2024-08-06 14:23:41,730 INFO [trainer.py:870] (6/8) Training started
2024-08-06 14:23:41,731 INFO [trainer.py:889] (6/8) Device: cuda:6
2024-08-06 14:23:41,731 INFO [trainer.py:890] (6/8) {'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 14:23:41,731 INFO [trainer.py:892] (6/8) About to create model
2024-08-06 14:23:42,497 INFO [trainer.py:899] (6/8) Number of model parameters: 367386628
2024-08-06 14:23:42,497 INFO [checkpoint.py:112] (6/8) Loading checkpoint from exp/valle/epoch-99.pt
2024-08-06 14:23:47,480 INFO [trainer.py:914] (6/8) Using DDP
2024-08-06 14:23:49,642 INFO [datamodule.py:427] (6/8) About to get train cuts
2024-08-06 14:23:49,644 INFO [datamodule.py:434] (6/8) About to get dev cuts
2024-08-06 14:23:49,646 INFO [datamodule.py:292] (6/8) Disable SpecAugment
2024-08-06 14:23:49,646 INFO [datamodule.py:294] (6/8) About to create train dataset
2024-08-06 14:23:49,646 INFO [datamodule.py:323] (6/8) Using DynamicBucketingSampler
2024-08-06 14:23:50,252 INFO [datamodule.py:344] (6/8) About to create train dataloader
2024-08-06 14:23:50,252 INFO [datamodule.py:367] (6/8) About to create dev dataset
2024-08-06 14:23:50,581 INFO [datamodule.py:388] (6/8) About to create dev dataloader
2024-08-06 14:24:38,248 INFO [trainer.py:765] (6/8) Epoch 1, batch 100, train_loss[loss=106.7, NarTop10Accuracy=0.02046, over 7203.00 frames. ], tot_loss[loss=73.99, NarTop10Accuracy=0.0468, over 2357.27 frames. ], batch size: 31, lr: 2.25e-02
2024-08-06 14:25:07,518 INFO [trainer.py:765] (6/8) Epoch 1, batch 200, train_loss[loss=135.7, NarTop10Accuracy=0.01382, over 6819.00 frames. ], tot_loss[loss=97.65, NarTop10Accuracy=0.04253, over 3832.72 frames. ], batch size: 17, lr: 3.00e-02
2024-08-06 14:25:37,111 INFO [trainer.py:765] (6/8) Epoch 1, batch 300, train_loss[loss=108.2, NarTop10Accuracy=0.02574, over 7242.00 frames. ], tot_loss[loss=85.23, NarTop10Accuracy=0.04302, over 4651.54 frames. ], batch size: 22, lr: 3.00e-02
2024-08-06 14:26:07,482 INFO [trainer.py:765] (6/8) Epoch 1, batch 400, train_loss[loss=52.2, NarTop10Accuracy=0.02431, over 5031.00 frames. ], tot_loss[loss=67.99, NarTop10Accuracy=0.04725, over 5097.29 frames. ], batch size: 7, lr: 3.00e-02
2024-08-06 14:26:35,357 INFO [trainer.py:765] (6/8) Epoch 1, batch 500, train_loss[loss=14.76, NarTop10Accuracy=0.02818, over 6021.00 frames. ], tot_loss[loss=48.94, NarTop10Accuracy=0.04963, over 5396.75 frames. ], batch size: 11, lr: 2.99e-02
2024-08-06 14:27:04,000 INFO [trainer.py:765] (6/8) Epoch 1, batch 600, train_loss[loss=6.205, NarTop10Accuracy=0.1748, over 5619.00 frames. ], tot_loss[loss=33.4, NarTop10Accuracy=0.05472, over 5652.45 frames. ], batch size: 9, lr: 2.99e-02
2024-08-06 14:27:39,490 INFO [trainer.py:765] (6/8) Epoch 1, batch 700, train_loss[loss=6.663, NarTop10Accuracy=0.1233, over 4368.00 frames. ], tot_loss[loss=23.42, NarTop10Accuracy=0.06343, over 5712.64 frames. ], batch size: 5, lr: 2.99e-02
2024-08-06 14:28:08,832 INFO [trainer.py:765] (6/8) Epoch 1, batch 800, train_loss[loss=6.515, NarTop10Accuracy=0.12, over 4983.00 frames. ], tot_loss[loss=17.18, NarTop10Accuracy=0.08516, over 5756.53 frames. ], batch size: 6, lr: 2.98e-02
2024-08-06 14:28:36,758 INFO [trainer.py:765] (6/8) Epoch 1, batch 900, train_loss[loss=5.893, NarTop10Accuracy=0.1519, over 6276.00 frames. ], tot_loss[loss=12.8, NarTop10Accuracy=0.1139, over 5775.56 frames. ], batch size: 13, lr: 2.98e-02
2024-08-06 14:29:12,586 INFO [trainer.py:765] (6/8) Epoch 1, batch 1000, train_loss[loss=5.766, NarTop10Accuracy=0.1795, over 6636.00 frames. ], tot_loss[loss=10.11, NarTop10Accuracy=0.1336, over 5884.14 frames. ], batch size: 14, lr: 2.97e-02
2024-08-06 14:29:42,825 INFO [trainer.py:765] (6/8) Epoch 1, batch 1100, train_loss[loss=5.579, NarTop10Accuracy=0.2151, over 6834.00 frames. ], tot_loss[loss=8.421, NarTop10Accuracy=0.1513, over 5930.64 frames. ], batch size: 17, lr: 2.96e-02
2024-08-06 14:30:11,468 INFO [trainer.py:765] (6/8) Epoch 1, batch 1200, train_loss[loss=5.847, NarTop10Accuracy=0.1839, over 7206.00 frames. ], tot_loss[loss=7.348, NarTop10Accuracy=0.1705, over 5933.82 frames. ], batch size: 31, lr: 2.96e-02
2024-08-06 14:30:48,747 INFO [trainer.py:765] (6/8) Epoch 1, batch 1300, train_loss[loss=5.506, NarTop10Accuracy=0.232, over 4401.00 frames. ], tot_loss[loss=6.688, NarTop10Accuracy=0.185, over 5987.91 frames. ], batch size: 5, lr: 2.95e-02
2024-08-06 14:31:18,144 INFO [trainer.py:765] (6/8) Epoch 1, batch 1400, train_loss[loss=5.61, NarTop10Accuracy=0.204, over 6015.00 frames. ], tot_loss[loss=6.252, NarTop10Accuracy=0.1967, over 6024.49 frames. ], batch size: 11, lr: 2.94e-02
2024-08-06 14:31:46,026 INFO [trainer.py:765] (6/8) Epoch 1, batch 1500, train_loss[loss=5.766, NarTop10Accuracy=0.1813, over 6273.00 frames. ], tot_loss[loss=5.973, NarTop10Accuracy=0.2082, over 5956.27 frames. ], batch size: 50, lr: 2.94e-02
2024-08-06 14:32:13,691 INFO [trainer.py:765] (6/8) Epoch 1, batch 1600, train_loss[loss=5.612, NarTop10Accuracy=0.2033, over 7098.00 frames. ], tot_loss[loss=5.788, NarTop10Accuracy=0.2176, over 5935.23 frames. ], batch size: 22, lr: 2.93e-02
2024-08-06 14:32:40,198 INFO [trainer.py:765] (6/8) Epoch 1, batch 1700, train_loss[loss=5.369, NarTop10Accuracy=0.2582, over 6783.00 frames. ], tot_loss[loss=5.661, NarTop10Accuracy=0.226, over 5908.48 frames. ], batch size: 14, lr: 2.92e-02
2024-08-06 14:33:06,499 INFO [trainer.py:765] (6/8) Epoch 1, batch 1800, train_loss[loss=5.577, NarTop10Accuracy=0.2129, over 7113.00 frames. ], tot_loss[loss=5.573, NarTop10Accuracy=0.2328, over 5966.86 frames. ], batch size: 22, lr: 2.91e-02
2024-08-06 14:33:32,625 INFO [trainer.py:765] (6/8) Epoch 1, batch 1900, train_loss[loss=5.788, NarTop10Accuracy=0.1783, over 5982.00 frames. ], tot_loss[loss=5.505, NarTop10Accuracy=0.2412, over 6012.02 frames. ], batch size: 50, lr: 2.90e-02
2024-08-06 14:33:58,014 INFO [trainer.py:765] (6/8) Epoch 1, batch 2000, train_loss[loss=5.543, NarTop10Accuracy=0.2328, over 6072.00 frames. ], tot_loss[loss=5.45, NarTop10Accuracy=0.2488, over 6000.03 frames. ], batch size: 50, lr: 2.89e-02
2024-08-06 14:33:58,015 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 14:34:06,103 INFO [trainer.py:811] (6/8) Epoch 1, validation: loss=5.397, NarTop10Accuracy=0.2581, over 1905321.00 frames. 
2024-08-06 14:34:06,104 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 26623MB
2024-08-06 14:34:06,612 INFO [optim.py:386] (6/8) 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 14:34:32,061 INFO [trainer.py:765] (6/8) Epoch 1, batch 2100, train_loss[loss=5.236, NarTop10Accuracy=0.2844, over 4905.00 frames. ], tot_loss[loss=5.385, NarTop10Accuracy=0.2595, over 5990.33 frames. ], batch size: 5, lr: 2.88e-02
2024-08-06 14:34:57,303 INFO [trainer.py:765] (6/8) Epoch 1, batch 2200, train_loss[loss=5.41, NarTop10Accuracy=0.2464, over 7218.00 frames. ], tot_loss[loss=5.353, NarTop10Accuracy=0.2641, over 6016.43 frames. ], batch size: 31, lr: 2.87e-02
2024-08-06 14:35:22,456 INFO [trainer.py:765] (6/8) Epoch 1, batch 2300, train_loss[loss=5.337, NarTop10Accuracy=0.2634, over 5724.00 frames. ], tot_loss[loss=5.337, NarTop10Accuracy=0.2669, over 6016.53 frames. ], batch size: 9, lr: 2.86e-02
2024-08-06 14:35:46,815 INFO [trainer.py:765] (6/8) Epoch 1, batch 2400, train_loss[loss=5.425, NarTop10Accuracy=0.2483, over 5055.00 frames. ], tot_loss[loss=5.283, NarTop10Accuracy=0.277, over 5771.75 frames. ], batch size: 7, lr: 2.85e-02
2024-08-06 14:36:10,408 INFO [trainer.py:765] (6/8) Epoch 1, batch 2500, train_loss[loss=5.062, NarTop10Accuracy=0.3107, over 5115.00 frames. ], tot_loss[loss=5.219, NarTop10Accuracy=0.2883, over 5499.02 frames. ], batch size: 7, lr: 2.84e-02
2024-08-06 14:36:31,071 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 14:37:29,669 INFO [trainer.py:765] (6/8) Epoch 2, batch 100, train_loss[loss=4.977, NarTop10Accuracy=0.3376, over 7383.00 frames. ], tot_loss[loss=5.197, NarTop10Accuracy=0.2928, over 2375.73 frames. ], batch size: 31, lr: 2.77e-02
2024-08-06 14:38:10,014 INFO [trainer.py:765] (6/8) Epoch 2, batch 200, train_loss[loss=5.146, NarTop10Accuracy=0.3068, over 6804.00 frames. ], tot_loss[loss=5.166, NarTop10Accuracy=0.2986, over 3870.73 frames. ], batch size: 17, lr: 2.76e-02
2024-08-06 14:38:38,297 INFO [trainer.py:765] (6/8) Epoch 2, batch 300, train_loss[loss=5.17, NarTop10Accuracy=0.2958, over 7065.00 frames. ], tot_loss[loss=5.139, NarTop10Accuracy=0.3033, over 4651.71 frames. ], batch size: 22, lr: 2.75e-02
2024-08-06 14:39:06,998 INFO [trainer.py:765] (6/8) Epoch 2, batch 400, train_loss[loss=4.9, NarTop10Accuracy=0.3448, over 4986.00 frames. ], tot_loss[loss=5.113, NarTop10Accuracy=0.3078, over 5110.71 frames. ], batch size: 7, lr: 2.74e-02
2024-08-06 14:39:46,119 INFO [trainer.py:765] (6/8) Epoch 2, batch 500, train_loss[loss=4.888, NarTop10Accuracy=0.3477, over 6027.00 frames. ], tot_loss[loss=5.07, NarTop10Accuracy=0.3159, over 5368.09 frames. ], batch size: 11, lr: 2.73e-02
2024-08-06 14:40:15,083 INFO [trainer.py:765] (6/8) Epoch 2, batch 600, train_loss[loss=4.86, NarTop10Accuracy=0.3591, over 5523.00 frames. ], tot_loss[loss=5.051, NarTop10Accuracy=0.3194, over 5644.09 frames. ], batch size: 9, lr: 2.71e-02
2024-08-06 14:40:44,589 INFO [trainer.py:765] (6/8) Epoch 2, batch 700, train_loss[loss=5.053, NarTop10Accuracy=0.3179, over 4980.00 frames. ], tot_loss[loss=5.036, NarTop10Accuracy=0.3221, over 5721.30 frames. ], batch size: 6, lr: 2.70e-02
2024-08-06 14:41:24,514 INFO [trainer.py:765] (6/8) Epoch 2, batch 800, train_loss[loss=5.337, NarTop10Accuracy=0.2507, over 5019.00 frames. ], tot_loss[loss=5.018, NarTop10Accuracy=0.3252, over 5798.17 frames. ], batch size: 6, lr: 2.69e-02
2024-08-06 14:41:54,404 INFO [trainer.py:765] (6/8) Epoch 2, batch 900, train_loss[loss=4.846, NarTop10Accuracy=0.3545, over 6261.00 frames. ], tot_loss[loss=4.979, NarTop10Accuracy=0.333, over 5812.02 frames. ], batch size: 13, lr: 2.68e-02
2024-08-06 14:42:23,901 INFO [trainer.py:765] (6/8) Epoch 2, batch 1000, train_loss[loss=4.669, NarTop10Accuracy=0.4013, over 6057.00 frames. ], tot_loss[loss=4.951, NarTop10Accuracy=0.3381, over 5914.53 frames. ], batch size: 13, lr: 2.66e-02
2024-08-06 14:42:56,254 INFO [trainer.py:765] (6/8) Epoch 2, batch 1100, train_loss[loss=5.063, NarTop10Accuracy=0.3154, over 6690.00 frames. ], tot_loss[loss=4.929, NarTop10Accuracy=0.3422, over 5939.25 frames. ], batch size: 17, lr: 2.65e-02
2024-08-06 14:43:35,186 INFO [trainer.py:765] (6/8) Epoch 2, batch 1200, train_loss[loss=4.874, NarTop10Accuracy=0.3434, over 7110.00 frames. ], tot_loss[loss=4.907, NarTop10Accuracy=0.3459, over 5940.74 frames. ], batch size: 31, lr: 2.64e-02
2024-08-06 14:44:04,345 INFO [trainer.py:765] (6/8) Epoch 2, batch 1300, train_loss[loss=4.702, NarTop10Accuracy=0.3756, over 5205.00 frames. ], tot_loss[loss=4.868, NarTop10Accuracy=0.3535, over 5999.29 frames. ], batch size: 6, lr: 2.63e-02
2024-08-06 14:44:33,727 INFO [trainer.py:765] (6/8) Epoch 2, batch 1400, train_loss[loss=4.925, NarTop10Accuracy=0.3407, over 6105.00 frames. ], tot_loss[loss=4.853, NarTop10Accuracy=0.3564, over 6022.43 frames. ], batch size: 11, lr: 2.61e-02
2024-08-06 14:44:40,441 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 14:44:48,506 INFO [trainer.py:811] (6/8) Epoch 2, validation: loss=4.808, NarTop10Accuracy=0.3642, over 1905321.00 frames. 
2024-08-06 14:44:48,506 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 26729MB
2024-08-06 14:44:49,204 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 2, batch 1500, train_loss[loss=4.775, NarTop10Accuracy=0.3759, over 6087.00 frames. ], tot_loss[loss=4.827, NarTop10Accuracy=0.3615, over 5957.52 frames. ], batch size: 50, lr: 2.60e-02
2024-08-06 14:45:37,660 INFO [trainer.py:765] (6/8) Epoch 2, batch 1600, train_loss[loss=4.8, NarTop10Accuracy=0.3727, over 7080.00 frames. ], tot_loss[loss=4.795, NarTop10Accuracy=0.3674, over 5945.67 frames. ], batch size: 22, lr: 2.59e-02
2024-08-06 14:46:04,368 INFO [trainer.py:765] (6/8) Epoch 2, batch 1700, train_loss[loss=4.899, NarTop10Accuracy=0.3434, over 6162.00 frames. ], tot_loss[loss=4.792, NarTop10Accuracy=0.368, over 5928.32 frames. ], batch size: 13, lr: 2.58e-02
2024-08-06 14:46:31,034 INFO [trainer.py:765] (6/8) Epoch 2, batch 1800, train_loss[loss=4.702, NarTop10Accuracy=0.381, over 7020.00 frames. ], tot_loss[loss=4.768, NarTop10Accuracy=0.3731, over 5982.84 frames. ], batch size: 22, lr: 2.56e-02
2024-08-06 14:46:57,532 INFO [trainer.py:765] (6/8) Epoch 2, batch 1900, train_loss[loss=4.763, NarTop10Accuracy=0.3704, over 6492.00 frames. ], tot_loss[loss=4.75, NarTop10Accuracy=0.3764, over 6027.17 frames. ], batch size: 50, lr: 2.55e-02
2024-08-06 14:47:23,234 INFO [trainer.py:765] (6/8) Epoch 2, batch 2000, train_loss[loss=4.864, NarTop10Accuracy=0.3535, over 6222.00 frames. ], tot_loss[loss=4.726, NarTop10Accuracy=0.3807, over 5988.26 frames. ], batch size: 51, lr: 2.54e-02
2024-08-06 14:47:48,589 INFO [trainer.py:765] (6/8) Epoch 2, batch 2100, train_loss[loss=4.575, NarTop10Accuracy=0.4124, over 4011.00 frames. ], tot_loss[loss=4.721, NarTop10Accuracy=0.3816, over 5972.45 frames. ], batch size: 4, lr: 2.53e-02
2024-08-06 14:48:13,765 INFO [trainer.py:765] (6/8) Epoch 2, batch 2200, train_loss[loss=4.749, NarTop10Accuracy=0.3711, over 7197.00 frames. ], tot_loss[loss=4.685, NarTop10Accuracy=0.3886, over 6013.84 frames. ], batch size: 31, lr: 2.51e-02
2024-08-06 14:48:38,952 INFO [trainer.py:765] (6/8) Epoch 2, batch 2300, train_loss[loss=4.878, NarTop10Accuracy=0.3546, over 5667.00 frames. ], tot_loss[loss=4.688, NarTop10Accuracy=0.3879, over 6035.89 frames. ], batch size: 9, lr: 2.50e-02
2024-08-06 14:49:03,319 INFO [trainer.py:765] (6/8) Epoch 2, batch 2400, train_loss[loss=4.486, NarTop10Accuracy=0.4316, over 5166.00 frames. ], tot_loss[loss=4.644, NarTop10Accuracy=0.3963, over 5779.80 frames. ], batch size: 7, lr: 2.49e-02
2024-08-06 14:49:26,868 INFO [trainer.py:765] (6/8) Epoch 2, batch 2500, train_loss[loss=4.712, NarTop10Accuracy=0.3843, over 5142.00 frames. ], tot_loss[loss=4.62, NarTop10Accuracy=0.401, over 5499.64 frames. ], batch size: 7, lr: 2.48e-02
2024-08-06 14:49:46,731 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 14:50:51,116 INFO [trainer.py:765] (6/8) Epoch 3, batch 100, train_loss[loss=4.709, NarTop10Accuracy=0.3814, over 7143.00 frames. ], tot_loss[loss=4.567, NarTop10Accuracy=0.4112, over 2365.63 frames. ], batch size: 31, lr: 2.36e-02
2024-08-06 14:51:20,387 INFO [trainer.py:765] (6/8) Epoch 3, batch 200, train_loss[loss=4.556, NarTop10Accuracy=0.4119, over 6699.00 frames. ], tot_loss[loss=4.54, NarTop10Accuracy=0.4171, over 3840.91 frames. ], batch size: 17, lr: 2.34e-02
2024-08-06 14:51:50,953 INFO [trainer.py:765] (6/8) Epoch 3, batch 300, train_loss[loss=4.808, NarTop10Accuracy=0.3658, over 7284.00 frames. ], tot_loss[loss=4.511, NarTop10Accuracy=0.4227, over 4654.51 frames. ], batch size: 23, lr: 2.33e-02
2024-08-06 14:52:32,359 INFO [trainer.py:765] (6/8) Epoch 3, batch 400, train_loss[loss=4.585, NarTop10Accuracy=0.3922, over 5139.00 frames. ], tot_loss[loss=4.484, NarTop10Accuracy=0.4278, over 5096.30 frames. ], batch size: 7, lr: 2.32e-02
2024-08-06 14:53:00,679 INFO [trainer.py:765] (6/8) Epoch 3, batch 500, train_loss[loss=4.188, NarTop10Accuracy=0.4876, over 6045.00 frames. ], tot_loss[loss=4.482, NarTop10Accuracy=0.428, over 5375.17 frames. ], batch size: 11, lr: 2.31e-02
2024-08-06 14:53:29,551 INFO [trainer.py:765] (6/8) Epoch 3, batch 600, train_loss[loss=4.419, NarTop10Accuracy=0.4393, over 5655.00 frames. ], tot_loss[loss=4.472, NarTop10Accuracy=0.4299, over 5641.04 frames. ], batch size: 9, lr: 2.30e-02
2024-08-06 14:54:12,465 INFO [trainer.py:765] (6/8) Epoch 3, batch 700, train_loss[loss=4.082, NarTop10Accuracy=0.4973, over 5106.00 frames. ], tot_loss[loss=4.441, NarTop10Accuracy=0.4361, over 5705.32 frames. ], batch size: 6, lr: 2.29e-02
2024-08-06 14:54:44,784 INFO [trainer.py:765] (6/8) Epoch 3, batch 800, train_loss[loss=4.206, NarTop10Accuracy=0.48, over 4977.00 frames. ], tot_loss[loss=4.418, NarTop10Accuracy=0.4409, over 5769.07 frames. ], batch size: 6, lr: 2.28e-02
2024-08-06 14:54:58,684 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 14:55:06,655 INFO [trainer.py:811] (6/8) Epoch 3, validation: loss=4.276, NarTop10Accuracy=0.4689, over 1905321.00 frames. 
2024-08-06 14:55:06,656 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 26864MB
2024-08-06 14:55:07,182 INFO [optim.py:386] (6/8) 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 14:55:21,051 INFO [trainer.py:765] (6/8) Epoch 3, batch 900, train_loss[loss=4.175, NarTop10Accuracy=0.4891, over 6333.00 frames. ], tot_loss[loss=4.387, NarTop10Accuracy=0.4471, over 5807.82 frames. ], batch size: 13, lr: 2.26e-02
2024-08-06 14:56:04,957 INFO [trainer.py:765] (6/8) Epoch 3, batch 1000, train_loss[loss=4.264, NarTop10Accuracy=0.4725, over 6189.00 frames. ], tot_loss[loss=4.371, NarTop10Accuracy=0.45, over 5911.64 frames. ], batch size: 13, lr: 2.25e-02
2024-08-06 14:56:37,300 INFO [trainer.py:765] (6/8) Epoch 3, batch 1100, train_loss[loss=4.499, NarTop10Accuracy=0.4129, over 7131.00 frames. ], tot_loss[loss=4.348, NarTop10Accuracy=0.454, over 5940.54 frames. ], batch size: 18, lr: 2.24e-02
2024-08-06 14:57:06,377 INFO [trainer.py:765] (6/8) Epoch 3, batch 1200, train_loss[loss=4.327, NarTop10Accuracy=0.4566, over 7254.00 frames. ], tot_loss[loss=4.335, NarTop10Accuracy=0.457, over 5939.96 frames. ], batch size: 31, lr: 2.23e-02
2024-08-06 14:57:51,630 INFO [trainer.py:765] (6/8) Epoch 3, batch 1300, train_loss[loss=4.256, NarTop10Accuracy=0.4727, over 5109.00 frames. ], tot_loss[loss=4.305, NarTop10Accuracy=0.4631, over 6001.43 frames. ], batch size: 6, lr: 2.22e-02
2024-08-06 14:58:22,899 INFO [trainer.py:765] (6/8) Epoch 3, batch 1400, train_loss[loss=4.141, NarTop10Accuracy=0.4982, over 6000.00 frames. ], tot_loss[loss=4.294, NarTop10Accuracy=0.4649, over 6020.30 frames. ], batch size: 11, lr: 2.21e-02
2024-08-06 14:58:50,854 INFO [trainer.py:765] (6/8) Epoch 3, batch 1500, train_loss[loss=4.311, NarTop10Accuracy=0.4604, over 5448.00 frames. ], tot_loss[loss=4.269, NarTop10Accuracy=0.4694, over 5952.85 frames. ], batch size: 50, lr: 2.20e-02
2024-08-06 14:59:18,714 INFO [trainer.py:765] (6/8) Epoch 3, batch 1600, train_loss[loss=4.024, NarTop10Accuracy=0.5187, over 7134.00 frames. ], tot_loss[loss=4.256, NarTop10Accuracy=0.4715, over 5928.05 frames. ], batch size: 22, lr: 2.19e-02
2024-08-06 14:59:45,951 INFO [trainer.py:765] (6/8) Epoch 3, batch 1700, train_loss[loss=4.103, NarTop10Accuracy=0.5031, over 6582.00 frames. ], tot_loss[loss=4.233, NarTop10Accuracy=0.4762, over 5910.14 frames. ], batch size: 14, lr: 2.18e-02
2024-08-06 15:00:12,498 INFO [trainer.py:765] (6/8) Epoch 3, batch 1800, train_loss[loss=3.973, NarTop10Accuracy=0.5287, over 7011.00 frames. ], tot_loss[loss=4.208, NarTop10Accuracy=0.4816, over 5995.22 frames. ], batch size: 22, lr: 2.17e-02
2024-08-06 15:00:38,948 INFO [trainer.py:765] (6/8) Epoch 3, batch 1900, train_loss[loss=4.741, NarTop10Accuracy=0.3801, over 6306.00 frames. ], tot_loss[loss=4.198, NarTop10Accuracy=0.4836, over 6037.25 frames. ], batch size: 50, lr: 2.16e-02
2024-08-06 15:01:04,606 INFO [trainer.py:765] (6/8) Epoch 3, batch 2000, train_loss[loss=4.354, NarTop10Accuracy=0.4459, over 6072.00 frames. ], tot_loss[loss=4.17, NarTop10Accuracy=0.4891, over 6015.47 frames. ], batch size: 50, lr: 2.15e-02
2024-08-06 15:01:29,898 INFO [trainer.py:765] (6/8) Epoch 3, batch 2100, train_loss[loss=3.565, NarTop10Accuracy=0.6158, over 3849.00 frames. ], tot_loss[loss=4.142, NarTop10Accuracy=0.4947, over 5987.73 frames. ], batch size: 4, lr: 2.14e-02
2024-08-06 15:01:55,182 INFO [trainer.py:765] (6/8) Epoch 3, batch 2200, train_loss[loss=3.867, NarTop10Accuracy=0.5503, over 7161.00 frames. ], tot_loss[loss=4.115, NarTop10Accuracy=0.5003, over 6014.94 frames. ], batch size: 31, lr: 2.13e-02
2024-08-06 15:02:20,410 INFO [trainer.py:765] (6/8) Epoch 3, batch 2300, train_loss[loss=4.442, NarTop10Accuracy=0.4245, over 5805.00 frames. ], tot_loss[loss=4.125, NarTop10Accuracy=0.4986, over 6009.02 frames. ], batch size: 9, lr: 2.12e-02
2024-08-06 15:02:44,663 INFO [trainer.py:765] (6/8) Epoch 3, batch 2400, train_loss[loss=4.271, NarTop10Accuracy=0.4715, over 5100.00 frames. ], tot_loss[loss=4.096, NarTop10Accuracy=0.5043, over 5765.52 frames. ], batch size: 7, lr: 2.11e-02
2024-08-06 15:03:08,234 INFO [trainer.py:765] (6/8) Epoch 3, batch 2500, train_loss[loss=3.728, NarTop10Accuracy=0.5718, over 5127.00 frames. ], tot_loss[loss=4.045, NarTop10Accuracy=0.5146, over 5463.88 frames. ], batch size: 7, lr: 2.10e-02
2024-08-06 15:03:28,326 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 15:04:28,131 INFO [trainer.py:765] (6/8) Epoch 4, batch 100, train_loss[loss=3.821, NarTop10Accuracy=0.5638, over 7323.00 frames. ], tot_loss[loss=4.035, NarTop10Accuracy=0.5177, over 2389.36 frames. ], batch size: 31, lr: 1.97e-02
2024-08-06 15:04:59,842 INFO [trainer.py:765] (6/8) Epoch 4, batch 200, train_loss[loss=3.87, NarTop10Accuracy=0.5537, over 6822.00 frames. ], tot_loss[loss=4.011, NarTop10Accuracy=0.5224, over 3875.56 frames. ], batch size: 17, lr: 1.96e-02
2024-08-06 15:05:27,509 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 15:05:35,694 INFO [trainer.py:811] (6/8) Epoch 4, validation: loss=3.804, NarTop10Accuracy=0.5644, over 1905321.00 frames. 
2024-08-06 15:05:35,695 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 27368MB
2024-08-06 15:05:36,237 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 4, batch 300, train_loss[loss=3.701, NarTop10Accuracy=0.5839, over 7074.00 frames. ], tot_loss[loss=3.996, NarTop10Accuracy=0.5252, over 4670.95 frames. ], batch size: 22, lr: 1.95e-02
2024-08-06 15:06:16,124 INFO [trainer.py:765] (6/8) Epoch 4, batch 400, train_loss[loss=3.745, NarTop10Accuracy=0.5819, over 5187.00 frames. ], tot_loss[loss=4.004, NarTop10Accuracy=0.5237, over 5112.98 frames. ], batch size: 7, lr: 1.94e-02
2024-08-06 15:06:46,473 INFO [trainer.py:765] (6/8) Epoch 4, batch 500, train_loss[loss=4.044, NarTop10Accuracy=0.5068, over 6117.00 frames. ], tot_loss[loss=3.984, NarTop10Accuracy=0.5281, over 5387.52 frames. ], batch size: 11, lr: 1.93e-02
2024-08-06 15:07:23,818 INFO [trainer.py:765] (6/8) Epoch 4, batch 600, train_loss[loss=3.795, NarTop10Accuracy=0.5682, over 5742.00 frames. ], tot_loss[loss=3.981, NarTop10Accuracy=0.5284, over 5655.73 frames. ], batch size: 9, lr: 1.93e-02
2024-08-06 15:07:59,002 INFO [trainer.py:765] (6/8) Epoch 4, batch 700, train_loss[loss=4.22, NarTop10Accuracy=0.4886, over 5001.00 frames. ], tot_loss[loss=3.979, NarTop10Accuracy=0.5287, over 5720.42 frames. ], batch size: 6, lr: 1.92e-02
2024-08-06 15:08:32,429 INFO [trainer.py:765] (6/8) Epoch 4, batch 800, train_loss[loss=3.677, NarTop10Accuracy=0.5928, over 4977.00 frames. ], tot_loss[loss=3.964, NarTop10Accuracy=0.5314, over 5783.39 frames. ], batch size: 6, lr: 1.91e-02
2024-08-06 15:09:10,689 INFO [trainer.py:765] (6/8) Epoch 4, batch 900, train_loss[loss=3.631, NarTop10Accuracy=0.6039, over 6231.00 frames. ], tot_loss[loss=3.925, NarTop10Accuracy=0.5397, over 5785.27 frames. ], batch size: 13, lr: 1.90e-02
2024-08-06 15:09:46,075 INFO [trainer.py:765] (6/8) Epoch 4, batch 1000, train_loss[loss=3.618, NarTop10Accuracy=0.6036, over 6159.00 frames. ], tot_loss[loss=3.92, NarTop10Accuracy=0.5408, over 5896.88 frames. ], batch size: 13, lr: 1.89e-02
2024-08-06 15:10:18,140 INFO [trainer.py:765] (6/8) Epoch 4, batch 1100, train_loss[loss=3.94, NarTop10Accuracy=0.548, over 6756.00 frames. ], tot_loss[loss=3.911, NarTop10Accuracy=0.5426, over 5931.15 frames. ], batch size: 17, lr: 1.88e-02
2024-08-06 15:10:55,075 INFO [trainer.py:765] (6/8) Epoch 4, batch 1200, train_loss[loss=4.343, NarTop10Accuracy=0.4539, over 7155.00 frames. ], tot_loss[loss=3.907, NarTop10Accuracy=0.5434, over 5928.15 frames. ], batch size: 31, lr: 1.88e-02
2024-08-06 15:11:32,074 INFO [trainer.py:765] (6/8) Epoch 4, batch 1300, train_loss[loss=3.646, NarTop10Accuracy=0.6058, over 5241.00 frames. ], tot_loss[loss=3.864, NarTop10Accuracy=0.5521, over 6003.41 frames. ], batch size: 6, lr: 1.87e-02
2024-08-06 15:12:05,688 INFO [trainer.py:765] (6/8) Epoch 4, batch 1400, train_loss[loss=3.755, NarTop10Accuracy=0.5785, over 6219.00 frames. ], tot_loss[loss=3.857, NarTop10Accuracy=0.5535, over 6027.73 frames. ], batch size: 11, lr: 1.86e-02
2024-08-06 15:12:33,695 INFO [trainer.py:765] (6/8) Epoch 4, batch 1500, train_loss[loss=3.913, NarTop10Accuracy=0.5492, over 6015.00 frames. ], tot_loss[loss=3.858, NarTop10Accuracy=0.5535, over 5943.66 frames. ], batch size: 52, lr: 1.85e-02
2024-08-06 15:13:01,510 INFO [trainer.py:765] (6/8) Epoch 4, batch 1600, train_loss[loss=3.692, NarTop10Accuracy=0.5979, over 7236.00 frames. ], tot_loss[loss=3.851, NarTop10Accuracy=0.5548, over 5915.05 frames. ], batch size: 22, lr: 1.84e-02
2024-08-06 15:13:28,133 INFO [trainer.py:765] (6/8) Epoch 4, batch 1700, train_loss[loss=3.899, NarTop10Accuracy=0.5437, over 6708.00 frames. ], tot_loss[loss=3.827, NarTop10Accuracy=0.559, over 5891.09 frames. ], batch size: 14, lr: 1.84e-02
2024-08-06 15:13:54,557 INFO [trainer.py:765] (6/8) Epoch 4, batch 1800, train_loss[loss=3.742, NarTop10Accuracy=0.5763, over 7113.00 frames. ], tot_loss[loss=3.832, NarTop10Accuracy=0.5584, over 5946.88 frames. ], batch size: 22, lr: 1.83e-02
2024-08-06 15:14:20,998 INFO [trainer.py:765] (6/8) Epoch 4, batch 1900, train_loss[loss=3.801, NarTop10Accuracy=0.5669, over 5913.00 frames. ], tot_loss[loss=3.85, NarTop10Accuracy=0.5546, over 6003.91 frames. ], batch size: 51, lr: 1.82e-02
2024-08-06 15:14:46,671 INFO [trainer.py:765] (6/8) Epoch 4, batch 2000, train_loss[loss=3.666, NarTop10Accuracy=0.5932, over 6324.00 frames. ], tot_loss[loss=3.82, NarTop10Accuracy=0.5608, over 5997.93 frames. ], batch size: 50, lr: 1.81e-02
2024-08-06 15:15:11,859 INFO [trainer.py:765] (6/8) Epoch 4, batch 2100, train_loss[loss=3.705, NarTop10Accuracy=0.5778, over 3903.00 frames. ], tot_loss[loss=3.812, NarTop10Accuracy=0.5626, over 5968.68 frames. ], batch size: 4, lr: 1.81e-02
2024-08-06 15:15:37,089 INFO [trainer.py:765] (6/8) Epoch 4, batch 2200, train_loss[loss=3.626, NarTop10Accuracy=0.6057, over 7191.00 frames. ], tot_loss[loss=3.804, NarTop10Accuracy=0.5642, over 5994.73 frames. ], batch size: 31, lr: 1.80e-02
2024-08-06 15:15:55,089 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 15:16:03,242 INFO [trainer.py:811] (6/8) Epoch 4, validation: loss=3.665, NarTop10Accuracy=0.5912, over 1905321.00 frames. 
2024-08-06 15:16:03,243 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 29575MB
2024-08-06 15:16:03,740 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 4, batch 2300, train_loss[loss=3.596, NarTop10Accuracy=0.5997, over 5802.00 frames. ], tot_loss[loss=3.809, NarTop10Accuracy=0.5635, over 6008.90 frames. ], batch size: 9, lr: 1.79e-02
2024-08-06 15:16:34,840 INFO [trainer.py:765] (6/8) Epoch 4, batch 2400, train_loss[loss=3.601, NarTop10Accuracy=0.6083, over 5136.00 frames. ], tot_loss[loss=3.777, NarTop10Accuracy=0.5696, over 5759.05 frames. ], batch size: 7, lr: 1.79e-02
2024-08-06 15:16:58,534 INFO [trainer.py:765] (6/8) Epoch 4, batch 2500, train_loss[loss=3.595, NarTop10Accuracy=0.6189, over 5052.00 frames. ], tot_loss[loss=3.762, NarTop10Accuracy=0.5723, over 5475.95 frames. ], batch size: 7, lr: 1.78e-02
2024-08-06 15:17:18,827 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 15:18:24,100 INFO [trainer.py:765] (6/8) Epoch 5, batch 100, train_loss[loss=3.484, NarTop10Accuracy=0.6289, over 7389.00 frames. ], tot_loss[loss=3.783, NarTop10Accuracy=0.5683, over 2360.81 frames. ], batch size: 31, lr: 1.66e-02
2024-08-06 15:18:59,675 INFO [trainer.py:765] (6/8) Epoch 5, batch 200, train_loss[loss=4.093, NarTop10Accuracy=0.5035, over 6828.00 frames. ], tot_loss[loss=3.757, NarTop10Accuracy=0.5742, over 3852.68 frames. ], batch size: 17, lr: 1.65e-02
2024-08-06 15:19:32,887 INFO [trainer.py:765] (6/8) Epoch 5, batch 300, train_loss[loss=3.99, NarTop10Accuracy=0.5218, over 7098.00 frames. ], tot_loss[loss=3.73, NarTop10Accuracy=0.5794, over 4659.91 frames. ], batch size: 22, lr: 1.65e-02
2024-08-06 15:20:01,656 INFO [trainer.py:765] (6/8) Epoch 5, batch 400, train_loss[loss=3.41, NarTop10Accuracy=0.6437, over 5097.00 frames. ], tot_loss[loss=3.72, NarTop10Accuracy=0.5814, over 5099.05 frames. ], batch size: 7, lr: 1.64e-02
2024-08-06 15:20:38,298 INFO [trainer.py:765] (6/8) Epoch 5, batch 500, train_loss[loss=4.013, NarTop10Accuracy=0.512, over 6171.00 frames. ], tot_loss[loss=3.738, NarTop10Accuracy=0.5773, over 5384.88 frames. ], batch size: 11, lr: 1.63e-02
2024-08-06 15:21:13,710 INFO [trainer.py:765] (6/8) Epoch 5, batch 600, train_loss[loss=3.923, NarTop10Accuracy=0.5268, over 5745.00 frames. ], tot_loss[loss=3.731, NarTop10Accuracy=0.5787, over 5645.61 frames. ], batch size: 9, lr: 1.63e-02
2024-08-06 15:21:45,881 INFO [trainer.py:765] (6/8) Epoch 5, batch 700, train_loss[loss=3.375, NarTop10Accuracy=0.6532, over 5130.00 frames. ], tot_loss[loss=3.72, NarTop10Accuracy=0.5809, over 5718.32 frames. ], batch size: 6, lr: 1.62e-02
2024-08-06 15:22:24,498 INFO [trainer.py:765] (6/8) Epoch 5, batch 800, train_loss[loss=3.869, NarTop10Accuracy=0.5337, over 4974.00 frames. ], tot_loss[loss=3.705, NarTop10Accuracy=0.5837, over 5770.67 frames. ], batch size: 6, lr: 1.62e-02
2024-08-06 15:22:56,783 INFO [trainer.py:765] (6/8) Epoch 5, batch 900, train_loss[loss=3.631, NarTop10Accuracy=0.5919, over 6171.00 frames. ], tot_loss[loss=3.692, NarTop10Accuracy=0.5863, over 5806.32 frames. ], batch size: 13, lr: 1.61e-02
2024-08-06 15:23:31,914 INFO [trainer.py:765] (6/8) Epoch 5, batch 1000, train_loss[loss=3.577, NarTop10Accuracy=0.6192, over 6129.00 frames. ], tot_loss[loss=3.683, NarTop10Accuracy=0.5884, over 5883.92 frames. ], batch size: 13, lr: 1.60e-02
2024-08-06 15:24:09,572 INFO [trainer.py:765] (6/8) Epoch 5, batch 1100, train_loss[loss=3.51, NarTop10Accuracy=0.6275, over 6792.00 frames. ], tot_loss[loss=3.681, NarTop10Accuracy=0.5893, over 5923.67 frames. ], batch size: 17, lr: 1.60e-02
2024-08-06 15:24:44,528 INFO [trainer.py:765] (6/8) Epoch 5, batch 1200, train_loss[loss=3.529, NarTop10Accuracy=0.6197, over 7092.00 frames. ], tot_loss[loss=3.676, NarTop10Accuracy=0.59, over 5934.67 frames. ], batch size: 31, lr: 1.59e-02
2024-08-06 15:25:19,379 INFO [trainer.py:765] (6/8) Epoch 5, batch 1300, train_loss[loss=3.78, NarTop10Accuracy=0.5559, over 5043.00 frames. ], tot_loss[loss=3.664, NarTop10Accuracy=0.5922, over 6008.46 frames. ], batch size: 6, lr: 1.59e-02
2024-08-06 15:25:51,694 INFO [trainer.py:765] (6/8) Epoch 5, batch 1400, train_loss[loss=3.842, NarTop10Accuracy=0.5492, over 6090.00 frames. ], tot_loss[loss=3.672, NarTop10Accuracy=0.5906, over 6016.33 frames. ], batch size: 11, lr: 1.58e-02
2024-08-06 15:26:26,195 INFO [trainer.py:765] (6/8) Epoch 5, batch 1500, train_loss[loss=3.704, NarTop10Accuracy=0.583, over 6051.00 frames. ], tot_loss[loss=3.667, NarTop10Accuracy=0.5916, over 5956.63 frames. ], batch size: 51, lr: 1.58e-02
2024-08-06 15:26:54,130 INFO [trainer.py:765] (6/8) Epoch 5, batch 1600, train_loss[loss=3.51, NarTop10Accuracy=0.6318, over 7203.00 frames. ], tot_loss[loss=3.677, NarTop10Accuracy=0.5896, over 5944.78 frames. ], batch size: 22, lr: 1.57e-02
2024-08-06 15:27:19,603 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 15:27:27,821 INFO [trainer.py:811] (6/8) Epoch 5, validation: loss=3.552, NarTop10Accuracy=0.6147, over 1905321.00 frames. 
