2022-05-03 11:40:27,490 INFO [train.py:775] (4/8) Training started
2022-05-03 11:40:27,490 INFO [train.py:785] (4/8) Device: cuda:4
2022-05-03 11:40:27,492 INFO [train.py:794] (4/8) {'best_train_loss': inf, 'best_valid_loss': inf, 'best_train_epoch': -1, 'best_valid_epoch': -1, 'batch_idx_train': 0, 'log_interval': 50, 'reset_interval': 200, 'valid_interval': 3000, 'feature_dim': 80, 'subsampling_factor': 4, 'encoder_dim': 512, 'nhead': 8, 'dim_feedforward': 2048, 'num_encoder_layers': 12, 'decoder_dim': 512, 'joiner_dim': 512, 'model_warm_step': 3000, 'env_info': {'k2-version': '1.14', 'k2-build-type': 'Debug', 'k2-with-cuda': True, 'k2-git-sha1': '1b29f0a946f50186aaa82df46a59f492ade9692b', 'k2-git-date': 'Tue Apr 12 20:46:49 2022', 'lhotse-version': '1.1.0', 'torch-version': '1.10.1+cu111', 'torch-cuda-available': True, 'torch-cuda-version': '11.1', 'python-version': '3.8', 'icefall-git-branch': 'spgi', 'icefall-git-sha1': 'e2e5c77-dirty', 'icefall-git-date': 'Mon May 2 14:38:25 2022', 'icefall-path': '/exp/draj/mini_scale_2022/icefall', 'k2-path': '/exp/draj/mini_scale_2022/k2/k2/python/k2/__init__.py', 'lhotse-path': '/exp/draj/mini_scale_2022/lhotse/lhotse/__init__.py', 'hostname': 'r8n04', 'IP address': '10.1.8.4'}, 'world_size': 8, 'master_port': 12354, 'tensorboard': True, 'num_epochs': 20, 'start_epoch': 0, 'start_batch': 0, 'exp_dir': PosixPath('pruned_transducer_stateless2/exp/v2'), 'bpe_model': 'data/lang_bpe_500/bpe.model', 'initial_lr': 0.003, 'lr_batches': 5000, 'lr_epochs': 4, 'context_size': 2, 'prune_range': 5, 'lm_scale': 0.25, 'am_scale': 0.0, 'simple_loss_scale': 0.5, 'seed': 42, 'print_diagnostics': False, 'save_every_n': 8000, 'keep_last_k': 10, 'use_fp16': True, 'manifest_dir': PosixPath('data/manifests'), 'enable_musan': True, 'concatenate_cuts': False, 'duration_factor': 1.0, 'gap': 1.0, 'max_duration': 200, 'num_buckets': 30, 'on_the_fly_feats': False, 'shuffle': True, 'num_workers': 8, 'enable_spec_aug': True, 'spec_aug_time_warp_factor': 80, 'blank_id': 0, 'vocab_size': 500}
2022-05-03 11:40:27,492 INFO [train.py:796] (4/8) About to create model
2022-05-03 11:40:27,845 INFO [train.py:800] (4/8) Number of model parameters: 78648040
2022-05-03 11:40:33,493 INFO [train.py:806] (4/8) Using DDP
2022-05-03 11:40:34,136 INFO [asr_datamodule.py:321] (4/8) About to get SPGISpeech train cuts
2022-05-03 11:40:34,138 INFO [asr_datamodule.py:179] (4/8) About to get Musan cuts
2022-05-03 11:40:35,873 INFO [asr_datamodule.py:184] (4/8) Enable MUSAN
2022-05-03 11:40:35,873 INFO [asr_datamodule.py:207] (4/8) Enable SpecAugment
2022-05-03 11:40:35,873 INFO [asr_datamodule.py:208] (4/8) Time warp factor: 80
2022-05-03 11:40:35,873 INFO [asr_datamodule.py:221] (4/8) About to create train dataset
2022-05-03 11:40:35,873 INFO [asr_datamodule.py:234] (4/8) Using DynamicBucketingSampler.
2022-05-03 11:40:36,266 INFO [asr_datamodule.py:242] (4/8) About to create train dataloader
2022-05-03 11:40:36,267 INFO [asr_datamodule.py:326] (4/8) About to get SPGISpeech dev cuts
2022-05-03 11:40:36,267 INFO [asr_datamodule.py:274] (4/8) About to create dev dataset
2022-05-03 11:40:36,413 INFO [asr_datamodule.py:289] (4/8) About to create dev dataloader
2022-05-03 11:41:08,011 INFO [train.py:715] (4/8) Epoch 0, batch 0, loss[loss=3.368, simple_loss=6.736, pruned_loss=5.868, over 4935.00 frames.], tot_loss[loss=3.368, simple_loss=6.736, pruned_loss=5.868, over 4935.00 frames.], batch size: 21, lr: 3.00e-03
2022-05-03 11:41:08,404 INFO [distributed.py:874] (4/8) Reducer buckets have been rebuilt in this iteration.
2022-05-03 11:41:46,314 INFO [train.py:715] (4/8) Epoch 0, batch 50, loss[loss=0.4684, simple_loss=0.9367, pruned_loss=6.832, over 4838.00 frames.], tot_loss[loss=1.319, simple_loss=2.637, pruned_loss=6.459, over 219586.68 frames.], batch size: 13, lr: 3.00e-03
2022-05-03 11:42:25,577 INFO [train.py:715] (4/8) Epoch 0, batch 100, loss[loss=0.3639, simple_loss=0.7279, pruned_loss=6.622, over 4866.00 frames.], tot_loss[loss=0.8179, simple_loss=1.636, pruned_loss=6.578, over 386111.44 frames.], batch size: 20, lr: 3.00e-03
2022-05-03 11:43:04,756 INFO [train.py:715] (4/8) Epoch 0, batch 150, loss[loss=0.3352, simple_loss=0.6704, pruned_loss=6.585, over 4888.00 frames.], tot_loss[loss=0.6284, simple_loss=1.257, pruned_loss=6.585, over 516248.88 frames.], batch size: 22, lr: 3.00e-03
2022-05-03 11:43:43,121 INFO [train.py:715] (4/8) Epoch 0, batch 200, loss[loss=0.3142, simple_loss=0.6283, pruned_loss=6.585, over 4816.00 frames.], tot_loss[loss=0.5315, simple_loss=1.063, pruned_loss=6.577, over 617405.95 frames.], batch size: 13, lr: 3.00e-03
2022-05-03 11:44:22,063 INFO [train.py:715] (4/8) Epoch 0, batch 250, loss[loss=0.3369, simple_loss=0.6737, pruned_loss=6.572, over 4801.00 frames.], tot_loss[loss=0.4732, simple_loss=0.9464, pruned_loss=6.591, over 695953.09 frames.], batch size: 24, lr: 3.00e-03
2022-05-03 11:45:01,534 INFO [train.py:715] (4/8) Epoch 0, batch 300, loss[loss=0.3379, simple_loss=0.6758, pruned_loss=6.705, over 4973.00 frames.], tot_loss[loss=0.4331, simple_loss=0.8661, pruned_loss=6.605, over 756910.04 frames.], batch size: 21, lr: 3.00e-03
2022-05-03 11:45:41,186 INFO [train.py:715] (4/8) Epoch 0, batch 350, loss[loss=0.305, simple_loss=0.61, pruned_loss=6.542, over 4972.00 frames.], tot_loss[loss=0.4038, simple_loss=0.8076, pruned_loss=6.617, over 804495.55 frames.], batch size: 15, lr: 3.00e-03
2022-05-03 11:46:19,550 INFO [train.py:715] (4/8) Epoch 0, batch 400, loss[loss=0.2861, simple_loss=0.5722, pruned_loss=6.509, over 4770.00 frames.], tot_loss[loss=0.3841, simple_loss=0.7682, pruned_loss=6.636, over 840921.01 frames.], batch size: 12, lr: 3.00e-03
2022-05-03 11:46:58,907 INFO [train.py:715] (4/8) Epoch 0, batch 450, loss[loss=0.3154, simple_loss=0.6307, pruned_loss=6.589, over 4906.00 frames.], tot_loss[loss=0.3698, simple_loss=0.7396, pruned_loss=6.651, over 870914.78 frames.], batch size: 23, lr: 2.99e-03
2022-05-03 11:47:38,001 INFO [train.py:715] (4/8) Epoch 0, batch 500, loss[loss=0.3027, simple_loss=0.6053, pruned_loss=6.554, over 4895.00 frames.], tot_loss[loss=0.3579, simple_loss=0.7157, pruned_loss=6.655, over 893479.44 frames.], batch size: 19, lr: 2.99e-03
2022-05-03 11:48:17,105 INFO [train.py:715] (4/8) Epoch 0, batch 550, loss[loss=0.3134, simple_loss=0.6267, pruned_loss=6.713, over 4754.00 frames.], tot_loss[loss=0.3467, simple_loss=0.6934, pruned_loss=6.657, over 910442.82 frames.], batch size: 19, lr: 2.99e-03
2022-05-03 11:48:55,926 INFO [train.py:715] (4/8) Epoch 0, batch 600, loss[loss=0.2967, simple_loss=0.5934, pruned_loss=6.654, over 4837.00 frames.], tot_loss[loss=0.3369, simple_loss=0.6738, pruned_loss=6.667, over 924017.34 frames.], batch size: 30, lr: 2.99e-03
2022-05-03 11:49:35,147 INFO [train.py:715] (4/8) Epoch 0, batch 650, loss[loss=0.3082, simple_loss=0.6164, pruned_loss=6.756, over 4872.00 frames.], tot_loss[loss=0.3254, simple_loss=0.6509, pruned_loss=6.684, over 934576.67 frames.], batch size: 16, lr: 2.99e-03
2022-05-03 11:50:14,496 INFO [train.py:715] (4/8) Epoch 0, batch 700, loss[loss=0.267, simple_loss=0.5339, pruned_loss=6.866, over 4903.00 frames.], tot_loss[loss=0.3129, simple_loss=0.6258, pruned_loss=6.7, over 942369.51 frames.], batch size: 17, lr: 2.99e-03
2022-05-03 11:50:52,997 INFO [train.py:715] (4/8) Epoch 0, batch 750, loss[loss=0.2567, simple_loss=0.5133, pruned_loss=6.727, over 4844.00 frames.], tot_loss[loss=0.3009, simple_loss=0.6018, pruned_loss=6.713, over 950402.46 frames.], batch size: 30, lr: 2.98e-03
2022-05-03 11:51:32,778 INFO [train.py:715] (4/8) Epoch 0, batch 800, loss[loss=0.2536, simple_loss=0.5071, pruned_loss=6.662, over 4940.00 frames.], tot_loss[loss=0.2888, simple_loss=0.5776, pruned_loss=6.717, over 955034.86 frames.], batch size: 23, lr: 2.98e-03
2022-05-03 11:52:12,741 INFO [train.py:715] (4/8) Epoch 0, batch 850, loss[loss=0.2171, simple_loss=0.4342, pruned_loss=6.671, over 4975.00 frames.], tot_loss[loss=0.2779, simple_loss=0.5558, pruned_loss=6.715, over 958789.73 frames.], batch size: 15, lr: 2.98e-03
2022-05-03 11:52:51,635 INFO [train.py:715] (4/8) Epoch 0, batch 900, loss[loss=0.2119, simple_loss=0.4238, pruned_loss=6.646, over 4783.00 frames.], tot_loss[loss=0.268, simple_loss=0.5359, pruned_loss=6.711, over 961872.87 frames.], batch size: 17, lr: 2.98e-03
2022-05-03 11:53:30,228 INFO [train.py:715] (4/8) Epoch 0, batch 950, loss[loss=0.2436, simple_loss=0.4872, pruned_loss=6.67, over 4902.00 frames.], tot_loss[loss=0.2591, simple_loss=0.5181, pruned_loss=6.709, over 964647.17 frames.], batch size: 29, lr: 2.97e-03
2022-05-03 11:54:09,539 INFO [train.py:715] (4/8) Epoch 0, batch 1000, loss[loss=0.2279, simple_loss=0.4558, pruned_loss=6.719, over 4900.00 frames.], tot_loss[loss=0.2506, simple_loss=0.5012, pruned_loss=6.71, over 965773.05 frames.], batch size: 22, lr: 2.97e-03
2022-05-03 11:54:48,898 INFO [train.py:715] (4/8) Epoch 0, batch 1050, loss[loss=0.246, simple_loss=0.4921, pruned_loss=6.765, over 4860.00 frames.], tot_loss[loss=0.2435, simple_loss=0.487, pruned_loss=6.713, over 966867.62 frames.], batch size: 20, lr: 2.97e-03
2022-05-03 11:55:27,464 INFO [train.py:715] (4/8) Epoch 0, batch 1100, loss[loss=0.2441, simple_loss=0.4883, pruned_loss=6.819, over 4732.00 frames.], tot_loss[loss=0.2369, simple_loss=0.4738, pruned_loss=6.711, over 968123.23 frames.], batch size: 16, lr: 2.96e-03
2022-05-03 11:56:07,471 INFO [train.py:715] (4/8) Epoch 0, batch 1150, loss[loss=0.2139, simple_loss=0.4278, pruned_loss=6.803, over 4886.00 frames.], tot_loss[loss=0.2317, simple_loss=0.4634, pruned_loss=6.715, over 969220.95 frames.], batch size: 19, lr: 2.96e-03
2022-05-03 11:56:47,805 INFO [train.py:715] (4/8) Epoch 0, batch 1200, loss[loss=0.1849, simple_loss=0.3698, pruned_loss=6.713, over 4834.00 frames.], tot_loss[loss=0.226, simple_loss=0.452, pruned_loss=6.713, over 969353.90 frames.], batch size: 13, lr: 2.96e-03
2022-05-03 11:57:28,431 INFO [train.py:715] (4/8) Epoch 0, batch 1250, loss[loss=0.1897, simple_loss=0.3795, pruned_loss=6.682, over 4826.00 frames.], tot_loss[loss=0.2218, simple_loss=0.4435, pruned_loss=6.713, over 970079.35 frames.], batch size: 15, lr: 2.95e-03
2022-05-03 11:58:07,329 INFO [train.py:715] (4/8) Epoch 0, batch 1300, loss[loss=0.1906, simple_loss=0.3812, pruned_loss=6.72, over 4992.00 frames.], tot_loss[loss=0.2169, simple_loss=0.4337, pruned_loss=6.712, over 970333.83 frames.], batch size: 15, lr: 2.95e-03
2022-05-03 11:58:47,741 INFO [train.py:715] (4/8) Epoch 0, batch 1350, loss[loss=0.1857, simple_loss=0.3714, pruned_loss=6.617, over 4841.00 frames.], tot_loss[loss=0.213, simple_loss=0.4261, pruned_loss=6.714, over 970798.77 frames.], batch size: 13, lr: 2.95e-03
2022-05-03 11:59:28,704 INFO [train.py:715] (4/8) Epoch 0, batch 1400, loss[loss=0.1986, simple_loss=0.3973, pruned_loss=6.665, over 4864.00 frames.], tot_loss[loss=0.2105, simple_loss=0.421, pruned_loss=6.713, over 970830.65 frames.], batch size: 22, lr: 2.94e-03
2022-05-03 12:00:09,323 INFO [train.py:715] (4/8) Epoch 0, batch 1450, loss[loss=0.2164, simple_loss=0.4329, pruned_loss=6.793, over 4765.00 frames.], tot_loss[loss=0.2074, simple_loss=0.4149, pruned_loss=6.712, over 971316.95 frames.], batch size: 17, lr: 2.94e-03
2022-05-03 12:00:48,848 INFO [train.py:715] (4/8) Epoch 0, batch 1500, loss[loss=0.2089, simple_loss=0.4179, pruned_loss=6.811, over 4907.00 frames.], tot_loss[loss=0.2049, simple_loss=0.4098, pruned_loss=6.708, over 970778.88 frames.], batch size: 17, lr: 2.94e-03
2022-05-03 12:01:29,915 INFO [train.py:715] (4/8) Epoch 0, batch 1550, loss[loss=0.1758, simple_loss=0.3517, pruned_loss=6.644, over 4754.00 frames.], tot_loss[loss=0.2023, simple_loss=0.4047, pruned_loss=6.708, over 970581.43 frames.], batch size: 16, lr: 2.93e-03
2022-05-03 12:02:11,264 INFO [train.py:715] (4/8) Epoch 0, batch 1600, loss[loss=0.1878, simple_loss=0.3756, pruned_loss=6.634, over 4988.00 frames.], tot_loss[loss=0.1994, simple_loss=0.3988, pruned_loss=6.7, over 970747.60 frames.], batch size: 16, lr: 2.93e-03
2022-05-03 12:02:51,028 INFO [train.py:715] (4/8) Epoch 0, batch 1650, loss[loss=0.1919, simple_loss=0.3838, pruned_loss=6.63, over 4905.00 frames.], tot_loss[loss=0.1973, simple_loss=0.3945, pruned_loss=6.697, over 972532.27 frames.], batch size: 19, lr: 2.92e-03
2022-05-03 12:03:32,801 INFO [train.py:715] (4/8) Epoch 0, batch 1700, loss[loss=0.1818, simple_loss=0.3636, pruned_loss=6.625, over 4986.00 frames.], tot_loss[loss=0.1951, simple_loss=0.3902, pruned_loss=6.69, over 973023.62 frames.], batch size: 28, lr: 2.92e-03
2022-05-03 12:04:14,548 INFO [train.py:715] (4/8) Epoch 0, batch 1750, loss[loss=0.1586, simple_loss=0.3172, pruned_loss=6.482, over 4764.00 frames.], tot_loss[loss=0.1936, simple_loss=0.3871, pruned_loss=6.686, over 972761.17 frames.], batch size: 19, lr: 2.91e-03
2022-05-03 12:04:55,999 INFO [train.py:715] (4/8) Epoch 0, batch 1800, loss[loss=0.188, simple_loss=0.376, pruned_loss=6.643, over 4847.00 frames.], tot_loss[loss=0.1918, simple_loss=0.3835, pruned_loss=6.681, over 972893.57 frames.], batch size: 20, lr: 2.91e-03
2022-05-03 12:05:36,573 INFO [train.py:715] (4/8) Epoch 0, batch 1850, loss[loss=0.1838, simple_loss=0.3676, pruned_loss=6.656, over 4793.00 frames.], tot_loss[loss=0.1899, simple_loss=0.3799, pruned_loss=6.676, over 972465.33 frames.], batch size: 21, lr: 2.91e-03
2022-05-03 12:06:18,610 INFO [train.py:715] (4/8) Epoch 0, batch 1900, loss[loss=0.1721, simple_loss=0.3441, pruned_loss=6.657, over 4888.00 frames.], tot_loss[loss=0.1869, simple_loss=0.3739, pruned_loss=6.674, over 973018.91 frames.], batch size: 22, lr: 2.90e-03
2022-05-03 12:07:00,147 INFO [train.py:715] (4/8) Epoch 0, batch 1950, loss[loss=0.1854, simple_loss=0.3708, pruned_loss=6.608, over 4957.00 frames.], tot_loss[loss=0.1852, simple_loss=0.3703, pruned_loss=6.673, over 973592.38 frames.], batch size: 21, lr: 2.90e-03
2022-05-03 12:07:38,870 INFO [train.py:715] (4/8) Epoch 0, batch 2000, loss[loss=0.1903, simple_loss=0.3806, pruned_loss=6.655, over 4904.00 frames.], tot_loss[loss=0.1842, simple_loss=0.3684, pruned_loss=6.668, over 974247.85 frames.], batch size: 17, lr: 2.89e-03
2022-05-03 12:08:19,991 INFO [train.py:715] (4/8) Epoch 0, batch 2050, loss[loss=0.1939, simple_loss=0.3877, pruned_loss=6.713, over 4847.00 frames.], tot_loss[loss=0.1837, simple_loss=0.3673, pruned_loss=6.664, over 972872.30 frames.], batch size: 26, lr: 2.89e-03
2022-05-03 12:09:00,592 INFO [train.py:715] (4/8) Epoch 0, batch 2100, loss[loss=0.1983, simple_loss=0.3966, pruned_loss=6.624, over 4918.00 frames.], tot_loss[loss=0.1829, simple_loss=0.3657, pruned_loss=6.662, over 972863.94 frames.], batch size: 18, lr: 2.88e-03
2022-05-03 12:09:41,209 INFO [train.py:715] (4/8) Epoch 0, batch 2150, loss[loss=0.2165, simple_loss=0.433, pruned_loss=6.685, over 4784.00 frames.], tot_loss[loss=0.182, simple_loss=0.3641, pruned_loss=6.665, over 971895.97 frames.], batch size: 17, lr: 2.88e-03
2022-05-03 12:10:20,517 INFO [train.py:715] (4/8) Epoch 0, batch 2200, loss[loss=0.1489, simple_loss=0.2978, pruned_loss=6.577, over 4695.00 frames.], tot_loss[loss=0.1812, simple_loss=0.3623, pruned_loss=6.668, over 972090.80 frames.], batch size: 15, lr: 2.87e-03
2022-05-03 12:11:01,489 INFO [train.py:715] (4/8) Epoch 0, batch 2250, loss[loss=0.1622, simple_loss=0.3245, pruned_loss=6.544, over 4789.00 frames.], tot_loss[loss=0.1806, simple_loss=0.3612, pruned_loss=6.666, over 972635.81 frames.], batch size: 12, lr: 2.86e-03
2022-05-03 12:11:42,772 INFO [train.py:715] (4/8) Epoch 0, batch 2300, loss[loss=0.1582, simple_loss=0.3165, pruned_loss=6.598, over 4983.00 frames.], tot_loss[loss=0.1795, simple_loss=0.3591, pruned_loss=6.667, over 972414.28 frames.], batch size: 25, lr: 2.86e-03
2022-05-03 12:12:22,379 INFO [train.py:715] (4/8) Epoch 0, batch 2350, loss[loss=0.1507, simple_loss=0.3015, pruned_loss=6.604, over 4900.00 frames.], tot_loss[loss=0.1781, simple_loss=0.3563, pruned_loss=6.664, over 972711.51 frames.], batch size: 19, lr: 2.85e-03
2022-05-03 12:13:03,123 INFO [train.py:715] (4/8) Epoch 0, batch 2400, loss[loss=0.177, simple_loss=0.354, pruned_loss=6.671, over 4834.00 frames.], tot_loss[loss=0.1772, simple_loss=0.3545, pruned_loss=6.669, over 971973.77 frames.], batch size: 27, lr: 2.85e-03
2022-05-03 12:13:43,810 INFO [train.py:715] (4/8) Epoch 0, batch 2450, loss[loss=0.1693, simple_loss=0.3385, pruned_loss=6.73, over 4993.00 frames.], tot_loss[loss=0.1764, simple_loss=0.3528, pruned_loss=6.67, over 972905.14 frames.], batch size: 14, lr: 2.84e-03
2022-05-03 12:14:24,675 INFO [train.py:715] (4/8) Epoch 0, batch 2500, loss[loss=0.1557, simple_loss=0.3114, pruned_loss=6.614, over 4947.00 frames.], tot_loss[loss=0.1752, simple_loss=0.3504, pruned_loss=6.668, over 973173.17 frames.], batch size: 23, lr: 2.84e-03
2022-05-03 12:15:03,906 INFO [train.py:715] (4/8) Epoch 0, batch 2550, loss[loss=0.1746, simple_loss=0.3491, pruned_loss=6.639, over 4814.00 frames.], tot_loss[loss=0.1754, simple_loss=0.3508, pruned_loss=6.668, over 972497.23 frames.], batch size: 27, lr: 2.83e-03
2022-05-03 12:15:44,622 INFO [train.py:715] (4/8) Epoch 0, batch 2600, loss[loss=0.1641, simple_loss=0.3281, pruned_loss=6.701, over 4944.00 frames.], tot_loss[loss=0.1743, simple_loss=0.3487, pruned_loss=6.659, over 972067.71 frames.], batch size: 23, lr: 2.83e-03
2022-05-03 12:16:25,709 INFO [train.py:715] (4/8) Epoch 0, batch 2650, loss[loss=0.1498, simple_loss=0.2996, pruned_loss=6.779, over 4982.00 frames.], tot_loss[loss=0.1739, simple_loss=0.3477, pruned_loss=6.656, over 971989.18 frames.], batch size: 14, lr: 2.82e-03
2022-05-03 12:17:08,084 INFO [train.py:715] (4/8) Epoch 0, batch 2700, loss[loss=0.195, simple_loss=0.39, pruned_loss=6.703, over 4969.00 frames.], tot_loss[loss=0.1735, simple_loss=0.347, pruned_loss=6.654, over 972569.92 frames.], batch size: 15, lr: 2.81e-03
2022-05-03 12:17:48,869 INFO [train.py:715] (4/8) Epoch 0, batch 2750, loss[loss=0.173, simple_loss=0.346, pruned_loss=6.68, over 4772.00 frames.], tot_loss[loss=0.1739, simple_loss=0.3478, pruned_loss=6.655, over 972340.70 frames.], batch size: 18, lr: 2.81e-03
2022-05-03 12:18:29,709 INFO [train.py:715] (4/8) Epoch 0, batch 2800, loss[loss=0.1755, simple_loss=0.351, pruned_loss=6.57, over 4955.00 frames.], tot_loss[loss=0.173, simple_loss=0.346, pruned_loss=6.647, over 972561.91 frames.], batch size: 35, lr: 2.80e-03
2022-05-03 12:19:10,261 INFO [train.py:715] (4/8) Epoch 0, batch 2850, loss[loss=0.1815, simple_loss=0.3631, pruned_loss=6.73, over 4969.00 frames.], tot_loss[loss=0.1723, simple_loss=0.3447, pruned_loss=6.644, over 973167.74 frames.], batch size: 15, lr: 2.80e-03
2022-05-03 12:19:49,110 INFO [train.py:715] (4/8) Epoch 0, batch 2900, loss[loss=0.1825, simple_loss=0.365, pruned_loss=6.657, over 4741.00 frames.], tot_loss[loss=0.1711, simple_loss=0.3421, pruned_loss=6.636, over 973608.70 frames.], batch size: 16, lr: 2.79e-03
2022-05-03 12:20:29,365 INFO [train.py:715] (4/8) Epoch 0, batch 2950, loss[loss=0.1721, simple_loss=0.3442, pruned_loss=6.718, over 4925.00 frames.], tot_loss[loss=0.1709, simple_loss=0.3417, pruned_loss=6.643, over 973066.62 frames.], batch size: 29, lr: 2.78e-03
2022-05-03 12:21:11,354 INFO [train.py:715] (4/8) Epoch 0, batch 3000, loss[loss=0.8468, simple_loss=0.3773, pruned_loss=6.582, over 4695.00 frames.], tot_loss[loss=0.2073, simple_loss=0.3424, pruned_loss=6.647, over 973090.08 frames.], batch size: 15, lr: 2.78e-03
2022-05-03 12:21:11,355 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 12:21:21,129 INFO [train.py:742] (4/8) Epoch 0, validation: loss=2.223, simple_loss=0.2788, pruned_loss=2.083, over 914524.00 frames.
2022-05-03 12:22:02,147 INFO [train.py:715] (4/8) Epoch 0, batch 3050, loss[loss=0.2388, simple_loss=0.3373, pruned_loss=0.7016, over 4945.00 frames.], tot_loss[loss=0.2226, simple_loss=0.3426, pruned_loss=5.406, over 972789.44 frames.], batch size: 23, lr: 2.77e-03
2022-05-03 12:22:41,557 INFO [train.py:715] (4/8) Epoch 0, batch 3100, loss[loss=0.1878, simple_loss=0.31, pruned_loss=0.3284, over 4780.00 frames.], tot_loss[loss=0.2213, simple_loss=0.3411, pruned_loss=4.313, over 973769.42 frames.], batch size: 17, lr: 2.77e-03
2022-05-03 12:23:22,409 INFO [train.py:715] (4/8) Epoch 0, batch 3150, loss[loss=0.2051, simple_loss=0.3536, pruned_loss=0.2829, over 4812.00 frames.], tot_loss[loss=0.2174, simple_loss=0.3417, pruned_loss=3.427, over 973964.82 frames.], batch size: 26, lr: 2.76e-03
2022-05-03 12:24:03,655 INFO [train.py:715] (4/8) Epoch 0, batch 3200, loss[loss=0.1655, simple_loss=0.2922, pruned_loss=0.1937, over 4826.00 frames.], tot_loss[loss=0.2109, simple_loss=0.3384, pruned_loss=2.724, over 972978.19 frames.], batch size: 26, lr: 2.75e-03
2022-05-03 12:24:44,868 INFO [train.py:715] (4/8) Epoch 0, batch 3250, loss[loss=0.1987, simple_loss=0.3475, pruned_loss=0.2493, over 4877.00 frames.], tot_loss[loss=0.2064, simple_loss=0.3378, pruned_loss=2.171, over 972837.24 frames.], batch size: 32, lr: 2.75e-03
2022-05-03 12:25:24,106 INFO [train.py:715] (4/8) Epoch 0, batch 3300, loss[loss=0.1723, simple_loss=0.3049, pruned_loss=0.199, over 4981.00 frames.], tot_loss[loss=0.2024, simple_loss=0.3369, pruned_loss=1.737, over 972753.79 frames.], batch size: 28, lr: 2.74e-03
2022-05-03 12:26:05,349 INFO [train.py:715] (4/8) Epoch 0, batch 3350, loss[loss=0.199, simple_loss=0.351, pruned_loss=0.2349, over 4829.00 frames.], tot_loss[loss=0.1979, simple_loss=0.3342, pruned_loss=1.395, over 972908.00 frames.], batch size: 15, lr: 2.73e-03
2022-05-03 12:26:46,179 INFO [train.py:715] (4/8) Epoch 0, batch 3400, loss[loss=0.1843, simple_loss=0.3303, pruned_loss=0.1913, over 4792.00 frames.], tot_loss[loss=0.1954, simple_loss=0.3339, pruned_loss=1.13, over 973002.13 frames.], batch size: 24, lr: 2.73e-03
2022-05-03 12:27:25,310 INFO [train.py:715] (4/8) Epoch 0, batch 3450, loss[loss=0.2152, simple_loss=0.3854, pruned_loss=0.2252, over 4879.00 frames.], tot_loss[loss=0.1938, simple_loss=0.3347, pruned_loss=0.9239, over 972909.90 frames.], batch size: 16, lr: 2.72e-03
2022-05-03 12:28:06,920 INFO [train.py:715] (4/8) Epoch 0, batch 3500, loss[loss=0.163, simple_loss=0.294, pruned_loss=0.1597, over 4928.00 frames.], tot_loss[loss=0.1905, simple_loss=0.3318, pruned_loss=0.7585, over 972904.74 frames.], batch size: 23, lr: 2.72e-03
2022-05-03 12:28:48,556 INFO [train.py:715] (4/8) Epoch 0, batch 3550, loss[loss=0.1701, simple_loss=0.3083, pruned_loss=0.1595, over 4974.00 frames.], tot_loss[loss=0.1883, simple_loss=0.3304, pruned_loss=0.6298, over 973799.93 frames.], batch size: 15, lr: 2.71e-03
2022-05-03 12:29:29,805 INFO [train.py:715] (4/8) Epoch 0, batch 3600, loss[loss=0.1759, simple_loss=0.3166, pruned_loss=0.1756, over 4959.00 frames.], tot_loss[loss=0.1869, simple_loss=0.33, pruned_loss=0.5298, over 973411.28 frames.], batch size: 35, lr: 2.70e-03
2022-05-03 12:30:08,994 INFO [train.py:715] (4/8) Epoch 0, batch 3650, loss[loss=0.1638, simple_loss=0.301, pruned_loss=0.1326, over 4896.00 frames.], tot_loss[loss=0.1851, simple_loss=0.3284, pruned_loss=0.4502, over 973265.12 frames.], batch size: 16, lr: 2.70e-03
2022-05-03 12:30:50,506 INFO [train.py:715] (4/8) Epoch 0, batch 3700, loss[loss=0.1897, simple_loss=0.3413, pruned_loss=0.1906, over 4802.00 frames.], tot_loss[loss=0.184, simple_loss=0.3276, pruned_loss=0.3899, over 972758.65 frames.], batch size: 24, lr: 2.69e-03
2022-05-03 12:31:32,098 INFO [train.py:715] (4/8) Epoch 0, batch 3750, loss[loss=0.2021, simple_loss=0.3636, pruned_loss=0.2028, over 4754.00 frames.], tot_loss[loss=0.1829, simple_loss=0.3268, pruned_loss=0.3413, over 971651.14 frames.], batch size: 16, lr: 2.68e-03
2022-05-03 12:32:11,303 INFO [train.py:715] (4/8) Epoch 0, batch 3800, loss[loss=0.1598, simple_loss=0.2945, pruned_loss=0.1257, over 4864.00 frames.], tot_loss[loss=0.1813, simple_loss=0.325, pruned_loss=0.3022, over 971628.38 frames.], batch size: 20, lr: 2.68e-03
2022-05-03 12:33:05,632 INFO [train.py:715] (4/8) Epoch 0, batch 3850, loss[loss=0.1939, simple_loss=0.3534, pruned_loss=0.1721, over 4814.00 frames.], tot_loss[loss=0.1811, simple_loss=0.3254, pruned_loss=0.2732, over 971345.02 frames.], batch size: 21, lr: 2.67e-03
2022-05-03 12:33:46,695 INFO [train.py:715] (4/8) Epoch 0, batch 3900, loss[loss=0.1809, simple_loss=0.3305, pruned_loss=0.1565, over 4854.00 frames.], tot_loss[loss=0.1805, simple_loss=0.3249, pruned_loss=0.2495, over 970778.70 frames.], batch size: 20, lr: 2.66e-03
2022-05-03 12:34:26,856 INFO [train.py:715] (4/8) Epoch 0, batch 3950, loss[loss=0.1891, simple_loss=0.3425, pruned_loss=0.1785, over 4936.00 frames.], tot_loss[loss=0.1792, simple_loss=0.3232, pruned_loss=0.2298, over 971461.65 frames.], batch size: 29, lr: 2.66e-03
2022-05-03 12:35:06,663 INFO [train.py:715] (4/8) Epoch 0, batch 4000, loss[loss=0.1835, simple_loss=0.3321, pruned_loss=0.1749, over 4686.00 frames.], tot_loss[loss=0.1785, simple_loss=0.3226, pruned_loss=0.214, over 972017.76 frames.], batch size: 15, lr: 2.65e-03
2022-05-03 12:35:47,600 INFO [train.py:715] (4/8) Epoch 0, batch 4050, loss[loss=0.1941, simple_loss=0.3466, pruned_loss=0.2075, over 4821.00 frames.], tot_loss[loss=0.1786, simple_loss=0.3231, pruned_loss=0.2037, over 971598.29 frames.], batch size: 26, lr: 2.64e-03
2022-05-03 12:36:28,802 INFO [train.py:715] (4/8) Epoch 0, batch 4100, loss[loss=0.1745, simple_loss=0.3171, pruned_loss=0.1588, over 4868.00 frames.], tot_loss[loss=0.1789, simple_loss=0.3238, pruned_loss=0.1955, over 971550.10 frames.], batch size: 32, lr: 2.64e-03
2022-05-03 12:37:07,947 INFO [train.py:715] (4/8) Epoch 0, batch 4150, loss[loss=0.1925, simple_loss=0.3513, pruned_loss=0.1691, over 4778.00 frames.], tot_loss[loss=0.1782, simple_loss=0.323, pruned_loss=0.1873, over 971470.34 frames.], batch size: 18, lr: 2.63e-03
2022-05-03 12:37:49,182 INFO [train.py:715] (4/8) Epoch 0, batch 4200, loss[loss=0.1729, simple_loss=0.3133, pruned_loss=0.1621, over 4932.00 frames.], tot_loss[loss=0.1777, simple_loss=0.3224, pruned_loss=0.181, over 972068.48 frames.], batch size: 23, lr: 2.63e-03
2022-05-03 12:38:30,912 INFO [train.py:715] (4/8) Epoch 0, batch 4250, loss[loss=0.1673, simple_loss=0.3099, pruned_loss=0.1237, over 4919.00 frames.], tot_loss[loss=0.1766, simple_loss=0.3206, pruned_loss=0.1746, over 972015.41 frames.], batch size: 18, lr: 2.62e-03
2022-05-03 12:39:11,497 INFO [train.py:715] (4/8) Epoch 0, batch 4300, loss[loss=0.1721, simple_loss=0.3141, pruned_loss=0.1501, over 4849.00 frames.], tot_loss[loss=0.1764, simple_loss=0.3205, pruned_loss=0.1708, over 971582.21 frames.], batch size: 15, lr: 2.61e-03
2022-05-03 12:39:51,569 INFO [train.py:715] (4/8) Epoch 0, batch 4350, loss[loss=0.1564, simple_loss=0.2894, pruned_loss=0.1171, over 4812.00 frames.], tot_loss[loss=0.177, simple_loss=0.3216, pruned_loss=0.1693, over 971748.08 frames.], batch size: 26, lr: 2.61e-03
2022-05-03 12:40:33,086 INFO [train.py:715] (4/8) Epoch 0, batch 4400, loss[loss=0.1804, simple_loss=0.3304, pruned_loss=0.1523, over 4916.00 frames.], tot_loss[loss=0.1768, simple_loss=0.3214, pruned_loss=0.1664, over 972263.60 frames.], batch size: 18, lr: 2.60e-03
2022-05-03 12:41:14,310 INFO [train.py:715] (4/8) Epoch 0, batch 4450, loss[loss=0.183, simple_loss=0.3344, pruned_loss=0.1583, over 4777.00 frames.], tot_loss[loss=0.1768, simple_loss=0.3216, pruned_loss=0.1646, over 971793.39 frames.], batch size: 18, lr: 2.59e-03
2022-05-03 12:41:53,444 INFO [train.py:715] (4/8) Epoch 0, batch 4500, loss[loss=0.1509, simple_loss=0.2779, pruned_loss=0.1201, over 4962.00 frames.], tot_loss[loss=0.1756, simple_loss=0.3196, pruned_loss=0.1615, over 971304.69 frames.], batch size: 24, lr: 2.59e-03
2022-05-03 12:42:34,809 INFO [train.py:715] (4/8) Epoch 0, batch 4550, loss[loss=0.194, simple_loss=0.3502, pruned_loss=0.1889, over 4941.00 frames.], tot_loss[loss=0.1757, simple_loss=0.32, pruned_loss=0.1598, over 971572.09 frames.], batch size: 39, lr: 2.58e-03
2022-05-03 12:43:16,360 INFO [train.py:715] (4/8) Epoch 0, batch 4600, loss[loss=0.1887, simple_loss=0.3414, pruned_loss=0.1796, over 4844.00 frames.], tot_loss[loss=0.1747, simple_loss=0.3184, pruned_loss=0.1573, over 972329.01 frames.], batch size: 32, lr: 2.57e-03
2022-05-03 12:43:56,548 INFO [train.py:715] (4/8) Epoch 0, batch 4650, loss[loss=0.1752, simple_loss=0.3208, pruned_loss=0.1478, over 4931.00 frames.], tot_loss[loss=0.1737, simple_loss=0.3169, pruned_loss=0.1546, over 972908.72 frames.], batch size: 21, lr: 2.57e-03
2022-05-03 12:44:36,466 INFO [train.py:715] (4/8) Epoch 0, batch 4700, loss[loss=0.1764, simple_loss=0.3203, pruned_loss=0.1625, over 4909.00 frames.], tot_loss[loss=0.1734, simple_loss=0.3163, pruned_loss=0.1541, over 972654.97 frames.], batch size: 17, lr: 2.56e-03
2022-05-03 12:45:17,605 INFO [train.py:715] (4/8) Epoch 0, batch 4750, loss[loss=0.1569, simple_loss=0.2892, pruned_loss=0.1231, over 4780.00 frames.], tot_loss[loss=0.1719, simple_loss=0.314, pruned_loss=0.1503, over 972400.60 frames.], batch size: 14, lr: 2.55e-03
2022-05-03 12:45:58,874 INFO [train.py:715] (4/8) Epoch 0, batch 4800, loss[loss=0.1592, simple_loss=0.2935, pruned_loss=0.1246, over 4941.00 frames.], tot_loss[loss=0.1719, simple_loss=0.314, pruned_loss=0.1499, over 971761.71 frames.], batch size: 21, lr: 2.55e-03
2022-05-03 12:46:38,835 INFO [train.py:715] (4/8) Epoch 0, batch 4850, loss[loss=0.1679, simple_loss=0.304, pruned_loss=0.1596, over 4688.00 frames.], tot_loss[loss=0.1711, simple_loss=0.3127, pruned_loss=0.1483, over 971551.25 frames.], batch size: 15, lr: 2.54e-03
2022-05-03 12:47:19,638 INFO [train.py:715] (4/8) Epoch 0, batch 4900, loss[loss=0.1977, simple_loss=0.3558, pruned_loss=0.1983, over 4981.00 frames.], tot_loss[loss=0.1704, simple_loss=0.3114, pruned_loss=0.1471, over 971039.87 frames.], batch size: 15, lr: 2.54e-03
2022-05-03 12:48:01,137 INFO [train.py:715] (4/8) Epoch 0, batch 4950, loss[loss=0.1657, simple_loss=0.3043, pruned_loss=0.1354, over 4804.00 frames.], tot_loss[loss=0.1703, simple_loss=0.3115, pruned_loss=0.1462, over 971855.88 frames.], batch size: 26, lr: 2.53e-03
2022-05-03 12:48:41,417 INFO [train.py:715] (4/8) Epoch 0, batch 5000, loss[loss=0.1774, simple_loss=0.3237, pruned_loss=0.1558, over 4938.00 frames.], tot_loss[loss=0.1702, simple_loss=0.3114, pruned_loss=0.1453, over 972645.89 frames.], batch size: 21, lr: 2.52e-03
2022-05-03 12:49:22,148 INFO [train.py:715] (4/8) Epoch 0, batch 5050, loss[loss=0.1769, simple_loss=0.3206, pruned_loss=0.1658, over 4955.00 frames.], tot_loss[loss=0.1705, simple_loss=0.3119, pruned_loss=0.1454, over 973485.24 frames.], batch size: 15, lr: 2.52e-03
2022-05-03 12:50:05,002 INFO [train.py:715] (4/8) Epoch 0, batch 5100, loss[loss=0.1452, simple_loss=0.2701, pruned_loss=0.102, over 4738.00 frames.], tot_loss[loss=0.1705, simple_loss=0.3119, pruned_loss=0.1456, over 972802.35 frames.], batch size: 12, lr: 2.51e-03
2022-05-03 12:50:48,200 INFO [train.py:715] (4/8) Epoch 0, batch 5150, loss[loss=0.1873, simple_loss=0.3409, pruned_loss=0.1684, over 4982.00 frames.], tot_loss[loss=0.1704, simple_loss=0.3119, pruned_loss=0.1448, over 972157.47 frames.], batch size: 35, lr: 2.50e-03
2022-05-03 12:51:28,094 INFO [train.py:715] (4/8) Epoch 0, batch 5200, loss[loss=0.1828, simple_loss=0.3352, pruned_loss=0.1526, over 4798.00 frames.], tot_loss[loss=0.1703, simple_loss=0.3117, pruned_loss=0.1441, over 971272.88 frames.], batch size: 25, lr: 2.50e-03
2022-05-03 12:52:08,705 INFO [train.py:715] (4/8) Epoch 0, batch 5250, loss[loss=0.1819, simple_loss=0.3318, pruned_loss=0.1595, over 4806.00 frames.], tot_loss[loss=0.1704, simple_loss=0.312, pruned_loss=0.1441, over 971108.42 frames.], batch size: 26, lr: 2.49e-03
2022-05-03 12:52:49,809 INFO [train.py:715] (4/8) Epoch 0, batch 5300, loss[loss=0.1671, simple_loss=0.3065, pruned_loss=0.1382, over 4876.00 frames.], tot_loss[loss=0.1697, simple_loss=0.3109, pruned_loss=0.1428, over 971392.59 frames.], batch size: 32, lr: 2.49e-03
2022-05-03 12:53:30,341 INFO [train.py:715] (4/8) Epoch 0, batch 5350, loss[loss=0.1987, simple_loss=0.3574, pruned_loss=0.2001, over 4852.00 frames.], tot_loss[loss=0.1696, simple_loss=0.3107, pruned_loss=0.1422, over 972075.34 frames.], batch size: 32, lr: 2.48e-03
2022-05-03 12:54:10,011 INFO [train.py:715] (4/8) Epoch 0, batch 5400, loss[loss=0.1935, simple_loss=0.3473, pruned_loss=0.1986, over 4960.00 frames.], tot_loss[loss=0.1697, simple_loss=0.3111, pruned_loss=0.1417, over 972619.57 frames.], batch size: 35, lr: 2.47e-03
2022-05-03 12:54:50,447 INFO [train.py:715] (4/8) Epoch 0, batch 5450, loss[loss=0.1772, simple_loss=0.3249, pruned_loss=0.1473, over 4860.00 frames.], tot_loss[loss=0.1691, simple_loss=0.3101, pruned_loss=0.1404, over 972540.07 frames.], batch size: 30, lr: 2.47e-03
2022-05-03 12:55:31,401 INFO [train.py:715] (4/8) Epoch 0, batch 5500, loss[loss=0.177, simple_loss=0.3207, pruned_loss=0.1672, over 4986.00 frames.], tot_loss[loss=0.1688, simple_loss=0.3097, pruned_loss=0.1395, over 973003.77 frames.], batch size: 31, lr: 2.46e-03
2022-05-03 12:56:11,117 INFO [train.py:715] (4/8) Epoch 0, batch 5550, loss[loss=0.1443, simple_loss=0.2651, pruned_loss=0.1178, over 4808.00 frames.], tot_loss[loss=0.1691, simple_loss=0.3102, pruned_loss=0.1398, over 973165.72 frames.], batch size: 12, lr: 2.45e-03
2022-05-03 12:56:51,155 INFO [train.py:715] (4/8) Epoch 0, batch 5600, loss[loss=0.1779, simple_loss=0.3244, pruned_loss=0.1566, over 4926.00 frames.], tot_loss[loss=0.1682, simple_loss=0.3087, pruned_loss=0.1381, over 972912.36 frames.], batch size: 29, lr: 2.45e-03
2022-05-03 12:57:32,365 INFO [train.py:715] (4/8) Epoch 0, batch 5650, loss[loss=0.1792, simple_loss=0.327, pruned_loss=0.1569, over 4952.00 frames.], tot_loss[loss=0.1677, simple_loss=0.3079, pruned_loss=0.1374, over 972620.74 frames.], batch size: 24, lr: 2.44e-03
2022-05-03 12:58:12,915 INFO [train.py:715] (4/8) Epoch 0, batch 5700, loss[loss=0.1398, simple_loss=0.2568, pruned_loss=0.1142, over 4802.00 frames.], tot_loss[loss=0.1674, simple_loss=0.3075, pruned_loss=0.1369, over 972277.65 frames.], batch size: 13, lr: 2.44e-03
2022-05-03 12:58:52,120 INFO [train.py:715] (4/8) Epoch 0, batch 5750, loss[loss=0.1572, simple_loss=0.2909, pruned_loss=0.117, over 4920.00 frames.], tot_loss[loss=0.1679, simple_loss=0.3082, pruned_loss=0.1379, over 972861.25 frames.], batch size: 23, lr: 2.43e-03
2022-05-03 12:59:33,143 INFO [train.py:715] (4/8) Epoch 0, batch 5800, loss[loss=0.1734, simple_loss=0.3159, pruned_loss=0.1546, over 4886.00 frames.], tot_loss[loss=0.1672, simple_loss=0.3071, pruned_loss=0.1363, over 972895.45 frames.], batch size: 32, lr: 2.42e-03
2022-05-03 13:00:14,328 INFO [train.py:715] (4/8) Epoch 0, batch 5850, loss[loss=0.1777, simple_loss=0.3254, pruned_loss=0.1497, over 4878.00 frames.], tot_loss[loss=0.1667, simple_loss=0.3063, pruned_loss=0.1353, over 972895.21 frames.], batch size: 32, lr: 2.42e-03
2022-05-03 13:00:54,226 INFO [train.py:715] (4/8) Epoch 0, batch 5900, loss[loss=0.2085, simple_loss=0.3787, pruned_loss=0.1913, over 4765.00 frames.], tot_loss[loss=0.167, simple_loss=0.3069, pruned_loss=0.1355, over 972449.69 frames.], batch size: 14, lr: 2.41e-03
2022-05-03 13:01:33,974 INFO [train.py:715] (4/8) Epoch 0, batch 5950, loss[loss=0.182, simple_loss=0.3335, pruned_loss=0.1526, over 4932.00 frames.], tot_loss[loss=0.167, simple_loss=0.3068, pruned_loss=0.1355, over 972942.63 frames.], batch size: 23, lr: 2.41e-03
2022-05-03 13:02:14,771 INFO [train.py:715] (4/8) Epoch 0, batch 6000, loss[loss=0.2912, simple_loss=0.3107, pruned_loss=0.1359, over 4868.00 frames.], tot_loss[loss=0.1683, simple_loss=0.3069, pruned_loss=0.1356, over 973202.83 frames.], batch size: 32, lr: 2.40e-03
2022-05-03 13:02:14,773 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 13:02:25,809 INFO [train.py:742] (4/8) Epoch 0, validation: loss=0.1779, simple_loss=0.2457, pruned_loss=0.05502, over 914524.00 frames.
2022-05-03 13:03:07,299 INFO [train.py:715] (4/8) Epoch 0, batch 6050, loss[loss=0.3375, simple_loss=0.3288, pruned_loss=0.1731, over 4886.00 frames.], tot_loss[loss=0.2009, simple_loss=0.3099, pruned_loss=0.14, over 973166.94 frames.], batch size: 16, lr: 2.39e-03
2022-05-03 13:03:47,838 INFO [train.py:715] (4/8) Epoch 0, batch 6100, loss[loss=0.338, simple_loss=0.3435, pruned_loss=0.1663, over 4970.00 frames.], tot_loss[loss=0.2218, simple_loss=0.3104, pruned_loss=0.1397, over 973302.25 frames.], batch size: 35, lr: 2.39e-03
2022-05-03 13:04:27,369 INFO [train.py:715] (4/8) Epoch 0, batch 6150, loss[loss=0.2676, simple_loss=0.3002, pruned_loss=0.1175, over 4812.00 frames.], tot_loss[loss=0.2376, simple_loss=0.3109, pruned_loss=0.1392, over 972715.36 frames.], batch size: 13, lr: 2.38e-03
2022-05-03 13:05:08,102 INFO [train.py:715] (4/8) Epoch 0, batch 6200, loss[loss=0.2746, simple_loss=0.2982, pruned_loss=0.1255, over 4694.00 frames.], tot_loss[loss=0.2502, simple_loss=0.3117, pruned_loss=0.1387, over 972682.84 frames.], batch size: 15, lr: 2.38e-03
2022-05-03 13:05:48,929 INFO [train.py:715] (4/8) Epoch 0, batch 6250, loss[loss=0.2653, simple_loss=0.3014, pruned_loss=0.1145, over 4778.00 frames.], tot_loss[loss=0.2574, simple_loss=0.3105, pruned_loss=0.1367, over 972543.01 frames.], batch size: 18, lr: 2.37e-03
2022-05-03 13:06:29,125 INFO [train.py:715] (4/8) Epoch 0, batch 6300, loss[loss=0.2919, simple_loss=0.3273, pruned_loss=0.1283, over 4782.00 frames.], tot_loss[loss=0.2639, simple_loss=0.3105, pruned_loss=0.1355, over 972595.91 frames.], batch size: 14, lr: 2.37e-03
2022-05-03 13:07:09,808 INFO [train.py:715] (4/8) Epoch 0, batch 6350, loss[loss=0.4088, simple_loss=0.385, pruned_loss=0.2163, over 4837.00 frames.], tot_loss[loss=0.2702, simple_loss=0.3108, pruned_loss=0.1358, over 972323.18 frames.], batch size: 26, lr: 2.36e-03
2022-05-03 13:07:50,713 INFO [train.py:715] (4/8) Epoch 0, batch 6400, loss[loss=0.2823, simple_loss=0.3137, pruned_loss=0.1254, over 4884.00 frames.], tot_loss[loss=0.2722, simple_loss=0.3097, pruned_loss=0.1337, over 973052.61 frames.], batch size: 16, lr: 2.35e-03
2022-05-03 13:08:30,734 INFO [train.py:715] (4/8) Epoch 0, batch 6450, loss[loss=0.2427, simple_loss=0.2837, pruned_loss=0.1009, over 4754.00 frames.], tot_loss[loss=0.2717, simple_loss=0.3074, pruned_loss=0.1306, over 972349.89 frames.], batch size: 16, lr: 2.35e-03
2022-05-03 13:09:10,062 INFO [train.py:715] (4/8) Epoch 0, batch 6500, loss[loss=0.3045, simple_loss=0.3151, pruned_loss=0.1469, over 4762.00 frames.], tot_loss[loss=0.2735, simple_loss=0.3069, pruned_loss=0.1299, over 971788.53 frames.], batch size: 18, lr: 2.34e-03
2022-05-03 13:09:50,934 INFO [train.py:715] (4/8) Epoch 0, batch 6550, loss[loss=0.2485, simple_loss=0.2835, pruned_loss=0.1067, over 4966.00 frames.], tot_loss[loss=0.2775, simple_loss=0.3083, pruned_loss=0.131, over 971875.87 frames.], batch size: 15, lr: 2.34e-03
2022-05-03 13:10:31,733 INFO [train.py:715] (4/8) Epoch 0, batch 6600, loss[loss=0.2974, simple_loss=0.3197, pruned_loss=0.1376, over 4774.00 frames.], tot_loss[loss=0.28, simple_loss=0.3092, pruned_loss=0.1313, over 971968.40 frames.], batch size: 14, lr: 2.33e-03
2022-05-03 13:11:11,206 INFO [train.py:715] (4/8) Epoch 0, batch 6650, loss[loss=0.2608, simple_loss=0.3062, pruned_loss=0.1077, over 4734.00 frames.], tot_loss[loss=0.2784, simple_loss=0.3081, pruned_loss=0.129, over 972067.24 frames.], batch size: 16, lr: 2.33e-03
2022-05-03 13:11:51,646 INFO [train.py:715] (4/8) Epoch 0, batch 6700, loss[loss=0.2662, simple_loss=0.3043, pruned_loss=0.1141, over 4936.00 frames.], tot_loss[loss=0.2773, simple_loss=0.3073, pruned_loss=0.1273, over 972655.09 frames.], batch size: 21, lr: 2.32e-03
2022-05-03 13:12:32,417 INFO [train.py:715] (4/8) Epoch 0, batch 6750, loss[loss=0.3191, simple_loss=0.334, pruned_loss=0.1521, over 4644.00 frames.], tot_loss[loss=0.2782, simple_loss=0.3078, pruned_loss=0.1271, over 973716.45 frames.], batch size: 13, lr: 2.31e-03
2022-05-03 13:13:12,492 INFO [train.py:715] (4/8) Epoch 0, batch 6800, loss[loss=0.3004, simple_loss=0.3328, pruned_loss=0.134, over 4899.00 frames.], tot_loss[loss=0.2781, simple_loss=0.3074, pruned_loss=0.1266, over 973395.59 frames.], batch size: 39, lr: 2.31e-03
2022-05-03 13:13:52,210 INFO [train.py:715] (4/8) Epoch 0, batch 6850, loss[loss=0.2408, simple_loss=0.2872, pruned_loss=0.09716, over 4835.00 frames.], tot_loss[loss=0.2758, simple_loss=0.3059, pruned_loss=0.1245, over 973348.27 frames.], batch size: 26, lr: 2.30e-03
2022-05-03 13:14:32,484 INFO [train.py:715] (4/8) Epoch 0, batch 6900, loss[loss=0.2598, simple_loss=0.3051, pruned_loss=0.1073, over 4735.00 frames.], tot_loss[loss=0.2776, simple_loss=0.3073, pruned_loss=0.1253, over 972009.81 frames.], batch size: 16, lr: 2.30e-03
2022-05-03 13:15:12,910 INFO [train.py:715] (4/8) Epoch 0, batch 6950, loss[loss=0.2589, simple_loss=0.2952, pruned_loss=0.1113, over 4976.00 frames.], tot_loss[loss=0.2788, simple_loss=0.3082, pruned_loss=0.1258, over 972234.27 frames.], batch size: 31, lr: 2.29e-03
2022-05-03 13:15:53,028 INFO [train.py:715] (4/8) Epoch 0, batch 7000, loss[loss=0.3049, simple_loss=0.3395, pruned_loss=0.1352, over 4984.00 frames.], tot_loss[loss=0.2778, simple_loss=0.3076, pruned_loss=0.1248, over 971955.09 frames.], batch size: 24, lr: 2.29e-03
2022-05-03 13:16:33,735 INFO [train.py:715] (4/8) Epoch 0, batch 7050, loss[loss=0.3134, simple_loss=0.3186, pruned_loss=0.1541, over 4987.00 frames.], tot_loss[loss=0.2758, simple_loss=0.306, pruned_loss=0.1234, over 972070.95 frames.], batch size: 31, lr: 2.28e-03
2022-05-03 13:17:14,937 INFO [train.py:715] (4/8) Epoch 0, batch 7100, loss[loss=0.2837, simple_loss=0.2999, pruned_loss=0.1338, over 4980.00 frames.], tot_loss[loss=0.2758, simple_loss=0.3062, pruned_loss=0.1232, over 972320.37 frames.], batch size: 25, lr: 2.28e-03
2022-05-03 13:17:55,882 INFO [train.py:715] (4/8) Epoch 0, batch 7150, loss[loss=0.2296, simple_loss=0.2777, pruned_loss=0.09077, over 4820.00 frames.], tot_loss[loss=0.2749, simple_loss=0.3057, pruned_loss=0.1224, over 971858.43 frames.], batch size: 26, lr: 2.27e-03
2022-05-03 13:18:35,507 INFO [train.py:715] (4/8) Epoch 0, batch 7200, loss[loss=0.2149, simple_loss=0.2661, pruned_loss=0.08189, over 4924.00 frames.], tot_loss[loss=0.2757, simple_loss=0.3065, pruned_loss=0.1227, over 972492.28 frames.], batch size: 29, lr: 2.27e-03
2022-05-03 13:19:16,090 INFO [train.py:715] (4/8) Epoch 0, batch 7250, loss[loss=0.2377, simple_loss=0.2902, pruned_loss=0.09261, over 4972.00 frames.], tot_loss[loss=0.2751, simple_loss=0.306, pruned_loss=0.1223, over 972025.22 frames.], batch size: 24, lr: 2.26e-03
2022-05-03 13:19:55,968 INFO [train.py:715] (4/8) Epoch 0, batch 7300, loss[loss=0.2119, simple_loss=0.2528, pruned_loss=0.08552, over 4776.00 frames.], tot_loss[loss=0.2718, simple_loss=0.3042, pruned_loss=0.1199, over 971763.72 frames.], batch size: 17, lr: 2.26e-03
2022-05-03 13:20:36,062 INFO [train.py:715] (4/8) Epoch 0, batch 7350, loss[loss=0.2513, simple_loss=0.2944, pruned_loss=0.1041, over 4894.00 frames.], tot_loss[loss=0.2718, simple_loss=0.3041, pruned_loss=0.1199, over 972906.45 frames.], batch size: 17, lr: 2.25e-03
2022-05-03 13:21:16,435 INFO [train.py:715] (4/8) Epoch 0, batch 7400, loss[loss=0.2123, simple_loss=0.2674, pruned_loss=0.07866, over 4843.00 frames.], tot_loss[loss=0.2728, simple_loss=0.3047, pruned_loss=0.1206, over 972128.83 frames.], batch size: 13, lr: 2.24e-03
2022-05-03 13:21:57,037 INFO [train.py:715] (4/8) Epoch 0, batch 7450, loss[loss=0.2852, simple_loss=0.2997, pruned_loss=0.1353, over 4762.00 frames.], tot_loss[loss=0.2731, simple_loss=0.305, pruned_loss=0.1207, over 972050.24 frames.], batch size: 16, lr: 2.24e-03
2022-05-03 13:22:36,836 INFO [train.py:715] (4/8) Epoch 0, batch 7500, loss[loss=0.1615, simple_loss=0.2073, pruned_loss=0.05789, over 4849.00 frames.], tot_loss[loss=0.2707, simple_loss=0.3031, pruned_loss=0.1192, over 972636.61 frames.], batch size: 12, lr: 2.23e-03
2022-05-03 13:23:16,561 INFO [train.py:715] (4/8) Epoch 0, batch 7550, loss[loss=0.2924, simple_loss=0.3147, pruned_loss=0.135, over 4740.00 frames.], tot_loss[loss=0.2713, simple_loss=0.3039, pruned_loss=0.1194, over 972544.85 frames.], batch size: 16, lr: 2.23e-03
2022-05-03 13:23:57,044 INFO [train.py:715] (4/8) Epoch 0, batch 7600, loss[loss=0.2358, simple_loss=0.2808, pruned_loss=0.09537, over 4853.00 frames.], tot_loss[loss=0.2713, simple_loss=0.3043, pruned_loss=0.1192, over 972297.21 frames.], batch size: 20, lr: 2.22e-03
2022-05-03 13:24:37,510 INFO [train.py:715] (4/8) Epoch 0, batch 7650, loss[loss=0.2525, simple_loss=0.2981, pruned_loss=0.1035, over 4837.00 frames.], tot_loss[loss=0.2715, simple_loss=0.3048, pruned_loss=0.1192, over 972594.53 frames.], batch size: 15, lr: 2.22e-03
2022-05-03 13:25:16,989 INFO [train.py:715] (4/8) Epoch 0, batch 7700, loss[loss=0.2556, simple_loss=0.3021, pruned_loss=0.1045, over 4739.00 frames.], tot_loss[loss=0.272, simple_loss=0.3053, pruned_loss=0.1194, over 971491.28 frames.], batch size: 16, lr: 2.21e-03
2022-05-03 13:25:57,318 INFO [train.py:715] (4/8) Epoch 0, batch 7750, loss[loss=0.2715, simple_loss=0.3108, pruned_loss=0.1161, over 4929.00 frames.], tot_loss[loss=0.2714, simple_loss=0.3053, pruned_loss=0.1188, over 971615.39 frames.], batch size: 21, lr: 2.21e-03
2022-05-03 13:26:38,373 INFO [train.py:715] (4/8) Epoch 0, batch 7800, loss[loss=0.2773, simple_loss=0.309, pruned_loss=0.1228, over 4883.00 frames.], tot_loss[loss=0.2706, simple_loss=0.3049, pruned_loss=0.1181, over 971731.22 frames.], batch size: 16, lr: 2.20e-03
2022-05-03 13:27:18,711 INFO [train.py:715] (4/8) Epoch 0, batch 7850, loss[loss=0.3252, simple_loss=0.3477, pruned_loss=0.1513, over 4947.00 frames.], tot_loss[loss=0.2715, simple_loss=0.3056, pruned_loss=0.1187, over 972063.01 frames.], batch size: 23, lr: 2.20e-03
2022-05-03 13:27:58,876 INFO [train.py:715] (4/8) Epoch 0, batch 7900, loss[loss=0.2587, simple_loss=0.3003, pruned_loss=0.1086, over 4690.00 frames.], tot_loss[loss=0.2723, simple_loss=0.3068, pruned_loss=0.1189, over 972521.68 frames.], batch size: 15, lr: 2.19e-03
2022-05-03 13:28:39,527 INFO [train.py:715] (4/8) Epoch 0, batch 7950, loss[loss=0.2984, simple_loss=0.3249, pruned_loss=0.1359, over 4796.00 frames.], tot_loss[loss=0.2706, simple_loss=0.3056, pruned_loss=0.1178, over 972907.34 frames.], batch size: 25, lr: 2.19e-03
2022-05-03 13:29:22,259 INFO [train.py:715] (4/8) Epoch 0, batch 8000, loss[loss=0.2483, simple_loss=0.292, pruned_loss=0.1023, over 4908.00 frames.], tot_loss[loss=0.2699, simple_loss=0.3048, pruned_loss=0.1175, over 972249.26 frames.], batch size: 19, lr: 2.18e-03
2022-05-03 13:30:02,107 INFO [train.py:715] (4/8) Epoch 0, batch 8050, loss[loss=0.3367, simple_loss=0.3733, pruned_loss=0.15, over 4860.00 frames.], tot_loss[loss=0.27, simple_loss=0.3047, pruned_loss=0.1177, over 972490.80 frames.], batch size: 20, lr: 2.18e-03
2022-05-03 13:30:41,976 INFO [train.py:715] (4/8) Epoch 0, batch 8100, loss[loss=0.2865, simple_loss=0.3086, pruned_loss=0.1323, over 4760.00 frames.], tot_loss[loss=0.2692, simple_loss=0.3045, pruned_loss=0.1169, over 971978.20 frames.], batch size: 19, lr: 2.17e-03
2022-05-03 13:31:22,996 INFO [train.py:715] (4/8) Epoch 0, batch 8150, loss[loss=0.2781, simple_loss=0.3136, pruned_loss=0.1213, over 4882.00 frames.], tot_loss[loss=0.2691, simple_loss=0.3043, pruned_loss=0.1169, over 970895.86 frames.], batch size: 19, lr: 2.17e-03
2022-05-03 13:32:02,626 INFO [train.py:715] (4/8) Epoch 0, batch 8200, loss[loss=0.2171, simple_loss=0.2568, pruned_loss=0.08871, over 4691.00 frames.], tot_loss[loss=0.2694, simple_loss=0.3044, pruned_loss=0.1172, over 970870.79 frames.], batch size: 15, lr: 2.16e-03
2022-05-03 13:32:42,134 INFO [train.py:715] (4/8) Epoch 0, batch 8250, loss[loss=0.274, simple_loss=0.3147, pruned_loss=0.1167, over 4972.00 frames.], tot_loss[loss=0.2682, simple_loss=0.3035, pruned_loss=0.1165, over 971843.31 frames.], batch size: 15, lr: 2.16e-03
2022-05-03 13:33:22,996 INFO [train.py:715] (4/8) Epoch 0, batch 8300, loss[loss=0.2826, simple_loss=0.3102, pruned_loss=0.1275, over 4836.00 frames.], tot_loss[loss=0.2665, simple_loss=0.3023, pruned_loss=0.1153, over 972035.43 frames.], batch size: 13, lr: 2.15e-03
2022-05-03 13:34:03,423 INFO [train.py:715] (4/8) Epoch 0, batch 8350, loss[loss=0.2405, simple_loss=0.2822, pruned_loss=0.09938, over 4768.00 frames.], tot_loss[loss=0.2672, simple_loss=0.3031, pruned_loss=0.1156, over 971367.52 frames.], batch size: 18, lr: 2.15e-03
2022-05-03 13:34:43,095 INFO [train.py:715] (4/8) Epoch 0, batch 8400, loss[loss=0.2425, simple_loss=0.2806, pruned_loss=0.1022, over 4932.00 frames.], tot_loss[loss=0.2645, simple_loss=0.3014, pruned_loss=0.1138, over 972854.33 frames.], batch size: 18, lr: 2.15e-03
2022-05-03 13:35:23,396 INFO [train.py:715] (4/8) Epoch 0, batch 8450, loss[loss=0.27, simple_loss=0.2834, pruned_loss=0.1283, over 4894.00 frames.], tot_loss[loss=0.2633, simple_loss=0.3005, pruned_loss=0.113, over 973762.03 frames.], batch size: 19, lr: 2.14e-03
2022-05-03 13:36:04,636 INFO [train.py:715] (4/8) Epoch 0, batch 8500, loss[loss=0.2411, simple_loss=0.2801, pruned_loss=0.1011, over 4814.00 frames.], tot_loss[loss=0.2608, simple_loss=0.2986, pruned_loss=0.1115, over 972471.32 frames.], batch size: 15, lr: 2.14e-03
2022-05-03 13:36:45,704 INFO [train.py:715] (4/8) Epoch 0, batch 8550, loss[loss=0.2707, simple_loss=0.3074, pruned_loss=0.117, over 4941.00 frames.], tot_loss[loss=0.2617, simple_loss=0.2994, pruned_loss=0.112, over 973054.56 frames.], batch size: 35, lr: 2.13e-03
2022-05-03 13:37:25,352 INFO [train.py:715] (4/8) Epoch 0, batch 8600, loss[loss=0.2692, simple_loss=0.2971, pruned_loss=0.1207, over 4788.00 frames.], tot_loss[loss=0.2626, simple_loss=0.3002, pruned_loss=0.1125, over 972803.06 frames.], batch size: 18, lr: 2.13e-03
2022-05-03 13:38:06,731 INFO [train.py:715] (4/8) Epoch 0, batch 8650, loss[loss=0.223, simple_loss=0.2752, pruned_loss=0.08538, over 4888.00 frames.], tot_loss[loss=0.2604, simple_loss=0.2988, pruned_loss=0.111, over 972336.81 frames.], batch size: 19, lr: 2.12e-03
2022-05-03 13:38:47,676 INFO [train.py:715] (4/8) Epoch 0, batch 8700, loss[loss=0.2744, simple_loss=0.3016, pruned_loss=0.1236, over 4833.00 frames.], tot_loss[loss=0.2605, simple_loss=0.2988, pruned_loss=0.1111, over 972706.92 frames.], batch size: 15, lr: 2.12e-03
2022-05-03 13:39:27,755 INFO [train.py:715] (4/8) Epoch 0, batch 8750, loss[loss=0.2599, simple_loss=0.2963, pruned_loss=0.1117, over 4973.00 frames.], tot_loss[loss=0.26, simple_loss=0.2986, pruned_loss=0.1107, over 972978.74 frames.], batch size: 15, lr: 2.11e-03
2022-05-03 13:40:08,238 INFO [train.py:715] (4/8) Epoch 0, batch 8800, loss[loss=0.2441, simple_loss=0.2742, pruned_loss=0.107, over 4908.00 frames.], tot_loss[loss=0.2599, simple_loss=0.2988, pruned_loss=0.1105, over 973305.20 frames.], batch size: 19, lr: 2.11e-03
2022-05-03 13:40:48,816 INFO [train.py:715] (4/8) Epoch 0, batch 8850, loss[loss=0.2854, simple_loss=0.3122, pruned_loss=0.1293, over 4835.00 frames.], tot_loss[loss=0.2606, simple_loss=0.2992, pruned_loss=0.111, over 972740.29 frames.], batch size: 30, lr: 2.10e-03
2022-05-03 13:41:29,551 INFO [train.py:715] (4/8) Epoch 0, batch 8900, loss[loss=0.2743, simple_loss=0.3172, pruned_loss=0.1157, over 4937.00 frames.], tot_loss[loss=0.2626, simple_loss=0.3008, pruned_loss=0.1122, over 973426.87 frames.], batch size: 39, lr: 2.10e-03
2022-05-03 13:42:09,367 INFO [train.py:715] (4/8) Epoch 0, batch 8950, loss[loss=0.2671, simple_loss=0.3023, pruned_loss=0.116, over 4986.00 frames.], tot_loss[loss=0.2631, simple_loss=0.3009, pruned_loss=0.1126, over 973452.74 frames.], batch size: 14, lr: 2.10e-03
2022-05-03 13:42:49,916 INFO [train.py:715] (4/8) Epoch 0, batch 9000, loss[loss=0.2207, simple_loss=0.2727, pruned_loss=0.08439, over 4911.00 frames.], tot_loss[loss=0.2618, simple_loss=0.2999, pruned_loss=0.1119, over 973487.63 frames.], batch size: 18, lr: 2.09e-03
2022-05-03 13:42:49,917 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 13:43:03,383 INFO [train.py:742] (4/8) Epoch 0, validation: loss=0.1592, simple_loss=0.2426, pruned_loss=0.03794, over 914524.00 frames.
2022-05-03 13:43:44,294 INFO [train.py:715] (4/8) Epoch 0, batch 9050, loss[loss=0.299, simple_loss=0.3269, pruned_loss=0.1356, over 4794.00 frames.], tot_loss[loss=0.2605, simple_loss=0.2988, pruned_loss=0.1112, over 973455.52 frames.], batch size: 14, lr: 2.09e-03
2022-05-03 13:44:24,657 INFO [train.py:715] (4/8) Epoch 0, batch 9100, loss[loss=0.2792, simple_loss=0.3107, pruned_loss=0.1239, over 4979.00 frames.], tot_loss[loss=0.2606, simple_loss=0.2992, pruned_loss=0.111, over 972882.40 frames.], batch size: 28, lr: 2.08e-03
2022-05-03 13:45:04,783 INFO [train.py:715] (4/8) Epoch 0, batch 9150, loss[loss=0.2988, simple_loss=0.3223, pruned_loss=0.1377, over 4746.00 frames.], tot_loss[loss=0.2586, simple_loss=0.2984, pruned_loss=0.1094, over 973355.88 frames.], batch size: 19, lr: 2.08e-03
2022-05-03 13:45:44,978 INFO [train.py:715] (4/8) Epoch 0, batch 9200, loss[loss=0.2293, simple_loss=0.2826, pruned_loss=0.08801, over 4843.00 frames.], tot_loss[loss=0.2602, simple_loss=0.2995, pruned_loss=0.1104, over 972993.44 frames.], batch size: 20, lr: 2.07e-03
2022-05-03 13:46:26,064 INFO [train.py:715] (4/8) Epoch 0, batch 9250, loss[loss=0.2316, simple_loss=0.2833, pruned_loss=0.08993, over 4789.00 frames.], tot_loss[loss=0.2604, simple_loss=0.2994, pruned_loss=0.1107, over 972767.55 frames.], batch size: 17, lr: 2.07e-03
2022-05-03 13:47:06,379 INFO [train.py:715] (4/8) Epoch 0, batch 9300, loss[loss=0.2714, simple_loss=0.3178, pruned_loss=0.1126, over 4979.00 frames.], tot_loss[loss=0.2588, simple_loss=0.2985, pruned_loss=0.1095, over 973208.03 frames.], batch size: 24, lr: 2.06e-03
2022-05-03 13:47:45,667 INFO [train.py:715] (4/8) Epoch 0, batch 9350, loss[loss=0.2412, simple_loss=0.2872, pruned_loss=0.09759, over 4857.00 frames.], tot_loss[loss=0.2576, simple_loss=0.2981, pruned_loss=0.1086, over 973449.01 frames.], batch size: 22, lr: 2.06e-03
2022-05-03 13:48:27,111 INFO [train.py:715] (4/8) Epoch 0, batch 9400, loss[loss=0.2245, simple_loss=0.2685, pruned_loss=0.09031, over 4779.00 frames.], tot_loss[loss=0.2556, simple_loss=0.2969, pruned_loss=0.1072, over 973203.23 frames.], batch size: 18, lr: 2.06e-03
2022-05-03 13:49:07,597 INFO [train.py:715] (4/8) Epoch 0, batch 9450, loss[loss=0.26, simple_loss=0.2947, pruned_loss=0.1127, over 4841.00 frames.], tot_loss[loss=0.2566, simple_loss=0.2973, pruned_loss=0.108, over 972992.22 frames.], batch size: 15, lr: 2.05e-03
2022-05-03 13:49:47,924 INFO [train.py:715] (4/8) Epoch 0, batch 9500, loss[loss=0.2268, simple_loss=0.281, pruned_loss=0.08635, over 4769.00 frames.], tot_loss[loss=0.2543, simple_loss=0.2954, pruned_loss=0.1066, over 972503.91 frames.], batch size: 19, lr: 2.05e-03
2022-05-03 13:50:28,007 INFO [train.py:715] (4/8) Epoch 0, batch 9550, loss[loss=0.2803, simple_loss=0.3154, pruned_loss=0.1226, over 4925.00 frames.], tot_loss[loss=0.2546, simple_loss=0.2953, pruned_loss=0.1069, over 972375.23 frames.], batch size: 17, lr: 2.04e-03
2022-05-03 13:51:08,461 INFO [train.py:715] (4/8) Epoch 0, batch 9600, loss[loss=0.2622, simple_loss=0.3075, pruned_loss=0.1084, over 4830.00 frames.], tot_loss[loss=0.2541, simple_loss=0.295, pruned_loss=0.1066, over 971726.97 frames.], batch size: 26, lr: 2.04e-03
2022-05-03 13:51:48,903 INFO [train.py:715] (4/8) Epoch 0, batch 9650, loss[loss=0.2335, simple_loss=0.2741, pruned_loss=0.09643, over 4858.00 frames.], tot_loss[loss=0.2533, simple_loss=0.2944, pruned_loss=0.1061, over 971985.15 frames.], batch size: 32, lr: 2.03e-03
2022-05-03 13:52:27,668 INFO [train.py:715] (4/8) Epoch 0, batch 9700, loss[loss=0.2522, simple_loss=0.2932, pruned_loss=0.1056, over 4803.00 frames.], tot_loss[loss=0.2541, simple_loss=0.2948, pruned_loss=0.1067, over 972463.36 frames.], batch size: 15, lr: 2.03e-03
2022-05-03 13:53:08,237 INFO [train.py:715] (4/8) Epoch 0, batch 9750, loss[loss=0.2673, simple_loss=0.3053, pruned_loss=0.1147, over 4966.00 frames.], tot_loss[loss=0.2548, simple_loss=0.2954, pruned_loss=0.1071, over 972997.33 frames.], batch size: 35, lr: 2.03e-03
2022-05-03 13:53:47,971 INFO [train.py:715] (4/8) Epoch 0, batch 9800, loss[loss=0.2015, simple_loss=0.2488, pruned_loss=0.07715, over 4750.00 frames.], tot_loss[loss=0.2544, simple_loss=0.2953, pruned_loss=0.1068, over 972674.68 frames.], batch size: 16, lr: 2.02e-03
2022-05-03 13:54:27,875 INFO [train.py:715] (4/8) Epoch 0, batch 9850, loss[loss=0.2142, simple_loss=0.2653, pruned_loss=0.08157, over 4978.00 frames.], tot_loss[loss=0.252, simple_loss=0.2936, pruned_loss=0.1052, over 972857.90 frames.], batch size: 35, lr: 2.02e-03
2022-05-03 13:55:07,631 INFO [train.py:715] (4/8) Epoch 0, batch 9900, loss[loss=0.2035, simple_loss=0.2588, pruned_loss=0.07409, over 4826.00 frames.], tot_loss[loss=0.2512, simple_loss=0.293, pruned_loss=0.1047, over 973328.52 frames.], batch size: 13, lr: 2.01e-03
2022-05-03 13:55:47,708 INFO [train.py:715] (4/8) Epoch 0, batch 9950, loss[loss=0.2291, simple_loss=0.2775, pruned_loss=0.09038, over 4987.00 frames.], tot_loss[loss=0.2518, simple_loss=0.2936, pruned_loss=0.105, over 973599.14 frames.], batch size: 28, lr: 2.01e-03
2022-05-03 13:56:27,932 INFO [train.py:715] (4/8) Epoch 0, batch 10000, loss[loss=0.2671, simple_loss=0.3133, pruned_loss=0.1105, over 4854.00 frames.], tot_loss[loss=0.2528, simple_loss=0.2948, pruned_loss=0.1054, over 972446.33 frames.], batch size: 20, lr: 2.01e-03
2022-05-03 13:57:07,304 INFO [train.py:715] (4/8) Epoch 0, batch 10050, loss[loss=0.2599, simple_loss=0.3164, pruned_loss=0.1017, over 4971.00 frames.], tot_loss[loss=0.2529, simple_loss=0.2949, pruned_loss=0.1055, over 973584.44 frames.], batch size: 15, lr: 2.00e-03
2022-05-03 13:57:47,854 INFO [train.py:715] (4/8) Epoch 0, batch 10100, loss[loss=0.253, simple_loss=0.2921, pruned_loss=0.107, over 4756.00 frames.], tot_loss[loss=0.2517, simple_loss=0.2939, pruned_loss=0.1048, over 972460.19 frames.], batch size: 19, lr: 2.00e-03
2022-05-03 13:58:27,699 INFO [train.py:715] (4/8) Epoch 0, batch 10150, loss[loss=0.2155, simple_loss=0.2611, pruned_loss=0.08494, over 4970.00 frames.], tot_loss[loss=0.2516, simple_loss=0.2937, pruned_loss=0.1048, over 972208.56 frames.], batch size: 35, lr: 1.99e-03
2022-05-03 13:59:07,280 INFO [train.py:715] (4/8) Epoch 0, batch 10200, loss[loss=0.2435, simple_loss=0.2927, pruned_loss=0.09711, over 4917.00 frames.], tot_loss[loss=0.2516, simple_loss=0.2938, pruned_loss=0.1047, over 972804.82 frames.], batch size: 23, lr: 1.99e-03
2022-05-03 13:59:47,202 INFO [train.py:715] (4/8) Epoch 0, batch 10250, loss[loss=0.2671, simple_loss=0.2981, pruned_loss=0.118, over 4894.00 frames.], tot_loss[loss=0.2518, simple_loss=0.294, pruned_loss=0.1048, over 973085.64 frames.], batch size: 19, lr: 1.99e-03
2022-05-03 14:00:28,074 INFO [train.py:715] (4/8) Epoch 0, batch 10300, loss[loss=0.3041, simple_loss=0.3359, pruned_loss=0.1361, over 4771.00 frames.], tot_loss[loss=0.2531, simple_loss=0.2951, pruned_loss=0.1056, over 973000.67 frames.], batch size: 17, lr: 1.98e-03
2022-05-03 14:01:08,330 INFO [train.py:715] (4/8) Epoch 0, batch 10350, loss[loss=0.275, simple_loss=0.3109, pruned_loss=0.1196, over 4927.00 frames.], tot_loss[loss=0.2554, simple_loss=0.2967, pruned_loss=0.107, over 973240.49 frames.], batch size: 21, lr: 1.98e-03
2022-05-03 14:01:47,788 INFO [train.py:715] (4/8) Epoch 0, batch 10400, loss[loss=0.3622, simple_loss=0.3799, pruned_loss=0.1722, over 4958.00 frames.], tot_loss[loss=0.2539, simple_loss=0.2962, pruned_loss=0.1058, over 973524.42 frames.], batch size: 21, lr: 1.97e-03
2022-05-03 14:02:28,418 INFO [train.py:715] (4/8) Epoch 0, batch 10450, loss[loss=0.2079, simple_loss=0.2726, pruned_loss=0.0716, over 4916.00 frames.], tot_loss[loss=0.2534, simple_loss=0.2961, pruned_loss=0.1053, over 973017.36 frames.], batch size: 17, lr: 1.97e-03
2022-05-03 14:03:09,159 INFO [train.py:715] (4/8) Epoch 0, batch 10500, loss[loss=0.2583, simple_loss=0.2957, pruned_loss=0.1104, over 4987.00 frames.], tot_loss[loss=0.2519, simple_loss=0.295, pruned_loss=0.1044, over 972936.53 frames.], batch size: 31, lr: 1.97e-03
2022-05-03 14:03:48,866 INFO [train.py:715] (4/8) Epoch 0, batch 10550, loss[loss=0.281, simple_loss=0.3207, pruned_loss=0.1207, over 4837.00 frames.], tot_loss[loss=0.2511, simple_loss=0.2945, pruned_loss=0.1038, over 972660.94 frames.], batch size: 30, lr: 1.96e-03
2022-05-03 14:04:28,875 INFO [train.py:715] (4/8) Epoch 0, batch 10600, loss[loss=0.2642, simple_loss=0.3083, pruned_loss=0.1101, over 4977.00 frames.], tot_loss[loss=0.2507, simple_loss=0.2941, pruned_loss=0.1036, over 972359.54 frames.], batch size: 25, lr: 1.96e-03
2022-05-03 14:05:09,748 INFO [train.py:715] (4/8) Epoch 0, batch 10650, loss[loss=0.2385, simple_loss=0.2921, pruned_loss=0.09247, over 4748.00 frames.], tot_loss[loss=0.2515, simple_loss=0.2947, pruned_loss=0.1042, over 973150.32 frames.], batch size: 19, lr: 1.96e-03
2022-05-03 14:05:49,654 INFO [train.py:715] (4/8) Epoch 0, batch 10700, loss[loss=0.2313, simple_loss=0.2784, pruned_loss=0.0921, over 4748.00 frames.], tot_loss[loss=0.25, simple_loss=0.2939, pruned_loss=0.1031, over 973360.89 frames.], batch size: 16, lr: 1.95e-03
2022-05-03 14:06:29,544 INFO [train.py:715] (4/8) Epoch 0, batch 10750, loss[loss=0.1997, simple_loss=0.2698, pruned_loss=0.06483, over 4868.00 frames.], tot_loss[loss=0.2489, simple_loss=0.2932, pruned_loss=0.1023, over 973860.28 frames.], batch size: 20, lr: 1.95e-03
2022-05-03 14:07:09,720 INFO [train.py:715] (4/8) Epoch 0, batch 10800, loss[loss=0.2714, simple_loss=0.304, pruned_loss=0.1194, over 4976.00 frames.], tot_loss[loss=0.2487, simple_loss=0.2929, pruned_loss=0.1023, over 973371.54 frames.], batch size: 35, lr: 1.94e-03
2022-05-03 14:07:50,565 INFO [train.py:715] (4/8) Epoch 0, batch 10850, loss[loss=0.2614, simple_loss=0.3062, pruned_loss=0.1083, over 4962.00 frames.], tot_loss[loss=0.2487, simple_loss=0.2926, pruned_loss=0.1024, over 972677.36 frames.], batch size: 24, lr: 1.94e-03
2022-05-03 14:08:30,099 INFO [train.py:715] (4/8) Epoch 0, batch 10900, loss[loss=0.2225, simple_loss=0.2757, pruned_loss=0.08471, over 4874.00 frames.], tot_loss[loss=0.2462, simple_loss=0.2912, pruned_loss=0.1006, over 972037.21 frames.], batch size: 20, lr: 1.94e-03
2022-05-03 14:09:10,037 INFO [train.py:715] (4/8) Epoch 0, batch 10950, loss[loss=0.2549, simple_loss=0.2904, pruned_loss=0.1096, over 4909.00 frames.], tot_loss[loss=0.2462, simple_loss=0.2913, pruned_loss=0.1006, over 971677.02 frames.], batch size: 17, lr: 1.93e-03
2022-05-03 14:09:50,811 INFO [train.py:715] (4/8) Epoch 0, batch 11000, loss[loss=0.2157, simple_loss=0.2641, pruned_loss=0.08367, over 4845.00 frames.], tot_loss[loss=0.245, simple_loss=0.291, pruned_loss=0.09951, over 972195.94 frames.], batch size: 12, lr: 1.93e-03
2022-05-03 14:10:31,098 INFO [train.py:715] (4/8) Epoch 0, batch 11050, loss[loss=0.223, simple_loss=0.2757, pruned_loss=0.08519, over 4709.00 frames.], tot_loss[loss=0.2446, simple_loss=0.2905, pruned_loss=0.09931, over 971664.68 frames.], batch size: 15, lr: 1.93e-03
2022-05-03 14:11:11,141 INFO [train.py:715] (4/8) Epoch 0, batch 11100, loss[loss=0.281, simple_loss=0.3199, pruned_loss=0.1211, over 4845.00 frames.], tot_loss[loss=0.2432, simple_loss=0.2894, pruned_loss=0.09854, over 971514.69 frames.], batch size: 32, lr: 1.92e-03
2022-05-03 14:11:51,016 INFO [train.py:715] (4/8) Epoch 0, batch 11150, loss[loss=0.3005, simple_loss=0.3319, pruned_loss=0.1346, over 4861.00 frames.], tot_loss[loss=0.2454, simple_loss=0.2906, pruned_loss=0.1001, over 971101.26 frames.], batch size: 30, lr: 1.92e-03
2022-05-03 14:12:31,464 INFO [train.py:715] (4/8) Epoch 0, batch 11200, loss[loss=0.286, simple_loss=0.3166, pruned_loss=0.1277, over 4951.00 frames.], tot_loss[loss=0.2463, simple_loss=0.2914, pruned_loss=0.1006, over 970382.46 frames.], batch size: 21, lr: 1.92e-03
2022-05-03 14:13:10,941 INFO [train.py:715] (4/8) Epoch 0, batch 11250, loss[loss=0.289, simple_loss=0.3164, pruned_loss=0.1308, over 4683.00 frames.], tot_loss[loss=0.2461, simple_loss=0.2916, pruned_loss=0.1003, over 970343.67 frames.], batch size: 15, lr: 1.91e-03
2022-05-03 14:13:51,033 INFO [train.py:715] (4/8) Epoch 0, batch 11300, loss[loss=0.208, simple_loss=0.2585, pruned_loss=0.07874, over 4994.00 frames.], tot_loss[loss=0.2458, simple_loss=0.2911, pruned_loss=0.1003, over 970844.09 frames.], batch size: 14, lr: 1.91e-03
2022-05-03 14:14:31,681 INFO [train.py:715] (4/8) Epoch 0, batch 11350, loss[loss=0.2404, simple_loss=0.2875, pruned_loss=0.09669, over 4912.00 frames.], tot_loss[loss=0.2441, simple_loss=0.2896, pruned_loss=0.09933, over 971458.48 frames.], batch size: 17, lr: 1.90e-03
2022-05-03 14:15:12,105 INFO [train.py:715] (4/8) Epoch 0, batch 11400, loss[loss=0.2076, simple_loss=0.2654, pruned_loss=0.07485, over 4966.00 frames.], tot_loss[loss=0.2442, simple_loss=0.29, pruned_loss=0.09924, over 970920.63 frames.], batch size: 25, lr: 1.90e-03
2022-05-03 14:15:51,355 INFO [train.py:715] (4/8) Epoch 0, batch 11450, loss[loss=0.2421, simple_loss=0.2898, pruned_loss=0.09721, over 4689.00 frames.], tot_loss[loss=0.2449, simple_loss=0.2898, pruned_loss=0.09994, over 970714.42 frames.], batch size: 15, lr: 1.90e-03
2022-05-03 14:16:32,011 INFO [train.py:715] (4/8) Epoch 0, batch 11500, loss[loss=0.2415, simple_loss=0.2945, pruned_loss=0.09422, over 4955.00 frames.], tot_loss[loss=0.2454, simple_loss=0.2905, pruned_loss=0.1002, over 972075.12 frames.], batch size: 39, lr: 1.89e-03
2022-05-03 14:17:12,405 INFO [train.py:715] (4/8) Epoch 0, batch 11550, loss[loss=0.2061, simple_loss=0.2616, pruned_loss=0.07535, over 4765.00 frames.], tot_loss[loss=0.2451, simple_loss=0.2903, pruned_loss=0.09995, over 972653.26 frames.], batch size: 12, lr: 1.89e-03
2022-05-03 14:17:52,476 INFO [train.py:715] (4/8) Epoch 0, batch 11600, loss[loss=0.2938, simple_loss=0.3343, pruned_loss=0.1267, over 4970.00 frames.], tot_loss[loss=0.2445, simple_loss=0.2897, pruned_loss=0.09969, over 972583.20 frames.], batch size: 15, lr: 1.89e-03
2022-05-03 14:18:32,571 INFO [train.py:715] (4/8) Epoch 0, batch 11650, loss[loss=0.2538, simple_loss=0.2997, pruned_loss=0.1039, over 4832.00 frames.], tot_loss[loss=0.2452, simple_loss=0.2905, pruned_loss=0.09999, over 972774.51 frames.], batch size: 13, lr: 1.88e-03
2022-05-03 14:19:13,487 INFO [train.py:715] (4/8) Epoch 0, batch 11700, loss[loss=0.2932, simple_loss=0.3317, pruned_loss=0.1273, over 4786.00 frames.], tot_loss[loss=0.2439, simple_loss=0.2896, pruned_loss=0.0991, over 972754.31 frames.], batch size: 14, lr: 1.88e-03
2022-05-03 14:19:53,840 INFO [train.py:715] (4/8) Epoch 0, batch 11750, loss[loss=0.2305, simple_loss=0.2786, pruned_loss=0.09119, over 4785.00 frames.], tot_loss[loss=0.2446, simple_loss=0.2901, pruned_loss=0.09951, over 972711.35 frames.], batch size: 17, lr: 1.88e-03
2022-05-03 14:20:34,216 INFO [train.py:715] (4/8) Epoch 0, batch 11800, loss[loss=0.2445, simple_loss=0.2866, pruned_loss=0.1012, over 4826.00 frames.], tot_loss[loss=0.246, simple_loss=0.291, pruned_loss=0.1005, over 972097.49 frames.], batch size: 26, lr: 1.87e-03
2022-05-03 14:21:14,572 INFO [train.py:715] (4/8) Epoch 0, batch 11850, loss[loss=0.1589, simple_loss=0.2259, pruned_loss=0.04596, over 4970.00 frames.], tot_loss[loss=0.2438, simple_loss=0.2895, pruned_loss=0.09909, over 972092.71 frames.], batch size: 28, lr: 1.87e-03
2022-05-03 14:21:55,674 INFO [train.py:715] (4/8) Epoch 0, batch 11900, loss[loss=0.1912, simple_loss=0.2406, pruned_loss=0.07088, over 4839.00 frames.], tot_loss[loss=0.2416, simple_loss=0.2875, pruned_loss=0.09782, over 972106.24 frames.], batch size: 12, lr: 1.87e-03
2022-05-03 14:22:35,857 INFO [train.py:715] (4/8) Epoch 0, batch 11950, loss[loss=0.2209, simple_loss=0.2813, pruned_loss=0.08025, over 4928.00 frames.], tot_loss[loss=0.2414, simple_loss=0.2874, pruned_loss=0.09773, over 971964.34 frames.], batch size: 23, lr: 1.86e-03
2022-05-03 14:23:15,972 INFO [train.py:715] (4/8) Epoch 0, batch 12000, loss[loss=0.2141, simple_loss=0.2757, pruned_loss=0.07619, over 4865.00 frames.], tot_loss[loss=0.2415, simple_loss=0.2875, pruned_loss=0.09775, over 972283.88 frames.], batch size: 16, lr: 1.86e-03
2022-05-03 14:23:15,972 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 14:23:31,273 INFO [train.py:742] (4/8) Epoch 0, validation: loss=0.1516, simple_loss=0.2368, pruned_loss=0.03315, over 914524.00 frames.
2022-05-03 14:24:11,263 INFO [train.py:715] (4/8) Epoch 0, batch 12050, loss[loss=0.2536, simple_loss=0.3078, pruned_loss=0.09972, over 4888.00 frames.], tot_loss[loss=0.242, simple_loss=0.2877, pruned_loss=0.0981, over 972940.93 frames.], batch size: 22, lr: 1.86e-03
2022-05-03 14:24:51,293 INFO [train.py:715] (4/8) Epoch 0, batch 12100, loss[loss=0.2723, simple_loss=0.3052, pruned_loss=0.1197, over 4882.00 frames.], tot_loss[loss=0.2429, simple_loss=0.2886, pruned_loss=0.09858, over 972903.81 frames.], batch size: 32, lr: 1.85e-03
2022-05-03 14:25:31,592 INFO [train.py:715] (4/8) Epoch 0, batch 12150, loss[loss=0.2578, simple_loss=0.3002, pruned_loss=0.1077, over 4714.00 frames.], tot_loss[loss=0.242, simple_loss=0.2884, pruned_loss=0.09782, over 971530.95 frames.], batch size: 15, lr: 1.85e-03
2022-05-03 14:26:11,158 INFO [train.py:715] (4/8) Epoch 0, batch 12200, loss[loss=0.2143, simple_loss=0.2606, pruned_loss=0.084, over 4879.00 frames.], tot_loss[loss=0.2429, simple_loss=0.289, pruned_loss=0.09841, over 972540.11 frames.], batch size: 32, lr: 1.85e-03
2022-05-03 14:26:51,061 INFO [train.py:715] (4/8) Epoch 0, batch 12250, loss[loss=0.239, simple_loss=0.2779, pruned_loss=0.1, over 4838.00 frames.], tot_loss[loss=0.2444, simple_loss=0.2899, pruned_loss=0.09943, over 972909.16 frames.], batch size: 30, lr: 1.84e-03
2022-05-03 14:27:31,548 INFO [train.py:715] (4/8) Epoch 0, batch 12300, loss[loss=0.2434, simple_loss=0.284, pruned_loss=0.1014, over 4892.00 frames.], tot_loss[loss=0.2434, simple_loss=0.2893, pruned_loss=0.09872, over 974132.08 frames.], batch size: 22, lr: 1.84e-03
2022-05-03 14:28:10,856 INFO [train.py:715] (4/8) Epoch 0, batch 12350, loss[loss=0.2498, simple_loss=0.3059, pruned_loss=0.09689, over 4919.00 frames.], tot_loss[loss=0.2433, simple_loss=0.2896, pruned_loss=0.09846, over 973316.05 frames.], batch size: 18, lr: 1.84e-03
2022-05-03 14:28:50,833 INFO [train.py:715] (4/8) Epoch 0, batch 12400, loss[loss=0.2356, simple_loss=0.2874, pruned_loss=0.09189, over 4750.00 frames.], tot_loss[loss=0.2421, simple_loss=0.2885, pruned_loss=0.09779, over 972211.92 frames.], batch size: 16, lr: 1.83e-03
2022-05-03 14:29:31,157 INFO [train.py:715] (4/8) Epoch 0, batch 12450, loss[loss=0.2277, simple_loss=0.2803, pruned_loss=0.08761, over 4983.00 frames.], tot_loss[loss=0.2439, simple_loss=0.2898, pruned_loss=0.09902, over 973742.50 frames.], batch size: 26, lr: 1.83e-03
2022-05-03 14:30:11,383 INFO [train.py:715] (4/8) Epoch 0, batch 12500, loss[loss=0.2437, simple_loss=0.2875, pruned_loss=0.1, over 4857.00 frames.], tot_loss[loss=0.2441, simple_loss=0.2897, pruned_loss=0.09927, over 974482.53 frames.], batch size: 20, lr: 1.83e-03
2022-05-03 14:30:50,304 INFO [train.py:715] (4/8) Epoch 0, batch 12550, loss[loss=0.2258, simple_loss=0.2705, pruned_loss=0.09058, over 4806.00 frames.], tot_loss[loss=0.2441, simple_loss=0.2894, pruned_loss=0.09944, over 973827.41 frames.], batch size: 14, lr: 1.83e-03
2022-05-03 14:31:30,333 INFO [train.py:715] (4/8) Epoch 0, batch 12600, loss[loss=0.2431, simple_loss=0.2908, pruned_loss=0.09765, over 4815.00 frames.], tot_loss[loss=0.2431, simple_loss=0.2891, pruned_loss=0.09856, over 973005.02 frames.], batch size: 27, lr: 1.82e-03
2022-05-03 14:32:11,362 INFO [train.py:715] (4/8) Epoch 0, batch 12650, loss[loss=0.2901, simple_loss=0.3304, pruned_loss=0.1249, over 4832.00 frames.], tot_loss[loss=0.2418, simple_loss=0.288, pruned_loss=0.09774, over 972480.46 frames.], batch size: 25, lr: 1.82e-03
2022-05-03 14:32:51,083 INFO [train.py:715] (4/8) Epoch 0, batch 12700, loss[loss=0.2285, simple_loss=0.2775, pruned_loss=0.08973, over 4987.00 frames.], tot_loss[loss=0.2422, simple_loss=0.2886, pruned_loss=0.09791, over 972232.30 frames.], batch size: 25, lr: 1.82e-03
2022-05-03 14:33:30,729 INFO [train.py:715] (4/8) Epoch 0, batch 12750, loss[loss=0.2422, simple_loss=0.2964, pruned_loss=0.09397, over 4864.00 frames.], tot_loss[loss=0.2416, simple_loss=0.2881, pruned_loss=0.09753, over 972676.41 frames.], batch size: 20, lr: 1.81e-03
2022-05-03 14:34:11,170 INFO [train.py:715] (4/8) Epoch 0, batch 12800, loss[loss=0.2298, simple_loss=0.2933, pruned_loss=0.08314, over 4765.00 frames.], tot_loss[loss=0.2404, simple_loss=0.2872, pruned_loss=0.09683, over 973142.52 frames.], batch size: 14, lr: 1.81e-03
2022-05-03 14:34:51,654 INFO [train.py:715] (4/8) Epoch 0, batch 12850, loss[loss=0.2127, simple_loss=0.2776, pruned_loss=0.07388, over 4780.00 frames.], tot_loss[loss=0.2386, simple_loss=0.286, pruned_loss=0.09556, over 972800.89 frames.], batch size: 18, lr: 1.81e-03
2022-05-03 14:35:31,479 INFO [train.py:715] (4/8) Epoch 0, batch 12900, loss[loss=0.2562, simple_loss=0.2945, pruned_loss=0.109, over 4941.00 frames.], tot_loss[loss=0.2399, simple_loss=0.2871, pruned_loss=0.09633, over 972501.80 frames.], batch size: 35, lr: 1.80e-03
2022-05-03 14:36:11,737 INFO [train.py:715] (4/8) Epoch 0, batch 12950, loss[loss=0.2776, simple_loss=0.3229, pruned_loss=0.1162, over 4820.00 frames.], tot_loss[loss=0.2404, simple_loss=0.2876, pruned_loss=0.09663, over 972568.11 frames.], batch size: 15, lr: 1.80e-03
2022-05-03 14:36:52,262 INFO [train.py:715] (4/8) Epoch 0, batch 13000, loss[loss=0.1879, simple_loss=0.2524, pruned_loss=0.06172, over 4979.00 frames.], tot_loss[loss=0.2401, simple_loss=0.2871, pruned_loss=0.09656, over 972547.41 frames.], batch size: 24, lr: 1.80e-03
2022-05-03 14:37:32,725 INFO [train.py:715] (4/8) Epoch 0, batch 13050, loss[loss=0.2198, simple_loss=0.2652, pruned_loss=0.08718, over 4895.00 frames.], tot_loss[loss=0.2398, simple_loss=0.2871, pruned_loss=0.09629, over 971565.85 frames.], batch size: 19, lr: 1.79e-03
2022-05-03 14:38:12,065 INFO [train.py:715] (4/8) Epoch 0, batch 13100, loss[loss=0.2192, simple_loss=0.2696, pruned_loss=0.08442, over 4829.00 frames.], tot_loss[loss=0.2379, simple_loss=0.2854, pruned_loss=0.09522, over 972486.17 frames.], batch size: 13, lr: 1.79e-03
2022-05-03 14:38:52,498 INFO [train.py:715] (4/8) Epoch 0, batch 13150, loss[loss=0.2085, simple_loss=0.2586, pruned_loss=0.07924, over 4846.00 frames.], tot_loss[loss=0.2386, simple_loss=0.2857, pruned_loss=0.0958, over 973171.00 frames.], batch size: 30, lr: 1.79e-03
2022-05-03 14:39:32,989 INFO [train.py:715] (4/8) Epoch 0, batch 13200, loss[loss=0.278, simple_loss=0.3214, pruned_loss=0.1173, over 4731.00 frames.], tot_loss[loss=0.2403, simple_loss=0.2869, pruned_loss=0.09686, over 972960.03 frames.], batch size: 16, lr: 1.79e-03
2022-05-03 14:40:12,562 INFO [train.py:715] (4/8) Epoch 0, batch 13250, loss[loss=0.2138, simple_loss=0.2661, pruned_loss=0.08074, over 4881.00 frames.], tot_loss[loss=0.2384, simple_loss=0.2855, pruned_loss=0.09563, over 973373.89 frames.], batch size: 22, lr: 1.78e-03
2022-05-03 14:40:52,440 INFO [train.py:715] (4/8) Epoch 0, batch 13300, loss[loss=0.2379, simple_loss=0.2713, pruned_loss=0.1023, over 4984.00 frames.], tot_loss[loss=0.2375, simple_loss=0.2849, pruned_loss=0.09509, over 973858.29 frames.], batch size: 14, lr: 1.78e-03
2022-05-03 14:41:32,817 INFO [train.py:715] (4/8) Epoch 0, batch 13350, loss[loss=0.2618, simple_loss=0.3018, pruned_loss=0.1109, over 4825.00 frames.], tot_loss[loss=0.238, simple_loss=0.2856, pruned_loss=0.09524, over 973027.73 frames.], batch size: 25, lr: 1.78e-03
2022-05-03 14:42:13,146 INFO [train.py:715] (4/8) Epoch 0, batch 13400, loss[loss=0.2597, simple_loss=0.3023, pruned_loss=0.1086, over 4814.00 frames.], tot_loss[loss=0.2379, simple_loss=0.2859, pruned_loss=0.09493, over 972659.96 frames.], batch size: 26, lr: 1.77e-03
2022-05-03 14:42:52,941 INFO [train.py:715] (4/8) Epoch 0, batch 13450, loss[loss=0.231, simple_loss=0.2796, pruned_loss=0.09119, over 4896.00 frames.], tot_loss[loss=0.2396, simple_loss=0.2871, pruned_loss=0.0961, over 972713.18 frames.], batch size: 19, lr: 1.77e-03
2022-05-03 14:43:33,173 INFO [train.py:715] (4/8) Epoch 0, batch 13500, loss[loss=0.2176, simple_loss=0.2657, pruned_loss=0.08481, over 4737.00 frames.], tot_loss[loss=0.239, simple_loss=0.2865, pruned_loss=0.09579, over 972469.51 frames.], batch size: 12, lr: 1.77e-03
2022-05-03 14:44:13,340 INFO [train.py:715] (4/8) Epoch 0, batch 13550, loss[loss=0.2346, simple_loss=0.2759, pruned_loss=0.09664, over 4982.00 frames.], tot_loss[loss=0.2384, simple_loss=0.2865, pruned_loss=0.09514, over 973036.36 frames.], batch size: 35, lr: 1.77e-03
2022-05-03 14:44:52,789 INFO [train.py:715] (4/8) Epoch 0, batch 13600, loss[loss=0.2196, simple_loss=0.2741, pruned_loss=0.08255, over 4864.00 frames.], tot_loss[loss=0.2379, simple_loss=0.2864, pruned_loss=0.09467, over 972814.74 frames.], batch size: 32, lr: 1.76e-03
2022-05-03 14:45:32,767 INFO [train.py:715] (4/8) Epoch 0, batch 13650, loss[loss=0.2494, simple_loss=0.2954, pruned_loss=0.1017, over 4914.00 frames.], tot_loss[loss=0.2372, simple_loss=0.2854, pruned_loss=0.09446, over 973580.57 frames.], batch size: 18, lr: 1.76e-03
2022-05-03 14:46:12,698 INFO [train.py:715] (4/8) Epoch 0, batch 13700, loss[loss=0.295, simple_loss=0.3332, pruned_loss=0.1284, over 4943.00 frames.], tot_loss[loss=0.2372, simple_loss=0.2854, pruned_loss=0.09449, over 973282.94 frames.], batch size: 21, lr: 1.76e-03
2022-05-03 14:46:52,708 INFO [train.py:715] (4/8) Epoch 0, batch 13750, loss[loss=0.2394, simple_loss=0.2899, pruned_loss=0.09442, over 4695.00 frames.], tot_loss[loss=0.2373, simple_loss=0.2856, pruned_loss=0.09446, over 972758.90 frames.], batch size: 15, lr: 1.75e-03
2022-05-03 14:47:32,535 INFO [train.py:715] (4/8) Epoch 0, batch 13800, loss[loss=0.2003, simple_loss=0.258, pruned_loss=0.07125, over 4809.00 frames.], tot_loss[loss=0.2374, simple_loss=0.2856, pruned_loss=0.09462, over 973387.23 frames.], batch size: 12, lr: 1.75e-03
2022-05-03 14:48:12,865 INFO [train.py:715] (4/8) Epoch 0, batch 13850, loss[loss=0.2068, simple_loss=0.2594, pruned_loss=0.0771, over 4804.00 frames.], tot_loss[loss=0.2359, simple_loss=0.2843, pruned_loss=0.09373, over 972650.99 frames.], batch size: 25, lr: 1.75e-03
2022-05-03 14:48:53,730 INFO [train.py:715] (4/8) Epoch 0, batch 13900, loss[loss=0.2112, simple_loss=0.2621, pruned_loss=0.08018, over 4839.00 frames.], tot_loss[loss=0.2331, simple_loss=0.2826, pruned_loss=0.09177, over 973110.06 frames.], batch size: 13, lr: 1.75e-03
2022-05-03 14:49:33,779 INFO [train.py:715] (4/8) Epoch 0, batch 13950, loss[loss=0.2336, simple_loss=0.2821, pruned_loss=0.0925, over 4696.00 frames.], tot_loss[loss=0.2336, simple_loss=0.2831, pruned_loss=0.09201, over 974042.64 frames.], batch size: 15, lr: 1.74e-03
2022-05-03 14:50:14,371 INFO [train.py:715] (4/8) Epoch 0, batch 14000, loss[loss=0.2871, simple_loss=0.3104, pruned_loss=0.1319, over 4861.00 frames.], tot_loss[loss=0.2338, simple_loss=0.2829, pruned_loss=0.09235, over 973736.57 frames.], batch size: 30, lr: 1.74e-03
2022-05-03 14:50:55,236 INFO [train.py:715] (4/8) Epoch 0, batch 14050, loss[loss=0.2098, simple_loss=0.2802, pruned_loss=0.06966, over 4812.00 frames.], tot_loss[loss=0.2348, simple_loss=0.2838, pruned_loss=0.09293, over 973746.66 frames.], batch size: 27, lr: 1.74e-03
2022-05-03 14:51:35,694 INFO [train.py:715] (4/8) Epoch 0, batch 14100, loss[loss=0.2901, simple_loss=0.3228, pruned_loss=0.1287, over 4783.00 frames.], tot_loss[loss=0.2347, simple_loss=0.2838, pruned_loss=0.09276, over 973362.21 frames.], batch size: 17, lr: 1.73e-03
2022-05-03 14:52:16,198 INFO [train.py:715] (4/8) Epoch 0, batch 14150, loss[loss=0.2175, simple_loss=0.2672, pruned_loss=0.08395, over 4845.00 frames.], tot_loss[loss=0.2365, simple_loss=0.2848, pruned_loss=0.09405, over 973553.98 frames.], batch size: 26, lr: 1.73e-03
2022-05-03 14:52:56,856 INFO [train.py:715] (4/8) Epoch 0, batch 14200, loss[loss=0.2741, simple_loss=0.3026, pruned_loss=0.1228, over 4871.00 frames.], tot_loss[loss=0.2368, simple_loss=0.285, pruned_loss=0.09429, over 973495.49 frames.], batch size: 39, lr: 1.73e-03
2022-05-03 14:53:37,710 INFO [train.py:715] (4/8) Epoch 0, batch 14250, loss[loss=0.2189, simple_loss=0.2725, pruned_loss=0.08266, over 4986.00 frames.], tot_loss[loss=0.2381, simple_loss=0.2861, pruned_loss=0.0951, over 974293.54 frames.], batch size: 15, lr: 1.73e-03
2022-05-03 14:54:18,413 INFO [train.py:715] (4/8) Epoch 0, batch 14300, loss[loss=0.2663, simple_loss=0.2978, pruned_loss=0.1174, over 4925.00 frames.], tot_loss[loss=0.2368, simple_loss=0.2849, pruned_loss=0.09434, over 973927.12 frames.], batch size: 18, lr: 1.72e-03
2022-05-03 14:54:59,474 INFO [train.py:715] (4/8) Epoch 0, batch 14350, loss[loss=0.2133, simple_loss=0.2661, pruned_loss=0.08027, over 4802.00 frames.], tot_loss[loss=0.2377, simple_loss=0.286, pruned_loss=0.09472, over 973640.04 frames.], batch size: 21, lr: 1.72e-03
2022-05-03 14:55:40,712 INFO [train.py:715] (4/8) Epoch 0, batch 14400, loss[loss=0.2344, simple_loss=0.2897, pruned_loss=0.08955, over 4760.00 frames.], tot_loss[loss=0.236, simple_loss=0.285, pruned_loss=0.09349, over 973325.05 frames.], batch size: 19, lr: 1.72e-03
2022-05-03 14:56:21,182 INFO [train.py:715] (4/8) Epoch 0, batch 14450, loss[loss=0.2834, simple_loss=0.3125, pruned_loss=0.1271, over 4943.00 frames.], tot_loss[loss=0.235, simple_loss=0.2838, pruned_loss=0.09315, over 974369.92 frames.], batch size: 21, lr: 1.72e-03
2022-05-03 14:57:01,533 INFO [train.py:715] (4/8) Epoch 0, batch 14500, loss[loss=0.3093, simple_loss=0.3327, pruned_loss=0.143, over 4923.00 frames.], tot_loss[loss=0.2349, simple_loss=0.2838, pruned_loss=0.09297, over 973783.93 frames.], batch size: 18, lr: 1.71e-03
2022-05-03 14:57:42,203 INFO [train.py:715] (4/8) Epoch 0, batch 14550, loss[loss=0.2516, simple_loss=0.2884, pruned_loss=0.1074, over 4977.00 frames.], tot_loss[loss=0.2351, simple_loss=0.2836, pruned_loss=0.09324, over 973952.63 frames.], batch size: 28, lr: 1.71e-03
2022-05-03 14:58:22,166 INFO [train.py:715] (4/8) Epoch 0, batch 14600, loss[loss=0.2474, simple_loss=0.2891, pruned_loss=0.1029, over 4683.00 frames.], tot_loss[loss=0.2339, simple_loss=0.283, pruned_loss=0.09234, over 973313.44 frames.], batch size: 15, lr: 1.71e-03
2022-05-03 14:59:01,452 INFO [train.py:715] (4/8) Epoch 0, batch 14650, loss[loss=0.2382, simple_loss=0.2912, pruned_loss=0.09259, over 4914.00 frames.], tot_loss[loss=0.2335, simple_loss=0.2828, pruned_loss=0.09206, over 973699.20 frames.], batch size: 19, lr: 1.70e-03
2022-05-03 14:59:41,810 INFO [train.py:715] (4/8) Epoch 0, batch 14700, loss[loss=0.1798, simple_loss=0.2319, pruned_loss=0.06387, over 4817.00 frames.], tot_loss[loss=0.2328, simple_loss=0.282, pruned_loss=0.09181, over 973017.32 frames.], batch size: 21, lr: 1.70e-03
2022-05-03 15:00:22,078 INFO [train.py:715] (4/8) Epoch 0, batch 14750, loss[loss=0.226, simple_loss=0.2779, pruned_loss=0.08702, over 4663.00 frames.], tot_loss[loss=0.232, simple_loss=0.2815, pruned_loss=0.09128, over 972141.71 frames.], batch size: 13, lr: 1.70e-03
2022-05-03 15:01:02,119 INFO [train.py:715] (4/8) Epoch 0, batch 14800, loss[loss=0.2013, simple_loss=0.2554, pruned_loss=0.0736, over 4986.00 frames.], tot_loss[loss=0.2338, simple_loss=0.283, pruned_loss=0.09227, over 972492.19 frames.], batch size: 25, lr: 1.70e-03
2022-05-03 15:01:41,993 INFO [train.py:715] (4/8) Epoch 0, batch 14850, loss[loss=0.2429, simple_loss=0.3006, pruned_loss=0.09266, over 4975.00 frames.], tot_loss[loss=0.234, simple_loss=0.2829, pruned_loss=0.09253, over 972774.64 frames.], batch size: 15, lr: 1.69e-03
2022-05-03 15:02:22,716 INFO [train.py:715] (4/8) Epoch 0, batch 14900, loss[loss=0.22, simple_loss=0.2699, pruned_loss=0.08501, over 4954.00 frames.], tot_loss[loss=0.2346, simple_loss=0.2832, pruned_loss=0.09305, over 972289.07 frames.], batch size: 35, lr: 1.69e-03
2022-05-03 15:03:02,603 INFO [train.py:715] (4/8) Epoch 0, batch 14950, loss[loss=0.2249, simple_loss=0.2765, pruned_loss=0.08667, over 4823.00 frames.], tot_loss[loss=0.2349, simple_loss=0.2836, pruned_loss=0.09311, over 972440.31 frames.], batch size: 27, lr: 1.69e-03
2022-05-03 15:03:42,039 INFO [train.py:715] (4/8) Epoch 0, batch 15000, loss[loss=0.1998, simple_loss=0.2594, pruned_loss=0.0701, over 4827.00 frames.], tot_loss[loss=0.233, simple_loss=0.2821, pruned_loss=0.09193, over 972638.68 frames.], batch size: 26, lr: 1.69e-03
2022-05-03 15:03:42,039 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 15:03:53,632 INFO [train.py:742] (4/8) Epoch 0, validation: loss=0.1454, simple_loss=0.2314, pruned_loss=0.02968, over 914524.00 frames.
2022-05-03 15:04:32,987 INFO [train.py:715] (4/8) Epoch 0, batch 15050, loss[loss=0.2853, simple_loss=0.3164, pruned_loss=0.127, over 4964.00 frames.], tot_loss[loss=0.2334, simple_loss=0.2825, pruned_loss=0.09214, over 973243.53 frames.], batch size: 14, lr: 1.68e-03
2022-05-03 15:05:13,559 INFO [train.py:715] (4/8) Epoch 0, batch 15100, loss[loss=0.1944, simple_loss=0.2472, pruned_loss=0.07076, over 4974.00 frames.], tot_loss[loss=0.2329, simple_loss=0.2816, pruned_loss=0.09205, over 973052.55 frames.], batch size: 14, lr: 1.68e-03
2022-05-03 15:05:53,895 INFO [train.py:715] (4/8) Epoch 0, batch 15150, loss[loss=0.2359, simple_loss=0.2825, pruned_loss=0.09467, over 4843.00 frames.], tot_loss[loss=0.2338, simple_loss=0.2829, pruned_loss=0.09232, over 972934.30 frames.], batch size: 30, lr: 1.68e-03
2022-05-03 15:06:33,821 INFO [train.py:715] (4/8) Epoch 0, batch 15200, loss[loss=0.2133, simple_loss=0.2763, pruned_loss=0.07518, over 4987.00 frames.], tot_loss[loss=0.2345, simple_loss=0.2831, pruned_loss=0.09294, over 973171.78 frames.], batch size: 24, lr: 1.68e-03
2022-05-03 15:07:13,389 INFO [train.py:715] (4/8) Epoch 0, batch 15250, loss[loss=0.3043, simple_loss=0.3389, pruned_loss=0.1349, over 4899.00 frames.], tot_loss[loss=0.2338, simple_loss=0.283, pruned_loss=0.09228, over 972898.06 frames.], batch size: 19, lr: 1.67e-03
2022-05-03 15:07:53,252 INFO [train.py:715] (4/8) Epoch 0, batch 15300, loss[loss=0.2731, simple_loss=0.3143, pruned_loss=0.1159, over 4797.00 frames.], tot_loss[loss=0.2348, simple_loss=0.2839, pruned_loss=0.0928, over 972416.19 frames.], batch size: 21, lr: 1.67e-03
2022-05-03 15:08:33,611 INFO [train.py:715] (4/8) Epoch 0, batch 15350, loss[loss=0.2371, simple_loss=0.2787, pruned_loss=0.09777, over 4755.00 frames.], tot_loss[loss=0.2342, simple_loss=0.2837, pruned_loss=0.09234, over 971811.62 frames.], batch size: 18, lr: 1.67e-03
2022-05-03 15:09:13,458 INFO [train.py:715] (4/8) Epoch 0, batch 15400, loss[loss=0.153, simple_loss=0.2106, pruned_loss=0.04771, over 4917.00 frames.], tot_loss[loss=0.2342, simple_loss=0.2834, pruned_loss=0.09246, over 970814.07 frames.], batch size: 23, lr: 1.67e-03
2022-05-03 15:09:53,906 INFO [train.py:715] (4/8) Epoch 0, batch 15450, loss[loss=0.2777, simple_loss=0.3212, pruned_loss=0.1171, over 4890.00 frames.], tot_loss[loss=0.2322, simple_loss=0.2819, pruned_loss=0.09124, over 970368.58 frames.], batch size: 22, lr: 1.66e-03
2022-05-03 15:10:33,370 INFO [train.py:715] (4/8) Epoch 0, batch 15500, loss[loss=0.2243, simple_loss=0.279, pruned_loss=0.08485, over 4951.00 frames.], tot_loss[loss=0.2315, simple_loss=0.2814, pruned_loss=0.09084, over 970948.12 frames.], batch size: 35, lr: 1.66e-03
2022-05-03 15:11:12,568 INFO [train.py:715] (4/8) Epoch 0, batch 15550, loss[loss=0.2132, simple_loss=0.2724, pruned_loss=0.07702, over 4791.00 frames.], tot_loss[loss=0.2321, simple_loss=0.2819, pruned_loss=0.09119, over 971460.67 frames.], batch size: 14, lr: 1.66e-03
2022-05-03 15:11:52,062 INFO [train.py:715] (4/8) Epoch 0, batch 15600, loss[loss=0.1975, simple_loss=0.2596, pruned_loss=0.06767, over 4776.00 frames.], tot_loss[loss=0.2317, simple_loss=0.2818, pruned_loss=0.09078, over 970990.27 frames.], batch size: 17, lr: 1.66e-03
2022-05-03 15:12:31,507 INFO [train.py:715] (4/8) Epoch 0, batch 15650, loss[loss=0.2207, simple_loss=0.2766, pruned_loss=0.08245, over 4990.00 frames.], tot_loss[loss=0.232, simple_loss=0.2816, pruned_loss=0.09115, over 970964.42 frames.], batch size: 25, lr: 1.65e-03
2022-05-03 15:13:11,299 INFO [train.py:715] (4/8) Epoch 0, batch 15700, loss[loss=0.2502, simple_loss=0.3041, pruned_loss=0.09815, over 4910.00 frames.], tot_loss[loss=0.231, simple_loss=0.2807, pruned_loss=0.09063, over 971194.53 frames.], batch size: 18, lr: 1.65e-03
2022-05-03 15:13:50,899 INFO [train.py:715] (4/8) Epoch 0, batch 15750, loss[loss=0.2286, simple_loss=0.2844, pruned_loss=0.08639, over 4862.00 frames.], tot_loss[loss=0.2298, simple_loss=0.2803, pruned_loss=0.08966, over 971722.26 frames.], batch size: 16, lr: 1.65e-03
2022-05-03 15:14:30,844 INFO [train.py:715] (4/8) Epoch 0, batch 15800, loss[loss=0.2608, simple_loss=0.2923, pruned_loss=0.1147, over 4881.00 frames.], tot_loss[loss=0.2296, simple_loss=0.2799, pruned_loss=0.08969, over 970966.33 frames.], batch size: 32, lr: 1.65e-03
2022-05-03 15:15:10,666 INFO [train.py:715] (4/8) Epoch 0, batch 15850, loss[loss=0.2463, simple_loss=0.2993, pruned_loss=0.09665, over 4944.00 frames.], tot_loss[loss=0.2294, simple_loss=0.2794, pruned_loss=0.08968, over 971343.17 frames.], batch size: 23, lr: 1.65e-03
2022-05-03 15:15:50,239 INFO [train.py:715] (4/8) Epoch 0, batch 15900, loss[loss=0.2067, simple_loss=0.2586, pruned_loss=0.07742, over 4646.00 frames.], tot_loss[loss=0.2285, simple_loss=0.2786, pruned_loss=0.08922, over 970966.37 frames.], batch size: 13, lr: 1.64e-03
2022-05-03 15:16:30,471 INFO [train.py:715] (4/8) Epoch 0, batch 15950, loss[loss=0.2405, simple_loss=0.2892, pruned_loss=0.09591, over 4757.00 frames.], tot_loss[loss=0.2286, simple_loss=0.2791, pruned_loss=0.08902, over 971329.21 frames.], batch size: 16, lr: 1.64e-03
2022-05-03 15:17:12,823 INFO [train.py:715] (4/8) Epoch 0, batch 16000, loss[loss=0.3235, simple_loss=0.3551, pruned_loss=0.1459, over 4936.00 frames.], tot_loss[loss=0.228, simple_loss=0.2791, pruned_loss=0.08844, over 971194.77 frames.], batch size: 21, lr: 1.64e-03
2022-05-03 15:17:52,705 INFO [train.py:715] (4/8) Epoch 0, batch 16050, loss[loss=0.2503, simple_loss=0.2986, pruned_loss=0.101, over 4752.00 frames.], tot_loss[loss=0.2282, simple_loss=0.2793, pruned_loss=0.0886, over 971990.81 frames.], batch size: 19, lr: 1.64e-03
2022-05-03 15:18:33,249 INFO [train.py:715] (4/8) Epoch 0, batch 16100, loss[loss=0.2915, simple_loss=0.3218, pruned_loss=0.1306, over 4786.00 frames.], tot_loss[loss=0.2274, simple_loss=0.2786, pruned_loss=0.08812, over 971838.33 frames.], batch size: 18, lr: 1.63e-03
2022-05-03 15:19:13,426 INFO [train.py:715] (4/8) Epoch 0, batch 16150, loss[loss=0.215, simple_loss=0.2767, pruned_loss=0.07666, over 4702.00 frames.], tot_loss[loss=0.2286, simple_loss=0.2793, pruned_loss=0.08892, over 971389.73 frames.], batch size: 15, lr: 1.63e-03
2022-05-03 15:19:52,895 INFO [train.py:715] (4/8) Epoch 0, batch 16200, loss[loss=0.2555, simple_loss=0.2895, pruned_loss=0.1107, over 4646.00 frames.], tot_loss[loss=0.2275, simple_loss=0.2786, pruned_loss=0.08818, over 971524.97 frames.], batch size: 13, lr: 1.63e-03
2022-05-03 15:20:32,318 INFO [train.py:715] (4/8) Epoch 0, batch 16250, loss[loss=0.2217, simple_loss=0.2797, pruned_loss=0.08186, over 4944.00 frames.], tot_loss[loss=0.227, simple_loss=0.2786, pruned_loss=0.08773, over 971894.57 frames.], batch size: 39, lr: 1.63e-03
2022-05-03 15:21:12,242 INFO [train.py:715] (4/8) Epoch 0, batch 16300, loss[loss=0.2151, simple_loss=0.2709, pruned_loss=0.07968, over 4960.00 frames.], tot_loss[loss=0.226, simple_loss=0.2774, pruned_loss=0.08727, over 972593.23 frames.], batch size: 15, lr: 1.62e-03
2022-05-03 15:21:51,666 INFO [train.py:715] (4/8) Epoch 0, batch 16350, loss[loss=0.2266, simple_loss=0.2951, pruned_loss=0.07907, over 4810.00 frames.], tot_loss[loss=0.2265, simple_loss=0.2778, pruned_loss=0.08761, over 972728.43 frames.], batch size: 26, lr: 1.62e-03
2022-05-03 15:22:31,095 INFO [train.py:715] (4/8) Epoch 0, batch 16400, loss[loss=0.2292, simple_loss=0.2866, pruned_loss=0.08585, over 4940.00 frames.], tot_loss[loss=0.2258, simple_loss=0.2774, pruned_loss=0.08707, over 972240.34 frames.], batch size: 29, lr: 1.62e-03
2022-05-03 15:23:11,044 INFO [train.py:715] (4/8) Epoch 0, batch 16450, loss[loss=0.2382, simple_loss=0.2861, pruned_loss=0.09513, over 4691.00 frames.], tot_loss[loss=0.2274, simple_loss=0.2784, pruned_loss=0.08816, over 972014.13 frames.], batch size: 15, lr: 1.62e-03
2022-05-03 15:23:51,576 INFO [train.py:715] (4/8) Epoch 0, batch 16500, loss[loss=0.2089, simple_loss=0.2546, pruned_loss=0.08157, over 4902.00 frames.], tot_loss[loss=0.2265, simple_loss=0.2779, pruned_loss=0.08756, over 972303.01 frames.], batch size: 19, lr: 1.62e-03
2022-05-03 15:24:31,538 INFO [train.py:715] (4/8) Epoch 0, batch 16550, loss[loss=0.2549, simple_loss=0.3152, pruned_loss=0.09726, over 4795.00 frames.], tot_loss[loss=0.2276, simple_loss=0.279, pruned_loss=0.08807, over 972186.84 frames.], batch size: 21, lr: 1.61e-03
2022-05-03 15:25:11,221 INFO [train.py:715] (4/8) Epoch 0, batch 16600, loss[loss=0.1791, simple_loss=0.2401, pruned_loss=0.05903, over 4907.00 frames.], tot_loss[loss=0.2289, simple_loss=0.2803, pruned_loss=0.0887, over 972791.39 frames.], batch size: 19, lr: 1.61e-03
2022-05-03 15:25:50,675 INFO [train.py:715] (4/8) Epoch 0, batch 16650, loss[loss=0.2255, simple_loss=0.2764, pruned_loss=0.08724, over 4768.00 frames.], tot_loss[loss=0.2284, simple_loss=0.28, pruned_loss=0.0884, over 972291.78 frames.], batch size: 14, lr: 1.61e-03
2022-05-03 15:26:30,540 INFO [train.py:715] (4/8) Epoch 0, batch 16700, loss[loss=0.2535, simple_loss=0.293, pruned_loss=0.107, over 4802.00 frames.], tot_loss[loss=0.2273, simple_loss=0.2789, pruned_loss=0.08787, over 972196.74 frames.], batch size: 14, lr: 1.61e-03
2022-05-03 15:27:09,629 INFO [train.py:715] (4/8) Epoch 0, batch 16750, loss[loss=0.1939, simple_loss=0.2523, pruned_loss=0.06771, over 4926.00 frames.], tot_loss[loss=0.2276, simple_loss=0.2793, pruned_loss=0.088, over 972434.89 frames.], batch size: 29, lr: 1.60e-03
2022-05-03 15:27:48,776 INFO [train.py:715] (4/8) Epoch 0, batch 16800, loss[loss=0.17, simple_loss=0.233, pruned_loss=0.05348, over 4833.00 frames.], tot_loss[loss=0.2265, simple_loss=0.2782, pruned_loss=0.08736, over 973585.91 frames.], batch size: 12, lr: 1.60e-03
2022-05-03 15:28:28,412 INFO [train.py:715] (4/8) Epoch 0, batch 16850, loss[loss=0.2009, simple_loss=0.2634, pruned_loss=0.06916, over 4909.00 frames.], tot_loss[loss=0.2264, simple_loss=0.2786, pruned_loss=0.08713, over 973227.76 frames.], batch size: 18, lr: 1.60e-03
2022-05-03 15:29:08,022 INFO [train.py:715] (4/8) Epoch 0, batch 16900, loss[loss=0.2093, simple_loss=0.2617, pruned_loss=0.07845, over 4839.00 frames.], tot_loss[loss=0.2274, simple_loss=0.2792, pruned_loss=0.08775, over 972539.06 frames.], batch size: 15, lr: 1.60e-03
2022-05-03 15:29:47,263 INFO [train.py:715] (4/8) Epoch 0, batch 16950, loss[loss=0.197, simple_loss=0.2572, pruned_loss=0.06835, over 4967.00 frames.], tot_loss[loss=0.2265, simple_loss=0.2785, pruned_loss=0.08725, over 972332.38 frames.], batch size: 15, lr: 1.60e-03
2022-05-03 15:30:27,231 INFO [train.py:715] (4/8) Epoch 0, batch 17000, loss[loss=0.2145, simple_loss=0.2725, pruned_loss=0.07826, over 4903.00 frames.], tot_loss[loss=0.2266, simple_loss=0.2789, pruned_loss=0.08713, over 971967.54 frames.], batch size: 39, lr: 1.59e-03
2022-05-03 15:31:07,728 INFO [train.py:715] (4/8) Epoch 0, batch 17050, loss[loss=0.3214, simple_loss=0.3368, pruned_loss=0.153, over 4835.00 frames.], tot_loss[loss=0.2263, simple_loss=0.2788, pruned_loss=0.08689, over 971382.96 frames.], batch size: 12, lr: 1.59e-03
2022-05-03 15:31:47,483 INFO [train.py:715] (4/8) Epoch 0, batch 17100, loss[loss=0.2114, simple_loss=0.281, pruned_loss=0.07092, over 4868.00 frames.], tot_loss[loss=0.2248, simple_loss=0.2779, pruned_loss=0.08582, over 971981.44 frames.], batch size: 22, lr: 1.59e-03
2022-05-03 15:32:26,649 INFO [train.py:715] (4/8) Epoch 0, batch 17150, loss[loss=0.2393, simple_loss=0.288, pruned_loss=0.09527, over 4941.00 frames.], tot_loss[loss=0.2237, simple_loss=0.2764, pruned_loss=0.0855, over 972952.06 frames.], batch size: 21, lr: 1.59e-03
2022-05-03 15:33:06,919 INFO [train.py:715] (4/8) Epoch 0, batch 17200, loss[loss=0.2286, simple_loss=0.2701, pruned_loss=0.0935, over 4775.00 frames.], tot_loss[loss=0.2242, simple_loss=0.277, pruned_loss=0.08573, over 972961.25 frames.], batch size: 17, lr: 1.58e-03
2022-05-03 15:33:46,677 INFO [train.py:715] (4/8) Epoch 0, batch 17250, loss[loss=0.2363, simple_loss=0.2885, pruned_loss=0.09206, over 4775.00 frames.], tot_loss[loss=0.2242, simple_loss=0.277, pruned_loss=0.08565, over 972559.81 frames.], batch size: 14, lr: 1.58e-03
2022-05-03 15:34:26,232 INFO [train.py:715] (4/8) Epoch 0, batch 17300, loss[loss=0.2068, simple_loss=0.2558, pruned_loss=0.0789, over 4985.00 frames.], tot_loss[loss=0.2235, simple_loss=0.2762, pruned_loss=0.08544, over 971890.28 frames.], batch size: 16, lr: 1.58e-03
2022-05-03 15:35:06,289 INFO [train.py:715] (4/8) Epoch 0, batch 17350, loss[loss=0.2199, simple_loss=0.2546, pruned_loss=0.09261, over 4818.00 frames.], tot_loss[loss=0.2246, simple_loss=0.277, pruned_loss=0.08611, over 972067.42 frames.], batch size: 12, lr: 1.58e-03
2022-05-03 15:35:46,527 INFO [train.py:715] (4/8) Epoch 0, batch 17400, loss[loss=0.2214, simple_loss=0.2699, pruned_loss=0.08649, over 4976.00 frames.], tot_loss[loss=0.2261, simple_loss=0.2779, pruned_loss=0.08713, over 971976.74 frames.], batch size: 28, lr: 1.58e-03
2022-05-03 15:36:26,419 INFO [train.py:715] (4/8) Epoch 0, batch 17450, loss[loss=0.2383, simple_loss=0.301, pruned_loss=0.08776, over 4956.00 frames.], tot_loss[loss=0.2241, simple_loss=0.2767, pruned_loss=0.08578, over 973191.83 frames.], batch size: 21, lr: 1.57e-03
2022-05-03 15:37:07,035 INFO [train.py:715] (4/8) Epoch 0, batch 17500, loss[loss=0.1899, simple_loss=0.2551, pruned_loss=0.06236, over 4944.00 frames.], tot_loss[loss=0.2238, simple_loss=0.2763, pruned_loss=0.08562, over 972410.33 frames.], batch size: 21, lr: 1.57e-03
2022-05-03 15:37:47,460 INFO [train.py:715] (4/8) Epoch 0, batch 17550, loss[loss=0.1657, simple_loss=0.2385, pruned_loss=0.04639, over 4810.00 frames.], tot_loss[loss=0.2247, simple_loss=0.2772, pruned_loss=0.08611, over 972724.23 frames.], batch size: 26, lr: 1.57e-03
2022-05-03 15:38:27,017 INFO [train.py:715] (4/8) Epoch 0, batch 17600, loss[loss=0.2436, simple_loss=0.2984, pruned_loss=0.09439, over 4761.00 frames.], tot_loss[loss=0.2233, simple_loss=0.2762, pruned_loss=0.0852, over 972538.73 frames.], batch size: 19, lr: 1.57e-03
2022-05-03 15:39:06,935 INFO [train.py:715] (4/8) Epoch 0, batch 17650, loss[loss=0.2101, simple_loss=0.2757, pruned_loss=0.07226, over 4930.00 frames.], tot_loss[loss=0.2233, simple_loss=0.2766, pruned_loss=0.08498, over 973178.14 frames.], batch size: 29, lr: 1.57e-03
2022-05-03 15:39:47,479 INFO [train.py:715] (4/8) Epoch 0, batch 17700, loss[loss=0.1915, simple_loss=0.25, pruned_loss=0.06651, over 4940.00 frames.], tot_loss[loss=0.2231, simple_loss=0.2763, pruned_loss=0.08499, over 974175.63 frames.], batch size: 14, lr: 1.56e-03
2022-05-03 15:40:27,378 INFO [train.py:715] (4/8) Epoch 0, batch 17750, loss[loss=0.1783, simple_loss=0.2395, pruned_loss=0.0585, over 4770.00 frames.], tot_loss[loss=0.2233, simple_loss=0.2766, pruned_loss=0.08507, over 974077.61 frames.], batch size: 14, lr: 1.56e-03
2022-05-03 15:41:07,053 INFO [train.py:715] (4/8) Epoch 0, batch 17800, loss[loss=0.191, simple_loss=0.2375, pruned_loss=0.07229, over 4814.00 frames.], tot_loss[loss=0.2243, simple_loss=0.2768, pruned_loss=0.08591, over 974800.32 frames.], batch size: 14, lr: 1.56e-03
2022-05-03 15:41:47,856 INFO [train.py:715] (4/8) Epoch 0, batch 17850, loss[loss=0.215, simple_loss=0.2682, pruned_loss=0.08093, over 4799.00 frames.], tot_loss[loss=0.2245, simple_loss=0.2772, pruned_loss=0.0859, over 974086.67 frames.], batch size: 17, lr: 1.56e-03
2022-05-03 15:42:28,480 INFO [train.py:715] (4/8) Epoch 0, batch 17900, loss[loss=0.3439, simple_loss=0.3493, pruned_loss=0.1693, over 4808.00 frames.], tot_loss[loss=0.2249, simple_loss=0.2771, pruned_loss=0.08638, over 973524.02 frames.], batch size: 21, lr: 1.56e-03
2022-05-03 15:43:07,988 INFO [train.py:715] (4/8) Epoch 0, batch 17950, loss[loss=0.2295, simple_loss=0.2785, pruned_loss=0.09024, over 4727.00 frames.], tot_loss[loss=0.2243, simple_loss=0.2763, pruned_loss=0.08614, over 972462.56 frames.], batch size: 16, lr: 1.55e-03
2022-05-03 15:43:48,219 INFO [train.py:715] (4/8) Epoch 0, batch 18000, loss[loss=0.2266, simple_loss=0.2738, pruned_loss=0.08974, over 4876.00 frames.], tot_loss[loss=0.2253, simple_loss=0.2771, pruned_loss=0.08673, over 972447.90 frames.], batch size: 22, lr: 1.55e-03
2022-05-03 15:43:48,220 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 15:43:57,826 INFO [train.py:742] (4/8) Epoch 0, validation: loss=0.141, simple_loss=0.228, pruned_loss=0.02706, over 914524.00 frames.
2022-05-03 15:44:38,090 INFO [train.py:715] (4/8) Epoch 0, batch 18050, loss[loss=0.2476, simple_loss=0.2944, pruned_loss=0.1004, over 4780.00 frames.], tot_loss[loss=0.226, simple_loss=0.2774, pruned_loss=0.08727, over 971457.36 frames.], batch size: 17, lr: 1.55e-03
2022-05-03 15:45:18,340 INFO [train.py:715] (4/8) Epoch 0, batch 18100, loss[loss=0.2051, simple_loss=0.2605, pruned_loss=0.07479, over 4957.00 frames.], tot_loss[loss=0.2247, simple_loss=0.2767, pruned_loss=0.08631, over 971243.15 frames.], batch size: 21, lr: 1.55e-03
2022-05-03 15:45:58,158 INFO [train.py:715] (4/8) Epoch 0, batch 18150, loss[loss=0.2467, simple_loss=0.2856, pruned_loss=0.1039, over 4837.00 frames.], tot_loss[loss=0.2241, simple_loss=0.2764, pruned_loss=0.08588, over 971209.96 frames.], batch size: 15, lr: 1.55e-03
2022-05-03 15:46:37,566 INFO [train.py:715] (4/8) Epoch 0, batch 18200, loss[loss=0.216, simple_loss=0.2694, pruned_loss=0.08129, over 4828.00 frames.], tot_loss[loss=0.2226, simple_loss=0.2754, pruned_loss=0.08496, over 971427.16 frames.], batch size: 26, lr: 1.54e-03
2022-05-03 15:47:17,759 INFO [train.py:715] (4/8) Epoch 0, batch 18250, loss[loss=0.2481, simple_loss=0.2995, pruned_loss=0.09836, over 4872.00 frames.], tot_loss[loss=0.2219, simple_loss=0.2753, pruned_loss=0.08424, over 971320.95 frames.], batch size: 20, lr: 1.54e-03
2022-05-03 15:47:59,042 INFO [train.py:715] (4/8) Epoch 0, batch 18300, loss[loss=0.2197, simple_loss=0.2781, pruned_loss=0.08065, over 4777.00 frames.], tot_loss[loss=0.2231, simple_loss=0.2765, pruned_loss=0.08486, over 972004.12 frames.], batch size: 14, lr: 1.54e-03
2022-05-03 15:48:38,801 INFO [train.py:715] (4/8) Epoch 0, batch 18350, loss[loss=0.1951, simple_loss=0.2459, pruned_loss=0.07218, over 4918.00 frames.], tot_loss[loss=0.2215, simple_loss=0.2747, pruned_loss=0.08417, over 972187.72 frames.], batch size: 18, lr: 1.54e-03
2022-05-03 15:49:19,068 INFO [train.py:715] (4/8) Epoch 0, batch 18400, loss[loss=0.2064, simple_loss=0.2581, pruned_loss=0.0773, over 4888.00 frames.], tot_loss[loss=0.2218, simple_loss=0.275, pruned_loss=0.08435, over 972095.95 frames.], batch size: 16, lr: 1.54e-03
2022-05-03 15:49:59,576 INFO [train.py:715] (4/8) Epoch 0, batch 18450, loss[loss=0.2369, simple_loss=0.2788, pruned_loss=0.09752, over 4962.00 frames.], tot_loss[loss=0.2204, simple_loss=0.2737, pruned_loss=0.08359, over 972377.96 frames.], batch size: 35, lr: 1.53e-03
2022-05-03 15:50:39,244 INFO [train.py:715] (4/8) Epoch 0, batch 18500, loss[loss=0.2571, simple_loss=0.3177, pruned_loss=0.09823, over 4840.00 frames.], tot_loss[loss=0.2222, simple_loss=0.2756, pruned_loss=0.08439, over 972729.10 frames.], batch size: 30, lr: 1.53e-03
2022-05-03 15:51:19,774 INFO [train.py:715] (4/8) Epoch 0, batch 18550, loss[loss=0.1988, simple_loss=0.2637, pruned_loss=0.06692, over 4899.00 frames.], tot_loss[loss=0.2231, simple_loss=0.2761, pruned_loss=0.08498, over 973664.03 frames.], batch size: 19, lr: 1.53e-03
2022-05-03 15:52:00,079 INFO [train.py:715] (4/8) Epoch 0, batch 18600, loss[loss=0.2151, simple_loss=0.2639, pruned_loss=0.08317, over 4978.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2761, pruned_loss=0.08466, over 972971.68 frames.], batch size: 15, lr: 1.53e-03
2022-05-03 15:52:40,190 INFO [train.py:715] (4/8) Epoch 0, batch 18650, loss[loss=0.191, simple_loss=0.2519, pruned_loss=0.065, over 4801.00 frames.], tot_loss[loss=0.2243, simple_loss=0.2772, pruned_loss=0.08572, over 972963.04 frames.], batch size: 21, lr: 1.53e-03
2022-05-03 15:53:19,598 INFO [train.py:715] (4/8) Epoch 0, batch 18700, loss[loss=0.225, simple_loss=0.2761, pruned_loss=0.08698, over 4851.00 frames.], tot_loss[loss=0.2227, simple_loss=0.2762, pruned_loss=0.08455, over 972807.93 frames.], batch size: 32, lr: 1.52e-03
2022-05-03 15:53:59,905 INFO [train.py:715] (4/8) Epoch 0, batch 18750, loss[loss=0.2218, simple_loss=0.2706, pruned_loss=0.08653, over 4870.00 frames.], tot_loss[loss=0.2212, simple_loss=0.2748, pruned_loss=0.08375, over 972992.38 frames.], batch size: 32, lr: 1.52e-03
2022-05-03 15:54:41,174 INFO [train.py:715] (4/8) Epoch 0, batch 18800, loss[loss=0.2014, simple_loss=0.2552, pruned_loss=0.07378, over 4824.00 frames.], tot_loss[loss=0.2216, simple_loss=0.275, pruned_loss=0.08412, over 972250.91 frames.], batch size: 26, lr: 1.52e-03
2022-05-03 15:55:20,400 INFO [train.py:715] (4/8) Epoch 0, batch 18850, loss[loss=0.2247, simple_loss=0.2792, pruned_loss=0.08517, over 4778.00 frames.], tot_loss[loss=0.2207, simple_loss=0.2741, pruned_loss=0.08365, over 972276.99 frames.], batch size: 14, lr: 1.52e-03
2022-05-03 15:56:01,307 INFO [train.py:715] (4/8) Epoch 0, batch 18900, loss[loss=0.2254, simple_loss=0.2761, pruned_loss=0.08739, over 4906.00 frames.], tot_loss[loss=0.2212, simple_loss=0.2743, pruned_loss=0.08398, over 972388.29 frames.], batch size: 17, lr: 1.52e-03
2022-05-03 15:56:41,739 INFO [train.py:715] (4/8) Epoch 0, batch 18950, loss[loss=0.211, simple_loss=0.2668, pruned_loss=0.07759, over 4961.00 frames.], tot_loss[loss=0.2212, simple_loss=0.2746, pruned_loss=0.08393, over 971912.48 frames.], batch size: 35, lr: 1.52e-03
2022-05-03 15:57:21,401 INFO [train.py:715] (4/8) Epoch 0, batch 19000, loss[loss=0.1675, simple_loss=0.223, pruned_loss=0.05603, over 4805.00 frames.], tot_loss[loss=0.2206, simple_loss=0.2739, pruned_loss=0.08365, over 971657.02 frames.], batch size: 13, lr: 1.51e-03
2022-05-03 15:58:01,847 INFO [train.py:715] (4/8) Epoch 0, batch 19050, loss[loss=0.2027, simple_loss=0.2481, pruned_loss=0.07859, over 4761.00 frames.], tot_loss[loss=0.221, simple_loss=0.2744, pruned_loss=0.08382, over 971801.87 frames.], batch size: 17, lr: 1.51e-03
2022-05-03 15:58:42,180 INFO [train.py:715] (4/8) Epoch 0, batch 19100, loss[loss=0.2258, simple_loss=0.2764, pruned_loss=0.0876, over 4813.00 frames.], tot_loss[loss=0.2206, simple_loss=0.2737, pruned_loss=0.0837, over 971916.60 frames.], batch size: 26, lr: 1.51e-03
2022-05-03 15:59:22,501 INFO [train.py:715] (4/8) Epoch 0, batch 19150, loss[loss=0.1936, simple_loss=0.2513, pruned_loss=0.06801, over 4979.00 frames.], tot_loss[loss=0.2185, simple_loss=0.2722, pruned_loss=0.08238, over 972449.20 frames.], batch size: 35, lr: 1.51e-03
2022-05-03 16:00:01,714 INFO [train.py:715] (4/8) Epoch 0, batch 19200, loss[loss=0.2037, simple_loss=0.2592, pruned_loss=0.07407, over 4947.00 frames.], tot_loss[loss=0.2176, simple_loss=0.2715, pruned_loss=0.08186, over 973005.40 frames.], batch size: 21, lr: 1.51e-03
2022-05-03 16:00:42,578 INFO [train.py:715] (4/8) Epoch 0, batch 19250, loss[loss=0.205, simple_loss=0.2678, pruned_loss=0.07112, over 4960.00 frames.], tot_loss[loss=0.2193, simple_loss=0.2733, pruned_loss=0.08261, over 973157.78 frames.], batch size: 24, lr: 1.50e-03
2022-05-03 16:01:23,351 INFO [train.py:715] (4/8) Epoch 0, batch 19300, loss[loss=0.2436, simple_loss=0.2892, pruned_loss=0.09899, over 4774.00 frames.], tot_loss[loss=0.2199, simple_loss=0.2738, pruned_loss=0.08293, over 972276.80 frames.], batch size: 17, lr: 1.50e-03
2022-05-03 16:02:03,055 INFO [train.py:715] (4/8) Epoch 0, batch 19350, loss[loss=0.2351, simple_loss=0.287, pruned_loss=0.09162, over 4870.00 frames.], tot_loss[loss=0.2205, simple_loss=0.2738, pruned_loss=0.08357, over 971484.86 frames.], batch size: 16, lr: 1.50e-03
2022-05-03 16:02:43,210 INFO [train.py:715] (4/8) Epoch 0, batch 19400, loss[loss=0.2166, simple_loss=0.2732, pruned_loss=0.07996, over 4830.00 frames.], tot_loss[loss=0.2199, simple_loss=0.2741, pruned_loss=0.0828, over 971625.65 frames.], batch size: 26, lr: 1.50e-03
2022-05-03 16:03:24,061 INFO [train.py:715] (4/8) Epoch 0, batch 19450, loss[loss=0.1992, simple_loss=0.2581, pruned_loss=0.07017, over 4921.00 frames.], tot_loss[loss=0.2193, simple_loss=0.2736, pruned_loss=0.08244, over 972236.73 frames.], batch size: 18, lr: 1.50e-03
2022-05-03 16:04:03,571 INFO [train.py:715] (4/8) Epoch 0, batch 19500, loss[loss=0.1891, simple_loss=0.2459, pruned_loss=0.06615, over 4833.00 frames.], tot_loss[loss=0.2199, simple_loss=0.2744, pruned_loss=0.08274, over 971767.30 frames.], batch size: 15, lr: 1.50e-03
2022-05-03 16:04:42,925 INFO [train.py:715] (4/8) Epoch 0, batch 19550, loss[loss=0.2389, simple_loss=0.2966, pruned_loss=0.09063, over 4880.00 frames.], tot_loss[loss=0.2201, simple_loss=0.2742, pruned_loss=0.08304, over 971028.56 frames.], batch size: 22, lr: 1.49e-03
2022-05-03 16:05:23,274 INFO [train.py:715] (4/8) Epoch 0, batch 19600, loss[loss=0.2071, simple_loss=0.2459, pruned_loss=0.08416, over 4976.00 frames.], tot_loss[loss=0.2213, simple_loss=0.2748, pruned_loss=0.08392, over 971360.33 frames.], batch size: 16, lr: 1.49e-03
2022-05-03 16:06:03,058 INFO [train.py:715] (4/8) Epoch 0, batch 19650, loss[loss=0.22, simple_loss=0.2752, pruned_loss=0.08244, over 4986.00 frames.], tot_loss[loss=0.2212, simple_loss=0.2746, pruned_loss=0.0839, over 971418.44 frames.], batch size: 25, lr: 1.49e-03
2022-05-03 16:06:42,545 INFO [train.py:715] (4/8) Epoch 0, batch 19700, loss[loss=0.2455, simple_loss=0.2912, pruned_loss=0.09988, over 4944.00 frames.], tot_loss[loss=0.2211, simple_loss=0.2744, pruned_loss=0.08387, over 971209.12 frames.], batch size: 35, lr: 1.49e-03
2022-05-03 16:07:22,615 INFO [train.py:715] (4/8) Epoch 0, batch 19750, loss[loss=0.2541, simple_loss=0.3062, pruned_loss=0.101, over 4787.00 frames.], tot_loss[loss=0.2215, simple_loss=0.2751, pruned_loss=0.08389, over 972773.61 frames.], batch size: 17, lr: 1.49e-03
2022-05-03 16:08:02,295 INFO [train.py:715] (4/8) Epoch 0, batch 19800, loss[loss=0.2181, simple_loss=0.2802, pruned_loss=0.07799, over 4934.00 frames.], tot_loss[loss=0.2203, simple_loss=0.274, pruned_loss=0.08327, over 972388.56 frames.], batch size: 29, lr: 1.48e-03
2022-05-03 16:08:42,107 INFO [train.py:715] (4/8) Epoch 0, batch 19850, loss[loss=0.2198, simple_loss=0.282, pruned_loss=0.07882, over 4971.00 frames.], tot_loss[loss=0.2207, simple_loss=0.2747, pruned_loss=0.08334, over 972280.01 frames.], batch size: 15, lr: 1.48e-03
2022-05-03 16:09:21,341 INFO [train.py:715] (4/8) Epoch 0, batch 19900, loss[loss=0.2174, simple_loss=0.278, pruned_loss=0.07846, over 4768.00 frames.], tot_loss[loss=0.2193, simple_loss=0.2734, pruned_loss=0.08254, over 972115.29 frames.], batch size: 14, lr: 1.48e-03
2022-05-03 16:10:02,118 INFO [train.py:715] (4/8) Epoch 0, batch 19950, loss[loss=0.2028, simple_loss=0.2741, pruned_loss=0.06573, over 4748.00 frames.], tot_loss[loss=0.2181, simple_loss=0.2724, pruned_loss=0.08196, over 972574.14 frames.], batch size: 19, lr: 1.48e-03
2022-05-03 16:10:42,169 INFO [train.py:715] (4/8) Epoch 0, batch 20000, loss[loss=0.2209, simple_loss=0.2749, pruned_loss=0.08351, over 4939.00 frames.], tot_loss[loss=0.219, simple_loss=0.2729, pruned_loss=0.08258, over 972682.55 frames.], batch size: 21, lr: 1.48e-03
2022-05-03 16:11:21,520 INFO [train.py:715] (4/8) Epoch 0, batch 20050, loss[loss=0.2106, simple_loss=0.2687, pruned_loss=0.07621, over 4884.00 frames.], tot_loss[loss=0.2182, simple_loss=0.2723, pruned_loss=0.08208, over 972955.13 frames.], batch size: 16, lr: 1.48e-03
2022-05-03 16:12:01,705 INFO [train.py:715] (4/8) Epoch 0, batch 20100, loss[loss=0.1605, simple_loss=0.227, pruned_loss=0.047, over 4641.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2708, pruned_loss=0.08073, over 972826.21 frames.], batch size: 13, lr: 1.47e-03
2022-05-03 16:12:41,690 INFO [train.py:715] (4/8) Epoch 0, batch 20150, loss[loss=0.197, simple_loss=0.2586, pruned_loss=0.06772, over 4840.00 frames.], tot_loss[loss=0.2151, simple_loss=0.2701, pruned_loss=0.08004, over 973411.18 frames.], batch size: 15, lr: 1.47e-03
2022-05-03 16:13:21,724 INFO [train.py:715] (4/8) Epoch 0, batch 20200, loss[loss=0.254, simple_loss=0.297, pruned_loss=0.1055, over 4738.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2722, pruned_loss=0.08125, over 973101.09 frames.], batch size: 16, lr: 1.47e-03
2022-05-03 16:14:01,255 INFO [train.py:715] (4/8) Epoch 0, batch 20250, loss[loss=0.2247, simple_loss=0.2809, pruned_loss=0.08423, over 4944.00 frames.], tot_loss[loss=0.2178, simple_loss=0.2721, pruned_loss=0.08172, over 973015.87 frames.], batch size: 21, lr: 1.47e-03
2022-05-03 16:14:42,003 INFO [train.py:715] (4/8) Epoch 0, batch 20300, loss[loss=0.2274, simple_loss=0.2801, pruned_loss=0.08729, over 4853.00 frames.], tot_loss[loss=0.2169, simple_loss=0.2718, pruned_loss=0.08096, over 972625.40 frames.], batch size: 20, lr: 1.47e-03
2022-05-03 16:15:21,889 INFO [train.py:715] (4/8) Epoch 0, batch 20350, loss[loss=0.2666, simple_loss=0.2963, pruned_loss=0.1185, over 4944.00 frames.], tot_loss[loss=0.2177, simple_loss=0.2722, pruned_loss=0.08158, over 973122.94 frames.], batch size: 29, lr: 1.47e-03
2022-05-03 16:16:00,949 INFO [train.py:715] (4/8) Epoch 0, batch 20400, loss[loss=0.1853, simple_loss=0.2448, pruned_loss=0.06291, over 4807.00 frames.], tot_loss[loss=0.2171, simple_loss=0.2717, pruned_loss=0.08122, over 973032.25 frames.], batch size: 25, lr: 1.46e-03
2022-05-03 16:16:40,896 INFO [train.py:715] (4/8) Epoch 0, batch 20450, loss[loss=0.2635, simple_loss=0.2899, pruned_loss=0.1186, over 4808.00 frames.], tot_loss[loss=0.2176, simple_loss=0.2721, pruned_loss=0.08157, over 972858.65 frames.], batch size: 15, lr: 1.46e-03
2022-05-03 16:17:20,436 INFO [train.py:715] (4/8) Epoch 0, batch 20500, loss[loss=0.186, simple_loss=0.2365, pruned_loss=0.06776, over 4796.00 frames.], tot_loss[loss=0.2167, simple_loss=0.2716, pruned_loss=0.08093, over 973180.20 frames.], batch size: 12, lr: 1.46e-03
2022-05-03 16:18:00,495 INFO [train.py:715] (4/8) Epoch 0, batch 20550, loss[loss=0.2212, simple_loss=0.2677, pruned_loss=0.08731, over 4978.00 frames.], tot_loss[loss=0.2202, simple_loss=0.2741, pruned_loss=0.08312, over 973854.63 frames.], batch size: 25, lr: 1.46e-03
2022-05-03 16:18:39,954 INFO [train.py:715] (4/8) Epoch 0, batch 20600, loss[loss=0.221, simple_loss=0.2731, pruned_loss=0.08442, over 4837.00 frames.], tot_loss[loss=0.2196, simple_loss=0.2737, pruned_loss=0.08269, over 973377.91 frames.], batch size: 15, lr: 1.46e-03
2022-05-03 16:19:19,643 INFO [train.py:715] (4/8) Epoch 0, batch 20650, loss[loss=0.2471, simple_loss=0.2871, pruned_loss=0.1036, over 4870.00 frames.], tot_loss[loss=0.2193, simple_loss=0.2733, pruned_loss=0.08261, over 972792.15 frames.], batch size: 32, lr: 1.46e-03
2022-05-03 16:20:00,375 INFO [train.py:715] (4/8) Epoch 0, batch 20700, loss[loss=0.203, simple_loss=0.2617, pruned_loss=0.07211, over 4979.00 frames.], tot_loss[loss=0.2184, simple_loss=0.2729, pruned_loss=0.0819, over 972548.58 frames.], batch size: 28, lr: 1.45e-03
2022-05-03 16:20:39,702 INFO [train.py:715] (4/8) Epoch 0, batch 20750, loss[loss=0.1421, simple_loss=0.2085, pruned_loss=0.03785, over 4763.00 frames.], tot_loss[loss=0.2178, simple_loss=0.2729, pruned_loss=0.08138, over 971835.05 frames.], batch size: 12, lr: 1.45e-03
2022-05-03 16:21:19,880 INFO [train.py:715] (4/8) Epoch 0, batch 20800, loss[loss=0.2081, simple_loss=0.268, pruned_loss=0.07409, over 4801.00 frames.], tot_loss[loss=0.2164, simple_loss=0.2718, pruned_loss=0.08052, over 972101.17 frames.], batch size: 21, lr: 1.45e-03
2022-05-03 16:21:59,636 INFO [train.py:715] (4/8) Epoch 0, batch 20850, loss[loss=0.1675, simple_loss=0.22, pruned_loss=0.05745, over 4812.00 frames.], tot_loss[loss=0.216, simple_loss=0.2712, pruned_loss=0.08043, over 971852.26 frames.], batch size: 12, lr: 1.45e-03
2022-05-03 16:22:39,122 INFO [train.py:715] (4/8) Epoch 0, batch 20900, loss[loss=0.1708, simple_loss=0.2436, pruned_loss=0.04902, over 4792.00 frames.], tot_loss[loss=0.2157, simple_loss=0.2711, pruned_loss=0.08017, over 971822.74 frames.], batch size: 24, lr: 1.45e-03
2022-05-03 16:23:19,644 INFO [train.py:715] (4/8) Epoch 0, batch 20950, loss[loss=0.2118, simple_loss=0.2577, pruned_loss=0.08291, over 4799.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2702, pruned_loss=0.07946, over 971503.45 frames.], batch size: 12, lr: 1.45e-03
2022-05-03 16:24:00,680 INFO [train.py:715] (4/8) Epoch 0, batch 21000, loss[loss=0.2388, simple_loss=0.2845, pruned_loss=0.09649, over 4976.00 frames.], tot_loss[loss=0.2159, simple_loss=0.271, pruned_loss=0.08038, over 972580.42 frames.], batch size: 28, lr: 1.44e-03
2022-05-03 16:24:00,680 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 16:24:16,219 INFO [train.py:742] (4/8) Epoch 0, validation: loss=0.1386, simple_loss=0.2255, pruned_loss=0.02581, over 914524.00 frames.
2022-05-03 16:24:57,016 INFO [train.py:715] (4/8) Epoch 0, batch 21050, loss[loss=0.1698, simple_loss=0.2304, pruned_loss=0.05456, over 4941.00 frames.], tot_loss[loss=0.2171, simple_loss=0.272, pruned_loss=0.08104, over 972848.57 frames.], batch size: 35, lr: 1.44e-03
2022-05-03 16:25:36,597 INFO [train.py:715] (4/8) Epoch 0, batch 21100, loss[loss=0.201, simple_loss=0.2677, pruned_loss=0.06713, over 4754.00 frames.], tot_loss[loss=0.2162, simple_loss=0.271, pruned_loss=0.08075, over 972971.24 frames.], batch size: 16, lr: 1.44e-03
2022-05-03 16:26:16,950 INFO [train.py:715] (4/8) Epoch 0, batch 21150, loss[loss=0.2104, simple_loss=0.2618, pruned_loss=0.07947, over 4948.00 frames.], tot_loss[loss=0.2161, simple_loss=0.2708, pruned_loss=0.08072, over 972588.05 frames.], batch size: 21, lr: 1.44e-03
2022-05-03 16:26:56,814 INFO [train.py:715] (4/8) Epoch 0, batch 21200, loss[loss=0.2021, simple_loss=0.2719, pruned_loss=0.06619, over 4897.00 frames.], tot_loss[loss=0.217, simple_loss=0.2715, pruned_loss=0.08126, over 973099.72 frames.], batch size: 19, lr: 1.44e-03
2022-05-03 16:27:37,351 INFO [train.py:715] (4/8) Epoch 0, batch 21250, loss[loss=0.2878, simple_loss=0.3256, pruned_loss=0.125, over 4962.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2722, pruned_loss=0.08132, over 973089.50 frames.], batch size: 24, lr: 1.44e-03
2022-05-03 16:28:17,121 INFO [train.py:715] (4/8) Epoch 0, batch 21300, loss[loss=0.2165, simple_loss=0.2729, pruned_loss=0.08006, over 4821.00 frames.], tot_loss[loss=0.2172, simple_loss=0.2718, pruned_loss=0.08135, over 972247.56 frames.], batch size: 13, lr: 1.43e-03
2022-05-03 16:28:57,541 INFO [train.py:715] (4/8) Epoch 0, batch 21350, loss[loss=0.1681, simple_loss=0.239, pruned_loss=0.04859, over 4991.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2714, pruned_loss=0.08067, over 972075.26 frames.], batch size: 16, lr: 1.43e-03
2022-05-03 16:29:38,275 INFO [train.py:715] (4/8) Epoch 0, batch 21400, loss[loss=0.2163, simple_loss=0.2649, pruned_loss=0.08381, over 4895.00 frames.], tot_loss[loss=0.2173, simple_loss=0.2722, pruned_loss=0.08122, over 972865.55 frames.], batch size: 19, lr: 1.43e-03
2022-05-03 16:30:17,947 INFO [train.py:715] (4/8) Epoch 0, batch 21450, loss[loss=0.2366, simple_loss=0.2879, pruned_loss=0.09264, over 4796.00 frames.], tot_loss[loss=0.2167, simple_loss=0.2721, pruned_loss=0.08065, over 972688.87 frames.], batch size: 24, lr: 1.43e-03
2022-05-03 16:30:57,792 INFO [train.py:715] (4/8) Epoch 0, batch 21500, loss[loss=0.2123, simple_loss=0.2699, pruned_loss=0.07732, over 4823.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2706, pruned_loss=0.07959, over 972715.52 frames.], batch size: 25, lr: 1.43e-03
2022-05-03 16:31:38,006 INFO [train.py:715] (4/8) Epoch 0, batch 21550, loss[loss=0.1785, simple_loss=0.2381, pruned_loss=0.05943, over 4804.00 frames.], tot_loss[loss=0.216, simple_loss=0.2714, pruned_loss=0.08036, over 972365.44 frames.], batch size: 21, lr: 1.43e-03
2022-05-03 16:32:18,466 INFO [train.py:715] (4/8) Epoch 0, batch 21600, loss[loss=0.2491, simple_loss=0.296, pruned_loss=0.1011, over 4968.00 frames.], tot_loss[loss=0.2163, simple_loss=0.2712, pruned_loss=0.08069, over 972379.45 frames.], batch size: 24, lr: 1.42e-03
2022-05-03 16:32:58,234 INFO [train.py:715] (4/8) Epoch 0, batch 21650, loss[loss=0.19, simple_loss=0.252, pruned_loss=0.064, over 4905.00 frames.], tot_loss[loss=0.2174, simple_loss=0.2722, pruned_loss=0.08134, over 971560.48 frames.], batch size: 32, lr: 1.42e-03
2022-05-03 16:33:39,045 INFO [train.py:715] (4/8) Epoch 0, batch 21700, loss[loss=0.2058, simple_loss=0.2689, pruned_loss=0.07133, over 4890.00 frames.], tot_loss[loss=0.2159, simple_loss=0.2714, pruned_loss=0.08024, over 972061.74 frames.], batch size: 22, lr: 1.42e-03
2022-05-03 16:34:19,206 INFO [train.py:715] (4/8) Epoch 0, batch 21750, loss[loss=0.2088, simple_loss=0.2629, pruned_loss=0.07736, over 4855.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2704, pruned_loss=0.0796, over 972603.54 frames.], batch size: 32, lr: 1.42e-03
2022-05-03 16:34:58,788 INFO [train.py:715] (4/8) Epoch 0, batch 21800, loss[loss=0.203, simple_loss=0.2587, pruned_loss=0.07371, over 4881.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2697, pruned_loss=0.07962, over 972391.43 frames.], batch size: 16, lr: 1.42e-03
2022-05-03 16:35:38,617 INFO [train.py:715] (4/8) Epoch 0, batch 21850, loss[loss=0.2532, simple_loss=0.2992, pruned_loss=0.1036, over 4987.00 frames.], tot_loss[loss=0.2149, simple_loss=0.2701, pruned_loss=0.07983, over 972647.09 frames.], batch size: 39, lr: 1.42e-03
2022-05-03 16:36:19,093 INFO [train.py:715] (4/8) Epoch 0, batch 21900, loss[loss=0.2705, simple_loss=0.3118, pruned_loss=0.1146, over 4834.00 frames.], tot_loss[loss=0.2143, simple_loss=0.2694, pruned_loss=0.07963, over 972689.30 frames.], batch size: 15, lr: 1.42e-03
2022-05-03 16:36:59,001 INFO [train.py:715] (4/8) Epoch 0, batch 21950, loss[loss=0.2025, simple_loss=0.2548, pruned_loss=0.0751, over 4947.00 frames.], tot_loss[loss=0.2137, simple_loss=0.2688, pruned_loss=0.07932, over 972909.65 frames.], batch size: 21, lr: 1.41e-03
2022-05-03 16:37:38,285 INFO [train.py:715] (4/8) Epoch 0, batch 22000, loss[loss=0.1937, simple_loss=0.2461, pruned_loss=0.0707, over 4972.00 frames.], tot_loss[loss=0.2124, simple_loss=0.2681, pruned_loss=0.0783, over 973001.24 frames.], batch size: 14, lr: 1.41e-03
2022-05-03 16:38:18,443 INFO [train.py:715] (4/8) Epoch 0, batch 22050, loss[loss=0.2219, simple_loss=0.2729, pruned_loss=0.08548, over 4760.00 frames.], tot_loss[loss=0.2136, simple_loss=0.2692, pruned_loss=0.07898, over 973791.96 frames.], batch size: 19, lr: 1.41e-03
2022-05-03 16:38:58,600 INFO [train.py:715] (4/8) Epoch 0, batch 22100, loss[loss=0.2406, simple_loss=0.2877, pruned_loss=0.09678, over 4833.00 frames.], tot_loss[loss=0.2155, simple_loss=0.2713, pruned_loss=0.07982, over 973729.56 frames.], batch size: 15, lr: 1.41e-03
2022-05-03 16:39:38,115 INFO [train.py:715] (4/8) Epoch 0, batch 22150, loss[loss=0.2364, simple_loss=0.2773, pruned_loss=0.0977, over 4897.00 frames.], tot_loss[loss=0.2153, simple_loss=0.2708, pruned_loss=0.07993, over 973009.05 frames.], batch size: 22, lr: 1.41e-03
2022-05-03 16:40:17,923 INFO [train.py:715] (4/8) Epoch 0, batch 22200, loss[loss=0.2019, simple_loss=0.2598, pruned_loss=0.07199, over 4905.00 frames.], tot_loss[loss=0.2148, simple_loss=0.2704, pruned_loss=0.07957, over 972481.37 frames.], batch size: 39, lr: 1.41e-03
2022-05-03 16:40:58,312 INFO [train.py:715] (4/8) Epoch 0, batch 22250, loss[loss=0.2066, simple_loss=0.256, pruned_loss=0.07862, over 4971.00 frames.], tot_loss[loss=0.2154, simple_loss=0.271, pruned_loss=0.07989, over 972356.95 frames.], batch size: 35, lr: 1.40e-03
2022-05-03 16:41:38,376 INFO [train.py:715] (4/8) Epoch 0, batch 22300, loss[loss=0.2144, simple_loss=0.2867, pruned_loss=0.07102, over 4759.00 frames.], tot_loss[loss=0.2145, simple_loss=0.2703, pruned_loss=0.0793, over 972836.93 frames.], batch size: 14, lr: 1.40e-03
2022-05-03 16:42:18,079 INFO [train.py:715] (4/8) Epoch 0, batch 22350, loss[loss=0.2752, simple_loss=0.3325, pruned_loss=0.1089, over 4871.00 frames.], tot_loss[loss=0.2143, simple_loss=0.2698, pruned_loss=0.07944, over 971379.25 frames.], batch size: 32, lr: 1.40e-03
2022-05-03 16:42:58,248 INFO [train.py:715] (4/8) Epoch 0, batch 22400, loss[loss=0.2222, simple_loss=0.2806, pruned_loss=0.08191, over 4952.00 frames.], tot_loss[loss=0.212, simple_loss=0.2679, pruned_loss=0.07804, over 970668.81 frames.], batch size: 35, lr: 1.40e-03
2022-05-03 16:43:38,082 INFO [train.py:715] (4/8) Epoch 0, batch 22450, loss[loss=0.1768, simple_loss=0.2432, pruned_loss=0.05521, over 4920.00 frames.], tot_loss[loss=0.2125, simple_loss=0.2683, pruned_loss=0.07832, over 971462.72 frames.], batch size: 23, lr: 1.40e-03
2022-05-03 16:44:17,445 INFO [train.py:715] (4/8) Epoch 0, batch 22500, loss[loss=0.1979, simple_loss=0.2504, pruned_loss=0.07268, over 4876.00 frames.], tot_loss[loss=0.2116, simple_loss=0.2677, pruned_loss=0.07778, over 972049.92 frames.], batch size: 16, lr: 1.40e-03
2022-05-03 16:44:57,227 INFO [train.py:715] (4/8) Epoch 0, batch 22550, loss[loss=0.2, simple_loss=0.2477, pruned_loss=0.07622, over 4821.00 frames.], tot_loss[loss=0.2122, simple_loss=0.268, pruned_loss=0.07817, over 971626.10 frames.], batch size: 15, lr: 1.40e-03
2022-05-03 16:45:37,438 INFO [train.py:715] (4/8) Epoch 0, batch 22600, loss[loss=0.2413, simple_loss=0.2941, pruned_loss=0.09428, over 4943.00 frames.], tot_loss[loss=0.2123, simple_loss=0.2679, pruned_loss=0.07841, over 972333.71 frames.], batch size: 35, lr: 1.39e-03
2022-05-03 16:46:18,079 INFO [train.py:715] (4/8) Epoch 0, batch 22650, loss[loss=0.1819, simple_loss=0.2366, pruned_loss=0.06357, over 4985.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2683, pruned_loss=0.07896, over 972823.46 frames.], batch size: 28, lr: 1.39e-03
2022-05-03 16:46:57,298 INFO [train.py:715] (4/8) Epoch 0, batch 22700, loss[loss=0.2475, simple_loss=0.2994, pruned_loss=0.09777, over 4888.00 frames.], tot_loss[loss=0.2144, simple_loss=0.2696, pruned_loss=0.07964, over 973907.97 frames.], batch size: 22, lr: 1.39e-03
2022-05-03 16:47:37,375 INFO [train.py:715] (4/8) Epoch 0, batch 22750, loss[loss=0.1813, simple_loss=0.2438, pruned_loss=0.05937, over 4959.00 frames.], tot_loss[loss=0.215, simple_loss=0.2703, pruned_loss=0.07989, over 973301.20 frames.], batch size: 21, lr: 1.39e-03
2022-05-03 16:48:17,858 INFO [train.py:715] (4/8) Epoch 0, batch 22800, loss[loss=0.2263, simple_loss=0.2886, pruned_loss=0.08201, over 4795.00 frames.], tot_loss[loss=0.2138, simple_loss=0.2693, pruned_loss=0.07919, over 972878.39 frames.], batch size: 24, lr: 1.39e-03
2022-05-03 16:48:57,451 INFO [train.py:715] (4/8) Epoch 0, batch 22850, loss[loss=0.2514, simple_loss=0.2929, pruned_loss=0.1049, over 4813.00 frames.], tot_loss[loss=0.2147, simple_loss=0.2699, pruned_loss=0.07972, over 972794.78 frames.], batch size: 25, lr: 1.39e-03
2022-05-03 16:49:37,563 INFO [train.py:715] (4/8) Epoch 0, batch 22900, loss[loss=0.2232, simple_loss=0.2626, pruned_loss=0.09186, over 4876.00 frames.], tot_loss[loss=0.2137, simple_loss=0.2694, pruned_loss=0.079, over 972861.19 frames.], batch size: 22, lr: 1.39e-03
2022-05-03 16:50:17,830 INFO [train.py:715] (4/8) Epoch 0, batch 22950, loss[loss=0.2139, simple_loss=0.2668, pruned_loss=0.08048, over 4780.00 frames.], tot_loss[loss=0.2126, simple_loss=0.2689, pruned_loss=0.07816, over 973006.02 frames.], batch size: 14, lr: 1.38e-03
2022-05-03 16:50:58,461 INFO [train.py:715] (4/8) Epoch 0, batch 23000, loss[loss=0.2388, simple_loss=0.2904, pruned_loss=0.09361, over 4967.00 frames.], tot_loss[loss=0.2129, simple_loss=0.269, pruned_loss=0.07841, over 972328.83 frames.], batch size: 15, lr: 1.38e-03
2022-05-03 16:51:37,473 INFO [train.py:715] (4/8) Epoch 0, batch 23050, loss[loss=0.1927, simple_loss=0.2479, pruned_loss=0.06875, over 4837.00 frames.], tot_loss[loss=0.2131, simple_loss=0.2694, pruned_loss=0.07836, over 972715.38 frames.], batch size: 12, lr: 1.38e-03
2022-05-03 16:52:18,413 INFO [train.py:715] (4/8) Epoch 0, batch 23100, loss[loss=0.2073, simple_loss=0.2698, pruned_loss=0.07242, over 4978.00 frames.], tot_loss[loss=0.2138, simple_loss=0.27, pruned_loss=0.07878, over 973001.27 frames.], batch size: 35, lr: 1.38e-03
2022-05-03 16:52:59,435 INFO [train.py:715] (4/8) Epoch 0, batch 23150, loss[loss=0.2029, simple_loss=0.266, pruned_loss=0.06988, over 4986.00 frames.], tot_loss[loss=0.2146, simple_loss=0.2709, pruned_loss=0.07916, over 973142.07 frames.], batch size: 28, lr: 1.38e-03
2022-05-03 16:53:39,183 INFO [train.py:715] (4/8) Epoch 0, batch 23200, loss[loss=0.2248, simple_loss=0.2742, pruned_loss=0.08766, over 4792.00 frames.], tot_loss[loss=0.2147, simple_loss=0.2711, pruned_loss=0.07919, over 972917.46 frames.], batch size: 18, lr: 1.38e-03
2022-05-03 16:54:19,751 INFO [train.py:715] (4/8) Epoch 0, batch 23250, loss[loss=0.1932, simple_loss=0.2587, pruned_loss=0.06384, over 4836.00 frames.], tot_loss[loss=0.214, simple_loss=0.27, pruned_loss=0.07898, over 972747.13 frames.], batch size: 15, lr: 1.38e-03
2022-05-03 16:55:00,175 INFO [train.py:715] (4/8) Epoch 0, batch 23300, loss[loss=0.132, simple_loss=0.195, pruned_loss=0.03456, over 4741.00 frames.], tot_loss[loss=0.2133, simple_loss=0.27, pruned_loss=0.0783, over 971901.57 frames.], batch size: 12, lr: 1.37e-03
2022-05-03 16:55:40,656 INFO [train.py:715] (4/8) Epoch 0, batch 23350, loss[loss=0.2551, simple_loss=0.3017, pruned_loss=0.1043, over 4869.00 frames.], tot_loss[loss=0.2125, simple_loss=0.2691, pruned_loss=0.07799, over 970633.70 frames.], batch size: 22, lr: 1.37e-03
2022-05-03 16:56:21,250 INFO [train.py:715] (4/8) Epoch 0, batch 23400, loss[loss=0.1835, simple_loss=0.2594, pruned_loss=0.05377, over 4916.00 frames.], tot_loss[loss=0.2119, simple_loss=0.2685, pruned_loss=0.07767, over 970801.87 frames.], batch size: 18, lr: 1.37e-03
2022-05-03 16:57:02,265 INFO [train.py:715] (4/8) Epoch 0, batch 23450, loss[loss=0.2014, simple_loss=0.2563, pruned_loss=0.07327, over 4899.00 frames.], tot_loss[loss=0.2118, simple_loss=0.2687, pruned_loss=0.07748, over 971534.45 frames.], batch size: 18, lr: 1.37e-03
2022-05-03 16:57:43,368 INFO [train.py:715] (4/8) Epoch 0, batch 23500, loss[loss=0.2152, simple_loss=0.2749, pruned_loss=0.07775, over 4960.00 frames.], tot_loss[loss=0.2122, simple_loss=0.2685, pruned_loss=0.07799, over 971992.67 frames.], batch size: 24, lr: 1.37e-03
2022-05-03 16:58:23,221 INFO [train.py:715] (4/8) Epoch 0, batch 23550, loss[loss=0.1876, simple_loss=0.253, pruned_loss=0.06114, over 4785.00 frames.], tot_loss[loss=0.2125, simple_loss=0.2686, pruned_loss=0.07822, over 971853.06 frames.], batch size: 14, lr: 1.37e-03
2022-05-03 16:59:04,081 INFO [train.py:715] (4/8) Epoch 0, batch 23600, loss[loss=0.2389, simple_loss=0.293, pruned_loss=0.09245, over 4845.00 frames.], tot_loss[loss=0.2135, simple_loss=0.2697, pruned_loss=0.07869, over 971569.49 frames.], batch size: 30, lr: 1.37e-03
2022-05-03 16:59:44,345 INFO [train.py:715] (4/8) Epoch 0, batch 23650, loss[loss=0.1777, simple_loss=0.2466, pruned_loss=0.05438, over 4918.00 frames.], tot_loss[loss=0.2119, simple_loss=0.2683, pruned_loss=0.07776, over 971584.89 frames.], batch size: 18, lr: 1.36e-03
2022-05-03 17:00:24,467 INFO [train.py:715] (4/8) Epoch 0, batch 23700, loss[loss=0.1975, simple_loss=0.2546, pruned_loss=0.07022, over 4926.00 frames.], tot_loss[loss=0.2116, simple_loss=0.268, pruned_loss=0.07759, over 971019.49 frames.], batch size: 18, lr: 1.36e-03
2022-05-03 17:01:03,657 INFO [train.py:715] (4/8) Epoch 0, batch 23750, loss[loss=0.1557, simple_loss=0.2143, pruned_loss=0.0486, over 4840.00 frames.], tot_loss[loss=0.2113, simple_loss=0.2681, pruned_loss=0.07731, over 971383.20 frames.], batch size: 15, lr: 1.36e-03
2022-05-03 17:01:43,658 INFO [train.py:715] (4/8) Epoch 0, batch 23800, loss[loss=0.2548, simple_loss=0.3025, pruned_loss=0.1035, over 4799.00 frames.], tot_loss[loss=0.2108, simple_loss=0.2676, pruned_loss=0.07699, over 971540.37 frames.], batch size: 21, lr: 1.36e-03
2022-05-03 17:02:24,141 INFO [train.py:715] (4/8) Epoch 0, batch 23850, loss[loss=0.186, simple_loss=0.2416, pruned_loss=0.06524, over 4941.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2672, pruned_loss=0.07711, over 971442.97 frames.], batch size: 23, lr: 1.36e-03
2022-05-03 17:03:03,303 INFO [train.py:715] (4/8) Epoch 0, batch 23900, loss[loss=0.2222, simple_loss=0.2728, pruned_loss=0.08584, over 4896.00 frames.], tot_loss[loss=0.2112, simple_loss=0.2679, pruned_loss=0.07727, over 971415.84 frames.], batch size: 16, lr: 1.36e-03
2022-05-03 17:03:43,452 INFO [train.py:715] (4/8) Epoch 0, batch 23950, loss[loss=0.1751, simple_loss=0.238, pruned_loss=0.05612, over 4825.00 frames.], tot_loss[loss=0.2103, simple_loss=0.2672, pruned_loss=0.07674, over 972086.39 frames.], batch size: 15, lr: 1.36e-03
2022-05-03 17:04:26,565 INFO [train.py:715] (4/8) Epoch 0, batch 24000, loss[loss=0.2224, simple_loss=0.2899, pruned_loss=0.07744, over 4801.00 frames.], tot_loss[loss=0.2111, simple_loss=0.2675, pruned_loss=0.07729, over 972486.62 frames.], batch size: 14, lr: 1.35e-03
2022-05-03 17:04:26,566 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 17:04:40,849 INFO [train.py:742] (4/8) Epoch 0, validation: loss=0.1357, simple_loss=0.2226, pruned_loss=0.02435, over 914524.00 frames.
2022-05-03 17:05:21,167 INFO [train.py:715] (4/8) Epoch 0, batch 24050, loss[loss=0.2598, simple_loss=0.2962, pruned_loss=0.1117, over 4974.00 frames.], tot_loss[loss=0.2116, simple_loss=0.2681, pruned_loss=0.07762, over 972989.85 frames.], batch size: 15, lr: 1.35e-03
2022-05-03 17:06:00,593 INFO [train.py:715] (4/8) Epoch 0, batch 24100, loss[loss=0.2047, simple_loss=0.2629, pruned_loss=0.0732, over 4985.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2671, pruned_loss=0.07687, over 972961.03 frames.], batch size: 24, lr: 1.35e-03
2022-05-03 17:06:40,580 INFO [train.py:715] (4/8) Epoch 0, batch 24150, loss[loss=0.2016, simple_loss=0.2682, pruned_loss=0.06755, over 4987.00 frames.], tot_loss[loss=0.2117, simple_loss=0.2679, pruned_loss=0.07778, over 972337.32 frames.], batch size: 25, lr: 1.35e-03
2022-05-03 17:07:20,600 INFO [train.py:715] (4/8) Epoch 0, batch 24200, loss[loss=0.2176, simple_loss=0.2678, pruned_loss=0.08371, over 4838.00 frames.], tot_loss[loss=0.2109, simple_loss=0.2672, pruned_loss=0.07736, over 973120.48 frames.], batch size: 15, lr: 1.35e-03
2022-05-03 17:08:01,223 INFO [train.py:715] (4/8) Epoch 0, batch 24250, loss[loss=0.2065, simple_loss=0.2697, pruned_loss=0.07165, over 4939.00 frames.], tot_loss[loss=0.2111, simple_loss=0.2672, pruned_loss=0.07753, over 972562.51 frames.], batch size: 21, lr: 1.35e-03
2022-05-03 17:08:40,832 INFO [train.py:715] (4/8) Epoch 0, batch 24300, loss[loss=0.1984, simple_loss=0.2585, pruned_loss=0.06914, over 4871.00 frames.], tot_loss[loss=0.2101, simple_loss=0.2665, pruned_loss=0.0769, over 973135.98 frames.], batch size: 16, lr: 1.35e-03
2022-05-03 17:09:21,010 INFO [train.py:715] (4/8) Epoch 0, batch 24350, loss[loss=0.1945, simple_loss=0.258, pruned_loss=0.06551, over 4788.00 frames.], tot_loss[loss=0.2104, simple_loss=0.2667, pruned_loss=0.07708, over 973471.75 frames.], batch size: 12, lr: 1.35e-03
2022-05-03 17:10:01,416 INFO [train.py:715] (4/8) Epoch 0, batch 24400, loss[loss=0.2047, simple_loss=0.2642, pruned_loss=0.07262, over 4785.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2667, pruned_loss=0.07728, over 973164.40 frames.], batch size: 17, lr: 1.34e-03
2022-05-03 17:10:40,937 INFO [train.py:715] (4/8) Epoch 0, batch 24450, loss[loss=0.1837, simple_loss=0.2502, pruned_loss=0.05859, over 4944.00 frames.], tot_loss[loss=0.211, simple_loss=0.2674, pruned_loss=0.0773, over 973199.67 frames.], batch size: 23, lr: 1.34e-03
2022-05-03 17:11:21,048 INFO [train.py:715] (4/8) Epoch 0, batch 24500, loss[loss=0.2011, simple_loss=0.2626, pruned_loss=0.06979, over 4813.00 frames.], tot_loss[loss=0.2106, simple_loss=0.2672, pruned_loss=0.07705, over 973518.38 frames.], batch size: 25, lr: 1.34e-03
2022-05-03 17:12:01,318 INFO [train.py:715] (4/8) Epoch 0, batch 24550, loss[loss=0.1979, simple_loss=0.2634, pruned_loss=0.06618, over 4829.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2671, pruned_loss=0.07699, over 973119.60 frames.], batch size: 13, lr: 1.34e-03
2022-05-03 17:12:41,512 INFO [train.py:715] (4/8) Epoch 0, batch 24600, loss[loss=0.2069, simple_loss=0.2668, pruned_loss=0.07346, over 4813.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2676, pruned_loss=0.07669, over 972836.59 frames.], batch size: 13, lr: 1.34e-03
2022-05-03 17:13:20,990 INFO [train.py:715] (4/8) Epoch 0, batch 24650, loss[loss=0.2079, simple_loss=0.2608, pruned_loss=0.07756, over 4950.00 frames.], tot_loss[loss=0.2108, simple_loss=0.268, pruned_loss=0.07675, over 972994.03 frames.], batch size: 21, lr: 1.34e-03
2022-05-03 17:14:01,415 INFO [train.py:715] (4/8) Epoch 0, batch 24700, loss[loss=0.2209, simple_loss=0.2759, pruned_loss=0.08293, over 4863.00 frames.], tot_loss[loss=0.2109, simple_loss=0.2678, pruned_loss=0.07698, over 972466.35 frames.], batch size: 16, lr: 1.34e-03
2022-05-03 17:14:42,117 INFO [train.py:715] (4/8) Epoch 0, batch 24750, loss[loss=0.2074, simple_loss=0.2729, pruned_loss=0.07094, over 4975.00 frames.], tot_loss[loss=0.2105, simple_loss=0.2674, pruned_loss=0.07684, over 972302.61 frames.], batch size: 24, lr: 1.33e-03
2022-05-03 17:15:21,171 INFO [train.py:715] (4/8) Epoch 0, batch 24800, loss[loss=0.2119, simple_loss=0.2674, pruned_loss=0.07823, over 4863.00 frames.], tot_loss[loss=0.2095, simple_loss=0.2664, pruned_loss=0.07628, over 971375.61 frames.], batch size: 20, lr: 1.33e-03
2022-05-03 17:16:01,309 INFO [train.py:715] (4/8) Epoch 0, batch 24850, loss[loss=0.1999, simple_loss=0.255, pruned_loss=0.07244, over 4830.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2666, pruned_loss=0.0769, over 972154.08 frames.], batch size: 30, lr: 1.33e-03
2022-05-03 17:16:41,587 INFO [train.py:715] (4/8) Epoch 0, batch 24900, loss[loss=0.1915, simple_loss=0.253, pruned_loss=0.06502, over 4969.00 frames.], tot_loss[loss=0.2092, simple_loss=0.2656, pruned_loss=0.07643, over 972029.14 frames.], batch size: 25, lr: 1.33e-03
2022-05-03 17:17:21,628 INFO [train.py:715] (4/8) Epoch 0, batch 24950, loss[loss=0.2755, simple_loss=0.3119, pruned_loss=0.1196, over 4943.00 frames.], tot_loss[loss=0.2081, simple_loss=0.2653, pruned_loss=0.07548, over 971549.92 frames.], batch size: 21, lr: 1.33e-03
2022-05-03 17:18:01,147 INFO [train.py:715] (4/8) Epoch 0, batch 25000, loss[loss=0.1917, simple_loss=0.2482, pruned_loss=0.06764, over 4751.00 frames.], tot_loss[loss=0.2094, simple_loss=0.266, pruned_loss=0.07644, over 971911.78 frames.], batch size: 19, lr: 1.33e-03
2022-05-03 17:18:41,403 INFO [train.py:715] (4/8) Epoch 0, batch 25050, loss[loss=0.1847, simple_loss=0.2521, pruned_loss=0.05869, over 4786.00 frames.], tot_loss[loss=0.2097, simple_loss=0.2663, pruned_loss=0.07654, over 972276.04 frames.], batch size: 14, lr: 1.33e-03
2022-05-03 17:19:21,099 INFO [train.py:715] (4/8) Epoch 0, batch 25100, loss[loss=0.2107, simple_loss=0.2662, pruned_loss=0.07764, over 4910.00 frames.], tot_loss[loss=0.209, simple_loss=0.2654, pruned_loss=0.07626, over 971418.62 frames.], batch size: 18, lr: 1.33e-03
2022-05-03 17:20:00,599 INFO [train.py:715] (4/8) Epoch 0, batch 25150, loss[loss=0.2261, simple_loss=0.2845, pruned_loss=0.08387, over 4744.00 frames.], tot_loss[loss=0.207, simple_loss=0.2641, pruned_loss=0.07498, over 972019.09 frames.], batch size: 16, lr: 1.32e-03
2022-05-03 17:20:41,130 INFO [train.py:715] (4/8) Epoch 0, batch 25200, loss[loss=0.2165, simple_loss=0.2699, pruned_loss=0.08155, over 4848.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2644, pruned_loss=0.07512, over 972279.52 frames.], batch size: 34, lr: 1.32e-03
2022-05-03 17:21:21,699 INFO [train.py:715] (4/8) Epoch 0, batch 25250, loss[loss=0.2382, simple_loss=0.2871, pruned_loss=0.09469, over 4694.00 frames.], tot_loss[loss=0.2058, simple_loss=0.2628, pruned_loss=0.07435, over 972308.94 frames.], batch size: 15, lr: 1.32e-03
2022-05-03 17:22:02,261 INFO [train.py:715] (4/8) Epoch 0, batch 25300, loss[loss=0.2222, simple_loss=0.2747, pruned_loss=0.08484, over 4867.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2639, pruned_loss=0.07511, over 972641.35 frames.], batch size: 16, lr: 1.32e-03
2022-05-03 17:22:42,093 INFO [train.py:715] (4/8) Epoch 0, batch 25350, loss[loss=0.2188, simple_loss=0.2781, pruned_loss=0.0797, over 4929.00 frames.], tot_loss[loss=0.2074, simple_loss=0.2643, pruned_loss=0.07526, over 971957.20 frames.], batch size: 23, lr: 1.32e-03
2022-05-03 17:23:22,550 INFO [train.py:715] (4/8) Epoch 0, batch 25400, loss[loss=0.2553, simple_loss=0.2854, pruned_loss=0.1126, over 4961.00 frames.], tot_loss[loss=0.2094, simple_loss=0.2661, pruned_loss=0.07638, over 971953.65 frames.], batch size: 15, lr: 1.32e-03
2022-05-03 17:24:02,720 INFO [train.py:715] (4/8) Epoch 0, batch 25450, loss[loss=0.1692, simple_loss=0.2373, pruned_loss=0.05056, over 4988.00 frames.], tot_loss[loss=0.2111, simple_loss=0.2674, pruned_loss=0.07738, over 972684.62 frames.], batch size: 26, lr: 1.32e-03
2022-05-03 17:24:41,711 INFO [train.py:715] (4/8) Epoch 0, batch 25500, loss[loss=0.211, simple_loss=0.271, pruned_loss=0.07549, over 4936.00 frames.], tot_loss[loss=0.2107, simple_loss=0.2675, pruned_loss=0.07697, over 973239.00 frames.], batch size: 21, lr: 1.32e-03
2022-05-03 17:25:22,414 INFO [train.py:715] (4/8) Epoch 0, batch 25550, loss[loss=0.1937, simple_loss=0.2665, pruned_loss=0.06046, over 4736.00 frames.], tot_loss[loss=0.2112, simple_loss=0.2681, pruned_loss=0.07717, over 972727.33 frames.], batch size: 16, lr: 1.31e-03
2022-05-03 17:26:02,026 INFO [train.py:715] (4/8) Epoch 0, batch 25600, loss[loss=0.1977, simple_loss=0.2626, pruned_loss=0.06642, over 4718.00 frames.], tot_loss[loss=0.2118, simple_loss=0.2689, pruned_loss=0.0773, over 972630.07 frames.], batch size: 15, lr: 1.31e-03
2022-05-03 17:26:41,734 INFO [train.py:715] (4/8) Epoch 0, batch 25650, loss[loss=0.2104, simple_loss=0.2675, pruned_loss=0.07665, over 4932.00 frames.], tot_loss[loss=0.211, simple_loss=0.2684, pruned_loss=0.07683, over 973556.80 frames.], batch size: 21, lr: 1.31e-03
2022-05-03 17:27:21,449 INFO [train.py:715] (4/8) Epoch 0, batch 25700, loss[loss=0.2255, simple_loss=0.2887, pruned_loss=0.08118, over 4769.00 frames.], tot_loss[loss=0.2091, simple_loss=0.267, pruned_loss=0.07558, over 973576.69 frames.], batch size: 18, lr: 1.31e-03
2022-05-03 17:28:01,731 INFO [train.py:715] (4/8) Epoch 0, batch 25750, loss[loss=0.2325, simple_loss=0.277, pruned_loss=0.09398, over 4920.00 frames.], tot_loss[loss=0.2114, simple_loss=0.2689, pruned_loss=0.07698, over 972927.06 frames.], batch size: 18, lr: 1.31e-03
2022-05-03 17:28:41,509 INFO [train.py:715] (4/8) Epoch 0, batch 25800, loss[loss=0.2232, simple_loss=0.2752, pruned_loss=0.08554, over 4860.00 frames.], tot_loss[loss=0.2099, simple_loss=0.2677, pruned_loss=0.07609, over 973241.90 frames.], batch size: 38, lr: 1.31e-03
2022-05-03 17:29:20,753 INFO [train.py:715] (4/8) Epoch 0, batch 25850, loss[loss=0.2096, simple_loss=0.269, pruned_loss=0.07512, over 4909.00 frames.], tot_loss[loss=0.2089, simple_loss=0.2664, pruned_loss=0.07572, over 973163.59 frames.], batch size: 17, lr: 1.31e-03
2022-05-03 17:30:01,472 INFO [train.py:715] (4/8) Epoch 0, batch 25900, loss[loss=0.2658, simple_loss=0.2953, pruned_loss=0.1181, over 4984.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2655, pruned_loss=0.07494, over 973138.78 frames.], batch size: 15, lr: 1.31e-03
2022-05-03 17:30:41,208 INFO [train.py:715] (4/8) Epoch 0, batch 25950, loss[loss=0.1883, simple_loss=0.2531, pruned_loss=0.06168, over 4976.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2654, pruned_loss=0.07459, over 973064.43 frames.], batch size: 25, lr: 1.30e-03
2022-05-03 17:31:21,225 INFO [train.py:715] (4/8) Epoch 0, batch 26000, loss[loss=0.2666, simple_loss=0.3084, pruned_loss=0.1124, over 4909.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2658, pruned_loss=0.07538, over 972905.12 frames.], batch size: 19, lr: 1.30e-03
2022-05-03 17:32:01,170 INFO [train.py:715] (4/8) Epoch 0, batch 26050, loss[loss=0.2326, simple_loss=0.2877, pruned_loss=0.0888, over 4780.00 frames.], tot_loss[loss=0.2085, simple_loss=0.2658, pruned_loss=0.07564, over 972666.15 frames.], batch size: 17, lr: 1.30e-03
2022-05-03 17:32:41,633 INFO [train.py:715] (4/8) Epoch 0, batch 26100, loss[loss=0.179, simple_loss=0.2285, pruned_loss=0.06472, over 4793.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2649, pruned_loss=0.0751, over 973097.08 frames.], batch size: 17, lr: 1.30e-03
2022-05-03 17:33:21,953 INFO [train.py:715] (4/8) Epoch 0, batch 26150, loss[loss=0.188, simple_loss=0.2444, pruned_loss=0.06577, over 4906.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2647, pruned_loss=0.07515, over 973538.48 frames.], batch size: 19, lr: 1.30e-03
2022-05-03 17:34:00,856 INFO [train.py:715] (4/8) Epoch 0, batch 26200, loss[loss=0.1898, simple_loss=0.2471, pruned_loss=0.0662, over 4899.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2637, pruned_loss=0.07463, over 973995.27 frames.], batch size: 19, lr: 1.30e-03
2022-05-03 17:34:41,485 INFO [train.py:715] (4/8) Epoch 0, batch 26250, loss[loss=0.2444, simple_loss=0.2909, pruned_loss=0.09897, over 4904.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2641, pruned_loss=0.07479, over 972558.73 frames.], batch size: 19, lr: 1.30e-03
2022-05-03 17:35:21,435 INFO [train.py:715] (4/8) Epoch 0, batch 26300, loss[loss=0.2222, simple_loss=0.2769, pruned_loss=0.08379, over 4786.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2647, pruned_loss=0.07539, over 971480.49 frames.], batch size: 17, lr: 1.30e-03
2022-05-03 17:36:01,272 INFO [train.py:715] (4/8) Epoch 0, batch 26350, loss[loss=0.2091, simple_loss=0.2688, pruned_loss=0.0747, over 4963.00 frames.], tot_loss[loss=0.208, simple_loss=0.2651, pruned_loss=0.07543, over 972266.75 frames.], batch size: 35, lr: 1.30e-03
2022-05-03 17:36:41,217 INFO [train.py:715] (4/8) Epoch 0, batch 26400, loss[loss=0.2198, simple_loss=0.2742, pruned_loss=0.08266, over 4918.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2638, pruned_loss=0.07459, over 972085.48 frames.], batch size: 23, lr: 1.29e-03
2022-05-03 17:37:21,338 INFO [train.py:715] (4/8) Epoch 0, batch 26450, loss[loss=0.1751, simple_loss=0.242, pruned_loss=0.05408, over 4981.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2634, pruned_loss=0.07435, over 972935.09 frames.], batch size: 25, lr: 1.29e-03
2022-05-03 17:38:02,049 INFO [train.py:715] (4/8) Epoch 0, batch 26500, loss[loss=0.1804, simple_loss=0.2551, pruned_loss=0.05285, over 4930.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2641, pruned_loss=0.07444, over 972913.82 frames.], batch size: 23, lr: 1.29e-03
2022-05-03 17:38:41,409 INFO [train.py:715] (4/8) Epoch 0, batch 26550, loss[loss=0.1892, simple_loss=0.2598, pruned_loss=0.05935, over 4944.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2642, pruned_loss=0.07467, over 972745.53 frames.], batch size: 29, lr: 1.29e-03
2022-05-03 17:39:21,083 INFO [train.py:715] (4/8) Epoch 0, batch 26600, loss[loss=0.2386, simple_loss=0.2857, pruned_loss=0.09571, over 4819.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2646, pruned_loss=0.07524, over 972638.59 frames.], batch size: 26, lr: 1.29e-03
2022-05-03 17:40:01,332 INFO [train.py:715] (4/8) Epoch 0, batch 26650, loss[loss=0.2158, simple_loss=0.2752, pruned_loss=0.07816, over 4652.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2638, pruned_loss=0.07474, over 971701.12 frames.], batch size: 13, lr: 1.29e-03
2022-05-03 17:40:40,794 INFO [train.py:715] (4/8) Epoch 0, batch 26700, loss[loss=0.353, simple_loss=0.385, pruned_loss=0.1605, over 4696.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2658, pruned_loss=0.07582, over 971855.05 frames.], batch size: 15, lr: 1.29e-03
2022-05-03 17:41:20,820 INFO [train.py:715] (4/8) Epoch 0, batch 26750, loss[loss=0.2147, simple_loss=0.2694, pruned_loss=0.08, over 4907.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2657, pruned_loss=0.07587, over 972424.93 frames.], batch size: 17, lr: 1.29e-03
2022-05-03 17:42:01,249 INFO [train.py:715] (4/8) Epoch 0, batch 26800, loss[loss=0.1894, simple_loss=0.2408, pruned_loss=0.06896, over 4838.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2653, pruned_loss=0.07565, over 972380.52 frames.], batch size: 12, lr: 1.28e-03
2022-05-03 17:42:41,668 INFO [train.py:715] (4/8) Epoch 0, batch 26850, loss[loss=0.2161, simple_loss=0.2707, pruned_loss=0.08072, over 4869.00 frames.], tot_loss[loss=0.2073, simple_loss=0.2649, pruned_loss=0.07489, over 972626.25 frames.], batch size: 20, lr: 1.28e-03
2022-05-03 17:43:21,530 INFO [train.py:715] (4/8) Epoch 0, batch 26900, loss[loss=0.1882, simple_loss=0.2517, pruned_loss=0.06238, over 4810.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2646, pruned_loss=0.07487, over 972250.45 frames.], batch size: 13, lr: 1.28e-03
2022-05-03 17:44:02,263 INFO [train.py:715] (4/8) Epoch 0, batch 26950, loss[loss=0.2444, simple_loss=0.3019, pruned_loss=0.09339, over 4760.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2645, pruned_loss=0.07457, over 973232.29 frames.], batch size: 19, lr: 1.28e-03
2022-05-03 17:44:42,418 INFO [train.py:715] (4/8) Epoch 0, batch 27000, loss[loss=0.2952, simple_loss=0.3319, pruned_loss=0.1293, over 4804.00 frames.], tot_loss[loss=0.2072, simple_loss=0.265, pruned_loss=0.07472, over 973581.73 frames.], batch size: 24, lr: 1.28e-03
2022-05-03 17:44:42,418 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 17:44:51,200 INFO [train.py:742] (4/8) Epoch 0, validation: loss=0.1338, simple_loss=0.2208, pruned_loss=0.02337, over 914524.00 frames.
