Accuracy=0.6671, over 5304.00 frames. ], tot_loss[loss=3.303, NarTop10Accuracy=0.6651, over 5126.48 frames. ], batch size: 7, lr: 7.92e-03
2024-08-06 16:43:25,718 INFO [trainer.py:765] (2/8) Epoch 11, batch 500, train_loss[loss=3.082, NarTop10Accuracy=0.7177, over 6081.00 frames. ], tot_loss[loss=3.295, NarTop10Accuracy=0.6666, over 5378.25 frames. ], batch size: 11, lr: 7.91e-03
2024-08-06 16:44:02,241 INFO [trainer.py:765] (2/8) Epoch 11, batch 600, train_loss[loss=3.5, NarTop10Accuracy=0.6222, over 5670.00 frames. ], tot_loss[loss=3.306, NarTop10Accuracy=0.6646, over 5647.51 frames. ], batch size: 9, lr: 7.89e-03
2024-08-06 16:44:35,715 INFO [trainer.py:765] (2/8) Epoch 11, batch 700, train_loss[loss=3.634, NarTop10Accuracy=0.5926, over 5106.00 frames. ], tot_loss[loss=3.3, NarTop10Accuracy=0.666, over 5719.74 frames. ], batch size: 6, lr: 7.88e-03
2024-08-06 16:45:10,467 INFO [trainer.py:765] (2/8) Epoch 11, batch 800, train_loss[loss=3.169, NarTop10Accuracy=0.6987, over 5037.00 frames. ], tot_loss[loss=3.315, NarTop10Accuracy=0.6619, over 5772.58 frames. ], batch size: 6, lr: 7.86e-03
2024-08-06 16:45:46,456 INFO [trainer.py:765] (2/8) Epoch 11, batch 900, train_loss[loss=3.599, NarTop10Accuracy=0.596, over 6309.00 frames. ], tot_loss[loss=3.308, NarTop10Accuracy=0.6637, over 5787.45 frames. ], batch size: 13, lr: 7.85e-03
2024-08-06 16:46:20,310 INFO [trainer.py:765] (2/8) Epoch 11, batch 1000, train_loss[loss=3.376, NarTop10Accuracy=0.6457, over 6570.00 frames. ], tot_loss[loss=3.305, NarTop10Accuracy=0.6645, over 5907.05 frames. ], batch size: 14, lr: 7.84e-03
2024-08-06 16:46:53,456 INFO [trainer.py:765] (2/8) Epoch 11, batch 1100, train_loss[loss=3.053, NarTop10Accuracy=0.7184, over 6834.00 frames. ], tot_loss[loss=3.293, NarTop10Accuracy=0.6667, over 5921.86 frames. ], batch size: 17, lr: 7.82e-03
2024-08-06 16:47:33,030 INFO [trainer.py:765] (2/8) Epoch 11, batch 1200, train_loss[loss=3.515, NarTop10Accuracy=0.6194, over 7188.00 frames. ], tot_loss[loss=3.303, NarTop10Accuracy=0.665, over 5912.99 frames. ], batch size: 31, lr: 7.81e-03
2024-08-06 16:48:06,481 INFO [trainer.py:765] (2/8) Epoch 11, batch 1300, train_loss[loss=3.181, NarTop10Accuracy=0.6832, over 5274.00 frames. ], tot_loss[loss=3.313, NarTop10Accuracy=0.6629, over 5991.11 frames. ], batch size: 6, lr: 7.79e-03
2024-08-06 16:48:41,353 INFO [trainer.py:765] (2/8) Epoch 11, batch 1400, train_loss[loss=3.364, NarTop10Accuracy=0.657, over 6081.00 frames. ], tot_loss[loss=3.33, NarTop10Accuracy=0.6592, over 6029.09 frames. ], batch size: 11, lr: 7.78e-03
2024-08-06 16:49:09,344 INFO [trainer.py:765] (2/8) Epoch 11, batch 1500, train_loss[loss=3.242, NarTop10Accuracy=0.6767, over 6225.00 frames. ], tot_loss[loss=3.325, NarTop10Accuracy=0.6599, over 5958.97 frames. ], batch size: 50, lr: 7.77e-03
2024-08-06 16:49:37,102 INFO [trainer.py:765] (2/8) Epoch 11, batch 1600, train_loss[loss=3.319, NarTop10Accuracy=0.6611, over 7176.00 frames. ], tot_loss[loss=3.315, NarTop10Accuracy=0.6626, over 5924.50 frames. ], batch size: 22, lr: 7.75e-03
2024-08-06 16:50:03,791 INFO [trainer.py:765] (2/8) Epoch 11, batch 1700, train_loss[loss=3.383, NarTop10Accuracy=0.6411, over 6726.00 frames. ], tot_loss[loss=3.304, NarTop10Accuracy=0.6647, over 5916.83 frames. ], batch size: 14, lr: 7.74e-03
2024-08-06 16:50:30,352 INFO [trainer.py:765] (2/8) Epoch 11, batch 1800, train_loss[loss=3.377, NarTop10Accuracy=0.6476, over 7323.00 frames. ], tot_loss[loss=3.318, NarTop10Accuracy=0.6621, over 5988.05 frames. ], batch size: 22, lr: 7.72e-03
2024-08-06 16:50:56,820 INFO [trainer.py:765] (2/8) Epoch 11, batch 1900, train_loss[loss=3.872, NarTop10Accuracy=0.5435, over 6246.00 frames. ], tot_loss[loss=3.327, NarTop10Accuracy=0.6603, over 6028.77 frames. ], batch size: 51, lr: 7.71e-03
2024-08-06 16:51:22,404 INFO [trainer.py:765] (2/8) Epoch 11, batch 2000, train_loss[loss=3.816, NarTop10Accuracy=0.5611, over 5883.00 frames. ], tot_loss[loss=3.316, NarTop10Accuracy=0.662, over 6022.26 frames. ], batch size: 51, lr: 7.70e-03
2024-08-06 16:51:47,793 INFO [trainer.py:765] (2/8) Epoch 11, batch 2100, train_loss[loss=2.934, NarTop10Accuracy=0.7354, over 4833.00 frames. ], tot_loss[loss=3.312, NarTop10Accuracy=0.6632, over 5996.87 frames. ], batch size: 5, lr: 7.68e-03
2024-08-06 16:52:13,117 INFO [trainer.py:765] (2/8) Epoch 11, batch 2200, train_loss[loss=3.286, NarTop10Accuracy=0.6718, over 7359.00 frames. ], tot_loss[loss=3.311, NarTop10Accuracy=0.6635, over 6010.62 frames. ], batch size: 31, lr: 7.67e-03
2024-08-06 16:52:23,898 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 16:52:32,079 INFO [trainer.py:811] (2/8) Epoch 11, validation: loss=3.101, NarTop10Accuracy=0.7058, over 1905321.00 frames. 
2024-08-06 16:52:32,079 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29440MB
2024-08-06 16:52:32,593 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.491e+02 1.920e+02 2.088e+02 2.244e+02 3.599e+02, threshold=4.177e+02, percent-clipped=0.0
2024-08-06 16:52:46,445 INFO [trainer.py:765] (2/8) Epoch 11, batch 2300, train_loss[loss=3.245, NarTop10Accuracy=0.6779, over 5577.00 frames. ], tot_loss[loss=3.316, NarTop10Accuracy=0.6625, over 6014.71 frames. ], batch size: 9, lr: 7.66e-03
2024-08-06 16:53:10,887 INFO [trainer.py:765] (2/8) Epoch 11, batch 2400, train_loss[loss=3.527, NarTop10Accuracy=0.6189, over 5307.00 frames. ], tot_loss[loss=3.305, NarTop10Accuracy=0.6647, over 5776.01 frames. ], batch size: 7, lr: 7.64e-03
2024-08-06 16:53:34,371 INFO [trainer.py:765] (2/8) Epoch 11, batch 2500, train_loss[loss=3.486, NarTop10Accuracy=0.6217, over 5127.00 frames. ], tot_loss[loss=3.3, NarTop10Accuracy=0.6658, over 5471.61 frames. ], batch size: 7, lr: 7.63e-03
2024-08-06 16:53:54,343 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 16:54:58,525 INFO [trainer.py:765] (2/8) Epoch 12, batch 100, train_loss[loss=3.66, NarTop10Accuracy=0.5895, over 6948.00 frames. ], tot_loss[loss=3.295, NarTop10Accuracy=0.6667, over 2373.39 frames. ], batch size: 31, lr: 7.30e-03
2024-08-06 16:55:32,432 INFO [trainer.py:765] (2/8) Epoch 12, batch 200, train_loss[loss=3.174, NarTop10Accuracy=0.6971, over 6849.00 frames. ], tot_loss[loss=3.266, NarTop10Accuracy=0.6732, over 3865.50 frames. ], batch size: 17, lr: 7.29e-03
2024-08-06 16:56:05,096 INFO [trainer.py:765] (2/8) Epoch 12, batch 300, train_loss[loss=2.981, NarTop10Accuracy=0.7338, over 7053.00 frames. ], tot_loss[loss=3.25, NarTop10Accuracy=0.6763, over 4651.69 frames. ], batch size: 22, lr: 7.27e-03
2024-08-06 16:56:36,426 INFO [trainer.py:765] (2/8) Epoch 12, batch 400, train_loss[loss=3.049, NarTop10Accuracy=0.7118, over 5211.00 frames. ], tot_loss[loss=3.265, NarTop10Accuracy=0.6732, over 5093.35 frames. ], batch size: 7, lr: 7.26e-03
2024-08-06 16:57:10,503 INFO [trainer.py:765] (2/8) Epoch 12, batch 500, train_loss[loss=3.655, NarTop10Accuracy=0.5957, over 6093.00 frames. ], tot_loss[loss=3.275, NarTop10Accuracy=0.6708, over 5367.25 frames. ], batch size: 11, lr: 7.25e-03
2024-08-06 16:57:45,484 INFO [trainer.py:765] (2/8) Epoch 12, batch 600, train_loss[loss=2.976, NarTop10Accuracy=0.7358, over 5763.00 frames. ], tot_loss[loss=3.269, NarTop10Accuracy=0.6723, over 5646.74 frames. ], batch size: 9, lr: 7.24e-03
2024-08-06 16:58:17,005 INFO [trainer.py:765] (2/8) Epoch 12, batch 700, train_loss[loss=3.76, NarTop10Accuracy=0.5692, over 5229.00 frames. ], tot_loss[loss=3.284, NarTop10Accuracy=0.669, over 5716.16 frames. ], batch size: 6, lr: 7.22e-03
2024-08-06 16:58:53,469 INFO [trainer.py:765] (2/8) Epoch 12, batch 800, train_loss[loss=3.306, NarTop10Accuracy=0.6614, over 5043.00 frames. ], tot_loss[loss=3.297, NarTop10Accuracy=0.6668, over 5782.92 frames. ], batch size: 6, lr: 7.21e-03
2024-08-06 16:59:27,206 INFO [trainer.py:765] (2/8) Epoch 12, batch 900, train_loss[loss=3.132, NarTop10Accuracy=0.6954, over 6042.00 frames. ], tot_loss[loss=3.277, NarTop10Accuracy=0.6707, over 5792.02 frames. ], batch size: 13, lr: 7.20e-03
2024-08-06 17:00:01,574 INFO [trainer.py:765] (2/8) Epoch 12, batch 1000, train_loss[loss=3.109, NarTop10Accuracy=0.7046, over 6186.00 frames. ], tot_loss[loss=3.286, NarTop10Accuracy=0.6686, over 5898.89 frames. ], batch size: 13, lr: 7.19e-03
2024-08-06 17:00:39,189 INFO [trainer.py:765] (2/8) Epoch 12, batch 1100, train_loss[loss=3.604, NarTop10Accuracy=0.6023, over 6804.00 frames. ], tot_loss[loss=3.299, NarTop10Accuracy=0.6656, over 5948.11 frames. ], batch size: 17, lr: 7.18e-03
2024-08-06 17:01:13,963 INFO [trainer.py:765] (2/8) Epoch 12, batch 1200, train_loss[loss=3.126, NarTop10Accuracy=0.7013, over 7071.00 frames. ], tot_loss[loss=3.266, NarTop10Accuracy=0.6724, over 5941.18 frames. ], batch size: 31, lr: 7.17e-03
2024-08-06 17:01:48,108 INFO [trainer.py:765] (2/8) Epoch 12, batch 1300, train_loss[loss=3.284, NarTop10Accuracy=0.6688, over 5049.00 frames. ], tot_loss[loss=3.282, NarTop10Accuracy=0.669, over 6008.06 frames. ], batch size: 6, lr: 7.15e-03
2024-08-06 17:02:22,323 INFO [trainer.py:765] (2/8) Epoch 12, batch 1400, train_loss[loss=3.709, NarTop10Accuracy=0.5846, over 6234.00 frames. ], tot_loss[loss=3.29, NarTop10Accuracy=0.6679, over 6035.28 frames. ], batch size: 11, lr: 7.14e-03
2024-08-06 17:02:52,877 INFO [trainer.py:765] (2/8) Epoch 12, batch 1500, train_loss[loss=3.418, NarTop10Accuracy=0.6441, over 5928.00 frames. ], tot_loss[loss=3.273, NarTop10Accuracy=0.6715, over 5978.85 frames. ], batch size: 51, lr: 7.13e-03
2024-08-06 17:03:20,691 INFO [trainer.py:765] (2/8) Epoch 12, batch 1600, train_loss[loss=3.195, NarTop10Accuracy=0.6836, over 7197.00 frames. ], tot_loss[loss=3.278, NarTop10Accuracy=0.67, over 5936.95 frames. ], batch size: 22, lr: 7.12e-03
2024-08-06 17:03:38,297 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 17:03:46,474 INFO [trainer.py:811] (2/8) Epoch 12, validation: loss=3.054, NarTop10Accuracy=0.7153, over 1905321.00 frames. 
2024-08-06 17:03:46,474 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29440MB
2024-08-06 17:03:46,988 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.507e+02 1.899e+02 2.078e+02 2.276e+02 5.455e+02, threshold=4.157e+02, percent-clipped=0.1
2024-08-06 17:03:55,602 INFO [trainer.py:765] (2/8) Epoch 12, batch 1700, train_loss[loss=3.365, NarTop10Accuracy=0.6533, over 6132.00 frames. ], tot_loss[loss=3.285, NarTop10Accuracy=0.6692, over 5922.69 frames. ], batch size: 13, lr: 7.11e-03
2024-08-06 17:04:22,119 INFO [trainer.py:765] (2/8) Epoch 12, batch 1800, train_loss[loss=3.772, NarTop10Accuracy=0.5763, over 7302.00 frames. ], tot_loss[loss=3.279, NarTop10Accuracy=0.6699, over 5984.71 frames. ], batch size: 22, lr: 7.10e-03
2024-08-06 17:04:48,590 INFO [trainer.py:765] (2/8) Epoch 12, batch 1900, train_loss[loss=3.222, NarTop10Accuracy=0.6813, over 6159.00 frames. ], tot_loss[loss=3.278, NarTop10Accuracy=0.6703, over 6014.28 frames. ], batch size: 52, lr: 7.08e-03
2024-08-06 17:05:14,196 INFO [trainer.py:765] (2/8) Epoch 12, batch 2000, train_loss[loss=3.484, NarTop10Accuracy=0.6259, over 6438.00 frames. ], tot_loss[loss=3.265, NarTop10Accuracy=0.6726, over 6009.92 frames. ], batch size: 50, lr: 7.07e-03
2024-08-06 17:05:39,467 INFO [trainer.py:765] (2/8) Epoch 12, batch 2100, train_loss[loss=3.357, NarTop10Accuracy=0.6574, over 4797.00 frames. ], tot_loss[loss=3.271, NarTop10Accuracy=0.6714, over 5999.48 frames. ], batch size: 5, lr: 7.06e-03
2024-08-06 17:06:04,689 INFO [trainer.py:765] (2/8) Epoch 12, batch 2200, train_loss[loss=3.445, NarTop10Accuracy=0.6362, over 7461.00 frames. ], tot_loss[loss=3.289, NarTop10Accuracy=0.6676, over 6032.09 frames. ], batch size: 31, lr: 7.05e-03
2024-08-06 17:06:29,846 INFO [trainer.py:765] (2/8) Epoch 12, batch 2300, train_loss[loss=3.446, NarTop10Accuracy=0.631, over 6225.00 frames. ], tot_loss[loss=3.285, NarTop10Accuracy=0.6688, over 6034.30 frames. ], batch size: 10, lr: 7.04e-03
2024-08-06 17:06:54,199 INFO [trainer.py:765] (2/8) Epoch 12, batch 2400, train_loss[loss=3.218, NarTop10Accuracy=0.6906, over 5085.00 frames. ], tot_loss[loss=3.269, NarTop10Accuracy=0.6717, over 5774.91 frames. ], batch size: 7, lr: 7.03e-03
2024-08-06 17:07:17,645 INFO [trainer.py:765] (2/8) Epoch 12, batch 2500, train_loss[loss=3.245, NarTop10Accuracy=0.6787, over 5235.00 frames. ], tot_loss[loss=3.25, NarTop10Accuracy=0.6754, over 5485.59 frames. ], batch size: 7, lr: 7.02e-03
2024-08-06 17:07:37,546 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 17:08:40,079 INFO [trainer.py:765] (2/8) Epoch 13, batch 100, train_loss[loss=3.054, NarTop10Accuracy=0.7246, over 7458.00 frames. ], tot_loss[loss=3.285, NarTop10Accuracy=0.6677, over 2376.43 frames. ], batch size: 31, lr: 6.73e-03
2024-08-06 17:09:14,120 INFO [trainer.py:765] (2/8) Epoch 13, batch 200, train_loss[loss=2.938, NarTop10Accuracy=0.7438, over 6852.00 frames. ], tot_loss[loss=3.286, NarTop10Accuracy=0.6685, over 3862.95 frames. ], batch size: 17, lr: 6.72e-03
2024-08-06 17:09:46,276 INFO [trainer.py:765] (2/8) Epoch 13, batch 300, train_loss[loss=3.509, NarTop10Accuracy=0.6166, over 7014.00 frames. ], tot_loss[loss=3.261, NarTop10Accuracy=0.6734, over 4651.97 frames. ], batch size: 22, lr: 6.71e-03
2024-08-06 17:10:19,164 INFO [trainer.py:765] (2/8) Epoch 13, batch 400, train_loss[loss=2.915, NarTop10Accuracy=0.7455, over 5103.00 frames. ], tot_loss[loss=3.25, NarTop10Accuracy=0.6755, over 5103.00 frames. ], batch size: 7, lr: 6.70e-03
2024-08-06 17:10:49,336 INFO [trainer.py:765] (2/8) Epoch 13, batch 500, train_loss[loss=3.184, NarTop10Accuracy=0.6949, over 6237.00 frames. ], tot_loss[loss=3.235, NarTop10Accuracy=0.6783, over 5398.09 frames. ], batch size: 11, lr: 6.69e-03
2024-08-06 17:11:26,244 INFO [trainer.py:765] (2/8) Epoch 13, batch 600, train_loss[loss=2.991, NarTop10Accuracy=0.7232, over 5754.00 frames. ], tot_loss[loss=3.231, NarTop10Accuracy=0.6792, over 5662.55 frames. ], batch size: 9, lr: 6.68e-03
2024-08-06 17:11:57,381 INFO [trainer.py:765] (2/8) Epoch 13, batch 700, train_loss[loss=3.259, NarTop10Accuracy=0.6698, over 5157.00 frames. ], tot_loss[loss=3.242, NarTop10Accuracy=0.6771, over 5724.27 frames. ], batch size: 6, lr: 6.67e-03
2024-08-06 17:12:33,442 INFO [trainer.py:765] (2/8) Epoch 13, batch 800, train_loss[loss=3.041, NarTop10Accuracy=0.7212, over 5016.00 frames. ], tot_loss[loss=3.25, NarTop10Accuracy=0.6757, over 5780.18 frames. ], batch size: 6, lr: 6.66e-03
2024-08-06 17:13:10,032 INFO [trainer.py:765] (2/8) Epoch 13, batch 900, train_loss[loss=3.235, NarTop10Accuracy=0.6824, over 6576.00 frames. ], tot_loss[loss=3.24, NarTop10Accuracy=0.6778, over 5792.83 frames. ], batch size: 14, lr: 6.65e-03
2024-08-06 17:13:41,442 INFO [trainer.py:765] (2/8) Epoch 13, batch 1000, train_loss[loss=3.648, NarTop10Accuracy=0.5925, over 6675.00 frames. ], tot_loss[loss=3.245, NarTop10Accuracy=0.677, over 5887.75 frames. ], batch size: 14, lr: 6.64e-03
2024-08-06 17:14:15,537 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 17:14:23,644 INFO [trainer.py:811] (2/8) Epoch 13, validation: loss=3.099, NarTop10Accuracy=0.7062, over 1905321.00 frames. 
2024-08-06 17:14:23,645 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29440MB
2024-08-06 17:14:24,470 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.548e+02 1.948e+02 2.091e+02 2.295e+02 3.353e+02, threshold=4.181e+02, percent-clipped=0.0
2024-08-06 17:14:26,697 INFO [trainer.py:765] (2/8) Epoch 13, batch 1100, train_loss[loss=3.579, NarTop10Accuracy=0.6117, over 6747.00 frames. ], tot_loss[loss=3.254, NarTop10Accuracy=0.675, over 5914.06 frames. ], batch size: 17, lr: 6.63e-03
2024-08-06 17:15:03,475 INFO [trainer.py:765] (2/8) Epoch 13, batch 1200, train_loss[loss=3.402, NarTop10Accuracy=0.6461, over 7275.00 frames. ], tot_loss[loss=3.256, NarTop10Accuracy=0.6745, over 5906.73 frames. ], batch size: 31, lr: 6.62e-03
2024-08-06 17:15:35,514 INFO [trainer.py:765] (2/8) Epoch 13, batch 1300, train_loss[loss=3.165, NarTop10Accuracy=0.705, over 5106.00 frames. ], tot_loss[loss=3.261, NarTop10Accuracy=0.6736, over 5978.93 frames. ], batch size: 6, lr: 6.61e-03
2024-08-06 17:16:11,782 INFO [trainer.py:765] (2/8) Epoch 13, batch 1400, train_loss[loss=3.148, NarTop10Accuracy=0.6944, over 6027.00 frames. ], tot_loss[loss=3.265, NarTop10Accuracy=0.6726, over 6002.90 frames. ], batch size: 11, lr: 6.60e-03
2024-08-06 17:16:39,787 INFO [trainer.py:765] (2/8) Epoch 13, batch 1500, train_loss[loss=3.493, NarTop10Accuracy=0.6257, over 6648.00 frames. ], tot_loss[loss=3.257, NarTop10Accuracy=0.6741, over 5954.51 frames. ], batch size: 50, lr: 6.59e-03
2024-08-06 17:17:07,603 INFO [trainer.py:765] (2/8) Epoch 13, batch 1600, train_loss[loss=3.034, NarTop10Accuracy=0.7147, over 6969.00 frames. ], tot_loss[loss=3.264, NarTop10Accuracy=0.6732, over 5922.48 frames. ], batch size: 22, lr: 6.58e-03
2024-08-06 17:17:34,259 INFO [trainer.py:765] (2/8) Epoch 13, batch 1700, train_loss[loss=3.185, NarTop10Accuracy=0.6916, over 6201.00 frames. ], tot_loss[loss=3.264, NarTop10Accuracy=0.6731, over 5915.81 frames. ], batch size: 13, lr: 6.57e-03
2024-08-06 17:18:00,761 INFO [trainer.py:765] (2/8) Epoch 13, batch 1800, train_loss[loss=3.11, NarTop10Accuracy=0.706, over 6915.00 frames. ], tot_loss[loss=3.252, NarTop10Accuracy=0.6754, over 5983.15 frames. ], batch size: 22, lr: 6.56e-03
2024-08-06 17:18:27,244 INFO [trainer.py:765] (2/8) Epoch 13, batch 1900, train_loss[loss=3.563, NarTop10Accuracy=0.6137, over 5625.00 frames. ], tot_loss[loss=3.251, NarTop10Accuracy=0.6756, over 6021.57 frames. ], batch size: 50, lr: 6.55e-03
2024-08-06 17:18:52,777 INFO [trainer.py:765] (2/8) Epoch 13, batch 2000, train_loss[loss=3.581, NarTop10Accuracy=0.6056, over 5772.00 frames. ], tot_loss[loss=3.236, NarTop10Accuracy=0.6787, over 5989.22 frames. ], batch size: 50, lr: 6.54e-03
2024-08-06 17:19:18,147 INFO [trainer.py:765] (2/8) Epoch 13, batch 2100, train_loss[loss=2.776, NarTop10Accuracy=0.7706, over 4866.00 frames. ], tot_loss[loss=3.233, NarTop10Accuracy=0.6793, over 5977.29 frames. ], batch size: 5, lr: 6.53e-03
2024-08-06 17:19:43,412 INFO [trainer.py:765] (2/8) Epoch 13, batch 2200, train_loss[loss=3.467, NarTop10Accuracy=0.6339, over 7323.00 frames. ], tot_loss[loss=3.247, NarTop10Accuracy=0.6764, over 6034.04 frames. ], batch size: 31, lr: 6.52e-03
2024-08-06 17:20:08,542 INFO [trainer.py:765] (2/8) Epoch 13, batch 2300, train_loss[loss=3.622, NarTop10Accuracy=0.5986, over 5652.00 frames. ], tot_loss[loss=3.266, NarTop10Accuracy=0.673, over 6043.13 frames. ], batch size: 9, lr: 6.51e-03
2024-08-06 17:20:32,939 INFO [trainer.py:765] (2/8) Epoch 13, batch 2400, train_loss[loss=3.595, NarTop10Accuracy=0.6067, over 5721.00 frames. ], tot_loss[loss=3.237, NarTop10Accuracy=0.6792, over 5792.22 frames. ], batch size: 8, lr: 6.50e-03
2024-08-06 17:20:56,408 INFO [trainer.py:765] (2/8) Epoch 13, batch 2500, train_loss[loss=3.529, NarTop10Accuracy=0.6231, over 5043.00 frames. ], tot_loss[loss=3.227, NarTop10Accuracy=0.6806, over 5490.73 frames. ], batch size: 7, lr: 6.49e-03
2024-08-06 17:21:16,079 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 17:22:19,315 INFO [trainer.py:765] (2/8) Epoch 14, batch 100, train_loss[loss=3.057, NarTop10Accuracy=0.7174, over 7182.00 frames. ], tot_loss[loss=3.215, NarTop10Accuracy=0.6834, over 2358.00 frames. ], batch size: 31, lr: 6.24e-03
2024-08-06 17:22:50,378 INFO [trainer.py:765] (2/8) Epoch 14, batch 200, train_loss[loss=3.149, NarTop10Accuracy=0.7058, over 6723.00 frames. ], tot_loss[loss=3.239, NarTop10Accuracy=0.6782, over 3848.09 frames. ], batch size: 17, lr: 6.23e-03
2024-08-06 17:23:23,879 INFO [trainer.py:765] (2/8) Epoch 14, batch 300, train_loss[loss=3.199, NarTop10Accuracy=0.6858, over 7278.00 frames. ], tot_loss[loss=3.21, NarTop10Accuracy=0.6843, over 4662.98 frames. ], batch size: 22, lr: 6.22e-03
2024-08-06 17:23:57,484 INFO [trainer.py:765] (2/8) Epoch 14, batch 400, train_loss[loss=2.88, NarTop10Accuracy=0.742, over 5040.00 frames. ], tot_loss[loss=3.229, NarTop10Accuracy=0.6804, over 5111.33 frames. ], batch size: 7, lr: 6.22e-03
2024-08-06 17:24:32,113 INFO [trainer.py:765] (2/8) Epoch 14, batch 500, train_loss[loss=3.355, NarTop10Accuracy=0.6582, over 6129.00 frames. ], tot_loss[loss=3.232, NarTop10Accuracy=0.6794, over 5376.10 frames. ], batch size: 11, lr: 6.21e-03
2024-08-06 17:24:36,213 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 17:24:44,275 INFO [trainer.py:811] (2/8) Epoch 14, validation: loss=3.004, NarTop10Accuracy=0.726, over 1905321.00 frames. 
