2024-08-06 14:23:41,788 INFO [trainer.py:870] (5/8) Training started
2024-08-06 14:23:41,789 INFO [trainer.py:889] (5/8) Device: cuda:5
2024-08-06 14:23:41,790 INFO [trainer.py:890] (5/8) {'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 14:23:41,790 INFO [trainer.py:892] (5/8) About to create model
2024-08-06 14:23:42,582 INFO [trainer.py:899] (5/8) Number of model parameters: 367386628
2024-08-06 14:23:42,582 INFO [checkpoint.py:112] (5/8) Loading checkpoint from exp/valle/epoch-99.pt
2024-08-06 14:23:47,598 INFO [trainer.py:914] (5/8) Using DDP
2024-08-06 14:23:49,643 INFO [datamodule.py:427] (5/8) About to get train cuts
2024-08-06 14:23:49,645 INFO [datamodule.py:434] (5/8) About to get dev cuts
2024-08-06 14:23:49,646 INFO [datamodule.py:292] (5/8) Disable SpecAugment
2024-08-06 14:23:49,646 INFO [datamodule.py:294] (5/8) About to create train dataset
2024-08-06 14:23:49,646 INFO [datamodule.py:323] (5/8) Using DynamicBucketingSampler
2024-08-06 14:23:50,265 INFO [datamodule.py:344] (5/8) About to create train dataloader
2024-08-06 14:23:50,266 INFO [datamodule.py:367] (5/8) About to create dev dataset
2024-08-06 14:23:50,597 INFO [datamodule.py:388] (5/8) About to create dev dataloader
2024-08-06 14:24:38,248 INFO [trainer.py:765] (5/8) Epoch 1, batch 100, train_loss[loss=107.4, NarTop10Accuracy=0.02412, over 7362.00 frames. ], tot_loss[loss=74.42, NarTop10Accuracy=0.0463, over 2355.37 frames. ], batch size: 31, lr: 2.25e-02
2024-08-06 14:25:07,518 INFO [trainer.py:765] (5/8) Epoch 1, batch 200, train_loss[loss=133.4, NarTop10Accuracy=0.01583, over 6780.00 frames. ], tot_loss[loss=97.51, NarTop10Accuracy=0.04142, over 3853.30 frames. ], batch size: 17, lr: 3.00e-02
2024-08-06 14:25:37,110 INFO [trainer.py:765] (5/8) Epoch 1, batch 300, train_loss[loss=103.5, NarTop10Accuracy=0.02536, over 7077.00 frames. ], tot_loss[loss=85.29, NarTop10Accuracy=0.04331, over 4644.95 frames. ], batch size: 22, lr: 3.00e-02
2024-08-06 14:26:07,482 INFO [trainer.py:765] (5/8) Epoch 1, batch 400, train_loss[loss=52.49, NarTop10Accuracy=0.02052, over 5133.00 frames. ], tot_loss[loss=67.83, NarTop10Accuracy=0.04752, over 5102.37 frames. ], batch size: 7, lr: 3.00e-02
2024-08-06 14:26:35,356 INFO [trainer.py:765] (5/8) Epoch 1, batch 500, train_loss[loss=14.22, NarTop10Accuracy=0.0275, over 5898.00 frames. ], tot_loss[loss=48.93, NarTop10Accuracy=0.04979, over 5392.11 frames. ], batch size: 11, lr: 2.99e-02
2024-08-06 14:27:03,999 INFO [trainer.py:765] (5/8) Epoch 1, batch 600, train_loss[loss=6.084, NarTop10Accuracy=0.193, over 5769.00 frames. ], tot_loss[loss=33.42, NarTop10Accuracy=0.05616, over 5648.88 frames. ], batch size: 9, lr: 2.99e-02
2024-08-06 14:27:39,490 INFO [trainer.py:765] (5/8) Epoch 1, batch 700, train_loss[loss=6.762, NarTop10Accuracy=0.1191, over 4995.00 frames. ], tot_loss[loss=23.37, NarTop10Accuracy=0.06458, over 5727.25 frames. ], batch size: 6, lr: 2.99e-02
2024-08-06 14:28:08,832 INFO [trainer.py:765] (5/8) Epoch 1, batch 800, train_loss[loss=6.323, NarTop10Accuracy=0.1641, over 4941.00 frames. ], tot_loss[loss=17.16, NarTop10Accuracy=0.08561, over 5771.70 frames. ], batch size: 6, lr: 2.98e-02
2024-08-06 14:28:36,758 INFO [trainer.py:765] (5/8) Epoch 1, batch 900, train_loss[loss=5.811, NarTop10Accuracy=0.1644, over 6306.00 frames. ], tot_loss[loss=12.76, NarTop10Accuracy=0.1141, over 5815.38 frames. ], batch size: 13, lr: 2.98e-02
2024-08-06 14:29:12,586 INFO [trainer.py:765] (5/8) Epoch 1, batch 1000, train_loss[loss=5.705, NarTop10Accuracy=0.1982, over 6585.00 frames. ], tot_loss[loss=10.08, NarTop10Accuracy=0.1347, over 5924.60 frames. ], batch size: 14, lr: 2.97e-02
2024-08-06 14:29:42,825 INFO [trainer.py:765] (5/8) Epoch 1, batch 1100, train_loss[loss=5.749, NarTop10Accuracy=0.1885, over 6822.00 frames. ], tot_loss[loss=8.399, NarTop10Accuracy=0.153, over 5971.23 frames. ], batch size: 17, lr: 2.96e-02
2024-08-06 14:30:11,468 INFO [trainer.py:765] (5/8) Epoch 1, batch 1200, train_loss[loss=5.848, NarTop10Accuracy=0.179, over 7533.00 frames. ], tot_loss[loss=7.338, NarTop10Accuracy=0.1715, over 5960.66 frames. ], batch size: 32, lr: 2.96e-02
2024-08-06 14:30:48,747 INFO [trainer.py:765] (5/8) Epoch 1, batch 1300, train_loss[loss=5.243, NarTop10Accuracy=0.3136, over 4263.00 frames. ], tot_loss[loss=6.68, NarTop10Accuracy=0.1858, over 6012.91 frames. ], batch size: 5, lr: 2.95e-02
2024-08-06 14:31:18,144 INFO [trainer.py:765] (5/8) Epoch 1, batch 1400, train_loss[loss=5.495, NarTop10Accuracy=0.2389, over 6045.00 frames. ], tot_loss[loss=6.248, NarTop10Accuracy=0.1976, over 6016.35 frames. ], batch size: 11, lr: 2.94e-02
2024-08-06 14:31:46,026 INFO [trainer.py:765] (5/8) Epoch 1, batch 1500, train_loss[loss=5.723, NarTop10Accuracy=0.1865, over 6102.00 frames. ], tot_loss[loss=5.968, NarTop10Accuracy=0.2094, over 5938.71 frames. ], batch size: 52, lr: 2.94e-02
2024-08-06 14:32:13,691 INFO [trainer.py:765] (5/8) Epoch 1, batch 1600, train_loss[loss=5.443, NarTop10Accuracy=0.2313, over 7119.00 frames. ], tot_loss[loss=5.786, NarTop10Accuracy=0.2179, over 5921.42 frames. ], batch size: 22, lr: 2.93e-02
2024-08-06 14:32:40,197 INFO [trainer.py:765] (5/8) Epoch 1, batch 1700, train_loss[loss=5.442, NarTop10Accuracy=0.2396, over 6690.00 frames. ], tot_loss[loss=5.666, NarTop10Accuracy=0.225, over 5918.96 frames. ], batch size: 14, lr: 2.92e-02
2024-08-06 14:33:06,498 INFO [trainer.py:765] (5/8) Epoch 1, batch 1800, train_loss[loss=5.43, NarTop10Accuracy=0.2447, over 7032.00 frames. ], tot_loss[loss=5.566, NarTop10Accuracy=0.2345, over 5988.46 frames. ], batch size: 22, lr: 2.91e-02
2024-08-06 14:33:32,625 INFO [trainer.py:765] (5/8) Epoch 1, batch 1900, train_loss[loss=5.679, NarTop10Accuracy=0.1946, over 6546.00 frames. ], tot_loss[loss=5.505, NarTop10Accuracy=0.2415, over 6032.02 frames. ], batch size: 52, lr: 2.90e-02
2024-08-06 14:33:58,014 INFO [trainer.py:765] (5/8) Epoch 1, batch 2000, train_loss[loss=5.454, NarTop10Accuracy=0.2432, over 6078.00 frames. ], tot_loss[loss=5.445, NarTop10Accuracy=0.25, over 6003.75 frames. ], batch size: 50, lr: 2.89e-02
2024-08-06 14:33:58,016 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 14:34:06,103 INFO [trainer.py:811] (5/8) Epoch 1, validation: loss=5.397, NarTop10Accuracy=0.2581, over 1905321.00 frames. 
2024-08-06 14:34:06,104 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 14:34:06,612 INFO [optim.py:386] (5/8) 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 14:34:32,063 INFO [trainer.py:765] (5/8) Epoch 1, batch 2100, train_loss[loss=5.151, NarTop10Accuracy=0.3005, over 3945.00 frames. ], tot_loss[loss=5.381, NarTop10Accuracy=0.2608, over 5974.03 frames. ], batch size: 4, lr: 2.88e-02
2024-08-06 14:34:57,303 INFO [trainer.py:765] (5/8) Epoch 1, batch 2200, train_loss[loss=5.376, NarTop10Accuracy=0.2529, over 7161.00 frames. ], tot_loss[loss=5.349, NarTop10Accuracy=0.265, over 6006.07 frames. ], batch size: 31, lr: 2.87e-02
2024-08-06 14:35:22,455 INFO [trainer.py:765] (5/8) Epoch 1, batch 2300, train_loss[loss=5.072, NarTop10Accuracy=0.31, over 5751.00 frames. ], tot_loss[loss=5.332, NarTop10Accuracy=0.2675, over 6001.36 frames. ], batch size: 9, lr: 2.86e-02
2024-08-06 14:35:46,815 INFO [trainer.py:765] (5/8) Epoch 1, batch 2400, train_loss[loss=5.309, NarTop10Accuracy=0.2749, over 5136.00 frames. ], tot_loss[loss=5.28, NarTop10Accuracy=0.2767, over 5754.47 frames. ], batch size: 7, lr: 2.85e-02
2024-08-06 14:36:10,408 INFO [trainer.py:765] (5/8) Epoch 1, batch 2500, train_loss[loss=4.91, NarTop10Accuracy=0.3376, over 5145.00 frames. ], tot_loss[loss=5.221, NarTop10Accuracy=0.2872, over 5451.86 frames. ], batch size: 7, lr: 2.84e-02
2024-08-06 14:36:31,220 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 14:37:29,669 INFO [trainer.py:765] (5/8) Epoch 2, batch 100, train_loss[loss=4.942, NarTop10Accuracy=0.352, over 7035.00 frames. ], tot_loss[loss=5.177, NarTop10Accuracy=0.297, over 2361.52 frames. ], batch size: 31, lr: 2.77e-02
2024-08-06 14:38:10,015 INFO [trainer.py:765] (5/8) Epoch 2, batch 200, train_loss[loss=5.018, NarTop10Accuracy=0.3295, over 7203.00 frames. ], tot_loss[loss=5.148, NarTop10Accuracy=0.3024, over 3852.01 frames. ], batch size: 18, lr: 2.76e-02
2024-08-06 14:38:38,297 INFO [trainer.py:765] (5/8) Epoch 2, batch 300, train_loss[loss=5.208, NarTop10Accuracy=0.2862, over 7251.00 frames. ], tot_loss[loss=5.131, NarTop10Accuracy=0.3049, over 4640.92 frames. ], batch size: 22, lr: 2.75e-02
2024-08-06 14:39:06,999 INFO [trainer.py:765] (5/8) Epoch 2, batch 400, train_loss[loss=4.989, NarTop10Accuracy=0.3266, over 5664.00 frames. ], tot_loss[loss=5.108, NarTop10Accuracy=0.3087, over 5084.47 frames. ], batch size: 8, lr: 2.74e-02
2024-08-06 14:39:46,119 INFO [trainer.py:765] (5/8) Epoch 2, batch 500, train_loss[loss=4.903, NarTop10Accuracy=0.3488, over 6189.00 frames. ], tot_loss[loss=5.07, NarTop10Accuracy=0.3163, over 5371.20 frames. ], batch size: 11, lr: 2.73e-02
2024-08-06 14:40:15,083 INFO [trainer.py:765] (5/8) Epoch 2, batch 600, train_loss[loss=4.987, NarTop10Accuracy=0.3423, over 5598.00 frames. ], tot_loss[loss=5.047, NarTop10Accuracy=0.3208, over 5647.76 frames. ], batch size: 9, lr: 2.71e-02
2024-08-06 14:40:44,589 INFO [trainer.py:765] (5/8) Epoch 2, batch 700, train_loss[loss=5.113, NarTop10Accuracy=0.3113, over 5073.00 frames. ], tot_loss[loss=5.035, NarTop10Accuracy=0.3221, over 5716.65 frames. ], batch size: 6, lr: 2.70e-02
2024-08-06 14:41:24,513 INFO [trainer.py:765] (5/8) Epoch 2, batch 800, train_loss[loss=5.183, NarTop10Accuracy=0.2937, over 4230.00 frames. ], tot_loss[loss=5.012, NarTop10Accuracy=0.3264, over 5779.24 frames. ], batch size: 5, lr: 2.69e-02
2024-08-06 14:41:54,405 INFO [trainer.py:765] (5/8) Epoch 2, batch 900, train_loss[loss=4.826, NarTop10Accuracy=0.3598, over 6090.00 frames. ], tot_loss[loss=4.977, NarTop10Accuracy=0.3333, over 5817.09 frames. ], batch size: 13, lr: 2.68e-02
2024-08-06 14:42:23,902 INFO [trainer.py:765] (5/8) Epoch 2, batch 1000, train_loss[loss=4.863, NarTop10Accuracy=0.3586, over 6276.00 frames. ], tot_loss[loss=4.947, NarTop10Accuracy=0.3394, over 5912.25 frames. ], batch size: 13, lr: 2.66e-02
2024-08-06 14:42:56,254 INFO [trainer.py:765] (5/8) Epoch 2, batch 1100, train_loss[loss=5.001, NarTop10Accuracy=0.3167, over 6828.00 frames. ], tot_loss[loss=4.931, NarTop10Accuracy=0.3425, over 5940.72 frames. ], batch size: 17, lr: 2.65e-02
2024-08-06 14:43:35,186 INFO [trainer.py:765] (5/8) Epoch 2, batch 1200, train_loss[loss=4.825, NarTop10Accuracy=0.3607, over 7302.00 frames. ], tot_loss[loss=4.91, NarTop10Accuracy=0.3461, over 5925.62 frames. ], batch size: 31, lr: 2.64e-02
2024-08-06 14:44:04,346 INFO [trainer.py:765] (5/8) Epoch 2, batch 1300, train_loss[loss=4.815, NarTop10Accuracy=0.3583, over 5034.00 frames. ], tot_loss[loss=4.859, NarTop10Accuracy=0.3555, over 5994.43 frames. ], batch size: 6, lr: 2.63e-02
2024-08-06 14:44:33,728 INFO [trainer.py:765] (5/8) Epoch 2, batch 1400, train_loss[loss=4.918, NarTop10Accuracy=0.343, over 6057.00 frames. ], tot_loss[loss=4.842, NarTop10Accuracy=0.3586, over 6022.21 frames. ], batch size: 11, lr: 2.61e-02
2024-08-06 14:44:40,441 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 14:44:48,506 INFO [trainer.py:811] (5/8) Epoch 2, validation: loss=4.808, NarTop10Accuracy=0.3642, over 1905321.00 frames. 
2024-08-06 14:44:48,506 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 14:44:49,204 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 2, batch 1500, train_loss[loss=4.717, NarTop10Accuracy=0.3793, over 5871.00 frames. ], tot_loss[loss=4.83, NarTop10Accuracy=0.361, over 5950.10 frames. ], batch size: 50, lr: 2.60e-02
2024-08-06 14:45:37,660 INFO [trainer.py:765] (5/8) Epoch 2, batch 1600, train_loss[loss=4.688, NarTop10Accuracy=0.3879, over 6936.00 frames. ], tot_loss[loss=4.803, NarTop10Accuracy=0.3661, over 5933.27 frames. ], batch size: 22, lr: 2.59e-02
2024-08-06 14:46:04,368 INFO [trainer.py:765] (5/8) Epoch 2, batch 1700, train_loss[loss=4.729, NarTop10Accuracy=0.3761, over 6096.00 frames. ], tot_loss[loss=4.795, NarTop10Accuracy=0.3677, over 5914.20 frames. ], batch size: 13, lr: 2.58e-02
2024-08-06 14:46:31,034 INFO [trainer.py:765] (5/8) Epoch 2, batch 1800, train_loss[loss=4.65, NarTop10Accuracy=0.3934, over 7053.00 frames. ], tot_loss[loss=4.771, NarTop10Accuracy=0.3727, over 5978.84 frames. ], batch size: 22, lr: 2.56e-02
2024-08-06 14:46:57,532 INFO [trainer.py:765] (5/8) Epoch 2, batch 1900, train_loss[loss=4.635, NarTop10Accuracy=0.4024, over 6549.00 frames. ], tot_loss[loss=4.746, NarTop10Accuracy=0.3769, over 6028.81 frames. ], batch size: 51, lr: 2.55e-02
2024-08-06 14:47:23,234 INFO [trainer.py:765] (5/8) Epoch 2, batch 2000, train_loss[loss=4.754, NarTop10Accuracy=0.3748, over 5919.00 frames. ], tot_loss[loss=4.726, NarTop10Accuracy=0.3804, over 6019.84 frames. ], batch size: 50, lr: 2.54e-02
2024-08-06 14:47:48,589 INFO [trainer.py:765] (5/8) Epoch 2, batch 2100, train_loss[loss=4.507, NarTop10Accuracy=0.4222, over 3915.00 frames. ], tot_loss[loss=4.715, NarTop10Accuracy=0.3824, over 5978.83 frames. ], batch size: 4, lr: 2.53e-02
2024-08-06 14:48:13,765 INFO [trainer.py:765] (5/8) Epoch 2, batch 2200, train_loss[loss=4.623, NarTop10Accuracy=0.3993, over 7293.00 frames. ], tot_loss[loss=4.677, NarTop10Accuracy=0.3897, over 6014.68 frames. ], batch size: 31, lr: 2.51e-02
2024-08-06 14:48:38,952 INFO [trainer.py:765] (5/8) Epoch 2, batch 2300, train_loss[loss=4.684, NarTop10Accuracy=0.3801, over 5745.00 frames. ], tot_loss[loss=4.678, NarTop10Accuracy=0.3896, over 6024.93 frames. ], batch size: 9, lr: 2.50e-02
2024-08-06 14:49:03,319 INFO [trainer.py:765] (5/8) Epoch 2, batch 2400, train_loss[loss=4.346, NarTop10Accuracy=0.4574, over 5106.00 frames. ], tot_loss[loss=4.635, NarTop10Accuracy=0.3979, over 5772.97 frames. ], batch size: 7, lr: 2.49e-02
2024-08-06 14:49:26,868 INFO [trainer.py:765] (5/8) Epoch 2, batch 2500, train_loss[loss=4.768, NarTop10Accuracy=0.3604, over 5052.00 frames. ], tot_loss[loss=4.614, NarTop10Accuracy=0.4021, over 5469.94 frames. ], batch size: 7, lr: 2.48e-02
2024-08-06 14:49:46,850 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 14:50:51,115 INFO [trainer.py:765] (5/8) Epoch 3, batch 100, train_loss[loss=4.725, NarTop10Accuracy=0.3843, over 7266.00 frames. ], tot_loss[loss=4.591, NarTop10Accuracy=0.4066, over 2365.23 frames. ], batch size: 31, lr: 2.36e-02
2024-08-06 14:51:20,386 INFO [trainer.py:765] (5/8) Epoch 3, batch 200, train_loss[loss=4.545, NarTop10Accuracy=0.4176, over 6867.00 frames. ], tot_loss[loss=4.545, NarTop10Accuracy=0.416, over 3849.14 frames. ], batch size: 17, lr: 2.34e-02
2024-08-06 14:51:50,953 INFO [trainer.py:765] (5/8) Epoch 3, batch 300, train_loss[loss=4.751, NarTop10Accuracy=0.3667, over 7086.00 frames. ], tot_loss[loss=4.524, NarTop10Accuracy=0.4197, over 4653.17 frames. ], batch size: 22, lr: 2.33e-02
2024-08-06 14:52:32,357 INFO [trainer.py:765] (5/8) Epoch 3, batch 400, train_loss[loss=4.484, NarTop10Accuracy=0.4256, over 4986.00 frames. ], tot_loss[loss=4.507, NarTop10Accuracy=0.4235, over 5088.91 frames. ], batch size: 7, lr: 2.32e-02
2024-08-06 14:53:00,678 INFO [trainer.py:765] (5/8) Epoch 3, batch 500, train_loss[loss=4.402, NarTop10Accuracy=0.4569, over 6144.00 frames. ], tot_loss[loss=4.492, NarTop10Accuracy=0.4261, over 5392.24 frames. ], batch size: 11, lr: 2.31e-02
2024-08-06 14:53:29,550 INFO [trainer.py:765] (5/8) Epoch 3, batch 600, train_loss[loss=4.29, NarTop10Accuracy=0.4747, over 5670.00 frames. ], tot_loss[loss=4.479, NarTop10Accuracy=0.4288, over 5658.64 frames. ], batch size: 9, lr: 2.30e-02
2024-08-06 14:54:12,464 INFO [trainer.py:765] (5/8) Epoch 3, batch 700, train_loss[loss=3.986, NarTop10Accuracy=0.5259, over 5016.00 frames. ], tot_loss[loss=4.454, NarTop10Accuracy=0.4337, over 5735.88 frames. ], batch size: 6, lr: 2.29e-02
2024-08-06 14:54:44,784 INFO [trainer.py:765] (5/8) Epoch 3, batch 800, train_loss[loss=4.101, NarTop10Accuracy=0.5069, over 4443.00 frames. ], tot_loss[loss=4.431, NarTop10Accuracy=0.4383, over 5787.12 frames. ], batch size: 5, lr: 2.28e-02
2024-08-06 14:54:58,683 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 14:55:06,655 INFO [trainer.py:811] (5/8) Epoch 3, validation: loss=4.276, NarTop10Accuracy=0.4689, over 1905321.00 frames. 
2024-08-06 14:55:06,656 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 14:55:07,183 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 3, batch 900, train_loss[loss=4.073, NarTop10Accuracy=0.5084, over 6633.00 frames. ], tot_loss[loss=4.403, NarTop10Accuracy=0.4436, over 5803.11 frames. ], batch size: 14, lr: 2.26e-02
2024-08-06 14:56:04,958 INFO [trainer.py:765] (5/8) Epoch 3, batch 1000, train_loss[loss=4.278, NarTop10Accuracy=0.4642, over 6216.00 frames. ], tot_loss[loss=4.382, NarTop10Accuracy=0.4475, over 5908.88 frames. ], batch size: 13, lr: 2.25e-02
2024-08-06 14:56:37,300 INFO [trainer.py:765] (5/8) Epoch 3, batch 1100, train_loss[loss=4.579, NarTop10Accuracy=0.4015, over 6753.00 frames. ], tot_loss[loss=4.356, NarTop10Accuracy=0.4527, over 5940.87 frames. ], batch size: 17, lr: 2.24e-02
2024-08-06 14:57:06,377 INFO [trainer.py:765] (5/8) Epoch 3, batch 1200, train_loss[loss=4.395, NarTop10Accuracy=0.4402, over 7308.00 frames. ], tot_loss[loss=4.341, NarTop10Accuracy=0.4558, over 5930.22 frames. ], batch size: 31, lr: 2.23e-02
2024-08-06 14:57:51,631 INFO [trainer.py:765] (5/8) Epoch 3, batch 1300, train_loss[loss=4.197, NarTop10Accuracy=0.479, over 4365.00 frames. ], tot_loss[loss=4.312, NarTop10Accuracy=0.4617, over 5984.52 frames. ], batch size: 5, lr: 2.22e-02
2024-08-06 14:58:22,900 INFO [trainer.py:765] (5/8) Epoch 3, batch 1400, train_loss[loss=4.213, NarTop10Accuracy=0.4778, over 6009.00 frames. ], tot_loss[loss=4.3, NarTop10Accuracy=0.4638, over 6017.12 frames. ], batch size: 11, lr: 2.21e-02
2024-08-06 14:58:50,856 INFO [trainer.py:765] (5/8) Epoch 3, batch 1500, train_loss[loss=4.373, NarTop10Accuracy=0.4451, over 6138.00 frames. ], tot_loss[loss=4.282, NarTop10Accuracy=0.4672, over 5956.63 frames. ], batch size: 51, lr: 2.20e-02
2024-08-06 14:59:18,715 INFO [trainer.py:765] (5/8) Epoch 3, batch 1600, train_loss[loss=4.063, NarTop10Accuracy=0.5136, over 7230.00 frames. ], tot_loss[loss=4.264, NarTop10Accuracy=0.4706, over 5935.02 frames. ], batch size: 22, lr: 2.19e-02
2024-08-06 14:59:45,953 INFO [trainer.py:765] (5/8) Epoch 3, batch 1700, train_loss[loss=3.983, NarTop10Accuracy=0.525, over 6174.00 frames. ], tot_loss[loss=4.237, NarTop10Accuracy=0.4761, over 5929.12 frames. ], batch size: 13, lr: 2.18e-02
2024-08-06 15:00:12,498 INFO [trainer.py:765] (5/8) Epoch 3, batch 1800, train_loss[loss=3.92, NarTop10Accuracy=0.5351, over 6918.00 frames. ], tot_loss[loss=4.215, NarTop10Accuracy=0.4805, over 5979.17 frames. ], batch size: 22, lr: 2.17e-02
2024-08-06 15:00:38,949 INFO [trainer.py:765] (5/8) Epoch 3, batch 1900, train_loss[loss=4.709, NarTop10Accuracy=0.3867, over 6465.00 frames. ], tot_loss[loss=4.194, NarTop10Accuracy=0.4848, over 6030.99 frames. ], batch size: 50, lr: 2.16e-02
2024-08-06 15:01:04,606 INFO [trainer.py:765] (5/8) Epoch 3, batch 2000, train_loss[loss=4.452, NarTop10Accuracy=0.4298, over 5880.00 frames. ], tot_loss[loss=4.169, NarTop10Accuracy=0.4897, over 6005.27 frames. ], batch size: 50, lr: 2.15e-02
2024-08-06 15:01:29,899 INFO [trainer.py:765] (5/8) Epoch 3, batch 2100, train_loss[loss=3.988, NarTop10Accuracy=0.5281, over 3930.00 frames. ], tot_loss[loss=4.145, NarTop10Accuracy=0.4943, over 5981.38 frames. ], batch size: 4, lr: 2.14e-02
2024-08-06 15:01:55,183 INFO [trainer.py:765] (5/8) Epoch 3, batch 2200, train_loss[loss=3.946, NarTop10Accuracy=0.5436, over 7266.00 frames. ], tot_loss[loss=4.12, NarTop10Accuracy=0.5, over 6008.25 frames. ], batch size: 31, lr: 2.13e-02
2024-08-06 15:02:20,410 INFO [trainer.py:765] (5/8) Epoch 3, batch 2300, train_loss[loss=4.324, NarTop10Accuracy=0.4565, over 5721.00 frames. ], tot_loss[loss=4.128, NarTop10Accuracy=0.4985, over 6005.06 frames. ], batch size: 9, lr: 2.12e-02
2024-08-06 15:02:44,663 INFO [trainer.py:765] (5/8) Epoch 3, batch 2400, train_loss[loss=4.22, NarTop10Accuracy=0.4793, over 5082.00 frames. ], tot_loss[loss=4.096, NarTop10Accuracy=0.5045, over 5761.61 frames. ], batch size: 7, lr: 2.11e-02
2024-08-06 15:03:08,234 INFO [trainer.py:765] (5/8) Epoch 3, batch 2500, train_loss[loss=3.737, NarTop10Accuracy=0.5817, over 5097.00 frames. ], tot_loss[loss=4.043, NarTop10Accuracy=0.5153, over 5456.22 frames. ], batch size: 7, lr: 2.10e-02
2024-08-06 15:03:28,319 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 15:04:28,130 INFO [trainer.py:765] (5/8) Epoch 4, batch 100, train_loss[loss=3.91, NarTop10Accuracy=0.5434, over 7158.00 frames. ], tot_loss[loss=4.04, NarTop10Accuracy=0.517, over 2359.48 frames. ], batch size: 31, lr: 1.97e-02
2024-08-06 15:04:59,842 INFO [trainer.py:765] (5/8) Epoch 4, batch 200, train_loss[loss=3.845, NarTop10Accuracy=0.5585, over 6858.00 frames. ], tot_loss[loss=4.008, NarTop10Accuracy=0.5237, over 3845.46 frames. ], batch size: 17, lr: 1.96e-02
2024-08-06 15:05:27,509 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 15:05:35,694 INFO [trainer.py:811] (5/8) Epoch 4, validation: loss=3.804, NarTop10Accuracy=0.5644, over 1905321.00 frames. 
2024-08-06 15:05:35,695 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 15:05:36,237 INFO [optim.py:386] (5/8) 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 15:05:43,888 INFO [trainer.py:765] (5/8) Epoch 4, batch 300, train_loss[loss=3.761, NarTop10Accuracy=0.5753, over 7119.00 frames. ], tot_loss[loss=3.988, NarTop10Accuracy=0.5275, over 4657.51 frames. ], batch size: 22, lr: 1.95e-02
2024-08-06 15:06:16,123 INFO [trainer.py:765] (5/8) Epoch 4, batch 400, train_loss[loss=3.826, NarTop10Accuracy=0.5654, over 5100.00 frames. ], tot_loss[loss=3.995, NarTop10Accuracy=0.526, over 5088.45 frames. ], batch size: 7, lr: 1.94e-02
2024-08-06 15:06:46,472 INFO [trainer.py:765] (5/8) Epoch 4, batch 500, train_loss[loss=3.947, NarTop10Accuracy=0.5312, over 6159.00 frames. ], tot_loss[loss=3.98, NarTop10Accuracy=0.5288, over 5364.91 frames. ], batch size: 11, lr: 1.93e-02
2024-08-06 15:07:23,817 INFO [trainer.py:765] (5/8) Epoch 4, batch 600, train_loss[loss=3.629, NarTop10Accuracy=0.6053, over 5760.00 frames. ], tot_loss[loss=3.979, NarTop10Accuracy=0.5291, over 5642.97 frames. ], batch size: 9, lr: 1.93e-02
2024-08-06 15:07:59,001 INFO [trainer.py:765] (5/8) Epoch 4, batch 700, train_loss[loss=4.27, NarTop10Accuracy=0.4648, over 4281.00 frames. ], tot_loss[loss=3.969, NarTop10Accuracy=0.5309, over 5715.78 frames. ], batch size: 5, lr: 1.92e-02
2024-08-06 15:08:32,429 INFO [trainer.py:765] (5/8) Epoch 4, batch 800, train_loss[loss=3.615, NarTop10Accuracy=0.6013, over 5157.00 frames. ], tot_loss[loss=3.959, NarTop10Accuracy=0.5325, over 5763.99 frames. ], batch size: 6, lr: 1.91e-02
2024-08-06 15:09:10,688 INFO [trainer.py:765] (5/8) Epoch 4, batch 900, train_loss[loss=3.553, NarTop10Accuracy=0.6192, over 6297.00 frames. ], tot_loss[loss=3.918, NarTop10Accuracy=0.541, over 5789.14 frames. ], batch size: 13, lr: 1.90e-02
2024-08-06 15:09:46,075 INFO [trainer.py:765] (5/8) Epoch 4, batch 1000, train_loss[loss=3.528, NarTop10Accuracy=0.6315, over 6180.00 frames. ], tot_loss[loss=3.908, NarTop10Accuracy=0.5433, over 5883.31 frames. ], batch size: 13, lr: 1.89e-02
2024-08-06 15:10:18,138 INFO [trainer.py:765] (5/8) Epoch 4, batch 1100, train_loss[loss=3.701, NarTop10Accuracy=0.5849, over 6870.00 frames. ], tot_loss[loss=3.903, NarTop10Accuracy=0.5442, over 5936.93 frames. ], batch size: 17, lr: 1.88e-02
2024-08-06 15:10:55,075 INFO [trainer.py:765] (5/8) Epoch 4, batch 1200, train_loss[loss=4.317, NarTop10Accuracy=0.4607, over 7401.00 frames. ], tot_loss[loss=3.901, NarTop10Accuracy=0.5447, over 5944.68 frames. ], batch size: 31, lr: 1.88e-02
2024-08-06 15:11:32,073 INFO [trainer.py:765] (5/8) Epoch 4, batch 1300, train_loss[loss=3.487, NarTop10Accuracy=0.6274, over 5199.00 frames. ], tot_loss[loss=3.857, NarTop10Accuracy=0.5534, over 5997.07 frames. ], batch size: 6, lr: 1.87e-02
2024-08-06 15:12:05,687 INFO [trainer.py:765] (5/8) Epoch 4, batch 1400, train_loss[loss=3.757, NarTop10Accuracy=0.5868, over 6150.00 frames. ], tot_loss[loss=3.86, NarTop10Accuracy=0.5529, over 6011.03 frames. ], batch size: 11, lr: 1.86e-02
2024-08-06 15:12:33,695 INFO [trainer.py:765] (5/8) Epoch 4, batch 1500, train_loss[loss=3.842, NarTop10Accuracy=0.5593, over 5901.00 frames. ], tot_loss[loss=3.858, NarTop10Accuracy=0.553, over 5943.86 frames. ], batch size: 50, lr: 1.85e-02
2024-08-06 15:13:01,510 INFO [trainer.py:765] (5/8) Epoch 4, batch 1600, train_loss[loss=3.843, NarTop10Accuracy=0.5658, over 6975.00 frames. ], tot_loss[loss=3.849, NarTop10Accuracy=0.555, over 5931.23 frames. ], batch size: 22, lr: 1.84e-02
2024-08-06 15:13:28,132 INFO [trainer.py:765] (5/8) Epoch 4, batch 1700, train_loss[loss=3.841, NarTop10Accuracy=0.5622, over 6690.00 frames. ], tot_loss[loss=3.827, NarTop10Accuracy=0.5594, over 5926.85 frames. ], batch size: 14, lr: 1.84e-02
2024-08-06 15:13:54,557 INFO [trainer.py:765] (5/8) Epoch 4, batch 1800, train_loss[loss=3.583, NarTop10Accuracy=0.6071, over 7107.00 frames. ], tot_loss[loss=3.826, NarTop10Accuracy=0.5596, over 6005.17 frames. ], batch size: 22, lr: 1.83e-02
2024-08-06 15:14:20,997 INFO [trainer.py:765] (5/8) Epoch 4, batch 1900, train_loss[loss=3.738, NarTop10Accuracy=0.5782, over 5901.00 frames. ], tot_loss[loss=3.844, NarTop10Accuracy=0.5559, over 6038.21 frames. ], batch size: 51, lr: 1.82e-02
2024-08-06 15:14:46,671 INFO [trainer.py:765] (5/8) Epoch 4, batch 2000, train_loss[loss=3.677, NarTop10Accuracy=0.5884, over 6417.00 frames. ], tot_loss[loss=3.813, NarTop10Accuracy=0.5622, over 6011.48 frames. ], batch size: 50, lr: 1.81e-02
2024-08-06 15:15:11,858 INFO [trainer.py:765] (5/8) Epoch 4, batch 2100, train_loss[loss=3.551, NarTop10Accuracy=0.6175, over 4809.00 frames. ], tot_loss[loss=3.805, NarTop10Accuracy=0.5641, over 5970.65 frames. ], batch size: 5, lr: 1.81e-02
2024-08-06 15:15:37,089 INFO [trainer.py:765] (5/8) Epoch 4, batch 2200, train_loss[loss=3.744, NarTop10Accuracy=0.5798, over 6954.00 frames. ], tot_loss[loss=3.797, NarTop10Accuracy=0.5657, over 6006.64 frames. ], batch size: 31, lr: 1.80e-02
2024-08-06 15:15:55,087 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 15:16:03,243 INFO [trainer.py:811] (5/8) Epoch 4, validation: loss=3.665, NarTop10Accuracy=0.5912, over 1905321.00 frames. 
2024-08-06 15:16:03,243 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 15:16:03,740 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 4, batch 2300, train_loss[loss=3.493, NarTop10Accuracy=0.6264, over 5778.00 frames. ], tot_loss[loss=3.804, NarTop10Accuracy=0.5641, over 6013.21 frames. ], batch size: 9, lr: 1.79e-02
2024-08-06 15:16:34,840 INFO [trainer.py:765] (5/8) Epoch 4, batch 2400, train_loss[loss=3.482, NarTop10Accuracy=0.6389, over 5190.00 frames. ], tot_loss[loss=3.776, NarTop10Accuracy=0.5696, over 5780.27 frames. ], batch size: 7, lr: 1.79e-02
2024-08-06 15:16:58,534 INFO [trainer.py:765] (5/8) Epoch 4, batch 2500, train_loss[loss=3.615, NarTop10Accuracy=0.6169, over 5193.00 frames. ], tot_loss[loss=3.758, NarTop10Accuracy=0.573, over 5488.67 frames. ], batch size: 7, lr: 1.78e-02
2024-08-06 15:17:18,466 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 15:18:24,100 INFO [trainer.py:765] (5/8) Epoch 5, batch 100, train_loss[loss=3.624, NarTop10Accuracy=0.6064, over 7107.00 frames. ], tot_loss[loss=3.769, NarTop10Accuracy=0.5716, over 2349.34 frames. ], batch size: 31, lr: 1.66e-02
2024-08-06 15:18:59,675 INFO [trainer.py:765] (5/8) Epoch 5, batch 200, train_loss[loss=4.121, NarTop10Accuracy=0.4924, over 6780.00 frames. ], tot_loss[loss=3.757, NarTop10Accuracy=0.5743, over 3864.84 frames. ], batch size: 17, lr: 1.65e-02
2024-08-06 15:19:32,887 INFO [trainer.py:765] (5/8) Epoch 5, batch 300, train_loss[loss=3.98, NarTop10Accuracy=0.5206, over 6894.00 frames. ], tot_loss[loss=3.73, NarTop10Accuracy=0.5796, over 4659.97 frames. ], batch size: 22, lr: 1.65e-02
2024-08-06 15:20:01,656 INFO [trainer.py:765] (5/8) Epoch 5, batch 400, train_loss[loss=3.453, NarTop10Accuracy=0.6275, over 5121.00 frames. ], tot_loss[loss=3.722, NarTop10Accuracy=0.581, over 5119.87 frames. ], batch size: 7, lr: 1.64e-02
2024-08-06 15:20:38,298 INFO [trainer.py:765] (5/8) Epoch 5, batch 500, train_loss[loss=3.968, NarTop10Accuracy=0.5287, over 6069.00 frames. ], tot_loss[loss=3.736, NarTop10Accuracy=0.5772, over 5391.24 frames. ], batch size: 11, lr: 1.63e-02
2024-08-06 15:21:13,710 INFO [trainer.py:765] (5/8) Epoch 5, batch 600, train_loss[loss=3.785, NarTop10Accuracy=0.5587, over 5709.00 frames. ], tot_loss[loss=3.725, NarTop10Accuracy=0.58, over 5642.51 frames. ], batch size: 9, lr: 1.63e-02
2024-08-06 15:21:45,881 INFO [trainer.py:765] (5/8) Epoch 5, batch 700, train_loss[loss=3.537, NarTop10Accuracy=0.6233, over 5133.00 frames. ], tot_loss[loss=3.722, NarTop10Accuracy=0.5805, over 5721.36 frames. ], batch size: 6, lr: 1.62e-02
2024-08-06 15:22:24,498 INFO [trainer.py:765] (5/8) Epoch 5, batch 800, train_loss[loss=3.986, NarTop10Accuracy=0.5184, over 5025.00 frames. ], tot_loss[loss=3.709, NarTop10Accuracy=0.5827, over 5771.19 frames. ], batch size: 6, lr: 1.62e-02
2024-08-06 15:22:56,783 INFO [trainer.py:765] (5/8) Epoch 5, batch 900, train_loss[loss=3.639, NarTop10Accuracy=0.6016, over 6249.00 frames. ], tot_loss[loss=3.701, NarTop10Accuracy=0.5847, over 5811.55 frames. ], batch size: 13, lr: 1.61e-02
2024-08-06 15:23:31,914 INFO [trainer.py:765] (5/8) Epoch 5, batch 1000, train_loss[loss=3.457, NarTop10Accuracy=0.6513, over 6708.00 frames. ], tot_loss[loss=3.68, NarTop10Accuracy=0.5886, over 5899.38 frames. ], batch size: 14, lr: 1.60e-02
2024-08-06 15:24:09,571 INFO [trainer.py:765] (5/8) Epoch 5, batch 1100, train_loss[loss=3.462, NarTop10Accuracy=0.6318, over 6771.00 frames. ], tot_loss[loss=3.679, NarTop10Accuracy=0.5892, over 5929.17 frames. ], batch size: 17, lr: 1.60e-02
2024-08-06 15:24:44,528 INFO [trainer.py:765] (5/8) Epoch 5, batch 1200, train_loss[loss=3.642, NarTop10Accuracy=0.5967, over 7359.00 frames. ], tot_loss[loss=3.674, NarTop10Accuracy=0.5903, over 5921.24 frames. ], batch size: 31, lr: 1.59e-02
2024-08-06 15:25:19,379 INFO [trainer.py:765] (5/8) Epoch 5, batch 1300, train_loss[loss=3.784, NarTop10Accuracy=0.5666, over 5178.00 frames. ], tot_loss[loss=3.664, NarTop10Accuracy=0.5926, over 5977.83 frames. ], batch size: 6, lr: 1.59e-02
2024-08-06 15:25:51,694 INFO [trainer.py:765] (5/8) Epoch 5, batch 1400, train_loss[loss=3.85, NarTop10Accuracy=0.5496, over 6066.00 frames. ], tot_loss[loss=3.672, NarTop10Accuracy=0.5909, over 6012.52 frames. ], batch size: 11, lr: 1.58e-02
2024-08-06 15:26:26,195 INFO [trainer.py:765] (5/8) Epoch 5, batch 1500, train_loss[loss=3.697, NarTop10Accuracy=0.59, over 6012.00 frames. ], tot_loss[loss=3.665, NarTop10Accuracy=0.5919, over 5935.97 frames. ], batch size: 50, lr: 1.58e-02
2024-08-06 15:26:54,130 INFO [trainer.py:765] (5/8) Epoch 5, batch 1600, train_loss[loss=3.5, NarTop10Accuracy=0.6234, over 7125.00 frames. ], tot_loss[loss=3.677, NarTop10Accuracy=0.5896, over 5921.56 frames. ], batch size: 22, lr: 1.57e-02
2024-08-06 15:27:19,603 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 15:27:27,821 INFO [trainer.py:811] (5/8) Epoch 5, validation: loss=3.552, NarTop10Accuracy=0.6147, over 1905321.00 frames. 
