2024-08-06 14:23:41,780 INFO [trainer.py:870] (7/8) Training started
2024-08-06 14:23:41,781 INFO [trainer.py:889] (7/8) Device: cuda:7
2024-08-06 14:23:41,781 INFO [trainer.py:890] (7/8) {'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 14:23:41,781 INFO [trainer.py:892] (7/8) About to create model
2024-08-06 14:23:42,502 INFO [trainer.py:899] (7/8) Number of model parameters: 367386628
2024-08-06 14:23:42,503 INFO [checkpoint.py:112] (7/8) Loading checkpoint from exp/valle/epoch-99.pt
2024-08-06 14:23:47,405 INFO [trainer.py:914] (7/8) Using DDP
2024-08-06 14:23:49,635 INFO [datamodule.py:427] (7/8) About to get train cuts
2024-08-06 14:23:49,638 INFO [datamodule.py:434] (7/8) About to get dev cuts
2024-08-06 14:23:49,639 INFO [datamodule.py:292] (7/8) Disable SpecAugment
2024-08-06 14:23:49,639 INFO [datamodule.py:294] (7/8) About to create train dataset
2024-08-06 14:23:49,642 INFO [datamodule.py:323] (7/8) Using DynamicBucketingSampler
2024-08-06 14:23:50,260 INFO [datamodule.py:344] (7/8) About to create train dataloader
2024-08-06 14:23:50,260 INFO [datamodule.py:367] (7/8) About to create dev dataset
2024-08-06 14:23:50,593 INFO [datamodule.py:388] (7/8) About to create dev dataloader
2024-08-06 14:24:38,250 INFO [trainer.py:765] (7/8) Epoch 1, batch 100, train_loss[loss=103.5, NarTop10Accuracy=0.02183, over 7275.00 frames. ], tot_loss[loss=74.16, NarTop10Accuracy=0.04611, over 2357.02 frames. ], batch size: 31, lr: 2.25e-02
2024-08-06 14:25:07,520 INFO [trainer.py:765] (7/8) Epoch 1, batch 200, train_loss[loss=143.3, NarTop10Accuracy=0.01556, over 6918.00 frames. ], tot_loss[loss=97.4, NarTop10Accuracy=0.04159, over 3849.95 frames. ], batch size: 17, lr: 3.00e-02
2024-08-06 14:25:37,111 INFO [trainer.py:765] (7/8) Epoch 1, batch 300, train_loss[loss=104.7, NarTop10Accuracy=0.0253, over 7089.00 frames. ], tot_loss[loss=84.96, NarTop10Accuracy=0.04262, over 4637.01 frames. ], batch size: 22, lr: 3.00e-02
2024-08-06 14:26:07,483 INFO [trainer.py:765] (7/8) Epoch 1, batch 400, train_loss[loss=52.83, NarTop10Accuracy=0.02097, over 5247.00 frames. ], tot_loss[loss=67.82, NarTop10Accuracy=0.04698, over 5084.36 frames. ], batch size: 7, lr: 3.00e-02
2024-08-06 14:26:35,358 INFO [trainer.py:765] (7/8) Epoch 1, batch 500, train_loss[loss=14.57, NarTop10Accuracy=0.02305, over 5964.00 frames. ], tot_loss[loss=48.99, NarTop10Accuracy=0.05073, over 5372.44 frames. ], batch size: 11, lr: 2.99e-02
2024-08-06 14:27:04,001 INFO [trainer.py:765] (7/8) Epoch 1, batch 600, train_loss[loss=6.292, NarTop10Accuracy=0.1426, over 5664.00 frames. ], tot_loss[loss=33.4, NarTop10Accuracy=0.05573, over 5644.19 frames. ], batch size: 9, lr: 2.99e-02
2024-08-06 14:27:39,491 INFO [trainer.py:765] (7/8) Epoch 1, batch 700, train_loss[loss=6.78, NarTop10Accuracy=0.1415, over 4347.00 frames. ], tot_loss[loss=23.36, NarTop10Accuracy=0.06433, over 5726.15 frames. ], batch size: 5, lr: 2.99e-02
2024-08-06 14:28:08,832 INFO [trainer.py:765] (7/8) Epoch 1, batch 800, train_loss[loss=6.497, NarTop10Accuracy=0.1292, over 5106.00 frames. ], tot_loss[loss=17.1, NarTop10Accuracy=0.08539, over 5802.30 frames. ], batch size: 6, lr: 2.98e-02
2024-08-06 14:28:36,758 INFO [trainer.py:765] (7/8) Epoch 1, batch 900, train_loss[loss=5.749, NarTop10Accuracy=0.1873, over 6552.00 frames. ], tot_loss[loss=12.76, NarTop10Accuracy=0.1136, over 5809.49 frames. ], batch size: 14, lr: 2.98e-02
2024-08-06 14:29:12,587 INFO [trainer.py:765] (7/8) Epoch 1, batch 1000, train_loss[loss=5.706, NarTop10Accuracy=0.1899, over 6186.00 frames. ], tot_loss[loss=10.09, NarTop10Accuracy=0.1334, over 5911.50 frames. ], batch size: 13, lr: 2.97e-02
2024-08-06 14:29:42,826 INFO [trainer.py:765] (7/8) Epoch 1, batch 1100, train_loss[loss=5.693, NarTop10Accuracy=0.1925, over 6918.00 frames. ], tot_loss[loss=8.407, NarTop10Accuracy=0.1515, over 5957.99 frames. ], batch size: 17, lr: 2.96e-02
2024-08-06 14:30:11,469 INFO [trainer.py:765] (7/8) Epoch 1, batch 1200, train_loss[loss=5.936, NarTop10Accuracy=0.1677, over 7143.00 frames. ], tot_loss[loss=7.343, NarTop10Accuracy=0.1717, over 5930.53 frames. ], batch size: 31, lr: 2.96e-02
2024-08-06 14:30:48,748 INFO [trainer.py:765] (7/8) Epoch 1, batch 1300, train_loss[loss=5.253, NarTop10Accuracy=0.2725, over 4968.00 frames. ], tot_loss[loss=6.673, NarTop10Accuracy=0.1876, over 5993.47 frames. ], batch size: 6, lr: 2.95e-02
2024-08-06 14:31:18,144 INFO [trainer.py:765] (7/8) Epoch 1, batch 1400, train_loss[loss=5.685, NarTop10Accuracy=0.1904, over 6060.00 frames. ], tot_loss[loss=6.247, NarTop10Accuracy=0.1979, over 6003.05 frames. ], batch size: 11, lr: 2.94e-02
2024-08-06 14:31:46,026 INFO [trainer.py:765] (7/8) Epoch 1, batch 1500, train_loss[loss=5.648, NarTop10Accuracy=0.209, over 5748.00 frames. ], tot_loss[loss=5.969, NarTop10Accuracy=0.2095, over 5936.07 frames. ], batch size: 50, lr: 2.94e-02
2024-08-06 14:32:13,692 INFO [trainer.py:765] (7/8) Epoch 1, batch 1600, train_loss[loss=5.588, NarTop10Accuracy=0.215, over 6840.00 frames. ], tot_loss[loss=5.788, NarTop10Accuracy=0.218, over 5928.93 frames. ], batch size: 22, lr: 2.93e-02
2024-08-06 14:32:40,199 INFO [trainer.py:765] (7/8) Epoch 1, batch 1700, train_loss[loss=5.307, NarTop10Accuracy=0.281, over 6201.00 frames. ], tot_loss[loss=5.669, NarTop10Accuracy=0.2244, over 5940.57 frames. ], batch size: 13, lr: 2.92e-02
2024-08-06 14:33:06,500 INFO [trainer.py:765] (7/8) Epoch 1, batch 1800, train_loss[loss=5.657, NarTop10Accuracy=0.1914, over 6969.00 frames. ], tot_loss[loss=5.581, NarTop10Accuracy=0.232, over 5985.38 frames. ], batch size: 22, lr: 2.91e-02
2024-08-06 14:33:32,625 INFO [trainer.py:765] (7/8) Epoch 1, batch 1900, train_loss[loss=5.803, NarTop10Accuracy=0.1758, over 5970.00 frames. ], tot_loss[loss=5.516, NarTop10Accuracy=0.2392, over 6028.30 frames. ], batch size: 50, lr: 2.90e-02
2024-08-06 14:33:58,015 INFO [trainer.py:765] (7/8) Epoch 1, batch 2000, train_loss[loss=5.538, NarTop10Accuracy=0.2249, over 6180.00 frames. ], tot_loss[loss=5.453, NarTop10Accuracy=0.2481, over 5974.13 frames. ], batch size: 52, lr: 2.89e-02
2024-08-06 14:33:58,016 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 14:34:06,103 INFO [trainer.py:811] (7/8) Epoch 1, validation: loss=5.397, NarTop10Accuracy=0.2581, over 1905321.00 frames. 
2024-08-06 14:34:06,104 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 26703MB
2024-08-06 14:34:06,612 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 1, batch 2100, train_loss[loss=5.309, NarTop10Accuracy=0.2659, over 4800.00 frames. ], tot_loss[loss=5.385, NarTop10Accuracy=0.2597, over 5967.37 frames. ], batch size: 5, lr: 2.88e-02
2024-08-06 14:34:57,304 INFO [trainer.py:765] (7/8) Epoch 1, batch 2200, train_loss[loss=5.409, NarTop10Accuracy=0.2639, over 7545.00 frames. ], tot_loss[loss=5.345, NarTop10Accuracy=0.266, over 6007.51 frames. ], batch size: 31, lr: 2.87e-02
2024-08-06 14:35:22,456 INFO [trainer.py:765] (7/8) Epoch 1, batch 2300, train_loss[loss=5.259, NarTop10Accuracy=0.2727, over 5718.00 frames. ], tot_loss[loss=5.331, NarTop10Accuracy=0.2684, over 6013.97 frames. ], batch size: 9, lr: 2.86e-02
2024-08-06 14:35:46,816 INFO [trainer.py:765] (7/8) Epoch 1, batch 2400, train_loss[loss=5.347, NarTop10Accuracy=0.2648, over 5049.00 frames. ], tot_loss[loss=5.278, NarTop10Accuracy=0.2783, over 5761.50 frames. ], batch size: 7, lr: 2.85e-02
2024-08-06 14:36:10,408 INFO [trainer.py:765] (7/8) Epoch 1, batch 2500, train_loss[loss=4.847, NarTop10Accuracy=0.3618, over 5199.00 frames. ], tot_loss[loss=5.217, NarTop10Accuracy=0.2889, over 5448.35 frames. ], batch size: 7, lr: 2.84e-02
2024-08-06 14:36:31,241 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 14:37:29,670 INFO [trainer.py:765] (7/8) Epoch 2, batch 100, train_loss[loss=4.949, NarTop10Accuracy=0.3522, over 7461.00 frames. ], tot_loss[loss=5.194, NarTop10Accuracy=0.2945, over 2368.21 frames. ], batch size: 32, lr: 2.77e-02
2024-08-06 14:38:10,016 INFO [trainer.py:765] (7/8) Epoch 2, batch 200, train_loss[loss=5.033, NarTop10Accuracy=0.3297, over 6681.00 frames. ], tot_loss[loss=5.165, NarTop10Accuracy=0.2994, over 3849.30 frames. ], batch size: 17, lr: 2.76e-02
2024-08-06 14:38:38,299 INFO [trainer.py:765] (7/8) Epoch 2, batch 300, train_loss[loss=5.161, NarTop10Accuracy=0.3015, over 6945.00 frames. ], tot_loss[loss=5.144, NarTop10Accuracy=0.3021, over 4651.14 frames. ], batch size: 22, lr: 2.75e-02
2024-08-06 14:39:07,000 INFO [trainer.py:765] (7/8) Epoch 2, batch 400, train_loss[loss=4.947, NarTop10Accuracy=0.3375, over 5034.00 frames. ], tot_loss[loss=5.11, NarTop10Accuracy=0.3078, over 5106.76 frames. ], batch size: 7, lr: 2.74e-02
2024-08-06 14:39:46,121 INFO [trainer.py:765] (7/8) Epoch 2, batch 500, train_loss[loss=5.028, NarTop10Accuracy=0.326, over 6078.00 frames. ], tot_loss[loss=5.076, NarTop10Accuracy=0.3149, over 5381.89 frames. ], batch size: 11, lr: 2.73e-02
2024-08-06 14:40:15,084 INFO [trainer.py:765] (7/8) Epoch 2, batch 600, train_loss[loss=4.928, NarTop10Accuracy=0.342, over 5619.00 frames. ], tot_loss[loss=5.053, NarTop10Accuracy=0.3191, over 5653.02 frames. ], batch size: 9, lr: 2.71e-02
2024-08-06 14:40:44,590 INFO [trainer.py:765] (7/8) Epoch 2, batch 700, train_loss[loss=5.016, NarTop10Accuracy=0.3258, over 4920.00 frames. ], tot_loss[loss=5.035, NarTop10Accuracy=0.322, over 5720.62 frames. ], batch size: 6, lr: 2.70e-02
2024-08-06 14:41:24,515 INFO [trainer.py:765] (7/8) Epoch 2, batch 800, train_loss[loss=5.147, NarTop10Accuracy=0.2925, over 5196.00 frames. ], tot_loss[loss=5.021, NarTop10Accuracy=0.3245, over 5769.14 frames. ], batch size: 6, lr: 2.69e-02
2024-08-06 14:41:54,406 INFO [trainer.py:765] (7/8) Epoch 2, batch 900, train_loss[loss=4.723, NarTop10Accuracy=0.382, over 6552.00 frames. ], tot_loss[loss=4.98, NarTop10Accuracy=0.3326, over 5812.00 frames. ], batch size: 14, lr: 2.68e-02
2024-08-06 14:42:23,903 INFO [trainer.py:765] (7/8) Epoch 2, batch 1000, train_loss[loss=4.744, NarTop10Accuracy=0.3803, over 6279.00 frames. ], tot_loss[loss=4.943, NarTop10Accuracy=0.3396, over 5902.87 frames. ], batch size: 13, lr: 2.66e-02
2024-08-06 14:42:56,256 INFO [trainer.py:765] (7/8) Epoch 2, batch 1100, train_loss[loss=5.004, NarTop10Accuracy=0.3297, over 6792.00 frames. ], tot_loss[loss=4.931, NarTop10Accuracy=0.3418, over 5936.72 frames. ], batch size: 17, lr: 2.65e-02
2024-08-06 14:43:35,187 INFO [trainer.py:765] (7/8) Epoch 2, batch 1200, train_loss[loss=4.809, NarTop10Accuracy=0.3634, over 7329.00 frames. ], tot_loss[loss=4.913, NarTop10Accuracy=0.3449, over 5931.35 frames. ], batch size: 31, lr: 2.64e-02
2024-08-06 14:44:04,348 INFO [trainer.py:765] (7/8) Epoch 2, batch 1300, train_loss[loss=4.874, NarTop10Accuracy=0.3499, over 5040.00 frames. ], tot_loss[loss=4.867, NarTop10Accuracy=0.3537, over 6000.91 frames. ], batch size: 6, lr: 2.63e-02
2024-08-06 14:44:33,728 INFO [trainer.py:765] (7/8) Epoch 2, batch 1400, train_loss[loss=4.878, NarTop10Accuracy=0.3497, over 6090.00 frames. ], tot_loss[loss=4.848, NarTop10Accuracy=0.3572, over 6011.51 frames. ], batch size: 11, lr: 2.61e-02
2024-08-06 14:44:40,442 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 14:44:48,506 INFO [trainer.py:811] (7/8) Epoch 2, validation: loss=4.808, NarTop10Accuracy=0.3642, over 1905321.00 frames. 
2024-08-06 14:44:48,506 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 26703MB
2024-08-06 14:44:49,204 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 2, batch 1500, train_loss[loss=4.873, NarTop10Accuracy=0.3492, over 5802.00 frames. ], tot_loss[loss=4.826, NarTop10Accuracy=0.3616, over 5951.23 frames. ], batch size: 50, lr: 2.60e-02
2024-08-06 14:45:37,659 INFO [trainer.py:765] (7/8) Epoch 2, batch 1600, train_loss[loss=4.719, NarTop10Accuracy=0.3809, over 7161.00 frames. ], tot_loss[loss=4.798, NarTop10Accuracy=0.3671, over 5933.45 frames. ], batch size: 22, lr: 2.59e-02
2024-08-06 14:46:04,368 INFO [trainer.py:765] (7/8) Epoch 2, batch 1700, train_loss[loss=4.798, NarTop10Accuracy=0.3643, over 6657.00 frames. ], tot_loss[loss=4.793, NarTop10Accuracy=0.3678, over 5918.01 frames. ], batch size: 14, lr: 2.58e-02
2024-08-06 14:46:31,034 INFO [trainer.py:765] (7/8) Epoch 2, batch 1800, train_loss[loss=4.672, NarTop10Accuracy=0.39, over 7017.00 frames. ], tot_loss[loss=4.771, NarTop10Accuracy=0.3722, over 5971.63 frames. ], batch size: 22, lr: 2.56e-02
2024-08-06 14:46:57,532 INFO [trainer.py:765] (7/8) Epoch 2, batch 1900, train_loss[loss=4.749, NarTop10Accuracy=0.3719, over 6399.00 frames. ], tot_loss[loss=4.743, NarTop10Accuracy=0.3779, over 6018.52 frames. ], batch size: 50, lr: 2.55e-02
2024-08-06 14:47:23,234 INFO [trainer.py:765] (7/8) Epoch 2, batch 2000, train_loss[loss=4.861, NarTop10Accuracy=0.362, over 5814.00 frames. ], tot_loss[loss=4.721, NarTop10Accuracy=0.3825, over 5995.37 frames. ], batch size: 50, lr: 2.54e-02
2024-08-06 14:47:48,588 INFO [trainer.py:765] (7/8) Epoch 2, batch 2100, train_loss[loss=4.703, NarTop10Accuracy=0.3802, over 4101.00 frames. ], tot_loss[loss=4.711, NarTop10Accuracy=0.3841, over 5968.96 frames. ], batch size: 4, lr: 2.53e-02
2024-08-06 14:48:13,765 INFO [trainer.py:765] (7/8) Epoch 2, batch 2200, train_loss[loss=4.628, NarTop10Accuracy=0.3973, over 7197.00 frames. ], tot_loss[loss=4.677, NarTop10Accuracy=0.3904, over 6003.98 frames. ], batch size: 31, lr: 2.51e-02
2024-08-06 14:48:38,951 INFO [trainer.py:765] (7/8) Epoch 2, batch 2300, train_loss[loss=4.781, NarTop10Accuracy=0.3589, over 5640.00 frames. ], tot_loss[loss=4.685, NarTop10Accuracy=0.3886, over 6021.34 frames. ], batch size: 9, lr: 2.50e-02
2024-08-06 14:49:03,319 INFO [trainer.py:765] (7/8) Epoch 2, batch 2400, train_loss[loss=4.532, NarTop10Accuracy=0.4153, over 5103.00 frames. ], tot_loss[loss=4.641, NarTop10Accuracy=0.3967, over 5765.71 frames. ], batch size: 7, lr: 2.49e-02
2024-08-06 14:49:26,867 INFO [trainer.py:765] (7/8) Epoch 2, batch 2500, train_loss[loss=4.678, NarTop10Accuracy=0.3882, over 5067.00 frames. ], tot_loss[loss=4.612, NarTop10Accuracy=0.4023, over 5475.98 frames. ], batch size: 7, lr: 2.48e-02
2024-08-06 14:49:46,816 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 14:50:51,117 INFO [trainer.py:765] (7/8) Epoch 3, batch 100, train_loss[loss=4.718, NarTop10Accuracy=0.3759, over 7464.00 frames. ], tot_loss[loss=4.585, NarTop10Accuracy=0.4079, over 2368.24 frames. ], batch size: 31, lr: 2.36e-02
2024-08-06 14:51:20,388 INFO [trainer.py:765] (7/8) Epoch 3, batch 200, train_loss[loss=4.751, NarTop10Accuracy=0.3717, over 6906.00 frames. ], tot_loss[loss=4.547, NarTop10Accuracy=0.4153, over 3860.36 frames. ], batch size: 17, lr: 2.34e-02
2024-08-06 14:51:50,953 INFO [trainer.py:765] (7/8) Epoch 3, batch 300, train_loss[loss=4.827, NarTop10Accuracy=0.3605, over 6906.00 frames. ], tot_loss[loss=4.521, NarTop10Accuracy=0.4205, over 4650.83 frames. ], batch size: 22, lr: 2.33e-02
2024-08-06 14:52:32,359 INFO [trainer.py:765] (7/8) Epoch 3, batch 400, train_loss[loss=4.758, NarTop10Accuracy=0.3733, over 5100.00 frames. ], tot_loss[loss=4.504, NarTop10Accuracy=0.4238, over 5089.34 frames. ], batch size: 7, lr: 2.32e-02
2024-08-06 14:53:00,680 INFO [trainer.py:765] (7/8) Epoch 3, batch 500, train_loss[loss=4.335, NarTop10Accuracy=0.4548, over 6504.00 frames. ], tot_loss[loss=4.495, NarTop10Accuracy=0.4256, over 5382.54 frames. ], batch size: 12, lr: 2.31e-02
2024-08-06 14:53:29,551 INFO [trainer.py:765] (7/8) Epoch 3, batch 600, train_loss[loss=4.186, NarTop10Accuracy=0.4943, over 5646.00 frames. ], tot_loss[loss=4.477, NarTop10Accuracy=0.4296, over 5649.23 frames. ], batch size: 9, lr: 2.30e-02
2024-08-06 14:54:12,465 INFO [trainer.py:765] (7/8) Epoch 3, batch 700, train_loss[loss=4.455, NarTop10Accuracy=0.4348, over 4269.00 frames. ], tot_loss[loss=4.45, NarTop10Accuracy=0.4346, over 5721.19 frames. ], batch size: 5, lr: 2.29e-02
2024-08-06 14:54:44,785 INFO [trainer.py:765] (7/8) Epoch 3, batch 800, train_loss[loss=4.282, NarTop10Accuracy=0.467, over 5262.00 frames. ], tot_loss[loss=4.426, NarTop10Accuracy=0.4397, over 5774.01 frames. ], batch size: 6, lr: 2.28e-02
2024-08-06 14:54:58,684 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 14:55:06,655 INFO [trainer.py:811] (7/8) Epoch 3, validation: loss=4.276, NarTop10Accuracy=0.4689, over 1905321.00 frames. 
2024-08-06 14:55:06,656 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 26703MB
2024-08-06 14:55:07,183 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 3, batch 900, train_loss[loss=4.25, NarTop10Accuracy=0.4737, over 6186.00 frames. ], tot_loss[loss=4.399, NarTop10Accuracy=0.4454, over 5787.96 frames. ], batch size: 13, lr: 2.26e-02
2024-08-06 14:56:04,958 INFO [trainer.py:765] (7/8) Epoch 3, batch 1000, train_loss[loss=4.297, NarTop10Accuracy=0.4703, over 6312.00 frames. ], tot_loss[loss=4.379, NarTop10Accuracy=0.4491, over 5888.54 frames. ], batch size: 13, lr: 2.25e-02
2024-08-06 14:56:37,300 INFO [trainer.py:765] (7/8) Epoch 3, batch 1100, train_loss[loss=4.542, NarTop10Accuracy=0.4187, over 6738.00 frames. ], tot_loss[loss=4.354, NarTop10Accuracy=0.4538, over 5928.27 frames. ], batch size: 17, lr: 2.24e-02
2024-08-06 14:57:06,377 INFO [trainer.py:765] (7/8) Epoch 3, batch 1200, train_loss[loss=4.429, NarTop10Accuracy=0.4404, over 7449.00 frames. ], tot_loss[loss=4.337, NarTop10Accuracy=0.4566, over 5923.02 frames. ], batch size: 31, lr: 2.23e-02
2024-08-06 14:57:51,630 INFO [trainer.py:765] (7/8) Epoch 3, batch 1300, train_loss[loss=4.304, NarTop10Accuracy=0.4529, over 5055.00 frames. ], tot_loss[loss=4.308, NarTop10Accuracy=0.4621, over 5985.69 frames. ], batch size: 6, lr: 2.22e-02
2024-08-06 14:58:22,899 INFO [trainer.py:765] (7/8) Epoch 3, batch 1400, train_loss[loss=4.16, NarTop10Accuracy=0.496, over 6102.00 frames. ], tot_loss[loss=4.297, NarTop10Accuracy=0.4642, over 6010.56 frames. ], batch size: 11, lr: 2.21e-02
2024-08-06 14:58:50,855 INFO [trainer.py:765] (7/8) Epoch 3, batch 1500, train_loss[loss=4.293, NarTop10Accuracy=0.4642, over 6270.00 frames. ], tot_loss[loss=4.278, NarTop10Accuracy=0.4675, over 5962.08 frames. ], batch size: 51, lr: 2.20e-02
2024-08-06 14:59:18,715 INFO [trainer.py:765] (7/8) Epoch 3, batch 1600, train_loss[loss=4.158, NarTop10Accuracy=0.4883, over 7050.00 frames. ], tot_loss[loss=4.254, NarTop10Accuracy=0.4722, over 5947.29 frames. ], batch size: 23, lr: 2.19e-02
2024-08-06 14:59:45,952 INFO [trainer.py:765] (7/8) Epoch 3, batch 1700, train_loss[loss=4.121, NarTop10Accuracy=0.5042, over 6747.00 frames. ], tot_loss[loss=4.228, NarTop10Accuracy=0.4774, over 5950.28 frames. ], batch size: 14, lr: 2.18e-02
2024-08-06 15:00:12,498 INFO [trainer.py:765] (7/8) Epoch 3, batch 1800, train_loss[loss=3.952, NarTop10Accuracy=0.5365, over 6996.00 frames. ], tot_loss[loss=4.207, NarTop10Accuracy=0.4816, over 5996.67 frames. ], batch size: 22, lr: 2.17e-02
2024-08-06 15:00:38,949 INFO [trainer.py:765] (7/8) Epoch 3, batch 1900, train_loss[loss=4.696, NarTop10Accuracy=0.3814, over 5850.00 frames. ], tot_loss[loss=4.194, NarTop10Accuracy=0.4848, over 6034.34 frames. ], batch size: 51, lr: 2.16e-02
2024-08-06 15:01:04,606 INFO [trainer.py:765] (7/8) Epoch 3, batch 2000, train_loss[loss=4.539, NarTop10Accuracy=0.4137, over 6354.00 frames. ], tot_loss[loss=4.172, NarTop10Accuracy=0.4895, over 6011.68 frames. ], batch size: 50, lr: 2.15e-02
2024-08-06 15:01:29,898 INFO [trainer.py:765] (7/8) Epoch 3, batch 2100, train_loss[loss=3.732, NarTop10Accuracy=0.5744, over 4746.00 frames. ], tot_loss[loss=4.148, NarTop10Accuracy=0.494, over 5976.48 frames. ], batch size: 5, lr: 2.14e-02
2024-08-06 15:01:55,182 INFO [trainer.py:765] (7/8) Epoch 3, batch 2200, train_loss[loss=4.032, NarTop10Accuracy=0.5145, over 7209.00 frames. ], tot_loss[loss=4.115, NarTop10Accuracy=0.5009, over 6012.76 frames. ], batch size: 31, lr: 2.13e-02
2024-08-06 15:02:20,410 INFO [trainer.py:765] (7/8) Epoch 3, batch 2300, train_loss[loss=4.282, NarTop10Accuracy=0.4601, over 5613.00 frames. ], tot_loss[loss=4.128, NarTop10Accuracy=0.4985, over 6034.86 frames. ], batch size: 9, lr: 2.12e-02
2024-08-06 15:02:44,663 INFO [trainer.py:765] (7/8) Epoch 3, batch 2400, train_loss[loss=4.15, NarTop10Accuracy=0.485, over 5097.00 frames. ], tot_loss[loss=4.095, NarTop10Accuracy=0.5051, over 5767.93 frames. ], batch size: 7, lr: 2.11e-02
2024-08-06 15:03:08,234 INFO [trainer.py:765] (7/8) Epoch 3, batch 2500, train_loss[loss=3.706, NarTop10Accuracy=0.5856, over 5820.00 frames. ], tot_loss[loss=4.036, NarTop10Accuracy=0.5168, over 5483.00 frames. ], batch size: 8, lr: 2.10e-02
2024-08-06 15:03:28,174 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 15:04:28,130 INFO [trainer.py:765] (7/8) Epoch 4, batch 100, train_loss[loss=3.927, NarTop10Accuracy=0.5392, over 7353.00 frames. ], tot_loss[loss=4.026, NarTop10Accuracy=0.5193, over 2364.79 frames. ], batch size: 31, lr: 1.97e-02
2024-08-06 15:04:59,842 INFO [trainer.py:765] (7/8) Epoch 4, batch 200, train_loss[loss=3.931, NarTop10Accuracy=0.536, over 6729.00 frames. ], tot_loss[loss=4.001, NarTop10Accuracy=0.5249, over 3861.09 frames. ], batch size: 17, lr: 1.96e-02
2024-08-06 15:05:27,509 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 15:05:35,694 INFO [trainer.py:811] (7/8) Epoch 4, validation: loss=3.804, NarTop10Accuracy=0.5644, over 1905321.00 frames. 
2024-08-06 15:05:35,695 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 26785MB
2024-08-06 15:05:36,238 INFO [optim.py:386] (7/8) 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 15:05:43,889 INFO [trainer.py:765] (7/8) Epoch 4, batch 300, train_loss[loss=3.744, NarTop10Accuracy=0.5823, over 7143.00 frames. ], tot_loss[loss=3.996, NarTop10Accuracy=0.5255, over 4650.09 frames. ], batch size: 22, lr: 1.95e-02
2024-08-06 15:06:16,124 INFO [trainer.py:765] (7/8) Epoch 4, batch 400, train_loss[loss=3.818, NarTop10Accuracy=0.5576, over 5157.00 frames. ], tot_loss[loss=4.01, NarTop10Accuracy=0.5227, over 5098.02 frames. ], batch size: 7, lr: 1.94e-02
2024-08-06 15:06:46,473 INFO [trainer.py:765] (7/8) Epoch 4, batch 500, train_loss[loss=4.156, NarTop10Accuracy=0.49, over 6168.00 frames. ], tot_loss[loss=3.985, NarTop10Accuracy=0.5274, over 5371.29 frames. ], batch size: 11, lr: 1.93e-02
2024-08-06 15:07:23,817 INFO [trainer.py:765] (7/8) Epoch 4, batch 600, train_loss[loss=3.71, NarTop10Accuracy=0.5924, over 5796.00 frames. ], tot_loss[loss=3.984, NarTop10Accuracy=0.5282, over 5646.29 frames. ], batch size: 9, lr: 1.93e-02
2024-08-06 15:07:59,001 INFO [trainer.py:765] (7/8) Epoch 4, batch 700, train_loss[loss=4.104, NarTop10Accuracy=0.5056, over 5031.00 frames. ], tot_loss[loss=3.973, NarTop10Accuracy=0.5305, over 5721.10 frames. ], batch size: 6, lr: 1.92e-02
2024-08-06 15:08:32,429 INFO [trainer.py:765] (7/8) Epoch 4, batch 800, train_loss[loss=3.667, NarTop10Accuracy=0.5867, over 4251.00 frames. ], tot_loss[loss=3.963, NarTop10Accuracy=0.5322, over 5759.15 frames. ], batch size: 5, lr: 1.91e-02
2024-08-06 15:09:10,689 INFO [trainer.py:765] (7/8) Epoch 4, batch 900, train_loss[loss=3.577, NarTop10Accuracy=0.6132, over 6744.00 frames. ], tot_loss[loss=3.925, NarTop10Accuracy=0.5404, over 5779.11 frames. ], batch size: 14, lr: 1.90e-02
2024-08-06 15:09:46,076 INFO [trainer.py:765] (7/8) Epoch 4, batch 1000, train_loss[loss=3.641, NarTop10Accuracy=0.6031, over 6567.00 frames. ], tot_loss[loss=3.912, NarTop10Accuracy=0.5427, over 5892.94 frames. ], batch size: 14, lr: 1.89e-02
2024-08-06 15:10:18,139 INFO [trainer.py:765] (7/8) Epoch 4, batch 1100, train_loss[loss=3.795, NarTop10Accuracy=0.5656, over 6909.00 frames. ], tot_loss[loss=3.905, NarTop10Accuracy=0.5439, over 5923.38 frames. ], batch size: 17, lr: 1.88e-02
2024-08-06 15:10:55,075 INFO [trainer.py:765] (7/8) Epoch 4, batch 1200, train_loss[loss=4.307, NarTop10Accuracy=0.4696, over 7392.00 frames. ], tot_loss[loss=3.905, NarTop10Accuracy=0.5434, over 5922.54 frames. ], batch size: 32, lr: 1.88e-02
2024-08-06 15:11:32,074 INFO [trainer.py:765] (7/8) Epoch 4, batch 1300, train_loss[loss=3.558, NarTop10Accuracy=0.6132, over 5130.00 frames. ], tot_loss[loss=3.863, NarTop10Accuracy=0.5519, over 5989.00 frames. ], batch size: 6, lr: 1.87e-02
2024-08-06 15:12:05,688 INFO [trainer.py:765] (7/8) Epoch 4, batch 1400, train_loss[loss=3.725, NarTop10Accuracy=0.5846, over 6153.00 frames. ], tot_loss[loss=3.865, NarTop10Accuracy=0.5516, over 6009.16 frames. ], batch size: 11, lr: 1.86e-02
2024-08-06 15:12:33,695 INFO [trainer.py:765] (7/8) Epoch 4, batch 1500, train_loss[loss=3.871, NarTop10Accuracy=0.5519, over 6504.00 frames. ], tot_loss[loss=3.863, NarTop10Accuracy=0.5521, over 5951.62 frames. ], batch size: 50, lr: 1.85e-02
2024-08-06 15:13:01,510 INFO [trainer.py:765] (7/8) Epoch 4, batch 1600, train_loss[loss=3.777, NarTop10Accuracy=0.5704, over 6957.00 frames. ], tot_loss[loss=3.849, NarTop10Accuracy=0.5547, over 5933.40 frames. ], batch size: 22, lr: 1.84e-02
2024-08-06 15:13:28,132 INFO [trainer.py:765] (7/8) Epoch 4, batch 1700, train_loss[loss=3.74, NarTop10Accuracy=0.5869, over 6681.00 frames. ], tot_loss[loss=3.823, NarTop10Accuracy=0.56, over 5909.51 frames. ], batch size: 14, lr: 1.84e-02
2024-08-06 15:13:54,557 INFO [trainer.py:765] (7/8) Epoch 4, batch 1800, train_loss[loss=3.84, NarTop10Accuracy=0.5541, over 7113.00 frames. ], tot_loss[loss=3.828, NarTop10Accuracy=0.5589, over 5983.18 frames. ], batch size: 22, lr: 1.83e-02
2024-08-06 15:14:20,998 INFO [trainer.py:765] (7/8) Epoch 4, batch 1900, train_loss[loss=3.893, NarTop10Accuracy=0.5435, over 5700.00 frames. ], tot_loss[loss=3.851, NarTop10Accuracy=0.5542, over 6024.03 frames. ], batch size: 50, lr: 1.82e-02
2024-08-06 15:14:46,671 INFO [trainer.py:765] (7/8) Epoch 4, batch 2000, train_loss[loss=3.794, NarTop10Accuracy=0.5671, over 6126.00 frames. ], tot_loss[loss=3.826, NarTop10Accuracy=0.5592, over 6001.90 frames. ], batch size: 50, lr: 1.81e-02
2024-08-06 15:15:11,859 INFO [trainer.py:765] (7/8) Epoch 4, batch 2100, train_loss[loss=3.56, NarTop10Accuracy=0.6139, over 4893.00 frames. ], tot_loss[loss=3.809, NarTop10Accuracy=0.563, over 5971.42 frames. ], batch size: 5, lr: 1.81e-02
2024-08-06 15:15:37,089 INFO [trainer.py:765] (7/8) Epoch 4, batch 2200, train_loss[loss=3.638, NarTop10Accuracy=0.6055, over 7227.00 frames. ], tot_loss[loss=3.805, NarTop10Accuracy=0.5635, over 6013.24 frames. ], batch size: 31, lr: 1.80e-02
2024-08-06 15:15:55,089 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 15:16:03,243 INFO [trainer.py:811] (7/8) Epoch 4, validation: loss=3.665, NarTop10Accuracy=0.5912, over 1905321.00 frames. 
2024-08-06 15:16:03,243 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 26785MB
2024-08-06 15:16:03,741 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 4, batch 2300, train_loss[loss=3.668, NarTop10Accuracy=0.5994, over 5550.00 frames. ], tot_loss[loss=3.82, NarTop10Accuracy=0.5607, over 6027.18 frames. ], batch size: 9, lr: 1.79e-02
2024-08-06 15:16:34,841 INFO [trainer.py:765] (7/8) Epoch 4, batch 2400, train_loss[loss=3.532, NarTop10Accuracy=0.621, over 5166.00 frames. ], tot_loss[loss=3.787, NarTop10Accuracy=0.5676, over 5772.52 frames. ], batch size: 7, lr: 1.79e-02
2024-08-06 15:16:58,535 INFO [trainer.py:765] (7/8) Epoch 4, batch 2500, train_loss[loss=3.633, NarTop10Accuracy=0.6096, over 5097.00 frames. ], tot_loss[loss=3.773, NarTop10Accuracy=0.5702, over 5474.48 frames. ], batch size: 7, lr: 1.78e-02
2024-08-06 15:17:18,638 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 15:18:24,100 INFO [trainer.py:765] (7/8) Epoch 5, batch 100, train_loss[loss=3.498, NarTop10Accuracy=0.6302, over 7143.00 frames. ], tot_loss[loss=3.771, NarTop10Accuracy=0.5701, over 2363.87 frames. ], batch size: 31, lr: 1.66e-02
2024-08-06 15:18:59,675 INFO [trainer.py:765] (7/8) Epoch 5, batch 200, train_loss[loss=4.205, NarTop10Accuracy=0.4892, over 6942.00 frames. ], tot_loss[loss=3.758, NarTop10Accuracy=0.5735, over 3869.10 frames. ], batch size: 17, lr: 1.65e-02
2024-08-06 15:19:32,887 INFO [trainer.py:765] (7/8) Epoch 5, batch 300, train_loss[loss=3.948, NarTop10Accuracy=0.5282, over 7209.00 frames. ], tot_loss[loss=3.735, NarTop10Accuracy=0.5779, over 4659.35 frames. ], batch size: 22, lr: 1.65e-02
2024-08-06 15:20:01,655 INFO [trainer.py:765] (7/8) Epoch 5, batch 400, train_loss[loss=3.558, NarTop10Accuracy=0.6101, over 5094.00 frames. ], tot_loss[loss=3.726, NarTop10Accuracy=0.5794, over 5112.63 frames. ], batch size: 7, lr: 1.64e-02
2024-08-06 15:20:38,298 INFO [trainer.py:765] (7/8) Epoch 5, batch 500, train_loss[loss=3.993, NarTop10Accuracy=0.5197, over 6051.00 frames. ], tot_loss[loss=3.73, NarTop10Accuracy=0.578, over 5376.42 frames. ], batch size: 11, lr: 1.63e-02
2024-08-06 15:21:13,710 INFO [trainer.py:765] (7/8) Epoch 5, batch 600, train_loss[loss=3.73, NarTop10Accuracy=0.5663, over 5745.00 frames. ], tot_loss[loss=3.722, NarTop10Accuracy=0.5796, over 5653.77 frames. ], batch size: 9, lr: 1.63e-02
2024-08-06 15:21:45,881 INFO [trainer.py:765] (7/8) Epoch 5, batch 700, train_loss[loss=3.599, NarTop10Accuracy=0.6105, over 5127.00 frames. ], tot_loss[loss=3.721, NarTop10Accuracy=0.5806, over 5724.83 frames. ], batch size: 6, lr: 1.62e-02
2024-08-06 15:22:24,498 INFO [trainer.py:765] (7/8) Epoch 5, batch 800, train_loss[loss=3.929, NarTop10Accuracy=0.5297, over 4992.00 frames. ], tot_loss[loss=3.705, NarTop10Accuracy=0.5838, over 5786.73 frames. ], batch size: 6, lr: 1.62e-02
2024-08-06 15:22:56,783 INFO [trainer.py:765] (7/8) Epoch 5, batch 900, train_loss[loss=3.708, NarTop10Accuracy=0.5849, over 6663.00 frames. ], tot_loss[loss=3.694, NarTop10Accuracy=0.5859, over 5810.10 frames. ], batch size: 14, lr: 1.61e-02
2024-08-06 15:23:31,914 INFO [trainer.py:765] (7/8) Epoch 5, batch 1000, train_loss[loss=3.579, NarTop10Accuracy=0.6171, over 6246.00 frames. ], tot_loss[loss=3.685, NarTop10Accuracy=0.5878, over 5911.18 frames. ], batch size: 13, lr: 1.60e-02
2024-08-06 15:24:09,571 INFO [trainer.py:765] (7/8) Epoch 5, batch 1100, train_loss[loss=3.513, NarTop10Accuracy=0.6277, over 6876.00 frames. ], tot_loss[loss=3.677, NarTop10Accuracy=0.5894, over 5946.48 frames. ], batch size: 17, lr: 1.60e-02
2024-08-06 15:24:44,528 INFO [trainer.py:765] (7/8) Epoch 5, batch 1200, train_loss[loss=3.497, NarTop10Accuracy=0.6227, over 7305.00 frames. ], tot_loss[loss=3.673, NarTop10Accuracy=0.59, over 5950.72 frames. ], batch size: 31, lr: 1.59e-02
2024-08-06 15:25:19,379 INFO [trainer.py:765] (7/8) Epoch 5, batch 1300, train_loss[loss=3.813, NarTop10Accuracy=0.556, over 4305.00 frames. ], tot_loss[loss=3.658, NarTop10Accuracy=0.5931, over 6004.84 frames. ], batch size: 5, lr: 1.59e-02
2024-08-06 15:25:51,694 INFO [trainer.py:765] (7/8) Epoch 5, batch 1400, train_loss[loss=3.721, NarTop10Accuracy=0.5731, over 6033.00 frames. ], tot_loss[loss=3.667, NarTop10Accuracy=0.5913, over 6019.79 frames. ], batch size: 11, lr: 1.58e-02
2024-08-06 15:26:26,195 INFO [trainer.py:765] (7/8) Epoch 5, batch 1500, train_loss[loss=3.712, NarTop10Accuracy=0.5908, over 6423.00 frames. ], tot_loss[loss=3.663, NarTop10Accuracy=0.5922, over 5940.01 frames. ], batch size: 50, lr: 1.58e-02
2024-08-06 15:26:54,130 INFO [trainer.py:765] (7/8) Epoch 5, batch 1600, train_loss[loss=3.525, NarTop10Accuracy=0.6237, over 7053.00 frames. ], tot_loss[loss=3.676, NarTop10Accuracy=0.59, over 5924.97 frames. ], batch size: 22, lr: 1.57e-02
2024-08-06 15:27:19,603 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 15:27:27,821 INFO [trainer.py:811] (7/8) Epoch 5, validation: loss=3.552, NarTop10Accuracy=0.6147, over 1905321.00 frames. 