2024-08-06 17:24:44,276 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29440MB
2024-08-06 17:24:44,823 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.601e+02 1.969e+02 2.114e+02 2.287e+02 4.406e+02, threshold=4.227e+02, percent-clipped=0.1
2024-08-06 17:25:12,914 INFO [trainer.py:765] (2/8) Epoch 14, batch 600, train_loss[loss=3.031, NarTop10Accuracy=0.7175, over 5781.00 frames. ], tot_loss[loss=3.236, NarTop10Accuracy=0.6784, over 5647.77 frames. ], batch size: 9, lr: 6.20e-03
2024-08-06 17:25:48,548 INFO [trainer.py:765] (2/8) Epoch 14, batch 700, train_loss[loss=3.293, NarTop10Accuracy=0.659, over 4980.00 frames. ], tot_loss[loss=3.223, NarTop10Accuracy=0.6808, over 5720.73 frames. ], batch size: 6, lr: 6.19e-03
2024-08-06 17:26:25,279 INFO [trainer.py:765] (2/8) Epoch 14, batch 800, train_loss[loss=3.068, NarTop10Accuracy=0.719, over 5076.00 frames. ], tot_loss[loss=3.207, NarTop10Accuracy=0.6842, over 5776.22 frames. ], batch size: 6, lr: 6.18e-03
2024-08-06 17:26:57,659 INFO [trainer.py:765] (2/8) Epoch 14, batch 900, train_loss[loss=3.34, NarTop10Accuracy=0.6505, over 6333.00 frames. ], tot_loss[loss=3.204, NarTop10Accuracy=0.6845, over 5795.83 frames. ], batch size: 13, lr: 6.17e-03
2024-08-06 17:27:31,716 INFO [trainer.py:765] (2/8) Epoch 14, batch 1000, train_loss[loss=3.404, NarTop10Accuracy=0.6487, over 6207.00 frames. ], tot_loss[loss=3.224, NarTop10Accuracy=0.6811, over 5905.89 frames. ], batch size: 13, lr: 6.16e-03
2024-08-06 17:28:11,597 INFO [trainer.py:765] (2/8) Epoch 14, batch 1100, train_loss[loss=3.001, NarTop10Accuracy=0.7232, over 6672.00 frames. ], tot_loss[loss=3.223, NarTop10Accuracy=0.6809, over 5931.86 frames. ], batch size: 17, lr: 6.15e-03
2024-08-06 17:28:40,733 INFO [trainer.py:765] (2/8) Epoch 14, batch 1200, train_loss[loss=3.527, NarTop10Accuracy=0.6177, over 7185.00 frames. ], tot_loss[loss=3.216, NarTop10Accuracy=0.6822, over 5934.10 frames. ], batch size: 31, lr: 6.15e-03
2024-08-06 17:29:16,214 INFO [trainer.py:765] (2/8) Epoch 14, batch 1300, train_loss[loss=3.481, NarTop10Accuracy=0.628, over 5079.00 frames. ], tot_loss[loss=3.221, NarTop10Accuracy=0.6812, over 5989.78 frames. ], batch size: 6, lr: 6.14e-03
2024-08-06 17:29:54,602 INFO [trainer.py:765] (2/8) Epoch 14, batch 1400, train_loss[loss=3.362, NarTop10Accuracy=0.6589, over 5994.00 frames. ], tot_loss[loss=3.228, NarTop10Accuracy=0.6799, over 6021.32 frames. ], batch size: 11, lr: 6.13e-03
2024-08-06 17:30:25,315 INFO [trainer.py:765] (2/8) Epoch 14, batch 1500, train_loss[loss=3.784, NarTop10Accuracy=0.5708, over 6153.00 frames. ], tot_loss[loss=3.236, NarTop10Accuracy=0.6784, over 5957.38 frames. ], batch size: 51, lr: 6.12e-03
2024-08-06 17:30:53,043 INFO [trainer.py:765] (2/8) Epoch 14, batch 1600, train_loss[loss=3.009, NarTop10Accuracy=0.7312, over 7350.00 frames. ], tot_loss[loss=3.224, NarTop10Accuracy=0.6809, over 5930.11 frames. ], batch size: 23, lr: 6.11e-03
2024-08-06 17:31:19,728 INFO [trainer.py:765] (2/8) Epoch 14, batch 1700, train_loss[loss=3.075, NarTop10Accuracy=0.7117, over 6234.00 frames. ], tot_loss[loss=3.208, NarTop10Accuracy=0.6846, over 5920.44 frames. ], batch size: 13, lr: 6.10e-03
2024-08-06 17:31:46,289 INFO [trainer.py:765] (2/8) Epoch 14, batch 1800, train_loss[loss=3.052, NarTop10Accuracy=0.7193, over 6921.00 frames. ], tot_loss[loss=3.194, NarTop10Accuracy=0.6879, over 5987.01 frames. ], batch size: 22, lr: 6.09e-03
2024-08-06 17:32:12,727 INFO [trainer.py:765] (2/8) Epoch 14, batch 1900, train_loss[loss=3.585, NarTop10Accuracy=0.6054, over 5889.00 frames. ], tot_loss[loss=3.211, NarTop10Accuracy=0.6842, over 6028.54 frames. ], batch size: 50, lr: 6.09e-03
2024-08-06 17:32:38,282 INFO [trainer.py:765] (2/8) Epoch 14, batch 2000, train_loss[loss=3.238, NarTop10Accuracy=0.6792, over 6078.00 frames. ], tot_loss[loss=3.221, NarTop10Accuracy=0.6819, over 6002.66 frames. ], batch size: 50, lr: 6.08e-03
2024-08-06 17:33:03,646 INFO [trainer.py:765] (2/8) Epoch 14, batch 2100, train_loss[loss=2.865, NarTop10Accuracy=0.7557, over 3945.00 frames. ], tot_loss[loss=3.225, NarTop10Accuracy=0.681, over 5959.87 frames. ], batch size: 4, lr: 6.07e-03
2024-08-06 17:33:28,999 INFO [trainer.py:765] (2/8) Epoch 14, batch 2200, train_loss[loss=3.18, NarTop10Accuracy=0.6907, over 7398.00 frames. ], tot_loss[loss=3.222, NarTop10Accuracy=0.6821, over 6006.60 frames. ], batch size: 31, lr: 6.06e-03
2024-08-06 17:33:54,087 INFO [trainer.py:765] (2/8) Epoch 14, batch 2300, train_loss[loss=3.03, NarTop10Accuracy=0.7266, over 5763.00 frames. ], tot_loss[loss=3.237, NarTop10Accuracy=0.6787, over 6018.58 frames. ], batch size: 9, lr: 6.05e-03
2024-08-06 17:34:18,535 INFO [trainer.py:765] (2/8) Epoch 14, batch 2400, train_loss[loss=3.041, NarTop10Accuracy=0.7326, over 5109.00 frames. ], tot_loss[loss=3.233, NarTop10Accuracy=0.6791, over 5768.80 frames. ], batch size: 7, lr: 6.04e-03
2024-08-06 17:34:42,116 INFO [trainer.py:765] (2/8) Epoch 14, batch 2500, train_loss[loss=2.971, NarTop10Accuracy=0.7267, over 4989.00 frames. ], tot_loss[loss=3.2, NarTop10Accuracy=0.6856, over 5492.97 frames. ], batch size: 7, lr: 6.04e-03
2024-08-06 17:34:45,395 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 17:34:53,209 INFO [trainer.py:811] (2/8) Epoch 14, validation: loss=3.062, NarTop10Accuracy=0.7136, over 1905321.00 frames. 
2024-08-06 17:34:53,209 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29440MB
2024-08-06 17:34:53,679 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.574e+02 1.975e+02 2.132e+02 2.304e+02 3.875e+02, threshold=4.265e+02, percent-clipped=0.0
2024-08-06 17:35:09,835 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 17:36:11,739 INFO [trainer.py:765] (2/8) Epoch 15, batch 100, train_loss[loss=3.024, NarTop10Accuracy=0.7247, over 7095.00 frames. ], tot_loss[loss=3.218, NarTop10Accuracy=0.6828, over 2364.64 frames. ], batch size: 31, lr: 5.82e-03
2024-08-06 17:36:44,334 INFO [trainer.py:765] (2/8) Epoch 15, batch 200, train_loss[loss=3.464, NarTop10Accuracy=0.619, over 6843.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6873, over 3861.10 frames. ], batch size: 17, lr: 5.81e-03
2024-08-06 17:37:17,715 INFO [trainer.py:765] (2/8) Epoch 15, batch 300, train_loss[loss=3.251, NarTop10Accuracy=0.6644, over 6972.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6868, over 4670.64 frames. ], batch size: 22, lr: 5.80e-03
2024-08-06 17:37:48,904 INFO [trainer.py:765] (2/8) Epoch 15, batch 400, train_loss[loss=2.939, NarTop10Accuracy=0.7421, over 5112.00 frames. ], tot_loss[loss=3.189, NarTop10Accuracy=0.6885, over 5121.35 frames. ], batch size: 7, lr: 5.80e-03
2024-08-06 17:38:22,354 INFO [trainer.py:765] (2/8) Epoch 15, batch 500, train_loss[loss=2.949, NarTop10Accuracy=0.7395, over 6210.00 frames. ], tot_loss[loss=3.186, NarTop10Accuracy=0.6889, over 5392.92 frames. ], batch size: 11, lr: 5.79e-03
2024-08-06 17:38:53,094 INFO [trainer.py:765] (2/8) Epoch 15, batch 600, train_loss[loss=2.877, NarTop10Accuracy=0.7352, over 5715.00 frames. ], tot_loss[loss=3.201, NarTop10Accuracy=0.6857, over 5640.80 frames. ], batch size: 9, lr: 5.78e-03
2024-08-06 17:39:27,922 INFO [trainer.py:765] (2/8) Epoch 15, batch 700, train_loss[loss=2.818, NarTop10Accuracy=0.7607, over 5169.00 frames. ], tot_loss[loss=3.207, NarTop10Accuracy=0.6847, over 5722.14 frames. ], batch size: 6, lr: 5.77e-03
2024-08-06 17:40:05,565 INFO [trainer.py:765] (2/8) Epoch 15, batch 800, train_loss[loss=3.288, NarTop10Accuracy=0.6699, over 4227.00 frames. ], tot_loss[loss=3.229, NarTop10Accuracy=0.68, over 5782.49 frames. ], batch size: 5, lr: 5.76e-03
2024-08-06 17:40:35,791 INFO [trainer.py:765] (2/8) Epoch 15, batch 900, train_loss[loss=3.471, NarTop10Accuracy=0.6213, over 6252.00 frames. ], tot_loss[loss=3.207, NarTop10Accuracy=0.6845, over 5805.97 frames. ], batch size: 13, lr: 5.76e-03
2024-08-06 17:41:11,251 INFO [trainer.py:765] (2/8) Epoch 15, batch 1000, train_loss[loss=3.182, NarTop10Accuracy=0.6959, over 6258.00 frames. ], tot_loss[loss=3.198, NarTop10Accuracy=0.6863, over 5905.07 frames. ], batch size: 13, lr: 5.75e-03
2024-08-06 17:41:46,452 INFO [trainer.py:765] (2/8) Epoch 15, batch 1100, train_loss[loss=3.184, NarTop10Accuracy=0.6961, over 6879.00 frames. ], tot_loss[loss=3.197, NarTop10Accuracy=0.6865, over 5936.53 frames. ], batch size: 17, lr: 5.74e-03
2024-08-06 17:42:19,456 INFO [trainer.py:765] (2/8) Epoch 15, batch 1200, train_loss[loss=3.358, NarTop10Accuracy=0.6594, over 7188.00 frames. ], tot_loss[loss=3.227, NarTop10Accuracy=0.6802, over 5927.74 frames. ], batch size: 31, lr: 5.73e-03
2024-08-06 17:42:54,428 INFO [trainer.py:765] (2/8) Epoch 15, batch 1300, train_loss[loss=2.918, NarTop10Accuracy=0.7297, over 5028.00 frames. ], tot_loss[loss=3.204, NarTop10Accuracy=0.6847, over 5998.60 frames. ], batch size: 6, lr: 5.73e-03
2024-08-06 17:43:26,607 INFO [trainer.py:765] (2/8) Epoch 15, batch 1400, train_loss[loss=3.345, NarTop10Accuracy=0.6584, over 6108.00 frames. ], tot_loss[loss=3.216, NarTop10Accuracy=0.6823, over 6015.64 frames. ], batch size: 11, lr: 5.72e-03
2024-08-06 17:43:56,558 INFO [trainer.py:765] (2/8) Epoch 15, batch 1500, train_loss[loss=3.188, NarTop10Accuracy=0.6949, over 5640.00 frames. ], tot_loss[loss=3.222, NarTop10Accuracy=0.6813, over 5955.51 frames. ], batch size: 50, lr: 5.71e-03
2024-08-06 17:44:24,241 INFO [trainer.py:765] (2/8) Epoch 15, batch 1600, train_loss[loss=3.574, NarTop10Accuracy=0.6004, over 7089.00 frames. ], tot_loss[loss=3.2, NarTop10Accuracy=0.6855, over 5935.59 frames. ], batch size: 22, lr: 5.70e-03
2024-08-06 17:44:50,856 INFO [trainer.py:765] (2/8) Epoch 15, batch 1700, train_loss[loss=2.986, NarTop10Accuracy=0.7221, over 6648.00 frames. ], tot_loss[loss=3.186, NarTop10Accuracy=0.6883, over 5913.57 frames. ], batch size: 14, lr: 5.70e-03
2024-08-06 17:45:17,294 INFO [trainer.py:765] (2/8) Epoch 15, batch 1800, train_loss[loss=3.253, NarTop10Accuracy=0.6725, over 7161.00 frames. ], tot_loss[loss=3.186, NarTop10Accuracy=0.6884, over 5993.56 frames. ], batch size: 22, lr: 5.69e-03
2024-08-06 17:45:43,679 INFO [trainer.py:765] (2/8) Epoch 15, batch 1900, train_loss[loss=3.112, NarTop10Accuracy=0.7068, over 6603.00 frames. ], tot_loss[loss=3.208, NarTop10Accuracy=0.6839, over 6023.54 frames. ], batch size: 52, lr: 5.68e-03
2024-08-06 17:45:53,541 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 17:46:01,743 INFO [trainer.py:811] (2/8) Epoch 15, validation: loss=3.006, NarTop10Accuracy=0.725, over 1905321.00 frames. 
2024-08-06 17:46:01,743 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29440MB
2024-08-06 17:46:02,217 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.631e+02 2.004e+02 2.149e+02 2.324e+02 3.721e+02, threshold=4.298e+02, percent-clipped=0.0
2024-08-06 17:46:17,371 INFO [trainer.py:765] (2/8) Epoch 15, batch 2000, train_loss[loss=3.227, NarTop10Accuracy=0.6779, over 6447.00 frames. ], tot_loss[loss=3.208, NarTop10Accuracy=0.6843, over 5982.31 frames. ], batch size: 51, lr: 5.67e-03
2024-08-06 17:46:42,773 INFO [trainer.py:765] (2/8) Epoch 15, batch 2100, train_loss[loss=3.027, NarTop10Accuracy=0.7203, over 3993.00 frames. ], tot_loss[loss=3.199, NarTop10Accuracy=0.6861, over 5957.40 frames. ], batch size: 4, lr: 5.67e-03
2024-08-06 17:47:08,033 INFO [trainer.py:765] (2/8) Epoch 15, batch 2200, train_loss[loss=3.071, NarTop10Accuracy=0.7199, over 7440.00 frames. ], tot_loss[loss=3.201, NarTop10Accuracy=0.6856, over 5990.05 frames. ], batch size: 31, lr: 5.66e-03
2024-08-06 17:47:33,291 INFO [trainer.py:765] (2/8) Epoch 15, batch 2300, train_loss[loss=3.518, NarTop10Accuracy=0.6198, over 5685.00 frames. ], tot_loss[loss=3.212, NarTop10Accuracy=0.6837, over 6009.55 frames. ], batch size: 9, lr: 5.65e-03
2024-08-06 17:47:57,640 INFO [trainer.py:765] (2/8) Epoch 15, batch 2400, train_loss[loss=3.16, NarTop10Accuracy=0.6872, over 5130.00 frames. ], tot_loss[loss=3.187, NarTop10Accuracy=0.6887, over 5753.09 frames. ], batch size: 7, lr: 5.65e-03
2024-08-06 17:48:21,162 INFO [trainer.py:765] (2/8) Epoch 15, batch 2500, train_loss[loss=3.004, NarTop10Accuracy=0.7217, over 5283.00 frames. ], tot_loss[loss=3.167, NarTop10Accuracy=0.6928, over 5471.66 frames. ], batch size: 7, lr: 5.64e-03
2024-08-06 17:48:41,285 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 17:49:41,221 INFO [trainer.py:765] (2/8) Epoch 16, batch 100, train_loss[loss=3.538, NarTop10Accuracy=0.6179, over 7527.00 frames. ], tot_loss[loss=3.165, NarTop10Accuracy=0.6934, over 2372.92 frames. ], batch size: 31, lr: 5.45e-03
2024-08-06 17:50:12,157 INFO [trainer.py:765] (2/8) Epoch 16, batch 200, train_loss[loss=2.935, NarTop10Accuracy=0.7384, over 6726.00 frames. ], tot_loss[loss=3.211, NarTop10Accuracy=0.6838, over 3845.15 frames. ], batch size: 17, lr: 5.44e-03
2024-08-06 17:50:45,159 INFO [trainer.py:765] (2/8) Epoch 16, batch 300, train_loss[loss=3.156, NarTop10Accuracy=0.7001, over 7128.00 frames. ], tot_loss[loss=3.198, NarTop10Accuracy=0.6865, over 4635.07 frames. ], batch size: 22, lr: 5.43e-03
2024-08-06 17:51:15,976 INFO [trainer.py:765] (2/8) Epoch 16, batch 400, train_loss[loss=3.483, NarTop10Accuracy=0.6231, over 5154.00 frames. ], tot_loss[loss=3.202, NarTop10Accuracy=0.6857, over 5078.40 frames. ], batch size: 7, lr: 5.43e-03
2024-08-06 17:51:50,323 INFO [trainer.py:765] (2/8) Epoch 16, batch 500, train_loss[loss=3.04, NarTop10Accuracy=0.7189, over 6219.00 frames. ], tot_loss[loss=3.187, NarTop10Accuracy=0.6884, over 5359.95 frames. ], batch size: 11, lr: 5.42e-03
2024-08-06 17:52:24,251 INFO [trainer.py:765] (2/8) Epoch 16, batch 600, train_loss[loss=2.854, NarTop10Accuracy=0.7486, over 5712.00 frames. ], tot_loss[loss=3.202, NarTop10Accuracy=0.6857, over 5643.87 frames. ], batch size: 9, lr: 5.41e-03
2024-08-06 17:52:55,386 INFO [trainer.py:765] (2/8) Epoch 16, batch 700, train_loss[loss=2.916, NarTop10Accuracy=0.7607, over 4305.00 frames. ], tot_loss[loss=3.194, NarTop10Accuracy=0.6867, over 5721.16 frames. ], batch size: 5, lr: 5.41e-03
2024-08-06 17:53:33,815 INFO [trainer.py:765] (2/8) Epoch 16, batch 800, train_loss[loss=3.273, NarTop10Accuracy=0.6716, over 5190.00 frames. ], tot_loss[loss=3.185, NarTop10Accuracy=0.6887, over 5772.38 frames. ], batch size: 6, lr: 5.40e-03
2024-08-06 17:54:03,922 INFO [trainer.py:765] (2/8) Epoch 16, batch 900, train_loss[loss=3.462, NarTop10Accuracy=0.6295, over 6531.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6917, over 5801.06 frames. ], batch size: 14, lr: 5.39e-03
2024-08-06 17:54:37,607 INFO [trainer.py:765] (2/8) Epoch 16, batch 1000, train_loss[loss=3.016, NarTop10Accuracy=0.7211, over 6669.00 frames. ], tot_loss[loss=3.17, NarTop10Accuracy=0.6922, over 5905.70 frames. ], batch size: 14, lr: 5.39e-03
2024-08-06 17:55:17,196 INFO [trainer.py:765] (2/8) Epoch 16, batch 1100, train_loss[loss=3.198, NarTop10Accuracy=0.6918, over 6765.00 frames. ], tot_loss[loss=3.194, NarTop10Accuracy=0.687, over 5942.20 frames. ], batch size: 17, lr: 5.38e-03
2024-08-06 17:55:46,209 INFO [trainer.py:765] (2/8) Epoch 16, batch 1200, train_loss[loss=3.472, NarTop10Accuracy=0.63, over 7284.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6859, over 5930.31 frames. ], batch size: 31, lr: 5.37e-03
2024-08-06 17:56:22,775 INFO [trainer.py:765] (2/8) Epoch 16, batch 1300, train_loss[loss=3.454, NarTop10Accuracy=0.6346, over 5025.00 frames. ], tot_loss[loss=3.191, NarTop10Accuracy=0.6874, over 6002.63 frames. ], batch size: 6, lr: 5.37e-03
2024-08-06 17:56:44,648 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 17:56:53,428 INFO [trainer.py:811] (2/8) Epoch 16, validation: loss=3.112, NarTop10Accuracy=0.703, over 1905321.00 frames. 
2024-08-06 17:56:53,429 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29440MB
2024-08-06 17:56:54,007 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.620e+02 1.974e+02 2.136e+02 2.310e+02 5.351e+02, threshold=4.271e+02, percent-clipped=0.2
2024-08-06 17:57:06,171 INFO [trainer.py:765] (2/8) Epoch 16, batch 1400, train_loss[loss=3.14, NarTop10Accuracy=0.6952, over 6084.00 frames. ], tot_loss[loss=3.187, NarTop10Accuracy=0.6884, over 6018.61 frames. ], batch size: 11, lr: 5.36e-03
2024-08-06 17:57:34,033 INFO [trainer.py:765] (2/8) Epoch 16, batch 1500, train_loss[loss=3.358, NarTop10Accuracy=0.6583, over 6501.00 frames. ], tot_loss[loss=3.185, NarTop10Accuracy=0.6887, over 5943.09 frames. ], batch size: 51, lr: 5.35e-03
2024-08-06 17:58:01,774 INFO [trainer.py:765] (2/8) Epoch 16, batch 1600, train_loss[loss=3.066, NarTop10Accuracy=0.7158, over 7119.00 frames. ], tot_loss[loss=3.18, NarTop10Accuracy=0.6898, over 5928.23 frames. ], batch size: 22, lr: 5.35e-03
2024-08-06 17:58:28,475 INFO [trainer.py:765] (2/8) Epoch 16, batch 1700, train_loss[loss=2.998, NarTop10Accuracy=0.7302, over 6255.00 frames. ], tot_loss[loss=3.193, NarTop10Accuracy=0.687, over 5925.14 frames. ], batch size: 13, lr: 5.34e-03
2024-08-06 17:58:54,975 INFO [trainer.py:765] (2/8) Epoch 16, batch 1800, train_loss[loss=3.154, NarTop10Accuracy=0.6926, over 7515.00 frames. ], tot_loss[loss=3.178, NarTop10Accuracy=0.6905, over 5999.60 frames. ], batch size: 23, lr: 5.33e-03
2024-08-06 17:59:21,359 INFO [trainer.py:765] (2/8) Epoch 16, batch 1900, train_loss[loss=3.384, NarTop10Accuracy=0.6452, over 6078.00 frames. ], tot_loss[loss=3.206, NarTop10Accuracy=0.6846, over 6049.91 frames. ], batch size: 50, lr: 5.33e-03
2024-08-06 17:59:46,857 INFO [trainer.py:765] (2/8) Epoch 16, batch 2000, train_loss[loss=3.071, NarTop10Accuracy=0.7184, over 5763.00 frames. ], tot_loss[loss=3.178, NarTop10Accuracy=0.6904, over 6011.37 frames. ], batch size: 53, lr: 5.32e-03
2024-08-06 18:00:12,117 INFO [trainer.py:765] (2/8) Epoch 16, batch 2100, train_loss[loss=3.368, NarTop10Accuracy=0.644, over 3897.00 frames. ], tot_loss[loss=3.202, NarTop10Accuracy=0.6854, over 5965.51 frames. ], batch size: 4, lr: 5.32e-03
2024-08-06 18:00:37,333 INFO [trainer.py:765] (2/8) Epoch 16, batch 2200, train_loss[loss=3.352, NarTop10Accuracy=0.6619, over 7392.00 frames. ], tot_loss[loss=3.213, NarTop10Accuracy=0.6832, over 6006.60 frames. ], batch size: 32, lr: 5.31e-03
2024-08-06 18:01:02,502 INFO [trainer.py:765] (2/8) Epoch 16, batch 2300, train_loss[loss=2.976, NarTop10Accuracy=0.7234, over 5709.00 frames. ], tot_loss[loss=3.216, NarTop10Accuracy=0.6829, over 6002.69 frames. ], batch size: 9, lr: 5.30e-03
2024-08-06 18:01:26,883 INFO [trainer.py:765] (2/8) Epoch 16, batch 2400, train_loss[loss=3.05, NarTop10Accuracy=0.716, over 5145.00 frames. ], tot_loss[loss=3.194, NarTop10Accuracy=0.6871, over 5778.23 frames. ], batch size: 7, lr: 5.30e-03
2024-08-06 18:01:50,406 INFO [trainer.py:765] (2/8) Epoch 16, batch 2500, train_loss[loss=3.034, NarTop10Accuracy=0.724, over 5046.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.6937, over 5473.81 frames. ], batch size: 7, lr: 5.29e-03
2024-08-06 18:02:10,589 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 18:03:08,531 INFO [trainer.py:765] (2/8) Epoch 17, batch 100, train_loss[loss=3.2, NarTop10Accuracy=0.687, over 7176.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.6998, over 2358.63 frames. ], batch size: 31, lr: 5.12e-03
2024-08-06 18:03:45,145 INFO [trainer.py:765] (2/8) Epoch 17, batch 200, train_loss[loss=3.402, NarTop10Accuracy=0.6428, over 6906.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6972, over 3855.26 frames. ], batch size: 17, lr: 5.12e-03
2024-08-06 18:04:19,590 INFO [trainer.py:765] (2/8) Epoch 17, batch 300, train_loss[loss=3.359, NarTop10Accuracy=0.6534, over 7221.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6928, over 4656.74 frames. ], batch size: 22, lr: 5.11e-03
2024-08-06 18:04:48,402 INFO [trainer.py:765] (2/8) Epoch 17, batch 400, train_loss[loss=3.423, NarTop10Accuracy=0.6355, over 5070.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6914, over 5127.32 frames. ], batch size: 7, lr: 5.10e-03
2024-08-06 18:05:24,680 INFO [trainer.py:765] (2/8) Epoch 17, batch 500, train_loss[loss=2.908, NarTop10Accuracy=0.7435, over 6006.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6961, over 5393.74 frames. ], batch size: 11, lr: 5.10e-03
2024-08-06 18:05:58,739 INFO [trainer.py:765] (2/8) Epoch 17, batch 600, train_loss[loss=3.089, NarTop10Accuracy=0.7023, over 5847.00 frames. ], tot_loss[loss=3.165, NarTop10Accuracy=0.6933, over 5652.21 frames. ], batch size: 9, lr: 5.09e-03
2024-08-06 18:06:32,475 INFO [trainer.py:765] (2/8) Epoch 17, batch 700, train_loss[loss=3.083, NarTop10Accuracy=0.7142, over 5199.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6924, over 5729.84 frames. ], batch size: 6, lr: 5.08e-03
2024-08-06 18:07:02,724 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 18:07:10,763 INFO [trainer.py:811] (2/8) Epoch 17, validation: loss=3.018, NarTop10Accuracy=0.7223, over 1905321.00 frames. 