2024-08-06 15:27:27,822 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 15:27:28,341 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 5, batch 1700, train_loss[loss=3.811, NarTop10Accuracy=0.5511, over 6090.00 frames. ], tot_loss[loss=3.667, NarTop10Accuracy=0.5917, over 5908.53 frames. ], batch size: 13, lr: 1.56e-02
2024-08-06 15:27:55,652 INFO [trainer.py:765] (5/8) Epoch 5, batch 1800, train_loss[loss=3.805, NarTop10Accuracy=0.5675, over 6957.00 frames. ], tot_loss[loss=3.661, NarTop10Accuracy=0.593, over 5970.72 frames. ], batch size: 22, lr: 1.56e-02
2024-08-06 15:28:22,171 INFO [trainer.py:765] (5/8) Epoch 5, batch 1900, train_loss[loss=3.682, NarTop10Accuracy=0.5963, over 6003.00 frames. ], tot_loss[loss=3.664, NarTop10Accuracy=0.5921, over 6013.98 frames. ], batch size: 50, lr: 1.55e-02
2024-08-06 15:28:47,893 INFO [trainer.py:765] (5/8) Epoch 5, batch 2000, train_loss[loss=3.609, NarTop10Accuracy=0.607, over 6348.00 frames. ], tot_loss[loss=3.667, NarTop10Accuracy=0.5913, over 6003.27 frames. ], batch size: 52, lr: 1.55e-02
2024-08-06 15:29:13,770 INFO [trainer.py:765] (5/8) Epoch 5, batch 2100, train_loss[loss=3.357, NarTop10Accuracy=0.6565, over 4851.00 frames. ], tot_loss[loss=3.678, NarTop10Accuracy=0.5889, over 5990.51 frames. ], batch size: 5, lr: 1.54e-02
2024-08-06 15:29:39,177 INFO [trainer.py:765] (5/8) Epoch 5, batch 2200, train_loss[loss=4.084, NarTop10Accuracy=0.503, over 7251.00 frames. ], tot_loss[loss=3.662, NarTop10Accuracy=0.5924, over 6028.91 frames. ], batch size: 31, lr: 1.54e-02
2024-08-06 15:30:04,429 INFO [trainer.py:765] (5/8) Epoch 5, batch 2300, train_loss[loss=3.509, NarTop10Accuracy=0.6296, over 5778.00 frames. ], tot_loss[loss=3.669, NarTop10Accuracy=0.591, over 6035.96 frames. ], batch size: 9, lr: 1.53e-02
2024-08-06 15:30:28,862 INFO [trainer.py:765] (5/8) Epoch 5, batch 2400, train_loss[loss=3.363, NarTop10Accuracy=0.6576, over 5208.00 frames. ], tot_loss[loss=3.645, NarTop10Accuracy=0.5961, over 5790.42 frames. ], batch size: 7, lr: 1.53e-02
2024-08-06 15:30:52,503 INFO [trainer.py:765] (5/8) Epoch 5, batch 2500, train_loss[loss=3.487, NarTop10Accuracy=0.6339, over 5088.00 frames. ], tot_loss[loss=3.611, NarTop10Accuracy=0.603, over 5494.91 frames. ], batch size: 7, lr: 1.52e-02
2024-08-06 15:31:12,338 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 15:32:14,415 INFO [trainer.py:765] (5/8) Epoch 6, batch 100, train_loss[loss=3.473, NarTop10Accuracy=0.6349, over 7149.00 frames. ], tot_loss[loss=3.63, NarTop10Accuracy=0.5994, over 2359.08 frames. ], batch size: 31, lr: 1.42e-02
2024-08-06 15:32:46,015 INFO [trainer.py:765] (5/8) Epoch 6, batch 200, train_loss[loss=3.993, NarTop10Accuracy=0.514, over 6831.00 frames. ], tot_loss[loss=3.615, NarTop10Accuracy=0.6021, over 3860.27 frames. ], batch size: 17, lr: 1.42e-02
2024-08-06 15:33:21,242 INFO [trainer.py:765] (5/8) Epoch 6, batch 300, train_loss[loss=3.503, NarTop10Accuracy=0.6324, over 7188.00 frames. ], tot_loss[loss=3.609, NarTop10Accuracy=0.6036, over 4659.02 frames. ], batch size: 22, lr: 1.41e-02
2024-08-06 15:33:56,035 INFO [trainer.py:765] (5/8) Epoch 6, batch 400, train_loss[loss=3.557, NarTop10Accuracy=0.625, over 5124.00 frames. ], tot_loss[loss=3.593, NarTop10Accuracy=0.6066, over 5104.39 frames. ], batch size: 7, lr: 1.41e-02
2024-08-06 15:34:26,759 INFO [trainer.py:765] (5/8) Epoch 6, batch 500, train_loss[loss=3.408, NarTop10Accuracy=0.6469, over 6006.00 frames. ], tot_loss[loss=3.581, NarTop10Accuracy=0.6093, over 5372.35 frames. ], batch size: 11, lr: 1.40e-02
2024-08-06 15:35:01,458 INFO [trainer.py:765] (5/8) Epoch 6, batch 600, train_loss[loss=3.18, NarTop10Accuracy=0.6918, over 5688.00 frames. ], tot_loss[loss=3.582, NarTop10Accuracy=0.6089, over 5640.38 frames. ], batch size: 9, lr: 1.40e-02
2024-08-06 15:35:32,733 INFO [trainer.py:765] (5/8) Epoch 6, batch 700, train_loss[loss=3.441, NarTop10Accuracy=0.634, over 5265.00 frames. ], tot_loss[loss=3.585, NarTop10Accuracy=0.6083, over 5716.38 frames. ], batch size: 6, lr: 1.39e-02
2024-08-06 15:36:06,844 INFO [trainer.py:765] (5/8) Epoch 6, batch 800, train_loss[loss=3.755, NarTop10Accuracy=0.5739, over 5010.00 frames. ], tot_loss[loss=3.6, NarTop10Accuracy=0.6051, over 5752.94 frames. ], batch size: 6, lr: 1.39e-02
2024-08-06 15:36:40,384 INFO [trainer.py:765] (5/8) Epoch 6, batch 900, train_loss[loss=4.006, NarTop10Accuracy=0.5298, over 6177.00 frames. ], tot_loss[loss=3.588, NarTop10Accuracy=0.6075, over 5779.07 frames. ], batch size: 13, lr: 1.38e-02
2024-08-06 15:37:15,272 INFO [trainer.py:765] (5/8) Epoch 6, batch 1000, train_loss[loss=3.385, NarTop10Accuracy=0.6541, over 6285.00 frames. ], tot_loss[loss=3.603, NarTop10Accuracy=0.6046, over 5896.31 frames. ], batch size: 13, lr: 1.38e-02
2024-08-06 15:37:50,508 INFO [trainer.py:765] (5/8) Epoch 6, batch 1100, train_loss[loss=3.37, NarTop10Accuracy=0.6543, over 6879.00 frames. ], tot_loss[loss=3.596, NarTop10Accuracy=0.6061, over 5932.05 frames. ], batch size: 17, lr: 1.38e-02
2024-08-06 15:37:55,827 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 15:38:04,436 INFO [trainer.py:811] (5/8) Epoch 6, validation: loss=3.421, NarTop10Accuracy=0.6418, over 1905321.00 frames. 
2024-08-06 15:38:04,437 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 15:38:04,966 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 6, batch 1200, train_loss[loss=3.451, NarTop10Accuracy=0.6427, over 7476.00 frames. ], tot_loss[loss=3.589, NarTop10Accuracy=0.6073, over 5914.76 frames. ], batch size: 31, lr: 1.37e-02
2024-08-06 15:39:08,242 INFO [trainer.py:765] (5/8) Epoch 6, batch 1300, train_loss[loss=3.377, NarTop10Accuracy=0.6466, over 4257.00 frames. ], tot_loss[loss=3.577, NarTop10Accuracy=0.6097, over 5983.45 frames. ], batch size: 5, lr: 1.37e-02
2024-08-06 15:39:44,070 INFO [trainer.py:765] (5/8) Epoch 6, batch 1400, train_loss[loss=3.435, NarTop10Accuracy=0.6396, over 6135.00 frames. ], tot_loss[loss=3.572, NarTop10Accuracy=0.6107, over 5994.64 frames. ], batch size: 11, lr: 1.36e-02
2024-08-06 15:40:15,383 INFO [trainer.py:765] (5/8) Epoch 6, batch 1500, train_loss[loss=3.937, NarTop10Accuracy=0.5258, over 5580.00 frames. ], tot_loss[loss=3.572, NarTop10Accuracy=0.6105, over 5949.71 frames. ], batch size: 50, lr: 1.36e-02
2024-08-06 15:40:43,106 INFO [trainer.py:765] (5/8) Epoch 6, batch 1600, train_loss[loss=3.383, NarTop10Accuracy=0.6469, over 6951.00 frames. ], tot_loss[loss=3.57, NarTop10Accuracy=0.6112, over 5934.08 frames. ], batch size: 22, lr: 1.35e-02
2024-08-06 15:41:09,789 INFO [trainer.py:765] (5/8) Epoch 6, batch 1700, train_loss[loss=3.459, NarTop10Accuracy=0.6275, over 6309.00 frames. ], tot_loss[loss=3.558, NarTop10Accuracy=0.6136, over 5914.60 frames. ], batch size: 13, lr: 1.35e-02
2024-08-06 15:41:36,317 INFO [trainer.py:765] (5/8) Epoch 6, batch 1800, train_loss[loss=3.393, NarTop10Accuracy=0.6516, over 7059.00 frames. ], tot_loss[loss=3.571, NarTop10Accuracy=0.611, over 5990.49 frames. ], batch size: 22, lr: 1.35e-02
2024-08-06 15:42:02,720 INFO [trainer.py:765] (5/8) Epoch 6, batch 1900, train_loss[loss=3.878, NarTop10Accuracy=0.5405, over 6855.00 frames. ], tot_loss[loss=3.589, NarTop10Accuracy=0.6074, over 6020.21 frames. ], batch size: 51, lr: 1.34e-02
2024-08-06 15:42:28,319 INFO [trainer.py:765] (5/8) Epoch 6, batch 2000, train_loss[loss=3.509, NarTop10Accuracy=0.6333, over 6252.00 frames. ], tot_loss[loss=3.578, NarTop10Accuracy=0.6096, over 5996.87 frames. ], batch size: 50, lr: 1.34e-02
2024-08-06 15:42:53,669 INFO [trainer.py:765] (5/8) Epoch 6, batch 2100, train_loss[loss=3.336, NarTop10Accuracy=0.6616, over 4866.00 frames. ], tot_loss[loss=3.567, NarTop10Accuracy=0.6114, over 5959.37 frames. ], batch size: 5, lr: 1.33e-02
2024-08-06 15:43:18,978 INFO [trainer.py:765] (5/8) Epoch 6, batch 2200, train_loss[loss=3.899, NarTop10Accuracy=0.5471, over 7404.00 frames. ], tot_loss[loss=3.569, NarTop10Accuracy=0.6116, over 6003.12 frames. ], batch size: 32, lr: 1.33e-02
2024-08-06 15:43:44,106 INFO [trainer.py:765] (5/8) Epoch 6, batch 2300, train_loss[loss=3.384, NarTop10Accuracy=0.652, over 5697.00 frames. ], tot_loss[loss=3.57, NarTop10Accuracy=0.6117, over 6022.51 frames. ], batch size: 9, lr: 1.33e-02
2024-08-06 15:44:08,620 INFO [trainer.py:765] (5/8) Epoch 6, batch 2400, train_loss[loss=3.178, NarTop10Accuracy=0.6953, over 5034.00 frames. ], tot_loss[loss=3.543, NarTop10Accuracy=0.6173, over 5786.51 frames. ], batch size: 7, lr: 1.32e-02
2024-08-06 15:44:32,132 INFO [trainer.py:765] (5/8) Epoch 6, batch 2500, train_loss[loss=3.436, NarTop10Accuracy=0.6475, over 5130.00 frames. ], tot_loss[loss=3.525, NarTop10Accuracy=0.6203, over 5488.28 frames. ], batch size: 7, lr: 1.32e-02
2024-08-06 15:44:51,606 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 15:45:58,043 INFO [trainer.py:765] (5/8) Epoch 7, batch 100, train_loss[loss=3.312, NarTop10Accuracy=0.6631, over 7110.00 frames. ], tot_loss[loss=3.537, NarTop10Accuracy=0.6188, over 2364.60 frames. ], batch size: 31, lr: 1.24e-02
2024-08-06 15:46:33,614 INFO [trainer.py:765] (5/8) Epoch 7, batch 200, train_loss[loss=3.553, NarTop10Accuracy=0.6255, over 6876.00 frames. ], tot_loss[loss=3.521, NarTop10Accuracy=0.6208, over 3852.88 frames. ], batch size: 17, lr: 1.23e-02
2024-08-06 15:47:03,246 INFO [trainer.py:765] (5/8) Epoch 7, batch 300, train_loss[loss=3.682, NarTop10Accuracy=0.5892, over 6951.00 frames. ], tot_loss[loss=3.536, NarTop10Accuracy=0.6181, over 4660.02 frames. ], batch size: 22, lr: 1.23e-02
2024-08-06 15:47:34,495 INFO [trainer.py:765] (5/8) Epoch 7, batch 400, train_loss[loss=3.517, NarTop10Accuracy=0.6168, over 5133.00 frames. ], tot_loss[loss=3.528, NarTop10Accuracy=0.6194, over 5112.31 frames. ], batch size: 7, lr: 1.23e-02
2024-08-06 15:48:13,730 INFO [trainer.py:765] (5/8) Epoch 7, batch 500, train_loss[loss=3.599, NarTop10Accuracy=0.6006, over 5943.00 frames. ], tot_loss[loss=3.518, NarTop10Accuracy=0.6213, over 5383.04 frames. ], batch size: 11, lr: 1.22e-02
2024-08-06 15:48:26,369 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 15:48:34,533 INFO [trainer.py:811] (5/8) Epoch 7, validation: loss=3.326, NarTop10Accuracy=0.6612, over 1905321.00 frames. 
2024-08-06 15:48:34,534 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 15:48:35,078 INFO [optim.py:386] (5/8) 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 15:48:52,721 INFO [trainer.py:765] (5/8) Epoch 7, batch 600, train_loss[loss=3.092, NarTop10Accuracy=0.7073, over 5640.00 frames. ], tot_loss[loss=3.519, NarTop10Accuracy=0.6211, over 5660.25 frames. ], batch size: 9, lr: 1.22e-02
2024-08-06 15:49:24,912 INFO [trainer.py:765] (5/8) Epoch 7, batch 700, train_loss[loss=3.769, NarTop10Accuracy=0.5596, over 5031.00 frames. ], tot_loss[loss=3.51, NarTop10Accuracy=0.6235, over 5739.39 frames. ], batch size: 6, lr: 1.21e-02
2024-08-06 15:50:04,382 INFO [trainer.py:765] (5/8) Epoch 7, batch 800, train_loss[loss=3.288, NarTop10Accuracy=0.671, over 4320.00 frames. ], tot_loss[loss=3.497, NarTop10Accuracy=0.6264, over 5787.91 frames. ], batch size: 5, lr: 1.21e-02
2024-08-06 15:50:34,549 INFO [trainer.py:765] (5/8) Epoch 7, batch 900, train_loss[loss=3.309, NarTop10Accuracy=0.6654, over 6273.00 frames. ], tot_loss[loss=3.487, NarTop10Accuracy=0.6282, over 5810.56 frames. ], batch size: 13, lr: 1.21e-02
2024-08-06 15:51:07,156 INFO [trainer.py:765] (5/8) Epoch 7, batch 1000, train_loss[loss=3.275, NarTop10Accuracy=0.6699, over 6708.00 frames. ], tot_loss[loss=3.486, NarTop10Accuracy=0.6281, over 5914.66 frames. ], batch size: 14, lr: 1.20e-02
2024-08-06 15:51:51,759 INFO [trainer.py:765] (5/8) Epoch 7, batch 1100, train_loss[loss=3.276, NarTop10Accuracy=0.6718, over 6801.00 frames. ], tot_loss[loss=3.494, NarTop10Accuracy=0.6268, over 5938.25 frames. ], batch size: 17, lr: 1.20e-02
2024-08-06 15:52:22,700 INFO [trainer.py:765] (5/8) Epoch 7, batch 1200, train_loss[loss=3.393, NarTop10Accuracy=0.649, over 7239.00 frames. ], tot_loss[loss=3.486, NarTop10Accuracy=0.6286, over 5908.50 frames. ], batch size: 31, lr: 1.20e-02
2024-08-06 15:52:52,008 INFO [trainer.py:765] (5/8) Epoch 7, batch 1300, train_loss[loss=3.592, NarTop10Accuracy=0.5954, over 5154.00 frames. ], tot_loss[loss=3.49, NarTop10Accuracy=0.6273, over 5987.75 frames. ], batch size: 6, lr: 1.19e-02
2024-08-06 15:53:33,843 INFO [trainer.py:765] (5/8) Epoch 7, batch 1400, train_loss[loss=3.229, NarTop10Accuracy=0.6842, over 6237.00 frames. ], tot_loss[loss=3.491, NarTop10Accuracy=0.6272, over 6023.45 frames. ], batch size: 11, lr: 1.19e-02
2024-08-06 15:54:04,600 INFO [trainer.py:765] (5/8) Epoch 7, batch 1500, train_loss[loss=3.779, NarTop10Accuracy=0.5697, over 5847.00 frames. ], tot_loss[loss=3.467, NarTop10Accuracy=0.632, over 5963.35 frames. ], batch size: 50, lr: 1.19e-02
2024-08-06 15:54:32,386 INFO [trainer.py:765] (5/8) Epoch 7, batch 1600, train_loss[loss=3.698, NarTop10Accuracy=0.5777, over 6918.00 frames. ], tot_loss[loss=3.472, NarTop10Accuracy=0.6308, over 5935.54 frames. ], batch size: 22, lr: 1.19e-02
2024-08-06 15:54:59,055 INFO [trainer.py:765] (5/8) Epoch 7, batch 1700, train_loss[loss=3.655, NarTop10Accuracy=0.581, over 6159.00 frames. ], tot_loss[loss=3.492, NarTop10Accuracy=0.6264, over 5936.50 frames. ], batch size: 13, lr: 1.18e-02
2024-08-06 15:55:25,513 INFO [trainer.py:765] (5/8) Epoch 7, batch 1800, train_loss[loss=3.906, NarTop10Accuracy=0.5339, over 6963.00 frames. ], tot_loss[loss=3.489, NarTop10Accuracy=0.6272, over 5994.28 frames. ], batch size: 22, lr: 1.18e-02
2024-08-06 15:55:52,083 INFO [trainer.py:765] (5/8) Epoch 7, batch 1900, train_loss[loss=3.41, NarTop10Accuracy=0.6459, over 6015.00 frames. ], tot_loss[loss=3.51, NarTop10Accuracy=0.6227, over 6043.53 frames. ], batch size: 51, lr: 1.18e-02
2024-08-06 15:56:17,592 INFO [trainer.py:765] (5/8) Epoch 7, batch 2000, train_loss[loss=3.78, NarTop10Accuracy=0.5662, over 6264.00 frames. ], tot_loss[loss=3.5, NarTop10Accuracy=0.6246, over 6003.59 frames. ], batch size: 50, lr: 1.17e-02
2024-08-06 15:56:42,857 INFO [trainer.py:765] (5/8) Epoch 7, batch 2100, train_loss[loss=3.764, NarTop10Accuracy=0.5606, over 3897.00 frames. ], tot_loss[loss=3.485, NarTop10Accuracy=0.6279, over 5969.67 frames. ], batch size: 4, lr: 1.17e-02
2024-08-06 15:57:08,080 INFO [trainer.py:765] (5/8) Epoch 7, batch 2200, train_loss[loss=3.471, NarTop10Accuracy=0.6327, over 7341.00 frames. ], tot_loss[loss=3.509, NarTop10Accuracy=0.6233, over 6003.26 frames. ], batch size: 31, lr: 1.17e-02
2024-08-06 15:57:33,179 INFO [trainer.py:765] (5/8) Epoch 7, batch 2300, train_loss[loss=3.326, NarTop10Accuracy=0.6561, over 5817.00 frames. ], tot_loss[loss=3.511, NarTop10Accuracy=0.6227, over 6005.65 frames. ], batch size: 9, lr: 1.16e-02
2024-08-06 15:57:57,620 INFO [trainer.py:765] (5/8) Epoch 7, batch 2400, train_loss[loss=3.132, NarTop10Accuracy=0.6951, over 4953.00 frames. ], tot_loss[loss=3.492, NarTop10Accuracy=0.6265, over 5763.41 frames. ], batch size: 7, lr: 1.16e-02
2024-08-06 15:58:21,089 INFO [trainer.py:765] (5/8) Epoch 7, batch 2500, train_loss[loss=3.794, NarTop10Accuracy=0.5609, over 5064.00 frames. ], tot_loss[loss=3.467, NarTop10Accuracy=0.6314, over 5467.11 frames. ], batch size: 7, lr: 1.16e-02
2024-08-06 15:58:31,566 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 15:58:39,769 INFO [trainer.py:811] (5/8) Epoch 7, validation: loss=3.381, NarTop10Accuracy=0.6488, over 1905321.00 frames. 
2024-08-06 15:58:39,770 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 15:58:40,221 INFO [optim.py:386] (5/8) Clipping_scale=2.0, grad-norm quartiles 1.471e+02 1.831e+02 1.996e+02 2.207e+02 5.229e+02, threshold=3.992e+02, percent-clipped=0.2
2024-08-06 15:58:49,032 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 15:59:52,877 INFO [trainer.py:765] (5/8) Epoch 8, batch 100, train_loss[loss=3.524, NarTop10Accuracy=0.6129, over 7293.00 frames. ], tot_loss[loss=3.462, NarTop10Accuracy=0.6336, over 2367.73 frames. ], batch size: 31, lr: 1.09e-02
2024-08-06 16:00:27,881 INFO [trainer.py:765] (5/8) Epoch 8, batch 200, train_loss[loss=3.206, NarTop10Accuracy=0.684, over 6840.00 frames. ], tot_loss[loss=3.469, NarTop10Accuracy=0.6315, over 3859.04 frames. ], batch size: 17, lr: 1.09e-02
2024-08-06 16:00:58,563 INFO [trainer.py:765] (5/8) Epoch 8, batch 300, train_loss[loss=3.134, NarTop10Accuracy=0.6933, over 7209.00 frames. ], tot_loss[loss=3.462, NarTop10Accuracy=0.633, over 4651.66 frames. ], batch size: 23, lr: 1.08e-02
2024-08-06 16:01:29,760 INFO [trainer.py:765] (5/8) Epoch 8, batch 400, train_loss[loss=3.67, NarTop10Accuracy=0.5903, over 5688.00 frames. ], tot_loss[loss=3.469, NarTop10Accuracy=0.6315, over 5091.31 frames. ], batch size: 8, lr: 1.08e-02
2024-08-06 16:02:04,066 INFO [trainer.py:765] (5/8) Epoch 8, batch 500, train_loss[loss=3.902, NarTop10Accuracy=0.541, over 6015.00 frames. ], tot_loss[loss=3.453, NarTop10Accuracy=0.6347, over 5376.07 frames. ], batch size: 11, lr: 1.08e-02
2024-08-06 16:02:41,836 INFO [trainer.py:765] (5/8) Epoch 8, batch 600, train_loss[loss=3.164, NarTop10Accuracy=0.6911, over 5685.00 frames. ], tot_loss[loss=3.473, NarTop10Accuracy=0.6305, over 5644.43 frames. ], batch size: 9, lr: 1.08e-02
2024-08-06 16:03:11,500 INFO [trainer.py:765] (5/8) Epoch 8, batch 700, train_loss[loss=3.735, NarTop10Accuracy=0.581, over 5145.00 frames. ], tot_loss[loss=3.481, NarTop10Accuracy=0.6286, over 5702.07 frames. ], batch size: 6, lr: 1.07e-02
2024-08-06 16:03:50,084 INFO [trainer.py:765] (5/8) Epoch 8, batch 800, train_loss[loss=3.554, NarTop10Accuracy=0.615, over 5067.00 frames. ], tot_loss[loss=3.472, NarTop10Accuracy=0.6306, over 5752.39 frames. ], batch size: 6, lr: 1.07e-02
2024-08-06 16:04:27,588 INFO [trainer.py:765] (5/8) Epoch 8, batch 900, train_loss[loss=3.332, NarTop10Accuracy=0.6667, over 6126.00 frames. ], tot_loss[loss=3.454, NarTop10Accuracy=0.6342, over 5766.06 frames. ], batch size: 13, lr: 1.07e-02
2024-08-06 16:04:57,466 INFO [trainer.py:765] (5/8) Epoch 8, batch 1000, train_loss[loss=3.56, NarTop10Accuracy=0.6102, over 6168.00 frames. ], tot_loss[loss=3.437, NarTop10Accuracy=0.6373, over 5867.17 frames. ], batch size: 13, lr: 1.07e-02
2024-08-06 16:05:37,294 INFO [trainer.py:765] (5/8) Epoch 8, batch 1100, train_loss[loss=3.868, NarTop10Accuracy=0.5454, over 6909.00 frames. ], tot_loss[loss=3.43, NarTop10Accuracy=0.6392, over 5911.41 frames. ], batch size: 17, lr: 1.06e-02
2024-08-06 16:06:15,860 INFO [trainer.py:765] (5/8) Epoch 8, batch 1200, train_loss[loss=3.422, NarTop10Accuracy=0.6451, over 7371.00 frames. ], tot_loss[loss=3.442, NarTop10Accuracy=0.6366, over 5920.40 frames. ], batch size: 31, lr: 1.06e-02
2024-08-06 16:06:45,187 INFO [trainer.py:765] (5/8) Epoch 8, batch 1300, train_loss[loss=3.257, NarTop10Accuracy=0.6882, over 4281.00 frames. ], tot_loss[loss=3.433, NarTop10Accuracy=0.6385, over 5989.19 frames. ], batch size: 5, lr: 1.06e-02
2024-08-06 16:07:24,235 INFO [trainer.py:765] (5/8) Epoch 8, batch 1400, train_loss[loss=3.413, NarTop10Accuracy=0.6424, over 6105.00 frames. ], tot_loss[loss=3.438, NarTop10Accuracy=0.6378, over 6010.40 frames. ], batch size: 11, lr: 1.05e-02
2024-08-06 16:07:52,169 INFO [trainer.py:765] (5/8) Epoch 8, batch 1500, train_loss[loss=3.326, NarTop10Accuracy=0.6617, over 6684.00 frames. ], tot_loss[loss=3.423, NarTop10Accuracy=0.6409, over 5958.79 frames. ], batch size: 50, lr: 1.05e-02
2024-08-06 16:08:19,949 INFO [trainer.py:765] (5/8) Epoch 8, batch 1600, train_loss[loss=3.233, NarTop10Accuracy=0.6846, over 7344.00 frames. ], tot_loss[loss=3.422, NarTop10Accuracy=0.6413, over 5932.84 frames. ], batch size: 22, lr: 1.05e-02
2024-08-06 16:08:46,618 INFO [trainer.py:765] (5/8) Epoch 8, batch 1700, train_loss[loss=3.382, NarTop10Accuracy=0.6543, over 6597.00 frames. ], tot_loss[loss=3.424, NarTop10Accuracy=0.6409, over 5922.16 frames. ], batch size: 14, lr: 1.05e-02
2024-08-06 16:09:13,106 INFO [trainer.py:765] (5/8) Epoch 8, batch 1800, train_loss[loss=3.189, NarTop10Accuracy=0.6977, over 7311.00 frames. ], tot_loss[loss=3.414, NarTop10Accuracy=0.6427, over 5987.60 frames. ], batch size: 22, lr: 1.04e-02
2024-08-06 16:09:39,635 INFO [trainer.py:765] (5/8) Epoch 8, batch 1900, train_loss[loss=3.742, NarTop10Accuracy=0.5792, over 6384.00 frames. ], tot_loss[loss=3.407, NarTop10Accuracy=0.6444, over 6031.39 frames. ], batch size: 50, lr: 1.04e-02
2024-08-06 16:09:56,939 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 16:10:04,970 INFO [trainer.py:811] (5/8) Epoch 8, validation: loss=3.282, NarTop10Accuracy=0.6699, over 1905321.00 frames. 
2024-08-06 16:10:04,970 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 16:10:05,470 INFO [optim.py:386] (5/8) 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 16:10:13,203 INFO [trainer.py:765] (5/8) Epoch 8, batch 2000, train_loss[loss=3.925, NarTop10Accuracy=0.527, over 6267.00 frames. ], tot_loss[loss=3.415, NarTop10Accuracy=0.6432, over 6008.78 frames. ], batch size: 50, lr: 1.04e-02
2024-08-06 16:10:38,514 INFO [trainer.py:765] (5/8) Epoch 8, batch 2100, train_loss[loss=3.184, NarTop10Accuracy=0.6827, over 4737.00 frames. ], tot_loss[loss=3.407, NarTop10Accuracy=0.6443, over 5982.20 frames. ], batch size: 5, lr: 1.04e-02
2024-08-06 16:11:03,747 INFO [trainer.py:765] (5/8) Epoch 8, batch 2200, train_loss[loss=3.578, NarTop10Accuracy=0.598, over 7218.00 frames. ], tot_loss[loss=3.419, NarTop10Accuracy=0.6415, over 6003.72 frames. ], batch size: 31, lr: 1.04e-02
2024-08-06 16:11:28,905 INFO [trainer.py:765] (5/8) Epoch 8, batch 2300, train_loss[loss=3.725, NarTop10Accuracy=0.5784, over 5745.00 frames. ], tot_loss[loss=3.44, NarTop10Accuracy=0.6374, over 6016.20 frames. ], batch size: 9, lr: 1.03e-02
2024-08-06 16:11:53,092 INFO [trainer.py:765] (5/8) Epoch 8, batch 2400, train_loss[loss=3.511, NarTop10Accuracy=0.6325, over 5262.00 frames. ], tot_loss[loss=3.421, NarTop10Accuracy=0.6411, over 5777.59 frames. ], batch size: 7, lr: 1.03e-02
2024-08-06 16:12:16,444 INFO [trainer.py:765] (5/8) Epoch 8, batch 2500, train_loss[loss=3.301, NarTop10Accuracy=0.6581, over 5142.00 frames. ], tot_loss[loss=3.411, NarTop10Accuracy=0.6429, over 5459.45 frames. ], batch size: 7, lr: 1.03e-02
2024-08-06 16:12:36,202 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 16:13:37,515 INFO [trainer.py:765] (5/8) Epoch 9, batch 100, train_loss[loss=3.191, NarTop10Accuracy=0.6878, over 7239.00 frames. ], tot_loss[loss=3.372, NarTop10Accuracy=0.6521, over 2341.76 frames. ], batch size: 31, lr: 9.72e-03
2024-08-06 16:14:14,441 INFO [trainer.py:765] (5/8) Epoch 9, batch 200, train_loss[loss=3.562, NarTop10Accuracy=0.6059, over 6756.00 frames. ], tot_loss[loss=3.365, NarTop10Accuracy=0.654, over 3839.49 frames. ], batch size: 17, lr: 9.70e-03
2024-08-06 16:14:44,508 INFO [trainer.py:765] (5/8) Epoch 9, batch 300, train_loss[loss=3.324, NarTop10Accuracy=0.6662, over 7185.00 frames. ], tot_loss[loss=3.378, NarTop10Accuracy=0.6507, over 4644.31 frames. ], batch size: 22, lr: 9.68e-03
2024-08-06 16:15:14,915 INFO [trainer.py:765] (5/8) Epoch 9, batch 400, train_loss[loss=3.166, NarTop10Accuracy=0.6946, over 5196.00 frames. ], tot_loss[loss=3.36, NarTop10Accuracy=0.654, over 5117.32 frames. ], batch size: 7, lr: 9.65e-03
2024-08-06 16:15:50,337 INFO [trainer.py:765] (5/8) Epoch 9, batch 500, train_loss[loss=3.142, NarTop10Accuracy=0.6973, over 6090.00 frames. ], tot_loss[loss=3.346, NarTop10Accuracy=0.6565, over 5384.95 frames. ], batch size: 11, lr: 9.63e-03
2024-08-06 16:16:23,973 INFO [trainer.py:765] (5/8) Epoch 9, batch 600, train_loss[loss=3.644, NarTop10Accuracy=0.5976, over 5790.00 frames. ], tot_loss[loss=3.34, NarTop10Accuracy=0.6582, over 5651.41 frames. ], batch size: 9, lr: 9.61e-03
2024-08-06 16:16:57,146 INFO [trainer.py:765] (5/8) Epoch 9, batch 700, train_loss[loss=3.229, NarTop10Accuracy=0.6848, over 4275.00 frames. ], tot_loss[loss=3.351, NarTop10Accuracy=0.656, over 5730.21 frames. ], batch size: 5, lr: 9.59e-03
2024-08-06 16:17:32,053 INFO [trainer.py:765] (5/8) Epoch 9, batch 800, train_loss[loss=3.17, NarTop10Accuracy=0.6982, over 4395.00 frames. ], tot_loss[loss=3.382, NarTop10Accuracy=0.6493, over 5784.44 frames. ], batch size: 5, lr: 9.57e-03
2024-08-06 16:18:07,816 INFO [trainer.py:765] (5/8) Epoch 9, batch 900, train_loss[loss=3.157, NarTop10Accuracy=0.7065, over 6189.00 frames. ], tot_loss[loss=3.382, NarTop10Accuracy=0.6492, over 5799.13 frames. ], batch size: 13, lr: 9.55e-03
2024-08-06 16:18:39,346 INFO [trainer.py:765] (5/8) Epoch 9, batch 1000, train_loss[loss=3.243, NarTop10Accuracy=0.6657, over 6279.00 frames. ], tot_loss[loss=3.39, NarTop10Accuracy=0.6475, over 5897.92 frames. ], batch size: 13, lr: 9.53e-03
2024-08-06 16:19:15,383 INFO [trainer.py:765] (5/8) Epoch 9, batch 1100, train_loss[loss=3.369, NarTop10Accuracy=0.6521, over 6891.00 frames. ], tot_loss[loss=3.39, NarTop10Accuracy=0.6472, over 5937.90 frames. ], batch size: 17, lr: 9.50e-03
2024-08-06 16:19:53,879 INFO [trainer.py:765] (5/8) Epoch 9, batch 1200, train_loss[loss=3.714, NarTop10Accuracy=0.5793, over 7185.00 frames. ], tot_loss[loss=3.391, NarTop10Accuracy=0.6469, over 5940.87 frames. ], batch size: 31, lr: 9.48e-03
2024-08-06 16:20:24,907 INFO [trainer.py:765] (5/8) Epoch 9, batch 1300, train_loss[loss=3.077, NarTop10Accuracy=0.7113, over 5319.00 frames. ], tot_loss[loss=3.393, NarTop10Accuracy=0.6468, over 6002.25 frames. ], batch size: 6, lr: 9.46e-03
2024-08-06 16:20:56,580 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 16:21:04,483 INFO [trainer.py:811] (5/8) Epoch 9, validation: loss=3.266, NarTop10Accuracy=0.6725, over 1905321.00 frames. 