2024-08-06 15:27:27,822 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 29995MB
2024-08-06 15:27:28,341 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 5, batch 1700, train_loss[loss=3.689, NarTop10Accuracy=0.5805, over 6264.00 frames. ], tot_loss[loss=3.669, NarTop10Accuracy=0.5911, over 5918.73 frames. ], batch size: 13, lr: 1.56e-02
2024-08-06 15:27:55,652 INFO [trainer.py:765] (6/8) Epoch 5, batch 1800, train_loss[loss=3.867, NarTop10Accuracy=0.5422, over 7086.00 frames. ], tot_loss[loss=3.659, NarTop10Accuracy=0.5931, over 5984.35 frames. ], batch size: 22, lr: 1.56e-02
2024-08-06 15:28:22,172 INFO [trainer.py:765] (6/8) Epoch 5, batch 1900, train_loss[loss=3.678, NarTop10Accuracy=0.5972, over 6312.00 frames. ], tot_loss[loss=3.669, NarTop10Accuracy=0.591, over 6037.42 frames. ], batch size: 51, lr: 1.55e-02
2024-08-06 15:28:47,893 INFO [trainer.py:765] (6/8) Epoch 5, batch 2000, train_loss[loss=3.68, NarTop10Accuracy=0.5899, over 5841.00 frames. ], tot_loss[loss=3.673, NarTop10Accuracy=0.5902, over 6006.26 frames. ], batch size: 50, lr: 1.55e-02
2024-08-06 15:29:13,770 INFO [trainer.py:765] (6/8) Epoch 5, batch 2100, train_loss[loss=3.384, NarTop10Accuracy=0.6542, over 4815.00 frames. ], tot_loss[loss=3.686, NarTop10Accuracy=0.5873, over 5970.34 frames. ], batch size: 5, lr: 1.54e-02
2024-08-06 15:29:39,177 INFO [trainer.py:765] (6/8) Epoch 5, batch 2200, train_loss[loss=3.972, NarTop10Accuracy=0.5312, over 7245.00 frames. ], tot_loss[loss=3.666, NarTop10Accuracy=0.5915, over 6003.28 frames. ], batch size: 31, lr: 1.54e-02
2024-08-06 15:30:04,430 INFO [trainer.py:765] (6/8) Epoch 5, batch 2300, train_loss[loss=3.445, NarTop10Accuracy=0.6377, over 5787.00 frames. ], tot_loss[loss=3.667, NarTop10Accuracy=0.5911, over 6012.66 frames. ], batch size: 9, lr: 1.53e-02
2024-08-06 15:30:28,862 INFO [trainer.py:765] (6/8) Epoch 5, batch 2400, train_loss[loss=3.541, NarTop10Accuracy=0.6148, over 5643.00 frames. ], tot_loss[loss=3.646, NarTop10Accuracy=0.5951, over 5769.75 frames. ], batch size: 8, lr: 1.53e-02
2024-08-06 15:30:52,503 INFO [trainer.py:765] (6/8) Epoch 5, batch 2500, train_loss[loss=3.503, NarTop10Accuracy=0.6298, over 5187.00 frames. ], tot_loss[loss=3.614, NarTop10Accuracy=0.6018, over 5479.21 frames. ], batch size: 7, lr: 1.52e-02
2024-08-06 15:31:12,173 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 15:32:14,414 INFO [trainer.py:765] (6/8) Epoch 6, batch 100, train_loss[loss=3.508, NarTop10Accuracy=0.6289, over 7344.00 frames. ], tot_loss[loss=3.639, NarTop10Accuracy=0.5969, over 2366.39 frames. ], batch size: 31, lr: 1.42e-02
2024-08-06 15:32:46,015 INFO [trainer.py:765] (6/8) Epoch 6, batch 200, train_loss[loss=4.088, NarTop10Accuracy=0.504, over 6828.00 frames. ], tot_loss[loss=3.617, NarTop10Accuracy=0.6015, over 3855.86 frames. ], batch size: 17, lr: 1.42e-02
2024-08-06 15:33:21,242 INFO [trainer.py:765] (6/8) Epoch 6, batch 300, train_loss[loss=3.378, NarTop10Accuracy=0.6605, over 6942.00 frames. ], tot_loss[loss=3.607, NarTop10Accuracy=0.6034, over 4656.06 frames. ], batch size: 22, lr: 1.41e-02
2024-08-06 15:33:56,035 INFO [trainer.py:765] (6/8) Epoch 6, batch 400, train_loss[loss=3.341, NarTop10Accuracy=0.6597, over 4992.00 frames. ], tot_loss[loss=3.585, NarTop10Accuracy=0.6082, over 5101.08 frames. ], batch size: 7, lr: 1.41e-02
2024-08-06 15:34:26,759 INFO [trainer.py:765] (6/8) Epoch 6, batch 500, train_loss[loss=3.298, NarTop10Accuracy=0.6725, over 6054.00 frames. ], tot_loss[loss=3.572, NarTop10Accuracy=0.6109, over 5382.42 frames. ], batch size: 11, lr: 1.40e-02
2024-08-06 15:35:01,457 INFO [trainer.py:765] (6/8) Epoch 6, batch 600, train_loss[loss=3.568, NarTop10Accuracy=0.6126, over 5637.00 frames. ], tot_loss[loss=3.572, NarTop10Accuracy=0.6107, over 5661.45 frames. ], batch size: 9, lr: 1.40e-02
2024-08-06 15:35:32,733 INFO [trainer.py:765] (6/8) Epoch 6, batch 700, train_loss[loss=3.769, NarTop10Accuracy=0.5701, over 5109.00 frames. ], tot_loss[loss=3.587, NarTop10Accuracy=0.6078, over 5703.56 frames. ], batch size: 6, lr: 1.39e-02
2024-08-06 15:36:06,844 INFO [trainer.py:765] (6/8) Epoch 6, batch 800, train_loss[loss=3.668, NarTop10Accuracy=0.5896, over 5112.00 frames. ], tot_loss[loss=3.596, NarTop10Accuracy=0.606, over 5749.08 frames. ], batch size: 6, lr: 1.39e-02
2024-08-06 15:36:40,384 INFO [trainer.py:765] (6/8) Epoch 6, batch 900, train_loss[loss=4.044, NarTop10Accuracy=0.5114, over 6591.00 frames. ], tot_loss[loss=3.58, NarTop10Accuracy=0.6093, over 5776.73 frames. ], batch size: 14, lr: 1.38e-02
2024-08-06 15:37:15,271 INFO [trainer.py:765] (6/8) Epoch 6, batch 1000, train_loss[loss=3.288, NarTop10Accuracy=0.67, over 6105.00 frames. ], tot_loss[loss=3.594, NarTop10Accuracy=0.606, over 5901.50 frames. ], batch size: 13, lr: 1.38e-02
2024-08-06 15:37:50,508 INFO [trainer.py:765] (6/8) Epoch 6, batch 1100, train_loss[loss=3.419, NarTop10Accuracy=0.6403, over 6924.00 frames. ], tot_loss[loss=3.589, NarTop10Accuracy=0.6075, over 5934.86 frames. ], batch size: 17, lr: 1.38e-02
2024-08-06 15:37:55,826 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 15:38:04,436 INFO [trainer.py:811] (6/8) Epoch 6, validation: loss=3.421, NarTop10Accuracy=0.6418, over 1905321.00 frames. 
2024-08-06 15:38:04,437 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 29995MB
2024-08-06 15:38:04,966 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 6, batch 1200, train_loss[loss=3.468, NarTop10Accuracy=0.6332, over 7347.00 frames. ], tot_loss[loss=3.577, NarTop10Accuracy=0.6097, over 5935.59 frames. ], batch size: 31, lr: 1.37e-02
2024-08-06 15:39:08,242 INFO [trainer.py:765] (6/8) Epoch 6, batch 1300, train_loss[loss=3.288, NarTop10Accuracy=0.6683, over 4962.00 frames. ], tot_loss[loss=3.572, NarTop10Accuracy=0.6106, over 5998.94 frames. ], batch size: 6, lr: 1.37e-02
2024-08-06 15:39:44,070 INFO [trainer.py:765] (6/8) Epoch 6, batch 1400, train_loss[loss=3.332, NarTop10Accuracy=0.6575, over 6063.00 frames. ], tot_loss[loss=3.569, NarTop10Accuracy=0.6115, over 6025.86 frames. ], batch size: 11, lr: 1.36e-02
2024-08-06 15:40:15,383 INFO [trainer.py:765] (6/8) Epoch 6, batch 1500, train_loss[loss=3.915, NarTop10Accuracy=0.5409, over 6366.00 frames. ], tot_loss[loss=3.57, NarTop10Accuracy=0.6115, over 5956.81 frames. ], batch size: 51, lr: 1.36e-02
2024-08-06 15:40:43,106 INFO [trainer.py:765] (6/8) Epoch 6, batch 1600, train_loss[loss=3.361, NarTop10Accuracy=0.6477, over 7125.00 frames. ], tot_loss[loss=3.563, NarTop10Accuracy=0.6129, over 5939.07 frames. ], batch size: 22, lr: 1.35e-02
2024-08-06 15:41:09,789 INFO [trainer.py:765] (6/8) Epoch 6, batch 1700, train_loss[loss=3.665, NarTop10Accuracy=0.5935, over 6300.00 frames. ], tot_loss[loss=3.557, NarTop10Accuracy=0.614, over 5911.71 frames. ], batch size: 13, lr: 1.35e-02
2024-08-06 15:41:36,317 INFO [trainer.py:765] (6/8) Epoch 6, batch 1800, train_loss[loss=3.326, NarTop10Accuracy=0.6718, over 7083.00 frames. ], tot_loss[loss=3.562, NarTop10Accuracy=0.6127, over 5974.72 frames. ], batch size: 22, lr: 1.35e-02
2024-08-06 15:42:02,720 INFO [trainer.py:765] (6/8) Epoch 6, batch 1900, train_loss[loss=3.825, NarTop10Accuracy=0.5578, over 5892.00 frames. ], tot_loss[loss=3.578, NarTop10Accuracy=0.6094, over 6019.47 frames. ], batch size: 50, lr: 1.34e-02
2024-08-06 15:42:28,319 INFO [trainer.py:765] (6/8) Epoch 6, batch 2000, train_loss[loss=3.438, NarTop10Accuracy=0.6349, over 5970.00 frames. ], tot_loss[loss=3.574, NarTop10Accuracy=0.6103, over 5978.01 frames. ], batch size: 50, lr: 1.34e-02
2024-08-06 15:42:53,668 INFO [trainer.py:765] (6/8) Epoch 6, batch 2100, train_loss[loss=3.439, NarTop10Accuracy=0.6464, over 3807.00 frames. ], tot_loss[loss=3.567, NarTop10Accuracy=0.6118, over 5972.15 frames. ], batch size: 4, lr: 1.33e-02
2024-08-06 15:43:18,977 INFO [trainer.py:765] (6/8) Epoch 6, batch 2200, train_loss[loss=3.796, NarTop10Accuracy=0.566, over 7212.00 frames. ], tot_loss[loss=3.568, NarTop10Accuracy=0.6113, over 6012.27 frames. ], batch size: 31, lr: 1.33e-02
2024-08-06 15:43:44,106 INFO [trainer.py:765] (6/8) Epoch 6, batch 2300, train_loss[loss=3.306, NarTop10Accuracy=0.6715, over 5631.00 frames. ], tot_loss[loss=3.569, NarTop10Accuracy=0.6111, over 6037.84 frames. ], batch size: 9, lr: 1.33e-02
2024-08-06 15:44:08,620 INFO [trainer.py:765] (6/8) Epoch 6, batch 2400, train_loss[loss=3.274, NarTop10Accuracy=0.6765, over 5124.00 frames. ], tot_loss[loss=3.535, NarTop10Accuracy=0.6183, over 5788.26 frames. ], batch size: 7, lr: 1.32e-02
2024-08-06 15:44:32,132 INFO [trainer.py:765] (6/8) Epoch 6, batch 2500, train_loss[loss=3.619, NarTop10Accuracy=0.6062, over 5196.00 frames. ], tot_loss[loss=3.52, NarTop10Accuracy=0.621, over 5507.89 frames. ], batch size: 7, lr: 1.32e-02
2024-08-06 15:44:51,698 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 15:45:58,042 INFO [trainer.py:765] (6/8) Epoch 7, batch 100, train_loss[loss=3.22, NarTop10Accuracy=0.6802, over 7380.00 frames. ], tot_loss[loss=3.544, NarTop10Accuracy=0.617, over 2378.78 frames. ], batch size: 31, lr: 1.24e-02
2024-08-06 15:46:33,614 INFO [trainer.py:765] (6/8) Epoch 7, batch 200, train_loss[loss=3.549, NarTop10Accuracy=0.6138, over 6852.00 frames. ], tot_loss[loss=3.533, NarTop10Accuracy=0.619, over 3868.43 frames. ], batch size: 17, lr: 1.23e-02
2024-08-06 15:47:03,246 INFO [trainer.py:765] (6/8) Epoch 7, batch 300, train_loss[loss=3.774, NarTop10Accuracy=0.5694, over 7095.00 frames. ], tot_loss[loss=3.537, NarTop10Accuracy=0.6181, over 4651.48 frames. ], batch size: 22, lr: 1.23e-02
2024-08-06 15:47:34,494 INFO [trainer.py:765] (6/8) Epoch 7, batch 400, train_loss[loss=3.632, NarTop10Accuracy=0.598, over 5130.00 frames. ], tot_loss[loss=3.529, NarTop10Accuracy=0.6197, over 5096.58 frames. ], batch size: 7, lr: 1.23e-02
2024-08-06 15:48:13,729 INFO [trainer.py:765] (6/8) Epoch 7, batch 500, train_loss[loss=3.516, NarTop10Accuracy=0.6178, over 6057.00 frames. ], tot_loss[loss=3.518, NarTop10Accuracy=0.6217, over 5394.53 frames. ], batch size: 11, lr: 1.22e-02
2024-08-06 15:48:26,368 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 15:48:34,533 INFO [trainer.py:811] (6/8) Epoch 7, validation: loss=3.326, NarTop10Accuracy=0.6612, over 1905321.00 frames. 
2024-08-06 15:48:34,534 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 29995MB
2024-08-06 15:48:35,078 INFO [optim.py:386] (6/8) Clipping_scale=2.0, grad-norm quartiles 1.466e+02 1.860e+02 2.018e+02 2.241e+02 5.111e+02, threshold=4.035e+02, percent-clipped=0.3
2024-08-06 15:48:52,720 INFO [trainer.py:765] (6/8) Epoch 7, batch 600, train_loss[loss=3.233, NarTop10Accuracy=0.6834, over 5844.00 frames. ], tot_loss[loss=3.519, NarTop10Accuracy=0.6212, over 5653.21 frames. ], batch size: 9, lr: 1.22e-02
2024-08-06 15:49:24,912 INFO [trainer.py:765] (6/8) Epoch 7, batch 700, train_loss[loss=3.741, NarTop10Accuracy=0.5764, over 5160.00 frames. ], tot_loss[loss=3.512, NarTop10Accuracy=0.6228, over 5713.85 frames. ], batch size: 6, lr: 1.21e-02
2024-08-06 15:50:04,380 INFO [trainer.py:765] (6/8) Epoch 7, batch 800, train_loss[loss=3.332, NarTop10Accuracy=0.6612, over 4983.00 frames. ], tot_loss[loss=3.496, NarTop10Accuracy=0.6262, over 5765.29 frames. ], batch size: 6, lr: 1.21e-02
2024-08-06 15:50:34,548 INFO [trainer.py:765] (6/8) Epoch 7, batch 900, train_loss[loss=3.327, NarTop10Accuracy=0.6662, over 6249.00 frames. ], tot_loss[loss=3.488, NarTop10Accuracy=0.6276, over 5803.56 frames. ], batch size: 13, lr: 1.21e-02
2024-08-06 15:51:07,155 INFO [trainer.py:765] (6/8) Epoch 7, batch 1000, train_loss[loss=3.357, NarTop10Accuracy=0.6553, over 6177.00 frames. ], tot_loss[loss=3.493, NarTop10Accuracy=0.6268, over 5906.08 frames. ], batch size: 13, lr: 1.20e-02
2024-08-06 15:51:51,758 INFO [trainer.py:765] (6/8) Epoch 7, batch 1100, train_loss[loss=3.27, NarTop10Accuracy=0.6688, over 6975.00 frames. ], tot_loss[loss=3.494, NarTop10Accuracy=0.6273, over 5949.69 frames. ], batch size: 17, lr: 1.20e-02
2024-08-06 15:52:22,699 INFO [trainer.py:765] (6/8) Epoch 7, batch 1200, train_loss[loss=3.392, NarTop10Accuracy=0.6501, over 6990.00 frames. ], tot_loss[loss=3.484, NarTop10Accuracy=0.629, over 5926.93 frames. ], batch size: 31, lr: 1.20e-02
2024-08-06 15:52:52,007 INFO [trainer.py:765] (6/8) Epoch 7, batch 1300, train_loss[loss=3.412, NarTop10Accuracy=0.6413, over 5220.00 frames. ], tot_loss[loss=3.483, NarTop10Accuracy=0.6286, over 6001.27 frames. ], batch size: 6, lr: 1.19e-02
2024-08-06 15:53:33,842 INFO [trainer.py:765] (6/8) Epoch 7, batch 1400, train_loss[loss=3.453, NarTop10Accuracy=0.6496, over 6108.00 frames. ], tot_loss[loss=3.5, NarTop10Accuracy=0.6254, over 6025.11 frames. ], batch size: 11, lr: 1.19e-02
2024-08-06 15:54:04,600 INFO [trainer.py:765] (6/8) Epoch 7, batch 1500, train_loss[loss=3.807, NarTop10Accuracy=0.5656, over 6414.00 frames. ], tot_loss[loss=3.48, NarTop10Accuracy=0.6296, over 5951.15 frames. ], batch size: 53, lr: 1.19e-02
2024-08-06 15:54:32,385 INFO [trainer.py:765] (6/8) Epoch 7, batch 1600, train_loss[loss=3.587, NarTop10Accuracy=0.6109, over 7044.00 frames. ], tot_loss[loss=3.478, NarTop10Accuracy=0.6296, over 5945.11 frames. ], batch size: 22, lr: 1.19e-02
2024-08-06 15:54:59,054 INFO [trainer.py:765] (6/8) Epoch 7, batch 1700, train_loss[loss=3.437, NarTop10Accuracy=0.64, over 6372.00 frames. ], tot_loss[loss=3.502, NarTop10Accuracy=0.6248, over 5918.10 frames. ], batch size: 13, lr: 1.18e-02
2024-08-06 15:55:25,512 INFO [trainer.py:765] (6/8) Epoch 7, batch 1800, train_loss[loss=4.009, NarTop10Accuracy=0.5118, over 6894.00 frames. ], tot_loss[loss=3.494, NarTop10Accuracy=0.6265, over 5995.56 frames. ], batch size: 22, lr: 1.18e-02
2024-08-06 15:55:52,083 INFO [trainer.py:765] (6/8) Epoch 7, batch 1900, train_loss[loss=3.434, NarTop10Accuracy=0.6445, over 5634.00 frames. ], tot_loss[loss=3.512, NarTop10Accuracy=0.6232, over 6034.12 frames. ], batch size: 50, lr: 1.18e-02
2024-08-06 15:56:17,591 INFO [trainer.py:765] (6/8) Epoch 7, batch 2000, train_loss[loss=3.722, NarTop10Accuracy=0.5765, over 6315.00 frames. ], tot_loss[loss=3.504, NarTop10Accuracy=0.6245, over 5998.06 frames. ], batch size: 51, lr: 1.17e-02
2024-08-06 15:56:42,856 INFO [trainer.py:765] (6/8) Epoch 7, batch 2100, train_loss[loss=3.688, NarTop10Accuracy=0.5822, over 3906.00 frames. ], tot_loss[loss=3.49, NarTop10Accuracy=0.6274, over 5967.36 frames. ], batch size: 4, lr: 1.17e-02
2024-08-06 15:57:08,079 INFO [trainer.py:765] (6/8) Epoch 7, batch 2200, train_loss[loss=3.454, NarTop10Accuracy=0.6356, over 7239.00 frames. ], tot_loss[loss=3.51, NarTop10Accuracy=0.6233, over 6006.23 frames. ], batch size: 32, lr: 1.17e-02
2024-08-06 15:57:33,178 INFO [trainer.py:765] (6/8) Epoch 7, batch 2300, train_loss[loss=3.192, NarTop10Accuracy=0.6845, over 5790.00 frames. ], tot_loss[loss=3.507, NarTop10Accuracy=0.6243, over 6008.84 frames. ], batch size: 9, lr: 1.16e-02
2024-08-06 15:57:57,619 INFO [trainer.py:765] (6/8) Epoch 7, batch 2400, train_loss[loss=3.196, NarTop10Accuracy=0.6875, over 5028.00 frames. ], tot_loss[loss=3.495, NarTop10Accuracy=0.6264, over 5768.19 frames. ], batch size: 7, lr: 1.16e-02
2024-08-06 15:58:21,088 INFO [trainer.py:765] (6/8) Epoch 7, batch 2500, train_loss[loss=3.664, NarTop10Accuracy=0.5851, over 5001.00 frames. ], tot_loss[loss=3.466, NarTop10Accuracy=0.6321, over 5472.02 frames. ], batch size: 7, lr: 1.16e-02
2024-08-06 15:58:31,565 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 15:58:39,769 INFO [trainer.py:811] (6/8) Epoch 7, validation: loss=3.381, NarTop10Accuracy=0.6488, over 1905321.00 frames. 
2024-08-06 15:58:39,770 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 29995MB
2024-08-06 15:58:40,220 INFO [optim.py:386] (6/8) Clipping_scale=2.0, grad-norm quartiles 1.471e+02 1.831e+02 1.996e+02 2.207e+02 5.229e+02, threshold=3.992e+02, percent-clipped=0.2
2024-08-06 15:58:48,956 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 15:59:52,876 INFO [trainer.py:765] (6/8) Epoch 8, batch 100, train_loss[loss=3.669, NarTop10Accuracy=0.5975, over 7062.00 frames. ], tot_loss[loss=3.453, NarTop10Accuracy=0.6363, over 2359.67 frames. ], batch size: 31, lr: 1.09e-02
2024-08-06 16:00:27,880 INFO [trainer.py:765] (6/8) Epoch 8, batch 200, train_loss[loss=3.299, NarTop10Accuracy=0.6786, over 6654.00 frames. ], tot_loss[loss=3.478, NarTop10Accuracy=0.6306, over 3846.00 frames. ], batch size: 17, lr: 1.09e-02
2024-08-06 16:00:58,562 INFO [trainer.py:765] (6/8) Epoch 8, batch 300, train_loss[loss=3.283, NarTop10Accuracy=0.6667, over 7029.00 frames. ], tot_loss[loss=3.468, NarTop10Accuracy=0.6324, over 4639.78 frames. ], batch size: 22, lr: 1.08e-02
2024-08-06 16:01:29,759 INFO [trainer.py:765] (6/8) Epoch 8, batch 400, train_loss[loss=3.621, NarTop10Accuracy=0.5924, over 5118.00 frames. ], tot_loss[loss=3.465, NarTop10Accuracy=0.6325, over 5105.54 frames. ], batch size: 7, lr: 1.08e-02
2024-08-06 16:02:04,065 INFO [trainer.py:765] (6/8) Epoch 8, batch 500, train_loss[loss=3.781, NarTop10Accuracy=0.5666, over 6009.00 frames. ], tot_loss[loss=3.446, NarTop10Accuracy=0.636, over 5393.70 frames. ], batch size: 11, lr: 1.08e-02
2024-08-06 16:02:41,835 INFO [trainer.py:765] (6/8) Epoch 8, batch 600, train_loss[loss=3.057, NarTop10Accuracy=0.7193, over 5772.00 frames. ], tot_loss[loss=3.463, NarTop10Accuracy=0.6328, over 5658.64 frames. ], batch size: 9, lr: 1.08e-02
2024-08-06 16:03:11,499 INFO [trainer.py:765] (6/8) Epoch 8, batch 700, train_loss[loss=3.725, NarTop10Accuracy=0.5731, over 5091.00 frames. ], tot_loss[loss=3.47, NarTop10Accuracy=0.631, over 5723.45 frames. ], batch size: 6, lr: 1.07e-02
2024-08-06 16:03:50,083 INFO [trainer.py:765] (6/8) Epoch 8, batch 800, train_loss[loss=3.49, NarTop10Accuracy=0.6136, over 4293.00 frames. ], tot_loss[loss=3.461, NarTop10Accuracy=0.6331, over 5764.55 frames. ], batch size: 5, lr: 1.07e-02
2024-08-06 16:04:27,587 INFO [trainer.py:765] (6/8) Epoch 8, batch 900, train_loss[loss=3.26, NarTop10Accuracy=0.6892, over 6597.00 frames. ], tot_loss[loss=3.449, NarTop10Accuracy=0.6357, over 5794.49 frames. ], batch size: 14, lr: 1.07e-02
2024-08-06 16:04:57,465 INFO [trainer.py:765] (6/8) Epoch 8, batch 1000, train_loss[loss=3.65, NarTop10Accuracy=0.5983, over 6585.00 frames. ], tot_loss[loss=3.443, NarTop10Accuracy=0.6374, over 5892.09 frames. ], batch size: 14, lr: 1.07e-02
2024-08-06 16:05:37,293 INFO [trainer.py:765] (6/8) Epoch 8, batch 1100, train_loss[loss=3.617, NarTop10Accuracy=0.5908, over 6819.00 frames. ], tot_loss[loss=3.439, NarTop10Accuracy=0.6381, over 5949.98 frames. ], batch size: 17, lr: 1.06e-02
2024-08-06 16:06:15,858 INFO [trainer.py:765] (6/8) Epoch 8, batch 1200, train_loss[loss=3.418, NarTop10Accuracy=0.6419, over 7158.00 frames. ], tot_loss[loss=3.443, NarTop10Accuracy=0.6367, over 5939.24 frames. ], batch size: 31, lr: 1.06e-02
2024-08-06 16:06:45,186 INFO [trainer.py:765] (6/8) Epoch 8, batch 1300, train_loss[loss=3.263, NarTop10Accuracy=0.6857, over 5130.00 frames. ], tot_loss[loss=3.434, NarTop10Accuracy=0.6388, over 6001.24 frames. ], batch size: 6, lr: 1.06e-02
2024-08-06 16:07:24,234 INFO [trainer.py:765] (6/8) Epoch 8, batch 1400, train_loss[loss=3.454, NarTop10Accuracy=0.6334, over 6030.00 frames. ], tot_loss[loss=3.437, NarTop10Accuracy=0.6385, over 6020.77 frames. ], batch size: 11, lr: 1.05e-02
2024-08-06 16:07:52,168 INFO [trainer.py:765] (6/8) Epoch 8, batch 1500, train_loss[loss=3.445, NarTop10Accuracy=0.6382, over 6123.00 frames. ], tot_loss[loss=3.42, NarTop10Accuracy=0.642, over 5979.31 frames. ], batch size: 50, lr: 1.05e-02
2024-08-06 16:08:19,948 INFO [trainer.py:765] (6/8) Epoch 8, batch 1600, train_loss[loss=3.24, NarTop10Accuracy=0.6855, over 6930.00 frames. ], tot_loss[loss=3.418, NarTop10Accuracy=0.6422, over 5960.21 frames. ], batch size: 22, lr: 1.05e-02
2024-08-06 16:08:46,617 INFO [trainer.py:765] (6/8) Epoch 8, batch 1700, train_loss[loss=3.37, NarTop10Accuracy=0.6522, over 6267.00 frames. ], tot_loss[loss=3.416, NarTop10Accuracy=0.6424, over 5926.58 frames. ], batch size: 13, lr: 1.05e-02
2024-08-06 16:09:13,105 INFO [trainer.py:765] (6/8) Epoch 8, batch 1800, train_loss[loss=3.204, NarTop10Accuracy=0.6895, over 7122.00 frames. ], tot_loss[loss=3.419, NarTop10Accuracy=0.6421, over 5986.66 frames. ], batch size: 22, lr: 1.04e-02
2024-08-06 16:09:39,635 INFO [trainer.py:765] (6/8) Epoch 8, batch 1900, train_loss[loss=3.649, NarTop10Accuracy=0.5883, over 6129.00 frames. ], tot_loss[loss=3.41, NarTop10Accuracy=0.6441, over 6014.79 frames. ], batch size: 50, lr: 1.04e-02
2024-08-06 16:09:56,939 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 16:10:04,970 INFO [trainer.py:811] (6/8) Epoch 8, validation: loss=3.282, NarTop10Accuracy=0.6699, over 1905321.00 frames. 
2024-08-06 16:10:04,970 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 29995MB
2024-08-06 16:10:05,470 INFO [optim.py:386] (6/8) Clipping_scale=2.0, grad-norm quartiles 1.411e+02 1.814e+02 1.981e+02 2.158e+02 5.862e+02, threshold=3.962e+02, percent-clipped=0.1
2024-08-06 16:10:13,204 INFO [trainer.py:765] (6/8) Epoch 8, batch 2000, train_loss[loss=4.011, NarTop10Accuracy=0.5161, over 6453.00 frames. ], tot_loss[loss=3.42, NarTop10Accuracy=0.6421, over 5986.85 frames. ], batch size: 51, lr: 1.04e-02
2024-08-06 16:10:38,514 INFO [trainer.py:765] (6/8) Epoch 8, batch 2100, train_loss[loss=3.183, NarTop10Accuracy=0.685, over 4008.00 frames. ], tot_loss[loss=3.412, NarTop10Accuracy=0.6433, over 5975.30 frames. ], batch size: 4, lr: 1.04e-02
2024-08-06 16:11:03,747 INFO [trainer.py:765] (6/8) Epoch 8, batch 2200, train_loss[loss=3.566, NarTop10Accuracy=0.6099, over 7428.00 frames. ], tot_loss[loss=3.421, NarTop10Accuracy=0.6412, over 6013.13 frames. ], batch size: 32, lr: 1.04e-02
2024-08-06 16:11:28,905 INFO [trainer.py:765] (6/8) Epoch 8, batch 2300, train_loss[loss=3.698, NarTop10Accuracy=0.58, over 5676.00 frames. ], tot_loss[loss=3.439, NarTop10Accuracy=0.6372, over 6025.32 frames. ], batch size: 9, lr: 1.03e-02
2024-08-06 16:11:53,093 INFO [trainer.py:765] (6/8) Epoch 8, batch 2400, train_loss[loss=3.538, NarTop10Accuracy=0.6175, over 5112.00 frames. ], tot_loss[loss=3.427, NarTop10Accuracy=0.6398, over 5787.41 frames. ], batch size: 7, lr: 1.03e-02
2024-08-06 16:12:16,444 INFO [trainer.py:765] (6/8) Epoch 8, batch 2500, train_loss[loss=3.14, NarTop10Accuracy=0.6962, over 5205.00 frames. ], tot_loss[loss=3.42, NarTop10Accuracy=0.6412, over 5494.53 frames. ], batch size: 7, lr: 1.03e-02
2024-08-06 16:12:36,624 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 16:13:37,514 INFO [trainer.py:765] (6/8) Epoch 9, batch 100, train_loss[loss=3.109, NarTop10Accuracy=0.7031, over 7101.00 frames. ], tot_loss[loss=3.373, NarTop10Accuracy=0.6512, over 2370.26 frames. ], batch size: 31, lr: 9.72e-03
2024-08-06 16:14:14,440 INFO [trainer.py:765] (6/8) Epoch 9, batch 200, train_loss[loss=3.65, NarTop10Accuracy=0.5923, over 6750.00 frames. ], tot_loss[loss=3.38, NarTop10Accuracy=0.6503, over 3850.61 frames. ], batch size: 17, lr: 9.70e-03
2024-08-06 16:14:44,507 INFO [trainer.py:765] (6/8) Epoch 9, batch 300, train_loss[loss=3.36, NarTop10Accuracy=0.6537, over 6996.00 frames. ], tot_loss[loss=3.387, NarTop10Accuracy=0.6489, over 4656.05 frames. ], batch size: 22, lr: 9.68e-03
2024-08-06 16:15:14,914 INFO [trainer.py:765] (6/8) Epoch 9, batch 400, train_loss[loss=3.241, NarTop10Accuracy=0.6678, over 5151.00 frames. ], tot_loss[loss=3.359, NarTop10Accuracy=0.6544, over 5115.89 frames. ], batch size: 7, lr: 9.65e-03
2024-08-06 16:15:50,336 INFO [trainer.py:765] (6/8) Epoch 9, batch 500, train_loss[loss=3.169, NarTop10Accuracy=0.6897, over 6303.00 frames. ], tot_loss[loss=3.347, NarTop10Accuracy=0.6565, over 5403.32 frames. ], batch size: 11, lr: 9.63e-03
2024-08-06 16:16:23,972 INFO [trainer.py:765] (6/8) Epoch 9, batch 600, train_loss[loss=3.765, NarTop10Accuracy=0.5658, over 5823.00 frames. ], tot_loss[loss=3.339, NarTop10Accuracy=0.6581, over 5660.29 frames. ], batch size: 9, lr: 9.61e-03
2024-08-06 16:16:57,145 INFO [trainer.py:765] (6/8) Epoch 9, batch 700, train_loss[loss=3.017, NarTop10Accuracy=0.7147, over 5115.00 frames. ], tot_loss[loss=3.351, NarTop10Accuracy=0.6553, over 5730.13 frames. ], batch size: 6, lr: 9.59e-03
2024-08-06 16:17:32,052 INFO [trainer.py:765] (6/8) Epoch 9, batch 800, train_loss[loss=3.268, NarTop10Accuracy=0.6755, over 4989.00 frames. ], tot_loss[loss=3.388, NarTop10Accuracy=0.648, over 5784.60 frames. ], batch size: 6, lr: 9.57e-03
2024-08-06 16:18:07,815 INFO [trainer.py:765] (6/8) Epoch 9, batch 900, train_loss[loss=3.055, NarTop10Accuracy=0.7248, over 6024.00 frames. ], tot_loss[loss=3.385, NarTop10Accuracy=0.6487, over 5800.63 frames. ], batch size: 13, lr: 9.55e-03
2024-08-06 16:18:39,345 INFO [trainer.py:765] (6/8) Epoch 9, batch 1000, train_loss[loss=3.157, NarTop10Accuracy=0.6899, over 6093.00 frames. ], tot_loss[loss=3.396, NarTop10Accuracy=0.6462, over 5891.74 frames. ], batch size: 13, lr: 9.53e-03
2024-08-06 16:19:15,382 INFO [trainer.py:765] (6/8) Epoch 9, batch 1100, train_loss[loss=3.448, NarTop10Accuracy=0.6349, over 6684.00 frames. ], tot_loss[loss=3.396, NarTop10Accuracy=0.6461, over 5948.00 frames. ], batch size: 17, lr: 9.50e-03
2024-08-06 16:19:53,877 INFO [trainer.py:765] (6/8) Epoch 9, batch 1200, train_loss[loss=3.811, NarTop10Accuracy=0.5587, over 7233.00 frames. ], tot_loss[loss=3.404, NarTop10Accuracy=0.6444, over 5928.62 frames. ], batch size: 31, lr: 9.48e-03
2024-08-06 16:20:24,906 INFO [trainer.py:765] (6/8) Epoch 9, batch 1300, train_loss[loss=3.165, NarTop10Accuracy=0.6975, over 5175.00 frames. ], tot_loss[loss=3.394, NarTop10Accuracy=0.6462, over 6007.27 frames. ], batch size: 6, lr: 9.46e-03
2024-08-06 16:20:56,579 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 16:21:04,483 INFO [trainer.py:811] (6/8) Epoch 9, validation: loss=3.266, NarTop10Accuracy=0.6725, over 1905321.00 frames. 
2024-08-06 16:21:04,484 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 16:21:05,035 INFO [optim.py:386] (6/8) Clipping_scale=2.0, grad-norm quartiles 1.473e+02 1.808e+02 1.967e+02 2.142e+02 6.126e+02, threshold=3.935e+02, percent-clipped=0.5
2024-08-06 16:21:06,690 INFO [trainer.py:765] (6/8) Epoch 9, batch 1400, train_loss[loss=3.633, NarTop10Accuracy=0.5891, over 6099.00 frames. ], tot_loss[loss=3.399, NarTop10Accuracy=0.6448, over 6026.01 frames. ], batch size: 11, lr: 9.44e-03
2024-08-06 16:21:38,895 INFO [trainer.py:765] (6/8) Epoch 9, batch 1500, train_loss[loss=3.392, NarTop10Accuracy=0.6512, over 5847.00 frames. ], tot_loss[loss=3.377, NarTop10Accuracy=0.6499, over 5958.36 frames. ], batch size: 52, lr: 9.42e-03
2024-08-06 16:22:06,720 INFO [trainer.py:765] (6/8) Epoch 9, batch 1600, train_loss[loss=3.272, NarTop10Accuracy=0.6738, over 7011.00 frames. ], tot_loss[loss=3.372, NarTop10Accuracy=0.6514, over 5939.29 frames. ], batch size: 22, lr: 9.40e-03
2024-08-06 16:22:33,469 INFO [trainer.py:765] (6/8) Epoch 9, batch 1700, train_loss[loss=3.427, NarTop10Accuracy=0.6467, over 6405.00 frames. ], tot_loss[loss=3.389, NarTop10Accuracy=0.6479, over 5903.65 frames. ], batch size: 13, lr: 9.38e-03
2024-08-06 16:23:00,063 INFO [trainer.py:765] (6/8) Epoch 9, batch 1800, train_loss[loss=3.353, NarTop10Accuracy=0.6681, over 7257.00 frames. ], tot_loss[loss=3.382, NarTop10Accuracy=0.6493, over 5969.46 frames. ], batch size: 23, lr: 9.36e-03
2024-08-06 16:23:26,782 INFO [trainer.py:765] (6/8) Epoch 9, batch 1900, train_loss[loss=3.379, NarTop10Accuracy=0.6517, over 6471.00 frames. ], tot_loss[loss=3.398, NarTop10Accuracy=0.6464, over 6012.07 frames. ], batch size: 50, lr: 9.34e-03
2024-08-06 16:23:52,484 INFO [trainer.py:765] (6/8) Epoch 9, batch 2000, train_loss[loss=3.891, NarTop10Accuracy=0.5463, over 6123.00 frames. ], tot_loss[loss=3.389, NarTop10Accuracy=0.648, over 5981.11 frames. ], batch size: 50, lr: 9.32e-03
2024-08-06 16:24:17,962 INFO [trainer.py:765] (6/8) Epoch 9, batch 2100, train_loss[loss=3.116, NarTop10Accuracy=0.701, over 4680.00 frames. ], tot_loss[loss=3.386, NarTop10Accuracy=0.6483, over 5950.15 frames. ], batch size: 5, lr: 9.30e-03
2024-08-06 16:24:43,420 INFO [trainer.py:765] (6/8) Epoch 9, batch 2200, train_loss[loss=3.788, NarTop10Accuracy=0.5681, over 7236.00 frames. ], tot_loss[loss=3.39, NarTop10Accuracy=0.6477, over 5994.91 frames. ], batch size: 31, lr: 9.28e-03
2024-08-06 16:25:08,720 INFO [trainer.py:765] (6/8) Epoch 9, batch 2300, train_loss[loss=3.243, NarTop10Accuracy=0.6838, over 5685.00 frames. ], tot_loss[loss=3.405, NarTop10Accuracy=0.6445, over 6013.52 frames. ], batch size: 9, lr: 9.26e-03
2024-08-06 16:25:33,162 INFO [trainer.py:765] (6/8) Epoch 9, batch 2400, train_loss[loss=3.247, NarTop10Accuracy=0.6734, over 5124.00 frames. ], tot_loss[loss=3.396, NarTop10Accuracy=0.646, over 5759.71 frames. ], batch size: 7, lr: 9.25e-03
2024-08-06 16:25:56,767 INFO [trainer.py:765] (6/8) Epoch 9, batch 2500, train_loss[loss=3.122, NarTop10Accuracy=0.7047, over 5097.00 frames. ], tot_loss[loss=3.36, NarTop10Accuracy=0.653, over 5487.94 frames. ], batch size: 7, lr: 9.23e-03
2024-08-06 16:26:16,340 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 16:27:19,583 INFO [trainer.py:765] (6/8) Epoch 10, batch 100, train_loss[loss=3.21, NarTop10Accuracy=0.6841, over 7062.00 frames. ], tot_loss[loss=3.369, NarTop10Accuracy=0.6519, over 2368.65 frames. ], batch size: 31, lr: 8.76e-03
2024-08-06 16:27:52,627 INFO [trainer.py:765] (6/8) Epoch 10, batch 200, train_loss[loss=3.096, NarTop10Accuracy=0.7172, over 6762.00 frames. ], tot_loss[loss=3.346, NarTop10Accuracy=0.6569, over 3854.54 frames. ], batch size: 17, lr: 8.74e-03
2024-08-06 16:28:23,057 INFO [trainer.py:765] (6/8) Epoch 10, batch 300, train_loss[loss=3.062, NarTop10Accuracy=0.7228, over 7023.00 frames. ], tot_loss[loss=3.346, NarTop10Accuracy=0.6566, over 4652.12 frames. ], batch size: 22, lr: 8.72e-03
2024-08-06 16:28:59,199 INFO [trainer.py:765] (6/8) Epoch 10, batch 400, train_loss[loss=3.161, NarTop10Accuracy=0.6992, over 5166.00 frames. ], tot_loss[loss=3.338, NarTop10Accuracy=0.6583, over 5109.77 frames. ], batch size: 7, lr: 8.71e-03
2024-08-06 16:29:29,218 INFO [trainer.py:765] (6/8) Epoch 10, batch 500, train_loss[loss=3.125, NarTop10Accuracy=0.7083, over 6042.00 frames. ], tot_loss[loss=3.336, NarTop10Accuracy=0.6591, over 5400.06 frames. ], batch size: 11, lr: 8.69e-03
2024-08-06 16:30:02,765 INFO [trainer.py:765] (6/8) Epoch 10, batch 600, train_loss[loss=3.608, NarTop10Accuracy=0.5927, over 5727.00 frames. ], tot_loss[loss=3.348, NarTop10Accuracy=0.6565, over 5660.21 frames. ], batch size: 9, lr: 8.67e-03
2024-08-06 16:30:34,264 INFO [trainer.py:765] (6/8) Epoch 10, batch 700, train_loss[loss=3.625, NarTop10Accuracy=0.5923, over 5022.00 frames. ], tot_loss[loss=3.356, NarTop10Accuracy=0.6548, over 5723.22 frames. ], batch size: 6, lr: 8.65e-03
2024-08-06 16:31:09,842 INFO [trainer.py:765] (6/8) Epoch 10, batch 800, train_loss[loss=3.608, NarTop10Accuracy=0.608, over 4320.00 frames. ], tot_loss[loss=3.362, NarTop10Accuracy=0.6534, over 5763.93 frames. ], batch size: 5, lr: 8.64e-03
2024-08-06 16:31:16,257 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 16:31:24,565 INFO [trainer.py:811] (6/8) Epoch 10, validation: loss=3.184, NarTop10Accuracy=0.6898, over 1905321.00 frames. 