2024-08-06 15:27:27,822 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27149MB
2024-08-06 15:27:28,341 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 5, batch 1700, train_loss[loss=3.711, NarTop10Accuracy=0.5779, over 6516.00 frames. ], tot_loss[loss=3.669, NarTop10Accuracy=0.5913, over 5914.84 frames. ], batch size: 14, lr: 1.56e-02
2024-08-06 15:27:55,653 INFO [trainer.py:765] (7/8) Epoch 5, batch 1800, train_loss[loss=3.85, NarTop10Accuracy=0.5517, over 6945.00 frames. ], tot_loss[loss=3.665, NarTop10Accuracy=0.5919, over 5985.80 frames. ], batch size: 22, lr: 1.56e-02
2024-08-06 15:28:22,172 INFO [trainer.py:765] (7/8) Epoch 5, batch 1900, train_loss[loss=3.861, NarTop10Accuracy=0.5582, over 6030.00 frames. ], tot_loss[loss=3.675, NarTop10Accuracy=0.5901, over 6035.88 frames. ], batch size: 53, lr: 1.55e-02
2024-08-06 15:28:47,893 INFO [trainer.py:765] (7/8) Epoch 5, batch 2000, train_loss[loss=3.679, NarTop10Accuracy=0.593, over 6087.00 frames. ], tot_loss[loss=3.67, NarTop10Accuracy=0.5911, over 6020.19 frames. ], batch size: 50, lr: 1.55e-02
2024-08-06 15:29:13,770 INFO [trainer.py:765] (7/8) Epoch 5, batch 2100, train_loss[loss=3.382, NarTop10Accuracy=0.6575, over 4839.00 frames. ], tot_loss[loss=3.688, NarTop10Accuracy=0.5874, over 6001.31 frames. ], batch size: 5, lr: 1.54e-02
2024-08-06 15:29:39,177 INFO [trainer.py:765] (7/8) Epoch 5, batch 2200, train_loss[loss=4.039, NarTop10Accuracy=0.5124, over 7101.00 frames. ], tot_loss[loss=3.664, NarTop10Accuracy=0.5923, over 6013.35 frames. ], batch size: 31, lr: 1.54e-02
2024-08-06 15:30:04,430 INFO [trainer.py:765] (7/8) Epoch 5, batch 2300, train_loss[loss=3.526, NarTop10Accuracy=0.6265, over 5727.00 frames. ], tot_loss[loss=3.675, NarTop10Accuracy=0.5902, over 6032.12 frames. ], batch size: 9, lr: 1.53e-02
2024-08-06 15:30:28,862 INFO [trainer.py:765] (7/8) Epoch 5, batch 2400, train_loss[loss=3.42, NarTop10Accuracy=0.647, over 5184.00 frames. ], tot_loss[loss=3.646, NarTop10Accuracy=0.5955, over 5774.66 frames. ], batch size: 7, lr: 1.53e-02
2024-08-06 15:30:52,503 INFO [trainer.py:765] (7/8) Epoch 5, batch 2500, train_loss[loss=3.31, NarTop10Accuracy=0.665, over 5127.00 frames. ], tot_loss[loss=3.604, NarTop10Accuracy=0.6039, over 5477.97 frames. ], batch size: 7, lr: 1.52e-02
2024-08-06 15:31:12,586 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 15:32:14,415 INFO [trainer.py:765] (7/8) Epoch 6, batch 100, train_loss[loss=3.568, NarTop10Accuracy=0.6134, over 7119.00 frames. ], tot_loss[loss=3.627, NarTop10Accuracy=0.6001, over 2372.64 frames. ], batch size: 31, lr: 1.42e-02
2024-08-06 15:32:46,016 INFO [trainer.py:765] (7/8) Epoch 6, batch 200, train_loss[loss=4.041, NarTop10Accuracy=0.5128, over 6678.00 frames. ], tot_loss[loss=3.61, NarTop10Accuracy=0.6025, over 3871.57 frames. ], batch size: 17, lr: 1.42e-02
2024-08-06 15:33:21,243 INFO [trainer.py:765] (7/8) Epoch 6, batch 300, train_loss[loss=3.499, NarTop10Accuracy=0.6288, over 6948.00 frames. ], tot_loss[loss=3.605, NarTop10Accuracy=0.6037, over 4664.07 frames. ], batch size: 22, lr: 1.41e-02
2024-08-06 15:33:56,035 INFO [trainer.py:765] (7/8) Epoch 6, batch 400, train_loss[loss=3.514, NarTop10Accuracy=0.627, over 5052.00 frames. ], tot_loss[loss=3.589, NarTop10Accuracy=0.6068, over 5111.94 frames. ], batch size: 7, lr: 1.41e-02
2024-08-06 15:34:26,759 INFO [trainer.py:765] (7/8) Epoch 6, batch 500, train_loss[loss=3.285, NarTop10Accuracy=0.6645, over 6138.00 frames. ], tot_loss[loss=3.58, NarTop10Accuracy=0.6092, over 5386.00 frames. ], batch size: 11, lr: 1.40e-02
2024-08-06 15:35:01,458 INFO [trainer.py:765] (7/8) Epoch 6, batch 600, train_loss[loss=3.228, NarTop10Accuracy=0.6753, over 5658.00 frames. ], tot_loss[loss=3.583, NarTop10Accuracy=0.6088, over 5656.36 frames. ], batch size: 9, lr: 1.40e-02
2024-08-06 15:35:32,734 INFO [trainer.py:765] (7/8) Epoch 6, batch 700, train_loss[loss=3.307, NarTop10Accuracy=0.6699, over 4305.00 frames. ], tot_loss[loss=3.583, NarTop10Accuracy=0.6089, over 5726.69 frames. ], batch size: 5, lr: 1.39e-02
2024-08-06 15:36:06,844 INFO [trainer.py:765] (7/8) Epoch 6, batch 800, train_loss[loss=3.837, NarTop10Accuracy=0.5524, over 5184.00 frames. ], tot_loss[loss=3.588, NarTop10Accuracy=0.6076, over 5772.62 frames. ], batch size: 6, lr: 1.39e-02
2024-08-06 15:36:40,385 INFO [trainer.py:765] (7/8) Epoch 6, batch 900, train_loss[loss=3.964, NarTop10Accuracy=0.5266, over 6597.00 frames. ], tot_loss[loss=3.578, NarTop10Accuracy=0.6095, over 5809.53 frames. ], batch size: 14, lr: 1.38e-02
2024-08-06 15:37:15,272 INFO [trainer.py:765] (7/8) Epoch 6, batch 1000, train_loss[loss=3.386, NarTop10Accuracy=0.6538, over 6702.00 frames. ], tot_loss[loss=3.592, NarTop10Accuracy=0.6066, over 5913.69 frames. ], batch size: 14, lr: 1.38e-02
2024-08-06 15:37:50,508 INFO [trainer.py:765] (7/8) Epoch 6, batch 1100, train_loss[loss=3.328, NarTop10Accuracy=0.6662, over 6852.00 frames. ], tot_loss[loss=3.59, NarTop10Accuracy=0.6074, over 5941.16 frames. ], batch size: 17, lr: 1.38e-02
2024-08-06 15:37:55,829 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 15:38:04,436 INFO [trainer.py:811] (7/8) Epoch 6, validation: loss=3.421, NarTop10Accuracy=0.6418, over 1905321.00 frames. 
2024-08-06 15:38:04,437 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27149MB
2024-08-06 15:38:04,965 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 6, batch 1200, train_loss[loss=3.387, NarTop10Accuracy=0.6469, over 7329.00 frames. ], tot_loss[loss=3.579, NarTop10Accuracy=0.6095, over 5935.24 frames. ], batch size: 31, lr: 1.37e-02
2024-08-06 15:39:08,242 INFO [trainer.py:765] (7/8) Epoch 6, batch 1300, train_loss[loss=3.373, NarTop10Accuracy=0.6515, over 5031.00 frames. ], tot_loss[loss=3.576, NarTop10Accuracy=0.6102, over 6000.52 frames. ], batch size: 6, lr: 1.37e-02
2024-08-06 15:39:44,069 INFO [trainer.py:765] (7/8) Epoch 6, batch 1400, train_loss[loss=3.309, NarTop10Accuracy=0.6549, over 6102.00 frames. ], tot_loss[loss=3.571, NarTop10Accuracy=0.6108, over 6034.41 frames. ], batch size: 11, lr: 1.36e-02
2024-08-06 15:40:15,383 INFO [trainer.py:765] (7/8) Epoch 6, batch 1500, train_loss[loss=3.989, NarTop10Accuracy=0.5371, over 6018.00 frames. ], tot_loss[loss=3.568, NarTop10Accuracy=0.6114, over 5967.98 frames. ], batch size: 50, lr: 1.36e-02
2024-08-06 15:40:43,105 INFO [trainer.py:765] (7/8) Epoch 6, batch 1600, train_loss[loss=3.549, NarTop10Accuracy=0.6201, over 7179.00 frames. ], tot_loss[loss=3.57, NarTop10Accuracy=0.6109, over 5954.16 frames. ], batch size: 22, lr: 1.35e-02
2024-08-06 15:41:09,788 INFO [trainer.py:765] (7/8) Epoch 6, batch 1700, train_loss[loss=3.55, NarTop10Accuracy=0.6164, over 6708.00 frames. ], tot_loss[loss=3.555, NarTop10Accuracy=0.6142, over 5940.03 frames. ], batch size: 14, lr: 1.35e-02
2024-08-06 15:41:36,317 INFO [trainer.py:765] (7/8) Epoch 6, batch 1800, train_loss[loss=3.513, NarTop10Accuracy=0.6264, over 7212.00 frames. ], tot_loss[loss=3.561, NarTop10Accuracy=0.6129, over 5984.40 frames. ], batch size: 23, lr: 1.35e-02
2024-08-06 15:42:02,720 INFO [trainer.py:765] (7/8) Epoch 6, batch 1900, train_loss[loss=3.905, NarTop10Accuracy=0.5398, over 6222.00 frames. ], tot_loss[loss=3.581, NarTop10Accuracy=0.609, over 6019.04 frames. ], batch size: 50, lr: 1.34e-02
2024-08-06 15:42:28,319 INFO [trainer.py:765] (7/8) Epoch 6, batch 2000, train_loss[loss=3.454, NarTop10Accuracy=0.6348, over 5904.00 frames. ], tot_loss[loss=3.574, NarTop10Accuracy=0.6103, over 6001.97 frames. ], batch size: 51, lr: 1.34e-02
2024-08-06 15:42:53,668 INFO [trainer.py:765] (7/8) Epoch 6, batch 2100, train_loss[loss=3.06, NarTop10Accuracy=0.7183, over 3843.00 frames. ], tot_loss[loss=3.561, NarTop10Accuracy=0.6125, over 5966.34 frames. ], batch size: 4, lr: 1.33e-02
2024-08-06 15:43:18,977 INFO [trainer.py:765] (7/8) Epoch 6, batch 2200, train_loss[loss=3.804, NarTop10Accuracy=0.5603, over 7215.00 frames. ], tot_loss[loss=3.563, NarTop10Accuracy=0.6123, over 6009.95 frames. ], batch size: 31, lr: 1.33e-02
2024-08-06 15:43:44,106 INFO [trainer.py:765] (7/8) Epoch 6, batch 2300, train_loss[loss=3.431, NarTop10Accuracy=0.6364, over 5754.00 frames. ], tot_loss[loss=3.56, NarTop10Accuracy=0.6132, over 6028.19 frames. ], batch size: 9, lr: 1.33e-02
2024-08-06 15:44:08,620 INFO [trainer.py:765] (7/8) Epoch 6, batch 2400, train_loss[loss=3.24, NarTop10Accuracy=0.6702, over 5091.00 frames. ], tot_loss[loss=3.538, NarTop10Accuracy=0.6179, over 5776.22 frames. ], batch size: 7, lr: 1.32e-02
2024-08-06 15:44:32,132 INFO [trainer.py:765] (7/8) Epoch 6, batch 2500, train_loss[loss=3.33, NarTop10Accuracy=0.6548, over 5292.00 frames. ], tot_loss[loss=3.522, NarTop10Accuracy=0.6208, over 5482.82 frames. ], batch size: 7, lr: 1.32e-02
2024-08-06 15:44:51,850 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 15:45:58,043 INFO [trainer.py:765] (7/8) Epoch 7, batch 100, train_loss[loss=3.321, NarTop10Accuracy=0.66, over 7185.00 frames. ], tot_loss[loss=3.532, NarTop10Accuracy=0.6184, over 2353.99 frames. ], batch size: 32, lr: 1.24e-02
2024-08-06 15:46:33,614 INFO [trainer.py:765] (7/8) Epoch 7, batch 200, train_loss[loss=3.422, NarTop10Accuracy=0.6411, over 6807.00 frames. ], tot_loss[loss=3.522, NarTop10Accuracy=0.6212, over 3841.06 frames. ], batch size: 17, lr: 1.23e-02
2024-08-06 15:47:03,246 INFO [trainer.py:765] (7/8) Epoch 7, batch 300, train_loss[loss=3.86, NarTop10Accuracy=0.5528, over 7176.00 frames. ], tot_loss[loss=3.54, NarTop10Accuracy=0.6177, over 4638.91 frames. ], batch size: 22, lr: 1.23e-02
2024-08-06 15:47:34,495 INFO [trainer.py:765] (7/8) Epoch 7, batch 400, train_loss[loss=3.502, NarTop10Accuracy=0.6179, over 5091.00 frames. ], tot_loss[loss=3.528, NarTop10Accuracy=0.6198, over 5095.27 frames. ], batch size: 7, lr: 1.23e-02
2024-08-06 15:48:13,730 INFO [trainer.py:765] (7/8) Epoch 7, batch 500, train_loss[loss=3.663, NarTop10Accuracy=0.591, over 6018.00 frames. ], tot_loss[loss=3.523, NarTop10Accuracy=0.6208, over 5362.79 frames. ], batch size: 11, lr: 1.22e-02
2024-08-06 15:48:26,369 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 15:48:34,533 INFO [trainer.py:811] (7/8) Epoch 7, validation: loss=3.326, NarTop10Accuracy=0.6612, over 1905321.00 frames. 
2024-08-06 15:48:34,534 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27149MB
2024-08-06 15:48:35,079 INFO [optim.py:386] (7/8) 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 15:48:52,720 INFO [trainer.py:765] (7/8) Epoch 7, batch 600, train_loss[loss=3.251, NarTop10Accuracy=0.6802, over 5721.00 frames. ], tot_loss[loss=3.526, NarTop10Accuracy=0.6202, over 5633.23 frames. ], batch size: 9, lr: 1.22e-02
2024-08-06 15:49:24,913 INFO [trainer.py:765] (7/8) Epoch 7, batch 700, train_loss[loss=3.846, NarTop10Accuracy=0.5487, over 5019.00 frames. ], tot_loss[loss=3.522, NarTop10Accuracy=0.6212, over 5688.11 frames. ], batch size: 6, lr: 1.21e-02
2024-08-06 15:50:04,381 INFO [trainer.py:765] (7/8) Epoch 7, batch 800, train_loss[loss=3.151, NarTop10Accuracy=0.6989, over 5070.00 frames. ], tot_loss[loss=3.504, NarTop10Accuracy=0.6249, over 5760.99 frames. ], batch size: 6, lr: 1.21e-02
2024-08-06 15:50:34,549 INFO [trainer.py:765] (7/8) Epoch 7, batch 900, train_loss[loss=3.324, NarTop10Accuracy=0.6551, over 6717.00 frames. ], tot_loss[loss=3.495, NarTop10Accuracy=0.6267, over 5788.01 frames. ], batch size: 14, lr: 1.21e-02
2024-08-06 15:51:07,156 INFO [trainer.py:765] (7/8) Epoch 7, batch 1000, train_loss[loss=3.274, NarTop10Accuracy=0.6777, over 6618.00 frames. ], tot_loss[loss=3.491, NarTop10Accuracy=0.6274, over 5888.15 frames. ], batch size: 14, lr: 1.20e-02
2024-08-06 15:51:51,758 INFO [trainer.py:765] (7/8) Epoch 7, batch 1100, train_loss[loss=3.288, NarTop10Accuracy=0.6714, over 6837.00 frames. ], tot_loss[loss=3.494, NarTop10Accuracy=0.6265, over 5937.00 frames. ], batch size: 17, lr: 1.20e-02
2024-08-06 15:52:22,700 INFO [trainer.py:765] (7/8) Epoch 7, batch 1200, train_loss[loss=3.315, NarTop10Accuracy=0.6598, over 7314.00 frames. ], tot_loss[loss=3.488, NarTop10Accuracy=0.6276, over 5923.06 frames. ], batch size: 31, lr: 1.20e-02
2024-08-06 15:52:52,008 INFO [trainer.py:765] (7/8) Epoch 7, batch 1300, train_loss[loss=3.499, NarTop10Accuracy=0.6276, over 4890.00 frames. ], tot_loss[loss=3.491, NarTop10Accuracy=0.6273, over 5993.87 frames. ], batch size: 6, lr: 1.19e-02
2024-08-06 15:53:33,842 INFO [trainer.py:765] (7/8) Epoch 7, batch 1400, train_loss[loss=3.302, NarTop10Accuracy=0.6708, over 6087.00 frames. ], tot_loss[loss=3.503, NarTop10Accuracy=0.6244, over 6013.93 frames. ], batch size: 11, lr: 1.19e-02
2024-08-06 15:54:04,600 INFO [trainer.py:765] (7/8) Epoch 7, batch 1500, train_loss[loss=3.789, NarTop10Accuracy=0.5631, over 6171.00 frames. ], tot_loss[loss=3.484, NarTop10Accuracy=0.6286, over 5951.81 frames. ], batch size: 50, lr: 1.19e-02
2024-08-06 15:54:32,385 INFO [trainer.py:765] (7/8) Epoch 7, batch 1600, train_loss[loss=3.594, NarTop10Accuracy=0.6044, over 7032.00 frames. ], tot_loss[loss=3.485, NarTop10Accuracy=0.6282, over 5920.57 frames. ], batch size: 22, lr: 1.19e-02
2024-08-06 15:54:59,055 INFO [trainer.py:765] (7/8) Epoch 7, batch 1700, train_loss[loss=3.656, NarTop10Accuracy=0.5901, over 6252.00 frames. ], tot_loss[loss=3.504, NarTop10Accuracy=0.6242, over 5920.10 frames. ], batch size: 13, lr: 1.18e-02
2024-08-06 15:55:25,513 INFO [trainer.py:765] (7/8) Epoch 7, batch 1800, train_loss[loss=4.025, NarTop10Accuracy=0.5231, over 7176.00 frames. ], tot_loss[loss=3.497, NarTop10Accuracy=0.6257, over 5983.61 frames. ], batch size: 22, lr: 1.18e-02
2024-08-06 15:55:52,083 INFO [trainer.py:765] (7/8) Epoch 7, batch 1900, train_loss[loss=3.351, NarTop10Accuracy=0.6528, over 6186.00 frames. ], tot_loss[loss=3.511, NarTop10Accuracy=0.6229, over 6027.70 frames. ], batch size: 54, lr: 1.18e-02
2024-08-06 15:56:17,592 INFO [trainer.py:765] (7/8) Epoch 7, batch 2000, train_loss[loss=3.789, NarTop10Accuracy=0.5633, over 6033.00 frames. ], tot_loss[loss=3.506, NarTop10Accuracy=0.624, over 5990.23 frames. ], batch size: 50, lr: 1.17e-02
2024-08-06 15:56:42,856 INFO [trainer.py:765] (7/8) Epoch 7, batch 2100, train_loss[loss=3.704, NarTop10Accuracy=0.5812, over 4857.00 frames. ], tot_loss[loss=3.488, NarTop10Accuracy=0.6278, over 5974.93 frames. ], batch size: 5, lr: 1.17e-02
2024-08-06 15:57:08,079 INFO [trainer.py:765] (7/8) Epoch 7, batch 2200, train_loss[loss=3.494, NarTop10Accuracy=0.6249, over 7134.00 frames. ], tot_loss[loss=3.505, NarTop10Accuracy=0.6239, over 6013.48 frames. ], batch size: 31, lr: 1.17e-02
2024-08-06 15:57:33,178 INFO [trainer.py:765] (7/8) Epoch 7, batch 2300, train_loss[loss=3.22, NarTop10Accuracy=0.6858, over 5652.00 frames. ], tot_loss[loss=3.51, NarTop10Accuracy=0.6237, over 6021.57 frames. ], batch size: 9, lr: 1.16e-02
2024-08-06 15:57:57,619 INFO [trainer.py:765] (7/8) Epoch 7, batch 2400, train_loss[loss=3.213, NarTop10Accuracy=0.6848, over 5154.00 frames. ], tot_loss[loss=3.496, NarTop10Accuracy=0.6262, over 5785.10 frames. ], batch size: 7, lr: 1.16e-02
2024-08-06 15:58:21,088 INFO [trainer.py:765] (7/8) Epoch 7, batch 2500, train_loss[loss=3.588, NarTop10Accuracy=0.5998, over 5133.00 frames. ], tot_loss[loss=3.466, NarTop10Accuracy=0.6317, over 5492.87 frames. ], batch size: 7, lr: 1.16e-02
2024-08-06 15:58:31,565 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 15:58:39,769 INFO [trainer.py:811] (7/8) Epoch 7, validation: loss=3.381, NarTop10Accuracy=0.6488, over 1905321.00 frames. 
2024-08-06 15:58:39,770 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27149MB
2024-08-06 15:58:40,221 INFO [optim.py:386] (7/8) 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 15:58:48,984 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 15:59:52,876 INFO [trainer.py:765] (7/8) Epoch 8, batch 100, train_loss[loss=3.686, NarTop10Accuracy=0.5803, over 7323.00 frames. ], tot_loss[loss=3.464, NarTop10Accuracy=0.6329, over 2369.09 frames. ], batch size: 31, lr: 1.09e-02
2024-08-06 16:00:27,881 INFO [trainer.py:765] (7/8) Epoch 8, batch 200, train_loss[loss=3.377, NarTop10Accuracy=0.6479, over 6741.00 frames. ], tot_loss[loss=3.486, NarTop10Accuracy=0.6284, over 3881.24 frames. ], batch size: 17, lr: 1.09e-02
2024-08-06 16:00:58,563 INFO [trainer.py:765] (7/8) Epoch 8, batch 300, train_loss[loss=3.326, NarTop10Accuracy=0.6521, over 7080.00 frames. ], tot_loss[loss=3.469, NarTop10Accuracy=0.6318, over 4679.84 frames. ], batch size: 22, lr: 1.08e-02
2024-08-06 16:01:29,760 INFO [trainer.py:765] (7/8) Epoch 8, batch 400, train_loss[loss=3.73, NarTop10Accuracy=0.5732, over 5235.00 frames. ], tot_loss[loss=3.471, NarTop10Accuracy=0.631, over 5100.91 frames. ], batch size: 7, lr: 1.08e-02
2024-08-06 16:02:04,066 INFO [trainer.py:765] (7/8) Epoch 8, batch 500, train_loss[loss=3.78, NarTop10Accuracy=0.5647, over 6093.00 frames. ], tot_loss[loss=3.448, NarTop10Accuracy=0.6356, over 5393.60 frames. ], batch size: 11, lr: 1.08e-02
2024-08-06 16:02:41,836 INFO [trainer.py:765] (7/8) Epoch 8, batch 600, train_loss[loss=3.266, NarTop10Accuracy=0.6759, over 5739.00 frames. ], tot_loss[loss=3.467, NarTop10Accuracy=0.6319, over 5660.96 frames. ], batch size: 9, lr: 1.08e-02
2024-08-06 16:03:11,500 INFO [trainer.py:765] (7/8) Epoch 8, batch 700, train_loss[loss=3.927, NarTop10Accuracy=0.5281, over 4344.00 frames. ], tot_loss[loss=3.473, NarTop10Accuracy=0.6304, over 5713.02 frames. ], batch size: 5, lr: 1.07e-02
2024-08-06 16:03:50,084 INFO [trainer.py:765] (7/8) Epoch 8, batch 800, train_loss[loss=3.432, NarTop10Accuracy=0.6358, over 4272.00 frames. ], tot_loss[loss=3.467, NarTop10Accuracy=0.632, over 5768.11 frames. ], batch size: 5, lr: 1.07e-02
2024-08-06 16:04:27,588 INFO [trainer.py:765] (7/8) Epoch 8, batch 900, train_loss[loss=3.261, NarTop10Accuracy=0.6804, over 6609.00 frames. ], tot_loss[loss=3.448, NarTop10Accuracy=0.636, over 5795.25 frames. ], batch size: 14, lr: 1.07e-02
2024-08-06 16:04:57,466 INFO [trainer.py:765] (7/8) Epoch 8, batch 1000, train_loss[loss=3.65, NarTop10Accuracy=0.5951, over 6159.00 frames. ], tot_loss[loss=3.44, NarTop10Accuracy=0.6375, over 5900.88 frames. ], batch size: 13, lr: 1.07e-02
2024-08-06 16:05:37,294 INFO [trainer.py:765] (7/8) Epoch 8, batch 1100, train_loss[loss=3.718, NarTop10Accuracy=0.5864, over 6846.00 frames. ], tot_loss[loss=3.431, NarTop10Accuracy=0.6393, over 5927.97 frames. ], batch size: 17, lr: 1.06e-02
2024-08-06 16:06:15,859 INFO [trainer.py:765] (7/8) Epoch 8, batch 1200, train_loss[loss=3.401, NarTop10Accuracy=0.6378, over 7182.00 frames. ], tot_loss[loss=3.442, NarTop10Accuracy=0.6366, over 5926.39 frames. ], batch size: 32, lr: 1.06e-02
2024-08-06 16:06:45,187 INFO [trainer.py:765] (7/8) Epoch 8, batch 1300, train_loss[loss=3.212, NarTop10Accuracy=0.6889, over 4365.00 frames. ], tot_loss[loss=3.436, NarTop10Accuracy=0.638, over 5995.79 frames. ], batch size: 5, lr: 1.06e-02
2024-08-06 16:07:24,235 INFO [trainer.py:765] (7/8) Epoch 8, batch 1400, train_loss[loss=3.489, NarTop10Accuracy=0.6348, over 6108.00 frames. ], tot_loss[loss=3.439, NarTop10Accuracy=0.6381, over 6023.02 frames. ], batch size: 11, lr: 1.05e-02
2024-08-06 16:07:52,169 INFO [trainer.py:765] (7/8) Epoch 8, batch 1500, train_loss[loss=3.419, NarTop10Accuracy=0.6395, over 6042.00 frames. ], tot_loss[loss=3.425, NarTop10Accuracy=0.6407, over 5957.26 frames. ], batch size: 50, lr: 1.05e-02
2024-08-06 16:08:19,948 INFO [trainer.py:765] (7/8) Epoch 8, batch 1600, train_loss[loss=3.265, NarTop10Accuracy=0.6752, over 7191.00 frames. ], tot_loss[loss=3.426, NarTop10Accuracy=0.6406, over 5943.25 frames. ], batch size: 22, lr: 1.05e-02
2024-08-06 16:08:46,617 INFO [trainer.py:765] (7/8) Epoch 8, batch 1700, train_loss[loss=3.397, NarTop10Accuracy=0.646, over 6687.00 frames. ], tot_loss[loss=3.425, NarTop10Accuracy=0.6407, over 5934.78 frames. ], batch size: 14, lr: 1.05e-02
2024-08-06 16:09:13,106 INFO [trainer.py:765] (7/8) Epoch 8, batch 1800, train_loss[loss=3.262, NarTop10Accuracy=0.6711, over 7164.00 frames. ], tot_loss[loss=3.422, NarTop10Accuracy=0.6412, over 5994.72 frames. ], batch size: 22, lr: 1.04e-02
2024-08-06 16:09:39,636 INFO [trainer.py:765] (7/8) Epoch 8, batch 1900, train_loss[loss=3.828, NarTop10Accuracy=0.5578, over 6165.00 frames. ], tot_loss[loss=3.409, NarTop10Accuracy=0.6439, over 6023.91 frames. ], batch size: 52, lr: 1.04e-02
2024-08-06 16:09:56,940 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 16:10:04,970 INFO [trainer.py:811] (7/8) Epoch 8, validation: loss=3.282, NarTop10Accuracy=0.6699, over 1905321.00 frames. 
2024-08-06 16:10:04,970 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27199MB
2024-08-06 16:10:05,470 INFO [optim.py:386] (7/8) 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 16:10:13,204 INFO [trainer.py:765] (7/8) Epoch 8, batch 2000, train_loss[loss=3.973, NarTop10Accuracy=0.5303, over 6417.00 frames. ], tot_loss[loss=3.421, NarTop10Accuracy=0.6411, over 6008.34 frames. ], batch size: 50, lr: 1.04e-02
2024-08-06 16:10:38,514 INFO [trainer.py:765] (7/8) Epoch 8, batch 2100, train_loss[loss=3.22, NarTop10Accuracy=0.6813, over 3981.00 frames. ], tot_loss[loss=3.411, NarTop10Accuracy=0.6435, over 5992.54 frames. ], batch size: 4, lr: 1.04e-02
2024-08-06 16:11:03,747 INFO [trainer.py:765] (7/8) Epoch 8, batch 2200, train_loss[loss=3.677, NarTop10Accuracy=0.5856, over 7245.00 frames. ], tot_loss[loss=3.425, NarTop10Accuracy=0.6407, over 6029.51 frames. ], batch size: 31, lr: 1.04e-02
2024-08-06 16:11:28,904 INFO [trainer.py:765] (7/8) Epoch 8, batch 2300, train_loss[loss=3.646, NarTop10Accuracy=0.5847, over 5763.00 frames. ], tot_loss[loss=3.445, NarTop10Accuracy=0.6364, over 6046.38 frames. ], batch size: 9, lr: 1.03e-02
2024-08-06 16:11:53,093 INFO [trainer.py:765] (7/8) Epoch 8, batch 2400, train_loss[loss=3.49, NarTop10Accuracy=0.6324, over 5685.00 frames. ], tot_loss[loss=3.424, NarTop10Accuracy=0.6408, over 5781.81 frames. ], batch size: 8, lr: 1.03e-02
2024-08-06 16:12:16,444 INFO [trainer.py:765] (7/8) Epoch 8, batch 2500, train_loss[loss=3.344, NarTop10Accuracy=0.6568, over 5835.00 frames. ], tot_loss[loss=3.418, NarTop10Accuracy=0.6414, over 5485.87 frames. ], batch size: 8, lr: 1.03e-02
2024-08-06 16:12:36,280 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 16:13:37,515 INFO [trainer.py:765] (7/8) Epoch 9, batch 100, train_loss[loss=3.239, NarTop10Accuracy=0.6811, over 7458.00 frames. ], tot_loss[loss=3.378, NarTop10Accuracy=0.651, over 2376.84 frames. ], batch size: 31, lr: 9.72e-03
2024-08-06 16:14:14,441 INFO [trainer.py:765] (7/8) Epoch 9, batch 200, train_loss[loss=3.636, NarTop10Accuracy=0.5947, over 6837.00 frames. ], tot_loss[loss=3.367, NarTop10Accuracy=0.6531, over 3861.61 frames. ], batch size: 17, lr: 9.70e-03
2024-08-06 16:14:44,508 INFO [trainer.py:765] (7/8) Epoch 9, batch 300, train_loss[loss=3.345, NarTop10Accuracy=0.6562, over 7377.00 frames. ], tot_loss[loss=3.37, NarTop10Accuracy=0.652, over 4655.25 frames. ], batch size: 23, lr: 9.68e-03
2024-08-06 16:15:14,915 INFO [trainer.py:765] (7/8) Epoch 9, batch 400, train_loss[loss=3.263, NarTop10Accuracy=0.6774, over 5031.00 frames. ], tot_loss[loss=3.362, NarTop10Accuracy=0.6538, over 5121.21 frames. ], batch size: 7, lr: 9.65e-03
2024-08-06 16:15:50,336 INFO [trainer.py:765] (7/8) Epoch 9, batch 500, train_loss[loss=3.282, NarTop10Accuracy=0.6709, over 6111.00 frames. ], tot_loss[loss=3.352, NarTop10Accuracy=0.6559, over 5398.52 frames. ], batch size: 11, lr: 9.63e-03
2024-08-06 16:16:23,973 INFO [trainer.py:765] (7/8) Epoch 9, batch 600, train_loss[loss=3.525, NarTop10Accuracy=0.6237, over 5823.00 frames. ], tot_loss[loss=3.343, NarTop10Accuracy=0.6586, over 5653.29 frames. ], batch size: 9, lr: 9.61e-03
2024-08-06 16:16:57,145 INFO [trainer.py:765] (7/8) Epoch 9, batch 700, train_loss[loss=3.192, NarTop10Accuracy=0.696, over 5064.00 frames. ], tot_loss[loss=3.359, NarTop10Accuracy=0.6549, over 5737.59 frames. ], batch size: 6, lr: 9.59e-03
2024-08-06 16:17:32,052 INFO [trainer.py:765] (7/8) Epoch 9, batch 800, train_loss[loss=3.182, NarTop10Accuracy=0.6908, over 5043.00 frames. ], tot_loss[loss=3.391, NarTop10Accuracy=0.6479, over 5777.11 frames. ], batch size: 6, lr: 9.57e-03
2024-08-06 16:18:07,816 INFO [trainer.py:765] (7/8) Epoch 9, batch 900, train_loss[loss=3.245, NarTop10Accuracy=0.6838, over 6180.00 frames. ], tot_loss[loss=3.381, NarTop10Accuracy=0.6497, over 5793.31 frames. ], batch size: 13, lr: 9.55e-03
2024-08-06 16:18:39,345 INFO [trainer.py:765] (7/8) Epoch 9, batch 1000, train_loss[loss=3.157, NarTop10Accuracy=0.6921, over 6189.00 frames. ], tot_loss[loss=3.393, NarTop10Accuracy=0.6472, over 5900.64 frames. ], batch size: 13, lr: 9.53e-03
2024-08-06 16:19:15,383 INFO [trainer.py:765] (7/8) Epoch 9, batch 1100, train_loss[loss=3.523, NarTop10Accuracy=0.6253, over 6774.00 frames. ], tot_loss[loss=3.4, NarTop10Accuracy=0.6457, over 5934.99 frames. ], batch size: 17, lr: 9.50e-03
2024-08-06 16:19:53,878 INFO [trainer.py:765] (7/8) Epoch 9, batch 1200, train_loss[loss=3.721, NarTop10Accuracy=0.5681, over 7305.00 frames. ], tot_loss[loss=3.403, NarTop10Accuracy=0.6447, over 5936.73 frames. ], batch size: 31, lr: 9.48e-03
2024-08-06 16:20:24,907 INFO [trainer.py:765] (7/8) Epoch 9, batch 1300, train_loss[loss=3.217, NarTop10Accuracy=0.6887, over 5025.00 frames. ], tot_loss[loss=3.393, NarTop10Accuracy=0.6467, over 5995.91 frames. ], batch size: 6, lr: 9.46e-03
2024-08-06 16:20:56,580 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 16:21:04,483 INFO [trainer.py:811] (7/8) Epoch 9, validation: loss=3.266, NarTop10Accuracy=0.6725, over 1905321.00 frames. 