2022-05-03 17:45:31,272 INFO [train.py:715] (4/8) Epoch 0, batch 27050, loss[loss=0.1871, simple_loss=0.246, pruned_loss=0.0641, over 4979.00 frames.], tot_loss[loss=0.2065, simple_loss=0.2641, pruned_loss=0.0744, over 973367.75 frames.], batch size: 35, lr: 1.28e-03
2022-05-03 17:46:10,744 INFO [train.py:715] (4/8) Epoch 0, batch 27100, loss[loss=0.233, simple_loss=0.2824, pruned_loss=0.09177, over 4790.00 frames.], tot_loss[loss=0.2076, simple_loss=0.2647, pruned_loss=0.0752, over 971951.26 frames.], batch size: 24, lr: 1.28e-03
2022-05-03 17:46:51,329 INFO [train.py:715] (4/8) Epoch 0, batch 27150, loss[loss=0.2522, simple_loss=0.3033, pruned_loss=0.1005, over 4870.00 frames.], tot_loss[loss=0.2078, simple_loss=0.2655, pruned_loss=0.07507, over 972947.45 frames.], batch size: 22, lr: 1.28e-03
2022-05-03 17:47:31,710 INFO [train.py:715] (4/8) Epoch 0, batch 27200, loss[loss=0.2053, simple_loss=0.2521, pruned_loss=0.07924, over 4919.00 frames.], tot_loss[loss=0.2087, simple_loss=0.2658, pruned_loss=0.07583, over 973581.25 frames.], batch size: 18, lr: 1.28e-03
2022-05-03 17:48:11,811 INFO [train.py:715] (4/8) Epoch 0, batch 27250, loss[loss=0.2349, simple_loss=0.2877, pruned_loss=0.09104, over 4835.00 frames.], tot_loss[loss=0.2071, simple_loss=0.2645, pruned_loss=0.07483, over 973720.20 frames.], batch size: 15, lr: 1.27e-03
2022-05-03 17:48:51,956 INFO [train.py:715] (4/8) Epoch 0, batch 27300, loss[loss=0.2298, simple_loss=0.2652, pruned_loss=0.09725, over 4989.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2646, pruned_loss=0.07485, over 973927.00 frames.], batch size: 14, lr: 1.27e-03
2022-05-03 17:49:31,860 INFO [train.py:715] (4/8) Epoch 0, batch 27350, loss[loss=0.2281, simple_loss=0.2785, pruned_loss=0.08879, over 4785.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2649, pruned_loss=0.07416, over 973431.58 frames.], batch size: 14, lr: 1.27e-03
2022-05-03 17:50:11,822 INFO [train.py:715] (4/8) Epoch 0, batch 27400, loss[loss=0.2241, simple_loss=0.2777, pruned_loss=0.08518, over 4873.00 frames.], tot_loss[loss=0.207, simple_loss=0.2652, pruned_loss=0.0744, over 973696.34 frames.], batch size: 16, lr: 1.27e-03
2022-05-03 17:50:51,093 INFO [train.py:715] (4/8) Epoch 0, batch 27450, loss[loss=0.175, simple_loss=0.2468, pruned_loss=0.0516, over 4943.00 frames.], tot_loss[loss=0.2068, simple_loss=0.2655, pruned_loss=0.07407, over 973373.77 frames.], batch size: 29, lr: 1.27e-03
2022-05-03 17:51:31,240 INFO [train.py:715] (4/8) Epoch 0, batch 27500, loss[loss=0.2176, simple_loss=0.2616, pruned_loss=0.0868, over 4939.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2649, pruned_loss=0.07425, over 972179.39 frames.], batch size: 29, lr: 1.27e-03
2022-05-03 17:52:11,048 INFO [train.py:715] (4/8) Epoch 0, batch 27550, loss[loss=0.1785, simple_loss=0.2486, pruned_loss=0.05423, over 4988.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2649, pruned_loss=0.07443, over 972124.59 frames.], batch size: 25, lr: 1.27e-03
2022-05-03 17:52:50,538 INFO [train.py:715] (4/8) Epoch 0, batch 27600, loss[loss=0.1731, simple_loss=0.2233, pruned_loss=0.06146, over 4813.00 frames.], tot_loss[loss=0.2064, simple_loss=0.2641, pruned_loss=0.07435, over 971678.43 frames.], batch size: 13, lr: 1.27e-03
2022-05-03 17:53:29,967 INFO [train.py:715] (4/8) Epoch 0, batch 27650, loss[loss=0.188, simple_loss=0.2442, pruned_loss=0.06595, over 4790.00 frames.], tot_loss[loss=0.206, simple_loss=0.2636, pruned_loss=0.07421, over 971407.03 frames.], batch size: 12, lr: 1.27e-03
2022-05-03 17:54:09,970 INFO [train.py:715] (4/8) Epoch 0, batch 27700, loss[loss=0.2275, simple_loss=0.2743, pruned_loss=0.09034, over 4792.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2643, pruned_loss=0.07479, over 971352.61 frames.], batch size: 18, lr: 1.26e-03
2022-05-03 17:54:50,358 INFO [train.py:715] (4/8) Epoch 0, batch 27750, loss[loss=0.196, simple_loss=0.2569, pruned_loss=0.06752, over 4897.00 frames.], tot_loss[loss=0.2055, simple_loss=0.2631, pruned_loss=0.07391, over 971745.75 frames.], batch size: 19, lr: 1.26e-03
2022-05-03 17:55:30,105 INFO [train.py:715] (4/8) Epoch 0, batch 27800, loss[loss=0.1709, simple_loss=0.2302, pruned_loss=0.0558, over 4886.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2625, pruned_loss=0.07345, over 972420.68 frames.], batch size: 16, lr: 1.26e-03
2022-05-03 17:56:10,357 INFO [train.py:715] (4/8) Epoch 0, batch 27850, loss[loss=0.2341, simple_loss=0.2934, pruned_loss=0.08739, over 4739.00 frames.], tot_loss[loss=0.2063, simple_loss=0.264, pruned_loss=0.07426, over 972142.53 frames.], batch size: 16, lr: 1.26e-03
2022-05-03 17:56:49,941 INFO [train.py:715] (4/8) Epoch 0, batch 27900, loss[loss=0.1782, simple_loss=0.2494, pruned_loss=0.0535, over 4968.00 frames.], tot_loss[loss=0.2075, simple_loss=0.2652, pruned_loss=0.07493, over 971403.47 frames.], batch size: 24, lr: 1.26e-03
2022-05-03 17:57:29,409 INFO [train.py:715] (4/8) Epoch 0, batch 27950, loss[loss=0.2162, simple_loss=0.2732, pruned_loss=0.07958, over 4861.00 frames.], tot_loss[loss=0.2066, simple_loss=0.2646, pruned_loss=0.07428, over 972130.16 frames.], batch size: 13, lr: 1.26e-03
2022-05-03 17:58:09,430 INFO [train.py:715] (4/8) Epoch 0, batch 28000, loss[loss=0.221, simple_loss=0.2687, pruned_loss=0.08661, over 4785.00 frames.], tot_loss[loss=0.2061, simple_loss=0.2642, pruned_loss=0.07397, over 972188.74 frames.], batch size: 18, lr: 1.26e-03
2022-05-03 17:58:49,656 INFO [train.py:715] (4/8) Epoch 0, batch 28050, loss[loss=0.2412, simple_loss=0.2819, pruned_loss=0.1002, over 4982.00 frames.], tot_loss[loss=0.207, simple_loss=0.2647, pruned_loss=0.07461, over 972261.35 frames.], batch size: 15, lr: 1.26e-03
2022-05-03 17:59:29,706 INFO [train.py:715] (4/8) Epoch 0, batch 28100, loss[loss=0.2372, simple_loss=0.3068, pruned_loss=0.08385, over 4922.00 frames.], tot_loss[loss=0.2102, simple_loss=0.2669, pruned_loss=0.07675, over 972730.50 frames.], batch size: 39, lr: 1.26e-03
2022-05-03 18:00:08,962 INFO [train.py:715] (4/8) Epoch 0, batch 28150, loss[loss=0.1819, simple_loss=0.2402, pruned_loss=0.06177, over 4804.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2653, pruned_loss=0.07561, over 972699.72 frames.], batch size: 13, lr: 1.25e-03
2022-05-03 18:00:49,199 INFO [train.py:715] (4/8) Epoch 0, batch 28200, loss[loss=0.1949, simple_loss=0.2559, pruned_loss=0.06699, over 4805.00 frames.], tot_loss[loss=0.2077, simple_loss=0.2647, pruned_loss=0.07536, over 972838.28 frames.], batch size: 25, lr: 1.25e-03
2022-05-03 18:01:28,907 INFO [train.py:715] (4/8) Epoch 0, batch 28250, loss[loss=0.1924, simple_loss=0.2583, pruned_loss=0.06321, over 4960.00 frames.], tot_loss[loss=0.2088, simple_loss=0.2656, pruned_loss=0.07601, over 972496.88 frames.], batch size: 14, lr: 1.25e-03
2022-05-03 18:02:07,675 INFO [train.py:715] (4/8) Epoch 0, batch 28300, loss[loss=0.2439, simple_loss=0.2961, pruned_loss=0.09585, over 4796.00 frames.], tot_loss[loss=0.2083, simple_loss=0.2652, pruned_loss=0.07574, over 972222.71 frames.], batch size: 25, lr: 1.25e-03
2022-05-03 18:02:48,208 INFO [train.py:715] (4/8) Epoch 0, batch 28350, loss[loss=0.2246, simple_loss=0.2834, pruned_loss=0.08292, over 4777.00 frames.], tot_loss[loss=0.208, simple_loss=0.2648, pruned_loss=0.07557, over 971608.78 frames.], batch size: 18, lr: 1.25e-03
2022-05-03 18:03:27,711 INFO [train.py:715] (4/8) Epoch 0, batch 28400, loss[loss=0.1984, simple_loss=0.2706, pruned_loss=0.06315, over 4799.00 frames.], tot_loss[loss=0.2084, simple_loss=0.2651, pruned_loss=0.07584, over 972128.98 frames.], batch size: 24, lr: 1.25e-03
2022-05-03 18:04:07,957 INFO [train.py:715] (4/8) Epoch 0, batch 28450, loss[loss=0.1972, simple_loss=0.2448, pruned_loss=0.07476, over 4853.00 frames.], tot_loss[loss=0.2067, simple_loss=0.264, pruned_loss=0.07472, over 971399.78 frames.], batch size: 30, lr: 1.25e-03
2022-05-03 18:04:47,629 INFO [train.py:715] (4/8) Epoch 0, batch 28500, loss[loss=0.1813, simple_loss=0.2475, pruned_loss=0.05755, over 4918.00 frames.], tot_loss[loss=0.2054, simple_loss=0.2632, pruned_loss=0.07377, over 973026.21 frames.], batch size: 18, lr: 1.25e-03
2022-05-03 18:05:28,099 INFO [train.py:715] (4/8) Epoch 0, batch 28550, loss[loss=0.1888, simple_loss=0.2497, pruned_loss=0.06398, over 4950.00 frames.], tot_loss[loss=0.2052, simple_loss=0.2628, pruned_loss=0.07376, over 973259.04 frames.], batch size: 24, lr: 1.25e-03
2022-05-03 18:06:07,732 INFO [train.py:715] (4/8) Epoch 0, batch 28600, loss[loss=0.1907, simple_loss=0.2564, pruned_loss=0.06253, over 4815.00 frames.], tot_loss[loss=0.2056, simple_loss=0.264, pruned_loss=0.07364, over 972833.33 frames.], batch size: 26, lr: 1.24e-03
2022-05-03 18:06:46,955 INFO [train.py:715] (4/8) Epoch 0, batch 28650, loss[loss=0.2545, simple_loss=0.3095, pruned_loss=0.09973, over 4964.00 frames.], tot_loss[loss=0.2069, simple_loss=0.2647, pruned_loss=0.07456, over 973442.75 frames.], batch size: 39, lr: 1.24e-03
2022-05-03 18:07:26,840 INFO [train.py:715] (4/8) Epoch 0, batch 28700, loss[loss=0.1784, simple_loss=0.2426, pruned_loss=0.05714, over 4922.00 frames.], tot_loss[loss=0.2064, simple_loss=0.264, pruned_loss=0.07441, over 973666.18 frames.], batch size: 18, lr: 1.24e-03
2022-05-03 18:08:06,485 INFO [train.py:715] (4/8) Epoch 0, batch 28750, loss[loss=0.2067, simple_loss=0.2759, pruned_loss=0.06875, over 4798.00 frames.], tot_loss[loss=0.2059, simple_loss=0.2637, pruned_loss=0.07407, over 972772.08 frames.], batch size: 21, lr: 1.24e-03
2022-05-03 18:08:46,800 INFO [train.py:715] (4/8) Epoch 0, batch 28800, loss[loss=0.1922, simple_loss=0.2461, pruned_loss=0.06911, over 4960.00 frames.], tot_loss[loss=0.2072, simple_loss=0.2649, pruned_loss=0.07473, over 973197.46 frames.], batch size: 35, lr: 1.24e-03
2022-05-03 18:09:25,925 INFO [train.py:715] (4/8) Epoch 0, batch 28850, loss[loss=0.1781, simple_loss=0.2489, pruned_loss=0.05365, over 4935.00 frames.], tot_loss[loss=0.2067, simple_loss=0.2645, pruned_loss=0.07442, over 973003.15 frames.], batch size: 23, lr: 1.24e-03
2022-05-03 18:10:05,951 INFO [train.py:715] (4/8) Epoch 0, batch 28900, loss[loss=0.1678, simple_loss=0.2273, pruned_loss=0.05421, over 4749.00 frames.], tot_loss[loss=0.2047, simple_loss=0.2631, pruned_loss=0.0732, over 972429.81 frames.], batch size: 19, lr: 1.24e-03
2022-05-03 18:10:45,832 INFO [train.py:715] (4/8) Epoch 0, batch 28950, loss[loss=0.1942, simple_loss=0.2669, pruned_loss=0.06071, over 4975.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2628, pruned_loss=0.07289, over 972626.22 frames.], batch size: 15, lr: 1.24e-03
2022-05-03 18:11:24,705 INFO [train.py:715] (4/8) Epoch 0, batch 29000, loss[loss=0.16, simple_loss=0.2297, pruned_loss=0.04518, over 4936.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2618, pruned_loss=0.07232, over 973299.25 frames.], batch size: 23, lr: 1.24e-03
2022-05-03 18:12:05,309 INFO [train.py:715] (4/8) Epoch 0, batch 29050, loss[loss=0.1738, simple_loss=0.2333, pruned_loss=0.05715, over 4820.00 frames.], tot_loss[loss=0.2023, simple_loss=0.2611, pruned_loss=0.07177, over 973280.72 frames.], batch size: 25, lr: 1.24e-03
2022-05-03 18:12:45,440 INFO [train.py:715] (4/8) Epoch 0, batch 29100, loss[loss=0.2059, simple_loss=0.2772, pruned_loss=0.06731, over 4938.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2602, pruned_loss=0.07079, over 972408.07 frames.], batch size: 29, lr: 1.23e-03
2022-05-03 18:13:25,065 INFO [train.py:715] (4/8) Epoch 0, batch 29150, loss[loss=0.1664, simple_loss=0.23, pruned_loss=0.05136, over 4787.00 frames.], tot_loss[loss=0.202, simple_loss=0.2609, pruned_loss=0.07154, over 972169.80 frames.], batch size: 14, lr: 1.23e-03
2022-05-03 18:14:04,265 INFO [train.py:715] (4/8) Epoch 0, batch 29200, loss[loss=0.1929, simple_loss=0.2512, pruned_loss=0.06729, over 4872.00 frames.], tot_loss[loss=0.2012, simple_loss=0.26, pruned_loss=0.07114, over 972620.77 frames.], batch size: 38, lr: 1.23e-03
2022-05-03 18:14:44,207 INFO [train.py:715] (4/8) Epoch 0, batch 29250, loss[loss=0.2444, simple_loss=0.3014, pruned_loss=0.09367, over 4685.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2603, pruned_loss=0.07136, over 972444.31 frames.], batch size: 15, lr: 1.23e-03
2022-05-03 18:15:24,221 INFO [train.py:715] (4/8) Epoch 0, batch 29300, loss[loss=0.2297, simple_loss=0.2797, pruned_loss=0.08984, over 4972.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2604, pruned_loss=0.0717, over 972384.00 frames.], batch size: 39, lr: 1.23e-03
2022-05-03 18:16:04,639 INFO [train.py:715] (4/8) Epoch 0, batch 29350, loss[loss=0.1643, simple_loss=0.2241, pruned_loss=0.05229, over 4974.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2608, pruned_loss=0.07208, over 972616.68 frames.], batch size: 31, lr: 1.23e-03
2022-05-03 18:16:44,081 INFO [train.py:715] (4/8) Epoch 0, batch 29400, loss[loss=0.2291, simple_loss=0.288, pruned_loss=0.08514, over 4818.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2613, pruned_loss=0.07203, over 972566.49 frames.], batch size: 15, lr: 1.23e-03
2022-05-03 18:17:23,553 INFO [train.py:715] (4/8) Epoch 0, batch 29450, loss[loss=0.1639, simple_loss=0.2298, pruned_loss=0.049, over 4731.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2622, pruned_loss=0.07302, over 972877.02 frames.], batch size: 12, lr: 1.23e-03
2022-05-03 18:18:03,747 INFO [train.py:715] (4/8) Epoch 0, batch 29500, loss[loss=0.2036, simple_loss=0.2486, pruned_loss=0.07934, over 4921.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2623, pruned_loss=0.07335, over 972583.80 frames.], batch size: 23, lr: 1.23e-03
2022-05-03 18:18:42,858 INFO [train.py:715] (4/8) Epoch 0, batch 29550, loss[loss=0.1642, simple_loss=0.2335, pruned_loss=0.04743, over 4852.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2618, pruned_loss=0.07289, over 972195.88 frames.], batch size: 32, lr: 1.23e-03
2022-05-03 18:19:23,015 INFO [train.py:715] (4/8) Epoch 0, batch 29600, loss[loss=0.1664, simple_loss=0.2381, pruned_loss=0.04739, over 4923.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2612, pruned_loss=0.07309, over 971737.53 frames.], batch size: 23, lr: 1.22e-03
2022-05-03 18:20:02,960 INFO [train.py:715] (4/8) Epoch 0, batch 29650, loss[loss=0.2259, simple_loss=0.2818, pruned_loss=0.08502, over 4788.00 frames.], tot_loss[loss=0.2038, simple_loss=0.2615, pruned_loss=0.07309, over 972454.92 frames.], batch size: 21, lr: 1.22e-03
2022-05-03 18:20:42,829 INFO [train.py:715] (4/8) Epoch 0, batch 29700, loss[loss=0.1824, simple_loss=0.2512, pruned_loss=0.05679, over 4984.00 frames.], tot_loss[loss=0.2045, simple_loss=0.2625, pruned_loss=0.07328, over 972829.26 frames.], batch size: 26, lr: 1.22e-03
2022-05-03 18:21:23,323 INFO [train.py:715] (4/8) Epoch 0, batch 29750, loss[loss=0.189, simple_loss=0.2474, pruned_loss=0.0653, over 4780.00 frames.], tot_loss[loss=0.2052, simple_loss=0.263, pruned_loss=0.07368, over 973592.27 frames.], batch size: 17, lr: 1.22e-03
2022-05-03 18:22:03,150 INFO [train.py:715] (4/8) Epoch 0, batch 29800, loss[loss=0.2239, simple_loss=0.2895, pruned_loss=0.07913, over 4922.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2623, pruned_loss=0.07317, over 973592.03 frames.], batch size: 23, lr: 1.22e-03
2022-05-03 18:22:44,057 INFO [train.py:715] (4/8) Epoch 0, batch 29850, loss[loss=0.1717, simple_loss=0.2372, pruned_loss=0.05307, over 4955.00 frames.], tot_loss[loss=0.203, simple_loss=0.2613, pruned_loss=0.07234, over 973410.04 frames.], batch size: 24, lr: 1.22e-03
2022-05-03 18:23:23,987 INFO [train.py:715] (4/8) Epoch 0, batch 29900, loss[loss=0.2076, simple_loss=0.2624, pruned_loss=0.07636, over 4803.00 frames.], tot_loss[loss=0.2034, simple_loss=0.262, pruned_loss=0.07238, over 973526.94 frames.], batch size: 14, lr: 1.22e-03
2022-05-03 18:24:03,886 INFO [train.py:715] (4/8) Epoch 0, batch 29950, loss[loss=0.1807, simple_loss=0.2516, pruned_loss=0.05488, over 4986.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2614, pruned_loss=0.0715, over 973327.64 frames.], batch size: 25, lr: 1.22e-03
2022-05-03 18:24:43,766 INFO [train.py:715] (4/8) Epoch 0, batch 30000, loss[loss=0.1719, simple_loss=0.2358, pruned_loss=0.05401, over 4816.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2621, pruned_loss=0.07147, over 974063.19 frames.], batch size: 27, lr: 1.22e-03
2022-05-03 18:24:43,766 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 18:25:00,379 INFO [train.py:742] (4/8) Epoch 0, validation: loss=0.1316, simple_loss=0.2189, pruned_loss=0.02213, over 914524.00 frames.
2022-05-03 18:25:40,682 INFO [train.py:715] (4/8) Epoch 0, batch 30050, loss[loss=0.2106, simple_loss=0.2657, pruned_loss=0.07773, over 4959.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2623, pruned_loss=0.07153, over 974172.10 frames.], batch size: 24, lr: 1.22e-03
2022-05-03 18:26:21,231 INFO [train.py:715] (4/8) Epoch 0, batch 30100, loss[loss=0.2165, simple_loss=0.2791, pruned_loss=0.07696, over 4889.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2625, pruned_loss=0.07195, over 974731.20 frames.], batch size: 19, lr: 1.21e-03
2022-05-03 18:27:01,914 INFO [train.py:715] (4/8) Epoch 0, batch 30150, loss[loss=0.1997, simple_loss=0.2553, pruned_loss=0.072, over 4989.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2619, pruned_loss=0.0716, over 974331.56 frames.], batch size: 14, lr: 1.21e-03
2022-05-03 18:27:42,050 INFO [train.py:715] (4/8) Epoch 0, batch 30200, loss[loss=0.1564, simple_loss=0.222, pruned_loss=0.04536, over 4868.00 frames.], tot_loss[loss=0.203, simple_loss=0.262, pruned_loss=0.07204, over 973980.19 frames.], batch size: 16, lr: 1.21e-03
2022-05-03 18:28:22,541 INFO [train.py:715] (4/8) Epoch 0, batch 30250, loss[loss=0.1934, simple_loss=0.2582, pruned_loss=0.06429, over 4804.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2608, pruned_loss=0.07144, over 973153.81 frames.], batch size: 25, lr: 1.21e-03
2022-05-03 18:29:02,641 INFO [train.py:715] (4/8) Epoch 0, batch 30300, loss[loss=0.1974, simple_loss=0.2624, pruned_loss=0.06617, over 4920.00 frames.], tot_loss[loss=0.2011, simple_loss=0.26, pruned_loss=0.07112, over 973355.96 frames.], batch size: 18, lr: 1.21e-03
2022-05-03 18:29:43,071 INFO [train.py:715] (4/8) Epoch 0, batch 30350, loss[loss=0.1955, simple_loss=0.2497, pruned_loss=0.07071, over 4765.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2604, pruned_loss=0.07131, over 972462.67 frames.], batch size: 12, lr: 1.21e-03
2022-05-03 18:30:23,199 INFO [train.py:715] (4/8) Epoch 0, batch 30400, loss[loss=0.2427, simple_loss=0.2951, pruned_loss=0.09513, over 4811.00 frames.], tot_loss[loss=0.2007, simple_loss=0.2601, pruned_loss=0.07066, over 972103.49 frames.], batch size: 21, lr: 1.21e-03
2022-05-03 18:31:02,968 INFO [train.py:715] (4/8) Epoch 0, batch 30450, loss[loss=0.2022, simple_loss=0.2606, pruned_loss=0.07192, over 4959.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2612, pruned_loss=0.0715, over 972787.92 frames.], batch size: 14, lr: 1.21e-03
2022-05-03 18:31:42,723 INFO [train.py:715] (4/8) Epoch 0, batch 30500, loss[loss=0.2337, simple_loss=0.2875, pruned_loss=0.08997, over 4755.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2626, pruned_loss=0.07243, over 972418.31 frames.], batch size: 19, lr: 1.21e-03
2022-05-03 18:32:22,640 INFO [train.py:715] (4/8) Epoch 0, batch 30550, loss[loss=0.2001, simple_loss=0.2615, pruned_loss=0.06938, over 4940.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2618, pruned_loss=0.07199, over 971929.62 frames.], batch size: 21, lr: 1.21e-03
2022-05-03 18:33:01,762 INFO [train.py:715] (4/8) Epoch 0, batch 30600, loss[loss=0.227, simple_loss=0.2767, pruned_loss=0.08865, over 4945.00 frames.], tot_loss[loss=0.202, simple_loss=0.2609, pruned_loss=0.07155, over 971975.91 frames.], batch size: 29, lr: 1.20e-03
2022-05-03 18:33:41,703 INFO [train.py:715] (4/8) Epoch 0, batch 30650, loss[loss=0.2007, simple_loss=0.2664, pruned_loss=0.06755, over 4899.00 frames.], tot_loss[loss=0.2016, simple_loss=0.2608, pruned_loss=0.0712, over 971797.22 frames.], batch size: 19, lr: 1.20e-03
2022-05-03 18:34:21,519 INFO [train.py:715] (4/8) Epoch 0, batch 30700, loss[loss=0.205, simple_loss=0.2633, pruned_loss=0.07334, over 4845.00 frames.], tot_loss[loss=0.2021, simple_loss=0.261, pruned_loss=0.07167, over 971910.50 frames.], batch size: 30, lr: 1.20e-03
2022-05-03 18:35:01,620 INFO [train.py:715] (4/8) Epoch 0, batch 30750, loss[loss=0.1625, simple_loss=0.225, pruned_loss=0.04994, over 4968.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2609, pruned_loss=0.07179, over 972460.54 frames.], batch size: 28, lr: 1.20e-03
2022-05-03 18:35:40,971 INFO [train.py:715] (4/8) Epoch 0, batch 30800, loss[loss=0.1992, simple_loss=0.2566, pruned_loss=0.07094, over 4906.00 frames.], tot_loss[loss=0.2013, simple_loss=0.2602, pruned_loss=0.07117, over 971872.43 frames.], batch size: 18, lr: 1.20e-03
2022-05-03 18:36:21,304 INFO [train.py:715] (4/8) Epoch 0, batch 30850, loss[loss=0.1897, simple_loss=0.2561, pruned_loss=0.06167, over 4957.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2598, pruned_loss=0.07131, over 972535.80 frames.], batch size: 21, lr: 1.20e-03
2022-05-03 18:37:01,145 INFO [train.py:715] (4/8) Epoch 0, batch 30900, loss[loss=0.2024, simple_loss=0.2519, pruned_loss=0.07647, over 4974.00 frames.], tot_loss[loss=0.202, simple_loss=0.2601, pruned_loss=0.07191, over 972129.20 frames.], batch size: 14, lr: 1.20e-03
2022-05-03 18:37:40,862 INFO [train.py:715] (4/8) Epoch 0, batch 30950, loss[loss=0.188, simple_loss=0.2523, pruned_loss=0.06188, over 4790.00 frames.], tot_loss[loss=0.2029, simple_loss=0.261, pruned_loss=0.07241, over 971416.99 frames.], batch size: 17, lr: 1.20e-03
2022-05-03 18:38:20,947 INFO [train.py:715] (4/8) Epoch 0, batch 31000, loss[loss=0.1798, simple_loss=0.2433, pruned_loss=0.05817, over 4803.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2618, pruned_loss=0.07264, over 972074.88 frames.], batch size: 21, lr: 1.20e-03
2022-05-03 18:39:00,965 INFO [train.py:715] (4/8) Epoch 0, batch 31050, loss[loss=0.161, simple_loss=0.2364, pruned_loss=0.04278, over 4738.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2611, pruned_loss=0.07195, over 972039.61 frames.], batch size: 16, lr: 1.20e-03
2022-05-03 18:39:40,374 INFO [train.py:715] (4/8) Epoch 0, batch 31100, loss[loss=0.1707, simple_loss=0.2384, pruned_loss=0.05153, over 4978.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2607, pruned_loss=0.07111, over 971870.58 frames.], batch size: 28, lr: 1.20e-03
2022-05-03 18:40:19,532 INFO [train.py:715] (4/8) Epoch 0, batch 31150, loss[loss=0.238, simple_loss=0.2828, pruned_loss=0.09661, over 4857.00 frames.], tot_loss[loss=0.2005, simple_loss=0.26, pruned_loss=0.07053, over 971807.64 frames.], batch size: 20, lr: 1.19e-03
2022-05-03 18:40:59,611 INFO [train.py:715] (4/8) Epoch 0, batch 31200, loss[loss=0.2159, simple_loss=0.2714, pruned_loss=0.08016, over 4900.00 frames.], tot_loss[loss=0.201, simple_loss=0.2605, pruned_loss=0.07068, over 972631.82 frames.], batch size: 23, lr: 1.19e-03
2022-05-03 18:41:39,408 INFO [train.py:715] (4/8) Epoch 0, batch 31250, loss[loss=0.1992, simple_loss=0.2753, pruned_loss=0.06154, over 4959.00 frames.], tot_loss[loss=0.2017, simple_loss=0.2612, pruned_loss=0.07112, over 972394.84 frames.], batch size: 24, lr: 1.19e-03
2022-05-03 18:42:18,876 INFO [train.py:715] (4/8) Epoch 0, batch 31300, loss[loss=0.1563, simple_loss=0.2221, pruned_loss=0.04528, over 4911.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2615, pruned_loss=0.07111, over 972577.24 frames.], batch size: 17, lr: 1.19e-03
2022-05-03 18:42:59,213 INFO [train.py:715] (4/8) Epoch 0, batch 31350, loss[loss=0.2014, simple_loss=0.2564, pruned_loss=0.07323, over 4957.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2618, pruned_loss=0.07121, over 972216.06 frames.], batch size: 21, lr: 1.19e-03
2022-05-03 18:43:38,895 INFO [train.py:715] (4/8) Epoch 0, batch 31400, loss[loss=0.1643, simple_loss=0.23, pruned_loss=0.04929, over 4812.00 frames.], tot_loss[loss=0.2012, simple_loss=0.261, pruned_loss=0.07068, over 972311.11 frames.], batch size: 14, lr: 1.19e-03
2022-05-03 18:44:18,171 INFO [train.py:715] (4/8) Epoch 0, batch 31450, loss[loss=0.1975, simple_loss=0.255, pruned_loss=0.07, over 4787.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2629, pruned_loss=0.07222, over 972521.05 frames.], batch size: 14, lr: 1.19e-03
2022-05-03 18:44:57,272 INFO [train.py:715] (4/8) Epoch 0, batch 31500, loss[loss=0.1731, simple_loss=0.2396, pruned_loss=0.0533, over 4825.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2619, pruned_loss=0.07218, over 972080.90 frames.], batch size: 13, lr: 1.19e-03
2022-05-03 18:45:37,321 INFO [train.py:715] (4/8) Epoch 0, batch 31550, loss[loss=0.162, simple_loss=0.2339, pruned_loss=0.04505, over 4782.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2624, pruned_loss=0.07226, over 972101.63 frames.], batch size: 17, lr: 1.19e-03
2022-05-03 18:46:17,102 INFO [train.py:715] (4/8) Epoch 0, batch 31600, loss[loss=0.1876, simple_loss=0.2464, pruned_loss=0.06436, over 4850.00 frames.], tot_loss[loss=0.2033, simple_loss=0.2618, pruned_loss=0.07238, over 971452.18 frames.], batch size: 13, lr: 1.19e-03
2022-05-03 18:46:56,334 INFO [train.py:715] (4/8) Epoch 0, batch 31650, loss[loss=0.2215, simple_loss=0.2764, pruned_loss=0.08329, over 4880.00 frames.], tot_loss[loss=0.2041, simple_loss=0.2625, pruned_loss=0.07288, over 971976.79 frames.], batch size: 22, lr: 1.19e-03
2022-05-03 18:47:36,246 INFO [train.py:715] (4/8) Epoch 0, batch 31700, loss[loss=0.2174, simple_loss=0.2711, pruned_loss=0.08183, over 4755.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2615, pruned_loss=0.07263, over 971298.46 frames.], batch size: 19, lr: 1.18e-03
2022-05-03 18:48:16,470 INFO [train.py:715] (4/8) Epoch 0, batch 31750, loss[loss=0.1793, simple_loss=0.2455, pruned_loss=0.05656, over 4799.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2614, pruned_loss=0.0724, over 971421.92 frames.], batch size: 25, lr: 1.18e-03
2022-05-03 18:48:56,201 INFO [train.py:715] (4/8) Epoch 0, batch 31800, loss[loss=0.1991, simple_loss=0.2536, pruned_loss=0.07223, over 4784.00 frames.], tot_loss[loss=0.2022, simple_loss=0.2606, pruned_loss=0.07187, over 971663.88 frames.], batch size: 18, lr: 1.18e-03
2022-05-03 18:49:35,467 INFO [train.py:715] (4/8) Epoch 0, batch 31850, loss[loss=0.1817, simple_loss=0.2449, pruned_loss=0.05921, over 4853.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2614, pruned_loss=0.07273, over 971702.03 frames.], batch size: 20, lr: 1.18e-03
2022-05-03 18:50:15,965 INFO [train.py:715] (4/8) Epoch 0, batch 31900, loss[loss=0.2215, simple_loss=0.2899, pruned_loss=0.07656, over 4826.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2606, pruned_loss=0.07221, over 971579.90 frames.], batch size: 15, lr: 1.18e-03
2022-05-03 18:50:55,672 INFO [train.py:715] (4/8) Epoch 0, batch 31950, loss[loss=0.1562, simple_loss=0.2143, pruned_loss=0.04905, over 4886.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2617, pruned_loss=0.0721, over 971453.31 frames.], batch size: 22, lr: 1.18e-03
2022-05-03 18:51:37,230 INFO [train.py:715] (4/8) Epoch 0, batch 32000, loss[loss=0.1751, simple_loss=0.2295, pruned_loss=0.06036, over 4979.00 frames.], tot_loss[loss=0.2021, simple_loss=0.2608, pruned_loss=0.07167, over 971074.80 frames.], batch size: 25, lr: 1.18e-03
2022-05-03 18:52:17,385 INFO [train.py:715] (4/8) Epoch 0, batch 32050, loss[loss=0.2114, simple_loss=0.2636, pruned_loss=0.07959, over 4888.00 frames.], tot_loss[loss=0.2024, simple_loss=0.2613, pruned_loss=0.07177, over 970845.23 frames.], batch size: 19, lr: 1.18e-03
2022-05-03 18:52:57,276 INFO [train.py:715] (4/8) Epoch 0, batch 32100, loss[loss=0.1868, simple_loss=0.2547, pruned_loss=0.05948, over 4802.00 frames.], tot_loss[loss=0.2025, simple_loss=0.2615, pruned_loss=0.07172, over 971028.26 frames.], batch size: 21, lr: 1.18e-03
2022-05-03 18:53:36,625 INFO [train.py:715] (4/8) Epoch 0, batch 32150, loss[loss=0.1965, simple_loss=0.2634, pruned_loss=0.06478, over 4920.00 frames.], tot_loss[loss=0.2029, simple_loss=0.2621, pruned_loss=0.07185, over 971130.69 frames.], batch size: 23, lr: 1.18e-03
2022-05-03 18:54:15,807 INFO [train.py:715] (4/8) Epoch 0, batch 32200, loss[loss=0.2014, simple_loss=0.2785, pruned_loss=0.06212, over 4856.00 frames.], tot_loss[loss=0.2031, simple_loss=0.2623, pruned_loss=0.07199, over 971676.85 frames.], batch size: 20, lr: 1.18e-03
2022-05-03 18:54:55,961 INFO [train.py:715] (4/8) Epoch 0, batch 32250, loss[loss=0.2209, simple_loss=0.2785, pruned_loss=0.0817, over 4957.00 frames.], tot_loss[loss=0.2032, simple_loss=0.2622, pruned_loss=0.07214, over 971818.28 frames.], batch size: 21, lr: 1.17e-03
2022-05-03 18:55:35,807 INFO [train.py:715] (4/8) Epoch 0, batch 32300, loss[loss=0.1738, simple_loss=0.2341, pruned_loss=0.05672, over 4968.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2623, pruned_loss=0.07253, over 972654.13 frames.], batch size: 24, lr: 1.17e-03
2022-05-03 18:56:15,320 INFO [train.py:715] (4/8) Epoch 0, batch 32350, loss[loss=0.1863, simple_loss=0.2497, pruned_loss=0.06144, over 4903.00 frames.], tot_loss[loss=0.2037, simple_loss=0.2627, pruned_loss=0.07237, over 972872.22 frames.], batch size: 19, lr: 1.17e-03
2022-05-03 18:56:55,312 INFO [train.py:715] (4/8) Epoch 0, batch 32400, loss[loss=0.1937, simple_loss=0.2709, pruned_loss=0.05823, over 4945.00 frames.], tot_loss[loss=0.204, simple_loss=0.2628, pruned_loss=0.07258, over 973293.98 frames.], batch size: 21, lr: 1.17e-03
2022-05-03 18:57:35,388 INFO [train.py:715] (4/8) Epoch 0, batch 32450, loss[loss=0.1789, simple_loss=0.2479, pruned_loss=0.0549, over 4945.00 frames.], tot_loss[loss=0.2053, simple_loss=0.2639, pruned_loss=0.07331, over 972977.82 frames.], batch size: 24, lr: 1.17e-03
2022-05-03 18:58:15,183 INFO [train.py:715] (4/8) Epoch 0, batch 32500, loss[loss=0.1969, simple_loss=0.2573, pruned_loss=0.06825, over 4935.00 frames.], tot_loss[loss=0.2035, simple_loss=0.2622, pruned_loss=0.07244, over 973444.35 frames.], batch size: 39, lr: 1.17e-03
2022-05-03 18:58:54,506 INFO [train.py:715] (4/8) Epoch 0, batch 32550, loss[loss=0.1682, simple_loss=0.2346, pruned_loss=0.05091, over 4859.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2619, pruned_loss=0.07246, over 973087.96 frames.], batch size: 20, lr: 1.17e-03
2022-05-03 18:59:34,022 INFO [train.py:715] (4/8) Epoch 0, batch 32600, loss[loss=0.1923, simple_loss=0.2567, pruned_loss=0.06393, over 4752.00 frames.], tot_loss[loss=0.2037, simple_loss=0.262, pruned_loss=0.07272, over 972320.20 frames.], batch size: 19, lr: 1.17e-03
2022-05-03 19:00:13,280 INFO [train.py:715] (4/8) Epoch 0, batch 32650, loss[loss=0.1797, simple_loss=0.2552, pruned_loss=0.0521, over 4911.00 frames.], tot_loss[loss=0.204, simple_loss=0.2627, pruned_loss=0.07265, over 971927.17 frames.], batch size: 18, lr: 1.17e-03
2022-05-03 19:00:52,618 INFO [train.py:715] (4/8) Epoch 0, batch 32700, loss[loss=0.2147, simple_loss=0.2775, pruned_loss=0.07595, over 4906.00 frames.], tot_loss[loss=0.2043, simple_loss=0.2631, pruned_loss=0.07272, over 972500.36 frames.], batch size: 17, lr: 1.17e-03
2022-05-03 19:01:32,097 INFO [train.py:715] (4/8) Epoch 0, batch 32750, loss[loss=0.204, simple_loss=0.2621, pruned_loss=0.07294, over 4985.00 frames.], tot_loss[loss=0.2034, simple_loss=0.2624, pruned_loss=0.07224, over 972135.97 frames.], batch size: 28, lr: 1.17e-03
2022-05-03 19:02:12,126 INFO [train.py:715] (4/8) Epoch 0, batch 32800, loss[loss=0.2414, simple_loss=0.2955, pruned_loss=0.09367, over 4983.00 frames.], tot_loss[loss=0.2026, simple_loss=0.2622, pruned_loss=0.07153, over 971745.51 frames.], batch size: 25, lr: 1.16e-03
2022-05-03 19:02:51,635 INFO [train.py:715] (4/8) Epoch 0, batch 32850, loss[loss=0.2239, simple_loss=0.2865, pruned_loss=0.08063, over 4824.00 frames.], tot_loss[loss=0.2027, simple_loss=0.2623, pruned_loss=0.07161, over 971593.42 frames.], batch size: 25, lr: 1.16e-03
2022-05-03 19:03:31,121 INFO [train.py:715] (4/8) Epoch 0, batch 32900, loss[loss=0.2052, simple_loss=0.2473, pruned_loss=0.08155, over 4843.00 frames.], tot_loss[loss=0.2031, simple_loss=0.262, pruned_loss=0.07212, over 972213.11 frames.], batch size: 13, lr: 1.16e-03
2022-05-03 19:04:11,178 INFO [train.py:715] (4/8) Epoch 0, batch 32950, loss[loss=0.1973, simple_loss=0.2642, pruned_loss=0.0652, over 4788.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2604, pruned_loss=0.0712, over 972341.62 frames.], batch size: 13, lr: 1.16e-03
2022-05-03 19:04:50,685 INFO [train.py:715] (4/8) Epoch 0, batch 33000, loss[loss=0.1946, simple_loss=0.2453, pruned_loss=0.07196, over 4950.00 frames.], tot_loss[loss=0.2014, simple_loss=0.2603, pruned_loss=0.07122, over 972626.35 frames.], batch size: 23, lr: 1.16e-03
2022-05-03 19:04:50,686 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 19:05:00,796 INFO [train.py:742] (4/8) Epoch 0, validation: loss=0.1303, simple_loss=0.2174, pruned_loss=0.02158, over 914524.00 frames.
2022-05-03 19:05:40,756 INFO [train.py:715] (4/8) Epoch 0, batch 33050, loss[loss=0.1865, simple_loss=0.2577, pruned_loss=0.0576, over 4846.00 frames.], tot_loss[loss=0.2019, simple_loss=0.2608, pruned_loss=0.07145, over 972540.99 frames.], batch size: 20, lr: 1.16e-03
2022-05-03 19:06:20,362 INFO [train.py:715] (4/8) Epoch 0, batch 33100, loss[loss=0.1498, simple_loss=0.2278, pruned_loss=0.03594, over 4793.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2596, pruned_loss=0.0703, over 972574.74 frames.], batch size: 24, lr: 1.16e-03
2022-05-03 19:07:01,034 INFO [train.py:715] (4/8) Epoch 0, batch 33150, loss[loss=0.2088, simple_loss=0.276, pruned_loss=0.07082, over 4806.00 frames.], tot_loss[loss=0.2008, simple_loss=0.2605, pruned_loss=0.07053, over 973079.31 frames.], batch size: 25, lr: 1.16e-03
2022-05-03 19:07:41,374 INFO [train.py:715] (4/8) Epoch 0, batch 33200, loss[loss=0.179, simple_loss=0.2347, pruned_loss=0.06158, over 4823.00 frames.], tot_loss[loss=0.2012, simple_loss=0.2604, pruned_loss=0.07103, over 972772.10 frames.], batch size: 13, lr: 1.16e-03
2022-05-03 19:08:21,610 INFO [train.py:715] (4/8) Epoch 0, batch 33250, loss[loss=0.1984, simple_loss=0.2574, pruned_loss=0.06974, over 4952.00 frames.], tot_loss[loss=0.2002, simple_loss=0.2597, pruned_loss=0.07039, over 973588.37 frames.], batch size: 39, lr: 1.16e-03
2022-05-03 19:09:01,823 INFO [train.py:715] (4/8) Epoch 0, batch 33300, loss[loss=0.1471, simple_loss=0.2172, pruned_loss=0.03845, over 4736.00 frames.], tot_loss[loss=0.1993, simple_loss=0.259, pruned_loss=0.06978, over 973538.66 frames.], batch size: 16, lr: 1.16e-03
2022-05-03 19:09:42,543 INFO [train.py:715] (4/8) Epoch 0, batch 33350, loss[loss=0.2747, simple_loss=0.3153, pruned_loss=0.117, over 4939.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2581, pruned_loss=0.06915, over 974706.99 frames.], batch size: 24, lr: 1.16e-03
2022-05-03 19:10:22,693 INFO [train.py:715] (4/8) Epoch 0, batch 33400, loss[loss=0.1999, simple_loss=0.2707, pruned_loss=0.06456, over 4807.00 frames.], tot_loss[loss=0.1979, simple_loss=0.2582, pruned_loss=0.06879, over 974685.42 frames.], batch size: 21, lr: 1.15e-03
2022-05-03 19:11:02,717 INFO [train.py:715] (4/8) Epoch 0, batch 33450, loss[loss=0.1694, simple_loss=0.2389, pruned_loss=0.04994, over 4856.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2586, pruned_loss=0.06891, over 973274.41 frames.], batch size: 20, lr: 1.15e-03
2022-05-03 19:11:43,375 INFO [train.py:715] (4/8) Epoch 0, batch 33500, loss[loss=0.1928, simple_loss=0.2527, pruned_loss=0.06642, over 4873.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2593, pruned_loss=0.06896, over 973211.47 frames.], batch size: 32, lr: 1.15e-03
2022-05-03 19:12:23,729 INFO [train.py:715] (4/8) Epoch 0, batch 33550, loss[loss=0.189, simple_loss=0.2497, pruned_loss=0.06409, over 4772.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2579, pruned_loss=0.06844, over 972387.91 frames.], batch size: 14, lr: 1.15e-03
2022-05-03 19:13:02,912 INFO [train.py:715] (4/8) Epoch 0, batch 33600, loss[loss=0.2373, simple_loss=0.2924, pruned_loss=0.09105, over 4885.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2594, pruned_loss=0.06969, over 972123.42 frames.], batch size: 16, lr: 1.15e-03
2022-05-03 19:13:43,488 INFO [train.py:715] (4/8) Epoch 0, batch 33650, loss[loss=0.2164, simple_loss=0.2802, pruned_loss=0.07633, over 4910.00 frames.], tot_loss[loss=0.199, simple_loss=0.2594, pruned_loss=0.06927, over 972312.60 frames.], batch size: 19, lr: 1.15e-03
2022-05-03 19:14:23,803 INFO [train.py:715] (4/8) Epoch 0, batch 33700, loss[loss=0.2361, simple_loss=0.297, pruned_loss=0.08764, over 4856.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2585, pruned_loss=0.06952, over 972804.41 frames.], batch size: 30, lr: 1.15e-03
2022-05-03 19:15:03,031 INFO [train.py:715] (4/8) Epoch 0, batch 33750, loss[loss=0.1832, simple_loss=0.2452, pruned_loss=0.0606, over 4870.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2582, pruned_loss=0.06919, over 971938.47 frames.], batch size: 16, lr: 1.15e-03
2022-05-03 19:15:42,514 INFO [train.py:715] (4/8) Epoch 0, batch 33800, loss[loss=0.2412, simple_loss=0.2979, pruned_loss=0.09222, over 4694.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2585, pruned_loss=0.06923, over 972278.53 frames.], batch size: 15, lr: 1.15e-03
2022-05-03 19:16:22,772 INFO [train.py:715] (4/8) Epoch 0, batch 33850, loss[loss=0.1625, simple_loss=0.2293, pruned_loss=0.0479, over 4988.00 frames.], tot_loss[loss=0.1987, simple_loss=0.2586, pruned_loss=0.06945, over 972128.99 frames.], batch size: 14, lr: 1.15e-03
2022-05-03 19:17:02,059 INFO [train.py:715] (4/8) Epoch 0, batch 33900, loss[loss=0.1677, simple_loss=0.2243, pruned_loss=0.05553, over 4646.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2586, pruned_loss=0.06918, over 971705.90 frames.], batch size: 13, lr: 1.15e-03
2022-05-03 19:17:41,114 INFO [train.py:715] (4/8) Epoch 0, batch 33950, loss[loss=0.1995, simple_loss=0.2683, pruned_loss=0.06538, over 4707.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2583, pruned_loss=0.06918, over 971706.76 frames.], batch size: 15, lr: 1.15e-03
2022-05-03 19:18:21,086 INFO [train.py:715] (4/8) Epoch 0, batch 34000, loss[loss=0.2124, simple_loss=0.254, pruned_loss=0.0854, over 4972.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2579, pruned_loss=0.06918, over 972861.22 frames.], batch size: 14, lr: 1.14e-03
2022-05-03 19:19:00,964 INFO [train.py:715] (4/8) Epoch 0, batch 34050, loss[loss=0.1418, simple_loss=0.2126, pruned_loss=0.03545, over 4751.00 frames.], tot_loss[loss=0.1988, simple_loss=0.2583, pruned_loss=0.06963, over 972671.71 frames.], batch size: 14, lr: 1.14e-03
2022-05-03 19:19:40,628 INFO [train.py:715] (4/8) Epoch 0, batch 34100, loss[loss=0.2211, simple_loss=0.2776, pruned_loss=0.08235, over 4932.00 frames.], tot_loss[loss=0.1999, simple_loss=0.2594, pruned_loss=0.07026, over 972500.74 frames.], batch size: 21, lr: 1.14e-03
2022-05-03 19:20:19,826 INFO [train.py:715] (4/8) Epoch 0, batch 34150, loss[loss=0.1795, simple_loss=0.2318, pruned_loss=0.06363, over 4903.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2581, pruned_loss=0.06916, over 972748.97 frames.], batch size: 17, lr: 1.14e-03
2022-05-03 19:20:59,753 INFO [train.py:715] (4/8) Epoch 0, batch 34200, loss[loss=0.2039, simple_loss=0.2684, pruned_loss=0.06969, over 4992.00 frames.], tot_loss[loss=0.1977, simple_loss=0.258, pruned_loss=0.06866, over 973284.39 frames.], batch size: 26, lr: 1.14e-03
2022-05-03 19:21:39,297 INFO [train.py:715] (4/8) Epoch 0, batch 34250, loss[loss=0.1963, simple_loss=0.2563, pruned_loss=0.06813, over 4893.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2584, pruned_loss=0.06912, over 973035.39 frames.], batch size: 19, lr: 1.14e-03
2022-05-03 19:22:18,601 INFO [train.py:715] (4/8) Epoch 0, batch 34300, loss[loss=0.1643, simple_loss=0.2436, pruned_loss=0.04251, over 4869.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2575, pruned_loss=0.06885, over 973607.36 frames.], batch size: 20, lr: 1.14e-03
2022-05-03 19:22:58,854 INFO [train.py:715] (4/8) Epoch 0, batch 34350, loss[loss=0.1779, simple_loss=0.233, pruned_loss=0.06141, over 4883.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2575, pruned_loss=0.06897, over 972538.55 frames.], batch size: 22, lr: 1.14e-03
2022-05-03 19:23:39,059 INFO [train.py:715] (4/8) Epoch 0, batch 34400, loss[loss=0.2039, simple_loss=0.2663, pruned_loss=0.07072, over 4904.00 frames.], tot_loss[loss=0.1989, simple_loss=0.2588, pruned_loss=0.06945, over 972555.80 frames.], batch size: 19, lr: 1.14e-03
2022-05-03 19:24:18,629 INFO [train.py:715] (4/8) Epoch 0, batch 34450, loss[loss=0.2528, simple_loss=0.2846, pruned_loss=0.1105, over 4828.00 frames.], tot_loss[loss=0.201, simple_loss=0.2607, pruned_loss=0.07065, over 972103.67 frames.], batch size: 13, lr: 1.14e-03
2022-05-03 19:24:57,901 INFO [train.py:715] (4/8) Epoch 0, batch 34500, loss[loss=0.2009, simple_loss=0.2592, pruned_loss=0.07127, over 4778.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2606, pruned_loss=0.07056, over 972805.17 frames.], batch size: 14, lr: 1.14e-03
2022-05-03 19:25:38,245 INFO [train.py:715] (4/8) Epoch 0, batch 34550, loss[loss=0.1583, simple_loss=0.2307, pruned_loss=0.04296, over 4882.00 frames.], tot_loss[loss=0.2009, simple_loss=0.2604, pruned_loss=0.0707, over 973338.61 frames.], batch size: 22, lr: 1.14e-03
2022-05-03 19:26:17,980 INFO [train.py:715] (4/8) Epoch 0, batch 34600, loss[loss=0.1936, simple_loss=0.2485, pruned_loss=0.0694, over 4905.00 frames.], tot_loss[loss=0.2001, simple_loss=0.2596, pruned_loss=0.07028, over 972676.25 frames.], batch size: 23, lr: 1.13e-03
2022-05-03 19:26:57,210 INFO [train.py:715] (4/8) Epoch 0, batch 34650, loss[loss=0.158, simple_loss=0.222, pruned_loss=0.04705, over 4763.00 frames.], tot_loss[loss=0.1994, simple_loss=0.2588, pruned_loss=0.06998, over 971795.50 frames.], batch size: 19, lr: 1.13e-03
2022-05-03 19:27:37,737 INFO [train.py:715] (4/8) Epoch 0, batch 34700, loss[loss=0.2045, simple_loss=0.2674, pruned_loss=0.0708, over 4811.00 frames.], tot_loss[loss=0.1978, simple_loss=0.2575, pruned_loss=0.06907, over 971542.58 frames.], batch size: 25, lr: 1.13e-03
2022-05-03 19:28:15,920 INFO [train.py:715] (4/8) Epoch 0, batch 34750, loss[loss=0.197, simple_loss=0.2515, pruned_loss=0.07126, over 4854.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2572, pruned_loss=0.06909, over 970965.24 frames.], batch size: 20, lr: 1.13e-03
2022-05-03 19:28:53,213 INFO [train.py:715] (4/8) Epoch 0, batch 34800, loss[loss=0.1734, simple_loss=0.2347, pruned_loss=0.05606, over 4756.00 frames.], tot_loss[loss=0.1961, simple_loss=0.2557, pruned_loss=0.06824, over 970441.79 frames.], batch size: 12, lr: 1.13e-03
2022-05-03 19:29:42,569 INFO [train.py:715] (4/8) Epoch 1, batch 0, loss[loss=0.2404, simple_loss=0.2993, pruned_loss=0.0907, over 4825.00 frames.], tot_loss[loss=0.2404, simple_loss=0.2993, pruned_loss=0.0907, over 4825.00 frames.], batch size: 15, lr: 1.11e-03
2022-05-03 19:30:21,872 INFO [train.py:715] (4/8) Epoch 1, batch 50, loss[loss=0.2161, simple_loss=0.2641, pruned_loss=0.08407, over 4862.00 frames.], tot_loss[loss=0.2018, simple_loss=0.2594, pruned_loss=0.07212, over 219110.38 frames.], batch size: 32, lr: 1.11e-03
2022-05-03 19:31:01,847 INFO [train.py:715] (4/8) Epoch 1, batch 100, loss[loss=0.1779, simple_loss=0.232, pruned_loss=0.06193, over 4897.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2572, pruned_loss=0.06896, over 386233.29 frames.], batch size: 19, lr: 1.11e-03
2022-05-03 19:31:41,279 INFO [train.py:715] (4/8) Epoch 1, batch 150, loss[loss=0.2225, simple_loss=0.2714, pruned_loss=0.08683, over 4852.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2579, pruned_loss=0.06917, over 516566.32 frames.], batch size: 30, lr: 1.11e-03
2022-05-03 19:32:20,517 INFO [train.py:715] (4/8) Epoch 1, batch 200, loss[loss=0.2288, simple_loss=0.2852, pruned_loss=0.08616, over 4802.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2571, pruned_loss=0.06902, over 616947.58 frames.], batch size: 21, lr: 1.11e-03
2022-05-03 19:33:00,052 INFO [train.py:715] (4/8) Epoch 1, batch 250, loss[loss=0.2274, simple_loss=0.2757, pruned_loss=0.08955, over 4805.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2574, pruned_loss=0.06841, over 695539.36 frames.], batch size: 21, lr: 1.11e-03
2022-05-03 19:33:40,735 INFO [train.py:715] (4/8) Epoch 1, batch 300, loss[loss=0.2148, simple_loss=0.2679, pruned_loss=0.08087, over 4855.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2559, pruned_loss=0.06773, over 757741.41 frames.], batch size: 20, lr: 1.11e-03
2022-05-03 19:34:21,106 INFO [train.py:715] (4/8) Epoch 1, batch 350, loss[loss=0.2152, simple_loss=0.2721, pruned_loss=0.07919, over 4869.00 frames.], tot_loss[loss=0.1971, simple_loss=0.2568, pruned_loss=0.06875, over 805994.90 frames.], batch size: 16, lr: 1.11e-03
2022-05-03 19:35:01,379 INFO [train.py:715] (4/8) Epoch 1, batch 400, loss[loss=0.1974, simple_loss=0.2506, pruned_loss=0.07206, over 4975.00 frames.], tot_loss[loss=0.1993, simple_loss=0.258, pruned_loss=0.07029, over 842711.07 frames.], batch size: 15, lr: 1.11e-03
2022-05-03 19:35:42,056 INFO [train.py:715] (4/8) Epoch 1, batch 450, loss[loss=0.191, simple_loss=0.2614, pruned_loss=0.06031, over 4882.00 frames.], tot_loss[loss=0.1983, simple_loss=0.2578, pruned_loss=0.06942, over 871191.87 frames.], batch size: 22, lr: 1.11e-03
2022-05-03 19:36:22,780 INFO [train.py:715] (4/8) Epoch 1, batch 500, loss[loss=0.2211, simple_loss=0.2806, pruned_loss=0.08086, over 4782.00 frames.], tot_loss[loss=0.198, simple_loss=0.2576, pruned_loss=0.06916, over 892973.05 frames.], batch size: 14, lr: 1.11e-03
2022-05-03 19:37:03,285 INFO [train.py:715] (4/8) Epoch 1, batch 550, loss[loss=0.2193, simple_loss=0.2725, pruned_loss=0.08306, over 4825.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2575, pruned_loss=0.06869, over 911103.32 frames.], batch size: 15, lr: 1.11e-03
2022-05-03 19:37:43,265 INFO [train.py:715] (4/8) Epoch 1, batch 600, loss[loss=0.1708, simple_loss=0.2394, pruned_loss=0.05104, over 4897.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2579, pruned_loss=0.06873, over 924350.34 frames.], batch size: 19, lr: 1.10e-03
2022-05-03 19:38:23,974 INFO [train.py:715] (4/8) Epoch 1, batch 650, loss[loss=0.1729, simple_loss=0.2465, pruned_loss=0.0496, over 4919.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2575, pruned_loss=0.06807, over 934693.73 frames.], batch size: 39, lr: 1.10e-03
2022-05-03 19:39:04,139 INFO [train.py:715] (4/8) Epoch 1, batch 700, loss[loss=0.2122, simple_loss=0.2666, pruned_loss=0.07885, over 4786.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2572, pruned_loss=0.06819, over 942403.38 frames.], batch size: 14, lr: 1.10e-03
2022-05-03 19:39:44,117 INFO [train.py:715] (4/8) Epoch 1, batch 750, loss[loss=0.2202, simple_loss=0.2702, pruned_loss=0.08507, over 4924.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2575, pruned_loss=0.06843, over 949327.57 frames.], batch size: 17, lr: 1.10e-03
2022-05-03 19:40:24,214 INFO [train.py:715] (4/8) Epoch 1, batch 800, loss[loss=0.1854, simple_loss=0.2304, pruned_loss=0.07023, over 4983.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2571, pruned_loss=0.06811, over 954659.46 frames.], batch size: 31, lr: 1.10e-03
2022-05-03 19:41:04,457 INFO [train.py:715] (4/8) Epoch 1, batch 850, loss[loss=0.1983, simple_loss=0.2596, pruned_loss=0.06849, over 4856.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2571, pruned_loss=0.06781, over 958262.78 frames.], batch size: 15, lr: 1.10e-03
2022-05-03 19:41:43,688 INFO [train.py:715] (4/8) Epoch 1, batch 900, loss[loss=0.1951, simple_loss=0.2667, pruned_loss=0.06175, over 4826.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2567, pruned_loss=0.06749, over 961833.59 frames.], batch size: 26, lr: 1.10e-03
2022-05-03 19:42:22,967 INFO [train.py:715] (4/8) Epoch 1, batch 950, loss[loss=0.1931, simple_loss=0.2502, pruned_loss=0.06805, over 4963.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2576, pruned_loss=0.06849, over 964093.39 frames.], batch size: 15, lr: 1.10e-03
2022-05-03 19:43:02,563 INFO [train.py:715] (4/8) Epoch 1, batch 1000, loss[loss=0.2213, simple_loss=0.2741, pruned_loss=0.0842, over 4795.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2569, pruned_loss=0.0679, over 965453.03 frames.], batch size: 24, lr: 1.10e-03
2022-05-03 19:43:41,900 INFO [train.py:715] (4/8) Epoch 1, batch 1050, loss[loss=0.2333, simple_loss=0.2719, pruned_loss=0.09742, over 4839.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2569, pruned_loss=0.06817, over 966330.11 frames.], batch size: 30, lr: 1.10e-03
2022-05-03 19:44:20,961 INFO [train.py:715] (4/8) Epoch 1, batch 1100, loss[loss=0.1794, simple_loss=0.2488, pruned_loss=0.05494, over 4811.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2579, pruned_loss=0.06839, over 967677.75 frames.], batch size: 25, lr: 1.10e-03
2022-05-03 19:45:00,272 INFO [train.py:715] (4/8) Epoch 1, batch 1150, loss[loss=0.224, simple_loss=0.2814, pruned_loss=0.08334, over 4963.00 frames.], tot_loss[loss=0.1974, simple_loss=0.258, pruned_loss=0.06838, over 968842.79 frames.], batch size: 39, lr: 1.10e-03
2022-05-03 19:45:40,268 INFO [train.py:715] (4/8) Epoch 1, batch 1200, loss[loss=0.2017, simple_loss=0.2706, pruned_loss=0.06643, over 4875.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2577, pruned_loss=0.06808, over 969736.68 frames.], batch size: 16, lr: 1.10e-03
2022-05-03 19:46:19,424 INFO [train.py:715] (4/8) Epoch 1, batch 1250, loss[loss=0.1875, simple_loss=0.2439, pruned_loss=0.06552, over 4891.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2579, pruned_loss=0.06825, over 970536.32 frames.], batch size: 22, lr: 1.10e-03
2022-05-03 19:46:58,954 INFO [train.py:715] (4/8) Epoch 1, batch 1300, loss[loss=0.2426, simple_loss=0.2639, pruned_loss=0.1107, over 4959.00 frames.], tot_loss[loss=0.1972, simple_loss=0.2574, pruned_loss=0.06847, over 970112.56 frames.], batch size: 14, lr: 1.09e-03
2022-05-03 19:47:39,267 INFO [train.py:715] (4/8) Epoch 1, batch 1350, loss[loss=0.1935, simple_loss=0.2597, pruned_loss=0.06365, over 4772.00 frames.], tot_loss[loss=0.1962, simple_loss=0.2563, pruned_loss=0.068, over 970337.37 frames.], batch size: 12, lr: 1.09e-03
2022-05-03 19:48:18,892 INFO [train.py:715] (4/8) Epoch 1, batch 1400, loss[loss=0.165, simple_loss=0.2388, pruned_loss=0.04563, over 4744.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2566, pruned_loss=0.06839, over 970313.32 frames.], batch size: 19, lr: 1.09e-03
2022-05-03 19:48:58,740 INFO [train.py:715] (4/8) Epoch 1, batch 1450, loss[loss=0.2572, simple_loss=0.3085, pruned_loss=0.103, over 4973.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2571, pruned_loss=0.06882, over 971734.58 frames.], batch size: 24, lr: 1.09e-03
2022-05-03 19:49:38,349 INFO [train.py:715] (4/8) Epoch 1, batch 1500, loss[loss=0.2495, simple_loss=0.2969, pruned_loss=0.101, over 4712.00 frames.], tot_loss[loss=0.1985, simple_loss=0.2582, pruned_loss=0.06938, over 971290.55 frames.], batch size: 15, lr: 1.09e-03
2022-05-03 19:50:17,873 INFO [train.py:715] (4/8) Epoch 1, batch 1550, loss[loss=0.1697, simple_loss=0.2327, pruned_loss=0.05332, over 4844.00 frames.], tot_loss[loss=0.199, simple_loss=0.2591, pruned_loss=0.06949, over 971512.45 frames.], batch size: 13, lr: 1.09e-03
2022-05-03 19:50:57,100 INFO [train.py:715] (4/8) Epoch 1, batch 1600, loss[loss=0.1876, simple_loss=0.2434, pruned_loss=0.06593, over 4959.00 frames.], tot_loss[loss=0.1981, simple_loss=0.2587, pruned_loss=0.06877, over 971698.27 frames.], batch size: 24, lr: 1.09e-03
2022-05-03 19:51:36,398 INFO [train.py:715] (4/8) Epoch 1, batch 1650, loss[loss=0.162, simple_loss=0.2204, pruned_loss=0.05185, over 4852.00 frames.], tot_loss[loss=0.198, simple_loss=0.2587, pruned_loss=0.06872, over 972312.40 frames.], batch size: 20, lr: 1.09e-03
2022-05-03 19:52:16,979 INFO [train.py:715] (4/8) Epoch 1, batch 1700, loss[loss=0.237, simple_loss=0.3067, pruned_loss=0.08368, over 4859.00 frames.], tot_loss[loss=0.1969, simple_loss=0.2577, pruned_loss=0.06801, over 971436.25 frames.], batch size: 20, lr: 1.09e-03
2022-05-03 19:52:56,158 INFO [train.py:715] (4/8) Epoch 1, batch 1750, loss[loss=0.2171, simple_loss=0.2571, pruned_loss=0.0886, over 4695.00 frames.], tot_loss[loss=0.1982, simple_loss=0.2586, pruned_loss=0.06886, over 971423.53 frames.], batch size: 15, lr: 1.09e-03
2022-05-03 19:53:35,893 INFO [train.py:715] (4/8) Epoch 1, batch 1800, loss[loss=0.1649, simple_loss=0.2396, pruned_loss=0.04513, over 4970.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2578, pruned_loss=0.06871, over 972104.95 frames.], batch size: 24, lr: 1.09e-03
2022-05-03 19:54:15,256 INFO [train.py:715] (4/8) Epoch 1, batch 1850, loss[loss=0.2094, simple_loss=0.2684, pruned_loss=0.07516, over 4798.00 frames.], tot_loss[loss=0.1986, simple_loss=0.2586, pruned_loss=0.0693, over 972137.10 frames.], batch size: 17, lr: 1.09e-03
2022-05-03 19:54:54,776 INFO [train.py:715] (4/8) Epoch 1, batch 1900, loss[loss=0.1873, simple_loss=0.2394, pruned_loss=0.06757, over 4989.00 frames.], tot_loss[loss=0.1984, simple_loss=0.2583, pruned_loss=0.06924, over 971937.32 frames.], batch size: 14, lr: 1.09e-03
2022-05-03 19:55:34,084 INFO [train.py:715] (4/8) Epoch 1, batch 1950, loss[loss=0.1865, simple_loss=0.2448, pruned_loss=0.06412, over 4930.00 frames.], tot_loss[loss=0.197, simple_loss=0.2572, pruned_loss=0.06841, over 972165.82 frames.], batch size: 29, lr: 1.08e-03
2022-05-03 19:56:14,076 INFO [train.py:715] (4/8) Epoch 1, batch 2000, loss[loss=0.1981, simple_loss=0.2524, pruned_loss=0.07192, over 4793.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2576, pruned_loss=0.06851, over 971658.52 frames.], batch size: 21, lr: 1.08e-03
2022-05-03 19:56:53,565 INFO [train.py:715] (4/8) Epoch 1, batch 2050, loss[loss=0.2879, simple_loss=0.3149, pruned_loss=0.1304, over 4862.00 frames.], tot_loss[loss=0.1977, simple_loss=0.2576, pruned_loss=0.06884, over 971378.59 frames.], batch size: 32, lr: 1.08e-03
2022-05-03 19:57:33,037 INFO [train.py:715] (4/8) Epoch 1, batch 2100, loss[loss=0.1875, simple_loss=0.2541, pruned_loss=0.06049, over 4973.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2576, pruned_loss=0.06873, over 971146.81 frames.], batch size: 28, lr: 1.08e-03
2022-05-03 19:58:12,716 INFO [train.py:715] (4/8) Epoch 1, batch 2150, loss[loss=0.2139, simple_loss=0.2773, pruned_loss=0.07527, over 4966.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2578, pruned_loss=0.0686, over 970816.87 frames.], batch size: 39, lr: 1.08e-03
2022-05-03 19:58:52,400 INFO [train.py:715] (4/8) Epoch 1, batch 2200, loss[loss=0.1758, simple_loss=0.2493, pruned_loss=0.05113, over 4890.00 frames.], tot_loss[loss=0.1975, simple_loss=0.2575, pruned_loss=0.06875, over 971277.82 frames.], batch size: 19, lr: 1.08e-03
2022-05-03 19:59:32,132 INFO [train.py:715] (4/8) Epoch 1, batch 2250, loss[loss=0.2004, simple_loss=0.2782, pruned_loss=0.06131, over 4904.00 frames.], tot_loss[loss=0.1974, simple_loss=0.2573, pruned_loss=0.06876, over 972013.73 frames.], batch size: 19, lr: 1.08e-03
2022-05-03 20:00:11,170 INFO [train.py:715] (4/8) Epoch 1, batch 2300, loss[loss=0.2135, simple_loss=0.2787, pruned_loss=0.07413, over 4811.00 frames.], tot_loss[loss=0.1976, simple_loss=0.2579, pruned_loss=0.06868, over 971884.96 frames.], batch size: 25, lr: 1.08e-03
2022-05-03 20:00:51,307 INFO [train.py:715] (4/8) Epoch 1, batch 2350, loss[loss=0.2091, simple_loss=0.2712, pruned_loss=0.07352, over 4824.00 frames.], tot_loss[loss=0.1968, simple_loss=0.2576, pruned_loss=0.06796, over 972366.30 frames.], batch size: 25, lr: 1.08e-03
2022-05-03 20:01:30,583 INFO [train.py:715] (4/8) Epoch 1, batch 2400, loss[loss=0.1702, simple_loss=0.2412, pruned_loss=0.04962, over 4993.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2569, pruned_loss=0.06737, over 972885.98 frames.], batch size: 14, lr: 1.08e-03
2022-05-03 20:02:09,729 INFO [train.py:715] (4/8) Epoch 1, batch 2450, loss[loss=0.1626, simple_loss=0.2255, pruned_loss=0.04988, over 4785.00 frames.], tot_loss[loss=0.1964, simple_loss=0.2569, pruned_loss=0.06799, over 972724.84 frames.], batch size: 14, lr: 1.08e-03
2022-05-03 20:02:48,983 INFO [train.py:715] (4/8) Epoch 1, batch 2500, loss[loss=0.2008, simple_loss=0.2498, pruned_loss=0.07589, over 4988.00 frames.], tot_loss[loss=0.1959, simple_loss=0.2565, pruned_loss=0.06771, over 972715.71 frames.], batch size: 25, lr: 1.08e-03
2022-05-03 20:03:28,531 INFO [train.py:715] (4/8) Epoch 1, batch 2550, loss[loss=0.1901, simple_loss=0.2555, pruned_loss=0.06237, over 4742.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2573, pruned_loss=0.06808, over 973476.79 frames.], batch size: 16, lr: 1.08e-03
2022-05-03 20:04:08,263 INFO [train.py:715] (4/8) Epoch 1, batch 2600, loss[loss=0.2338, simple_loss=0.2895, pruned_loss=0.08904, over 4704.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2568, pruned_loss=0.0681, over 974151.43 frames.], batch size: 15, lr: 1.08e-03
2022-05-03 20:04:47,472 INFO [train.py:715] (4/8) Epoch 1, batch 2650, loss[loss=0.2059, simple_loss=0.2702, pruned_loss=0.07087, over 4870.00 frames.], tot_loss[loss=0.1965, simple_loss=0.2567, pruned_loss=0.06817, over 974416.79 frames.], batch size: 20, lr: 1.07e-03
2022-05-03 20:05:27,539 INFO [train.py:715] (4/8) Epoch 1, batch 2700, loss[loss=0.1565, simple_loss=0.2148, pruned_loss=0.04913, over 4739.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2567, pruned_loss=0.06824, over 973976.15 frames.], batch size: 16, lr: 1.07e-03
2022-05-03 20:06:06,954 INFO [train.py:715] (4/8) Epoch 1, batch 2750, loss[loss=0.176, simple_loss=0.233, pruned_loss=0.05956, over 4689.00 frames.], tot_loss[loss=0.1973, simple_loss=0.2576, pruned_loss=0.06851, over 973566.34 frames.], batch size: 15, lr: 1.07e-03
2022-05-03 20:06:45,687 INFO [train.py:715] (4/8) Epoch 1, batch 2800, loss[loss=0.1716, simple_loss=0.2394, pruned_loss=0.05193, over 4840.00 frames.], tot_loss[loss=0.198, simple_loss=0.258, pruned_loss=0.06898, over 973296.67 frames.], batch size: 15, lr: 1.07e-03
2022-05-03 20:07:25,350 INFO [train.py:715] (4/8) Epoch 1, batch 2850, loss[loss=0.1658, simple_loss=0.2294, pruned_loss=0.05114, over 4933.00 frames.], tot_loss[loss=0.197, simple_loss=0.2573, pruned_loss=0.06836, over 973478.09 frames.], batch size: 18, lr: 1.07e-03
2022-05-03 20:08:05,006 INFO [train.py:715] (4/8) Epoch 1, batch 2900, loss[loss=0.1694, simple_loss=0.2379, pruned_loss=0.05045, over 4750.00 frames.], tot_loss[loss=0.196, simple_loss=0.2567, pruned_loss=0.06761, over 973388.76 frames.], batch size: 19, lr: 1.07e-03
2022-05-03 20:08:44,123 INFO [train.py:715] (4/8) Epoch 1, batch 2950, loss[loss=0.1779, simple_loss=0.247, pruned_loss=0.05442, over 4967.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2562, pruned_loss=0.06753, over 973609.66 frames.], batch size: 21, lr: 1.07e-03
2022-05-03 20:09:22,832 INFO [train.py:715] (4/8) Epoch 1, batch 3000, loss[loss=0.1531, simple_loss=0.2151, pruned_loss=0.04557, over 4765.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2558, pruned_loss=0.0669, over 973648.38 frames.], batch size: 12, lr: 1.07e-03
2022-05-03 20:09:22,832 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 20:09:34,564 INFO [train.py:742] (4/8) Epoch 1, validation: loss=0.1276, simple_loss=0.2149, pruned_loss=0.0201, over 914524.00 frames.
2022-05-03 20:10:13,439 INFO [train.py:715] (4/8) Epoch 1, batch 3050, loss[loss=0.1674, simple_loss=0.2334, pruned_loss=0.0507, over 4811.00 frames.], tot_loss[loss=0.1948, simple_loss=0.2561, pruned_loss=0.06679, over 973502.37 frames.], batch size: 13, lr: 1.07e-03
2022-05-03 20:10:53,453 INFO [train.py:715] (4/8) Epoch 1, batch 3100, loss[loss=0.1718, simple_loss=0.2211, pruned_loss=0.06123, over 4982.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2562, pruned_loss=0.06768, over 973052.00 frames.], batch size: 14, lr: 1.07e-03
2022-05-03 20:11:32,597 INFO [train.py:715] (4/8) Epoch 1, batch 3150, loss[loss=0.2423, simple_loss=0.2857, pruned_loss=0.09948, over 4766.00 frames.], tot_loss[loss=0.1953, simple_loss=0.256, pruned_loss=0.06733, over 972868.15 frames.], batch size: 19, lr: 1.07e-03
2022-05-03 20:12:11,816 INFO [train.py:715] (4/8) Epoch 1, batch 3200, loss[loss=0.2109, simple_loss=0.2606, pruned_loss=0.0806, over 4850.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2562, pruned_loss=0.06735, over 973108.90 frames.], batch size: 32, lr: 1.07e-03
2022-05-03 20:12:51,454 INFO [train.py:715] (4/8) Epoch 1, batch 3250, loss[loss=0.2196, simple_loss=0.2768, pruned_loss=0.08117, over 4983.00 frames.], tot_loss[loss=0.1966, simple_loss=0.2574, pruned_loss=0.06796, over 973123.83 frames.], batch size: 31, lr: 1.07e-03
2022-05-03 20:13:31,211 INFO [train.py:715] (4/8) Epoch 1, batch 3300, loss[loss=0.1717, simple_loss=0.2251, pruned_loss=0.05915, over 4804.00 frames.], tot_loss[loss=0.1967, simple_loss=0.2575, pruned_loss=0.06797, over 973018.59 frames.], batch size: 12, lr: 1.07e-03
2022-05-03 20:14:10,766 INFO [train.py:715] (4/8) Epoch 1, batch 3350, loss[loss=0.1776, simple_loss=0.2385, pruned_loss=0.05841, over 4961.00 frames.], tot_loss[loss=0.196, simple_loss=0.2569, pruned_loss=0.0675, over 973759.15 frames.], batch size: 35, lr: 1.07e-03
2022-05-03 20:14:50,046 INFO [train.py:715] (4/8) Epoch 1, batch 3400, loss[loss=0.1895, simple_loss=0.2491, pruned_loss=0.06492, over 4805.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2557, pruned_loss=0.06618, over 974256.62 frames.], batch size: 21, lr: 1.06e-03
2022-05-03 20:15:30,666 INFO [train.py:715] (4/8) Epoch 1, batch 3450, loss[loss=0.1549, simple_loss=0.2186, pruned_loss=0.04559, over 4926.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2564, pruned_loss=0.06676, over 974861.41 frames.], batch size: 23, lr: 1.06e-03
2022-05-03 20:16:09,590 INFO [train.py:715] (4/8) Epoch 1, batch 3500, loss[loss=0.1765, simple_loss=0.2411, pruned_loss=0.05599, over 4674.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2558, pruned_loss=0.06653, over 973494.93 frames.], batch size: 14, lr: 1.06e-03
2022-05-03 20:16:48,616 INFO [train.py:715] (4/8) Epoch 1, batch 3550, loss[loss=0.1763, simple_loss=0.2408, pruned_loss=0.05589, over 4988.00 frames.], tot_loss[loss=0.1948, simple_loss=0.256, pruned_loss=0.06678, over 973723.88 frames.], batch size: 20, lr: 1.06e-03
2022-05-03 20:17:28,373 INFO [train.py:715] (4/8) Epoch 1, batch 3600, loss[loss=0.193, simple_loss=0.2543, pruned_loss=0.06584, over 4705.00 frames.], tot_loss[loss=0.192, simple_loss=0.2535, pruned_loss=0.06528, over 972468.49 frames.], batch size: 15, lr: 1.06e-03
2022-05-03 20:18:08,020 INFO [train.py:715] (4/8) Epoch 1, batch 3650, loss[loss=0.1499, simple_loss=0.2199, pruned_loss=0.03999, over 4982.00 frames.], tot_loss[loss=0.192, simple_loss=0.2533, pruned_loss=0.06529, over 972613.88 frames.], batch size: 14, lr: 1.06e-03
2022-05-03 20:18:46,983 INFO [train.py:715] (4/8) Epoch 1, batch 3700, loss[loss=0.1674, simple_loss=0.2411, pruned_loss=0.04685, over 4955.00 frames.], tot_loss[loss=0.1929, simple_loss=0.254, pruned_loss=0.06592, over 971860.28 frames.], batch size: 29, lr: 1.06e-03
2022-05-03 20:19:25,659 INFO [train.py:715] (4/8) Epoch 1, batch 3750, loss[loss=0.1711, simple_loss=0.2455, pruned_loss=0.0483, over 4799.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2538, pruned_loss=0.066, over 971663.81 frames.], batch size: 21, lr: 1.06e-03
2022-05-03 20:20:05,931 INFO [train.py:715] (4/8) Epoch 1, batch 3800, loss[loss=0.1547, simple_loss=0.2201, pruned_loss=0.04461, over 4814.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2533, pruned_loss=0.06559, over 970806.00 frames.], batch size: 21, lr: 1.06e-03
2022-05-03 20:20:44,900 INFO [train.py:715] (4/8) Epoch 1, batch 3850, loss[loss=0.1667, simple_loss=0.2296, pruned_loss=0.05189, over 4836.00 frames.], tot_loss[loss=0.1927, simple_loss=0.2539, pruned_loss=0.06577, over 970200.32 frames.], batch size: 13, lr: 1.06e-03
2022-05-03 20:21:23,755 INFO [train.py:715] (4/8) Epoch 1, batch 3900, loss[loss=0.2501, simple_loss=0.3066, pruned_loss=0.09678, over 4830.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2538, pruned_loss=0.0653, over 970669.08 frames.], batch size: 13, lr: 1.06e-03
2022-05-03 20:22:03,281 INFO [train.py:715] (4/8) Epoch 1, batch 3950, loss[loss=0.1727, simple_loss=0.2359, pruned_loss=0.05477, over 4828.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2541, pruned_loss=0.06617, over 971077.07 frames.], batch size: 27, lr: 1.06e-03
2022-05-03 20:22:42,793 INFO [train.py:715] (4/8) Epoch 1, batch 4000, loss[loss=0.1591, simple_loss=0.2316, pruned_loss=0.04327, over 4923.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2542, pruned_loss=0.06552, over 971453.08 frames.], batch size: 18, lr: 1.06e-03
2022-05-03 20:23:21,454 INFO [train.py:715] (4/8) Epoch 1, batch 4050, loss[loss=0.3351, simple_loss=0.385, pruned_loss=0.1426, over 4894.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2546, pruned_loss=0.06575, over 971171.63 frames.], batch size: 17, lr: 1.06e-03
2022-05-03 20:24:00,882 INFO [train.py:715] (4/8) Epoch 1, batch 4100, loss[loss=0.152, simple_loss=0.2244, pruned_loss=0.03979, over 4701.00 frames.], tot_loss[loss=0.1951, simple_loss=0.2559, pruned_loss=0.0671, over 971006.17 frames.], batch size: 15, lr: 1.05e-03
2022-05-03 20:24:40,532 INFO [train.py:715] (4/8) Epoch 1, batch 4150, loss[loss=0.1758, simple_loss=0.2373, pruned_loss=0.05711, over 4772.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2557, pruned_loss=0.06674, over 971730.46 frames.], batch size: 17, lr: 1.05e-03
2022-05-03 20:25:19,582 INFO [train.py:715] (4/8) Epoch 1, batch 4200, loss[loss=0.2184, simple_loss=0.259, pruned_loss=0.08884, over 4944.00 frames.], tot_loss[loss=0.1939, simple_loss=0.2548, pruned_loss=0.06649, over 971793.28 frames.], batch size: 14, lr: 1.05e-03
2022-05-03 20:25:58,622 INFO [train.py:715] (4/8) Epoch 1, batch 4250, loss[loss=0.193, simple_loss=0.252, pruned_loss=0.06697, over 4973.00 frames.], tot_loss[loss=0.1943, simple_loss=0.255, pruned_loss=0.06679, over 971407.96 frames.], batch size: 28, lr: 1.05e-03
2022-05-03 20:26:38,138 INFO [train.py:715] (4/8) Epoch 1, batch 4300, loss[loss=0.1664, simple_loss=0.2307, pruned_loss=0.05101, over 4954.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2553, pruned_loss=0.06675, over 971941.40 frames.], batch size: 21, lr: 1.05e-03
2022-05-03 20:27:17,802 INFO [train.py:715] (4/8) Epoch 1, batch 4350, loss[loss=0.1711, simple_loss=0.2357, pruned_loss=0.05326, over 4836.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2551, pruned_loss=0.06651, over 972862.79 frames.], batch size: 26, lr: 1.05e-03
2022-05-03 20:27:56,250 INFO [train.py:715] (4/8) Epoch 1, batch 4400, loss[loss=0.2043, simple_loss=0.2628, pruned_loss=0.07287, over 4940.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2554, pruned_loss=0.06663, over 972146.73 frames.], batch size: 24, lr: 1.05e-03
2022-05-03 20:28:35,843 INFO [train.py:715] (4/8) Epoch 1, batch 4450, loss[loss=0.2006, simple_loss=0.261, pruned_loss=0.07006, over 4852.00 frames.], tot_loss[loss=0.1946, simple_loss=0.2554, pruned_loss=0.06692, over 971572.04 frames.], batch size: 20, lr: 1.05e-03
2022-05-03 20:29:15,593 INFO [train.py:715] (4/8) Epoch 1, batch 4500, loss[loss=0.2059, simple_loss=0.271, pruned_loss=0.07039, over 4934.00 frames.], tot_loss[loss=0.1955, simple_loss=0.2566, pruned_loss=0.06723, over 971842.36 frames.], batch size: 23, lr: 1.05e-03
2022-05-03 20:29:54,816 INFO [train.py:715] (4/8) Epoch 1, batch 4550, loss[loss=0.2026, simple_loss=0.2585, pruned_loss=0.07335, over 4875.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2556, pruned_loss=0.06627, over 971867.20 frames.], batch size: 32, lr: 1.05e-03
2022-05-03 20:30:33,518 INFO [train.py:715] (4/8) Epoch 1, batch 4600, loss[loss=0.2167, simple_loss=0.2646, pruned_loss=0.08446, over 4774.00 frames.], tot_loss[loss=0.1943, simple_loss=0.2559, pruned_loss=0.06635, over 971433.45 frames.], batch size: 14, lr: 1.05e-03
2022-05-03 20:31:13,057 INFO [train.py:715] (4/8) Epoch 1, batch 4650, loss[loss=0.2261, simple_loss=0.2771, pruned_loss=0.08756, over 4871.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2564, pruned_loss=0.0667, over 971133.14 frames.], batch size: 32, lr: 1.05e-03
2022-05-03 20:31:52,506 INFO [train.py:715] (4/8) Epoch 1, batch 4700, loss[loss=0.1535, simple_loss=0.2334, pruned_loss=0.0368, over 4849.00 frames.], tot_loss[loss=0.194, simple_loss=0.2553, pruned_loss=0.06636, over 970974.84 frames.], batch size: 13, lr: 1.05e-03
2022-05-03 20:32:31,320 INFO [train.py:715] (4/8) Epoch 1, batch 4750, loss[loss=0.1768, simple_loss=0.2418, pruned_loss=0.0559, over 4897.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2552, pruned_loss=0.06623, over 971560.62 frames.], batch size: 29, lr: 1.05e-03
2022-05-03 20:33:11,342 INFO [train.py:715] (4/8) Epoch 1, batch 4800, loss[loss=0.1576, simple_loss=0.224, pruned_loss=0.04557, over 4918.00 frames.], tot_loss[loss=0.1946, simple_loss=0.256, pruned_loss=0.06664, over 972506.97 frames.], batch size: 18, lr: 1.05e-03
2022-05-03 20:33:51,185 INFO [train.py:715] (4/8) Epoch 1, batch 4850, loss[loss=0.2172, simple_loss=0.2789, pruned_loss=0.07778, over 4947.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2545, pruned_loss=0.06609, over 971913.41 frames.], batch size: 24, lr: 1.05e-03
2022-05-03 20:34:30,464 INFO [train.py:715] (4/8) Epoch 1, batch 4900, loss[loss=0.1615, simple_loss=0.2321, pruned_loss=0.04541, over 4909.00 frames.], tot_loss[loss=0.1934, simple_loss=0.2545, pruned_loss=0.06617, over 972728.37 frames.], batch size: 23, lr: 1.04e-03
2022-05-03 20:35:09,823 INFO [train.py:715] (4/8) Epoch 1, batch 4950, loss[loss=0.2332, simple_loss=0.2921, pruned_loss=0.08717, over 4951.00 frames.], tot_loss[loss=0.1957, simple_loss=0.2565, pruned_loss=0.0675, over 972981.16 frames.], batch size: 39, lr: 1.04e-03
2022-05-03 20:35:50,159 INFO [train.py:715] (4/8) Epoch 1, batch 5000, loss[loss=0.1869, simple_loss=0.2481, pruned_loss=0.06283, over 4935.00 frames.], tot_loss[loss=0.1956, simple_loss=0.2566, pruned_loss=0.06725, over 972660.42 frames.], batch size: 23, lr: 1.04e-03
2022-05-03 20:36:29,717 INFO [train.py:715] (4/8) Epoch 1, batch 5050, loss[loss=0.2501, simple_loss=0.3059, pruned_loss=0.09716, over 4739.00 frames.], tot_loss[loss=0.1958, simple_loss=0.2568, pruned_loss=0.06733, over 973133.19 frames.], batch size: 16, lr: 1.04e-03
2022-05-03 20:37:08,715 INFO [train.py:715] (4/8) Epoch 1, batch 5100, loss[loss=0.1913, simple_loss=0.2585, pruned_loss=0.06202, over 4864.00 frames.], tot_loss[loss=0.1949, simple_loss=0.2564, pruned_loss=0.06666, over 973216.03 frames.], batch size: 38, lr: 1.04e-03
2022-05-03 20:37:48,747 INFO [train.py:715] (4/8) Epoch 1, batch 5150, loss[loss=0.1534, simple_loss=0.2118, pruned_loss=0.04752, over 4802.00 frames.], tot_loss[loss=0.1936, simple_loss=0.2554, pruned_loss=0.06595, over 972839.75 frames.], batch size: 12, lr: 1.04e-03
2022-05-03 20:38:30,128 INFO [train.py:715] (4/8) Epoch 1, batch 5200, loss[loss=0.2202, simple_loss=0.2776, pruned_loss=0.08144, over 4989.00 frames.], tot_loss[loss=0.1938, simple_loss=0.2553, pruned_loss=0.06619, over 973160.67 frames.], batch size: 20, lr: 1.04e-03
2022-05-03 20:39:09,104 INFO [train.py:715] (4/8) Epoch 1, batch 5250, loss[loss=0.2108, simple_loss=0.2704, pruned_loss=0.07559, over 4956.00 frames.], tot_loss[loss=0.1935, simple_loss=0.2556, pruned_loss=0.06576, over 973562.33 frames.], batch size: 39, lr: 1.04e-03
2022-05-03 20:39:48,467 INFO [train.py:715] (4/8) Epoch 1, batch 5300, loss[loss=0.2223, simple_loss=0.2899, pruned_loss=0.07735, over 4952.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2557, pruned_loss=0.06624, over 973449.32 frames.], batch size: 15, lr: 1.04e-03
2022-05-03 20:40:28,102 INFO [train.py:715] (4/8) Epoch 1, batch 5350, loss[loss=0.2016, simple_loss=0.2582, pruned_loss=0.0725, over 4858.00 frames.], tot_loss[loss=0.1929, simple_loss=0.2548, pruned_loss=0.06548, over 973650.17 frames.], batch size: 30, lr: 1.04e-03
2022-05-03 20:41:07,643 INFO [train.py:715] (4/8) Epoch 1, batch 5400, loss[loss=0.1841, simple_loss=0.2448, pruned_loss=0.06166, over 4701.00 frames.], tot_loss[loss=0.1924, simple_loss=0.254, pruned_loss=0.0654, over 972627.13 frames.], batch size: 15, lr: 1.04e-03
2022-05-03 20:41:46,694 INFO [train.py:715] (4/8) Epoch 1, batch 5450, loss[loss=0.1809, simple_loss=0.2437, pruned_loss=0.05905, over 4829.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2534, pruned_loss=0.06496, over 972418.83 frames.], batch size: 15, lr: 1.04e-03
2022-05-03 20:42:26,574 INFO [train.py:715] (4/8) Epoch 1, batch 5500, loss[loss=0.1706, simple_loss=0.246, pruned_loss=0.04766, over 4782.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2547, pruned_loss=0.06529, over 972773.99 frames.], batch size: 18, lr: 1.04e-03
2022-05-03 20:43:06,477 INFO [train.py:715] (4/8) Epoch 1, batch 5550, loss[loss=0.1772, simple_loss=0.2435, pruned_loss=0.05548, over 4828.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2541, pruned_loss=0.06517, over 972560.21 frames.], batch size: 15, lr: 1.04e-03
2022-05-03 20:43:45,489 INFO [train.py:715] (4/8) Epoch 1, batch 5600, loss[loss=0.192, simple_loss=0.2674, pruned_loss=0.0583, over 4778.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2537, pruned_loss=0.06499, over 971170.09 frames.], batch size: 17, lr: 1.04e-03
2022-05-03 20:44:24,783 INFO [train.py:715] (4/8) Epoch 1, batch 5650, loss[loss=0.19, simple_loss=0.2372, pruned_loss=0.07138, over 4849.00 frames.], tot_loss[loss=0.1923, simple_loss=0.254, pruned_loss=0.06524, over 972597.75 frames.], batch size: 32, lr: 1.03e-03
2022-05-03 20:45:04,549 INFO [train.py:715] (4/8) Epoch 1, batch 5700, loss[loss=0.1955, simple_loss=0.2475, pruned_loss=0.07175, over 4982.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2536, pruned_loss=0.06474, over 972368.70 frames.], batch size: 35, lr: 1.03e-03
2022-05-03 20:45:44,078 INFO [train.py:715] (4/8) Epoch 1, batch 5750, loss[loss=0.1594, simple_loss=0.2161, pruned_loss=0.05136, over 4771.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2528, pruned_loss=0.06385, over 973208.88 frames.], batch size: 18, lr: 1.03e-03
2022-05-03 20:46:23,088 INFO [train.py:715] (4/8) Epoch 1, batch 5800, loss[loss=0.1922, simple_loss=0.2587, pruned_loss=0.06278, over 4969.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2519, pruned_loss=0.06292, over 972930.82 frames.], batch size: 39, lr: 1.03e-03
2022-05-03 20:47:03,044 INFO [train.py:715] (4/8) Epoch 1, batch 5850, loss[loss=0.1708, simple_loss=0.2396, pruned_loss=0.051, over 4949.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2521, pruned_loss=0.06357, over 972671.32 frames.], batch size: 21, lr: 1.03e-03
2022-05-03 20:47:42,849 INFO [train.py:715] (4/8) Epoch 1, batch 5900, loss[loss=0.1851, simple_loss=0.2375, pruned_loss=0.06636, over 4897.00 frames.], tot_loss[loss=0.1894, simple_loss=0.252, pruned_loss=0.06339, over 973352.81 frames.], batch size: 19, lr: 1.03e-03
2022-05-03 20:48:21,954 INFO [train.py:715] (4/8) Epoch 1, batch 5950, loss[loss=0.2007, simple_loss=0.2543, pruned_loss=0.07357, over 4949.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2525, pruned_loss=0.06385, over 973483.78 frames.], batch size: 21, lr: 1.03e-03
2022-05-03 20:49:01,787 INFO [train.py:715] (4/8) Epoch 1, batch 6000, loss[loss=0.1878, simple_loss=0.2541, pruned_loss=0.06079, over 4985.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2516, pruned_loss=0.06301, over 973059.37 frames.], batch size: 28, lr: 1.03e-03
2022-05-03 20:49:01,787 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 20:49:14,257 INFO [train.py:742] (4/8) Epoch 1, validation: loss=0.1267, simple_loss=0.2135, pruned_loss=0.01993, over 914524.00 frames.
2022-05-03 20:49:53,682 INFO [train.py:715] (4/8) Epoch 1, batch 6050, loss[loss=0.2035, simple_loss=0.2548, pruned_loss=0.07609, over 4889.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2517, pruned_loss=0.0633, over 974134.69 frames.], batch size: 22, lr: 1.03e-03
2022-05-03 20:50:33,748 INFO [train.py:715] (4/8) Epoch 1, batch 6100, loss[loss=0.1624, simple_loss=0.2299, pruned_loss=0.04744, over 4785.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2507, pruned_loss=0.06305, over 973703.33 frames.], batch size: 12, lr: 1.03e-03
2022-05-03 20:51:13,274 INFO [train.py:715] (4/8) Epoch 1, batch 6150, loss[loss=0.1669, simple_loss=0.2313, pruned_loss=0.05127, over 4740.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2525, pruned_loss=0.06434, over 972608.57 frames.], batch size: 12, lr: 1.03e-03
2022-05-03 20:51:51,973 INFO [train.py:715] (4/8) Epoch 1, batch 6200, loss[loss=0.1729, simple_loss=0.2255, pruned_loss=0.06014, over 4788.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2529, pruned_loss=0.06475, over 972976.09 frames.], batch size: 14, lr: 1.03e-03
2022-05-03 20:52:32,161 INFO [train.py:715] (4/8) Epoch 1, batch 6250, loss[loss=0.2016, simple_loss=0.2571, pruned_loss=0.07303, over 4790.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2534, pruned_loss=0.06518, over 972633.33 frames.], batch size: 12, lr: 1.03e-03
2022-05-03 20:53:11,875 INFO [train.py:715] (4/8) Epoch 1, batch 6300, loss[loss=0.174, simple_loss=0.2344, pruned_loss=0.05677, over 4818.00 frames.], tot_loss[loss=0.192, simple_loss=0.2534, pruned_loss=0.06529, over 972423.85 frames.], batch size: 13, lr: 1.03e-03
2022-05-03 20:53:51,072 INFO [train.py:715] (4/8) Epoch 1, batch 6350, loss[loss=0.2038, simple_loss=0.2642, pruned_loss=0.07175, over 4937.00 frames.], tot_loss[loss=0.193, simple_loss=0.2542, pruned_loss=0.06589, over 972441.26 frames.], batch size: 39, lr: 1.03e-03
2022-05-03 20:54:30,388 INFO [train.py:715] (4/8) Epoch 1, batch 6400, loss[loss=0.1366, simple_loss=0.2095, pruned_loss=0.03181, over 4806.00 frames.], tot_loss[loss=0.191, simple_loss=0.2524, pruned_loss=0.06474, over 972146.93 frames.], batch size: 12, lr: 1.03e-03
2022-05-03 20:55:09,939 INFO [train.py:715] (4/8) Epoch 1, batch 6450, loss[loss=0.2156, simple_loss=0.2709, pruned_loss=0.08015, over 4905.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2522, pruned_loss=0.06499, over 971162.16 frames.], batch size: 39, lr: 1.02e-03
2022-05-03 20:55:49,579 INFO [train.py:715] (4/8) Epoch 1, batch 6500, loss[loss=0.1848, simple_loss=0.2352, pruned_loss=0.06719, over 4902.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2531, pruned_loss=0.06534, over 971130.40 frames.], batch size: 17, lr: 1.02e-03
2022-05-03 20:56:28,199 INFO [train.py:715] (4/8) Epoch 1, batch 6550, loss[loss=0.188, simple_loss=0.2499, pruned_loss=0.06301, over 4765.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2526, pruned_loss=0.06508, over 970855.15 frames.], batch size: 16, lr: 1.02e-03
2022-05-03 20:57:08,075 INFO [train.py:715] (4/8) Epoch 1, batch 6600, loss[loss=0.1784, simple_loss=0.2437, pruned_loss=0.05654, over 4912.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2524, pruned_loss=0.06459, over 970328.91 frames.], batch size: 18, lr: 1.02e-03
2022-05-03 20:57:48,547 INFO [train.py:715] (4/8) Epoch 1, batch 6650, loss[loss=0.1659, simple_loss=0.2264, pruned_loss=0.05264, over 4796.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2533, pruned_loss=0.06523, over 970772.62 frames.], batch size: 17, lr: 1.02e-03
2022-05-03 20:58:28,003 INFO [train.py:715] (4/8) Epoch 1, batch 6700, loss[loss=0.2465, simple_loss=0.2936, pruned_loss=0.09972, over 4902.00 frames.], tot_loss[loss=0.1922, simple_loss=0.2537, pruned_loss=0.0654, over 971063.12 frames.], batch size: 17, lr: 1.02e-03
2022-05-03 20:59:07,321 INFO [train.py:715] (4/8) Epoch 1, batch 6750, loss[loss=0.2211, simple_loss=0.2818, pruned_loss=0.08019, over 4924.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2545, pruned_loss=0.06539, over 971250.68 frames.], batch size: 17, lr: 1.02e-03
2022-05-03 20:59:47,254 INFO [train.py:715] (4/8) Epoch 1, batch 6800, loss[loss=0.1855, simple_loss=0.2524, pruned_loss=0.05929, over 4766.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2547, pruned_loss=0.06574, over 971928.72 frames.], batch size: 17, lr: 1.02e-03
2022-05-03 21:00:26,798 INFO [train.py:715] (4/8) Epoch 1, batch 6850, loss[loss=0.2038, simple_loss=0.26, pruned_loss=0.07381, over 4785.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2544, pruned_loss=0.06526, over 972122.29 frames.], batch size: 17, lr: 1.02e-03
2022-05-03 21:01:05,422 INFO [train.py:715] (4/8) Epoch 1, batch 6900, loss[loss=0.1919, simple_loss=0.2556, pruned_loss=0.06417, over 4834.00 frames.], tot_loss[loss=0.1935, simple_loss=0.255, pruned_loss=0.06598, over 972568.31 frames.], batch size: 13, lr: 1.02e-03
2022-05-03 21:01:44,713 INFO [train.py:715] (4/8) Epoch 1, batch 6950, loss[loss=0.2018, simple_loss=0.2566, pruned_loss=0.07354, over 4886.00 frames.], tot_loss[loss=0.1933, simple_loss=0.2552, pruned_loss=0.06573, over 972399.04 frames.], batch size: 22, lr: 1.02e-03
2022-05-03 21:02:24,793 INFO [train.py:715] (4/8) Epoch 1, batch 7000, loss[loss=0.179, simple_loss=0.2418, pruned_loss=0.05813, over 4831.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2542, pruned_loss=0.06531, over 972757.93 frames.], batch size: 15, lr: 1.02e-03
2022-05-03 21:03:03,639 INFO [train.py:715] (4/8) Epoch 1, batch 7050, loss[loss=0.164, simple_loss=0.2312, pruned_loss=0.04847, over 4773.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2537, pruned_loss=0.0651, over 971792.46 frames.], batch size: 18, lr: 1.02e-03
2022-05-03 21:03:42,606 INFO [train.py:715] (4/8) Epoch 1, batch 7100, loss[loss=0.2329, simple_loss=0.2804, pruned_loss=0.09266, over 4969.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2545, pruned_loss=0.06584, over 972435.87 frames.], batch size: 24, lr: 1.02e-03
2022-05-03 21:04:22,594 INFO [train.py:715] (4/8) Epoch 1, batch 7150, loss[loss=0.1943, simple_loss=0.249, pruned_loss=0.06977, over 4926.00 frames.], tot_loss[loss=0.1941, simple_loss=0.2554, pruned_loss=0.06643, over 972251.88 frames.], batch size: 39, lr: 1.02e-03
2022-05-03 21:05:02,513 INFO [train.py:715] (4/8) Epoch 1, batch 7200, loss[loss=0.1845, simple_loss=0.2427, pruned_loss=0.06319, over 4849.00 frames.], tot_loss[loss=0.194, simple_loss=0.2547, pruned_loss=0.06662, over 971877.09 frames.], batch size: 30, lr: 1.02e-03
2022-05-03 21:05:41,154 INFO [train.py:715] (4/8) Epoch 1, batch 7250, loss[loss=0.1888, simple_loss=0.2538, pruned_loss=0.06187, over 4881.00 frames.], tot_loss[loss=0.1944, simple_loss=0.2552, pruned_loss=0.0668, over 972429.10 frames.], batch size: 20, lr: 1.02e-03
2022-05-03 21:06:21,084 INFO [train.py:715] (4/8) Epoch 1, batch 7300, loss[loss=0.2247, simple_loss=0.2749, pruned_loss=0.08727, over 4941.00 frames.], tot_loss[loss=0.194, simple_loss=0.2553, pruned_loss=0.06636, over 971925.05 frames.], batch size: 21, lr: 1.01e-03
2022-05-03 21:07:00,828 INFO [train.py:715] (4/8) Epoch 1, batch 7350, loss[loss=0.2167, simple_loss=0.2671, pruned_loss=0.08315, over 4985.00 frames.], tot_loss[loss=0.193, simple_loss=0.254, pruned_loss=0.06602, over 972059.44 frames.], batch size: 35, lr: 1.01e-03
2022-05-03 21:07:39,614 INFO [train.py:715] (4/8) Epoch 1, batch 7400, loss[loss=0.1584, simple_loss=0.2284, pruned_loss=0.04422, over 4951.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2536, pruned_loss=0.06564, over 972615.76 frames.], batch size: 29, lr: 1.01e-03
2022-05-03 21:08:18,529 INFO [train.py:715] (4/8) Epoch 1, batch 7450, loss[loss=0.1909, simple_loss=0.2565, pruned_loss=0.06268, over 4767.00 frames.], tot_loss[loss=0.193, simple_loss=0.2547, pruned_loss=0.06564, over 972702.22 frames.], batch size: 19, lr: 1.01e-03
2022-05-03 21:08:58,342 INFO [train.py:715] (4/8) Epoch 1, batch 7500, loss[loss=0.1626, simple_loss=0.2255, pruned_loss=0.04987, over 4748.00 frames.], tot_loss[loss=0.1932, simple_loss=0.2547, pruned_loss=0.06586, over 972064.57 frames.], batch size: 19, lr: 1.01e-03
2022-05-03 21:09:38,022 INFO [train.py:715] (4/8) Epoch 1, batch 7550, loss[loss=0.1683, simple_loss=0.2303, pruned_loss=0.05318, over 4832.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2536, pruned_loss=0.06453, over 972133.44 frames.], batch size: 13, lr: 1.01e-03
2022-05-03 21:10:16,231 INFO [train.py:715] (4/8) Epoch 1, batch 7600, loss[loss=0.2076, simple_loss=0.2654, pruned_loss=0.07484, over 4952.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2532, pruned_loss=0.06423, over 972279.59 frames.], batch size: 24, lr: 1.01e-03
2022-05-03 21:10:55,969 INFO [train.py:715] (4/8) Epoch 1, batch 7650, loss[loss=0.1855, simple_loss=0.2422, pruned_loss=0.06444, over 4929.00 frames.], tot_loss[loss=0.192, simple_loss=0.2542, pruned_loss=0.06493, over 971862.91 frames.], batch size: 23, lr: 1.01e-03
2022-05-03 21:11:35,787 INFO [train.py:715] (4/8) Epoch 1, batch 7700, loss[loss=0.1843, simple_loss=0.2379, pruned_loss=0.06534, over 4767.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2527, pruned_loss=0.06399, over 971759.20 frames.], batch size: 18, lr: 1.01e-03
2022-05-03 21:12:14,131 INFO [train.py:715] (4/8) Epoch 1, batch 7750, loss[loss=0.1591, simple_loss=0.2224, pruned_loss=0.04783, over 4895.00 frames.], tot_loss[loss=0.1907, simple_loss=0.2529, pruned_loss=0.06431, over 972051.59 frames.], batch size: 17, lr: 1.01e-03
2022-05-03 21:12:53,240 INFO [train.py:715] (4/8) Epoch 1, batch 7800, loss[loss=0.1633, simple_loss=0.2324, pruned_loss=0.0471, over 4834.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2532, pruned_loss=0.06496, over 971949.56 frames.], batch size: 13, lr: 1.01e-03
2022-05-03 21:13:33,312 INFO [train.py:715] (4/8) Epoch 1, batch 7850, loss[loss=0.2221, simple_loss=0.2725, pruned_loss=0.08585, over 4845.00 frames.], tot_loss[loss=0.191, simple_loss=0.2528, pruned_loss=0.06457, over 971514.59 frames.], batch size: 15, lr: 1.01e-03
2022-05-03 21:14:12,714 INFO [train.py:715] (4/8) Epoch 1, batch 7900, loss[loss=0.1502, simple_loss=0.2129, pruned_loss=0.04377, over 4779.00 frames.], tot_loss[loss=0.1903, simple_loss=0.2523, pruned_loss=0.06422, over 971606.47 frames.], batch size: 12, lr: 1.01e-03
2022-05-03 21:14:51,152 INFO [train.py:715] (4/8) Epoch 1, batch 7950, loss[loss=0.1744, simple_loss=0.2419, pruned_loss=0.05341, over 4907.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2524, pruned_loss=0.06428, over 971533.18 frames.], batch size: 17, lr: 1.01e-03
2022-05-03 21:15:31,263 INFO [train.py:715] (4/8) Epoch 1, batch 8000, loss[loss=0.1427, simple_loss=0.2144, pruned_loss=0.03549, over 4933.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2529, pruned_loss=0.0647, over 971630.87 frames.], batch size: 21, lr: 1.01e-03
2022-05-03 21:16:11,048 INFO [train.py:715] (4/8) Epoch 1, batch 8050, loss[loss=0.1732, simple_loss=0.2311, pruned_loss=0.05764, over 4798.00 frames.], tot_loss[loss=0.1916, simple_loss=0.2533, pruned_loss=0.06493, over 971640.71 frames.], batch size: 14, lr: 1.01e-03
2022-05-03 21:16:50,422 INFO [train.py:715] (4/8) Epoch 1, batch 8100, loss[loss=0.2244, simple_loss=0.2679, pruned_loss=0.09042, over 4835.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2536, pruned_loss=0.06488, over 971518.99 frames.], batch size: 30, lr: 1.01e-03
2022-05-03 21:17:28,623 INFO [train.py:715] (4/8) Epoch 1, batch 8150, loss[loss=0.229, simple_loss=0.2837, pruned_loss=0.08718, over 4981.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2537, pruned_loss=0.06506, over 970600.96 frames.], batch size: 24, lr: 1.00e-03
2022-05-03 21:18:08,542 INFO [train.py:715] (4/8) Epoch 1, batch 8200, loss[loss=0.2194, simple_loss=0.2702, pruned_loss=0.08431, over 4780.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2548, pruned_loss=0.06567, over 971392.12 frames.], batch size: 18, lr: 1.00e-03
2022-05-03 21:18:48,018 INFO [train.py:715] (4/8) Epoch 1, batch 8250, loss[loss=0.1685, simple_loss=0.2456, pruned_loss=0.0457, over 4739.00 frames.], tot_loss[loss=0.193, simple_loss=0.2547, pruned_loss=0.06565, over 970356.09 frames.], batch size: 16, lr: 1.00e-03
2022-05-03 21:19:26,203 INFO [train.py:715] (4/8) Epoch 1, batch 8300, loss[loss=0.1724, simple_loss=0.2365, pruned_loss=0.05412, over 4844.00 frames.], tot_loss[loss=0.192, simple_loss=0.2539, pruned_loss=0.06503, over 970703.12 frames.], batch size: 15, lr: 1.00e-03
2022-05-03 21:20:06,143 INFO [train.py:715] (4/8) Epoch 1, batch 8350, loss[loss=0.1645, simple_loss=0.2288, pruned_loss=0.05014, over 4858.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2531, pruned_loss=0.06451, over 971049.18 frames.], batch size: 20, lr: 1.00e-03
2022-05-03 21:20:45,727 INFO [train.py:715] (4/8) Epoch 1, batch 8400, loss[loss=0.1848, simple_loss=0.2391, pruned_loss=0.0653, over 4968.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2546, pruned_loss=0.06534, over 971097.35 frames.], batch size: 15, lr: 1.00e-03
2022-05-03 21:21:25,101 INFO [train.py:715] (4/8) Epoch 1, batch 8450, loss[loss=0.1816, simple_loss=0.2501, pruned_loss=0.0565, over 4966.00 frames.], tot_loss[loss=0.192, simple_loss=0.2537, pruned_loss=0.0652, over 971458.54 frames.], batch size: 24, lr: 1.00e-03
2022-05-03 21:22:03,495 INFO [train.py:715] (4/8) Epoch 1, batch 8500, loss[loss=0.2484, simple_loss=0.2712, pruned_loss=0.1128, over 4823.00 frames.], tot_loss[loss=0.1916, simple_loss=0.253, pruned_loss=0.06506, over 971500.56 frames.], batch size: 15, lr: 1.00e-03
2022-05-03 21:22:43,391 INFO [train.py:715] (4/8) Epoch 1, batch 8550, loss[loss=0.1862, simple_loss=0.2415, pruned_loss=0.06546, over 4760.00 frames.], tot_loss[loss=0.1914, simple_loss=0.2528, pruned_loss=0.06498, over 971976.71 frames.], batch size: 16, lr: 1.00e-03
2022-05-03 21:23:22,900 INFO [train.py:715] (4/8) Epoch 1, batch 8600, loss[loss=0.1799, simple_loss=0.2573, pruned_loss=0.05129, over 4803.00 frames.], tot_loss[loss=0.1916, simple_loss=0.253, pruned_loss=0.06514, over 972344.03 frames.], batch size: 24, lr: 1.00e-03
2022-05-03 21:24:00,900 INFO [train.py:715] (4/8) Epoch 1, batch 8650, loss[loss=0.1841, simple_loss=0.2481, pruned_loss=0.06002, over 4879.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2519, pruned_loss=0.06445, over 972086.55 frames.], batch size: 16, lr: 9.99e-04
2022-05-03 21:24:41,123 INFO [train.py:715] (4/8) Epoch 1, batch 8700, loss[loss=0.2887, simple_loss=0.3242, pruned_loss=0.1266, over 4876.00 frames.], tot_loss[loss=0.1918, simple_loss=0.2527, pruned_loss=0.0654, over 972697.94 frames.], batch size: 38, lr: 9.98e-04
2022-05-03 21:25:21,116 INFO [train.py:715] (4/8) Epoch 1, batch 8750, loss[loss=0.2107, simple_loss=0.2707, pruned_loss=0.07534, over 4928.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2535, pruned_loss=0.0657, over 972495.09 frames.], batch size: 17, lr: 9.98e-04
2022-05-03 21:26:00,205 INFO [train.py:715] (4/8) Epoch 1, batch 8800, loss[loss=0.1644, simple_loss=0.2309, pruned_loss=0.04895, over 4919.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2537, pruned_loss=0.06557, over 973200.72 frames.], batch size: 18, lr: 9.97e-04
2022-05-03 21:26:39,533 INFO [train.py:715] (4/8) Epoch 1, batch 8850, loss[loss=0.1587, simple_loss=0.222, pruned_loss=0.04771, over 4768.00 frames.], tot_loss[loss=0.1928, simple_loss=0.2538, pruned_loss=0.06586, over 973436.59 frames.], batch size: 12, lr: 9.97e-04
2022-05-03 21:27:19,650 INFO [train.py:715] (4/8) Epoch 1, batch 8900, loss[loss=0.2123, simple_loss=0.2715, pruned_loss=0.07655, over 4895.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2525, pruned_loss=0.06469, over 972712.61 frames.], batch size: 19, lr: 9.96e-04
2022-05-03 21:27:59,352 INFO [train.py:715] (4/8) Epoch 1, batch 8950, loss[loss=0.2182, simple_loss=0.2755, pruned_loss=0.08051, over 4790.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2528, pruned_loss=0.06484, over 972386.25 frames.], batch size: 17, lr: 9.96e-04
2022-05-03 21:28:37,780 INFO [train.py:715] (4/8) Epoch 1, batch 9000, loss[loss=0.1817, simple_loss=0.2449, pruned_loss=0.05923, over 4860.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2525, pruned_loss=0.0646, over 972139.69 frames.], batch size: 32, lr: 9.95e-04
2022-05-03 21:28:37,781 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 21:28:47,501 INFO [train.py:742] (4/8) Epoch 1, validation: loss=0.1253, simple_loss=0.2125, pruned_loss=0.01906, over 914524.00 frames.
2022-05-03 21:29:25,993 INFO [train.py:715] (4/8) Epoch 1, batch 9050, loss[loss=0.172, simple_loss=0.2403, pruned_loss=0.05181, over 4807.00 frames.], tot_loss[loss=0.191, simple_loss=0.2526, pruned_loss=0.06467, over 972702.31 frames.], batch size: 21, lr: 9.94e-04
2022-05-03 21:30:06,205 INFO [train.py:715] (4/8) Epoch 1, batch 9100, loss[loss=0.1848, simple_loss=0.255, pruned_loss=0.05723, over 4849.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2538, pruned_loss=0.06548, over 973394.45 frames.], batch size: 20, lr: 9.94e-04
2022-05-03 21:30:45,842 INFO [train.py:715] (4/8) Epoch 1, batch 9150, loss[loss=0.2078, simple_loss=0.2651, pruned_loss=0.07528, over 4984.00 frames.], tot_loss[loss=0.1918, simple_loss=0.253, pruned_loss=0.0653, over 973407.38 frames.], batch size: 39, lr: 9.93e-04
2022-05-03 21:31:24,121 INFO [train.py:715] (4/8) Epoch 1, batch 9200, loss[loss=0.1909, simple_loss=0.2575, pruned_loss=0.06212, over 4859.00 frames.], tot_loss[loss=0.1931, simple_loss=0.2543, pruned_loss=0.06594, over 972905.03 frames.], batch size: 20, lr: 9.93e-04
2022-05-03 21:32:03,945 INFO [train.py:715] (4/8) Epoch 1, batch 9250, loss[loss=0.1519, simple_loss=0.2308, pruned_loss=0.03651, over 4751.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2539, pruned_loss=0.06533, over 972517.25 frames.], batch size: 19, lr: 9.92e-04
2022-05-03 21:32:43,821 INFO [train.py:715] (4/8) Epoch 1, batch 9300, loss[loss=0.1586, simple_loss=0.2345, pruned_loss=0.04134, over 4748.00 frames.], tot_loss[loss=0.1923, simple_loss=0.2543, pruned_loss=0.06517, over 972139.32 frames.], batch size: 16, lr: 9.92e-04
2022-05-03 21:33:22,873 INFO [train.py:715] (4/8) Epoch 1, batch 9350, loss[loss=0.228, simple_loss=0.2761, pruned_loss=0.08995, over 4962.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2531, pruned_loss=0.06393, over 971671.79 frames.], batch size: 35, lr: 9.91e-04
2022-05-03 21:34:02,360 INFO [train.py:715] (4/8) Epoch 1, batch 9400, loss[loss=0.2164, simple_loss=0.2532, pruned_loss=0.08978, over 4825.00 frames.], tot_loss[loss=0.1906, simple_loss=0.2531, pruned_loss=0.06409, over 971402.04 frames.], batch size: 13, lr: 9.91e-04
2022-05-03 21:34:42,532 INFO [train.py:715] (4/8) Epoch 1, batch 9450, loss[loss=0.2057, simple_loss=0.2659, pruned_loss=0.07279, over 4812.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2521, pruned_loss=0.06369, over 971452.38 frames.], batch size: 21, lr: 9.90e-04
2022-05-03 21:35:22,126 INFO [train.py:715] (4/8) Epoch 1, batch 9500, loss[loss=0.206, simple_loss=0.2641, pruned_loss=0.07397, over 4753.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2533, pruned_loss=0.06422, over 972224.74 frames.], batch size: 19, lr: 9.89e-04
2022-05-03 21:36:00,390 INFO [train.py:715] (4/8) Epoch 1, batch 9550, loss[loss=0.2168, simple_loss=0.2712, pruned_loss=0.08123, over 4739.00 frames.], tot_loss[loss=0.1919, simple_loss=0.2543, pruned_loss=0.06478, over 971454.84 frames.], batch size: 16, lr: 9.89e-04
2022-05-03 21:36:40,617 INFO [train.py:715] (4/8) Epoch 1, batch 9600, loss[loss=0.1764, simple_loss=0.2468, pruned_loss=0.05304, over 4766.00 frames.], tot_loss[loss=0.1926, simple_loss=0.2546, pruned_loss=0.06532, over 972347.75 frames.], batch size: 14, lr: 9.88e-04
2022-05-03 21:37:20,354 INFO [train.py:715] (4/8) Epoch 1, batch 9650, loss[loss=0.2111, simple_loss=0.2708, pruned_loss=0.07572, over 4930.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2544, pruned_loss=0.06513, over 972475.33 frames.], batch size: 29, lr: 9.88e-04
2022-05-03 21:37:58,744 INFO [train.py:715] (4/8) Epoch 1, batch 9700, loss[loss=0.1765, simple_loss=0.2495, pruned_loss=0.05178, over 4953.00 frames.], tot_loss[loss=0.1921, simple_loss=0.2543, pruned_loss=0.06496, over 972486.31 frames.], batch size: 23, lr: 9.87e-04
2022-05-03 21:38:38,644 INFO [train.py:715] (4/8) Epoch 1, batch 9750, loss[loss=0.2001, simple_loss=0.2471, pruned_loss=0.07651, over 4974.00 frames.], tot_loss[loss=0.1915, simple_loss=0.2536, pruned_loss=0.0647, over 972256.88 frames.], batch size: 15, lr: 9.87e-04
2022-05-03 21:39:19,057 INFO [train.py:715] (4/8) Epoch 1, batch 9800, loss[loss=0.2213, simple_loss=0.2786, pruned_loss=0.08202, over 4873.00 frames.], tot_loss[loss=0.1899, simple_loss=0.2525, pruned_loss=0.06362, over 972714.50 frames.], batch size: 16, lr: 9.86e-04
2022-05-03 21:39:58,295 INFO [train.py:715] (4/8) Epoch 1, batch 9850, loss[loss=0.1621, simple_loss=0.229, pruned_loss=0.04759, over 4939.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2519, pruned_loss=0.06326, over 973621.46 frames.], batch size: 21, lr: 9.86e-04
2022-05-03 21:40:37,079 INFO [train.py:715] (4/8) Epoch 1, batch 9900, loss[loss=0.1911, simple_loss=0.2515, pruned_loss=0.06534, over 4828.00 frames.], tot_loss[loss=0.1904, simple_loss=0.253, pruned_loss=0.06388, over 974350.71 frames.], batch size: 26, lr: 9.85e-04
2022-05-03 21:41:17,360 INFO [train.py:715] (4/8) Epoch 1, batch 9950, loss[loss=0.1615, simple_loss=0.2347, pruned_loss=0.04414, over 4903.00 frames.], tot_loss[loss=0.1913, simple_loss=0.2534, pruned_loss=0.06453, over 973911.56 frames.], batch size: 19, lr: 9.85e-04
2022-05-03 21:41:57,262 INFO [train.py:715] (4/8) Epoch 1, batch 10000, loss[loss=0.1871, simple_loss=0.2484, pruned_loss=0.06287, over 4855.00 frames.], tot_loss[loss=0.1924, simple_loss=0.2545, pruned_loss=0.06512, over 974571.84 frames.], batch size: 20, lr: 9.84e-04
2022-05-03 21:42:36,322 INFO [train.py:715] (4/8) Epoch 1, batch 10050, loss[loss=0.2061, simple_loss=0.2559, pruned_loss=0.07818, over 4813.00 frames.], tot_loss[loss=0.1917, simple_loss=0.2539, pruned_loss=0.06472, over 973599.88 frames.], batch size: 13, lr: 9.83e-04
2022-05-03 21:43:15,952 INFO [train.py:715] (4/8) Epoch 1, batch 10100, loss[loss=0.1385, simple_loss=0.2072, pruned_loss=0.03487, over 4837.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2532, pruned_loss=0.06448, over 973430.65 frames.], batch size: 13, lr: 9.83e-04
2022-05-03 21:43:55,967 INFO [train.py:715] (4/8) Epoch 1, batch 10150, loss[loss=0.2096, simple_loss=0.2738, pruned_loss=0.07276, over 4959.00 frames.], tot_loss[loss=0.19, simple_loss=0.2523, pruned_loss=0.0638, over 973467.61 frames.], batch size: 39, lr: 9.82e-04
2022-05-03 21:44:35,078 INFO [train.py:715] (4/8) Epoch 1, batch 10200, loss[loss=0.1951, simple_loss=0.2683, pruned_loss=0.061, over 4757.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2523, pruned_loss=0.06395, over 973311.55 frames.], batch size: 16, lr: 9.82e-04
2022-05-03 21:45:14,035 INFO [train.py:715] (4/8) Epoch 1, batch 10250, loss[loss=0.1867, simple_loss=0.2424, pruned_loss=0.0655, over 4872.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2525, pruned_loss=0.06393, over 972053.91 frames.], batch size: 32, lr: 9.81e-04
2022-05-03 21:45:54,203 INFO [train.py:715] (4/8) Epoch 1, batch 10300, loss[loss=0.2252, simple_loss=0.2629, pruned_loss=0.09372, over 4900.00 frames.], tot_loss[loss=0.1897, simple_loss=0.252, pruned_loss=0.0637, over 972492.48 frames.], batch size: 17, lr: 9.81e-04
2022-05-03 21:46:34,448 INFO [train.py:715] (4/8) Epoch 1, batch 10350, loss[loss=0.1678, simple_loss=0.2255, pruned_loss=0.05505, over 4883.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2509, pruned_loss=0.06334, over 972724.36 frames.], batch size: 22, lr: 9.80e-04
2022-05-03 21:47:13,904 INFO [train.py:715] (4/8) Epoch 1, batch 10400, loss[loss=0.1704, simple_loss=0.2488, pruned_loss=0.04598, over 4777.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2497, pruned_loss=0.06277, over 972317.02 frames.], batch size: 18, lr: 9.80e-04
2022-05-03 21:47:53,943 INFO [train.py:715] (4/8) Epoch 1, batch 10450, loss[loss=0.2752, simple_loss=0.2964, pruned_loss=0.1269, over 4873.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2518, pruned_loss=0.06432, over 972015.05 frames.], batch size: 13, lr: 9.79e-04
2022-05-03 21:48:34,475 INFO [train.py:715] (4/8) Epoch 1, batch 10500, loss[loss=0.1641, simple_loss=0.2455, pruned_loss=0.04135, over 4939.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2507, pruned_loss=0.06393, over 971587.45 frames.], batch size: 23, lr: 9.79e-04
2022-05-03 21:49:13,759 INFO [train.py:715] (4/8) Epoch 1, batch 10550, loss[loss=0.1695, simple_loss=0.2422, pruned_loss=0.04834, over 4909.00 frames.], tot_loss[loss=0.1891, simple_loss=0.2511, pruned_loss=0.06357, over 971857.82 frames.], batch size: 17, lr: 9.78e-04
2022-05-03 21:49:52,640 INFO [train.py:715] (4/8) Epoch 1, batch 10600, loss[loss=0.19, simple_loss=0.2583, pruned_loss=0.0608, over 4933.00 frames.], tot_loss[loss=0.1901, simple_loss=0.2522, pruned_loss=0.06397, over 972194.92 frames.], batch size: 21, lr: 9.78e-04
2022-05-03 21:50:33,175 INFO [train.py:715] (4/8) Epoch 1, batch 10650, loss[loss=0.1645, simple_loss=0.2264, pruned_loss=0.05129, over 4932.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2519, pruned_loss=0.0638, over 972203.08 frames.], batch size: 29, lr: 9.77e-04
2022-05-03 21:51:13,725 INFO [train.py:715] (4/8) Epoch 1, batch 10700, loss[loss=0.2097, simple_loss=0.2878, pruned_loss=0.06577, over 4791.00 frames.], tot_loss[loss=0.1904, simple_loss=0.2527, pruned_loss=0.06408, over 972920.50 frames.], batch size: 24, lr: 9.76e-04
2022-05-03 21:51:52,989 INFO [train.py:715] (4/8) Epoch 1, batch 10750, loss[loss=0.1925, simple_loss=0.2567, pruned_loss=0.06419, over 4796.00 frames.], tot_loss[loss=0.1909, simple_loss=0.2534, pruned_loss=0.06423, over 973805.19 frames.], batch size: 24, lr: 9.76e-04
2022-05-03 21:52:32,273 INFO [train.py:715] (4/8) Epoch 1, batch 10800, loss[loss=0.222, simple_loss=0.2745, pruned_loss=0.08474, over 4854.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2526, pruned_loss=0.0633, over 973379.02 frames.], batch size: 34, lr: 9.75e-04
2022-05-03 21:53:12,728 INFO [train.py:715] (4/8) Epoch 1, batch 10850, loss[loss=0.1883, simple_loss=0.2375, pruned_loss=0.0696, over 4893.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2519, pruned_loss=0.06328, over 972959.08 frames.], batch size: 17, lr: 9.75e-04
2022-05-03 21:53:52,217 INFO [train.py:715] (4/8) Epoch 1, batch 10900, loss[loss=0.192, simple_loss=0.2575, pruned_loss=0.0632, over 4966.00 frames.], tot_loss[loss=0.1881, simple_loss=0.2506, pruned_loss=0.06284, over 972925.55 frames.], batch size: 39, lr: 9.74e-04
2022-05-03 21:54:30,706 INFO [train.py:715] (4/8) Epoch 1, batch 10950, loss[loss=0.192, simple_loss=0.2435, pruned_loss=0.07027, over 4851.00 frames.], tot_loss[loss=0.188, simple_loss=0.2505, pruned_loss=0.06276, over 973417.93 frames.], batch size: 32, lr: 9.74e-04
2022-05-03 21:55:10,755 INFO [train.py:715] (4/8) Epoch 1, batch 11000, loss[loss=0.183, simple_loss=0.2361, pruned_loss=0.06493, over 4980.00 frames.], tot_loss[loss=0.188, simple_loss=0.25, pruned_loss=0.06302, over 973702.41 frames.], batch size: 33, lr: 9.73e-04
2022-05-03 21:55:50,515 INFO [train.py:715] (4/8) Epoch 1, batch 11050, loss[loss=0.1724, simple_loss=0.2501, pruned_loss=0.04733, over 4723.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2498, pruned_loss=0.06334, over 973046.85 frames.], batch size: 16, lr: 9.73e-04
2022-05-03 21:56:29,266 INFO [train.py:715] (4/8) Epoch 1, batch 11100, loss[loss=0.1794, simple_loss=0.2477, pruned_loss=0.05554, over 4852.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2497, pruned_loss=0.06295, over 973128.99 frames.], batch size: 20, lr: 9.72e-04
2022-05-03 21:57:08,675 INFO [train.py:715] (4/8) Epoch 1, batch 11150, loss[loss=0.1651, simple_loss=0.2296, pruned_loss=0.05036, over 4848.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2504, pruned_loss=0.06318, over 972244.94 frames.], batch size: 32, lr: 9.72e-04
2022-05-03 21:57:48,800 INFO [train.py:715] (4/8) Epoch 1, batch 11200, loss[loss=0.2042, simple_loss=0.2626, pruned_loss=0.07295, over 4960.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2505, pruned_loss=0.06318, over 972220.44 frames.], batch size: 35, lr: 9.71e-04
2022-05-03 21:58:28,396 INFO [train.py:715] (4/8) Epoch 1, batch 11250, loss[loss=0.1736, simple_loss=0.247, pruned_loss=0.05011, over 4808.00 frames.], tot_loss[loss=0.19, simple_loss=0.2517, pruned_loss=0.06412, over 972858.82 frames.], batch size: 25, lr: 9.71e-04
2022-05-03 21:59:06,581 INFO [train.py:715] (4/8) Epoch 1, batch 11300, loss[loss=0.1564, simple_loss=0.2206, pruned_loss=0.04607, over 4972.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2499, pruned_loss=0.06324, over 973395.04 frames.], batch size: 24, lr: 9.70e-04
2022-05-03 21:59:46,982 INFO [train.py:715] (4/8) Epoch 1, batch 11350, loss[loss=0.2085, simple_loss=0.2735, pruned_loss=0.0718, over 4914.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2505, pruned_loss=0.06355, over 972959.92 frames.], batch size: 19, lr: 9.70e-04
2022-05-03 22:00:26,694 INFO [train.py:715] (4/8) Epoch 1, batch 11400, loss[loss=0.1504, simple_loss=0.2124, pruned_loss=0.04422, over 4930.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2498, pruned_loss=0.06285, over 972937.88 frames.], batch size: 18, lr: 9.69e-04
2022-05-03 22:01:04,857 INFO [train.py:715] (4/8) Epoch 1, batch 11450, loss[loss=0.2028, simple_loss=0.2537, pruned_loss=0.07595, over 4823.00 frames.], tot_loss[loss=0.1889, simple_loss=0.2504, pruned_loss=0.06367, over 972332.27 frames.], batch size: 15, lr: 9.69e-04
2022-05-03 22:01:44,067 INFO [train.py:715] (4/8) Epoch 1, batch 11500, loss[loss=0.1881, simple_loss=0.2429, pruned_loss=0.0666, over 4774.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2502, pruned_loss=0.06312, over 972469.42 frames.], batch size: 14, lr: 9.68e-04
2022-05-03 22:02:23,956 INFO [train.py:715] (4/8) Epoch 1, batch 11550, loss[loss=0.1798, simple_loss=0.2324, pruned_loss=0.06356, over 4777.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2509, pruned_loss=0.06425, over 971494.30 frames.], batch size: 18, lr: 9.68e-04
2022-05-03 22:03:03,163 INFO [train.py:715] (4/8) Epoch 1, batch 11600, loss[loss=0.1773, simple_loss=0.2333, pruned_loss=0.06067, over 4963.00 frames.], tot_loss[loss=0.1898, simple_loss=0.2511, pruned_loss=0.06422, over 971610.77 frames.], batch size: 35, lr: 9.67e-04
2022-05-03 22:03:41,492 INFO [train.py:715] (4/8) Epoch 1, batch 11650, loss[loss=0.1889, simple_loss=0.2497, pruned_loss=0.06409, over 4975.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2511, pruned_loss=0.06364, over 972007.38 frames.], batch size: 35, lr: 9.67e-04
2022-05-03 22:04:21,431 INFO [train.py:715] (4/8) Epoch 1, batch 11700, loss[loss=0.1572, simple_loss=0.226, pruned_loss=0.04416, over 4815.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2514, pruned_loss=0.06363, over 970994.84 frames.], batch size: 13, lr: 9.66e-04
2022-05-03 22:05:01,248 INFO [train.py:715] (4/8) Epoch 1, batch 11750, loss[loss=0.1703, simple_loss=0.2319, pruned_loss=0.05433, over 4813.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2508, pruned_loss=0.06342, over 971122.36 frames.], batch size: 25, lr: 9.66e-04
2022-05-03 22:05:40,551 INFO [train.py:715] (4/8) Epoch 1, batch 11800, loss[loss=0.1609, simple_loss=0.2288, pruned_loss=0.0465, over 4828.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2512, pruned_loss=0.06364, over 970871.19 frames.], batch size: 13, lr: 9.65e-04
2022-05-03 22:06:19,254 INFO [train.py:715] (4/8) Epoch 1, batch 11850, loss[loss=0.1729, simple_loss=0.2422, pruned_loss=0.05181, over 4884.00 frames.], tot_loss[loss=0.1884, simple_loss=0.2505, pruned_loss=0.06313, over 970151.63 frames.], batch size: 20, lr: 9.65e-04
2022-05-03 22:06:59,286 INFO [train.py:715] (4/8) Epoch 1, batch 11900, loss[loss=0.1822, simple_loss=0.2322, pruned_loss=0.06612, over 4985.00 frames.], tot_loss[loss=0.1878, simple_loss=0.25, pruned_loss=0.06285, over 971689.64 frames.], batch size: 14, lr: 9.64e-04
2022-05-03 22:07:38,634 INFO [train.py:715] (4/8) Epoch 1, batch 11950, loss[loss=0.1787, simple_loss=0.2401, pruned_loss=0.05871, over 4842.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2507, pruned_loss=0.06312, over 972233.68 frames.], batch size: 34, lr: 9.63e-04
2022-05-03 22:08:17,118 INFO [train.py:715] (4/8) Epoch 1, batch 12000, loss[loss=0.2096, simple_loss=0.2684, pruned_loss=0.07538, over 4938.00 frames.], tot_loss[loss=0.1876, simple_loss=0.25, pruned_loss=0.06261, over 971929.45 frames.], batch size: 21, lr: 9.63e-04
2022-05-03 22:08:17,119 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 22:08:27,630 INFO [train.py:742] (4/8) Epoch 1, validation: loss=0.1244, simple_loss=0.2116, pruned_loss=0.01858, over 914524.00 frames.
2022-05-03 22:09:06,364 INFO [train.py:715] (4/8) Epoch 1, batch 12050, loss[loss=0.2445, simple_loss=0.3041, pruned_loss=0.09243, over 4873.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2508, pruned_loss=0.06278, over 972180.68 frames.], batch size: 16, lr: 9.62e-04
2022-05-03 22:09:46,985 INFO [train.py:715] (4/8) Epoch 1, batch 12100, loss[loss=0.2108, simple_loss=0.271, pruned_loss=0.07527, over 4865.00 frames.], tot_loss[loss=0.188, simple_loss=0.251, pruned_loss=0.06253, over 972637.47 frames.], batch size: 20, lr: 9.62e-04
2022-05-03 22:10:27,669 INFO [train.py:715] (4/8) Epoch 1, batch 12150, loss[loss=0.13, simple_loss=0.2045, pruned_loss=0.02772, over 4842.00 frames.], tot_loss[loss=0.188, simple_loss=0.2509, pruned_loss=0.06254, over 971893.56 frames.], batch size: 15, lr: 9.61e-04
2022-05-03 22:11:06,640 INFO [train.py:715] (4/8) Epoch 1, batch 12200, loss[loss=0.187, simple_loss=0.2616, pruned_loss=0.05626, over 4763.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2512, pruned_loss=0.06318, over 972637.81 frames.], batch size: 14, lr: 9.61e-04
2022-05-03 22:11:46,545 INFO [train.py:715] (4/8) Epoch 1, batch 12250, loss[loss=0.1705, simple_loss=0.2335, pruned_loss=0.05373, over 4852.00 frames.], tot_loss[loss=0.1893, simple_loss=0.2517, pruned_loss=0.06343, over 973301.57 frames.], batch size: 20, lr: 9.60e-04
2022-05-03 22:12:27,156 INFO [train.py:715] (4/8) Epoch 1, batch 12300, loss[loss=0.2207, simple_loss=0.2782, pruned_loss=0.08162, over 4771.00 frames.], tot_loss[loss=0.1887, simple_loss=0.2515, pruned_loss=0.06297, over 972819.61 frames.], batch size: 14, lr: 9.60e-04
2022-05-03 22:13:06,772 INFO [train.py:715] (4/8) Epoch 1, batch 12350, loss[loss=0.2356, simple_loss=0.2966, pruned_loss=0.08729, over 4963.00 frames.], tot_loss[loss=0.1885, simple_loss=0.251, pruned_loss=0.06299, over 972654.07 frames.], batch size: 21, lr: 9.59e-04
2022-05-03 22:13:45,539 INFO [train.py:715] (4/8) Epoch 1, batch 12400, loss[loss=0.2429, simple_loss=0.2844, pruned_loss=0.1007, over 4803.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2504, pruned_loss=0.06232, over 973225.54 frames.], batch size: 14, lr: 9.59e-04
2022-05-03 22:14:25,686 INFO [train.py:715] (4/8) Epoch 1, batch 12450, loss[loss=0.1946, simple_loss=0.2642, pruned_loss=0.06255, over 4768.00 frames.], tot_loss[loss=0.187, simple_loss=0.2498, pruned_loss=0.06212, over 972891.12 frames.], batch size: 19, lr: 9.58e-04
2022-05-03 22:15:05,667 INFO [train.py:715] (4/8) Epoch 1, batch 12500, loss[loss=0.1804, simple_loss=0.2452, pruned_loss=0.05782, over 4817.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2506, pruned_loss=0.0623, over 972095.05 frames.], batch size: 21, lr: 9.58e-04
2022-05-03 22:15:44,875 INFO [train.py:715] (4/8) Epoch 1, batch 12550, loss[loss=0.166, simple_loss=0.2462, pruned_loss=0.04283, over 4943.00 frames.], tot_loss[loss=0.1881, simple_loss=0.251, pruned_loss=0.06263, over 972439.57 frames.], batch size: 29, lr: 9.57e-04
2022-05-03 22:16:24,272 INFO [train.py:715] (4/8) Epoch 1, batch 12600, loss[loss=0.1482, simple_loss=0.2174, pruned_loss=0.03947, over 4788.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2511, pruned_loss=0.06232, over 971755.43 frames.], batch size: 14, lr: 9.57e-04
2022-05-03 22:17:04,549 INFO [train.py:715] (4/8) Epoch 1, batch 12650, loss[loss=0.2533, simple_loss=0.3029, pruned_loss=0.1019, over 4956.00 frames.], tot_loss[loss=0.1886, simple_loss=0.2515, pruned_loss=0.06288, over 971748.33 frames.], batch size: 39, lr: 9.56e-04
2022-05-03 22:17:43,554 INFO [train.py:715] (4/8) Epoch 1, batch 12700, loss[loss=0.1913, simple_loss=0.2447, pruned_loss=0.06894, over 4992.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2521, pruned_loss=0.06312, over 971467.33 frames.], batch size: 15, lr: 9.56e-04
2022-05-03 22:18:22,949 INFO [train.py:715] (4/8) Epoch 1, batch 12750, loss[loss=0.1963, simple_loss=0.2568, pruned_loss=0.0679, over 4966.00 frames.], tot_loss[loss=0.1902, simple_loss=0.2527, pruned_loss=0.06388, over 971516.29 frames.], batch size: 15, lr: 9.55e-04
2022-05-03 22:19:03,050 INFO [train.py:715] (4/8) Epoch 1, batch 12800, loss[loss=0.1922, simple_loss=0.2479, pruned_loss=0.06823, over 4855.00 frames.], tot_loss[loss=0.1892, simple_loss=0.2517, pruned_loss=0.06334, over 971837.36 frames.], batch size: 30, lr: 9.55e-04
2022-05-03 22:19:42,870 INFO [train.py:715] (4/8) Epoch 1, batch 12850, loss[loss=0.1621, simple_loss=0.2224, pruned_loss=0.05091, over 4949.00 frames.], tot_loss[loss=0.1898, simple_loss=0.252, pruned_loss=0.06378, over 971597.99 frames.], batch size: 21, lr: 9.54e-04
2022-05-03 22:20:21,820 INFO [train.py:715] (4/8) Epoch 1, batch 12900, loss[loss=0.1612, simple_loss=0.2315, pruned_loss=0.04544, over 4797.00 frames.], tot_loss[loss=0.1905, simple_loss=0.2525, pruned_loss=0.06426, over 971514.23 frames.], batch size: 24, lr: 9.54e-04
2022-05-03 22:21:01,112 INFO [train.py:715] (4/8) Epoch 1, batch 12950, loss[loss=0.1616, simple_loss=0.226, pruned_loss=0.04865, over 4915.00 frames.], tot_loss[loss=0.1912, simple_loss=0.253, pruned_loss=0.06475, over 971327.31 frames.], batch size: 23, lr: 9.53e-04
2022-05-03 22:21:41,543 INFO [train.py:715] (4/8) Epoch 1, batch 13000, loss[loss=0.2015, simple_loss=0.2547, pruned_loss=0.0741, over 4823.00 frames.], tot_loss[loss=0.1912, simple_loss=0.2528, pruned_loss=0.06478, over 971862.13 frames.], batch size: 13, lr: 9.53e-04
2022-05-03 22:22:21,116 INFO [train.py:715] (4/8) Epoch 1, batch 13050, loss[loss=0.1472, simple_loss=0.2175, pruned_loss=0.03845, over 4988.00 frames.], tot_loss[loss=0.1908, simple_loss=0.2526, pruned_loss=0.06451, over 971459.37 frames.], batch size: 25, lr: 9.52e-04
2022-05-03 22:23:01,176 INFO [train.py:715] (4/8) Epoch 1, batch 13100, loss[loss=0.1872, simple_loss=0.2585, pruned_loss=0.05792, over 4817.00 frames.], tot_loss[loss=0.1911, simple_loss=0.2532, pruned_loss=0.06453, over 972000.98 frames.], batch size: 27, lr: 9.52e-04
2022-05-03 22:23:41,360 INFO [train.py:715] (4/8) Epoch 1, batch 13150, loss[loss=0.1753, simple_loss=0.2458, pruned_loss=0.05242, over 4905.00 frames.], tot_loss[loss=0.1897, simple_loss=0.2519, pruned_loss=0.06376, over 971906.03 frames.], batch size: 17, lr: 9.51e-04
2022-05-03 22:24:23,878 INFO [train.py:715] (4/8) Epoch 1, batch 13200, loss[loss=0.1706, simple_loss=0.2387, pruned_loss=0.05123, over 4977.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2506, pruned_loss=0.06261, over 971680.32 frames.], batch size: 28, lr: 9.51e-04
2022-05-03 22:25:03,006 INFO [train.py:715] (4/8) Epoch 1, batch 13250, loss[loss=0.1947, simple_loss=0.2493, pruned_loss=0.06999, over 4788.00 frames.], tot_loss[loss=0.1873, simple_loss=0.25, pruned_loss=0.06231, over 972001.59 frames.], batch size: 14, lr: 9.51e-04
2022-05-03 22:25:41,752 INFO [train.py:715] (4/8) Epoch 1, batch 13300, loss[loss=0.2115, simple_loss=0.2627, pruned_loss=0.0801, over 4950.00 frames.], tot_loss[loss=0.188, simple_loss=0.2505, pruned_loss=0.06277, over 972301.67 frames.], batch size: 15, lr: 9.50e-04
2022-05-03 22:26:21,980 INFO [train.py:715] (4/8) Epoch 1, batch 13350, loss[loss=0.173, simple_loss=0.2395, pruned_loss=0.05329, over 4748.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2489, pruned_loss=0.0621, over 972150.99 frames.], batch size: 19, lr: 9.50e-04
2022-05-03 22:27:01,384 INFO [train.py:715] (4/8) Epoch 1, batch 13400, loss[loss=0.1534, simple_loss=0.2179, pruned_loss=0.04444, over 4936.00 frames.], tot_loss[loss=0.187, simple_loss=0.2494, pruned_loss=0.06229, over 971569.04 frames.], batch size: 21, lr: 9.49e-04
2022-05-03 22:27:41,355 INFO [train.py:715] (4/8) Epoch 1, batch 13450, loss[loss=0.2057, simple_loss=0.2732, pruned_loss=0.0691, over 4964.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2498, pruned_loss=0.06229, over 972217.85 frames.], batch size: 24, lr: 9.49e-04
2022-05-03 22:28:21,085 INFO [train.py:715] (4/8) Epoch 1, batch 13500, loss[loss=0.1806, simple_loss=0.2542, pruned_loss=0.05347, over 4755.00 frames.], tot_loss[loss=0.1879, simple_loss=0.2505, pruned_loss=0.06271, over 972229.35 frames.], batch size: 16, lr: 9.48e-04
2022-05-03 22:29:01,036 INFO [train.py:715] (4/8) Epoch 1, batch 13550, loss[loss=0.194, simple_loss=0.2627, pruned_loss=0.06267, over 4936.00 frames.], tot_loss[loss=0.1896, simple_loss=0.2523, pruned_loss=0.06346, over 972240.99 frames.], batch size: 39, lr: 9.48e-04
2022-05-03 22:29:39,301 INFO [train.py:715] (4/8) Epoch 1, batch 13600, loss[loss=0.1833, simple_loss=0.2478, pruned_loss=0.05937, over 4980.00 frames.], tot_loss[loss=0.1885, simple_loss=0.2514, pruned_loss=0.06281, over 972346.45 frames.], batch size: 25, lr: 9.47e-04
2022-05-03 22:30:18,505 INFO [train.py:715] (4/8) Epoch 1, batch 13650, loss[loss=0.1872, simple_loss=0.2539, pruned_loss=0.06025, over 4921.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2512, pruned_loss=0.06258, over 972408.99 frames.], batch size: 29, lr: 9.47e-04
2022-05-03 22:30:58,736 INFO [train.py:715] (4/8) Epoch 1, batch 13700, loss[loss=0.1619, simple_loss=0.2341, pruned_loss=0.04481, over 4839.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2499, pruned_loss=0.06224, over 972248.65 frames.], batch size: 15, lr: 9.46e-04
2022-05-03 22:31:38,135 INFO [train.py:715] (4/8) Epoch 1, batch 13750, loss[loss=0.1954, simple_loss=0.2602, pruned_loss=0.0653, over 4910.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2489, pruned_loss=0.06184, over 972707.69 frames.], batch size: 17, lr: 9.46e-04
2022-05-03 22:32:17,280 INFO [train.py:715] (4/8) Epoch 1, batch 13800, loss[loss=0.2014, simple_loss=0.2728, pruned_loss=0.06505, over 4974.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2493, pruned_loss=0.06219, over 973140.66 frames.], batch size: 15, lr: 9.45e-04
2022-05-03 22:32:56,966 INFO [train.py:715] (4/8) Epoch 1, batch 13850, loss[loss=0.2047, simple_loss=0.2674, pruned_loss=0.07096, over 4813.00 frames.], tot_loss[loss=0.188, simple_loss=0.2502, pruned_loss=0.06288, over 973669.66 frames.], batch size: 21, lr: 9.45e-04
2022-05-03 22:33:36,809 INFO [train.py:715] (4/8) Epoch 1, batch 13900, loss[loss=0.1777, simple_loss=0.2436, pruned_loss=0.0559, over 4925.00 frames.], tot_loss[loss=0.1883, simple_loss=0.2505, pruned_loss=0.06307, over 972508.16 frames.], batch size: 39, lr: 9.44e-04
2022-05-03 22:34:15,306 INFO [train.py:715] (4/8) Epoch 1, batch 13950, loss[loss=0.2012, simple_loss=0.2584, pruned_loss=0.07202, over 4831.00 frames.], tot_loss[loss=0.189, simple_loss=0.251, pruned_loss=0.06352, over 972943.99 frames.], batch size: 30, lr: 9.44e-04
2022-05-03 22:34:54,565 INFO [train.py:715] (4/8) Epoch 1, batch 14000, loss[loss=0.1591, simple_loss=0.2396, pruned_loss=0.03931, over 4831.00 frames.], tot_loss[loss=0.1888, simple_loss=0.2514, pruned_loss=0.06317, over 972478.78 frames.], batch size: 27, lr: 9.43e-04
2022-05-03 22:35:34,713 INFO [train.py:715] (4/8) Epoch 1, batch 14050, loss[loss=0.2128, simple_loss=0.2663, pruned_loss=0.07969, over 4707.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2499, pruned_loss=0.06175, over 973354.27 frames.], batch size: 15, lr: 9.43e-04
2022-05-03 22:36:13,514 INFO [train.py:715] (4/8) Epoch 1, batch 14100, loss[loss=0.2086, simple_loss=0.2756, pruned_loss=0.07083, over 4952.00 frames.], tot_loss[loss=0.187, simple_loss=0.2502, pruned_loss=0.0619, over 972853.51 frames.], batch size: 21, lr: 9.42e-04
2022-05-03 22:36:52,748 INFO [train.py:715] (4/8) Epoch 1, batch 14150, loss[loss=0.1678, simple_loss=0.2394, pruned_loss=0.04807, over 4959.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2506, pruned_loss=0.06202, over 973321.52 frames.], batch size: 29, lr: 9.42e-04
2022-05-03 22:37:31,980 INFO [train.py:715] (4/8) Epoch 1, batch 14200, loss[loss=0.2086, simple_loss=0.2664, pruned_loss=0.0754, over 4773.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2496, pruned_loss=0.06179, over 972575.67 frames.], batch size: 18, lr: 9.41e-04
2022-05-03 22:38:12,095 INFO [train.py:715] (4/8) Epoch 1, batch 14250, loss[loss=0.1855, simple_loss=0.2373, pruned_loss=0.0668, over 4856.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2494, pruned_loss=0.06136, over 972672.13 frames.], batch size: 32, lr: 9.41e-04
2022-05-03 22:38:50,570 INFO [train.py:715] (4/8) Epoch 1, batch 14300, loss[loss=0.1773, simple_loss=0.2513, pruned_loss=0.05172, over 4853.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2482, pruned_loss=0.06073, over 972299.76 frames.], batch size: 20, lr: 9.40e-04
2022-05-03 22:39:29,557 INFO [train.py:715] (4/8) Epoch 1, batch 14350, loss[loss=0.1563, simple_loss=0.2184, pruned_loss=0.04711, over 4774.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2493, pruned_loss=0.06209, over 971610.42 frames.], batch size: 17, lr: 9.40e-04
2022-05-03 22:40:09,907 INFO [train.py:715] (4/8) Epoch 1, batch 14400, loss[loss=0.2074, simple_loss=0.2714, pruned_loss=0.0717, over 4945.00 frames.], tot_loss[loss=0.187, simple_loss=0.2496, pruned_loss=0.0622, over 971232.62 frames.], batch size: 39, lr: 9.39e-04
2022-05-03 22:40:48,727 INFO [train.py:715] (4/8) Epoch 1, batch 14450, loss[loss=0.152, simple_loss=0.2269, pruned_loss=0.03859, over 4820.00 frames.], tot_loss[loss=0.1869, simple_loss=0.25, pruned_loss=0.06194, over 971065.70 frames.], batch size: 15, lr: 9.39e-04
2022-05-03 22:41:28,250 INFO [train.py:715] (4/8) Epoch 1, batch 14500, loss[loss=0.2568, simple_loss=0.3008, pruned_loss=0.1064, over 4862.00 frames.], tot_loss[loss=0.187, simple_loss=0.2499, pruned_loss=0.06203, over 971633.98 frames.], batch size: 32, lr: 9.39e-04
2022-05-03 22:42:08,355 INFO [train.py:715] (4/8) Epoch 1, batch 14550, loss[loss=0.174, simple_loss=0.2397, pruned_loss=0.05412, over 4864.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2502, pruned_loss=0.06215, over 971322.75 frames.], batch size: 39, lr: 9.38e-04
2022-05-03 22:42:47,866 INFO [train.py:715] (4/8) Epoch 1, batch 14600, loss[loss=0.1683, simple_loss=0.2377, pruned_loss=0.04948, over 4778.00 frames.], tot_loss[loss=0.187, simple_loss=0.2499, pruned_loss=0.06207, over 971208.60 frames.], batch size: 18, lr: 9.38e-04
2022-05-03 22:43:26,826 INFO [train.py:715] (4/8) Epoch 1, batch 14650, loss[loss=0.1747, simple_loss=0.2592, pruned_loss=0.04511, over 4776.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2501, pruned_loss=0.06182, over 971833.88 frames.], batch size: 17, lr: 9.37e-04
2022-05-03 22:44:05,664 INFO [train.py:715] (4/8) Epoch 1, batch 14700, loss[loss=0.1664, simple_loss=0.2236, pruned_loss=0.05463, over 4976.00 frames.], tot_loss[loss=0.1856, simple_loss=0.249, pruned_loss=0.06112, over 972591.52 frames.], batch size: 14, lr: 9.37e-04
2022-05-03 22:44:45,792 INFO [train.py:715] (4/8) Epoch 1, batch 14750, loss[loss=0.227, simple_loss=0.2778, pruned_loss=0.08812, over 4748.00 frames.], tot_loss[loss=0.1852, simple_loss=0.2484, pruned_loss=0.06097, over 972227.49 frames.], batch size: 16, lr: 9.36e-04
2022-05-03 22:45:24,935 INFO [train.py:715] (4/8) Epoch 1, batch 14800, loss[loss=0.204, simple_loss=0.2722, pruned_loss=0.06787, over 4859.00 frames.], tot_loss[loss=0.1847, simple_loss=0.248, pruned_loss=0.06066, over 972282.09 frames.], batch size: 32, lr: 9.36e-04
2022-05-03 22:46:04,492 INFO [train.py:715] (4/8) Epoch 1, batch 14850, loss[loss=0.2186, simple_loss=0.2827, pruned_loss=0.07725, over 4872.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2486, pruned_loss=0.06154, over 971647.21 frames.], batch size: 16, lr: 9.35e-04
2022-05-03 22:46:43,811 INFO [train.py:715] (4/8) Epoch 1, batch 14900, loss[loss=0.15, simple_loss=0.2154, pruned_loss=0.04229, over 4935.00 frames.], tot_loss[loss=0.185, simple_loss=0.2479, pruned_loss=0.06104, over 971191.78 frames.], batch size: 29, lr: 9.35e-04
2022-05-03 22:47:22,416 INFO [train.py:715] (4/8) Epoch 1, batch 14950, loss[loss=0.2121, simple_loss=0.2573, pruned_loss=0.08351, over 4752.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2482, pruned_loss=0.06127, over 971906.47 frames.], batch size: 19, lr: 9.34e-04
2022-05-03 22:48:02,034 INFO [train.py:715] (4/8) Epoch 1, batch 15000, loss[loss=0.2255, simple_loss=0.2773, pruned_loss=0.08683, over 4828.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2489, pruned_loss=0.06166, over 972850.78 frames.], batch size: 26, lr: 9.34e-04
2022-05-03 22:48:02,035 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 22:48:17,508 INFO [train.py:742] (4/8) Epoch 1, validation: loss=0.1242, simple_loss=0.2115, pruned_loss=0.01842, over 914524.00 frames.
2022-05-03 22:48:57,644 INFO [train.py:715] (4/8) Epoch 1, batch 15050, loss[loss=0.1831, simple_loss=0.2592, pruned_loss=0.05354, over 4919.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2501, pruned_loss=0.06232, over 973003.43 frames.], batch size: 29, lr: 9.33e-04
2022-05-03 22:49:37,575 INFO [train.py:715] (4/8) Epoch 1, batch 15100, loss[loss=0.1753, simple_loss=0.2419, pruned_loss=0.05432, over 4884.00 frames.], tot_loss[loss=0.1876, simple_loss=0.2501, pruned_loss=0.06252, over 973025.41 frames.], batch size: 22, lr: 9.33e-04
2022-05-03 22:50:18,113 INFO [train.py:715] (4/8) Epoch 1, batch 15150, loss[loss=0.1843, simple_loss=0.2546, pruned_loss=0.05694, over 4953.00 frames.], tot_loss[loss=0.1877, simple_loss=0.2502, pruned_loss=0.0626, over 972663.81 frames.], batch size: 21, lr: 9.32e-04
2022-05-03 22:50:57,490 INFO [train.py:715] (4/8) Epoch 1, batch 15200, loss[loss=0.1874, simple_loss=0.2545, pruned_loss=0.06011, over 4806.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2492, pruned_loss=0.06149, over 973084.12 frames.], batch size: 21, lr: 9.32e-04
2022-05-03 22:51:37,971 INFO [train.py:715] (4/8) Epoch 1, batch 15250, loss[loss=0.2002, simple_loss=0.2615, pruned_loss=0.0694, over 4916.00 frames.], tot_loss[loss=0.1861, simple_loss=0.249, pruned_loss=0.06161, over 973329.35 frames.], batch size: 17, lr: 9.32e-04
2022-05-03 22:52:17,891 INFO [train.py:715] (4/8) Epoch 1, batch 15300, loss[loss=0.1979, simple_loss=0.2679, pruned_loss=0.06394, over 4820.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2488, pruned_loss=0.06109, over 973069.22 frames.], batch size: 26, lr: 9.31e-04
2022-05-03 22:52:57,778 INFO [train.py:715] (4/8) Epoch 1, batch 15350, loss[loss=0.1974, simple_loss=0.2675, pruned_loss=0.0636, over 4955.00 frames.], tot_loss[loss=0.1868, simple_loss=0.25, pruned_loss=0.06181, over 972694.53 frames.], batch size: 21, lr: 9.31e-04
2022-05-03 22:53:37,914 INFO [train.py:715] (4/8) Epoch 1, batch 15400, loss[loss=0.1641, simple_loss=0.2326, pruned_loss=0.0478, over 4936.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2493, pruned_loss=0.06114, over 972783.08 frames.], batch size: 23, lr: 9.30e-04
2022-05-03 22:54:18,185 INFO [train.py:715] (4/8) Epoch 1, batch 15450, loss[loss=0.1613, simple_loss=0.2345, pruned_loss=0.04404, over 4816.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2494, pruned_loss=0.06158, over 972691.50 frames.], batch size: 25, lr: 9.30e-04
2022-05-03 22:54:58,660 INFO [train.py:715] (4/8) Epoch 1, batch 15500, loss[loss=0.2017, simple_loss=0.2777, pruned_loss=0.06286, over 4816.00 frames.], tot_loss[loss=0.187, simple_loss=0.25, pruned_loss=0.06199, over 971275.84 frames.], batch size: 25, lr: 9.29e-04
2022-05-03 22:55:37,752 INFO [train.py:715] (4/8) Epoch 1, batch 15550, loss[loss=0.1793, simple_loss=0.2449, pruned_loss=0.05688, over 4941.00 frames.], tot_loss[loss=0.1878, simple_loss=0.2505, pruned_loss=0.06257, over 971937.41 frames.], batch size: 29, lr: 9.29e-04
2022-05-03 22:56:18,079 INFO [train.py:715] (4/8) Epoch 1, batch 15600, loss[loss=0.1752, simple_loss=0.2318, pruned_loss=0.05936, over 4742.00 frames.], tot_loss[loss=0.1882, simple_loss=0.2511, pruned_loss=0.06264, over 972520.50 frames.], batch size: 16, lr: 9.28e-04
2022-05-03 22:56:58,369 INFO [train.py:715] (4/8) Epoch 1, batch 15650, loss[loss=0.1909, simple_loss=0.2435, pruned_loss=0.06914, over 4968.00 frames.], tot_loss[loss=0.1873, simple_loss=0.2504, pruned_loss=0.06207, over 972669.47 frames.], batch size: 24, lr: 9.28e-04
2022-05-03 22:57:38,292 INFO [train.py:715] (4/8) Epoch 1, batch 15700, loss[loss=0.1968, simple_loss=0.2529, pruned_loss=0.07031, over 4971.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2505, pruned_loss=0.06193, over 973082.14 frames.], batch size: 35, lr: 9.27e-04
2022-05-03 22:58:17,928 INFO [train.py:715] (4/8) Epoch 1, batch 15750, loss[loss=0.1898, simple_loss=0.2458, pruned_loss=0.06688, over 4826.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2505, pruned_loss=0.06228, over 973138.21 frames.], batch size: 30, lr: 9.27e-04
2022-05-03 22:58:58,211 INFO [train.py:715] (4/8) Epoch 1, batch 15800, loss[loss=0.2271, simple_loss=0.2888, pruned_loss=0.08271, over 4877.00 frames.], tot_loss[loss=0.1871, simple_loss=0.2503, pruned_loss=0.06194, over 973769.58 frames.], batch size: 22, lr: 9.27e-04
2022-05-03 22:59:38,893 INFO [train.py:715] (4/8) Epoch 1, batch 15850, loss[loss=0.2585, simple_loss=0.2928, pruned_loss=0.1121, over 4638.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2505, pruned_loss=0.06191, over 973446.17 frames.], batch size: 13, lr: 9.26e-04
2022-05-03 23:00:18,432 INFO [train.py:715] (4/8) Epoch 1, batch 15900, loss[loss=0.1568, simple_loss=0.2274, pruned_loss=0.0431, over 4858.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2493, pruned_loss=0.06126, over 973156.13 frames.], batch size: 34, lr: 9.26e-04
2022-05-03 23:00:58,070 INFO [train.py:715] (4/8) Epoch 1, batch 15950, loss[loss=0.2049, simple_loss=0.2602, pruned_loss=0.07477, over 4837.00 frames.], tot_loss[loss=0.185, simple_loss=0.2481, pruned_loss=0.0609, over 972801.34 frames.], batch size: 30, lr: 9.25e-04
2022-05-03 23:01:37,502 INFO [train.py:715] (4/8) Epoch 1, batch 16000, loss[loss=0.1839, simple_loss=0.2523, pruned_loss=0.05779, over 4795.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2494, pruned_loss=0.06165, over 972593.06 frames.], batch size: 13, lr: 9.25e-04
2022-05-03 23:02:16,258 INFO [train.py:715] (4/8) Epoch 1, batch 16050, loss[loss=0.1713, simple_loss=0.2454, pruned_loss=0.04862, over 4838.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2494, pruned_loss=0.06139, over 972026.13 frames.], batch size: 32, lr: 9.24e-04
2022-05-03 23:02:55,585 INFO [train.py:715] (4/8) Epoch 1, batch 16100, loss[loss=0.1793, simple_loss=0.2358, pruned_loss=0.0614, over 4692.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2491, pruned_loss=0.06128, over 971551.16 frames.], batch size: 15, lr: 9.24e-04
2022-05-03 23:03:35,230 INFO [train.py:715] (4/8) Epoch 1, batch 16150, loss[loss=0.1961, simple_loss=0.2515, pruned_loss=0.07034, over 4795.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2496, pruned_loss=0.06177, over 971318.31 frames.], batch size: 14, lr: 9.23e-04
2022-05-03 23:04:15,420 INFO [train.py:715] (4/8) Epoch 1, batch 16200, loss[loss=0.1735, simple_loss=0.2446, pruned_loss=0.05123, over 4760.00 frames.], tot_loss[loss=0.1869, simple_loss=0.2498, pruned_loss=0.06197, over 972134.41 frames.], batch size: 18, lr: 9.23e-04
2022-05-03 23:04:53,726 INFO [train.py:715] (4/8) Epoch 1, batch 16250, loss[loss=0.1775, simple_loss=0.2428, pruned_loss=0.05612, over 4974.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2496, pruned_loss=0.06163, over 971932.04 frames.], batch size: 15, lr: 9.22e-04
2022-05-03 23:05:33,191 INFO [train.py:715] (4/8) Epoch 1, batch 16300, loss[loss=0.2486, simple_loss=0.293, pruned_loss=0.102, over 4816.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2502, pruned_loss=0.06206, over 971664.15 frames.], batch size: 21, lr: 9.22e-04
2022-05-03 23:06:12,741 INFO [train.py:715] (4/8) Epoch 1, batch 16350, loss[loss=0.2272, simple_loss=0.2783, pruned_loss=0.08805, over 4933.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2507, pruned_loss=0.06216, over 972129.18 frames.], batch size: 29, lr: 9.22e-04
2022-05-03 23:06:51,398 INFO [train.py:715] (4/8) Epoch 1, batch 16400, loss[loss=0.1978, simple_loss=0.2675, pruned_loss=0.06405, over 4808.00 frames.], tot_loss[loss=0.1875, simple_loss=0.2505, pruned_loss=0.06219, over 971914.25 frames.], batch size: 25, lr: 9.21e-04
2022-05-03 23:07:30,895 INFO [train.py:715] (4/8) Epoch 1, batch 16450, loss[loss=0.2019, simple_loss=0.2633, pruned_loss=0.07021, over 4979.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2492, pruned_loss=0.06116, over 972187.18 frames.], batch size: 24, lr: 9.21e-04
2022-05-03 23:08:10,541 INFO [train.py:715] (4/8) Epoch 1, batch 16500, loss[loss=0.1802, simple_loss=0.2429, pruned_loss=0.05876, over 4803.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2496, pruned_loss=0.06094, over 972430.59 frames.], batch size: 24, lr: 9.20e-04
2022-05-03 23:08:50,453 INFO [train.py:715] (4/8) Epoch 1, batch 16550, loss[loss=0.1874, simple_loss=0.2613, pruned_loss=0.05678, over 4968.00 frames.], tot_loss[loss=0.1848, simple_loss=0.2485, pruned_loss=0.0605, over 972058.74 frames.], batch size: 28, lr: 9.20e-04
2022-05-03 23:09:28,844 INFO [train.py:715] (4/8) Epoch 1, batch 16600, loss[loss=0.1681, simple_loss=0.2406, pruned_loss=0.04779, over 4978.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2478, pruned_loss=0.06037, over 972500.62 frames.], batch size: 28, lr: 9.19e-04
2022-05-03 23:10:09,003 INFO [train.py:715] (4/8) Epoch 1, batch 16650, loss[loss=0.1952, simple_loss=0.2549, pruned_loss=0.06773, over 4907.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2474, pruned_loss=0.06049, over 972633.45 frames.], batch size: 38, lr: 9.19e-04
2022-05-03 23:10:48,682 INFO [train.py:715] (4/8) Epoch 1, batch 16700, loss[loss=0.1558, simple_loss=0.2326, pruned_loss=0.03947, over 4756.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2474, pruned_loss=0.05992, over 972162.98 frames.], batch size: 16, lr: 9.18e-04
2022-05-03 23:11:28,441 INFO [train.py:715] (4/8) Epoch 1, batch 16750, loss[loss=0.1754, simple_loss=0.241, pruned_loss=0.05486, over 4798.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2473, pruned_loss=0.05978, over 971462.06 frames.], batch size: 24, lr: 9.18e-04
2022-05-03 23:12:08,271 INFO [train.py:715] (4/8) Epoch 1, batch 16800, loss[loss=0.1662, simple_loss=0.238, pruned_loss=0.04723, over 4962.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2473, pruned_loss=0.05975, over 971179.65 frames.], batch size: 24, lr: 9.18e-04
2022-05-03 23:12:47,925 INFO [train.py:715] (4/8) Epoch 1, batch 16850, loss[loss=0.1747, simple_loss=0.2499, pruned_loss=0.04969, over 4945.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2474, pruned_loss=0.06059, over 972083.96 frames.], batch size: 23, lr: 9.17e-04
2022-05-03 23:13:27,907 INFO [train.py:715] (4/8) Epoch 1, batch 16900, loss[loss=0.1728, simple_loss=0.2407, pruned_loss=0.05246, over 4890.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2475, pruned_loss=0.06061, over 971810.47 frames.], batch size: 19, lr: 9.17e-04
2022-05-03 23:14:06,929 INFO [train.py:715] (4/8) Epoch 1, batch 16950, loss[loss=0.186, simple_loss=0.254, pruned_loss=0.05897, over 4944.00 frames.], tot_loss[loss=0.186, simple_loss=0.2486, pruned_loss=0.06168, over 971555.67 frames.], batch size: 21, lr: 9.16e-04
2022-05-03 23:14:46,346 INFO [train.py:715] (4/8) Epoch 1, batch 17000, loss[loss=0.1833, simple_loss=0.2484, pruned_loss=0.0591, over 4958.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2478, pruned_loss=0.0612, over 972024.65 frames.], batch size: 24, lr: 9.16e-04
2022-05-03 23:15:26,357 INFO [train.py:715] (4/8) Epoch 1, batch 17050, loss[loss=0.2048, simple_loss=0.2788, pruned_loss=0.0654, over 4916.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2486, pruned_loss=0.06128, over 972927.19 frames.], batch size: 29, lr: 9.15e-04
2022-05-03 23:16:05,140 INFO [train.py:715] (4/8) Epoch 1, batch 17100, loss[loss=0.1968, simple_loss=0.25, pruned_loss=0.07182, over 4933.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2484, pruned_loss=0.06147, over 972177.96 frames.], batch size: 23, lr: 9.15e-04
2022-05-03 23:16:44,847 INFO [train.py:715] (4/8) Epoch 1, batch 17150, loss[loss=0.2245, simple_loss=0.2927, pruned_loss=0.07812, over 4782.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2487, pruned_loss=0.06114, over 972622.45 frames.], batch size: 18, lr: 9.15e-04
2022-05-03 23:17:25,478 INFO [train.py:715] (4/8) Epoch 1, batch 17200, loss[loss=0.1996, simple_loss=0.2618, pruned_loss=0.06874, over 4781.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2488, pruned_loss=0.06073, over 972146.92 frames.], batch size: 18, lr: 9.14e-04
2022-05-03 23:18:05,277 INFO [train.py:715] (4/8) Epoch 1, batch 17250, loss[loss=0.2249, simple_loss=0.2799, pruned_loss=0.08492, over 4716.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2493, pruned_loss=0.06096, over 972370.65 frames.], batch size: 15, lr: 9.14e-04
2022-05-03 23:18:43,787 INFO [train.py:715] (4/8) Epoch 1, batch 17300, loss[loss=0.2088, simple_loss=0.2719, pruned_loss=0.07287, over 4934.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2493, pruned_loss=0.06101, over 972455.74 frames.], batch size: 29, lr: 9.13e-04
2022-05-03 23:19:23,810 INFO [train.py:715] (4/8) Epoch 1, batch 17350, loss[loss=0.2125, simple_loss=0.2642, pruned_loss=0.08041, over 4899.00 frames.], tot_loss[loss=0.1857, simple_loss=0.2495, pruned_loss=0.0609, over 971835.11 frames.], batch size: 16, lr: 9.13e-04
2022-05-03 23:20:03,642 INFO [train.py:715] (4/8) Epoch 1, batch 17400, loss[loss=0.1758, simple_loss=0.2458, pruned_loss=0.05286, over 4985.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2495, pruned_loss=0.06101, over 972120.26 frames.], batch size: 15, lr: 9.12e-04
2022-05-03 23:20:42,896 INFO [train.py:715] (4/8) Epoch 1, batch 17450, loss[loss=0.1871, simple_loss=0.2445, pruned_loss=0.06481, over 4816.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2489, pruned_loss=0.06082, over 972033.65 frames.], batch size: 25, lr: 9.12e-04
2022-05-03 23:21:23,295 INFO [train.py:715] (4/8) Epoch 1, batch 17500, loss[loss=0.1877, simple_loss=0.2556, pruned_loss=0.05989, over 4900.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2472, pruned_loss=0.05967, over 971749.08 frames.], batch size: 17, lr: 9.11e-04
2022-05-03 23:22:03,723 INFO [train.py:715] (4/8) Epoch 1, batch 17550, loss[loss=0.1631, simple_loss=0.2303, pruned_loss=0.04791, over 4825.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2481, pruned_loss=0.06049, over 970403.97 frames.], batch size: 30, lr: 9.11e-04
2022-05-03 23:22:44,345 INFO [train.py:715] (4/8) Epoch 1, batch 17600, loss[loss=0.1536, simple_loss=0.2282, pruned_loss=0.03949, over 4923.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2488, pruned_loss=0.06109, over 970697.90 frames.], batch size: 29, lr: 9.11e-04
2022-05-03 23:23:24,040 INFO [train.py:715] (4/8) Epoch 1, batch 17650, loss[loss=0.1562, simple_loss=0.2153, pruned_loss=0.04859, over 4854.00 frames.], tot_loss[loss=0.184, simple_loss=0.2473, pruned_loss=0.06038, over 971018.24 frames.], batch size: 30, lr: 9.10e-04
2022-05-03 23:24:04,738 INFO [train.py:715] (4/8) Epoch 1, batch 17700, loss[loss=0.1652, simple_loss=0.2324, pruned_loss=0.04903, over 4852.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2462, pruned_loss=0.0595, over 971264.14 frames.], batch size: 26, lr: 9.10e-04
2022-05-03 23:24:44,982 INFO [train.py:715] (4/8) Epoch 1, batch 17750, loss[loss=0.2059, simple_loss=0.2606, pruned_loss=0.07562, over 4824.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2473, pruned_loss=0.06051, over 971475.64 frames.], batch size: 26, lr: 9.09e-04
2022-05-03 23:25:24,520 INFO [train.py:715] (4/8) Epoch 1, batch 17800, loss[loss=0.1914, simple_loss=0.2563, pruned_loss=0.06329, over 4766.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2483, pruned_loss=0.06054, over 971238.76 frames.], batch size: 14, lr: 9.09e-04
2022-05-03 23:26:04,929 INFO [train.py:715] (4/8) Epoch 1, batch 17850, loss[loss=0.1772, simple_loss=0.2364, pruned_loss=0.05903, over 4832.00 frames.], tot_loss[loss=0.1842, simple_loss=0.248, pruned_loss=0.06023, over 970873.27 frames.], batch size: 15, lr: 9.08e-04
2022-05-03 23:26:44,323 INFO [train.py:715] (4/8) Epoch 1, batch 17900, loss[loss=0.1835, simple_loss=0.2469, pruned_loss=0.0601, over 4896.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2484, pruned_loss=0.06055, over 971147.86 frames.], batch size: 19, lr: 9.08e-04
2022-05-03 23:27:23,561 INFO [train.py:715] (4/8) Epoch 1, batch 17950, loss[loss=0.1806, simple_loss=0.2405, pruned_loss=0.0603, over 4957.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2487, pruned_loss=0.06125, over 971755.61 frames.], batch size: 24, lr: 9.08e-04
2022-05-03 23:28:02,859 INFO [train.py:715] (4/8) Epoch 1, batch 18000, loss[loss=0.1586, simple_loss=0.2205, pruned_loss=0.04833, over 4771.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2493, pruned_loss=0.06169, over 972341.55 frames.], batch size: 17, lr: 9.07e-04
2022-05-03 23:28:02,859 INFO [train.py:733] (4/8) Computing validation loss
2022-05-03 23:28:17,469 INFO [train.py:742] (4/8) Epoch 1, validation: loss=0.123, simple_loss=0.21, pruned_loss=0.01804, over 914524.00 frames.
2022-05-03 23:28:56,681 INFO [train.py:715] (4/8) Epoch 1, batch 18050, loss[loss=0.172, simple_loss=0.2334, pruned_loss=0.05527, over 4837.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2494, pruned_loss=0.06165, over 972553.78 frames.], batch size: 13, lr: 9.07e-04
2022-05-03 23:29:37,116 INFO [train.py:715] (4/8) Epoch 1, batch 18100, loss[loss=0.2414, simple_loss=0.3103, pruned_loss=0.08627, over 4867.00 frames.], tot_loss[loss=0.1861, simple_loss=0.2494, pruned_loss=0.06138, over 973971.81 frames.], batch size: 16, lr: 9.06e-04
2022-05-03 23:30:16,932 INFO [train.py:715] (4/8) Epoch 1, batch 18150, loss[loss=0.1917, simple_loss=0.2655, pruned_loss=0.05894, over 4955.00 frames.], tot_loss[loss=0.1864, simple_loss=0.2499, pruned_loss=0.06148, over 973204.39 frames.], batch size: 24, lr: 9.06e-04
2022-05-03 23:30:55,302 INFO [train.py:715] (4/8) Epoch 1, batch 18200, loss[loss=0.1807, simple_loss=0.2494, pruned_loss=0.05599, over 4805.00 frames.], tot_loss[loss=0.1853, simple_loss=0.249, pruned_loss=0.06081, over 973031.64 frames.], batch size: 21, lr: 9.05e-04
2022-05-03 23:31:34,987 INFO [train.py:715] (4/8) Epoch 1, batch 18250, loss[loss=0.184, simple_loss=0.2436, pruned_loss=0.0622, over 4785.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2495, pruned_loss=0.06183, over 973045.26 frames.], batch size: 17, lr: 9.05e-04
2022-05-03 23:32:14,614 INFO [train.py:715] (4/8) Epoch 1, batch 18300, loss[loss=0.1786, simple_loss=0.253, pruned_loss=0.05209, over 4984.00 frames.], tot_loss[loss=0.1872, simple_loss=0.2502, pruned_loss=0.06212, over 971677.89 frames.], batch size: 25, lr: 9.05e-04
2022-05-03 23:32:53,399 INFO [train.py:715] (4/8) Epoch 1, batch 18350, loss[loss=0.1895, simple_loss=0.251, pruned_loss=0.06403, over 4961.00 frames.], tot_loss[loss=0.1865, simple_loss=0.2494, pruned_loss=0.06179, over 971736.03 frames.], batch size: 21, lr: 9.04e-04
2022-05-03 23:33:33,133 INFO [train.py:715] (4/8) Epoch 1, batch 18400, loss[loss=0.2091, simple_loss=0.2681, pruned_loss=0.07506, over 4978.00 frames.], tot_loss[loss=0.1867, simple_loss=0.2497, pruned_loss=0.06183, over 971984.38 frames.], batch size: 25, lr: 9.04e-04
2022-05-03 23:34:13,410 INFO [train.py:715] (4/8) Epoch 1, batch 18450, loss[loss=0.1946, simple_loss=0.2717, pruned_loss=0.05873, over 4832.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2504, pruned_loss=0.06217, over 971417.78 frames.], batch size: 27, lr: 9.03e-04
2022-05-03 23:34:52,237 INFO [train.py:715] (4/8) Epoch 1, batch 18500, loss[loss=0.1846, simple_loss=0.2402, pruned_loss=0.06456, over 4704.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2497, pruned_loss=0.06176, over 971246.71 frames.], batch size: 15, lr: 9.03e-04
2022-05-03 23:35:31,271 INFO [train.py:715] (4/8) Epoch 1, batch 18550, loss[loss=0.1911, simple_loss=0.2568, pruned_loss=0.06268, over 4923.00 frames.], tot_loss[loss=0.1874, simple_loss=0.2503, pruned_loss=0.06219, over 970429.74 frames.], batch size: 23, lr: 9.03e-04
2022-05-03 23:36:11,451 INFO [train.py:715] (4/8) Epoch 1, batch 18600, loss[loss=0.1762, simple_loss=0.2414, pruned_loss=0.05545, over 4883.00 frames.], tot_loss[loss=0.1866, simple_loss=0.2496, pruned_loss=0.06178, over 970638.96 frames.], batch size: 22, lr: 9.02e-04
2022-05-03 23:36:50,769 INFO [train.py:715] (4/8) Epoch 1, batch 18650, loss[loss=0.1904, simple_loss=0.2481, pruned_loss=0.06638, over 4876.00 frames.], tot_loss[loss=0.1868, simple_loss=0.2501, pruned_loss=0.06171, over 971756.52 frames.], batch size: 16, lr: 9.02e-04
2022-05-03 23:37:29,514 INFO [train.py:715] (4/8) Epoch 1, batch 18700, loss[loss=0.1622, simple_loss=0.2322, pruned_loss=0.04605, over 4962.00 frames.], tot_loss[loss=0.1859, simple_loss=0.2497, pruned_loss=0.06109, over 972338.25 frames.], batch size: 15, lr: 9.01e-04
2022-05-03 23:38:08,760 INFO [train.py:715] (4/8) Epoch 1, batch 18750, loss[loss=0.1849, simple_loss=0.2371, pruned_loss=0.06634, over 4967.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2486, pruned_loss=0.06017, over 972680.14 frames.], batch size: 15, lr: 9.01e-04
2022-05-03 23:38:48,687 INFO [train.py:715] (4/8) Epoch 1, batch 18800, loss[loss=0.1845, simple_loss=0.2498, pruned_loss=0.05959, over 4969.00 frames.], tot_loss[loss=0.1862, simple_loss=0.2497, pruned_loss=0.06134, over 973450.14 frames.], batch size: 24, lr: 9.00e-04
2022-05-03 23:39:27,387 INFO [train.py:715] (4/8) Epoch 1, batch 18850, loss[loss=0.1556, simple_loss=0.2295, pruned_loss=0.04084, over 4819.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2488, pruned_loss=0.06084, over 972313.37 frames.], batch size: 25, lr: 9.00e-04
2022-05-03 23:40:06,873 INFO [train.py:715] (4/8) Epoch 1, batch 18900, loss[loss=0.2231, simple_loss=0.2867, pruned_loss=0.07971, over 4693.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2488, pruned_loss=0.06102, over 971908.22 frames.], batch size: 15, lr: 9.00e-04
2022-05-03 23:40:46,607 INFO [train.py:715] (4/8) Epoch 1, batch 18950, loss[loss=0.1815, simple_loss=0.2441, pruned_loss=0.05946, over 4944.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2477, pruned_loss=0.06058, over 972515.70 frames.], batch size: 39, lr: 8.99e-04
2022-05-03 23:41:25,994 INFO [train.py:715] (4/8) Epoch 1, batch 19000, loss[loss=0.2167, simple_loss=0.2674, pruned_loss=0.08305, over 4852.00 frames.], tot_loss[loss=0.1855, simple_loss=0.2485, pruned_loss=0.06123, over 971773.76 frames.], batch size: 32, lr: 8.99e-04
2022-05-03 23:42:05,675 INFO [train.py:715] (4/8) Epoch 1, batch 19050, loss[loss=0.1952, simple_loss=0.2645, pruned_loss=0.06295, over 4809.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2487, pruned_loss=0.06094, over 972312.73 frames.], batch size: 21, lr: 8.98e-04
2022-05-03 23:42:44,847 INFO [train.py:715] (4/8) Epoch 1, batch 19100, loss[loss=0.1503, simple_loss=0.2144, pruned_loss=0.0431, over 4851.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2485, pruned_loss=0.06106, over 972362.33 frames.], batch size: 20, lr: 8.98e-04
2022-05-03 23:43:24,773 INFO [train.py:715] (4/8) Epoch 1, batch 19150, loss[loss=0.1945, simple_loss=0.2516, pruned_loss=0.06867, over 4831.00 frames.], tot_loss[loss=0.186, simple_loss=0.249, pruned_loss=0.06151, over 973052.57 frames.], batch size: 26, lr: 8.98e-04
2022-05-03 23:44:03,412 INFO [train.py:715] (4/8) Epoch 1, batch 19200, loss[loss=0.1777, simple_loss=0.2368, pruned_loss=0.05933, over 4901.00 frames.], tot_loss[loss=0.1853, simple_loss=0.2489, pruned_loss=0.06091, over 973556.89 frames.], batch size: 17, lr: 8.97e-04
2022-05-03 23:44:42,696 INFO [train.py:715] (4/8) Epoch 1, batch 19250, loss[loss=0.1629, simple_loss=0.2314, pruned_loss=0.04725, over 4696.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2483, pruned_loss=0.06047, over 973455.77 frames.], batch size: 15, lr: 8.97e-04
2022-05-03 23:45:23,326 INFO [train.py:715] (4/8) Epoch 1, batch 19300, loss[loss=0.218, simple_loss=0.2858, pruned_loss=0.07509, over 4784.00 frames.], tot_loss[loss=0.1841, simple_loss=0.248, pruned_loss=0.06006, over 972988.14 frames.], batch size: 18, lr: 8.96e-04
2022-05-03 23:46:02,786 INFO [train.py:715] (4/8) Epoch 1, batch 19350, loss[loss=0.2091, simple_loss=0.2712, pruned_loss=0.07357, over 4709.00 frames.], tot_loss[loss=0.184, simple_loss=0.2474, pruned_loss=0.06025, over 972896.47 frames.], batch size: 15, lr: 8.96e-04
2022-05-03 23:46:41,169 INFO [train.py:715] (4/8) Epoch 1, batch 19400, loss[loss=0.175, simple_loss=0.2348, pruned_loss=0.05764, over 4858.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2478, pruned_loss=0.06075, over 972132.32 frames.], batch size: 30, lr: 8.95e-04
2022-05-03 23:47:20,595 INFO [train.py:715] (4/8) Epoch 1, batch 19450, loss[loss=0.1387, simple_loss=0.2002, pruned_loss=0.03864, over 4843.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2468, pruned_loss=0.06007, over 971575.88 frames.], batch size: 13, lr: 8.95e-04
2022-05-03 23:48:00,485 INFO [train.py:715] (4/8) Epoch 1, batch 19500, loss[loss=0.1452, simple_loss=0.2124, pruned_loss=0.03901, over 4915.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2465, pruned_loss=0.05985, over 971777.89 frames.], batch size: 17, lr: 8.95e-04
2022-05-03 23:48:39,201 INFO [train.py:715] (4/8) Epoch 1, batch 19550, loss[loss=0.1913, simple_loss=0.2523, pruned_loss=0.06519, over 4961.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2467, pruned_loss=0.05957, over 971403.57 frames.], batch size: 15, lr: 8.94e-04
2022-05-03 23:49:18,325 INFO [train.py:715] (4/8) Epoch 1, batch 19600, loss[loss=0.1655, simple_loss=0.2372, pruned_loss=0.04688, over 4837.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2461, pruned_loss=0.05887, over 972426.26 frames.], batch size: 13, lr: 8.94e-04
2022-05-03 23:49:58,545 INFO [train.py:715] (4/8) Epoch 1, batch 19650, loss[loss=0.2024, simple_loss=0.2525, pruned_loss=0.07616, over 4785.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2461, pruned_loss=0.05929, over 972698.37 frames.], batch size: 18, lr: 8.93e-04
2022-05-03 23:50:37,446 INFO [train.py:715] (4/8) Epoch 1, batch 19700, loss[loss=0.1634, simple_loss=0.2414, pruned_loss=0.04271, over 4854.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2464, pruned_loss=0.05924, over 972804.89 frames.], batch size: 20, lr: 8.93e-04
2022-05-03 23:51:16,597 INFO [train.py:715] (4/8) Epoch 1, batch 19750, loss[loss=0.169, simple_loss=0.241, pruned_loss=0.04853, over 4803.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2474, pruned_loss=0.05987, over 972281.40 frames.], batch size: 26, lr: 8.93e-04
2022-05-03 23:51:56,238 INFO [train.py:715] (4/8) Epoch 1, batch 19800, loss[loss=0.2093, simple_loss=0.2619, pruned_loss=0.07834, over 4817.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2487, pruned_loss=0.06072, over 972635.00 frames.], batch size: 25, lr: 8.92e-04
2022-05-03 23:52:36,506 INFO [train.py:715] (4/8) Epoch 1, batch 19850, loss[loss=0.1959, simple_loss=0.252, pruned_loss=0.06986, over 4918.00 frames.], tot_loss[loss=0.184, simple_loss=0.2475, pruned_loss=0.06023, over 972484.98 frames.], batch size: 18, lr: 8.92e-04
2022-05-03 23:53:15,890 INFO [train.py:715] (4/8) Epoch 1, batch 19900, loss[loss=0.1733, simple_loss=0.2415, pruned_loss=0.05255, over 4879.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2467, pruned_loss=0.05986, over 972434.18 frames.], batch size: 16, lr: 8.91e-04
2022-05-03 23:53:54,987 INFO [train.py:715] (4/8) Epoch 1, batch 19950, loss[loss=0.1929, simple_loss=0.2519, pruned_loss=0.06695, over 4849.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2471, pruned_loss=0.05996, over 971933.27 frames.], batch size: 20, lr: 8.91e-04
2022-05-03 23:54:35,250 INFO [train.py:715] (4/8) Epoch 1, batch 20000, loss[loss=0.1802, simple_loss=0.2638, pruned_loss=0.04826, over 4867.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2466, pruned_loss=0.05993, over 972346.65 frames.], batch size: 20, lr: 8.91e-04
2022-05-03 23:55:14,864 INFO [train.py:715] (4/8) Epoch 1, batch 20050, loss[loss=0.208, simple_loss=0.2608, pruned_loss=0.07763, over 4858.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2475, pruned_loss=0.06047, over 972374.25 frames.], batch size: 30, lr: 8.90e-04
2022-05-03 23:55:54,267 INFO [train.py:715] (4/8) Epoch 1, batch 20100, loss[loss=0.1652, simple_loss=0.2382, pruned_loss=0.04604, over 4767.00 frames.], tot_loss[loss=0.1838, simple_loss=0.247, pruned_loss=0.06036, over 972099.34 frames.], batch size: 19, lr: 8.90e-04
2022-05-03 23:56:34,284 INFO [train.py:715] (4/8) Epoch 1, batch 20150, loss[loss=0.1576, simple_loss=0.2323, pruned_loss=0.04142, over 4778.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2473, pruned_loss=0.06019, over 971758.86 frames.], batch size: 18, lr: 8.89e-04
2022-05-03 23:57:15,157 INFO [train.py:715] (4/8) Epoch 1, batch 20200, loss[loss=0.206, simple_loss=0.2631, pruned_loss=0.07442, over 4850.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2472, pruned_loss=0.06021, over 972079.36 frames.], batch size: 30, lr: 8.89e-04
2022-05-03 23:57:53,971 INFO [train.py:715] (4/8) Epoch 1, batch 20250, loss[loss=0.1853, simple_loss=0.2586, pruned_loss=0.056, over 4754.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2482, pruned_loss=0.06027, over 971621.85 frames.], batch size: 14, lr: 8.89e-04
2022-05-03 23:58:33,270 INFO [train.py:715] (4/8) Epoch 1, batch 20300, loss[loss=0.1627, simple_loss=0.2404, pruned_loss=0.04251, over 4982.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2483, pruned_loss=0.06016, over 972372.63 frames.], batch size: 28, lr: 8.88e-04
2022-05-03 23:59:13,198 INFO [train.py:715] (4/8) Epoch 1, batch 20350, loss[loss=0.139, simple_loss=0.2032, pruned_loss=0.03744, over 4851.00 frames.], tot_loss[loss=0.184, simple_loss=0.2482, pruned_loss=0.0599, over 973473.20 frames.], batch size: 20, lr: 8.88e-04
2022-05-03 23:59:51,741 INFO [train.py:715] (4/8) Epoch 1, batch 20400, loss[loss=0.1926, simple_loss=0.2544, pruned_loss=0.06537, over 4938.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2473, pruned_loss=0.05985, over 972489.89 frames.], batch size: 23, lr: 8.87e-04
2022-05-04 00:00:31,296 INFO [train.py:715] (4/8) Epoch 1, batch 20450, loss[loss=0.16, simple_loss=0.2276, pruned_loss=0.04621, over 4784.00 frames.], tot_loss[loss=0.183, simple_loss=0.2469, pruned_loss=0.05955, over 971986.59 frames.], batch size: 12, lr: 8.87e-04
2022-05-04 00:01:10,342 INFO [train.py:715] (4/8) Epoch 1, batch 20500, loss[loss=0.2026, simple_loss=0.2796, pruned_loss=0.06278, over 4753.00 frames.], tot_loss[loss=0.184, simple_loss=0.2475, pruned_loss=0.0602, over 972036.93 frames.], batch size: 19, lr: 8.87e-04
2022-05-04 00:01:50,042 INFO [train.py:715] (4/8) Epoch 1, batch 20550, loss[loss=0.204, simple_loss=0.2733, pruned_loss=0.06736, over 4763.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2477, pruned_loss=0.06004, over 972916.50 frames.], batch size: 19, lr: 8.86e-04
2022-05-04 00:02:28,927 INFO [train.py:715] (4/8) Epoch 1, batch 20600, loss[loss=0.1704, simple_loss=0.2382, pruned_loss=0.05134, over 4927.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2478, pruned_loss=0.06033, over 972420.61 frames.], batch size: 23, lr: 8.86e-04
2022-05-04 00:03:08,467 INFO [train.py:715] (4/8) Epoch 1, batch 20650, loss[loss=0.1969, simple_loss=0.2632, pruned_loss=0.06533, over 4935.00 frames.], tot_loss[loss=0.184, simple_loss=0.2474, pruned_loss=0.06023, over 972257.88 frames.], batch size: 21, lr: 8.85e-04
2022-05-04 00:03:48,955 INFO [train.py:715] (4/8) Epoch 1, batch 20700, loss[loss=0.2638, simple_loss=0.3221, pruned_loss=0.1028, over 4932.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2474, pruned_loss=0.05982, over 971811.66 frames.], batch size: 39, lr: 8.85e-04
2022-05-04 00:04:28,576 INFO [train.py:715] (4/8) Epoch 1, batch 20750, loss[loss=0.199, simple_loss=0.2567, pruned_loss=0.07065, over 4795.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2474, pruned_loss=0.05971, over 972077.70 frames.], batch size: 18, lr: 8.85e-04
2022-05-04 00:05:07,877 INFO [train.py:715] (4/8) Epoch 1, batch 20800, loss[loss=0.1837, simple_loss=0.2524, pruned_loss=0.05753, over 4931.00 frames.], tot_loss[loss=0.183, simple_loss=0.2465, pruned_loss=0.05972, over 972315.54 frames.], batch size: 29, lr: 8.84e-04
2022-05-04 00:05:47,728 INFO [train.py:715] (4/8) Epoch 1, batch 20850, loss[loss=0.1779, simple_loss=0.2528, pruned_loss=0.05152, over 4878.00 frames.], tot_loss[loss=0.184, simple_loss=0.2472, pruned_loss=0.06046, over 971600.58 frames.], batch size: 13, lr: 8.84e-04
2022-05-04 00:06:27,484 INFO [train.py:715] (4/8) Epoch 1, batch 20900, loss[loss=0.2173, simple_loss=0.2624, pruned_loss=0.08608, over 4836.00 frames.], tot_loss[loss=0.185, simple_loss=0.2481, pruned_loss=0.06095, over 972226.84 frames.], batch size: 30, lr: 8.83e-04
2022-05-04 00:07:06,274 INFO [train.py:715] (4/8) Epoch 1, batch 20950, loss[loss=0.2202, simple_loss=0.2862, pruned_loss=0.07705, over 4946.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2477, pruned_loss=0.06052, over 972240.74 frames.], batch size: 21, lr: 8.83e-04
2022-05-04 00:07:45,659 INFO [train.py:715] (4/8) Epoch 1, batch 21000, loss[loss=0.171, simple_loss=0.2439, pruned_loss=0.04906, over 4751.00 frames.], tot_loss[loss=0.1851, simple_loss=0.2485, pruned_loss=0.06082, over 971067.53 frames.], batch size: 16, lr: 8.83e-04
2022-05-04 00:07:45,660 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 00:08:00,761 INFO [train.py:742] (4/8) Epoch 1, validation: loss=0.1226, simple_loss=0.2094, pruned_loss=0.01784, over 914524.00 frames.