2024-08-06 16:21:04,484 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 16:21:05,035 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 9, batch 1400, train_loss[loss=3.679, NarTop10Accuracy=0.5834, over 6030.00 frames. ], tot_loss[loss=3.405, NarTop10Accuracy=0.6444, over 6026.82 frames. ], batch size: 11, lr: 9.44e-03
2024-08-06 16:21:38,896 INFO [trainer.py:765] (5/8) Epoch 9, batch 1500, train_loss[loss=3.37, NarTop10Accuracy=0.6541, over 5793.00 frames. ], tot_loss[loss=3.379, NarTop10Accuracy=0.6501, over 5970.51 frames. ], batch size: 52, lr: 9.42e-03
2024-08-06 16:22:06,721 INFO [trainer.py:765] (5/8) Epoch 9, batch 1600, train_loss[loss=3.355, NarTop10Accuracy=0.6544, over 7110.00 frames. ], tot_loss[loss=3.373, NarTop10Accuracy=0.6513, over 5931.30 frames. ], batch size: 22, lr: 9.40e-03
2024-08-06 16:22:33,470 INFO [trainer.py:765] (5/8) Epoch 9, batch 1700, train_loss[loss=3.566, NarTop10Accuracy=0.6132, over 6576.00 frames. ], tot_loss[loss=3.391, NarTop10Accuracy=0.6475, over 5917.02 frames. ], batch size: 14, lr: 9.38e-03
2024-08-06 16:23:00,063 INFO [trainer.py:765] (5/8) Epoch 9, batch 1800, train_loss[loss=3.287, NarTop10Accuracy=0.6768, over 7053.00 frames. ], tot_loss[loss=3.378, NarTop10Accuracy=0.65, over 5982.12 frames. ], batch size: 22, lr: 9.36e-03
2024-08-06 16:23:26,782 INFO [trainer.py:765] (5/8) Epoch 9, batch 1900, train_loss[loss=3.404, NarTop10Accuracy=0.6572, over 6411.00 frames. ], tot_loss[loss=3.391, NarTop10Accuracy=0.6476, over 6017.57 frames. ], batch size: 50, lr: 9.34e-03
2024-08-06 16:23:52,485 INFO [trainer.py:765] (5/8) Epoch 9, batch 2000, train_loss[loss=3.971, NarTop10Accuracy=0.5217, over 6279.00 frames. ], tot_loss[loss=3.38, NarTop10Accuracy=0.6495, over 5999.17 frames. ], batch size: 50, lr: 9.32e-03
2024-08-06 16:24:17,963 INFO [trainer.py:765] (5/8) Epoch 9, batch 2100, train_loss[loss=3.314, NarTop10Accuracy=0.665, over 4833.00 frames. ], tot_loss[loss=3.383, NarTop10Accuracy=0.6487, over 5997.16 frames. ], batch size: 5, lr: 9.30e-03
2024-08-06 16:24:43,421 INFO [trainer.py:765] (5/8) Epoch 9, batch 2200, train_loss[loss=3.64, NarTop10Accuracy=0.601, over 7098.00 frames. ], tot_loss[loss=3.389, NarTop10Accuracy=0.6474, over 6027.38 frames. ], batch size: 31, lr: 9.28e-03
2024-08-06 16:25:08,721 INFO [trainer.py:765] (5/8) Epoch 9, batch 2300, train_loss[loss=3.255, NarTop10Accuracy=0.6813, over 5658.00 frames. ], tot_loss[loss=3.404, NarTop10Accuracy=0.6447, over 6030.76 frames. ], batch size: 9, lr: 9.26e-03
2024-08-06 16:25:33,163 INFO [trainer.py:765] (5/8) Epoch 9, batch 2400, train_loss[loss=3.316, NarTop10Accuracy=0.6664, over 4974.00 frames. ], tot_loss[loss=3.4, NarTop10Accuracy=0.6453, over 5784.53 frames. ], batch size: 7, lr: 9.25e-03
2024-08-06 16:25:56,768 INFO [trainer.py:765] (5/8) Epoch 9, batch 2500, train_loss[loss=3.278, NarTop10Accuracy=0.664, over 5316.00 frames. ], tot_loss[loss=3.367, NarTop10Accuracy=0.6518, over 5491.91 frames. ], batch size: 7, lr: 9.23e-03
2024-08-06 16:26:16,496 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 16:27:19,583 INFO [trainer.py:765] (5/8) Epoch 10, batch 100, train_loss[loss=3.265, NarTop10Accuracy=0.6721, over 7335.00 frames. ], tot_loss[loss=3.371, NarTop10Accuracy=0.6512, over 2370.10 frames. ], batch size: 31, lr: 8.76e-03
2024-08-06 16:27:52,628 INFO [trainer.py:765] (5/8) Epoch 10, batch 200, train_loss[loss=3.046, NarTop10Accuracy=0.7233, over 7146.00 frames. ], tot_loss[loss=3.346, NarTop10Accuracy=0.6567, over 3877.84 frames. ], batch size: 18, lr: 8.74e-03
2024-08-06 16:28:23,057 INFO [trainer.py:765] (5/8) Epoch 10, batch 300, train_loss[loss=3.162, NarTop10Accuracy=0.699, over 7161.00 frames. ], tot_loss[loss=3.352, NarTop10Accuracy=0.6555, over 4693.36 frames. ], batch size: 22, lr: 8.72e-03
2024-08-06 16:28:59,199 INFO [trainer.py:765] (5/8) Epoch 10, batch 400, train_loss[loss=3.227, NarTop10Accuracy=0.6772, over 5181.00 frames. ], tot_loss[loss=3.344, NarTop10Accuracy=0.6568, over 5114.18 frames. ], batch size: 7, lr: 8.71e-03
2024-08-06 16:29:29,218 INFO [trainer.py:765] (5/8) Epoch 10, batch 500, train_loss[loss=3.055, NarTop10Accuracy=0.7179, over 6009.00 frames. ], tot_loss[loss=3.339, NarTop10Accuracy=0.6579, over 5391.24 frames. ], batch size: 11, lr: 8.69e-03
2024-08-06 16:30:02,765 INFO [trainer.py:765] (5/8) Epoch 10, batch 600, train_loss[loss=3.525, NarTop10Accuracy=0.6111, over 5748.00 frames. ], tot_loss[loss=3.35, NarTop10Accuracy=0.6558, over 5656.39 frames. ], batch size: 9, lr: 8.67e-03
2024-08-06 16:30:34,264 INFO [trainer.py:765] (5/8) Epoch 10, batch 700, train_loss[loss=3.376, NarTop10Accuracy=0.6509, over 5151.00 frames. ], tot_loss[loss=3.356, NarTop10Accuracy=0.6548, over 5720.88 frames. ], batch size: 6, lr: 8.65e-03
2024-08-06 16:31:09,842 INFO [trainer.py:765] (5/8) Epoch 10, batch 800, train_loss[loss=3.441, NarTop10Accuracy=0.6308, over 5145.00 frames. ], tot_loss[loss=3.361, NarTop10Accuracy=0.6537, over 5790.81 frames. ], batch size: 6, lr: 8.64e-03
2024-08-06 16:31:16,257 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 16:31:24,565 INFO [trainer.py:811] (5/8) Epoch 10, validation: loss=3.184, NarTop10Accuracy=0.6898, over 1905321.00 frames. 
2024-08-06 16:31:24,567 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 16:31:25,154 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 10, batch 900, train_loss[loss=3.132, NarTop10Accuracy=0.6967, over 6744.00 frames. ], tot_loss[loss=3.335, NarTop10Accuracy=0.6588, over 5810.47 frames. ], batch size: 14, lr: 8.62e-03
2024-08-06 16:32:28,589 INFO [trainer.py:765] (5/8) Epoch 10, batch 1000, train_loss[loss=3.092, NarTop10Accuracy=0.7111, over 6189.00 frames. ], tot_loss[loss=3.339, NarTop10Accuracy=0.6579, over 5906.91 frames. ], batch size: 13, lr: 8.60e-03
2024-08-06 16:33:06,376 INFO [trainer.py:765] (5/8) Epoch 10, batch 1100, train_loss[loss=3.016, NarTop10Accuracy=0.7252, over 7038.00 frames. ], tot_loss[loss=3.344, NarTop10Accuracy=0.6571, over 5941.33 frames. ], batch size: 17, lr: 8.59e-03
2024-08-06 16:33:40,960 INFO [trainer.py:765] (5/8) Epoch 10, batch 1200, train_loss[loss=3.265, NarTop10Accuracy=0.6698, over 7317.00 frames. ], tot_loss[loss=3.339, NarTop10Accuracy=0.6585, over 5937.29 frames. ], batch size: 31, lr: 8.57e-03
2024-08-06 16:34:16,170 INFO [trainer.py:765] (5/8) Epoch 10, batch 1300, train_loss[loss=3.289, NarTop10Accuracy=0.6664, over 4947.00 frames. ], tot_loss[loss=3.339, NarTop10Accuracy=0.6583, over 5997.20 frames. ], batch size: 6, lr: 8.55e-03
2024-08-06 16:34:51,200 INFO [trainer.py:765] (5/8) Epoch 10, batch 1400, train_loss[loss=3.285, NarTop10Accuracy=0.6615, over 6048.00 frames. ], tot_loss[loss=3.36, NarTop10Accuracy=0.6532, over 6016.40 frames. ], batch size: 11, lr: 8.54e-03
2024-08-06 16:35:22,159 INFO [trainer.py:765] (5/8) Epoch 10, batch 1500, train_loss[loss=3.64, NarTop10Accuracy=0.5889, over 6132.00 frames. ], tot_loss[loss=3.339, NarTop10Accuracy=0.6577, over 5965.66 frames. ], batch size: 50, lr: 8.52e-03
2024-08-06 16:35:50,136 INFO [trainer.py:765] (5/8) Epoch 10, batch 1600, train_loss[loss=3.591, NarTop10Accuracy=0.6055, over 6987.00 frames. ], tot_loss[loss=3.33, NarTop10Accuracy=0.6597, over 5954.49 frames. ], batch size: 22, lr: 8.50e-03
2024-08-06 16:36:16,976 INFO [trainer.py:765] (5/8) Epoch 10, batch 1700, train_loss[loss=3.369, NarTop10Accuracy=0.6433, over 6516.00 frames. ], tot_loss[loss=3.34, NarTop10Accuracy=0.6576, over 5947.18 frames. ], batch size: 14, lr: 8.49e-03
2024-08-06 16:36:43,647 INFO [trainer.py:765] (5/8) Epoch 10, batch 1800, train_loss[loss=3.105, NarTop10Accuracy=0.7062, over 7146.00 frames. ], tot_loss[loss=3.325, NarTop10Accuracy=0.6606, over 5997.29 frames. ], batch size: 22, lr: 8.47e-03
2024-08-06 16:37:10,290 INFO [trainer.py:765] (5/8) Epoch 10, batch 1900, train_loss[loss=3.226, NarTop10Accuracy=0.6885, over 6348.00 frames. ], tot_loss[loss=3.327, NarTop10Accuracy=0.6607, over 6030.85 frames. ], batch size: 54, lr: 8.45e-03
2024-08-06 16:37:36,089 INFO [trainer.py:765] (5/8) Epoch 10, batch 2000, train_loss[loss=3.192, NarTop10Accuracy=0.6881, over 6033.00 frames. ], tot_loss[loss=3.326, NarTop10Accuracy=0.6607, over 6003.77 frames. ], batch size: 50, lr: 8.44e-03
2024-08-06 16:38:01,650 INFO [trainer.py:765] (5/8) Epoch 10, batch 2100, train_loss[loss=3.326, NarTop10Accuracy=0.654, over 3900.00 frames. ], tot_loss[loss=3.336, NarTop10Accuracy=0.6585, over 5986.78 frames. ], batch size: 4, lr: 8.42e-03
2024-08-06 16:38:27,120 INFO [trainer.py:765] (5/8) Epoch 10, batch 2200, train_loss[loss=3.772, NarTop10Accuracy=0.5693, over 7551.00 frames. ], tot_loss[loss=3.337, NarTop10Accuracy=0.6579, over 6031.34 frames. ], batch size: 32, lr: 8.41e-03
2024-08-06 16:38:52,447 INFO [trainer.py:765] (5/8) Epoch 10, batch 2300, train_loss[loss=2.99, NarTop10Accuracy=0.7258, over 5673.00 frames. ], tot_loss[loss=3.344, NarTop10Accuracy=0.6568, over 6033.10 frames. ], batch size: 9, lr: 8.39e-03
2024-08-06 16:39:17,006 INFO [trainer.py:765] (5/8) Epoch 10, batch 2400, train_loss[loss=3.232, NarTop10Accuracy=0.6785, over 5115.00 frames. ], tot_loss[loss=3.32, NarTop10Accuracy=0.6617, over 5781.19 frames. ], batch size: 7, lr: 8.37e-03
2024-08-06 16:39:40,801 INFO [trainer.py:765] (5/8) Epoch 10, batch 2500, train_loss[loss=3.596, NarTop10Accuracy=0.6048, over 5088.00 frames. ], tot_loss[loss=3.295, NarTop10Accuracy=0.6664, over 5486.70 frames. ], batch size: 7, lr: 8.36e-03
2024-08-06 16:40:00,798 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 16:41:06,234 INFO [trainer.py:765] (5/8) Epoch 11, batch 100, train_loss[loss=3.581, NarTop10Accuracy=0.6104, over 7158.00 frames. ], tot_loss[loss=3.346, NarTop10Accuracy=0.6563, over 2357.39 frames. ], batch size: 31, lr: 7.97e-03
2024-08-06 16:41:39,021 INFO [trainer.py:765] (5/8) Epoch 11, batch 200, train_loss[loss=3.739, NarTop10Accuracy=0.5795, over 6750.00 frames. ], tot_loss[loss=3.329, NarTop10Accuracy=0.6599, over 3863.27 frames. ], batch size: 17, lr: 7.95e-03
2024-08-06 16:41:53,190 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 16:42:01,355 INFO [trainer.py:811] (5/8) Epoch 11, validation: loss=3.116, NarTop10Accuracy=0.7034, over 1905321.00 frames. 
2024-08-06 16:42:01,356 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 16:42:01,879 INFO [optim.py:386] (5/8) Clipping_scale=2.0, grad-norm quartiles 1.526e+02 1.889e+02 2.046e+02 2.249e+02 5.417e+02, threshold=4.093e+02, percent-clipped=0.2
2024-08-06 16:42:17,975 INFO [trainer.py:765] (5/8) Epoch 11, batch 300, train_loss[loss=3.054, NarTop10Accuracy=0.7164, over 7341.00 frames. ], tot_loss[loss=3.309, NarTop10Accuracy=0.6642, over 4659.80 frames. ], batch size: 23, lr: 7.94e-03
2024-08-06 16:42:55,153 INFO [trainer.py:765] (5/8) Epoch 11, batch 400, train_loss[loss=3.281, NarTop10Accuracy=0.6712, over 5127.00 frames. ], tot_loss[loss=3.299, NarTop10Accuracy=0.6662, over 5102.15 frames. ], batch size: 7, lr: 7.92e-03
2024-08-06 16:43:25,718 INFO [trainer.py:765] (5/8) Epoch 11, batch 500, train_loss[loss=3.057, NarTop10Accuracy=0.7115, over 6135.00 frames. ], tot_loss[loss=3.287, NarTop10Accuracy=0.6686, over 5364.32 frames. ], batch size: 11, lr: 7.91e-03
2024-08-06 16:44:02,242 INFO [trainer.py:765] (5/8) Epoch 11, batch 600, train_loss[loss=3.425, NarTop10Accuracy=0.6264, over 5733.00 frames. ], tot_loss[loss=3.3, NarTop10Accuracy=0.6657, over 5632.12 frames. ], batch size: 9, lr: 7.89e-03
2024-08-06 16:44:35,716 INFO [trainer.py:765] (5/8) Epoch 11, batch 700, train_loss[loss=3.625, NarTop10Accuracy=0.5943, over 4887.00 frames. ], tot_loss[loss=3.294, NarTop10Accuracy=0.667, over 5695.69 frames. ], batch size: 6, lr: 7.88e-03
2024-08-06 16:45:10,468 INFO [trainer.py:765] (5/8) Epoch 11, batch 800, train_loss[loss=3.055, NarTop10Accuracy=0.7163, over 4407.00 frames. ], tot_loss[loss=3.311, NarTop10Accuracy=0.6633, over 5750.83 frames. ], batch size: 5, lr: 7.86e-03
2024-08-06 16:45:46,457 INFO [trainer.py:765] (5/8) Epoch 11, batch 900, train_loss[loss=3.671, NarTop10Accuracy=0.5875, over 6195.00 frames. ], tot_loss[loss=3.299, NarTop10Accuracy=0.6659, over 5788.01 frames. ], batch size: 13, lr: 7.85e-03
2024-08-06 16:46:20,311 INFO [trainer.py:765] (5/8) Epoch 11, batch 1000, train_loss[loss=3.273, NarTop10Accuracy=0.6665, over 6216.00 frames. ], tot_loss[loss=3.303, NarTop10Accuracy=0.665, over 5894.65 frames. ], batch size: 13, lr: 7.84e-03
2024-08-06 16:46:53,456 INFO [trainer.py:765] (5/8) Epoch 11, batch 1100, train_loss[loss=2.997, NarTop10Accuracy=0.7235, over 6810.00 frames. ], tot_loss[loss=3.294, NarTop10Accuracy=0.667, over 5929.68 frames. ], batch size: 17, lr: 7.82e-03
2024-08-06 16:47:33,030 INFO [trainer.py:765] (5/8) Epoch 11, batch 1200, train_loss[loss=3.503, NarTop10Accuracy=0.6257, over 7275.00 frames. ], tot_loss[loss=3.304, NarTop10Accuracy=0.6645, over 5930.75 frames. ], batch size: 31, lr: 7.81e-03
2024-08-06 16:48:06,481 INFO [trainer.py:765] (5/8) Epoch 11, batch 1300, train_loss[loss=2.929, NarTop10Accuracy=0.7378, over 5061.00 frames. ], tot_loss[loss=3.311, NarTop10Accuracy=0.6628, over 5988.60 frames. ], batch size: 6, lr: 7.79e-03
2024-08-06 16:48:41,353 INFO [trainer.py:765] (5/8) Epoch 11, batch 1400, train_loss[loss=3.552, NarTop10Accuracy=0.6112, over 6138.00 frames. ], tot_loss[loss=3.327, NarTop10Accuracy=0.6599, over 6011.25 frames. ], batch size: 11, lr: 7.78e-03
2024-08-06 16:49:09,344 INFO [trainer.py:765] (5/8) Epoch 11, batch 1500, train_loss[loss=3.333, NarTop10Accuracy=0.6525, over 6117.00 frames. ], tot_loss[loss=3.328, NarTop10Accuracy=0.6598, over 5941.29 frames. ], batch size: 54, lr: 7.77e-03
2024-08-06 16:49:37,103 INFO [trainer.py:765] (5/8) Epoch 11, batch 1600, train_loss[loss=3.213, NarTop10Accuracy=0.6804, over 7023.00 frames. ], tot_loss[loss=3.311, NarTop10Accuracy=0.6633, over 5936.34 frames. ], batch size: 22, lr: 7.75e-03
2024-08-06 16:50:03,791 INFO [trainer.py:765] (5/8) Epoch 11, batch 1700, train_loss[loss=3.377, NarTop10Accuracy=0.6469, over 6570.00 frames. ], tot_loss[loss=3.306, NarTop10Accuracy=0.6645, over 5937.01 frames. ], batch size: 14, lr: 7.74e-03
2024-08-06 16:50:30,353 INFO [trainer.py:765] (5/8) Epoch 11, batch 1800, train_loss[loss=3.516, NarTop10Accuracy=0.6166, over 6939.00 frames. ], tot_loss[loss=3.319, NarTop10Accuracy=0.6615, over 6004.15 frames. ], batch size: 22, lr: 7.72e-03
2024-08-06 16:50:56,821 INFO [trainer.py:765] (5/8) Epoch 11, batch 1900, train_loss[loss=3.804, NarTop10Accuracy=0.5672, over 6165.00 frames. ], tot_loss[loss=3.331, NarTop10Accuracy=0.6593, over 6037.58 frames. ], batch size: 51, lr: 7.71e-03
2024-08-06 16:51:22,404 INFO [trainer.py:765] (5/8) Epoch 11, batch 2000, train_loss[loss=3.818, NarTop10Accuracy=0.5528, over 6120.00 frames. ], tot_loss[loss=3.326, NarTop10Accuracy=0.6604, over 6007.11 frames. ], batch size: 51, lr: 7.70e-03
2024-08-06 16:51:47,794 INFO [trainer.py:765] (5/8) Epoch 11, batch 2100, train_loss[loss=2.892, NarTop10Accuracy=0.7541, over 4821.00 frames. ], tot_loss[loss=3.314, NarTop10Accuracy=0.6631, over 5983.55 frames. ], batch size: 5, lr: 7.68e-03
2024-08-06 16:52:13,118 INFO [trainer.py:765] (5/8) Epoch 11, batch 2200, train_loss[loss=3.288, NarTop10Accuracy=0.6693, over 7335.00 frames. ], tot_loss[loss=3.307, NarTop10Accuracy=0.6641, over 6020.04 frames. ], batch size: 31, lr: 7.67e-03
2024-08-06 16:52:23,899 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 16:52:32,079 INFO [trainer.py:811] (5/8) Epoch 11, validation: loss=3.101, NarTop10Accuracy=0.7058, over 1905321.00 frames. 
2024-08-06 16:52:32,080 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 16:52:32,593 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 11, batch 2300, train_loss[loss=3.383, NarTop10Accuracy=0.6463, over 5802.00 frames. ], tot_loss[loss=3.315, NarTop10Accuracy=0.6627, over 6022.88 frames. ], batch size: 9, lr: 7.66e-03
2024-08-06 16:53:10,887 INFO [trainer.py:765] (5/8) Epoch 11, batch 2400, train_loss[loss=3.377, NarTop10Accuracy=0.6461, over 5118.00 frames. ], tot_loss[loss=3.305, NarTop10Accuracy=0.6648, over 5771.68 frames. ], batch size: 7, lr: 7.64e-03
2024-08-06 16:53:34,372 INFO [trainer.py:765] (5/8) Epoch 11, batch 2500, train_loss[loss=3.716, NarTop10Accuracy=0.5846, over 5289.00 frames. ], tot_loss[loss=3.303, NarTop10Accuracy=0.6645, over 5482.27 frames. ], batch size: 7, lr: 7.63e-03
2024-08-06 16:53:54,102 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 16:54:58,525 INFO [trainer.py:765] (5/8) Epoch 12, batch 100, train_loss[loss=3.692, NarTop10Accuracy=0.5869, over 7077.00 frames. ], tot_loss[loss=3.304, NarTop10Accuracy=0.665, over 2346.08 frames. ], batch size: 31, lr: 7.30e-03
2024-08-06 16:55:32,432 INFO [trainer.py:765] (5/8) Epoch 12, batch 200, train_loss[loss=3.04, NarTop10Accuracy=0.7236, over 6918.00 frames. ], tot_loss[loss=3.272, NarTop10Accuracy=0.6713, over 3843.81 frames. ], batch size: 17, lr: 7.29e-03
2024-08-06 16:56:05,096 INFO [trainer.py:765] (5/8) Epoch 12, batch 300, train_loss[loss=3.025, NarTop10Accuracy=0.7197, over 7005.00 frames. ], tot_loss[loss=3.243, NarTop10Accuracy=0.6772, over 4652.89 frames. ], batch size: 22, lr: 7.27e-03
2024-08-06 16:56:36,426 INFO [trainer.py:765] (5/8) Epoch 12, batch 400, train_loss[loss=3, NarTop10Accuracy=0.7239, over 5103.00 frames. ], tot_loss[loss=3.253, NarTop10Accuracy=0.6753, over 5108.30 frames. ], batch size: 7, lr: 7.26e-03
2024-08-06 16:57:10,503 INFO [trainer.py:765] (5/8) Epoch 12, batch 500, train_loss[loss=3.608, NarTop10Accuracy=0.6055, over 5982.00 frames. ], tot_loss[loss=3.27, NarTop10Accuracy=0.672, over 5388.12 frames. ], batch size: 11, lr: 7.25e-03
2024-08-06 16:57:45,483 INFO [trainer.py:765] (5/8) Epoch 12, batch 600, train_loss[loss=2.913, NarTop10Accuracy=0.7404, over 5820.00 frames. ], tot_loss[loss=3.271, NarTop10Accuracy=0.6716, over 5645.21 frames. ], batch size: 9, lr: 7.24e-03
2024-08-06 16:58:17,004 INFO [trainer.py:765] (5/8) Epoch 12, batch 700, train_loss[loss=3.465, NarTop10Accuracy=0.6421, over 5010.00 frames. ], tot_loss[loss=3.281, NarTop10Accuracy=0.6698, over 5712.68 frames. ], batch size: 6, lr: 7.22e-03
2024-08-06 16:58:53,469 INFO [trainer.py:765] (5/8) Epoch 12, batch 800, train_loss[loss=3.16, NarTop10Accuracy=0.6809, over 5214.00 frames. ], tot_loss[loss=3.287, NarTop10Accuracy=0.6683, over 5762.34 frames. ], batch size: 6, lr: 7.21e-03
2024-08-06 16:59:27,205 INFO [trainer.py:765] (5/8) Epoch 12, batch 900, train_loss[loss=2.887, NarTop10Accuracy=0.748, over 6291.00 frames. ], tot_loss[loss=3.27, NarTop10Accuracy=0.6719, over 5782.64 frames. ], batch size: 13, lr: 7.20e-03
2024-08-06 17:00:01,574 INFO [trainer.py:765] (5/8) Epoch 12, batch 1000, train_loss[loss=2.911, NarTop10Accuracy=0.7446, over 6534.00 frames. ], tot_loss[loss=3.282, NarTop10Accuracy=0.6692, over 5883.56 frames. ], batch size: 14, lr: 7.19e-03
2024-08-06 17:00:39,188 INFO [trainer.py:765] (5/8) Epoch 12, batch 1100, train_loss[loss=3.749, NarTop10Accuracy=0.5781, over 6777.00 frames. ], tot_loss[loss=3.3, NarTop10Accuracy=0.6656, over 5929.52 frames. ], batch size: 17, lr: 7.18e-03
2024-08-06 17:01:13,964 INFO [trainer.py:765] (5/8) Epoch 12, batch 1200, train_loss[loss=3.077, NarTop10Accuracy=0.7133, over 7263.00 frames. ], tot_loss[loss=3.269, NarTop10Accuracy=0.6721, over 5920.74 frames. ], batch size: 31, lr: 7.17e-03
2024-08-06 17:01:48,107 INFO [trainer.py:765] (5/8) Epoch 12, batch 1300, train_loss[loss=3.155, NarTop10Accuracy=0.6896, over 4881.00 frames. ], tot_loss[loss=3.281, NarTop10Accuracy=0.6698, over 5989.30 frames. ], batch size: 6, lr: 7.15e-03
2024-08-06 17:02:22,323 INFO [trainer.py:765] (5/8) Epoch 12, batch 1400, train_loss[loss=3.587, NarTop10Accuracy=0.5999, over 6159.00 frames. ], tot_loss[loss=3.289, NarTop10Accuracy=0.668, over 5988.69 frames. ], batch size: 11, lr: 7.14e-03
2024-08-06 17:02:52,877 INFO [trainer.py:765] (5/8) Epoch 12, batch 1500, train_loss[loss=3.363, NarTop10Accuracy=0.6597, over 5946.00 frames. ], tot_loss[loss=3.272, NarTop10Accuracy=0.6714, over 5936.17 frames. ], batch size: 50, lr: 7.13e-03
2024-08-06 17:03:20,691 INFO [trainer.py:765] (5/8) Epoch 12, batch 1600, train_loss[loss=3.198, NarTop10Accuracy=0.6876, over 7080.00 frames. ], tot_loss[loss=3.281, NarTop10Accuracy=0.6694, over 5926.42 frames. ], batch size: 22, lr: 7.12e-03
2024-08-06 17:03:38,296 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 17:03:46,474 INFO [trainer.py:811] (5/8) Epoch 12, validation: loss=3.054, NarTop10Accuracy=0.7153, over 1905321.00 frames. 
2024-08-06 17:03:46,474 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 17:03:46,988 INFO [optim.py:386] (5/8) Clipping_scale=2.0, grad-norm quartiles 1.507e+02 1.899e+02 2.078e+02 2.276e+02 5.455e+02, threshold=4.157e+02, percent-clipped=0.1
2024-08-06 17:03:55,602 INFO [trainer.py:765] (5/8) Epoch 12, batch 1700, train_loss[loss=3.402, NarTop10Accuracy=0.657, over 6681.00 frames. ], tot_loss[loss=3.289, NarTop10Accuracy=0.6683, over 5922.08 frames. ], batch size: 14, lr: 7.11e-03
2024-08-06 17:04:22,120 INFO [trainer.py:765] (5/8) Epoch 12, batch 1800, train_loss[loss=3.604, NarTop10Accuracy=0.6036, over 7464.00 frames. ], tot_loss[loss=3.291, NarTop10Accuracy=0.6677, over 5986.03 frames. ], batch size: 23, lr: 7.10e-03
2024-08-06 17:04:48,590 INFO [trainer.py:765] (5/8) Epoch 12, batch 1900, train_loss[loss=3.28, NarTop10Accuracy=0.6743, over 5520.00 frames. ], tot_loss[loss=3.285, NarTop10Accuracy=0.6688, over 6023.28 frames. ], batch size: 50, lr: 7.08e-03
2024-08-06 17:05:14,197 INFO [trainer.py:765] (5/8) Epoch 12, batch 2000, train_loss[loss=3.56, NarTop10Accuracy=0.6084, over 5886.00 frames. ], tot_loss[loss=3.27, NarTop10Accuracy=0.672, over 5999.20 frames. ], batch size: 50, lr: 7.07e-03
2024-08-06 17:05:39,467 INFO [trainer.py:765] (5/8) Epoch 12, batch 2100, train_loss[loss=3.286, NarTop10Accuracy=0.6727, over 3897.00 frames. ], tot_loss[loss=3.285, NarTop10Accuracy=0.6689, over 5973.80 frames. ], batch size: 4, lr: 7.06e-03
2024-08-06 17:06:04,690 INFO [trainer.py:765] (5/8) Epoch 12, batch 2200, train_loss[loss=3.503, NarTop10Accuracy=0.6242, over 7311.00 frames. ], tot_loss[loss=3.299, NarTop10Accuracy=0.6664, over 6014.44 frames. ], batch size: 31, lr: 7.05e-03
2024-08-06 17:06:29,846 INFO [trainer.py:765] (5/8) Epoch 12, batch 2300, train_loss[loss=3.498, NarTop10Accuracy=0.6351, over 5760.00 frames. ], tot_loss[loss=3.292, NarTop10Accuracy=0.6675, over 6020.49 frames. ], batch size: 9, lr: 7.04e-03
2024-08-06 17:06:54,199 INFO [trainer.py:765] (5/8) Epoch 12, batch 2400, train_loss[loss=3.122, NarTop10Accuracy=0.6957, over 5190.00 frames. ], tot_loss[loss=3.276, NarTop10Accuracy=0.6704, over 5769.87 frames. ], batch size: 7, lr: 7.03e-03
2024-08-06 17:07:17,645 INFO [trainer.py:765] (5/8) Epoch 12, batch 2500, train_loss[loss=3.192, NarTop10Accuracy=0.6886, over 5898.00 frames. ], tot_loss[loss=3.255, NarTop10Accuracy=0.6744, over 5464.10 frames. ], batch size: 8, lr: 7.02e-03
2024-08-06 17:07:37,434 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 17:08:40,078 INFO [trainer.py:765] (5/8) Epoch 13, batch 100, train_loss[loss=2.983, NarTop10Accuracy=0.729, over 7239.00 frames. ], tot_loss[loss=3.275, NarTop10Accuracy=0.6703, over 2377.72 frames. ], batch size: 31, lr: 6.73e-03
2024-08-06 17:09:14,119 INFO [trainer.py:765] (5/8) Epoch 13, batch 200, train_loss[loss=2.897, NarTop10Accuracy=0.7428, over 6768.00 frames. ], tot_loss[loss=3.28, NarTop10Accuracy=0.6703, over 3859.95 frames. ], batch size: 17, lr: 6.72e-03
2024-08-06 17:09:46,276 INFO [trainer.py:765] (5/8) Epoch 13, batch 300, train_loss[loss=3.589, NarTop10Accuracy=0.6069, over 7251.00 frames. ], tot_loss[loss=3.269, NarTop10Accuracy=0.6726, over 4658.90 frames. ], batch size: 23, lr: 6.71e-03
2024-08-06 17:10:19,163 INFO [trainer.py:765] (5/8) Epoch 13, batch 400, train_loss[loss=2.781, NarTop10Accuracy=0.7675, over 5025.00 frames. ], tot_loss[loss=3.254, NarTop10Accuracy=0.6756, over 5091.94 frames. ], batch size: 7, lr: 6.70e-03
2024-08-06 17:10:49,334 INFO [trainer.py:765] (5/8) Epoch 13, batch 500, train_loss[loss=3.058, NarTop10Accuracy=0.7203, over 6183.00 frames. ], tot_loss[loss=3.236, NarTop10Accuracy=0.6789, over 5383.27 frames. ], batch size: 11, lr: 6.69e-03
2024-08-06 17:11:26,244 INFO [trainer.py:765] (5/8) Epoch 13, batch 600, train_loss[loss=3.046, NarTop10Accuracy=0.718, over 5763.00 frames. ], tot_loss[loss=3.231, NarTop10Accuracy=0.6798, over 5644.67 frames. ], batch size: 9, lr: 6.68e-03
2024-08-06 17:11:57,381 INFO [trainer.py:765] (5/8) Epoch 13, batch 700, train_loss[loss=3.117, NarTop10Accuracy=0.7002, over 5193.00 frames. ], tot_loss[loss=3.232, NarTop10Accuracy=0.6796, over 5717.75 frames. ], batch size: 6, lr: 6.67e-03
2024-08-06 17:12:33,441 INFO [trainer.py:765] (5/8) Epoch 13, batch 800, train_loss[loss=3.048, NarTop10Accuracy=0.7111, over 5142.00 frames. ], tot_loss[loss=3.242, NarTop10Accuracy=0.6774, over 5789.91 frames. ], batch size: 6, lr: 6.66e-03
2024-08-06 17:13:10,031 INFO [trainer.py:765] (5/8) Epoch 13, batch 900, train_loss[loss=3.212, NarTop10Accuracy=0.6854, over 6273.00 frames. ], tot_loss[loss=3.236, NarTop10Accuracy=0.6789, over 5807.37 frames. ], batch size: 13, lr: 6.65e-03
2024-08-06 17:13:41,442 INFO [trainer.py:765] (5/8) Epoch 13, batch 1000, train_loss[loss=3.499, NarTop10Accuracy=0.6188, over 6636.00 frames. ], tot_loss[loss=3.242, NarTop10Accuracy=0.6773, over 5888.38 frames. ], batch size: 14, lr: 6.64e-03
2024-08-06 17:14:15,536 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 17:14:23,644 INFO [trainer.py:811] (5/8) Epoch 13, validation: loss=3.099, NarTop10Accuracy=0.7062, over 1905321.00 frames. 
2024-08-06 17:14:23,645 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 17:14:24,471 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 13, batch 1100, train_loss[loss=3.637, NarTop10Accuracy=0.6007, over 7035.00 frames. ], tot_loss[loss=3.252, NarTop10Accuracy=0.6755, over 5927.60 frames. ], batch size: 18, lr: 6.63e-03
2024-08-06 17:15:03,475 INFO [trainer.py:765] (5/8) Epoch 13, batch 1200, train_loss[loss=3.406, NarTop10Accuracy=0.6414, over 7101.00 frames. ], tot_loss[loss=3.254, NarTop10Accuracy=0.6746, over 5908.38 frames. ], batch size: 31, lr: 6.62e-03
2024-08-06 17:15:35,514 INFO [trainer.py:765] (5/8) Epoch 13, batch 1300, train_loss[loss=3.036, NarTop10Accuracy=0.7268, over 5106.00 frames. ], tot_loss[loss=3.256, NarTop10Accuracy=0.6745, over 5984.26 frames. ], batch size: 6, lr: 6.61e-03
2024-08-06 17:16:11,782 INFO [trainer.py:765] (5/8) Epoch 13, batch 1400, train_loss[loss=3.155, NarTop10Accuracy=0.7044, over 6084.00 frames. ], tot_loss[loss=3.263, NarTop10Accuracy=0.6734, over 6001.96 frames. ], batch size: 11, lr: 6.60e-03
2024-08-06 17:16:39,788 INFO [trainer.py:765] (5/8) Epoch 13, batch 1500, train_loss[loss=3.501, NarTop10Accuracy=0.6265, over 6363.00 frames. ], tot_loss[loss=3.264, NarTop10Accuracy=0.6732, over 5953.67 frames. ], batch size: 52, lr: 6.59e-03
2024-08-06 17:17:07,603 INFO [trainer.py:765] (5/8) Epoch 13, batch 1600, train_loss[loss=2.956, NarTop10Accuracy=0.7404, over 6888.00 frames. ], tot_loss[loss=3.266, NarTop10Accuracy=0.6725, over 5948.03 frames. ], batch size: 22, lr: 6.58e-03
2024-08-06 17:17:34,259 INFO [trainer.py:765] (5/8) Epoch 13, batch 1700, train_loss[loss=3.217, NarTop10Accuracy=0.6824, over 6072.00 frames. ], tot_loss[loss=3.264, NarTop10Accuracy=0.673, over 5918.26 frames. ], batch size: 13, lr: 6.57e-03
2024-08-06 17:18:00,762 INFO [trainer.py:765] (5/8) Epoch 13, batch 1800, train_loss[loss=3.09, NarTop10Accuracy=0.7055, over 7029.00 frames. ], tot_loss[loss=3.26, NarTop10Accuracy=0.6738, over 5971.77 frames. ], batch size: 22, lr: 6.56e-03
2024-08-06 17:18:27,244 INFO [trainer.py:765] (5/8) Epoch 13, batch 1900, train_loss[loss=3.545, NarTop10Accuracy=0.6203, over 6315.00 frames. ], tot_loss[loss=3.252, NarTop10Accuracy=0.6758, over 6025.41 frames. ], batch size: 51, lr: 6.55e-03
2024-08-06 17:18:52,777 INFO [trainer.py:765] (5/8) Epoch 13, batch 2000, train_loss[loss=3.555, NarTop10Accuracy=0.6155, over 6000.00 frames. ], tot_loss[loss=3.24, NarTop10Accuracy=0.6785, over 6005.49 frames. ], batch size: 50, lr: 6.54e-03
2024-08-06 17:19:18,148 INFO [trainer.py:765] (5/8) Epoch 13, batch 2100, train_loss[loss=2.945, NarTop10Accuracy=0.7444, over 4944.00 frames. ], tot_loss[loss=3.238, NarTop10Accuracy=0.6785, over 5969.33 frames. ], batch size: 5, lr: 6.53e-03
2024-08-06 17:19:43,412 INFO [trainer.py:765] (5/8) Epoch 13, batch 2200, train_loss[loss=3.409, NarTop10Accuracy=0.6374, over 7293.00 frames. ], tot_loss[loss=3.249, NarTop10Accuracy=0.6763, over 5998.74 frames. ], batch size: 31, lr: 6.52e-03
2024-08-06 17:20:08,543 INFO [trainer.py:765] (5/8) Epoch 13, batch 2300, train_loss[loss=3.529, NarTop10Accuracy=0.6276, over 5688.00 frames. ], tot_loss[loss=3.271, NarTop10Accuracy=0.6719, over 6005.59 frames. ], batch size: 9, lr: 6.51e-03
2024-08-06 17:20:32,939 INFO [trainer.py:765] (5/8) Epoch 13, batch 2400, train_loss[loss=3.411, NarTop10Accuracy=0.6389, over 5136.00 frames. ], tot_loss[loss=3.24, NarTop10Accuracy=0.6776, over 5756.71 frames. ], batch size: 7, lr: 6.50e-03
2024-08-06 17:20:56,408 INFO [trainer.py:765] (5/8) Epoch 13, batch 2500, train_loss[loss=3.649, NarTop10Accuracy=0.5924, over 5010.00 frames. ], tot_loss[loss=3.229, NarTop10Accuracy=0.6798, over 5471.97 frames. ], batch size: 7, lr: 6.49e-03
2024-08-06 17:21:16,065 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 17:22:19,315 INFO [trainer.py:765] (5/8) Epoch 14, batch 100, train_loss[loss=3.012, NarTop10Accuracy=0.7184, over 7461.00 frames. ], tot_loss[loss=3.224, NarTop10Accuracy=0.6821, over 2361.94 frames. ], batch size: 32, lr: 6.24e-03
2024-08-06 17:22:50,379 INFO [trainer.py:765] (5/8) Epoch 14, batch 200, train_loss[loss=3.287, NarTop10Accuracy=0.6659, over 6879.00 frames. ], tot_loss[loss=3.233, NarTop10Accuracy=0.6795, over 3860.09 frames. ], batch size: 17, lr: 6.23e-03
2024-08-06 17:23:23,879 INFO [trainer.py:765] (5/8) Epoch 14, batch 300, train_loss[loss=3.135, NarTop10Accuracy=0.7049, over 7221.00 frames. ], tot_loss[loss=3.212, NarTop10Accuracy=0.6839, over 4654.94 frames. ], batch size: 22, lr: 6.22e-03
2024-08-06 17:23:57,484 INFO [trainer.py:765] (5/8) Epoch 14, batch 400, train_loss[loss=3.196, NarTop10Accuracy=0.6939, over 5103.00 frames. ], tot_loss[loss=3.228, NarTop10Accuracy=0.6806, over 5100.86 frames. ], batch size: 7, lr: 6.22e-03
2024-08-06 17:24:32,113 INFO [trainer.py:765] (5/8) Epoch 14, batch 500, train_loss[loss=3.287, NarTop10Accuracy=0.665, over 6033.00 frames. ], tot_loss[loss=3.239, NarTop10Accuracy=0.6781, over 5373.89 frames. ], batch size: 11, lr: 6.21e-03
2024-08-06 17:24:36,213 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 17:24:44,275 INFO [trainer.py:811] (5/8) Epoch 14, validation: loss=3.004, NarTop10Accuracy=0.726, over 1905321.00 frames. 