2024-08-06 16:31:24,566 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 16:31:25,154 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 10, batch 900, train_loss[loss=3.048, NarTop10Accuracy=0.7275, over 6483.00 frames. ], tot_loss[loss=3.336, NarTop10Accuracy=0.6588, over 5794.28 frames. ], batch size: 14, lr: 8.62e-03
2024-08-06 16:32:28,589 INFO [trainer.py:765] (6/8) Epoch 10, batch 1000, train_loss[loss=3.209, NarTop10Accuracy=0.693, over 6243.00 frames. ], tot_loss[loss=3.344, NarTop10Accuracy=0.6573, over 5902.04 frames. ], batch size: 13, lr: 8.60e-03
2024-08-06 16:33:06,376 INFO [trainer.py:765] (6/8) Epoch 10, batch 1100, train_loss[loss=3.146, NarTop10Accuracy=0.6976, over 6750.00 frames. ], tot_loss[loss=3.35, NarTop10Accuracy=0.6558, over 5944.96 frames. ], batch size: 17, lr: 8.59e-03
2024-08-06 16:33:40,961 INFO [trainer.py:765] (6/8) Epoch 10, batch 1200, train_loss[loss=3.221, NarTop10Accuracy=0.6893, over 7533.00 frames. ], tot_loss[loss=3.345, NarTop10Accuracy=0.6564, over 5959.83 frames. ], batch size: 33, lr: 8.57e-03
2024-08-06 16:34:16,169 INFO [trainer.py:765] (6/8) Epoch 10, batch 1300, train_loss[loss=3.541, NarTop10Accuracy=0.6172, over 5028.00 frames. ], tot_loss[loss=3.34, NarTop10Accuracy=0.6574, over 6024.09 frames. ], batch size: 6, lr: 8.55e-03
2024-08-06 16:34:51,201 INFO [trainer.py:765] (6/8) Epoch 10, batch 1400, train_loss[loss=3.384, NarTop10Accuracy=0.655, over 6036.00 frames. ], tot_loss[loss=3.371, NarTop10Accuracy=0.6511, over 6018.48 frames. ], batch size: 11, lr: 8.54e-03
2024-08-06 16:35:22,159 INFO [trainer.py:765] (6/8) Epoch 10, batch 1500, train_loss[loss=3.726, NarTop10Accuracy=0.5835, over 6111.00 frames. ], tot_loss[loss=3.348, NarTop10Accuracy=0.6563, over 5937.67 frames. ], batch size: 50, lr: 8.52e-03
2024-08-06 16:35:50,136 INFO [trainer.py:765] (6/8) Epoch 10, batch 1600, train_loss[loss=3.614, NarTop10Accuracy=0.6021, over 7128.00 frames. ], tot_loss[loss=3.332, NarTop10Accuracy=0.6593, over 5931.18 frames. ], batch size: 22, lr: 8.50e-03
2024-08-06 16:36:16,976 INFO [trainer.py:765] (6/8) Epoch 10, batch 1700, train_loss[loss=3.251, NarTop10Accuracy=0.6745, over 6228.00 frames. ], tot_loss[loss=3.343, NarTop10Accuracy=0.6571, over 5909.89 frames. ], batch size: 13, lr: 8.49e-03
2024-08-06 16:36:43,647 INFO [trainer.py:765] (6/8) Epoch 10, batch 1800, train_loss[loss=3.225, NarTop10Accuracy=0.6834, over 7050.00 frames. ], tot_loss[loss=3.331, NarTop10Accuracy=0.6594, over 5995.03 frames. ], batch size: 22, lr: 8.47e-03
2024-08-06 16:37:10,290 INFO [trainer.py:765] (6/8) Epoch 10, batch 1900, train_loss[loss=3.37, NarTop10Accuracy=0.6569, over 6582.00 frames. ], tot_loss[loss=3.327, NarTop10Accuracy=0.6604, over 6033.26 frames. ], batch size: 50, lr: 8.45e-03
2024-08-06 16:37:36,089 INFO [trainer.py:765] (6/8) Epoch 10, batch 2000, train_loss[loss=3.3, NarTop10Accuracy=0.6672, over 5739.00 frames. ], tot_loss[loss=3.318, NarTop10Accuracy=0.6624, over 6004.10 frames. ], batch size: 50, lr: 8.44e-03
2024-08-06 16:38:01,650 INFO [trainer.py:765] (6/8) Epoch 10, batch 2100, train_loss[loss=3.485, NarTop10Accuracy=0.6222, over 4005.00 frames. ], tot_loss[loss=3.331, NarTop10Accuracy=0.6597, over 5983.97 frames. ], batch size: 4, lr: 8.42e-03
2024-08-06 16:38:27,120 INFO [trainer.py:765] (6/8) Epoch 10, batch 2200, train_loss[loss=3.783, NarTop10Accuracy=0.5618, over 7380.00 frames. ], tot_loss[loss=3.34, NarTop10Accuracy=0.6577, over 6015.73 frames. ], batch size: 31, lr: 8.41e-03
2024-08-06 16:38:52,447 INFO [trainer.py:765] (6/8) Epoch 10, batch 2300, train_loss[loss=3.14, NarTop10Accuracy=0.6975, over 5685.00 frames. ], tot_loss[loss=3.347, NarTop10Accuracy=0.6564, over 6030.06 frames. ], batch size: 9, lr: 8.39e-03
2024-08-06 16:39:17,006 INFO [trainer.py:765] (6/8) Epoch 10, batch 2400, train_loss[loss=3.292, NarTop10Accuracy=0.6733, over 5193.00 frames. ], tot_loss[loss=3.317, NarTop10Accuracy=0.6625, over 5796.75 frames. ], batch size: 7, lr: 8.37e-03
2024-08-06 16:39:40,801 INFO [trainer.py:765] (6/8) Epoch 10, batch 2500, train_loss[loss=3.676, NarTop10Accuracy=0.5933, over 5172.00 frames. ], tot_loss[loss=3.292, NarTop10Accuracy=0.6671, over 5489.69 frames. ], batch size: 7, lr: 8.36e-03
2024-08-06 16:40:00,617 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 16:41:06,233 INFO [trainer.py:765] (6/8) Epoch 11, batch 100, train_loss[loss=3.615, NarTop10Accuracy=0.5969, over 7485.00 frames. ], tot_loss[loss=3.366, NarTop10Accuracy=0.653, over 2370.60 frames. ], batch size: 31, lr: 7.97e-03
2024-08-06 16:41:39,020 INFO [trainer.py:765] (6/8) Epoch 11, batch 200, train_loss[loss=3.584, NarTop10Accuracy=0.6045, over 6813.00 frames. ], tot_loss[loss=3.337, NarTop10Accuracy=0.6589, over 3859.08 frames. ], batch size: 17, lr: 7.95e-03
2024-08-06 16:41:53,188 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 16:42:01,355 INFO [trainer.py:811] (6/8) Epoch 11, validation: loss=3.116, NarTop10Accuracy=0.7034, over 1905321.00 frames. 
2024-08-06 16:42:01,356 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 16:42:01,879 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 11, batch 300, train_loss[loss=3.132, NarTop10Accuracy=0.7039, over 7119.00 frames. ], tot_loss[loss=3.31, NarTop10Accuracy=0.6645, over 4653.90 frames. ], batch size: 22, lr: 7.94e-03
2024-08-06 16:42:55,154 INFO [trainer.py:765] (6/8) Epoch 11, batch 400, train_loss[loss=3.292, NarTop10Accuracy=0.6661, over 4950.00 frames. ], tot_loss[loss=3.301, NarTop10Accuracy=0.6663, over 5087.13 frames. ], batch size: 7, lr: 7.92e-03
2024-08-06 16:43:25,719 INFO [trainer.py:765] (6/8) Epoch 11, batch 500, train_loss[loss=3.055, NarTop10Accuracy=0.7175, over 6018.00 frames. ], tot_loss[loss=3.289, NarTop10Accuracy=0.6686, over 5376.11 frames. ], batch size: 11, lr: 7.91e-03
2024-08-06 16:44:02,241 INFO [trainer.py:765] (6/8) Epoch 11, batch 600, train_loss[loss=3.542, NarTop10Accuracy=0.6129, over 5589.00 frames. ], tot_loss[loss=3.303, NarTop10Accuracy=0.6658, over 5644.84 frames. ], batch size: 9, lr: 7.89e-03
2024-08-06 16:44:35,716 INFO [trainer.py:765] (6/8) Epoch 11, batch 700, train_loss[loss=3.872, NarTop10Accuracy=0.5477, over 5016.00 frames. ], tot_loss[loss=3.297, NarTop10Accuracy=0.6669, over 5738.86 frames. ], batch size: 6, lr: 7.88e-03
2024-08-06 16:45:10,467 INFO [trainer.py:765] (6/8) Epoch 11, batch 800, train_loss[loss=3, NarTop10Accuracy=0.7199, over 5052.00 frames. ], tot_loss[loss=3.309, NarTop10Accuracy=0.6638, over 5785.08 frames. ], batch size: 6, lr: 7.86e-03
2024-08-06 16:45:46,458 INFO [trainer.py:765] (6/8) Epoch 11, batch 900, train_loss[loss=3.548, NarTop10Accuracy=0.6112, over 6303.00 frames. ], tot_loss[loss=3.302, NarTop10Accuracy=0.6651, over 5804.58 frames. ], batch size: 13, lr: 7.85e-03
2024-08-06 16:46:20,310 INFO [trainer.py:765] (6/8) Epoch 11, batch 1000, train_loss[loss=3.424, NarTop10Accuracy=0.64, over 6216.00 frames. ], tot_loss[loss=3.304, NarTop10Accuracy=0.6648, over 5916.99 frames. ], batch size: 13, lr: 7.84e-03
2024-08-06 16:46:53,456 INFO [trainer.py:765] (6/8) Epoch 11, batch 1100, train_loss[loss=3.102, NarTop10Accuracy=0.706, over 6915.00 frames. ], tot_loss[loss=3.299, NarTop10Accuracy=0.6665, over 5949.54 frames. ], batch size: 17, lr: 7.82e-03
2024-08-06 16:47:33,030 INFO [trainer.py:765] (6/8) Epoch 11, batch 1200, train_loss[loss=3.413, NarTop10Accuracy=0.6409, over 7509.00 frames. ], tot_loss[loss=3.307, NarTop10Accuracy=0.6643, over 5954.97 frames. ], batch size: 31, lr: 7.81e-03
2024-08-06 16:48:06,482 INFO [trainer.py:765] (6/8) Epoch 11, batch 1300, train_loss[loss=3.004, NarTop10Accuracy=0.732, over 5070.00 frames. ], tot_loss[loss=3.309, NarTop10Accuracy=0.6638, over 6008.88 frames. ], batch size: 6, lr: 7.79e-03
2024-08-06 16:48:41,353 INFO [trainer.py:765] (6/8) Epoch 11, batch 1400, train_loss[loss=3.394, NarTop10Accuracy=0.6434, over 6129.00 frames. ], tot_loss[loss=3.321, NarTop10Accuracy=0.6612, over 6032.76 frames. ], batch size: 11, lr: 7.78e-03
2024-08-06 16:49:09,345 INFO [trainer.py:765] (6/8) Epoch 11, batch 1500, train_loss[loss=3.274, NarTop10Accuracy=0.6753, over 6228.00 frames. ], tot_loss[loss=3.323, NarTop10Accuracy=0.6608, over 5972.48 frames. ], batch size: 52, lr: 7.77e-03
2024-08-06 16:49:37,103 INFO [trainer.py:765] (6/8) Epoch 11, batch 1600, train_loss[loss=3.3, NarTop10Accuracy=0.6641, over 7116.00 frames. ], tot_loss[loss=3.316, NarTop10Accuracy=0.6621, over 5964.10 frames. ], batch size: 22, lr: 7.75e-03
2024-08-06 16:50:03,792 INFO [trainer.py:765] (6/8) Epoch 11, batch 1700, train_loss[loss=3.415, NarTop10Accuracy=0.6458, over 6330.00 frames. ], tot_loss[loss=3.307, NarTop10Accuracy=0.6639, over 5946.74 frames. ], batch size: 13, lr: 7.74e-03
2024-08-06 16:50:30,353 INFO [trainer.py:765] (6/8) Epoch 11, batch 1800, train_loss[loss=3.367, NarTop10Accuracy=0.6511, over 6981.00 frames. ], tot_loss[loss=3.323, NarTop10Accuracy=0.6608, over 5980.23 frames. ], batch size: 22, lr: 7.72e-03
2024-08-06 16:50:56,821 INFO [trainer.py:765] (6/8) Epoch 11, batch 1900, train_loss[loss=3.889, NarTop10Accuracy=0.5472, over 5646.00 frames. ], tot_loss[loss=3.331, NarTop10Accuracy=0.6593, over 6038.83 frames. ], batch size: 50, lr: 7.71e-03
2024-08-06 16:51:22,405 INFO [trainer.py:765] (6/8) Epoch 11, batch 2000, train_loss[loss=3.834, NarTop10Accuracy=0.5612, over 6399.00 frames. ], tot_loss[loss=3.325, NarTop10Accuracy=0.6608, over 5994.97 frames. ], batch size: 53, lr: 7.70e-03
2024-08-06 16:51:47,793 INFO [trainer.py:765] (6/8) Epoch 11, batch 2100, train_loss[loss=3.144, NarTop10Accuracy=0.704, over 4011.00 frames. ], tot_loss[loss=3.315, NarTop10Accuracy=0.6631, over 5972.77 frames. ], batch size: 4, lr: 7.68e-03
2024-08-06 16:52:13,118 INFO [trainer.py:765] (6/8) Epoch 11, batch 2200, train_loss[loss=3.299, NarTop10Accuracy=0.6689, over 7356.00 frames. ], tot_loss[loss=3.31, NarTop10Accuracy=0.6636, over 6004.66 frames. ], batch size: 31, lr: 7.67e-03
2024-08-06 16:52:23,900 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 16:52:32,079 INFO [trainer.py:811] (6/8) Epoch 11, validation: loss=3.101, NarTop10Accuracy=0.7058, over 1905321.00 frames. 
2024-08-06 16:52:32,079 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 16:52:32,593 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 11, batch 2300, train_loss[loss=3.313, NarTop10Accuracy=0.6694, over 5682.00 frames. ], tot_loss[loss=3.318, NarTop10Accuracy=0.662, over 6024.01 frames. ], batch size: 9, lr: 7.66e-03
2024-08-06 16:53:10,887 INFO [trainer.py:765] (6/8) Epoch 11, batch 2400, train_loss[loss=3.496, NarTop10Accuracy=0.6255, over 5196.00 frames. ], tot_loss[loss=3.301, NarTop10Accuracy=0.6652, over 5779.45 frames. ], batch size: 7, lr: 7.64e-03
2024-08-06 16:53:34,372 INFO [trainer.py:765] (6/8) Epoch 11, batch 2500, train_loss[loss=3.335, NarTop10Accuracy=0.645, over 5043.00 frames. ], tot_loss[loss=3.297, NarTop10Accuracy=0.6657, over 5473.42 frames. ], batch size: 7, lr: 7.63e-03
2024-08-06 16:53:54,172 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 16:54:58,524 INFO [trainer.py:765] (6/8) Epoch 12, batch 100, train_loss[loss=3.68, NarTop10Accuracy=0.5774, over 7131.00 frames. ], tot_loss[loss=3.318, NarTop10Accuracy=0.6623, over 2354.05 frames. ], batch size: 31, lr: 7.30e-03
2024-08-06 16:55:32,431 INFO [trainer.py:765] (6/8) Epoch 12, batch 200, train_loss[loss=3.105, NarTop10Accuracy=0.7055, over 6588.00 frames. ], tot_loss[loss=3.273, NarTop10Accuracy=0.6712, over 3843.29 frames. ], batch size: 17, lr: 7.29e-03
2024-08-06 16:56:05,095 INFO [trainer.py:765] (6/8) Epoch 12, batch 300, train_loss[loss=3.044, NarTop10Accuracy=0.7221, over 7008.00 frames. ], tot_loss[loss=3.248, NarTop10Accuracy=0.6767, over 4649.24 frames. ], batch size: 22, lr: 7.27e-03
2024-08-06 16:56:36,425 INFO [trainer.py:765] (6/8) Epoch 12, batch 400, train_loss[loss=3.083, NarTop10Accuracy=0.7097, over 5022.00 frames. ], tot_loss[loss=3.256, NarTop10Accuracy=0.6746, over 5132.28 frames. ], batch size: 7, lr: 7.26e-03
2024-08-06 16:57:10,502 INFO [trainer.py:765] (6/8) Epoch 12, batch 500, train_loss[loss=3.584, NarTop10Accuracy=0.605, over 5970.00 frames. ], tot_loss[loss=3.267, NarTop10Accuracy=0.6721, over 5400.91 frames. ], batch size: 11, lr: 7.25e-03
2024-08-06 16:57:45,482 INFO [trainer.py:765] (6/8) Epoch 12, batch 600, train_loss[loss=3.168, NarTop10Accuracy=0.6929, over 5682.00 frames. ], tot_loss[loss=3.268, NarTop10Accuracy=0.672, over 5642.85 frames. ], batch size: 9, lr: 7.24e-03
2024-08-06 16:58:17,003 INFO [trainer.py:765] (6/8) Epoch 12, batch 700, train_loss[loss=3.429, NarTop10Accuracy=0.6412, over 4269.00 frames. ], tot_loss[loss=3.287, NarTop10Accuracy=0.6682, over 5709.10 frames. ], batch size: 5, lr: 7.22e-03
2024-08-06 16:58:53,468 INFO [trainer.py:765] (6/8) Epoch 12, batch 800, train_loss[loss=3.37, NarTop10Accuracy=0.6557, over 4416.00 frames. ], tot_loss[loss=3.289, NarTop10Accuracy=0.6678, over 5764.96 frames. ], batch size: 5, lr: 7.21e-03
2024-08-06 16:59:27,205 INFO [trainer.py:765] (6/8) Epoch 12, batch 900, train_loss[loss=3.083, NarTop10Accuracy=0.7048, over 6213.00 frames. ], tot_loss[loss=3.272, NarTop10Accuracy=0.6718, over 5792.79 frames. ], batch size: 13, lr: 7.20e-03
2024-08-06 17:00:01,573 INFO [trainer.py:765] (6/8) Epoch 12, batch 1000, train_loss[loss=2.915, NarTop10Accuracy=0.7437, over 6216.00 frames. ], tot_loss[loss=3.282, NarTop10Accuracy=0.6696, over 5901.59 frames. ], batch size: 13, lr: 7.19e-03
2024-08-06 17:00:39,188 INFO [trainer.py:765] (6/8) Epoch 12, batch 1100, train_loss[loss=3.651, NarTop10Accuracy=0.5847, over 6888.00 frames. ], tot_loss[loss=3.299, NarTop10Accuracy=0.6657, over 5939.44 frames. ], batch size: 17, lr: 7.18e-03
2024-08-06 17:01:13,963 INFO [trainer.py:765] (6/8) Epoch 12, batch 1200, train_loss[loss=3.064, NarTop10Accuracy=0.7247, over 7014.00 frames. ], tot_loss[loss=3.268, NarTop10Accuracy=0.6718, over 5917.71 frames. ], batch size: 31, lr: 7.17e-03
2024-08-06 17:01:48,107 INFO [trainer.py:765] (6/8) Epoch 12, batch 1300, train_loss[loss=3.263, NarTop10Accuracy=0.6715, over 5061.00 frames. ], tot_loss[loss=3.282, NarTop10Accuracy=0.6685, over 5981.88 frames. ], batch size: 6, lr: 7.15e-03
2024-08-06 17:02:22,322 INFO [trainer.py:765] (6/8) Epoch 12, batch 1400, train_loss[loss=3.62, NarTop10Accuracy=0.6027, over 6102.00 frames. ], tot_loss[loss=3.285, NarTop10Accuracy=0.668, over 6019.44 frames. ], batch size: 11, lr: 7.14e-03
2024-08-06 17:02:52,876 INFO [trainer.py:765] (6/8) Epoch 12, batch 1500, train_loss[loss=3.337, NarTop10Accuracy=0.6641, over 6201.00 frames. ], tot_loss[loss=3.267, NarTop10Accuracy=0.6722, over 5968.77 frames. ], batch size: 50, lr: 7.13e-03
2024-08-06 17:03:20,690 INFO [trainer.py:765] (6/8) Epoch 12, batch 1600, train_loss[loss=3.236, NarTop10Accuracy=0.6725, over 7341.00 frames. ], tot_loss[loss=3.275, NarTop10Accuracy=0.6708, over 5946.63 frames. ], batch size: 22, lr: 7.12e-03
2024-08-06 17:03:38,296 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 17:03:46,474 INFO [trainer.py:811] (6/8) Epoch 12, validation: loss=3.054, NarTop10Accuracy=0.7153, over 1905321.00 frames. 
2024-08-06 17:03:46,474 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 17:03:46,988 INFO [optim.py:386] (6/8) 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 17:03:55,603 INFO [trainer.py:765] (6/8) Epoch 12, batch 1700, train_loss[loss=3.303, NarTop10Accuracy=0.6575, over 6207.00 frames. ], tot_loss[loss=3.28, NarTop10Accuracy=0.6699, over 5927.63 frames. ], batch size: 13, lr: 7.11e-03
2024-08-06 17:04:22,121 INFO [trainer.py:765] (6/8) Epoch 12, batch 1800, train_loss[loss=3.704, NarTop10Accuracy=0.5796, over 7230.00 frames. ], tot_loss[loss=3.279, NarTop10Accuracy=0.6698, over 5992.98 frames. ], batch size: 23, lr: 7.10e-03
2024-08-06 17:04:48,591 INFO [trainer.py:765] (6/8) Epoch 12, batch 1900, train_loss[loss=3.23, NarTop10Accuracy=0.6844, over 6261.00 frames. ], tot_loss[loss=3.277, NarTop10Accuracy=0.6708, over 6031.90 frames. ], batch size: 51, lr: 7.08e-03
2024-08-06 17:05:14,198 INFO [trainer.py:765] (6/8) Epoch 12, batch 2000, train_loss[loss=3.579, NarTop10Accuracy=0.5997, over 5367.00 frames. ], tot_loss[loss=3.268, NarTop10Accuracy=0.6725, over 5993.35 frames. ], batch size: 50, lr: 7.07e-03
2024-08-06 17:05:39,468 INFO [trainer.py:765] (6/8) Epoch 12, batch 2100, train_loss[loss=3.262, NarTop10Accuracy=0.6688, over 4836.00 frames. ], tot_loss[loss=3.277, NarTop10Accuracy=0.6706, over 5971.77 frames. ], batch size: 5, lr: 7.06e-03
2024-08-06 17:06:04,691 INFO [trainer.py:765] (6/8) Epoch 12, batch 2200, train_loss[loss=3.48, NarTop10Accuracy=0.6265, over 7143.00 frames. ], tot_loss[loss=3.292, NarTop10Accuracy=0.6672, over 6025.91 frames. ], batch size: 31, lr: 7.05e-03
2024-08-06 17:06:29,847 INFO [trainer.py:765] (6/8) Epoch 12, batch 2300, train_loss[loss=3.516, NarTop10Accuracy=0.6303, over 5724.00 frames. ], tot_loss[loss=3.29, NarTop10Accuracy=0.6678, over 6054.37 frames. ], batch size: 9, lr: 7.04e-03
2024-08-06 17:06:54,200 INFO [trainer.py:765] (6/8) Epoch 12, batch 2400, train_loss[loss=3.089, NarTop10Accuracy=0.7065, over 5265.00 frames. ], tot_loss[loss=3.28, NarTop10Accuracy=0.6697, over 5790.77 frames. ], batch size: 7, lr: 7.03e-03
2024-08-06 17:07:17,646 INFO [trainer.py:765] (6/8) Epoch 12, batch 2500, train_loss[loss=3.212, NarTop10Accuracy=0.6891, over 5055.00 frames. ], tot_loss[loss=3.257, NarTop10Accuracy=0.6739, over 5487.44 frames. ], batch size: 7, lr: 7.02e-03
2024-08-06 17:07:37,943 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 17:08:40,079 INFO [trainer.py:765] (6/8) Epoch 13, batch 100, train_loss[loss=3.08, NarTop10Accuracy=0.7193, over 7236.00 frames. ], tot_loss[loss=3.285, NarTop10Accuracy=0.6691, over 2355.81 frames. ], batch size: 31, lr: 6.73e-03
2024-08-06 17:09:14,120 INFO [trainer.py:765] (6/8) Epoch 13, batch 200, train_loss[loss=3.104, NarTop10Accuracy=0.7145, over 6867.00 frames. ], tot_loss[loss=3.284, NarTop10Accuracy=0.669, over 3850.93 frames. ], batch size: 17, lr: 6.72e-03
2024-08-06 17:09:46,277 INFO [trainer.py:765] (6/8) Epoch 13, batch 300, train_loss[loss=3.517, NarTop10Accuracy=0.6105, over 7020.00 frames. ], tot_loss[loss=3.265, NarTop10Accuracy=0.6729, over 4644.37 frames. ], batch size: 22, lr: 6.71e-03
2024-08-06 17:10:19,163 INFO [trainer.py:765] (6/8) Epoch 13, batch 400, train_loss[loss=3.104, NarTop10Accuracy=0.7122, over 5199.00 frames. ], tot_loss[loss=3.246, NarTop10Accuracy=0.6767, over 5092.62 frames. ], batch size: 7, lr: 6.70e-03
2024-08-06 17:10:49,335 INFO [trainer.py:765] (6/8) Epoch 13, batch 500, train_loss[loss=3.211, NarTop10Accuracy=0.6887, over 6087.00 frames. ], tot_loss[loss=3.238, NarTop10Accuracy=0.6784, over 5377.82 frames. ], batch size: 11, lr: 6.69e-03
2024-08-06 17:11:26,244 INFO [trainer.py:765] (6/8) Epoch 13, batch 600, train_loss[loss=2.915, NarTop10Accuracy=0.7412, over 5637.00 frames. ], tot_loss[loss=3.235, NarTop10Accuracy=0.6794, over 5651.10 frames. ], batch size: 9, lr: 6.68e-03
2024-08-06 17:11:57,381 INFO [trainer.py:765] (6/8) Epoch 13, batch 700, train_loss[loss=3.219, NarTop10Accuracy=0.6806, over 5022.00 frames. ], tot_loss[loss=3.244, NarTop10Accuracy=0.6773, over 5721.65 frames. ], batch size: 6, lr: 6.67e-03
2024-08-06 17:12:33,442 INFO [trainer.py:765] (6/8) Epoch 13, batch 800, train_loss[loss=3.209, NarTop10Accuracy=0.6799, over 4371.00 frames. ], tot_loss[loss=3.251, NarTop10Accuracy=0.6756, over 5773.23 frames. ], batch size: 5, lr: 6.66e-03
2024-08-06 17:13:10,031 INFO [trainer.py:765] (6/8) Epoch 13, batch 900, train_loss[loss=3.235, NarTop10Accuracy=0.6852, over 6225.00 frames. ], tot_loss[loss=3.239, NarTop10Accuracy=0.6778, over 5781.87 frames. ], batch size: 13, lr: 6.65e-03
2024-08-06 17:13:41,442 INFO [trainer.py:765] (6/8) Epoch 13, batch 1000, train_loss[loss=3.509, NarTop10Accuracy=0.6323, over 6837.00 frames. ], tot_loss[loss=3.243, NarTop10Accuracy=0.6771, over 5884.29 frames. ], batch size: 14, lr: 6.64e-03
2024-08-06 17:14:15,537 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 17:14:23,644 INFO [trainer.py:811] (6/8) Epoch 13, validation: loss=3.099, NarTop10Accuracy=0.7062, over 1905321.00 frames. 
2024-08-06 17:14:23,645 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 17:14:24,471 INFO [optim.py:386] (6/8) 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 17:14:26,696 INFO [trainer.py:765] (6/8) Epoch 13, batch 1100, train_loss[loss=3.416, NarTop10Accuracy=0.6427, over 6687.00 frames. ], tot_loss[loss=3.249, NarTop10Accuracy=0.6757, over 5916.12 frames. ], batch size: 17, lr: 6.63e-03
2024-08-06 17:15:03,474 INFO [trainer.py:765] (6/8) Epoch 13, batch 1200, train_loss[loss=3.331, NarTop10Accuracy=0.6582, over 7230.00 frames. ], tot_loss[loss=3.252, NarTop10Accuracy=0.675, over 5929.96 frames. ], batch size: 31, lr: 6.62e-03
2024-08-06 17:15:35,514 INFO [trainer.py:765] (6/8) Epoch 13, batch 1300, train_loss[loss=3.105, NarTop10Accuracy=0.7095, over 4413.00 frames. ], tot_loss[loss=3.259, NarTop10Accuracy=0.6735, over 6003.17 frames. ], batch size: 5, lr: 6.61e-03
2024-08-06 17:16:11,782 INFO [trainer.py:765] (6/8) Epoch 13, batch 1400, train_loss[loss=3.037, NarTop10Accuracy=0.7193, over 5958.00 frames. ], tot_loss[loss=3.262, NarTop10Accuracy=0.6736, over 6037.32 frames. ], batch size: 11, lr: 6.60e-03
2024-08-06 17:16:39,787 INFO [trainer.py:765] (6/8) Epoch 13, batch 1500, train_loss[loss=3.486, NarTop10Accuracy=0.627, over 6429.00 frames. ], tot_loss[loss=3.26, NarTop10Accuracy=0.6738, over 5964.80 frames. ], batch size: 50, lr: 6.59e-03
2024-08-06 17:17:07,602 INFO [trainer.py:765] (6/8) Epoch 13, batch 1600, train_loss[loss=3.136, NarTop10Accuracy=0.7049, over 7074.00 frames. ], tot_loss[loss=3.263, NarTop10Accuracy=0.6729, over 5937.57 frames. ], batch size: 22, lr: 6.58e-03
2024-08-06 17:17:34,259 INFO [trainer.py:765] (6/8) Epoch 13, batch 1700, train_loss[loss=3.184, NarTop10Accuracy=0.6965, over 6261.00 frames. ], tot_loss[loss=3.262, NarTop10Accuracy=0.673, over 5928.56 frames. ], batch size: 13, lr: 6.57e-03
2024-08-06 17:18:00,761 INFO [trainer.py:765] (6/8) Epoch 13, batch 1800, train_loss[loss=3.174, NarTop10Accuracy=0.6983, over 7218.00 frames. ], tot_loss[loss=3.256, NarTop10Accuracy=0.6744, over 5983.36 frames. ], batch size: 22, lr: 6.56e-03
2024-08-06 17:18:27,243 INFO [trainer.py:765] (6/8) Epoch 13, batch 1900, train_loss[loss=3.531, NarTop10Accuracy=0.6228, over 6033.00 frames. ], tot_loss[loss=3.254, NarTop10Accuracy=0.675, over 6019.16 frames. ], batch size: 50, lr: 6.55e-03
2024-08-06 17:18:52,776 INFO [trainer.py:765] (6/8) Epoch 13, batch 2000, train_loss[loss=3.565, NarTop10Accuracy=0.6157, over 6522.00 frames. ], tot_loss[loss=3.239, NarTop10Accuracy=0.6785, over 6002.45 frames. ], batch size: 50, lr: 6.54e-03
2024-08-06 17:19:18,147 INFO [trainer.py:765] (6/8) Epoch 13, batch 2100, train_loss[loss=2.858, NarTop10Accuracy=0.7575, over 4725.00 frames. ], tot_loss[loss=3.24, NarTop10Accuracy=0.6782, over 6000.67 frames. ], batch size: 5, lr: 6.53e-03
2024-08-06 17:19:43,412 INFO [trainer.py:765] (6/8) Epoch 13, batch 2200, train_loss[loss=3.406, NarTop10Accuracy=0.6501, over 6969.00 frames. ], tot_loss[loss=3.251, NarTop10Accuracy=0.6759, over 6035.57 frames. ], batch size: 31, lr: 6.52e-03
2024-08-06 17:20:08,542 INFO [trainer.py:765] (6/8) Epoch 13, batch 2300, train_loss[loss=3.363, NarTop10Accuracy=0.6393, over 5673.00 frames. ], tot_loss[loss=3.27, NarTop10Accuracy=0.6718, over 6034.54 frames. ], batch size: 9, lr: 6.51e-03
2024-08-06 17:20:32,939 INFO [trainer.py:765] (6/8) Epoch 13, batch 2400, train_loss[loss=3.528, NarTop10Accuracy=0.6091, over 5163.00 frames. ], tot_loss[loss=3.243, NarTop10Accuracy=0.6771, over 5767.29 frames. ], batch size: 7, lr: 6.50e-03
2024-08-06 17:20:56,408 INFO [trainer.py:765] (6/8) Epoch 13, batch 2500, train_loss[loss=3.469, NarTop10Accuracy=0.6362, over 5100.00 frames. ], tot_loss[loss=3.224, NarTop10Accuracy=0.6808, over 5467.57 frames. ], batch size: 7, lr: 6.49e-03
2024-08-06 17:21:16,262 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 17:22:19,316 INFO [trainer.py:765] (6/8) Epoch 14, batch 100, train_loss[loss=2.985, NarTop10Accuracy=0.7346, over 7224.00 frames. ], tot_loss[loss=3.216, NarTop10Accuracy=0.6839, over 2387.72 frames. ], batch size: 32, lr: 6.24e-03
2024-08-06 17:22:50,378 INFO [trainer.py:765] (6/8) Epoch 14, batch 200, train_loss[loss=3.154, NarTop10Accuracy=0.6988, over 6717.00 frames. ], tot_loss[loss=3.231, NarTop10Accuracy=0.6805, over 3869.35 frames. ], batch size: 17, lr: 6.23e-03
2024-08-06 17:23:23,880 INFO [trainer.py:765] (6/8) Epoch 14, batch 300, train_loss[loss=3.161, NarTop10Accuracy=0.6981, over 7071.00 frames. ], tot_loss[loss=3.209, NarTop10Accuracy=0.6848, over 4648.52 frames. ], batch size: 22, lr: 6.22e-03
2024-08-06 17:23:57,484 INFO [trainer.py:765] (6/8) Epoch 14, batch 400, train_loss[loss=2.883, NarTop10Accuracy=0.75, over 4983.00 frames. ], tot_loss[loss=3.226, NarTop10Accuracy=0.6813, over 5092.21 frames. ], batch size: 7, lr: 6.22e-03
2024-08-06 17:24:32,114 INFO [trainer.py:765] (6/8) Epoch 14, batch 500, train_loss[loss=3.292, NarTop10Accuracy=0.6697, over 6006.00 frames. ], tot_loss[loss=3.231, NarTop10Accuracy=0.68, over 5371.47 frames. ], batch size: 11, lr: 6.21e-03
2024-08-06 17:24:36,214 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 17:24:44,275 INFO [trainer.py:811] (6/8) Epoch 14, validation: loss=3.004, NarTop10Accuracy=0.726, over 1905321.00 frames. 
2024-08-06 17:24:44,276 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 17:24:44,823 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 14, batch 600, train_loss[loss=2.98, NarTop10Accuracy=0.73, over 5718.00 frames. ], tot_loss[loss=3.23, NarTop10Accuracy=0.6802, over 5642.42 frames. ], batch size: 9, lr: 6.20e-03
2024-08-06 17:25:48,548 INFO [trainer.py:765] (6/8) Epoch 14, batch 700, train_loss[loss=3.328, NarTop10Accuracy=0.6551, over 5166.00 frames. ], tot_loss[loss=3.224, NarTop10Accuracy=0.6815, over 5726.04 frames. ], batch size: 6, lr: 6.19e-03
2024-08-06 17:26:25,279 INFO [trainer.py:765] (6/8) Epoch 14, batch 800, train_loss[loss=2.828, NarTop10Accuracy=0.7684, over 5145.00 frames. ], tot_loss[loss=3.216, NarTop10Accuracy=0.6826, over 5782.40 frames. ], batch size: 6, lr: 6.18e-03
2024-08-06 17:26:57,659 INFO [trainer.py:765] (6/8) Epoch 14, batch 900, train_loss[loss=3.198, NarTop10Accuracy=0.6781, over 6615.00 frames. ], tot_loss[loss=3.208, NarTop10Accuracy=0.684, over 5787.22 frames. ], batch size: 14, lr: 6.17e-03
2024-08-06 17:27:31,716 INFO [trainer.py:765] (6/8) Epoch 14, batch 1000, train_loss[loss=3.415, NarTop10Accuracy=0.6472, over 6294.00 frames. ], tot_loss[loss=3.223, NarTop10Accuracy=0.6809, over 5866.09 frames. ], batch size: 13, lr: 6.16e-03
2024-08-06 17:28:11,597 INFO [trainer.py:765] (6/8) Epoch 14, batch 1100, train_loss[loss=2.972, NarTop10Accuracy=0.7405, over 6933.00 frames. ], tot_loss[loss=3.22, NarTop10Accuracy=0.6816, over 5914.50 frames. ], batch size: 17, lr: 6.15e-03
2024-08-06 17:28:40,733 INFO [trainer.py:765] (6/8) Epoch 14, batch 1200, train_loss[loss=3.6, NarTop10Accuracy=0.6035, over 7512.00 frames. ], tot_loss[loss=3.218, NarTop10Accuracy=0.6822, over 5919.56 frames. ], batch size: 31, lr: 6.15e-03
2024-08-06 17:29:16,214 INFO [trainer.py:765] (6/8) Epoch 14, batch 1300, train_loss[loss=3.566, NarTop10Accuracy=0.6119, over 5196.00 frames. ], tot_loss[loss=3.22, NarTop10Accuracy=0.6821, over 5996.29 frames. ], batch size: 6, lr: 6.14e-03
2024-08-06 17:29:54,602 INFO [trainer.py:765] (6/8) Epoch 14, batch 1400, train_loss[loss=3.367, NarTop10Accuracy=0.6498, over 6081.00 frames. ], tot_loss[loss=3.226, NarTop10Accuracy=0.6803, over 6015.82 frames. ], batch size: 11, lr: 6.13e-03
2024-08-06 17:30:25,315 INFO [trainer.py:765] (6/8) Epoch 14, batch 1500, train_loss[loss=3.772, NarTop10Accuracy=0.5673, over 5769.00 frames. ], tot_loss[loss=3.231, NarTop10Accuracy=0.6793, over 5953.10 frames. ], batch size: 51, lr: 6.12e-03
2024-08-06 17:30:53,042 INFO [trainer.py:765] (6/8) Epoch 14, batch 1600, train_loss[loss=3.115, NarTop10Accuracy=0.706, over 7359.00 frames. ], tot_loss[loss=3.221, NarTop10Accuracy=0.6815, over 5915.37 frames. ], batch size: 23, lr: 6.11e-03
2024-08-06 17:31:19,728 INFO [trainer.py:765] (6/8) Epoch 14, batch 1700, train_loss[loss=2.994, NarTop10Accuracy=0.7287, over 6579.00 frames. ], tot_loss[loss=3.206, NarTop10Accuracy=0.6851, over 5891.40 frames. ], batch size: 14, lr: 6.10e-03
2024-08-06 17:31:46,289 INFO [trainer.py:765] (6/8) Epoch 14, batch 1800, train_loss[loss=2.976, NarTop10Accuracy=0.7334, over 7191.00 frames. ], tot_loss[loss=3.188, NarTop10Accuracy=0.6892, over 5963.79 frames. ], batch size: 22, lr: 6.09e-03
2024-08-06 17:32:12,727 INFO [trainer.py:765] (6/8) Epoch 14, batch 1900, train_loss[loss=3.604, NarTop10Accuracy=0.5986, over 5676.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6869, over 6000.20 frames. ], batch size: 50, lr: 6.09e-03
2024-08-06 17:32:38,282 INFO [trainer.py:765] (6/8) Epoch 14, batch 2000, train_loss[loss=3.321, NarTop10Accuracy=0.6701, over 5919.00 frames. ], tot_loss[loss=3.214, NarTop10Accuracy=0.6834, over 5982.87 frames. ], batch size: 52, lr: 6.08e-03
2024-08-06 17:33:03,646 INFO [trainer.py:765] (6/8) Epoch 14, batch 2100, train_loss[loss=2.92, NarTop10Accuracy=0.7301, over 3972.00 frames. ], tot_loss[loss=3.216, NarTop10Accuracy=0.6825, over 5963.05 frames. ], batch size: 4, lr: 6.07e-03
2024-08-06 17:33:28,999 INFO [trainer.py:765] (6/8) Epoch 14, batch 2200, train_loss[loss=3.25, NarTop10Accuracy=0.6714, over 7371.00 frames. ], tot_loss[loss=3.213, NarTop10Accuracy=0.683, over 5998.24 frames. ], batch size: 32, lr: 6.06e-03
2024-08-06 17:33:54,089 INFO [trainer.py:765] (6/8) Epoch 14, batch 2300, train_loss[loss=2.782, NarTop10Accuracy=0.772, over 5766.00 frames. ], tot_loss[loss=3.233, NarTop10Accuracy=0.6791, over 6009.68 frames. ], batch size: 9, lr: 6.05e-03
2024-08-06 17:34:18,534 INFO [trainer.py:765] (6/8) Epoch 14, batch 2400, train_loss[loss=2.92, NarTop10Accuracy=0.746, over 5343.00 frames. ], tot_loss[loss=3.235, NarTop10Accuracy=0.6787, over 5756.45 frames. ], batch size: 7, lr: 6.04e-03
2024-08-06 17:34:42,116 INFO [trainer.py:765] (6/8) Epoch 14, batch 2500, train_loss[loss=2.927, NarTop10Accuracy=0.7444, over 5124.00 frames. ], tot_loss[loss=3.204, NarTop10Accuracy=0.6849, over 5457.46 frames. ], batch size: 7, lr: 6.04e-03
2024-08-06 17:34:45,395 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 17:34:53,209 INFO [trainer.py:811] (6/8) Epoch 14, validation: loss=3.062, NarTop10Accuracy=0.7136, over 1905321.00 frames. 