2022-05-04 00:08:40,111 INFO [train.py:715] (4/8) Epoch 1, batch 21050, loss[loss=0.2122, simple_loss=0.2788, pruned_loss=0.07282, over 4918.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2479, pruned_loss=0.06026, over 971091.01 frames.], batch size: 29, lr: 8.82e-04
2022-05-04 00:09:19,948 INFO [train.py:715] (4/8) Epoch 1, batch 21100, loss[loss=0.1758, simple_loss=0.2396, pruned_loss=0.056, over 4929.00 frames.], tot_loss[loss=0.1847, simple_loss=0.2483, pruned_loss=0.06053, over 971384.15 frames.], batch size: 29, lr: 8.82e-04
2022-05-04 00:09:58,321 INFO [train.py:715] (4/8) Epoch 1, batch 21150, loss[loss=0.1997, simple_loss=0.2607, pruned_loss=0.06933, over 4859.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2476, pruned_loss=0.06015, over 971424.69 frames.], batch size: 20, lr: 8.81e-04
2022-05-04 00:10:40,730 INFO [train.py:715] (4/8) Epoch 1, batch 21200, loss[loss=0.1642, simple_loss=0.2342, pruned_loss=0.04714, over 4897.00 frames.], tot_loss[loss=0.184, simple_loss=0.2478, pruned_loss=0.06014, over 971414.37 frames.], batch size: 17, lr: 8.81e-04
2022-05-04 00:11:20,089 INFO [train.py:715] (4/8) Epoch 1, batch 21250, loss[loss=0.135, simple_loss=0.209, pruned_loss=0.0305, over 4874.00 frames.], tot_loss[loss=0.1838, simple_loss=0.2477, pruned_loss=0.05992, over 971934.11 frames.], batch size: 16, lr: 8.81e-04
2022-05-04 00:11:59,258 INFO [train.py:715] (4/8) Epoch 1, batch 21300, loss[loss=0.1672, simple_loss=0.2367, pruned_loss=0.04888, over 4645.00 frames.], tot_loss[loss=0.1854, simple_loss=0.2486, pruned_loss=0.06111, over 971584.34 frames.], batch size: 13, lr: 8.80e-04
2022-05-04 00:12:38,146 INFO [train.py:715] (4/8) Epoch 1, batch 21350, loss[loss=0.1471, simple_loss=0.2134, pruned_loss=0.04039, over 4854.00 frames.], tot_loss[loss=0.1849, simple_loss=0.2482, pruned_loss=0.06075, over 973049.69 frames.], batch size: 20, lr: 8.80e-04
2022-05-04 00:13:17,801 INFO [train.py:715] (4/8) Epoch 1, batch 21400, loss[loss=0.1491, simple_loss=0.2113, pruned_loss=0.04343, over 4952.00 frames.], tot_loss[loss=0.1844, simple_loss=0.2479, pruned_loss=0.06042, over 973366.91 frames.], batch size: 14, lr: 8.80e-04
2022-05-04 00:13:57,967 INFO [train.py:715] (4/8) Epoch 1, batch 21450, loss[loss=0.2774, simple_loss=0.3089, pruned_loss=0.123, over 4841.00 frames.], tot_loss[loss=0.1863, simple_loss=0.2491, pruned_loss=0.06178, over 973317.43 frames.], batch size: 15, lr: 8.79e-04
2022-05-04 00:14:36,215 INFO [train.py:715] (4/8) Epoch 1, batch 21500, loss[loss=0.1846, simple_loss=0.2394, pruned_loss=0.06484, over 4916.00 frames.], tot_loss[loss=0.1856, simple_loss=0.2489, pruned_loss=0.06114, over 974033.69 frames.], batch size: 19, lr: 8.79e-04
2022-05-04 00:15:15,309 INFO [train.py:715] (4/8) Epoch 1, batch 21550, loss[loss=0.1777, simple_loss=0.2321, pruned_loss=0.06163, over 4791.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2477, pruned_loss=0.06072, over 973112.62 frames.], batch size: 12, lr: 8.78e-04
2022-05-04 00:15:54,610 INFO [train.py:715] (4/8) Epoch 1, batch 21600, loss[loss=0.1603, simple_loss=0.2194, pruned_loss=0.05053, over 4768.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2473, pruned_loss=0.06056, over 972771.19 frames.], batch size: 19, lr: 8.78e-04
2022-05-04 00:16:33,915 INFO [train.py:715] (4/8) Epoch 1, batch 21650, loss[loss=0.1964, simple_loss=0.261, pruned_loss=0.0659, over 4979.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2476, pruned_loss=0.06066, over 972785.42 frames.], batch size: 28, lr: 8.78e-04
2022-05-04 00:17:12,479 INFO [train.py:715] (4/8) Epoch 1, batch 21700, loss[loss=0.1563, simple_loss=0.2308, pruned_loss=0.0409, over 4936.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2476, pruned_loss=0.06029, over 973947.24 frames.], batch size: 21, lr: 8.77e-04
2022-05-04 00:17:52,133 INFO [train.py:715] (4/8) Epoch 1, batch 21750, loss[loss=0.1994, simple_loss=0.2726, pruned_loss=0.06304, over 4874.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2476, pruned_loss=0.06007, over 973202.54 frames.], batch size: 22, lr: 8.77e-04
2022-05-04 00:18:31,689 INFO [train.py:715] (4/8) Epoch 1, batch 21800, loss[loss=0.1981, simple_loss=0.2565, pruned_loss=0.06982, over 4922.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2471, pruned_loss=0.05961, over 973542.70 frames.], batch size: 18, lr: 8.76e-04
2022-05-04 00:19:10,442 INFO [train.py:715] (4/8) Epoch 1, batch 21850, loss[loss=0.2122, simple_loss=0.2708, pruned_loss=0.07684, over 4784.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2475, pruned_loss=0.05967, over 973268.99 frames.], batch size: 17, lr: 8.76e-04
2022-05-04 00:19:50,596 INFO [train.py:715] (4/8) Epoch 1, batch 21900, loss[loss=0.1858, simple_loss=0.2452, pruned_loss=0.06323, over 4886.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2477, pruned_loss=0.06, over 973594.75 frames.], batch size: 22, lr: 8.76e-04
2022-05-04 00:20:30,151 INFO [train.py:715] (4/8) Epoch 1, batch 21950, loss[loss=0.1881, simple_loss=0.2569, pruned_loss=0.05964, over 4703.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2475, pruned_loss=0.05957, over 972768.38 frames.], batch size: 15, lr: 8.75e-04
2022-05-04 00:21:09,938 INFO [train.py:715] (4/8) Epoch 1, batch 22000, loss[loss=0.1677, simple_loss=0.2365, pruned_loss=0.04945, over 4816.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2472, pruned_loss=0.05945, over 973391.64 frames.], batch size: 25, lr: 8.75e-04
2022-05-04 00:21:48,920 INFO [train.py:715] (4/8) Epoch 1, batch 22050, loss[loss=0.1813, simple_loss=0.2448, pruned_loss=0.0589, over 4765.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2475, pruned_loss=0.05974, over 973050.81 frames.], batch size: 19, lr: 8.75e-04
2022-05-04 00:22:28,892 INFO [train.py:715] (4/8) Epoch 1, batch 22100, loss[loss=0.1971, simple_loss=0.2508, pruned_loss=0.07176, over 4860.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2473, pruned_loss=0.05972, over 972307.89 frames.], batch size: 20, lr: 8.74e-04
2022-05-04 00:23:08,222 INFO [train.py:715] (4/8) Epoch 1, batch 22150, loss[loss=0.2101, simple_loss=0.2654, pruned_loss=0.07738, over 4742.00 frames.], tot_loss[loss=0.1833, simple_loss=0.2473, pruned_loss=0.05963, over 972281.77 frames.], batch size: 16, lr: 8.74e-04
2022-05-04 00:23:46,648 INFO [train.py:715] (4/8) Epoch 1, batch 22200, loss[loss=0.1521, simple_loss=0.2262, pruned_loss=0.03895, over 4983.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2478, pruned_loss=0.06017, over 973299.71 frames.], batch size: 25, lr: 8.73e-04
2022-05-04 00:24:25,883 INFO [train.py:715] (4/8) Epoch 1, batch 22250, loss[loss=0.1511, simple_loss=0.2139, pruned_loss=0.04413, over 4908.00 frames.], tot_loss[loss=0.1836, simple_loss=0.2473, pruned_loss=0.0599, over 973552.88 frames.], batch size: 17, lr: 8.73e-04
2022-05-04 00:25:05,560 INFO [train.py:715] (4/8) Epoch 1, batch 22300, loss[loss=0.1986, simple_loss=0.2608, pruned_loss=0.06824, over 4980.00 frames.], tot_loss[loss=0.1846, simple_loss=0.2484, pruned_loss=0.06037, over 973167.95 frames.], batch size: 28, lr: 8.73e-04
2022-05-04 00:25:45,330 INFO [train.py:715] (4/8) Epoch 1, batch 22350, loss[loss=0.1719, simple_loss=0.2307, pruned_loss=0.0565, over 4794.00 frames.], tot_loss[loss=0.183, simple_loss=0.2469, pruned_loss=0.05954, over 972225.90 frames.], batch size: 14, lr: 8.72e-04
2022-05-04 00:26:24,287 INFO [train.py:715] (4/8) Epoch 1, batch 22400, loss[loss=0.1649, simple_loss=0.2259, pruned_loss=0.0519, over 4883.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2472, pruned_loss=0.05963, over 971458.69 frames.], batch size: 19, lr: 8.72e-04
2022-05-04 00:27:04,011 INFO [train.py:715] (4/8) Epoch 1, batch 22450, loss[loss=0.2069, simple_loss=0.2615, pruned_loss=0.07614, over 4970.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2477, pruned_loss=0.05968, over 971621.79 frames.], batch size: 39, lr: 8.72e-04
2022-05-04 00:27:43,648 INFO [train.py:715] (4/8) Epoch 1, batch 22500, loss[loss=0.1808, simple_loss=0.2412, pruned_loss=0.06018, over 4896.00 frames.], tot_loss[loss=0.1858, simple_loss=0.2491, pruned_loss=0.06121, over 971717.27 frames.], batch size: 19, lr: 8.71e-04
2022-05-04 00:28:22,144 INFO [train.py:715] (4/8) Epoch 1, batch 22550, loss[loss=0.2163, simple_loss=0.2574, pruned_loss=0.08762, over 4970.00 frames.], tot_loss[loss=0.1839, simple_loss=0.2473, pruned_loss=0.06028, over 972258.92 frames.], batch size: 35, lr: 8.71e-04
2022-05-04 00:29:02,211 INFO [train.py:715] (4/8) Epoch 1, batch 22600, loss[loss=0.1828, simple_loss=0.2457, pruned_loss=0.0599, over 4887.00 frames.], tot_loss[loss=0.183, simple_loss=0.2468, pruned_loss=0.05959, over 971827.56 frames.], batch size: 22, lr: 8.70e-04
2022-05-04 00:29:42,689 INFO [train.py:715] (4/8) Epoch 1, batch 22650, loss[loss=0.1962, simple_loss=0.2666, pruned_loss=0.0629, over 4886.00 frames.], tot_loss[loss=0.1837, simple_loss=0.2476, pruned_loss=0.05989, over 972707.78 frames.], batch size: 16, lr: 8.70e-04
2022-05-04 00:30:22,585 INFO [train.py:715] (4/8) Epoch 1, batch 22700, loss[loss=0.196, simple_loss=0.2637, pruned_loss=0.06416, over 4924.00 frames.], tot_loss[loss=0.1829, simple_loss=0.2469, pruned_loss=0.05949, over 972504.70 frames.], batch size: 29, lr: 8.70e-04
2022-05-04 00:31:00,978 INFO [train.py:715] (4/8) Epoch 1, batch 22750, loss[loss=0.1844, simple_loss=0.2449, pruned_loss=0.06195, over 4981.00 frames.], tot_loss[loss=0.1841, simple_loss=0.248, pruned_loss=0.06008, over 973638.42 frames.], batch size: 31, lr: 8.69e-04
2022-05-04 00:31:41,165 INFO [train.py:715] (4/8) Epoch 1, batch 22800, loss[loss=0.1605, simple_loss=0.2231, pruned_loss=0.0489, over 4776.00 frames.], tot_loss[loss=0.1838, simple_loss=0.248, pruned_loss=0.05975, over 972953.03 frames.], batch size: 19, lr: 8.69e-04
2022-05-04 00:32:20,888 INFO [train.py:715] (4/8) Epoch 1, batch 22850, loss[loss=0.2143, simple_loss=0.2536, pruned_loss=0.08746, over 4798.00 frames.], tot_loss[loss=0.1842, simple_loss=0.2482, pruned_loss=0.06009, over 972295.89 frames.], batch size: 14, lr: 8.68e-04
2022-05-04 00:32:59,722 INFO [train.py:715] (4/8) Epoch 1, batch 22900, loss[loss=0.1448, simple_loss=0.211, pruned_loss=0.03934, over 4869.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2483, pruned_loss=0.06016, over 972057.61 frames.], batch size: 22, lr: 8.68e-04
2022-05-04 00:33:39,273 INFO [train.py:715] (4/8) Epoch 1, batch 22950, loss[loss=0.2261, simple_loss=0.2775, pruned_loss=0.08732, over 4748.00 frames.], tot_loss[loss=0.1841, simple_loss=0.2483, pruned_loss=0.05998, over 971382.99 frames.], batch size: 16, lr: 8.68e-04
2022-05-04 00:34:19,075 INFO [train.py:715] (4/8) Epoch 1, batch 23000, loss[loss=0.1949, simple_loss=0.2521, pruned_loss=0.06886, over 4978.00 frames.], tot_loss[loss=0.1845, simple_loss=0.248, pruned_loss=0.06055, over 971224.19 frames.], batch size: 39, lr: 8.67e-04
2022-05-04 00:34:57,981 INFO [train.py:715] (4/8) Epoch 1, batch 23050, loss[loss=0.1765, simple_loss=0.2445, pruned_loss=0.0542, over 4868.00 frames.], tot_loss[loss=0.1835, simple_loss=0.2471, pruned_loss=0.05999, over 971530.76 frames.], batch size: 32, lr: 8.67e-04
2022-05-04 00:35:37,123 INFO [train.py:715] (4/8) Epoch 1, batch 23100, loss[loss=0.1873, simple_loss=0.2337, pruned_loss=0.07041, over 4837.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2468, pruned_loss=0.05987, over 972454.43 frames.], batch size: 30, lr: 8.67e-04
2022-05-04 00:36:16,854 INFO [train.py:715] (4/8) Epoch 1, batch 23150, loss[loss=0.177, simple_loss=0.2492, pruned_loss=0.05241, over 4910.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2464, pruned_loss=0.05926, over 972365.12 frames.], batch size: 19, lr: 8.66e-04
2022-05-04 00:36:56,381 INFO [train.py:715] (4/8) Epoch 1, batch 23200, loss[loss=0.1743, simple_loss=0.2267, pruned_loss=0.06097, over 4876.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2465, pruned_loss=0.05906, over 972570.38 frames.], batch size: 30, lr: 8.66e-04
2022-05-04 00:37:34,617 INFO [train.py:715] (4/8) Epoch 1, batch 23250, loss[loss=0.2109, simple_loss=0.2689, pruned_loss=0.07646, over 4894.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2468, pruned_loss=0.05933, over 972966.11 frames.], batch size: 22, lr: 8.66e-04
2022-05-04 00:38:14,195 INFO [train.py:715] (4/8) Epoch 1, batch 23300, loss[loss=0.1709, simple_loss=0.2447, pruned_loss=0.04853, over 4914.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2463, pruned_loss=0.05917, over 973422.21 frames.], batch size: 18, lr: 8.65e-04
2022-05-04 00:38:53,772 INFO [train.py:715] (4/8) Epoch 1, batch 23350, loss[loss=0.1712, simple_loss=0.2416, pruned_loss=0.05041, over 4850.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2458, pruned_loss=0.05877, over 972394.64 frames.], batch size: 32, lr: 8.65e-04
2022-05-04 00:39:32,068 INFO [train.py:715] (4/8) Epoch 1, batch 23400, loss[loss=0.1997, simple_loss=0.2491, pruned_loss=0.07515, over 4885.00 frames.], tot_loss[loss=0.183, simple_loss=0.2466, pruned_loss=0.05969, over 971928.42 frames.], batch size: 22, lr: 8.64e-04
2022-05-04 00:40:11,306 INFO [train.py:715] (4/8) Epoch 1, batch 23450, loss[loss=0.1519, simple_loss=0.2136, pruned_loss=0.04511, over 4712.00 frames.], tot_loss[loss=0.183, simple_loss=0.2464, pruned_loss=0.05975, over 971398.65 frames.], batch size: 12, lr: 8.64e-04
2022-05-04 00:40:50,695 INFO [train.py:715] (4/8) Epoch 1, batch 23500, loss[loss=0.1616, simple_loss=0.2292, pruned_loss=0.04695, over 4925.00 frames.], tot_loss[loss=0.184, simple_loss=0.2477, pruned_loss=0.06015, over 971286.02 frames.], batch size: 29, lr: 8.64e-04
2022-05-04 00:41:29,530 INFO [train.py:715] (4/8) Epoch 1, batch 23550, loss[loss=0.1771, simple_loss=0.2518, pruned_loss=0.05114, over 4697.00 frames.], tot_loss[loss=0.1845, simple_loss=0.2481, pruned_loss=0.06045, over 972028.46 frames.], batch size: 15, lr: 8.63e-04
2022-05-04 00:42:07,727 INFO [train.py:715] (4/8) Epoch 1, batch 23600, loss[loss=0.1611, simple_loss=0.2501, pruned_loss=0.03601, over 4751.00 frames.], tot_loss[loss=0.1843, simple_loss=0.2481, pruned_loss=0.06022, over 971630.91 frames.], batch size: 16, lr: 8.63e-04
2022-05-04 00:42:47,235 INFO [train.py:715] (4/8) Epoch 1, batch 23650, loss[loss=0.2066, simple_loss=0.2682, pruned_loss=0.07251, over 4746.00 frames.], tot_loss[loss=0.1834, simple_loss=0.2474, pruned_loss=0.0597, over 971705.90 frames.], batch size: 12, lr: 8.63e-04
2022-05-04 00:43:26,750 INFO [train.py:715] (4/8) Epoch 1, batch 23700, loss[loss=0.1974, simple_loss=0.2633, pruned_loss=0.06571, over 4968.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2466, pruned_loss=0.05898, over 972603.86 frames.], batch size: 15, lr: 8.62e-04
2022-05-04 00:44:05,090 INFO [train.py:715] (4/8) Epoch 1, batch 23750, loss[loss=0.1522, simple_loss=0.2264, pruned_loss=0.03896, over 4782.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2466, pruned_loss=0.05917, over 972408.37 frames.], batch size: 14, lr: 8.62e-04
2022-05-04 00:44:44,143 INFO [train.py:715] (4/8) Epoch 1, batch 23800, loss[loss=0.1722, simple_loss=0.2379, pruned_loss=0.05324, over 4851.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2468, pruned_loss=0.05906, over 971630.04 frames.], batch size: 32, lr: 8.61e-04
2022-05-04 00:45:24,228 INFO [train.py:715] (4/8) Epoch 1, batch 23850, loss[loss=0.1773, simple_loss=0.2365, pruned_loss=0.05907, over 4758.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2468, pruned_loss=0.05876, over 971848.50 frames.], batch size: 19, lr: 8.61e-04
2022-05-04 00:46:03,789 INFO [train.py:715] (4/8) Epoch 1, batch 23900, loss[loss=0.1418, simple_loss=0.2166, pruned_loss=0.03347, over 4786.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2457, pruned_loss=0.05823, over 971711.96 frames.], batch size: 14, lr: 8.61e-04
2022-05-04 00:46:42,592 INFO [train.py:715] (4/8) Epoch 1, batch 23950, loss[loss=0.1686, simple_loss=0.2334, pruned_loss=0.05195, over 4989.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2458, pruned_loss=0.05842, over 972306.13 frames.], batch size: 16, lr: 8.60e-04
2022-05-04 00:47:22,330 INFO [train.py:715] (4/8) Epoch 1, batch 24000, loss[loss=0.1862, simple_loss=0.2401, pruned_loss=0.06616, over 4845.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2458, pruned_loss=0.05863, over 972621.92 frames.], batch size: 32, lr: 8.60e-04
2022-05-04 00:47:22,331 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 00:47:34,528 INFO [train.py:742] (4/8) Epoch 1, validation: loss=0.1217, simple_loss=0.2087, pruned_loss=0.01736, over 914524.00 frames.
2022-05-04 00:48:14,358 INFO [train.py:715] (4/8) Epoch 1, batch 24050, loss[loss=0.1551, simple_loss=0.2247, pruned_loss=0.0428, over 4889.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2457, pruned_loss=0.05855, over 972931.46 frames.], batch size: 19, lr: 8.60e-04
2022-05-04 00:48:53,681 INFO [train.py:715] (4/8) Epoch 1, batch 24100, loss[loss=0.1789, simple_loss=0.247, pruned_loss=0.05543, over 4810.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2462, pruned_loss=0.05862, over 972406.55 frames.], batch size: 25, lr: 8.59e-04
2022-05-04 00:49:32,277 INFO [train.py:715] (4/8) Epoch 1, batch 24150, loss[loss=0.2208, simple_loss=0.2679, pruned_loss=0.08689, over 4856.00 frames.], tot_loss[loss=0.1817, simple_loss=0.246, pruned_loss=0.05874, over 973375.79 frames.], batch size: 32, lr: 8.59e-04
2022-05-04 00:50:11,571 INFO [train.py:715] (4/8) Epoch 1, batch 24200, loss[loss=0.1802, simple_loss=0.2336, pruned_loss=0.06342, over 4774.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2468, pruned_loss=0.05918, over 973426.13 frames.], batch size: 17, lr: 8.59e-04
2022-05-04 00:50:52,251 INFO [train.py:715] (4/8) Epoch 1, batch 24250, loss[loss=0.1684, simple_loss=0.2367, pruned_loss=0.05012, over 4941.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2453, pruned_loss=0.0586, over 972589.47 frames.], batch size: 21, lr: 8.58e-04
2022-05-04 00:51:31,678 INFO [train.py:715] (4/8) Epoch 1, batch 24300, loss[loss=0.1581, simple_loss=0.2196, pruned_loss=0.04828, over 4649.00 frames.], tot_loss[loss=0.1819, simple_loss=0.2459, pruned_loss=0.05896, over 972329.11 frames.], batch size: 13, lr: 8.58e-04
2022-05-04 00:52:11,124 INFO [train.py:715] (4/8) Epoch 1, batch 24350, loss[loss=0.1867, simple_loss=0.2459, pruned_loss=0.06377, over 4701.00 frames.], tot_loss[loss=0.181, simple_loss=0.2451, pruned_loss=0.05842, over 972217.91 frames.], batch size: 15, lr: 8.57e-04
2022-05-04 00:52:51,498 INFO [train.py:715] (4/8) Epoch 1, batch 24400, loss[loss=0.1693, simple_loss=0.2307, pruned_loss=0.05389, over 4914.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2452, pruned_loss=0.05785, over 973313.87 frames.], batch size: 19, lr: 8.57e-04
2022-05-04 00:53:30,578 INFO [train.py:715] (4/8) Epoch 1, batch 24450, loss[loss=0.214, simple_loss=0.285, pruned_loss=0.07146, over 4899.00 frames.], tot_loss[loss=0.1809, simple_loss=0.2454, pruned_loss=0.05816, over 972221.09 frames.], batch size: 19, lr: 8.57e-04
2022-05-04 00:54:09,300 INFO [train.py:715] (4/8) Epoch 1, batch 24500, loss[loss=0.2266, simple_loss=0.2712, pruned_loss=0.09101, over 4977.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2468, pruned_loss=0.05915, over 973007.36 frames.], batch size: 15, lr: 8.56e-04
2022-05-04 00:54:48,963 INFO [train.py:715] (4/8) Epoch 1, batch 24550, loss[loss=0.1974, simple_loss=0.2564, pruned_loss=0.06924, over 4974.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2466, pruned_loss=0.05924, over 972737.55 frames.], batch size: 15, lr: 8.56e-04
2022-05-04 00:55:29,264 INFO [train.py:715] (4/8) Epoch 1, batch 24600, loss[loss=0.2392, simple_loss=0.286, pruned_loss=0.09622, over 4699.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2457, pruned_loss=0.05839, over 972294.24 frames.], batch size: 15, lr: 8.56e-04
2022-05-04 00:56:08,133 INFO [train.py:715] (4/8) Epoch 1, batch 24650, loss[loss=0.2033, simple_loss=0.2553, pruned_loss=0.07568, over 4716.00 frames.], tot_loss[loss=0.1814, simple_loss=0.246, pruned_loss=0.05837, over 971694.89 frames.], batch size: 15, lr: 8.55e-04
2022-05-04 00:56:47,164 INFO [train.py:715] (4/8) Epoch 1, batch 24700, loss[loss=0.1595, simple_loss=0.2334, pruned_loss=0.04277, over 4806.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2465, pruned_loss=0.05912, over 972342.27 frames.], batch size: 21, lr: 8.55e-04
2022-05-04 00:57:27,341 INFO [train.py:715] (4/8) Epoch 1, batch 24750, loss[loss=0.1461, simple_loss=0.2203, pruned_loss=0.03602, over 4930.00 frames.], tot_loss[loss=0.1819, simple_loss=0.246, pruned_loss=0.0589, over 972105.21 frames.], batch size: 17, lr: 8.55e-04
2022-05-04 00:58:06,478 INFO [train.py:715] (4/8) Epoch 1, batch 24800, loss[loss=0.1643, simple_loss=0.2405, pruned_loss=0.0441, over 4860.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2443, pruned_loss=0.05775, over 972125.93 frames.], batch size: 20, lr: 8.54e-04
2022-05-04 00:58:45,104 INFO [train.py:715] (4/8) Epoch 1, batch 24850, loss[loss=0.1796, simple_loss=0.2457, pruned_loss=0.05673, over 4788.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2451, pruned_loss=0.05784, over 972154.05 frames.], batch size: 18, lr: 8.54e-04
2022-05-04 00:59:25,588 INFO [train.py:715] (4/8) Epoch 1, batch 24900, loss[loss=0.1539, simple_loss=0.2235, pruned_loss=0.04219, over 4821.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2454, pruned_loss=0.05806, over 972348.84 frames.], batch size: 15, lr: 8.54e-04
2022-05-04 01:00:05,519 INFO [train.py:715] (4/8) Epoch 1, batch 24950, loss[loss=0.2307, simple_loss=0.2839, pruned_loss=0.08879, over 4876.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2459, pruned_loss=0.05828, over 972258.67 frames.], batch size: 32, lr: 8.53e-04
2022-05-04 01:00:44,291 INFO [train.py:715] (4/8) Epoch 1, batch 25000, loss[loss=0.1497, simple_loss=0.2207, pruned_loss=0.0393, over 4840.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2466, pruned_loss=0.05894, over 972413.63 frames.], batch size: 15, lr: 8.53e-04
2022-05-04 01:01:22,933 INFO [train.py:715] (4/8) Epoch 1, batch 25050, loss[loss=0.206, simple_loss=0.2578, pruned_loss=0.07712, over 4905.00 frames.], tot_loss[loss=0.182, simple_loss=0.2463, pruned_loss=0.05889, over 973049.11 frames.], batch size: 19, lr: 8.53e-04
2022-05-04 01:02:02,855 INFO [train.py:715] (4/8) Epoch 1, batch 25100, loss[loss=0.1913, simple_loss=0.248, pruned_loss=0.06729, over 4900.00 frames.], tot_loss[loss=0.182, simple_loss=0.2461, pruned_loss=0.05897, over 971984.39 frames.], batch size: 19, lr: 8.52e-04
2022-05-04 01:02:42,031 INFO [train.py:715] (4/8) Epoch 1, batch 25150, loss[loss=0.1853, simple_loss=0.235, pruned_loss=0.06782, over 4905.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2449, pruned_loss=0.05805, over 971507.10 frames.], batch size: 17, lr: 8.52e-04
2022-05-04 01:03:20,872 INFO [train.py:715] (4/8) Epoch 1, batch 25200, loss[loss=0.1434, simple_loss=0.1989, pruned_loss=0.04395, over 4753.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2458, pruned_loss=0.05856, over 971818.09 frames.], batch size: 12, lr: 8.51e-04
2022-05-04 01:04:00,097 INFO [train.py:715] (4/8) Epoch 1, batch 25250, loss[loss=0.2223, simple_loss=0.2702, pruned_loss=0.08724, over 4835.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2454, pruned_loss=0.05884, over 971463.15 frames.], batch size: 32, lr: 8.51e-04
2022-05-04 01:04:40,223 INFO [train.py:715] (4/8) Epoch 1, batch 25300, loss[loss=0.2002, simple_loss=0.2612, pruned_loss=0.06957, over 4964.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2449, pruned_loss=0.0582, over 970709.21 frames.], batch size: 15, lr: 8.51e-04
2022-05-04 01:05:18,876 INFO [train.py:715] (4/8) Epoch 1, batch 25350, loss[loss=0.2001, simple_loss=0.2591, pruned_loss=0.07056, over 4816.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2454, pruned_loss=0.05835, over 971726.02 frames.], batch size: 27, lr: 8.50e-04
2022-05-04 01:05:58,215 INFO [train.py:715] (4/8) Epoch 1, batch 25400, loss[loss=0.1736, simple_loss=0.2468, pruned_loss=0.05023, over 4824.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2454, pruned_loss=0.05861, over 972496.74 frames.], batch size: 27, lr: 8.50e-04
2022-05-04 01:06:38,479 INFO [train.py:715] (4/8) Epoch 1, batch 25450, loss[loss=0.1714, simple_loss=0.2327, pruned_loss=0.05506, over 4880.00 frames.], tot_loss[loss=0.1806, simple_loss=0.2448, pruned_loss=0.05822, over 972646.67 frames.], batch size: 16, lr: 8.50e-04
2022-05-04 01:07:18,420 INFO [train.py:715] (4/8) Epoch 1, batch 25500, loss[loss=0.1363, simple_loss=0.2106, pruned_loss=0.03096, over 4939.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2446, pruned_loss=0.05837, over 972774.46 frames.], batch size: 21, lr: 8.49e-04
2022-05-04 01:07:56,846 INFO [train.py:715] (4/8) Epoch 1, batch 25550, loss[loss=0.1667, simple_loss=0.2418, pruned_loss=0.04575, over 4802.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2455, pruned_loss=0.059, over 972586.73 frames.], batch size: 24, lr: 8.49e-04
2022-05-04 01:08:36,978 INFO [train.py:715] (4/8) Epoch 1, batch 25600, loss[loss=0.1639, simple_loss=0.2382, pruned_loss=0.04477, over 4788.00 frames.], tot_loss[loss=0.181, simple_loss=0.2454, pruned_loss=0.05836, over 972470.39 frames.], batch size: 18, lr: 8.49e-04
2022-05-04 01:09:17,500 INFO [train.py:715] (4/8) Epoch 1, batch 25650, loss[loss=0.1964, simple_loss=0.256, pruned_loss=0.06834, over 4776.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2453, pruned_loss=0.05815, over 971835.86 frames.], batch size: 18, lr: 8.48e-04
2022-05-04 01:09:56,988 INFO [train.py:715] (4/8) Epoch 1, batch 25700, loss[loss=0.1714, simple_loss=0.2444, pruned_loss=0.04919, over 4832.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2466, pruned_loss=0.059, over 972882.01 frames.], batch size: 27, lr: 8.48e-04
2022-05-04 01:10:36,900 INFO [train.py:715] (4/8) Epoch 1, batch 25750, loss[loss=0.1552, simple_loss=0.2217, pruned_loss=0.04436, over 4989.00 frames.], tot_loss[loss=0.1814, simple_loss=0.2459, pruned_loss=0.05844, over 972760.31 frames.], batch size: 27, lr: 8.48e-04
2022-05-04 01:11:17,392 INFO [train.py:715] (4/8) Epoch 1, batch 25800, loss[loss=0.1615, simple_loss=0.2388, pruned_loss=0.04214, over 4779.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2462, pruned_loss=0.05852, over 973314.37 frames.], batch size: 17, lr: 8.47e-04
2022-05-04 01:11:56,816 INFO [train.py:715] (4/8) Epoch 1, batch 25850, loss[loss=0.1495, simple_loss=0.2068, pruned_loss=0.04606, over 4839.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2457, pruned_loss=0.05823, over 973294.73 frames.], batch size: 13, lr: 8.47e-04
2022-05-04 01:12:35,650 INFO [train.py:715] (4/8) Epoch 1, batch 25900, loss[loss=0.222, simple_loss=0.2699, pruned_loss=0.0871, over 4961.00 frames.], tot_loss[loss=0.181, simple_loss=0.2452, pruned_loss=0.05841, over 972481.95 frames.], batch size: 24, lr: 8.47e-04
2022-05-04 01:13:15,323 INFO [train.py:715] (4/8) Epoch 1, batch 25950, loss[loss=0.2092, simple_loss=0.2664, pruned_loss=0.07597, over 4987.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2458, pruned_loss=0.0589, over 972680.20 frames.], batch size: 35, lr: 8.46e-04
2022-05-04 01:13:55,203 INFO [train.py:715] (4/8) Epoch 1, batch 26000, loss[loss=0.1949, simple_loss=0.2577, pruned_loss=0.066, over 4756.00 frames.], tot_loss[loss=0.1825, simple_loss=0.2464, pruned_loss=0.05925, over 972006.88 frames.], batch size: 19, lr: 8.46e-04
2022-05-04 01:14:34,093 INFO [train.py:715] (4/8) Epoch 1, batch 26050, loss[loss=0.1947, simple_loss=0.2687, pruned_loss=0.0603, over 4877.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2461, pruned_loss=0.05912, over 972227.67 frames.], batch size: 22, lr: 8.46e-04
2022-05-04 01:15:13,488 INFO [train.py:715] (4/8) Epoch 1, batch 26100, loss[loss=0.2114, simple_loss=0.2677, pruned_loss=0.07751, over 4847.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2459, pruned_loss=0.05941, over 972654.66 frames.], batch size: 15, lr: 8.45e-04
2022-05-04 01:15:53,620 INFO [train.py:715] (4/8) Epoch 1, batch 26150, loss[loss=0.1644, simple_loss=0.2369, pruned_loss=0.04599, over 4810.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2458, pruned_loss=0.0594, over 973236.64 frames.], batch size: 25, lr: 8.45e-04
2022-05-04 01:16:32,589 INFO [train.py:715] (4/8) Epoch 1, batch 26200, loss[loss=0.1824, simple_loss=0.2484, pruned_loss=0.0582, over 4882.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2449, pruned_loss=0.05907, over 973038.56 frames.], batch size: 22, lr: 8.44e-04
2022-05-04 01:17:11,434 INFO [train.py:715] (4/8) Epoch 1, batch 26250, loss[loss=0.1951, simple_loss=0.2466, pruned_loss=0.07178, over 4902.00 frames.], tot_loss[loss=0.1815, simple_loss=0.2451, pruned_loss=0.05896, over 972970.01 frames.], batch size: 17, lr: 8.44e-04
2022-05-04 01:17:51,342 INFO [train.py:715] (4/8) Epoch 1, batch 26300, loss[loss=0.1901, simple_loss=0.251, pruned_loss=0.06457, over 4900.00 frames.], tot_loss[loss=0.181, simple_loss=0.2444, pruned_loss=0.05875, over 973854.58 frames.], batch size: 17, lr: 8.44e-04
2022-05-04 01:18:31,200 INFO [train.py:715] (4/8) Epoch 1, batch 26350, loss[loss=0.1459, simple_loss=0.2141, pruned_loss=0.03884, over 4905.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2457, pruned_loss=0.05951, over 974238.28 frames.], batch size: 23, lr: 8.43e-04
2022-05-04 01:19:09,967 INFO [train.py:715] (4/8) Epoch 1, batch 26400, loss[loss=0.1846, simple_loss=0.2559, pruned_loss=0.05662, over 4792.00 frames.], tot_loss[loss=0.1823, simple_loss=0.2459, pruned_loss=0.05938, over 973229.07 frames.], batch size: 14, lr: 8.43e-04
2022-05-04 01:19:49,169 INFO [train.py:715] (4/8) Epoch 1, batch 26450, loss[loss=0.223, simple_loss=0.2761, pruned_loss=0.08496, over 4912.00 frames.], tot_loss[loss=0.1824, simple_loss=0.2463, pruned_loss=0.05924, over 972916.73 frames.], batch size: 39, lr: 8.43e-04
2022-05-04 01:20:28,906 INFO [train.py:715] (4/8) Epoch 1, batch 26500, loss[loss=0.1907, simple_loss=0.2511, pruned_loss=0.06517, over 4970.00 frames.], tot_loss[loss=0.1821, simple_loss=0.246, pruned_loss=0.05912, over 972596.42 frames.], batch size: 39, lr: 8.42e-04
2022-05-04 01:21:08,261 INFO [train.py:715] (4/8) Epoch 1, batch 26550, loss[loss=0.1938, simple_loss=0.2575, pruned_loss=0.06502, over 4818.00 frames.], tot_loss[loss=0.1832, simple_loss=0.2468, pruned_loss=0.05983, over 973228.58 frames.], batch size: 15, lr: 8.42e-04
2022-05-04 01:21:47,616 INFO [train.py:715] (4/8) Epoch 1, batch 26600, loss[loss=0.186, simple_loss=0.2384, pruned_loss=0.06675, over 4742.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2469, pruned_loss=0.05927, over 973202.36 frames.], batch size: 16, lr: 8.42e-04
2022-05-04 01:22:27,659 INFO [train.py:715] (4/8) Epoch 1, batch 26650, loss[loss=0.1831, simple_loss=0.2398, pruned_loss=0.06319, over 4941.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2467, pruned_loss=0.05922, over 972428.81 frames.], batch size: 29, lr: 8.41e-04
2022-05-04 01:23:07,610 INFO [train.py:715] (4/8) Epoch 1, batch 26700, loss[loss=0.2084, simple_loss=0.2678, pruned_loss=0.07446, over 4948.00 frames.], tot_loss[loss=0.1826, simple_loss=0.2467, pruned_loss=0.05926, over 972485.44 frames.], batch size: 23, lr: 8.41e-04
2022-05-04 01:23:46,583 INFO [train.py:715] (4/8) Epoch 1, batch 26750, loss[loss=0.2106, simple_loss=0.2752, pruned_loss=0.07305, over 4915.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2461, pruned_loss=0.05906, over 972706.45 frames.], batch size: 17, lr: 8.41e-04
2022-05-04 01:24:26,590 INFO [train.py:715] (4/8) Epoch 1, batch 26800, loss[loss=0.1463, simple_loss=0.2198, pruned_loss=0.03642, over 4742.00 frames.], tot_loss[loss=0.1818, simple_loss=0.2461, pruned_loss=0.05878, over 972001.75 frames.], batch size: 19, lr: 8.40e-04
2022-05-04 01:25:06,137 INFO [train.py:715] (4/8) Epoch 1, batch 26850, loss[loss=0.1889, simple_loss=0.2493, pruned_loss=0.06422, over 4818.00 frames.], tot_loss[loss=0.1817, simple_loss=0.2461, pruned_loss=0.05866, over 972274.95 frames.], batch size: 12, lr: 8.40e-04
2022-05-04 01:25:45,416 INFO [train.py:715] (4/8) Epoch 1, batch 26900, loss[loss=0.1836, simple_loss=0.2451, pruned_loss=0.06103, over 4742.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2464, pruned_loss=0.05893, over 972539.22 frames.], batch size: 16, lr: 8.40e-04
2022-05-04 01:26:24,109 INFO [train.py:715] (4/8) Epoch 1, batch 26950, loss[loss=0.1609, simple_loss=0.2297, pruned_loss=0.04608, over 4909.00 frames.], tot_loss[loss=0.1827, simple_loss=0.2468, pruned_loss=0.05936, over 972132.22 frames.], batch size: 17, lr: 8.39e-04
2022-05-04 01:27:04,123 INFO [train.py:715] (4/8) Epoch 1, batch 27000, loss[loss=0.136, simple_loss=0.2027, pruned_loss=0.03462, over 4934.00 frames.], tot_loss[loss=0.1821, simple_loss=0.2461, pruned_loss=0.05909, over 972035.28 frames.], batch size: 29, lr: 8.39e-04
2022-05-04 01:27:04,123 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 01:27:12,717 INFO [train.py:742] (4/8) Epoch 1, validation: loss=0.1212, simple_loss=0.2081, pruned_loss=0.01718, over 914524.00 frames.
2022-05-04 01:27:53,059 INFO [train.py:715] (4/8) Epoch 1, batch 27050, loss[loss=0.148, simple_loss=0.2117, pruned_loss=0.04219, over 4819.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2448, pruned_loss=0.05847, over 973070.08 frames.], batch size: 12, lr: 8.39e-04
2022-05-04 01:28:33,373 INFO [train.py:715] (4/8) Epoch 1, batch 27100, loss[loss=0.1891, simple_loss=0.2472, pruned_loss=0.0655, over 4876.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2455, pruned_loss=0.05882, over 972367.24 frames.], batch size: 16, lr: 8.38e-04
2022-05-04 01:29:11,778 INFO [train.py:715] (4/8) Epoch 1, batch 27150, loss[loss=0.183, simple_loss=0.2555, pruned_loss=0.05529, over 4888.00 frames.], tot_loss[loss=0.1831, simple_loss=0.2466, pruned_loss=0.0598, over 972631.32 frames.], batch size: 22, lr: 8.38e-04
2022-05-04 01:29:51,721 INFO [train.py:715] (4/8) Epoch 1, batch 27200, loss[loss=0.1473, simple_loss=0.2141, pruned_loss=0.04029, over 4958.00 frames.], tot_loss[loss=0.1812, simple_loss=0.2456, pruned_loss=0.0584, over 972799.67 frames.], batch size: 24, lr: 8.38e-04
2022-05-04 01:30:32,012 INFO [train.py:715] (4/8) Epoch 1, batch 27250, loss[loss=0.159, simple_loss=0.2253, pruned_loss=0.0464, over 4818.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2443, pruned_loss=0.0576, over 972538.83 frames.], batch size: 26, lr: 8.37e-04
2022-05-04 01:31:11,136 INFO [train.py:715] (4/8) Epoch 1, batch 27300, loss[loss=0.1614, simple_loss=0.2335, pruned_loss=0.04458, over 4798.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2443, pruned_loss=0.05744, over 972144.86 frames.], batch size: 21, lr: 8.37e-04
2022-05-04 01:31:49,671 INFO [train.py:715] (4/8) Epoch 1, batch 27350, loss[loss=0.1772, simple_loss=0.2443, pruned_loss=0.0551, over 4978.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2444, pruned_loss=0.05702, over 972991.52 frames.], batch size: 14, lr: 8.37e-04
2022-05-04 01:32:29,601 INFO [train.py:715] (4/8) Epoch 1, batch 27400, loss[loss=0.1843, simple_loss=0.258, pruned_loss=0.0553, over 4977.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2441, pruned_loss=0.05675, over 972636.64 frames.], batch size: 28, lr: 8.36e-04
2022-05-04 01:33:09,595 INFO [train.py:715] (4/8) Epoch 1, batch 27450, loss[loss=0.1564, simple_loss=0.239, pruned_loss=0.03694, over 4923.00 frames.], tot_loss[loss=0.1801, simple_loss=0.245, pruned_loss=0.05767, over 972116.80 frames.], batch size: 29, lr: 8.36e-04
2022-05-04 01:33:48,104 INFO [train.py:715] (4/8) Epoch 1, batch 27500, loss[loss=0.183, simple_loss=0.2595, pruned_loss=0.05328, over 4935.00 frames.], tot_loss[loss=0.18, simple_loss=0.2447, pruned_loss=0.05761, over 972705.04 frames.], batch size: 21, lr: 8.36e-04
2022-05-04 01:34:27,759 INFO [train.py:715] (4/8) Epoch 1, batch 27550, loss[loss=0.1735, simple_loss=0.2378, pruned_loss=0.05461, over 4834.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2447, pruned_loss=0.05744, over 972490.97 frames.], batch size: 30, lr: 8.35e-04
2022-05-04 01:35:07,987 INFO [train.py:715] (4/8) Epoch 1, batch 27600, loss[loss=0.2031, simple_loss=0.2637, pruned_loss=0.07125, over 4789.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2459, pruned_loss=0.0582, over 972180.96 frames.], batch size: 24, lr: 8.35e-04
2022-05-04 01:35:47,295 INFO [train.py:715] (4/8) Epoch 1, batch 27650, loss[loss=0.1853, simple_loss=0.2465, pruned_loss=0.06207, over 4926.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2454, pruned_loss=0.05774, over 972551.51 frames.], batch size: 23, lr: 8.35e-04
2022-05-04 01:36:26,733 INFO [train.py:715] (4/8) Epoch 1, batch 27700, loss[loss=0.1521, simple_loss=0.2247, pruned_loss=0.03971, over 4897.00 frames.], tot_loss[loss=0.1816, simple_loss=0.2463, pruned_loss=0.05848, over 973128.27 frames.], batch size: 19, lr: 8.34e-04
2022-05-04 01:37:07,281 INFO [train.py:715] (4/8) Epoch 1, batch 27750, loss[loss=0.2156, simple_loss=0.2695, pruned_loss=0.08087, over 4880.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2444, pruned_loss=0.05746, over 972464.45 frames.], batch size: 16, lr: 8.34e-04
2022-05-04 01:37:47,072 INFO [train.py:715] (4/8) Epoch 1, batch 27800, loss[loss=0.161, simple_loss=0.2338, pruned_loss=0.0441, over 4802.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2438, pruned_loss=0.05698, over 972296.25 frames.], batch size: 21, lr: 8.34e-04
2022-05-04 01:38:26,356 INFO [train.py:715] (4/8) Epoch 1, batch 27850, loss[loss=0.1927, simple_loss=0.2566, pruned_loss=0.06438, over 4818.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2439, pruned_loss=0.05746, over 971702.50 frames.], batch size: 27, lr: 8.33e-04
2022-05-04 01:39:06,468 INFO [train.py:715] (4/8) Epoch 1, batch 27900, loss[loss=0.2157, simple_loss=0.2718, pruned_loss=0.07979, over 4849.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2448, pruned_loss=0.0583, over 971084.56 frames.], batch size: 32, lr: 8.33e-04
2022-05-04 01:39:45,945 INFO [train.py:715] (4/8) Epoch 1, batch 27950, loss[loss=0.1428, simple_loss=0.2062, pruned_loss=0.03966, over 4966.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2449, pruned_loss=0.05886, over 971058.63 frames.], batch size: 14, lr: 8.33e-04
2022-05-04 01:40:25,329 INFO [train.py:715] (4/8) Epoch 1, batch 28000, loss[loss=0.1325, simple_loss=0.1996, pruned_loss=0.03269, over 4796.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2447, pruned_loss=0.05849, over 972035.06 frames.], batch size: 14, lr: 8.32e-04
2022-05-04 01:41:04,104 INFO [train.py:715] (4/8) Epoch 1, batch 28050, loss[loss=0.2029, simple_loss=0.2623, pruned_loss=0.07174, over 4814.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2446, pruned_loss=0.05803, over 973030.22 frames.], batch size: 27, lr: 8.32e-04
2022-05-04 01:41:44,523 INFO [train.py:715] (4/8) Epoch 1, batch 28100, loss[loss=0.2413, simple_loss=0.2765, pruned_loss=0.103, over 4902.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2445, pruned_loss=0.05828, over 971838.45 frames.], batch size: 19, lr: 8.32e-04
2022-05-04 01:42:23,899 INFO [train.py:715] (4/8) Epoch 1, batch 28150, loss[loss=0.1512, simple_loss=0.2208, pruned_loss=0.04075, over 4727.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2442, pruned_loss=0.05806, over 971499.08 frames.], batch size: 16, lr: 8.31e-04
2022-05-04 01:43:03,288 INFO [train.py:715] (4/8) Epoch 1, batch 28200, loss[loss=0.2316, simple_loss=0.2924, pruned_loss=0.08544, over 4829.00 frames.], tot_loss[loss=0.179, simple_loss=0.2433, pruned_loss=0.05738, over 972207.67 frames.], batch size: 15, lr: 8.31e-04
2022-05-04 01:43:43,972 INFO [train.py:715] (4/8) Epoch 1, batch 28250, loss[loss=0.1493, simple_loss=0.23, pruned_loss=0.03433, over 4702.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2425, pruned_loss=0.0564, over 972524.36 frames.], batch size: 15, lr: 8.31e-04
2022-05-04 01:44:24,420 INFO [train.py:715] (4/8) Epoch 1, batch 28300, loss[loss=0.1903, simple_loss=0.2548, pruned_loss=0.06293, over 4910.00 frames.], tot_loss[loss=0.178, simple_loss=0.243, pruned_loss=0.05648, over 972038.00 frames.], batch size: 17, lr: 8.30e-04
2022-05-04 01:45:03,750 INFO [train.py:715] (4/8) Epoch 1, batch 28350, loss[loss=0.163, simple_loss=0.2294, pruned_loss=0.04829, over 4753.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2435, pruned_loss=0.05691, over 972490.13 frames.], batch size: 19, lr: 8.30e-04
2022-05-04 01:45:42,701 INFO [train.py:715] (4/8) Epoch 1, batch 28400, loss[loss=0.1681, simple_loss=0.2226, pruned_loss=0.05679, over 4945.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2444, pruned_loss=0.05769, over 972379.25 frames.], batch size: 35, lr: 8.30e-04
2022-05-04 01:46:23,129 INFO [train.py:715] (4/8) Epoch 1, batch 28450, loss[loss=0.1775, simple_loss=0.2495, pruned_loss=0.05271, over 4933.00 frames.], tot_loss[loss=0.1795, simple_loss=0.244, pruned_loss=0.05754, over 972634.78 frames.], batch size: 29, lr: 8.29e-04
2022-05-04 01:47:02,714 INFO [train.py:715] (4/8) Epoch 1, batch 28500, loss[loss=0.1756, simple_loss=0.2339, pruned_loss=0.05866, over 4985.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2444, pruned_loss=0.05791, over 972789.64 frames.], batch size: 14, lr: 8.29e-04
2022-05-04 01:47:41,715 INFO [train.py:715] (4/8) Epoch 1, batch 28550, loss[loss=0.1894, simple_loss=0.2559, pruned_loss=0.06145, over 4989.00 frames.], tot_loss[loss=0.1805, simple_loss=0.2449, pruned_loss=0.05804, over 972608.79 frames.], batch size: 26, lr: 8.29e-04
2022-05-04 01:48:22,005 INFO [train.py:715] (4/8) Epoch 1, batch 28600, loss[loss=0.1527, simple_loss=0.211, pruned_loss=0.04716, over 4979.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2433, pruned_loss=0.0571, over 973050.41 frames.], batch size: 14, lr: 8.28e-04
2022-05-04 01:49:01,949 INFO [train.py:715] (4/8) Epoch 1, batch 28650, loss[loss=0.1609, simple_loss=0.2309, pruned_loss=0.04542, over 4779.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2448, pruned_loss=0.05794, over 972768.86 frames.], batch size: 12, lr: 8.28e-04
2022-05-04 01:49:41,101 INFO [train.py:715] (4/8) Epoch 1, batch 28700, loss[loss=0.1632, simple_loss=0.2295, pruned_loss=0.04841, over 4777.00 frames.], tot_loss[loss=0.1822, simple_loss=0.2463, pruned_loss=0.05909, over 972626.10 frames.], batch size: 14, lr: 8.28e-04
2022-05-04 01:50:20,242 INFO [train.py:715] (4/8) Epoch 1, batch 28750, loss[loss=0.2071, simple_loss=0.2774, pruned_loss=0.0684, over 4936.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2457, pruned_loss=0.05847, over 973072.76 frames.], batch size: 21, lr: 8.27e-04
2022-05-04 01:51:00,836 INFO [train.py:715] (4/8) Epoch 1, batch 28800, loss[loss=0.1677, simple_loss=0.2344, pruned_loss=0.05048, over 4693.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2455, pruned_loss=0.05803, over 971854.40 frames.], batch size: 15, lr: 8.27e-04
2022-05-04 01:51:40,145 INFO [train.py:715] (4/8) Epoch 1, batch 28850, loss[loss=0.1419, simple_loss=0.2109, pruned_loss=0.03648, over 4714.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2449, pruned_loss=0.05773, over 971031.63 frames.], batch size: 15, lr: 8.27e-04
2022-05-04 01:52:19,907 INFO [train.py:715] (4/8) Epoch 1, batch 28900, loss[loss=0.1629, simple_loss=0.2374, pruned_loss=0.04421, over 4946.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2444, pruned_loss=0.05772, over 971838.80 frames.], batch size: 21, lr: 8.27e-04
2022-05-04 01:53:00,603 INFO [train.py:715] (4/8) Epoch 1, batch 28950, loss[loss=0.1765, simple_loss=0.2422, pruned_loss=0.05535, over 4942.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2432, pruned_loss=0.05709, over 972172.92 frames.], batch size: 24, lr: 8.26e-04
2022-05-04 01:53:40,737 INFO [train.py:715] (4/8) Epoch 1, batch 29000, loss[loss=0.1822, simple_loss=0.2559, pruned_loss=0.05423, over 4745.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2421, pruned_loss=0.05636, over 972347.40 frames.], batch size: 19, lr: 8.26e-04
2022-05-04 01:54:19,716 INFO [train.py:715] (4/8) Epoch 1, batch 29050, loss[loss=0.1492, simple_loss=0.2097, pruned_loss=0.04437, over 4805.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2426, pruned_loss=0.05594, over 971676.57 frames.], batch size: 21, lr: 8.26e-04
2022-05-04 01:54:59,585 INFO [train.py:715] (4/8) Epoch 1, batch 29100, loss[loss=0.1755, simple_loss=0.2278, pruned_loss=0.06163, over 4812.00 frames.], tot_loss[loss=0.177, simple_loss=0.2425, pruned_loss=0.05576, over 971556.73 frames.], batch size: 13, lr: 8.25e-04
2022-05-04 01:55:40,265 INFO [train.py:715] (4/8) Epoch 1, batch 29150, loss[loss=0.1881, simple_loss=0.25, pruned_loss=0.06311, over 4991.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2444, pruned_loss=0.05712, over 972678.99 frames.], batch size: 14, lr: 8.25e-04
2022-05-04 01:56:22,372 INFO [train.py:715] (4/8) Epoch 1, batch 29200, loss[loss=0.1785, simple_loss=0.2438, pruned_loss=0.05663, over 4912.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2442, pruned_loss=0.05741, over 972843.40 frames.], batch size: 17, lr: 8.25e-04
2022-05-04 01:57:01,394 INFO [train.py:715] (4/8) Epoch 1, batch 29250, loss[loss=0.1856, simple_loss=0.2623, pruned_loss=0.05445, over 4925.00 frames.], tot_loss[loss=0.1808, simple_loss=0.2452, pruned_loss=0.05824, over 972688.69 frames.], batch size: 18, lr: 8.24e-04
2022-05-04 01:57:41,944 INFO [train.py:715] (4/8) Epoch 1, batch 29300, loss[loss=0.1666, simple_loss=0.229, pruned_loss=0.05212, over 4762.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2447, pruned_loss=0.05795, over 971661.20 frames.], batch size: 17, lr: 8.24e-04
2022-05-04 01:58:22,150 INFO [train.py:715] (4/8) Epoch 1, batch 29350, loss[loss=0.1698, simple_loss=0.2304, pruned_loss=0.05456, over 4855.00 frames.], tot_loss[loss=0.1799, simple_loss=0.2444, pruned_loss=0.05774, over 972336.27 frames.], batch size: 32, lr: 8.24e-04
2022-05-04 01:59:00,689 INFO [train.py:715] (4/8) Epoch 1, batch 29400, loss[loss=0.195, simple_loss=0.2737, pruned_loss=0.0581, over 4833.00 frames.], tot_loss[loss=0.1811, simple_loss=0.2456, pruned_loss=0.05828, over 971920.71 frames.], batch size: 26, lr: 8.23e-04
2022-05-04 01:59:40,306 INFO [train.py:715] (4/8) Epoch 1, batch 29450, loss[loss=0.17, simple_loss=0.2384, pruned_loss=0.05081, over 4913.00 frames.], tot_loss[loss=0.1807, simple_loss=0.245, pruned_loss=0.0582, over 971847.01 frames.], batch size: 39, lr: 8.23e-04
2022-05-04 02:00:20,004 INFO [train.py:715] (4/8) Epoch 1, batch 29500, loss[loss=0.1635, simple_loss=0.2336, pruned_loss=0.04673, over 4973.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2443, pruned_loss=0.05764, over 971497.72 frames.], batch size: 24, lr: 8.23e-04
2022-05-04 02:00:59,409 INFO [train.py:715] (4/8) Epoch 1, batch 29550, loss[loss=0.1663, simple_loss=0.2331, pruned_loss=0.04978, over 4983.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2436, pruned_loss=0.05729, over 972226.37 frames.], batch size: 14, lr: 8.22e-04
2022-05-04 02:01:37,991 INFO [train.py:715] (4/8) Epoch 1, batch 29600, loss[loss=0.1785, simple_loss=0.2443, pruned_loss=0.05637, over 4863.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2446, pruned_loss=0.05753, over 970929.91 frames.], batch size: 20, lr: 8.22e-04
2022-05-04 02:02:18,239 INFO [train.py:715] (4/8) Epoch 1, batch 29650, loss[loss=0.1779, simple_loss=0.2422, pruned_loss=0.05675, over 4928.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2447, pruned_loss=0.05805, over 971393.60 frames.], batch size: 29, lr: 8.22e-04
2022-05-04 02:02:58,331 INFO [train.py:715] (4/8) Epoch 1, batch 29700, loss[loss=0.1911, simple_loss=0.2477, pruned_loss=0.0673, over 4781.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2441, pruned_loss=0.0576, over 972242.29 frames.], batch size: 16, lr: 8.21e-04
2022-05-04 02:03:36,329 INFO [train.py:715] (4/8) Epoch 1, batch 29750, loss[loss=0.1588, simple_loss=0.232, pruned_loss=0.04276, over 4931.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2443, pruned_loss=0.05721, over 972643.56 frames.], batch size: 18, lr: 8.21e-04
2022-05-04 02:04:15,635 INFO [train.py:715] (4/8) Epoch 1, batch 29800, loss[loss=0.1469, simple_loss=0.2155, pruned_loss=0.03917, over 4875.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2429, pruned_loss=0.05639, over 973206.33 frames.], batch size: 22, lr: 8.21e-04
2022-05-04 02:04:55,050 INFO [train.py:715] (4/8) Epoch 1, batch 29850, loss[loss=0.221, simple_loss=0.2833, pruned_loss=0.07934, over 4851.00 frames.], tot_loss[loss=0.1785, simple_loss=0.243, pruned_loss=0.05703, over 973412.74 frames.], batch size: 15, lr: 8.20e-04
2022-05-04 02:05:34,428 INFO [train.py:715] (4/8) Epoch 1, batch 29900, loss[loss=0.1945, simple_loss=0.2552, pruned_loss=0.06684, over 4890.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2437, pruned_loss=0.05764, over 973451.88 frames.], batch size: 22, lr: 8.20e-04
2022-05-04 02:06:12,928 INFO [train.py:715] (4/8) Epoch 1, batch 29950, loss[loss=0.1722, simple_loss=0.2299, pruned_loss=0.05729, over 4770.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2425, pruned_loss=0.05693, over 973693.29 frames.], batch size: 18, lr: 8.20e-04
2022-05-04 02:06:52,735 INFO [train.py:715] (4/8) Epoch 1, batch 30000, loss[loss=0.1723, simple_loss=0.245, pruned_loss=0.04977, over 4897.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2433, pruned_loss=0.05691, over 973212.57 frames.], batch size: 19, lr: 8.20e-04
2022-05-04 02:06:52,736 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 02:07:09,691 INFO [train.py:742] (4/8) Epoch 1, validation: loss=0.1207, simple_loss=0.2076, pruned_loss=0.01687, over 914524.00 frames.
2022-05-04 02:07:50,180 INFO [train.py:715] (4/8) Epoch 1, batch 30050, loss[loss=0.1879, simple_loss=0.248, pruned_loss=0.06388, over 4959.00 frames.], tot_loss[loss=0.1791, simple_loss=0.244, pruned_loss=0.05714, over 973791.94 frames.], batch size: 24, lr: 8.19e-04
2022-05-04 02:08:29,663 INFO [train.py:715] (4/8) Epoch 1, batch 30100, loss[loss=0.1699, simple_loss=0.2349, pruned_loss=0.05239, over 4909.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2431, pruned_loss=0.05681, over 973580.76 frames.], batch size: 18, lr: 8.19e-04
2022-05-04 02:09:09,058 INFO [train.py:715] (4/8) Epoch 1, batch 30150, loss[loss=0.2415, simple_loss=0.2809, pruned_loss=0.101, over 4810.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2431, pruned_loss=0.0568, over 973192.45 frames.], batch size: 12, lr: 8.19e-04
2022-05-04 02:09:48,369 INFO [train.py:715] (4/8) Epoch 1, batch 30200, loss[loss=0.22, simple_loss=0.2958, pruned_loss=0.07211, over 4926.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2442, pruned_loss=0.05743, over 973505.78 frames.], batch size: 23, lr: 8.18e-04
2022-05-04 02:10:28,819 INFO [train.py:715] (4/8) Epoch 1, batch 30250, loss[loss=0.2009, simple_loss=0.2536, pruned_loss=0.07415, over 4880.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2447, pruned_loss=0.05788, over 972826.46 frames.], batch size: 32, lr: 8.18e-04
2022-05-04 02:11:08,797 INFO [train.py:715] (4/8) Epoch 1, batch 30300, loss[loss=0.1659, simple_loss=0.2315, pruned_loss=0.0501, over 4780.00 frames.], tot_loss[loss=0.1793, simple_loss=0.2437, pruned_loss=0.0574, over 972220.63 frames.], batch size: 18, lr: 8.18e-04
2022-05-04 02:11:47,710 INFO [train.py:715] (4/8) Epoch 1, batch 30350, loss[loss=0.1772, simple_loss=0.243, pruned_loss=0.05568, over 4804.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2437, pruned_loss=0.05739, over 971580.93 frames.], batch size: 25, lr: 8.17e-04
2022-05-04 02:12:27,773 INFO [train.py:715] (4/8) Epoch 1, batch 30400, loss[loss=0.1482, simple_loss=0.22, pruned_loss=0.0382, over 4907.00 frames.], tot_loss[loss=0.1792, simple_loss=0.244, pruned_loss=0.05721, over 971833.82 frames.], batch size: 19, lr: 8.17e-04
2022-05-04 02:13:07,269 INFO [train.py:715] (4/8) Epoch 1, batch 30450, loss[loss=0.1886, simple_loss=0.258, pruned_loss=0.05954, over 4746.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2455, pruned_loss=0.05749, over 971810.97 frames.], batch size: 16, lr: 8.17e-04
2022-05-04 02:13:46,440 INFO [train.py:715] (4/8) Epoch 1, batch 30500, loss[loss=0.1923, simple_loss=0.2601, pruned_loss=0.06225, over 4970.00 frames.], tot_loss[loss=0.1813, simple_loss=0.2455, pruned_loss=0.05851, over 971992.89 frames.], batch size: 39, lr: 8.16e-04
2022-05-04 02:14:25,541 INFO [train.py:715] (4/8) Epoch 1, batch 30550, loss[loss=0.1723, simple_loss=0.2298, pruned_loss=0.05742, over 4935.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2441, pruned_loss=0.05754, over 972603.31 frames.], batch size: 21, lr: 8.16e-04
2022-05-04 02:15:05,342 INFO [train.py:715] (4/8) Epoch 1, batch 30600, loss[loss=0.1321, simple_loss=0.1943, pruned_loss=0.03492, over 4793.00 frames.], tot_loss[loss=0.1798, simple_loss=0.2441, pruned_loss=0.05773, over 972462.60 frames.], batch size: 12, lr: 8.16e-04
2022-05-04 02:15:44,805 INFO [train.py:715] (4/8) Epoch 1, batch 30650, loss[loss=0.2171, simple_loss=0.2725, pruned_loss=0.08081, over 4769.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2441, pruned_loss=0.05742, over 972996.10 frames.], batch size: 18, lr: 8.15e-04
2022-05-04 02:16:23,387 INFO [train.py:715] (4/8) Epoch 1, batch 30700, loss[loss=0.1893, simple_loss=0.2513, pruned_loss=0.06363, over 4979.00 frames.], tot_loss[loss=0.1784, simple_loss=0.243, pruned_loss=0.05696, over 973627.63 frames.], batch size: 25, lr: 8.15e-04
2022-05-04 02:17:03,636 INFO [train.py:715] (4/8) Epoch 1, batch 30750, loss[loss=0.1536, simple_loss=0.2224, pruned_loss=0.04237, over 4978.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2424, pruned_loss=0.05661, over 973630.96 frames.], batch size: 14, lr: 8.15e-04
2022-05-04 02:17:43,207 INFO [train.py:715] (4/8) Epoch 1, batch 30800, loss[loss=0.1835, simple_loss=0.2439, pruned_loss=0.06162, over 4968.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2425, pruned_loss=0.05622, over 973797.85 frames.], batch size: 39, lr: 8.15e-04
2022-05-04 02:18:22,130 INFO [train.py:715] (4/8) Epoch 1, batch 30850, loss[loss=0.1623, simple_loss=0.2344, pruned_loss=0.04508, over 4816.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2423, pruned_loss=0.05647, over 972760.38 frames.], batch size: 26, lr: 8.14e-04
2022-05-04 02:19:01,714 INFO [train.py:715] (4/8) Epoch 1, batch 30900, loss[loss=0.1786, simple_loss=0.2209, pruned_loss=0.06817, over 4780.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2429, pruned_loss=0.05682, over 972654.78 frames.], batch size: 12, lr: 8.14e-04
2022-05-04 02:19:41,342 INFO [train.py:715] (4/8) Epoch 1, batch 30950, loss[loss=0.2042, simple_loss=0.2642, pruned_loss=0.07207, over 4809.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2436, pruned_loss=0.0569, over 972340.66 frames.], batch size: 25, lr: 8.14e-04
2022-05-04 02:20:20,851 INFO [train.py:715] (4/8) Epoch 1, batch 31000, loss[loss=0.1563, simple_loss=0.2264, pruned_loss=0.04311, over 4952.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2432, pruned_loss=0.05611, over 972533.50 frames.], batch size: 15, lr: 8.13e-04
2022-05-04 02:21:00,351 INFO [train.py:715] (4/8) Epoch 1, batch 31050, loss[loss=0.2535, simple_loss=0.2953, pruned_loss=0.1059, over 4822.00 frames.], tot_loss[loss=0.178, simple_loss=0.2434, pruned_loss=0.05625, over 972853.87 frames.], batch size: 15, lr: 8.13e-04
2022-05-04 02:21:40,837 INFO [train.py:715] (4/8) Epoch 1, batch 31100, loss[loss=0.1981, simple_loss=0.2605, pruned_loss=0.06782, over 4964.00 frames.], tot_loss[loss=0.1776, simple_loss=0.2428, pruned_loss=0.0562, over 972791.78 frames.], batch size: 39, lr: 8.13e-04
2022-05-04 02:22:20,581 INFO [train.py:715] (4/8) Epoch 1, batch 31150, loss[loss=0.189, simple_loss=0.2489, pruned_loss=0.06452, over 4903.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2436, pruned_loss=0.05657, over 972356.73 frames.], batch size: 19, lr: 8.12e-04
2022-05-04 02:22:59,624 INFO [train.py:715] (4/8) Epoch 1, batch 31200, loss[loss=0.1557, simple_loss=0.2146, pruned_loss=0.04836, over 4838.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2435, pruned_loss=0.05677, over 971977.09 frames.], batch size: 13, lr: 8.12e-04
2022-05-04 02:23:39,858 INFO [train.py:715] (4/8) Epoch 1, batch 31250, loss[loss=0.1818, simple_loss=0.2523, pruned_loss=0.05568, over 4953.00 frames.], tot_loss[loss=0.1802, simple_loss=0.2442, pruned_loss=0.05816, over 971931.15 frames.], batch size: 21, lr: 8.12e-04
2022-05-04 02:24:19,619 INFO [train.py:715] (4/8) Epoch 1, batch 31300, loss[loss=0.1788, simple_loss=0.2479, pruned_loss=0.05483, over 4818.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2443, pruned_loss=0.05818, over 972246.13 frames.], batch size: 27, lr: 8.11e-04
2022-05-04 02:24:59,060 INFO [train.py:715] (4/8) Epoch 1, batch 31350, loss[loss=0.2052, simple_loss=0.2681, pruned_loss=0.07111, over 4987.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2438, pruned_loss=0.05761, over 971630.52 frames.], batch size: 25, lr: 8.11e-04
2022-05-04 02:25:38,857 INFO [train.py:715] (4/8) Epoch 1, batch 31400, loss[loss=0.181, simple_loss=0.2459, pruned_loss=0.05808, over 4885.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2447, pruned_loss=0.05781, over 971628.17 frames.], batch size: 16, lr: 8.11e-04
2022-05-04 02:26:18,864 INFO [train.py:715] (4/8) Epoch 1, batch 31450, loss[loss=0.1891, simple_loss=0.2651, pruned_loss=0.05659, over 4841.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2439, pruned_loss=0.05743, over 972067.70 frames.], batch size: 20, lr: 8.11e-04
2022-05-04 02:26:58,728 INFO [train.py:715] (4/8) Epoch 1, batch 31500, loss[loss=0.1762, simple_loss=0.2419, pruned_loss=0.05526, over 4967.00 frames.], tot_loss[loss=0.18, simple_loss=0.2443, pruned_loss=0.05779, over 972373.92 frames.], batch size: 15, lr: 8.10e-04
2022-05-04 02:27:37,229 INFO [train.py:715] (4/8) Epoch 1, batch 31550, loss[loss=0.1601, simple_loss=0.2259, pruned_loss=0.0472, over 4834.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2434, pruned_loss=0.05737, over 972133.03 frames.], batch size: 15, lr: 8.10e-04
2022-05-04 02:28:17,414 INFO [train.py:715] (4/8) Epoch 1, batch 31600, loss[loss=0.172, simple_loss=0.2502, pruned_loss=0.04691, over 4835.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2436, pruned_loss=0.05758, over 971848.11 frames.], batch size: 15, lr: 8.10e-04
2022-05-04 02:28:57,103 INFO [train.py:715] (4/8) Epoch 1, batch 31650, loss[loss=0.2365, simple_loss=0.2821, pruned_loss=0.09538, over 4917.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2437, pruned_loss=0.05764, over 972708.83 frames.], batch size: 39, lr: 8.09e-04
2022-05-04 02:29:37,001 INFO [train.py:715] (4/8) Epoch 1, batch 31700, loss[loss=0.2095, simple_loss=0.2692, pruned_loss=0.07494, over 4917.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2435, pruned_loss=0.05675, over 972773.15 frames.], batch size: 18, lr: 8.09e-04
2022-05-04 02:30:16,362 INFO [train.py:715] (4/8) Epoch 1, batch 31750, loss[loss=0.2246, simple_loss=0.2792, pruned_loss=0.08506, over 4818.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2433, pruned_loss=0.05662, over 972763.15 frames.], batch size: 26, lr: 8.09e-04
2022-05-04 02:30:56,484 INFO [train.py:715] (4/8) Epoch 1, batch 31800, loss[loss=0.1278, simple_loss=0.1986, pruned_loss=0.02852, over 4844.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2434, pruned_loss=0.05693, over 973061.54 frames.], batch size: 26, lr: 8.08e-04
2022-05-04 02:31:36,270 INFO [train.py:715] (4/8) Epoch 1, batch 31850, loss[loss=0.1801, simple_loss=0.2348, pruned_loss=0.06268, over 4767.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2431, pruned_loss=0.05662, over 972118.95 frames.], batch size: 14, lr: 8.08e-04
2022-05-04 02:32:15,742 INFO [train.py:715] (4/8) Epoch 1, batch 31900, loss[loss=0.1594, simple_loss=0.2275, pruned_loss=0.04567, over 4813.00 frames.], tot_loss[loss=0.1771, simple_loss=0.242, pruned_loss=0.0561, over 972865.68 frames.], batch size: 12, lr: 8.08e-04
2022-05-04 02:32:55,106 INFO [train.py:715] (4/8) Epoch 1, batch 31950, loss[loss=0.1464, simple_loss=0.2155, pruned_loss=0.03865, over 4702.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2426, pruned_loss=0.05604, over 971834.04 frames.], batch size: 15, lr: 8.08e-04
2022-05-04 02:33:34,637 INFO [train.py:715] (4/8) Epoch 1, batch 32000, loss[loss=0.1703, simple_loss=0.2478, pruned_loss=0.04645, over 4752.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2417, pruned_loss=0.0553, over 970909.67 frames.], batch size: 19, lr: 8.07e-04
2022-05-04 02:34:14,067 INFO [train.py:715] (4/8) Epoch 1, batch 32050, loss[loss=0.1734, simple_loss=0.2475, pruned_loss=0.04961, over 4754.00 frames.], tot_loss[loss=0.176, simple_loss=0.2413, pruned_loss=0.05533, over 971137.04 frames.], batch size: 19, lr: 8.07e-04
2022-05-04 02:34:53,316 INFO [train.py:715] (4/8) Epoch 1, batch 32100, loss[loss=0.1458, simple_loss=0.2093, pruned_loss=0.04116, over 4968.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2429, pruned_loss=0.05639, over 971249.41 frames.], batch size: 35, lr: 8.07e-04
2022-05-04 02:35:32,938 INFO [train.py:715] (4/8) Epoch 1, batch 32150, loss[loss=0.1622, simple_loss=0.2386, pruned_loss=0.04288, over 4651.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2424, pruned_loss=0.05603, over 971036.41 frames.], batch size: 13, lr: 8.06e-04
2022-05-04 02:36:12,938 INFO [train.py:715] (4/8) Epoch 1, batch 32200, loss[loss=0.2456, simple_loss=0.286, pruned_loss=0.1026, over 4853.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2432, pruned_loss=0.05669, over 971598.90 frames.], batch size: 30, lr: 8.06e-04
2022-05-04 02:36:51,838 INFO [train.py:715] (4/8) Epoch 1, batch 32250, loss[loss=0.1849, simple_loss=0.2473, pruned_loss=0.06124, over 4782.00 frames.], tot_loss[loss=0.1791, simple_loss=0.2436, pruned_loss=0.05728, over 971473.81 frames.], batch size: 17, lr: 8.06e-04
2022-05-04 02:37:31,251 INFO [train.py:715] (4/8) Epoch 1, batch 32300, loss[loss=0.1699, simple_loss=0.2413, pruned_loss=0.04928, over 4923.00 frames.], tot_loss[loss=0.1782, simple_loss=0.243, pruned_loss=0.05664, over 971444.73 frames.], batch size: 21, lr: 8.05e-04
2022-05-04 02:38:10,686 INFO [train.py:715] (4/8) Epoch 1, batch 32350, loss[loss=0.2241, simple_loss=0.2705, pruned_loss=0.08886, over 4690.00 frames.], tot_loss[loss=0.1787, simple_loss=0.2434, pruned_loss=0.05701, over 971034.03 frames.], batch size: 15, lr: 8.05e-04
2022-05-04 02:38:50,280 INFO [train.py:715] (4/8) Epoch 1, batch 32400, loss[loss=0.2044, simple_loss=0.2672, pruned_loss=0.07075, over 4779.00 frames.], tot_loss[loss=0.1797, simple_loss=0.2443, pruned_loss=0.05749, over 971852.04 frames.], batch size: 18, lr: 8.05e-04
2022-05-04 02:39:29,214 INFO [train.py:715] (4/8) Epoch 1, batch 32450, loss[loss=0.2016, simple_loss=0.2607, pruned_loss=0.07128, over 4735.00 frames.], tot_loss[loss=0.1794, simple_loss=0.244, pruned_loss=0.05745, over 972342.58 frames.], batch size: 16, lr: 8.05e-04
2022-05-04 02:40:08,858 INFO [train.py:715] (4/8) Epoch 1, batch 32500, loss[loss=0.1614, simple_loss=0.2337, pruned_loss=0.04454, over 4982.00 frames.], tot_loss[loss=0.1794, simple_loss=0.2442, pruned_loss=0.05732, over 971547.04 frames.], batch size: 25, lr: 8.04e-04
2022-05-04 02:40:48,376 INFO [train.py:715] (4/8) Epoch 1, batch 32550, loss[loss=0.1596, simple_loss=0.2281, pruned_loss=0.04554, over 4941.00 frames.], tot_loss[loss=0.1795, simple_loss=0.2438, pruned_loss=0.05754, over 971597.22 frames.], batch size: 21, lr: 8.04e-04
2022-05-04 02:41:27,296 INFO [train.py:715] (4/8) Epoch 1, batch 32600, loss[loss=0.1586, simple_loss=0.2372, pruned_loss=0.03997, over 4986.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2439, pruned_loss=0.05764, over 972487.15 frames.], batch size: 26, lr: 8.04e-04
2022-05-04 02:42:06,688 INFO [train.py:715] (4/8) Epoch 1, batch 32650, loss[loss=0.1701, simple_loss=0.2311, pruned_loss=0.0545, over 4930.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2435, pruned_loss=0.05746, over 973197.04 frames.], batch size: 29, lr: 8.03e-04
2022-05-04 02:42:46,232 INFO [train.py:715] (4/8) Epoch 1, batch 32700, loss[loss=0.177, simple_loss=0.2401, pruned_loss=0.05695, over 4742.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2437, pruned_loss=0.05771, over 972705.11 frames.], batch size: 16, lr: 8.03e-04
2022-05-04 02:43:25,961 INFO [train.py:715] (4/8) Epoch 1, batch 32750, loss[loss=0.1752, simple_loss=0.251, pruned_loss=0.04969, over 4816.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2445, pruned_loss=0.05818, over 972351.28 frames.], batch size: 21, lr: 8.03e-04
2022-05-04 02:44:05,921 INFO [train.py:715] (4/8) Epoch 1, batch 32800, loss[loss=0.1823, simple_loss=0.2455, pruned_loss=0.05957, over 4848.00 frames.], tot_loss[loss=0.1806, simple_loss=0.245, pruned_loss=0.05813, over 971840.94 frames.], batch size: 20, lr: 8.02e-04
2022-05-04 02:44:45,555 INFO [train.py:715] (4/8) Epoch 1, batch 32850, loss[loss=0.1365, simple_loss=0.2067, pruned_loss=0.03317, over 4923.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2442, pruned_loss=0.05753, over 970630.61 frames.], batch size: 29, lr: 8.02e-04
2022-05-04 02:45:24,930 INFO [train.py:715] (4/8) Epoch 1, batch 32900, loss[loss=0.1692, simple_loss=0.2407, pruned_loss=0.04883, over 4742.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2432, pruned_loss=0.05697, over 970830.68 frames.], batch size: 16, lr: 8.02e-04
2022-05-04 02:46:04,179 INFO [train.py:715] (4/8) Epoch 1, batch 32950, loss[loss=0.1929, simple_loss=0.2574, pruned_loss=0.06421, over 4919.00 frames.], tot_loss[loss=0.18, simple_loss=0.2443, pruned_loss=0.05789, over 970711.36 frames.], batch size: 29, lr: 8.02e-04
2022-05-04 02:46:43,642 INFO [train.py:715] (4/8) Epoch 1, batch 33000, loss[loss=0.191, simple_loss=0.2499, pruned_loss=0.06599, over 4953.00 frames.], tot_loss[loss=0.18, simple_loss=0.2443, pruned_loss=0.05786, over 970568.08 frames.], batch size: 21, lr: 8.01e-04
2022-05-04 02:46:43,642 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 02:46:52,424 INFO [train.py:742] (4/8) Epoch 1, validation: loss=0.1208, simple_loss=0.2074, pruned_loss=0.01714, over 914524.00 frames.
2022-05-04 02:47:32,101 INFO [train.py:715] (4/8) Epoch 1, batch 33050, loss[loss=0.1692, simple_loss=0.2425, pruned_loss=0.04797, over 4858.00 frames.], tot_loss[loss=0.1796, simple_loss=0.244, pruned_loss=0.05764, over 970355.03 frames.], batch size: 20, lr: 8.01e-04
2022-05-04 02:48:12,127 INFO [train.py:715] (4/8) Epoch 1, batch 33100, loss[loss=0.1771, simple_loss=0.2525, pruned_loss=0.05086, over 4849.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2427, pruned_loss=0.05658, over 971131.50 frames.], batch size: 30, lr: 8.01e-04
2022-05-04 02:48:52,000 INFO [train.py:715] (4/8) Epoch 1, batch 33150, loss[loss=0.1909, simple_loss=0.2764, pruned_loss=0.05266, over 4787.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2435, pruned_loss=0.05683, over 971101.72 frames.], batch size: 17, lr: 8.00e-04
2022-05-04 02:49:31,137 INFO [train.py:715] (4/8) Epoch 1, batch 33200, loss[loss=0.1367, simple_loss=0.2011, pruned_loss=0.03609, over 4835.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2435, pruned_loss=0.05691, over 971664.79 frames.], batch size: 26, lr: 8.00e-04
2022-05-04 02:50:11,557 INFO [train.py:715] (4/8) Epoch 1, batch 33250, loss[loss=0.2266, simple_loss=0.29, pruned_loss=0.08157, over 4781.00 frames.], tot_loss[loss=0.1795, simple_loss=0.244, pruned_loss=0.05749, over 970817.78 frames.], batch size: 14, lr: 8.00e-04
2022-05-04 02:50:51,590 INFO [train.py:715] (4/8) Epoch 1, batch 33300, loss[loss=0.1773, simple_loss=0.2389, pruned_loss=0.0579, over 4799.00 frames.], tot_loss[loss=0.1792, simple_loss=0.2442, pruned_loss=0.05707, over 971879.74 frames.], batch size: 21, lr: 8.00e-04
2022-05-04 02:51:31,060 INFO [train.py:715] (4/8) Epoch 1, batch 33350, loss[loss=0.1728, simple_loss=0.2438, pruned_loss=0.05094, over 4986.00 frames.], tot_loss[loss=0.1803, simple_loss=0.2453, pruned_loss=0.05769, over 972304.93 frames.], batch size: 25, lr: 7.99e-04
2022-05-04 02:52:11,435 INFO [train.py:715] (4/8) Epoch 1, batch 33400, loss[loss=0.1754, simple_loss=0.2456, pruned_loss=0.05256, over 4756.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2441, pruned_loss=0.05681, over 972505.83 frames.], batch size: 19, lr: 7.99e-04
2022-05-04 02:52:51,301 INFO [train.py:715] (4/8) Epoch 1, batch 33450, loss[loss=0.173, simple_loss=0.245, pruned_loss=0.05047, over 4877.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2439, pruned_loss=0.05686, over 972857.69 frames.], batch size: 22, lr: 7.99e-04
2022-05-04 02:53:30,409 INFO [train.py:715] (4/8) Epoch 1, batch 33500, loss[loss=0.1779, simple_loss=0.2466, pruned_loss=0.05458, over 4902.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2436, pruned_loss=0.05643, over 973450.49 frames.], batch size: 22, lr: 7.98e-04
2022-05-04 02:54:10,337 INFO [train.py:715] (4/8) Epoch 1, batch 33550, loss[loss=0.2372, simple_loss=0.2805, pruned_loss=0.09693, over 4849.00 frames.], tot_loss[loss=0.1781, simple_loss=0.243, pruned_loss=0.0566, over 973223.73 frames.], batch size: 15, lr: 7.98e-04
2022-05-04 02:54:50,183 INFO [train.py:715] (4/8) Epoch 1, batch 33600, loss[loss=0.1794, simple_loss=0.2385, pruned_loss=0.06016, over 4824.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2437, pruned_loss=0.05707, over 973852.28 frames.], batch size: 15, lr: 7.98e-04
2022-05-04 02:55:29,606 INFO [train.py:715] (4/8) Epoch 1, batch 33650, loss[loss=0.1404, simple_loss=0.2102, pruned_loss=0.03535, over 4782.00 frames.], tot_loss[loss=0.1796, simple_loss=0.2445, pruned_loss=0.05732, over 972807.21 frames.], batch size: 17, lr: 7.97e-04
2022-05-04 02:56:08,650 INFO [train.py:715] (4/8) Epoch 1, batch 33700, loss[loss=0.1557, simple_loss=0.2259, pruned_loss=0.04273, over 4849.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2439, pruned_loss=0.05692, over 972209.56 frames.], batch size: 20, lr: 7.97e-04
2022-05-04 02:56:47,806 INFO [train.py:715] (4/8) Epoch 1, batch 33750, loss[loss=0.1441, simple_loss=0.2158, pruned_loss=0.0362, over 4924.00 frames.], tot_loss[loss=0.1781, simple_loss=0.2429, pruned_loss=0.05658, over 972344.75 frames.], batch size: 21, lr: 7.97e-04
2022-05-04 02:57:27,452 INFO [train.py:715] (4/8) Epoch 1, batch 33800, loss[loss=0.1693, simple_loss=0.2383, pruned_loss=0.05018, over 4811.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2434, pruned_loss=0.05658, over 972049.37 frames.], batch size: 27, lr: 7.97e-04
2022-05-04 02:58:06,283 INFO [train.py:715] (4/8) Epoch 1, batch 33850, loss[loss=0.2057, simple_loss=0.2664, pruned_loss=0.07245, over 4738.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2434, pruned_loss=0.05667, over 971496.93 frames.], batch size: 16, lr: 7.96e-04
2022-05-04 02:58:45,801 INFO [train.py:715] (4/8) Epoch 1, batch 33900, loss[loss=0.1726, simple_loss=0.2441, pruned_loss=0.0506, over 4981.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2426, pruned_loss=0.05606, over 971401.69 frames.], batch size: 24, lr: 7.96e-04
2022-05-04 02:59:25,365 INFO [train.py:715] (4/8) Epoch 1, batch 33950, loss[loss=0.1811, simple_loss=0.247, pruned_loss=0.05759, over 4814.00 frames.], tot_loss[loss=0.1778, simple_loss=0.243, pruned_loss=0.05627, over 971069.85 frames.], batch size: 25, lr: 7.96e-04
2022-05-04 03:00:05,091 INFO [train.py:715] (4/8) Epoch 1, batch 34000, loss[loss=0.1836, simple_loss=0.2479, pruned_loss=0.05964, over 4965.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2423, pruned_loss=0.0556, over 971325.92 frames.], batch size: 15, lr: 7.95e-04
2022-05-04 03:00:44,412 INFO [train.py:715] (4/8) Epoch 1, batch 34050, loss[loss=0.1983, simple_loss=0.2654, pruned_loss=0.06563, over 4826.00 frames.], tot_loss[loss=0.1783, simple_loss=0.2436, pruned_loss=0.05649, over 971367.50 frames.], batch size: 26, lr: 7.95e-04
2022-05-04 03:01:23,796 INFO [train.py:715] (4/8) Epoch 1, batch 34100, loss[loss=0.1718, simple_loss=0.238, pruned_loss=0.05278, over 4727.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2437, pruned_loss=0.05651, over 971866.58 frames.], batch size: 12, lr: 7.95e-04
2022-05-04 03:02:03,181 INFO [train.py:715] (4/8) Epoch 1, batch 34150, loss[loss=0.172, simple_loss=0.2425, pruned_loss=0.05072, over 4956.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2428, pruned_loss=0.05602, over 971491.55 frames.], batch size: 39, lr: 7.95e-04
2022-05-04 03:02:42,209 INFO [train.py:715] (4/8) Epoch 1, batch 34200, loss[loss=0.1736, simple_loss=0.2454, pruned_loss=0.05095, over 4975.00 frames.], tot_loss[loss=0.1763, simple_loss=0.242, pruned_loss=0.05529, over 973185.37 frames.], batch size: 15, lr: 7.94e-04
2022-05-04 03:03:21,755 INFO [train.py:715] (4/8) Epoch 1, batch 34250, loss[loss=0.171, simple_loss=0.2399, pruned_loss=0.05106, over 4688.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2427, pruned_loss=0.05597, over 972473.80 frames.], batch size: 15, lr: 7.94e-04
2022-05-04 03:04:01,436 INFO [train.py:715] (4/8) Epoch 1, batch 34300, loss[loss=0.23, simple_loss=0.2819, pruned_loss=0.08902, over 4748.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2422, pruned_loss=0.0558, over 972251.09 frames.], batch size: 16, lr: 7.94e-04
2022-05-04 03:04:40,847 INFO [train.py:715] (4/8) Epoch 1, batch 34350, loss[loss=0.155, simple_loss=0.2188, pruned_loss=0.04556, over 4773.00 frames.], tot_loss[loss=0.1771, simple_loss=0.2423, pruned_loss=0.05591, over 972629.87 frames.], batch size: 17, lr: 7.93e-04
2022-05-04 03:05:19,751 INFO [train.py:715] (4/8) Epoch 1, batch 34400, loss[loss=0.1495, simple_loss=0.2194, pruned_loss=0.03982, over 4817.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2434, pruned_loss=0.0572, over 972284.62 frames.], batch size: 13, lr: 7.93e-04
2022-05-04 03:05:59,255 INFO [train.py:715] (4/8) Epoch 1, batch 34450, loss[loss=0.1881, simple_loss=0.245, pruned_loss=0.06564, over 4772.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2425, pruned_loss=0.05699, over 972454.16 frames.], batch size: 14, lr: 7.93e-04
2022-05-04 03:06:38,479 INFO [train.py:715] (4/8) Epoch 1, batch 34500, loss[loss=0.2075, simple_loss=0.2831, pruned_loss=0.06592, over 4824.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2428, pruned_loss=0.05734, over 971860.42 frames.], batch size: 25, lr: 7.93e-04
2022-05-04 03:07:17,762 INFO [train.py:715] (4/8) Epoch 1, batch 34550, loss[loss=0.2134, simple_loss=0.2692, pruned_loss=0.07884, over 4691.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2428, pruned_loss=0.05699, over 971895.10 frames.], batch size: 15, lr: 7.92e-04
2022-05-04 03:07:57,340 INFO [train.py:715] (4/8) Epoch 1, batch 34600, loss[loss=0.2005, simple_loss=0.2586, pruned_loss=0.07117, over 4850.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2433, pruned_loss=0.05698, over 971817.06 frames.], batch size: 34, lr: 7.92e-04
2022-05-04 03:08:37,227 INFO [train.py:715] (4/8) Epoch 1, batch 34650, loss[loss=0.1803, simple_loss=0.2436, pruned_loss=0.05845, over 4901.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2417, pruned_loss=0.05589, over 972337.03 frames.], batch size: 17, lr: 7.92e-04
2022-05-04 03:09:17,429 INFO [train.py:715] (4/8) Epoch 1, batch 34700, loss[loss=0.1626, simple_loss=0.2282, pruned_loss=0.04846, over 4749.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2415, pruned_loss=0.05588, over 972725.52 frames.], batch size: 16, lr: 7.91e-04
2022-05-04 03:09:55,738 INFO [train.py:715] (4/8) Epoch 1, batch 34750, loss[loss=0.1334, simple_loss=0.2018, pruned_loss=0.03252, over 4789.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2424, pruned_loss=0.05657, over 973149.05 frames.], batch size: 18, lr: 7.91e-04
2022-05-04 03:10:32,243 INFO [train.py:715] (4/8) Epoch 1, batch 34800, loss[loss=0.1727, simple_loss=0.2391, pruned_loss=0.05313, over 4952.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2426, pruned_loss=0.05587, over 973907.20 frames.], batch size: 21, lr: 7.91e-04
2022-05-04 03:11:25,702 INFO [train.py:715] (4/8) Epoch 2, batch 0, loss[loss=0.2015, simple_loss=0.2571, pruned_loss=0.07295, over 4897.00 frames.], tot_loss[loss=0.2015, simple_loss=0.2571, pruned_loss=0.07295, over 4897.00 frames.], batch size: 32, lr: 7.59e-04
2022-05-04 03:12:05,766 INFO [train.py:715] (4/8) Epoch 2, batch 50, loss[loss=0.1934, simple_loss=0.2485, pruned_loss=0.06912, over 4869.00 frames.], tot_loss[loss=0.1807, simple_loss=0.2435, pruned_loss=0.05897, over 219932.16 frames.], batch size: 32, lr: 7.59e-04
2022-05-04 03:12:46,578 INFO [train.py:715] (4/8) Epoch 2, batch 100, loss[loss=0.234, simple_loss=0.283, pruned_loss=0.09253, over 4909.00 frames.], tot_loss[loss=0.177, simple_loss=0.242, pruned_loss=0.05601, over 386604.16 frames.], batch size: 17, lr: 7.59e-04
2022-05-04 03:13:27,194 INFO [train.py:715] (4/8) Epoch 2, batch 150, loss[loss=0.1755, simple_loss=0.2518, pruned_loss=0.04964, over 4834.00 frames.], tot_loss[loss=0.1778, simple_loss=0.2423, pruned_loss=0.05661, over 517018.85 frames.], batch size: 15, lr: 7.59e-04
2022-05-04 03:14:07,258 INFO [train.py:715] (4/8) Epoch 2, batch 200, loss[loss=0.1901, simple_loss=0.2564, pruned_loss=0.06188, over 4983.00 frames.], tot_loss[loss=0.1777, simple_loss=0.2428, pruned_loss=0.05633, over 618750.86 frames.], batch size: 16, lr: 7.58e-04
2022-05-04 03:14:48,046 INFO [train.py:715] (4/8) Epoch 2, batch 250, loss[loss=0.1411, simple_loss=0.2058, pruned_loss=0.03818, over 4982.00 frames.], tot_loss[loss=0.1784, simple_loss=0.2436, pruned_loss=0.0566, over 697795.98 frames.], batch size: 25, lr: 7.58e-04
2022-05-04 03:15:29,373 INFO [train.py:715] (4/8) Epoch 2, batch 300, loss[loss=0.1491, simple_loss=0.2134, pruned_loss=0.04242, over 4784.00 frames.], tot_loss[loss=0.1782, simple_loss=0.2436, pruned_loss=0.05637, over 758064.32 frames.], batch size: 17, lr: 7.58e-04
2022-05-04 03:16:10,299 INFO [train.py:715] (4/8) Epoch 2, batch 350, loss[loss=0.1501, simple_loss=0.2233, pruned_loss=0.03842, over 4885.00 frames.], tot_loss[loss=0.178, simple_loss=0.2433, pruned_loss=0.0563, over 806251.06 frames.], batch size: 22, lr: 7.57e-04
2022-05-04 03:16:49,962 INFO [train.py:715] (4/8) Epoch 2, batch 400, loss[loss=0.1807, simple_loss=0.2462, pruned_loss=0.05761, over 4971.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2439, pruned_loss=0.05692, over 843517.55 frames.], batch size: 24, lr: 7.57e-04
2022-05-04 03:17:30,474 INFO [train.py:715] (4/8) Epoch 2, batch 450, loss[loss=0.1999, simple_loss=0.2591, pruned_loss=0.07035, over 4802.00 frames.], tot_loss[loss=0.1788, simple_loss=0.2437, pruned_loss=0.05699, over 871597.48 frames.], batch size: 17, lr: 7.57e-04
2022-05-04 03:18:11,614 INFO [train.py:715] (4/8) Epoch 2, batch 500, loss[loss=0.1611, simple_loss=0.2286, pruned_loss=0.04674, over 4940.00 frames.], tot_loss[loss=0.1789, simple_loss=0.2434, pruned_loss=0.05717, over 893365.06 frames.], batch size: 23, lr: 7.57e-04
2022-05-04 03:18:51,547 INFO [train.py:715] (4/8) Epoch 2, batch 550, loss[loss=0.1897, simple_loss=0.2489, pruned_loss=0.0652, over 4887.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2432, pruned_loss=0.05699, over 910720.51 frames.], batch size: 38, lr: 7.56e-04
2022-05-04 03:19:31,927 INFO [train.py:715] (4/8) Epoch 2, batch 600, loss[loss=0.1921, simple_loss=0.2503, pruned_loss=0.06696, over 4749.00 frames.], tot_loss[loss=0.1801, simple_loss=0.2444, pruned_loss=0.05797, over 924085.89 frames.], batch size: 16, lr: 7.56e-04
2022-05-04 03:20:12,749 INFO [train.py:715] (4/8) Epoch 2, batch 650, loss[loss=0.2097, simple_loss=0.2804, pruned_loss=0.06947, over 4913.00 frames.], tot_loss[loss=0.1804, simple_loss=0.2448, pruned_loss=0.05799, over 934531.10 frames.], batch size: 39, lr: 7.56e-04
2022-05-04 03:20:53,344 INFO [train.py:715] (4/8) Epoch 2, batch 700, loss[loss=0.1518, simple_loss=0.2158, pruned_loss=0.04389, over 4881.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2437, pruned_loss=0.05673, over 943004.74 frames.], batch size: 19, lr: 7.56e-04
2022-05-04 03:21:32,898 INFO [train.py:715] (4/8) Epoch 2, batch 750, loss[loss=0.1713, simple_loss=0.2368, pruned_loss=0.05284, over 4955.00 frames.], tot_loss[loss=0.1791, simple_loss=0.244, pruned_loss=0.05706, over 950119.91 frames.], batch size: 24, lr: 7.55e-04
2022-05-04 03:22:13,340 INFO [train.py:715] (4/8) Epoch 2, batch 800, loss[loss=0.1675, simple_loss=0.2271, pruned_loss=0.05395, over 4841.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2435, pruned_loss=0.05676, over 956206.33 frames.], batch size: 13, lr: 7.55e-04
2022-05-04 03:22:54,008 INFO [train.py:715] (4/8) Epoch 2, batch 850, loss[loss=0.1966, simple_loss=0.2485, pruned_loss=0.07231, over 4790.00 frames.], tot_loss[loss=0.1785, simple_loss=0.2438, pruned_loss=0.05664, over 959593.37 frames.], batch size: 14, lr: 7.55e-04
2022-05-04 03:23:34,283 INFO [train.py:715] (4/8) Epoch 2, batch 900, loss[loss=0.1711, simple_loss=0.2314, pruned_loss=0.05535, over 4868.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2427, pruned_loss=0.05591, over 962066.46 frames.], batch size: 32, lr: 7.55e-04
2022-05-04 03:24:14,706 INFO [train.py:715] (4/8) Epoch 2, batch 950, loss[loss=0.167, simple_loss=0.2368, pruned_loss=0.04859, over 4973.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2415, pruned_loss=0.05568, over 964525.60 frames.], batch size: 14, lr: 7.54e-04
2022-05-04 03:24:55,391 INFO [train.py:715] (4/8) Epoch 2, batch 1000, loss[loss=0.1587, simple_loss=0.2301, pruned_loss=0.04365, over 4877.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2424, pruned_loss=0.05611, over 966920.32 frames.], batch size: 16, lr: 7.54e-04
2022-05-04 03:25:36,194 INFO [train.py:715] (4/8) Epoch 2, batch 1050, loss[loss=0.1877, simple_loss=0.2624, pruned_loss=0.05648, over 4764.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2425, pruned_loss=0.05625, over 967892.48 frames.], batch size: 19, lr: 7.54e-04
2022-05-04 03:26:15,799 INFO [train.py:715] (4/8) Epoch 2, batch 1100, loss[loss=0.1822, simple_loss=0.2467, pruned_loss=0.05884, over 4815.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2424, pruned_loss=0.05599, over 968457.88 frames.], batch size: 12, lr: 7.53e-04
2022-05-04 03:26:56,314 INFO [train.py:715] (4/8) Epoch 2, batch 1150, loss[loss=0.1973, simple_loss=0.255, pruned_loss=0.06977, over 4974.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2423, pruned_loss=0.05622, over 969260.79 frames.], batch size: 14, lr: 7.53e-04
2022-05-04 03:27:37,630 INFO [train.py:715] (4/8) Epoch 2, batch 1200, loss[loss=0.1984, simple_loss=0.2626, pruned_loss=0.06716, over 4974.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2423, pruned_loss=0.05634, over 969724.30 frames.], batch size: 24, lr: 7.53e-04
2022-05-04 03:28:18,247 INFO [train.py:715] (4/8) Epoch 2, batch 1250, loss[loss=0.1571, simple_loss=0.2308, pruned_loss=0.04172, over 4833.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2412, pruned_loss=0.05553, over 970624.46 frames.], batch size: 20, lr: 7.53e-04
2022-05-04 03:28:57,933 INFO [train.py:715] (4/8) Epoch 2, batch 1300, loss[loss=0.152, simple_loss=0.2255, pruned_loss=0.03921, over 4924.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2415, pruned_loss=0.05589, over 970604.47 frames.], batch size: 29, lr: 7.52e-04
2022-05-04 03:29:38,470 INFO [train.py:715] (4/8) Epoch 2, batch 1350, loss[loss=0.1705, simple_loss=0.2375, pruned_loss=0.05174, over 4908.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2408, pruned_loss=0.05535, over 971165.31 frames.], batch size: 18, lr: 7.52e-04
2022-05-04 03:30:19,101 INFO [train.py:715] (4/8) Epoch 2, batch 1400, loss[loss=0.1424, simple_loss=0.2054, pruned_loss=0.03975, over 4771.00 frames.], tot_loss[loss=0.176, simple_loss=0.241, pruned_loss=0.05548, over 971278.61 frames.], batch size: 12, lr: 7.52e-04
2022-05-04 03:30:59,073 INFO [train.py:715] (4/8) Epoch 2, batch 1450, loss[loss=0.182, simple_loss=0.2378, pruned_loss=0.06304, over 4981.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2406, pruned_loss=0.05512, over 971767.48 frames.], batch size: 35, lr: 7.52e-04
2022-05-04 03:31:39,477 INFO [train.py:715] (4/8) Epoch 2, batch 1500, loss[loss=0.2153, simple_loss=0.2744, pruned_loss=0.0781, over 4931.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2406, pruned_loss=0.05485, over 972368.03 frames.], batch size: 39, lr: 7.51e-04
2022-05-04 03:32:20,476 INFO [train.py:715] (4/8) Epoch 2, batch 1550, loss[loss=0.1578, simple_loss=0.2255, pruned_loss=0.04509, over 4867.00 frames.], tot_loss[loss=0.175, simple_loss=0.2408, pruned_loss=0.05462, over 971344.28 frames.], batch size: 32, lr: 7.51e-04
2022-05-04 03:33:00,533 INFO [train.py:715] (4/8) Epoch 2, batch 1600, loss[loss=0.1839, simple_loss=0.2532, pruned_loss=0.05731, over 4986.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2413, pruned_loss=0.05522, over 971116.16 frames.], batch size: 39, lr: 7.51e-04
2022-05-04 03:33:40,353 INFO [train.py:715] (4/8) Epoch 2, batch 1650, loss[loss=0.1416, simple_loss=0.2213, pruned_loss=0.03089, over 4984.00 frames.], tot_loss[loss=0.1768, simple_loss=0.2426, pruned_loss=0.0555, over 971880.08 frames.], batch size: 24, lr: 7.51e-04
2022-05-04 03:34:21,224 INFO [train.py:715] (4/8) Epoch 2, batch 1700, loss[loss=0.1806, simple_loss=0.242, pruned_loss=0.05955, over 4882.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2426, pruned_loss=0.05589, over 972978.22 frames.], batch size: 22, lr: 7.50e-04
2022-05-04 03:35:02,267 INFO [train.py:715] (4/8) Epoch 2, batch 1750, loss[loss=0.1925, simple_loss=0.2535, pruned_loss=0.06576, over 4809.00 frames.], tot_loss[loss=0.178, simple_loss=0.2429, pruned_loss=0.05652, over 972592.92 frames.], batch size: 26, lr: 7.50e-04
2022-05-04 03:35:42,177 INFO [train.py:715] (4/8) Epoch 2, batch 1800, loss[loss=0.1792, simple_loss=0.2466, pruned_loss=0.05588, over 4856.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2425, pruned_loss=0.05609, over 972874.74 frames.], batch size: 20, lr: 7.50e-04
2022-05-04 03:36:22,538 INFO [train.py:715] (4/8) Epoch 2, batch 1850, loss[loss=0.1703, simple_loss=0.2354, pruned_loss=0.05261, over 4936.00 frames.], tot_loss[loss=0.1786, simple_loss=0.2434, pruned_loss=0.05687, over 972410.36 frames.], batch size: 29, lr: 7.50e-04
2022-05-04 03:37:03,508 INFO [train.py:715] (4/8) Epoch 2, batch 1900, loss[loss=0.1822, simple_loss=0.2601, pruned_loss=0.05209, over 4754.00 frames.], tot_loss[loss=0.1772, simple_loss=0.2429, pruned_loss=0.05573, over 973192.65 frames.], batch size: 14, lr: 7.49e-04
2022-05-04 03:37:44,291 INFO [train.py:715] (4/8) Epoch 2, batch 1950, loss[loss=0.2056, simple_loss=0.2555, pruned_loss=0.07784, over 4838.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2427, pruned_loss=0.05553, over 972463.03 frames.], batch size: 15, lr: 7.49e-04
2022-05-04 03:38:24,072 INFO [train.py:715] (4/8) Epoch 2, batch 2000, loss[loss=0.1723, simple_loss=0.2349, pruned_loss=0.05482, over 4811.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2423, pruned_loss=0.05537, over 972754.45 frames.], batch size: 25, lr: 7.49e-04
2022-05-04 03:39:04,253 INFO [train.py:715] (4/8) Epoch 2, batch 2050, loss[loss=0.1561, simple_loss=0.2241, pruned_loss=0.04408, over 4909.00 frames.], tot_loss[loss=0.1766, simple_loss=0.2423, pruned_loss=0.05546, over 972656.55 frames.], batch size: 17, lr: 7.48e-04
2022-05-04 03:39:45,382 INFO [train.py:715] (4/8) Epoch 2, batch 2100, loss[loss=0.1261, simple_loss=0.1915, pruned_loss=0.03039, over 4875.00 frames.], tot_loss[loss=0.176, simple_loss=0.2418, pruned_loss=0.05509, over 973014.84 frames.], batch size: 16, lr: 7.48e-04
2022-05-04 03:40:25,359 INFO [train.py:715] (4/8) Epoch 2, batch 2150, loss[loss=0.1833, simple_loss=0.2444, pruned_loss=0.06112, over 4753.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2414, pruned_loss=0.0551, over 972869.54 frames.], batch size: 16, lr: 7.48e-04
2022-05-04 03:41:04,883 INFO [train.py:715] (4/8) Epoch 2, batch 2200, loss[loss=0.153, simple_loss=0.2198, pruned_loss=0.04313, over 4933.00 frames.], tot_loss[loss=0.175, simple_loss=0.2404, pruned_loss=0.05475, over 972680.39 frames.], batch size: 23, lr: 7.48e-04
2022-05-04 03:41:45,606 INFO [train.py:715] (4/8) Epoch 2, batch 2250, loss[loss=0.186, simple_loss=0.2543, pruned_loss=0.05883, over 4928.00 frames.], tot_loss[loss=0.175, simple_loss=0.2402, pruned_loss=0.05488, over 972985.06 frames.], batch size: 18, lr: 7.47e-04
2022-05-04 03:42:26,408 INFO [train.py:715] (4/8) Epoch 2, batch 2300, loss[loss=0.1715, simple_loss=0.2404, pruned_loss=0.05129, over 4887.00 frames.], tot_loss[loss=0.175, simple_loss=0.24, pruned_loss=0.05501, over 972098.96 frames.], batch size: 16, lr: 7.47e-04
2022-05-04 03:43:05,609 INFO [train.py:715] (4/8) Epoch 2, batch 2350, loss[loss=0.1672, simple_loss=0.2432, pruned_loss=0.04561, over 4818.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2397, pruned_loss=0.05428, over 972366.57 frames.], batch size: 25, lr: 7.47e-04
2022-05-04 03:43:48,322 INFO [train.py:715] (4/8) Epoch 2, batch 2400, loss[loss=0.2018, simple_loss=0.2693, pruned_loss=0.06718, over 4847.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2398, pruned_loss=0.05434, over 971834.34 frames.], batch size: 32, lr: 7.47e-04
2022-05-04 03:44:29,313 INFO [train.py:715] (4/8) Epoch 2, batch 2450, loss[loss=0.2016, simple_loss=0.2664, pruned_loss=0.06839, over 4776.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2403, pruned_loss=0.05467, over 972033.38 frames.], batch size: 18, lr: 7.46e-04
2022-05-04 03:45:09,453 INFO [train.py:715] (4/8) Epoch 2, batch 2500, loss[loss=0.185, simple_loss=0.261, pruned_loss=0.0545, over 4904.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2404, pruned_loss=0.05472, over 971927.69 frames.], batch size: 18, lr: 7.46e-04
2022-05-04 03:45:49,045 INFO [train.py:715] (4/8) Epoch 2, batch 2550, loss[loss=0.1762, simple_loss=0.2386, pruned_loss=0.05693, over 4987.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2415, pruned_loss=0.05556, over 971166.35 frames.], batch size: 28, lr: 7.46e-04
2022-05-04 03:46:29,870 INFO [train.py:715] (4/8) Epoch 2, batch 2600, loss[loss=0.2055, simple_loss=0.2653, pruned_loss=0.07289, over 4807.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2421, pruned_loss=0.0559, over 971089.13 frames.], batch size: 14, lr: 7.46e-04
2022-05-04 03:47:10,390 INFO [train.py:715] (4/8) Epoch 2, batch 2650, loss[loss=0.166, simple_loss=0.2285, pruned_loss=0.05172, over 4921.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2414, pruned_loss=0.05576, over 971847.22 frames.], batch size: 18, lr: 7.45e-04
2022-05-04 03:47:49,282 INFO [train.py:715] (4/8) Epoch 2, batch 2700, loss[loss=0.1978, simple_loss=0.2651, pruned_loss=0.06522, over 4816.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2418, pruned_loss=0.05554, over 972723.48 frames.], batch size: 27, lr: 7.45e-04
2022-05-04 03:48:29,304 INFO [train.py:715] (4/8) Epoch 2, batch 2750, loss[loss=0.1708, simple_loss=0.2371, pruned_loss=0.05223, over 4881.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2415, pruned_loss=0.05551, over 973213.86 frames.], batch size: 22, lr: 7.45e-04
2022-05-04 03:49:10,374 INFO [train.py:715] (4/8) Epoch 2, batch 2800, loss[loss=0.1806, simple_loss=0.2442, pruned_loss=0.05848, over 4903.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2412, pruned_loss=0.05512, over 972773.81 frames.], batch size: 39, lr: 7.45e-04
2022-05-04 03:49:50,284 INFO [train.py:715] (4/8) Epoch 2, batch 2850, loss[loss=0.238, simple_loss=0.2907, pruned_loss=0.09263, over 4743.00 frames.], tot_loss[loss=0.175, simple_loss=0.2405, pruned_loss=0.05471, over 972913.65 frames.], batch size: 16, lr: 7.44e-04
2022-05-04 03:50:29,538 INFO [train.py:715] (4/8) Epoch 2, batch 2900, loss[loss=0.2063, simple_loss=0.2708, pruned_loss=0.0709, over 4823.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2405, pruned_loss=0.0547, over 972803.57 frames.], batch size: 25, lr: 7.44e-04
2022-05-04 03:51:09,901 INFO [train.py:715] (4/8) Epoch 2, batch 2950, loss[loss=0.1884, simple_loss=0.2574, pruned_loss=0.0597, over 4911.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2411, pruned_loss=0.05507, over 972477.18 frames.], batch size: 19, lr: 7.44e-04
2022-05-04 03:51:50,589 INFO [train.py:715] (4/8) Epoch 2, batch 3000, loss[loss=0.1723, simple_loss=0.253, pruned_loss=0.04582, over 4707.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2411, pruned_loss=0.05499, over 972652.42 frames.], batch size: 15, lr: 7.44e-04
2022-05-04 03:51:50,590 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 03:52:00,001 INFO [train.py:742] (4/8) Epoch 2, validation: loss=0.1191, simple_loss=0.2058, pruned_loss=0.01615, over 914524.00 frames.
2022-05-04 03:52:40,623 INFO [train.py:715] (4/8) Epoch 2, batch 3050, loss[loss=0.1677, simple_loss=0.2503, pruned_loss=0.04257, over 4863.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2414, pruned_loss=0.05516, over 971790.36 frames.], batch size: 20, lr: 7.43e-04
2022-05-04 03:53:19,891 INFO [train.py:715] (4/8) Epoch 2, batch 3100, loss[loss=0.1626, simple_loss=0.2233, pruned_loss=0.05095, over 4946.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2409, pruned_loss=0.05474, over 971609.06 frames.], batch size: 21, lr: 7.43e-04
2022-05-04 03:53:59,897 INFO [train.py:715] (4/8) Epoch 2, batch 3150, loss[loss=0.2252, simple_loss=0.2937, pruned_loss=0.07836, over 4749.00 frames.], tot_loss[loss=0.1769, simple_loss=0.2424, pruned_loss=0.05573, over 970734.50 frames.], batch size: 16, lr: 7.43e-04
2022-05-04 03:54:40,190 INFO [train.py:715] (4/8) Epoch 2, batch 3200, loss[loss=0.2161, simple_loss=0.2698, pruned_loss=0.08124, over 4812.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2429, pruned_loss=0.0565, over 970560.03 frames.], batch size: 27, lr: 7.43e-04
2022-05-04 03:55:19,789 INFO [train.py:715] (4/8) Epoch 2, batch 3250, loss[loss=0.1758, simple_loss=0.2359, pruned_loss=0.05788, over 4939.00 frames.], tot_loss[loss=0.1779, simple_loss=0.2428, pruned_loss=0.05655, over 971727.95 frames.], batch size: 29, lr: 7.42e-04
2022-05-04 03:55:59,349 INFO [train.py:715] (4/8) Epoch 2, batch 3300, loss[loss=0.1835, simple_loss=0.2434, pruned_loss=0.06176, over 4783.00 frames.], tot_loss[loss=0.1775, simple_loss=0.2426, pruned_loss=0.05623, over 972183.58 frames.], batch size: 17, lr: 7.42e-04
2022-05-04 03:56:39,593 INFO [train.py:715] (4/8) Epoch 2, batch 3350, loss[loss=0.1364, simple_loss=0.2093, pruned_loss=0.03174, over 4869.00 frames.], tot_loss[loss=0.1774, simple_loss=0.2426, pruned_loss=0.05607, over 972503.41 frames.], batch size: 13, lr: 7.42e-04
2022-05-04 03:57:20,093 INFO [train.py:715] (4/8) Epoch 2, batch 3400, loss[loss=0.1654, simple_loss=0.237, pruned_loss=0.04691, over 4820.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2415, pruned_loss=0.05532, over 973211.25 frames.], batch size: 25, lr: 7.42e-04
2022-05-04 03:57:58,924 INFO [train.py:715] (4/8) Epoch 2, batch 3450, loss[loss=0.1647, simple_loss=0.2241, pruned_loss=0.05268, over 4980.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2413, pruned_loss=0.05519, over 973315.67 frames.], batch size: 28, lr: 7.41e-04
2022-05-04 03:58:38,958 INFO [train.py:715] (4/8) Epoch 2, batch 3500, loss[loss=0.2017, simple_loss=0.264, pruned_loss=0.06967, over 4759.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2404, pruned_loss=0.05464, over 972516.90 frames.], batch size: 19, lr: 7.41e-04
2022-05-04 03:59:19,007 INFO [train.py:715] (4/8) Epoch 2, batch 3550, loss[loss=0.1757, simple_loss=0.2349, pruned_loss=0.05823, over 4875.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2404, pruned_loss=0.05454, over 973131.19 frames.], batch size: 32, lr: 7.41e-04
2022-05-04 03:59:58,774 INFO [train.py:715] (4/8) Epoch 2, batch 3600, loss[loss=0.2009, simple_loss=0.2583, pruned_loss=0.07172, over 4883.00 frames.], tot_loss[loss=0.1757, simple_loss=0.241, pruned_loss=0.05516, over 973023.39 frames.], batch size: 30, lr: 7.41e-04
2022-05-04 04:00:37,775 INFO [train.py:715] (4/8) Epoch 2, batch 3650, loss[loss=0.1801, simple_loss=0.2517, pruned_loss=0.05423, over 4935.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2405, pruned_loss=0.05448, over 973094.12 frames.], batch size: 29, lr: 7.40e-04
2022-05-04 04:01:18,177 INFO [train.py:715] (4/8) Epoch 2, batch 3700, loss[loss=0.1495, simple_loss=0.2136, pruned_loss=0.04265, over 4955.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2396, pruned_loss=0.05386, over 973061.86 frames.], batch size: 15, lr: 7.40e-04
2022-05-04 04:01:58,348 INFO [train.py:715] (4/8) Epoch 2, batch 3750, loss[loss=0.2025, simple_loss=0.2645, pruned_loss=0.07027, over 4776.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2397, pruned_loss=0.05385, over 973513.44 frames.], batch size: 18, lr: 7.40e-04
2022-05-04 04:02:37,083 INFO [train.py:715] (4/8) Epoch 2, batch 3800, loss[loss=0.2026, simple_loss=0.2687, pruned_loss=0.06824, over 4846.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2404, pruned_loss=0.05471, over 972802.38 frames.], batch size: 15, lr: 7.40e-04
2022-05-04 04:03:17,275 INFO [train.py:715] (4/8) Epoch 2, batch 3850, loss[loss=0.1426, simple_loss=0.216, pruned_loss=0.03459, over 4789.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2404, pruned_loss=0.05445, over 971384.36 frames.], batch size: 24, lr: 7.39e-04
2022-05-04 04:03:57,604 INFO [train.py:715] (4/8) Epoch 2, batch 3900, loss[loss=0.215, simple_loss=0.2731, pruned_loss=0.07849, over 4713.00 frames.], tot_loss[loss=0.1752, simple_loss=0.241, pruned_loss=0.05465, over 972422.87 frames.], batch size: 15, lr: 7.39e-04
2022-05-04 04:04:36,841 INFO [train.py:715] (4/8) Epoch 2, batch 3950, loss[loss=0.1506, simple_loss=0.2322, pruned_loss=0.03455, over 4983.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2414, pruned_loss=0.05473, over 972172.88 frames.], batch size: 25, lr: 7.39e-04
2022-05-04 04:05:16,462 INFO [train.py:715] (4/8) Epoch 2, batch 4000, loss[loss=0.1814, simple_loss=0.2312, pruned_loss=0.06578, over 4880.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2406, pruned_loss=0.05488, over 973019.67 frames.], batch size: 32, lr: 7.39e-04
2022-05-04 04:05:57,029 INFO [train.py:715] (4/8) Epoch 2, batch 4050, loss[loss=0.1775, simple_loss=0.2361, pruned_loss=0.05939, over 4843.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2412, pruned_loss=0.05484, over 972131.10 frames.], batch size: 26, lr: 7.38e-04
2022-05-04 04:06:37,527 INFO [train.py:715] (4/8) Epoch 2, batch 4100, loss[loss=0.1399, simple_loss=0.2172, pruned_loss=0.0313, over 4800.00 frames.], tot_loss[loss=0.176, simple_loss=0.2419, pruned_loss=0.05509, over 971517.32 frames.], batch size: 17, lr: 7.38e-04
2022-05-04 04:07:16,027 INFO [train.py:715] (4/8) Epoch 2, batch 4150, loss[loss=0.2019, simple_loss=0.2679, pruned_loss=0.06798, over 4831.00 frames.], tot_loss[loss=0.1746, simple_loss=0.241, pruned_loss=0.05408, over 970585.19 frames.], batch size: 30, lr: 7.38e-04
2022-05-04 04:07:55,388 INFO [train.py:715] (4/8) Epoch 2, batch 4200, loss[loss=0.1659, simple_loss=0.2274, pruned_loss=0.05222, over 4840.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2398, pruned_loss=0.05343, over 970091.79 frames.], batch size: 15, lr: 7.38e-04
2022-05-04 04:08:35,833 INFO [train.py:715] (4/8) Epoch 2, batch 4250, loss[loss=0.1584, simple_loss=0.236, pruned_loss=0.04035, over 4810.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2399, pruned_loss=0.05373, over 970901.46 frames.], batch size: 25, lr: 7.37e-04
2022-05-04 04:09:15,084 INFO [train.py:715] (4/8) Epoch 2, batch 4300, loss[loss=0.1633, simple_loss=0.238, pruned_loss=0.04432, over 4738.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2396, pruned_loss=0.05349, over 971183.57 frames.], batch size: 16, lr: 7.37e-04
2022-05-04 04:09:54,871 INFO [train.py:715] (4/8) Epoch 2, batch 4350, loss[loss=0.2101, simple_loss=0.2871, pruned_loss=0.06654, over 4733.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2414, pruned_loss=0.05466, over 971306.49 frames.], batch size: 16, lr: 7.37e-04
2022-05-04 04:10:34,719 INFO [train.py:715] (4/8) Epoch 2, batch 4400, loss[loss=0.1641, simple_loss=0.2328, pruned_loss=0.04771, over 4924.00 frames.], tot_loss[loss=0.1765, simple_loss=0.242, pruned_loss=0.05547, over 971349.03 frames.], batch size: 18, lr: 7.37e-04
2022-05-04 04:11:14,736 INFO [train.py:715] (4/8) Epoch 2, batch 4450, loss[loss=0.1566, simple_loss=0.2224, pruned_loss=0.04537, over 4990.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2416, pruned_loss=0.05477, over 971727.76 frames.], batch size: 16, lr: 7.36e-04
2022-05-04 04:11:53,880 INFO [train.py:715] (4/8) Epoch 2, batch 4500, loss[loss=0.1652, simple_loss=0.2352, pruned_loss=0.04761, over 4825.00 frames.], tot_loss[loss=0.1753, simple_loss=0.241, pruned_loss=0.05477, over 972002.94 frames.], batch size: 26, lr: 7.36e-04
2022-05-04 04:12:33,895 INFO [train.py:715] (4/8) Epoch 2, batch 4550, loss[loss=0.1687, simple_loss=0.243, pruned_loss=0.04722, over 4807.00 frames.], tot_loss[loss=0.1742, simple_loss=0.24, pruned_loss=0.05422, over 972668.63 frames.], batch size: 21, lr: 7.36e-04
2022-05-04 04:13:14,640 INFO [train.py:715] (4/8) Epoch 2, batch 4600, loss[loss=0.1568, simple_loss=0.2174, pruned_loss=0.04807, over 4901.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2393, pruned_loss=0.05369, over 972440.53 frames.], batch size: 18, lr: 7.36e-04
2022-05-04 04:13:53,695 INFO [train.py:715] (4/8) Epoch 2, batch 4650, loss[loss=0.1291, simple_loss=0.2002, pruned_loss=0.02901, over 4756.00 frames.], tot_loss[loss=0.1747, simple_loss=0.2405, pruned_loss=0.05439, over 972650.18 frames.], batch size: 16, lr: 7.35e-04
2022-05-04 04:14:33,001 INFO [train.py:715] (4/8) Epoch 2, batch 4700, loss[loss=0.193, simple_loss=0.2698, pruned_loss=0.05815, over 4770.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2408, pruned_loss=0.0545, over 972008.11 frames.], batch size: 18, lr: 7.35e-04
2022-05-04 04:15:13,202 INFO [train.py:715] (4/8) Epoch 2, batch 4750, loss[loss=0.1435, simple_loss=0.2098, pruned_loss=0.03857, over 4889.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2406, pruned_loss=0.0543, over 971993.56 frames.], batch size: 19, lr: 7.35e-04
2022-05-04 04:15:53,743 INFO [train.py:715] (4/8) Epoch 2, batch 4800, loss[loss=0.172, simple_loss=0.2405, pruned_loss=0.0517, over 4899.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2414, pruned_loss=0.05493, over 972302.07 frames.], batch size: 19, lr: 7.35e-04
2022-05-04 04:16:33,023 INFO [train.py:715] (4/8) Epoch 2, batch 4850, loss[loss=0.1511, simple_loss=0.2137, pruned_loss=0.04429, over 4760.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2413, pruned_loss=0.05513, over 972204.29 frames.], batch size: 12, lr: 7.34e-04
2022-05-04 04:17:12,479 INFO [train.py:715] (4/8) Epoch 2, batch 4900, loss[loss=0.1722, simple_loss=0.2473, pruned_loss=0.04858, over 4897.00 frames.], tot_loss[loss=0.1755, simple_loss=0.2408, pruned_loss=0.0551, over 971839.10 frames.], batch size: 19, lr: 7.34e-04
2022-05-04 04:17:52,934 INFO [train.py:715] (4/8) Epoch 2, batch 4950, loss[loss=0.195, simple_loss=0.2659, pruned_loss=0.06203, over 4773.00 frames.], tot_loss[loss=0.1753, simple_loss=0.2408, pruned_loss=0.05491, over 971612.76 frames.], batch size: 14, lr: 7.34e-04
2022-05-04 04:18:32,534 INFO [train.py:715] (4/8) Epoch 2, batch 5000, loss[loss=0.1341, simple_loss=0.2028, pruned_loss=0.03267, over 4853.00 frames.], tot_loss[loss=0.175, simple_loss=0.2402, pruned_loss=0.05489, over 972247.88 frames.], batch size: 20, lr: 7.34e-04
2022-05-04 04:19:12,095 INFO [train.py:715] (4/8) Epoch 2, batch 5050, loss[loss=0.2325, simple_loss=0.2906, pruned_loss=0.08721, over 4869.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2408, pruned_loss=0.05521, over 972213.18 frames.], batch size: 16, lr: 7.33e-04
2022-05-04 04:19:53,166 INFO [train.py:715] (4/8) Epoch 2, batch 5100, loss[loss=0.1924, simple_loss=0.2429, pruned_loss=0.07099, over 4905.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2401, pruned_loss=0.05479, over 972356.83 frames.], batch size: 18, lr: 7.33e-04
2022-05-04 04:20:34,130 INFO [train.py:715] (4/8) Epoch 2, batch 5150, loss[loss=0.1625, simple_loss=0.2259, pruned_loss=0.04952, over 4771.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2397, pruned_loss=0.05456, over 972652.44 frames.], batch size: 17, lr: 7.33e-04
2022-05-04 04:21:13,084 INFO [train.py:715] (4/8) Epoch 2, batch 5200, loss[loss=0.1456, simple_loss=0.2148, pruned_loss=0.03824, over 4973.00 frames.], tot_loss[loss=0.1735, simple_loss=0.239, pruned_loss=0.05402, over 972958.97 frames.], batch size: 25, lr: 7.33e-04
2022-05-04 04:21:52,852 INFO [train.py:715] (4/8) Epoch 2, batch 5250, loss[loss=0.1796, simple_loss=0.2498, pruned_loss=0.05471, over 4907.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2391, pruned_loss=0.05377, over 972116.24 frames.], batch size: 19, lr: 7.32e-04
2022-05-04 04:22:33,066 INFO [train.py:715] (4/8) Epoch 2, batch 5300, loss[loss=0.1687, simple_loss=0.2345, pruned_loss=0.05145, over 4921.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2409, pruned_loss=0.05471, over 972277.28 frames.], batch size: 18, lr: 7.32e-04
2022-05-04 04:23:12,243 INFO [train.py:715] (4/8) Epoch 2, batch 5350, loss[loss=0.2318, simple_loss=0.2778, pruned_loss=0.09293, over 4743.00 frames.], tot_loss[loss=0.1744, simple_loss=0.2403, pruned_loss=0.05423, over 972975.26 frames.], batch size: 16, lr: 7.32e-04
2022-05-04 04:23:51,607 INFO [train.py:715] (4/8) Epoch 2, batch 5400, loss[loss=0.1666, simple_loss=0.2325, pruned_loss=0.05036, over 4699.00 frames.], tot_loss[loss=0.175, simple_loss=0.2407, pruned_loss=0.0546, over 973319.41 frames.], batch size: 15, lr: 7.32e-04
2022-05-04 04:24:32,283 INFO [train.py:715] (4/8) Epoch 2, batch 5450, loss[loss=0.1788, simple_loss=0.2421, pruned_loss=0.05777, over 4990.00 frames.], tot_loss[loss=0.175, simple_loss=0.2405, pruned_loss=0.0548, over 973569.52 frames.], batch size: 14, lr: 7.31e-04
2022-05-04 04:25:12,072 INFO [train.py:715] (4/8) Epoch 2, batch 5500, loss[loss=0.1733, simple_loss=0.2464, pruned_loss=0.05005, over 4852.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2411, pruned_loss=0.05515, over 973001.04 frames.], batch size: 20, lr: 7.31e-04
2022-05-04 04:25:51,708 INFO [train.py:715] (4/8) Epoch 2, batch 5550, loss[loss=0.1636, simple_loss=0.223, pruned_loss=0.05209, over 4938.00 frames.], tot_loss[loss=0.1759, simple_loss=0.2412, pruned_loss=0.05528, over 972780.70 frames.], batch size: 29, lr: 7.31e-04
2022-05-04 04:26:32,206 INFO [train.py:715] (4/8) Epoch 2, batch 5600, loss[loss=0.1769, simple_loss=0.2357, pruned_loss=0.05902, over 4646.00 frames.], tot_loss[loss=0.1762, simple_loss=0.2412, pruned_loss=0.05556, over 972257.90 frames.], batch size: 13, lr: 7.31e-04
2022-05-04 04:27:13,267 INFO [train.py:715] (4/8) Epoch 2, batch 5650, loss[loss=0.197, simple_loss=0.2555, pruned_loss=0.06922, over 4951.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2418, pruned_loss=0.05584, over 972039.59 frames.], batch size: 21, lr: 7.30e-04
2022-05-04 04:27:53,173 INFO [train.py:715] (4/8) Epoch 2, batch 5700, loss[loss=0.1661, simple_loss=0.2385, pruned_loss=0.0468, over 4921.00 frames.], tot_loss[loss=0.177, simple_loss=0.2421, pruned_loss=0.05599, over 972060.99 frames.], batch size: 23, lr: 7.30e-04
2022-05-04 04:28:33,028 INFO [train.py:715] (4/8) Epoch 2, batch 5750, loss[loss=0.1699, simple_loss=0.2364, pruned_loss=0.05166, over 4951.00 frames.], tot_loss[loss=0.1773, simple_loss=0.2426, pruned_loss=0.05598, over 973043.98 frames.], batch size: 21, lr: 7.30e-04
2022-05-04 04:29:13,947 INFO [train.py:715] (4/8) Epoch 2, batch 5800, loss[loss=0.1903, simple_loss=0.262, pruned_loss=0.05926, over 4969.00 frames.], tot_loss[loss=0.1764, simple_loss=0.2418, pruned_loss=0.05546, over 972840.76 frames.], batch size: 39, lr: 7.30e-04
2022-05-04 04:29:55,098 INFO [train.py:715] (4/8) Epoch 2, batch 5850, loss[loss=0.1705, simple_loss=0.236, pruned_loss=0.05253, over 4969.00 frames.], tot_loss[loss=0.1767, simple_loss=0.2426, pruned_loss=0.05542, over 973999.00 frames.], batch size: 24, lr: 7.29e-04
2022-05-04 04:30:34,548 INFO [train.py:715] (4/8) Epoch 2, batch 5900, loss[loss=0.167, simple_loss=0.2324, pruned_loss=0.05077, over 4737.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2417, pruned_loss=0.05497, over 973149.48 frames.], batch size: 16, lr: 7.29e-04
2022-05-04 04:31:15,146 INFO [train.py:715] (4/8) Epoch 2, batch 5950, loss[loss=0.1711, simple_loss=0.2382, pruned_loss=0.05199, over 4848.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2414, pruned_loss=0.05496, over 973069.00 frames.], batch size: 32, lr: 7.29e-04
2022-05-04 04:31:56,154 INFO [train.py:715] (4/8) Epoch 2, batch 6000, loss[loss=0.1781, simple_loss=0.2526, pruned_loss=0.05185, over 4745.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2406, pruned_loss=0.05477, over 973102.38 frames.], batch size: 16, lr: 7.29e-04
2022-05-04 04:31:56,154 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 04:32:04,806 INFO [train.py:742] (4/8) Epoch 2, validation: loss=0.1188, simple_loss=0.2054, pruned_loss=0.01614, over 914524.00 frames.
2022-05-04 04:32:46,138 INFO [train.py:715] (4/8) Epoch 2, batch 6050, loss[loss=0.1896, simple_loss=0.2594, pruned_loss=0.05995, over 4878.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2413, pruned_loss=0.05503, over 972811.82 frames.], batch size: 16, lr: 7.29e-04
2022-05-04 04:33:25,850 INFO [train.py:715] (4/8) Epoch 2, batch 6100, loss[loss=0.1779, simple_loss=0.2412, pruned_loss=0.05727, over 4690.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2412, pruned_loss=0.05485, over 972796.97 frames.], batch size: 15, lr: 7.28e-04
2022-05-04 04:34:05,820 INFO [train.py:715] (4/8) Epoch 2, batch 6150, loss[loss=0.2137, simple_loss=0.2652, pruned_loss=0.08113, over 4866.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2412, pruned_loss=0.0548, over 972804.01 frames.], batch size: 20, lr: 7.28e-04
2022-05-04 04:34:46,186 INFO [train.py:715] (4/8) Epoch 2, batch 6200, loss[loss=0.1481, simple_loss=0.2244, pruned_loss=0.03592, over 4967.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2409, pruned_loss=0.05466, over 973498.78 frames.], batch size: 21, lr: 7.28e-04
2022-05-04 04:35:26,609 INFO [train.py:715] (4/8) Epoch 2, batch 6250, loss[loss=0.1856, simple_loss=0.2493, pruned_loss=0.06093, over 4984.00 frames.], tot_loss[loss=0.175, simple_loss=0.2408, pruned_loss=0.05465, over 973278.31 frames.], batch size: 33, lr: 7.28e-04
2022-05-04 04:36:05,782 INFO [train.py:715] (4/8) Epoch 2, batch 6300, loss[loss=0.1918, simple_loss=0.2514, pruned_loss=0.06608, over 4941.00 frames.], tot_loss[loss=0.1763, simple_loss=0.2418, pruned_loss=0.05543, over 973911.89 frames.], batch size: 39, lr: 7.27e-04
2022-05-04 04:36:46,030 INFO [train.py:715] (4/8) Epoch 2, batch 6350, loss[loss=0.2277, simple_loss=0.2828, pruned_loss=0.08633, over 4962.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2415, pruned_loss=0.05495, over 974216.00 frames.], batch size: 15, lr: 7.27e-04
2022-05-04 04:37:26,523 INFO [train.py:715] (4/8) Epoch 2, batch 6400, loss[loss=0.1659, simple_loss=0.232, pruned_loss=0.04988, over 4927.00 frames.], tot_loss[loss=0.1758, simple_loss=0.2418, pruned_loss=0.05493, over 974379.86 frames.], batch size: 18, lr: 7.27e-04
2022-05-04 04:38:05,328 INFO [train.py:715] (4/8) Epoch 2, batch 6450, loss[loss=0.1773, simple_loss=0.2447, pruned_loss=0.05498, over 4942.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2413, pruned_loss=0.05476, over 973743.98 frames.], batch size: 39, lr: 7.27e-04
2022-05-04 04:38:44,595 INFO [train.py:715] (4/8) Epoch 2, batch 6500, loss[loss=0.2088, simple_loss=0.2638, pruned_loss=0.07694, over 4896.00 frames.], tot_loss[loss=0.175, simple_loss=0.2408, pruned_loss=0.05461, over 973790.79 frames.], batch size: 32, lr: 7.26e-04
2022-05-04 04:39:24,834 INFO [train.py:715] (4/8) Epoch 2, batch 6550, loss[loss=0.1808, simple_loss=0.2543, pruned_loss=0.0537, over 4808.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2402, pruned_loss=0.05415, over 973015.40 frames.], batch size: 21, lr: 7.26e-04
2022-05-04 04:40:04,768 INFO [train.py:715] (4/8) Epoch 2, batch 6600, loss[loss=0.1949, simple_loss=0.2576, pruned_loss=0.06615, over 4795.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2404, pruned_loss=0.05459, over 972614.45 frames.], batch size: 18, lr: 7.26e-04
2022-05-04 04:40:43,854 INFO [train.py:715] (4/8) Epoch 2, batch 6650, loss[loss=0.1387, simple_loss=0.2034, pruned_loss=0.03696, over 4785.00 frames.], tot_loss[loss=0.1747, simple_loss=0.24, pruned_loss=0.05471, over 971827.26 frames.], batch size: 13, lr: 7.26e-04
2022-05-04 04:41:23,375 INFO [train.py:715] (4/8) Epoch 2, batch 6700, loss[loss=0.17, simple_loss=0.2342, pruned_loss=0.05287, over 4780.00 frames.], tot_loss[loss=0.1756, simple_loss=0.2407, pruned_loss=0.05522, over 971371.05 frames.], batch size: 18, lr: 7.25e-04
2022-05-04 04:42:03,555 INFO [train.py:715] (4/8) Epoch 2, batch 6750, loss[loss=0.165, simple_loss=0.2273, pruned_loss=0.0513, over 4936.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2407, pruned_loss=0.05536, over 971465.09 frames.], batch size: 18, lr: 7.25e-04
2022-05-04 04:42:41,721 INFO [train.py:715] (4/8) Epoch 2, batch 6800, loss[loss=0.1401, simple_loss=0.1993, pruned_loss=0.04046, over 4692.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2414, pruned_loss=0.05575, over 971854.51 frames.], batch size: 15, lr: 7.25e-04
2022-05-04 04:43:20,946 INFO [train.py:715] (4/8) Epoch 2, batch 6850, loss[loss=0.1561, simple_loss=0.2102, pruned_loss=0.05096, over 4958.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2417, pruned_loss=0.05564, over 971860.87 frames.], batch size: 14, lr: 7.25e-04
2022-05-04 04:44:01,043 INFO [train.py:715] (4/8) Epoch 2, batch 6900, loss[loss=0.2145, simple_loss=0.2723, pruned_loss=0.07834, over 4944.00 frames.], tot_loss[loss=0.1761, simple_loss=0.2415, pruned_loss=0.05535, over 971371.32 frames.], batch size: 35, lr: 7.24e-04
2022-05-04 04:44:41,212 INFO [train.py:715] (4/8) Epoch 2, batch 6950, loss[loss=0.1533, simple_loss=0.2287, pruned_loss=0.03891, over 4892.00 frames.], tot_loss[loss=0.1765, simple_loss=0.2417, pruned_loss=0.05565, over 971454.23 frames.], batch size: 19, lr: 7.24e-04
2022-05-04 04:45:19,414 INFO [train.py:715] (4/8) Epoch 2, batch 7000, loss[loss=0.1883, simple_loss=0.2488, pruned_loss=0.06383, over 4743.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2411, pruned_loss=0.05514, over 971309.29 frames.], batch size: 16, lr: 7.24e-04
2022-05-04 04:45:59,981 INFO [train.py:715] (4/8) Epoch 2, batch 7050, loss[loss=0.1514, simple_loss=0.2167, pruned_loss=0.04304, over 4793.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2399, pruned_loss=0.05459, over 972009.88 frames.], batch size: 18, lr: 7.24e-04
2022-05-04 04:46:40,405 INFO [train.py:715] (4/8) Epoch 2, batch 7100, loss[loss=0.1783, simple_loss=0.2454, pruned_loss=0.0556, over 4845.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2404, pruned_loss=0.05446, over 972128.93 frames.], batch size: 30, lr: 7.24e-04
2022-05-04 04:47:19,798 INFO [train.py:715] (4/8) Epoch 2, batch 7150, loss[loss=0.1994, simple_loss=0.2613, pruned_loss=0.06875, over 4811.00 frames.], tot_loss[loss=0.175, simple_loss=0.2406, pruned_loss=0.05473, over 971638.27 frames.], batch size: 21, lr: 7.23e-04
2022-05-04 04:48:00,090 INFO [train.py:715] (4/8) Epoch 2, batch 7200, loss[loss=0.1751, simple_loss=0.2307, pruned_loss=0.05971, over 4793.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2406, pruned_loss=0.05455, over 971631.80 frames.], batch size: 14, lr: 7.23e-04
2022-05-04 04:48:41,281 INFO [train.py:715] (4/8) Epoch 2, batch 7250, loss[loss=0.1544, simple_loss=0.2156, pruned_loss=0.04661, over 4980.00 frames.], tot_loss[loss=0.1746, simple_loss=0.2403, pruned_loss=0.05447, over 972330.05 frames.], batch size: 14, lr: 7.23e-04
2022-05-04 04:49:21,909 INFO [train.py:715] (4/8) Epoch 2, batch 7300, loss[loss=0.1922, simple_loss=0.268, pruned_loss=0.0582, over 4759.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2398, pruned_loss=0.05424, over 972388.74 frames.], batch size: 16, lr: 7.23e-04
2022-05-04 04:50:01,610 INFO [train.py:715] (4/8) Epoch 2, batch 7350, loss[loss=0.1851, simple_loss=0.262, pruned_loss=0.05411, over 4821.00 frames.], tot_loss[loss=0.1755, simple_loss=0.241, pruned_loss=0.05495, over 972565.81 frames.], batch size: 25, lr: 7.22e-04
2022-05-04 04:50:42,534 INFO [train.py:715] (4/8) Epoch 2, batch 7400, loss[loss=0.168, simple_loss=0.2349, pruned_loss=0.05053, over 4953.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2409, pruned_loss=0.05497, over 973099.23 frames.], batch size: 35, lr: 7.22e-04
2022-05-04 04:51:24,349 INFO [train.py:715] (4/8) Epoch 2, batch 7450, loss[loss=0.1716, simple_loss=0.2397, pruned_loss=0.05172, over 4987.00 frames.], tot_loss[loss=0.1757, simple_loss=0.2415, pruned_loss=0.05495, over 972462.41 frames.], batch size: 28, lr: 7.22e-04
2022-05-04 04:52:04,713 INFO [train.py:715] (4/8) Epoch 2, batch 7500, loss[loss=0.1881, simple_loss=0.2614, pruned_loss=0.05745, over 4964.00 frames.], tot_loss[loss=0.1749, simple_loss=0.2408, pruned_loss=0.05447, over 972646.52 frames.], batch size: 15, lr: 7.22e-04
2022-05-04 04:52:45,160 INFO [train.py:715] (4/8) Epoch 2, batch 7550, loss[loss=0.1756, simple_loss=0.2425, pruned_loss=0.05432, over 4906.00 frames.], tot_loss[loss=0.1745, simple_loss=0.2412, pruned_loss=0.05388, over 973273.12 frames.], batch size: 17, lr: 7.21e-04
2022-05-04 04:53:26,940 INFO [train.py:715] (4/8) Epoch 2, batch 7600, loss[loss=0.1697, simple_loss=0.2326, pruned_loss=0.05335, over 4899.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2406, pruned_loss=0.05363, over 973603.68 frames.], batch size: 18, lr: 7.21e-04
2022-05-04 04:54:08,308 INFO [train.py:715] (4/8) Epoch 2, batch 7650, loss[loss=0.157, simple_loss=0.2212, pruned_loss=0.04646, over 4844.00 frames.], tot_loss[loss=0.1752, simple_loss=0.2419, pruned_loss=0.0543, over 973365.90 frames.], batch size: 30, lr: 7.21e-04
2022-05-04 04:54:48,367 INFO [train.py:715] (4/8) Epoch 2, batch 7700, loss[loss=0.1703, simple_loss=0.2477, pruned_loss=0.0465, over 4893.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2406, pruned_loss=0.05377, over 973667.21 frames.], batch size: 17, lr: 7.21e-04
2022-05-04 04:55:29,827 INFO [train.py:715] (4/8) Epoch 2, batch 7750, loss[loss=0.2157, simple_loss=0.2754, pruned_loss=0.078, over 4921.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2404, pruned_loss=0.05369, over 973655.56 frames.], batch size: 18, lr: 7.21e-04
2022-05-04 04:56:11,496 INFO [train.py:715] (4/8) Epoch 2, batch 7800, loss[loss=0.1893, simple_loss=0.2439, pruned_loss=0.0673, over 4690.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2413, pruned_loss=0.05443, over 973199.35 frames.], batch size: 15, lr: 7.20e-04
2022-05-04 04:56:52,001 INFO [train.py:715] (4/8) Epoch 2, batch 7850, loss[loss=0.1944, simple_loss=0.2542, pruned_loss=0.06734, over 4919.00 frames.], tot_loss[loss=0.175, simple_loss=0.2415, pruned_loss=0.0543, over 973134.97 frames.], batch size: 18, lr: 7.20e-04
2022-05-04 04:57:33,348 INFO [train.py:715] (4/8) Epoch 2, batch 7900, loss[loss=0.14, simple_loss=0.2058, pruned_loss=0.03706, over 4829.00 frames.], tot_loss[loss=0.1754, simple_loss=0.2416, pruned_loss=0.05459, over 972383.14 frames.], batch size: 13, lr: 7.20e-04
2022-05-04 04:58:15,542 INFO [train.py:715] (4/8) Epoch 2, batch 7950, loss[loss=0.1794, simple_loss=0.2498, pruned_loss=0.05452, over 4824.00 frames.], tot_loss[loss=0.174, simple_loss=0.2406, pruned_loss=0.05371, over 972206.98 frames.], batch size: 26, lr: 7.20e-04
2022-05-04 04:58:57,039 INFO [train.py:715] (4/8) Epoch 2, batch 8000, loss[loss=0.1685, simple_loss=0.2418, pruned_loss=0.0476, over 4972.00 frames.], tot_loss[loss=0.1751, simple_loss=0.2412, pruned_loss=0.05451, over 972849.91 frames.], batch size: 24, lr: 7.19e-04
2022-05-04 04:59:37,236 INFO [train.py:715] (4/8) Epoch 2, batch 8050, loss[loss=0.1837, simple_loss=0.2553, pruned_loss=0.05609, over 4752.00 frames.], tot_loss[loss=0.1734, simple_loss=0.24, pruned_loss=0.05338, over 972688.45 frames.], batch size: 16, lr: 7.19e-04
2022-05-04 05:00:18,962 INFO [train.py:715] (4/8) Epoch 2, batch 8100, loss[loss=0.149, simple_loss=0.2277, pruned_loss=0.03516, over 4975.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2393, pruned_loss=0.053, over 972848.11 frames.], batch size: 25, lr: 7.19e-04
2022-05-04 05:01:00,829 INFO [train.py:715] (4/8) Epoch 2, batch 8150, loss[loss=0.1602, simple_loss=0.2249, pruned_loss=0.04774, over 4860.00 frames.], tot_loss[loss=0.173, simple_loss=0.2395, pruned_loss=0.05323, over 971691.69 frames.], batch size: 20, lr: 7.19e-04
2022-05-04 05:01:41,268 INFO [train.py:715] (4/8) Epoch 2, batch 8200, loss[loss=0.1997, simple_loss=0.2608, pruned_loss=0.0693, over 4979.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2391, pruned_loss=0.05324, over 971567.78 frames.], batch size: 15, lr: 7.18e-04
2022-05-04 05:02:22,244 INFO [train.py:715] (4/8) Epoch 2, batch 8250, loss[loss=0.1651, simple_loss=0.2331, pruned_loss=0.04859, over 4934.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2384, pruned_loss=0.05304, over 970373.65 frames.], batch size: 23, lr: 7.18e-04
2022-05-04 05:03:04,358 INFO [train.py:715] (4/8) Epoch 2, batch 8300, loss[loss=0.138, simple_loss=0.2126, pruned_loss=0.03167, over 4831.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2385, pruned_loss=0.0531, over 970753.34 frames.], batch size: 27, lr: 7.18e-04
2022-05-04 05:03:46,071 INFO [train.py:715] (4/8) Epoch 2, batch 8350, loss[loss=0.1521, simple_loss=0.2249, pruned_loss=0.03961, over 4808.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2393, pruned_loss=0.05353, over 971143.54 frames.], batch size: 25, lr: 7.18e-04
2022-05-04 05:04:26,321 INFO [train.py:715] (4/8) Epoch 2, batch 8400, loss[loss=0.172, simple_loss=0.2415, pruned_loss=0.05127, over 4751.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2394, pruned_loss=0.05347, over 972775.88 frames.], batch size: 19, lr: 7.18e-04
2022-05-04 05:05:07,464 INFO [train.py:715] (4/8) Epoch 2, batch 8450, loss[loss=0.1912, simple_loss=0.2518, pruned_loss=0.06531, over 4974.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2388, pruned_loss=0.05337, over 972770.97 frames.], batch size: 15, lr: 7.17e-04
2022-05-04 05:05:49,554 INFO [train.py:715] (4/8) Epoch 2, batch 8500, loss[loss=0.1695, simple_loss=0.2394, pruned_loss=0.0498, over 4800.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2389, pruned_loss=0.05389, over 972642.41 frames.], batch size: 21, lr: 7.17e-04
2022-05-04 05:06:29,755 INFO [train.py:715] (4/8) Epoch 2, batch 8550, loss[loss=0.1671, simple_loss=0.2368, pruned_loss=0.04875, over 4877.00 frames.], tot_loss[loss=0.1741, simple_loss=0.2399, pruned_loss=0.05422, over 973242.94 frames.], batch size: 20, lr: 7.17e-04
2022-05-04 05:07:10,944 INFO [train.py:715] (4/8) Epoch 2, batch 8600, loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03405, over 4942.00 frames.], tot_loss[loss=0.1728, simple_loss=0.239, pruned_loss=0.05332, over 973331.97 frames.], batch size: 21, lr: 7.17e-04
2022-05-04 05:07:52,986 INFO [train.py:715] (4/8) Epoch 2, batch 8650, loss[loss=0.2119, simple_loss=0.2713, pruned_loss=0.07624, over 4832.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2389, pruned_loss=0.05327, over 973401.36 frames.], batch size: 15, lr: 7.16e-04
2022-05-04 05:08:34,285 INFO [train.py:715] (4/8) Epoch 2, batch 8700, loss[loss=0.1512, simple_loss=0.2118, pruned_loss=0.0453, over 4789.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2394, pruned_loss=0.05396, over 973491.40 frames.], batch size: 14, lr: 7.16e-04
2022-05-04 05:09:14,819 INFO [train.py:715] (4/8) Epoch 2, batch 8750, loss[loss=0.1654, simple_loss=0.2295, pruned_loss=0.05063, over 4687.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2397, pruned_loss=0.05387, over 973480.20 frames.], batch size: 15, lr: 7.16e-04
2022-05-04 05:09:56,621 INFO [train.py:715] (4/8) Epoch 2, batch 8800, loss[loss=0.1535, simple_loss=0.2234, pruned_loss=0.04185, over 4840.00 frames.], tot_loss[loss=0.1734, simple_loss=0.239, pruned_loss=0.05388, over 973692.24 frames.], batch size: 13, lr: 7.16e-04
2022-05-04 05:10:38,729 INFO [train.py:715] (4/8) Epoch 2, batch 8850, loss[loss=0.1929, simple_loss=0.2528, pruned_loss=0.06652, over 4977.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2395, pruned_loss=0.05455, over 973308.47 frames.], batch size: 28, lr: 7.15e-04
2022-05-04 05:11:18,688 INFO [train.py:715] (4/8) Epoch 2, batch 8900, loss[loss=0.1665, simple_loss=0.2345, pruned_loss=0.04929, over 4948.00 frames.], tot_loss[loss=0.1735, simple_loss=0.239, pruned_loss=0.05399, over 973390.37 frames.], batch size: 21, lr: 7.15e-04
2022-05-04 05:12:00,191 INFO [train.py:715] (4/8) Epoch 2, batch 8950, loss[loss=0.2102, simple_loss=0.2859, pruned_loss=0.06727, over 4871.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2391, pruned_loss=0.05391, over 972479.03 frames.], batch size: 20, lr: 7.15e-04
2022-05-04 05:12:42,411 INFO [train.py:715] (4/8) Epoch 2, batch 9000, loss[loss=0.2123, simple_loss=0.2736, pruned_loss=0.07554, over 4824.00 frames.], tot_loss[loss=0.1732, simple_loss=0.239, pruned_loss=0.05377, over 972583.21 frames.], batch size: 25, lr: 7.15e-04
2022-05-04 05:12:42,411 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 05:12:58,991 INFO [train.py:742] (4/8) Epoch 2, validation: loss=0.1181, simple_loss=0.2047, pruned_loss=0.01572, over 914524.00 frames.
2022-05-04 05:13:41,055 INFO [train.py:715] (4/8) Epoch 2, batch 9050, loss[loss=0.1616, simple_loss=0.2347, pruned_loss=0.04428, over 4929.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2383, pruned_loss=0.05335, over 972465.53 frames.], batch size: 18, lr: 7.15e-04
2022-05-04 05:14:21,244 INFO [train.py:715] (4/8) Epoch 2, batch 9100, loss[loss=0.1945, simple_loss=0.2648, pruned_loss=0.06216, over 4917.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2387, pruned_loss=0.05334, over 972536.34 frames.], batch size: 18, lr: 7.14e-04
2022-05-04 05:15:02,330 INFO [train.py:715] (4/8) Epoch 2, batch 9150, loss[loss=0.1804, simple_loss=0.2397, pruned_loss=0.06049, over 4969.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2387, pruned_loss=0.05331, over 971989.08 frames.], batch size: 35, lr: 7.14e-04
2022-05-04 05:15:43,579 INFO [train.py:715] (4/8) Epoch 2, batch 9200, loss[loss=0.1649, simple_loss=0.233, pruned_loss=0.04839, over 4988.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2382, pruned_loss=0.05323, over 971997.38 frames.], batch size: 25, lr: 7.14e-04
2022-05-04 05:16:25,091 INFO [train.py:715] (4/8) Epoch 2, batch 9250, loss[loss=0.1854, simple_loss=0.2354, pruned_loss=0.06774, over 4871.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2385, pruned_loss=0.05342, over 972096.00 frames.], batch size: 32, lr: 7.14e-04
2022-05-04 05:17:05,070 INFO [train.py:715] (4/8) Epoch 2, batch 9300, loss[loss=0.1433, simple_loss=0.213, pruned_loss=0.03681, over 4855.00 frames.], tot_loss[loss=0.173, simple_loss=0.2392, pruned_loss=0.05337, over 971116.33 frames.], batch size: 13, lr: 7.13e-04
2022-05-04 05:17:46,755 INFO [train.py:715] (4/8) Epoch 2, batch 9350, loss[loss=0.1879, simple_loss=0.239, pruned_loss=0.06839, over 4810.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2392, pruned_loss=0.05322, over 971994.99 frames.], batch size: 21, lr: 7.13e-04
2022-05-04 05:18:28,856 INFO [train.py:715] (4/8) Epoch 2, batch 9400, loss[loss=0.2183, simple_loss=0.2788, pruned_loss=0.07889, over 4986.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2385, pruned_loss=0.05296, over 971828.48 frames.], batch size: 28, lr: 7.13e-04
2022-05-04 05:19:08,499 INFO [train.py:715] (4/8) Epoch 2, batch 9450, loss[loss=0.1701, simple_loss=0.2332, pruned_loss=0.05352, over 4689.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2393, pruned_loss=0.05345, over 972020.03 frames.], batch size: 15, lr: 7.13e-04
2022-05-04 05:19:48,357 INFO [train.py:715] (4/8) Epoch 2, batch 9500, loss[loss=0.1515, simple_loss=0.2283, pruned_loss=0.0373, over 4961.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2387, pruned_loss=0.05332, over 972135.66 frames.], batch size: 15, lr: 7.13e-04
2022-05-04 05:20:28,630 INFO [train.py:715] (4/8) Epoch 2, batch 9550, loss[loss=0.1721, simple_loss=0.2265, pruned_loss=0.05888, over 4959.00 frames.], tot_loss[loss=0.1729, simple_loss=0.239, pruned_loss=0.05341, over 972460.15 frames.], batch size: 21, lr: 7.12e-04
2022-05-04 05:21:08,637 INFO [train.py:715] (4/8) Epoch 2, batch 9600, loss[loss=0.1657, simple_loss=0.2364, pruned_loss=0.04748, over 4936.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2385, pruned_loss=0.05326, over 972305.71 frames.], batch size: 21, lr: 7.12e-04
2022-05-04 05:21:47,533 INFO [train.py:715] (4/8) Epoch 2, batch 9650, loss[loss=0.1613, simple_loss=0.2225, pruned_loss=0.0501, over 4774.00 frames.], tot_loss[loss=0.1719, simple_loss=0.238, pruned_loss=0.05289, over 972777.29 frames.], batch size: 17, lr: 7.12e-04
2022-05-04 05:22:27,777 INFO [train.py:715] (4/8) Epoch 2, batch 9700, loss[loss=0.2045, simple_loss=0.2804, pruned_loss=0.06431, over 4903.00 frames.], tot_loss[loss=0.1727, simple_loss=0.239, pruned_loss=0.05315, over 973155.81 frames.], batch size: 19, lr: 7.12e-04
2022-05-04 05:23:08,406 INFO [train.py:715] (4/8) Epoch 2, batch 9750, loss[loss=0.1512, simple_loss=0.2283, pruned_loss=0.03709, over 4837.00 frames.], tot_loss[loss=0.1732, simple_loss=0.24, pruned_loss=0.05321, over 972998.52 frames.], batch size: 13, lr: 7.11e-04
2022-05-04 05:23:47,696 INFO [train.py:715] (4/8) Epoch 2, batch 9800, loss[loss=0.1754, simple_loss=0.2398, pruned_loss=0.05554, over 4853.00 frames.], tot_loss[loss=0.1724, simple_loss=0.239, pruned_loss=0.05291, over 973102.94 frames.], batch size: 32, lr: 7.11e-04
2022-05-04 05:24:26,793 INFO [train.py:715] (4/8) Epoch 2, batch 9850, loss[loss=0.1436, simple_loss=0.2153, pruned_loss=0.03593, over 4896.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2388, pruned_loss=0.05303, over 972567.53 frames.], batch size: 19, lr: 7.11e-04
2022-05-04 05:25:06,815 INFO [train.py:715] (4/8) Epoch 2, batch 9900, loss[loss=0.1692, simple_loss=0.2279, pruned_loss=0.05524, over 4748.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2398, pruned_loss=0.05403, over 972666.68 frames.], batch size: 16, lr: 7.11e-04
2022-05-04 05:25:46,406 INFO [train.py:715] (4/8) Epoch 2, batch 9950, loss[loss=0.169, simple_loss=0.2276, pruned_loss=0.05518, over 4956.00 frames.], tot_loss[loss=0.173, simple_loss=0.2389, pruned_loss=0.05355, over 972470.95 frames.], batch size: 15, lr: 7.11e-04
2022-05-04 05:26:25,428 INFO [train.py:715] (4/8) Epoch 2, batch 10000, loss[loss=0.1688, simple_loss=0.2267, pruned_loss=0.0555, over 4961.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2393, pruned_loss=0.05354, over 972686.50 frames.], batch size: 14, lr: 7.10e-04
2022-05-04 05:27:06,103 INFO [train.py:715] (4/8) Epoch 2, batch 10050, loss[loss=0.1759, simple_loss=0.2243, pruned_loss=0.06374, over 4765.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2393, pruned_loss=0.05369, over 972876.24 frames.], batch size: 14, lr: 7.10e-04
2022-05-04 05:27:45,912 INFO [train.py:715] (4/8) Epoch 2, batch 10100, loss[loss=0.1566, simple_loss=0.2221, pruned_loss=0.04549, over 4955.00 frames.], tot_loss[loss=0.1732, simple_loss=0.239, pruned_loss=0.05367, over 972479.38 frames.], batch size: 21, lr: 7.10e-04
2022-05-04 05:28:25,917 INFO [train.py:715] (4/8) Epoch 2, batch 10150, loss[loss=0.2029, simple_loss=0.273, pruned_loss=0.0664, over 4698.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2393, pruned_loss=0.0539, over 972254.59 frames.], batch size: 15, lr: 7.10e-04
2022-05-04 05:29:06,173 INFO [train.py:715] (4/8) Epoch 2, batch 10200, loss[loss=0.1378, simple_loss=0.2172, pruned_loss=0.02915, over 4938.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2385, pruned_loss=0.05317, over 972823.73 frames.], batch size: 23, lr: 7.09e-04
2022-05-04 05:29:47,602 INFO [train.py:715] (4/8) Epoch 2, batch 10250, loss[loss=0.1624, simple_loss=0.2246, pruned_loss=0.05005, over 4755.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2399, pruned_loss=0.0539, over 972496.79 frames.], batch size: 19, lr: 7.09e-04
2022-05-04 05:30:27,420 INFO [train.py:715] (4/8) Epoch 2, batch 10300, loss[loss=0.1936, simple_loss=0.2587, pruned_loss=0.06424, over 4867.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2402, pruned_loss=0.05427, over 971490.68 frames.], batch size: 30, lr: 7.09e-04
2022-05-04 05:31:07,036 INFO [train.py:715] (4/8) Epoch 2, batch 10350, loss[loss=0.1692, simple_loss=0.2352, pruned_loss=0.05161, over 4874.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2397, pruned_loss=0.05359, over 971698.91 frames.], batch size: 38, lr: 7.09e-04
2022-05-04 05:31:49,852 INFO [train.py:715] (4/8) Epoch 2, batch 10400, loss[loss=0.1395, simple_loss=0.2078, pruned_loss=0.03558, over 4978.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2399, pruned_loss=0.0537, over 971816.71 frames.], batch size: 28, lr: 7.09e-04
2022-05-04 05:32:31,018 INFO [train.py:715] (4/8) Epoch 2, batch 10450, loss[loss=0.1726, simple_loss=0.2463, pruned_loss=0.04942, over 4777.00 frames.], tot_loss[loss=0.1737, simple_loss=0.24, pruned_loss=0.05368, over 971623.85 frames.], batch size: 18, lr: 7.08e-04
2022-05-04 05:33:11,274 INFO [train.py:715] (4/8) Epoch 2, batch 10500, loss[loss=0.1595, simple_loss=0.2085, pruned_loss=0.05521, over 4845.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2393, pruned_loss=0.0532, over 971917.78 frames.], batch size: 30, lr: 7.08e-04
2022-05-04 05:33:50,622 INFO [train.py:715] (4/8) Epoch 2, batch 10550, loss[loss=0.1701, simple_loss=0.2437, pruned_loss=0.04823, over 4940.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2398, pruned_loss=0.05352, over 971635.33 frames.], batch size: 24, lr: 7.08e-04
2022-05-04 05:34:31,847 INFO [train.py:715] (4/8) Epoch 2, batch 10600, loss[loss=0.2021, simple_loss=0.268, pruned_loss=0.06806, over 4863.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2397, pruned_loss=0.05332, over 971929.34 frames.], batch size: 20, lr: 7.08e-04
2022-05-04 05:35:12,037 INFO [train.py:715] (4/8) Epoch 2, batch 10650, loss[loss=0.1732, simple_loss=0.2431, pruned_loss=0.05166, over 4884.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2392, pruned_loss=0.05292, over 972023.92 frames.], batch size: 22, lr: 7.07e-04
2022-05-04 05:35:51,940 INFO [train.py:715] (4/8) Epoch 2, batch 10700, loss[loss=0.1921, simple_loss=0.2709, pruned_loss=0.05663, over 4972.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2398, pruned_loss=0.05301, over 972366.24 frames.], batch size: 15, lr: 7.07e-04
2022-05-04 05:36:32,502 INFO [train.py:715] (4/8) Epoch 2, batch 10750, loss[loss=0.1483, simple_loss=0.2187, pruned_loss=0.03898, over 4864.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2395, pruned_loss=0.05265, over 971828.88 frames.], batch size: 20, lr: 7.07e-04
2022-05-04 05:37:13,632 INFO [train.py:715] (4/8) Epoch 2, batch 10800, loss[loss=0.1551, simple_loss=0.2303, pruned_loss=0.03998, over 4786.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2409, pruned_loss=0.05348, over 972174.76 frames.], batch size: 18, lr: 7.07e-04
2022-05-04 05:37:53,807 INFO [train.py:715] (4/8) Epoch 2, batch 10850, loss[loss=0.1545, simple_loss=0.2282, pruned_loss=0.0404, over 4692.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2411, pruned_loss=0.05338, over 971868.86 frames.], batch size: 15, lr: 7.07e-04
2022-05-04 05:38:33,326 INFO [train.py:715] (4/8) Epoch 2, batch 10900, loss[loss=0.1851, simple_loss=0.2547, pruned_loss=0.05774, over 4913.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2413, pruned_loss=0.05357, over 972130.29 frames.], batch size: 19, lr: 7.06e-04
2022-05-04 05:39:14,357 INFO [train.py:715] (4/8) Epoch 2, batch 10950, loss[loss=0.1453, simple_loss=0.2177, pruned_loss=0.03647, over 4801.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2406, pruned_loss=0.05333, over 972348.58 frames.], batch size: 12, lr: 7.06e-04
2022-05-04 05:39:54,159 INFO [train.py:715] (4/8) Epoch 2, batch 11000, loss[loss=0.1832, simple_loss=0.2534, pruned_loss=0.05645, over 4803.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2393, pruned_loss=0.05283, over 972533.26 frames.], batch size: 21, lr: 7.06e-04
2022-05-04 05:40:33,759 INFO [train.py:715] (4/8) Epoch 2, batch 11050, loss[loss=0.1528, simple_loss=0.2212, pruned_loss=0.04215, over 4739.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2394, pruned_loss=0.05281, over 971821.90 frames.], batch size: 16, lr: 7.06e-04
2022-05-04 05:41:14,434 INFO [train.py:715] (4/8) Epoch 2, batch 11100, loss[loss=0.177, simple_loss=0.2361, pruned_loss=0.05897, over 4866.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2395, pruned_loss=0.05385, over 972018.67 frames.], batch size: 13, lr: 7.05e-04
2022-05-04 05:41:54,866 INFO [train.py:715] (4/8) Epoch 2, batch 11150, loss[loss=0.1884, simple_loss=0.2612, pruned_loss=0.05782, over 4864.00 frames.], tot_loss[loss=0.174, simple_loss=0.2397, pruned_loss=0.05411, over 971969.26 frames.], batch size: 22, lr: 7.05e-04
2022-05-04 05:42:35,625 INFO [train.py:715] (4/8) Epoch 2, batch 11200, loss[loss=0.131, simple_loss=0.1967, pruned_loss=0.0326, over 4845.00 frames.], tot_loss[loss=0.1731, simple_loss=0.2391, pruned_loss=0.05356, over 971190.88 frames.], batch size: 13, lr: 7.05e-04
2022-05-04 05:43:15,654 INFO [train.py:715] (4/8) Epoch 2, batch 11250, loss[loss=0.1636, simple_loss=0.2304, pruned_loss=0.04837, over 4943.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2393, pruned_loss=0.05365, over 972062.70 frames.], batch size: 21, lr: 7.05e-04
2022-05-04 05:43:56,718 INFO [train.py:715] (4/8) Epoch 2, batch 11300, loss[loss=0.1693, simple_loss=0.224, pruned_loss=0.05735, over 4785.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2383, pruned_loss=0.05315, over 972504.44 frames.], batch size: 17, lr: 7.05e-04
2022-05-04 05:44:37,057 INFO [train.py:715] (4/8) Epoch 2, batch 11350, loss[loss=0.1258, simple_loss=0.2052, pruned_loss=0.02317, over 4848.00 frames.], tot_loss[loss=0.1728, simple_loss=0.239, pruned_loss=0.05324, over 972000.81 frames.], batch size: 15, lr: 7.04e-04
2022-05-04 05:45:16,681 INFO [train.py:715] (4/8) Epoch 2, batch 11400, loss[loss=0.1639, simple_loss=0.2432, pruned_loss=0.04228, over 4882.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2396, pruned_loss=0.0537, over 972197.79 frames.], batch size: 22, lr: 7.04e-04
2022-05-04 05:45:56,735 INFO [train.py:715] (4/8) Epoch 2, batch 11450, loss[loss=0.1836, simple_loss=0.239, pruned_loss=0.06411, over 4972.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2391, pruned_loss=0.05327, over 973171.49 frames.], batch size: 15, lr: 7.04e-04
2022-05-04 05:46:37,326 INFO [train.py:715] (4/8) Epoch 2, batch 11500, loss[loss=0.1852, simple_loss=0.2582, pruned_loss=0.0561, over 4916.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2387, pruned_loss=0.0529, over 971765.41 frames.], batch size: 19, lr: 7.04e-04
2022-05-04 05:47:18,052 INFO [train.py:715] (4/8) Epoch 2, batch 11550, loss[loss=0.16, simple_loss=0.2322, pruned_loss=0.04391, over 4980.00 frames.], tot_loss[loss=0.1713, simple_loss=0.238, pruned_loss=0.05226, over 971416.72 frames.], batch size: 31, lr: 7.04e-04
2022-05-04 05:47:58,021 INFO [train.py:715] (4/8) Epoch 2, batch 11600, loss[loss=0.186, simple_loss=0.2416, pruned_loss=0.06514, over 4949.00 frames.], tot_loss[loss=0.171, simple_loss=0.2376, pruned_loss=0.05221, over 972827.51 frames.], batch size: 35, lr: 7.03e-04
2022-05-04 05:48:39,176 INFO [train.py:715] (4/8) Epoch 2, batch 11650, loss[loss=0.1894, simple_loss=0.2505, pruned_loss=0.06418, over 4862.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2378, pruned_loss=0.05239, over 972028.07 frames.], batch size: 20, lr: 7.03e-04
2022-05-04 05:49:19,421 INFO [train.py:715] (4/8) Epoch 2, batch 11700, loss[loss=0.1909, simple_loss=0.2544, pruned_loss=0.06369, over 4966.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2375, pruned_loss=0.05263, over 971885.95 frames.], batch size: 15, lr: 7.03e-04
2022-05-04 05:49:59,621 INFO [train.py:715] (4/8) Epoch 2, batch 11750, loss[loss=0.1995, simple_loss=0.2679, pruned_loss=0.06558, over 4948.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2376, pruned_loss=0.05264, over 972177.92 frames.], batch size: 21, lr: 7.03e-04
2022-05-04 05:50:40,401 INFO [train.py:715] (4/8) Epoch 2, batch 11800, loss[loss=0.1889, simple_loss=0.2513, pruned_loss=0.06325, over 4861.00 frames.], tot_loss[loss=0.172, simple_loss=0.238, pruned_loss=0.05301, over 973192.27 frames.], batch size: 16, lr: 7.02e-04
2022-05-04 05:51:20,986 INFO [train.py:715] (4/8) Epoch 2, batch 11850, loss[loss=0.1937, simple_loss=0.2667, pruned_loss=0.06035, over 4965.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2372, pruned_loss=0.05285, over 973634.71 frames.], batch size: 15, lr: 7.02e-04
2022-05-04 05:52:00,403 INFO [train.py:715] (4/8) Epoch 2, batch 11900, loss[loss=0.1695, simple_loss=0.2351, pruned_loss=0.05191, over 4856.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2382, pruned_loss=0.05317, over 972982.83 frames.], batch size: 20, lr: 7.02e-04
2022-05-04 05:52:40,332 INFO [train.py:715] (4/8) Epoch 2, batch 11950, loss[loss=0.1699, simple_loss=0.2386, pruned_loss=0.05067, over 4798.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2379, pruned_loss=0.05247, over 971579.80 frames.], batch size: 21, lr: 7.02e-04
2022-05-04 05:53:21,657 INFO [train.py:715] (4/8) Epoch 2, batch 12000, loss[loss=0.1757, simple_loss=0.2423, pruned_loss=0.05455, over 4957.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2398, pruned_loss=0.05366, over 971218.69 frames.], batch size: 39, lr: 7.02e-04
2022-05-04 05:53:21,657 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 05:53:45,622 INFO [train.py:742] (4/8) Epoch 2, validation: loss=0.1181, simple_loss=0.2049, pruned_loss=0.01568, over 914524.00 frames.
2022-05-04 05:54:27,024 INFO [train.py:715] (4/8) Epoch 2, batch 12050, loss[loss=0.1882, simple_loss=0.2475, pruned_loss=0.06444, over 4861.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2385, pruned_loss=0.05317, over 971094.47 frames.], batch size: 26, lr: 7.01e-04
2022-05-04 05:55:07,114 INFO [train.py:715] (4/8) Epoch 2, batch 12100, loss[loss=0.1997, simple_loss=0.256, pruned_loss=0.07171, over 4760.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2387, pruned_loss=0.05301, over 970910.73 frames.], batch size: 19, lr: 7.01e-04
2022-05-04 05:55:47,106 INFO [train.py:715] (4/8) Epoch 2, batch 12150, loss[loss=0.1542, simple_loss=0.2229, pruned_loss=0.04277, over 4696.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2387, pruned_loss=0.05273, over 970759.00 frames.], batch size: 15, lr: 7.01e-04
2022-05-04 05:56:27,808 INFO [train.py:715] (4/8) Epoch 2, batch 12200, loss[loss=0.1752, simple_loss=0.2455, pruned_loss=0.05251, over 4880.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2385, pruned_loss=0.05309, over 970291.06 frames.], batch size: 22, lr: 7.01e-04
2022-05-04 05:57:07,982 INFO [train.py:715] (4/8) Epoch 2, batch 12250, loss[loss=0.1565, simple_loss=0.2272, pruned_loss=0.04289, over 4828.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2379, pruned_loss=0.05269, over 969716.62 frames.], batch size: 15, lr: 7.01e-04
2022-05-04 05:57:48,411 INFO [train.py:715] (4/8) Epoch 2, batch 12300, loss[loss=0.1872, simple_loss=0.2436, pruned_loss=0.06534, over 4842.00 frames.], tot_loss[loss=0.1735, simple_loss=0.2395, pruned_loss=0.0538, over 971286.91 frames.], batch size: 32, lr: 7.00e-04
2022-05-04 05:58:28,538 INFO [train.py:715] (4/8) Epoch 2, batch 12350, loss[loss=0.1818, simple_loss=0.2446, pruned_loss=0.05955, over 4781.00 frames.], tot_loss[loss=0.174, simple_loss=0.2399, pruned_loss=0.05399, over 971785.56 frames.], batch size: 18, lr: 7.00e-04
2022-05-04 05:59:09,756 INFO [train.py:715] (4/8) Epoch 2, batch 12400, loss[loss=0.1927, simple_loss=0.2385, pruned_loss=0.07347, over 4836.00 frames.], tot_loss[loss=0.1729, simple_loss=0.239, pruned_loss=0.05337, over 971260.64 frames.], batch size: 13, lr: 7.00e-04
2022-05-04 05:59:50,014 INFO [train.py:715] (4/8) Epoch 2, batch 12450, loss[loss=0.1762, simple_loss=0.2449, pruned_loss=0.05375, over 4824.00 frames.], tot_loss[loss=0.1728, simple_loss=0.239, pruned_loss=0.05329, over 972188.68 frames.], batch size: 15, lr: 7.00e-04
2022-05-04 06:00:29,871 INFO [train.py:715] (4/8) Epoch 2, batch 12500, loss[loss=0.147, simple_loss=0.2188, pruned_loss=0.03764, over 4696.00 frames.], tot_loss[loss=0.1737, simple_loss=0.2398, pruned_loss=0.05379, over 971969.25 frames.], batch size: 15, lr: 6.99e-04
2022-05-04 06:01:10,537 INFO [train.py:715] (4/8) Epoch 2, batch 12550, loss[loss=0.1831, simple_loss=0.2573, pruned_loss=0.05444, over 4875.00 frames.], tot_loss[loss=0.1736, simple_loss=0.2396, pruned_loss=0.05377, over 972395.60 frames.], batch size: 16, lr: 6.99e-04
2022-05-04 06:01:50,872 INFO [train.py:715] (4/8) Epoch 2, batch 12600, loss[loss=0.1868, simple_loss=0.2661, pruned_loss=0.05375, over 4909.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2389, pruned_loss=0.05314, over 972354.00 frames.], batch size: 39, lr: 6.99e-04
2022-05-04 06:02:30,888 INFO [train.py:715] (4/8) Epoch 2, batch 12650, loss[loss=0.1786, simple_loss=0.2523, pruned_loss=0.05241, over 4795.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2386, pruned_loss=0.0526, over 971969.99 frames.], batch size: 21, lr: 6.99e-04
2022-05-04 06:03:11,021 INFO [train.py:715] (4/8) Epoch 2, batch 12700, loss[loss=0.1901, simple_loss=0.2563, pruned_loss=0.06192, over 4755.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2391, pruned_loss=0.05282, over 972464.17 frames.], batch size: 19, lr: 6.99e-04
2022-05-04 06:03:51,750 INFO [train.py:715] (4/8) Epoch 2, batch 12750, loss[loss=0.1493, simple_loss=0.2155, pruned_loss=0.04155, over 4915.00 frames.], tot_loss[loss=0.172, simple_loss=0.2385, pruned_loss=0.05276, over 972757.64 frames.], batch size: 23, lr: 6.98e-04
2022-05-04 06:04:31,914 INFO [train.py:715] (4/8) Epoch 2, batch 12800, loss[loss=0.1385, simple_loss=0.2088, pruned_loss=0.03405, over 4859.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2392, pruned_loss=0.05373, over 973032.16 frames.], batch size: 15, lr: 6.98e-04
2022-05-04 06:05:11,605 INFO [train.py:715] (4/8) Epoch 2, batch 12850, loss[loss=0.1346, simple_loss=0.1991, pruned_loss=0.03506, over 4967.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2382, pruned_loss=0.05273, over 972595.20 frames.], batch size: 14, lr: 6.98e-04
2022-05-04 06:05:52,434 INFO [train.py:715] (4/8) Epoch 2, batch 12900, loss[loss=0.177, simple_loss=0.2407, pruned_loss=0.05664, over 4960.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2385, pruned_loss=0.05328, over 972498.27 frames.], batch size: 24, lr: 6.98e-04
2022-05-04 06:06:32,853 INFO [train.py:715] (4/8) Epoch 2, batch 12950, loss[loss=0.1751, simple_loss=0.2384, pruned_loss=0.05594, over 4816.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2389, pruned_loss=0.0532, over 971838.41 frames.], batch size: 26, lr: 6.98e-04
2022-05-04 06:07:12,807 INFO [train.py:715] (4/8) Epoch 2, batch 13000, loss[loss=0.223, simple_loss=0.2722, pruned_loss=0.08695, over 4910.00 frames.], tot_loss[loss=0.1748, simple_loss=0.2407, pruned_loss=0.05448, over 971837.19 frames.], batch size: 39, lr: 6.97e-04
2022-05-04 06:07:53,250 INFO [train.py:715] (4/8) Epoch 2, batch 13050, loss[loss=0.1761, simple_loss=0.2482, pruned_loss=0.05205, over 4944.00 frames.], tot_loss[loss=0.1742, simple_loss=0.2403, pruned_loss=0.05404, over 971872.84 frames.], batch size: 21, lr: 6.97e-04
2022-05-04 06:08:34,488 INFO [train.py:715] (4/8) Epoch 2, batch 13100, loss[loss=0.1826, simple_loss=0.2497, pruned_loss=0.05778, over 4986.00 frames.], tot_loss[loss=0.1743, simple_loss=0.2405, pruned_loss=0.05408, over 972250.22 frames.], batch size: 35, lr: 6.97e-04
2022-05-04 06:09:14,672 INFO [train.py:715] (4/8) Epoch 2, batch 13150, loss[loss=0.2208, simple_loss=0.2809, pruned_loss=0.0804, over 4785.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2399, pruned_loss=0.0534, over 972486.55 frames.], batch size: 17, lr: 6.97e-04
2022-05-04 06:09:54,433 INFO [train.py:715] (4/8) Epoch 2, batch 13200, loss[loss=0.1409, simple_loss=0.2061, pruned_loss=0.03784, over 4933.00 frames.], tot_loss[loss=0.173, simple_loss=0.2393, pruned_loss=0.05335, over 972969.67 frames.], batch size: 23, lr: 6.96e-04
2022-05-04 06:10:35,328 INFO [train.py:715] (4/8) Epoch 2, batch 13250, loss[loss=0.1618, simple_loss=0.2201, pruned_loss=0.05174, over 4808.00 frames.], tot_loss[loss=0.1733, simple_loss=0.2391, pruned_loss=0.05377, over 973238.51 frames.], batch size: 26, lr: 6.96e-04
2022-05-04 06:11:15,861 INFO [train.py:715] (4/8) Epoch 2, batch 13300, loss[loss=0.1426, simple_loss=0.2156, pruned_loss=0.03475, over 4757.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2388, pruned_loss=0.05378, over 971871.40 frames.], batch size: 19, lr: 6.96e-04
2022-05-04 06:11:55,896 INFO [train.py:715] (4/8) Epoch 2, batch 13350, loss[loss=0.2002, simple_loss=0.266, pruned_loss=0.0672, over 4933.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2391, pruned_loss=0.05365, over 972842.94 frames.], batch size: 23, lr: 6.96e-04
2022-05-04 06:12:36,495 INFO [train.py:715] (4/8) Epoch 2, batch 13400, loss[loss=0.1654, simple_loss=0.2258, pruned_loss=0.05249, over 4751.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2389, pruned_loss=0.05323, over 972765.32 frames.], batch size: 19, lr: 6.96e-04
2022-05-04 06:13:17,576 INFO [train.py:715] (4/8) Epoch 2, batch 13450, loss[loss=0.1919, simple_loss=0.2647, pruned_loss=0.05958, over 4979.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2386, pruned_loss=0.05341, over 972685.40 frames.], batch size: 28, lr: 6.95e-04
2022-05-04 06:13:57,531 INFO [train.py:715] (4/8) Epoch 2, batch 13500, loss[loss=0.1801, simple_loss=0.2375, pruned_loss=0.06132, over 4936.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2383, pruned_loss=0.05351, over 972851.21 frames.], batch size: 23, lr: 6.95e-04
2022-05-04 06:14:37,537 INFO [train.py:715] (4/8) Epoch 2, batch 13550, loss[loss=0.1411, simple_loss=0.2101, pruned_loss=0.03608, over 4820.00 frames.], tot_loss[loss=0.173, simple_loss=0.239, pruned_loss=0.05348, over 973485.62 frames.], batch size: 27, lr: 6.95e-04
2022-05-04 06:15:18,680 INFO [train.py:715] (4/8) Epoch 2, batch 13600, loss[loss=0.1588, simple_loss=0.2278, pruned_loss=0.04488, over 4794.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2388, pruned_loss=0.05343, over 973318.62 frames.], batch size: 14, lr: 6.95e-04
2022-05-04 06:15:59,125 INFO [train.py:715] (4/8) Epoch 2, batch 13650, loss[loss=0.1784, simple_loss=0.2491, pruned_loss=0.05382, over 4876.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2389, pruned_loss=0.05326, over 973401.09 frames.], batch size: 32, lr: 6.95e-04
2022-05-04 06:16:38,691 INFO [train.py:715] (4/8) Epoch 2, batch 13700, loss[loss=0.1613, simple_loss=0.2392, pruned_loss=0.04166, over 4975.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2392, pruned_loss=0.0536, over 973043.39 frames.], batch size: 28, lr: 6.94e-04
2022-05-04 06:17:19,956 INFO [train.py:715] (4/8) Epoch 2, batch 13750, loss[loss=0.1573, simple_loss=0.2311, pruned_loss=0.04175, over 4772.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2379, pruned_loss=0.05295, over 972285.07 frames.], batch size: 17, lr: 6.94e-04
2022-05-04 06:18:00,036 INFO [train.py:715] (4/8) Epoch 2, batch 13800, loss[loss=0.1835, simple_loss=0.239, pruned_loss=0.06398, over 4899.00 frames.], tot_loss[loss=0.1733, simple_loss=0.239, pruned_loss=0.05385, over 971992.62 frames.], batch size: 17, lr: 6.94e-04
2022-05-04 06:18:39,726 INFO [train.py:715] (4/8) Epoch 2, batch 13850, loss[loss=0.2014, simple_loss=0.255, pruned_loss=0.0739, over 4756.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2392, pruned_loss=0.05373, over 972720.22 frames.], batch size: 19, lr: 6.94e-04
2022-05-04 06:19:19,318 INFO [train.py:715] (4/8) Epoch 2, batch 13900, loss[loss=0.1466, simple_loss=0.2188, pruned_loss=0.03716, over 4913.00 frames.], tot_loss[loss=0.1728, simple_loss=0.2387, pruned_loss=0.0534, over 973476.47 frames.], batch size: 19, lr: 6.94e-04
2022-05-04 06:20:00,084 INFO [train.py:715] (4/8) Epoch 2, batch 13950, loss[loss=0.1909, simple_loss=0.2561, pruned_loss=0.06288, over 4951.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2386, pruned_loss=0.05279, over 973750.18 frames.], batch size: 14, lr: 6.93e-04
2022-05-04 06:20:40,294 INFO [train.py:715] (4/8) Epoch 2, batch 14000, loss[loss=0.17, simple_loss=0.2388, pruned_loss=0.05055, over 4791.00 frames.], tot_loss[loss=0.172, simple_loss=0.2387, pruned_loss=0.05266, over 973462.81 frames.], batch size: 18, lr: 6.93e-04
2022-05-04 06:21:19,543 INFO [train.py:715] (4/8) Epoch 2, batch 14050, loss[loss=0.1513, simple_loss=0.2182, pruned_loss=0.04227, over 4962.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2377, pruned_loss=0.05246, over 972900.00 frames.], batch size: 14, lr: 6.93e-04
2022-05-04 06:22:01,049 INFO [train.py:715] (4/8) Epoch 2, batch 14100, loss[loss=0.1707, simple_loss=0.2384, pruned_loss=0.05154, over 4940.00 frames.], tot_loss[loss=0.1712, simple_loss=0.238, pruned_loss=0.05222, over 972630.79 frames.], batch size: 21, lr: 6.93e-04
2022-05-04 06:22:41,689 INFO [train.py:715] (4/8) Epoch 2, batch 14150, loss[loss=0.1351, simple_loss=0.2061, pruned_loss=0.03203, over 4985.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2381, pruned_loss=0.05229, over 972743.71 frames.], batch size: 14, lr: 6.93e-04
2022-05-04 06:23:21,639 INFO [train.py:715] (4/8) Epoch 2, batch 14200, loss[loss=0.1683, simple_loss=0.2353, pruned_loss=0.05062, over 4893.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2376, pruned_loss=0.05225, over 971755.01 frames.], batch size: 22, lr: 6.92e-04
2022-05-04 06:24:01,479 INFO [train.py:715] (4/8) Epoch 2, batch 14250, loss[loss=0.153, simple_loss=0.2116, pruned_loss=0.04724, over 4883.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2384, pruned_loss=0.05268, over 972290.25 frames.], batch size: 16, lr: 6.92e-04
2022-05-04 06:24:42,096 INFO [train.py:715] (4/8) Epoch 2, batch 14300, loss[loss=0.1983, simple_loss=0.2704, pruned_loss=0.06308, over 4959.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2373, pruned_loss=0.05217, over 971925.92 frames.], batch size: 15, lr: 6.92e-04
2022-05-04 06:25:21,659 INFO [train.py:715] (4/8) Epoch 2, batch 14350, loss[loss=0.1483, simple_loss=0.2215, pruned_loss=0.03757, over 4961.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2386, pruned_loss=0.05294, over 972396.49 frames.], batch size: 15, lr: 6.92e-04
2022-05-04 06:26:01,519 INFO [train.py:715] (4/8) Epoch 2, batch 14400, loss[loss=0.1561, simple_loss=0.2274, pruned_loss=0.04242, over 4906.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2386, pruned_loss=0.05327, over 971531.49 frames.], batch size: 17, lr: 6.92e-04
2022-05-04 06:26:41,858 INFO [train.py:715] (4/8) Epoch 2, batch 14450, loss[loss=0.148, simple_loss=0.2243, pruned_loss=0.03592, over 4823.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2391, pruned_loss=0.05331, over 971164.48 frames.], batch size: 15, lr: 6.91e-04
2022-05-04 06:27:22,095 INFO [train.py:715] (4/8) Epoch 2, batch 14500, loss[loss=0.187, simple_loss=0.2416, pruned_loss=0.0662, over 4806.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2385, pruned_loss=0.05316, over 972044.68 frames.], batch size: 25, lr: 6.91e-04
2022-05-04 06:28:01,692 INFO [train.py:715] (4/8) Epoch 2, batch 14550, loss[loss=0.171, simple_loss=0.2415, pruned_loss=0.0502, over 4950.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2377, pruned_loss=0.05261, over 971372.31 frames.], batch size: 21, lr: 6.91e-04
2022-05-04 06:28:42,166 INFO [train.py:715] (4/8) Epoch 2, batch 14600, loss[loss=0.173, simple_loss=0.2405, pruned_loss=0.05275, over 4990.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2386, pruned_loss=0.05292, over 972601.15 frames.], batch size: 20, lr: 6.91e-04
2022-05-04 06:29:22,663 INFO [train.py:715] (4/8) Epoch 2, batch 14650, loss[loss=0.1852, simple_loss=0.2475, pruned_loss=0.06145, over 4778.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2382, pruned_loss=0.0528, over 972563.46 frames.], batch size: 18, lr: 6.90e-04
2022-05-04 06:30:01,956 INFO [train.py:715] (4/8) Epoch 2, batch 14700, loss[loss=0.1823, simple_loss=0.2396, pruned_loss=0.06256, over 4977.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2371, pruned_loss=0.0525, over 972796.29 frames.], batch size: 14, lr: 6.90e-04
2022-05-04 06:30:41,281 INFO [train.py:715] (4/8) Epoch 2, batch 14750, loss[loss=0.1458, simple_loss=0.23, pruned_loss=0.03076, over 4811.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2374, pruned_loss=0.05257, over 973483.25 frames.], batch size: 25, lr: 6.90e-04
2022-05-04 06:31:21,768 INFO [train.py:715] (4/8) Epoch 2, batch 14800, loss[loss=0.1643, simple_loss=0.233, pruned_loss=0.04783, over 4989.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2384, pruned_loss=0.05269, over 973472.25 frames.], batch size: 14, lr: 6.90e-04
2022-05-04 06:32:01,269 INFO [train.py:715] (4/8) Epoch 2, batch 14850, loss[loss=0.2031, simple_loss=0.2563, pruned_loss=0.07494, over 4962.00 frames.], tot_loss[loss=0.1729, simple_loss=0.2391, pruned_loss=0.05334, over 973152.67 frames.], batch size: 35, lr: 6.90e-04
2022-05-04 06:32:40,952 INFO [train.py:715] (4/8) Epoch 2, batch 14900, loss[loss=0.1547, simple_loss=0.2078, pruned_loss=0.05082, over 4824.00 frames.], tot_loss[loss=0.1734, simple_loss=0.2394, pruned_loss=0.05369, over 972397.55 frames.], batch size: 13, lr: 6.89e-04
2022-05-04 06:33:21,118 INFO [train.py:715] (4/8) Epoch 2, batch 14950, loss[loss=0.2442, simple_loss=0.3035, pruned_loss=0.09251, over 4933.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2384, pruned_loss=0.05306, over 971659.88 frames.], batch size: 23, lr: 6.89e-04
2022-05-04 06:34:01,757 INFO [train.py:715] (4/8) Epoch 2, batch 15000, loss[loss=0.168, simple_loss=0.24, pruned_loss=0.04803, over 4745.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2383, pruned_loss=0.05307, over 971886.76 frames.], batch size: 16, lr: 6.89e-04
2022-05-04 06:34:01,757 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 06:34:11,141 INFO [train.py:742] (4/8) Epoch 2, validation: loss=0.1176, simple_loss=0.2043, pruned_loss=0.01548, over 914524.00 frames.