2024-08-06 18:07:10,764 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29440MB
2024-08-06 18:07:11,312 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.649e+02 2.005e+02 2.161e+02 2.341e+02 3.806e+02, threshold=4.323e+02, percent-clipped=0.0
2024-08-06 18:07:14,353 INFO [trainer.py:765] (2/8) Epoch 17, batch 800, train_loss[loss=3.115, NarTop10Accuracy=0.7006, over 5178.00 frames. ], tot_loss[loss=3.188, NarTop10Accuracy=0.6886, over 5777.16 frames. ], batch size: 6, lr: 5.08e-03
2024-08-06 18:07:49,721 INFO [trainer.py:765] (2/8) Epoch 17, batch 900, train_loss[loss=3.567, NarTop10Accuracy=0.6087, over 6153.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6937, over 5801.26 frames. ], batch size: 13, lr: 5.07e-03
2024-08-06 18:08:21,598 INFO [trainer.py:765] (2/8) Epoch 17, batch 1000, train_loss[loss=3.227, NarTop10Accuracy=0.6804, over 6096.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6925, over 5900.33 frames. ], batch size: 13, lr: 5.07e-03
2024-08-06 18:09:03,106 INFO [trainer.py:765] (2/8) Epoch 17, batch 1100, train_loss[loss=2.957, NarTop10Accuracy=0.7391, over 6756.00 frames. ], tot_loss[loss=3.181, NarTop10Accuracy=0.6898, over 5930.01 frames. ], batch size: 17, lr: 5.06e-03
2024-08-06 18:09:36,746 INFO [trainer.py:765] (2/8) Epoch 17, batch 1200, train_loss[loss=3.012, NarTop10Accuracy=0.7299, over 7305.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6913, over 5927.33 frames. ], batch size: 32, lr: 5.06e-03
2024-08-06 18:10:10,688 INFO [trainer.py:765] (2/8) Epoch 17, batch 1300, train_loss[loss=3.312, NarTop10Accuracy=0.6627, over 4155.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6913, over 5981.05 frames. ], batch size: 5, lr: 5.05e-03
2024-08-06 18:10:48,026 INFO [trainer.py:765] (2/8) Epoch 17, batch 1400, train_loss[loss=3.379, NarTop10Accuracy=0.6534, over 6129.00 frames. ], tot_loss[loss=3.177, NarTop10Accuracy=0.6904, over 5984.87 frames. ], batch size: 11, lr: 5.04e-03
2024-08-06 18:11:19,105 INFO [trainer.py:765] (2/8) Epoch 17, batch 1500, train_loss[loss=3.483, NarTop10Accuracy=0.6374, over 6618.00 frames. ], tot_loss[loss=3.165, NarTop10Accuracy=0.6932, over 5942.80 frames. ], batch size: 51, lr: 5.04e-03
2024-08-06 18:11:46,855 INFO [trainer.py:765] (2/8) Epoch 17, batch 1600, train_loss[loss=3.088, NarTop10Accuracy=0.7093, over 6855.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6947, over 5923.27 frames. ], batch size: 22, lr: 5.03e-03
2024-08-06 18:12:13,508 INFO [trainer.py:765] (2/8) Epoch 17, batch 1700, train_loss[loss=3.545, NarTop10Accuracy=0.6153, over 6312.00 frames. ], tot_loss[loss=3.173, NarTop10Accuracy=0.6914, over 5904.41 frames. ], batch size: 13, lr: 5.03e-03
2024-08-06 18:12:40,001 INFO [trainer.py:765] (2/8) Epoch 17, batch 1800, train_loss[loss=2.897, NarTop10Accuracy=0.7519, over 7104.00 frames. ], tot_loss[loss=3.185, NarTop10Accuracy=0.6884, over 5973.33 frames. ], batch size: 22, lr: 5.02e-03
2024-08-06 18:13:06,380 INFO [trainer.py:765] (2/8) Epoch 17, batch 1900, train_loss[loss=3.073, NarTop10Accuracy=0.7196, over 6102.00 frames. ], tot_loss[loss=3.195, NarTop10Accuracy=0.6866, over 6023.55 frames. ], batch size: 51, lr: 5.01e-03
2024-08-06 18:13:31,923 INFO [trainer.py:765] (2/8) Epoch 17, batch 2000, train_loss[loss=3.646, NarTop10Accuracy=0.5894, over 5982.00 frames. ], tot_loss[loss=3.175, NarTop10Accuracy=0.6911, over 5996.77 frames. ], batch size: 51, lr: 5.01e-03
2024-08-06 18:13:57,228 INFO [trainer.py:765] (2/8) Epoch 17, batch 2100, train_loss[loss=2.976, NarTop10Accuracy=0.7263, over 4731.00 frames. ], tot_loss[loss=3.176, NarTop10Accuracy=0.6908, over 5987.46 frames. ], batch size: 5, lr: 5.00e-03
2024-08-06 18:14:22,434 INFO [trainer.py:765] (2/8) Epoch 17, batch 2200, train_loss[loss=2.944, NarTop10Accuracy=0.7468, over 7329.00 frames. ], tot_loss[loss=3.195, NarTop10Accuracy=0.6869, over 6022.52 frames. ], batch size: 31, lr: 5.00e-03
2024-08-06 18:14:47,592 INFO [trainer.py:765] (2/8) Epoch 17, batch 2300, train_loss[loss=3.019, NarTop10Accuracy=0.7262, over 5655.00 frames. ], tot_loss[loss=3.187, NarTop10Accuracy=0.6884, over 6016.69 frames. ], batch size: 9, lr: 4.99e-03
2024-08-06 18:15:12,061 INFO [trainer.py:765] (2/8) Epoch 17, batch 2400, train_loss[loss=3.022, NarTop10Accuracy=0.7264, over 5070.00 frames. ], tot_loss[loss=3.181, NarTop10Accuracy=0.6895, over 5779.31 frames. ], batch size: 7, lr: 4.99e-03
2024-08-06 18:15:35,515 INFO [trainer.py:765] (2/8) Epoch 17, batch 2500, train_loss[loss=2.836, NarTop10Accuracy=0.7633, over 5094.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6915, over 5488.00 frames. ], batch size: 7, lr: 4.98e-03
2024-08-06 18:15:56,062 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 18:16:49,908 INFO [trainer.py:765] (2/8) Epoch 18, batch 100, train_loss[loss=3.028, NarTop10Accuracy=0.718, over 7395.00 frames. ], tot_loss[loss=3.179, NarTop10Accuracy=0.6905, over 2373.08 frames. ], batch size: 31, lr: 4.83e-03
2024-08-06 18:17:24,749 INFO [trainer.py:765] (2/8) Epoch 18, batch 200, train_loss[loss=2.953, NarTop10Accuracy=0.7342, over 6801.00 frames. ], tot_loss[loss=3.162, NarTop10Accuracy=0.6936, over 3869.50 frames. ], batch size: 17, lr: 4.83e-03
2024-08-06 18:17:27,717 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 18:17:35,927 INFO [trainer.py:811] (2/8) Epoch 18, validation: loss=3.062, NarTop10Accuracy=0.7137, over 1905321.00 frames. 
2024-08-06 18:17:35,927 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29440MB
2024-08-06 18:17:36,529 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.649e+02 2.024e+02 2.164e+02 2.334e+02 7.024e+02, threshold=4.329e+02, percent-clipped=0.1
2024-08-06 18:18:06,912 INFO [trainer.py:765] (2/8) Epoch 18, batch 300, train_loss[loss=3.455, NarTop10Accuracy=0.6298, over 7044.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6921, over 4655.92 frames. ], batch size: 22, lr: 4.82e-03
2024-08-06 18:18:38,183 INFO [trainer.py:765] (2/8) Epoch 18, batch 400, train_loss[loss=3.148, NarTop10Accuracy=0.6935, over 5154.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6957, over 5091.61 frames. ], batch size: 7, lr: 4.81e-03
2024-08-06 18:19:13,599 INFO [trainer.py:765] (2/8) Epoch 18, batch 500, train_loss[loss=3.057, NarTop10Accuracy=0.7148, over 6216.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.6947, over 5380.84 frames. ], batch size: 11, lr: 4.81e-03
2024-08-06 18:19:48,151 INFO [trainer.py:765] (2/8) Epoch 18, batch 600, train_loss[loss=3.406, NarTop10Accuracy=0.6412, over 6192.00 frames. ], tot_loss[loss=3.159, NarTop10Accuracy=0.6941, over 5640.78 frames. ], batch size: 10, lr: 4.80e-03
2024-08-06 18:20:23,869 INFO [trainer.py:765] (2/8) Epoch 18, batch 700, train_loss[loss=3.484, NarTop10Accuracy=0.6185, over 5070.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6924, over 5712.17 frames. ], batch size: 6, lr: 4.80e-03
2024-08-06 18:21:01,026 INFO [trainer.py:765] (2/8) Epoch 18, batch 800, train_loss[loss=2.785, NarTop10Accuracy=0.7698, over 5121.00 frames. ], tot_loss[loss=3.173, NarTop10Accuracy=0.6913, over 5779.49 frames. ], batch size: 6, lr: 4.79e-03
2024-08-06 18:21:32,409 INFO [trainer.py:765] (2/8) Epoch 18, batch 900, train_loss[loss=3.014, NarTop10Accuracy=0.7252, over 6213.00 frames. ], tot_loss[loss=3.153, NarTop10Accuracy=0.6959, over 5816.96 frames. ], batch size: 13, lr: 4.79e-03
2024-08-06 18:22:11,192 INFO [trainer.py:765] (2/8) Epoch 18, batch 1000, train_loss[loss=2.918, NarTop10Accuracy=0.7442, over 6342.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6935, over 5904.50 frames. ], batch size: 13, lr: 4.78e-03
2024-08-06 18:22:46,969 INFO [trainer.py:765] (2/8) Epoch 18, batch 1100, train_loss[loss=3.456, NarTop10Accuracy=0.6318, over 6942.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6931, over 5924.61 frames. ], batch size: 17, lr: 4.78e-03
2024-08-06 18:23:18,605 INFO [trainer.py:765] (2/8) Epoch 18, batch 1200, train_loss[loss=3.439, NarTop10Accuracy=0.628, over 7272.00 frames. ], tot_loss[loss=3.173, NarTop10Accuracy=0.6906, over 5921.87 frames. ], batch size: 31, lr: 4.77e-03
2024-08-06 18:24:00,099 INFO [trainer.py:765] (2/8) Epoch 18, batch 1300, train_loss[loss=2.836, NarTop10Accuracy=0.7669, over 5112.00 frames. ], tot_loss[loss=3.153, NarTop10Accuracy=0.695, over 5982.11 frames. ], batch size: 6, lr: 4.77e-03
2024-08-06 18:24:29,574 INFO [trainer.py:765] (2/8) Epoch 18, batch 1400, train_loss[loss=2.991, NarTop10Accuracy=0.727, over 5925.00 frames. ], tot_loss[loss=3.159, NarTop10Accuracy=0.6937, over 5988.87 frames. ], batch size: 11, lr: 4.76e-03
2024-08-06 18:25:00,307 INFO [trainer.py:765] (2/8) Epoch 18, batch 1500, train_loss[loss=3.109, NarTop10Accuracy=0.7103, over 6240.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6941, over 5942.82 frames. ], batch size: 50, lr: 4.76e-03
2024-08-06 18:25:28,085 INFO [trainer.py:765] (2/8) Epoch 18, batch 1600, train_loss[loss=3, NarTop10Accuracy=0.7244, over 7170.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.6935, over 5928.46 frames. ], batch size: 22, lr: 4.75e-03
2024-08-06 18:25:54,687 INFO [trainer.py:765] (2/8) Epoch 18, batch 1700, train_loss[loss=3.042, NarTop10Accuracy=0.7177, over 6642.00 frames. ], tot_loss[loss=3.162, NarTop10Accuracy=0.6932, over 5894.36 frames. ], batch size: 14, lr: 4.75e-03
2024-08-06 18:26:21,196 INFO [trainer.py:765] (2/8) Epoch 18, batch 1800, train_loss[loss=3.384, NarTop10Accuracy=0.6476, over 7146.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6956, over 5961.74 frames. ], batch size: 22, lr: 4.74e-03
2024-08-06 18:26:47,567 INFO [trainer.py:765] (2/8) Epoch 18, batch 1900, train_loss[loss=3.087, NarTop10Accuracy=0.715, over 6321.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.6933, over 6015.54 frames. ], batch size: 51, lr: 4.74e-03
2024-08-06 18:27:13,176 INFO [trainer.py:765] (2/8) Epoch 18, batch 2000, train_loss[loss=3.064, NarTop10Accuracy=0.7105, over 6030.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6945, over 5995.48 frames. ], batch size: 50, lr: 4.73e-03
2024-08-06 18:27:38,529 INFO [trainer.py:765] (2/8) Epoch 18, batch 2100, train_loss[loss=3.227, NarTop10Accuracy=0.6779, over 4854.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6949, over 5955.49 frames. ], batch size: 5, lr: 4.73e-03
2024-08-06 18:28:03,812 INFO [trainer.py:765] (2/8) Epoch 18, batch 2200, train_loss[loss=3.023, NarTop10Accuracy=0.7234, over 7086.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6947, over 5987.32 frames. ], batch size: 31, lr: 4.72e-03
2024-08-06 18:28:06,571 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 18:28:14,650 INFO [trainer.py:811] (2/8) Epoch 18, validation: loss=3.028, NarTop10Accuracy=0.7201, over 1905321.00 frames. 
2024-08-06 18:28:14,650 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29440MB
2024-08-06 18:28:15,147 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.654e+02 2.054e+02 2.220e+02 2.384e+02 3.992e+02, threshold=4.441e+02, percent-clipped=0.0
2024-08-06 18:28:37,096 INFO [trainer.py:765] (2/8) Epoch 18, batch 2300, train_loss[loss=2.806, NarTop10Accuracy=0.7563, over 5691.00 frames. ], tot_loss[loss=3.17, NarTop10Accuracy=0.6921, over 6016.71 frames. ], batch size: 9, lr: 4.72e-03
2024-08-06 18:29:01,592 INFO [trainer.py:765] (2/8) Epoch 18, batch 2400, train_loss[loss=3.039, NarTop10Accuracy=0.7143, over 4935.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6971, over 5754.38 frames. ], batch size: 7, lr: 4.71e-03
2024-08-06 18:29:25,027 INFO [trainer.py:765] (2/8) Epoch 18, batch 2500, train_loss[loss=2.964, NarTop10Accuracy=0.7295, over 5124.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7011, over 5453.51 frames. ], batch size: 7, lr: 4.71e-03
2024-08-06 18:29:45,351 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 18:30:41,232 INFO [trainer.py:765] (2/8) Epoch 19, batch 100, train_loss[loss=2.906, NarTop10Accuracy=0.745, over 7179.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.695, over 2351.38 frames. ], batch size: 31, lr: 4.57e-03
2024-08-06 18:31:15,603 INFO [trainer.py:765] (2/8) Epoch 19, batch 200, train_loss[loss=2.936, NarTop10Accuracy=0.7426, over 6861.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6956, over 3844.92 frames. ], batch size: 17, lr: 4.57e-03
2024-08-06 18:31:47,468 INFO [trainer.py:765] (2/8) Epoch 19, batch 300, train_loss[loss=3.535, NarTop10Accuracy=0.6219, over 7215.00 frames. ], tot_loss[loss=3.136, NarTop10Accuracy=0.6987, over 4643.28 frames. ], batch size: 22, lr: 4.56e-03
2024-08-06 18:32:20,355 INFO [trainer.py:765] (2/8) Epoch 19, batch 400, train_loss[loss=3.217, NarTop10Accuracy=0.6791, over 5220.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.6991, over 5097.89 frames. ], batch size: 7, lr: 4.56e-03
2024-08-06 18:32:50,335 INFO [trainer.py:765] (2/8) Epoch 19, batch 500, train_loss[loss=3.09, NarTop10Accuracy=0.7109, over 6156.00 frames. ], tot_loss[loss=3.136, NarTop10Accuracy=0.6989, over 5388.63 frames. ], batch size: 11, lr: 4.55e-03
2024-08-06 18:33:29,610 INFO [trainer.py:765] (2/8) Epoch 19, batch 600, train_loss[loss=3.025, NarTop10Accuracy=0.7159, over 5748.00 frames. ], tot_loss[loss=3.141, NarTop10Accuracy=0.6974, over 5660.39 frames. ], batch size: 9, lr: 4.55e-03
2024-08-06 18:34:03,592 INFO [trainer.py:765] (2/8) Epoch 19, batch 700, train_loss[loss=2.845, NarTop10Accuracy=0.7621, over 5091.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6968, over 5708.00 frames. ], batch size: 6, lr: 4.54e-03
2024-08-06 18:34:35,179 INFO [trainer.py:765] (2/8) Epoch 19, batch 800, train_loss[loss=3.175, NarTop10Accuracy=0.6923, over 5022.00 frames. ], tot_loss[loss=3.153, NarTop10Accuracy=0.695, over 5776.14 frames. ], batch size: 6, lr: 4.54e-03
2024-08-06 18:35:10,263 INFO [trainer.py:765] (2/8) Epoch 19, batch 900, train_loss[loss=2.759, NarTop10Accuracy=0.7702, over 6177.00 frames. ], tot_loss[loss=3.143, NarTop10Accuracy=0.6969, over 5791.03 frames. ], batch size: 13, lr: 4.53e-03
2024-08-06 18:35:48,637 INFO [trainer.py:765] (2/8) Epoch 19, batch 1000, train_loss[loss=3.309, NarTop10Accuracy=0.6617, over 6180.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6969, over 5900.25 frames. ], batch size: 13, lr: 4.53e-03
2024-08-06 18:36:20,939 INFO [trainer.py:765] (2/8) Epoch 19, batch 1100, train_loss[loss=3.03, NarTop10Accuracy=0.7204, over 6789.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.6937, over 5935.31 frames. ], batch size: 17, lr: 4.52e-03
2024-08-06 18:36:57,130 INFO [trainer.py:765] (2/8) Epoch 19, batch 1200, train_loss[loss=2.964, NarTop10Accuracy=0.735, over 7212.00 frames. ], tot_loss[loss=3.17, NarTop10Accuracy=0.6918, over 5942.96 frames. ], batch size: 31, lr: 4.52e-03
2024-08-06 18:37:35,315 INFO [trainer.py:765] (2/8) Epoch 19, batch 1300, train_loss[loss=2.816, NarTop10Accuracy=0.7683, over 4254.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.6926, over 6008.80 frames. ], batch size: 5, lr: 4.51e-03
2024-08-06 18:38:04,679 INFO [trainer.py:765] (2/8) Epoch 19, batch 1400, train_loss[loss=3.088, NarTop10Accuracy=0.7157, over 6078.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.692, over 6024.58 frames. ], batch size: 11, lr: 4.51e-03
2024-08-06 18:38:34,550 INFO [trainer.py:765] (2/8) Epoch 19, batch 1500, train_loss[loss=3.443, NarTop10Accuracy=0.6398, over 6699.00 frames. ], tot_loss[loss=3.143, NarTop10Accuracy=0.6973, over 5961.24 frames. ], batch size: 55, lr: 4.50e-03
2024-08-06 18:39:02,311 INFO [trainer.py:765] (2/8) Epoch 19, batch 1600, train_loss[loss=3.462, NarTop10Accuracy=0.6333, over 7092.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6969, over 5942.46 frames. ], batch size: 22, lr: 4.50e-03
2024-08-06 18:39:11,591 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 18:39:19,795 INFO [trainer.py:811] (2/8) Epoch 19, validation: loss=2.958, NarTop10Accuracy=0.7345, over 1905321.00 frames. 
2024-08-06 18:39:19,796 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 29440MB
2024-08-06 18:39:20,378 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.633e+02 2.040e+02 2.194e+02 2.364e+02 6.410e+02, threshold=4.387e+02, percent-clipped=0.2
2024-08-06 18:39:37,191 INFO [trainer.py:765] (2/8) Epoch 19, batch 1700, train_loss[loss=3.619, NarTop10Accuracy=0.5964, over 6330.00 frames. ], tot_loss[loss=3.142, NarTop10Accuracy=0.6974, over 5925.62 frames. ], batch size: 13, lr: 4.49e-03
2024-08-06 18:40:03,789 INFO [trainer.py:765] (2/8) Epoch 19, batch 1800, train_loss[loss=3.529, NarTop10Accuracy=0.6128, over 7059.00 frames. ], tot_loss[loss=3.141, NarTop10Accuracy=0.6974, over 5976.41 frames. ], batch size: 22, lr: 4.49e-03
2024-08-06 18:40:30,217 INFO [trainer.py:765] (2/8) Epoch 19, batch 1900, train_loss[loss=3.131, NarTop10Accuracy=0.7093, over 5901.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.697, over 6016.48 frames. ], batch size: 51, lr: 4.49e-03
2024-08-06 18:40:55,794 INFO [trainer.py:765] (2/8) Epoch 19, batch 2000, train_loss[loss=3.33, NarTop10Accuracy=0.6593, over 5748.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6971, over 5994.50 frames. ], batch size: 50, lr: 4.48e-03
2024-08-06 18:41:21,183 INFO [trainer.py:765] (2/8) Epoch 19, batch 2100, train_loss[loss=2.941, NarTop10Accuracy=0.7446, over 4716.00 frames. ], tot_loss[loss=3.137, NarTop10Accuracy=0.6984, over 5956.37 frames. ], batch size: 5, lr: 4.48e-03
2024-08-06 18:41:46,455 INFO [trainer.py:765] (2/8) Epoch 19, batch 2200, train_loss[loss=3.19, NarTop10Accuracy=0.6887, over 7308.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6966, over 5996.84 frames. ], batch size: 32, lr: 4.47e-03
2024-08-06 18:42:11,559 INFO [trainer.py:765] (2/8) Epoch 19, batch 2300, train_loss[loss=3.077, NarTop10Accuracy=0.7108, over 5628.00 frames. ], tot_loss[loss=3.162, NarTop10Accuracy=0.6934, over 5997.50 frames. ], batch size: 9, lr: 4.47e-03
2024-08-06 18:42:35,987 INFO [trainer.py:765] (2/8) Epoch 19, batch 2400, train_loss[loss=3.004, NarTop10Accuracy=0.7179, over 5031.00 frames. ], tot_loss[loss=3.143, NarTop10Accuracy=0.6969, over 5768.66 frames. ], batch size: 7, lr: 4.46e-03
2024-08-06 18:42:59,690 INFO [trainer.py:765] (2/8) Epoch 19, batch 2500, train_loss[loss=2.895, NarTop10Accuracy=0.7489, over 5199.00 frames. ], tot_loss[loss=3.123, NarTop10Accuracy=0.701, over 5485.06 frames. ], batch size: 7, lr: 4.46e-03
2024-08-06 18:43:19,650 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 18:44:22,974 INFO [trainer.py:765] (2/8) Epoch 20, batch 100, train_loss[loss=3.269, NarTop10Accuracy=0.6681, over 7140.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6948, over 2365.79 frames. ], batch size: 31, lr: 4.34e-03
2024-08-06 18:44:58,379 INFO [trainer.py:765] (2/8) Epoch 20, batch 200, train_loss[loss=3.482, NarTop10Accuracy=0.6237, over 6903.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7017, over 3870.31 frames. ], batch size: 17, lr: 4.33e-03
2024-08-06 18:45:32,279 INFO [trainer.py:765] (2/8) Epoch 20, batch 300, train_loss[loss=3.402, NarTop10Accuracy=0.6412, over 6990.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7038, over 4680.65 frames. ], batch size: 22, lr: 4.33e-03
2024-08-06 18:46:05,128 INFO [trainer.py:765] (2/8) Epoch 20, batch 400, train_loss[loss=2.873, NarTop10Accuracy=0.752, over 5196.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.703, over 5127.09 frames. ], batch size: 7, lr: 4.32e-03
2024-08-06 18:46:35,770 INFO [trainer.py:765] (2/8) Epoch 20, batch 500, train_loss[loss=2.791, NarTop10Accuracy=0.77, over 6297.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.7003, over 5410.01 frames. ], batch size: 11, lr: 4.32e-03
2024-08-06 18:47:13,255 INFO [trainer.py:765] (2/8) Epoch 20, batch 600, train_loss[loss=3.083, NarTop10Accuracy=0.7036, over 5814.00 frames. ], tot_loss[loss=3.124, NarTop10Accuracy=0.7009, over 5665.04 frames. ], batch size: 9, lr: 4.31e-03
2024-08-06 18:47:44,481 INFO [trainer.py:765] (2/8) Epoch 20, batch 700, train_loss[loss=2.755, NarTop10Accuracy=0.7759, over 5040.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7037, over 5724.20 frames. ], batch size: 6, lr: 4.31e-03
2024-08-06 18:48:21,016 INFO [trainer.py:765] (2/8) Epoch 20, batch 800, train_loss[loss=2.781, NarTop10Accuracy=0.7747, over 5217.00 frames. ], tot_loss[loss=3.129, NarTop10Accuracy=0.7001, over 5785.16 frames. ], batch size: 6, lr: 4.31e-03
2024-08-06 18:48:56,535 INFO [trainer.py:765] (2/8) Epoch 20, batch 900, train_loss[loss=2.932, NarTop10Accuracy=0.749, over 6312.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.7004, over 5810.16 frames. ], batch size: 13, lr: 4.30e-03
2024-08-06 18:49:29,805 INFO [trainer.py:765] (2/8) Epoch 20, batch 1000, train_loss[loss=3.186, NarTop10Accuracy=0.6926, over 6630.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6961, over 5911.04 frames. ], batch size: 14, lr: 4.30e-03
2024-08-06 18:49:52,237 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 18:50:00,327 INFO [trainer.py:811] (2/8) Epoch 20, validation: loss=2.962, NarTop10Accuracy=0.7336, over 1905321.00 frames. 
2024-08-06 18:50:00,328 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 18:50:00,875 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.681e+02 2.061e+02 2.223e+02 2.401e+02 3.871e+02, threshold=4.447e+02, percent-clipped=0.0
2024-08-06 18:50:15,426 INFO [trainer.py:765] (2/8) Epoch 20, batch 1100, train_loss[loss=3.311, NarTop10Accuracy=0.6618, over 6630.00 frames. ], tot_loss[loss=3.143, NarTop10Accuracy=0.6969, over 5927.58 frames. ], batch size: 17, lr: 4.29e-03
2024-08-06 18:50:53,776 INFO [trainer.py:765] (2/8) Epoch 20, batch 1200, train_loss[loss=3.019, NarTop10Accuracy=0.7269, over 7332.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6953, over 5920.22 frames. ], batch size: 31, lr: 4.29e-03
2024-08-06 18:51:25,129 INFO [trainer.py:765] (2/8) Epoch 20, batch 1300, train_loss[loss=3.327, NarTop10Accuracy=0.6538, over 5088.00 frames. ], tot_loss[loss=3.136, NarTop10Accuracy=0.6984, over 5988.77 frames. ], batch size: 6, lr: 4.29e-03
2024-08-06 18:51:59,314 INFO [trainer.py:765] (2/8) Epoch 20, batch 1400, train_loss[loss=3.047, NarTop10Accuracy=0.7293, over 6177.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7007, over 6002.73 frames. ], batch size: 11, lr: 4.28e-03
2024-08-06 18:52:32,805 INFO [trainer.py:765] (2/8) Epoch 20, batch 1500, train_loss[loss=3.209, NarTop10Accuracy=0.687, over 6327.00 frames. ], tot_loss[loss=3.136, NarTop10Accuracy=0.6984, over 5934.76 frames. ], batch size: 50, lr: 4.28e-03
2024-08-06 18:53:00,635 INFO [trainer.py:765] (2/8) Epoch 20, batch 1600, train_loss[loss=2.898, NarTop10Accuracy=0.752, over 6975.00 frames. ], tot_loss[loss=3.143, NarTop10Accuracy=0.6966, over 5911.78 frames. ], batch size: 22, lr: 4.27e-03
2024-08-06 18:53:27,328 INFO [trainer.py:765] (2/8) Epoch 20, batch 1700, train_loss[loss=3.583, NarTop10Accuracy=0.6107, over 6207.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6967, over 5908.28 frames. ], batch size: 13, lr: 4.27e-03
2024-08-06 18:53:53,850 INFO [trainer.py:765] (2/8) Epoch 20, batch 1800, train_loss[loss=3.062, NarTop10Accuracy=0.718, over 7026.00 frames. ], tot_loss[loss=3.133, NarTop10Accuracy=0.6992, over 5983.12 frames. ], batch size: 22, lr: 4.26e-03
2024-08-06 18:54:20,315 INFO [trainer.py:765] (2/8) Epoch 20, batch 1900, train_loss[loss=3.102, NarTop10Accuracy=0.7055, over 6123.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.6932, over 6030.60 frames. ], batch size: 50, lr: 4.26e-03
2024-08-06 18:54:45,890 INFO [trainer.py:765] (2/8) Epoch 20, batch 2000, train_loss[loss=3.582, NarTop10Accuracy=0.6048, over 6273.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.692, over 6016.25 frames. ], batch size: 50, lr: 4.26e-03
2024-08-06 18:55:11,182 INFO [trainer.py:765] (2/8) Epoch 20, batch 2100, train_loss[loss=3.348, NarTop10Accuracy=0.6705, over 4800.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6946, over 5969.45 frames. ], batch size: 5, lr: 4.25e-03
2024-08-06 18:55:36,414 INFO [trainer.py:765] (2/8) Epoch 20, batch 2200, train_loss[loss=2.937, NarTop10Accuracy=0.7387, over 7092.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6926, over 6011.53 frames. ], batch size: 31, lr: 4.25e-03
2024-08-06 18:56:01,635 INFO [trainer.py:765] (2/8) Epoch 20, batch 2300, train_loss[loss=3.273, NarTop10Accuracy=0.675, over 5856.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6919, over 6024.86 frames. ], batch size: 9, lr: 4.24e-03
2024-08-06 18:56:26,049 INFO [trainer.py:765] (2/8) Epoch 20, batch 2400, train_loss[loss=2.874, NarTop10Accuracy=0.7553, over 5121.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6954, over 5777.39 frames. ], batch size: 7, lr: 4.24e-03
2024-08-06 18:56:49,566 INFO [trainer.py:765] (2/8) Epoch 20, batch 2500, train_loss[loss=2.987, NarTop10Accuracy=0.7314, over 5784.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7024, over 5490.10 frames. ], batch size: 8, lr: 4.24e-03
2024-08-06 18:57:09,627 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 18:58:09,585 INFO [trainer.py:765] (2/8) Epoch 21, batch 100, train_loss[loss=3.201, NarTop10Accuracy=0.6839, over 7479.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7054, over 2377.69 frames. ], batch size: 32, lr: 4.13e-03
2024-08-06 18:58:40,417 INFO [trainer.py:765] (2/8) Epoch 21, batch 200, train_loss[loss=2.819, NarTop10Accuracy=0.7715, over 6837.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7019, over 3866.70 frames. ], batch size: 17, lr: 4.12e-03
2024-08-06 18:59:13,333 INFO [trainer.py:765] (2/8) Epoch 21, batch 300, train_loss[loss=2.941, NarTop10Accuracy=0.7416, over 6909.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.7002, over 4662.67 frames. ], batch size: 22, lr: 4.12e-03
2024-08-06 18:59:48,151 INFO [trainer.py:765] (2/8) Epoch 21, batch 400, train_loss[loss=2.794, NarTop10Accuracy=0.7678, over 5076.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7029, over 5126.11 frames. ], batch size: 7, lr: 4.11e-03
2024-08-06 19:00:16,839 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 19:00:25,075 INFO [trainer.py:811] (2/8) Epoch 21, validation: loss=2.992, NarTop10Accuracy=0.7268, over 1905321.00 frames. 