2024-08-06 16:21:04,484 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27199MB
2024-08-06 16:21:05,035 INFO [optim.py:386] (7/8) Clipping_scale=2.0, grad-norm quartiles 1.473e+02 1.808e+02 1.967e+02 2.142e+02 6.126e+02, threshold=3.935e+02, percent-clipped=0.5
2024-08-06 16:21:06,691 INFO [trainer.py:765] (7/8) Epoch 9, batch 1400, train_loss[loss=3.586, NarTop10Accuracy=0.6057, over 6054.00 frames. ], tot_loss[loss=3.4, NarTop10Accuracy=0.6455, over 6019.07 frames. ], batch size: 11, lr: 9.44e-03
2024-08-06 16:21:38,895 INFO [trainer.py:765] (7/8) Epoch 9, batch 1500, train_loss[loss=3.465, NarTop10Accuracy=0.6355, over 6168.00 frames. ], tot_loss[loss=3.377, NarTop10Accuracy=0.6507, over 5952.91 frames. ], batch size: 51, lr: 9.42e-03
2024-08-06 16:22:06,721 INFO [trainer.py:765] (7/8) Epoch 9, batch 1600, train_loss[loss=3.377, NarTop10Accuracy=0.6561, over 7059.00 frames. ], tot_loss[loss=3.371, NarTop10Accuracy=0.6518, over 5926.83 frames. ], batch size: 22, lr: 9.40e-03
2024-08-06 16:22:33,470 INFO [trainer.py:765] (7/8) Epoch 9, batch 1700, train_loss[loss=3.361, NarTop10Accuracy=0.6427, over 6234.00 frames. ], tot_loss[loss=3.386, NarTop10Accuracy=0.6484, over 5912.39 frames. ], batch size: 13, lr: 9.38e-03
2024-08-06 16:23:00,064 INFO [trainer.py:765] (7/8) Epoch 9, batch 1800, train_loss[loss=3.156, NarTop10Accuracy=0.6969, over 7188.00 frames. ], tot_loss[loss=3.375, NarTop10Accuracy=0.6508, over 5983.20 frames. ], batch size: 22, lr: 9.36e-03
2024-08-06 16:23:26,783 INFO [trainer.py:765] (7/8) Epoch 9, batch 1900, train_loss[loss=3.366, NarTop10Accuracy=0.6545, over 6051.00 frames. ], tot_loss[loss=3.391, NarTop10Accuracy=0.6479, over 6035.25 frames. ], batch size: 51, lr: 9.34e-03
2024-08-06 16:23:52,486 INFO [trainer.py:765] (7/8) Epoch 9, batch 2000, train_loss[loss=4.064, NarTop10Accuracy=0.5093, over 5700.00 frames. ], tot_loss[loss=3.38, NarTop10Accuracy=0.6498, over 5993.98 frames. ], batch size: 50, lr: 9.32e-03
2024-08-06 16:24:17,963 INFO [trainer.py:765] (7/8) Epoch 9, batch 2100, train_loss[loss=3.097, NarTop10Accuracy=0.7099, over 4731.00 frames. ], tot_loss[loss=3.382, NarTop10Accuracy=0.6497, over 5983.66 frames. ], batch size: 5, lr: 9.30e-03
2024-08-06 16:24:43,421 INFO [trainer.py:765] (7/8) Epoch 9, batch 2200, train_loss[loss=3.636, NarTop10Accuracy=0.5877, over 7536.00 frames. ], tot_loss[loss=3.386, NarTop10Accuracy=0.6487, over 6014.92 frames. ], batch size: 31, lr: 9.28e-03
2024-08-06 16:25:08,721 INFO [trainer.py:765] (7/8) Epoch 9, batch 2300, train_loss[loss=3.168, NarTop10Accuracy=0.6901, over 5742.00 frames. ], tot_loss[loss=3.402, NarTop10Accuracy=0.645, over 6030.66 frames. ], batch size: 9, lr: 9.26e-03
2024-08-06 16:25:33,164 INFO [trainer.py:765] (7/8) Epoch 9, batch 2400, train_loss[loss=3.129, NarTop10Accuracy=0.6907, over 5238.00 frames. ], tot_loss[loss=3.397, NarTop10Accuracy=0.6457, over 5781.75 frames. ], batch size: 7, lr: 9.25e-03
2024-08-06 16:25:56,768 INFO [trainer.py:765] (7/8) Epoch 9, batch 2500, train_loss[loss=3.19, NarTop10Accuracy=0.6846, over 5136.00 frames. ], tot_loss[loss=3.359, NarTop10Accuracy=0.6535, over 5484.32 frames. ], batch size: 7, lr: 9.23e-03
2024-08-06 16:26:16,487 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 16:27:19,584 INFO [trainer.py:765] (7/8) Epoch 10, batch 100, train_loss[loss=3.211, NarTop10Accuracy=0.6819, over 7380.00 frames. ], tot_loss[loss=3.372, NarTop10Accuracy=0.6518, over 2372.49 frames. ], batch size: 31, lr: 8.76e-03
2024-08-06 16:27:52,628 INFO [trainer.py:765] (7/8) Epoch 10, batch 200, train_loss[loss=3.208, NarTop10Accuracy=0.6822, over 6816.00 frames. ], tot_loss[loss=3.352, NarTop10Accuracy=0.6558, over 3859.47 frames. ], batch size: 17, lr: 8.74e-03
2024-08-06 16:28:23,057 INFO [trainer.py:765] (7/8) Epoch 10, batch 300, train_loss[loss=3.135, NarTop10Accuracy=0.7037, over 7206.00 frames. ], tot_loss[loss=3.354, NarTop10Accuracy=0.6553, over 4670.29 frames. ], batch size: 22, lr: 8.72e-03
2024-08-06 16:28:59,200 INFO [trainer.py:765] (7/8) Epoch 10, batch 400, train_loss[loss=3.361, NarTop10Accuracy=0.6503, over 5154.00 frames. ], tot_loss[loss=3.348, NarTop10Accuracy=0.6566, over 5124.41 frames. ], batch size: 7, lr: 8.71e-03
2024-08-06 16:29:29,218 INFO [trainer.py:765] (7/8) Epoch 10, batch 500, train_loss[loss=3.073, NarTop10Accuracy=0.7111, over 6099.00 frames. ], tot_loss[loss=3.341, NarTop10Accuracy=0.6579, over 5387.69 frames. ], batch size: 11, lr: 8.69e-03
2024-08-06 16:30:02,765 INFO [trainer.py:765] (7/8) Epoch 10, batch 600, train_loss[loss=3.745, NarTop10Accuracy=0.579, over 6177.00 frames. ], tot_loss[loss=3.352, NarTop10Accuracy=0.6553, over 5657.94 frames. ], batch size: 10, lr: 8.67e-03
2024-08-06 16:30:34,265 INFO [trainer.py:765] (7/8) Epoch 10, batch 700, train_loss[loss=3.29, NarTop10Accuracy=0.668, over 5070.00 frames. ], tot_loss[loss=3.353, NarTop10Accuracy=0.6548, over 5733.93 frames. ], batch size: 6, lr: 8.65e-03
2024-08-06 16:31:09,843 INFO [trainer.py:765] (7/8) Epoch 10, batch 800, train_loss[loss=3.468, NarTop10Accuracy=0.6264, over 4947.00 frames. ], tot_loss[loss=3.355, NarTop10Accuracy=0.6547, over 5781.97 frames. ], batch size: 6, lr: 8.64e-03
2024-08-06 16:31:16,259 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 16:31:24,565 INFO [trainer.py:811] (7/8) Epoch 10, validation: loss=3.184, NarTop10Accuracy=0.6898, over 1905321.00 frames. 
2024-08-06 16:31:24,566 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27199MB
2024-08-06 16:31:25,154 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 10, batch 900, train_loss[loss=3.123, NarTop10Accuracy=0.7016, over 6675.00 frames. ], tot_loss[loss=3.329, NarTop10Accuracy=0.66, over 5788.55 frames. ], batch size: 14, lr: 8.62e-03
2024-08-06 16:32:28,589 INFO [trainer.py:765] (7/8) Epoch 10, batch 1000, train_loss[loss=3.073, NarTop10Accuracy=0.7185, over 6084.00 frames. ], tot_loss[loss=3.333, NarTop10Accuracy=0.6593, over 5887.93 frames. ], batch size: 13, lr: 8.60e-03
2024-08-06 16:33:06,376 INFO [trainer.py:765] (7/8) Epoch 10, batch 1100, train_loss[loss=3.249, NarTop10Accuracy=0.6779, over 6747.00 frames. ], tot_loss[loss=3.344, NarTop10Accuracy=0.6571, over 5934.78 frames. ], batch size: 17, lr: 8.59e-03
2024-08-06 16:33:40,960 INFO [trainer.py:765] (7/8) Epoch 10, batch 1200, train_loss[loss=3.251, NarTop10Accuracy=0.6791, over 7380.00 frames. ], tot_loss[loss=3.335, NarTop10Accuracy=0.6585, over 5922.22 frames. ], batch size: 32, lr: 8.57e-03
2024-08-06 16:34:16,169 INFO [trainer.py:765] (7/8) Epoch 10, batch 1300, train_loss[loss=3.226, NarTop10Accuracy=0.6672, over 5073.00 frames. ], tot_loss[loss=3.335, NarTop10Accuracy=0.6583, over 5988.57 frames. ], batch size: 6, lr: 8.55e-03
2024-08-06 16:34:51,200 INFO [trainer.py:765] (7/8) Epoch 10, batch 1400, train_loss[loss=3.277, NarTop10Accuracy=0.6705, over 6009.00 frames. ], tot_loss[loss=3.363, NarTop10Accuracy=0.6529, over 6032.47 frames. ], batch size: 11, lr: 8.54e-03
2024-08-06 16:35:22,159 INFO [trainer.py:765] (7/8) Epoch 10, batch 1500, train_loss[loss=3.533, NarTop10Accuracy=0.6209, over 5982.00 frames. ], tot_loss[loss=3.343, NarTop10Accuracy=0.657, over 5981.35 frames. ], batch size: 50, lr: 8.52e-03
2024-08-06 16:35:50,136 INFO [trainer.py:765] (7/8) Epoch 10, batch 1600, train_loss[loss=3.594, NarTop10Accuracy=0.6061, over 6843.00 frames. ], tot_loss[loss=3.333, NarTop10Accuracy=0.659, over 5937.98 frames. ], batch size: 22, lr: 8.50e-03
2024-08-06 16:36:16,976 INFO [trainer.py:765] (7/8) Epoch 10, batch 1700, train_loss[loss=3.437, NarTop10Accuracy=0.639, over 6669.00 frames. ], tot_loss[loss=3.34, NarTop10Accuracy=0.6576, over 5918.51 frames. ], batch size: 14, lr: 8.49e-03
2024-08-06 16:36:43,647 INFO [trainer.py:765] (7/8) Epoch 10, batch 1800, train_loss[loss=3.201, NarTop10Accuracy=0.6853, over 7203.00 frames. ], tot_loss[loss=3.335, NarTop10Accuracy=0.6591, over 5976.40 frames. ], batch size: 22, lr: 8.47e-03
2024-08-06 16:37:10,290 INFO [trainer.py:765] (7/8) Epoch 10, batch 1900, train_loss[loss=3.235, NarTop10Accuracy=0.6846, over 5637.00 frames. ], tot_loss[loss=3.331, NarTop10Accuracy=0.6599, over 6014.91 frames. ], batch size: 50, lr: 8.45e-03
2024-08-06 16:37:36,089 INFO [trainer.py:765] (7/8) Epoch 10, batch 2000, train_loss[loss=3.284, NarTop10Accuracy=0.6733, over 6285.00 frames. ], tot_loss[loss=3.322, NarTop10Accuracy=0.6615, over 5992.28 frames. ], batch size: 51, lr: 8.44e-03
2024-08-06 16:38:01,650 INFO [trainer.py:765] (7/8) Epoch 10, batch 2100, train_loss[loss=3.489, NarTop10Accuracy=0.6248, over 3840.00 frames. ], tot_loss[loss=3.34, NarTop10Accuracy=0.6577, over 5956.81 frames. ], batch size: 4, lr: 8.42e-03
2024-08-06 16:38:27,120 INFO [trainer.py:765] (7/8) Epoch 10, batch 2200, train_loss[loss=3.735, NarTop10Accuracy=0.5738, over 7287.00 frames. ], tot_loss[loss=3.345, NarTop10Accuracy=0.6566, over 6010.40 frames. ], batch size: 32, lr: 8.41e-03
2024-08-06 16:38:52,447 INFO [trainer.py:765] (7/8) Epoch 10, batch 2300, train_loss[loss=3.167, NarTop10Accuracy=0.6926, over 5685.00 frames. ], tot_loss[loss=3.354, NarTop10Accuracy=0.6549, over 6012.99 frames. ], batch size: 9, lr: 8.39e-03
2024-08-06 16:39:17,005 INFO [trainer.py:765] (7/8) Epoch 10, batch 2400, train_loss[loss=3.197, NarTop10Accuracy=0.6885, over 5001.00 frames. ], tot_loss[loss=3.326, NarTop10Accuracy=0.6608, over 5762.30 frames. ], batch size: 7, lr: 8.37e-03
2024-08-06 16:39:40,801 INFO [trainer.py:765] (7/8) Epoch 10, batch 2500, train_loss[loss=3.414, NarTop10Accuracy=0.6369, over 5205.00 frames. ], tot_loss[loss=3.3, NarTop10Accuracy=0.666, over 5462.89 frames. ], batch size: 7, lr: 8.36e-03
2024-08-06 16:40:00,497 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 16:41:06,235 INFO [trainer.py:765] (7/8) Epoch 11, batch 100, train_loss[loss=3.553, NarTop10Accuracy=0.6116, over 7314.00 frames. ], tot_loss[loss=3.344, NarTop10Accuracy=0.6568, over 2364.75 frames. ], batch size: 32, lr: 7.97e-03
2024-08-06 16:41:39,021 INFO [trainer.py:765] (7/8) Epoch 11, batch 200, train_loss[loss=3.661, NarTop10Accuracy=0.5858, over 6744.00 frames. ], tot_loss[loss=3.329, NarTop10Accuracy=0.6604, over 3852.44 frames. ], batch size: 17, lr: 7.95e-03
2024-08-06 16:41:53,190 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 16:42:01,355 INFO [trainer.py:811] (7/8) Epoch 11, validation: loss=3.116, NarTop10Accuracy=0.7034, over 1905321.00 frames. 
2024-08-06 16:42:01,356 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27199MB
2024-08-06 16:42:01,879 INFO [optim.py:386] (7/8) 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 16:42:17,976 INFO [trainer.py:765] (7/8) Epoch 11, batch 300, train_loss[loss=3.121, NarTop10Accuracy=0.706, over 7002.00 frames. ], tot_loss[loss=3.304, NarTop10Accuracy=0.6653, over 4653.89 frames. ], batch size: 22, lr: 7.94e-03
2024-08-06 16:42:55,155 INFO [trainer.py:765] (7/8) Epoch 11, batch 400, train_loss[loss=3.216, NarTop10Accuracy=0.6812, over 5148.00 frames. ], tot_loss[loss=3.292, NarTop10Accuracy=0.6679, over 5115.93 frames. ], batch size: 7, lr: 7.92e-03
2024-08-06 16:43:25,719 INFO [trainer.py:765] (7/8) Epoch 11, batch 500, train_loss[loss=3.151, NarTop10Accuracy=0.6939, over 6183.00 frames. ], tot_loss[loss=3.287, NarTop10Accuracy=0.6688, over 5383.26 frames. ], batch size: 11, lr: 7.91e-03
2024-08-06 16:44:02,242 INFO [trainer.py:765] (7/8) Epoch 11, batch 600, train_loss[loss=3.457, NarTop10Accuracy=0.6283, over 5781.00 frames. ], tot_loss[loss=3.3, NarTop10Accuracy=0.6663, over 5644.32 frames. ], batch size: 9, lr: 7.89e-03
2024-08-06 16:44:35,716 INFO [trainer.py:765] (7/8) Epoch 11, batch 700, train_loss[loss=3.674, NarTop10Accuracy=0.5859, over 5088.00 frames. ], tot_loss[loss=3.294, NarTop10Accuracy=0.6674, over 5735.03 frames. ], batch size: 6, lr: 7.88e-03
2024-08-06 16:45:10,468 INFO [trainer.py:765] (7/8) Epoch 11, batch 800, train_loss[loss=3.085, NarTop10Accuracy=0.716, over 5157.00 frames. ], tot_loss[loss=3.31, NarTop10Accuracy=0.6638, over 5781.34 frames. ], batch size: 6, lr: 7.86e-03
2024-08-06 16:45:46,457 INFO [trainer.py:765] (7/8) Epoch 11, batch 900, train_loss[loss=3.662, NarTop10Accuracy=0.5889, over 6234.00 frames. ], tot_loss[loss=3.304, NarTop10Accuracy=0.6648, over 5799.19 frames. ], batch size: 13, lr: 7.85e-03
2024-08-06 16:46:20,310 INFO [trainer.py:765] (7/8) Epoch 11, batch 1000, train_loss[loss=3.449, NarTop10Accuracy=0.641, over 6558.00 frames. ], tot_loss[loss=3.298, NarTop10Accuracy=0.666, over 5898.44 frames. ], batch size: 14, lr: 7.84e-03
2024-08-06 16:46:53,457 INFO [trainer.py:765] (7/8) Epoch 11, batch 1100, train_loss[loss=3.105, NarTop10Accuracy=0.7106, over 6864.00 frames. ], tot_loss[loss=3.293, NarTop10Accuracy=0.6671, over 5926.50 frames. ], batch size: 17, lr: 7.82e-03
2024-08-06 16:47:33,030 INFO [trainer.py:765] (7/8) Epoch 11, batch 1200, train_loss[loss=3.441, NarTop10Accuracy=0.6334, over 7488.00 frames. ], tot_loss[loss=3.303, NarTop10Accuracy=0.6652, over 5923.43 frames. ], batch size: 32, lr: 7.81e-03
2024-08-06 16:48:06,481 INFO [trainer.py:765] (7/8) Epoch 11, batch 1300, train_loss[loss=2.987, NarTop10Accuracy=0.7366, over 4923.00 frames. ], tot_loss[loss=3.314, NarTop10Accuracy=0.6631, over 6000.43 frames. ], batch size: 6, lr: 7.79e-03
2024-08-06 16:48:41,353 INFO [trainer.py:765] (7/8) Epoch 11, batch 1400, train_loss[loss=3.39, NarTop10Accuracy=0.6501, over 6093.00 frames. ], tot_loss[loss=3.332, NarTop10Accuracy=0.6594, over 6033.30 frames. ], batch size: 11, lr: 7.78e-03
2024-08-06 16:49:09,345 INFO [trainer.py:765] (7/8) Epoch 11, batch 1500, train_loss[loss=3.379, NarTop10Accuracy=0.6524, over 6213.00 frames. ], tot_loss[loss=3.33, NarTop10Accuracy=0.6596, over 5976.77 frames. ], batch size: 51, lr: 7.77e-03
2024-08-06 16:49:37,103 INFO [trainer.py:765] (7/8) Epoch 11, batch 1600, train_loss[loss=3.298, NarTop10Accuracy=0.6732, over 7098.00 frames. ], tot_loss[loss=3.305, NarTop10Accuracy=0.6645, over 5958.49 frames. ], batch size: 22, lr: 7.75e-03
2024-08-06 16:50:03,792 INFO [trainer.py:765] (7/8) Epoch 11, batch 1700, train_loss[loss=3.397, NarTop10Accuracy=0.642, over 6270.00 frames. ], tot_loss[loss=3.298, NarTop10Accuracy=0.6658, over 5952.14 frames. ], batch size: 13, lr: 7.74e-03
2024-08-06 16:50:30,353 INFO [trainer.py:765] (7/8) Epoch 11, batch 1800, train_loss[loss=3.461, NarTop10Accuracy=0.6331, over 7023.00 frames. ], tot_loss[loss=3.316, NarTop10Accuracy=0.6622, over 5999.77 frames. ], batch size: 22, lr: 7.72e-03
2024-08-06 16:50:56,821 INFO [trainer.py:765] (7/8) Epoch 11, batch 1900, train_loss[loss=3.864, NarTop10Accuracy=0.5501, over 6450.00 frames. ], tot_loss[loss=3.326, NarTop10Accuracy=0.6603, over 6043.75 frames. ], batch size: 50, lr: 7.71e-03
2024-08-06 16:51:22,405 INFO [trainer.py:765] (7/8) Epoch 11, batch 2000, train_loss[loss=3.761, NarTop10Accuracy=0.5667, over 5775.00 frames. ], tot_loss[loss=3.319, NarTop10Accuracy=0.6613, over 6008.73 frames. ], batch size: 51, lr: 7.70e-03
2024-08-06 16:51:47,794 INFO [trainer.py:765] (7/8) Epoch 11, batch 2100, train_loss[loss=2.998, NarTop10Accuracy=0.7311, over 3957.00 frames. ], tot_loss[loss=3.315, NarTop10Accuracy=0.662, over 5985.18 frames. ], batch size: 4, lr: 7.68e-03
2024-08-06 16:52:13,118 INFO [trainer.py:765] (7/8) Epoch 11, batch 2200, train_loss[loss=3.282, NarTop10Accuracy=0.6728, over 7176.00 frames. ], tot_loss[loss=3.31, NarTop10Accuracy=0.6632, over 6012.87 frames. ], batch size: 31, lr: 7.67e-03
2024-08-06 16:52:23,899 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 16:52:32,079 INFO [trainer.py:811] (7/8) Epoch 11, validation: loss=3.101, NarTop10Accuracy=0.7058, over 1905321.00 frames. 
2024-08-06 16:52:32,079 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27199MB
2024-08-06 16:52:32,593 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 11, batch 2300, train_loss[loss=3.08, NarTop10Accuracy=0.7088, over 5616.00 frames. ], tot_loss[loss=3.32, NarTop10Accuracy=0.6614, over 6019.89 frames. ], batch size: 9, lr: 7.66e-03
2024-08-06 16:53:10,887 INFO [trainer.py:765] (7/8) Epoch 11, batch 2400, train_loss[loss=3.495, NarTop10Accuracy=0.6381, over 4938.00 frames. ], tot_loss[loss=3.31, NarTop10Accuracy=0.6636, over 5776.81 frames. ], batch size: 7, lr: 7.64e-03
2024-08-06 16:53:34,371 INFO [trainer.py:765] (7/8) Epoch 11, batch 2500, train_loss[loss=3.376, NarTop10Accuracy=0.6471, over 5208.00 frames. ], tot_loss[loss=3.298, NarTop10Accuracy=0.6652, over 5473.51 frames. ], batch size: 7, lr: 7.63e-03
2024-08-06 16:53:54,308 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 16:54:58,525 INFO [trainer.py:765] (7/8) Epoch 12, batch 100, train_loss[loss=3.635, NarTop10Accuracy=0.5915, over 7158.00 frames. ], tot_loss[loss=3.296, NarTop10Accuracy=0.6671, over 2366.19 frames. ], batch size: 31, lr: 7.30e-03
2024-08-06 16:55:32,432 INFO [trainer.py:765] (7/8) Epoch 12, batch 200, train_loss[loss=3.072, NarTop10Accuracy=0.7164, over 6777.00 frames. ], tot_loss[loss=3.265, NarTop10Accuracy=0.6735, over 3860.68 frames. ], batch size: 17, lr: 7.29e-03
2024-08-06 16:56:05,096 INFO [trainer.py:765] (7/8) Epoch 12, batch 300, train_loss[loss=2.96, NarTop10Accuracy=0.7337, over 7032.00 frames. ], tot_loss[loss=3.245, NarTop10Accuracy=0.6774, over 4672.13 frames. ], batch size: 22, lr: 7.27e-03
2024-08-06 16:56:36,426 INFO [trainer.py:765] (7/8) Epoch 12, batch 400, train_loss[loss=3.033, NarTop10Accuracy=0.7186, over 5076.00 frames. ], tot_loss[loss=3.256, NarTop10Accuracy=0.6747, over 5122.57 frames. ], batch size: 7, lr: 7.26e-03
2024-08-06 16:57:10,503 INFO [trainer.py:765] (7/8) Epoch 12, batch 500, train_loss[loss=3.601, NarTop10Accuracy=0.6007, over 6045.00 frames. ], tot_loss[loss=3.264, NarTop10Accuracy=0.673, over 5397.49 frames. ], batch size: 11, lr: 7.25e-03
2024-08-06 16:57:45,483 INFO [trainer.py:765] (7/8) Epoch 12, batch 600, train_loss[loss=2.97, NarTop10Accuracy=0.7433, over 5835.00 frames. ], tot_loss[loss=3.274, NarTop10Accuracy=0.6711, over 5672.39 frames. ], batch size: 9, lr: 7.24e-03
2024-08-06 16:58:17,005 INFO [trainer.py:765] (7/8) Epoch 12, batch 700, train_loss[loss=3.459, NarTop10Accuracy=0.6249, over 4260.00 frames. ], tot_loss[loss=3.292, NarTop10Accuracy=0.6672, over 5718.22 frames. ], batch size: 5, lr: 7.22e-03
2024-08-06 16:58:53,469 INFO [trainer.py:765] (7/8) Epoch 12, batch 800, train_loss[loss=3.448, NarTop10Accuracy=0.6243, over 5058.00 frames. ], tot_loss[loss=3.289, NarTop10Accuracy=0.6676, over 5782.27 frames. ], batch size: 6, lr: 7.21e-03
2024-08-06 16:59:27,206 INFO [trainer.py:765] (7/8) Epoch 12, batch 900, train_loss[loss=3.065, NarTop10Accuracy=0.7136, over 6714.00 frames. ], tot_loss[loss=3.27, NarTop10Accuracy=0.6716, over 5794.74 frames. ], batch size: 14, lr: 7.20e-03
2024-08-06 17:00:01,574 INFO [trainer.py:765] (7/8) Epoch 12, batch 1000, train_loss[loss=2.974, NarTop10Accuracy=0.7333, over 6390.00 frames. ], tot_loss[loss=3.282, NarTop10Accuracy=0.6693, over 5903.95 frames. ], batch size: 13, lr: 7.19e-03
2024-08-06 17:00:39,189 INFO [trainer.py:765] (7/8) Epoch 12, batch 1100, train_loss[loss=3.466, NarTop10Accuracy=0.6206, over 6789.00 frames. ], tot_loss[loss=3.298, NarTop10Accuracy=0.6658, over 5947.51 frames. ], batch size: 17, lr: 7.18e-03
2024-08-06 17:01:13,964 INFO [trainer.py:765] (7/8) Epoch 12, batch 1200, train_loss[loss=3.019, NarTop10Accuracy=0.722, over 7221.00 frames. ], tot_loss[loss=3.265, NarTop10Accuracy=0.6726, over 5938.39 frames. ], batch size: 31, lr: 7.17e-03
2024-08-06 17:01:48,108 INFO [trainer.py:765] (7/8) Epoch 12, batch 1300, train_loss[loss=3.281, NarTop10Accuracy=0.6677, over 5220.00 frames. ], tot_loss[loss=3.282, NarTop10Accuracy=0.6693, over 6000.94 frames. ], batch size: 6, lr: 7.15e-03
2024-08-06 17:02:22,323 INFO [trainer.py:765] (7/8) Epoch 12, batch 1400, train_loss[loss=3.637, NarTop10Accuracy=0.598, over 5994.00 frames. ], tot_loss[loss=3.29, NarTop10Accuracy=0.6672, over 6017.36 frames. ], batch size: 11, lr: 7.14e-03
2024-08-06 17:02:52,877 INFO [trainer.py:765] (7/8) Epoch 12, batch 1500, train_loss[loss=3.369, NarTop10Accuracy=0.6554, over 6189.00 frames. ], tot_loss[loss=3.27, NarTop10Accuracy=0.6715, over 5949.24 frames. ], batch size: 50, lr: 7.13e-03
2024-08-06 17:03:20,691 INFO [trainer.py:765] (7/8) Epoch 12, batch 1600, train_loss[loss=3.294, NarTop10Accuracy=0.6688, over 7122.00 frames. ], tot_loss[loss=3.281, NarTop10Accuracy=0.6698, over 5921.89 frames. ], batch size: 22, lr: 7.12e-03
2024-08-06 17:03:38,297 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 17:03:46,474 INFO [trainer.py:811] (7/8) Epoch 12, validation: loss=3.054, NarTop10Accuracy=0.7153, over 1905321.00 frames. 
2024-08-06 17:03:46,474 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 17:03:46,988 INFO [optim.py:386] (7/8) Clipping_scale=2.0, grad-norm quartiles 1.507e+02 1.899e+02 2.078e+02 2.276e+02 5.455e+02, threshold=4.157e+02, percent-clipped=0.1
2024-08-06 17:03:55,604 INFO [trainer.py:765] (7/8) Epoch 12, batch 1700, train_loss[loss=3.458, NarTop10Accuracy=0.636, over 6366.00 frames. ], tot_loss[loss=3.291, NarTop10Accuracy=0.6678, over 5913.28 frames. ], batch size: 13, lr: 7.11e-03
2024-08-06 17:04:22,121 INFO [trainer.py:765] (7/8) Epoch 12, batch 1800, train_loss[loss=3.477, NarTop10Accuracy=0.6241, over 6930.00 frames. ], tot_loss[loss=3.288, NarTop10Accuracy=0.6684, over 5987.09 frames. ], batch size: 22, lr: 7.10e-03
2024-08-06 17:04:48,592 INFO [trainer.py:765] (7/8) Epoch 12, batch 1900, train_loss[loss=3.285, NarTop10Accuracy=0.671, over 6378.00 frames. ], tot_loss[loss=3.285, NarTop10Accuracy=0.6689, over 6029.56 frames. ], batch size: 50, lr: 7.08e-03
2024-08-06 17:05:14,198 INFO [trainer.py:765] (7/8) Epoch 12, batch 2000, train_loss[loss=3.55, NarTop10Accuracy=0.6185, over 6393.00 frames. ], tot_loss[loss=3.273, NarTop10Accuracy=0.6717, over 6013.24 frames. ], batch size: 51, lr: 7.07e-03
2024-08-06 17:05:39,468 INFO [trainer.py:765] (7/8) Epoch 12, batch 2100, train_loss[loss=3.401, NarTop10Accuracy=0.6441, over 3996.00 frames. ], tot_loss[loss=3.277, NarTop10Accuracy=0.6705, over 5987.38 frames. ], batch size: 4, lr: 7.06e-03
2024-08-06 17:06:04,691 INFO [trainer.py:765] (7/8) Epoch 12, batch 2200, train_loss[loss=3.285, NarTop10Accuracy=0.6611, over 7305.00 frames. ], tot_loss[loss=3.291, NarTop10Accuracy=0.6674, over 6018.15 frames. ], batch size: 31, lr: 7.05e-03
2024-08-06 17:06:29,847 INFO [trainer.py:765] (7/8) Epoch 12, batch 2300, train_loss[loss=3.483, NarTop10Accuracy=0.6321, over 5556.00 frames. ], tot_loss[loss=3.286, NarTop10Accuracy=0.6685, over 6029.72 frames. ], batch size: 9, lr: 7.04e-03
2024-08-06 17:06:54,200 INFO [trainer.py:765] (7/8) Epoch 12, batch 2400, train_loss[loss=3.113, NarTop10Accuracy=0.7006, over 5715.00 frames. ], tot_loss[loss=3.283, NarTop10Accuracy=0.6692, over 5774.13 frames. ], batch size: 8, lr: 7.03e-03
2024-08-06 17:07:17,646 INFO [trainer.py:765] (7/8) Epoch 12, batch 2500, train_loss[loss=3.24, NarTop10Accuracy=0.6739, over 5052.00 frames. ], tot_loss[loss=3.256, NarTop10Accuracy=0.674, over 5490.55 frames. ], batch size: 7, lr: 7.02e-03
2024-08-06 17:07:37,539 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 17:08:40,079 INFO [trainer.py:765] (7/8) Epoch 13, batch 100, train_loss[loss=2.92, NarTop10Accuracy=0.7456, over 7341.00 frames. ], tot_loss[loss=3.269, NarTop10Accuracy=0.6714, over 2372.50 frames. ], batch size: 31, lr: 6.73e-03
2024-08-06 17:09:14,120 INFO [trainer.py:765] (7/8) Epoch 13, batch 200, train_loss[loss=3.087, NarTop10Accuracy=0.711, over 6774.00 frames. ], tot_loss[loss=3.285, NarTop10Accuracy=0.669, over 3870.65 frames. ], batch size: 17, lr: 6.72e-03
2024-08-06 17:09:46,276 INFO [trainer.py:765] (7/8) Epoch 13, batch 300, train_loss[loss=3.416, NarTop10Accuracy=0.6481, over 6978.00 frames. ], tot_loss[loss=3.266, NarTop10Accuracy=0.6725, over 4662.38 frames. ], batch size: 22, lr: 6.71e-03
2024-08-06 17:10:19,164 INFO [trainer.py:765] (7/8) Epoch 13, batch 400, train_loss[loss=3.017, NarTop10Accuracy=0.7132, over 5160.00 frames. ], tot_loss[loss=3.254, NarTop10Accuracy=0.6751, over 5114.05 frames. ], batch size: 7, lr: 6.70e-03
2024-08-06 17:10:49,335 INFO [trainer.py:765] (7/8) Epoch 13, batch 500, train_loss[loss=3.269, NarTop10Accuracy=0.6763, over 6009.00 frames. ], tot_loss[loss=3.249, NarTop10Accuracy=0.6762, over 5401.77 frames. ], batch size: 11, lr: 6.69e-03
2024-08-06 17:11:26,244 INFO [trainer.py:765] (7/8) Epoch 13, batch 600, train_loss[loss=2.943, NarTop10Accuracy=0.7319, over 5577.00 frames. ], tot_loss[loss=3.24, NarTop10Accuracy=0.6781, over 5648.90 frames. ], batch size: 9, lr: 6.68e-03
2024-08-06 17:11:57,381 INFO [trainer.py:765] (7/8) Epoch 13, batch 700, train_loss[loss=3.064, NarTop10Accuracy=0.7112, over 4989.00 frames. ], tot_loss[loss=3.242, NarTop10Accuracy=0.6777, over 5741.55 frames. ], batch size: 6, lr: 6.67e-03
2024-08-06 17:12:33,442 INFO [trainer.py:765] (7/8) Epoch 13, batch 800, train_loss[loss=2.923, NarTop10Accuracy=0.737, over 4239.00 frames. ], tot_loss[loss=3.244, NarTop10Accuracy=0.6773, over 5770.80 frames. ], batch size: 5, lr: 6.66e-03
2024-08-06 17:13:10,032 INFO [trainer.py:765] (7/8) Epoch 13, batch 900, train_loss[loss=3.104, NarTop10Accuracy=0.7044, over 6237.00 frames. ], tot_loss[loss=3.243, NarTop10Accuracy=0.6776, over 5784.78 frames. ], batch size: 13, lr: 6.65e-03
2024-08-06 17:13:41,443 INFO [trainer.py:765] (7/8) Epoch 13, batch 1000, train_loss[loss=3.461, NarTop10Accuracy=0.6333, over 6201.00 frames. ], tot_loss[loss=3.238, NarTop10Accuracy=0.6785, over 5886.20 frames. ], batch size: 13, lr: 6.64e-03
2024-08-06 17:14:15,537 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 17:14:23,644 INFO [trainer.py:811] (7/8) Epoch 13, validation: loss=3.099, NarTop10Accuracy=0.7062, over 1905321.00 frames. 
2024-08-06 17:14:23,645 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 17:14:24,470 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 13, batch 1100, train_loss[loss=3.337, NarTop10Accuracy=0.6504, over 6927.00 frames. ], tot_loss[loss=3.25, NarTop10Accuracy=0.6757, over 5925.71 frames. ], batch size: 17, lr: 6.63e-03
2024-08-06 17:15:03,475 INFO [trainer.py:765] (7/8) Epoch 13, batch 1200, train_loss[loss=3.519, NarTop10Accuracy=0.622, over 7245.00 frames. ], tot_loss[loss=3.258, NarTop10Accuracy=0.6737, over 5923.87 frames. ], batch size: 32, lr: 6.62e-03
2024-08-06 17:15:35,514 INFO [trainer.py:765] (7/8) Epoch 13, batch 1300, train_loss[loss=3.116, NarTop10Accuracy=0.7062, over 4341.00 frames. ], tot_loss[loss=3.258, NarTop10Accuracy=0.6737, over 5997.87 frames. ], batch size: 5, lr: 6.61e-03
2024-08-06 17:16:11,782 INFO [trainer.py:765] (7/8) Epoch 13, batch 1400, train_loss[loss=3.041, NarTop10Accuracy=0.7241, over 6099.00 frames. ], tot_loss[loss=3.261, NarTop10Accuracy=0.6731, over 6033.19 frames. ], batch size: 11, lr: 6.60e-03
2024-08-06 17:16:39,787 INFO [trainer.py:765] (7/8) Epoch 13, batch 1500, train_loss[loss=3.532, NarTop10Accuracy=0.6228, over 6204.00 frames. ], tot_loss[loss=3.258, NarTop10Accuracy=0.6743, over 5949.87 frames. ], batch size: 50, lr: 6.59e-03
2024-08-06 17:17:07,603 INFO [trainer.py:765] (7/8) Epoch 13, batch 1600, train_loss[loss=3.018, NarTop10Accuracy=0.7294, over 6993.00 frames. ], tot_loss[loss=3.264, NarTop10Accuracy=0.6732, over 5936.19 frames. ], batch size: 22, lr: 6.58e-03
2024-08-06 17:17:34,259 INFO [trainer.py:765] (7/8) Epoch 13, batch 1700, train_loss[loss=3.185, NarTop10Accuracy=0.6838, over 6213.00 frames. ], tot_loss[loss=3.265, NarTop10Accuracy=0.6727, over 5929.54 frames. ], batch size: 13, lr: 6.57e-03
2024-08-06 17:18:00,762 INFO [trainer.py:765] (7/8) Epoch 13, batch 1800, train_loss[loss=3.133, NarTop10Accuracy=0.6959, over 7023.00 frames. ], tot_loss[loss=3.259, NarTop10Accuracy=0.6738, over 5984.90 frames. ], batch size: 22, lr: 6.56e-03
2024-08-06 17:18:27,244 INFO [trainer.py:765] (7/8) Epoch 13, batch 1900, train_loss[loss=3.534, NarTop10Accuracy=0.6208, over 5505.00 frames. ], tot_loss[loss=3.253, NarTop10Accuracy=0.6754, over 6020.31 frames. ], batch size: 50, lr: 6.55e-03
2024-08-06 17:18:52,777 INFO [trainer.py:765] (7/8) Epoch 13, batch 2000, train_loss[loss=3.489, NarTop10Accuracy=0.6213, over 6441.00 frames. ], tot_loss[loss=3.236, NarTop10Accuracy=0.679, over 6003.72 frames. ], batch size: 51, lr: 6.54e-03
2024-08-06 17:19:18,147 INFO [trainer.py:765] (7/8) Epoch 13, batch 2100, train_loss[loss=2.881, NarTop10Accuracy=0.7497, over 4749.00 frames. ], tot_loss[loss=3.236, NarTop10Accuracy=0.6791, over 5981.96 frames. ], batch size: 5, lr: 6.53e-03
2024-08-06 17:19:43,412 INFO [trainer.py:765] (7/8) Epoch 13, batch 2200, train_loss[loss=3.44, NarTop10Accuracy=0.6386, over 7275.00 frames. ], tot_loss[loss=3.247, NarTop10Accuracy=0.6766, over 6007.00 frames. ], batch size: 31, lr: 6.52e-03
2024-08-06 17:20:08,543 INFO [trainer.py:765] (7/8) Epoch 13, batch 2300, train_loss[loss=3.577, NarTop10Accuracy=0.6046, over 5844.00 frames. ], tot_loss[loss=3.266, NarTop10Accuracy=0.6728, over 6008.47 frames. ], batch size: 9, lr: 6.51e-03
2024-08-06 17:20:32,939 INFO [trainer.py:765] (7/8) Epoch 13, batch 2400, train_loss[loss=3.5, NarTop10Accuracy=0.617, over 5130.00 frames. ], tot_loss[loss=3.242, NarTop10Accuracy=0.6778, over 5776.63 frames. ], batch size: 7, lr: 6.50e-03
2024-08-06 17:20:56,408 INFO [trainer.py:765] (7/8) Epoch 13, batch 2500, train_loss[loss=3.293, NarTop10Accuracy=0.6562, over 5052.00 frames. ], tot_loss[loss=3.219, NarTop10Accuracy=0.6818, over 5481.09 frames. ], batch size: 7, lr: 6.49e-03
2024-08-06 17:21:16,261 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 17:22:19,315 INFO [trainer.py:765] (7/8) Epoch 14, batch 100, train_loss[loss=3.042, NarTop10Accuracy=0.7187, over 7155.00 frames. ], tot_loss[loss=3.224, NarTop10Accuracy=0.6815, over 2381.06 frames. ], batch size: 31, lr: 6.24e-03
2024-08-06 17:22:50,378 INFO [trainer.py:765] (7/8) Epoch 14, batch 200, train_loss[loss=3.194, NarTop10Accuracy=0.6836, over 6684.00 frames. ], tot_loss[loss=3.23, NarTop10Accuracy=0.6798, over 3878.97 frames. ], batch size: 17, lr: 6.23e-03
2024-08-06 17:23:23,880 INFO [trainer.py:765] (7/8) Epoch 14, batch 300, train_loss[loss=3.056, NarTop10Accuracy=0.7215, over 7251.00 frames. ], tot_loss[loss=3.208, NarTop10Accuracy=0.6843, over 4664.71 frames. ], batch size: 22, lr: 6.22e-03
2024-08-06 17:23:57,484 INFO [trainer.py:765] (7/8) Epoch 14, batch 400, train_loss[loss=3.093, NarTop10Accuracy=0.7168, over 5127.00 frames. ], tot_loss[loss=3.225, NarTop10Accuracy=0.6809, over 5111.90 frames. ], batch size: 7, lr: 6.22e-03
2024-08-06 17:24:32,114 INFO [trainer.py:765] (7/8) Epoch 14, batch 500, train_loss[loss=3.28, NarTop10Accuracy=0.6712, over 6162.00 frames. ], tot_loss[loss=3.231, NarTop10Accuracy=0.6793, over 5394.90 frames. ], batch size: 11, lr: 6.21e-03
2024-08-06 17:24:36,213 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 17:24:44,275 INFO [trainer.py:811] (7/8) Epoch 14, validation: loss=3.004, NarTop10Accuracy=0.726, over 1905321.00 frames. 