2024-08-06 17:24:44,275 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 17:24:44,822 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 14, batch 600, train_loss[loss=2.897, NarTop10Accuracy=0.7581, over 5718.00 frames. ], tot_loss[loss=3.238, NarTop10Accuracy=0.6784, over 5647.08 frames. ], batch size: 9, lr: 6.20e-03
2024-08-06 17:25:48,547 INFO [trainer.py:765] (5/8) Epoch 14, batch 700, train_loss[loss=3.403, NarTop10Accuracy=0.6476, over 4911.00 frames. ], tot_loss[loss=3.23, NarTop10Accuracy=0.6798, over 5723.86 frames. ], batch size: 6, lr: 6.19e-03
2024-08-06 17:26:25,279 INFO [trainer.py:765] (5/8) Epoch 14, batch 800, train_loss[loss=2.997, NarTop10Accuracy=0.7342, over 4191.00 frames. ], tot_loss[loss=3.214, NarTop10Accuracy=0.6835, over 5775.66 frames. ], batch size: 5, lr: 6.18e-03
2024-08-06 17:26:57,658 INFO [trainer.py:765] (5/8) Epoch 14, batch 900, train_loss[loss=3.156, NarTop10Accuracy=0.6872, over 6291.00 frames. ], tot_loss[loss=3.205, NarTop10Accuracy=0.6847, over 5788.67 frames. ], batch size: 13, lr: 6.17e-03
2024-08-06 17:27:31,716 INFO [trainer.py:765] (5/8) Epoch 14, batch 1000, train_loss[loss=3.449, NarTop10Accuracy=0.6271, over 6348.00 frames. ], tot_loss[loss=3.219, NarTop10Accuracy=0.6818, over 5894.46 frames. ], batch size: 13, lr: 6.16e-03
2024-08-06 17:28:11,596 INFO [trainer.py:765] (5/8) Epoch 14, batch 1100, train_loss[loss=3.034, NarTop10Accuracy=0.7222, over 6735.00 frames. ], tot_loss[loss=3.219, NarTop10Accuracy=0.6818, over 5928.11 frames. ], batch size: 17, lr: 6.15e-03
2024-08-06 17:28:40,733 INFO [trainer.py:765] (5/8) Epoch 14, batch 1200, train_loss[loss=3.575, NarTop10Accuracy=0.6112, over 7104.00 frames. ], tot_loss[loss=3.219, NarTop10Accuracy=0.682, over 5906.11 frames. ], batch size: 31, lr: 6.15e-03
2024-08-06 17:29:16,214 INFO [trainer.py:765] (5/8) Epoch 14, batch 1300, train_loss[loss=3.587, NarTop10Accuracy=0.6, over 5085.00 frames. ], tot_loss[loss=3.219, NarTop10Accuracy=0.682, over 5977.89 frames. ], batch size: 6, lr: 6.14e-03
2024-08-06 17:29:54,601 INFO [trainer.py:765] (5/8) Epoch 14, batch 1400, train_loss[loss=3.36, NarTop10Accuracy=0.664, over 6084.00 frames. ], tot_loss[loss=3.231, NarTop10Accuracy=0.6798, over 6005.92 frames. ], batch size: 11, lr: 6.13e-03
2024-08-06 17:30:25,315 INFO [trainer.py:765] (5/8) Epoch 14, batch 1500, train_loss[loss=3.713, NarTop10Accuracy=0.5763, over 6243.00 frames. ], tot_loss[loss=3.241, NarTop10Accuracy=0.6781, over 5949.08 frames. ], batch size: 51, lr: 6.12e-03
2024-08-06 17:30:53,043 INFO [trainer.py:765] (5/8) Epoch 14, batch 1600, train_loss[loss=3.002, NarTop10Accuracy=0.7274, over 7149.00 frames. ], tot_loss[loss=3.232, NarTop10Accuracy=0.6799, over 5928.71 frames. ], batch size: 22, lr: 6.11e-03
2024-08-06 17:31:19,728 INFO [trainer.py:765] (5/8) Epoch 14, batch 1700, train_loss[loss=3.066, NarTop10Accuracy=0.7146, over 6171.00 frames. ], tot_loss[loss=3.211, NarTop10Accuracy=0.6841, over 5916.63 frames. ], batch size: 13, lr: 6.10e-03
2024-08-06 17:31:46,289 INFO [trainer.py:765] (5/8) Epoch 14, batch 1800, train_loss[loss=3.083, NarTop10Accuracy=0.711, over 7131.00 frames. ], tot_loss[loss=3.189, NarTop10Accuracy=0.6886, over 5979.14 frames. ], batch size: 22, lr: 6.09e-03
2024-08-06 17:32:12,727 INFO [trainer.py:765] (5/8) Epoch 14, batch 1900, train_loss[loss=3.606, NarTop10Accuracy=0.6078, over 6318.00 frames. ], tot_loss[loss=3.209, NarTop10Accuracy=0.6848, over 6022.01 frames. ], batch size: 50, lr: 6.09e-03
2024-08-06 17:32:38,282 INFO [trainer.py:765] (5/8) Epoch 14, batch 2000, train_loss[loss=3.215, NarTop10Accuracy=0.6886, over 6108.00 frames. ], tot_loss[loss=3.222, NarTop10Accuracy=0.6822, over 6017.07 frames. ], batch size: 50, lr: 6.08e-03
2024-08-06 17:33:03,646 INFO [trainer.py:765] (5/8) Epoch 14, batch 2100, train_loss[loss=3.085, NarTop10Accuracy=0.7154, over 3957.00 frames. ], tot_loss[loss=3.226, NarTop10Accuracy=0.6813, over 6002.15 frames. ], batch size: 4, lr: 6.07e-03
2024-08-06 17:33:28,998 INFO [trainer.py:765] (5/8) Epoch 14, batch 2200, train_loss[loss=3.324, NarTop10Accuracy=0.6641, over 7350.00 frames. ], tot_loss[loss=3.223, NarTop10Accuracy=0.6816, over 6029.72 frames. ], batch size: 31, lr: 6.06e-03
2024-08-06 17:33:54,087 INFO [trainer.py:765] (5/8) Epoch 14, batch 2300, train_loss[loss=2.899, NarTop10Accuracy=0.7528, over 5733.00 frames. ], tot_loss[loss=3.24, NarTop10Accuracy=0.6783, over 6025.70 frames. ], batch size: 9, lr: 6.05e-03
2024-08-06 17:34:18,534 INFO [trainer.py:765] (5/8) Epoch 14, batch 2400, train_loss[loss=2.895, NarTop10Accuracy=0.7501, over 5097.00 frames. ], tot_loss[loss=3.237, NarTop10Accuracy=0.678, over 5771.52 frames. ], batch size: 7, lr: 6.04e-03
2024-08-06 17:34:42,116 INFO [trainer.py:765] (5/8) Epoch 14, batch 2500, train_loss[loss=3.002, NarTop10Accuracy=0.727, over 5070.00 frames. ], tot_loss[loss=3.203, NarTop10Accuracy=0.6844, over 5480.97 frames. ], batch size: 7, lr: 6.04e-03
2024-08-06 17:34:45,394 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 17:34:53,209 INFO [trainer.py:811] (5/8) Epoch 14, validation: loss=3.062, NarTop10Accuracy=0.7136, over 1905321.00 frames. 
2024-08-06 17:34:53,209 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 17:34:53,679 INFO [optim.py:386] (5/8) 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 17:35:09,737 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 17:36:11,738 INFO [trainer.py:765] (5/8) Epoch 15, batch 100, train_loss[loss=2.998, NarTop10Accuracy=0.7287, over 7224.00 frames. ], tot_loss[loss=3.212, NarTop10Accuracy=0.6838, over 2383.46 frames. ], batch size: 31, lr: 5.82e-03
2024-08-06 17:36:44,334 INFO [trainer.py:765] (5/8) Epoch 15, batch 200, train_loss[loss=3.417, NarTop10Accuracy=0.64, over 6918.00 frames. ], tot_loss[loss=3.191, NarTop10Accuracy=0.6883, over 3854.51 frames. ], batch size: 17, lr: 5.81e-03
2024-08-06 17:37:17,714 INFO [trainer.py:765] (5/8) Epoch 15, batch 300, train_loss[loss=3.193, NarTop10Accuracy=0.6823, over 7053.00 frames. ], tot_loss[loss=3.2, NarTop10Accuracy=0.6861, over 4640.03 frames. ], batch size: 22, lr: 5.80e-03
2024-08-06 17:37:48,903 INFO [trainer.py:765] (5/8) Epoch 15, batch 400, train_loss[loss=2.901, NarTop10Accuracy=0.7318, over 5121.00 frames. ], tot_loss[loss=3.192, NarTop10Accuracy=0.6876, over 5096.25 frames. ], batch size: 7, lr: 5.80e-03
2024-08-06 17:38:22,354 INFO [trainer.py:765] (5/8) Epoch 15, batch 500, train_loss[loss=2.945, NarTop10Accuracy=0.7474, over 6060.00 frames. ], tot_loss[loss=3.191, NarTop10Accuracy=0.6881, over 5380.13 frames. ], batch size: 11, lr: 5.79e-03
2024-08-06 17:38:53,093 INFO [trainer.py:765] (5/8) Epoch 15, batch 600, train_loss[loss=2.791, NarTop10Accuracy=0.7633, over 5694.00 frames. ], tot_loss[loss=3.2, NarTop10Accuracy=0.6858, over 5623.56 frames. ], batch size: 9, lr: 5.78e-03
2024-08-06 17:39:27,921 INFO [trainer.py:765] (5/8) Epoch 15, batch 700, train_loss[loss=2.836, NarTop10Accuracy=0.7611, over 5079.00 frames. ], tot_loss[loss=3.209, NarTop10Accuracy=0.6836, over 5724.95 frames. ], batch size: 6, lr: 5.77e-03
2024-08-06 17:40:05,564 INFO [trainer.py:765] (5/8) Epoch 15, batch 800, train_loss[loss=3.282, NarTop10Accuracy=0.6629, over 5019.00 frames. ], tot_loss[loss=3.235, NarTop10Accuracy=0.6783, over 5787.54 frames. ], batch size: 6, lr: 5.76e-03
2024-08-06 17:40:35,790 INFO [trainer.py:765] (5/8) Epoch 15, batch 900, train_loss[loss=3.386, NarTop10Accuracy=0.6505, over 6450.00 frames. ], tot_loss[loss=3.211, NarTop10Accuracy=0.6836, over 5795.74 frames. ], batch size: 14, lr: 5.76e-03
2024-08-06 17:41:11,250 INFO [trainer.py:765] (5/8) Epoch 15, batch 1000, train_loss[loss=3.281, NarTop10Accuracy=0.6641, over 6606.00 frames. ], tot_loss[loss=3.197, NarTop10Accuracy=0.6862, over 5915.19 frames. ], batch size: 14, lr: 5.75e-03
2024-08-06 17:41:46,451 INFO [trainer.py:765] (5/8) Epoch 15, batch 1100, train_loss[loss=3.198, NarTop10Accuracy=0.6938, over 6729.00 frames. ], tot_loss[loss=3.198, NarTop10Accuracy=0.6864, over 5955.69 frames. ], batch size: 17, lr: 5.74e-03
2024-08-06 17:42:19,455 INFO [trainer.py:765] (5/8) Epoch 15, batch 1200, train_loss[loss=3.253, NarTop10Accuracy=0.6727, over 7116.00 frames. ], tot_loss[loss=3.221, NarTop10Accuracy=0.6816, over 5943.38 frames. ], batch size: 31, lr: 5.73e-03
2024-08-06 17:42:54,427 INFO [trainer.py:765] (5/8) Epoch 15, batch 1300, train_loss[loss=2.939, NarTop10Accuracy=0.7323, over 5085.00 frames. ], tot_loss[loss=3.207, NarTop10Accuracy=0.6843, over 6007.06 frames. ], batch size: 6, lr: 5.73e-03
2024-08-06 17:43:26,607 INFO [trainer.py:765] (5/8) Epoch 15, batch 1400, train_loss[loss=3.432, NarTop10Accuracy=0.6363, over 6159.00 frames. ], tot_loss[loss=3.217, NarTop10Accuracy=0.6821, over 6011.99 frames. ], batch size: 11, lr: 5.72e-03
2024-08-06 17:43:56,558 INFO [trainer.py:765] (5/8) Epoch 15, batch 1500, train_loss[loss=3.186, NarTop10Accuracy=0.7, over 6012.00 frames. ], tot_loss[loss=3.219, NarTop10Accuracy=0.6818, over 5951.66 frames. ], batch size: 51, lr: 5.71e-03
2024-08-06 17:44:24,241 INFO [trainer.py:765] (5/8) Epoch 15, batch 1600, train_loss[loss=3.52, NarTop10Accuracy=0.6172, over 7125.00 frames. ], tot_loss[loss=3.2, NarTop10Accuracy=0.6859, over 5927.62 frames. ], batch size: 22, lr: 5.70e-03
2024-08-06 17:44:50,856 INFO [trainer.py:765] (5/8) Epoch 15, batch 1700, train_loss[loss=3.003, NarTop10Accuracy=0.719, over 6336.00 frames. ], tot_loss[loss=3.194, NarTop10Accuracy=0.6875, over 5917.21 frames. ], batch size: 13, lr: 5.70e-03
2024-08-06 17:45:17,293 INFO [trainer.py:765] (5/8) Epoch 15, batch 1800, train_loss[loss=3.23, NarTop10Accuracy=0.6896, over 6867.00 frames. ], tot_loss[loss=3.192, NarTop10Accuracy=0.6878, over 5970.85 frames. ], batch size: 22, lr: 5.69e-03
2024-08-06 17:45:43,679 INFO [trainer.py:765] (5/8) Epoch 15, batch 1900, train_loss[loss=3.198, NarTop10Accuracy=0.6877, over 5865.00 frames. ], tot_loss[loss=3.218, NarTop10Accuracy=0.6822, over 6012.22 frames. ], batch size: 50, lr: 5.68e-03
2024-08-06 17:45:53,540 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 17:46:01,742 INFO [trainer.py:811] (5/8) Epoch 15, validation: loss=3.006, NarTop10Accuracy=0.725, over 1905321.00 frames. 
2024-08-06 17:46:01,743 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 17:46:02,217 INFO [optim.py:386] (5/8) Clipping_scale=2.0, grad-norm quartiles 1.631e+02 2.004e+02 2.149e+02 2.324e+02 3.721e+02, threshold=4.298e+02, percent-clipped=0.0
2024-08-06 17:46:17,371 INFO [trainer.py:765] (5/8) Epoch 15, batch 2000, train_loss[loss=3.222, NarTop10Accuracy=0.685, over 6678.00 frames. ], tot_loss[loss=3.21, NarTop10Accuracy=0.6839, over 5982.63 frames. ], batch size: 50, lr: 5.67e-03
2024-08-06 17:46:42,773 INFO [trainer.py:765] (5/8) Epoch 15, batch 2100, train_loss[loss=3.167, NarTop10Accuracy=0.6941, over 4959.00 frames. ], tot_loss[loss=3.201, NarTop10Accuracy=0.6857, over 5985.38 frames. ], batch size: 5, lr: 5.67e-03
2024-08-06 17:47:08,033 INFO [trainer.py:765] (5/8) Epoch 15, batch 2200, train_loss[loss=3.052, NarTop10Accuracy=0.7225, over 7215.00 frames. ], tot_loss[loss=3.209, NarTop10Accuracy=0.684, over 6016.28 frames. ], batch size: 31, lr: 5.66e-03
2024-08-06 17:47:33,291 INFO [trainer.py:765] (5/8) Epoch 15, batch 2300, train_loss[loss=3.636, NarTop10Accuracy=0.5961, over 5769.00 frames. ], tot_loss[loss=3.212, NarTop10Accuracy=0.6833, over 6025.19 frames. ], batch size: 9, lr: 5.65e-03
2024-08-06 17:47:57,640 INFO [trainer.py:765] (5/8) Epoch 15, batch 2400, train_loss[loss=3.276, NarTop10Accuracy=0.6705, over 5208.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.6881, over 5775.83 frames. ], batch size: 7, lr: 5.65e-03
2024-08-06 17:48:21,161 INFO [trainer.py:765] (5/8) Epoch 15, batch 2500, train_loss[loss=2.807, NarTop10Accuracy=0.7649, over 5118.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6932, over 5468.24 frames. ], batch size: 7, lr: 5.64e-03
2024-08-06 17:48:40,519 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 17:49:41,221 INFO [trainer.py:765] (5/8) Epoch 16, batch 100, train_loss[loss=3.566, NarTop10Accuracy=0.6104, over 7218.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6968, over 2355.67 frames. ], batch size: 31, lr: 5.45e-03
2024-08-06 17:50:12,157 INFO [trainer.py:765] (5/8) Epoch 16, batch 200, train_loss[loss=2.881, NarTop10Accuracy=0.7536, over 6897.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6868, over 3850.36 frames. ], batch size: 17, lr: 5.44e-03
2024-08-06 17:50:45,159 INFO [trainer.py:765] (5/8) Epoch 16, batch 300, train_loss[loss=3.24, NarTop10Accuracy=0.6768, over 7014.00 frames. ], tot_loss[loss=3.185, NarTop10Accuracy=0.6886, over 4669.84 frames. ], batch size: 22, lr: 5.43e-03
2024-08-06 17:51:15,976 INFO [trainer.py:765] (5/8) Epoch 16, batch 400, train_loss[loss=3.517, NarTop10Accuracy=0.6262, over 5088.00 frames. ], tot_loss[loss=3.188, NarTop10Accuracy=0.6881, over 5109.76 frames. ], batch size: 7, lr: 5.43e-03
2024-08-06 17:51:50,323 INFO [trainer.py:765] (5/8) Epoch 16, batch 500, train_loss[loss=3.001, NarTop10Accuracy=0.727, over 6123.00 frames. ], tot_loss[loss=3.181, NarTop10Accuracy=0.6898, over 5386.13 frames. ], batch size: 11, lr: 5.42e-03
2024-08-06 17:52:24,251 INFO [trainer.py:765] (5/8) Epoch 16, batch 600, train_loss[loss=2.972, NarTop10Accuracy=0.7446, over 5649.00 frames. ], tot_loss[loss=3.192, NarTop10Accuracy=0.6877, over 5653.04 frames. ], batch size: 9, lr: 5.41e-03
2024-08-06 17:52:55,387 INFO [trainer.py:765] (5/8) Epoch 16, batch 700, train_loss[loss=2.915, NarTop10Accuracy=0.7454, over 4995.00 frames. ], tot_loss[loss=3.189, NarTop10Accuracy=0.6886, over 5723.51 frames. ], batch size: 6, lr: 5.41e-03
2024-08-06 17:53:33,815 INFO [trainer.py:765] (5/8) Epoch 16, batch 800, train_loss[loss=3.23, NarTop10Accuracy=0.6758, over 5055.00 frames. ], tot_loss[loss=3.184, NarTop10Accuracy=0.6896, over 5772.34 frames. ], batch size: 6, lr: 5.40e-03
2024-08-06 17:54:03,923 INFO [trainer.py:765] (5/8) Epoch 16, batch 900, train_loss[loss=3.428, NarTop10Accuracy=0.643, over 6159.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6928, over 5804.79 frames. ], batch size: 13, lr: 5.39e-03
2024-08-06 17:54:37,607 INFO [trainer.py:765] (5/8) Epoch 16, batch 1000, train_loss[loss=2.915, NarTop10Accuracy=0.7473, over 6201.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6945, over 5907.87 frames. ], batch size: 13, lr: 5.39e-03
2024-08-06 17:55:17,197 INFO [trainer.py:765] (5/8) Epoch 16, batch 1100, train_loss[loss=3.11, NarTop10Accuracy=0.7066, over 6801.00 frames. ], tot_loss[loss=3.191, NarTop10Accuracy=0.6876, over 5942.01 frames. ], batch size: 17, lr: 5.38e-03
2024-08-06 17:55:46,209 INFO [trainer.py:765] (5/8) Epoch 16, batch 1200, train_loss[loss=3.387, NarTop10Accuracy=0.6525, over 7089.00 frames. ], tot_loss[loss=3.192, NarTop10Accuracy=0.6875, over 5931.35 frames. ], batch size: 31, lr: 5.37e-03
2024-08-06 17:56:22,775 INFO [trainer.py:765] (5/8) Epoch 16, batch 1300, train_loss[loss=3.444, NarTop10Accuracy=0.6284, over 4953.00 frames. ], tot_loss[loss=3.189, NarTop10Accuracy=0.6879, over 5998.17 frames. ], batch size: 6, lr: 5.37e-03
2024-08-06 17:56:44,648 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 17:56:53,428 INFO [trainer.py:811] (5/8) Epoch 16, validation: loss=3.112, NarTop10Accuracy=0.703, over 1905321.00 frames. 
2024-08-06 17:56:53,429 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 17:56:54,007 INFO [optim.py:386] (5/8) 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 17:57:06,170 INFO [trainer.py:765] (5/8) Epoch 16, batch 1400, train_loss[loss=3.227, NarTop10Accuracy=0.6894, over 6108.00 frames. ], tot_loss[loss=3.187, NarTop10Accuracy=0.6883, over 6035.83 frames. ], batch size: 11, lr: 5.36e-03
2024-08-06 17:57:34,032 INFO [trainer.py:765] (5/8) Epoch 16, batch 1500, train_loss[loss=3.298, NarTop10Accuracy=0.671, over 5892.00 frames. ], tot_loss[loss=3.181, NarTop10Accuracy=0.6895, over 5967.43 frames. ], batch size: 50, lr: 5.35e-03
2024-08-06 17:58:01,773 INFO [trainer.py:765] (5/8) Epoch 16, batch 1600, train_loss[loss=3.005, NarTop10Accuracy=0.7317, over 7002.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6913, over 5949.91 frames. ], batch size: 22, lr: 5.35e-03
2024-08-06 17:58:28,474 INFO [trainer.py:765] (5/8) Epoch 16, batch 1700, train_loss[loss=2.957, NarTop10Accuracy=0.7327, over 6174.00 frames. ], tot_loss[loss=3.191, NarTop10Accuracy=0.6878, over 5944.87 frames. ], batch size: 13, lr: 5.34e-03
2024-08-06 17:58:54,975 INFO [trainer.py:765] (5/8) Epoch 16, batch 1800, train_loss[loss=3.18, NarTop10Accuracy=0.6932, over 7389.00 frames. ], tot_loss[loss=3.182, NarTop10Accuracy=0.6894, over 5998.83 frames. ], batch size: 22, lr: 5.33e-03
2024-08-06 17:59:21,360 INFO [trainer.py:765] (5/8) Epoch 16, batch 1900, train_loss[loss=3.528, NarTop10Accuracy=0.6238, over 6669.00 frames. ], tot_loss[loss=3.211, NarTop10Accuracy=0.684, over 6039.97 frames. ], batch size: 50, lr: 5.33e-03
2024-08-06 17:59:46,856 INFO [trainer.py:765] (5/8) Epoch 16, batch 2000, train_loss[loss=3.155, NarTop10Accuracy=0.7029, over 6087.00 frames. ], tot_loss[loss=3.176, NarTop10Accuracy=0.6911, over 6013.82 frames. ], batch size: 52, lr: 5.32e-03
2024-08-06 18:00:12,116 INFO [trainer.py:765] (5/8) Epoch 16, batch 2100, train_loss[loss=3.487, NarTop10Accuracy=0.6218, over 4821.00 frames. ], tot_loss[loss=3.2, NarTop10Accuracy=0.6863, over 5989.94 frames. ], batch size: 5, lr: 5.32e-03
2024-08-06 18:00:37,333 INFO [trainer.py:765] (5/8) Epoch 16, batch 2200, train_loss[loss=3.261, NarTop10Accuracy=0.6718, over 7164.00 frames. ], tot_loss[loss=3.208, NarTop10Accuracy=0.6841, over 6040.88 frames. ], batch size: 31, lr: 5.31e-03
2024-08-06 18:01:02,502 INFO [trainer.py:765] (5/8) Epoch 16, batch 2300, train_loss[loss=3.052, NarTop10Accuracy=0.7263, over 5640.00 frames. ], tot_loss[loss=3.21, NarTop10Accuracy=0.6837, over 6023.99 frames. ], batch size: 9, lr: 5.30e-03
2024-08-06 18:01:26,883 INFO [trainer.py:765] (5/8) Epoch 16, batch 2400, train_loss[loss=3.033, NarTop10Accuracy=0.7156, over 5031.00 frames. ], tot_loss[loss=3.193, NarTop10Accuracy=0.6871, over 5788.79 frames. ], batch size: 7, lr: 5.30e-03
2024-08-06 18:01:50,405 INFO [trainer.py:765] (5/8) Epoch 16, batch 2500, train_loss[loss=3.003, NarTop10Accuracy=0.7268, over 5034.00 frames. ], tot_loss[loss=3.159, NarTop10Accuracy=0.6939, over 5488.96 frames. ], batch size: 7, lr: 5.29e-03
2024-08-06 18:02:10,712 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 18:03:08,531 INFO [trainer.py:765] (5/8) Epoch 17, batch 100, train_loss[loss=3.205, NarTop10Accuracy=0.6938, over 7422.00 frames. ], tot_loss[loss=3.137, NarTop10Accuracy=0.6992, over 2371.02 frames. ], batch size: 32, lr: 5.12e-03
2024-08-06 18:03:45,145 INFO [trainer.py:765] (5/8) Epoch 17, batch 200, train_loss[loss=3.379, NarTop10Accuracy=0.6485, over 6846.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.6958, over 3863.13 frames. ], batch size: 17, lr: 5.12e-03
2024-08-06 18:04:19,590 INFO [trainer.py:765] (5/8) Epoch 17, batch 300, train_loss[loss=3.251, NarTop10Accuracy=0.6739, over 7197.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6913, over 4653.65 frames. ], batch size: 22, lr: 5.11e-03
2024-08-06 18:04:48,402 INFO [trainer.py:765] (5/8) Epoch 17, batch 400, train_loss[loss=3.386, NarTop10Accuracy=0.6426, over 5190.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6922, over 5086.20 frames. ], batch size: 7, lr: 5.10e-03
2024-08-06 18:05:24,680 INFO [trainer.py:765] (5/8) Epoch 17, batch 500, train_loss[loss=2.83, NarTop10Accuracy=0.7614, over 6201.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6957, over 5381.31 frames. ], batch size: 11, lr: 5.10e-03
2024-08-06 18:05:58,739 INFO [trainer.py:765] (5/8) Epoch 17, batch 600, train_loss[loss=3.21, NarTop10Accuracy=0.6922, over 5739.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6923, over 5646.11 frames. ], batch size: 9, lr: 5.09e-03
2024-08-06 18:06:32,475 INFO [trainer.py:765] (5/8) Epoch 17, batch 700, train_loss[loss=3.021, NarTop10Accuracy=0.7209, over 4947.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.693, over 5728.94 frames. ], batch size: 6, lr: 5.08e-03
2024-08-06 18:07:02,724 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 18:07:10,763 INFO [trainer.py:811] (5/8) Epoch 17, validation: loss=3.018, NarTop10Accuracy=0.7223, over 1905321.00 frames. 
2024-08-06 18:07:10,763 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 18:07:11,312 INFO [optim.py:386] (5/8) Clipping_scale=2.0, grad-norm quartiles 1.649e+02 2.005e+02 2.161e+02 2.341e+02 3.806e+02, threshold=4.323e+02, percent-clipped=0.0
2024-08-06 18:07:14,353 INFO [trainer.py:765] (5/8) Epoch 17, batch 800, train_loss[loss=3.085, NarTop10Accuracy=0.7059, over 4182.00 frames. ], tot_loss[loss=3.182, NarTop10Accuracy=0.6896, over 5774.46 frames. ], batch size: 5, lr: 5.08e-03
2024-08-06 18:07:49,721 INFO [trainer.py:765] (5/8) Epoch 17, batch 900, train_loss[loss=3.572, NarTop10Accuracy=0.6266, over 6192.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6949, over 5786.31 frames. ], batch size: 13, lr: 5.07e-03
2024-08-06 18:08:21,597 INFO [trainer.py:765] (5/8) Epoch 17, batch 1000, train_loss[loss=3.255, NarTop10Accuracy=0.6767, over 6225.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.6926, over 5889.42 frames. ], batch size: 13, lr: 5.07e-03
2024-08-06 18:09:03,106 INFO [trainer.py:765] (5/8) Epoch 17, batch 1100, train_loss[loss=2.979, NarTop10Accuracy=0.7327, over 6816.00 frames. ], tot_loss[loss=3.171, NarTop10Accuracy=0.6915, over 5918.83 frames. ], batch size: 17, lr: 5.06e-03
2024-08-06 18:09:36,745 INFO [trainer.py:765] (5/8) Epoch 17, batch 1200, train_loss[loss=3.005, NarTop10Accuracy=0.7289, over 7128.00 frames. ], tot_loss[loss=3.167, NarTop10Accuracy=0.6923, over 5917.41 frames. ], batch size: 31, lr: 5.06e-03
2024-08-06 18:10:10,688 INFO [trainer.py:765] (5/8) Epoch 17, batch 1300, train_loss[loss=3.283, NarTop10Accuracy=0.6625, over 4923.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6916, over 6005.71 frames. ], batch size: 6, lr: 5.05e-03
2024-08-06 18:10:48,026 INFO [trainer.py:765] (5/8) Epoch 17, batch 1400, train_loss[loss=3.249, NarTop10Accuracy=0.6749, over 6249.00 frames. ], tot_loss[loss=3.178, NarTop10Accuracy=0.6902, over 6018.59 frames. ], batch size: 11, lr: 5.04e-03
2024-08-06 18:11:19,105 INFO [trainer.py:765] (5/8) Epoch 17, batch 1500, train_loss[loss=3.529, NarTop10Accuracy=0.6219, over 6357.00 frames. ], tot_loss[loss=3.17, NarTop10Accuracy=0.6919, over 5966.28 frames. ], batch size: 50, lr: 5.04e-03
2024-08-06 18:11:46,855 INFO [trainer.py:765] (5/8) Epoch 17, batch 1600, train_loss[loss=3.103, NarTop10Accuracy=0.7064, over 7011.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6952, over 5954.67 frames. ], batch size: 22, lr: 5.03e-03
2024-08-06 18:12:13,508 INFO [trainer.py:765] (5/8) Epoch 17, batch 1700, train_loss[loss=3.458, NarTop10Accuracy=0.6229, over 6693.00 frames. ], tot_loss[loss=3.175, NarTop10Accuracy=0.6908, over 5944.20 frames. ], batch size: 14, lr: 5.03e-03
2024-08-06 18:12:40,001 INFO [trainer.py:765] (5/8) Epoch 17, batch 1800, train_loss[loss=2.905, NarTop10Accuracy=0.7458, over 7215.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.6878, over 6003.08 frames. ], batch size: 23, lr: 5.02e-03
2024-08-06 18:13:06,380 INFO [trainer.py:765] (5/8) Epoch 17, batch 1900, train_loss[loss=3.172, NarTop10Accuracy=0.6919, over 5604.00 frames. ], tot_loss[loss=3.2, NarTop10Accuracy=0.6856, over 6027.97 frames. ], batch size: 50, lr: 5.01e-03
2024-08-06 18:13:31,922 INFO [trainer.py:765] (5/8) Epoch 17, batch 2000, train_loss[loss=3.576, NarTop10Accuracy=0.6085, over 6141.00 frames. ], tot_loss[loss=3.177, NarTop10Accuracy=0.6905, over 6015.42 frames. ], batch size: 50, lr: 5.01e-03
2024-08-06 18:13:57,228 INFO [trainer.py:765] (5/8) Epoch 17, batch 2100, train_loss[loss=2.886, NarTop10Accuracy=0.7362, over 3891.00 frames. ], tot_loss[loss=3.185, NarTop10Accuracy=0.6886, over 5989.62 frames. ], batch size: 4, lr: 5.00e-03
2024-08-06 18:14:22,434 INFO [trainer.py:765] (5/8) Epoch 17, batch 2200, train_loss[loss=2.919, NarTop10Accuracy=0.7396, over 6996.00 frames. ], tot_loss[loss=3.202, NarTop10Accuracy=0.6852, over 6016.41 frames. ], batch size: 31, lr: 5.00e-03
2024-08-06 18:14:47,592 INFO [trainer.py:765] (5/8) Epoch 17, batch 2300, train_loss[loss=2.936, NarTop10Accuracy=0.7453, over 5796.00 frames. ], tot_loss[loss=3.193, NarTop10Accuracy=0.6873, over 6041.09 frames. ], batch size: 9, lr: 4.99e-03
2024-08-06 18:15:12,061 INFO [trainer.py:765] (5/8) Epoch 17, batch 2400, train_loss[loss=2.845, NarTop10Accuracy=0.7519, over 5106.00 frames. ], tot_loss[loss=3.187, NarTop10Accuracy=0.688, over 5779.36 frames. ], batch size: 7, lr: 4.99e-03
2024-08-06 18:15:35,514 INFO [trainer.py:765] (5/8) Epoch 17, batch 2500, train_loss[loss=3.009, NarTop10Accuracy=0.7314, over 5145.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6921, over 5483.04 frames. ], batch size: 7, lr: 4.98e-03
2024-08-06 18:15:55,169 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 18:16:49,908 INFO [trainer.py:765] (5/8) Epoch 18, batch 100, train_loss[loss=3.124, NarTop10Accuracy=0.7041, over 7146.00 frames. ], tot_loss[loss=3.176, NarTop10Accuracy=0.6911, over 2358.19 frames. ], batch size: 31, lr: 4.83e-03
2024-08-06 18:17:24,749 INFO [trainer.py:765] (5/8) Epoch 18, batch 200, train_loss[loss=2.978, NarTop10Accuracy=0.7329, over 6786.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.6929, over 3844.79 frames. ], batch size: 17, lr: 4.83e-03
2024-08-06 18:17:27,717 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 18:17:35,926 INFO [trainer.py:811] (5/8) Epoch 18, validation: loss=3.062, NarTop10Accuracy=0.7137, over 1905321.00 frames. 
2024-08-06 18:17:35,927 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 18:17:36,529 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 18, batch 300, train_loss[loss=3.404, NarTop10Accuracy=0.6376, over 7191.00 frames. ], tot_loss[loss=3.17, NarTop10Accuracy=0.6922, over 4654.36 frames. ], batch size: 22, lr: 4.82e-03
2024-08-06 18:18:38,183 INFO [trainer.py:765] (5/8) Epoch 18, batch 400, train_loss[loss=3.181, NarTop10Accuracy=0.6779, over 5148.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6957, over 5115.70 frames. ], batch size: 7, lr: 4.81e-03
2024-08-06 18:19:13,600 INFO [trainer.py:765] (5/8) Epoch 18, batch 500, train_loss[loss=3.05, NarTop10Accuracy=0.7096, over 6063.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6959, over 5373.31 frames. ], batch size: 11, lr: 4.81e-03
2024-08-06 18:19:48,151 INFO [trainer.py:765] (5/8) Epoch 18, batch 600, train_loss[loss=3.384, NarTop10Accuracy=0.6399, over 5763.00 frames. ], tot_loss[loss=3.156, NarTop10Accuracy=0.695, over 5645.50 frames. ], batch size: 9, lr: 4.80e-03
2024-08-06 18:20:23,870 INFO [trainer.py:765] (5/8) Epoch 18, batch 700, train_loss[loss=3.35, NarTop10Accuracy=0.6514, over 5019.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6935, over 5734.30 frames. ], batch size: 6, lr: 4.80e-03
2024-08-06 18:21:01,027 INFO [trainer.py:765] (5/8) Epoch 18, batch 800, train_loss[loss=2.845, NarTop10Accuracy=0.7547, over 5052.00 frames. ], tot_loss[loss=3.173, NarTop10Accuracy=0.6913, over 5791.95 frames. ], batch size: 6, lr: 4.79e-03
2024-08-06 18:21:32,409 INFO [trainer.py:765] (5/8) Epoch 18, batch 900, train_loss[loss=3.081, NarTop10Accuracy=0.7108, over 6627.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6948, over 5799.60 frames. ], batch size: 14, lr: 4.79e-03
2024-08-06 18:22:11,192 INFO [trainer.py:765] (5/8) Epoch 18, batch 1000, train_loss[loss=2.841, NarTop10Accuracy=0.7504, over 6264.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6922, over 5904.56 frames. ], batch size: 13, lr: 4.78e-03
2024-08-06 18:22:46,970 INFO [trainer.py:765] (5/8) Epoch 18, batch 1100, train_loss[loss=3.561, NarTop10Accuracy=0.6142, over 6957.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.6933, over 5934.21 frames. ], batch size: 17, lr: 4.78e-03
2024-08-06 18:23:18,605 INFO [trainer.py:765] (5/8) Epoch 18, batch 1200, train_loss[loss=3.598, NarTop10Accuracy=0.6108, over 7113.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6905, over 5939.56 frames. ], batch size: 31, lr: 4.77e-03
2024-08-06 18:24:00,100 INFO [trainer.py:765] (5/8) Epoch 18, batch 1300, train_loss[loss=2.734, NarTop10Accuracy=0.7793, over 5151.00 frames. ], tot_loss[loss=3.156, NarTop10Accuracy=0.6943, over 6003.40 frames. ], batch size: 6, lr: 4.77e-03
2024-08-06 18:24:29,575 INFO [trainer.py:765] (5/8) Epoch 18, batch 1400, train_loss[loss=3.041, NarTop10Accuracy=0.7251, over 6075.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6947, over 6006.24 frames. ], batch size: 11, lr: 4.76e-03
2024-08-06 18:25:00,307 INFO [trainer.py:765] (5/8) Epoch 18, batch 1500, train_loss[loss=3.072, NarTop10Accuracy=0.7108, over 6495.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.6953, over 5957.13 frames. ], batch size: 50, lr: 4.76e-03
2024-08-06 18:25:28,085 INFO [trainer.py:765] (5/8) Epoch 18, batch 1600, train_loss[loss=3.078, NarTop10Accuracy=0.7083, over 6927.00 frames. ], tot_loss[loss=3.162, NarTop10Accuracy=0.6934, over 5933.49 frames. ], batch size: 22, lr: 4.75e-03
2024-08-06 18:25:54,688 INFO [trainer.py:765] (5/8) Epoch 18, batch 1700, train_loss[loss=3.138, NarTop10Accuracy=0.7052, over 6633.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.6937, over 5927.87 frames. ], batch size: 14, lr: 4.75e-03
2024-08-06 18:26:21,197 INFO [trainer.py:765] (5/8) Epoch 18, batch 1800, train_loss[loss=3.424, NarTop10Accuracy=0.6375, over 7212.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6955, over 5983.51 frames. ], batch size: 22, lr: 4.74e-03
2024-08-06 18:26:47,567 INFO [trainer.py:765] (5/8) Epoch 18, batch 1900, train_loss[loss=3.101, NarTop10Accuracy=0.7078, over 5883.00 frames. ], tot_loss[loss=3.167, NarTop10Accuracy=0.6923, over 6018.39 frames. ], batch size: 50, lr: 4.74e-03
2024-08-06 18:27:13,176 INFO [trainer.py:765] (5/8) Epoch 18, batch 2000, train_loss[loss=3.065, NarTop10Accuracy=0.7232, over 6216.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6947, over 5996.85 frames. ], batch size: 50, lr: 4.73e-03
2024-08-06 18:27:38,529 INFO [trainer.py:765] (5/8) Epoch 18, batch 2100, train_loss[loss=3.272, NarTop10Accuracy=0.6699, over 3975.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6955, over 5982.95 frames. ], batch size: 4, lr: 4.73e-03
2024-08-06 18:28:03,812 INFO [trainer.py:765] (5/8) Epoch 18, batch 2200, train_loss[loss=3.123, NarTop10Accuracy=0.7066, over 7305.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.694, over 6029.89 frames. ], batch size: 31, lr: 4.72e-03
2024-08-06 18:28:06,571 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 18:28:14,649 INFO [trainer.py:811] (5/8) Epoch 18, validation: loss=3.028, NarTop10Accuracy=0.7201, over 1905321.00 frames. 