2024-08-06 19:00:25,076 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 19:00:25,622 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.727e+02 2.071e+02 2.224e+02 2.387e+02 3.839e+02, threshold=4.447e+02, percent-clipped=0.0
2024-08-06 19:00:29,891 INFO [trainer.py:765] (2/8) Epoch 21, batch 500, train_loss[loss=2.8, NarTop10Accuracy=0.7677, over 6108.00 frames. ], tot_loss[loss=3.117, NarTop10Accuracy=0.7021, over 5389.39 frames. ], batch size: 11, lr: 4.11e-03
2024-08-06 19:01:03,329 INFO [trainer.py:765] (2/8) Epoch 21, batch 600, train_loss[loss=3.519, NarTop10Accuracy=0.6189, over 5715.00 frames. ], tot_loss[loss=3.107, NarTop10Accuracy=0.7043, over 5668.98 frames. ], batch size: 9, lr: 4.11e-03
2024-08-06 19:01:39,388 INFO [trainer.py:765] (2/8) Epoch 21, batch 700, train_loss[loss=2.631, NarTop10Accuracy=0.7974, over 5052.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7023, over 5737.46 frames. ], batch size: 6, lr: 4.10e-03
2024-08-06 19:02:18,047 INFO [trainer.py:765] (2/8) Epoch 21, batch 800, train_loss[loss=3.149, NarTop10Accuracy=0.7055, over 5004.00 frames. ], tot_loss[loss=3.13, NarTop10Accuracy=0.6997, over 5794.79 frames. ], batch size: 6, lr: 4.10e-03
2024-08-06 19:02:48,663 INFO [trainer.py:765] (2/8) Epoch 21, batch 900, train_loss[loss=3.012, NarTop10Accuracy=0.7292, over 6117.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.7, over 5812.32 frames. ], batch size: 13, lr: 4.09e-03
2024-08-06 19:03:25,801 INFO [trainer.py:765] (2/8) Epoch 21, batch 1000, train_loss[loss=2.982, NarTop10Accuracy=0.7301, over 6603.00 frames. ], tot_loss[loss=3.131, NarTop10Accuracy=0.6993, over 5917.86 frames. ], batch size: 14, lr: 4.09e-03
2024-08-06 19:04:07,207 INFO [trainer.py:765] (2/8) Epoch 21, batch 1100, train_loss[loss=3.385, NarTop10Accuracy=0.6479, over 6732.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6954, over 5966.31 frames. ], batch size: 17, lr: 4.09e-03
2024-08-06 19:04:38,463 INFO [trainer.py:765] (2/8) Epoch 21, batch 1200, train_loss[loss=3.287, NarTop10Accuracy=0.6652, over 7278.00 frames. ], tot_loss[loss=3.129, NarTop10Accuracy=0.6992, over 5957.18 frames. ], batch size: 31, lr: 4.08e-03
2024-08-06 19:05:15,316 INFO [trainer.py:765] (2/8) Epoch 21, batch 1300, train_loss[loss=2.782, NarTop10Accuracy=0.7643, over 4977.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7028, over 6005.05 frames. ], batch size: 6, lr: 4.08e-03
2024-08-06 19:05:55,560 INFO [trainer.py:765] (2/8) Epoch 21, batch 1400, train_loss[loss=3.442, NarTop10Accuracy=0.6309, over 6108.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7025, over 6030.22 frames. ], batch size: 11, lr: 4.07e-03
2024-08-06 19:06:23,600 INFO [trainer.py:765] (2/8) Epoch 21, batch 1500, train_loss[loss=3.294, NarTop10Accuracy=0.6713, over 6627.00 frames. ], tot_loss[loss=3.132, NarTop10Accuracy=0.6993, over 5951.06 frames. ], batch size: 50, lr: 4.07e-03
2024-08-06 19:06:51,462 INFO [trainer.py:765] (2/8) Epoch 21, batch 1600, train_loss[loss=2.907, NarTop10Accuracy=0.7476, over 7128.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.6991, over 5925.02 frames. ], batch size: 22, lr: 4.07e-03
2024-08-06 19:07:18,212 INFO [trainer.py:765] (2/8) Epoch 21, batch 1700, train_loss[loss=3.256, NarTop10Accuracy=0.6792, over 6330.00 frames. ], tot_loss[loss=3.136, NarTop10Accuracy=0.6988, over 5902.02 frames. ], batch size: 13, lr: 4.06e-03
2024-08-06 19:07:44,809 INFO [trainer.py:765] (2/8) Epoch 21, batch 1800, train_loss[loss=2.949, NarTop10Accuracy=0.7386, over 7038.00 frames. ], tot_loss[loss=3.129, NarTop10Accuracy=0.7001, over 5976.75 frames. ], batch size: 22, lr: 4.06e-03
2024-08-06 19:08:11,369 INFO [trainer.py:765] (2/8) Epoch 21, batch 1900, train_loss[loss=3.634, NarTop10Accuracy=0.5926, over 6591.00 frames. ], tot_loss[loss=3.141, NarTop10Accuracy=0.6972, over 6035.97 frames. ], batch size: 50, lr: 4.06e-03
2024-08-06 19:08:37,105 INFO [trainer.py:765] (2/8) Epoch 21, batch 2000, train_loss[loss=3.493, NarTop10Accuracy=0.6209, over 6198.00 frames. ], tot_loss[loss=3.139, NarTop10Accuracy=0.6979, over 6003.31 frames. ], batch size: 51, lr: 4.05e-03
2024-08-06 19:09:02,507 INFO [trainer.py:765] (2/8) Epoch 21, batch 2100, train_loss[loss=2.748, NarTop10Accuracy=0.78, over 3927.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6962, over 5964.35 frames. ], batch size: 4, lr: 4.05e-03
2024-08-06 19:09:27,891 INFO [trainer.py:765] (2/8) Epoch 21, batch 2200, train_loss[loss=2.919, NarTop10Accuracy=0.7422, over 7263.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6955, over 6022.45 frames. ], batch size: 31, lr: 4.04e-03
2024-08-06 19:09:53,223 INFO [trainer.py:765] (2/8) Epoch 21, batch 2300, train_loss[loss=3.042, NarTop10Accuracy=0.718, over 5709.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6927, over 6026.20 frames. ], batch size: 9, lr: 4.04e-03
2024-08-06 19:10:17,597 INFO [trainer.py:765] (2/8) Epoch 21, batch 2400, train_loss[loss=3.286, NarTop10Accuracy=0.6629, over 5250.00 frames. ], tot_loss[loss=3.139, NarTop10Accuracy=0.6975, over 5786.39 frames. ], batch size: 7, lr: 4.04e-03
2024-08-06 19:10:37,229 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 19:10:45,275 INFO [trainer.py:811] (2/8) Epoch 21, validation: loss=2.971, NarTop10Accuracy=0.7316, over 1905321.00 frames. 
2024-08-06 19:10:45,275 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 19:10:45,741 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.703e+02 2.100e+02 2.242e+02 2.407e+02 6.546e+02, threshold=4.484e+02, percent-clipped=0.1
2024-08-06 19:10:49,272 INFO [trainer.py:765] (2/8) Epoch 21, batch 2500, train_loss[loss=3.283, NarTop10Accuracy=0.6526, over 5208.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.7046, over 5481.23 frames. ], batch size: 7, lr: 4.03e-03
2024-08-06 19:11:09,181 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 19:12:09,054 INFO [trainer.py:765] (2/8) Epoch 22, batch 100, train_loss[loss=2.909, NarTop10Accuracy=0.7449, over 7077.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7074, over 2360.75 frames. ], batch size: 31, lr: 3.93e-03
2024-08-06 19:12:44,462 INFO [trainer.py:765] (2/8) Epoch 22, batch 200, train_loss[loss=3.259, NarTop10Accuracy=0.6667, over 6537.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7068, over 3859.11 frames. ], batch size: 17, lr: 3.93e-03
2024-08-06 19:13:14,533 INFO [trainer.py:765] (2/8) Epoch 22, batch 300, train_loss[loss=2.902, NarTop10Accuracy=0.7461, over 7203.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7066, over 4652.54 frames. ], batch size: 22, lr: 3.93e-03
2024-08-06 19:13:49,229 INFO [trainer.py:765] (2/8) Epoch 22, batch 400, train_loss[loss=3.031, NarTop10Accuracy=0.7243, over 5046.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7085, over 5102.95 frames. ], batch size: 7, lr: 3.92e-03
2024-08-06 19:14:24,850 INFO [trainer.py:765] (2/8) Epoch 22, batch 500, train_loss[loss=3.243, NarTop10Accuracy=0.6741, over 5982.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7083, over 5368.18 frames. ], batch size: 11, lr: 3.92e-03
2024-08-06 19:14:55,701 INFO [trainer.py:765] (2/8) Epoch 22, batch 600, train_loss[loss=2.96, NarTop10Accuracy=0.7349, over 5715.00 frames. ], tot_loss[loss=3.121, NarTop10Accuracy=0.7012, over 5645.64 frames. ], batch size: 9, lr: 3.92e-03
2024-08-06 19:15:30,867 INFO [trainer.py:765] (2/8) Epoch 22, batch 700, train_loss[loss=3.246, NarTop10Accuracy=0.6698, over 4380.00 frames. ], tot_loss[loss=3.119, NarTop10Accuracy=0.7019, over 5704.81 frames. ], batch size: 5, lr: 3.91e-03
2024-08-06 19:16:10,665 INFO [trainer.py:765] (2/8) Epoch 22, batch 800, train_loss[loss=3.003, NarTop10Accuracy=0.7266, over 5007.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.703, over 5759.79 frames. ], batch size: 6, lr: 3.91e-03
2024-08-06 19:16:40,952 INFO [trainer.py:765] (2/8) Epoch 22, batch 900, train_loss[loss=2.876, NarTop10Accuracy=0.7521, over 6570.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7028, over 5798.36 frames. ], batch size: 14, lr: 3.90e-03
2024-08-06 19:17:16,433 INFO [trainer.py:765] (2/8) Epoch 22, batch 1000, train_loss[loss=3.09, NarTop10Accuracy=0.7111, over 6726.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7041, over 5904.17 frames. ], batch size: 14, lr: 3.90e-03
2024-08-06 19:17:52,086 INFO [trainer.py:765] (2/8) Epoch 22, batch 1100, train_loss[loss=2.961, NarTop10Accuracy=0.741, over 6915.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7024, over 5929.23 frames. ], batch size: 17, lr: 3.90e-03
2024-08-06 19:18:25,927 INFO [trainer.py:765] (2/8) Epoch 22, batch 1200, train_loss[loss=2.945, NarTop10Accuracy=0.7273, over 7218.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7062, over 5922.75 frames. ], batch size: 31, lr: 3.89e-03
2024-08-06 19:19:01,253 INFO [trainer.py:765] (2/8) Epoch 22, batch 1300, train_loss[loss=3.037, NarTop10Accuracy=0.7238, over 5097.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7071, over 5990.48 frames. ], batch size: 6, lr: 3.89e-03
2024-08-06 19:19:33,317 INFO [trainer.py:765] (2/8) Epoch 22, batch 1400, train_loss[loss=2.808, NarTop10Accuracy=0.7642, over 6078.00 frames. ], tot_loss[loss=3.104, NarTop10Accuracy=0.7049, over 5992.14 frames. ], batch size: 11, lr: 3.89e-03
2024-08-06 19:20:03,830 INFO [trainer.py:765] (2/8) Epoch 22, batch 1500, train_loss[loss=3.442, NarTop10Accuracy=0.6368, over 6279.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7043, over 5936.06 frames. ], batch size: 50, lr: 3.88e-03
2024-08-06 19:20:31,647 INFO [trainer.py:765] (2/8) Epoch 22, batch 1600, train_loss[loss=3.112, NarTop10Accuracy=0.7012, over 7053.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7004, over 5908.11 frames. ], batch size: 22, lr: 3.88e-03
2024-08-06 19:20:58,418 INFO [trainer.py:765] (2/8) Epoch 22, batch 1700, train_loss[loss=3.155, NarTop10Accuracy=0.7009, over 6096.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7006, over 5905.12 frames. ], batch size: 13, lr: 3.88e-03
2024-08-06 19:21:25,010 INFO [trainer.py:765] (2/8) Epoch 22, batch 1800, train_loss[loss=2.823, NarTop10Accuracy=0.7671, over 7059.00 frames. ], tot_loss[loss=3.123, NarTop10Accuracy=0.701, over 5968.99 frames. ], batch size: 22, lr: 3.87e-03
2024-08-06 19:21:51,372 INFO [trainer.py:765] (2/8) Epoch 22, batch 1900, train_loss[loss=3.043, NarTop10Accuracy=0.7205, over 6414.00 frames. ], tot_loss[loss=3.142, NarTop10Accuracy=0.6975, over 6018.95 frames. ], batch size: 50, lr: 3.87e-03
2024-08-06 19:21:53,110 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 19:22:01,088 INFO [trainer.py:811] (2/8) Epoch 22, validation: loss=3.009, NarTop10Accuracy=0.7241, over 1905321.00 frames. 
2024-08-06 19:22:01,089 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 19:22:01,575 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.670e+02 2.114e+02 2.276e+02 2.445e+02 4.438e+02, threshold=4.551e+02, percent-clipped=0.0
2024-08-06 19:22:24,819 INFO [trainer.py:765] (2/8) Epoch 22, batch 2000, train_loss[loss=3.513, NarTop10Accuracy=0.6239, over 6204.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7029, over 5993.41 frames. ], batch size: 50, lr: 3.87e-03
2024-08-06 19:22:50,041 INFO [trainer.py:765] (2/8) Epoch 22, batch 2100, train_loss[loss=3.076, NarTop10Accuracy=0.7137, over 3810.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7038, over 5962.31 frames. ], batch size: 4, lr: 3.86e-03
2024-08-06 19:23:15,230 INFO [trainer.py:765] (2/8) Epoch 22, batch 2200, train_loss[loss=3.006, NarTop10Accuracy=0.7219, over 7116.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7034, over 5996.16 frames. ], batch size: 31, lr: 3.86e-03
2024-08-06 19:23:40,315 INFO [trainer.py:765] (2/8) Epoch 22, batch 2300, train_loss[loss=2.909, NarTop10Accuracy=0.7317, over 5802.00 frames. ], tot_loss[loss=3.13, NarTop10Accuracy=0.6994, over 6013.72 frames. ], batch size: 9, lr: 3.86e-03
2024-08-06 19:24:04,602 INFO [trainer.py:765] (2/8) Epoch 22, batch 2400, train_loss[loss=3.147, NarTop10Accuracy=0.6953, over 5085.00 frames. ], tot_loss[loss=3.121, NarTop10Accuracy=0.7013, over 5778.88 frames. ], batch size: 7, lr: 3.85e-03
2024-08-06 19:24:28,024 INFO [trainer.py:765] (2/8) Epoch 22, batch 2500, train_loss[loss=3.247, NarTop10Accuracy=0.6818, over 5211.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7046, over 5484.28 frames. ], batch size: 7, lr: 3.85e-03
2024-08-06 19:24:47,489 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 19:25:45,385 INFO [trainer.py:765] (2/8) Epoch 23, batch 100, train_loss[loss=3.043, NarTop10Accuracy=0.715, over 7104.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7031, over 2362.25 frames. ], batch size: 31, lr: 3.76e-03
2024-08-06 19:26:21,309 INFO [trainer.py:765] (2/8) Epoch 23, batch 200, train_loss[loss=3.506, NarTop10Accuracy=0.6192, over 6864.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7018, over 3860.31 frames. ], batch size: 17, lr: 3.76e-03
2024-08-06 19:26:57,603 INFO [trainer.py:765] (2/8) Epoch 23, batch 300, train_loss[loss=3, NarTop10Accuracy=0.7286, over 7032.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7065, over 4669.10 frames. ], batch size: 22, lr: 3.75e-03
2024-08-06 19:27:26,540 INFO [trainer.py:765] (2/8) Epoch 23, batch 400, train_loss[loss=3.353, NarTop10Accuracy=0.6528, over 5766.00 frames. ], tot_loss[loss=3.105, NarTop10Accuracy=0.7045, over 5129.71 frames. ], batch size: 8, lr: 3.75e-03
2024-08-06 19:27:59,713 INFO [trainer.py:765] (2/8) Epoch 23, batch 500, train_loss[loss=3.285, NarTop10Accuracy=0.6627, over 6123.00 frames. ], tot_loss[loss=3.104, NarTop10Accuracy=0.7042, over 5392.11 frames. ], batch size: 11, lr: 3.75e-03
2024-08-06 19:28:35,883 INFO [trainer.py:765] (2/8) Epoch 23, batch 600, train_loss[loss=3.273, NarTop10Accuracy=0.6828, over 5631.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7062, over 5648.54 frames. ], batch size: 9, lr: 3.74e-03
2024-08-06 19:29:11,367 INFO [trainer.py:765] (2/8) Epoch 23, batch 700, train_loss[loss=3.103, NarTop10Accuracy=0.7038, over 4386.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7084, over 5715.14 frames. ], batch size: 5, lr: 3.74e-03
2024-08-06 19:29:43,613 INFO [trainer.py:765] (2/8) Epoch 23, batch 800, train_loss[loss=2.823, NarTop10Accuracy=0.7626, over 4212.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7053, over 5782.13 frames. ], batch size: 5, lr: 3.74e-03
2024-08-06 19:30:19,390 INFO [trainer.py:765] (2/8) Epoch 23, batch 900, train_loss[loss=3.333, NarTop10Accuracy=0.6571, over 6534.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7064, over 5801.20 frames. ], batch size: 14, lr: 3.73e-03
2024-08-06 19:30:58,195 INFO [trainer.py:765] (2/8) Epoch 23, batch 1000, train_loss[loss=3.049, NarTop10Accuracy=0.7123, over 6171.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7072, over 5895.28 frames. ], batch size: 13, lr: 3.73e-03
2024-08-06 19:31:31,521 INFO [trainer.py:765] (2/8) Epoch 23, batch 1100, train_loss[loss=3.101, NarTop10Accuracy=0.717, over 6840.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7061, over 5933.33 frames. ], batch size: 17, lr: 3.73e-03
2024-08-06 19:32:08,518 INFO [trainer.py:765] (2/8) Epoch 23, batch 1200, train_loss[loss=3.013, NarTop10Accuracy=0.723, over 7134.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7041, over 5921.93 frames. ], batch size: 31, lr: 3.72e-03
2024-08-06 19:32:46,937 INFO [trainer.py:765] (2/8) Epoch 23, batch 1300, train_loss[loss=3.094, NarTop10Accuracy=0.7, over 5070.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7039, over 5969.65 frames. ], batch size: 6, lr: 3.72e-03
2024-08-06 19:32:56,402 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 19:33:04,722 INFO [trainer.py:811] (2/8) Epoch 23, validation: loss=2.893, NarTop10Accuracy=0.7468, over 1905321.00 frames. 
2024-08-06 19:33:04,723 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 19:33:05,262 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.759e+02 2.108e+02 2.273e+02 2.457e+02 3.966e+02, threshold=4.546e+02, percent-clipped=0.0
2024-08-06 19:33:27,407 INFO [trainer.py:765] (2/8) Epoch 23, batch 1400, train_loss[loss=2.79, NarTop10Accuracy=0.7723, over 6198.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7035, over 5987.66 frames. ], batch size: 11, lr: 3.72e-03
2024-08-06 19:33:58,216 INFO [trainer.py:765] (2/8) Epoch 23, batch 1500, train_loss[loss=3.237, NarTop10Accuracy=0.6851, over 5901.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7065, over 5939.66 frames. ], batch size: 52, lr: 3.71e-03
2024-08-06 19:34:26,015 INFO [trainer.py:765] (2/8) Epoch 23, batch 1600, train_loss[loss=2.957, NarTop10Accuracy=0.7356, over 6987.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.7058, over 5915.55 frames. ], batch size: 22, lr: 3.71e-03
2024-08-06 19:34:52,783 INFO [trainer.py:765] (2/8) Epoch 23, batch 1700, train_loss[loss=3.351, NarTop10Accuracy=0.6536, over 6549.00 frames. ], tot_loss[loss=3.124, NarTop10Accuracy=0.7012, over 5928.22 frames. ], batch size: 14, lr: 3.71e-03
2024-08-06 19:35:19,262 INFO [trainer.py:765] (2/8) Epoch 23, batch 1800, train_loss[loss=2.988, NarTop10Accuracy=0.727, over 7038.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7024, over 5985.92 frames. ], batch size: 22, lr: 3.70e-03
2024-08-06 19:35:45,597 INFO [trainer.py:765] (2/8) Epoch 23, batch 1900, train_loss[loss=3.377, NarTop10Accuracy=0.6489, over 5697.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7006, over 6008.94 frames. ], batch size: 52, lr: 3.70e-03
2024-08-06 19:36:11,171 INFO [trainer.py:765] (2/8) Epoch 23, batch 2000, train_loss[loss=3.655, NarTop10Accuracy=0.5943, over 6015.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7032, over 5994.07 frames. ], batch size: 50, lr: 3.70e-03
2024-08-06 19:36:36,517 INFO [trainer.py:765] (2/8) Epoch 23, batch 2100, train_loss[loss=3.451, NarTop10Accuracy=0.6478, over 4020.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7037, over 5966.80 frames. ], batch size: 4, lr: 3.69e-03
2024-08-06 19:37:01,908 INFO [trainer.py:765] (2/8) Epoch 23, batch 2200, train_loss[loss=3.067, NarTop10Accuracy=0.7186, over 7362.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.6999, over 5986.88 frames. ], batch size: 31, lr: 3.69e-03
2024-08-06 19:37:27,061 INFO [trainer.py:765] (2/8) Epoch 23, batch 2300, train_loss[loss=2.959, NarTop10Accuracy=0.7408, over 5649.00 frames. ], tot_loss[loss=3.123, NarTop10Accuracy=0.7009, over 6008.06 frames. ], batch size: 9, lr: 3.69e-03
2024-08-06 19:37:51,424 INFO [trainer.py:765] (2/8) Epoch 23, batch 2400, train_loss[loss=2.974, NarTop10Accuracy=0.7368, over 5124.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7013, over 5773.93 frames. ], batch size: 7, lr: 3.69e-03
2024-08-06 19:38:15,053 INFO [trainer.py:765] (2/8) Epoch 23, batch 2500, train_loss[loss=3.321, NarTop10Accuracy=0.6561, over 5160.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7066, over 5477.30 frames. ], batch size: 7, lr: 3.68e-03
2024-08-06 19:38:35,062 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 19:39:37,632 INFO [trainer.py:765] (2/8) Epoch 24, batch 100, train_loss[loss=3.472, NarTop10Accuracy=0.6281, over 7380.00 frames. ], tot_loss[loss=3.129, NarTop10Accuracy=0.7007, over 2378.09 frames. ], batch size: 31, lr: 3.60e-03
2024-08-06 19:40:10,190 INFO [trainer.py:765] (2/8) Epoch 24, batch 200, train_loss[loss=2.796, NarTop10Accuracy=0.7725, over 6768.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.7063, over 3864.48 frames. ], batch size: 17, lr: 3.60e-03
2024-08-06 19:40:40,556 INFO [trainer.py:765] (2/8) Epoch 24, batch 300, train_loss[loss=2.924, NarTop10Accuracy=0.7407, over 7167.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.707, over 4649.64 frames. ], batch size: 22, lr: 3.59e-03
2024-08-06 19:41:18,234 INFO [trainer.py:765] (2/8) Epoch 24, batch 400, train_loss[loss=2.97, NarTop10Accuracy=0.7287, over 5151.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7048, over 5109.26 frames. ], batch size: 7, lr: 3.59e-03
2024-08-06 19:41:50,322 INFO [trainer.py:765] (2/8) Epoch 24, batch 500, train_loss[loss=2.948, NarTop10Accuracy=0.7383, over 6228.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7077, over 5387.72 frames. ], batch size: 11, lr: 3.59e-03
2024-08-06 19:42:21,452 INFO [trainer.py:765] (2/8) Epoch 24, batch 600, train_loss[loss=2.798, NarTop10Accuracy=0.7631, over 5745.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7078, over 5650.21 frames. ], batch size: 9, lr: 3.58e-03
2024-08-06 19:42:52,843 INFO [trainer.py:765] (2/8) Epoch 24, batch 700, train_loss[loss=2.817, NarTop10Accuracy=0.7575, over 5106.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7078, over 5728.81 frames. ], batch size: 6, lr: 3.58e-03
2024-08-06 19:43:17,381 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 19:43:25,410 INFO [trainer.py:811] (2/8) Epoch 24, validation: loss=3.021, NarTop10Accuracy=0.7204, over 1905321.00 frames. 
2024-08-06 19:43:25,411 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 19:43:28,562 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.744e+02 2.113e+02 2.282e+02 2.472e+02 2.357e+03, threshold=4.564e+02, percent-clipped=0.2
2024-08-06 19:43:40,814 INFO [trainer.py:765] (2/8) Epoch 24, batch 800, train_loss[loss=2.701, NarTop10Accuracy=0.7793, over 4401.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7085, over 5785.11 frames. ], batch size: 5, lr: 3.58e-03
2024-08-06 19:44:11,410 INFO [trainer.py:765] (2/8) Epoch 24, batch 900, train_loss[loss=2.795, NarTop10Accuracy=0.7615, over 6123.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7094, over 5783.74 frames. ], batch size: 13, lr: 3.57e-03
2024-08-06 19:44:47,489 INFO [trainer.py:765] (2/8) Epoch 24, batch 1000, train_loss[loss=3.265, NarTop10Accuracy=0.6739, over 6231.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7068, over 5873.93 frames. ], batch size: 13, lr: 3.57e-03
2024-08-06 19:45:27,107 INFO [trainer.py:765] (2/8) Epoch 24, batch 1100, train_loss[loss=3.427, NarTop10Accuracy=0.6382, over 6888.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7037, over 5908.93 frames. ], batch size: 17, lr: 3.57e-03
2024-08-06 19:45:58,437 INFO [trainer.py:765] (2/8) Epoch 24, batch 1200, train_loss[loss=3.016, NarTop10Accuracy=0.7259, over 7119.00 frames. ], tot_loss[loss=3.107, NarTop10Accuracy=0.7047, over 5922.07 frames. ], batch size: 31, lr: 3.57e-03
2024-08-06 19:46:30,294 INFO [trainer.py:765] (2/8) Epoch 24, batch 1300, train_loss[loss=3.447, NarTop10Accuracy=0.6339, over 5040.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7061, over 6001.22 frames. ], batch size: 6, lr: 3.56e-03
2024-08-06 19:47:07,859 INFO [trainer.py:765] (2/8) Epoch 24, batch 1400, train_loss[loss=3.304, NarTop10Accuracy=0.6647, over 6027.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.704, over 6011.75 frames. ], batch size: 11, lr: 3.56e-03
2024-08-06 19:47:40,956 INFO [trainer.py:765] (2/8) Epoch 24, batch 1500, train_loss[loss=3.431, NarTop10Accuracy=0.6428, over 6186.00 frames. ], tot_loss[loss=3.119, NarTop10Accuracy=0.7019, over 5943.60 frames. ], batch size: 50, lr: 3.56e-03
2024-08-06 19:48:08,676 INFO [trainer.py:765] (2/8) Epoch 24, batch 1600, train_loss[loss=3.563, NarTop10Accuracy=0.6098, over 7068.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7011, over 5914.27 frames. ], batch size: 22, lr: 3.55e-03
2024-08-06 19:48:35,267 INFO [trainer.py:765] (2/8) Epoch 24, batch 1700, train_loss[loss=2.905, NarTop10Accuracy=0.7559, over 6333.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7019, over 5912.78 frames. ], batch size: 13, lr: 3.55e-03
2024-08-06 19:49:01,637 INFO [trainer.py:765] (2/8) Epoch 24, batch 1800, train_loss[loss=2.881, NarTop10Accuracy=0.7565, over 7437.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7007, over 5983.34 frames. ], batch size: 23, lr: 3.55e-03
2024-08-06 19:49:28,042 INFO [trainer.py:765] (2/8) Epoch 24, batch 1900, train_loss[loss=3.587, NarTop10Accuracy=0.6095, over 6336.00 frames. ], tot_loss[loss=3.137, NarTop10Accuracy=0.6982, over 6022.19 frames. ], batch size: 52, lr: 3.55e-03
2024-08-06 19:49:53,533 INFO [trainer.py:765] (2/8) Epoch 24, batch 2000, train_loss[loss=3.573, NarTop10Accuracy=0.6128, over 6180.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7028, over 5993.01 frames. ], batch size: 50, lr: 3.54e-03
2024-08-06 19:50:18,819 INFO [trainer.py:765] (2/8) Epoch 24, batch 2100, train_loss[loss=2.831, NarTop10Accuracy=0.7572, over 4038.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.704, over 5974.95 frames. ], batch size: 4, lr: 3.54e-03
2024-08-06 19:50:43,942 INFO [trainer.py:765] (2/8) Epoch 24, batch 2200, train_loss[loss=3.465, NarTop10Accuracy=0.632, over 7461.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7037, over 6013.93 frames. ], batch size: 31, lr: 3.54e-03
2024-08-06 19:51:09,024 INFO [trainer.py:765] (2/8) Epoch 24, batch 2300, train_loss[loss=3.004, NarTop10Accuracy=0.7242, over 5724.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7039, over 6020.73 frames. ], batch size: 9, lr: 3.53e-03
2024-08-06 19:51:33,348 INFO [trainer.py:765] (2/8) Epoch 24, batch 2400, train_loss[loss=2.95, NarTop10Accuracy=0.7409, over 5775.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7062, over 5772.35 frames. ], batch size: 8, lr: 3.53e-03
2024-08-06 19:51:56,783 INFO [trainer.py:765] (2/8) Epoch 24, batch 2500, train_loss[loss=2.835, NarTop10Accuracy=0.761, over 5211.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7095, over 5474.06 frames. ], batch size: 7, lr: 3.53e-03
2024-08-06 19:52:16,971 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 19:53:22,198 INFO [trainer.py:765] (2/8) Epoch 25, batch 100, train_loss[loss=3.341, NarTop10Accuracy=0.659, over 7059.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7095, over 2362.24 frames. ], batch size: 31, lr: 3.45e-03
2024-08-06 19:53:47,262 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 19:53:55,329 INFO [trainer.py:811] (2/8) Epoch 25, validation: loss=2.96, NarTop10Accuracy=0.7332, over 1905321.00 frames. 