2024-08-06 17:24:44,275 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 17:24:44,823 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 14, batch 600, train_loss[loss=2.987, NarTop10Accuracy=0.7349, over 5790.00 frames. ], tot_loss[loss=3.231, NarTop10Accuracy=0.6793, over 5668.66 frames. ], batch size: 9, lr: 6.20e-03
2024-08-06 17:25:48,548 INFO [trainer.py:765] (7/8) Epoch 14, batch 700, train_loss[loss=3.566, NarTop10Accuracy=0.6106, over 5112.00 frames. ], tot_loss[loss=3.225, NarTop10Accuracy=0.6805, over 5721.61 frames. ], batch size: 6, lr: 6.19e-03
2024-08-06 17:26:25,280 INFO [trainer.py:765] (7/8) Epoch 14, batch 800, train_loss[loss=2.951, NarTop10Accuracy=0.7398, over 4350.00 frames. ], tot_loss[loss=3.217, NarTop10Accuracy=0.6827, over 5794.41 frames. ], batch size: 5, lr: 6.18e-03
2024-08-06 17:26:57,660 INFO [trainer.py:765] (7/8) Epoch 14, batch 900, train_loss[loss=3.343, NarTop10Accuracy=0.6565, over 6276.00 frames. ], tot_loss[loss=3.211, NarTop10Accuracy=0.6842, over 5794.85 frames. ], batch size: 13, lr: 6.17e-03
2024-08-06 17:27:31,717 INFO [trainer.py:765] (7/8) Epoch 14, batch 1000, train_loss[loss=3.407, NarTop10Accuracy=0.6445, over 6327.00 frames. ], tot_loss[loss=3.223, NarTop10Accuracy=0.6814, over 5897.79 frames. ], batch size: 13, lr: 6.16e-03
2024-08-06 17:28:11,597 INFO [trainer.py:765] (7/8) Epoch 14, batch 1100, train_loss[loss=2.878, NarTop10Accuracy=0.7518, over 6840.00 frames. ], tot_loss[loss=3.218, NarTop10Accuracy=0.6825, over 5960.40 frames. ], batch size: 17, lr: 6.15e-03
2024-08-06 17:28:40,734 INFO [trainer.py:765] (7/8) Epoch 14, batch 1200, train_loss[loss=3.501, NarTop10Accuracy=0.6246, over 6891.00 frames. ], tot_loss[loss=3.213, NarTop10Accuracy=0.6831, over 5941.08 frames. ], batch size: 31, lr: 6.15e-03
2024-08-06 17:29:16,215 INFO [trainer.py:765] (7/8) Epoch 14, batch 1300, train_loss[loss=3.529, NarTop10Accuracy=0.6139, over 5082.00 frames. ], tot_loss[loss=3.218, NarTop10Accuracy=0.6823, over 5988.05 frames. ], batch size: 6, lr: 6.14e-03
2024-08-06 17:29:54,602 INFO [trainer.py:765] (7/8) Epoch 14, batch 1400, train_loss[loss=3.358, NarTop10Accuracy=0.6442, over 5892.00 frames. ], tot_loss[loss=3.227, NarTop10Accuracy=0.6803, over 6004.75 frames. ], batch size: 11, lr: 6.13e-03
2024-08-06 17:30:25,315 INFO [trainer.py:765] (7/8) Epoch 14, batch 1500, train_loss[loss=3.755, NarTop10Accuracy=0.5768, over 5778.00 frames. ], tot_loss[loss=3.233, NarTop10Accuracy=0.6791, over 5957.73 frames. ], batch size: 50, lr: 6.12e-03
2024-08-06 17:30:53,043 INFO [trainer.py:765] (7/8) Epoch 14, batch 1600, train_loss[loss=2.955, NarTop10Accuracy=0.7351, over 7041.00 frames. ], tot_loss[loss=3.221, NarTop10Accuracy=0.6816, over 5925.61 frames. ], batch size: 22, lr: 6.11e-03
2024-08-06 17:31:19,728 INFO [trainer.py:765] (7/8) Epoch 14, batch 1700, train_loss[loss=3.06, NarTop10Accuracy=0.7214, over 6318.00 frames. ], tot_loss[loss=3.207, NarTop10Accuracy=0.6852, over 5899.34 frames. ], batch size: 13, lr: 6.10e-03
2024-08-06 17:31:46,290 INFO [trainer.py:765] (7/8) Epoch 14, batch 1800, train_loss[loss=2.97, NarTop10Accuracy=0.729, over 7074.00 frames. ], tot_loss[loss=3.185, NarTop10Accuracy=0.6893, over 5965.46 frames. ], batch size: 22, lr: 6.09e-03
2024-08-06 17:32:12,728 INFO [trainer.py:765] (7/8) Epoch 14, batch 1900, train_loss[loss=3.686, NarTop10Accuracy=0.5871, over 6399.00 frames. ], tot_loss[loss=3.207, NarTop10Accuracy=0.6848, over 6021.86 frames. ], batch size: 50, lr: 6.09e-03
2024-08-06 17:32:38,283 INFO [trainer.py:765] (7/8) Epoch 14, batch 2000, train_loss[loss=3.252, NarTop10Accuracy=0.6852, over 6189.00 frames. ], tot_loss[loss=3.217, NarTop10Accuracy=0.6827, over 6003.36 frames. ], batch size: 53, lr: 6.08e-03
2024-08-06 17:33:03,646 INFO [trainer.py:765] (7/8) Epoch 14, batch 2100, train_loss[loss=2.907, NarTop10Accuracy=0.7468, over 4782.00 frames. ], tot_loss[loss=3.217, NarTop10Accuracy=0.6827, over 5981.26 frames. ], batch size: 5, lr: 6.07e-03
2024-08-06 17:33:28,999 INFO [trainer.py:765] (7/8) Epoch 14, batch 2200, train_loss[loss=3.312, NarTop10Accuracy=0.6693, over 7242.00 frames. ], tot_loss[loss=3.211, NarTop10Accuracy=0.6838, over 5986.10 frames. ], batch size: 32, lr: 6.06e-03
2024-08-06 17:33:54,089 INFO [trainer.py:765] (7/8) Epoch 14, batch 2300, train_loss[loss=2.99, NarTop10Accuracy=0.728, over 5679.00 frames. ], tot_loss[loss=3.231, NarTop10Accuracy=0.68, over 5990.52 frames. ], batch size: 9, lr: 6.05e-03
2024-08-06 17:34:18,534 INFO [trainer.py:765] (7/8) Epoch 14, batch 2400, train_loss[loss=2.934, NarTop10Accuracy=0.7459, over 5235.00 frames. ], tot_loss[loss=3.232, NarTop10Accuracy=0.6793, over 5753.90 frames. ], batch size: 7, lr: 6.04e-03
2024-08-06 17:34:42,116 INFO [trainer.py:765] (7/8) Epoch 14, batch 2500, train_loss[loss=2.903, NarTop10Accuracy=0.7442, over 5094.00 frames. ], tot_loss[loss=3.203, NarTop10Accuracy=0.6849, over 5461.85 frames. ], batch size: 7, lr: 6.04e-03
2024-08-06 17:34:45,395 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 17:34:53,209 INFO [trainer.py:811] (7/8) Epoch 14, validation: loss=3.062, NarTop10Accuracy=0.7136, over 1905321.00 frames. 
2024-08-06 17:34:53,209 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 17:34:53,680 INFO [optim.py:386] (7/8) 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 17:35:09,823 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 17:36:11,738 INFO [trainer.py:765] (7/8) Epoch 15, batch 100, train_loss[loss=3.191, NarTop10Accuracy=0.6849, over 7092.00 frames. ], tot_loss[loss=3.229, NarTop10Accuracy=0.6806, over 2357.71 frames. ], batch size: 31, lr: 5.82e-03
2024-08-06 17:36:44,334 INFO [trainer.py:765] (7/8) Epoch 15, batch 200, train_loss[loss=3.41, NarTop10Accuracy=0.6413, over 6759.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.6888, over 3846.23 frames. ], batch size: 17, lr: 5.81e-03
2024-08-06 17:37:17,714 INFO [trainer.py:765] (7/8) Epoch 15, batch 300, train_loss[loss=3.425, NarTop10Accuracy=0.6377, over 7005.00 frames. ], tot_loss[loss=3.193, NarTop10Accuracy=0.6878, over 4655.63 frames. ], batch size: 22, lr: 5.80e-03
2024-08-06 17:37:48,904 INFO [trainer.py:765] (7/8) Epoch 15, batch 400, train_loss[loss=2.876, NarTop10Accuracy=0.7587, over 5151.00 frames. ], tot_loss[loss=3.191, NarTop10Accuracy=0.6881, over 5107.48 frames. ], batch size: 7, lr: 5.80e-03
2024-08-06 17:38:22,354 INFO [trainer.py:765] (7/8) Epoch 15, batch 500, train_loss[loss=2.803, NarTop10Accuracy=0.7673, over 6003.00 frames. ], tot_loss[loss=3.188, NarTop10Accuracy=0.6887, over 5391.20 frames. ], batch size: 11, lr: 5.79e-03
2024-08-06 17:38:53,094 INFO [trainer.py:765] (7/8) Epoch 15, batch 600, train_loss[loss=2.929, NarTop10Accuracy=0.7416, over 5676.00 frames. ], tot_loss[loss=3.201, NarTop10Accuracy=0.6858, over 5664.61 frames. ], batch size: 9, lr: 5.78e-03
2024-08-06 17:39:27,922 INFO [trainer.py:765] (7/8) Epoch 15, batch 700, train_loss[loss=2.947, NarTop10Accuracy=0.7441, over 5106.00 frames. ], tot_loss[loss=3.209, NarTop10Accuracy=0.6846, over 5753.05 frames. ], batch size: 6, lr: 5.77e-03
2024-08-06 17:40:05,565 INFO [trainer.py:765] (7/8) Epoch 15, batch 800, train_loss[loss=3.322, NarTop10Accuracy=0.6647, over 5187.00 frames. ], tot_loss[loss=3.227, NarTop10Accuracy=0.6807, over 5806.45 frames. ], batch size: 6, lr: 5.76e-03
2024-08-06 17:40:35,791 INFO [trainer.py:765] (7/8) Epoch 15, batch 900, train_loss[loss=3.393, NarTop10Accuracy=0.6465, over 6267.00 frames. ], tot_loss[loss=3.206, NarTop10Accuracy=0.6848, over 5807.82 frames. ], batch size: 13, lr: 5.76e-03
2024-08-06 17:41:11,251 INFO [trainer.py:765] (7/8) Epoch 15, batch 1000, train_loss[loss=3.196, NarTop10Accuracy=0.6862, over 6231.00 frames. ], tot_loss[loss=3.198, NarTop10Accuracy=0.6865, over 5919.13 frames. ], batch size: 13, lr: 5.75e-03
2024-08-06 17:41:46,452 INFO [trainer.py:765] (7/8) Epoch 15, batch 1100, train_loss[loss=3.143, NarTop10Accuracy=0.7015, over 6780.00 frames. ], tot_loss[loss=3.197, NarTop10Accuracy=0.6868, over 5938.63 frames. ], batch size: 17, lr: 5.74e-03
2024-08-06 17:42:19,456 INFO [trainer.py:765] (7/8) Epoch 15, batch 1200, train_loss[loss=3.445, NarTop10Accuracy=0.6353, over 7269.00 frames. ], tot_loss[loss=3.228, NarTop10Accuracy=0.6807, over 5930.30 frames. ], batch size: 31, lr: 5.73e-03
2024-08-06 17:42:54,428 INFO [trainer.py:765] (7/8) Epoch 15, batch 1300, train_loss[loss=3, NarTop10Accuracy=0.729, over 5073.00 frames. ], tot_loss[loss=3.213, NarTop10Accuracy=0.6833, over 6003.65 frames. ], batch size: 6, lr: 5.73e-03
2024-08-06 17:43:26,607 INFO [trainer.py:765] (7/8) Epoch 15, batch 1400, train_loss[loss=3.275, NarTop10Accuracy=0.6678, over 6066.00 frames. ], tot_loss[loss=3.222, NarTop10Accuracy=0.6816, over 6026.75 frames. ], batch size: 11, lr: 5.72e-03
2024-08-06 17:43:56,558 INFO [trainer.py:765] (7/8) Epoch 15, batch 1500, train_loss[loss=3.132, NarTop10Accuracy=0.7024, over 5784.00 frames. ], tot_loss[loss=3.229, NarTop10Accuracy=0.6798, over 5952.20 frames. ], batch size: 50, lr: 5.71e-03
2024-08-06 17:44:24,241 INFO [trainer.py:765] (7/8) Epoch 15, batch 1600, train_loss[loss=3.643, NarTop10Accuracy=0.597, over 6945.00 frames. ], tot_loss[loss=3.205, NarTop10Accuracy=0.6849, over 5940.72 frames. ], batch size: 22, lr: 5.70e-03
2024-08-06 17:44:50,856 INFO [trainer.py:765] (7/8) Epoch 15, batch 1700, train_loss[loss=3.008, NarTop10Accuracy=0.7301, over 6714.00 frames. ], tot_loss[loss=3.193, NarTop10Accuracy=0.6871, over 5914.53 frames. ], batch size: 14, lr: 5.70e-03
2024-08-06 17:45:17,294 INFO [trainer.py:765] (7/8) Epoch 15, batch 1800, train_loss[loss=3.181, NarTop10Accuracy=0.6871, over 7011.00 frames. ], tot_loss[loss=3.189, NarTop10Accuracy=0.6883, over 5957.57 frames. ], batch size: 22, lr: 5.69e-03
2024-08-06 17:45:43,679 INFO [trainer.py:765] (7/8) Epoch 15, batch 1900, train_loss[loss=3.133, NarTop10Accuracy=0.7038, over 5961.00 frames. ], tot_loss[loss=3.215, NarTop10Accuracy=0.6829, over 6016.40 frames. ], batch size: 50, lr: 5.68e-03
2024-08-06 17:45:53,541 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 17:46:01,743 INFO [trainer.py:811] (7/8) Epoch 15, validation: loss=3.006, NarTop10Accuracy=0.725, over 1905321.00 frames. 
2024-08-06 17:46:01,743 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 17:46:02,217 INFO [optim.py:386] (7/8) 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 17:46:17,372 INFO [trainer.py:765] (7/8) Epoch 15, batch 2000, train_loss[loss=3.226, NarTop10Accuracy=0.6789, over 6333.00 frames. ], tot_loss[loss=3.209, NarTop10Accuracy=0.684, over 5998.71 frames. ], batch size: 52, lr: 5.67e-03
2024-08-06 17:46:42,773 INFO [trainer.py:765] (7/8) Epoch 15, batch 2100, train_loss[loss=3.256, NarTop10Accuracy=0.6742, over 4833.00 frames. ], tot_loss[loss=3.201, NarTop10Accuracy=0.6853, over 5973.07 frames. ], batch size: 5, lr: 5.67e-03
2024-08-06 17:47:08,033 INFO [trainer.py:765] (7/8) Epoch 15, batch 2200, train_loss[loss=2.933, NarTop10Accuracy=0.7423, over 7218.00 frames. ], tot_loss[loss=3.208, NarTop10Accuracy=0.6837, over 6008.79 frames. ], batch size: 31, lr: 5.66e-03
2024-08-06 17:47:33,292 INFO [trainer.py:765] (7/8) Epoch 15, batch 2300, train_loss[loss=3.564, NarTop10Accuracy=0.6108, over 5619.00 frames. ], tot_loss[loss=3.212, NarTop10Accuracy=0.6832, over 6035.68 frames. ], batch size: 9, lr: 5.65e-03
2024-08-06 17:47:57,640 INFO [trainer.py:765] (7/8) Epoch 15, batch 2400, train_loss[loss=3.322, NarTop10Accuracy=0.6625, over 5190.00 frames. ], tot_loss[loss=3.186, NarTop10Accuracy=0.6885, over 5768.49 frames. ], batch size: 7, lr: 5.65e-03
2024-08-06 17:48:21,162 INFO [trainer.py:765] (7/8) Epoch 15, batch 2500, train_loss[loss=2.909, NarTop10Accuracy=0.738, over 5079.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6921, over 5469.49 frames. ], batch size: 7, lr: 5.64e-03
2024-08-06 17:48:41,220 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 17:49:41,222 INFO [trainer.py:765] (7/8) Epoch 16, batch 100, train_loss[loss=3.485, NarTop10Accuracy=0.6287, over 7815.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6969, over 2364.28 frames. ], batch size: 32, lr: 5.45e-03
2024-08-06 17:50:12,158 INFO [trainer.py:765] (7/8) Epoch 16, batch 200, train_loss[loss=2.873, NarTop10Accuracy=0.7493, over 6948.00 frames. ], tot_loss[loss=3.197, NarTop10Accuracy=0.687, over 3858.91 frames. ], batch size: 17, lr: 5.44e-03
2024-08-06 17:50:45,159 INFO [trainer.py:765] (7/8) Epoch 16, batch 300, train_loss[loss=3.151, NarTop10Accuracy=0.6947, over 7122.00 frames. ], tot_loss[loss=3.188, NarTop10Accuracy=0.6885, over 4673.96 frames. ], batch size: 22, lr: 5.43e-03
2024-08-06 17:51:15,976 INFO [trainer.py:765] (7/8) Epoch 16, batch 400, train_loss[loss=3.414, NarTop10Accuracy=0.6372, over 5100.00 frames. ], tot_loss[loss=3.193, NarTop10Accuracy=0.6879, over 5116.52 frames. ], batch size: 7, lr: 5.43e-03
2024-08-06 17:51:50,324 INFO [trainer.py:765] (7/8) Epoch 16, batch 500, train_loss[loss=2.99, NarTop10Accuracy=0.7397, over 6225.00 frames. ], tot_loss[loss=3.185, NarTop10Accuracy=0.6891, over 5388.69 frames. ], batch size: 11, lr: 5.42e-03
2024-08-06 17:52:24,252 INFO [trainer.py:765] (7/8) Epoch 16, batch 600, train_loss[loss=2.938, NarTop10Accuracy=0.7439, over 5769.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.688, over 5654.65 frames. ], batch size: 9, lr: 5.41e-03
2024-08-06 17:52:55,387 INFO [trainer.py:765] (7/8) Epoch 16, batch 700, train_loss[loss=2.99, NarTop10Accuracy=0.7294, over 5046.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.688, over 5715.45 frames. ], batch size: 6, lr: 5.41e-03
2024-08-06 17:53:33,816 INFO [trainer.py:765] (7/8) Epoch 16, batch 800, train_loss[loss=3.285, NarTop10Accuracy=0.673, over 5115.00 frames. ], tot_loss[loss=3.184, NarTop10Accuracy=0.6894, over 5760.78 frames. ], batch size: 6, lr: 5.40e-03
2024-08-06 17:54:03,923 INFO [trainer.py:765] (7/8) Epoch 16, batch 900, train_loss[loss=3.256, NarTop10Accuracy=0.6768, over 6045.00 frames. ], tot_loss[loss=3.172, NarTop10Accuracy=0.692, over 5787.84 frames. ], batch size: 13, lr: 5.39e-03
2024-08-06 17:54:37,608 INFO [trainer.py:765] (7/8) Epoch 16, batch 1000, train_loss[loss=2.978, NarTop10Accuracy=0.7275, over 6573.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6939, over 5912.69 frames. ], batch size: 14, lr: 5.39e-03
2024-08-06 17:55:17,197 INFO [trainer.py:765] (7/8) Epoch 16, batch 1100, train_loss[loss=3.138, NarTop10Accuracy=0.6962, over 6609.00 frames. ], tot_loss[loss=3.192, NarTop10Accuracy=0.6876, over 5958.90 frames. ], batch size: 17, lr: 5.38e-03
2024-08-06 17:55:46,210 INFO [trainer.py:765] (7/8) Epoch 16, batch 1200, train_loss[loss=3.385, NarTop10Accuracy=0.6453, over 7188.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6866, over 5942.01 frames. ], batch size: 31, lr: 5.37e-03
2024-08-06 17:56:22,776 INFO [trainer.py:765] (7/8) Epoch 16, batch 1300, train_loss[loss=3.433, NarTop10Accuracy=0.6395, over 5109.00 frames. ], tot_loss[loss=3.192, NarTop10Accuracy=0.6873, over 5989.95 frames. ], batch size: 6, lr: 5.37e-03
2024-08-06 17:56:44,648 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 17:56:53,428 INFO [trainer.py:811] (7/8) Epoch 16, validation: loss=3.112, NarTop10Accuracy=0.703, over 1905321.00 frames. 
2024-08-06 17:56:53,429 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 17:56:54,007 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 16, batch 1400, train_loss[loss=3.209, NarTop10Accuracy=0.6872, over 6096.00 frames. ], tot_loss[loss=3.186, NarTop10Accuracy=0.6887, over 6018.76 frames. ], batch size: 11, lr: 5.36e-03
2024-08-06 17:57:34,033 INFO [trainer.py:765] (7/8) Epoch 16, batch 1500, train_loss[loss=3.239, NarTop10Accuracy=0.6804, over 6225.00 frames. ], tot_loss[loss=3.182, NarTop10Accuracy=0.6896, over 5934.26 frames. ], batch size: 50, lr: 5.35e-03
2024-08-06 17:58:01,775 INFO [trainer.py:765] (7/8) Epoch 16, batch 1600, train_loss[loss=2.968, NarTop10Accuracy=0.7373, over 7188.00 frames. ], tot_loss[loss=3.179, NarTop10Accuracy=0.6904, over 5929.32 frames. ], batch size: 22, lr: 5.35e-03
2024-08-06 17:58:28,475 INFO [trainer.py:765] (7/8) Epoch 16, batch 1700, train_loss[loss=2.964, NarTop10Accuracy=0.7398, over 6579.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6866, over 5913.34 frames. ], batch size: 14, lr: 5.34e-03
2024-08-06 17:58:54,976 INFO [trainer.py:765] (7/8) Epoch 16, batch 1800, train_loss[loss=3.05, NarTop10Accuracy=0.7213, over 7344.00 frames. ], tot_loss[loss=3.184, NarTop10Accuracy=0.6893, over 5975.07 frames. ], batch size: 23, lr: 5.33e-03
2024-08-06 17:59:21,360 INFO [trainer.py:765] (7/8) Epoch 16, batch 1900, train_loss[loss=3.397, NarTop10Accuracy=0.6471, over 6486.00 frames. ], tot_loss[loss=3.208, NarTop10Accuracy=0.6846, over 6011.08 frames. ], batch size: 58, lr: 5.33e-03
2024-08-06 17:59:46,857 INFO [trainer.py:765] (7/8) Epoch 16, batch 2000, train_loss[loss=3.083, NarTop10Accuracy=0.7159, over 5799.00 frames. ], tot_loss[loss=3.173, NarTop10Accuracy=0.6915, over 5987.46 frames. ], batch size: 50, lr: 5.32e-03
2024-08-06 18:00:12,117 INFO [trainer.py:765] (7/8) Epoch 16, batch 2100, train_loss[loss=3.676, NarTop10Accuracy=0.5803, over 3969.00 frames. ], tot_loss[loss=3.201, NarTop10Accuracy=0.6859, over 5976.73 frames. ], batch size: 4, lr: 5.32e-03
2024-08-06 18:00:37,333 INFO [trainer.py:765] (7/8) Epoch 16, batch 2200, train_loss[loss=3.204, NarTop10Accuracy=0.695, over 7158.00 frames. ], tot_loss[loss=3.208, NarTop10Accuracy=0.6845, over 6019.45 frames. ], batch size: 31, lr: 5.31e-03
2024-08-06 18:01:02,502 INFO [trainer.py:765] (7/8) Epoch 16, batch 2300, train_loss[loss=3.03, NarTop10Accuracy=0.7247, over 5694.00 frames. ], tot_loss[loss=3.209, NarTop10Accuracy=0.684, over 6041.75 frames. ], batch size: 9, lr: 5.30e-03
2024-08-06 18:01:26,883 INFO [trainer.py:765] (7/8) Epoch 16, batch 2400, train_loss[loss=3.069, NarTop10Accuracy=0.7172, over 5058.00 frames. ], tot_loss[loss=3.193, NarTop10Accuracy=0.6876, over 5782.82 frames. ], batch size: 7, lr: 5.30e-03
2024-08-06 18:01:50,406 INFO [trainer.py:765] (7/8) Epoch 16, batch 2500, train_loss[loss=3.05, NarTop10Accuracy=0.7224, over 5100.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.6935, over 5481.86 frames. ], batch size: 7, lr: 5.29e-03
2024-08-06 18:02:10,737 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 18:03:08,531 INFO [trainer.py:765] (7/8) Epoch 17, batch 100, train_loss[loss=3.092, NarTop10Accuracy=0.7072, over 7338.00 frames. ], tot_loss[loss=3.133, NarTop10Accuracy=0.7, over 2352.40 frames. ], batch size: 31, lr: 5.12e-03
2024-08-06 18:03:45,145 INFO [trainer.py:765] (7/8) Epoch 17, batch 200, train_loss[loss=3.485, NarTop10Accuracy=0.6214, over 6717.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6973, over 3846.94 frames. ], batch size: 17, lr: 5.12e-03
2024-08-06 18:04:19,591 INFO [trainer.py:765] (7/8) Epoch 17, batch 300, train_loss[loss=3.326, NarTop10Accuracy=0.658, over 7122.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6931, over 4643.88 frames. ], batch size: 22, lr: 5.11e-03
2024-08-06 18:04:48,402 INFO [trainer.py:765] (7/8) Epoch 17, batch 400, train_loss[loss=3.227, NarTop10Accuracy=0.6771, over 5217.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6923, over 5093.64 frames. ], batch size: 7, lr: 5.10e-03
2024-08-06 18:05:24,680 INFO [trainer.py:765] (7/8) Epoch 17, batch 500, train_loss[loss=2.942, NarTop10Accuracy=0.7412, over 6147.00 frames. ], tot_loss[loss=3.156, NarTop10Accuracy=0.6959, over 5374.72 frames. ], batch size: 11, lr: 5.10e-03
2024-08-06 18:05:58,739 INFO [trainer.py:765] (7/8) Epoch 17, batch 600, train_loss[loss=3.032, NarTop10Accuracy=0.7228, over 5697.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6923, over 5631.62 frames. ], batch size: 9, lr: 5.09e-03
2024-08-06 18:06:32,475 INFO [trainer.py:765] (7/8) Epoch 17, batch 700, train_loss[loss=3.042, NarTop10Accuracy=0.7149, over 5247.00 frames. ], tot_loss[loss=3.172, NarTop10Accuracy=0.6919, over 5711.95 frames. ], batch size: 6, lr: 5.08e-03
2024-08-06 18:07:02,725 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 18:07:10,763 INFO [trainer.py:811] (7/8) Epoch 17, validation: loss=3.018, NarTop10Accuracy=0.7223, over 1905321.00 frames. 
2024-08-06 18:07:10,764 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 18:07:11,312 INFO [optim.py:386] (7/8) Clipping_scale=2.0, grad-norm quartiles 1.649e+02 2.005e+02 2.161e+02 2.341e+02 3.806e+02, threshold=4.323e+02, percent-clipped=0.0
2024-08-06 18:07:14,354 INFO [trainer.py:765] (7/8) Epoch 17, batch 800, train_loss[loss=3.097, NarTop10Accuracy=0.7101, over 5013.00 frames. ], tot_loss[loss=3.177, NarTop10Accuracy=0.6906, over 5784.21 frames. ], batch size: 6, lr: 5.08e-03
2024-08-06 18:07:49,721 INFO [trainer.py:765] (7/8) Epoch 17, batch 900, train_loss[loss=3.504, NarTop10Accuracy=0.6231, over 6138.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6949, over 5806.17 frames. ], batch size: 13, lr: 5.07e-03
2024-08-06 18:08:21,598 INFO [trainer.py:765] (7/8) Epoch 17, batch 1000, train_loss[loss=3.366, NarTop10Accuracy=0.6604, over 6852.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6922, over 5906.11 frames. ], batch size: 14, lr: 5.07e-03
2024-08-06 18:09:03,106 INFO [trainer.py:765] (7/8) Epoch 17, batch 1100, train_loss[loss=2.918, NarTop10Accuracy=0.7487, over 6843.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6924, over 5927.78 frames. ], batch size: 17, lr: 5.06e-03
2024-08-06 18:09:36,746 INFO [trainer.py:765] (7/8) Epoch 17, batch 1200, train_loss[loss=3.164, NarTop10Accuracy=0.6931, over 7122.00 frames. ], tot_loss[loss=3.173, NarTop10Accuracy=0.6911, over 5934.70 frames. ], batch size: 31, lr: 5.06e-03
2024-08-06 18:10:10,688 INFO [trainer.py:765] (7/8) Epoch 17, batch 1300, train_loss[loss=3.38, NarTop10Accuracy=0.6451, over 4920.00 frames. ], tot_loss[loss=3.176, NarTop10Accuracy=0.6904, over 5991.19 frames. ], batch size: 6, lr: 5.05e-03
2024-08-06 18:10:48,027 INFO [trainer.py:765] (7/8) Epoch 17, batch 1400, train_loss[loss=3.216, NarTop10Accuracy=0.6795, over 6144.00 frames. ], tot_loss[loss=3.181, NarTop10Accuracy=0.6895, over 6009.19 frames. ], batch size: 11, lr: 5.04e-03
2024-08-06 18:11:19,105 INFO [trainer.py:765] (7/8) Epoch 17, batch 1500, train_loss[loss=3.382, NarTop10Accuracy=0.6397, over 5979.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6923, over 5941.77 frames. ], batch size: 50, lr: 5.04e-03
2024-08-06 18:11:46,855 INFO [trainer.py:765] (7/8) Epoch 17, batch 1600, train_loss[loss=3.052, NarTop10Accuracy=0.7154, over 6936.00 frames. ], tot_loss[loss=3.159, NarTop10Accuracy=0.6945, over 5924.73 frames. ], batch size: 22, lr: 5.03e-03
2024-08-06 18:12:13,509 INFO [trainer.py:765] (7/8) Epoch 17, batch 1700, train_loss[loss=3.451, NarTop10Accuracy=0.6288, over 6123.00 frames. ], tot_loss[loss=3.172, NarTop10Accuracy=0.6916, over 5935.75 frames. ], batch size: 13, lr: 5.03e-03
2024-08-06 18:12:40,002 INFO [trainer.py:765] (7/8) Epoch 17, batch 1800, train_loss[loss=2.935, NarTop10Accuracy=0.7377, over 7185.00 frames. ], tot_loss[loss=3.179, NarTop10Accuracy=0.6897, over 5982.36 frames. ], batch size: 22, lr: 5.02e-03
2024-08-06 18:13:06,380 INFO [trainer.py:765] (7/8) Epoch 17, batch 1900, train_loss[loss=3.14, NarTop10Accuracy=0.6938, over 5589.00 frames. ], tot_loss[loss=3.188, NarTop10Accuracy=0.6882, over 6021.57 frames. ], batch size: 50, lr: 5.01e-03
2024-08-06 18:13:31,923 INFO [trainer.py:765] (7/8) Epoch 17, batch 2000, train_loss[loss=3.589, NarTop10Accuracy=0.6068, over 5697.00 frames. ], tot_loss[loss=3.162, NarTop10Accuracy=0.6936, over 5997.42 frames. ], batch size: 52, lr: 5.01e-03
2024-08-06 18:13:57,228 INFO [trainer.py:765] (7/8) Epoch 17, batch 2100, train_loss[loss=3.094, NarTop10Accuracy=0.7189, over 3870.00 frames. ], tot_loss[loss=3.172, NarTop10Accuracy=0.6916, over 5970.49 frames. ], batch size: 4, lr: 5.00e-03
2024-08-06 18:14:22,434 INFO [trainer.py:765] (7/8) Epoch 17, batch 2200, train_loss[loss=3.021, NarTop10Accuracy=0.7332, over 7659.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6864, over 6003.08 frames. ], batch size: 31, lr: 5.00e-03
2024-08-06 18:14:47,592 INFO [trainer.py:765] (7/8) Epoch 17, batch 2300, train_loss[loss=2.959, NarTop10Accuracy=0.73, over 5673.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.6878, over 6021.38 frames. ], batch size: 9, lr: 4.99e-03
2024-08-06 18:15:12,061 INFO [trainer.py:765] (7/8) Epoch 17, batch 2400, train_loss[loss=3.083, NarTop10Accuracy=0.7111, over 5130.00 frames. ], tot_loss[loss=3.189, NarTop10Accuracy=0.6877, over 5765.27 frames. ], batch size: 7, lr: 4.99e-03
2024-08-06 18:15:35,515 INFO [trainer.py:765] (7/8) Epoch 17, batch 2500, train_loss[loss=2.757, NarTop10Accuracy=0.7759, over 5211.00 frames. ], tot_loss[loss=3.172, NarTop10Accuracy=0.691, over 5463.09 frames. ], batch size: 7, lr: 4.98e-03
2024-08-06 18:15:55,360 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 18:16:49,908 INFO [trainer.py:765] (7/8) Epoch 18, batch 100, train_loss[loss=3.096, NarTop10Accuracy=0.7121, over 7041.00 frames. ], tot_loss[loss=3.181, NarTop10Accuracy=0.6905, over 2384.36 frames. ], batch size: 31, lr: 4.83e-03
2024-08-06 18:17:24,749 INFO [trainer.py:765] (7/8) Epoch 18, batch 200, train_loss[loss=2.967, NarTop10Accuracy=0.732, over 6957.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6937, over 3876.03 frames. ], batch size: 17, lr: 4.83e-03
2024-08-06 18:17:27,716 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 18:17:35,927 INFO [trainer.py:811] (7/8) Epoch 18, validation: loss=3.062, NarTop10Accuracy=0.7137, over 1905321.00 frames. 
2024-08-06 18:17:35,927 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 18:17:36,529 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 18, batch 300, train_loss[loss=3.456, NarTop10Accuracy=0.6349, over 7215.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6928, over 4675.78 frames. ], batch size: 22, lr: 4.82e-03
2024-08-06 18:18:38,183 INFO [trainer.py:765] (7/8) Epoch 18, batch 400, train_loss[loss=3.352, NarTop10Accuracy=0.6522, over 5733.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6961, over 5125.25 frames. ], batch size: 8, lr: 4.81e-03
2024-08-06 18:19:13,599 INFO [trainer.py:765] (7/8) Epoch 18, batch 500, train_loss[loss=2.99, NarTop10Accuracy=0.731, over 6042.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6962, over 5394.47 frames. ], batch size: 11, lr: 4.81e-03
2024-08-06 18:19:48,151 INFO [trainer.py:765] (7/8) Epoch 18, batch 600, train_loss[loss=3.463, NarTop10Accuracy=0.6274, over 5739.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.696, over 5639.57 frames. ], batch size: 9, lr: 4.80e-03
2024-08-06 18:20:23,870 INFO [trainer.py:765] (7/8) Epoch 18, batch 700, train_loss[loss=3.331, NarTop10Accuracy=0.6533, over 4875.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6945, over 5708.38 frames. ], batch size: 6, lr: 4.80e-03
2024-08-06 18:21:01,026 INFO [trainer.py:765] (7/8) Epoch 18, batch 800, train_loss[loss=2.759, NarTop10Accuracy=0.7739, over 5034.00 frames. ], tot_loss[loss=3.17, NarTop10Accuracy=0.6915, over 5788.78 frames. ], batch size: 6, lr: 4.79e-03
2024-08-06 18:21:32,409 INFO [trainer.py:765] (7/8) Epoch 18, batch 900, train_loss[loss=2.992, NarTop10Accuracy=0.729, over 6363.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6957, over 5801.80 frames. ], batch size: 13, lr: 4.79e-03
2024-08-06 18:22:11,192 INFO [trainer.py:765] (7/8) Epoch 18, batch 1000, train_loss[loss=2.957, NarTop10Accuracy=0.7335, over 6687.00 frames. ], tot_loss[loss=3.167, NarTop10Accuracy=0.6925, over 5904.16 frames. ], batch size: 14, lr: 4.78e-03
2024-08-06 18:22:46,969 INFO [trainer.py:765] (7/8) Epoch 18, batch 1100, train_loss[loss=3.378, NarTop10Accuracy=0.6458, over 6762.00 frames. ], tot_loss[loss=3.165, NarTop10Accuracy=0.6928, over 5954.59 frames. ], batch size: 17, lr: 4.78e-03
2024-08-06 18:23:18,605 INFO [trainer.py:765] (7/8) Epoch 18, batch 1200, train_loss[loss=3.67, NarTop10Accuracy=0.5889, over 7443.00 frames. ], tot_loss[loss=3.178, NarTop10Accuracy=0.6899, over 5941.77 frames. ], batch size: 31, lr: 4.77e-03
2024-08-06 18:24:00,099 INFO [trainer.py:765] (7/8) Epoch 18, batch 1300, train_loss[loss=2.899, NarTop10Accuracy=0.7487, over 5019.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.6935, over 6009.95 frames. ], batch size: 6, lr: 4.77e-03
2024-08-06 18:24:29,574 INFO [trainer.py:765] (7/8) Epoch 18, batch 1400, train_loss[loss=2.955, NarTop10Accuracy=0.7424, over 6051.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.6937, over 6032.54 frames. ], batch size: 11, lr: 4.76e-03
2024-08-06 18:25:00,307 INFO [trainer.py:765] (7/8) Epoch 18, batch 1500, train_loss[loss=3.124, NarTop10Accuracy=0.7048, over 5967.00 frames. ], tot_loss[loss=3.153, NarTop10Accuracy=0.695, over 5958.76 frames. ], batch size: 50, lr: 4.76e-03
2024-08-06 18:25:28,085 INFO [trainer.py:765] (7/8) Epoch 18, batch 1600, train_loss[loss=3.012, NarTop10Accuracy=0.7264, over 7128.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.6933, over 5933.80 frames. ], batch size: 22, lr: 4.75e-03
2024-08-06 18:25:54,688 INFO [trainer.py:765] (7/8) Epoch 18, batch 1700, train_loss[loss=3.134, NarTop10Accuracy=0.7055, over 6528.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6942, over 5916.73 frames. ], batch size: 14, lr: 4.75e-03
2024-08-06 18:26:21,196 INFO [trainer.py:765] (7/8) Epoch 18, batch 1800, train_loss[loss=3.426, NarTop10Accuracy=0.6324, over 7278.00 frames. ], tot_loss[loss=3.156, NarTop10Accuracy=0.6941, over 5976.35 frames. ], batch size: 23, lr: 4.74e-03
2024-08-06 18:26:47,567 INFO [trainer.py:765] (7/8) Epoch 18, batch 1900, train_loss[loss=3.17, NarTop10Accuracy=0.6958, over 6099.00 frames. ], tot_loss[loss=3.17, NarTop10Accuracy=0.6916, over 6034.37 frames. ], batch size: 50, lr: 4.74e-03
2024-08-06 18:27:13,176 INFO [trainer.py:765] (7/8) Epoch 18, batch 2000, train_loss[loss=3.143, NarTop10Accuracy=0.7025, over 6267.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6923, over 6021.81 frames. ], batch size: 50, lr: 4.73e-03
2024-08-06 18:27:38,529 INFO [trainer.py:765] (7/8) Epoch 18, batch 2100, train_loss[loss=3.32, NarTop10Accuracy=0.6537, over 3918.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.6941, over 5999.59 frames. ], batch size: 4, lr: 4.73e-03
2024-08-06 18:28:03,812 INFO [trainer.py:765] (7/8) Epoch 18, batch 2200, train_loss[loss=2.986, NarTop10Accuracy=0.7299, over 7029.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6935, over 6023.94 frames. ], batch size: 31, lr: 4.72e-03
2024-08-06 18:28:06,571 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 18:28:14,649 INFO [trainer.py:811] (7/8) Epoch 18, validation: loss=3.028, NarTop10Accuracy=0.7201, over 1905321.00 frames. 