2024-08-06 18:28:14,650 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 18:28:15,147 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 18, batch 2300, train_loss[loss=2.824, NarTop10Accuracy=0.7696, over 5631.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6913, over 6030.20 frames. ], batch size: 9, lr: 4.72e-03
2024-08-06 18:29:01,593 INFO [trainer.py:765] (5/8) Epoch 18, batch 2400, train_loss[loss=2.963, NarTop10Accuracy=0.7225, over 5124.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6962, over 5782.76 frames. ], batch size: 7, lr: 4.71e-03
2024-08-06 18:29:25,027 INFO [trainer.py:765] (5/8) Epoch 18, batch 2500, train_loss[loss=3.133, NarTop10Accuracy=0.704, over 5193.00 frames. ], tot_loss[loss=3.136, NarTop10Accuracy=0.699, over 5495.23 frames. ], batch size: 7, lr: 4.71e-03
2024-08-06 18:29:45,034 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 18:30:41,231 INFO [trainer.py:765] (5/8) Epoch 19, batch 100, train_loss[loss=2.955, NarTop10Accuracy=0.7307, over 7182.00 frames. ], tot_loss[loss=3.172, NarTop10Accuracy=0.6929, over 2360.40 frames. ], batch size: 31, lr: 4.57e-03
2024-08-06 18:31:15,602 INFO [trainer.py:765] (5/8) Epoch 19, batch 200, train_loss[loss=3.018, NarTop10Accuracy=0.7313, over 6837.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.6946, over 3850.22 frames. ], batch size: 17, lr: 4.57e-03
2024-08-06 18:31:47,468 INFO [trainer.py:765] (5/8) Epoch 19, batch 300, train_loss[loss=3.531, NarTop10Accuracy=0.6169, over 7275.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.6989, over 4657.45 frames. ], batch size: 23, lr: 4.56e-03
2024-08-06 18:32:20,355 INFO [trainer.py:765] (5/8) Epoch 19, batch 400, train_loss[loss=3.11, NarTop10Accuracy=0.6924, over 5166.00 frames. ], tot_loss[loss=3.136, NarTop10Accuracy=0.6985, over 5132.98 frames. ], batch size: 7, lr: 4.56e-03
2024-08-06 18:32:50,335 INFO [trainer.py:765] (5/8) Epoch 19, batch 500, train_loss[loss=3.145, NarTop10Accuracy=0.697, over 5937.00 frames. ], tot_loss[loss=3.133, NarTop10Accuracy=0.699, over 5411.33 frames. ], batch size: 11, lr: 4.55e-03
2024-08-06 18:33:29,610 INFO [trainer.py:765] (5/8) Epoch 19, batch 600, train_loss[loss=3.059, NarTop10Accuracy=0.7173, over 5583.00 frames. ], tot_loss[loss=3.14, NarTop10Accuracy=0.6979, over 5669.53 frames. ], batch size: 9, lr: 4.55e-03
2024-08-06 18:34:03,592 INFO [trainer.py:765] (5/8) Epoch 19, batch 700, train_loss[loss=2.976, NarTop10Accuracy=0.7288, over 5052.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6962, over 5724.52 frames. ], batch size: 6, lr: 4.54e-03
2024-08-06 18:34:35,179 INFO [trainer.py:765] (5/8) Epoch 19, batch 800, train_loss[loss=3.14, NarTop10Accuracy=0.6948, over 5184.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.6949, over 5780.43 frames. ], batch size: 6, lr: 4.54e-03
2024-08-06 18:35:10,263 INFO [trainer.py:765] (5/8) Epoch 19, batch 900, train_loss[loss=2.88, NarTop10Accuracy=0.7471, over 6258.00 frames. ], tot_loss[loss=3.143, NarTop10Accuracy=0.6974, over 5791.02 frames. ], batch size: 13, lr: 4.53e-03
2024-08-06 18:35:48,637 INFO [trainer.py:765] (5/8) Epoch 19, batch 1000, train_loss[loss=3.432, NarTop10Accuracy=0.6362, over 6201.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6965, over 5892.65 frames. ], batch size: 13, lr: 4.53e-03
2024-08-06 18:36:20,938 INFO [trainer.py:765] (5/8) Epoch 19, batch 1100, train_loss[loss=2.952, NarTop10Accuracy=0.7314, over 6942.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.6934, over 5922.89 frames. ], batch size: 17, lr: 4.52e-03
2024-08-06 18:36:57,130 INFO [trainer.py:765] (5/8) Epoch 19, batch 1200, train_loss[loss=3.036, NarTop10Accuracy=0.7215, over 7008.00 frames. ], tot_loss[loss=3.167, NarTop10Accuracy=0.6917, over 5928.18 frames. ], batch size: 31, lr: 4.52e-03
2024-08-06 18:37:35,315 INFO [trainer.py:765] (5/8) Epoch 19, batch 1300, train_loss[loss=2.852, NarTop10Accuracy=0.7539, over 5097.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6924, over 5999.48 frames. ], batch size: 6, lr: 4.51e-03
2024-08-06 18:38:04,679 INFO [trainer.py:765] (5/8) Epoch 19, batch 1400, train_loss[loss=2.869, NarTop10Accuracy=0.7537, over 6219.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6913, over 6026.80 frames. ], batch size: 11, lr: 4.51e-03
2024-08-06 18:38:34,550 INFO [trainer.py:765] (5/8) Epoch 19, batch 1500, train_loss[loss=3.495, NarTop10Accuracy=0.6226, over 6057.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6956, over 5952.16 frames. ], batch size: 52, lr: 4.50e-03
2024-08-06 18:39:02,311 INFO [trainer.py:765] (5/8) Epoch 19, batch 1600, train_loss[loss=3.429, NarTop10Accuracy=0.6424, over 7050.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6967, over 5937.68 frames. ], batch size: 22, lr: 4.50e-03
2024-08-06 18:39:11,590 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 18:39:19,795 INFO [trainer.py:811] (5/8) Epoch 19, validation: loss=2.958, NarTop10Accuracy=0.7345, over 1905321.00 frames. 
2024-08-06 18:39:19,796 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 18:39:20,378 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 19, batch 1700, train_loss[loss=3.454, NarTop10Accuracy=0.6246, over 6204.00 frames. ], tot_loss[loss=3.142, NarTop10Accuracy=0.6973, over 5923.49 frames. ], batch size: 13, lr: 4.49e-03
2024-08-06 18:40:03,789 INFO [trainer.py:765] (5/8) Epoch 19, batch 1800, train_loss[loss=3.56, NarTop10Accuracy=0.6122, over 6921.00 frames. ], tot_loss[loss=3.147, NarTop10Accuracy=0.696, over 5982.05 frames. ], batch size: 22, lr: 4.49e-03
2024-08-06 18:40:30,217 INFO [trainer.py:765] (5/8) Epoch 19, batch 1900, train_loss[loss=3.093, NarTop10Accuracy=0.7146, over 6171.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6956, over 6003.07 frames. ], batch size: 50, lr: 4.49e-03
2024-08-06 18:40:55,793 INFO [trainer.py:765] (5/8) Epoch 19, batch 2000, train_loss[loss=3.336, NarTop10Accuracy=0.6655, over 5964.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6956, over 5999.38 frames. ], batch size: 51, lr: 4.48e-03
2024-08-06 18:41:21,183 INFO [trainer.py:765] (5/8) Epoch 19, batch 2100, train_loss[loss=2.775, NarTop10Accuracy=0.7707, over 4875.00 frames. ], tot_loss[loss=3.14, NarTop10Accuracy=0.6977, over 5964.06 frames. ], batch size: 5, lr: 4.48e-03
2024-08-06 18:41:46,455 INFO [trainer.py:765] (5/8) Epoch 19, batch 2200, train_loss[loss=3.185, NarTop10Accuracy=0.6886, over 7344.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6956, over 6005.09 frames. ], batch size: 31, lr: 4.47e-03
2024-08-06 18:42:11,559 INFO [trainer.py:765] (5/8) Epoch 19, batch 2300, train_loss[loss=3.158, NarTop10Accuracy=0.691, over 5679.00 frames. ], tot_loss[loss=3.167, NarTop10Accuracy=0.6922, over 6027.71 frames. ], batch size: 9, lr: 4.47e-03
2024-08-06 18:42:35,988 INFO [trainer.py:765] (5/8) Epoch 19, batch 2400, train_loss[loss=3.1, NarTop10Accuracy=0.701, over 5448.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6971, over 5768.71 frames. ], batch size: 7, lr: 4.46e-03
2024-08-06 18:42:59,690 INFO [trainer.py:765] (5/8) Epoch 19, batch 2500, train_loss[loss=2.894, NarTop10Accuracy=0.7448, over 5247.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7019, over 5466.13 frames. ], batch size: 7, lr: 4.46e-03
2024-08-06 18:43:19,838 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 18:44:22,973 INFO [trainer.py:765] (5/8) Epoch 20, batch 100, train_loss[loss=3.355, NarTop10Accuracy=0.6647, over 7068.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6936, over 2358.79 frames. ], batch size: 31, lr: 4.34e-03
2024-08-06 18:44:58,379 INFO [trainer.py:765] (5/8) Epoch 20, batch 200, train_loss[loss=3.537, NarTop10Accuracy=0.6191, over 6729.00 frames. ], tot_loss[loss=3.129, NarTop10Accuracy=0.7002, over 3863.86 frames. ], batch size: 17, lr: 4.33e-03
2024-08-06 18:45:32,279 INFO [trainer.py:765] (5/8) Epoch 20, batch 300, train_loss[loss=3.425, NarTop10Accuracy=0.6362, over 7029.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7031, over 4660.73 frames. ], batch size: 22, lr: 4.33e-03
2024-08-06 18:46:05,128 INFO [trainer.py:765] (5/8) Epoch 20, batch 400, train_loss[loss=2.83, NarTop10Accuracy=0.7654, over 5322.00 frames. ], tot_loss[loss=3.123, NarTop10Accuracy=0.7012, over 5127.74 frames. ], batch size: 7, lr: 4.32e-03
2024-08-06 18:46:35,770 INFO [trainer.py:765] (5/8) Epoch 20, batch 500, train_loss[loss=2.836, NarTop10Accuracy=0.7612, over 6114.00 frames. ], tot_loss[loss=3.13, NarTop10Accuracy=0.6996, over 5393.26 frames. ], batch size: 11, lr: 4.32e-03
2024-08-06 18:47:13,255 INFO [trainer.py:765] (5/8) Epoch 20, batch 600, train_loss[loss=3.01, NarTop10Accuracy=0.732, over 5847.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7008, over 5643.64 frames. ], batch size: 9, lr: 4.31e-03
2024-08-06 18:47:44,481 INFO [trainer.py:765] (5/8) Epoch 20, batch 700, train_loss[loss=2.729, NarTop10Accuracy=0.7826, over 4251.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7024, over 5710.76 frames. ], batch size: 5, lr: 4.31e-03
2024-08-06 18:48:21,016 INFO [trainer.py:765] (5/8) Epoch 20, batch 800, train_loss[loss=2.767, NarTop10Accuracy=0.7743, over 5121.00 frames. ], tot_loss[loss=3.131, NarTop10Accuracy=0.6997, over 5780.72 frames. ], batch size: 6, lr: 4.31e-03
2024-08-06 18:48:56,534 INFO [trainer.py:765] (5/8) Epoch 20, batch 900, train_loss[loss=2.836, NarTop10Accuracy=0.7576, over 6618.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.7009, over 5785.66 frames. ], batch size: 14, lr: 4.30e-03
2024-08-06 18:49:29,805 INFO [trainer.py:765] (5/8) Epoch 20, batch 1000, train_loss[loss=3.309, NarTop10Accuracy=0.6722, over 6162.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6954, over 5899.99 frames. ], batch size: 13, lr: 4.30e-03
2024-08-06 18:49:52,237 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 18:50:00,327 INFO [trainer.py:811] (5/8) Epoch 20, validation: loss=2.962, NarTop10Accuracy=0.7336, over 1905321.00 frames. 
2024-08-06 18:50:00,327 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 18:50:00,875 INFO [optim.py:386] (5/8) Clipping_scale=2.0, grad-norm quartiles 1.681e+02 2.061e+02 2.223e+02 2.401e+02 3.871e+02, threshold=4.447e+02, percent-clipped=0.0
2024-08-06 18:50:15,426 INFO [trainer.py:765] (5/8) Epoch 20, batch 1100, train_loss[loss=3.314, NarTop10Accuracy=0.659, over 6843.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6961, over 5925.10 frames. ], batch size: 17, lr: 4.29e-03
2024-08-06 18:50:53,776 INFO [trainer.py:765] (5/8) Epoch 20, batch 1200, train_loss[loss=2.9, NarTop10Accuracy=0.7498, over 7431.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6966, over 5930.66 frames. ], batch size: 31, lr: 4.29e-03
2024-08-06 18:51:25,129 INFO [trainer.py:765] (5/8) Epoch 20, batch 1300, train_loss[loss=3.335, NarTop10Accuracy=0.657, over 4989.00 frames. ], tot_loss[loss=3.14, NarTop10Accuracy=0.6979, over 5985.72 frames. ], batch size: 6, lr: 4.29e-03
2024-08-06 18:51:59,314 INFO [trainer.py:765] (5/8) Epoch 20, batch 1400, train_loss[loss=3.182, NarTop10Accuracy=0.6932, over 5997.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.6992, over 6003.57 frames. ], batch size: 11, lr: 4.28e-03
2024-08-06 18:52:32,805 INFO [trainer.py:765] (5/8) Epoch 20, batch 1500, train_loss[loss=3.277, NarTop10Accuracy=0.667, over 5994.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6965, over 5958.91 frames. ], batch size: 50, lr: 4.28e-03
2024-08-06 18:53:00,635 INFO [trainer.py:765] (5/8) Epoch 20, batch 1600, train_loss[loss=2.922, NarTop10Accuracy=0.7457, over 7446.00 frames. ], tot_loss[loss=3.151, NarTop10Accuracy=0.6952, over 5944.74 frames. ], batch size: 22, lr: 4.27e-03
2024-08-06 18:53:27,328 INFO [trainer.py:765] (5/8) Epoch 20, batch 1700, train_loss[loss=3.394, NarTop10Accuracy=0.6387, over 6675.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6963, over 5923.27 frames. ], batch size: 14, lr: 4.27e-03
2024-08-06 18:53:53,850 INFO [trainer.py:765] (5/8) Epoch 20, batch 1800, train_loss[loss=3.02, NarTop10Accuracy=0.7161, over 7203.00 frames. ], tot_loss[loss=3.138, NarTop10Accuracy=0.6982, over 5984.69 frames. ], batch size: 22, lr: 4.26e-03
2024-08-06 18:54:20,316 INFO [trainer.py:765] (5/8) Epoch 20, batch 1900, train_loss[loss=3.032, NarTop10Accuracy=0.7258, over 6093.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.6937, over 6041.15 frames. ], batch size: 51, lr: 4.26e-03
2024-08-06 18:54:45,890 INFO [trainer.py:765] (5/8) Epoch 20, batch 2000, train_loss[loss=3.696, NarTop10Accuracy=0.5725, over 6396.00 frames. ], tot_loss[loss=3.161, NarTop10Accuracy=0.6933, over 6023.23 frames. ], batch size: 52, lr: 4.26e-03
2024-08-06 18:55:11,182 INFO [trainer.py:765] (5/8) Epoch 20, batch 2100, train_loss[loss=3.456, NarTop10Accuracy=0.6332, over 3981.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6941, over 5983.54 frames. ], batch size: 4, lr: 4.25e-03
2024-08-06 18:55:36,414 INFO [trainer.py:765] (5/8) Epoch 20, batch 2200, train_loss[loss=3.036, NarTop10Accuracy=0.7253, over 7164.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6942, over 6009.81 frames. ], batch size: 31, lr: 4.25e-03
2024-08-06 18:56:01,635 INFO [trainer.py:765] (5/8) Epoch 20, batch 2300, train_loss[loss=3.14, NarTop10Accuracy=0.6909, over 5547.00 frames. ], tot_loss[loss=3.162, NarTop10Accuracy=0.6931, over 6014.19 frames. ], batch size: 9, lr: 4.24e-03
2024-08-06 18:56:26,050 INFO [trainer.py:765] (5/8) Epoch 20, batch 2400, train_loss[loss=2.942, NarTop10Accuracy=0.7359, over 5100.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6955, over 5777.06 frames. ], batch size: 7, lr: 4.24e-03
2024-08-06 18:56:49,566 INFO [trainer.py:765] (5/8) Epoch 20, batch 2500, train_loss[loss=2.863, NarTop10Accuracy=0.7592, over 5154.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7017, over 5461.79 frames. ], batch size: 7, lr: 4.24e-03
2024-08-06 18:57:09,595 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 18:58:09,585 INFO [trainer.py:765] (5/8) Epoch 21, batch 100, train_loss[loss=3.284, NarTop10Accuracy=0.6667, over 7146.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.703, over 2354.06 frames. ], batch size: 31, lr: 4.13e-03
2024-08-06 18:58:40,417 INFO [trainer.py:765] (5/8) Epoch 21, batch 200, train_loss[loss=2.837, NarTop10Accuracy=0.7688, over 6774.00 frames. ], tot_loss[loss=3.123, NarTop10Accuracy=0.7012, over 3848.83 frames. ], batch size: 17, lr: 4.12e-03
2024-08-06 18:59:13,333 INFO [trainer.py:765] (5/8) Epoch 21, batch 300, train_loss[loss=2.917, NarTop10Accuracy=0.7383, over 7209.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.699, over 4647.66 frames. ], batch size: 22, lr: 4.12e-03
2024-08-06 18:59:48,151 INFO [trainer.py:765] (5/8) Epoch 21, batch 400, train_loss[loss=2.885, NarTop10Accuracy=0.7535, over 5097.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7027, over 5105.75 frames. ], batch size: 7, lr: 4.11e-03
2024-08-06 19:00:16,840 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 19:00:25,076 INFO [trainer.py:811] (5/8) Epoch 21, validation: loss=2.992, NarTop10Accuracy=0.7268, over 1905321.00 frames. 
2024-08-06 19:00:25,077 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 19:00:25,623 INFO [optim.py:386] (5/8) Clipping_scale=2.0, grad-norm quartiles 1.727e+02 2.071e+02 2.224e+02 2.387e+02 3.839e+02, threshold=4.447e+02, percent-clipped=0.0
2024-08-06 19:00:29,891 INFO [trainer.py:765] (5/8) Epoch 21, batch 500, train_loss[loss=2.877, NarTop10Accuracy=0.7523, over 6123.00 frames. ], tot_loss[loss=3.117, NarTop10Accuracy=0.7021, over 5375.50 frames. ], batch size: 11, lr: 4.11e-03
2024-08-06 19:01:03,329 INFO [trainer.py:765] (5/8) Epoch 21, batch 600, train_loss[loss=3.434, NarTop10Accuracy=0.6383, over 5709.00 frames. ], tot_loss[loss=3.099, NarTop10Accuracy=0.7059, over 5644.23 frames. ], batch size: 9, lr: 4.11e-03
2024-08-06 19:01:39,388 INFO [trainer.py:765] (5/8) Epoch 21, batch 700, train_loss[loss=2.886, NarTop10Accuracy=0.7423, over 4989.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7033, over 5725.41 frames. ], batch size: 6, lr: 4.10e-03
2024-08-06 19:02:18,047 INFO [trainer.py:765] (5/8) Epoch 21, batch 800, train_loss[loss=2.942, NarTop10Accuracy=0.7373, over 5109.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.7004, over 5770.64 frames. ], batch size: 6, lr: 4.10e-03
2024-08-06 19:02:48,663 INFO [trainer.py:765] (5/8) Epoch 21, batch 900, train_loss[loss=3.015, NarTop10Accuracy=0.7155, over 6636.00 frames. ], tot_loss[loss=3.124, NarTop10Accuracy=0.7008, over 5783.77 frames. ], batch size: 14, lr: 4.09e-03
2024-08-06 19:03:25,801 INFO [trainer.py:765] (5/8) Epoch 21, batch 1000, train_loss[loss=2.97, NarTop10Accuracy=0.729, over 6582.00 frames. ], tot_loss[loss=3.136, NarTop10Accuracy=0.6982, over 5883.74 frames. ], batch size: 14, lr: 4.09e-03
2024-08-06 19:04:07,207 INFO [trainer.py:765] (5/8) Epoch 21, batch 1100, train_loss[loss=3.41, NarTop10Accuracy=0.636, over 6909.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6956, over 5935.71 frames. ], batch size: 17, lr: 4.09e-03
2024-08-06 19:04:38,463 INFO [trainer.py:765] (5/8) Epoch 21, batch 1200, train_loss[loss=3.361, NarTop10Accuracy=0.656, over 7338.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.6986, over 5940.63 frames. ], batch size: 31, lr: 4.08e-03
2024-08-06 19:05:15,316 INFO [trainer.py:765] (5/8) Epoch 21, batch 1300, train_loss[loss=3.037, NarTop10Accuracy=0.7236, over 5040.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7035, over 6004.37 frames. ], batch size: 6, lr: 4.08e-03
2024-08-06 19:05:55,559 INFO [trainer.py:765] (5/8) Epoch 21, batch 1400, train_loss[loss=3.384, NarTop10Accuracy=0.6486, over 6579.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7019, over 6033.25 frames. ], batch size: 12, lr: 4.07e-03
2024-08-06 19:06:23,600 INFO [trainer.py:765] (5/8) Epoch 21, batch 1500, train_loss[loss=3.278, NarTop10Accuracy=0.6716, over 6009.00 frames. ], tot_loss[loss=3.132, NarTop10Accuracy=0.6991, over 5952.18 frames. ], batch size: 52, lr: 4.07e-03
2024-08-06 19:06:51,461 INFO [trainer.py:765] (5/8) Epoch 21, batch 1600, train_loss[loss=2.915, NarTop10Accuracy=0.7458, over 7299.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.6996, over 5926.42 frames. ], batch size: 22, lr: 4.07e-03
2024-08-06 19:07:18,212 INFO [trainer.py:765] (5/8) Epoch 21, batch 1700, train_loss[loss=3.251, NarTop10Accuracy=0.6756, over 6726.00 frames. ], tot_loss[loss=3.132, NarTop10Accuracy=0.6992, over 5921.71 frames. ], batch size: 14, lr: 4.06e-03
2024-08-06 19:07:44,809 INFO [trainer.py:765] (5/8) Epoch 21, batch 1800, train_loss[loss=2.962, NarTop10Accuracy=0.7307, over 7272.00 frames. ], tot_loss[loss=3.138, NarTop10Accuracy=0.6976, over 5983.45 frames. ], batch size: 22, lr: 4.06e-03
2024-08-06 19:08:11,370 INFO [trainer.py:765] (5/8) Epoch 21, batch 1900, train_loss[loss=3.705, NarTop10Accuracy=0.595, over 6225.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.6955, over 6021.34 frames. ], batch size: 51, lr: 4.06e-03
2024-08-06 19:08:37,106 INFO [trainer.py:765] (5/8) Epoch 21, batch 2000, train_loss[loss=3.56, NarTop10Accuracy=0.6172, over 6360.00 frames. ], tot_loss[loss=3.137, NarTop10Accuracy=0.698, over 5997.22 frames. ], batch size: 52, lr: 4.05e-03
2024-08-06 19:09:02,507 INFO [trainer.py:765] (5/8) Epoch 21, batch 2100, train_loss[loss=2.82, NarTop10Accuracy=0.7527, over 3909.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6963, over 5968.95 frames. ], batch size: 4, lr: 4.05e-03
2024-08-06 19:09:27,891 INFO [trainer.py:765] (5/8) Epoch 21, batch 2200, train_loss[loss=2.877, NarTop10Accuracy=0.756, over 7590.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6947, over 6024.60 frames. ], batch size: 32, lr: 4.04e-03
2024-08-06 19:09:53,223 INFO [trainer.py:765] (5/8) Epoch 21, batch 2300, train_loss[loss=2.988, NarTop10Accuracy=0.7301, over 5634.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6922, over 6033.24 frames. ], batch size: 9, lr: 4.04e-03
2024-08-06 19:10:17,597 INFO [trainer.py:765] (5/8) Epoch 21, batch 2400, train_loss[loss=3.482, NarTop10Accuracy=0.62, over 5172.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.696, over 5785.57 frames. ], batch size: 7, lr: 4.04e-03
2024-08-06 19:10:37,229 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 19:10:45,275 INFO [trainer.py:811] (5/8) Epoch 21, validation: loss=2.971, NarTop10Accuracy=0.7316, over 1905321.00 frames. 
2024-08-06 19:10:45,276 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 19:10:45,741 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 21, batch 2500, train_loss[loss=3.212, NarTop10Accuracy=0.6758, over 4968.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7053, over 5483.29 frames. ], batch size: 7, lr: 4.03e-03
2024-08-06 19:11:08,850 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 19:12:09,054 INFO [trainer.py:765] (5/8) Epoch 22, batch 100, train_loss[loss=2.876, NarTop10Accuracy=0.7431, over 7434.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7082, over 2375.56 frames. ], batch size: 31, lr: 3.93e-03
2024-08-06 19:12:44,462 INFO [trainer.py:765] (5/8) Epoch 22, batch 200, train_loss[loss=3.215, NarTop10Accuracy=0.6848, over 6798.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7062, over 3859.90 frames. ], batch size: 17, lr: 3.93e-03
2024-08-06 19:13:14,533 INFO [trainer.py:765] (5/8) Epoch 22, batch 300, train_loss[loss=2.843, NarTop10Accuracy=0.754, over 7011.00 frames. ], tot_loss[loss=3.099, NarTop10Accuracy=0.7065, over 4664.13 frames. ], batch size: 22, lr: 3.93e-03
2024-08-06 19:13:49,229 INFO [trainer.py:765] (5/8) Epoch 22, batch 400, train_loss[loss=2.921, NarTop10Accuracy=0.7373, over 5079.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7085, over 5139.88 frames. ], batch size: 7, lr: 3.92e-03
2024-08-06 19:14:24,850 INFO [trainer.py:765] (5/8) Epoch 22, batch 500, train_loss[loss=3.174, NarTop10Accuracy=0.6883, over 6171.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7091, over 5418.63 frames. ], batch size: 11, lr: 3.92e-03
2024-08-06 19:14:55,701 INFO [trainer.py:765] (5/8) Epoch 22, batch 600, train_loss[loss=2.816, NarTop10Accuracy=0.7588, over 5889.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7026, over 5675.01 frames. ], batch size: 9, lr: 3.92e-03
2024-08-06 19:15:30,867 INFO [trainer.py:765] (5/8) Epoch 22, batch 700, train_loss[loss=3.324, NarTop10Accuracy=0.6592, over 5085.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7019, over 5736.75 frames. ], batch size: 6, lr: 3.91e-03
2024-08-06 19:16:10,664 INFO [trainer.py:765] (5/8) Epoch 22, batch 800, train_loss[loss=3.169, NarTop10Accuracy=0.6874, over 4962.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7027, over 5800.80 frames. ], batch size: 6, lr: 3.91e-03
2024-08-06 19:16:40,953 INFO [trainer.py:765] (5/8) Epoch 22, batch 900, train_loss[loss=2.874, NarTop10Accuracy=0.7535, over 6276.00 frames. ], tot_loss[loss=3.119, NarTop10Accuracy=0.7015, over 5815.09 frames. ], batch size: 13, lr: 3.90e-03
2024-08-06 19:17:16,434 INFO [trainer.py:765] (5/8) Epoch 22, batch 1000, train_loss[loss=3.066, NarTop10Accuracy=0.7066, over 6150.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7034, over 5899.18 frames. ], batch size: 13, lr: 3.90e-03
2024-08-06 19:17:52,086 INFO [trainer.py:765] (5/8) Epoch 22, batch 1100, train_loss[loss=2.923, NarTop10Accuracy=0.7388, over 6765.00 frames. ], tot_loss[loss=3.119, NarTop10Accuracy=0.7015, over 5925.76 frames. ], batch size: 17, lr: 3.90e-03
2024-08-06 19:18:25,927 INFO [trainer.py:765] (5/8) Epoch 22, batch 1200, train_loss[loss=2.838, NarTop10Accuracy=0.7574, over 7425.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7051, over 5926.21 frames. ], batch size: 31, lr: 3.89e-03
2024-08-06 19:19:01,253 INFO [trainer.py:765] (5/8) Epoch 22, batch 1300, train_loss[loss=2.877, NarTop10Accuracy=0.7529, over 5028.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.7052, over 5996.57 frames. ], batch size: 6, lr: 3.89e-03
2024-08-06 19:19:33,317 INFO [trainer.py:765] (5/8) Epoch 22, batch 1400, train_loss[loss=2.863, NarTop10Accuracy=0.7555, over 6075.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7028, over 6005.71 frames. ], batch size: 11, lr: 3.89e-03
2024-08-06 19:20:03,830 INFO [trainer.py:765] (5/8) Epoch 22, batch 1500, train_loss[loss=3.563, NarTop10Accuracy=0.6176, over 5763.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7038, over 5928.71 frames. ], batch size: 50, lr: 3.88e-03
2024-08-06 19:20:31,647 INFO [trainer.py:765] (5/8) Epoch 22, batch 1600, train_loss[loss=3.176, NarTop10Accuracy=0.6856, over 7194.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.701, over 5922.34 frames. ], batch size: 22, lr: 3.88e-03
2024-08-06 19:20:58,418 INFO [trainer.py:765] (5/8) Epoch 22, batch 1700, train_loss[loss=3.203, NarTop10Accuracy=0.68, over 6672.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7013, over 5907.42 frames. ], batch size: 14, lr: 3.88e-03
2024-08-06 19:21:25,010 INFO [trainer.py:765] (5/8) Epoch 22, batch 1800, train_loss[loss=3.019, NarTop10Accuracy=0.7239, over 7053.00 frames. ], tot_loss[loss=3.117, NarTop10Accuracy=0.7024, over 5981.65 frames. ], batch size: 22, lr: 3.87e-03
2024-08-06 19:21:51,372 INFO [trainer.py:765] (5/8) Epoch 22, batch 1900, train_loss[loss=3.007, NarTop10Accuracy=0.7229, over 6198.00 frames. ], tot_loss[loss=3.139, NarTop10Accuracy=0.6976, over 6030.06 frames. ], batch size: 50, lr: 3.87e-03
2024-08-06 19:21:53,109 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 19:22:01,088 INFO [trainer.py:811] (5/8) Epoch 22, validation: loss=3.009, NarTop10Accuracy=0.7241, over 1905321.00 frames. 
2024-08-06 19:22:01,089 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 19:22:01,575 INFO [optim.py:386] (5/8) 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 19:22:24,818 INFO [trainer.py:765] (5/8) Epoch 22, batch 2000, train_loss[loss=3.55, NarTop10Accuracy=0.62, over 6117.00 frames. ], tot_loss[loss=3.119, NarTop10Accuracy=0.7018, over 6020.88 frames. ], batch size: 51, lr: 3.87e-03
2024-08-06 19:22:50,041 INFO [trainer.py:765] (5/8) Epoch 22, batch 2100, train_loss[loss=3.148, NarTop10Accuracy=0.6987, over 4869.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7039, over 5993.93 frames. ], batch size: 5, lr: 3.86e-03
2024-08-06 19:23:15,229 INFO [trainer.py:765] (5/8) Epoch 22, batch 2200, train_loss[loss=3.109, NarTop10Accuracy=0.7067, over 7497.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7039, over 6017.02 frames. ], batch size: 32, lr: 3.86e-03
2024-08-06 19:23:40,314 INFO [trainer.py:765] (5/8) Epoch 22, batch 2300, train_loss[loss=3.029, NarTop10Accuracy=0.7164, over 5850.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.7006, over 6015.44 frames. ], batch size: 9, lr: 3.86e-03
2024-08-06 19:24:04,602 INFO [trainer.py:765] (5/8) Epoch 22, batch 2400, train_loss[loss=3.058, NarTop10Accuracy=0.7095, over 5124.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7016, over 5768.61 frames. ], batch size: 7, lr: 3.85e-03
2024-08-06 19:24:28,024 INFO [trainer.py:765] (5/8) Epoch 22, batch 2500, train_loss[loss=3.22, NarTop10Accuracy=0.6908, over 5055.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7036, over 5463.39 frames. ], batch size: 7, lr: 3.85e-03
2024-08-06 19:24:47,355 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 19:25:45,383 INFO [trainer.py:765] (5/8) Epoch 23, batch 100, train_loss[loss=2.91, NarTop10Accuracy=0.743, over 7416.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.699, over 2366.31 frames. ], batch size: 32, lr: 3.76e-03
2024-08-06 19:26:21,307 INFO [trainer.py:765] (5/8) Epoch 23, batch 200, train_loss[loss=3.394, NarTop10Accuracy=0.6394, over 6870.00 frames. ], tot_loss[loss=3.13, NarTop10Accuracy=0.6996, over 3862.21 frames. ], batch size: 17, lr: 3.76e-03
2024-08-06 19:26:57,601 INFO [trainer.py:765] (5/8) Epoch 23, batch 300, train_loss[loss=3.052, NarTop10Accuracy=0.716, over 7023.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.706, over 4657.41 frames. ], batch size: 22, lr: 3.75e-03
2024-08-06 19:27:26,539 INFO [trainer.py:765] (5/8) Epoch 23, batch 400, train_loss[loss=3.275, NarTop10Accuracy=0.6659, over 5106.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7043, over 5107.20 frames. ], batch size: 7, lr: 3.75e-03
2024-08-06 19:27:59,711 INFO [trainer.py:765] (5/8) Epoch 23, batch 500, train_loss[loss=3.484, NarTop10Accuracy=0.6306, over 6021.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7028, over 5372.95 frames. ], batch size: 11, lr: 3.75e-03
2024-08-06 19:28:35,881 INFO [trainer.py:765] (5/8) Epoch 23, batch 600, train_loss[loss=3.298, NarTop10Accuracy=0.6531, over 5703.00 frames. ], tot_loss[loss=3.104, NarTop10Accuracy=0.7051, over 5636.09 frames. ], batch size: 9, lr: 3.74e-03
2024-08-06 19:29:11,365 INFO [trainer.py:765] (5/8) Epoch 23, batch 700, train_loss[loss=3.234, NarTop10Accuracy=0.6746, over 5145.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7071, over 5729.04 frames. ], batch size: 6, lr: 3.74e-03
2024-08-06 19:29:43,611 INFO [trainer.py:765] (5/8) Epoch 23, batch 800, train_loss[loss=2.937, NarTop10Accuracy=0.7481, over 5082.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7039, over 5784.25 frames. ], batch size: 6, lr: 3.74e-03
2024-08-06 19:30:19,388 INFO [trainer.py:765] (5/8) Epoch 23, batch 900, train_loss[loss=3.278, NarTop10Accuracy=0.6661, over 6591.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.7053, over 5795.87 frames. ], batch size: 14, lr: 3.73e-03
2024-08-06 19:30:58,193 INFO [trainer.py:765] (5/8) Epoch 23, batch 1000, train_loss[loss=3.023, NarTop10Accuracy=0.7182, over 6213.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7069, over 5901.02 frames. ], batch size: 13, lr: 3.73e-03
2024-08-06 19:31:31,519 INFO [trainer.py:765] (5/8) Epoch 23, batch 1100, train_loss[loss=3.115, NarTop10Accuracy=0.707, over 6816.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7059, over 5918.94 frames. ], batch size: 17, lr: 3.73e-03
2024-08-06 19:32:08,516 INFO [trainer.py:765] (5/8) Epoch 23, batch 1200, train_loss[loss=3.022, NarTop10Accuracy=0.729, over 7473.00 frames. ], tot_loss[loss=3.107, NarTop10Accuracy=0.704, over 5927.81 frames. ], batch size: 31, lr: 3.72e-03
2024-08-06 19:32:46,935 INFO [trainer.py:765] (5/8) Epoch 23, batch 1300, train_loss[loss=3.069, NarTop10Accuracy=0.7049, over 5142.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7033, over 6004.18 frames. ], batch size: 6, lr: 3.72e-03
2024-08-06 19:32:56,401 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 19:33:04,722 INFO [trainer.py:811] (5/8) Epoch 23, validation: loss=2.893, NarTop10Accuracy=0.7468, over 1905321.00 frames. 
2024-08-06 19:33:04,723 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 19:33:05,262 INFO [optim.py:386] (5/8) 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 19:33:27,406 INFO [trainer.py:765] (5/8) Epoch 23, batch 1400, train_loss[loss=2.803, NarTop10Accuracy=0.7698, over 5964.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7029, over 6019.55 frames. ], batch size: 11, lr: 3.72e-03
2024-08-06 19:33:58,215 INFO [trainer.py:765] (5/8) Epoch 23, batch 1500, train_loss[loss=3.252, NarTop10Accuracy=0.6742, over 6126.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7069, over 5956.34 frames. ], batch size: 50, lr: 3.71e-03
2024-08-06 19:34:26,014 INFO [trainer.py:765] (5/8) Epoch 23, batch 1600, train_loss[loss=3.013, NarTop10Accuracy=0.7283, over 6981.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7053, over 5927.72 frames. ], batch size: 22, lr: 3.71e-03
2024-08-06 19:34:52,782 INFO [trainer.py:765] (5/8) Epoch 23, batch 1700, train_loss[loss=3.219, NarTop10Accuracy=0.6772, over 6195.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7013, over 5907.18 frames. ], batch size: 13, lr: 3.71e-03
2024-08-06 19:35:19,261 INFO [trainer.py:765] (5/8) Epoch 23, batch 1800, train_loss[loss=3.008, NarTop10Accuracy=0.7278, over 7041.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.703, over 5975.26 frames. ], batch size: 22, lr: 3.70e-03
2024-08-06 19:35:45,595 INFO [trainer.py:765] (5/8) Epoch 23, batch 1900, train_loss[loss=3.432, NarTop10Accuracy=0.645, over 5940.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7006, over 6013.25 frames. ], batch size: 50, lr: 3.70e-03
2024-08-06 19:36:11,170 INFO [trainer.py:765] (5/8) Epoch 23, batch 2000, train_loss[loss=3.626, NarTop10Accuracy=0.5982, over 5763.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7034, over 6002.02 frames. ], batch size: 51, lr: 3.70e-03
2024-08-06 19:36:36,517 INFO [trainer.py:765] (5/8) Epoch 23, batch 2100, train_loss[loss=3.319, NarTop10Accuracy=0.6582, over 4776.00 frames. ], tot_loss[loss=3.119, NarTop10Accuracy=0.7022, over 5973.59 frames. ], batch size: 5, lr: 3.69e-03
2024-08-06 19:37:01,907 INFO [trainer.py:765] (5/8) Epoch 23, batch 2200, train_loss[loss=3.05, NarTop10Accuracy=0.7133, over 7392.00 frames. ], tot_loss[loss=3.129, NarTop10Accuracy=0.6998, over 5999.41 frames. ], batch size: 32, lr: 3.69e-03
2024-08-06 19:37:27,059 INFO [trainer.py:765] (5/8) Epoch 23, batch 2300, train_loss[loss=2.931, NarTop10Accuracy=0.7394, over 6114.00 frames. ], tot_loss[loss=3.121, NarTop10Accuracy=0.702, over 6020.49 frames. ], batch size: 10, lr: 3.69e-03
2024-08-06 19:37:51,423 INFO [trainer.py:765] (5/8) Epoch 23, batch 2400, train_loss[loss=3.055, NarTop10Accuracy=0.7216, over 5196.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7003, over 5785.41 frames. ], batch size: 7, lr: 3.69e-03
2024-08-06 19:38:15,052 INFO [trainer.py:765] (5/8) Epoch 23, batch 2500, train_loss[loss=3.431, NarTop10Accuracy=0.6348, over 5190.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7051, over 5501.62 frames. ], batch size: 7, lr: 3.68e-03
2024-08-06 19:38:34,638 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 19:39:37,631 INFO [trainer.py:765] (5/8) Epoch 24, batch 100, train_loss[loss=3.449, NarTop10Accuracy=0.6302, over 7500.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7012, over 2358.82 frames. ], batch size: 31, lr: 3.60e-03
2024-08-06 19:40:10,189 INFO [trainer.py:765] (5/8) Epoch 24, batch 200, train_loss[loss=2.841, NarTop10Accuracy=0.7663, over 6711.00 frames. ], tot_loss[loss=3.104, NarTop10Accuracy=0.7047, over 3849.31 frames. ], batch size: 17, lr: 3.60e-03
2024-08-06 19:40:40,555 INFO [trainer.py:765] (5/8) Epoch 24, batch 300, train_loss[loss=2.848, NarTop10Accuracy=0.7597, over 7026.00 frames. ], tot_loss[loss=3.105, NarTop10Accuracy=0.7048, over 4667.62 frames. ], batch size: 22, lr: 3.59e-03
2024-08-06 19:41:18,233 INFO [trainer.py:765] (5/8) Epoch 24, batch 400, train_loss[loss=2.941, NarTop10Accuracy=0.7401, over 5763.00 frames. ], tot_loss[loss=3.104, NarTop10Accuracy=0.7051, over 5112.80 frames. ], batch size: 8, lr: 3.59e-03
2024-08-06 19:41:50,322 INFO [trainer.py:765] (5/8) Epoch 24, batch 500, train_loss[loss=2.959, NarTop10Accuracy=0.7332, over 5979.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7074, over 5391.18 frames. ], batch size: 11, lr: 3.59e-03
2024-08-06 19:42:21,451 INFO [trainer.py:765] (5/8) Epoch 24, batch 600, train_loss[loss=2.82, NarTop10Accuracy=0.7717, over 5745.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7071, over 5662.36 frames. ], batch size: 9, lr: 3.58e-03
2024-08-06 19:42:52,843 INFO [trainer.py:765] (5/8) Epoch 24, batch 700, train_loss[loss=2.959, NarTop10Accuracy=0.7317, over 5130.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7077, over 5726.05 frames. ], batch size: 6, lr: 3.58e-03
2024-08-06 19:43:17,381 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 19:43:25,410 INFO [trainer.py:811] (5/8) Epoch 24, validation: loss=3.021, NarTop10Accuracy=0.7204, over 1905321.00 frames. 