2024-08-06 19:53:55,329 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 19:53:55,916 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.693e+02 2.155e+02 2.306e+02 2.475e+02 6.485e+02, threshold=4.611e+02, percent-clipped=0.1
2024-08-06 19:54:01,176 INFO [trainer.py:765] (2/8) Epoch 25, batch 200, train_loss[loss=2.899, NarTop10Accuracy=0.7497, over 6789.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7078, over 3858.05 frames. ], batch size: 17, lr: 3.45e-03
2024-08-06 19:54:35,646 INFO [trainer.py:765] (2/8) Epoch 25, batch 300, train_loss[loss=3.16, NarTop10Accuracy=0.6911, over 7020.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7094, over 4645.76 frames. ], batch size: 22, lr: 3.45e-03
2024-08-06 19:55:12,958 INFO [trainer.py:765] (2/8) Epoch 25, batch 400, train_loss[loss=2.973, NarTop10Accuracy=0.7328, over 5025.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7099, over 5104.35 frames. ], batch size: 7, lr: 3.44e-03
2024-08-06 19:55:43,737 INFO [trainer.py:765] (2/8) Epoch 25, batch 500, train_loss[loss=2.773, NarTop10Accuracy=0.7754, over 6081.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7104, over 5373.57 frames. ], batch size: 11, lr: 3.44e-03
2024-08-06 19:56:14,814 INFO [trainer.py:765] (2/8) Epoch 25, batch 600, train_loss[loss=2.927, NarTop10Accuracy=0.7359, over 5793.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7105, over 5641.69 frames. ], batch size: 9, lr: 3.44e-03
2024-08-06 19:56:55,496 INFO [trainer.py:765] (2/8) Epoch 25, batch 700, train_loss[loss=2.735, NarTop10Accuracy=0.7781, over 5010.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.711, over 5705.78 frames. ], batch size: 6, lr: 3.43e-03
2024-08-06 19:57:30,136 INFO [trainer.py:765] (2/8) Epoch 25, batch 800, train_loss[loss=2.896, NarTop10Accuracy=0.7499, over 5109.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7095, over 5776.74 frames. ], batch size: 6, lr: 3.43e-03
2024-08-06 19:58:00,678 INFO [trainer.py:765] (2/8) Epoch 25, batch 900, train_loss[loss=3.084, NarTop10Accuracy=0.705, over 6423.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7101, over 5788.93 frames. ], batch size: 13, lr: 3.43e-03
2024-08-06 19:58:37,640 INFO [trainer.py:765] (2/8) Epoch 25, batch 1000, train_loss[loss=2.759, NarTop10Accuracy=0.7687, over 6213.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7066, over 5885.17 frames. ], batch size: 13, lr: 3.43e-03
2024-08-06 19:59:14,854 INFO [trainer.py:765] (2/8) Epoch 25, batch 1100, train_loss[loss=3.445, NarTop10Accuracy=0.6332, over 6843.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7053, over 5915.90 frames. ], batch size: 17, lr: 3.42e-03
2024-08-06 19:59:49,039 INFO [trainer.py:765] (2/8) Epoch 25, batch 1200, train_loss[loss=3.344, NarTop10Accuracy=0.6487, over 7296.00 frames. ], tot_loss[loss=3.099, NarTop10Accuracy=0.7059, over 5921.75 frames. ], batch size: 31, lr: 3.42e-03
2024-08-06 20:00:25,598 INFO [trainer.py:765] (2/8) Epoch 25, batch 1300, train_loss[loss=2.994, NarTop10Accuracy=0.7323, over 4989.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7081, over 5977.84 frames. ], batch size: 6, lr: 3.42e-03
2024-08-06 20:01:02,015 INFO [trainer.py:765] (2/8) Epoch 25, batch 1400, train_loss[loss=2.828, NarTop10Accuracy=0.7641, over 6078.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7096, over 6018.23 frames. ], batch size: 11, lr: 3.42e-03
2024-08-06 20:01:32,822 INFO [trainer.py:765] (2/8) Epoch 25, batch 1500, train_loss[loss=3.218, NarTop10Accuracy=0.6875, over 6738.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7075, over 5959.17 frames. ], batch size: 52, lr: 3.41e-03
2024-08-06 20:02:00,624 INFO [trainer.py:765] (2/8) Epoch 25, batch 1600, train_loss[loss=2.846, NarTop10Accuracy=0.7496, over 6882.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7078, over 5934.43 frames. ], batch size: 22, lr: 3.41e-03
2024-08-06 20:02:27,359 INFO [trainer.py:765] (2/8) Epoch 25, batch 1700, train_loss[loss=3.027, NarTop10Accuracy=0.7217, over 6354.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7078, over 5915.27 frames. ], batch size: 13, lr: 3.41e-03
2024-08-06 20:02:53,853 INFO [trainer.py:765] (2/8) Epoch 25, batch 1800, train_loss[loss=3.315, NarTop10Accuracy=0.6568, over 7236.00 frames. ], tot_loss[loss=3.107, NarTop10Accuracy=0.7041, over 5977.16 frames. ], batch size: 23, lr: 3.40e-03
2024-08-06 20:03:20,340 INFO [trainer.py:765] (2/8) Epoch 25, batch 1900, train_loss[loss=3.182, NarTop10Accuracy=0.6892, over 5643.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.703, over 6028.29 frames. ], batch size: 50, lr: 3.40e-03
2024-08-06 20:03:45,933 INFO [trainer.py:765] (2/8) Epoch 25, batch 2000, train_loss[loss=3.486, NarTop10Accuracy=0.6274, over 6444.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7011, over 5995.00 frames. ], batch size: 50, lr: 3.40e-03
2024-08-06 20:04:11,245 INFO [trainer.py:765] (2/8) Epoch 25, batch 2100, train_loss[loss=2.776, NarTop10Accuracy=0.7657, over 3900.00 frames. ], tot_loss[loss=3.107, NarTop10Accuracy=0.7037, over 5950.01 frames. ], batch size: 4, lr: 3.40e-03
2024-08-06 20:04:31,409 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 20:04:39,344 INFO [trainer.py:811] (2/8) Epoch 25, validation: loss=2.999, NarTop10Accuracy=0.7251, over 1905321.00 frames. 
2024-08-06 20:04:39,344 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 20:04:39,840 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.755e+02 2.185e+02 2.339e+02 2.507e+02 3.640e+02, threshold=4.678e+02, percent-clipped=0.0
2024-08-06 20:04:44,512 INFO [trainer.py:765] (2/8) Epoch 25, batch 2200, train_loss[loss=3.302, NarTop10Accuracy=0.6617, over 7311.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7024, over 6010.14 frames. ], batch size: 31, lr: 3.39e-03
2024-08-06 20:05:09,645 INFO [trainer.py:765] (2/8) Epoch 25, batch 2300, train_loss[loss=2.883, NarTop10Accuracy=0.7437, over 5640.00 frames. ], tot_loss[loss=3.117, NarTop10Accuracy=0.7022, over 6017.61 frames. ], batch size: 9, lr: 3.39e-03
2024-08-06 20:05:34,141 INFO [trainer.py:765] (2/8) Epoch 25, batch 2400, train_loss[loss=2.849, NarTop10Accuracy=0.7546, over 5145.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.705, over 5777.04 frames. ], batch size: 7, lr: 3.39e-03
2024-08-06 20:05:57,846 INFO [trainer.py:765] (2/8) Epoch 25, batch 2500, train_loss[loss=2.892, NarTop10Accuracy=0.7555, over 5061.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7116, over 5476.09 frames. ], batch size: 7, lr: 3.39e-03
2024-08-06 20:06:18,175 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 20:07:19,304 INFO [trainer.py:765] (2/8) Epoch 26, batch 100, train_loss[loss=3.013, NarTop10Accuracy=0.7144, over 7371.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7074, over 2357.20 frames. ], batch size: 31, lr: 3.32e-03
2024-08-06 20:07:52,381 INFO [trainer.py:765] (2/8) Epoch 26, batch 200, train_loss[loss=2.78, NarTop10Accuracy=0.7681, over 6687.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7061, over 3859.29 frames. ], batch size: 17, lr: 3.31e-03
2024-08-06 20:08:24,733 INFO [trainer.py:765] (2/8) Epoch 26, batch 300, train_loss[loss=3.009, NarTop10Accuracy=0.7251, over 6930.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7084, over 4647.90 frames. ], batch size: 22, lr: 3.31e-03
2024-08-06 20:08:58,184 INFO [trainer.py:765] (2/8) Epoch 26, batch 400, train_loss[loss=3.008, NarTop10Accuracy=0.7076, over 5214.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7088, over 5095.07 frames. ], batch size: 7, lr: 3.31e-03
2024-08-06 20:09:33,147 INFO [trainer.py:765] (2/8) Epoch 26, batch 500, train_loss[loss=2.824, NarTop10Accuracy=0.765, over 6084.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.708, over 5374.36 frames. ], batch size: 11, lr: 3.30e-03
2024-08-06 20:10:03,890 INFO [trainer.py:765] (2/8) Epoch 26, batch 600, train_loss[loss=2.734, NarTop10Accuracy=0.7818, over 5718.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7119, over 5645.44 frames. ], batch size: 9, lr: 3.30e-03
2024-08-06 20:10:39,872 INFO [trainer.py:765] (2/8) Epoch 26, batch 700, train_loss[loss=3.129, NarTop10Accuracy=0.6946, over 5181.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7075, over 5705.34 frames. ], batch size: 6, lr: 3.30e-03
2024-08-06 20:11:19,060 INFO [trainer.py:765] (2/8) Epoch 26, batch 800, train_loss[loss=3, NarTop10Accuracy=0.7278, over 5052.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7082, over 5770.41 frames. ], batch size: 6, lr: 3.30e-03
2024-08-06 20:11:49,315 INFO [trainer.py:765] (2/8) Epoch 26, batch 900, train_loss[loss=2.845, NarTop10Accuracy=0.7552, over 6042.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7092, over 5800.97 frames. ], batch size: 13, lr: 3.29e-03
2024-08-06 20:12:25,972 INFO [trainer.py:765] (2/8) Epoch 26, batch 1000, train_loss[loss=2.906, NarTop10Accuracy=0.7452, over 6183.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7062, over 5902.74 frames. ], batch size: 13, lr: 3.29e-03
2024-08-06 20:13:06,376 INFO [trainer.py:765] (2/8) Epoch 26, batch 1100, train_loss[loss=3.316, NarTop10Accuracy=0.6612, over 6723.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7047, over 5929.56 frames. ], batch size: 17, lr: 3.29e-03
2024-08-06 20:13:37,535 INFO [trainer.py:765] (2/8) Epoch 26, batch 1200, train_loss[loss=3.329, NarTop10Accuracy=0.6581, over 7314.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7074, over 5932.49 frames. ], batch size: 31, lr: 3.29e-03
2024-08-06 20:14:13,695 INFO [trainer.py:765] (2/8) Epoch 26, batch 1300, train_loss[loss=2.829, NarTop10Accuracy=0.768, over 5118.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7088, over 6006.19 frames. ], batch size: 6, lr: 3.28e-03
2024-08-06 20:14:50,538 INFO [trainer.py:765] (2/8) Epoch 26, batch 1400, train_loss[loss=2.921, NarTop10Accuracy=0.7479, over 6072.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.709, over 6019.38 frames. ], batch size: 11, lr: 3.28e-03
2024-08-06 20:15:21,155 INFO [trainer.py:765] (2/8) Epoch 26, batch 1500, train_loss[loss=3.153, NarTop10Accuracy=0.6994, over 6555.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7095, over 5952.76 frames. ], batch size: 51, lr: 3.28e-03
2024-08-06 20:15:48,979 INFO [trainer.py:765] (2/8) Epoch 26, batch 1600, train_loss[loss=3.002, NarTop10Accuracy=0.7176, over 6939.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7108, over 5925.06 frames. ], batch size: 22, lr: 3.28e-03
2024-08-06 20:15:50,001 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 20:15:58,238 INFO [trainer.py:811] (2/8) Epoch 26, validation: loss=2.899, NarTop10Accuracy=0.7457, over 1905321.00 frames. 
2024-08-06 20:15:58,239 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 20:15:58,778 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.752e+02 2.166e+02 2.322e+02 2.511e+02 3.952e+02, threshold=4.644e+02, percent-clipped=0.0
2024-08-06 20:16:23,951 INFO [trainer.py:765] (2/8) Epoch 26, batch 1700, train_loss[loss=3.137, NarTop10Accuracy=0.6919, over 6621.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7126, over 5929.30 frames. ], batch size: 14, lr: 3.28e-03
2024-08-06 20:16:50,425 INFO [trainer.py:765] (2/8) Epoch 26, batch 1800, train_loss[loss=2.715, NarTop10Accuracy=0.7849, over 7074.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7117, over 5986.66 frames. ], batch size: 22, lr: 3.27e-03
2024-08-06 20:17:16,839 INFO [trainer.py:765] (2/8) Epoch 26, batch 1900, train_loss[loss=3.105, NarTop10Accuracy=0.7105, over 6069.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7077, over 6038.52 frames. ], batch size: 50, lr: 3.27e-03
2024-08-06 20:17:42,378 INFO [trainer.py:765] (2/8) Epoch 26, batch 2000, train_loss[loss=3.561, NarTop10Accuracy=0.6162, over 5913.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7066, over 5998.75 frames. ], batch size: 50, lr: 3.27e-03
2024-08-06 20:18:07,562 INFO [trainer.py:765] (2/8) Epoch 26, batch 2100, train_loss[loss=3.091, NarTop10Accuracy=0.7035, over 4815.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7049, over 5972.30 frames. ], batch size: 5, lr: 3.27e-03
2024-08-06 20:18:32,775 INFO [trainer.py:765] (2/8) Epoch 26, batch 2200, train_loss[loss=2.974, NarTop10Accuracy=0.7377, over 7023.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7066, over 5996.89 frames. ], batch size: 31, lr: 3.26e-03
2024-08-06 20:18:57,896 INFO [trainer.py:765] (2/8) Epoch 26, batch 2300, train_loss[loss=3.238, NarTop10Accuracy=0.6576, over 5664.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.705, over 6006.45 frames. ], batch size: 9, lr: 3.26e-03
2024-08-06 20:19:22,204 INFO [trainer.py:765] (2/8) Epoch 26, batch 2400, train_loss[loss=2.895, NarTop10Accuracy=0.7515, over 5172.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7093, over 5766.28 frames. ], batch size: 7, lr: 3.26e-03
2024-08-06 20:19:45,650 INFO [trainer.py:765] (2/8) Epoch 26, batch 2500, train_loss[loss=2.7, NarTop10Accuracy=0.7895, over 5115.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7155, over 5481.51 frames. ], batch size: 7, lr: 3.26e-03
2024-08-06 20:20:05,853 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 20:21:04,874 INFO [trainer.py:765] (2/8) Epoch 27, batch 100, train_loss[loss=3.182, NarTop10Accuracy=0.6939, over 7332.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7105, over 2367.74 frames. ], batch size: 32, lr: 3.19e-03
2024-08-06 20:21:39,783 INFO [trainer.py:765] (2/8) Epoch 27, batch 200, train_loss[loss=2.79, NarTop10Accuracy=0.7733, over 7005.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7093, over 3854.98 frames. ], batch size: 17, lr: 3.19e-03
2024-08-06 20:22:13,050 INFO [trainer.py:765] (2/8) Epoch 27, batch 300, train_loss[loss=2.887, NarTop10Accuracy=0.7494, over 6993.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7105, over 4657.25 frames. ], batch size: 22, lr: 3.18e-03
2024-08-06 20:22:43,557 INFO [trainer.py:765] (2/8) Epoch 27, batch 400, train_loss[loss=2.789, NarTop10Accuracy=0.7663, over 5190.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7129, over 5102.67 frames. ], batch size: 7, lr: 3.18e-03
2024-08-06 20:23:18,084 INFO [trainer.py:765] (2/8) Epoch 27, batch 500, train_loss[loss=2.776, NarTop10Accuracy=0.7641, over 6066.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7153, over 5393.35 frames. ], batch size: 11, lr: 3.18e-03
2024-08-06 20:23:51,435 INFO [trainer.py:765] (2/8) Epoch 27, batch 600, train_loss[loss=3.297, NarTop10Accuracy=0.6697, over 5679.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7143, over 5666.78 frames. ], batch size: 9, lr: 3.18e-03
2024-08-06 20:24:24,975 INFO [trainer.py:765] (2/8) Epoch 27, batch 700, train_loss[loss=2.873, NarTop10Accuracy=0.7528, over 5136.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7152, over 5727.46 frames. ], batch size: 6, lr: 3.18e-03
2024-08-06 20:25:03,408 INFO [trainer.py:765] (2/8) Epoch 27, batch 800, train_loss[loss=2.973, NarTop10Accuracy=0.7236, over 5217.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7105, over 5785.35 frames. ], batch size: 6, lr: 3.17e-03
2024-08-06 20:25:34,176 INFO [trainer.py:765] (2/8) Epoch 27, batch 900, train_loss[loss=3.199, NarTop10Accuracy=0.6937, over 6552.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7111, over 5808.56 frames. ], batch size: 14, lr: 3.17e-03
2024-08-06 20:26:10,097 INFO [trainer.py:765] (2/8) Epoch 27, batch 1000, train_loss[loss=2.86, NarTop10Accuracy=0.7593, over 6240.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7103, over 5897.39 frames. ], batch size: 13, lr: 3.17e-03
2024-08-06 20:26:18,315 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 20:26:26,346 INFO [trainer.py:811] (2/8) Epoch 27, validation: loss=2.95, NarTop10Accuracy=0.735, over 1905321.00 frames. 
2024-08-06 20:26:26,347 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 20:26:26,877 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.789e+02 2.166e+02 2.331e+02 2.512e+02 4.284e+02, threshold=4.663e+02, percent-clipped=0.0
2024-08-06 20:26:50,899 INFO [trainer.py:765] (2/8) Epoch 27, batch 1100, train_loss[loss=2.957, NarTop10Accuracy=0.7346, over 6912.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.71, over 5941.72 frames. ], batch size: 17, lr: 3.17e-03
2024-08-06 20:27:24,545 INFO [trainer.py:765] (2/8) Epoch 27, batch 1200, train_loss[loss=2.865, NarTop10Accuracy=0.7491, over 7260.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7105, over 5935.14 frames. ], batch size: 31, lr: 3.16e-03
2024-08-06 20:27:58,568 INFO [trainer.py:765] (2/8) Epoch 27, batch 1300, train_loss[loss=2.856, NarTop10Accuracy=0.7573, over 5058.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7124, over 5988.34 frames. ], batch size: 6, lr: 3.16e-03
2024-08-06 20:28:36,745 INFO [trainer.py:765] (2/8) Epoch 27, batch 1400, train_loss[loss=3.25, NarTop10Accuracy=0.6675, over 5979.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7076, over 5992.76 frames. ], batch size: 11, lr: 3.16e-03
2024-08-06 20:29:04,632 INFO [trainer.py:765] (2/8) Epoch 27, batch 1500, train_loss[loss=3.006, NarTop10Accuracy=0.7277, over 5835.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7087, over 5930.07 frames. ], batch size: 50, lr: 3.16e-03
2024-08-06 20:29:32,362 INFO [trainer.py:765] (2/8) Epoch 27, batch 1600, train_loss[loss=2.742, NarTop10Accuracy=0.7785, over 7176.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.707, over 5909.78 frames. ], batch size: 22, lr: 3.15e-03
2024-08-06 20:29:58,977 INFO [trainer.py:765] (2/8) Epoch 27, batch 1700, train_loss[loss=3.278, NarTop10Accuracy=0.6712, over 6651.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7095, over 5905.27 frames. ], batch size: 14, lr: 3.15e-03
2024-08-06 20:30:25,463 INFO [trainer.py:765] (2/8) Epoch 27, batch 1800, train_loss[loss=3.403, NarTop10Accuracy=0.6434, over 6960.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7081, over 5971.29 frames. ], batch size: 22, lr: 3.15e-03
2024-08-06 20:30:51,845 INFO [trainer.py:765] (2/8) Epoch 27, batch 1900, train_loss[loss=3.101, NarTop10Accuracy=0.7005, over 6303.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7076, over 6015.16 frames. ], batch size: 50, lr: 3.15e-03
2024-08-06 20:31:17,390 INFO [trainer.py:765] (2/8) Epoch 27, batch 2000, train_loss[loss=3.121, NarTop10Accuracy=0.7007, over 6477.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7105, over 5993.89 frames. ], batch size: 50, lr: 3.15e-03
2024-08-06 20:31:42,659 INFO [trainer.py:765] (2/8) Epoch 27, batch 2100, train_loss[loss=2.58, NarTop10Accuracy=0.805, over 4704.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7108, over 5991.96 frames. ], batch size: 5, lr: 3.14e-03
2024-08-06 20:32:07,804 INFO [trainer.py:765] (2/8) Epoch 27, batch 2200, train_loss[loss=3.323, NarTop10Accuracy=0.6547, over 7167.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7088, over 6018.48 frames. ], batch size: 32, lr: 3.14e-03
2024-08-06 20:32:32,942 INFO [trainer.py:765] (2/8) Epoch 27, batch 2300, train_loss[loss=2.866, NarTop10Accuracy=0.7534, over 5841.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7083, over 6025.78 frames. ], batch size: 9, lr: 3.14e-03
2024-08-06 20:32:57,246 INFO [trainer.py:765] (2/8) Epoch 27, batch 2400, train_loss[loss=2.735, NarTop10Accuracy=0.7798, over 5031.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7067, over 5783.51 frames. ], batch size: 7, lr: 3.14e-03
2024-08-06 20:33:20,615 INFO [trainer.py:765] (2/8) Epoch 27, batch 2500, train_loss[loss=3.347, NarTop10Accuracy=0.6446, over 5103.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7119, over 5473.59 frames. ], batch size: 7, lr: 3.13e-03
2024-08-06 20:33:40,891 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 20:34:35,831 INFO [trainer.py:765] (2/8) Epoch 28, batch 100, train_loss[loss=3.035, NarTop10Accuracy=0.7259, over 7575.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7075, over 2370.80 frames. ], batch size: 31, lr: 3.07e-03
2024-08-06 20:35:07,393 INFO [trainer.py:765] (2/8) Epoch 28, batch 200, train_loss[loss=2.694, NarTop10Accuracy=0.7811, over 6918.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7082, over 3860.88 frames. ], batch size: 17, lr: 3.07e-03
2024-08-06 20:35:45,422 INFO [trainer.py:765] (2/8) Epoch 28, batch 300, train_loss[loss=3.085, NarTop10Accuracy=0.7137, over 7245.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.711, over 4654.47 frames. ], batch size: 22, lr: 3.07e-03
2024-08-06 20:36:15,865 INFO [trainer.py:765] (2/8) Epoch 28, batch 400, train_loss[loss=3.184, NarTop10Accuracy=0.6805, over 5193.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7078, over 5089.01 frames. ], batch size: 7, lr: 3.07e-03
2024-08-06 20:36:32,406 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 20:36:40,530 INFO [trainer.py:811] (2/8) Epoch 28, validation: loss=2.963, NarTop10Accuracy=0.7327, over 1905321.00 frames. 
2024-08-06 20:36:40,531 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 20:36:41,103 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.761e+02 2.179e+02 2.348e+02 2.536e+02 3.573e+02, threshold=4.696e+02, percent-clipped=0.0
2024-08-06 20:36:56,664 INFO [trainer.py:765] (2/8) Epoch 28, batch 500, train_loss[loss=3.121, NarTop10Accuracy=0.7012, over 6033.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7108, over 5370.24 frames. ], batch size: 11, lr: 3.06e-03
2024-08-06 20:37:29,463 INFO [trainer.py:765] (2/8) Epoch 28, batch 600, train_loss[loss=2.916, NarTop10Accuracy=0.7479, over 5679.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7097, over 5644.92 frames. ], batch size: 9, lr: 3.06e-03
2024-08-06 20:38:08,892 INFO [trainer.py:765] (2/8) Epoch 28, batch 700, train_loss[loss=3.166, NarTop10Accuracy=0.6837, over 4941.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7071, over 5734.23 frames. ], batch size: 6, lr: 3.06e-03
2024-08-06 20:38:42,490 INFO [trainer.py:765] (2/8) Epoch 28, batch 800, train_loss[loss=3.024, NarTop10Accuracy=0.7227, over 5100.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7125, over 5782.48 frames. ], batch size: 6, lr: 3.06e-03
2024-08-06 20:39:15,507 INFO [trainer.py:765] (2/8) Epoch 28, batch 900, train_loss[loss=3.209, NarTop10Accuracy=0.6846, over 6156.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7138, over 5804.26 frames. ], batch size: 13, lr: 3.06e-03
2024-08-06 20:39:53,240 INFO [trainer.py:765] (2/8) Epoch 28, batch 1000, train_loss[loss=3.156, NarTop10Accuracy=0.6816, over 6489.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7132, over 5909.64 frames. ], batch size: 14, lr: 3.05e-03
2024-08-06 20:40:25,868 INFO [trainer.py:765] (2/8) Epoch 28, batch 1100, train_loss[loss=2.845, NarTop10Accuracy=0.761, over 6855.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7094, over 5931.61 frames. ], batch size: 17, lr: 3.05e-03
2024-08-06 20:40:59,419 INFO [trainer.py:765] (2/8) Epoch 28, batch 1200, train_loss[loss=3.295, NarTop10Accuracy=0.6663, over 7347.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.708, over 5917.51 frames. ], batch size: 31, lr: 3.05e-03
2024-08-06 20:41:38,681 INFO [trainer.py:765] (2/8) Epoch 28, batch 1300, train_loss[loss=3.247, NarTop10Accuracy=0.6537, over 4323.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7087, over 5984.69 frames. ], batch size: 5, lr: 3.05e-03
2024-08-06 20:42:13,047 INFO [trainer.py:765] (2/8) Epoch 28, batch 1400, train_loss[loss=2.877, NarTop10Accuracy=0.751, over 6138.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7078, over 6003.42 frames. ], batch size: 11, lr: 3.04e-03
2024-08-06 20:42:43,171 INFO [trainer.py:765] (2/8) Epoch 28, batch 1500, train_loss[loss=3.419, NarTop10Accuracy=0.6368, over 5742.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7098, over 5953.63 frames. ], batch size: 50, lr: 3.04e-03
2024-08-06 20:43:11,081 INFO [trainer.py:765] (2/8) Epoch 28, batch 1600, train_loss[loss=2.841, NarTop10Accuracy=0.7585, over 7071.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.71, over 5944.73 frames. ], batch size: 22, lr: 3.04e-03
2024-08-06 20:43:37,786 INFO [trainer.py:765] (2/8) Epoch 28, batch 1700, train_loss[loss=2.895, NarTop10Accuracy=0.7427, over 6411.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.709, over 5925.99 frames. ], batch size: 13, lr: 3.04e-03
2024-08-06 20:44:04,326 INFO [trainer.py:765] (2/8) Epoch 28, batch 1800, train_loss[loss=3.177, NarTop10Accuracy=0.7009, over 7017.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.71, over 5985.51 frames. ], batch size: 22, lr: 3.04e-03
2024-08-06 20:44:30,758 INFO [trainer.py:765] (2/8) Epoch 28, batch 1900, train_loss[loss=3.123, NarTop10Accuracy=0.7006, over 5874.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7114, over 6023.49 frames. ], batch size: 50, lr: 3.03e-03
2024-08-06 20:44:56,328 INFO [trainer.py:765] (2/8) Epoch 28, batch 2000, train_loss[loss=2.969, NarTop10Accuracy=0.7321, over 6558.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7134, over 5994.61 frames. ], batch size: 51, lr: 3.03e-03
2024-08-06 20:45:21,651 INFO [trainer.py:765] (2/8) Epoch 28, batch 2100, train_loss[loss=3.043, NarTop10Accuracy=0.7176, over 3984.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7141, over 5964.81 frames. ], batch size: 4, lr: 3.03e-03
2024-08-06 20:45:47,076 INFO [trainer.py:765] (2/8) Epoch 28, batch 2200, train_loss[loss=2.913, NarTop10Accuracy=0.7367, over 7263.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7122, over 6013.79 frames. ], batch size: 31, lr: 3.03e-03
2024-08-06 20:46:12,308 INFO [trainer.py:765] (2/8) Epoch 28, batch 2300, train_loss[loss=3.505, NarTop10Accuracy=0.6284, over 5649.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7085, over 6012.31 frames. ], batch size: 9, lr: 3.03e-03
2024-08-06 20:46:36,807 INFO [trainer.py:765] (2/8) Epoch 28, batch 2400, train_loss[loss=2.923, NarTop10Accuracy=0.7473, over 5259.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7083, over 5771.78 frames. ], batch size: 7, lr: 3.02e-03
2024-08-06 20:46:48,595 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 20:46:56,604 INFO [trainer.py:811] (2/8) Epoch 28, validation: loss=2.931, NarTop10Accuracy=0.7396, over 1905321.00 frames. 