2024-08-06 18:28:14,650 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 18:28:15,147 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 18, batch 2300, train_loss[loss=2.736, NarTop10Accuracy=0.787, over 5814.00 frames. ], tot_loss[loss=3.175, NarTop10Accuracy=0.691, over 6040.00 frames. ], batch size: 9, lr: 4.72e-03
2024-08-06 18:29:01,592 INFO [trainer.py:765] (7/8) Epoch 18, batch 2400, train_loss[loss=2.884, NarTop10Accuracy=0.7402, over 5070.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6957, over 5775.97 frames. ], batch size: 7, lr: 4.71e-03
2024-08-06 18:29:25,027 INFO [trainer.py:765] (7/8) Epoch 18, batch 2500, train_loss[loss=2.981, NarTop10Accuracy=0.7269, over 5328.00 frames. ], tot_loss[loss=3.129, NarTop10Accuracy=0.6995, over 5467.81 frames. ], batch size: 7, lr: 4.71e-03
2024-08-06 18:29:45,270 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 18:30:41,232 INFO [trainer.py:765] (7/8) Epoch 19, batch 100, train_loss[loss=2.966, NarTop10Accuracy=0.7307, over 7503.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.6938, over 2366.76 frames. ], batch size: 32, lr: 4.57e-03
2024-08-06 18:31:15,603 INFO [trainer.py:765] (7/8) Epoch 19, batch 200, train_loss[loss=2.857, NarTop10Accuracy=0.753, over 6816.00 frames. ], tot_loss[loss=3.159, NarTop10Accuracy=0.6938, over 3848.53 frames. ], batch size: 17, lr: 4.57e-03
2024-08-06 18:31:47,468 INFO [trainer.py:765] (7/8) Epoch 19, batch 300, train_loss[loss=3.417, NarTop10Accuracy=0.6451, over 7275.00 frames. ], tot_loss[loss=3.14, NarTop10Accuracy=0.698, over 4649.18 frames. ], batch size: 22, lr: 4.56e-03
2024-08-06 18:32:20,355 INFO [trainer.py:765] (7/8) Epoch 19, batch 400, train_loss[loss=3.171, NarTop10Accuracy=0.6975, over 5259.00 frames. ], tot_loss[loss=3.143, NarTop10Accuracy=0.6971, over 5096.51 frames. ], batch size: 7, lr: 4.56e-03
2024-08-06 18:32:50,335 INFO [trainer.py:765] (7/8) Epoch 19, batch 500, train_loss[loss=3.025, NarTop10Accuracy=0.7204, over 6012.00 frames. ], tot_loss[loss=3.137, NarTop10Accuracy=0.6984, over 5371.32 frames. ], batch size: 11, lr: 4.55e-03
2024-08-06 18:33:29,610 INFO [trainer.py:765] (7/8) Epoch 19, batch 600, train_loss[loss=2.921, NarTop10Accuracy=0.7388, over 5742.00 frames. ], tot_loss[loss=3.143, NarTop10Accuracy=0.6969, over 5639.91 frames. ], batch size: 9, lr: 4.55e-03
2024-08-06 18:34:03,592 INFO [trainer.py:765] (7/8) Epoch 19, batch 700, train_loss[loss=2.802, NarTop10Accuracy=0.7763, over 5094.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6966, over 5719.34 frames. ], batch size: 6, lr: 4.54e-03
2024-08-06 18:34:35,179 INFO [trainer.py:765] (7/8) Epoch 19, batch 800, train_loss[loss=3.114, NarTop10Accuracy=0.6985, over 4362.00 frames. ], tot_loss[loss=3.153, NarTop10Accuracy=0.6954, over 5774.86 frames. ], batch size: 5, lr: 4.54e-03
2024-08-06 18:35:10,263 INFO [trainer.py:765] (7/8) Epoch 19, batch 900, train_loss[loss=2.975, NarTop10Accuracy=0.7331, over 6702.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6972, over 5802.55 frames. ], batch size: 14, lr: 4.53e-03
2024-08-06 18:35:48,638 INFO [trainer.py:765] (7/8) Epoch 19, batch 1000, train_loss[loss=3.346, NarTop10Accuracy=0.6622, over 6729.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6964, over 5901.33 frames. ], batch size: 14, lr: 4.53e-03
2024-08-06 18:36:20,939 INFO [trainer.py:765] (7/8) Epoch 19, batch 1100, train_loss[loss=3.027, NarTop10Accuracy=0.7363, over 6873.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.6942, over 5933.50 frames. ], batch size: 17, lr: 4.52e-03
2024-08-06 18:36:57,130 INFO [trainer.py:765] (7/8) Epoch 19, batch 1200, train_loss[loss=2.953, NarTop10Accuracy=0.7376, over 7320.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6922, over 5931.50 frames. ], batch size: 32, lr: 4.52e-03
2024-08-06 18:37:35,315 INFO [trainer.py:765] (7/8) Epoch 19, batch 1300, train_loss[loss=2.773, NarTop10Accuracy=0.7719, over 4395.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.6937, over 5996.48 frames. ], batch size: 5, lr: 4.51e-03
2024-08-06 18:38:04,680 INFO [trainer.py:765] (7/8) Epoch 19, batch 1400, train_loss[loss=2.879, NarTop10Accuracy=0.7558, over 6048.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6929, over 6000.74 frames. ], batch size: 11, lr: 4.51e-03
2024-08-06 18:38:34,551 INFO [trainer.py:765] (7/8) Epoch 19, batch 1500, train_loss[loss=3.369, NarTop10Accuracy=0.6585, over 5928.00 frames. ], tot_loss[loss=3.147, NarTop10Accuracy=0.6969, over 5953.15 frames. ], batch size: 50, lr: 4.50e-03
2024-08-06 18:39:02,311 INFO [trainer.py:765] (7/8) Epoch 19, batch 1600, train_loss[loss=3.336, NarTop10Accuracy=0.6555, over 7077.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6967, over 5959.05 frames. ], batch size: 22, lr: 4.50e-03
2024-08-06 18:39:11,591 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 18:39:19,795 INFO [trainer.py:811] (7/8) Epoch 19, validation: loss=2.958, NarTop10Accuracy=0.7345, over 1905321.00 frames. 
2024-08-06 18:39:19,795 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 18:39:20,378 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 19, batch 1700, train_loss[loss=3.545, NarTop10Accuracy=0.6131, over 6255.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6961, over 5925.74 frames. ], batch size: 13, lr: 4.49e-03
2024-08-06 18:40:03,789 INFO [trainer.py:765] (7/8) Epoch 19, batch 1800, train_loss[loss=3.603, NarTop10Accuracy=0.6016, over 7125.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6953, over 5978.46 frames. ], batch size: 22, lr: 4.49e-03
2024-08-06 18:40:30,217 INFO [trainer.py:765] (7/8) Epoch 19, batch 1900, train_loss[loss=3.086, NarTop10Accuracy=0.7117, over 6378.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6956, over 6028.62 frames. ], batch size: 52, lr: 4.49e-03
2024-08-06 18:40:55,793 INFO [trainer.py:765] (7/8) Epoch 19, batch 2000, train_loss[loss=3.349, NarTop10Accuracy=0.6532, over 6513.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6952, over 5997.64 frames. ], batch size: 50, lr: 4.48e-03
2024-08-06 18:41:21,183 INFO [trainer.py:765] (7/8) Epoch 19, batch 2100, train_loss[loss=3.009, NarTop10Accuracy=0.7213, over 3996.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6973, over 5976.71 frames. ], batch size: 4, lr: 4.48e-03
2024-08-06 18:41:46,455 INFO [trainer.py:765] (7/8) Epoch 19, batch 2200, train_loss[loss=3.197, NarTop10Accuracy=0.6853, over 7419.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6958, over 6018.63 frames. ], batch size: 31, lr: 4.47e-03
2024-08-06 18:42:11,559 INFO [trainer.py:765] (7/8) Epoch 19, batch 2300, train_loss[loss=3.132, NarTop10Accuracy=0.6989, over 5712.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6922, over 6029.06 frames. ], batch size: 9, lr: 4.47e-03
2024-08-06 18:42:35,986 INFO [trainer.py:765] (7/8) Epoch 19, batch 2400, train_loss[loss=2.826, NarTop10Accuracy=0.7546, over 5088.00 frames. ], tot_loss[loss=3.147, NarTop10Accuracy=0.6967, over 5788.15 frames. ], batch size: 7, lr: 4.46e-03
2024-08-06 18:42:59,689 INFO [trainer.py:765] (7/8) Epoch 19, batch 2500, train_loss[loss=2.713, NarTop10Accuracy=0.778, over 5043.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7007, over 5491.02 frames. ], batch size: 7, lr: 4.46e-03
2024-08-06 18:43:19,345 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 18:44:22,974 INFO [trainer.py:765] (7/8) Epoch 20, batch 100, train_loss[loss=3.204, NarTop10Accuracy=0.6864, over 7194.00 frames. ], tot_loss[loss=3.175, NarTop10Accuracy=0.6906, over 2367.58 frames. ], batch size: 31, lr: 4.34e-03
2024-08-06 18:44:58,379 INFO [trainer.py:765] (7/8) Epoch 20, batch 200, train_loss[loss=3.423, NarTop10Accuracy=0.6344, over 6819.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.7004, over 3857.76 frames. ], batch size: 17, lr: 4.33e-03
2024-08-06 18:45:32,279 INFO [trainer.py:765] (7/8) Epoch 20, batch 300, train_loss[loss=3.408, NarTop10Accuracy=0.6385, over 6888.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7027, over 4663.88 frames. ], batch size: 22, lr: 4.33e-03
2024-08-06 18:46:05,128 INFO [trainer.py:765] (7/8) Epoch 20, batch 400, train_loss[loss=2.84, NarTop10Accuracy=0.7613, over 5106.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7021, over 5101.36 frames. ], batch size: 7, lr: 4.32e-03
2024-08-06 18:46:35,770 INFO [trainer.py:765] (7/8) Epoch 20, batch 500, train_loss[loss=2.91, NarTop10Accuracy=0.7495, over 6036.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.6999, over 5375.02 frames. ], batch size: 11, lr: 4.32e-03
2024-08-06 18:47:13,255 INFO [trainer.py:765] (7/8) Epoch 20, batch 600, train_loss[loss=2.965, NarTop10Accuracy=0.7254, over 5751.00 frames. ], tot_loss[loss=3.123, NarTop10Accuracy=0.7007, over 5646.12 frames. ], batch size: 9, lr: 4.31e-03
2024-08-06 18:47:44,481 INFO [trainer.py:765] (7/8) Epoch 20, batch 700, train_loss[loss=2.871, NarTop10Accuracy=0.7615, over 4290.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7028, over 5728.64 frames. ], batch size: 5, lr: 4.31e-03
2024-08-06 18:48:21,016 INFO [trainer.py:765] (7/8) Epoch 20, batch 800, train_loss[loss=2.752, NarTop10Accuracy=0.7785, over 5187.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7003, over 5786.39 frames. ], batch size: 6, lr: 4.31e-03
2024-08-06 18:48:56,535 INFO [trainer.py:765] (7/8) Epoch 20, batch 900, train_loss[loss=2.907, NarTop10Accuracy=0.751, over 6423.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.701, over 5800.54 frames. ], batch size: 13, lr: 4.30e-03
2024-08-06 18:49:29,805 INFO [trainer.py:765] (7/8) Epoch 20, batch 1000, train_loss[loss=3.255, NarTop10Accuracy=0.6706, over 6570.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6958, over 5909.02 frames. ], batch size: 14, lr: 4.30e-03
2024-08-06 18:49:52,237 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 18:50:00,326 INFO [trainer.py:811] (7/8) Epoch 20, validation: loss=2.962, NarTop10Accuracy=0.7336, over 1905321.00 frames. 
2024-08-06 18:50:00,327 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 18:50:00,875 INFO [optim.py:386] (7/8) 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 18:50:15,427 INFO [trainer.py:765] (7/8) Epoch 20, batch 1100, train_loss[loss=3.191, NarTop10Accuracy=0.6885, over 6879.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6968, over 5931.50 frames. ], batch size: 17, lr: 4.29e-03
2024-08-06 18:50:53,776 INFO [trainer.py:765] (7/8) Epoch 20, batch 1200, train_loss[loss=2.941, NarTop10Accuracy=0.7376, over 7266.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6965, over 5936.47 frames. ], batch size: 32, lr: 4.29e-03
2024-08-06 18:51:25,130 INFO [trainer.py:765] (7/8) Epoch 20, batch 1300, train_loss[loss=3.158, NarTop10Accuracy=0.6864, over 5010.00 frames. ], tot_loss[loss=3.141, NarTop10Accuracy=0.6974, over 6000.29 frames. ], batch size: 6, lr: 4.29e-03
2024-08-06 18:51:59,315 INFO [trainer.py:765] (7/8) Epoch 20, batch 1400, train_loss[loss=2.972, NarTop10Accuracy=0.7252, over 6009.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.6987, over 6007.65 frames. ], batch size: 11, lr: 4.28e-03
2024-08-06 18:52:32,806 INFO [trainer.py:765] (7/8) Epoch 20, batch 1500, train_loss[loss=3.345, NarTop10Accuracy=0.6616, over 6354.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6964, over 5950.98 frames. ], batch size: 50, lr: 4.28e-03
2024-08-06 18:53:00,635 INFO [trainer.py:765] (7/8) Epoch 20, batch 1600, train_loss[loss=2.948, NarTop10Accuracy=0.7434, over 7209.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6959, over 5916.44 frames. ], batch size: 22, lr: 4.27e-03
2024-08-06 18:53:27,328 INFO [trainer.py:765] (7/8) Epoch 20, batch 1700, train_loss[loss=3.415, NarTop10Accuracy=0.6414, over 6720.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6966, over 5904.26 frames. ], batch size: 14, lr: 4.27e-03
2024-08-06 18:53:53,851 INFO [trainer.py:765] (7/8) Epoch 20, batch 1800, train_loss[loss=3.118, NarTop10Accuracy=0.7061, over 7290.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.6994, over 5965.84 frames. ], batch size: 22, lr: 4.26e-03
2024-08-06 18:54:20,316 INFO [trainer.py:765] (7/8) Epoch 20, batch 1900, train_loss[loss=3.082, NarTop10Accuracy=0.7153, over 5940.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.695, over 6001.11 frames. ], batch size: 50, lr: 4.26e-03
2024-08-06 18:54:45,890 INFO [trainer.py:765] (7/8) Epoch 20, batch 2000, train_loss[loss=3.653, NarTop10Accuracy=0.5897, over 6102.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.6937, over 5995.70 frames. ], batch size: 50, lr: 4.26e-03
2024-08-06 18:55:11,182 INFO [trainer.py:765] (7/8) Epoch 20, batch 2100, train_loss[loss=3.363, NarTop10Accuracy=0.6481, over 4842.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.696, over 5970.58 frames. ], batch size: 5, lr: 4.25e-03
2024-08-06 18:55:36,414 INFO [trainer.py:765] (7/8) Epoch 20, batch 2200, train_loss[loss=2.881, NarTop10Accuracy=0.7531, over 7212.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6951, over 6005.16 frames. ], batch size: 31, lr: 4.25e-03
2024-08-06 18:56:01,636 INFO [trainer.py:765] (7/8) Epoch 20, batch 2300, train_loss[loss=3.003, NarTop10Accuracy=0.7207, over 5715.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6922, over 6034.43 frames. ], batch size: 9, lr: 4.24e-03
2024-08-06 18:56:26,050 INFO [trainer.py:765] (7/8) Epoch 20, batch 2400, train_loss[loss=2.869, NarTop10Accuracy=0.7532, over 5148.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6953, over 5780.03 frames. ], batch size: 7, lr: 4.24e-03
2024-08-06 18:56:49,566 INFO [trainer.py:765] (7/8) Epoch 20, batch 2500, train_loss[loss=2.919, NarTop10Accuracy=0.7419, over 5046.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7025, over 5463.22 frames. ], batch size: 7, lr: 4.24e-03
2024-08-06 18:57:09,582 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 18:58:09,585 INFO [trainer.py:765] (7/8) Epoch 21, batch 100, train_loss[loss=3.321, NarTop10Accuracy=0.665, over 7629.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7043, over 2366.29 frames. ], batch size: 32, lr: 4.13e-03
2024-08-06 18:58:40,418 INFO [trainer.py:765] (7/8) Epoch 21, batch 200, train_loss[loss=2.861, NarTop10Accuracy=0.7631, over 6687.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7015, over 3849.21 frames. ], batch size: 17, lr: 4.12e-03
2024-08-06 18:59:13,334 INFO [trainer.py:765] (7/8) Epoch 21, batch 300, train_loss[loss=2.831, NarTop10Accuracy=0.7584, over 7125.00 frames. ], tot_loss[loss=3.121, NarTop10Accuracy=0.7013, over 4669.50 frames. ], batch size: 22, lr: 4.12e-03
2024-08-06 18:59:48,151 INFO [trainer.py:765] (7/8) Epoch 21, batch 400, train_loss[loss=2.886, NarTop10Accuracy=0.7567, over 5040.00 frames. ], tot_loss[loss=3.105, NarTop10Accuracy=0.7046, over 5106.75 frames. ], batch size: 7, lr: 4.11e-03
2024-08-06 19:00:16,841 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 19:00:25,075 INFO [trainer.py:811] (7/8) Epoch 21, validation: loss=2.992, NarTop10Accuracy=0.7268, over 1905321.00 frames. 
2024-08-06 19:00:25,076 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 19:00:25,622 INFO [optim.py:386] (7/8) Clipping_scale=2.0, grad-norm quartiles 1.727e+02 2.071e+02 2.224e+02 2.387e+02 3.839e+02, threshold=4.447e+02, percent-clipped=0.0
2024-08-06 19:00:29,890 INFO [trainer.py:765] (7/8) Epoch 21, batch 500, train_loss[loss=2.827, NarTop10Accuracy=0.7581, over 6183.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7026, over 5382.68 frames. ], batch size: 11, lr: 4.11e-03
2024-08-06 19:01:03,328 INFO [trainer.py:765] (7/8) Epoch 21, batch 600, train_loss[loss=3.382, NarTop10Accuracy=0.6417, over 5658.00 frames. ], tot_loss[loss=3.106, NarTop10Accuracy=0.705, over 5641.98 frames. ], batch size: 9, lr: 4.11e-03
2024-08-06 19:01:39,388 INFO [trainer.py:765] (7/8) Epoch 21, batch 700, train_loss[loss=2.838, NarTop10Accuracy=0.7588, over 5136.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7028, over 5729.39 frames. ], batch size: 6, lr: 4.10e-03
2024-08-06 19:02:18,047 INFO [trainer.py:765] (7/8) Epoch 21, batch 800, train_loss[loss=3.071, NarTop10Accuracy=0.7127, over 5112.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.7007, over 5776.56 frames. ], batch size: 6, lr: 4.10e-03
2024-08-06 19:02:48,663 INFO [trainer.py:765] (7/8) Epoch 21, batch 900, train_loss[loss=2.943, NarTop10Accuracy=0.7348, over 6699.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7007, over 5796.95 frames. ], batch size: 14, lr: 4.09e-03
2024-08-06 19:03:25,800 INFO [trainer.py:765] (7/8) Epoch 21, batch 1000, train_loss[loss=3.09, NarTop10Accuracy=0.7077, over 6543.00 frames. ], tot_loss[loss=3.132, NarTop10Accuracy=0.6992, over 5889.21 frames. ], batch size: 14, lr: 4.09e-03
2024-08-06 19:04:07,206 INFO [trainer.py:765] (7/8) Epoch 21, batch 1100, train_loss[loss=3.446, NarTop10Accuracy=0.6386, over 6819.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6965, over 5941.68 frames. ], batch size: 17, lr: 4.09e-03
2024-08-06 19:04:38,462 INFO [trainer.py:765] (7/8) Epoch 21, batch 1200, train_loss[loss=3.365, NarTop10Accuracy=0.6514, over 7116.00 frames. ], tot_loss[loss=3.13, NarTop10Accuracy=0.6997, over 5942.32 frames. ], batch size: 31, lr: 4.08e-03
2024-08-06 19:05:15,316 INFO [trainer.py:765] (7/8) Epoch 21, batch 1300, train_loss[loss=2.696, NarTop10Accuracy=0.789, over 5199.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7046, over 6005.52 frames. ], batch size: 6, lr: 4.08e-03
2024-08-06 19:05:55,559 INFO [trainer.py:765] (7/8) Epoch 21, batch 1400, train_loss[loss=3.482, NarTop10Accuracy=0.633, over 6039.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7036, over 6011.71 frames. ], batch size: 11, lr: 4.07e-03
2024-08-06 19:06:23,600 INFO [trainer.py:765] (7/8) Epoch 21, batch 1500, train_loss[loss=3.275, NarTop10Accuracy=0.6643, over 6249.00 frames. ], tot_loss[loss=3.133, NarTop10Accuracy=0.6993, over 5965.56 frames. ], batch size: 50, lr: 4.07e-03
2024-08-06 19:06:51,461 INFO [trainer.py:765] (7/8) Epoch 21, batch 1600, train_loss[loss=3.004, NarTop10Accuracy=0.7259, over 7158.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.6991, over 5940.59 frames. ], batch size: 22, lr: 4.07e-03
2024-08-06 19:07:18,211 INFO [trainer.py:765] (7/8) Epoch 21, batch 1700, train_loss[loss=3.205, NarTop10Accuracy=0.6824, over 6540.00 frames. ], tot_loss[loss=3.141, NarTop10Accuracy=0.6978, over 5934.42 frames. ], batch size: 14, lr: 4.06e-03
2024-08-06 19:07:44,809 INFO [trainer.py:765] (7/8) Epoch 21, batch 1800, train_loss[loss=2.797, NarTop10Accuracy=0.7716, over 7206.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.699, over 5994.56 frames. ], batch size: 22, lr: 4.06e-03
2024-08-06 19:08:11,369 INFO [trainer.py:765] (7/8) Epoch 21, batch 1900, train_loss[loss=3.695, NarTop10Accuracy=0.5825, over 5793.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6972, over 6033.93 frames. ], batch size: 50, lr: 4.06e-03
2024-08-06 19:08:37,105 INFO [trainer.py:765] (7/8) Epoch 21, batch 2000, train_loss[loss=3.506, NarTop10Accuracy=0.6297, over 5997.00 frames. ], tot_loss[loss=3.131, NarTop10Accuracy=0.6997, over 6014.99 frames. ], batch size: 50, lr: 4.05e-03
2024-08-06 19:09:02,507 INFO [trainer.py:765] (7/8) Epoch 21, batch 2100, train_loss[loss=2.912, NarTop10Accuracy=0.743, over 3915.00 frames. ], tot_loss[loss=3.142, NarTop10Accuracy=0.6969, over 5988.29 frames. ], batch size: 4, lr: 4.05e-03
2024-08-06 19:09:27,891 INFO [trainer.py:765] (7/8) Epoch 21, batch 2200, train_loss[loss=3, NarTop10Accuracy=0.7402, over 7056.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6957, over 6016.10 frames. ], batch size: 31, lr: 4.04e-03
2024-08-06 19:09:53,222 INFO [trainer.py:765] (7/8) Epoch 21, batch 2300, train_loss[loss=2.926, NarTop10Accuracy=0.7447, over 5688.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.694, over 6023.30 frames. ], batch size: 9, lr: 4.04e-03
2024-08-06 19:10:17,596 INFO [trainer.py:765] (7/8) Epoch 21, batch 2400, train_loss[loss=3.436, NarTop10Accuracy=0.635, over 5130.00 frames. ], tot_loss[loss=3.142, NarTop10Accuracy=0.6972, over 5768.75 frames. ], batch size: 7, lr: 4.04e-03
2024-08-06 19:10:37,229 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 19:10:45,275 INFO [trainer.py:811] (7/8) Epoch 21, validation: loss=2.971, NarTop10Accuracy=0.7316, over 1905321.00 frames. 
2024-08-06 19:10:45,275 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 19:10:45,741 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 21, batch 2500, train_loss[loss=3.372, NarTop10Accuracy=0.6538, over 5145.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7051, over 5483.22 frames. ], batch size: 7, lr: 4.03e-03
2024-08-06 19:11:08,992 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 19:12:09,054 INFO [trainer.py:765] (7/8) Epoch 22, batch 100, train_loss[loss=2.853, NarTop10Accuracy=0.762, over 7284.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7099, over 2367.91 frames. ], batch size: 31, lr: 3.93e-03
2024-08-06 19:12:44,462 INFO [trainer.py:765] (7/8) Epoch 22, batch 200, train_loss[loss=3.248, NarTop10Accuracy=0.6748, over 6861.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7069, over 3859.88 frames. ], batch size: 17, lr: 3.93e-03
2024-08-06 19:13:14,533 INFO [trainer.py:765] (7/8) Epoch 22, batch 300, train_loss[loss=2.912, NarTop10Accuracy=0.7441, over 7137.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7071, over 4650.27 frames. ], batch size: 22, lr: 3.93e-03
2024-08-06 19:13:49,229 INFO [trainer.py:765] (7/8) Epoch 22, batch 400, train_loss[loss=2.846, NarTop10Accuracy=0.7442, over 4980.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7082, over 5100.47 frames. ], batch size: 7, lr: 3.92e-03
2024-08-06 19:14:24,850 INFO [trainer.py:765] (7/8) Epoch 22, batch 500, train_loss[loss=3.138, NarTop10Accuracy=0.6982, over 6189.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.708, over 5385.14 frames. ], batch size: 11, lr: 3.92e-03
2024-08-06 19:14:55,701 INFO [trainer.py:765] (7/8) Epoch 22, batch 600, train_loss[loss=2.912, NarTop10Accuracy=0.7312, over 5727.00 frames. ], tot_loss[loss=3.119, NarTop10Accuracy=0.7013, over 5645.81 frames. ], batch size: 9, lr: 3.92e-03
2024-08-06 19:15:30,867 INFO [trainer.py:765] (7/8) Epoch 22, batch 700, train_loss[loss=3.505, NarTop10Accuracy=0.6228, over 5046.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7005, over 5706.51 frames. ], batch size: 6, lr: 3.91e-03
2024-08-06 19:16:10,665 INFO [trainer.py:765] (7/8) Epoch 22, batch 800, train_loss[loss=2.975, NarTop10Accuracy=0.7295, over 4212.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7023, over 5768.12 frames. ], batch size: 5, lr: 3.91e-03
2024-08-06 19:16:40,952 INFO [trainer.py:765] (7/8) Epoch 22, batch 900, train_loss[loss=2.924, NarTop10Accuracy=0.7478, over 6657.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7025, over 5783.60 frames. ], batch size: 14, lr: 3.90e-03
2024-08-06 19:17:16,433 INFO [trainer.py:765] (7/8) Epoch 22, batch 1000, train_loss[loss=3.045, NarTop10Accuracy=0.7222, over 6222.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7034, over 5902.74 frames. ], batch size: 13, lr: 3.90e-03
2024-08-06 19:17:52,085 INFO [trainer.py:765] (7/8) Epoch 22, batch 1100, train_loss[loss=3, NarTop10Accuracy=0.7246, over 6693.00 frames. ], tot_loss[loss=3.124, NarTop10Accuracy=0.7011, over 5918.97 frames. ], batch size: 17, lr: 3.90e-03
2024-08-06 19:18:25,927 INFO [trainer.py:765] (7/8) Epoch 22, batch 1200, train_loss[loss=2.902, NarTop10Accuracy=0.7471, over 7296.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.704, over 5915.46 frames. ], batch size: 31, lr: 3.89e-03
2024-08-06 19:19:01,253 INFO [trainer.py:765] (7/8) Epoch 22, batch 1300, train_loss[loss=2.887, NarTop10Accuracy=0.7497, over 5130.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7057, over 5985.62 frames. ], batch size: 6, lr: 3.89e-03
2024-08-06 19:19:33,317 INFO [trainer.py:765] (7/8) Epoch 22, batch 1400, train_loss[loss=2.821, NarTop10Accuracy=0.767, over 6132.00 frames. ], tot_loss[loss=3.117, NarTop10Accuracy=0.7022, over 6010.17 frames. ], batch size: 11, lr: 3.89e-03
2024-08-06 19:20:03,830 INFO [trainer.py:765] (7/8) Epoch 22, batch 1500, train_loss[loss=3.541, NarTop10Accuracy=0.6224, over 6357.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7037, over 5934.92 frames. ], batch size: 50, lr: 3.88e-03
2024-08-06 19:20:31,647 INFO [trainer.py:765] (7/8) Epoch 22, batch 1600, train_loss[loss=3.145, NarTop10Accuracy=0.6953, over 6975.00 frames. ], tot_loss[loss=3.124, NarTop10Accuracy=0.701, over 5919.47 frames. ], batch size: 22, lr: 3.88e-03
2024-08-06 19:20:58,418 INFO [trainer.py:765] (7/8) Epoch 22, batch 1700, train_loss[loss=3.165, NarTop10Accuracy=0.6885, over 6621.00 frames. ], tot_loss[loss=3.123, NarTop10Accuracy=0.7007, over 5915.21 frames. ], batch size: 14, lr: 3.88e-03
2024-08-06 19:21:25,010 INFO [trainer.py:765] (7/8) Epoch 22, batch 1800, train_loss[loss=2.968, NarTop10Accuracy=0.7354, over 7053.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7018, over 5990.38 frames. ], batch size: 22, lr: 3.87e-03
2024-08-06 19:21:51,372 INFO [trainer.py:765] (7/8) Epoch 22, batch 1900, train_loss[loss=3.071, NarTop10Accuracy=0.7154, over 5742.00 frames. ], tot_loss[loss=3.138, NarTop10Accuracy=0.698, over 6018.61 frames. ], batch size: 50, lr: 3.87e-03
2024-08-06 19:21:53,110 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 19:22:01,088 INFO [trainer.py:811] (7/8) Epoch 22, validation: loss=3.009, NarTop10Accuracy=0.7241, over 1905321.00 frames. 
2024-08-06 19:22:01,089 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 27201MB
2024-08-06 19:22:01,575 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 22, batch 2000, train_loss[loss=3.459, NarTop10Accuracy=0.6346, over 6306.00 frames. ], tot_loss[loss=3.121, NarTop10Accuracy=0.7018, over 6006.22 frames. ], batch size: 50, lr: 3.87e-03
2024-08-06 19:22:50,041 INFO [trainer.py:765] (7/8) Epoch 22, batch 2100, train_loss[loss=2.795, NarTop10Accuracy=0.7569, over 3969.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7035, over 5987.54 frames. ], batch size: 4, lr: 3.86e-03
2024-08-06 19:23:15,230 INFO [trainer.py:765] (7/8) Epoch 22, batch 2200, train_loss[loss=2.951, NarTop10Accuracy=0.7316, over 7398.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.704, over 6023.76 frames. ], batch size: 31, lr: 3.86e-03
2024-08-06 19:23:40,315 INFO [trainer.py:765] (7/8) Epoch 22, batch 2300, train_loss[loss=3.028, NarTop10Accuracy=0.7158, over 5712.00 frames. ], tot_loss[loss=3.131, NarTop10Accuracy=0.7002, over 6033.13 frames. ], batch size: 9, lr: 3.86e-03
2024-08-06 19:24:04,602 INFO [trainer.py:765] (7/8) Epoch 22, batch 2400, train_loss[loss=3.214, NarTop10Accuracy=0.6818, over 5208.00 frames. ], tot_loss[loss=3.121, NarTop10Accuracy=0.7018, over 5764.19 frames. ], batch size: 7, lr: 3.85e-03
2024-08-06 19:24:28,024 INFO [trainer.py:765] (7/8) Epoch 22, batch 2500, train_loss[loss=3.172, NarTop10Accuracy=0.6927, over 5070.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.704, over 5485.17 frames. ], batch size: 7, lr: 3.85e-03
2024-08-06 19:24:47,187 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 19:25:45,385 INFO [trainer.py:765] (7/8) Epoch 23, batch 100, train_loss[loss=2.987, NarTop10Accuracy=0.7296, over 7470.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.7002, over 2371.06 frames. ], batch size: 31, lr: 3.76e-03
2024-08-06 19:26:21,309 INFO [trainer.py:765] (7/8) Epoch 23, batch 200, train_loss[loss=3.383, NarTop10Accuracy=0.659, over 6915.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.7006, over 3862.39 frames. ], batch size: 17, lr: 3.76e-03
2024-08-06 19:26:57,603 INFO [trainer.py:765] (7/8) Epoch 23, batch 300, train_loss[loss=2.944, NarTop10Accuracy=0.7344, over 7581.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7054, over 4657.72 frames. ], batch size: 23, lr: 3.75e-03
2024-08-06 19:27:26,540 INFO [trainer.py:765] (7/8) Epoch 23, batch 400, train_loss[loss=3.261, NarTop10Accuracy=0.679, over 5103.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7035, over 5110.18 frames. ], batch size: 7, lr: 3.75e-03
2024-08-06 19:27:59,712 INFO [trainer.py:765] (7/8) Epoch 23, batch 500, train_loss[loss=3.213, NarTop10Accuracy=0.6743, over 6003.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7029, over 5385.07 frames. ], batch size: 11, lr: 3.75e-03
2024-08-06 19:28:35,882 INFO [trainer.py:765] (7/8) Epoch 23, batch 600, train_loss[loss=3.318, NarTop10Accuracy=0.66, over 5748.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7047, over 5657.40 frames. ], batch size: 9, lr: 3.74e-03
2024-08-06 19:29:11,367 INFO [trainer.py:765] (7/8) Epoch 23, batch 700, train_loss[loss=3.354, NarTop10Accuracy=0.6473, over 5010.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7071, over 5735.92 frames. ], batch size: 6, lr: 3.74e-03
2024-08-06 19:29:43,613 INFO [trainer.py:765] (7/8) Epoch 23, batch 800, train_loss[loss=3.007, NarTop10Accuracy=0.7289, over 4386.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7051, over 5791.00 frames. ], batch size: 5, lr: 3.74e-03
2024-08-06 19:30:19,390 INFO [trainer.py:765] (7/8) Epoch 23, batch 900, train_loss[loss=3.234, NarTop10Accuracy=0.6779, over 6066.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7057, over 5775.86 frames. ], batch size: 13, lr: 3.73e-03
2024-08-06 19:30:58,195 INFO [trainer.py:765] (7/8) Epoch 23, batch 1000, train_loss[loss=3.007, NarTop10Accuracy=0.7251, over 6750.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7079, over 5892.64 frames. ], batch size: 14, lr: 3.73e-03
2024-08-06 19:31:31,520 INFO [trainer.py:765] (7/8) Epoch 23, batch 1100, train_loss[loss=3.114, NarTop10Accuracy=0.6998, over 6807.00 frames. ], tot_loss[loss=3.099, NarTop10Accuracy=0.7062, over 5923.35 frames. ], batch size: 17, lr: 3.73e-03
2024-08-06 19:32:08,518 INFO [trainer.py:765] (7/8) Epoch 23, batch 1200, train_loss[loss=2.965, NarTop10Accuracy=0.7369, over 7371.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7035, over 5917.52 frames. ], batch size: 31, lr: 3.72e-03
2024-08-06 19:32:46,937 INFO [trainer.py:765] (7/8) Epoch 23, batch 1300, train_loss[loss=3.065, NarTop10Accuracy=0.7201, over 5001.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7039, over 5980.46 frames. ], batch size: 6, lr: 3.72e-03
2024-08-06 19:32:56,402 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 19:33:04,722 INFO [trainer.py:811] (7/8) Epoch 23, validation: loss=2.893, NarTop10Accuracy=0.7468, over 1905321.00 frames. 
2024-08-06 19:33:04,723 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 19:33:05,262 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 23, batch 1400, train_loss[loss=2.67, NarTop10Accuracy=0.7932, over 6165.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7029, over 6010.98 frames. ], batch size: 11, lr: 3.72e-03
2024-08-06 19:33:58,215 INFO [trainer.py:765] (7/8) Epoch 23, batch 1500, train_loss[loss=3.224, NarTop10Accuracy=0.6845, over 6252.00 frames. ], tot_loss[loss=3.099, NarTop10Accuracy=0.706, over 5943.72 frames. ], batch size: 50, lr: 3.71e-03
2024-08-06 19:34:26,014 INFO [trainer.py:765] (7/8) Epoch 23, batch 1600, train_loss[loss=2.929, NarTop10Accuracy=0.7411, over 7053.00 frames. ], tot_loss[loss=3.106, NarTop10Accuracy=0.7046, over 5938.68 frames. ], batch size: 22, lr: 3.71e-03
2024-08-06 19:34:52,783 INFO [trainer.py:765] (7/8) Epoch 23, batch 1700, train_loss[loss=3.266, NarTop10Accuracy=0.6576, over 6198.00 frames. ], tot_loss[loss=3.121, NarTop10Accuracy=0.7014, over 5933.00 frames. ], batch size: 13, lr: 3.71e-03
2024-08-06 19:35:19,261 INFO [trainer.py:765] (7/8) Epoch 23, batch 1800, train_loss[loss=2.913, NarTop10Accuracy=0.745, over 7173.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7027, over 5978.88 frames. ], batch size: 22, lr: 3.70e-03
2024-08-06 19:35:45,596 INFO [trainer.py:765] (7/8) Epoch 23, batch 1900, train_loss[loss=3.326, NarTop10Accuracy=0.659, over 5832.00 frames. ], tot_loss[loss=3.124, NarTop10Accuracy=0.7009, over 6012.02 frames. ], batch size: 50, lr: 3.70e-03
2024-08-06 19:36:11,170 INFO [trainer.py:765] (7/8) Epoch 23, batch 2000, train_loss[loss=3.61, NarTop10Accuracy=0.603, over 6441.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7033, over 5978.80 frames. ], batch size: 50, lr: 3.70e-03
2024-08-06 19:36:36,517 INFO [trainer.py:765] (7/8) Epoch 23, batch 2100, train_loss[loss=3.307, NarTop10Accuracy=0.6598, over 4620.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7029, over 5956.30 frames. ], batch size: 5, lr: 3.69e-03
2024-08-06 19:37:01,908 INFO [trainer.py:765] (7/8) Epoch 23, batch 2200, train_loss[loss=3.167, NarTop10Accuracy=0.6942, over 7551.00 frames. ], tot_loss[loss=3.13, NarTop10Accuracy=0.6996, over 6022.55 frames. ], batch size: 31, lr: 3.69e-03
2024-08-06 19:37:27,060 INFO [trainer.py:765] (7/8) Epoch 23, batch 2300, train_loss[loss=2.976, NarTop10Accuracy=0.7315, over 5715.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.701, over 6019.88 frames. ], batch size: 9, lr: 3.69e-03
2024-08-06 19:37:51,424 INFO [trainer.py:765] (7/8) Epoch 23, batch 2400, train_loss[loss=3.021, NarTop10Accuracy=0.7209, over 5118.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.702, over 5769.05 frames. ], batch size: 7, lr: 3.69e-03
2024-08-06 19:38:15,052 INFO [trainer.py:765] (7/8) Epoch 23, batch 2500, train_loss[loss=3.369, NarTop10Accuracy=0.6593, over 5100.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7063, over 5462.37 frames. ], batch size: 7, lr: 3.68e-03
2024-08-06 19:38:35,063 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 19:39:37,631 INFO [trainer.py:765] (7/8) Epoch 24, batch 100, train_loss[loss=3.529, NarTop10Accuracy=0.6205, over 7344.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7022, over 2367.39 frames. ], batch size: 31, lr: 3.60e-03
2024-08-06 19:40:10,190 INFO [trainer.py:765] (7/8) Epoch 24, batch 200, train_loss[loss=2.93, NarTop10Accuracy=0.744, over 6774.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7066, over 3858.40 frames. ], batch size: 17, lr: 3.60e-03
2024-08-06 19:40:40,555 INFO [trainer.py:765] (7/8) Epoch 24, batch 300, train_loss[loss=2.903, NarTop10Accuracy=0.7484, over 7041.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.706, over 4673.71 frames. ], batch size: 22, lr: 3.59e-03
2024-08-06 19:41:18,234 INFO [trainer.py:765] (7/8) Epoch 24, batch 400, train_loss[loss=2.922, NarTop10Accuracy=0.7516, over 5130.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.706, over 5115.71 frames. ], batch size: 7, lr: 3.59e-03
2024-08-06 19:41:50,322 INFO [trainer.py:765] (7/8) Epoch 24, batch 500, train_loss[loss=2.944, NarTop10Accuracy=0.7443, over 6141.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7081, over 5395.74 frames. ], batch size: 11, lr: 3.59e-03
2024-08-06 19:42:21,451 INFO [trainer.py:765] (7/8) Epoch 24, batch 600, train_loss[loss=2.77, NarTop10Accuracy=0.7671, over 5718.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7078, over 5646.85 frames. ], batch size: 9, lr: 3.58e-03
2024-08-06 19:42:52,843 INFO [trainer.py:765] (7/8) Epoch 24, batch 700, train_loss[loss=2.902, NarTop10Accuracy=0.7435, over 5214.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7071, over 5718.23 frames. ], batch size: 6, lr: 3.58e-03
2024-08-06 19:43:17,381 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 19:43:25,410 INFO [trainer.py:811] (7/8) Epoch 24, validation: loss=3.021, NarTop10Accuracy=0.7204, over 1905321.00 frames. 