2024-08-06 19:43:25,411 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 19:43:28,562 INFO [optim.py:386] (5/8) Clipping_scale=2.0, grad-norm quartiles 1.744e+02 2.113e+02 2.282e+02 2.472e+02 2.357e+03, threshold=4.564e+02, percent-clipped=0.2
2024-08-06 19:43:40,814 INFO [trainer.py:765] (5/8) Epoch 24, batch 800, train_loss[loss=2.831, NarTop10Accuracy=0.7632, over 5070.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.709, over 5787.51 frames. ], batch size: 6, lr: 3.58e-03
2024-08-06 19:44:11,409 INFO [trainer.py:765] (5/8) Epoch 24, batch 900, train_loss[loss=2.908, NarTop10Accuracy=0.7469, over 6315.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.71, over 5830.84 frames. ], batch size: 13, lr: 3.57e-03
2024-08-06 19:44:47,489 INFO [trainer.py:765] (5/8) Epoch 24, batch 1000, train_loss[loss=3.23, NarTop10Accuracy=0.676, over 6636.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7066, over 5912.47 frames. ], batch size: 14, lr: 3.57e-03
2024-08-06 19:45:27,107 INFO [trainer.py:765] (5/8) Epoch 24, batch 1100, train_loss[loss=3.463, NarTop10Accuracy=0.6366, over 6813.00 frames. ], tot_loss[loss=3.107, NarTop10Accuracy=0.7045, over 5952.67 frames. ], batch size: 17, lr: 3.57e-03
2024-08-06 19:45:58,437 INFO [trainer.py:765] (5/8) Epoch 24, batch 1200, train_loss[loss=3.061, NarTop10Accuracy=0.7172, over 7290.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.7054, over 5929.47 frames. ], batch size: 31, lr: 3.57e-03
2024-08-06 19:46:30,294 INFO [trainer.py:765] (5/8) Epoch 24, batch 1300, train_loss[loss=3.413, NarTop10Accuracy=0.631, over 4317.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7061, over 5975.86 frames. ], batch size: 5, lr: 3.56e-03
2024-08-06 19:47:07,859 INFO [trainer.py:765] (5/8) Epoch 24, batch 1400, train_loss[loss=3.341, NarTop10Accuracy=0.6494, over 6189.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7033, over 6013.28 frames. ], batch size: 11, lr: 3.56e-03
2024-08-06 19:47:40,957 INFO [trainer.py:765] (5/8) Epoch 24, batch 1500, train_loss[loss=3.465, NarTop10Accuracy=0.6339, over 6465.00 frames. ], tot_loss[loss=3.129, NarTop10Accuracy=0.6997, over 5950.30 frames. ], batch size: 51, lr: 3.56e-03
2024-08-06 19:48:08,676 INFO [trainer.py:765] (5/8) Epoch 24, batch 1600, train_loss[loss=3.331, NarTop10Accuracy=0.6667, over 7038.00 frames. ], tot_loss[loss=3.132, NarTop10Accuracy=0.699, over 5911.12 frames. ], batch size: 22, lr: 3.55e-03
2024-08-06 19:48:35,267 INFO [trainer.py:765] (5/8) Epoch 24, batch 1700, train_loss[loss=2.837, NarTop10Accuracy=0.7565, over 6135.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7003, over 5889.01 frames. ], batch size: 13, lr: 3.55e-03
2024-08-06 19:49:01,638 INFO [trainer.py:765] (5/8) Epoch 24, batch 1800, train_loss[loss=2.921, NarTop10Accuracy=0.7419, over 6945.00 frames. ], tot_loss[loss=3.133, NarTop10Accuracy=0.6988, over 5956.75 frames. ], batch size: 22, lr: 3.55e-03
2024-08-06 19:49:28,042 INFO [trainer.py:765] (5/8) Epoch 24, batch 1900, train_loss[loss=3.563, NarTop10Accuracy=0.6169, over 6516.00 frames. ], tot_loss[loss=3.137, NarTop10Accuracy=0.6982, over 6019.60 frames. ], batch size: 50, lr: 3.55e-03
2024-08-06 19:49:53,533 INFO [trainer.py:765] (5/8) Epoch 24, batch 2000, train_loss[loss=3.618, NarTop10Accuracy=0.5983, over 5799.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7034, over 6001.97 frames. ], batch size: 51, lr: 3.54e-03
2024-08-06 19:50:18,819 INFO [trainer.py:765] (5/8) Epoch 24, batch 2100, train_loss[loss=2.78, NarTop10Accuracy=0.7648, over 4815.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7032, over 5982.28 frames. ], batch size: 5, lr: 3.54e-03
2024-08-06 19:50:43,942 INFO [trainer.py:765] (5/8) Epoch 24, batch 2200, train_loss[loss=3.448, NarTop10Accuracy=0.6389, over 6879.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.703, over 6022.01 frames. ], batch size: 31, lr: 3.54e-03
2024-08-06 19:51:09,025 INFO [trainer.py:765] (5/8) Epoch 24, batch 2300, train_loss[loss=3.036, NarTop10Accuracy=0.719, over 5748.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7033, over 6023.81 frames. ], batch size: 9, lr: 3.53e-03
2024-08-06 19:51:33,348 INFO [trainer.py:765] (5/8) Epoch 24, batch 2400, train_loss[loss=3.077, NarTop10Accuracy=0.7113, over 5034.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7055, over 5782.52 frames. ], batch size: 7, lr: 3.53e-03
2024-08-06 19:51:56,783 INFO [trainer.py:765] (5/8) Epoch 24, batch 2500, train_loss[loss=2.734, NarTop10Accuracy=0.7754, over 5127.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7108, over 5479.80 frames. ], batch size: 7, lr: 3.53e-03
2024-08-06 19:52:17,079 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 19:53:22,197 INFO [trainer.py:765] (5/8) Epoch 25, batch 100, train_loss[loss=3.397, NarTop10Accuracy=0.6354, over 7188.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7091, over 2367.83 frames. ], batch size: 31, lr: 3.45e-03
2024-08-06 19:53:47,262 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 19:53:55,329 INFO [trainer.py:811] (5/8) Epoch 25, validation: loss=2.96, NarTop10Accuracy=0.7332, over 1905321.00 frames. 
2024-08-06 19:53:55,330 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 19:53:55,916 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 25, batch 200, train_loss[loss=3.024, NarTop10Accuracy=0.7261, over 6966.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7084, over 3855.18 frames. ], batch size: 17, lr: 3.45e-03
2024-08-06 19:54:35,647 INFO [trainer.py:765] (5/8) Epoch 25, batch 300, train_loss[loss=3.286, NarTop10Accuracy=0.6656, over 7383.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7087, over 4641.88 frames. ], batch size: 23, lr: 3.45e-03
2024-08-06 19:55:12,958 INFO [trainer.py:765] (5/8) Epoch 25, batch 400, train_loss[loss=3.151, NarTop10Accuracy=0.6999, over 5190.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7077, over 5095.67 frames. ], batch size: 7, lr: 3.44e-03
2024-08-06 19:55:43,738 INFO [trainer.py:765] (5/8) Epoch 25, batch 500, train_loss[loss=2.875, NarTop10Accuracy=0.755, over 6096.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7094, over 5384.09 frames. ], batch size: 11, lr: 3.44e-03
2024-08-06 19:56:14,815 INFO [trainer.py:765] (5/8) Epoch 25, batch 600, train_loss[loss=2.861, NarTop10Accuracy=0.7536, over 5649.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7099, over 5650.68 frames. ], batch size: 9, lr: 3.44e-03
2024-08-06 19:56:55,496 INFO [trainer.py:765] (5/8) Epoch 25, batch 700, train_loss[loss=2.8, NarTop10Accuracy=0.762, over 4167.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7115, over 5709.96 frames. ], batch size: 5, lr: 3.43e-03
2024-08-06 19:57:30,136 INFO [trainer.py:765] (5/8) Epoch 25, batch 800, train_loss[loss=2.91, NarTop10Accuracy=0.7334, over 4989.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7092, over 5769.51 frames. ], batch size: 6, lr: 3.43e-03
2024-08-06 19:58:00,679 INFO [trainer.py:765] (5/8) Epoch 25, batch 900, train_loss[loss=3.076, NarTop10Accuracy=0.7089, over 6564.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7115, over 5805.04 frames. ], batch size: 14, lr: 3.43e-03
2024-08-06 19:58:37,639 INFO [trainer.py:765] (5/8) Epoch 25, batch 1000, train_loss[loss=2.891, NarTop10Accuracy=0.7502, over 6189.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7083, over 5912.62 frames. ], batch size: 13, lr: 3.43e-03
2024-08-06 19:59:14,855 INFO [trainer.py:765] (5/8) Epoch 25, batch 1100, train_loss[loss=3.444, NarTop10Accuracy=0.638, over 6978.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7071, over 5950.72 frames. ], batch size: 17, lr: 3.42e-03
2024-08-06 19:59:49,039 INFO [trainer.py:765] (5/8) Epoch 25, batch 1200, train_loss[loss=3.288, NarTop10Accuracy=0.6717, over 7206.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7074, over 5939.55 frames. ], batch size: 31, lr: 3.42e-03
2024-08-06 20:00:25,598 INFO [trainer.py:765] (5/8) Epoch 25, batch 1300, train_loss[loss=2.82, NarTop10Accuracy=0.7642, over 5040.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7079, over 6002.56 frames. ], batch size: 6, lr: 3.42e-03
2024-08-06 20:01:02,016 INFO [trainer.py:765] (5/8) Epoch 25, batch 1400, train_loss[loss=2.87, NarTop10Accuracy=0.7582, over 6114.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7096, over 6018.45 frames. ], batch size: 11, lr: 3.42e-03
2024-08-06 20:01:32,823 INFO [trainer.py:765] (5/8) Epoch 25, batch 1500, train_loss[loss=3.324, NarTop10Accuracy=0.6615, over 5550.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7086, over 5956.85 frames. ], batch size: 50, lr: 3.41e-03
2024-08-06 20:02:00,624 INFO [trainer.py:765] (5/8) Epoch 25, batch 1600, train_loss[loss=2.989, NarTop10Accuracy=0.7386, over 7281.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7084, over 5928.60 frames. ], batch size: 23, lr: 3.41e-03
2024-08-06 20:02:27,359 INFO [trainer.py:765] (5/8) Epoch 25, batch 1700, train_loss[loss=3.015, NarTop10Accuracy=0.7072, over 6648.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7076, over 5921.54 frames. ], batch size: 14, lr: 3.41e-03
2024-08-06 20:02:53,853 INFO [trainer.py:765] (5/8) Epoch 25, batch 1800, train_loss[loss=3.385, NarTop10Accuracy=0.6495, over 7326.00 frames. ], tot_loss[loss=3.099, NarTop10Accuracy=0.7056, over 5986.35 frames. ], batch size: 23, lr: 3.40e-03
2024-08-06 20:03:20,340 INFO [trainer.py:765] (5/8) Epoch 25, batch 1900, train_loss[loss=3.262, NarTop10Accuracy=0.677, over 5970.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.704, over 6019.84 frames. ], batch size: 50, lr: 3.40e-03
2024-08-06 20:03:45,935 INFO [trainer.py:765] (5/8) Epoch 25, batch 2000, train_loss[loss=3.552, NarTop10Accuracy=0.6082, over 5904.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.7004, over 5982.67 frames. ], batch size: 52, lr: 3.40e-03
2024-08-06 20:04:11,245 INFO [trainer.py:765] (5/8) Epoch 25, batch 2100, train_loss[loss=3.036, NarTop10Accuracy=0.7283, over 4794.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.703, over 5974.78 frames. ], batch size: 5, lr: 3.40e-03
2024-08-06 20:04:31,409 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 20:04:39,343 INFO [trainer.py:811] (5/8) Epoch 25, validation: loss=2.999, NarTop10Accuracy=0.7251, over 1905321.00 frames. 
2024-08-06 20:04:39,344 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 20:04:39,840 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 25, batch 2200, train_loss[loss=3.291, NarTop10Accuracy=0.6661, over 7065.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7024, over 5999.43 frames. ], batch size: 31, lr: 3.39e-03
2024-08-06 20:05:09,645 INFO [trainer.py:765] (5/8) Epoch 25, batch 2300, train_loss[loss=3.159, NarTop10Accuracy=0.6882, over 5697.00 frames. ], tot_loss[loss=3.117, NarTop10Accuracy=0.7024, over 6004.17 frames. ], batch size: 9, lr: 3.39e-03
2024-08-06 20:05:34,141 INFO [trainer.py:765] (5/8) Epoch 25, batch 2400, train_loss[loss=2.779, NarTop10Accuracy=0.7653, over 5265.00 frames. ], tot_loss[loss=3.101, NarTop10Accuracy=0.7055, over 5763.67 frames. ], batch size: 7, lr: 3.39e-03
2024-08-06 20:05:57,845 INFO [trainer.py:765] (5/8) Epoch 25, batch 2500, train_loss[loss=2.732, NarTop10Accuracy=0.7778, over 5061.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7107, over 5466.07 frames. ], batch size: 7, lr: 3.39e-03
2024-08-06 20:06:17,603 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 20:07:19,304 INFO [trainer.py:765] (5/8) Epoch 26, batch 100, train_loss[loss=3.105, NarTop10Accuracy=0.7073, over 7434.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7055, over 2363.67 frames. ], batch size: 32, lr: 3.32e-03
2024-08-06 20:07:52,382 INFO [trainer.py:765] (5/8) Epoch 26, batch 200, train_loss[loss=2.827, NarTop10Accuracy=0.7627, over 6921.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7063, over 3846.93 frames. ], batch size: 17, lr: 3.31e-03
2024-08-06 20:08:24,733 INFO [trainer.py:765] (5/8) Epoch 26, batch 300, train_loss[loss=2.977, NarTop10Accuracy=0.7314, over 7074.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7083, over 4629.92 frames. ], batch size: 22, lr: 3.31e-03
2024-08-06 20:08:58,184 INFO [trainer.py:765] (5/8) Epoch 26, batch 400, train_loss[loss=3.096, NarTop10Accuracy=0.6939, over 5013.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7073, over 5101.09 frames. ], batch size: 7, lr: 3.31e-03
2024-08-06 20:09:33,147 INFO [trainer.py:765] (5/8) Epoch 26, batch 500, train_loss[loss=2.835, NarTop10Accuracy=0.7653, over 6063.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7062, over 5377.08 frames. ], batch size: 11, lr: 3.30e-03
2024-08-06 20:10:03,890 INFO [trainer.py:765] (5/8) Epoch 26, batch 600, train_loss[loss=2.881, NarTop10Accuracy=0.7489, over 5640.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7117, over 5642.51 frames. ], batch size: 9, lr: 3.30e-03
2024-08-06 20:10:39,872 INFO [trainer.py:765] (5/8) Epoch 26, batch 700, train_loss[loss=3.238, NarTop10Accuracy=0.6797, over 4194.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7077, over 5717.53 frames. ], batch size: 5, lr: 3.30e-03
2024-08-06 20:11:19,060 INFO [trainer.py:765] (5/8) Epoch 26, batch 800, train_loss[loss=3.075, NarTop10Accuracy=0.7157, over 5082.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7084, over 5769.39 frames. ], batch size: 6, lr: 3.30e-03
2024-08-06 20:11:49,315 INFO [trainer.py:765] (5/8) Epoch 26, batch 900, train_loss[loss=2.77, NarTop10Accuracy=0.7801, over 6195.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7082, over 5803.80 frames. ], batch size: 13, lr: 3.29e-03
2024-08-06 20:12:25,972 INFO [trainer.py:765] (5/8) Epoch 26, batch 1000, train_loss[loss=2.77, NarTop10Accuracy=0.7771, over 6780.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7069, over 5879.98 frames. ], batch size: 14, lr: 3.29e-03
2024-08-06 20:13:06,376 INFO [trainer.py:765] (5/8) Epoch 26, batch 1100, train_loss[loss=3.442, NarTop10Accuracy=0.6346, over 6768.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7049, over 5921.87 frames. ], batch size: 17, lr: 3.29e-03
2024-08-06 20:13:37,535 INFO [trainer.py:765] (5/8) Epoch 26, batch 1200, train_loss[loss=3.384, NarTop10Accuracy=0.6551, over 7425.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7084, over 5927.27 frames. ], batch size: 32, lr: 3.29e-03
2024-08-06 20:14:13,695 INFO [trainer.py:765] (5/8) Epoch 26, batch 1300, train_loss[loss=2.954, NarTop10Accuracy=0.7376, over 4284.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7091, over 5980.15 frames. ], batch size: 5, lr: 3.28e-03
2024-08-06 20:14:50,538 INFO [trainer.py:765] (5/8) Epoch 26, batch 1400, train_loss[loss=2.86, NarTop10Accuracy=0.7583, over 6114.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7085, over 5982.40 frames. ], batch size: 11, lr: 3.28e-03
2024-08-06 20:15:21,155 INFO [trainer.py:765] (5/8) Epoch 26, batch 1500, train_loss[loss=3.155, NarTop10Accuracy=0.7004, over 6387.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7074, over 5933.23 frames. ], batch size: 50, lr: 3.28e-03
2024-08-06 20:15:48,979 INFO [trainer.py:765] (5/8) Epoch 26, batch 1600, train_loss[loss=2.956, NarTop10Accuracy=0.7318, over 7230.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7093, over 5929.18 frames. ], batch size: 22, lr: 3.28e-03
2024-08-06 20:15:50,002 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 20:15:58,239 INFO [trainer.py:811] (5/8) Epoch 26, validation: loss=2.899, NarTop10Accuracy=0.7457, over 1905321.00 frames. 
2024-08-06 20:15:58,239 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 20:15:58,779 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 26, batch 1700, train_loss[loss=3.152, NarTop10Accuracy=0.6914, over 6300.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.711, over 5903.85 frames. ], batch size: 13, lr: 3.28e-03
2024-08-06 20:16:50,426 INFO [trainer.py:765] (5/8) Epoch 26, batch 1800, train_loss[loss=2.739, NarTop10Accuracy=0.7693, over 7176.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7089, over 5971.45 frames. ], batch size: 22, lr: 3.27e-03
2024-08-06 20:17:16,840 INFO [trainer.py:765] (5/8) Epoch 26, batch 1900, train_loss[loss=3.045, NarTop10Accuracy=0.7175, over 5481.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7069, over 6014.47 frames. ], batch size: 50, lr: 3.27e-03
2024-08-06 20:17:42,379 INFO [trainer.py:765] (5/8) Epoch 26, batch 2000, train_loss[loss=3.713, NarTop10Accuracy=0.5721, over 6243.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7066, over 6002.80 frames. ], batch size: 50, lr: 3.27e-03
2024-08-06 20:18:07,563 INFO [trainer.py:765] (5/8) Epoch 26, batch 2100, train_loss[loss=3.037, NarTop10Accuracy=0.7153, over 4827.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7066, over 5957.19 frames. ], batch size: 5, lr: 3.27e-03
2024-08-06 20:18:32,776 INFO [trainer.py:765] (5/8) Epoch 26, batch 2200, train_loss[loss=2.907, NarTop10Accuracy=0.7408, over 7329.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.707, over 6009.78 frames. ], batch size: 31, lr: 3.26e-03
2024-08-06 20:18:57,897 INFO [trainer.py:765] (5/8) Epoch 26, batch 2300, train_loss[loss=3.167, NarTop10Accuracy=0.6934, over 5691.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7057, over 6016.23 frames. ], batch size: 9, lr: 3.26e-03
2024-08-06 20:19:22,205 INFO [trainer.py:765] (5/8) Epoch 26, batch 2400, train_loss[loss=2.837, NarTop10Accuracy=0.758, over 5055.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7114, over 5767.10 frames. ], batch size: 7, lr: 3.26e-03
2024-08-06 20:19:45,651 INFO [trainer.py:765] (5/8) Epoch 26, batch 2500, train_loss[loss=2.762, NarTop10Accuracy=0.7801, over 5220.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.715, over 5470.58 frames. ], batch size: 7, lr: 3.26e-03
2024-08-06 20:20:06,065 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 20:21:04,874 INFO [trainer.py:765] (5/8) Epoch 27, batch 100, train_loss[loss=3.278, NarTop10Accuracy=0.6745, over 7128.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7097, over 2354.28 frames. ], batch size: 31, lr: 3.19e-03
2024-08-06 20:21:39,783 INFO [trainer.py:765] (5/8) Epoch 27, batch 200, train_loss[loss=2.834, NarTop10Accuracy=0.7727, over 6822.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7095, over 3852.04 frames. ], batch size: 17, lr: 3.19e-03
2024-08-06 20:22:13,049 INFO [trainer.py:765] (5/8) Epoch 27, batch 300, train_loss[loss=2.726, NarTop10Accuracy=0.7797, over 6993.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7098, over 4653.19 frames. ], batch size: 22, lr: 3.18e-03
2024-08-06 20:22:43,557 INFO [trainer.py:765] (5/8) Epoch 27, batch 400, train_loss[loss=2.856, NarTop10Accuracy=0.7539, over 5082.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7125, over 5100.45 frames. ], batch size: 7, lr: 3.18e-03
2024-08-06 20:23:18,084 INFO [trainer.py:765] (5/8) Epoch 27, batch 500, train_loss[loss=2.82, NarTop10Accuracy=0.7676, over 6150.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7158, over 5398.86 frames. ], batch size: 11, lr: 3.18e-03
2024-08-06 20:23:51,435 INFO [trainer.py:765] (5/8) Epoch 27, batch 600, train_loss[loss=3.19, NarTop10Accuracy=0.684, over 5829.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7159, over 5657.77 frames. ], batch size: 9, lr: 3.18e-03
2024-08-06 20:24:24,975 INFO [trainer.py:765] (5/8) Epoch 27, batch 700, train_loss[loss=2.869, NarTop10Accuracy=0.7471, over 4257.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7164, over 5744.15 frames. ], batch size: 5, lr: 3.18e-03
2024-08-06 20:25:03,407 INFO [trainer.py:765] (5/8) Epoch 27, batch 800, train_loss[loss=3.265, NarTop10Accuracy=0.6753, over 5049.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7124, over 5801.26 frames. ], batch size: 6, lr: 3.17e-03
2024-08-06 20:25:34,176 INFO [trainer.py:765] (5/8) Epoch 27, batch 900, train_loss[loss=3.34, NarTop10Accuracy=0.6593, over 6228.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7129, over 5811.34 frames. ], batch size: 13, lr: 3.17e-03
2024-08-06 20:26:10,097 INFO [trainer.py:765] (5/8) Epoch 27, batch 1000, train_loss[loss=2.767, NarTop10Accuracy=0.7678, over 6612.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.712, over 5906.58 frames. ], batch size: 14, lr: 3.17e-03
2024-08-06 20:26:18,314 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 20:26:26,346 INFO [trainer.py:811] (5/8) Epoch 27, validation: loss=2.95, NarTop10Accuracy=0.735, over 1905321.00 frames. 
2024-08-06 20:26:26,347 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 20:26:26,878 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 27, batch 1100, train_loss[loss=3.051, NarTop10Accuracy=0.7097, over 6768.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7111, over 5927.47 frames. ], batch size: 17, lr: 3.17e-03
2024-08-06 20:27:24,544 INFO [trainer.py:765] (5/8) Epoch 27, batch 1200, train_loss[loss=2.878, NarTop10Accuracy=0.7593, over 7176.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7115, over 5919.78 frames. ], batch size: 32, lr: 3.16e-03
2024-08-06 20:27:58,567 INFO [trainer.py:765] (5/8) Epoch 27, batch 1300, train_loss[loss=2.799, NarTop10Accuracy=0.7624, over 4302.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7125, over 5989.24 frames. ], batch size: 5, lr: 3.16e-03
2024-08-06 20:28:36,744 INFO [trainer.py:765] (5/8) Epoch 27, batch 1400, train_loss[loss=3.379, NarTop10Accuracy=0.6516, over 6051.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7081, over 5998.10 frames. ], batch size: 11, lr: 3.16e-03
2024-08-06 20:29:04,632 INFO [trainer.py:765] (5/8) Epoch 27, batch 1500, train_loss[loss=3.068, NarTop10Accuracy=0.714, over 6081.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7096, over 5942.20 frames. ], batch size: 50, lr: 3.16e-03
2024-08-06 20:29:32,361 INFO [trainer.py:765] (5/8) Epoch 27, batch 1600, train_loss[loss=2.888, NarTop10Accuracy=0.7541, over 7278.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7078, over 5908.62 frames. ], batch size: 22, lr: 3.15e-03
2024-08-06 20:29:58,977 INFO [trainer.py:765] (5/8) Epoch 27, batch 1700, train_loss[loss=3.225, NarTop10Accuracy=0.6745, over 6279.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7094, over 5885.89 frames. ], batch size: 13, lr: 3.15e-03
2024-08-06 20:30:25,463 INFO [trainer.py:765] (5/8) Epoch 27, batch 1800, train_loss[loss=3.516, NarTop10Accuracy=0.6199, over 7173.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7085, over 5974.17 frames. ], batch size: 22, lr: 3.15e-03
2024-08-06 20:30:51,844 INFO [trainer.py:765] (5/8) Epoch 27, batch 1900, train_loss[loss=3.049, NarTop10Accuracy=0.7108, over 6582.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7088, over 6008.19 frames. ], batch size: 50, lr: 3.15e-03
2024-08-06 20:31:17,390 INFO [trainer.py:765] (5/8) Epoch 27, batch 2000, train_loss[loss=3.158, NarTop10Accuracy=0.6982, over 6312.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7108, over 5985.53 frames. ], batch size: 50, lr: 3.15e-03
2024-08-06 20:31:42,659 INFO [trainer.py:765] (5/8) Epoch 27, batch 2100, train_loss[loss=2.787, NarTop10Accuracy=0.7592, over 3969.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7104, over 5956.10 frames. ], batch size: 4, lr: 3.14e-03
2024-08-06 20:32:07,804 INFO [trainer.py:765] (5/8) Epoch 27, batch 2200, train_loss[loss=3.253, NarTop10Accuracy=0.6776, over 7260.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7093, over 6002.06 frames. ], batch size: 32, lr: 3.14e-03
2024-08-06 20:32:32,941 INFO [trainer.py:765] (5/8) Epoch 27, batch 2300, train_loss[loss=2.965, NarTop10Accuracy=0.7353, over 5640.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7086, over 6008.61 frames. ], batch size: 9, lr: 3.14e-03
2024-08-06 20:32:57,246 INFO [trainer.py:765] (5/8) Epoch 27, batch 2400, train_loss[loss=2.844, NarTop10Accuracy=0.7604, over 5073.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.709, over 5756.18 frames. ], batch size: 7, lr: 3.14e-03
2024-08-06 20:33:20,615 INFO [trainer.py:765] (5/8) Epoch 27, batch 2500, train_loss[loss=3.436, NarTop10Accuracy=0.6338, over 5262.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7154, over 5468.57 frames. ], batch size: 7, lr: 3.13e-03
2024-08-06 20:33:40,589 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 20:34:35,831 INFO [trainer.py:765] (5/8) Epoch 28, batch 100, train_loss[loss=2.918, NarTop10Accuracy=0.7483, over 7158.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7096, over 2354.87 frames. ], batch size: 31, lr: 3.07e-03
2024-08-06 20:35:07,393 INFO [trainer.py:765] (5/8) Epoch 28, batch 200, train_loss[loss=2.816, NarTop10Accuracy=0.7555, over 6840.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7091, over 3843.92 frames. ], batch size: 17, lr: 3.07e-03
2024-08-06 20:35:45,422 INFO [trainer.py:765] (5/8) Epoch 28, batch 300, train_loss[loss=3.082, NarTop10Accuracy=0.7069, over 7152.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7113, over 4662.60 frames. ], batch size: 22, lr: 3.07e-03
2024-08-06 20:36:15,865 INFO [trainer.py:765] (5/8) Epoch 28, batch 400, train_loss[loss=3.17, NarTop10Accuracy=0.6808, over 5115.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7075, over 5120.88 frames. ], batch size: 7, lr: 3.07e-03
2024-08-06 20:36:32,406 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 20:36:40,530 INFO [trainer.py:811] (5/8) Epoch 28, validation: loss=2.963, NarTop10Accuracy=0.7327, over 1905321.00 frames. 
2024-08-06 20:36:40,531 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 20:36:41,102 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 28, batch 500, train_loss[loss=3.122, NarTop10Accuracy=0.6946, over 6084.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7101, over 5387.56 frames. ], batch size: 11, lr: 3.06e-03
2024-08-06 20:37:29,463 INFO [trainer.py:765] (5/8) Epoch 28, batch 600, train_loss[loss=2.989, NarTop10Accuracy=0.73, over 5784.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7104, over 5661.49 frames. ], batch size: 9, lr: 3.06e-03
2024-08-06 20:38:08,891 INFO [trainer.py:765] (5/8) Epoch 28, batch 700, train_loss[loss=2.988, NarTop10Accuracy=0.7311, over 5169.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7084, over 5730.43 frames. ], batch size: 6, lr: 3.06e-03
2024-08-06 20:38:42,489 INFO [trainer.py:765] (5/8) Epoch 28, batch 800, train_loss[loss=2.872, NarTop10Accuracy=0.7543, over 4992.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.714, over 5779.97 frames. ], batch size: 6, lr: 3.06e-03
2024-08-06 20:39:15,507 INFO [trainer.py:765] (5/8) Epoch 28, batch 900, train_loss[loss=3.241, NarTop10Accuracy=0.6732, over 6195.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7136, over 5789.44 frames. ], batch size: 13, lr: 3.06e-03
2024-08-06 20:39:53,240 INFO [trainer.py:765] (5/8) Epoch 28, batch 1000, train_loss[loss=3.306, NarTop10Accuracy=0.6598, over 6165.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7139, over 5901.56 frames. ], batch size: 13, lr: 3.05e-03
2024-08-06 20:40:25,867 INFO [trainer.py:765] (5/8) Epoch 28, batch 1100, train_loss[loss=2.818, NarTop10Accuracy=0.7612, over 6834.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7101, over 5931.22 frames. ], batch size: 17, lr: 3.05e-03
2024-08-06 20:40:59,419 INFO [trainer.py:765] (5/8) Epoch 28, batch 1200, train_loss[loss=3.485, NarTop10Accuracy=0.6275, over 7275.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7084, over 5935.42 frames. ], batch size: 31, lr: 3.05e-03
2024-08-06 20:41:38,681 INFO [trainer.py:765] (5/8) Epoch 28, batch 1300, train_loss[loss=3.148, NarTop10Accuracy=0.696, over 5097.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7098, over 5995.96 frames. ], batch size: 6, lr: 3.05e-03
2024-08-06 20:42:13,047 INFO [trainer.py:765] (5/8) Epoch 28, batch 1400, train_loss[loss=2.781, NarTop10Accuracy=0.7612, over 6030.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7087, over 6020.95 frames. ], batch size: 11, lr: 3.04e-03
2024-08-06 20:42:43,171 INFO [trainer.py:765] (5/8) Epoch 28, batch 1500, train_loss[loss=3.556, NarTop10Accuracy=0.6101, over 6615.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7122, over 5944.91 frames. ], batch size: 50, lr: 3.04e-03
2024-08-06 20:43:11,081 INFO [trainer.py:765] (5/8) Epoch 28, batch 1600, train_loss[loss=2.924, NarTop10Accuracy=0.7459, over 6906.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7115, over 5921.61 frames. ], batch size: 22, lr: 3.04e-03
2024-08-06 20:43:37,785 INFO [trainer.py:765] (5/8) Epoch 28, batch 1700, train_loss[loss=3.074, NarTop10Accuracy=0.7129, over 6594.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7105, over 5916.43 frames. ], batch size: 14, lr: 3.04e-03
2024-08-06 20:44:04,326 INFO [trainer.py:765] (5/8) Epoch 28, batch 1800, train_loss[loss=3.078, NarTop10Accuracy=0.7102, over 7215.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7108, over 5983.80 frames. ], batch size: 22, lr: 3.04e-03
2024-08-06 20:44:30,757 INFO [trainer.py:765] (5/8) Epoch 28, batch 1900, train_loss[loss=3.085, NarTop10Accuracy=0.7014, over 6780.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7111, over 6019.82 frames. ], batch size: 51, lr: 3.03e-03
2024-08-06 20:44:56,328 INFO [trainer.py:765] (5/8) Epoch 28, batch 2000, train_loss[loss=2.994, NarTop10Accuracy=0.729, over 5940.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7143, over 5995.33 frames. ], batch size: 51, lr: 3.03e-03
2024-08-06 20:45:21,651 INFO [trainer.py:765] (5/8) Epoch 28, batch 2100, train_loss[loss=3.007, NarTop10Accuracy=0.7154, over 3981.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7145, over 5962.26 frames. ], batch size: 4, lr: 3.03e-03
2024-08-06 20:45:47,076 INFO [trainer.py:765] (5/8) Epoch 28, batch 2200, train_loss[loss=3.026, NarTop10Accuracy=0.7318, over 7410.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7122, over 6003.41 frames. ], batch size: 32, lr: 3.03e-03
2024-08-06 20:46:12,308 INFO [trainer.py:765] (5/8) Epoch 28, batch 2300, train_loss[loss=3.389, NarTop10Accuracy=0.6396, over 5706.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7083, over 6011.26 frames. ], batch size: 9, lr: 3.03e-03
2024-08-06 20:46:36,807 INFO [trainer.py:765] (5/8) Epoch 28, batch 2400, train_loss[loss=2.922, NarTop10Accuracy=0.7474, over 5169.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7086, over 5799.48 frames. ], batch size: 7, lr: 3.02e-03
2024-08-06 20:46:48,595 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 20:46:56,604 INFO [trainer.py:811] (5/8) Epoch 28, validation: loss=2.931, NarTop10Accuracy=0.7396, over 1905321.00 frames. 
2024-08-06 20:46:56,605 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 20:46:57,082 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 28, batch 2500, train_loss[loss=3.081, NarTop10Accuracy=0.7258, over 5349.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7131, over 5488.33 frames. ], batch size: 7, lr: 3.02e-03
2024-08-06 20:47:28,163 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 20:48:21,053 INFO [trainer.py:765] (5/8) Epoch 29, batch 100, train_loss[loss=2.909, NarTop10Accuracy=0.7379, over 7149.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7097, over 2368.64 frames. ], batch size: 31, lr: 2.96e-03
2024-08-06 20:48:53,405 INFO [trainer.py:765] (5/8) Epoch 29, batch 200, train_loss[loss=3.39, NarTop10Accuracy=0.6467, over 6660.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7161, over 3856.85 frames. ], batch size: 17, lr: 2.96e-03
2024-08-06 20:49:27,476 INFO [trainer.py:765] (5/8) Epoch 29, batch 300, train_loss[loss=3.238, NarTop10Accuracy=0.6749, over 7317.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7179, over 4668.97 frames. ], batch size: 23, lr: 2.96e-03
2024-08-06 20:49:56,052 INFO [trainer.py:765] (5/8) Epoch 29, batch 400, train_loss[loss=3.389, NarTop10Accuracy=0.6525, over 5220.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7126, over 5110.89 frames. ], batch size: 7, lr: 2.96e-03
2024-08-06 20:50:29,435 INFO [trainer.py:765] (5/8) Epoch 29, batch 500, train_loss[loss=3.184, NarTop10Accuracy=0.6877, over 6084.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7153, over 5394.92 frames. ], batch size: 11, lr: 2.96e-03
2024-08-06 20:51:00,023 INFO [trainer.py:765] (5/8) Epoch 29, batch 600, train_loss[loss=2.95, NarTop10Accuracy=0.7416, over 5787.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7151, over 5643.78 frames. ], batch size: 9, lr: 2.95e-03
2024-08-06 20:51:35,677 INFO [trainer.py:765] (5/8) Epoch 29, batch 700, train_loss[loss=2.748, NarTop10Accuracy=0.777, over 5058.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7108, over 5740.25 frames. ], batch size: 6, lr: 2.95e-03
2024-08-06 20:52:10,724 INFO [trainer.py:765] (5/8) Epoch 29, batch 800, train_loss[loss=2.709, NarTop10Accuracy=0.7831, over 5085.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7121, over 5792.18 frames. ], batch size: 6, lr: 2.95e-03
2024-08-06 20:52:40,742 INFO [trainer.py:765] (5/8) Epoch 29, batch 900, train_loss[loss=2.747, NarTop10Accuracy=0.7771, over 6657.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7105, over 5805.75 frames. ], batch size: 14, lr: 2.95e-03
2024-08-06 20:53:16,861 INFO [trainer.py:765] (5/8) Epoch 29, batch 1000, train_loss[loss=3.309, NarTop10Accuracy=0.6538, over 6717.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7087, over 5913.58 frames. ], batch size: 14, lr: 2.95e-03
2024-08-06 20:53:52,902 INFO [trainer.py:765] (5/8) Epoch 29, batch 1100, train_loss[loss=3.226, NarTop10Accuracy=0.6751, over 6837.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.708, over 5945.46 frames. ], batch size: 17, lr: 2.94e-03
2024-08-06 20:54:23,690 INFO [trainer.py:765] (5/8) Epoch 29, batch 1200, train_loss[loss=3.103, NarTop10Accuracy=0.7066, over 7155.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7084, over 5923.74 frames. ], batch size: 31, lr: 2.94e-03
2024-08-06 20:55:01,428 INFO [trainer.py:765] (5/8) Epoch 29, batch 1300, train_loss[loss=2.806, NarTop10Accuracy=0.7564, over 5127.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7093, over 5978.63 frames. ], batch size: 6, lr: 2.94e-03
2024-08-06 20:55:32,557 INFO [trainer.py:765] (5/8) Epoch 29, batch 1400, train_loss[loss=3.477, NarTop10Accuracy=0.6308, over 6072.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7082, over 6005.09 frames. ], batch size: 11, lr: 2.94e-03
2024-08-06 20:56:04,359 INFO [trainer.py:765] (5/8) Epoch 29, batch 1500, train_loss[loss=3.369, NarTop10Accuracy=0.6489, over 5988.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7091, over 5970.45 frames. ], batch size: 52, lr: 2.94e-03
2024-08-06 20:56:32,041 INFO [trainer.py:765] (5/8) Epoch 29, batch 1600, train_loss[loss=3.321, NarTop10Accuracy=0.6666, over 6966.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7073, over 5944.09 frames. ], batch size: 22, lr: 2.93e-03
2024-08-06 20:56:58,639 INFO [trainer.py:765] (5/8) Epoch 29, batch 1700, train_loss[loss=2.885, NarTop10Accuracy=0.7479, over 6654.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7078, over 5922.83 frames. ], batch size: 14, lr: 2.93e-03
2024-08-06 20:57:25,000 INFO [trainer.py:765] (5/8) Epoch 29, batch 1800, train_loss[loss=3.132, NarTop10Accuracy=0.7001, over 7143.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7105, over 5985.98 frames. ], batch size: 22, lr: 2.93e-03
2024-08-06 20:57:44,621 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 20:57:52,863 INFO [trainer.py:811] (5/8) Epoch 29, validation: loss=2.897, NarTop10Accuracy=0.7458, over 1905321.00 frames. 