2024-08-06 20:46:56,605 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 20:46:57,082 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.745e+02 2.201e+02 2.381e+02 2.551e+02 4.872e+02, threshold=4.762e+02, percent-clipped=0.1
2024-08-06 20:47:08,293 INFO [trainer.py:765] (2/8) Epoch 28, batch 2500, train_loss[loss=2.986, NarTop10Accuracy=0.7258, over 5226.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7119, over 5468.90 frames. ], batch size: 7, lr: 3.02e-03
2024-08-06 20:47:28,325 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 20:48:21,053 INFO [trainer.py:765] (2/8) Epoch 29, batch 100, train_loss[loss=2.971, NarTop10Accuracy=0.7296, over 7176.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7105, over 2358.94 frames. ], batch size: 32, lr: 2.96e-03
2024-08-06 20:48:53,406 INFO [trainer.py:765] (2/8) Epoch 29, batch 200, train_loss[loss=3.313, NarTop10Accuracy=0.6665, over 6771.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7176, over 3847.78 frames. ], batch size: 17, lr: 2.96e-03
2024-08-06 20:49:27,477 INFO [trainer.py:765] (2/8) Epoch 29, batch 300, train_loss[loss=3.268, NarTop10Accuracy=0.6773, over 7155.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7172, over 4641.86 frames. ], batch size: 22, lr: 2.96e-03
2024-08-06 20:49:56,053 INFO [trainer.py:765] (2/8) Epoch 29, batch 400, train_loss[loss=3.365, NarTop10Accuracy=0.6433, over 5088.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7126, over 5087.44 frames. ], batch size: 7, lr: 2.96e-03
2024-08-06 20:50:29,436 INFO [trainer.py:765] (2/8) Epoch 29, batch 500, train_loss[loss=3.207, NarTop10Accuracy=0.6757, over 6051.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.715, over 5380.87 frames. ], batch size: 11, lr: 2.96e-03
2024-08-06 20:51:00,025 INFO [trainer.py:765] (2/8) Epoch 29, batch 600, train_loss[loss=2.775, NarTop10Accuracy=0.7678, over 5691.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7157, over 5638.66 frames. ], batch size: 9, lr: 2.95e-03
2024-08-06 20:51:35,678 INFO [trainer.py:765] (2/8) Epoch 29, batch 700, train_loss[loss=2.96, NarTop10Accuracy=0.7393, over 5094.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7109, over 5703.00 frames. ], batch size: 6, lr: 2.95e-03
2024-08-06 20:52:10,725 INFO [trainer.py:765] (2/8) Epoch 29, batch 800, train_loss[loss=2.753, NarTop10Accuracy=0.7854, over 4983.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7105, over 5776.24 frames. ], batch size: 6, lr: 2.95e-03
2024-08-06 20:52:40,743 INFO [trainer.py:765] (2/8) Epoch 29, batch 900, train_loss[loss=2.759, NarTop10Accuracy=0.7714, over 6594.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7088, over 5809.15 frames. ], batch size: 14, lr: 2.95e-03
2024-08-06 20:53:16,862 INFO [trainer.py:765] (2/8) Epoch 29, batch 1000, train_loss[loss=3.405, NarTop10Accuracy=0.6413, over 6273.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7077, over 5904.56 frames. ], batch size: 13, lr: 2.95e-03
2024-08-06 20:53:52,903 INFO [trainer.py:765] (2/8) Epoch 29, batch 1100, train_loss[loss=3.18, NarTop10Accuracy=0.6912, over 6942.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.707, over 5928.07 frames. ], batch size: 17, lr: 2.94e-03
2024-08-06 20:54:23,691 INFO [trainer.py:765] (2/8) Epoch 29, batch 1200, train_loss[loss=3.096, NarTop10Accuracy=0.7107, over 7326.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7093, over 5928.02 frames. ], batch size: 31, lr: 2.94e-03
2024-08-06 20:55:01,428 INFO [trainer.py:765] (2/8) Epoch 29, batch 1300, train_loss[loss=2.912, NarTop10Accuracy=0.7464, over 5013.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7109, over 5980.62 frames. ], batch size: 6, lr: 2.94e-03
2024-08-06 20:55:32,557 INFO [trainer.py:765] (2/8) Epoch 29, batch 1400, train_loss[loss=3.303, NarTop10Accuracy=0.6642, over 6120.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7103, over 6004.76 frames. ], batch size: 11, lr: 2.94e-03
2024-08-06 20:56:04,360 INFO [trainer.py:765] (2/8) Epoch 29, batch 1500, train_loss[loss=3.374, NarTop10Accuracy=0.6494, over 5856.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7097, over 5926.46 frames. ], batch size: 50, lr: 2.94e-03
2024-08-06 20:56:32,041 INFO [trainer.py:765] (2/8) Epoch 29, batch 1600, train_loss[loss=3.196, NarTop10Accuracy=0.6824, over 7023.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7085, over 5913.37 frames. ], batch size: 22, lr: 2.93e-03
2024-08-06 20:56:58,640 INFO [trainer.py:765] (2/8) Epoch 29, batch 1700, train_loss[loss=2.749, NarTop10Accuracy=0.7807, over 6159.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7098, over 5906.91 frames. ], batch size: 13, lr: 2.93e-03
2024-08-06 20:57:25,001 INFO [trainer.py:765] (2/8) Epoch 29, batch 1800, train_loss[loss=3.035, NarTop10Accuracy=0.7222, over 6951.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7112, over 5976.33 frames. ], batch size: 22, lr: 2.93e-03
2024-08-06 20:57:44,622 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 20:57:52,863 INFO [trainer.py:811] (2/8) Epoch 29, validation: loss=2.897, NarTop10Accuracy=0.7458, over 1905321.00 frames. 
2024-08-06 20:57:52,864 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 20:57:53,424 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.772e+02 2.206e+02 2.380e+02 2.554e+02 4.464e+02, threshold=4.759e+02, percent-clipped=0.0
2024-08-06 20:57:59,756 INFO [trainer.py:765] (2/8) Epoch 29, batch 1900, train_loss[loss=2.978, NarTop10Accuracy=0.7415, over 6522.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7079, over 6036.25 frames. ], batch size: 50, lr: 2.93e-03
2024-08-06 20:58:25,308 INFO [trainer.py:765] (2/8) Epoch 29, batch 2000, train_loss[loss=3.393, NarTop10Accuracy=0.6486, over 6267.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7093, over 6005.82 frames. ], batch size: 50, lr: 2.93e-03
2024-08-06 20:58:50,629 INFO [trainer.py:765] (2/8) Epoch 29, batch 2100, train_loss[loss=3.103, NarTop10Accuracy=0.705, over 4929.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7092, over 5986.02 frames. ], batch size: 5, lr: 2.92e-03
2024-08-06 20:59:15,805 INFO [trainer.py:765] (2/8) Epoch 29, batch 2200, train_loss[loss=2.837, NarTop10Accuracy=0.7673, over 7164.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7104, over 6017.31 frames. ], batch size: 31, lr: 2.92e-03
2024-08-06 20:59:40,910 INFO [trainer.py:765] (2/8) Epoch 29, batch 2300, train_loss[loss=2.887, NarTop10Accuracy=0.7446, over 5613.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7075, over 6028.25 frames. ], batch size: 9, lr: 2.92e-03
2024-08-06 21:00:05,155 INFO [trainer.py:765] (2/8) Epoch 29, batch 2400, train_loss[loss=2.692, NarTop10Accuracy=0.7863, over 5193.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7109, over 5791.27 frames. ], batch size: 7, lr: 2.92e-03
2024-08-06 21:00:28,742 INFO [trainer.py:765] (2/8) Epoch 29, batch 2500, train_loss[loss=3.392, NarTop10Accuracy=0.6485, over 5658.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7148, over 5492.73 frames. ], batch size: 8, lr: 2.92e-03
2024-08-06 21:00:48,651 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 21:01:41,716 INFO [trainer.py:765] (2/8) Epoch 30, batch 100, train_loss[loss=2.823, NarTop10Accuracy=0.7625, over 7206.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7191, over 2366.56 frames. ], batch size: 31, lr: 2.86e-03
2024-08-06 21:02:17,013 INFO [trainer.py:765] (2/8) Epoch 30, batch 200, train_loss[loss=2.953, NarTop10Accuracy=0.7324, over 6795.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7213, over 3842.56 frames. ], batch size: 17, lr: 2.86e-03
2024-08-06 21:02:51,342 INFO [trainer.py:765] (2/8) Epoch 30, batch 300, train_loss[loss=2.893, NarTop10Accuracy=0.7491, over 7086.00 frames. ], tot_loss[loss=3.01, NarTop10Accuracy=0.723, over 4656.62 frames. ], batch size: 22, lr: 2.86e-03
2024-08-06 21:03:21,642 INFO [trainer.py:765] (2/8) Epoch 30, batch 400, train_loss[loss=2.758, NarTop10Accuracy=0.7775, over 5091.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7192, over 5106.64 frames. ], batch size: 7, lr: 2.86e-03
2024-08-06 21:03:58,545 INFO [trainer.py:765] (2/8) Epoch 30, batch 500, train_loss[loss=3.36, NarTop10Accuracy=0.6517, over 6015.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7168, over 5381.33 frames. ], batch size: 11, lr: 2.86e-03
2024-08-06 21:04:31,655 INFO [trainer.py:765] (2/8) Epoch 30, batch 600, train_loss[loss=2.962, NarTop10Accuracy=0.7399, over 5589.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7161, over 5644.54 frames. ], batch size: 9, lr: 2.85e-03
2024-08-06 21:05:03,525 INFO [trainer.py:765] (2/8) Epoch 30, batch 700, train_loss[loss=2.745, NarTop10Accuracy=0.7632, over 4965.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.719, over 5708.21 frames. ], batch size: 6, lr: 2.85e-03
2024-08-06 21:05:44,131 INFO [trainer.py:765] (2/8) Epoch 30, batch 800, train_loss[loss=2.89, NarTop10Accuracy=0.7459, over 5010.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.718, over 5754.53 frames. ], batch size: 6, lr: 2.85e-03
2024-08-06 21:06:14,843 INFO [trainer.py:765] (2/8) Epoch 30, batch 900, train_loss[loss=2.999, NarTop10Accuracy=0.7402, over 6237.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7184, over 5777.92 frames. ], batch size: 13, lr: 2.85e-03
2024-08-06 21:06:48,951 INFO [trainer.py:765] (2/8) Epoch 30, batch 1000, train_loss[loss=2.911, NarTop10Accuracy=0.749, over 6150.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7117, over 5893.33 frames. ], batch size: 13, lr: 2.85e-03
2024-08-06 21:07:25,936 INFO [trainer.py:765] (2/8) Epoch 30, batch 1100, train_loss[loss=3.354, NarTop10Accuracy=0.6515, over 6840.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7093, over 5946.16 frames. ], batch size: 17, lr: 2.84e-03
2024-08-06 21:08:02,380 INFO [trainer.py:765] (2/8) Epoch 30, batch 1200, train_loss[loss=3.029, NarTop10Accuracy=0.7159, over 7152.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7104, over 5954.78 frames. ], batch size: 31, lr: 2.84e-03
2024-08-06 21:08:35,370 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 21:08:43,457 INFO [trainer.py:811] (2/8) Epoch 30, validation: loss=2.93, NarTop10Accuracy=0.7391, over 1905321.00 frames. 
2024-08-06 21:08:43,457 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 21:08:44,197 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.770e+02 2.209e+02 2.377e+02 2.553e+02 3.956e+02, threshold=4.754e+02, percent-clipped=0.0
2024-08-06 21:08:44,203 INFO [trainer.py:765] (2/8) Epoch 30, batch 1300, train_loss[loss=3.09, NarTop10Accuracy=0.7136, over 4329.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7112, over 5995.94 frames. ], batch size: 5, lr: 2.84e-03
2024-08-06 21:09:22,396 INFO [trainer.py:765] (2/8) Epoch 30, batch 1400, train_loss[loss=2.838, NarTop10Accuracy=0.7616, over 6201.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7117, over 6030.04 frames. ], batch size: 11, lr: 2.84e-03
2024-08-06 21:09:52,372 INFO [trainer.py:765] (2/8) Epoch 30, batch 1500, train_loss[loss=3.068, NarTop10Accuracy=0.7125, over 5835.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.713, over 5960.96 frames. ], batch size: 50, lr: 2.84e-03
2024-08-06 21:10:20,083 INFO [trainer.py:765] (2/8) Epoch 30, batch 1600, train_loss[loss=3.041, NarTop10Accuracy=0.7155, over 6990.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7123, over 5943.75 frames. ], batch size: 22, lr: 2.84e-03
2024-08-06 21:10:46,679 INFO [trainer.py:765] (2/8) Epoch 30, batch 1700, train_loss[loss=3.078, NarTop10Accuracy=0.7079, over 6642.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7103, over 5930.16 frames. ], batch size: 14, lr: 2.83e-03
2024-08-06 21:11:13,058 INFO [trainer.py:765] (2/8) Epoch 30, batch 1800, train_loss[loss=3.422, NarTop10Accuracy=0.6407, over 7113.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7113, over 5991.63 frames. ], batch size: 22, lr: 2.83e-03
2024-08-06 21:11:39,418 INFO [trainer.py:765] (2/8) Epoch 30, batch 1900, train_loss[loss=3.133, NarTop10Accuracy=0.7001, over 6045.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7105, over 6020.86 frames. ], batch size: 50, lr: 2.83e-03
2024-08-06 21:12:04,825 INFO [trainer.py:765] (2/8) Epoch 30, batch 2000, train_loss[loss=3.379, NarTop10Accuracy=0.647, over 6069.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7129, over 6012.48 frames. ], batch size: 50, lr: 2.83e-03
2024-08-06 21:12:30,088 INFO [trainer.py:765] (2/8) Epoch 30, batch 2100, train_loss[loss=2.919, NarTop10Accuracy=0.7436, over 3954.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7122, over 5980.76 frames. ], batch size: 4, lr: 2.83e-03
2024-08-06 21:12:55,225 INFO [trainer.py:765] (2/8) Epoch 30, batch 2200, train_loss[loss=2.929, NarTop10Accuracy=0.7369, over 7344.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7133, over 6008.63 frames. ], batch size: 32, lr: 2.82e-03
2024-08-06 21:13:20,297 INFO [trainer.py:765] (2/8) Epoch 30, batch 2300, train_loss[loss=2.779, NarTop10Accuracy=0.778, over 5700.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7092, over 6034.53 frames. ], batch size: 9, lr: 2.82e-03
2024-08-06 21:13:44,490 INFO [trainer.py:765] (2/8) Epoch 30, batch 2400, train_loss[loss=2.678, NarTop10Accuracy=0.7947, over 5097.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7163, over 5784.14 frames. ], batch size: 7, lr: 2.82e-03
2024-08-06 21:14:07,987 INFO [trainer.py:765] (2/8) Epoch 30, batch 2500, train_loss[loss=3.065, NarTop10Accuracy=0.7056, over 4968.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7168, over 5471.98 frames. ], batch size: 7, lr: 2.82e-03
2024-08-06 21:14:27,723 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 21:15:23,633 INFO [trainer.py:765] (2/8) Epoch 31, batch 100, train_loss[loss=3.519, NarTop10Accuracy=0.6285, over 7344.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7135, over 2363.73 frames. ], batch size: 31, lr: 2.77e-03
2024-08-06 21:15:55,128 INFO [trainer.py:765] (2/8) Epoch 31, batch 200, train_loss[loss=2.93, NarTop10Accuracy=0.7446, over 6690.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7203, over 3856.35 frames. ], batch size: 17, lr: 2.77e-03
2024-08-06 21:16:31,217 INFO [trainer.py:765] (2/8) Epoch 31, batch 300, train_loss[loss=2.852, NarTop10Accuracy=0.754, over 7215.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7183, over 4650.54 frames. ], batch size: 22, lr: 2.77e-03
2024-08-06 21:17:01,625 INFO [trainer.py:765] (2/8) Epoch 31, batch 400, train_loss[loss=3.204, NarTop10Accuracy=0.6894, over 5088.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7163, over 5099.53 frames. ], batch size: 7, lr: 2.76e-03
2024-08-06 21:17:35,725 INFO [trainer.py:765] (2/8) Epoch 31, batch 500, train_loss[loss=2.769, NarTop10Accuracy=0.778, over 6123.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.717, over 5395.33 frames. ], batch size: 11, lr: 2.76e-03
2024-08-06 21:18:07,085 INFO [trainer.py:765] (2/8) Epoch 31, batch 600, train_loss[loss=2.806, NarTop10Accuracy=0.7698, over 5793.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7136, over 5661.86 frames. ], batch size: 9, lr: 2.76e-03
2024-08-06 21:18:44,611 INFO [trainer.py:765] (2/8) Epoch 31, batch 700, train_loss[loss=3.398, NarTop10Accuracy=0.6413, over 5172.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7133, over 5734.66 frames. ], batch size: 6, lr: 2.76e-03
2024-08-06 21:18:51,096 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 21:18:59,276 INFO [trainer.py:811] (2/8) Epoch 31, validation: loss=2.984, NarTop10Accuracy=0.7279, over 1905321.00 frames. 
2024-08-06 21:18:59,277 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 21:18:59,986 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.824e+02 2.222e+02 2.378e+02 2.557e+02 4.306e+02, threshold=4.755e+02, percent-clipped=0.0
2024-08-06 21:19:24,246 INFO [trainer.py:765] (2/8) Epoch 31, batch 800, train_loss[loss=2.761, NarTop10Accuracy=0.7781, over 5037.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7157, over 5797.59 frames. ], batch size: 6, lr: 2.76e-03
2024-08-06 21:19:56,951 INFO [trainer.py:765] (2/8) Epoch 31, batch 900, train_loss[loss=3.455, NarTop10Accuracy=0.6266, over 6537.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7163, over 5810.34 frames. ], batch size: 14, lr: 2.76e-03
2024-08-06 21:20:33,311 INFO [trainer.py:765] (2/8) Epoch 31, batch 1000, train_loss[loss=3.348, NarTop10Accuracy=0.6547, over 6312.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.717, over 5924.94 frames. ], batch size: 13, lr: 2.75e-03
2024-08-06 21:21:10,216 INFO [trainer.py:765] (2/8) Epoch 31, batch 1100, train_loss[loss=3.112, NarTop10Accuracy=0.6981, over 6741.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.717, over 5941.77 frames. ], batch size: 17, lr: 2.75e-03
2024-08-06 21:21:41,120 INFO [trainer.py:765] (2/8) Epoch 31, batch 1200, train_loss[loss=2.959, NarTop10Accuracy=0.7196, over 7428.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7201, over 5934.39 frames. ], batch size: 32, lr: 2.75e-03
2024-08-06 21:22:19,742 INFO [trainer.py:765] (2/8) Epoch 31, batch 1300, train_loss[loss=2.969, NarTop10Accuracy=0.7384, over 5241.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7137, over 5997.16 frames. ], batch size: 6, lr: 2.75e-03
2024-08-06 21:22:53,535 INFO [trainer.py:765] (2/8) Epoch 31, batch 1400, train_loss[loss=2.809, NarTop10Accuracy=0.7643, over 6117.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.712, over 6025.56 frames. ], batch size: 11, lr: 2.75e-03
2024-08-06 21:23:21,271 INFO [trainer.py:765] (2/8) Epoch 31, batch 1500, train_loss[loss=3.331, NarTop10Accuracy=0.6654, over 6342.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7156, over 5947.03 frames. ], batch size: 50, lr: 2.74e-03
2024-08-06 21:23:49,005 INFO [trainer.py:765] (2/8) Epoch 31, batch 1600, train_loss[loss=3.32, NarTop10Accuracy=0.6674, over 7296.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7146, over 5937.60 frames. ], batch size: 22, lr: 2.74e-03
2024-08-06 21:24:15,513 INFO [trainer.py:765] (2/8) Epoch 31, batch 1700, train_loss[loss=3.192, NarTop10Accuracy=0.689, over 6264.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7135, over 5917.32 frames. ], batch size: 13, lr: 2.74e-03
2024-08-06 21:24:41,997 INFO [trainer.py:765] (2/8) Epoch 31, batch 1800, train_loss[loss=2.811, NarTop10Accuracy=0.7692, over 7158.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7163, over 5974.79 frames. ], batch size: 23, lr: 2.74e-03
2024-08-06 21:25:08,358 INFO [trainer.py:765] (2/8) Epoch 31, batch 1900, train_loss[loss=3.271, NarTop10Accuracy=0.6753, over 6387.00 frames. ], tot_loss[loss=3.062, NarTop10Accuracy=0.713, over 6020.51 frames. ], batch size: 50, lr: 2.74e-03
2024-08-06 21:25:33,774 INFO [trainer.py:765] (2/8) Epoch 31, batch 2000, train_loss[loss=3.002, NarTop10Accuracy=0.7324, over 6054.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7151, over 5978.35 frames. ], batch size: 50, lr: 2.74e-03
2024-08-06 21:25:59,107 INFO [trainer.py:765] (2/8) Epoch 31, batch 2100, train_loss[loss=2.888, NarTop10Accuracy=0.7514, over 4782.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7156, over 5954.10 frames. ], batch size: 5, lr: 2.73e-03
2024-08-06 21:26:24,238 INFO [trainer.py:765] (2/8) Epoch 31, batch 2200, train_loss[loss=3.02, NarTop10Accuracy=0.7237, over 7116.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7179, over 5997.55 frames. ], batch size: 31, lr: 2.73e-03
2024-08-06 21:26:49,322 INFO [trainer.py:765] (2/8) Epoch 31, batch 2300, train_loss[loss=2.791, NarTop10Accuracy=0.7701, over 5679.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.715, over 6008.69 frames. ], batch size: 9, lr: 2.73e-03
2024-08-06 21:27:13,608 INFO [trainer.py:765] (2/8) Epoch 31, batch 2400, train_loss[loss=2.824, NarTop10Accuracy=0.7609, over 5118.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7154, over 5766.80 frames. ], batch size: 7, lr: 2.73e-03
2024-08-06 21:27:37,028 INFO [trainer.py:765] (2/8) Epoch 31, batch 2500, train_loss[loss=2.913, NarTop10Accuracy=0.7411, over 5268.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7183, over 5478.74 frames. ], batch size: 7, lr: 2.73e-03
2024-08-06 21:27:56,943 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 21:28:49,393 INFO [trainer.py:765] (2/8) Epoch 32, batch 100, train_loss[loss=2.84, NarTop10Accuracy=0.7609, over 7257.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7137, over 2364.63 frames. ], batch size: 31, lr: 2.68e-03
2024-08-06 21:29:08,161 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 21:29:16,392 INFO [trainer.py:811] (2/8) Epoch 32, validation: loss=2.919, NarTop10Accuracy=0.7409, over 1905321.00 frames. 
2024-08-06 21:29:16,393 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 21:29:16,940 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.842e+02 2.253e+02 2.413e+02 2.600e+02 5.680e+02, threshold=4.826e+02, percent-clipped=0.1
2024-08-06 21:29:32,273 INFO [trainer.py:765] (2/8) Epoch 32, batch 200, train_loss[loss=3.316, NarTop10Accuracy=0.6661, over 6816.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7128, over 3854.05 frames. ], batch size: 17, lr: 2.68e-03
2024-08-06 21:30:05,279 INFO [trainer.py:765] (2/8) Epoch 32, batch 300, train_loss[loss=3.119, NarTop10Accuracy=0.7026, over 6903.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7152, over 4646.00 frames. ], batch size: 22, lr: 2.68e-03
2024-08-06 21:30:34,104 INFO [trainer.py:765] (2/8) Epoch 32, batch 400, train_loss[loss=2.849, NarTop10Accuracy=0.7593, over 5073.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7123, over 5113.84 frames. ], batch size: 7, lr: 2.68e-03
2024-08-06 21:31:13,531 INFO [trainer.py:765] (2/8) Epoch 32, batch 500, train_loss[loss=3.061, NarTop10Accuracy=0.7147, over 6183.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7139, over 5402.18 frames. ], batch size: 11, lr: 2.67e-03
2024-08-06 21:31:42,487 INFO [trainer.py:765] (2/8) Epoch 32, batch 600, train_loss[loss=3.235, NarTop10Accuracy=0.679, over 5640.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7148, over 5669.69 frames. ], batch size: 9, lr: 2.67e-03
2024-08-06 21:32:17,029 INFO [trainer.py:765] (2/8) Epoch 32, batch 700, train_loss[loss=2.679, NarTop10Accuracy=0.7871, over 5085.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7164, over 5735.72 frames. ], batch size: 6, lr: 2.67e-03
2024-08-06 21:33:00,647 INFO [trainer.py:765] (2/8) Epoch 32, batch 800, train_loss[loss=3.141, NarTop10Accuracy=0.6967, over 4326.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7165, over 5784.57 frames. ], batch size: 5, lr: 2.67e-03
2024-08-06 21:33:28,992 INFO [trainer.py:765] (2/8) Epoch 32, batch 900, train_loss[loss=2.826, NarTop10Accuracy=0.7581, over 6828.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7193, over 5808.31 frames. ], batch size: 14, lr: 2.67e-03
2024-08-06 21:34:04,050 INFO [trainer.py:765] (2/8) Epoch 32, batch 1000, train_loss[loss=3.206, NarTop10Accuracy=0.6873, over 6816.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7173, over 5913.35 frames. ], batch size: 14, lr: 2.67e-03
2024-08-06 21:34:46,674 INFO [trainer.py:765] (2/8) Epoch 32, batch 1100, train_loss[loss=3.14, NarTop10Accuracy=0.6926, over 6840.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7165, over 5926.10 frames. ], batch size: 17, lr: 2.66e-03
2024-08-06 21:35:18,171 INFO [trainer.py:765] (2/8) Epoch 32, batch 1200, train_loss[loss=3.223, NarTop10Accuracy=0.6718, over 7071.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7148, over 5917.94 frames. ], batch size: 31, lr: 2.66e-03
2024-08-06 21:35:52,801 INFO [trainer.py:765] (2/8) Epoch 32, batch 1300, train_loss[loss=3.102, NarTop10Accuracy=0.7032, over 5154.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7141, over 5991.44 frames. ], batch size: 6, lr: 2.66e-03
2024-08-06 21:36:29,479 INFO [trainer.py:765] (2/8) Epoch 32, batch 1400, train_loss[loss=3.256, NarTop10Accuracy=0.6814, over 6144.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7138, over 6009.85 frames. ], batch size: 11, lr: 2.66e-03
2024-08-06 21:37:04,734 INFO [trainer.py:765] (2/8) Epoch 32, batch 1500, train_loss[loss=3.422, NarTop10Accuracy=0.6399, over 5925.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7137, over 5934.07 frames. ], batch size: 51, lr: 2.66e-03
2024-08-06 21:37:32,522 INFO [trainer.py:765] (2/8) Epoch 32, batch 1600, train_loss[loss=3.155, NarTop10Accuracy=0.6986, over 7083.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7143, over 5929.83 frames. ], batch size: 22, lr: 2.66e-03
2024-08-06 21:37:59,160 INFO [trainer.py:765] (2/8) Epoch 32, batch 1700, train_loss[loss=3.024, NarTop10Accuracy=0.718, over 6303.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7149, over 5910.62 frames. ], batch size: 13, lr: 2.65e-03
2024-08-06 21:38:25,703 INFO [trainer.py:765] (2/8) Epoch 32, batch 1800, train_loss[loss=3.025, NarTop10Accuracy=0.7188, over 6987.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7147, over 5979.91 frames. ], batch size: 22, lr: 2.65e-03
2024-08-06 21:38:52,169 INFO [trainer.py:765] (2/8) Epoch 32, batch 1900, train_loss[loss=3.164, NarTop10Accuracy=0.6985, over 6420.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7105, over 6039.26 frames. ], batch size: 50, lr: 2.65e-03
2024-08-06 21:39:17,769 INFO [trainer.py:765] (2/8) Epoch 32, batch 2000, train_loss[loss=3.483, NarTop10Accuracy=0.6266, over 6072.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7134, over 6015.13 frames. ], batch size: 50, lr: 2.65e-03
2024-08-06 21:39:43,179 INFO [trainer.py:765] (2/8) Epoch 32, batch 2100, train_loss[loss=2.987, NarTop10Accuracy=0.7333, over 3855.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7147, over 5980.65 frames. ], batch size: 4, lr: 2.65e-03
2024-08-06 21:39:54,782 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 21:40:02,941 INFO [trainer.py:811] (2/8) Epoch 32, validation: loss=2.886, NarTop10Accuracy=0.7482, over 1905321.00 frames. 