2022-05-04 06:34:52,067 INFO [train.py:715] (4/8) Epoch 2, batch 15050, loss[loss=0.2224, simple_loss=0.2661, pruned_loss=0.08937, over 4970.00 frames.], tot_loss[loss=0.1719, simple_loss=0.238, pruned_loss=0.0529, over 971717.63 frames.], batch size: 31, lr: 6.89e-04
2022-05-04 06:35:31,186 INFO [train.py:715] (4/8) Epoch 2, batch 15100, loss[loss=0.1761, simple_loss=0.2435, pruned_loss=0.05442, over 4986.00 frames.], tot_loss[loss=0.172, simple_loss=0.2379, pruned_loss=0.05307, over 972086.55 frames.], batch size: 25, lr: 6.89e-04
2022-05-04 06:36:11,669 INFO [train.py:715] (4/8) Epoch 2, batch 15150, loss[loss=0.1318, simple_loss=0.1989, pruned_loss=0.03236, over 4783.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2378, pruned_loss=0.05281, over 972834.93 frames.], batch size: 17, lr: 6.88e-04
2022-05-04 06:36:52,157 INFO [train.py:715] (4/8) Epoch 2, batch 15200, loss[loss=0.2022, simple_loss=0.258, pruned_loss=0.07317, over 4690.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2368, pruned_loss=0.05247, over 972076.00 frames.], batch size: 15, lr: 6.88e-04
2022-05-04 06:37:31,885 INFO [train.py:715] (4/8) Epoch 2, batch 15250, loss[loss=0.1623, simple_loss=0.233, pruned_loss=0.0458, over 4813.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2364, pruned_loss=0.0521, over 972626.01 frames.], batch size: 27, lr: 6.88e-04
2022-05-04 06:38:11,344 INFO [train.py:715] (4/8) Epoch 2, batch 15300, loss[loss=0.1383, simple_loss=0.2047, pruned_loss=0.03594, over 4940.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2372, pruned_loss=0.05252, over 972180.58 frames.], batch size: 18, lr: 6.88e-04
2022-05-04 06:38:51,802 INFO [train.py:715] (4/8) Epoch 2, batch 15350, loss[loss=0.1714, simple_loss=0.2426, pruned_loss=0.05011, over 4744.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2376, pruned_loss=0.05236, over 973072.84 frames.], batch size: 16, lr: 6.88e-04
2022-05-04 06:39:32,693 INFO [train.py:715] (4/8) Epoch 2, batch 15400, loss[loss=0.1665, simple_loss=0.2376, pruned_loss=0.04773, over 4956.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2385, pruned_loss=0.0532, over 972878.03 frames.], batch size: 24, lr: 6.87e-04
2022-05-04 06:40:11,869 INFO [train.py:715] (4/8) Epoch 2, batch 15450, loss[loss=0.1512, simple_loss=0.2172, pruned_loss=0.04259, over 4773.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2372, pruned_loss=0.05253, over 973072.61 frames.], batch size: 14, lr: 6.87e-04
2022-05-04 06:40:52,373 INFO [train.py:715] (4/8) Epoch 2, batch 15500, loss[loss=0.1722, simple_loss=0.2447, pruned_loss=0.04981, over 4800.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2377, pruned_loss=0.05275, over 972853.19 frames.], batch size: 21, lr: 6.87e-04
2022-05-04 06:41:32,621 INFO [train.py:715] (4/8) Epoch 2, batch 15550, loss[loss=0.1801, simple_loss=0.2399, pruned_loss=0.06015, over 4804.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2388, pruned_loss=0.0532, over 972299.58 frames.], batch size: 14, lr: 6.87e-04
2022-05-04 06:42:12,561 INFO [train.py:715] (4/8) Epoch 2, batch 15600, loss[loss=0.1635, simple_loss=0.2263, pruned_loss=0.05038, over 4772.00 frames.], tot_loss[loss=0.1722, simple_loss=0.2387, pruned_loss=0.05285, over 972901.89 frames.], batch size: 17, lr: 6.87e-04
2022-05-04 06:42:52,372 INFO [train.py:715] (4/8) Epoch 2, batch 15650, loss[loss=0.1618, simple_loss=0.2294, pruned_loss=0.04706, over 4723.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2382, pruned_loss=0.05271, over 972653.26 frames.], batch size: 16, lr: 6.86e-04
2022-05-04 06:43:33,099 INFO [train.py:715] (4/8) Epoch 2, batch 15700, loss[loss=0.1666, simple_loss=0.2338, pruned_loss=0.04973, over 4754.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2365, pruned_loss=0.05161, over 972237.22 frames.], batch size: 16, lr: 6.86e-04
2022-05-04 06:44:13,628 INFO [train.py:715] (4/8) Epoch 2, batch 15750, loss[loss=0.1571, simple_loss=0.2231, pruned_loss=0.04556, over 4751.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2378, pruned_loss=0.05232, over 972295.00 frames.], batch size: 16, lr: 6.86e-04
2022-05-04 06:44:52,970 INFO [train.py:715] (4/8) Epoch 2, batch 15800, loss[loss=0.1827, simple_loss=0.2513, pruned_loss=0.05707, over 4975.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2373, pruned_loss=0.05206, over 972242.66 frames.], batch size: 25, lr: 6.86e-04
2022-05-04 06:45:33,630 INFO [train.py:715] (4/8) Epoch 2, batch 15850, loss[loss=0.1599, simple_loss=0.2209, pruned_loss=0.04941, over 4937.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2379, pruned_loss=0.05275, over 972254.10 frames.], batch size: 21, lr: 6.86e-04
2022-05-04 06:46:14,113 INFO [train.py:715] (4/8) Epoch 2, batch 15900, loss[loss=0.1602, simple_loss=0.2272, pruned_loss=0.04654, over 4933.00 frames.], tot_loss[loss=0.1719, simple_loss=0.238, pruned_loss=0.05286, over 972472.06 frames.], batch size: 35, lr: 6.85e-04
2022-05-04 06:46:53,877 INFO [train.py:715] (4/8) Epoch 2, batch 15950, loss[loss=0.1694, simple_loss=0.2436, pruned_loss=0.04756, over 4935.00 frames.], tot_loss[loss=0.1721, simple_loss=0.238, pruned_loss=0.05307, over 971355.68 frames.], batch size: 23, lr: 6.85e-04
2022-05-04 06:47:34,110 INFO [train.py:715] (4/8) Epoch 2, batch 16000, loss[loss=0.1553, simple_loss=0.2207, pruned_loss=0.04496, over 4821.00 frames.], tot_loss[loss=0.1718, simple_loss=0.2381, pruned_loss=0.05278, over 970745.97 frames.], batch size: 26, lr: 6.85e-04
2022-05-04 06:48:14,441 INFO [train.py:715] (4/8) Epoch 2, batch 16050, loss[loss=0.1721, simple_loss=0.2383, pruned_loss=0.05293, over 4984.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2378, pruned_loss=0.05245, over 970916.15 frames.], batch size: 39, lr: 6.85e-04
2022-05-04 06:48:54,891 INFO [train.py:715] (4/8) Epoch 2, batch 16100, loss[loss=0.1966, simple_loss=0.2499, pruned_loss=0.0716, over 4781.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2386, pruned_loss=0.05303, over 971800.90 frames.], batch size: 18, lr: 6.85e-04
2022-05-04 06:49:34,155 INFO [train.py:715] (4/8) Epoch 2, batch 16150, loss[loss=0.1519, simple_loss=0.2179, pruned_loss=0.04293, over 4789.00 frames.], tot_loss[loss=0.1718, simple_loss=0.238, pruned_loss=0.05276, over 971500.10 frames.], batch size: 18, lr: 6.84e-04
2022-05-04 06:50:14,544 INFO [train.py:715] (4/8) Epoch 2, batch 16200, loss[loss=0.1395, simple_loss=0.2112, pruned_loss=0.03394, over 4801.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2372, pruned_loss=0.05198, over 971698.34 frames.], batch size: 12, lr: 6.84e-04
2022-05-04 06:50:54,951 INFO [train.py:715] (4/8) Epoch 2, batch 16250, loss[loss=0.1898, simple_loss=0.2622, pruned_loss=0.05867, over 4924.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2375, pruned_loss=0.05199, over 972081.62 frames.], batch size: 23, lr: 6.84e-04
2022-05-04 06:51:34,791 INFO [train.py:715] (4/8) Epoch 2, batch 16300, loss[loss=0.1672, simple_loss=0.2363, pruned_loss=0.04902, over 4860.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2381, pruned_loss=0.05233, over 973088.56 frames.], batch size: 16, lr: 6.84e-04
2022-05-04 06:52:14,668 INFO [train.py:715] (4/8) Epoch 2, batch 16350, loss[loss=0.152, simple_loss=0.2194, pruned_loss=0.04225, over 4796.00 frames.], tot_loss[loss=0.1724, simple_loss=0.2393, pruned_loss=0.05277, over 972031.88 frames.], batch size: 21, lr: 6.84e-04
2022-05-04 06:52:55,172 INFO [train.py:715] (4/8) Epoch 2, batch 16400, loss[loss=0.1891, simple_loss=0.2596, pruned_loss=0.0593, over 4815.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2392, pruned_loss=0.05251, over 972457.83 frames.], batch size: 25, lr: 6.83e-04
2022-05-04 06:53:35,563 INFO [train.py:715] (4/8) Epoch 2, batch 16450, loss[loss=0.138, simple_loss=0.2136, pruned_loss=0.03127, over 4961.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2382, pruned_loss=0.05206, over 972471.81 frames.], batch size: 21, lr: 6.83e-04
2022-05-04 06:54:15,145 INFO [train.py:715] (4/8) Epoch 2, batch 16500, loss[loss=0.1944, simple_loss=0.2568, pruned_loss=0.06605, over 4923.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2381, pruned_loss=0.0525, over 971581.25 frames.], batch size: 39, lr: 6.83e-04
2022-05-04 06:54:56,122 INFO [train.py:715] (4/8) Epoch 2, batch 16550, loss[loss=0.1628, simple_loss=0.2272, pruned_loss=0.04923, over 4892.00 frames.], tot_loss[loss=0.1713, simple_loss=0.238, pruned_loss=0.05231, over 970769.00 frames.], batch size: 19, lr: 6.83e-04
2022-05-04 06:55:36,862 INFO [train.py:715] (4/8) Epoch 2, batch 16600, loss[loss=0.2112, simple_loss=0.2743, pruned_loss=0.07402, over 4936.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2372, pruned_loss=0.05189, over 970542.33 frames.], batch size: 39, lr: 6.83e-04
2022-05-04 06:56:16,713 INFO [train.py:715] (4/8) Epoch 2, batch 16650, loss[loss=0.1489, simple_loss=0.2232, pruned_loss=0.03728, over 4889.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2378, pruned_loss=0.05233, over 971061.17 frames.], batch size: 19, lr: 6.82e-04
2022-05-04 06:56:57,160 INFO [train.py:715] (4/8) Epoch 2, batch 16700, loss[loss=0.169, simple_loss=0.229, pruned_loss=0.05453, over 4886.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2381, pruned_loss=0.05239, over 971446.03 frames.], batch size: 32, lr: 6.82e-04
2022-05-04 06:57:37,915 INFO [train.py:715] (4/8) Epoch 2, batch 16750, loss[loss=0.1232, simple_loss=0.191, pruned_loss=0.02771, over 4978.00 frames.], tot_loss[loss=0.171, simple_loss=0.2377, pruned_loss=0.0522, over 971714.42 frames.], batch size: 14, lr: 6.82e-04
2022-05-04 06:58:18,617 INFO [train.py:715] (4/8) Epoch 2, batch 16800, loss[loss=0.1837, simple_loss=0.2577, pruned_loss=0.05482, over 4972.00 frames.], tot_loss[loss=0.1698, simple_loss=0.237, pruned_loss=0.05127, over 971263.41 frames.], batch size: 15, lr: 6.82e-04
2022-05-04 06:58:58,045 INFO [train.py:715] (4/8) Epoch 2, batch 16850, loss[loss=0.1507, simple_loss=0.236, pruned_loss=0.03266, over 4901.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2366, pruned_loss=0.05142, over 971676.49 frames.], batch size: 29, lr: 6.82e-04
2022-05-04 06:59:39,314 INFO [train.py:715] (4/8) Epoch 2, batch 16900, loss[loss=0.1693, simple_loss=0.2297, pruned_loss=0.05444, over 4691.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2381, pruned_loss=0.052, over 971856.65 frames.], batch size: 15, lr: 6.81e-04
2022-05-04 07:00:20,133 INFO [train.py:715] (4/8) Epoch 2, batch 16950, loss[loss=0.145, simple_loss=0.2196, pruned_loss=0.03519, over 4916.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2391, pruned_loss=0.05288, over 972578.47 frames.], batch size: 17, lr: 6.81e-04
2022-05-04 07:00:59,942 INFO [train.py:715] (4/8) Epoch 2, batch 17000, loss[loss=0.2007, simple_loss=0.2663, pruned_loss=0.06761, over 4968.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2391, pruned_loss=0.05293, over 972421.70 frames.], batch size: 39, lr: 6.81e-04
2022-05-04 07:01:40,372 INFO [train.py:715] (4/8) Epoch 2, batch 17050, loss[loss=0.1813, simple_loss=0.2392, pruned_loss=0.06165, over 4798.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2385, pruned_loss=0.05283, over 972140.02 frames.], batch size: 21, lr: 6.81e-04
2022-05-04 07:02:20,962 INFO [train.py:715] (4/8) Epoch 2, batch 17100, loss[loss=0.1643, simple_loss=0.2361, pruned_loss=0.04625, over 4789.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2379, pruned_loss=0.0527, over 972200.17 frames.], batch size: 18, lr: 6.81e-04
2022-05-04 07:03:01,189 INFO [train.py:715] (4/8) Epoch 2, batch 17150, loss[loss=0.155, simple_loss=0.2237, pruned_loss=0.04315, over 4939.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2383, pruned_loss=0.05278, over 972343.89 frames.], batch size: 23, lr: 6.81e-04
2022-05-04 07:03:40,480 INFO [train.py:715] (4/8) Epoch 2, batch 17200, loss[loss=0.161, simple_loss=0.2326, pruned_loss=0.04466, over 4976.00 frames.], tot_loss[loss=0.1732, simple_loss=0.2398, pruned_loss=0.05328, over 971808.43 frames.], batch size: 15, lr: 6.80e-04
2022-05-04 07:04:20,885 INFO [train.py:715] (4/8) Epoch 2, batch 17250, loss[loss=0.2322, simple_loss=0.2715, pruned_loss=0.09646, over 4865.00 frames.], tot_loss[loss=0.1739, simple_loss=0.2403, pruned_loss=0.05376, over 972001.08 frames.], batch size: 32, lr: 6.80e-04
2022-05-04 07:05:01,344 INFO [train.py:715] (4/8) Epoch 2, batch 17300, loss[loss=0.1857, simple_loss=0.2354, pruned_loss=0.06798, over 4840.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2392, pruned_loss=0.05306, over 973343.69 frames.], batch size: 15, lr: 6.80e-04
2022-05-04 07:05:40,924 INFO [train.py:715] (4/8) Epoch 2, batch 17350, loss[loss=0.189, simple_loss=0.2592, pruned_loss=0.05938, over 4804.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2383, pruned_loss=0.05231, over 972490.66 frames.], batch size: 21, lr: 6.80e-04
2022-05-04 07:06:20,385 INFO [train.py:715] (4/8) Epoch 2, batch 17400, loss[loss=0.1414, simple_loss=0.2134, pruned_loss=0.0347, over 4935.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2385, pruned_loss=0.05201, over 972717.60 frames.], batch size: 23, lr: 6.80e-04
2022-05-04 07:07:00,339 INFO [train.py:715] (4/8) Epoch 2, batch 17450, loss[loss=0.1499, simple_loss=0.2252, pruned_loss=0.03732, over 4963.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2382, pruned_loss=0.0523, over 972597.87 frames.], batch size: 24, lr: 6.79e-04
2022-05-04 07:07:40,091 INFO [train.py:715] (4/8) Epoch 2, batch 17500, loss[loss=0.1404, simple_loss=0.2124, pruned_loss=0.03421, over 4814.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2378, pruned_loss=0.05228, over 972411.30 frames.], batch size: 13, lr: 6.79e-04
2022-05-04 07:08:18,850 INFO [train.py:715] (4/8) Epoch 2, batch 17550, loss[loss=0.1832, simple_loss=0.2413, pruned_loss=0.06251, over 4783.00 frames.], tot_loss[loss=0.1727, simple_loss=0.2389, pruned_loss=0.0533, over 972950.69 frames.], batch size: 18, lr: 6.79e-04
2022-05-04 07:08:58,969 INFO [train.py:715] (4/8) Epoch 2, batch 17600, loss[loss=0.1447, simple_loss=0.2051, pruned_loss=0.04215, over 4967.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2376, pruned_loss=0.0528, over 972102.33 frames.], batch size: 24, lr: 6.79e-04
2022-05-04 07:09:38,385 INFO [train.py:715] (4/8) Epoch 2, batch 17650, loss[loss=0.1883, simple_loss=0.2493, pruned_loss=0.06363, over 4738.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2375, pruned_loss=0.0527, over 972002.98 frames.], batch size: 16, lr: 6.79e-04
2022-05-04 07:10:17,891 INFO [train.py:715] (4/8) Epoch 2, batch 17700, loss[loss=0.1764, simple_loss=0.2506, pruned_loss=0.05111, over 4850.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2379, pruned_loss=0.05277, over 972204.45 frames.], batch size: 20, lr: 6.78e-04
2022-05-04 07:10:57,825 INFO [train.py:715] (4/8) Epoch 2, batch 17750, loss[loss=0.1656, simple_loss=0.2494, pruned_loss=0.04089, over 4936.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2383, pruned_loss=0.05274, over 972825.82 frames.], batch size: 23, lr: 6.78e-04
2022-05-04 07:11:37,689 INFO [train.py:715] (4/8) Epoch 2, batch 17800, loss[loss=0.1779, simple_loss=0.2403, pruned_loss=0.05773, over 4847.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2379, pruned_loss=0.05247, over 972998.16 frames.], batch size: 15, lr: 6.78e-04
2022-05-04 07:12:17,974 INFO [train.py:715] (4/8) Epoch 2, batch 17850, loss[loss=0.1579, simple_loss=0.234, pruned_loss=0.04085, over 4765.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2391, pruned_loss=0.05305, over 973432.72 frames.], batch size: 14, lr: 6.78e-04
2022-05-04 07:12:56,814 INFO [train.py:715] (4/8) Epoch 2, batch 17900, loss[loss=0.2281, simple_loss=0.2925, pruned_loss=0.08187, over 4949.00 frames.], tot_loss[loss=0.1726, simple_loss=0.2387, pruned_loss=0.05325, over 973025.35 frames.], batch size: 35, lr: 6.78e-04
2022-05-04 07:13:36,734 INFO [train.py:715] (4/8) Epoch 2, batch 17950, loss[loss=0.135, simple_loss=0.216, pruned_loss=0.027, over 4768.00 frames.], tot_loss[loss=0.1725, simple_loss=0.2392, pruned_loss=0.05295, over 971639.59 frames.], batch size: 12, lr: 6.77e-04
2022-05-04 07:14:16,910 INFO [train.py:715] (4/8) Epoch 2, batch 18000, loss[loss=0.1844, simple_loss=0.2524, pruned_loss=0.0582, over 4943.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2389, pruned_loss=0.0528, over 972023.92 frames.], batch size: 39, lr: 6.77e-04
2022-05-04 07:14:16,910 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 07:14:26,627 INFO [train.py:742] (4/8) Epoch 2, validation: loss=0.1173, simple_loss=0.2039, pruned_loss=0.01538, over 914524.00 frames.
2022-05-04 07:15:07,357 INFO [train.py:715] (4/8) Epoch 2, batch 18050, loss[loss=0.1766, simple_loss=0.2362, pruned_loss=0.05853, over 4971.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2374, pruned_loss=0.05181, over 972483.76 frames.], batch size: 28, lr: 6.77e-04
2022-05-04 07:15:46,535 INFO [train.py:715] (4/8) Epoch 2, batch 18100, loss[loss=0.1685, simple_loss=0.2398, pruned_loss=0.0486, over 4986.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2371, pruned_loss=0.05209, over 972546.78 frames.], batch size: 28, lr: 6.77e-04
2022-05-04 07:16:27,421 INFO [train.py:715] (4/8) Epoch 2, batch 18150, loss[loss=0.2394, simple_loss=0.295, pruned_loss=0.09192, over 4846.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2381, pruned_loss=0.05269, over 973127.71 frames.], batch size: 30, lr: 6.77e-04
2022-05-04 07:17:08,371 INFO [train.py:715] (4/8) Epoch 2, batch 18200, loss[loss=0.145, simple_loss=0.2201, pruned_loss=0.03493, over 4984.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2375, pruned_loss=0.0522, over 972836.84 frames.], batch size: 28, lr: 6.76e-04
2022-05-04 07:17:49,831 INFO [train.py:715] (4/8) Epoch 2, batch 18250, loss[loss=0.1678, simple_loss=0.2378, pruned_loss=0.0489, over 4753.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2377, pruned_loss=0.05232, over 972002.48 frames.], batch size: 19, lr: 6.76e-04
2022-05-04 07:18:30,274 INFO [train.py:715] (4/8) Epoch 2, batch 18300, loss[loss=0.1552, simple_loss=0.2279, pruned_loss=0.04129, over 4959.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2368, pruned_loss=0.0517, over 971539.17 frames.], batch size: 24, lr: 6.76e-04
2022-05-04 07:19:12,137 INFO [train.py:715] (4/8) Epoch 2, batch 18350, loss[loss=0.1736, simple_loss=0.2268, pruned_loss=0.06021, over 4883.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2368, pruned_loss=0.05214, over 971846.45 frames.], batch size: 16, lr: 6.76e-04
2022-05-04 07:19:56,504 INFO [train.py:715] (4/8) Epoch 2, batch 18400, loss[loss=0.1668, simple_loss=0.2415, pruned_loss=0.04603, over 4892.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2376, pruned_loss=0.05214, over 970613.66 frames.], batch size: 19, lr: 6.76e-04
2022-05-04 07:20:36,594 INFO [train.py:715] (4/8) Epoch 2, batch 18450, loss[loss=0.1596, simple_loss=0.2228, pruned_loss=0.04818, over 4763.00 frames.], tot_loss[loss=0.172, simple_loss=0.2385, pruned_loss=0.05279, over 970687.24 frames.], batch size: 19, lr: 6.75e-04
2022-05-04 07:21:18,110 INFO [train.py:715] (4/8) Epoch 2, batch 18500, loss[loss=0.1785, simple_loss=0.2362, pruned_loss=0.06038, over 4887.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2375, pruned_loss=0.05201, over 970970.42 frames.], batch size: 19, lr: 6.75e-04
2022-05-04 07:21:59,811 INFO [train.py:715] (4/8) Epoch 2, batch 18550, loss[loss=0.1928, simple_loss=0.2583, pruned_loss=0.06363, over 4805.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2379, pruned_loss=0.05246, over 971877.27 frames.], batch size: 21, lr: 6.75e-04
2022-05-04 07:22:41,510 INFO [train.py:715] (4/8) Epoch 2, batch 18600, loss[loss=0.1883, simple_loss=0.2639, pruned_loss=0.05636, over 4781.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2376, pruned_loss=0.05231, over 971948.94 frames.], batch size: 14, lr: 6.75e-04
2022-05-04 07:23:21,829 INFO [train.py:715] (4/8) Epoch 2, batch 18650, loss[loss=0.1779, simple_loss=0.247, pruned_loss=0.05442, over 4904.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2378, pruned_loss=0.05241, over 971998.56 frames.], batch size: 19, lr: 6.75e-04
2022-05-04 07:24:03,483 INFO [train.py:715] (4/8) Epoch 2, batch 18700, loss[loss=0.1877, simple_loss=0.2579, pruned_loss=0.05881, over 4803.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2389, pruned_loss=0.05284, over 972279.86 frames.], batch size: 21, lr: 6.75e-04
2022-05-04 07:24:45,169 INFO [train.py:715] (4/8) Epoch 2, batch 18750, loss[loss=0.1598, simple_loss=0.2315, pruned_loss=0.04404, over 4778.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2385, pruned_loss=0.05269, over 971901.77 frames.], batch size: 18, lr: 6.74e-04
2022-05-04 07:25:25,717 INFO [train.py:715] (4/8) Epoch 2, batch 18800, loss[loss=0.1908, simple_loss=0.2413, pruned_loss=0.07014, over 4841.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2379, pruned_loss=0.05228, over 972366.88 frames.], batch size: 30, lr: 6.74e-04
2022-05-04 07:26:06,668 INFO [train.py:715] (4/8) Epoch 2, batch 18850, loss[loss=0.1701, simple_loss=0.243, pruned_loss=0.0486, over 4780.00 frames.], tot_loss[loss=0.1713, simple_loss=0.238, pruned_loss=0.05233, over 972378.78 frames.], batch size: 14, lr: 6.74e-04
2022-05-04 07:26:48,079 INFO [train.py:715] (4/8) Epoch 2, batch 18900, loss[loss=0.1529, simple_loss=0.2163, pruned_loss=0.04476, over 4842.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2378, pruned_loss=0.05197, over 972557.28 frames.], batch size: 13, lr: 6.74e-04
2022-05-04 07:27:29,071 INFO [train.py:715] (4/8) Epoch 2, batch 18950, loss[loss=0.1522, simple_loss=0.2137, pruned_loss=0.04534, over 4841.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2369, pruned_loss=0.05139, over 973441.68 frames.], batch size: 32, lr: 6.74e-04
2022-05-04 07:28:09,484 INFO [train.py:715] (4/8) Epoch 2, batch 19000, loss[loss=0.1656, simple_loss=0.2278, pruned_loss=0.0517, over 4776.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2371, pruned_loss=0.05158, over 972782.61 frames.], batch size: 14, lr: 6.73e-04
2022-05-04 07:28:50,996 INFO [train.py:715] (4/8) Epoch 2, batch 19050, loss[loss=0.1588, simple_loss=0.2353, pruned_loss=0.04122, over 4959.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2371, pruned_loss=0.05165, over 971367.86 frames.], batch size: 21, lr: 6.73e-04
2022-05-04 07:29:32,578 INFO [train.py:715] (4/8) Epoch 2, batch 19100, loss[loss=0.1681, simple_loss=0.2349, pruned_loss=0.05064, over 4965.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2368, pruned_loss=0.05154, over 971979.50 frames.], batch size: 35, lr: 6.73e-04
2022-05-04 07:30:13,195 INFO [train.py:715] (4/8) Epoch 2, batch 19150, loss[loss=0.1669, simple_loss=0.234, pruned_loss=0.04991, over 4991.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2373, pruned_loss=0.05164, over 972488.08 frames.], batch size: 20, lr: 6.73e-04
2022-05-04 07:30:53,904 INFO [train.py:715] (4/8) Epoch 2, batch 19200, loss[loss=0.1573, simple_loss=0.2308, pruned_loss=0.04193, over 4950.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2383, pruned_loss=0.05203, over 972376.87 frames.], batch size: 15, lr: 6.73e-04
2022-05-04 07:31:35,012 INFO [train.py:715] (4/8) Epoch 2, batch 19250, loss[loss=0.2075, simple_loss=0.2769, pruned_loss=0.06903, over 4949.00 frames.], tot_loss[loss=0.1711, simple_loss=0.2383, pruned_loss=0.05198, over 973037.81 frames.], batch size: 21, lr: 6.72e-04
2022-05-04 07:32:15,454 INFO [train.py:715] (4/8) Epoch 2, batch 19300, loss[loss=0.1834, simple_loss=0.2523, pruned_loss=0.05725, over 4751.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2385, pruned_loss=0.05206, over 973550.56 frames.], batch size: 19, lr: 6.72e-04
2022-05-04 07:32:55,609 INFO [train.py:715] (4/8) Epoch 2, batch 19350, loss[loss=0.1486, simple_loss=0.2186, pruned_loss=0.03928, over 4862.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2383, pruned_loss=0.05203, over 973497.90 frames.], batch size: 13, lr: 6.72e-04
2022-05-04 07:33:36,557 INFO [train.py:715] (4/8) Epoch 2, batch 19400, loss[loss=0.1829, simple_loss=0.234, pruned_loss=0.06591, over 4836.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2372, pruned_loss=0.05127, over 972404.40 frames.], batch size: 12, lr: 6.72e-04
2022-05-04 07:34:18,478 INFO [train.py:715] (4/8) Epoch 2, batch 19450, loss[loss=0.1615, simple_loss=0.2402, pruned_loss=0.04143, over 4847.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2369, pruned_loss=0.05125, over 972561.12 frames.], batch size: 20, lr: 6.72e-04
2022-05-04 07:34:58,696 INFO [train.py:715] (4/8) Epoch 2, batch 19500, loss[loss=0.1682, simple_loss=0.2404, pruned_loss=0.04801, over 4934.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2375, pruned_loss=0.05175, over 972295.67 frames.], batch size: 23, lr: 6.72e-04
2022-05-04 07:35:38,981 INFO [train.py:715] (4/8) Epoch 2, batch 19550, loss[loss=0.1243, simple_loss=0.2033, pruned_loss=0.02268, over 4935.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2371, pruned_loss=0.05153, over 972011.63 frames.], batch size: 29, lr: 6.71e-04
2022-05-04 07:36:20,456 INFO [train.py:715] (4/8) Epoch 2, batch 19600, loss[loss=0.1562, simple_loss=0.2212, pruned_loss=0.04565, over 4922.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2368, pruned_loss=0.05113, over 972372.71 frames.], batch size: 29, lr: 6.71e-04
2022-05-04 07:37:01,111 INFO [train.py:715] (4/8) Epoch 2, batch 19650, loss[loss=0.128, simple_loss=0.2032, pruned_loss=0.02639, over 4815.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2361, pruned_loss=0.05057, over 972246.95 frames.], batch size: 13, lr: 6.71e-04
2022-05-04 07:37:40,950 INFO [train.py:715] (4/8) Epoch 2, batch 19700, loss[loss=0.153, simple_loss=0.2135, pruned_loss=0.04621, over 4855.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2355, pruned_loss=0.05039, over 971909.52 frames.], batch size: 13, lr: 6.71e-04
2022-05-04 07:38:21,855 INFO [train.py:715] (4/8) Epoch 2, batch 19750, loss[loss=0.1751, simple_loss=0.2484, pruned_loss=0.05089, over 4872.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2369, pruned_loss=0.05094, over 971783.53 frames.], batch size: 22, lr: 6.71e-04
2022-05-04 07:39:02,976 INFO [train.py:715] (4/8) Epoch 2, batch 19800, loss[loss=0.1771, simple_loss=0.2396, pruned_loss=0.05729, over 4899.00 frames.], tot_loss[loss=0.17, simple_loss=0.2372, pruned_loss=0.05144, over 971292.01 frames.], batch size: 17, lr: 6.70e-04
2022-05-04 07:39:42,767 INFO [train.py:715] (4/8) Epoch 2, batch 19850, loss[loss=0.151, simple_loss=0.229, pruned_loss=0.03651, over 4840.00 frames.], tot_loss[loss=0.169, simple_loss=0.2361, pruned_loss=0.05092, over 971306.30 frames.], batch size: 20, lr: 6.70e-04
2022-05-04 07:40:23,482 INFO [train.py:715] (4/8) Epoch 2, batch 19900, loss[loss=0.2202, simple_loss=0.2921, pruned_loss=0.07412, over 4929.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2366, pruned_loss=0.0511, over 971058.80 frames.], batch size: 18, lr: 6.70e-04
2022-05-04 07:41:04,460 INFO [train.py:715] (4/8) Epoch 2, batch 19950, loss[loss=0.1615, simple_loss=0.232, pruned_loss=0.04546, over 4769.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2367, pruned_loss=0.05131, over 972657.01 frames.], batch size: 18, lr: 6.70e-04
2022-05-04 07:41:44,809 INFO [train.py:715] (4/8) Epoch 2, batch 20000, loss[loss=0.1777, simple_loss=0.2479, pruned_loss=0.05375, over 4850.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2364, pruned_loss=0.05113, over 973131.33 frames.], batch size: 30, lr: 6.70e-04
2022-05-04 07:42:25,546 INFO [train.py:715] (4/8) Epoch 2, batch 20050, loss[loss=0.1774, simple_loss=0.2424, pruned_loss=0.05625, over 4855.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2363, pruned_loss=0.05125, over 973508.64 frames.], batch size: 32, lr: 6.69e-04
2022-05-04 07:43:06,874 INFO [train.py:715] (4/8) Epoch 2, batch 20100, loss[loss=0.1896, simple_loss=0.2624, pruned_loss=0.05839, over 4773.00 frames.], tot_loss[loss=0.1708, simple_loss=0.2376, pruned_loss=0.05202, over 973163.42 frames.], batch size: 14, lr: 6.69e-04
2022-05-04 07:43:48,580 INFO [train.py:715] (4/8) Epoch 2, batch 20150, loss[loss=0.1359, simple_loss=0.2089, pruned_loss=0.03149, over 4798.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2377, pruned_loss=0.05176, over 972309.37 frames.], batch size: 21, lr: 6.69e-04
2022-05-04 07:44:28,873 INFO [train.py:715] (4/8) Epoch 2, batch 20200, loss[loss=0.1188, simple_loss=0.1874, pruned_loss=0.02507, over 4692.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2369, pruned_loss=0.05171, over 971682.83 frames.], batch size: 15, lr: 6.69e-04
2022-05-04 07:45:10,315 INFO [train.py:715] (4/8) Epoch 2, batch 20250, loss[loss=0.1849, simple_loss=0.2454, pruned_loss=0.06221, over 4821.00 frames.], tot_loss[loss=0.171, simple_loss=0.2378, pruned_loss=0.05213, over 972489.63 frames.], batch size: 25, lr: 6.69e-04
2022-05-04 07:45:52,272 INFO [train.py:715] (4/8) Epoch 2, batch 20300, loss[loss=0.1515, simple_loss=0.2177, pruned_loss=0.04263, over 4788.00 frames.], tot_loss[loss=0.1715, simple_loss=0.2381, pruned_loss=0.05245, over 971370.88 frames.], batch size: 18, lr: 6.69e-04
2022-05-04 07:46:33,088 INFO [train.py:715] (4/8) Epoch 2, batch 20350, loss[loss=0.1624, simple_loss=0.2366, pruned_loss=0.04405, over 4741.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2365, pruned_loss=0.05149, over 971161.47 frames.], batch size: 16, lr: 6.68e-04
2022-05-04 07:47:14,061 INFO [train.py:715] (4/8) Epoch 2, batch 20400, loss[loss=0.1775, simple_loss=0.2405, pruned_loss=0.0572, over 4785.00 frames.], tot_loss[loss=0.169, simple_loss=0.2358, pruned_loss=0.05112, over 970557.37 frames.], batch size: 17, lr: 6.68e-04
2022-05-04 07:47:56,148 INFO [train.py:715] (4/8) Epoch 2, batch 20450, loss[loss=0.1646, simple_loss=0.2416, pruned_loss=0.04383, over 4760.00 frames.], tot_loss[loss=0.171, simple_loss=0.2376, pruned_loss=0.05218, over 971221.87 frames.], batch size: 17, lr: 6.68e-04
2022-05-04 07:48:37,714 INFO [train.py:715] (4/8) Epoch 2, batch 20500, loss[loss=0.2017, simple_loss=0.2494, pruned_loss=0.07701, over 4864.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2375, pruned_loss=0.05188, over 971622.65 frames.], batch size: 20, lr: 6.68e-04
2022-05-04 07:49:18,505 INFO [train.py:715] (4/8) Epoch 2, batch 20550, loss[loss=0.182, simple_loss=0.2476, pruned_loss=0.05815, over 4864.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2377, pruned_loss=0.05179, over 973100.27 frames.], batch size: 20, lr: 6.68e-04
2022-05-04 07:49:59,711 INFO [train.py:715] (4/8) Epoch 2, batch 20600, loss[loss=0.1543, simple_loss=0.2258, pruned_loss=0.04141, over 4983.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2375, pruned_loss=0.05172, over 973547.05 frames.], batch size: 15, lr: 6.67e-04
2022-05-04 07:50:41,268 INFO [train.py:715] (4/8) Epoch 2, batch 20650, loss[loss=0.181, simple_loss=0.2573, pruned_loss=0.05238, over 4774.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2376, pruned_loss=0.05177, over 973480.34 frames.], batch size: 19, lr: 6.67e-04
2022-05-04 07:51:22,505 INFO [train.py:715] (4/8) Epoch 2, batch 20700, loss[loss=0.1508, simple_loss=0.2213, pruned_loss=0.04014, over 4828.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2381, pruned_loss=0.05185, over 974245.72 frames.], batch size: 25, lr: 6.67e-04
2022-05-04 07:52:03,036 INFO [train.py:715] (4/8) Epoch 2, batch 20750, loss[loss=0.1944, simple_loss=0.2596, pruned_loss=0.06457, over 4773.00 frames.], tot_loss[loss=0.1719, simple_loss=0.2387, pruned_loss=0.0525, over 973464.02 frames.], batch size: 18, lr: 6.67e-04
2022-05-04 07:52:44,281 INFO [train.py:715] (4/8) Epoch 2, batch 20800, loss[loss=0.2153, simple_loss=0.2805, pruned_loss=0.07501, over 4842.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2387, pruned_loss=0.05278, over 972759.57 frames.], batch size: 13, lr: 6.67e-04
2022-05-04 07:53:25,483 INFO [train.py:715] (4/8) Epoch 2, batch 20850, loss[loss=0.1838, simple_loss=0.2545, pruned_loss=0.05655, over 4773.00 frames.], tot_loss[loss=0.1711, simple_loss=0.238, pruned_loss=0.05211, over 972264.09 frames.], batch size: 17, lr: 6.66e-04
2022-05-04 07:54:06,157 INFO [train.py:715] (4/8) Epoch 2, batch 20900, loss[loss=0.1932, simple_loss=0.2536, pruned_loss=0.06635, over 4909.00 frames.], tot_loss[loss=0.1723, simple_loss=0.2388, pruned_loss=0.05293, over 971911.42 frames.], batch size: 17, lr: 6.66e-04
2022-05-04 07:54:47,191 INFO [train.py:715] (4/8) Epoch 2, batch 20950, loss[loss=0.2002, simple_loss=0.2579, pruned_loss=0.07125, over 4918.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2384, pruned_loss=0.05243, over 972715.70 frames.], batch size: 17, lr: 6.66e-04
2022-05-04 07:55:28,391 INFO [train.py:715] (4/8) Epoch 2, batch 21000, loss[loss=0.15, simple_loss=0.2248, pruned_loss=0.03759, over 4805.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2388, pruned_loss=0.05274, over 972422.84 frames.], batch size: 26, lr: 6.66e-04
2022-05-04 07:55:28,392 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 07:55:39,043 INFO [train.py:742] (4/8) Epoch 2, validation: loss=0.1174, simple_loss=0.2036, pruned_loss=0.01562, over 914524.00 frames.
2022-05-04 07:56:20,519 INFO [train.py:715] (4/8) Epoch 2, batch 21050, loss[loss=0.181, simple_loss=0.248, pruned_loss=0.05702, over 4864.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2388, pruned_loss=0.05266, over 972783.18 frames.], batch size: 20, lr: 6.66e-04
2022-05-04 07:57:00,991 INFO [train.py:715] (4/8) Epoch 2, batch 21100, loss[loss=0.1294, simple_loss=0.1998, pruned_loss=0.02947, over 4979.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2377, pruned_loss=0.05164, over 973196.66 frames.], batch size: 15, lr: 6.66e-04
2022-05-04 07:57:41,494 INFO [train.py:715] (4/8) Epoch 2, batch 21150, loss[loss=0.1793, simple_loss=0.2453, pruned_loss=0.05666, over 4841.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2372, pruned_loss=0.05114, over 973046.02 frames.], batch size: 15, lr: 6.65e-04
2022-05-04 07:58:22,037 INFO [train.py:715] (4/8) Epoch 2, batch 21200, loss[loss=0.165, simple_loss=0.2393, pruned_loss=0.04536, over 4949.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2369, pruned_loss=0.05141, over 973007.53 frames.], batch size: 21, lr: 6.65e-04
2022-05-04 07:59:02,135 INFO [train.py:715] (4/8) Epoch 2, batch 21250, loss[loss=0.141, simple_loss=0.2137, pruned_loss=0.03409, over 4848.00 frames.], tot_loss[loss=0.1702, simple_loss=0.237, pruned_loss=0.05168, over 973394.08 frames.], batch size: 30, lr: 6.65e-04
2022-05-04 07:59:42,846 INFO [train.py:715] (4/8) Epoch 2, batch 21300, loss[loss=0.1505, simple_loss=0.2317, pruned_loss=0.03465, over 4850.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2374, pruned_loss=0.05183, over 972908.84 frames.], batch size: 15, lr: 6.65e-04
2022-05-04 08:00:23,557 INFO [train.py:715] (4/8) Epoch 2, batch 21350, loss[loss=0.1991, simple_loss=0.2571, pruned_loss=0.07059, over 4933.00 frames.], tot_loss[loss=0.1713, simple_loss=0.238, pruned_loss=0.05227, over 973160.51 frames.], batch size: 35, lr: 6.65e-04
2022-05-04 08:01:04,864 INFO [train.py:715] (4/8) Epoch 2, batch 21400, loss[loss=0.1442, simple_loss=0.2115, pruned_loss=0.03842, over 4865.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2373, pruned_loss=0.05203, over 972915.22 frames.], batch size: 20, lr: 6.64e-04
2022-05-04 08:01:45,136 INFO [train.py:715] (4/8) Epoch 2, batch 21450, loss[loss=0.1538, simple_loss=0.2204, pruned_loss=0.04362, over 4828.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2379, pruned_loss=0.05219, over 973273.04 frames.], batch size: 30, lr: 6.64e-04
2022-05-04 08:02:26,068 INFO [train.py:715] (4/8) Epoch 2, batch 21500, loss[loss=0.1502, simple_loss=0.2129, pruned_loss=0.0437, over 4798.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2374, pruned_loss=0.05188, over 973652.74 frames.], batch size: 14, lr: 6.64e-04
2022-05-04 08:03:07,355 INFO [train.py:715] (4/8) Epoch 2, batch 21550, loss[loss=0.1617, simple_loss=0.2286, pruned_loss=0.04742, over 4876.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2378, pruned_loss=0.0518, over 974219.59 frames.], batch size: 16, lr: 6.64e-04
2022-05-04 08:03:47,337 INFO [train.py:715] (4/8) Epoch 2, batch 21600, loss[loss=0.1409, simple_loss=0.221, pruned_loss=0.03039, over 4968.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2379, pruned_loss=0.05225, over 972563.84 frames.], batch size: 24, lr: 6.64e-04
2022-05-04 08:04:28,568 INFO [train.py:715] (4/8) Epoch 2, batch 21650, loss[loss=0.2022, simple_loss=0.2504, pruned_loss=0.07699, over 4985.00 frames.], tot_loss[loss=0.171, simple_loss=0.2375, pruned_loss=0.05223, over 972603.05 frames.], batch size: 15, lr: 6.64e-04
2022-05-04 08:05:10,113 INFO [train.py:715] (4/8) Epoch 2, batch 21700, loss[loss=0.1714, simple_loss=0.2458, pruned_loss=0.04848, over 4898.00 frames.], tot_loss[loss=0.1721, simple_loss=0.2386, pruned_loss=0.05279, over 972872.94 frames.], batch size: 19, lr: 6.63e-04
2022-05-04 08:05:50,687 INFO [train.py:715] (4/8) Epoch 2, batch 21750, loss[loss=0.1461, simple_loss=0.2183, pruned_loss=0.03691, over 4798.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2368, pruned_loss=0.05155, over 973404.38 frames.], batch size: 21, lr: 6.63e-04
2022-05-04 08:06:31,761 INFO [train.py:715] (4/8) Epoch 2, batch 21800, loss[loss=0.1771, simple_loss=0.2414, pruned_loss=0.05642, over 4961.00 frames.], tot_loss[loss=0.1703, simple_loss=0.237, pruned_loss=0.05181, over 972679.73 frames.], batch size: 35, lr: 6.63e-04
2022-05-04 08:07:12,177 INFO [train.py:715] (4/8) Epoch 2, batch 21850, loss[loss=0.1559, simple_loss=0.2215, pruned_loss=0.04518, over 4835.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2367, pruned_loss=0.05176, over 972091.07 frames.], batch size: 12, lr: 6.63e-04
2022-05-04 08:07:53,268 INFO [train.py:715] (4/8) Epoch 2, batch 21900, loss[loss=0.174, simple_loss=0.2334, pruned_loss=0.05726, over 4833.00 frames.], tot_loss[loss=0.169, simple_loss=0.236, pruned_loss=0.05103, over 971909.17 frames.], batch size: 15, lr: 6.63e-04
2022-05-04 08:08:33,965 INFO [train.py:715] (4/8) Epoch 2, batch 21950, loss[loss=0.1843, simple_loss=0.2526, pruned_loss=0.05801, over 4815.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2353, pruned_loss=0.05015, over 971530.46 frames.], batch size: 26, lr: 6.62e-04
2022-05-04 08:09:15,714 INFO [train.py:715] (4/8) Epoch 2, batch 22000, loss[loss=0.1529, simple_loss=0.2317, pruned_loss=0.03702, over 4816.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2353, pruned_loss=0.0498, over 971893.32 frames.], batch size: 25, lr: 6.62e-04
2022-05-04 08:09:57,814 INFO [train.py:715] (4/8) Epoch 2, batch 22050, loss[loss=0.1551, simple_loss=0.2303, pruned_loss=0.03994, over 4926.00 frames.], tot_loss[loss=0.168, simple_loss=0.2356, pruned_loss=0.05014, over 972284.29 frames.], batch size: 19, lr: 6.62e-04
2022-05-04 08:10:38,624 INFO [train.py:715] (4/8) Epoch 2, batch 22100, loss[loss=0.1772, simple_loss=0.2295, pruned_loss=0.0625, over 4829.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2366, pruned_loss=0.05086, over 972042.45 frames.], batch size: 30, lr: 6.62e-04
2022-05-04 08:11:20,104 INFO [train.py:715] (4/8) Epoch 2, batch 22150, loss[loss=0.1692, simple_loss=0.2343, pruned_loss=0.05211, over 4771.00 frames.], tot_loss[loss=0.1695, simple_loss=0.237, pruned_loss=0.05104, over 971924.80 frames.], batch size: 17, lr: 6.62e-04
2022-05-04 08:12:01,865 INFO [train.py:715] (4/8) Epoch 2, batch 22200, loss[loss=0.1814, simple_loss=0.2676, pruned_loss=0.04764, over 4909.00 frames.], tot_loss[loss=0.1699, simple_loss=0.237, pruned_loss=0.05141, over 973702.63 frames.], batch size: 18, lr: 6.62e-04
2022-05-04 08:12:43,326 INFO [train.py:715] (4/8) Epoch 2, batch 22250, loss[loss=0.1597, simple_loss=0.2391, pruned_loss=0.04018, over 4958.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2367, pruned_loss=0.05153, over 972571.07 frames.], batch size: 29, lr: 6.61e-04
2022-05-04 08:13:24,127 INFO [train.py:715] (4/8) Epoch 2, batch 22300, loss[loss=0.1968, simple_loss=0.2609, pruned_loss=0.06633, over 4838.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2372, pruned_loss=0.05163, over 972095.31 frames.], batch size: 32, lr: 6.61e-04
2022-05-04 08:14:05,210 INFO [train.py:715] (4/8) Epoch 2, batch 22350, loss[loss=0.1805, simple_loss=0.2482, pruned_loss=0.05639, over 4965.00 frames.], tot_loss[loss=0.171, simple_loss=0.2376, pruned_loss=0.05218, over 972454.11 frames.], batch size: 21, lr: 6.61e-04
2022-05-04 08:14:46,094 INFO [train.py:715] (4/8) Epoch 2, batch 22400, loss[loss=0.1814, simple_loss=0.2462, pruned_loss=0.05828, over 4982.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2364, pruned_loss=0.0514, over 972053.98 frames.], batch size: 15, lr: 6.61e-04
2022-05-04 08:15:26,446 INFO [train.py:715] (4/8) Epoch 2, batch 22450, loss[loss=0.1692, simple_loss=0.2472, pruned_loss=0.04559, over 4784.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2363, pruned_loss=0.05142, over 972719.47 frames.], batch size: 14, lr: 6.61e-04
2022-05-04 08:16:07,667 INFO [train.py:715] (4/8) Epoch 2, batch 22500, loss[loss=0.1788, simple_loss=0.2362, pruned_loss=0.06072, over 4971.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2366, pruned_loss=0.05179, over 972628.05 frames.], batch size: 14, lr: 6.61e-04
2022-05-04 08:16:48,520 INFO [train.py:715] (4/8) Epoch 2, batch 22550, loss[loss=0.1953, simple_loss=0.2551, pruned_loss=0.06775, over 4914.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2368, pruned_loss=0.05177, over 972551.31 frames.], batch size: 18, lr: 6.60e-04
2022-05-04 08:17:29,226 INFO [train.py:715] (4/8) Epoch 2, batch 22600, loss[loss=0.1638, simple_loss=0.2442, pruned_loss=0.04169, over 4798.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2368, pruned_loss=0.05148, over 972145.36 frames.], batch size: 24, lr: 6.60e-04
2022-05-04 08:18:10,001 INFO [train.py:715] (4/8) Epoch 2, batch 22650, loss[loss=0.1634, simple_loss=0.2249, pruned_loss=0.05092, over 4905.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2375, pruned_loss=0.05166, over 972495.93 frames.], batch size: 19, lr: 6.60e-04
2022-05-04 08:18:50,673 INFO [train.py:715] (4/8) Epoch 2, batch 22700, loss[loss=0.1818, simple_loss=0.2581, pruned_loss=0.0527, over 4885.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2384, pruned_loss=0.05222, over 972069.66 frames.], batch size: 16, lr: 6.60e-04
2022-05-04 08:19:31,391 INFO [train.py:715] (4/8) Epoch 2, batch 22750, loss[loss=0.1683, simple_loss=0.227, pruned_loss=0.05485, over 4855.00 frames.], tot_loss[loss=0.1722, simple_loss=0.239, pruned_loss=0.05274, over 972133.64 frames.], batch size: 32, lr: 6.60e-04
2022-05-04 08:20:12,250 INFO [train.py:715] (4/8) Epoch 2, batch 22800, loss[loss=0.161, simple_loss=0.2364, pruned_loss=0.04282, over 4704.00 frames.], tot_loss[loss=0.172, simple_loss=0.2387, pruned_loss=0.05263, over 971896.87 frames.], batch size: 15, lr: 6.59e-04
2022-05-04 08:20:53,300 INFO [train.py:715] (4/8) Epoch 2, batch 22850, loss[loss=0.1566, simple_loss=0.2278, pruned_loss=0.04265, over 4874.00 frames.], tot_loss[loss=0.1722, simple_loss=0.239, pruned_loss=0.05273, over 971635.52 frames.], batch size: 16, lr: 6.59e-04
2022-05-04 08:21:34,654 INFO [train.py:715] (4/8) Epoch 2, batch 22900, loss[loss=0.1299, simple_loss=0.2037, pruned_loss=0.02802, over 4827.00 frames.], tot_loss[loss=0.1707, simple_loss=0.2376, pruned_loss=0.05185, over 971056.56 frames.], batch size: 13, lr: 6.59e-04
2022-05-04 08:22:15,453 INFO [train.py:715] (4/8) Epoch 2, batch 22950, loss[loss=0.1322, simple_loss=0.1971, pruned_loss=0.03369, over 4835.00 frames.], tot_loss[loss=0.171, simple_loss=0.2375, pruned_loss=0.05225, over 971398.95 frames.], batch size: 12, lr: 6.59e-04
2022-05-04 08:22:56,051 INFO [train.py:715] (4/8) Epoch 2, batch 23000, loss[loss=0.1652, simple_loss=0.2462, pruned_loss=0.04214, over 4806.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2382, pruned_loss=0.05252, over 971501.11 frames.], batch size: 21, lr: 6.59e-04
2022-05-04 08:23:37,067 INFO [train.py:715] (4/8) Epoch 2, batch 23050, loss[loss=0.1589, simple_loss=0.2357, pruned_loss=0.04104, over 4815.00 frames.], tot_loss[loss=0.1712, simple_loss=0.2378, pruned_loss=0.05228, over 972235.16 frames.], batch size: 26, lr: 6.59e-04
2022-05-04 08:24:17,898 INFO [train.py:715] (4/8) Epoch 2, batch 23100, loss[loss=0.1559, simple_loss=0.2198, pruned_loss=0.04596, over 4900.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2368, pruned_loss=0.05179, over 971871.51 frames.], batch size: 32, lr: 6.58e-04
2022-05-04 08:24:58,404 INFO [train.py:715] (4/8) Epoch 2, batch 23150, loss[loss=0.1853, simple_loss=0.2632, pruned_loss=0.05372, over 4694.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2367, pruned_loss=0.05203, over 972006.39 frames.], batch size: 15, lr: 6.58e-04
2022-05-04 08:25:39,721 INFO [train.py:715] (4/8) Epoch 2, batch 23200, loss[loss=0.1393, simple_loss=0.213, pruned_loss=0.0328, over 4897.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2364, pruned_loss=0.05153, over 971950.55 frames.], batch size: 17, lr: 6.58e-04
2022-05-04 08:26:20,391 INFO [train.py:715] (4/8) Epoch 2, batch 23250, loss[loss=0.1479, simple_loss=0.214, pruned_loss=0.04094, over 4766.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2362, pruned_loss=0.05149, over 972416.80 frames.], batch size: 14, lr: 6.58e-04
2022-05-04 08:27:00,741 INFO [train.py:715] (4/8) Epoch 2, batch 23300, loss[loss=0.1597, simple_loss=0.2252, pruned_loss=0.04707, over 4766.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2363, pruned_loss=0.0512, over 973002.29 frames.], batch size: 19, lr: 6.58e-04
2022-05-04 08:27:41,441 INFO [train.py:715] (4/8) Epoch 2, batch 23350, loss[loss=0.1524, simple_loss=0.2224, pruned_loss=0.04119, over 4978.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2367, pruned_loss=0.05122, over 973050.08 frames.], batch size: 28, lr: 6.57e-04
2022-05-04 08:28:22,386 INFO [train.py:715] (4/8) Epoch 2, batch 23400, loss[loss=0.1507, simple_loss=0.2088, pruned_loss=0.04628, over 4987.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2369, pruned_loss=0.05182, over 973345.34 frames.], batch size: 14, lr: 6.57e-04
2022-05-04 08:29:03,322 INFO [train.py:715] (4/8) Epoch 2, batch 23450, loss[loss=0.1573, simple_loss=0.2355, pruned_loss=0.03952, over 4809.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2362, pruned_loss=0.05146, over 973608.01 frames.], batch size: 14, lr: 6.57e-04
2022-05-04 08:29:43,611 INFO [train.py:715] (4/8) Epoch 2, batch 23500, loss[loss=0.2061, simple_loss=0.2806, pruned_loss=0.0658, over 4808.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2368, pruned_loss=0.05126, over 973687.22 frames.], batch size: 13, lr: 6.57e-04
2022-05-04 08:30:24,807 INFO [train.py:715] (4/8) Epoch 2, batch 23550, loss[loss=0.1778, simple_loss=0.249, pruned_loss=0.05328, over 4921.00 frames.], tot_loss[loss=0.17, simple_loss=0.2369, pruned_loss=0.05158, over 973169.97 frames.], batch size: 18, lr: 6.57e-04
2022-05-04 08:31:05,697 INFO [train.py:715] (4/8) Epoch 2, batch 23600, loss[loss=0.1665, simple_loss=0.2338, pruned_loss=0.04957, over 4978.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2359, pruned_loss=0.05116, over 973458.98 frames.], batch size: 31, lr: 6.57e-04
2022-05-04 08:31:45,432 INFO [train.py:715] (4/8) Epoch 2, batch 23650, loss[loss=0.1728, simple_loss=0.2426, pruned_loss=0.05154, over 4868.00 frames.], tot_loss[loss=0.1697, simple_loss=0.236, pruned_loss=0.05166, over 972078.75 frames.], batch size: 20, lr: 6.56e-04
2022-05-04 08:32:27,501 INFO [train.py:715] (4/8) Epoch 2, batch 23700, loss[loss=0.1643, simple_loss=0.2306, pruned_loss=0.04903, over 4979.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2363, pruned_loss=0.05145, over 971792.95 frames.], batch size: 14, lr: 6.56e-04
2022-05-04 08:33:07,927 INFO [train.py:715] (4/8) Epoch 2, batch 23750, loss[loss=0.1367, simple_loss=0.2033, pruned_loss=0.03503, over 4980.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2356, pruned_loss=0.0506, over 971594.84 frames.], batch size: 14, lr: 6.56e-04
2022-05-04 08:33:48,784 INFO [train.py:715] (4/8) Epoch 2, batch 23800, loss[loss=0.1445, simple_loss=0.21, pruned_loss=0.03948, over 4962.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2353, pruned_loss=0.05055, over 971635.92 frames.], batch size: 35, lr: 6.56e-04
2022-05-04 08:34:29,259 INFO [train.py:715] (4/8) Epoch 2, batch 23850, loss[loss=0.1422, simple_loss=0.2017, pruned_loss=0.04138, over 4840.00 frames.], tot_loss[loss=0.168, simple_loss=0.2355, pruned_loss=0.0503, over 971173.73 frames.], batch size: 15, lr: 6.56e-04
2022-05-04 08:35:10,695 INFO [train.py:715] (4/8) Epoch 2, batch 23900, loss[loss=0.1478, simple_loss=0.2226, pruned_loss=0.03653, over 4807.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2361, pruned_loss=0.05057, over 971404.87 frames.], batch size: 25, lr: 6.56e-04
2022-05-04 08:35:51,709 INFO [train.py:715] (4/8) Epoch 2, batch 23950, loss[loss=0.1449, simple_loss=0.2185, pruned_loss=0.03571, over 4983.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2363, pruned_loss=0.05048, over 971898.33 frames.], batch size: 25, lr: 6.55e-04
2022-05-04 08:36:31,643 INFO [train.py:715] (4/8) Epoch 2, batch 24000, loss[loss=0.1881, simple_loss=0.2662, pruned_loss=0.055, over 4872.00 frames.], tot_loss[loss=0.17, simple_loss=0.2376, pruned_loss=0.05123, over 972137.19 frames.], batch size: 16, lr: 6.55e-04
2022-05-04 08:36:31,643 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 08:36:40,332 INFO [train.py:742] (4/8) Epoch 2, validation: loss=0.1168, simple_loss=0.2032, pruned_loss=0.01518, over 914524.00 frames.
2022-05-04 08:37:20,456 INFO [train.py:715] (4/8) Epoch 2, batch 24050, loss[loss=0.1353, simple_loss=0.2099, pruned_loss=0.03031, over 4867.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2378, pruned_loss=0.0514, over 971122.05 frames.], batch size: 20, lr: 6.55e-04
2022-05-04 08:38:01,989 INFO [train.py:715] (4/8) Epoch 2, batch 24100, loss[loss=0.1405, simple_loss=0.2173, pruned_loss=0.03184, over 4776.00 frames.], tot_loss[loss=0.1705, simple_loss=0.2378, pruned_loss=0.05159, over 971053.21 frames.], batch size: 17, lr: 6.55e-04
2022-05-04 08:38:42,989 INFO [train.py:715] (4/8) Epoch 2, batch 24150, loss[loss=0.2208, simple_loss=0.279, pruned_loss=0.08136, over 4946.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2385, pruned_loss=0.05202, over 972535.87 frames.], batch size: 21, lr: 6.55e-04
2022-05-04 08:39:24,307 INFO [train.py:715] (4/8) Epoch 2, batch 24200, loss[loss=0.2015, simple_loss=0.2599, pruned_loss=0.0715, over 4875.00 frames.], tot_loss[loss=0.1697, simple_loss=0.237, pruned_loss=0.05123, over 972949.56 frames.], batch size: 16, lr: 6.55e-04
2022-05-04 08:40:05,185 INFO [train.py:715] (4/8) Epoch 2, batch 24250, loss[loss=0.1601, simple_loss=0.2269, pruned_loss=0.0466, over 4926.00 frames.], tot_loss[loss=0.172, simple_loss=0.2387, pruned_loss=0.05265, over 972630.95 frames.], batch size: 23, lr: 6.54e-04
2022-05-04 08:40:46,088 INFO [train.py:715] (4/8) Epoch 2, batch 24300, loss[loss=0.1603, simple_loss=0.2307, pruned_loss=0.04493, over 4874.00 frames.], tot_loss[loss=0.171, simple_loss=0.238, pruned_loss=0.05204, over 972172.04 frames.], batch size: 16, lr: 6.54e-04
2022-05-04 08:41:26,658 INFO [train.py:715] (4/8) Epoch 2, batch 24350, loss[loss=0.1582, simple_loss=0.2351, pruned_loss=0.04063, over 4820.00 frames.], tot_loss[loss=0.1709, simple_loss=0.238, pruned_loss=0.05192, over 971867.22 frames.], batch size: 25, lr: 6.54e-04
2022-05-04 08:42:06,524 INFO [train.py:715] (4/8) Epoch 2, batch 24400, loss[loss=0.1829, simple_loss=0.2505, pruned_loss=0.05763, over 4818.00 frames.], tot_loss[loss=0.1717, simple_loss=0.2389, pruned_loss=0.05224, over 972917.14 frames.], batch size: 15, lr: 6.54e-04
2022-05-04 08:42:47,544 INFO [train.py:715] (4/8) Epoch 2, batch 24450, loss[loss=0.1499, simple_loss=0.2252, pruned_loss=0.03725, over 4939.00 frames.], tot_loss[loss=0.1714, simple_loss=0.2385, pruned_loss=0.05219, over 972145.35 frames.], batch size: 29, lr: 6.54e-04
2022-05-04 08:43:27,487 INFO [train.py:715] (4/8) Epoch 2, batch 24500, loss[loss=0.1843, simple_loss=0.2511, pruned_loss=0.05868, over 4977.00 frames.], tot_loss[loss=0.1699, simple_loss=0.237, pruned_loss=0.05143, over 972375.67 frames.], batch size: 26, lr: 6.53e-04
2022-05-04 08:44:07,366 INFO [train.py:715] (4/8) Epoch 2, batch 24550, loss[loss=0.2198, simple_loss=0.2794, pruned_loss=0.08012, over 4872.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2375, pruned_loss=0.05166, over 973453.51 frames.], batch size: 39, lr: 6.53e-04
2022-05-04 08:44:46,873 INFO [train.py:715] (4/8) Epoch 2, batch 24600, loss[loss=0.1653, simple_loss=0.2393, pruned_loss=0.04565, over 4836.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2369, pruned_loss=0.05131, over 973490.45 frames.], batch size: 15, lr: 6.53e-04
2022-05-04 08:45:27,055 INFO [train.py:715] (4/8) Epoch 2, batch 24650, loss[loss=0.1618, simple_loss=0.227, pruned_loss=0.04831, over 4889.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2363, pruned_loss=0.05144, over 972988.45 frames.], batch size: 22, lr: 6.53e-04
2022-05-04 08:46:06,407 INFO [train.py:715] (4/8) Epoch 2, batch 24700, loss[loss=0.1614, simple_loss=0.2284, pruned_loss=0.04717, over 4949.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2361, pruned_loss=0.05113, over 972434.65 frames.], batch size: 21, lr: 6.53e-04
2022-05-04 08:46:45,150 INFO [train.py:715] (4/8) Epoch 2, batch 24750, loss[loss=0.1775, simple_loss=0.2455, pruned_loss=0.05474, over 4839.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2363, pruned_loss=0.05127, over 973059.33 frames.], batch size: 15, lr: 6.53e-04
2022-05-04 08:47:24,975 INFO [train.py:715] (4/8) Epoch 2, batch 24800, loss[loss=0.1387, simple_loss=0.215, pruned_loss=0.03123, over 4806.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2357, pruned_loss=0.05125, over 972602.91 frames.], batch size: 21, lr: 6.52e-04
2022-05-04 08:48:04,566 INFO [train.py:715] (4/8) Epoch 2, batch 24850, loss[loss=0.1389, simple_loss=0.2057, pruned_loss=0.0361, over 4774.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2351, pruned_loss=0.05091, over 972374.85 frames.], batch size: 18, lr: 6.52e-04
2022-05-04 08:48:43,454 INFO [train.py:715] (4/8) Epoch 2, batch 24900, loss[loss=0.1652, simple_loss=0.2395, pruned_loss=0.04547, over 4977.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2352, pruned_loss=0.05078, over 971893.32 frames.], batch size: 28, lr: 6.52e-04
2022-05-04 08:49:22,923 INFO [train.py:715] (4/8) Epoch 2, batch 24950, loss[loss=0.1995, simple_loss=0.2594, pruned_loss=0.06976, over 4827.00 frames.], tot_loss[loss=0.1681, simple_loss=0.235, pruned_loss=0.05061, over 971765.96 frames.], batch size: 30, lr: 6.52e-04
2022-05-04 08:50:02,456 INFO [train.py:715] (4/8) Epoch 2, batch 25000, loss[loss=0.1637, simple_loss=0.2295, pruned_loss=0.04897, over 4861.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2349, pruned_loss=0.05033, over 972778.29 frames.], batch size: 32, lr: 6.52e-04
2022-05-04 08:50:41,253 INFO [train.py:715] (4/8) Epoch 2, batch 25050, loss[loss=0.1794, simple_loss=0.2671, pruned_loss=0.0458, over 4811.00 frames.], tot_loss[loss=0.169, simple_loss=0.2359, pruned_loss=0.05102, over 972257.84 frames.], batch size: 25, lr: 6.52e-04
2022-05-04 08:51:19,781 INFO [train.py:715] (4/8) Epoch 2, batch 25100, loss[loss=0.1447, simple_loss=0.2225, pruned_loss=0.03346, over 4809.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2361, pruned_loss=0.05084, over 972622.80 frames.], batch size: 25, lr: 6.51e-04
2022-05-04 08:51:59,031 INFO [train.py:715] (4/8) Epoch 2, batch 25150, loss[loss=0.1692, simple_loss=0.2457, pruned_loss=0.04637, over 4897.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2362, pruned_loss=0.05127, over 972748.61 frames.], batch size: 17, lr: 6.51e-04
2022-05-04 08:52:37,844 INFO [train.py:715] (4/8) Epoch 2, batch 25200, loss[loss=0.1637, simple_loss=0.2271, pruned_loss=0.05013, over 4982.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2367, pruned_loss=0.05176, over 972716.63 frames.], batch size: 31, lr: 6.51e-04
2022-05-04 08:53:16,877 INFO [train.py:715] (4/8) Epoch 2, batch 25250, loss[loss=0.1912, simple_loss=0.2533, pruned_loss=0.06459, over 4911.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2368, pruned_loss=0.05184, over 973088.57 frames.], batch size: 39, lr: 6.51e-04
2022-05-04 08:53:55,851 INFO [train.py:715] (4/8) Epoch 2, batch 25300, loss[loss=0.1923, simple_loss=0.2542, pruned_loss=0.06519, over 4707.00 frames.], tot_loss[loss=0.1695, simple_loss=0.236, pruned_loss=0.05154, over 972435.63 frames.], batch size: 15, lr: 6.51e-04
2022-05-04 08:54:35,068 INFO [train.py:715] (4/8) Epoch 2, batch 25350, loss[loss=0.1525, simple_loss=0.2313, pruned_loss=0.03688, over 4933.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2362, pruned_loss=0.05156, over 971860.31 frames.], batch size: 29, lr: 6.51e-04
2022-05-04 08:55:14,142 INFO [train.py:715] (4/8) Epoch 2, batch 25400, loss[loss=0.1717, simple_loss=0.2432, pruned_loss=0.05016, over 4820.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2356, pruned_loss=0.05108, over 971167.00 frames.], batch size: 27, lr: 6.50e-04
2022-05-04 08:55:52,989 INFO [train.py:715] (4/8) Epoch 2, batch 25450, loss[loss=0.1579, simple_loss=0.2254, pruned_loss=0.0452, over 4781.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2356, pruned_loss=0.0513, over 970979.21 frames.], batch size: 18, lr: 6.50e-04
2022-05-04 08:56:32,018 INFO [train.py:715] (4/8) Epoch 2, batch 25500, loss[loss=0.1644, simple_loss=0.2364, pruned_loss=0.04614, over 4875.00 frames.], tot_loss[loss=0.17, simple_loss=0.2365, pruned_loss=0.05175, over 970966.18 frames.], batch size: 22, lr: 6.50e-04
2022-05-04 08:57:11,299 INFO [train.py:715] (4/8) Epoch 2, batch 25550, loss[loss=0.1473, simple_loss=0.2143, pruned_loss=0.04017, over 4926.00 frames.], tot_loss[loss=0.17, simple_loss=0.2366, pruned_loss=0.05169, over 971404.08 frames.], batch size: 18, lr: 6.50e-04
2022-05-04 08:57:50,307 INFO [train.py:715] (4/8) Epoch 2, batch 25600, loss[loss=0.1467, simple_loss=0.207, pruned_loss=0.04322, over 4826.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2361, pruned_loss=0.0515, over 971629.47 frames.], batch size: 25, lr: 6.50e-04
2022-05-04 08:58:29,640 INFO [train.py:715] (4/8) Epoch 2, batch 25650, loss[loss=0.1417, simple_loss=0.2087, pruned_loss=0.03731, over 4814.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2353, pruned_loss=0.0509, over 972511.20 frames.], batch size: 27, lr: 6.50e-04
2022-05-04 08:59:09,547 INFO [train.py:715] (4/8) Epoch 2, batch 25700, loss[loss=0.186, simple_loss=0.2491, pruned_loss=0.06143, over 4852.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2354, pruned_loss=0.05101, over 972252.27 frames.], batch size: 20, lr: 6.49e-04
2022-05-04 08:59:48,685 INFO [train.py:715] (4/8) Epoch 2, batch 25750, loss[loss=0.2233, simple_loss=0.2638, pruned_loss=0.09139, over 4853.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2359, pruned_loss=0.05093, over 972828.19 frames.], batch size: 13, lr: 6.49e-04
2022-05-04 09:00:27,437 INFO [train.py:715] (4/8) Epoch 2, batch 25800, loss[loss=0.1717, simple_loss=0.2376, pruned_loss=0.05289, over 4905.00 frames.], tot_loss[loss=0.17, simple_loss=0.2369, pruned_loss=0.05152, over 973267.70 frames.], batch size: 19, lr: 6.49e-04
2022-05-04 09:01:06,416 INFO [train.py:715] (4/8) Epoch 2, batch 25850, loss[loss=0.1589, simple_loss=0.2239, pruned_loss=0.04689, over 4966.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2361, pruned_loss=0.05063, over 972567.95 frames.], batch size: 28, lr: 6.49e-04
2022-05-04 09:01:46,179 INFO [train.py:715] (4/8) Epoch 2, batch 25900, loss[loss=0.1624, simple_loss=0.2257, pruned_loss=0.0496, over 4704.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2348, pruned_loss=0.05016, over 972915.19 frames.], batch size: 15, lr: 6.49e-04
2022-05-04 09:02:25,987 INFO [train.py:715] (4/8) Epoch 2, batch 25950, loss[loss=0.1392, simple_loss=0.2146, pruned_loss=0.03192, over 4926.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2345, pruned_loss=0.04951, over 974052.39 frames.], batch size: 29, lr: 6.49e-04
2022-05-04 09:03:05,064 INFO [train.py:715] (4/8) Epoch 2, batch 26000, loss[loss=0.1545, simple_loss=0.2193, pruned_loss=0.04483, over 4902.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2352, pruned_loss=0.05019, over 973835.25 frames.], batch size: 17, lr: 6.48e-04
2022-05-04 09:03:44,733 INFO [train.py:715] (4/8) Epoch 2, batch 26050, loss[loss=0.1634, simple_loss=0.2258, pruned_loss=0.05046, over 4753.00 frames.], tot_loss[loss=0.1691, simple_loss=0.236, pruned_loss=0.05107, over 974041.46 frames.], batch size: 16, lr: 6.48e-04
2022-05-04 09:04:24,304 INFO [train.py:715] (4/8) Epoch 2, batch 26100, loss[loss=0.1631, simple_loss=0.2351, pruned_loss=0.0456, over 4810.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2355, pruned_loss=0.0508, over 973882.92 frames.], batch size: 21, lr: 6.48e-04
2022-05-04 09:05:03,478 INFO [train.py:715] (4/8) Epoch 2, batch 26150, loss[loss=0.1453, simple_loss=0.2145, pruned_loss=0.03803, over 4986.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2349, pruned_loss=0.05083, over 974797.97 frames.], batch size: 25, lr: 6.48e-04
2022-05-04 09:05:42,983 INFO [train.py:715] (4/8) Epoch 2, batch 26200, loss[loss=0.1711, simple_loss=0.2512, pruned_loss=0.04544, over 4883.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2348, pruned_loss=0.05056, over 974008.94 frames.], batch size: 22, lr: 6.48e-04
2022-05-04 09:06:22,731 INFO [train.py:715] (4/8) Epoch 2, batch 26250, loss[loss=0.1805, simple_loss=0.2386, pruned_loss=0.06122, over 4785.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2349, pruned_loss=0.05034, over 973891.98 frames.], batch size: 14, lr: 6.48e-04
2022-05-04 09:07:02,318 INFO [train.py:715] (4/8) Epoch 2, batch 26300, loss[loss=0.1498, simple_loss=0.2154, pruned_loss=0.04208, over 4777.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2351, pruned_loss=0.05037, over 973030.39 frames.], batch size: 17, lr: 6.47e-04
2022-05-04 09:07:40,823 INFO [train.py:715] (4/8) Epoch 2, batch 26350, loss[loss=0.1735, simple_loss=0.2333, pruned_loss=0.05688, over 4981.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2352, pruned_loss=0.05035, over 972464.14 frames.], batch size: 15, lr: 6.47e-04
2022-05-04 09:08:23,928 INFO [train.py:715] (4/8) Epoch 2, batch 26400, loss[loss=0.1932, simple_loss=0.2624, pruned_loss=0.06198, over 4882.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2364, pruned_loss=0.05128, over 971507.64 frames.], batch size: 16, lr: 6.47e-04
2022-05-04 09:09:03,681 INFO [train.py:715] (4/8) Epoch 2, batch 26450, loss[loss=0.1879, simple_loss=0.2637, pruned_loss=0.05605, over 4901.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2358, pruned_loss=0.05101, over 971541.72 frames.], batch size: 19, lr: 6.47e-04
2022-05-04 09:09:42,579 INFO [train.py:715] (4/8) Epoch 2, batch 26500, loss[loss=0.1928, simple_loss=0.2585, pruned_loss=0.06359, over 4961.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2358, pruned_loss=0.05074, over 972086.80 frames.], batch size: 24, lr: 6.47e-04
2022-05-04 09:10:22,390 INFO [train.py:715] (4/8) Epoch 2, batch 26550, loss[loss=0.1395, simple_loss=0.2044, pruned_loss=0.03734, over 4796.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2344, pruned_loss=0.04998, over 972485.32 frames.], batch size: 18, lr: 6.46e-04
2022-05-04 09:11:02,375 INFO [train.py:715] (4/8) Epoch 2, batch 26600, loss[loss=0.1738, simple_loss=0.2382, pruned_loss=0.05471, over 4980.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2337, pruned_loss=0.04967, over 971725.98 frames.], batch size: 28, lr: 6.46e-04
2022-05-04 09:11:41,991 INFO [train.py:715] (4/8) Epoch 2, batch 26650, loss[loss=0.1844, simple_loss=0.2567, pruned_loss=0.05603, over 4964.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2337, pruned_loss=0.04966, over 972057.69 frames.], batch size: 31, lr: 6.46e-04
2022-05-04 09:12:21,005 INFO [train.py:715] (4/8) Epoch 2, batch 26700, loss[loss=0.1292, simple_loss=0.2015, pruned_loss=0.02841, over 4793.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2338, pruned_loss=0.05001, over 971847.58 frames.], batch size: 14, lr: 6.46e-04
2022-05-04 09:13:00,966 INFO [train.py:715] (4/8) Epoch 2, batch 26750, loss[loss=0.1664, simple_loss=0.2436, pruned_loss=0.04454, over 4872.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2357, pruned_loss=0.05106, over 971884.27 frames.], batch size: 22, lr: 6.46e-04
2022-05-04 09:13:40,191 INFO [train.py:715] (4/8) Epoch 2, batch 26800, loss[loss=0.1398, simple_loss=0.2091, pruned_loss=0.03529, over 4981.00 frames.], tot_loss[loss=0.1691, simple_loss=0.236, pruned_loss=0.05106, over 972015.14 frames.], batch size: 24, lr: 6.46e-04
2022-05-04 09:14:19,181 INFO [train.py:715] (4/8) Epoch 2, batch 26850, loss[loss=0.1877, simple_loss=0.2516, pruned_loss=0.06189, over 4958.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2352, pruned_loss=0.05058, over 972236.44 frames.], batch size: 35, lr: 6.45e-04
2022-05-04 09:14:58,117 INFO [train.py:715] (4/8) Epoch 2, batch 26900, loss[loss=0.1551, simple_loss=0.217, pruned_loss=0.04658, over 4919.00 frames.], tot_loss[loss=0.168, simple_loss=0.2351, pruned_loss=0.05047, over 972499.84 frames.], batch size: 18, lr: 6.45e-04
2022-05-04 09:15:37,579 INFO [train.py:715] (4/8) Epoch 2, batch 26950, loss[loss=0.1508, simple_loss=0.2099, pruned_loss=0.0458, over 4845.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2357, pruned_loss=0.05085, over 971507.47 frames.], batch size: 32, lr: 6.45e-04
2022-05-04 09:16:16,464 INFO [train.py:715] (4/8) Epoch 2, batch 27000, loss[loss=0.1863, simple_loss=0.2423, pruned_loss=0.06516, over 4958.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2356, pruned_loss=0.05071, over 972428.90 frames.], batch size: 39, lr: 6.45e-04
2022-05-04 09:16:16,464 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 09:16:25,253 INFO [train.py:742] (4/8) Epoch 2, validation: loss=0.1164, simple_loss=0.2027, pruned_loss=0.01502, over 914524.00 frames.
2022-05-04 09:17:03,617 INFO [train.py:715] (4/8) Epoch 2, batch 27050, loss[loss=0.1522, simple_loss=0.2103, pruned_loss=0.04705, over 4821.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2354, pruned_loss=0.0508, over 972616.18 frames.], batch size: 26, lr: 6.45e-04
2022-05-04 09:17:42,881 INFO [train.py:715] (4/8) Epoch 2, batch 27100, loss[loss=0.1768, simple_loss=0.238, pruned_loss=0.05774, over 4876.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2358, pruned_loss=0.05095, over 972713.35 frames.], batch size: 16, lr: 6.45e-04
2022-05-04 09:18:22,883 INFO [train.py:715] (4/8) Epoch 2, batch 27150, loss[loss=0.2053, simple_loss=0.2589, pruned_loss=0.07585, over 4799.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2362, pruned_loss=0.05135, over 972743.27 frames.], batch size: 13, lr: 6.44e-04
2022-05-04 09:19:02,264 INFO [train.py:715] (4/8) Epoch 2, batch 27200, loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03772, over 4814.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2357, pruned_loss=0.05105, over 972287.14 frames.], batch size: 25, lr: 6.44e-04
2022-05-04 09:19:41,120 INFO [train.py:715] (4/8) Epoch 2, batch 27250, loss[loss=0.1583, simple_loss=0.2233, pruned_loss=0.04661, over 4688.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2366, pruned_loss=0.05109, over 972216.21 frames.], batch size: 15, lr: 6.44e-04
2022-05-04 09:20:20,688 INFO [train.py:715] (4/8) Epoch 2, batch 27300, loss[loss=0.1606, simple_loss=0.2216, pruned_loss=0.0498, over 4894.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2374, pruned_loss=0.0512, over 972160.91 frames.], batch size: 22, lr: 6.44e-04
2022-05-04 09:20:59,721 INFO [train.py:715] (4/8) Epoch 2, batch 27350, loss[loss=0.1747, simple_loss=0.2419, pruned_loss=0.05371, over 4690.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2372, pruned_loss=0.05093, over 972107.56 frames.], batch size: 15, lr: 6.44e-04
2022-05-04 09:21:38,801 INFO [train.py:715] (4/8) Epoch 2, batch 27400, loss[loss=0.1626, simple_loss=0.2453, pruned_loss=0.03996, over 4941.00 frames.], tot_loss[loss=0.1706, simple_loss=0.2384, pruned_loss=0.05133, over 972908.44 frames.], batch size: 21, lr: 6.44e-04
2022-05-04 09:22:17,479 INFO [train.py:715] (4/8) Epoch 2, batch 27450, loss[loss=0.1387, simple_loss=0.2054, pruned_loss=0.03599, over 4927.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2367, pruned_loss=0.0508, over 972976.61 frames.], batch size: 29, lr: 6.44e-04
2022-05-04 09:22:57,210 INFO [train.py:715] (4/8) Epoch 2, batch 27500, loss[loss=0.1782, simple_loss=0.2531, pruned_loss=0.05161, over 4824.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2362, pruned_loss=0.05057, over 973055.69 frames.], batch size: 25, lr: 6.43e-04
2022-05-04 09:23:37,092 INFO [train.py:715] (4/8) Epoch 2, batch 27550, loss[loss=0.1432, simple_loss=0.2164, pruned_loss=0.03499, over 4774.00 frames.], tot_loss[loss=0.1699, simple_loss=0.2373, pruned_loss=0.05131, over 973283.03 frames.], batch size: 12, lr: 6.43e-04
2022-05-04 09:24:16,421 INFO [train.py:715] (4/8) Epoch 2, batch 27600, loss[loss=0.19, simple_loss=0.2452, pruned_loss=0.06737, over 4852.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2373, pruned_loss=0.05149, over 973475.08 frames.], batch size: 32, lr: 6.43e-04
2022-05-04 09:24:55,993 INFO [train.py:715] (4/8) Epoch 2, batch 27650, loss[loss=0.1617, simple_loss=0.2236, pruned_loss=0.0499, over 4833.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2371, pruned_loss=0.05116, over 972822.14 frames.], batch size: 30, lr: 6.43e-04
2022-05-04 09:25:36,591 INFO [train.py:715] (4/8) Epoch 2, batch 27700, loss[loss=0.1809, simple_loss=0.2468, pruned_loss=0.05749, over 4983.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2359, pruned_loss=0.05096, over 973129.08 frames.], batch size: 26, lr: 6.43e-04
2022-05-04 09:26:16,918 INFO [train.py:715] (4/8) Epoch 2, batch 27750, loss[loss=0.1786, simple_loss=0.2401, pruned_loss=0.05857, over 4948.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2358, pruned_loss=0.05104, over 972828.19 frames.], batch size: 21, lr: 6.43e-04
2022-05-04 09:26:56,303 INFO [train.py:715] (4/8) Epoch 2, batch 27800, loss[loss=0.2024, simple_loss=0.2619, pruned_loss=0.07146, over 4886.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2364, pruned_loss=0.05129, over 973552.93 frames.], batch size: 22, lr: 6.42e-04
2022-05-04 09:27:36,593 INFO [train.py:715] (4/8) Epoch 2, batch 27850, loss[loss=0.2017, simple_loss=0.2664, pruned_loss=0.06847, over 4981.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2362, pruned_loss=0.05124, over 974074.37 frames.], batch size: 39, lr: 6.42e-04
2022-05-04 09:28:15,906 INFO [train.py:715] (4/8) Epoch 2, batch 27900, loss[loss=0.1934, simple_loss=0.2559, pruned_loss=0.06544, over 4918.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2363, pruned_loss=0.05154, over 973355.32 frames.], batch size: 39, lr: 6.42e-04
2022-05-04 09:28:55,086 INFO [train.py:715] (4/8) Epoch 2, batch 27950, loss[loss=0.187, simple_loss=0.2555, pruned_loss=0.0592, over 4897.00 frames.], tot_loss[loss=0.1704, simple_loss=0.2371, pruned_loss=0.05184, over 973277.41 frames.], batch size: 19, lr: 6.42e-04
2022-05-04 09:29:34,665 INFO [train.py:715] (4/8) Epoch 2, batch 28000, loss[loss=0.1505, simple_loss=0.2196, pruned_loss=0.04066, over 4689.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2363, pruned_loss=0.05154, over 972099.68 frames.], batch size: 15, lr: 6.42e-04
2022-05-04 09:30:15,041 INFO [train.py:715] (4/8) Epoch 2, batch 28050, loss[loss=0.163, simple_loss=0.2198, pruned_loss=0.05315, over 4775.00 frames.], tot_loss[loss=0.17, simple_loss=0.2365, pruned_loss=0.05177, over 971717.75 frames.], batch size: 12, lr: 6.42e-04
2022-05-04 09:30:54,018 INFO [train.py:715] (4/8) Epoch 2, batch 28100, loss[loss=0.1537, simple_loss=0.2294, pruned_loss=0.03901, over 4711.00 frames.], tot_loss[loss=0.17, simple_loss=0.2365, pruned_loss=0.05179, over 971378.10 frames.], batch size: 15, lr: 6.41e-04
2022-05-04 09:31:33,557 INFO [train.py:715] (4/8) Epoch 2, batch 28150, loss[loss=0.1793, simple_loss=0.2509, pruned_loss=0.05381, over 4817.00 frames.], tot_loss[loss=0.17, simple_loss=0.2364, pruned_loss=0.05181, over 971248.88 frames.], batch size: 15, lr: 6.41e-04
2022-05-04 09:32:13,295 INFO [train.py:715] (4/8) Epoch 2, batch 28200, loss[loss=0.1896, simple_loss=0.26, pruned_loss=0.05967, over 4896.00 frames.], tot_loss[loss=0.17, simple_loss=0.2366, pruned_loss=0.05166, over 972420.02 frames.], batch size: 39, lr: 6.41e-04
2022-05-04 09:32:52,899 INFO [train.py:715] (4/8) Epoch 2, batch 28250, loss[loss=0.1624, simple_loss=0.2268, pruned_loss=0.04901, over 4916.00 frames.], tot_loss[loss=0.1696, simple_loss=0.2362, pruned_loss=0.05148, over 972536.38 frames.], batch size: 39, lr: 6.41e-04
2022-05-04 09:33:31,976 INFO [train.py:715] (4/8) Epoch 2, batch 28300, loss[loss=0.1882, simple_loss=0.2558, pruned_loss=0.06025, over 4845.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2371, pruned_loss=0.0517, over 971558.90 frames.], batch size: 32, lr: 6.41e-04
2022-05-04 09:34:11,317 INFO [train.py:715] (4/8) Epoch 2, batch 28350, loss[loss=0.1623, simple_loss=0.2301, pruned_loss=0.04727, over 4963.00 frames.], tot_loss[loss=0.1701, simple_loss=0.237, pruned_loss=0.0516, over 971363.72 frames.], batch size: 35, lr: 6.41e-04
2022-05-04 09:34:51,511 INFO [train.py:715] (4/8) Epoch 2, batch 28400, loss[loss=0.1907, simple_loss=0.2581, pruned_loss=0.06167, over 4965.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2364, pruned_loss=0.05151, over 971449.80 frames.], batch size: 24, lr: 6.40e-04
2022-05-04 09:35:30,758 INFO [train.py:715] (4/8) Epoch 2, batch 28450, loss[loss=0.1614, simple_loss=0.2305, pruned_loss=0.04613, over 4932.00 frames.], tot_loss[loss=0.1713, simple_loss=0.2376, pruned_loss=0.0525, over 972081.35 frames.], batch size: 23, lr: 6.40e-04
2022-05-04 09:36:10,158 INFO [train.py:715] (4/8) Epoch 2, batch 28500, loss[loss=0.1884, simple_loss=0.2549, pruned_loss=0.06094, over 4833.00 frames.], tot_loss[loss=0.1709, simple_loss=0.2374, pruned_loss=0.05221, over 971713.00 frames.], batch size: 13, lr: 6.40e-04
2022-05-04 09:36:50,108 INFO [train.py:715] (4/8) Epoch 2, batch 28550, loss[loss=0.2123, simple_loss=0.28, pruned_loss=0.07233, over 4983.00 frames.], tot_loss[loss=0.1716, simple_loss=0.2381, pruned_loss=0.05259, over 973094.70 frames.], batch size: 35, lr: 6.40e-04
2022-05-04 09:37:30,235 INFO [train.py:715] (4/8) Epoch 2, batch 28600, loss[loss=0.1467, simple_loss=0.2229, pruned_loss=0.03519, over 4765.00 frames.], tot_loss[loss=0.1702, simple_loss=0.2367, pruned_loss=0.05183, over 973171.25 frames.], batch size: 14, lr: 6.40e-04
2022-05-04 09:38:09,269 INFO [train.py:715] (4/8) Epoch 2, batch 28650, loss[loss=0.1405, simple_loss=0.2081, pruned_loss=0.03644, over 4697.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2348, pruned_loss=0.0507, over 973023.87 frames.], batch size: 15, lr: 6.40e-04
2022-05-04 09:38:49,123 INFO [train.py:715] (4/8) Epoch 2, batch 28700, loss[loss=0.1507, simple_loss=0.2238, pruned_loss=0.03877, over 4928.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2344, pruned_loss=0.05021, over 973766.90 frames.], batch size: 23, lr: 6.39e-04
2022-05-04 09:39:29,583 INFO [train.py:715] (4/8) Epoch 2, batch 28750, loss[loss=0.1682, simple_loss=0.2454, pruned_loss=0.04548, over 4889.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2338, pruned_loss=0.04969, over 974140.56 frames.], batch size: 22, lr: 6.39e-04
2022-05-04 09:40:08,506 INFO [train.py:715] (4/8) Epoch 2, batch 28800, loss[loss=0.172, simple_loss=0.2467, pruned_loss=0.04867, over 4848.00 frames.], tot_loss[loss=0.1669, simple_loss=0.234, pruned_loss=0.04993, over 973344.17 frames.], batch size: 20, lr: 6.39e-04
2022-05-04 09:40:48,100 INFO [train.py:715] (4/8) Epoch 2, batch 28850, loss[loss=0.1515, simple_loss=0.2289, pruned_loss=0.03705, over 4935.00 frames.], tot_loss[loss=0.167, simple_loss=0.2344, pruned_loss=0.04978, over 973213.52 frames.], batch size: 21, lr: 6.39e-04
2022-05-04 09:41:28,106 INFO [train.py:715] (4/8) Epoch 2, batch 28900, loss[loss=0.1544, simple_loss=0.2218, pruned_loss=0.04345, over 4838.00 frames.], tot_loss[loss=0.1683, simple_loss=0.2351, pruned_loss=0.05072, over 973503.49 frames.], batch size: 15, lr: 6.39e-04
2022-05-04 09:42:07,483 INFO [train.py:715] (4/8) Epoch 2, batch 28950, loss[loss=0.1425, simple_loss=0.2045, pruned_loss=0.04022, over 4774.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2362, pruned_loss=0.05164, over 972477.06 frames.], batch size: 12, lr: 6.39e-04
2022-05-04 09:42:46,856 INFO [train.py:715] (4/8) Epoch 2, batch 29000, loss[loss=0.1556, simple_loss=0.2083, pruned_loss=0.0515, over 4831.00 frames.], tot_loss[loss=0.17, simple_loss=0.2363, pruned_loss=0.05192, over 973217.20 frames.], batch size: 15, lr: 6.38e-04
2022-05-04 09:43:26,612 INFO [train.py:715] (4/8) Epoch 2, batch 29050, loss[loss=0.1273, simple_loss=0.1991, pruned_loss=0.02772, over 4819.00 frames.], tot_loss[loss=0.1691, simple_loss=0.236, pruned_loss=0.05111, over 973082.63 frames.], batch size: 13, lr: 6.38e-04
2022-05-04 09:44:06,287 INFO [train.py:715] (4/8) Epoch 2, batch 29100, loss[loss=0.1929, simple_loss=0.2477, pruned_loss=0.06906, over 4783.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2358, pruned_loss=0.0508, over 973485.67 frames.], batch size: 18, lr: 6.38e-04
2022-05-04 09:44:45,460 INFO [train.py:715] (4/8) Epoch 2, batch 29150, loss[loss=0.1759, simple_loss=0.2303, pruned_loss=0.0607, over 4915.00 frames.], tot_loss[loss=0.169, simple_loss=0.2363, pruned_loss=0.05085, over 972818.89 frames.], batch size: 19, lr: 6.38e-04
2022-05-04 09:45:24,944 INFO [train.py:715] (4/8) Epoch 2, batch 29200, loss[loss=0.1533, simple_loss=0.2211, pruned_loss=0.04276, over 4823.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2362, pruned_loss=0.05116, over 972837.40 frames.], batch size: 26, lr: 6.38e-04
2022-05-04 09:46:05,374 INFO [train.py:715] (4/8) Epoch 2, batch 29250, loss[loss=0.1712, simple_loss=0.2294, pruned_loss=0.05655, over 4856.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2362, pruned_loss=0.05134, over 973337.79 frames.], batch size: 20, lr: 6.38e-04
2022-05-04 09:46:44,478 INFO [train.py:715] (4/8) Epoch 2, batch 29300, loss[loss=0.1529, simple_loss=0.2363, pruned_loss=0.03475, over 4978.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2362, pruned_loss=0.05119, over 972959.89 frames.], batch size: 14, lr: 6.37e-04
2022-05-04 09:47:23,246 INFO [train.py:715] (4/8) Epoch 2, batch 29350, loss[loss=0.1393, simple_loss=0.2105, pruned_loss=0.03401, over 4956.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2355, pruned_loss=0.05083, over 973209.10 frames.], batch size: 21, lr: 6.37e-04
2022-05-04 09:48:02,463 INFO [train.py:715] (4/8) Epoch 2, batch 29400, loss[loss=0.2223, simple_loss=0.267, pruned_loss=0.08877, over 4911.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2353, pruned_loss=0.05078, over 973613.89 frames.], batch size: 17, lr: 6.37e-04
2022-05-04 09:48:41,885 INFO [train.py:715] (4/8) Epoch 2, batch 29450, loss[loss=0.1853, simple_loss=0.2543, pruned_loss=0.05812, over 4756.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2352, pruned_loss=0.05063, over 973851.85 frames.], batch size: 19, lr: 6.37e-04
2022-05-04 09:49:20,753 INFO [train.py:715] (4/8) Epoch 2, batch 29500, loss[loss=0.1691, simple_loss=0.235, pruned_loss=0.05166, over 4797.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2361, pruned_loss=0.05151, over 973564.24 frames.], batch size: 17, lr: 6.37e-04
2022-05-04 09:49:59,766 INFO [train.py:715] (4/8) Epoch 2, batch 29550, loss[loss=0.2361, simple_loss=0.2829, pruned_loss=0.09461, over 4895.00 frames.], tot_loss[loss=0.1694, simple_loss=0.236, pruned_loss=0.05142, over 973004.11 frames.], batch size: 39, lr: 6.37e-04
2022-05-04 09:50:39,179 INFO [train.py:715] (4/8) Epoch 2, batch 29600, loss[loss=0.1577, simple_loss=0.2263, pruned_loss=0.04451, over 4788.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2356, pruned_loss=0.05095, over 972958.33 frames.], batch size: 21, lr: 6.37e-04
2022-05-04 09:51:18,363 INFO [train.py:715] (4/8) Epoch 2, batch 29650, loss[loss=0.1397, simple_loss=0.21, pruned_loss=0.03465, over 4759.00 frames.], tot_loss[loss=0.1689, simple_loss=0.236, pruned_loss=0.05086, over 973452.33 frames.], batch size: 19, lr: 6.36e-04
2022-05-04 09:51:57,125 INFO [train.py:715] (4/8) Epoch 2, batch 29700, loss[loss=0.1352, simple_loss=0.201, pruned_loss=0.03472, over 4867.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2358, pruned_loss=0.05034, over 973705.52 frames.], batch size: 20, lr: 6.36e-04
2022-05-04 09:52:36,250 INFO [train.py:715] (4/8) Epoch 2, batch 29750, loss[loss=0.1522, simple_loss=0.2187, pruned_loss=0.04287, over 4780.00 frames.], tot_loss[loss=0.1691, simple_loss=0.2365, pruned_loss=0.05079, over 973852.35 frames.], batch size: 17, lr: 6.36e-04
2022-05-04 09:53:15,367 INFO [train.py:715] (4/8) Epoch 2, batch 29800, loss[loss=0.161, simple_loss=0.2318, pruned_loss=0.04505, over 4798.00 frames.], tot_loss[loss=0.1695, simple_loss=0.2368, pruned_loss=0.05109, over 972727.62 frames.], batch size: 15, lr: 6.36e-04
2022-05-04 09:53:53,996 INFO [train.py:715] (4/8) Epoch 2, batch 29850, loss[loss=0.1468, simple_loss=0.2179, pruned_loss=0.03789, over 4972.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2358, pruned_loss=0.05027, over 972433.54 frames.], batch size: 28, lr: 6.36e-04
2022-05-04 09:54:33,007 INFO [train.py:715] (4/8) Epoch 2, batch 29900, loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03438, over 4959.00 frames.], tot_loss[loss=0.1681, simple_loss=0.2359, pruned_loss=0.05009, over 972621.17 frames.], batch size: 15, lr: 6.36e-04
2022-05-04 09:55:12,826 INFO [train.py:715] (4/8) Epoch 2, batch 29950, loss[loss=0.1476, simple_loss=0.221, pruned_loss=0.0371, over 4982.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2354, pruned_loss=0.04938, over 972738.91 frames.], batch size: 15, lr: 6.35e-04
2022-05-04 09:55:51,633 INFO [train.py:715] (4/8) Epoch 2, batch 30000, loss[loss=0.1554, simple_loss=0.2214, pruned_loss=0.04471, over 4864.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2362, pruned_loss=0.0497, over 973050.41 frames.], batch size: 30, lr: 6.35e-04
2022-05-04 09:55:51,634 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 09:56:00,453 INFO [train.py:742] (4/8) Epoch 2, validation: loss=0.1166, simple_loss=0.2028, pruned_loss=0.01515, over 914524.00 frames.
2022-05-04 09:56:39,115 INFO [train.py:715] (4/8) Epoch 2, batch 30050, loss[loss=0.1665, simple_loss=0.2335, pruned_loss=0.04969, over 4796.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2371, pruned_loss=0.05058, over 973254.14 frames.], batch size: 24, lr: 6.35e-04
2022-05-04 09:57:18,477 INFO [train.py:715] (4/8) Epoch 2, batch 30100, loss[loss=0.1588, simple_loss=0.2331, pruned_loss=0.04221, over 4883.00 frames.], tot_loss[loss=0.1688, simple_loss=0.237, pruned_loss=0.05033, over 972564.03 frames.], batch size: 22, lr: 6.35e-04
2022-05-04 09:57:57,547 INFO [train.py:715] (4/8) Epoch 2, batch 30150, loss[loss=0.1486, simple_loss=0.2177, pruned_loss=0.03972, over 4903.00 frames.], tot_loss[loss=0.1687, simple_loss=0.2367, pruned_loss=0.05036, over 972493.08 frames.], batch size: 23, lr: 6.35e-04
2022-05-04 09:58:37,028 INFO [train.py:715] (4/8) Epoch 2, batch 30200, loss[loss=0.1592, simple_loss=0.2233, pruned_loss=0.04754, over 4832.00 frames.], tot_loss[loss=0.1686, simple_loss=0.2362, pruned_loss=0.05052, over 971817.97 frames.], batch size: 20, lr: 6.35e-04
2022-05-04 09:59:15,772 INFO [train.py:715] (4/8) Epoch 2, batch 30250, loss[loss=0.1431, simple_loss=0.2154, pruned_loss=0.0354, over 4836.00 frames.], tot_loss[loss=0.1698, simple_loss=0.2372, pruned_loss=0.0512, over 970998.72 frames.], batch size: 25, lr: 6.34e-04
2022-05-04 09:59:55,024 INFO [train.py:715] (4/8) Epoch 2, batch 30300, loss[loss=0.1702, simple_loss=0.2396, pruned_loss=0.05039, over 4893.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2365, pruned_loss=0.05097, over 971333.52 frames.], batch size: 22, lr: 6.34e-04
2022-05-04 10:00:35,004 INFO [train.py:715] (4/8) Epoch 2, batch 30350, loss[loss=0.1838, simple_loss=0.2435, pruned_loss=0.06207, over 4811.00 frames.], tot_loss[loss=0.1689, simple_loss=0.2359, pruned_loss=0.05092, over 971773.65 frames.], batch size: 13, lr: 6.34e-04
2022-05-04 10:01:14,090 INFO [train.py:715] (4/8) Epoch 2, batch 30400, loss[loss=0.1525, simple_loss=0.2227, pruned_loss=0.04117, over 4947.00 frames.], tot_loss[loss=0.1694, simple_loss=0.2365, pruned_loss=0.05122, over 971626.89 frames.], batch size: 21, lr: 6.34e-04
2022-05-04 10:01:53,190 INFO [train.py:715] (4/8) Epoch 2, batch 30450, loss[loss=0.2065, simple_loss=0.2702, pruned_loss=0.07135, over 4985.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2365, pruned_loss=0.05098, over 972196.24 frames.], batch size: 16, lr: 6.34e-04
2022-05-04 10:02:32,960 INFO [train.py:715] (4/8) Epoch 2, batch 30500, loss[loss=0.1873, simple_loss=0.2474, pruned_loss=0.06361, over 4834.00 frames.], tot_loss[loss=0.1703, simple_loss=0.2373, pruned_loss=0.05163, over 971811.35 frames.], batch size: 26, lr: 6.34e-04
2022-05-04 10:03:12,630 INFO [train.py:715] (4/8) Epoch 2, batch 30550, loss[loss=0.2237, simple_loss=0.2754, pruned_loss=0.08596, over 4810.00 frames.], tot_loss[loss=0.1697, simple_loss=0.2366, pruned_loss=0.05134, over 970936.70 frames.], batch size: 21, lr: 6.33e-04
2022-05-04 10:03:51,361 INFO [train.py:715] (4/8) Epoch 2, batch 30600, loss[loss=0.1535, simple_loss=0.2316, pruned_loss=0.03773, over 4763.00 frames.], tot_loss[loss=0.169, simple_loss=0.236, pruned_loss=0.05097, over 970571.30 frames.], batch size: 19, lr: 6.33e-04
2022-05-04 10:04:31,216 INFO [train.py:715] (4/8) Epoch 2, batch 30650, loss[loss=0.1188, simple_loss=0.186, pruned_loss=0.02578, over 4787.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2349, pruned_loss=0.04985, over 970652.66 frames.], batch size: 12, lr: 6.33e-04
2022-05-04 10:05:11,276 INFO [train.py:715] (4/8) Epoch 2, batch 30700, loss[loss=0.1568, simple_loss=0.2223, pruned_loss=0.04561, over 4984.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2345, pruned_loss=0.0502, over 971720.16 frames.], batch size: 14, lr: 6.33e-04
2022-05-04 10:05:51,102 INFO [train.py:715] (4/8) Epoch 2, batch 30750, loss[loss=0.1747, simple_loss=0.2467, pruned_loss=0.05134, over 4790.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2343, pruned_loss=0.05012, over 972633.10 frames.], batch size: 17, lr: 6.33e-04
2022-05-04 10:06:30,170 INFO [train.py:715] (4/8) Epoch 2, batch 30800, loss[loss=0.1809, simple_loss=0.2501, pruned_loss=0.05583, over 4829.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2335, pruned_loss=0.04977, over 971892.41 frames.], batch size: 15, lr: 6.33e-04
2022-05-04 10:07:09,683 INFO [train.py:715] (4/8) Epoch 2, batch 30850, loss[loss=0.1676, simple_loss=0.2381, pruned_loss=0.04851, over 4981.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2349, pruned_loss=0.05026, over 972312.90 frames.], batch size: 24, lr: 6.33e-04
2022-05-04 10:07:49,326 INFO [train.py:715] (4/8) Epoch 2, batch 30900, loss[loss=0.1438, simple_loss=0.2226, pruned_loss=0.03244, over 4991.00 frames.], tot_loss[loss=0.168, simple_loss=0.2351, pruned_loss=0.0504, over 971422.78 frames.], batch size: 28, lr: 6.32e-04
2022-05-04 10:08:27,844 INFO [train.py:715] (4/8) Epoch 2, batch 30950, loss[loss=0.1336, simple_loss=0.2091, pruned_loss=0.02905, over 4920.00 frames.], tot_loss[loss=0.1679, simple_loss=0.235, pruned_loss=0.05039, over 971159.55 frames.], batch size: 18, lr: 6.32e-04
2022-05-04 10:09:07,770 INFO [train.py:715] (4/8) Epoch 2, batch 31000, loss[loss=0.1622, simple_loss=0.2254, pruned_loss=0.04947, over 4885.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2345, pruned_loss=0.05026, over 971932.90 frames.], batch size: 19, lr: 6.32e-04
2022-05-04 10:09:48,211 INFO [train.py:715] (4/8) Epoch 2, batch 31050, loss[loss=0.138, simple_loss=0.2013, pruned_loss=0.03735, over 4816.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2348, pruned_loss=0.05029, over 972769.67 frames.], batch size: 12, lr: 6.32e-04
2022-05-04 10:10:27,687 INFO [train.py:715] (4/8) Epoch 2, batch 31100, loss[loss=0.1505, simple_loss=0.2192, pruned_loss=0.04093, over 4814.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2345, pruned_loss=0.05007, over 973033.67 frames.], batch size: 25, lr: 6.32e-04
2022-05-04 10:11:07,479 INFO [train.py:715] (4/8) Epoch 2, batch 31150, loss[loss=0.1919, simple_loss=0.2686, pruned_loss=0.05764, over 4797.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2359, pruned_loss=0.05081, over 972670.23 frames.], batch size: 24, lr: 6.32e-04
2022-05-04 10:11:47,660 INFO [train.py:715] (4/8) Epoch 2, batch 31200, loss[loss=0.1536, simple_loss=0.222, pruned_loss=0.04263, over 4940.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2339, pruned_loss=0.04985, over 972717.65 frames.], batch size: 18, lr: 6.31e-04
2022-05-04 10:12:27,439 INFO [train.py:715] (4/8) Epoch 2, batch 31250, loss[loss=0.1541, simple_loss=0.2242, pruned_loss=0.04194, over 4897.00 frames.], tot_loss[loss=0.1669, simple_loss=0.234, pruned_loss=0.04987, over 973423.00 frames.], batch size: 16, lr: 6.31e-04
2022-05-04 10:13:06,634 INFO [train.py:715] (4/8) Epoch 2, batch 31300, loss[loss=0.135, simple_loss=0.2101, pruned_loss=0.02999, over 4766.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2336, pruned_loss=0.04963, over 972879.47 frames.], batch size: 17, lr: 6.31e-04
2022-05-04 10:13:46,584 INFO [train.py:715] (4/8) Epoch 2, batch 31350, loss[loss=0.179, simple_loss=0.2468, pruned_loss=0.05558, over 4871.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2349, pruned_loss=0.0498, over 972284.16 frames.], batch size: 20, lr: 6.31e-04
2022-05-04 10:14:26,952 INFO [train.py:715] (4/8) Epoch 2, batch 31400, loss[loss=0.1443, simple_loss=0.2113, pruned_loss=0.03866, over 4711.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2346, pruned_loss=0.05019, over 971975.04 frames.], batch size: 15, lr: 6.31e-04
2022-05-04 10:15:06,595 INFO [train.py:715] (4/8) Epoch 2, batch 31450, loss[loss=0.1813, simple_loss=0.2421, pruned_loss=0.0602, over 4891.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2349, pruned_loss=0.05098, over 971894.99 frames.], batch size: 39, lr: 6.31e-04
2022-05-04 10:15:46,237 INFO [train.py:715] (4/8) Epoch 2, batch 31500, loss[loss=0.1753, simple_loss=0.2505, pruned_loss=0.05002, over 4922.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2362, pruned_loss=0.05113, over 972695.50 frames.], batch size: 19, lr: 6.31e-04
2022-05-04 10:16:26,030 INFO [train.py:715] (4/8) Epoch 2, batch 31550, loss[loss=0.1962, simple_loss=0.2697, pruned_loss=0.06132, over 4946.00 frames.], tot_loss[loss=0.1692, simple_loss=0.2362, pruned_loss=0.05109, over 971834.10 frames.], batch size: 21, lr: 6.30e-04
2022-05-04 10:17:05,438 INFO [train.py:715] (4/8) Epoch 2, batch 31600, loss[loss=0.1795, simple_loss=0.2466, pruned_loss=0.05623, over 4863.00 frames.], tot_loss[loss=0.1693, simple_loss=0.2364, pruned_loss=0.05106, over 971281.50 frames.], batch size: 20, lr: 6.30e-04
2022-05-04 10:17:44,221 INFO [train.py:715] (4/8) Epoch 2, batch 31650, loss[loss=0.1747, simple_loss=0.2335, pruned_loss=0.05793, over 4874.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2359, pruned_loss=0.05046, over 971026.64 frames.], batch size: 32, lr: 6.30e-04
2022-05-04 10:18:24,067 INFO [train.py:715] (4/8) Epoch 2, batch 31700, loss[loss=0.1695, simple_loss=0.2299, pruned_loss=0.05459, over 4799.00 frames.], tot_loss[loss=0.169, simple_loss=0.2364, pruned_loss=0.05075, over 971243.63 frames.], batch size: 17, lr: 6.30e-04
2022-05-04 10:19:04,306 INFO [train.py:715] (4/8) Epoch 2, batch 31750, loss[loss=0.1286, simple_loss=0.2034, pruned_loss=0.02691, over 4759.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2357, pruned_loss=0.05061, over 970462.50 frames.], batch size: 14, lr: 6.30e-04
2022-05-04 10:19:44,140 INFO [train.py:715] (4/8) Epoch 2, batch 31800, loss[loss=0.1797, simple_loss=0.2521, pruned_loss=0.05369, over 4978.00 frames.], tot_loss[loss=0.1685, simple_loss=0.2356, pruned_loss=0.05068, over 970864.50 frames.], batch size: 31, lr: 6.30e-04
2022-05-04 10:20:23,463 INFO [train.py:715] (4/8) Epoch 2, batch 31850, loss[loss=0.159, simple_loss=0.2258, pruned_loss=0.04615, over 4778.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2347, pruned_loss=0.05043, over 971459.83 frames.], batch size: 14, lr: 6.29e-04
2022-05-04 10:21:02,955 INFO [train.py:715] (4/8) Epoch 2, batch 31900, loss[loss=0.2057, simple_loss=0.2669, pruned_loss=0.0723, over 4950.00 frames.], tot_loss[loss=0.1679, simple_loss=0.2347, pruned_loss=0.05054, over 971586.53 frames.], batch size: 35, lr: 6.29e-04
2022-05-04 10:21:42,550 INFO [train.py:715] (4/8) Epoch 2, batch 31950, loss[loss=0.1235, simple_loss=0.1885, pruned_loss=0.02922, over 4640.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2348, pruned_loss=0.05043, over 972802.11 frames.], batch size: 13, lr: 6.29e-04
2022-05-04 10:22:21,473 INFO [train.py:715] (4/8) Epoch 2, batch 32000, loss[loss=0.1782, simple_loss=0.2438, pruned_loss=0.05626, over 4915.00 frames.], tot_loss[loss=0.1669, simple_loss=0.234, pruned_loss=0.04991, over 972363.93 frames.], batch size: 18, lr: 6.29e-04
2022-05-04 10:23:01,122 INFO [train.py:715] (4/8) Epoch 2, batch 32050, loss[loss=0.1679, simple_loss=0.2372, pruned_loss=0.04931, over 4755.00 frames.], tot_loss[loss=0.1669, simple_loss=0.234, pruned_loss=0.04993, over 972304.47 frames.], batch size: 19, lr: 6.29e-04
2022-05-04 10:23:41,014 INFO [train.py:715] (4/8) Epoch 2, batch 32100, loss[loss=0.2141, simple_loss=0.2704, pruned_loss=0.07889, over 4889.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2333, pruned_loss=0.04962, over 972828.67 frames.], batch size: 22, lr: 6.29e-04
2022-05-04 10:24:20,301 INFO [train.py:715] (4/8) Epoch 2, batch 32150, loss[loss=0.1324, simple_loss=0.2028, pruned_loss=0.03104, over 4780.00 frames.], tot_loss[loss=0.1659, simple_loss=0.233, pruned_loss=0.04935, over 972987.76 frames.], batch size: 14, lr: 6.29e-04
2022-05-04 10:24:59,275 INFO [train.py:715] (4/8) Epoch 2, batch 32200, loss[loss=0.1808, simple_loss=0.2438, pruned_loss=0.05888, over 4893.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2332, pruned_loss=0.04949, over 972039.72 frames.], batch size: 22, lr: 6.28e-04
2022-05-04 10:25:39,137 INFO [train.py:715] (4/8) Epoch 2, batch 32250, loss[loss=0.165, simple_loss=0.2351, pruned_loss=0.04742, over 4732.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2335, pruned_loss=0.04966, over 972712.24 frames.], batch size: 16, lr: 6.28e-04
2022-05-04 10:26:18,493 INFO [train.py:715] (4/8) Epoch 2, batch 32300, loss[loss=0.1879, simple_loss=0.2589, pruned_loss=0.05847, over 4832.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2333, pruned_loss=0.0496, over 972246.62 frames.], batch size: 15, lr: 6.28e-04
2022-05-04 10:26:57,488 INFO [train.py:715] (4/8) Epoch 2, batch 32350, loss[loss=0.1454, simple_loss=0.2194, pruned_loss=0.03576, over 4952.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2333, pruned_loss=0.04946, over 972570.95 frames.], batch size: 21, lr: 6.28e-04
2022-05-04 10:27:37,323 INFO [train.py:715] (4/8) Epoch 2, batch 32400, loss[loss=0.1916, simple_loss=0.2515, pruned_loss=0.06587, over 4979.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2331, pruned_loss=0.0491, over 972831.96 frames.], batch size: 28, lr: 6.28e-04
2022-05-04 10:28:17,091 INFO [train.py:715] (4/8) Epoch 2, batch 32450, loss[loss=0.1539, simple_loss=0.2286, pruned_loss=0.03957, over 4783.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2333, pruned_loss=0.04927, over 972223.23 frames.], batch size: 18, lr: 6.28e-04
2022-05-04 10:28:56,077 INFO [train.py:715] (4/8) Epoch 2, batch 32500, loss[loss=0.1242, simple_loss=0.1845, pruned_loss=0.03196, over 4689.00 frames.], tot_loss[loss=0.1675, simple_loss=0.2345, pruned_loss=0.05022, over 972722.67 frames.], batch size: 15, lr: 6.27e-04
2022-05-04 10:29:35,591 INFO [train.py:715] (4/8) Epoch 2, batch 32550, loss[loss=0.1725, simple_loss=0.2353, pruned_loss=0.05482, over 4960.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2344, pruned_loss=0.05015, over 972612.36 frames.], batch size: 14, lr: 6.27e-04
2022-05-04 10:30:15,646 INFO [train.py:715] (4/8) Epoch 2, batch 32600, loss[loss=0.1718, simple_loss=0.2423, pruned_loss=0.05067, over 4869.00 frames.], tot_loss[loss=0.168, simple_loss=0.2352, pruned_loss=0.05043, over 972758.45 frames.], batch size: 20, lr: 6.27e-04
2022-05-04 10:30:54,903 INFO [train.py:715] (4/8) Epoch 2, batch 32650, loss[loss=0.232, simple_loss=0.267, pruned_loss=0.0985, over 4845.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2346, pruned_loss=0.05053, over 972215.70 frames.], batch size: 32, lr: 6.27e-04
2022-05-04 10:31:33,745 INFO [train.py:715] (4/8) Epoch 2, batch 32700, loss[loss=0.1584, simple_loss=0.2316, pruned_loss=0.04262, over 4940.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2346, pruned_loss=0.05052, over 972776.23 frames.], batch size: 35, lr: 6.27e-04
2022-05-04 10:32:13,537 INFO [train.py:715] (4/8) Epoch 2, batch 32750, loss[loss=0.1619, simple_loss=0.2376, pruned_loss=0.04312, over 4797.00 frames.], tot_loss[loss=0.1674, simple_loss=0.234, pruned_loss=0.05045, over 972115.60 frames.], batch size: 18, lr: 6.27e-04
2022-05-04 10:32:53,520 INFO [train.py:715] (4/8) Epoch 2, batch 32800, loss[loss=0.198, simple_loss=0.267, pruned_loss=0.06445, over 4813.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2336, pruned_loss=0.04976, over 972168.40 frames.], batch size: 26, lr: 6.27e-04
2022-05-04 10:33:32,248 INFO [train.py:715] (4/8) Epoch 2, batch 32850, loss[loss=0.1613, simple_loss=0.2327, pruned_loss=0.04496, over 4899.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2344, pruned_loss=0.05006, over 972429.86 frames.], batch size: 17, lr: 6.26e-04
2022-05-04 10:34:11,594 INFO [train.py:715] (4/8) Epoch 2, batch 32900, loss[loss=0.1629, simple_loss=0.2326, pruned_loss=0.04664, over 4898.00 frames.], tot_loss[loss=0.168, simple_loss=0.235, pruned_loss=0.05045, over 972407.10 frames.], batch size: 19, lr: 6.26e-04
2022-05-04 10:34:51,510 INFO [train.py:715] (4/8) Epoch 2, batch 32950, loss[loss=0.1366, simple_loss=0.2036, pruned_loss=0.03476, over 4767.00 frames.], tot_loss[loss=0.168, simple_loss=0.2347, pruned_loss=0.05064, over 971667.28 frames.], batch size: 18, lr: 6.26e-04
2022-05-04 10:35:30,091 INFO [train.py:715] (4/8) Epoch 2, batch 33000, loss[loss=0.1569, simple_loss=0.2289, pruned_loss=0.04242, over 4965.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2339, pruned_loss=0.04969, over 971872.49 frames.], batch size: 24, lr: 6.26e-04
2022-05-04 10:35:30,092 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 10:35:38,852 INFO [train.py:742] (4/8) Epoch 2, validation: loss=0.1163, simple_loss=0.2025, pruned_loss=0.01504, over 914524.00 frames.
2022-05-04 10:36:17,839 INFO [train.py:715] (4/8) Epoch 2, batch 33050, loss[loss=0.1791, simple_loss=0.2536, pruned_loss=0.05231, over 4763.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2348, pruned_loss=0.05035, over 972587.17 frames.], batch size: 19, lr: 6.26e-04
2022-05-04 10:36:57,378 INFO [train.py:715] (4/8) Epoch 2, batch 33100, loss[loss=0.176, simple_loss=0.2466, pruned_loss=0.05272, over 4749.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2345, pruned_loss=0.05009, over 972070.73 frames.], batch size: 19, lr: 6.26e-04
2022-05-04 10:37:37,175 INFO [train.py:715] (4/8) Epoch 2, batch 33150, loss[loss=0.1686, simple_loss=0.2378, pruned_loss=0.04973, over 4755.00 frames.], tot_loss[loss=0.1672, simple_loss=0.234, pruned_loss=0.05019, over 972193.84 frames.], batch size: 16, lr: 6.25e-04
2022-05-04 10:38:16,779 INFO [train.py:715] (4/8) Epoch 2, batch 33200, loss[loss=0.18, simple_loss=0.2391, pruned_loss=0.06043, over 4757.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2339, pruned_loss=0.04972, over 971143.82 frames.], batch size: 16, lr: 6.25e-04
2022-05-04 10:38:56,316 INFO [train.py:715] (4/8) Epoch 2, batch 33250, loss[loss=0.1394, simple_loss=0.2072, pruned_loss=0.03582, over 4682.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2338, pruned_loss=0.04972, over 970846.55 frames.], batch size: 15, lr: 6.25e-04
2022-05-04 10:39:35,520 INFO [train.py:715] (4/8) Epoch 2, batch 33300, loss[loss=0.1782, simple_loss=0.2574, pruned_loss=0.04949, over 4795.00 frames.], tot_loss[loss=0.1672, simple_loss=0.2346, pruned_loss=0.04987, over 970938.54 frames.], batch size: 14, lr: 6.25e-04
2022-05-04 10:40:14,692 INFO [train.py:715] (4/8) Epoch 2, batch 33350, loss[loss=0.1719, simple_loss=0.2329, pruned_loss=0.05548, over 4908.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2345, pruned_loss=0.05021, over 971391.83 frames.], batch size: 18, lr: 6.25e-04
2022-05-04 10:40:53,958 INFO [train.py:715] (4/8) Epoch 2, batch 33400, loss[loss=0.2027, simple_loss=0.2638, pruned_loss=0.07082, over 4936.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2342, pruned_loss=0.04977, over 971854.81 frames.], batch size: 39, lr: 6.25e-04
2022-05-04 10:41:33,181 INFO [train.py:715] (4/8) Epoch 2, batch 33450, loss[loss=0.164, simple_loss=0.2444, pruned_loss=0.04181, over 4855.00 frames.], tot_loss[loss=0.166, simple_loss=0.2334, pruned_loss=0.0493, over 972438.24 frames.], batch size: 32, lr: 6.25e-04
2022-05-04 10:42:13,244 INFO [train.py:715] (4/8) Epoch 2, batch 33500, loss[loss=0.1697, simple_loss=0.2395, pruned_loss=0.04991, over 4886.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2341, pruned_loss=0.04959, over 972046.33 frames.], batch size: 22, lr: 6.24e-04
2022-05-04 10:42:52,005 INFO [train.py:715] (4/8) Epoch 2, batch 33550, loss[loss=0.2042, simple_loss=0.2588, pruned_loss=0.07481, over 4690.00 frames.], tot_loss[loss=0.167, simple_loss=0.2345, pruned_loss=0.0498, over 971960.09 frames.], batch size: 15, lr: 6.24e-04
2022-05-04 10:43:31,502 INFO [train.py:715] (4/8) Epoch 2, batch 33600, loss[loss=0.1866, simple_loss=0.2476, pruned_loss=0.06279, over 4754.00 frames.], tot_loss[loss=0.167, simple_loss=0.2346, pruned_loss=0.04966, over 972118.80 frames.], batch size: 16, lr: 6.24e-04
2022-05-04 10:44:11,048 INFO [train.py:715] (4/8) Epoch 2, batch 33650, loss[loss=0.1618, simple_loss=0.2422, pruned_loss=0.04073, over 4895.00 frames.], tot_loss[loss=0.1661, simple_loss=0.234, pruned_loss=0.04911, over 971645.74 frames.], batch size: 17, lr: 6.24e-04
2022-05-04 10:44:50,485 INFO [train.py:715] (4/8) Epoch 2, batch 33700, loss[loss=0.1766, simple_loss=0.2516, pruned_loss=0.05074, over 4759.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2339, pruned_loss=0.04886, over 971527.85 frames.], batch size: 19, lr: 6.24e-04
2022-05-04 10:45:29,903 INFO [train.py:715] (4/8) Epoch 2, batch 33750, loss[loss=0.1571, simple_loss=0.2255, pruned_loss=0.04432, over 4980.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2341, pruned_loss=0.04888, over 971457.07 frames.], batch size: 28, lr: 6.24e-04
2022-05-04 10:46:09,308 INFO [train.py:715] (4/8) Epoch 2, batch 33800, loss[loss=0.2127, simple_loss=0.2746, pruned_loss=0.07541, over 4789.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2341, pruned_loss=0.04907, over 972196.37 frames.], batch size: 21, lr: 6.23e-04
2022-05-04 10:46:49,487 INFO [train.py:715] (4/8) Epoch 2, batch 33850, loss[loss=0.1651, simple_loss=0.2344, pruned_loss=0.04792, over 4940.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2358, pruned_loss=0.05025, over 972314.95 frames.], batch size: 23, lr: 6.23e-04
2022-05-04 10:47:28,883 INFO [train.py:715] (4/8) Epoch 2, batch 33900, loss[loss=0.1505, simple_loss=0.2313, pruned_loss=0.03483, over 4953.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2351, pruned_loss=0.04977, over 971842.70 frames.], batch size: 39, lr: 6.23e-04
2022-05-04 10:48:08,027 INFO [train.py:715] (4/8) Epoch 2, batch 33950, loss[loss=0.1586, simple_loss=0.2297, pruned_loss=0.04381, over 4870.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2347, pruned_loss=0.04946, over 971583.51 frames.], batch size: 16, lr: 6.23e-04
2022-05-04 10:48:47,951 INFO [train.py:715] (4/8) Epoch 2, batch 34000, loss[loss=0.142, simple_loss=0.2175, pruned_loss=0.03322, over 4815.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2353, pruned_loss=0.05008, over 972351.32 frames.], batch size: 27, lr: 6.23e-04
2022-05-04 10:49:27,580 INFO [train.py:715] (4/8) Epoch 2, batch 34050, loss[loss=0.2054, simple_loss=0.271, pruned_loss=0.06984, over 4812.00 frames.], tot_loss[loss=0.1682, simple_loss=0.2356, pruned_loss=0.05045, over 972778.42 frames.], batch size: 26, lr: 6.23e-04
2022-05-04 10:50:07,045 INFO [train.py:715] (4/8) Epoch 2, batch 34100, loss[loss=0.1849, simple_loss=0.2364, pruned_loss=0.06674, over 4776.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2361, pruned_loss=0.05078, over 972679.76 frames.], batch size: 12, lr: 6.23e-04
2022-05-04 10:50:46,458 INFO [train.py:715] (4/8) Epoch 2, batch 34150, loss[loss=0.1389, simple_loss=0.2137, pruned_loss=0.03205, over 4946.00 frames.], tot_loss[loss=0.1688, simple_loss=0.2364, pruned_loss=0.05061, over 972360.45 frames.], batch size: 29, lr: 6.22e-04
2022-05-04 10:51:26,744 INFO [train.py:715] (4/8) Epoch 2, batch 34200, loss[loss=0.142, simple_loss=0.2067, pruned_loss=0.03864, over 4982.00 frames.], tot_loss[loss=0.1686, simple_loss=0.236, pruned_loss=0.05061, over 972350.85 frames.], batch size: 14, lr: 6.22e-04
2022-05-04 10:52:06,316 INFO [train.py:715] (4/8) Epoch 2, batch 34250, loss[loss=0.1971, simple_loss=0.2717, pruned_loss=0.06124, over 4837.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2349, pruned_loss=0.04996, over 972344.32 frames.], batch size: 13, lr: 6.22e-04
2022-05-04 10:52:45,480 INFO [train.py:715] (4/8) Epoch 2, batch 34300, loss[loss=0.1986, simple_loss=0.2664, pruned_loss=0.06542, over 4836.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2347, pruned_loss=0.04994, over 972947.85 frames.], batch size: 15, lr: 6.22e-04
2022-05-04 10:53:25,366 INFO [train.py:715] (4/8) Epoch 2, batch 34350, loss[loss=0.1932, simple_loss=0.2633, pruned_loss=0.06152, over 4927.00 frames.], tot_loss[loss=0.1677, simple_loss=0.2349, pruned_loss=0.05018, over 973570.45 frames.], batch size: 18, lr: 6.22e-04
2022-05-04 10:54:07,390 INFO [train.py:715] (4/8) Epoch 2, batch 34400, loss[loss=0.1375, simple_loss=0.2005, pruned_loss=0.03719, over 4830.00 frames.], tot_loss[loss=0.1676, simple_loss=0.2349, pruned_loss=0.05016, over 973408.34 frames.], batch size: 13, lr: 6.22e-04
2022-05-04 10:54:46,513 INFO [train.py:715] (4/8) Epoch 2, batch 34450, loss[loss=0.1502, simple_loss=0.2201, pruned_loss=0.04008, over 4970.00 frames.], tot_loss[loss=0.1673, simple_loss=0.235, pruned_loss=0.04976, over 973045.85 frames.], batch size: 15, lr: 6.22e-04
2022-05-04 10:55:25,437 INFO [train.py:715] (4/8) Epoch 2, batch 34500, loss[loss=0.1631, simple_loss=0.2386, pruned_loss=0.04383, over 4820.00 frames.], tot_loss[loss=0.1684, simple_loss=0.2357, pruned_loss=0.05058, over 972832.13 frames.], batch size: 25, lr: 6.21e-04
2022-05-04 10:56:05,346 INFO [train.py:715] (4/8) Epoch 2, batch 34550, loss[loss=0.1794, simple_loss=0.2471, pruned_loss=0.05587, over 4976.00 frames.], tot_loss[loss=0.1701, simple_loss=0.2372, pruned_loss=0.05153, over 972075.96 frames.], batch size: 15, lr: 6.21e-04
2022-05-04 10:56:44,132 INFO [train.py:715] (4/8) Epoch 2, batch 34600, loss[loss=0.1619, simple_loss=0.2289, pruned_loss=0.04743, over 4991.00 frames.], tot_loss[loss=0.1678, simple_loss=0.2351, pruned_loss=0.0502, over 972505.92 frames.], batch size: 16, lr: 6.21e-04
2022-05-04 10:57:23,173 INFO [train.py:715] (4/8) Epoch 2, batch 34650, loss[loss=0.1818, simple_loss=0.2448, pruned_loss=0.05939, over 4767.00 frames.], tot_loss[loss=0.1671, simple_loss=0.2344, pruned_loss=0.04993, over 971677.66 frames.], batch size: 18, lr: 6.21e-04
2022-05-04 10:58:02,538 INFO [train.py:715] (4/8) Epoch 2, batch 34700, loss[loss=0.1822, simple_loss=0.2563, pruned_loss=0.05407, over 4810.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2347, pruned_loss=0.05003, over 971496.44 frames.], batch size: 25, lr: 6.21e-04
2022-05-04 10:58:40,563 INFO [train.py:715] (4/8) Epoch 2, batch 34750, loss[loss=0.2237, simple_loss=0.2782, pruned_loss=0.08456, over 4793.00 frames.], tot_loss[loss=0.168, simple_loss=0.2352, pruned_loss=0.05036, over 971728.01 frames.], batch size: 14, lr: 6.21e-04
2022-05-04 10:59:17,104 INFO [train.py:715] (4/8) Epoch 2, batch 34800, loss[loss=0.1459, simple_loss=0.2184, pruned_loss=0.03676, over 4778.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2337, pruned_loss=0.04994, over 971110.85 frames.], batch size: 12, lr: 6.20e-04
2022-05-04 11:00:07,064 INFO [train.py:715] (4/8) Epoch 3, batch 0, loss[loss=0.1534, simple_loss=0.2276, pruned_loss=0.03959, over 4883.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2276, pruned_loss=0.03959, over 4883.00 frames.], batch size: 22, lr: 5.87e-04
2022-05-04 11:00:45,739 INFO [train.py:715] (4/8) Epoch 3, batch 50, loss[loss=0.1575, simple_loss=0.2162, pruned_loss=0.04938, over 4746.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2334, pruned_loss=0.04967, over 220073.88 frames.], batch size: 12, lr: 5.87e-04
2022-05-04 11:01:25,675 INFO [train.py:715] (4/8) Epoch 3, batch 100, loss[loss=0.1653, simple_loss=0.2361, pruned_loss=0.04724, over 4806.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2332, pruned_loss=0.0503, over 386011.94 frames.], batch size: 21, lr: 5.87e-04
2022-05-04 11:02:05,240 INFO [train.py:715] (4/8) Epoch 3, batch 150, loss[loss=0.1885, simple_loss=0.2472, pruned_loss=0.06491, over 4897.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2343, pruned_loss=0.05029, over 516438.02 frames.], batch size: 39, lr: 5.86e-04
2022-05-04 11:02:44,384 INFO [train.py:715] (4/8) Epoch 3, batch 200, loss[loss=0.1713, simple_loss=0.2366, pruned_loss=0.05294, over 4932.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2344, pruned_loss=0.05007, over 618035.94 frames.], batch size: 18, lr: 5.86e-04
2022-05-04 11:03:23,629 INFO [train.py:715] (4/8) Epoch 3, batch 250, loss[loss=0.1467, simple_loss=0.224, pruned_loss=0.03467, over 4947.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2347, pruned_loss=0.04949, over 696168.39 frames.], batch size: 29, lr: 5.86e-04
2022-05-04 11:04:03,633 INFO [train.py:715] (4/8) Epoch 3, batch 300, loss[loss=0.199, simple_loss=0.2686, pruned_loss=0.06473, over 4892.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2339, pruned_loss=0.04861, over 756799.77 frames.], batch size: 19, lr: 5.86e-04
2022-05-04 11:04:42,644 INFO [train.py:715] (4/8) Epoch 3, batch 350, loss[loss=0.1891, simple_loss=0.2418, pruned_loss=0.06818, over 4955.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2351, pruned_loss=0.04929, over 803963.96 frames.], batch size: 35, lr: 5.86e-04
2022-05-04 11:05:21,844 INFO [train.py:715] (4/8) Epoch 3, batch 400, loss[loss=0.1666, simple_loss=0.2393, pruned_loss=0.04692, over 4918.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2347, pruned_loss=0.04944, over 841785.53 frames.], batch size: 18, lr: 5.86e-04
2022-05-04 11:06:01,611 INFO [train.py:715] (4/8) Epoch 3, batch 450, loss[loss=0.169, simple_loss=0.2442, pruned_loss=0.04687, over 4805.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2345, pruned_loss=0.04943, over 871196.38 frames.], batch size: 15, lr: 5.86e-04
2022-05-04 11:06:41,122 INFO [train.py:715] (4/8) Epoch 3, batch 500, loss[loss=0.1448, simple_loss=0.2142, pruned_loss=0.03768, over 4898.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2333, pruned_loss=0.04878, over 892916.01 frames.], batch size: 23, lr: 5.85e-04
2022-05-04 11:07:20,466 INFO [train.py:715] (4/8) Epoch 3, batch 550, loss[loss=0.1715, simple_loss=0.2302, pruned_loss=0.05641, over 4966.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2345, pruned_loss=0.04967, over 910263.45 frames.], batch size: 21, lr: 5.85e-04
2022-05-04 11:07:59,337 INFO [train.py:715] (4/8) Epoch 3, batch 600, loss[loss=0.1255, simple_loss=0.2017, pruned_loss=0.02463, over 4750.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2339, pruned_loss=0.04923, over 923350.76 frames.], batch size: 16, lr: 5.85e-04
2022-05-04 11:08:39,295 INFO [train.py:715] (4/8) Epoch 3, batch 650, loss[loss=0.1361, simple_loss=0.2041, pruned_loss=0.03401, over 4922.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2335, pruned_loss=0.04908, over 933224.16 frames.], batch size: 23, lr: 5.85e-04
2022-05-04 11:09:18,635 INFO [train.py:715] (4/8) Epoch 3, batch 700, loss[loss=0.1596, simple_loss=0.2233, pruned_loss=0.04802, over 4829.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2339, pruned_loss=0.04961, over 942025.59 frames.], batch size: 27, lr: 5.85e-04
2022-05-04 11:09:57,738 INFO [train.py:715] (4/8) Epoch 3, batch 750, loss[loss=0.1563, simple_loss=0.2246, pruned_loss=0.04398, over 4834.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2333, pruned_loss=0.04909, over 948462.58 frames.], batch size: 30, lr: 5.85e-04
2022-05-04 11:10:37,302 INFO [train.py:715] (4/8) Epoch 3, batch 800, loss[loss=0.1539, simple_loss=0.2356, pruned_loss=0.03616, over 4805.00 frames.], tot_loss[loss=0.1663, simple_loss=0.234, pruned_loss=0.0493, over 953819.32 frames.], batch size: 21, lr: 5.85e-04
2022-05-04 11:11:17,440 INFO [train.py:715] (4/8) Epoch 3, batch 850, loss[loss=0.1394, simple_loss=0.2009, pruned_loss=0.03897, over 4791.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2337, pruned_loss=0.04899, over 958181.76 frames.], batch size: 14, lr: 5.84e-04
2022-05-04 11:11:56,827 INFO [train.py:715] (4/8) Epoch 3, batch 900, loss[loss=0.1475, simple_loss=0.215, pruned_loss=0.03996, over 4825.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2331, pruned_loss=0.04896, over 961129.65 frames.], batch size: 26, lr: 5.84e-04
2022-05-04 11:12:35,438 INFO [train.py:715] (4/8) Epoch 3, batch 950, loss[loss=0.1728, simple_loss=0.2302, pruned_loss=0.05773, over 4829.00 frames.], tot_loss[loss=0.1657, simple_loss=0.233, pruned_loss=0.04921, over 963118.21 frames.], batch size: 27, lr: 5.84e-04
2022-05-04 11:13:15,423 INFO [train.py:715] (4/8) Epoch 3, batch 1000, loss[loss=0.1613, simple_loss=0.2254, pruned_loss=0.04858, over 4858.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2327, pruned_loss=0.04943, over 965552.83 frames.], batch size: 20, lr: 5.84e-04
2022-05-04 11:13:55,092 INFO [train.py:715] (4/8) Epoch 3, batch 1050, loss[loss=0.1693, simple_loss=0.2341, pruned_loss=0.05228, over 4907.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2323, pruned_loss=0.04922, over 966680.92 frames.], batch size: 39, lr: 5.84e-04
2022-05-04 11:14:34,003 INFO [train.py:715] (4/8) Epoch 3, batch 1100, loss[loss=0.1759, simple_loss=0.2406, pruned_loss=0.05563, over 4915.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2326, pruned_loss=0.04891, over 968429.64 frames.], batch size: 17, lr: 5.84e-04
2022-05-04 11:15:12,875 INFO [train.py:715] (4/8) Epoch 3, batch 1150, loss[loss=0.1728, simple_loss=0.2463, pruned_loss=0.04967, over 4904.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2335, pruned_loss=0.04952, over 969559.43 frames.], batch size: 19, lr: 5.84e-04
2022-05-04 11:15:52,682 INFO [train.py:715] (4/8) Epoch 3, batch 1200, loss[loss=0.1639, simple_loss=0.2271, pruned_loss=0.05036, over 4793.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2335, pruned_loss=0.04956, over 969683.95 frames.], batch size: 14, lr: 5.83e-04
2022-05-04 11:16:31,656 INFO [train.py:715] (4/8) Epoch 3, batch 1250, loss[loss=0.1806, simple_loss=0.2585, pruned_loss=0.05134, over 4954.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2335, pruned_loss=0.04993, over 970586.87 frames.], batch size: 39, lr: 5.83e-04
2022-05-04 11:17:10,163 INFO [train.py:715] (4/8) Epoch 3, batch 1300, loss[loss=0.19, simple_loss=0.2393, pruned_loss=0.07034, over 4838.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2334, pruned_loss=0.04951, over 971453.95 frames.], batch size: 15, lr: 5.83e-04
2022-05-04 11:17:49,722 INFO [train.py:715] (4/8) Epoch 3, batch 1350, loss[loss=0.1313, simple_loss=0.2043, pruned_loss=0.02912, over 4971.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2332, pruned_loss=0.04928, over 971354.19 frames.], batch size: 14, lr: 5.83e-04
2022-05-04 11:18:29,002 INFO [train.py:715] (4/8) Epoch 3, batch 1400, loss[loss=0.1792, simple_loss=0.2447, pruned_loss=0.05685, over 4987.00 frames.], tot_loss[loss=0.1665, simple_loss=0.2338, pruned_loss=0.0496, over 972068.80 frames.], batch size: 14, lr: 5.83e-04
2022-05-04 11:19:07,864 INFO [train.py:715] (4/8) Epoch 3, batch 1450, loss[loss=0.2139, simple_loss=0.2725, pruned_loss=0.07767, over 4881.00 frames.], tot_loss[loss=0.1667, simple_loss=0.2341, pruned_loss=0.04966, over 971795.17 frames.], batch size: 16, lr: 5.83e-04
2022-05-04 11:19:46,420 INFO [train.py:715] (4/8) Epoch 3, batch 1500, loss[loss=0.1748, simple_loss=0.24, pruned_loss=0.05486, over 4943.00 frames.], tot_loss[loss=0.167, simple_loss=0.2345, pruned_loss=0.04973, over 972154.85 frames.], batch size: 21, lr: 5.83e-04
2022-05-04 11:20:26,148 INFO [train.py:715] (4/8) Epoch 3, batch 1550, loss[loss=0.1725, simple_loss=0.2507, pruned_loss=0.04708, over 4893.00 frames.], tot_loss[loss=0.1663, simple_loss=0.2343, pruned_loss=0.04918, over 971518.86 frames.], batch size: 22, lr: 5.83e-04
2022-05-04 11:21:05,411 INFO [train.py:715] (4/8) Epoch 3, batch 1600, loss[loss=0.1777, simple_loss=0.2391, pruned_loss=0.05811, over 4931.00 frames.], tot_loss[loss=0.1669, simple_loss=0.2348, pruned_loss=0.04952, over 971915.31 frames.], batch size: 18, lr: 5.82e-04
2022-05-04 11:21:43,529 INFO [train.py:715] (4/8) Epoch 3, batch 1650, loss[loss=0.1835, simple_loss=0.2546, pruned_loss=0.05622, over 4923.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2333, pruned_loss=0.04887, over 972021.28 frames.], batch size: 18, lr: 5.82e-04
2022-05-04 11:22:22,779 INFO [train.py:715] (4/8) Epoch 3, batch 1700, loss[loss=0.2099, simple_loss=0.283, pruned_loss=0.06836, over 4927.00 frames.], tot_loss[loss=0.1661, simple_loss=0.2338, pruned_loss=0.04918, over 972220.36 frames.], batch size: 23, lr: 5.82e-04
2022-05-04 11:23:02,318 INFO [train.py:715] (4/8) Epoch 3, batch 1750, loss[loss=0.1569, simple_loss=0.2267, pruned_loss=0.04354, over 4772.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2323, pruned_loss=0.04831, over 972216.44 frames.], batch size: 18, lr: 5.82e-04
2022-05-04 11:23:41,619 INFO [train.py:715] (4/8) Epoch 3, batch 1800, loss[loss=0.1652, simple_loss=0.2302, pruned_loss=0.05009, over 4785.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2316, pruned_loss=0.04824, over 971666.70 frames.], batch size: 14, lr: 5.82e-04
2022-05-04 11:24:20,319 INFO [train.py:715] (4/8) Epoch 3, batch 1850, loss[loss=0.1786, simple_loss=0.2463, pruned_loss=0.05546, over 4944.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2317, pruned_loss=0.0483, over 971594.85 frames.], batch size: 23, lr: 5.82e-04
2022-05-04 11:25:00,294 INFO [train.py:715] (4/8) Epoch 3, batch 1900, loss[loss=0.1702, simple_loss=0.2414, pruned_loss=0.04951, over 4779.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2323, pruned_loss=0.04829, over 970801.42 frames.], batch size: 18, lr: 5.82e-04
2022-05-04 11:25:39,886 INFO [train.py:715] (4/8) Epoch 3, batch 1950, loss[loss=0.1434, simple_loss=0.2154, pruned_loss=0.03569, over 4926.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2331, pruned_loss=0.04871, over 971576.04 frames.], batch size: 18, lr: 5.81e-04
2022-05-04 11:26:18,803 INFO [train.py:715] (4/8) Epoch 3, batch 2000, loss[loss=0.1601, simple_loss=0.242, pruned_loss=0.03907, over 4761.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2333, pruned_loss=0.0487, over 971755.89 frames.], batch size: 14, lr: 5.81e-04
2022-05-04 11:26:58,011 INFO [train.py:715] (4/8) Epoch 3, batch 2050, loss[loss=0.1536, simple_loss=0.2329, pruned_loss=0.03716, over 4955.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2338, pruned_loss=0.04925, over 971924.17 frames.], batch size: 29, lr: 5.81e-04
2022-05-04 11:27:37,795 INFO [train.py:715] (4/8) Epoch 3, batch 2100, loss[loss=0.1904, simple_loss=0.2477, pruned_loss=0.06656, over 4989.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2318, pruned_loss=0.04848, over 972211.45 frames.], batch size: 31, lr: 5.81e-04
2022-05-04 11:28:17,048 INFO [train.py:715] (4/8) Epoch 3, batch 2150, loss[loss=0.1855, simple_loss=0.2503, pruned_loss=0.06036, over 4784.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2326, pruned_loss=0.04938, over 971767.93 frames.], batch size: 18, lr: 5.81e-04
2022-05-04 11:28:55,720 INFO [train.py:715] (4/8) Epoch 3, batch 2200, loss[loss=0.1659, simple_loss=0.2305, pruned_loss=0.05066, over 4976.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2327, pruned_loss=0.04931, over 972929.13 frames.], batch size: 28, lr: 5.81e-04
2022-05-04 11:29:35,101 INFO [train.py:715] (4/8) Epoch 3, batch 2250, loss[loss=0.2016, simple_loss=0.2699, pruned_loss=0.06662, over 4828.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2332, pruned_loss=0.04918, over 973037.71 frames.], batch size: 15, lr: 5.81e-04
2022-05-04 11:30:14,520 INFO [train.py:715] (4/8) Epoch 3, batch 2300, loss[loss=0.1289, simple_loss=0.1916, pruned_loss=0.03309, over 4799.00 frames.], tot_loss[loss=0.1668, simple_loss=0.2341, pruned_loss=0.04978, over 973278.82 frames.], batch size: 14, lr: 5.80e-04
2022-05-04 11:30:53,578 INFO [train.py:715] (4/8) Epoch 3, batch 2350, loss[loss=0.1459, simple_loss=0.1972, pruned_loss=0.04732, over 4789.00 frames.], tot_loss[loss=0.1662, simple_loss=0.2335, pruned_loss=0.04946, over 973600.89 frames.], batch size: 12, lr: 5.80e-04
2022-05-04 11:31:32,372 INFO [train.py:715] (4/8) Epoch 3, batch 2400, loss[loss=0.1599, simple_loss=0.2337, pruned_loss=0.043, over 4978.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2329, pruned_loss=0.04933, over 972801.02 frames.], batch size: 28, lr: 5.80e-04
2022-05-04 11:32:12,610 INFO [train.py:715] (4/8) Epoch 3, batch 2450, loss[loss=0.142, simple_loss=0.2198, pruned_loss=0.03209, over 4779.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2325, pruned_loss=0.04892, over 973292.97 frames.], batch size: 17, lr: 5.80e-04
2022-05-04 11:32:51,963 INFO [train.py:715] (4/8) Epoch 3, batch 2500, loss[loss=0.1733, simple_loss=0.2375, pruned_loss=0.05452, over 4752.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2325, pruned_loss=0.04889, over 972712.48 frames.], batch size: 16, lr: 5.80e-04
2022-05-04 11:33:30,787 INFO [train.py:715] (4/8) Epoch 3, batch 2550, loss[loss=0.1437, simple_loss=0.212, pruned_loss=0.0377, over 4981.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2331, pruned_loss=0.04878, over 972344.02 frames.], batch size: 15, lr: 5.80e-04
2022-05-04 11:34:11,445 INFO [train.py:715] (4/8) Epoch 3, batch 2600, loss[loss=0.2075, simple_loss=0.26, pruned_loss=0.07748, over 4769.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2339, pruned_loss=0.04898, over 971868.82 frames.], batch size: 14, lr: 5.80e-04
2022-05-04 11:34:51,560 INFO [train.py:715] (4/8) Epoch 3, batch 2650, loss[loss=0.1513, simple_loss=0.2327, pruned_loss=0.03498, over 4878.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2321, pruned_loss=0.0481, over 970924.26 frames.], batch size: 16, lr: 5.80e-04
2022-05-04 11:35:30,754 INFO [train.py:715] (4/8) Epoch 3, batch 2700, loss[loss=0.1504, simple_loss=0.2154, pruned_loss=0.0427, over 4747.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2326, pruned_loss=0.04809, over 971122.97 frames.], batch size: 12, lr: 5.79e-04
2022-05-04 11:36:10,255 INFO [train.py:715] (4/8) Epoch 3, batch 2750, loss[loss=0.1319, simple_loss=0.2042, pruned_loss=0.02982, over 4754.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2312, pruned_loss=0.04768, over 970419.69 frames.], batch size: 16, lr: 5.79e-04
2022-05-04 11:36:50,508 INFO [train.py:715] (4/8) Epoch 3, batch 2800, loss[loss=0.14, simple_loss=0.217, pruned_loss=0.03151, over 4947.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2316, pruned_loss=0.04791, over 970831.59 frames.], batch size: 35, lr: 5.79e-04
2022-05-04 11:37:29,792 INFO [train.py:715] (4/8) Epoch 3, batch 2850, loss[loss=0.1631, simple_loss=0.2338, pruned_loss=0.04621, over 4827.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2326, pruned_loss=0.04825, over 971072.43 frames.], batch size: 25, lr: 5.79e-04
2022-05-04 11:38:08,469 INFO [train.py:715] (4/8) Epoch 3, batch 2900, loss[loss=0.1471, simple_loss=0.2174, pruned_loss=0.0384, over 4751.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2319, pruned_loss=0.04793, over 970642.25 frames.], batch size: 19, lr: 5.79e-04
2022-05-04 11:38:48,426 INFO [train.py:715] (4/8) Epoch 3, batch 2950, loss[loss=0.1747, simple_loss=0.2345, pruned_loss=0.05745, over 4926.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2324, pruned_loss=0.04805, over 971233.97 frames.], batch size: 18, lr: 5.79e-04
2022-05-04 11:39:28,055 INFO [train.py:715] (4/8) Epoch 3, batch 3000, loss[loss=0.1903, simple_loss=0.2527, pruned_loss=0.06397, over 4941.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2325, pruned_loss=0.04815, over 971742.76 frames.], batch size: 18, lr: 5.79e-04
2022-05-04 11:39:28,056 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 11:39:36,789 INFO [train.py:742] (4/8) Epoch 3, validation: loss=0.1153, simple_loss=0.2015, pruned_loss=0.0146, over 914524.00 frames.
2022-05-04 11:40:16,885 INFO [train.py:715] (4/8) Epoch 3, batch 3050, loss[loss=0.1503, simple_loss=0.2231, pruned_loss=0.03877, over 4936.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2335, pruned_loss=0.04907, over 972528.21 frames.], batch size: 18, lr: 5.78e-04
2022-05-04 11:40:55,666 INFO [train.py:715] (4/8) Epoch 3, batch 3100, loss[loss=0.1565, simple_loss=0.2317, pruned_loss=0.04065, over 4816.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2337, pruned_loss=0.04888, over 972802.53 frames.], batch size: 27, lr: 5.78e-04
2022-05-04 11:41:35,054 INFO [train.py:715] (4/8) Epoch 3, batch 3150, loss[loss=0.1426, simple_loss=0.2058, pruned_loss=0.03969, over 4732.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2331, pruned_loss=0.04833, over 972625.62 frames.], batch size: 12, lr: 5.78e-04
2022-05-04 11:42:14,854 INFO [train.py:715] (4/8) Epoch 3, batch 3200, loss[loss=0.1648, simple_loss=0.2414, pruned_loss=0.04412, over 4988.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2327, pruned_loss=0.04773, over 972061.38 frames.], batch size: 26, lr: 5.78e-04
2022-05-04 11:42:54,655 INFO [train.py:715] (4/8) Epoch 3, batch 3250, loss[loss=0.1956, simple_loss=0.274, pruned_loss=0.05858, over 4922.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2334, pruned_loss=0.04808, over 973063.75 frames.], batch size: 23, lr: 5.78e-04
2022-05-04 11:43:33,194 INFO [train.py:715] (4/8) Epoch 3, batch 3300, loss[loss=0.1673, simple_loss=0.2411, pruned_loss=0.0467, over 4991.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2337, pruned_loss=0.04829, over 973300.22 frames.], batch size: 15, lr: 5.78e-04
2022-05-04 11:44:13,008 INFO [train.py:715] (4/8) Epoch 3, batch 3350, loss[loss=0.1832, simple_loss=0.2326, pruned_loss=0.06685, over 4794.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2333, pruned_loss=0.04803, over 973130.75 frames.], batch size: 14, lr: 5.78e-04
2022-05-04 11:44:52,484 INFO [train.py:715] (4/8) Epoch 3, batch 3400, loss[loss=0.1442, simple_loss=0.2141, pruned_loss=0.03719, over 4993.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2334, pruned_loss=0.04845, over 973960.91 frames.], batch size: 28, lr: 5.77e-04
2022-05-04 11:45:31,169 INFO [train.py:715] (4/8) Epoch 3, batch 3450, loss[loss=0.1547, simple_loss=0.2262, pruned_loss=0.04157, over 4977.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2337, pruned_loss=0.04859, over 973655.26 frames.], batch size: 15, lr: 5.77e-04
2022-05-04 11:46:10,504 INFO [train.py:715] (4/8) Epoch 3, batch 3500, loss[loss=0.1531, simple_loss=0.2275, pruned_loss=0.03933, over 4939.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2337, pruned_loss=0.04895, over 973385.22 frames.], batch size: 21, lr: 5.77e-04
2022-05-04 11:46:50,808 INFO [train.py:715] (4/8) Epoch 3, batch 3550, loss[loss=0.2059, simple_loss=0.2802, pruned_loss=0.06577, over 4922.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2326, pruned_loss=0.04809, over 972846.17 frames.], batch size: 23, lr: 5.77e-04
2022-05-04 11:47:30,666 INFO [train.py:715] (4/8) Epoch 3, batch 3600, loss[loss=0.1783, simple_loss=0.2528, pruned_loss=0.05194, over 4946.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2315, pruned_loss=0.04736, over 972310.60 frames.], batch size: 15, lr: 5.77e-04
2022-05-04 11:48:09,899 INFO [train.py:715] (4/8) Epoch 3, batch 3650, loss[loss=0.1284, simple_loss=0.202, pruned_loss=0.02737, over 4745.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2308, pruned_loss=0.04731, over 972196.15 frames.], batch size: 16, lr: 5.77e-04
2022-05-04 11:48:49,623 INFO [train.py:715] (4/8) Epoch 3, batch 3700, loss[loss=0.1452, simple_loss=0.2103, pruned_loss=0.04002, over 4761.00 frames.], tot_loss[loss=0.162, simple_loss=0.2304, pruned_loss=0.04686, over 972455.30 frames.], batch size: 19, lr: 5.77e-04
2022-05-04 11:49:29,643 INFO [train.py:715] (4/8) Epoch 3, batch 3750, loss[loss=0.151, simple_loss=0.2329, pruned_loss=0.03457, over 4846.00 frames.], tot_loss[loss=0.1628, simple_loss=0.231, pruned_loss=0.04723, over 973086.71 frames.], batch size: 32, lr: 5.77e-04
2022-05-04 11:50:09,329 INFO [train.py:715] (4/8) Epoch 3, batch 3800, loss[loss=0.1341, simple_loss=0.201, pruned_loss=0.03366, over 4823.00 frames.], tot_loss[loss=0.1628, simple_loss=0.231, pruned_loss=0.04727, over 972336.33 frames.], batch size: 13, lr: 5.76e-04
2022-05-04 11:50:48,711 INFO [train.py:715] (4/8) Epoch 3, batch 3850, loss[loss=0.1635, simple_loss=0.2238, pruned_loss=0.05165, over 4880.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2314, pruned_loss=0.04783, over 972979.21 frames.], batch size: 22, lr: 5.76e-04
2022-05-04 11:51:28,561 INFO [train.py:715] (4/8) Epoch 3, batch 3900, loss[loss=0.1742, simple_loss=0.2384, pruned_loss=0.05501, over 4928.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2314, pruned_loss=0.04823, over 972929.36 frames.], batch size: 39, lr: 5.76e-04
2022-05-04 11:52:08,060 INFO [train.py:715] (4/8) Epoch 3, batch 3950, loss[loss=0.1917, simple_loss=0.2553, pruned_loss=0.06411, over 4765.00 frames.], tot_loss[loss=0.164, simple_loss=0.2316, pruned_loss=0.04819, over 972419.44 frames.], batch size: 14, lr: 5.76e-04
2022-05-04 11:52:47,079 INFO [train.py:715] (4/8) Epoch 3, batch 4000, loss[loss=0.1668, simple_loss=0.2379, pruned_loss=0.04784, over 4976.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2318, pruned_loss=0.04849, over 972418.93 frames.], batch size: 25, lr: 5.76e-04
2022-05-04 11:53:26,526 INFO [train.py:715] (4/8) Epoch 3, batch 4050, loss[loss=0.2019, simple_loss=0.2717, pruned_loss=0.06601, over 4897.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2316, pruned_loss=0.0485, over 972572.32 frames.], batch size: 19, lr: 5.76e-04
2022-05-04 11:54:06,701 INFO [train.py:715] (4/8) Epoch 3, batch 4100, loss[loss=0.1581, simple_loss=0.2342, pruned_loss=0.04103, over 4958.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2314, pruned_loss=0.04847, over 973033.01 frames.], batch size: 35, lr: 5.76e-04
2022-05-04 11:54:45,655 INFO [train.py:715] (4/8) Epoch 3, batch 4150, loss[loss=0.1679, simple_loss=0.2447, pruned_loss=0.04558, over 4828.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2321, pruned_loss=0.04842, over 972227.22 frames.], batch size: 26, lr: 5.76e-04
2022-05-04 11:55:24,491 INFO [train.py:715] (4/8) Epoch 3, batch 4200, loss[loss=0.1569, simple_loss=0.2309, pruned_loss=0.04147, over 4913.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2326, pruned_loss=0.04877, over 972593.69 frames.], batch size: 18, lr: 5.75e-04
2022-05-04 11:56:04,945 INFO [train.py:715] (4/8) Epoch 3, batch 4250, loss[loss=0.1802, simple_loss=0.2569, pruned_loss=0.05174, over 4818.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2324, pruned_loss=0.0483, over 971703.36 frames.], batch size: 25, lr: 5.75e-04
2022-05-04 11:56:44,321 INFO [train.py:715] (4/8) Epoch 3, batch 4300, loss[loss=0.1476, simple_loss=0.2218, pruned_loss=0.03668, over 4809.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2323, pruned_loss=0.04821, over 972056.26 frames.], batch size: 26, lr: 5.75e-04
2022-05-04 11:57:23,798 INFO [train.py:715] (4/8) Epoch 3, batch 4350, loss[loss=0.1575, simple_loss=0.2197, pruned_loss=0.04767, over 4818.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2319, pruned_loss=0.04846, over 972399.46 frames.], batch size: 15, lr: 5.75e-04
2022-05-04 11:58:03,479 INFO [train.py:715] (4/8) Epoch 3, batch 4400, loss[loss=0.1958, simple_loss=0.2522, pruned_loss=0.06972, over 4911.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2323, pruned_loss=0.04855, over 972401.00 frames.], batch size: 19, lr: 5.75e-04
2022-05-04 11:58:43,519 INFO [train.py:715] (4/8) Epoch 3, batch 4450, loss[loss=0.1638, simple_loss=0.2322, pruned_loss=0.04769, over 4891.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2326, pruned_loss=0.04881, over 972646.97 frames.], batch size: 22, lr: 5.75e-04
2022-05-04 11:59:22,566 INFO [train.py:715] (4/8) Epoch 3, batch 4500, loss[loss=0.1613, simple_loss=0.2258, pruned_loss=0.04836, over 4911.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2326, pruned_loss=0.04906, over 972079.14 frames.], batch size: 18, lr: 5.75e-04
2022-05-04 12:00:01,992 INFO [train.py:715] (4/8) Epoch 3, batch 4550, loss[loss=0.155, simple_loss=0.2261, pruned_loss=0.04194, over 4830.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2334, pruned_loss=0.0491, over 971363.94 frames.], batch size: 15, lr: 5.74e-04
2022-05-04 12:00:41,745 INFO [train.py:715] (4/8) Epoch 3, batch 4600, loss[loss=0.1505, simple_loss=0.2266, pruned_loss=0.03716, over 4752.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2328, pruned_loss=0.04854, over 972044.29 frames.], batch size: 16, lr: 5.74e-04
2022-05-04 12:01:21,001 INFO [train.py:715] (4/8) Epoch 3, batch 4650, loss[loss=0.1693, simple_loss=0.2363, pruned_loss=0.05117, over 4754.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2316, pruned_loss=0.04791, over 971722.73 frames.], batch size: 19, lr: 5.74e-04
2022-05-04 12:01:59,931 INFO [train.py:715] (4/8) Epoch 3, batch 4700, loss[loss=0.1356, simple_loss=0.2115, pruned_loss=0.0298, over 4984.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2315, pruned_loss=0.04808, over 971777.58 frames.], batch size: 16, lr: 5.74e-04
2022-05-04 12:02:39,134 INFO [train.py:715] (4/8) Epoch 3, batch 4750, loss[loss=0.1578, simple_loss=0.2271, pruned_loss=0.04429, over 4985.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2322, pruned_loss=0.0482, over 972199.45 frames.], batch size: 14, lr: 5.74e-04
2022-05-04 12:03:18,737 INFO [train.py:715] (4/8) Epoch 3, batch 4800, loss[loss=0.1698, simple_loss=0.2344, pruned_loss=0.05255, over 4942.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2328, pruned_loss=0.04833, over 971844.51 frames.], batch size: 39, lr: 5.74e-04
2022-05-04 12:03:58,123 INFO [train.py:715] (4/8) Epoch 3, batch 4850, loss[loss=0.1287, simple_loss=0.2046, pruned_loss=0.02645, over 4820.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2331, pruned_loss=0.04858, over 972455.46 frames.], batch size: 26, lr: 5.74e-04
2022-05-04 12:04:36,951 INFO [train.py:715] (4/8) Epoch 3, batch 4900, loss[loss=0.1738, simple_loss=0.2432, pruned_loss=0.05219, over 4816.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2324, pruned_loss=0.04801, over 971674.05 frames.], batch size: 25, lr: 5.74e-04
2022-05-04 12:05:16,866 INFO [train.py:715] (4/8) Epoch 3, batch 4950, loss[loss=0.1663, simple_loss=0.2375, pruned_loss=0.0476, over 4910.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2323, pruned_loss=0.04801, over 971843.34 frames.], batch size: 19, lr: 5.73e-04
2022-05-04 12:05:56,314 INFO [train.py:715] (4/8) Epoch 3, batch 5000, loss[loss=0.1703, simple_loss=0.2279, pruned_loss=0.05635, over 4981.00 frames.], tot_loss[loss=0.163, simple_loss=0.2312, pruned_loss=0.04742, over 972224.28 frames.], batch size: 14, lr: 5.73e-04
2022-05-04 12:06:35,119 INFO [train.py:715] (4/8) Epoch 3, batch 5050, loss[loss=0.1692, simple_loss=0.2342, pruned_loss=0.05214, over 4990.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2325, pruned_loss=0.0484, over 971898.99 frames.], batch size: 16, lr: 5.73e-04
2022-05-04 12:07:14,485 INFO [train.py:715] (4/8) Epoch 3, batch 5100, loss[loss=0.1743, simple_loss=0.2478, pruned_loss=0.05038, over 4977.00 frames.], tot_loss[loss=0.1659, simple_loss=0.2335, pruned_loss=0.04917, over 972598.51 frames.], batch size: 24, lr: 5.73e-04
2022-05-04 12:07:54,246 INFO [train.py:715] (4/8) Epoch 3, batch 5150, loss[loss=0.1371, simple_loss=0.2088, pruned_loss=0.03273, over 4735.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2333, pruned_loss=0.04883, over 972485.29 frames.], batch size: 16, lr: 5.73e-04
2022-05-04 12:08:32,989 INFO [train.py:715] (4/8) Epoch 3, batch 5200, loss[loss=0.1964, simple_loss=0.2538, pruned_loss=0.06949, over 4849.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2326, pruned_loss=0.04862, over 971726.57 frames.], batch size: 34, lr: 5.73e-04
2022-05-04 12:09:12,106 INFO [train.py:715] (4/8) Epoch 3, batch 5250, loss[loss=0.199, simple_loss=0.2698, pruned_loss=0.06411, over 4991.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2326, pruned_loss=0.04844, over 971467.31 frames.], batch size: 28, lr: 5.73e-04
2022-05-04 12:09:52,193 INFO [train.py:715] (4/8) Epoch 3, batch 5300, loss[loss=0.1434, simple_loss=0.2157, pruned_loss=0.03557, over 4701.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2322, pruned_loss=0.04761, over 971806.92 frames.], batch size: 15, lr: 5.72e-04
2022-05-04 12:10:31,370 INFO [train.py:715] (4/8) Epoch 3, batch 5350, loss[loss=0.1486, simple_loss=0.224, pruned_loss=0.03663, over 4787.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2331, pruned_loss=0.04777, over 971415.72 frames.], batch size: 14, lr: 5.72e-04
2022-05-04 12:11:10,302 INFO [train.py:715] (4/8) Epoch 3, batch 5400, loss[loss=0.1704, simple_loss=0.2506, pruned_loss=0.04512, over 4964.00 frames.], tot_loss[loss=0.1658, simple_loss=0.234, pruned_loss=0.04879, over 972318.73 frames.], batch size: 35, lr: 5.72e-04
2022-05-04 12:11:49,949 INFO [train.py:715] (4/8) Epoch 3, batch 5450, loss[loss=0.1563, simple_loss=0.2321, pruned_loss=0.04019, over 4879.00 frames.], tot_loss[loss=0.166, simple_loss=0.2343, pruned_loss=0.04878, over 972619.00 frames.], batch size: 19, lr: 5.72e-04
2022-05-04 12:12:30,201 INFO [train.py:715] (4/8) Epoch 3, batch 5500, loss[loss=0.158, simple_loss=0.22, pruned_loss=0.04803, over 4794.00 frames.], tot_loss[loss=0.1661, simple_loss=0.234, pruned_loss=0.04913, over 972139.39 frames.], batch size: 21, lr: 5.72e-04
2022-05-04 12:13:09,478 INFO [train.py:715] (4/8) Epoch 3, batch 5550, loss[loss=0.1894, simple_loss=0.256, pruned_loss=0.0614, over 4891.00 frames.], tot_loss[loss=0.1652, simple_loss=0.2333, pruned_loss=0.04858, over 972280.59 frames.], batch size: 22, lr: 5.72e-04
2022-05-04 12:13:49,876 INFO [train.py:715] (4/8) Epoch 3, batch 5600, loss[loss=0.2006, simple_loss=0.2788, pruned_loss=0.06118, over 4819.00 frames.], tot_loss[loss=0.165, simple_loss=0.2331, pruned_loss=0.0485, over 972352.35 frames.], batch size: 25, lr: 5.72e-04
2022-05-04 12:14:29,645 INFO [train.py:715] (4/8) Epoch 3, batch 5650, loss[loss=0.1973, simple_loss=0.2535, pruned_loss=0.07051, over 4730.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2325, pruned_loss=0.04798, over 971566.93 frames.], batch size: 16, lr: 5.72e-04
2022-05-04 12:15:08,733 INFO [train.py:715] (4/8) Epoch 3, batch 5700, loss[loss=0.1656, simple_loss=0.2338, pruned_loss=0.04866, over 4836.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2323, pruned_loss=0.0477, over 971002.02 frames.], batch size: 15, lr: 5.71e-04
2022-05-04 12:15:48,069 INFO [train.py:715] (4/8) Epoch 3, batch 5750, loss[loss=0.1689, simple_loss=0.2392, pruned_loss=0.04926, over 4855.00 frames.], tot_loss[loss=0.164, simple_loss=0.2323, pruned_loss=0.0478, over 971613.17 frames.], batch size: 20, lr: 5.71e-04
2022-05-04 12:16:27,886 INFO [train.py:715] (4/8) Epoch 3, batch 5800, loss[loss=0.1674, simple_loss=0.2419, pruned_loss=0.0465, over 4897.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2318, pruned_loss=0.04701, over 972328.49 frames.], batch size: 19, lr: 5.71e-04
2022-05-04 12:17:07,625 INFO [train.py:715] (4/8) Epoch 3, batch 5850, loss[loss=0.1991, simple_loss=0.2681, pruned_loss=0.06506, over 4903.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2318, pruned_loss=0.04681, over 972815.22 frames.], batch size: 39, lr: 5.71e-04
2022-05-04 12:17:46,986 INFO [train.py:715] (4/8) Epoch 3, batch 5900, loss[loss=0.1751, simple_loss=0.2396, pruned_loss=0.05526, over 4820.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2309, pruned_loss=0.04644, over 973076.91 frames.], batch size: 27, lr: 5.71e-04
2022-05-04 12:18:26,960 INFO [train.py:715] (4/8) Epoch 3, batch 5950, loss[loss=0.1763, simple_loss=0.2592, pruned_loss=0.04668, over 4777.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2309, pruned_loss=0.04643, over 973031.96 frames.], batch size: 14, lr: 5.71e-04
2022-05-04 12:19:06,643 INFO [train.py:715] (4/8) Epoch 3, batch 6000, loss[loss=0.1615, simple_loss=0.2309, pruned_loss=0.04606, over 4859.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2307, pruned_loss=0.04699, over 973170.44 frames.], batch size: 20, lr: 5.71e-04
2022-05-04 12:19:06,643 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 12:19:15,396 INFO [train.py:742] (4/8) Epoch 3, validation: loss=0.1149, simple_loss=0.2013, pruned_loss=0.01424, over 914524.00 frames.
2022-05-04 12:19:55,208 INFO [train.py:715] (4/8) Epoch 3, batch 6050, loss[loss=0.1737, simple_loss=0.2323, pruned_loss=0.05755, over 4934.00 frames.], tot_loss[loss=0.1635, simple_loss=0.232, pruned_loss=0.0475, over 973538.47 frames.], batch size: 39, lr: 5.71e-04
2022-05-04 12:20:34,637 INFO [train.py:715] (4/8) Epoch 3, batch 6100, loss[loss=0.1595, simple_loss=0.2303, pruned_loss=0.04431, over 4880.00 frames.], tot_loss[loss=0.1642, simple_loss=0.232, pruned_loss=0.04816, over 973201.16 frames.], batch size: 16, lr: 5.70e-04
2022-05-04 12:21:13,560 INFO [train.py:715] (4/8) Epoch 3, batch 6150, loss[loss=0.1789, simple_loss=0.24, pruned_loss=0.05887, over 4909.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2323, pruned_loss=0.04801, over 972448.52 frames.], batch size: 39, lr: 5.70e-04
2022-05-04 12:21:53,159 INFO [train.py:715] (4/8) Epoch 3, batch 6200, loss[loss=0.1287, simple_loss=0.202, pruned_loss=0.02764, over 4717.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2316, pruned_loss=0.04772, over 972598.61 frames.], batch size: 12, lr: 5.70e-04
2022-05-04 12:22:33,153 INFO [train.py:715] (4/8) Epoch 3, batch 6250, loss[loss=0.1476, simple_loss=0.2172, pruned_loss=0.03896, over 4862.00 frames.], tot_loss[loss=0.1636, simple_loss=0.232, pruned_loss=0.0476, over 972588.95 frames.], batch size: 20, lr: 5.70e-04
2022-05-04 12:23:12,503 INFO [train.py:715] (4/8) Epoch 3, batch 6300, loss[loss=0.1604, simple_loss=0.2308, pruned_loss=0.04501, over 4982.00 frames.], tot_loss[loss=0.1634, simple_loss=0.232, pruned_loss=0.04736, over 972407.78 frames.], batch size: 35, lr: 5.70e-04
2022-05-04 12:23:51,736 INFO [train.py:715] (4/8) Epoch 3, batch 6350, loss[loss=0.1644, simple_loss=0.2266, pruned_loss=0.05114, over 4947.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2324, pruned_loss=0.04801, over 972927.52 frames.], batch size: 21, lr: 5.70e-04
2022-05-04 12:24:31,948 INFO [train.py:715] (4/8) Epoch 3, batch 6400, loss[loss=0.1667, simple_loss=0.2238, pruned_loss=0.05482, over 4857.00 frames.], tot_loss[loss=0.1648, simple_loss=0.233, pruned_loss=0.04836, over 973074.50 frames.], batch size: 32, lr: 5.70e-04
2022-05-04 12:25:11,500 INFO [train.py:715] (4/8) Epoch 3, batch 6450, loss[loss=0.181, simple_loss=0.2679, pruned_loss=0.04705, over 4776.00 frames.], tot_loss[loss=0.1671, simple_loss=0.235, pruned_loss=0.04957, over 972249.27 frames.], batch size: 18, lr: 5.70e-04
2022-05-04 12:25:50,479 INFO [train.py:715] (4/8) Epoch 3, batch 6500, loss[loss=0.1759, simple_loss=0.2495, pruned_loss=0.05113, over 4910.00 frames.], tot_loss[loss=0.1673, simple_loss=0.2351, pruned_loss=0.04975, over 972647.32 frames.], batch size: 17, lr: 5.69e-04
2022-05-04 12:26:30,132 INFO [train.py:715] (4/8) Epoch 3, batch 6550, loss[loss=0.1946, simple_loss=0.2664, pruned_loss=0.06137, over 4866.00 frames.], tot_loss[loss=0.167, simple_loss=0.2354, pruned_loss=0.04928, over 972462.54 frames.], batch size: 16, lr: 5.69e-04
2022-05-04 12:27:09,928 INFO [train.py:715] (4/8) Epoch 3, batch 6600, loss[loss=0.1739, simple_loss=0.2485, pruned_loss=0.04966, over 4962.00 frames.], tot_loss[loss=0.1664, simple_loss=0.2351, pruned_loss=0.04885, over 972487.00 frames.], batch size: 21, lr: 5.69e-04
2022-05-04 12:27:49,182 INFO [train.py:715] (4/8) Epoch 3, batch 6650, loss[loss=0.1875, simple_loss=0.2513, pruned_loss=0.06183, over 4819.00 frames.], tot_loss[loss=0.1666, simple_loss=0.2352, pruned_loss=0.04896, over 972396.22 frames.], batch size: 25, lr: 5.69e-04
2022-05-04 12:28:28,359 INFO [train.py:715] (4/8) Epoch 3, batch 6700, loss[loss=0.1811, simple_loss=0.2353, pruned_loss=0.06342, over 4822.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2342, pruned_loss=0.04835, over 972302.93 frames.], batch size: 26, lr: 5.69e-04
2022-05-04 12:29:08,702 INFO [train.py:715] (4/8) Epoch 3, batch 6750, loss[loss=0.143, simple_loss=0.2116, pruned_loss=0.03723, over 4962.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2336, pruned_loss=0.04836, over 972815.68 frames.], batch size: 15, lr: 5.69e-04
2022-05-04 12:29:47,741 INFO [train.py:715] (4/8) Epoch 3, batch 6800, loss[loss=0.2091, simple_loss=0.2741, pruned_loss=0.07206, over 4950.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2336, pruned_loss=0.04834, over 972337.98 frames.], batch size: 21, lr: 5.69e-04
2022-05-04 12:30:27,116 INFO [train.py:715] (4/8) Epoch 3, batch 6850, loss[loss=0.1677, simple_loss=0.238, pruned_loss=0.04873, over 4987.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2326, pruned_loss=0.04806, over 971977.16 frames.], batch size: 25, lr: 5.68e-04
2022-05-04 12:31:06,818 INFO [train.py:715] (4/8) Epoch 3, batch 6900, loss[loss=0.1719, simple_loss=0.2295, pruned_loss=0.05713, over 4704.00 frames.], tot_loss[loss=0.164, simple_loss=0.2323, pruned_loss=0.04781, over 971679.97 frames.], batch size: 15, lr: 5.68e-04
2022-05-04 12:31:46,650 INFO [train.py:715] (4/8) Epoch 3, batch 6950, loss[loss=0.1425, simple_loss=0.2098, pruned_loss=0.03761, over 4870.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2325, pruned_loss=0.04755, over 972279.89 frames.], batch size: 22, lr: 5.68e-04
2022-05-04 12:32:25,806 INFO [train.py:715] (4/8) Epoch 3, batch 7000, loss[loss=0.1417, simple_loss=0.2155, pruned_loss=0.03391, over 4949.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2326, pruned_loss=0.04764, over 971958.26 frames.], batch size: 29, lr: 5.68e-04
2022-05-04 12:33:05,828 INFO [train.py:715] (4/8) Epoch 3, batch 7050, loss[loss=0.141, simple_loss=0.2264, pruned_loss=0.02786, over 4812.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2331, pruned_loss=0.04848, over 971922.82 frames.], batch size: 25, lr: 5.68e-04
2022-05-04 12:33:45,719 INFO [train.py:715] (4/8) Epoch 3, batch 7100, loss[loss=0.1566, simple_loss=0.222, pruned_loss=0.04562, over 4958.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2326, pruned_loss=0.04817, over 971606.31 frames.], batch size: 24, lr: 5.68e-04
2022-05-04 12:34:24,805 INFO [train.py:715] (4/8) Epoch 3, batch 7150, loss[loss=0.1701, simple_loss=0.2253, pruned_loss=0.05747, over 4915.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2318, pruned_loss=0.04788, over 971525.15 frames.], batch size: 39, lr: 5.68e-04
2022-05-04 12:35:04,375 INFO [train.py:715] (4/8) Epoch 3, batch 7200, loss[loss=0.1713, simple_loss=0.236, pruned_loss=0.05325, over 4760.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2315, pruned_loss=0.04751, over 971595.80 frames.], batch size: 17, lr: 5.68e-04
2022-05-04 12:35:44,147 INFO [train.py:715] (4/8) Epoch 3, batch 7250, loss[loss=0.1683, simple_loss=0.2424, pruned_loss=0.04712, over 4900.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2311, pruned_loss=0.0473, over 971635.59 frames.], batch size: 22, lr: 5.67e-04
2022-05-04 12:36:23,544 INFO [train.py:715] (4/8) Epoch 3, batch 7300, loss[loss=0.1498, simple_loss=0.2241, pruned_loss=0.03775, over 4986.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2316, pruned_loss=0.04768, over 972435.05 frames.], batch size: 28, lr: 5.67e-04
2022-05-04 12:37:03,011 INFO [train.py:715] (4/8) Epoch 3, batch 7350, loss[loss=0.1727, simple_loss=0.2461, pruned_loss=0.04965, over 4761.00 frames.], tot_loss[loss=0.164, simple_loss=0.2323, pruned_loss=0.04787, over 972671.30 frames.], batch size: 19, lr: 5.67e-04
2022-05-04 12:37:42,374 INFO [train.py:715] (4/8) Epoch 3, batch 7400, loss[loss=0.1598, simple_loss=0.2402, pruned_loss=0.03972, over 4808.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2326, pruned_loss=0.04859, over 972804.90 frames.], batch size: 21, lr: 5.67e-04
2022-05-04 12:38:22,631 INFO [train.py:715] (4/8) Epoch 3, batch 7450, loss[loss=0.1615, simple_loss=0.2348, pruned_loss=0.0441, over 4984.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2328, pruned_loss=0.04912, over 972148.86 frames.], batch size: 25, lr: 5.67e-04
2022-05-04 12:39:01,777 INFO [train.py:715] (4/8) Epoch 3, batch 7500, loss[loss=0.1259, simple_loss=0.2072, pruned_loss=0.02233, over 4904.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2311, pruned_loss=0.04831, over 972341.90 frames.], batch size: 22, lr: 5.67e-04
2022-05-04 12:39:41,042 INFO [train.py:715] (4/8) Epoch 3, batch 7550, loss[loss=0.1992, simple_loss=0.263, pruned_loss=0.06768, over 4700.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2309, pruned_loss=0.04819, over 971692.11 frames.], batch size: 15, lr: 5.67e-04
2022-05-04 12:40:22,795 INFO [train.py:715] (4/8) Epoch 3, batch 7600, loss[loss=0.2039, simple_loss=0.2512, pruned_loss=0.07827, over 4913.00 frames.], tot_loss[loss=0.165, simple_loss=0.2322, pruned_loss=0.04892, over 972524.42 frames.], batch size: 17, lr: 5.67e-04
2022-05-04 12:41:02,149 INFO [train.py:715] (4/8) Epoch 3, batch 7650, loss[loss=0.2045, simple_loss=0.2705, pruned_loss=0.06927, over 4880.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2323, pruned_loss=0.0487, over 972486.82 frames.], batch size: 16, lr: 5.66e-04
2022-05-04 12:41:41,413 INFO [train.py:715] (4/8) Epoch 3, batch 7700, loss[loss=0.1497, simple_loss=0.2208, pruned_loss=0.03932, over 4819.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2321, pruned_loss=0.04863, over 972204.58 frames.], batch size: 13, lr: 5.66e-04
2022-05-04 12:42:20,881 INFO [train.py:715] (4/8) Epoch 3, batch 7750, loss[loss=0.1529, simple_loss=0.2287, pruned_loss=0.0386, over 4798.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2318, pruned_loss=0.04803, over 972230.03 frames.], batch size: 14, lr: 5.66e-04
2022-05-04 12:43:00,214 INFO [train.py:715] (4/8) Epoch 3, batch 7800, loss[loss=0.1562, simple_loss=0.2217, pruned_loss=0.04541, over 4766.00 frames.], tot_loss[loss=0.1642, simple_loss=0.232, pruned_loss=0.04816, over 971116.61 frames.], batch size: 18, lr: 5.66e-04
2022-05-04 12:43:38,787 INFO [train.py:715] (4/8) Epoch 3, batch 7850, loss[loss=0.163, simple_loss=0.2346, pruned_loss=0.04568, over 4941.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2316, pruned_loss=0.04789, over 972037.71 frames.], batch size: 21, lr: 5.66e-04
2022-05-04 12:44:18,371 INFO [train.py:715] (4/8) Epoch 3, batch 7900, loss[loss=0.1544, simple_loss=0.2176, pruned_loss=0.04563, over 4961.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2311, pruned_loss=0.04733, over 972038.30 frames.], batch size: 14, lr: 5.66e-04
2022-05-04 12:44:58,146 INFO [train.py:715] (4/8) Epoch 3, batch 7950, loss[loss=0.1893, simple_loss=0.2573, pruned_loss=0.0606, over 4925.00 frames.], tot_loss[loss=0.1638, simple_loss=0.232, pruned_loss=0.04778, over 972371.72 frames.], batch size: 39, lr: 5.66e-04
2022-05-04 12:45:36,729 INFO [train.py:715] (4/8) Epoch 3, batch 8000, loss[loss=0.1474, simple_loss=0.2196, pruned_loss=0.03757, over 4898.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2322, pruned_loss=0.048, over 973368.38 frames.], batch size: 19, lr: 5.66e-04
2022-05-04 12:46:14,905 INFO [train.py:715] (4/8) Epoch 3, batch 8050, loss[loss=0.1476, simple_loss=0.2179, pruned_loss=0.03868, over 4887.00 frames.], tot_loss[loss=0.1639, simple_loss=0.232, pruned_loss=0.04794, over 973320.14 frames.], batch size: 19, lr: 5.65e-04
2022-05-04 12:46:53,637 INFO [train.py:715] (4/8) Epoch 3, batch 8100, loss[loss=0.1405, simple_loss=0.2171, pruned_loss=0.03189, over 4953.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2319, pruned_loss=0.04757, over 972240.02 frames.], batch size: 21, lr: 5.65e-04
2022-05-04 12:47:31,942 INFO [train.py:715] (4/8) Epoch 3, batch 8150, loss[loss=0.189, simple_loss=0.25, pruned_loss=0.064, over 4826.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2307, pruned_loss=0.04709, over 971866.98 frames.], batch size: 30, lr: 5.65e-04
2022-05-04 12:48:10,085 INFO [train.py:715] (4/8) Epoch 3, batch 8200, loss[loss=0.1755, simple_loss=0.232, pruned_loss=0.0595, over 4827.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2311, pruned_loss=0.04753, over 972046.36 frames.], batch size: 15, lr: 5.65e-04
2022-05-04 12:48:49,887 INFO [train.py:715] (4/8) Epoch 3, batch 8250, loss[loss=0.1589, simple_loss=0.2282, pruned_loss=0.04485, over 4978.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2303, pruned_loss=0.04733, over 971015.98 frames.], batch size: 15, lr: 5.65e-04
2022-05-04 12:49:30,614 INFO [train.py:715] (4/8) Epoch 3, batch 8300, loss[loss=0.1949, simple_loss=0.2648, pruned_loss=0.0625, over 4983.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2311, pruned_loss=0.04771, over 971501.78 frames.], batch size: 15, lr: 5.65e-04
2022-05-04 12:50:10,666 INFO [train.py:715] (4/8) Epoch 3, batch 8350, loss[loss=0.1665, simple_loss=0.2339, pruned_loss=0.04959, over 4745.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2319, pruned_loss=0.04811, over 971816.62 frames.], batch size: 16, lr: 5.65e-04
2022-05-04 12:50:50,665 INFO [train.py:715] (4/8) Epoch 3, batch 8400, loss[loss=0.1626, simple_loss=0.2401, pruned_loss=0.04251, over 4879.00 frames.], tot_loss[loss=0.1643, simple_loss=0.232, pruned_loss=0.0483, over 972868.55 frames.], batch size: 16, lr: 5.65e-04
2022-05-04 12:51:30,650 INFO [train.py:715] (4/8) Epoch 3, batch 8450, loss[loss=0.1248, simple_loss=0.1777, pruned_loss=0.03593, over 4806.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2314, pruned_loss=0.04847, over 973646.16 frames.], batch size: 12, lr: 5.64e-04
2022-05-04 12:52:10,869 INFO [train.py:715] (4/8) Epoch 3, batch 8500, loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03412, over 4826.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2319, pruned_loss=0.04849, over 972737.62 frames.], batch size: 25, lr: 5.64e-04
2022-05-04 12:52:49,924 INFO [train.py:715] (4/8) Epoch 3, batch 8550, loss[loss=0.1635, simple_loss=0.245, pruned_loss=0.04098, over 4802.00 frames.], tot_loss[loss=0.164, simple_loss=0.232, pruned_loss=0.04801, over 972221.77 frames.], batch size: 21, lr: 5.64e-04
2022-05-04 12:53:31,547 INFO [train.py:715] (4/8) Epoch 3, batch 8600, loss[loss=0.146, simple_loss=0.2032, pruned_loss=0.04445, over 4756.00 frames.], tot_loss[loss=0.164, simple_loss=0.2318, pruned_loss=0.0481, over 972425.18 frames.], batch size: 12, lr: 5.64e-04
2022-05-04 12:54:13,126 INFO [train.py:715] (4/8) Epoch 3, batch 8650, loss[loss=0.1678, simple_loss=0.2358, pruned_loss=0.04986, over 4804.00 frames.], tot_loss[loss=0.164, simple_loss=0.2318, pruned_loss=0.04808, over 972885.37 frames.], batch size: 21, lr: 5.64e-04
2022-05-04 12:54:53,241 INFO [train.py:715] (4/8) Epoch 3, batch 8700, loss[loss=0.1463, simple_loss=0.2123, pruned_loss=0.04012, over 4837.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2319, pruned_loss=0.04828, over 972233.98 frames.], batch size: 30, lr: 5.64e-04
2022-05-04 12:55:34,484 INFO [train.py:715] (4/8) Epoch 3, batch 8750, loss[loss=0.1467, simple_loss=0.2163, pruned_loss=0.03856, over 4827.00 frames.], tot_loss[loss=0.163, simple_loss=0.231, pruned_loss=0.04747, over 971341.91 frames.], batch size: 26, lr: 5.64e-04
2022-05-04 12:56:14,900 INFO [train.py:715] (4/8) Epoch 3, batch 8800, loss[loss=0.1489, simple_loss=0.2258, pruned_loss=0.03605, over 4901.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2318, pruned_loss=0.04834, over 971229.67 frames.], batch size: 19, lr: 5.64e-04
2022-05-04 12:56:55,635 INFO [train.py:715] (4/8) Epoch 3, batch 8850, loss[loss=0.2177, simple_loss=0.2717, pruned_loss=0.08192, over 4832.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2322, pruned_loss=0.04883, over 971367.19 frames.], batch size: 15, lr: 5.63e-04
2022-05-04 12:57:35,612 INFO [train.py:715] (4/8) Epoch 3, batch 8900, loss[loss=0.1615, simple_loss=0.2264, pruned_loss=0.04824, over 4761.00 frames.], tot_loss[loss=0.164, simple_loss=0.2318, pruned_loss=0.04806, over 972263.12 frames.], batch size: 16, lr: 5.63e-04
2022-05-04 12:58:17,382 INFO [train.py:715] (4/8) Epoch 3, batch 8950, loss[loss=0.156, simple_loss=0.2208, pruned_loss=0.04562, over 4712.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2315, pruned_loss=0.04794, over 971665.24 frames.], batch size: 15, lr: 5.63e-04
2022-05-04 12:58:59,317 INFO [train.py:715] (4/8) Epoch 3, batch 9000, loss[loss=0.1556, simple_loss=0.2239, pruned_loss=0.04362, over 4776.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2308, pruned_loss=0.04745, over 971520.71 frames.], batch size: 18, lr: 5.63e-04
2022-05-04 12:58:59,318 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 12:59:08,108 INFO [train.py:742] (4/8) Epoch 3, validation: loss=0.1147, simple_loss=0.2006, pruned_loss=0.01442, over 914524.00 frames.
2022-05-04 12:59:49,673 INFO [train.py:715] (4/8) Epoch 3, batch 9050, loss[loss=0.1527, simple_loss=0.2184, pruned_loss=0.04345, over 4792.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2313, pruned_loss=0.0476, over 971571.22 frames.], batch size: 14, lr: 5.63e-04
2022-05-04 13:00:30,622 INFO [train.py:715] (4/8) Epoch 3, batch 9100, loss[loss=0.2131, simple_loss=0.2782, pruned_loss=0.07396, over 4899.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2324, pruned_loss=0.04796, over 971964.12 frames.], batch size: 19, lr: 5.63e-04
2022-05-04 13:01:11,922 INFO [train.py:715] (4/8) Epoch 3, batch 9150, loss[loss=0.1213, simple_loss=0.1882, pruned_loss=0.02725, over 4809.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2319, pruned_loss=0.04765, over 972475.34 frames.], batch size: 12, lr: 5.63e-04
2022-05-04 13:01:53,297 INFO [train.py:715] (4/8) Epoch 3, batch 9200, loss[loss=0.1475, simple_loss=0.2267, pruned_loss=0.03418, over 4818.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2316, pruned_loss=0.04708, over 971635.39 frames.], batch size: 25, lr: 5.63e-04
2022-05-04 13:02:34,661 INFO [train.py:715] (4/8) Epoch 3, batch 9250, loss[loss=0.16, simple_loss=0.2246, pruned_loss=0.04771, over 4829.00 frames.], tot_loss[loss=0.1646, simple_loss=0.233, pruned_loss=0.04808, over 972457.08 frames.], batch size: 26, lr: 5.62e-04
2022-05-04 13:03:15,390 INFO [train.py:715] (4/8) Epoch 3, batch 9300, loss[loss=0.1505, simple_loss=0.2298, pruned_loss=0.03556, over 4971.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2326, pruned_loss=0.04803, over 971905.80 frames.], batch size: 25, lr: 5.62e-04
2022-05-04 13:03:56,624 INFO [train.py:715] (4/8) Epoch 3, batch 9350, loss[loss=0.1574, simple_loss=0.2293, pruned_loss=0.04272, over 4785.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2331, pruned_loss=0.04859, over 972597.21 frames.], batch size: 18, lr: 5.62e-04
2022-05-04 13:04:38,912 INFO [train.py:715] (4/8) Epoch 3, batch 9400, loss[loss=0.1844, simple_loss=0.2411, pruned_loss=0.06384, over 4847.00 frames.], tot_loss[loss=0.1655, simple_loss=0.2332, pruned_loss=0.04885, over 972866.77 frames.], batch size: 30, lr: 5.62e-04
2022-05-04 13:05:19,293 INFO [train.py:715] (4/8) Epoch 3, batch 9450, loss[loss=0.1671, simple_loss=0.2383, pruned_loss=0.04794, over 4907.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2335, pruned_loss=0.04906, over 972621.26 frames.], batch size: 19, lr: 5.62e-04
2022-05-04 13:06:00,839 INFO [train.py:715] (4/8) Epoch 3, batch 9500, loss[loss=0.1586, simple_loss=0.2352, pruned_loss=0.04101, over 4879.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2325, pruned_loss=0.04812, over 973474.21 frames.], batch size: 22, lr: 5.62e-04
2022-05-04 13:06:42,688 INFO [train.py:715] (4/8) Epoch 3, batch 9550, loss[loss=0.1633, simple_loss=0.2285, pruned_loss=0.04902, over 4826.00 frames.], tot_loss[loss=0.164, simple_loss=0.232, pruned_loss=0.04804, over 973593.60 frames.], batch size: 15, lr: 5.62e-04
2022-05-04 13:07:24,285 INFO [train.py:715] (4/8) Epoch 3, batch 9600, loss[loss=0.181, simple_loss=0.2408, pruned_loss=0.06063, over 4833.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2324, pruned_loss=0.04836, over 973950.57 frames.], batch size: 15, lr: 5.62e-04
2022-05-04 13:08:05,439 INFO [train.py:715] (4/8) Epoch 3, batch 9650, loss[loss=0.1792, simple_loss=0.2524, pruned_loss=0.05301, over 4836.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2333, pruned_loss=0.04906, over 974172.97 frames.], batch size: 15, lr: 5.61e-04
2022-05-04 13:08:46,948 INFO [train.py:715] (4/8) Epoch 3, batch 9700, loss[loss=0.1298, simple_loss=0.2029, pruned_loss=0.02836, over 4801.00 frames.], tot_loss[loss=0.1656, simple_loss=0.2332, pruned_loss=0.04896, over 973813.82 frames.], batch size: 24, lr: 5.61e-04
2022-05-04 13:09:27,940 INFO [train.py:715] (4/8) Epoch 3, batch 9750, loss[loss=0.1973, simple_loss=0.27, pruned_loss=0.06232, over 4794.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2324, pruned_loss=0.04821, over 974059.32 frames.], batch size: 17, lr: 5.61e-04
2022-05-04 13:10:08,812 INFO [train.py:715] (4/8) Epoch 3, batch 9800, loss[loss=0.1691, simple_loss=0.229, pruned_loss=0.05461, over 4706.00 frames.], tot_loss[loss=0.1644, simple_loss=0.2327, pruned_loss=0.04809, over 973639.93 frames.], batch size: 15, lr: 5.61e-04
2022-05-04 13:10:50,545 INFO [train.py:715] (4/8) Epoch 3, batch 9850, loss[loss=0.1286, simple_loss=0.2044, pruned_loss=0.02643, over 4821.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2321, pruned_loss=0.04759, over 974265.18 frames.], batch size: 13, lr: 5.61e-04
2022-05-04 13:11:32,493 INFO [train.py:715] (4/8) Epoch 3, batch 9900, loss[loss=0.1862, simple_loss=0.2485, pruned_loss=0.06194, over 4910.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2319, pruned_loss=0.04777, over 973789.32 frames.], batch size: 18, lr: 5.61e-04
2022-05-04 13:12:12,991 INFO [train.py:715] (4/8) Epoch 3, batch 9950, loss[loss=0.1491, simple_loss=0.222, pruned_loss=0.03804, over 4770.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2318, pruned_loss=0.04749, over 973745.95 frames.], batch size: 18, lr: 5.61e-04
2022-05-04 13:12:54,730 INFO [train.py:715] (4/8) Epoch 3, batch 10000, loss[loss=0.1693, simple_loss=0.2385, pruned_loss=0.05004, over 4834.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2309, pruned_loss=0.04731, over 973522.66 frames.], batch size: 13, lr: 5.61e-04
2022-05-04 13:13:36,176 INFO [train.py:715] (4/8) Epoch 3, batch 10050, loss[loss=0.1403, simple_loss=0.2111, pruned_loss=0.03475, over 4933.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2302, pruned_loss=0.04677, over 973589.09 frames.], batch size: 23, lr: 5.61e-04
2022-05-04 13:14:17,623 INFO [train.py:715] (4/8) Epoch 3, batch 10100, loss[loss=0.2393, simple_loss=0.2921, pruned_loss=0.09327, over 4756.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2302, pruned_loss=0.04669, over 973318.33 frames.], batch size: 14, lr: 5.60e-04
2022-05-04 13:14:58,623 INFO [train.py:715] (4/8) Epoch 3, batch 10150, loss[loss=0.2211, simple_loss=0.26, pruned_loss=0.09108, over 4836.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2326, pruned_loss=0.0485, over 973156.49 frames.], batch size: 15, lr: 5.60e-04
2022-05-04 13:15:40,198 INFO [train.py:715] (4/8) Epoch 3, batch 10200, loss[loss=0.1492, simple_loss=0.218, pruned_loss=0.04013, over 4960.00 frames.], tot_loss[loss=0.1658, simple_loss=0.2335, pruned_loss=0.04898, over 972763.73 frames.], batch size: 24, lr: 5.60e-04
2022-05-04 13:16:21,935 INFO [train.py:715] (4/8) Epoch 3, batch 10250, loss[loss=0.1304, simple_loss=0.2018, pruned_loss=0.02946, over 4918.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2316, pruned_loss=0.0478, over 972747.52 frames.], batch size: 29, lr: 5.60e-04
2022-05-04 13:17:01,804 INFO [train.py:715] (4/8) Epoch 3, batch 10300, loss[loss=0.132, simple_loss=0.2112, pruned_loss=0.02642, over 4871.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2314, pruned_loss=0.04773, over 972695.54 frames.], batch size: 32, lr: 5.60e-04
2022-05-04 13:17:42,040 INFO [train.py:715] (4/8) Epoch 3, batch 10350, loss[loss=0.1581, simple_loss=0.2449, pruned_loss=0.03562, over 4945.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2311, pruned_loss=0.04751, over 971904.82 frames.], batch size: 21, lr: 5.60e-04
2022-05-04 13:18:22,568 INFO [train.py:715] (4/8) Epoch 3, batch 10400, loss[loss=0.1791, simple_loss=0.2266, pruned_loss=0.06582, over 4969.00 frames.], tot_loss[loss=0.164, simple_loss=0.2317, pruned_loss=0.04814, over 971167.25 frames.], batch size: 31, lr: 5.60e-04
2022-05-04 13:19:03,194 INFO [train.py:715] (4/8) Epoch 3, batch 10450, loss[loss=0.1547, simple_loss=0.237, pruned_loss=0.03619, over 4796.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2317, pruned_loss=0.04782, over 971227.45 frames.], batch size: 24, lr: 5.60e-04
2022-05-04 13:19:43,609 INFO [train.py:715] (4/8) Epoch 3, batch 10500, loss[loss=0.1743, simple_loss=0.2303, pruned_loss=0.05914, over 4848.00 frames.], tot_loss[loss=0.163, simple_loss=0.2308, pruned_loss=0.04761, over 970578.17 frames.], batch size: 32, lr: 5.59e-04
2022-05-04 13:20:24,611 INFO [train.py:715] (4/8) Epoch 3, batch 10550, loss[loss=0.1627, simple_loss=0.233, pruned_loss=0.04624, over 4927.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2315, pruned_loss=0.04803, over 971031.21 frames.], batch size: 35, lr: 5.59e-04
2022-05-04 13:21:07,125 INFO [train.py:715] (4/8) Epoch 3, batch 10600, loss[loss=0.1908, simple_loss=0.2536, pruned_loss=0.06396, over 4971.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2313, pruned_loss=0.04773, over 971250.49 frames.], batch size: 15, lr: 5.59e-04
2022-05-04 13:21:48,605 INFO [train.py:715] (4/8) Epoch 3, batch 10650, loss[loss=0.1427, simple_loss=0.2141, pruned_loss=0.03564, over 4743.00 frames.], tot_loss[loss=0.163, simple_loss=0.2313, pruned_loss=0.04738, over 970678.78 frames.], batch size: 16, lr: 5.59e-04
2022-05-04 13:22:30,732 INFO [train.py:715] (4/8) Epoch 3, batch 10700, loss[loss=0.2005, simple_loss=0.2653, pruned_loss=0.06785, over 4956.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2318, pruned_loss=0.04764, over 970996.38 frames.], batch size: 39, lr: 5.59e-04
2022-05-04 13:23:13,509 INFO [train.py:715] (4/8) Epoch 3, batch 10750, loss[loss=0.1756, simple_loss=0.2552, pruned_loss=0.04797, over 4918.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2325, pruned_loss=0.04835, over 970975.15 frames.], batch size: 18, lr: 5.59e-04
2022-05-04 13:23:56,750 INFO [train.py:715] (4/8) Epoch 3, batch 10800, loss[loss=0.1958, simple_loss=0.2495, pruned_loss=0.07101, over 4895.00 frames.], tot_loss[loss=0.1639, simple_loss=0.232, pruned_loss=0.04794, over 971010.66 frames.], batch size: 19, lr: 5.59e-04
2022-05-04 13:24:38,548 INFO [train.py:715] (4/8) Epoch 3, batch 10850, loss[loss=0.1579, simple_loss=0.2308, pruned_loss=0.04245, over 4877.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2318, pruned_loss=0.04768, over 971341.92 frames.], batch size: 19, lr: 5.59e-04
2022-05-04 13:25:21,304 INFO [train.py:715] (4/8) Epoch 3, batch 10900, loss[loss=0.1597, simple_loss=0.2274, pruned_loss=0.04597, over 4848.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2313, pruned_loss=0.04786, over 971682.36 frames.], batch size: 20, lr: 5.58e-04
2022-05-04 13:26:04,549 INFO [train.py:715] (4/8) Epoch 3, batch 10950, loss[loss=0.1815, simple_loss=0.2527, pruned_loss=0.05517, over 4792.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2315, pruned_loss=0.04779, over 972477.93 frames.], batch size: 17, lr: 5.58e-04
2022-05-04 13:26:46,503 INFO [train.py:715] (4/8) Epoch 3, batch 11000, loss[loss=0.1186, simple_loss=0.1893, pruned_loss=0.02391, over 4757.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2315, pruned_loss=0.0474, over 971569.46 frames.], batch size: 12, lr: 5.58e-04
2022-05-04 13:27:28,086 INFO [train.py:715] (4/8) Epoch 3, batch 11050, loss[loss=0.1604, simple_loss=0.2364, pruned_loss=0.04219, over 4811.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2316, pruned_loss=0.04688, over 971170.12 frames.], batch size: 27, lr: 5.58e-04
2022-05-04 13:28:11,588 INFO [train.py:715] (4/8) Epoch 3, batch 11100, loss[loss=0.171, simple_loss=0.2364, pruned_loss=0.05285, over 4988.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2315, pruned_loss=0.04711, over 971440.70 frames.], batch size: 31, lr: 5.58e-04
2022-05-04 13:28:53,666 INFO [train.py:715] (4/8) Epoch 3, batch 11150, loss[loss=0.1256, simple_loss=0.1951, pruned_loss=0.0281, over 4986.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2303, pruned_loss=0.04632, over 971554.67 frames.], batch size: 25, lr: 5.58e-04
2022-05-04 13:29:35,723 INFO [train.py:715] (4/8) Epoch 3, batch 11200, loss[loss=0.1621, simple_loss=0.2325, pruned_loss=0.0458, over 4978.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2324, pruned_loss=0.04796, over 971803.04 frames.], batch size: 35, lr: 5.58e-04
2022-05-04 13:30:18,264 INFO [train.py:715] (4/8) Epoch 3, batch 11250, loss[loss=0.1553, simple_loss=0.2333, pruned_loss=0.03864, over 4817.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2326, pruned_loss=0.04798, over 972355.78 frames.], batch size: 27, lr: 5.58e-04
2022-05-04 13:31:01,487 INFO [train.py:715] (4/8) Epoch 3, batch 11300, loss[loss=0.1597, simple_loss=0.2293, pruned_loss=0.04509, over 4909.00 frames.], tot_loss[loss=0.1647, simple_loss=0.233, pruned_loss=0.04819, over 972977.86 frames.], batch size: 19, lr: 5.57e-04
2022-05-04 13:31:42,766 INFO [train.py:715] (4/8) Epoch 3, batch 11350, loss[loss=0.1641, simple_loss=0.2326, pruned_loss=0.04778, over 4754.00 frames.], tot_loss[loss=0.1648, simple_loss=0.2331, pruned_loss=0.04825, over 972721.18 frames.], batch size: 16, lr: 5.57e-04
2022-05-04 13:32:25,097 INFO [train.py:715] (4/8) Epoch 3, batch 11400, loss[loss=0.1625, simple_loss=0.2334, pruned_loss=0.04586, over 4955.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2329, pruned_loss=0.04821, over 973353.44 frames.], batch size: 24, lr: 5.57e-04
2022-05-04 13:33:08,040 INFO [train.py:715] (4/8) Epoch 3, batch 11450, loss[loss=0.1582, simple_loss=0.22, pruned_loss=0.04817, over 4754.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2328, pruned_loss=0.04792, over 974505.29 frames.], batch size: 16, lr: 5.57e-04
2022-05-04 13:33:50,177 INFO [train.py:715] (4/8) Epoch 3, batch 11500, loss[loss=0.1742, simple_loss=0.2406, pruned_loss=0.05393, over 4970.00 frames.], tot_loss[loss=0.1643, simple_loss=0.233, pruned_loss=0.04777, over 974829.33 frames.], batch size: 39, lr: 5.57e-04
2022-05-04 13:34:32,215 INFO [train.py:715] (4/8) Epoch 3, batch 11550, loss[loss=0.1475, simple_loss=0.2172, pruned_loss=0.03896, over 4948.00 frames.], tot_loss[loss=0.1636, simple_loss=0.232, pruned_loss=0.04759, over 974836.27 frames.], batch size: 24, lr: 5.57e-04
2022-05-04 13:35:14,412 INFO [train.py:715] (4/8) Epoch 3, batch 11600, loss[loss=0.1731, simple_loss=0.2424, pruned_loss=0.05196, over 4920.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2319, pruned_loss=0.04735, over 974530.44 frames.], batch size: 18, lr: 5.57e-04
2022-05-04 13:35:57,164 INFO [train.py:715] (4/8) Epoch 3, batch 11650, loss[loss=0.139, simple_loss=0.2107, pruned_loss=0.03367, over 4843.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2315, pruned_loss=0.04719, over 973505.11 frames.], batch size: 30, lr: 5.57e-04
2022-05-04 13:36:39,247 INFO [train.py:715] (4/8) Epoch 3, batch 11700, loss[loss=0.1818, simple_loss=0.2405, pruned_loss=0.06156, over 4690.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2316, pruned_loss=0.04732, over 971837.46 frames.], batch size: 15, lr: 5.57e-04
2022-05-04 13:37:21,468 INFO [train.py:715] (4/8) Epoch 3, batch 11750, loss[loss=0.1601, simple_loss=0.2262, pruned_loss=0.04702, over 4983.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2316, pruned_loss=0.04745, over 972228.80 frames.], batch size: 25, lr: 5.56e-04
2022-05-04 13:38:05,267 INFO [train.py:715] (4/8) Epoch 3, batch 11800, loss[loss=0.1241, simple_loss=0.1925, pruned_loss=0.0278, over 4980.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2314, pruned_loss=0.04745, over 972863.47 frames.], batch size: 14, lr: 5.56e-04
2022-05-04 13:38:47,442 INFO [train.py:715] (4/8) Epoch 3, batch 11850, loss[loss=0.17, simple_loss=0.2342, pruned_loss=0.05294, over 4919.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2308, pruned_loss=0.04735, over 972410.43 frames.], batch size: 18, lr: 5.56e-04
2022-05-04 13:39:29,602 INFO [train.py:715] (4/8) Epoch 3, batch 11900, loss[loss=0.1774, simple_loss=0.2391, pruned_loss=0.0579, over 4662.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2306, pruned_loss=0.0473, over 971764.53 frames.], batch size: 13, lr: 5.56e-04
2022-05-04 13:40:11,693 INFO [train.py:715] (4/8) Epoch 3, batch 11950, loss[loss=0.1712, simple_loss=0.2475, pruned_loss=0.04741, over 4819.00 frames.], tot_loss[loss=0.162, simple_loss=0.2301, pruned_loss=0.047, over 971572.66 frames.], batch size: 25, lr: 5.56e-04
2022-05-04 13:40:54,192 INFO [train.py:715] (4/8) Epoch 3, batch 12000, loss[loss=0.1564, simple_loss=0.224, pruned_loss=0.04436, over 4639.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2302, pruned_loss=0.04717, over 971439.02 frames.], batch size: 13, lr: 5.56e-04
2022-05-04 13:40:54,193 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 13:41:02,571 INFO [train.py:742] (4/8) Epoch 3, validation: loss=0.1142, simple_loss=0.2003, pruned_loss=0.01401, over 914524.00 frames.