2024-08-06 20:57:52,864 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 20:57:53,424 INFO [optim.py:386] (5/8) 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 20:57:59,757 INFO [trainer.py:765] (5/8) Epoch 29, batch 1900, train_loss[loss=3.036, NarTop10Accuracy=0.7201, over 5727.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7073, over 6026.70 frames. ], batch size: 50, lr: 2.93e-03
2024-08-06 20:58:25,309 INFO [trainer.py:765] (5/8) Epoch 29, batch 2000, train_loss[loss=3.61, NarTop10Accuracy=0.6043, over 5862.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7076, over 6006.10 frames. ], batch size: 51, lr: 2.93e-03
2024-08-06 20:58:50,630 INFO [trainer.py:765] (5/8) Epoch 29, batch 2100, train_loss[loss=2.73, NarTop10Accuracy=0.76, over 3867.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7083, over 5977.52 frames. ], batch size: 4, lr: 2.92e-03
2024-08-06 20:59:15,807 INFO [trainer.py:765] (5/8) Epoch 29, batch 2200, train_loss[loss=2.924, NarTop10Accuracy=0.7409, over 7518.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7093, over 6005.60 frames. ], batch size: 31, lr: 2.92e-03
2024-08-06 20:59:40,910 INFO [trainer.py:765] (5/8) Epoch 29, batch 2300, train_loss[loss=2.906, NarTop10Accuracy=0.7518, over 5781.00 frames. ], tot_loss[loss=3.094, NarTop10Accuracy=0.7063, over 6012.40 frames. ], batch size: 9, lr: 2.92e-03
2024-08-06 21:00:05,156 INFO [trainer.py:765] (5/8) Epoch 29, batch 2400, train_loss[loss=2.857, NarTop10Accuracy=0.7609, over 4956.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7093, over 5765.07 frames. ], batch size: 7, lr: 2.92e-03
2024-08-06 21:00:28,742 INFO [trainer.py:765] (5/8) Epoch 29, batch 2500, train_loss[loss=3.341, NarTop10Accuracy=0.649, over 5700.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7141, over 5484.48 frames. ], batch size: 8, lr: 2.92e-03
2024-08-06 21:00:48,854 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 21:01:41,716 INFO [trainer.py:765] (5/8) Epoch 30, batch 100, train_loss[loss=2.817, NarTop10Accuracy=0.7614, over 7401.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7202, over 2358.96 frames. ], batch size: 31, lr: 2.86e-03
2024-08-06 21:02:17,013 INFO [trainer.py:765] (5/8) Epoch 30, batch 200, train_loss[loss=2.869, NarTop10Accuracy=0.7502, over 6783.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.723, over 3849.59 frames. ], batch size: 17, lr: 2.86e-03
2024-08-06 21:02:51,343 INFO [trainer.py:765] (5/8) Epoch 30, batch 300, train_loss[loss=2.833, NarTop10Accuracy=0.7473, over 7263.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7246, over 4660.06 frames. ], batch size: 22, lr: 2.86e-03
2024-08-06 21:03:21,642 INFO [trainer.py:765] (5/8) Epoch 30, batch 400, train_loss[loss=2.729, NarTop10Accuracy=0.7818, over 5112.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7203, over 5095.64 frames. ], batch size: 7, lr: 2.86e-03
2024-08-06 21:03:58,545 INFO [trainer.py:765] (5/8) Epoch 30, batch 500, train_loss[loss=3.26, NarTop10Accuracy=0.6639, over 6120.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7179, over 5385.91 frames. ], batch size: 11, lr: 2.86e-03
2024-08-06 21:04:31,655 INFO [trainer.py:765] (5/8) Epoch 30, batch 600, train_loss[loss=2.968, NarTop10Accuracy=0.7181, over 5658.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7171, over 5660.02 frames. ], batch size: 9, lr: 2.85e-03
2024-08-06 21:05:03,525 INFO [trainer.py:765] (5/8) Epoch 30, batch 700, train_loss[loss=2.873, NarTop10Accuracy=0.7488, over 5151.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7195, over 5723.77 frames. ], batch size: 6, lr: 2.85e-03
2024-08-06 21:05:44,131 INFO [trainer.py:765] (5/8) Epoch 30, batch 800, train_loss[loss=2.983, NarTop10Accuracy=0.7313, over 5094.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7203, over 5771.57 frames. ], batch size: 6, lr: 2.85e-03
2024-08-06 21:06:14,843 INFO [trainer.py:765] (5/8) Epoch 30, batch 900, train_loss[loss=2.938, NarTop10Accuracy=0.7407, over 6186.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.719, over 5794.12 frames. ], batch size: 13, lr: 2.85e-03
2024-08-06 21:06:48,952 INFO [trainer.py:765] (5/8) Epoch 30, batch 1000, train_loss[loss=2.872, NarTop10Accuracy=0.755, over 6093.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7128, over 5866.00 frames. ], batch size: 13, lr: 2.85e-03
2024-08-06 21:07:25,936 INFO [trainer.py:765] (5/8) Epoch 30, batch 1100, train_loss[loss=3.378, NarTop10Accuracy=0.6411, over 6798.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7104, over 5905.68 frames. ], batch size: 17, lr: 2.84e-03
2024-08-06 21:08:02,380 INFO [trainer.py:765] (5/8) Epoch 30, batch 1200, train_loss[loss=3.041, NarTop10Accuracy=0.71, over 7365.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7114, over 5896.99 frames. ], batch size: 31, lr: 2.84e-03
2024-08-06 21:08:35,371 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 21:08:43,457 INFO [trainer.py:811] (5/8) Epoch 30, validation: loss=2.93, NarTop10Accuracy=0.7391, over 1905321.00 frames. 
2024-08-06 21:08:43,458 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 21:08:44,197 INFO [optim.py:386] (5/8) 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 21:08:44,202 INFO [trainer.py:765] (5/8) Epoch 30, batch 1300, train_loss[loss=3.144, NarTop10Accuracy=0.6994, over 4926.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7125, over 5975.32 frames. ], batch size: 6, lr: 2.84e-03
2024-08-06 21:09:22,396 INFO [trainer.py:765] (5/8) Epoch 30, batch 1400, train_loss[loss=2.845, NarTop10Accuracy=0.7573, over 6096.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7108, over 6005.30 frames. ], batch size: 11, lr: 2.84e-03
2024-08-06 21:09:52,372 INFO [trainer.py:765] (5/8) Epoch 30, batch 1500, train_loss[loss=3.045, NarTop10Accuracy=0.722, over 5961.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7125, over 5949.63 frames. ], batch size: 50, lr: 2.84e-03
2024-08-06 21:10:20,083 INFO [trainer.py:765] (5/8) Epoch 30, batch 1600, train_loss[loss=2.956, NarTop10Accuracy=0.7274, over 6951.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.712, over 5929.76 frames. ], batch size: 22, lr: 2.84e-03
2024-08-06 21:10:46,680 INFO [trainer.py:765] (5/8) Epoch 30, batch 1700, train_loss[loss=3.086, NarTop10Accuracy=0.7011, over 6183.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.71, over 5912.32 frames. ], batch size: 13, lr: 2.83e-03
2024-08-06 21:11:13,058 INFO [trainer.py:765] (5/8) Epoch 30, batch 1800, train_loss[loss=3.387, NarTop10Accuracy=0.6406, over 6834.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7102, over 5981.57 frames. ], batch size: 22, lr: 2.83e-03
2024-08-06 21:11:39,417 INFO [trainer.py:765] (5/8) Epoch 30, batch 1900, train_loss[loss=3.001, NarTop10Accuracy=0.7314, over 5757.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.709, over 6029.33 frames. ], batch size: 51, lr: 2.83e-03
2024-08-06 21:12:04,825 INFO [trainer.py:765] (5/8) Epoch 30, batch 2000, train_loss[loss=3.338, NarTop10Accuracy=0.6474, over 5703.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7127, over 6003.86 frames. ], batch size: 51, lr: 2.83e-03
2024-08-06 21:12:30,087 INFO [trainer.py:765] (5/8) Epoch 30, batch 2100, train_loss[loss=2.817, NarTop10Accuracy=0.7641, over 4770.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7115, over 5985.10 frames. ], batch size: 5, lr: 2.83e-03
2024-08-06 21:12:55,225 INFO [trainer.py:765] (5/8) Epoch 30, batch 2200, train_loss[loss=2.863, NarTop10Accuracy=0.7563, over 7200.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7119, over 6023.75 frames. ], batch size: 31, lr: 2.82e-03
2024-08-06 21:13:20,296 INFO [trainer.py:765] (5/8) Epoch 30, batch 2300, train_loss[loss=2.809, NarTop10Accuracy=0.7676, over 5811.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7084, over 6010.19 frames. ], batch size: 9, lr: 2.82e-03
2024-08-06 21:13:44,490 INFO [trainer.py:765] (5/8) Epoch 30, batch 2400, train_loss[loss=2.567, NarTop10Accuracy=0.8046, over 5109.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.716, over 5771.15 frames. ], batch size: 7, lr: 2.82e-03
2024-08-06 21:14:07,986 INFO [trainer.py:765] (5/8) Epoch 30, batch 2500, train_loss[loss=2.844, NarTop10Accuracy=0.7499, over 5142.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7175, over 5457.33 frames. ], batch size: 7, lr: 2.82e-03
2024-08-06 21:14:27,902 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 21:15:23,633 INFO [trainer.py:765] (5/8) Epoch 31, batch 100, train_loss[loss=3.349, NarTop10Accuracy=0.653, over 7323.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7149, over 2362.03 frames. ], batch size: 31, lr: 2.77e-03
2024-08-06 21:15:55,127 INFO [trainer.py:765] (5/8) Epoch 31, batch 200, train_loss[loss=2.974, NarTop10Accuracy=0.7365, over 6831.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7188, over 3860.67 frames. ], batch size: 17, lr: 2.77e-03
2024-08-06 21:16:31,215 INFO [trainer.py:765] (5/8) Epoch 31, batch 300, train_loss[loss=2.94, NarTop10Accuracy=0.7372, over 7218.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7187, over 4669.14 frames. ], batch size: 22, lr: 2.77e-03
2024-08-06 21:17:01,625 INFO [trainer.py:765] (5/8) Epoch 31, batch 400, train_loss[loss=3.002, NarTop10Accuracy=0.7207, over 5148.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7163, over 5108.89 frames. ], batch size: 7, lr: 2.76e-03
2024-08-06 21:17:35,724 INFO [trainer.py:765] (5/8) Epoch 31, batch 500, train_loss[loss=2.84, NarTop10Accuracy=0.7568, over 6135.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7169, over 5385.23 frames. ], batch size: 11, lr: 2.76e-03
2024-08-06 21:18:07,084 INFO [trainer.py:765] (5/8) Epoch 31, batch 600, train_loss[loss=2.662, NarTop10Accuracy=0.7941, over 5829.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7138, over 5655.44 frames. ], batch size: 9, lr: 2.76e-03
2024-08-06 21:18:44,610 INFO [trainer.py:765] (5/8) Epoch 31, batch 700, train_loss[loss=3.401, NarTop10Accuracy=0.6533, over 5004.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7129, over 5721.53 frames. ], batch size: 6, lr: 2.76e-03
2024-08-06 21:18:51,095 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 21:18:59,276 INFO [trainer.py:811] (5/8) Epoch 31, validation: loss=2.984, NarTop10Accuracy=0.7279, over 1905321.00 frames. 
2024-08-06 21:18:59,277 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 21:18:59,986 INFO [optim.py:386] (5/8) 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 21:19:24,245 INFO [trainer.py:765] (5/8) Epoch 31, batch 800, train_loss[loss=2.725, NarTop10Accuracy=0.783, over 5088.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7158, over 5781.80 frames. ], batch size: 6, lr: 2.76e-03
2024-08-06 21:19:56,950 INFO [trainer.py:765] (5/8) Epoch 31, batch 900, train_loss[loss=3.217, NarTop10Accuracy=0.6801, over 6240.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7157, over 5800.59 frames. ], batch size: 13, lr: 2.76e-03
2024-08-06 21:20:33,310 INFO [trainer.py:765] (5/8) Epoch 31, batch 1000, train_loss[loss=3.412, NarTop10Accuracy=0.6299, over 6294.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7173, over 5895.42 frames. ], batch size: 13, lr: 2.75e-03
2024-08-06 21:21:10,215 INFO [trainer.py:765] (5/8) Epoch 31, batch 1100, train_loss[loss=3.246, NarTop10Accuracy=0.6697, over 6831.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7157, over 5931.89 frames. ], batch size: 17, lr: 2.75e-03
2024-08-06 21:21:41,119 INFO [trainer.py:765] (5/8) Epoch 31, batch 1200, train_loss[loss=2.902, NarTop10Accuracy=0.7419, over 7095.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7184, over 5922.05 frames. ], batch size: 31, lr: 2.75e-03
2024-08-06 21:22:19,741 INFO [trainer.py:765] (5/8) Epoch 31, batch 1300, train_loss[loss=2.769, NarTop10Accuracy=0.7689, over 5067.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7138, over 5993.76 frames. ], batch size: 6, lr: 2.75e-03
2024-08-06 21:22:53,533 INFO [trainer.py:765] (5/8) Epoch 31, batch 1400, train_loss[loss=2.894, NarTop10Accuracy=0.7446, over 6207.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7113, over 6026.93 frames. ], batch size: 11, lr: 2.75e-03
2024-08-06 21:23:21,269 INFO [trainer.py:765] (5/8) Epoch 31, batch 1500, train_loss[loss=3.361, NarTop10Accuracy=0.6547, over 6129.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7136, over 5947.18 frames. ], batch size: 52, lr: 2.74e-03
2024-08-06 21:23:49,004 INFO [trainer.py:765] (5/8) Epoch 31, batch 1600, train_loss[loss=3.295, NarTop10Accuracy=0.6595, over 7125.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7146, over 5921.79 frames. ], batch size: 22, lr: 2.74e-03
2024-08-06 21:24:15,512 INFO [trainer.py:765] (5/8) Epoch 31, batch 1700, train_loss[loss=3.339, NarTop10Accuracy=0.6543, over 6264.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7138, over 5906.38 frames. ], batch size: 13, lr: 2.74e-03
2024-08-06 21:24:41,995 INFO [trainer.py:765] (5/8) Epoch 31, batch 1800, train_loss[loss=2.838, NarTop10Accuracy=0.7647, over 7254.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7168, over 5977.31 frames. ], batch size: 22, lr: 2.74e-03
2024-08-06 21:25:08,357 INFO [trainer.py:765] (5/8) Epoch 31, batch 1900, train_loss[loss=3.245, NarTop10Accuracy=0.6776, over 6003.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7138, over 6022.64 frames. ], batch size: 50, lr: 2.74e-03
2024-08-06 21:25:33,773 INFO [trainer.py:765] (5/8) Epoch 31, batch 2000, train_loss[loss=3.017, NarTop10Accuracy=0.7257, over 6033.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7145, over 5996.08 frames. ], batch size: 51, lr: 2.74e-03
2024-08-06 21:25:59,107 INFO [trainer.py:765] (5/8) Epoch 31, batch 2100, train_loss[loss=2.649, NarTop10Accuracy=0.8035, over 3933.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7162, over 5969.82 frames. ], batch size: 4, lr: 2.73e-03
2024-08-06 21:26:24,238 INFO [trainer.py:765] (5/8) Epoch 31, batch 2200, train_loss[loss=2.959, NarTop10Accuracy=0.7407, over 7200.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7197, over 6002.24 frames. ], batch size: 31, lr: 2.73e-03
2024-08-06 21:26:49,322 INFO [trainer.py:765] (5/8) Epoch 31, batch 2300, train_loss[loss=2.743, NarTop10Accuracy=0.7776, over 5532.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7152, over 6023.28 frames. ], batch size: 9, lr: 2.73e-03
2024-08-06 21:27:13,607 INFO [trainer.py:765] (5/8) Epoch 31, batch 2400, train_loss[loss=2.851, NarTop10Accuracy=0.7502, over 5226.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7156, over 5784.57 frames. ], batch size: 7, lr: 2.73e-03
2024-08-06 21:27:37,027 INFO [trainer.py:765] (5/8) Epoch 31, batch 2500, train_loss[loss=2.952, NarTop10Accuracy=0.7377, over 5040.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7183, over 5479.18 frames. ], batch size: 7, lr: 2.73e-03
2024-08-06 21:27:57,461 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 21:28:49,392 INFO [trainer.py:765] (5/8) Epoch 32, batch 100, train_loss[loss=2.892, NarTop10Accuracy=0.7463, over 7350.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7136, over 2359.27 frames. ], batch size: 31, lr: 2.68e-03
2024-08-06 21:29:08,160 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 21:29:16,392 INFO [trainer.py:811] (5/8) Epoch 32, validation: loss=2.919, NarTop10Accuracy=0.7409, over 1905321.00 frames. 
2024-08-06 21:29:16,393 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 21:29:16,939 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 32, batch 200, train_loss[loss=3.317, NarTop10Accuracy=0.6643, over 6831.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.712, over 3856.83 frames. ], batch size: 17, lr: 2.68e-03
2024-08-06 21:30:05,279 INFO [trainer.py:765] (5/8) Epoch 32, batch 300, train_loss[loss=2.986, NarTop10Accuracy=0.7268, over 7107.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7151, over 4660.71 frames. ], batch size: 22, lr: 2.68e-03
2024-08-06 21:30:34,103 INFO [trainer.py:765] (5/8) Epoch 32, batch 400, train_loss[loss=2.683, NarTop10Accuracy=0.7959, over 5079.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7132, over 5107.55 frames. ], batch size: 7, lr: 2.68e-03
2024-08-06 21:31:13,531 INFO [trainer.py:765] (5/8) Epoch 32, batch 500, train_loss[loss=2.92, NarTop10Accuracy=0.7454, over 6069.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7152, over 5382.61 frames. ], batch size: 11, lr: 2.67e-03
2024-08-06 21:31:42,487 INFO [trainer.py:765] (5/8) Epoch 32, batch 600, train_loss[loss=3.182, NarTop10Accuracy=0.6845, over 5745.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.716, over 5651.21 frames. ], batch size: 9, lr: 2.67e-03
2024-08-06 21:32:17,029 INFO [trainer.py:765] (5/8) Epoch 32, batch 700, train_loss[loss=2.743, NarTop10Accuracy=0.778, over 4251.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7176, over 5709.36 frames. ], batch size: 5, lr: 2.67e-03
2024-08-06 21:33:00,647 INFO [trainer.py:765] (5/8) Epoch 32, batch 800, train_loss[loss=3.325, NarTop10Accuracy=0.6645, over 4320.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7169, over 5787.08 frames. ], batch size: 5, lr: 2.67e-03
2024-08-06 21:33:28,992 INFO [trainer.py:765] (5/8) Epoch 32, batch 900, train_loss[loss=2.762, NarTop10Accuracy=0.7744, over 6288.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.719, over 5806.66 frames. ], batch size: 13, lr: 2.67e-03
2024-08-06 21:34:04,049 INFO [trainer.py:765] (5/8) Epoch 32, batch 1000, train_loss[loss=3.168, NarTop10Accuracy=0.6892, over 6096.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7167, over 5903.61 frames. ], batch size: 13, lr: 2.67e-03
2024-08-06 21:34:46,675 INFO [trainer.py:765] (5/8) Epoch 32, batch 1100, train_loss[loss=3.144, NarTop10Accuracy=0.6955, over 6831.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7157, over 5935.99 frames. ], batch size: 17, lr: 2.66e-03
2024-08-06 21:35:18,171 INFO [trainer.py:765] (5/8) Epoch 32, batch 1200, train_loss[loss=3.181, NarTop10Accuracy=0.6864, over 7338.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7138, over 5944.49 frames. ], batch size: 32, lr: 2.66e-03
2024-08-06 21:35:52,801 INFO [trainer.py:765] (5/8) Epoch 32, batch 1300, train_loss[loss=3.131, NarTop10Accuracy=0.6972, over 5013.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7134, over 6013.02 frames. ], batch size: 6, lr: 2.66e-03
2024-08-06 21:36:29,479 INFO [trainer.py:765] (5/8) Epoch 32, batch 1400, train_loss[loss=3.371, NarTop10Accuracy=0.6457, over 5997.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7138, over 6029.48 frames. ], batch size: 11, lr: 2.66e-03
2024-08-06 21:37:04,734 INFO [trainer.py:765] (5/8) Epoch 32, batch 1500, train_loss[loss=3.423, NarTop10Accuracy=0.6404, over 6189.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7133, over 5961.21 frames. ], batch size: 50, lr: 2.66e-03
2024-08-06 21:37:32,522 INFO [trainer.py:765] (5/8) Epoch 32, batch 1600, train_loss[loss=3.092, NarTop10Accuracy=0.7064, over 6915.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7135, over 5944.07 frames. ], batch size: 22, lr: 2.66e-03
2024-08-06 21:37:59,160 INFO [trainer.py:765] (5/8) Epoch 32, batch 1700, train_loss[loss=3.044, NarTop10Accuracy=0.7164, over 6297.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7141, over 5933.97 frames. ], batch size: 13, lr: 2.65e-03
2024-08-06 21:38:25,703 INFO [trainer.py:765] (5/8) Epoch 32, batch 1800, train_loss[loss=3.09, NarTop10Accuracy=0.7074, over 7155.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.714, over 5987.84 frames. ], batch size: 22, lr: 2.65e-03
2024-08-06 21:38:52,170 INFO [trainer.py:765] (5/8) Epoch 32, batch 1900, train_loss[loss=3.056, NarTop10Accuracy=0.7155, over 6729.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7103, over 6038.25 frames. ], batch size: 51, lr: 2.65e-03
2024-08-06 21:39:17,769 INFO [trainer.py:765] (5/8) Epoch 32, batch 2000, train_loss[loss=3.474, NarTop10Accuracy=0.6334, over 6258.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.714, over 5982.98 frames. ], batch size: 50, lr: 2.65e-03
2024-08-06 21:39:43,178 INFO [trainer.py:765] (5/8) Epoch 32, batch 2100, train_loss[loss=2.696, NarTop10Accuracy=0.7778, over 4770.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.715, over 5974.50 frames. ], batch size: 5, lr: 2.65e-03
2024-08-06 21:39:54,783 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 21:40:02,941 INFO [trainer.py:811] (5/8) Epoch 32, validation: loss=2.886, NarTop10Accuracy=0.7482, over 1905321.00 frames. 
2024-08-06 21:40:02,942 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 21:40:03,423 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 32, batch 2200, train_loss[loss=3.1, NarTop10Accuracy=0.7107, over 7248.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7157, over 6011.41 frames. ], batch size: 32, lr: 2.65e-03
2024-08-06 21:40:41,717 INFO [trainer.py:765] (5/8) Epoch 32, batch 2300, train_loss[loss=3.282, NarTop10Accuracy=0.6657, over 5775.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7102, over 6026.38 frames. ], batch size: 9, lr: 2.65e-03
2024-08-06 21:41:06,072 INFO [trainer.py:765] (5/8) Epoch 32, batch 2400, train_loss[loss=3.255, NarTop10Accuracy=0.6667, over 5133.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7144, over 5774.55 frames. ], batch size: 7, lr: 2.64e-03
2024-08-06 21:41:29,538 INFO [trainer.py:765] (5/8) Epoch 32, batch 2500, train_loss[loss=2.774, NarTop10Accuracy=0.7773, over 4968.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7205, over 5462.29 frames. ], batch size: 7, lr: 2.64e-03
2024-08-06 21:41:49,517 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 21:42:47,616 INFO [trainer.py:765] (5/8) Epoch 33, batch 100, train_loss[loss=3.075, NarTop10Accuracy=0.705, over 7440.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7231, over 2365.65 frames. ], batch size: 32, lr: 2.60e-03
2024-08-06 21:43:22,368 INFO [trainer.py:765] (5/8) Epoch 33, batch 200, train_loss[loss=2.764, NarTop10Accuracy=0.778, over 6906.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7208, over 3860.29 frames. ], batch size: 17, lr: 2.60e-03
2024-08-06 21:43:56,513 INFO [trainer.py:765] (5/8) Epoch 33, batch 300, train_loss[loss=3.351, NarTop10Accuracy=0.654, over 7170.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7169, over 4652.80 frames. ], batch size: 22, lr: 2.60e-03
2024-08-06 21:44:30,316 INFO [trainer.py:765] (5/8) Epoch 33, batch 400, train_loss[loss=2.828, NarTop10Accuracy=0.7578, over 5055.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7167, over 5110.88 frames. ], batch size: 7, lr: 2.59e-03
2024-08-06 21:45:02,870 INFO [trainer.py:765] (5/8) Epoch 33, batch 500, train_loss[loss=2.715, NarTop10Accuracy=0.7818, over 6090.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7205, over 5378.54 frames. ], batch size: 11, lr: 2.59e-03
2024-08-06 21:45:36,227 INFO [trainer.py:765] (5/8) Epoch 33, batch 600, train_loss[loss=3.434, NarTop10Accuracy=0.6351, over 5775.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7148, over 5650.07 frames. ], batch size: 9, lr: 2.59e-03
2024-08-06 21:46:11,317 INFO [trainer.py:765] (5/8) Epoch 33, batch 700, train_loss[loss=2.75, NarTop10Accuracy=0.7826, over 5076.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7144, over 5724.06 frames. ], batch size: 6, lr: 2.59e-03
2024-08-06 21:46:46,169 INFO [trainer.py:765] (5/8) Epoch 33, batch 800, train_loss[loss=2.83, NarTop10Accuracy=0.7667, over 4353.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7155, over 5778.71 frames. ], batch size: 5, lr: 2.59e-03
2024-08-06 21:47:18,908 INFO [trainer.py:765] (5/8) Epoch 33, batch 900, train_loss[loss=3.177, NarTop10Accuracy=0.6941, over 6657.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7146, over 5799.25 frames. ], batch size: 14, lr: 2.59e-03
2024-08-06 21:47:57,316 INFO [trainer.py:765] (5/8) Epoch 33, batch 1000, train_loss[loss=2.909, NarTop10Accuracy=0.7409, over 6708.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7134, over 5900.82 frames. ], batch size: 14, lr: 2.58e-03
2024-08-06 21:48:30,908 INFO [trainer.py:765] (5/8) Epoch 33, batch 1100, train_loss[loss=2.967, NarTop10Accuracy=0.7349, over 6855.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7103, over 5934.52 frames. ], batch size: 17, lr: 2.58e-03
2024-08-06 21:49:06,660 INFO [trainer.py:765] (5/8) Epoch 33, batch 1200, train_loss[loss=2.855, NarTop10Accuracy=0.7601, over 7437.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7121, over 5927.88 frames. ], batch size: 31, lr: 2.58e-03
2024-08-06 21:49:42,816 INFO [trainer.py:765] (5/8) Epoch 33, batch 1300, train_loss[loss=2.975, NarTop10Accuracy=0.7364, over 5205.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7148, over 5996.44 frames. ], batch size: 6, lr: 2.58e-03
2024-08-06 21:50:17,310 INFO [trainer.py:765] (5/8) Epoch 33, batch 1400, train_loss[loss=3.432, NarTop10Accuracy=0.6375, over 6120.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7142, over 6001.97 frames. ], batch size: 11, lr: 2.58e-03
2024-08-06 21:50:45,370 INFO [trainer.py:765] (5/8) Epoch 33, batch 1500, train_loss[loss=3.023, NarTop10Accuracy=0.7273, over 6066.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7148, over 5954.47 frames. ], batch size: 51, lr: 2.58e-03
2024-08-06 21:51:04,607 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 21:51:12,661 INFO [trainer.py:811] (5/8) Epoch 33, validation: loss=2.938, NarTop10Accuracy=0.7372, over 1905321.00 frames. 
2024-08-06 21:51:12,662 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 21:51:13,181 INFO [optim.py:386] (5/8) 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 21:51:21,262 INFO [trainer.py:765] (5/8) Epoch 33, batch 1600, train_loss[loss=3.178, NarTop10Accuracy=0.6843, over 7137.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.716, over 5939.75 frames. ], batch size: 22, lr: 2.57e-03
2024-08-06 21:51:47,923 INFO [trainer.py:765] (5/8) Epoch 33, batch 1700, train_loss[loss=2.87, NarTop10Accuracy=0.7533, over 6141.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7147, over 5915.48 frames. ], batch size: 13, lr: 2.57e-03
2024-08-06 21:52:14,392 INFO [trainer.py:765] (5/8) Epoch 33, batch 1800, train_loss[loss=2.761, NarTop10Accuracy=0.7728, over 7275.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7163, over 5991.45 frames. ], batch size: 22, lr: 2.57e-03
2024-08-06 21:52:40,856 INFO [trainer.py:765] (5/8) Epoch 33, batch 1900, train_loss[loss=3.486, NarTop10Accuracy=0.6271, over 6027.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7118, over 6022.38 frames. ], batch size: 51, lr: 2.57e-03
2024-08-06 21:53:06,353 INFO [trainer.py:765] (5/8) Epoch 33, batch 2000, train_loss[loss=3.491, NarTop10Accuracy=0.6301, over 6225.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7175, over 6016.34 frames. ], batch size: 50, lr: 2.57e-03
2024-08-06 21:53:31,659 INFO [trainer.py:765] (5/8) Epoch 33, batch 2100, train_loss[loss=3.331, NarTop10Accuracy=0.6522, over 4797.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7154, over 5990.52 frames. ], batch size: 5, lr: 2.57e-03
2024-08-06 21:53:56,891 INFO [trainer.py:765] (5/8) Epoch 33, batch 2200, train_loss[loss=3.462, NarTop10Accuracy=0.6232, over 7350.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7129, over 6008.84 frames. ], batch size: 31, lr: 2.57e-03
2024-08-06 21:54:21,990 INFO [trainer.py:765] (5/8) Epoch 33, batch 2300, train_loss[loss=2.784, NarTop10Accuracy=0.7791, over 5628.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7134, over 6025.27 frames. ], batch size: 9, lr: 2.56e-03
2024-08-06 21:54:46,430 INFO [trainer.py:765] (5/8) Epoch 33, batch 2400, train_loss[loss=2.801, NarTop10Accuracy=0.7733, over 5040.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7176, over 5799.43 frames. ], batch size: 7, lr: 2.56e-03
2024-08-06 21:55:09,862 INFO [trainer.py:765] (5/8) Epoch 33, batch 2500, train_loss[loss=2.723, NarTop10Accuracy=0.7789, over 5058.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7213, over 5487.41 frames. ], batch size: 7, lr: 2.56e-03
2024-08-06 21:55:29,874 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 21:56:24,722 INFO [trainer.py:765] (5/8) Epoch 34, batch 100, train_loss[loss=3.48, NarTop10Accuracy=0.6308, over 7377.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7163, over 2352.11 frames. ], batch size: 31, lr: 2.52e-03
2024-08-06 21:56:55,614 INFO [trainer.py:765] (5/8) Epoch 34, batch 200, train_loss[loss=3.24, NarTop10Accuracy=0.6773, over 6930.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7225, over 3843.06 frames. ], batch size: 17, lr: 2.52e-03
2024-08-06 21:57:31,777 INFO [trainer.py:765] (5/8) Epoch 34, batch 300, train_loss[loss=2.846, NarTop10Accuracy=0.7619, over 7353.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7211, over 4654.84 frames. ], batch size: 23, lr: 2.52e-03
2024-08-06 21:58:02,724 INFO [trainer.py:765] (5/8) Epoch 34, batch 400, train_loss[loss=3.094, NarTop10Accuracy=0.7051, over 5244.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7231, over 5098.16 frames. ], batch size: 7, lr: 2.52e-03
2024-08-06 21:58:34,690 INFO [trainer.py:765] (5/8) Epoch 34, batch 500, train_loss[loss=3.316, NarTop10Accuracy=0.6591, over 6054.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7208, over 5383.76 frames. ], batch size: 11, lr: 2.51e-03
2024-08-06 21:59:09,616 INFO [trainer.py:765] (5/8) Epoch 34, batch 600, train_loss[loss=2.739, NarTop10Accuracy=0.7683, over 5754.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7192, over 5655.64 frames. ], batch size: 9, lr: 2.51e-03
2024-08-06 21:59:46,057 INFO [trainer.py:765] (5/8) Epoch 34, batch 700, train_loss[loss=2.856, NarTop10Accuracy=0.7394, over 5019.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7178, over 5724.76 frames. ], batch size: 6, lr: 2.51e-03
2024-08-06 22:00:17,575 INFO [trainer.py:765] (5/8) Epoch 34, batch 800, train_loss[loss=2.869, NarTop10Accuracy=0.7538, over 5133.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7196, over 5773.41 frames. ], batch size: 6, lr: 2.51e-03
2024-08-06 22:00:49,874 INFO [trainer.py:765] (5/8) Epoch 34, batch 900, train_loss[loss=2.873, NarTop10Accuracy=0.7495, over 6300.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7197, over 5786.23 frames. ], batch size: 13, lr: 2.51e-03
2024-08-06 22:01:25,339 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 22:01:33,386 INFO [trainer.py:811] (5/8) Epoch 34, validation: loss=2.9, NarTop10Accuracy=0.7444, over 1905321.00 frames. 
2024-08-06 22:01:33,387 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 22:01:34,091 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 34, batch 1000, train_loss[loss=3.28, NarTop10Accuracy=0.6589, over 6189.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7174, over 5893.81 frames. ], batch size: 13, lr: 2.51e-03
2024-08-06 22:02:10,829 INFO [trainer.py:765] (5/8) Epoch 34, batch 1100, train_loss[loss=3.254, NarTop10Accuracy=0.6706, over 6870.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7165, over 5927.68 frames. ], batch size: 17, lr: 2.51e-03
2024-08-06 22:02:46,786 INFO [trainer.py:765] (5/8) Epoch 34, batch 1200, train_loss[loss=2.772, NarTop10Accuracy=0.7662, over 7422.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7175, over 5935.20 frames. ], batch size: 31, lr: 2.50e-03
2024-08-06 22:03:20,813 INFO [trainer.py:765] (5/8) Epoch 34, batch 1300, train_loss[loss=2.856, NarTop10Accuracy=0.7602, over 5166.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7169, over 6001.61 frames. ], batch size: 6, lr: 2.50e-03
2024-08-06 22:03:52,949 INFO [trainer.py:765] (5/8) Epoch 34, batch 1400, train_loss[loss=3.247, NarTop10Accuracy=0.6778, over 6009.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7161, over 6031.21 frames. ], batch size: 11, lr: 2.50e-03
2024-08-06 22:04:20,822 INFO [trainer.py:765] (5/8) Epoch 34, batch 1500, train_loss[loss=3.079, NarTop10Accuracy=0.7085, over 6330.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7163, over 5967.17 frames. ], batch size: 50, lr: 2.50e-03
2024-08-06 22:04:48,599 INFO [trainer.py:765] (5/8) Epoch 34, batch 1600, train_loss[loss=3.04, NarTop10Accuracy=0.7177, over 7092.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7155, over 5936.69 frames. ], batch size: 22, lr: 2.50e-03
2024-08-06 22:05:15,241 INFO [trainer.py:765] (5/8) Epoch 34, batch 1700, train_loss[loss=3.039, NarTop10Accuracy=0.7155, over 6771.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7174, over 5919.90 frames. ], batch size: 14, lr: 2.50e-03
2024-08-06 22:05:41,720 INFO [trainer.py:765] (5/8) Epoch 34, batch 1800, train_loss[loss=3.216, NarTop10Accuracy=0.6749, over 7119.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.715, over 5981.43 frames. ], batch size: 22, lr: 2.50e-03
2024-08-06 22:06:08,206 INFO [trainer.py:765] (5/8) Epoch 34, batch 1900, train_loss[loss=3.057, NarTop10Accuracy=0.7114, over 5814.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7125, over 6029.19 frames. ], batch size: 50, lr: 2.49e-03
2024-08-06 22:06:33,769 INFO [trainer.py:765] (5/8) Epoch 34, batch 2000, train_loss[loss=3.097, NarTop10Accuracy=0.7093, over 6567.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7148, over 6023.48 frames. ], batch size: 50, lr: 2.49e-03
2024-08-06 22:06:59,125 INFO [trainer.py:765] (5/8) Epoch 34, batch 2100, train_loss[loss=3.111, NarTop10Accuracy=0.6811, over 4731.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7123, over 5996.48 frames. ], batch size: 5, lr: 2.49e-03
2024-08-06 22:07:24,398 INFO [trainer.py:765] (5/8) Epoch 34, batch 2200, train_loss[loss=2.944, NarTop10Accuracy=0.7428, over 7095.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7123, over 6013.87 frames. ], batch size: 31, lr: 2.49e-03
2024-08-06 22:07:49,535 INFO [trainer.py:765] (5/8) Epoch 34, batch 2300, train_loss[loss=2.765, NarTop10Accuracy=0.7751, over 5628.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.712, over 6023.42 frames. ], batch size: 9, lr: 2.49e-03
2024-08-06 22:08:14,059 INFO [trainer.py:765] (5/8) Epoch 34, batch 2400, train_loss[loss=3.338, NarTop10Accuracy=0.6456, over 5160.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7131, over 5757.33 frames. ], batch size: 7, lr: 2.49e-03
2024-08-06 22:08:37,648 INFO [trainer.py:765] (5/8) Epoch 34, batch 2500, train_loss[loss=2.926, NarTop10Accuracy=0.7436, over 5187.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7199, over 5470.01 frames. ], batch size: 7, lr: 2.49e-03
2024-08-06 22:08:57,621 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 22:09:52,640 INFO [trainer.py:765] (5/8) Epoch 35, batch 100, train_loss[loss=2.984, NarTop10Accuracy=0.7278, over 7410.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7154, over 2366.74 frames. ], batch size: 32, lr: 2.45e-03
2024-08-06 22:10:29,697 INFO [trainer.py:765] (5/8) Epoch 35, batch 200, train_loss[loss=3.155, NarTop10Accuracy=0.694, over 6837.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7139, over 3862.98 frames. ], batch size: 17, lr: 2.45e-03
2024-08-06 22:11:04,943 INFO [trainer.py:765] (5/8) Epoch 35, batch 300, train_loss[loss=2.805, NarTop10Accuracy=0.7667, over 7266.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7184, over 4667.70 frames. ], batch size: 22, lr: 2.44e-03
2024-08-06 22:11:35,333 INFO [trainer.py:765] (5/8) Epoch 35, batch 400, train_loss[loss=2.969, NarTop10Accuracy=0.735, over 5103.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7183, over 5113.23 frames. ], batch size: 7, lr: 2.44e-03
2024-08-06 22:11:40,048 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 22:11:48,129 INFO [trainer.py:811] (5/8) Epoch 35, validation: loss=2.84, NarTop10Accuracy=0.7576, over 1905321.00 frames. 