2024-08-06 21:40:02,942 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 21:40:03,423 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.874e+02 2.278e+02 2.449e+02 2.609e+02 8.207e+02, threshold=4.898e+02, percent-clipped=0.3
2024-08-06 21:40:16,628 INFO [trainer.py:765] (2/8) Epoch 32, batch 2200, train_loss[loss=3.155, NarTop10Accuracy=0.7006, over 7344.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7142, over 6023.69 frames. ], batch size: 31, lr: 2.65e-03
2024-08-06 21:40:41,717 INFO [trainer.py:765] (2/8) Epoch 32, batch 2300, train_loss[loss=3.359, NarTop10Accuracy=0.6498, over 5646.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7102, over 6018.75 frames. ], batch size: 9, lr: 2.65e-03
2024-08-06 21:41:06,073 INFO [trainer.py:765] (2/8) Epoch 32, batch 2400, train_loss[loss=3.227, NarTop10Accuracy=0.6676, over 5055.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7151, over 5762.10 frames. ], batch size: 7, lr: 2.64e-03
2024-08-06 21:41:29,538 INFO [trainer.py:765] (2/8) Epoch 32, batch 2500, train_loss[loss=2.687, NarTop10Accuracy=0.7868, over 5124.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7224, over 5457.29 frames. ], batch size: 7, lr: 2.64e-03
2024-08-06 21:41:49,590 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 21:42:47,616 INFO [trainer.py:765] (2/8) Epoch 33, batch 100, train_loss[loss=3.083, NarTop10Accuracy=0.7096, over 7599.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7236, over 2360.28 frames. ], batch size: 32, lr: 2.60e-03
2024-08-06 21:43:22,368 INFO [trainer.py:765] (2/8) Epoch 33, batch 200, train_loss[loss=2.689, NarTop10Accuracy=0.7838, over 6732.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.72, over 3858.56 frames. ], batch size: 17, lr: 2.60e-03
2024-08-06 21:43:56,513 INFO [trainer.py:765] (2/8) Epoch 33, batch 300, train_loss[loss=3.422, NarTop10Accuracy=0.6297, over 7080.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7163, over 4662.91 frames. ], batch size: 22, lr: 2.60e-03
2024-08-06 21:44:30,316 INFO [trainer.py:765] (2/8) Epoch 33, batch 400, train_loss[loss=2.744, NarTop10Accuracy=0.7798, over 5172.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.717, over 5100.40 frames. ], batch size: 7, lr: 2.59e-03
2024-08-06 21:45:02,870 INFO [trainer.py:765] (2/8) Epoch 33, batch 500, train_loss[loss=2.777, NarTop10Accuracy=0.7666, over 6114.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7212, over 5377.51 frames. ], batch size: 11, lr: 2.59e-03
2024-08-06 21:45:36,226 INFO [trainer.py:765] (2/8) Epoch 33, batch 600, train_loss[loss=3.424, NarTop10Accuracy=0.6402, over 5724.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7159, over 5663.84 frames. ], batch size: 9, lr: 2.59e-03
2024-08-06 21:46:11,317 INFO [trainer.py:765] (2/8) Epoch 33, batch 700, train_loss[loss=2.709, NarTop10Accuracy=0.7894, over 5205.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7162, over 5723.23 frames. ], batch size: 6, lr: 2.59e-03
2024-08-06 21:46:46,169 INFO [trainer.py:765] (2/8) Epoch 33, batch 800, train_loss[loss=2.79, NarTop10Accuracy=0.759, over 5010.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7163, over 5776.53 frames. ], batch size: 6, lr: 2.59e-03
2024-08-06 21:47:18,908 INFO [trainer.py:765] (2/8) Epoch 33, batch 900, train_loss[loss=3.21, NarTop10Accuracy=0.6876, over 6756.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7156, over 5789.21 frames. ], batch size: 14, lr: 2.59e-03
2024-08-06 21:47:57,316 INFO [trainer.py:765] (2/8) Epoch 33, batch 1000, train_loss[loss=2.931, NarTop10Accuracy=0.7307, over 6240.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7142, over 5890.66 frames. ], batch size: 13, lr: 2.58e-03
2024-08-06 21:48:30,908 INFO [trainer.py:765] (2/8) Epoch 33, batch 1100, train_loss[loss=2.907, NarTop10Accuracy=0.7483, over 6897.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7108, over 5926.85 frames. ], batch size: 17, lr: 2.58e-03
2024-08-06 21:49:06,660 INFO [trainer.py:765] (2/8) Epoch 33, batch 1200, train_loss[loss=2.801, NarTop10Accuracy=0.7629, over 7026.00 frames. ], tot_loss[loss=3.062, NarTop10Accuracy=0.7129, over 5922.82 frames. ], batch size: 31, lr: 2.58e-03
2024-08-06 21:49:42,816 INFO [trainer.py:765] (2/8) Epoch 33, batch 1300, train_loss[loss=2.988, NarTop10Accuracy=0.7322, over 4995.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7134, over 5989.17 frames. ], batch size: 6, lr: 2.58e-03
2024-08-06 21:50:17,310 INFO [trainer.py:765] (2/8) Epoch 33, batch 1400, train_loss[loss=3.211, NarTop10Accuracy=0.682, over 6396.00 frames. ], tot_loss[loss=3.062, NarTop10Accuracy=0.7129, over 6017.87 frames. ], batch size: 12, lr: 2.58e-03
2024-08-06 21:50:45,370 INFO [trainer.py:765] (2/8) Epoch 33, batch 1500, train_loss[loss=3.048, NarTop10Accuracy=0.7148, over 6552.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7143, over 5956.77 frames. ], batch size: 50, lr: 2.58e-03
2024-08-06 21:51:04,607 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 21:51:12,661 INFO [trainer.py:811] (2/8) Epoch 33, validation: loss=2.938, NarTop10Accuracy=0.7372, over 1905321.00 frames. 
2024-08-06 21:51:12,662 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 21:51:13,180 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.834e+02 2.250e+02 2.409e+02 2.586e+02 3.975e+02, threshold=4.818e+02, percent-clipped=0.0
2024-08-06 21:51:21,261 INFO [trainer.py:765] (2/8) Epoch 33, batch 1600, train_loss[loss=3.166, NarTop10Accuracy=0.6969, over 6987.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7169, over 5941.64 frames. ], batch size: 22, lr: 2.57e-03
2024-08-06 21:51:47,923 INFO [trainer.py:765] (2/8) Epoch 33, batch 1700, train_loss[loss=2.771, NarTop10Accuracy=0.7623, over 6156.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7143, over 5937.39 frames. ], batch size: 13, lr: 2.57e-03
2024-08-06 21:52:14,392 INFO [trainer.py:765] (2/8) Epoch 33, batch 1800, train_loss[loss=2.857, NarTop10Accuracy=0.7602, over 7086.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7152, over 5990.51 frames. ], batch size: 22, lr: 2.57e-03
2024-08-06 21:52:40,855 INFO [trainer.py:765] (2/8) Epoch 33, batch 1900, train_loss[loss=3.534, NarTop10Accuracy=0.6189, over 6396.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7117, over 6043.32 frames. ], batch size: 50, lr: 2.57e-03
2024-08-06 21:53:06,352 INFO [trainer.py:765] (2/8) Epoch 33, batch 2000, train_loss[loss=3.444, NarTop10Accuracy=0.6336, over 6423.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7173, over 5996.07 frames. ], batch size: 50, lr: 2.57e-03
2024-08-06 21:53:31,658 INFO [trainer.py:765] (2/8) Epoch 33, batch 2100, train_loss[loss=3.493, NarTop10Accuracy=0.6223, over 4707.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7158, over 5993.98 frames. ], batch size: 5, lr: 2.57e-03
2024-08-06 21:53:56,890 INFO [trainer.py:765] (2/8) Epoch 33, batch 2200, train_loss[loss=3.329, NarTop10Accuracy=0.6475, over 7272.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7146, over 6020.29 frames. ], batch size: 31, lr: 2.57e-03
2024-08-06 21:54:21,990 INFO [trainer.py:765] (2/8) Epoch 33, batch 2300, train_loss[loss=2.896, NarTop10Accuracy=0.7481, over 5733.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7157, over 6033.06 frames. ], batch size: 9, lr: 2.56e-03
2024-08-06 21:54:46,429 INFO [trainer.py:765] (2/8) Epoch 33, batch 2400, train_loss[loss=2.836, NarTop10Accuracy=0.7597, over 5112.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7185, over 5781.68 frames. ], batch size: 7, lr: 2.56e-03
2024-08-06 21:55:09,862 INFO [trainer.py:765] (2/8) Epoch 33, batch 2500, train_loss[loss=2.688, NarTop10Accuracy=0.7867, over 4998.00 frames. ], tot_loss[loss=3.008, NarTop10Accuracy=0.7235, over 5475.20 frames. ], batch size: 7, lr: 2.56e-03
2024-08-06 21:55:29,915 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 21:56:24,721 INFO [trainer.py:765] (2/8) Epoch 34, batch 100, train_loss[loss=3.382, NarTop10Accuracy=0.6476, over 7245.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7172, over 2368.84 frames. ], batch size: 31, lr: 2.52e-03
2024-08-06 21:56:55,613 INFO [trainer.py:765] (2/8) Epoch 34, batch 200, train_loss[loss=3.249, NarTop10Accuracy=0.6778, over 6951.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7222, over 3863.61 frames. ], batch size: 17, lr: 2.52e-03
2024-08-06 21:57:31,776 INFO [trainer.py:765] (2/8) Epoch 34, batch 300, train_loss[loss=2.757, NarTop10Accuracy=0.7689, over 7104.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7188, over 4670.17 frames. ], batch size: 22, lr: 2.52e-03
2024-08-06 21:58:02,724 INFO [trainer.py:765] (2/8) Epoch 34, batch 400, train_loss[loss=3.325, NarTop10Accuracy=0.6587, over 5073.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7224, over 5118.95 frames. ], batch size: 7, lr: 2.52e-03
2024-08-06 21:58:34,690 INFO [trainer.py:765] (2/8) Epoch 34, batch 500, train_loss[loss=3.195, NarTop10Accuracy=0.686, over 5976.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7195, over 5401.09 frames. ], batch size: 11, lr: 2.51e-03
2024-08-06 21:59:09,616 INFO [trainer.py:765] (2/8) Epoch 34, batch 600, train_loss[loss=2.803, NarTop10Accuracy=0.7612, over 5721.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7189, over 5660.21 frames. ], batch size: 9, lr: 2.51e-03
2024-08-06 21:59:46,056 INFO [trainer.py:765] (2/8) Epoch 34, batch 700, train_loss[loss=3.131, NarTop10Accuracy=0.7014, over 5094.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7184, over 5732.83 frames. ], batch size: 6, lr: 2.51e-03
2024-08-06 22:00:17,575 INFO [trainer.py:765] (2/8) Epoch 34, batch 800, train_loss[loss=2.815, NarTop10Accuracy=0.761, over 5070.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.721, over 5792.26 frames. ], batch size: 6, lr: 2.51e-03
2024-08-06 22:00:49,874 INFO [trainer.py:765] (2/8) Epoch 34, batch 900, train_loss[loss=2.868, NarTop10Accuracy=0.7651, over 6651.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7202, over 5822.76 frames. ], batch size: 14, lr: 2.51e-03
2024-08-06 22:01:25,342 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 22:01:33,386 INFO [trainer.py:811] (2/8) Epoch 34, validation: loss=2.9, NarTop10Accuracy=0.7444, over 1905321.00 frames. 
2024-08-06 22:01:33,387 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 22:01:34,092 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.819e+02 2.259e+02 2.434e+02 2.615e+02 5.125e+02, threshold=4.868e+02, percent-clipped=0.1
2024-08-06 22:01:35,625 INFO [trainer.py:765] (2/8) Epoch 34, batch 1000, train_loss[loss=3.226, NarTop10Accuracy=0.6779, over 6651.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7176, over 5914.66 frames. ], batch size: 14, lr: 2.51e-03
2024-08-06 22:02:10,829 INFO [trainer.py:765] (2/8) Epoch 34, batch 1100, train_loss[loss=3.177, NarTop10Accuracy=0.6906, over 6822.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7173, over 5939.80 frames. ], batch size: 17, lr: 2.51e-03
2024-08-06 22:02:46,786 INFO [trainer.py:765] (2/8) Epoch 34, batch 1200, train_loss[loss=2.89, NarTop10Accuracy=0.7534, over 7302.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7168, over 5928.57 frames. ], batch size: 31, lr: 2.50e-03
2024-08-06 22:03:20,814 INFO [trainer.py:765] (2/8) Epoch 34, batch 1300, train_loss[loss=2.795, NarTop10Accuracy=0.7805, over 5085.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7164, over 6001.04 frames. ], batch size: 6, lr: 2.50e-03
2024-08-06 22:03:52,950 INFO [trainer.py:765] (2/8) Epoch 34, batch 1400, train_loss[loss=3.151, NarTop10Accuracy=0.6864, over 5967.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7167, over 6007.26 frames. ], batch size: 11, lr: 2.50e-03
2024-08-06 22:04:20,823 INFO [trainer.py:765] (2/8) Epoch 34, batch 1500, train_loss[loss=3.081, NarTop10Accuracy=0.7109, over 5268.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7176, over 5938.22 frames. ], batch size: 51, lr: 2.50e-03
2024-08-06 22:04:48,600 INFO [trainer.py:765] (2/8) Epoch 34, batch 1600, train_loss[loss=3.004, NarTop10Accuracy=0.7204, over 6873.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7164, over 5947.06 frames. ], batch size: 22, lr: 2.50e-03
2024-08-06 22:05:15,241 INFO [trainer.py:765] (2/8) Epoch 34, batch 1700, train_loss[loss=3.027, NarTop10Accuracy=0.714, over 6615.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7185, over 5927.82 frames. ], batch size: 14, lr: 2.50e-03
2024-08-06 22:05:41,721 INFO [trainer.py:765] (2/8) Epoch 34, batch 1800, train_loss[loss=3.376, NarTop10Accuracy=0.6391, over 6999.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7162, over 5995.50 frames. ], batch size: 22, lr: 2.50e-03
2024-08-06 22:06:08,207 INFO [trainer.py:765] (2/8) Epoch 34, batch 1900, train_loss[loss=3.09, NarTop10Accuracy=0.7074, over 6078.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7118, over 6033.33 frames. ], batch size: 50, lr: 2.49e-03
2024-08-06 22:06:33,770 INFO [trainer.py:765] (2/8) Epoch 34, batch 2000, train_loss[loss=3.127, NarTop10Accuracy=0.6987, over 6258.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7151, over 5993.78 frames. ], batch size: 50, lr: 2.49e-03
2024-08-06 22:06:59,126 INFO [trainer.py:765] (2/8) Epoch 34, batch 2100, train_loss[loss=3.406, NarTop10Accuracy=0.6368, over 4944.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7121, over 5980.02 frames. ], batch size: 5, lr: 2.49e-03
2024-08-06 22:07:24,398 INFO [trainer.py:765] (2/8) Epoch 34, batch 2200, train_loss[loss=2.894, NarTop10Accuracy=0.7523, over 7422.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7123, over 6015.38 frames. ], batch size: 31, lr: 2.49e-03
2024-08-06 22:07:49,535 INFO [trainer.py:765] (2/8) Epoch 34, batch 2300, train_loss[loss=2.844, NarTop10Accuracy=0.7634, over 5634.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7105, over 6032.38 frames. ], batch size: 9, lr: 2.49e-03
2024-08-06 22:08:14,059 INFO [trainer.py:765] (2/8) Epoch 34, batch 2400, train_loss[loss=3.262, NarTop10Accuracy=0.6716, over 5040.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7122, over 5769.39 frames. ], batch size: 7, lr: 2.49e-03
2024-08-06 22:08:37,648 INFO [trainer.py:765] (2/8) Epoch 34, batch 2500, train_loss[loss=2.731, NarTop10Accuracy=0.7907, over 5220.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7184, over 5478.16 frames. ], batch size: 7, lr: 2.49e-03
2024-08-06 22:08:57,693 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 22:09:52,641 INFO [trainer.py:765] (2/8) Epoch 35, batch 100, train_loss[loss=2.824, NarTop10Accuracy=0.7589, over 7200.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7161, over 2373.37 frames. ], batch size: 31, lr: 2.45e-03
2024-08-06 22:10:29,698 INFO [trainer.py:765] (2/8) Epoch 35, batch 200, train_loss[loss=3.16, NarTop10Accuracy=0.6874, over 6813.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7132, over 3877.94 frames. ], batch size: 17, lr: 2.45e-03
2024-08-06 22:11:04,942 INFO [trainer.py:765] (2/8) Epoch 35, batch 300, train_loss[loss=2.88, NarTop10Accuracy=0.7658, over 7071.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7187, over 4687.87 frames. ], batch size: 22, lr: 2.44e-03
2024-08-06 22:11:35,333 INFO [trainer.py:765] (2/8) Epoch 35, batch 400, train_loss[loss=2.961, NarTop10Accuracy=0.7394, over 5220.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7194, over 5126.40 frames. ], batch size: 7, lr: 2.44e-03
2024-08-06 22:11:40,048 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 22:11:48,129 INFO [trainer.py:811] (2/8) Epoch 35, validation: loss=2.84, NarTop10Accuracy=0.7576, over 1905321.00 frames. 
2024-08-06 22:11:48,130 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 22:11:48,702 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.898e+02 2.275e+02 2.426e+02 2.615e+02 4.095e+02, threshold=4.852e+02, percent-clipped=0.0
2024-08-06 22:12:17,723 INFO [trainer.py:765] (2/8) Epoch 35, batch 500, train_loss[loss=2.766, NarTop10Accuracy=0.7695, over 6036.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7208, over 5392.21 frames. ], batch size: 11, lr: 2.44e-03
2024-08-06 22:12:51,424 INFO [trainer.py:765] (2/8) Epoch 35, batch 600, train_loss[loss=3.32, NarTop10Accuracy=0.6623, over 5691.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7175, over 5649.78 frames. ], batch size: 9, lr: 2.44e-03
2024-08-06 22:13:24,940 INFO [trainer.py:765] (2/8) Epoch 35, batch 700, train_loss[loss=2.647, NarTop10Accuracy=0.7904, over 5181.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7177, over 5732.09 frames. ], batch size: 6, lr: 2.44e-03
2024-08-06 22:14:01,383 INFO [trainer.py:765] (2/8) Epoch 35, batch 800, train_loss[loss=2.708, NarTop10Accuracy=0.7824, over 4329.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7167, over 5803.49 frames. ], batch size: 5, lr: 2.44e-03
2024-08-06 22:14:34,372 INFO [trainer.py:765] (2/8) Epoch 35, batch 900, train_loss[loss=3.25, NarTop10Accuracy=0.6768, over 6159.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7197, over 5815.07 frames. ], batch size: 13, lr: 2.44e-03
2024-08-06 22:15:09,372 INFO [trainer.py:765] (2/8) Epoch 35, batch 1000, train_loss[loss=2.814, NarTop10Accuracy=0.7696, over 6246.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7177, over 5910.13 frames. ], batch size: 13, lr: 2.43e-03
2024-08-06 22:15:48,495 INFO [trainer.py:765] (2/8) Epoch 35, batch 1100, train_loss[loss=2.963, NarTop10Accuracy=0.7186, over 6795.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7164, over 5946.16 frames. ], batch size: 17, lr: 2.43e-03
2024-08-06 22:16:22,484 INFO [trainer.py:765] (2/8) Epoch 35, batch 1200, train_loss[loss=2.925, NarTop10Accuracy=0.7415, over 7170.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7196, over 5931.71 frames. ], batch size: 31, lr: 2.43e-03
2024-08-06 22:16:57,060 INFO [trainer.py:765] (2/8) Epoch 35, batch 1300, train_loss[loss=2.792, NarTop10Accuracy=0.7638, over 5010.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7213, over 5998.76 frames. ], batch size: 6, lr: 2.43e-03
2024-08-06 22:17:31,060 INFO [trainer.py:765] (2/8) Epoch 35, batch 1400, train_loss[loss=3.109, NarTop10Accuracy=0.7106, over 6093.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7192, over 6026.50 frames. ], batch size: 11, lr: 2.43e-03
2024-08-06 22:18:03,062 INFO [trainer.py:765] (2/8) Epoch 35, batch 1500, train_loss[loss=3.129, NarTop10Accuracy=0.7077, over 5793.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7179, over 5961.97 frames. ], batch size: 51, lr: 2.43e-03
2024-08-06 22:18:30,728 INFO [trainer.py:765] (2/8) Epoch 35, batch 1600, train_loss[loss=2.824, NarTop10Accuracy=0.7621, over 7143.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7159, over 5939.97 frames. ], batch size: 22, lr: 2.43e-03
2024-08-06 22:18:57,320 INFO [trainer.py:765] (2/8) Epoch 35, batch 1700, train_loss[loss=2.967, NarTop10Accuracy=0.7339, over 6627.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7145, over 5903.24 frames. ], batch size: 14, lr: 2.42e-03
2024-08-06 22:19:23,702 INFO [trainer.py:765] (2/8) Epoch 35, batch 1800, train_loss[loss=3.434, NarTop10Accuracy=0.6349, over 7224.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7152, over 5973.46 frames. ], batch size: 22, lr: 2.42e-03
2024-08-06 22:19:50,201 INFO [trainer.py:765] (2/8) Epoch 35, batch 1900, train_loss[loss=3.18, NarTop10Accuracy=0.6996, over 6177.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7153, over 6013.66 frames. ], batch size: 50, lr: 2.42e-03
2024-08-06 22:20:15,762 INFO [trainer.py:765] (2/8) Epoch 35, batch 2000, train_loss[loss=3.102, NarTop10Accuracy=0.7069, over 6309.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7159, over 5997.80 frames. ], batch size: 50, lr: 2.42e-03
2024-08-06 22:20:41,045 INFO [trainer.py:765] (2/8) Epoch 35, batch 2100, train_loss[loss=2.63, NarTop10Accuracy=0.7997, over 3960.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7158, over 5967.81 frames. ], batch size: 4, lr: 2.42e-03
2024-08-06 22:21:06,226 INFO [trainer.py:765] (2/8) Epoch 35, batch 2200, train_loss[loss=2.932, NarTop10Accuracy=0.7485, over 7317.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7141, over 6002.21 frames. ], batch size: 31, lr: 2.42e-03
2024-08-06 22:21:31,286 INFO [trainer.py:765] (2/8) Epoch 35, batch 2300, train_loss[loss=3.015, NarTop10Accuracy=0.7213, over 5742.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7142, over 6026.60 frames. ], batch size: 9, lr: 2.42e-03
2024-08-06 22:21:55,648 INFO [trainer.py:765] (2/8) Epoch 35, batch 2400, train_loss[loss=3.334, NarTop10Accuracy=0.6639, over 5148.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7157, over 5776.63 frames. ], batch size: 7, lr: 2.42e-03
2024-08-06 22:21:59,681 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 22:22:07,656 INFO [trainer.py:811] (2/8) Epoch 35, validation: loss=2.905, NarTop10Accuracy=0.7437, over 1905321.00 frames. 
2024-08-06 22:22:07,657 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 22:22:08,116 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.895e+02 2.316e+02 2.462e+02 2.653e+02 5.566e+02, threshold=4.923e+02, percent-clipped=0.1
2024-08-06 22:22:27,128 INFO [trainer.py:765] (2/8) Epoch 35, batch 2500, train_loss[loss=3.12, NarTop10Accuracy=0.7022, over 5124.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.719, over 5470.61 frames. ], batch size: 7, lr: 2.41e-03
2024-08-06 22:22:46,976 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 22:23:47,172 INFO [trainer.py:765] (2/8) Epoch 36, batch 100, train_loss[loss=3.059, NarTop10Accuracy=0.7112, over 7449.00 frames. ], tot_loss[loss=2.99, NarTop10Accuracy=0.7275, over 2366.89 frames. ], batch size: 31, lr: 2.38e-03
2024-08-06 22:24:22,494 INFO [trainer.py:765] (2/8) Epoch 36, batch 200, train_loss[loss=2.862, NarTop10Accuracy=0.752, over 6792.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7223, over 3850.65 frames. ], batch size: 17, lr: 2.38e-03
2024-08-06 22:24:54,721 INFO [trainer.py:765] (2/8) Epoch 36, batch 300, train_loss[loss=3.261, NarTop10Accuracy=0.6726, over 7017.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7209, over 4646.74 frames. ], batch size: 22, lr: 2.37e-03
2024-08-06 22:25:29,276 INFO [trainer.py:765] (2/8) Epoch 36, batch 400, train_loss[loss=2.947, NarTop10Accuracy=0.735, over 5049.00 frames. ], tot_loss[loss=3.011, NarTop10Accuracy=0.723, over 5091.55 frames. ], batch size: 7, lr: 2.37e-03
2024-08-06 22:26:01,818 INFO [trainer.py:765] (2/8) Epoch 36, batch 500, train_loss[loss=3.254, NarTop10Accuracy=0.6678, over 6138.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.722, over 5361.46 frames. ], batch size: 11, lr: 2.37e-03
2024-08-06 22:26:35,026 INFO [trainer.py:765] (2/8) Epoch 36, batch 600, train_loss[loss=2.978, NarTop10Accuracy=0.7292, over 5733.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7219, over 5640.98 frames. ], batch size: 9, lr: 2.37e-03
2024-08-06 22:27:10,990 INFO [trainer.py:765] (2/8) Epoch 36, batch 700, train_loss[loss=3.176, NarTop10Accuracy=0.6908, over 5034.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7215, over 5699.94 frames. ], batch size: 6, lr: 2.37e-03
2024-08-06 22:27:44,914 INFO [trainer.py:765] (2/8) Epoch 36, batch 800, train_loss[loss=3.323, NarTop10Accuracy=0.6503, over 5070.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7188, over 5751.03 frames. ], batch size: 6, lr: 2.37e-03
2024-08-06 22:28:17,811 INFO [trainer.py:765] (2/8) Epoch 36, batch 900, train_loss[loss=2.815, NarTop10Accuracy=0.7695, over 6546.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7214, over 5798.99 frames. ], batch size: 14, lr: 2.37e-03
2024-08-06 22:28:56,983 INFO [trainer.py:765] (2/8) Epoch 36, batch 1000, train_loss[loss=3.335, NarTop10Accuracy=0.6523, over 6078.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7191, over 5908.23 frames. ], batch size: 13, lr: 2.37e-03
2024-08-06 22:29:29,364 INFO [trainer.py:765] (2/8) Epoch 36, batch 1100, train_loss[loss=2.853, NarTop10Accuracy=0.7586, over 6819.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7187, over 5931.98 frames. ], batch size: 17, lr: 2.36e-03
2024-08-06 22:30:05,681 INFO [trainer.py:765] (2/8) Epoch 36, batch 1200, train_loss[loss=2.997, NarTop10Accuracy=0.7194, over 7434.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7197, over 5934.57 frames. ], batch size: 32, lr: 2.36e-03
2024-08-06 22:30:42,575 INFO [trainer.py:765] (2/8) Epoch 36, batch 1300, train_loss[loss=2.823, NarTop10Accuracy=0.7557, over 5058.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7196, over 5988.09 frames. ], batch size: 6, lr: 2.36e-03
2024-08-06 22:31:15,938 INFO [trainer.py:765] (2/8) Epoch 36, batch 1400, train_loss[loss=3.078, NarTop10Accuracy=0.7089, over 6087.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7212, over 5993.17 frames. ], batch size: 11, lr: 2.36e-03
2024-08-06 22:31:43,748 INFO [trainer.py:765] (2/8) Epoch 36, batch 1500, train_loss[loss=3.422, NarTop10Accuracy=0.6427, over 5958.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7202, over 5929.60 frames. ], batch size: 50, lr: 2.36e-03
2024-08-06 22:32:11,459 INFO [trainer.py:765] (2/8) Epoch 36, batch 1600, train_loss[loss=3.318, NarTop10Accuracy=0.6644, over 7089.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7201, over 5928.54 frames. ], batch size: 22, lr: 2.36e-03
2024-08-06 22:32:38,108 INFO [trainer.py:765] (2/8) Epoch 36, batch 1700, train_loss[loss=3.259, NarTop10Accuracy=0.6635, over 6630.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7186, over 5917.05 frames. ], batch size: 14, lr: 2.36e-03
2024-08-06 22:33:04,554 INFO [trainer.py:765] (2/8) Epoch 36, batch 1800, train_loss[loss=3.272, NarTop10Accuracy=0.6691, over 6834.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7186, over 5985.46 frames. ], batch size: 22, lr: 2.36e-03
2024-08-06 22:33:15,169 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 22:33:23,567 INFO [trainer.py:811] (2/8) Epoch 36, validation: loss=2.897, NarTop10Accuracy=0.7457, over 1905321.00 frames. 
2024-08-06 22:33:23,568 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 22:33:24,096 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.876e+02 2.309e+02 2.476e+02 2.664e+02 4.811e+02, threshold=4.951e+02, percent-clipped=0.0
2024-08-06 22:33:39,456 INFO [trainer.py:765] (2/8) Epoch 36, batch 1900, train_loss[loss=2.958, NarTop10Accuracy=0.7315, over 6096.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7176, over 6045.77 frames. ], batch size: 53, lr: 2.35e-03
2024-08-06 22:34:05,077 INFO [trainer.py:765] (2/8) Epoch 36, batch 2000, train_loss[loss=3.217, NarTop10Accuracy=0.6904, over 6597.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7181, over 6021.83 frames. ], batch size: 50, lr: 2.35e-03
2024-08-06 22:34:30,514 INFO [trainer.py:765] (2/8) Epoch 36, batch 2100, train_loss[loss=2.688, NarTop10Accuracy=0.7829, over 4713.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7194, over 5995.24 frames. ], batch size: 5, lr: 2.35e-03
2024-08-06 22:34:55,938 INFO [trainer.py:765] (2/8) Epoch 36, batch 2200, train_loss[loss=3.418, NarTop10Accuracy=0.641, over 7068.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7152, over 6031.13 frames. ], batch size: 31, lr: 2.35e-03
2024-08-06 22:35:21,145 INFO [trainer.py:765] (2/8) Epoch 36, batch 2300, train_loss[loss=3.357, NarTop10Accuracy=0.6531, over 5637.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7133, over 6032.18 frames. ], batch size: 9, lr: 2.35e-03
2024-08-06 22:35:45,600 INFO [trainer.py:765] (2/8) Epoch 36, batch 2400, train_loss[loss=3.27, NarTop10Accuracy=0.675, over 5187.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.716, over 5801.87 frames. ], batch size: 7, lr: 2.35e-03
2024-08-06 22:36:09,182 INFO [trainer.py:765] (2/8) Epoch 36, batch 2500, train_loss[loss=2.675, NarTop10Accuracy=0.7842, over 5268.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7204, over 5503.40 frames. ], batch size: 7, lr: 2.35e-03
2024-08-06 22:36:28,955 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 22:37:29,724 INFO [trainer.py:765] (2/8) Epoch 37, batch 100, train_loss[loss=2.895, NarTop10Accuracy=0.7505, over 7128.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7152, over 2366.79 frames. ], batch size: 31, lr: 2.31e-03
2024-08-06 22:38:01,272 INFO [trainer.py:765] (2/8) Epoch 37, batch 200, train_loss[loss=2.761, NarTop10Accuracy=0.774, over 6750.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7193, over 3855.18 frames. ], batch size: 17, lr: 2.31e-03
2024-08-06 22:38:35,956 INFO [trainer.py:765] (2/8) Epoch 37, batch 300, train_loss[loss=3.075, NarTop10Accuracy=0.7024, over 7068.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7202, over 4653.94 frames. ], batch size: 22, lr: 2.31e-03
2024-08-06 22:39:09,306 INFO [trainer.py:765] (2/8) Epoch 37, batch 400, train_loss[loss=2.666, NarTop10Accuracy=0.7896, over 5097.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.723, over 5105.61 frames. ], batch size: 7, lr: 2.31e-03
2024-08-06 22:39:43,860 INFO [trainer.py:765] (2/8) Epoch 37, batch 500, train_loss[loss=3.337, NarTop10Accuracy=0.6568, over 6111.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7231, over 5387.56 frames. ], batch size: 11, lr: 2.31e-03
2024-08-06 22:40:17,332 INFO [trainer.py:765] (2/8) Epoch 37, batch 600, train_loss[loss=2.704, NarTop10Accuracy=0.793, over 5715.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7221, over 5642.39 frames. ], batch size: 9, lr: 2.31e-03
2024-08-06 22:40:51,615 INFO [trainer.py:765] (2/8) Epoch 37, batch 700, train_loss[loss=3.204, NarTop10Accuracy=0.6841, over 4299.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7172, over 5714.21 frames. ], batch size: 5, lr: 2.30e-03
2024-08-06 22:41:30,564 INFO [trainer.py:765] (2/8) Epoch 37, batch 800, train_loss[loss=2.755, NarTop10Accuracy=0.7697, over 5145.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7168, over 5761.36 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:41:59,082 INFO [trainer.py:765] (2/8) Epoch 37, batch 900, train_loss[loss=2.977, NarTop10Accuracy=0.7258, over 6687.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7208, over 5804.59 frames. ], batch size: 14, lr: 2.30e-03
2024-08-06 22:42:38,267 INFO [trainer.py:765] (2/8) Epoch 37, batch 1000, train_loss[loss=3.253, NarTop10Accuracy=0.6706, over 6570.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7183, over 5898.84 frames. ], batch size: 14, lr: 2.30e-03
2024-08-06 22:43:15,906 INFO [trainer.py:765] (2/8) Epoch 37, batch 1100, train_loss[loss=2.964, NarTop10Accuracy=0.7328, over 7071.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7171, over 5933.70 frames. ], batch size: 18, lr: 2.30e-03
2024-08-06 22:43:47,739 INFO [trainer.py:765] (2/8) Epoch 37, batch 1200, train_loss[loss=2.919, NarTop10Accuracy=0.7424, over 7563.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7172, over 5924.00 frames. ], batch size: 31, lr: 2.30e-03
2024-08-06 22:44:11,753 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 22:44:20,075 INFO [trainer.py:811] (2/8) Epoch 37, validation: loss=2.92, NarTop10Accuracy=0.7407, over 1905321.00 frames. 