2022-05-04 13:41:44,672 INFO [train.py:715] (4/8) Epoch 3, batch 12050, loss[loss=0.1877, simple_loss=0.2495, pruned_loss=0.06298, over 4919.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2301, pruned_loss=0.04729, over 972617.01 frames.], batch size: 23, lr: 5.56e-04
2022-05-04 13:42:26,361 INFO [train.py:715] (4/8) Epoch 3, batch 12100, loss[loss=0.1661, simple_loss=0.2334, pruned_loss=0.04938, over 4894.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2313, pruned_loss=0.04755, over 972373.71 frames.], batch size: 19, lr: 5.56e-04
2022-05-04 13:43:08,764 INFO [train.py:715] (4/8) Epoch 3, batch 12150, loss[loss=0.1747, simple_loss=0.2491, pruned_loss=0.05015, over 4883.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2313, pruned_loss=0.04742, over 973183.67 frames.], batch size: 19, lr: 5.55e-04
2022-05-04 13:43:52,012 INFO [train.py:715] (4/8) Epoch 3, batch 12200, loss[loss=0.1329, simple_loss=0.1991, pruned_loss=0.03337, over 4887.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2304, pruned_loss=0.04754, over 972481.14 frames.], batch size: 22, lr: 5.55e-04
2022-05-04 13:44:33,678 INFO [train.py:715] (4/8) Epoch 3, batch 12250, loss[loss=0.1727, simple_loss=0.2318, pruned_loss=0.05684, over 4816.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2311, pruned_loss=0.04778, over 971933.42 frames.], batch size: 27, lr: 5.55e-04
2022-05-04 13:45:15,586 INFO [train.py:715] (4/8) Epoch 3, batch 12300, loss[loss=0.1518, simple_loss=0.2335, pruned_loss=0.035, over 4800.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2313, pruned_loss=0.04753, over 971546.29 frames.], batch size: 17, lr: 5.55e-04
2022-05-04 13:45:58,037 INFO [train.py:715] (4/8) Epoch 3, batch 12350, loss[loss=0.1454, simple_loss=0.2127, pruned_loss=0.039, over 4920.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2315, pruned_loss=0.04746, over 972476.46 frames.], batch size: 18, lr: 5.55e-04
2022-05-04 13:46:41,401 INFO [train.py:715] (4/8) Epoch 3, batch 12400, loss[loss=0.1814, simple_loss=0.2358, pruned_loss=0.06352, over 4802.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2309, pruned_loss=0.04716, over 972659.41 frames.], batch size: 15, lr: 5.55e-04
2022-05-04 13:47:23,060 INFO [train.py:715] (4/8) Epoch 3, batch 12450, loss[loss=0.241, simple_loss=0.2996, pruned_loss=0.09125, over 4871.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2329, pruned_loss=0.0486, over 973541.35 frames.], batch size: 16, lr: 5.55e-04
2022-05-04 13:48:04,560 INFO [train.py:715] (4/8) Epoch 3, batch 12500, loss[loss=0.1241, simple_loss=0.2008, pruned_loss=0.02371, over 4938.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2332, pruned_loss=0.0487, over 973157.46 frames.], batch size: 23, lr: 5.55e-04
2022-05-04 13:48:47,316 INFO [train.py:715] (4/8) Epoch 3, batch 12550, loss[loss=0.1559, simple_loss=0.229, pruned_loss=0.04137, over 4707.00 frames.], tot_loss[loss=0.1654, simple_loss=0.2332, pruned_loss=0.04885, over 972770.46 frames.], batch size: 15, lr: 5.54e-04
2022-05-04 13:49:29,586 INFO [train.py:715] (4/8) Epoch 3, batch 12600, loss[loss=0.1376, simple_loss=0.216, pruned_loss=0.02954, over 4817.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2325, pruned_loss=0.04827, over 973266.98 frames.], batch size: 27, lr: 5.54e-04
2022-05-04 13:50:11,350 INFO [train.py:715] (4/8) Epoch 3, batch 12650, loss[loss=0.1366, simple_loss=0.2036, pruned_loss=0.0348, over 4773.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2317, pruned_loss=0.04769, over 973400.53 frames.], batch size: 19, lr: 5.54e-04
2022-05-04 13:50:53,052 INFO [train.py:715] (4/8) Epoch 3, batch 12700, loss[loss=0.1735, simple_loss=0.2379, pruned_loss=0.05457, over 4698.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2317, pruned_loss=0.04753, over 972397.04 frames.], batch size: 15, lr: 5.54e-04
2022-05-04 13:51:35,147 INFO [train.py:715] (4/8) Epoch 3, batch 12750, loss[loss=0.1396, simple_loss=0.2107, pruned_loss=0.03426, over 4913.00 frames.], tot_loss[loss=0.162, simple_loss=0.2302, pruned_loss=0.04687, over 973449.70 frames.], batch size: 18, lr: 5.54e-04
2022-05-04 13:52:17,421 INFO [train.py:715] (4/8) Epoch 3, batch 12800, loss[loss=0.1598, simple_loss=0.2274, pruned_loss=0.04604, over 4777.00 frames.], tot_loss[loss=0.162, simple_loss=0.2302, pruned_loss=0.04691, over 973040.13 frames.], batch size: 17, lr: 5.54e-04
2022-05-04 13:52:58,250 INFO [train.py:715] (4/8) Epoch 3, batch 12850, loss[loss=0.1539, simple_loss=0.2277, pruned_loss=0.04002, over 4861.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2308, pruned_loss=0.04721, over 972178.44 frames.], batch size: 32, lr: 5.54e-04
2022-05-04 13:53:40,951 INFO [train.py:715] (4/8) Epoch 3, batch 12900, loss[loss=0.1396, simple_loss=0.2092, pruned_loss=0.03502, over 4833.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2312, pruned_loss=0.04731, over 972686.32 frames.], batch size: 13, lr: 5.54e-04
2022-05-04 13:54:23,549 INFO [train.py:715] (4/8) Epoch 3, batch 12950, loss[loss=0.1429, simple_loss=0.2141, pruned_loss=0.03581, over 4984.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2318, pruned_loss=0.04766, over 972486.95 frames.], batch size: 28, lr: 5.54e-04
2022-05-04 13:55:04,911 INFO [train.py:715] (4/8) Epoch 3, batch 13000, loss[loss=0.1315, simple_loss=0.1968, pruned_loss=0.03307, over 4757.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2327, pruned_loss=0.04826, over 972876.53 frames.], batch size: 19, lr: 5.53e-04
2022-05-04 13:55:46,784 INFO [train.py:715] (4/8) Epoch 3, batch 13050, loss[loss=0.1592, simple_loss=0.2256, pruned_loss=0.04641, over 4920.00 frames.], tot_loss[loss=0.1641, simple_loss=0.232, pruned_loss=0.04813, over 973425.34 frames.], batch size: 18, lr: 5.53e-04
2022-05-04 13:56:28,779 INFO [train.py:715] (4/8) Epoch 3, batch 13100, loss[loss=0.1596, simple_loss=0.2242, pruned_loss=0.0475, over 4808.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2316, pruned_loss=0.04763, over 972535.32 frames.], batch size: 25, lr: 5.53e-04
2022-05-04 13:57:10,544 INFO [train.py:715] (4/8) Epoch 3, batch 13150, loss[loss=0.1855, simple_loss=0.2527, pruned_loss=0.05909, over 4830.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2314, pruned_loss=0.04767, over 972342.58 frames.], batch size: 27, lr: 5.53e-04
2022-05-04 13:57:52,108 INFO [train.py:715] (4/8) Epoch 3, batch 13200, loss[loss=0.1454, simple_loss=0.2147, pruned_loss=0.038, over 4809.00 frames.], tot_loss[loss=0.163, simple_loss=0.2313, pruned_loss=0.04736, over 971991.54 frames.], batch size: 12, lr: 5.53e-04
2022-05-04 13:58:34,741 INFO [train.py:715] (4/8) Epoch 3, batch 13250, loss[loss=0.1485, simple_loss=0.2167, pruned_loss=0.04014, over 4861.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2304, pruned_loss=0.04729, over 972464.31 frames.], batch size: 20, lr: 5.53e-04
2022-05-04 13:59:17,139 INFO [train.py:715] (4/8) Epoch 3, batch 13300, loss[loss=0.1686, simple_loss=0.2318, pruned_loss=0.05268, over 4907.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2307, pruned_loss=0.04734, over 971269.73 frames.], batch size: 17, lr: 5.53e-04
2022-05-04 13:59:58,633 INFO [train.py:715] (4/8) Epoch 3, batch 13350, loss[loss=0.1567, simple_loss=0.2367, pruned_loss=0.03835, over 4823.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2307, pruned_loss=0.0473, over 970759.96 frames.], batch size: 15, lr: 5.53e-04
2022-05-04 14:00:40,457 INFO [train.py:715] (4/8) Epoch 3, batch 13400, loss[loss=0.1582, simple_loss=0.2234, pruned_loss=0.04651, over 4983.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2314, pruned_loss=0.04771, over 971766.31 frames.], batch size: 28, lr: 5.52e-04
2022-05-04 14:01:23,048 INFO [train.py:715] (4/8) Epoch 3, batch 13450, loss[loss=0.1421, simple_loss=0.2173, pruned_loss=0.03344, over 4985.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2318, pruned_loss=0.04759, over 971949.57 frames.], batch size: 25, lr: 5.52e-04
2022-05-04 14:02:04,530 INFO [train.py:715] (4/8) Epoch 3, batch 13500, loss[loss=0.1525, simple_loss=0.2251, pruned_loss=0.03999, over 4818.00 frames.], tot_loss[loss=0.1634, simple_loss=0.232, pruned_loss=0.04743, over 972141.81 frames.], batch size: 13, lr: 5.52e-04
2022-05-04 14:02:46,049 INFO [train.py:715] (4/8) Epoch 3, batch 13550, loss[loss=0.1532, simple_loss=0.227, pruned_loss=0.03972, over 4886.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2315, pruned_loss=0.04757, over 971949.70 frames.], batch size: 16, lr: 5.52e-04
2022-05-04 14:03:28,369 INFO [train.py:715] (4/8) Epoch 3, batch 13600, loss[loss=0.1538, simple_loss=0.2196, pruned_loss=0.04397, over 4933.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2319, pruned_loss=0.04787, over 972417.34 frames.], batch size: 23, lr: 5.52e-04
2022-05-04 14:04:10,267 INFO [train.py:715] (4/8) Epoch 3, batch 13650, loss[loss=0.1678, simple_loss=0.2333, pruned_loss=0.05117, over 4963.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2312, pruned_loss=0.04726, over 972535.88 frames.], batch size: 24, lr: 5.52e-04
2022-05-04 14:04:51,692 INFO [train.py:715] (4/8) Epoch 3, batch 13700, loss[loss=0.1508, simple_loss=0.2283, pruned_loss=0.03667, over 4868.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2315, pruned_loss=0.04746, over 972735.17 frames.], batch size: 20, lr: 5.52e-04
2022-05-04 14:05:34,455 INFO [train.py:715] (4/8) Epoch 3, batch 13750, loss[loss=0.1493, simple_loss=0.2326, pruned_loss=0.03294, over 4771.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2319, pruned_loss=0.04765, over 972163.94 frames.], batch size: 14, lr: 5.52e-04
2022-05-04 14:06:16,542 INFO [train.py:715] (4/8) Epoch 3, batch 13800, loss[loss=0.1625, simple_loss=0.2222, pruned_loss=0.05144, over 4736.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2306, pruned_loss=0.04779, over 971950.17 frames.], batch size: 16, lr: 5.52e-04
2022-05-04 14:06:58,015 INFO [train.py:715] (4/8) Epoch 3, batch 13850, loss[loss=0.2066, simple_loss=0.2691, pruned_loss=0.07206, over 4773.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2311, pruned_loss=0.04755, over 971869.19 frames.], batch size: 17, lr: 5.51e-04
2022-05-04 14:07:39,251 INFO [train.py:715] (4/8) Epoch 3, batch 13900, loss[loss=0.1466, simple_loss=0.2206, pruned_loss=0.03629, over 4813.00 frames.], tot_loss[loss=0.162, simple_loss=0.23, pruned_loss=0.04697, over 971901.95 frames.], batch size: 15, lr: 5.51e-04
2022-05-04 14:08:21,699 INFO [train.py:715] (4/8) Epoch 3, batch 13950, loss[loss=0.1549, simple_loss=0.2369, pruned_loss=0.03642, over 4897.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2306, pruned_loss=0.04736, over 971196.88 frames.], batch size: 22, lr: 5.51e-04
2022-05-04 14:09:04,147 INFO [train.py:715] (4/8) Epoch 3, batch 14000, loss[loss=0.1957, simple_loss=0.274, pruned_loss=0.05874, over 4911.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2316, pruned_loss=0.04794, over 971555.84 frames.], batch size: 23, lr: 5.51e-04
2022-05-04 14:09:45,575 INFO [train.py:715] (4/8) Epoch 3, batch 14050, loss[loss=0.1943, simple_loss=0.2454, pruned_loss=0.07158, over 4783.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2324, pruned_loss=0.04851, over 971544.58 frames.], batch size: 14, lr: 5.51e-04
2022-05-04 14:10:28,384 INFO [train.py:715] (4/8) Epoch 3, batch 14100, loss[loss=0.1344, simple_loss=0.2132, pruned_loss=0.02783, over 4943.00 frames.], tot_loss[loss=0.1653, simple_loss=0.2334, pruned_loss=0.04859, over 972454.54 frames.], batch size: 21, lr: 5.51e-04
2022-05-04 14:11:10,214 INFO [train.py:715] (4/8) Epoch 3, batch 14150, loss[loss=0.1713, simple_loss=0.2414, pruned_loss=0.05056, over 4864.00 frames.], tot_loss[loss=0.1649, simple_loss=0.2331, pruned_loss=0.04838, over 972470.84 frames.], batch size: 20, lr: 5.51e-04
2022-05-04 14:11:51,376 INFO [train.py:715] (4/8) Epoch 3, batch 14200, loss[loss=0.1595, simple_loss=0.2208, pruned_loss=0.04909, over 4848.00 frames.], tot_loss[loss=0.1645, simple_loss=0.2325, pruned_loss=0.04823, over 971971.32 frames.], batch size: 34, lr: 5.51e-04
2022-05-04 14:12:33,499 INFO [train.py:715] (4/8) Epoch 3, batch 14250, loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03108, over 4971.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2325, pruned_loss=0.04799, over 971576.28 frames.], batch size: 28, lr: 5.51e-04
2022-05-04 14:13:15,868 INFO [train.py:715] (4/8) Epoch 3, batch 14300, loss[loss=0.2049, simple_loss=0.2604, pruned_loss=0.07473, over 4985.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2314, pruned_loss=0.04709, over 971902.81 frames.], batch size: 20, lr: 5.50e-04
2022-05-04 14:13:58,164 INFO [train.py:715] (4/8) Epoch 3, batch 14350, loss[loss=0.158, simple_loss=0.2329, pruned_loss=0.04158, over 4875.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2322, pruned_loss=0.04751, over 972882.04 frames.], batch size: 22, lr: 5.50e-04
2022-05-04 14:14:38,940 INFO [train.py:715] (4/8) Epoch 3, batch 14400, loss[loss=0.1699, simple_loss=0.2469, pruned_loss=0.04645, over 4812.00 frames.], tot_loss[loss=0.1625, simple_loss=0.231, pruned_loss=0.04698, over 973067.02 frames.], batch size: 25, lr: 5.50e-04
2022-05-04 14:15:21,396 INFO [train.py:715] (4/8) Epoch 3, batch 14450, loss[loss=0.192, simple_loss=0.252, pruned_loss=0.06604, over 4813.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2318, pruned_loss=0.04768, over 973256.98 frames.], batch size: 25, lr: 5.50e-04
2022-05-04 14:16:03,335 INFO [train.py:715] (4/8) Epoch 3, batch 14500, loss[loss=0.1733, simple_loss=0.239, pruned_loss=0.05379, over 4948.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2322, pruned_loss=0.04771, over 973327.64 frames.], batch size: 14, lr: 5.50e-04
2022-05-04 14:16:44,524 INFO [train.py:715] (4/8) Epoch 3, batch 14550, loss[loss=0.1525, simple_loss=0.2219, pruned_loss=0.04155, over 4971.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2318, pruned_loss=0.04768, over 973443.10 frames.], batch size: 25, lr: 5.50e-04
2022-05-04 14:17:26,973 INFO [train.py:715] (4/8) Epoch 3, batch 14600, loss[loss=0.1563, simple_loss=0.2374, pruned_loss=0.03762, over 4883.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2318, pruned_loss=0.04773, over 972869.17 frames.], batch size: 22, lr: 5.50e-04
2022-05-04 14:18:08,849 INFO [train.py:715] (4/8) Epoch 3, batch 14650, loss[loss=0.1675, simple_loss=0.2381, pruned_loss=0.04851, over 4910.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2328, pruned_loss=0.04792, over 972207.93 frames.], batch size: 23, lr: 5.50e-04
2022-05-04 14:18:50,905 INFO [train.py:715] (4/8) Epoch 3, batch 14700, loss[loss=0.1611, simple_loss=0.2216, pruned_loss=0.05029, over 4847.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2321, pruned_loss=0.04756, over 972272.80 frames.], batch size: 32, lr: 5.49e-04
2022-05-04 14:19:32,222 INFO [train.py:715] (4/8) Epoch 3, batch 14750, loss[loss=0.1781, simple_loss=0.2507, pruned_loss=0.05276, over 4902.00 frames.], tot_loss[loss=0.164, simple_loss=0.2324, pruned_loss=0.04784, over 971682.92 frames.], batch size: 19, lr: 5.49e-04
2022-05-04 14:20:14,619 INFO [train.py:715] (4/8) Epoch 3, batch 14800, loss[loss=0.1666, simple_loss=0.2298, pruned_loss=0.05168, over 4763.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2314, pruned_loss=0.0472, over 971354.57 frames.], batch size: 19, lr: 5.49e-04
2022-05-04 14:20:56,926 INFO [train.py:715] (4/8) Epoch 3, batch 14850, loss[loss=0.1437, simple_loss=0.217, pruned_loss=0.03514, over 4911.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2318, pruned_loss=0.04719, over 971798.11 frames.], batch size: 19, lr: 5.49e-04
2022-05-04 14:21:37,847 INFO [train.py:715] (4/8) Epoch 3, batch 14900, loss[loss=0.1592, simple_loss=0.2324, pruned_loss=0.04298, over 4922.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2312, pruned_loss=0.04716, over 971641.60 frames.], batch size: 21, lr: 5.49e-04
2022-05-04 14:22:20,806 INFO [train.py:715] (4/8) Epoch 3, batch 14950, loss[loss=0.1501, simple_loss=0.216, pruned_loss=0.04216, over 4845.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2307, pruned_loss=0.04717, over 972057.32 frames.], batch size: 20, lr: 5.49e-04
2022-05-04 14:23:02,218 INFO [train.py:715] (4/8) Epoch 3, batch 15000, loss[loss=0.1666, simple_loss=0.231, pruned_loss=0.05113, over 4651.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2306, pruned_loss=0.04699, over 972232.52 frames.], batch size: 13, lr: 5.49e-04
2022-05-04 14:23:02,218 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 14:23:10,875 INFO [train.py:742] (4/8) Epoch 3, validation: loss=0.1142, simple_loss=0.2003, pruned_loss=0.01402, over 914524.00 frames.
2022-05-04 14:23:52,695 INFO [train.py:715] (4/8) Epoch 3, batch 15050, loss[loss=0.1776, simple_loss=0.2487, pruned_loss=0.0533, over 4973.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2307, pruned_loss=0.04681, over 972036.31 frames.], batch size: 14, lr: 5.49e-04
2022-05-04 14:24:34,021 INFO [train.py:715] (4/8) Epoch 3, batch 15100, loss[loss=0.1746, simple_loss=0.2396, pruned_loss=0.05482, over 4705.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2313, pruned_loss=0.04696, over 971647.38 frames.], batch size: 15, lr: 5.49e-04
2022-05-04 14:25:16,172 INFO [train.py:715] (4/8) Epoch 3, batch 15150, loss[loss=0.1843, simple_loss=0.2495, pruned_loss=0.05958, over 4798.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2317, pruned_loss=0.04678, over 972678.03 frames.], batch size: 24, lr: 5.48e-04
2022-05-04 14:25:57,800 INFO [train.py:715] (4/8) Epoch 3, batch 15200, loss[loss=0.1803, simple_loss=0.2571, pruned_loss=0.05178, over 4967.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2311, pruned_loss=0.04675, over 972356.73 frames.], batch size: 35, lr: 5.48e-04
2022-05-04 14:26:39,361 INFO [train.py:715] (4/8) Epoch 3, batch 15250, loss[loss=0.1363, simple_loss=0.1981, pruned_loss=0.03723, over 4805.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2304, pruned_loss=0.0466, over 972014.44 frames.], batch size: 12, lr: 5.48e-04
2022-05-04 14:27:20,699 INFO [train.py:715] (4/8) Epoch 3, batch 15300, loss[loss=0.1758, simple_loss=0.2503, pruned_loss=0.05066, over 4925.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2309, pruned_loss=0.04666, over 972495.18 frames.], batch size: 17, lr: 5.48e-04
2022-05-04 14:28:02,525 INFO [train.py:715] (4/8) Epoch 3, batch 15350, loss[loss=0.1773, simple_loss=0.2447, pruned_loss=0.05497, over 4984.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2305, pruned_loss=0.04638, over 972730.97 frames.], batch size: 25, lr: 5.48e-04
2022-05-04 14:28:44,649 INFO [train.py:715] (4/8) Epoch 3, batch 15400, loss[loss=0.1322, simple_loss=0.2094, pruned_loss=0.02747, over 4960.00 frames.], tot_loss[loss=0.1622, simple_loss=0.231, pruned_loss=0.0467, over 972534.13 frames.], batch size: 24, lr: 5.48e-04
2022-05-04 14:29:25,740 INFO [train.py:715] (4/8) Epoch 3, batch 15450, loss[loss=0.171, simple_loss=0.2458, pruned_loss=0.04806, over 4933.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2307, pruned_loss=0.04673, over 972609.44 frames.], batch size: 21, lr: 5.48e-04
2022-05-04 14:30:08,669 INFO [train.py:715] (4/8) Epoch 3, batch 15500, loss[loss=0.1479, simple_loss=0.213, pruned_loss=0.04144, over 4984.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2307, pruned_loss=0.04712, over 971747.45 frames.], batch size: 35, lr: 5.48e-04
2022-05-04 14:30:50,501 INFO [train.py:715] (4/8) Epoch 3, batch 15550, loss[loss=0.2062, simple_loss=0.2833, pruned_loss=0.06459, over 4913.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2322, pruned_loss=0.04778, over 972352.90 frames.], batch size: 17, lr: 5.48e-04
2022-05-04 14:31:35,081 INFO [train.py:715] (4/8) Epoch 3, batch 15600, loss[loss=0.1529, simple_loss=0.2305, pruned_loss=0.03767, over 4951.00 frames.], tot_loss[loss=0.1646, simple_loss=0.2327, pruned_loss=0.04829, over 972814.04 frames.], batch size: 21, lr: 5.47e-04
2022-05-04 14:32:16,087 INFO [train.py:715] (4/8) Epoch 3, batch 15650, loss[loss=0.1713, simple_loss=0.2442, pruned_loss=0.04918, over 4789.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2325, pruned_loss=0.04793, over 972939.70 frames.], batch size: 17, lr: 5.47e-04
2022-05-04 14:32:57,682 INFO [train.py:715] (4/8) Epoch 3, batch 15700, loss[loss=0.1863, simple_loss=0.2516, pruned_loss=0.06049, over 4751.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2321, pruned_loss=0.0478, over 971780.61 frames.], batch size: 19, lr: 5.47e-04
2022-05-04 14:33:40,519 INFO [train.py:715] (4/8) Epoch 3, batch 15750, loss[loss=0.1594, simple_loss=0.2349, pruned_loss=0.04192, over 4889.00 frames.], tot_loss[loss=0.163, simple_loss=0.2312, pruned_loss=0.04744, over 972721.95 frames.], batch size: 16, lr: 5.47e-04
2022-05-04 14:34:22,322 INFO [train.py:715] (4/8) Epoch 3, batch 15800, loss[loss=0.2298, simple_loss=0.2875, pruned_loss=0.08603, over 4971.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2317, pruned_loss=0.0477, over 972460.31 frames.], batch size: 39, lr: 5.47e-04
2022-05-04 14:35:03,570 INFO [train.py:715] (4/8) Epoch 3, batch 15850, loss[loss=0.1691, simple_loss=0.2297, pruned_loss=0.05426, over 4776.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2308, pruned_loss=0.04685, over 972821.62 frames.], batch size: 14, lr: 5.47e-04
2022-05-04 14:35:45,947 INFO [train.py:715] (4/8) Epoch 3, batch 15900, loss[loss=0.163, simple_loss=0.219, pruned_loss=0.05346, over 4736.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2311, pruned_loss=0.04718, over 971849.68 frames.], batch size: 12, lr: 5.47e-04
2022-05-04 14:36:28,583 INFO [train.py:715] (4/8) Epoch 3, batch 15950, loss[loss=0.153, simple_loss=0.2297, pruned_loss=0.03813, over 4969.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2317, pruned_loss=0.04744, over 971927.37 frames.], batch size: 24, lr: 5.47e-04
2022-05-04 14:37:09,186 INFO [train.py:715] (4/8) Epoch 3, batch 16000, loss[loss=0.1477, simple_loss=0.2105, pruned_loss=0.04241, over 4696.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2317, pruned_loss=0.04749, over 971726.46 frames.], batch size: 15, lr: 5.47e-04
2022-05-04 14:37:50,853 INFO [train.py:715] (4/8) Epoch 3, batch 16050, loss[loss=0.1584, simple_loss=0.2239, pruned_loss=0.04645, over 4880.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2317, pruned_loss=0.04744, over 972074.91 frames.], batch size: 16, lr: 5.46e-04
2022-05-04 14:38:33,464 INFO [train.py:715] (4/8) Epoch 3, batch 16100, loss[loss=0.1978, simple_loss=0.2703, pruned_loss=0.06262, over 4811.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2317, pruned_loss=0.04722, over 972607.14 frames.], batch size: 21, lr: 5.46e-04
2022-05-04 14:39:15,433 INFO [train.py:715] (4/8) Epoch 3, batch 16150, loss[loss=0.1564, simple_loss=0.2222, pruned_loss=0.04529, over 4915.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2326, pruned_loss=0.04777, over 971611.40 frames.], batch size: 23, lr: 5.46e-04
2022-05-04 14:39:56,172 INFO [train.py:715] (4/8) Epoch 3, batch 16200, loss[loss=0.1188, simple_loss=0.1877, pruned_loss=0.02498, over 4820.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2328, pruned_loss=0.04747, over 971308.73 frames.], batch size: 12, lr: 5.46e-04
2022-05-04 14:40:38,466 INFO [train.py:715] (4/8) Epoch 3, batch 16250, loss[loss=0.2155, simple_loss=0.2935, pruned_loss=0.06878, over 4701.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2324, pruned_loss=0.04713, over 971734.09 frames.], batch size: 15, lr: 5.46e-04
2022-05-04 14:41:20,554 INFO [train.py:715] (4/8) Epoch 3, batch 16300, loss[loss=0.152, simple_loss=0.2241, pruned_loss=0.03996, over 4919.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2314, pruned_loss=0.04648, over 971807.87 frames.], batch size: 39, lr: 5.46e-04
2022-05-04 14:42:01,209 INFO [train.py:715] (4/8) Epoch 3, batch 16350, loss[loss=0.1452, simple_loss=0.2212, pruned_loss=0.03464, over 4763.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2314, pruned_loss=0.04666, over 971375.95 frames.], batch size: 14, lr: 5.46e-04
2022-05-04 14:42:43,174 INFO [train.py:715] (4/8) Epoch 3, batch 16400, loss[loss=0.1654, simple_loss=0.2346, pruned_loss=0.04807, over 4944.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2315, pruned_loss=0.04695, over 971109.70 frames.], batch size: 24, lr: 5.46e-04
2022-05-04 14:43:25,709 INFO [train.py:715] (4/8) Epoch 3, batch 16450, loss[loss=0.1904, simple_loss=0.2414, pruned_loss=0.06969, over 4826.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2314, pruned_loss=0.04707, over 970755.00 frames.], batch size: 25, lr: 5.45e-04
2022-05-04 14:44:08,343 INFO [train.py:715] (4/8) Epoch 3, batch 16500, loss[loss=0.1596, simple_loss=0.2236, pruned_loss=0.04779, over 4849.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2316, pruned_loss=0.04727, over 970775.89 frames.], batch size: 32, lr: 5.45e-04
2022-05-04 14:44:49,048 INFO [train.py:715] (4/8) Epoch 3, batch 16550, loss[loss=0.1643, simple_loss=0.2406, pruned_loss=0.04402, over 4874.00 frames.], tot_loss[loss=0.163, simple_loss=0.2319, pruned_loss=0.04705, over 971102.69 frames.], batch size: 22, lr: 5.45e-04
2022-05-04 14:45:31,906 INFO [train.py:715] (4/8) Epoch 3, batch 16600, loss[loss=0.1897, simple_loss=0.2511, pruned_loss=0.06414, over 4841.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2313, pruned_loss=0.04662, over 971725.16 frames.], batch size: 32, lr: 5.45e-04
2022-05-04 14:46:14,682 INFO [train.py:715] (4/8) Epoch 3, batch 16650, loss[loss=0.1621, simple_loss=0.224, pruned_loss=0.05004, over 4986.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2316, pruned_loss=0.04673, over 971822.22 frames.], batch size: 25, lr: 5.45e-04
2022-05-04 14:46:55,380 INFO [train.py:715] (4/8) Epoch 3, batch 16700, loss[loss=0.1594, simple_loss=0.2304, pruned_loss=0.04416, over 4817.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2324, pruned_loss=0.04745, over 972463.33 frames.], batch size: 25, lr: 5.45e-04
2022-05-04 14:47:37,395 INFO [train.py:715] (4/8) Epoch 3, batch 16750, loss[loss=0.1725, simple_loss=0.2421, pruned_loss=0.05148, over 4765.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2326, pruned_loss=0.04715, over 972296.68 frames.], batch size: 19, lr: 5.45e-04
2022-05-04 14:48:19,853 INFO [train.py:715] (4/8) Epoch 3, batch 16800, loss[loss=0.1502, simple_loss=0.2194, pruned_loss=0.04049, over 4969.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2324, pruned_loss=0.04718, over 972087.15 frames.], batch size: 24, lr: 5.45e-04
2022-05-04 14:49:01,320 INFO [train.py:715] (4/8) Epoch 3, batch 16850, loss[loss=0.1927, simple_loss=0.2571, pruned_loss=0.06414, over 4872.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2323, pruned_loss=0.04739, over 972051.58 frames.], batch size: 20, lr: 5.45e-04
2022-05-04 14:49:42,723 INFO [train.py:715] (4/8) Epoch 3, batch 16900, loss[loss=0.1606, simple_loss=0.2353, pruned_loss=0.04292, over 4907.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2327, pruned_loss=0.04792, over 972193.12 frames.], batch size: 19, lr: 5.44e-04
2022-05-04 14:50:24,672 INFO [train.py:715] (4/8) Epoch 3, batch 16950, loss[loss=0.1791, simple_loss=0.2504, pruned_loss=0.05387, over 4866.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2329, pruned_loss=0.04781, over 972326.00 frames.], batch size: 20, lr: 5.44e-04
2022-05-04 14:51:07,222 INFO [train.py:715] (4/8) Epoch 3, batch 17000, loss[loss=0.1591, simple_loss=0.2372, pruned_loss=0.04045, over 4946.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2328, pruned_loss=0.0474, over 972024.95 frames.], batch size: 21, lr: 5.44e-04
2022-05-04 14:51:47,552 INFO [train.py:715] (4/8) Epoch 3, batch 17050, loss[loss=0.1588, simple_loss=0.2206, pruned_loss=0.04848, over 4991.00 frames.], tot_loss[loss=0.1644, simple_loss=0.233, pruned_loss=0.04787, over 973276.31 frames.], batch size: 16, lr: 5.44e-04
2022-05-04 14:52:29,475 INFO [train.py:715] (4/8) Epoch 3, batch 17100, loss[loss=0.1784, simple_loss=0.2519, pruned_loss=0.05243, over 4944.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2327, pruned_loss=0.04787, over 974152.37 frames.], batch size: 39, lr: 5.44e-04
2022-05-04 14:53:11,170 INFO [train.py:715] (4/8) Epoch 3, batch 17150, loss[loss=0.163, simple_loss=0.2313, pruned_loss=0.04737, over 4849.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2318, pruned_loss=0.04724, over 973197.27 frames.], batch size: 15, lr: 5.44e-04
2022-05-04 14:53:52,350 INFO [train.py:715] (4/8) Epoch 3, batch 17200, loss[loss=0.1558, simple_loss=0.226, pruned_loss=0.0428, over 4969.00 frames.], tot_loss[loss=0.1622, simple_loss=0.231, pruned_loss=0.04664, over 973129.88 frames.], batch size: 24, lr: 5.44e-04
2022-05-04 14:54:33,046 INFO [train.py:715] (4/8) Epoch 3, batch 17250, loss[loss=0.177, simple_loss=0.2397, pruned_loss=0.05718, over 4811.00 frames.], tot_loss[loss=0.1626, simple_loss=0.231, pruned_loss=0.04711, over 972144.51 frames.], batch size: 13, lr: 5.44e-04
2022-05-04 14:55:14,506 INFO [train.py:715] (4/8) Epoch 3, batch 17300, loss[loss=0.1511, simple_loss=0.212, pruned_loss=0.0451, over 4975.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2309, pruned_loss=0.04689, over 971324.63 frames.], batch size: 14, lr: 5.44e-04
2022-05-04 14:55:56,122 INFO [train.py:715] (4/8) Epoch 3, batch 17350, loss[loss=0.1535, simple_loss=0.214, pruned_loss=0.04644, over 4956.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2312, pruned_loss=0.04709, over 971761.93 frames.], batch size: 21, lr: 5.43e-04
2022-05-04 14:56:36,179 INFO [train.py:715] (4/8) Epoch 3, batch 17400, loss[loss=0.1598, simple_loss=0.2215, pruned_loss=0.04906, over 4798.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2312, pruned_loss=0.04733, over 972385.67 frames.], batch size: 14, lr: 5.43e-04
2022-05-04 14:57:18,240 INFO [train.py:715] (4/8) Epoch 3, batch 17450, loss[loss=0.2056, simple_loss=0.2837, pruned_loss=0.06375, over 4747.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2314, pruned_loss=0.04758, over 971380.66 frames.], batch size: 19, lr: 5.43e-04
2022-05-04 14:58:00,465 INFO [train.py:715] (4/8) Epoch 3, batch 17500, loss[loss=0.1732, simple_loss=0.2364, pruned_loss=0.05495, over 4933.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2313, pruned_loss=0.04716, over 972664.25 frames.], batch size: 29, lr: 5.43e-04
2022-05-04 14:58:41,511 INFO [train.py:715] (4/8) Epoch 3, batch 17550, loss[loss=0.1575, simple_loss=0.226, pruned_loss=0.04451, over 4861.00 frames.], tot_loss[loss=0.1625, simple_loss=0.231, pruned_loss=0.04704, over 971983.94 frames.], batch size: 32, lr: 5.43e-04
2022-05-04 14:59:22,848 INFO [train.py:715] (4/8) Epoch 3, batch 17600, loss[loss=0.185, simple_loss=0.2368, pruned_loss=0.06658, over 4759.00 frames.], tot_loss[loss=0.1616, simple_loss=0.23, pruned_loss=0.04663, over 971793.03 frames.], batch size: 19, lr: 5.43e-04
2022-05-04 15:00:04,538 INFO [train.py:715] (4/8) Epoch 3, batch 17650, loss[loss=0.1463, simple_loss=0.2205, pruned_loss=0.03611, over 4982.00 frames.], tot_loss[loss=0.163, simple_loss=0.2312, pruned_loss=0.04741, over 972079.62 frames.], batch size: 15, lr: 5.43e-04
2022-05-04 15:00:46,077 INFO [train.py:715] (4/8) Epoch 3, batch 17700, loss[loss=0.1734, simple_loss=0.2422, pruned_loss=0.05226, over 4889.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2314, pruned_loss=0.04744, over 972382.99 frames.], batch size: 22, lr: 5.43e-04
2022-05-04 15:01:26,896 INFO [train.py:715] (4/8) Epoch 3, batch 17750, loss[loss=0.1711, simple_loss=0.2427, pruned_loss=0.04974, over 4970.00 frames.], tot_loss[loss=0.1639, simple_loss=0.2319, pruned_loss=0.04792, over 973185.06 frames.], batch size: 39, lr: 5.43e-04
2022-05-04 15:02:08,924 INFO [train.py:715] (4/8) Epoch 3, batch 17800, loss[loss=0.1716, simple_loss=0.2351, pruned_loss=0.05408, over 4926.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2318, pruned_loss=0.04791, over 973541.31 frames.], batch size: 18, lr: 5.42e-04
2022-05-04 15:02:50,346 INFO [train.py:715] (4/8) Epoch 3, batch 17850, loss[loss=0.1305, simple_loss=0.2024, pruned_loss=0.02931, over 4808.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2308, pruned_loss=0.04714, over 972554.10 frames.], batch size: 21, lr: 5.42e-04
2022-05-04 15:03:30,304 INFO [train.py:715] (4/8) Epoch 3, batch 17900, loss[loss=0.1555, simple_loss=0.2258, pruned_loss=0.04258, over 4986.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2315, pruned_loss=0.04746, over 971699.94 frames.], batch size: 26, lr: 5.42e-04
2022-05-04 15:04:12,133 INFO [train.py:715] (4/8) Epoch 3, batch 17950, loss[loss=0.1643, simple_loss=0.2337, pruned_loss=0.04747, over 4910.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2311, pruned_loss=0.04771, over 971628.67 frames.], batch size: 18, lr: 5.42e-04
2022-05-04 15:04:53,392 INFO [train.py:715] (4/8) Epoch 3, batch 18000, loss[loss=0.1693, simple_loss=0.2506, pruned_loss=0.04399, over 4804.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2321, pruned_loss=0.04821, over 973193.24 frames.], batch size: 25, lr: 5.42e-04
2022-05-04 15:04:53,393 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 15:05:02,069 INFO [train.py:742] (4/8) Epoch 3, validation: loss=0.1143, simple_loss=0.2002, pruned_loss=0.01414, over 914524.00 frames.
2022-05-04 15:05:43,854 INFO [train.py:715] (4/8) Epoch 3, batch 18050, loss[loss=0.2024, simple_loss=0.2572, pruned_loss=0.07379, over 4846.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2317, pruned_loss=0.04787, over 974005.09 frames.], batch size: 30, lr: 5.42e-04
2022-05-04 15:06:25,498 INFO [train.py:715] (4/8) Epoch 3, batch 18100, loss[loss=0.1527, simple_loss=0.2287, pruned_loss=0.03828, over 4926.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2316, pruned_loss=0.04763, over 973781.22 frames.], batch size: 18, lr: 5.42e-04
2022-05-04 15:07:06,180 INFO [train.py:715] (4/8) Epoch 3, batch 18150, loss[loss=0.1636, simple_loss=0.2259, pruned_loss=0.05068, over 4786.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2317, pruned_loss=0.04734, over 973638.97 frames.], batch size: 12, lr: 5.42e-04
2022-05-04 15:07:47,675 INFO [train.py:715] (4/8) Epoch 3, batch 18200, loss[loss=0.1323, simple_loss=0.2006, pruned_loss=0.032, over 4978.00 frames.], tot_loss[loss=0.1637, simple_loss=0.232, pruned_loss=0.04765, over 973386.10 frames.], batch size: 15, lr: 5.42e-04
2022-05-04 15:08:29,487 INFO [train.py:715] (4/8) Epoch 3, batch 18250, loss[loss=0.1958, simple_loss=0.2604, pruned_loss=0.0656, over 4899.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2322, pruned_loss=0.04743, over 973328.11 frames.], batch size: 19, lr: 5.41e-04
2022-05-04 15:09:10,282 INFO [train.py:715] (4/8) Epoch 3, batch 18300, loss[loss=0.1596, simple_loss=0.232, pruned_loss=0.04364, over 4810.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2314, pruned_loss=0.04714, over 972306.98 frames.], batch size: 21, lr: 5.41e-04
2022-05-04 15:09:51,608 INFO [train.py:715] (4/8) Epoch 3, batch 18350, loss[loss=0.1423, simple_loss=0.2145, pruned_loss=0.03504, over 4889.00 frames.], tot_loss[loss=0.1626, simple_loss=0.231, pruned_loss=0.04712, over 971155.68 frames.], batch size: 22, lr: 5.41e-04
2022-05-04 15:10:33,019 INFO [train.py:715] (4/8) Epoch 3, batch 18400, loss[loss=0.1356, simple_loss=0.2132, pruned_loss=0.029, over 4791.00 frames.], tot_loss[loss=0.163, simple_loss=0.2318, pruned_loss=0.04707, over 971415.70 frames.], batch size: 24, lr: 5.41e-04
2022-05-04 15:11:13,985 INFO [train.py:715] (4/8) Epoch 3, batch 18450, loss[loss=0.1504, simple_loss=0.223, pruned_loss=0.03893, over 4786.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2333, pruned_loss=0.04744, over 970967.75 frames.], batch size: 17, lr: 5.41e-04
2022-05-04 15:11:55,015 INFO [train.py:715] (4/8) Epoch 3, batch 18500, loss[loss=0.1476, simple_loss=0.219, pruned_loss=0.03813, over 4949.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2336, pruned_loss=0.04745, over 971267.30 frames.], batch size: 21, lr: 5.41e-04
2022-05-04 15:12:36,386 INFO [train.py:715] (4/8) Epoch 3, batch 18550, loss[loss=0.1521, simple_loss=0.2255, pruned_loss=0.03937, over 4947.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2328, pruned_loss=0.04733, over 971186.14 frames.], batch size: 39, lr: 5.41e-04
2022-05-04 15:13:18,620 INFO [train.py:715] (4/8) Epoch 3, batch 18600, loss[loss=0.1773, simple_loss=0.2497, pruned_loss=0.05244, over 4988.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2322, pruned_loss=0.04739, over 971519.09 frames.], batch size: 33, lr: 5.41e-04
2022-05-04 15:13:58,616 INFO [train.py:715] (4/8) Epoch 3, batch 18650, loss[loss=0.1584, simple_loss=0.2393, pruned_loss=0.03875, over 4886.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2315, pruned_loss=0.0472, over 971677.74 frames.], batch size: 22, lr: 5.41e-04
2022-05-04 15:14:39,316 INFO [train.py:715] (4/8) Epoch 3, batch 18700, loss[loss=0.1629, simple_loss=0.227, pruned_loss=0.04939, over 4747.00 frames.], tot_loss[loss=0.1636, simple_loss=0.232, pruned_loss=0.04763, over 972208.22 frames.], batch size: 19, lr: 5.40e-04
2022-05-04 15:15:20,414 INFO [train.py:715] (4/8) Epoch 3, batch 18750, loss[loss=0.1312, simple_loss=0.2027, pruned_loss=0.02983, over 4850.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2313, pruned_loss=0.04724, over 973230.08 frames.], batch size: 15, lr: 5.40e-04
2022-05-04 15:16:00,276 INFO [train.py:715] (4/8) Epoch 3, batch 18800, loss[loss=0.1544, simple_loss=0.2347, pruned_loss=0.03704, over 4687.00 frames.], tot_loss[loss=0.1627, simple_loss=0.231, pruned_loss=0.04717, over 972471.90 frames.], batch size: 15, lr: 5.40e-04
2022-05-04 15:16:41,092 INFO [train.py:715] (4/8) Epoch 3, batch 18850, loss[loss=0.1799, simple_loss=0.2645, pruned_loss=0.04762, over 4799.00 frames.], tot_loss[loss=0.164, simple_loss=0.2323, pruned_loss=0.0479, over 971834.42 frames.], batch size: 24, lr: 5.40e-04
2022-05-04 15:17:21,057 INFO [train.py:715] (4/8) Epoch 3, batch 18900, loss[loss=0.1391, simple_loss=0.2117, pruned_loss=0.03328, over 4962.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2311, pruned_loss=0.04758, over 971874.24 frames.], batch size: 28, lr: 5.40e-04
2022-05-04 15:18:01,553 INFO [train.py:715] (4/8) Epoch 3, batch 18950, loss[loss=0.1469, simple_loss=0.2101, pruned_loss=0.04185, over 4649.00 frames.], tot_loss[loss=0.164, simple_loss=0.232, pruned_loss=0.04797, over 971828.19 frames.], batch size: 13, lr: 5.40e-04
2022-05-04 15:18:40,943 INFO [train.py:715] (4/8) Epoch 3, batch 19000, loss[loss=0.1701, simple_loss=0.232, pruned_loss=0.05411, over 4988.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2314, pruned_loss=0.0474, over 972221.86 frames.], batch size: 28, lr: 5.40e-04
2022-05-04 15:19:20,769 INFO [train.py:715] (4/8) Epoch 3, batch 19050, loss[loss=0.1453, simple_loss=0.2126, pruned_loss=0.03902, over 4927.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2313, pruned_loss=0.04752, over 971779.59 frames.], batch size: 18, lr: 5.40e-04
2022-05-04 15:20:01,078 INFO [train.py:715] (4/8) Epoch 3, batch 19100, loss[loss=0.2052, simple_loss=0.256, pruned_loss=0.07724, over 4844.00 frames.], tot_loss[loss=0.163, simple_loss=0.2313, pruned_loss=0.04736, over 972056.85 frames.], batch size: 32, lr: 5.40e-04
2022-05-04 15:20:40,498 INFO [train.py:715] (4/8) Epoch 3, batch 19150, loss[loss=0.1654, simple_loss=0.2247, pruned_loss=0.05306, over 4864.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2314, pruned_loss=0.04696, over 971798.34 frames.], batch size: 32, lr: 5.40e-04
2022-05-04 15:21:20,179 INFO [train.py:715] (4/8) Epoch 3, batch 19200, loss[loss=0.1694, simple_loss=0.2397, pruned_loss=0.04959, over 4899.00 frames.], tot_loss[loss=0.1636, simple_loss=0.232, pruned_loss=0.04764, over 972080.69 frames.], batch size: 19, lr: 5.39e-04
2022-05-04 15:21:59,821 INFO [train.py:715] (4/8) Epoch 3, batch 19250, loss[loss=0.1301, simple_loss=0.2069, pruned_loss=0.02658, over 4936.00 frames.], tot_loss[loss=0.1643, simple_loss=0.2326, pruned_loss=0.04799, over 972580.28 frames.], batch size: 23, lr: 5.39e-04
2022-05-04 15:22:40,130 INFO [train.py:715] (4/8) Epoch 3, batch 19300, loss[loss=0.1504, simple_loss=0.2272, pruned_loss=0.0368, over 4949.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2314, pruned_loss=0.04684, over 973223.20 frames.], batch size: 21, lr: 5.39e-04
2022-05-04 15:23:19,471 INFO [train.py:715] (4/8) Epoch 3, batch 19350, loss[loss=0.2207, simple_loss=0.2996, pruned_loss=0.07087, over 4694.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2315, pruned_loss=0.04719, over 972837.30 frames.], batch size: 15, lr: 5.39e-04
2022-05-04 15:23:59,201 INFO [train.py:715] (4/8) Epoch 3, batch 19400, loss[loss=0.2069, simple_loss=0.2684, pruned_loss=0.07274, over 4854.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2311, pruned_loss=0.04703, over 972593.55 frames.], batch size: 34, lr: 5.39e-04
2022-05-04 15:24:39,294 INFO [train.py:715] (4/8) Epoch 3, batch 19450, loss[loss=0.1403, simple_loss=0.2208, pruned_loss=0.02991, over 4938.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2312, pruned_loss=0.04702, over 972815.61 frames.], batch size: 23, lr: 5.39e-04
2022-05-04 15:25:18,371 INFO [train.py:715] (4/8) Epoch 3, batch 19500, loss[loss=0.187, simple_loss=0.2422, pruned_loss=0.06594, over 4883.00 frames.], tot_loss[loss=0.163, simple_loss=0.2312, pruned_loss=0.04742, over 972823.92 frames.], batch size: 16, lr: 5.39e-04
2022-05-04 15:25:58,126 INFO [train.py:715] (4/8) Epoch 3, batch 19550, loss[loss=0.1613, simple_loss=0.232, pruned_loss=0.04526, over 4817.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2305, pruned_loss=0.04712, over 972499.24 frames.], batch size: 26, lr: 5.39e-04
2022-05-04 15:26:37,672 INFO [train.py:715] (4/8) Epoch 3, batch 19600, loss[loss=0.1707, simple_loss=0.2306, pruned_loss=0.05541, over 4830.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2308, pruned_loss=0.04726, over 972707.81 frames.], batch size: 30, lr: 5.39e-04
2022-05-04 15:27:17,574 INFO [train.py:715] (4/8) Epoch 3, batch 19650, loss[loss=0.1425, simple_loss=0.2232, pruned_loss=0.0309, over 4975.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2316, pruned_loss=0.04776, over 971976.75 frames.], batch size: 25, lr: 5.38e-04
2022-05-04 15:27:56,472 INFO [train.py:715] (4/8) Epoch 3, batch 19700, loss[loss=0.1848, simple_loss=0.2451, pruned_loss=0.06225, over 4793.00 frames.], tot_loss[loss=0.1657, simple_loss=0.2331, pruned_loss=0.04919, over 972295.06 frames.], batch size: 14, lr: 5.38e-04
2022-05-04 15:28:36,069 INFO [train.py:715] (4/8) Epoch 3, batch 19750, loss[loss=0.1581, simple_loss=0.2241, pruned_loss=0.04604, over 4930.00 frames.], tot_loss[loss=0.1651, simple_loss=0.2326, pruned_loss=0.04877, over 972730.16 frames.], batch size: 23, lr: 5.38e-04
2022-05-04 15:29:15,546 INFO [train.py:715] (4/8) Epoch 3, batch 19800, loss[loss=0.1626, simple_loss=0.2243, pruned_loss=0.05047, over 4688.00 frames.], tot_loss[loss=0.1641, simple_loss=0.2317, pruned_loss=0.04822, over 972048.94 frames.], batch size: 15, lr: 5.38e-04
2022-05-04 15:29:55,117 INFO [train.py:715] (4/8) Epoch 3, batch 19850, loss[loss=0.1638, simple_loss=0.2321, pruned_loss=0.04774, over 4877.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2312, pruned_loss=0.0475, over 971973.53 frames.], batch size: 38, lr: 5.38e-04
2022-05-04 15:30:34,817 INFO [train.py:715] (4/8) Epoch 3, batch 19900, loss[loss=0.1371, simple_loss=0.2059, pruned_loss=0.03418, over 4809.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2312, pruned_loss=0.04759, over 972883.18 frames.], batch size: 21, lr: 5.38e-04
2022-05-04 15:31:15,111 INFO [train.py:715] (4/8) Epoch 3, batch 19950, loss[loss=0.1347, simple_loss=0.2161, pruned_loss=0.02667, over 4946.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2309, pruned_loss=0.04704, over 972390.64 frames.], batch size: 18, lr: 5.38e-04
2022-05-04 15:31:54,891 INFO [train.py:715] (4/8) Epoch 3, batch 20000, loss[loss=0.1677, simple_loss=0.2427, pruned_loss=0.04639, over 4790.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2306, pruned_loss=0.04678, over 973065.61 frames.], batch size: 17, lr: 5.38e-04
2022-05-04 15:32:34,160 INFO [train.py:715] (4/8) Epoch 3, batch 20050, loss[loss=0.1495, simple_loss=0.2127, pruned_loss=0.04316, over 4982.00 frames.], tot_loss[loss=0.16, simple_loss=0.2289, pruned_loss=0.04555, over 972914.61 frames.], batch size: 14, lr: 5.38e-04
2022-05-04 15:33:14,398 INFO [train.py:715] (4/8) Epoch 3, batch 20100, loss[loss=0.187, simple_loss=0.2549, pruned_loss=0.05951, over 4757.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2297, pruned_loss=0.04569, over 973263.37 frames.], batch size: 16, lr: 5.37e-04
2022-05-04 15:33:54,295 INFO [train.py:715] (4/8) Epoch 3, batch 20150, loss[loss=0.1585, simple_loss=0.2371, pruned_loss=0.03993, over 4751.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2304, pruned_loss=0.04613, over 973244.61 frames.], batch size: 19, lr: 5.37e-04
2022-05-04 15:34:33,627 INFO [train.py:715] (4/8) Epoch 3, batch 20200, loss[loss=0.2058, simple_loss=0.2697, pruned_loss=0.07098, over 4941.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2295, pruned_loss=0.04563, over 973268.39 frames.], batch size: 39, lr: 5.37e-04
2022-05-04 15:35:13,294 INFO [train.py:715] (4/8) Epoch 3, batch 20250, loss[loss=0.1695, simple_loss=0.2477, pruned_loss=0.04569, over 4962.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2294, pruned_loss=0.04542, over 973043.74 frames.], batch size: 24, lr: 5.37e-04
2022-05-04 15:35:53,118 INFO [train.py:715] (4/8) Epoch 3, batch 20300, loss[loss=0.1931, simple_loss=0.2423, pruned_loss=0.07199, over 4689.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2302, pruned_loss=0.04625, over 973217.26 frames.], batch size: 15, lr: 5.37e-04
2022-05-04 15:36:33,505 INFO [train.py:715] (4/8) Epoch 3, batch 20350, loss[loss=0.1629, simple_loss=0.2251, pruned_loss=0.05036, over 4985.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2304, pruned_loss=0.04656, over 972221.41 frames.], batch size: 14, lr: 5.37e-04
2022-05-04 15:37:12,085 INFO [train.py:715] (4/8) Epoch 3, batch 20400, loss[loss=0.1591, simple_loss=0.2384, pruned_loss=0.03988, over 4981.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2301, pruned_loss=0.04609, over 972232.21 frames.], batch size: 25, lr: 5.37e-04
2022-05-04 15:37:51,789 INFO [train.py:715] (4/8) Epoch 3, batch 20450, loss[loss=0.1807, simple_loss=0.2445, pruned_loss=0.05851, over 4847.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2303, pruned_loss=0.04597, over 972643.83 frames.], batch size: 30, lr: 5.37e-04
2022-05-04 15:38:31,858 INFO [train.py:715] (4/8) Epoch 3, batch 20500, loss[loss=0.1331, simple_loss=0.2035, pruned_loss=0.03132, over 4790.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2302, pruned_loss=0.04629, over 972617.79 frames.], batch size: 13, lr: 5.37e-04
2022-05-04 15:39:10,979 INFO [train.py:715] (4/8) Epoch 3, batch 20550, loss[loss=0.1564, simple_loss=0.2318, pruned_loss=0.04046, over 4853.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2315, pruned_loss=0.04718, over 971479.79 frames.], batch size: 20, lr: 5.36e-04
2022-05-04 15:39:50,434 INFO [train.py:715] (4/8) Epoch 3, batch 20600, loss[loss=0.2115, simple_loss=0.2885, pruned_loss=0.06723, over 4898.00 frames.], tot_loss[loss=0.1647, simple_loss=0.2329, pruned_loss=0.04822, over 971873.10 frames.], batch size: 16, lr: 5.36e-04
2022-05-04 15:40:30,882 INFO [train.py:715] (4/8) Epoch 3, batch 20650, loss[loss=0.1663, simple_loss=0.2321, pruned_loss=0.0502, over 4923.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2322, pruned_loss=0.04769, over 972753.20 frames.], batch size: 18, lr: 5.36e-04
2022-05-04 15:41:10,735 INFO [train.py:715] (4/8) Epoch 3, batch 20700, loss[loss=0.1672, simple_loss=0.236, pruned_loss=0.04915, over 4835.00 frames.], tot_loss[loss=0.1637, simple_loss=0.232, pruned_loss=0.04774, over 973146.99 frames.], batch size: 15, lr: 5.36e-04
2022-05-04 15:41:50,196 INFO [train.py:715] (4/8) Epoch 3, batch 20750, loss[loss=0.1638, simple_loss=0.238, pruned_loss=0.04481, over 4859.00 frames.], tot_loss[loss=0.163, simple_loss=0.2315, pruned_loss=0.04723, over 972800.96 frames.], batch size: 20, lr: 5.36e-04
2022-05-04 15:42:30,288 INFO [train.py:715] (4/8) Epoch 3, batch 20800, loss[loss=0.1603, simple_loss=0.2234, pruned_loss=0.04863, over 4952.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2305, pruned_loss=0.04656, over 972438.47 frames.], batch size: 23, lr: 5.36e-04
2022-05-04 15:43:11,025 INFO [train.py:715] (4/8) Epoch 3, batch 20850, loss[loss=0.1615, simple_loss=0.2217, pruned_loss=0.05064, over 4892.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2301, pruned_loss=0.04635, over 972265.49 frames.], batch size: 22, lr: 5.36e-04
2022-05-04 15:43:50,800 INFO [train.py:715] (4/8) Epoch 3, batch 20900, loss[loss=0.1683, simple_loss=0.2513, pruned_loss=0.04261, over 4790.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2302, pruned_loss=0.04676, over 972199.27 frames.], batch size: 18, lr: 5.36e-04
2022-05-04 15:44:31,205 INFO [train.py:715] (4/8) Epoch 3, batch 20950, loss[loss=0.1272, simple_loss=0.1858, pruned_loss=0.03436, over 4788.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2298, pruned_loss=0.04666, over 972767.89 frames.], batch size: 12, lr: 5.36e-04
2022-05-04 15:45:11,740 INFO [train.py:715] (4/8) Epoch 3, batch 21000, loss[loss=0.1603, simple_loss=0.2348, pruned_loss=0.04292, over 4952.00 frames.], tot_loss[loss=0.1619, simple_loss=0.23, pruned_loss=0.04692, over 972847.69 frames.], batch size: 29, lr: 5.36e-04
2022-05-04 15:45:11,741 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 15:45:24,192 INFO [train.py:742] (4/8) Epoch 3, validation: loss=0.1137, simple_loss=0.1999, pruned_loss=0.01377, over 914524.00 frames.
2022-05-04 15:46:04,593 INFO [train.py:715] (4/8) Epoch 3, batch 21050, loss[loss=0.1467, simple_loss=0.211, pruned_loss=0.04118, over 4809.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2298, pruned_loss=0.04638, over 972296.67 frames.], batch size: 13, lr: 5.35e-04
2022-05-04 15:46:45,374 INFO [train.py:715] (4/8) Epoch 3, batch 21100, loss[loss=0.1726, simple_loss=0.233, pruned_loss=0.05608, over 4842.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2309, pruned_loss=0.04707, over 972089.69 frames.], batch size: 32, lr: 5.35e-04
2022-05-04 15:47:25,755 INFO [train.py:715] (4/8) Epoch 3, batch 21150, loss[loss=0.1966, simple_loss=0.2635, pruned_loss=0.06487, over 4985.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2316, pruned_loss=0.04772, over 973364.06 frames.], batch size: 28, lr: 5.35e-04
2022-05-04 15:48:08,563 INFO [train.py:715] (4/8) Epoch 3, batch 21200, loss[loss=0.1506, simple_loss=0.2146, pruned_loss=0.04336, over 4968.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2318, pruned_loss=0.04776, over 973678.33 frames.], batch size: 15, lr: 5.35e-04
2022-05-04 15:48:49,621 INFO [train.py:715] (4/8) Epoch 3, batch 21250, loss[loss=0.1377, simple_loss=0.2133, pruned_loss=0.031, over 4981.00 frames.], tot_loss[loss=0.1629, simple_loss=0.231, pruned_loss=0.04738, over 973431.23 frames.], batch size: 25, lr: 5.35e-04
2022-05-04 15:49:28,343 INFO [train.py:715] (4/8) Epoch 3, batch 21300, loss[loss=0.1742, simple_loss=0.2349, pruned_loss=0.0567, over 4864.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2304, pruned_loss=0.04711, over 972438.31 frames.], batch size: 32, lr: 5.35e-04
2022-05-04 15:50:10,525 INFO [train.py:715] (4/8) Epoch 3, batch 21350, loss[loss=0.1451, simple_loss=0.2177, pruned_loss=0.03629, over 4916.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2296, pruned_loss=0.04658, over 972772.26 frames.], batch size: 18, lr: 5.35e-04
2022-05-04 15:50:51,356 INFO [train.py:715] (4/8) Epoch 3, batch 21400, loss[loss=0.1478, simple_loss=0.211, pruned_loss=0.04229, over 4856.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2303, pruned_loss=0.04699, over 972639.52 frames.], batch size: 13, lr: 5.35e-04
2022-05-04 15:51:30,337 INFO [train.py:715] (4/8) Epoch 3, batch 21450, loss[loss=0.1451, simple_loss=0.213, pruned_loss=0.03865, over 4779.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2297, pruned_loss=0.04669, over 972036.99 frames.], batch size: 18, lr: 5.35e-04
2022-05-04 15:52:08,620 INFO [train.py:715] (4/8) Epoch 3, batch 21500, loss[loss=0.1577, simple_loss=0.2252, pruned_loss=0.04511, over 4970.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2302, pruned_loss=0.04664, over 973022.98 frames.], batch size: 24, lr: 5.34e-04
2022-05-04 15:52:47,661 INFO [train.py:715] (4/8) Epoch 3, batch 21550, loss[loss=0.1366, simple_loss=0.2096, pruned_loss=0.03185, over 4868.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2302, pruned_loss=0.04658, over 972841.94 frames.], batch size: 22, lr: 5.34e-04
2022-05-04 15:53:27,189 INFO [train.py:715] (4/8) Epoch 3, batch 21600, loss[loss=0.1564, simple_loss=0.219, pruned_loss=0.04686, over 4967.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2293, pruned_loss=0.04652, over 971921.15 frames.], batch size: 35, lr: 5.34e-04
2022-05-04 15:54:06,105 INFO [train.py:715] (4/8) Epoch 3, batch 21650, loss[loss=0.1694, simple_loss=0.2359, pruned_loss=0.05139, over 4784.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2294, pruned_loss=0.04685, over 971153.96 frames.], batch size: 17, lr: 5.34e-04
2022-05-04 15:54:46,388 INFO [train.py:715] (4/8) Epoch 3, batch 21700, loss[loss=0.1578, simple_loss=0.2279, pruned_loss=0.04383, over 4811.00 frames.], tot_loss[loss=0.1621, simple_loss=0.23, pruned_loss=0.04704, over 970845.28 frames.], batch size: 15, lr: 5.34e-04
2022-05-04 15:55:26,897 INFO [train.py:715] (4/8) Epoch 3, batch 21750, loss[loss=0.151, simple_loss=0.213, pruned_loss=0.04452, over 4991.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2312, pruned_loss=0.0475, over 971340.45 frames.], batch size: 14, lr: 5.34e-04
2022-05-04 15:56:06,025 INFO [train.py:715] (4/8) Epoch 3, batch 21800, loss[loss=0.1599, simple_loss=0.2208, pruned_loss=0.04946, over 4714.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2313, pruned_loss=0.0475, over 972024.19 frames.], batch size: 15, lr: 5.34e-04
2022-05-04 15:56:44,182 INFO [train.py:715] (4/8) Epoch 3, batch 21850, loss[loss=0.1884, simple_loss=0.2597, pruned_loss=0.05859, over 4982.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2315, pruned_loss=0.04753, over 971389.68 frames.], batch size: 25, lr: 5.34e-04
2022-05-04 15:57:22,931 INFO [train.py:715] (4/8) Epoch 3, batch 21900, loss[loss=0.1698, simple_loss=0.2373, pruned_loss=0.05115, over 4762.00 frames.], tot_loss[loss=0.1635, simple_loss=0.2318, pruned_loss=0.04756, over 972089.17 frames.], batch size: 19, lr: 5.34e-04
2022-05-04 15:58:03,623 INFO [train.py:715] (4/8) Epoch 3, batch 21950, loss[loss=0.1649, simple_loss=0.2219, pruned_loss=0.05396, over 4839.00 frames.], tot_loss[loss=0.1638, simple_loss=0.2324, pruned_loss=0.04759, over 971992.59 frames.], batch size: 13, lr: 5.34e-04
2022-05-04 15:58:43,253 INFO [train.py:715] (4/8) Epoch 3, batch 22000, loss[loss=0.1891, simple_loss=0.2522, pruned_loss=0.06296, over 4945.00 frames.], tot_loss[loss=0.1632, simple_loss=0.232, pruned_loss=0.0472, over 972815.11 frames.], batch size: 39, lr: 5.33e-04
2022-05-04 15:59:23,575 INFO [train.py:715] (4/8) Epoch 3, batch 22050, loss[loss=0.1462, simple_loss=0.2211, pruned_loss=0.03562, over 4801.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2315, pruned_loss=0.04701, over 972781.90 frames.], batch size: 24, lr: 5.33e-04
2022-05-04 16:00:04,303 INFO [train.py:715] (4/8) Epoch 3, batch 22100, loss[loss=0.1309, simple_loss=0.2068, pruned_loss=0.02752, over 4784.00 frames.], tot_loss[loss=0.1612, simple_loss=0.23, pruned_loss=0.04621, over 973286.97 frames.], batch size: 23, lr: 5.33e-04
2022-05-04 16:00:44,829 INFO [train.py:715] (4/8) Epoch 3, batch 22150, loss[loss=0.1575, simple_loss=0.2313, pruned_loss=0.04181, over 4854.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2309, pruned_loss=0.04662, over 973627.70 frames.], batch size: 30, lr: 5.33e-04
2022-05-04 16:01:24,045 INFO [train.py:715] (4/8) Epoch 3, batch 22200, loss[loss=0.1622, simple_loss=0.2416, pruned_loss=0.04146, over 4864.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2313, pruned_loss=0.0469, over 972636.89 frames.], batch size: 20, lr: 5.33e-04
2022-05-04 16:02:04,299 INFO [train.py:715] (4/8) Epoch 3, batch 22250, loss[loss=0.2007, simple_loss=0.2582, pruned_loss=0.07162, over 4896.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2316, pruned_loss=0.04695, over 972259.60 frames.], batch size: 17, lr: 5.33e-04
2022-05-04 16:02:45,555 INFO [train.py:715] (4/8) Epoch 3, batch 22300, loss[loss=0.1575, simple_loss=0.2334, pruned_loss=0.04076, over 4918.00 frames.], tot_loss[loss=0.162, simple_loss=0.2309, pruned_loss=0.04649, over 972436.90 frames.], batch size: 39, lr: 5.33e-04
2022-05-04 16:03:24,537 INFO [train.py:715] (4/8) Epoch 3, batch 22350, loss[loss=0.1243, simple_loss=0.2027, pruned_loss=0.02295, over 4907.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2316, pruned_loss=0.04734, over 972846.10 frames.], batch size: 17, lr: 5.33e-04
2022-05-04 16:04:04,620 INFO [train.py:715] (4/8) Epoch 3, batch 22400, loss[loss=0.1754, simple_loss=0.2404, pruned_loss=0.05521, over 4898.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2314, pruned_loss=0.04716, over 973434.62 frames.], batch size: 19, lr: 5.33e-04
2022-05-04 16:04:45,522 INFO [train.py:715] (4/8) Epoch 3, batch 22450, loss[loss=0.1561, simple_loss=0.2305, pruned_loss=0.04087, over 4848.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2313, pruned_loss=0.04664, over 973309.23 frames.], batch size: 20, lr: 5.32e-04
2022-05-04 16:05:25,977 INFO [train.py:715] (4/8) Epoch 3, batch 22500, loss[loss=0.1797, simple_loss=0.2429, pruned_loss=0.05826, over 4812.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2318, pruned_loss=0.04693, over 973526.39 frames.], batch size: 13, lr: 5.32e-04
2022-05-04 16:06:05,408 INFO [train.py:715] (4/8) Epoch 3, batch 22550, loss[loss=0.1755, simple_loss=0.2387, pruned_loss=0.05611, over 4989.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2319, pruned_loss=0.04683, over 973246.71 frames.], batch size: 26, lr: 5.32e-04
2022-05-04 16:06:45,621 INFO [train.py:715] (4/8) Epoch 3, batch 22600, loss[loss=0.1738, simple_loss=0.2306, pruned_loss=0.05848, over 4872.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2311, pruned_loss=0.04699, over 973229.13 frames.], batch size: 32, lr: 5.32e-04
2022-05-04 16:07:26,487 INFO [train.py:715] (4/8) Epoch 3, batch 22650, loss[loss=0.1636, simple_loss=0.2299, pruned_loss=0.04868, over 4911.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2302, pruned_loss=0.04665, over 972616.29 frames.], batch size: 17, lr: 5.32e-04
2022-05-04 16:08:06,316 INFO [train.py:715] (4/8) Epoch 3, batch 22700, loss[loss=0.1505, simple_loss=0.2162, pruned_loss=0.04233, over 4704.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2293, pruned_loss=0.04623, over 972485.54 frames.], batch size: 15, lr: 5.32e-04
2022-05-04 16:08:46,716 INFO [train.py:715] (4/8) Epoch 3, batch 22750, loss[loss=0.1703, simple_loss=0.2395, pruned_loss=0.05053, over 4813.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2295, pruned_loss=0.04607, over 972179.86 frames.], batch size: 15, lr: 5.32e-04
2022-05-04 16:09:27,107 INFO [train.py:715] (4/8) Epoch 3, batch 22800, loss[loss=0.1598, simple_loss=0.2276, pruned_loss=0.04602, over 4894.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2284, pruned_loss=0.04535, over 972648.37 frames.], batch size: 17, lr: 5.32e-04
2022-05-04 16:10:07,183 INFO [train.py:715] (4/8) Epoch 3, batch 22850, loss[loss=0.1517, simple_loss=0.2202, pruned_loss=0.04161, over 4920.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2295, pruned_loss=0.04584, over 972832.89 frames.], batch size: 23, lr: 5.32e-04
2022-05-04 16:10:46,908 INFO [train.py:715] (4/8) Epoch 3, batch 22900, loss[loss=0.1358, simple_loss=0.2175, pruned_loss=0.02704, over 4950.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2297, pruned_loss=0.04608, over 972888.48 frames.], batch size: 29, lr: 5.32e-04
2022-05-04 16:11:27,330 INFO [train.py:715] (4/8) Epoch 3, batch 22950, loss[loss=0.1829, simple_loss=0.2388, pruned_loss=0.06355, over 4800.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2306, pruned_loss=0.0468, over 972156.90 frames.], batch size: 14, lr: 5.31e-04
2022-05-04 16:12:08,456 INFO [train.py:715] (4/8) Epoch 3, batch 23000, loss[loss=0.1388, simple_loss=0.2207, pruned_loss=0.02849, over 4844.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2296, pruned_loss=0.04606, over 972307.36 frames.], batch size: 15, lr: 5.31e-04
2022-05-04 16:12:48,305 INFO [train.py:715] (4/8) Epoch 3, batch 23050, loss[loss=0.1599, simple_loss=0.2363, pruned_loss=0.04174, over 4892.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2302, pruned_loss=0.04643, over 972429.26 frames.], batch size: 16, lr: 5.31e-04
2022-05-04 16:13:28,632 INFO [train.py:715] (4/8) Epoch 3, batch 23100, loss[loss=0.1572, simple_loss=0.2204, pruned_loss=0.04693, over 4983.00 frames.], tot_loss[loss=0.1611, simple_loss=0.23, pruned_loss=0.04612, over 972364.37 frames.], batch size: 31, lr: 5.31e-04
2022-05-04 16:14:09,397 INFO [train.py:715] (4/8) Epoch 3, batch 23150, loss[loss=0.1775, simple_loss=0.243, pruned_loss=0.05599, over 4882.00 frames.], tot_loss[loss=0.1611, simple_loss=0.23, pruned_loss=0.04614, over 973306.21 frames.], batch size: 22, lr: 5.31e-04
2022-05-04 16:14:49,971 INFO [train.py:715] (4/8) Epoch 3, batch 23200, loss[loss=0.1322, simple_loss=0.2045, pruned_loss=0.02989, over 4896.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2293, pruned_loss=0.04588, over 973000.33 frames.], batch size: 19, lr: 5.31e-04
2022-05-04 16:15:29,514 INFO [train.py:715] (4/8) Epoch 3, batch 23250, loss[loss=0.1726, simple_loss=0.2414, pruned_loss=0.05185, over 4959.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2294, pruned_loss=0.04621, over 972679.77 frames.], batch size: 15, lr: 5.31e-04
2022-05-04 16:16:10,268 INFO [train.py:715] (4/8) Epoch 3, batch 23300, loss[loss=0.1749, simple_loss=0.2583, pruned_loss=0.04577, over 4949.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2308, pruned_loss=0.04687, over 972891.65 frames.], batch size: 24, lr: 5.31e-04
2022-05-04 16:16:49,872 INFO [train.py:715] (4/8) Epoch 3, batch 23350, loss[loss=0.1548, simple_loss=0.2289, pruned_loss=0.0404, over 4974.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2302, pruned_loss=0.04646, over 972747.50 frames.], batch size: 15, lr: 5.31e-04
2022-05-04 16:17:27,677 INFO [train.py:715] (4/8) Epoch 3, batch 23400, loss[loss=0.1384, simple_loss=0.2192, pruned_loss=0.02882, over 4955.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2304, pruned_loss=0.04638, over 973275.18 frames.], batch size: 29, lr: 5.30e-04
2022-05-04 16:18:06,223 INFO [train.py:715] (4/8) Epoch 3, batch 23450, loss[loss=0.163, simple_loss=0.2267, pruned_loss=0.04962, over 4795.00 frames.], tot_loss[loss=0.162, simple_loss=0.2308, pruned_loss=0.04659, over 971978.89 frames.], batch size: 24, lr: 5.30e-04
2022-05-04 16:18:44,911 INFO [train.py:715] (4/8) Epoch 3, batch 23500, loss[loss=0.1856, simple_loss=0.26, pruned_loss=0.05558, over 4795.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2303, pruned_loss=0.04605, over 972144.24 frames.], batch size: 24, lr: 5.30e-04
2022-05-04 16:19:24,105 INFO [train.py:715] (4/8) Epoch 3, batch 23550, loss[loss=0.1788, simple_loss=0.2403, pruned_loss=0.05871, over 4977.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2294, pruned_loss=0.04573, over 971797.96 frames.], batch size: 25, lr: 5.30e-04
2022-05-04 16:20:05,335 INFO [train.py:715] (4/8) Epoch 3, batch 23600, loss[loss=0.1644, simple_loss=0.2356, pruned_loss=0.04665, over 4878.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2302, pruned_loss=0.04622, over 971321.26 frames.], batch size: 22, lr: 5.30e-04
2022-05-04 16:20:44,861 INFO [train.py:715] (4/8) Epoch 3, batch 23650, loss[loss=0.1593, simple_loss=0.2278, pruned_loss=0.04541, over 4973.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2299, pruned_loss=0.04619, over 971772.08 frames.], batch size: 24, lr: 5.30e-04
2022-05-04 16:21:24,817 INFO [train.py:715] (4/8) Epoch 3, batch 23700, loss[loss=0.1772, simple_loss=0.2345, pruned_loss=0.05996, over 4814.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2301, pruned_loss=0.0465, over 972292.60 frames.], batch size: 21, lr: 5.30e-04
2022-05-04 16:22:03,567 INFO [train.py:715] (4/8) Epoch 3, batch 23750, loss[loss=0.1689, simple_loss=0.2308, pruned_loss=0.05346, over 4802.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2298, pruned_loss=0.04648, over 971556.26 frames.], batch size: 14, lr: 5.30e-04
2022-05-04 16:22:43,183 INFO [train.py:715] (4/8) Epoch 3, batch 23800, loss[loss=0.1709, simple_loss=0.2337, pruned_loss=0.0541, over 4944.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2311, pruned_loss=0.04715, over 970840.75 frames.], batch size: 21, lr: 5.30e-04
2022-05-04 16:23:22,780 INFO [train.py:715] (4/8) Epoch 3, batch 23850, loss[loss=0.1452, simple_loss=0.2248, pruned_loss=0.03278, over 4950.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2313, pruned_loss=0.0471, over 971714.01 frames.], batch size: 15, lr: 5.30e-04
2022-05-04 16:24:02,497 INFO [train.py:715] (4/8) Epoch 3, batch 23900, loss[loss=0.1393, simple_loss=0.2086, pruned_loss=0.03501, over 4770.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2307, pruned_loss=0.04687, over 972202.51 frames.], batch size: 18, lr: 5.29e-04
2022-05-04 16:24:41,551 INFO [train.py:715] (4/8) Epoch 3, batch 23950, loss[loss=0.157, simple_loss=0.2284, pruned_loss=0.04276, over 4781.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2296, pruned_loss=0.04595, over 972330.00 frames.], batch size: 17, lr: 5.29e-04
2022-05-04 16:25:20,398 INFO [train.py:715] (4/8) Epoch 3, batch 24000, loss[loss=0.1707, simple_loss=0.2309, pruned_loss=0.05522, over 4962.00 frames.], tot_loss[loss=0.162, simple_loss=0.2307, pruned_loss=0.04669, over 972059.82 frames.], batch size: 35, lr: 5.29e-04
2022-05-04 16:25:20,398 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 16:25:32,860 INFO [train.py:742] (4/8) Epoch 3, validation: loss=0.1132, simple_loss=0.1992, pruned_loss=0.0136, over 914524.00 frames.
2022-05-04 16:26:12,212 INFO [train.py:715] (4/8) Epoch 3, batch 24050, loss[loss=0.1885, simple_loss=0.2495, pruned_loss=0.06376, over 4805.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2308, pruned_loss=0.04686, over 972526.84 frames.], batch size: 13, lr: 5.29e-04
2022-05-04 16:26:52,061 INFO [train.py:715] (4/8) Epoch 3, batch 24100, loss[loss=0.1505, simple_loss=0.2282, pruned_loss=0.03639, over 4914.00 frames.], tot_loss[loss=0.1625, simple_loss=0.231, pruned_loss=0.04705, over 972121.87 frames.], batch size: 23, lr: 5.29e-04
2022-05-04 16:27:30,860 INFO [train.py:715] (4/8) Epoch 3, batch 24150, loss[loss=0.1294, simple_loss=0.1979, pruned_loss=0.03048, over 4761.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2309, pruned_loss=0.04679, over 971893.64 frames.], batch size: 12, lr: 5.29e-04
2022-05-04 16:28:10,106 INFO [train.py:715] (4/8) Epoch 3, batch 24200, loss[loss=0.1615, simple_loss=0.225, pruned_loss=0.04906, over 4932.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2303, pruned_loss=0.04656, over 972746.37 frames.], batch size: 18, lr: 5.29e-04
2022-05-04 16:28:50,502 INFO [train.py:715] (4/8) Epoch 3, batch 24250, loss[loss=0.1634, simple_loss=0.2232, pruned_loss=0.05182, over 4981.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2306, pruned_loss=0.04692, over 973090.26 frames.], batch size: 15, lr: 5.29e-04
2022-05-04 16:29:30,781 INFO [train.py:715] (4/8) Epoch 3, batch 24300, loss[loss=0.1439, simple_loss=0.2145, pruned_loss=0.03666, over 4970.00 frames.], tot_loss[loss=0.163, simple_loss=0.2309, pruned_loss=0.04752, over 972929.56 frames.], batch size: 25, lr: 5.29e-04
2022-05-04 16:30:10,088 INFO [train.py:715] (4/8) Epoch 3, batch 24350, loss[loss=0.1458, simple_loss=0.2079, pruned_loss=0.04186, over 4844.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2315, pruned_loss=0.04782, over 973238.54 frames.], batch size: 13, lr: 5.29e-04
2022-05-04 16:30:49,733 INFO [train.py:715] (4/8) Epoch 3, batch 24400, loss[loss=0.1467, simple_loss=0.2302, pruned_loss=0.0316, over 4960.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2313, pruned_loss=0.0476, over 972901.96 frames.], batch size: 21, lr: 5.28e-04
2022-05-04 16:31:29,802 INFO [train.py:715] (4/8) Epoch 3, batch 24450, loss[loss=0.1281, simple_loss=0.1996, pruned_loss=0.02827, over 4688.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2311, pruned_loss=0.04777, over 972389.17 frames.], batch size: 15, lr: 5.28e-04
2022-05-04 16:32:09,117 INFO [train.py:715] (4/8) Epoch 3, batch 24500, loss[loss=0.174, simple_loss=0.2523, pruned_loss=0.04787, over 4970.00 frames.], tot_loss[loss=0.1621, simple_loss=0.23, pruned_loss=0.04713, over 972456.67 frames.], batch size: 21, lr: 5.28e-04
2022-05-04 16:32:48,514 INFO [train.py:715] (4/8) Epoch 3, batch 24550, loss[loss=0.1689, simple_loss=0.2409, pruned_loss=0.04847, over 4893.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2309, pruned_loss=0.04731, over 972457.52 frames.], batch size: 19, lr: 5.28e-04
2022-05-04 16:33:28,754 INFO [train.py:715] (4/8) Epoch 3, batch 24600, loss[loss=0.1456, simple_loss=0.2125, pruned_loss=0.03937, over 4794.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2316, pruned_loss=0.04726, over 973105.83 frames.], batch size: 14, lr: 5.28e-04
2022-05-04 16:34:08,287 INFO [train.py:715] (4/8) Epoch 3, batch 24650, loss[loss=0.2061, simple_loss=0.2684, pruned_loss=0.07193, over 4767.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2309, pruned_loss=0.04691, over 973094.07 frames.], batch size: 14, lr: 5.28e-04
2022-05-04 16:34:47,791 INFO [train.py:715] (4/8) Epoch 3, batch 24700, loss[loss=0.1458, simple_loss=0.2142, pruned_loss=0.0387, over 4908.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2306, pruned_loss=0.04661, over 972550.47 frames.], batch size: 23, lr: 5.28e-04
2022-05-04 16:35:26,426 INFO [train.py:715] (4/8) Epoch 3, batch 24750, loss[loss=0.1594, simple_loss=0.2254, pruned_loss=0.04669, over 4793.00 frames.], tot_loss[loss=0.162, simple_loss=0.2306, pruned_loss=0.04673, over 972738.77 frames.], batch size: 14, lr: 5.28e-04
2022-05-04 16:36:07,077 INFO [train.py:715] (4/8) Epoch 3, batch 24800, loss[loss=0.1729, simple_loss=0.2536, pruned_loss=0.04612, over 4824.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2305, pruned_loss=0.0466, over 973945.09 frames.], batch size: 25, lr: 5.28e-04
2022-05-04 16:36:46,783 INFO [train.py:715] (4/8) Epoch 3, batch 24850, loss[loss=0.1651, simple_loss=0.216, pruned_loss=0.05703, over 4690.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2299, pruned_loss=0.04667, over 973554.38 frames.], batch size: 15, lr: 5.28e-04
2022-05-04 16:37:25,563 INFO [train.py:715] (4/8) Epoch 3, batch 24900, loss[loss=0.1326, simple_loss=0.2051, pruned_loss=0.03009, over 4985.00 frames.], tot_loss[loss=0.162, simple_loss=0.2304, pruned_loss=0.04684, over 973210.88 frames.], batch size: 28, lr: 5.27e-04
2022-05-04 16:38:05,477 INFO [train.py:715] (4/8) Epoch 3, batch 24950, loss[loss=0.167, simple_loss=0.2384, pruned_loss=0.04785, over 4916.00 frames.], tot_loss[loss=0.1625, simple_loss=0.231, pruned_loss=0.04702, over 973133.29 frames.], batch size: 23, lr: 5.27e-04
2022-05-04 16:38:45,652 INFO [train.py:715] (4/8) Epoch 3, batch 25000, loss[loss=0.1475, simple_loss=0.2155, pruned_loss=0.03972, over 4794.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2311, pruned_loss=0.04695, over 972886.03 frames.], batch size: 17, lr: 5.27e-04
2022-05-04 16:39:25,198 INFO [train.py:715] (4/8) Epoch 3, batch 25050, loss[loss=0.1427, simple_loss=0.2188, pruned_loss=0.03327, over 4942.00 frames.], tot_loss[loss=0.163, simple_loss=0.2315, pruned_loss=0.0473, over 973051.81 frames.], batch size: 21, lr: 5.27e-04
2022-05-04 16:40:04,366 INFO [train.py:715] (4/8) Epoch 3, batch 25100, loss[loss=0.1478, simple_loss=0.2176, pruned_loss=0.03903, over 4960.00 frames.], tot_loss[loss=0.1626, simple_loss=0.2312, pruned_loss=0.04701, over 974035.25 frames.], batch size: 14, lr: 5.27e-04
2022-05-04 16:40:44,394 INFO [train.py:715] (4/8) Epoch 3, batch 25150, loss[loss=0.1514, simple_loss=0.2236, pruned_loss=0.03958, over 4941.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2318, pruned_loss=0.04727, over 973656.03 frames.], batch size: 24, lr: 5.27e-04
2022-05-04 16:41:23,890 INFO [train.py:715] (4/8) Epoch 3, batch 25200, loss[loss=0.1449, simple_loss=0.2174, pruned_loss=0.03619, over 4808.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2307, pruned_loss=0.0468, over 972888.88 frames.], batch size: 13, lr: 5.27e-04
2022-05-04 16:42:03,022 INFO [train.py:715] (4/8) Epoch 3, batch 25250, loss[loss=0.1635, simple_loss=0.2309, pruned_loss=0.04801, over 4902.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2291, pruned_loss=0.04603, over 972737.10 frames.], batch size: 19, lr: 5.27e-04
2022-05-04 16:42:43,125 INFO [train.py:715] (4/8) Epoch 3, batch 25300, loss[loss=0.1633, simple_loss=0.2285, pruned_loss=0.04905, over 4883.00 frames.], tot_loss[loss=0.1617, simple_loss=0.23, pruned_loss=0.0467, over 971022.41 frames.], batch size: 16, lr: 5.27e-04
2022-05-04 16:43:22,953 INFO [train.py:715] (4/8) Epoch 3, batch 25350, loss[loss=0.1525, simple_loss=0.2326, pruned_loss=0.03613, over 4920.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2294, pruned_loss=0.04609, over 970851.40 frames.], batch size: 29, lr: 5.26e-04
2022-05-04 16:44:02,966 INFO [train.py:715] (4/8) Epoch 3, batch 25400, loss[loss=0.1484, simple_loss=0.2209, pruned_loss=0.03798, over 4821.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2295, pruned_loss=0.04618, over 970675.39 frames.], batch size: 26, lr: 5.26e-04
2022-05-04 16:44:42,161 INFO [train.py:715] (4/8) Epoch 3, batch 25450, loss[loss=0.1687, simple_loss=0.2463, pruned_loss=0.04553, over 4763.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2289, pruned_loss=0.04597, over 971657.73 frames.], batch size: 19, lr: 5.26e-04
2022-05-04 16:45:22,339 INFO [train.py:715] (4/8) Epoch 3, batch 25500, loss[loss=0.144, simple_loss=0.2204, pruned_loss=0.03377, over 4981.00 frames.], tot_loss[loss=0.161, simple_loss=0.2297, pruned_loss=0.04616, over 972035.93 frames.], batch size: 20, lr: 5.26e-04
2022-05-04 16:46:02,169 INFO [train.py:715] (4/8) Epoch 3, batch 25550, loss[loss=0.1404, simple_loss=0.2177, pruned_loss=0.03154, over 4788.00 frames.], tot_loss[loss=0.1606, simple_loss=0.229, pruned_loss=0.04613, over 971688.97 frames.], batch size: 17, lr: 5.26e-04
2022-05-04 16:46:41,626 INFO [train.py:715] (4/8) Epoch 3, batch 25600, loss[loss=0.158, simple_loss=0.216, pruned_loss=0.04993, over 4914.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2291, pruned_loss=0.04678, over 972392.38 frames.], batch size: 39, lr: 5.26e-04
2022-05-04 16:47:22,008 INFO [train.py:715] (4/8) Epoch 3, batch 25650, loss[loss=0.1652, simple_loss=0.2229, pruned_loss=0.05374, over 4911.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2287, pruned_loss=0.0465, over 972664.96 frames.], batch size: 29, lr: 5.26e-04
2022-05-04 16:48:02,205 INFO [train.py:715] (4/8) Epoch 3, batch 25700, loss[loss=0.1721, simple_loss=0.2304, pruned_loss=0.05689, over 4795.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2294, pruned_loss=0.04667, over 971398.34 frames.], batch size: 24, lr: 5.26e-04
2022-05-04 16:48:41,537 INFO [train.py:715] (4/8) Epoch 3, batch 25750, loss[loss=0.1268, simple_loss=0.1956, pruned_loss=0.02902, over 4813.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2287, pruned_loss=0.04623, over 970768.49 frames.], batch size: 27, lr: 5.26e-04
2022-05-04 16:49:21,102 INFO [train.py:715] (4/8) Epoch 3, batch 25800, loss[loss=0.156, simple_loss=0.2184, pruned_loss=0.04676, over 4845.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2303, pruned_loss=0.04705, over 971578.87 frames.], batch size: 15, lr: 5.26e-04
2022-05-04 16:50:01,076 INFO [train.py:715] (4/8) Epoch 3, batch 25850, loss[loss=0.2045, simple_loss=0.2413, pruned_loss=0.08387, over 4787.00 frames.], tot_loss[loss=0.1629, simple_loss=0.2313, pruned_loss=0.04727, over 971879.21 frames.], batch size: 14, lr: 5.25e-04
2022-05-04 16:50:39,397 INFO [train.py:715] (4/8) Epoch 3, batch 25900, loss[loss=0.1661, simple_loss=0.2355, pruned_loss=0.0483, over 4892.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2307, pruned_loss=0.04674, over 971825.91 frames.], batch size: 39, lr: 5.25e-04
2022-05-04 16:51:18,327 INFO [train.py:715] (4/8) Epoch 3, batch 25950, loss[loss=0.1472, simple_loss=0.225, pruned_loss=0.03471, over 4768.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2309, pruned_loss=0.04724, over 971340.33 frames.], batch size: 14, lr: 5.25e-04
2022-05-04 16:51:58,432 INFO [train.py:715] (4/8) Epoch 3, batch 26000, loss[loss=0.1346, simple_loss=0.204, pruned_loss=0.03262, over 4979.00 frames.], tot_loss[loss=0.163, simple_loss=0.231, pruned_loss=0.04752, over 971521.19 frames.], batch size: 28, lr: 5.25e-04
2022-05-04 16:52:37,676 INFO [train.py:715] (4/8) Epoch 3, batch 26050, loss[loss=0.1548, simple_loss=0.2268, pruned_loss=0.04145, over 4857.00 frames.], tot_loss[loss=0.1625, simple_loss=0.2308, pruned_loss=0.04709, over 972064.07 frames.], batch size: 20, lr: 5.25e-04
2022-05-04 16:53:16,013 INFO [train.py:715] (4/8) Epoch 3, batch 26100, loss[loss=0.1415, simple_loss=0.2201, pruned_loss=0.03143, over 4922.00 frames.], tot_loss[loss=0.1624, simple_loss=0.2309, pruned_loss=0.04695, over 972548.97 frames.], batch size: 29, lr: 5.25e-04
2022-05-04 16:53:55,502 INFO [train.py:715] (4/8) Epoch 3, batch 26150, loss[loss=0.1499, simple_loss=0.218, pruned_loss=0.04091, over 4787.00 frames.], tot_loss[loss=0.1642, simple_loss=0.2324, pruned_loss=0.04804, over 971186.81 frames.], batch size: 17, lr: 5.25e-04
2022-05-04 16:54:35,542 INFO [train.py:715] (4/8) Epoch 3, batch 26200, loss[loss=0.2133, simple_loss=0.2727, pruned_loss=0.07698, over 4944.00 frames.], tot_loss[loss=0.1632, simple_loss=0.2313, pruned_loss=0.04755, over 971259.00 frames.], batch size: 21, lr: 5.25e-04
2022-05-04 16:55:13,647 INFO [train.py:715] (4/8) Epoch 3, batch 26250, loss[loss=0.1569, simple_loss=0.2202, pruned_loss=0.04679, over 4987.00 frames.], tot_loss[loss=0.1634, simple_loss=0.2315, pruned_loss=0.04767, over 971418.66 frames.], batch size: 14, lr: 5.25e-04
2022-05-04 16:55:52,855 INFO [train.py:715] (4/8) Epoch 3, batch 26300, loss[loss=0.1399, simple_loss=0.2221, pruned_loss=0.02886, over 4981.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2312, pruned_loss=0.04715, over 971310.30 frames.], batch size: 14, lr: 5.25e-04
2022-05-04 16:56:32,818 INFO [train.py:715] (4/8) Epoch 3, batch 26350, loss[loss=0.176, simple_loss=0.2438, pruned_loss=0.05409, over 4743.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2308, pruned_loss=0.04672, over 970790.20 frames.], batch size: 16, lr: 5.24e-04
2022-05-04 16:57:12,181 INFO [train.py:715] (4/8) Epoch 3, batch 26400, loss[loss=0.159, simple_loss=0.2304, pruned_loss=0.04385, over 4897.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2301, pruned_loss=0.04584, over 971851.39 frames.], batch size: 16, lr: 5.24e-04
2022-05-04 16:57:51,173 INFO [train.py:715] (4/8) Epoch 3, batch 26450, loss[loss=0.1767, simple_loss=0.233, pruned_loss=0.06021, over 4772.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2295, pruned_loss=0.04567, over 972162.85 frames.], batch size: 17, lr: 5.24e-04
2022-05-04 16:58:30,425 INFO [train.py:715] (4/8) Epoch 3, batch 26500, loss[loss=0.1392, simple_loss=0.2065, pruned_loss=0.0359, over 4810.00 frames.], tot_loss[loss=0.1596, simple_loss=0.229, pruned_loss=0.04508, over 971862.79 frames.], batch size: 24, lr: 5.24e-04
2022-05-04 16:59:09,907 INFO [train.py:715] (4/8) Epoch 3, batch 26550, loss[loss=0.1776, simple_loss=0.2403, pruned_loss=0.0575, over 4940.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2291, pruned_loss=0.04493, over 971255.27 frames.], batch size: 21, lr: 5.24e-04
2022-05-04 16:59:48,113 INFO [train.py:715] (4/8) Epoch 3, batch 26600, loss[loss=0.1241, simple_loss=0.1957, pruned_loss=0.02628, over 4961.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2293, pruned_loss=0.04527, over 971488.12 frames.], batch size: 14, lr: 5.24e-04
2022-05-04 17:00:27,329 INFO [train.py:715] (4/8) Epoch 3, batch 26650, loss[loss=0.1772, simple_loss=0.2351, pruned_loss=0.05963, over 4831.00 frames.], tot_loss[loss=0.161, simple_loss=0.2297, pruned_loss=0.04614, over 971341.22 frames.], batch size: 15, lr: 5.24e-04
2022-05-04 17:01:07,872 INFO [train.py:715] (4/8) Epoch 3, batch 26700, loss[loss=0.1483, simple_loss=0.2122, pruned_loss=0.04218, over 4872.00 frames.], tot_loss[loss=0.1603, simple_loss=0.229, pruned_loss=0.04581, over 970824.38 frames.], batch size: 30, lr: 5.24e-04
2022-05-04 17:01:47,352 INFO [train.py:715] (4/8) Epoch 3, batch 26750, loss[loss=0.1454, simple_loss=0.2242, pruned_loss=0.03333, over 4874.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2294, pruned_loss=0.04602, over 971701.50 frames.], batch size: 22, lr: 5.24e-04
2022-05-04 17:02:26,599 INFO [train.py:715] (4/8) Epoch 3, batch 26800, loss[loss=0.1466, simple_loss=0.2198, pruned_loss=0.03666, over 4884.00 frames.], tot_loss[loss=0.1622, simple_loss=0.231, pruned_loss=0.04675, over 972319.69 frames.], batch size: 22, lr: 5.24e-04
2022-05-04 17:03:06,721 INFO [train.py:715] (4/8) Epoch 3, batch 26850, loss[loss=0.1683, simple_loss=0.2366, pruned_loss=0.05003, over 4944.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2302, pruned_loss=0.0462, over 972239.05 frames.], batch size: 21, lr: 5.23e-04
2022-05-04 17:03:47,105 INFO [train.py:715] (4/8) Epoch 3, batch 26900, loss[loss=0.1389, simple_loss=0.2104, pruned_loss=0.0337, over 4866.00 frames.], tot_loss[loss=0.1599, simple_loss=0.229, pruned_loss=0.04536, over 971940.27 frames.], batch size: 20, lr: 5.23e-04
2022-05-04 17:04:26,666 INFO [train.py:715] (4/8) Epoch 3, batch 26950, loss[loss=0.2181, simple_loss=0.2809, pruned_loss=0.07769, over 4912.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2301, pruned_loss=0.04577, over 972838.07 frames.], batch size: 17, lr: 5.23e-04
2022-05-04 17:05:05,428 INFO [train.py:715] (4/8) Epoch 3, batch 27000, loss[loss=0.1711, simple_loss=0.2338, pruned_loss=0.05418, over 4935.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2308, pruned_loss=0.04606, over 973193.83 frames.], batch size: 18, lr: 5.23e-04
2022-05-04 17:05:05,428 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 17:05:14,908 INFO [train.py:742] (4/8) Epoch 3, validation: loss=0.1134, simple_loss=0.1995, pruned_loss=0.01366, over 914524.00 frames.
2022-05-04 17:05:54,548 INFO [train.py:715] (4/8) Epoch 3, batch 27050, loss[loss=0.2192, simple_loss=0.2888, pruned_loss=0.07477, over 4955.00 frames.], tot_loss[loss=0.161, simple_loss=0.2304, pruned_loss=0.04581, over 973149.53 frames.], batch size: 39, lr: 5.23e-04
2022-05-04 17:06:34,872 INFO [train.py:715] (4/8) Epoch 3, batch 27100, loss[loss=0.1433, simple_loss=0.2151, pruned_loss=0.03576, over 4755.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2295, pruned_loss=0.04542, over 972533.31 frames.], batch size: 19, lr: 5.23e-04
2022-05-04 17:07:14,168 INFO [train.py:715] (4/8) Epoch 3, batch 27150, loss[loss=0.1566, simple_loss=0.2214, pruned_loss=0.04589, over 4848.00 frames.], tot_loss[loss=0.1608, simple_loss=0.23, pruned_loss=0.0458, over 972417.11 frames.], batch size: 30, lr: 5.23e-04
2022-05-04 17:07:52,929 INFO [train.py:715] (4/8) Epoch 3, batch 27200, loss[loss=0.204, simple_loss=0.2678, pruned_loss=0.07005, over 4829.00 frames.], tot_loss[loss=0.1609, simple_loss=0.23, pruned_loss=0.0459, over 971826.18 frames.], batch size: 26, lr: 5.23e-04
2022-05-04 17:08:32,666 INFO [train.py:715] (4/8) Epoch 3, batch 27250, loss[loss=0.1838, simple_loss=0.2513, pruned_loss=0.05817, over 4938.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2309, pruned_loss=0.04678, over 972184.77 frames.], batch size: 18, lr: 5.23e-04
2022-05-04 17:09:12,364 INFO [train.py:715] (4/8) Epoch 3, batch 27300, loss[loss=0.1583, simple_loss=0.2228, pruned_loss=0.04695, over 4892.00 frames.], tot_loss[loss=0.1617, simple_loss=0.2307, pruned_loss=0.04636, over 972372.00 frames.], batch size: 19, lr: 5.23e-04
2022-05-04 17:09:51,020 INFO [train.py:715] (4/8) Epoch 3, batch 27350, loss[loss=0.1842, simple_loss=0.2452, pruned_loss=0.06162, over 4861.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2303, pruned_loss=0.04643, over 972721.12 frames.], batch size: 20, lr: 5.22e-04
2022-05-04 17:10:30,268 INFO [train.py:715] (4/8) Epoch 3, batch 27400, loss[loss=0.1266, simple_loss=0.1897, pruned_loss=0.03175, over 4834.00 frames.], tot_loss[loss=0.161, simple_loss=0.2296, pruned_loss=0.0462, over 972022.34 frames.], batch size: 26, lr: 5.22e-04
2022-05-04 17:11:10,415 INFO [train.py:715] (4/8) Epoch 3, batch 27450, loss[loss=0.1413, simple_loss=0.2101, pruned_loss=0.03628, over 4800.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2291, pruned_loss=0.04584, over 972500.69 frames.], batch size: 17, lr: 5.22e-04
2022-05-04 17:11:49,742 INFO [train.py:715] (4/8) Epoch 3, batch 27500, loss[loss=0.2081, simple_loss=0.2709, pruned_loss=0.07264, over 4972.00 frames.], tot_loss[loss=0.161, simple_loss=0.2296, pruned_loss=0.0462, over 971650.40 frames.], batch size: 21, lr: 5.22e-04
2022-05-04 17:12:28,640 INFO [train.py:715] (4/8) Epoch 3, batch 27550, loss[loss=0.1979, simple_loss=0.252, pruned_loss=0.07192, over 4870.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2304, pruned_loss=0.0471, over 972335.92 frames.], batch size: 32, lr: 5.22e-04
2022-05-04 17:13:08,352 INFO [train.py:715] (4/8) Epoch 3, batch 27600, loss[loss=0.1501, simple_loss=0.2239, pruned_loss=0.0381, over 4851.00 frames.], tot_loss[loss=0.1622, simple_loss=0.2303, pruned_loss=0.04705, over 972416.57 frames.], batch size: 20, lr: 5.22e-04
2022-05-04 17:13:47,999 INFO [train.py:715] (4/8) Epoch 3, batch 27650, loss[loss=0.1786, simple_loss=0.245, pruned_loss=0.0561, over 4979.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2298, pruned_loss=0.04661, over 972681.42 frames.], batch size: 15, lr: 5.22e-04
2022-05-04 17:14:26,622 INFO [train.py:715] (4/8) Epoch 3, batch 27700, loss[loss=0.1331, simple_loss=0.2086, pruned_loss=0.0288, over 4795.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2298, pruned_loss=0.04645, over 973317.44 frames.], batch size: 21, lr: 5.22e-04
2022-05-04 17:15:06,394 INFO [train.py:715] (4/8) Epoch 3, batch 27750, loss[loss=0.1362, simple_loss=0.2091, pruned_loss=0.03168, over 4845.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2295, pruned_loss=0.04656, over 972479.85 frames.], batch size: 32, lr: 5.22e-04
2022-05-04 17:15:46,349 INFO [train.py:715] (4/8) Epoch 3, batch 27800, loss[loss=0.1793, simple_loss=0.2504, pruned_loss=0.0541, over 4753.00 frames.], tot_loss[loss=0.162, simple_loss=0.2301, pruned_loss=0.04698, over 973162.59 frames.], batch size: 16, lr: 5.22e-04
2022-05-04 17:16:25,743 INFO [train.py:715] (4/8) Epoch 3, batch 27850, loss[loss=0.18, simple_loss=0.2364, pruned_loss=0.06186, over 4681.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2297, pruned_loss=0.04691, over 973184.70 frames.], batch size: 15, lr: 5.21e-04
2022-05-04 17:17:04,209 INFO [train.py:715] (4/8) Epoch 3, batch 27900, loss[loss=0.1706, simple_loss=0.244, pruned_loss=0.04865, over 4757.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2302, pruned_loss=0.04719, over 973447.83 frames.], batch size: 19, lr: 5.21e-04
2022-05-04 17:17:43,814 INFO [train.py:715] (4/8) Epoch 3, batch 27950, loss[loss=0.1849, simple_loss=0.2556, pruned_loss=0.05715, over 4981.00 frames.], tot_loss[loss=0.1632, simple_loss=0.231, pruned_loss=0.04767, over 973869.18 frames.], batch size: 25, lr: 5.21e-04
2022-05-04 17:18:23,714 INFO [train.py:715] (4/8) Epoch 3, batch 28000, loss[loss=0.1353, simple_loss=0.2143, pruned_loss=0.02812, over 4927.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2307, pruned_loss=0.0474, over 974090.85 frames.], batch size: 29, lr: 5.21e-04
2022-05-04 17:19:02,275 INFO [train.py:715] (4/8) Epoch 3, batch 28050, loss[loss=0.1532, simple_loss=0.2094, pruned_loss=0.04853, over 4768.00 frames.], tot_loss[loss=0.1633, simple_loss=0.2312, pruned_loss=0.04773, over 973600.93 frames.], batch size: 14, lr: 5.21e-04
2022-05-04 17:19:41,709 INFO [train.py:715] (4/8) Epoch 3, batch 28100, loss[loss=0.168, simple_loss=0.2425, pruned_loss=0.0467, over 4765.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2298, pruned_loss=0.04697, over 973025.38 frames.], batch size: 18, lr: 5.21e-04
2022-05-04 17:20:21,588 INFO [train.py:715] (4/8) Epoch 3, batch 28150, loss[loss=0.1579, simple_loss=0.2305, pruned_loss=0.04268, over 4757.00 frames.], tot_loss[loss=0.1608, simple_loss=0.229, pruned_loss=0.04631, over 972642.32 frames.], batch size: 19, lr: 5.21e-04
2022-05-04 17:21:00,810 INFO [train.py:715] (4/8) Epoch 3, batch 28200, loss[loss=0.1827, simple_loss=0.2424, pruned_loss=0.06152, over 4761.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2294, pruned_loss=0.04657, over 972726.16 frames.], batch size: 19, lr: 5.21e-04
2022-05-04 17:21:39,658 INFO [train.py:715] (4/8) Epoch 3, batch 28250, loss[loss=0.1832, simple_loss=0.2379, pruned_loss=0.06419, over 4791.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2294, pruned_loss=0.04651, over 971815.46 frames.], batch size: 12, lr: 5.21e-04
2022-05-04 17:22:18,998 INFO [train.py:715] (4/8) Epoch 3, batch 28300, loss[loss=0.1627, simple_loss=0.2193, pruned_loss=0.05302, over 4856.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2302, pruned_loss=0.04698, over 972215.56 frames.], batch size: 32, lr: 5.21e-04
2022-05-04 17:22:58,002 INFO [train.py:715] (4/8) Epoch 3, batch 28350, loss[loss=0.133, simple_loss=0.2065, pruned_loss=0.02974, over 4869.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2299, pruned_loss=0.04685, over 972519.26 frames.], batch size: 16, lr: 5.21e-04
2022-05-04 17:23:37,192 INFO [train.py:715] (4/8) Epoch 3, batch 28400, loss[loss=0.1527, simple_loss=0.2339, pruned_loss=0.03578, over 4934.00 frames.], tot_loss[loss=0.1629, simple_loss=0.231, pruned_loss=0.04743, over 973190.71 frames.], batch size: 21, lr: 5.20e-04
2022-05-04 17:24:15,826 INFO [train.py:715] (4/8) Epoch 3, batch 28450, loss[loss=0.1818, simple_loss=0.2326, pruned_loss=0.0655, over 4739.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2309, pruned_loss=0.04765, over 973016.03 frames.], batch size: 16, lr: 5.20e-04
2022-05-04 17:24:55,564 INFO [train.py:715] (4/8) Epoch 3, batch 28500, loss[loss=0.1408, simple_loss=0.2132, pruned_loss=0.03422, over 4787.00 frames.], tot_loss[loss=0.163, simple_loss=0.2306, pruned_loss=0.04772, over 973446.07 frames.], batch size: 18, lr: 5.20e-04
2022-05-04 17:25:34,506 INFO [train.py:715] (4/8) Epoch 3, batch 28550, loss[loss=0.1786, simple_loss=0.2431, pruned_loss=0.05702, over 4849.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2307, pruned_loss=0.0475, over 974403.80 frames.], batch size: 30, lr: 5.20e-04
2022-05-04 17:26:13,420 INFO [train.py:715] (4/8) Epoch 3, batch 28600, loss[loss=0.1872, simple_loss=0.246, pruned_loss=0.06424, over 4753.00 frames.], tot_loss[loss=0.1636, simple_loss=0.2317, pruned_loss=0.04779, over 972978.87 frames.], batch size: 16, lr: 5.20e-04
2022-05-04 17:26:53,127 INFO [train.py:715] (4/8) Epoch 3, batch 28650, loss[loss=0.1776, simple_loss=0.2397, pruned_loss=0.05777, over 4847.00 frames.], tot_loss[loss=0.1637, simple_loss=0.2313, pruned_loss=0.04806, over 972681.71 frames.], batch size: 32, lr: 5.20e-04
2022-05-04 17:27:33,005 INFO [train.py:715] (4/8) Epoch 3, batch 28700, loss[loss=0.1381, simple_loss=0.2016, pruned_loss=0.03735, over 4905.00 frames.], tot_loss[loss=0.1628, simple_loss=0.2308, pruned_loss=0.04745, over 973337.02 frames.], batch size: 17, lr: 5.20e-04
2022-05-04 17:28:12,157 INFO [train.py:715] (4/8) Epoch 3, batch 28750, loss[loss=0.1448, simple_loss=0.2183, pruned_loss=0.03566, over 4758.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2303, pruned_loss=0.04697, over 973174.71 frames.], batch size: 16, lr: 5.20e-04
2022-05-04 17:28:51,999 INFO [train.py:715] (4/8) Epoch 3, batch 28800, loss[loss=0.1468, simple_loss=0.2168, pruned_loss=0.03839, over 4810.00 frames.], tot_loss[loss=0.163, simple_loss=0.2308, pruned_loss=0.04761, over 973299.81 frames.], batch size: 27, lr: 5.20e-04
2022-05-04 17:29:32,019 INFO [train.py:715] (4/8) Epoch 3, batch 28850, loss[loss=0.1691, simple_loss=0.2325, pruned_loss=0.05287, over 4890.00 frames.], tot_loss[loss=0.1631, simple_loss=0.2313, pruned_loss=0.04746, over 973474.94 frames.], batch size: 19, lr: 5.20e-04
2022-05-04 17:30:11,199 INFO [train.py:715] (4/8) Epoch 3, batch 28900, loss[loss=0.1519, simple_loss=0.2301, pruned_loss=0.03687, over 4940.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2304, pruned_loss=0.04671, over 973061.07 frames.], batch size: 21, lr: 5.19e-04
2022-05-04 17:30:50,079 INFO [train.py:715] (4/8) Epoch 3, batch 28950, loss[loss=0.1629, simple_loss=0.2396, pruned_loss=0.04308, over 4913.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2306, pruned_loss=0.04655, over 972397.69 frames.], batch size: 18, lr: 5.19e-04
2022-05-04 17:31:29,815 INFO [train.py:715] (4/8) Epoch 3, batch 29000, loss[loss=0.1589, simple_loss=0.2213, pruned_loss=0.04829, over 4864.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2296, pruned_loss=0.04591, over 971310.58 frames.], batch size: 16, lr: 5.19e-04
2022-05-04 17:32:10,056 INFO [train.py:715] (4/8) Epoch 3, batch 29050, loss[loss=0.1508, simple_loss=0.227, pruned_loss=0.03731, over 4875.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2291, pruned_loss=0.0453, over 972003.77 frames.], batch size: 20, lr: 5.19e-04
2022-05-04 17:32:48,614 INFO [train.py:715] (4/8) Epoch 3, batch 29100, loss[loss=0.2212, simple_loss=0.2749, pruned_loss=0.08377, over 4784.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2298, pruned_loss=0.04561, over 971992.38 frames.], batch size: 14, lr: 5.19e-04
2022-05-04 17:33:28,198 INFO [train.py:715] (4/8) Epoch 3, batch 29150, loss[loss=0.1404, simple_loss=0.2181, pruned_loss=0.03135, over 4836.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2285, pruned_loss=0.04531, over 972286.99 frames.], batch size: 26, lr: 5.19e-04
2022-05-04 17:34:08,091 INFO [train.py:715] (4/8) Epoch 3, batch 29200, loss[loss=0.1434, simple_loss=0.2159, pruned_loss=0.0354, over 4948.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2279, pruned_loss=0.04468, over 972071.95 frames.], batch size: 21, lr: 5.19e-04
2022-05-04 17:34:47,190 INFO [train.py:715] (4/8) Epoch 3, batch 29250, loss[loss=0.17, simple_loss=0.239, pruned_loss=0.05044, over 4766.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2282, pruned_loss=0.04501, over 972055.44 frames.], batch size: 14, lr: 5.19e-04
2022-05-04 17:35:26,069 INFO [train.py:715] (4/8) Epoch 3, batch 29300, loss[loss=0.1469, simple_loss=0.2142, pruned_loss=0.03979, over 4761.00 frames.], tot_loss[loss=0.1605, simple_loss=0.229, pruned_loss=0.04606, over 972902.31 frames.], batch size: 12, lr: 5.19e-04
2022-05-04 17:36:06,260 INFO [train.py:715] (4/8) Epoch 3, batch 29350, loss[loss=0.1814, simple_loss=0.256, pruned_loss=0.05343, over 4785.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2288, pruned_loss=0.04574, over 973427.69 frames.], batch size: 17, lr: 5.19e-04
2022-05-04 17:36:45,935 INFO [train.py:715] (4/8) Epoch 3, batch 29400, loss[loss=0.1405, simple_loss=0.2142, pruned_loss=0.03343, over 4754.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2294, pruned_loss=0.04612, over 973493.61 frames.], batch size: 19, lr: 5.18e-04
2022-05-04 17:37:24,686 INFO [train.py:715] (4/8) Epoch 3, batch 29450, loss[loss=0.1637, simple_loss=0.2289, pruned_loss=0.04925, over 4689.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2304, pruned_loss=0.04659, over 972984.27 frames.], batch size: 15, lr: 5.18e-04
2022-05-04 17:38:03,871 INFO [train.py:715] (4/8) Epoch 3, batch 29500, loss[loss=0.2089, simple_loss=0.2669, pruned_loss=0.07543, over 4748.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2307, pruned_loss=0.04695, over 972343.84 frames.], batch size: 16, lr: 5.18e-04
2022-05-04 17:38:43,452 INFO [train.py:715] (4/8) Epoch 3, batch 29550, loss[loss=0.2058, simple_loss=0.2664, pruned_loss=0.07256, over 4855.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2298, pruned_loss=0.04652, over 972358.78 frames.], batch size: 20, lr: 5.18e-04
2022-05-04 17:39:22,771 INFO [train.py:715] (4/8) Epoch 3, batch 29600, loss[loss=0.1648, simple_loss=0.2425, pruned_loss=0.04352, over 4763.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2297, pruned_loss=0.04629, over 972819.65 frames.], batch size: 19, lr: 5.18e-04
2022-05-04 17:40:01,837 INFO [train.py:715] (4/8) Epoch 3, batch 29650, loss[loss=0.1513, simple_loss=0.2292, pruned_loss=0.03666, over 4932.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2301, pruned_loss=0.04616, over 973192.43 frames.], batch size: 18, lr: 5.18e-04
2022-05-04 17:40:41,989 INFO [train.py:715] (4/8) Epoch 3, batch 29700, loss[loss=0.1364, simple_loss=0.2112, pruned_loss=0.03077, over 4941.00 frames.], tot_loss[loss=0.161, simple_loss=0.2299, pruned_loss=0.04607, over 973271.22 frames.], batch size: 21, lr: 5.18e-04
2022-05-04 17:41:22,016 INFO [train.py:715] (4/8) Epoch 3, batch 29750, loss[loss=0.1388, simple_loss=0.2066, pruned_loss=0.03544, over 4848.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2304, pruned_loss=0.04607, over 972827.11 frames.], batch size: 15, lr: 5.18e-04
2022-05-04 17:42:00,524 INFO [train.py:715] (4/8) Epoch 3, batch 29800, loss[loss=0.1374, simple_loss=0.2, pruned_loss=0.03747, over 4794.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2309, pruned_loss=0.04615, over 973055.06 frames.], batch size: 12, lr: 5.18e-04
2022-05-04 17:42:40,509 INFO [train.py:715] (4/8) Epoch 3, batch 29850, loss[loss=0.2082, simple_loss=0.2706, pruned_loss=0.07295, over 4775.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2298, pruned_loss=0.04596, over 972703.14 frames.], batch size: 17, lr: 5.18e-04
2022-05-04 17:43:20,048 INFO [train.py:715] (4/8) Epoch 3, batch 29900, loss[loss=0.1706, simple_loss=0.2374, pruned_loss=0.05189, over 4989.00 frames.], tot_loss[loss=0.162, simple_loss=0.2309, pruned_loss=0.04658, over 972712.81 frames.], batch size: 25, lr: 5.18e-04
2022-05-04 17:43:58,720 INFO [train.py:715] (4/8) Epoch 3, batch 29950, loss[loss=0.1404, simple_loss=0.2149, pruned_loss=0.03289, over 4936.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2301, pruned_loss=0.04637, over 973496.81 frames.], batch size: 23, lr: 5.17e-04
2022-05-04 17:44:37,449 INFO [train.py:715] (4/8) Epoch 3, batch 30000, loss[loss=0.1501, simple_loss=0.2188, pruned_loss=0.04065, over 4803.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2287, pruned_loss=0.04548, over 973188.88 frames.], batch size: 21, lr: 5.17e-04
2022-05-04 17:44:37,450 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 17:44:47,856 INFO [train.py:742] (4/8) Epoch 3, validation: loss=0.1135, simple_loss=0.1993, pruned_loss=0.01381, over 914524.00 frames.
2022-05-04 17:45:26,663 INFO [train.py:715] (4/8) Epoch 3, batch 30050, loss[loss=0.1813, simple_loss=0.2677, pruned_loss=0.04745, over 4812.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2294, pruned_loss=0.04572, over 973197.94 frames.], batch size: 25, lr: 5.17e-04
2022-05-04 17:46:06,303 INFO [train.py:715] (4/8) Epoch 3, batch 30100, loss[loss=0.1543, simple_loss=0.2253, pruned_loss=0.04169, over 4897.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2295, pruned_loss=0.04617, over 972240.89 frames.], batch size: 19, lr: 5.17e-04
2022-05-04 17:46:46,370 INFO [train.py:715] (4/8) Epoch 3, batch 30150, loss[loss=0.1394, simple_loss=0.2053, pruned_loss=0.03674, over 4855.00 frames.], tot_loss[loss=0.1617, simple_loss=0.23, pruned_loss=0.04665, over 972860.58 frames.], batch size: 32, lr: 5.17e-04
2022-05-04 17:47:24,500 INFO [train.py:715] (4/8) Epoch 3, batch 30200, loss[loss=0.1459, simple_loss=0.2168, pruned_loss=0.03745, over 4965.00 frames.], tot_loss[loss=0.1621, simple_loss=0.2304, pruned_loss=0.04691, over 973666.47 frames.], batch size: 35, lr: 5.17e-04
2022-05-04 17:48:04,129 INFO [train.py:715] (4/8) Epoch 3, batch 30250, loss[loss=0.1289, simple_loss=0.1975, pruned_loss=0.03011, over 4978.00 frames.], tot_loss[loss=0.1623, simple_loss=0.2305, pruned_loss=0.04704, over 973305.16 frames.], batch size: 14, lr: 5.17e-04
2022-05-04 17:48:44,309 INFO [train.py:715] (4/8) Epoch 3, batch 30300, loss[loss=0.1715, simple_loss=0.2356, pruned_loss=0.05372, over 4791.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2295, pruned_loss=0.04607, over 973705.20 frames.], batch size: 17, lr: 5.17e-04
2022-05-04 17:49:23,078 INFO [train.py:715] (4/8) Epoch 3, batch 30350, loss[loss=0.1487, simple_loss=0.2082, pruned_loss=0.04463, over 4902.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2296, pruned_loss=0.04636, over 973778.37 frames.], batch size: 17, lr: 5.17e-04
2022-05-04 17:50:02,734 INFO [train.py:715] (4/8) Epoch 3, batch 30400, loss[loss=0.2025, simple_loss=0.2499, pruned_loss=0.07751, over 4863.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2298, pruned_loss=0.04673, over 973050.06 frames.], batch size: 32, lr: 5.17e-04
2022-05-04 17:50:42,519 INFO [train.py:715] (4/8) Epoch 3, batch 30450, loss[loss=0.1479, simple_loss=0.2111, pruned_loss=0.04239, over 4901.00 frames.], tot_loss[loss=0.161, simple_loss=0.2294, pruned_loss=0.04628, over 972236.09 frames.], batch size: 19, lr: 5.16e-04
2022-05-04 17:51:22,932 INFO [train.py:715] (4/8) Epoch 3, batch 30500, loss[loss=0.1553, simple_loss=0.2225, pruned_loss=0.04407, over 4830.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2293, pruned_loss=0.04612, over 971289.36 frames.], batch size: 15, lr: 5.16e-04
2022-05-04 17:52:02,153 INFO [train.py:715] (4/8) Epoch 3, batch 30550, loss[loss=0.1733, simple_loss=0.2494, pruned_loss=0.04861, over 4986.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2289, pruned_loss=0.04595, over 971935.78 frames.], batch size: 31, lr: 5.16e-04
2022-05-04 17:52:41,686 INFO [train.py:715] (4/8) Epoch 3, batch 30600, loss[loss=0.1335, simple_loss=0.2097, pruned_loss=0.0286, over 4898.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2286, pruned_loss=0.04587, over 972217.69 frames.], batch size: 19, lr: 5.16e-04
2022-05-04 17:53:21,641 INFO [train.py:715] (4/8) Epoch 3, batch 30650, loss[loss=0.1743, simple_loss=0.2348, pruned_loss=0.05684, over 4984.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2281, pruned_loss=0.04574, over 972559.93 frames.], batch size: 39, lr: 5.16e-04
2022-05-04 17:54:00,303 INFO [train.py:715] (4/8) Epoch 3, batch 30700, loss[loss=0.1613, simple_loss=0.222, pruned_loss=0.0503, over 4848.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2292, pruned_loss=0.0463, over 973085.47 frames.], batch size: 12, lr: 5.16e-04
2022-05-04 17:54:39,862 INFO [train.py:715] (4/8) Epoch 3, batch 30750, loss[loss=0.1514, simple_loss=0.2232, pruned_loss=0.03981, over 4804.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2293, pruned_loss=0.04626, over 971594.53 frames.], batch size: 21, lr: 5.16e-04
2022-05-04 17:55:19,268 INFO [train.py:715] (4/8) Epoch 3, batch 30800, loss[loss=0.1796, simple_loss=0.2443, pruned_loss=0.05745, over 4963.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2298, pruned_loss=0.0466, over 971622.80 frames.], batch size: 35, lr: 5.16e-04
2022-05-04 17:55:59,084 INFO [train.py:715] (4/8) Epoch 3, batch 30850, loss[loss=0.1706, simple_loss=0.2354, pruned_loss=0.05287, over 4980.00 frames.], tot_loss[loss=0.1616, simple_loss=0.2297, pruned_loss=0.04672, over 972125.21 frames.], batch size: 24, lr: 5.16e-04
2022-05-04 17:56:37,364 INFO [train.py:715] (4/8) Epoch 3, batch 30900, loss[loss=0.1515, simple_loss=0.2235, pruned_loss=0.03973, over 4822.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2281, pruned_loss=0.04543, over 972775.30 frames.], batch size: 27, lr: 5.16e-04
2022-05-04 17:57:16,438 INFO [train.py:715] (4/8) Epoch 3, batch 30950, loss[loss=0.1769, simple_loss=0.241, pruned_loss=0.05639, over 4860.00 frames.], tot_loss[loss=0.159, simple_loss=0.2279, pruned_loss=0.04504, over 972311.89 frames.], batch size: 13, lr: 5.15e-04
2022-05-04 17:57:55,757 INFO [train.py:715] (4/8) Epoch 3, batch 31000, loss[loss=0.1669, simple_loss=0.2335, pruned_loss=0.05019, over 4947.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2283, pruned_loss=0.0455, over 973094.91 frames.], batch size: 35, lr: 5.15e-04
2022-05-04 17:58:35,031 INFO [train.py:715] (4/8) Epoch 3, batch 31050, loss[loss=0.1454, simple_loss=0.2203, pruned_loss=0.03526, over 4894.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2287, pruned_loss=0.04553, over 972292.78 frames.], batch size: 22, lr: 5.15e-04
2022-05-04 17:59:13,610 INFO [train.py:715] (4/8) Epoch 3, batch 31100, loss[loss=0.1327, simple_loss=0.2076, pruned_loss=0.02889, over 4969.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2292, pruned_loss=0.04562, over 973444.39 frames.], batch size: 14, lr: 5.15e-04
2022-05-04 17:59:53,183 INFO [train.py:715] (4/8) Epoch 3, batch 31150, loss[loss=0.1351, simple_loss=0.2018, pruned_loss=0.03426, over 4831.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2297, pruned_loss=0.0455, over 973110.25 frames.], batch size: 13, lr: 5.15e-04
2022-05-04 18:00:32,418 INFO [train.py:715] (4/8) Epoch 3, batch 31200, loss[loss=0.1702, simple_loss=0.2345, pruned_loss=0.05295, over 4941.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2295, pruned_loss=0.04572, over 973222.10 frames.], batch size: 35, lr: 5.15e-04
2022-05-04 18:01:11,061 INFO [train.py:715] (4/8) Epoch 3, batch 31250, loss[loss=0.1442, simple_loss=0.2112, pruned_loss=0.03865, over 4786.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2291, pruned_loss=0.04561, over 972808.44 frames.], batch size: 17, lr: 5.15e-04
2022-05-04 18:01:50,132 INFO [train.py:715] (4/8) Epoch 3, batch 31300, loss[loss=0.1766, simple_loss=0.2383, pruned_loss=0.05744, over 4897.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2293, pruned_loss=0.04576, over 973344.10 frames.], batch size: 19, lr: 5.15e-04
2022-05-04 18:02:29,481 INFO [train.py:715] (4/8) Epoch 3, batch 31350, loss[loss=0.1817, simple_loss=0.2286, pruned_loss=0.06734, over 4852.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2306, pruned_loss=0.04661, over 973064.06 frames.], batch size: 13, lr: 5.15e-04
2022-05-04 18:03:08,645 INFO [train.py:715] (4/8) Epoch 3, batch 31400, loss[loss=0.162, simple_loss=0.2344, pruned_loss=0.04481, over 4954.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2302, pruned_loss=0.04625, over 973306.26 frames.], batch size: 21, lr: 5.15e-04
2022-05-04 18:03:47,229 INFO [train.py:715] (4/8) Epoch 3, batch 31450, loss[loss=0.1748, simple_loss=0.255, pruned_loss=0.0473, over 4788.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2301, pruned_loss=0.04627, over 972704.19 frames.], batch size: 18, lr: 5.15e-04
2022-05-04 18:04:26,975 INFO [train.py:715] (4/8) Epoch 3, batch 31500, loss[loss=0.1635, simple_loss=0.2453, pruned_loss=0.04086, over 4765.00 frames.], tot_loss[loss=0.1607, simple_loss=0.2298, pruned_loss=0.04578, over 972099.07 frames.], batch size: 18, lr: 5.14e-04
2022-05-04 18:05:06,851 INFO [train.py:715] (4/8) Epoch 3, batch 31550, loss[loss=0.1918, simple_loss=0.2602, pruned_loss=0.06172, over 4697.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2303, pruned_loss=0.04609, over 972397.14 frames.], batch size: 15, lr: 5.14e-04
2022-05-04 18:05:47,989 INFO [train.py:715] (4/8) Epoch 3, batch 31600, loss[loss=0.1715, simple_loss=0.2508, pruned_loss=0.04613, over 4755.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2297, pruned_loss=0.04592, over 972018.45 frames.], batch size: 16, lr: 5.14e-04
2022-05-04 18:06:26,994 INFO [train.py:715] (4/8) Epoch 3, batch 31650, loss[loss=0.1556, simple_loss=0.219, pruned_loss=0.04609, over 4946.00 frames.], tot_loss[loss=0.1613, simple_loss=0.2299, pruned_loss=0.04638, over 972343.55 frames.], batch size: 21, lr: 5.14e-04
2022-05-04 18:07:07,175 INFO [train.py:715] (4/8) Epoch 3, batch 31700, loss[loss=0.1937, simple_loss=0.2605, pruned_loss=0.06343, over 4965.00 frames.], tot_loss[loss=0.1619, simple_loss=0.2305, pruned_loss=0.04667, over 972886.29 frames.], batch size: 15, lr: 5.14e-04
2022-05-04 18:07:46,355 INFO [train.py:715] (4/8) Epoch 3, batch 31750, loss[loss=0.203, simple_loss=0.2699, pruned_loss=0.06805, over 4786.00 frames.], tot_loss[loss=0.1614, simple_loss=0.23, pruned_loss=0.04645, over 973905.94 frames.], batch size: 14, lr: 5.14e-04
2022-05-04 18:08:24,493 INFO [train.py:715] (4/8) Epoch 3, batch 31800, loss[loss=0.1519, simple_loss=0.2219, pruned_loss=0.04093, over 4849.00 frames.], tot_loss[loss=0.1614, simple_loss=0.23, pruned_loss=0.04642, over 973502.92 frames.], batch size: 32, lr: 5.14e-04
2022-05-04 18:09:04,270 INFO [train.py:715] (4/8) Epoch 3, batch 31850, loss[loss=0.1675, simple_loss=0.2332, pruned_loss=0.05096, over 4916.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2295, pruned_loss=0.04611, over 972586.38 frames.], batch size: 17, lr: 5.14e-04
2022-05-04 18:09:43,771 INFO [train.py:715] (4/8) Epoch 3, batch 31900, loss[loss=0.1902, simple_loss=0.2511, pruned_loss=0.06459, over 4845.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2296, pruned_loss=0.0461, over 972089.61 frames.], batch size: 32, lr: 5.14e-04
2022-05-04 18:10:22,478 INFO [train.py:715] (4/8) Epoch 3, batch 31950, loss[loss=0.185, simple_loss=0.2472, pruned_loss=0.06143, over 4892.00 frames.], tot_loss[loss=0.161, simple_loss=0.2295, pruned_loss=0.04622, over 973031.69 frames.], batch size: 19, lr: 5.14e-04
2022-05-04 18:11:01,411 INFO [train.py:715] (4/8) Epoch 3, batch 32000, loss[loss=0.1612, simple_loss=0.2205, pruned_loss=0.05098, over 4770.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2293, pruned_loss=0.04589, over 972465.30 frames.], batch size: 17, lr: 5.14e-04
2022-05-04 18:11:41,008 INFO [train.py:715] (4/8) Epoch 3, batch 32050, loss[loss=0.1469, simple_loss=0.2194, pruned_loss=0.03726, over 4865.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2288, pruned_loss=0.0455, over 971960.29 frames.], batch size: 20, lr: 5.13e-04
2022-05-04 18:12:19,203 INFO [train.py:715] (4/8) Epoch 3, batch 32100, loss[loss=0.172, simple_loss=0.2356, pruned_loss=0.05419, over 4966.00 frames.], tot_loss[loss=0.1606, simple_loss=0.2294, pruned_loss=0.04588, over 971073.01 frames.], batch size: 39, lr: 5.13e-04
2022-05-04 18:12:58,310 INFO [train.py:715] (4/8) Epoch 3, batch 32150, loss[loss=0.1451, simple_loss=0.2122, pruned_loss=0.03898, over 4779.00 frames.], tot_loss[loss=0.1603, simple_loss=0.2292, pruned_loss=0.04569, over 971362.69 frames.], batch size: 18, lr: 5.13e-04
2022-05-04 18:13:37,851 INFO [train.py:715] (4/8) Epoch 3, batch 32200, loss[loss=0.1654, simple_loss=0.228, pruned_loss=0.05138, over 4651.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2272, pruned_loss=0.04457, over 970962.12 frames.], batch size: 13, lr: 5.13e-04
2022-05-04 18:14:16,672 INFO [train.py:715] (4/8) Epoch 3, batch 32250, loss[loss=0.2147, simple_loss=0.2678, pruned_loss=0.08079, over 4938.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2279, pruned_loss=0.04496, over 971468.87 frames.], batch size: 18, lr: 5.13e-04
2022-05-04 18:14:55,234 INFO [train.py:715] (4/8) Epoch 3, batch 32300, loss[loss=0.1498, simple_loss=0.2129, pruned_loss=0.04338, over 4808.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2272, pruned_loss=0.04481, over 971275.89 frames.], batch size: 21, lr: 5.13e-04
2022-05-04 18:15:34,898 INFO [train.py:715] (4/8) Epoch 3, batch 32350, loss[loss=0.1944, simple_loss=0.2636, pruned_loss=0.06258, over 4919.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2281, pruned_loss=0.04479, over 971350.15 frames.], batch size: 17, lr: 5.13e-04
2022-05-04 18:16:14,619 INFO [train.py:715] (4/8) Epoch 3, batch 32400, loss[loss=0.1471, simple_loss=0.2279, pruned_loss=0.03314, over 4929.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2293, pruned_loss=0.04552, over 971622.00 frames.], batch size: 29, lr: 5.13e-04
2022-05-04 18:16:52,599 INFO [train.py:715] (4/8) Epoch 3, batch 32450, loss[loss=0.1591, simple_loss=0.2445, pruned_loss=0.03691, over 4817.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2295, pruned_loss=0.04578, over 971725.85 frames.], batch size: 25, lr: 5.13e-04
2022-05-04 18:17:32,077 INFO [train.py:715] (4/8) Epoch 3, batch 32500, loss[loss=0.1827, simple_loss=0.2486, pruned_loss=0.05842, over 4757.00 frames.], tot_loss[loss=0.1592, simple_loss=0.228, pruned_loss=0.04515, over 970489.50 frames.], batch size: 16, lr: 5.13e-04
2022-05-04 18:18:11,714 INFO [train.py:715] (4/8) Epoch 3, batch 32550, loss[loss=0.1377, simple_loss=0.2136, pruned_loss=0.03083, over 4753.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2275, pruned_loss=0.04486, over 970737.40 frames.], batch size: 16, lr: 5.12e-04
2022-05-04 18:18:50,229 INFO [train.py:715] (4/8) Epoch 3, batch 32600, loss[loss=0.1469, simple_loss=0.2138, pruned_loss=0.04002, over 4940.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2286, pruned_loss=0.0455, over 970907.28 frames.], batch size: 23, lr: 5.12e-04
2022-05-04 18:19:29,061 INFO [train.py:715] (4/8) Epoch 3, batch 32650, loss[loss=0.1573, simple_loss=0.2332, pruned_loss=0.04074, over 4983.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2281, pruned_loss=0.04506, over 971686.16 frames.], batch size: 26, lr: 5.12e-04
2022-05-04 18:20:08,687 INFO [train.py:715] (4/8) Epoch 3, batch 32700, loss[loss=0.1689, simple_loss=0.2346, pruned_loss=0.05159, over 4989.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2286, pruned_loss=0.04538, over 972490.69 frames.], batch size: 14, lr: 5.12e-04
2022-05-04 18:20:47,704 INFO [train.py:715] (4/8) Epoch 3, batch 32750, loss[loss=0.1761, simple_loss=0.2354, pruned_loss=0.05842, over 4778.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2291, pruned_loss=0.04582, over 972346.34 frames.], batch size: 17, lr: 5.12e-04
2022-05-04 18:21:26,288 INFO [train.py:715] (4/8) Epoch 3, batch 32800, loss[loss=0.1551, simple_loss=0.2163, pruned_loss=0.04696, over 4927.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2283, pruned_loss=0.04553, over 972020.05 frames.], batch size: 18, lr: 5.12e-04
2022-05-04 18:22:05,408 INFO [train.py:715] (4/8) Epoch 3, batch 32850, loss[loss=0.1452, simple_loss=0.2261, pruned_loss=0.03211, over 4789.00 frames.], tot_loss[loss=0.16, simple_loss=0.2285, pruned_loss=0.04575, over 971920.58 frames.], batch size: 24, lr: 5.12e-04
2022-05-04 18:22:44,589 INFO [train.py:715] (4/8) Epoch 3, batch 32900, loss[loss=0.1771, simple_loss=0.2437, pruned_loss=0.05525, over 4850.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2282, pruned_loss=0.04535, over 971668.79 frames.], batch size: 32, lr: 5.12e-04
2022-05-04 18:23:23,655 INFO [train.py:715] (4/8) Epoch 3, batch 32950, loss[loss=0.2138, simple_loss=0.263, pruned_loss=0.08231, over 4767.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2285, pruned_loss=0.04505, over 972272.98 frames.], batch size: 17, lr: 5.12e-04
2022-05-04 18:24:02,386 INFO [train.py:715] (4/8) Epoch 3, batch 33000, loss[loss=0.1418, simple_loss=0.212, pruned_loss=0.03582, over 4799.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2285, pruned_loss=0.04489, over 972792.82 frames.], batch size: 14, lr: 5.12e-04
2022-05-04 18:24:02,387 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 18:24:11,703 INFO [train.py:742] (4/8) Epoch 3, validation: loss=0.1131, simple_loss=0.199, pruned_loss=0.01363, over 914524.00 frames.
2022-05-04 18:24:50,800 INFO [train.py:715] (4/8) Epoch 3, batch 33050, loss[loss=0.1876, simple_loss=0.2446, pruned_loss=0.06527, over 4979.00 frames.], tot_loss[loss=0.1596, simple_loss=0.2286, pruned_loss=0.04529, over 972590.57 frames.], batch size: 35, lr: 5.12e-04
2022-05-04 18:25:30,711 INFO [train.py:715] (4/8) Epoch 3, batch 33100, loss[loss=0.1604, simple_loss=0.2417, pruned_loss=0.03954, over 4949.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2284, pruned_loss=0.04533, over 972494.31 frames.], batch size: 21, lr: 5.11e-04
2022-05-04 18:26:09,586 INFO [train.py:715] (4/8) Epoch 3, batch 33150, loss[loss=0.1465, simple_loss=0.2245, pruned_loss=0.03424, over 4981.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2286, pruned_loss=0.04505, over 972131.17 frames.], batch size: 28, lr: 5.11e-04
2022-05-04 18:26:48,263 INFO [train.py:715] (4/8) Epoch 3, batch 33200, loss[loss=0.139, simple_loss=0.2103, pruned_loss=0.03382, over 4891.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2281, pruned_loss=0.04508, over 972272.61 frames.], batch size: 22, lr: 5.11e-04
2022-05-04 18:27:28,161 INFO [train.py:715] (4/8) Epoch 3, batch 33250, loss[loss=0.1365, simple_loss=0.2053, pruned_loss=0.03382, over 4792.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2275, pruned_loss=0.04501, over 972270.95 frames.], batch size: 14, lr: 5.11e-04
2022-05-04 18:28:07,720 INFO [train.py:715] (4/8) Epoch 3, batch 33300, loss[loss=0.1449, simple_loss=0.2329, pruned_loss=0.02848, over 4817.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2278, pruned_loss=0.04467, over 973124.56 frames.], batch size: 27, lr: 5.11e-04
2022-05-04 18:28:46,233 INFO [train.py:715] (4/8) Epoch 3, batch 33350, loss[loss=0.1355, simple_loss=0.2036, pruned_loss=0.03373, over 4868.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2287, pruned_loss=0.04502, over 973089.59 frames.], batch size: 20, lr: 5.11e-04
2022-05-04 18:29:25,534 INFO [train.py:715] (4/8) Epoch 3, batch 33400, loss[loss=0.1587, simple_loss=0.237, pruned_loss=0.04019, over 4978.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2289, pruned_loss=0.0449, over 973923.47 frames.], batch size: 15, lr: 5.11e-04
2022-05-04 18:30:05,187 INFO [train.py:715] (4/8) Epoch 3, batch 33450, loss[loss=0.2504, simple_loss=0.3128, pruned_loss=0.09403, over 4912.00 frames.], tot_loss[loss=0.1599, simple_loss=0.229, pruned_loss=0.04542, over 972877.29 frames.], batch size: 18, lr: 5.11e-04
2022-05-04 18:30:44,205 INFO [train.py:715] (4/8) Epoch 3, batch 33500, loss[loss=0.1764, simple_loss=0.2507, pruned_loss=0.05108, over 4916.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2295, pruned_loss=0.04539, over 972609.21 frames.], batch size: 18, lr: 5.11e-04
2022-05-04 18:31:23,292 INFO [train.py:715] (4/8) Epoch 3, batch 33550, loss[loss=0.1636, simple_loss=0.2279, pruned_loss=0.0496, over 4946.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2289, pruned_loss=0.04564, over 973143.40 frames.], batch size: 35, lr: 5.11e-04
2022-05-04 18:32:03,652 INFO [train.py:715] (4/8) Epoch 3, batch 33600, loss[loss=0.1912, simple_loss=0.2544, pruned_loss=0.06396, over 4869.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2289, pruned_loss=0.0453, over 973858.97 frames.], batch size: 32, lr: 5.11e-04
2022-05-04 18:32:43,010 INFO [train.py:715] (4/8) Epoch 3, batch 33650, loss[loss=0.1631, simple_loss=0.2466, pruned_loss=0.03983, over 4890.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2284, pruned_loss=0.04466, over 974164.59 frames.], batch size: 16, lr: 5.10e-04
2022-05-04 18:33:21,655 INFO [train.py:715] (4/8) Epoch 3, batch 33700, loss[loss=0.1661, simple_loss=0.2443, pruned_loss=0.04394, over 4804.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2287, pruned_loss=0.04486, over 974471.33 frames.], batch size: 21, lr: 5.10e-04
2022-05-04 18:34:01,449 INFO [train.py:715] (4/8) Epoch 3, batch 33750, loss[loss=0.1268, simple_loss=0.199, pruned_loss=0.02734, over 4924.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2283, pruned_loss=0.04514, over 973076.97 frames.], batch size: 18, lr: 5.10e-04
2022-05-04 18:34:40,932 INFO [train.py:715] (4/8) Epoch 3, batch 33800, loss[loss=0.194, simple_loss=0.2544, pruned_loss=0.06678, over 4779.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2282, pruned_loss=0.04503, over 973190.11 frames.], batch size: 18, lr: 5.10e-04
2022-05-04 18:35:19,311 INFO [train.py:715] (4/8) Epoch 3, batch 33850, loss[loss=0.1563, simple_loss=0.2415, pruned_loss=0.03555, over 4921.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2283, pruned_loss=0.04503, over 973347.01 frames.], batch size: 29, lr: 5.10e-04
2022-05-04 18:35:58,140 INFO [train.py:715] (4/8) Epoch 3, batch 33900, loss[loss=0.1406, simple_loss=0.2163, pruned_loss=0.03249, over 4964.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2283, pruned_loss=0.04505, over 973240.75 frames.], batch size: 28, lr: 5.10e-04
2022-05-04 18:36:38,298 INFO [train.py:715] (4/8) Epoch 3, batch 33950, loss[loss=0.1399, simple_loss=0.2088, pruned_loss=0.03552, over 4823.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2284, pruned_loss=0.0453, over 973053.31 frames.], batch size: 26, lr: 5.10e-04
2022-05-04 18:37:17,237 INFO [train.py:715] (4/8) Epoch 3, batch 34000, loss[loss=0.138, simple_loss=0.2129, pruned_loss=0.03155, over 4794.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2289, pruned_loss=0.04528, over 972939.03 frames.], batch size: 24, lr: 5.10e-04
2022-05-04 18:37:55,979 INFO [train.py:715] (4/8) Epoch 3, batch 34050, loss[loss=0.1222, simple_loss=0.1882, pruned_loss=0.02813, over 4736.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2279, pruned_loss=0.04487, over 972498.94 frames.], batch size: 16, lr: 5.10e-04
2022-05-04 18:38:35,310 INFO [train.py:715] (4/8) Epoch 3, batch 34100, loss[loss=0.1724, simple_loss=0.2307, pruned_loss=0.05703, over 4637.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2288, pruned_loss=0.04548, over 971585.28 frames.], batch size: 13, lr: 5.10e-04
2022-05-04 18:39:15,278 INFO [train.py:715] (4/8) Epoch 3, batch 34150, loss[loss=0.1375, simple_loss=0.2057, pruned_loss=0.0347, over 4829.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2291, pruned_loss=0.04531, over 971429.15 frames.], batch size: 12, lr: 5.10e-04
2022-05-04 18:39:53,555 INFO [train.py:715] (4/8) Epoch 3, batch 34200, loss[loss=0.1303, simple_loss=0.1997, pruned_loss=0.0305, over 4758.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2288, pruned_loss=0.04476, over 972516.05 frames.], batch size: 19, lr: 5.09e-04
2022-05-04 18:40:33,002 INFO [train.py:715] (4/8) Epoch 3, batch 34250, loss[loss=0.1341, simple_loss=0.2013, pruned_loss=0.03343, over 4988.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2282, pruned_loss=0.0448, over 972166.88 frames.], batch size: 27, lr: 5.09e-04
2022-05-04 18:41:13,062 INFO [train.py:715] (4/8) Epoch 3, batch 34300, loss[loss=0.1338, simple_loss=0.2053, pruned_loss=0.03111, over 4972.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2267, pruned_loss=0.04354, over 973149.41 frames.], batch size: 24, lr: 5.09e-04
2022-05-04 18:41:52,482 INFO [train.py:715] (4/8) Epoch 3, batch 34350, loss[loss=0.1416, simple_loss=0.2215, pruned_loss=0.03092, over 4796.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2272, pruned_loss=0.04394, over 973317.05 frames.], batch size: 21, lr: 5.09e-04
2022-05-04 18:42:31,602 INFO [train.py:715] (4/8) Epoch 3, batch 34400, loss[loss=0.2015, simple_loss=0.2634, pruned_loss=0.06986, over 4772.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2276, pruned_loss=0.04404, over 973088.01 frames.], batch size: 19, lr: 5.09e-04
2022-05-04 18:43:11,182 INFO [train.py:715] (4/8) Epoch 3, batch 34450, loss[loss=0.1839, simple_loss=0.2496, pruned_loss=0.0591, over 4983.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2292, pruned_loss=0.04491, over 973166.58 frames.], batch size: 25, lr: 5.09e-04
2022-05-04 18:43:51,338 INFO [train.py:715] (4/8) Epoch 3, batch 34500, loss[loss=0.1525, simple_loss=0.2223, pruned_loss=0.0413, over 4817.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2298, pruned_loss=0.04596, over 973530.52 frames.], batch size: 15, lr: 5.09e-04
2022-05-04 18:44:29,765 INFO [train.py:715] (4/8) Epoch 3, batch 34550, loss[loss=0.1587, simple_loss=0.2221, pruned_loss=0.0477, over 4742.00 frames.], tot_loss[loss=0.161, simple_loss=0.2295, pruned_loss=0.04627, over 973738.84 frames.], batch size: 16, lr: 5.09e-04
2022-05-04 18:45:08,807 INFO [train.py:715] (4/8) Epoch 3, batch 34600, loss[loss=0.1356, simple_loss=0.2151, pruned_loss=0.02805, over 4799.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2296, pruned_loss=0.04668, over 973163.02 frames.], batch size: 25, lr: 5.09e-04
2022-05-04 18:45:49,188 INFO [train.py:715] (4/8) Epoch 3, batch 34650, loss[loss=0.1466, simple_loss=0.2243, pruned_loss=0.03438, over 4656.00 frames.], tot_loss[loss=0.1611, simple_loss=0.2294, pruned_loss=0.0464, over 971938.50 frames.], batch size: 13, lr: 5.09e-04
2022-05-04 18:46:28,783 INFO [train.py:715] (4/8) Epoch 3, batch 34700, loss[loss=0.144, simple_loss=0.2203, pruned_loss=0.03388, over 4872.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2291, pruned_loss=0.04588, over 971340.29 frames.], batch size: 20, lr: 5.09e-04
2022-05-04 18:47:07,066 INFO [train.py:715] (4/8) Epoch 3, batch 34750, loss[loss=0.1479, simple_loss=0.2186, pruned_loss=0.0386, over 4795.00 frames.], tot_loss[loss=0.161, simple_loss=0.2298, pruned_loss=0.04614, over 971195.42 frames.], batch size: 12, lr: 5.08e-04
2022-05-04 18:47:44,767 INFO [train.py:715] (4/8) Epoch 3, batch 34800, loss[loss=0.1242, simple_loss=0.1951, pruned_loss=0.02672, over 4762.00 frames.], tot_loss[loss=0.16, simple_loss=0.228, pruned_loss=0.04596, over 970310.97 frames.], batch size: 12, lr: 5.08e-04
2022-05-04 18:48:35,147 INFO [train.py:715] (4/8) Epoch 4, batch 0, loss[loss=0.153, simple_loss=0.2127, pruned_loss=0.04662, over 4795.00 frames.], tot_loss[loss=0.153, simple_loss=0.2127, pruned_loss=0.04662, over 4795.00 frames.], batch size: 21, lr: 4.78e-04
2022-05-04 18:49:16,529 INFO [train.py:715] (4/8) Epoch 4, batch 50, loss[loss=0.1375, simple_loss=0.2151, pruned_loss=0.03, over 4792.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2292, pruned_loss=0.04624, over 219204.66 frames.], batch size: 17, lr: 4.78e-04
2022-05-04 18:49:57,182 INFO [train.py:715] (4/8) Epoch 4, batch 100, loss[loss=0.1731, simple_loss=0.2455, pruned_loss=0.05035, over 4893.00 frames.], tot_loss[loss=0.16, simple_loss=0.2293, pruned_loss=0.04532, over 386734.52 frames.], batch size: 19, lr: 4.78e-04
2022-05-04 18:50:38,011 INFO [train.py:715] (4/8) Epoch 4, batch 150, loss[loss=0.1458, simple_loss=0.2066, pruned_loss=0.04243, over 4800.00 frames.], tot_loss[loss=0.1612, simple_loss=0.2301, pruned_loss=0.04612, over 516599.53 frames.], batch size: 12, lr: 4.78e-04
2022-05-04 18:51:19,057 INFO [train.py:715] (4/8) Epoch 4, batch 200, loss[loss=0.1661, simple_loss=0.2429, pruned_loss=0.04464, over 4939.00 frames.], tot_loss[loss=0.1615, simple_loss=0.2304, pruned_loss=0.04627, over 618259.48 frames.], batch size: 29, lr: 4.78e-04
2022-05-04 18:52:00,261 INFO [train.py:715] (4/8) Epoch 4, batch 250, loss[loss=0.1408, simple_loss=0.2077, pruned_loss=0.03698, over 4812.00 frames.], tot_loss[loss=0.1627, simple_loss=0.2316, pruned_loss=0.04694, over 696930.88 frames.], batch size: 26, lr: 4.77e-04
2022-05-04 18:52:41,185 INFO [train.py:715] (4/8) Epoch 4, batch 300, loss[loss=0.1716, simple_loss=0.2426, pruned_loss=0.05033, over 4953.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2311, pruned_loss=0.04625, over 757609.73 frames.], batch size: 39, lr: 4.77e-04
2022-05-04 18:53:22,430 INFO [train.py:715] (4/8) Epoch 4, batch 350, loss[loss=0.1943, simple_loss=0.2592, pruned_loss=0.0647, over 4919.00 frames.], tot_loss[loss=0.1609, simple_loss=0.2303, pruned_loss=0.04576, over 805937.26 frames.], batch size: 18, lr: 4.77e-04
2022-05-04 18:54:04,557 INFO [train.py:715] (4/8) Epoch 4, batch 400, loss[loss=0.1244, simple_loss=0.1981, pruned_loss=0.02535, over 4898.00 frames.], tot_loss[loss=0.1618, simple_loss=0.2309, pruned_loss=0.04636, over 843240.59 frames.], batch size: 19, lr: 4.77e-04
2022-05-04 18:54:45,203 INFO [train.py:715] (4/8) Epoch 4, batch 450, loss[loss=0.1484, simple_loss=0.2255, pruned_loss=0.03559, over 4972.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2307, pruned_loss=0.04603, over 871626.35 frames.], batch size: 15, lr: 4.77e-04
2022-05-04 18:55:26,263 INFO [train.py:715] (4/8) Epoch 4, batch 500, loss[loss=0.1541, simple_loss=0.2199, pruned_loss=0.04411, over 4788.00 frames.], tot_loss[loss=0.1606, simple_loss=0.23, pruned_loss=0.04563, over 894105.88 frames.], batch size: 17, lr: 4.77e-04
2022-05-04 18:56:07,515 INFO [train.py:715] (4/8) Epoch 4, batch 550, loss[loss=0.1521, simple_loss=0.219, pruned_loss=0.04258, over 4791.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2291, pruned_loss=0.04499, over 911731.09 frames.], batch size: 24, lr: 4.77e-04
2022-05-04 18:56:48,419 INFO [train.py:715] (4/8) Epoch 4, batch 600, loss[loss=0.1349, simple_loss=0.1993, pruned_loss=0.03521, over 4776.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2286, pruned_loss=0.045, over 924571.86 frames.], batch size: 14, lr: 4.77e-04
2022-05-04 18:57:28,929 INFO [train.py:715] (4/8) Epoch 4, batch 650, loss[loss=0.16, simple_loss=0.215, pruned_loss=0.05252, over 4932.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2281, pruned_loss=0.04513, over 934976.43 frames.], batch size: 23, lr: 4.77e-04
2022-05-04 18:58:10,005 INFO [train.py:715] (4/8) Epoch 4, batch 700, loss[loss=0.1446, simple_loss=0.2161, pruned_loss=0.03653, over 4805.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2275, pruned_loss=0.04508, over 943060.24 frames.], batch size: 21, lr: 4.77e-04
2022-05-04 18:58:51,940 INFO [train.py:715] (4/8) Epoch 4, batch 750, loss[loss=0.1503, simple_loss=0.2171, pruned_loss=0.04174, over 4795.00 frames.], tot_loss[loss=0.1592, simple_loss=0.228, pruned_loss=0.04516, over 950089.82 frames.], batch size: 13, lr: 4.77e-04
2022-05-04 18:59:33,014 INFO [train.py:715] (4/8) Epoch 4, batch 800, loss[loss=0.1743, simple_loss=0.2615, pruned_loss=0.04352, over 4758.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2282, pruned_loss=0.04524, over 954724.44 frames.], batch size: 19, lr: 4.77e-04
2022-05-04 19:00:13,437 INFO [train.py:715] (4/8) Epoch 4, batch 850, loss[loss=0.1513, simple_loss=0.2315, pruned_loss=0.03554, over 4819.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2273, pruned_loss=0.04456, over 958604.73 frames.], batch size: 12, lr: 4.76e-04
2022-05-04 19:00:54,499 INFO [train.py:715] (4/8) Epoch 4, batch 900, loss[loss=0.1286, simple_loss=0.2055, pruned_loss=0.02585, over 4797.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2273, pruned_loss=0.04501, over 960487.42 frames.], batch size: 21, lr: 4.76e-04
2022-05-04 19:01:35,348 INFO [train.py:715] (4/8) Epoch 4, batch 950, loss[loss=0.1585, simple_loss=0.221, pruned_loss=0.04802, over 4980.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2277, pruned_loss=0.04523, over 963192.56 frames.], batch size: 25, lr: 4.76e-04
2022-05-04 19:02:16,237 INFO [train.py:715] (4/8) Epoch 4, batch 1000, loss[loss=0.1468, simple_loss=0.2152, pruned_loss=0.03915, over 4687.00 frames.], tot_loss[loss=0.1608, simple_loss=0.2292, pruned_loss=0.04615, over 965127.77 frames.], batch size: 15, lr: 4.76e-04
2022-05-04 19:02:56,946 INFO [train.py:715] (4/8) Epoch 4, batch 1050, loss[loss=0.1426, simple_loss=0.2084, pruned_loss=0.03843, over 4799.00 frames.], tot_loss[loss=0.1614, simple_loss=0.2298, pruned_loss=0.04651, over 966226.06 frames.], batch size: 12, lr: 4.76e-04
2022-05-04 19:03:38,125 INFO [train.py:715] (4/8) Epoch 4, batch 1100, loss[loss=0.1357, simple_loss=0.2, pruned_loss=0.03574, over 4757.00 frames.], tot_loss[loss=0.1604, simple_loss=0.2287, pruned_loss=0.04609, over 967093.34 frames.], batch size: 19, lr: 4.76e-04
2022-05-04 19:04:18,525 INFO [train.py:715] (4/8) Epoch 4, batch 1150, loss[loss=0.1549, simple_loss=0.2191, pruned_loss=0.04539, over 4741.00 frames.], tot_loss[loss=0.16, simple_loss=0.2285, pruned_loss=0.04579, over 968534.00 frames.], batch size: 12, lr: 4.76e-04
2022-05-04 19:04:58,026 INFO [train.py:715] (4/8) Epoch 4, batch 1200, loss[loss=0.1621, simple_loss=0.2396, pruned_loss=0.0423, over 4802.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2284, pruned_loss=0.04573, over 969478.70 frames.], batch size: 25, lr: 4.76e-04
2022-05-04 19:05:38,585 INFO [train.py:715] (4/8) Epoch 4, batch 1250, loss[loss=0.1743, simple_loss=0.2404, pruned_loss=0.05409, over 4827.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2281, pruned_loss=0.04526, over 969656.68 frames.], batch size: 15, lr: 4.76e-04
2022-05-04 19:06:19,645 INFO [train.py:715] (4/8) Epoch 4, batch 1300, loss[loss=0.16, simple_loss=0.2455, pruned_loss=0.03724, over 4972.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2274, pruned_loss=0.04504, over 970623.56 frames.], batch size: 24, lr: 4.76e-04
2022-05-04 19:06:59,650 INFO [train.py:715] (4/8) Epoch 4, batch 1350, loss[loss=0.1756, simple_loss=0.2452, pruned_loss=0.05303, over 4785.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2281, pruned_loss=0.04527, over 971204.54 frames.], batch size: 17, lr: 4.76e-04
2022-05-04 19:07:40,367 INFO [train.py:715] (4/8) Epoch 4, batch 1400, loss[loss=0.1532, simple_loss=0.2222, pruned_loss=0.04208, over 4864.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2281, pruned_loss=0.04542, over 971384.23 frames.], batch size: 32, lr: 4.76e-04
2022-05-04 19:08:21,344 INFO [train.py:715] (4/8) Epoch 4, batch 1450, loss[loss=0.1679, simple_loss=0.2289, pruned_loss=0.05347, over 4848.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2279, pruned_loss=0.045, over 970831.33 frames.], batch size: 15, lr: 4.75e-04
2022-05-04 19:09:02,413 INFO [train.py:715] (4/8) Epoch 4, batch 1500, loss[loss=0.1892, simple_loss=0.2504, pruned_loss=0.06399, over 4781.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2276, pruned_loss=0.04402, over 970902.13 frames.], batch size: 14, lr: 4.75e-04
2022-05-04 19:09:42,028 INFO [train.py:715] (4/8) Epoch 4, batch 1550, loss[loss=0.1622, simple_loss=0.2301, pruned_loss=0.04717, over 4774.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2281, pruned_loss=0.04431, over 970409.10 frames.], batch size: 18, lr: 4.75e-04
2022-05-04 19:10:23,015 INFO [train.py:715] (4/8) Epoch 4, batch 1600, loss[loss=0.1425, simple_loss=0.2113, pruned_loss=0.03686, over 4781.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2282, pruned_loss=0.04468, over 970848.78 frames.], batch size: 14, lr: 4.75e-04
2022-05-04 19:11:04,733 INFO [train.py:715] (4/8) Epoch 4, batch 1650, loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.0314, over 4825.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2283, pruned_loss=0.04475, over 971153.22 frames.], batch size: 25, lr: 4.75e-04
2022-05-04 19:11:45,099 INFO [train.py:715] (4/8) Epoch 4, batch 1700, loss[loss=0.1514, simple_loss=0.2242, pruned_loss=0.03927, over 4708.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2281, pruned_loss=0.04506, over 970933.90 frames.], batch size: 15, lr: 4.75e-04
2022-05-04 19:12:25,102 INFO [train.py:715] (4/8) Epoch 4, batch 1750, loss[loss=0.1386, simple_loss=0.2125, pruned_loss=0.03241, over 4983.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2271, pruned_loss=0.04428, over 971236.90 frames.], batch size: 28, lr: 4.75e-04
2022-05-04 19:13:06,304 INFO [train.py:715] (4/8) Epoch 4, batch 1800, loss[loss=0.1371, simple_loss=0.2121, pruned_loss=0.031, over 4888.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2271, pruned_loss=0.04433, over 972587.47 frames.], batch size: 16, lr: 4.75e-04
2022-05-04 19:13:47,653 INFO [train.py:715] (4/8) Epoch 4, batch 1850, loss[loss=0.1612, simple_loss=0.2411, pruned_loss=0.04064, over 4892.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2281, pruned_loss=0.04501, over 972310.25 frames.], batch size: 19, lr: 4.75e-04
2022-05-04 19:14:27,696 INFO [train.py:715] (4/8) Epoch 4, batch 1900, loss[loss=0.1323, simple_loss=0.2083, pruned_loss=0.02818, over 4850.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2272, pruned_loss=0.04488, over 972010.33 frames.], batch size: 30, lr: 4.75e-04
2022-05-04 19:15:08,449 INFO [train.py:715] (4/8) Epoch 4, batch 1950, loss[loss=0.1705, simple_loss=0.2365, pruned_loss=0.05227, over 4931.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2272, pruned_loss=0.04509, over 972305.50 frames.], batch size: 29, lr: 4.75e-04
2022-05-04 19:15:48,966 INFO [train.py:715] (4/8) Epoch 4, batch 2000, loss[loss=0.1434, simple_loss=0.2181, pruned_loss=0.03435, over 4925.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2278, pruned_loss=0.04536, over 972315.37 frames.], batch size: 23, lr: 4.74e-04
2022-05-04 19:16:28,965 INFO [train.py:715] (4/8) Epoch 4, batch 2050, loss[loss=0.1694, simple_loss=0.2424, pruned_loss=0.04821, over 4936.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2278, pruned_loss=0.04539, over 972493.53 frames.], batch size: 18, lr: 4.74e-04
2022-05-04 19:17:08,513 INFO [train.py:715] (4/8) Epoch 4, batch 2100, loss[loss=0.1412, simple_loss=0.2049, pruned_loss=0.03878, over 4783.00 frames.], tot_loss[loss=0.1601, simple_loss=0.2284, pruned_loss=0.04589, over 972719.12 frames.], batch size: 12, lr: 4.74e-04
2022-05-04 19:17:48,261 INFO [train.py:715] (4/8) Epoch 4, batch 2150, loss[loss=0.146, simple_loss=0.226, pruned_loss=0.03303, over 4793.00 frames.], tot_loss[loss=0.1594, simple_loss=0.2277, pruned_loss=0.04556, over 971986.71 frames.], batch size: 18, lr: 4.74e-04
2022-05-04 19:18:29,061 INFO [train.py:715] (4/8) Epoch 4, batch 2200, loss[loss=0.1613, simple_loss=0.2327, pruned_loss=0.04494, over 4896.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2264, pruned_loss=0.04469, over 972665.45 frames.], batch size: 17, lr: 4.74e-04
2022-05-04 19:19:09,440 INFO [train.py:715] (4/8) Epoch 4, batch 2250, loss[loss=0.1461, simple_loss=0.211, pruned_loss=0.04065, over 4971.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2275, pruned_loss=0.04501, over 973437.68 frames.], batch size: 31, lr: 4.74e-04
2022-05-04 19:19:48,813 INFO [train.py:715] (4/8) Epoch 4, batch 2300, loss[loss=0.151, simple_loss=0.2301, pruned_loss=0.03596, over 4811.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2278, pruned_loss=0.04542, over 973194.68 frames.], batch size: 25, lr: 4.74e-04
2022-05-04 19:20:28,745 INFO [train.py:715] (4/8) Epoch 4, batch 2350, loss[loss=0.168, simple_loss=0.2439, pruned_loss=0.04604, over 4783.00 frames.], tot_loss[loss=0.1596, simple_loss=0.228, pruned_loss=0.04559, over 973714.80 frames.], batch size: 17, lr: 4.74e-04
2022-05-04 19:21:08,833 INFO [train.py:715] (4/8) Epoch 4, batch 2400, loss[loss=0.1653, simple_loss=0.2392, pruned_loss=0.0457, over 4886.00 frames.], tot_loss[loss=0.1599, simple_loss=0.2282, pruned_loss=0.04581, over 973267.55 frames.], batch size: 22, lr: 4.74e-04
2022-05-04 19:21:48,318 INFO [train.py:715] (4/8) Epoch 4, batch 2450, loss[loss=0.1571, simple_loss=0.2273, pruned_loss=0.04343, over 4880.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2278, pruned_loss=0.04562, over 972811.41 frames.], batch size: 22, lr: 4.74e-04
2022-05-04 19:22:28,659 INFO [train.py:715] (4/8) Epoch 4, batch 2500, loss[loss=0.1412, simple_loss=0.2062, pruned_loss=0.03808, over 4842.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2275, pruned_loss=0.04514, over 973082.75 frames.], batch size: 32, lr: 4.74e-04
2022-05-04 19:23:09,574 INFO [train.py:715] (4/8) Epoch 4, batch 2550, loss[loss=0.152, simple_loss=0.2225, pruned_loss=0.04071, over 4988.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2277, pruned_loss=0.04482, over 972493.20 frames.], batch size: 14, lr: 4.74e-04
2022-05-04 19:23:49,883 INFO [train.py:715] (4/8) Epoch 4, batch 2600, loss[loss=0.1562, simple_loss=0.2241, pruned_loss=0.04411, over 4864.00 frames.], tot_loss[loss=0.1584, simple_loss=0.228, pruned_loss=0.04438, over 973086.25 frames.], batch size: 32, lr: 4.73e-04
2022-05-04 19:24:29,135 INFO [train.py:715] (4/8) Epoch 4, batch 2650, loss[loss=0.1947, simple_loss=0.2575, pruned_loss=0.06595, over 4962.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2294, pruned_loss=0.04483, over 973391.06 frames.], batch size: 35, lr: 4.73e-04
2022-05-04 19:25:09,499 INFO [train.py:715] (4/8) Epoch 4, batch 2700, loss[loss=0.131, simple_loss=0.198, pruned_loss=0.03205, over 4874.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2286, pruned_loss=0.04451, over 973213.07 frames.], batch size: 22, lr: 4.73e-04
2022-05-04 19:25:49,763 INFO [train.py:715] (4/8) Epoch 4, batch 2750, loss[loss=0.1622, simple_loss=0.2435, pruned_loss=0.04044, over 4896.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2278, pruned_loss=0.04417, over 973709.21 frames.], batch size: 19, lr: 4.73e-04
2022-05-04 19:26:29,539 INFO [train.py:715] (4/8) Epoch 4, batch 2800, loss[loss=0.1371, simple_loss=0.2149, pruned_loss=0.02963, over 4838.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2283, pruned_loss=0.04433, over 973262.60 frames.], batch size: 13, lr: 4.73e-04
2022-05-04 19:27:08,932 INFO [train.py:715] (4/8) Epoch 4, batch 2850, loss[loss=0.1278, simple_loss=0.1932, pruned_loss=0.03124, over 4692.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2279, pruned_loss=0.04463, over 973266.75 frames.], batch size: 15, lr: 4.73e-04
2022-05-04 19:27:49,244 INFO [train.py:715] (4/8) Epoch 4, batch 2900, loss[loss=0.1749, simple_loss=0.2326, pruned_loss=0.05858, over 4961.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2276, pruned_loss=0.04463, over 972720.34 frames.], batch size: 35, lr: 4.73e-04
2022-05-04 19:28:29,132 INFO [train.py:715] (4/8) Epoch 4, batch 2950, loss[loss=0.1324, simple_loss=0.204, pruned_loss=0.03043, over 4860.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2273, pruned_loss=0.04492, over 973174.67 frames.], batch size: 15, lr: 4.73e-04
2022-05-04 19:29:08,449 INFO [train.py:715] (4/8) Epoch 4, batch 3000, loss[loss=0.1335, simple_loss=0.2118, pruned_loss=0.02761, over 4870.00 frames.], tot_loss[loss=0.1589, simple_loss=0.228, pruned_loss=0.04489, over 973525.97 frames.], batch size: 20, lr: 4.73e-04
2022-05-04 19:29:08,450 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 19:29:17,943 INFO [train.py:742] (4/8) Epoch 4, validation: loss=0.1127, simple_loss=0.1984, pruned_loss=0.01346, over 914524.00 frames.
2022-05-04 19:29:57,093 INFO [train.py:715] (4/8) Epoch 4, batch 3050, loss[loss=0.1575, simple_loss=0.2239, pruned_loss=0.04558, over 4974.00 frames.], tot_loss[loss=0.1592, simple_loss=0.2282, pruned_loss=0.0451, over 972665.77 frames.], batch size: 28, lr: 4.73e-04
2022-05-04 19:30:37,134 INFO [train.py:715] (4/8) Epoch 4, batch 3100, loss[loss=0.224, simple_loss=0.2682, pruned_loss=0.08997, over 4883.00 frames.], tot_loss[loss=0.1602, simple_loss=0.2287, pruned_loss=0.04585, over 971761.44 frames.], batch size: 16, lr: 4.73e-04
2022-05-04 19:31:17,410 INFO [train.py:715] (4/8) Epoch 4, batch 3150, loss[loss=0.2243, simple_loss=0.2818, pruned_loss=0.08336, over 4871.00 frames.], tot_loss[loss=0.161, simple_loss=0.2292, pruned_loss=0.04635, over 970807.84 frames.], batch size: 16, lr: 4.73e-04
2022-05-04 19:31:57,023 INFO [train.py:715] (4/8) Epoch 4, batch 3200, loss[loss=0.175, simple_loss=0.243, pruned_loss=0.05353, over 4944.00 frames.], tot_loss[loss=0.1605, simple_loss=0.2292, pruned_loss=0.04592, over 971396.48 frames.], batch size: 21, lr: 4.72e-04
2022-05-04 19:32:36,973 INFO [train.py:715] (4/8) Epoch 4, batch 3250, loss[loss=0.1815, simple_loss=0.241, pruned_loss=0.06103, over 4959.00 frames.], tot_loss[loss=0.1602, simple_loss=0.229, pruned_loss=0.04571, over 971300.94 frames.], batch size: 35, lr: 4.72e-04
2022-05-04 19:33:16,910 INFO [train.py:715] (4/8) Epoch 4, batch 3300, loss[loss=0.1715, simple_loss=0.2234, pruned_loss=0.05983, over 4908.00 frames.], tot_loss[loss=0.1597, simple_loss=0.2287, pruned_loss=0.04541, over 970859.80 frames.], batch size: 18, lr: 4.72e-04
2022-05-04 19:33:56,289 INFO [train.py:715] (4/8) Epoch 4, batch 3350, loss[loss=0.2015, simple_loss=0.2707, pruned_loss=0.06617, over 4923.00 frames.], tot_loss[loss=0.159, simple_loss=0.2283, pruned_loss=0.04485, over 971364.61 frames.], batch size: 39, lr: 4.72e-04
2022-05-04 19:34:35,329 INFO [train.py:715] (4/8) Epoch 4, batch 3400, loss[loss=0.169, simple_loss=0.2276, pruned_loss=0.05517, over 4869.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2281, pruned_loss=0.04489, over 971996.34 frames.], batch size: 16, lr: 4.72e-04
2022-05-04 19:35:15,775 INFO [train.py:715] (4/8) Epoch 4, batch 3450, loss[loss=0.1564, simple_loss=0.2204, pruned_loss=0.04615, over 4945.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2275, pruned_loss=0.04474, over 971978.61 frames.], batch size: 35, lr: 4.72e-04
2022-05-04 19:35:55,189 INFO [train.py:715] (4/8) Epoch 4, batch 3500, loss[loss=0.1507, simple_loss=0.2251, pruned_loss=0.03816, over 4954.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2268, pruned_loss=0.04438, over 972504.71 frames.], batch size: 35, lr: 4.72e-04
2022-05-04 19:36:34,860 INFO [train.py:715] (4/8) Epoch 4, batch 3550, loss[loss=0.1803, simple_loss=0.2549, pruned_loss=0.05284, over 4983.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2269, pruned_loss=0.04407, over 972915.88 frames.], batch size: 14, lr: 4.72e-04
2022-05-04 19:37:14,696 INFO [train.py:715] (4/8) Epoch 4, batch 3600, loss[loss=0.1743, simple_loss=0.242, pruned_loss=0.05333, over 4774.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2275, pruned_loss=0.04479, over 972504.46 frames.], batch size: 17, lr: 4.72e-04
2022-05-04 19:37:54,697 INFO [train.py:715] (4/8) Epoch 4, batch 3650, loss[loss=0.1455, simple_loss=0.222, pruned_loss=0.03454, over 4869.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2278, pruned_loss=0.04458, over 973473.17 frames.], batch size: 22, lr: 4.72e-04
2022-05-04 19:38:34,068 INFO [train.py:715] (4/8) Epoch 4, batch 3700, loss[loss=0.143, simple_loss=0.2164, pruned_loss=0.03486, over 4881.00 frames.], tot_loss[loss=0.1587, simple_loss=0.228, pruned_loss=0.04473, over 973816.64 frames.], batch size: 22, lr: 4.72e-04
2022-05-04 19:39:13,349 INFO [train.py:715] (4/8) Epoch 4, batch 3750, loss[loss=0.1833, simple_loss=0.2478, pruned_loss=0.05941, over 4887.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2273, pruned_loss=0.04425, over 973059.68 frames.], batch size: 22, lr: 4.72e-04
2022-05-04 19:39:53,216 INFO [train.py:715] (4/8) Epoch 4, batch 3800, loss[loss=0.1634, simple_loss=0.226, pruned_loss=0.05041, over 4877.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2276, pruned_loss=0.04474, over 973476.55 frames.], batch size: 39, lr: 4.72e-04
2022-05-04 19:40:32,932 INFO [train.py:715] (4/8) Epoch 4, batch 3850, loss[loss=0.1728, simple_loss=0.2335, pruned_loss=0.05603, over 4838.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2273, pruned_loss=0.04419, over 973587.69 frames.], batch size: 15, lr: 4.71e-04
2022-05-04 19:41:13,115 INFO [train.py:715] (4/8) Epoch 4, batch 3900, loss[loss=0.1646, simple_loss=0.2308, pruned_loss=0.04924, over 4852.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2276, pruned_loss=0.04448, over 973811.99 frames.], batch size: 20, lr: 4.71e-04
2022-05-04 19:41:53,259 INFO [train.py:715] (4/8) Epoch 4, batch 3950, loss[loss=0.1855, simple_loss=0.2577, pruned_loss=0.05663, over 4770.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2272, pruned_loss=0.04448, over 974280.07 frames.], batch size: 18, lr: 4.71e-04
2022-05-04 19:42:33,630 INFO [train.py:715] (4/8) Epoch 4, batch 4000, loss[loss=0.1438, simple_loss=0.21, pruned_loss=0.03883, over 4778.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2269, pruned_loss=0.04432, over 973659.58 frames.], batch size: 17, lr: 4.71e-04
2022-05-04 19:43:13,664 INFO [train.py:715] (4/8) Epoch 4, batch 4050, loss[loss=0.1452, simple_loss=0.2105, pruned_loss=0.03994, over 4771.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2268, pruned_loss=0.04408, over 973088.15 frames.], batch size: 18, lr: 4.71e-04
2022-05-04 19:43:53,263 INFO [train.py:715] (4/8) Epoch 4, batch 4100, loss[loss=0.1634, simple_loss=0.2417, pruned_loss=0.04251, over 4856.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2269, pruned_loss=0.04379, over 972647.85 frames.], batch size: 20, lr: 4.71e-04
2022-05-04 19:44:33,947 INFO [train.py:715] (4/8) Epoch 4, batch 4150, loss[loss=0.1496, simple_loss=0.2206, pruned_loss=0.03933, over 4868.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2271, pruned_loss=0.04406, over 972411.06 frames.], batch size: 20, lr: 4.71e-04
2022-05-04 19:45:13,438 INFO [train.py:715] (4/8) Epoch 4, batch 4200, loss[loss=0.1464, simple_loss=0.2219, pruned_loss=0.0354, over 4873.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2275, pruned_loss=0.04422, over 973145.68 frames.], batch size: 20, lr: 4.71e-04
2022-05-04 19:45:52,908 INFO [train.py:715] (4/8) Epoch 4, batch 4250, loss[loss=0.158, simple_loss=0.2244, pruned_loss=0.04584, over 4907.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2272, pruned_loss=0.04405, over 973016.03 frames.], batch size: 19, lr: 4.71e-04
2022-05-04 19:46:33,011 INFO [train.py:715] (4/8) Epoch 4, batch 4300, loss[loss=0.1575, simple_loss=0.2381, pruned_loss=0.03846, over 4803.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2271, pruned_loss=0.04388, over 972828.60 frames.], batch size: 25, lr: 4.71e-04
2022-05-04 19:47:13,033 INFO [train.py:715] (4/8) Epoch 4, batch 4350, loss[loss=0.1648, simple_loss=0.2303, pruned_loss=0.04969, over 4967.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2277, pruned_loss=0.04437, over 972532.76 frames.], batch size: 25, lr: 4.71e-04
2022-05-04 19:47:52,119 INFO [train.py:715] (4/8) Epoch 4, batch 4400, loss[loss=0.1318, simple_loss=0.201, pruned_loss=0.03136, over 4986.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2277, pruned_loss=0.04449, over 973225.78 frames.], batch size: 31, lr: 4.71e-04
2022-05-04 19:48:31,827 INFO [train.py:715] (4/8) Epoch 4, batch 4450, loss[loss=0.1697, simple_loss=0.2395, pruned_loss=0.05, over 4767.00 frames.], tot_loss[loss=0.1573, simple_loss=0.227, pruned_loss=0.04376, over 972573.56 frames.], batch size: 17, lr: 4.70e-04
2022-05-04 19:49:12,001 INFO [train.py:715] (4/8) Epoch 4, batch 4500, loss[loss=0.1498, simple_loss=0.2184, pruned_loss=0.0406, over 4778.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2257, pruned_loss=0.04292, over 972726.93 frames.], batch size: 14, lr: 4.70e-04
2022-05-04 19:49:51,274 INFO [train.py:715] (4/8) Epoch 4, batch 4550, loss[loss=0.1777, simple_loss=0.2508, pruned_loss=0.05233, over 4810.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2254, pruned_loss=0.04253, over 973179.05 frames.], batch size: 24, lr: 4.70e-04
2022-05-04 19:50:30,674 INFO [train.py:715] (4/8) Epoch 4, batch 4600, loss[loss=0.1552, simple_loss=0.2271, pruned_loss=0.04167, over 4747.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2252, pruned_loss=0.0427, over 973069.32 frames.], batch size: 16, lr: 4.70e-04
2022-05-04 19:51:10,986 INFO [train.py:715] (4/8) Epoch 4, batch 4650, loss[loss=0.1701, simple_loss=0.2363, pruned_loss=0.05193, over 4884.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2256, pruned_loss=0.04311, over 972460.82 frames.], batch size: 19, lr: 4.70e-04
2022-05-04 19:51:51,341 INFO [train.py:715] (4/8) Epoch 4, batch 4700, loss[loss=0.1574, simple_loss=0.2295, pruned_loss=0.04264, over 4860.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2264, pruned_loss=0.04368, over 971822.91 frames.], batch size: 20, lr: 4.70e-04
2022-05-04 19:52:31,248 INFO [train.py:715] (4/8) Epoch 4, batch 4750, loss[loss=0.175, simple_loss=0.2445, pruned_loss=0.05271, over 4962.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2268, pruned_loss=0.04411, over 972419.78 frames.], batch size: 35, lr: 4.70e-04
2022-05-04 19:53:13,034 INFO [train.py:715] (4/8) Epoch 4, batch 4800, loss[loss=0.1816, simple_loss=0.2388, pruned_loss=0.06221, over 4897.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2268, pruned_loss=0.04393, over 972333.36 frames.], batch size: 19, lr: 4.70e-04
2022-05-04 19:53:53,557 INFO [train.py:715] (4/8) Epoch 4, batch 4850, loss[loss=0.1622, simple_loss=0.2441, pruned_loss=0.04014, over 4976.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2264, pruned_loss=0.04359, over 972860.78 frames.], batch size: 28, lr: 4.70e-04
2022-05-04 19:54:32,959 INFO [train.py:715] (4/8) Epoch 4, batch 4900, loss[loss=0.1733, simple_loss=0.2529, pruned_loss=0.04686, over 4809.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2257, pruned_loss=0.04279, over 972589.81 frames.], batch size: 25, lr: 4.70e-04
2022-05-04 19:55:12,348 INFO [train.py:715] (4/8) Epoch 4, batch 4950, loss[loss=0.1444, simple_loss=0.2177, pruned_loss=0.03554, over 4972.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2271, pruned_loss=0.04373, over 971998.77 frames.], batch size: 14, lr: 4.70e-04
2022-05-04 19:55:52,410 INFO [train.py:715] (4/8) Epoch 4, batch 5000, loss[loss=0.1548, simple_loss=0.2263, pruned_loss=0.04167, over 4911.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2266, pruned_loss=0.04373, over 972183.37 frames.], batch size: 17, lr: 4.70e-04
2022-05-04 19:56:32,440 INFO [train.py:715] (4/8) Epoch 4, batch 5050, loss[loss=0.1518, simple_loss=0.2159, pruned_loss=0.04386, over 4871.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2276, pruned_loss=0.04397, over 972363.16 frames.], batch size: 32, lr: 4.69e-04
2022-05-04 19:57:12,347 INFO [train.py:715] (4/8) Epoch 4, batch 5100, loss[loss=0.1574, simple_loss=0.2364, pruned_loss=0.03917, over 4803.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2274, pruned_loss=0.0437, over 972582.43 frames.], batch size: 25, lr: 4.69e-04
2022-05-04 19:57:51,519 INFO [train.py:715] (4/8) Epoch 4, batch 5150, loss[loss=0.1577, simple_loss=0.2235, pruned_loss=0.04588, over 4752.00 frames.], tot_loss[loss=0.1583, simple_loss=0.228, pruned_loss=0.04429, over 972771.95 frames.], batch size: 19, lr: 4.69e-04
2022-05-04 19:58:31,723 INFO [train.py:715] (4/8) Epoch 4, batch 5200, loss[loss=0.1371, simple_loss=0.1998, pruned_loss=0.03723, over 4649.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2273, pruned_loss=0.04426, over 972756.34 frames.], batch size: 13, lr: 4.69e-04
2022-05-04 19:59:11,083 INFO [train.py:715] (4/8) Epoch 4, batch 5250, loss[loss=0.1532, simple_loss=0.226, pruned_loss=0.04023, over 4885.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2276, pruned_loss=0.04448, over 973088.88 frames.], batch size: 22, lr: 4.69e-04
2022-05-04 19:59:50,712 INFO [train.py:715] (4/8) Epoch 4, batch 5300, loss[loss=0.2078, simple_loss=0.2599, pruned_loss=0.07784, over 4878.00 frames.], tot_loss[loss=0.158, simple_loss=0.2272, pruned_loss=0.04445, over 972985.04 frames.], batch size: 32, lr: 4.69e-04
2022-05-04 20:00:30,977 INFO [train.py:715] (4/8) Epoch 4, batch 5350, loss[loss=0.1411, simple_loss=0.2282, pruned_loss=0.02705, over 4819.00 frames.], tot_loss[loss=0.158, simple_loss=0.2271, pruned_loss=0.04443, over 972278.34 frames.], batch size: 26, lr: 4.69e-04
2022-05-04 20:01:11,127 INFO [train.py:715] (4/8) Epoch 4, batch 5400, loss[loss=0.1394, simple_loss=0.2114, pruned_loss=0.03374, over 4928.00 frames.], tot_loss[loss=0.1589, simple_loss=0.228, pruned_loss=0.04489, over 972079.05 frames.], batch size: 29, lr: 4.69e-04
2022-05-04 20:01:51,427 INFO [train.py:715] (4/8) Epoch 4, batch 5450, loss[loss=0.1538, simple_loss=0.2331, pruned_loss=0.03722, over 4922.00 frames.], tot_loss[loss=0.159, simple_loss=0.2285, pruned_loss=0.04476, over 971586.87 frames.], batch size: 29, lr: 4.69e-04
2022-05-04 20:02:30,838 INFO [train.py:715] (4/8) Epoch 4, batch 5500, loss[loss=0.1599, simple_loss=0.2359, pruned_loss=0.04196, over 4781.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2272, pruned_loss=0.04378, over 972159.67 frames.], batch size: 17, lr: 4.69e-04
2022-05-04 20:03:11,385 INFO [train.py:715] (4/8) Epoch 4, batch 5550, loss[loss=0.1448, simple_loss=0.2203, pruned_loss=0.03467, over 4950.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2276, pruned_loss=0.04405, over 971862.64 frames.], batch size: 21, lr: 4.69e-04
2022-05-04 20:03:51,125 INFO [train.py:715] (4/8) Epoch 4, batch 5600, loss[loss=0.115, simple_loss=0.1787, pruned_loss=0.0256, over 4780.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2274, pruned_loss=0.04388, over 972841.58 frames.], batch size: 12, lr: 4.69e-04
2022-05-04 20:04:31,008 INFO [train.py:715] (4/8) Epoch 4, batch 5650, loss[loss=0.1559, simple_loss=0.2178, pruned_loss=0.04704, over 4983.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2265, pruned_loss=0.04342, over 972729.49 frames.], batch size: 16, lr: 4.68e-04
2022-05-04 20:05:10,989 INFO [train.py:715] (4/8) Epoch 4, batch 5700, loss[loss=0.1652, simple_loss=0.232, pruned_loss=0.04916, over 4961.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2263, pruned_loss=0.04353, over 972687.07 frames.], batch size: 24, lr: 4.68e-04
2022-05-04 20:05:51,206 INFO [train.py:715] (4/8) Epoch 4, batch 5750, loss[loss=0.18, simple_loss=0.2462, pruned_loss=0.05689, over 4873.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2267, pruned_loss=0.04397, over 972695.35 frames.], batch size: 32, lr: 4.68e-04
2022-05-04 20:06:31,307 INFO [train.py:715] (4/8) Epoch 4, batch 5800, loss[loss=0.1917, simple_loss=0.2589, pruned_loss=0.06231, over 4925.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2268, pruned_loss=0.04397, over 972963.01 frames.], batch size: 35, lr: 4.68e-04
2022-05-04 20:07:10,960 INFO [train.py:715] (4/8) Epoch 4, batch 5850, loss[loss=0.1712, simple_loss=0.246, pruned_loss=0.04822, over 4744.00 frames.], tot_loss[loss=0.1588, simple_loss=0.2279, pruned_loss=0.04483, over 972946.51 frames.], batch size: 16, lr: 4.68e-04
2022-05-04 20:07:51,257 INFO [train.py:715] (4/8) Epoch 4, batch 5900, loss[loss=0.1401, simple_loss=0.2116, pruned_loss=0.03431, over 4772.00 frames.], tot_loss[loss=0.159, simple_loss=0.2285, pruned_loss=0.04476, over 972827.09 frames.], batch size: 17, lr: 4.68e-04
2022-05-04 20:08:30,935 INFO [train.py:715] (4/8) Epoch 4, batch 5950, loss[loss=0.1305, simple_loss=0.2064, pruned_loss=0.02735, over 4810.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2283, pruned_loss=0.04476, over 973685.42 frames.], batch size: 26, lr: 4.68e-04
2022-05-04 20:09:10,570 INFO [train.py:715] (4/8) Epoch 4, batch 6000, loss[loss=0.1457, simple_loss=0.2159, pruned_loss=0.0378, over 4928.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2288, pruned_loss=0.04493, over 973362.94 frames.], batch size: 29, lr: 4.68e-04
2022-05-04 20:09:10,571 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 20:09:20,450 INFO [train.py:742] (4/8) Epoch 4, validation: loss=0.1124, simple_loss=0.1981, pruned_loss=0.01337, over 914524.00 frames.
2022-05-04 20:10:00,565 INFO [train.py:715] (4/8) Epoch 4, batch 6050, loss[loss=0.1635, simple_loss=0.2491, pruned_loss=0.03893, over 4973.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2273, pruned_loss=0.04391, over 972209.74 frames.], batch size: 25, lr: 4.68e-04
2022-05-04 20:10:40,766 INFO [train.py:715] (4/8) Epoch 4, batch 6100, loss[loss=0.1494, simple_loss=0.2221, pruned_loss=0.03836, over 4799.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2278, pruned_loss=0.04398, over 972834.24 frames.], batch size: 14, lr: 4.68e-04
2022-05-04 20:11:21,160 INFO [train.py:715] (4/8) Epoch 4, batch 6150, loss[loss=0.1469, simple_loss=0.2192, pruned_loss=0.03728, over 4953.00 frames.], tot_loss[loss=0.1569, simple_loss=0.227, pruned_loss=0.04344, over 972302.23 frames.], batch size: 24, lr: 4.68e-04
2022-05-04 20:12:01,191 INFO [train.py:715] (4/8) Epoch 4, batch 6200, loss[loss=0.163, simple_loss=0.2378, pruned_loss=0.04416, over 4763.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2281, pruned_loss=0.04429, over 973036.49 frames.], batch size: 17, lr: 4.68e-04
2022-05-04 20:12:40,825 INFO [train.py:715] (4/8) Epoch 4, batch 6250, loss[loss=0.1701, simple_loss=0.235, pruned_loss=0.05256, over 4867.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2268, pruned_loss=0.04388, over 973151.74 frames.], batch size: 20, lr: 4.68e-04
2022-05-04 20:13:21,481 INFO [train.py:715] (4/8) Epoch 4, batch 6300, loss[loss=0.1299, simple_loss=0.2072, pruned_loss=0.02627, over 4871.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2265, pruned_loss=0.04356, over 973152.31 frames.], batch size: 20, lr: 4.67e-04
2022-05-04 20:14:00,894 INFO [train.py:715] (4/8) Epoch 4, batch 6350, loss[loss=0.1289, simple_loss=0.2122, pruned_loss=0.02283, over 4880.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2273, pruned_loss=0.04413, over 973076.81 frames.], batch size: 22, lr: 4.67e-04
2022-05-04 20:14:41,821 INFO [train.py:715] (4/8) Epoch 4, batch 6400, loss[loss=0.1422, simple_loss=0.2076, pruned_loss=0.03834, over 4821.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2268, pruned_loss=0.04404, over 972790.90 frames.], batch size: 30, lr: 4.67e-04
2022-05-04 20:15:21,559 INFO [train.py:715] (4/8) Epoch 4, batch 6450, loss[loss=0.1487, simple_loss=0.2182, pruned_loss=0.03962, over 4799.00 frames.], tot_loss[loss=0.158, simple_loss=0.2269, pruned_loss=0.04448, over 972250.79 frames.], batch size: 21, lr: 4.67e-04
2022-05-04 20:16:01,662 INFO [train.py:715] (4/8) Epoch 4, batch 6500, loss[loss=0.1678, simple_loss=0.231, pruned_loss=0.05228, over 4931.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2266, pruned_loss=0.04434, over 972424.20 frames.], batch size: 18, lr: 4.67e-04
2022-05-04 20:16:41,332 INFO [train.py:715] (4/8) Epoch 4, batch 6550, loss[loss=0.1426, simple_loss=0.2213, pruned_loss=0.03192, over 4746.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2265, pruned_loss=0.04428, over 972063.00 frames.], batch size: 19, lr: 4.67e-04
2022-05-04 20:17:20,644 INFO [train.py:715] (4/8) Epoch 4, batch 6600, loss[loss=0.1719, simple_loss=0.226, pruned_loss=0.05885, over 4774.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2258, pruned_loss=0.04372, over 972295.24 frames.], batch size: 12, lr: 4.67e-04
2022-05-04 20:18:01,341 INFO [train.py:715] (4/8) Epoch 4, batch 6650, loss[loss=0.175, simple_loss=0.244, pruned_loss=0.05299, over 4984.00 frames.], tot_loss[loss=0.1572, simple_loss=0.226, pruned_loss=0.04414, over 972671.85 frames.], batch size: 25, lr: 4.67e-04
2022-05-04 20:18:40,886 INFO [train.py:715] (4/8) Epoch 4, batch 6700, loss[loss=0.1412, simple_loss=0.213, pruned_loss=0.0347, over 4891.00 frames.], tot_loss[loss=0.1567, simple_loss=0.226, pruned_loss=0.04368, over 972332.87 frames.], batch size: 22, lr: 4.67e-04
2022-05-04 20:19:21,001 INFO [train.py:715] (4/8) Epoch 4, batch 6750, loss[loss=0.1883, simple_loss=0.2492, pruned_loss=0.06371, over 4838.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2271, pruned_loss=0.04431, over 972364.37 frames.], batch size: 30, lr: 4.67e-04
2022-05-04 20:20:00,756 INFO [train.py:715] (4/8) Epoch 4, batch 6800, loss[loss=0.1554, simple_loss=0.2219, pruned_loss=0.04446, over 4827.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2267, pruned_loss=0.04375, over 973072.77 frames.], batch size: 13, lr: 4.67e-04
2022-05-04 20:20:40,795 INFO [train.py:715] (4/8) Epoch 4, batch 6850, loss[loss=0.1612, simple_loss=0.2414, pruned_loss=0.04051, over 4747.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2279, pruned_loss=0.04438, over 972128.71 frames.], batch size: 16, lr: 4.67e-04
2022-05-04 20:21:20,096 INFO [train.py:715] (4/8) Epoch 4, batch 6900, loss[loss=0.1657, simple_loss=0.2256, pruned_loss=0.05286, over 4868.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2281, pruned_loss=0.04468, over 972396.84 frames.], batch size: 20, lr: 4.66e-04
2022-05-04 20:21:59,579 INFO [train.py:715] (4/8) Epoch 4, batch 6950, loss[loss=0.1928, simple_loss=0.2488, pruned_loss=0.0684, over 4915.00 frames.], tot_loss[loss=0.1584, simple_loss=0.228, pruned_loss=0.04443, over 972138.52 frames.], batch size: 39, lr: 4.66e-04
2022-05-04 20:22:39,323 INFO [train.py:715] (4/8) Epoch 4, batch 7000, loss[loss=0.1704, simple_loss=0.2348, pruned_loss=0.05297, over 4955.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2281, pruned_loss=0.04457, over 972204.68 frames.], batch size: 24, lr: 4.66e-04
2022-05-04 20:23:19,211 INFO [train.py:715] (4/8) Epoch 4, batch 7050, loss[loss=0.1405, simple_loss=0.2138, pruned_loss=0.03361, over 4987.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2275, pruned_loss=0.04409, over 972443.23 frames.], batch size: 28, lr: 4.66e-04
2022-05-04 20:23:58,941 INFO [train.py:715] (4/8) Epoch 4, batch 7100, loss[loss=0.168, simple_loss=0.2465, pruned_loss=0.0447, over 4980.00 frames.], tot_loss[loss=0.1585, simple_loss=0.228, pruned_loss=0.04456, over 972944.23 frames.], batch size: 24, lr: 4.66e-04
2022-05-04 20:24:39,015 INFO [train.py:715] (4/8) Epoch 4, batch 7150, loss[loss=0.1588, simple_loss=0.2347, pruned_loss=0.04144, over 4875.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2275, pruned_loss=0.04439, over 972407.45 frames.], batch size: 39, lr: 4.66e-04
2022-05-04 20:25:18,944 INFO [train.py:715] (4/8) Epoch 4, batch 7200, loss[loss=0.1468, simple_loss=0.2127, pruned_loss=0.04048, over 4924.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2276, pruned_loss=0.04459, over 971976.86 frames.], batch size: 29, lr: 4.66e-04
2022-05-04 20:25:59,098 INFO [train.py:715] (4/8) Epoch 4, batch 7250, loss[loss=0.1639, simple_loss=0.2347, pruned_loss=0.04658, over 4787.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2272, pruned_loss=0.04421, over 972205.20 frames.], batch size: 18, lr: 4.66e-04
2022-05-04 20:26:38,420 INFO [train.py:715] (4/8) Epoch 4, batch 7300, loss[loss=0.1521, simple_loss=0.2209, pruned_loss=0.04167, over 4741.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2265, pruned_loss=0.04396, over 973049.08 frames.], batch size: 16, lr: 4.66e-04
2022-05-04 20:27:18,105 INFO [train.py:715] (4/8) Epoch 4, batch 7350, loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03335, over 4878.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2258, pruned_loss=0.04327, over 972769.42 frames.], batch size: 22, lr: 4.66e-04
2022-05-04 20:27:58,075 INFO [train.py:715] (4/8) Epoch 4, batch 7400, loss[loss=0.1742, simple_loss=0.2401, pruned_loss=0.05414, over 4910.00 frames.], tot_loss[loss=0.1561, simple_loss=0.226, pruned_loss=0.04311, over 972650.84 frames.], batch size: 29, lr: 4.66e-04
2022-05-04 20:28:38,811 INFO [train.py:715] (4/8) Epoch 4, batch 7450, loss[loss=0.1246, simple_loss=0.1978, pruned_loss=0.02569, over 4816.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2251, pruned_loss=0.04286, over 972769.82 frames.], batch size: 25, lr: 4.66e-04
2022-05-04 20:29:18,221 INFO [train.py:715] (4/8) Epoch 4, batch 7500, loss[loss=0.1525, simple_loss=0.2188, pruned_loss=0.04311, over 4976.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2251, pruned_loss=0.0428, over 973301.88 frames.], batch size: 24, lr: 4.66e-04
2022-05-04 20:29:58,243 INFO [train.py:715] (4/8) Epoch 4, batch 7550, loss[loss=0.1444, simple_loss=0.2181, pruned_loss=0.03539, over 4906.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2256, pruned_loss=0.04304, over 973369.53 frames.], batch size: 17, lr: 4.65e-04
2022-05-04 20:30:38,895 INFO [train.py:715] (4/8) Epoch 4, batch 7600, loss[loss=0.1429, simple_loss=0.2124, pruned_loss=0.03671, over 4797.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2261, pruned_loss=0.04259, over 973368.35 frames.], batch size: 14, lr: 4.65e-04
2022-05-04 20:31:18,408 INFO [train.py:715] (4/8) Epoch 4, batch 7650, loss[loss=0.1777, simple_loss=0.2395, pruned_loss=0.05798, over 4902.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2265, pruned_loss=0.04282, over 973346.52 frames.], batch size: 39, lr: 4.65e-04
2022-05-04 20:31:58,070 INFO [train.py:715] (4/8) Epoch 4, batch 7700, loss[loss=0.1862, simple_loss=0.246, pruned_loss=0.06323, over 4855.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2271, pruned_loss=0.0436, over 973239.54 frames.], batch size: 30, lr: 4.65e-04
2022-05-04 20:32:38,169 INFO [train.py:715] (4/8) Epoch 4, batch 7750, loss[loss=0.1695, simple_loss=0.24, pruned_loss=0.04949, over 4843.00 frames.], tot_loss[loss=0.157, simple_loss=0.227, pruned_loss=0.0435, over 973224.82 frames.], batch size: 15, lr: 4.65e-04
2022-05-04 20:33:18,312 INFO [train.py:715] (4/8) Epoch 4, batch 7800, loss[loss=0.1861, simple_loss=0.2504, pruned_loss=0.06086, over 4848.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2267, pruned_loss=0.04349, over 972810.49 frames.], batch size: 30, lr: 4.65e-04
2022-05-04 20:33:57,309 INFO [train.py:715] (4/8) Epoch 4, batch 7850, loss[loss=0.1456, simple_loss=0.2118, pruned_loss=0.03965, over 4866.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2264, pruned_loss=0.04327, over 973203.24 frames.], batch size: 32, lr: 4.65e-04
2022-05-04 20:34:36,905 INFO [train.py:715] (4/8) Epoch 4, batch 7900, loss[loss=0.1391, simple_loss=0.2084, pruned_loss=0.03495, over 4873.00 frames.], tot_loss[loss=0.157, simple_loss=0.2266, pruned_loss=0.0437, over 972686.78 frames.], batch size: 16, lr: 4.65e-04
2022-05-04 20:35:16,766 INFO [train.py:715] (4/8) Epoch 4, batch 7950, loss[loss=0.1641, simple_loss=0.2265, pruned_loss=0.05088, over 4987.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2263, pruned_loss=0.04328, over 973415.79 frames.], batch size: 27, lr: 4.65e-04
2022-05-04 20:35:56,346 INFO [train.py:715] (4/8) Epoch 4, batch 8000, loss[loss=0.1842, simple_loss=0.2388, pruned_loss=0.06482, over 4951.00 frames.], tot_loss[loss=0.1567, simple_loss=0.226, pruned_loss=0.04367, over 973512.03 frames.], batch size: 15, lr: 4.65e-04
2022-05-04 20:36:36,316 INFO [train.py:715] (4/8) Epoch 4, batch 8050, loss[loss=0.1412, simple_loss=0.2231, pruned_loss=0.02962, over 4871.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2264, pruned_loss=0.04412, over 972966.98 frames.], batch size: 22, lr: 4.65e-04
2022-05-04 20:37:16,267 INFO [train.py:715] (4/8) Epoch 4, batch 8100, loss[loss=0.1602, simple_loss=0.2353, pruned_loss=0.04255, over 4766.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2265, pruned_loss=0.04399, over 972588.62 frames.], batch size: 19, lr: 4.65e-04
2022-05-04 20:37:56,506 INFO [train.py:715] (4/8) Epoch 4, batch 8150, loss[loss=0.1333, simple_loss=0.2061, pruned_loss=0.03029, over 4812.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2269, pruned_loss=0.04421, over 972585.82 frames.], batch size: 25, lr: 4.65e-04
2022-05-04 20:38:35,992 INFO [train.py:715] (4/8) Epoch 4, batch 8200, loss[loss=0.1662, simple_loss=0.2267, pruned_loss=0.05282, over 4948.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2267, pruned_loss=0.04412, over 973034.77 frames.], batch size: 39, lr: 4.64e-04
2022-05-04 20:39:15,725 INFO [train.py:715] (4/8) Epoch 4, batch 8250, loss[loss=0.1625, simple_loss=0.2357, pruned_loss=0.04465, over 4747.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2269, pruned_loss=0.0446, over 972549.68 frames.], batch size: 19, lr: 4.64e-04
2022-05-04 20:39:55,876 INFO [train.py:715] (4/8) Epoch 4, batch 8300, loss[loss=0.1333, simple_loss=0.2153, pruned_loss=0.02567, over 4953.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2275, pruned_loss=0.04489, over 973504.12 frames.], batch size: 21, lr: 4.64e-04
2022-05-04 20:40:35,314 INFO [train.py:715] (4/8) Epoch 4, batch 8350, loss[loss=0.1421, simple_loss=0.2054, pruned_loss=0.03938, over 4772.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2285, pruned_loss=0.04522, over 972878.64 frames.], batch size: 14, lr: 4.64e-04
2022-05-04 20:41:15,403 INFO [train.py:715] (4/8) Epoch 4, batch 8400, loss[loss=0.1734, simple_loss=0.2295, pruned_loss=0.05871, over 4848.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2285, pruned_loss=0.04505, over 973782.80 frames.], batch size: 30, lr: 4.64e-04
2022-05-04 20:41:55,744 INFO [train.py:715] (4/8) Epoch 4, batch 8450, loss[loss=0.169, simple_loss=0.2375, pruned_loss=0.05021, over 4930.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2272, pruned_loss=0.04457, over 972544.93 frames.], batch size: 21, lr: 4.64e-04
2022-05-04 20:42:35,851 INFO [train.py:715] (4/8) Epoch 4, batch 8500, loss[loss=0.1714, simple_loss=0.2368, pruned_loss=0.05301, over 4848.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2272, pruned_loss=0.04464, over 973395.43 frames.], batch size: 13, lr: 4.64e-04
2022-05-04 20:43:15,261 INFO [train.py:715] (4/8) Epoch 4, batch 8550, loss[loss=0.1451, simple_loss=0.2132, pruned_loss=0.03846, over 4911.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2271, pruned_loss=0.04474, over 973525.00 frames.], batch size: 17, lr: 4.64e-04
2022-05-04 20:43:55,080 INFO [train.py:715] (4/8) Epoch 4, batch 8600, loss[loss=0.1347, simple_loss=0.2093, pruned_loss=0.03007, over 4770.00 frames.], tot_loss[loss=0.1584, simple_loss=0.227, pruned_loss=0.04493, over 973774.45 frames.], batch size: 17, lr: 4.64e-04
2022-05-04 20:44:35,239 INFO [train.py:715] (4/8) Epoch 4, batch 8650, loss[loss=0.165, simple_loss=0.2352, pruned_loss=0.04745, over 4894.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2266, pruned_loss=0.04431, over 972938.95 frames.], batch size: 19, lr: 4.64e-04
2022-05-04 20:45:14,869 INFO [train.py:715] (4/8) Epoch 4, batch 8700, loss[loss=0.1451, simple_loss=0.2143, pruned_loss=0.03799, over 4885.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2265, pruned_loss=0.04441, over 972530.87 frames.], batch size: 22, lr: 4.64e-04
2022-05-04 20:45:55,167 INFO [train.py:715] (4/8) Epoch 4, batch 8750, loss[loss=0.1283, simple_loss=0.2051, pruned_loss=0.02579, over 4775.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2263, pruned_loss=0.04408, over 971930.85 frames.], batch size: 18, lr: 4.64e-04
2022-05-04 20:46:35,396 INFO [train.py:715] (4/8) Epoch 4, batch 8800, loss[loss=0.1506, simple_loss=0.2205, pruned_loss=0.04032, over 4900.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2259, pruned_loss=0.04371, over 972552.48 frames.], batch size: 19, lr: 4.63e-04
2022-05-04 20:47:15,432 INFO [train.py:715] (4/8) Epoch 4, batch 8850, loss[loss=0.2031, simple_loss=0.2612, pruned_loss=0.07256, over 4970.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2267, pruned_loss=0.04387, over 971845.78 frames.], batch size: 15, lr: 4.63e-04
2022-05-04 20:47:55,128 INFO [train.py:715] (4/8) Epoch 4, batch 8900, loss[loss=0.1548, simple_loss=0.2197, pruned_loss=0.04492, over 4756.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2266, pruned_loss=0.04427, over 971392.90 frames.], batch size: 12, lr: 4.63e-04
2022-05-04 20:48:34,760 INFO [train.py:715] (4/8) Epoch 4, batch 8950, loss[loss=0.1784, simple_loss=0.2438, pruned_loss=0.05649, over 4948.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2271, pruned_loss=0.044, over 971654.49 frames.], batch size: 35, lr: 4.63e-04
2022-05-04 20:49:15,024 INFO [train.py:715] (4/8) Epoch 4, batch 9000, loss[loss=0.1585, simple_loss=0.235, pruned_loss=0.04102, over 4757.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2273, pruned_loss=0.04422, over 971695.42 frames.], batch size: 19, lr: 4.63e-04
2022-05-04 20:49:15,025 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 20:49:24,975 INFO [train.py:742] (4/8) Epoch 4, validation: loss=0.1123, simple_loss=0.1979, pruned_loss=0.01336, over 914524.00 frames.