2024-08-06 17:34:53,209 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 17:34:53,679 INFO [optim.py:386] (6/8) 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 17:35:09,535 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 17:36:11,738 INFO [trainer.py:765] (6/8) Epoch 15, batch 100, train_loss[loss=3.127, NarTop10Accuracy=0.7016, over 7464.00 frames. ], tot_loss[loss=3.232, NarTop10Accuracy=0.6802, over 2386.58 frames. ], batch size: 31, lr: 5.82e-03
2024-08-06 17:36:44,334 INFO [trainer.py:765] (6/8) Epoch 15, batch 200, train_loss[loss=3.432, NarTop10Accuracy=0.6412, over 6864.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6876, over 3867.52 frames. ], batch size: 17, lr: 5.81e-03
2024-08-06 17:37:17,714 INFO [trainer.py:765] (6/8) Epoch 15, batch 300, train_loss[loss=3.265, NarTop10Accuracy=0.6664, over 7263.00 frames. ], tot_loss[loss=3.204, NarTop10Accuracy=0.6852, over 4657.52 frames. ], batch size: 22, lr: 5.80e-03
2024-08-06 17:37:48,904 INFO [trainer.py:765] (6/8) Epoch 15, batch 400, train_loss[loss=2.942, NarTop10Accuracy=0.7454, over 5208.00 frames. ], tot_loss[loss=3.197, NarTop10Accuracy=0.6865, over 5100.50 frames. ], batch size: 7, lr: 5.80e-03
2024-08-06 17:38:22,354 INFO [trainer.py:765] (6/8) Epoch 15, batch 500, train_loss[loss=2.984, NarTop10Accuracy=0.7351, over 6183.00 frames. ], tot_loss[loss=3.194, NarTop10Accuracy=0.6872, over 5402.96 frames. ], batch size: 11, lr: 5.79e-03
2024-08-06 17:38:53,093 INFO [trainer.py:765] (6/8) Epoch 15, batch 600, train_loss[loss=2.826, NarTop10Accuracy=0.7689, over 5613.00 frames. ], tot_loss[loss=3.209, NarTop10Accuracy=0.6844, over 5657.99 frames. ], batch size: 9, lr: 5.78e-03
2024-08-06 17:39:27,922 INFO [trainer.py:765] (6/8) Epoch 15, batch 700, train_loss[loss=2.949, NarTop10Accuracy=0.7397, over 5049.00 frames. ], tot_loss[loss=3.212, NarTop10Accuracy=0.6834, over 5719.12 frames. ], batch size: 6, lr: 5.77e-03
2024-08-06 17:40:05,565 INFO [trainer.py:765] (6/8) Epoch 15, batch 800, train_loss[loss=3.293, NarTop10Accuracy=0.6629, over 5064.00 frames. ], tot_loss[loss=3.235, NarTop10Accuracy=0.6787, over 5778.87 frames. ], batch size: 6, lr: 5.76e-03
2024-08-06 17:40:35,791 INFO [trainer.py:765] (6/8) Epoch 15, batch 900, train_loss[loss=3.426, NarTop10Accuracy=0.6342, over 6183.00 frames. ], tot_loss[loss=3.212, NarTop10Accuracy=0.6831, over 5813.22 frames. ], batch size: 13, lr: 5.76e-03
2024-08-06 17:41:11,251 INFO [trainer.py:765] (6/8) Epoch 15, batch 1000, train_loss[loss=3.06, NarTop10Accuracy=0.7148, over 6297.00 frames. ], tot_loss[loss=3.198, NarTop10Accuracy=0.6862, over 5918.80 frames. ], batch size: 13, lr: 5.75e-03
2024-08-06 17:41:46,452 INFO [trainer.py:765] (6/8) Epoch 15, batch 1100, train_loss[loss=3.202, NarTop10Accuracy=0.6781, over 6831.00 frames. ], tot_loss[loss=3.196, NarTop10Accuracy=0.6863, over 5931.78 frames. ], batch size: 17, lr: 5.74e-03
2024-08-06 17:42:19,456 INFO [trainer.py:765] (6/8) Epoch 15, batch 1200, train_loss[loss=3.315, NarTop10Accuracy=0.6598, over 7110.00 frames. ], tot_loss[loss=3.224, NarTop10Accuracy=0.681, over 5931.46 frames. ], batch size: 31, lr: 5.73e-03
2024-08-06 17:42:54,428 INFO [trainer.py:765] (6/8) Epoch 15, batch 1300, train_loss[loss=3.181, NarTop10Accuracy=0.691, over 5094.00 frames. ], tot_loss[loss=3.215, NarTop10Accuracy=0.683, over 6004.38 frames. ], batch size: 6, lr: 5.73e-03
2024-08-06 17:43:26,607 INFO [trainer.py:765] (6/8) Epoch 15, batch 1400, train_loss[loss=3.365, NarTop10Accuracy=0.6563, over 6153.00 frames. ], tot_loss[loss=3.224, NarTop10Accuracy=0.681, over 6020.79 frames. ], batch size: 11, lr: 5.72e-03
2024-08-06 17:43:56,558 INFO [trainer.py:765] (6/8) Epoch 15, batch 1500, train_loss[loss=3.244, NarTop10Accuracy=0.6829, over 6252.00 frames. ], tot_loss[loss=3.226, NarTop10Accuracy=0.6808, over 5944.21 frames. ], batch size: 51, lr: 5.71e-03
2024-08-06 17:44:24,241 INFO [trainer.py:765] (6/8) Epoch 15, batch 1600, train_loss[loss=3.709, NarTop10Accuracy=0.5854, over 7041.00 frames. ], tot_loss[loss=3.207, NarTop10Accuracy=0.6846, over 5934.46 frames. ], batch size: 22, lr: 5.70e-03
2024-08-06 17:44:50,856 INFO [trainer.py:765] (6/8) Epoch 15, batch 1700, train_loss[loss=2.99, NarTop10Accuracy=0.7309, over 6501.00 frames. ], tot_loss[loss=3.195, NarTop10Accuracy=0.6872, over 5933.14 frames. ], batch size: 14, lr: 5.70e-03
2024-08-06 17:45:17,294 INFO [trainer.py:765] (6/8) Epoch 15, batch 1800, train_loss[loss=3.153, NarTop10Accuracy=0.6926, over 7212.00 frames. ], tot_loss[loss=3.188, NarTop10Accuracy=0.6882, over 5987.41 frames. ], batch size: 22, lr: 5.69e-03
2024-08-06 17:45:43,679 INFO [trainer.py:765] (6/8) Epoch 15, batch 1900, train_loss[loss=3.103, NarTop10Accuracy=0.7042, over 6171.00 frames. ], tot_loss[loss=3.216, NarTop10Accuracy=0.6824, over 6024.94 frames. ], batch size: 50, lr: 5.68e-03
2024-08-06 17:45:53,540 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 17:46:01,743 INFO [trainer.py:811] (6/8) Epoch 15, validation: loss=3.006, NarTop10Accuracy=0.725, over 1905321.00 frames. 
2024-08-06 17:46:01,743 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 17:46:02,217 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 15, batch 2000, train_loss[loss=3.258, NarTop10Accuracy=0.6768, over 5922.00 frames. ], tot_loss[loss=3.208, NarTop10Accuracy=0.6841, over 5992.94 frames. ], batch size: 51, lr: 5.67e-03
2024-08-06 17:46:42,773 INFO [trainer.py:765] (6/8) Epoch 15, batch 2100, train_loss[loss=3.286, NarTop10Accuracy=0.6678, over 4773.00 frames. ], tot_loss[loss=3.201, NarTop10Accuracy=0.6857, over 5994.04 frames. ], batch size: 5, lr: 5.67e-03
2024-08-06 17:47:08,033 INFO [trainer.py:765] (6/8) Epoch 15, batch 2200, train_loss[loss=3.089, NarTop10Accuracy=0.7126, over 7239.00 frames. ], tot_loss[loss=3.215, NarTop10Accuracy=0.6831, over 6035.03 frames. ], batch size: 31, lr: 5.66e-03
2024-08-06 17:47:33,291 INFO [trainer.py:765] (6/8) Epoch 15, batch 2300, train_loss[loss=3.687, NarTop10Accuracy=0.5933, over 5679.00 frames. ], tot_loss[loss=3.216, NarTop10Accuracy=0.6827, over 6044.11 frames. ], batch size: 9, lr: 5.65e-03
2024-08-06 17:47:57,640 INFO [trainer.py:765] (6/8) Epoch 15, batch 2400, train_loss[loss=3.127, NarTop10Accuracy=0.6966, over 5055.00 frames. ], tot_loss[loss=3.197, NarTop10Accuracy=0.6863, over 5766.54 frames. ], batch size: 7, lr: 5.65e-03
2024-08-06 17:48:21,161 INFO [trainer.py:765] (6/8) Epoch 15, batch 2500, train_loss[loss=2.776, NarTop10Accuracy=0.7751, over 5097.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.691, over 5470.98 frames. ], batch size: 7, lr: 5.64e-03
2024-08-06 17:48:40,661 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 17:49:41,221 INFO [trainer.py:765] (6/8) Epoch 16, batch 100, train_loss[loss=3.571, NarTop10Accuracy=0.6129, over 7305.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6939, over 2363.35 frames. ], batch size: 31, lr: 5.45e-03
2024-08-06 17:50:12,158 INFO [trainer.py:765] (6/8) Epoch 16, batch 200, train_loss[loss=2.904, NarTop10Accuracy=0.7493, over 6894.00 frames. ], tot_loss[loss=3.201, NarTop10Accuracy=0.6855, over 3845.08 frames. ], batch size: 17, lr: 5.44e-03
2024-08-06 17:50:45,160 INFO [trainer.py:765] (6/8) Epoch 16, batch 300, train_loss[loss=3.098, NarTop10Accuracy=0.7098, over 6972.00 frames. ], tot_loss[loss=3.192, NarTop10Accuracy=0.6875, over 4641.76 frames. ], batch size: 22, lr: 5.43e-03
2024-08-06 17:51:15,976 INFO [trainer.py:765] (6/8) Epoch 16, batch 400, train_loss[loss=3.44, NarTop10Accuracy=0.6347, over 5175.00 frames. ], tot_loss[loss=3.193, NarTop10Accuracy=0.6872, over 5100.04 frames. ], batch size: 7, lr: 5.43e-03
2024-08-06 17:51:50,324 INFO [trainer.py:765] (6/8) Epoch 16, batch 500, train_loss[loss=2.984, NarTop10Accuracy=0.7338, over 6165.00 frames. ], tot_loss[loss=3.184, NarTop10Accuracy=0.6891, over 5365.77 frames. ], batch size: 11, lr: 5.42e-03
2024-08-06 17:52:24,252 INFO [trainer.py:765] (6/8) Epoch 16, batch 600, train_loss[loss=3.004, NarTop10Accuracy=0.7289, over 5610.00 frames. ], tot_loss[loss=3.188, NarTop10Accuracy=0.6883, over 5636.30 frames. ], batch size: 9, lr: 5.41e-03
2024-08-06 17:52:55,387 INFO [trainer.py:765] (6/8) Epoch 16, batch 700, train_loss[loss=2.901, NarTop10Accuracy=0.7437, over 5142.00 frames. ], tot_loss[loss=3.184, NarTop10Accuracy=0.6892, over 5707.82 frames. ], batch size: 6, lr: 5.41e-03
2024-08-06 17:53:33,816 INFO [trainer.py:765] (6/8) Epoch 16, batch 800, train_loss[loss=3.278, NarTop10Accuracy=0.6686, over 4998.00 frames. ], tot_loss[loss=3.184, NarTop10Accuracy=0.6894, over 5757.91 frames. ], batch size: 6, lr: 5.40e-03
2024-08-06 17:54:03,923 INFO [trainer.py:765] (6/8) Epoch 16, batch 900, train_loss[loss=3.399, NarTop10Accuracy=0.651, over 6264.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6915, over 5785.21 frames. ], batch size: 13, lr: 5.39e-03
2024-08-06 17:54:37,607 INFO [trainer.py:765] (6/8) Epoch 16, batch 1000, train_loss[loss=3.042, NarTop10Accuracy=0.7227, over 6801.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6934, over 5879.46 frames. ], batch size: 14, lr: 5.39e-03
2024-08-06 17:55:17,197 INFO [trainer.py:765] (6/8) Epoch 16, batch 1100, train_loss[loss=3.119, NarTop10Accuracy=0.7031, over 6771.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.6878, over 5910.39 frames. ], batch size: 17, lr: 5.38e-03
2024-08-06 17:55:46,210 INFO [trainer.py:765] (6/8) Epoch 16, batch 1200, train_loss[loss=3.474, NarTop10Accuracy=0.6372, over 7077.00 frames. ], tot_loss[loss=3.193, NarTop10Accuracy=0.687, over 5900.38 frames. ], batch size: 31, lr: 5.37e-03
2024-08-06 17:56:22,776 INFO [trainer.py:765] (6/8) Epoch 16, batch 1300, train_loss[loss=3.45, NarTop10Accuracy=0.6303, over 5064.00 frames. ], tot_loss[loss=3.189, NarTop10Accuracy=0.6878, over 5964.38 frames. ], batch size: 6, lr: 5.37e-03
2024-08-06 17:56:44,648 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 17:56:53,428 INFO [trainer.py:811] (6/8) Epoch 16, validation: loss=3.112, NarTop10Accuracy=0.703, over 1905321.00 frames. 
2024-08-06 17:56:53,429 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 17:56:54,008 INFO [optim.py:386] (6/8) Clipping_scale=2.0, grad-norm quartiles 1.620e+02 1.974e+02 2.136e+02 2.310e+02 5.351e+02, threshold=4.271e+02, percent-clipped=0.2
2024-08-06 17:57:06,171 INFO [trainer.py:765] (6/8) Epoch 16, batch 1400, train_loss[loss=3.061, NarTop10Accuracy=0.7149, over 5991.00 frames. ], tot_loss[loss=3.187, NarTop10Accuracy=0.6886, over 5989.22 frames. ], batch size: 11, lr: 5.36e-03
2024-08-06 17:57:34,034 INFO [trainer.py:765] (6/8) Epoch 16, batch 1500, train_loss[loss=3.337, NarTop10Accuracy=0.6602, over 6090.00 frames. ], tot_loss[loss=3.184, NarTop10Accuracy=0.689, over 5935.55 frames. ], batch size: 53, lr: 5.35e-03
2024-08-06 17:58:01,775 INFO [trainer.py:765] (6/8) Epoch 16, batch 1600, train_loss[loss=3.082, NarTop10Accuracy=0.7102, over 7080.00 frames. ], tot_loss[loss=3.184, NarTop10Accuracy=0.6892, over 5913.63 frames. ], batch size: 22, lr: 5.35e-03
2024-08-06 17:58:28,475 INFO [trainer.py:765] (6/8) Epoch 16, batch 1700, train_loss[loss=2.94, NarTop10Accuracy=0.7454, over 6255.00 frames. ], tot_loss[loss=3.194, NarTop10Accuracy=0.6872, over 5909.55 frames. ], batch size: 13, lr: 5.34e-03
2024-08-06 17:58:54,976 INFO [trainer.py:765] (6/8) Epoch 16, batch 1800, train_loss[loss=3.071, NarTop10Accuracy=0.7066, over 6990.00 frames. ], tot_loss[loss=3.185, NarTop10Accuracy=0.689, over 5969.88 frames. ], batch size: 22, lr: 5.33e-03
2024-08-06 17:59:21,360 INFO [trainer.py:765] (6/8) Epoch 16, batch 1900, train_loss[loss=3.474, NarTop10Accuracy=0.6338, over 6228.00 frames. ], tot_loss[loss=3.208, NarTop10Accuracy=0.6842, over 6014.37 frames. ], batch size: 53, lr: 5.33e-03
2024-08-06 17:59:46,857 INFO [trainer.py:765] (6/8) Epoch 16, batch 2000, train_loss[loss=3.13, NarTop10Accuracy=0.7014, over 6204.00 frames. ], tot_loss[loss=3.178, NarTop10Accuracy=0.6904, over 5995.28 frames. ], batch size: 51, lr: 5.32e-03
2024-08-06 18:00:12,117 INFO [trainer.py:765] (6/8) Epoch 16, batch 2100, train_loss[loss=3.32, NarTop10Accuracy=0.6648, over 4818.00 frames. ], tot_loss[loss=3.21, NarTop10Accuracy=0.684, over 5975.22 frames. ], batch size: 5, lr: 5.32e-03
2024-08-06 18:00:37,333 INFO [trainer.py:765] (6/8) Epoch 16, batch 2200, train_loss[loss=3.29, NarTop10Accuracy=0.6627, over 7311.00 frames. ], tot_loss[loss=3.22, NarTop10Accuracy=0.6818, over 6009.73 frames. ], batch size: 31, lr: 5.31e-03
2024-08-06 18:01:02,503 INFO [trainer.py:765] (6/8) Epoch 16, batch 2300, train_loss[loss=3.057, NarTop10Accuracy=0.7241, over 5682.00 frames. ], tot_loss[loss=3.218, NarTop10Accuracy=0.6821, over 6017.44 frames. ], batch size: 9, lr: 5.30e-03
2024-08-06 18:01:26,883 INFO [trainer.py:765] (6/8) Epoch 16, batch 2400, train_loss[loss=3.081, NarTop10Accuracy=0.7068, over 5061.00 frames. ], tot_loss[loss=3.197, NarTop10Accuracy=0.6863, over 5755.12 frames. ], batch size: 7, lr: 5.30e-03
2024-08-06 18:01:50,406 INFO [trainer.py:765] (6/8) Epoch 16, batch 2500, train_loss[loss=2.83, NarTop10Accuracy=0.757, over 5217.00 frames. ], tot_loss[loss=3.162, NarTop10Accuracy=0.6933, over 5489.18 frames. ], batch size: 7, lr: 5.29e-03
2024-08-06 18:02:10,329 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 18:03:08,531 INFO [trainer.py:765] (6/8) Epoch 17, batch 100, train_loss[loss=3.12, NarTop10Accuracy=0.7023, over 7296.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6968, over 2357.15 frames. ], batch size: 31, lr: 5.12e-03
2024-08-06 18:03:45,145 INFO [trainer.py:765] (6/8) Epoch 17, batch 200, train_loss[loss=3.469, NarTop10Accuracy=0.6302, over 6744.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6939, over 3871.82 frames. ], batch size: 17, lr: 5.12e-03
2024-08-06 18:04:19,591 INFO [trainer.py:765] (6/8) Epoch 17, batch 300, train_loss[loss=3.405, NarTop10Accuracy=0.6473, over 6936.00 frames. ], tot_loss[loss=3.176, NarTop10Accuracy=0.6903, over 4666.85 frames. ], batch size: 22, lr: 5.11e-03
2024-08-06 18:04:48,402 INFO [trainer.py:765] (6/8) Epoch 17, batch 400, train_loss[loss=3.272, NarTop10Accuracy=0.6789, over 5247.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6909, over 5111.89 frames. ], batch size: 7, lr: 5.10e-03
2024-08-06 18:05:24,681 INFO [trainer.py:765] (6/8) Epoch 17, batch 500, train_loss[loss=2.825, NarTop10Accuracy=0.7599, over 6099.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6945, over 5379.47 frames. ], batch size: 11, lr: 5.10e-03
2024-08-06 18:05:58,739 INFO [trainer.py:765] (6/8) Epoch 17, batch 600, train_loss[loss=3.037, NarTop10Accuracy=0.7263, over 5733.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6912, over 5655.50 frames. ], batch size: 9, lr: 5.09e-03
2024-08-06 18:06:32,475 INFO [trainer.py:765] (6/8) Epoch 17, batch 700, train_loss[loss=3.229, NarTop10Accuracy=0.6784, over 4350.00 frames. ], tot_loss[loss=3.177, NarTop10Accuracy=0.6906, over 5708.96 frames. ], batch size: 5, lr: 5.08e-03
2024-08-06 18:07:02,725 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 18:07:10,763 INFO [trainer.py:811] (6/8) Epoch 17, validation: loss=3.018, NarTop10Accuracy=0.7223, over 1905321.00 frames. 
2024-08-06 18:07:10,763 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 18:07:11,311 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 17, batch 800, train_loss[loss=3.091, NarTop10Accuracy=0.7107, over 4302.00 frames. ], tot_loss[loss=3.19, NarTop10Accuracy=0.6878, over 5754.40 frames. ], batch size: 5, lr: 5.08e-03
2024-08-06 18:07:49,721 INFO [trainer.py:765] (6/8) Epoch 17, batch 900, train_loss[loss=3.54, NarTop10Accuracy=0.6141, over 6507.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.693, over 5793.40 frames. ], batch size: 14, lr: 5.07e-03
2024-08-06 18:08:21,598 INFO [trainer.py:765] (6/8) Epoch 17, batch 1000, train_loss[loss=3.286, NarTop10Accuracy=0.6667, over 6552.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6917, over 5897.17 frames. ], batch size: 14, lr: 5.07e-03
2024-08-06 18:09:03,106 INFO [trainer.py:765] (6/8) Epoch 17, batch 1100, train_loss[loss=2.987, NarTop10Accuracy=0.7313, over 6780.00 frames. ], tot_loss[loss=3.175, NarTop10Accuracy=0.6909, over 5940.43 frames. ], batch size: 17, lr: 5.06e-03
2024-08-06 18:09:36,745 INFO [trainer.py:765] (6/8) Epoch 17, batch 1200, train_loss[loss=3.089, NarTop10Accuracy=0.7115, over 7413.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6921, over 5927.26 frames. ], batch size: 31, lr: 5.06e-03
2024-08-06 18:10:10,688 INFO [trainer.py:765] (6/8) Epoch 17, batch 1300, train_loss[loss=3.28, NarTop10Accuracy=0.6624, over 5079.00 frames. ], tot_loss[loss=3.172, NarTop10Accuracy=0.6915, over 5998.41 frames. ], batch size: 6, lr: 5.05e-03
2024-08-06 18:10:48,026 INFO [trainer.py:765] (6/8) Epoch 17, batch 1400, train_loss[loss=3.315, NarTop10Accuracy=0.664, over 6177.00 frames. ], tot_loss[loss=3.178, NarTop10Accuracy=0.6906, over 5999.05 frames. ], batch size: 11, lr: 5.04e-03
2024-08-06 18:11:19,105 INFO [trainer.py:765] (6/8) Epoch 17, batch 1500, train_loss[loss=3.43, NarTop10Accuracy=0.6387, over 6267.00 frames. ], tot_loss[loss=3.174, NarTop10Accuracy=0.6914, over 5937.58 frames. ], batch size: 51, lr: 5.04e-03
2024-08-06 18:11:46,854 INFO [trainer.py:765] (6/8) Epoch 17, batch 1600, train_loss[loss=2.967, NarTop10Accuracy=0.7268, over 7140.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6935, over 5908.71 frames. ], batch size: 22, lr: 5.03e-03
2024-08-06 18:12:13,508 INFO [trainer.py:765] (6/8) Epoch 17, batch 1700, train_loss[loss=3.542, NarTop10Accuracy=0.6163, over 6639.00 frames. ], tot_loss[loss=3.181, NarTop10Accuracy=0.6897, over 5909.69 frames. ], batch size: 14, lr: 5.03e-03
2024-08-06 18:12:40,001 INFO [trainer.py:765] (6/8) Epoch 17, batch 1800, train_loss[loss=2.963, NarTop10Accuracy=0.7348, over 7134.00 frames. ], tot_loss[loss=3.186, NarTop10Accuracy=0.6883, over 5976.50 frames. ], batch size: 22, lr: 5.02e-03
2024-08-06 18:13:06,379 INFO [trainer.py:765] (6/8) Epoch 17, batch 1900, train_loss[loss=3.211, NarTop10Accuracy=0.689, over 6579.00 frames. ], tot_loss[loss=3.197, NarTop10Accuracy=0.6858, over 6010.71 frames. ], batch size: 51, lr: 5.01e-03
2024-08-06 18:13:31,923 INFO [trainer.py:765] (6/8) Epoch 17, batch 2000, train_loss[loss=3.592, NarTop10Accuracy=0.6079, over 5832.00 frames. ], tot_loss[loss=3.18, NarTop10Accuracy=0.6899, over 6002.12 frames. ], batch size: 51, lr: 5.01e-03
2024-08-06 18:13:57,228 INFO [trainer.py:765] (6/8) Epoch 17, batch 2100, train_loss[loss=2.918, NarTop10Accuracy=0.7486, over 3891.00 frames. ], tot_loss[loss=3.178, NarTop10Accuracy=0.6901, over 5967.83 frames. ], batch size: 4, lr: 5.00e-03
2024-08-06 18:14:22,434 INFO [trainer.py:765] (6/8) Epoch 17, batch 2200, train_loss[loss=3.024, NarTop10Accuracy=0.7274, over 7095.00 frames. ], tot_loss[loss=3.195, NarTop10Accuracy=0.6865, over 6011.05 frames. ], batch size: 31, lr: 5.00e-03
2024-08-06 18:14:47,592 INFO [trainer.py:765] (6/8) Epoch 17, batch 2300, train_loss[loss=2.939, NarTop10Accuracy=0.7373, over 5643.00 frames. ], tot_loss[loss=3.184, NarTop10Accuracy=0.689, over 6016.98 frames. ], batch size: 9, lr: 4.99e-03
2024-08-06 18:15:12,061 INFO [trainer.py:765] (6/8) Epoch 17, batch 2400, train_loss[loss=2.932, NarTop10Accuracy=0.7402, over 5220.00 frames. ], tot_loss[loss=3.183, NarTop10Accuracy=0.6891, over 5780.83 frames. ], batch size: 7, lr: 4.99e-03
2024-08-06 18:15:35,514 INFO [trainer.py:765] (6/8) Epoch 17, batch 2500, train_loss[loss=2.898, NarTop10Accuracy=0.7519, over 5190.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.6924, over 5473.16 frames. ], batch size: 7, lr: 4.98e-03
2024-08-06 18:15:54,965 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 18:16:49,907 INFO [trainer.py:765] (6/8) Epoch 18, batch 100, train_loss[loss=3.037, NarTop10Accuracy=0.7228, over 7122.00 frames. ], tot_loss[loss=3.183, NarTop10Accuracy=0.6901, over 2377.90 frames. ], batch size: 31, lr: 4.83e-03
2024-08-06 18:17:24,749 INFO [trainer.py:765] (6/8) Epoch 18, batch 200, train_loss[loss=2.939, NarTop10Accuracy=0.7447, over 6759.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6937, over 3851.92 frames. ], batch size: 17, lr: 4.83e-03
2024-08-06 18:17:27,715 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 18:17:35,926 INFO [trainer.py:811] (6/8) Epoch 18, validation: loss=3.062, NarTop10Accuracy=0.7137, over 1905321.00 frames. 
2024-08-06 18:17:35,927 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 18:17:36,528 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 18, batch 300, train_loss[loss=3.386, NarTop10Accuracy=0.6422, over 6942.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6931, over 4653.18 frames. ], batch size: 22, lr: 4.82e-03
2024-08-06 18:18:38,183 INFO [trainer.py:765] (6/8) Epoch 18, batch 400, train_loss[loss=3.315, NarTop10Accuracy=0.6641, over 5046.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.6951, over 5111.84 frames. ], batch size: 7, lr: 4.81e-03
2024-08-06 18:19:13,599 INFO [trainer.py:765] (6/8) Epoch 18, batch 500, train_loss[loss=3.103, NarTop10Accuracy=0.7098, over 6219.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6947, over 5401.39 frames. ], batch size: 11, lr: 4.81e-03
2024-08-06 18:19:48,151 INFO [trainer.py:765] (6/8) Epoch 18, batch 600, train_loss[loss=3.507, NarTop10Accuracy=0.6309, over 5745.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6947, over 5657.06 frames. ], batch size: 9, lr: 4.80e-03
2024-08-06 18:20:23,870 INFO [trainer.py:765] (6/8) Epoch 18, batch 700, train_loss[loss=3.284, NarTop10Accuracy=0.664, over 5115.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.6926, over 5730.41 frames. ], batch size: 6, lr: 4.80e-03
2024-08-06 18:21:01,026 INFO [trainer.py:765] (6/8) Epoch 18, batch 800, train_loss[loss=2.685, NarTop10Accuracy=0.7954, over 4992.00 frames. ], tot_loss[loss=3.165, NarTop10Accuracy=0.6926, over 5797.58 frames. ], batch size: 6, lr: 4.79e-03
2024-08-06 18:21:32,409 INFO [trainer.py:765] (6/8) Epoch 18, batch 900, train_loss[loss=2.955, NarTop10Accuracy=0.7256, over 6201.00 frames. ], tot_loss[loss=3.149, NarTop10Accuracy=0.696, over 5822.87 frames. ], batch size: 13, lr: 4.79e-03
2024-08-06 18:22:11,192 INFO [trainer.py:765] (6/8) Epoch 18, batch 1000, train_loss[loss=2.992, NarTop10Accuracy=0.7283, over 6639.00 frames. ], tot_loss[loss=3.159, NarTop10Accuracy=0.6936, over 5917.94 frames. ], batch size: 14, lr: 4.78e-03
2024-08-06 18:22:46,969 INFO [trainer.py:765] (6/8) Epoch 18, batch 1100, train_loss[loss=3.4, NarTop10Accuracy=0.641, over 6771.00 frames. ], tot_loss[loss=3.166, NarTop10Accuracy=0.6927, over 5928.99 frames. ], batch size: 17, lr: 4.78e-03
2024-08-06 18:23:18,605 INFO [trainer.py:765] (6/8) Epoch 18, batch 1200, train_loss[loss=3.514, NarTop10Accuracy=0.6158, over 7536.00 frames. ], tot_loss[loss=3.175, NarTop10Accuracy=0.6909, over 5920.93 frames. ], batch size: 31, lr: 4.77e-03
2024-08-06 18:24:00,099 INFO [trainer.py:765] (6/8) Epoch 18, batch 1300, train_loss[loss=2.956, NarTop10Accuracy=0.7497, over 4149.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6946, over 5988.84 frames. ], batch size: 5, lr: 4.77e-03
2024-08-06 18:24:29,574 INFO [trainer.py:765] (6/8) Epoch 18, batch 1400, train_loss[loss=3.018, NarTop10Accuracy=0.7189, over 6018.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6949, over 6016.93 frames. ], batch size: 11, lr: 4.76e-03
2024-08-06 18:25:00,307 INFO [trainer.py:765] (6/8) Epoch 18, batch 1500, train_loss[loss=3.117, NarTop10Accuracy=0.7067, over 6060.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6948, over 5962.69 frames. ], batch size: 50, lr: 4.76e-03
2024-08-06 18:25:28,085 INFO [trainer.py:765] (6/8) Epoch 18, batch 1600, train_loss[loss=2.992, NarTop10Accuracy=0.7289, over 7029.00 frames. ], tot_loss[loss=3.165, NarTop10Accuracy=0.6934, over 5938.61 frames. ], batch size: 22, lr: 4.75e-03
2024-08-06 18:25:54,688 INFO [trainer.py:765] (6/8) Epoch 18, batch 1700, train_loss[loss=3.159, NarTop10Accuracy=0.6945, over 6195.00 frames. ], tot_loss[loss=3.168, NarTop10Accuracy=0.6924, over 5912.17 frames. ], batch size: 13, lr: 4.75e-03
2024-08-06 18:26:21,197 INFO [trainer.py:765] (6/8) Epoch 18, batch 1800, train_loss[loss=3.372, NarTop10Accuracy=0.6484, over 7716.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.695, over 5975.40 frames. ], batch size: 23, lr: 4.74e-03
2024-08-06 18:26:47,567 INFO [trainer.py:765] (6/8) Epoch 18, batch 1900, train_loss[loss=3.046, NarTop10Accuracy=0.7166, over 6261.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6924, over 6020.62 frames. ], batch size: 51, lr: 4.74e-03
2024-08-06 18:27:13,176 INFO [trainer.py:765] (6/8) Epoch 18, batch 2000, train_loss[loss=3.063, NarTop10Accuracy=0.7181, over 6153.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6945, over 5980.48 frames. ], batch size: 51, lr: 4.73e-03
2024-08-06 18:27:38,529 INFO [trainer.py:765] (6/8) Epoch 18, batch 2100, train_loss[loss=3.216, NarTop10Accuracy=0.6717, over 4923.00 frames. ], tot_loss[loss=3.158, NarTop10Accuracy=0.6945, over 5975.77 frames. ], batch size: 5, lr: 4.73e-03
2024-08-06 18:28:03,812 INFO [trainer.py:765] (6/8) Epoch 18, batch 2200, train_loss[loss=3.033, NarTop10Accuracy=0.7182, over 7482.00 frames. ], tot_loss[loss=3.16, NarTop10Accuracy=0.6943, over 6000.64 frames. ], batch size: 33, lr: 4.72e-03
2024-08-06 18:28:06,572 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 18:28:14,649 INFO [trainer.py:811] (6/8) Epoch 18, validation: loss=3.028, NarTop10Accuracy=0.7201, over 1905321.00 frames. 
2024-08-06 18:28:14,650 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 18:28:15,147 INFO [optim.py:386] (6/8) 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 18:28:37,097 INFO [trainer.py:765] (6/8) Epoch 18, batch 2300, train_loss[loss=2.937, NarTop10Accuracy=0.7478, over 5832.00 frames. ], tot_loss[loss=3.176, NarTop10Accuracy=0.6908, over 6016.09 frames. ], batch size: 9, lr: 4.72e-03
2024-08-06 18:29:01,592 INFO [trainer.py:765] (6/8) Epoch 18, batch 2400, train_loss[loss=2.973, NarTop10Accuracy=0.7269, over 5277.00 frames. ], tot_loss[loss=3.155, NarTop10Accuracy=0.6949, over 5778.90 frames. ], batch size: 7, lr: 4.71e-03
2024-08-06 18:29:25,027 INFO [trainer.py:765] (6/8) Epoch 18, batch 2500, train_loss[loss=2.914, NarTop10Accuracy=0.7405, over 5352.00 frames. ], tot_loss[loss=3.137, NarTop10Accuracy=0.6984, over 5502.01 frames. ], batch size: 7, lr: 4.71e-03
2024-08-06 18:29:45,229 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 18:30:41,232 INFO [trainer.py:765] (6/8) Epoch 19, batch 100, train_loss[loss=2.992, NarTop10Accuracy=0.7299, over 7494.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6931, over 2373.25 frames. ], batch size: 32, lr: 4.57e-03
2024-08-06 18:31:15,602 INFO [trainer.py:765] (6/8) Epoch 19, batch 200, train_loss[loss=3.077, NarTop10Accuracy=0.7173, over 6822.00 frames. ], tot_loss[loss=3.164, NarTop10Accuracy=0.6937, over 3858.92 frames. ], batch size: 17, lr: 4.57e-03
2024-08-06 18:31:47,468 INFO [trainer.py:765] (6/8) Epoch 19, batch 300, train_loss[loss=3.475, NarTop10Accuracy=0.6322, over 7089.00 frames. ], tot_loss[loss=3.141, NarTop10Accuracy=0.6982, over 4665.50 frames. ], batch size: 22, lr: 4.56e-03
2024-08-06 18:32:20,355 INFO [trainer.py:765] (6/8) Epoch 19, batch 400, train_loss[loss=3.183, NarTop10Accuracy=0.6885, over 5049.00 frames. ], tot_loss[loss=3.14, NarTop10Accuracy=0.6984, over 5119.97 frames. ], batch size: 7, lr: 4.56e-03
2024-08-06 18:32:50,335 INFO [trainer.py:765] (6/8) Epoch 19, batch 500, train_loss[loss=2.914, NarTop10Accuracy=0.7562, over 6093.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.6988, over 5384.44 frames. ], batch size: 11, lr: 4.55e-03
2024-08-06 18:33:29,610 INFO [trainer.py:765] (6/8) Epoch 19, batch 600, train_loss[loss=3.116, NarTop10Accuracy=0.7109, over 5616.00 frames. ], tot_loss[loss=3.142, NarTop10Accuracy=0.6973, over 5642.15 frames. ], batch size: 9, lr: 4.55e-03
2024-08-06 18:34:03,592 INFO [trainer.py:765] (6/8) Epoch 19, batch 700, train_loss[loss=2.805, NarTop10Accuracy=0.7628, over 5166.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6968, over 5720.97 frames. ], batch size: 6, lr: 4.54e-03
2024-08-06 18:34:35,179 INFO [trainer.py:765] (6/8) Epoch 19, batch 800, train_loss[loss=3.279, NarTop10Accuracy=0.668, over 4989.00 frames. ], tot_loss[loss=3.153, NarTop10Accuracy=0.6953, over 5788.65 frames. ], batch size: 6, lr: 4.54e-03
2024-08-06 18:35:10,263 INFO [trainer.py:765] (6/8) Epoch 19, batch 900, train_loss[loss=2.866, NarTop10Accuracy=0.7568, over 6273.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6965, over 5810.34 frames. ], batch size: 13, lr: 4.53e-03
2024-08-06 18:35:48,637 INFO [trainer.py:765] (6/8) Epoch 19, batch 1000, train_loss[loss=3.398, NarTop10Accuracy=0.6473, over 6705.00 frames. ], tot_loss[loss=3.147, NarTop10Accuracy=0.6964, over 5906.78 frames. ], batch size: 14, lr: 4.53e-03
2024-08-06 18:36:20,938 INFO [trainer.py:765] (6/8) Epoch 19, batch 1100, train_loss[loss=2.953, NarTop10Accuracy=0.7412, over 6843.00 frames. ], tot_loss[loss=3.159, NarTop10Accuracy=0.6942, over 5938.44 frames. ], batch size: 17, lr: 4.52e-03
2024-08-06 18:36:57,130 INFO [trainer.py:765] (6/8) Epoch 19, batch 1200, train_loss[loss=3.008, NarTop10Accuracy=0.7318, over 7167.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6932, over 5937.40 frames. ], batch size: 31, lr: 4.52e-03
2024-08-06 18:37:35,314 INFO [trainer.py:765] (6/8) Epoch 19, batch 1300, train_loss[loss=2.845, NarTop10Accuracy=0.7566, over 5076.00 frames. ], tot_loss[loss=3.169, NarTop10Accuracy=0.6917, over 5996.96 frames. ], batch size: 6, lr: 4.51e-03
2024-08-06 18:38:04,679 INFO [trainer.py:765] (6/8) Epoch 19, batch 1400, train_loss[loss=2.871, NarTop10Accuracy=0.7545, over 6000.00 frames. ], tot_loss[loss=3.17, NarTop10Accuracy=0.6915, over 6007.85 frames. ], batch size: 11, lr: 4.51e-03
2024-08-06 18:38:34,550 INFO [trainer.py:765] (6/8) Epoch 19, batch 1500, train_loss[loss=3.341, NarTop10Accuracy=0.6586, over 6039.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6963, over 5950.58 frames. ], batch size: 50, lr: 4.50e-03
2024-08-06 18:39:02,311 INFO [trainer.py:765] (6/8) Epoch 19, batch 1600, train_loss[loss=3.522, NarTop10Accuracy=0.6199, over 7044.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6964, over 5936.85 frames. ], batch size: 22, lr: 4.50e-03
2024-08-06 18:39:11,590 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 18:39:19,795 INFO [trainer.py:811] (6/8) Epoch 19, validation: loss=2.958, NarTop10Accuracy=0.7345, over 1905321.00 frames. 