2024-08-06 22:44:20,076 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 22:44:20,606 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.887e+02 2.309e+02 2.481e+02 2.647e+02 8.766e+02, threshold=4.961e+02, percent-clipped=0.1
2024-08-06 22:44:32,783 INFO [trainer.py:765] (2/8) Epoch 37, batch 1300, train_loss[loss=2.699, NarTop10Accuracy=0.7833, over 5064.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7208, over 5998.50 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:45:10,387 INFO [trainer.py:765] (2/8) Epoch 37, batch 1400, train_loss[loss=2.767, NarTop10Accuracy=0.7826, over 6066.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7217, over 6013.38 frames. ], batch size: 11, lr: 2.30e-03
2024-08-06 22:45:40,511 INFO [trainer.py:765] (2/8) Epoch 37, batch 1500, train_loss[loss=2.976, NarTop10Accuracy=0.734, over 5655.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7189, over 5947.98 frames. ], batch size: 51, lr: 2.29e-03
2024-08-06 22:46:08,437 INFO [trainer.py:765] (2/8) Epoch 37, batch 1600, train_loss[loss=3.313, NarTop10Accuracy=0.6631, over 7131.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7169, over 5924.64 frames. ], batch size: 22, lr: 2.29e-03
2024-08-06 22:46:35,186 INFO [trainer.py:765] (2/8) Epoch 37, batch 1700, train_loss[loss=3.323, NarTop10Accuracy=0.6567, over 6189.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7178, over 5900.92 frames. ], batch size: 13, lr: 2.29e-03
2024-08-06 22:47:01,792 INFO [trainer.py:765] (2/8) Epoch 37, batch 1800, train_loss[loss=2.9, NarTop10Accuracy=0.7436, over 6939.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7186, over 5975.70 frames. ], batch size: 22, lr: 2.29e-03
2024-08-06 22:47:28,311 INFO [trainer.py:765] (2/8) Epoch 37, batch 1900, train_loss[loss=3.105, NarTop10Accuracy=0.7033, over 6480.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7187, over 6002.84 frames. ], batch size: 50, lr: 2.29e-03
2024-08-06 22:47:53,924 INFO [trainer.py:765] (2/8) Epoch 37, batch 2000, train_loss[loss=3.217, NarTop10Accuracy=0.6858, over 6024.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7188, over 5989.86 frames. ], batch size: 54, lr: 2.29e-03
2024-08-06 22:48:19,325 INFO [trainer.py:765] (2/8) Epoch 37, batch 2100, train_loss[loss=2.945, NarTop10Accuracy=0.7345, over 5034.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7187, over 5972.78 frames. ], batch size: 5, lr: 2.29e-03
2024-08-06 22:48:44,707 INFO [trainer.py:765] (2/8) Epoch 37, batch 2200, train_loss[loss=2.914, NarTop10Accuracy=0.7458, over 7257.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7171, over 6026.64 frames. ], batch size: 31, lr: 2.29e-03
2024-08-06 22:49:09,912 INFO [trainer.py:765] (2/8) Epoch 37, batch 2300, train_loss[loss=2.846, NarTop10Accuracy=0.7625, over 5781.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7172, over 6043.25 frames. ], batch size: 9, lr: 2.29e-03
2024-08-06 22:49:34,318 INFO [trainer.py:765] (2/8) Epoch 37, batch 2400, train_loss[loss=3.272, NarTop10Accuracy=0.6744, over 5070.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7194, over 5778.10 frames. ], batch size: 7, lr: 2.28e-03
2024-08-06 22:49:57,860 INFO [trainer.py:765] (2/8) Epoch 37, batch 2500, train_loss[loss=3.113, NarTop10Accuracy=0.6913, over 5166.00 frames. ], tot_loss[loss=2.993, NarTop10Accuracy=0.7267, over 5490.62 frames. ], batch size: 7, lr: 2.28e-03
2024-08-06 22:50:17,816 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 22:51:16,152 INFO [trainer.py:765] (2/8) Epoch 38, batch 100, train_loss[loss=2.951, NarTop10Accuracy=0.7369, over 7443.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7232, over 2363.44 frames. ], batch size: 31, lr: 2.25e-03
2024-08-06 22:51:53,014 INFO [trainer.py:765] (2/8) Epoch 38, batch 200, train_loss[loss=3.276, NarTop10Accuracy=0.6712, over 6789.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7218, over 3867.62 frames. ], batch size: 17, lr: 2.25e-03
2024-08-06 22:52:25,202 INFO [trainer.py:765] (2/8) Epoch 38, batch 300, train_loss[loss=2.959, NarTop10Accuracy=0.7384, over 7011.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7184, over 4666.06 frames. ], batch size: 22, lr: 2.25e-03
2024-08-06 22:52:55,627 INFO [trainer.py:765] (2/8) Epoch 38, batch 400, train_loss[loss=3.168, NarTop10Accuracy=0.6886, over 5052.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.721, over 5114.42 frames. ], batch size: 7, lr: 2.25e-03
2024-08-06 22:53:32,229 INFO [trainer.py:765] (2/8) Epoch 38, batch 500, train_loss[loss=2.856, NarTop10Accuracy=0.7572, over 6042.00 frames. ], tot_loss[loss=2.982, NarTop10Accuracy=0.7288, over 5398.97 frames. ], batch size: 11, lr: 2.25e-03
2024-08-06 22:54:05,497 INFO [trainer.py:765] (2/8) Epoch 38, batch 600, train_loss[loss=3.1, NarTop10Accuracy=0.7069, over 5877.00 frames. ], tot_loss[loss=3.001, NarTop10Accuracy=0.7251, over 5651.15 frames. ], batch size: 9, lr: 2.24e-03
2024-08-06 22:54:36,002 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 22:54:43,918 INFO [trainer.py:811] (2/8) Epoch 38, validation: loss=2.939, NarTop10Accuracy=0.7369, over 1905321.00 frames. 
2024-08-06 22:54:43,919 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 22:54:44,427 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.880e+02 2.313e+02 2.478e+02 2.663e+02 7.254e+02, threshold=4.957e+02, percent-clipped=0.3
2024-08-06 22:54:46,657 INFO [trainer.py:765] (2/8) Epoch 38, batch 700, train_loss[loss=2.818, NarTop10Accuracy=0.7523, over 5004.00 frames. ], tot_loss[loss=3.003, NarTop10Accuracy=0.7249, over 5721.99 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:55:24,937 INFO [trainer.py:765] (2/8) Epoch 38, batch 800, train_loss[loss=2.869, NarTop10Accuracy=0.7538, over 5139.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7213, over 5777.74 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:55:59,704 INFO [trainer.py:765] (2/8) Epoch 38, batch 900, train_loss[loss=2.836, NarTop10Accuracy=0.758, over 6291.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7219, over 5785.97 frames. ], batch size: 13, lr: 2.24e-03
2024-08-06 22:56:32,090 INFO [trainer.py:765] (2/8) Epoch 38, batch 1000, train_loss[loss=3.257, NarTop10Accuracy=0.6679, over 6045.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7212, over 5891.53 frames. ], batch size: 13, lr: 2.24e-03
2024-08-06 22:57:08,990 INFO [trainer.py:765] (2/8) Epoch 38, batch 1100, train_loss[loss=3.132, NarTop10Accuracy=0.6934, over 6984.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7175, over 5914.24 frames. ], batch size: 17, lr: 2.24e-03
2024-08-06 22:57:42,661 INFO [trainer.py:765] (2/8) Epoch 38, batch 1200, train_loss[loss=2.889, NarTop10Accuracy=0.7539, over 7182.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7184, over 5896.53 frames. ], batch size: 31, lr: 2.24e-03
2024-08-06 22:58:16,545 INFO [trainer.py:765] (2/8) Epoch 38, batch 1300, train_loss[loss=3.008, NarTop10Accuracy=0.6956, over 5013.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7176, over 5972.42 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:58:49,810 INFO [trainer.py:765] (2/8) Epoch 38, batch 1400, train_loss[loss=2.921, NarTop10Accuracy=0.7486, over 6102.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7141, over 5984.32 frames. ], batch size: 11, lr: 2.23e-03
2024-08-06 22:59:22,853 INFO [trainer.py:765] (2/8) Epoch 38, batch 1500, train_loss[loss=3.568, NarTop10Accuracy=0.6108, over 6207.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7183, over 5914.30 frames. ], batch size: 50, lr: 2.23e-03
2024-08-06 22:59:50,644 INFO [trainer.py:765] (2/8) Epoch 38, batch 1600, train_loss[loss=3.301, NarTop10Accuracy=0.6616, over 7074.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7171, over 5905.42 frames. ], batch size: 22, lr: 2.23e-03
2024-08-06 23:00:17,315 INFO [trainer.py:765] (2/8) Epoch 38, batch 1700, train_loss[loss=3.039, NarTop10Accuracy=0.7213, over 6063.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7143, over 5910.93 frames. ], batch size: 13, lr: 2.23e-03
2024-08-06 23:00:43,763 INFO [trainer.py:765] (2/8) Epoch 38, batch 1800, train_loss[loss=3.378, NarTop10Accuracy=0.6496, over 7062.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7163, over 5980.02 frames. ], batch size: 22, lr: 2.23e-03
2024-08-06 23:01:10,192 INFO [trainer.py:765] (2/8) Epoch 38, batch 1900, train_loss[loss=3.388, NarTop10Accuracy=0.6489, over 6213.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7155, over 6005.89 frames. ], batch size: 51, lr: 2.23e-03
2024-08-06 23:01:35,681 INFO [trainer.py:765] (2/8) Epoch 38, batch 2000, train_loss[loss=3.268, NarTop10Accuracy=0.6674, over 5799.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7153, over 5978.34 frames. ], batch size: 50, lr: 2.23e-03
2024-08-06 23:02:01,050 INFO [trainer.py:765] (2/8) Epoch 38, batch 2100, train_loss[loss=2.891, NarTop10Accuracy=0.7414, over 3936.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7168, over 5954.39 frames. ], batch size: 4, lr: 2.23e-03
2024-08-06 23:02:26,314 INFO [trainer.py:765] (2/8) Epoch 38, batch 2200, train_loss[loss=2.945, NarTop10Accuracy=0.735, over 7266.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7169, over 6000.37 frames. ], batch size: 31, lr: 2.23e-03
2024-08-06 23:02:51,419 INFO [trainer.py:765] (2/8) Epoch 38, batch 2300, train_loss[loss=2.762, NarTop10Accuracy=0.7761, over 5754.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7162, over 6009.26 frames. ], batch size: 9, lr: 2.22e-03
2024-08-06 23:03:16,348 INFO [trainer.py:765] (2/8) Epoch 38, batch 2400, train_loss[loss=2.682, NarTop10Accuracy=0.7911, over 5142.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7182, over 5775.12 frames. ], batch size: 7, lr: 2.22e-03
2024-08-06 23:03:39,824 INFO [trainer.py:765] (2/8) Epoch 38, batch 2500, train_loss[loss=3.26, NarTop10Accuracy=0.6765, over 5130.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.723, over 5487.08 frames. ], batch size: 7, lr: 2.22e-03
2024-08-06 23:03:59,318 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 23:04:58,940 INFO [trainer.py:765] (2/8) Epoch 39, batch 100, train_loss[loss=3.394, NarTop10Accuracy=0.6484, over 7224.00 frames. ], tot_loss[loss=2.987, NarTop10Accuracy=0.7281, over 2384.12 frames. ], batch size: 31, lr: 2.19e-03
2024-08-06 23:05:03,468 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 23:05:11,563 INFO [trainer.py:811] (2/8) Epoch 39, validation: loss=2.9, NarTop10Accuracy=0.7445, over 1905321.00 frames. 
2024-08-06 23:05:11,564 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 23:05:12,137 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.911e+02 2.316e+02 2.500e+02 2.688e+02 4.683e+02, threshold=5.001e+02, percent-clipped=0.0
2024-08-06 23:05:40,163 INFO [trainer.py:765] (2/8) Epoch 39, batch 200, train_loss[loss=2.803, NarTop10Accuracy=0.7724, over 6954.00 frames. ], tot_loss[loss=2.998, NarTop10Accuracy=0.7255, over 3859.08 frames. ], batch size: 17, lr: 2.19e-03
2024-08-06 23:06:17,293 INFO [trainer.py:765] (2/8) Epoch 39, batch 300, train_loss[loss=2.967, NarTop10Accuracy=0.7292, over 7140.00 frames. ], tot_loss[loss=2.99, NarTop10Accuracy=0.7275, over 4643.54 frames. ], batch size: 22, lr: 2.19e-03
2024-08-06 23:06:48,275 INFO [trainer.py:765] (2/8) Epoch 39, batch 400, train_loss[loss=2.871, NarTop10Accuracy=0.749, over 5145.00 frames. ], tot_loss[loss=2.995, NarTop10Accuracy=0.7268, over 5090.47 frames. ], batch size: 7, lr: 2.19e-03
2024-08-06 23:07:19,175 INFO [trainer.py:765] (2/8) Epoch 39, batch 500, train_loss[loss=3.406, NarTop10Accuracy=0.6374, over 6093.00 frames. ], tot_loss[loss=2.997, NarTop10Accuracy=0.726, over 5367.16 frames. ], batch size: 11, lr: 2.19e-03
2024-08-06 23:07:52,563 INFO [trainer.py:765] (2/8) Epoch 39, batch 600, train_loss[loss=2.764, NarTop10Accuracy=0.778, over 5709.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7231, over 5648.57 frames. ], batch size: 9, lr: 2.19e-03
2024-08-06 23:08:33,695 INFO [trainer.py:765] (2/8) Epoch 39, batch 700, train_loss[loss=3.152, NarTop10Accuracy=0.6968, over 5202.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7199, over 5699.04 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:09:05,861 INFO [trainer.py:765] (2/8) Epoch 39, batch 800, train_loss[loss=2.592, NarTop10Accuracy=0.8068, over 5010.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.719, over 5769.04 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:09:38,866 INFO [trainer.py:765] (2/8) Epoch 39, batch 900, train_loss[loss=3.436, NarTop10Accuracy=0.6434, over 6744.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7194, over 5793.83 frames. ], batch size: 14, lr: 2.18e-03
2024-08-06 23:10:18,460 INFO [trainer.py:765] (2/8) Epoch 39, batch 1000, train_loss[loss=2.874, NarTop10Accuracy=0.7516, over 6819.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7212, over 5904.50 frames. ], batch size: 14, lr: 2.18e-03
2024-08-06 23:10:53,934 INFO [trainer.py:765] (2/8) Epoch 39, batch 1100, train_loss[loss=2.821, NarTop10Accuracy=0.7717, over 6762.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7182, over 5944.60 frames. ], batch size: 17, lr: 2.18e-03
2024-08-06 23:11:27,822 INFO [trainer.py:765] (2/8) Epoch 39, batch 1200, train_loss[loss=2.94, NarTop10Accuracy=0.7422, over 7035.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7209, over 5923.87 frames. ], batch size: 31, lr: 2.18e-03
2024-08-06 23:12:07,253 INFO [trainer.py:765] (2/8) Epoch 39, batch 1300, train_loss[loss=2.783, NarTop10Accuracy=0.7743, over 5178.00 frames. ], tot_loss[loss=3.01, NarTop10Accuracy=0.7235, over 5998.58 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:12:39,301 INFO [trainer.py:765] (2/8) Epoch 39, batch 1400, train_loss[loss=3.012, NarTop10Accuracy=0.7213, over 6153.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7221, over 6037.97 frames. ], batch size: 11, lr: 2.18e-03
2024-08-06 23:13:09,756 INFO [trainer.py:765] (2/8) Epoch 39, batch 1500, train_loss[loss=3.541, NarTop10Accuracy=0.6184, over 6156.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7226, over 5971.99 frames. ], batch size: 50, lr: 2.18e-03
2024-08-06 23:13:37,586 INFO [trainer.py:765] (2/8) Epoch 39, batch 1600, train_loss[loss=2.913, NarTop10Accuracy=0.7349, over 6975.00 frames. ], tot_loss[loss=3.005, NarTop10Accuracy=0.7245, over 5932.93 frames. ], batch size: 22, lr: 2.17e-03
2024-08-06 23:14:04,220 INFO [trainer.py:765] (2/8) Epoch 39, batch 1700, train_loss[loss=3.317, NarTop10Accuracy=0.6572, over 6711.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7177, over 5920.98 frames. ], batch size: 14, lr: 2.17e-03
2024-08-06 23:14:30,768 INFO [trainer.py:765] (2/8) Epoch 39, batch 1800, train_loss[loss=2.834, NarTop10Accuracy=0.7585, over 7290.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.718, over 5972.47 frames. ], batch size: 22, lr: 2.17e-03
2024-08-06 23:14:57,180 INFO [trainer.py:765] (2/8) Epoch 39, batch 1900, train_loss[loss=3.022, NarTop10Accuracy=0.7265, over 6264.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7158, over 6020.54 frames. ], batch size: 50, lr: 2.17e-03
2024-08-06 23:15:22,750 INFO [trainer.py:765] (2/8) Epoch 39, batch 2000, train_loss[loss=3.234, NarTop10Accuracy=0.6689, over 5949.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7201, over 5989.24 frames. ], batch size: 50, lr: 2.17e-03
2024-08-06 23:15:48,060 INFO [trainer.py:765] (2/8) Epoch 39, batch 2100, train_loss[loss=3.242, NarTop10Accuracy=0.6708, over 4749.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7204, over 5962.05 frames. ], batch size: 5, lr: 2.17e-03
2024-08-06 23:15:51,871 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 23:16:02,156 INFO [trainer.py:811] (2/8) Epoch 39, validation: loss=2.85, NarTop10Accuracy=0.7552, over 1905321.00 frames. 
2024-08-06 23:16:02,157 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 23:16:02,645 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.940e+02 2.369e+02 2.530e+02 2.720e+02 6.127e+02, threshold=5.059e+02, percent-clipped=0.2
2024-08-06 23:16:23,652 INFO [trainer.py:765] (2/8) Epoch 39, batch 2200, train_loss[loss=3.154, NarTop10Accuracy=0.696, over 7155.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.72, over 6007.73 frames. ], batch size: 31, lr: 2.17e-03
2024-08-06 23:16:48,847 INFO [trainer.py:765] (2/8) Epoch 39, batch 2300, train_loss[loss=2.78, NarTop10Accuracy=0.7764, over 5805.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7166, over 6021.53 frames. ], batch size: 9, lr: 2.17e-03
2024-08-06 23:17:13,136 INFO [trainer.py:765] (2/8) Epoch 39, batch 2400, train_loss[loss=2.753, NarTop10Accuracy=0.7723, over 5088.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7222, over 5770.20 frames. ], batch size: 7, lr: 2.17e-03
2024-08-06 23:17:36,712 INFO [trainer.py:765] (2/8) Epoch 39, batch 2500, train_loss[loss=2.904, NarTop10Accuracy=0.7388, over 5181.00 frames. ], tot_loss[loss=2.991, NarTop10Accuracy=0.7265, over 5475.22 frames. ], batch size: 7, lr: 2.16e-03
2024-08-06 23:17:56,329 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 23:18:48,947 INFO [trainer.py:765] (2/8) Epoch 40, batch 100, train_loss[loss=3.043, NarTop10Accuracy=0.7177, over 7452.00 frames. ], tot_loss[loss=2.996, NarTop10Accuracy=0.7261, over 2386.02 frames. ], batch size: 33, lr: 2.14e-03
2024-08-06 23:19:23,035 INFO [trainer.py:765] (2/8) Epoch 40, batch 200, train_loss[loss=2.743, NarTop10Accuracy=0.7797, over 6933.00 frames. ], tot_loss[loss=2.992, NarTop10Accuracy=0.7275, over 3859.19 frames. ], batch size: 17, lr: 2.13e-03
2024-08-06 23:19:57,188 INFO [trainer.py:765] (2/8) Epoch 40, batch 300, train_loss[loss=2.74, NarTop10Accuracy=0.7675, over 7275.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7223, over 4653.45 frames. ], batch size: 22, lr: 2.13e-03
2024-08-06 23:20:30,182 INFO [trainer.py:765] (2/8) Epoch 40, batch 400, train_loss[loss=2.962, NarTop10Accuracy=0.7348, over 5055.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7233, over 5111.17 frames. ], batch size: 7, lr: 2.13e-03
2024-08-06 23:21:00,250 INFO [trainer.py:765] (2/8) Epoch 40, batch 500, train_loss[loss=2.758, NarTop10Accuracy=0.7779, over 6099.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7232, over 5378.39 frames. ], batch size: 11, lr: 2.13e-03
2024-08-06 23:21:34,880 INFO [trainer.py:765] (2/8) Epoch 40, batch 600, train_loss[loss=2.913, NarTop10Accuracy=0.7406, over 5652.00 frames. ], tot_loss[loss=2.997, NarTop10Accuracy=0.7257, over 5631.56 frames. ], batch size: 9, lr: 2.13e-03
2024-08-06 23:22:11,097 INFO [trainer.py:765] (2/8) Epoch 40, batch 700, train_loss[loss=3.067, NarTop10Accuracy=0.7095, over 5019.00 frames. ], tot_loss[loss=3.011, NarTop10Accuracy=0.7229, over 5720.15 frames. ], batch size: 6, lr: 2.13e-03
2024-08-06 23:22:44,753 INFO [trainer.py:765] (2/8) Epoch 40, batch 800, train_loss[loss=2.722, NarTop10Accuracy=0.7772, over 5067.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.721, over 5782.69 frames. ], batch size: 6, lr: 2.13e-03
2024-08-06 23:23:16,635 INFO [trainer.py:765] (2/8) Epoch 40, batch 900, train_loss[loss=3.265, NarTop10Accuracy=0.6697, over 6282.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7212, over 5802.91 frames. ], batch size: 13, lr: 2.13e-03
2024-08-06 23:23:55,591 INFO [trainer.py:765] (2/8) Epoch 40, batch 1000, train_loss[loss=3.247, NarTop10Accuracy=0.6647, over 6261.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7192, over 5909.27 frames. ], batch size: 13, lr: 2.13e-03
2024-08-06 23:24:30,208 INFO [trainer.py:765] (2/8) Epoch 40, batch 1100, train_loss[loss=2.768, NarTop10Accuracy=0.7715, over 6879.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7203, over 5931.54 frames. ], batch size: 17, lr: 2.12e-03
2024-08-06 23:25:03,090 INFO [trainer.py:765] (2/8) Epoch 40, batch 1200, train_loss[loss=2.867, NarTop10Accuracy=0.7521, over 7041.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.721, over 5935.84 frames. ], batch size: 31, lr: 2.12e-03
2024-08-06 23:25:41,842 INFO [trainer.py:765] (2/8) Epoch 40, batch 1300, train_loss[loss=2.823, NarTop10Accuracy=0.7659, over 5031.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7224, over 6007.05 frames. ], batch size: 6, lr: 2.12e-03
2024-08-06 23:26:13,385 INFO [trainer.py:765] (2/8) Epoch 40, batch 1400, train_loss[loss=2.833, NarTop10Accuracy=0.7686, over 6015.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7213, over 6010.38 frames. ], batch size: 11, lr: 2.12e-03
2024-08-06 23:26:43,377 INFO [trainer.py:765] (2/8) Epoch 40, batch 1500, train_loss[loss=3.243, NarTop10Accuracy=0.6776, over 5703.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7233, over 5940.99 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:26:54,420 INFO [trainer.py:803] (2/8) Computing validation loss
2024-08-06 23:27:02,676 INFO [trainer.py:811] (2/8) Epoch 40, validation: loss=2.86, NarTop10Accuracy=0.7522, over 1905321.00 frames. 
2024-08-06 23:27:02,677 INFO [trainer.py:814] (2/8) Maximum memory allocated so far is 30120MB
2024-08-06 23:27:03,156 INFO [optim.py:386] (2/8) Clipping_scale=2.0, grad-norm quartiles 1.941e+02 2.329e+02 2.511e+02 2.723e+02 1.241e+03, threshold=5.022e+02, percent-clipped=0.2
2024-08-06 23:27:19,381 INFO [trainer.py:765] (2/8) Epoch 40, batch 1600, train_loss[loss=2.892, NarTop10Accuracy=0.7482, over 6927.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7228, over 5933.03 frames. ], batch size: 22, lr: 2.12e-03
2024-08-06 23:27:46,056 INFO [trainer.py:765] (2/8) Epoch 40, batch 1700, train_loss[loss=3.315, NarTop10Accuracy=0.6573, over 6150.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7216, over 5918.01 frames. ], batch size: 13, lr: 2.12e-03
2024-08-06 23:28:12,578 INFO [trainer.py:765] (2/8) Epoch 40, batch 1800, train_loss[loss=3.08, NarTop10Accuracy=0.711, over 7260.00 frames. ], tot_loss[loss=3.002, NarTop10Accuracy=0.7244, over 5970.24 frames. ], batch size: 22, lr: 2.12e-03
2024-08-06 23:28:38,908 INFO [trainer.py:765] (2/8) Epoch 40, batch 1900, train_loss[loss=3.183, NarTop10Accuracy=0.6875, over 5928.00 frames. ], tot_loss[loss=3.007, NarTop10Accuracy=0.7236, over 6015.93 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:29:04,444 INFO [trainer.py:765] (2/8) Epoch 40, batch 2000, train_loss[loss=3.516, NarTop10Accuracy=0.6232, over 6153.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7235, over 5994.93 frames. ], batch size: 51, lr: 2.12e-03
2024-08-06 23:29:29,750 INFO [trainer.py:765] (2/8) Epoch 40, batch 2100, train_loss[loss=2.884, NarTop10Accuracy=0.7569, over 4035.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7229, over 5975.79 frames. ], batch size: 4, lr: 2.11e-03
2024-08-06 23:29:54,939 INFO [trainer.py:765] (2/8) Epoch 40, batch 2200, train_loss[loss=3.168, NarTop10Accuracy=0.6909, over 7416.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7203, over 6018.34 frames. ], batch size: 31, lr: 2.11e-03
2024-08-06 23:30:20,012 INFO [trainer.py:765] (2/8) Epoch 40, batch 2300, train_loss[loss=2.843, NarTop10Accuracy=0.7537, over 5703.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.72, over 6022.31 frames. ], batch size: 9, lr: 2.11e-03
2024-08-06 23:30:44,296 INFO [trainer.py:765] (2/8) Epoch 40, batch 2400, train_loss[loss=2.729, NarTop10Accuracy=0.7802, over 5223.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7215, over 5766.36 frames. ], batch size: 7, lr: 2.11e-03
2024-08-06 23:31:07,738 INFO [trainer.py:765] (2/8) Epoch 40, batch 2500, train_loss[loss=2.914, NarTop10Accuracy=0.7318, over 5154.00 frames. ], tot_loss[loss=2.984, NarTop10Accuracy=0.728, over 5468.88 frames. ], batch size: 7, lr: 2.11e-03
2024-08-06 23:31:27,883 INFO [trainer.py:650] (2/8) Reaches end of dataloader.
2024-08-06 23:31:27,886 INFO [trainer.py:1069] (2/8) Done!