2022-05-04 20:50:05,302 INFO [train.py:715] (4/8) Epoch 4, batch 9050, loss[loss=0.1604, simple_loss=0.2255, pruned_loss=0.04761, over 4964.00 frames.], tot_loss[loss=0.1595, simple_loss=0.2289, pruned_loss=0.04503, over 971847.10 frames.], batch size: 24, lr: 4.63e-04
2022-05-04 20:50:45,312 INFO [train.py:715] (4/8) Epoch 4, batch 9100, loss[loss=0.1312, simple_loss=0.2093, pruned_loss=0.02656, over 4980.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2282, pruned_loss=0.0441, over 971826.63 frames.], batch size: 15, lr: 4.63e-04
2022-05-04 20:51:24,709 INFO [train.py:715] (4/8) Epoch 4, batch 9150, loss[loss=0.1668, simple_loss=0.2302, pruned_loss=0.0517, over 4955.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2274, pruned_loss=0.04402, over 971757.77 frames.], batch size: 15, lr: 4.63e-04
2022-05-04 20:52:04,886 INFO [train.py:715] (4/8) Epoch 4, batch 9200, loss[loss=0.1479, simple_loss=0.2261, pruned_loss=0.03484, over 4968.00 frames.], tot_loss[loss=0.158, simple_loss=0.2275, pruned_loss=0.04421, over 972522.44 frames.], batch size: 35, lr: 4.63e-04
2022-05-04 20:52:45,290 INFO [train.py:715] (4/8) Epoch 4, batch 9250, loss[loss=0.1331, simple_loss=0.2036, pruned_loss=0.03131, over 4934.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2272, pruned_loss=0.04394, over 970882.11 frames.], batch size: 21, lr: 4.63e-04
2022-05-04 20:53:24,537 INFO [train.py:715] (4/8) Epoch 4, batch 9300, loss[loss=0.1758, simple_loss=0.2411, pruned_loss=0.05528, over 4825.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2274, pruned_loss=0.04462, over 971267.04 frames.], batch size: 15, lr: 4.63e-04
2022-05-04 20:54:04,527 INFO [train.py:715] (4/8) Epoch 4, batch 9350, loss[loss=0.1529, simple_loss=0.2203, pruned_loss=0.04277, over 4784.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2272, pruned_loss=0.04408, over 971376.65 frames.], batch size: 14, lr: 4.63e-04
2022-05-04 20:54:44,470 INFO [train.py:715] (4/8) Epoch 4, batch 9400, loss[loss=0.1629, simple_loss=0.2293, pruned_loss=0.04827, over 4639.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2265, pruned_loss=0.04406, over 971587.94 frames.], batch size: 13, lr: 4.63e-04
2022-05-04 20:55:24,002 INFO [train.py:715] (4/8) Epoch 4, batch 9450, loss[loss=0.1537, simple_loss=0.2131, pruned_loss=0.04714, over 4980.00 frames.], tot_loss[loss=0.158, simple_loss=0.2272, pruned_loss=0.04445, over 971576.46 frames.], batch size: 35, lr: 4.62e-04
2022-05-04 20:56:04,094 INFO [train.py:715] (4/8) Epoch 4, batch 9500, loss[loss=0.1386, simple_loss=0.2075, pruned_loss=0.0349, over 4846.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2267, pruned_loss=0.04407, over 971857.41 frames.], batch size: 13, lr: 4.62e-04
2022-05-04 20:56:44,149 INFO [train.py:715] (4/8) Epoch 4, batch 9550, loss[loss=0.1295, simple_loss=0.2054, pruned_loss=0.02675, over 4797.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2276, pruned_loss=0.04455, over 972459.56 frames.], batch size: 21, lr: 4.62e-04
2022-05-04 20:57:24,667 INFO [train.py:715] (4/8) Epoch 4, batch 9600, loss[loss=0.1451, simple_loss=0.213, pruned_loss=0.03863, over 4983.00 frames.], tot_loss[loss=0.159, simple_loss=0.2279, pruned_loss=0.04507, over 972044.84 frames.], batch size: 33, lr: 4.62e-04
2022-05-04 20:58:04,093 INFO [train.py:715] (4/8) Epoch 4, batch 9650, loss[loss=0.1382, simple_loss=0.1969, pruned_loss=0.03978, over 4816.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2275, pruned_loss=0.04454, over 972765.02 frames.], batch size: 12, lr: 4.62e-04
2022-05-04 20:58:44,656 INFO [train.py:715] (4/8) Epoch 4, batch 9700, loss[loss=0.1599, simple_loss=0.2171, pruned_loss=0.0513, over 4983.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2269, pruned_loss=0.04403, over 971786.80 frames.], batch size: 26, lr: 4.62e-04
2022-05-04 20:59:25,196 INFO [train.py:715] (4/8) Epoch 4, batch 9750, loss[loss=0.1584, simple_loss=0.237, pruned_loss=0.03986, over 4869.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2259, pruned_loss=0.04319, over 972008.65 frames.], batch size: 16, lr: 4.62e-04
2022-05-04 21:00:04,727 INFO [train.py:715] (4/8) Epoch 4, batch 9800, loss[loss=0.1609, simple_loss=0.2315, pruned_loss=0.04517, over 4810.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2263, pruned_loss=0.04353, over 971169.41 frames.], batch size: 12, lr: 4.62e-04
2022-05-04 21:00:43,863 INFO [train.py:715] (4/8) Epoch 4, batch 9850, loss[loss=0.1691, simple_loss=0.2401, pruned_loss=0.04899, over 4986.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2264, pruned_loss=0.04351, over 971364.62 frames.], batch size: 15, lr: 4.62e-04
2022-05-04 21:01:23,905 INFO [train.py:715] (4/8) Epoch 4, batch 9900, loss[loss=0.145, simple_loss=0.2114, pruned_loss=0.03929, over 4880.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2267, pruned_loss=0.04387, over 972246.66 frames.], batch size: 32, lr: 4.62e-04
2022-05-04 21:02:03,378 INFO [train.py:715] (4/8) Epoch 4, batch 9950, loss[loss=0.1825, simple_loss=0.2519, pruned_loss=0.05649, over 4773.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2274, pruned_loss=0.04393, over 972179.28 frames.], batch size: 17, lr: 4.62e-04
2022-05-04 21:02:42,768 INFO [train.py:715] (4/8) Epoch 4, batch 10000, loss[loss=0.1341, simple_loss=0.2177, pruned_loss=0.02524, over 4971.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2279, pruned_loss=0.04418, over 972033.58 frames.], batch size: 14, lr: 4.62e-04
2022-05-04 21:03:22,514 INFO [train.py:715] (4/8) Epoch 4, batch 10050, loss[loss=0.2306, simple_loss=0.308, pruned_loss=0.07657, over 4799.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2276, pruned_loss=0.04435, over 971188.30 frames.], batch size: 24, lr: 4.62e-04
2022-05-04 21:04:02,313 INFO [train.py:715] (4/8) Epoch 4, batch 10100, loss[loss=0.1584, simple_loss=0.225, pruned_loss=0.04594, over 4841.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2265, pruned_loss=0.04366, over 971530.84 frames.], batch size: 13, lr: 4.61e-04
2022-05-04 21:04:41,555 INFO [train.py:715] (4/8) Epoch 4, batch 10150, loss[loss=0.1437, simple_loss=0.2291, pruned_loss=0.02912, over 4806.00 frames.], tot_loss[loss=0.1561, simple_loss=0.226, pruned_loss=0.04309, over 972288.16 frames.], batch size: 25, lr: 4.61e-04
2022-05-04 21:05:21,475 INFO [train.py:715] (4/8) Epoch 4, batch 10200, loss[loss=0.1661, simple_loss=0.2331, pruned_loss=0.04959, over 4950.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2262, pruned_loss=0.04318, over 972988.12 frames.], batch size: 23, lr: 4.61e-04
2022-05-04 21:06:02,062 INFO [train.py:715] (4/8) Epoch 4, batch 10250, loss[loss=0.1625, simple_loss=0.2375, pruned_loss=0.04377, over 4892.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2272, pruned_loss=0.04368, over 973749.29 frames.], batch size: 19, lr: 4.61e-04
2022-05-04 21:06:41,846 INFO [train.py:715] (4/8) Epoch 4, batch 10300, loss[loss=0.1409, simple_loss=0.2191, pruned_loss=0.03141, over 4976.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2275, pruned_loss=0.04398, over 973615.30 frames.], batch size: 24, lr: 4.61e-04
2022-05-04 21:07:21,505 INFO [train.py:715] (4/8) Epoch 4, batch 10350, loss[loss=0.176, simple_loss=0.2442, pruned_loss=0.05385, over 4827.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2273, pruned_loss=0.04408, over 973064.40 frames.], batch size: 13, lr: 4.61e-04
2022-05-04 21:08:01,704 INFO [train.py:715] (4/8) Epoch 4, batch 10400, loss[loss=0.1776, simple_loss=0.2487, pruned_loss=0.05325, over 4741.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2275, pruned_loss=0.04407, over 973053.37 frames.], batch size: 16, lr: 4.61e-04
2022-05-04 21:08:42,279 INFO [train.py:715] (4/8) Epoch 4, batch 10450, loss[loss=0.1373, simple_loss=0.1965, pruned_loss=0.03904, over 4801.00 frames.], tot_loss[loss=0.158, simple_loss=0.2281, pruned_loss=0.04397, over 972738.13 frames.], batch size: 12, lr: 4.61e-04
2022-05-04 21:09:21,890 INFO [train.py:715] (4/8) Epoch 4, batch 10500, loss[loss=0.1734, simple_loss=0.2377, pruned_loss=0.05455, over 4955.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2273, pruned_loss=0.04358, over 972780.17 frames.], batch size: 35, lr: 4.61e-04
2022-05-04 21:10:02,143 INFO [train.py:715] (4/8) Epoch 4, batch 10550, loss[loss=0.148, simple_loss=0.2195, pruned_loss=0.03826, over 4830.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2263, pruned_loss=0.04328, over 972155.19 frames.], batch size: 26, lr: 4.61e-04
2022-05-04 21:10:42,492 INFO [train.py:715] (4/8) Epoch 4, batch 10600, loss[loss=0.1505, simple_loss=0.2138, pruned_loss=0.04357, over 4816.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2264, pruned_loss=0.04305, over 972679.49 frames.], batch size: 21, lr: 4.61e-04
2022-05-04 21:11:22,293 INFO [train.py:715] (4/8) Epoch 4, batch 10650, loss[loss=0.1645, simple_loss=0.2288, pruned_loss=0.05006, over 4836.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2261, pruned_loss=0.04337, over 972238.37 frames.], batch size: 15, lr: 4.61e-04
2022-05-04 21:12:02,339 INFO [train.py:715] (4/8) Epoch 4, batch 10700, loss[loss=0.1488, simple_loss=0.2156, pruned_loss=0.041, over 4805.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2274, pruned_loss=0.04411, over 972299.18 frames.], batch size: 21, lr: 4.61e-04
2022-05-04 21:12:42,038 INFO [train.py:715] (4/8) Epoch 4, batch 10750, loss[loss=0.1694, simple_loss=0.2482, pruned_loss=0.04531, over 4813.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2282, pruned_loss=0.04443, over 972383.72 frames.], batch size: 21, lr: 4.60e-04
2022-05-04 21:13:22,453 INFO [train.py:715] (4/8) Epoch 4, batch 10800, loss[loss=0.1299, simple_loss=0.2121, pruned_loss=0.02382, over 4971.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2272, pruned_loss=0.04426, over 972460.10 frames.], batch size: 28, lr: 4.60e-04
2022-05-04 21:14:01,772 INFO [train.py:715] (4/8) Epoch 4, batch 10850, loss[loss=0.1487, simple_loss=0.2235, pruned_loss=0.03693, over 4857.00 frames.], tot_loss[loss=0.157, simple_loss=0.2262, pruned_loss=0.04386, over 972080.02 frames.], batch size: 20, lr: 4.60e-04
2022-05-04 21:14:41,704 INFO [train.py:715] (4/8) Epoch 4, batch 10900, loss[loss=0.1728, simple_loss=0.2442, pruned_loss=0.05074, over 4759.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2257, pruned_loss=0.04328, over 971615.87 frames.], batch size: 16, lr: 4.60e-04
2022-05-04 21:15:22,021 INFO [train.py:715] (4/8) Epoch 4, batch 10950, loss[loss=0.1681, simple_loss=0.2424, pruned_loss=0.0469, over 4979.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2264, pruned_loss=0.04342, over 971541.80 frames.], batch size: 28, lr: 4.60e-04
2022-05-04 21:16:01,657 INFO [train.py:715] (4/8) Epoch 4, batch 11000, loss[loss=0.1119, simple_loss=0.1811, pruned_loss=0.0213, over 4982.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2263, pruned_loss=0.04364, over 971966.58 frames.], batch size: 14, lr: 4.60e-04
2022-05-04 21:16:44,070 INFO [train.py:715] (4/8) Epoch 4, batch 11050, loss[loss=0.1469, simple_loss=0.217, pruned_loss=0.03839, over 4924.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2269, pruned_loss=0.04407, over 971874.95 frames.], batch size: 29, lr: 4.60e-04
2022-05-04 21:17:24,550 INFO [train.py:715] (4/8) Epoch 4, batch 11100, loss[loss=0.1886, simple_loss=0.2443, pruned_loss=0.06646, over 4963.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2253, pruned_loss=0.04327, over 971310.41 frames.], batch size: 15, lr: 4.60e-04
2022-05-04 21:18:07,347 INFO [train.py:715] (4/8) Epoch 4, batch 11150, loss[loss=0.1626, simple_loss=0.225, pruned_loss=0.05007, over 4904.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2254, pruned_loss=0.04305, over 971494.11 frames.], batch size: 17, lr: 4.60e-04
2022-05-04 21:18:49,570 INFO [train.py:715] (4/8) Epoch 4, batch 11200, loss[loss=0.1447, simple_loss=0.2194, pruned_loss=0.03503, over 4882.00 frames.], tot_loss[loss=0.1566, simple_loss=0.226, pruned_loss=0.04359, over 971353.65 frames.], batch size: 22, lr: 4.60e-04
2022-05-04 21:19:29,976 INFO [train.py:715] (4/8) Epoch 4, batch 11250, loss[loss=0.1591, simple_loss=0.2332, pruned_loss=0.04249, over 4859.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2257, pruned_loss=0.04305, over 971473.57 frames.], batch size: 22, lr: 4.60e-04
2022-05-04 21:20:12,900 INFO [train.py:715] (4/8) Epoch 4, batch 11300, loss[loss=0.167, simple_loss=0.2385, pruned_loss=0.04776, over 4798.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2253, pruned_loss=0.04291, over 971701.70 frames.], batch size: 21, lr: 4.60e-04
2022-05-04 21:20:52,357 INFO [train.py:715] (4/8) Epoch 4, batch 11350, loss[loss=0.1587, simple_loss=0.224, pruned_loss=0.0467, over 4848.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2252, pruned_loss=0.04259, over 972029.01 frames.], batch size: 30, lr: 4.60e-04
2022-05-04 21:21:31,874 INFO [train.py:715] (4/8) Epoch 4, batch 11400, loss[loss=0.1691, simple_loss=0.2392, pruned_loss=0.04954, over 4823.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2252, pruned_loss=0.04285, over 971433.23 frames.], batch size: 25, lr: 4.59e-04
2022-05-04 21:22:11,698 INFO [train.py:715] (4/8) Epoch 4, batch 11450, loss[loss=0.1429, simple_loss=0.2179, pruned_loss=0.03399, over 4837.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2251, pruned_loss=0.0427, over 971556.58 frames.], batch size: 15, lr: 4.59e-04
2022-05-04 21:22:51,363 INFO [train.py:715] (4/8) Epoch 4, batch 11500, loss[loss=0.1161, simple_loss=0.1815, pruned_loss=0.02537, over 4736.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2247, pruned_loss=0.04271, over 971652.21 frames.], batch size: 12, lr: 4.59e-04
2022-05-04 21:23:30,602 INFO [train.py:715] (4/8) Epoch 4, batch 11550, loss[loss=0.1395, simple_loss=0.2156, pruned_loss=0.03168, over 4751.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2249, pruned_loss=0.04313, over 971275.76 frames.], batch size: 16, lr: 4.59e-04
2022-05-04 21:24:09,869 INFO [train.py:715] (4/8) Epoch 4, batch 11600, loss[loss=0.1552, simple_loss=0.2263, pruned_loss=0.04201, over 4820.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2262, pruned_loss=0.0436, over 971861.60 frames.], batch size: 25, lr: 4.59e-04
2022-05-04 21:24:50,382 INFO [train.py:715] (4/8) Epoch 4, batch 11650, loss[loss=0.1522, simple_loss=0.2211, pruned_loss=0.04168, over 4900.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2258, pruned_loss=0.04333, over 971763.58 frames.], batch size: 17, lr: 4.59e-04
2022-05-04 21:25:30,283 INFO [train.py:715] (4/8) Epoch 4, batch 11700, loss[loss=0.1707, simple_loss=0.2405, pruned_loss=0.05043, over 4969.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2262, pruned_loss=0.04383, over 970925.05 frames.], batch size: 24, lr: 4.59e-04
2022-05-04 21:26:10,254 INFO [train.py:715] (4/8) Epoch 4, batch 11750, loss[loss=0.1742, simple_loss=0.2615, pruned_loss=0.04341, over 4765.00 frames.], tot_loss[loss=0.1566, simple_loss=0.226, pruned_loss=0.04365, over 970720.00 frames.], batch size: 16, lr: 4.59e-04
2022-05-04 21:26:50,002 INFO [train.py:715] (4/8) Epoch 4, batch 11800, loss[loss=0.16, simple_loss=0.2381, pruned_loss=0.04098, over 4804.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2259, pruned_loss=0.04353, over 971630.82 frames.], batch size: 21, lr: 4.59e-04
2022-05-04 21:27:30,283 INFO [train.py:715] (4/8) Epoch 4, batch 11850, loss[loss=0.1445, simple_loss=0.2103, pruned_loss=0.03939, over 4731.00 frames.], tot_loss[loss=0.156, simple_loss=0.2253, pruned_loss=0.04338, over 972328.43 frames.], batch size: 16, lr: 4.59e-04
2022-05-04 21:28:09,541 INFO [train.py:715] (4/8) Epoch 4, batch 11900, loss[loss=0.1674, simple_loss=0.2368, pruned_loss=0.04901, over 4872.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2259, pruned_loss=0.04367, over 972660.31 frames.], batch size: 16, lr: 4.59e-04
2022-05-04 21:28:49,320 INFO [train.py:715] (4/8) Epoch 4, batch 11950, loss[loss=0.1873, simple_loss=0.2498, pruned_loss=0.0624, over 4789.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2259, pruned_loss=0.04368, over 972561.64 frames.], batch size: 14, lr: 4.59e-04
2022-05-04 21:29:29,774 INFO [train.py:715] (4/8) Epoch 4, batch 12000, loss[loss=0.1615, simple_loss=0.2371, pruned_loss=0.04292, over 4880.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2261, pruned_loss=0.04374, over 972933.32 frames.], batch size: 22, lr: 4.59e-04
2022-05-04 21:29:29,775 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 21:29:49,525 INFO [train.py:742] (4/8) Epoch 4, validation: loss=0.1122, simple_loss=0.198, pruned_loss=0.01324, over 914524.00 frames.
2022-05-04 21:30:30,060 INFO [train.py:715] (4/8) Epoch 4, batch 12050, loss[loss=0.1503, simple_loss=0.2156, pruned_loss=0.04247, over 4849.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2254, pruned_loss=0.04309, over 972010.54 frames.], batch size: 32, lr: 4.58e-04
2022-05-04 21:31:09,877 INFO [train.py:715] (4/8) Epoch 4, batch 12100, loss[loss=0.1767, simple_loss=0.2472, pruned_loss=0.05307, over 4909.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2262, pruned_loss=0.04357, over 972175.37 frames.], batch size: 19, lr: 4.58e-04
2022-05-04 21:31:50,048 INFO [train.py:715] (4/8) Epoch 4, batch 12150, loss[loss=0.1556, simple_loss=0.2256, pruned_loss=0.0428, over 4962.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2266, pruned_loss=0.04399, over 971538.36 frames.], batch size: 24, lr: 4.58e-04
2022-05-04 21:32:30,093 INFO [train.py:715] (4/8) Epoch 4, batch 12200, loss[loss=0.1527, simple_loss=0.2234, pruned_loss=0.04103, over 4877.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2269, pruned_loss=0.04433, over 971264.21 frames.], batch size: 32, lr: 4.58e-04
2022-05-04 21:33:10,432 INFO [train.py:715] (4/8) Epoch 4, batch 12250, loss[loss=0.1274, simple_loss=0.203, pruned_loss=0.02591, over 4701.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2267, pruned_loss=0.0441, over 970284.24 frames.], batch size: 15, lr: 4.58e-04
2022-05-04 21:33:49,414 INFO [train.py:715] (4/8) Epoch 4, batch 12300, loss[loss=0.1477, simple_loss=0.2232, pruned_loss=0.03614, over 4967.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2261, pruned_loss=0.04374, over 971314.21 frames.], batch size: 24, lr: 4.58e-04
2022-05-04 21:34:29,433 INFO [train.py:715] (4/8) Epoch 4, batch 12350, loss[loss=0.1424, simple_loss=0.2128, pruned_loss=0.03598, over 4822.00 frames.], tot_loss[loss=0.1564, simple_loss=0.226, pruned_loss=0.04339, over 971490.10 frames.], batch size: 26, lr: 4.58e-04
2022-05-04 21:35:10,020 INFO [train.py:715] (4/8) Epoch 4, batch 12400, loss[loss=0.1879, simple_loss=0.2549, pruned_loss=0.06047, over 4801.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2249, pruned_loss=0.04315, over 971554.63 frames.], batch size: 21, lr: 4.58e-04
2022-05-04 21:35:49,230 INFO [train.py:715] (4/8) Epoch 4, batch 12450, loss[loss=0.1509, simple_loss=0.2298, pruned_loss=0.03604, over 4985.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2254, pruned_loss=0.04316, over 971939.03 frames.], batch size: 25, lr: 4.58e-04
2022-05-04 21:36:29,195 INFO [train.py:715] (4/8) Epoch 4, batch 12500, loss[loss=0.1713, simple_loss=0.2376, pruned_loss=0.0525, over 4798.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2254, pruned_loss=0.0431, over 971749.68 frames.], batch size: 13, lr: 4.58e-04
2022-05-04 21:37:08,753 INFO [train.py:715] (4/8) Epoch 4, batch 12550, loss[loss=0.1445, simple_loss=0.2141, pruned_loss=0.03748, over 4739.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2245, pruned_loss=0.04255, over 971471.13 frames.], batch size: 12, lr: 4.58e-04
2022-05-04 21:37:48,537 INFO [train.py:715] (4/8) Epoch 4, batch 12600, loss[loss=0.2216, simple_loss=0.2696, pruned_loss=0.08684, over 4856.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2244, pruned_loss=0.04236, over 971623.48 frames.], batch size: 13, lr: 4.58e-04
2022-05-04 21:38:27,426 INFO [train.py:715] (4/8) Epoch 4, batch 12650, loss[loss=0.1256, simple_loss=0.1902, pruned_loss=0.03047, over 4719.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2239, pruned_loss=0.04228, over 971056.60 frames.], batch size: 12, lr: 4.58e-04
2022-05-04 21:39:07,268 INFO [train.py:715] (4/8) Epoch 4, batch 12700, loss[loss=0.1645, simple_loss=0.2403, pruned_loss=0.04434, over 4832.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2248, pruned_loss=0.04248, over 972064.77 frames.], batch size: 30, lr: 4.58e-04
2022-05-04 21:39:47,351 INFO [train.py:715] (4/8) Epoch 4, batch 12750, loss[loss=0.1454, simple_loss=0.2141, pruned_loss=0.03833, over 4928.00 frames.], tot_loss[loss=0.155, simple_loss=0.2248, pruned_loss=0.04262, over 972372.65 frames.], batch size: 23, lr: 4.57e-04
2022-05-04 21:40:29,595 INFO [train.py:715] (4/8) Epoch 4, batch 12800, loss[loss=0.1658, simple_loss=0.2328, pruned_loss=0.04943, over 4858.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2245, pruned_loss=0.04242, over 972505.74 frames.], batch size: 20, lr: 4.57e-04
2022-05-04 21:41:08,985 INFO [train.py:715] (4/8) Epoch 4, batch 12850, loss[loss=0.1467, simple_loss=0.2209, pruned_loss=0.03627, over 4756.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2249, pruned_loss=0.04279, over 972283.17 frames.], batch size: 16, lr: 4.57e-04
2022-05-04 21:41:49,118 INFO [train.py:715] (4/8) Epoch 4, batch 12900, loss[loss=0.1524, simple_loss=0.2191, pruned_loss=0.0429, over 4881.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2244, pruned_loss=0.04291, over 972748.89 frames.], batch size: 32, lr: 4.57e-04
2022-05-04 21:42:29,043 INFO [train.py:715] (4/8) Epoch 4, batch 12950, loss[loss=0.1606, simple_loss=0.2351, pruned_loss=0.04308, over 4967.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2249, pruned_loss=0.04273, over 972995.33 frames.], batch size: 24, lr: 4.57e-04
2022-05-04 21:43:07,909 INFO [train.py:715] (4/8) Epoch 4, batch 13000, loss[loss=0.1507, simple_loss=0.2175, pruned_loss=0.04196, over 4805.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2258, pruned_loss=0.04302, over 972342.37 frames.], batch size: 21, lr: 4.57e-04
2022-05-04 21:43:47,495 INFO [train.py:715] (4/8) Epoch 4, batch 13050, loss[loss=0.1739, simple_loss=0.2467, pruned_loss=0.05057, over 4749.00 frames.], tot_loss[loss=0.156, simple_loss=0.2261, pruned_loss=0.04299, over 972155.70 frames.], batch size: 19, lr: 4.57e-04
2022-05-04 21:44:27,454 INFO [train.py:715] (4/8) Epoch 4, batch 13100, loss[loss=0.1672, simple_loss=0.2418, pruned_loss=0.04626, over 4958.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2263, pruned_loss=0.04303, over 971896.83 frames.], batch size: 24, lr: 4.57e-04
2022-05-04 21:45:06,499 INFO [train.py:715] (4/8) Epoch 4, batch 13150, loss[loss=0.1481, simple_loss=0.2128, pruned_loss=0.04171, over 4748.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2266, pruned_loss=0.04364, over 971060.36 frames.], batch size: 16, lr: 4.57e-04
2022-05-04 21:45:46,238 INFO [train.py:715] (4/8) Epoch 4, batch 13200, loss[loss=0.1509, simple_loss=0.2285, pruned_loss=0.0366, over 4894.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2271, pruned_loss=0.04394, over 971413.37 frames.], batch size: 17, lr: 4.57e-04
2022-05-04 21:46:26,576 INFO [train.py:715] (4/8) Epoch 4, batch 13250, loss[loss=0.1266, simple_loss=0.1944, pruned_loss=0.0294, over 4941.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2271, pruned_loss=0.04414, over 971623.00 frames.], batch size: 29, lr: 4.57e-04
2022-05-04 21:47:06,164 INFO [train.py:715] (4/8) Epoch 4, batch 13300, loss[loss=0.1778, simple_loss=0.2445, pruned_loss=0.05554, over 4878.00 frames.], tot_loss[loss=0.1576, simple_loss=0.227, pruned_loss=0.04408, over 971990.97 frames.], batch size: 16, lr: 4.57e-04
2022-05-04 21:47:45,754 INFO [train.py:715] (4/8) Epoch 4, batch 13350, loss[loss=0.1467, simple_loss=0.2162, pruned_loss=0.03858, over 4894.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2262, pruned_loss=0.04323, over 971857.90 frames.], batch size: 19, lr: 4.57e-04
2022-05-04 21:48:25,394 INFO [train.py:715] (4/8) Epoch 4, batch 13400, loss[loss=0.1702, simple_loss=0.2388, pruned_loss=0.05076, over 4963.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2266, pruned_loss=0.04357, over 971909.95 frames.], batch size: 15, lr: 4.56e-04
2022-05-04 21:49:05,420 INFO [train.py:715] (4/8) Epoch 4, batch 13450, loss[loss=0.1718, simple_loss=0.2273, pruned_loss=0.05818, over 4844.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2262, pruned_loss=0.04368, over 972826.54 frames.], batch size: 32, lr: 4.56e-04
2022-05-04 21:49:45,241 INFO [train.py:715] (4/8) Epoch 4, batch 13500, loss[loss=0.1685, simple_loss=0.2409, pruned_loss=0.04805, over 4883.00 frames.], tot_loss[loss=0.156, simple_loss=0.2256, pruned_loss=0.04322, over 973130.34 frames.], batch size: 22, lr: 4.56e-04
2022-05-04 21:50:27,087 INFO [train.py:715] (4/8) Epoch 4, batch 13550, loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02924, over 4978.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2264, pruned_loss=0.04359, over 973912.60 frames.], batch size: 28, lr: 4.56e-04
2022-05-04 21:51:07,657 INFO [train.py:715] (4/8) Epoch 4, batch 13600, loss[loss=0.1646, simple_loss=0.2403, pruned_loss=0.04446, over 4847.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2274, pruned_loss=0.04391, over 973703.14 frames.], batch size: 32, lr: 4.56e-04
2022-05-04 21:51:47,208 INFO [train.py:715] (4/8) Epoch 4, batch 13650, loss[loss=0.1588, simple_loss=0.2262, pruned_loss=0.04572, over 4832.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2266, pruned_loss=0.04306, over 974521.93 frames.], batch size: 27, lr: 4.56e-04
2022-05-04 21:52:26,522 INFO [train.py:715] (4/8) Epoch 4, batch 13700, loss[loss=0.1279, simple_loss=0.2001, pruned_loss=0.02787, over 4921.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2267, pruned_loss=0.0434, over 974201.19 frames.], batch size: 17, lr: 4.56e-04
2022-05-04 21:53:06,451 INFO [train.py:715] (4/8) Epoch 4, batch 13750, loss[loss=0.1379, simple_loss=0.2132, pruned_loss=0.0313, over 4816.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2271, pruned_loss=0.0435, over 973523.44 frames.], batch size: 13, lr: 4.56e-04
2022-05-04 21:53:48,109 INFO [train.py:715] (4/8) Epoch 4, batch 13800, loss[loss=0.1663, simple_loss=0.2273, pruned_loss=0.05262, over 4964.00 frames.], tot_loss[loss=0.157, simple_loss=0.2269, pruned_loss=0.04351, over 972808.38 frames.], batch size: 39, lr: 4.56e-04
2022-05-04 21:54:29,031 INFO [train.py:715] (4/8) Epoch 4, batch 13850, loss[loss=0.1386, simple_loss=0.213, pruned_loss=0.03211, over 4966.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2259, pruned_loss=0.04314, over 973351.55 frames.], batch size: 25, lr: 4.56e-04
2022-05-04 21:55:10,916 INFO [train.py:715] (4/8) Epoch 4, batch 13900, loss[loss=0.1904, simple_loss=0.2567, pruned_loss=0.06208, over 4912.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2255, pruned_loss=0.04292, over 972720.15 frames.], batch size: 23, lr: 4.56e-04
2022-05-04 21:55:52,329 INFO [train.py:715] (4/8) Epoch 4, batch 13950, loss[loss=0.1757, simple_loss=0.2533, pruned_loss=0.04902, over 4944.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2254, pruned_loss=0.04279, over 972944.30 frames.], batch size: 29, lr: 4.56e-04
2022-05-04 21:56:31,849 INFO [train.py:715] (4/8) Epoch 4, batch 14000, loss[loss=0.1322, simple_loss=0.2122, pruned_loss=0.0261, over 4863.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2264, pruned_loss=0.04317, over 973562.51 frames.], batch size: 13, lr: 4.56e-04
2022-05-04 21:57:12,897 INFO [train.py:715] (4/8) Epoch 4, batch 14050, loss[loss=0.1606, simple_loss=0.2292, pruned_loss=0.04601, over 4851.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2271, pruned_loss=0.04371, over 973165.47 frames.], batch size: 30, lr: 4.55e-04
2022-05-04 21:57:52,558 INFO [train.py:715] (4/8) Epoch 4, batch 14100, loss[loss=0.1713, simple_loss=0.2294, pruned_loss=0.05658, over 4751.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2267, pruned_loss=0.04395, over 972626.70 frames.], batch size: 19, lr: 4.55e-04
2022-05-04 21:58:32,924 INFO [train.py:715] (4/8) Epoch 4, batch 14150, loss[loss=0.1656, simple_loss=0.2252, pruned_loss=0.05297, over 4803.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2269, pruned_loss=0.04418, over 972729.24 frames.], batch size: 21, lr: 4.55e-04
2022-05-04 21:59:12,284 INFO [train.py:715] (4/8) Epoch 4, batch 14200, loss[loss=0.1625, simple_loss=0.2339, pruned_loss=0.04554, over 4986.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2267, pruned_loss=0.04406, over 972143.00 frames.], batch size: 14, lr: 4.55e-04
2022-05-04 21:59:51,971 INFO [train.py:715] (4/8) Epoch 4, batch 14250, loss[loss=0.1612, simple_loss=0.2262, pruned_loss=0.04812, over 4776.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2266, pruned_loss=0.04392, over 972249.02 frames.], batch size: 14, lr: 4.55e-04
2022-05-04 22:00:32,126 INFO [train.py:715] (4/8) Epoch 4, batch 14300, loss[loss=0.1452, simple_loss=0.2204, pruned_loss=0.03502, over 4971.00 frames.], tot_loss[loss=0.1564, simple_loss=0.226, pruned_loss=0.0434, over 971551.08 frames.], batch size: 39, lr: 4.55e-04
2022-05-04 22:01:10,594 INFO [train.py:715] (4/8) Epoch 4, batch 14350, loss[loss=0.1225, simple_loss=0.1975, pruned_loss=0.02372, over 4819.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2262, pruned_loss=0.04361, over 971998.46 frames.], batch size: 27, lr: 4.55e-04
2022-05-04 22:01:50,875 INFO [train.py:715] (4/8) Epoch 4, batch 14400, loss[loss=0.165, simple_loss=0.2352, pruned_loss=0.04741, over 4965.00 frames.], tot_loss[loss=0.1565, simple_loss=0.226, pruned_loss=0.04348, over 972276.38 frames.], batch size: 21, lr: 4.55e-04
2022-05-04 22:02:30,287 INFO [train.py:715] (4/8) Epoch 4, batch 14450, loss[loss=0.1636, simple_loss=0.2439, pruned_loss=0.04162, over 4860.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2262, pruned_loss=0.04334, over 972023.67 frames.], batch size: 20, lr: 4.55e-04
2022-05-04 22:03:09,284 INFO [train.py:715] (4/8) Epoch 4, batch 14500, loss[loss=0.1529, simple_loss=0.225, pruned_loss=0.04043, over 4779.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2258, pruned_loss=0.04318, over 971874.47 frames.], batch size: 14, lr: 4.55e-04
2022-05-04 22:03:48,139 INFO [train.py:715] (4/8) Epoch 4, batch 14550, loss[loss=0.1439, simple_loss=0.224, pruned_loss=0.03193, over 4814.00 frames.], tot_loss[loss=0.157, simple_loss=0.2266, pruned_loss=0.04373, over 972000.13 frames.], batch size: 25, lr: 4.55e-04
2022-05-04 22:04:27,667 INFO [train.py:715] (4/8) Epoch 4, batch 14600, loss[loss=0.1958, simple_loss=0.2434, pruned_loss=0.07405, over 4871.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2275, pruned_loss=0.0444, over 971838.00 frames.], batch size: 16, lr: 4.55e-04
2022-05-04 22:05:07,542 INFO [train.py:715] (4/8) Epoch 4, batch 14650, loss[loss=0.1313, simple_loss=0.2078, pruned_loss=0.02738, over 4965.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2275, pruned_loss=0.04443, over 972310.94 frames.], batch size: 24, lr: 4.55e-04
2022-05-04 22:05:46,286 INFO [train.py:715] (4/8) Epoch 4, batch 14700, loss[loss=0.1599, simple_loss=0.2339, pruned_loss=0.04293, over 4974.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2263, pruned_loss=0.04355, over 972901.79 frames.], batch size: 35, lr: 4.55e-04
2022-05-04 22:06:26,138 INFO [train.py:715] (4/8) Epoch 4, batch 14750, loss[loss=0.1719, simple_loss=0.2319, pruned_loss=0.05596, over 4867.00 frames.], tot_loss[loss=0.1563, simple_loss=0.226, pruned_loss=0.04332, over 972860.49 frames.], batch size: 32, lr: 4.54e-04
2022-05-04 22:07:06,149 INFO [train.py:715] (4/8) Epoch 4, batch 14800, loss[loss=0.1576, simple_loss=0.2235, pruned_loss=0.04589, over 4762.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2265, pruned_loss=0.04337, over 971479.01 frames.], batch size: 17, lr: 4.54e-04
2022-05-04 22:07:51,020 INFO [train.py:715] (4/8) Epoch 4, batch 14850, loss[loss=0.1469, simple_loss=0.2241, pruned_loss=0.03478, over 4827.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2266, pruned_loss=0.04375, over 971854.94 frames.], batch size: 26, lr: 4.54e-04
2022-05-04 22:08:31,239 INFO [train.py:715] (4/8) Epoch 4, batch 14900, loss[loss=0.1169, simple_loss=0.1927, pruned_loss=0.0205, over 4860.00 frames.], tot_loss[loss=0.158, simple_loss=0.2272, pruned_loss=0.0444, over 972314.39 frames.], batch size: 16, lr: 4.54e-04
2022-05-04 22:09:11,324 INFO [train.py:715] (4/8) Epoch 4, batch 14950, loss[loss=0.1583, simple_loss=0.2275, pruned_loss=0.04456, over 4929.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2279, pruned_loss=0.04493, over 972180.23 frames.], batch size: 23, lr: 4.54e-04
2022-05-04 22:09:51,651 INFO [train.py:715] (4/8) Epoch 4, batch 15000, loss[loss=0.1475, simple_loss=0.2251, pruned_loss=0.03494, over 4761.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2279, pruned_loss=0.04463, over 972997.71 frames.], batch size: 14, lr: 4.54e-04
2022-05-04 22:09:51,652 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 22:10:32,003 INFO [train.py:742] (4/8) Epoch 4, validation: loss=0.1122, simple_loss=0.1978, pruned_loss=0.01336, over 914524.00 frames.
2022-05-04 22:11:12,753 INFO [train.py:715] (4/8) Epoch 4, batch 15050, loss[loss=0.15, simple_loss=0.2211, pruned_loss=0.03942, over 4940.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2278, pruned_loss=0.04439, over 973381.65 frames.], batch size: 21, lr: 4.54e-04
2022-05-04 22:11:52,196 INFO [train.py:715] (4/8) Epoch 4, batch 15100, loss[loss=0.1668, simple_loss=0.2413, pruned_loss=0.04609, over 4923.00 frames.], tot_loss[loss=0.1593, simple_loss=0.2287, pruned_loss=0.04492, over 972592.07 frames.], batch size: 23, lr: 4.54e-04
2022-05-04 22:12:32,089 INFO [train.py:715] (4/8) Epoch 4, batch 15150, loss[loss=0.1395, simple_loss=0.2183, pruned_loss=0.03031, over 4955.00 frames.], tot_loss[loss=0.1591, simple_loss=0.2285, pruned_loss=0.04486, over 972952.93 frames.], batch size: 21, lr: 4.54e-04
2022-05-04 22:13:12,025 INFO [train.py:715] (4/8) Epoch 4, batch 15200, loss[loss=0.1466, simple_loss=0.2137, pruned_loss=0.03973, over 4814.00 frames.], tot_loss[loss=0.1598, simple_loss=0.2289, pruned_loss=0.04531, over 973257.66 frames.], batch size: 12, lr: 4.54e-04
2022-05-04 22:13:51,743 INFO [train.py:715] (4/8) Epoch 4, batch 15250, loss[loss=0.155, simple_loss=0.2302, pruned_loss=0.03991, over 4889.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2279, pruned_loss=0.04454, over 972860.35 frames.], batch size: 16, lr: 4.54e-04
2022-05-04 22:14:31,961 INFO [train.py:715] (4/8) Epoch 4, batch 15300, loss[loss=0.168, simple_loss=0.242, pruned_loss=0.04707, over 4976.00 frames.], tot_loss[loss=0.1589, simple_loss=0.2283, pruned_loss=0.04474, over 972390.70 frames.], batch size: 24, lr: 4.54e-04
2022-05-04 22:15:12,429 INFO [train.py:715] (4/8) Epoch 4, batch 15350, loss[loss=0.1749, simple_loss=0.2429, pruned_loss=0.05347, over 4867.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2276, pruned_loss=0.04454, over 972372.61 frames.], batch size: 20, lr: 4.54e-04
2022-05-04 22:15:52,261 INFO [train.py:715] (4/8) Epoch 4, batch 15400, loss[loss=0.1711, simple_loss=0.2453, pruned_loss=0.04845, over 4862.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2271, pruned_loss=0.04471, over 971684.04 frames.], batch size: 20, lr: 4.53e-04
2022-05-04 22:16:32,478 INFO [train.py:715] (4/8) Epoch 4, batch 15450, loss[loss=0.1606, simple_loss=0.22, pruned_loss=0.05055, over 4831.00 frames.], tot_loss[loss=0.1577, simple_loss=0.227, pruned_loss=0.04421, over 971496.46 frames.], batch size: 30, lr: 4.53e-04
2022-05-04 22:17:12,935 INFO [train.py:715] (4/8) Epoch 4, batch 15500, loss[loss=0.1761, simple_loss=0.2575, pruned_loss=0.04734, over 4689.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2275, pruned_loss=0.04446, over 971913.97 frames.], batch size: 15, lr: 4.53e-04
2022-05-04 22:17:53,289 INFO [train.py:715] (4/8) Epoch 4, batch 15550, loss[loss=0.1183, simple_loss=0.1899, pruned_loss=0.02334, over 4837.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2276, pruned_loss=0.04437, over 972208.43 frames.], batch size: 13, lr: 4.53e-04
2022-05-04 22:18:32,669 INFO [train.py:715] (4/8) Epoch 4, batch 15600, loss[loss=0.1629, simple_loss=0.2302, pruned_loss=0.04776, over 4954.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2262, pruned_loss=0.04331, over 972576.00 frames.], batch size: 29, lr: 4.53e-04
2022-05-04 22:19:13,499 INFO [train.py:715] (4/8) Epoch 4, batch 15650, loss[loss=0.1542, simple_loss=0.2295, pruned_loss=0.03948, over 4762.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2255, pruned_loss=0.04277, over 972952.43 frames.], batch size: 19, lr: 4.53e-04
2022-05-04 22:19:53,093 INFO [train.py:715] (4/8) Epoch 4, batch 15700, loss[loss=0.1352, simple_loss=0.212, pruned_loss=0.02924, over 4826.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2262, pruned_loss=0.04317, over 973512.33 frames.], batch size: 25, lr: 4.53e-04
2022-05-04 22:20:33,264 INFO [train.py:715] (4/8) Epoch 4, batch 15750, loss[loss=0.1673, simple_loss=0.2379, pruned_loss=0.04834, over 4974.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2259, pruned_loss=0.04288, over 973959.43 frames.], batch size: 15, lr: 4.53e-04
2022-05-04 22:21:12,833 INFO [train.py:715] (4/8) Epoch 4, batch 15800, loss[loss=0.1406, simple_loss=0.2127, pruned_loss=0.03419, over 4910.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2264, pruned_loss=0.04341, over 974092.16 frames.], batch size: 18, lr: 4.53e-04
2022-05-04 22:21:53,777 INFO [train.py:715] (4/8) Epoch 4, batch 15850, loss[loss=0.1281, simple_loss=0.2058, pruned_loss=0.02526, over 4971.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2268, pruned_loss=0.04378, over 974342.59 frames.], batch size: 28, lr: 4.53e-04
2022-05-04 22:22:34,991 INFO [train.py:715] (4/8) Epoch 4, batch 15900, loss[loss=0.1422, simple_loss=0.2221, pruned_loss=0.03116, over 4933.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2267, pruned_loss=0.04346, over 974731.88 frames.], batch size: 21, lr: 4.53e-04
2022-05-04 22:23:14,304 INFO [train.py:715] (4/8) Epoch 4, batch 15950, loss[loss=0.1627, simple_loss=0.2394, pruned_loss=0.04295, over 4879.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2269, pruned_loss=0.04384, over 974643.68 frames.], batch size: 16, lr: 4.53e-04
2022-05-04 22:23:54,446 INFO [train.py:715] (4/8) Epoch 4, batch 16000, loss[loss=0.1594, simple_loss=0.2244, pruned_loss=0.04723, over 4862.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2261, pruned_loss=0.0433, over 974926.17 frames.], batch size: 20, lr: 4.53e-04
2022-05-04 22:24:34,929 INFO [train.py:715] (4/8) Epoch 4, batch 16050, loss[loss=0.1881, simple_loss=0.2561, pruned_loss=0.06007, over 4984.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2246, pruned_loss=0.04242, over 973482.99 frames.], batch size: 39, lr: 4.53e-04
2022-05-04 22:25:14,766 INFO [train.py:715] (4/8) Epoch 4, batch 16100, loss[loss=0.1472, simple_loss=0.2128, pruned_loss=0.04077, over 4941.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2238, pruned_loss=0.04231, over 973316.68 frames.], batch size: 21, lr: 4.52e-04
2022-05-04 22:25:54,147 INFO [train.py:715] (4/8) Epoch 4, batch 16150, loss[loss=0.1786, simple_loss=0.2485, pruned_loss=0.05435, over 4816.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2239, pruned_loss=0.04238, over 972386.81 frames.], batch size: 26, lr: 4.52e-04
2022-05-04 22:26:34,756 INFO [train.py:715] (4/8) Epoch 4, batch 16200, loss[loss=0.1424, simple_loss=0.218, pruned_loss=0.03344, over 4762.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2249, pruned_loss=0.0428, over 972378.11 frames.], batch size: 16, lr: 4.52e-04
2022-05-04 22:27:15,080 INFO [train.py:715] (4/8) Epoch 4, batch 16250, loss[loss=0.1432, simple_loss=0.2109, pruned_loss=0.03777, over 4879.00 frames.], tot_loss[loss=0.156, simple_loss=0.2256, pruned_loss=0.04321, over 972717.29 frames.], batch size: 16, lr: 4.52e-04
2022-05-04 22:27:54,412 INFO [train.py:715] (4/8) Epoch 4, batch 16300, loss[loss=0.1406, simple_loss=0.2203, pruned_loss=0.0304, over 4793.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2256, pruned_loss=0.04316, over 972386.02 frames.], batch size: 14, lr: 4.52e-04
2022-05-04 22:28:34,990 INFO [train.py:715] (4/8) Epoch 4, batch 16350, loss[loss=0.1597, simple_loss=0.2127, pruned_loss=0.05338, over 4841.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2259, pruned_loss=0.04324, over 972634.28 frames.], batch size: 12, lr: 4.52e-04
2022-05-04 22:29:15,681 INFO [train.py:715] (4/8) Epoch 4, batch 16400, loss[loss=0.196, simple_loss=0.2511, pruned_loss=0.07046, over 4857.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2263, pruned_loss=0.04348, over 972193.77 frames.], batch size: 20, lr: 4.52e-04
2022-05-04 22:29:56,024 INFO [train.py:715] (4/8) Epoch 4, batch 16450, loss[loss=0.1371, simple_loss=0.21, pruned_loss=0.03214, over 4897.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2273, pruned_loss=0.04398, over 972351.88 frames.], batch size: 19, lr: 4.52e-04
2022-05-04 22:30:35,468 INFO [train.py:715] (4/8) Epoch 4, batch 16500, loss[loss=0.1572, simple_loss=0.2365, pruned_loss=0.03891, over 4940.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2264, pruned_loss=0.04326, over 971817.93 frames.], batch size: 23, lr: 4.52e-04
2022-05-04 22:31:15,355 INFO [train.py:715] (4/8) Epoch 4, batch 16550, loss[loss=0.1925, simple_loss=0.2573, pruned_loss=0.06383, over 4862.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2265, pruned_loss=0.04335, over 971227.91 frames.], batch size: 32, lr: 4.52e-04
2022-05-04 22:31:55,168 INFO [train.py:715] (4/8) Epoch 4, batch 16600, loss[loss=0.1537, simple_loss=0.2238, pruned_loss=0.04181, over 4896.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2266, pruned_loss=0.04332, over 971097.80 frames.], batch size: 17, lr: 4.52e-04
2022-05-04 22:32:33,986 INFO [train.py:715] (4/8) Epoch 4, batch 16650, loss[loss=0.1946, simple_loss=0.2519, pruned_loss=0.06865, over 4913.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2267, pruned_loss=0.04378, over 971836.77 frames.], batch size: 39, lr: 4.52e-04
2022-05-04 22:33:12,846 INFO [train.py:715] (4/8) Epoch 4, batch 16700, loss[loss=0.1607, simple_loss=0.2331, pruned_loss=0.04413, over 4766.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2267, pruned_loss=0.04385, over 971702.89 frames.], batch size: 16, lr: 4.52e-04
2022-05-04 22:33:52,190 INFO [train.py:715] (4/8) Epoch 4, batch 16750, loss[loss=0.1377, simple_loss=0.2129, pruned_loss=0.03127, over 4876.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2272, pruned_loss=0.04402, over 971810.53 frames.], batch size: 22, lr: 4.52e-04
2022-05-04 22:34:31,640 INFO [train.py:715] (4/8) Epoch 4, batch 16800, loss[loss=0.1522, simple_loss=0.2346, pruned_loss=0.03489, over 4804.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2282, pruned_loss=0.04452, over 971597.12 frames.], batch size: 26, lr: 4.51e-04
2022-05-04 22:35:10,393 INFO [train.py:715] (4/8) Epoch 4, batch 16850, loss[loss=0.1434, simple_loss=0.2024, pruned_loss=0.04221, over 4856.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2277, pruned_loss=0.04451, over 972248.15 frames.], batch size: 13, lr: 4.51e-04
2022-05-04 22:35:50,732 INFO [train.py:715] (4/8) Epoch 4, batch 16900, loss[loss=0.1427, simple_loss=0.2142, pruned_loss=0.03566, over 4802.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2271, pruned_loss=0.04406, over 973185.70 frames.], batch size: 26, lr: 4.51e-04
2022-05-04 22:36:31,083 INFO [train.py:715] (4/8) Epoch 4, batch 16950, loss[loss=0.1688, simple_loss=0.2409, pruned_loss=0.04837, over 4828.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2271, pruned_loss=0.04331, over 973659.21 frames.], batch size: 30, lr: 4.51e-04
2022-05-04 22:37:10,621 INFO [train.py:715] (4/8) Epoch 4, batch 17000, loss[loss=0.1886, simple_loss=0.2505, pruned_loss=0.06338, over 4930.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2282, pruned_loss=0.04397, over 974069.23 frames.], batch size: 39, lr: 4.51e-04
2022-05-04 22:37:50,465 INFO [train.py:715] (4/8) Epoch 4, batch 17050, loss[loss=0.1565, simple_loss=0.2173, pruned_loss=0.0478, over 4900.00 frames.], tot_loss[loss=0.158, simple_loss=0.2279, pruned_loss=0.04405, over 974201.55 frames.], batch size: 17, lr: 4.51e-04
2022-05-04 22:38:30,853 INFO [train.py:715] (4/8) Epoch 4, batch 17100, loss[loss=0.1816, simple_loss=0.24, pruned_loss=0.0616, over 4958.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2274, pruned_loss=0.0439, over 974761.90 frames.], batch size: 24, lr: 4.51e-04
2022-05-04 22:39:10,955 INFO [train.py:715] (4/8) Epoch 4, batch 17150, loss[loss=0.1179, simple_loss=0.1903, pruned_loss=0.02276, over 4803.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2275, pruned_loss=0.0436, over 974301.64 frames.], batch size: 13, lr: 4.51e-04
2022-05-04 22:39:50,097 INFO [train.py:715] (4/8) Epoch 4, batch 17200, loss[loss=0.1343, simple_loss=0.2099, pruned_loss=0.02935, over 4813.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2274, pruned_loss=0.04376, over 974343.74 frames.], batch size: 25, lr: 4.51e-04
2022-05-04 22:40:30,242 INFO [train.py:715] (4/8) Epoch 4, batch 17250, loss[loss=0.1473, simple_loss=0.2163, pruned_loss=0.03916, over 4964.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2266, pruned_loss=0.04353, over 974430.54 frames.], batch size: 24, lr: 4.51e-04
2022-05-04 22:41:10,187 INFO [train.py:715] (4/8) Epoch 4, batch 17300, loss[loss=0.1528, simple_loss=0.2298, pruned_loss=0.03791, over 4791.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2267, pruned_loss=0.04333, over 974997.08 frames.], batch size: 18, lr: 4.51e-04
2022-05-04 22:41:49,921 INFO [train.py:715] (4/8) Epoch 4, batch 17350, loss[loss=0.164, simple_loss=0.2305, pruned_loss=0.04877, over 4750.00 frames.], tot_loss[loss=0.1559, simple_loss=0.226, pruned_loss=0.04295, over 974126.89 frames.], batch size: 19, lr: 4.51e-04
2022-05-04 22:42:29,440 INFO [train.py:715] (4/8) Epoch 4, batch 17400, loss[loss=0.1564, simple_loss=0.2321, pruned_loss=0.04038, over 4929.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2257, pruned_loss=0.04276, over 973130.11 frames.], batch size: 23, lr: 4.51e-04
2022-05-04 22:43:09,749 INFO [train.py:715] (4/8) Epoch 4, batch 17450, loss[loss=0.2034, simple_loss=0.2647, pruned_loss=0.07107, over 4831.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2267, pruned_loss=0.04302, over 972770.74 frames.], batch size: 15, lr: 4.51e-04
2022-05-04 22:43:50,023 INFO [train.py:715] (4/8) Epoch 4, batch 17500, loss[loss=0.19, simple_loss=0.2626, pruned_loss=0.05873, over 4910.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2275, pruned_loss=0.04381, over 973001.66 frames.], batch size: 17, lr: 4.50e-04
2022-05-04 22:44:29,242 INFO [train.py:715] (4/8) Epoch 4, batch 17550, loss[loss=0.141, simple_loss=0.2189, pruned_loss=0.03154, over 4844.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2271, pruned_loss=0.04369, over 972377.14 frames.], batch size: 20, lr: 4.50e-04
2022-05-04 22:45:09,113 INFO [train.py:715] (4/8) Epoch 4, batch 17600, loss[loss=0.1289, simple_loss=0.1979, pruned_loss=0.02993, over 4972.00 frames.], tot_loss[loss=0.1583, simple_loss=0.2278, pruned_loss=0.04437, over 971702.57 frames.], batch size: 28, lr: 4.50e-04
2022-05-04 22:45:49,507 INFO [train.py:715] (4/8) Epoch 4, batch 17650, loss[loss=0.1567, simple_loss=0.2279, pruned_loss=0.04273, over 4884.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2271, pruned_loss=0.04408, over 972216.21 frames.], batch size: 22, lr: 4.50e-04
2022-05-04 22:46:29,566 INFO [train.py:715] (4/8) Epoch 4, batch 17700, loss[loss=0.1414, simple_loss=0.2129, pruned_loss=0.03499, over 4809.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2274, pruned_loss=0.04434, over 972915.98 frames.], batch size: 25, lr: 4.50e-04
2022-05-04 22:47:09,154 INFO [train.py:715] (4/8) Epoch 4, batch 17750, loss[loss=0.1568, simple_loss=0.2207, pruned_loss=0.04646, over 4866.00 frames.], tot_loss[loss=0.157, simple_loss=0.2265, pruned_loss=0.04372, over 972467.60 frames.], batch size: 34, lr: 4.50e-04
2022-05-04 22:47:49,249 INFO [train.py:715] (4/8) Epoch 4, batch 17800, loss[loss=0.1531, simple_loss=0.2256, pruned_loss=0.04028, over 4778.00 frames.], tot_loss[loss=0.1567, simple_loss=0.226, pruned_loss=0.0437, over 972216.25 frames.], batch size: 18, lr: 4.50e-04
2022-05-04 22:48:29,922 INFO [train.py:715] (4/8) Epoch 4, batch 17850, loss[loss=0.1484, simple_loss=0.2181, pruned_loss=0.03932, over 4792.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2261, pruned_loss=0.04387, over 971917.62 frames.], batch size: 24, lr: 4.50e-04
2022-05-04 22:49:09,019 INFO [train.py:715] (4/8) Epoch 4, batch 17900, loss[loss=0.1557, simple_loss=0.2299, pruned_loss=0.04071, over 4961.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2272, pruned_loss=0.04429, over 972705.49 frames.], batch size: 24, lr: 4.50e-04
2022-05-04 22:49:49,020 INFO [train.py:715] (4/8) Epoch 4, batch 17950, loss[loss=0.1789, simple_loss=0.2403, pruned_loss=0.05875, over 4794.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2265, pruned_loss=0.04388, over 971939.71 frames.], batch size: 24, lr: 4.50e-04
2022-05-04 22:50:29,178 INFO [train.py:715] (4/8) Epoch 4, batch 18000, loss[loss=0.1523, simple_loss=0.2288, pruned_loss=0.03787, over 4884.00 frames.], tot_loss[loss=0.157, simple_loss=0.2263, pruned_loss=0.04378, over 971631.03 frames.], batch size: 32, lr: 4.50e-04
2022-05-04 22:50:29,179 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 22:50:38,823 INFO [train.py:742] (4/8) Epoch 4, validation: loss=0.1119, simple_loss=0.1976, pruned_loss=0.01313, over 914524.00 frames.
2022-05-04 22:51:19,284 INFO [train.py:715] (4/8) Epoch 4, batch 18050, loss[loss=0.1423, simple_loss=0.2053, pruned_loss=0.03966, over 4879.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2249, pruned_loss=0.0429, over 971893.19 frames.], batch size: 19, lr: 4.50e-04
2022-05-04 22:51:59,527 INFO [train.py:715] (4/8) Epoch 4, batch 18100, loss[loss=0.1282, simple_loss=0.1948, pruned_loss=0.03085, over 4815.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2244, pruned_loss=0.04323, over 971654.26 frames.], batch size: 12, lr: 4.50e-04
2022-05-04 22:52:39,088 INFO [train.py:715] (4/8) Epoch 4, batch 18150, loss[loss=0.1726, simple_loss=0.2432, pruned_loss=0.05097, over 4950.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2252, pruned_loss=0.04346, over 972058.74 frames.], batch size: 35, lr: 4.50e-04
2022-05-04 22:53:19,399 INFO [train.py:715] (4/8) Epoch 4, batch 18200, loss[loss=0.1662, simple_loss=0.2351, pruned_loss=0.04863, over 4785.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2255, pruned_loss=0.04346, over 971972.51 frames.], batch size: 21, lr: 4.49e-04
2022-05-04 22:53:59,864 INFO [train.py:715] (4/8) Epoch 4, batch 18250, loss[loss=0.147, simple_loss=0.2344, pruned_loss=0.02983, over 4950.00 frames.], tot_loss[loss=0.156, simple_loss=0.2255, pruned_loss=0.04329, over 972041.54 frames.], batch size: 24, lr: 4.49e-04
2022-05-04 22:54:39,563 INFO [train.py:715] (4/8) Epoch 4, batch 18300, loss[loss=0.1449, simple_loss=0.2113, pruned_loss=0.03922, over 4979.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2254, pruned_loss=0.04322, over 971819.66 frames.], batch size: 39, lr: 4.49e-04
2022-05-04 22:55:19,274 INFO [train.py:715] (4/8) Epoch 4, batch 18350, loss[loss=0.2007, simple_loss=0.2662, pruned_loss=0.06765, over 4922.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2267, pruned_loss=0.04377, over 972479.45 frames.], batch size: 18, lr: 4.49e-04
2022-05-04 22:56:00,391 INFO [train.py:715] (4/8) Epoch 4, batch 18400, loss[loss=0.1571, simple_loss=0.2309, pruned_loss=0.04168, over 4772.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2272, pruned_loss=0.04423, over 972808.95 frames.], batch size: 18, lr: 4.49e-04
2022-05-04 22:56:40,806 INFO [train.py:715] (4/8) Epoch 4, batch 18450, loss[loss=0.1635, simple_loss=0.2302, pruned_loss=0.04842, over 4917.00 frames.], tot_loss[loss=0.1582, simple_loss=0.2277, pruned_loss=0.04433, over 972821.76 frames.], batch size: 19, lr: 4.49e-04
2022-05-04 22:57:20,891 INFO [train.py:715] (4/8) Epoch 4, batch 18500, loss[loss=0.1964, simple_loss=0.2573, pruned_loss=0.06774, over 4843.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2276, pruned_loss=0.04383, over 973169.92 frames.], batch size: 15, lr: 4.49e-04
2022-05-04 22:58:01,182 INFO [train.py:715] (4/8) Epoch 4, batch 18550, loss[loss=0.2026, simple_loss=0.2572, pruned_loss=0.07402, over 4875.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2274, pruned_loss=0.04419, over 972941.33 frames.], batch size: 32, lr: 4.49e-04
2022-05-04 22:58:41,891 INFO [train.py:715] (4/8) Epoch 4, batch 18600, loss[loss=0.1724, simple_loss=0.2544, pruned_loss=0.04524, over 4767.00 frames.], tot_loss[loss=0.158, simple_loss=0.2275, pruned_loss=0.04425, over 972802.89 frames.], batch size: 18, lr: 4.49e-04
2022-05-04 22:59:21,450 INFO [train.py:715] (4/8) Epoch 4, batch 18650, loss[loss=0.1627, simple_loss=0.2347, pruned_loss=0.04536, over 4808.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2266, pruned_loss=0.04342, over 973256.16 frames.], batch size: 21, lr: 4.49e-04
2022-05-04 23:00:01,608 INFO [train.py:715] (4/8) Epoch 4, batch 18700, loss[loss=0.1173, simple_loss=0.1868, pruned_loss=0.02389, over 4830.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2268, pruned_loss=0.04345, over 972593.77 frames.], batch size: 13, lr: 4.49e-04
2022-05-04 23:00:42,462 INFO [train.py:715] (4/8) Epoch 4, batch 18750, loss[loss=0.1706, simple_loss=0.2339, pruned_loss=0.05368, over 4964.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2263, pruned_loss=0.04298, over 972111.82 frames.], batch size: 24, lr: 4.49e-04
2022-05-04 23:01:21,953 INFO [train.py:715] (4/8) Epoch 4, batch 18800, loss[loss=0.1329, simple_loss=0.2022, pruned_loss=0.03184, over 4983.00 frames.], tot_loss[loss=0.157, simple_loss=0.2268, pruned_loss=0.04365, over 973085.81 frames.], batch size: 24, lr: 4.49e-04
2022-05-04 23:02:02,021 INFO [train.py:715] (4/8) Epoch 4, batch 18850, loss[loss=0.149, simple_loss=0.2294, pruned_loss=0.03425, over 4805.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2273, pruned_loss=0.04358, over 973160.35 frames.], batch size: 25, lr: 4.49e-04
2022-05-04 23:02:42,419 INFO [train.py:715] (4/8) Epoch 4, batch 18900, loss[loss=0.1578, simple_loss=0.2338, pruned_loss=0.04093, over 4977.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2276, pruned_loss=0.04395, over 973394.00 frames.], batch size: 15, lr: 4.48e-04
2022-05-04 23:03:22,739 INFO [train.py:715] (4/8) Epoch 4, batch 18950, loss[loss=0.1411, simple_loss=0.2146, pruned_loss=0.03382, over 4834.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2267, pruned_loss=0.04377, over 972443.48 frames.], batch size: 26, lr: 4.48e-04
2022-05-04 23:04:01,999 INFO [train.py:715] (4/8) Epoch 4, batch 19000, loss[loss=0.1587, simple_loss=0.2289, pruned_loss=0.04424, over 4748.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2265, pruned_loss=0.0434, over 972564.92 frames.], batch size: 19, lr: 4.48e-04
2022-05-04 23:04:42,512 INFO [train.py:715] (4/8) Epoch 4, batch 19050, loss[loss=0.1554, simple_loss=0.2228, pruned_loss=0.04402, over 4786.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2268, pruned_loss=0.04379, over 971741.35 frames.], batch size: 14, lr: 4.48e-04
2022-05-04 23:05:23,233 INFO [train.py:715] (4/8) Epoch 4, batch 19100, loss[loss=0.1529, simple_loss=0.2173, pruned_loss=0.04423, over 4817.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2263, pruned_loss=0.04351, over 971579.62 frames.], batch size: 13, lr: 4.48e-04
2022-05-04 23:06:03,187 INFO [train.py:715] (4/8) Epoch 4, batch 19150, loss[loss=0.155, simple_loss=0.2144, pruned_loss=0.04777, over 4865.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2267, pruned_loss=0.04386, over 971947.01 frames.], batch size: 20, lr: 4.48e-04
2022-05-04 23:06:43,535 INFO [train.py:715] (4/8) Epoch 4, batch 19200, loss[loss=0.1572, simple_loss=0.2279, pruned_loss=0.04324, over 4978.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2259, pruned_loss=0.04377, over 971636.43 frames.], batch size: 28, lr: 4.48e-04
2022-05-04 23:07:24,301 INFO [train.py:715] (4/8) Epoch 4, batch 19250, loss[loss=0.146, simple_loss=0.2171, pruned_loss=0.03741, over 4970.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2264, pruned_loss=0.04402, over 972002.84 frames.], batch size: 15, lr: 4.48e-04
2022-05-04 23:08:04,902 INFO [train.py:715] (4/8) Epoch 4, batch 19300, loss[loss=0.1393, simple_loss=0.2088, pruned_loss=0.03486, over 4793.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2253, pruned_loss=0.04384, over 972052.23 frames.], batch size: 24, lr: 4.48e-04
2022-05-04 23:08:44,075 INFO [train.py:715] (4/8) Epoch 4, batch 19350, loss[loss=0.1628, simple_loss=0.2249, pruned_loss=0.05039, over 4753.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2254, pruned_loss=0.04369, over 972186.70 frames.], batch size: 19, lr: 4.48e-04
2022-05-04 23:09:24,770 INFO [train.py:715] (4/8) Epoch 4, batch 19400, loss[loss=0.1252, simple_loss=0.1926, pruned_loss=0.02887, over 4855.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2247, pruned_loss=0.04313, over 971701.01 frames.], batch size: 13, lr: 4.48e-04
2022-05-04 23:10:06,274 INFO [train.py:715] (4/8) Epoch 4, batch 19450, loss[loss=0.1423, simple_loss=0.2052, pruned_loss=0.03968, over 4969.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2245, pruned_loss=0.04295, over 970658.95 frames.], batch size: 14, lr: 4.48e-04
2022-05-04 23:10:47,426 INFO [train.py:715] (4/8) Epoch 4, batch 19500, loss[loss=0.1477, simple_loss=0.2212, pruned_loss=0.03706, over 4952.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2252, pruned_loss=0.04328, over 971293.60 frames.], batch size: 21, lr: 4.48e-04
2022-05-04 23:11:27,083 INFO [train.py:715] (4/8) Epoch 4, batch 19550, loss[loss=0.1277, simple_loss=0.1909, pruned_loss=0.03227, over 4730.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2252, pruned_loss=0.0435, over 971713.38 frames.], batch size: 12, lr: 4.48e-04
2022-05-04 23:12:07,472 INFO [train.py:715] (4/8) Epoch 4, batch 19600, loss[loss=0.1608, simple_loss=0.2246, pruned_loss=0.04846, over 4942.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2258, pruned_loss=0.04393, over 972043.96 frames.], batch size: 35, lr: 4.47e-04
2022-05-04 23:12:47,696 INFO [train.py:715] (4/8) Epoch 4, batch 19650, loss[loss=0.1725, simple_loss=0.234, pruned_loss=0.05549, over 4888.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2264, pruned_loss=0.04405, over 973005.40 frames.], batch size: 19, lr: 4.47e-04
2022-05-04 23:13:26,461 INFO [train.py:715] (4/8) Epoch 4, batch 19700, loss[loss=0.1552, simple_loss=0.2299, pruned_loss=0.04023, over 4853.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2271, pruned_loss=0.0442, over 972783.96 frames.], batch size: 32, lr: 4.47e-04
2022-05-04 23:14:07,137 INFO [train.py:715] (4/8) Epoch 4, batch 19750, loss[loss=0.1811, simple_loss=0.2502, pruned_loss=0.05602, over 4980.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2282, pruned_loss=0.04453, over 972357.71 frames.], batch size: 31, lr: 4.47e-04
2022-05-04 23:14:47,959 INFO [train.py:715] (4/8) Epoch 4, batch 19800, loss[loss=0.1434, simple_loss=0.2149, pruned_loss=0.03598, over 4988.00 frames.], tot_loss[loss=0.158, simple_loss=0.2275, pruned_loss=0.04431, over 972692.44 frames.], batch size: 31, lr: 4.47e-04
2022-05-04 23:15:27,700 INFO [train.py:715] (4/8) Epoch 4, batch 19850, loss[loss=0.1609, simple_loss=0.235, pruned_loss=0.04343, over 4974.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2274, pruned_loss=0.04437, over 972773.86 frames.], batch size: 24, lr: 4.47e-04
2022-05-04 23:16:07,779 INFO [train.py:715] (4/8) Epoch 4, batch 19900, loss[loss=0.1667, simple_loss=0.2372, pruned_loss=0.04807, over 4802.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2264, pruned_loss=0.04423, over 973179.04 frames.], batch size: 14, lr: 4.47e-04
2022-05-04 23:16:47,892 INFO [train.py:715] (4/8) Epoch 4, batch 19950, loss[loss=0.1305, simple_loss=0.1948, pruned_loss=0.03307, over 4781.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2268, pruned_loss=0.04453, over 972612.86 frames.], batch size: 17, lr: 4.47e-04
2022-05-04 23:17:28,061 INFO [train.py:715] (4/8) Epoch 4, batch 20000, loss[loss=0.1443, simple_loss=0.2194, pruned_loss=0.03461, over 4986.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2269, pruned_loss=0.04437, over 972950.09 frames.], batch size: 28, lr: 4.47e-04
2022-05-04 23:18:06,763 INFO [train.py:715] (4/8) Epoch 4, batch 20050, loss[loss=0.1381, simple_loss=0.2109, pruned_loss=0.03263, over 4809.00 frames.], tot_loss[loss=0.157, simple_loss=0.2264, pruned_loss=0.04378, over 973066.12 frames.], batch size: 21, lr: 4.47e-04
2022-05-04 23:18:46,565 INFO [train.py:715] (4/8) Epoch 4, batch 20100, loss[loss=0.1664, simple_loss=0.2535, pruned_loss=0.03964, over 4837.00 frames.], tot_loss[loss=0.1571, simple_loss=0.227, pruned_loss=0.04359, over 972829.36 frames.], batch size: 15, lr: 4.47e-04
2022-05-04 23:19:26,623 INFO [train.py:715] (4/8) Epoch 4, batch 20150, loss[loss=0.1724, simple_loss=0.2342, pruned_loss=0.05531, over 4981.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2264, pruned_loss=0.04348, over 972362.52 frames.], batch size: 25, lr: 4.47e-04
2022-05-04 23:20:06,063 INFO [train.py:715] (4/8) Epoch 4, batch 20200, loss[loss=0.1301, simple_loss=0.218, pruned_loss=0.02113, over 4804.00 frames.], tot_loss[loss=0.1557, simple_loss=0.226, pruned_loss=0.04272, over 972354.83 frames.], batch size: 21, lr: 4.47e-04
2022-05-04 23:20:45,806 INFO [train.py:715] (4/8) Epoch 4, batch 20250, loss[loss=0.1825, simple_loss=0.2425, pruned_loss=0.06125, over 4821.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2252, pruned_loss=0.04229, over 971767.99 frames.], batch size: 25, lr: 4.47e-04
2022-05-04 23:21:26,124 INFO [train.py:715] (4/8) Epoch 4, batch 20300, loss[loss=0.1892, simple_loss=0.25, pruned_loss=0.06416, over 4845.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2257, pruned_loss=0.04249, over 972865.88 frames.], batch size: 30, lr: 4.46e-04
2022-05-04 23:22:06,209 INFO [train.py:715] (4/8) Epoch 4, batch 20350, loss[loss=0.1464, simple_loss=0.2207, pruned_loss=0.03602, over 4903.00 frames.], tot_loss[loss=0.157, simple_loss=0.2274, pruned_loss=0.0433, over 972528.56 frames.], batch size: 19, lr: 4.46e-04
2022-05-04 23:22:45,045 INFO [train.py:715] (4/8) Epoch 4, batch 20400, loss[loss=0.1802, simple_loss=0.2463, pruned_loss=0.05699, over 4955.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2273, pruned_loss=0.04357, over 972097.71 frames.], batch size: 35, lr: 4.46e-04
2022-05-04 23:23:25,031 INFO [train.py:715] (4/8) Epoch 4, batch 20450, loss[loss=0.1516, simple_loss=0.2244, pruned_loss=0.03935, over 4896.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2272, pruned_loss=0.04388, over 972138.86 frames.], batch size: 19, lr: 4.46e-04
2022-05-04 23:24:04,955 INFO [train.py:715] (4/8) Epoch 4, batch 20500, loss[loss=0.1521, simple_loss=0.2119, pruned_loss=0.04615, over 4885.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2262, pruned_loss=0.04383, over 972186.10 frames.], batch size: 16, lr: 4.46e-04
2022-05-04 23:24:44,747 INFO [train.py:715] (4/8) Epoch 4, batch 20550, loss[loss=0.1628, simple_loss=0.2276, pruned_loss=0.04907, over 4968.00 frames.], tot_loss[loss=0.1567, simple_loss=0.226, pruned_loss=0.04369, over 971585.99 frames.], batch size: 35, lr: 4.46e-04
2022-05-04 23:25:23,714 INFO [train.py:715] (4/8) Epoch 4, batch 20600, loss[loss=0.1429, simple_loss=0.2182, pruned_loss=0.03387, over 4913.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2255, pruned_loss=0.04319, over 971767.57 frames.], batch size: 19, lr: 4.46e-04
2022-05-04 23:26:03,652 INFO [train.py:715] (4/8) Epoch 4, batch 20650, loss[loss=0.1554, simple_loss=0.2366, pruned_loss=0.03706, over 4971.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2258, pruned_loss=0.04344, over 972849.18 frames.], batch size: 15, lr: 4.46e-04
2022-05-04 23:26:44,149 INFO [train.py:715] (4/8) Epoch 4, batch 20700, loss[loss=0.1733, simple_loss=0.2424, pruned_loss=0.05212, over 4881.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2255, pruned_loss=0.04301, over 972281.83 frames.], batch size: 38, lr: 4.46e-04
2022-05-04 23:27:22,801 INFO [train.py:715] (4/8) Epoch 4, batch 20750, loss[loss=0.1775, simple_loss=0.2293, pruned_loss=0.06287, over 4972.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2257, pruned_loss=0.04335, over 973080.35 frames.], batch size: 35, lr: 4.46e-04
2022-05-04 23:28:04,809 INFO [train.py:715] (4/8) Epoch 4, batch 20800, loss[loss=0.1603, simple_loss=0.2277, pruned_loss=0.0465, over 4824.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2267, pruned_loss=0.04423, over 972480.78 frames.], batch size: 27, lr: 4.46e-04
2022-05-04 23:28:44,591 INFO [train.py:715] (4/8) Epoch 4, batch 20850, loss[loss=0.15, simple_loss=0.2122, pruned_loss=0.04391, over 4798.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2265, pruned_loss=0.04385, over 972710.74 frames.], batch size: 12, lr: 4.46e-04
2022-05-04 23:29:24,434 INFO [train.py:715] (4/8) Epoch 4, batch 20900, loss[loss=0.1607, simple_loss=0.2383, pruned_loss=0.04157, over 4948.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2266, pruned_loss=0.04397, over 972273.09 frames.], batch size: 21, lr: 4.46e-04
2022-05-04 23:30:03,465 INFO [train.py:715] (4/8) Epoch 4, batch 20950, loss[loss=0.1538, simple_loss=0.2199, pruned_loss=0.04384, over 4985.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2257, pruned_loss=0.04293, over 973280.20 frames.], batch size: 28, lr: 4.46e-04
2022-05-04 23:30:43,440 INFO [train.py:715] (4/8) Epoch 4, batch 21000, loss[loss=0.1738, simple_loss=0.2449, pruned_loss=0.05132, over 4933.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2266, pruned_loss=0.04353, over 972247.39 frames.], batch size: 21, lr: 4.46e-04
2022-05-04 23:30:43,441 INFO [train.py:733] (4/8) Computing validation loss
2022-05-04 23:30:52,894 INFO [train.py:742] (4/8) Epoch 4, validation: loss=0.1116, simple_loss=0.1973, pruned_loss=0.01293, over 914524.00 frames.
2022-05-04 23:31:33,182 INFO [train.py:715] (4/8) Epoch 4, batch 21050, loss[loss=0.1599, simple_loss=0.2278, pruned_loss=0.04602, over 4914.00 frames.], tot_loss[loss=0.1585, simple_loss=0.228, pruned_loss=0.04447, over 972689.57 frames.], batch size: 17, lr: 4.45e-04
2022-05-04 23:32:12,975 INFO [train.py:715] (4/8) Epoch 4, batch 21100, loss[loss=0.1614, simple_loss=0.2238, pruned_loss=0.04949, over 4977.00 frames.], tot_loss[loss=0.1585, simple_loss=0.2283, pruned_loss=0.04435, over 972512.00 frames.], batch size: 14, lr: 4.45e-04
2022-05-04 23:32:52,567 INFO [train.py:715] (4/8) Epoch 4, batch 21150, loss[loss=0.1577, simple_loss=0.2259, pruned_loss=0.04477, over 4693.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2279, pruned_loss=0.04398, over 972064.93 frames.], batch size: 15, lr: 4.45e-04
2022-05-04 23:33:32,143 INFO [train.py:715] (4/8) Epoch 4, batch 21200, loss[loss=0.19, simple_loss=0.2629, pruned_loss=0.05858, over 4966.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2276, pruned_loss=0.04344, over 972507.71 frames.], batch size: 24, lr: 4.45e-04
2022-05-04 23:34:12,357 INFO [train.py:715] (4/8) Epoch 4, batch 21250, loss[loss=0.1353, simple_loss=0.195, pruned_loss=0.03785, over 4907.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2268, pruned_loss=0.04308, over 972771.93 frames.], batch size: 18, lr: 4.45e-04
2022-05-04 23:34:51,183 INFO [train.py:715] (4/8) Epoch 4, batch 21300, loss[loss=0.1389, simple_loss=0.2125, pruned_loss=0.03269, over 4786.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2262, pruned_loss=0.04275, over 971099.12 frames.], batch size: 19, lr: 4.45e-04
2022-05-04 23:35:30,238 INFO [train.py:715] (4/8) Epoch 4, batch 21350, loss[loss=0.1576, simple_loss=0.2237, pruned_loss=0.0457, over 4774.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2262, pruned_loss=0.04255, over 971814.73 frames.], batch size: 19, lr: 4.45e-04
2022-05-04 23:36:09,888 INFO [train.py:715] (4/8) Epoch 4, batch 21400, loss[loss=0.1607, simple_loss=0.2297, pruned_loss=0.04585, over 4956.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2257, pruned_loss=0.04252, over 971238.25 frames.], batch size: 24, lr: 4.45e-04
2022-05-04 23:36:49,452 INFO [train.py:715] (4/8) Epoch 4, batch 21450, loss[loss=0.1711, simple_loss=0.2481, pruned_loss=0.04706, over 4938.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2258, pruned_loss=0.04288, over 971876.50 frames.], batch size: 39, lr: 4.45e-04
2022-05-04 23:37:28,639 INFO [train.py:715] (4/8) Epoch 4, batch 21500, loss[loss=0.1609, simple_loss=0.2193, pruned_loss=0.05121, over 4846.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2248, pruned_loss=0.04254, over 972437.79 frames.], batch size: 30, lr: 4.45e-04
2022-05-04 23:38:08,473 INFO [train.py:715] (4/8) Epoch 4, batch 21550, loss[loss=0.1839, simple_loss=0.2442, pruned_loss=0.06178, over 4986.00 frames.], tot_loss[loss=0.155, simple_loss=0.2249, pruned_loss=0.04257, over 972857.39 frames.], batch size: 26, lr: 4.45e-04
2022-05-04 23:38:48,860 INFO [train.py:715] (4/8) Epoch 4, batch 21600, loss[loss=0.1399, simple_loss=0.2143, pruned_loss=0.03273, over 4806.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2242, pruned_loss=0.04237, over 973055.41 frames.], batch size: 14, lr: 4.45e-04
2022-05-04 23:39:28,092 INFO [train.py:715] (4/8) Epoch 4, batch 21650, loss[loss=0.1635, simple_loss=0.2417, pruned_loss=0.04264, over 4878.00 frames.], tot_loss[loss=0.1548, simple_loss=0.225, pruned_loss=0.04228, over 972155.60 frames.], batch size: 32, lr: 4.45e-04
2022-05-04 23:40:08,348 INFO [train.py:715] (4/8) Epoch 4, batch 21700, loss[loss=0.1726, simple_loss=0.2529, pruned_loss=0.04615, over 4879.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2257, pruned_loss=0.043, over 973462.55 frames.], batch size: 39, lr: 4.45e-04
2022-05-04 23:40:49,359 INFO [train.py:715] (4/8) Epoch 4, batch 21750, loss[loss=0.1479, simple_loss=0.2196, pruned_loss=0.03807, over 4978.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2254, pruned_loss=0.04298, over 972750.70 frames.], batch size: 15, lr: 4.44e-04
2022-05-04 23:41:29,008 INFO [train.py:715] (4/8) Epoch 4, batch 21800, loss[loss=0.1582, simple_loss=0.2182, pruned_loss=0.0491, over 4709.00 frames.], tot_loss[loss=0.155, simple_loss=0.2247, pruned_loss=0.04268, over 972995.06 frames.], batch size: 15, lr: 4.44e-04
2022-05-04 23:42:08,601 INFO [train.py:715] (4/8) Epoch 4, batch 21850, loss[loss=0.1326, simple_loss=0.203, pruned_loss=0.03112, over 4953.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2251, pruned_loss=0.0428, over 972739.04 frames.], batch size: 24, lr: 4.44e-04
2022-05-04 23:42:48,643 INFO [train.py:715] (4/8) Epoch 4, batch 21900, loss[loss=0.1786, simple_loss=0.2483, pruned_loss=0.05441, over 4856.00 frames.], tot_loss[loss=0.1564, simple_loss=0.226, pruned_loss=0.04339, over 971364.89 frames.], batch size: 20, lr: 4.44e-04
2022-05-04 23:43:29,089 INFO [train.py:715] (4/8) Epoch 4, batch 21950, loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.0292, over 4799.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2264, pruned_loss=0.04354, over 971202.25 frames.], batch size: 14, lr: 4.44e-04
2022-05-04 23:44:08,289 INFO [train.py:715] (4/8) Epoch 4, batch 22000, loss[loss=0.1709, simple_loss=0.2401, pruned_loss=0.0509, over 4807.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2262, pruned_loss=0.04317, over 971245.96 frames.], batch size: 21, lr: 4.44e-04
2022-05-04 23:44:48,072 INFO [train.py:715] (4/8) Epoch 4, batch 22050, loss[loss=0.1647, simple_loss=0.2391, pruned_loss=0.04519, over 4884.00 frames.], tot_loss[loss=0.156, simple_loss=0.2259, pruned_loss=0.04307, over 971246.20 frames.], batch size: 39, lr: 4.44e-04
2022-05-04 23:45:28,540 INFO [train.py:715] (4/8) Epoch 4, batch 22100, loss[loss=0.1294, simple_loss=0.2038, pruned_loss=0.02745, over 4924.00 frames.], tot_loss[loss=0.1574, simple_loss=0.227, pruned_loss=0.04394, over 971586.60 frames.], batch size: 21, lr: 4.44e-04
2022-05-04 23:46:08,383 INFO [train.py:715] (4/8) Epoch 4, batch 22150, loss[loss=0.1373, simple_loss=0.2145, pruned_loss=0.03002, over 4938.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2266, pruned_loss=0.04358, over 972214.53 frames.], batch size: 18, lr: 4.44e-04
2022-05-04 23:46:47,293 INFO [train.py:715] (4/8) Epoch 4, batch 22200, loss[loss=0.1431, simple_loss=0.2198, pruned_loss=0.03323, over 4940.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2256, pruned_loss=0.04329, over 972308.48 frames.], batch size: 29, lr: 4.44e-04
2022-05-04 23:47:27,358 INFO [train.py:715] (4/8) Epoch 4, batch 22250, loss[loss=0.1402, simple_loss=0.2106, pruned_loss=0.03487, over 4819.00 frames.], tot_loss[loss=0.156, simple_loss=0.2258, pruned_loss=0.04312, over 972880.72 frames.], batch size: 13, lr: 4.44e-04
2022-05-04 23:48:07,757 INFO [train.py:715] (4/8) Epoch 4, batch 22300, loss[loss=0.1972, simple_loss=0.2768, pruned_loss=0.05884, over 4887.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2256, pruned_loss=0.04297, over 972390.52 frames.], batch size: 16, lr: 4.44e-04
2022-05-04 23:48:46,511 INFO [train.py:715] (4/8) Epoch 4, batch 22350, loss[loss=0.188, simple_loss=0.2507, pruned_loss=0.06268, over 4984.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2259, pruned_loss=0.04291, over 972473.21 frames.], batch size: 40, lr: 4.44e-04
2022-05-04 23:49:25,541 INFO [train.py:715] (4/8) Epoch 4, batch 22400, loss[loss=0.1709, simple_loss=0.2391, pruned_loss=0.0513, over 4858.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2262, pruned_loss=0.04311, over 972496.63 frames.], batch size: 20, lr: 4.44e-04
2022-05-04 23:50:06,127 INFO [train.py:715] (4/8) Epoch 4, batch 22450, loss[loss=0.1453, simple_loss=0.2293, pruned_loss=0.03068, over 4962.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2272, pruned_loss=0.04312, over 973060.17 frames.], batch size: 24, lr: 4.44e-04
2022-05-04 23:50:45,306 INFO [train.py:715] (4/8) Epoch 4, batch 22500, loss[loss=0.1698, simple_loss=0.2456, pruned_loss=0.04702, over 4902.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2261, pruned_loss=0.04287, over 972988.05 frames.], batch size: 19, lr: 4.43e-04
2022-05-04 23:51:24,251 INFO [train.py:715] (4/8) Epoch 4, batch 22550, loss[loss=0.1361, simple_loss=0.2107, pruned_loss=0.03071, over 4942.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2256, pruned_loss=0.04289, over 973146.78 frames.], batch size: 29, lr: 4.43e-04
2022-05-04 23:52:04,194 INFO [train.py:715] (4/8) Epoch 4, batch 22600, loss[loss=0.1437, simple_loss=0.2154, pruned_loss=0.03602, over 4820.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2255, pruned_loss=0.04301, over 972868.05 frames.], batch size: 25, lr: 4.43e-04
2022-05-04 23:52:44,016 INFO [train.py:715] (4/8) Epoch 4, batch 22650, loss[loss=0.129, simple_loss=0.1946, pruned_loss=0.03172, over 4981.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2248, pruned_loss=0.04271, over 973489.05 frames.], batch size: 14, lr: 4.43e-04
2022-05-04 23:53:22,939 INFO [train.py:715] (4/8) Epoch 4, batch 22700, loss[loss=0.1943, simple_loss=0.2578, pruned_loss=0.06534, over 4958.00 frames.], tot_loss[loss=0.1565, simple_loss=0.226, pruned_loss=0.04354, over 974356.11 frames.], batch size: 39, lr: 4.43e-04
2022-05-04 23:54:02,341 INFO [train.py:715] (4/8) Epoch 4, batch 22750, loss[loss=0.1453, simple_loss=0.2161, pruned_loss=0.03729, over 4793.00 frames.], tot_loss[loss=0.1563, simple_loss=0.226, pruned_loss=0.04331, over 973830.58 frames.], batch size: 24, lr: 4.43e-04
2022-05-04 23:54:42,047 INFO [train.py:715] (4/8) Epoch 4, batch 22800, loss[loss=0.1819, simple_loss=0.2655, pruned_loss=0.04914, over 4914.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2269, pruned_loss=0.04362, over 973489.62 frames.], batch size: 18, lr: 4.43e-04
2022-05-04 23:55:21,165 INFO [train.py:715] (4/8) Epoch 4, batch 22850, loss[loss=0.1877, simple_loss=0.2594, pruned_loss=0.05807, over 4638.00 frames.], tot_loss[loss=0.1577, simple_loss=0.2273, pruned_loss=0.04405, over 973424.27 frames.], batch size: 13, lr: 4.43e-04
2022-05-04 23:55:59,896 INFO [train.py:715] (4/8) Epoch 4, batch 22900, loss[loss=0.1817, simple_loss=0.2437, pruned_loss=0.05984, over 4871.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2273, pruned_loss=0.04419, over 973130.85 frames.], batch size: 32, lr: 4.43e-04
2022-05-04 23:56:39,563 INFO [train.py:715] (4/8) Epoch 4, batch 22950, loss[loss=0.1595, simple_loss=0.2146, pruned_loss=0.05216, over 4675.00 frames.], tot_loss[loss=0.1579, simple_loss=0.2274, pruned_loss=0.0442, over 972431.68 frames.], batch size: 13, lr: 4.43e-04
2022-05-04 23:57:19,675 INFO [train.py:715] (4/8) Epoch 4, batch 23000, loss[loss=0.1467, simple_loss=0.2132, pruned_loss=0.04008, over 4967.00 frames.], tot_loss[loss=0.1572, simple_loss=0.227, pruned_loss=0.04369, over 973287.54 frames.], batch size: 24, lr: 4.43e-04
2022-05-04 23:57:58,010 INFO [train.py:715] (4/8) Epoch 4, batch 23050, loss[loss=0.196, simple_loss=0.2501, pruned_loss=0.07095, over 4803.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2268, pruned_loss=0.0434, over 973959.10 frames.], batch size: 17, lr: 4.43e-04
2022-05-04 23:58:37,653 INFO [train.py:715] (4/8) Epoch 4, batch 23100, loss[loss=0.1895, simple_loss=0.2516, pruned_loss=0.06374, over 4966.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2275, pruned_loss=0.0439, over 973363.75 frames.], batch size: 35, lr: 4.43e-04
2022-05-04 23:59:18,002 INFO [train.py:715] (4/8) Epoch 4, batch 23150, loss[loss=0.1347, simple_loss=0.2038, pruned_loss=0.03277, over 4721.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2269, pruned_loss=0.04372, over 973603.30 frames.], batch size: 16, lr: 4.43e-04
2022-05-04 23:59:57,817 INFO [train.py:715] (4/8) Epoch 4, batch 23200, loss[loss=0.1486, simple_loss=0.2271, pruned_loss=0.03505, over 4916.00 frames.], tot_loss[loss=0.1574, simple_loss=0.227, pruned_loss=0.04392, over 972795.39 frames.], batch size: 19, lr: 4.42e-04
2022-05-05 00:00:36,520 INFO [train.py:715] (4/8) Epoch 4, batch 23250, loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02903, over 4947.00 frames.], tot_loss[loss=0.158, simple_loss=0.2277, pruned_loss=0.04419, over 973199.54 frames.], batch size: 21, lr: 4.42e-04
2022-05-05 00:01:16,397 INFO [train.py:715] (4/8) Epoch 4, batch 23300, loss[loss=0.1628, simple_loss=0.2281, pruned_loss=0.04875, over 4970.00 frames.], tot_loss[loss=0.1581, simple_loss=0.2275, pruned_loss=0.04433, over 973197.64 frames.], batch size: 35, lr: 4.42e-04
2022-05-05 00:01:56,690 INFO [train.py:715] (4/8) Epoch 4, batch 23350, loss[loss=0.1492, simple_loss=0.2153, pruned_loss=0.04157, over 4789.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2268, pruned_loss=0.04378, over 972808.94 frames.], batch size: 21, lr: 4.42e-04
2022-05-05 00:02:35,077 INFO [train.py:715] (4/8) Epoch 4, batch 23400, loss[loss=0.1198, simple_loss=0.1933, pruned_loss=0.02312, over 4871.00 frames.], tot_loss[loss=0.1575, simple_loss=0.227, pruned_loss=0.04395, over 972395.76 frames.], batch size: 16, lr: 4.42e-04
2022-05-05 00:03:14,411 INFO [train.py:715] (4/8) Epoch 4, batch 23450, loss[loss=0.1374, simple_loss=0.2041, pruned_loss=0.03532, over 4808.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2261, pruned_loss=0.04345, over 971861.36 frames.], batch size: 21, lr: 4.42e-04
2022-05-05 00:03:55,002 INFO [train.py:715] (4/8) Epoch 4, batch 23500, loss[loss=0.1508, simple_loss=0.2272, pruned_loss=0.03723, over 4741.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2262, pruned_loss=0.04379, over 971779.12 frames.], batch size: 16, lr: 4.42e-04
2022-05-05 00:04:33,369 INFO [train.py:715] (4/8) Epoch 4, batch 23550, loss[loss=0.1745, simple_loss=0.243, pruned_loss=0.05305, over 4946.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2259, pruned_loss=0.04328, over 972400.95 frames.], batch size: 29, lr: 4.42e-04
2022-05-05 00:05:12,655 INFO [train.py:715] (4/8) Epoch 4, batch 23600, loss[loss=0.1272, simple_loss=0.2059, pruned_loss=0.02426, over 4917.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2258, pruned_loss=0.04298, over 972037.10 frames.], batch size: 23, lr: 4.42e-04
2022-05-05 00:05:53,466 INFO [train.py:715] (4/8) Epoch 4, batch 23650, loss[loss=0.1356, simple_loss=0.2126, pruned_loss=0.02929, over 4980.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2265, pruned_loss=0.04336, over 972242.96 frames.], batch size: 25, lr: 4.42e-04
2022-05-05 00:06:34,877 INFO [train.py:715] (4/8) Epoch 4, batch 23700, loss[loss=0.1547, simple_loss=0.2266, pruned_loss=0.04135, over 4982.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2273, pruned_loss=0.0438, over 973621.91 frames.], batch size: 35, lr: 4.42e-04
2022-05-05 00:07:14,385 INFO [train.py:715] (4/8) Epoch 4, batch 23750, loss[loss=0.178, simple_loss=0.2252, pruned_loss=0.06538, over 4907.00 frames.], tot_loss[loss=0.1586, simple_loss=0.2282, pruned_loss=0.04448, over 973964.61 frames.], batch size: 17, lr: 4.42e-04
2022-05-05 00:07:53,794 INFO [train.py:715] (4/8) Epoch 4, batch 23800, loss[loss=0.1756, simple_loss=0.2388, pruned_loss=0.05619, over 4921.00 frames.], tot_loss[loss=0.1584, simple_loss=0.2278, pruned_loss=0.04452, over 973849.31 frames.], batch size: 29, lr: 4.42e-04
2022-05-05 00:08:34,394 INFO [train.py:715] (4/8) Epoch 4, batch 23850, loss[loss=0.1857, simple_loss=0.2495, pruned_loss=0.06094, over 4830.00 frames.], tot_loss[loss=0.1587, simple_loss=0.2281, pruned_loss=0.04465, over 973540.61 frames.], batch size: 15, lr: 4.42e-04
2022-05-05 00:09:13,910 INFO [train.py:715] (4/8) Epoch 4, batch 23900, loss[loss=0.1462, simple_loss=0.2139, pruned_loss=0.03929, over 4967.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2268, pruned_loss=0.04391, over 973123.77 frames.], batch size: 14, lr: 4.42e-04
2022-05-05 00:09:53,726 INFO [train.py:715] (4/8) Epoch 4, batch 23950, loss[loss=0.18, simple_loss=0.2523, pruned_loss=0.05388, over 4784.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2267, pruned_loss=0.04395, over 973144.63 frames.], batch size: 14, lr: 4.41e-04
2022-05-05 00:10:34,512 INFO [train.py:715] (4/8) Epoch 4, batch 24000, loss[loss=0.1694, simple_loss=0.2368, pruned_loss=0.05097, over 4923.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2261, pruned_loss=0.04356, over 973596.59 frames.], batch size: 19, lr: 4.41e-04
2022-05-05 00:10:34,513 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 00:10:44,331 INFO [train.py:742] (4/8) Epoch 4, validation: loss=0.1115, simple_loss=0.1974, pruned_loss=0.01276, over 914524.00 frames.
2022-05-05 00:11:25,486 INFO [train.py:715] (4/8) Epoch 4, batch 24050, loss[loss=0.1342, simple_loss=0.2119, pruned_loss=0.02824, over 4957.00 frames.], tot_loss[loss=0.157, simple_loss=0.2264, pruned_loss=0.04379, over 974268.15 frames.], batch size: 35, lr: 4.41e-04
2022-05-05 00:12:06,055 INFO [train.py:715] (4/8) Epoch 4, batch 24100, loss[loss=0.1493, simple_loss=0.2277, pruned_loss=0.03546, over 4816.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2269, pruned_loss=0.04363, over 974184.49 frames.], batch size: 27, lr: 4.41e-04
2022-05-05 00:12:45,924 INFO [train.py:715] (4/8) Epoch 4, batch 24150, loss[loss=0.1374, simple_loss=0.223, pruned_loss=0.02589, over 4828.00 frames.], tot_loss[loss=0.156, simple_loss=0.2262, pruned_loss=0.04287, over 974191.07 frames.], batch size: 25, lr: 4.41e-04
2022-05-05 00:13:25,915 INFO [train.py:715] (4/8) Epoch 4, batch 24200, loss[loss=0.1339, simple_loss=0.2059, pruned_loss=0.03098, over 4950.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2265, pruned_loss=0.04319, over 974050.76 frames.], batch size: 29, lr: 4.41e-04
2022-05-05 00:14:07,335 INFO [train.py:715] (4/8) Epoch 4, batch 24250, loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03019, over 4899.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2255, pruned_loss=0.0425, over 973242.91 frames.], batch size: 17, lr: 4.41e-04
2022-05-05 00:14:46,255 INFO [train.py:715] (4/8) Epoch 4, batch 24300, loss[loss=0.1449, simple_loss=0.2039, pruned_loss=0.04292, over 4752.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2254, pruned_loss=0.04243, over 972718.30 frames.], batch size: 19, lr: 4.41e-04
2022-05-05 00:15:26,712 INFO [train.py:715] (4/8) Epoch 4, batch 24350, loss[loss=0.1461, simple_loss=0.2162, pruned_loss=0.03801, over 4762.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2253, pruned_loss=0.04287, over 972075.56 frames.], batch size: 19, lr: 4.41e-04
2022-05-05 00:16:07,661 INFO [train.py:715] (4/8) Epoch 4, batch 24400, loss[loss=0.1411, simple_loss=0.2228, pruned_loss=0.02977, over 4870.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2262, pruned_loss=0.0431, over 972527.81 frames.], batch size: 16, lr: 4.41e-04
2022-05-05 00:16:47,241 INFO [train.py:715] (4/8) Epoch 4, batch 24450, loss[loss=0.1428, simple_loss=0.2169, pruned_loss=0.03432, over 4919.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2266, pruned_loss=0.0435, over 972539.18 frames.], batch size: 18, lr: 4.41e-04
2022-05-05 00:17:27,007 INFO [train.py:715] (4/8) Epoch 4, batch 24500, loss[loss=0.1164, simple_loss=0.1916, pruned_loss=0.02064, over 4869.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2255, pruned_loss=0.0429, over 972542.55 frames.], batch size: 20, lr: 4.41e-04
2022-05-05 00:18:06,875 INFO [train.py:715] (4/8) Epoch 4, batch 24550, loss[loss=0.1558, simple_loss=0.2281, pruned_loss=0.04177, over 4853.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2243, pruned_loss=0.04229, over 971762.68 frames.], batch size: 32, lr: 4.41e-04
2022-05-05 00:18:48,115 INFO [train.py:715] (4/8) Epoch 4, batch 24600, loss[loss=0.1617, simple_loss=0.2253, pruned_loss=0.04911, over 4776.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2245, pruned_loss=0.04246, over 971061.93 frames.], batch size: 14, lr: 4.41e-04
2022-05-05 00:19:27,460 INFO [train.py:715] (4/8) Epoch 4, batch 24650, loss[loss=0.1419, simple_loss=0.2123, pruned_loss=0.03574, over 4934.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2246, pruned_loss=0.04315, over 971359.14 frames.], batch size: 18, lr: 4.41e-04
2022-05-05 00:20:08,194 INFO [train.py:715] (4/8) Epoch 4, batch 24700, loss[loss=0.1315, simple_loss=0.2091, pruned_loss=0.02698, over 4821.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2252, pruned_loss=0.04318, over 971515.28 frames.], batch size: 26, lr: 4.40e-04
2022-05-05 00:20:49,273 INFO [train.py:715] (4/8) Epoch 4, batch 24750, loss[loss=0.1591, simple_loss=0.2233, pruned_loss=0.04741, over 4931.00 frames.], tot_loss[loss=0.1556, simple_loss=0.225, pruned_loss=0.04315, over 971028.61 frames.], batch size: 39, lr: 4.40e-04
2022-05-05 00:21:28,792 INFO [train.py:715] (4/8) Epoch 4, batch 24800, loss[loss=0.1414, simple_loss=0.2141, pruned_loss=0.03431, over 4778.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2247, pruned_loss=0.04289, over 970909.29 frames.], batch size: 17, lr: 4.40e-04
2022-05-05 00:22:08,801 INFO [train.py:715] (4/8) Epoch 4, batch 24850, loss[loss=0.1362, simple_loss=0.2033, pruned_loss=0.03453, over 4833.00 frames.], tot_loss[loss=0.155, simple_loss=0.2246, pruned_loss=0.04265, over 970936.69 frames.], batch size: 13, lr: 4.40e-04
2022-05-05 00:22:49,032 INFO [train.py:715] (4/8) Epoch 4, batch 24900, loss[loss=0.1375, simple_loss=0.2083, pruned_loss=0.03329, over 4956.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2247, pruned_loss=0.04282, over 971692.65 frames.], batch size: 35, lr: 4.40e-04
2022-05-05 00:23:30,186 INFO [train.py:715] (4/8) Epoch 4, batch 24950, loss[loss=0.1337, simple_loss=0.2049, pruned_loss=0.03128, over 4910.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2248, pruned_loss=0.04284, over 971867.72 frames.], batch size: 17, lr: 4.40e-04
2022-05-05 00:24:09,090 INFO [train.py:715] (4/8) Epoch 4, batch 25000, loss[loss=0.1618, simple_loss=0.2295, pruned_loss=0.04701, over 4802.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2249, pruned_loss=0.04276, over 971877.63 frames.], batch size: 25, lr: 4.40e-04
2022-05-05 00:24:49,347 INFO [train.py:715] (4/8) Epoch 4, batch 25050, loss[loss=0.1306, simple_loss=0.2092, pruned_loss=0.02595, over 4899.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2254, pruned_loss=0.04309, over 972397.78 frames.], batch size: 19, lr: 4.40e-04
2022-05-05 00:25:30,443 INFO [train.py:715] (4/8) Epoch 4, batch 25100, loss[loss=0.14, simple_loss=0.2002, pruned_loss=0.0399, over 4846.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2254, pruned_loss=0.04322, over 972748.62 frames.], batch size: 13, lr: 4.40e-04
2022-05-05 00:26:10,368 INFO [train.py:715] (4/8) Epoch 4, batch 25150, loss[loss=0.1796, simple_loss=0.2426, pruned_loss=0.05833, over 4838.00 frames.], tot_loss[loss=0.1565, simple_loss=0.226, pruned_loss=0.04352, over 972973.66 frames.], batch size: 15, lr: 4.40e-04
2022-05-05 00:26:49,787 INFO [train.py:715] (4/8) Epoch 4, batch 25200, loss[loss=0.1346, simple_loss=0.2143, pruned_loss=0.02744, over 4991.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2258, pruned_loss=0.0433, over 973221.68 frames.], batch size: 20, lr: 4.40e-04
2022-05-05 00:27:30,056 INFO [train.py:715] (4/8) Epoch 4, batch 25250, loss[loss=0.1489, simple_loss=0.2146, pruned_loss=0.04156, over 4742.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2241, pruned_loss=0.04215, over 973000.25 frames.], batch size: 16, lr: 4.40e-04
2022-05-05 00:28:10,080 INFO [train.py:715] (4/8) Epoch 4, batch 25300, loss[loss=0.1312, simple_loss=0.2043, pruned_loss=0.02908, over 4801.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2227, pruned_loss=0.04156, over 972910.56 frames.], batch size: 24, lr: 4.40e-04
2022-05-05 00:28:47,882 INFO [train.py:715] (4/8) Epoch 4, batch 25350, loss[loss=0.1441, simple_loss=0.2103, pruned_loss=0.03894, over 4897.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2239, pruned_loss=0.04222, over 973300.01 frames.], batch size: 17, lr: 4.40e-04
2022-05-05 00:29:26,724 INFO [train.py:715] (4/8) Epoch 4, batch 25400, loss[loss=0.1284, simple_loss=0.2073, pruned_loss=0.02478, over 4738.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2248, pruned_loss=0.04291, over 972894.78 frames.], batch size: 16, lr: 4.40e-04
2022-05-05 00:30:06,395 INFO [train.py:715] (4/8) Epoch 4, batch 25450, loss[loss=0.1413, simple_loss=0.2144, pruned_loss=0.03405, over 4853.00 frames.], tot_loss[loss=0.156, simple_loss=0.2255, pruned_loss=0.04324, over 972300.32 frames.], batch size: 32, lr: 4.39e-04
2022-05-05 00:30:45,456 INFO [train.py:715] (4/8) Epoch 4, batch 25500, loss[loss=0.1218, simple_loss=0.2038, pruned_loss=0.01987, over 4805.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2259, pruned_loss=0.04355, over 971709.24 frames.], batch size: 25, lr: 4.39e-04
2022-05-05 00:31:25,317 INFO [train.py:715] (4/8) Epoch 4, batch 25550, loss[loss=0.1477, simple_loss=0.2115, pruned_loss=0.04197, over 4955.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2262, pruned_loss=0.04369, over 971759.64 frames.], batch size: 15, lr: 4.39e-04
2022-05-05 00:32:05,292 INFO [train.py:715] (4/8) Epoch 4, batch 25600, loss[loss=0.1603, simple_loss=0.2343, pruned_loss=0.04316, over 4771.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2267, pruned_loss=0.04371, over 971953.65 frames.], batch size: 17, lr: 4.39e-04
2022-05-05 00:32:45,562 INFO [train.py:715] (4/8) Epoch 4, batch 25650, loss[loss=0.1472, simple_loss=0.2143, pruned_loss=0.04007, over 4807.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2268, pruned_loss=0.0439, over 972550.61 frames.], batch size: 27, lr: 4.39e-04
2022-05-05 00:33:24,673 INFO [train.py:715] (4/8) Epoch 4, batch 25700, loss[loss=0.1385, simple_loss=0.2133, pruned_loss=0.03183, over 4822.00 frames.], tot_loss[loss=0.157, simple_loss=0.2264, pruned_loss=0.04376, over 972685.18 frames.], batch size: 15, lr: 4.39e-04
2022-05-05 00:34:04,657 INFO [train.py:715] (4/8) Epoch 4, batch 25750, loss[loss=0.1372, simple_loss=0.1994, pruned_loss=0.03749, over 4777.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2267, pruned_loss=0.04395, over 971871.21 frames.], batch size: 12, lr: 4.39e-04
2022-05-05 00:34:45,101 INFO [train.py:715] (4/8) Epoch 4, batch 25800, loss[loss=0.145, simple_loss=0.2093, pruned_loss=0.04036, over 4819.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2267, pruned_loss=0.04387, over 971898.39 frames.], batch size: 15, lr: 4.39e-04
2022-05-05 00:35:24,455 INFO [train.py:715] (4/8) Epoch 4, batch 25850, loss[loss=0.1578, simple_loss=0.2333, pruned_loss=0.04114, over 4780.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2269, pruned_loss=0.04407, over 971498.87 frames.], batch size: 14, lr: 4.39e-04
2022-05-05 00:36:03,599 INFO [train.py:715] (4/8) Epoch 4, batch 25900, loss[loss=0.1655, simple_loss=0.2378, pruned_loss=0.04663, over 4978.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2263, pruned_loss=0.04368, over 971686.12 frames.], batch size: 39, lr: 4.39e-04
2022-05-05 00:36:43,843 INFO [train.py:715] (4/8) Epoch 4, batch 25950, loss[loss=0.1766, simple_loss=0.2461, pruned_loss=0.05357, over 4861.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2266, pruned_loss=0.04388, over 970424.30 frames.], batch size: 20, lr: 4.39e-04
2022-05-05 00:37:24,110 INFO [train.py:715] (4/8) Epoch 4, batch 26000, loss[loss=0.1416, simple_loss=0.2112, pruned_loss=0.03599, over 4847.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2264, pruned_loss=0.04352, over 970865.91 frames.], batch size: 32, lr: 4.39e-04
2022-05-05 00:38:02,818 INFO [train.py:715] (4/8) Epoch 4, batch 26050, loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.0291, over 4780.00 frames.], tot_loss[loss=0.1577, simple_loss=0.227, pruned_loss=0.04416, over 970939.65 frames.], batch size: 14, lr: 4.39e-04
2022-05-05 00:38:42,225 INFO [train.py:715] (4/8) Epoch 4, batch 26100, loss[loss=0.1765, simple_loss=0.249, pruned_loss=0.05205, over 4700.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2263, pruned_loss=0.04368, over 970649.40 frames.], batch size: 15, lr: 4.39e-04
2022-05-05 00:39:22,680 INFO [train.py:715] (4/8) Epoch 4, batch 26150, loss[loss=0.1753, simple_loss=0.2347, pruned_loss=0.05798, over 4770.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2263, pruned_loss=0.04352, over 970386.45 frames.], batch size: 19, lr: 4.39e-04
2022-05-05 00:40:01,757 INFO [train.py:715] (4/8) Epoch 4, batch 26200, loss[loss=0.1325, simple_loss=0.2103, pruned_loss=0.02732, over 4898.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2259, pruned_loss=0.04315, over 970856.12 frames.], batch size: 19, lr: 4.38e-04
2022-05-05 00:40:41,521 INFO [train.py:715] (4/8) Epoch 4, batch 26250, loss[loss=0.146, simple_loss=0.2156, pruned_loss=0.03822, over 4916.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2257, pruned_loss=0.04304, over 970817.50 frames.], batch size: 23, lr: 4.38e-04
2022-05-05 00:41:21,387 INFO [train.py:715] (4/8) Epoch 4, batch 26300, loss[loss=0.1358, simple_loss=0.2102, pruned_loss=0.03066, over 4782.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2255, pruned_loss=0.04281, over 971036.25 frames.], batch size: 17, lr: 4.38e-04
2022-05-05 00:42:01,534 INFO [train.py:715] (4/8) Epoch 4, batch 26350, loss[loss=0.1297, simple_loss=0.1969, pruned_loss=0.03125, over 4753.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2247, pruned_loss=0.04225, over 970743.21 frames.], batch size: 12, lr: 4.38e-04
2022-05-05 00:42:40,874 INFO [train.py:715] (4/8) Epoch 4, batch 26400, loss[loss=0.1603, simple_loss=0.229, pruned_loss=0.04581, over 4798.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2262, pruned_loss=0.04367, over 970362.25 frames.], batch size: 21, lr: 4.38e-04
2022-05-05 00:43:20,962 INFO [train.py:715] (4/8) Epoch 4, batch 26450, loss[loss=0.1266, simple_loss=0.1881, pruned_loss=0.03257, over 4977.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2263, pruned_loss=0.0438, over 970811.27 frames.], batch size: 15, lr: 4.38e-04
2022-05-05 00:44:01,485 INFO [train.py:715] (4/8) Epoch 4, batch 26500, loss[loss=0.1779, simple_loss=0.2422, pruned_loss=0.05682, over 4859.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2259, pruned_loss=0.04346, over 971230.54 frames.], batch size: 20, lr: 4.38e-04
2022-05-05 00:44:40,386 INFO [train.py:715] (4/8) Epoch 4, batch 26550, loss[loss=0.169, simple_loss=0.2295, pruned_loss=0.05421, over 4756.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2252, pruned_loss=0.04294, over 971504.97 frames.], batch size: 16, lr: 4.38e-04
2022-05-05 00:45:20,029 INFO [train.py:715] (4/8) Epoch 4, batch 26600, loss[loss=0.1779, simple_loss=0.2467, pruned_loss=0.05452, over 4916.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2253, pruned_loss=0.0431, over 972129.97 frames.], batch size: 17, lr: 4.38e-04
2022-05-05 00:46:00,417 INFO [train.py:715] (4/8) Epoch 4, batch 26650, loss[loss=0.1525, simple_loss=0.2287, pruned_loss=0.0382, over 4819.00 frames.], tot_loss[loss=0.1566, simple_loss=0.226, pruned_loss=0.04359, over 971874.33 frames.], batch size: 26, lr: 4.38e-04
2022-05-05 00:46:41,230 INFO [train.py:715] (4/8) Epoch 4, batch 26700, loss[loss=0.15, simple_loss=0.2184, pruned_loss=0.04082, over 4990.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2257, pruned_loss=0.04325, over 971981.94 frames.], batch size: 14, lr: 4.38e-04
2022-05-05 00:47:20,021 INFO [train.py:715] (4/8) Epoch 4, batch 26750, loss[loss=0.1273, simple_loss=0.2087, pruned_loss=0.02297, over 4936.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2251, pruned_loss=0.04272, over 971716.51 frames.], batch size: 21, lr: 4.38e-04
2022-05-05 00:47:59,595 INFO [train.py:715] (4/8) Epoch 4, batch 26800, loss[loss=0.1504, simple_loss=0.2232, pruned_loss=0.03881, over 4924.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2267, pruned_loss=0.04357, over 972744.02 frames.], batch size: 23, lr: 4.38e-04
2022-05-05 00:48:39,807 INFO [train.py:715] (4/8) Epoch 4, batch 26850, loss[loss=0.1419, simple_loss=0.2106, pruned_loss=0.0366, over 4849.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2255, pruned_loss=0.04286, over 973238.66 frames.], batch size: 34, lr: 4.38e-04
2022-05-05 00:49:18,739 INFO [train.py:715] (4/8) Epoch 4, batch 26900, loss[loss=0.2018, simple_loss=0.2645, pruned_loss=0.06951, over 4752.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2255, pruned_loss=0.04283, over 972741.79 frames.], batch size: 16, lr: 4.38e-04
2022-05-05 00:49:58,559 INFO [train.py:715] (4/8) Epoch 4, batch 26950, loss[loss=0.1833, simple_loss=0.2394, pruned_loss=0.06365, over 4911.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2252, pruned_loss=0.04281, over 972336.74 frames.], batch size: 39, lr: 4.37e-04
2022-05-05 00:50:38,533 INFO [train.py:715] (4/8) Epoch 4, batch 27000, loss[loss=0.1586, simple_loss=0.2389, pruned_loss=0.03917, over 4818.00 frames.], tot_loss[loss=0.1561, simple_loss=0.226, pruned_loss=0.04305, over 972521.35 frames.], batch size: 25, lr: 4.37e-04
2022-05-05 00:50:38,534 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 00:50:48,690 INFO [train.py:742] (4/8) Epoch 4, validation: loss=0.1114, simple_loss=0.197, pruned_loss=0.01284, over 914524.00 frames.
2022-05-05 00:51:28,849 INFO [train.py:715] (4/8) Epoch 4, batch 27050, loss[loss=0.1498, simple_loss=0.2267, pruned_loss=0.03647, over 4880.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2255, pruned_loss=0.04304, over 972763.27 frames.], batch size: 30, lr: 4.37e-04
2022-05-05 00:52:08,421 INFO [train.py:715] (4/8) Epoch 4, batch 27100, loss[loss=0.1492, simple_loss=0.2229, pruned_loss=0.03774, over 4789.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2264, pruned_loss=0.04328, over 972160.21 frames.], batch size: 12, lr: 4.37e-04
2022-05-05 00:52:47,743 INFO [train.py:715] (4/8) Epoch 4, batch 27150, loss[loss=0.1891, simple_loss=0.2392, pruned_loss=0.06947, over 4931.00 frames.], tot_loss[loss=0.1573, simple_loss=0.2269, pruned_loss=0.04391, over 972269.88 frames.], batch size: 35, lr: 4.37e-04
2022-05-05 00:53:27,407 INFO [train.py:715] (4/8) Epoch 4, batch 27200, loss[loss=0.1995, simple_loss=0.2564, pruned_loss=0.07125, over 4977.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2267, pruned_loss=0.04389, over 973460.27 frames.], batch size: 31, lr: 4.37e-04
2022-05-05 00:54:07,870 INFO [train.py:715] (4/8) Epoch 4, batch 27250, loss[loss=0.1478, simple_loss=0.2151, pruned_loss=0.04029, over 4819.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2259, pruned_loss=0.0435, over 972986.90 frames.], batch size: 27, lr: 4.37e-04
2022-05-05 00:54:46,634 INFO [train.py:715] (4/8) Epoch 4, batch 27300, loss[loss=0.1486, simple_loss=0.2204, pruned_loss=0.03836, over 4895.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2255, pruned_loss=0.04316, over 972923.05 frames.], batch size: 22, lr: 4.37e-04
2022-05-05 00:55:26,631 INFO [train.py:715] (4/8) Epoch 4, batch 27350, loss[loss=0.1463, simple_loss=0.2214, pruned_loss=0.03564, over 4840.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2253, pruned_loss=0.04304, over 972755.58 frames.], batch size: 20, lr: 4.37e-04
2022-05-05 00:56:06,583 INFO [train.py:715] (4/8) Epoch 4, batch 27400, loss[loss=0.1543, simple_loss=0.2359, pruned_loss=0.03632, over 4818.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2253, pruned_loss=0.04295, over 972780.69 frames.], batch size: 25, lr: 4.37e-04
2022-05-05 00:56:45,007 INFO [train.py:715] (4/8) Epoch 4, batch 27450, loss[loss=0.131, simple_loss=0.2002, pruned_loss=0.03094, over 4747.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2251, pruned_loss=0.04306, over 972636.72 frames.], batch size: 19, lr: 4.37e-04
2022-05-05 00:57:24,954 INFO [train.py:715] (4/8) Epoch 4, batch 27500, loss[loss=0.1269, simple_loss=0.2061, pruned_loss=0.02385, over 4927.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2254, pruned_loss=0.04348, over 972137.08 frames.], batch size: 21, lr: 4.37e-04
2022-05-05 00:58:03,977 INFO [train.py:715] (4/8) Epoch 4, batch 27550, loss[loss=0.1965, simple_loss=0.2611, pruned_loss=0.066, over 4819.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2268, pruned_loss=0.04406, over 972811.73 frames.], batch size: 15, lr: 4.37e-04
2022-05-05 00:58:43,889 INFO [train.py:715] (4/8) Epoch 4, batch 27600, loss[loss=0.1488, simple_loss=0.2196, pruned_loss=0.03903, over 4753.00 frames.], tot_loss[loss=0.1572, simple_loss=0.2268, pruned_loss=0.0438, over 972246.86 frames.], batch size: 19, lr: 4.37e-04
2022-05-05 00:59:22,450 INFO [train.py:715] (4/8) Epoch 4, batch 27650, loss[loss=0.1432, simple_loss=0.2226, pruned_loss=0.03184, over 4949.00 frames.], tot_loss[loss=0.1574, simple_loss=0.2272, pruned_loss=0.04376, over 972422.41 frames.], batch size: 14, lr: 4.37e-04
2022-05-05 01:00:01,781 INFO [train.py:715] (4/8) Epoch 4, batch 27700, loss[loss=0.1283, simple_loss=0.209, pruned_loss=0.02383, over 4823.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2258, pruned_loss=0.04285, over 972620.40 frames.], batch size: 26, lr: 4.36e-04
2022-05-05 01:00:41,403 INFO [train.py:715] (4/8) Epoch 4, batch 27750, loss[loss=0.145, simple_loss=0.213, pruned_loss=0.03848, over 4775.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2255, pruned_loss=0.04258, over 973123.83 frames.], batch size: 18, lr: 4.36e-04
2022-05-05 01:01:20,721 INFO [train.py:715] (4/8) Epoch 4, batch 27800, loss[loss=0.1274, simple_loss=0.1976, pruned_loss=0.02859, over 4985.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2258, pruned_loss=0.04261, over 971678.77 frames.], batch size: 25, lr: 4.36e-04
2022-05-05 01:01:59,771 INFO [train.py:715] (4/8) Epoch 4, batch 27850, loss[loss=0.1296, simple_loss=0.1976, pruned_loss=0.03081, over 4791.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2255, pruned_loss=0.04263, over 972127.47 frames.], batch size: 14, lr: 4.36e-04
2022-05-05 01:02:38,862 INFO [train.py:715] (4/8) Epoch 4, batch 27900, loss[loss=0.1596, simple_loss=0.2344, pruned_loss=0.04243, over 4918.00 frames.], tot_loss[loss=0.1562, simple_loss=0.2262, pruned_loss=0.04312, over 971299.08 frames.], batch size: 39, lr: 4.36e-04
2022-05-05 01:03:18,311 INFO [train.py:715] (4/8) Epoch 4, batch 27950, loss[loss=0.1496, simple_loss=0.2077, pruned_loss=0.04577, over 4781.00 frames.], tot_loss[loss=0.1562, simple_loss=0.226, pruned_loss=0.04315, over 971496.70 frames.], batch size: 14, lr: 4.36e-04
2022-05-05 01:03:57,878 INFO [train.py:715] (4/8) Epoch 4, batch 28000, loss[loss=0.1411, simple_loss=0.2167, pruned_loss=0.03271, over 4804.00 frames.], tot_loss[loss=0.156, simple_loss=0.2255, pruned_loss=0.04325, over 971481.98 frames.], batch size: 18, lr: 4.36e-04
2022-05-05 01:04:37,837 INFO [train.py:715] (4/8) Epoch 4, batch 28050, loss[loss=0.1395, simple_loss=0.216, pruned_loss=0.03154, over 4750.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2256, pruned_loss=0.04303, over 971351.04 frames.], batch size: 19, lr: 4.36e-04
2022-05-05 01:05:17,719 INFO [train.py:715] (4/8) Epoch 4, batch 28100, loss[loss=0.1754, simple_loss=0.2357, pruned_loss=0.05759, over 4694.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2257, pruned_loss=0.04344, over 971284.67 frames.], batch size: 15, lr: 4.36e-04
2022-05-05 01:05:57,312 INFO [train.py:715] (4/8) Epoch 4, batch 28150, loss[loss=0.1587, simple_loss=0.2257, pruned_loss=0.04581, over 4875.00 frames.], tot_loss[loss=0.1578, simple_loss=0.2271, pruned_loss=0.0442, over 971090.16 frames.], batch size: 19, lr: 4.36e-04
2022-05-05 01:06:36,803 INFO [train.py:715] (4/8) Epoch 4, batch 28200, loss[loss=0.1397, simple_loss=0.215, pruned_loss=0.03216, over 4795.00 frames.], tot_loss[loss=0.1576, simple_loss=0.2268, pruned_loss=0.04423, over 972670.02 frames.], batch size: 14, lr: 4.36e-04
2022-05-05 01:07:15,869 INFO [train.py:715] (4/8) Epoch 4, batch 28250, loss[loss=0.1311, simple_loss=0.2014, pruned_loss=0.03039, over 4904.00 frames.], tot_loss[loss=0.157, simple_loss=0.2261, pruned_loss=0.04396, over 972729.29 frames.], batch size: 18, lr: 4.36e-04
2022-05-05 01:07:55,427 INFO [train.py:715] (4/8) Epoch 4, batch 28300, loss[loss=0.1507, simple_loss=0.235, pruned_loss=0.03319, over 4774.00 frames.], tot_loss[loss=0.1571, simple_loss=0.2262, pruned_loss=0.04403, over 972650.68 frames.], batch size: 18, lr: 4.36e-04
2022-05-05 01:08:34,754 INFO [train.py:715] (4/8) Epoch 4, batch 28350, loss[loss=0.1281, simple_loss=0.2112, pruned_loss=0.02251, over 4957.00 frames.], tot_loss[loss=0.1569, simple_loss=0.2259, pruned_loss=0.04395, over 973414.41 frames.], batch size: 24, lr: 4.36e-04
2022-05-05 01:09:14,656 INFO [train.py:715] (4/8) Epoch 4, batch 28400, loss[loss=0.1566, simple_loss=0.2294, pruned_loss=0.04195, over 4819.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2257, pruned_loss=0.04365, over 973449.99 frames.], batch size: 25, lr: 4.36e-04
2022-05-05 01:09:53,871 INFO [train.py:715] (4/8) Epoch 4, batch 28450, loss[loss=0.1414, simple_loss=0.2161, pruned_loss=0.03338, over 4927.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2254, pruned_loss=0.04356, over 973541.96 frames.], batch size: 23, lr: 4.36e-04
2022-05-05 01:10:32,528 INFO [train.py:715] (4/8) Epoch 4, batch 28500, loss[loss=0.1654, simple_loss=0.2317, pruned_loss=0.04954, over 4807.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2255, pruned_loss=0.04308, over 972882.98 frames.], batch size: 13, lr: 4.35e-04
2022-05-05 01:11:12,039 INFO [train.py:715] (4/8) Epoch 4, batch 28550, loss[loss=0.1757, simple_loss=0.2584, pruned_loss=0.04646, over 4789.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2251, pruned_loss=0.04281, over 972716.17 frames.], batch size: 17, lr: 4.35e-04
2022-05-05 01:11:51,206 INFO [train.py:715] (4/8) Epoch 4, batch 28600, loss[loss=0.1665, simple_loss=0.2289, pruned_loss=0.05202, over 4784.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2247, pruned_loss=0.04275, over 971966.06 frames.], batch size: 14, lr: 4.35e-04
2022-05-05 01:12:30,864 INFO [train.py:715] (4/8) Epoch 4, batch 28650, loss[loss=0.1271, simple_loss=0.2074, pruned_loss=0.02334, over 4942.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2253, pruned_loss=0.04296, over 972459.94 frames.], batch size: 29, lr: 4.35e-04
2022-05-05 01:13:10,039 INFO [train.py:715] (4/8) Epoch 4, batch 28700, loss[loss=0.1348, simple_loss=0.2121, pruned_loss=0.02869, over 4792.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2256, pruned_loss=0.04285, over 972139.58 frames.], batch size: 21, lr: 4.35e-04
2022-05-05 01:13:49,556 INFO [train.py:715] (4/8) Epoch 4, batch 28750, loss[loss=0.1727, simple_loss=0.2376, pruned_loss=0.05386, over 4798.00 frames.], tot_loss[loss=0.1557, simple_loss=0.225, pruned_loss=0.04317, over 971816.55 frames.], batch size: 21, lr: 4.35e-04
2022-05-05 01:14:31,713 INFO [train.py:715] (4/8) Epoch 4, batch 28800, loss[loss=0.1501, simple_loss=0.2293, pruned_loss=0.03546, over 4825.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2255, pruned_loss=0.04259, over 971581.69 frames.], batch size: 26, lr: 4.35e-04
2022-05-05 01:15:10,515 INFO [train.py:715] (4/8) Epoch 4, batch 28850, loss[loss=0.1645, simple_loss=0.2284, pruned_loss=0.05024, over 4841.00 frames.], tot_loss[loss=0.155, simple_loss=0.2249, pruned_loss=0.04257, over 972140.75 frames.], batch size: 32, lr: 4.35e-04
2022-05-05 01:15:50,212 INFO [train.py:715] (4/8) Epoch 4, batch 28900, loss[loss=0.1973, simple_loss=0.2517, pruned_loss=0.07147, over 4855.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2255, pruned_loss=0.04297, over 972441.36 frames.], batch size: 32, lr: 4.35e-04
2022-05-05 01:16:29,308 INFO [train.py:715] (4/8) Epoch 4, batch 28950, loss[loss=0.1726, simple_loss=0.2257, pruned_loss=0.05979, over 4850.00 frames.], tot_loss[loss=0.1568, simple_loss=0.226, pruned_loss=0.04379, over 972741.38 frames.], batch size: 32, lr: 4.35e-04
2022-05-05 01:17:08,541 INFO [train.py:715] (4/8) Epoch 4, batch 29000, loss[loss=0.1442, simple_loss=0.2114, pruned_loss=0.03851, over 4872.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2253, pruned_loss=0.04325, over 972512.69 frames.], batch size: 32, lr: 4.35e-04
2022-05-05 01:17:48,159 INFO [train.py:715] (4/8) Epoch 4, batch 29050, loss[loss=0.1191, simple_loss=0.1986, pruned_loss=0.01977, over 4968.00 frames.], tot_loss[loss=0.155, simple_loss=0.2244, pruned_loss=0.04282, over 973081.06 frames.], batch size: 14, lr: 4.35e-04
2022-05-05 01:18:28,174 INFO [train.py:715] (4/8) Epoch 4, batch 29100, loss[loss=0.207, simple_loss=0.2585, pruned_loss=0.0777, over 4978.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2252, pruned_loss=0.04297, over 973868.70 frames.], batch size: 39, lr: 4.35e-04
2022-05-05 01:19:07,857 INFO [train.py:715] (4/8) Epoch 4, batch 29150, loss[loss=0.1529, simple_loss=0.2184, pruned_loss=0.04374, over 4843.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2245, pruned_loss=0.04241, over 972875.15 frames.], batch size: 20, lr: 4.35e-04
2022-05-05 01:19:46,740 INFO [train.py:715] (4/8) Epoch 4, batch 29200, loss[loss=0.1813, simple_loss=0.2427, pruned_loss=0.05995, over 4904.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2259, pruned_loss=0.04334, over 972600.54 frames.], batch size: 22, lr: 4.35e-04
2022-05-05 01:20:26,106 INFO [train.py:715] (4/8) Epoch 4, batch 29250, loss[loss=0.143, simple_loss=0.2117, pruned_loss=0.03717, over 4859.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2247, pruned_loss=0.04272, over 972611.83 frames.], batch size: 20, lr: 4.34e-04
2022-05-05 01:21:05,000 INFO [train.py:715] (4/8) Epoch 4, batch 29300, loss[loss=0.1368, simple_loss=0.2043, pruned_loss=0.03463, over 4806.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2243, pruned_loss=0.04211, over 972552.65 frames.], batch size: 15, lr: 4.34e-04
2022-05-05 01:21:43,984 INFO [train.py:715] (4/8) Epoch 4, batch 29350, loss[loss=0.1506, simple_loss=0.2163, pruned_loss=0.04247, over 4981.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2244, pruned_loss=0.04223, over 971708.82 frames.], batch size: 35, lr: 4.34e-04
2022-05-05 01:22:22,964 INFO [train.py:715] (4/8) Epoch 4, batch 29400, loss[loss=0.1536, simple_loss=0.2329, pruned_loss=0.0372, over 4979.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2241, pruned_loss=0.04235, over 971797.58 frames.], batch size: 24, lr: 4.34e-04
2022-05-05 01:23:02,045 INFO [train.py:715] (4/8) Epoch 4, batch 29450, loss[loss=0.1543, simple_loss=0.2107, pruned_loss=0.04893, over 4818.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2239, pruned_loss=0.04253, over 971836.61 frames.], batch size: 25, lr: 4.34e-04
2022-05-05 01:23:41,623 INFO [train.py:715] (4/8) Epoch 4, batch 29500, loss[loss=0.1615, simple_loss=0.2183, pruned_loss=0.05229, over 4741.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2243, pruned_loss=0.04265, over 971456.26 frames.], batch size: 12, lr: 4.34e-04
2022-05-05 01:24:20,879 INFO [train.py:715] (4/8) Epoch 4, batch 29550, loss[loss=0.1252, simple_loss=0.1966, pruned_loss=0.02692, over 4790.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2239, pruned_loss=0.04246, over 971307.63 frames.], batch size: 18, lr: 4.34e-04
2022-05-05 01:25:00,162 INFO [train.py:715] (4/8) Epoch 4, batch 29600, loss[loss=0.1641, simple_loss=0.2315, pruned_loss=0.0483, over 4958.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2245, pruned_loss=0.04263, over 970647.02 frames.], batch size: 35, lr: 4.34e-04
2022-05-05 01:25:39,285 INFO [train.py:715] (4/8) Epoch 4, batch 29650, loss[loss=0.1942, simple_loss=0.2589, pruned_loss=0.06471, over 4910.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2239, pruned_loss=0.04198, over 971454.34 frames.], batch size: 39, lr: 4.34e-04
2022-05-05 01:26:18,055 INFO [train.py:715] (4/8) Epoch 4, batch 29700, loss[loss=0.1229, simple_loss=0.1867, pruned_loss=0.0296, over 4857.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2242, pruned_loss=0.04209, over 971148.57 frames.], batch size: 13, lr: 4.34e-04
2022-05-05 01:26:57,623 INFO [train.py:715] (4/8) Epoch 4, batch 29750, loss[loss=0.1743, simple_loss=0.2389, pruned_loss=0.05481, over 4831.00 frames.], tot_loss[loss=0.1549, simple_loss=0.225, pruned_loss=0.04244, over 971095.79 frames.], batch size: 15, lr: 4.34e-04
2022-05-05 01:27:36,802 INFO [train.py:715] (4/8) Epoch 4, batch 29800, loss[loss=0.1295, simple_loss=0.1962, pruned_loss=0.03141, over 4883.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2253, pruned_loss=0.04269, over 971014.68 frames.], batch size: 16, lr: 4.34e-04
2022-05-05 01:28:16,331 INFO [train.py:715] (4/8) Epoch 4, batch 29850, loss[loss=0.1491, simple_loss=0.2252, pruned_loss=0.03654, over 4937.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2246, pruned_loss=0.04204, over 971210.89 frames.], batch size: 21, lr: 4.34e-04
2022-05-05 01:28:55,200 INFO [train.py:715] (4/8) Epoch 4, batch 29900, loss[loss=0.1579, simple_loss=0.2335, pruned_loss=0.04114, over 4992.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2257, pruned_loss=0.04262, over 971898.85 frames.], batch size: 25, lr: 4.34e-04
2022-05-05 01:29:34,840 INFO [train.py:715] (4/8) Epoch 4, batch 29950, loss[loss=0.1379, simple_loss=0.2137, pruned_loss=0.03102, over 4887.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2248, pruned_loss=0.04224, over 971678.69 frames.], batch size: 22, lr: 4.34e-04
2022-05-05 01:30:13,995 INFO [train.py:715] (4/8) Epoch 4, batch 30000, loss[loss=0.1511, simple_loss=0.2193, pruned_loss=0.04146, over 4923.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2252, pruned_loss=0.04218, over 972211.38 frames.], batch size: 18, lr: 4.34e-04
2022-05-05 01:30:13,995 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 01:30:23,827 INFO [train.py:742] (4/8) Epoch 4, validation: loss=0.1113, simple_loss=0.1968, pruned_loss=0.01286, over 914524.00 frames.
2022-05-05 01:31:03,988 INFO [train.py:715] (4/8) Epoch 4, batch 30050, loss[loss=0.1689, simple_loss=0.2523, pruned_loss=0.04269, over 4869.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2248, pruned_loss=0.04198, over 972247.71 frames.], batch size: 22, lr: 4.33e-04
2022-05-05 01:31:43,424 INFO [train.py:715] (4/8) Epoch 4, batch 30100, loss[loss=0.1329, simple_loss=0.2038, pruned_loss=0.03093, over 4839.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2246, pruned_loss=0.04191, over 971770.45 frames.], batch size: 32, lr: 4.33e-04
2022-05-05 01:32:23,322 INFO [train.py:715] (4/8) Epoch 4, batch 30150, loss[loss=0.1333, simple_loss=0.2044, pruned_loss=0.03115, over 4980.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2248, pruned_loss=0.04196, over 971738.80 frames.], batch size: 25, lr: 4.33e-04
2022-05-05 01:33:02,790 INFO [train.py:715] (4/8) Epoch 4, batch 30200, loss[loss=0.1468, simple_loss=0.2246, pruned_loss=0.03451, over 4965.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2256, pruned_loss=0.04249, over 971740.88 frames.], batch size: 35, lr: 4.33e-04
2022-05-05 01:33:42,426 INFO [train.py:715] (4/8) Epoch 4, batch 30250, loss[loss=0.1503, simple_loss=0.2227, pruned_loss=0.03896, over 4993.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2248, pruned_loss=0.04222, over 972722.04 frames.], batch size: 14, lr: 4.33e-04
2022-05-05 01:34:21,595 INFO [train.py:715] (4/8) Epoch 4, batch 30300, loss[loss=0.1442, simple_loss=0.2142, pruned_loss=0.03707, over 4825.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2248, pruned_loss=0.04255, over 972858.31 frames.], batch size: 27, lr: 4.33e-04
2022-05-05 01:35:01,076 INFO [train.py:715] (4/8) Epoch 4, batch 30350, loss[loss=0.1631, simple_loss=0.2147, pruned_loss=0.05576, over 4902.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2238, pruned_loss=0.04223, over 972958.86 frames.], batch size: 17, lr: 4.33e-04
2022-05-05 01:35:41,053 INFO [train.py:715] (4/8) Epoch 4, batch 30400, loss[loss=0.1298, simple_loss=0.2011, pruned_loss=0.02925, over 4819.00 frames.], tot_loss[loss=0.1535, simple_loss=0.223, pruned_loss=0.04196, over 972835.07 frames.], batch size: 12, lr: 4.33e-04
2022-05-05 01:36:20,213 INFO [train.py:715] (4/8) Epoch 4, batch 30450, loss[loss=0.1584, simple_loss=0.2434, pruned_loss=0.03674, over 4982.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2234, pruned_loss=0.04182, over 972918.53 frames.], batch size: 28, lr: 4.33e-04
2022-05-05 01:36:59,979 INFO [train.py:715] (4/8) Epoch 4, batch 30500, loss[loss=0.1675, simple_loss=0.2417, pruned_loss=0.04669, over 4966.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2233, pruned_loss=0.0418, over 972566.14 frames.], batch size: 24, lr: 4.33e-04
2022-05-05 01:37:40,026 INFO [train.py:715] (4/8) Epoch 4, batch 30550, loss[loss=0.1485, simple_loss=0.2169, pruned_loss=0.04006, over 4840.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2243, pruned_loss=0.04271, over 973172.17 frames.], batch size: 13, lr: 4.33e-04
2022-05-05 01:38:19,333 INFO [train.py:715] (4/8) Epoch 4, batch 30600, loss[loss=0.1397, simple_loss=0.2079, pruned_loss=0.03581, over 4789.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2246, pruned_loss=0.04313, over 972753.72 frames.], batch size: 12, lr: 4.33e-04
2022-05-05 01:38:58,940 INFO [train.py:715] (4/8) Epoch 4, batch 30650, loss[loss=0.135, simple_loss=0.2019, pruned_loss=0.03408, over 4968.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2246, pruned_loss=0.043, over 972362.21 frames.], batch size: 14, lr: 4.33e-04
2022-05-05 01:39:38,414 INFO [train.py:715] (4/8) Epoch 4, batch 30700, loss[loss=0.1517, simple_loss=0.2249, pruned_loss=0.0392, over 4856.00 frames.], tot_loss[loss=0.155, simple_loss=0.2242, pruned_loss=0.04293, over 971982.34 frames.], batch size: 20, lr: 4.33e-04
2022-05-05 01:40:18,147 INFO [train.py:715] (4/8) Epoch 4, batch 30750, loss[loss=0.1793, simple_loss=0.2672, pruned_loss=0.04568, over 4786.00 frames.], tot_loss[loss=0.155, simple_loss=0.2244, pruned_loss=0.04282, over 972395.71 frames.], batch size: 14, lr: 4.33e-04
2022-05-05 01:40:57,685 INFO [train.py:715] (4/8) Epoch 4, batch 30800, loss[loss=0.1747, simple_loss=0.2399, pruned_loss=0.05478, over 4707.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2241, pruned_loss=0.04282, over 971530.81 frames.], batch size: 15, lr: 4.32e-04
2022-05-05 01:41:37,511 INFO [train.py:715] (4/8) Epoch 4, batch 30850, loss[loss=0.1279, simple_loss=0.1933, pruned_loss=0.03121, over 4783.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2234, pruned_loss=0.04255, over 971132.09 frames.], batch size: 14, lr: 4.32e-04
2022-05-05 01:42:17,791 INFO [train.py:715] (4/8) Epoch 4, batch 30900, loss[loss=0.1628, simple_loss=0.2295, pruned_loss=0.04803, over 4911.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2242, pruned_loss=0.04276, over 970808.05 frames.], batch size: 17, lr: 4.32e-04
2022-05-05 01:42:57,279 INFO [train.py:715] (4/8) Epoch 4, batch 30950, loss[loss=0.205, simple_loss=0.2758, pruned_loss=0.06714, over 4863.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2242, pruned_loss=0.04268, over 971067.87 frames.], batch size: 32, lr: 4.32e-04
2022-05-05 01:43:36,634 INFO [train.py:715] (4/8) Epoch 4, batch 31000, loss[loss=0.157, simple_loss=0.2204, pruned_loss=0.04684, over 4733.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2238, pruned_loss=0.04241, over 971035.85 frames.], batch size: 16, lr: 4.32e-04
2022-05-05 01:44:16,108 INFO [train.py:715] (4/8) Epoch 4, batch 31050, loss[loss=0.1479, simple_loss=0.2236, pruned_loss=0.03616, over 4777.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2248, pruned_loss=0.04252, over 972112.95 frames.], batch size: 17, lr: 4.32e-04
2022-05-05 01:44:55,519 INFO [train.py:715] (4/8) Epoch 4, batch 31100, loss[loss=0.1719, simple_loss=0.2383, pruned_loss=0.05279, over 4786.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2252, pruned_loss=0.04283, over 972388.14 frames.], batch size: 18, lr: 4.32e-04
2022-05-05 01:45:35,034 INFO [train.py:715] (4/8) Epoch 4, batch 31150, loss[loss=0.1679, simple_loss=0.2306, pruned_loss=0.05257, over 4751.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2256, pruned_loss=0.04264, over 971664.43 frames.], batch size: 19, lr: 4.32e-04
2022-05-05 01:46:13,901 INFO [train.py:715] (4/8) Epoch 4, batch 31200, loss[loss=0.1723, simple_loss=0.2449, pruned_loss=0.04979, over 4809.00 frames.], tot_loss[loss=0.1561, simple_loss=0.2258, pruned_loss=0.0432, over 971550.78 frames.], batch size: 25, lr: 4.32e-04
2022-05-05 01:46:53,972 INFO [train.py:715] (4/8) Epoch 4, batch 31250, loss[loss=0.1627, simple_loss=0.2374, pruned_loss=0.04399, over 4811.00 frames.], tot_loss[loss=0.1563, simple_loss=0.2263, pruned_loss=0.04312, over 972537.46 frames.], batch size: 25, lr: 4.32e-04
2022-05-05 01:47:33,179 INFO [train.py:715] (4/8) Epoch 4, batch 31300, loss[loss=0.1871, simple_loss=0.2506, pruned_loss=0.06186, over 4905.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2259, pruned_loss=0.0427, over 972449.88 frames.], batch size: 18, lr: 4.32e-04
2022-05-05 01:48:12,187 INFO [train.py:715] (4/8) Epoch 4, batch 31350, loss[loss=0.152, simple_loss=0.2303, pruned_loss=0.03683, over 4987.00 frames.], tot_loss[loss=0.1557, simple_loss=0.2258, pruned_loss=0.04287, over 972587.38 frames.], batch size: 25, lr: 4.32e-04
2022-05-05 01:48:52,069 INFO [train.py:715] (4/8) Epoch 4, batch 31400, loss[loss=0.1264, simple_loss=0.2051, pruned_loss=0.02385, over 4804.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2249, pruned_loss=0.04223, over 972601.96 frames.], batch size: 26, lr: 4.32e-04
2022-05-05 01:49:31,803 INFO [train.py:715] (4/8) Epoch 4, batch 31450, loss[loss=0.1522, simple_loss=0.2103, pruned_loss=0.04704, over 4836.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2241, pruned_loss=0.04202, over 971880.76 frames.], batch size: 30, lr: 4.32e-04
2022-05-05 01:50:11,368 INFO [train.py:715] (4/8) Epoch 4, batch 31500, loss[loss=0.1749, simple_loss=0.2433, pruned_loss=0.05325, over 4768.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2251, pruned_loss=0.04304, over 971635.06 frames.], batch size: 19, lr: 4.32e-04
2022-05-05 01:50:51,753 INFO [train.py:715] (4/8) Epoch 4, batch 31550, loss[loss=0.132, simple_loss=0.2032, pruned_loss=0.03036, over 4802.00 frames.], tot_loss[loss=0.1556, simple_loss=0.225, pruned_loss=0.04307, over 971887.44 frames.], batch size: 12, lr: 4.32e-04
2022-05-05 01:51:32,266 INFO [train.py:715] (4/8) Epoch 4, batch 31600, loss[loss=0.1506, simple_loss=0.2236, pruned_loss=0.03878, over 4981.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2249, pruned_loss=0.04261, over 971995.69 frames.], batch size: 15, lr: 4.31e-04
2022-05-05 01:52:11,914 INFO [train.py:715] (4/8) Epoch 4, batch 31650, loss[loss=0.1533, simple_loss=0.2172, pruned_loss=0.04467, over 4838.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2241, pruned_loss=0.0423, over 972339.83 frames.], batch size: 12, lr: 4.31e-04
2022-05-05 01:52:51,499 INFO [train.py:715] (4/8) Epoch 4, batch 31700, loss[loss=0.1738, simple_loss=0.2552, pruned_loss=0.04615, over 4929.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2227, pruned_loss=0.04176, over 972037.87 frames.], batch size: 23, lr: 4.31e-04
2022-05-05 01:53:31,555 INFO [train.py:715] (4/8) Epoch 4, batch 31750, loss[loss=0.1757, simple_loss=0.2398, pruned_loss=0.0558, over 4970.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2229, pruned_loss=0.04168, over 972119.56 frames.], batch size: 15, lr: 4.31e-04
2022-05-05 01:54:11,604 INFO [train.py:715] (4/8) Epoch 4, batch 31800, loss[loss=0.1268, simple_loss=0.2052, pruned_loss=0.02421, over 4938.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2235, pruned_loss=0.04181, over 971934.97 frames.], batch size: 23, lr: 4.31e-04
2022-05-05 01:54:51,197 INFO [train.py:715] (4/8) Epoch 4, batch 31850, loss[loss=0.1463, simple_loss=0.2069, pruned_loss=0.04285, over 4759.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2244, pruned_loss=0.04198, over 971932.90 frames.], batch size: 12, lr: 4.31e-04
2022-05-05 01:55:30,807 INFO [train.py:715] (4/8) Epoch 4, batch 31900, loss[loss=0.1538, simple_loss=0.2124, pruned_loss=0.04756, over 4933.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2244, pruned_loss=0.04224, over 972634.88 frames.], batch size: 23, lr: 4.31e-04
2022-05-05 01:56:11,029 INFO [train.py:715] (4/8) Epoch 4, batch 31950, loss[loss=0.1591, simple_loss=0.2342, pruned_loss=0.04202, over 4865.00 frames.], tot_loss[loss=0.1552, simple_loss=0.225, pruned_loss=0.0427, over 972629.79 frames.], batch size: 32, lr: 4.31e-04
2022-05-05 01:56:50,985 INFO [train.py:715] (4/8) Epoch 4, batch 32000, loss[loss=0.1865, simple_loss=0.2499, pruned_loss=0.06158, over 4834.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2258, pruned_loss=0.04297, over 972303.04 frames.], batch size: 30, lr: 4.31e-04
2022-05-05 01:57:30,375 INFO [train.py:715] (4/8) Epoch 4, batch 32050, loss[loss=0.1522, simple_loss=0.2264, pruned_loss=0.03897, over 4880.00 frames.], tot_loss[loss=0.155, simple_loss=0.2248, pruned_loss=0.04263, over 972011.65 frames.], batch size: 22, lr: 4.31e-04
2022-05-05 01:58:10,942 INFO [train.py:715] (4/8) Epoch 4, batch 32100, loss[loss=0.1703, simple_loss=0.2223, pruned_loss=0.05919, over 4913.00 frames.], tot_loss[loss=0.1553, simple_loss=0.225, pruned_loss=0.0428, over 972337.04 frames.], batch size: 18, lr: 4.31e-04
2022-05-05 01:58:50,867 INFO [train.py:715] (4/8) Epoch 4, batch 32150, loss[loss=0.1507, simple_loss=0.2207, pruned_loss=0.04033, over 4838.00 frames.], tot_loss[loss=0.1557, simple_loss=0.225, pruned_loss=0.04321, over 972294.55 frames.], batch size: 30, lr: 4.31e-04
2022-05-05 01:59:30,405 INFO [train.py:715] (4/8) Epoch 4, batch 32200, loss[loss=0.16, simple_loss=0.233, pruned_loss=0.04353, over 4768.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2249, pruned_loss=0.04299, over 971413.93 frames.], batch size: 16, lr: 4.31e-04
2022-05-05 02:00:10,360 INFO [train.py:715] (4/8) Epoch 4, batch 32250, loss[loss=0.1566, simple_loss=0.2318, pruned_loss=0.04068, over 4984.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2252, pruned_loss=0.04314, over 971294.81 frames.], batch size: 31, lr: 4.31e-04
2022-05-05 02:00:51,157 INFO [train.py:715] (4/8) Epoch 4, batch 32300, loss[loss=0.1586, simple_loss=0.2132, pruned_loss=0.05202, over 4814.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2261, pruned_loss=0.04355, over 972118.78 frames.], batch size: 13, lr: 4.31e-04
2022-05-05 02:01:31,941 INFO [train.py:715] (4/8) Epoch 4, batch 32350, loss[loss=0.1706, simple_loss=0.2593, pruned_loss=0.04098, over 4919.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2263, pruned_loss=0.04349, over 972979.94 frames.], batch size: 17, lr: 4.31e-04
2022-05-05 02:02:12,274 INFO [train.py:715] (4/8) Epoch 4, batch 32400, loss[loss=0.1241, simple_loss=0.1921, pruned_loss=0.02806, over 4794.00 frames.], tot_loss[loss=0.1568, simple_loss=0.2264, pruned_loss=0.04355, over 972868.28 frames.], batch size: 14, lr: 4.30e-04
2022-05-05 02:02:52,623 INFO [train.py:715] (4/8) Epoch 4, batch 32450, loss[loss=0.1414, simple_loss=0.2128, pruned_loss=0.03497, over 4687.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2252, pruned_loss=0.04298, over 971999.69 frames.], batch size: 15, lr: 4.30e-04
2022-05-05 02:03:31,863 INFO [train.py:715] (4/8) Epoch 4, batch 32500, loss[loss=0.1524, simple_loss=0.2249, pruned_loss=0.04, over 4862.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2261, pruned_loss=0.0435, over 972223.54 frames.], batch size: 38, lr: 4.30e-04
2022-05-05 02:04:11,769 INFO [train.py:715] (4/8) Epoch 4, batch 32550, loss[loss=0.1485, simple_loss=0.2132, pruned_loss=0.04193, over 4851.00 frames.], tot_loss[loss=0.156, simple_loss=0.2256, pruned_loss=0.04314, over 973042.28 frames.], batch size: 32, lr: 4.30e-04
2022-05-05 02:04:50,739 INFO [train.py:715] (4/8) Epoch 4, batch 32600, loss[loss=0.1328, simple_loss=0.1933, pruned_loss=0.03622, over 4775.00 frames.], tot_loss[loss=0.1575, simple_loss=0.2269, pruned_loss=0.0441, over 973518.02 frames.], batch size: 14, lr: 4.30e-04
2022-05-05 02:05:30,803 INFO [train.py:715] (4/8) Epoch 4, batch 32650, loss[loss=0.142, simple_loss=0.2104, pruned_loss=0.0368, over 4904.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2261, pruned_loss=0.04335, over 972953.15 frames.], batch size: 22, lr: 4.30e-04
2022-05-05 02:06:09,913 INFO [train.py:715] (4/8) Epoch 4, batch 32700, loss[loss=0.1819, simple_loss=0.2388, pruned_loss=0.0625, over 4855.00 frames.], tot_loss[loss=0.1567, simple_loss=0.2266, pruned_loss=0.04338, over 972434.22 frames.], batch size: 20, lr: 4.30e-04
2022-05-05 02:06:49,543 INFO [train.py:715] (4/8) Epoch 4, batch 32750, loss[loss=0.1539, simple_loss=0.2205, pruned_loss=0.04368, over 4938.00 frames.], tot_loss[loss=0.1559, simple_loss=0.2255, pruned_loss=0.04316, over 972610.34 frames.], batch size: 35, lr: 4.30e-04
2022-05-05 02:07:29,259 INFO [train.py:715] (4/8) Epoch 4, batch 32800, loss[loss=0.1429, simple_loss=0.2154, pruned_loss=0.03522, over 4897.00 frames.], tot_loss[loss=0.1554, simple_loss=0.2251, pruned_loss=0.04282, over 973271.65 frames.], batch size: 19, lr: 4.30e-04
2022-05-05 02:08:09,338 INFO [train.py:715] (4/8) Epoch 4, batch 32850, loss[loss=0.1569, simple_loss=0.2251, pruned_loss=0.04436, over 4980.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2243, pruned_loss=0.04234, over 973753.44 frames.], batch size: 14, lr: 4.30e-04
2022-05-05 02:08:49,846 INFO [train.py:715] (4/8) Epoch 4, batch 32900, loss[loss=0.1558, simple_loss=0.2257, pruned_loss=0.04291, over 4979.00 frames.], tot_loss[loss=0.154, simple_loss=0.2239, pruned_loss=0.04205, over 973734.79 frames.], batch size: 39, lr: 4.30e-04
2022-05-05 02:09:30,075 INFO [train.py:715] (4/8) Epoch 4, batch 32950, loss[loss=0.1178, simple_loss=0.1921, pruned_loss=0.02178, over 4789.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2242, pruned_loss=0.04209, over 972930.16 frames.], batch size: 12, lr: 4.30e-04
2022-05-05 02:10:10,302 INFO [train.py:715] (4/8) Epoch 4, batch 33000, loss[loss=0.1464, simple_loss=0.2166, pruned_loss=0.03811, over 4778.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2249, pruned_loss=0.0424, over 972059.26 frames.], batch size: 18, lr: 4.30e-04
2022-05-05 02:10:10,303 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 02:10:20,090 INFO [train.py:742] (4/8) Epoch 4, validation: loss=0.1115, simple_loss=0.197, pruned_loss=0.01298, over 914524.00 frames.
2022-05-05 02:11:00,300 INFO [train.py:715] (4/8) Epoch 4, batch 33050, loss[loss=0.1427, simple_loss=0.2112, pruned_loss=0.03714, over 4863.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2245, pruned_loss=0.04223, over 973111.07 frames.], batch size: 16, lr: 4.30e-04
2022-05-05 02:11:40,005 INFO [train.py:715] (4/8) Epoch 4, batch 33100, loss[loss=0.1595, simple_loss=0.2309, pruned_loss=0.0441, over 4814.00 frames.], tot_loss[loss=0.154, simple_loss=0.2242, pruned_loss=0.04187, over 972070.99 frames.], batch size: 27, lr: 4.30e-04
2022-05-05 02:12:20,026 INFO [train.py:715] (4/8) Epoch 4, batch 33150, loss[loss=0.1969, simple_loss=0.2636, pruned_loss=0.06508, over 4880.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2247, pruned_loss=0.04273, over 971042.50 frames.], batch size: 22, lr: 4.30e-04
2022-05-05 02:13:00,225 INFO [train.py:715] (4/8) Epoch 4, batch 33200, loss[loss=0.1371, simple_loss=0.2016, pruned_loss=0.0363, over 4762.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2252, pruned_loss=0.04272, over 971076.83 frames.], batch size: 12, lr: 4.29e-04
2022-05-05 02:13:40,202 INFO [train.py:715] (4/8) Epoch 4, batch 33250, loss[loss=0.1348, simple_loss=0.204, pruned_loss=0.03282, over 4849.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2252, pruned_loss=0.0427, over 971736.17 frames.], batch size: 15, lr: 4.29e-04
2022-05-05 02:14:20,214 INFO [train.py:715] (4/8) Epoch 4, batch 33300, loss[loss=0.1645, simple_loss=0.2298, pruned_loss=0.04958, over 4927.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2259, pruned_loss=0.04288, over 971766.01 frames.], batch size: 23, lr: 4.29e-04
2022-05-05 02:14:59,209 INFO [train.py:715] (4/8) Epoch 4, batch 33350, loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02915, over 4743.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2244, pruned_loss=0.04246, over 971606.18 frames.], batch size: 16, lr: 4.29e-04
2022-05-05 02:15:38,981 INFO [train.py:715] (4/8) Epoch 4, batch 33400, loss[loss=0.1721, simple_loss=0.2409, pruned_loss=0.05168, over 4802.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2247, pruned_loss=0.04224, over 971949.51 frames.], batch size: 21, lr: 4.29e-04
2022-05-05 02:16:18,843 INFO [train.py:715] (4/8) Epoch 4, batch 33450, loss[loss=0.1429, simple_loss=0.2012, pruned_loss=0.04233, over 4955.00 frames.], tot_loss[loss=0.1553, simple_loss=0.2252, pruned_loss=0.04269, over 972201.79 frames.], batch size: 35, lr: 4.29e-04
2022-05-05 02:16:58,394 INFO [train.py:715] (4/8) Epoch 4, batch 33500, loss[loss=0.1222, simple_loss=0.1912, pruned_loss=0.02659, over 4981.00 frames.], tot_loss[loss=0.1558, simple_loss=0.226, pruned_loss=0.04281, over 973332.94 frames.], batch size: 24, lr: 4.29e-04
2022-05-05 02:17:38,199 INFO [train.py:715] (4/8) Epoch 4, batch 33550, loss[loss=0.1475, simple_loss=0.2097, pruned_loss=0.04269, over 4830.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2251, pruned_loss=0.04254, over 973531.57 frames.], batch size: 30, lr: 4.29e-04
2022-05-05 02:18:17,698 INFO [train.py:715] (4/8) Epoch 4, batch 33600, loss[loss=0.1718, simple_loss=0.2415, pruned_loss=0.05104, over 4978.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2258, pruned_loss=0.04273, over 972670.80 frames.], batch size: 25, lr: 4.29e-04
2022-05-05 02:18:57,441 INFO [train.py:715] (4/8) Epoch 4, batch 33650, loss[loss=0.1532, simple_loss=0.2146, pruned_loss=0.04589, over 4802.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2255, pruned_loss=0.04274, over 972183.86 frames.], batch size: 17, lr: 4.29e-04
2022-05-05 02:19:36,828 INFO [train.py:715] (4/8) Epoch 4, batch 33700, loss[loss=0.1368, simple_loss=0.2146, pruned_loss=0.02953, over 4925.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2258, pruned_loss=0.04287, over 972504.72 frames.], batch size: 23, lr: 4.29e-04
2022-05-05 02:20:16,627 INFO [train.py:715] (4/8) Epoch 4, batch 33750, loss[loss=0.1739, simple_loss=0.2345, pruned_loss=0.05663, over 4903.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2255, pruned_loss=0.04303, over 972823.03 frames.], batch size: 17, lr: 4.29e-04
2022-05-05 02:20:56,488 INFO [train.py:715] (4/8) Epoch 4, batch 33800, loss[loss=0.1514, simple_loss=0.2184, pruned_loss=0.04218, over 4815.00 frames.], tot_loss[loss=0.1558, simple_loss=0.2254, pruned_loss=0.04315, over 972518.19 frames.], batch size: 27, lr: 4.29e-04
2022-05-05 02:21:35,971 INFO [train.py:715] (4/8) Epoch 4, batch 33850, loss[loss=0.1376, simple_loss=0.2293, pruned_loss=0.02294, over 4786.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2251, pruned_loss=0.04261, over 972187.33 frames.], batch size: 21, lr: 4.29e-04
2022-05-05 02:22:15,607 INFO [train.py:715] (4/8) Epoch 4, batch 33900, loss[loss=0.1647, simple_loss=0.2347, pruned_loss=0.04734, over 4914.00 frames.], tot_loss[loss=0.155, simple_loss=0.2253, pruned_loss=0.04233, over 971879.73 frames.], batch size: 23, lr: 4.29e-04
2022-05-05 02:22:55,357 INFO [train.py:715] (4/8) Epoch 4, batch 33950, loss[loss=0.1896, simple_loss=0.2558, pruned_loss=0.06168, over 4746.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2248, pruned_loss=0.042, over 971679.32 frames.], batch size: 16, lr: 4.29e-04
2022-05-05 02:23:35,324 INFO [train.py:715] (4/8) Epoch 4, batch 34000, loss[loss=0.1825, simple_loss=0.2435, pruned_loss=0.0607, over 4857.00 frames.], tot_loss[loss=0.154, simple_loss=0.2245, pruned_loss=0.04171, over 972079.81 frames.], batch size: 20, lr: 4.28e-04
2022-05-05 02:24:14,850 INFO [train.py:715] (4/8) Epoch 4, batch 34050, loss[loss=0.1369, simple_loss=0.2185, pruned_loss=0.02762, over 4970.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2243, pruned_loss=0.04129, over 972820.32 frames.], batch size: 24, lr: 4.28e-04
2022-05-05 02:24:54,569 INFO [train.py:715] (4/8) Epoch 4, batch 34100, loss[loss=0.1557, simple_loss=0.2292, pruned_loss=0.04112, over 4984.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2245, pruned_loss=0.04185, over 972285.35 frames.], batch size: 39, lr: 4.28e-04
2022-05-05 02:25:34,631 INFO [train.py:715] (4/8) Epoch 4, batch 34150, loss[loss=0.1623, simple_loss=0.2292, pruned_loss=0.04773, over 4664.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2241, pruned_loss=0.04209, over 972101.02 frames.], batch size: 13, lr: 4.28e-04
2022-05-05 02:26:13,484 INFO [train.py:715] (4/8) Epoch 4, batch 34200, loss[loss=0.1438, simple_loss=0.2229, pruned_loss=0.03241, over 4782.00 frames.], tot_loss[loss=0.1536, simple_loss=0.224, pruned_loss=0.0416, over 972437.84 frames.], batch size: 14, lr: 4.28e-04
2022-05-05 02:26:54,315 INFO [train.py:715] (4/8) Epoch 4, batch 34250, loss[loss=0.1668, simple_loss=0.2419, pruned_loss=0.04583, over 4978.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2239, pruned_loss=0.04151, over 972689.24 frames.], batch size: 35, lr: 4.28e-04
2022-05-05 02:27:34,206 INFO [train.py:715] (4/8) Epoch 4, batch 34300, loss[loss=0.1414, simple_loss=0.2102, pruned_loss=0.03629, over 4704.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2242, pruned_loss=0.04173, over 972120.90 frames.], batch size: 15, lr: 4.28e-04
2022-05-05 02:28:13,960 INFO [train.py:715] (4/8) Epoch 4, batch 34350, loss[loss=0.1505, simple_loss=0.2178, pruned_loss=0.04158, over 4734.00 frames.], tot_loss[loss=0.1538, simple_loss=0.224, pruned_loss=0.04185, over 971468.39 frames.], batch size: 16, lr: 4.28e-04
2022-05-05 02:28:53,991 INFO [train.py:715] (4/8) Epoch 4, batch 34400, loss[loss=0.167, simple_loss=0.2379, pruned_loss=0.04807, over 4735.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2252, pruned_loss=0.0426, over 971845.29 frames.], batch size: 16, lr: 4.28e-04
2022-05-05 02:29:33,823 INFO [train.py:715] (4/8) Epoch 4, batch 34450, loss[loss=0.1311, simple_loss=0.214, pruned_loss=0.0241, over 4994.00 frames.], tot_loss[loss=0.1545, simple_loss=0.225, pruned_loss=0.04201, over 972366.51 frames.], batch size: 14, lr: 4.28e-04
2022-05-05 02:30:14,469 INFO [train.py:715] (4/8) Epoch 4, batch 34500, loss[loss=0.2065, simple_loss=0.2608, pruned_loss=0.07613, over 4817.00 frames.], tot_loss[loss=0.156, simple_loss=0.2262, pruned_loss=0.04291, over 971802.08 frames.], batch size: 26, lr: 4.28e-04
2022-05-05 02:30:53,315 INFO [train.py:715] (4/8) Epoch 4, batch 34550, loss[loss=0.1479, simple_loss=0.2102, pruned_loss=0.04275, over 4917.00 frames.], tot_loss[loss=0.1565, simple_loss=0.2269, pruned_loss=0.0431, over 971666.30 frames.], batch size: 17, lr: 4.28e-04
2022-05-05 02:31:33,260 INFO [train.py:715] (4/8) Epoch 4, batch 34600, loss[loss=0.1366, simple_loss=0.2096, pruned_loss=0.03179, over 4913.00 frames.], tot_loss[loss=0.1564, simple_loss=0.2268, pruned_loss=0.04303, over 971648.07 frames.], batch size: 29, lr: 4.28e-04
2022-05-05 02:32:13,236 INFO [train.py:715] (4/8) Epoch 4, batch 34650, loss[loss=0.1547, simple_loss=0.2331, pruned_loss=0.03818, over 4912.00 frames.], tot_loss[loss=0.156, simple_loss=0.2261, pruned_loss=0.04294, over 972201.43 frames.], batch size: 17, lr: 4.28e-04
2022-05-05 02:32:52,590 INFO [train.py:715] (4/8) Epoch 4, batch 34700, loss[loss=0.1522, simple_loss=0.2207, pruned_loss=0.04187, over 4872.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2246, pruned_loss=0.04207, over 972781.50 frames.], batch size: 30, lr: 4.28e-04
2022-05-05 02:33:30,871 INFO [train.py:715] (4/8) Epoch 4, batch 34750, loss[loss=0.16, simple_loss=0.2364, pruned_loss=0.04181, over 4782.00 frames.], tot_loss[loss=0.1548, simple_loss=0.225, pruned_loss=0.04229, over 972009.34 frames.], batch size: 14, lr: 4.28e-04
2022-05-05 02:34:07,932 INFO [train.py:715] (4/8) Epoch 4, batch 34800, loss[loss=0.2264, simple_loss=0.3059, pruned_loss=0.07344, over 4915.00 frames.], tot_loss[loss=0.156, simple_loss=0.2262, pruned_loss=0.04292, over 973084.63 frames.], batch size: 18, lr: 4.27e-04
2022-05-05 02:34:57,763 INFO [train.py:715] (4/8) Epoch 5, batch 0, loss[loss=0.1324, simple_loss=0.1934, pruned_loss=0.03566, over 4964.00 frames.], tot_loss[loss=0.1324, simple_loss=0.1934, pruned_loss=0.03566, over 4964.00 frames.], batch size: 15, lr: 4.02e-04
2022-05-05 02:35:38,096 INFO [train.py:715] (4/8) Epoch 5, batch 50, loss[loss=0.1595, simple_loss=0.229, pruned_loss=0.045, over 4871.00 frames.], tot_loss[loss=0.159, simple_loss=0.2279, pruned_loss=0.04502, over 219874.70 frames.], batch size: 30, lr: 4.02e-04
2022-05-05 02:36:17,797 INFO [train.py:715] (4/8) Epoch 5, batch 100, loss[loss=0.1293, simple_loss=0.2056, pruned_loss=0.02649, over 4831.00 frames.], tot_loss[loss=0.1556, simple_loss=0.226, pruned_loss=0.04258, over 386731.21 frames.], batch size: 26, lr: 4.02e-04
2022-05-05 02:36:57,765 INFO [train.py:715] (4/8) Epoch 5, batch 150, loss[loss=0.1308, simple_loss=0.2042, pruned_loss=0.02876, over 4962.00 frames.], tot_loss[loss=0.154, simple_loss=0.2254, pruned_loss=0.0413, over 516699.68 frames.], batch size: 35, lr: 4.02e-04
2022-05-05 02:37:38,287 INFO [train.py:715] (4/8) Epoch 5, batch 200, loss[loss=0.1748, simple_loss=0.2349, pruned_loss=0.05732, over 4927.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2248, pruned_loss=0.04168, over 617890.27 frames.], batch size: 18, lr: 4.02e-04
2022-05-05 02:38:17,737 INFO [train.py:715] (4/8) Epoch 5, batch 250, loss[loss=0.1485, simple_loss=0.2201, pruned_loss=0.03846, over 4801.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2245, pruned_loss=0.04217, over 696765.97 frames.], batch size: 24, lr: 4.02e-04
2022-05-05 02:38:57,161 INFO [train.py:715] (4/8) Epoch 5, batch 300, loss[loss=0.1569, simple_loss=0.2302, pruned_loss=0.04185, over 4864.00 frames.], tot_loss[loss=0.155, simple_loss=0.2249, pruned_loss=0.04253, over 757384.65 frames.], batch size: 22, lr: 4.01e-04
2022-05-05 02:39:36,892 INFO [train.py:715] (4/8) Epoch 5, batch 350, loss[loss=0.1331, simple_loss=0.2104, pruned_loss=0.02787, over 4985.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2246, pruned_loss=0.04228, over 805532.56 frames.], batch size: 26, lr: 4.01e-04
2022-05-05 02:40:16,659 INFO [train.py:715] (4/8) Epoch 5, batch 400, loss[loss=0.1751, simple_loss=0.2392, pruned_loss=0.05556, over 4880.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2242, pruned_loss=0.04214, over 842533.99 frames.], batch size: 16, lr: 4.01e-04
2022-05-05 02:40:56,046 INFO [train.py:715] (4/8) Epoch 5, batch 450, loss[loss=0.132, simple_loss=0.2034, pruned_loss=0.03028, over 4893.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2249, pruned_loss=0.04229, over 872044.71 frames.], batch size: 22, lr: 4.01e-04
2022-05-05 02:41:35,798 INFO [train.py:715] (4/8) Epoch 5, batch 500, loss[loss=0.1876, simple_loss=0.2598, pruned_loss=0.05775, over 4825.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2251, pruned_loss=0.04215, over 894577.11 frames.], batch size: 27, lr: 4.01e-04
2022-05-05 02:42:15,653 INFO [train.py:715] (4/8) Epoch 5, batch 550, loss[loss=0.1684, simple_loss=0.227, pruned_loss=0.0549, over 4835.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2244, pruned_loss=0.0419, over 911164.89 frames.], batch size: 13, lr: 4.01e-04
2022-05-05 02:42:54,759 INFO [train.py:715] (4/8) Epoch 5, batch 600, loss[loss=0.1293, simple_loss=0.2003, pruned_loss=0.02915, over 4895.00 frames.], tot_loss[loss=0.153, simple_loss=0.2234, pruned_loss=0.04134, over 925337.09 frames.], batch size: 22, lr: 4.01e-04
2022-05-05 02:43:34,141 INFO [train.py:715] (4/8) Epoch 5, batch 650, loss[loss=0.1773, simple_loss=0.242, pruned_loss=0.05628, over 4901.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2243, pruned_loss=0.04196, over 935999.48 frames.], batch size: 19, lr: 4.01e-04
2022-05-05 02:44:13,846 INFO [train.py:715] (4/8) Epoch 5, batch 700, loss[loss=0.1682, simple_loss=0.2297, pruned_loss=0.05334, over 4897.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2241, pruned_loss=0.04229, over 944012.19 frames.], batch size: 22, lr: 4.01e-04
2022-05-05 02:44:53,909 INFO [train.py:715] (4/8) Epoch 5, batch 750, loss[loss=0.1844, simple_loss=0.2442, pruned_loss=0.06225, over 4946.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2236, pruned_loss=0.04193, over 950641.48 frames.], batch size: 21, lr: 4.01e-04
2022-05-05 02:45:33,281 INFO [train.py:715] (4/8) Epoch 5, batch 800, loss[loss=0.1932, simple_loss=0.2649, pruned_loss=0.06081, over 4903.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2248, pruned_loss=0.04226, over 955291.29 frames.], batch size: 17, lr: 4.01e-04
2022-05-05 02:46:12,787 INFO [train.py:715] (4/8) Epoch 5, batch 850, loss[loss=0.1855, simple_loss=0.2319, pruned_loss=0.06949, over 4852.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2248, pruned_loss=0.04304, over 958921.66 frames.], batch size: 20, lr: 4.01e-04
2022-05-05 02:46:52,356 INFO [train.py:715] (4/8) Epoch 5, batch 900, loss[loss=0.1353, simple_loss=0.2077, pruned_loss=0.03146, over 4978.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2247, pruned_loss=0.04312, over 961350.53 frames.], batch size: 24, lr: 4.01e-04
2022-05-05 02:47:31,844 INFO [train.py:715] (4/8) Epoch 5, batch 950, loss[loss=0.1664, simple_loss=0.2361, pruned_loss=0.04834, over 4788.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2245, pruned_loss=0.04301, over 964241.24 frames.], batch size: 17, lr: 4.01e-04
2022-05-05 02:48:11,355 INFO [train.py:715] (4/8) Epoch 5, batch 1000, loss[loss=0.1533, simple_loss=0.2204, pruned_loss=0.04315, over 4707.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2244, pruned_loss=0.04305, over 964457.80 frames.], batch size: 15, lr: 4.01e-04
2022-05-05 02:48:50,614 INFO [train.py:715] (4/8) Epoch 5, batch 1050, loss[loss=0.1266, simple_loss=0.1945, pruned_loss=0.02934, over 4919.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2236, pruned_loss=0.04264, over 965573.59 frames.], batch size: 29, lr: 4.01e-04
2022-05-05 02:49:30,324 INFO [train.py:715] (4/8) Epoch 5, batch 1100, loss[loss=0.1548, simple_loss=0.2308, pruned_loss=0.03943, over 4971.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2232, pruned_loss=0.04206, over 967109.82 frames.], batch size: 24, lr: 4.01e-04
2022-05-05 02:50:09,329 INFO [train.py:715] (4/8) Epoch 5, batch 1150, loss[loss=0.1103, simple_loss=0.1802, pruned_loss=0.02017, over 4844.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2237, pruned_loss=0.04253, over 968927.48 frames.], batch size: 13, lr: 4.00e-04
2022-05-05 02:50:49,092 INFO [train.py:715] (4/8) Epoch 5, batch 1200, loss[loss=0.1447, simple_loss=0.2182, pruned_loss=0.03563, over 4813.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2236, pruned_loss=0.04255, over 970171.55 frames.], batch size: 25, lr: 4.00e-04
2022-05-05 02:51:29,240 INFO [train.py:715] (4/8) Epoch 5, batch 1250, loss[loss=0.1686, simple_loss=0.2448, pruned_loss=0.04623, over 4818.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2248, pruned_loss=0.04275, over 971075.59 frames.], batch size: 25, lr: 4.00e-04
2022-05-05 02:52:08,411 INFO [train.py:715] (4/8) Epoch 5, batch 1300, loss[loss=0.1597, simple_loss=0.2228, pruned_loss=0.04825, over 4847.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2245, pruned_loss=0.04237, over 971360.25 frames.], batch size: 30, lr: 4.00e-04
2022-05-05 02:52:48,191 INFO [train.py:715] (4/8) Epoch 5, batch 1350, loss[loss=0.138, simple_loss=0.2089, pruned_loss=0.0336, over 4793.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2237, pruned_loss=0.04204, over 972032.33 frames.], batch size: 17, lr: 4.00e-04
2022-05-05 02:53:27,483 INFO [train.py:715] (4/8) Epoch 5, batch 1400, loss[loss=0.1632, simple_loss=0.2355, pruned_loss=0.04545, over 4788.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2236, pruned_loss=0.04187, over 971305.37 frames.], batch size: 14, lr: 4.00e-04
2022-05-05 02:54:07,303 INFO [train.py:715] (4/8) Epoch 5, batch 1450, loss[loss=0.1547, simple_loss=0.2325, pruned_loss=0.03845, over 4916.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2232, pruned_loss=0.04189, over 972235.65 frames.], batch size: 18, lr: 4.00e-04
2022-05-05 02:54:46,730 INFO [train.py:715] (4/8) Epoch 5, batch 1500, loss[loss=0.1665, simple_loss=0.2436, pruned_loss=0.04474, over 4745.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2241, pruned_loss=0.04188, over 972446.31 frames.], batch size: 16, lr: 4.00e-04
2022-05-05 02:55:25,725 INFO [train.py:715] (4/8) Epoch 5, batch 1550, loss[loss=0.1355, simple_loss=0.2083, pruned_loss=0.03138, over 4946.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2245, pruned_loss=0.04209, over 971964.06 frames.], batch size: 24, lr: 4.00e-04
2022-05-05 02:56:05,366 INFO [train.py:715] (4/8) Epoch 5, batch 1600, loss[loss=0.1385, simple_loss=0.2083, pruned_loss=0.03429, over 4755.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2246, pruned_loss=0.04229, over 971890.17 frames.], batch size: 19, lr: 4.00e-04
2022-05-05 02:56:45,702 INFO [train.py:715] (4/8) Epoch 5, batch 1650, loss[loss=0.1417, simple_loss=0.2099, pruned_loss=0.03669, over 4844.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2243, pruned_loss=0.04228, over 971858.11 frames.], batch size: 15, lr: 4.00e-04
2022-05-05 02:57:24,642 INFO [train.py:715] (4/8) Epoch 5, batch 1700, loss[loss=0.1371, simple_loss=0.2037, pruned_loss=0.03523, over 4954.00 frames.], tot_loss[loss=0.154, simple_loss=0.2238, pruned_loss=0.0421, over 972958.68 frames.], batch size: 14, lr: 4.00e-04
2022-05-05 02:58:05,305 INFO [train.py:715] (4/8) Epoch 5, batch 1750, loss[loss=0.1584, simple_loss=0.2215, pruned_loss=0.04769, over 4864.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2237, pruned_loss=0.04205, over 973179.83 frames.], batch size: 20, lr: 4.00e-04
2022-05-05 02:58:45,440 INFO [train.py:715] (4/8) Epoch 5, batch 1800, loss[loss=0.1821, simple_loss=0.2482, pruned_loss=0.058, over 4975.00 frames.], tot_loss[loss=0.154, simple_loss=0.2235, pruned_loss=0.0422, over 973789.26 frames.], batch size: 39, lr: 4.00e-04
2022-05-05 02:59:25,915 INFO [train.py:715] (4/8) Epoch 5, batch 1850, loss[loss=0.1136, simple_loss=0.1923, pruned_loss=0.01741, over 4841.00 frames.], tot_loss[loss=0.1544, simple_loss=0.224, pruned_loss=0.04244, over 973591.32 frames.], batch size: 13, lr: 4.00e-04
2022-05-05 03:00:06,294 INFO [train.py:715] (4/8) Epoch 5, batch 1900, loss[loss=0.173, simple_loss=0.2254, pruned_loss=0.06035, over 4977.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2245, pruned_loss=0.04295, over 973134.36 frames.], batch size: 28, lr: 4.00e-04
2022-05-05 03:00:46,053 INFO [train.py:715] (4/8) Epoch 5, batch 1950, loss[loss=0.1401, simple_loss=0.2242, pruned_loss=0.02801, over 4988.00 frames.], tot_loss[loss=0.154, simple_loss=0.2236, pruned_loss=0.04222, over 972340.43 frames.], batch size: 28, lr: 4.00e-04
2022-05-05 03:01:29,141 INFO [train.py:715] (4/8) Epoch 5, batch 2000, loss[loss=0.1654, simple_loss=0.2348, pruned_loss=0.04801, over 4861.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2236, pruned_loss=0.04234, over 972033.46 frames.], batch size: 20, lr: 4.00e-04
2022-05-05 03:02:09,158 INFO [train.py:715] (4/8) Epoch 5, batch 2050, loss[loss=0.1297, simple_loss=0.2033, pruned_loss=0.02809, over 4853.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2248, pruned_loss=0.04246, over 972139.10 frames.], batch size: 12, lr: 3.99e-04
2022-05-05 03:02:49,515 INFO [train.py:715] (4/8) Epoch 5, batch 2100, loss[loss=0.1494, simple_loss=0.221, pruned_loss=0.0389, over 4885.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2244, pruned_loss=0.04245, over 972514.27 frames.], batch size: 19, lr: 3.99e-04
2022-05-05 03:03:30,095 INFO [train.py:715] (4/8) Epoch 5, batch 2150, loss[loss=0.1478, simple_loss=0.2211, pruned_loss=0.03718, over 4853.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2231, pruned_loss=0.04155, over 972457.57 frames.], batch size: 20, lr: 3.99e-04
2022-05-05 03:04:09,688 INFO [train.py:715] (4/8) Epoch 5, batch 2200, loss[loss=0.1479, simple_loss=0.2175, pruned_loss=0.03913, over 4924.00 frames.], tot_loss[loss=0.1535, simple_loss=0.224, pruned_loss=0.04151, over 972474.03 frames.], batch size: 18, lr: 3.99e-04
2022-05-05 03:04:50,060 INFO [train.py:715] (4/8) Epoch 5, batch 2250, loss[loss=0.1471, simple_loss=0.2186, pruned_loss=0.03778, over 4703.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2233, pruned_loss=0.0407, over 972736.17 frames.], batch size: 15, lr: 3.99e-04
2022-05-05 03:05:30,781 INFO [train.py:715] (4/8) Epoch 5, batch 2300, loss[loss=0.1408, simple_loss=0.2148, pruned_loss=0.03336, over 4911.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2238, pruned_loss=0.04134, over 973007.85 frames.], batch size: 18, lr: 3.99e-04
2022-05-05 03:06:10,992 INFO [train.py:715] (4/8) Epoch 5, batch 2350, loss[loss=0.1564, simple_loss=0.2275, pruned_loss=0.04268, over 4919.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2236, pruned_loss=0.04153, over 972373.15 frames.], batch size: 18, lr: 3.99e-04
2022-05-05 03:06:51,193 INFO [train.py:715] (4/8) Epoch 5, batch 2400, loss[loss=0.1498, simple_loss=0.2239, pruned_loss=0.03782, over 4946.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2231, pruned_loss=0.04107, over 971842.68 frames.], batch size: 21, lr: 3.99e-04
2022-05-05 03:07:31,716 INFO [train.py:715] (4/8) Epoch 5, batch 2450, loss[loss=0.1817, simple_loss=0.2541, pruned_loss=0.05467, over 4888.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2225, pruned_loss=0.0413, over 971359.88 frames.], batch size: 22, lr: 3.99e-04
2022-05-05 03:08:12,405 INFO [train.py:715] (4/8) Epoch 5, batch 2500, loss[loss=0.1629, simple_loss=0.2419, pruned_loss=0.04193, over 4849.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2217, pruned_loss=0.04061, over 971773.99 frames.], batch size: 20, lr: 3.99e-04
2022-05-05 03:08:52,450 INFO [train.py:715] (4/8) Epoch 5, batch 2550, loss[loss=0.1651, simple_loss=0.2343, pruned_loss=0.04788, over 4802.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2228, pruned_loss=0.04135, over 971781.35 frames.], batch size: 21, lr: 3.99e-04
2022-05-05 03:09:33,372 INFO [train.py:715] (4/8) Epoch 5, batch 2600, loss[loss=0.139, simple_loss=0.2128, pruned_loss=0.03256, over 4794.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2242, pruned_loss=0.04206, over 971861.53 frames.], batch size: 21, lr: 3.99e-04
2022-05-05 03:10:13,557 INFO [train.py:715] (4/8) Epoch 5, batch 2650, loss[loss=0.1648, simple_loss=0.231, pruned_loss=0.04928, over 4908.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2239, pruned_loss=0.04174, over 972497.67 frames.], batch size: 18, lr: 3.99e-04
2022-05-05 03:10:54,132 INFO [train.py:715] (4/8) Epoch 5, batch 2700, loss[loss=0.146, simple_loss=0.2232, pruned_loss=0.03435, over 4960.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2247, pruned_loss=0.04197, over 972739.10 frames.], batch size: 39, lr: 3.99e-04
2022-05-05 03:11:34,322 INFO [train.py:715] (4/8) Epoch 5, batch 2750, loss[loss=0.1604, simple_loss=0.226, pruned_loss=0.04743, over 4956.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2255, pruned_loss=0.042, over 972564.73 frames.], batch size: 15, lr: 3.99e-04
2022-05-05 03:12:14,301 INFO [train.py:715] (4/8) Epoch 5, batch 2800, loss[loss=0.1628, simple_loss=0.2301, pruned_loss=0.04775, over 4692.00 frames.], tot_loss[loss=0.1549, simple_loss=0.2259, pruned_loss=0.04198, over 972973.69 frames.], batch size: 15, lr: 3.99e-04
2022-05-05 03:12:54,882 INFO [train.py:715] (4/8) Epoch 5, batch 2850, loss[loss=0.1604, simple_loss=0.2246, pruned_loss=0.04813, over 4978.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2255, pruned_loss=0.04194, over 973041.82 frames.], batch size: 15, lr: 3.99e-04
2022-05-05 03:13:35,009 INFO [train.py:715] (4/8) Epoch 5, batch 2900, loss[loss=0.1549, simple_loss=0.2324, pruned_loss=0.03871, over 4771.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2255, pruned_loss=0.04188, over 973415.20 frames.], batch size: 17, lr: 3.99e-04
2022-05-05 03:14:15,391 INFO [train.py:715] (4/8) Epoch 5, batch 2950, loss[loss=0.1261, simple_loss=0.2019, pruned_loss=0.02517, over 4760.00 frames.], tot_loss[loss=0.1556, simple_loss=0.2263, pruned_loss=0.04244, over 973375.22 frames.], batch size: 17, lr: 3.98e-04
2022-05-05 03:14:54,471 INFO [train.py:715] (4/8) Epoch 5, batch 3000, loss[loss=0.1257, simple_loss=0.203, pruned_loss=0.02427, over 4890.00 frames.], tot_loss[loss=0.1542, simple_loss=0.225, pruned_loss=0.04168, over 973249.64 frames.], batch size: 19, lr: 3.98e-04
2022-05-05 03:14:54,472 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 03:15:03,919 INFO [train.py:742] (4/8) Epoch 5, validation: loss=0.1108, simple_loss=0.1962, pruned_loss=0.01274, over 914524.00 frames.