2024-08-06 18:39:19,796 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 18:39:20,379 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 19, batch 1700, train_loss[loss=3.421, NarTop10Accuracy=0.6373, over 6249.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6961, over 5905.83 frames. ], batch size: 13, lr: 4.49e-03
2024-08-06 18:40:03,789 INFO [trainer.py:765] (6/8) Epoch 19, batch 1800, train_loss[loss=3.568, NarTop10Accuracy=0.6177, over 7104.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6968, over 5967.31 frames. ], batch size: 22, lr: 4.49e-03
2024-08-06 18:40:30,217 INFO [trainer.py:765] (6/8) Epoch 19, batch 1900, train_loss[loss=3.133, NarTop10Accuracy=0.7008, over 6438.00 frames. ], tot_loss[loss=3.147, NarTop10Accuracy=0.6964, over 6019.44 frames. ], batch size: 50, lr: 4.49e-03
2024-08-06 18:40:55,793 INFO [trainer.py:765] (6/8) Epoch 19, batch 2000, train_loss[loss=3.276, NarTop10Accuracy=0.672, over 5853.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6965, over 6001.39 frames. ], batch size: 51, lr: 4.48e-03
2024-08-06 18:41:21,183 INFO [trainer.py:765] (6/8) Epoch 19, batch 2100, train_loss[loss=2.791, NarTop10Accuracy=0.7735, over 3969.00 frames. ], tot_loss[loss=3.136, NarTop10Accuracy=0.6984, over 5965.49 frames. ], batch size: 4, lr: 4.48e-03
2024-08-06 18:41:46,455 INFO [trainer.py:765] (6/8) Epoch 19, batch 2200, train_loss[loss=3.169, NarTop10Accuracy=0.689, over 6984.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6963, over 6009.46 frames. ], batch size: 31, lr: 4.47e-03
2024-08-06 18:42:11,559 INFO [trainer.py:765] (6/8) Epoch 19, batch 2300, train_loss[loss=3.288, NarTop10Accuracy=0.6512, over 5721.00 frames. ], tot_loss[loss=3.165, NarTop10Accuracy=0.6928, over 6003.71 frames. ], batch size: 9, lr: 4.47e-03
2024-08-06 18:42:35,988 INFO [trainer.py:765] (6/8) Epoch 19, batch 2400, train_loss[loss=2.954, NarTop10Accuracy=0.7309, over 5109.00 frames. ], tot_loss[loss=3.139, NarTop10Accuracy=0.6978, over 5762.13 frames. ], batch size: 7, lr: 4.46e-03
2024-08-06 18:42:59,690 INFO [trainer.py:765] (6/8) Epoch 19, batch 2500, train_loss[loss=2.972, NarTop10Accuracy=0.7297, over 5106.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7019, over 5471.70 frames. ], batch size: 7, lr: 4.46e-03
2024-08-06 18:43:19,816 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 18:44:22,973 INFO [trainer.py:765] (6/8) Epoch 20, batch 100, train_loss[loss=3.256, NarTop10Accuracy=0.6703, over 7434.00 frames. ], tot_loss[loss=3.163, NarTop10Accuracy=0.6934, over 2366.08 frames. ], batch size: 31, lr: 4.34e-03
2024-08-06 18:44:58,379 INFO [trainer.py:765] (6/8) Epoch 20, batch 200, train_loss[loss=3.48, NarTop10Accuracy=0.6196, over 6786.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7019, over 3866.86 frames. ], batch size: 17, lr: 4.33e-03
2024-08-06 18:45:32,278 INFO [trainer.py:765] (6/8) Epoch 20, batch 300, train_loss[loss=3.384, NarTop10Accuracy=0.6453, over 7200.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7034, over 4670.06 frames. ], batch size: 22, lr: 4.33e-03
2024-08-06 18:46:05,128 INFO [trainer.py:765] (6/8) Epoch 20, batch 400, train_loss[loss=2.819, NarTop10Accuracy=0.7627, over 5745.00 frames. ], tot_loss[loss=3.117, NarTop10Accuracy=0.7028, over 5120.23 frames. ], batch size: 8, lr: 4.32e-03
2024-08-06 18:46:35,769 INFO [trainer.py:765] (6/8) Epoch 20, batch 500, train_loss[loss=2.883, NarTop10Accuracy=0.7598, over 6192.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.7004, over 5388.71 frames. ], batch size: 11, lr: 4.32e-03
2024-08-06 18:47:13,255 INFO [trainer.py:765] (6/8) Epoch 20, batch 600, train_loss[loss=2.819, NarTop10Accuracy=0.7485, over 5727.00 frames. ], tot_loss[loss=3.13, NarTop10Accuracy=0.7, over 5641.06 frames. ], batch size: 9, lr: 4.31e-03
2024-08-06 18:47:44,481 INFO [trainer.py:765] (6/8) Epoch 20, batch 700, train_loss[loss=2.745, NarTop10Accuracy=0.7775, over 5067.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7022, over 5711.15 frames. ], batch size: 6, lr: 4.31e-03
2024-08-06 18:48:21,016 INFO [trainer.py:765] (6/8) Epoch 20, batch 800, train_loss[loss=2.809, NarTop10Accuracy=0.7644, over 5196.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.7, over 5775.10 frames. ], batch size: 6, lr: 4.31e-03
2024-08-06 18:48:56,534 INFO [trainer.py:765] (6/8) Epoch 20, batch 900, train_loss[loss=2.965, NarTop10Accuracy=0.7403, over 6315.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.7006, over 5793.62 frames. ], batch size: 13, lr: 4.30e-03
2024-08-06 18:49:29,805 INFO [trainer.py:765] (6/8) Epoch 20, batch 1000, train_loss[loss=3.107, NarTop10Accuracy=0.6938, over 6162.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6966, over 5889.08 frames. ], batch size: 13, lr: 4.30e-03
2024-08-06 18:49:52,236 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 18:50:00,327 INFO [trainer.py:811] (6/8) Epoch 20, validation: loss=2.962, NarTop10Accuracy=0.7336, over 1905321.00 frames. 
2024-08-06 18:50:00,327 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30248MB
2024-08-06 18:50:00,874 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 20, batch 1100, train_loss[loss=3.255, NarTop10Accuracy=0.6796, over 6843.00 frames. ], tot_loss[loss=3.142, NarTop10Accuracy=0.6967, over 5928.68 frames. ], batch size: 17, lr: 4.29e-03
2024-08-06 18:50:53,775 INFO [trainer.py:765] (6/8) Epoch 20, batch 1200, train_loss[loss=3.003, NarTop10Accuracy=0.7334, over 7503.00 frames. ], tot_loss[loss=3.148, NarTop10Accuracy=0.6956, over 5912.11 frames. ], batch size: 32, lr: 4.29e-03
2024-08-06 18:51:25,129 INFO [trainer.py:765] (6/8) Epoch 20, batch 1300, train_loss[loss=3.253, NarTop10Accuracy=0.6703, over 4959.00 frames. ], tot_loss[loss=3.136, NarTop10Accuracy=0.698, over 5980.43 frames. ], batch size: 6, lr: 4.29e-03
2024-08-06 18:51:59,314 INFO [trainer.py:765] (6/8) Epoch 20, batch 1400, train_loss[loss=3.194, NarTop10Accuracy=0.6938, over 6048.00 frames. ], tot_loss[loss=3.13, NarTop10Accuracy=0.6995, over 6006.34 frames. ], batch size: 11, lr: 4.28e-03
2024-08-06 18:52:32,805 INFO [trainer.py:765] (6/8) Epoch 20, batch 1500, train_loss[loss=3.297, NarTop10Accuracy=0.6705, over 6219.00 frames. ], tot_loss[loss=3.141, NarTop10Accuracy=0.6973, over 5955.64 frames. ], batch size: 50, lr: 4.28e-03
2024-08-06 18:53:00,635 INFO [trainer.py:765] (6/8) Epoch 20, batch 1600, train_loss[loss=2.88, NarTop10Accuracy=0.7536, over 6942.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6965, over 5937.66 frames. ], batch size: 22, lr: 4.27e-03
2024-08-06 18:53:27,327 INFO [trainer.py:765] (6/8) Epoch 20, batch 1700, train_loss[loss=3.494, NarTop10Accuracy=0.6395, over 6303.00 frames. ], tot_loss[loss=3.139, NarTop10Accuracy=0.6978, over 5924.57 frames. ], batch size: 13, lr: 4.27e-03
2024-08-06 18:53:53,850 INFO [trainer.py:765] (6/8) Epoch 20, batch 1800, train_loss[loss=3.117, NarTop10Accuracy=0.7079, over 7053.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.6987, over 5979.26 frames. ], batch size: 22, lr: 4.26e-03
2024-08-06 18:54:20,316 INFO [trainer.py:765] (6/8) Epoch 20, batch 1900, train_loss[loss=3.103, NarTop10Accuracy=0.7039, over 6528.00 frames. ], tot_loss[loss=3.154, NarTop10Accuracy=0.6947, over 6030.82 frames. ], batch size: 51, lr: 4.26e-03
2024-08-06 18:54:45,890 INFO [trainer.py:765] (6/8) Epoch 20, batch 2000, train_loss[loss=3.664, NarTop10Accuracy=0.5939, over 5913.00 frames. ], tot_loss[loss=3.157, NarTop10Accuracy=0.6941, over 5994.45 frames. ], batch size: 51, lr: 4.26e-03
2024-08-06 18:55:11,182 INFO [trainer.py:765] (6/8) Epoch 20, batch 2100, train_loss[loss=3.269, NarTop10Accuracy=0.6664, over 4689.00 frames. ], tot_loss[loss=3.152, NarTop10Accuracy=0.6952, over 5981.12 frames. ], batch size: 5, lr: 4.25e-03
2024-08-06 18:55:36,414 INFO [trainer.py:765] (6/8) Epoch 20, batch 2200, train_loss[loss=2.942, NarTop10Accuracy=0.749, over 7389.00 frames. ], tot_loss[loss=3.153, NarTop10Accuracy=0.6953, over 6031.23 frames. ], batch size: 31, lr: 4.25e-03
2024-08-06 18:56:01,635 INFO [trainer.py:765] (6/8) Epoch 20, batch 2300, train_loss[loss=3.22, NarTop10Accuracy=0.6881, over 5742.00 frames. ], tot_loss[loss=3.165, NarTop10Accuracy=0.6929, over 6043.12 frames. ], batch size: 9, lr: 4.24e-03
2024-08-06 18:56:26,049 INFO [trainer.py:765] (6/8) Epoch 20, batch 2400, train_loss[loss=2.964, NarTop10Accuracy=0.7405, over 5217.00 frames. ], tot_loss[loss=3.153, NarTop10Accuracy=0.6952, over 5808.44 frames. ], batch size: 7, lr: 4.24e-03
2024-08-06 18:56:49,565 INFO [trainer.py:765] (6/8) Epoch 20, batch 2500, train_loss[loss=2.838, NarTop10Accuracy=0.7625, over 5166.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7032, over 5511.09 frames. ], batch size: 7, lr: 4.24e-03
2024-08-06 18:57:09,470 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 18:58:09,585 INFO [trainer.py:765] (6/8) Epoch 21, batch 100, train_loss[loss=3.221, NarTop10Accuracy=0.6762, over 7203.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7042, over 2369.48 frames. ], batch size: 31, lr: 4.13e-03
2024-08-06 18:58:40,418 INFO [trainer.py:765] (6/8) Epoch 21, batch 200, train_loss[loss=2.884, NarTop10Accuracy=0.7529, over 6789.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7007, over 3864.59 frames. ], batch size: 17, lr: 4.12e-03
2024-08-06 18:59:13,333 INFO [trainer.py:765] (6/8) Epoch 21, batch 300, train_loss[loss=2.918, NarTop10Accuracy=0.7531, over 7134.00 frames. ], tot_loss[loss=3.131, NarTop10Accuracy=0.6995, over 4656.80 frames. ], batch size: 22, lr: 4.12e-03
2024-08-06 18:59:48,151 INFO [trainer.py:765] (6/8) Epoch 21, batch 400, train_loss[loss=2.841, NarTop10Accuracy=0.7587, over 5127.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7028, over 5113.81 frames. ], batch size: 7, lr: 4.11e-03
2024-08-06 19:00:16,840 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 19:00:25,075 INFO [trainer.py:811] (6/8) Epoch 21, validation: loss=2.992, NarTop10Accuracy=0.7268, over 1905321.00 frames. 
2024-08-06 19:00:25,076 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 19:00:25,622 INFO [optim.py:386] (6/8) Clipping_scale=2.0, grad-norm quartiles 1.727e+02 2.071e+02 2.224e+02 2.387e+02 3.839e+02, threshold=4.447e+02, percent-clipped=0.0
2024-08-06 19:00:29,890 INFO [trainer.py:765] (6/8) Epoch 21, batch 500, train_loss[loss=2.841, NarTop10Accuracy=0.7647, over 6039.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7017, over 5377.83 frames. ], batch size: 11, lr: 4.11e-03
2024-08-06 19:01:03,328 INFO [trainer.py:765] (6/8) Epoch 21, batch 600, train_loss[loss=3.32, NarTop10Accuracy=0.6553, over 5715.00 frames. ], tot_loss[loss=3.104, NarTop10Accuracy=0.7051, over 5646.25 frames. ], batch size: 9, lr: 4.11e-03
2024-08-06 19:01:39,388 INFO [trainer.py:765] (6/8) Epoch 21, batch 700, train_loss[loss=2.75, NarTop10Accuracy=0.7799, over 4326.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7029, over 5709.10 frames. ], batch size: 5, lr: 4.10e-03
2024-08-06 19:02:18,047 INFO [trainer.py:765] (6/8) Epoch 21, batch 800, train_loss[loss=2.891, NarTop10Accuracy=0.7406, over 5163.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7006, over 5789.42 frames. ], batch size: 6, lr: 4.10e-03
2024-08-06 19:02:48,663 INFO [trainer.py:765] (6/8) Epoch 21, batch 900, train_loss[loss=3.034, NarTop10Accuracy=0.721, over 6327.00 frames. ], tot_loss[loss=3.127, NarTop10Accuracy=0.7002, over 5789.98 frames. ], batch size: 13, lr: 4.09e-03
2024-08-06 19:03:25,801 INFO [trainer.py:765] (6/8) Epoch 21, batch 1000, train_loss[loss=2.902, NarTop10Accuracy=0.7489, over 6855.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.6985, over 5895.25 frames. ], batch size: 14, lr: 4.09e-03
2024-08-06 19:04:07,206 INFO [trainer.py:765] (6/8) Epoch 21, batch 1100, train_loss[loss=3.507, NarTop10Accuracy=0.6113, over 6732.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6953, over 5932.83 frames. ], batch size: 17, lr: 4.09e-03
2024-08-06 19:04:38,462 INFO [trainer.py:765] (6/8) Epoch 21, batch 1200, train_loss[loss=3.206, NarTop10Accuracy=0.6817, over 7077.00 frames. ], tot_loss[loss=3.134, NarTop10Accuracy=0.6986, over 5902.83 frames. ], batch size: 31, lr: 4.08e-03
2024-08-06 19:05:15,315 INFO [trainer.py:765] (6/8) Epoch 21, batch 1300, train_loss[loss=3.025, NarTop10Accuracy=0.7232, over 4293.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7026, over 5981.63 frames. ], batch size: 5, lr: 4.08e-03
2024-08-06 19:05:55,559 INFO [trainer.py:765] (6/8) Epoch 21, batch 1400, train_loss[loss=3.439, NarTop10Accuracy=0.6368, over 6231.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7026, over 6003.08 frames. ], batch size: 11, lr: 4.07e-03
2024-08-06 19:06:23,599 INFO [trainer.py:765] (6/8) Epoch 21, batch 1500, train_loss[loss=3.308, NarTop10Accuracy=0.665, over 5868.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.6998, over 5934.08 frames. ], batch size: 50, lr: 4.07e-03
2024-08-06 19:06:51,461 INFO [trainer.py:765] (6/8) Epoch 21, batch 1600, train_loss[loss=2.933, NarTop10Accuracy=0.7315, over 6888.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7005, over 5945.46 frames. ], batch size: 22, lr: 4.07e-03
2024-08-06 19:07:18,211 INFO [trainer.py:765] (6/8) Epoch 21, batch 1700, train_loss[loss=3.191, NarTop10Accuracy=0.6856, over 6258.00 frames. ], tot_loss[loss=3.131, NarTop10Accuracy=0.6992, over 5918.00 frames. ], batch size: 13, lr: 4.06e-03
2024-08-06 19:07:44,809 INFO [trainer.py:765] (6/8) Epoch 21, batch 1800, train_loss[loss=2.96, NarTop10Accuracy=0.7417, over 7203.00 frames. ], tot_loss[loss=3.128, NarTop10Accuracy=0.7002, over 5963.12 frames. ], batch size: 22, lr: 4.06e-03
2024-08-06 19:08:11,369 INFO [trainer.py:765] (6/8) Epoch 21, batch 1900, train_loss[loss=3.653, NarTop10Accuracy=0.5929, over 5943.00 frames. ], tot_loss[loss=3.144, NarTop10Accuracy=0.6967, over 6013.34 frames. ], batch size: 50, lr: 4.06e-03
2024-08-06 19:08:37,105 INFO [trainer.py:765] (6/8) Epoch 21, batch 2000, train_loss[loss=3.507, NarTop10Accuracy=0.6178, over 6840.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.6983, over 6007.30 frames. ], batch size: 51, lr: 4.05e-03
2024-08-06 19:09:02,507 INFO [trainer.py:765] (6/8) Epoch 21, batch 2100, train_loss[loss=2.751, NarTop10Accuracy=0.7796, over 3954.00 frames. ], tot_loss[loss=3.146, NarTop10Accuracy=0.6958, over 5981.18 frames. ], batch size: 4, lr: 4.05e-03
2024-08-06 19:09:27,891 INFO [trainer.py:765] (6/8) Epoch 21, batch 2200, train_loss[loss=2.905, NarTop10Accuracy=0.7455, over 7308.00 frames. ], tot_loss[loss=3.15, NarTop10Accuracy=0.6953, over 6019.37 frames. ], batch size: 32, lr: 4.04e-03
2024-08-06 19:09:53,222 INFO [trainer.py:765] (6/8) Epoch 21, batch 2300, train_loss[loss=3.058, NarTop10Accuracy=0.7124, over 5850.00 frames. ], tot_loss[loss=3.162, NarTop10Accuracy=0.6927, over 6029.61 frames. ], batch size: 9, lr: 4.04e-03
2024-08-06 19:10:17,596 INFO [trainer.py:765] (6/8) Epoch 21, batch 2400, train_loss[loss=3.417, NarTop10Accuracy=0.633, over 5202.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6964, over 5785.28 frames. ], batch size: 7, lr: 4.04e-03
2024-08-06 19:10:37,229 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 19:10:45,275 INFO [trainer.py:811] (6/8) Epoch 21, validation: loss=2.971, NarTop10Accuracy=0.7316, over 1905321.00 frames. 
2024-08-06 19:10:45,276 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 19:10:45,741 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 21, batch 2500, train_loss[loss=3.137, NarTop10Accuracy=0.6875, over 5157.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7056, over 5495.05 frames. ], batch size: 7, lr: 4.03e-03
2024-08-06 19:11:08,869 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 19:12:09,054 INFO [trainer.py:765] (6/8) Epoch 22, batch 100, train_loss[loss=2.968, NarTop10Accuracy=0.7378, over 7536.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7105, over 2355.65 frames. ], batch size: 31, lr: 3.93e-03
2024-08-06 19:12:44,462 INFO [trainer.py:765] (6/8) Epoch 22, batch 200, train_loss[loss=3.106, NarTop10Accuracy=0.6982, over 6960.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7071, over 3859.39 frames. ], batch size: 17, lr: 3.93e-03
2024-08-06 19:13:14,533 INFO [trainer.py:765] (6/8) Epoch 22, batch 300, train_loss[loss=2.888, NarTop10Accuracy=0.7576, over 7092.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7082, over 4657.63 frames. ], batch size: 22, lr: 3.93e-03
2024-08-06 19:13:49,229 INFO [trainer.py:765] (6/8) Epoch 22, batch 400, train_loss[loss=3.085, NarTop10Accuracy=0.7161, over 5052.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7086, over 5117.11 frames. ], batch size: 7, lr: 3.92e-03
2024-08-06 19:14:24,850 INFO [trainer.py:765] (6/8) Epoch 22, batch 500, train_loss[loss=3.141, NarTop10Accuracy=0.6868, over 6048.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7077, over 5380.52 frames. ], batch size: 11, lr: 3.92e-03
2024-08-06 19:14:55,701 INFO [trainer.py:765] (6/8) Epoch 22, batch 600, train_loss[loss=3.003, NarTop10Accuracy=0.7324, over 5874.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.701, over 5660.87 frames. ], batch size: 9, lr: 3.92e-03
2024-08-06 19:15:30,867 INFO [trainer.py:765] (6/8) Epoch 22, batch 700, train_loss[loss=3.167, NarTop10Accuracy=0.6868, over 5178.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7023, over 5734.64 frames. ], batch size: 6, lr: 3.91e-03
2024-08-06 19:16:10,664 INFO [trainer.py:765] (6/8) Epoch 22, batch 800, train_loss[loss=3.021, NarTop10Accuracy=0.722, over 4983.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7029, over 5782.33 frames. ], batch size: 6, lr: 3.91e-03
2024-08-06 19:16:40,952 INFO [trainer.py:765] (6/8) Epoch 22, batch 900, train_loss[loss=2.9, NarTop10Accuracy=0.7431, over 6639.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7027, over 5796.63 frames. ], batch size: 14, lr: 3.90e-03
2024-08-06 19:17:16,433 INFO [trainer.py:765] (6/8) Epoch 22, batch 1000, train_loss[loss=3.164, NarTop10Accuracy=0.6866, over 6144.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7042, over 5913.07 frames. ], batch size: 13, lr: 3.90e-03
2024-08-06 19:17:52,085 INFO [trainer.py:765] (6/8) Epoch 22, batch 1100, train_loss[loss=2.944, NarTop10Accuracy=0.7363, over 6699.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7023, over 5934.53 frames. ], batch size: 17, lr: 3.90e-03
2024-08-06 19:18:25,927 INFO [trainer.py:765] (6/8) Epoch 22, batch 1200, train_loss[loss=2.967, NarTop10Accuracy=0.7328, over 7182.00 frames. ], tot_loss[loss=3.099, NarTop10Accuracy=0.7061, over 5918.99 frames. ], batch size: 32, lr: 3.89e-03
2024-08-06 19:19:01,253 INFO [trainer.py:765] (6/8) Epoch 22, batch 1300, train_loss[loss=2.799, NarTop10Accuracy=0.7619, over 4992.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7073, over 5970.94 frames. ], batch size: 6, lr: 3.89e-03
2024-08-06 19:19:33,317 INFO [trainer.py:765] (6/8) Epoch 22, batch 1400, train_loss[loss=2.789, NarTop10Accuracy=0.7728, over 6021.00 frames. ], tot_loss[loss=3.105, NarTop10Accuracy=0.7047, over 6006.22 frames. ], batch size: 11, lr: 3.89e-03
2024-08-06 19:20:03,830 INFO [trainer.py:765] (6/8) Epoch 22, batch 1500, train_loss[loss=3.475, NarTop10Accuracy=0.6293, over 6225.00 frames. ], tot_loss[loss=3.105, NarTop10Accuracy=0.7047, over 5933.93 frames. ], batch size: 50, lr: 3.88e-03
2024-08-06 19:20:31,647 INFO [trainer.py:765] (6/8) Epoch 22, batch 1600, train_loss[loss=3.112, NarTop10Accuracy=0.7034, over 7254.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7012, over 5921.12 frames. ], batch size: 23, lr: 3.88e-03
2024-08-06 19:20:58,418 INFO [trainer.py:765] (6/8) Epoch 22, batch 1700, train_loss[loss=3.171, NarTop10Accuracy=0.691, over 6609.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7006, over 5931.48 frames. ], batch size: 14, lr: 3.88e-03
2024-08-06 19:21:25,010 INFO [trainer.py:765] (6/8) Epoch 22, batch 1800, train_loss[loss=2.886, NarTop10Accuracy=0.7446, over 7221.00 frames. ], tot_loss[loss=3.119, NarTop10Accuracy=0.7022, over 5978.93 frames. ], batch size: 22, lr: 3.87e-03
2024-08-06 19:21:51,372 INFO [trainer.py:765] (6/8) Epoch 22, batch 1900, train_loss[loss=3.112, NarTop10Accuracy=0.7077, over 6126.00 frames. ], tot_loss[loss=3.142, NarTop10Accuracy=0.6976, over 6025.93 frames. ], batch size: 50, lr: 3.87e-03
2024-08-06 19:21:53,110 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 19:22:01,088 INFO [trainer.py:811] (6/8) Epoch 22, validation: loss=3.009, NarTop10Accuracy=0.7241, over 1905321.00 frames. 
2024-08-06 19:22:01,089 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 19:22:01,575 INFO [optim.py:386] (6/8) Clipping_scale=2.0, grad-norm quartiles 1.670e+02 2.114e+02 2.276e+02 2.445e+02 4.438e+02, threshold=4.551e+02, percent-clipped=0.0
2024-08-06 19:22:24,819 INFO [trainer.py:765] (6/8) Epoch 22, batch 2000, train_loss[loss=3.484, NarTop10Accuracy=0.628, over 6087.00 frames. ], tot_loss[loss=3.118, NarTop10Accuracy=0.7024, over 6005.83 frames. ], batch size: 50, lr: 3.87e-03
2024-08-06 19:22:50,041 INFO [trainer.py:765] (6/8) Epoch 22, batch 2100, train_loss[loss=3.193, NarTop10Accuracy=0.6837, over 3828.00 frames. ], tot_loss[loss=3.111, NarTop10Accuracy=0.7038, over 5976.59 frames. ], batch size: 4, lr: 3.86e-03
2024-08-06 19:23:15,230 INFO [trainer.py:765] (6/8) Epoch 22, batch 2200, train_loss[loss=3.036, NarTop10Accuracy=0.7217, over 7170.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7038, over 6010.03 frames. ], batch size: 31, lr: 3.86e-03
2024-08-06 19:23:40,315 INFO [trainer.py:765] (6/8) Epoch 22, batch 2300, train_loss[loss=3.006, NarTop10Accuracy=0.7291, over 5658.00 frames. ], tot_loss[loss=3.133, NarTop10Accuracy=0.699, over 6025.40 frames. ], batch size: 9, lr: 3.86e-03
2024-08-06 19:24:04,602 INFO [trainer.py:765] (6/8) Epoch 22, batch 2400, train_loss[loss=3.025, NarTop10Accuracy=0.7144, over 5094.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7015, over 5776.49 frames. ], batch size: 7, lr: 3.85e-03
2024-08-06 19:24:28,024 INFO [trainer.py:765] (6/8) Epoch 22, batch 2500, train_loss[loss=3.181, NarTop10Accuracy=0.6918, over 5025.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7055, over 5483.72 frames. ], batch size: 7, lr: 3.85e-03
2024-08-06 19:24:47,714 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 19:25:45,385 INFO [trainer.py:765] (6/8) Epoch 23, batch 100, train_loss[loss=3.065, NarTop10Accuracy=0.7105, over 7437.00 frames. ], tot_loss[loss=3.135, NarTop10Accuracy=0.6987, over 2376.10 frames. ], batch size: 32, lr: 3.76e-03
2024-08-06 19:26:21,309 INFO [trainer.py:765] (6/8) Epoch 23, batch 200, train_loss[loss=3.46, NarTop10Accuracy=0.6328, over 6660.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7002, over 3863.61 frames. ], batch size: 17, lr: 3.76e-03
2024-08-06 19:26:57,603 INFO [trainer.py:765] (6/8) Epoch 23, batch 300, train_loss[loss=3.011, NarTop10Accuracy=0.7241, over 7389.00 frames. ], tot_loss[loss=3.104, NarTop10Accuracy=0.705, over 4692.65 frames. ], batch size: 22, lr: 3.75e-03
2024-08-06 19:27:26,541 INFO [trainer.py:765] (6/8) Epoch 23, batch 400, train_loss[loss=3.321, NarTop10Accuracy=0.6573, over 5214.00 frames. ], tot_loss[loss=3.11, NarTop10Accuracy=0.7039, over 5128.74 frames. ], batch size: 7, lr: 3.75e-03
2024-08-06 19:27:59,713 INFO [trainer.py:765] (6/8) Epoch 23, batch 500, train_loss[loss=3.369, NarTop10Accuracy=0.6552, over 6099.00 frames. ], tot_loss[loss=3.119, NarTop10Accuracy=0.7017, over 5400.72 frames. ], batch size: 11, lr: 3.75e-03
2024-08-06 19:28:35,883 INFO [trainer.py:765] (6/8) Epoch 23, batch 600, train_loss[loss=3.283, NarTop10Accuracy=0.6672, over 5697.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7034, over 5652.32 frames. ], batch size: 9, lr: 3.74e-03
2024-08-06 19:29:11,367 INFO [trainer.py:765] (6/8) Epoch 23, batch 700, train_loss[loss=3.114, NarTop10Accuracy=0.699, over 5148.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7069, over 5738.03 frames. ], batch size: 6, lr: 3.74e-03
2024-08-06 19:29:43,613 INFO [trainer.py:765] (6/8) Epoch 23, batch 800, train_loss[loss=2.861, NarTop10Accuracy=0.7587, over 5043.00 frames. ], tot_loss[loss=3.104, NarTop10Accuracy=0.7054, over 5776.26 frames. ], batch size: 6, lr: 3.74e-03
2024-08-06 19:30:19,390 INFO [trainer.py:765] (6/8) Epoch 23, batch 900, train_loss[loss=3.361, NarTop10Accuracy=0.6574, over 6243.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7069, over 5781.48 frames. ], batch size: 13, lr: 3.73e-03
2024-08-06 19:30:58,195 INFO [trainer.py:765] (6/8) Epoch 23, batch 1000, train_loss[loss=3.058, NarTop10Accuracy=0.7115, over 6228.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7088, over 5899.85 frames. ], batch size: 13, lr: 3.73e-03
2024-08-06 19:31:31,521 INFO [trainer.py:765] (6/8) Epoch 23, batch 1100, train_loss[loss=3.078, NarTop10Accuracy=0.7176, over 6900.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7065, over 5916.46 frames. ], batch size: 17, lr: 3.73e-03
2024-08-06 19:32:08,518 INFO [trainer.py:765] (6/8) Epoch 23, batch 1200, train_loss[loss=3.037, NarTop10Accuracy=0.7267, over 7197.00 frames. ], tot_loss[loss=3.105, NarTop10Accuracy=0.7049, over 5902.05 frames. ], batch size: 31, lr: 3.72e-03
2024-08-06 19:32:46,937 INFO [trainer.py:765] (6/8) Epoch 23, batch 1300, train_loss[loss=3.121, NarTop10Accuracy=0.7074, over 4344.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7039, over 5975.22 frames. ], batch size: 5, lr: 3.72e-03
2024-08-06 19:32:56,402 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 19:33:04,722 INFO [trainer.py:811] (6/8) Epoch 23, validation: loss=2.893, NarTop10Accuracy=0.7468, over 1905321.00 frames. 
2024-08-06 19:33:04,723 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 19:33:05,262 INFO [optim.py:386] (6/8) Clipping_scale=2.0, grad-norm quartiles 1.759e+02 2.108e+02 2.273e+02 2.457e+02 3.966e+02, threshold=4.546e+02, percent-clipped=0.0
2024-08-06 19:33:27,407 INFO [trainer.py:765] (6/8) Epoch 23, batch 1400, train_loss[loss=2.867, NarTop10Accuracy=0.7441, over 6027.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7038, over 6000.25 frames. ], batch size: 11, lr: 3.72e-03
2024-08-06 19:33:58,215 INFO [trainer.py:765] (6/8) Epoch 23, batch 1500, train_loss[loss=3.299, NarTop10Accuracy=0.6714, over 5784.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7066, over 5941.64 frames. ], batch size: 50, lr: 3.71e-03
2024-08-06 19:34:26,015 INFO [trainer.py:765] (6/8) Epoch 23, batch 1600, train_loss[loss=2.945, NarTop10Accuracy=0.7356, over 7281.00 frames. ], tot_loss[loss=3.104, NarTop10Accuracy=0.7051, over 5925.40 frames. ], batch size: 23, lr: 3.71e-03
2024-08-06 19:34:52,783 INFO [trainer.py:765] (6/8) Epoch 23, batch 1700, train_loss[loss=3.352, NarTop10Accuracy=0.6497, over 6612.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7005, over 5910.92 frames. ], batch size: 14, lr: 3.71e-03
2024-08-06 19:35:19,261 INFO [trainer.py:765] (6/8) Epoch 23, batch 1800, train_loss[loss=2.932, NarTop10Accuracy=0.7414, over 6924.00 frames. ], tot_loss[loss=3.117, NarTop10Accuracy=0.7019, over 5973.38 frames. ], batch size: 22, lr: 3.70e-03
2024-08-06 19:35:45,596 INFO [trainer.py:765] (6/8) Epoch 23, batch 1900, train_loss[loss=3.478, NarTop10Accuracy=0.6306, over 6060.00 frames. ], tot_loss[loss=3.124, NarTop10Accuracy=0.7008, over 6025.66 frames. ], batch size: 50, lr: 3.70e-03
2024-08-06 19:36:11,170 INFO [trainer.py:765] (6/8) Epoch 23, batch 2000, train_loss[loss=3.532, NarTop10Accuracy=0.6103, over 5874.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7028, over 6007.95 frames. ], batch size: 50, lr: 3.70e-03
2024-08-06 19:36:36,517 INFO [trainer.py:765] (6/8) Epoch 23, batch 2100, train_loss[loss=3.432, NarTop10Accuracy=0.6384, over 4764.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7027, over 5995.10 frames. ], batch size: 5, lr: 3.69e-03
2024-08-06 19:37:01,908 INFO [trainer.py:765] (6/8) Epoch 23, batch 2200, train_loss[loss=3.184, NarTop10Accuracy=0.6913, over 7350.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7009, over 6026.16 frames. ], batch size: 32, lr: 3.69e-03
2024-08-06 19:37:27,060 INFO [trainer.py:765] (6/8) Epoch 23, batch 2300, train_loss[loss=2.945, NarTop10Accuracy=0.7374, over 5514.00 frames. ], tot_loss[loss=3.119, NarTop10Accuracy=0.7019, over 6035.08 frames. ], batch size: 9, lr: 3.69e-03
2024-08-06 19:37:51,423 INFO [trainer.py:765] (6/8) Epoch 23, batch 2400, train_loss[loss=2.996, NarTop10Accuracy=0.7247, over 5073.00 frames. ], tot_loss[loss=3.114, NarTop10Accuracy=0.7022, over 5784.28 frames. ], batch size: 7, lr: 3.69e-03
2024-08-06 19:38:15,052 INFO [trainer.py:765] (6/8) Epoch 23, batch 2500, train_loss[loss=3.309, NarTop10Accuracy=0.657, over 5085.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7064, over 5480.23 frames. ], batch size: 7, lr: 3.68e-03
2024-08-06 19:38:34,908 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 19:39:37,631 INFO [trainer.py:765] (6/8) Epoch 24, batch 100, train_loss[loss=3.55, NarTop10Accuracy=0.6207, over 7167.00 frames. ], tot_loss[loss=3.125, NarTop10Accuracy=0.7002, over 2344.29 frames. ], batch size: 31, lr: 3.60e-03
2024-08-06 19:40:10,189 INFO [trainer.py:765] (6/8) Epoch 24, batch 200, train_loss[loss=2.893, NarTop10Accuracy=0.7558, over 6852.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7063, over 3839.35 frames. ], batch size: 17, lr: 3.60e-03
2024-08-06 19:40:40,555 INFO [trainer.py:765] (6/8) Epoch 24, batch 300, train_loss[loss=2.824, NarTop10Accuracy=0.7598, over 6777.00 frames. ], tot_loss[loss=3.103, NarTop10Accuracy=0.7051, over 4639.04 frames. ], batch size: 22, lr: 3.59e-03
2024-08-06 19:41:18,233 INFO [trainer.py:765] (6/8) Epoch 24, batch 400, train_loss[loss=3.009, NarTop10Accuracy=0.7219, over 5181.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7063, over 5077.06 frames. ], batch size: 7, lr: 3.59e-03
2024-08-06 19:41:50,322 INFO [trainer.py:765] (6/8) Epoch 24, batch 500, train_loss[loss=2.911, NarTop10Accuracy=0.7343, over 6105.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.708, over 5369.99 frames. ], batch size: 11, lr: 3.59e-03
2024-08-06 19:42:21,451 INFO [trainer.py:765] (6/8) Epoch 24, batch 600, train_loss[loss=2.81, NarTop10Accuracy=0.7749, over 5664.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7073, over 5633.81 frames. ], batch size: 9, lr: 3.58e-03
2024-08-06 19:42:52,843 INFO [trainer.py:765] (6/8) Epoch 24, batch 700, train_loss[loss=2.848, NarTop10Accuracy=0.7608, over 5109.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7068, over 5708.99 frames. ], batch size: 6, lr: 3.58e-03
2024-08-06 19:43:17,380 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 19:43:25,410 INFO [trainer.py:811] (6/8) Epoch 24, validation: loss=3.021, NarTop10Accuracy=0.7204, over 1905321.00 frames. 
2024-08-06 19:43:25,411 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 19:43:28,562 INFO [optim.py:386] (6/8) 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 19:43:40,813 INFO [trainer.py:765] (6/8) Epoch 24, batch 800, train_loss[loss=2.784, NarTop10Accuracy=0.7652, over 5073.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7077, over 5782.14 frames. ], batch size: 6, lr: 3.58e-03
2024-08-06 19:44:11,409 INFO [trainer.py:765] (6/8) Epoch 24, batch 900, train_loss[loss=2.901, NarTop10Accuracy=0.7487, over 6201.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7101, over 5800.73 frames. ], batch size: 13, lr: 3.57e-03
2024-08-06 19:44:47,488 INFO [trainer.py:765] (6/8) Epoch 24, batch 1000, train_loss[loss=3.231, NarTop10Accuracy=0.6835, over 6654.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7076, over 5902.13 frames. ], batch size: 14, lr: 3.57e-03
2024-08-06 19:45:27,106 INFO [trainer.py:765] (6/8) Epoch 24, batch 1100, train_loss[loss=3.5, NarTop10Accuracy=0.6178, over 6636.00 frames. ], tot_loss[loss=3.105, NarTop10Accuracy=0.7047, over 5929.10 frames. ], batch size: 17, lr: 3.57e-03
2024-08-06 19:45:58,436 INFO [trainer.py:765] (6/8) Epoch 24, batch 1200, train_loss[loss=3.144, NarTop10Accuracy=0.6946, over 7164.00 frames. ], tot_loss[loss=3.102, NarTop10Accuracy=0.7051, over 5928.26 frames. ], batch size: 31, lr: 3.57e-03
2024-08-06 19:46:30,293 INFO [trainer.py:765] (6/8) Epoch 24, batch 1300, train_loss[loss=3.383, NarTop10Accuracy=0.6455, over 5232.00 frames. ], tot_loss[loss=3.098, NarTop10Accuracy=0.7059, over 6000.25 frames. ], batch size: 6, lr: 3.56e-03
2024-08-06 19:47:07,858 INFO [trainer.py:765] (6/8) Epoch 24, batch 1400, train_loss[loss=3.303, NarTop10Accuracy=0.6679, over 5907.00 frames. ], tot_loss[loss=3.109, NarTop10Accuracy=0.7034, over 6015.10 frames. ], batch size: 11, lr: 3.56e-03
2024-08-06 19:47:40,956 INFO [trainer.py:765] (6/8) Epoch 24, batch 1500, train_loss[loss=3.435, NarTop10Accuracy=0.6376, over 6624.00 frames. ], tot_loss[loss=3.122, NarTop10Accuracy=0.7008, over 5954.94 frames. ], batch size: 50, lr: 3.56e-03
2024-08-06 19:48:08,675 INFO [trainer.py:765] (6/8) Epoch 24, batch 1600, train_loss[loss=3.345, NarTop10Accuracy=0.6473, over 7020.00 frames. ], tot_loss[loss=3.123, NarTop10Accuracy=0.7008, over 5937.17 frames. ], batch size: 22, lr: 3.55e-03
2024-08-06 19:48:35,266 INFO [trainer.py:765] (6/8) Epoch 24, batch 1700, train_loss[loss=2.919, NarTop10Accuracy=0.746, over 6276.00 frames. ], tot_loss[loss=3.126, NarTop10Accuracy=0.7002, over 5911.97 frames. ], batch size: 13, lr: 3.55e-03
2024-08-06 19:49:01,636 INFO [trainer.py:765] (6/8) Epoch 24, batch 1800, train_loss[loss=2.996, NarTop10Accuracy=0.726, over 7215.00 frames. ], tot_loss[loss=3.133, NarTop10Accuracy=0.6984, over 5981.81 frames. ], batch size: 22, lr: 3.55e-03
2024-08-06 19:49:28,041 INFO [trainer.py:765] (6/8) Epoch 24, batch 1900, train_loss[loss=3.566, NarTop10Accuracy=0.6087, over 5841.00 frames. ], tot_loss[loss=3.145, NarTop10Accuracy=0.6964, over 6030.17 frames. ], batch size: 50, lr: 3.55e-03
2024-08-06 19:49:53,533 INFO [trainer.py:765] (6/8) Epoch 24, batch 2000, train_loss[loss=3.572, NarTop10Accuracy=0.6081, over 6033.00 frames. ], tot_loss[loss=3.12, NarTop10Accuracy=0.7016, over 5999.19 frames. ], batch size: 50, lr: 3.54e-03
2024-08-06 19:50:18,819 INFO [trainer.py:765] (6/8) Epoch 24, batch 2100, train_loss[loss=2.86, NarTop10Accuracy=0.7567, over 4911.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.7023, over 5985.78 frames. ], batch size: 5, lr: 3.54e-03
2024-08-06 19:50:43,942 INFO [trainer.py:765] (6/8) Epoch 24, batch 2200, train_loss[loss=3.435, NarTop10Accuracy=0.6321, over 7095.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7029, over 6015.62 frames. ], batch size: 31, lr: 3.54e-03
2024-08-06 19:51:09,024 INFO [trainer.py:765] (6/8) Epoch 24, batch 2300, train_loss[loss=2.936, NarTop10Accuracy=0.7392, over 5805.00 frames. ], tot_loss[loss=3.112, NarTop10Accuracy=0.7032, over 6026.72 frames. ], batch size: 9, lr: 3.53e-03
2024-08-06 19:51:33,349 INFO [trainer.py:765] (6/8) Epoch 24, batch 2400, train_loss[loss=2.918, NarTop10Accuracy=0.7286, over 5094.00 frames. ], tot_loss[loss=3.099, NarTop10Accuracy=0.7058, over 5774.79 frames. ], batch size: 7, lr: 3.53e-03
2024-08-06 19:51:56,782 INFO [trainer.py:765] (6/8) Epoch 24, batch 2500, train_loss[loss=2.932, NarTop10Accuracy=0.745, over 5250.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7099, over 5457.17 frames. ], batch size: 7, lr: 3.53e-03
2024-08-06 19:52:17,335 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 19:53:22,197 INFO [trainer.py:765] (6/8) Epoch 25, batch 100, train_loss[loss=3.369, NarTop10Accuracy=0.6484, over 7113.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7093, over 2372.88 frames. ], batch size: 31, lr: 3.45e-03
2024-08-06 19:53:47,262 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 19:53:55,329 INFO [trainer.py:811] (6/8) Epoch 25, validation: loss=2.96, NarTop10Accuracy=0.7332, over 1905321.00 frames. 