2024-08-06 19:43:25,411 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 19:43:28,562 INFO [optim.py:386] (7/8) 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 19:43:40,815 INFO [trainer.py:765] (7/8) Epoch 24, batch 800, train_loss[loss=2.755, NarTop10Accuracy=0.7736, over 5052.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7076, over 5803.12 frames. ], batch size: 6, lr: 3.58e-03
2024-08-06 19:44:11,410 INFO [trainer.py:765] (7/8) Epoch 24, batch 900, train_loss[loss=2.879, NarTop10Accuracy=0.7595, over 6570.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7088, over 5810.75 frames. ], batch size: 14, lr: 3.57e-03
2024-08-06 19:44:47,490 INFO [trainer.py:765] (7/8) Epoch 24, batch 1000, train_loss[loss=3.051, NarTop10Accuracy=0.7082, over 6699.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7072, over 5913.18 frames. ], batch size: 14, lr: 3.57e-03
2024-08-06 19:45:27,108 INFO [trainer.py:765] (7/8) Epoch 24, batch 1100, train_loss[loss=3.343, NarTop10Accuracy=0.6635, over 6690.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7058, over 5928.80 frames. ], batch size: 17, lr: 3.57e-03
2024-08-06 19:45:58,437 INFO [trainer.py:765] (7/8) Epoch 24, batch 1200, train_loss[loss=2.927, NarTop10Accuracy=0.7511, over 7119.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7066, over 5925.18 frames. ], batch size: 31, lr: 3.57e-03
2024-08-06 19:46:30,295 INFO [trainer.py:765] (7/8) Epoch 24, batch 1300, train_loss[loss=3.351, NarTop10Accuracy=0.6424, over 5022.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7066, over 5988.85 frames. ], batch size: 6, lr: 3.56e-03
2024-08-06 19:47:07,860 INFO [trainer.py:765] (7/8) Epoch 24, batch 1400, train_loss[loss=3.193, NarTop10Accuracy=0.6856, over 6012.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7036, over 5998.92 frames. ], batch size: 11, lr: 3.56e-03
2024-08-06 19:47:40,957 INFO [trainer.py:765] (7/8) Epoch 24, batch 1500, train_loss[loss=3.373, NarTop10Accuracy=0.6561, over 6021.00 frames. ], tot_loss[loss=3.119, NarTop10Accuracy=0.7015, over 5948.64 frames. ], batch size: 50, lr: 3.56e-03
2024-08-06 19:48:08,676 INFO [trainer.py:765] (7/8) Epoch 24, batch 1600, train_loss[loss=3.427, NarTop10Accuracy=0.6278, over 7191.00 frames. ], tot_loss[loss=3.123, NarTop10Accuracy=0.7003, over 5912.92 frames. ], batch size: 22, lr: 3.55e-03
2024-08-06 19:48:35,267 INFO [trainer.py:765] (7/8) Epoch 24, batch 1700, train_loss[loss=2.873, NarTop10Accuracy=0.7558, over 6579.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.6996, over 5908.41 frames. ], batch size: 14, lr: 3.55e-03
2024-08-06 19:49:01,638 INFO [trainer.py:765] (7/8) Epoch 24, batch 1800, train_loss[loss=2.973, NarTop10Accuracy=0.7226, over 7098.00 frames. ], tot_loss[loss=3.13, NarTop10Accuracy=0.6996, over 5948.82 frames. ], batch size: 22, lr: 3.55e-03
2024-08-06 19:49:28,042 INFO [trainer.py:765] (7/8) Epoch 24, batch 1900, train_loss[loss=3.537, NarTop10Accuracy=0.6168, over 6276.00 frames. ], tot_loss[loss=3.139, NarTop10Accuracy=0.6976, over 6009.39 frames. ], batch size: 50, lr: 3.55e-03
2024-08-06 19:49:53,533 INFO [trainer.py:765] (7/8) Epoch 24, batch 2000, train_loss[loss=3.511, NarTop10Accuracy=0.6271, over 6135.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7036, over 5994.50 frames. ], batch size: 50, lr: 3.54e-03
2024-08-06 19:50:18,820 INFO [trainer.py:765] (7/8) Epoch 24, batch 2100, train_loss[loss=2.799, NarTop10Accuracy=0.7717, over 4770.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7036, over 5977.50 frames. ], batch size: 5, lr: 3.54e-03
2024-08-06 19:50:43,943 INFO [trainer.py:765] (7/8) Epoch 24, batch 2200, train_loss[loss=3.434, NarTop10Accuracy=0.633, over 7455.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7034, over 6020.84 frames. ], batch size: 31, lr: 3.54e-03
2024-08-06 19:51:09,024 INFO [trainer.py:765] (7/8) Epoch 24, batch 2300, train_loss[loss=2.707, NarTop10Accuracy=0.7802, over 5760.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7043, over 6029.55 frames. ], batch size: 9, lr: 3.53e-03
2024-08-06 19:51:33,349 INFO [trainer.py:765] (7/8) Epoch 24, batch 2400, train_loss[loss=2.971, NarTop10Accuracy=0.7261, over 5208.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7068, over 5776.42 frames. ], batch size: 7, lr: 3.53e-03
2024-08-06 19:51:56,783 INFO [trainer.py:765] (7/8) Epoch 24, batch 2500, train_loss[loss=2.91, NarTop10Accuracy=0.7408, over 5232.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7109, over 5480.74 frames. ], batch size: 7, lr: 3.53e-03
2024-08-06 19:52:17,080 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 19:53:22,197 INFO [trainer.py:765] (7/8) Epoch 25, batch 100, train_loss[loss=3.437, NarTop10Accuracy=0.6449, over 7251.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.711, over 2372.47 frames. ], batch size: 31, lr: 3.45e-03
2024-08-06 19:53:47,261 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 19:53:55,329 INFO [trainer.py:811] (7/8) Epoch 25, validation: loss=2.96, NarTop10Accuracy=0.7332, over 1905321.00 frames. 
2024-08-06 19:53:55,329 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 19:53:55,916 INFO [optim.py:386] (7/8) 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 19:54:01,177 INFO [trainer.py:765] (7/8) Epoch 25, batch 200, train_loss[loss=2.823, NarTop10Accuracy=0.7616, over 7023.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7072, over 3870.09 frames. ], batch size: 17, lr: 3.45e-03
2024-08-06 19:54:35,647 INFO [trainer.py:765] (7/8) Epoch 25, batch 300, train_loss[loss=3.174, NarTop10Accuracy=0.6962, over 7137.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7101, over 4662.27 frames. ], batch size: 22, lr: 3.45e-03
2024-08-06 19:55:12,958 INFO [trainer.py:765] (7/8) Epoch 25, batch 400, train_loss[loss=2.83, NarTop10Accuracy=0.7572, over 5109.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7082, over 5114.58 frames. ], batch size: 7, lr: 3.44e-03
2024-08-06 19:55:43,738 INFO [trainer.py:765] (7/8) Epoch 25, batch 500, train_loss[loss=2.75, NarTop10Accuracy=0.7749, over 6051.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.71, over 5389.96 frames. ], batch size: 11, lr: 3.44e-03
2024-08-06 19:56:14,815 INFO [trainer.py:765] (7/8) Epoch 25, batch 600, train_loss[loss=2.683, NarTop10Accuracy=0.7877, over 5808.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7094, over 5647.75 frames. ], batch size: 9, lr: 3.44e-03
2024-08-06 19:56:55,497 INFO [trainer.py:765] (7/8) Epoch 25, batch 700, train_loss[loss=2.641, NarTop10Accuracy=0.8065, over 5127.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7095, over 5725.84 frames. ], batch size: 6, lr: 3.43e-03
2024-08-06 19:57:30,136 INFO [trainer.py:765] (7/8) Epoch 25, batch 800, train_loss[loss=2.93, NarTop10Accuracy=0.7338, over 4908.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.708, over 5787.87 frames. ], batch size: 6, lr: 3.43e-03
2024-08-06 19:58:00,679 INFO [trainer.py:765] (7/8) Epoch 25, batch 900, train_loss[loss=3.224, NarTop10Accuracy=0.6822, over 6189.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7093, over 5814.51 frames. ], batch size: 13, lr: 3.43e-03
2024-08-06 19:58:37,640 INFO [trainer.py:765] (7/8) Epoch 25, batch 1000, train_loss[loss=2.72, NarTop10Accuracy=0.7829, over 6153.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7063, over 5921.27 frames. ], batch size: 13, lr: 3.43e-03
2024-08-06 19:59:14,856 INFO [trainer.py:765] (7/8) Epoch 25, batch 1100, train_loss[loss=3.467, NarTop10Accuracy=0.6225, over 6663.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7053, over 5942.48 frames. ], batch size: 17, lr: 3.42e-03
2024-08-06 19:59:49,040 INFO [trainer.py:765] (7/8) Epoch 25, batch 1200, train_loss[loss=3.406, NarTop10Accuracy=0.6465, over 7248.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7067, over 5926.59 frames. ], batch size: 31, lr: 3.42e-03
2024-08-06 20:00:25,599 INFO [trainer.py:765] (7/8) Epoch 25, batch 1300, train_loss[loss=2.813, NarTop10Accuracy=0.7479, over 4263.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7082, over 5985.01 frames. ], batch size: 5, lr: 3.42e-03
2024-08-06 20:01:02,016 INFO [trainer.py:765] (7/8) Epoch 25, batch 1400, train_loss[loss=2.852, NarTop10Accuracy=0.755, over 6144.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7099, over 6007.74 frames. ], batch size: 11, lr: 3.42e-03
2024-08-06 20:01:32,823 INFO [trainer.py:765] (7/8) Epoch 25, batch 1500, train_loss[loss=3.257, NarTop10Accuracy=0.6814, over 6324.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7085, over 5937.43 frames. ], batch size: 50, lr: 3.41e-03
2024-08-06 20:02:00,625 INFO [trainer.py:765] (7/8) Epoch 25, batch 1600, train_loss[loss=2.946, NarTop10Accuracy=0.738, over 6957.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7086, over 5923.05 frames. ], batch size: 22, lr: 3.41e-03
2024-08-06 20:02:27,360 INFO [trainer.py:765] (7/8) Epoch 25, batch 1700, train_loss[loss=3.062, NarTop10Accuracy=0.7134, over 6378.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7079, over 5915.67 frames. ], batch size: 13, lr: 3.41e-03
2024-08-06 20:02:53,854 INFO [trainer.py:765] (7/8) Epoch 25, batch 1800, train_loss[loss=3.365, NarTop10Accuracy=0.6439, over 7359.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.705, over 5982.54 frames. ], batch size: 22, lr: 3.40e-03
2024-08-06 20:03:20,341 INFO [trainer.py:765] (7/8) Epoch 25, batch 1900, train_loss[loss=3.265, NarTop10Accuracy=0.6796, over 6402.00 frames. ], tot_loss[loss=3.117, NarTop10Accuracy=0.7025, over 6019.53 frames. ], batch size: 50, lr: 3.40e-03
2024-08-06 20:03:45,936 INFO [trainer.py:765] (7/8) Epoch 25, batch 2000, train_loss[loss=3.467, NarTop10Accuracy=0.6304, over 5820.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7005, over 6003.96 frames. ], batch size: 50, lr: 3.40e-03
2024-08-06 20:04:11,246 INFO [trainer.py:765] (7/8) Epoch 25, batch 2100, train_loss[loss=2.724, NarTop10Accuracy=0.784, over 4053.00 frames. ], tot_loss[loss=3.107, NarTop10Accuracy=0.7039, over 5958.05 frames. ], batch size: 4, lr: 3.40e-03
2024-08-06 20:04:31,410 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 20:04:39,343 INFO [trainer.py:811] (7/8) Epoch 25, validation: loss=2.999, NarTop10Accuracy=0.7251, over 1905321.00 frames. 
2024-08-06 20:04:39,344 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 20:04:39,840 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 25, batch 2200, train_loss[loss=3.287, NarTop10Accuracy=0.6681, over 7239.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7035, over 6013.47 frames. ], batch size: 31, lr: 3.39e-03
2024-08-06 20:05:09,645 INFO [trainer.py:765] (7/8) Epoch 25, batch 2300, train_loss[loss=3.01, NarTop10Accuracy=0.7292, over 5730.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7034, over 6021.42 frames. ], batch size: 9, lr: 3.39e-03
2024-08-06 20:05:34,141 INFO [trainer.py:765] (7/8) Epoch 25, batch 2400, train_loss[loss=2.926, NarTop10Accuracy=0.7518, over 5136.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7065, over 5791.16 frames. ], batch size: 7, lr: 3.39e-03
2024-08-06 20:05:57,845 INFO [trainer.py:765] (7/8) Epoch 25, batch 2500, train_loss[loss=2.832, NarTop10Accuracy=0.7645, over 5205.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7114, over 5493.88 frames. ], batch size: 7, lr: 3.39e-03
2024-08-06 20:06:18,068 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 20:07:19,303 INFO [trainer.py:765] (7/8) Epoch 26, batch 100, train_loss[loss=3.15, NarTop10Accuracy=0.7025, over 7239.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7088, over 2374.93 frames. ], batch size: 31, lr: 3.32e-03
2024-08-06 20:07:52,381 INFO [trainer.py:765] (7/8) Epoch 26, batch 200, train_loss[loss=2.766, NarTop10Accuracy=0.7705, over 6786.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7077, over 3861.10 frames. ], batch size: 17, lr: 3.31e-03
2024-08-06 20:08:24,732 INFO [trainer.py:765] (7/8) Epoch 26, batch 300, train_loss[loss=2.95, NarTop10Accuracy=0.739, over 7137.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7084, over 4666.91 frames. ], batch size: 22, lr: 3.31e-03
2024-08-06 20:08:58,184 INFO [trainer.py:765] (7/8) Epoch 26, batch 400, train_loss[loss=3.039, NarTop10Accuracy=0.7286, over 5094.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7084, over 5124.72 frames. ], batch size: 7, lr: 3.31e-03
2024-08-06 20:09:33,146 INFO [trainer.py:765] (7/8) Epoch 26, batch 500, train_loss[loss=2.854, NarTop10Accuracy=0.75, over 6087.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7059, over 5374.75 frames. ], batch size: 11, lr: 3.30e-03
2024-08-06 20:10:03,889 INFO [trainer.py:765] (7/8) Epoch 26, batch 600, train_loss[loss=2.755, NarTop10Accuracy=0.78, over 6231.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7103, over 5632.77 frames. ], batch size: 10, lr: 3.30e-03
2024-08-06 20:10:39,871 INFO [trainer.py:765] (7/8) Epoch 26, batch 700, train_loss[loss=3.213, NarTop10Accuracy=0.6907, over 4323.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7066, over 5732.11 frames. ], batch size: 5, lr: 3.30e-03
2024-08-06 20:11:19,060 INFO [trainer.py:765] (7/8) Epoch 26, batch 800, train_loss[loss=2.981, NarTop10Accuracy=0.7361, over 5076.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7074, over 5805.22 frames. ], batch size: 6, lr: 3.30e-03
2024-08-06 20:11:49,314 INFO [trainer.py:765] (7/8) Epoch 26, batch 900, train_loss[loss=2.787, NarTop10Accuracy=0.7684, over 6597.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7084, over 5812.61 frames. ], batch size: 14, lr: 3.29e-03
2024-08-06 20:12:25,972 INFO [trainer.py:765] (7/8) Epoch 26, batch 1000, train_loss[loss=2.955, NarTop10Accuracy=0.7388, over 6567.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.707, over 5907.41 frames. ], batch size: 14, lr: 3.29e-03
2024-08-06 20:13:06,376 INFO [trainer.py:765] (7/8) Epoch 26, batch 1100, train_loss[loss=3.264, NarTop10Accuracy=0.6679, over 6744.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7055, over 5944.69 frames. ], batch size: 17, lr: 3.29e-03
2024-08-06 20:13:37,535 INFO [trainer.py:765] (7/8) Epoch 26, batch 1200, train_loss[loss=3.34, NarTop10Accuracy=0.6588, over 7263.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7073, over 5937.22 frames. ], batch size: 31, lr: 3.29e-03
2024-08-06 20:14:13,695 INFO [trainer.py:765] (7/8) Epoch 26, batch 1300, train_loss[loss=2.711, NarTop10Accuracy=0.7857, over 5055.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7074, over 6002.53 frames. ], batch size: 6, lr: 3.28e-03
2024-08-06 20:14:50,537 INFO [trainer.py:765] (7/8) Epoch 26, batch 1400, train_loss[loss=2.639, NarTop10Accuracy=0.7925, over 6108.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7077, over 6018.93 frames. ], batch size: 11, lr: 3.28e-03
2024-08-06 20:15:21,154 INFO [trainer.py:765] (7/8) Epoch 26, batch 1500, train_loss[loss=3.15, NarTop10Accuracy=0.6988, over 6270.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7067, over 5956.04 frames. ], batch size: 52, lr: 3.28e-03
2024-08-06 20:15:48,978 INFO [trainer.py:765] (7/8) Epoch 26, batch 1600, train_loss[loss=2.983, NarTop10Accuracy=0.7238, over 7065.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7082, over 5927.41 frames. ], batch size: 22, lr: 3.28e-03
2024-08-06 20:15:50,001 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 20:15:58,239 INFO [trainer.py:811] (7/8) Epoch 26, validation: loss=2.899, NarTop10Accuracy=0.7457, over 1905321.00 frames. 
2024-08-06 20:15:58,239 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 20:15:58,779 INFO [optim.py:386] (7/8) 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 20:16:23,952 INFO [trainer.py:765] (7/8) Epoch 26, batch 1700, train_loss[loss=3.153, NarTop10Accuracy=0.702, over 6111.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7121, over 5927.13 frames. ], batch size: 13, lr: 3.28e-03
2024-08-06 20:16:50,427 INFO [trainer.py:765] (7/8) Epoch 26, batch 1800, train_loss[loss=2.893, NarTop10Accuracy=0.7545, over 6939.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7108, over 5993.97 frames. ], batch size: 22, lr: 3.27e-03
2024-08-06 20:17:16,840 INFO [trainer.py:765] (7/8) Epoch 26, batch 1900, train_loss[loss=3.059, NarTop10Accuracy=0.7197, over 5913.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7085, over 6024.86 frames. ], batch size: 52, lr: 3.27e-03
2024-08-06 20:17:42,379 INFO [trainer.py:765] (7/8) Epoch 26, batch 2000, train_loss[loss=3.578, NarTop10Accuracy=0.6092, over 5772.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.707, over 6005.73 frames. ], batch size: 50, lr: 3.27e-03
2024-08-06 20:18:07,563 INFO [trainer.py:765] (7/8) Epoch 26, batch 2100, train_loss[loss=2.914, NarTop10Accuracy=0.7515, over 4932.00 frames. ], tot_loss[loss=3.099, NarTop10Accuracy=0.7055, over 5966.27 frames. ], batch size: 5, lr: 3.27e-03
2024-08-06 20:18:32,777 INFO [trainer.py:765] (7/8) Epoch 26, batch 2200, train_loss[loss=2.836, NarTop10Accuracy=0.7532, over 7284.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7069, over 6016.72 frames. ], batch size: 31, lr: 3.26e-03
2024-08-06 20:18:57,897 INFO [trainer.py:765] (7/8) Epoch 26, batch 2300, train_loss[loss=3.134, NarTop10Accuracy=0.6979, over 5739.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7062, over 6020.06 frames. ], batch size: 9, lr: 3.26e-03
2024-08-06 20:19:22,205 INFO [trainer.py:765] (7/8) Epoch 26, batch 2400, train_loss[loss=2.833, NarTop10Accuracy=0.7601, over 5280.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7115, over 5780.95 frames. ], batch size: 7, lr: 3.26e-03
2024-08-06 20:19:45,651 INFO [trainer.py:765] (7/8) Epoch 26, batch 2500, train_loss[loss=2.879, NarTop10Accuracy=0.749, over 5034.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7154, over 5479.68 frames. ], batch size: 7, lr: 3.26e-03
2024-08-06 20:20:05,863 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 20:21:04,874 INFO [trainer.py:765] (7/8) Epoch 27, batch 100, train_loss[loss=3.243, NarTop10Accuracy=0.67, over 7092.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7103, over 2366.56 frames. ], batch size: 31, lr: 3.19e-03
2024-08-06 20:21:39,784 INFO [trainer.py:765] (7/8) Epoch 27, batch 200, train_loss[loss=2.806, NarTop10Accuracy=0.7521, over 6813.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7085, over 3862.14 frames. ], batch size: 17, lr: 3.19e-03
2024-08-06 20:22:13,050 INFO [trainer.py:765] (7/8) Epoch 27, batch 300, train_loss[loss=2.867, NarTop10Accuracy=0.7615, over 7293.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7094, over 4665.00 frames. ], batch size: 22, lr: 3.18e-03
2024-08-06 20:22:43,557 INFO [trainer.py:765] (7/8) Epoch 27, batch 400, train_loss[loss=2.893, NarTop10Accuracy=0.7442, over 5226.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7118, over 5104.69 frames. ], batch size: 7, lr: 3.18e-03
2024-08-06 20:23:18,084 INFO [trainer.py:765] (7/8) Epoch 27, batch 500, train_loss[loss=2.895, NarTop10Accuracy=0.743, over 6036.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7147, over 5377.99 frames. ], batch size: 11, lr: 3.18e-03
2024-08-06 20:23:51,435 INFO [trainer.py:765] (7/8) Epoch 27, batch 600, train_loss[loss=3.253, NarTop10Accuracy=0.6661, over 5730.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7151, over 5655.43 frames. ], batch size: 9, lr: 3.18e-03
2024-08-06 20:24:24,976 INFO [trainer.py:765] (7/8) Epoch 27, batch 700, train_loss[loss=2.871, NarTop10Accuracy=0.7563, over 5064.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7161, over 5724.78 frames. ], batch size: 6, lr: 3.18e-03
2024-08-06 20:25:03,407 INFO [trainer.py:765] (7/8) Epoch 27, batch 800, train_loss[loss=3.123, NarTop10Accuracy=0.6957, over 4359.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7106, over 5778.41 frames. ], batch size: 5, lr: 3.17e-03
2024-08-06 20:25:34,176 INFO [trainer.py:765] (7/8) Epoch 27, batch 900, train_loss[loss=3.309, NarTop10Accuracy=0.6715, over 6303.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7096, over 5778.17 frames. ], batch size: 13, lr: 3.17e-03
2024-08-06 20:26:10,097 INFO [trainer.py:765] (7/8) Epoch 27, batch 1000, train_loss[loss=2.844, NarTop10Accuracy=0.7711, over 6168.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7101, over 5884.82 frames. ], batch size: 13, lr: 3.17e-03
2024-08-06 20:26:18,316 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 20:26:26,346 INFO [trainer.py:811] (7/8) Epoch 27, validation: loss=2.95, NarTop10Accuracy=0.735, over 1905321.00 frames. 
2024-08-06 20:26:26,347 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 20:26:26,877 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 27, batch 1100, train_loss[loss=2.96, NarTop10Accuracy=0.7288, over 6771.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7098, over 5923.61 frames. ], batch size: 17, lr: 3.17e-03
2024-08-06 20:27:24,545 INFO [trainer.py:765] (7/8) Epoch 27, batch 1200, train_loss[loss=2.899, NarTop10Accuracy=0.7445, over 7227.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7107, over 5927.32 frames. ], batch size: 31, lr: 3.16e-03
2024-08-06 20:27:58,568 INFO [trainer.py:765] (7/8) Epoch 27, batch 1300, train_loss[loss=2.658, NarTop10Accuracy=0.7978, over 5094.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7128, over 6000.61 frames. ], batch size: 6, lr: 3.16e-03
2024-08-06 20:28:36,745 INFO [trainer.py:765] (7/8) Epoch 27, batch 1400, train_loss[loss=3.372, NarTop10Accuracy=0.6422, over 5994.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.709, over 6028.94 frames. ], batch size: 11, lr: 3.16e-03
2024-08-06 20:29:04,632 INFO [trainer.py:765] (7/8) Epoch 27, batch 1500, train_loss[loss=3.026, NarTop10Accuracy=0.7293, over 6096.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7108, over 5964.81 frames. ], batch size: 50, lr: 3.16e-03
2024-08-06 20:29:32,362 INFO [trainer.py:765] (7/8) Epoch 27, batch 1600, train_loss[loss=2.94, NarTop10Accuracy=0.7431, over 7050.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7085, over 5932.01 frames. ], batch size: 22, lr: 3.15e-03
2024-08-06 20:29:58,977 INFO [trainer.py:765] (7/8) Epoch 27, batch 1700, train_loss[loss=3.249, NarTop10Accuracy=0.6826, over 6735.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7089, over 5938.63 frames. ], batch size: 14, lr: 3.15e-03
2024-08-06 20:30:25,463 INFO [trainer.py:765] (7/8) Epoch 27, batch 1800, train_loss[loss=3.312, NarTop10Accuracy=0.66, over 6840.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7083, over 6004.53 frames. ], batch size: 22, lr: 3.15e-03
2024-08-06 20:30:51,845 INFO [trainer.py:765] (7/8) Epoch 27, batch 1900, train_loss[loss=3.087, NarTop10Accuracy=0.7068, over 5781.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.709, over 6047.62 frames. ], batch size: 50, lr: 3.15e-03
2024-08-06 20:31:17,390 INFO [trainer.py:765] (7/8) Epoch 27, batch 2000, train_loss[loss=3.118, NarTop10Accuracy=0.6907, over 6225.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7112, over 6017.32 frames. ], batch size: 51, lr: 3.15e-03
2024-08-06 20:31:42,660 INFO [trainer.py:765] (7/8) Epoch 27, batch 2100, train_loss[loss=2.956, NarTop10Accuracy=0.7369, over 3903.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7093, over 5980.60 frames. ], batch size: 4, lr: 3.14e-03
2024-08-06 20:32:07,804 INFO [trainer.py:765] (7/8) Epoch 27, batch 2200, train_loss[loss=3.444, NarTop10Accuracy=0.6381, over 7164.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7083, over 6016.87 frames. ], batch size: 31, lr: 3.14e-03
2024-08-06 20:32:32,941 INFO [trainer.py:765] (7/8) Epoch 27, batch 2300, train_loss[loss=2.899, NarTop10Accuracy=0.746, over 5706.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7071, over 6031.97 frames. ], batch size: 9, lr: 3.14e-03
2024-08-06 20:32:57,246 INFO [trainer.py:765] (7/8) Epoch 27, batch 2400, train_loss[loss=2.788, NarTop10Accuracy=0.7758, over 5130.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7065, over 5794.32 frames. ], batch size: 7, lr: 3.14e-03
2024-08-06 20:33:20,615 INFO [trainer.py:765] (7/8) Epoch 27, batch 2500, train_loss[loss=3.374, NarTop10Accuracy=0.6459, over 5112.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.713, over 5497.56 frames. ], batch size: 7, lr: 3.13e-03
2024-08-06 20:33:40,790 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 20:34:35,829 INFO [trainer.py:765] (7/8) Epoch 28, batch 100, train_loss[loss=2.88, NarTop10Accuracy=0.7489, over 7314.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7113, over 2366.91 frames. ], batch size: 31, lr: 3.07e-03
2024-08-06 20:35:07,394 INFO [trainer.py:765] (7/8) Epoch 28, batch 200, train_loss[loss=2.78, NarTop10Accuracy=0.7757, over 6759.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7093, over 3853.79 frames. ], batch size: 17, lr: 3.07e-03
2024-08-06 20:35:45,423 INFO [trainer.py:765] (7/8) Epoch 28, batch 300, train_loss[loss=3.082, NarTop10Accuracy=0.7171, over 7125.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7115, over 4659.01 frames. ], batch size: 22, lr: 3.07e-03
2024-08-06 20:36:15,865 INFO [trainer.py:765] (7/8) Epoch 28, batch 400, train_loss[loss=3.155, NarTop10Accuracy=0.6832, over 5259.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7091, over 5095.94 frames. ], batch size: 7, lr: 3.07e-03
2024-08-06 20:36:32,407 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 20:36:40,530 INFO [trainer.py:811] (7/8) Epoch 28, validation: loss=2.963, NarTop10Accuracy=0.7327, over 1905321.00 frames. 
2024-08-06 20:36:40,531 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 20:36:41,103 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 28, batch 500, train_loss[loss=3.365, NarTop10Accuracy=0.6561, over 6138.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7115, over 5375.21 frames. ], batch size: 11, lr: 3.06e-03
2024-08-06 20:37:29,462 INFO [trainer.py:765] (7/8) Epoch 28, batch 600, train_loss[loss=3.061, NarTop10Accuracy=0.7149, over 5712.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7098, over 5642.95 frames. ], batch size: 9, lr: 3.06e-03
2024-08-06 20:38:08,891 INFO [trainer.py:765] (7/8) Epoch 28, batch 700, train_loss[loss=3.059, NarTop10Accuracy=0.6993, over 5145.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7086, over 5694.31 frames. ], batch size: 6, lr: 3.06e-03
2024-08-06 20:38:42,489 INFO [trainer.py:765] (7/8) Epoch 28, batch 800, train_loss[loss=2.884, NarTop10Accuracy=0.7404, over 5091.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7134, over 5760.11 frames. ], batch size: 6, lr: 3.06e-03
2024-08-06 20:39:15,506 INFO [trainer.py:765] (7/8) Epoch 28, batch 900, train_loss[loss=3.291, NarTop10Accuracy=0.6702, over 6261.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7132, over 5799.41 frames. ], batch size: 13, lr: 3.06e-03
2024-08-06 20:39:53,240 INFO [trainer.py:765] (7/8) Epoch 28, batch 1000, train_loss[loss=3.376, NarTop10Accuracy=0.6557, over 6183.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7128, over 5906.35 frames. ], batch size: 13, lr: 3.05e-03
2024-08-06 20:40:25,867 INFO [trainer.py:765] (7/8) Epoch 28, batch 1100, train_loss[loss=2.797, NarTop10Accuracy=0.7671, over 6807.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7093, over 5945.76 frames. ], batch size: 17, lr: 3.05e-03
2024-08-06 20:40:59,418 INFO [trainer.py:765] (7/8) Epoch 28, batch 1200, train_loss[loss=3.349, NarTop10Accuracy=0.6634, over 7227.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7076, over 5938.23 frames. ], batch size: 32, lr: 3.05e-03
2024-08-06 20:41:38,681 INFO [trainer.py:765] (7/8) Epoch 28, batch 1300, train_loss[loss=3.232, NarTop10Accuracy=0.6766, over 4965.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7086, over 5982.52 frames. ], batch size: 6, lr: 3.05e-03
2024-08-06 20:42:13,047 INFO [trainer.py:765] (7/8) Epoch 28, batch 1400, train_loss[loss=2.946, NarTop10Accuracy=0.7387, over 6204.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7076, over 5996.93 frames. ], batch size: 11, lr: 3.04e-03
2024-08-06 20:42:43,171 INFO [trainer.py:765] (7/8) Epoch 28, batch 1500, train_loss[loss=3.449, NarTop10Accuracy=0.6344, over 6579.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7106, over 5946.56 frames. ], batch size: 50, lr: 3.04e-03
2024-08-06 20:43:11,080 INFO [trainer.py:765] (7/8) Epoch 28, batch 1600, train_loss[loss=2.791, NarTop10Accuracy=0.774, over 7377.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7109, over 5918.59 frames. ], batch size: 23, lr: 3.04e-03
2024-08-06 20:43:37,785 INFO [trainer.py:765] (7/8) Epoch 28, batch 1700, train_loss[loss=2.994, NarTop10Accuracy=0.7218, over 6234.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7089, over 5907.25 frames. ], batch size: 13, lr: 3.04e-03
2024-08-06 20:44:04,326 INFO [trainer.py:765] (7/8) Epoch 28, batch 1800, train_loss[loss=3.137, NarTop10Accuracy=0.7019, over 7071.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7087, over 5975.20 frames. ], batch size: 22, lr: 3.04e-03
2024-08-06 20:44:30,757 INFO [trainer.py:765] (7/8) Epoch 28, batch 1900, train_loss[loss=3.075, NarTop10Accuracy=0.7103, over 6156.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7097, over 6014.10 frames. ], batch size: 50, lr: 3.03e-03
2024-08-06 20:44:56,328 INFO [trainer.py:765] (7/8) Epoch 28, batch 2000, train_loss[loss=3.018, NarTop10Accuracy=0.725, over 6045.00 frames. ], tot_loss[loss=3.062, NarTop10Accuracy=0.7134, over 5995.78 frames. ], batch size: 50, lr: 3.03e-03
2024-08-06 20:45:21,651 INFO [trainer.py:765] (7/8) Epoch 28, batch 2100, train_loss[loss=2.749, NarTop10Accuracy=0.7711, over 3936.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7142, over 5963.26 frames. ], batch size: 4, lr: 3.03e-03
2024-08-06 20:45:47,076 INFO [trainer.py:765] (7/8) Epoch 28, batch 2200, train_loss[loss=2.882, NarTop10Accuracy=0.7484, over 7140.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7115, over 5996.77 frames. ], batch size: 31, lr: 3.03e-03
2024-08-06 20:46:12,307 INFO [trainer.py:765] (7/8) Epoch 28, batch 2300, train_loss[loss=3.314, NarTop10Accuracy=0.661, over 5727.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7065, over 6027.52 frames. ], batch size: 9, lr: 3.03e-03
2024-08-06 20:46:36,806 INFO [trainer.py:765] (7/8) Epoch 28, batch 2400, train_loss[loss=2.956, NarTop10Accuracy=0.7298, over 5073.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.707, over 5787.43 frames. ], batch size: 7, lr: 3.02e-03
2024-08-06 20:46:48,595 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 20:46:56,604 INFO [trainer.py:811] (7/8) Epoch 28, validation: loss=2.931, NarTop10Accuracy=0.7396, over 1905321.00 frames. 
2024-08-06 20:46:56,605 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 20:46:57,082 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 28, batch 2500, train_loss[loss=3.042, NarTop10Accuracy=0.72, over 5028.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7119, over 5482.48 frames. ], batch size: 7, lr: 3.02e-03
2024-08-06 20:47:28,122 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 20:48:21,053 INFO [trainer.py:765] (7/8) Epoch 29, batch 100, train_loss[loss=3.041, NarTop10Accuracy=0.7181, over 7344.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7122, over 2377.54 frames. ], batch size: 32, lr: 2.96e-03
2024-08-06 20:48:53,407 INFO [trainer.py:765] (7/8) Epoch 29, batch 200, train_loss[loss=3.285, NarTop10Accuracy=0.662, over 6834.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7173, over 3861.31 frames. ], batch size: 17, lr: 2.96e-03
2024-08-06 20:49:27,477 INFO [trainer.py:765] (7/8) Epoch 29, batch 300, train_loss[loss=3.213, NarTop10Accuracy=0.6787, over 7116.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7173, over 4668.16 frames. ], batch size: 22, lr: 2.96e-03
2024-08-06 20:49:56,054 INFO [trainer.py:765] (7/8) Epoch 29, batch 400, train_loss[loss=3.333, NarTop10Accuracy=0.6693, over 5016.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7122, over 5108.20 frames. ], batch size: 7, lr: 2.96e-03
2024-08-06 20:50:29,436 INFO [trainer.py:765] (7/8) Epoch 29, batch 500, train_loss[loss=3.292, NarTop10Accuracy=0.6678, over 6126.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7143, over 5402.00 frames. ], batch size: 11, lr: 2.96e-03
2024-08-06 20:51:00,025 INFO [trainer.py:765] (7/8) Epoch 29, batch 600, train_loss[loss=2.795, NarTop10Accuracy=0.765, over 5580.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7147, over 5655.41 frames. ], batch size: 9, lr: 2.95e-03
2024-08-06 20:51:35,678 INFO [trainer.py:765] (7/8) Epoch 29, batch 700, train_loss[loss=2.793, NarTop10Accuracy=0.7565, over 4431.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7099, over 5725.48 frames. ], batch size: 5, lr: 2.95e-03
2024-08-06 20:52:10,725 INFO [trainer.py:765] (7/8) Epoch 29, batch 800, train_loss[loss=2.663, NarTop10Accuracy=0.7841, over 5115.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7106, over 5789.50 frames. ], batch size: 6, lr: 2.95e-03
2024-08-06 20:52:40,743 INFO [trainer.py:765] (7/8) Epoch 29, batch 900, train_loss[loss=2.762, NarTop10Accuracy=0.7841, over 6297.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7098, over 5795.48 frames. ], batch size: 13, lr: 2.95e-03
2024-08-06 20:53:16,862 INFO [trainer.py:765] (7/8) Epoch 29, batch 1000, train_loss[loss=3.384, NarTop10Accuracy=0.6505, over 6363.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.708, over 5894.01 frames. ], batch size: 13, lr: 2.95e-03
2024-08-06 20:53:52,903 INFO [trainer.py:765] (7/8) Epoch 29, batch 1100, train_loss[loss=3.194, NarTop10Accuracy=0.6828, over 6684.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7074, over 5925.55 frames. ], batch size: 17, lr: 2.94e-03
2024-08-06 20:54:23,691 INFO [trainer.py:765] (7/8) Epoch 29, batch 1200, train_loss[loss=3.186, NarTop10Accuracy=0.6888, over 7317.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7087, over 5927.39 frames. ], batch size: 31, lr: 2.94e-03
2024-08-06 20:55:01,429 INFO [trainer.py:765] (7/8) Epoch 29, batch 1300, train_loss[loss=2.852, NarTop10Accuracy=0.7586, over 4443.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7091, over 5996.31 frames. ], batch size: 5, lr: 2.94e-03
2024-08-06 20:55:32,558 INFO [trainer.py:765] (7/8) Epoch 29, batch 1400, train_loss[loss=3.457, NarTop10Accuracy=0.632, over 6048.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7087, over 6012.33 frames. ], batch size: 11, lr: 2.94e-03
2024-08-06 20:56:04,360 INFO [trainer.py:765] (7/8) Epoch 29, batch 1500, train_loss[loss=3.399, NarTop10Accuracy=0.6443, over 6351.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7093, over 5940.89 frames. ], batch size: 51, lr: 2.94e-03
2024-08-06 20:56:32,041 INFO [trainer.py:765] (7/8) Epoch 29, batch 1600, train_loss[loss=3.29, NarTop10Accuracy=0.6614, over 6966.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7081, over 5920.69 frames. ], batch size: 22, lr: 2.93e-03
2024-08-06 20:56:58,640 INFO [trainer.py:765] (7/8) Epoch 29, batch 1700, train_loss[loss=2.814, NarTop10Accuracy=0.758, over 6243.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7112, over 5901.66 frames. ], batch size: 13, lr: 2.93e-03
2024-08-06 20:57:25,001 INFO [trainer.py:765] (7/8) Epoch 29, batch 1800, train_loss[loss=3.087, NarTop10Accuracy=0.7163, over 7227.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7121, over 5962.67 frames. ], batch size: 22, lr: 2.93e-03
2024-08-06 20:57:44,622 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 20:57:52,863 INFO [trainer.py:811] (7/8) Epoch 29, validation: loss=2.897, NarTop10Accuracy=0.7458, over 1905321.00 frames. 