2022-05-05 03:15:42,395 INFO [train.py:715] (4/8) Epoch 5, batch 3050, loss[loss=0.1403, simple_loss=0.2091, pruned_loss=0.03575, over 4852.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2246, pruned_loss=0.04158, over 973924.43 frames.], batch size: 13, lr: 3.98e-04
2022-05-05 03:16:21,553 INFO [train.py:715] (4/8) Epoch 5, batch 3100, loss[loss=0.1415, simple_loss=0.2107, pruned_loss=0.03616, over 4784.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2249, pruned_loss=0.04174, over 973413.58 frames.], batch size: 18, lr: 3.98e-04
2022-05-05 03:17:00,519 INFO [train.py:715] (4/8) Epoch 5, batch 3150, loss[loss=0.1466, simple_loss=0.2226, pruned_loss=0.03533, over 4860.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2249, pruned_loss=0.04183, over 973749.83 frames.], batch size: 20, lr: 3.98e-04
2022-05-05 03:17:40,035 INFO [train.py:715] (4/8) Epoch 5, batch 3200, loss[loss=0.1748, simple_loss=0.2306, pruned_loss=0.05952, over 4780.00 frames.], tot_loss[loss=0.1541, simple_loss=0.225, pruned_loss=0.04158, over 973679.42 frames.], batch size: 18, lr: 3.98e-04
2022-05-05 03:18:19,743 INFO [train.py:715] (4/8) Epoch 5, batch 3250, loss[loss=0.157, simple_loss=0.2291, pruned_loss=0.04242, over 4966.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2256, pruned_loss=0.04188, over 973704.11 frames.], batch size: 15, lr: 3.98e-04
2022-05-05 03:18:58,957 INFO [train.py:715] (4/8) Epoch 5, batch 3300, loss[loss=0.1503, simple_loss=0.2274, pruned_loss=0.03663, over 4989.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2239, pruned_loss=0.04132, over 973042.00 frames.], batch size: 14, lr: 3.98e-04
2022-05-05 03:19:38,239 INFO [train.py:715] (4/8) Epoch 5, batch 3350, loss[loss=0.1422, simple_loss=0.2148, pruned_loss=0.03479, over 4813.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2239, pruned_loss=0.04133, over 973364.69 frames.], batch size: 26, lr: 3.98e-04
2022-05-05 03:20:17,969 INFO [train.py:715] (4/8) Epoch 5, batch 3400, loss[loss=0.1528, simple_loss=0.2256, pruned_loss=0.04003, over 4805.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2238, pruned_loss=0.04139, over 972668.34 frames.], batch size: 21, lr: 3.98e-04
2022-05-05 03:20:57,513 INFO [train.py:715] (4/8) Epoch 5, batch 3450, loss[loss=0.1494, simple_loss=0.2242, pruned_loss=0.03734, over 4962.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2255, pruned_loss=0.04248, over 972504.68 frames.], batch size: 39, lr: 3.98e-04
2022-05-05 03:21:36,806 INFO [train.py:715] (4/8) Epoch 5, batch 3500, loss[loss=0.1512, simple_loss=0.2112, pruned_loss=0.04563, over 4867.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2245, pruned_loss=0.04192, over 972442.61 frames.], batch size: 16, lr: 3.98e-04
2022-05-05 03:22:16,030 INFO [train.py:715] (4/8) Epoch 5, batch 3550, loss[loss=0.1492, simple_loss=0.2269, pruned_loss=0.03573, over 4953.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2242, pruned_loss=0.04204, over 973063.25 frames.], batch size: 21, lr: 3.98e-04
2022-05-05 03:22:55,529 INFO [train.py:715] (4/8) Epoch 5, batch 3600, loss[loss=0.1704, simple_loss=0.2468, pruned_loss=0.04698, over 4978.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2245, pruned_loss=0.04184, over 973823.42 frames.], batch size: 21, lr: 3.98e-04
2022-05-05 03:23:34,520 INFO [train.py:715] (4/8) Epoch 5, batch 3650, loss[loss=0.1469, simple_loss=0.2154, pruned_loss=0.03923, over 4961.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2242, pruned_loss=0.04232, over 973303.88 frames.], batch size: 25, lr: 3.98e-04
2022-05-05 03:24:13,761 INFO [train.py:715] (4/8) Epoch 5, batch 3700, loss[loss=0.127, simple_loss=0.1977, pruned_loss=0.02814, over 4906.00 frames.], tot_loss[loss=0.1532, simple_loss=0.223, pruned_loss=0.04168, over 973583.81 frames.], batch size: 19, lr: 3.98e-04
2022-05-05 03:24:53,920 INFO [train.py:715] (4/8) Epoch 5, batch 3750, loss[loss=0.1411, simple_loss=0.2177, pruned_loss=0.03221, over 4979.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2231, pruned_loss=0.04164, over 973771.60 frames.], batch size: 28, lr: 3.98e-04
2022-05-05 03:25:33,699 INFO [train.py:715] (4/8) Epoch 5, batch 3800, loss[loss=0.1488, simple_loss=0.2148, pruned_loss=0.0414, over 4971.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2226, pruned_loss=0.04127, over 973491.82 frames.], batch size: 35, lr: 3.97e-04
2022-05-05 03:26:13,091 INFO [train.py:715] (4/8) Epoch 5, batch 3850, loss[loss=0.144, simple_loss=0.2187, pruned_loss=0.03462, over 4865.00 frames.], tot_loss[loss=0.1528, simple_loss=0.223, pruned_loss=0.04127, over 973594.64 frames.], batch size: 20, lr: 3.97e-04
2022-05-05 03:26:52,958 INFO [train.py:715] (4/8) Epoch 5, batch 3900, loss[loss=0.1511, simple_loss=0.2114, pruned_loss=0.04542, over 4842.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2226, pruned_loss=0.04105, over 972696.45 frames.], batch size: 12, lr: 3.97e-04
2022-05-05 03:27:32,995 INFO [train.py:715] (4/8) Epoch 5, batch 3950, loss[loss=0.194, simple_loss=0.252, pruned_loss=0.06795, over 4776.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2227, pruned_loss=0.04091, over 972703.56 frames.], batch size: 14, lr: 3.97e-04
2022-05-05 03:28:13,083 INFO [train.py:715] (4/8) Epoch 5, batch 4000, loss[loss=0.2021, simple_loss=0.2572, pruned_loss=0.07345, over 4832.00 frames.], tot_loss[loss=0.153, simple_loss=0.2233, pruned_loss=0.04138, over 972702.18 frames.], batch size: 15, lr: 3.97e-04
2022-05-05 03:28:53,737 INFO [train.py:715] (4/8) Epoch 5, batch 4050, loss[loss=0.195, simple_loss=0.261, pruned_loss=0.0645, over 4905.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2234, pruned_loss=0.04156, over 972993.59 frames.], batch size: 18, lr: 3.97e-04
2022-05-05 03:29:33,846 INFO [train.py:715] (4/8) Epoch 5, batch 4100, loss[loss=0.1226, simple_loss=0.2059, pruned_loss=0.01969, over 4756.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2233, pruned_loss=0.04158, over 972181.25 frames.], batch size: 16, lr: 3.97e-04
2022-05-05 03:30:14,065 INFO [train.py:715] (4/8) Epoch 5, batch 4150, loss[loss=0.1447, simple_loss=0.2148, pruned_loss=0.03732, over 4922.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2217, pruned_loss=0.0407, over 972483.81 frames.], batch size: 23, lr: 3.97e-04
2022-05-05 03:30:53,449 INFO [train.py:715] (4/8) Epoch 5, batch 4200, loss[loss=0.132, simple_loss=0.1994, pruned_loss=0.03232, over 4746.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2218, pruned_loss=0.04086, over 972643.94 frames.], batch size: 19, lr: 3.97e-04
2022-05-05 03:31:32,791 INFO [train.py:715] (4/8) Epoch 5, batch 4250, loss[loss=0.1305, simple_loss=0.2157, pruned_loss=0.02271, over 4796.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2219, pruned_loss=0.0408, over 971703.29 frames.], batch size: 24, lr: 3.97e-04
2022-05-05 03:32:12,486 INFO [train.py:715] (4/8) Epoch 5, batch 4300, loss[loss=0.1461, simple_loss=0.2148, pruned_loss=0.03865, over 4889.00 frames.], tot_loss[loss=0.1518, simple_loss=0.222, pruned_loss=0.04083, over 972315.39 frames.], batch size: 19, lr: 3.97e-04
2022-05-05 03:32:52,098 INFO [train.py:715] (4/8) Epoch 5, batch 4350, loss[loss=0.1311, simple_loss=0.2035, pruned_loss=0.02939, over 4767.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2227, pruned_loss=0.0415, over 971674.28 frames.], batch size: 19, lr: 3.97e-04
2022-05-05 03:33:32,068 INFO [train.py:715] (4/8) Epoch 5, batch 4400, loss[loss=0.1121, simple_loss=0.1755, pruned_loss=0.02436, over 4802.00 frames.], tot_loss[loss=0.1521, simple_loss=0.222, pruned_loss=0.04106, over 970716.58 frames.], batch size: 12, lr: 3.97e-04
2022-05-05 03:34:10,946 INFO [train.py:715] (4/8) Epoch 5, batch 4450, loss[loss=0.1581, simple_loss=0.245, pruned_loss=0.0356, over 4781.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2222, pruned_loss=0.04098, over 971489.73 frames.], batch size: 18, lr: 3.97e-04
2022-05-05 03:34:50,791 INFO [train.py:715] (4/8) Epoch 5, batch 4500, loss[loss=0.1516, simple_loss=0.2264, pruned_loss=0.03841, over 4850.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2234, pruned_loss=0.04157, over 971613.91 frames.], batch size: 30, lr: 3.97e-04
2022-05-05 03:35:30,122 INFO [train.py:715] (4/8) Epoch 5, batch 4550, loss[loss=0.1495, simple_loss=0.2314, pruned_loss=0.03375, over 4818.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2229, pruned_loss=0.04129, over 970586.73 frames.], batch size: 27, lr: 3.97e-04
2022-05-05 03:36:09,740 INFO [train.py:715] (4/8) Epoch 5, batch 4600, loss[loss=0.1585, simple_loss=0.2293, pruned_loss=0.04389, over 4806.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2238, pruned_loss=0.04169, over 971036.07 frames.], batch size: 25, lr: 3.97e-04
2022-05-05 03:36:50,098 INFO [train.py:715] (4/8) Epoch 5, batch 4650, loss[loss=0.1507, simple_loss=0.2321, pruned_loss=0.03464, over 4798.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2233, pruned_loss=0.04131, over 971147.25 frames.], batch size: 24, lr: 3.97e-04
2022-05-05 03:37:30,432 INFO [train.py:715] (4/8) Epoch 5, batch 4700, loss[loss=0.1408, simple_loss=0.2158, pruned_loss=0.03289, over 4776.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2241, pruned_loss=0.04213, over 971516.48 frames.], batch size: 18, lr: 3.96e-04
2022-05-05 03:38:10,931 INFO [train.py:715] (4/8) Epoch 5, batch 4750, loss[loss=0.1611, simple_loss=0.2264, pruned_loss=0.04789, over 4859.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2241, pruned_loss=0.04234, over 972362.64 frames.], batch size: 20, lr: 3.96e-04
2022-05-05 03:38:50,697 INFO [train.py:715] (4/8) Epoch 5, batch 4800, loss[loss=0.1495, simple_loss=0.2173, pruned_loss=0.04081, over 4938.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2229, pruned_loss=0.042, over 972800.49 frames.], batch size: 29, lr: 3.96e-04
2022-05-05 03:39:31,183 INFO [train.py:715] (4/8) Epoch 5, batch 4850, loss[loss=0.1357, simple_loss=0.21, pruned_loss=0.03067, over 4805.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2236, pruned_loss=0.04247, over 972137.11 frames.], batch size: 24, lr: 3.96e-04
2022-05-05 03:40:11,790 INFO [train.py:715] (4/8) Epoch 5, batch 4900, loss[loss=0.1439, simple_loss=0.2169, pruned_loss=0.03546, over 4950.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2228, pruned_loss=0.0419, over 972514.35 frames.], batch size: 24, lr: 3.96e-04
2022-05-05 03:40:51,917 INFO [train.py:715] (4/8) Epoch 5, batch 4950, loss[loss=0.1273, simple_loss=0.2062, pruned_loss=0.02419, over 4819.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2231, pruned_loss=0.04196, over 972718.82 frames.], batch size: 25, lr: 3.96e-04
2022-05-05 03:41:32,221 INFO [train.py:715] (4/8) Epoch 5, batch 5000, loss[loss=0.1508, simple_loss=0.2329, pruned_loss=0.03436, over 4887.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2229, pruned_loss=0.04189, over 972237.13 frames.], batch size: 22, lr: 3.96e-04
2022-05-05 03:42:13,227 INFO [train.py:715] (4/8) Epoch 5, batch 5050, loss[loss=0.1347, simple_loss=0.2141, pruned_loss=0.02767, over 4811.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2238, pruned_loss=0.04181, over 972221.81 frames.], batch size: 21, lr: 3.96e-04
2022-05-05 03:42:52,852 INFO [train.py:715] (4/8) Epoch 5, batch 5100, loss[loss=0.1907, simple_loss=0.249, pruned_loss=0.06616, over 4759.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2252, pruned_loss=0.04263, over 972122.84 frames.], batch size: 16, lr: 3.96e-04
2022-05-05 03:43:32,132 INFO [train.py:715] (4/8) Epoch 5, batch 5150, loss[loss=0.1863, simple_loss=0.2607, pruned_loss=0.05597, over 4931.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2252, pruned_loss=0.04255, over 972454.59 frames.], batch size: 18, lr: 3.96e-04
2022-05-05 03:44:11,855 INFO [train.py:715] (4/8) Epoch 5, batch 5200, loss[loss=0.212, simple_loss=0.2577, pruned_loss=0.08316, over 4894.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2245, pruned_loss=0.0425, over 972728.90 frames.], batch size: 17, lr: 3.96e-04
2022-05-05 03:44:51,638 INFO [train.py:715] (4/8) Epoch 5, batch 5250, loss[loss=0.1508, simple_loss=0.2129, pruned_loss=0.04434, over 4748.00 frames.], tot_loss[loss=0.1546, simple_loss=0.2245, pruned_loss=0.04229, over 973922.52 frames.], batch size: 16, lr: 3.96e-04
2022-05-05 03:45:32,215 INFO [train.py:715] (4/8) Epoch 5, batch 5300, loss[loss=0.1107, simple_loss=0.1788, pruned_loss=0.0213, over 4768.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2234, pruned_loss=0.04188, over 972945.37 frames.], batch size: 12, lr: 3.96e-04
2022-05-05 03:46:12,527 INFO [train.py:715] (4/8) Epoch 5, batch 5350, loss[loss=0.1911, simple_loss=0.2466, pruned_loss=0.06775, over 4881.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2227, pruned_loss=0.04137, over 972541.92 frames.], batch size: 16, lr: 3.96e-04
2022-05-05 03:46:52,865 INFO [train.py:715] (4/8) Epoch 5, batch 5400, loss[loss=0.1597, simple_loss=0.2338, pruned_loss=0.04277, over 4801.00 frames.], tot_loss[loss=0.154, simple_loss=0.224, pruned_loss=0.04193, over 972137.48 frames.], batch size: 14, lr: 3.96e-04
2022-05-05 03:47:32,598 INFO [train.py:715] (4/8) Epoch 5, batch 5450, loss[loss=0.1443, simple_loss=0.215, pruned_loss=0.03678, over 4797.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2246, pruned_loss=0.04201, over 972053.43 frames.], batch size: 17, lr: 3.96e-04
2022-05-05 03:48:12,713 INFO [train.py:715] (4/8) Epoch 5, batch 5500, loss[loss=0.1469, simple_loss=0.2155, pruned_loss=0.03917, over 4849.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2247, pruned_loss=0.04245, over 971959.09 frames.], batch size: 15, lr: 3.96e-04
2022-05-05 03:48:53,046 INFO [train.py:715] (4/8) Epoch 5, batch 5550, loss[loss=0.1401, simple_loss=0.2182, pruned_loss=0.031, over 4915.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2254, pruned_loss=0.04255, over 972559.65 frames.], batch size: 29, lr: 3.96e-04
2022-05-05 03:49:33,425 INFO [train.py:715] (4/8) Epoch 5, batch 5600, loss[loss=0.1601, simple_loss=0.2314, pruned_loss=0.04437, over 4945.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2252, pruned_loss=0.04218, over 972521.48 frames.], batch size: 39, lr: 3.95e-04
2022-05-05 03:50:13,560 INFO [train.py:715] (4/8) Epoch 5, batch 5650, loss[loss=0.2092, simple_loss=0.2878, pruned_loss=0.06532, over 4828.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2253, pruned_loss=0.04166, over 972737.03 frames.], batch size: 15, lr: 3.95e-04
2022-05-05 03:50:52,916 INFO [train.py:715] (4/8) Epoch 5, batch 5700, loss[loss=0.2002, simple_loss=0.2435, pruned_loss=0.07845, over 4971.00 frames.], tot_loss[loss=0.154, simple_loss=0.2247, pruned_loss=0.04163, over 973125.63 frames.], batch size: 35, lr: 3.95e-04
2022-05-05 03:51:33,335 INFO [train.py:715] (4/8) Epoch 5, batch 5750, loss[loss=0.1429, simple_loss=0.2134, pruned_loss=0.03613, over 4816.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2239, pruned_loss=0.04179, over 973320.91 frames.], batch size: 26, lr: 3.95e-04
2022-05-05 03:52:13,243 INFO [train.py:715] (4/8) Epoch 5, batch 5800, loss[loss=0.1645, simple_loss=0.2293, pruned_loss=0.04987, over 4825.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2234, pruned_loss=0.04147, over 974110.45 frames.], batch size: 25, lr: 3.95e-04
2022-05-05 03:52:53,778 INFO [train.py:715] (4/8) Epoch 5, batch 5850, loss[loss=0.1487, simple_loss=0.2317, pruned_loss=0.03287, over 4926.00 frames.], tot_loss[loss=0.1537, simple_loss=0.224, pruned_loss=0.04168, over 974599.91 frames.], batch size: 23, lr: 3.95e-04
2022-05-05 03:53:33,411 INFO [train.py:715] (4/8) Epoch 5, batch 5900, loss[loss=0.1307, simple_loss=0.2003, pruned_loss=0.03054, over 4691.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2235, pruned_loss=0.04156, over 973581.00 frames.], batch size: 15, lr: 3.95e-04
2022-05-05 03:54:13,801 INFO [train.py:715] (4/8) Epoch 5, batch 5950, loss[loss=0.2073, simple_loss=0.2687, pruned_loss=0.07291, over 4694.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2236, pruned_loss=0.0413, over 972799.88 frames.], batch size: 15, lr: 3.95e-04
2022-05-05 03:54:53,636 INFO [train.py:715] (4/8) Epoch 5, batch 6000, loss[loss=0.1362, simple_loss=0.2182, pruned_loss=0.02713, over 4850.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2226, pruned_loss=0.04076, over 971444.74 frames.], batch size: 20, lr: 3.95e-04
2022-05-05 03:54:53,637 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 03:55:03,070 INFO [train.py:742] (4/8) Epoch 5, validation: loss=0.1106, simple_loss=0.1959, pruned_loss=0.01263, over 914524.00 frames.
2022-05-05 03:55:42,937 INFO [train.py:715] (4/8) Epoch 5, batch 6050, loss[loss=0.1397, simple_loss=0.2163, pruned_loss=0.03153, over 4884.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04039, over 971756.55 frames.], batch size: 22, lr: 3.95e-04
2022-05-05 03:56:22,014 INFO [train.py:715] (4/8) Epoch 5, batch 6100, loss[loss=0.1384, simple_loss=0.2195, pruned_loss=0.02869, over 4946.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2225, pruned_loss=0.04047, over 971959.78 frames.], batch size: 29, lr: 3.95e-04
2022-05-05 03:57:01,848 INFO [train.py:715] (4/8) Epoch 5, batch 6150, loss[loss=0.1609, simple_loss=0.2306, pruned_loss=0.04555, over 4784.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2226, pruned_loss=0.04079, over 971880.11 frames.], batch size: 18, lr: 3.95e-04
2022-05-05 03:57:40,837 INFO [train.py:715] (4/8) Epoch 5, batch 6200, loss[loss=0.1397, simple_loss=0.2151, pruned_loss=0.03211, over 4824.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2224, pruned_loss=0.04071, over 971856.54 frames.], batch size: 26, lr: 3.95e-04
2022-05-05 03:58:21,087 INFO [train.py:715] (4/8) Epoch 5, batch 6250, loss[loss=0.1529, simple_loss=0.2205, pruned_loss=0.04263, over 4969.00 frames.], tot_loss[loss=0.1517, simple_loss=0.222, pruned_loss=0.04071, over 971245.59 frames.], batch size: 25, lr: 3.95e-04
2022-05-05 03:58:59,727 INFO [train.py:715] (4/8) Epoch 5, batch 6300, loss[loss=0.1502, simple_loss=0.2207, pruned_loss=0.03989, over 4831.00 frames.], tot_loss[loss=0.153, simple_loss=0.223, pruned_loss=0.04152, over 972050.91 frames.], batch size: 13, lr: 3.95e-04
2022-05-05 03:59:39,537 INFO [train.py:715] (4/8) Epoch 5, batch 6350, loss[loss=0.1701, simple_loss=0.2327, pruned_loss=0.05372, over 4781.00 frames.], tot_loss[loss=0.153, simple_loss=0.2234, pruned_loss=0.0413, over 971601.40 frames.], batch size: 17, lr: 3.95e-04
2022-05-05 04:00:18,900 INFO [train.py:715] (4/8) Epoch 5, batch 6400, loss[loss=0.1135, simple_loss=0.184, pruned_loss=0.02154, over 4981.00 frames.], tot_loss[loss=0.153, simple_loss=0.2237, pruned_loss=0.04111, over 971303.85 frames.], batch size: 28, lr: 3.95e-04
2022-05-05 04:00:57,766 INFO [train.py:715] (4/8) Epoch 5, batch 6450, loss[loss=0.1921, simple_loss=0.2582, pruned_loss=0.063, over 4773.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2249, pruned_loss=0.04188, over 971965.05 frames.], batch size: 18, lr: 3.95e-04
2022-05-05 04:01:37,236 INFO [train.py:715] (4/8) Epoch 5, batch 6500, loss[loss=0.141, simple_loss=0.2182, pruned_loss=0.03188, over 4948.00 frames.], tot_loss[loss=0.1547, simple_loss=0.2256, pruned_loss=0.04188, over 972473.50 frames.], batch size: 23, lr: 3.95e-04
2022-05-05 04:02:16,580 INFO [train.py:715] (4/8) Epoch 5, batch 6550, loss[loss=0.1524, simple_loss=0.2199, pruned_loss=0.0424, over 4959.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2245, pruned_loss=0.04149, over 972787.16 frames.], batch size: 35, lr: 3.94e-04
2022-05-05 04:02:55,729 INFO [train.py:715] (4/8) Epoch 5, batch 6600, loss[loss=0.1691, simple_loss=0.2367, pruned_loss=0.0507, over 4957.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2245, pruned_loss=0.04137, over 973269.20 frames.], batch size: 24, lr: 3.94e-04
2022-05-05 04:03:35,249 INFO [train.py:715] (4/8) Epoch 5, batch 6650, loss[loss=0.1182, simple_loss=0.1979, pruned_loss=0.01924, over 4932.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2244, pruned_loss=0.04156, over 973281.62 frames.], batch size: 18, lr: 3.94e-04
2022-05-05 04:04:15,786 INFO [train.py:715] (4/8) Epoch 5, batch 6700, loss[loss=0.1308, simple_loss=0.1974, pruned_loss=0.03212, over 4859.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2242, pruned_loss=0.04145, over 973136.34 frames.], batch size: 32, lr: 3.94e-04
2022-05-05 04:04:56,120 INFO [train.py:715] (4/8) Epoch 5, batch 6750, loss[loss=0.1443, simple_loss=0.2205, pruned_loss=0.03406, over 4757.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2245, pruned_loss=0.04135, over 973587.56 frames.], batch size: 19, lr: 3.94e-04
2022-05-05 04:05:36,105 INFO [train.py:715] (4/8) Epoch 5, batch 6800, loss[loss=0.177, simple_loss=0.2356, pruned_loss=0.0592, over 4942.00 frames.], tot_loss[loss=0.1534, simple_loss=0.224, pruned_loss=0.04143, over 973491.08 frames.], batch size: 18, lr: 3.94e-04
2022-05-05 04:06:16,590 INFO [train.py:715] (4/8) Epoch 5, batch 6850, loss[loss=0.1327, simple_loss=0.2047, pruned_loss=0.03037, over 4820.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2248, pruned_loss=0.04177, over 973183.70 frames.], batch size: 12, lr: 3.94e-04
2022-05-05 04:06:56,550 INFO [train.py:715] (4/8) Epoch 5, batch 6900, loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02875, over 4978.00 frames.], tot_loss[loss=0.1555, simple_loss=0.2259, pruned_loss=0.04249, over 972801.04 frames.], batch size: 33, lr: 3.94e-04
2022-05-05 04:07:37,125 INFO [train.py:715] (4/8) Epoch 5, batch 6950, loss[loss=0.1643, simple_loss=0.248, pruned_loss=0.04035, over 4763.00 frames.], tot_loss[loss=0.1551, simple_loss=0.2255, pruned_loss=0.04238, over 972440.38 frames.], batch size: 19, lr: 3.94e-04
2022-05-05 04:08:16,565 INFO [train.py:715] (4/8) Epoch 5, batch 7000, loss[loss=0.1372, simple_loss=0.2109, pruned_loss=0.03171, over 4873.00 frames.], tot_loss[loss=0.1546, simple_loss=0.225, pruned_loss=0.0421, over 972754.61 frames.], batch size: 32, lr: 3.94e-04
2022-05-05 04:08:56,462 INFO [train.py:715] (4/8) Epoch 5, batch 7050, loss[loss=0.139, simple_loss=0.202, pruned_loss=0.03804, over 4831.00 frames.], tot_loss[loss=0.1534, simple_loss=0.224, pruned_loss=0.04142, over 972896.39 frames.], batch size: 15, lr: 3.94e-04
2022-05-05 04:09:36,250 INFO [train.py:715] (4/8) Epoch 5, batch 7100, loss[loss=0.1372, simple_loss=0.2033, pruned_loss=0.0356, over 4966.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2237, pruned_loss=0.0413, over 972936.05 frames.], batch size: 14, lr: 3.94e-04
2022-05-05 04:10:15,691 INFO [train.py:715] (4/8) Epoch 5, batch 7150, loss[loss=0.1678, simple_loss=0.244, pruned_loss=0.0458, over 4835.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2231, pruned_loss=0.04116, over 972400.51 frames.], batch size: 26, lr: 3.94e-04
2022-05-05 04:10:55,642 INFO [train.py:715] (4/8) Epoch 5, batch 7200, loss[loss=0.1503, simple_loss=0.2219, pruned_loss=0.03938, over 4792.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2229, pruned_loss=0.04089, over 971613.48 frames.], batch size: 17, lr: 3.94e-04
2022-05-05 04:11:35,238 INFO [train.py:715] (4/8) Epoch 5, batch 7250, loss[loss=0.1324, simple_loss=0.2106, pruned_loss=0.02712, over 4767.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2217, pruned_loss=0.04023, over 970910.96 frames.], batch size: 19, lr: 3.94e-04
2022-05-05 04:12:15,755 INFO [train.py:715] (4/8) Epoch 5, batch 7300, loss[loss=0.1941, simple_loss=0.2579, pruned_loss=0.06514, over 4694.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2218, pruned_loss=0.04029, over 971097.36 frames.], batch size: 15, lr: 3.94e-04
2022-05-05 04:12:55,316 INFO [train.py:715] (4/8) Epoch 5, batch 7350, loss[loss=0.1527, simple_loss=0.2278, pruned_loss=0.03882, over 4784.00 frames.], tot_loss[loss=0.1523, simple_loss=0.223, pruned_loss=0.04075, over 972583.49 frames.], batch size: 17, lr: 3.94e-04
2022-05-05 04:13:34,915 INFO [train.py:715] (4/8) Epoch 5, batch 7400, loss[loss=0.1466, simple_loss=0.2214, pruned_loss=0.03592, over 4733.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2224, pruned_loss=0.04056, over 972644.63 frames.], batch size: 12, lr: 3.94e-04
2022-05-05 04:14:14,461 INFO [train.py:715] (4/8) Epoch 5, batch 7450, loss[loss=0.1751, simple_loss=0.2407, pruned_loss=0.05471, over 4863.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2224, pruned_loss=0.04023, over 972556.81 frames.], batch size: 34, lr: 3.93e-04
2022-05-05 04:14:53,550 INFO [train.py:715] (4/8) Epoch 5, batch 7500, loss[loss=0.1554, simple_loss=0.2284, pruned_loss=0.04116, over 4754.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2225, pruned_loss=0.04038, over 972653.41 frames.], batch size: 12, lr: 3.93e-04
2022-05-05 04:15:33,686 INFO [train.py:715] (4/8) Epoch 5, batch 7550, loss[loss=0.1367, simple_loss=0.2087, pruned_loss=0.03237, over 4895.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2222, pruned_loss=0.04025, over 972992.78 frames.], batch size: 22, lr: 3.93e-04
2022-05-05 04:16:13,350 INFO [train.py:715] (4/8) Epoch 5, batch 7600, loss[loss=0.1409, simple_loss=0.2227, pruned_loss=0.02951, over 4883.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2224, pruned_loss=0.04013, over 973446.12 frames.], batch size: 22, lr: 3.93e-04
2022-05-05 04:16:53,610 INFO [train.py:715] (4/8) Epoch 5, batch 7650, loss[loss=0.1425, simple_loss=0.2198, pruned_loss=0.03266, over 4835.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2234, pruned_loss=0.04061, over 972963.92 frames.], batch size: 15, lr: 3.93e-04
2022-05-05 04:17:33,266 INFO [train.py:715] (4/8) Epoch 5, batch 7700, loss[loss=0.1449, simple_loss=0.2183, pruned_loss=0.0358, over 4891.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2235, pruned_loss=0.04088, over 973255.77 frames.], batch size: 19, lr: 3.93e-04
2022-05-05 04:18:12,777 INFO [train.py:715] (4/8) Epoch 5, batch 7750, loss[loss=0.1752, simple_loss=0.2506, pruned_loss=0.04992, over 4763.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2239, pruned_loss=0.04095, over 973023.31 frames.], batch size: 19, lr: 3.93e-04
2022-05-05 04:18:52,926 INFO [train.py:715] (4/8) Epoch 5, batch 7800, loss[loss=0.1409, simple_loss=0.2104, pruned_loss=0.03568, over 4840.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2233, pruned_loss=0.04066, over 973461.99 frames.], batch size: 30, lr: 3.93e-04
2022-05-05 04:19:32,130 INFO [train.py:715] (4/8) Epoch 5, batch 7850, loss[loss=0.1304, simple_loss=0.2047, pruned_loss=0.02805, over 4926.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2235, pruned_loss=0.041, over 973650.07 frames.], batch size: 23, lr: 3.93e-04
2022-05-05 04:20:12,357 INFO [train.py:715] (4/8) Epoch 5, batch 7900, loss[loss=0.1479, simple_loss=0.2046, pruned_loss=0.04555, over 4798.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2238, pruned_loss=0.04095, over 971807.67 frames.], batch size: 17, lr: 3.93e-04
2022-05-05 04:20:51,912 INFO [train.py:715] (4/8) Epoch 5, batch 7950, loss[loss=0.1428, simple_loss=0.2054, pruned_loss=0.04008, over 4970.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2242, pruned_loss=0.04143, over 971963.75 frames.], batch size: 15, lr: 3.93e-04
2022-05-05 04:21:32,116 INFO [train.py:715] (4/8) Epoch 5, batch 8000, loss[loss=0.1552, simple_loss=0.2186, pruned_loss=0.04587, over 4819.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2241, pruned_loss=0.04153, over 971854.01 frames.], batch size: 25, lr: 3.93e-04
2022-05-05 04:22:11,571 INFO [train.py:715] (4/8) Epoch 5, batch 8050, loss[loss=0.1392, simple_loss=0.2052, pruned_loss=0.03656, over 4844.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2239, pruned_loss=0.04177, over 971360.23 frames.], batch size: 13, lr: 3.93e-04
2022-05-05 04:22:51,022 INFO [train.py:715] (4/8) Epoch 5, batch 8100, loss[loss=0.1429, simple_loss=0.2151, pruned_loss=0.03537, over 4986.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2236, pruned_loss=0.04146, over 971832.38 frames.], batch size: 14, lr: 3.93e-04
2022-05-05 04:23:30,810 INFO [train.py:715] (4/8) Epoch 5, batch 8150, loss[loss=0.1652, simple_loss=0.2316, pruned_loss=0.04942, over 4737.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2237, pruned_loss=0.0412, over 971595.50 frames.], batch size: 16, lr: 3.93e-04
2022-05-05 04:24:09,994 INFO [train.py:715] (4/8) Epoch 5, batch 8200, loss[loss=0.1939, simple_loss=0.2654, pruned_loss=0.06123, over 4762.00 frames.], tot_loss[loss=0.1534, simple_loss=0.224, pruned_loss=0.0414, over 971932.31 frames.], batch size: 19, lr: 3.93e-04
2022-05-05 04:24:50,011 INFO [train.py:715] (4/8) Epoch 5, batch 8250, loss[loss=0.1568, simple_loss=0.2327, pruned_loss=0.04045, over 4864.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2235, pruned_loss=0.04138, over 971648.41 frames.], batch size: 32, lr: 3.93e-04
2022-05-05 04:25:29,482 INFO [train.py:715] (4/8) Epoch 5, batch 8300, loss[loss=0.1391, simple_loss=0.2068, pruned_loss=0.03575, over 4756.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2232, pruned_loss=0.04166, over 972181.99 frames.], batch size: 16, lr: 3.93e-04
2022-05-05 04:26:09,424 INFO [train.py:715] (4/8) Epoch 5, batch 8350, loss[loss=0.1324, simple_loss=0.1945, pruned_loss=0.03515, over 4889.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2235, pruned_loss=0.04172, over 973171.14 frames.], batch size: 16, lr: 3.93e-04
2022-05-05 04:26:48,501 INFO [train.py:715] (4/8) Epoch 5, batch 8400, loss[loss=0.1682, simple_loss=0.2276, pruned_loss=0.05437, over 4977.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2223, pruned_loss=0.04107, over 972438.11 frames.], batch size: 24, lr: 3.92e-04
2022-05-05 04:27:27,550 INFO [train.py:715] (4/8) Epoch 5, batch 8450, loss[loss=0.1498, simple_loss=0.2185, pruned_loss=0.04054, over 4945.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2225, pruned_loss=0.04111, over 972562.89 frames.], batch size: 35, lr: 3.92e-04
2022-05-05 04:28:06,815 INFO [train.py:715] (4/8) Epoch 5, batch 8500, loss[loss=0.1338, simple_loss=0.2131, pruned_loss=0.02725, over 4850.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2237, pruned_loss=0.04205, over 972194.11 frames.], batch size: 34, lr: 3.92e-04
2022-05-05 04:28:45,802 INFO [train.py:715] (4/8) Epoch 5, batch 8550, loss[loss=0.1568, simple_loss=0.224, pruned_loss=0.04483, over 4848.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2232, pruned_loss=0.04192, over 972354.96 frames.], batch size: 34, lr: 3.92e-04
2022-05-05 04:29:25,248 INFO [train.py:715] (4/8) Epoch 5, batch 8600, loss[loss=0.1248, simple_loss=0.2076, pruned_loss=0.021, over 4920.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2235, pruned_loss=0.04176, over 971676.11 frames.], batch size: 21, lr: 3.92e-04
2022-05-05 04:30:04,408 INFO [train.py:715] (4/8) Epoch 5, batch 8650, loss[loss=0.1648, simple_loss=0.2403, pruned_loss=0.04466, over 4938.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2227, pruned_loss=0.04128, over 971892.91 frames.], batch size: 21, lr: 3.92e-04
2022-05-05 04:30:43,884 INFO [train.py:715] (4/8) Epoch 5, batch 8700, loss[loss=0.1519, simple_loss=0.2231, pruned_loss=0.04036, over 4768.00 frames.], tot_loss[loss=0.154, simple_loss=0.2238, pruned_loss=0.04213, over 971617.59 frames.], batch size: 14, lr: 3.92e-04
2022-05-05 04:31:23,271 INFO [train.py:715] (4/8) Epoch 5, batch 8750, loss[loss=0.1529, simple_loss=0.2145, pruned_loss=0.04571, over 4687.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2229, pruned_loss=0.04169, over 971325.26 frames.], batch size: 15, lr: 3.92e-04
2022-05-05 04:32:02,280 INFO [train.py:715] (4/8) Epoch 5, batch 8800, loss[loss=0.1314, simple_loss=0.2001, pruned_loss=0.03139, over 4813.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2223, pruned_loss=0.04127, over 972055.91 frames.], batch size: 25, lr: 3.92e-04
2022-05-05 04:32:42,160 INFO [train.py:715] (4/8) Epoch 5, batch 8850, loss[loss=0.1441, simple_loss=0.2213, pruned_loss=0.03342, over 4787.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2232, pruned_loss=0.04165, over 972324.66 frames.], batch size: 18, lr: 3.92e-04
2022-05-05 04:33:20,885 INFO [train.py:715] (4/8) Epoch 5, batch 8900, loss[loss=0.1328, simple_loss=0.2008, pruned_loss=0.03245, over 4816.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2226, pruned_loss=0.04092, over 972236.77 frames.], batch size: 13, lr: 3.92e-04
2022-05-05 04:33:59,746 INFO [train.py:715] (4/8) Epoch 5, batch 8950, loss[loss=0.1483, simple_loss=0.2141, pruned_loss=0.04125, over 4884.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2227, pruned_loss=0.04069, over 972148.53 frames.], batch size: 22, lr: 3.92e-04
2022-05-05 04:34:39,031 INFO [train.py:715] (4/8) Epoch 5, batch 9000, loss[loss=0.1201, simple_loss=0.1817, pruned_loss=0.02926, over 4792.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2232, pruned_loss=0.04077, over 972036.14 frames.], batch size: 13, lr: 3.92e-04
2022-05-05 04:34:39,031 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 04:34:48,552 INFO [train.py:742] (4/8) Epoch 5, validation: loss=0.1105, simple_loss=0.196, pruned_loss=0.01252, over 914524.00 frames.
2022-05-05 04:35:28,194 INFO [train.py:715] (4/8) Epoch 5, batch 9050, loss[loss=0.1569, simple_loss=0.2308, pruned_loss=0.04153, over 4704.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2234, pruned_loss=0.04105, over 972740.64 frames.], batch size: 15, lr: 3.92e-04
2022-05-05 04:36:07,671 INFO [train.py:715] (4/8) Epoch 5, batch 9100, loss[loss=0.16, simple_loss=0.2155, pruned_loss=0.05226, over 4962.00 frames.], tot_loss[loss=0.154, simple_loss=0.2243, pruned_loss=0.04184, over 972918.85 frames.], batch size: 21, lr: 3.92e-04
2022-05-05 04:36:46,712 INFO [train.py:715] (4/8) Epoch 5, batch 9150, loss[loss=0.1582, simple_loss=0.2305, pruned_loss=0.043, over 4936.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2239, pruned_loss=0.0418, over 973622.30 frames.], batch size: 29, lr: 3.92e-04
2022-05-05 04:37:26,203 INFO [train.py:715] (4/8) Epoch 5, batch 9200, loss[loss=0.1491, simple_loss=0.2112, pruned_loss=0.04348, over 4972.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2243, pruned_loss=0.04222, over 972931.04 frames.], batch size: 35, lr: 3.92e-04
2022-05-05 04:38:06,418 INFO [train.py:715] (4/8) Epoch 5, batch 9250, loss[loss=0.1399, simple_loss=0.2219, pruned_loss=0.02892, over 4802.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2249, pruned_loss=0.04198, over 973652.37 frames.], batch size: 25, lr: 3.92e-04
2022-05-05 04:38:45,290 INFO [train.py:715] (4/8) Epoch 5, batch 9300, loss[loss=0.1405, simple_loss=0.2177, pruned_loss=0.03166, over 4754.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2238, pruned_loss=0.04138, over 973231.33 frames.], batch size: 16, lr: 3.91e-04
2022-05-05 04:39:24,930 INFO [train.py:715] (4/8) Epoch 5, batch 9350, loss[loss=0.1659, simple_loss=0.2374, pruned_loss=0.04722, over 4850.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2238, pruned_loss=0.04175, over 972707.17 frames.], batch size: 30, lr: 3.91e-04
2022-05-05 04:40:04,421 INFO [train.py:715] (4/8) Epoch 5, batch 9400, loss[loss=0.1798, simple_loss=0.2557, pruned_loss=0.05191, over 4700.00 frames.], tot_loss[loss=0.153, simple_loss=0.2232, pruned_loss=0.04142, over 972169.32 frames.], batch size: 15, lr: 3.91e-04
2022-05-05 04:40:43,713 INFO [train.py:715] (4/8) Epoch 5, batch 9450, loss[loss=0.1266, simple_loss=0.1995, pruned_loss=0.02681, over 4858.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2238, pruned_loss=0.04152, over 971266.91 frames.], batch size: 20, lr: 3.91e-04
2022-05-05 04:41:22,596 INFO [train.py:715] (4/8) Epoch 5, batch 9500, loss[loss=0.1523, simple_loss=0.2166, pruned_loss=0.04395, over 4757.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2233, pruned_loss=0.04121, over 971288.79 frames.], batch size: 17, lr: 3.91e-04
2022-05-05 04:42:02,153 INFO [train.py:715] (4/8) Epoch 5, batch 9550, loss[loss=0.156, simple_loss=0.2343, pruned_loss=0.03879, over 4985.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2238, pruned_loss=0.04171, over 970982.69 frames.], batch size: 25, lr: 3.91e-04
2022-05-05 04:42:41,920 INFO [train.py:715] (4/8) Epoch 5, batch 9600, loss[loss=0.1743, simple_loss=0.2454, pruned_loss=0.05161, over 4772.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2239, pruned_loss=0.0418, over 971041.11 frames.], batch size: 18, lr: 3.91e-04
2022-05-05 04:43:21,155 INFO [train.py:715] (4/8) Epoch 5, batch 9650, loss[loss=0.1462, simple_loss=0.2206, pruned_loss=0.03592, over 4940.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2229, pruned_loss=0.04135, over 972082.55 frames.], batch size: 35, lr: 3.91e-04
2022-05-05 04:44:00,807 INFO [train.py:715] (4/8) Epoch 5, batch 9700, loss[loss=0.1453, simple_loss=0.2208, pruned_loss=0.03492, over 4825.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2231, pruned_loss=0.04127, over 971451.88 frames.], batch size: 26, lr: 3.91e-04
2022-05-05 04:44:40,236 INFO [train.py:715] (4/8) Epoch 5, batch 9750, loss[loss=0.1375, simple_loss=0.2228, pruned_loss=0.02612, over 4756.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2231, pruned_loss=0.04106, over 972623.91 frames.], batch size: 19, lr: 3.91e-04
2022-05-05 04:45:19,134 INFO [train.py:715] (4/8) Epoch 5, batch 9800, loss[loss=0.1462, simple_loss=0.2107, pruned_loss=0.04089, over 4867.00 frames.], tot_loss[loss=0.1537, simple_loss=0.224, pruned_loss=0.04163, over 972502.11 frames.], batch size: 32, lr: 3.91e-04
2022-05-05 04:45:58,977 INFO [train.py:715] (4/8) Epoch 5, batch 9850, loss[loss=0.1489, simple_loss=0.2155, pruned_loss=0.0411, over 4835.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2237, pruned_loss=0.04126, over 972294.60 frames.], batch size: 15, lr: 3.91e-04
2022-05-05 04:46:38,173 INFO [train.py:715] (4/8) Epoch 5, batch 9900, loss[loss=0.1803, simple_loss=0.2487, pruned_loss=0.05595, over 4978.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2248, pruned_loss=0.04205, over 973381.83 frames.], batch size: 39, lr: 3.91e-04
2022-05-05 04:47:17,938 INFO [train.py:715] (4/8) Epoch 5, batch 9950, loss[loss=0.1365, simple_loss=0.2126, pruned_loss=0.03018, over 4924.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2247, pruned_loss=0.04144, over 973251.23 frames.], batch size: 18, lr: 3.91e-04
2022-05-05 04:47:59,850 INFO [train.py:715] (4/8) Epoch 5, batch 10000, loss[loss=0.1594, simple_loss=0.2339, pruned_loss=0.04245, over 4902.00 frames.], tot_loss[loss=0.1545, simple_loss=0.2251, pruned_loss=0.04195, over 972773.43 frames.], batch size: 18, lr: 3.91e-04
2022-05-05 04:48:39,807 INFO [train.py:715] (4/8) Epoch 5, batch 10050, loss[loss=0.1843, simple_loss=0.2447, pruned_loss=0.06191, over 4957.00 frames.], tot_loss[loss=0.155, simple_loss=0.2256, pruned_loss=0.04218, over 972930.11 frames.], batch size: 39, lr: 3.91e-04
2022-05-05 04:49:19,415 INFO [train.py:715] (4/8) Epoch 5, batch 10100, loss[loss=0.1529, simple_loss=0.2159, pruned_loss=0.04495, over 4937.00 frames.], tot_loss[loss=0.1552, simple_loss=0.2255, pruned_loss=0.04247, over 974004.95 frames.], batch size: 21, lr: 3.91e-04
2022-05-05 04:49:58,585 INFO [train.py:715] (4/8) Epoch 5, batch 10150, loss[loss=0.1436, simple_loss=0.2293, pruned_loss=0.02893, over 4895.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2247, pruned_loss=0.04208, over 973210.34 frames.], batch size: 39, lr: 3.91e-04
2022-05-05 04:50:38,451 INFO [train.py:715] (4/8) Epoch 5, batch 10200, loss[loss=0.1676, simple_loss=0.2377, pruned_loss=0.04875, over 4936.00 frames.], tot_loss[loss=0.1544, simple_loss=0.2248, pruned_loss=0.04196, over 972463.08 frames.], batch size: 23, lr: 3.91e-04
2022-05-05 04:51:17,794 INFO [train.py:715] (4/8) Epoch 5, batch 10250, loss[loss=0.1359, simple_loss=0.2079, pruned_loss=0.03196, over 4816.00 frames.], tot_loss[loss=0.1543, simple_loss=0.2246, pruned_loss=0.04203, over 972752.70 frames.], batch size: 14, lr: 3.90e-04
2022-05-05 04:51:56,801 INFO [train.py:715] (4/8) Epoch 5, batch 10300, loss[loss=0.1604, simple_loss=0.2394, pruned_loss=0.04069, over 4962.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2232, pruned_loss=0.0411, over 972737.94 frames.], batch size: 29, lr: 3.90e-04
2022-05-05 04:52:36,625 INFO [train.py:715] (4/8) Epoch 5, batch 10350, loss[loss=0.126, simple_loss=0.2011, pruned_loss=0.02549, over 4951.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2233, pruned_loss=0.04085, over 972977.60 frames.], batch size: 21, lr: 3.90e-04
2022-05-05 04:53:15,663 INFO [train.py:715] (4/8) Epoch 5, batch 10400, loss[loss=0.1293, simple_loss=0.2067, pruned_loss=0.02592, over 4913.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2232, pruned_loss=0.04169, over 972227.69 frames.], batch size: 17, lr: 3.90e-04
2022-05-05 04:53:55,615 INFO [train.py:715] (4/8) Epoch 5, batch 10450, loss[loss=0.1346, simple_loss=0.2115, pruned_loss=0.0289, over 4956.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2238, pruned_loss=0.04193, over 972338.83 frames.], batch size: 24, lr: 3.90e-04
2022-05-05 04:54:35,512 INFO [train.py:715] (4/8) Epoch 5, batch 10500, loss[loss=0.1833, simple_loss=0.257, pruned_loss=0.05481, over 4981.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2241, pruned_loss=0.04211, over 972125.53 frames.], batch size: 24, lr: 3.90e-04
2022-05-05 04:55:15,981 INFO [train.py:715] (4/8) Epoch 5, batch 10550, loss[loss=0.1361, simple_loss=0.1967, pruned_loss=0.03779, over 4790.00 frames.], tot_loss[loss=0.154, simple_loss=0.2242, pruned_loss=0.04189, over 971799.12 frames.], batch size: 12, lr: 3.90e-04
2022-05-05 04:55:55,071 INFO [train.py:715] (4/8) Epoch 5, batch 10600, loss[loss=0.1472, simple_loss=0.2256, pruned_loss=0.03442, over 4699.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2243, pruned_loss=0.042, over 971235.16 frames.], batch size: 15, lr: 3.90e-04
2022-05-05 04:56:34,538 INFO [train.py:715] (4/8) Epoch 5, batch 10650, loss[loss=0.1923, simple_loss=0.261, pruned_loss=0.06177, over 4843.00 frames.], tot_loss[loss=0.1542, simple_loss=0.2247, pruned_loss=0.0419, over 971650.71 frames.], batch size: 15, lr: 3.90e-04
2022-05-05 04:57:14,068 INFO [train.py:715] (4/8) Epoch 5, batch 10700, loss[loss=0.1391, simple_loss=0.2134, pruned_loss=0.03236, over 4804.00 frames.], tot_loss[loss=0.1548, simple_loss=0.2254, pruned_loss=0.04213, over 970944.01 frames.], batch size: 21, lr: 3.90e-04
2022-05-05 04:57:53,022 INFO [train.py:715] (4/8) Epoch 5, batch 10750, loss[loss=0.1537, simple_loss=0.2351, pruned_loss=0.03613, over 4974.00 frames.], tot_loss[loss=0.1541, simple_loss=0.225, pruned_loss=0.04165, over 972369.54 frames.], batch size: 14, lr: 3.90e-04
2022-05-05 04:58:32,275 INFO [train.py:715] (4/8) Epoch 5, batch 10800, loss[loss=0.1567, simple_loss=0.218, pruned_loss=0.04767, over 4895.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2235, pruned_loss=0.04077, over 971975.05 frames.], batch size: 16, lr: 3.90e-04
2022-05-05 04:59:11,503 INFO [train.py:715] (4/8) Epoch 5, batch 10850, loss[loss=0.1708, simple_loss=0.2372, pruned_loss=0.05219, over 4872.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2229, pruned_loss=0.04029, over 971414.62 frames.], batch size: 16, lr: 3.90e-04
2022-05-05 04:59:51,498 INFO [train.py:715] (4/8) Epoch 5, batch 10900, loss[loss=0.1465, simple_loss=0.2374, pruned_loss=0.02784, over 4787.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2236, pruned_loss=0.04028, over 971647.13 frames.], batch size: 14, lr: 3.90e-04
2022-05-05 05:00:30,697 INFO [train.py:715] (4/8) Epoch 5, batch 10950, loss[loss=0.1499, simple_loss=0.226, pruned_loss=0.0369, over 4771.00 frames.], tot_loss[loss=0.1525, simple_loss=0.224, pruned_loss=0.0405, over 972580.46 frames.], batch size: 14, lr: 3.90e-04
2022-05-05 05:01:10,468 INFO [train.py:715] (4/8) Epoch 5, batch 11000, loss[loss=0.1787, simple_loss=0.248, pruned_loss=0.05473, over 4969.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2237, pruned_loss=0.04098, over 972533.54 frames.], batch size: 35, lr: 3.90e-04
2022-05-05 05:01:49,963 INFO [train.py:715] (4/8) Epoch 5, batch 11050, loss[loss=0.1638, simple_loss=0.2352, pruned_loss=0.04623, over 4959.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2231, pruned_loss=0.04066, over 972933.65 frames.], batch size: 35, lr: 3.90e-04
2022-05-05 05:02:29,386 INFO [train.py:715] (4/8) Epoch 5, batch 11100, loss[loss=0.1567, simple_loss=0.2251, pruned_loss=0.04413, over 4951.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2232, pruned_loss=0.04063, over 972297.76 frames.], batch size: 24, lr: 3.90e-04
2022-05-05 05:03:08,927 INFO [train.py:715] (4/8) Epoch 5, batch 11150, loss[loss=0.1352, simple_loss=0.2105, pruned_loss=0.02996, over 4846.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2232, pruned_loss=0.04068, over 972144.92 frames.], batch size: 20, lr: 3.90e-04
2022-05-05 05:03:48,022 INFO [train.py:715] (4/8) Epoch 5, batch 11200, loss[loss=0.1502, simple_loss=0.2184, pruned_loss=0.04101, over 4888.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2225, pruned_loss=0.04062, over 971952.55 frames.], batch size: 19, lr: 3.89e-04
2022-05-05 05:04:27,936 INFO [train.py:715] (4/8) Epoch 5, batch 11250, loss[loss=0.1483, simple_loss=0.2188, pruned_loss=0.03887, over 4854.00 frames.], tot_loss[loss=0.152, simple_loss=0.2225, pruned_loss=0.04071, over 971659.04 frames.], batch size: 20, lr: 3.89e-04
2022-05-05 05:05:07,258 INFO [train.py:715] (4/8) Epoch 5, batch 11300, loss[loss=0.1513, simple_loss=0.2121, pruned_loss=0.04522, over 4931.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2224, pruned_loss=0.04058, over 972029.51 frames.], batch size: 23, lr: 3.89e-04
2022-05-05 05:05:46,393 INFO [train.py:715] (4/8) Epoch 5, batch 11350, loss[loss=0.1486, simple_loss=0.2309, pruned_loss=0.03318, over 4817.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2217, pruned_loss=0.03991, over 971911.46 frames.], batch size: 27, lr: 3.89e-04
2022-05-05 05:06:27,197 INFO [train.py:715] (4/8) Epoch 5, batch 11400, loss[loss=0.1195, simple_loss=0.1968, pruned_loss=0.02114, over 4938.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2215, pruned_loss=0.03972, over 971531.98 frames.], batch size: 21, lr: 3.89e-04
2022-05-05 05:07:07,355 INFO [train.py:715] (4/8) Epoch 5, batch 11450, loss[loss=0.1571, simple_loss=0.2179, pruned_loss=0.04814, over 4972.00 frames.], tot_loss[loss=0.151, simple_loss=0.2219, pruned_loss=0.04006, over 971816.55 frames.], batch size: 24, lr: 3.89e-04
2022-05-05 05:07:47,392 INFO [train.py:715] (4/8) Epoch 5, batch 11500, loss[loss=0.1124, simple_loss=0.1842, pruned_loss=0.02027, over 4952.00 frames.], tot_loss[loss=0.15, simple_loss=0.2207, pruned_loss=0.03959, over 972006.01 frames.], batch size: 14, lr: 3.89e-04
2022-05-05 05:08:27,418 INFO [train.py:715] (4/8) Epoch 5, batch 11550, loss[loss=0.1646, simple_loss=0.2402, pruned_loss=0.04453, over 4827.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2211, pruned_loss=0.03927, over 972523.69 frames.], batch size: 15, lr: 3.89e-04
2022-05-05 05:09:07,601 INFO [train.py:715] (4/8) Epoch 5, batch 11600, loss[loss=0.135, simple_loss=0.2053, pruned_loss=0.0324, over 4966.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2215, pruned_loss=0.03956, over 973474.52 frames.], batch size: 14, lr: 3.89e-04
2022-05-05 05:09:48,305 INFO [train.py:715] (4/8) Epoch 5, batch 11650, loss[loss=0.1409, simple_loss=0.2092, pruned_loss=0.03631, over 4803.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2227, pruned_loss=0.0405, over 972660.10 frames.], batch size: 21, lr: 3.89e-04
2022-05-05 05:10:28,058 INFO [train.py:715] (4/8) Epoch 5, batch 11700, loss[loss=0.1387, simple_loss=0.2207, pruned_loss=0.0284, over 4966.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2215, pruned_loss=0.04008, over 971955.93 frames.], batch size: 15, lr: 3.89e-04
2022-05-05 05:11:08,774 INFO [train.py:715] (4/8) Epoch 5, batch 11750, loss[loss=0.1647, simple_loss=0.2278, pruned_loss=0.05077, over 4971.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04041, over 971413.57 frames.], batch size: 15, lr: 3.89e-04
2022-05-05 05:11:48,918 INFO [train.py:715] (4/8) Epoch 5, batch 11800, loss[loss=0.1466, simple_loss=0.2181, pruned_loss=0.03758, over 4897.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2221, pruned_loss=0.04054, over 971580.50 frames.], batch size: 39, lr: 3.89e-04
2022-05-05 05:12:29,042 INFO [train.py:715] (4/8) Epoch 5, batch 11850, loss[loss=0.1431, simple_loss=0.2122, pruned_loss=0.03701, over 4764.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2223, pruned_loss=0.04091, over 971558.99 frames.], batch size: 18, lr: 3.89e-04
2022-05-05 05:13:08,178 INFO [train.py:715] (4/8) Epoch 5, batch 11900, loss[loss=0.1443, simple_loss=0.2095, pruned_loss=0.03957, over 4814.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2217, pruned_loss=0.04054, over 971590.70 frames.], batch size: 27, lr: 3.89e-04
2022-05-05 05:13:47,504 INFO [train.py:715] (4/8) Epoch 5, batch 11950, loss[loss=0.1299, simple_loss=0.205, pruned_loss=0.02741, over 4987.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2222, pruned_loss=0.04034, over 971659.76 frames.], batch size: 25, lr: 3.89e-04
2022-05-05 05:14:27,512 INFO [train.py:715] (4/8) Epoch 5, batch 12000, loss[loss=0.1477, simple_loss=0.2205, pruned_loss=0.03752, over 4929.00 frames.], tot_loss[loss=0.1504, simple_loss=0.221, pruned_loss=0.03986, over 971428.76 frames.], batch size: 18, lr: 3.89e-04
2022-05-05 05:14:27,513 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 05:14:37,326 INFO [train.py:742] (4/8) Epoch 5, validation: loss=0.1103, simple_loss=0.1957, pruned_loss=0.01243, over 914524.00 frames.
2022-05-05 05:15:17,600 INFO [train.py:715] (4/8) Epoch 5, batch 12050, loss[loss=0.1616, simple_loss=0.2258, pruned_loss=0.04868, over 4727.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04042, over 971401.07 frames.], batch size: 15, lr: 3.89e-04
2022-05-05 05:15:57,245 INFO [train.py:715] (4/8) Epoch 5, batch 12100, loss[loss=0.1675, simple_loss=0.2339, pruned_loss=0.05055, over 4760.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2228, pruned_loss=0.0408, over 972391.33 frames.], batch size: 16, lr: 3.89e-04
2022-05-05 05:16:36,757 INFO [train.py:715] (4/8) Epoch 5, batch 12150, loss[loss=0.1136, simple_loss=0.1883, pruned_loss=0.01943, over 4976.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2229, pruned_loss=0.04062, over 972494.62 frames.], batch size: 15, lr: 3.88e-04
2022-05-05 05:17:16,018 INFO [train.py:715] (4/8) Epoch 5, batch 12200, loss[loss=0.1383, simple_loss=0.2138, pruned_loss=0.03144, over 4984.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2232, pruned_loss=0.04084, over 972934.01 frames.], batch size: 24, lr: 3.88e-04
2022-05-05 05:17:56,096 INFO [train.py:715] (4/8) Epoch 5, batch 12250, loss[loss=0.1493, simple_loss=0.2254, pruned_loss=0.03656, over 4817.00 frames.], tot_loss[loss=0.1528, simple_loss=0.224, pruned_loss=0.0408, over 972393.52 frames.], batch size: 26, lr: 3.88e-04
2022-05-05 05:18:35,376 INFO [train.py:715] (4/8) Epoch 5, batch 12300, loss[loss=0.1314, simple_loss=0.212, pruned_loss=0.02537, over 4753.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2241, pruned_loss=0.04049, over 971722.37 frames.], batch size: 19, lr: 3.88e-04
2022-05-05 05:19:14,277 INFO [train.py:715] (4/8) Epoch 5, batch 12350, loss[loss=0.1358, simple_loss=0.2156, pruned_loss=0.02797, over 4903.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2229, pruned_loss=0.04006, over 972557.60 frames.], batch size: 19, lr: 3.88e-04
2022-05-05 05:19:53,842 INFO [train.py:715] (4/8) Epoch 5, batch 12400, loss[loss=0.1574, simple_loss=0.2233, pruned_loss=0.04575, over 4836.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2226, pruned_loss=0.04026, over 971956.88 frames.], batch size: 15, lr: 3.88e-04
2022-05-05 05:20:33,430 INFO [train.py:715] (4/8) Epoch 5, batch 12450, loss[loss=0.1657, simple_loss=0.219, pruned_loss=0.05615, over 4974.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03973, over 972465.27 frames.], batch size: 33, lr: 3.88e-04
2022-05-05 05:21:12,658 INFO [train.py:715] (4/8) Epoch 5, batch 12500, loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03069, over 4917.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2226, pruned_loss=0.04047, over 971905.16 frames.], batch size: 29, lr: 3.88e-04
2022-05-05 05:21:51,879 INFO [train.py:715] (4/8) Epoch 5, batch 12550, loss[loss=0.1636, simple_loss=0.2437, pruned_loss=0.04172, over 4786.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2232, pruned_loss=0.04058, over 972462.71 frames.], batch size: 21, lr: 3.88e-04
2022-05-05 05:22:30,628 INFO [train.py:715] (4/8) Epoch 5, batch 12600, loss[loss=0.1474, simple_loss=0.2141, pruned_loss=0.04032, over 4990.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2225, pruned_loss=0.04062, over 972307.15 frames.], batch size: 14, lr: 3.88e-04
2022-05-05 05:23:08,927 INFO [train.py:715] (4/8) Epoch 5, batch 12650, loss[loss=0.1454, simple_loss=0.2151, pruned_loss=0.03786, over 4931.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2229, pruned_loss=0.04051, over 972216.25 frames.], batch size: 23, lr: 3.88e-04
2022-05-05 05:23:47,147 INFO [train.py:715] (4/8) Epoch 5, batch 12700, loss[loss=0.1568, simple_loss=0.2164, pruned_loss=0.04861, over 4882.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2225, pruned_loss=0.04028, over 972358.08 frames.], batch size: 16, lr: 3.88e-04
2022-05-05 05:24:27,029 INFO [train.py:715] (4/8) Epoch 5, batch 12750, loss[loss=0.1478, simple_loss=0.2035, pruned_loss=0.04598, over 4833.00 frames.], tot_loss[loss=0.1519, simple_loss=0.223, pruned_loss=0.04039, over 972546.66 frames.], batch size: 30, lr: 3.88e-04
2022-05-05 05:25:06,593 INFO [train.py:715] (4/8) Epoch 5, batch 12800, loss[loss=0.1436, simple_loss=0.2202, pruned_loss=0.03356, over 4975.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2226, pruned_loss=0.0404, over 973114.89 frames.], batch size: 28, lr: 3.88e-04
2022-05-05 05:25:46,749 INFO [train.py:715] (4/8) Epoch 5, batch 12850, loss[loss=0.1874, simple_loss=0.2565, pruned_loss=0.05918, over 4870.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2229, pruned_loss=0.04074, over 972930.06 frames.], batch size: 32, lr: 3.88e-04
2022-05-05 05:26:26,311 INFO [train.py:715] (4/8) Epoch 5, batch 12900, loss[loss=0.1881, simple_loss=0.2575, pruned_loss=0.05931, over 4787.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2241, pruned_loss=0.04124, over 972790.01 frames.], batch size: 17, lr: 3.88e-04
2022-05-05 05:27:06,309 INFO [train.py:715] (4/8) Epoch 5, batch 12950, loss[loss=0.1715, simple_loss=0.2391, pruned_loss=0.052, over 4976.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2244, pruned_loss=0.0416, over 973739.19 frames.], batch size: 24, lr: 3.88e-04
2022-05-05 05:27:45,736 INFO [train.py:715] (4/8) Epoch 5, batch 13000, loss[loss=0.1345, simple_loss=0.2141, pruned_loss=0.02747, over 4927.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2224, pruned_loss=0.04056, over 974235.40 frames.], batch size: 23, lr: 3.88e-04
2022-05-05 05:28:25,603 INFO [train.py:715] (4/8) Epoch 5, batch 13050, loss[loss=0.1575, simple_loss=0.2238, pruned_loss=0.04562, over 4826.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2229, pruned_loss=0.04083, over 973326.59 frames.], batch size: 15, lr: 3.88e-04
2022-05-05 05:29:03,810 INFO [train.py:715] (4/8) Epoch 5, batch 13100, loss[loss=0.1655, simple_loss=0.2335, pruned_loss=0.04879, over 4825.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2226, pruned_loss=0.0409, over 973436.33 frames.], batch size: 15, lr: 3.87e-04
2022-05-05 05:29:42,389 INFO [train.py:715] (4/8) Epoch 5, batch 13150, loss[loss=0.1464, simple_loss=0.2225, pruned_loss=0.03519, over 4818.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2232, pruned_loss=0.0412, over 972544.08 frames.], batch size: 25, lr: 3.87e-04
2022-05-05 05:30:20,478 INFO [train.py:715] (4/8) Epoch 5, batch 13200, loss[loss=0.1576, simple_loss=0.2338, pruned_loss=0.04071, over 4986.00 frames.], tot_loss[loss=0.151, simple_loss=0.2218, pruned_loss=0.04005, over 972339.82 frames.], batch size: 24, lr: 3.87e-04
2022-05-05 05:30:58,489 INFO [train.py:715] (4/8) Epoch 5, batch 13250, loss[loss=0.1665, simple_loss=0.2346, pruned_loss=0.04924, over 4900.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2219, pruned_loss=0.04054, over 971688.71 frames.], batch size: 19, lr: 3.87e-04
2022-05-05 05:31:37,094 INFO [train.py:715] (4/8) Epoch 5, batch 13300, loss[loss=0.1398, simple_loss=0.2085, pruned_loss=0.03552, over 4794.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2222, pruned_loss=0.041, over 972490.26 frames.], batch size: 17, lr: 3.87e-04
2022-05-05 05:32:14,954 INFO [train.py:715] (4/8) Epoch 5, batch 13350, loss[loss=0.1842, simple_loss=0.246, pruned_loss=0.06117, over 4811.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2225, pruned_loss=0.04105, over 972977.07 frames.], batch size: 26, lr: 3.87e-04
2022-05-05 05:32:53,087 INFO [train.py:715] (4/8) Epoch 5, batch 13400, loss[loss=0.1523, simple_loss=0.2259, pruned_loss=0.03941, over 4803.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2229, pruned_loss=0.04107, over 971626.01 frames.], batch size: 21, lr: 3.87e-04
2022-05-05 05:33:30,832 INFO [train.py:715] (4/8) Epoch 5, batch 13450, loss[loss=0.1331, simple_loss=0.2103, pruned_loss=0.02794, over 4930.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2231, pruned_loss=0.04101, over 972840.09 frames.], batch size: 21, lr: 3.87e-04
2022-05-05 05:34:09,168 INFO [train.py:715] (4/8) Epoch 5, batch 13500, loss[loss=0.1351, simple_loss=0.2165, pruned_loss=0.0268, over 4941.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2226, pruned_loss=0.04046, over 973034.14 frames.], batch size: 29, lr: 3.87e-04
2022-05-05 05:34:47,072 INFO [train.py:715] (4/8) Epoch 5, batch 13550, loss[loss=0.1498, simple_loss=0.1995, pruned_loss=0.05002, over 4766.00 frames.], tot_loss[loss=0.1516, simple_loss=0.222, pruned_loss=0.04059, over 973235.96 frames.], batch size: 14, lr: 3.87e-04
2022-05-05 05:35:24,569 INFO [train.py:715] (4/8) Epoch 5, batch 13600, loss[loss=0.1674, simple_loss=0.2298, pruned_loss=0.05245, over 4887.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04038, over 972200.96 frames.], batch size: 16, lr: 3.87e-04
2022-05-05 05:36:03,224 INFO [train.py:715] (4/8) Epoch 5, batch 13650, loss[loss=0.1356, simple_loss=0.1958, pruned_loss=0.03765, over 4861.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2217, pruned_loss=0.04, over 971913.72 frames.], batch size: 32, lr: 3.87e-04
2022-05-05 05:36:41,018 INFO [train.py:715] (4/8) Epoch 5, batch 13700, loss[loss=0.1299, simple_loss=0.2092, pruned_loss=0.02526, over 4767.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2211, pruned_loss=0.03959, over 973001.86 frames.], batch size: 18, lr: 3.87e-04
2022-05-05 05:37:19,075 INFO [train.py:715] (4/8) Epoch 5, batch 13750, loss[loss=0.1495, simple_loss=0.2127, pruned_loss=0.04317, over 4895.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2205, pruned_loss=0.03924, over 972602.46 frames.], batch size: 19, lr: 3.87e-04
2022-05-05 05:37:56,882 INFO [train.py:715] (4/8) Epoch 5, batch 13800, loss[loss=0.1138, simple_loss=0.1893, pruned_loss=0.0192, over 4914.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2218, pruned_loss=0.0399, over 971622.49 frames.], batch size: 29, lr: 3.87e-04
2022-05-05 05:38:35,346 INFO [train.py:715] (4/8) Epoch 5, batch 13850, loss[loss=0.1428, simple_loss=0.2224, pruned_loss=0.03159, over 4813.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2215, pruned_loss=0.04044, over 971363.96 frames.], batch size: 21, lr: 3.87e-04
2022-05-05 05:39:13,572 INFO [train.py:715] (4/8) Epoch 5, batch 13900, loss[loss=0.1242, simple_loss=0.1996, pruned_loss=0.02435, over 4931.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2212, pruned_loss=0.04046, over 971433.67 frames.], batch size: 21, lr: 3.87e-04
2022-05-05 05:39:51,057 INFO [train.py:715] (4/8) Epoch 5, batch 13950, loss[loss=0.1784, simple_loss=0.2516, pruned_loss=0.05257, over 4963.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2211, pruned_loss=0.04032, over 971839.74 frames.], batch size: 39, lr: 3.87e-04
2022-05-05 05:40:29,789 INFO [train.py:715] (4/8) Epoch 5, batch 14000, loss[loss=0.1589, simple_loss=0.2201, pruned_loss=0.0489, over 4789.00 frames.], tot_loss[loss=0.15, simple_loss=0.2204, pruned_loss=0.03982, over 970751.84 frames.], batch size: 24, lr: 3.87e-04
2022-05-05 05:41:07,818 INFO [train.py:715] (4/8) Epoch 5, batch 14050, loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.03555, over 4828.00 frames.], tot_loss[loss=0.15, simple_loss=0.2205, pruned_loss=0.03973, over 970808.07 frames.], batch size: 13, lr: 3.87e-04
2022-05-05 05:41:45,579 INFO [train.py:715] (4/8) Epoch 5, batch 14100, loss[loss=0.1494, simple_loss=0.226, pruned_loss=0.0364, over 4814.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2216, pruned_loss=0.04029, over 970427.76 frames.], batch size: 21, lr: 3.86e-04
2022-05-05 05:42:23,455 INFO [train.py:715] (4/8) Epoch 5, batch 14150, loss[loss=0.1422, simple_loss=0.2124, pruned_loss=0.03604, over 4951.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2215, pruned_loss=0.04053, over 970996.69 frames.], batch size: 21, lr: 3.86e-04
2022-05-05 05:43:01,800 INFO [train.py:715] (4/8) Epoch 5, batch 14200, loss[loss=0.1575, simple_loss=0.2186, pruned_loss=0.04822, over 4817.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2219, pruned_loss=0.04033, over 970719.57 frames.], batch size: 15, lr: 3.86e-04
2022-05-05 05:43:40,052 INFO [train.py:715] (4/8) Epoch 5, batch 14250, loss[loss=0.1533, simple_loss=0.242, pruned_loss=0.03225, over 4878.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2224, pruned_loss=0.04034, over 971367.13 frames.], batch size: 16, lr: 3.86e-04
2022-05-05 05:44:18,050 INFO [train.py:715] (4/8) Epoch 5, batch 14300, loss[loss=0.1699, simple_loss=0.2372, pruned_loss=0.05128, over 4982.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2224, pruned_loss=0.04037, over 971824.05 frames.], batch size: 33, lr: 3.86e-04
2022-05-05 05:44:56,436 INFO [train.py:715] (4/8) Epoch 5, batch 14350, loss[loss=0.1892, simple_loss=0.2511, pruned_loss=0.06365, over 4852.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2227, pruned_loss=0.04024, over 972109.49 frames.], batch size: 15, lr: 3.86e-04
2022-05-05 05:45:34,231 INFO [train.py:715] (4/8) Epoch 5, batch 14400, loss[loss=0.1499, simple_loss=0.2256, pruned_loss=0.03711, over 4791.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2224, pruned_loss=0.03993, over 972105.74 frames.], batch size: 17, lr: 3.86e-04
2022-05-05 05:46:11,864 INFO [train.py:715] (4/8) Epoch 5, batch 14450, loss[loss=0.1892, simple_loss=0.2604, pruned_loss=0.05904, over 4804.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2208, pruned_loss=0.03926, over 970861.51 frames.], batch size: 25, lr: 3.86e-04
2022-05-05 05:46:49,662 INFO [train.py:715] (4/8) Epoch 5, batch 14500, loss[loss=0.1408, simple_loss=0.2099, pruned_loss=0.03588, over 4779.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2211, pruned_loss=0.03933, over 972151.04 frames.], batch size: 18, lr: 3.86e-04
2022-05-05 05:47:27,996 INFO [train.py:715] (4/8) Epoch 5, batch 14550, loss[loss=0.1438, simple_loss=0.2262, pruned_loss=0.03075, over 4871.00 frames.], tot_loss[loss=0.151, simple_loss=0.2218, pruned_loss=0.04006, over 973221.02 frames.], batch size: 32, lr: 3.86e-04
2022-05-05 05:48:06,093 INFO [train.py:715] (4/8) Epoch 5, batch 14600, loss[loss=0.1531, simple_loss=0.2221, pruned_loss=0.04209, over 4923.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2223, pruned_loss=0.04059, over 972655.80 frames.], batch size: 23, lr: 3.86e-04
2022-05-05 05:48:44,026 INFO [train.py:715] (4/8) Epoch 5, batch 14650, loss[loss=0.1447, simple_loss=0.21, pruned_loss=0.03966, over 4991.00 frames.], tot_loss[loss=0.1535, simple_loss=0.2235, pruned_loss=0.04171, over 972877.17 frames.], batch size: 14, lr: 3.86e-04
2022-05-05 05:49:22,272 INFO [train.py:715] (4/8) Epoch 5, batch 14700, loss[loss=0.1676, simple_loss=0.2273, pruned_loss=0.05393, over 4776.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2234, pruned_loss=0.0417, over 972882.15 frames.], batch size: 17, lr: 3.86e-04
2022-05-05 05:49:59,645 INFO [train.py:715] (4/8) Epoch 5, batch 14750, loss[loss=0.125, simple_loss=0.1894, pruned_loss=0.03026, over 4734.00 frames.], tot_loss[loss=0.1542, simple_loss=0.224, pruned_loss=0.04217, over 972454.62 frames.], batch size: 12, lr: 3.86e-04
2022-05-05 05:50:37,675 INFO [train.py:715] (4/8) Epoch 5, batch 14800, loss[loss=0.1279, simple_loss=0.2032, pruned_loss=0.02632, over 4770.00 frames.], tot_loss[loss=0.1541, simple_loss=0.2238, pruned_loss=0.04213, over 972502.34 frames.], batch size: 18, lr: 3.86e-04
2022-05-05 05:51:15,493 INFO [train.py:715] (4/8) Epoch 5, batch 14850, loss[loss=0.1577, simple_loss=0.2237, pruned_loss=0.04589, over 4851.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2237, pruned_loss=0.04188, over 972475.58 frames.], batch size: 20, lr: 3.86e-04
2022-05-05 05:51:54,089 INFO [train.py:715] (4/8) Epoch 5, batch 14900, loss[loss=0.1419, simple_loss=0.2047, pruned_loss=0.03955, over 4919.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2232, pruned_loss=0.04124, over 973015.15 frames.], batch size: 18, lr: 3.86e-04
2022-05-05 05:52:32,750 INFO [train.py:715] (4/8) Epoch 5, batch 14950, loss[loss=0.1577, simple_loss=0.2308, pruned_loss=0.04227, over 4831.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2225, pruned_loss=0.0406, over 973010.09 frames.], batch size: 15, lr: 3.86e-04
2022-05-05 05:53:10,810 INFO [train.py:715] (4/8) Epoch 5, batch 15000, loss[loss=0.1562, simple_loss=0.2204, pruned_loss=0.04599, over 4871.00 frames.], tot_loss[loss=0.1513, simple_loss=0.222, pruned_loss=0.04032, over 974224.80 frames.], batch size: 32, lr: 3.86e-04
2022-05-05 05:53:10,810 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 05:53:21,082 INFO [train.py:742] (4/8) Epoch 5, validation: loss=0.1105, simple_loss=0.1958, pruned_loss=0.01261, over 914524.00 frames.
2022-05-05 05:53:58,557 INFO [train.py:715] (4/8) Epoch 5, batch 15050, loss[loss=0.1303, simple_loss=0.2066, pruned_loss=0.02697, over 4944.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2223, pruned_loss=0.04062, over 973274.92 frames.], batch size: 21, lr: 3.85e-04
2022-05-05 05:54:37,214 INFO [train.py:715] (4/8) Epoch 5, batch 15100, loss[loss=0.1585, simple_loss=0.2376, pruned_loss=0.03968, over 4751.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2233, pruned_loss=0.04078, over 973074.38 frames.], batch size: 19, lr: 3.85e-04
2022-05-05 05:55:15,135 INFO [train.py:715] (4/8) Epoch 5, batch 15150, loss[loss=0.1493, simple_loss=0.2168, pruned_loss=0.04085, over 4966.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2243, pruned_loss=0.04147, over 972975.35 frames.], batch size: 31, lr: 3.85e-04
2022-05-05 05:55:53,270 INFO [train.py:715] (4/8) Epoch 5, batch 15200, loss[loss=0.1545, simple_loss=0.2348, pruned_loss=0.03707, over 4813.00 frames.], tot_loss[loss=0.1536, simple_loss=0.2245, pruned_loss=0.0414, over 973042.66 frames.], batch size: 27, lr: 3.85e-04
2022-05-05 05:56:32,188 INFO [train.py:715] (4/8) Epoch 5, batch 15250, loss[loss=0.1454, simple_loss=0.2239, pruned_loss=0.03346, over 4889.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2237, pruned_loss=0.04089, over 972765.81 frames.], batch size: 16, lr: 3.85e-04
2022-05-05 05:57:10,898 INFO [train.py:715] (4/8) Epoch 5, batch 15300, loss[loss=0.1853, simple_loss=0.247, pruned_loss=0.06183, over 4857.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2238, pruned_loss=0.04072, over 972518.43 frames.], batch size: 15, lr: 3.85e-04
2022-05-05 05:57:50,139 INFO [train.py:715] (4/8) Epoch 5, batch 15350, loss[loss=0.1408, simple_loss=0.2181, pruned_loss=0.03181, over 4935.00 frames.], tot_loss[loss=0.1532, simple_loss=0.224, pruned_loss=0.04119, over 972091.30 frames.], batch size: 23, lr: 3.85e-04
2022-05-05 05:58:28,474 INFO [train.py:715] (4/8) Epoch 5, batch 15400, loss[loss=0.1885, simple_loss=0.243, pruned_loss=0.06701, over 4848.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2233, pruned_loss=0.04082, over 972661.78 frames.], batch size: 15, lr: 3.85e-04
2022-05-05 05:59:07,519 INFO [train.py:715] (4/8) Epoch 5, batch 15450, loss[loss=0.1427, simple_loss=0.2057, pruned_loss=0.03986, over 4765.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2223, pruned_loss=0.04072, over 972537.38 frames.], batch size: 12, lr: 3.85e-04
2022-05-05 05:59:46,049 INFO [train.py:715] (4/8) Epoch 5, batch 15500, loss[loss=0.1156, simple_loss=0.1895, pruned_loss=0.02084, over 4961.00 frames.], tot_loss[loss=0.153, simple_loss=0.2232, pruned_loss=0.04138, over 972204.97 frames.], batch size: 24, lr: 3.85e-04
2022-05-05 06:00:25,317 INFO [train.py:715] (4/8) Epoch 5, batch 15550, loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03004, over 4938.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2236, pruned_loss=0.04148, over 973166.24 frames.], batch size: 23, lr: 3.85e-04
2022-05-05 06:01:03,324 INFO [train.py:715] (4/8) Epoch 5, batch 15600, loss[loss=0.1468, simple_loss=0.2296, pruned_loss=0.032, over 4773.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2239, pruned_loss=0.04118, over 973123.52 frames.], batch size: 18, lr: 3.85e-04
2022-05-05 06:01:40,923 INFO [train.py:715] (4/8) Epoch 5, batch 15650, loss[loss=0.1545, simple_loss=0.2238, pruned_loss=0.04254, over 4772.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2232, pruned_loss=0.04105, over 973283.78 frames.], batch size: 17, lr: 3.85e-04
2022-05-05 06:02:18,446 INFO [train.py:715] (4/8) Epoch 5, batch 15700, loss[loss=0.1383, simple_loss=0.2164, pruned_loss=0.03011, over 4688.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2226, pruned_loss=0.04087, over 972626.96 frames.], batch size: 15, lr: 3.85e-04
2022-05-05 06:02:56,463 INFO [train.py:715] (4/8) Epoch 5, batch 15750, loss[loss=0.1458, simple_loss=0.2138, pruned_loss=0.03892, over 4787.00 frames.], tot_loss[loss=0.1526, simple_loss=0.223, pruned_loss=0.04106, over 971997.57 frames.], batch size: 17, lr: 3.85e-04
2022-05-05 06:03:34,887 INFO [train.py:715] (4/8) Epoch 5, batch 15800, loss[loss=0.16, simple_loss=0.239, pruned_loss=0.04046, over 4976.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2225, pruned_loss=0.0404, over 972548.99 frames.], batch size: 39, lr: 3.85e-04
2022-05-05 06:04:12,955 INFO [train.py:715] (4/8) Epoch 5, batch 15850, loss[loss=0.1658, simple_loss=0.2325, pruned_loss=0.04954, over 4876.00 frames.], tot_loss[loss=0.1511, simple_loss=0.222, pruned_loss=0.04013, over 972768.29 frames.], batch size: 16, lr: 3.85e-04
2022-05-05 06:04:50,528 INFO [train.py:715] (4/8) Epoch 5, batch 15900, loss[loss=0.1711, simple_loss=0.2454, pruned_loss=0.04836, over 4811.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2224, pruned_loss=0.04023, over 973087.17 frames.], batch size: 15, lr: 3.85e-04
2022-05-05 06:05:28,343 INFO [train.py:715] (4/8) Epoch 5, batch 15950, loss[loss=0.141, simple_loss=0.2059, pruned_loss=0.03804, over 4943.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2223, pruned_loss=0.04064, over 972953.92 frames.], batch size: 21, lr: 3.85e-04
2022-05-05 06:06:05,813 INFO [train.py:715] (4/8) Epoch 5, batch 16000, loss[loss=0.1385, simple_loss=0.2113, pruned_loss=0.03287, over 4939.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2219, pruned_loss=0.04056, over 973327.91 frames.], batch size: 21, lr: 3.85e-04
2022-05-05 06:06:43,535 INFO [train.py:715] (4/8) Epoch 5, batch 16050, loss[loss=0.1651, simple_loss=0.2312, pruned_loss=0.04948, over 4905.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.04026, over 972866.47 frames.], batch size: 19, lr: 3.84e-04
2022-05-05 06:07:21,601 INFO [train.py:715] (4/8) Epoch 5, batch 16100, loss[loss=0.1464, simple_loss=0.2174, pruned_loss=0.0377, over 4878.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2219, pruned_loss=0.04065, over 972367.55 frames.], batch size: 22, lr: 3.84e-04
2022-05-05 06:08:00,772 INFO [train.py:715] (4/8) Epoch 5, batch 16150, loss[loss=0.1287, simple_loss=0.2028, pruned_loss=0.02731, over 4936.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2228, pruned_loss=0.04071, over 972159.03 frames.], batch size: 18, lr: 3.84e-04
2022-05-05 06:08:39,729 INFO [train.py:715] (4/8) Epoch 5, batch 16200, loss[loss=0.1457, simple_loss=0.226, pruned_loss=0.03268, over 4949.00 frames.], tot_loss[loss=0.1515, simple_loss=0.222, pruned_loss=0.04046, over 971802.77 frames.], batch size: 21, lr: 3.84e-04
2022-05-05 06:09:18,291 INFO [train.py:715] (4/8) Epoch 5, batch 16250, loss[loss=0.1514, simple_loss=0.2271, pruned_loss=0.03782, over 4894.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2215, pruned_loss=0.04009, over 971601.71 frames.], batch size: 17, lr: 3.84e-04
2022-05-05 06:09:56,099 INFO [train.py:715] (4/8) Epoch 5, batch 16300, loss[loss=0.15, simple_loss=0.2213, pruned_loss=0.03934, over 4753.00 frames.], tot_loss[loss=0.151, simple_loss=0.2218, pruned_loss=0.04011, over 971456.58 frames.], batch size: 14, lr: 3.84e-04
2022-05-05 06:10:34,129 INFO [train.py:715] (4/8) Epoch 5, batch 16350, loss[loss=0.1475, simple_loss=0.2217, pruned_loss=0.03659, over 4987.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2222, pruned_loss=0.04024, over 971564.81 frames.], batch size: 25, lr: 3.84e-04
2022-05-05 06:11:12,494 INFO [train.py:715] (4/8) Epoch 5, batch 16400, loss[loss=0.1348, simple_loss=0.2092, pruned_loss=0.03023, over 4988.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2216, pruned_loss=0.03983, over 971604.37 frames.], batch size: 14, lr: 3.84e-04
2022-05-05 06:11:50,949 INFO [train.py:715] (4/8) Epoch 5, batch 16450, loss[loss=0.1548, simple_loss=0.2239, pruned_loss=0.04283, over 4964.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2225, pruned_loss=0.04051, over 972953.49 frames.], batch size: 35, lr: 3.84e-04
2022-05-05 06:12:30,301 INFO [train.py:715] (4/8) Epoch 5, batch 16500, loss[loss=0.137, simple_loss=0.206, pruned_loss=0.03396, over 4976.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2226, pruned_loss=0.04078, over 972237.16 frames.], batch size: 39, lr: 3.84e-04
2022-05-05 06:13:08,220 INFO [train.py:715] (4/8) Epoch 5, batch 16550, loss[loss=0.188, simple_loss=0.2607, pruned_loss=0.05769, over 4697.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2224, pruned_loss=0.04093, over 972223.83 frames.], batch size: 15, lr: 3.84e-04
2022-05-05 06:13:46,905 INFO [train.py:715] (4/8) Epoch 5, batch 16600, loss[loss=0.1693, simple_loss=0.2409, pruned_loss=0.04889, over 4880.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2235, pruned_loss=0.04155, over 971968.15 frames.], batch size: 32, lr: 3.84e-04
2022-05-05 06:14:25,620 INFO [train.py:715] (4/8) Epoch 5, batch 16650, loss[loss=0.1606, simple_loss=0.2251, pruned_loss=0.04807, over 4966.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2232, pruned_loss=0.04169, over 972209.54 frames.], batch size: 35, lr: 3.84e-04
2022-05-05 06:15:04,295 INFO [train.py:715] (4/8) Epoch 5, batch 16700, loss[loss=0.1453, simple_loss=0.2226, pruned_loss=0.03398, over 4821.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2229, pruned_loss=0.04149, over 972334.66 frames.], batch size: 26, lr: 3.84e-04
2022-05-05 06:15:42,484 INFO [train.py:715] (4/8) Epoch 5, batch 16750, loss[loss=0.1356, simple_loss=0.1993, pruned_loss=0.03589, over 4794.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2221, pruned_loss=0.04139, over 972928.49 frames.], batch size: 12, lr: 3.84e-04
2022-05-05 06:16:20,935 INFO [train.py:715] (4/8) Epoch 5, batch 16800, loss[loss=0.1391, simple_loss=0.2097, pruned_loss=0.0342, over 4785.00 frames.], tot_loss[loss=0.153, simple_loss=0.2225, pruned_loss=0.04172, over 973430.42 frames.], batch size: 12, lr: 3.84e-04
2022-05-05 06:17:00,069 INFO [train.py:715] (4/8) Epoch 5, batch 16850, loss[loss=0.1521, simple_loss=0.2198, pruned_loss=0.04218, over 4974.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2228, pruned_loss=0.04185, over 972808.58 frames.], batch size: 15, lr: 3.84e-04
2022-05-05 06:17:37,929 INFO [train.py:715] (4/8) Epoch 5, batch 16900, loss[loss=0.1504, simple_loss=0.225, pruned_loss=0.03792, over 4826.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2221, pruned_loss=0.04183, over 972655.68 frames.], batch size: 25, lr: 3.84e-04
2022-05-05 06:18:16,756 INFO [train.py:715] (4/8) Epoch 5, batch 16950, loss[loss=0.1537, simple_loss=0.2324, pruned_loss=0.0375, over 4836.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2224, pruned_loss=0.04171, over 972480.35 frames.], batch size: 27, lr: 3.84e-04
2022-05-05 06:18:55,160 INFO [train.py:715] (4/8) Epoch 5, batch 17000, loss[loss=0.1236, simple_loss=0.1951, pruned_loss=0.02602, over 4968.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2227, pruned_loss=0.04155, over 972613.25 frames.], batch size: 35, lr: 3.84e-04
2022-05-05 06:19:33,550 INFO [train.py:715] (4/8) Epoch 5, batch 17050, loss[loss=0.1956, simple_loss=0.2574, pruned_loss=0.06696, over 4927.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2213, pruned_loss=0.04048, over 973598.49 frames.], batch size: 18, lr: 3.83e-04
2022-05-05 06:20:11,943 INFO [train.py:715] (4/8) Epoch 5, batch 17100, loss[loss=0.1794, simple_loss=0.2482, pruned_loss=0.05531, over 4841.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2227, pruned_loss=0.04106, over 973724.58 frames.], batch size: 15, lr: 3.83e-04
2022-05-05 06:20:49,749 INFO [train.py:715] (4/8) Epoch 5, batch 17150, loss[loss=0.1658, simple_loss=0.236, pruned_loss=0.04775, over 4911.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2224, pruned_loss=0.04073, over 973308.92 frames.], batch size: 17, lr: 3.83e-04
2022-05-05 06:21:27,630 INFO [train.py:715] (4/8) Epoch 5, batch 17200, loss[loss=0.1175, simple_loss=0.1927, pruned_loss=0.0212, over 4897.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2226, pruned_loss=0.04092, over 973277.91 frames.], batch size: 19, lr: 3.83e-04
2022-05-05 06:22:04,736 INFO [train.py:715] (4/8) Epoch 5, batch 17250, loss[loss=0.1674, simple_loss=0.2542, pruned_loss=0.04027, over 4874.00 frames.], tot_loss[loss=0.1518, simple_loss=0.222, pruned_loss=0.04075, over 973166.52 frames.], batch size: 22, lr: 3.83e-04
2022-05-05 06:22:42,971 INFO [train.py:715] (4/8) Epoch 5, batch 17300, loss[loss=0.1403, simple_loss=0.2236, pruned_loss=0.0285, over 4831.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2225, pruned_loss=0.04063, over 972576.97 frames.], batch size: 25, lr: 3.83e-04
2022-05-05 06:23:22,498 INFO [train.py:715] (4/8) Epoch 5, batch 17350, loss[loss=0.1298, simple_loss=0.2107, pruned_loss=0.0244, over 4980.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2219, pruned_loss=0.04054, over 972685.36 frames.], batch size: 28, lr: 3.83e-04
2022-05-05 06:24:00,864 INFO [train.py:715] (4/8) Epoch 5, batch 17400, loss[loss=0.1554, simple_loss=0.2272, pruned_loss=0.04183, over 4917.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2222, pruned_loss=0.04065, over 972618.13 frames.], batch size: 17, lr: 3.83e-04
2022-05-05 06:24:39,482 INFO [train.py:715] (4/8) Epoch 5, batch 17450, loss[loss=0.1516, simple_loss=0.2181, pruned_loss=0.0426, over 4868.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2221, pruned_loss=0.0407, over 972185.10 frames.], batch size: 16, lr: 3.83e-04
2022-05-05 06:25:17,956 INFO [train.py:715] (4/8) Epoch 5, batch 17500, loss[loss=0.1427, simple_loss=0.2157, pruned_loss=0.03488, over 4954.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2223, pruned_loss=0.04069, over 971640.85 frames.], batch size: 35, lr: 3.83e-04
2022-05-05 06:25:56,806 INFO [train.py:715] (4/8) Epoch 5, batch 17550, loss[loss=0.1376, simple_loss=0.2071, pruned_loss=0.03407, over 4817.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2223, pruned_loss=0.04033, over 970982.85 frames.], batch size: 13, lr: 3.83e-04
2022-05-05 06:26:35,441 INFO [train.py:715] (4/8) Epoch 5, batch 17600, loss[loss=0.1793, simple_loss=0.2658, pruned_loss=0.04645, over 4819.00 frames.], tot_loss[loss=0.1524, simple_loss=0.223, pruned_loss=0.04089, over 971382.33 frames.], batch size: 15, lr: 3.83e-04
2022-05-05 06:27:14,153 INFO [train.py:715] (4/8) Epoch 5, batch 17650, loss[loss=0.166, simple_loss=0.235, pruned_loss=0.04846, over 4951.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2223, pruned_loss=0.04037, over 971676.44 frames.], batch size: 29, lr: 3.83e-04
2022-05-05 06:27:52,810 INFO [train.py:715] (4/8) Epoch 5, batch 17700, loss[loss=0.1819, simple_loss=0.2482, pruned_loss=0.05778, over 4875.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2219, pruned_loss=0.04066, over 971405.83 frames.], batch size: 32, lr: 3.83e-04
2022-05-05 06:28:31,728 INFO [train.py:715] (4/8) Epoch 5, batch 17750, loss[loss=0.1378, simple_loss=0.1998, pruned_loss=0.03786, over 4831.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2215, pruned_loss=0.04037, over 971933.15 frames.], batch size: 15, lr: 3.83e-04
2022-05-05 06:29:09,753 INFO [train.py:715] (4/8) Epoch 5, batch 17800, loss[loss=0.1411, simple_loss=0.2173, pruned_loss=0.03241, over 4804.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2224, pruned_loss=0.04054, over 971857.12 frames.], batch size: 25, lr: 3.83e-04
2022-05-05 06:29:48,585 INFO [train.py:715] (4/8) Epoch 5, batch 17850, loss[loss=0.1583, simple_loss=0.2295, pruned_loss=0.04353, over 4822.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2226, pruned_loss=0.04031, over 971050.93 frames.], batch size: 27, lr: 3.83e-04
2022-05-05 06:30:27,679 INFO [train.py:715] (4/8) Epoch 5, batch 17900, loss[loss=0.1958, simple_loss=0.2715, pruned_loss=0.06009, over 4945.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2222, pruned_loss=0.04024, over 971501.16 frames.], batch size: 24, lr: 3.83e-04
2022-05-05 06:31:06,345 INFO [train.py:715] (4/8) Epoch 5, batch 17950, loss[loss=0.1555, simple_loss=0.2321, pruned_loss=0.0395, over 4922.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2231, pruned_loss=0.04072, over 970947.30 frames.], batch size: 23, lr: 3.83e-04
2022-05-05 06:31:47,054 INFO [train.py:715] (4/8) Epoch 5, batch 18000, loss[loss=0.1597, simple_loss=0.2155, pruned_loss=0.05195, over 4865.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2227, pruned_loss=0.04073, over 971078.82 frames.], batch size: 32, lr: 3.83e-04
2022-05-05 06:31:47,055 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 06:31:59,752 INFO [train.py:742] (4/8) Epoch 5, validation: loss=0.1102, simple_loss=0.1955, pruned_loss=0.01245, over 914524.00 frames.
2022-05-05 06:32:38,354 INFO [train.py:715] (4/8) Epoch 5, batch 18050, loss[loss=0.1126, simple_loss=0.1794, pruned_loss=0.02287, over 4777.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2221, pruned_loss=0.04088, over 971421.00 frames.], batch size: 12, lr: 3.82e-04
2022-05-05 06:33:17,598 INFO [train.py:715] (4/8) Epoch 5, batch 18100, loss[loss=0.1649, simple_loss=0.2224, pruned_loss=0.05366, over 4861.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2222, pruned_loss=0.04063, over 971505.92 frames.], batch size: 32, lr: 3.82e-04
2022-05-05 06:33:56,333 INFO [train.py:715] (4/8) Epoch 5, batch 18150, loss[loss=0.1728, simple_loss=0.2391, pruned_loss=0.0533, over 4738.00 frames.], tot_loss[loss=0.1525, simple_loss=0.223, pruned_loss=0.04097, over 971197.60 frames.], batch size: 16, lr: 3.82e-04
2022-05-05 06:34:34,860 INFO [train.py:715] (4/8) Epoch 5, batch 18200, loss[loss=0.1205, simple_loss=0.1945, pruned_loss=0.02322, over 4852.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2232, pruned_loss=0.041, over 971802.03 frames.], batch size: 13, lr: 3.82e-04
2022-05-05 06:35:14,237 INFO [train.py:715] (4/8) Epoch 5, batch 18250, loss[loss=0.185, simple_loss=0.2408, pruned_loss=0.06456, over 4825.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2233, pruned_loss=0.04113, over 971961.18 frames.], batch size: 15, lr: 3.82e-04
2022-05-05 06:35:53,137 INFO [train.py:715] (4/8) Epoch 5, batch 18300, loss[loss=0.1518, simple_loss=0.2218, pruned_loss=0.04084, over 4838.00 frames.], tot_loss[loss=0.1538, simple_loss=0.2244, pruned_loss=0.04157, over 972267.52 frames.], batch size: 13, lr: 3.82e-04
2022-05-05 06:36:31,710 INFO [train.py:715] (4/8) Epoch 5, batch 18350, loss[loss=0.1312, simple_loss=0.2216, pruned_loss=0.02042, over 4793.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2237, pruned_loss=0.04107, over 972344.43 frames.], batch size: 17, lr: 3.82e-04
2022-05-05 06:37:09,999 INFO [train.py:715] (4/8) Epoch 5, batch 18400, loss[loss=0.1401, simple_loss=0.2075, pruned_loss=0.03634, over 4869.00 frames.], tot_loss[loss=0.153, simple_loss=0.2238, pruned_loss=0.0411, over 971551.63 frames.], batch size: 22, lr: 3.82e-04
2022-05-05 06:37:49,155 INFO [train.py:715] (4/8) Epoch 5, batch 18450, loss[loss=0.1243, simple_loss=0.1859, pruned_loss=0.03133, over 4823.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2233, pruned_loss=0.04075, over 971691.97 frames.], batch size: 12, lr: 3.82e-04
2022-05-05 06:38:27,817 INFO [train.py:715] (4/8) Epoch 5, batch 18500, loss[loss=0.1516, simple_loss=0.2114, pruned_loss=0.04591, over 4899.00 frames.], tot_loss[loss=0.1533, simple_loss=0.224, pruned_loss=0.04135, over 972127.84 frames.], batch size: 19, lr: 3.82e-04
2022-05-05 06:39:06,127 INFO [train.py:715] (4/8) Epoch 5, batch 18550, loss[loss=0.1509, simple_loss=0.2283, pruned_loss=0.03677, over 4792.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2241, pruned_loss=0.0412, over 972659.70 frames.], batch size: 17, lr: 3.82e-04
2022-05-05 06:39:45,170 INFO [train.py:715] (4/8) Epoch 5, batch 18600, loss[loss=0.1396, simple_loss=0.2202, pruned_loss=0.02951, over 4815.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2247, pruned_loss=0.04134, over 972646.94 frames.], batch size: 25, lr: 3.82e-04
2022-05-05 06:40:23,781 INFO [train.py:715] (4/8) Epoch 5, batch 18650, loss[loss=0.1453, simple_loss=0.2261, pruned_loss=0.03228, over 4770.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2238, pruned_loss=0.04123, over 972889.66 frames.], batch size: 17, lr: 3.82e-04
2022-05-05 06:41:01,937 INFO [train.py:715] (4/8) Epoch 5, batch 18700, loss[loss=0.1771, simple_loss=0.2422, pruned_loss=0.05605, over 4858.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2244, pruned_loss=0.04171, over 973584.92 frames.], batch size: 32, lr: 3.82e-04
2022-05-05 06:41:40,677 INFO [train.py:715] (4/8) Epoch 5, batch 18750, loss[loss=0.1928, simple_loss=0.252, pruned_loss=0.06686, over 4951.00 frames.], tot_loss[loss=0.1533, simple_loss=0.224, pruned_loss=0.04125, over 973004.63 frames.], batch size: 39, lr: 3.82e-04
2022-05-05 06:42:19,955 INFO [train.py:715] (4/8) Epoch 5, batch 18800, loss[loss=0.1657, simple_loss=0.2272, pruned_loss=0.05212, over 4903.00 frames.], tot_loss[loss=0.1534, simple_loss=0.2239, pruned_loss=0.04144, over 972685.26 frames.], batch size: 19, lr: 3.82e-04
2022-05-05 06:42:59,658 INFO [train.py:715] (4/8) Epoch 5, batch 18850, loss[loss=0.1639, simple_loss=0.2354, pruned_loss=0.04625, over 4964.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2237, pruned_loss=0.04133, over 973653.04 frames.], batch size: 35, lr: 3.82e-04
2022-05-05 06:43:38,447 INFO [train.py:715] (4/8) Epoch 5, batch 18900, loss[loss=0.19, simple_loss=0.26, pruned_loss=0.05995, over 4979.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2244, pruned_loss=0.0417, over 974173.90 frames.], batch size: 24, lr: 3.82e-04
2022-05-05 06:44:16,646 INFO [train.py:715] (4/8) Epoch 5, batch 18950, loss[loss=0.1811, simple_loss=0.2448, pruned_loss=0.05875, over 4918.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2237, pruned_loss=0.04147, over 973581.72 frames.], batch size: 19, lr: 3.82e-04
2022-05-05 06:44:56,116 INFO [train.py:715] (4/8) Epoch 5, batch 19000, loss[loss=0.1533, simple_loss=0.2215, pruned_loss=0.04253, over 4860.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2228, pruned_loss=0.04096, over 973565.24 frames.], batch size: 32, lr: 3.82e-04
2022-05-05 06:45:34,090 INFO [train.py:715] (4/8) Epoch 5, batch 19050, loss[loss=0.1373, simple_loss=0.1887, pruned_loss=0.04298, over 4832.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2226, pruned_loss=0.04122, over 971781.95 frames.], batch size: 13, lr: 3.81e-04
2022-05-05 06:46:13,031 INFO [train.py:715] (4/8) Epoch 5, batch 19100, loss[loss=0.1474, simple_loss=0.2101, pruned_loss=0.04236, over 4966.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2215, pruned_loss=0.04088, over 971350.45 frames.], batch size: 14, lr: 3.81e-04
2022-05-05 06:46:52,736 INFO [train.py:715] (4/8) Epoch 5, batch 19150, loss[loss=0.1434, simple_loss=0.2282, pruned_loss=0.02932, over 4776.00 frames.], tot_loss[loss=0.152, simple_loss=0.2222, pruned_loss=0.04093, over 971452.15 frames.], batch size: 17, lr: 3.81e-04
2022-05-05 06:47:31,315 INFO [train.py:715] (4/8) Epoch 5, batch 19200, loss[loss=0.1638, simple_loss=0.2322, pruned_loss=0.04766, over 4959.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2223, pruned_loss=0.04053, over 971438.93 frames.], batch size: 35, lr: 3.81e-04
2022-05-05 06:48:10,847 INFO [train.py:715] (4/8) Epoch 5, batch 19250, loss[loss=0.1428, simple_loss=0.2155, pruned_loss=0.03503, over 4776.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2231, pruned_loss=0.04088, over 972268.90 frames.], batch size: 14, lr: 3.81e-04
2022-05-05 06:48:48,907 INFO [train.py:715] (4/8) Epoch 5, batch 19300, loss[loss=0.1926, simple_loss=0.2654, pruned_loss=0.05992, over 4973.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2228, pruned_loss=0.04075, over 972167.13 frames.], batch size: 15, lr: 3.81e-04
2022-05-05 06:49:28,000 INFO [train.py:715] (4/8) Epoch 5, batch 19350, loss[loss=0.1462, simple_loss=0.231, pruned_loss=0.03071, over 4798.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2235, pruned_loss=0.04087, over 971782.02 frames.], batch size: 21, lr: 3.81e-04
2022-05-05 06:50:06,760 INFO [train.py:715] (4/8) Epoch 5, batch 19400, loss[loss=0.161, simple_loss=0.2316, pruned_loss=0.04515, over 4938.00 frames.], tot_loss[loss=0.1522, simple_loss=0.223, pruned_loss=0.04074, over 971740.50 frames.], batch size: 18, lr: 3.81e-04
2022-05-05 06:50:45,414 INFO [train.py:715] (4/8) Epoch 5, batch 19450, loss[loss=0.159, simple_loss=0.2292, pruned_loss=0.04436, over 4821.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2221, pruned_loss=0.04019, over 971610.83 frames.], batch size: 15, lr: 3.81e-04
2022-05-05 06:51:25,049 INFO [train.py:715] (4/8) Epoch 5, batch 19500, loss[loss=0.1627, simple_loss=0.2254, pruned_loss=0.05003, over 4954.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04041, over 971519.33 frames.], batch size: 39, lr: 3.81e-04
2022-05-05 06:52:03,849 INFO [train.py:715] (4/8) Epoch 5, batch 19550, loss[loss=0.1521, simple_loss=0.2221, pruned_loss=0.04105, over 4979.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2212, pruned_loss=0.04005, over 971457.98 frames.], batch size: 35, lr: 3.81e-04
2022-05-05 06:52:42,736 INFO [train.py:715] (4/8) Epoch 5, batch 19600, loss[loss=0.1491, simple_loss=0.2124, pruned_loss=0.04294, over 4766.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2219, pruned_loss=0.04035, over 971207.64 frames.], batch size: 14, lr: 3.81e-04
2022-05-05 06:53:21,193 INFO [train.py:715] (4/8) Epoch 5, batch 19650, loss[loss=0.1809, simple_loss=0.2393, pruned_loss=0.06121, over 4845.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2225, pruned_loss=0.04083, over 971776.88 frames.], batch size: 30, lr: 3.81e-04
2022-05-05 06:54:00,679 INFO [train.py:715] (4/8) Epoch 5, batch 19700, loss[loss=0.173, simple_loss=0.2418, pruned_loss=0.05212, over 4981.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2222, pruned_loss=0.04049, over 972258.56 frames.], batch size: 39, lr: 3.81e-04
2022-05-05 06:54:39,904 INFO [train.py:715] (4/8) Epoch 5, batch 19750, loss[loss=0.1728, simple_loss=0.2512, pruned_loss=0.04726, over 4893.00 frames.], tot_loss[loss=0.152, simple_loss=0.2226, pruned_loss=0.0407, over 971927.92 frames.], batch size: 16, lr: 3.81e-04
2022-05-05 06:55:17,846 INFO [train.py:715] (4/8) Epoch 5, batch 19800, loss[loss=0.1663, simple_loss=0.245, pruned_loss=0.04379, over 4982.00 frames.], tot_loss[loss=0.153, simple_loss=0.2235, pruned_loss=0.04124, over 971384.72 frames.], batch size: 24, lr: 3.81e-04
2022-05-05 06:55:56,846 INFO [train.py:715] (4/8) Epoch 5, batch 19850, loss[loss=0.1628, simple_loss=0.2334, pruned_loss=0.04604, over 4905.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2232, pruned_loss=0.04076, over 971778.74 frames.], batch size: 17, lr: 3.81e-04
2022-05-05 06:56:35,744 INFO [train.py:715] (4/8) Epoch 5, batch 19900, loss[loss=0.1713, simple_loss=0.2336, pruned_loss=0.05446, over 4929.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2226, pruned_loss=0.04061, over 972456.66 frames.], batch size: 39, lr: 3.81e-04
2022-05-05 06:57:14,679 INFO [train.py:715] (4/8) Epoch 5, batch 19950, loss[loss=0.1568, simple_loss=0.2166, pruned_loss=0.04857, over 4925.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2219, pruned_loss=0.04049, over 972206.83 frames.], batch size: 18, lr: 3.81e-04
2022-05-05 06:57:53,094 INFO [train.py:715] (4/8) Epoch 5, batch 20000, loss[loss=0.1386, simple_loss=0.2106, pruned_loss=0.03329, over 4852.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2218, pruned_loss=0.04025, over 972197.04 frames.], batch size: 30, lr: 3.81e-04
2022-05-05 06:58:32,615 INFO [train.py:715] (4/8) Epoch 5, batch 20050, loss[loss=0.156, simple_loss=0.2204, pruned_loss=0.04578, over 4906.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2218, pruned_loss=0.04068, over 972360.86 frames.], batch size: 17, lr: 3.81e-04
2022-05-05 06:59:12,148 INFO [train.py:715] (4/8) Epoch 5, batch 20100, loss[loss=0.1809, simple_loss=0.2472, pruned_loss=0.05735, over 4856.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2229, pruned_loss=0.04127, over 972785.60 frames.], batch size: 30, lr: 3.80e-04
2022-05-05 06:59:50,437 INFO [train.py:715] (4/8) Epoch 5, batch 20150, loss[loss=0.09447, simple_loss=0.1652, pruned_loss=0.01184, over 4813.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2228, pruned_loss=0.0415, over 972792.37 frames.], batch size: 13, lr: 3.80e-04
2022-05-05 07:00:30,259 INFO [train.py:715] (4/8) Epoch 5, batch 20200, loss[loss=0.1639, simple_loss=0.2295, pruned_loss=0.04913, over 4960.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2223, pruned_loss=0.04128, over 973283.65 frames.], batch size: 24, lr: 3.80e-04
2022-05-05 07:01:09,277 INFO [train.py:715] (4/8) Epoch 5, batch 20250, loss[loss=0.1243, simple_loss=0.2025, pruned_loss=0.02306, over 4903.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2213, pruned_loss=0.04054, over 973909.04 frames.], batch size: 19, lr: 3.80e-04
2022-05-05 07:01:47,789 INFO [train.py:715] (4/8) Epoch 5, batch 20300, loss[loss=0.1357, simple_loss=0.2114, pruned_loss=0.03003, over 4969.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2226, pruned_loss=0.04088, over 973230.91 frames.], batch size: 28, lr: 3.80e-04
2022-05-05 07:02:25,750 INFO [train.py:715] (4/8) Epoch 5, batch 20350, loss[loss=0.1524, simple_loss=0.2332, pruned_loss=0.0358, over 4811.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2227, pruned_loss=0.04047, over 972522.86 frames.], batch size: 21, lr: 3.80e-04
2022-05-05 07:03:04,302 INFO [train.py:715] (4/8) Epoch 5, batch 20400, loss[loss=0.1555, simple_loss=0.228, pruned_loss=0.04153, over 4760.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2229, pruned_loss=0.04025, over 971719.32 frames.], batch size: 19, lr: 3.80e-04
2022-05-05 07:03:43,173 INFO [train.py:715] (4/8) Epoch 5, batch 20450, loss[loss=0.1306, simple_loss=0.2141, pruned_loss=0.02353, over 4985.00 frames.], tot_loss[loss=0.153, simple_loss=0.2242, pruned_loss=0.04093, over 971362.22 frames.], batch size: 26, lr: 3.80e-04
2022-05-05 07:04:21,314 INFO [train.py:715] (4/8) Epoch 5, batch 20500, loss[loss=0.164, simple_loss=0.2291, pruned_loss=0.04947, over 4936.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2243, pruned_loss=0.0415, over 971765.95 frames.], batch size: 21, lr: 3.80e-04
2022-05-05 07:05:00,716 INFO [train.py:715] (4/8) Epoch 5, batch 20550, loss[loss=0.1789, simple_loss=0.2475, pruned_loss=0.05519, over 4705.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2238, pruned_loss=0.04117, over 971260.44 frames.], batch size: 15, lr: 3.80e-04
2022-05-05 07:05:39,978 INFO [train.py:715] (4/8) Epoch 5, batch 20600, loss[loss=0.1596, simple_loss=0.2309, pruned_loss=0.04416, over 4914.00 frames.], tot_loss[loss=0.153, simple_loss=0.2235, pruned_loss=0.04121, over 972209.82 frames.], batch size: 29, lr: 3.80e-04
2022-05-05 07:06:18,974 INFO [train.py:715] (4/8) Epoch 5, batch 20650, loss[loss=0.1525, simple_loss=0.2272, pruned_loss=0.03886, over 4748.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2243, pruned_loss=0.04169, over 972044.47 frames.], batch size: 16, lr: 3.80e-04
2022-05-05 07:06:58,194 INFO [train.py:715] (4/8) Epoch 5, batch 20700, loss[loss=0.1751, simple_loss=0.2404, pruned_loss=0.0549, over 4898.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2233, pruned_loss=0.04098, over 972385.81 frames.], batch size: 19, lr: 3.80e-04
2022-05-05 07:07:36,950 INFO [train.py:715] (4/8) Epoch 5, batch 20750, loss[loss=0.1619, simple_loss=0.2369, pruned_loss=0.04342, over 4967.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2235, pruned_loss=0.04112, over 972464.82 frames.], batch size: 24, lr: 3.80e-04
2022-05-05 07:08:16,385 INFO [train.py:715] (4/8) Epoch 5, batch 20800, loss[loss=0.1627, simple_loss=0.227, pruned_loss=0.04918, over 4780.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2237, pruned_loss=0.041, over 972109.59 frames.], batch size: 17, lr: 3.80e-04
2022-05-05 07:08:55,024 INFO [train.py:715] (4/8) Epoch 5, batch 20850, loss[loss=0.1834, simple_loss=0.2542, pruned_loss=0.0563, over 4785.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2236, pruned_loss=0.041, over 971910.58 frames.], batch size: 14, lr: 3.80e-04
2022-05-05 07:09:34,327 INFO [train.py:715] (4/8) Epoch 5, batch 20900, loss[loss=0.163, simple_loss=0.22, pruned_loss=0.05305, over 4948.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2224, pruned_loss=0.04058, over 972887.18 frames.], batch size: 39, lr: 3.80e-04
2022-05-05 07:10:12,903 INFO [train.py:715] (4/8) Epoch 5, batch 20950, loss[loss=0.1469, simple_loss=0.2217, pruned_loss=0.03604, over 4918.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2223, pruned_loss=0.04068, over 973200.39 frames.], batch size: 17, lr: 3.80e-04
2022-05-05 07:10:51,486 INFO [train.py:715] (4/8) Epoch 5, batch 21000, loss[loss=0.1304, simple_loss=0.2097, pruned_loss=0.02554, over 4816.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2223, pruned_loss=0.04077, over 973283.47 frames.], batch size: 15, lr: 3.80e-04
2022-05-05 07:10:51,487 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 07:11:01,469 INFO [train.py:742] (4/8) Epoch 5, validation: loss=0.1101, simple_loss=0.1954, pruned_loss=0.01242, over 914524.00 frames.
2022-05-05 07:11:40,514 INFO [train.py:715] (4/8) Epoch 5, batch 21050, loss[loss=0.1391, simple_loss=0.2022, pruned_loss=0.03798, over 4743.00 frames.], tot_loss[loss=0.152, simple_loss=0.2229, pruned_loss=0.04059, over 972234.95 frames.], batch size: 16, lr: 3.80e-04
2022-05-05 07:12:19,699 INFO [train.py:715] (4/8) Epoch 5, batch 21100, loss[loss=0.162, simple_loss=0.2363, pruned_loss=0.04385, over 4655.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2224, pruned_loss=0.04007, over 971792.15 frames.], batch size: 13, lr: 3.79e-04
2022-05-05 07:12:58,336 INFO [train.py:715] (4/8) Epoch 5, batch 21150, loss[loss=0.1448, simple_loss=0.2089, pruned_loss=0.04029, over 4826.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2219, pruned_loss=0.03996, over 971753.78 frames.], batch size: 12, lr: 3.79e-04
2022-05-05 07:13:37,166 INFO [train.py:715] (4/8) Epoch 5, batch 21200, loss[loss=0.1451, simple_loss=0.2197, pruned_loss=0.03529, over 4939.00 frames.], tot_loss[loss=0.151, simple_loss=0.2222, pruned_loss=0.0399, over 970970.47 frames.], batch size: 23, lr: 3.79e-04
2022-05-05 07:14:15,842 INFO [train.py:715] (4/8) Epoch 5, batch 21250, loss[loss=0.1529, simple_loss=0.2227, pruned_loss=0.04156, over 4954.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2219, pruned_loss=0.03985, over 970764.17 frames.], batch size: 21, lr: 3.79e-04
2022-05-05 07:14:54,662 INFO [train.py:715] (4/8) Epoch 5, batch 21300, loss[loss=0.1619, simple_loss=0.2339, pruned_loss=0.04493, over 4970.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2218, pruned_loss=0.03982, over 970695.08 frames.], batch size: 15, lr: 3.79e-04
2022-05-05 07:15:33,335 INFO [train.py:715] (4/8) Epoch 5, batch 21350, loss[loss=0.1338, simple_loss=0.2157, pruned_loss=0.02597, over 4796.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.0402, over 970750.30 frames.], batch size: 17, lr: 3.79e-04
2022-05-05 07:16:11,915 INFO [train.py:715] (4/8) Epoch 5, batch 21400, loss[loss=0.137, simple_loss=0.208, pruned_loss=0.03294, over 4841.00 frames.], tot_loss[loss=0.151, simple_loss=0.222, pruned_loss=0.04006, over 970824.17 frames.], batch size: 13, lr: 3.79e-04
2022-05-05 07:16:50,973 INFO [train.py:715] (4/8) Epoch 5, batch 21450, loss[loss=0.1957, simple_loss=0.2473, pruned_loss=0.07211, over 4929.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2217, pruned_loss=0.03998, over 971701.82 frames.], batch size: 35, lr: 3.79e-04
2022-05-05 07:17:29,099 INFO [train.py:715] (4/8) Epoch 5, batch 21500, loss[loss=0.1319, simple_loss=0.2035, pruned_loss=0.03011, over 4869.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04039, over 971350.20 frames.], batch size: 22, lr: 3.79e-04
2022-05-05 07:18:08,224 INFO [train.py:715] (4/8) Epoch 5, batch 21550, loss[loss=0.1471, simple_loss=0.2031, pruned_loss=0.04551, over 4851.00 frames.], tot_loss[loss=0.1516, simple_loss=0.222, pruned_loss=0.0406, over 971770.77 frames.], batch size: 32, lr: 3.79e-04
2022-05-05 07:18:46,743 INFO [train.py:715] (4/8) Epoch 5, batch 21600, loss[loss=0.1524, simple_loss=0.2219, pruned_loss=0.04145, over 4988.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2221, pruned_loss=0.04066, over 971809.69 frames.], batch size: 16, lr: 3.79e-04
2022-05-05 07:19:25,825 INFO [train.py:715] (4/8) Epoch 5, batch 21650, loss[loss=0.1423, simple_loss=0.2158, pruned_loss=0.03436, over 4905.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2219, pruned_loss=0.04094, over 971519.79 frames.], batch size: 19, lr: 3.79e-04
2022-05-05 07:20:04,070 INFO [train.py:715] (4/8) Epoch 5, batch 21700, loss[loss=0.1759, simple_loss=0.2381, pruned_loss=0.05679, over 4926.00 frames.], tot_loss[loss=0.1522, simple_loss=0.222, pruned_loss=0.04119, over 971890.05 frames.], batch size: 39, lr: 3.79e-04
2022-05-05 07:20:42,464 INFO [train.py:715] (4/8) Epoch 5, batch 21750, loss[loss=0.1599, simple_loss=0.2384, pruned_loss=0.04067, over 4771.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2219, pruned_loss=0.04097, over 972314.41 frames.], batch size: 19, lr: 3.79e-04
2022-05-05 07:21:20,818 INFO [train.py:715] (4/8) Epoch 5, batch 21800, loss[loss=0.123, simple_loss=0.1892, pruned_loss=0.02841, over 4834.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2218, pruned_loss=0.04072, over 972014.92 frames.], batch size: 12, lr: 3.79e-04
2022-05-05 07:22:00,030 INFO [train.py:715] (4/8) Epoch 5, batch 21850, loss[loss=0.139, simple_loss=0.2051, pruned_loss=0.0364, over 4787.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2225, pruned_loss=0.0411, over 972116.68 frames.], batch size: 14, lr: 3.79e-04
2022-05-05 07:22:38,258 INFO [train.py:715] (4/8) Epoch 5, batch 21900, loss[loss=0.1571, simple_loss=0.23, pruned_loss=0.0421, over 4807.00 frames.], tot_loss[loss=0.1537, simple_loss=0.2243, pruned_loss=0.04156, over 971706.99 frames.], batch size: 21, lr: 3.79e-04
2022-05-05 07:23:16,805 INFO [train.py:715] (4/8) Epoch 5, batch 21950, loss[loss=0.1693, simple_loss=0.232, pruned_loss=0.05329, over 4872.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2227, pruned_loss=0.04095, over 972477.28 frames.], batch size: 16, lr: 3.79e-04
2022-05-05 07:23:55,216 INFO [train.py:715] (4/8) Epoch 5, batch 22000, loss[loss=0.1601, simple_loss=0.2236, pruned_loss=0.04826, over 4938.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2232, pruned_loss=0.04108, over 972911.65 frames.], batch size: 23, lr: 3.79e-04
2022-05-05 07:24:34,742 INFO [train.py:715] (4/8) Epoch 5, batch 22050, loss[loss=0.1378, simple_loss=0.213, pruned_loss=0.03128, over 4684.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2233, pruned_loss=0.04147, over 972006.04 frames.], batch size: 15, lr: 3.79e-04
2022-05-05 07:25:13,188 INFO [train.py:715] (4/8) Epoch 5, batch 22100, loss[loss=0.1665, simple_loss=0.2523, pruned_loss=0.04037, over 4971.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2238, pruned_loss=0.04144, over 971858.81 frames.], batch size: 24, lr: 3.79e-04
2022-05-05 07:25:52,415 INFO [train.py:715] (4/8) Epoch 5, batch 22150, loss[loss=0.1168, simple_loss=0.1908, pruned_loss=0.02145, over 4734.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2239, pruned_loss=0.04126, over 972133.29 frames.], batch size: 16, lr: 3.78e-04
2022-05-05 07:26:31,466 INFO [train.py:715] (4/8) Epoch 5, batch 22200, loss[loss=0.1634, simple_loss=0.2385, pruned_loss=0.04411, over 4987.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2232, pruned_loss=0.04089, over 971590.56 frames.], batch size: 25, lr: 3.78e-04
2022-05-05 07:27:11,167 INFO [train.py:715] (4/8) Epoch 5, batch 22250, loss[loss=0.1664, simple_loss=0.2497, pruned_loss=0.04157, over 4884.00 frames.], tot_loss[loss=0.1539, simple_loss=0.2247, pruned_loss=0.0416, over 972087.29 frames.], batch size: 22, lr: 3.78e-04
2022-05-05 07:27:50,340 INFO [train.py:715] (4/8) Epoch 5, batch 22300, loss[loss=0.105, simple_loss=0.1772, pruned_loss=0.01642, over 4839.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2238, pruned_loss=0.04129, over 971491.44 frames.], batch size: 13, lr: 3.78e-04
2022-05-05 07:28:28,463 INFO [train.py:715] (4/8) Epoch 5, batch 22350, loss[loss=0.1387, simple_loss=0.2069, pruned_loss=0.03524, over 4927.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2235, pruned_loss=0.04137, over 971414.66 frames.], batch size: 18, lr: 3.78e-04
2022-05-05 07:29:06,835 INFO [train.py:715] (4/8) Epoch 5, batch 22400, loss[loss=0.1521, simple_loss=0.2387, pruned_loss=0.03278, over 4934.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2227, pruned_loss=0.0406, over 971377.36 frames.], batch size: 29, lr: 3.78e-04
2022-05-05 07:29:45,744 INFO [train.py:715] (4/8) Epoch 5, batch 22450, loss[loss=0.1221, simple_loss=0.1954, pruned_loss=0.02442, over 4974.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2226, pruned_loss=0.04045, over 971755.30 frames.], batch size: 28, lr: 3.78e-04
2022-05-05 07:30:25,212 INFO [train.py:715] (4/8) Epoch 5, batch 22500, loss[loss=0.1664, simple_loss=0.2195, pruned_loss=0.05664, over 4775.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2221, pruned_loss=0.04042, over 971399.83 frames.], batch size: 17, lr: 3.78e-04
2022-05-05 07:31:03,489 INFO [train.py:715] (4/8) Epoch 5, batch 22550, loss[loss=0.1978, simple_loss=0.2482, pruned_loss=0.07366, over 4770.00 frames.], tot_loss[loss=0.151, simple_loss=0.2215, pruned_loss=0.04024, over 971127.32 frames.], batch size: 18, lr: 3.78e-04
2022-05-05 07:31:42,560 INFO [train.py:715] (4/8) Epoch 5, batch 22600, loss[loss=0.134, simple_loss=0.2023, pruned_loss=0.03285, over 4788.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2211, pruned_loss=0.04019, over 971728.09 frames.], batch size: 24, lr: 3.78e-04
2022-05-05 07:32:21,688 INFO [train.py:715] (4/8) Epoch 5, batch 22650, loss[loss=0.1741, simple_loss=0.2521, pruned_loss=0.04807, over 4773.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2224, pruned_loss=0.04097, over 971316.73 frames.], batch size: 18, lr: 3.78e-04
2022-05-05 07:33:00,846 INFO [train.py:715] (4/8) Epoch 5, batch 22700, loss[loss=0.1413, simple_loss=0.2104, pruned_loss=0.03606, over 4980.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2226, pruned_loss=0.04092, over 971683.86 frames.], batch size: 14, lr: 3.78e-04
2022-05-05 07:33:39,168 INFO [train.py:715] (4/8) Epoch 5, batch 22750, loss[loss=0.1473, simple_loss=0.2151, pruned_loss=0.03974, over 4976.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2223, pruned_loss=0.04067, over 971944.62 frames.], batch size: 25, lr: 3.78e-04
2022-05-05 07:34:18,364 INFO [train.py:715] (4/8) Epoch 5, batch 22800, loss[loss=0.1565, simple_loss=0.2268, pruned_loss=0.0431, over 4777.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04044, over 972452.95 frames.], batch size: 18, lr: 3.78e-04
2022-05-05 07:34:57,944 INFO [train.py:715] (4/8) Epoch 5, batch 22850, loss[loss=0.1704, simple_loss=0.2461, pruned_loss=0.04734, over 4961.00 frames.], tot_loss[loss=0.1531, simple_loss=0.2234, pruned_loss=0.0414, over 972073.79 frames.], batch size: 24, lr: 3.78e-04
2022-05-05 07:35:36,332 INFO [train.py:715] (4/8) Epoch 5, batch 22900, loss[loss=0.1414, simple_loss=0.2115, pruned_loss=0.03565, over 4773.00 frames.], tot_loss[loss=0.153, simple_loss=0.2234, pruned_loss=0.04129, over 971795.16 frames.], batch size: 14, lr: 3.78e-04
2022-05-05 07:36:15,064 INFO [train.py:715] (4/8) Epoch 5, batch 22950, loss[loss=0.1987, simple_loss=0.2618, pruned_loss=0.06776, over 4854.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2232, pruned_loss=0.04098, over 972351.41 frames.], batch size: 20, lr: 3.78e-04
2022-05-05 07:36:54,409 INFO [train.py:715] (4/8) Epoch 5, batch 23000, loss[loss=0.1433, simple_loss=0.2195, pruned_loss=0.03357, over 4792.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2226, pruned_loss=0.04076, over 972007.58 frames.], batch size: 12, lr: 3.78e-04
2022-05-05 07:37:33,567 INFO [train.py:715] (4/8) Epoch 5, batch 23050, loss[loss=0.1469, simple_loss=0.2203, pruned_loss=0.03672, over 4972.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2225, pruned_loss=0.04037, over 971749.52 frames.], batch size: 14, lr: 3.78e-04
2022-05-05 07:38:12,017 INFO [train.py:715] (4/8) Epoch 5, batch 23100, loss[loss=0.137, simple_loss=0.2097, pruned_loss=0.0322, over 4744.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2222, pruned_loss=0.04017, over 971086.81 frames.], batch size: 16, lr: 3.78e-04
2022-05-05 07:38:51,180 INFO [train.py:715] (4/8) Epoch 5, batch 23150, loss[loss=0.1529, simple_loss=0.2258, pruned_loss=0.03994, over 4938.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2232, pruned_loss=0.04059, over 972403.85 frames.], batch size: 23, lr: 3.78e-04
2022-05-05 07:39:30,784 INFO [train.py:715] (4/8) Epoch 5, batch 23200, loss[loss=0.1324, simple_loss=0.2007, pruned_loss=0.03201, over 4857.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2229, pruned_loss=0.04043, over 972273.79 frames.], batch size: 13, lr: 3.77e-04
2022-05-05 07:40:09,161 INFO [train.py:715] (4/8) Epoch 5, batch 23250, loss[loss=0.158, simple_loss=0.2284, pruned_loss=0.04381, over 4888.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2223, pruned_loss=0.0401, over 972758.74 frames.], batch size: 22, lr: 3.77e-04
2022-05-05 07:40:47,784 INFO [train.py:715] (4/8) Epoch 5, batch 23300, loss[loss=0.1284, simple_loss=0.2026, pruned_loss=0.02709, over 4772.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2223, pruned_loss=0.0401, over 972664.39 frames.], batch size: 17, lr: 3.77e-04
2022-05-05 07:41:27,167 INFO [train.py:715] (4/8) Epoch 5, batch 23350, loss[loss=0.1365, simple_loss=0.1987, pruned_loss=0.03712, over 4797.00 frames.], tot_loss[loss=0.1512, simple_loss=0.222, pruned_loss=0.04016, over 972553.55 frames.], batch size: 21, lr: 3.77e-04
2022-05-05 07:42:05,802 INFO [train.py:715] (4/8) Epoch 5, batch 23400, loss[loss=0.1747, simple_loss=0.2395, pruned_loss=0.05499, over 4942.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2214, pruned_loss=0.03971, over 972346.23 frames.], batch size: 39, lr: 3.77e-04
2022-05-05 07:42:44,246 INFO [train.py:715] (4/8) Epoch 5, batch 23450, loss[loss=0.1606, simple_loss=0.2268, pruned_loss=0.04718, over 4844.00 frames.], tot_loss[loss=0.15, simple_loss=0.221, pruned_loss=0.0395, over 971879.79 frames.], batch size: 34, lr: 3.77e-04
2022-05-05 07:43:22,952 INFO [train.py:715] (4/8) Epoch 5, batch 23500, loss[loss=0.1684, simple_loss=0.2453, pruned_loss=0.0458, over 4777.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2224, pruned_loss=0.04017, over 972086.51 frames.], batch size: 14, lr: 3.77e-04
2022-05-05 07:44:02,013 INFO [train.py:715] (4/8) Epoch 5, batch 23550, loss[loss=0.1334, simple_loss=0.2, pruned_loss=0.03342, over 4748.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2223, pruned_loss=0.04004, over 971366.59 frames.], batch size: 19, lr: 3.77e-04
2022-05-05 07:44:40,888 INFO [train.py:715] (4/8) Epoch 5, batch 23600, loss[loss=0.1949, simple_loss=0.2604, pruned_loss=0.06468, over 4993.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2229, pruned_loss=0.0404, over 970380.72 frames.], batch size: 26, lr: 3.77e-04
2022-05-05 07:45:19,392 INFO [train.py:715] (4/8) Epoch 5, batch 23650, loss[loss=0.1582, simple_loss=0.2335, pruned_loss=0.04142, over 4782.00 frames.], tot_loss[loss=0.1508, simple_loss=0.222, pruned_loss=0.03985, over 972107.38 frames.], batch size: 18, lr: 3.77e-04
2022-05-05 07:45:58,897 INFO [train.py:715] (4/8) Epoch 5, batch 23700, loss[loss=0.135, simple_loss=0.2029, pruned_loss=0.03359, over 4816.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2225, pruned_loss=0.04056, over 971560.12 frames.], batch size: 27, lr: 3.77e-04
2022-05-05 07:46:37,476 INFO [train.py:715] (4/8) Epoch 5, batch 23750, loss[loss=0.1727, simple_loss=0.2338, pruned_loss=0.05581, over 4783.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2224, pruned_loss=0.04053, over 971946.94 frames.], batch size: 14, lr: 3.77e-04
2022-05-05 07:47:16,505 INFO [train.py:715] (4/8) Epoch 5, batch 23800, loss[loss=0.1595, simple_loss=0.2346, pruned_loss=0.04223, over 4899.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2225, pruned_loss=0.04065, over 972759.44 frames.], batch size: 19, lr: 3.77e-04
2022-05-05 07:47:55,208 INFO [train.py:715] (4/8) Epoch 5, batch 23850, loss[loss=0.1456, simple_loss=0.2055, pruned_loss=0.04281, over 4831.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2217, pruned_loss=0.03999, over 971439.81 frames.], batch size: 15, lr: 3.77e-04
2022-05-05 07:48:34,418 INFO [train.py:715] (4/8) Epoch 5, batch 23900, loss[loss=0.1612, simple_loss=0.2287, pruned_loss=0.04683, over 4893.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03992, over 970931.03 frames.], batch size: 22, lr: 3.77e-04
2022-05-05 07:49:13,371 INFO [train.py:715] (4/8) Epoch 5, batch 23950, loss[loss=0.1527, simple_loss=0.2142, pruned_loss=0.04554, over 4839.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2219, pruned_loss=0.04032, over 971128.19 frames.], batch size: 15, lr: 3.77e-04
2022-05-05 07:49:51,753 INFO [train.py:715] (4/8) Epoch 5, batch 24000, loss[loss=0.1562, simple_loss=0.227, pruned_loss=0.04269, over 4812.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2224, pruned_loss=0.04085, over 970997.62 frames.], batch size: 14, lr: 3.77e-04
2022-05-05 07:49:51,754 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 07:50:02,183 INFO [train.py:742] (4/8) Epoch 5, validation: loss=0.11, simple_loss=0.1955, pruned_loss=0.0123, over 914524.00 frames.
2022-05-05 07:50:40,723 INFO [train.py:715] (4/8) Epoch 5, batch 24050, loss[loss=0.1605, simple_loss=0.2323, pruned_loss=0.04438, over 4882.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2219, pruned_loss=0.04063, over 971818.26 frames.], batch size: 22, lr: 3.77e-04
2022-05-05 07:51:20,434 INFO [train.py:715] (4/8) Epoch 5, batch 24100, loss[loss=0.1531, simple_loss=0.2181, pruned_loss=0.04406, over 4773.00 frames.], tot_loss[loss=0.152, simple_loss=0.2225, pruned_loss=0.04072, over 971662.70 frames.], batch size: 17, lr: 3.77e-04
2022-05-05 07:51:59,181 INFO [train.py:715] (4/8) Epoch 5, batch 24150, loss[loss=0.1554, simple_loss=0.224, pruned_loss=0.04341, over 4873.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2227, pruned_loss=0.04117, over 972462.81 frames.], batch size: 22, lr: 3.77e-04
2022-05-05 07:52:37,493 INFO [train.py:715] (4/8) Epoch 5, batch 24200, loss[loss=0.1468, simple_loss=0.2219, pruned_loss=0.03586, over 4988.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2222, pruned_loss=0.04096, over 972075.60 frames.], batch size: 25, lr: 3.77e-04
2022-05-05 07:53:16,811 INFO [train.py:715] (4/8) Epoch 5, batch 24250, loss[loss=0.2309, simple_loss=0.3139, pruned_loss=0.07394, over 4775.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2219, pruned_loss=0.04068, over 972392.15 frames.], batch size: 17, lr: 3.76e-04
2022-05-05 07:53:55,923 INFO [train.py:715] (4/8) Epoch 5, batch 24300, loss[loss=0.1433, simple_loss=0.2164, pruned_loss=0.03512, over 4897.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2216, pruned_loss=0.04042, over 972363.40 frames.], batch size: 17, lr: 3.76e-04
2022-05-05 07:54:34,803 INFO [train.py:715] (4/8) Epoch 5, batch 24350, loss[loss=0.1332, simple_loss=0.2114, pruned_loss=0.02753, over 4860.00 frames.], tot_loss[loss=0.15, simple_loss=0.2205, pruned_loss=0.03976, over 972426.18 frames.], batch size: 20, lr: 3.76e-04
2022-05-05 07:55:13,057 INFO [train.py:715] (4/8) Epoch 5, batch 24400, loss[loss=0.1464, simple_loss=0.2195, pruned_loss=0.03662, over 4743.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2203, pruned_loss=0.03937, over 972732.84 frames.], batch size: 16, lr: 3.76e-04
2022-05-05 07:55:52,739 INFO [train.py:715] (4/8) Epoch 5, batch 24450, loss[loss=0.1274, simple_loss=0.2004, pruned_loss=0.0272, over 4927.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2206, pruned_loss=0.03956, over 972552.93 frames.], batch size: 29, lr: 3.76e-04
2022-05-05 07:56:30,708 INFO [train.py:715] (4/8) Epoch 5, batch 24500, loss[loss=0.1445, simple_loss=0.2137, pruned_loss=0.03769, over 4991.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2211, pruned_loss=0.03958, over 972754.41 frames.], batch size: 25, lr: 3.76e-04
2022-05-05 07:57:09,367 INFO [train.py:715] (4/8) Epoch 5, batch 24550, loss[loss=0.1619, simple_loss=0.2335, pruned_loss=0.04519, over 4889.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2218, pruned_loss=0.04003, over 972858.33 frames.], batch size: 19, lr: 3.76e-04
2022-05-05 07:57:48,724 INFO [train.py:715] (4/8) Epoch 5, batch 24600, loss[loss=0.1663, simple_loss=0.2362, pruned_loss=0.04822, over 4748.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.04028, over 972905.33 frames.], batch size: 16, lr: 3.76e-04
2022-05-05 07:58:27,792 INFO [train.py:715] (4/8) Epoch 5, batch 24650, loss[loss=0.1619, simple_loss=0.2457, pruned_loss=0.03905, over 4942.00 frames.], tot_loss[loss=0.152, simple_loss=0.2222, pruned_loss=0.04087, over 973131.82 frames.], batch size: 35, lr: 3.76e-04
2022-05-05 07:59:06,983 INFO [train.py:715] (4/8) Epoch 5, batch 24700, loss[loss=0.1587, simple_loss=0.2399, pruned_loss=0.03881, over 4796.00 frames.], tot_loss[loss=0.152, simple_loss=0.2225, pruned_loss=0.04078, over 972899.83 frames.], batch size: 21, lr: 3.76e-04
2022-05-05 07:59:45,118 INFO [train.py:715] (4/8) Epoch 5, batch 24750, loss[loss=0.1556, simple_loss=0.2194, pruned_loss=0.0459, over 4802.00 frames.], tot_loss[loss=0.1515, simple_loss=0.222, pruned_loss=0.04046, over 973011.99 frames.], batch size: 14, lr: 3.76e-04
2022-05-05 08:00:24,685 INFO [train.py:715] (4/8) Epoch 5, batch 24800, loss[loss=0.1541, simple_loss=0.2208, pruned_loss=0.04364, over 4922.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2219, pruned_loss=0.04039, over 972249.16 frames.], batch size: 23, lr: 3.76e-04
2022-05-05 08:01:03,112 INFO [train.py:715] (4/8) Epoch 5, batch 24850, loss[loss=0.1257, simple_loss=0.2066, pruned_loss=0.02246, over 4951.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03982, over 972818.06 frames.], batch size: 24, lr: 3.76e-04
2022-05-05 08:01:41,876 INFO [train.py:715] (4/8) Epoch 5, batch 24900, loss[loss=0.1536, simple_loss=0.2242, pruned_loss=0.04155, over 4880.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2215, pruned_loss=0.03993, over 973434.36 frames.], batch size: 20, lr: 3.76e-04
2022-05-05 08:02:21,425 INFO [train.py:715] (4/8) Epoch 5, batch 24950, loss[loss=0.1525, simple_loss=0.2227, pruned_loss=0.04109, over 4825.00 frames.], tot_loss[loss=0.1509, simple_loss=0.222, pruned_loss=0.03991, over 973246.72 frames.], batch size: 13, lr: 3.76e-04
2022-05-05 08:03:00,473 INFO [train.py:715] (4/8) Epoch 5, batch 25000, loss[loss=0.1618, simple_loss=0.2385, pruned_loss=0.04255, over 4758.00 frames.], tot_loss[loss=0.1517, simple_loss=0.223, pruned_loss=0.04015, over 972825.89 frames.], batch size: 16, lr: 3.76e-04
2022-05-05 08:03:39,038 INFO [train.py:715] (4/8) Epoch 5, batch 25050, loss[loss=0.1358, simple_loss=0.2119, pruned_loss=0.02986, over 4978.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2233, pruned_loss=0.04045, over 972262.60 frames.], batch size: 25, lr: 3.76e-04
2022-05-05 08:04:17,285 INFO [train.py:715] (4/8) Epoch 5, batch 25100, loss[loss=0.1631, simple_loss=0.2413, pruned_loss=0.04247, over 4897.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2228, pruned_loss=0.0399, over 973503.99 frames.], batch size: 17, lr: 3.76e-04
2022-05-05 08:04:57,545 INFO [train.py:715] (4/8) Epoch 5, batch 25150, loss[loss=0.1332, simple_loss=0.1995, pruned_loss=0.03346, over 4949.00 frames.], tot_loss[loss=0.1514, simple_loss=0.223, pruned_loss=0.03987, over 974150.87 frames.], batch size: 24, lr: 3.76e-04
2022-05-05 08:05:35,727 INFO [train.py:715] (4/8) Epoch 5, batch 25200, loss[loss=0.1877, simple_loss=0.2411, pruned_loss=0.06717, over 4794.00 frames.], tot_loss[loss=0.152, simple_loss=0.2233, pruned_loss=0.0403, over 973227.49 frames.], batch size: 14, lr: 3.76e-04
2022-05-05 08:06:14,579 INFO [train.py:715] (4/8) Epoch 5, batch 25250, loss[loss=0.1604, simple_loss=0.2317, pruned_loss=0.04453, over 4849.00 frames.], tot_loss[loss=0.152, simple_loss=0.2231, pruned_loss=0.04046, over 972838.70 frames.], batch size: 20, lr: 3.76e-04
2022-05-05 08:06:53,405 INFO [train.py:715] (4/8) Epoch 5, batch 25300, loss[loss=0.1745, simple_loss=0.2382, pruned_loss=0.05536, over 4971.00 frames.], tot_loss[loss=0.1526, simple_loss=0.2237, pruned_loss=0.04074, over 972517.77 frames.], batch size: 35, lr: 3.75e-04
2022-05-05 08:07:31,748 INFO [train.py:715] (4/8) Epoch 5, batch 25350, loss[loss=0.1407, simple_loss=0.2278, pruned_loss=0.02683, over 4949.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2228, pruned_loss=0.04077, over 972163.99 frames.], batch size: 21, lr: 3.75e-04
2022-05-05 08:08:10,247 INFO [train.py:715] (4/8) Epoch 5, batch 25400, loss[loss=0.1807, simple_loss=0.2493, pruned_loss=0.05605, over 4849.00 frames.], tot_loss[loss=0.152, simple_loss=0.223, pruned_loss=0.04055, over 972805.84 frames.], batch size: 32, lr: 3.75e-04
2022-05-05 08:08:49,165 INFO [train.py:715] (4/8) Epoch 5, batch 25450, loss[loss=0.1317, simple_loss=0.2078, pruned_loss=0.02783, over 4810.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2233, pruned_loss=0.04076, over 972533.31 frames.], batch size: 25, lr: 3.75e-04
2022-05-05 08:09:28,361 INFO [train.py:715] (4/8) Epoch 5, batch 25500, loss[loss=0.22, simple_loss=0.2708, pruned_loss=0.08459, over 4795.00 frames.], tot_loss[loss=0.153, simple_loss=0.2234, pruned_loss=0.04124, over 972908.39 frames.], batch size: 14, lr: 3.75e-04
2022-05-05 08:10:07,142 INFO [train.py:715] (4/8) Epoch 5, batch 25550, loss[loss=0.1382, simple_loss=0.2185, pruned_loss=0.02898, over 4919.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2236, pruned_loss=0.04086, over 972141.55 frames.], batch size: 17, lr: 3.75e-04
2022-05-05 08:10:45,632 INFO [train.py:715] (4/8) Epoch 5, batch 25600, loss[loss=0.1327, simple_loss=0.2089, pruned_loss=0.02823, over 4820.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2229, pruned_loss=0.0408, over 972814.45 frames.], batch size: 25, lr: 3.75e-04
2022-05-05 08:11:24,704 INFO [train.py:715] (4/8) Epoch 5, batch 25650, loss[loss=0.1537, simple_loss=0.2273, pruned_loss=0.04008, over 4872.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.04011, over 972988.79 frames.], batch size: 22, lr: 3.75e-04
2022-05-05 08:12:03,095 INFO [train.py:715] (4/8) Epoch 5, batch 25700, loss[loss=0.1517, simple_loss=0.213, pruned_loss=0.04525, over 4856.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2219, pruned_loss=0.04047, over 972516.58 frames.], batch size: 32, lr: 3.75e-04
2022-05-05 08:12:41,257 INFO [train.py:715] (4/8) Epoch 5, batch 25750, loss[loss=0.1463, simple_loss=0.214, pruned_loss=0.0393, over 4835.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2218, pruned_loss=0.04049, over 972160.38 frames.], batch size: 30, lr: 3.75e-04
2022-05-05 08:13:20,738 INFO [train.py:715] (4/8) Epoch 5, batch 25800, loss[loss=0.1315, simple_loss=0.2047, pruned_loss=0.02915, over 4921.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2221, pruned_loss=0.04074, over 972240.69 frames.], batch size: 29, lr: 3.75e-04
2022-05-05 08:13:59,832 INFO [train.py:715] (4/8) Epoch 5, batch 25850, loss[loss=0.1516, simple_loss=0.215, pruned_loss=0.04416, over 4830.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2217, pruned_loss=0.04071, over 970986.37 frames.], batch size: 12, lr: 3.75e-04
2022-05-05 08:14:38,583 INFO [train.py:715] (4/8) Epoch 5, batch 25900, loss[loss=0.142, simple_loss=0.2126, pruned_loss=0.03572, over 4873.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2223, pruned_loss=0.04132, over 971656.35 frames.], batch size: 22, lr: 3.75e-04
2022-05-05 08:15:17,123 INFO [train.py:715] (4/8) Epoch 5, batch 25950, loss[loss=0.155, simple_loss=0.2261, pruned_loss=0.04191, over 4775.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2226, pruned_loss=0.04135, over 971468.07 frames.], batch size: 14, lr: 3.75e-04
2022-05-05 08:15:58,602 INFO [train.py:715] (4/8) Epoch 5, batch 26000, loss[loss=0.1536, simple_loss=0.2198, pruned_loss=0.04365, over 4741.00 frames.], tot_loss[loss=0.1519, simple_loss=0.222, pruned_loss=0.04088, over 971133.48 frames.], batch size: 16, lr: 3.75e-04
2022-05-05 08:16:37,295 INFO [train.py:715] (4/8) Epoch 5, batch 26050, loss[loss=0.1588, simple_loss=0.2256, pruned_loss=0.04599, over 4983.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2222, pruned_loss=0.04122, over 970196.20 frames.], batch size: 15, lr: 3.75e-04
2022-05-05 08:17:15,756 INFO [train.py:715] (4/8) Epoch 5, batch 26100, loss[loss=0.1164, simple_loss=0.1874, pruned_loss=0.02265, over 4862.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2225, pruned_loss=0.04141, over 969947.70 frames.], batch size: 20, lr: 3.75e-04
2022-05-05 08:17:54,716 INFO [train.py:715] (4/8) Epoch 5, batch 26150, loss[loss=0.1632, simple_loss=0.224, pruned_loss=0.05119, over 4888.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2223, pruned_loss=0.04101, over 969434.83 frames.], batch size: 22, lr: 3.75e-04
2022-05-05 08:18:33,049 INFO [train.py:715] (4/8) Epoch 5, batch 26200, loss[loss=0.1582, simple_loss=0.2357, pruned_loss=0.04033, over 4785.00 frames.], tot_loss[loss=0.151, simple_loss=0.2214, pruned_loss=0.04026, over 969936.64 frames.], batch size: 17, lr: 3.75e-04
2022-05-05 08:19:12,107 INFO [train.py:715] (4/8) Epoch 5, batch 26250, loss[loss=0.1618, simple_loss=0.2257, pruned_loss=0.04897, over 4946.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2209, pruned_loss=0.03979, over 970296.80 frames.], batch size: 29, lr: 3.75e-04
2022-05-05 08:19:51,344 INFO [train.py:715] (4/8) Epoch 5, batch 26300, loss[loss=0.1294, simple_loss=0.2018, pruned_loss=0.02853, over 4818.00 frames.], tot_loss[loss=0.1503, simple_loss=0.221, pruned_loss=0.03976, over 970579.53 frames.], batch size: 27, lr: 3.75e-04
2022-05-05 08:20:30,626 INFO [train.py:715] (4/8) Epoch 5, batch 26350, loss[loss=0.1535, simple_loss=0.2266, pruned_loss=0.04025, over 4924.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2221, pruned_loss=0.04035, over 971003.30 frames.], batch size: 23, lr: 3.74e-04
2022-05-05 08:21:09,441 INFO [train.py:715] (4/8) Epoch 5, batch 26400, loss[loss=0.1736, simple_loss=0.2337, pruned_loss=0.05674, over 4830.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2227, pruned_loss=0.04093, over 971053.05 frames.], batch size: 27, lr: 3.74e-04
2022-05-05 08:21:48,025 INFO [train.py:715] (4/8) Epoch 5, batch 26450, loss[loss=0.15, simple_loss=0.2229, pruned_loss=0.03855, over 4748.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2221, pruned_loss=0.04034, over 972424.25 frames.], batch size: 16, lr: 3.74e-04
2022-05-05 08:22:26,946 INFO [train.py:715] (4/8) Epoch 5, batch 26500, loss[loss=0.1517, simple_loss=0.2133, pruned_loss=0.04505, over 4869.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2217, pruned_loss=0.03999, over 972937.36 frames.], batch size: 16, lr: 3.74e-04
2022-05-05 08:23:06,040 INFO [train.py:715] (4/8) Epoch 5, batch 26550, loss[loss=0.1412, simple_loss=0.2151, pruned_loss=0.03366, over 4918.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03984, over 971939.78 frames.], batch size: 23, lr: 3.74e-04
2022-05-05 08:23:44,738 INFO [train.py:715] (4/8) Epoch 5, batch 26600, loss[loss=0.1352, simple_loss=0.2194, pruned_loss=0.02548, over 4926.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2222, pruned_loss=0.04019, over 972692.86 frames.], batch size: 29, lr: 3.74e-04
2022-05-05 08:24:24,176 INFO [train.py:715] (4/8) Epoch 5, batch 26650, loss[loss=0.1458, simple_loss=0.2191, pruned_loss=0.03621, over 4938.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2216, pruned_loss=0.04008, over 972125.11 frames.], batch size: 35, lr: 3.74e-04
2022-05-05 08:25:02,985 INFO [train.py:715] (4/8) Epoch 5, batch 26700, loss[loss=0.1582, simple_loss=0.2241, pruned_loss=0.04615, over 4869.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2223, pruned_loss=0.04067, over 971719.19 frames.], batch size: 16, lr: 3.74e-04
2022-05-05 08:25:41,811 INFO [train.py:715] (4/8) Epoch 5, batch 26750, loss[loss=0.1485, simple_loss=0.2168, pruned_loss=0.04007, over 4966.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2226, pruned_loss=0.04055, over 972075.37 frames.], batch size: 25, lr: 3.74e-04
2022-05-05 08:26:20,195 INFO [train.py:715] (4/8) Epoch 5, batch 26800, loss[loss=0.1419, simple_loss=0.2152, pruned_loss=0.03436, over 4815.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2232, pruned_loss=0.04085, over 970762.84 frames.], batch size: 27, lr: 3.74e-04
2022-05-05 08:26:59,359 INFO [train.py:715] (4/8) Epoch 5, batch 26850, loss[loss=0.1669, simple_loss=0.2266, pruned_loss=0.05361, over 4884.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2235, pruned_loss=0.04157, over 970520.43 frames.], batch size: 32, lr: 3.74e-04
2022-05-05 08:27:38,336 INFO [train.py:715] (4/8) Epoch 5, batch 26900, loss[loss=0.1801, simple_loss=0.2423, pruned_loss=0.05895, over 4844.00 frames.], tot_loss[loss=0.1529, simple_loss=0.2233, pruned_loss=0.04126, over 970655.72 frames.], batch size: 30, lr: 3.74e-04
2022-05-05 08:28:17,271 INFO [train.py:715] (4/8) Epoch 5, batch 26950, loss[loss=0.1512, simple_loss=0.2191, pruned_loss=0.04168, over 4912.00 frames.], tot_loss[loss=0.1527, simple_loss=0.2232, pruned_loss=0.04106, over 971623.87 frames.], batch size: 17, lr: 3.74e-04
2022-05-05 08:28:55,974 INFO [train.py:715] (4/8) Epoch 5, batch 27000, loss[loss=0.1568, simple_loss=0.2231, pruned_loss=0.04524, over 4789.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2222, pruned_loss=0.04096, over 971375.94 frames.], batch size: 18, lr: 3.74e-04
2022-05-05 08:28:55,975 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 08:29:05,774 INFO [train.py:742] (4/8) Epoch 5, validation: loss=0.1098, simple_loss=0.195, pruned_loss=0.01232, over 914524.00 frames.
2022-05-05 08:29:45,280 INFO [train.py:715] (4/8) Epoch 5, batch 27050, loss[loss=0.1568, simple_loss=0.2343, pruned_loss=0.03967, over 4981.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2216, pruned_loss=0.04047, over 972282.67 frames.], batch size: 39, lr: 3.74e-04
2022-05-05 08:30:24,755 INFO [train.py:715] (4/8) Epoch 5, batch 27100, loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02891, over 4884.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2218, pruned_loss=0.04053, over 972611.56 frames.], batch size: 19, lr: 3.74e-04
2022-05-05 08:31:04,147 INFO [train.py:715] (4/8) Epoch 5, batch 27150, loss[loss=0.186, simple_loss=0.2471, pruned_loss=0.06247, over 4799.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2216, pruned_loss=0.04015, over 972069.32 frames.], batch size: 18, lr: 3.74e-04
2022-05-05 08:31:42,965 INFO [train.py:715] (4/8) Epoch 5, batch 27200, loss[loss=0.1756, simple_loss=0.2607, pruned_loss=0.04524, over 4795.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2217, pruned_loss=0.03973, over 972018.76 frames.], batch size: 24, lr: 3.74e-04
2022-05-05 08:32:22,590 INFO [train.py:715] (4/8) Epoch 5, batch 27250, loss[loss=0.1522, simple_loss=0.2293, pruned_loss=0.03756, over 4759.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.04016, over 971149.11 frames.], batch size: 19, lr: 3.74e-04
2022-05-05 08:33:01,564 INFO [train.py:715] (4/8) Epoch 5, batch 27300, loss[loss=0.1472, simple_loss=0.2096, pruned_loss=0.04242, over 4765.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2223, pruned_loss=0.04024, over 971179.78 frames.], batch size: 12, lr: 3.74e-04
2022-05-05 08:33:40,119 INFO [train.py:715] (4/8) Epoch 5, batch 27350, loss[loss=0.1611, simple_loss=0.2277, pruned_loss=0.04727, over 4831.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2215, pruned_loss=0.04003, over 971491.56 frames.], batch size: 26, lr: 3.74e-04
2022-05-05 08:34:18,998 INFO [train.py:715] (4/8) Epoch 5, batch 27400, loss[loss=0.1841, simple_loss=0.2502, pruned_loss=0.05899, over 4811.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2222, pruned_loss=0.04066, over 971083.70 frames.], batch size: 24, lr: 3.74e-04
2022-05-05 08:34:58,264 INFO [train.py:715] (4/8) Epoch 5, batch 27450, loss[loss=0.1446, simple_loss=0.2242, pruned_loss=0.03251, over 4794.00 frames.], tot_loss[loss=0.153, simple_loss=0.2233, pruned_loss=0.04137, over 971955.12 frames.], batch size: 21, lr: 3.73e-04
2022-05-05 08:35:38,042 INFO [train.py:715] (4/8) Epoch 5, batch 27500, loss[loss=0.1528, simple_loss=0.2418, pruned_loss=0.03195, over 4864.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2236, pruned_loss=0.04153, over 972073.43 frames.], batch size: 20, lr: 3.73e-04
2022-05-05 08:36:16,528 INFO [train.py:715] (4/8) Epoch 5, batch 27550, loss[loss=0.1615, simple_loss=0.2292, pruned_loss=0.04692, over 4693.00 frames.], tot_loss[loss=0.153, simple_loss=0.2231, pruned_loss=0.0415, over 971313.29 frames.], batch size: 15, lr: 3.73e-04
2022-05-05 08:36:55,893 INFO [train.py:715] (4/8) Epoch 5, batch 27600, loss[loss=0.1606, simple_loss=0.2336, pruned_loss=0.04376, over 4811.00 frames.], tot_loss[loss=0.1522, simple_loss=0.223, pruned_loss=0.0407, over 970994.98 frames.], batch size: 25, lr: 3.73e-04
2022-05-05 08:37:34,976 INFO [train.py:715] (4/8) Epoch 5, batch 27650, loss[loss=0.1806, simple_loss=0.2562, pruned_loss=0.05256, over 4849.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2222, pruned_loss=0.04066, over 970858.58 frames.], batch size: 20, lr: 3.73e-04
2022-05-05 08:38:13,251 INFO [train.py:715] (4/8) Epoch 5, batch 27700, loss[loss=0.1584, simple_loss=0.2275, pruned_loss=0.04465, over 4988.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2217, pruned_loss=0.04027, over 970879.84 frames.], batch size: 31, lr: 3.73e-04
2022-05-05 08:38:52,830 INFO [train.py:715] (4/8) Epoch 5, batch 27750, loss[loss=0.1761, simple_loss=0.2385, pruned_loss=0.05681, over 4913.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2221, pruned_loss=0.04041, over 972301.90 frames.], batch size: 19, lr: 3.73e-04
2022-05-05 08:39:32,593 INFO [train.py:715] (4/8) Epoch 5, batch 27800, loss[loss=0.1744, simple_loss=0.2322, pruned_loss=0.05833, over 4896.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2221, pruned_loss=0.04058, over 971978.98 frames.], batch size: 17, lr: 3.73e-04
2022-05-05 08:40:11,944 INFO [train.py:715] (4/8) Epoch 5, batch 27850, loss[loss=0.1489, simple_loss=0.2122, pruned_loss=0.04276, over 4877.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2231, pruned_loss=0.04088, over 972980.41 frames.], batch size: 32, lr: 3.73e-04
2022-05-05 08:40:50,649 INFO [train.py:715] (4/8) Epoch 5, batch 27900, loss[loss=0.1284, simple_loss=0.1993, pruned_loss=0.02877, over 4815.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2224, pruned_loss=0.04033, over 972521.92 frames.], batch size: 13, lr: 3.73e-04
2022-05-05 08:41:29,601 INFO [train.py:715] (4/8) Epoch 5, batch 27950, loss[loss=0.1467, simple_loss=0.2217, pruned_loss=0.0358, over 4909.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2221, pruned_loss=0.04021, over 972701.15 frames.], batch size: 17, lr: 3.73e-04
2022-05-05 08:42:09,042 INFO [train.py:715] (4/8) Epoch 5, batch 28000, loss[loss=0.1644, simple_loss=0.2363, pruned_loss=0.04626, over 4892.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2224, pruned_loss=0.04037, over 972164.05 frames.], batch size: 16, lr: 3.73e-04
2022-05-05 08:42:47,127 INFO [train.py:715] (4/8) Epoch 5, batch 28050, loss[loss=0.141, simple_loss=0.2091, pruned_loss=0.03643, over 4848.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2224, pruned_loss=0.04052, over 972268.19 frames.], batch size: 34, lr: 3.73e-04
2022-05-05 08:43:25,855 INFO [train.py:715] (4/8) Epoch 5, batch 28100, loss[loss=0.207, simple_loss=0.2583, pruned_loss=0.07786, over 4825.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2228, pruned_loss=0.04106, over 971499.45 frames.], batch size: 26, lr: 3.73e-04
2022-05-05 08:44:04,994 INFO [train.py:715] (4/8) Epoch 5, batch 28150, loss[loss=0.1734, simple_loss=0.2484, pruned_loss=0.04917, over 4921.00 frames.], tot_loss[loss=0.1532, simple_loss=0.2231, pruned_loss=0.04167, over 972205.10 frames.], batch size: 29, lr: 3.73e-04
2022-05-05 08:44:43,938 INFO [train.py:715] (4/8) Epoch 5, batch 28200, loss[loss=0.1651, simple_loss=0.2347, pruned_loss=0.04771, over 4975.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2222, pruned_loss=0.04115, over 971562.78 frames.], batch size: 25, lr: 3.73e-04
2022-05-05 08:45:22,616 INFO [train.py:715] (4/8) Epoch 5, batch 28250, loss[loss=0.1648, simple_loss=0.2375, pruned_loss=0.04599, over 4791.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2217, pruned_loss=0.04082, over 971115.12 frames.], batch size: 24, lr: 3.73e-04
2022-05-05 08:46:01,488 INFO [train.py:715] (4/8) Epoch 5, batch 28300, loss[loss=0.1891, simple_loss=0.2578, pruned_loss=0.06026, over 4820.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2225, pruned_loss=0.04085, over 971603.32 frames.], batch size: 15, lr: 3.73e-04
2022-05-05 08:46:39,904 INFO [train.py:715] (4/8) Epoch 5, batch 28350, loss[loss=0.1545, simple_loss=0.2179, pruned_loss=0.0455, over 4951.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2232, pruned_loss=0.0409, over 971516.96 frames.], batch size: 35, lr: 3.73e-04
2022-05-05 08:47:18,561 INFO [train.py:715] (4/8) Epoch 5, batch 28400, loss[loss=0.1358, simple_loss=0.2154, pruned_loss=0.02807, over 4917.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2222, pruned_loss=0.04014, over 971926.58 frames.], batch size: 18, lr: 3.73e-04
2022-05-05 08:47:57,679 INFO [train.py:715] (4/8) Epoch 5, batch 28450, loss[loss=0.1564, simple_loss=0.2313, pruned_loss=0.04069, over 4985.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2229, pruned_loss=0.04076, over 972316.26 frames.], batch size: 15, lr: 3.73e-04
2022-05-05 08:48:36,727 INFO [train.py:715] (4/8) Epoch 5, batch 28500, loss[loss=0.1527, simple_loss=0.22, pruned_loss=0.0427, over 4827.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2232, pruned_loss=0.04069, over 972073.11 frames.], batch size: 26, lr: 3.72e-04
2022-05-05 08:49:15,939 INFO [train.py:715] (4/8) Epoch 5, batch 28550, loss[loss=0.1478, simple_loss=0.2189, pruned_loss=0.03837, over 4942.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2224, pruned_loss=0.04011, over 972756.40 frames.], batch size: 21, lr: 3.72e-04
2022-05-05 08:49:54,628 INFO [train.py:715] (4/8) Epoch 5, batch 28600, loss[loss=0.1575, simple_loss=0.2258, pruned_loss=0.04462, over 4750.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2218, pruned_loss=0.03991, over 972755.85 frames.], batch size: 14, lr: 3.72e-04
2022-05-05 08:50:34,062 INFO [train.py:715] (4/8) Epoch 5, batch 28650, loss[loss=0.1443, simple_loss=0.2133, pruned_loss=0.03762, over 4883.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2216, pruned_loss=0.03954, over 972050.19 frames.], batch size: 19, lr: 3.72e-04
2022-05-05 08:51:12,502 INFO [train.py:715] (4/8) Epoch 5, batch 28700, loss[loss=0.1372, simple_loss=0.2068, pruned_loss=0.03375, over 4988.00 frames.], tot_loss[loss=0.1497, simple_loss=0.221, pruned_loss=0.03924, over 972263.10 frames.], batch size: 26, lr: 3.72e-04
2022-05-05 08:51:51,352 INFO [train.py:715] (4/8) Epoch 5, batch 28750, loss[loss=0.1707, simple_loss=0.2498, pruned_loss=0.0458, over 4747.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2217, pruned_loss=0.03955, over 972335.62 frames.], batch size: 16, lr: 3.72e-04
2022-05-05 08:52:30,122 INFO [train.py:715] (4/8) Epoch 5, batch 28800, loss[loss=0.1596, simple_loss=0.2339, pruned_loss=0.04269, over 4894.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2222, pruned_loss=0.04019, over 972418.47 frames.], batch size: 19, lr: 3.72e-04
2022-05-05 08:53:09,038 INFO [train.py:715] (4/8) Epoch 5, batch 28850, loss[loss=0.1256, simple_loss=0.2059, pruned_loss=0.02261, over 4819.00 frames.], tot_loss[loss=0.152, simple_loss=0.2227, pruned_loss=0.04067, over 972679.31 frames.], batch size: 12, lr: 3.72e-04
2022-05-05 08:53:47,807 INFO [train.py:715] (4/8) Epoch 5, batch 28900, loss[loss=0.1364, simple_loss=0.2038, pruned_loss=0.03452, over 4875.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2225, pruned_loss=0.04104, over 971072.07 frames.], batch size: 16, lr: 3.72e-04
2022-05-05 08:54:26,495 INFO [train.py:715] (4/8) Epoch 5, batch 28950, loss[loss=0.1163, simple_loss=0.1978, pruned_loss=0.01739, over 4769.00 frames.], tot_loss[loss=0.1514, simple_loss=0.222, pruned_loss=0.04046, over 971725.65 frames.], batch size: 14, lr: 3.72e-04
2022-05-05 08:55:05,613 INFO [train.py:715] (4/8) Epoch 5, batch 29000, loss[loss=0.1198, simple_loss=0.1982, pruned_loss=0.02068, over 4951.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2223, pruned_loss=0.0411, over 972047.36 frames.], batch size: 21, lr: 3.72e-04
2022-05-05 08:55:43,853 INFO [train.py:715] (4/8) Epoch 5, batch 29050, loss[loss=0.1124, simple_loss=0.1873, pruned_loss=0.0187, over 4822.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2232, pruned_loss=0.04118, over 971260.30 frames.], batch size: 26, lr: 3.72e-04
2022-05-05 08:56:22,940 INFO [train.py:715] (4/8) Epoch 5, batch 29100, loss[loss=0.1636, simple_loss=0.2408, pruned_loss=0.04323, over 4808.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2216, pruned_loss=0.04036, over 971411.68 frames.], batch size: 26, lr: 3.72e-04
2022-05-05 08:57:01,740 INFO [train.py:715] (4/8) Epoch 5, batch 29150, loss[loss=0.1452, simple_loss=0.2268, pruned_loss=0.03185, over 4802.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03989, over 971630.28 frames.], batch size: 24, lr: 3.72e-04
2022-05-05 08:57:40,489 INFO [train.py:715] (4/8) Epoch 5, batch 29200, loss[loss=0.1415, simple_loss=0.2106, pruned_loss=0.03621, over 4938.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2216, pruned_loss=0.03991, over 973021.11 frames.], batch size: 29, lr: 3.72e-04
2022-05-05 08:58:19,233 INFO [train.py:715] (4/8) Epoch 5, batch 29250, loss[loss=0.1579, simple_loss=0.2259, pruned_loss=0.04496, over 4747.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2213, pruned_loss=0.03949, over 973442.87 frames.], batch size: 19, lr: 3.72e-04
2022-05-05 08:58:57,802 INFO [train.py:715] (4/8) Epoch 5, batch 29300, loss[loss=0.1216, simple_loss=0.1855, pruned_loss=0.02888, over 4750.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2215, pruned_loss=0.0397, over 973178.00 frames.], batch size: 12, lr: 3.72e-04
2022-05-05 08:59:37,058 INFO [train.py:715] (4/8) Epoch 5, batch 29350, loss[loss=0.1531, simple_loss=0.2387, pruned_loss=0.03374, over 4893.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2218, pruned_loss=0.03985, over 973227.39 frames.], batch size: 22, lr: 3.72e-04
2022-05-05 09:00:15,739 INFO [train.py:715] (4/8) Epoch 5, batch 29400, loss[loss=0.2174, simple_loss=0.285, pruned_loss=0.07487, over 4884.00 frames.], tot_loss[loss=0.1503, simple_loss=0.221, pruned_loss=0.0398, over 973071.94 frames.], batch size: 22, lr: 3.72e-04
2022-05-05 09:00:54,488 INFO [train.py:715] (4/8) Epoch 5, batch 29450, loss[loss=0.1397, simple_loss=0.2141, pruned_loss=0.03265, over 4809.00 frames.], tot_loss[loss=0.151, simple_loss=0.2221, pruned_loss=0.03998, over 972843.18 frames.], batch size: 27, lr: 3.72e-04
2022-05-05 09:01:34,122 INFO [train.py:715] (4/8) Epoch 5, batch 29500, loss[loss=0.1393, simple_loss=0.1938, pruned_loss=0.04243, over 4838.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2211, pruned_loss=0.03935, over 971529.61 frames.], batch size: 32, lr: 3.72e-04
2022-05-05 09:02:13,206 INFO [train.py:715] (4/8) Epoch 5, batch 29550, loss[loss=0.1796, simple_loss=0.2599, pruned_loss=0.04959, over 4964.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2215, pruned_loss=0.03958, over 971961.97 frames.], batch size: 24, lr: 3.72e-04
2022-05-05 09:02:52,390 INFO [train.py:715] (4/8) Epoch 5, batch 29600, loss[loss=0.1517, simple_loss=0.2096, pruned_loss=0.04689, over 4753.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2218, pruned_loss=0.04027, over 971427.73 frames.], batch size: 19, lr: 3.71e-04
2022-05-05 09:03:31,059 INFO [train.py:715] (4/8) Epoch 5, batch 29650, loss[loss=0.132, simple_loss=0.2102, pruned_loss=0.0269, over 4975.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2224, pruned_loss=0.04063, over 971312.86 frames.], batch size: 28, lr: 3.71e-04
2022-05-05 09:04:09,889 INFO [train.py:715] (4/8) Epoch 5, batch 29700, loss[loss=0.1309, simple_loss=0.2078, pruned_loss=0.02697, over 4895.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2224, pruned_loss=0.04043, over 972416.59 frames.], batch size: 17, lr: 3.71e-04
2022-05-05 09:04:48,811 INFO [train.py:715] (4/8) Epoch 5, batch 29750, loss[loss=0.109, simple_loss=0.1692, pruned_loss=0.0244, over 4793.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2226, pruned_loss=0.04007, over 973322.42 frames.], batch size: 12, lr: 3.71e-04
2022-05-05 09:05:27,383 INFO [train.py:715] (4/8) Epoch 5, batch 29800, loss[loss=0.1478, simple_loss=0.2212, pruned_loss=0.03716, over 4735.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2224, pruned_loss=0.04004, over 973133.69 frames.], batch size: 16, lr: 3.71e-04
2022-05-05 09:06:05,622 INFO [train.py:715] (4/8) Epoch 5, batch 29850, loss[loss=0.143, simple_loss=0.2124, pruned_loss=0.03685, over 4937.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2216, pruned_loss=0.0393, over 973407.21 frames.], batch size: 21, lr: 3.71e-04
2022-05-05 09:06:44,670 INFO [train.py:715] (4/8) Epoch 5, batch 29900, loss[loss=0.1412, simple_loss=0.2288, pruned_loss=0.02674, over 4899.00 frames.], tot_loss[loss=0.1515, simple_loss=0.223, pruned_loss=0.04005, over 973320.73 frames.], batch size: 19, lr: 3.71e-04
2022-05-05 09:07:24,016 INFO [train.py:715] (4/8) Epoch 5, batch 29950, loss[loss=0.1613, simple_loss=0.241, pruned_loss=0.04074, over 4821.00 frames.], tot_loss[loss=0.1517, simple_loss=0.223, pruned_loss=0.04018, over 973507.13 frames.], batch size: 24, lr: 3.71e-04
2022-05-05 09:08:02,567 INFO [train.py:715] (4/8) Epoch 5, batch 30000, loss[loss=0.1749, simple_loss=0.2412, pruned_loss=0.05434, over 4853.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2222, pruned_loss=0.04014, over 972534.05 frames.], batch size: 34, lr: 3.71e-04
2022-05-05 09:08:02,568 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 09:08:12,296 INFO [train.py:742] (4/8) Epoch 5, validation: loss=0.11, simple_loss=0.1953, pruned_loss=0.01241, over 914524.00 frames.
2022-05-05 09:08:51,326 INFO [train.py:715] (4/8) Epoch 5, batch 30050, loss[loss=0.1142, simple_loss=0.1926, pruned_loss=0.01796, over 4790.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.04026, over 971809.35 frames.], batch size: 12, lr: 3.71e-04
2022-05-05 09:09:31,493 INFO [train.py:715] (4/8) Epoch 5, batch 30100, loss[loss=0.1303, simple_loss=0.1974, pruned_loss=0.03165, over 4777.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2224, pruned_loss=0.04074, over 971591.81 frames.], batch size: 17, lr: 3.71e-04
2022-05-05 09:10:10,294 INFO [train.py:715] (4/8) Epoch 5, batch 30150, loss[loss=0.17, simple_loss=0.2404, pruned_loss=0.04977, over 4883.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2224, pruned_loss=0.04058, over 971435.90 frames.], batch size: 39, lr: 3.71e-04
2022-05-05 09:10:48,822 INFO [train.py:715] (4/8) Epoch 5, batch 30200, loss[loss=0.1467, simple_loss=0.2259, pruned_loss=0.03378, over 4948.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2216, pruned_loss=0.04013, over 971928.21 frames.], batch size: 23, lr: 3.71e-04
2022-05-05 09:11:27,806 INFO [train.py:715] (4/8) Epoch 5, batch 30250, loss[loss=0.1556, simple_loss=0.2127, pruned_loss=0.0493, over 4854.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2222, pruned_loss=0.04053, over 971685.15 frames.], batch size: 13, lr: 3.71e-04
2022-05-05 09:12:06,781 INFO [train.py:715] (4/8) Epoch 5, batch 30300, loss[loss=0.1921, simple_loss=0.2473, pruned_loss=0.06848, over 4828.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2219, pruned_loss=0.04059, over 971756.55 frames.], batch size: 25, lr: 3.71e-04
2022-05-05 09:12:45,785 INFO [train.py:715] (4/8) Epoch 5, batch 30350, loss[loss=0.1481, simple_loss=0.2325, pruned_loss=0.03187, over 4700.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2217, pruned_loss=0.0403, over 972055.70 frames.], batch size: 15, lr: 3.71e-04
2022-05-05 09:13:24,286 INFO [train.py:715] (4/8) Epoch 5, batch 30400, loss[loss=0.1213, simple_loss=0.1887, pruned_loss=0.02698, over 4797.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2214, pruned_loss=0.04017, over 972862.46 frames.], batch size: 12, lr: 3.71e-04
2022-05-05 09:14:03,373 INFO [train.py:715] (4/8) Epoch 5, batch 30450, loss[loss=0.1654, simple_loss=0.2272, pruned_loss=0.05178, over 4799.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2203, pruned_loss=0.03934, over 971875.39 frames.], batch size: 24, lr: 3.71e-04
2022-05-05 09:14:42,252 INFO [train.py:715] (4/8) Epoch 5, batch 30500, loss[loss=0.1467, simple_loss=0.2148, pruned_loss=0.03924, over 4954.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2212, pruned_loss=0.0399, over 972591.76 frames.], batch size: 35, lr: 3.71e-04
2022-05-05 09:15:20,923 INFO [train.py:715] (4/8) Epoch 5, batch 30550, loss[loss=0.1355, simple_loss=0.2128, pruned_loss=0.02908, over 4815.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2211, pruned_loss=0.04001, over 972124.59 frames.], batch size: 25, lr: 3.71e-04
2022-05-05 09:15:58,937 INFO [train.py:715] (4/8) Epoch 5, batch 30600, loss[loss=0.1447, simple_loss=0.2143, pruned_loss=0.03757, over 4927.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2205, pruned_loss=0.03988, over 971336.97 frames.], batch size: 21, lr: 3.71e-04
2022-05-05 09:16:37,780 INFO [train.py:715] (4/8) Epoch 5, batch 30650, loss[loss=0.1575, simple_loss=0.2304, pruned_loss=0.04224, over 4784.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2206, pruned_loss=0.0398, over 971321.01 frames.], batch size: 17, lr: 3.71e-04
2022-05-05 09:17:16,920 INFO [train.py:715] (4/8) Epoch 5, batch 30700, loss[loss=0.1505, simple_loss=0.2199, pruned_loss=0.04059, over 4871.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2209, pruned_loss=0.03981, over 971696.32 frames.], batch size: 20, lr: 3.70e-04
2022-05-05 09:17:55,174 INFO [train.py:715] (4/8) Epoch 5, batch 30750, loss[loss=0.1397, simple_loss=0.2213, pruned_loss=0.02908, over 4827.00 frames.], tot_loss[loss=0.1518, simple_loss=0.222, pruned_loss=0.04078, over 971551.35 frames.], batch size: 15, lr: 3.70e-04
2022-05-05 09:18:33,969 INFO [train.py:715] (4/8) Epoch 5, batch 30800, loss[loss=0.1484, simple_loss=0.2183, pruned_loss=0.03923, over 4876.00 frames.], tot_loss[loss=0.151, simple_loss=0.2216, pruned_loss=0.04021, over 970997.11 frames.], batch size: 16, lr: 3.70e-04
2022-05-05 09:19:12,987 INFO [train.py:715] (4/8) Epoch 5, batch 30850, loss[loss=0.1306, simple_loss=0.2098, pruned_loss=0.02567, over 4800.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2221, pruned_loss=0.04044, over 971133.05 frames.], batch size: 24, lr: 3.70e-04
2022-05-05 09:19:51,001 INFO [train.py:715] (4/8) Epoch 5, batch 30900, loss[loss=0.1638, simple_loss=0.2326, pruned_loss=0.04746, over 4985.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2226, pruned_loss=0.04062, over 971322.51 frames.], batch size: 25, lr: 3.70e-04
2022-05-05 09:20:29,874 INFO [train.py:715] (4/8) Epoch 5, batch 30950, loss[loss=0.1432, simple_loss=0.2128, pruned_loss=0.03684, over 4853.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2222, pruned_loss=0.0405, over 972415.82 frames.], batch size: 32, lr: 3.70e-04
2022-05-05 09:21:09,512 INFO [train.py:715] (4/8) Epoch 5, batch 31000, loss[loss=0.1606, simple_loss=0.2219, pruned_loss=0.04965, over 4801.00 frames.], tot_loss[loss=0.1522, simple_loss=0.2227, pruned_loss=0.04085, over 972507.39 frames.], batch size: 12, lr: 3.70e-04
2022-05-05 09:21:48,975 INFO [train.py:715] (4/8) Epoch 5, batch 31050, loss[loss=0.1463, simple_loss=0.2106, pruned_loss=0.041, over 4937.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2221, pruned_loss=0.04038, over 973222.79 frames.], batch size: 21, lr: 3.70e-04
2022-05-05 09:22:27,593 INFO [train.py:715] (4/8) Epoch 5, batch 31100, loss[loss=0.1618, simple_loss=0.2314, pruned_loss=0.0461, over 4786.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2215, pruned_loss=0.03954, over 973106.99 frames.], batch size: 18, lr: 3.70e-04
2022-05-05 09:23:06,676 INFO [train.py:715] (4/8) Epoch 5, batch 31150, loss[loss=0.1576, simple_loss=0.2305, pruned_loss=0.04231, over 4867.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2219, pruned_loss=0.03969, over 973089.68 frames.], batch size: 32, lr: 3.70e-04
2022-05-05 09:23:45,589 INFO [train.py:715] (4/8) Epoch 5, batch 31200, loss[loss=0.1518, simple_loss=0.2296, pruned_loss=0.03704, over 4804.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2218, pruned_loss=0.03982, over 973291.95 frames.], batch size: 21, lr: 3.70e-04
2022-05-05 09:24:24,057 INFO [train.py:715] (4/8) Epoch 5, batch 31250, loss[loss=0.1357, simple_loss=0.2102, pruned_loss=0.03063, over 4981.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2214, pruned_loss=0.03937, over 973163.68 frames.], batch size: 26, lr: 3.70e-04
2022-05-05 09:25:02,648 INFO [train.py:715] (4/8) Epoch 5, batch 31300, loss[loss=0.1423, simple_loss=0.2158, pruned_loss=0.03436, over 4986.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2205, pruned_loss=0.03917, over 973040.08 frames.], batch size: 28, lr: 3.70e-04
2022-05-05 09:25:41,535 INFO [train.py:715] (4/8) Epoch 5, batch 31350, loss[loss=0.2017, simple_loss=0.2675, pruned_loss=0.068, over 4860.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2214, pruned_loss=0.03996, over 973071.28 frames.], batch size: 32, lr: 3.70e-04
2022-05-05 09:26:20,317 INFO [train.py:715] (4/8) Epoch 5, batch 31400, loss[loss=0.1317, simple_loss=0.2055, pruned_loss=0.02893, over 4797.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2221, pruned_loss=0.04046, over 973224.20 frames.], batch size: 21, lr: 3.70e-04
2022-05-05 09:26:59,041 INFO [train.py:715] (4/8) Epoch 5, batch 31450, loss[loss=0.172, simple_loss=0.229, pruned_loss=0.05753, over 4645.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2217, pruned_loss=0.04065, over 973555.72 frames.], batch size: 13, lr: 3.70e-04
2022-05-05 09:27:37,867 INFO [train.py:715] (4/8) Epoch 5, batch 31500, loss[loss=0.1515, simple_loss=0.223, pruned_loss=0.04006, over 4882.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2222, pruned_loss=0.04043, over 974467.32 frames.], batch size: 16, lr: 3.70e-04
2022-05-05 09:28:16,783 INFO [train.py:715] (4/8) Epoch 5, batch 31550, loss[loss=0.1253, simple_loss=0.1984, pruned_loss=0.02611, over 4986.00 frames.], tot_loss[loss=0.151, simple_loss=0.2214, pruned_loss=0.04027, over 974340.90 frames.], batch size: 24, lr: 3.70e-04
2022-05-05 09:28:55,562 INFO [train.py:715] (4/8) Epoch 5, batch 31600, loss[loss=0.1386, simple_loss=0.2061, pruned_loss=0.03553, over 4764.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2221, pruned_loss=0.04034, over 974205.46 frames.], batch size: 19, lr: 3.70e-04
2022-05-05 09:29:34,424 INFO [train.py:715] (4/8) Epoch 5, batch 31650, loss[loss=0.1574, simple_loss=0.2272, pruned_loss=0.04378, over 4771.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2211, pruned_loss=0.04028, over 973487.05 frames.], batch size: 17, lr: 3.70e-04
2022-05-05 09:30:13,323 INFO [train.py:715] (4/8) Epoch 5, batch 31700, loss[loss=0.1743, simple_loss=0.2486, pruned_loss=0.04999, over 4958.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2212, pruned_loss=0.03998, over 973117.36 frames.], batch size: 24, lr: 3.70e-04
2022-05-05 09:30:52,059 INFO [train.py:715] (4/8) Epoch 5, batch 31750, loss[loss=0.1706, simple_loss=0.2396, pruned_loss=0.05084, over 4911.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2219, pruned_loss=0.0396, over 972498.46 frames.], batch size: 39, lr: 3.70e-04
2022-05-05 09:31:31,168 INFO [train.py:715] (4/8) Epoch 5, batch 31800, loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03408, over 4777.00 frames.], tot_loss[loss=0.15, simple_loss=0.2213, pruned_loss=0.03936, over 972597.00 frames.], batch size: 12, lr: 3.69e-04
2022-05-05 09:32:09,899 INFO [train.py:715] (4/8) Epoch 5, batch 31850, loss[loss=0.1823, simple_loss=0.2543, pruned_loss=0.05513, over 4816.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2211, pruned_loss=0.03931, over 973013.91 frames.], batch size: 21, lr: 3.69e-04
2022-05-05 09:32:49,447 INFO [train.py:715] (4/8) Epoch 5, batch 31900, loss[loss=0.1345, simple_loss=0.2068, pruned_loss=0.03112, over 4771.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2214, pruned_loss=0.03912, over 972245.83 frames.], batch size: 12, lr: 3.69e-04
2022-05-05 09:33:28,132 INFO [train.py:715] (4/8) Epoch 5, batch 31950, loss[loss=0.1844, simple_loss=0.2598, pruned_loss=0.05445, over 4909.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2219, pruned_loss=0.03931, over 972364.22 frames.], batch size: 17, lr: 3.69e-04
2022-05-05 09:34:06,676 INFO [train.py:715] (4/8) Epoch 5, batch 32000, loss[loss=0.1594, simple_loss=0.2243, pruned_loss=0.04726, over 4979.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2218, pruned_loss=0.03953, over 972223.13 frames.], batch size: 14, lr: 3.69e-04
2022-05-05 09:34:45,047 INFO [train.py:715] (4/8) Epoch 5, batch 32050, loss[loss=0.1401, simple_loss=0.1997, pruned_loss=0.04023, over 4883.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2221, pruned_loss=0.03988, over 972091.75 frames.], batch size: 22, lr: 3.69e-04
2022-05-05 09:35:24,096 INFO [train.py:715] (4/8) Epoch 5, batch 32100, loss[loss=0.1451, simple_loss=0.2095, pruned_loss=0.04034, over 4834.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2223, pruned_loss=0.04031, over 972466.70 frames.], batch size: 15, lr: 3.69e-04
2022-05-05 09:36:02,961 INFO [train.py:715] (4/8) Epoch 5, batch 32150, loss[loss=0.1617, simple_loss=0.2339, pruned_loss=0.04474, over 4861.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2224, pruned_loss=0.04036, over 972488.94 frames.], batch size: 20, lr: 3.69e-04
2022-05-05 09:36:41,524 INFO [train.py:715] (4/8) Epoch 5, batch 32200, loss[loss=0.137, simple_loss=0.201, pruned_loss=0.03647, over 4806.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2225, pruned_loss=0.04043, over 972294.08 frames.], batch size: 24, lr: 3.69e-04
2022-05-05 09:37:20,073 INFO [train.py:715] (4/8) Epoch 5, batch 32250, loss[loss=0.1343, simple_loss=0.2156, pruned_loss=0.02649, over 4792.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2217, pruned_loss=0.03963, over 972241.88 frames.], batch size: 17, lr: 3.69e-04
2022-05-05 09:37:59,209 INFO [train.py:715] (4/8) Epoch 5, batch 32300, loss[loss=0.1868, simple_loss=0.2426, pruned_loss=0.06549, over 4970.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2218, pruned_loss=0.03989, over 972457.30 frames.], batch size: 24, lr: 3.69e-04
2022-05-05 09:38:37,804 INFO [train.py:715] (4/8) Epoch 5, batch 32350, loss[loss=0.1497, simple_loss=0.2244, pruned_loss=0.03748, over 4813.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2216, pruned_loss=0.03994, over 972549.46 frames.], batch size: 25, lr: 3.69e-04
2022-05-05 09:39:16,504 INFO [train.py:715] (4/8) Epoch 5, batch 32400, loss[loss=0.156, simple_loss=0.2116, pruned_loss=0.05015, over 4846.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2228, pruned_loss=0.04104, over 972973.51 frames.], batch size: 13, lr: 3.69e-04
2022-05-05 09:39:55,117 INFO [train.py:715] (4/8) Epoch 5, batch 32450, loss[loss=0.1363, simple_loss=0.2123, pruned_loss=0.03012, over 4877.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2224, pruned_loss=0.04068, over 973469.90 frames.], batch size: 16, lr: 3.69e-04
2022-05-05 09:40:33,914 INFO [train.py:715] (4/8) Epoch 5, batch 32500, loss[loss=0.1559, simple_loss=0.2125, pruned_loss=0.04968, over 4871.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2218, pruned_loss=0.04038, over 973517.27 frames.], batch size: 32, lr: 3.69e-04
2022-05-05 09:41:13,471 INFO [train.py:715] (4/8) Epoch 5, batch 32550, loss[loss=0.163, simple_loss=0.2422, pruned_loss=0.0419, over 4980.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2217, pruned_loss=0.0401, over 972915.38 frames.], batch size: 28, lr: 3.69e-04
2022-05-05 09:41:51,932 INFO [train.py:715] (4/8) Epoch 5, batch 32600, loss[loss=0.1584, simple_loss=0.2339, pruned_loss=0.0414, over 4914.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03979, over 972067.02 frames.], batch size: 23, lr: 3.69e-04
2022-05-05 09:42:30,728 INFO [train.py:715] (4/8) Epoch 5, batch 32650, loss[loss=0.1308, simple_loss=0.2103, pruned_loss=0.02563, over 4753.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2219, pruned_loss=0.04061, over 972313.35 frames.], batch size: 19, lr: 3.69e-04
2022-05-05 09:43:09,271 INFO [train.py:715] (4/8) Epoch 5, batch 32700, loss[loss=0.1735, simple_loss=0.2374, pruned_loss=0.05482, over 4916.00 frames.], tot_loss[loss=0.151, simple_loss=0.2215, pruned_loss=0.0402, over 971837.12 frames.], batch size: 18, lr: 3.69e-04
2022-05-05 09:43:47,572 INFO [train.py:715] (4/8) Epoch 5, batch 32750, loss[loss=0.1798, simple_loss=0.2497, pruned_loss=0.05495, over 4907.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2224, pruned_loss=0.0407, over 971891.17 frames.], batch size: 19, lr: 3.69e-04
2022-05-05 09:44:26,277 INFO [train.py:715] (4/8) Epoch 5, batch 32800, loss[loss=0.174, simple_loss=0.2491, pruned_loss=0.04943, over 4748.00 frames.], tot_loss[loss=0.1524, simple_loss=0.223, pruned_loss=0.0409, over 970604.93 frames.], batch size: 19, lr: 3.69e-04
2022-05-05 09:45:05,107 INFO [train.py:715] (4/8) Epoch 5, batch 32850, loss[loss=0.1524, simple_loss=0.2303, pruned_loss=0.03727, over 4792.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2226, pruned_loss=0.04084, over 970899.63 frames.], batch size: 18, lr: 3.69e-04
2022-05-05 09:45:44,049 INFO [train.py:715] (4/8) Epoch 5, batch 32900, loss[loss=0.145, simple_loss=0.2069, pruned_loss=0.04158, over 4843.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2224, pruned_loss=0.04074, over 970975.68 frames.], batch size: 13, lr: 3.69e-04
2022-05-05 09:46:22,919 INFO [train.py:715] (4/8) Epoch 5, batch 32950, loss[loss=0.122, simple_loss=0.2008, pruned_loss=0.0216, over 4965.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2218, pruned_loss=0.0405, over 972129.62 frames.], batch size: 24, lr: 3.68e-04
2022-05-05 09:47:01,973 INFO [train.py:715] (4/8) Epoch 5, batch 33000, loss[loss=0.1483, simple_loss=0.219, pruned_loss=0.03878, over 4950.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2222, pruned_loss=0.04069, over 971555.22 frames.], batch size: 23, lr: 3.68e-04
2022-05-05 09:47:01,973 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 09:47:11,683 INFO [train.py:742] (4/8) Epoch 5, validation: loss=0.1099, simple_loss=0.1951, pruned_loss=0.01236, over 914524.00 frames.