2024-08-06 19:53:55,329 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 19:53:55,916 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 25, batch 200, train_loss[loss=2.785, NarTop10Accuracy=0.7664, over 6879.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7083, over 3848.76 frames. ], batch size: 17, lr: 3.45e-03
2024-08-06 19:54:35,647 INFO [trainer.py:765] (6/8) Epoch 25, batch 300, train_loss[loss=3.232, NarTop10Accuracy=0.6806, over 7137.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7093, over 4650.33 frames. ], batch size: 22, lr: 3.45e-03
2024-08-06 19:55:12,958 INFO [trainer.py:765] (6/8) Epoch 25, batch 400, train_loss[loss=2.932, NarTop10Accuracy=0.7453, over 5034.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7081, over 5123.77 frames. ], batch size: 7, lr: 3.44e-03
2024-08-06 19:55:43,738 INFO [trainer.py:765] (6/8) Epoch 25, batch 500, train_loss[loss=2.844, NarTop10Accuracy=0.7591, over 6096.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7092, over 5399.63 frames. ], batch size: 11, lr: 3.44e-03
2024-08-06 19:56:14,814 INFO [trainer.py:765] (6/8) Epoch 25, batch 600, train_loss[loss=2.943, NarTop10Accuracy=0.7421, over 5739.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7081, over 5667.96 frames. ], batch size: 9, lr: 3.44e-03
2024-08-06 19:56:55,496 INFO [trainer.py:765] (6/8) Epoch 25, batch 700, train_loss[loss=2.753, NarTop10Accuracy=0.7794, over 5085.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7095, over 5743.59 frames. ], batch size: 6, lr: 3.43e-03
2024-08-06 19:57:30,136 INFO [trainer.py:765] (6/8) Epoch 25, batch 800, train_loss[loss=3.017, NarTop10Accuracy=0.7275, over 4983.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7083, over 5793.21 frames. ], batch size: 6, lr: 3.43e-03
2024-08-06 19:58:00,679 INFO [trainer.py:765] (6/8) Epoch 25, batch 900, train_loss[loss=3.096, NarTop10Accuracy=0.7174, over 6174.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.711, over 5814.12 frames. ], batch size: 13, lr: 3.43e-03
2024-08-06 19:58:37,640 INFO [trainer.py:765] (6/8) Epoch 25, batch 1000, train_loss[loss=2.793, NarTop10Accuracy=0.7697, over 6408.00 frames. ], tot_loss[loss=3.093, NarTop10Accuracy=0.7074, over 5915.86 frames. ], batch size: 14, lr: 3.43e-03
2024-08-06 19:59:14,855 INFO [trainer.py:765] (6/8) Epoch 25, batch 1100, train_loss[loss=3.379, NarTop10Accuracy=0.642, over 6906.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.7061, over 5955.72 frames. ], batch size: 17, lr: 3.42e-03
2024-08-06 19:59:49,039 INFO [trainer.py:765] (6/8) Epoch 25, batch 1200, train_loss[loss=3.483, NarTop10Accuracy=0.6283, over 7362.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7067, over 5943.48 frames. ], batch size: 32, lr: 3.42e-03
2024-08-06 20:00:25,598 INFO [trainer.py:765] (6/8) Epoch 25, batch 1300, train_loss[loss=2.817, NarTop10Accuracy=0.7559, over 4995.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7088, over 6010.06 frames. ], batch size: 6, lr: 3.42e-03
2024-08-06 20:01:02,016 INFO [trainer.py:765] (6/8) Epoch 25, batch 1400, train_loss[loss=3.004, NarTop10Accuracy=0.727, over 6189.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7089, over 6035.26 frames. ], batch size: 11, lr: 3.42e-03
2024-08-06 20:01:32,823 INFO [trainer.py:765] (6/8) Epoch 25, batch 1500, train_loss[loss=3.267, NarTop10Accuracy=0.6664, over 6207.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7074, over 5977.65 frames. ], batch size: 50, lr: 3.41e-03
2024-08-06 20:02:00,625 INFO [trainer.py:765] (6/8) Epoch 25, batch 1600, train_loss[loss=2.911, NarTop10Accuracy=0.7489, over 7026.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7081, over 5934.27 frames. ], batch size: 22, lr: 3.41e-03
2024-08-06 20:02:27,360 INFO [trainer.py:765] (6/8) Epoch 25, batch 1700, train_loss[loss=3.105, NarTop10Accuracy=0.7037, over 6525.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.709, over 5912.70 frames. ], batch size: 14, lr: 3.41e-03
2024-08-06 20:02:53,854 INFO [trainer.py:765] (6/8) Epoch 25, batch 1800, train_loss[loss=3.302, NarTop10Accuracy=0.6596, over 6927.00 frames. ], tot_loss[loss=3.1, NarTop10Accuracy=0.705, over 5986.47 frames. ], batch size: 22, lr: 3.40e-03
2024-08-06 20:03:20,340 INFO [trainer.py:765] (6/8) Epoch 25, batch 1900, train_loss[loss=3.309, NarTop10Accuracy=0.6691, over 6057.00 frames. ], tot_loss[loss=3.116, NarTop10Accuracy=0.702, over 6024.94 frames. ], batch size: 51, lr: 3.40e-03
2024-08-06 20:03:45,935 INFO [trainer.py:765] (6/8) Epoch 25, batch 2000, train_loss[loss=3.571, NarTop10Accuracy=0.6123, over 5847.00 frames. ], tot_loss[loss=3.123, NarTop10Accuracy=0.7006, over 5996.92 frames. ], batch size: 53, lr: 3.40e-03
2024-08-06 20:04:11,245 INFO [trainer.py:765] (6/8) Epoch 25, batch 2100, train_loss[loss=2.719, NarTop10Accuracy=0.7859, over 4800.00 frames. ], tot_loss[loss=3.108, NarTop10Accuracy=0.7041, over 5969.48 frames. ], batch size: 5, lr: 3.40e-03
2024-08-06 20:04:31,409 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 20:04:39,343 INFO [trainer.py:811] (6/8) Epoch 25, validation: loss=2.999, NarTop10Accuracy=0.7251, over 1905321.00 frames. 
2024-08-06 20:04:39,344 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 20:04:39,840 INFO [optim.py:386] (6/8) 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 20:04:44,513 INFO [trainer.py:765] (6/8) Epoch 25, batch 2200, train_loss[loss=3.283, NarTop10Accuracy=0.6682, over 7047.00 frames. ], tot_loss[loss=3.115, NarTop10Accuracy=0.7028, over 6000.93 frames. ], batch size: 31, lr: 3.39e-03
2024-08-06 20:05:09,645 INFO [trainer.py:765] (6/8) Epoch 25, batch 2300, train_loss[loss=3.074, NarTop10Accuracy=0.7043, over 5775.00 frames. ], tot_loss[loss=3.113, NarTop10Accuracy=0.7031, over 6016.67 frames. ], batch size: 9, lr: 3.39e-03
2024-08-06 20:05:34,141 INFO [trainer.py:765] (6/8) Epoch 25, batch 2400, train_loss[loss=2.857, NarTop10Accuracy=0.7551, over 5184.00 frames. ], tot_loss[loss=3.104, NarTop10Accuracy=0.7048, over 5797.11 frames. ], batch size: 7, lr: 3.39e-03
2024-08-06 20:05:57,846 INFO [trainer.py:765] (6/8) Epoch 25, batch 2500, train_loss[loss=2.834, NarTop10Accuracy=0.7526, over 5598.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7111, over 5482.68 frames. ], batch size: 8, lr: 3.39e-03
2024-08-06 20:06:17,612 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 20:07:19,305 INFO [trainer.py:765] (6/8) Epoch 26, batch 100, train_loss[loss=3.051, NarTop10Accuracy=0.716, over 7404.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7097, over 2364.35 frames. ], batch size: 32, lr: 3.32e-03
2024-08-06 20:07:52,383 INFO [trainer.py:765] (6/8) Epoch 26, batch 200, train_loss[loss=2.884, NarTop10Accuracy=0.7564, over 6735.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7073, over 3860.68 frames. ], batch size: 17, lr: 3.31e-03
2024-08-06 20:08:24,734 INFO [trainer.py:765] (6/8) Epoch 26, batch 300, train_loss[loss=3.004, NarTop10Accuracy=0.7263, over 7062.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7077, over 4640.59 frames. ], batch size: 22, lr: 3.31e-03
2024-08-06 20:08:58,184 INFO [trainer.py:765] (6/8) Epoch 26, batch 400, train_loss[loss=2.803, NarTop10Accuracy=0.7551, over 5052.00 frames. ], tot_loss[loss=3.086, NarTop10Accuracy=0.7083, over 5071.95 frames. ], batch size: 7, lr: 3.31e-03
2024-08-06 20:09:33,147 INFO [trainer.py:765] (6/8) Epoch 26, batch 500, train_loss[loss=2.781, NarTop10Accuracy=0.7788, over 6111.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7062, over 5360.39 frames. ], batch size: 11, lr: 3.30e-03
2024-08-06 20:10:03,891 INFO [trainer.py:765] (6/8) Epoch 26, batch 600, train_loss[loss=2.692, NarTop10Accuracy=0.7857, over 5709.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7122, over 5634.89 frames. ], batch size: 9, lr: 3.30e-03
2024-08-06 20:10:39,872 INFO [trainer.py:765] (6/8) Epoch 26, batch 700, train_loss[loss=3.177, NarTop10Accuracy=0.6877, over 4305.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7088, over 5717.02 frames. ], batch size: 5, lr: 3.30e-03
2024-08-06 20:11:19,061 INFO [trainer.py:765] (6/8) Epoch 26, batch 800, train_loss[loss=3.086, NarTop10Accuracy=0.7135, over 5043.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7091, over 5768.77 frames. ], batch size: 6, lr: 3.30e-03
2024-08-06 20:11:49,315 INFO [trainer.py:765] (6/8) Epoch 26, batch 900, train_loss[loss=2.804, NarTop10Accuracy=0.7743, over 6657.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7097, over 5783.55 frames. ], batch size: 14, lr: 3.29e-03
2024-08-06 20:12:25,973 INFO [trainer.py:765] (6/8) Epoch 26, batch 1000, train_loss[loss=2.812, NarTop10Accuracy=0.7606, over 6588.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7079, over 5884.72 frames. ], batch size: 14, lr: 3.29e-03
2024-08-06 20:13:06,377 INFO [trainer.py:765] (6/8) Epoch 26, batch 1100, train_loss[loss=3.404, NarTop10Accuracy=0.6386, over 6837.00 frames. ], tot_loss[loss=3.095, NarTop10Accuracy=0.7063, over 5911.62 frames. ], batch size: 17, lr: 3.29e-03
2024-08-06 20:13:37,536 INFO [trainer.py:765] (6/8) Epoch 26, batch 1200, train_loss[loss=3.292, NarTop10Accuracy=0.6631, over 7479.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7087, over 5910.80 frames. ], batch size: 32, lr: 3.29e-03
2024-08-06 20:14:13,696 INFO [trainer.py:765] (6/8) Epoch 26, batch 1300, train_loss[loss=2.793, NarTop10Accuracy=0.7707, over 4239.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7092, over 5984.59 frames. ], batch size: 5, lr: 3.28e-03
2024-08-06 20:14:50,538 INFO [trainer.py:765] (6/8) Epoch 26, batch 1400, train_loss[loss=2.882, NarTop10Accuracy=0.7489, over 6081.00 frames. ], tot_loss[loss=3.087, NarTop10Accuracy=0.7081, over 5992.57 frames. ], batch size: 11, lr: 3.28e-03
2024-08-06 20:15:21,155 INFO [trainer.py:765] (6/8) Epoch 26, batch 1500, train_loss[loss=3.127, NarTop10Accuracy=0.6934, over 5805.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7077, over 5934.99 frames. ], batch size: 51, lr: 3.28e-03
2024-08-06 20:15:48,980 INFO [trainer.py:765] (6/8) Epoch 26, batch 1600, train_loss[loss=2.89, NarTop10Accuracy=0.7496, over 6867.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.71, over 5938.37 frames. ], batch size: 22, lr: 3.28e-03
2024-08-06 20:15:50,002 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 20:15:58,239 INFO [trainer.py:811] (6/8) Epoch 26, validation: loss=2.899, NarTop10Accuracy=0.7457, over 1905321.00 frames. 
2024-08-06 20:15:58,240 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 20:15:58,779 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 26, batch 1700, train_loss[loss=3.046, NarTop10Accuracy=0.7041, over 6783.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7133, over 5920.58 frames. ], batch size: 14, lr: 3.28e-03
2024-08-06 20:16:50,427 INFO [trainer.py:765] (6/8) Epoch 26, batch 1800, train_loss[loss=2.898, NarTop10Accuracy=0.756, over 7173.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7116, over 5966.40 frames. ], batch size: 22, lr: 3.27e-03
2024-08-06 20:17:16,841 INFO [trainer.py:765] (6/8) Epoch 26, batch 1900, train_loss[loss=3.086, NarTop10Accuracy=0.7175, over 6243.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7092, over 6011.74 frames. ], batch size: 50, lr: 3.27e-03
2024-08-06 20:17:42,380 INFO [trainer.py:765] (6/8) Epoch 26, batch 2000, train_loss[loss=3.616, NarTop10Accuracy=0.6001, over 6021.00 frames. ], tot_loss[loss=3.089, NarTop10Accuracy=0.7083, over 6015.95 frames. ], batch size: 50, lr: 3.27e-03
2024-08-06 20:18:07,563 INFO [trainer.py:765] (6/8) Epoch 26, batch 2100, train_loss[loss=3.133, NarTop10Accuracy=0.6959, over 3909.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7078, over 5995.91 frames. ], batch size: 4, lr: 3.27e-03
2024-08-06 20:18:32,777 INFO [trainer.py:765] (6/8) Epoch 26, batch 2200, train_loss[loss=2.812, NarTop10Accuracy=0.7604, over 7332.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7082, over 6030.98 frames. ], batch size: 31, lr: 3.26e-03
2024-08-06 20:18:57,898 INFO [trainer.py:765] (6/8) Epoch 26, batch 2300, train_loss[loss=3.19, NarTop10Accuracy=0.689, over 5658.00 frames. ], tot_loss[loss=3.096, NarTop10Accuracy=0.7067, over 6032.28 frames. ], batch size: 9, lr: 3.26e-03
2024-08-06 20:19:22,206 INFO [trainer.py:765] (6/8) Epoch 26, batch 2400, train_loss[loss=2.817, NarTop10Accuracy=0.7637, over 5286.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7113, over 5777.91 frames. ], batch size: 7, lr: 3.26e-03
2024-08-06 20:19:45,652 INFO [trainer.py:765] (6/8) Epoch 26, batch 2500, train_loss[loss=2.796, NarTop10Accuracy=0.7803, over 5115.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.716, over 5484.08 frames. ], batch size: 7, lr: 3.26e-03
2024-08-06 20:20:05,933 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 20:21:04,873 INFO [trainer.py:765] (6/8) Epoch 27, batch 100, train_loss[loss=3.22, NarTop10Accuracy=0.6802, over 7233.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7129, over 2378.52 frames. ], batch size: 31, lr: 3.19e-03
2024-08-06 20:21:39,783 INFO [trainer.py:765] (6/8) Epoch 27, batch 200, train_loss[loss=2.719, NarTop10Accuracy=0.7848, over 6813.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.7094, over 3866.55 frames. ], batch size: 17, lr: 3.19e-03
2024-08-06 20:22:13,049 INFO [trainer.py:765] (6/8) Epoch 27, batch 300, train_loss[loss=2.746, NarTop10Accuracy=0.7672, over 7131.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7107, over 4659.53 frames. ], batch size: 22, lr: 3.18e-03
2024-08-06 20:22:43,557 INFO [trainer.py:765] (6/8) Epoch 27, batch 400, train_loss[loss=2.875, NarTop10Accuracy=0.7551, over 5103.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.712, over 5106.96 frames. ], batch size: 7, lr: 3.18e-03
2024-08-06 20:23:18,083 INFO [trainer.py:765] (6/8) Epoch 27, batch 500, train_loss[loss=2.779, NarTop10Accuracy=0.7763, over 6078.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7147, over 5369.74 frames. ], batch size: 11, lr: 3.18e-03
2024-08-06 20:23:51,435 INFO [trainer.py:765] (6/8) Epoch 27, batch 600, train_loss[loss=3.266, NarTop10Accuracy=0.6664, over 5766.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7149, over 5642.91 frames. ], batch size: 9, lr: 3.18e-03
2024-08-06 20:24:24,975 INFO [trainer.py:765] (6/8) Epoch 27, batch 700, train_loss[loss=2.874, NarTop10Accuracy=0.7603, over 4242.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7153, over 5724.40 frames. ], batch size: 5, lr: 3.18e-03
2024-08-06 20:25:03,407 INFO [trainer.py:765] (6/8) Epoch 27, batch 800, train_loss[loss=3.209, NarTop10Accuracy=0.6722, over 4224.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7111, over 5785.22 frames. ], batch size: 5, lr: 3.17e-03
2024-08-06 20:25:34,176 INFO [trainer.py:765] (6/8) Epoch 27, batch 900, train_loss[loss=3.334, NarTop10Accuracy=0.6517, over 6210.00 frames. ], tot_loss[loss=3.07, NarTop10Accuracy=0.7112, over 5804.61 frames. ], batch size: 13, lr: 3.17e-03
2024-08-06 20:26:10,097 INFO [trainer.py:765] (6/8) Epoch 27, batch 1000, train_loss[loss=2.825, NarTop10Accuracy=0.7656, over 6327.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7109, over 5901.53 frames. ], batch size: 13, lr: 3.17e-03
2024-08-06 20:26:18,314 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 20:26:26,346 INFO [trainer.py:811] (6/8) Epoch 27, validation: loss=2.95, NarTop10Accuracy=0.735, over 1905321.00 frames. 
2024-08-06 20:26:26,347 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 20:26:26,877 INFO [optim.py:386] (6/8) 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 20:26:50,900 INFO [trainer.py:765] (6/8) Epoch 27, batch 1100, train_loss[loss=2.994, NarTop10Accuracy=0.7358, over 6735.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7098, over 5933.57 frames. ], batch size: 17, lr: 3.17e-03
2024-08-06 20:27:24,545 INFO [trainer.py:765] (6/8) Epoch 27, batch 1200, train_loss[loss=2.765, NarTop10Accuracy=0.7743, over 7473.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7119, over 5930.91 frames. ], batch size: 32, lr: 3.16e-03
2024-08-06 20:27:58,568 INFO [trainer.py:765] (6/8) Epoch 27, batch 1300, train_loss[loss=2.79, NarTop10Accuracy=0.766, over 5004.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7138, over 5994.60 frames. ], batch size: 6, lr: 3.16e-03
2024-08-06 20:28:36,745 INFO [trainer.py:765] (6/8) Epoch 27, batch 1400, train_loss[loss=3.423, NarTop10Accuracy=0.6415, over 6129.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7086, over 5996.43 frames. ], batch size: 11, lr: 3.16e-03
2024-08-06 20:29:04,632 INFO [trainer.py:765] (6/8) Epoch 27, batch 1500, train_loss[loss=3.047, NarTop10Accuracy=0.7164, over 5667.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7101, over 5945.94 frames. ], batch size: 50, lr: 3.16e-03
2024-08-06 20:29:32,362 INFO [trainer.py:765] (6/8) Epoch 27, batch 1600, train_loss[loss=2.971, NarTop10Accuracy=0.7322, over 7017.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7074, over 5933.65 frames. ], batch size: 22, lr: 3.15e-03
2024-08-06 20:29:58,978 INFO [trainer.py:765] (6/8) Epoch 27, batch 1700, train_loss[loss=3.094, NarTop10Accuracy=0.6934, over 6075.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7091, over 5914.62 frames. ], batch size: 13, lr: 3.15e-03
2024-08-06 20:30:25,463 INFO [trainer.py:765] (6/8) Epoch 27, batch 1800, train_loss[loss=3.393, NarTop10Accuracy=0.6504, over 7206.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.709, over 5981.79 frames. ], batch size: 22, lr: 3.15e-03
2024-08-06 20:30:51,845 INFO [trainer.py:765] (6/8) Epoch 27, batch 1900, train_loss[loss=3.132, NarTop10Accuracy=0.7057, over 5817.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7103, over 6025.29 frames. ], batch size: 51, lr: 3.15e-03
2024-08-06 20:31:17,390 INFO [trainer.py:765] (6/8) Epoch 27, batch 2000, train_loss[loss=3.117, NarTop10Accuracy=0.7012, over 5589.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7131, over 5977.33 frames. ], batch size: 50, lr: 3.15e-03
2024-08-06 20:31:42,659 INFO [trainer.py:765] (6/8) Epoch 27, batch 2100, train_loss[loss=2.719, NarTop10Accuracy=0.7765, over 4059.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7116, over 5972.37 frames. ], batch size: 4, lr: 3.14e-03
2024-08-06 20:32:07,804 INFO [trainer.py:765] (6/8) Epoch 27, batch 2200, train_loss[loss=3.508, NarTop10Accuracy=0.6236, over 6978.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7085, over 6013.50 frames. ], batch size: 31, lr: 3.14e-03
2024-08-06 20:32:32,942 INFO [trainer.py:765] (6/8) Epoch 27, batch 2300, train_loss[loss=2.951, NarTop10Accuracy=0.7349, over 5745.00 frames. ], tot_loss[loss=3.088, NarTop10Accuracy=0.7084, over 6040.84 frames. ], batch size: 9, lr: 3.14e-03
2024-08-06 20:32:57,246 INFO [trainer.py:765] (6/8) Epoch 27, batch 2400, train_loss[loss=2.711, NarTop10Accuracy=0.7901, over 5274.00 frames. ], tot_loss[loss=3.092, NarTop10Accuracy=0.7072, over 5785.21 frames. ], batch size: 7, lr: 3.14e-03
2024-08-06 20:33:20,615 INFO [trainer.py:765] (6/8) Epoch 27, batch 2500, train_loss[loss=3.436, NarTop10Accuracy=0.6325, over 5118.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7131, over 5478.75 frames. ], batch size: 7, lr: 3.13e-03
2024-08-06 20:33:40,788 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 20:34:35,827 INFO [trainer.py:765] (6/8) Epoch 28, batch 100, train_loss[loss=2.826, NarTop10Accuracy=0.7565, over 7236.00 frames. ], tot_loss[loss=3.085, NarTop10Accuracy=0.7079, over 2366.88 frames. ], batch size: 31, lr: 3.07e-03
2024-08-06 20:35:07,392 INFO [trainer.py:765] (6/8) Epoch 28, batch 200, train_loss[loss=2.762, NarTop10Accuracy=0.7737, over 6735.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7072, over 3861.86 frames. ], batch size: 17, lr: 3.07e-03
2024-08-06 20:35:45,421 INFO [trainer.py:765] (6/8) Epoch 28, batch 300, train_loss[loss=3.045, NarTop10Accuracy=0.7087, over 7062.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.7102, over 4672.01 frames. ], batch size: 22, lr: 3.07e-03
2024-08-06 20:36:15,863 INFO [trainer.py:765] (6/8) Epoch 28, batch 400, train_loss[loss=3.171, NarTop10Accuracy=0.6817, over 5229.00 frames. ], tot_loss[loss=3.091, NarTop10Accuracy=0.7072, over 5123.82 frames. ], batch size: 7, lr: 3.07e-03
2024-08-06 20:36:32,405 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 20:36:40,530 INFO [trainer.py:811] (6/8) Epoch 28, validation: loss=2.963, NarTop10Accuracy=0.7327, over 1905321.00 frames. 
2024-08-06 20:36:40,531 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 20:36:41,102 INFO [optim.py:386] (6/8) 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 20:36:56,663 INFO [trainer.py:765] (6/8) Epoch 28, batch 500, train_loss[loss=3.231, NarTop10Accuracy=0.6767, over 6075.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7105, over 5389.65 frames. ], batch size: 11, lr: 3.06e-03
2024-08-06 20:37:29,462 INFO [trainer.py:765] (6/8) Epoch 28, batch 600, train_loss[loss=2.934, NarTop10Accuracy=0.7444, over 5628.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.7105, over 5649.65 frames. ], batch size: 9, lr: 3.06e-03
2024-08-06 20:38:08,890 INFO [trainer.py:765] (6/8) Epoch 28, batch 700, train_loss[loss=3.057, NarTop10Accuracy=0.7063, over 5085.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7087, over 5732.38 frames. ], batch size: 6, lr: 3.06e-03
2024-08-06 20:38:42,488 INFO [trainer.py:765] (6/8) Epoch 28, batch 800, train_loss[loss=2.925, NarTop10Accuracy=0.7554, over 4293.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7126, over 5789.33 frames. ], batch size: 5, lr: 3.06e-03
2024-08-06 20:39:15,506 INFO [trainer.py:765] (6/8) Epoch 28, batch 900, train_loss[loss=3.29, NarTop10Accuracy=0.6706, over 6735.00 frames. ], tot_loss[loss=3.062, NarTop10Accuracy=0.7137, over 5803.37 frames. ], batch size: 14, lr: 3.06e-03
2024-08-06 20:39:53,239 INFO [trainer.py:765] (6/8) Epoch 28, batch 1000, train_loss[loss=3.121, NarTop10Accuracy=0.6915, over 6252.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7135, over 5893.74 frames. ], batch size: 13, lr: 3.05e-03
2024-08-06 20:40:25,866 INFO [trainer.py:765] (6/8) Epoch 28, batch 1100, train_loss[loss=2.831, NarTop10Accuracy=0.7604, over 6900.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7109, over 5906.12 frames. ], batch size: 17, lr: 3.05e-03
2024-08-06 20:40:59,418 INFO [trainer.py:765] (6/8) Epoch 28, batch 1200, train_loss[loss=3.307, NarTop10Accuracy=0.6622, over 7053.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7102, over 5904.08 frames. ], batch size: 31, lr: 3.05e-03
2024-08-06 20:41:38,680 INFO [trainer.py:765] (6/8) Epoch 28, batch 1300, train_loss[loss=2.955, NarTop10Accuracy=0.7242, over 5034.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7102, over 5960.69 frames. ], batch size: 6, lr: 3.05e-03
2024-08-06 20:42:13,047 INFO [trainer.py:765] (6/8) Epoch 28, batch 1400, train_loss[loss=2.982, NarTop10Accuracy=0.7278, over 5958.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7087, over 6007.00 frames. ], batch size: 11, lr: 3.04e-03
2024-08-06 20:42:43,170 INFO [trainer.py:765] (6/8) Epoch 28, batch 1500, train_loss[loss=3.442, NarTop10Accuracy=0.6357, over 6003.00 frames. ], tot_loss[loss=3.077, NarTop10Accuracy=0.71, over 5954.05 frames. ], batch size: 50, lr: 3.04e-03
2024-08-06 20:43:11,080 INFO [trainer.py:765] (6/8) Epoch 28, batch 1600, train_loss[loss=2.825, NarTop10Accuracy=0.7525, over 7284.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7095, over 5926.05 frames. ], batch size: 23, lr: 3.04e-03
2024-08-06 20:43:37,785 INFO [trainer.py:765] (6/8) Epoch 28, batch 1700, train_loss[loss=2.878, NarTop10Accuracy=0.7424, over 6540.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7083, over 5901.23 frames. ], batch size: 14, lr: 3.04e-03
2024-08-06 20:44:04,325 INFO [trainer.py:765] (6/8) Epoch 28, batch 1800, train_loss[loss=2.919, NarTop10Accuracy=0.7419, over 6975.00 frames. ], tot_loss[loss=3.081, NarTop10Accuracy=0.709, over 5958.74 frames. ], batch size: 22, lr: 3.04e-03
2024-08-06 20:44:30,756 INFO [trainer.py:765] (6/8) Epoch 28, batch 1900, train_loss[loss=3.201, NarTop10Accuracy=0.6889, over 6141.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7096, over 6014.14 frames. ], batch size: 50, lr: 3.03e-03
2024-08-06 20:44:56,328 INFO [trainer.py:765] (6/8) Epoch 28, batch 2000, train_loss[loss=2.934, NarTop10Accuracy=0.7389, over 6204.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7133, over 5997.62 frames. ], batch size: 51, lr: 3.03e-03
2024-08-06 20:45:21,650 INFO [trainer.py:765] (6/8) Epoch 28, batch 2100, train_loss[loss=2.715, NarTop10Accuracy=0.7917, over 4869.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7147, over 5968.68 frames. ], batch size: 5, lr: 3.03e-03
2024-08-06 20:45:47,077 INFO [trainer.py:765] (6/8) Epoch 28, batch 2200, train_loss[loss=2.901, NarTop10Accuracy=0.7515, over 7218.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7126, over 6015.17 frames. ], batch size: 31, lr: 3.03e-03
2024-08-06 20:46:12,308 INFO [trainer.py:765] (6/8) Epoch 28, batch 2300, train_loss[loss=3.351, NarTop10Accuracy=0.6619, over 5703.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7088, over 6025.59 frames. ], batch size: 9, lr: 3.03e-03
2024-08-06 20:46:36,807 INFO [trainer.py:765] (6/8) Epoch 28, batch 2400, train_loss[loss=3.016, NarTop10Accuracy=0.7217, over 5085.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7085, over 5779.15 frames. ], batch size: 7, lr: 3.02e-03
2024-08-06 20:46:48,595 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 20:46:56,604 INFO [trainer.py:811] (6/8) Epoch 28, validation: loss=2.931, NarTop10Accuracy=0.7396, over 1905321.00 frames. 
2024-08-06 20:46:56,605 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 20:46:57,082 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 28, batch 2500, train_loss[loss=3.221, NarTop10Accuracy=0.683, over 5070.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7132, over 5477.56 frames. ], batch size: 7, lr: 3.02e-03
2024-08-06 20:47:28,322 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 20:48:21,052 INFO [trainer.py:765] (6/8) Epoch 29, batch 100, train_loss[loss=2.964, NarTop10Accuracy=0.7307, over 7269.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.71, over 2364.45 frames. ], batch size: 31, lr: 2.96e-03
2024-08-06 20:48:53,405 INFO [trainer.py:765] (6/8) Epoch 29, batch 200, train_loss[loss=3.292, NarTop10Accuracy=0.6727, over 6897.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7156, over 3853.10 frames. ], batch size: 17, lr: 2.96e-03
2024-08-06 20:49:27,476 INFO [trainer.py:765] (6/8) Epoch 29, batch 300, train_loss[loss=3.114, NarTop10Accuracy=0.6976, over 6972.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7174, over 4642.08 frames. ], batch size: 22, lr: 2.96e-03
2024-08-06 20:49:56,052 INFO [trainer.py:765] (6/8) Epoch 29, batch 400, train_loss[loss=3.206, NarTop10Accuracy=0.6811, over 5181.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.713, over 5105.77 frames. ], batch size: 7, lr: 2.96e-03
2024-08-06 20:50:29,435 INFO [trainer.py:765] (6/8) Epoch 29, batch 500, train_loss[loss=3.073, NarTop10Accuracy=0.712, over 6108.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7153, over 5380.54 frames. ], batch size: 11, lr: 2.96e-03
2024-08-06 20:51:00,024 INFO [trainer.py:765] (6/8) Epoch 29, batch 600, train_loss[loss=2.743, NarTop10Accuracy=0.7794, over 5751.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7157, over 5661.98 frames. ], batch size: 9, lr: 2.95e-03
2024-08-06 20:51:35,677 INFO [trainer.py:765] (6/8) Epoch 29, batch 700, train_loss[loss=2.877, NarTop10Accuracy=0.7589, over 5079.00 frames. ], tot_loss[loss=3.073, NarTop10Accuracy=0.711, over 5718.51 frames. ], batch size: 6, lr: 2.95e-03
2024-08-06 20:52:10,725 INFO [trainer.py:765] (6/8) Epoch 29, batch 800, train_loss[loss=2.78, NarTop10Accuracy=0.7666, over 5070.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7116, over 5777.79 frames. ], batch size: 6, lr: 2.95e-03
2024-08-06 20:52:40,742 INFO [trainer.py:765] (6/8) Epoch 29, batch 900, train_loss[loss=2.758, NarTop10Accuracy=0.7803, over 6621.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7114, over 5803.40 frames. ], batch size: 14, lr: 2.95e-03
2024-08-06 20:53:16,861 INFO [trainer.py:765] (6/8) Epoch 29, batch 1000, train_loss[loss=3.389, NarTop10Accuracy=0.6534, over 6192.00 frames. ], tot_loss[loss=3.076, NarTop10Accuracy=0.7103, over 5895.17 frames. ], batch size: 13, lr: 2.95e-03
2024-08-06 20:53:52,902 INFO [trainer.py:765] (6/8) Epoch 29, batch 1100, train_loss[loss=3.188, NarTop10Accuracy=0.6812, over 6843.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7095, over 5928.43 frames. ], batch size: 17, lr: 2.94e-03
2024-08-06 20:54:23,690 INFO [trainer.py:765] (6/8) Epoch 29, batch 1200, train_loss[loss=3.064, NarTop10Accuracy=0.7089, over 7287.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7106, over 5922.91 frames. ], batch size: 31, lr: 2.94e-03
2024-08-06 20:55:01,428 INFO [trainer.py:765] (6/8) Epoch 29, batch 1300, train_loss[loss=3.004, NarTop10Accuracy=0.7184, over 4371.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7106, over 5998.58 frames. ], batch size: 5, lr: 2.94e-03
2024-08-06 20:55:32,557 INFO [trainer.py:765] (6/8) Epoch 29, batch 1400, train_loss[loss=3.262, NarTop10Accuracy=0.6666, over 6144.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7105, over 6021.86 frames. ], batch size: 11, lr: 2.94e-03
2024-08-06 20:56:04,359 INFO [trainer.py:765] (6/8) Epoch 29, batch 1500, train_loss[loss=3.339, NarTop10Accuracy=0.6546, over 6285.00 frames. ], tot_loss[loss=3.074, NarTop10Accuracy=0.7106, over 5946.00 frames. ], batch size: 50, lr: 2.94e-03
2024-08-06 20:56:32,041 INFO [trainer.py:765] (6/8) Epoch 29, batch 1600, train_loss[loss=3.367, NarTop10Accuracy=0.6421, over 6942.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.709, over 5925.47 frames. ], batch size: 22, lr: 2.93e-03
2024-08-06 20:56:58,640 INFO [trainer.py:765] (6/8) Epoch 29, batch 1700, train_loss[loss=2.727, NarTop10Accuracy=0.786, over 6312.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7114, over 5908.11 frames. ], batch size: 13, lr: 2.93e-03
2024-08-06 20:57:25,000 INFO [trainer.py:765] (6/8) Epoch 29, batch 1800, train_loss[loss=3.053, NarTop10Accuracy=0.7131, over 6957.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7124, over 5979.61 frames. ], batch size: 22, lr: 2.93e-03
2024-08-06 20:57:44,622 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 20:57:52,863 INFO [trainer.py:811] (6/8) Epoch 29, validation: loss=2.897, NarTop10Accuracy=0.7458, over 1905321.00 frames. 
2024-08-06 20:57:52,864 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 20:57:53,424 INFO [optim.py:386] (6/8) Clipping_scale=2.0, grad-norm quartiles 1.772e+02 2.206e+02 2.380e+02 2.554e+02 4.464e+02, threshold=4.759e+02, percent-clipped=0.0
2024-08-06 20:57:59,756 INFO [trainer.py:765] (6/8) Epoch 29, batch 1900, train_loss[loss=3.027, NarTop10Accuracy=0.7209, over 6513.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7093, over 6033.43 frames. ], batch size: 51, lr: 2.93e-03
2024-08-06 20:58:25,308 INFO [trainer.py:765] (6/8) Epoch 29, batch 2000, train_loss[loss=3.487, NarTop10Accuracy=0.6188, over 6336.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.709, over 6022.33 frames. ], batch size: 50, lr: 2.93e-03
2024-08-06 20:58:50,629 INFO [trainer.py:765] (6/8) Epoch 29, batch 2100, train_loss[loss=2.782, NarTop10Accuracy=0.7636, over 3840.00 frames. ], tot_loss[loss=3.09, NarTop10Accuracy=0.7075, over 5995.05 frames. ], batch size: 4, lr: 2.92e-03
2024-08-06 20:59:15,805 INFO [trainer.py:765] (6/8) Epoch 29, batch 2200, train_loss[loss=2.85, NarTop10Accuracy=0.7564, over 7263.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7095, over 6026.28 frames. ], batch size: 31, lr: 2.92e-03
2024-08-06 20:59:40,910 INFO [trainer.py:765] (6/8) Epoch 29, batch 2300, train_loss[loss=2.813, NarTop10Accuracy=0.7664, over 5784.00 frames. ], tot_loss[loss=3.097, NarTop10Accuracy=0.7057, over 6040.58 frames. ], batch size: 9, lr: 2.92e-03
2024-08-06 21:00:05,155 INFO [trainer.py:765] (6/8) Epoch 29, batch 2400, train_loss[loss=2.996, NarTop10Accuracy=0.7351, over 5238.00 frames. ], tot_loss[loss=3.083, NarTop10Accuracy=0.7085, over 5776.15 frames. ], batch size: 7, lr: 2.92e-03
2024-08-06 21:00:28,742 INFO [trainer.py:765] (6/8) Epoch 29, batch 2500, train_loss[loss=3.281, NarTop10Accuracy=0.6763, over 5133.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7145, over 5491.30 frames. ], batch size: 7, lr: 2.92e-03
2024-08-06 21:00:48,687 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 21:01:41,717 INFO [trainer.py:765] (6/8) Epoch 30, batch 100, train_loss[loss=2.917, NarTop10Accuracy=0.7502, over 7374.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7202, over 2361.22 frames. ], batch size: 31, lr: 2.86e-03
2024-08-06 21:02:17,013 INFO [trainer.py:765] (6/8) Epoch 30, batch 200, train_loss[loss=2.991, NarTop10Accuracy=0.7354, over 7149.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7231, over 3857.63 frames. ], batch size: 18, lr: 2.86e-03
2024-08-06 21:02:51,343 INFO [trainer.py:765] (6/8) Epoch 30, batch 300, train_loss[loss=2.955, NarTop10Accuracy=0.7307, over 7281.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7229, over 4651.28 frames. ], batch size: 22, lr: 2.86e-03
2024-08-06 21:03:21,643 INFO [trainer.py:765] (6/8) Epoch 30, batch 400, train_loss[loss=2.804, NarTop10Accuracy=0.7651, over 5091.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7197, over 5115.71 frames. ], batch size: 7, lr: 2.86e-03
2024-08-06 21:03:58,546 INFO [trainer.py:765] (6/8) Epoch 30, batch 500, train_loss[loss=3.532, NarTop10Accuracy=0.6108, over 6135.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7172, over 5401.59 frames. ], batch size: 11, lr: 2.86e-03
2024-08-06 21:04:31,656 INFO [trainer.py:765] (6/8) Epoch 30, batch 600, train_loss[loss=3.058, NarTop10Accuracy=0.7189, over 5832.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7163, over 5668.73 frames. ], batch size: 9, lr: 2.85e-03
2024-08-06 21:05:03,526 INFO [trainer.py:765] (6/8) Epoch 30, batch 700, train_loss[loss=3.017, NarTop10Accuracy=0.7243, over 4977.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7177, over 5737.76 frames. ], batch size: 6, lr: 2.85e-03
2024-08-06 21:05:44,132 INFO [trainer.py:765] (6/8) Epoch 30, batch 800, train_loss[loss=2.894, NarTop10Accuracy=0.7416, over 4233.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7188, over 5778.80 frames. ], batch size: 5, lr: 2.85e-03
2024-08-06 21:06:14,843 INFO [trainer.py:765] (6/8) Epoch 30, batch 900, train_loss[loss=2.932, NarTop10Accuracy=0.7406, over 6324.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7183, over 5795.36 frames. ], batch size: 13, lr: 2.85e-03
2024-08-06 21:06:48,952 INFO [trainer.py:765] (6/8) Epoch 30, batch 1000, train_loss[loss=2.945, NarTop10Accuracy=0.7333, over 6597.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.7105, over 5899.25 frames. ], batch size: 14, lr: 2.85e-03
2024-08-06 21:07:25,936 INFO [trainer.py:765] (6/8) Epoch 30, batch 1100, train_loss[loss=3.306, NarTop10Accuracy=0.6643, over 6747.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7086, over 5937.48 frames. ], batch size: 17, lr: 2.84e-03
2024-08-06 21:08:02,381 INFO [trainer.py:765] (6/8) Epoch 30, batch 1200, train_loss[loss=2.987, NarTop10Accuracy=0.7362, over 7323.00 frames. ], tot_loss[loss=3.071, NarTop10Accuracy=0.7109, over 5930.36 frames. ], batch size: 31, lr: 2.84e-03
2024-08-06 21:08:35,370 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 21:08:43,457 INFO [trainer.py:811] (6/8) Epoch 30, validation: loss=2.93, NarTop10Accuracy=0.7391, over 1905321.00 frames. 