2024-08-06 22:11:48,129 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 22:11:48,702 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 35, batch 500, train_loss[loss=2.801, NarTop10Accuracy=0.7694, over 6096.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7202, over 5378.15 frames. ], batch size: 11, lr: 2.44e-03
2024-08-06 22:12:51,425 INFO [trainer.py:765] (5/8) Epoch 35, batch 600, train_loss[loss=3.299, NarTop10Accuracy=0.6653, over 5634.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7173, over 5644.58 frames. ], batch size: 9, lr: 2.44e-03
2024-08-06 22:13:24,941 INFO [trainer.py:765] (5/8) Epoch 35, batch 700, train_loss[loss=2.53, NarTop10Accuracy=0.8106, over 5094.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7175, over 5732.12 frames. ], batch size: 6, lr: 2.44e-03
2024-08-06 22:14:01,384 INFO [trainer.py:765] (5/8) Epoch 35, batch 800, train_loss[loss=2.84, NarTop10Accuracy=0.7587, over 5034.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7157, over 5791.32 frames. ], batch size: 6, lr: 2.44e-03
2024-08-06 22:14:34,373 INFO [trainer.py:765] (5/8) Epoch 35, batch 900, train_loss[loss=3.206, NarTop10Accuracy=0.6847, over 6282.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.719, over 5812.33 frames. ], batch size: 13, lr: 2.44e-03
2024-08-06 22:15:09,372 INFO [trainer.py:765] (5/8) Epoch 35, batch 1000, train_loss[loss=2.854, NarTop10Accuracy=0.7452, over 6321.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7164, over 5905.95 frames. ], batch size: 13, lr: 2.43e-03
2024-08-06 22:15:48,495 INFO [trainer.py:765] (5/8) Epoch 35, batch 1100, train_loss[loss=3.12, NarTop10Accuracy=0.6996, over 7104.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7153, over 5940.42 frames. ], batch size: 18, lr: 2.43e-03
2024-08-06 22:16:22,484 INFO [trainer.py:765] (5/8) Epoch 35, batch 1200, train_loss[loss=2.988, NarTop10Accuracy=0.728, over 7218.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7185, over 5931.00 frames. ], batch size: 31, lr: 2.43e-03
2024-08-06 22:16:57,060 INFO [trainer.py:765] (5/8) Epoch 35, batch 1300, train_loss[loss=2.753, NarTop10Accuracy=0.784, over 5043.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7206, over 6005.88 frames. ], batch size: 6, lr: 2.43e-03
2024-08-06 22:17:31,061 INFO [trainer.py:765] (5/8) Epoch 35, batch 1400, train_loss[loss=3.03, NarTop10Accuracy=0.7129, over 6021.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7173, over 6028.11 frames. ], batch size: 11, lr: 2.43e-03
2024-08-06 22:18:03,062 INFO [trainer.py:765] (5/8) Epoch 35, batch 1500, train_loss[loss=3.014, NarTop10Accuracy=0.7209, over 6198.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7172, over 5955.68 frames. ], batch size: 50, lr: 2.43e-03
2024-08-06 22:18:30,728 INFO [trainer.py:765] (5/8) Epoch 35, batch 1600, train_loss[loss=2.884, NarTop10Accuracy=0.7478, over 7170.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7159, over 5919.46 frames. ], batch size: 22, lr: 2.43e-03
2024-08-06 22:18:57,320 INFO [trainer.py:765] (5/8) Epoch 35, batch 1700, train_loss[loss=2.766, NarTop10Accuracy=0.7706, over 6324.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.715, over 5897.99 frames. ], batch size: 13, lr: 2.42e-03
2024-08-06 22:19:23,703 INFO [trainer.py:765] (5/8) Epoch 35, batch 1800, train_loss[loss=3.469, NarTop10Accuracy=0.6345, over 7254.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7167, over 5959.19 frames. ], batch size: 22, lr: 2.42e-03
2024-08-06 22:19:50,201 INFO [trainer.py:765] (5/8) Epoch 35, batch 1900, train_loss[loss=3.116, NarTop10Accuracy=0.6991, over 6417.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7152, over 6003.15 frames. ], batch size: 50, lr: 2.42e-03
2024-08-06 22:20:15,762 INFO [trainer.py:765] (5/8) Epoch 35, batch 2000, train_loss[loss=3.003, NarTop10Accuracy=0.7237, over 6066.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7166, over 5989.55 frames. ], batch size: 53, lr: 2.42e-03
2024-08-06 22:20:41,045 INFO [trainer.py:765] (5/8) Epoch 35, batch 2100, train_loss[loss=2.655, NarTop10Accuracy=0.791, over 4794.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7166, over 5975.15 frames. ], batch size: 5, lr: 2.42e-03
2024-08-06 22:21:06,226 INFO [trainer.py:765] (5/8) Epoch 35, batch 2200, train_loss[loss=2.96, NarTop10Accuracy=0.7474, over 7317.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7151, over 6028.29 frames. ], batch size: 31, lr: 2.42e-03
2024-08-06 22:21:31,286 INFO [trainer.py:765] (5/8) Epoch 35, batch 2300, train_loss[loss=2.909, NarTop10Accuracy=0.7493, over 5703.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7153, over 6030.92 frames. ], batch size: 9, lr: 2.42e-03
2024-08-06 22:21:55,648 INFO [trainer.py:765] (5/8) Epoch 35, batch 2400, train_loss[loss=3.322, NarTop10Accuracy=0.6562, over 5124.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7152, over 5780.79 frames. ], batch size: 7, lr: 2.42e-03
2024-08-06 22:21:59,682 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 22:22:07,656 INFO [trainer.py:811] (5/8) Epoch 35, validation: loss=2.905, NarTop10Accuracy=0.7437, over 1905321.00 frames. 
2024-08-06 22:22:07,657 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 22:22:08,116 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 35, batch 2500, train_loss[loss=3.052, NarTop10Accuracy=0.7205, over 5253.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7183, over 5472.39 frames. ], batch size: 7, lr: 2.41e-03
2024-08-06 22:22:47,096 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 22:23:47,172 INFO [trainer.py:765] (5/8) Epoch 36, batch 100, train_loss[loss=3.259, NarTop10Accuracy=0.6764, over 7251.00 frames. ], tot_loss[loss=2.993, NarTop10Accuracy=0.7268, over 2384.29 frames. ], batch size: 31, lr: 2.38e-03
2024-08-06 22:24:22,494 INFO [trainer.py:765] (5/8) Epoch 36, batch 200, train_loss[loss=2.813, NarTop10Accuracy=0.7531, over 6852.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7201, over 3868.04 frames. ], batch size: 17, lr: 2.38e-03
2024-08-06 22:24:54,721 INFO [trainer.py:765] (5/8) Epoch 36, batch 300, train_loss[loss=3.307, NarTop10Accuracy=0.6625, over 6951.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7195, over 4672.30 frames. ], batch size: 22, lr: 2.37e-03
2024-08-06 22:25:29,276 INFO [trainer.py:765] (5/8) Epoch 36, batch 400, train_loss[loss=2.973, NarTop10Accuracy=0.7402, over 5328.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.723, over 5136.63 frames. ], batch size: 7, lr: 2.37e-03
2024-08-06 22:26:01,819 INFO [trainer.py:765] (5/8) Epoch 36, batch 500, train_loss[loss=3.353, NarTop10Accuracy=0.6486, over 6204.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7216, over 5415.20 frames. ], batch size: 11, lr: 2.37e-03
2024-08-06 22:26:35,026 INFO [trainer.py:765] (5/8) Epoch 36, batch 600, train_loss[loss=2.89, NarTop10Accuracy=0.7456, over 5685.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7219, over 5670.60 frames. ], batch size: 9, lr: 2.37e-03
2024-08-06 22:27:10,991 INFO [trainer.py:765] (5/8) Epoch 36, batch 700, train_loss[loss=3.16, NarTop10Accuracy=0.6805, over 5097.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7215, over 5726.96 frames. ], batch size: 6, lr: 2.37e-03
2024-08-06 22:27:44,915 INFO [trainer.py:765] (5/8) Epoch 36, batch 800, train_loss[loss=3.156, NarTop10Accuracy=0.7013, over 4362.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7193, over 5780.26 frames. ], batch size: 5, lr: 2.37e-03
2024-08-06 22:28:17,813 INFO [trainer.py:765] (5/8) Epoch 36, batch 900, train_loss[loss=2.819, NarTop10Accuracy=0.7692, over 6648.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.722, over 5797.98 frames. ], batch size: 14, lr: 2.37e-03
2024-08-06 22:28:56,984 INFO [trainer.py:765] (5/8) Epoch 36, batch 1000, train_loss[loss=3.36, NarTop10Accuracy=0.6406, over 6186.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7199, over 5899.45 frames. ], batch size: 13, lr: 2.37e-03
2024-08-06 22:29:29,365 INFO [trainer.py:765] (5/8) Epoch 36, batch 1100, train_loss[loss=2.912, NarTop10Accuracy=0.7385, over 6759.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7188, over 5928.43 frames. ], batch size: 17, lr: 2.36e-03
2024-08-06 22:30:05,681 INFO [trainer.py:765] (5/8) Epoch 36, batch 1200, train_loss[loss=3.119, NarTop10Accuracy=0.7002, over 7455.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7195, over 5933.99 frames. ], batch size: 31, lr: 2.36e-03
2024-08-06 22:30:42,576 INFO [trainer.py:765] (5/8) Epoch 36, batch 1300, train_loss[loss=2.98, NarTop10Accuracy=0.7389, over 4281.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7188, over 5973.58 frames. ], batch size: 5, lr: 2.36e-03
2024-08-06 22:31:15,938 INFO [trainer.py:765] (5/8) Epoch 36, batch 1400, train_loss[loss=3.048, NarTop10Accuracy=0.7205, over 6111.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7216, over 6004.06 frames. ], batch size: 11, lr: 2.36e-03
2024-08-06 22:31:43,748 INFO [trainer.py:765] (5/8) Epoch 36, batch 1500, train_loss[loss=3.395, NarTop10Accuracy=0.6558, over 5940.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7205, over 5920.95 frames. ], batch size: 51, lr: 2.36e-03
2024-08-06 22:32:11,460 INFO [trainer.py:765] (5/8) Epoch 36, batch 1600, train_loss[loss=3.432, NarTop10Accuracy=0.6388, over 7065.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7192, over 5920.87 frames. ], batch size: 22, lr: 2.36e-03
2024-08-06 22:32:38,109 INFO [trainer.py:765] (5/8) Epoch 36, batch 1700, train_loss[loss=3.42, NarTop10Accuracy=0.651, over 6240.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7174, over 5907.92 frames. ], batch size: 13, lr: 2.36e-03
2024-08-06 22:33:04,555 INFO [trainer.py:765] (5/8) Epoch 36, batch 1800, train_loss[loss=3.182, NarTop10Accuracy=0.687, over 7092.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7188, over 5971.41 frames. ], batch size: 22, lr: 2.36e-03
2024-08-06 22:33:15,172 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 22:33:23,567 INFO [trainer.py:811] (5/8) Epoch 36, validation: loss=2.897, NarTop10Accuracy=0.7457, over 1905321.00 frames. 
2024-08-06 22:33:23,568 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 22:33:24,096 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 36, batch 1900, train_loss[loss=2.899, NarTop10Accuracy=0.7518, over 6219.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7179, over 6008.07 frames. ], batch size: 50, lr: 2.35e-03
2024-08-06 22:34:05,077 INFO [trainer.py:765] (5/8) Epoch 36, batch 2000, train_loss[loss=3.256, NarTop10Accuracy=0.6771, over 6156.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7175, over 5970.16 frames. ], batch size: 50, lr: 2.35e-03
2024-08-06 22:34:30,514 INFO [trainer.py:765] (5/8) Epoch 36, batch 2100, train_loss[loss=2.616, NarTop10Accuracy=0.7966, over 3963.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7187, over 5950.66 frames. ], batch size: 4, lr: 2.35e-03
2024-08-06 22:34:55,938 INFO [trainer.py:765] (5/8) Epoch 36, batch 2200, train_loss[loss=3.443, NarTop10Accuracy=0.6389, over 7164.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7154, over 5988.83 frames. ], batch size: 31, lr: 2.35e-03
2024-08-06 22:35:21,145 INFO [trainer.py:765] (5/8) Epoch 36, batch 2300, train_loss[loss=3.429, NarTop10Accuracy=0.6446, over 5916.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7138, over 6001.60 frames. ], batch size: 9, lr: 2.35e-03
2024-08-06 22:35:45,601 INFO [trainer.py:765] (5/8) Epoch 36, batch 2400, train_loss[loss=3.201, NarTop10Accuracy=0.691, over 5274.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.718, over 5770.46 frames. ], batch size: 7, lr: 2.35e-03
2024-08-06 22:36:09,183 INFO [trainer.py:765] (5/8) Epoch 36, batch 2500, train_loss[loss=2.866, NarTop10Accuracy=0.7485, over 5058.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7224, over 5463.42 frames. ], batch size: 7, lr: 2.35e-03
2024-08-06 22:36:28,674 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 22:37:29,726 INFO [trainer.py:765] (5/8) Epoch 37, batch 100, train_loss[loss=2.842, NarTop10Accuracy=0.7605, over 7596.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.718, over 2367.76 frames. ], batch size: 32, lr: 2.31e-03
2024-08-06 22:38:01,273 INFO [trainer.py:765] (5/8) Epoch 37, batch 200, train_loss[loss=2.763, NarTop10Accuracy=0.7682, over 6651.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7193, over 3868.21 frames. ], batch size: 17, lr: 2.31e-03
2024-08-06 22:38:35,956 INFO [trainer.py:765] (5/8) Epoch 37, batch 300, train_loss[loss=3.163, NarTop10Accuracy=0.6906, over 6939.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7211, over 4659.08 frames. ], batch size: 22, lr: 2.31e-03
2024-08-06 22:39:09,307 INFO [trainer.py:765] (5/8) Epoch 37, batch 400, train_loss[loss=2.617, NarTop10Accuracy=0.7959, over 5049.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7237, over 5116.72 frames. ], batch size: 7, lr: 2.31e-03
2024-08-06 22:39:43,862 INFO [trainer.py:765] (5/8) Epoch 37, batch 500, train_loss[loss=3.297, NarTop10Accuracy=0.6712, over 6132.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7236, over 5391.72 frames. ], batch size: 11, lr: 2.31e-03
2024-08-06 22:40:17,334 INFO [trainer.py:765] (5/8) Epoch 37, batch 600, train_loss[loss=2.652, NarTop10Accuracy=0.7971, over 5568.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7209, over 5646.85 frames. ], batch size: 9, lr: 2.31e-03
2024-08-06 22:40:51,616 INFO [trainer.py:765] (5/8) Epoch 37, batch 700, train_loss[loss=3.015, NarTop10Accuracy=0.7238, over 4989.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.716, over 5715.28 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:41:30,566 INFO [trainer.py:765] (5/8) Epoch 37, batch 800, train_loss[loss=2.846, NarTop10Accuracy=0.7571, over 5034.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7162, over 5781.39 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:41:59,084 INFO [trainer.py:765] (5/8) Epoch 37, batch 900, train_loss[loss=2.776, NarTop10Accuracy=0.773, over 6579.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.719, over 5789.82 frames. ], batch size: 14, lr: 2.30e-03
2024-08-06 22:42:38,268 INFO [trainer.py:765] (5/8) Epoch 37, batch 1000, train_loss[loss=3.16, NarTop10Accuracy=0.6833, over 6678.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7165, over 5907.23 frames. ], batch size: 14, lr: 2.30e-03
2024-08-06 22:43:15,907 INFO [trainer.py:765] (5/8) Epoch 37, batch 1100, train_loss[loss=2.926, NarTop10Accuracy=0.739, over 6903.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7161, over 5926.45 frames. ], batch size: 17, lr: 2.30e-03
2024-08-06 22:43:47,740 INFO [trainer.py:765] (5/8) Epoch 37, batch 1200, train_loss[loss=2.835, NarTop10Accuracy=0.7626, over 7290.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.716, over 5928.44 frames. ], batch size: 31, lr: 2.30e-03
2024-08-06 22:44:11,754 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 22:44:20,075 INFO [trainer.py:811] (5/8) Epoch 37, validation: loss=2.92, NarTop10Accuracy=0.7407, over 1905321.00 frames. 
2024-08-06 22:44:20,076 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 22:44:20,606 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 37, batch 1300, train_loss[loss=2.63, NarTop10Accuracy=0.7907, over 5058.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7189, over 6006.66 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:45:10,388 INFO [trainer.py:765] (5/8) Epoch 37, batch 1400, train_loss[loss=2.892, NarTop10Accuracy=0.7504, over 6033.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7184, over 6020.93 frames. ], batch size: 11, lr: 2.30e-03
2024-08-06 22:45:40,512 INFO [trainer.py:765] (5/8) Epoch 37, batch 1500, train_loss[loss=3.031, NarTop10Accuracy=0.7204, over 6186.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7172, over 5964.17 frames. ], batch size: 50, lr: 2.29e-03
2024-08-06 22:46:08,437 INFO [trainer.py:765] (5/8) Epoch 37, batch 1600, train_loss[loss=3.339, NarTop10Accuracy=0.6502, over 7059.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7157, over 5922.56 frames. ], batch size: 22, lr: 2.29e-03
2024-08-06 22:46:35,186 INFO [trainer.py:765] (5/8) Epoch 37, batch 1700, train_loss[loss=3.379, NarTop10Accuracy=0.6446, over 6231.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7171, over 5893.41 frames. ], batch size: 13, lr: 2.29e-03
2024-08-06 22:47:01,792 INFO [trainer.py:765] (5/8) Epoch 37, batch 1800, train_loss[loss=2.748, NarTop10Accuracy=0.777, over 6930.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7182, over 5976.43 frames. ], batch size: 22, lr: 2.29e-03
2024-08-06 22:47:28,312 INFO [trainer.py:765] (5/8) Epoch 37, batch 1900, train_loss[loss=3.013, NarTop10Accuracy=0.7246, over 6462.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7184, over 6019.35 frames. ], batch size: 50, lr: 2.29e-03
2024-08-06 22:47:53,925 INFO [trainer.py:765] (5/8) Epoch 37, batch 2000, train_loss[loss=3.256, NarTop10Accuracy=0.6718, over 5952.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7205, over 5980.49 frames. ], batch size: 50, lr: 2.29e-03
2024-08-06 22:48:19,325 INFO [trainer.py:765] (5/8) Epoch 37, batch 2100, train_loss[loss=2.729, NarTop10Accuracy=0.7721, over 4059.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7179, over 5953.95 frames. ], batch size: 4, lr: 2.29e-03
2024-08-06 22:48:44,707 INFO [trainer.py:765] (5/8) Epoch 37, batch 2200, train_loss[loss=2.89, NarTop10Accuracy=0.7522, over 7170.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7166, over 5969.42 frames. ], batch size: 31, lr: 2.29e-03
2024-08-06 22:49:09,912 INFO [trainer.py:765] (5/8) Epoch 37, batch 2300, train_loss[loss=2.647, NarTop10Accuracy=0.802, over 5757.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7165, over 5998.41 frames. ], batch size: 9, lr: 2.29e-03
2024-08-06 22:49:34,318 INFO [trainer.py:765] (5/8) Epoch 37, batch 2400, train_loss[loss=3.268, NarTop10Accuracy=0.6685, over 5265.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7191, over 5764.36 frames. ], batch size: 7, lr: 2.28e-03
2024-08-06 22:49:57,860 INFO [trainer.py:765] (5/8) Epoch 37, batch 2500, train_loss[loss=3.226, NarTop10Accuracy=0.6784, over 5157.00 frames. ], tot_loss[loss=2.998, NarTop10Accuracy=0.7257, over 5476.92 frames. ], batch size: 7, lr: 2.28e-03
2024-08-06 22:50:17,675 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 22:51:16,152 INFO [trainer.py:765] (5/8) Epoch 38, batch 100, train_loss[loss=3.12, NarTop10Accuracy=0.7016, over 7275.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7233, over 2376.11 frames. ], batch size: 31, lr: 2.25e-03
2024-08-06 22:51:53,014 INFO [trainer.py:765] (5/8) Epoch 38, batch 200, train_loss[loss=3.216, NarTop10Accuracy=0.6882, over 6663.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7222, over 3852.97 frames. ], batch size: 17, lr: 2.25e-03
2024-08-06 22:52:25,202 INFO [trainer.py:765] (5/8) Epoch 38, batch 300, train_loss[loss=2.94, NarTop10Accuracy=0.7402, over 6924.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7181, over 4655.75 frames. ], batch size: 22, lr: 2.25e-03
2024-08-06 22:52:55,627 INFO [trainer.py:765] (5/8) Epoch 38, batch 400, train_loss[loss=3.191, NarTop10Accuracy=0.695, over 5208.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7216, over 5104.10 frames. ], batch size: 7, lr: 2.25e-03
2024-08-06 22:53:32,228 INFO [trainer.py:765] (5/8) Epoch 38, batch 500, train_loss[loss=2.662, NarTop10Accuracy=0.7929, over 6150.00 frames. ], tot_loss[loss=2.988, NarTop10Accuracy=0.7277, over 5381.94 frames. ], batch size: 11, lr: 2.25e-03
2024-08-06 22:54:05,498 INFO [trainer.py:765] (5/8) Epoch 38, batch 600, train_loss[loss=3.228, NarTop10Accuracy=0.6848, over 5778.00 frames. ], tot_loss[loss=3.007, NarTop10Accuracy=0.7241, over 5654.30 frames. ], batch size: 9, lr: 2.24e-03
2024-08-06 22:54:36,003 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 22:54:43,918 INFO [trainer.py:811] (5/8) Epoch 38, validation: loss=2.939, NarTop10Accuracy=0.7369, over 1905321.00 frames. 
2024-08-06 22:54:43,919 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 22:54:44,427 INFO [optim.py:386] (5/8) 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 22:54:46,658 INFO [trainer.py:765] (5/8) Epoch 38, batch 700, train_loss[loss=2.699, NarTop10Accuracy=0.778, over 5049.00 frames. ], tot_loss[loss=3.003, NarTop10Accuracy=0.7245, over 5725.38 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:55:24,937 INFO [trainer.py:765] (5/8) Epoch 38, batch 800, train_loss[loss=2.925, NarTop10Accuracy=0.7334, over 5172.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7218, over 5793.68 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:55:59,703 INFO [trainer.py:765] (5/8) Epoch 38, batch 900, train_loss[loss=2.831, NarTop10Accuracy=0.7541, over 6624.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7229, over 5808.01 frames. ], batch size: 14, lr: 2.24e-03
2024-08-06 22:56:32,090 INFO [trainer.py:765] (5/8) Epoch 38, batch 1000, train_loss[loss=3.272, NarTop10Accuracy=0.6668, over 6699.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7225, over 5919.52 frames. ], batch size: 14, lr: 2.24e-03
2024-08-06 22:57:08,991 INFO [trainer.py:765] (5/8) Epoch 38, batch 1100, train_loss[loss=3.153, NarTop10Accuracy=0.6945, over 6783.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7182, over 5939.12 frames. ], batch size: 17, lr: 2.24e-03
2024-08-06 22:57:42,661 INFO [trainer.py:765] (5/8) Epoch 38, batch 1200, train_loss[loss=2.785, NarTop10Accuracy=0.7765, over 7332.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7184, over 5920.05 frames. ], batch size: 31, lr: 2.24e-03
2024-08-06 22:58:16,545 INFO [trainer.py:765] (5/8) Epoch 38, batch 1300, train_loss[loss=3.146, NarTop10Accuracy=0.6953, over 4977.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7193, over 5985.32 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:58:49,810 INFO [trainer.py:765] (5/8) Epoch 38, batch 1400, train_loss[loss=2.857, NarTop10Accuracy=0.7534, over 6105.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7141, over 6004.53 frames. ], batch size: 11, lr: 2.23e-03
2024-08-06 22:59:22,853 INFO [trainer.py:765] (5/8) Epoch 38, batch 1500, train_loss[loss=3.608, NarTop10Accuracy=0.6054, over 6537.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7184, over 5953.40 frames. ], batch size: 50, lr: 2.23e-03
2024-08-06 22:59:50,643 INFO [trainer.py:765] (5/8) Epoch 38, batch 1600, train_loss[loss=3.386, NarTop10Accuracy=0.6462, over 6891.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.718, over 5928.73 frames. ], batch size: 22, lr: 2.23e-03
2024-08-06 23:00:17,315 INFO [trainer.py:765] (5/8) Epoch 38, batch 1700, train_loss[loss=3.143, NarTop10Accuracy=0.698, over 6495.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.714, over 5927.85 frames. ], batch size: 14, lr: 2.23e-03
2024-08-06 23:00:43,764 INFO [trainer.py:765] (5/8) Epoch 38, batch 1800, train_loss[loss=3.364, NarTop10Accuracy=0.6532, over 7080.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7156, over 5992.02 frames. ], batch size: 22, lr: 2.23e-03
2024-08-06 23:01:10,191 INFO [trainer.py:765] (5/8) Epoch 38, batch 1900, train_loss[loss=3.491, NarTop10Accuracy=0.6333, over 6141.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7145, over 6029.18 frames. ], batch size: 50, lr: 2.23e-03
2024-08-06 23:01:35,681 INFO [trainer.py:765] (5/8) Epoch 38, batch 2000, train_loss[loss=3.362, NarTop10Accuracy=0.6538, over 5820.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7147, over 6000.31 frames. ], batch size: 50, lr: 2.23e-03
2024-08-06 23:02:01,050 INFO [trainer.py:765] (5/8) Epoch 38, batch 2100, train_loss[loss=2.931, NarTop10Accuracy=0.7454, over 4011.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7172, over 5968.18 frames. ], batch size: 4, lr: 2.23e-03
2024-08-06 23:02:26,313 INFO [trainer.py:765] (5/8) Epoch 38, batch 2200, train_loss[loss=2.87, NarTop10Accuracy=0.7575, over 7176.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7176, over 6003.32 frames. ], batch size: 31, lr: 2.23e-03
2024-08-06 23:02:51,419 INFO [trainer.py:765] (5/8) Epoch 38, batch 2300, train_loss[loss=2.811, NarTop10Accuracy=0.764, over 5787.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7173, over 6009.49 frames. ], batch size: 9, lr: 2.22e-03
2024-08-06 23:03:16,348 INFO [trainer.py:765] (5/8) Epoch 38, batch 2400, train_loss[loss=2.691, NarTop10Accuracy=0.7806, over 5067.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7196, over 5757.84 frames. ], batch size: 7, lr: 2.22e-03
2024-08-06 23:03:39,823 INFO [trainer.py:765] (5/8) Epoch 38, batch 2500, train_loss[loss=3.162, NarTop10Accuracy=0.6848, over 5082.00 frames. ], tot_loss[loss=3.005, NarTop10Accuracy=0.7238, over 5475.29 frames. ], batch size: 7, lr: 2.22e-03
2024-08-06 23:03:59,600 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 23:04:58,940 INFO [trainer.py:765] (5/8) Epoch 39, batch 100, train_loss[loss=3.294, NarTop10Accuracy=0.6674, over 7236.00 frames. ], tot_loss[loss=2.971, NarTop10Accuracy=0.7313, over 2381.89 frames. ], batch size: 31, lr: 2.19e-03
2024-08-06 23:05:03,468 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 23:05:11,563 INFO [trainer.py:811] (5/8) Epoch 39, validation: loss=2.9, NarTop10Accuracy=0.7445, over 1905321.00 frames. 
2024-08-06 23:05:11,564 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 23:05:12,137 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 39, batch 200, train_loss[loss=2.714, NarTop10Accuracy=0.7825, over 6774.00 frames. ], tot_loss[loss=2.991, NarTop10Accuracy=0.7271, over 3863.87 frames. ], batch size: 17, lr: 2.19e-03
2024-08-06 23:06:17,293 INFO [trainer.py:765] (5/8) Epoch 39, batch 300, train_loss[loss=3.021, NarTop10Accuracy=0.7274, over 6918.00 frames. ], tot_loss[loss=2.99, NarTop10Accuracy=0.7278, over 4655.13 frames. ], batch size: 22, lr: 2.19e-03
2024-08-06 23:06:48,275 INFO [trainer.py:765] (5/8) Epoch 39, batch 400, train_loss[loss=3.004, NarTop10Accuracy=0.7275, over 5196.00 frames. ], tot_loss[loss=2.994, NarTop10Accuracy=0.7268, over 5117.69 frames. ], batch size: 7, lr: 2.19e-03
2024-08-06 23:07:19,175 INFO [trainer.py:765] (5/8) Epoch 39, batch 500, train_loss[loss=3.337, NarTop10Accuracy=0.6653, over 6012.00 frames. ], tot_loss[loss=3.003, NarTop10Accuracy=0.7242, over 5376.17 frames. ], batch size: 11, lr: 2.19e-03
2024-08-06 23:07:52,563 INFO [trainer.py:765] (5/8) Epoch 39, batch 600, train_loss[loss=2.712, NarTop10Accuracy=0.7886, over 5739.00 frames. ], tot_loss[loss=3.011, NarTop10Accuracy=0.7226, over 5654.81 frames. ], batch size: 9, lr: 2.19e-03
2024-08-06 23:08:33,695 INFO [trainer.py:765] (5/8) Epoch 39, batch 700, train_loss[loss=3.1, NarTop10Accuracy=0.7077, over 5007.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7196, over 5719.71 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:09:05,861 INFO [trainer.py:765] (5/8) Epoch 39, batch 800, train_loss[loss=2.485, NarTop10Accuracy=0.8226, over 5127.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7196, over 5775.30 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:09:38,865 INFO [trainer.py:765] (5/8) Epoch 39, batch 900, train_loss[loss=3.502, NarTop10Accuracy=0.621, over 6669.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7197, over 5789.62 frames. ], batch size: 14, lr: 2.18e-03
2024-08-06 23:10:18,460 INFO [trainer.py:765] (5/8) Epoch 39, batch 1000, train_loss[loss=2.827, NarTop10Accuracy=0.7618, over 6231.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7219, over 5891.58 frames. ], batch size: 13, lr: 2.18e-03
2024-08-06 23:10:53,934 INFO [trainer.py:765] (5/8) Epoch 39, batch 1100, train_loss[loss=2.665, NarTop10Accuracy=0.7896, over 6789.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7185, over 5934.54 frames. ], batch size: 17, lr: 2.18e-03
2024-08-06 23:11:27,822 INFO [trainer.py:765] (5/8) Epoch 39, batch 1200, train_loss[loss=2.962, NarTop10Accuracy=0.7363, over 7230.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7211, over 5928.27 frames. ], batch size: 31, lr: 2.18e-03
2024-08-06 23:12:07,253 INFO [trainer.py:765] (5/8) Epoch 39, batch 1300, train_loss[loss=2.749, NarTop10Accuracy=0.7752, over 5157.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7226, over 5996.87 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:12:39,302 INFO [trainer.py:765] (5/8) Epoch 39, batch 1400, train_loss[loss=2.921, NarTop10Accuracy=0.7366, over 6102.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7223, over 6022.67 frames. ], batch size: 11, lr: 2.18e-03
2024-08-06 23:13:09,756 INFO [trainer.py:765] (5/8) Epoch 39, batch 1500, train_loss[loss=3.615, NarTop10Accuracy=0.6041, over 6087.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7224, over 5944.15 frames. ], batch size: 51, lr: 2.18e-03
2024-08-06 23:13:37,587 INFO [trainer.py:765] (5/8) Epoch 39, batch 1600, train_loss[loss=2.773, NarTop10Accuracy=0.7776, over 7161.00 frames. ], tot_loss[loss=3.004, NarTop10Accuracy=0.7242, over 5937.06 frames. ], batch size: 22, lr: 2.17e-03
2024-08-06 23:14:04,220 INFO [trainer.py:765] (5/8) Epoch 39, batch 1700, train_loss[loss=3.275, NarTop10Accuracy=0.6658, over 6675.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7174, over 5905.63 frames. ], batch size: 14, lr: 2.17e-03
2024-08-06 23:14:30,767 INFO [trainer.py:765] (5/8) Epoch 39, batch 1800, train_loss[loss=2.833, NarTop10Accuracy=0.7636, over 7089.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.716, over 5950.59 frames. ], batch size: 22, lr: 2.17e-03
2024-08-06 23:14:57,180 INFO [trainer.py:765] (5/8) Epoch 39, batch 1900, train_loss[loss=3.022, NarTop10Accuracy=0.7228, over 5736.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7146, over 6002.82 frames. ], batch size: 50, lr: 2.17e-03
2024-08-06 23:15:22,751 INFO [trainer.py:765] (5/8) Epoch 39, batch 2000, train_loss[loss=3.352, NarTop10Accuracy=0.6582, over 6306.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7185, over 5987.85 frames. ], batch size: 50, lr: 2.17e-03
2024-08-06 23:15:48,060 INFO [trainer.py:765] (5/8) Epoch 39, batch 2100, train_loss[loss=3.223, NarTop10Accuracy=0.6883, over 4818.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7197, over 5961.94 frames. ], batch size: 5, lr: 2.17e-03
2024-08-06 23:15:51,871 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 23:16:02,156 INFO [trainer.py:811] (5/8) Epoch 39, validation: loss=2.85, NarTop10Accuracy=0.7552, over 1905321.00 frames. 
2024-08-06 23:16:02,156 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 23:16:02,645 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 39, batch 2200, train_loss[loss=3.178, NarTop10Accuracy=0.6951, over 7359.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7195, over 6014.50 frames. ], batch size: 31, lr: 2.17e-03
2024-08-06 23:16:48,846 INFO [trainer.py:765] (5/8) Epoch 39, batch 2300, train_loss[loss=2.743, NarTop10Accuracy=0.7795, over 5697.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7164, over 6012.09 frames. ], batch size: 9, lr: 2.17e-03
2024-08-06 23:17:13,135 INFO [trainer.py:765] (5/8) Epoch 39, batch 2400, train_loss[loss=2.618, NarTop10Accuracy=0.8003, over 5055.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7221, over 5769.05 frames. ], batch size: 7, lr: 2.17e-03
2024-08-06 23:17:36,711 INFO [trainer.py:765] (5/8) Epoch 39, batch 2500, train_loss[loss=2.947, NarTop10Accuracy=0.7431, over 5214.00 frames. ], tot_loss[loss=2.988, NarTop10Accuracy=0.7269, over 5470.75 frames. ], batch size: 7, lr: 2.16e-03
2024-08-06 23:17:56,587 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 23:18:48,946 INFO [trainer.py:765] (5/8) Epoch 40, batch 100, train_loss[loss=3.025, NarTop10Accuracy=0.7267, over 7053.00 frames. ], tot_loss[loss=2.993, NarTop10Accuracy=0.7271, over 2377.34 frames. ], batch size: 31, lr: 2.14e-03
2024-08-06 23:19:23,035 INFO [trainer.py:765] (5/8) Epoch 40, batch 200, train_loss[loss=2.703, NarTop10Accuracy=0.784, over 6792.00 frames. ], tot_loss[loss=2.983, NarTop10Accuracy=0.7286, over 3860.38 frames. ], batch size: 17, lr: 2.13e-03
2024-08-06 23:19:57,187 INFO [trainer.py:765] (5/8) Epoch 40, batch 300, train_loss[loss=2.82, NarTop10Accuracy=0.7658, over 7020.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.723, over 4658.32 frames. ], batch size: 22, lr: 2.13e-03
2024-08-06 23:20:30,182 INFO [trainer.py:765] (5/8) Epoch 40, batch 400, train_loss[loss=2.909, NarTop10Accuracy=0.7409, over 5172.00 frames. ], tot_loss[loss=3.011, NarTop10Accuracy=0.723, over 5121.62 frames. ], batch size: 7, lr: 2.13e-03
2024-08-06 23:21:00,250 INFO [trainer.py:765] (5/8) Epoch 40, batch 500, train_loss[loss=2.776, NarTop10Accuracy=0.7652, over 6078.00 frames. ], tot_loss[loss=3.01, NarTop10Accuracy=0.7233, over 5382.90 frames. ], batch size: 11, lr: 2.13e-03
2024-08-06 23:21:34,881 INFO [trainer.py:765] (5/8) Epoch 40, batch 600, train_loss[loss=2.923, NarTop10Accuracy=0.7367, over 5703.00 frames. ], tot_loss[loss=3.008, NarTop10Accuracy=0.7237, over 5648.20 frames. ], batch size: 9, lr: 2.13e-03
2024-08-06 23:22:11,097 INFO [trainer.py:765] (5/8) Epoch 40, batch 700, train_loss[loss=2.975, NarTop10Accuracy=0.7268, over 5106.00 frames. ], tot_loss[loss=3.01, NarTop10Accuracy=0.7235, over 5717.46 frames. ], batch size: 6, lr: 2.13e-03
2024-08-06 23:22:44,753 INFO [trainer.py:765] (5/8) Epoch 40, batch 800, train_loss[loss=2.821, NarTop10Accuracy=0.7698, over 5016.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7208, over 5766.10 frames. ], batch size: 6, lr: 2.13e-03
2024-08-06 23:23:16,635 INFO [trainer.py:765] (5/8) Epoch 40, batch 900, train_loss[loss=3.437, NarTop10Accuracy=0.6342, over 6234.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7227, over 5787.24 frames. ], batch size: 13, lr: 2.13e-03
2024-08-06 23:23:55,592 INFO [trainer.py:765] (5/8) Epoch 40, batch 1000, train_loss[loss=3.412, NarTop10Accuracy=0.6443, over 6624.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7202, over 5881.95 frames. ], batch size: 14, lr: 2.13e-03
2024-08-06 23:24:30,208 INFO [trainer.py:765] (5/8) Epoch 40, batch 1100, train_loss[loss=2.809, NarTop10Accuracy=0.7731, over 6894.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7201, over 5932.33 frames. ], batch size: 17, lr: 2.12e-03
2024-08-06 23:25:03,090 INFO [trainer.py:765] (5/8) Epoch 40, batch 1200, train_loss[loss=3.004, NarTop10Accuracy=0.7277, over 6993.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7213, over 5928.78 frames. ], batch size: 31, lr: 2.12e-03
2024-08-06 23:25:41,842 INFO [trainer.py:765] (5/8) Epoch 40, batch 1300, train_loss[loss=2.76, NarTop10Accuracy=0.7785, over 4926.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.7229, over 6004.24 frames. ], batch size: 6, lr: 2.12e-03
2024-08-06 23:26:13,384 INFO [trainer.py:765] (5/8) Epoch 40, batch 1400, train_loss[loss=2.801, NarTop10Accuracy=0.767, over 6084.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7208, over 6035.36 frames. ], batch size: 11, lr: 2.12e-03
2024-08-06 23:26:43,377 INFO [trainer.py:765] (5/8) Epoch 40, batch 1500, train_loss[loss=3.319, NarTop10Accuracy=0.6654, over 6471.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7224, over 5953.37 frames. ], batch size: 52, lr: 2.12e-03
2024-08-06 23:26:54,419 INFO [trainer.py:803] (5/8) Computing validation loss
2024-08-06 23:27:02,676 INFO [trainer.py:811] (5/8) Epoch 40, validation: loss=2.86, NarTop10Accuracy=0.7522, over 1905321.00 frames. 
2024-08-06 23:27:02,677 INFO [trainer.py:814] (5/8) Maximum memory allocated so far is 30143MB
2024-08-06 23:27:03,156 INFO [optim.py:386] (5/8) 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] (5/8) Epoch 40, batch 1600, train_loss[loss=2.799, NarTop10Accuracy=0.7604, over 7272.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7208, over 5933.07 frames. ], batch size: 22, lr: 2.12e-03
2024-08-06 23:27:46,056 INFO [trainer.py:765] (5/8) Epoch 40, batch 1700, train_loss[loss=3.402, NarTop10Accuracy=0.6425, over 6246.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7206, over 5913.18 frames. ], batch size: 13, lr: 2.12e-03
2024-08-06 23:28:12,579 INFO [trainer.py:765] (5/8) Epoch 40, batch 1800, train_loss[loss=3.092, NarTop10Accuracy=0.7142, over 7143.00 frames. ], tot_loss[loss=3, NarTop10Accuracy=0.7252, over 5981.03 frames. ], batch size: 22, lr: 2.12e-03
2024-08-06 23:28:38,909 INFO [trainer.py:765] (5/8) Epoch 40, batch 1900, train_loss[loss=3.143, NarTop10Accuracy=0.702, over 6006.00 frames. ], tot_loss[loss=3.008, NarTop10Accuracy=0.7238, over 6010.88 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:29:04,444 INFO [trainer.py:765] (5/8) Epoch 40, batch 2000, train_loss[loss=3.534, NarTop10Accuracy=0.6224, over 6189.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7231, over 5998.89 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:29:29,750 INFO [trainer.py:765] (5/8) Epoch 40, batch 2100, train_loss[loss=2.79, NarTop10Accuracy=0.7648, over 4875.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7223, over 5971.34 frames. ], batch size: 5, lr: 2.11e-03
2024-08-06 23:29:54,939 INFO [trainer.py:765] (5/8) Epoch 40, batch 2200, train_loss[loss=3.171, NarTop10Accuracy=0.6996, over 7191.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.72, over 6017.26 frames. ], batch size: 31, lr: 2.11e-03
2024-08-06 23:30:20,013 INFO [trainer.py:765] (5/8) Epoch 40, batch 2300, train_loss[loss=2.961, NarTop10Accuracy=0.7315, over 5712.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.719, over 6032.56 frames. ], batch size: 9, lr: 2.11e-03
2024-08-06 23:30:44,296 INFO [trainer.py:765] (5/8) Epoch 40, batch 2400, train_loss[loss=2.799, NarTop10Accuracy=0.7745, over 5202.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7206, over 5780.97 frames. ], batch size: 7, lr: 2.11e-03
2024-08-06 23:31:07,738 INFO [trainer.py:765] (5/8) Epoch 40, batch 2500, train_loss[loss=3.181, NarTop10Accuracy=0.6891, over 5061.00 frames. ], tot_loss[loss=2.986, NarTop10Accuracy=0.7279, over 5494.44 frames. ], batch size: 7, lr: 2.11e-03
2024-08-06 23:31:27,895 INFO [trainer.py:650] (5/8) Reaches end of dataloader.
2024-08-06 23:31:27,898 INFO [trainer.py:1069] (5/8) Done!