2024-08-06 20:57:52,864 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 20:57:53,424 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 29, batch 1900, train_loss[loss=3.022, NarTop10Accuracy=0.7189, over 6447.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7083, over 6020.71 frames. ], batch size: 50, lr: 2.93e-03
2024-08-06 20:58:25,309 INFO [trainer.py:765] (7/8) Epoch 29, batch 2000, train_loss[loss=3.574, NarTop10Accuracy=0.6094, over 5865.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7089, over 5999.10 frames. ], batch size: 50, lr: 2.93e-03
2024-08-06 20:58:50,630 INFO [trainer.py:765] (7/8) Epoch 29, batch 2100, train_loss[loss=2.958, NarTop10Accuracy=0.7304, over 4890.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7089, over 5971.44 frames. ], batch size: 5, lr: 2.92e-03
2024-08-06 20:59:15,806 INFO [trainer.py:765] (7/8) Epoch 29, batch 2200, train_loss[loss=2.849, NarTop10Accuracy=0.7552, over 7215.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7115, over 6004.23 frames. ], batch size: 31, lr: 2.92e-03
2024-08-06 20:59:40,911 INFO [trainer.py:765] (7/8) Epoch 29, batch 2300, train_loss[loss=2.766, NarTop10Accuracy=0.7794, over 5556.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7071, over 6025.68 frames. ], batch size: 9, lr: 2.92e-03
2024-08-06 21:00:05,156 INFO [trainer.py:765] (7/8) Epoch 29, batch 2400, train_loss[loss=2.829, NarTop10Accuracy=0.7663, over 4989.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7106, over 5773.17 frames. ], batch size: 7, lr: 2.92e-03
2024-08-06 21:00:28,742 INFO [trainer.py:765] (7/8) Epoch 29, batch 2500, train_loss[loss=3.272, NarTop10Accuracy=0.6728, over 5163.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.716, over 5475.70 frames. ], batch size: 7, lr: 2.92e-03
2024-08-06 21:00:48,776 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 21:01:41,717 INFO [trainer.py:765] (7/8) Epoch 30, batch 100, train_loss[loss=2.94, NarTop10Accuracy=0.7383, over 7056.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7194, over 2364.30 frames. ], batch size: 31, lr: 2.86e-03
2024-08-06 21:02:17,014 INFO [trainer.py:765] (7/8) Epoch 30, batch 200, train_loss[loss=2.857, NarTop10Accuracy=0.7508, over 6858.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7225, over 3856.52 frames. ], batch size: 17, lr: 2.86e-03
2024-08-06 21:02:51,344 INFO [trainer.py:765] (7/8) Epoch 30, batch 300, train_loss[loss=2.834, NarTop10Accuracy=0.7568, over 7296.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.724, over 4650.80 frames. ], batch size: 22, lr: 2.86e-03
2024-08-06 21:03:21,644 INFO [trainer.py:765] (7/8) Epoch 30, batch 400, train_loss[loss=2.862, NarTop10Accuracy=0.7637, over 5181.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7203, over 5113.08 frames. ], batch size: 7, lr: 2.86e-03
2024-08-06 21:03:58,546 INFO [trainer.py:765] (7/8) Epoch 30, batch 500, train_loss[loss=3.444, NarTop10Accuracy=0.6284, over 6006.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7183, over 5389.86 frames. ], batch size: 11, lr: 2.86e-03
2024-08-06 21:04:31,656 INFO [trainer.py:765] (7/8) Epoch 30, batch 600, train_loss[loss=2.978, NarTop10Accuracy=0.7333, over 5781.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7164, over 5655.17 frames. ], batch size: 9, lr: 2.85e-03
2024-08-06 21:05:03,526 INFO [trainer.py:765] (7/8) Epoch 30, batch 700, train_loss[loss=2.914, NarTop10Accuracy=0.7379, over 4212.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7192, over 5743.42 frames. ], batch size: 5, lr: 2.85e-03
2024-08-06 21:05:44,132 INFO [trainer.py:765] (7/8) Epoch 30, batch 800, train_loss[loss=2.859, NarTop10Accuracy=0.7458, over 5229.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7194, over 5783.65 frames. ], batch size: 6, lr: 2.85e-03
2024-08-06 21:06:14,844 INFO [trainer.py:765] (7/8) Epoch 30, batch 900, train_loss[loss=2.836, NarTop10Accuracy=0.756, over 6705.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7196, over 5785.31 frames. ], batch size: 14, lr: 2.85e-03
2024-08-06 21:06:48,952 INFO [trainer.py:765] (7/8) Epoch 30, batch 1000, train_loss[loss=2.888, NarTop10Accuracy=0.7414, over 6285.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7123, over 5892.18 frames. ], batch size: 13, lr: 2.85e-03
2024-08-06 21:07:25,937 INFO [trainer.py:765] (7/8) Epoch 30, batch 1100, train_loss[loss=3.405, NarTop10Accuracy=0.6433, over 7098.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7083, over 5918.31 frames. ], batch size: 18, lr: 2.84e-03
2024-08-06 21:08:02,381 INFO [trainer.py:765] (7/8) Epoch 30, batch 1200, train_loss[loss=2.867, NarTop10Accuracy=0.7548, over 7164.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7112, over 5911.28 frames. ], batch size: 31, lr: 2.84e-03
2024-08-06 21:08:35,371 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 21:08:43,457 INFO [trainer.py:811] (7/8) Epoch 30, validation: loss=2.93, NarTop10Accuracy=0.7391, over 1905321.00 frames. 
2024-08-06 21:08:43,457 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 21:08:44,197 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 30, batch 1300, train_loss[loss=3.155, NarTop10Accuracy=0.6844, over 5064.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7112, over 5979.96 frames. ], batch size: 6, lr: 2.84e-03
2024-08-06 21:09:22,397 INFO [trainer.py:765] (7/8) Epoch 30, batch 1400, train_loss[loss=2.922, NarTop10Accuracy=0.7431, over 6027.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7116, over 5990.32 frames. ], batch size: 11, lr: 2.84e-03
2024-08-06 21:09:52,373 INFO [trainer.py:765] (7/8) Epoch 30, batch 1500, train_loss[loss=2.991, NarTop10Accuracy=0.7245, over 6303.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7129, over 5955.86 frames. ], batch size: 50, lr: 2.84e-03
2024-08-06 21:10:20,083 INFO [trainer.py:765] (7/8) Epoch 30, batch 1600, train_loss[loss=3.066, NarTop10Accuracy=0.7143, over 7062.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7123, over 5941.59 frames. ], batch size: 22, lr: 2.84e-03
2024-08-06 21:10:46,679 INFO [trainer.py:765] (7/8) Epoch 30, batch 1700, train_loss[loss=3.123, NarTop10Accuracy=0.6982, over 6252.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7109, over 5928.77 frames. ], batch size: 13, lr: 2.83e-03
2024-08-06 21:11:13,059 INFO [trainer.py:765] (7/8) Epoch 30, batch 1800, train_loss[loss=3.279, NarTop10Accuracy=0.663, over 6921.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7111, over 5981.22 frames. ], batch size: 22, lr: 2.83e-03
2024-08-06 21:11:39,418 INFO [trainer.py:765] (7/8) Epoch 30, batch 1900, train_loss[loss=3.087, NarTop10Accuracy=0.7129, over 6516.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7105, over 6023.37 frames. ], batch size: 50, lr: 2.83e-03
2024-08-06 21:12:04,826 INFO [trainer.py:765] (7/8) Epoch 30, batch 2000, train_loss[loss=3.382, NarTop10Accuracy=0.652, over 6810.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7112, over 6013.17 frames. ], batch size: 50, lr: 2.83e-03
2024-08-06 21:12:30,088 INFO [trainer.py:765] (7/8) Epoch 30, batch 2100, train_loss[loss=2.92, NarTop10Accuracy=0.7454, over 4809.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.711, over 5988.19 frames. ], batch size: 5, lr: 2.83e-03
2024-08-06 21:12:55,225 INFO [trainer.py:765] (7/8) Epoch 30, batch 2200, train_loss[loss=2.914, NarTop10Accuracy=0.7482, over 7386.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7116, over 6007.69 frames. ], batch size: 31, lr: 2.82e-03
2024-08-06 21:13:20,297 INFO [trainer.py:765] (7/8) Epoch 30, batch 2300, train_loss[loss=2.706, NarTop10Accuracy=0.7924, over 5745.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7068, over 6019.48 frames. ], batch size: 9, lr: 2.82e-03
2024-08-06 21:13:44,491 INFO [trainer.py:765] (7/8) Epoch 30, batch 2400, train_loss[loss=2.603, NarTop10Accuracy=0.8025, over 5049.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7136, over 5782.69 frames. ], batch size: 7, lr: 2.82e-03
2024-08-06 21:14:07,987 INFO [trainer.py:765] (7/8) Epoch 30, batch 2500, train_loss[loss=2.966, NarTop10Accuracy=0.7364, over 5205.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.716, over 5503.50 frames. ], batch size: 7, lr: 2.82e-03
2024-08-06 21:14:27,936 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 21:15:23,633 INFO [trainer.py:765] (7/8) Epoch 31, batch 100, train_loss[loss=3.395, NarTop10Accuracy=0.6508, over 7014.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7115, over 2369.12 frames. ], batch size: 31, lr: 2.77e-03
2024-08-06 21:15:55,127 INFO [trainer.py:765] (7/8) Epoch 31, batch 200, train_loss[loss=2.821, NarTop10Accuracy=0.7579, over 6768.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7178, over 3867.95 frames. ], batch size: 17, lr: 2.77e-03
2024-08-06 21:16:31,216 INFO [trainer.py:765] (7/8) Epoch 31, batch 300, train_loss[loss=2.886, NarTop10Accuracy=0.7451, over 7101.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7173, over 4657.99 frames. ], batch size: 22, lr: 2.77e-03
2024-08-06 21:17:01,625 INFO [trainer.py:765] (7/8) Epoch 31, batch 400, train_loss[loss=3.131, NarTop10Accuracy=0.6947, over 5214.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.715, over 5115.65 frames. ], batch size: 7, lr: 2.76e-03
2024-08-06 21:17:35,725 INFO [trainer.py:765] (7/8) Epoch 31, batch 500, train_loss[loss=2.647, NarTop10Accuracy=0.7946, over 6186.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7169, over 5398.09 frames. ], batch size: 11, lr: 2.76e-03
2024-08-06 21:18:07,084 INFO [trainer.py:765] (7/8) Epoch 31, batch 600, train_loss[loss=2.767, NarTop10Accuracy=0.7797, over 5742.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7141, over 5652.23 frames. ], batch size: 9, lr: 2.76e-03
2024-08-06 21:18:44,610 INFO [trainer.py:765] (7/8) Epoch 31, batch 700, train_loss[loss=3.367, NarTop10Accuracy=0.6503, over 5145.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.712, over 5726.00 frames. ], batch size: 6, lr: 2.76e-03
2024-08-06 21:18:51,095 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 21:18:59,276 INFO [trainer.py:811] (7/8) Epoch 31, validation: loss=2.984, NarTop10Accuracy=0.7279, over 1905321.00 frames. 
2024-08-06 21:18:59,276 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 21:18:59,986 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 31, batch 800, train_loss[loss=2.812, NarTop10Accuracy=0.7691, over 5061.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7153, over 5784.80 frames. ], batch size: 6, lr: 2.76e-03
2024-08-06 21:19:56,950 INFO [trainer.py:765] (7/8) Epoch 31, batch 900, train_loss[loss=3.412, NarTop10Accuracy=0.6443, over 6147.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7158, over 5809.12 frames. ], batch size: 13, lr: 2.76e-03
2024-08-06 21:20:33,311 INFO [trainer.py:765] (7/8) Epoch 31, batch 1000, train_loss[loss=3.241, NarTop10Accuracy=0.676, over 6732.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.717, over 5911.48 frames. ], batch size: 14, lr: 2.75e-03
2024-08-06 21:21:10,215 INFO [trainer.py:765] (7/8) Epoch 31, batch 1100, train_loss[loss=3.275, NarTop10Accuracy=0.6645, over 6888.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7157, over 5926.71 frames. ], batch size: 17, lr: 2.75e-03
2024-08-06 21:21:41,119 INFO [trainer.py:765] (7/8) Epoch 31, batch 1200, train_loss[loss=3.042, NarTop10Accuracy=0.7137, over 7098.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7195, over 5925.63 frames. ], batch size: 31, lr: 2.75e-03
2024-08-06 21:22:19,741 INFO [trainer.py:765] (7/8) Epoch 31, batch 1300, train_loss[loss=2.909, NarTop10Accuracy=0.7501, over 5052.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7147, over 5997.14 frames. ], batch size: 6, lr: 2.75e-03
2024-08-06 21:22:53,534 INFO [trainer.py:765] (7/8) Epoch 31, batch 1400, train_loss[loss=2.864, NarTop10Accuracy=0.7469, over 6105.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7126, over 6012.40 frames. ], batch size: 11, lr: 2.75e-03
2024-08-06 21:23:21,269 INFO [trainer.py:765] (7/8) Epoch 31, batch 1500, train_loss[loss=3.361, NarTop10Accuracy=0.6566, over 6351.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7132, over 5943.46 frames. ], batch size: 50, lr: 2.74e-03
2024-08-06 21:23:49,005 INFO [trainer.py:765] (7/8) Epoch 31, batch 1600, train_loss[loss=3.261, NarTop10Accuracy=0.6676, over 7056.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7133, over 5922.80 frames. ], batch size: 22, lr: 2.74e-03
2024-08-06 21:24:15,512 INFO [trainer.py:765] (7/8) Epoch 31, batch 1700, train_loss[loss=3.277, NarTop10Accuracy=0.6694, over 6195.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7135, over 5895.52 frames. ], batch size: 13, lr: 2.74e-03
2024-08-06 21:24:41,996 INFO [trainer.py:765] (7/8) Epoch 31, batch 1800, train_loss[loss=2.851, NarTop10Accuracy=0.7572, over 7140.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7149, over 5969.53 frames. ], batch size: 22, lr: 2.74e-03
2024-08-06 21:25:08,357 INFO [trainer.py:765] (7/8) Epoch 31, batch 1900, train_loss[loss=3.166, NarTop10Accuracy=0.6898, over 6372.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7134, over 6011.33 frames. ], batch size: 51, lr: 2.74e-03
2024-08-06 21:25:33,773 INFO [trainer.py:765] (7/8) Epoch 31, batch 2000, train_loss[loss=3.059, NarTop10Accuracy=0.7199, over 5613.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7147, over 5997.85 frames. ], batch size: 50, lr: 2.74e-03
2024-08-06 21:25:59,106 INFO [trainer.py:765] (7/8) Epoch 31, batch 2100, train_loss[loss=2.726, NarTop10Accuracy=0.7792, over 3903.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7157, over 5981.71 frames. ], batch size: 4, lr: 2.73e-03
2024-08-06 21:26:24,238 INFO [trainer.py:765] (7/8) Epoch 31, batch 2200, train_loss[loss=2.942, NarTop10Accuracy=0.7359, over 7050.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7178, over 6022.25 frames. ], batch size: 31, lr: 2.73e-03
2024-08-06 21:26:49,322 INFO [trainer.py:765] (7/8) Epoch 31, batch 2300, train_loss[loss=2.785, NarTop10Accuracy=0.7659, over 5628.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7139, over 6026.59 frames. ], batch size: 9, lr: 2.73e-03
2024-08-06 21:27:13,608 INFO [trainer.py:765] (7/8) Epoch 31, batch 2400, train_loss[loss=2.835, NarTop10Accuracy=0.7507, over 5097.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7153, over 5784.11 frames. ], batch size: 7, lr: 2.73e-03
2024-08-06 21:27:37,027 INFO [trainer.py:765] (7/8) Epoch 31, batch 2500, train_loss[loss=2.995, NarTop10Accuracy=0.7351, over 5082.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7178, over 5491.06 frames. ], batch size: 7, lr: 2.73e-03
2024-08-06 21:27:57,305 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 21:28:49,393 INFO [trainer.py:765] (7/8) Epoch 32, batch 100, train_loss[loss=2.926, NarTop10Accuracy=0.7467, over 7299.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7131, over 2373.50 frames. ], batch size: 31, lr: 2.68e-03
2024-08-06 21:29:08,161 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 21:29:16,392 INFO [trainer.py:811] (7/8) Epoch 32, validation: loss=2.919, NarTop10Accuracy=0.7409, over 1905321.00 frames. 
2024-08-06 21:29:16,393 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 21:29:16,939 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 32, batch 200, train_loss[loss=3.227, NarTop10Accuracy=0.6725, over 6948.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7117, over 3867.85 frames. ], batch size: 17, lr: 2.68e-03
2024-08-06 21:30:05,278 INFO [trainer.py:765] (7/8) Epoch 32, batch 300, train_loss[loss=3.029, NarTop10Accuracy=0.7196, over 7050.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7161, over 4665.13 frames. ], batch size: 22, lr: 2.68e-03
2024-08-06 21:30:34,103 INFO [trainer.py:765] (7/8) Epoch 32, batch 400, train_loss[loss=2.789, NarTop10Accuracy=0.7694, over 5100.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7129, over 5118.66 frames. ], batch size: 7, lr: 2.68e-03
2024-08-06 21:31:13,530 INFO [trainer.py:765] (7/8) Epoch 32, batch 500, train_loss[loss=2.953, NarTop10Accuracy=0.7297, over 6030.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7155, over 5390.55 frames. ], batch size: 11, lr: 2.67e-03
2024-08-06 21:31:42,486 INFO [trainer.py:765] (7/8) Epoch 32, batch 600, train_loss[loss=3.203, NarTop10Accuracy=0.6876, over 5901.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7163, over 5667.18 frames. ], batch size: 9, lr: 2.67e-03
2024-08-06 21:32:17,029 INFO [trainer.py:765] (7/8) Epoch 32, batch 700, train_loss[loss=2.717, NarTop10Accuracy=0.7833, over 4995.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7176, over 5739.24 frames. ], batch size: 6, lr: 2.67e-03
2024-08-06 21:33:00,646 INFO [trainer.py:765] (7/8) Epoch 32, batch 800, train_loss[loss=3.546, NarTop10Accuracy=0.6217, over 4170.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7173, over 5777.54 frames. ], batch size: 5, lr: 2.67e-03
2024-08-06 21:33:28,991 INFO [trainer.py:765] (7/8) Epoch 32, batch 900, train_loss[loss=2.82, NarTop10Accuracy=0.7615, over 6198.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7191, over 5803.29 frames. ], batch size: 13, lr: 2.67e-03
2024-08-06 21:34:04,049 INFO [trainer.py:765] (7/8) Epoch 32, batch 1000, train_loss[loss=3.261, NarTop10Accuracy=0.6762, over 6591.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7159, over 5903.71 frames. ], batch size: 14, lr: 2.67e-03
2024-08-06 21:34:46,674 INFO [trainer.py:765] (7/8) Epoch 32, batch 1100, train_loss[loss=3.222, NarTop10Accuracy=0.6764, over 6882.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7147, over 5930.84 frames. ], batch size: 17, lr: 2.66e-03
2024-08-06 21:35:18,172 INFO [trainer.py:765] (7/8) Epoch 32, batch 1200, train_loss[loss=3.248, NarTop10Accuracy=0.6764, over 7104.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7137, over 5938.04 frames. ], batch size: 31, lr: 2.66e-03
2024-08-06 21:35:52,801 INFO [trainer.py:765] (7/8) Epoch 32, batch 1300, train_loss[loss=3.343, NarTop10Accuracy=0.651, over 5046.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7123, over 6001.77 frames. ], batch size: 6, lr: 2.66e-03
2024-08-06 21:36:29,478 INFO [trainer.py:765] (7/8) Epoch 32, batch 1400, train_loss[loss=3.386, NarTop10Accuracy=0.6446, over 6054.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7121, over 6004.18 frames. ], batch size: 11, lr: 2.66e-03
2024-08-06 21:37:04,733 INFO [trainer.py:765] (7/8) Epoch 32, batch 1500, train_loss[loss=3.465, NarTop10Accuracy=0.633, over 5976.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.713, over 5945.07 frames. ], batch size: 51, lr: 2.66e-03
2024-08-06 21:37:32,521 INFO [trainer.py:765] (7/8) Epoch 32, batch 1600, train_loss[loss=3.042, NarTop10Accuracy=0.7117, over 6975.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7142, over 5917.70 frames. ], batch size: 22, lr: 2.66e-03
2024-08-06 21:37:59,160 INFO [trainer.py:765] (7/8) Epoch 32, batch 1700, train_loss[loss=3.096, NarTop10Accuracy=0.7082, over 6696.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7145, over 5912.66 frames. ], batch size: 14, lr: 2.65e-03
2024-08-06 21:38:25,703 INFO [trainer.py:765] (7/8) Epoch 32, batch 1800, train_loss[loss=3.081, NarTop10Accuracy=0.7178, over 7125.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7144, over 5980.91 frames. ], batch size: 22, lr: 2.65e-03
2024-08-06 21:38:52,170 INFO [trainer.py:765] (7/8) Epoch 32, batch 1900, train_loss[loss=3.075, NarTop10Accuracy=0.6994, over 5730.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7106, over 6019.43 frames. ], batch size: 50, lr: 2.65e-03
2024-08-06 21:39:17,769 INFO [trainer.py:765] (7/8) Epoch 32, batch 2000, train_loss[loss=3.51, NarTop10Accuracy=0.6253, over 5997.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7137, over 5985.46 frames. ], batch size: 50, lr: 2.65e-03
2024-08-06 21:39:43,179 INFO [trainer.py:765] (7/8) Epoch 32, batch 2100, train_loss[loss=2.699, NarTop10Accuracy=0.7882, over 4836.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7144, over 5961.46 frames. ], batch size: 5, lr: 2.65e-03
2024-08-06 21:39:54,782 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 21:40:02,941 INFO [trainer.py:811] (7/8) Epoch 32, validation: loss=2.886, NarTop10Accuracy=0.7482, over 1905321.00 frames. 
2024-08-06 21:40:02,942 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 21:40:03,423 INFO [optim.py:386] (7/8) 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 21:40:16,629 INFO [trainer.py:765] (7/8) Epoch 32, batch 2200, train_loss[loss=3.04, NarTop10Accuracy=0.7169, over 7242.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7142, over 6006.19 frames. ], batch size: 31, lr: 2.65e-03
2024-08-06 21:40:41,717 INFO [trainer.py:765] (7/8) Epoch 32, batch 2300, train_loss[loss=3.303, NarTop10Accuracy=0.6646, over 5691.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7097, over 6009.73 frames. ], batch size: 9, lr: 2.65e-03
2024-08-06 21:41:06,072 INFO [trainer.py:765] (7/8) Epoch 32, batch 2400, train_loss[loss=3.216, NarTop10Accuracy=0.6758, over 5070.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7134, over 5781.42 frames. ], batch size: 7, lr: 2.64e-03
2024-08-06 21:41:29,538 INFO [trainer.py:765] (7/8) Epoch 32, batch 2500, train_loss[loss=2.741, NarTop10Accuracy=0.7778, over 5184.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7207, over 5461.12 frames. ], batch size: 7, lr: 2.64e-03
2024-08-06 21:41:49,414 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 21:42:47,615 INFO [trainer.py:765] (7/8) Epoch 33, batch 100, train_loss[loss=3.004, NarTop10Accuracy=0.7183, over 7344.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7227, over 2367.45 frames. ], batch size: 31, lr: 2.60e-03
2024-08-06 21:43:22,368 INFO [trainer.py:765] (7/8) Epoch 33, batch 200, train_loss[loss=2.833, NarTop10Accuracy=0.7635, over 7017.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7198, over 3849.85 frames. ], batch size: 18, lr: 2.60e-03
2024-08-06 21:43:56,513 INFO [trainer.py:765] (7/8) Epoch 33, batch 300, train_loss[loss=3.417, NarTop10Accuracy=0.6426, over 6948.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7154, over 4642.62 frames. ], batch size: 22, lr: 2.60e-03
2024-08-06 21:44:30,316 INFO [trainer.py:765] (7/8) Epoch 33, batch 400, train_loss[loss=2.915, NarTop10Accuracy=0.7426, over 5097.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7167, over 5095.28 frames. ], batch size: 7, lr: 2.59e-03
2024-08-06 21:45:02,870 INFO [trainer.py:765] (7/8) Epoch 33, batch 500, train_loss[loss=2.779, NarTop10Accuracy=0.7731, over 5949.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7208, over 5380.06 frames. ], batch size: 11, lr: 2.59e-03
2024-08-06 21:45:36,226 INFO [trainer.py:765] (7/8) Epoch 33, batch 600, train_loss[loss=3.48, NarTop10Accuracy=0.6282, over 5736.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7143, over 5653.67 frames. ], batch size: 9, lr: 2.59e-03
2024-08-06 21:46:11,317 INFO [trainer.py:765] (7/8) Epoch 33, batch 700, train_loss[loss=2.762, NarTop10Accuracy=0.7782, over 4920.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7137, over 5708.30 frames. ], batch size: 6, lr: 2.59e-03
2024-08-06 21:46:46,169 INFO [trainer.py:765] (7/8) Epoch 33, batch 800, train_loss[loss=2.573, NarTop10Accuracy=0.8067, over 4977.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7153, over 5790.89 frames. ], batch size: 6, lr: 2.59e-03
2024-08-06 21:47:18,908 INFO [trainer.py:765] (7/8) Epoch 33, batch 900, train_loss[loss=3.28, NarTop10Accuracy=0.669, over 6201.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.713, over 5796.95 frames. ], batch size: 13, lr: 2.59e-03
2024-08-06 21:47:57,316 INFO [trainer.py:765] (7/8) Epoch 33, batch 1000, train_loss[loss=2.978, NarTop10Accuracy=0.7267, over 6240.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7131, over 5896.52 frames. ], batch size: 13, lr: 2.58e-03
2024-08-06 21:48:30,908 INFO [trainer.py:765] (7/8) Epoch 33, batch 1100, train_loss[loss=2.833, NarTop10Accuracy=0.7679, over 6708.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7101, over 5939.64 frames. ], batch size: 17, lr: 2.58e-03
2024-08-06 21:49:06,660 INFO [trainer.py:765] (7/8) Epoch 33, batch 1200, train_loss[loss=2.911, NarTop10Accuracy=0.7409, over 7311.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7125, over 5920.57 frames. ], batch size: 31, lr: 2.58e-03
2024-08-06 21:49:42,816 INFO [trainer.py:765] (7/8) Epoch 33, batch 1300, train_loss[loss=2.934, NarTop10Accuracy=0.7397, over 5061.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7133, over 5986.05 frames. ], batch size: 6, lr: 2.58e-03
2024-08-06 21:50:17,310 INFO [trainer.py:765] (7/8) Epoch 33, batch 1400, train_loss[loss=3.201, NarTop10Accuracy=0.6814, over 6063.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7125, over 6011.37 frames. ], batch size: 11, lr: 2.58e-03
2024-08-06 21:50:45,370 INFO [trainer.py:765] (7/8) Epoch 33, batch 1500, train_loss[loss=2.96, NarTop10Accuracy=0.7292, over 5757.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7143, over 5934.06 frames. ], batch size: 50, lr: 2.58e-03
2024-08-06 21:51:04,607 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 21:51:12,662 INFO [trainer.py:811] (7/8) Epoch 33, validation: loss=2.938, NarTop10Accuracy=0.7372, over 1905321.00 frames. 
2024-08-06 21:51:12,662 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 21:51:13,180 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 33, batch 1600, train_loss[loss=3.215, NarTop10Accuracy=0.6845, over 6966.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7168, over 5922.62 frames. ], batch size: 22, lr: 2.57e-03
2024-08-06 21:51:47,922 INFO [trainer.py:765] (7/8) Epoch 33, batch 1700, train_loss[loss=2.707, NarTop10Accuracy=0.795, over 6186.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7138, over 5906.55 frames. ], batch size: 13, lr: 2.57e-03
2024-08-06 21:52:14,392 INFO [trainer.py:765] (7/8) Epoch 33, batch 1800, train_loss[loss=2.833, NarTop10Accuracy=0.7599, over 7104.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7146, over 5975.83 frames. ], batch size: 22, lr: 2.57e-03
2024-08-06 21:52:40,856 INFO [trainer.py:765] (7/8) Epoch 33, batch 1900, train_loss[loss=3.522, NarTop10Accuracy=0.6217, over 6045.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7106, over 6021.18 frames. ], batch size: 51, lr: 2.57e-03
2024-08-06 21:53:06,352 INFO [trainer.py:765] (7/8) Epoch 33, batch 2000, train_loss[loss=3.477, NarTop10Accuracy=0.6294, over 6237.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7169, over 5980.85 frames. ], batch size: 51, lr: 2.57e-03
2024-08-06 21:53:31,658 INFO [trainer.py:765] (7/8) Epoch 33, batch 2100, train_loss[loss=3.393, NarTop10Accuracy=0.6405, over 4827.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7153, over 5960.59 frames. ], batch size: 5, lr: 2.57e-03
2024-08-06 21:53:56,890 INFO [trainer.py:765] (7/8) Epoch 33, batch 2200, train_loss[loss=3.423, NarTop10Accuracy=0.6417, over 7323.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7137, over 5995.44 frames. ], batch size: 31, lr: 2.57e-03
2024-08-06 21:54:21,990 INFO [trainer.py:765] (7/8) Epoch 33, batch 2300, train_loss[loss=2.878, NarTop10Accuracy=0.7543, over 5730.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7143, over 6007.08 frames. ], batch size: 9, lr: 2.56e-03
2024-08-06 21:54:46,429 INFO [trainer.py:765] (7/8) Epoch 33, batch 2400, train_loss[loss=2.739, NarTop10Accuracy=0.7745, over 5073.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7185, over 5782.94 frames. ], batch size: 7, lr: 2.56e-03
2024-08-06 21:55:09,862 INFO [trainer.py:765] (7/8) Epoch 33, batch 2500, train_loss[loss=2.73, NarTop10Accuracy=0.7813, over 5073.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7221, over 5473.95 frames. ], batch size: 7, lr: 2.56e-03
2024-08-06 21:55:29,695 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 21:56:24,721 INFO [trainer.py:765] (7/8) Epoch 34, batch 100, train_loss[loss=3.395, NarTop10Accuracy=0.6403, over 7227.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7164, over 2369.93 frames. ], batch size: 31, lr: 2.52e-03
2024-08-06 21:56:55,613 INFO [trainer.py:765] (7/8) Epoch 34, batch 200, train_loss[loss=3.112, NarTop10Accuracy=0.7052, over 6777.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7217, over 3875.44 frames. ], batch size: 17, lr: 2.52e-03
2024-08-06 21:57:31,777 INFO [trainer.py:765] (7/8) Epoch 34, batch 300, train_loss[loss=2.82, NarTop10Accuracy=0.765, over 7380.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7192, over 4670.75 frames. ], batch size: 23, lr: 2.52e-03
2024-08-06 21:58:02,724 INFO [trainer.py:765] (7/8) Epoch 34, batch 400, train_loss[loss=3.099, NarTop10Accuracy=0.7112, over 5124.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7234, over 5098.39 frames. ], batch size: 7, lr: 2.52e-03
2024-08-06 21:58:34,690 INFO [trainer.py:765] (7/8) Epoch 34, batch 500, train_loss[loss=3.198, NarTop10Accuracy=0.6873, over 6201.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7207, over 5377.95 frames. ], batch size: 11, lr: 2.51e-03
2024-08-06 21:59:09,616 INFO [trainer.py:765] (7/8) Epoch 34, batch 600, train_loss[loss=2.894, NarTop10Accuracy=0.7427, over 5691.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7191, over 5648.95 frames. ], batch size: 9, lr: 2.51e-03
2024-08-06 21:59:46,056 INFO [trainer.py:765] (7/8) Epoch 34, batch 700, train_loss[loss=3.169, NarTop10Accuracy=0.6918, over 5010.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7179, over 5716.17 frames. ], batch size: 6, lr: 2.51e-03
2024-08-06 22:00:17,575 INFO [trainer.py:765] (7/8) Epoch 34, batch 800, train_loss[loss=2.856, NarTop10Accuracy=0.7543, over 5106.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.72, over 5763.49 frames. ], batch size: 6, lr: 2.51e-03
2024-08-06 22:00:49,874 INFO [trainer.py:765] (7/8) Epoch 34, batch 900, train_loss[loss=2.901, NarTop10Accuracy=0.7474, over 6258.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.72, over 5790.58 frames. ], batch size: 13, lr: 2.51e-03
2024-08-06 22:01:25,338 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 22:01:33,386 INFO [trainer.py:811] (7/8) Epoch 34, validation: loss=2.9, NarTop10Accuracy=0.7444, over 1905321.00 frames. 
2024-08-06 22:01:33,387 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 22:01:34,091 INFO [optim.py:386] (7/8) Clipping_scale=2.0, grad-norm quartiles 1.819e+02 2.259e+02 2.434e+02 2.615e+02 5.125e+02, threshold=4.868e+02, percent-clipped=0.1
2024-08-06 22:01:35,624 INFO [trainer.py:765] (7/8) Epoch 34, batch 1000, train_loss[loss=3.454, NarTop10Accuracy=0.6373, over 6291.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7171, over 5913.30 frames. ], batch size: 13, lr: 2.51e-03
2024-08-06 22:02:10,830 INFO [trainer.py:765] (7/8) Epoch 34, batch 1100, train_loss[loss=3.221, NarTop10Accuracy=0.6749, over 6942.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7153, over 5947.16 frames. ], batch size: 17, lr: 2.51e-03
2024-08-06 22:02:46,786 INFO [trainer.py:765] (7/8) Epoch 34, batch 1200, train_loss[loss=2.929, NarTop10Accuracy=0.7474, over 7257.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7172, over 5943.83 frames. ], batch size: 31, lr: 2.50e-03
2024-08-06 22:03:20,814 INFO [trainer.py:765] (7/8) Epoch 34, batch 1300, train_loss[loss=2.66, NarTop10Accuracy=0.7867, over 5007.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7175, over 5987.30 frames. ], batch size: 6, lr: 2.50e-03
2024-08-06 22:03:52,949 INFO [trainer.py:765] (7/8) Epoch 34, batch 1400, train_loss[loss=3.278, NarTop10Accuracy=0.6647, over 5997.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7178, over 5994.47 frames. ], batch size: 11, lr: 2.50e-03
2024-08-06 22:04:20,822 INFO [trainer.py:765] (7/8) Epoch 34, batch 1500, train_loss[loss=3.028, NarTop10Accuracy=0.7168, over 6453.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7177, over 5925.81 frames. ], batch size: 50, lr: 2.50e-03
2024-08-06 22:04:48,600 INFO [trainer.py:765] (7/8) Epoch 34, batch 1600, train_loss[loss=2.864, NarTop10Accuracy=0.7462, over 7269.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.716, over 5900.95 frames. ], batch size: 22, lr: 2.50e-03
2024-08-06 22:05:15,241 INFO [trainer.py:765] (7/8) Epoch 34, batch 1700, train_loss[loss=3.109, NarTop10Accuracy=0.7041, over 6183.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7175, over 5902.94 frames. ], batch size: 13, lr: 2.50e-03
2024-08-06 22:05:41,720 INFO [trainer.py:765] (7/8) Epoch 34, batch 1800, train_loss[loss=3.347, NarTop10Accuracy=0.6595, over 7122.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7165, over 5977.33 frames. ], batch size: 22, lr: 2.50e-03
2024-08-06 22:06:08,207 INFO [trainer.py:765] (7/8) Epoch 34, batch 1900, train_loss[loss=3.187, NarTop10Accuracy=0.6934, over 5769.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7125, over 6016.52 frames. ], batch size: 50, lr: 2.49e-03
2024-08-06 22:06:33,770 INFO [trainer.py:765] (7/8) Epoch 34, batch 2000, train_loss[loss=3.071, NarTop10Accuracy=0.7131, over 5952.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7158, over 5982.59 frames. ], batch size: 50, lr: 2.49e-03
2024-08-06 22:06:59,126 INFO [trainer.py:765] (7/8) Epoch 34, batch 2100, train_loss[loss=3.101, NarTop10Accuracy=0.6982, over 3879.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.714, over 5956.93 frames. ], batch size: 4, lr: 2.49e-03
2024-08-06 22:07:24,398 INFO [trainer.py:765] (7/8) Epoch 34, batch 2200, train_loss[loss=2.953, NarTop10Accuracy=0.742, over 7182.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7132, over 5990.43 frames. ], batch size: 31, lr: 2.49e-03
2024-08-06 22:07:49,535 INFO [trainer.py:765] (7/8) Epoch 34, batch 2300, train_loss[loss=2.757, NarTop10Accuracy=0.7797, over 5715.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7135, over 6013.13 frames. ], batch size: 9, lr: 2.49e-03
2024-08-06 22:08:14,059 INFO [trainer.py:765] (7/8) Epoch 34, batch 2400, train_loss[loss=3.282, NarTop10Accuracy=0.6612, over 5058.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.714, over 5756.24 frames. ], batch size: 7, lr: 2.49e-03
2024-08-06 22:08:37,648 INFO [trainer.py:765] (7/8) Epoch 34, batch 2500, train_loss[loss=2.757, NarTop10Accuracy=0.7772, over 5106.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7205, over 5461.99 frames. ], batch size: 7, lr: 2.49e-03
2024-08-06 22:08:57,311 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 22:09:52,640 INFO [trainer.py:765] (7/8) Epoch 35, batch 100, train_loss[loss=2.868, NarTop10Accuracy=0.7509, over 7587.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.717, over 2381.69 frames. ], batch size: 32, lr: 2.45e-03
2024-08-06 22:10:29,697 INFO [trainer.py:765] (7/8) Epoch 35, batch 200, train_loss[loss=3.144, NarTop10Accuracy=0.6942, over 6921.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7152, over 3850.19 frames. ], batch size: 17, lr: 2.45e-03
2024-08-06 22:11:04,942 INFO [trainer.py:765] (7/8) Epoch 35, batch 300, train_loss[loss=2.868, NarTop10Accuracy=0.7586, over 6918.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.719, over 4649.18 frames. ], batch size: 22, lr: 2.44e-03
2024-08-06 22:11:35,333 INFO [trainer.py:765] (7/8) Epoch 35, batch 400, train_loss[loss=3.002, NarTop10Accuracy=0.7258, over 5094.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7195, over 5089.80 frames. ], batch size: 7, lr: 2.44e-03
2024-08-06 22:11:40,047 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 22:11:48,129 INFO [trainer.py:811] (7/8) Epoch 35, validation: loss=2.84, NarTop10Accuracy=0.7576, over 1905321.00 frames. 