2024-08-06 21:08:43,458 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 21:08:44,197 INFO [optim.py:386] (6/8) Clipping_scale=2.0, grad-norm quartiles 1.770e+02 2.209e+02 2.377e+02 2.553e+02 3.956e+02, threshold=4.754e+02, percent-clipped=0.0
2024-08-06 21:08:44,203 INFO [trainer.py:765] (6/8) Epoch 30, batch 1300, train_loss[loss=2.977, NarTop10Accuracy=0.7268, over 5079.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7119, over 6002.96 frames. ], batch size: 6, lr: 2.84e-03
2024-08-06 21:09:22,397 INFO [trainer.py:765] (6/8) Epoch 30, batch 1400, train_loss[loss=2.806, NarTop10Accuracy=0.7614, over 6030.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7113, over 6015.82 frames. ], batch size: 11, lr: 2.84e-03
2024-08-06 21:09:52,373 INFO [trainer.py:765] (6/8) Epoch 30, batch 1500, train_loss[loss=3.075, NarTop10Accuracy=0.7197, over 6081.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7119, over 5957.95 frames. ], batch size: 51, lr: 2.84e-03
2024-08-06 21:10:20,084 INFO [trainer.py:765] (6/8) Epoch 30, batch 1600, train_loss[loss=3.053, NarTop10Accuracy=0.724, over 7425.00 frames. ], tot_loss[loss=3.072, NarTop10Accuracy=0.711, over 5937.20 frames. ], batch size: 23, lr: 2.84e-03
2024-08-06 21:10:46,679 INFO [trainer.py:765] (6/8) Epoch 30, batch 1700, train_loss[loss=3.156, NarTop10Accuracy=0.6953, over 6600.00 frames. ], tot_loss[loss=3.082, NarTop10Accuracy=0.7088, over 5917.27 frames. ], batch size: 14, lr: 2.83e-03
2024-08-06 21:11:13,059 INFO [trainer.py:765] (6/8) Epoch 30, batch 1800, train_loss[loss=3.403, NarTop10Accuracy=0.6543, over 6822.00 frames. ], tot_loss[loss=3.079, NarTop10Accuracy=0.7095, over 5962.56 frames. ], batch size: 22, lr: 2.83e-03
2024-08-06 21:11:39,419 INFO [trainer.py:765] (6/8) Epoch 30, batch 1900, train_loss[loss=3.023, NarTop10Accuracy=0.7277, over 6132.00 frames. ], tot_loss[loss=3.078, NarTop10Accuracy=0.7099, over 6022.42 frames. ], batch size: 50, lr: 2.83e-03
2024-08-06 21:12:04,826 INFO [trainer.py:765] (6/8) Epoch 30, batch 2000, train_loss[loss=3.309, NarTop10Accuracy=0.6675, over 5871.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7125, over 5985.14 frames. ], batch size: 52, lr: 2.83e-03
2024-08-06 21:12:30,089 INFO [trainer.py:765] (6/8) Epoch 30, batch 2100, train_loss[loss=2.641, NarTop10Accuracy=0.7888, over 4776.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.712, over 5970.47 frames. ], batch size: 5, lr: 2.83e-03
2024-08-06 21:12:55,225 INFO [trainer.py:765] (6/8) Epoch 30, batch 2200, train_loss[loss=2.94, NarTop10Accuracy=0.7376, over 7455.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7113, over 6009.45 frames. ], batch size: 31, lr: 2.82e-03
2024-08-06 21:13:20,297 INFO [trainer.py:765] (6/8) Epoch 30, batch 2300, train_loss[loss=2.71, NarTop10Accuracy=0.7904, over 5655.00 frames. ], tot_loss[loss=3.084, NarTop10Accuracy=0.7084, over 6024.16 frames. ], batch size: 9, lr: 2.82e-03
2024-08-06 21:13:44,491 INFO [trainer.py:765] (6/8) Epoch 30, batch 2400, train_loss[loss=2.686, NarTop10Accuracy=0.7896, over 5097.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7157, over 5782.44 frames. ], batch size: 7, lr: 2.82e-03
2024-08-06 21:14:07,988 INFO [trainer.py:765] (6/8) Epoch 30, batch 2500, train_loss[loss=2.883, NarTop10Accuracy=0.7397, over 5355.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.716, over 5485.52 frames. ], batch size: 7, lr: 2.82e-03
2024-08-06 21:14:27,968 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 21:15:23,633 INFO [trainer.py:765] (6/8) Epoch 31, batch 100, train_loss[loss=3.424, NarTop10Accuracy=0.6417, over 7080.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7134, over 2379.35 frames. ], batch size: 31, lr: 2.77e-03
2024-08-06 21:15:55,128 INFO [trainer.py:765] (6/8) Epoch 31, batch 200, train_loss[loss=2.804, NarTop10Accuracy=0.7568, over 6741.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7191, over 3865.26 frames. ], batch size: 17, lr: 2.77e-03
2024-08-06 21:16:31,216 INFO [trainer.py:765] (6/8) Epoch 31, batch 300, train_loss[loss=3.017, NarTop10Accuracy=0.7231, over 7119.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7195, over 4662.09 frames. ], batch size: 22, lr: 2.77e-03
2024-08-06 21:17:01,625 INFO [trainer.py:765] (6/8) Epoch 31, batch 400, train_loss[loss=3.156, NarTop10Accuracy=0.6863, over 5139.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7168, over 5101.54 frames. ], batch size: 7, lr: 2.76e-03
2024-08-06 21:17:35,725 INFO [trainer.py:765] (6/8) Epoch 31, batch 500, train_loss[loss=2.813, NarTop10Accuracy=0.7684, over 6129.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7178, over 5363.84 frames. ], batch size: 11, lr: 2.76e-03
2024-08-06 21:18:07,084 INFO [trainer.py:765] (6/8) Epoch 31, batch 600, train_loss[loss=2.671, NarTop10Accuracy=0.7968, over 5760.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7145, over 5625.61 frames. ], batch size: 9, lr: 2.76e-03
2024-08-06 21:18:44,611 INFO [trainer.py:765] (6/8) Epoch 31, batch 700, train_loss[loss=3.229, NarTop10Accuracy=0.6757, over 5016.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7136, over 5705.04 frames. ], batch size: 6, lr: 2.76e-03
2024-08-06 21:18:51,096 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 21:18:59,276 INFO [trainer.py:811] (6/8) Epoch 31, validation: loss=2.984, NarTop10Accuracy=0.7279, over 1905321.00 frames. 
2024-08-06 21:18:59,277 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 21:18:59,985 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 31, batch 800, train_loss[loss=2.776, NarTop10Accuracy=0.7712, over 5004.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7151, over 5772.30 frames. ], batch size: 6, lr: 2.76e-03
2024-08-06 21:19:56,950 INFO [trainer.py:765] (6/8) Epoch 31, batch 900, train_loss[loss=3.145, NarTop10Accuracy=0.6816, over 6246.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7168, over 5785.27 frames. ], batch size: 13, lr: 2.76e-03
2024-08-06 21:20:33,310 INFO [trainer.py:765] (6/8) Epoch 31, batch 1000, train_loss[loss=3.414, NarTop10Accuracy=0.639, over 6216.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.716, over 5897.50 frames. ], batch size: 13, lr: 2.75e-03
2024-08-06 21:21:10,215 INFO [trainer.py:765] (6/8) Epoch 31, batch 1100, train_loss[loss=3.32, NarTop10Accuracy=0.6594, over 6903.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7155, over 5946.62 frames. ], batch size: 17, lr: 2.75e-03
2024-08-06 21:21:41,119 INFO [trainer.py:765] (6/8) Epoch 31, batch 1200, train_loss[loss=2.906, NarTop10Accuracy=0.7412, over 7353.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7186, over 5932.06 frames. ], batch size: 31, lr: 2.75e-03
2024-08-06 21:22:19,741 INFO [trainer.py:765] (6/8) Epoch 31, batch 1300, train_loss[loss=2.662, NarTop10Accuracy=0.7835, over 4386.00 frames. ], tot_loss[loss=3.063, NarTop10Accuracy=0.7128, over 5985.87 frames. ], batch size: 5, lr: 2.75e-03
2024-08-06 21:22:53,533 INFO [trainer.py:765] (6/8) Epoch 31, batch 1400, train_loss[loss=2.865, NarTop10Accuracy=0.7463, over 6129.00 frames. ], tot_loss[loss=3.069, NarTop10Accuracy=0.7115, over 6005.84 frames. ], batch size: 11, lr: 2.75e-03
2024-08-06 21:23:21,269 INFO [trainer.py:765] (6/8) Epoch 31, batch 1500, train_loss[loss=3.315, NarTop10Accuracy=0.6609, over 6054.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7136, over 5948.06 frames. ], batch size: 51, lr: 2.74e-03
2024-08-06 21:23:49,004 INFO [trainer.py:765] (6/8) Epoch 31, batch 1600, train_loss[loss=3.221, NarTop10Accuracy=0.6764, over 7080.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7151, over 5923.04 frames. ], batch size: 22, lr: 2.74e-03
2024-08-06 21:24:15,511 INFO [trainer.py:765] (6/8) Epoch 31, batch 1700, train_loss[loss=3.281, NarTop10Accuracy=0.6731, over 6237.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7154, over 5915.46 frames. ], batch size: 13, lr: 2.74e-03
2024-08-06 21:24:41,995 INFO [trainer.py:765] (6/8) Epoch 31, batch 1800, train_loss[loss=2.804, NarTop10Accuracy=0.7674, over 6951.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7177, over 5984.95 frames. ], batch size: 22, lr: 2.74e-03
2024-08-06 21:25:08,357 INFO [trainer.py:765] (6/8) Epoch 31, batch 1900, train_loss[loss=3.099, NarTop10Accuracy=0.7045, over 6489.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7146, over 6032.14 frames. ], batch size: 52, lr: 2.74e-03
2024-08-06 21:25:33,773 INFO [trainer.py:765] (6/8) Epoch 31, batch 2000, train_loss[loss=3.02, NarTop10Accuracy=0.7218, over 6210.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7155, over 5998.65 frames. ], batch size: 50, lr: 2.74e-03
2024-08-06 21:25:59,106 INFO [trainer.py:765] (6/8) Epoch 31, batch 2100, train_loss[loss=2.644, NarTop10Accuracy=0.7915, over 3912.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7152, over 5973.89 frames. ], batch size: 4, lr: 2.73e-03
2024-08-06 21:26:24,238 INFO [trainer.py:765] (6/8) Epoch 31, batch 2200, train_loss[loss=2.982, NarTop10Accuracy=0.7321, over 7116.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.718, over 6005.64 frames. ], batch size: 31, lr: 2.73e-03
2024-08-06 21:26:49,321 INFO [trainer.py:765] (6/8) Epoch 31, batch 2300, train_loss[loss=2.751, NarTop10Accuracy=0.7704, over 5667.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7146, over 6009.88 frames. ], batch size: 9, lr: 2.73e-03
2024-08-06 21:27:13,607 INFO [trainer.py:765] (6/8) Epoch 31, batch 2400, train_loss[loss=2.8, NarTop10Accuracy=0.7589, over 5109.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7153, over 5763.81 frames. ], batch size: 7, lr: 2.73e-03
2024-08-06 21:27:37,027 INFO [trainer.py:765] (6/8) Epoch 31, batch 2500, train_loss[loss=2.99, NarTop10Accuracy=0.7293, over 5022.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7185, over 5456.04 frames. ], batch size: 7, lr: 2.73e-03
2024-08-06 21:27:57,405 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 21:28:49,392 INFO [trainer.py:765] (6/8) Epoch 32, batch 100, train_loss[loss=2.874, NarTop10Accuracy=0.756, over 7374.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7144, over 2372.63 frames. ], batch size: 31, lr: 2.68e-03
2024-08-06 21:29:08,160 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 21:29:16,392 INFO [trainer.py:811] (6/8) Epoch 32, validation: loss=2.919, NarTop10Accuracy=0.7409, over 1905321.00 frames. 
2024-08-06 21:29:16,393 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 21:29:16,939 INFO [optim.py:386] (6/8) 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 21:29:32,272 INFO [trainer.py:765] (6/8) Epoch 32, batch 200, train_loss[loss=3.171, NarTop10Accuracy=0.6944, over 6912.00 frames. ], tot_loss[loss=3.067, NarTop10Accuracy=0.7124, over 3861.03 frames. ], batch size: 17, lr: 2.68e-03
2024-08-06 21:30:05,279 INFO [trainer.py:765] (6/8) Epoch 32, batch 300, train_loss[loss=3.103, NarTop10Accuracy=0.7019, over 6981.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7153, over 4673.28 frames. ], batch size: 22, lr: 2.68e-03
2024-08-06 21:30:34,103 INFO [trainer.py:765] (6/8) Epoch 32, batch 400, train_loss[loss=2.784, NarTop10Accuracy=0.7723, over 5229.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7131, over 5101.30 frames. ], batch size: 7, lr: 2.68e-03
2024-08-06 21:31:13,530 INFO [trainer.py:765] (6/8) Epoch 32, batch 500, train_loss[loss=3.016, NarTop10Accuracy=0.7277, over 6108.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7142, over 5392.92 frames. ], batch size: 11, lr: 2.67e-03
2024-08-06 21:31:42,486 INFO [trainer.py:765] (6/8) Epoch 32, batch 600, train_loss[loss=3.084, NarTop10Accuracy=0.7173, over 5577.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7151, over 5638.86 frames. ], batch size: 9, lr: 2.67e-03
2024-08-06 21:32:17,029 INFO [trainer.py:765] (6/8) Epoch 32, batch 700, train_loss[loss=2.829, NarTop10Accuracy=0.7593, over 5136.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7178, over 5736.13 frames. ], batch size: 6, lr: 2.67e-03
2024-08-06 21:33:00,646 INFO [trainer.py:765] (6/8) Epoch 32, batch 800, train_loss[loss=3.324, NarTop10Accuracy=0.6554, over 5070.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7171, over 5787.63 frames. ], batch size: 6, lr: 2.67e-03
2024-08-06 21:33:28,991 INFO [trainer.py:765] (6/8) Epoch 32, batch 900, train_loss[loss=2.765, NarTop10Accuracy=0.7768, over 6180.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7193, over 5804.08 frames. ], batch size: 13, lr: 2.67e-03
2024-08-06 21:34:04,049 INFO [trainer.py:765] (6/8) Epoch 32, batch 1000, train_loss[loss=3.279, NarTop10Accuracy=0.6702, over 6591.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7167, over 5904.03 frames. ], batch size: 14, lr: 2.67e-03
2024-08-06 21:34:46,674 INFO [trainer.py:765] (6/8) Epoch 32, batch 1100, train_loss[loss=3.125, NarTop10Accuracy=0.6955, over 6795.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7158, over 5931.52 frames. ], batch size: 17, lr: 2.66e-03
2024-08-06 21:35:18,171 INFO [trainer.py:765] (6/8) Epoch 32, batch 1200, train_loss[loss=3.247, NarTop10Accuracy=0.671, over 7371.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7142, over 5912.97 frames. ], batch size: 31, lr: 2.66e-03
2024-08-06 21:35:52,801 INFO [trainer.py:765] (6/8) Epoch 32, batch 1300, train_loss[loss=3.259, NarTop10Accuracy=0.6749, over 4278.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7133, over 5989.30 frames. ], batch size: 5, lr: 2.66e-03
2024-08-06 21:36:29,479 INFO [trainer.py:765] (6/8) Epoch 32, batch 1400, train_loss[loss=3.452, NarTop10Accuracy=0.6366, over 6141.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.7134, over 6036.88 frames. ], batch size: 11, lr: 2.66e-03
2024-08-06 21:37:04,733 INFO [trainer.py:765] (6/8) Epoch 32, batch 1500, train_loss[loss=3.493, NarTop10Accuracy=0.6277, over 6057.00 frames. ], tot_loss[loss=3.06, NarTop10Accuracy=0.7133, over 5956.80 frames. ], batch size: 50, lr: 2.66e-03
2024-08-06 21:37:32,522 INFO [trainer.py:765] (6/8) Epoch 32, batch 1600, train_loss[loss=3.055, NarTop10Accuracy=0.722, over 7473.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.714, over 5933.51 frames. ], batch size: 23, lr: 2.66e-03
2024-08-06 21:37:59,160 INFO [trainer.py:765] (6/8) Epoch 32, batch 1700, train_loss[loss=3.153, NarTop10Accuracy=0.7085, over 6216.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7135, over 5912.68 frames. ], batch size: 13, lr: 2.65e-03
2024-08-06 21:38:25,702 INFO [trainer.py:765] (6/8) Epoch 32, batch 1800, train_loss[loss=3.1, NarTop10Accuracy=0.7023, over 7209.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7132, over 5978.03 frames. ], batch size: 22, lr: 2.65e-03
2024-08-06 21:38:52,169 INFO [trainer.py:765] (6/8) Epoch 32, batch 1900, train_loss[loss=3.024, NarTop10Accuracy=0.7233, over 6420.00 frames. ], tot_loss[loss=3.08, NarTop10Accuracy=0.7093, over 6011.29 frames. ], batch size: 51, lr: 2.65e-03
2024-08-06 21:39:17,769 INFO [trainer.py:765] (6/8) Epoch 32, batch 2000, train_loss[loss=3.448, NarTop10Accuracy=0.6353, over 5946.00 frames. ], tot_loss[loss=3.061, NarTop10Accuracy=0.7132, over 5997.90 frames. ], batch size: 50, lr: 2.65e-03
2024-08-06 21:39:43,178 INFO [trainer.py:765] (6/8) Epoch 32, batch 2100, train_loss[loss=2.443, NarTop10Accuracy=0.835, over 3912.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7143, over 5987.25 frames. ], batch size: 4, lr: 2.65e-03
2024-08-06 21:39:54,782 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 21:40:02,941 INFO [trainer.py:811] (6/8) Epoch 32, validation: loss=2.886, NarTop10Accuracy=0.7482, over 1905321.00 frames. 
2024-08-06 21:40:02,942 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 21:40:03,423 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 32, batch 2200, train_loss[loss=3.115, NarTop10Accuracy=0.7035, over 7053.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7148, over 6036.09 frames. ], batch size: 31, lr: 2.65e-03
2024-08-06 21:40:41,718 INFO [trainer.py:765] (6/8) Epoch 32, batch 2300, train_loss[loss=3.374, NarTop10Accuracy=0.634, over 5727.00 frames. ], tot_loss[loss=3.075, NarTop10Accuracy=0.7101, over 6043.57 frames. ], batch size: 9, lr: 2.65e-03
2024-08-06 21:41:06,072 INFO [trainer.py:765] (6/8) Epoch 32, batch 2400, train_loss[loss=3.258, NarTop10Accuracy=0.6767, over 5157.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.7123, over 5779.57 frames. ], batch size: 7, lr: 2.64e-03
2024-08-06 21:41:29,538 INFO [trainer.py:765] (6/8) Epoch 32, batch 2500, train_loss[loss=2.911, NarTop10Accuracy=0.7553, over 5127.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.721, over 5478.01 frames. ], batch size: 7, lr: 2.64e-03
2024-08-06 21:41:49,419 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 21:42:47,615 INFO [trainer.py:765] (6/8) Epoch 33, batch 100, train_loss[loss=3.109, NarTop10Accuracy=0.7033, over 7668.00 frames. ], tot_loss[loss=3.01, NarTop10Accuracy=0.7233, over 2368.40 frames. ], batch size: 33, lr: 2.60e-03
2024-08-06 21:43:22,368 INFO [trainer.py:765] (6/8) Epoch 33, batch 200, train_loss[loss=2.801, NarTop10Accuracy=0.7671, over 6873.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7207, over 3857.98 frames. ], batch size: 17, lr: 2.60e-03
2024-08-06 21:43:56,513 INFO [trainer.py:765] (6/8) Epoch 33, batch 300, train_loss[loss=3.455, NarTop10Accuracy=0.6272, over 7014.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7178, over 4662.42 frames. ], batch size: 22, lr: 2.60e-03
2024-08-06 21:44:30,316 INFO [trainer.py:765] (6/8) Epoch 33, batch 400, train_loss[loss=2.707, NarTop10Accuracy=0.772, over 5106.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7178, over 5118.33 frames. ], batch size: 7, lr: 2.59e-03
2024-08-06 21:45:02,870 INFO [trainer.py:765] (6/8) Epoch 33, batch 500, train_loss[loss=2.892, NarTop10Accuracy=0.7467, over 6090.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7214, over 5389.03 frames. ], batch size: 11, lr: 2.59e-03
2024-08-06 21:45:36,226 INFO [trainer.py:765] (6/8) Epoch 33, batch 600, train_loss[loss=3.296, NarTop10Accuracy=0.6551, over 5757.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.717, over 5656.78 frames. ], batch size: 9, lr: 2.59e-03
2024-08-06 21:46:11,316 INFO [trainer.py:765] (6/8) Epoch 33, batch 700, train_loss[loss=2.848, NarTop10Accuracy=0.7528, over 5112.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7155, over 5719.11 frames. ], batch size: 6, lr: 2.59e-03
2024-08-06 21:46:46,169 INFO [trainer.py:765] (6/8) Epoch 33, batch 800, train_loss[loss=2.649, NarTop10Accuracy=0.8002, over 5034.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7156, over 5780.96 frames. ], batch size: 6, lr: 2.59e-03
2024-08-06 21:47:18,908 INFO [trainer.py:765] (6/8) Epoch 33, batch 900, train_loss[loss=3.312, NarTop10Accuracy=0.6678, over 6576.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7145, over 5787.91 frames. ], batch size: 14, lr: 2.59e-03
2024-08-06 21:47:57,316 INFO [trainer.py:765] (6/8) Epoch 33, batch 1000, train_loss[loss=3.003, NarTop10Accuracy=0.7277, over 6237.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7154, over 5879.16 frames. ], batch size: 13, lr: 2.58e-03
2024-08-06 21:48:30,908 INFO [trainer.py:765] (6/8) Epoch 33, batch 1100, train_loss[loss=2.893, NarTop10Accuracy=0.7457, over 6783.00 frames. ], tot_loss[loss=3.065, NarTop10Accuracy=0.712, over 5916.13 frames. ], batch size: 17, lr: 2.58e-03
2024-08-06 21:49:06,659 INFO [trainer.py:765] (6/8) Epoch 33, batch 1200, train_loss[loss=2.858, NarTop10Accuracy=0.749, over 7236.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7139, over 5913.02 frames. ], batch size: 31, lr: 2.58e-03
2024-08-06 21:49:42,815 INFO [trainer.py:765] (6/8) Epoch 33, batch 1300, train_loss[loss=2.886, NarTop10Accuracy=0.7373, over 5046.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7135, over 5996.84 frames. ], batch size: 6, lr: 2.58e-03
2024-08-06 21:50:17,310 INFO [trainer.py:765] (6/8) Epoch 33, batch 1400, train_loss[loss=3.329, NarTop10Accuracy=0.6521, over 6048.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7123, over 6012.78 frames. ], batch size: 11, lr: 2.58e-03
2024-08-06 21:50:45,370 INFO [trainer.py:765] (6/8) Epoch 33, batch 1500, train_loss[loss=3.053, NarTop10Accuracy=0.7223, over 5634.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7139, over 5944.21 frames. ], batch size: 50, lr: 2.58e-03
2024-08-06 21:51:04,606 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 21:51:12,661 INFO [trainer.py:811] (6/8) Epoch 33, validation: loss=2.938, NarTop10Accuracy=0.7372, over 1905321.00 frames. 
2024-08-06 21:51:12,662 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 21:51:13,180 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 33, batch 1600, train_loss[loss=3.135, NarTop10Accuracy=0.6892, over 6987.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7165, over 5951.61 frames. ], batch size: 22, lr: 2.57e-03
2024-08-06 21:51:47,923 INFO [trainer.py:765] (6/8) Epoch 33, batch 1700, train_loss[loss=2.751, NarTop10Accuracy=0.7751, over 6255.00 frames. ], tot_loss[loss=3.054, NarTop10Accuracy=0.7143, over 5932.55 frames. ], batch size: 13, lr: 2.57e-03
2024-08-06 21:52:14,392 INFO [trainer.py:765] (6/8) Epoch 33, batch 1800, train_loss[loss=2.748, NarTop10Accuracy=0.7718, over 7065.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7163, over 5983.27 frames. ], batch size: 22, lr: 2.57e-03
2024-08-06 21:52:40,856 INFO [trainer.py:765] (6/8) Epoch 33, batch 1900, train_loss[loss=3.544, NarTop10Accuracy=0.6198, over 5892.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.712, over 6014.41 frames. ], batch size: 50, lr: 2.57e-03
2024-08-06 21:53:06,352 INFO [trainer.py:765] (6/8) Epoch 33, batch 2000, train_loss[loss=3.399, NarTop10Accuracy=0.64, over 5889.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7188, over 5995.41 frames. ], batch size: 50, lr: 2.57e-03
2024-08-06 21:53:31,659 INFO [trainer.py:765] (6/8) Epoch 33, batch 2100, train_loss[loss=2.995, NarTop10Accuracy=0.7101, over 4833.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7173, over 5956.65 frames. ], batch size: 5, lr: 2.57e-03
2024-08-06 21:53:56,890 INFO [trainer.py:765] (6/8) Epoch 33, batch 2200, train_loss[loss=3.399, NarTop10Accuracy=0.6387, over 7344.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.715, over 5996.96 frames. ], batch size: 31, lr: 2.57e-03
2024-08-06 21:54:21,990 INFO [trainer.py:765] (6/8) Epoch 33, batch 2300, train_loss[loss=2.738, NarTop10Accuracy=0.7713, over 5742.00 frames. ], tot_loss[loss=3.057, NarTop10Accuracy=0.7141, over 6024.86 frames. ], batch size: 9, lr: 2.56e-03
2024-08-06 21:54:46,430 INFO [trainer.py:765] (6/8) Epoch 33, batch 2400, train_loss[loss=2.665, NarTop10Accuracy=0.7927, over 5265.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.718, over 5778.76 frames. ], batch size: 7, lr: 2.56e-03
2024-08-06 21:55:09,862 INFO [trainer.py:765] (6/8) Epoch 33, batch 2500, train_loss[loss=2.872, NarTop10Accuracy=0.7608, over 5220.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7218, over 5493.36 frames. ], batch size: 7, lr: 2.56e-03
2024-08-06 21:55:29,808 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 21:56:24,721 INFO [trainer.py:765] (6/8) Epoch 34, batch 100, train_loss[loss=3.474, NarTop10Accuracy=0.626, over 7437.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7203, over 2367.41 frames. ], batch size: 31, lr: 2.52e-03
2024-08-06 21:56:55,613 INFO [trainer.py:765] (6/8) Epoch 34, batch 200, train_loss[loss=3.168, NarTop10Accuracy=0.6873, over 6726.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7225, over 3861.83 frames. ], batch size: 17, lr: 2.52e-03
2024-08-06 21:57:31,776 INFO [trainer.py:765] (6/8) Epoch 34, batch 300, train_loss[loss=2.803, NarTop10Accuracy=0.7671, over 7116.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7188, over 4662.80 frames. ], batch size: 22, lr: 2.52e-03
2024-08-06 21:58:02,724 INFO [trainer.py:765] (6/8) Epoch 34, batch 400, train_loss[loss=3.233, NarTop10Accuracy=0.6815, over 5292.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7209, over 5106.14 frames. ], batch size: 7, lr: 2.52e-03
2024-08-06 21:58:34,689 INFO [trainer.py:765] (6/8) Epoch 34, batch 500, train_loss[loss=3.371, NarTop10Accuracy=0.6481, over 6024.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7185, over 5387.77 frames. ], batch size: 11, lr: 2.51e-03
2024-08-06 21:59:09,616 INFO [trainer.py:765] (6/8) Epoch 34, batch 600, train_loss[loss=2.833, NarTop10Accuracy=0.7552, over 5832.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.7191, over 5659.55 frames. ], batch size: 9, lr: 2.51e-03
2024-08-06 21:59:46,056 INFO [trainer.py:765] (6/8) Epoch 34, batch 700, train_loss[loss=3.073, NarTop10Accuracy=0.7091, over 5004.00 frames. ], tot_loss[loss=3.04, NarTop10Accuracy=0.7174, over 5716.86 frames. ], batch size: 6, lr: 2.51e-03
2024-08-06 22:00:17,575 INFO [trainer.py:765] (6/8) Epoch 34, batch 800, train_loss[loss=2.946, NarTop10Accuracy=0.7324, over 4455.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7202, over 5759.30 frames. ], batch size: 5, lr: 2.51e-03
2024-08-06 22:00:49,874 INFO [trainer.py:765] (6/8) Epoch 34, batch 900, train_loss[loss=2.897, NarTop10Accuracy=0.7461, over 6597.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7202, over 5773.28 frames. ], batch size: 14, lr: 2.51e-03
2024-08-06 22:01:25,338 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 22:01:33,386 INFO [trainer.py:811] (6/8) Epoch 34, validation: loss=2.9, NarTop10Accuracy=0.7444, over 1905321.00 frames. 
2024-08-06 22:01:33,387 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 22:01:34,092 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 34, batch 1000, train_loss[loss=3.36, NarTop10Accuracy=0.657, over 6210.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7186, over 5880.09 frames. ], batch size: 13, lr: 2.51e-03
2024-08-06 22:02:10,829 INFO [trainer.py:765] (6/8) Epoch 34, batch 1100, train_loss[loss=3.264, NarTop10Accuracy=0.6752, over 6912.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7168, over 5921.65 frames. ], batch size: 17, lr: 2.51e-03
2024-08-06 22:02:46,786 INFO [trainer.py:765] (6/8) Epoch 34, batch 1200, train_loss[loss=2.787, NarTop10Accuracy=0.764, over 7533.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7168, over 5919.88 frames. ], batch size: 31, lr: 2.50e-03
2024-08-06 22:03:20,814 INFO [trainer.py:765] (6/8) Epoch 34, batch 1300, train_loss[loss=2.767, NarTop10Accuracy=0.7731, over 5079.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7171, over 5992.11 frames. ], batch size: 6, lr: 2.50e-03
2024-08-06 22:03:52,949 INFO [trainer.py:765] (6/8) Epoch 34, batch 1400, train_loss[loss=3.115, NarTop10Accuracy=0.7009, over 6036.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7161, over 6024.18 frames. ], batch size: 11, lr: 2.50e-03
2024-08-06 22:04:20,822 INFO [trainer.py:765] (6/8) Epoch 34, batch 1500, train_loss[loss=3.118, NarTop10Accuracy=0.7014, over 6399.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7158, over 5956.72 frames. ], batch size: 52, lr: 2.50e-03
2024-08-06 22:04:48,600 INFO [trainer.py:765] (6/8) Epoch 34, batch 1600, train_loss[loss=2.837, NarTop10Accuracy=0.7611, over 7491.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7151, over 5939.07 frames. ], batch size: 23, lr: 2.50e-03
2024-08-06 22:05:15,241 INFO [trainer.py:765] (6/8) Epoch 34, batch 1700, train_loss[loss=3.038, NarTop10Accuracy=0.7113, over 6666.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7181, over 5929.60 frames. ], batch size: 14, lr: 2.50e-03
2024-08-06 22:05:41,720 INFO [trainer.py:765] (6/8) Epoch 34, batch 1800, train_loss[loss=3.206, NarTop10Accuracy=0.6817, over 6963.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7154, over 5986.96 frames. ], batch size: 22, lr: 2.50e-03
2024-08-06 22:06:08,206 INFO [trainer.py:765] (6/8) Epoch 34, batch 1900, train_loss[loss=3.006, NarTop10Accuracy=0.7249, over 6108.00 frames. ], tot_loss[loss=3.068, NarTop10Accuracy=0.7119, over 6019.96 frames. ], batch size: 51, lr: 2.49e-03
2024-08-06 22:06:33,770 INFO [trainer.py:765] (6/8) Epoch 34, batch 2000, train_loss[loss=3.051, NarTop10Accuracy=0.7145, over 5598.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7153, over 6002.01 frames. ], batch size: 50, lr: 2.49e-03
2024-08-06 22:06:59,126 INFO [trainer.py:765] (6/8) Epoch 34, batch 2100, train_loss[loss=3.233, NarTop10Accuracy=0.6739, over 4986.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7126, over 5997.21 frames. ], batch size: 5, lr: 2.49e-03
2024-08-06 22:07:24,398 INFO [trainer.py:765] (6/8) Epoch 34, batch 2200, train_loss[loss=2.867, NarTop10Accuracy=0.76, over 7344.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7123, over 6015.75 frames. ], batch size: 31, lr: 2.49e-03
2024-08-06 22:07:49,536 INFO [trainer.py:765] (6/8) Epoch 34, batch 2300, train_loss[loss=2.752, NarTop10Accuracy=0.7717, over 5682.00 frames. ], tot_loss[loss=3.064, NarTop10Accuracy=0.7121, over 6015.98 frames. ], batch size: 9, lr: 2.49e-03
2024-08-06 22:08:14,059 INFO [trainer.py:765] (6/8) Epoch 34, batch 2400, train_loss[loss=3.29, NarTop10Accuracy=0.6612, over 5076.00 frames. ], tot_loss[loss=3.066, NarTop10Accuracy=0.7118, over 5774.87 frames. ], batch size: 7, lr: 2.49e-03
2024-08-06 22:08:37,648 INFO [trainer.py:765] (6/8) Epoch 34, batch 2500, train_loss[loss=2.853, NarTop10Accuracy=0.7673, over 5103.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.72, over 5481.65 frames. ], batch size: 7, lr: 2.49e-03
2024-08-06 22:08:57,519 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 22:09:52,640 INFO [trainer.py:765] (6/8) Epoch 35, batch 100, train_loss[loss=2.891, NarTop10Accuracy=0.7508, over 7335.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7153, over 2366.62 frames. ], batch size: 32, lr: 2.45e-03
2024-08-06 22:10:29,697 INFO [trainer.py:765] (6/8) Epoch 35, batch 200, train_loss[loss=3.153, NarTop10Accuracy=0.6923, over 6711.00 frames. ], tot_loss[loss=3.058, NarTop10Accuracy=0.714, over 3849.04 frames. ], batch size: 17, lr: 2.45e-03
2024-08-06 22:11:04,943 INFO [trainer.py:765] (6/8) Epoch 35, batch 300, train_loss[loss=2.898, NarTop10Accuracy=0.7489, over 6873.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7183, over 4649.65 frames. ], batch size: 22, lr: 2.44e-03
2024-08-06 22:11:35,333 INFO [trainer.py:765] (6/8) Epoch 35, batch 400, train_loss[loss=2.932, NarTop10Accuracy=0.7399, over 5100.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7194, over 5110.40 frames. ], batch size: 7, lr: 2.44e-03
2024-08-06 22:11:40,047 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 22:11:48,129 INFO [trainer.py:811] (6/8) Epoch 35, validation: loss=2.84, NarTop10Accuracy=0.7576, over 1905321.00 frames. 
2024-08-06 22:11:48,129 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 22:11:48,702 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 35, batch 500, train_loss[loss=2.564, NarTop10Accuracy=0.8146, over 6060.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7216, over 5388.69 frames. ], batch size: 11, lr: 2.44e-03
2024-08-06 22:12:51,424 INFO [trainer.py:765] (6/8) Epoch 35, batch 600, train_loss[loss=3.3, NarTop10Accuracy=0.6648, over 5757.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7189, over 5643.86 frames. ], batch size: 9, lr: 2.44e-03
2024-08-06 22:13:24,940 INFO [trainer.py:765] (6/8) Epoch 35, batch 700, train_loss[loss=2.698, NarTop10Accuracy=0.7852, over 4995.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.7182, over 5728.18 frames. ], batch size: 6, lr: 2.44e-03
2024-08-06 22:14:01,384 INFO [trainer.py:765] (6/8) Epoch 35, batch 800, train_loss[loss=2.632, NarTop10Accuracy=0.8089, over 5181.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7171, over 5773.57 frames. ], batch size: 6, lr: 2.44e-03
2024-08-06 22:14:34,372 INFO [trainer.py:765] (6/8) Epoch 35, batch 900, train_loss[loss=3.164, NarTop10Accuracy=0.6931, over 6675.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7199, over 5786.81 frames. ], batch size: 14, lr: 2.44e-03
2024-08-06 22:15:09,372 INFO [trainer.py:765] (6/8) Epoch 35, batch 1000, train_loss[loss=2.896, NarTop10Accuracy=0.7452, over 6108.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.718, over 5892.84 frames. ], batch size: 13, lr: 2.43e-03
2024-08-06 22:15:48,495 INFO [trainer.py:765] (6/8) Epoch 35, batch 1100, train_loss[loss=2.975, NarTop10Accuracy=0.7344, over 6735.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7169, over 5914.38 frames. ], batch size: 17, lr: 2.43e-03
2024-08-06 22:16:22,483 INFO [trainer.py:765] (6/8) Epoch 35, batch 1200, train_loss[loss=2.958, NarTop10Accuracy=0.7389, over 7503.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7185, over 5926.77 frames. ], batch size: 32, lr: 2.43e-03
2024-08-06 22:16:57,060 INFO [trainer.py:765] (6/8) Epoch 35, batch 1300, train_loss[loss=2.988, NarTop10Accuracy=0.7289, over 5079.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7204, over 5991.18 frames. ], batch size: 6, lr: 2.43e-03
2024-08-06 22:17:31,060 INFO [trainer.py:765] (6/8) Epoch 35, batch 1400, train_loss[loss=3.05, NarTop10Accuracy=0.7152, over 6057.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7184, over 6000.84 frames. ], batch size: 11, lr: 2.43e-03
2024-08-06 22:18:03,062 INFO [trainer.py:765] (6/8) Epoch 35, batch 1500, train_loss[loss=3.078, NarTop10Accuracy=0.7053, over 6201.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.717, over 5961.36 frames. ], batch size: 50, lr: 2.43e-03
2024-08-06 22:18:30,728 INFO [trainer.py:765] (6/8) Epoch 35, batch 1600, train_loss[loss=2.934, NarTop10Accuracy=0.7408, over 7425.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7143, over 5939.21 frames. ], batch size: 22, lr: 2.43e-03
2024-08-06 22:18:57,320 INFO [trainer.py:765] (6/8) Epoch 35, batch 1700, train_loss[loss=2.753, NarTop10Accuracy=0.78, over 6285.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.714, over 5922.13 frames. ], batch size: 13, lr: 2.42e-03
2024-08-06 22:19:23,702 INFO [trainer.py:765] (6/8) Epoch 35, batch 1800, train_loss[loss=3.455, NarTop10Accuracy=0.6315, over 7428.00 frames. ], tot_loss[loss=3.05, NarTop10Accuracy=0.7152, over 5989.18 frames. ], batch size: 23, lr: 2.42e-03
2024-08-06 22:19:50,201 INFO [trainer.py:765] (6/8) Epoch 35, batch 1900, train_loss[loss=3.147, NarTop10Accuracy=0.6898, over 5898.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7152, over 6018.65 frames. ], batch size: 50, lr: 2.42e-03
2024-08-06 22:20:15,762 INFO [trainer.py:765] (6/8) Epoch 35, batch 2000, train_loss[loss=3.088, NarTop10Accuracy=0.7092, over 6621.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7166, over 5993.93 frames. ], batch size: 52, lr: 2.42e-03
2024-08-06 22:20:41,045 INFO [trainer.py:765] (6/8) Epoch 35, batch 2100, train_loss[loss=2.701, NarTop10Accuracy=0.7995, over 4761.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7154, over 5958.96 frames. ], batch size: 5, lr: 2.42e-03
2024-08-06 22:21:06,227 INFO [trainer.py:765] (6/8) Epoch 35, batch 2200, train_loss[loss=2.902, NarTop10Accuracy=0.7492, over 7374.00 frames. ], tot_loss[loss=3.053, NarTop10Accuracy=0.7149, over 6010.01 frames. ], batch size: 31, lr: 2.42e-03
2024-08-06 22:21:31,286 INFO [trainer.py:765] (6/8) Epoch 35, batch 2300, train_loss[loss=2.894, NarTop10Accuracy=0.7404, over 5631.00 frames. ], tot_loss[loss=3.056, NarTop10Accuracy=0.7146, over 6025.82 frames. ], batch size: 9, lr: 2.42e-03
2024-08-06 22:21:55,648 INFO [trainer.py:765] (6/8) Epoch 35, batch 2400, train_loss[loss=3.338, NarTop10Accuracy=0.6502, over 5331.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7149, over 5778.91 frames. ], batch size: 7, lr: 2.42e-03
2024-08-06 22:21:59,681 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 22:22:07,656 INFO [trainer.py:811] (6/8) Epoch 35, validation: loss=2.905, NarTop10Accuracy=0.7437, over 1905321.00 frames. 
2024-08-06 22:22:07,657 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 22:22:08,116 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 35, batch 2500, train_loss[loss=3.093, NarTop10Accuracy=0.7154, over 5142.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7192, over 5488.80 frames. ], batch size: 7, lr: 2.41e-03
2024-08-06 22:22:46,747 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 22:23:47,172 INFO [trainer.py:765] (6/8) Epoch 36, batch 100, train_loss[loss=3.225, NarTop10Accuracy=0.6761, over 6990.00 frames. ], tot_loss[loss=3.001, NarTop10Accuracy=0.7262, over 2378.31 frames. ], batch size: 31, lr: 2.38e-03
2024-08-06 22:24:22,494 INFO [trainer.py:765] (6/8) Epoch 36, batch 200, train_loss[loss=2.851, NarTop10Accuracy=0.7669, over 6759.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7209, over 3861.54 frames. ], batch size: 17, lr: 2.38e-03
2024-08-06 22:24:54,721 INFO [trainer.py:765] (6/8) Epoch 36, batch 300, train_loss[loss=3.311, NarTop10Accuracy=0.6648, over 7095.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7182, over 4667.47 frames. ], batch size: 22, lr: 2.37e-03
2024-08-06 22:25:29,276 INFO [trainer.py:765] (6/8) Epoch 36, batch 400, train_loss[loss=2.868, NarTop10Accuracy=0.7556, over 5241.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.7224, over 5134.06 frames. ], batch size: 7, lr: 2.37e-03
2024-08-06 22:26:01,818 INFO [trainer.py:765] (6/8) Epoch 36, batch 500, train_loss[loss=3.409, NarTop10Accuracy=0.646, over 6096.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7217, over 5429.81 frames. ], batch size: 11, lr: 2.37e-03
2024-08-06 22:26:35,025 INFO [trainer.py:765] (6/8) Epoch 36, batch 600, train_loss[loss=2.931, NarTop10Accuracy=0.7494, over 5679.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7222, over 5679.70 frames. ], batch size: 9, lr: 2.37e-03
2024-08-06 22:27:10,991 INFO [trainer.py:765] (6/8) Epoch 36, batch 700, train_loss[loss=3.235, NarTop10Accuracy=0.6876, over 4419.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7224, over 5732.32 frames. ], batch size: 5, lr: 2.37e-03
2024-08-06 22:27:44,915 INFO [trainer.py:765] (6/8) Epoch 36, batch 800, train_loss[loss=3.314, NarTop10Accuracy=0.6586, over 4965.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7197, over 5794.89 frames. ], batch size: 6, lr: 2.37e-03
2024-08-06 22:28:17,812 INFO [trainer.py:765] (6/8) Epoch 36, batch 900, train_loss[loss=2.767, NarTop10Accuracy=0.7696, over 6573.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7221, over 5815.37 frames. ], batch size: 14, lr: 2.37e-03
2024-08-06 22:28:56,984 INFO [trainer.py:765] (6/8) Epoch 36, batch 1000, train_loss[loss=3.411, NarTop10Accuracy=0.6441, over 6672.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7199, over 5918.68 frames. ], batch size: 14, lr: 2.37e-03
2024-08-06 22:29:29,364 INFO [trainer.py:765] (6/8) Epoch 36, batch 1100, train_loss[loss=2.963, NarTop10Accuracy=0.7313, over 6717.00 frames. ], tot_loss[loss=3.029, NarTop10Accuracy=0.7196, over 5952.48 frames. ], batch size: 17, lr: 2.36e-03
2024-08-06 22:30:05,681 INFO [trainer.py:765] (6/8) Epoch 36, batch 1200, train_loss[loss=2.991, NarTop10Accuracy=0.7272, over 7395.00 frames. ], tot_loss[loss=3.02, NarTop10Accuracy=0.7212, over 5936.13 frames. ], batch size: 31, lr: 2.36e-03
2024-08-06 22:30:42,576 INFO [trainer.py:765] (6/8) Epoch 36, batch 1300, train_loss[loss=2.796, NarTop10Accuracy=0.7689, over 5010.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7191, over 5991.38 frames. ], batch size: 6, lr: 2.36e-03
2024-08-06 22:31:15,939 INFO [trainer.py:765] (6/8) Epoch 36, batch 1400, train_loss[loss=3.059, NarTop10Accuracy=0.7172, over 5976.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7213, over 6023.50 frames. ], batch size: 11, lr: 2.36e-03
2024-08-06 22:31:43,749 INFO [trainer.py:765] (6/8) Epoch 36, batch 1500, train_loss[loss=3.529, NarTop10Accuracy=0.6193, over 6264.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7202, over 5944.27 frames. ], batch size: 50, lr: 2.36e-03
2024-08-06 22:32:11,460 INFO [trainer.py:765] (6/8) Epoch 36, batch 1600, train_loss[loss=3.341, NarTop10Accuracy=0.6455, over 7056.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.72, over 5931.04 frames. ], batch size: 22, lr: 2.36e-03
2024-08-06 22:32:38,109 INFO [trainer.py:765] (6/8) Epoch 36, batch 1700, train_loss[loss=3.324, NarTop10Accuracy=0.6505, over 6105.00 frames. ], tot_loss[loss=3.037, NarTop10Accuracy=0.7176, over 5908.60 frames. ], batch size: 13, lr: 2.36e-03
2024-08-06 22:33:04,554 INFO [trainer.py:765] (6/8) Epoch 36, batch 1800, train_loss[loss=3.079, NarTop10Accuracy=0.705, over 7089.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7188, over 5986.33 frames. ], batch size: 22, lr: 2.36e-03
2024-08-06 22:33:15,171 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 22:33:23,567 INFO [trainer.py:811] (6/8) Epoch 36, validation: loss=2.897, NarTop10Accuracy=0.7457, over 1905321.00 frames. 
2024-08-06 22:33:23,568 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 22:33:24,096 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 36, batch 1900, train_loss[loss=3.019, NarTop10Accuracy=0.7281, over 6189.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7181, over 6028.92 frames. ], batch size: 50, lr: 2.35e-03
2024-08-06 22:34:05,077 INFO [trainer.py:765] (6/8) Epoch 36, batch 2000, train_loss[loss=3.182, NarTop10Accuracy=0.6954, over 6069.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.719, over 6009.28 frames. ], batch size: 50, lr: 2.35e-03
2024-08-06 22:34:30,514 INFO [trainer.py:765] (6/8) Epoch 36, batch 2100, train_loss[loss=2.84, NarTop10Accuracy=0.7571, over 4896.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7198, over 5971.47 frames. ], batch size: 5, lr: 2.35e-03
2024-08-06 22:34:55,938 INFO [trainer.py:765] (6/8) Epoch 36, batch 2200, train_loss[loss=3.369, NarTop10Accuracy=0.651, over 7149.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7163, over 6005.18 frames. ], batch size: 31, lr: 2.35e-03
2024-08-06 22:35:21,145 INFO [trainer.py:765] (6/8) Epoch 36, batch 2300, train_loss[loss=3.365, NarTop10Accuracy=0.6495, over 5631.00 frames. ], tot_loss[loss=3.059, NarTop10Accuracy=0.7139, over 6009.96 frames. ], batch size: 9, lr: 2.35e-03
2024-08-06 22:35:45,600 INFO [trainer.py:765] (6/8) Epoch 36, batch 2400, train_loss[loss=3.136, NarTop10Accuracy=0.6861, over 5232.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.7168, over 5765.29 frames. ], batch size: 7, lr: 2.35e-03
2024-08-06 22:36:09,182 INFO [trainer.py:765] (6/8) Epoch 36, batch 2500, train_loss[loss=2.872, NarTop10Accuracy=0.7537, over 5268.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7205, over 5468.45 frames. ], batch size: 7, lr: 2.35e-03
2024-08-06 22:36:29,013 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 22:37:29,727 INFO [trainer.py:765] (6/8) Epoch 37, batch 100, train_loss[loss=2.873, NarTop10Accuracy=0.759, over 7284.00 frames. ], tot_loss[loss=3.051, NarTop10Accuracy=0.7149, over 2357.00 frames. ], batch size: 31, lr: 2.31e-03
2024-08-06 22:38:01,273 INFO [trainer.py:765] (6/8) Epoch 37, batch 200, train_loss[loss=2.902, NarTop10Accuracy=0.7505, over 6810.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7197, over 3859.61 frames. ], batch size: 17, lr: 2.31e-03
2024-08-06 22:38:35,956 INFO [trainer.py:765] (6/8) Epoch 37, batch 300, train_loss[loss=3.182, NarTop10Accuracy=0.6885, over 6888.00 frames. ], tot_loss[loss=3.022, NarTop10Accuracy=0.7206, over 4675.85 frames. ], batch size: 22, lr: 2.31e-03
2024-08-06 22:39:09,307 INFO [trainer.py:765] (6/8) Epoch 37, batch 400, train_loss[loss=2.735, NarTop10Accuracy=0.7772, over 5256.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7237, over 5121.50 frames. ], batch size: 7, lr: 2.31e-03
2024-08-06 22:39:43,862 INFO [trainer.py:765] (6/8) Epoch 37, batch 500, train_loss[loss=3.258, NarTop10Accuracy=0.6776, over 6093.00 frames. ], tot_loss[loss=3.007, NarTop10Accuracy=0.7241, over 5383.23 frames. ], batch size: 11, lr: 2.31e-03
2024-08-06 22:40:17,334 INFO [trainer.py:765] (6/8) Epoch 37, batch 600, train_loss[loss=2.626, NarTop10Accuracy=0.8029, over 5802.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7228, over 5653.19 frames. ], batch size: 9, lr: 2.31e-03
2024-08-06 22:40:51,616 INFO [trainer.py:765] (6/8) Epoch 37, batch 700, train_loss[loss=3.038, NarTop10Accuracy=0.7098, over 4368.00 frames. ], tot_loss[loss=3.043, NarTop10Accuracy=0.717, over 5725.37 frames. ], batch size: 5, lr: 2.30e-03
2024-08-06 22:41:30,565 INFO [trainer.py:765] (6/8) Epoch 37, batch 800, train_loss[loss=2.765, NarTop10Accuracy=0.7627, over 5160.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7173, over 5770.62 frames. ], batch size: 6, lr: 2.30e-03
2024-08-06 22:41:59,083 INFO [trainer.py:765] (6/8) Epoch 37, batch 900, train_loss[loss=2.798, NarTop10Accuracy=0.7671, over 6186.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7203, over 5787.07 frames. ], batch size: 13, lr: 2.30e-03
2024-08-06 22:42:38,268 INFO [trainer.py:765] (6/8) Epoch 37, batch 1000, train_loss[loss=3.271, NarTop10Accuracy=0.6637, over 6207.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7168, over 5887.45 frames. ], batch size: 13, lr: 2.30e-03
2024-08-06 22:43:15,907 INFO [trainer.py:765] (6/8) Epoch 37, batch 1100, train_loss[loss=3.142, NarTop10Accuracy=0.6991, over 6870.00 frames. ], tot_loss[loss=3.044, NarTop10Accuracy=0.7159, over 5926.83 frames. ], batch size: 17, lr: 2.30e-03
2024-08-06 22:43:47,740 INFO [trainer.py:765] (6/8) Epoch 37, batch 1200, train_loss[loss=2.853, NarTop10Accuracy=0.7556, over 7122.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7154, over 5923.16 frames. ], batch size: 31, lr: 2.30e-03
2024-08-06 22:44:11,755 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 22:44:20,075 INFO [trainer.py:811] (6/8) Epoch 37, validation: loss=2.92, NarTop10Accuracy=0.7407, over 1905321.00 frames. 
2024-08-06 22:44:20,076 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 22:44:20,605 INFO [optim.py:386] (6/8) 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 22:44:32,782 INFO [trainer.py:765] (6/8) Epoch 37, batch 1300, train_loss[loss=2.669, NarTop10Accuracy=0.7893, over 4296.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7193, over 5993.98 frames. ], batch size: 5, lr: 2.30e-03
2024-08-06 22:45:10,386 INFO [trainer.py:765] (6/8) Epoch 37, batch 1400, train_loss[loss=2.72, NarTop10Accuracy=0.7837, over 6057.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7197, over 6012.99 frames. ], batch size: 11, lr: 2.30e-03
2024-08-06 22:45:40,511 INFO [trainer.py:765] (6/8) Epoch 37, batch 1500, train_loss[loss=2.9, NarTop10Accuracy=0.7446, over 6279.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.7185, over 5947.38 frames. ], batch size: 50, lr: 2.29e-03
2024-08-06 22:46:08,436 INFO [trainer.py:765] (6/8) Epoch 37, batch 1600, train_loss[loss=3.441, NarTop10Accuracy=0.6325, over 7272.00 frames. ], tot_loss[loss=3.041, NarTop10Accuracy=0.7171, over 5938.36 frames. ], batch size: 22, lr: 2.29e-03
2024-08-06 22:46:35,186 INFO [trainer.py:765] (6/8) Epoch 37, batch 1700, train_loss[loss=3.309, NarTop10Accuracy=0.662, over 6714.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.719, over 5937.26 frames. ], batch size: 14, lr: 2.29e-03
2024-08-06 22:47:01,791 INFO [trainer.py:765] (6/8) Epoch 37, batch 1800, train_loss[loss=2.836, NarTop10Accuracy=0.7613, over 7281.00 frames. ], tot_loss[loss=3.027, NarTop10Accuracy=0.7198, over 5991.81 frames. ], batch size: 23, lr: 2.29e-03
2024-08-06 22:47:28,310 INFO [trainer.py:765] (6/8) Epoch 37, batch 1900, train_loss[loss=3.003, NarTop10Accuracy=0.7243, over 5886.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.7186, over 6032.61 frames. ], batch size: 50, lr: 2.29e-03
2024-08-06 22:47:53,923 INFO [trainer.py:765] (6/8) Epoch 37, batch 2000, train_loss[loss=3.213, NarTop10Accuracy=0.6839, over 5658.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7199, over 6015.19 frames. ], batch size: 50, lr: 2.29e-03
2024-08-06 22:48:19,324 INFO [trainer.py:765] (6/8) Epoch 37, batch 2100, train_loss[loss=2.979, NarTop10Accuracy=0.7232, over 3942.00 frames. ], tot_loss[loss=3.035, NarTop10Accuracy=0.718, over 5975.88 frames. ], batch size: 4, lr: 2.29e-03
2024-08-06 22:48:44,706 INFO [trainer.py:765] (6/8) Epoch 37, batch 2200, train_loss[loss=2.932, NarTop10Accuracy=0.744, over 7131.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7156, over 6011.73 frames. ], batch size: 31, lr: 2.29e-03
2024-08-06 22:49:09,911 INFO [trainer.py:765] (6/8) Epoch 37, batch 2300, train_loss[loss=2.732, NarTop10Accuracy=0.7856, over 5760.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7167, over 6043.72 frames. ], batch size: 9, lr: 2.29e-03
2024-08-06 22:49:34,317 INFO [trainer.py:765] (6/8) Epoch 37, batch 2400, train_loss[loss=3.195, NarTop10Accuracy=0.6837, over 5157.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.7197, over 5762.07 frames. ], batch size: 7, lr: 2.28e-03
2024-08-06 22:49:57,859 INFO [trainer.py:765] (6/8) Epoch 37, batch 2500, train_loss[loss=3.243, NarTop10Accuracy=0.6834, over 4995.00 frames. ], tot_loss[loss=2.992, NarTop10Accuracy=0.7267, over 5471.08 frames. ], batch size: 7, lr: 2.28e-03
2024-08-06 22:50:17,882 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 22:51:16,151 INFO [trainer.py:765] (6/8) Epoch 38, batch 100, train_loss[loss=3.006, NarTop10Accuracy=0.7211, over 7269.00 frames. ], tot_loss[loss=3.011, NarTop10Accuracy=0.7233, over 2354.38 frames. ], batch size: 31, lr: 2.25e-03
2024-08-06 22:51:53,014 INFO [trainer.py:765] (6/8) Epoch 38, batch 200, train_loss[loss=3.243, NarTop10Accuracy=0.6791, over 6714.00 frames. ], tot_loss[loss=3.015, NarTop10Accuracy=0.7228, over 3859.93 frames. ], batch size: 17, lr: 2.25e-03
2024-08-06 22:52:25,201 INFO [trainer.py:765] (6/8) Epoch 38, batch 300, train_loss[loss=2.869, NarTop10Accuracy=0.7441, over 7083.00 frames. ], tot_loss[loss=3.031, NarTop10Accuracy=0.7194, over 4667.82 frames. ], batch size: 22, lr: 2.25e-03
2024-08-06 22:52:55,627 INFO [trainer.py:765] (6/8) Epoch 38, batch 400, train_loss[loss=3.275, NarTop10Accuracy=0.6714, over 5007.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7219, over 5115.46 frames. ], batch size: 7, lr: 2.25e-03
2024-08-06 22:53:32,227 INFO [trainer.py:765] (6/8) Epoch 38, batch 500, train_loss[loss=2.788, NarTop10Accuracy=0.7643, over 6069.00 frames. ], tot_loss[loss=2.99, NarTop10Accuracy=0.7272, over 5408.20 frames. ], batch size: 11, lr: 2.25e-03
2024-08-06 22:54:05,497 INFO [trainer.py:765] (6/8) Epoch 38, batch 600, train_loss[loss=3.266, NarTop10Accuracy=0.6713, over 5676.00 frames. ], tot_loss[loss=2.999, NarTop10Accuracy=0.7256, over 5668.65 frames. ], batch size: 9, lr: 2.24e-03
2024-08-06 22:54:36,002 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 22:54:43,918 INFO [trainer.py:811] (6/8) Epoch 38, validation: loss=2.939, NarTop10Accuracy=0.7369, over 1905321.00 frames. 
2024-08-06 22:54:43,919 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 22:54:44,427 INFO [optim.py:386] (6/8) Clipping_scale=2.0, grad-norm quartiles 1.880e+02 2.313e+02 2.478e+02 2.663e+02 7.254e+02, threshold=4.957e+02, percent-clipped=0.3
2024-08-06 22:54:46,659 INFO [trainer.py:765] (6/8) Epoch 38, batch 700, train_loss[loss=2.764, NarTop10Accuracy=0.7678, over 4938.00 frames. ], tot_loss[loss=2.999, NarTop10Accuracy=0.7255, over 5738.21 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:55:24,938 INFO [trainer.py:765] (6/8) Epoch 38, batch 800, train_loss[loss=2.888, NarTop10Accuracy=0.7472, over 5073.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7225, over 5776.81 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:55:59,704 INFO [trainer.py:765] (6/8) Epoch 38, batch 900, train_loss[loss=2.728, NarTop10Accuracy=0.7759, over 6333.00 frames. ], tot_loss[loss=3.01, NarTop10Accuracy=0.7227, over 5800.13 frames. ], batch size: 13, lr: 2.24e-03
2024-08-06 22:56:32,090 INFO [trainer.py:765] (6/8) Epoch 38, batch 1000, train_loss[loss=3.406, NarTop10Accuracy=0.6439, over 6684.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7223, over 5891.02 frames. ], batch size: 14, lr: 2.24e-03
2024-08-06 22:57:08,991 INFO [trainer.py:765] (6/8) Epoch 38, batch 1100, train_loss[loss=3.12, NarTop10Accuracy=0.6909, over 6831.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7194, over 5919.81 frames. ], batch size: 17, lr: 2.24e-03
2024-08-06 22:57:42,663 INFO [trainer.py:765] (6/8) Epoch 38, batch 1200, train_loss[loss=2.868, NarTop10Accuracy=0.7526, over 7149.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7194, over 5925.33 frames. ], batch size: 31, lr: 2.24e-03
2024-08-06 22:58:16,546 INFO [trainer.py:765] (6/8) Epoch 38, batch 1300, train_loss[loss=3.289, NarTop10Accuracy=0.6712, over 5106.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.7191, over 5989.40 frames. ], batch size: 6, lr: 2.24e-03
2024-08-06 22:58:49,810 INFO [trainer.py:765] (6/8) Epoch 38, batch 1400, train_loss[loss=2.842, NarTop10Accuracy=0.7558, over 6153.00 frames. ], tot_loss[loss=3.048, NarTop10Accuracy=0.7152, over 6001.23 frames. ], batch size: 11, lr: 2.23e-03
2024-08-06 22:59:22,854 INFO [trainer.py:765] (6/8) Epoch 38, batch 1500, train_loss[loss=3.472, NarTop10Accuracy=0.6353, over 6321.00 frames. ], tot_loss[loss=3.033, NarTop10Accuracy=0.718, over 5924.26 frames. ], batch size: 50, lr: 2.23e-03
2024-08-06 22:59:50,644 INFO [trainer.py:765] (6/8) Epoch 38, batch 1600, train_loss[loss=3.304, NarTop10Accuracy=0.6613, over 6999.00 frames. ], tot_loss[loss=3.042, NarTop10Accuracy=0.7165, over 5917.85 frames. ], batch size: 22, lr: 2.23e-03
2024-08-06 23:00:17,315 INFO [trainer.py:765] (6/8) Epoch 38, batch 1700, train_loss[loss=2.873, NarTop10Accuracy=0.7458, over 6213.00 frames. ], tot_loss[loss=3.055, NarTop10Accuracy=0.7138, over 5902.33 frames. ], batch size: 13, lr: 2.23e-03
2024-08-06 23:00:43,764 INFO [trainer.py:765] (6/8) Epoch 38, batch 1800, train_loss[loss=3.133, NarTop10Accuracy=0.6893, over 7050.00 frames. ], tot_loss[loss=3.049, NarTop10Accuracy=0.7153, over 5962.08 frames. ], batch size: 22, lr: 2.23e-03
2024-08-06 23:01:10,192 INFO [trainer.py:765] (6/8) Epoch 38, batch 1900, train_loss[loss=3.442, NarTop10Accuracy=0.6355, over 6081.00 frames. ], tot_loss[loss=3.052, NarTop10Accuracy=0.7147, over 6022.31 frames. ], batch size: 51, lr: 2.23e-03
2024-08-06 23:01:35,683 INFO [trainer.py:765] (6/8) Epoch 38, batch 2000, train_loss[loss=3.304, NarTop10Accuracy=0.6668, over 6039.00 frames. ], tot_loss[loss=3.047, NarTop10Accuracy=0.7157, over 5987.17 frames. ], batch size: 52, lr: 2.23e-03
2024-08-06 23:02:01,050 INFO [trainer.py:765] (6/8) Epoch 38, batch 2100, train_loss[loss=2.847, NarTop10Accuracy=0.7505, over 4905.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7174, over 5976.48 frames. ], batch size: 5, lr: 2.23e-03
2024-08-06 23:02:26,315 INFO [trainer.py:765] (6/8) Epoch 38, batch 2200, train_loss[loss=2.727, NarTop10Accuracy=0.7791, over 7329.00 frames. ], tot_loss[loss=3.038, NarTop10Accuracy=0.7176, over 6020.98 frames. ], batch size: 31, lr: 2.23e-03
2024-08-06 23:02:51,420 INFO [trainer.py:765] (6/8) Epoch 38, batch 2300, train_loss[loss=2.807, NarTop10Accuracy=0.7629, over 5781.00 frames. ], tot_loss[loss=3.045, NarTop10Accuracy=0.7165, over 6034.18 frames. ], batch size: 9, lr: 2.22e-03
2024-08-06 23:03:16,349 INFO [trainer.py:765] (6/8) Epoch 38, batch 2400, train_loss[loss=2.684, NarTop10Accuracy=0.7859, over 5190.00 frames. ], tot_loss[loss=3.03, NarTop10Accuracy=0.719, over 5797.06 frames. ], batch size: 7, lr: 2.22e-03
2024-08-06 23:03:39,823 INFO [trainer.py:765] (6/8) Epoch 38, batch 2500, train_loss[loss=3.229, NarTop10Accuracy=0.6767, over 4986.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7231, over 5466.14 frames. ], batch size: 7, lr: 2.22e-03
2024-08-06 23:03:59,661 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 23:04:58,940 INFO [trainer.py:765] (6/8) Epoch 39, batch 100, train_loss[loss=3.227, NarTop10Accuracy=0.6815, over 7251.00 frames. ], tot_loss[loss=2.976, NarTop10Accuracy=0.731, over 2372.46 frames. ], batch size: 31, lr: 2.19e-03
2024-08-06 23:05:03,468 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 23:05:11,563 INFO [trainer.py:811] (6/8) Epoch 39, validation: loss=2.9, NarTop10Accuracy=0.7445, over 1905321.00 frames. 
2024-08-06 23:05:11,564 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 23:05:12,137 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 39, batch 200, train_loss[loss=2.77, NarTop10Accuracy=0.7739, over 6819.00 frames. ], tot_loss[loss=2.995, NarTop10Accuracy=0.7271, over 3858.76 frames. ], batch size: 17, lr: 2.19e-03
2024-08-06 23:06:17,293 INFO [trainer.py:765] (6/8) Epoch 39, batch 300, train_loss[loss=2.983, NarTop10Accuracy=0.7278, over 6966.00 frames. ], tot_loss[loss=2.99, NarTop10Accuracy=0.7276, over 4666.83 frames. ], batch size: 22, lr: 2.19e-03
2024-08-06 23:06:48,275 INFO [trainer.py:765] (6/8) Epoch 39, batch 400, train_loss[loss=2.919, NarTop10Accuracy=0.7413, over 5262.00 frames. ], tot_loss[loss=2.981, NarTop10Accuracy=0.7292, over 5098.07 frames. ], batch size: 7, lr: 2.19e-03
2024-08-06 23:07:19,175 INFO [trainer.py:765] (6/8) Epoch 39, batch 500, train_loss[loss=3.402, NarTop10Accuracy=0.6376, over 6036.00 frames. ], tot_loss[loss=2.996, NarTop10Accuracy=0.726, over 5360.48 frames. ], batch size: 11, lr: 2.19e-03
2024-08-06 23:07:52,563 INFO [trainer.py:765] (6/8) Epoch 39, batch 600, train_loss[loss=2.812, NarTop10Accuracy=0.7649, over 5610.00 frames. ], tot_loss[loss=3.01, NarTop10Accuracy=0.7234, over 5636.22 frames. ], batch size: 9, lr: 2.19e-03
2024-08-06 23:08:33,694 INFO [trainer.py:765] (6/8) Epoch 39, batch 700, train_loss[loss=3.347, NarTop10Accuracy=0.6572, over 5154.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7207, over 5706.52 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:09:05,861 INFO [trainer.py:765] (6/8) Epoch 39, batch 800, train_loss[loss=2.814, NarTop10Accuracy=0.7623, over 4305.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7204, over 5787.68 frames. ], batch size: 5, lr: 2.18e-03
2024-08-06 23:09:38,865 INFO [trainer.py:765] (6/8) Epoch 39, batch 900, train_loss[loss=3.303, NarTop10Accuracy=0.6618, over 6663.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.7216, over 5818.56 frames. ], batch size: 14, lr: 2.18e-03
2024-08-06 23:10:18,460 INFO [trainer.py:765] (6/8) Epoch 39, batch 1000, train_loss[loss=2.859, NarTop10Accuracy=0.7566, over 6222.00 frames. ], tot_loss[loss=3.014, NarTop10Accuracy=0.7224, over 5909.29 frames. ], batch size: 13, lr: 2.18e-03
2024-08-06 23:10:53,934 INFO [trainer.py:765] (6/8) Epoch 39, batch 1100, train_loss[loss=2.854, NarTop10Accuracy=0.7524, over 6813.00 frames. ], tot_loss[loss=3.036, NarTop10Accuracy=0.718, over 5934.94 frames. ], batch size: 17, lr: 2.18e-03
2024-08-06 23:11:27,822 INFO [trainer.py:765] (6/8) Epoch 39, batch 1200, train_loss[loss=2.928, NarTop10Accuracy=0.7437, over 7161.00 frames. ], tot_loss[loss=3.017, NarTop10Accuracy=0.7217, over 5928.40 frames. ], batch size: 31, lr: 2.18e-03
2024-08-06 23:12:07,252 INFO [trainer.py:765] (6/8) Epoch 39, batch 1300, train_loss[loss=2.741, NarTop10Accuracy=0.7781, over 5073.00 frames. ], tot_loss[loss=3.003, NarTop10Accuracy=0.7244, over 6006.87 frames. ], batch size: 6, lr: 2.18e-03
2024-08-06 23:12:39,301 INFO [trainer.py:765] (6/8) Epoch 39, batch 1400, train_loss[loss=2.924, NarTop10Accuracy=0.736, over 5958.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7225, over 6021.92 frames. ], batch size: 11, lr: 2.18e-03
2024-08-06 23:13:09,756 INFO [trainer.py:765] (6/8) Epoch 39, batch 1500, train_loss[loss=3.615, NarTop10Accuracy=0.6038, over 6357.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7225, over 5954.15 frames. ], batch size: 50, lr: 2.18e-03
2024-08-06 23:13:37,586 INFO [trainer.py:765] (6/8) Epoch 39, batch 1600, train_loss[loss=2.864, NarTop10Accuracy=0.7472, over 6930.00 frames. ], tot_loss[loss=3.004, NarTop10Accuracy=0.7243, over 5931.97 frames. ], batch size: 22, lr: 2.17e-03
2024-08-06 23:14:04,219 INFO [trainer.py:765] (6/8) Epoch 39, batch 1700, train_loss[loss=3.39, NarTop10Accuracy=0.6503, over 6156.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.7184, over 5900.92 frames. ], batch size: 13, lr: 2.17e-03
2024-08-06 23:14:30,767 INFO [trainer.py:765] (6/8) Epoch 39, batch 1800, train_loss[loss=2.864, NarTop10Accuracy=0.7569, over 7170.00 frames. ], tot_loss[loss=3.034, NarTop10Accuracy=0.718, over 5981.18 frames. ], batch size: 22, lr: 2.17e-03
2024-08-06 23:14:57,179 INFO [trainer.py:765] (6/8) Epoch 39, batch 1900, train_loss[loss=3.002, NarTop10Accuracy=0.7307, over 6312.00 frames. ], tot_loss[loss=3.046, NarTop10Accuracy=0.7159, over 6026.16 frames. ], batch size: 51, lr: 2.17e-03
2024-08-06 23:15:22,750 INFO [trainer.py:765] (6/8) Epoch 39, batch 2000, train_loss[loss=3.386, NarTop10Accuracy=0.6476, over 6645.00 frames. ], tot_loss[loss=3.026, NarTop10Accuracy=0.72, over 5982.67 frames. ], batch size: 51, lr: 2.17e-03
2024-08-06 23:15:48,060 INFO [trainer.py:765] (6/8) Epoch 39, batch 2100, train_loss[loss=3.239, NarTop10Accuracy=0.6744, over 3882.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7204, over 5962.40 frames. ], batch size: 4, lr: 2.17e-03
2024-08-06 23:15:51,870 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 23:16:02,156 INFO [trainer.py:811] (6/8) Epoch 39, validation: loss=2.85, NarTop10Accuracy=0.7552, over 1905321.00 frames. 
2024-08-06 23:16:02,156 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 23:16:02,645 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 39, batch 2200, train_loss[loss=3.225, NarTop10Accuracy=0.6891, over 7137.00 frames. ], tot_loss[loss=3.028, NarTop10Accuracy=0.7194, over 6012.78 frames. ], batch size: 31, lr: 2.17e-03
2024-08-06 23:16:48,847 INFO [trainer.py:765] (6/8) Epoch 39, batch 2300, train_loss[loss=2.54, NarTop10Accuracy=0.8173, over 5643.00 frames. ], tot_loss[loss=3.039, NarTop10Accuracy=0.7175, over 6030.73 frames. ], batch size: 9, lr: 2.17e-03
2024-08-06 23:17:13,136 INFO [trainer.py:765] (6/8) Epoch 39, batch 2400, train_loss[loss=2.675, NarTop10Accuracy=0.7983, over 5238.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7233, over 5776.75 frames. ], batch size: 7, lr: 2.17e-03
2024-08-06 23:17:36,712 INFO [trainer.py:765] (6/8) Epoch 39, batch 2500, train_loss[loss=2.96, NarTop10Accuracy=0.7377, over 5148.00 frames. ], tot_loss[loss=2.989, NarTop10Accuracy=0.727, over 5463.48 frames. ], batch size: 7, lr: 2.16e-03
2024-08-06 23:17:56,481 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 23:18:48,946 INFO [trainer.py:765] (6/8) Epoch 40, batch 100, train_loss[loss=2.992, NarTop10Accuracy=0.7267, over 7323.00 frames. ], tot_loss[loss=3.006, NarTop10Accuracy=0.725, over 2369.38 frames. ], batch size: 31, lr: 2.14e-03
2024-08-06 23:19:23,035 INFO [trainer.py:765] (6/8) Epoch 40, batch 200, train_loss[loss=2.826, NarTop10Accuracy=0.7586, over 6672.00 frames. ], tot_loss[loss=3.001, NarTop10Accuracy=0.726, over 3863.52 frames. ], batch size: 17, lr: 2.13e-03
2024-08-06 23:19:57,187 INFO [trainer.py:765] (6/8) Epoch 40, batch 300, train_loss[loss=2.739, NarTop10Accuracy=0.7779, over 7113.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.7232, over 4653.26 frames. ], batch size: 22, lr: 2.13e-03
2024-08-06 23:20:30,182 INFO [trainer.py:765] (6/8) Epoch 40, batch 400, train_loss[loss=2.84, NarTop10Accuracy=0.7514, over 5445.00 frames. ], tot_loss[loss=3.013, NarTop10Accuracy=0.723, over 5124.71 frames. ], batch size: 7, lr: 2.13e-03
2024-08-06 23:21:00,250 INFO [trainer.py:765] (6/8) Epoch 40, batch 500, train_loss[loss=2.633, NarTop10Accuracy=0.7876, over 6048.00 frames. ], tot_loss[loss=3.012, NarTop10Accuracy=0.723, over 5386.32 frames. ], batch size: 11, lr: 2.13e-03
2024-08-06 23:21:34,881 INFO [trainer.py:765] (6/8) Epoch 40, batch 600, train_loss[loss=2.96, NarTop10Accuracy=0.7416, over 5748.00 frames. ], tot_loss[loss=3.002, NarTop10Accuracy=0.7248, over 5647.05 frames. ], batch size: 9, lr: 2.13e-03
2024-08-06 23:22:11,097 INFO [trainer.py:765] (6/8) Epoch 40, batch 700, train_loss[loss=3.017, NarTop10Accuracy=0.7359, over 5190.00 frames. ], tot_loss[loss=3.008, NarTop10Accuracy=0.7238, over 5727.68 frames. ], batch size: 6, lr: 2.13e-03
2024-08-06 23:22:44,755 INFO [trainer.py:765] (6/8) Epoch 40, batch 800, train_loss[loss=2.646, NarTop10Accuracy=0.7968, over 5253.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7203, over 5785.13 frames. ], batch size: 6, lr: 2.13e-03
2024-08-06 23:23:16,636 INFO [trainer.py:765] (6/8) Epoch 40, batch 900, train_loss[loss=3.327, NarTop10Accuracy=0.6602, over 6186.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7204, over 5789.27 frames. ], batch size: 13, lr: 2.13e-03
2024-08-06 23:23:55,591 INFO [trainer.py:765] (6/8) Epoch 40, batch 1000, train_loss[loss=3.255, NarTop10Accuracy=0.6706, over 6177.00 frames. ], tot_loss[loss=3.025, NarTop10Accuracy=0.7199, over 5892.79 frames. ], batch size: 13, lr: 2.13e-03
2024-08-06 23:24:30,208 INFO [trainer.py:765] (6/8) Epoch 40, batch 1100, train_loss[loss=2.729, NarTop10Accuracy=0.7792, over 6849.00 frames. ], tot_loss[loss=3.021, NarTop10Accuracy=0.7209, over 5933.04 frames. ], batch size: 17, lr: 2.12e-03
2024-08-06 23:25:03,090 INFO [trainer.py:765] (6/8) Epoch 40, batch 1200, train_loss[loss=2.885, NarTop10Accuracy=0.7489, over 7473.00 frames. ], tot_loss[loss=3.016, NarTop10Accuracy=0.722, over 5909.94 frames. ], batch size: 31, lr: 2.12e-03
2024-08-06 23:25:41,842 INFO [trainer.py:765] (6/8) Epoch 40, batch 1300, train_loss[loss=2.741, NarTop10Accuracy=0.7833, over 5004.00 frames. ], tot_loss[loss=3.011, NarTop10Accuracy=0.7229, over 5987.59 frames. ], batch size: 6, lr: 2.12e-03
2024-08-06 23:26:13,384 INFO [trainer.py:765] (6/8) Epoch 40, batch 1400, train_loss[loss=2.757, NarTop10Accuracy=0.7715, over 6159.00 frames. ], tot_loss[loss=3.023, NarTop10Accuracy=0.7207, over 6011.54 frames. ], batch size: 11, lr: 2.12e-03
2024-08-06 23:26:43,377 INFO [trainer.py:765] (6/8) Epoch 40, batch 1500, train_loss[loss=3.284, NarTop10Accuracy=0.6697, over 5988.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7234, over 5948.77 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:26:54,419 INFO [trainer.py:803] (6/8) Computing validation loss
2024-08-06 23:27:02,676 INFO [trainer.py:811] (6/8) Epoch 40, validation: loss=2.86, NarTop10Accuracy=0.7522, over 1905321.00 frames. 
2024-08-06 23:27:02,677 INFO [trainer.py:814] (6/8) Maximum memory allocated so far is 30374MB
2024-08-06 23:27:03,156 INFO [optim.py:386] (6/8) 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] (6/8) Epoch 40, batch 1600, train_loss[loss=2.914, NarTop10Accuracy=0.7456, over 7050.00 frames. ], tot_loss[loss=3.018, NarTop10Accuracy=0.7216, over 5932.89 frames. ], batch size: 22, lr: 2.12e-03
2024-08-06 23:27:46,056 INFO [trainer.py:765] (6/8) Epoch 40, batch 1700, train_loss[loss=3.251, NarTop10Accuracy=0.6697, over 6609.00 frames. ], tot_loss[loss=3.019, NarTop10Accuracy=0.721, over 5916.77 frames. ], batch size: 14, lr: 2.12e-03
2024-08-06 23:28:12,579 INFO [trainer.py:765] (6/8) Epoch 40, batch 1800, train_loss[loss=3.029, NarTop10Accuracy=0.7215, over 7074.00 frames. ], tot_loss[loss=3.003, NarTop10Accuracy=0.7244, over 5993.07 frames. ], batch size: 22, lr: 2.12e-03
2024-08-06 23:28:38,909 INFO [trainer.py:765] (6/8) Epoch 40, batch 1900, train_loss[loss=3.103, NarTop10Accuracy=0.704, over 6453.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7233, over 6025.05 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:29:04,444 INFO [trainer.py:765] (6/8) Epoch 40, batch 2000, train_loss[loss=3.597, NarTop10Accuracy=0.6041, over 6372.00 frames. ], tot_loss[loss=3.007, NarTop10Accuracy=0.7234, over 6007.21 frames. ], batch size: 50, lr: 2.12e-03
2024-08-06 23:29:29,750 INFO [trainer.py:765] (6/8) Epoch 40, batch 2100, train_loss[loss=2.659, NarTop10Accuracy=0.794, over 4896.00 frames. ], tot_loss[loss=3.009, NarTop10Accuracy=0.7233, over 5988.10 frames. ], batch size: 5, lr: 2.11e-03
2024-08-06 23:29:54,940 INFO [trainer.py:765] (6/8) Epoch 40, batch 2200, train_loss[loss=3.252, NarTop10Accuracy=0.6788, over 7203.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7202, over 6013.90 frames. ], batch size: 31, lr: 2.11e-03
2024-08-06 23:30:20,012 INFO [trainer.py:765] (6/8) Epoch 40, batch 2300, train_loss[loss=2.954, NarTop10Accuracy=0.7343, over 5679.00 frames. ], tot_loss[loss=3.032, NarTop10Accuracy=0.719, over 6010.38 frames. ], batch size: 9, lr: 2.11e-03
2024-08-06 23:30:44,296 INFO [trainer.py:765] (6/8) Epoch 40, batch 2400, train_loss[loss=2.799, NarTop10Accuracy=0.7685, over 5148.00 frames. ], tot_loss[loss=3.024, NarTop10Accuracy=0.7206, over 5761.50 frames. ], batch size: 7, lr: 2.11e-03
2024-08-06 23:31:07,738 INFO [trainer.py:765] (6/8) Epoch 40, batch 2500, train_loss[loss=2.996, NarTop10Accuracy=0.7235, over 5238.00 frames. ], tot_loss[loss=2.982, NarTop10Accuracy=0.7287, over 5463.32 frames. ], batch size: 7, lr: 2.11e-03
2024-08-06 23:31:27,899 INFO [trainer.py:650] (6/8) Reaches end of dataloader.
2024-08-06 23:31:27,901 INFO [trainer.py:1069] (6/8) Done!