2024-08-06 22:11:48,130 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 22:11:48,702 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 35, batch 500, train_loss[loss=2.69, NarTop10Accuracy=0.7938, over 6156.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7212, over 5390.71 frames. ], batch size: 11, lr: 2.44e-03
2024-08-06 22:12:51,425 INFO [trainer.py:765] (7/8) Epoch 35, batch 600, train_loss[loss=3.312, NarTop10Accuracy=0.6562, over 5757.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7176, over 5648.42 frames. ], batch size: 9, lr: 2.44e-03
2024-08-06 22:13:24,941 INFO [trainer.py:765] (7/8) Epoch 35, batch 700, train_loss[loss=2.56, NarTop10Accuracy=0.8134, over 4212.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7174, over 5700.28 frames. ], batch size: 5, lr: 2.44e-03
2024-08-06 22:14:01,384 INFO [trainer.py:765] (7/8) Epoch 35, batch 800, train_loss[loss=2.841, NarTop10Accuracy=0.7628, over 5154.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7162, over 5773.98 frames. ], batch size: 6, lr: 2.44e-03
2024-08-06 22:14:34,372 INFO [trainer.py:765] (7/8) Epoch 35, batch 900, train_loss[loss=3.272, NarTop10Accuracy=0.6703, over 6684.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7194, over 5805.15 frames. ], batch size: 14, lr: 2.44e-03
2024-08-06 22:15:09,372 INFO [trainer.py:765] (7/8) Epoch 35, batch 1000, train_loss[loss=2.826, NarTop10Accuracy=0.7549, over 6183.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7165, over 5900.18 frames. ], batch size: 13, lr: 2.43e-03
2024-08-06 22:15:48,495 INFO [trainer.py:765] (7/8) Epoch 35, batch 1100, train_loss[loss=3.049, NarTop10Accuracy=0.7174, over 6801.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7162, over 5956.17 frames. ], batch size: 17, lr: 2.43e-03
2024-08-06 22:16:22,484 INFO [trainer.py:765] (7/8) Epoch 35, batch 1200, train_loss[loss=2.876, NarTop10Accuracy=0.7459, over 6858.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.719, over 5941.31 frames. ], batch size: 31, lr: 2.43e-03
2024-08-06 22:16:57,060 INFO [trainer.py:765] (7/8) Epoch 35, batch 1300, train_loss[loss=2.895, NarTop10Accuracy=0.7432, over 5037.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7202, over 6012.60 frames. ], batch size: 6, lr: 2.43e-03
2024-08-06 22:17:31,061 INFO [trainer.py:765] (7/8) Epoch 35, batch 1400, train_loss[loss=3.167, NarTop10Accuracy=0.6973, over 6132.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7175, over 6012.71 frames. ], batch size: 11, lr: 2.43e-03
2024-08-06 22:18:03,062 INFO [trainer.py:765] (7/8) Epoch 35, batch 1500, train_loss[loss=3.084, NarTop10Accuracy=0.7109, over 6159.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7178, over 5950.98 frames. ], batch size: 50, lr: 2.43e-03
2024-08-06 22:18:30,728 INFO [trainer.py:765] (7/8) Epoch 35, batch 1600, train_loss[loss=2.946, NarTop10Accuracy=0.7388, over 7236.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7158, over 5924.79 frames. ], batch size: 23, lr: 2.43e-03
2024-08-06 22:18:57,320 INFO [trainer.py:765] (7/8) Epoch 35, batch 1700, train_loss[loss=2.749, NarTop10Accuracy=0.782, over 6339.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.715, over 5910.95 frames. ], batch size: 13, lr: 2.42e-03
2024-08-06 22:19:23,703 INFO [trainer.py:765] (7/8) Epoch 35, batch 1800, train_loss[loss=3.423, NarTop10Accuracy=0.6366, over 6780.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7166, over 5971.66 frames. ], batch size: 22, lr: 2.42e-03
2024-08-06 22:19:50,201 INFO [trainer.py:765] (7/8) Epoch 35, batch 1900, train_loss[loss=3.213, NarTop10Accuracy=0.6807, over 6285.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7143, over 6018.41 frames. ], batch size: 52, lr: 2.42e-03
2024-08-06 22:20:15,762 INFO [trainer.py:765] (7/8) Epoch 35, batch 2000, train_loss[loss=3.151, NarTop10Accuracy=0.7039, over 5703.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7174, over 5992.14 frames. ], batch size: 50, lr: 2.42e-03
2024-08-06 22:20:41,045 INFO [trainer.py:765] (7/8) Epoch 35, batch 2100, train_loss[loss=2.495, NarTop10Accuracy=0.8225, over 3858.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7171, over 5975.90 frames. ], batch size: 4, lr: 2.42e-03
2024-08-06 22:21:06,226 INFO [trainer.py:765] (7/8) Epoch 35, batch 2200, train_loss[loss=2.943, NarTop10Accuracy=0.74, over 7560.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7161, over 6008.86 frames. ], batch size: 32, lr: 2.42e-03
2024-08-06 22:21:31,286 INFO [trainer.py:765] (7/8) Epoch 35, batch 2300, train_loss[loss=3.001, NarTop10Accuracy=0.7259, over 5784.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7151, over 6022.91 frames. ], batch size: 9, lr: 2.42e-03
2024-08-06 22:21:55,648 INFO [trainer.py:765] (7/8) Epoch 35, batch 2400, train_loss[loss=3.082, NarTop10Accuracy=0.6999, over 5097.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7174, over 5772.33 frames. ], batch size: 7, lr: 2.42e-03
2024-08-06 22:21:59,681 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 22:22:07,656 INFO [trainer.py:811] (7/8) Epoch 35, validation: loss=2.905, NarTop10Accuracy=0.7437, over 1905321.00 frames. 
2024-08-06 22:22:07,657 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 22:22:08,116 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 35, batch 2500, train_loss[loss=3.031, NarTop10Accuracy=0.7234, over 5274.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7203, over 5457.30 frames. ], batch size: 7, lr: 2.41e-03
2024-08-06 22:22:46,832 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 22:23:47,171 INFO [trainer.py:765] (7/8) Epoch 36, batch 100, train_loss[loss=3.149, NarTop10Accuracy=0.6958, over 7503.00 frames. ], tot_loss[loss=2.99, NarTop10Accuracy=0.7278, over 2367.45 frames. ], batch size: 31, lr: 2.38e-03
2024-08-06 22:24:22,494 INFO [trainer.py:765] (7/8) Epoch 36, batch 200, train_loss[loss=2.816, NarTop10Accuracy=0.7594, over 6831.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7219, over 3851.26 frames. ], batch size: 17, lr: 2.38e-03
2024-08-06 22:24:54,721 INFO [trainer.py:765] (7/8) Epoch 36, batch 300, train_loss[loss=3.256, NarTop10Accuracy=0.675, over 6984.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7199, over 4664.03 frames. ], batch size: 22, lr: 2.37e-03
2024-08-06 22:25:29,275 INFO [trainer.py:765] (7/8) Epoch 36, batch 400, train_loss[loss=2.938, NarTop10Accuracy=0.7314, over 5073.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7223, over 5120.57 frames. ], batch size: 7, lr: 2.37e-03
2024-08-06 22:26:01,818 INFO [trainer.py:765] (7/8) Epoch 36, batch 500, train_loss[loss=3.425, NarTop10Accuracy=0.6391, over 6180.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7217, over 5386.72 frames. ], batch size: 11, lr: 2.37e-03
2024-08-06 22:26:35,025 INFO [trainer.py:765] (7/8) Epoch 36, batch 600, train_loss[loss=2.927, NarTop10Accuracy=0.7352, over 5655.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7225, over 5662.41 frames. ], batch size: 9, lr: 2.37e-03
2024-08-06 22:27:10,990 INFO [trainer.py:765] (7/8) Epoch 36, batch 700, train_loss[loss=3.266, NarTop10Accuracy=0.6563, over 5019.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7216, over 5734.71 frames. ], batch size: 6, lr: 2.37e-03
2024-08-06 22:27:44,915 INFO [trainer.py:765] (7/8) Epoch 36, batch 800, train_loss[loss=3.251, NarTop10Accuracy=0.6743, over 4998.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.719, over 5803.00 frames. ], batch size: 6, lr: 2.37e-03
2024-08-06 22:28:17,812 INFO [trainer.py:765] (7/8) Epoch 36, batch 900, train_loss[loss=2.686, NarTop10Accuracy=0.7824, over 6141.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7216, over 5813.04 frames. ], batch size: 13, lr: 2.37e-03
2024-08-06 22:28:56,983 INFO [trainer.py:765] (7/8) Epoch 36, batch 1000, train_loss[loss=3.379, NarTop10Accuracy=0.6516, over 6639.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7202, over 5912.65 frames. ], batch size: 14, lr: 2.37e-03
2024-08-06 22:29:29,364 INFO [trainer.py:765] (7/8) Epoch 36, batch 1100, train_loss[loss=2.937, NarTop10Accuracy=0.7376, over 7011.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7196, over 5935.35 frames. ], batch size: 17, lr: 2.36e-03
2024-08-06 22:30:05,680 INFO [trainer.py:765] (7/8) Epoch 36, batch 1200, train_loss[loss=3.135, NarTop10Accuracy=0.6986, over 7029.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7214, over 5949.10 frames. ], batch size: 31, lr: 2.36e-03
2024-08-06 22:30:42,576 INFO [trainer.py:765] (7/8) Epoch 36, batch 1300, train_loss[loss=2.805, NarTop10Accuracy=0.7738, over 5139.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7192, over 6011.70 frames. ], batch size: 6, lr: 2.36e-03
2024-08-06 22:31:15,938 INFO [trainer.py:765] (7/8) Epoch 36, batch 1400, train_loss[loss=3.066, NarTop10Accuracy=0.7125, over 6057.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7219, over 6026.03 frames. ], batch size: 11, lr: 2.36e-03
2024-08-06 22:31:43,748 INFO [trainer.py:765] (7/8) Epoch 36, batch 1500, train_loss[loss=3.37, NarTop10Accuracy=0.6549, over 5781.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7194, over 5954.20 frames. ], batch size: 50, lr: 2.36e-03
2024-08-06 22:32:11,459 INFO [trainer.py:765] (7/8) Epoch 36, batch 1600, train_loss[loss=3.461, NarTop10Accuracy=0.6331, over 6867.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7198, over 5939.52 frames. ], batch size: 22, lr: 2.36e-03
2024-08-06 22:32:38,108 INFO [trainer.py:765] (7/8) Epoch 36, batch 1700, train_loss[loss=3.334, NarTop10Accuracy=0.6559, over 6633.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.717, over 5914.78 frames. ], batch size: 14, lr: 2.36e-03
2024-08-06 22:33:04,554 INFO [trainer.py:765] (7/8) Epoch 36, batch 1800, train_loss[loss=3.031, NarTop10Accuracy=0.7101, over 7200.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7179, over 5975.87 frames. ], batch size: 23, lr: 2.36e-03
2024-08-06 22:33:15,170 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 22:33:23,567 INFO [trainer.py:811] (7/8) Epoch 36, validation: loss=2.897, NarTop10Accuracy=0.7457, over 1905321.00 frames. 
2024-08-06 22:33:23,568 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 22:33:24,096 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 36, batch 1900, train_loss[loss=2.985, NarTop10Accuracy=0.7314, over 6270.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7182, over 6009.02 frames. ], batch size: 51, lr: 2.35e-03
2024-08-06 22:34:05,077 INFO [trainer.py:765] (7/8) Epoch 36, batch 2000, train_loss[loss=3.247, NarTop10Accuracy=0.6822, over 5676.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7194, over 5995.75 frames. ], batch size: 50, lr: 2.35e-03
2024-08-06 22:34:30,515 INFO [trainer.py:765] (7/8) Epoch 36, batch 2100, train_loss[loss=2.727, NarTop10Accuracy=0.7776, over 4929.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7199, over 5969.94 frames. ], batch size: 5, lr: 2.35e-03
2024-08-06 22:34:55,938 INFO [trainer.py:765] (7/8) Epoch 36, batch 2200, train_loss[loss=3.381, NarTop10Accuracy=0.6481, over 7278.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7165, over 6012.86 frames. ], batch size: 31, lr: 2.35e-03
2024-08-06 22:35:21,146 INFO [trainer.py:765] (7/8) Epoch 36, batch 2300, train_loss[loss=3.267, NarTop10Accuracy=0.6713, over 5781.00 frames. ], tot_loss[loss=3.062, NarTop10Accuracy=0.7133, over 6012.03 frames. ], batch size: 9, lr: 2.35e-03
2024-08-06 22:35:45,600 INFO [trainer.py:765] (7/8) Epoch 36, batch 2400, train_loss[loss=3.132, NarTop10Accuracy=0.697, over 5067.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.716, over 5773.03 frames. ], batch size: 7, lr: 2.35e-03
2024-08-06 22:36:09,182 INFO [trainer.py:765] (7/8) Epoch 36, batch 2500, train_loss[loss=2.914, NarTop10Accuracy=0.7443, over 5055.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7207, over 5465.66 frames. ], batch size: 7, lr: 2.35e-03
2024-08-06 22:36:29,006 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 22:37:29,726 INFO [trainer.py:765] (7/8) Epoch 37, batch 100, train_loss[loss=2.839, NarTop10Accuracy=0.7584, over 7320.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7179, over 2389.81 frames. ], batch size: 31, lr: 2.31e-03
2024-08-06 22:38:01,273 INFO [trainer.py:765] (7/8) Epoch 37, batch 200, train_loss[loss=2.742, NarTop10Accuracy=0.7831, over 6696.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7218, over 3865.85 frames. ], batch size: 17, lr: 2.31e-03
2024-08-06 22:38:35,957 INFO [trainer.py:765] (7/8) Epoch 37, batch 300, train_loss[loss=3.247, NarTop10Accuracy=0.6869, over 7425.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7222, over 4647.48 frames. ], batch size: 23, lr: 2.31e-03
2024-08-06 22:39:09,308 INFO [trainer.py:765] (7/8) Epoch 37, batch 400, train_loss[loss=2.744, NarTop10Accuracy=0.7722, over 5232.00 frames. ], tot_loss[loss=3.007, NarTop10Accuracy=0.724, over 5104.66 frames. ], batch size: 7, lr: 2.31e-03
2024-08-06 22:39:43,862 INFO [trainer.py:765] (7/8) Epoch 37, batch 500, train_loss[loss=3.166, NarTop10Accuracy=0.6828, over 6102.00 frames. ], tot_loss[loss=3.007, NarTop10Accuracy=0.7243, over 5390.34 frames. ], batch size: 11, lr: 2.31e-03
2024-08-06 22:40:17,334 INFO [trainer.py:765] (7/8) Epoch 37, batch 600, train_loss[loss=2.799, NarTop10Accuracy=0.766, over 5679.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7228, over 5638.64 frames. ], batch size: 9, lr: 2.31e-03
2024-08-06 22:40:51,617 INFO [trainer.py:765] (7/8) Epoch 37, batch 700, train_loss[loss=3.122, NarTop10Accuracy=0.6967, over 5019.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7185, over 5705.81 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:41:30,566 INFO [trainer.py:765] (7/8) Epoch 37, batch 800, train_loss[loss=2.804, NarTop10Accuracy=0.7601, over 5067.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7176, over 5774.91 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:41:59,084 INFO [trainer.py:765] (7/8) Epoch 37, batch 900, train_loss[loss=2.866, NarTop10Accuracy=0.7523, over 6765.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7214, over 5783.03 frames. ], batch size: 14, lr: 2.30e-03
2024-08-06 22:42:38,268 INFO [trainer.py:765] (7/8) Epoch 37, batch 1000, train_loss[loss=3.193, NarTop10Accuracy=0.6877, over 6624.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7181, over 5878.84 frames. ], batch size: 14, lr: 2.30e-03
2024-08-06 22:43:15,907 INFO [trainer.py:765] (7/8) Epoch 37, batch 1100, train_loss[loss=2.879, NarTop10Accuracy=0.7451, over 6663.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7175, over 5935.60 frames. ], batch size: 17, lr: 2.30e-03
2024-08-06 22:43:47,741 INFO [trainer.py:765] (7/8) Epoch 37, batch 1200, train_loss[loss=2.865, NarTop10Accuracy=0.7544, over 7266.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7163, over 5947.89 frames. ], batch size: 31, lr: 2.30e-03
2024-08-06 22:44:11,755 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 22:44:20,075 INFO [trainer.py:811] (7/8) Epoch 37, validation: loss=2.92, NarTop10Accuracy=0.7407, over 1905321.00 frames. 
2024-08-06 22:44:20,075 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 22:44:20,606 INFO [optim.py:386] (7/8) Clipping_scale=2.0, grad-norm quartiles 1.887e+02 2.309e+02 2.481e+02 2.647e+02 8.766e+02, threshold=4.961e+02, percent-clipped=0.1
2024-08-06 22:44:32,784 INFO [trainer.py:765] (7/8) Epoch 37, batch 1300, train_loss[loss=2.704, NarTop10Accuracy=0.7823, over 4317.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7202, over 6006.19 frames. ], batch size: 5, lr: 2.30e-03
2024-08-06 22:45:10,388 INFO [trainer.py:765] (7/8) Epoch 37, batch 1400, train_loss[loss=2.715, NarTop10Accuracy=0.7778, over 6102.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7202, over 6012.92 frames. ], batch size: 11, lr: 2.30e-03
2024-08-06 22:45:40,512 INFO [trainer.py:765] (7/8) Epoch 37, batch 1500, train_loss[loss=2.855, NarTop10Accuracy=0.7538, over 5712.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7178, over 5958.39 frames. ], batch size: 50, lr: 2.29e-03
2024-08-06 22:46:08,437 INFO [trainer.py:765] (7/8) Epoch 37, batch 1600, train_loss[loss=3.38, NarTop10Accuracy=0.6462, over 7152.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7162, over 5934.97 frames. ], batch size: 22, lr: 2.29e-03
2024-08-06 22:46:35,187 INFO [trainer.py:765] (7/8) Epoch 37, batch 1700, train_loss[loss=3.239, NarTop10Accuracy=0.6796, over 6165.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7164, over 5928.30 frames. ], batch size: 13, lr: 2.29e-03
2024-08-06 22:47:01,793 INFO [trainer.py:765] (7/8) Epoch 37, batch 1800, train_loss[loss=2.799, NarTop10Accuracy=0.7715, over 7215.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7172, over 5997.18 frames. ], batch size: 22, lr: 2.29e-03
2024-08-06 22:47:28,311 INFO [trainer.py:765] (7/8) Epoch 37, batch 1900, train_loss[loss=3.101, NarTop10Accuracy=0.7144, over 6417.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7171, over 6035.92 frames. ], batch size: 51, lr: 2.29e-03
2024-08-06 22:47:53,925 INFO [trainer.py:765] (7/8) Epoch 37, batch 2000, train_loss[loss=3.22, NarTop10Accuracy=0.6877, over 6159.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7189, over 6005.89 frames. ], batch size: 52, lr: 2.29e-03
2024-08-06 22:48:19,325 INFO [trainer.py:765] (7/8) Epoch 37, batch 2100, train_loss[loss=2.877, NarTop10Accuracy=0.742, over 4749.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7177, over 5987.33 frames. ], batch size: 5, lr: 2.29e-03
2024-08-06 22:48:44,707 INFO [trainer.py:765] (7/8) Epoch 37, batch 2200, train_loss[loss=2.886, NarTop10Accuracy=0.7494, over 6933.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.716, over 6033.42 frames. ], batch size: 31, lr: 2.29e-03
2024-08-06 22:49:09,913 INFO [trainer.py:765] (7/8) Epoch 37, batch 2300, train_loss[loss=2.76, NarTop10Accuracy=0.7754, over 5622.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7162, over 6035.09 frames. ], batch size: 9, lr: 2.29e-03
2024-08-06 22:49:34,319 INFO [trainer.py:765] (7/8) Epoch 37, batch 2400, train_loss[loss=3.081, NarTop10Accuracy=0.6997, over 5145.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7205, over 5762.22 frames. ], batch size: 7, lr: 2.28e-03
2024-08-06 22:49:57,860 INFO [trainer.py:765] (7/8) Epoch 37, batch 2500, train_loss[loss=3.082, NarTop10Accuracy=0.6956, over 5112.00 frames. ], tot_loss[loss=2.993, NarTop10Accuracy=0.7265, over 5471.79 frames. ], batch size: 7, lr: 2.28e-03
2024-08-06 22:50:18,049 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 22:51:16,152 INFO [trainer.py:765] (7/8) Epoch 38, batch 100, train_loss[loss=2.988, NarTop10Accuracy=0.7236, over 6948.00 frames. ], tot_loss[loss=3.01, NarTop10Accuracy=0.7235, over 2384.66 frames. ], batch size: 31, lr: 2.25e-03
2024-08-06 22:51:53,015 INFO [trainer.py:765] (7/8) Epoch 38, batch 200, train_loss[loss=3.307, NarTop10Accuracy=0.6631, over 6900.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.721, over 3868.02 frames. ], batch size: 17, lr: 2.25e-03
2024-08-06 22:52:25,203 INFO [trainer.py:765] (7/8) Epoch 38, batch 300, train_loss[loss=2.836, NarTop10Accuracy=0.7658, over 7077.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7181, over 4664.84 frames. ], batch size: 22, lr: 2.25e-03
2024-08-06 22:52:55,627 INFO [trainer.py:765] (7/8) Epoch 38, batch 400, train_loss[loss=3.19, NarTop10Accuracy=0.685, over 5133.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.72, over 5121.69 frames. ], batch size: 7, lr: 2.25e-03
2024-08-06 22:53:32,230 INFO [trainer.py:765] (7/8) Epoch 38, batch 500, train_loss[loss=2.81, NarTop10Accuracy=0.7595, over 6459.00 frames. ], tot_loss[loss=2.993, NarTop10Accuracy=0.7266, over 5408.90 frames. ], batch size: 12, lr: 2.25e-03
2024-08-06 22:54:05,498 INFO [trainer.py:765] (7/8) Epoch 38, batch 600, train_loss[loss=3.218, NarTop10Accuracy=0.6838, over 5757.00 frames. ], tot_loss[loss=3.008, NarTop10Accuracy=0.7237, over 5658.72 frames. ], batch size: 9, lr: 2.24e-03
2024-08-06 22:54:36,003 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 22:54:43,918 INFO [trainer.py:811] (7/8) Epoch 38, validation: loss=2.939, NarTop10Accuracy=0.7369, over 1905321.00 frames. 
2024-08-06 22:54:43,919 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 22:54:44,427 INFO [optim.py:386] (7/8) 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 22:54:46,659 INFO [trainer.py:765] (7/8) Epoch 38, batch 700, train_loss[loss=2.839, NarTop10Accuracy=0.7575, over 5094.00 frames. ], tot_loss[loss=3.007, NarTop10Accuracy=0.7239, over 5721.18 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:55:24,938 INFO [trainer.py:765] (7/8) Epoch 38, batch 800, train_loss[loss=3.01, NarTop10Accuracy=0.7223, over 4965.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.721, over 5782.18 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:55:59,703 INFO [trainer.py:765] (7/8) Epoch 38, batch 900, train_loss[loss=2.843, NarTop10Accuracy=0.7548, over 6156.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7221, over 5804.28 frames. ], batch size: 13, lr: 2.24e-03
2024-08-06 22:56:32,091 INFO [trainer.py:765] (7/8) Epoch 38, batch 1000, train_loss[loss=3.383, NarTop10Accuracy=0.6531, over 6282.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7214, over 5895.93 frames. ], batch size: 13, lr: 2.24e-03
2024-08-06 22:57:08,991 INFO [trainer.py:765] (7/8) Epoch 38, batch 1100, train_loss[loss=2.991, NarTop10Accuracy=0.7278, over 6828.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7186, over 5945.72 frames. ], batch size: 17, lr: 2.24e-03
2024-08-06 22:57:42,662 INFO [trainer.py:765] (7/8) Epoch 38, batch 1200, train_loss[loss=2.878, NarTop10Accuracy=0.759, over 7143.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7178, over 5934.53 frames. ], batch size: 31, lr: 2.24e-03
2024-08-06 22:58:16,546 INFO [trainer.py:765] (7/8) Epoch 38, batch 1300, train_loss[loss=3.248, NarTop10Accuracy=0.6738, over 5010.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7184, over 5999.60 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:58:49,811 INFO [trainer.py:765] (7/8) Epoch 38, batch 1400, train_loss[loss=2.839, NarTop10Accuracy=0.7623, over 6126.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7147, over 6018.39 frames. ], batch size: 11, lr: 2.23e-03
2024-08-06 22:59:22,854 INFO [trainer.py:765] (7/8) Epoch 38, batch 1500, train_loss[loss=3.508, NarTop10Accuracy=0.6178, over 6147.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7185, over 5966.37 frames. ], batch size: 50, lr: 2.23e-03
2024-08-06 22:59:50,644 INFO [trainer.py:765] (7/8) Epoch 38, batch 1600, train_loss[loss=3.354, NarTop10Accuracy=0.6505, over 7293.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7178, over 5939.32 frames. ], batch size: 22, lr: 2.23e-03
2024-08-06 23:00:17,316 INFO [trainer.py:765] (7/8) Epoch 38, batch 1700, train_loss[loss=3.062, NarTop10Accuracy=0.7225, over 6114.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7137, over 5915.81 frames. ], batch size: 13, lr: 2.23e-03
2024-08-06 23:00:43,764 INFO [trainer.py:765] (7/8) Epoch 38, batch 1800, train_loss[loss=3.285, NarTop10Accuracy=0.667, over 7305.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7155, over 5983.55 frames. ], batch size: 23, lr: 2.23e-03
2024-08-06 23:01:10,192 INFO [trainer.py:765] (7/8) Epoch 38, batch 1900, train_loss[loss=3.352, NarTop10Accuracy=0.6619, over 6102.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7157, over 6030.61 frames. ], batch size: 50, lr: 2.23e-03
2024-08-06 23:01:35,681 INFO [trainer.py:765] (7/8) Epoch 38, batch 2000, train_loss[loss=3.366, NarTop10Accuracy=0.6517, over 6282.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7155, over 6000.76 frames. ], batch size: 50, lr: 2.23e-03
2024-08-06 23:02:01,051 INFO [trainer.py:765] (7/8) Epoch 38, batch 2100, train_loss[loss=2.755, NarTop10Accuracy=0.7629, over 3882.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.716, over 5962.01 frames. ], batch size: 4, lr: 2.23e-03
2024-08-06 23:02:26,315 INFO [trainer.py:765] (7/8) Epoch 38, batch 2200, train_loss[loss=2.906, NarTop10Accuracy=0.7393, over 7251.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7157, over 6007.00 frames. ], batch size: 31, lr: 2.23e-03
2024-08-06 23:02:51,420 INFO [trainer.py:765] (7/8) Epoch 38, batch 2300, train_loss[loss=2.697, NarTop10Accuracy=0.7813, over 5580.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7154, over 6030.91 frames. ], batch size: 9, lr: 2.22e-03
2024-08-06 23:03:16,348 INFO [trainer.py:765] (7/8) Epoch 38, batch 2400, train_loss[loss=2.686, NarTop10Accuracy=0.7845, over 5121.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7178, over 5783.36 frames. ], batch size: 7, lr: 2.22e-03
2024-08-06 23:03:39,824 INFO [trainer.py:765] (7/8) Epoch 38, batch 2500, train_loss[loss=3.468, NarTop10Accuracy=0.635, over 4953.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7219, over 5474.68 frames. ], batch size: 7, lr: 2.22e-03
2024-08-06 23:03:59,638 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 23:04:58,940 INFO [trainer.py:765] (7/8) Epoch 39, batch 100, train_loss[loss=3.36, NarTop10Accuracy=0.6515, over 6975.00 frames. ], tot_loss[loss=2.986, NarTop10Accuracy=0.7286, over 2367.07 frames. ], batch size: 31, lr: 2.19e-03
2024-08-06 23:05:03,469 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 23:05:11,563 INFO [trainer.py:811] (7/8) Epoch 39, validation: loss=2.9, NarTop10Accuracy=0.7445, over 1905321.00 frames. 
2024-08-06 23:05:11,564 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 23:05:12,137 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 39, batch 200, train_loss[loss=2.753, NarTop10Accuracy=0.7734, over 6852.00 frames. ], tot_loss[loss=2.993, NarTop10Accuracy=0.7266, over 3849.25 frames. ], batch size: 17, lr: 2.19e-03
2024-08-06 23:06:17,293 INFO [trainer.py:765] (7/8) Epoch 39, batch 300, train_loss[loss=3.091, NarTop10Accuracy=0.7142, over 7071.00 frames. ], tot_loss[loss=2.987, NarTop10Accuracy=0.7275, over 4661.97 frames. ], batch size: 22, lr: 2.19e-03
2024-08-06 23:06:48,276 INFO [trainer.py:765] (7/8) Epoch 39, batch 400, train_loss[loss=2.945, NarTop10Accuracy=0.7364, over 5115.00 frames. ], tot_loss[loss=2.985, NarTop10Accuracy=0.7284, over 5107.23 frames. ], batch size: 7, lr: 2.19e-03
2024-08-06 23:07:19,175 INFO [trainer.py:765] (7/8) Epoch 39, batch 500, train_loss[loss=3.41, NarTop10Accuracy=0.6436, over 6078.00 frames. ], tot_loss[loss=2.997, NarTop10Accuracy=0.7257, over 5389.84 frames. ], batch size: 11, lr: 2.19e-03
2024-08-06 23:07:52,563 INFO [trainer.py:765] (7/8) Epoch 39, batch 600, train_loss[loss=2.665, NarTop10Accuracy=0.7903, over 5712.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7223, over 5660.59 frames. ], batch size: 9, lr: 2.19e-03
2024-08-06 23:08:33,694 INFO [trainer.py:765] (7/8) Epoch 39, batch 700, train_loss[loss=3.117, NarTop10Accuracy=0.6976, over 4998.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7201, over 5723.31 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:09:05,861 INFO [trainer.py:765] (7/8) Epoch 39, batch 800, train_loss[loss=2.749, NarTop10Accuracy=0.7803, over 5109.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7197, over 5779.06 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:09:38,865 INFO [trainer.py:765] (7/8) Epoch 39, batch 900, train_loss[loss=3.294, NarTop10Accuracy=0.6637, over 6153.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7217, over 5792.45 frames. ], batch size: 13, lr: 2.18e-03
2024-08-06 23:10:18,460 INFO [trainer.py:765] (7/8) Epoch 39, batch 1000, train_loss[loss=2.662, NarTop10Accuracy=0.789, over 6468.00 frames. ], tot_loss[loss=3.01, NarTop10Accuracy=0.7229, over 5891.27 frames. ], batch size: 13, lr: 2.18e-03
2024-08-06 23:10:53,934 INFO [trainer.py:765] (7/8) Epoch 39, batch 1100, train_loss[loss=2.816, NarTop10Accuracy=0.7733, over 6864.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7189, over 5922.98 frames. ], batch size: 17, lr: 2.18e-03
2024-08-06 23:11:27,822 INFO [trainer.py:765] (7/8) Epoch 39, batch 1200, train_loss[loss=2.995, NarTop10Accuracy=0.7292, over 7272.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.721, over 5931.90 frames. ], batch size: 31, lr: 2.18e-03
2024-08-06 23:12:07,252 INFO [trainer.py:765] (7/8) Epoch 39, batch 1300, train_loss[loss=2.843, NarTop10Accuracy=0.7544, over 5112.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7221, over 5983.52 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:12:39,301 INFO [trainer.py:765] (7/8) Epoch 39, batch 1400, train_loss[loss=2.999, NarTop10Accuracy=0.7288, over 6174.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7211, over 5994.12 frames. ], batch size: 11, lr: 2.18e-03
2024-08-06 23:13:09,756 INFO [trainer.py:765] (7/8) Epoch 39, batch 1500, train_loss[loss=3.561, NarTop10Accuracy=0.6102, over 5919.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7208, over 5938.23 frames. ], batch size: 50, lr: 2.18e-03
2024-08-06 23:13:37,586 INFO [trainer.py:765] (7/8) Epoch 39, batch 1600, train_loss[loss=2.936, NarTop10Accuracy=0.7404, over 7218.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.723, over 5919.08 frames. ], batch size: 22, lr: 2.17e-03
2024-08-06 23:14:04,220 INFO [trainer.py:765] (7/8) Epoch 39, batch 1700, train_loss[loss=3.362, NarTop10Accuracy=0.6567, over 6378.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7182, over 5911.58 frames. ], batch size: 13, lr: 2.17e-03
2024-08-06 23:14:30,767 INFO [trainer.py:765] (7/8) Epoch 39, batch 1800, train_loss[loss=2.87, NarTop10Accuracy=0.7486, over 7119.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7185, over 5970.59 frames. ], batch size: 22, lr: 2.17e-03
2024-08-06 23:14:57,180 INFO [trainer.py:765] (7/8) Epoch 39, batch 1900, train_loss[loss=3.009, NarTop10Accuracy=0.7269, over 6321.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7159, over 6005.80 frames. ], batch size: 50, lr: 2.17e-03
2024-08-06 23:15:22,751 INFO [trainer.py:765] (7/8) Epoch 39, batch 2000, train_loss[loss=3.242, NarTop10Accuracy=0.6812, over 6486.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7198, over 5992.29 frames. ], batch size: 50, lr: 2.17e-03
2024-08-06 23:15:48,060 INFO [trainer.py:765] (7/8) Epoch 39, batch 2100, train_loss[loss=3.462, NarTop10Accuracy=0.6281, over 3855.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7201, over 5976.87 frames. ], batch size: 4, lr: 2.17e-03
2024-08-06 23:15:51,871 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 23:16:02,156 INFO [trainer.py:811] (7/8) Epoch 39, validation: loss=2.85, NarTop10Accuracy=0.7552, over 1905321.00 frames. 
2024-08-06 23:16:02,156 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 23:16:02,645 INFO [optim.py:386] (7/8) 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] (7/8) Epoch 39, batch 2200, train_loss[loss=3.151, NarTop10Accuracy=0.697, over 7257.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7191, over 6020.25 frames. ], batch size: 31, lr: 2.17e-03
2024-08-06 23:16:48,847 INFO [trainer.py:765] (7/8) Epoch 39, batch 2300, train_loss[loss=2.67, NarTop10Accuracy=0.7907, over 5640.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7167, over 6016.07 frames. ], batch size: 9, lr: 2.17e-03
2024-08-06 23:17:13,136 INFO [trainer.py:765] (7/8) Epoch 39, batch 2400, train_loss[loss=2.668, NarTop10Accuracy=0.7888, over 5136.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.722, over 5763.72 frames. ], batch size: 7, lr: 2.17e-03
2024-08-06 23:17:36,712 INFO [trainer.py:765] (7/8) Epoch 39, batch 2500, train_loss[loss=2.977, NarTop10Accuracy=0.7315, over 5166.00 frames. ], tot_loss[loss=2.993, NarTop10Accuracy=0.7265, over 5480.97 frames. ], batch size: 7, lr: 2.16e-03
2024-08-06 23:17:56,532 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 23:18:48,946 INFO [trainer.py:765] (7/8) Epoch 40, batch 100, train_loss[loss=3.077, NarTop10Accuracy=0.7076, over 7029.00 frames. ], tot_loss[loss=3, NarTop10Accuracy=0.725, over 2366.84 frames. ], batch size: 31, lr: 2.14e-03
2024-08-06 23:19:23,035 INFO [trainer.py:765] (7/8) Epoch 40, batch 200, train_loss[loss=2.797, NarTop10Accuracy=0.7729, over 6708.00 frames. ], tot_loss[loss=2.991, NarTop10Accuracy=0.727, over 3850.68 frames. ], batch size: 17, lr: 2.13e-03
2024-08-06 23:19:57,187 INFO [trainer.py:765] (7/8) Epoch 40, batch 300, train_loss[loss=2.82, NarTop10Accuracy=0.7588, over 7053.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7228, over 4675.47 frames. ], batch size: 22, lr: 2.13e-03
2024-08-06 23:20:30,182 INFO [trainer.py:765] (7/8) Epoch 40, batch 400, train_loss[loss=2.785, NarTop10Accuracy=0.7711, over 5256.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7217, over 5106.46 frames. ], batch size: 7, lr: 2.13e-03
2024-08-06 23:21:00,251 INFO [trainer.py:765] (7/8) Epoch 40, batch 500, train_loss[loss=2.718, NarTop10Accuracy=0.7856, over 6048.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7216, over 5386.26 frames. ], batch size: 11, lr: 2.13e-03
2024-08-06 23:21:34,882 INFO [trainer.py:765] (7/8) Epoch 40, batch 600, train_loss[loss=2.978, NarTop10Accuracy=0.7366, over 6198.00 frames. ], tot_loss[loss=3.006, NarTop10Accuracy=0.724, over 5653.83 frames. ], batch size: 10, lr: 2.13e-03
2024-08-06 23:22:11,097 INFO [trainer.py:765] (7/8) Epoch 40, batch 700, train_loss[loss=2.995, NarTop10Accuracy=0.7195, over 5208.00 frames. ], tot_loss[loss=3.006, NarTop10Accuracy=0.724, over 5724.72 frames. ], batch size: 6, lr: 2.13e-03
2024-08-06 23:22:44,754 INFO [trainer.py:765] (7/8) Epoch 40, batch 800, train_loss[loss=2.542, NarTop10Accuracy=0.8151, over 5022.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7213, over 5773.15 frames. ], batch size: 6, lr: 2.13e-03
2024-08-06 23:23:16,635 INFO [trainer.py:765] (7/8) Epoch 40, batch 900, train_loss[loss=3.353, NarTop10Accuracy=0.6624, over 6654.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7213, over 5810.33 frames. ], batch size: 14, lr: 2.13e-03
2024-08-06 23:23:55,591 INFO [trainer.py:765] (7/8) Epoch 40, batch 1000, train_loss[loss=3.425, NarTop10Accuracy=0.6405, over 6348.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7206, over 5902.54 frames. ], batch size: 13, lr: 2.13e-03
2024-08-06 23:24:30,208 INFO [trainer.py:765] (7/8) Epoch 40, batch 1100, train_loss[loss=2.755, NarTop10Accuracy=0.7822, over 6771.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7214, over 5922.12 frames. ], batch size: 17, lr: 2.12e-03
2024-08-06 23:25:03,090 INFO [trainer.py:765] (7/8) Epoch 40, batch 1200, train_loss[loss=2.926, NarTop10Accuracy=0.7365, over 7185.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7217, over 5928.68 frames. ], batch size: 31, lr: 2.12e-03
2024-08-06 23:25:41,843 INFO [trainer.py:765] (7/8) Epoch 40, batch 1300, train_loss[loss=2.847, NarTop10Accuracy=0.7576, over 5109.00 frames. ], tot_loss[loss=3.01, NarTop10Accuracy=0.7229, over 5993.12 frames. ], batch size: 6, lr: 2.12e-03
2024-08-06 23:26:13,385 INFO [trainer.py:765] (7/8) Epoch 40, batch 1400, train_loss[loss=2.792, NarTop10Accuracy=0.7766, over 6150.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7198, over 6009.27 frames. ], batch size: 11, lr: 2.12e-03
2024-08-06 23:26:43,377 INFO [trainer.py:765] (7/8) Epoch 40, batch 1500, train_loss[loss=3.246, NarTop10Accuracy=0.6787, over 6390.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7219, over 5949.10 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:26:54,419 INFO [trainer.py:803] (7/8) Computing validation loss
2024-08-06 23:27:02,676 INFO [trainer.py:811] (7/8) Epoch 40, validation: loss=2.86, NarTop10Accuracy=0.7522, over 1905321.00 frames. 
2024-08-06 23:27:02,677 INFO [trainer.py:814] (7/8) Maximum memory allocated so far is 29190MB
2024-08-06 23:27:03,156 INFO [optim.py:386] (7/8) 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 23:27:19,382 INFO [trainer.py:765] (7/8) Epoch 40, batch 1600, train_loss[loss=2.854, NarTop10Accuracy=0.7588, over 7257.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7208, over 5919.94 frames. ], batch size: 22, lr: 2.12e-03
2024-08-06 23:27:46,057 INFO [trainer.py:765] (7/8) Epoch 40, batch 1700, train_loss[loss=3.284, NarTop10Accuracy=0.6674, over 6381.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7212, over 5925.93 frames. ], batch size: 13, lr: 2.12e-03
2024-08-06 23:28:12,579 INFO [trainer.py:765] (7/8) Epoch 40, batch 1800, train_loss[loss=3.115, NarTop10Accuracy=0.7067, over 6885.00 frames. ], tot_loss[loss=3.002, NarTop10Accuracy=0.7249, over 5973.26 frames. ], batch size: 22, lr: 2.12e-03
2024-08-06 23:28:38,909 INFO [trainer.py:765] (7/8) Epoch 40, batch 1900, train_loss[loss=3.226, NarTop10Accuracy=0.6811, over 6432.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7238, over 6030.56 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:29:04,445 INFO [trainer.py:765] (7/8) Epoch 40, batch 2000, train_loss[loss=3.523, NarTop10Accuracy=0.6298, over 5991.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7228, over 6013.52 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:29:29,750 INFO [trainer.py:765] (7/8) Epoch 40, batch 2100, train_loss[loss=2.665, NarTop10Accuracy=0.7929, over 3759.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7225, over 5987.82 frames. ], batch size: 4, lr: 2.11e-03
2024-08-06 23:29:54,939 INFO [trainer.py:765] (7/8) Epoch 40, batch 2200, train_loss[loss=3.238, NarTop10Accuracy=0.6765, over 7359.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7206, over 6013.85 frames. ], batch size: 31, lr: 2.11e-03
2024-08-06 23:30:20,013 INFO [trainer.py:765] (7/8) Epoch 40, batch 2300, train_loss[loss=2.994, NarTop10Accuracy=0.7246, over 5787.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7195, over 6029.60 frames. ], batch size: 9, lr: 2.11e-03
2024-08-06 23:30:44,296 INFO [trainer.py:765] (7/8) Epoch 40, batch 2400, train_loss[loss=2.757, NarTop10Accuracy=0.7724, over 5016.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7222, over 5785.52 frames. ], batch size: 7, lr: 2.11e-03
2024-08-06 23:31:07,738 INFO [trainer.py:765] (7/8) Epoch 40, batch 2500, train_loss[loss=2.988, NarTop10Accuracy=0.7267, over 5175.00 frames. ], tot_loss[loss=2.984, NarTop10Accuracy=0.7285, over 5481.37 frames. ], batch size: 7, lr: 2.11e-03
2024-08-06 23:31:27,718 INFO [trainer.py:650] (7/8) Reaches end of dataloader.
2024-08-06 23:31:27,721 INFO [trainer.py:1069] (7/8) Done!