2022-05-05 09:47:50,705 INFO [train.py:715] (4/8) Epoch 5, batch 33050, loss[loss=0.1492, simple_loss=0.2198, pruned_loss=0.03926, over 4913.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2225, pruned_loss=0.04108, over 971778.87 frames.], batch size: 17, lr: 3.68e-04
2022-05-05 09:48:29,614 INFO [train.py:715] (4/8) Epoch 5, batch 33100, loss[loss=0.1732, simple_loss=0.2479, pruned_loss=0.04923, over 4851.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2232, pruned_loss=0.04118, over 972861.71 frames.], batch size: 15, lr: 3.68e-04
2022-05-05 09:49:07,622 INFO [train.py:715] (4/8) Epoch 5, batch 33150, loss[loss=0.1541, simple_loss=0.2318, pruned_loss=0.03819, over 4828.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2226, pruned_loss=0.0406, over 972915.71 frames.], batch size: 30, lr: 3.68e-04
2022-05-05 09:49:46,217 INFO [train.py:715] (4/8) Epoch 5, batch 33200, loss[loss=0.1579, simple_loss=0.2174, pruned_loss=0.04917, over 4988.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2224, pruned_loss=0.0405, over 972809.01 frames.], batch size: 14, lr: 3.68e-04
2022-05-05 09:50:25,071 INFO [train.py:715] (4/8) Epoch 5, batch 33250, loss[loss=0.1877, simple_loss=0.2559, pruned_loss=0.05975, over 4887.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2225, pruned_loss=0.04017, over 972976.47 frames.], batch size: 19, lr: 3.68e-04
2022-05-05 09:51:03,571 INFO [train.py:715] (4/8) Epoch 5, batch 33300, loss[loss=0.1937, simple_loss=0.2666, pruned_loss=0.06042, over 4983.00 frames.], tot_loss[loss=0.1528, simple_loss=0.2237, pruned_loss=0.04093, over 972140.79 frames.], batch size: 15, lr: 3.68e-04
2022-05-05 09:51:41,939 INFO [train.py:715] (4/8) Epoch 5, batch 33350, loss[loss=0.1489, simple_loss=0.2216, pruned_loss=0.03811, over 4893.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2231, pruned_loss=0.04087, over 972191.83 frames.], batch size: 39, lr: 3.68e-04
2022-05-05 09:52:21,207 INFO [train.py:715] (4/8) Epoch 5, batch 33400, loss[loss=0.1629, simple_loss=0.2387, pruned_loss=0.04357, over 4924.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2227, pruned_loss=0.0404, over 972758.23 frames.], batch size: 19, lr: 3.68e-04
2022-05-05 09:52:59,900 INFO [train.py:715] (4/8) Epoch 5, batch 33450, loss[loss=0.1702, simple_loss=0.2392, pruned_loss=0.05059, over 4733.00 frames.], tot_loss[loss=0.1525, simple_loss=0.2234, pruned_loss=0.04076, over 972392.33 frames.], batch size: 16, lr: 3.68e-04
2022-05-05 09:53:38,246 INFO [train.py:715] (4/8) Epoch 5, batch 33500, loss[loss=0.1398, simple_loss=0.2079, pruned_loss=0.03583, over 4688.00 frames.], tot_loss[loss=0.1533, simple_loss=0.2243, pruned_loss=0.04109, over 972150.84 frames.], batch size: 15, lr: 3.68e-04
2022-05-05 09:54:16,984 INFO [train.py:715] (4/8) Epoch 5, batch 33550, loss[loss=0.1378, simple_loss=0.2027, pruned_loss=0.03643, over 4983.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2229, pruned_loss=0.04041, over 973888.48 frames.], batch size: 26, lr: 3.68e-04
2022-05-05 09:54:55,688 INFO [train.py:715] (4/8) Epoch 5, batch 33600, loss[loss=0.138, simple_loss=0.2017, pruned_loss=0.03716, over 4830.00 frames.], tot_loss[loss=0.152, simple_loss=0.2229, pruned_loss=0.04049, over 974082.86 frames.], batch size: 13, lr: 3.68e-04
2022-05-05 09:55:34,354 INFO [train.py:715] (4/8) Epoch 5, batch 33650, loss[loss=0.1673, simple_loss=0.2317, pruned_loss=0.05139, over 4927.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2226, pruned_loss=0.04007, over 973327.20 frames.], batch size: 18, lr: 3.68e-04
2022-05-05 09:56:12,632 INFO [train.py:715] (4/8) Epoch 5, batch 33700, loss[loss=0.1824, simple_loss=0.2381, pruned_loss=0.06339, over 4739.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2216, pruned_loss=0.03961, over 972367.04 frames.], batch size: 16, lr: 3.68e-04
2022-05-05 09:56:51,515 INFO [train.py:715] (4/8) Epoch 5, batch 33750, loss[loss=0.1403, simple_loss=0.2179, pruned_loss=0.03136, over 4778.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2223, pruned_loss=0.04013, over 972402.37 frames.], batch size: 14, lr: 3.68e-04
2022-05-05 09:57:30,146 INFO [train.py:715] (4/8) Epoch 5, batch 33800, loss[loss=0.1651, simple_loss=0.2412, pruned_loss=0.04445, over 4817.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2223, pruned_loss=0.04008, over 972055.74 frames.], batch size: 25, lr: 3.68e-04
2022-05-05 09:58:09,141 INFO [train.py:715] (4/8) Epoch 5, batch 33850, loss[loss=0.133, simple_loss=0.2017, pruned_loss=0.03215, over 4932.00 frames.], tot_loss[loss=0.1518, simple_loss=0.2228, pruned_loss=0.04037, over 972754.60 frames.], batch size: 21, lr: 3.68e-04
2022-05-05 09:58:47,622 INFO [train.py:715] (4/8) Epoch 5, batch 33900, loss[loss=0.156, simple_loss=0.2162, pruned_loss=0.04793, over 4910.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2221, pruned_loss=0.04006, over 972816.92 frames.], batch size: 18, lr: 3.68e-04
2022-05-05 09:59:25,968 INFO [train.py:715] (4/8) Epoch 5, batch 33950, loss[loss=0.1198, simple_loss=0.1984, pruned_loss=0.02063, over 4975.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2222, pruned_loss=0.04002, over 972864.31 frames.], batch size: 24, lr: 3.68e-04
2022-05-05 10:00:06,983 INFO [train.py:715] (4/8) Epoch 5, batch 34000, loss[loss=0.1482, simple_loss=0.2125, pruned_loss=0.04195, over 4771.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2223, pruned_loss=0.04012, over 972687.48 frames.], batch size: 12, lr: 3.68e-04
2022-05-05 10:00:45,231 INFO [train.py:715] (4/8) Epoch 5, batch 34050, loss[loss=0.1664, simple_loss=0.2215, pruned_loss=0.05568, over 4784.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2222, pruned_loss=0.04011, over 972441.45 frames.], batch size: 14, lr: 3.67e-04
2022-05-05 10:01:23,919 INFO [train.py:715] (4/8) Epoch 5, batch 34100, loss[loss=0.1578, simple_loss=0.2174, pruned_loss=0.04906, over 4761.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2218, pruned_loss=0.03986, over 972347.84 frames.], batch size: 19, lr: 3.67e-04
2022-05-05 10:02:02,747 INFO [train.py:715] (4/8) Epoch 5, batch 34150, loss[loss=0.1675, simple_loss=0.2358, pruned_loss=0.0496, over 4965.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2211, pruned_loss=0.04002, over 972305.91 frames.], batch size: 35, lr: 3.67e-04
2022-05-05 10:02:41,106 INFO [train.py:715] (4/8) Epoch 5, batch 34200, loss[loss=0.1267, simple_loss=0.1924, pruned_loss=0.03047, over 4894.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2211, pruned_loss=0.0399, over 972495.86 frames.], batch size: 22, lr: 3.67e-04
2022-05-05 10:03:20,095 INFO [train.py:715] (4/8) Epoch 5, batch 34250, loss[loss=0.1473, simple_loss=0.2208, pruned_loss=0.03688, over 4994.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2214, pruned_loss=0.04021, over 973018.53 frames.], batch size: 15, lr: 3.67e-04
2022-05-05 10:03:58,247 INFO [train.py:715] (4/8) Epoch 5, batch 34300, loss[loss=0.1423, simple_loss=0.2037, pruned_loss=0.04049, over 4844.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2207, pruned_loss=0.03994, over 972839.34 frames.], batch size: 30, lr: 3.67e-04
2022-05-05 10:04:36,910 INFO [train.py:715] (4/8) Epoch 5, batch 34350, loss[loss=0.1633, simple_loss=0.226, pruned_loss=0.05027, over 4907.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2214, pruned_loss=0.04038, over 973186.96 frames.], batch size: 22, lr: 3.67e-04
2022-05-05 10:05:14,794 INFO [train.py:715] (4/8) Epoch 5, batch 34400, loss[loss=0.1714, simple_loss=0.2338, pruned_loss=0.05449, over 4969.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2219, pruned_loss=0.04013, over 972949.51 frames.], batch size: 35, lr: 3.67e-04
2022-05-05 10:05:53,764 INFO [train.py:715] (4/8) Epoch 5, batch 34450, loss[loss=0.1427, simple_loss=0.2203, pruned_loss=0.03256, over 4769.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2215, pruned_loss=0.03962, over 973362.91 frames.], batch size: 19, lr: 3.67e-04
2022-05-05 10:06:32,732 INFO [train.py:715] (4/8) Epoch 5, batch 34500, loss[loss=0.1332, simple_loss=0.2131, pruned_loss=0.02662, over 4883.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2221, pruned_loss=0.03988, over 973337.51 frames.], batch size: 22, lr: 3.67e-04
2022-05-05 10:07:11,202 INFO [train.py:715] (4/8) Epoch 5, batch 34550, loss[loss=0.1668, simple_loss=0.2302, pruned_loss=0.0517, over 4910.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2218, pruned_loss=0.03985, over 973185.37 frames.], batch size: 17, lr: 3.67e-04
2022-05-05 10:07:49,951 INFO [train.py:715] (4/8) Epoch 5, batch 34600, loss[loss=0.1265, simple_loss=0.2059, pruned_loss=0.02354, over 4982.00 frames.], tot_loss[loss=0.1502, simple_loss=0.221, pruned_loss=0.03968, over 973124.21 frames.], batch size: 25, lr: 3.67e-04
2022-05-05 10:08:28,654 INFO [train.py:715] (4/8) Epoch 5, batch 34650, loss[loss=0.1452, simple_loss=0.2113, pruned_loss=0.03954, over 4949.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2212, pruned_loss=0.03968, over 972132.39 frames.], batch size: 21, lr: 3.67e-04
2022-05-05 10:09:07,578 INFO [train.py:715] (4/8) Epoch 5, batch 34700, loss[loss=0.1612, simple_loss=0.2283, pruned_loss=0.0471, over 4836.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2203, pruned_loss=0.03922, over 971883.76 frames.], batch size: 13, lr: 3.67e-04
2022-05-05 10:09:44,907 INFO [train.py:715] (4/8) Epoch 5, batch 34750, loss[loss=0.1436, simple_loss=0.2177, pruned_loss=0.03475, over 4793.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2205, pruned_loss=0.03946, over 971407.28 frames.], batch size: 21, lr: 3.67e-04
2022-05-05 10:10:21,600 INFO [train.py:715] (4/8) Epoch 5, batch 34800, loss[loss=0.1805, simple_loss=0.2427, pruned_loss=0.05919, over 4777.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2197, pruned_loss=0.03952, over 969552.47 frames.], batch size: 14, lr: 3.67e-04
2022-05-05 10:11:11,224 INFO [train.py:715] (4/8) Epoch 6, batch 0, loss[loss=0.1463, simple_loss=0.2272, pruned_loss=0.03265, over 4761.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2272, pruned_loss=0.03265, over 4761.00 frames.], batch size: 19, lr: 3.46e-04
2022-05-05 10:11:50,183 INFO [train.py:715] (4/8) Epoch 6, batch 50, loss[loss=0.1051, simple_loss=0.1787, pruned_loss=0.01578, over 4960.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2182, pruned_loss=0.03954, over 219108.32 frames.], batch size: 14, lr: 3.46e-04
2022-05-05 10:12:29,110 INFO [train.py:715] (4/8) Epoch 6, batch 100, loss[loss=0.1285, simple_loss=0.2065, pruned_loss=0.02524, over 4778.00 frames.], tot_loss[loss=0.1476, simple_loss=0.218, pruned_loss=0.03857, over 386178.62 frames.], batch size: 19, lr: 3.46e-04
2022-05-05 10:13:08,348 INFO [train.py:715] (4/8) Epoch 6, batch 150, loss[loss=0.1509, simple_loss=0.2194, pruned_loss=0.04118, over 4758.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2193, pruned_loss=0.03953, over 516156.07 frames.], batch size: 19, lr: 3.46e-04
2022-05-05 10:13:47,627 INFO [train.py:715] (4/8) Epoch 6, batch 200, loss[loss=0.1434, simple_loss=0.2228, pruned_loss=0.03201, over 4830.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2194, pruned_loss=0.03888, over 617404.49 frames.], batch size: 15, lr: 3.45e-04
2022-05-05 10:14:26,641 INFO [train.py:715] (4/8) Epoch 6, batch 250, loss[loss=0.1798, simple_loss=0.2563, pruned_loss=0.05166, over 4844.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2196, pruned_loss=0.03846, over 695463.27 frames.], batch size: 26, lr: 3.45e-04
2022-05-05 10:15:05,466 INFO [train.py:715] (4/8) Epoch 6, batch 300, loss[loss=0.144, simple_loss=0.2097, pruned_loss=0.03913, over 4785.00 frames.], tot_loss[loss=0.1489, simple_loss=0.22, pruned_loss=0.03893, over 756632.06 frames.], batch size: 17, lr: 3.45e-04
2022-05-05 10:15:44,448 INFO [train.py:715] (4/8) Epoch 6, batch 350, loss[loss=0.162, simple_loss=0.234, pruned_loss=0.04496, over 4992.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2204, pruned_loss=0.03948, over 804415.16 frames.], batch size: 14, lr: 3.45e-04
2022-05-05 10:16:23,654 INFO [train.py:715] (4/8) Epoch 6, batch 400, loss[loss=0.1514, simple_loss=0.2222, pruned_loss=0.04034, over 4817.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2203, pruned_loss=0.04008, over 841591.98 frames.], batch size: 25, lr: 3.45e-04
2022-05-05 10:17:02,409 INFO [train.py:715] (4/8) Epoch 6, batch 450, loss[loss=0.1583, simple_loss=0.2176, pruned_loss=0.04953, over 4801.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2218, pruned_loss=0.0406, over 870251.11 frames.], batch size: 21, lr: 3.45e-04
2022-05-05 10:17:41,008 INFO [train.py:715] (4/8) Epoch 6, batch 500, loss[loss=0.1169, simple_loss=0.1937, pruned_loss=0.02004, over 4892.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2213, pruned_loss=0.04069, over 892743.78 frames.], batch size: 19, lr: 3.45e-04
2022-05-05 10:18:20,498 INFO [train.py:715] (4/8) Epoch 6, batch 550, loss[loss=0.1569, simple_loss=0.2191, pruned_loss=0.04738, over 4781.00 frames.], tot_loss[loss=0.151, simple_loss=0.2211, pruned_loss=0.04045, over 910920.27 frames.], batch size: 14, lr: 3.45e-04
2022-05-05 10:18:59,385 INFO [train.py:715] (4/8) Epoch 6, batch 600, loss[loss=0.1474, simple_loss=0.2244, pruned_loss=0.0352, over 4847.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2201, pruned_loss=0.03955, over 924395.44 frames.], batch size: 13, lr: 3.45e-04
2022-05-05 10:19:38,401 INFO [train.py:715] (4/8) Epoch 6, batch 650, loss[loss=0.1399, simple_loss=0.2079, pruned_loss=0.03599, over 4762.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2211, pruned_loss=0.04004, over 934841.94 frames.], batch size: 12, lr: 3.45e-04
2022-05-05 10:20:17,486 INFO [train.py:715] (4/8) Epoch 6, batch 700, loss[loss=0.1448, simple_loss=0.2154, pruned_loss=0.03704, over 4834.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2203, pruned_loss=0.03961, over 942397.68 frames.], batch size: 27, lr: 3.45e-04
2022-05-05 10:20:57,081 INFO [train.py:715] (4/8) Epoch 6, batch 750, loss[loss=0.1418, simple_loss=0.2285, pruned_loss=0.02757, over 4976.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2187, pruned_loss=0.03874, over 949640.28 frames.], batch size: 15, lr: 3.45e-04
2022-05-05 10:21:35,854 INFO [train.py:715] (4/8) Epoch 6, batch 800, loss[loss=0.1508, simple_loss=0.2285, pruned_loss=0.03657, over 4885.00 frames.], tot_loss[loss=0.149, simple_loss=0.2198, pruned_loss=0.03907, over 955414.77 frames.], batch size: 22, lr: 3.45e-04
2022-05-05 10:22:14,569 INFO [train.py:715] (4/8) Epoch 6, batch 850, loss[loss=0.1379, simple_loss=0.2009, pruned_loss=0.03742, over 4919.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2197, pruned_loss=0.03871, over 958084.33 frames.], batch size: 18, lr: 3.45e-04
2022-05-05 10:22:54,099 INFO [train.py:715] (4/8) Epoch 6, batch 900, loss[loss=0.1566, simple_loss=0.227, pruned_loss=0.04306, over 4899.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2203, pruned_loss=0.03924, over 961676.27 frames.], batch size: 19, lr: 3.45e-04
2022-05-05 10:23:33,400 INFO [train.py:715] (4/8) Epoch 6, batch 950, loss[loss=0.1688, simple_loss=0.2452, pruned_loss=0.0462, over 4829.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2202, pruned_loss=0.03902, over 964883.69 frames.], batch size: 15, lr: 3.45e-04
2022-05-05 10:24:12,117 INFO [train.py:715] (4/8) Epoch 6, batch 1000, loss[loss=0.1619, simple_loss=0.2273, pruned_loss=0.04821, over 4925.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2201, pruned_loss=0.0392, over 966112.17 frames.], batch size: 19, lr: 3.45e-04
2022-05-05 10:24:51,182 INFO [train.py:715] (4/8) Epoch 6, batch 1050, loss[loss=0.1306, simple_loss=0.2021, pruned_loss=0.0295, over 4806.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2205, pruned_loss=0.0393, over 966602.01 frames.], batch size: 25, lr: 3.45e-04
2022-05-05 10:25:30,722 INFO [train.py:715] (4/8) Epoch 6, batch 1100, loss[loss=0.1327, simple_loss=0.214, pruned_loss=0.02566, over 4822.00 frames.], tot_loss[loss=0.1492, simple_loss=0.22, pruned_loss=0.03918, over 967693.34 frames.], batch size: 26, lr: 3.45e-04
2022-05-05 10:26:09,923 INFO [train.py:715] (4/8) Epoch 6, batch 1150, loss[loss=0.1473, simple_loss=0.2147, pruned_loss=0.03997, over 4819.00 frames.], tot_loss[loss=0.1489, simple_loss=0.22, pruned_loss=0.03895, over 969046.06 frames.], batch size: 27, lr: 3.45e-04
2022-05-05 10:26:48,493 INFO [train.py:715] (4/8) Epoch 6, batch 1200, loss[loss=0.1574, simple_loss=0.2292, pruned_loss=0.04284, over 4771.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2191, pruned_loss=0.03858, over 969049.22 frames.], batch size: 19, lr: 3.45e-04
2022-05-05 10:27:28,195 INFO [train.py:715] (4/8) Epoch 6, batch 1250, loss[loss=0.1386, simple_loss=0.2097, pruned_loss=0.0338, over 4846.00 frames.], tot_loss[loss=0.1472, simple_loss=0.218, pruned_loss=0.03817, over 969102.45 frames.], batch size: 30, lr: 3.45e-04
2022-05-05 10:28:07,471 INFO [train.py:715] (4/8) Epoch 6, batch 1300, loss[loss=0.1721, simple_loss=0.2339, pruned_loss=0.05517, over 4897.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2188, pruned_loss=0.0388, over 969654.16 frames.], batch size: 39, lr: 3.45e-04
2022-05-05 10:28:46,065 INFO [train.py:715] (4/8) Epoch 6, batch 1350, loss[loss=0.1296, simple_loss=0.2118, pruned_loss=0.02374, over 4982.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2192, pruned_loss=0.03853, over 970335.58 frames.], batch size: 24, lr: 3.45e-04
2022-05-05 10:29:24,987 INFO [train.py:715] (4/8) Epoch 6, batch 1400, loss[loss=0.1389, simple_loss=0.2109, pruned_loss=0.03345, over 4653.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2196, pruned_loss=0.039, over 971584.53 frames.], batch size: 13, lr: 3.45e-04
2022-05-05 10:30:04,137 INFO [train.py:715] (4/8) Epoch 6, batch 1450, loss[loss=0.1225, simple_loss=0.1945, pruned_loss=0.02532, over 4758.00 frames.], tot_loss[loss=0.1471, simple_loss=0.218, pruned_loss=0.0381, over 972655.30 frames.], batch size: 19, lr: 3.44e-04
2022-05-05 10:30:42,812 INFO [train.py:715] (4/8) Epoch 6, batch 1500, loss[loss=0.1195, simple_loss=0.1946, pruned_loss=0.02218, over 4786.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2184, pruned_loss=0.03833, over 972323.64 frames.], batch size: 17, lr: 3.44e-04
2022-05-05 10:31:21,207 INFO [train.py:715] (4/8) Epoch 6, batch 1550, loss[loss=0.1263, simple_loss=0.1988, pruned_loss=0.02696, over 4989.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2195, pruned_loss=0.03857, over 972650.14 frames.], batch size: 25, lr: 3.44e-04
2022-05-05 10:32:00,468 INFO [train.py:715] (4/8) Epoch 6, batch 1600, loss[loss=0.1542, simple_loss=0.2232, pruned_loss=0.0426, over 4962.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2197, pruned_loss=0.03875, over 972078.29 frames.], batch size: 35, lr: 3.44e-04
2022-05-05 10:32:40,013 INFO [train.py:715] (4/8) Epoch 6, batch 1650, loss[loss=0.147, simple_loss=0.2313, pruned_loss=0.03135, over 4864.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2203, pruned_loss=0.0391, over 972730.98 frames.], batch size: 20, lr: 3.44e-04
2022-05-05 10:33:18,412 INFO [train.py:715] (4/8) Epoch 6, batch 1700, loss[loss=0.1464, simple_loss=0.2236, pruned_loss=0.03458, over 4922.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2202, pruned_loss=0.03903, over 973866.68 frames.], batch size: 29, lr: 3.44e-04
2022-05-05 10:33:57,728 INFO [train.py:715] (4/8) Epoch 6, batch 1750, loss[loss=0.1685, simple_loss=0.2317, pruned_loss=0.0526, over 4920.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2209, pruned_loss=0.03942, over 974725.28 frames.], batch size: 17, lr: 3.44e-04
2022-05-05 10:34:37,316 INFO [train.py:715] (4/8) Epoch 6, batch 1800, loss[loss=0.1451, simple_loss=0.2225, pruned_loss=0.03381, over 4843.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2206, pruned_loss=0.03917, over 972446.84 frames.], batch size: 13, lr: 3.44e-04
2022-05-05 10:35:16,402 INFO [train.py:715] (4/8) Epoch 6, batch 1850, loss[loss=0.1541, simple_loss=0.23, pruned_loss=0.03908, over 4947.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2211, pruned_loss=0.03975, over 972667.39 frames.], batch size: 24, lr: 3.44e-04
2022-05-05 10:35:54,731 INFO [train.py:715] (4/8) Epoch 6, batch 1900, loss[loss=0.1568, simple_loss=0.2343, pruned_loss=0.0397, over 4939.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2208, pruned_loss=0.03974, over 973173.59 frames.], batch size: 39, lr: 3.44e-04
2022-05-05 10:36:34,277 INFO [train.py:715] (4/8) Epoch 6, batch 1950, loss[loss=0.138, simple_loss=0.2008, pruned_loss=0.03763, over 4761.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2205, pruned_loss=0.03955, over 972837.60 frames.], batch size: 12, lr: 3.44e-04
2022-05-05 10:37:13,034 INFO [train.py:715] (4/8) Epoch 6, batch 2000, loss[loss=0.1588, simple_loss=0.2294, pruned_loss=0.04407, over 4891.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2204, pruned_loss=0.03944, over 972304.57 frames.], batch size: 19, lr: 3.44e-04
2022-05-05 10:37:52,080 INFO [train.py:715] (4/8) Epoch 6, batch 2050, loss[loss=0.1561, simple_loss=0.2261, pruned_loss=0.04306, over 4825.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2206, pruned_loss=0.03951, over 972347.66 frames.], batch size: 26, lr: 3.44e-04
2022-05-05 10:38:30,928 INFO [train.py:715] (4/8) Epoch 6, batch 2100, loss[loss=0.1616, simple_loss=0.2289, pruned_loss=0.04709, over 4990.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2204, pruned_loss=0.03943, over 972927.21 frames.], batch size: 16, lr: 3.44e-04
2022-05-05 10:39:10,111 INFO [train.py:715] (4/8) Epoch 6, batch 2150, loss[loss=0.1201, simple_loss=0.2, pruned_loss=0.0201, over 4811.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2202, pruned_loss=0.03918, over 972592.67 frames.], batch size: 27, lr: 3.44e-04
2022-05-05 10:39:49,070 INFO [train.py:715] (4/8) Epoch 6, batch 2200, loss[loss=0.1323, simple_loss=0.2019, pruned_loss=0.03131, over 4959.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2199, pruned_loss=0.03894, over 973248.10 frames.], batch size: 15, lr: 3.44e-04
2022-05-05 10:40:27,527 INFO [train.py:715] (4/8) Epoch 6, batch 2250, loss[loss=0.1526, simple_loss=0.2191, pruned_loss=0.04304, over 4893.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2197, pruned_loss=0.03886, over 973430.86 frames.], batch size: 19, lr: 3.44e-04
2022-05-05 10:41:06,873 INFO [train.py:715] (4/8) Epoch 6, batch 2300, loss[loss=0.1658, simple_loss=0.2317, pruned_loss=0.04997, over 4871.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2204, pruned_loss=0.03895, over 973555.15 frames.], batch size: 22, lr: 3.44e-04
2022-05-05 10:41:45,980 INFO [train.py:715] (4/8) Epoch 6, batch 2350, loss[loss=0.1299, simple_loss=0.2022, pruned_loss=0.0288, over 4973.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2204, pruned_loss=0.03893, over 974520.89 frames.], batch size: 24, lr: 3.44e-04
2022-05-05 10:42:24,702 INFO [train.py:715] (4/8) Epoch 6, batch 2400, loss[loss=0.1443, simple_loss=0.2174, pruned_loss=0.03565, over 4783.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2209, pruned_loss=0.03929, over 973375.81 frames.], batch size: 17, lr: 3.44e-04
2022-05-05 10:43:03,443 INFO [train.py:715] (4/8) Epoch 6, batch 2450, loss[loss=0.1583, simple_loss=0.2298, pruned_loss=0.0434, over 4910.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2203, pruned_loss=0.03923, over 973278.66 frames.], batch size: 39, lr: 3.44e-04
2022-05-05 10:43:42,678 INFO [train.py:715] (4/8) Epoch 6, batch 2500, loss[loss=0.1206, simple_loss=0.1984, pruned_loss=0.02136, over 4776.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2204, pruned_loss=0.03919, over 974005.50 frames.], batch size: 18, lr: 3.44e-04
2022-05-05 10:44:21,859 INFO [train.py:715] (4/8) Epoch 6, batch 2550, loss[loss=0.1512, simple_loss=0.2196, pruned_loss=0.04141, over 4866.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2209, pruned_loss=0.03939, over 973215.27 frames.], batch size: 38, lr: 3.44e-04
2022-05-05 10:45:00,759 INFO [train.py:715] (4/8) Epoch 6, batch 2600, loss[loss=0.1384, simple_loss=0.2112, pruned_loss=0.03278, over 4863.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2214, pruned_loss=0.03983, over 973351.99 frames.], batch size: 20, lr: 3.44e-04
2022-05-05 10:45:40,391 INFO [train.py:715] (4/8) Epoch 6, batch 2650, loss[loss=0.153, simple_loss=0.2262, pruned_loss=0.03992, over 4910.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2212, pruned_loss=0.03988, over 973281.32 frames.], batch size: 17, lr: 3.43e-04
2022-05-05 10:46:19,965 INFO [train.py:715] (4/8) Epoch 6, batch 2700, loss[loss=0.1639, simple_loss=0.2365, pruned_loss=0.04571, over 4875.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03988, over 973039.86 frames.], batch size: 16, lr: 3.43e-04
2022-05-05 10:46:58,105 INFO [train.py:715] (4/8) Epoch 6, batch 2750, loss[loss=0.1429, simple_loss=0.2034, pruned_loss=0.04117, over 4944.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2213, pruned_loss=0.03994, over 972722.17 frames.], batch size: 21, lr: 3.43e-04
2022-05-05 10:47:37,113 INFO [train.py:715] (4/8) Epoch 6, batch 2800, loss[loss=0.1609, simple_loss=0.2248, pruned_loss=0.04845, over 4959.00 frames.], tot_loss[loss=0.15, simple_loss=0.2206, pruned_loss=0.03972, over 972886.43 frames.], batch size: 35, lr: 3.43e-04
2022-05-05 10:48:16,469 INFO [train.py:715] (4/8) Epoch 6, batch 2850, loss[loss=0.1467, simple_loss=0.2316, pruned_loss=0.03091, over 4983.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2204, pruned_loss=0.0397, over 972565.87 frames.], batch size: 26, lr: 3.43e-04
2022-05-05 10:48:55,294 INFO [train.py:715] (4/8) Epoch 6, batch 2900, loss[loss=0.1225, simple_loss=0.197, pruned_loss=0.02406, over 4748.00 frames.], tot_loss[loss=0.15, simple_loss=0.2211, pruned_loss=0.03948, over 973554.47 frames.], batch size: 16, lr: 3.43e-04
2022-05-05 10:49:33,639 INFO [train.py:715] (4/8) Epoch 6, batch 2950, loss[loss=0.1652, simple_loss=0.2318, pruned_loss=0.04927, over 4952.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.04016, over 973603.34 frames.], batch size: 35, lr: 3.43e-04
2022-05-05 10:50:12,860 INFO [train.py:715] (4/8) Epoch 6, batch 3000, loss[loss=0.1575, simple_loss=0.2323, pruned_loss=0.04133, over 4930.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2214, pruned_loss=0.04052, over 973916.98 frames.], batch size: 29, lr: 3.43e-04
2022-05-05 10:50:12,861 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 10:50:22,538 INFO [train.py:742] (4/8) Epoch 6, validation: loss=0.1095, simple_loss=0.1945, pruned_loss=0.01223, over 914524.00 frames.
2022-05-05 10:51:02,175 INFO [train.py:715] (4/8) Epoch 6, batch 3050, loss[loss=0.1379, simple_loss=0.2131, pruned_loss=0.03139, over 4788.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2216, pruned_loss=0.04055, over 972907.65 frames.], batch size: 14, lr: 3.43e-04
2022-05-05 10:51:41,566 INFO [train.py:715] (4/8) Epoch 6, batch 3100, loss[loss=0.137, simple_loss=0.2124, pruned_loss=0.03082, over 4932.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2209, pruned_loss=0.03974, over 972591.05 frames.], batch size: 23, lr: 3.43e-04
2022-05-05 10:52:20,140 INFO [train.py:715] (4/8) Epoch 6, batch 3150, loss[loss=0.2101, simple_loss=0.2851, pruned_loss=0.06751, over 4822.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2226, pruned_loss=0.04034, over 972225.00 frames.], batch size: 26, lr: 3.43e-04
2022-05-05 10:52:58,781 INFO [train.py:715] (4/8) Epoch 6, batch 3200, loss[loss=0.1188, simple_loss=0.1882, pruned_loss=0.02471, over 4967.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2218, pruned_loss=0.03961, over 972649.12 frames.], batch size: 28, lr: 3.43e-04
2022-05-05 10:53:38,607 INFO [train.py:715] (4/8) Epoch 6, batch 3250, loss[loss=0.1402, simple_loss=0.2139, pruned_loss=0.0333, over 4825.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2213, pruned_loss=0.03983, over 973180.14 frames.], batch size: 26, lr: 3.43e-04
2022-05-05 10:54:17,328 INFO [train.py:715] (4/8) Epoch 6, batch 3300, loss[loss=0.1612, simple_loss=0.2223, pruned_loss=0.05012, over 4946.00 frames.], tot_loss[loss=0.151, simple_loss=0.2217, pruned_loss=0.04017, over 971692.57 frames.], batch size: 21, lr: 3.43e-04
2022-05-05 10:54:55,862 INFO [train.py:715] (4/8) Epoch 6, batch 3350, loss[loss=0.1452, simple_loss=0.2321, pruned_loss=0.0292, over 4811.00 frames.], tot_loss[loss=0.151, simple_loss=0.2218, pruned_loss=0.04005, over 971952.42 frames.], batch size: 25, lr: 3.43e-04
2022-05-05 10:55:35,256 INFO [train.py:715] (4/8) Epoch 6, batch 3400, loss[loss=0.1461, simple_loss=0.2232, pruned_loss=0.03452, over 4869.00 frames.], tot_loss[loss=0.151, simple_loss=0.2219, pruned_loss=0.04008, over 970647.28 frames.], batch size: 20, lr: 3.43e-04
2022-05-05 10:56:14,434 INFO [train.py:715] (4/8) Epoch 6, batch 3450, loss[loss=0.1556, simple_loss=0.231, pruned_loss=0.04007, over 4805.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2205, pruned_loss=0.03947, over 970908.16 frames.], batch size: 21, lr: 3.43e-04
2022-05-05 10:56:52,540 INFO [train.py:715] (4/8) Epoch 6, batch 3500, loss[loss=0.1503, simple_loss=0.2253, pruned_loss=0.03768, over 4757.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2208, pruned_loss=0.03989, over 971059.43 frames.], batch size: 19, lr: 3.43e-04
2022-05-05 10:57:31,372 INFO [train.py:715] (4/8) Epoch 6, batch 3550, loss[loss=0.1649, simple_loss=0.2333, pruned_loss=0.04826, over 4877.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2217, pruned_loss=0.04037, over 971138.62 frames.], batch size: 22, lr: 3.43e-04
2022-05-05 10:58:10,829 INFO [train.py:715] (4/8) Epoch 6, batch 3600, loss[loss=0.1723, simple_loss=0.2416, pruned_loss=0.05151, over 4781.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2206, pruned_loss=0.03988, over 971804.70 frames.], batch size: 17, lr: 3.43e-04
2022-05-05 10:58:49,772 INFO [train.py:715] (4/8) Epoch 6, batch 3650, loss[loss=0.1483, simple_loss=0.2199, pruned_loss=0.03838, over 4948.00 frames.], tot_loss[loss=0.15, simple_loss=0.2205, pruned_loss=0.03976, over 972102.14 frames.], batch size: 24, lr: 3.43e-04
2022-05-05 10:59:27,963 INFO [train.py:715] (4/8) Epoch 6, batch 3700, loss[loss=0.1558, simple_loss=0.237, pruned_loss=0.03732, over 4829.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2219, pruned_loss=0.03996, over 972442.78 frames.], batch size: 15, lr: 3.43e-04
2022-05-05 11:00:07,229 INFO [train.py:715] (4/8) Epoch 6, batch 3750, loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.03465, over 4904.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2214, pruned_loss=0.0397, over 971764.19 frames.], batch size: 19, lr: 3.43e-04
2022-05-05 11:00:46,317 INFO [train.py:715] (4/8) Epoch 6, batch 3800, loss[loss=0.1061, simple_loss=0.1886, pruned_loss=0.01176, over 4922.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2214, pruned_loss=0.03955, over 971267.53 frames.], batch size: 18, lr: 3.43e-04
2022-05-05 11:01:24,435 INFO [train.py:715] (4/8) Epoch 6, batch 3850, loss[loss=0.1361, simple_loss=0.1947, pruned_loss=0.03875, over 4788.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2206, pruned_loss=0.03935, over 970466.80 frames.], batch size: 18, lr: 3.43e-04
2022-05-05 11:02:03,349 INFO [train.py:715] (4/8) Epoch 6, batch 3900, loss[loss=0.1238, simple_loss=0.1895, pruned_loss=0.02898, over 4777.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2208, pruned_loss=0.03975, over 970473.50 frames.], batch size: 17, lr: 3.42e-04
2022-05-05 11:02:42,645 INFO [train.py:715] (4/8) Epoch 6, batch 3950, loss[loss=0.147, simple_loss=0.2118, pruned_loss=0.04112, over 4975.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2225, pruned_loss=0.04026, over 970953.08 frames.], batch size: 24, lr: 3.42e-04
2022-05-05 11:03:21,702 INFO [train.py:715] (4/8) Epoch 6, batch 4000, loss[loss=0.1438, simple_loss=0.2196, pruned_loss=0.03398, over 4876.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2225, pruned_loss=0.04029, over 971472.62 frames.], batch size: 22, lr: 3.42e-04
2022-05-05 11:04:00,014 INFO [train.py:715] (4/8) Epoch 6, batch 4050, loss[loss=0.1826, simple_loss=0.2517, pruned_loss=0.05678, over 4954.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2216, pruned_loss=0.03959, over 972514.15 frames.], batch size: 24, lr: 3.42e-04
2022-05-05 11:04:39,116 INFO [train.py:715] (4/8) Epoch 6, batch 4100, loss[loss=0.1411, simple_loss=0.2185, pruned_loss=0.03187, over 4977.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2218, pruned_loss=0.03975, over 972511.60 frames.], batch size: 14, lr: 3.42e-04
2022-05-05 11:05:17,848 INFO [train.py:715] (4/8) Epoch 6, batch 4150, loss[loss=0.1252, simple_loss=0.1902, pruned_loss=0.03012, over 4759.00 frames.], tot_loss[loss=0.1503, simple_loss=0.221, pruned_loss=0.03976, over 971549.15 frames.], batch size: 12, lr: 3.42e-04
2022-05-05 11:05:56,010 INFO [train.py:715] (4/8) Epoch 6, batch 4200, loss[loss=0.1797, simple_loss=0.2526, pruned_loss=0.05341, over 4903.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2206, pruned_loss=0.03941, over 971896.19 frames.], batch size: 17, lr: 3.42e-04
2022-05-05 11:06:34,725 INFO [train.py:715] (4/8) Epoch 6, batch 4250, loss[loss=0.1607, simple_loss=0.2424, pruned_loss=0.03954, over 4965.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2211, pruned_loss=0.03951, over 972916.60 frames.], batch size: 24, lr: 3.42e-04
2022-05-05 11:07:13,787 INFO [train.py:715] (4/8) Epoch 6, batch 4300, loss[loss=0.1452, simple_loss=0.2036, pruned_loss=0.04341, over 4858.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2214, pruned_loss=0.03971, over 972553.93 frames.], batch size: 32, lr: 3.42e-04
2022-05-05 11:07:52,578 INFO [train.py:715] (4/8) Epoch 6, batch 4350, loss[loss=0.1799, simple_loss=0.2515, pruned_loss=0.05415, over 4902.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2215, pruned_loss=0.03997, over 971936.10 frames.], batch size: 17, lr: 3.42e-04
2022-05-05 11:08:30,488 INFO [train.py:715] (4/8) Epoch 6, batch 4400, loss[loss=0.1218, simple_loss=0.2004, pruned_loss=0.0216, over 4972.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2214, pruned_loss=0.03937, over 971711.07 frames.], batch size: 28, lr: 3.42e-04
2022-05-05 11:09:08,936 INFO [train.py:715] (4/8) Epoch 6, batch 4450, loss[loss=0.1335, simple_loss=0.2017, pruned_loss=0.03264, over 4788.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2212, pruned_loss=0.03972, over 971721.10 frames.], batch size: 18, lr: 3.42e-04
2022-05-05 11:09:48,073 INFO [train.py:715] (4/8) Epoch 6, batch 4500, loss[loss=0.1351, simple_loss=0.2021, pruned_loss=0.03405, over 4904.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2204, pruned_loss=0.0394, over 971937.65 frames.], batch size: 19, lr: 3.42e-04
2022-05-05 11:10:26,352 INFO [train.py:715] (4/8) Epoch 6, batch 4550, loss[loss=0.1785, simple_loss=0.2384, pruned_loss=0.05928, over 4879.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2201, pruned_loss=0.03935, over 971991.87 frames.], batch size: 16, lr: 3.42e-04
2022-05-05 11:11:04,820 INFO [train.py:715] (4/8) Epoch 6, batch 4600, loss[loss=0.1489, simple_loss=0.2133, pruned_loss=0.04224, over 4823.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2218, pruned_loss=0.03974, over 971970.72 frames.], batch size: 13, lr: 3.42e-04
2022-05-05 11:11:44,224 INFO [train.py:715] (4/8) Epoch 6, batch 4650, loss[loss=0.1479, simple_loss=0.2213, pruned_loss=0.03731, over 4774.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2215, pruned_loss=0.03975, over 972610.91 frames.], batch size: 17, lr: 3.42e-04
2022-05-05 11:12:23,353 INFO [train.py:715] (4/8) Epoch 6, batch 4700, loss[loss=0.1625, simple_loss=0.2285, pruned_loss=0.04826, over 4926.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2213, pruned_loss=0.03946, over 971789.23 frames.], batch size: 29, lr: 3.42e-04
2022-05-05 11:13:01,632 INFO [train.py:715] (4/8) Epoch 6, batch 4750, loss[loss=0.1472, simple_loss=0.2217, pruned_loss=0.03636, over 4897.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03989, over 971887.88 frames.], batch size: 22, lr: 3.42e-04
2022-05-05 11:13:40,645 INFO [train.py:715] (4/8) Epoch 6, batch 4800, loss[loss=0.1504, simple_loss=0.2254, pruned_loss=0.0377, over 4803.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2209, pruned_loss=0.03976, over 972019.86 frames.], batch size: 21, lr: 3.42e-04
2022-05-05 11:14:19,738 INFO [train.py:715] (4/8) Epoch 6, batch 4850, loss[loss=0.1232, simple_loss=0.2031, pruned_loss=0.02163, over 4880.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2214, pruned_loss=0.04014, over 972025.10 frames.], batch size: 32, lr: 3.42e-04
2022-05-05 11:14:58,279 INFO [train.py:715] (4/8) Epoch 6, batch 4900, loss[loss=0.1639, simple_loss=0.2325, pruned_loss=0.04768, over 4888.00 frames.], tot_loss[loss=0.1492, simple_loss=0.22, pruned_loss=0.03925, over 972320.78 frames.], batch size: 17, lr: 3.42e-04
2022-05-05 11:15:37,164 INFO [train.py:715] (4/8) Epoch 6, batch 4950, loss[loss=0.1891, simple_loss=0.2458, pruned_loss=0.06614, over 4851.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2192, pruned_loss=0.03866, over 972614.66 frames.], batch size: 30, lr: 3.42e-04
2022-05-05 11:16:16,918 INFO [train.py:715] (4/8) Epoch 6, batch 5000, loss[loss=0.1386, simple_loss=0.2026, pruned_loss=0.03732, over 4749.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2192, pruned_loss=0.03882, over 972110.36 frames.], batch size: 19, lr: 3.42e-04
2022-05-05 11:16:55,993 INFO [train.py:715] (4/8) Epoch 6, batch 5050, loss[loss=0.1693, simple_loss=0.2473, pruned_loss=0.04561, over 4950.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2203, pruned_loss=0.03926, over 971986.73 frames.], batch size: 29, lr: 3.42e-04
2022-05-05 11:17:34,330 INFO [train.py:715] (4/8) Epoch 6, batch 5100, loss[loss=0.1602, simple_loss=0.2298, pruned_loss=0.04528, over 4983.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2205, pruned_loss=0.03939, over 971972.18 frames.], batch size: 35, lr: 3.42e-04
2022-05-05 11:18:13,255 INFO [train.py:715] (4/8) Epoch 6, batch 5150, loss[loss=0.119, simple_loss=0.2078, pruned_loss=0.01513, over 4955.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2202, pruned_loss=0.03882, over 971797.66 frames.], batch size: 21, lr: 3.41e-04
2022-05-05 11:18:52,359 INFO [train.py:715] (4/8) Epoch 6, batch 5200, loss[loss=0.1378, simple_loss=0.2063, pruned_loss=0.03463, over 4912.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2212, pruned_loss=0.03934, over 972930.98 frames.], batch size: 18, lr: 3.41e-04
2022-05-05 11:19:30,492 INFO [train.py:715] (4/8) Epoch 6, batch 5250, loss[loss=0.1444, simple_loss=0.2238, pruned_loss=0.03245, over 4849.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2208, pruned_loss=0.03901, over 973067.77 frames.], batch size: 32, lr: 3.41e-04
2022-05-05 11:20:09,574 INFO [train.py:715] (4/8) Epoch 6, batch 5300, loss[loss=0.1383, simple_loss=0.2094, pruned_loss=0.03356, over 4936.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2204, pruned_loss=0.03888, over 972804.48 frames.], batch size: 29, lr: 3.41e-04
2022-05-05 11:20:48,895 INFO [train.py:715] (4/8) Epoch 6, batch 5350, loss[loss=0.1747, simple_loss=0.2554, pruned_loss=0.04697, over 4965.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2207, pruned_loss=0.03924, over 972933.51 frames.], batch size: 24, lr: 3.41e-04
2022-05-05 11:21:27,941 INFO [train.py:715] (4/8) Epoch 6, batch 5400, loss[loss=0.1302, simple_loss=0.2047, pruned_loss=0.02782, over 4820.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2215, pruned_loss=0.03962, over 972600.15 frames.], batch size: 13, lr: 3.41e-04
2022-05-05 11:22:06,517 INFO [train.py:715] (4/8) Epoch 6, batch 5450, loss[loss=0.149, simple_loss=0.2357, pruned_loss=0.03111, over 4883.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2214, pruned_loss=0.0395, over 972759.87 frames.], batch size: 22, lr: 3.41e-04
2022-05-05 11:22:45,325 INFO [train.py:715] (4/8) Epoch 6, batch 5500, loss[loss=0.1368, simple_loss=0.2089, pruned_loss=0.03237, over 4802.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2208, pruned_loss=0.03937, over 972881.54 frames.], batch size: 25, lr: 3.41e-04
2022-05-05 11:23:24,192 INFO [train.py:715] (4/8) Epoch 6, batch 5550, loss[loss=0.1861, simple_loss=0.2468, pruned_loss=0.06276, over 4975.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03989, over 972820.16 frames.], batch size: 15, lr: 3.41e-04
2022-05-05 11:24:02,781 INFO [train.py:715] (4/8) Epoch 6, batch 5600, loss[loss=0.1677, simple_loss=0.2471, pruned_loss=0.04414, over 4978.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2218, pruned_loss=0.04032, over 972489.08 frames.], batch size: 24, lr: 3.41e-04
2022-05-05 11:24:42,275 INFO [train.py:715] (4/8) Epoch 6, batch 5650, loss[loss=0.1389, simple_loss=0.2133, pruned_loss=0.03224, over 4914.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2229, pruned_loss=0.04086, over 973603.23 frames.], batch size: 29, lr: 3.41e-04
2022-05-05 11:25:21,627 INFO [train.py:715] (4/8) Epoch 6, batch 5700, loss[loss=0.2045, simple_loss=0.2726, pruned_loss=0.06821, over 4911.00 frames.], tot_loss[loss=0.1516, simple_loss=0.2223, pruned_loss=0.0405, over 973491.80 frames.], batch size: 29, lr: 3.41e-04
2022-05-05 11:26:00,234 INFO [train.py:715] (4/8) Epoch 6, batch 5750, loss[loss=0.1541, simple_loss=0.2269, pruned_loss=0.04067, over 4959.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2222, pruned_loss=0.04027, over 973342.01 frames.], batch size: 24, lr: 3.41e-04
2022-05-05 11:26:38,645 INFO [train.py:715] (4/8) Epoch 6, batch 5800, loss[loss=0.182, simple_loss=0.2352, pruned_loss=0.0644, over 4891.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2221, pruned_loss=0.04048, over 972507.04 frames.], batch size: 16, lr: 3.41e-04
2022-05-05 11:27:17,531 INFO [train.py:715] (4/8) Epoch 6, batch 5850, loss[loss=0.1442, simple_loss=0.2277, pruned_loss=0.03035, over 4936.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2214, pruned_loss=0.03968, over 972427.25 frames.], batch size: 29, lr: 3.41e-04
2022-05-05 11:27:56,994 INFO [train.py:715] (4/8) Epoch 6, batch 5900, loss[loss=0.1467, simple_loss=0.2177, pruned_loss=0.03786, over 4781.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2217, pruned_loss=0.0399, over 972890.52 frames.], batch size: 17, lr: 3.41e-04
2022-05-05 11:28:34,909 INFO [train.py:715] (4/8) Epoch 6, batch 5950, loss[loss=0.1202, simple_loss=0.1898, pruned_loss=0.0253, over 4888.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2211, pruned_loss=0.03959, over 972272.30 frames.], batch size: 16, lr: 3.41e-04
2022-05-05 11:29:14,284 INFO [train.py:715] (4/8) Epoch 6, batch 6000, loss[loss=0.1773, simple_loss=0.242, pruned_loss=0.05631, over 4756.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2212, pruned_loss=0.03978, over 972273.81 frames.], batch size: 17, lr: 3.41e-04
2022-05-05 11:29:14,285 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 11:29:24,853 INFO [train.py:742] (4/8) Epoch 6, validation: loss=0.1095, simple_loss=0.1945, pruned_loss=0.01229, over 914524.00 frames.
2022-05-05 11:30:04,469 INFO [train.py:715] (4/8) Epoch 6, batch 6050, loss[loss=0.1901, simple_loss=0.2451, pruned_loss=0.06755, over 4971.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2213, pruned_loss=0.03963, over 972829.98 frames.], batch size: 15, lr: 3.41e-04
2022-05-05 11:30:43,725 INFO [train.py:715] (4/8) Epoch 6, batch 6100, loss[loss=0.1387, simple_loss=0.2045, pruned_loss=0.03646, over 4853.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2216, pruned_loss=0.03999, over 971892.90 frames.], batch size: 20, lr: 3.41e-04
2022-05-05 11:31:23,121 INFO [train.py:715] (4/8) Epoch 6, batch 6150, loss[loss=0.1385, simple_loss=0.2157, pruned_loss=0.03063, over 4890.00 frames.], tot_loss[loss=0.1519, simple_loss=0.2229, pruned_loss=0.0405, over 971997.22 frames.], batch size: 22, lr: 3.41e-04
2022-05-05 11:32:01,631 INFO [train.py:715] (4/8) Epoch 6, batch 6200, loss[loss=0.1432, simple_loss=0.2156, pruned_loss=0.03541, over 4811.00 frames.], tot_loss[loss=0.1524, simple_loss=0.2234, pruned_loss=0.04073, over 972605.19 frames.], batch size: 21, lr: 3.41e-04
2022-05-05 11:32:40,934 INFO [train.py:715] (4/8) Epoch 6, batch 6250, loss[loss=0.1281, simple_loss=0.2022, pruned_loss=0.02704, over 4986.00 frames.], tot_loss[loss=0.1521, simple_loss=0.2227, pruned_loss=0.0407, over 972289.43 frames.], batch size: 28, lr: 3.41e-04
2022-05-05 11:33:20,233 INFO [train.py:715] (4/8) Epoch 6, batch 6300, loss[loss=0.1626, simple_loss=0.2356, pruned_loss=0.04477, over 4906.00 frames.], tot_loss[loss=0.1517, simple_loss=0.2226, pruned_loss=0.04044, over 972848.95 frames.], batch size: 39, lr: 3.41e-04
2022-05-05 11:33:58,707 INFO [train.py:715] (4/8) Epoch 6, batch 6350, loss[loss=0.1549, simple_loss=0.2206, pruned_loss=0.04466, over 4804.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2222, pruned_loss=0.04035, over 973119.06 frames.], batch size: 14, lr: 3.41e-04
2022-05-05 11:34:37,339 INFO [train.py:715] (4/8) Epoch 6, batch 6400, loss[loss=0.1778, simple_loss=0.2364, pruned_loss=0.0596, over 4694.00 frames.], tot_loss[loss=0.1515, simple_loss=0.2225, pruned_loss=0.04027, over 972566.98 frames.], batch size: 15, lr: 3.40e-04
2022-05-05 11:35:16,565 INFO [train.py:715] (4/8) Epoch 6, batch 6450, loss[loss=0.1558, simple_loss=0.2311, pruned_loss=0.04021, over 4872.00 frames.], tot_loss[loss=0.1514, simple_loss=0.2229, pruned_loss=0.04001, over 972317.72 frames.], batch size: 22, lr: 3.40e-04
2022-05-05 11:35:55,386 INFO [train.py:715] (4/8) Epoch 6, batch 6500, loss[loss=0.1469, simple_loss=0.2215, pruned_loss=0.03613, over 4809.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2217, pruned_loss=0.03961, over 971886.16 frames.], batch size: 26, lr: 3.40e-04
2022-05-05 11:36:33,973 INFO [train.py:715] (4/8) Epoch 6, batch 6550, loss[loss=0.127, simple_loss=0.1913, pruned_loss=0.03135, over 4782.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2214, pruned_loss=0.03974, over 971863.21 frames.], batch size: 17, lr: 3.40e-04
2022-05-05 11:37:12,777 INFO [train.py:715] (4/8) Epoch 6, batch 6600, loss[loss=0.1349, simple_loss=0.2054, pruned_loss=0.03225, over 4805.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2214, pruned_loss=0.03946, over 971943.32 frames.], batch size: 21, lr: 3.40e-04
2022-05-05 11:37:52,989 INFO [train.py:715] (4/8) Epoch 6, batch 6650, loss[loss=0.129, simple_loss=0.2001, pruned_loss=0.02899, over 4874.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2207, pruned_loss=0.03902, over 971861.49 frames.], batch size: 30, lr: 3.40e-04
2022-05-05 11:38:31,783 INFO [train.py:715] (4/8) Epoch 6, batch 6700, loss[loss=0.1397, simple_loss=0.2071, pruned_loss=0.0361, over 4706.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2207, pruned_loss=0.03932, over 972066.54 frames.], batch size: 15, lr: 3.40e-04
2022-05-05 11:39:10,522 INFO [train.py:715] (4/8) Epoch 6, batch 6750, loss[loss=0.1558, simple_loss=0.2261, pruned_loss=0.04275, over 4764.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2211, pruned_loss=0.03962, over 971635.00 frames.], batch size: 14, lr: 3.40e-04
2022-05-05 11:39:49,800 INFO [train.py:715] (4/8) Epoch 6, batch 6800, loss[loss=0.1588, simple_loss=0.2428, pruned_loss=0.03745, over 4888.00 frames.], tot_loss[loss=0.1499, simple_loss=0.221, pruned_loss=0.03942, over 972037.42 frames.], batch size: 19, lr: 3.40e-04
2022-05-05 11:40:28,791 INFO [train.py:715] (4/8) Epoch 6, batch 6850, loss[loss=0.1431, simple_loss=0.2044, pruned_loss=0.04086, over 4957.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2208, pruned_loss=0.0392, over 972455.10 frames.], batch size: 24, lr: 3.40e-04
2022-05-05 11:41:06,842 INFO [train.py:715] (4/8) Epoch 6, batch 6900, loss[loss=0.1436, simple_loss=0.2218, pruned_loss=0.03274, over 4780.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2208, pruned_loss=0.03943, over 972244.80 frames.], batch size: 19, lr: 3.40e-04
2022-05-05 11:41:45,909 INFO [train.py:715] (4/8) Epoch 6, batch 6950, loss[loss=0.161, simple_loss=0.2288, pruned_loss=0.04658, over 4854.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2207, pruned_loss=0.03931, over 972705.37 frames.], batch size: 30, lr: 3.40e-04
2022-05-05 11:42:25,621 INFO [train.py:715] (4/8) Epoch 6, batch 7000, loss[loss=0.1375, simple_loss=0.2027, pruned_loss=0.03621, over 4937.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2202, pruned_loss=0.03922, over 972642.28 frames.], batch size: 29, lr: 3.40e-04
2022-05-05 11:43:04,217 INFO [train.py:715] (4/8) Epoch 6, batch 7050, loss[loss=0.1571, simple_loss=0.221, pruned_loss=0.04662, over 4798.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2204, pruned_loss=0.03938, over 972466.48 frames.], batch size: 21, lr: 3.40e-04
2022-05-05 11:43:42,734 INFO [train.py:715] (4/8) Epoch 6, batch 7100, loss[loss=0.1378, simple_loss=0.1974, pruned_loss=0.03908, over 4842.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2205, pruned_loss=0.03932, over 972513.27 frames.], batch size: 32, lr: 3.40e-04
2022-05-05 11:44:25,532 INFO [train.py:715] (4/8) Epoch 6, batch 7150, loss[loss=0.1554, simple_loss=0.2213, pruned_loss=0.04472, over 4759.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2205, pruned_loss=0.03897, over 972267.86 frames.], batch size: 16, lr: 3.40e-04
2022-05-05 11:45:04,230 INFO [train.py:715] (4/8) Epoch 6, batch 7200, loss[loss=0.1657, simple_loss=0.2319, pruned_loss=0.04975, over 4879.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2202, pruned_loss=0.0388, over 972766.51 frames.], batch size: 16, lr: 3.40e-04
2022-05-05 11:45:42,691 INFO [train.py:715] (4/8) Epoch 6, batch 7250, loss[loss=0.1772, simple_loss=0.2581, pruned_loss=0.04816, over 4834.00 frames.], tot_loss[loss=0.15, simple_loss=0.2215, pruned_loss=0.03924, over 973107.38 frames.], batch size: 15, lr: 3.40e-04
2022-05-05 11:46:21,451 INFO [train.py:715] (4/8) Epoch 6, batch 7300, loss[loss=0.1943, simple_loss=0.2459, pruned_loss=0.07133, over 4887.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2203, pruned_loss=0.03894, over 972976.74 frames.], batch size: 39, lr: 3.40e-04
2022-05-05 11:47:01,065 INFO [train.py:715] (4/8) Epoch 6, batch 7350, loss[loss=0.1707, simple_loss=0.2365, pruned_loss=0.05245, over 4981.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2207, pruned_loss=0.03907, over 972625.75 frames.], batch size: 24, lr: 3.40e-04
2022-05-05 11:47:38,866 INFO [train.py:715] (4/8) Epoch 6, batch 7400, loss[loss=0.138, simple_loss=0.2059, pruned_loss=0.03502, over 4856.00 frames.], tot_loss[loss=0.1488, simple_loss=0.22, pruned_loss=0.0388, over 973296.79 frames.], batch size: 15, lr: 3.40e-04
2022-05-05 11:48:18,379 INFO [train.py:715] (4/8) Epoch 6, batch 7450, loss[loss=0.1363, simple_loss=0.2041, pruned_loss=0.03425, over 4876.00 frames.], tot_loss[loss=0.15, simple_loss=0.221, pruned_loss=0.03952, over 973607.34 frames.], batch size: 16, lr: 3.40e-04
2022-05-05 11:48:56,996 INFO [train.py:715] (4/8) Epoch 6, batch 7500, loss[loss=0.1812, simple_loss=0.2496, pruned_loss=0.0564, over 4798.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2214, pruned_loss=0.0396, over 972784.44 frames.], batch size: 21, lr: 3.40e-04
2022-05-05 11:49:35,691 INFO [train.py:715] (4/8) Epoch 6, batch 7550, loss[loss=0.1467, simple_loss=0.2197, pruned_loss=0.03686, over 4943.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2208, pruned_loss=0.03901, over 972440.85 frames.], batch size: 23, lr: 3.40e-04
2022-05-05 11:50:14,634 INFO [train.py:715] (4/8) Epoch 6, batch 7600, loss[loss=0.1495, simple_loss=0.2257, pruned_loss=0.03665, over 4888.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2215, pruned_loss=0.03976, over 973399.37 frames.], batch size: 19, lr: 3.40e-04
2022-05-05 11:50:53,762 INFO [train.py:715] (4/8) Epoch 6, batch 7650, loss[loss=0.1528, simple_loss=0.2243, pruned_loss=0.04062, over 4757.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2217, pruned_loss=0.03945, over 974019.98 frames.], batch size: 16, lr: 3.40e-04
2022-05-05 11:51:33,382 INFO [train.py:715] (4/8) Epoch 6, batch 7700, loss[loss=0.1452, simple_loss=0.2114, pruned_loss=0.03946, over 4976.00 frames.], tot_loss[loss=0.1497, simple_loss=0.221, pruned_loss=0.03916, over 974381.30 frames.], batch size: 35, lr: 3.39e-04
2022-05-05 11:52:11,584 INFO [train.py:715] (4/8) Epoch 6, batch 7750, loss[loss=0.1591, simple_loss=0.2381, pruned_loss=0.04001, over 4763.00 frames.], tot_loss[loss=0.15, simple_loss=0.2213, pruned_loss=0.03932, over 974226.32 frames.], batch size: 14, lr: 3.39e-04
2022-05-05 11:52:51,084 INFO [train.py:715] (4/8) Epoch 6, batch 7800, loss[loss=0.1501, simple_loss=0.2208, pruned_loss=0.03972, over 4694.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2214, pruned_loss=0.03972, over 973332.25 frames.], batch size: 15, lr: 3.39e-04
2022-05-05 11:53:30,018 INFO [train.py:715] (4/8) Epoch 6, batch 7850, loss[loss=0.1388, simple_loss=0.2164, pruned_loss=0.03057, over 4908.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03974, over 973601.21 frames.], batch size: 29, lr: 3.39e-04
2022-05-05 11:54:08,583 INFO [train.py:715] (4/8) Epoch 6, batch 7900, loss[loss=0.1465, simple_loss=0.2145, pruned_loss=0.03924, over 4782.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2215, pruned_loss=0.03973, over 972960.50 frames.], batch size: 17, lr: 3.39e-04
2022-05-05 11:54:47,343 INFO [train.py:715] (4/8) Epoch 6, batch 7950, loss[loss=0.1462, simple_loss=0.2066, pruned_loss=0.04289, over 4822.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2217, pruned_loss=0.03964, over 973879.03 frames.], batch size: 15, lr: 3.39e-04
2022-05-05 11:55:26,516 INFO [train.py:715] (4/8) Epoch 6, batch 8000, loss[loss=0.1571, simple_loss=0.2312, pruned_loss=0.04154, over 4929.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2217, pruned_loss=0.03964, over 973585.21 frames.], batch size: 23, lr: 3.39e-04
2022-05-05 11:56:05,893 INFO [train.py:715] (4/8) Epoch 6, batch 8050, loss[loss=0.1696, simple_loss=0.2353, pruned_loss=0.05196, over 4846.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2208, pruned_loss=0.039, over 973419.80 frames.], batch size: 30, lr: 3.39e-04
2022-05-05 11:56:43,893 INFO [train.py:715] (4/8) Epoch 6, batch 8100, loss[loss=0.1527, simple_loss=0.2372, pruned_loss=0.03409, over 4856.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2216, pruned_loss=0.03932, over 972999.64 frames.], batch size: 20, lr: 3.39e-04
2022-05-05 11:57:22,883 INFO [train.py:715] (4/8) Epoch 6, batch 8150, loss[loss=0.1396, simple_loss=0.2242, pruned_loss=0.02755, over 4836.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2218, pruned_loss=0.03933, over 972809.65 frames.], batch size: 26, lr: 3.39e-04
2022-05-05 11:58:01,957 INFO [train.py:715] (4/8) Epoch 6, batch 8200, loss[loss=0.1404, simple_loss=0.2102, pruned_loss=0.0353, over 4806.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2213, pruned_loss=0.03946, over 972405.13 frames.], batch size: 14, lr: 3.39e-04
2022-05-05 11:58:41,278 INFO [train.py:715] (4/8) Epoch 6, batch 8250, loss[loss=0.1636, simple_loss=0.2368, pruned_loss=0.04514, over 4902.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2215, pruned_loss=0.03948, over 972427.62 frames.], batch size: 19, lr: 3.39e-04
2022-05-05 11:59:19,579 INFO [train.py:715] (4/8) Epoch 6, batch 8300, loss[loss=0.157, simple_loss=0.2199, pruned_loss=0.04705, over 4848.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2215, pruned_loss=0.03991, over 972360.93 frames.], batch size: 32, lr: 3.39e-04
2022-05-05 11:59:58,759 INFO [train.py:715] (4/8) Epoch 6, batch 8350, loss[loss=0.1436, simple_loss=0.2233, pruned_loss=0.03192, over 4965.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2223, pruned_loss=0.04008, over 972603.66 frames.], batch size: 39, lr: 3.39e-04
2022-05-05 12:00:37,620 INFO [train.py:715] (4/8) Epoch 6, batch 8400, loss[loss=0.1318, simple_loss=0.2012, pruned_loss=0.03122, over 4943.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2208, pruned_loss=0.03991, over 972765.91 frames.], batch size: 23, lr: 3.39e-04
2022-05-05 12:01:15,841 INFO [train.py:715] (4/8) Epoch 6, batch 8450, loss[loss=0.1248, simple_loss=0.2047, pruned_loss=0.02242, over 4849.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2206, pruned_loss=0.0395, over 972984.32 frames.], batch size: 20, lr: 3.39e-04
2022-05-05 12:01:54,986 INFO [train.py:715] (4/8) Epoch 6, batch 8500, loss[loss=0.1199, simple_loss=0.1903, pruned_loss=0.02479, over 4988.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2202, pruned_loss=0.0393, over 973623.71 frames.], batch size: 25, lr: 3.39e-04
2022-05-05 12:02:33,548 INFO [train.py:715] (4/8) Epoch 6, batch 8550, loss[loss=0.1469, simple_loss=0.2256, pruned_loss=0.03415, over 4982.00 frames.], tot_loss[loss=0.1495, simple_loss=0.22, pruned_loss=0.03955, over 974130.73 frames.], batch size: 14, lr: 3.39e-04
2022-05-05 12:03:12,438 INFO [train.py:715] (4/8) Epoch 6, batch 8600, loss[loss=0.1583, simple_loss=0.2281, pruned_loss=0.04427, over 4915.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2212, pruned_loss=0.04058, over 973808.44 frames.], batch size: 29, lr: 3.39e-04
2022-05-05 12:03:50,310 INFO [train.py:715] (4/8) Epoch 6, batch 8650, loss[loss=0.1643, simple_loss=0.2265, pruned_loss=0.051, over 4788.00 frames.], tot_loss[loss=0.1509, simple_loss=0.2214, pruned_loss=0.04021, over 972414.26 frames.], batch size: 14, lr: 3.39e-04
2022-05-05 12:04:29,732 INFO [train.py:715] (4/8) Epoch 6, batch 8700, loss[loss=0.1468, simple_loss=0.2209, pruned_loss=0.03634, over 4774.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2203, pruned_loss=0.03975, over 973074.65 frames.], batch size: 18, lr: 3.39e-04
2022-05-05 12:05:08,431 INFO [train.py:715] (4/8) Epoch 6, batch 8750, loss[loss=0.144, simple_loss=0.2148, pruned_loss=0.03656, over 4987.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2199, pruned_loss=0.03943, over 973559.09 frames.], batch size: 20, lr: 3.39e-04
2022-05-05 12:05:46,859 INFO [train.py:715] (4/8) Epoch 6, batch 8800, loss[loss=0.1305, simple_loss=0.204, pruned_loss=0.02853, over 4944.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2195, pruned_loss=0.03898, over 973340.13 frames.], batch size: 35, lr: 3.39e-04
2022-05-05 12:06:25,685 INFO [train.py:715] (4/8) Epoch 6, batch 8850, loss[loss=0.1378, simple_loss=0.208, pruned_loss=0.03377, over 4989.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2202, pruned_loss=0.03915, over 973167.98 frames.], batch size: 28, lr: 3.39e-04
2022-05-05 12:07:04,757 INFO [train.py:715] (4/8) Epoch 6, batch 8900, loss[loss=0.1364, simple_loss=0.2046, pruned_loss=0.03411, over 4968.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2199, pruned_loss=0.03878, over 972773.53 frames.], batch size: 14, lr: 3.39e-04
2022-05-05 12:07:43,994 INFO [train.py:715] (4/8) Epoch 6, batch 8950, loss[loss=0.1529, simple_loss=0.2222, pruned_loss=0.04182, over 4920.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2193, pruned_loss=0.03848, over 971849.89 frames.], batch size: 39, lr: 3.38e-04
2022-05-05 12:08:22,508 INFO [train.py:715] (4/8) Epoch 6, batch 9000, loss[loss=0.1857, simple_loss=0.2432, pruned_loss=0.06413, over 4748.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2198, pruned_loss=0.03878, over 972131.16 frames.], batch size: 16, lr: 3.38e-04
2022-05-05 12:08:22,508 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 12:08:35,890 INFO [train.py:742] (4/8) Epoch 6, validation: loss=0.1094, simple_loss=0.1946, pruned_loss=0.01213, over 914524.00 frames.
2022-05-05 12:09:14,900 INFO [train.py:715] (4/8) Epoch 6, batch 9050, loss[loss=0.1283, simple_loss=0.2058, pruned_loss=0.02535, over 4881.00 frames.], tot_loss[loss=0.148, simple_loss=0.219, pruned_loss=0.03846, over 972060.37 frames.], batch size: 16, lr: 3.38e-04
2022-05-05 12:09:53,934 INFO [train.py:715] (4/8) Epoch 6, batch 9100, loss[loss=0.1396, simple_loss=0.2154, pruned_loss=0.03187, over 4815.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2192, pruned_loss=0.03822, over 972185.72 frames.], batch size: 27, lr: 3.38e-04
2022-05-05 12:10:33,368 INFO [train.py:715] (4/8) Epoch 6, batch 9150, loss[loss=0.1591, simple_loss=0.2311, pruned_loss=0.04351, over 4932.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2198, pruned_loss=0.03873, over 972775.22 frames.], batch size: 29, lr: 3.38e-04
2022-05-05 12:11:11,395 INFO [train.py:715] (4/8) Epoch 6, batch 9200, loss[loss=0.1293, simple_loss=0.2015, pruned_loss=0.02861, over 4866.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2194, pruned_loss=0.0385, over 972703.01 frames.], batch size: 20, lr: 3.38e-04
2022-05-05 12:11:50,797 INFO [train.py:715] (4/8) Epoch 6, batch 9250, loss[loss=0.1859, simple_loss=0.2601, pruned_loss=0.05585, over 4909.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2198, pruned_loss=0.03873, over 972601.63 frames.], batch size: 18, lr: 3.38e-04
2022-05-05 12:12:29,886 INFO [train.py:715] (4/8) Epoch 6, batch 9300, loss[loss=0.1421, simple_loss=0.2088, pruned_loss=0.03772, over 4979.00 frames.], tot_loss[loss=0.15, simple_loss=0.2209, pruned_loss=0.03958, over 972873.07 frames.], batch size: 28, lr: 3.38e-04
2022-05-05 12:13:08,401 INFO [train.py:715] (4/8) Epoch 6, batch 9350, loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.0374, over 4791.00 frames.], tot_loss[loss=0.149, simple_loss=0.2198, pruned_loss=0.03914, over 972448.28 frames.], batch size: 14, lr: 3.38e-04
2022-05-05 12:13:47,628 INFO [train.py:715] (4/8) Epoch 6, batch 9400, loss[loss=0.1404, simple_loss=0.2152, pruned_loss=0.03274, over 4965.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2202, pruned_loss=0.03902, over 973384.36 frames.], batch size: 15, lr: 3.38e-04
2022-05-05 12:14:26,436 INFO [train.py:715] (4/8) Epoch 6, batch 9450, loss[loss=0.1457, simple_loss=0.2276, pruned_loss=0.03194, over 4790.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2206, pruned_loss=0.0395, over 972384.20 frames.], batch size: 17, lr: 3.38e-04
2022-05-05 12:15:05,763 INFO [train.py:715] (4/8) Epoch 6, batch 9500, loss[loss=0.1543, simple_loss=0.2235, pruned_loss=0.04255, over 4707.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2199, pruned_loss=0.03927, over 971356.50 frames.], batch size: 15, lr: 3.38e-04
2022-05-05 12:15:44,435 INFO [train.py:715] (4/8) Epoch 6, batch 9550, loss[loss=0.1546, simple_loss=0.2347, pruned_loss=0.03729, over 4878.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2204, pruned_loss=0.03937, over 970354.65 frames.], batch size: 22, lr: 3.38e-04
2022-05-05 12:16:23,398 INFO [train.py:715] (4/8) Epoch 6, batch 9600, loss[loss=0.145, simple_loss=0.2232, pruned_loss=0.03335, over 4821.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2207, pruned_loss=0.03971, over 970606.56 frames.], batch size: 26, lr: 3.38e-04
2022-05-05 12:17:02,129 INFO [train.py:715] (4/8) Epoch 6, batch 9650, loss[loss=0.1686, simple_loss=0.2375, pruned_loss=0.04988, over 4914.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2215, pruned_loss=0.03992, over 971297.05 frames.], batch size: 17, lr: 3.38e-04
2022-05-05 12:17:40,451 INFO [train.py:715] (4/8) Epoch 6, batch 9700, loss[loss=0.1515, simple_loss=0.2282, pruned_loss=0.03743, over 4953.00 frames.], tot_loss[loss=0.15, simple_loss=0.2211, pruned_loss=0.03948, over 972270.72 frames.], batch size: 21, lr: 3.38e-04
2022-05-05 12:18:19,758 INFO [train.py:715] (4/8) Epoch 6, batch 9750, loss[loss=0.1839, simple_loss=0.2416, pruned_loss=0.06305, over 4870.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2214, pruned_loss=0.03964, over 973180.37 frames.], batch size: 32, lr: 3.38e-04
2022-05-05 12:18:59,479 INFO [train.py:715] (4/8) Epoch 6, batch 9800, loss[loss=0.1572, simple_loss=0.2393, pruned_loss=0.03756, over 4948.00 frames.], tot_loss[loss=0.15, simple_loss=0.2213, pruned_loss=0.03942, over 972447.77 frames.], batch size: 21, lr: 3.38e-04
2022-05-05 12:19:39,847 INFO [train.py:715] (4/8) Epoch 6, batch 9850, loss[loss=0.1694, simple_loss=0.2456, pruned_loss=0.04661, over 4919.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2208, pruned_loss=0.03903, over 973188.41 frames.], batch size: 18, lr: 3.38e-04
2022-05-05 12:20:19,001 INFO [train.py:715] (4/8) Epoch 6, batch 9900, loss[loss=0.1299, simple_loss=0.2103, pruned_loss=0.02469, over 4954.00 frames.], tot_loss[loss=0.15, simple_loss=0.2213, pruned_loss=0.03935, over 973108.15 frames.], batch size: 21, lr: 3.38e-04
2022-05-05 12:20:59,135 INFO [train.py:715] (4/8) Epoch 6, batch 9950, loss[loss=0.1454, simple_loss=0.2107, pruned_loss=0.04002, over 4877.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2217, pruned_loss=0.03942, over 973356.48 frames.], batch size: 32, lr: 3.38e-04
2022-05-05 12:21:39,152 INFO [train.py:715] (4/8) Epoch 6, batch 10000, loss[loss=0.1536, simple_loss=0.2247, pruned_loss=0.04122, over 4775.00 frames.], tot_loss[loss=0.1511, simple_loss=0.2226, pruned_loss=0.03987, over 973613.42 frames.], batch size: 14, lr: 3.38e-04
2022-05-05 12:22:17,402 INFO [train.py:715] (4/8) Epoch 6, batch 10050, loss[loss=0.1644, simple_loss=0.2285, pruned_loss=0.05017, over 4869.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2219, pruned_loss=0.03974, over 973478.38 frames.], batch size: 16, lr: 3.38e-04
2022-05-05 12:22:56,769 INFO [train.py:715] (4/8) Epoch 6, batch 10100, loss[loss=0.1619, simple_loss=0.2322, pruned_loss=0.04582, over 4966.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2216, pruned_loss=0.03972, over 973808.26 frames.], batch size: 35, lr: 3.38e-04
2022-05-05 12:23:34,993 INFO [train.py:715] (4/8) Epoch 6, batch 10150, loss[loss=0.1483, simple_loss=0.2151, pruned_loss=0.04081, over 4762.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2216, pruned_loss=0.03992, over 972732.73 frames.], batch size: 14, lr: 3.38e-04
2022-05-05 12:24:14,025 INFO [train.py:715] (4/8) Epoch 6, batch 10200, loss[loss=0.16, simple_loss=0.2342, pruned_loss=0.04291, over 4992.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2207, pruned_loss=0.0396, over 972676.74 frames.], batch size: 14, lr: 3.38e-04
2022-05-05 12:24:52,553 INFO [train.py:715] (4/8) Epoch 6, batch 10250, loss[loss=0.1579, simple_loss=0.2317, pruned_loss=0.04202, over 4914.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2202, pruned_loss=0.0392, over 973089.24 frames.], batch size: 18, lr: 3.37e-04
2022-05-05 12:25:31,643 INFO [train.py:715] (4/8) Epoch 6, batch 10300, loss[loss=0.1683, simple_loss=0.2273, pruned_loss=0.05469, over 4878.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2203, pruned_loss=0.03969, over 972547.38 frames.], batch size: 16, lr: 3.37e-04
2022-05-05 12:26:10,144 INFO [train.py:715] (4/8) Epoch 6, batch 10350, loss[loss=0.1475, simple_loss=0.2241, pruned_loss=0.03548, over 4779.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2201, pruned_loss=0.03945, over 972524.59 frames.], batch size: 17, lr: 3.37e-04
2022-05-05 12:26:49,278 INFO [train.py:715] (4/8) Epoch 6, batch 10400, loss[loss=0.1365, simple_loss=0.2062, pruned_loss=0.03343, over 4792.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2208, pruned_loss=0.03956, over 973209.02 frames.], batch size: 18, lr: 3.37e-04
2022-05-05 12:27:27,709 INFO [train.py:715] (4/8) Epoch 6, batch 10450, loss[loss=0.13, simple_loss=0.2089, pruned_loss=0.02559, over 4910.00 frames.], tot_loss[loss=0.149, simple_loss=0.22, pruned_loss=0.039, over 972752.24 frames.], batch size: 17, lr: 3.37e-04
2022-05-05 12:28:06,364 INFO [train.py:715] (4/8) Epoch 6, batch 10500, loss[loss=0.158, simple_loss=0.2266, pruned_loss=0.04466, over 4907.00 frames.], tot_loss[loss=0.1489, simple_loss=0.22, pruned_loss=0.03887, over 972851.96 frames.], batch size: 17, lr: 3.37e-04
2022-05-05 12:28:45,431 INFO [train.py:715] (4/8) Epoch 6, batch 10550, loss[loss=0.1357, simple_loss=0.2129, pruned_loss=0.02927, over 4987.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2197, pruned_loss=0.03873, over 972325.08 frames.], batch size: 28, lr: 3.37e-04
2022-05-05 12:29:23,699 INFO [train.py:715] (4/8) Epoch 6, batch 10600, loss[loss=0.1494, simple_loss=0.2205, pruned_loss=0.03917, over 4758.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2206, pruned_loss=0.03915, over 972293.31 frames.], batch size: 16, lr: 3.37e-04
2022-05-05 12:30:02,901 INFO [train.py:715] (4/8) Epoch 6, batch 10650, loss[loss=0.154, simple_loss=0.2368, pruned_loss=0.03558, over 4971.00 frames.], tot_loss[loss=0.1487, simple_loss=0.22, pruned_loss=0.03866, over 972997.51 frames.], batch size: 15, lr: 3.37e-04
2022-05-05 12:30:41,617 INFO [train.py:715] (4/8) Epoch 6, batch 10700, loss[loss=0.1572, simple_loss=0.2324, pruned_loss=0.041, over 4913.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2203, pruned_loss=0.03862, over 972514.52 frames.], batch size: 17, lr: 3.37e-04
2022-05-05 12:31:20,572 INFO [train.py:715] (4/8) Epoch 6, batch 10750, loss[loss=0.1092, simple_loss=0.1852, pruned_loss=0.01661, over 4790.00 frames.], tot_loss[loss=0.149, simple_loss=0.2205, pruned_loss=0.03874, over 972744.55 frames.], batch size: 18, lr: 3.37e-04
2022-05-05 12:31:59,031 INFO [train.py:715] (4/8) Epoch 6, batch 10800, loss[loss=0.134, simple_loss=0.2165, pruned_loss=0.02577, over 4818.00 frames.], tot_loss[loss=0.1482, simple_loss=0.22, pruned_loss=0.03815, over 972498.80 frames.], batch size: 27, lr: 3.37e-04
2022-05-05 12:32:37,568 INFO [train.py:715] (4/8) Epoch 6, batch 10850, loss[loss=0.1604, simple_loss=0.2304, pruned_loss=0.04524, over 4833.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2197, pruned_loss=0.0385, over 972679.98 frames.], batch size: 30, lr: 3.37e-04
2022-05-05 12:33:15,995 INFO [train.py:715] (4/8) Epoch 6, batch 10900, loss[loss=0.1288, simple_loss=0.1993, pruned_loss=0.02911, over 4859.00 frames.], tot_loss[loss=0.148, simple_loss=0.2195, pruned_loss=0.03824, over 971765.34 frames.], batch size: 30, lr: 3.37e-04
2022-05-05 12:33:54,114 INFO [train.py:715] (4/8) Epoch 6, batch 10950, loss[loss=0.1269, simple_loss=0.1976, pruned_loss=0.02813, over 4882.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2195, pruned_loss=0.03876, over 971840.37 frames.], batch size: 22, lr: 3.37e-04
2022-05-05 12:34:33,261 INFO [train.py:715] (4/8) Epoch 6, batch 11000, loss[loss=0.1556, simple_loss=0.2199, pruned_loss=0.04569, over 4807.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2194, pruned_loss=0.03893, over 971549.49 frames.], batch size: 12, lr: 3.37e-04
2022-05-05 12:35:11,624 INFO [train.py:715] (4/8) Epoch 6, batch 11050, loss[loss=0.157, simple_loss=0.2272, pruned_loss=0.04339, over 4754.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2196, pruned_loss=0.03884, over 971870.72 frames.], batch size: 19, lr: 3.37e-04
2022-05-05 12:35:50,631 INFO [train.py:715] (4/8) Epoch 6, batch 11100, loss[loss=0.1399, simple_loss=0.2118, pruned_loss=0.03401, over 4879.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2196, pruned_loss=0.03909, over 972050.49 frames.], batch size: 16, lr: 3.37e-04
2022-05-05 12:36:29,029 INFO [train.py:715] (4/8) Epoch 6, batch 11150, loss[loss=0.1396, simple_loss=0.2092, pruned_loss=0.03501, over 4688.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2197, pruned_loss=0.03894, over 971871.44 frames.], batch size: 15, lr: 3.37e-04
2022-05-05 12:37:07,407 INFO [train.py:715] (4/8) Epoch 6, batch 11200, loss[loss=0.1461, simple_loss=0.216, pruned_loss=0.03808, over 4823.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2193, pruned_loss=0.03884, over 972087.47 frames.], batch size: 30, lr: 3.37e-04
2022-05-05 12:37:45,843 INFO [train.py:715] (4/8) Epoch 6, batch 11250, loss[loss=0.122, simple_loss=0.2022, pruned_loss=0.02088, over 4854.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2193, pruned_loss=0.03868, over 972154.06 frames.], batch size: 20, lr: 3.37e-04
2022-05-05 12:38:24,405 INFO [train.py:715] (4/8) Epoch 6, batch 11300, loss[loss=0.1555, simple_loss=0.2324, pruned_loss=0.03923, over 4962.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2191, pruned_loss=0.03889, over 972587.83 frames.], batch size: 24, lr: 3.37e-04
2022-05-05 12:39:03,681 INFO [train.py:715] (4/8) Epoch 6, batch 11350, loss[loss=0.1784, simple_loss=0.2578, pruned_loss=0.04945, over 4937.00 frames.], tot_loss[loss=0.149, simple_loss=0.2196, pruned_loss=0.03921, over 973282.99 frames.], batch size: 21, lr: 3.37e-04
2022-05-05 12:39:42,620 INFO [train.py:715] (4/8) Epoch 6, batch 11400, loss[loss=0.1463, simple_loss=0.2176, pruned_loss=0.03749, over 4951.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2194, pruned_loss=0.03889, over 973659.90 frames.], batch size: 35, lr: 3.37e-04
2022-05-05 12:40:21,680 INFO [train.py:715] (4/8) Epoch 6, batch 11450, loss[loss=0.197, simple_loss=0.2629, pruned_loss=0.0655, over 4890.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2191, pruned_loss=0.03862, over 973686.04 frames.], batch size: 19, lr: 3.37e-04
2022-05-05 12:40:59,950 INFO [train.py:715] (4/8) Epoch 6, batch 11500, loss[loss=0.1363, simple_loss=0.1942, pruned_loss=0.03915, over 4770.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2182, pruned_loss=0.03801, over 973441.69 frames.], batch size: 18, lr: 3.37e-04
2022-05-05 12:41:38,301 INFO [train.py:715] (4/8) Epoch 6, batch 11550, loss[loss=0.1668, simple_loss=0.2345, pruned_loss=0.04949, over 4863.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2175, pruned_loss=0.03761, over 973211.71 frames.], batch size: 32, lr: 3.36e-04
2022-05-05 12:42:17,677 INFO [train.py:715] (4/8) Epoch 6, batch 11600, loss[loss=0.1276, simple_loss=0.2082, pruned_loss=0.02346, over 4824.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2177, pruned_loss=0.03767, over 973221.42 frames.], batch size: 27, lr: 3.36e-04
2022-05-05 12:42:56,130 INFO [train.py:715] (4/8) Epoch 6, batch 11650, loss[loss=0.1238, simple_loss=0.2049, pruned_loss=0.02134, over 4910.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2177, pruned_loss=0.03761, over 973376.81 frames.], batch size: 29, lr: 3.36e-04
2022-05-05 12:43:34,997 INFO [train.py:715] (4/8) Epoch 6, batch 11700, loss[loss=0.1634, simple_loss=0.2332, pruned_loss=0.04679, over 4776.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2183, pruned_loss=0.03823, over 972446.94 frames.], batch size: 14, lr: 3.36e-04
2022-05-05 12:44:13,936 INFO [train.py:715] (4/8) Epoch 6, batch 11750, loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03367, over 4933.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2195, pruned_loss=0.03898, over 972752.28 frames.], batch size: 29, lr: 3.36e-04
2022-05-05 12:44:53,165 INFO [train.py:715] (4/8) Epoch 6, batch 11800, loss[loss=0.1345, simple_loss=0.2143, pruned_loss=0.02739, over 4779.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2194, pruned_loss=0.03877, over 972951.30 frames.], batch size: 17, lr: 3.36e-04
2022-05-05 12:45:31,841 INFO [train.py:715] (4/8) Epoch 6, batch 11850, loss[loss=0.1623, simple_loss=0.216, pruned_loss=0.05434, over 4788.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2192, pruned_loss=0.03866, over 973152.49 frames.], batch size: 21, lr: 3.36e-04
2022-05-05 12:46:10,413 INFO [train.py:715] (4/8) Epoch 6, batch 11900, loss[loss=0.1381, simple_loss=0.2003, pruned_loss=0.03797, over 4759.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2196, pruned_loss=0.03869, over 972916.05 frames.], batch size: 19, lr: 3.36e-04
2022-05-05 12:46:49,724 INFO [train.py:715] (4/8) Epoch 6, batch 11950, loss[loss=0.1497, simple_loss=0.2152, pruned_loss=0.04216, over 4867.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2194, pruned_loss=0.03851, over 973454.55 frames.], batch size: 20, lr: 3.36e-04
2022-05-05 12:47:28,220 INFO [train.py:715] (4/8) Epoch 6, batch 12000, loss[loss=0.1405, simple_loss=0.2075, pruned_loss=0.03675, over 4845.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2197, pruned_loss=0.03907, over 973231.38 frames.], batch size: 32, lr: 3.36e-04
2022-05-05 12:47:28,220 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 12:47:37,944 INFO [train.py:742] (4/8) Epoch 6, validation: loss=0.1091, simple_loss=0.1942, pruned_loss=0.01199, over 914524.00 frames.
2022-05-05 12:48:16,696 INFO [train.py:715] (4/8) Epoch 6, batch 12050, loss[loss=0.1222, simple_loss=0.2016, pruned_loss=0.02143, over 4776.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2187, pruned_loss=0.03847, over 973175.49 frames.], batch size: 18, lr: 3.36e-04
2022-05-05 12:48:56,375 INFO [train.py:715] (4/8) Epoch 6, batch 12100, loss[loss=0.1905, simple_loss=0.2453, pruned_loss=0.06787, over 4892.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2195, pruned_loss=0.03908, over 973104.69 frames.], batch size: 16, lr: 3.36e-04
2022-05-05 12:49:35,322 INFO [train.py:715] (4/8) Epoch 6, batch 12150, loss[loss=0.1811, simple_loss=0.2591, pruned_loss=0.05153, over 4757.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2194, pruned_loss=0.03921, over 972289.57 frames.], batch size: 19, lr: 3.36e-04
2022-05-05 12:50:14,104 INFO [train.py:715] (4/8) Epoch 6, batch 12200, loss[loss=0.1483, simple_loss=0.2376, pruned_loss=0.02952, over 4807.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2209, pruned_loss=0.03974, over 972382.07 frames.], batch size: 21, lr: 3.36e-04
2022-05-05 12:50:53,316 INFO [train.py:715] (4/8) Epoch 6, batch 12250, loss[loss=0.1764, simple_loss=0.2408, pruned_loss=0.056, over 4827.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2205, pruned_loss=0.03936, over 972793.43 frames.], batch size: 15, lr: 3.36e-04
2022-05-05 12:51:32,109 INFO [train.py:715] (4/8) Epoch 6, batch 12300, loss[loss=0.1684, simple_loss=0.228, pruned_loss=0.05441, over 4786.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2194, pruned_loss=0.03868, over 972597.95 frames.], batch size: 17, lr: 3.36e-04
2022-05-05 12:52:11,889 INFO [train.py:715] (4/8) Epoch 6, batch 12350, loss[loss=0.1619, simple_loss=0.2384, pruned_loss=0.04276, over 4973.00 frames.], tot_loss[loss=0.1491, simple_loss=0.22, pruned_loss=0.03908, over 973179.42 frames.], batch size: 15, lr: 3.36e-04
2022-05-05 12:52:50,505 INFO [train.py:715] (4/8) Epoch 6, batch 12400, loss[loss=0.1392, simple_loss=0.2029, pruned_loss=0.03778, over 4821.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2207, pruned_loss=0.03921, over 973442.64 frames.], batch size: 13, lr: 3.36e-04
2022-05-05 12:53:29,627 INFO [train.py:715] (4/8) Epoch 6, batch 12450, loss[loss=0.1519, simple_loss=0.2242, pruned_loss=0.03978, over 4975.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2213, pruned_loss=0.03956, over 972964.16 frames.], batch size: 15, lr: 3.36e-04
2022-05-05 12:54:08,747 INFO [train.py:715] (4/8) Epoch 6, batch 12500, loss[loss=0.1404, simple_loss=0.201, pruned_loss=0.03991, over 4758.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2212, pruned_loss=0.03966, over 973300.07 frames.], batch size: 12, lr: 3.36e-04
2022-05-05 12:54:47,050 INFO [train.py:715] (4/8) Epoch 6, batch 12550, loss[loss=0.1459, simple_loss=0.2224, pruned_loss=0.03474, over 4856.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2216, pruned_loss=0.03997, over 973006.17 frames.], batch size: 20, lr: 3.36e-04
2022-05-05 12:55:26,405 INFO [train.py:715] (4/8) Epoch 6, batch 12600, loss[loss=0.1805, simple_loss=0.2532, pruned_loss=0.05392, over 4960.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2217, pruned_loss=0.0398, over 972197.29 frames.], batch size: 15, lr: 3.36e-04
2022-05-05 12:56:05,093 INFO [train.py:715] (4/8) Epoch 6, batch 12650, loss[loss=0.1378, simple_loss=0.2108, pruned_loss=0.03245, over 4966.00 frames.], tot_loss[loss=0.15, simple_loss=0.2211, pruned_loss=0.03948, over 972234.78 frames.], batch size: 15, lr: 3.36e-04
2022-05-05 12:56:43,911 INFO [train.py:715] (4/8) Epoch 6, batch 12700, loss[loss=0.1364, simple_loss=0.205, pruned_loss=0.03392, over 4855.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2204, pruned_loss=0.03895, over 972308.74 frames.], batch size: 13, lr: 3.36e-04
2022-05-05 12:57:22,047 INFO [train.py:715] (4/8) Epoch 6, batch 12750, loss[loss=0.1243, simple_loss=0.201, pruned_loss=0.02379, over 4946.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2199, pruned_loss=0.03885, over 972024.39 frames.], batch size: 29, lr: 3.36e-04
2022-05-05 12:58:01,007 INFO [train.py:715] (4/8) Epoch 6, batch 12800, loss[loss=0.1508, simple_loss=0.2204, pruned_loss=0.04062, over 4861.00 frames.], tot_loss[loss=0.149, simple_loss=0.2204, pruned_loss=0.03884, over 972277.27 frames.], batch size: 38, lr: 3.36e-04
2022-05-05 12:58:39,732 INFO [train.py:715] (4/8) Epoch 6, batch 12850, loss[loss=0.1888, simple_loss=0.2372, pruned_loss=0.07021, over 4902.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2205, pruned_loss=0.039, over 971774.83 frames.], batch size: 17, lr: 3.35e-04
2022-05-05 12:59:18,385 INFO [train.py:715] (4/8) Epoch 6, batch 12900, loss[loss=0.1433, simple_loss=0.2171, pruned_loss=0.03481, over 4911.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2202, pruned_loss=0.03906, over 971767.51 frames.], batch size: 18, lr: 3.35e-04
2022-05-05 12:59:58,331 INFO [train.py:715] (4/8) Epoch 6, batch 12950, loss[loss=0.1595, simple_loss=0.2264, pruned_loss=0.0463, over 4908.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2195, pruned_loss=0.03862, over 971606.34 frames.], batch size: 17, lr: 3.35e-04
2022-05-05 13:00:37,483 INFO [train.py:715] (4/8) Epoch 6, batch 13000, loss[loss=0.1481, simple_loss=0.2157, pruned_loss=0.04021, over 4913.00 frames.], tot_loss[loss=0.148, simple_loss=0.2194, pruned_loss=0.03829, over 971637.19 frames.], batch size: 39, lr: 3.35e-04
2022-05-05 13:01:16,479 INFO [train.py:715] (4/8) Epoch 6, batch 13050, loss[loss=0.1539, simple_loss=0.2228, pruned_loss=0.04249, over 4692.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2205, pruned_loss=0.03899, over 971242.50 frames.], batch size: 15, lr: 3.35e-04
2022-05-05 13:01:54,766 INFO [train.py:715] (4/8) Epoch 6, batch 13100, loss[loss=0.1512, simple_loss=0.2213, pruned_loss=0.0406, over 4991.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2194, pruned_loss=0.03821, over 972419.89 frames.], batch size: 25, lr: 3.35e-04
2022-05-05 13:02:34,370 INFO [train.py:715] (4/8) Epoch 6, batch 13150, loss[loss=0.1454, simple_loss=0.2222, pruned_loss=0.03432, over 4771.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2202, pruned_loss=0.03872, over 972052.21 frames.], batch size: 17, lr: 3.35e-04
2022-05-05 13:03:12,923 INFO [train.py:715] (4/8) Epoch 6, batch 13200, loss[loss=0.1312, simple_loss=0.1954, pruned_loss=0.03348, over 4785.00 frames.], tot_loss[loss=0.149, simple_loss=0.2207, pruned_loss=0.03861, over 972157.35 frames.], batch size: 14, lr: 3.35e-04
2022-05-05 13:03:51,768 INFO [train.py:715] (4/8) Epoch 6, batch 13250, loss[loss=0.1632, simple_loss=0.2312, pruned_loss=0.04766, over 4843.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2207, pruned_loss=0.03898, over 972837.88 frames.], batch size: 30, lr: 3.35e-04
2022-05-05 13:04:30,643 INFO [train.py:715] (4/8) Epoch 6, batch 13300, loss[loss=0.1186, simple_loss=0.1998, pruned_loss=0.01867, over 4774.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2205, pruned_loss=0.03895, over 972451.59 frames.], batch size: 18, lr: 3.35e-04
2022-05-05 13:05:09,758 INFO [train.py:715] (4/8) Epoch 6, batch 13350, loss[loss=0.1387, simple_loss=0.2148, pruned_loss=0.03129, over 4831.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2199, pruned_loss=0.03884, over 971533.37 frames.], batch size: 15, lr: 3.35e-04
2022-05-05 13:05:48,893 INFO [train.py:715] (4/8) Epoch 6, batch 13400, loss[loss=0.15, simple_loss=0.2189, pruned_loss=0.04051, over 4832.00 frames.], tot_loss[loss=0.149, simple_loss=0.2204, pruned_loss=0.03883, over 972121.52 frames.], batch size: 30, lr: 3.35e-04
2022-05-05 13:06:27,484 INFO [train.py:715] (4/8) Epoch 6, batch 13450, loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.02828, over 4749.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2209, pruned_loss=0.03944, over 972292.86 frames.], batch size: 19, lr: 3.35e-04
2022-05-05 13:07:07,014 INFO [train.py:715] (4/8) Epoch 6, batch 13500, loss[loss=0.1883, simple_loss=0.2503, pruned_loss=0.06318, over 4903.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2213, pruned_loss=0.03988, over 972698.46 frames.], batch size: 17, lr: 3.35e-04
2022-05-05 13:07:45,023 INFO [train.py:715] (4/8) Epoch 6, batch 13550, loss[loss=0.2192, simple_loss=0.2615, pruned_loss=0.08843, over 4829.00 frames.], tot_loss[loss=0.1507, simple_loss=0.2217, pruned_loss=0.03988, over 972703.82 frames.], batch size: 15, lr: 3.35e-04
2022-05-05 13:08:23,985 INFO [train.py:715] (4/8) Epoch 6, batch 13600, loss[loss=0.1332, simple_loss=0.2133, pruned_loss=0.02656, over 4891.00 frames.], tot_loss[loss=0.1505, simple_loss=0.2217, pruned_loss=0.03963, over 972642.44 frames.], batch size: 19, lr: 3.35e-04
2022-05-05 13:09:03,111 INFO [train.py:715] (4/8) Epoch 6, batch 13650, loss[loss=0.1284, simple_loss=0.1989, pruned_loss=0.029, over 4945.00 frames.], tot_loss[loss=0.1513, simple_loss=0.2224, pruned_loss=0.0401, over 972429.13 frames.], batch size: 29, lr: 3.35e-04
2022-05-05 13:09:42,437 INFO [train.py:715] (4/8) Epoch 6, batch 13700, loss[loss=0.1375, simple_loss=0.2057, pruned_loss=0.03467, over 4909.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2221, pruned_loss=0.04017, over 972242.62 frames.], batch size: 18, lr: 3.35e-04
2022-05-05 13:10:21,547 INFO [train.py:715] (4/8) Epoch 6, batch 13750, loss[loss=0.1541, simple_loss=0.226, pruned_loss=0.04106, over 4988.00 frames.], tot_loss[loss=0.1506, simple_loss=0.2221, pruned_loss=0.0396, over 972358.86 frames.], batch size: 28, lr: 3.35e-04
2022-05-05 13:11:00,146 INFO [train.py:715] (4/8) Epoch 6, batch 13800, loss[loss=0.1312, simple_loss=0.1999, pruned_loss=0.03124, over 4885.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2212, pruned_loss=0.03946, over 971888.24 frames.], batch size: 22, lr: 3.35e-04
2022-05-05 13:11:40,117 INFO [train.py:715] (4/8) Epoch 6, batch 13850, loss[loss=0.1245, simple_loss=0.1994, pruned_loss=0.02485, over 4903.00 frames.], tot_loss[loss=0.1499, simple_loss=0.221, pruned_loss=0.03947, over 971990.46 frames.], batch size: 17, lr: 3.35e-04
2022-05-05 13:12:18,448 INFO [train.py:715] (4/8) Epoch 6, batch 13900, loss[loss=0.14, simple_loss=0.2035, pruned_loss=0.03826, over 4661.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2203, pruned_loss=0.03927, over 972140.10 frames.], batch size: 13, lr: 3.35e-04
2022-05-05 13:12:57,457 INFO [train.py:715] (4/8) Epoch 6, batch 13950, loss[loss=0.1544, simple_loss=0.2267, pruned_loss=0.04103, over 4773.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2197, pruned_loss=0.0388, over 972769.37 frames.], batch size: 14, lr: 3.35e-04
2022-05-05 13:13:36,063 INFO [train.py:715] (4/8) Epoch 6, batch 14000, loss[loss=0.1408, simple_loss=0.2157, pruned_loss=0.03297, over 4953.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2208, pruned_loss=0.03876, over 972833.60 frames.], batch size: 21, lr: 3.35e-04
2022-05-05 13:14:15,112 INFO [train.py:715] (4/8) Epoch 6, batch 14050, loss[loss=0.1377, simple_loss=0.212, pruned_loss=0.03166, over 4925.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.0385, over 973147.65 frames.], batch size: 18, lr: 3.35e-04
2022-05-05 13:14:53,532 INFO [train.py:715] (4/8) Epoch 6, batch 14100, loss[loss=0.1687, simple_loss=0.2422, pruned_loss=0.0476, over 4702.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2198, pruned_loss=0.03854, over 972268.68 frames.], batch size: 15, lr: 3.35e-04
2022-05-05 13:15:32,014 INFO [train.py:715] (4/8) Epoch 6, batch 14150, loss[loss=0.1324, simple_loss=0.2177, pruned_loss=0.02357, over 4876.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2203, pruned_loss=0.03865, over 972940.23 frames.], batch size: 22, lr: 3.35e-04
2022-05-05 13:16:11,445 INFO [train.py:715] (4/8) Epoch 6, batch 14200, loss[loss=0.145, simple_loss=0.2228, pruned_loss=0.03357, over 4966.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2192, pruned_loss=0.03832, over 972778.81 frames.], batch size: 25, lr: 3.34e-04
2022-05-05 13:16:50,086 INFO [train.py:715] (4/8) Epoch 6, batch 14250, loss[loss=0.1378, simple_loss=0.2067, pruned_loss=0.03447, over 4954.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.03855, over 973005.03 frames.], batch size: 24, lr: 3.34e-04
2022-05-05 13:17:29,121 INFO [train.py:715] (4/8) Epoch 6, batch 14300, loss[loss=0.1266, simple_loss=0.1889, pruned_loss=0.03217, over 4982.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2198, pruned_loss=0.03894, over 972681.70 frames.], batch size: 14, lr: 3.34e-04
2022-05-05 13:18:07,580 INFO [train.py:715] (4/8) Epoch 6, batch 14350, loss[loss=0.1714, simple_loss=0.2393, pruned_loss=0.05178, over 4878.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2202, pruned_loss=0.03925, over 972681.77 frames.], batch size: 16, lr: 3.34e-04
2022-05-05 13:18:47,508 INFO [train.py:715] (4/8) Epoch 6, batch 14400, loss[loss=0.1504, simple_loss=0.23, pruned_loss=0.03539, over 4935.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2201, pruned_loss=0.03917, over 972667.10 frames.], batch size: 23, lr: 3.34e-04
2022-05-05 13:19:25,857 INFO [train.py:715] (4/8) Epoch 6, batch 14450, loss[loss=0.1424, simple_loss=0.206, pruned_loss=0.03945, over 4849.00 frames.], tot_loss[loss=0.1491, simple_loss=0.22, pruned_loss=0.03908, over 973110.95 frames.], batch size: 30, lr: 3.34e-04
2022-05-05 13:20:04,246 INFO [train.py:715] (4/8) Epoch 6, batch 14500, loss[loss=0.1497, simple_loss=0.2224, pruned_loss=0.03846, over 4938.00 frames.], tot_loss[loss=0.149, simple_loss=0.2199, pruned_loss=0.03907, over 972997.28 frames.], batch size: 21, lr: 3.34e-04
2022-05-05 13:20:43,928 INFO [train.py:715] (4/8) Epoch 6, batch 14550, loss[loss=0.1339, simple_loss=0.21, pruned_loss=0.02888, over 4821.00 frames.], tot_loss[loss=0.149, simple_loss=0.2195, pruned_loss=0.03923, over 973390.00 frames.], batch size: 26, lr: 3.34e-04
2022-05-05 13:21:22,652 INFO [train.py:715] (4/8) Epoch 6, batch 14600, loss[loss=0.1436, simple_loss=0.224, pruned_loss=0.03162, over 4957.00 frames.], tot_loss[loss=0.149, simple_loss=0.22, pruned_loss=0.03903, over 973562.78 frames.], batch size: 21, lr: 3.34e-04
2022-05-05 13:22:01,119 INFO [train.py:715] (4/8) Epoch 6, batch 14650, loss[loss=0.1974, simple_loss=0.2587, pruned_loss=0.06802, over 4831.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2205, pruned_loss=0.03907, over 972419.42 frames.], batch size: 15, lr: 3.34e-04
2022-05-05 13:22:40,129 INFO [train.py:715] (4/8) Epoch 6, batch 14700, loss[loss=0.1233, simple_loss=0.1967, pruned_loss=0.02491, over 4851.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2197, pruned_loss=0.03882, over 971959.03 frames.], batch size: 13, lr: 3.34e-04
2022-05-05 13:23:19,674 INFO [train.py:715] (4/8) Epoch 6, batch 14750, loss[loss=0.1345, simple_loss=0.2182, pruned_loss=0.02536, over 4806.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2203, pruned_loss=0.03919, over 971457.22 frames.], batch size: 14, lr: 3.34e-04
2022-05-05 13:23:57,830 INFO [train.py:715] (4/8) Epoch 6, batch 14800, loss[loss=0.1266, simple_loss=0.2039, pruned_loss=0.02463, over 4728.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2194, pruned_loss=0.03862, over 972169.97 frames.], batch size: 16, lr: 3.34e-04
2022-05-05 13:24:35,998 INFO [train.py:715] (4/8) Epoch 6, batch 14850, loss[loss=0.1608, simple_loss=0.232, pruned_loss=0.04478, over 4872.00 frames.], tot_loss[loss=0.149, simple_loss=0.2202, pruned_loss=0.03891, over 971294.36 frames.], batch size: 20, lr: 3.34e-04
2022-05-05 13:25:15,102 INFO [train.py:715] (4/8) Epoch 6, batch 14900, loss[loss=0.1881, simple_loss=0.2582, pruned_loss=0.05899, over 4791.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2201, pruned_loss=0.03878, over 971069.09 frames.], batch size: 24, lr: 3.34e-04
2022-05-05 13:25:53,361 INFO [train.py:715] (4/8) Epoch 6, batch 14950, loss[loss=0.1523, simple_loss=0.2343, pruned_loss=0.03513, over 4912.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2207, pruned_loss=0.03905, over 971863.71 frames.], batch size: 23, lr: 3.34e-04
2022-05-05 13:26:32,022 INFO [train.py:715] (4/8) Epoch 6, batch 15000, loss[loss=0.119, simple_loss=0.1826, pruned_loss=0.02767, over 4887.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2194, pruned_loss=0.03844, over 972686.17 frames.], batch size: 32, lr: 3.34e-04
2022-05-05 13:26:32,022 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 13:26:41,818 INFO [train.py:742] (4/8) Epoch 6, validation: loss=0.1091, simple_loss=0.1941, pruned_loss=0.01202, over 914524.00 frames.
2022-05-05 13:27:20,604 INFO [train.py:715] (4/8) Epoch 6, batch 15050, loss[loss=0.1532, simple_loss=0.2271, pruned_loss=0.03966, over 4993.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2193, pruned_loss=0.03831, over 972026.18 frames.], batch size: 14, lr: 3.34e-04
2022-05-05 13:27:59,349 INFO [train.py:715] (4/8) Epoch 6, batch 15100, loss[loss=0.1655, simple_loss=0.2384, pruned_loss=0.04626, over 4813.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2193, pruned_loss=0.03828, over 971871.27 frames.], batch size: 27, lr: 3.34e-04
2022-05-05 13:28:41,261 INFO [train.py:715] (4/8) Epoch 6, batch 15150, loss[loss=0.1357, simple_loss=0.2049, pruned_loss=0.03323, over 4932.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2196, pruned_loss=0.03859, over 971786.73 frames.], batch size: 18, lr: 3.34e-04
2022-05-05 13:29:19,831 INFO [train.py:715] (4/8) Epoch 6, batch 15200, loss[loss=0.1401, simple_loss=0.2215, pruned_loss=0.02939, over 4892.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2189, pruned_loss=0.0384, over 972109.89 frames.], batch size: 17, lr: 3.34e-04
2022-05-05 13:29:58,374 INFO [train.py:715] (4/8) Epoch 6, batch 15250, loss[loss=0.1518, simple_loss=0.2186, pruned_loss=0.04246, over 4901.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2195, pruned_loss=0.03881, over 972595.82 frames.], batch size: 17, lr: 3.34e-04
2022-05-05 13:30:37,907 INFO [train.py:715] (4/8) Epoch 6, batch 15300, loss[loss=0.1737, simple_loss=0.244, pruned_loss=0.05172, over 4745.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2191, pruned_loss=0.0387, over 972059.52 frames.], batch size: 16, lr: 3.34e-04
2022-05-05 13:31:15,935 INFO [train.py:715] (4/8) Epoch 6, batch 15350, loss[loss=0.1017, simple_loss=0.1702, pruned_loss=0.0166, over 4803.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2192, pruned_loss=0.03863, over 971005.13 frames.], batch size: 13, lr: 3.34e-04
2022-05-05 13:31:54,941 INFO [train.py:715] (4/8) Epoch 6, batch 15400, loss[loss=0.1447, simple_loss=0.2161, pruned_loss=0.03665, over 4857.00 frames.], tot_loss[loss=0.1486, simple_loss=0.22, pruned_loss=0.03861, over 971391.81 frames.], batch size: 30, lr: 3.34e-04
2022-05-05 13:32:33,865 INFO [train.py:715] (4/8) Epoch 6, batch 15450, loss[loss=0.1435, simple_loss=0.2248, pruned_loss=0.03112, over 4923.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2205, pruned_loss=0.03886, over 971651.54 frames.], batch size: 19, lr: 3.34e-04
2022-05-05 13:33:13,326 INFO [train.py:715] (4/8) Epoch 6, batch 15500, loss[loss=0.1723, simple_loss=0.2474, pruned_loss=0.04859, over 4772.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2207, pruned_loss=0.0393, over 971924.42 frames.], batch size: 18, lr: 3.34e-04
2022-05-05 13:33:51,504 INFO [train.py:715] (4/8) Epoch 6, batch 15550, loss[loss=0.1304, simple_loss=0.1977, pruned_loss=0.03156, over 4837.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2208, pruned_loss=0.03949, over 972865.73 frames.], batch size: 13, lr: 3.33e-04
2022-05-05 13:34:30,394 INFO [train.py:715] (4/8) Epoch 6, batch 15600, loss[loss=0.1174, simple_loss=0.1885, pruned_loss=0.02312, over 4795.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2208, pruned_loss=0.03927, over 972644.00 frames.], batch size: 12, lr: 3.33e-04
2022-05-05 13:35:09,326 INFO [train.py:715] (4/8) Epoch 6, batch 15650, loss[loss=0.1532, simple_loss=0.2161, pruned_loss=0.04519, over 4924.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2205, pruned_loss=0.03909, over 973826.39 frames.], batch size: 18, lr: 3.33e-04
2022-05-05 13:35:47,370 INFO [train.py:715] (4/8) Epoch 6, batch 15700, loss[loss=0.1446, simple_loss=0.2161, pruned_loss=0.03654, over 4950.00 frames.], tot_loss[loss=0.149, simple_loss=0.2201, pruned_loss=0.03899, over 974063.86 frames.], batch size: 29, lr: 3.33e-04
2022-05-05 13:36:26,051 INFO [train.py:715] (4/8) Epoch 6, batch 15750, loss[loss=0.1425, simple_loss=0.2261, pruned_loss=0.02945, over 4881.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2203, pruned_loss=0.03906, over 973976.08 frames.], batch size: 16, lr: 3.33e-04
2022-05-05 13:37:04,792 INFO [train.py:715] (4/8) Epoch 6, batch 15800, loss[loss=0.1391, simple_loss=0.2094, pruned_loss=0.03439, over 4751.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2194, pruned_loss=0.03885, over 973323.97 frames.], batch size: 16, lr: 3.33e-04
2022-05-05 13:37:43,839 INFO [train.py:715] (4/8) Epoch 6, batch 15850, loss[loss=0.1296, simple_loss=0.2045, pruned_loss=0.02735, over 4940.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2191, pruned_loss=0.03877, over 972957.45 frames.], batch size: 23, lr: 3.33e-04
2022-05-05 13:38:22,282 INFO [train.py:715] (4/8) Epoch 6, batch 15900, loss[loss=0.1283, simple_loss=0.2057, pruned_loss=0.02551, over 4756.00 frames.], tot_loss[loss=0.148, simple_loss=0.2186, pruned_loss=0.03869, over 972793.84 frames.], batch size: 19, lr: 3.33e-04
2022-05-05 13:39:00,647 INFO [train.py:715] (4/8) Epoch 6, batch 15950, loss[loss=0.1569, simple_loss=0.2213, pruned_loss=0.04628, over 4837.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2186, pruned_loss=0.03858, over 972938.87 frames.], batch size: 30, lr: 3.33e-04
2022-05-05 13:39:39,974 INFO [train.py:715] (4/8) Epoch 6, batch 16000, loss[loss=0.16, simple_loss=0.2173, pruned_loss=0.05131, over 4862.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2194, pruned_loss=0.03869, over 972157.77 frames.], batch size: 30, lr: 3.33e-04
2022-05-05 13:40:18,431 INFO [train.py:715] (4/8) Epoch 6, batch 16050, loss[loss=0.1533, simple_loss=0.2301, pruned_loss=0.0382, over 4970.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2196, pruned_loss=0.03857, over 970987.04 frames.], batch size: 21, lr: 3.33e-04
2022-05-05 13:40:56,899 INFO [train.py:715] (4/8) Epoch 6, batch 16100, loss[loss=0.1483, simple_loss=0.2213, pruned_loss=0.03767, over 4783.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03767, over 972118.77 frames.], batch size: 18, lr: 3.33e-04
2022-05-05 13:41:35,294 INFO [train.py:715] (4/8) Epoch 6, batch 16150, loss[loss=0.167, simple_loss=0.2283, pruned_loss=0.05288, over 4904.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2191, pruned_loss=0.03796, over 971724.31 frames.], batch size: 17, lr: 3.33e-04
2022-05-05 13:42:14,794 INFO [train.py:715] (4/8) Epoch 6, batch 16200, loss[loss=0.1452, simple_loss=0.2129, pruned_loss=0.03878, over 4981.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2194, pruned_loss=0.038, over 972630.32 frames.], batch size: 14, lr: 3.33e-04
2022-05-05 13:42:53,110 INFO [train.py:715] (4/8) Epoch 6, batch 16250, loss[loss=0.2258, simple_loss=0.2991, pruned_loss=0.0763, over 4954.00 frames.], tot_loss[loss=0.1486, simple_loss=0.22, pruned_loss=0.03862, over 972646.30 frames.], batch size: 35, lr: 3.33e-04
2022-05-05 13:43:31,726 INFO [train.py:715] (4/8) Epoch 6, batch 16300, loss[loss=0.1458, simple_loss=0.2153, pruned_loss=0.03813, over 4993.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2197, pruned_loss=0.03825, over 973265.65 frames.], batch size: 14, lr: 3.33e-04
2022-05-05 13:44:11,198 INFO [train.py:715] (4/8) Epoch 6, batch 16350, loss[loss=0.1411, simple_loss=0.2139, pruned_loss=0.03419, over 4777.00 frames.], tot_loss[loss=0.1488, simple_loss=0.22, pruned_loss=0.03878, over 971857.11 frames.], batch size: 12, lr: 3.33e-04
2022-05-05 13:44:49,507 INFO [train.py:715] (4/8) Epoch 6, batch 16400, loss[loss=0.1213, simple_loss=0.1904, pruned_loss=0.02613, over 4780.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2193, pruned_loss=0.03826, over 972208.30 frames.], batch size: 17, lr: 3.33e-04
2022-05-05 13:45:28,822 INFO [train.py:715] (4/8) Epoch 6, batch 16450, loss[loss=0.1457, simple_loss=0.226, pruned_loss=0.03272, over 4926.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2195, pruned_loss=0.03847, over 971905.12 frames.], batch size: 23, lr: 3.33e-04
2022-05-05 13:46:07,627 INFO [train.py:715] (4/8) Epoch 6, batch 16500, loss[loss=0.1495, simple_loss=0.2241, pruned_loss=0.03746, over 4814.00 frames.], tot_loss[loss=0.148, simple_loss=0.2193, pruned_loss=0.03835, over 972045.42 frames.], batch size: 26, lr: 3.33e-04
2022-05-05 13:46:46,577 INFO [train.py:715] (4/8) Epoch 6, batch 16550, loss[loss=0.1548, simple_loss=0.2237, pruned_loss=0.04291, over 4959.00 frames.], tot_loss[loss=0.148, simple_loss=0.2194, pruned_loss=0.0383, over 971755.53 frames.], batch size: 23, lr: 3.33e-04
2022-05-05 13:47:24,408 INFO [train.py:715] (4/8) Epoch 6, batch 16600, loss[loss=0.155, simple_loss=0.2147, pruned_loss=0.04758, over 4793.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2193, pruned_loss=0.03844, over 971521.55 frames.], batch size: 14, lr: 3.33e-04
2022-05-05 13:48:03,149 INFO [train.py:715] (4/8) Epoch 6, batch 16650, loss[loss=0.1701, simple_loss=0.2551, pruned_loss=0.04258, over 4922.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2192, pruned_loss=0.03848, over 971412.73 frames.], batch size: 18, lr: 3.33e-04
2022-05-05 13:48:42,812 INFO [train.py:715] (4/8) Epoch 6, batch 16700, loss[loss=0.1322, simple_loss=0.2055, pruned_loss=0.0295, over 4916.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2193, pruned_loss=0.03865, over 971320.71 frames.], batch size: 17, lr: 3.33e-04
2022-05-05 13:49:21,220 INFO [train.py:715] (4/8) Epoch 6, batch 16750, loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03428, over 4974.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2197, pruned_loss=0.03871, over 971715.79 frames.], batch size: 25, lr: 3.33e-04
2022-05-05 13:50:00,119 INFO [train.py:715] (4/8) Epoch 6, batch 16800, loss[loss=0.1463, simple_loss=0.2119, pruned_loss=0.04037, over 4772.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2203, pruned_loss=0.03898, over 970954.19 frames.], batch size: 14, lr: 3.33e-04
2022-05-05 13:50:39,327 INFO [train.py:715] (4/8) Epoch 6, batch 16850, loss[loss=0.1437, simple_loss=0.2171, pruned_loss=0.03514, over 4971.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2206, pruned_loss=0.03907, over 971465.99 frames.], batch size: 24, lr: 3.33e-04
2022-05-05 13:51:19,121 INFO [train.py:715] (4/8) Epoch 6, batch 16900, loss[loss=0.1517, simple_loss=0.2321, pruned_loss=0.03564, over 4830.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2206, pruned_loss=0.03893, over 972509.74 frames.], batch size: 25, lr: 3.32e-04
2022-05-05 13:51:57,173 INFO [train.py:715] (4/8) Epoch 6, batch 16950, loss[loss=0.1507, simple_loss=0.2314, pruned_loss=0.03497, over 4819.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2209, pruned_loss=0.03911, over 972292.41 frames.], batch size: 27, lr: 3.32e-04
2022-05-05 13:52:36,226 INFO [train.py:715] (4/8) Epoch 6, batch 17000, loss[loss=0.1675, simple_loss=0.2392, pruned_loss=0.04794, over 4958.00 frames.], tot_loss[loss=0.149, simple_loss=0.2204, pruned_loss=0.03875, over 971707.08 frames.], batch size: 24, lr: 3.32e-04
2022-05-05 13:53:15,742 INFO [train.py:715] (4/8) Epoch 6, batch 17050, loss[loss=0.1572, simple_loss=0.2184, pruned_loss=0.04805, over 4852.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2199, pruned_loss=0.03843, over 972330.90 frames.], batch size: 30, lr: 3.32e-04
2022-05-05 13:53:53,897 INFO [train.py:715] (4/8) Epoch 6, batch 17100, loss[loss=0.1385, simple_loss=0.219, pruned_loss=0.02905, over 4746.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2198, pruned_loss=0.03856, over 972119.83 frames.], batch size: 19, lr: 3.32e-04
2022-05-05 13:54:32,774 INFO [train.py:715] (4/8) Epoch 6, batch 17150, loss[loss=0.1461, simple_loss=0.2241, pruned_loss=0.03401, over 4982.00 frames.], tot_loss[loss=0.149, simple_loss=0.22, pruned_loss=0.03906, over 972669.60 frames.], batch size: 27, lr: 3.32e-04
2022-05-05 13:55:11,750 INFO [train.py:715] (4/8) Epoch 6, batch 17200, loss[loss=0.1403, simple_loss=0.2097, pruned_loss=0.0355, over 4976.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2203, pruned_loss=0.03971, over 973302.44 frames.], batch size: 14, lr: 3.32e-04
2022-05-05 13:55:51,109 INFO [train.py:715] (4/8) Epoch 6, batch 17250, loss[loss=0.1498, simple_loss=0.2227, pruned_loss=0.03847, over 4986.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2196, pruned_loss=0.03937, over 973164.34 frames.], batch size: 14, lr: 3.32e-04
2022-05-05 13:56:29,075 INFO [train.py:715] (4/8) Epoch 6, batch 17300, loss[loss=0.1629, simple_loss=0.2276, pruned_loss=0.04909, over 4886.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2192, pruned_loss=0.03874, over 972226.55 frames.], batch size: 16, lr: 3.32e-04
2022-05-05 13:57:07,891 INFO [train.py:715] (4/8) Epoch 6, batch 17350, loss[loss=0.1591, simple_loss=0.2307, pruned_loss=0.04378, over 4764.00 frames.], tot_loss[loss=0.1493, simple_loss=0.22, pruned_loss=0.03927, over 971454.24 frames.], batch size: 17, lr: 3.32e-04
2022-05-05 13:57:47,273 INFO [train.py:715] (4/8) Epoch 6, batch 17400, loss[loss=0.1301, simple_loss=0.2014, pruned_loss=0.02938, over 4863.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2197, pruned_loss=0.0389, over 970490.71 frames.], batch size: 32, lr: 3.32e-04
2022-05-05 13:58:26,213 INFO [train.py:715] (4/8) Epoch 6, batch 17450, loss[loss=0.1536, simple_loss=0.2181, pruned_loss=0.04461, over 4857.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2186, pruned_loss=0.03832, over 970376.61 frames.], batch size: 12, lr: 3.32e-04
2022-05-05 13:59:04,830 INFO [train.py:715] (4/8) Epoch 6, batch 17500, loss[loss=0.1097, simple_loss=0.1794, pruned_loss=0.02, over 4781.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2183, pruned_loss=0.03806, over 971191.44 frames.], batch size: 14, lr: 3.32e-04
2022-05-05 13:59:43,982 INFO [train.py:715] (4/8) Epoch 6, batch 17550, loss[loss=0.1517, simple_loss=0.2358, pruned_loss=0.03379, over 4901.00 frames.], tot_loss[loss=0.147, simple_loss=0.2183, pruned_loss=0.03782, over 972024.86 frames.], batch size: 22, lr: 3.32e-04
2022-05-05 14:00:23,862 INFO [train.py:715] (4/8) Epoch 6, batch 17600, loss[loss=0.1344, simple_loss=0.2101, pruned_loss=0.02929, over 4903.00 frames.], tot_loss[loss=0.1479, simple_loss=0.219, pruned_loss=0.03845, over 972207.42 frames.], batch size: 39, lr: 3.32e-04
2022-05-05 14:01:01,424 INFO [train.py:715] (4/8) Epoch 6, batch 17650, loss[loss=0.1578, simple_loss=0.2214, pruned_loss=0.04716, over 4881.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2196, pruned_loss=0.0391, over 972333.00 frames.], batch size: 32, lr: 3.32e-04
2022-05-05 14:01:40,865 INFO [train.py:715] (4/8) Epoch 6, batch 17700, loss[loss=0.1222, simple_loss=0.2025, pruned_loss=0.02092, over 4811.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2198, pruned_loss=0.03888, over 972792.96 frames.], batch size: 21, lr: 3.32e-04
2022-05-05 14:02:20,252 INFO [train.py:715] (4/8) Epoch 6, batch 17750, loss[loss=0.1559, simple_loss=0.2368, pruned_loss=0.03748, over 4880.00 frames.], tot_loss[loss=0.1489, simple_loss=0.22, pruned_loss=0.03891, over 973214.32 frames.], batch size: 22, lr: 3.32e-04
2022-05-05 14:02:58,607 INFO [train.py:715] (4/8) Epoch 6, batch 17800, loss[loss=0.1339, simple_loss=0.1961, pruned_loss=0.03578, over 4993.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2196, pruned_loss=0.03892, over 973847.57 frames.], batch size: 14, lr: 3.32e-04
2022-05-05 14:03:37,539 INFO [train.py:715] (4/8) Epoch 6, batch 17850, loss[loss=0.1324, simple_loss=0.197, pruned_loss=0.03387, over 4893.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2192, pruned_loss=0.03895, over 973453.63 frames.], batch size: 16, lr: 3.32e-04
2022-05-05 14:04:16,748 INFO [train.py:715] (4/8) Epoch 6, batch 17900, loss[loss=0.1605, simple_loss=0.22, pruned_loss=0.05045, over 4982.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2192, pruned_loss=0.03872, over 973325.98 frames.], batch size: 39, lr: 3.32e-04
2022-05-05 14:04:56,311 INFO [train.py:715] (4/8) Epoch 6, batch 17950, loss[loss=0.1844, simple_loss=0.2528, pruned_loss=0.05794, over 4917.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2191, pruned_loss=0.03877, over 974229.04 frames.], batch size: 39, lr: 3.32e-04
2022-05-05 14:05:34,138 INFO [train.py:715] (4/8) Epoch 6, batch 18000, loss[loss=0.1236, simple_loss=0.1934, pruned_loss=0.0269, over 4873.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2187, pruned_loss=0.03846, over 973898.09 frames.], batch size: 20, lr: 3.32e-04
2022-05-05 14:05:34,139 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 14:05:43,883 INFO [train.py:742] (4/8) Epoch 6, validation: loss=0.1087, simple_loss=0.1939, pruned_loss=0.0118, over 914524.00 frames.
2022-05-05 14:06:22,340 INFO [train.py:715] (4/8) Epoch 6, batch 18050, loss[loss=0.1537, simple_loss=0.2248, pruned_loss=0.04128, over 4735.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2192, pruned_loss=0.03854, over 973090.17 frames.], batch size: 16, lr: 3.32e-04
2022-05-05 14:07:01,820 INFO [train.py:715] (4/8) Epoch 6, batch 18100, loss[loss=0.1594, simple_loss=0.2356, pruned_loss=0.0416, over 4726.00 frames.], tot_loss[loss=0.148, simple_loss=0.2192, pruned_loss=0.0384, over 973238.22 frames.], batch size: 16, lr: 3.32e-04
2022-05-05 14:07:41,266 INFO [train.py:715] (4/8) Epoch 6, batch 18150, loss[loss=0.1434, simple_loss=0.2106, pruned_loss=0.03807, over 4954.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2202, pruned_loss=0.0393, over 973186.11 frames.], batch size: 24, lr: 3.32e-04
2022-05-05 14:08:19,364 INFO [train.py:715] (4/8) Epoch 6, batch 18200, loss[loss=0.1523, simple_loss=0.2193, pruned_loss=0.04262, over 4887.00 frames.], tot_loss[loss=0.1489, simple_loss=0.22, pruned_loss=0.03888, over 972414.45 frames.], batch size: 16, lr: 3.32e-04
2022-05-05 14:08:58,863 INFO [train.py:715] (4/8) Epoch 6, batch 18250, loss[loss=0.169, simple_loss=0.2242, pruned_loss=0.05688, over 4885.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2196, pruned_loss=0.03865, over 972527.88 frames.], batch size: 22, lr: 3.31e-04
2022-05-05 14:09:38,214 INFO [train.py:715] (4/8) Epoch 6, batch 18300, loss[loss=0.1429, simple_loss=0.2162, pruned_loss=0.03475, over 4932.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2207, pruned_loss=0.03899, over 972725.91 frames.], batch size: 18, lr: 3.31e-04
2022-05-05 14:10:17,263 INFO [train.py:715] (4/8) Epoch 6, batch 18350, loss[loss=0.1457, simple_loss=0.2193, pruned_loss=0.03599, over 4766.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2199, pruned_loss=0.03863, over 972779.32 frames.], batch size: 14, lr: 3.31e-04
2022-05-05 14:10:55,593 INFO [train.py:715] (4/8) Epoch 6, batch 18400, loss[loss=0.1716, simple_loss=0.2355, pruned_loss=0.05382, over 4855.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2194, pruned_loss=0.03858, over 972525.36 frames.], batch size: 30, lr: 3.31e-04
2022-05-05 14:11:34,886 INFO [train.py:715] (4/8) Epoch 6, batch 18450, loss[loss=0.1545, simple_loss=0.223, pruned_loss=0.04304, over 4766.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2199, pruned_loss=0.03876, over 973808.87 frames.], batch size: 14, lr: 3.31e-04
2022-05-05 14:12:14,310 INFO [train.py:715] (4/8) Epoch 6, batch 18500, loss[loss=0.1497, simple_loss=0.224, pruned_loss=0.03773, over 4959.00 frames.], tot_loss[loss=0.148, simple_loss=0.2194, pruned_loss=0.03835, over 973905.26 frames.], batch size: 25, lr: 3.31e-04
2022-05-05 14:12:52,316 INFO [train.py:715] (4/8) Epoch 6, batch 18550, loss[loss=0.1411, simple_loss=0.2139, pruned_loss=0.03416, over 4777.00 frames.], tot_loss[loss=0.1488, simple_loss=0.22, pruned_loss=0.03881, over 973345.65 frames.], batch size: 18, lr: 3.31e-04
2022-05-05 14:13:31,752 INFO [train.py:715] (4/8) Epoch 6, batch 18600, loss[loss=0.1467, simple_loss=0.2175, pruned_loss=0.03788, over 4812.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2184, pruned_loss=0.03835, over 973004.64 frames.], batch size: 21, lr: 3.31e-04
2022-05-05 14:14:10,848 INFO [train.py:715] (4/8) Epoch 6, batch 18650, loss[loss=0.1361, simple_loss=0.2017, pruned_loss=0.03529, over 4990.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2186, pruned_loss=0.03828, over 973840.63 frames.], batch size: 14, lr: 3.31e-04
2022-05-05 14:14:50,389 INFO [train.py:715] (4/8) Epoch 6, batch 18700, loss[loss=0.1427, simple_loss=0.21, pruned_loss=0.03775, over 4845.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2189, pruned_loss=0.03825, over 973313.61 frames.], batch size: 26, lr: 3.31e-04
2022-05-05 14:15:28,530 INFO [train.py:715] (4/8) Epoch 6, batch 18750, loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02866, over 4938.00 frames.], tot_loss[loss=0.1476, simple_loss=0.219, pruned_loss=0.03807, over 972838.48 frames.], batch size: 21, lr: 3.31e-04
2022-05-05 14:16:07,703 INFO [train.py:715] (4/8) Epoch 6, batch 18800, loss[loss=0.1494, simple_loss=0.2261, pruned_loss=0.0363, over 4898.00 frames.], tot_loss[loss=0.148, simple_loss=0.2194, pruned_loss=0.03836, over 972862.18 frames.], batch size: 19, lr: 3.31e-04
2022-05-05 14:16:47,208 INFO [train.py:715] (4/8) Epoch 6, batch 18850, loss[loss=0.1399, simple_loss=0.2116, pruned_loss=0.03411, over 4830.00 frames.], tot_loss[loss=0.1479, simple_loss=0.219, pruned_loss=0.03839, over 972494.81 frames.], batch size: 26, lr: 3.31e-04
2022-05-05 14:17:25,255 INFO [train.py:715] (4/8) Epoch 6, batch 18900, loss[loss=0.1268, simple_loss=0.1975, pruned_loss=0.02812, over 4694.00 frames.], tot_loss[loss=0.1479, simple_loss=0.219, pruned_loss=0.03836, over 972522.80 frames.], batch size: 15, lr: 3.31e-04
2022-05-05 14:18:04,839 INFO [train.py:715] (4/8) Epoch 6, batch 18950, loss[loss=0.1499, simple_loss=0.2227, pruned_loss=0.0386, over 4832.00 frames.], tot_loss[loss=0.149, simple_loss=0.2199, pruned_loss=0.03903, over 972985.51 frames.], batch size: 15, lr: 3.31e-04
2022-05-05 14:18:43,966 INFO [train.py:715] (4/8) Epoch 6, batch 19000, loss[loss=0.1258, simple_loss=0.2031, pruned_loss=0.02422, over 4815.00 frames.], tot_loss[loss=0.149, simple_loss=0.22, pruned_loss=0.03903, over 971905.32 frames.], batch size: 27, lr: 3.31e-04
2022-05-05 14:19:23,160 INFO [train.py:715] (4/8) Epoch 6, batch 19050, loss[loss=0.1419, simple_loss=0.216, pruned_loss=0.03392, over 4824.00 frames.], tot_loss[loss=0.1499, simple_loss=0.221, pruned_loss=0.03943, over 971988.96 frames.], batch size: 26, lr: 3.31e-04
2022-05-05 14:20:01,541 INFO [train.py:715] (4/8) Epoch 6, batch 19100, loss[loss=0.1602, simple_loss=0.2274, pruned_loss=0.04653, over 4865.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2202, pruned_loss=0.03877, over 971656.66 frames.], batch size: 20, lr: 3.31e-04
2022-05-05 14:20:40,516 INFO [train.py:715] (4/8) Epoch 6, batch 19150, loss[loss=0.1473, simple_loss=0.2242, pruned_loss=0.03518, over 4968.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.03851, over 972195.69 frames.], batch size: 28, lr: 3.31e-04
2022-05-05 14:21:20,171 INFO [train.py:715] (4/8) Epoch 6, batch 19200, loss[loss=0.1626, simple_loss=0.2332, pruned_loss=0.04603, over 4908.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.03854, over 973526.71 frames.], batch size: 18, lr: 3.31e-04
2022-05-05 14:21:58,237 INFO [train.py:715] (4/8) Epoch 6, batch 19250, loss[loss=0.1203, simple_loss=0.1971, pruned_loss=0.02181, over 4783.00 frames.], tot_loss[loss=0.1488, simple_loss=0.22, pruned_loss=0.03875, over 972952.54 frames.], batch size: 17, lr: 3.31e-04
2022-05-05 14:22:37,141 INFO [train.py:715] (4/8) Epoch 6, batch 19300, loss[loss=0.1279, simple_loss=0.204, pruned_loss=0.02592, over 4810.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2197, pruned_loss=0.03866, over 971234.58 frames.], batch size: 25, lr: 3.31e-04
2022-05-05 14:23:16,401 INFO [train.py:715] (4/8) Epoch 6, batch 19350, loss[loss=0.1716, simple_loss=0.2255, pruned_loss=0.05882, over 4866.00 frames.], tot_loss[loss=0.1478, simple_loss=0.219, pruned_loss=0.0383, over 970854.11 frames.], batch size: 32, lr: 3.31e-04
2022-05-05 14:23:54,985 INFO [train.py:715] (4/8) Epoch 6, batch 19400, loss[loss=0.1544, simple_loss=0.2343, pruned_loss=0.03722, over 4793.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2197, pruned_loss=0.03851, over 970663.79 frames.], batch size: 14, lr: 3.31e-04
2022-05-05 14:24:33,671 INFO [train.py:715] (4/8) Epoch 6, batch 19450, loss[loss=0.1323, simple_loss=0.2021, pruned_loss=0.03123, over 4907.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2199, pruned_loss=0.03852, over 970880.89 frames.], batch size: 18, lr: 3.31e-04
2022-05-05 14:25:13,066 INFO [train.py:715] (4/8) Epoch 6, batch 19500, loss[loss=0.1573, simple_loss=0.2266, pruned_loss=0.044, over 4974.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2192, pruned_loss=0.03816, over 971103.17 frames.], batch size: 28, lr: 3.31e-04
2022-05-05 14:25:51,974 INFO [train.py:715] (4/8) Epoch 6, batch 19550, loss[loss=0.125, simple_loss=0.1989, pruned_loss=0.02553, over 4757.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2189, pruned_loss=0.03817, over 970480.93 frames.], batch size: 12, lr: 3.31e-04
2022-05-05 14:26:30,329 INFO [train.py:715] (4/8) Epoch 6, batch 19600, loss[loss=0.1267, simple_loss=0.2109, pruned_loss=0.02126, over 4798.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2185, pruned_loss=0.03765, over 970875.61 frames.], batch size: 21, lr: 3.31e-04
2022-05-05 14:27:09,234 INFO [train.py:715] (4/8) Epoch 6, batch 19650, loss[loss=0.1554, simple_loss=0.2282, pruned_loss=0.0413, over 4923.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2181, pruned_loss=0.03716, over 971142.58 frames.], batch size: 18, lr: 3.30e-04
2022-05-05 14:27:48,352 INFO [train.py:715] (4/8) Epoch 6, batch 19700, loss[loss=0.1877, simple_loss=0.2506, pruned_loss=0.06244, over 4985.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2183, pruned_loss=0.03734, over 972062.53 frames.], batch size: 25, lr: 3.30e-04
2022-05-05 14:28:27,134 INFO [train.py:715] (4/8) Epoch 6, batch 19750, loss[loss=0.1668, simple_loss=0.2303, pruned_loss=0.05169, over 4985.00 frames.], tot_loss[loss=0.147, simple_loss=0.2189, pruned_loss=0.03752, over 972542.15 frames.], batch size: 20, lr: 3.30e-04
2022-05-05 14:29:05,244 INFO [train.py:715] (4/8) Epoch 6, batch 19800, loss[loss=0.1438, simple_loss=0.2102, pruned_loss=0.03866, over 4829.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2194, pruned_loss=0.03792, over 972878.40 frames.], batch size: 13, lr: 3.30e-04
2022-05-05 14:29:44,605 INFO [train.py:715] (4/8) Epoch 6, batch 19850, loss[loss=0.15, simple_loss=0.2114, pruned_loss=0.04431, over 4690.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2196, pruned_loss=0.03827, over 972759.63 frames.], batch size: 15, lr: 3.30e-04
2022-05-05 14:30:24,343 INFO [train.py:715] (4/8) Epoch 6, batch 19900, loss[loss=0.1968, simple_loss=0.2537, pruned_loss=0.06998, over 4839.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2202, pruned_loss=0.03911, over 973012.39 frames.], batch size: 30, lr: 3.30e-04
2022-05-05 14:31:02,424 INFO [train.py:715] (4/8) Epoch 6, batch 19950, loss[loss=0.1409, simple_loss=0.2191, pruned_loss=0.03134, over 4820.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2202, pruned_loss=0.03939, over 972626.89 frames.], batch size: 25, lr: 3.30e-04
2022-05-05 14:31:41,548 INFO [train.py:715] (4/8) Epoch 6, batch 20000, loss[loss=0.1721, simple_loss=0.2486, pruned_loss=0.04777, over 4732.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2202, pruned_loss=0.03908, over 971926.61 frames.], batch size: 16, lr: 3.30e-04
2022-05-05 14:32:21,020 INFO [train.py:715] (4/8) Epoch 6, batch 20050, loss[loss=0.1448, simple_loss=0.2036, pruned_loss=0.04294, over 4780.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2191, pruned_loss=0.0382, over 972196.08 frames.], batch size: 14, lr: 3.30e-04
2022-05-05 14:32:59,452 INFO [train.py:715] (4/8) Epoch 6, batch 20100, loss[loss=0.1614, simple_loss=0.2296, pruned_loss=0.04661, over 4751.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2187, pruned_loss=0.0383, over 972576.52 frames.], batch size: 12, lr: 3.30e-04
2022-05-05 14:33:38,527 INFO [train.py:715] (4/8) Epoch 6, batch 20150, loss[loss=0.1516, simple_loss=0.2159, pruned_loss=0.04371, over 4989.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2192, pruned_loss=0.03824, over 972803.92 frames.], batch size: 14, lr: 3.30e-04
2022-05-05 14:34:17,810 INFO [train.py:715] (4/8) Epoch 6, batch 20200, loss[loss=0.1186, simple_loss=0.1966, pruned_loss=0.02025, over 4822.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2185, pruned_loss=0.03809, over 972428.66 frames.], batch size: 26, lr: 3.30e-04
2022-05-05 14:34:56,736 INFO [train.py:715] (4/8) Epoch 6, batch 20250, loss[loss=0.1807, simple_loss=0.2471, pruned_loss=0.05717, over 4689.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2185, pruned_loss=0.03807, over 972781.64 frames.], batch size: 15, lr: 3.30e-04
2022-05-05 14:35:35,498 INFO [train.py:715] (4/8) Epoch 6, batch 20300, loss[loss=0.1262, simple_loss=0.202, pruned_loss=0.02518, over 4816.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2189, pruned_loss=0.03819, over 971687.35 frames.], batch size: 25, lr: 3.30e-04
2022-05-05 14:36:14,861 INFO [train.py:715] (4/8) Epoch 6, batch 20350, loss[loss=0.1491, simple_loss=0.2176, pruned_loss=0.0403, over 4915.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2193, pruned_loss=0.03847, over 971513.51 frames.], batch size: 17, lr: 3.30e-04
2022-05-05 14:36:54,306 INFO [train.py:715] (4/8) Epoch 6, batch 20400, loss[loss=0.132, simple_loss=0.2113, pruned_loss=0.02636, over 4809.00 frames.], tot_loss[loss=0.148, simple_loss=0.2195, pruned_loss=0.03822, over 970905.96 frames.], batch size: 13, lr: 3.30e-04
2022-05-05 14:37:32,665 INFO [train.py:715] (4/8) Epoch 6, batch 20450, loss[loss=0.1337, simple_loss=0.2067, pruned_loss=0.03038, over 4703.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2205, pruned_loss=0.03904, over 971438.58 frames.], batch size: 15, lr: 3.30e-04
2022-05-05 14:38:11,469 INFO [train.py:715] (4/8) Epoch 6, batch 20500, loss[loss=0.159, simple_loss=0.2347, pruned_loss=0.04162, over 4774.00 frames.], tot_loss[loss=0.1502, simple_loss=0.2213, pruned_loss=0.03959, over 971712.94 frames.], batch size: 18, lr: 3.30e-04
2022-05-05 14:38:50,520 INFO [train.py:715] (4/8) Epoch 6, batch 20550, loss[loss=0.1347, simple_loss=0.2176, pruned_loss=0.02595, over 4804.00 frames.], tot_loss[loss=0.1498, simple_loss=0.2208, pruned_loss=0.03939, over 972273.81 frames.], batch size: 25, lr: 3.30e-04
2022-05-05 14:39:29,697 INFO [train.py:715] (4/8) Epoch 6, batch 20600, loss[loss=0.1934, simple_loss=0.2662, pruned_loss=0.06027, over 4889.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2209, pruned_loss=0.03923, over 972590.51 frames.], batch size: 32, lr: 3.30e-04
2022-05-05 14:40:07,965 INFO [train.py:715] (4/8) Epoch 6, batch 20650, loss[loss=0.127, simple_loss=0.1966, pruned_loss=0.02871, over 4893.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2203, pruned_loss=0.03844, over 972776.29 frames.], batch size: 19, lr: 3.30e-04
2022-05-05 14:40:46,654 INFO [train.py:715] (4/8) Epoch 6, batch 20700, loss[loss=0.1253, simple_loss=0.2035, pruned_loss=0.02352, over 4943.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2201, pruned_loss=0.03856, over 972550.25 frames.], batch size: 29, lr: 3.30e-04
2022-05-05 14:41:25,990 INFO [train.py:715] (4/8) Epoch 6, batch 20750, loss[loss=0.1594, simple_loss=0.2264, pruned_loss=0.04626, over 4744.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2194, pruned_loss=0.0385, over 972296.01 frames.], batch size: 16, lr: 3.30e-04
2022-05-05 14:42:04,389 INFO [train.py:715] (4/8) Epoch 6, batch 20800, loss[loss=0.1754, simple_loss=0.2425, pruned_loss=0.05419, over 4967.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2185, pruned_loss=0.03807, over 971693.88 frames.], batch size: 21, lr: 3.30e-04
2022-05-05 14:42:43,609 INFO [train.py:715] (4/8) Epoch 6, batch 20850, loss[loss=0.1339, simple_loss=0.2036, pruned_loss=0.03213, over 4762.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.03772, over 972068.18 frames.], batch size: 19, lr: 3.30e-04
2022-05-05 14:43:22,881 INFO [train.py:715] (4/8) Epoch 6, batch 20900, loss[loss=0.1448, simple_loss=0.2152, pruned_loss=0.0372, over 4983.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.0377, over 972592.47 frames.], batch size: 15, lr: 3.30e-04
2022-05-05 14:44:02,109 INFO [train.py:715] (4/8) Epoch 6, batch 20950, loss[loss=0.1418, simple_loss=0.2232, pruned_loss=0.03019, over 4879.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2187, pruned_loss=0.03782, over 972286.69 frames.], batch size: 22, lr: 3.30e-04
2022-05-05 14:44:40,092 INFO [train.py:715] (4/8) Epoch 6, batch 21000, loss[loss=0.1574, simple_loss=0.2321, pruned_loss=0.04133, over 4821.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2191, pruned_loss=0.03831, over 972165.18 frames.], batch size: 25, lr: 3.29e-04
2022-05-05 14:44:40,093 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 14:44:51,876 INFO [train.py:742] (4/8) Epoch 6, validation: loss=0.1089, simple_loss=0.1939, pruned_loss=0.01192, over 914524.00 frames.
2022-05-05 14:45:30,118 INFO [train.py:715] (4/8) Epoch 6, batch 21050, loss[loss=0.1658, simple_loss=0.2452, pruned_loss=0.04321, over 4961.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2194, pruned_loss=0.03817, over 971995.08 frames.], batch size: 39, lr: 3.29e-04
2022-05-05 14:46:09,485 INFO [train.py:715] (4/8) Epoch 6, batch 21100, loss[loss=0.1362, simple_loss=0.2085, pruned_loss=0.0319, over 4757.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2192, pruned_loss=0.038, over 971780.39 frames.], batch size: 16, lr: 3.29e-04
2022-05-05 14:46:48,885 INFO [train.py:715] (4/8) Epoch 6, batch 21150, loss[loss=0.1525, simple_loss=0.2288, pruned_loss=0.03805, over 4927.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2192, pruned_loss=0.03798, over 971609.48 frames.], batch size: 23, lr: 3.29e-04
2022-05-05 14:47:27,346 INFO [train.py:715] (4/8) Epoch 6, batch 21200, loss[loss=0.1681, simple_loss=0.238, pruned_loss=0.04913, over 4933.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2197, pruned_loss=0.03857, over 971908.24 frames.], batch size: 23, lr: 3.29e-04
2022-05-05 14:48:06,354 INFO [train.py:715] (4/8) Epoch 6, batch 21250, loss[loss=0.122, simple_loss=0.1937, pruned_loss=0.02517, over 4874.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2196, pruned_loss=0.03847, over 971391.40 frames.], batch size: 16, lr: 3.29e-04
2022-05-05 14:48:45,977 INFO [train.py:715] (4/8) Epoch 6, batch 21300, loss[loss=0.1316, simple_loss=0.2009, pruned_loss=0.03116, over 4822.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2187, pruned_loss=0.03798, over 971027.28 frames.], batch size: 26, lr: 3.29e-04
2022-05-05 14:49:24,955 INFO [train.py:715] (4/8) Epoch 6, batch 21350, loss[loss=0.1584, simple_loss=0.2311, pruned_loss=0.04285, over 4789.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2194, pruned_loss=0.03858, over 971295.29 frames.], batch size: 24, lr: 3.29e-04
2022-05-05 14:50:03,788 INFO [train.py:715] (4/8) Epoch 6, batch 21400, loss[loss=0.1445, simple_loss=0.2134, pruned_loss=0.03776, over 4761.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.03854, over 971455.11 frames.], batch size: 19, lr: 3.29e-04
2022-05-05 14:50:42,549 INFO [train.py:715] (4/8) Epoch 6, batch 21450, loss[loss=0.191, simple_loss=0.255, pruned_loss=0.06349, over 4976.00 frames.], tot_loss[loss=0.148, simple_loss=0.2195, pruned_loss=0.03825, over 973071.70 frames.], batch size: 24, lr: 3.29e-04
2022-05-05 14:51:21,821 INFO [train.py:715] (4/8) Epoch 6, batch 21500, loss[loss=0.1263, simple_loss=0.2054, pruned_loss=0.0236, over 4985.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2196, pruned_loss=0.03839, over 972751.84 frames.], batch size: 33, lr: 3.29e-04
2022-05-05 14:52:00,287 INFO [train.py:715] (4/8) Epoch 6, batch 21550, loss[loss=0.125, simple_loss=0.2062, pruned_loss=0.02188, over 4892.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2202, pruned_loss=0.03862, over 973200.95 frames.], batch size: 22, lr: 3.29e-04
2022-05-05 14:52:39,315 INFO [train.py:715] (4/8) Epoch 6, batch 21600, loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02991, over 4949.00 frames.], tot_loss[loss=0.1483, simple_loss=0.22, pruned_loss=0.03831, over 973191.59 frames.], batch size: 21, lr: 3.29e-04
2022-05-05 14:53:18,464 INFO [train.py:715] (4/8) Epoch 6, batch 21650, loss[loss=0.1631, simple_loss=0.2336, pruned_loss=0.04633, over 4908.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2201, pruned_loss=0.03821, over 973043.93 frames.], batch size: 17, lr: 3.29e-04
2022-05-05 14:53:57,744 INFO [train.py:715] (4/8) Epoch 6, batch 21700, loss[loss=0.1165, simple_loss=0.1889, pruned_loss=0.02208, over 4790.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2201, pruned_loss=0.0384, over 972412.38 frames.], batch size: 12, lr: 3.29e-04
2022-05-05 14:54:36,471 INFO [train.py:715] (4/8) Epoch 6, batch 21750, loss[loss=0.1684, simple_loss=0.2447, pruned_loss=0.04602, over 4748.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2204, pruned_loss=0.03854, over 972693.86 frames.], batch size: 19, lr: 3.29e-04
2022-05-05 14:55:15,313 INFO [train.py:715] (4/8) Epoch 6, batch 21800, loss[loss=0.1317, simple_loss=0.1986, pruned_loss=0.03242, over 4795.00 frames.], tot_loss[loss=0.149, simple_loss=0.2205, pruned_loss=0.03874, over 972475.12 frames.], batch size: 12, lr: 3.29e-04
2022-05-05 14:55:54,107 INFO [train.py:715] (4/8) Epoch 6, batch 21850, loss[loss=0.1501, simple_loss=0.2268, pruned_loss=0.03666, over 4926.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2205, pruned_loss=0.03922, over 972268.63 frames.], batch size: 17, lr: 3.29e-04
2022-05-05 14:56:32,647 INFO [train.py:715] (4/8) Epoch 6, batch 21900, loss[loss=0.162, simple_loss=0.2242, pruned_loss=0.04987, over 4708.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2208, pruned_loss=0.03976, over 972155.59 frames.], batch size: 15, lr: 3.29e-04
2022-05-05 14:57:11,519 INFO [train.py:715] (4/8) Epoch 6, batch 21950, loss[loss=0.1579, simple_loss=0.2154, pruned_loss=0.05018, over 4923.00 frames.], tot_loss[loss=0.1512, simple_loss=0.2216, pruned_loss=0.04039, over 971990.88 frames.], batch size: 17, lr: 3.29e-04
2022-05-05 14:57:50,235 INFO [train.py:715] (4/8) Epoch 6, batch 22000, loss[loss=0.1667, simple_loss=0.2357, pruned_loss=0.04882, over 4788.00 frames.], tot_loss[loss=0.1501, simple_loss=0.2208, pruned_loss=0.03974, over 971717.45 frames.], batch size: 14, lr: 3.29e-04
2022-05-05 14:58:29,939 INFO [train.py:715] (4/8) Epoch 6, batch 22050, loss[loss=0.1502, simple_loss=0.2183, pruned_loss=0.04101, over 4810.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2204, pruned_loss=0.03937, over 971892.35 frames.], batch size: 25, lr: 3.29e-04
2022-05-05 14:59:08,264 INFO [train.py:715] (4/8) Epoch 6, batch 22100, loss[loss=0.1365, simple_loss=0.212, pruned_loss=0.03055, over 4988.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2202, pruned_loss=0.03929, over 972220.59 frames.], batch size: 28, lr: 3.29e-04
2022-05-05 14:59:47,062 INFO [train.py:715] (4/8) Epoch 6, batch 22150, loss[loss=0.1756, simple_loss=0.2505, pruned_loss=0.05035, over 4903.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2191, pruned_loss=0.03835, over 971812.00 frames.], batch size: 29, lr: 3.29e-04
2022-05-05 15:00:26,257 INFO [train.py:715] (4/8) Epoch 6, batch 22200, loss[loss=0.1351, simple_loss=0.2072, pruned_loss=0.03152, over 4760.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2196, pruned_loss=0.03866, over 972316.45 frames.], batch size: 19, lr: 3.29e-04
2022-05-05 15:01:04,919 INFO [train.py:715] (4/8) Epoch 6, batch 22250, loss[loss=0.1299, simple_loss=0.2055, pruned_loss=0.02709, over 4911.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2206, pruned_loss=0.03921, over 971761.14 frames.], batch size: 29, lr: 3.29e-04
2022-05-05 15:01:43,599 INFO [train.py:715] (4/8) Epoch 6, batch 22300, loss[loss=0.1302, simple_loss=0.2047, pruned_loss=0.02786, over 4969.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2199, pruned_loss=0.0391, over 971726.63 frames.], batch size: 15, lr: 3.29e-04
2022-05-05 15:02:22,657 INFO [train.py:715] (4/8) Epoch 6, batch 22350, loss[loss=0.1289, simple_loss=0.2063, pruned_loss=0.02577, over 4854.00 frames.], tot_loss[loss=0.149, simple_loss=0.2201, pruned_loss=0.03891, over 970565.15 frames.], batch size: 15, lr: 3.29e-04
2022-05-05 15:03:02,003 INFO [train.py:715] (4/8) Epoch 6, batch 22400, loss[loss=0.1463, simple_loss=0.2168, pruned_loss=0.03789, over 4828.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2205, pruned_loss=0.03909, over 971509.88 frames.], batch size: 15, lr: 3.29e-04
2022-05-05 15:03:40,491 INFO [train.py:715] (4/8) Epoch 6, batch 22450, loss[loss=0.1614, simple_loss=0.2267, pruned_loss=0.04807, over 4866.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2196, pruned_loss=0.03866, over 970865.11 frames.], batch size: 32, lr: 3.28e-04
2022-05-05 15:04:19,440 INFO [train.py:715] (4/8) Epoch 6, batch 22500, loss[loss=0.2256, simple_loss=0.3018, pruned_loss=0.07468, over 4741.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2183, pruned_loss=0.03809, over 971015.02 frames.], batch size: 16, lr: 3.28e-04
2022-05-05 15:04:58,760 INFO [train.py:715] (4/8) Epoch 6, batch 22550, loss[loss=0.1378, simple_loss=0.2102, pruned_loss=0.03266, over 4920.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2178, pruned_loss=0.03792, over 971615.16 frames.], batch size: 19, lr: 3.28e-04
2022-05-05 15:05:37,170 INFO [train.py:715] (4/8) Epoch 6, batch 22600, loss[loss=0.1399, simple_loss=0.2089, pruned_loss=0.0355, over 4759.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2182, pruned_loss=0.03823, over 971444.70 frames.], batch size: 12, lr: 3.28e-04
2022-05-05 15:06:16,008 INFO [train.py:715] (4/8) Epoch 6, batch 22650, loss[loss=0.1713, simple_loss=0.2464, pruned_loss=0.04804, over 4899.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2202, pruned_loss=0.03874, over 971552.66 frames.], batch size: 19, lr: 3.28e-04
2022-05-05 15:06:54,605 INFO [train.py:715] (4/8) Epoch 6, batch 22700, loss[loss=0.1597, simple_loss=0.2272, pruned_loss=0.04607, over 4806.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2206, pruned_loss=0.03932, over 971036.69 frames.], batch size: 21, lr: 3.28e-04
2022-05-05 15:07:33,406 INFO [train.py:715] (4/8) Epoch 6, batch 22750, loss[loss=0.1373, simple_loss=0.2087, pruned_loss=0.03295, over 4866.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2204, pruned_loss=0.03928, over 971102.62 frames.], batch size: 20, lr: 3.28e-04
2022-05-05 15:08:11,865 INFO [train.py:715] (4/8) Epoch 6, batch 22800, loss[loss=0.1334, simple_loss=0.2066, pruned_loss=0.03008, over 4870.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2203, pruned_loss=0.03874, over 971632.40 frames.], batch size: 22, lr: 3.28e-04
2022-05-05 15:08:50,371 INFO [train.py:715] (4/8) Epoch 6, batch 22850, loss[loss=0.1442, simple_loss=0.2231, pruned_loss=0.0326, over 4759.00 frames.], tot_loss[loss=0.1493, simple_loss=0.221, pruned_loss=0.03885, over 971004.86 frames.], batch size: 14, lr: 3.28e-04
2022-05-05 15:09:29,030 INFO [train.py:715] (4/8) Epoch 6, batch 22900, loss[loss=0.1468, simple_loss=0.226, pruned_loss=0.03384, over 4791.00 frames.], tot_loss[loss=0.1496, simple_loss=0.221, pruned_loss=0.03912, over 970965.27 frames.], batch size: 21, lr: 3.28e-04
2022-05-05 15:10:08,159 INFO [train.py:715] (4/8) Epoch 6, batch 22950, loss[loss=0.1636, simple_loss=0.2249, pruned_loss=0.05113, over 4815.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2208, pruned_loss=0.03913, over 970876.29 frames.], batch size: 25, lr: 3.28e-04
2022-05-05 15:10:46,577 INFO [train.py:715] (4/8) Epoch 6, batch 23000, loss[loss=0.1683, simple_loss=0.2269, pruned_loss=0.05488, over 4739.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2198, pruned_loss=0.03926, over 971050.62 frames.], batch size: 16, lr: 3.28e-04
2022-05-05 15:11:25,821 INFO [train.py:715] (4/8) Epoch 6, batch 23050, loss[loss=0.1416, simple_loss=0.2287, pruned_loss=0.02729, over 4991.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2202, pruned_loss=0.03931, over 971693.07 frames.], batch size: 14, lr: 3.28e-04
2022-05-05 15:12:05,300 INFO [train.py:715] (4/8) Epoch 6, batch 23100, loss[loss=0.1339, simple_loss=0.1971, pruned_loss=0.03532, over 4967.00 frames.], tot_loss[loss=0.1491, simple_loss=0.22, pruned_loss=0.03914, over 971581.36 frames.], batch size: 14, lr: 3.28e-04
2022-05-05 15:12:46,120 INFO [train.py:715] (4/8) Epoch 6, batch 23150, loss[loss=0.1453, simple_loss=0.2193, pruned_loss=0.03571, over 4873.00 frames.], tot_loss[loss=0.1493, simple_loss=0.22, pruned_loss=0.03927, over 971589.87 frames.], batch size: 20, lr: 3.28e-04
2022-05-05 15:13:25,467 INFO [train.py:715] (4/8) Epoch 6, batch 23200, loss[loss=0.1592, simple_loss=0.2429, pruned_loss=0.03776, over 4888.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2203, pruned_loss=0.03907, over 972665.98 frames.], batch size: 22, lr: 3.28e-04
2022-05-05 15:14:04,867 INFO [train.py:715] (4/8) Epoch 6, batch 23250, loss[loss=0.147, simple_loss=0.2135, pruned_loss=0.04024, over 4912.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2192, pruned_loss=0.03897, over 972605.47 frames.], batch size: 29, lr: 3.28e-04
2022-05-05 15:14:43,526 INFO [train.py:715] (4/8) Epoch 6, batch 23300, loss[loss=0.1964, simple_loss=0.2505, pruned_loss=0.07112, over 4919.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2193, pruned_loss=0.03884, over 972273.54 frames.], batch size: 19, lr: 3.28e-04
2022-05-05 15:15:21,520 INFO [train.py:715] (4/8) Epoch 6, batch 23350, loss[loss=0.1273, simple_loss=0.1881, pruned_loss=0.0332, over 4896.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2196, pruned_loss=0.03878, over 972572.54 frames.], batch size: 22, lr: 3.28e-04
2022-05-05 15:16:00,567 INFO [train.py:715] (4/8) Epoch 6, batch 23400, loss[loss=0.1692, simple_loss=0.2243, pruned_loss=0.05704, over 4751.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2192, pruned_loss=0.03853, over 971906.85 frames.], batch size: 16, lr: 3.28e-04
2022-05-05 15:16:40,148 INFO [train.py:715] (4/8) Epoch 6, batch 23450, loss[loss=0.1379, simple_loss=0.2176, pruned_loss=0.02913, over 4793.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2188, pruned_loss=0.0382, over 971729.99 frames.], batch size: 24, lr: 3.28e-04
2022-05-05 15:17:19,140 INFO [train.py:715] (4/8) Epoch 6, batch 23500, loss[loss=0.138, simple_loss=0.2042, pruned_loss=0.03589, over 4823.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2191, pruned_loss=0.03827, over 971312.64 frames.], batch size: 13, lr: 3.28e-04
2022-05-05 15:17:58,347 INFO [train.py:715] (4/8) Epoch 6, batch 23550, loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03056, over 4974.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2195, pruned_loss=0.03807, over 972322.45 frames.], batch size: 25, lr: 3.28e-04
2022-05-05 15:18:37,515 INFO [train.py:715] (4/8) Epoch 6, batch 23600, loss[loss=0.1541, simple_loss=0.2295, pruned_loss=0.03938, over 4984.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2198, pruned_loss=0.03838, over 972059.71 frames.], batch size: 24, lr: 3.28e-04
2022-05-05 15:19:16,256 INFO [train.py:715] (4/8) Epoch 6, batch 23650, loss[loss=0.1479, simple_loss=0.222, pruned_loss=0.03688, over 4833.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2198, pruned_loss=0.03866, over 972051.31 frames.], batch size: 30, lr: 3.28e-04
2022-05-05 15:19:54,392 INFO [train.py:715] (4/8) Epoch 6, batch 23700, loss[loss=0.1523, simple_loss=0.2324, pruned_loss=0.03614, over 4823.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2204, pruned_loss=0.03862, over 972108.31 frames.], batch size: 25, lr: 3.28e-04
2022-05-05 15:20:33,414 INFO [train.py:715] (4/8) Epoch 6, batch 23750, loss[loss=0.1623, simple_loss=0.2275, pruned_loss=0.04856, over 4966.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2202, pruned_loss=0.03841, over 972569.04 frames.], batch size: 31, lr: 3.28e-04
2022-05-05 15:21:12,834 INFO [train.py:715] (4/8) Epoch 6, batch 23800, loss[loss=0.1467, simple_loss=0.2156, pruned_loss=0.0389, over 4963.00 frames.], tot_loss[loss=0.1482, simple_loss=0.22, pruned_loss=0.0382, over 973122.98 frames.], batch size: 21, lr: 3.28e-04
2022-05-05 15:21:51,202 INFO [train.py:715] (4/8) Epoch 6, batch 23850, loss[loss=0.1113, simple_loss=0.1813, pruned_loss=0.02067, over 4802.00 frames.], tot_loss[loss=0.1482, simple_loss=0.22, pruned_loss=0.03825, over 972478.72 frames.], batch size: 12, lr: 3.27e-04
2022-05-05 15:22:29,814 INFO [train.py:715] (4/8) Epoch 6, batch 23900, loss[loss=0.1417, simple_loss=0.2205, pruned_loss=0.03143, over 4938.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2202, pruned_loss=0.03811, over 972776.36 frames.], batch size: 29, lr: 3.27e-04
2022-05-05 15:23:08,545 INFO [train.py:715] (4/8) Epoch 6, batch 23950, loss[loss=0.117, simple_loss=0.1928, pruned_loss=0.02061, over 4946.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2194, pruned_loss=0.0382, over 972585.07 frames.], batch size: 29, lr: 3.27e-04
2022-05-05 15:23:47,224 INFO [train.py:715] (4/8) Epoch 6, batch 24000, loss[loss=0.1511, simple_loss=0.2167, pruned_loss=0.04276, over 4754.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2195, pruned_loss=0.03812, over 972858.03 frames.], batch size: 16, lr: 3.27e-04
2022-05-05 15:23:47,225 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 15:23:58,202 INFO [train.py:742] (4/8) Epoch 6, validation: loss=0.1089, simple_loss=0.1939, pruned_loss=0.01195, over 914524.00 frames.
2022-05-05 15:24:36,967 INFO [train.py:715] (4/8) Epoch 6, batch 24050, loss[loss=0.1648, simple_loss=0.2166, pruned_loss=0.05651, over 4839.00 frames.], tot_loss[loss=0.148, simple_loss=0.2198, pruned_loss=0.03809, over 972728.64 frames.], batch size: 30, lr: 3.27e-04
2022-05-05 15:25:15,031 INFO [train.py:715] (4/8) Epoch 6, batch 24100, loss[loss=0.1517, simple_loss=0.2208, pruned_loss=0.04128, over 4915.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2201, pruned_loss=0.03818, over 973234.44 frames.], batch size: 23, lr: 3.27e-04
2022-05-05 15:25:53,705 INFO [train.py:715] (4/8) Epoch 6, batch 24150, loss[loss=0.1939, simple_loss=0.2571, pruned_loss=0.06529, over 4981.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2202, pruned_loss=0.03803, over 972405.46 frames.], batch size: 20, lr: 3.27e-04
2022-05-05 15:26:32,799 INFO [train.py:715] (4/8) Epoch 6, batch 24200, loss[loss=0.1566, simple_loss=0.225, pruned_loss=0.04409, over 4842.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2214, pruned_loss=0.03898, over 973360.54 frames.], batch size: 13, lr: 3.27e-04
2022-05-05 15:27:10,721 INFO [train.py:715] (4/8) Epoch 6, batch 24250, loss[loss=0.1288, simple_loss=0.1964, pruned_loss=0.03063, over 4834.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2201, pruned_loss=0.0384, over 973118.34 frames.], batch size: 12, lr: 3.27e-04
2022-05-05 15:27:49,115 INFO [train.py:715] (4/8) Epoch 6, batch 24300, loss[loss=0.1487, simple_loss=0.2139, pruned_loss=0.04176, over 4866.00 frames.], tot_loss[loss=0.149, simple_loss=0.2204, pruned_loss=0.03883, over 973295.17 frames.], batch size: 32, lr: 3.27e-04
2022-05-05 15:28:28,043 INFO [train.py:715] (4/8) Epoch 6, batch 24350, loss[loss=0.1429, simple_loss=0.2226, pruned_loss=0.03165, over 4685.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2198, pruned_loss=0.03836, over 972318.13 frames.], batch size: 15, lr: 3.27e-04
2022-05-05 15:29:07,158 INFO [train.py:715] (4/8) Epoch 6, batch 24400, loss[loss=0.1459, simple_loss=0.2184, pruned_loss=0.03674, over 4759.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2202, pruned_loss=0.03869, over 972635.22 frames.], batch size: 14, lr: 3.27e-04
2022-05-05 15:29:45,509 INFO [train.py:715] (4/8) Epoch 6, batch 24450, loss[loss=0.1446, simple_loss=0.2234, pruned_loss=0.03291, over 4858.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2206, pruned_loss=0.03851, over 971610.99 frames.], batch size: 20, lr: 3.27e-04
2022-05-05 15:30:24,120 INFO [train.py:715] (4/8) Epoch 6, batch 24500, loss[loss=0.1508, simple_loss=0.2225, pruned_loss=0.03954, over 4757.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2209, pruned_loss=0.03868, over 972400.16 frames.], batch size: 19, lr: 3.27e-04
2022-05-05 15:31:03,940 INFO [train.py:715] (4/8) Epoch 6, batch 24550, loss[loss=0.1335, simple_loss=0.2069, pruned_loss=0.03005, over 4850.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2206, pruned_loss=0.03894, over 973194.80 frames.], batch size: 32, lr: 3.27e-04
2022-05-05 15:31:42,160 INFO [train.py:715] (4/8) Epoch 6, batch 24600, loss[loss=0.1346, simple_loss=0.1989, pruned_loss=0.03513, over 4764.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.0385, over 972418.47 frames.], batch size: 14, lr: 3.27e-04
2022-05-05 15:32:21,362 INFO [train.py:715] (4/8) Epoch 6, batch 24650, loss[loss=0.1224, simple_loss=0.1973, pruned_loss=0.02381, over 4768.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2198, pruned_loss=0.0384, over 971720.25 frames.], batch size: 19, lr: 3.27e-04
2022-05-05 15:33:00,613 INFO [train.py:715] (4/8) Epoch 6, batch 24700, loss[loss=0.1234, simple_loss=0.1986, pruned_loss=0.02416, over 4792.00 frames.], tot_loss[loss=0.1483, simple_loss=0.22, pruned_loss=0.03835, over 972424.67 frames.], batch size: 24, lr: 3.27e-04
2022-05-05 15:33:39,471 INFO [train.py:715] (4/8) Epoch 6, batch 24750, loss[loss=0.1773, simple_loss=0.2467, pruned_loss=0.05397, over 4988.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2199, pruned_loss=0.03837, over 972773.93 frames.], batch size: 25, lr: 3.27e-04
2022-05-05 15:34:17,834 INFO [train.py:715] (4/8) Epoch 6, batch 24800, loss[loss=0.1258, simple_loss=0.1965, pruned_loss=0.02761, over 4942.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2196, pruned_loss=0.03841, over 972696.69 frames.], batch size: 14, lr: 3.27e-04
2022-05-05 15:34:56,837 INFO [train.py:715] (4/8) Epoch 6, batch 24850, loss[loss=0.1361, simple_loss=0.2037, pruned_loss=0.03427, over 4748.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2193, pruned_loss=0.03816, over 971793.81 frames.], batch size: 12, lr: 3.27e-04
2022-05-05 15:35:36,648 INFO [train.py:715] (4/8) Epoch 6, batch 24900, loss[loss=0.1516, simple_loss=0.2261, pruned_loss=0.03857, over 4974.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2187, pruned_loss=0.03786, over 972149.57 frames.], batch size: 15, lr: 3.27e-04
2022-05-05 15:36:14,919 INFO [train.py:715] (4/8) Epoch 6, batch 24950, loss[loss=0.155, simple_loss=0.2294, pruned_loss=0.0403, over 4824.00 frames.], tot_loss[loss=0.1486, simple_loss=0.22, pruned_loss=0.03861, over 972819.50 frames.], batch size: 26, lr: 3.27e-04
2022-05-05 15:36:53,552 INFO [train.py:715] (4/8) Epoch 6, batch 25000, loss[loss=0.1347, simple_loss=0.2101, pruned_loss=0.02965, over 4983.00 frames.], tot_loss[loss=0.1485, simple_loss=0.22, pruned_loss=0.03849, over 972459.84 frames.], batch size: 25, lr: 3.27e-04
2022-05-05 15:37:32,634 INFO [train.py:715] (4/8) Epoch 6, batch 25050, loss[loss=0.1333, simple_loss=0.1997, pruned_loss=0.03344, over 4868.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2203, pruned_loss=0.03838, over 972358.37 frames.], batch size: 20, lr: 3.27e-04
2022-05-05 15:38:11,564 INFO [train.py:715] (4/8) Epoch 6, batch 25100, loss[loss=0.1281, simple_loss=0.2009, pruned_loss=0.02771, over 4696.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2204, pruned_loss=0.03828, over 972839.48 frames.], batch size: 15, lr: 3.27e-04
2022-05-05 15:38:50,093 INFO [train.py:715] (4/8) Epoch 6, batch 25150, loss[loss=0.1267, simple_loss=0.1965, pruned_loss=0.0284, over 4810.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2193, pruned_loss=0.03806, over 972207.99 frames.], batch size: 13, lr: 3.27e-04
2022-05-05 15:39:28,930 INFO [train.py:715] (4/8) Epoch 6, batch 25200, loss[loss=0.1287, simple_loss=0.2142, pruned_loss=0.02164, over 4989.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2197, pruned_loss=0.03793, over 972920.48 frames.], batch size: 25, lr: 3.27e-04
2022-05-05 15:40:07,782 INFO [train.py:715] (4/8) Epoch 6, batch 25250, loss[loss=0.1473, simple_loss=0.2139, pruned_loss=0.0403, over 4845.00 frames.], tot_loss[loss=0.1479, simple_loss=0.22, pruned_loss=0.03793, over 972942.33 frames.], batch size: 32, lr: 3.26e-04
2022-05-05 15:40:46,084 INFO [train.py:715] (4/8) Epoch 6, batch 25300, loss[loss=0.1627, simple_loss=0.2313, pruned_loss=0.04703, over 4808.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2202, pruned_loss=0.03826, over 972800.73 frames.], batch size: 25, lr: 3.26e-04
2022-05-05 15:41:24,369 INFO [train.py:715] (4/8) Epoch 6, batch 25350, loss[loss=0.1235, simple_loss=0.1947, pruned_loss=0.02611, over 4968.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2199, pruned_loss=0.03822, over 973546.34 frames.], batch size: 35, lr: 3.26e-04
2022-05-05 15:42:03,176 INFO [train.py:715] (4/8) Epoch 6, batch 25400, loss[loss=0.1456, simple_loss=0.2103, pruned_loss=0.04043, over 4953.00 frames.], tot_loss[loss=0.149, simple_loss=0.2205, pruned_loss=0.0387, over 972922.48 frames.], batch size: 35, lr: 3.26e-04
2022-05-05 15:42:41,991 INFO [train.py:715] (4/8) Epoch 6, batch 25450, loss[loss=0.1058, simple_loss=0.1738, pruned_loss=0.01894, over 4809.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2198, pruned_loss=0.03846, over 972340.78 frames.], batch size: 12, lr: 3.26e-04
2022-05-05 15:43:20,085 INFO [train.py:715] (4/8) Epoch 6, batch 25500, loss[loss=0.1396, simple_loss=0.2103, pruned_loss=0.03441, over 4864.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2189, pruned_loss=0.03809, over 971708.79 frames.], batch size: 32, lr: 3.26e-04
2022-05-05 15:43:58,583 INFO [train.py:715] (4/8) Epoch 6, batch 25550, loss[loss=0.1506, simple_loss=0.2267, pruned_loss=0.03724, over 4849.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2195, pruned_loss=0.03817, over 971616.11 frames.], batch size: 20, lr: 3.26e-04
2022-05-05 15:44:37,704 INFO [train.py:715] (4/8) Epoch 6, batch 25600, loss[loss=0.1304, simple_loss=0.1944, pruned_loss=0.03314, over 4641.00 frames.], tot_loss[loss=0.1471, simple_loss=0.219, pruned_loss=0.03766, over 971110.38 frames.], batch size: 13, lr: 3.26e-04
2022-05-05 15:45:15,952 INFO [train.py:715] (4/8) Epoch 6, batch 25650, loss[loss=0.1437, simple_loss=0.2222, pruned_loss=0.03262, over 4754.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2204, pruned_loss=0.03832, over 971327.35 frames.], batch size: 19, lr: 3.26e-04
2022-05-05 15:45:54,757 INFO [train.py:715] (4/8) Epoch 6, batch 25700, loss[loss=0.1539, simple_loss=0.2227, pruned_loss=0.0426, over 4840.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2192, pruned_loss=0.0377, over 970985.61 frames.], batch size: 32, lr: 3.26e-04
2022-05-05 15:46:34,045 INFO [train.py:715] (4/8) Epoch 6, batch 25750, loss[loss=0.1335, simple_loss=0.2186, pruned_loss=0.0242, over 4781.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2194, pruned_loss=0.03816, over 971323.42 frames.], batch size: 19, lr: 3.26e-04
2022-05-05 15:47:12,320 INFO [train.py:715] (4/8) Epoch 6, batch 25800, loss[loss=0.1591, simple_loss=0.2261, pruned_loss=0.04602, over 4799.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2185, pruned_loss=0.03823, over 971714.98 frames.], batch size: 13, lr: 3.26e-04
2022-05-05 15:47:50,579 INFO [train.py:715] (4/8) Epoch 6, batch 25850, loss[loss=0.137, simple_loss=0.2054, pruned_loss=0.03429, over 4984.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2175, pruned_loss=0.03767, over 972468.00 frames.], batch size: 27, lr: 3.26e-04
2022-05-05 15:48:29,219 INFO [train.py:715] (4/8) Epoch 6, batch 25900, loss[loss=0.1616, simple_loss=0.22, pruned_loss=0.05161, over 4944.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2188, pruned_loss=0.03854, over 972706.19 frames.], batch size: 18, lr: 3.26e-04
2022-05-05 15:49:08,367 INFO [train.py:715] (4/8) Epoch 6, batch 25950, loss[loss=0.1398, simple_loss=0.2029, pruned_loss=0.03834, over 4749.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2201, pruned_loss=0.03925, over 972882.71 frames.], batch size: 16, lr: 3.26e-04
2022-05-05 15:49:46,045 INFO [train.py:715] (4/8) Epoch 6, batch 26000, loss[loss=0.1632, simple_loss=0.2327, pruned_loss=0.04686, over 4981.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2198, pruned_loss=0.03888, over 972640.51 frames.], batch size: 15, lr: 3.26e-04
2022-05-05 15:50:24,230 INFO [train.py:715] (4/8) Epoch 6, batch 26050, loss[loss=0.1286, simple_loss=0.2037, pruned_loss=0.02672, over 4649.00 frames.], tot_loss[loss=0.148, simple_loss=0.2189, pruned_loss=0.0385, over 972637.77 frames.], batch size: 13, lr: 3.26e-04
2022-05-05 15:51:03,213 INFO [train.py:715] (4/8) Epoch 6, batch 26100, loss[loss=0.118, simple_loss=0.1941, pruned_loss=0.02092, over 4907.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2184, pruned_loss=0.03825, over 973111.68 frames.], batch size: 17, lr: 3.26e-04
2022-05-05 15:51:41,623 INFO [train.py:715] (4/8) Epoch 6, batch 26150, loss[loss=0.1426, simple_loss=0.2139, pruned_loss=0.0357, over 4829.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2187, pruned_loss=0.03835, over 972812.48 frames.], batch size: 15, lr: 3.26e-04
2022-05-05 15:52:20,119 INFO [train.py:715] (4/8) Epoch 6, batch 26200, loss[loss=0.1734, simple_loss=0.2418, pruned_loss=0.05249, over 4868.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2193, pruned_loss=0.03828, over 972642.03 frames.], batch size: 22, lr: 3.26e-04
2022-05-05 15:52:58,596 INFO [train.py:715] (4/8) Epoch 6, batch 26250, loss[loss=0.1249, simple_loss=0.2032, pruned_loss=0.02325, over 4804.00 frames.], tot_loss[loss=0.148, simple_loss=0.2195, pruned_loss=0.03826, over 971487.77 frames.], batch size: 25, lr: 3.26e-04
2022-05-05 15:53:37,251 INFO [train.py:715] (4/8) Epoch 6, batch 26300, loss[loss=0.138, simple_loss=0.2037, pruned_loss=0.03618, over 4805.00 frames.], tot_loss[loss=0.1487, simple_loss=0.22, pruned_loss=0.03872, over 971453.62 frames.], batch size: 14, lr: 3.26e-04
2022-05-05 15:54:15,317 INFO [train.py:715] (4/8) Epoch 6, batch 26350, loss[loss=0.165, simple_loss=0.2432, pruned_loss=0.04347, over 4935.00 frames.], tot_loss[loss=0.1499, simple_loss=0.2209, pruned_loss=0.03948, over 971746.91 frames.], batch size: 21, lr: 3.26e-04
2022-05-05 15:54:53,793 INFO [train.py:715] (4/8) Epoch 6, batch 26400, loss[loss=0.1347, simple_loss=0.2036, pruned_loss=0.03291, over 4840.00 frames.], tot_loss[loss=0.1504, simple_loss=0.221, pruned_loss=0.03987, over 971645.70 frames.], batch size: 13, lr: 3.26e-04
2022-05-05 15:55:33,105 INFO [train.py:715] (4/8) Epoch 6, batch 26450, loss[loss=0.142, simple_loss=0.2231, pruned_loss=0.03044, over 4764.00 frames.], tot_loss[loss=0.1493, simple_loss=0.22, pruned_loss=0.03934, over 971774.28 frames.], batch size: 14, lr: 3.26e-04
2022-05-05 15:56:11,694 INFO [train.py:715] (4/8) Epoch 6, batch 26500, loss[loss=0.1199, simple_loss=0.1916, pruned_loss=0.02413, over 4883.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2194, pruned_loss=0.03879, over 971956.91 frames.], batch size: 16, lr: 3.26e-04
2022-05-05 15:56:50,073 INFO [train.py:715] (4/8) Epoch 6, batch 26550, loss[loss=0.1338, simple_loss=0.2069, pruned_loss=0.03038, over 4936.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2191, pruned_loss=0.03895, over 972246.84 frames.], batch size: 29, lr: 3.26e-04
2022-05-05 15:57:28,901 INFO [train.py:715] (4/8) Epoch 6, batch 26600, loss[loss=0.1699, simple_loss=0.2153, pruned_loss=0.0623, over 4960.00 frames.], tot_loss[loss=0.1482, simple_loss=0.219, pruned_loss=0.03865, over 972178.40 frames.], batch size: 15, lr: 3.26e-04
2022-05-05 15:58:07,541 INFO [train.py:715] (4/8) Epoch 6, batch 26650, loss[loss=0.1447, simple_loss=0.2349, pruned_loss=0.02721, over 4888.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2189, pruned_loss=0.03848, over 972478.22 frames.], batch size: 19, lr: 3.26e-04
2022-05-05 15:58:46,266 INFO [train.py:715] (4/8) Epoch 6, batch 26700, loss[loss=0.1556, simple_loss=0.2248, pruned_loss=0.04327, over 4833.00 frames.], tot_loss[loss=0.147, simple_loss=0.2181, pruned_loss=0.038, over 972380.78 frames.], batch size: 15, lr: 3.25e-04
2022-05-05 15:59:24,554 INFO [train.py:715] (4/8) Epoch 6, batch 26750, loss[loss=0.1557, simple_loss=0.2296, pruned_loss=0.04096, over 4870.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2178, pruned_loss=0.03767, over 972913.25 frames.], batch size: 20, lr: 3.25e-04
2022-05-05 16:00:03,786 INFO [train.py:715] (4/8) Epoch 6, batch 26800, loss[loss=0.1543, simple_loss=0.2292, pruned_loss=0.03973, over 4973.00 frames.], tot_loss[loss=0.147, simple_loss=0.218, pruned_loss=0.03803, over 972600.25 frames.], batch size: 39, lr: 3.25e-04
2022-05-05 16:00:41,899 INFO [train.py:715] (4/8) Epoch 6, batch 26850, loss[loss=0.1297, simple_loss=0.1919, pruned_loss=0.03376, over 4774.00 frames.], tot_loss[loss=0.1472, simple_loss=0.218, pruned_loss=0.03814, over 972059.06 frames.], batch size: 14, lr: 3.25e-04
2022-05-05 16:01:20,552 INFO [train.py:715] (4/8) Epoch 6, batch 26900, loss[loss=0.1491, simple_loss=0.2153, pruned_loss=0.04145, over 4982.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2189, pruned_loss=0.03879, over 971944.60 frames.], batch size: 14, lr: 3.25e-04
2022-05-05 16:01:59,792 INFO [train.py:715] (4/8) Epoch 6, batch 26950, loss[loss=0.1646, simple_loss=0.2334, pruned_loss=0.04791, over 4947.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2183, pruned_loss=0.03857, over 971255.90 frames.], batch size: 35, lr: 3.25e-04
2022-05-05 16:02:39,038 INFO [train.py:715] (4/8) Epoch 6, batch 27000, loss[loss=0.1585, simple_loss=0.2322, pruned_loss=0.04238, over 4792.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2183, pruned_loss=0.03869, over 971566.22 frames.], batch size: 17, lr: 3.25e-04
2022-05-05 16:02:39,039 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 16:02:48,795 INFO [train.py:742] (4/8) Epoch 6, validation: loss=0.1088, simple_loss=0.1938, pruned_loss=0.01188, over 914524.00 frames.
2022-05-05 16:03:28,074 INFO [train.py:715] (4/8) Epoch 6, batch 27050, loss[loss=0.1403, simple_loss=0.2188, pruned_loss=0.03087, over 4913.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2187, pruned_loss=0.03878, over 972175.36 frames.], batch size: 19, lr: 3.25e-04
2022-05-05 16:04:06,806 INFO [train.py:715] (4/8) Epoch 6, batch 27100, loss[loss=0.1501, simple_loss=0.2241, pruned_loss=0.03804, over 4800.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2187, pruned_loss=0.03888, over 971287.91 frames.], batch size: 21, lr: 3.25e-04
2022-05-05 16:04:45,439 INFO [train.py:715] (4/8) Epoch 6, batch 27150, loss[loss=0.1317, simple_loss=0.204, pruned_loss=0.02972, over 4922.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2191, pruned_loss=0.03873, over 972149.72 frames.], batch size: 21, lr: 3.25e-04
2022-05-05 16:05:25,173 INFO [train.py:715] (4/8) Epoch 6, batch 27200, loss[loss=0.1634, simple_loss=0.2305, pruned_loss=0.04815, over 4888.00 frames.], tot_loss[loss=0.148, simple_loss=0.2191, pruned_loss=0.0385, over 972174.01 frames.], batch size: 30, lr: 3.25e-04
2022-05-05 16:06:03,413 INFO [train.py:715] (4/8) Epoch 6, batch 27250, loss[loss=0.1644, simple_loss=0.2329, pruned_loss=0.04795, over 4829.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2187, pruned_loss=0.03815, over 972159.24 frames.], batch size: 30, lr: 3.25e-04
2022-05-05 16:06:43,063 INFO [train.py:715] (4/8) Epoch 6, batch 27300, loss[loss=0.1439, simple_loss=0.2167, pruned_loss=0.03557, over 4783.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2186, pruned_loss=0.03825, over 971867.98 frames.], batch size: 18, lr: 3.25e-04
2022-05-05 16:07:22,057 INFO [train.py:715] (4/8) Epoch 6, batch 27350, loss[loss=0.1628, simple_loss=0.2308, pruned_loss=0.04741, over 4982.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2183, pruned_loss=0.03805, over 972594.60 frames.], batch size: 27, lr: 3.25e-04
2022-05-05 16:08:01,169 INFO [train.py:715] (4/8) Epoch 6, batch 27400, loss[loss=0.1691, simple_loss=0.2437, pruned_loss=0.0473, over 4776.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2187, pruned_loss=0.03805, over 972270.95 frames.], batch size: 17, lr: 3.25e-04
2022-05-05 16:08:39,770 INFO [train.py:715] (4/8) Epoch 6, batch 27450, loss[loss=0.1401, simple_loss=0.2096, pruned_loss=0.03534, over 4745.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2184, pruned_loss=0.03773, over 972730.48 frames.], batch size: 16, lr: 3.25e-04
2022-05-05 16:09:18,812 INFO [train.py:715] (4/8) Epoch 6, batch 27500, loss[loss=0.1854, simple_loss=0.2644, pruned_loss=0.05326, over 4826.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03742, over 972866.56 frames.], batch size: 15, lr: 3.25e-04
2022-05-05 16:09:58,189 INFO [train.py:715] (4/8) Epoch 6, batch 27550, loss[loss=0.1322, simple_loss=0.1997, pruned_loss=0.03239, over 4877.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2194, pruned_loss=0.03777, over 973613.21 frames.], batch size: 16, lr: 3.25e-04
2022-05-05 16:10:36,912 INFO [train.py:715] (4/8) Epoch 6, batch 27600, loss[loss=0.1448, simple_loss=0.229, pruned_loss=0.03024, over 4775.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03767, over 973221.91 frames.], batch size: 17, lr: 3.25e-04
2022-05-05 16:11:15,425 INFO [train.py:715] (4/8) Epoch 6, batch 27650, loss[loss=0.1679, simple_loss=0.2403, pruned_loss=0.04781, over 4865.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2194, pruned_loss=0.03815, over 973026.85 frames.], batch size: 20, lr: 3.25e-04
2022-05-05 16:11:54,438 INFO [train.py:715] (4/8) Epoch 6, batch 27700, loss[loss=0.168, simple_loss=0.2459, pruned_loss=0.04506, over 4907.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2197, pruned_loss=0.03826, over 972811.32 frames.], batch size: 18, lr: 3.25e-04
2022-05-05 16:12:32,979 INFO [train.py:715] (4/8) Epoch 6, batch 27750, loss[loss=0.1293, simple_loss=0.2035, pruned_loss=0.0276, over 4815.00 frames.], tot_loss[loss=0.1476, simple_loss=0.219, pruned_loss=0.03805, over 972693.47 frames.], batch size: 27, lr: 3.25e-04
2022-05-05 16:13:12,188 INFO [train.py:715] (4/8) Epoch 6, batch 27800, loss[loss=0.1374, simple_loss=0.2112, pruned_loss=0.03177, over 4872.00 frames.], tot_loss[loss=0.1484, simple_loss=0.22, pruned_loss=0.03838, over 972174.42 frames.], batch size: 38, lr: 3.25e-04
2022-05-05 16:13:51,230 INFO [train.py:715] (4/8) Epoch 6, batch 27850, loss[loss=0.1776, simple_loss=0.2442, pruned_loss=0.05546, over 4797.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2192, pruned_loss=0.03798, over 971708.64 frames.], batch size: 21, lr: 3.25e-04
2022-05-05 16:14:30,896 INFO [train.py:715] (4/8) Epoch 6, batch 27900, loss[loss=0.1444, simple_loss=0.2255, pruned_loss=0.03167, over 4862.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2195, pruned_loss=0.03843, over 972643.83 frames.], batch size: 16, lr: 3.25e-04
2022-05-05 16:15:09,372 INFO [train.py:715] (4/8) Epoch 6, batch 27950, loss[loss=0.1916, simple_loss=0.2546, pruned_loss=0.06432, over 4817.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2194, pruned_loss=0.03868, over 972316.21 frames.], batch size: 15, lr: 3.25e-04
2022-05-05 16:15:48,253 INFO [train.py:715] (4/8) Epoch 6, batch 28000, loss[loss=0.1452, simple_loss=0.2084, pruned_loss=0.04104, over 4915.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2194, pruned_loss=0.03876, over 973117.59 frames.], batch size: 18, lr: 3.25e-04
2022-05-05 16:16:27,386 INFO [train.py:715] (4/8) Epoch 6, batch 28050, loss[loss=0.1163, simple_loss=0.1858, pruned_loss=0.02347, over 4818.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2187, pruned_loss=0.03835, over 973578.49 frames.], batch size: 12, lr: 3.25e-04
2022-05-05 16:17:06,023 INFO [train.py:715] (4/8) Epoch 6, batch 28100, loss[loss=0.1337, simple_loss=0.2147, pruned_loss=0.02637, over 4700.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2199, pruned_loss=0.03899, over 973616.99 frames.], batch size: 15, lr: 3.25e-04
2022-05-05 16:17:44,943 INFO [train.py:715] (4/8) Epoch 6, batch 28150, loss[loss=0.1289, simple_loss=0.2018, pruned_loss=0.02802, over 4882.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2191, pruned_loss=0.03866, over 973113.28 frames.], batch size: 22, lr: 3.24e-04
2022-05-05 16:18:24,089 INFO [train.py:715] (4/8) Epoch 6, batch 28200, loss[loss=0.1724, simple_loss=0.2415, pruned_loss=0.05168, over 4748.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2193, pruned_loss=0.03848, over 973169.09 frames.], batch size: 16, lr: 3.24e-04
2022-05-05 16:19:03,412 INFO [train.py:715] (4/8) Epoch 6, batch 28250, loss[loss=0.1922, simple_loss=0.2666, pruned_loss=0.05888, over 4782.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2194, pruned_loss=0.03818, over 972937.44 frames.], batch size: 17, lr: 3.24e-04
2022-05-05 16:19:41,791 INFO [train.py:715] (4/8) Epoch 6, batch 28300, loss[loss=0.1684, simple_loss=0.2377, pruned_loss=0.04951, over 4705.00 frames.], tot_loss[loss=0.1484, simple_loss=0.22, pruned_loss=0.0384, over 972750.06 frames.], batch size: 15, lr: 3.24e-04
2022-05-05 16:20:20,025 INFO [train.py:715] (4/8) Epoch 6, batch 28350, loss[loss=0.1668, simple_loss=0.2309, pruned_loss=0.05134, over 4955.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2197, pruned_loss=0.03873, over 973206.75 frames.], batch size: 35, lr: 3.24e-04
2022-05-05 16:20:59,873 INFO [train.py:715] (4/8) Epoch 6, batch 28400, loss[loss=0.1317, simple_loss=0.2046, pruned_loss=0.02938, over 4944.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2204, pruned_loss=0.03908, over 973540.93 frames.], batch size: 21, lr: 3.24e-04
2022-05-05 16:21:38,683 INFO [train.py:715] (4/8) Epoch 6, batch 28450, loss[loss=0.1674, simple_loss=0.245, pruned_loss=0.04486, over 4756.00 frames.], tot_loss[loss=0.1488, simple_loss=0.22, pruned_loss=0.03882, over 973297.69 frames.], batch size: 16, lr: 3.24e-04
2022-05-05 16:22:17,504 INFO [train.py:715] (4/8) Epoch 6, batch 28500, loss[loss=0.1395, simple_loss=0.2112, pruned_loss=0.03389, over 4859.00 frames.], tot_loss[loss=0.148, simple_loss=0.2192, pruned_loss=0.03842, over 973187.59 frames.], batch size: 20, lr: 3.24e-04
2022-05-05 16:22:56,650 INFO [train.py:715] (4/8) Epoch 6, batch 28550, loss[loss=0.1562, simple_loss=0.2273, pruned_loss=0.0425, over 4812.00 frames.], tot_loss[loss=0.148, simple_loss=0.219, pruned_loss=0.03851, over 973165.06 frames.], batch size: 25, lr: 3.24e-04
2022-05-05 16:23:36,091 INFO [train.py:715] (4/8) Epoch 6, batch 28600, loss[loss=0.1301, simple_loss=0.199, pruned_loss=0.03063, over 4757.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2204, pruned_loss=0.039, over 973321.99 frames.], batch size: 12, lr: 3.24e-04
2022-05-05 16:24:14,190 INFO [train.py:715] (4/8) Epoch 6, batch 28650, loss[loss=0.1208, simple_loss=0.1875, pruned_loss=0.02707, over 4771.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2195, pruned_loss=0.03872, over 972904.19 frames.], batch size: 18, lr: 3.24e-04
2022-05-05 16:24:52,989 INFO [train.py:715] (4/8) Epoch 6, batch 28700, loss[loss=0.1592, simple_loss=0.2368, pruned_loss=0.04078, over 4757.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2188, pruned_loss=0.03831, over 972117.75 frames.], batch size: 19, lr: 3.24e-04
2022-05-05 16:25:32,176 INFO [train.py:715] (4/8) Epoch 6, batch 28750, loss[loss=0.1593, simple_loss=0.2218, pruned_loss=0.04844, over 4843.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2186, pruned_loss=0.0382, over 972637.18 frames.], batch size: 12, lr: 3.24e-04
2022-05-05 16:26:10,897 INFO [train.py:715] (4/8) Epoch 6, batch 28800, loss[loss=0.1687, simple_loss=0.2423, pruned_loss=0.04753, over 4963.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2194, pruned_loss=0.03806, over 972439.71 frames.], batch size: 24, lr: 3.24e-04
2022-05-05 16:26:49,768 INFO [train.py:715] (4/8) Epoch 6, batch 28850, loss[loss=0.1733, simple_loss=0.2329, pruned_loss=0.05684, over 4771.00 frames.], tot_loss[loss=0.1486, simple_loss=0.22, pruned_loss=0.0386, over 972247.31 frames.], batch size: 14, lr: 3.24e-04
2022-05-05 16:27:28,068 INFO [train.py:715] (4/8) Epoch 6, batch 28900, loss[loss=0.1628, simple_loss=0.2386, pruned_loss=0.04355, over 4986.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2201, pruned_loss=0.03856, over 972251.79 frames.], batch size: 15, lr: 3.24e-04
2022-05-05 16:28:07,515 INFO [train.py:715] (4/8) Epoch 6, batch 28950, loss[loss=0.1437, simple_loss=0.2053, pruned_loss=0.04106, over 4978.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2197, pruned_loss=0.03848, over 972020.53 frames.], batch size: 14, lr: 3.24e-04
2022-05-05 16:28:45,749 INFO [train.py:715] (4/8) Epoch 6, batch 29000, loss[loss=0.155, simple_loss=0.2294, pruned_loss=0.04029, over 4872.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2197, pruned_loss=0.03836, over 971997.32 frames.], batch size: 22, lr: 3.24e-04
2022-05-05 16:29:23,907 INFO [train.py:715] (4/8) Epoch 6, batch 29050, loss[loss=0.1428, simple_loss=0.2156, pruned_loss=0.03504, over 4829.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2204, pruned_loss=0.03871, over 971274.11 frames.], batch size: 27, lr: 3.24e-04
2022-05-05 16:30:02,945 INFO [train.py:715] (4/8) Epoch 6, batch 29100, loss[loss=0.1427, simple_loss=0.2251, pruned_loss=0.03011, over 4968.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2197, pruned_loss=0.0383, over 972207.99 frames.], batch size: 15, lr: 3.24e-04
2022-05-05 16:30:41,838 INFO [train.py:715] (4/8) Epoch 6, batch 29150, loss[loss=0.1155, simple_loss=0.187, pruned_loss=0.02194, over 4773.00 frames.], tot_loss[loss=0.1486, simple_loss=0.2202, pruned_loss=0.03851, over 971567.49 frames.], batch size: 17, lr: 3.24e-04
2022-05-05 16:31:20,686 INFO [train.py:715] (4/8) Epoch 6, batch 29200, loss[loss=0.1231, simple_loss=0.1932, pruned_loss=0.02652, over 4812.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2205, pruned_loss=0.03856, over 972005.38 frames.], batch size: 13, lr: 3.24e-04
2022-05-05 16:31:59,899 INFO [train.py:715] (4/8) Epoch 6, batch 29250, loss[loss=0.1422, simple_loss=0.2077, pruned_loss=0.03834, over 4947.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2197, pruned_loss=0.03823, over 972569.29 frames.], batch size: 35, lr: 3.24e-04
2022-05-05 16:32:39,922 INFO [train.py:715] (4/8) Epoch 6, batch 29300, loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03232, over 4867.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2192, pruned_loss=0.03792, over 972381.31 frames.], batch size: 13, lr: 3.24e-04
2022-05-05 16:33:18,207 INFO [train.py:715] (4/8) Epoch 6, batch 29350, loss[loss=0.1813, simple_loss=0.2457, pruned_loss=0.05848, over 4844.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2197, pruned_loss=0.03838, over 971847.51 frames.], batch size: 32, lr: 3.24e-04
2022-05-05 16:33:57,192 INFO [train.py:715] (4/8) Epoch 6, batch 29400, loss[loss=0.1683, simple_loss=0.2488, pruned_loss=0.0439, over 4900.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2193, pruned_loss=0.03863, over 970689.05 frames.], batch size: 19, lr: 3.24e-04
2022-05-05 16:34:36,596 INFO [train.py:715] (4/8) Epoch 6, batch 29450, loss[loss=0.1186, simple_loss=0.1867, pruned_loss=0.02528, over 4757.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2183, pruned_loss=0.03799, over 971413.21 frames.], batch size: 19, lr: 3.24e-04
2022-05-05 16:35:15,803 INFO [train.py:715] (4/8) Epoch 6, batch 29500, loss[loss=0.1315, simple_loss=0.2023, pruned_loss=0.03032, over 4789.00 frames.], tot_loss[loss=0.147, simple_loss=0.2179, pruned_loss=0.03803, over 972015.43 frames.], batch size: 24, lr: 3.24e-04
2022-05-05 16:35:53,792 INFO [train.py:715] (4/8) Epoch 6, batch 29550, loss[loss=0.1795, simple_loss=0.2409, pruned_loss=0.05907, over 4889.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2177, pruned_loss=0.03805, over 972204.24 frames.], batch size: 32, lr: 3.24e-04
2022-05-05 16:36:33,157 INFO [train.py:715] (4/8) Epoch 6, batch 29600, loss[loss=0.1194, simple_loss=0.1992, pruned_loss=0.0198, over 4944.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2183, pruned_loss=0.03809, over 973000.04 frames.], batch size: 21, lr: 3.24e-04
2022-05-05 16:37:12,531 INFO [train.py:715] (4/8) Epoch 6, batch 29650, loss[loss=0.1731, simple_loss=0.2483, pruned_loss=0.04894, over 4927.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2173, pruned_loss=0.0375, over 973748.42 frames.], batch size: 23, lr: 3.23e-04
2022-05-05 16:37:51,062 INFO [train.py:715] (4/8) Epoch 6, batch 29700, loss[loss=0.1287, simple_loss=0.2014, pruned_loss=0.02803, over 4976.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2182, pruned_loss=0.03825, over 973098.46 frames.], batch size: 28, lr: 3.23e-04
2022-05-05 16:38:29,763 INFO [train.py:715] (4/8) Epoch 6, batch 29750, loss[loss=0.1538, simple_loss=0.2356, pruned_loss=0.03595, over 4926.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2182, pruned_loss=0.03836, over 973249.00 frames.], batch size: 17, lr: 3.23e-04
2022-05-05 16:39:08,776 INFO [train.py:715] (4/8) Epoch 6, batch 29800, loss[loss=0.1584, simple_loss=0.2183, pruned_loss=0.04921, over 4940.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2176, pruned_loss=0.03784, over 972358.19 frames.], batch size: 35, lr: 3.23e-04
2022-05-05 16:39:48,203 INFO [train.py:715] (4/8) Epoch 6, batch 29850, loss[loss=0.118, simple_loss=0.1893, pruned_loss=0.02333, over 4863.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2179, pruned_loss=0.03797, over 972902.11 frames.], batch size: 20, lr: 3.23e-04
2022-05-05 16:40:26,713 INFO [train.py:715] (4/8) Epoch 6, batch 29900, loss[loss=0.1472, simple_loss=0.2083, pruned_loss=0.04303, over 4988.00 frames.], tot_loss[loss=0.147, simple_loss=0.2181, pruned_loss=0.03796, over 973086.43 frames.], batch size: 14, lr: 3.23e-04
2022-05-05 16:41:05,701 INFO [train.py:715] (4/8) Epoch 6, batch 29950, loss[loss=0.1715, simple_loss=0.2454, pruned_loss=0.04877, over 4920.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2176, pruned_loss=0.03776, over 973083.37 frames.], batch size: 18, lr: 3.23e-04
2022-05-05 16:41:45,054 INFO [train.py:715] (4/8) Epoch 6, batch 30000, loss[loss=0.1618, simple_loss=0.2428, pruned_loss=0.04034, over 4913.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2186, pruned_loss=0.03802, over 972789.55 frames.], batch size: 19, lr: 3.23e-04
2022-05-05 16:41:45,055 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 16:41:54,714 INFO [train.py:742] (4/8) Epoch 6, validation: loss=0.1088, simple_loss=0.1938, pruned_loss=0.0119, over 914524.00 frames.
2022-05-05 16:42:34,425 INFO [train.py:715] (4/8) Epoch 6, batch 30050, loss[loss=0.1639, simple_loss=0.227, pruned_loss=0.05045, over 4646.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2183, pruned_loss=0.03812, over 971731.18 frames.], batch size: 13, lr: 3.23e-04
2022-05-05 16:43:12,813 INFO [train.py:715] (4/8) Epoch 6, batch 30100, loss[loss=0.1148, simple_loss=0.1895, pruned_loss=0.02001, over 4841.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2193, pruned_loss=0.03882, over 971461.44 frames.], batch size: 13, lr: 3.23e-04
2022-05-05 16:43:51,559 INFO [train.py:715] (4/8) Epoch 6, batch 30150, loss[loss=0.1539, simple_loss=0.219, pruned_loss=0.04437, over 4861.00 frames.], tot_loss[loss=0.149, simple_loss=0.2194, pruned_loss=0.03933, over 971997.92 frames.], batch size: 22, lr: 3.23e-04
2022-05-05 16:44:30,968 INFO [train.py:715] (4/8) Epoch 6, batch 30200, loss[loss=0.1769, simple_loss=0.2457, pruned_loss=0.05403, over 4925.00 frames.], tot_loss[loss=0.149, simple_loss=0.2197, pruned_loss=0.03914, over 972596.18 frames.], batch size: 39, lr: 3.23e-04
2022-05-05 16:45:10,342 INFO [train.py:715] (4/8) Epoch 6, batch 30250, loss[loss=0.1373, simple_loss=0.2092, pruned_loss=0.03272, over 4940.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2198, pruned_loss=0.03903, over 973314.38 frames.], batch size: 21, lr: 3.23e-04
2022-05-05 16:45:48,511 INFO [train.py:715] (4/8) Epoch 6, batch 30300, loss[loss=0.1526, simple_loss=0.2237, pruned_loss=0.04073, over 4792.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2195, pruned_loss=0.03912, over 972764.91 frames.], batch size: 24, lr: 3.23e-04
2022-05-05 16:46:27,513 INFO [train.py:715] (4/8) Epoch 6, batch 30350, loss[loss=0.1493, simple_loss=0.2259, pruned_loss=0.03641, over 4882.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2188, pruned_loss=0.03868, over 972925.21 frames.], batch size: 22, lr: 3.23e-04
2022-05-05 16:47:06,587 INFO [train.py:715] (4/8) Epoch 6, batch 30400, loss[loss=0.1572, simple_loss=0.2197, pruned_loss=0.04731, over 4694.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2185, pruned_loss=0.03844, over 971834.32 frames.], batch size: 15, lr: 3.23e-04
2022-05-05 16:47:45,263 INFO [train.py:715] (4/8) Epoch 6, batch 30450, loss[loss=0.1341, simple_loss=0.2095, pruned_loss=0.02932, over 4897.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2185, pruned_loss=0.03806, over 972425.18 frames.], batch size: 19, lr: 3.23e-04
2022-05-05 16:48:23,948 INFO [train.py:715] (4/8) Epoch 6, batch 30500, loss[loss=0.1769, simple_loss=0.2284, pruned_loss=0.06271, over 4695.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2184, pruned_loss=0.03838, over 972430.19 frames.], batch size: 15, lr: 3.23e-04
2022-05-05 16:49:02,695 INFO [train.py:715] (4/8) Epoch 6, batch 30550, loss[loss=0.1349, simple_loss=0.2053, pruned_loss=0.03224, over 4733.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2184, pruned_loss=0.03787, over 973228.74 frames.], batch size: 12, lr: 3.23e-04
2022-05-05 16:49:41,852 INFO [train.py:715] (4/8) Epoch 6, batch 30600, loss[loss=0.1783, simple_loss=0.242, pruned_loss=0.05731, over 4749.00 frames.], tot_loss[loss=0.1476, simple_loss=0.219, pruned_loss=0.03811, over 973088.50 frames.], batch size: 14, lr: 3.23e-04
2022-05-05 16:50:20,374 INFO [train.py:715] (4/8) Epoch 6, batch 30650, loss[loss=0.1914, simple_loss=0.2677, pruned_loss=0.0575, over 4820.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2191, pruned_loss=0.03795, over 972067.84 frames.], batch size: 25, lr: 3.23e-04
2022-05-05 16:50:59,232 INFO [train.py:715] (4/8) Epoch 6, batch 30700, loss[loss=0.1778, simple_loss=0.2473, pruned_loss=0.05409, over 4758.00 frames.], tot_loss[loss=0.148, simple_loss=0.2198, pruned_loss=0.03814, over 972191.89 frames.], batch size: 16, lr: 3.23e-04
2022-05-05 16:51:38,190 INFO [train.py:715] (4/8) Epoch 6, batch 30750, loss[loss=0.1593, simple_loss=0.2355, pruned_loss=0.04153, over 4954.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2196, pruned_loss=0.03808, over 972823.38 frames.], batch size: 24, lr: 3.23e-04
2022-05-05 16:52:17,035 INFO [train.py:715] (4/8) Epoch 6, batch 30800, loss[loss=0.1525, simple_loss=0.2212, pruned_loss=0.04186, over 4801.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2189, pruned_loss=0.03813, over 973349.27 frames.], batch size: 24, lr: 3.23e-04
2022-05-05 16:52:55,431 INFO [train.py:715] (4/8) Epoch 6, batch 30850, loss[loss=0.1384, simple_loss=0.2191, pruned_loss=0.02881, over 4900.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2185, pruned_loss=0.0378, over 973992.79 frames.], batch size: 19, lr: 3.23e-04
2022-05-05 16:53:34,166 INFO [train.py:715] (4/8) Epoch 6, batch 30900, loss[loss=0.1504, simple_loss=0.2171, pruned_loss=0.0418, over 4979.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2192, pruned_loss=0.03819, over 973634.20 frames.], batch size: 25, lr: 3.23e-04
2022-05-05 16:54:13,772 INFO [train.py:715] (4/8) Epoch 6, batch 30950, loss[loss=0.1609, simple_loss=0.2383, pruned_loss=0.04178, over 4700.00 frames.], tot_loss[loss=0.149, simple_loss=0.2204, pruned_loss=0.03876, over 973768.03 frames.], batch size: 15, lr: 3.23e-04
2022-05-05 16:54:51,910 INFO [train.py:715] (4/8) Epoch 6, batch 31000, loss[loss=0.2069, simple_loss=0.2646, pruned_loss=0.07458, over 4905.00 frames.], tot_loss[loss=0.1504, simple_loss=0.2216, pruned_loss=0.03965, over 973667.01 frames.], batch size: 18, lr: 3.23e-04
2022-05-05 16:55:30,913 INFO [train.py:715] (4/8) Epoch 6, batch 31050, loss[loss=0.1466, simple_loss=0.2302, pruned_loss=0.03154, over 4831.00 frames.], tot_loss[loss=0.1508, simple_loss=0.2221, pruned_loss=0.03974, over 973707.08 frames.], batch size: 27, lr: 3.23e-04
2022-05-05 16:56:10,159 INFO [train.py:715] (4/8) Epoch 6, batch 31100, loss[loss=0.1572, simple_loss=0.222, pruned_loss=0.04617, over 4976.00 frames.], tot_loss[loss=0.15, simple_loss=0.2216, pruned_loss=0.03921, over 972823.05 frames.], batch size: 14, lr: 3.22e-04
2022-05-05 16:56:51,383 INFO [train.py:715] (4/8) Epoch 6, batch 31150, loss[loss=0.1133, simple_loss=0.1839, pruned_loss=0.02137, over 4871.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2214, pruned_loss=0.03958, over 973039.27 frames.], batch size: 32, lr: 3.22e-04
2022-05-05 16:57:30,157 INFO [train.py:715] (4/8) Epoch 6, batch 31200, loss[loss=0.1347, simple_loss=0.2142, pruned_loss=0.02765, over 4870.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2203, pruned_loss=0.03928, over 972211.59 frames.], batch size: 38, lr: 3.22e-04
2022-05-05 16:58:09,407 INFO [train.py:715] (4/8) Epoch 6, batch 31250, loss[loss=0.1476, simple_loss=0.221, pruned_loss=0.03707, over 4919.00 frames.], tot_loss[loss=0.1503, simple_loss=0.2215, pruned_loss=0.03949, over 972290.85 frames.], batch size: 29, lr: 3.22e-04
2022-05-05 16:58:48,262 INFO [train.py:715] (4/8) Epoch 6, batch 31300, loss[loss=0.1561, simple_loss=0.2351, pruned_loss=0.03851, over 4751.00 frames.], tot_loss[loss=0.1496, simple_loss=0.221, pruned_loss=0.03912, over 972159.14 frames.], batch size: 16, lr: 3.22e-04
2022-05-05 16:59:27,128 INFO [train.py:715] (4/8) Epoch 6, batch 31350, loss[loss=0.1488, simple_loss=0.2191, pruned_loss=0.0393, over 4977.00 frames.], tot_loss[loss=0.1493, simple_loss=0.2204, pruned_loss=0.03912, over 972107.08 frames.], batch size: 14, lr: 3.22e-04
2022-05-05 17:00:06,383 INFO [train.py:715] (4/8) Epoch 6, batch 31400, loss[loss=0.1386, simple_loss=0.2074, pruned_loss=0.03492, over 4900.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2204, pruned_loss=0.03918, over 972282.51 frames.], batch size: 22, lr: 3.22e-04
2022-05-05 17:00:45,703 INFO [train.py:715] (4/8) Epoch 6, batch 31450, loss[loss=0.1097, simple_loss=0.1925, pruned_loss=0.0135, over 4746.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2196, pruned_loss=0.03865, over 972851.24 frames.], batch size: 19, lr: 3.22e-04
2022-05-05 17:01:23,998 INFO [train.py:715] (4/8) Epoch 6, batch 31500, loss[loss=0.175, simple_loss=0.243, pruned_loss=0.05347, over 4870.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2197, pruned_loss=0.03848, over 973783.79 frames.], batch size: 16, lr: 3.22e-04
2022-05-05 17:02:02,411 INFO [train.py:715] (4/8) Epoch 6, batch 31550, loss[loss=0.1576, simple_loss=0.2179, pruned_loss=0.04864, over 4856.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2194, pruned_loss=0.03855, over 974609.09 frames.], batch size: 38, lr: 3.22e-04
2022-05-05 17:02:41,957 INFO [train.py:715] (4/8) Epoch 6, batch 31600, loss[loss=0.1759, simple_loss=0.2431, pruned_loss=0.05439, over 4935.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2198, pruned_loss=0.03861, over 972916.12 frames.], batch size: 23, lr: 3.22e-04
2022-05-05 17:03:21,197 INFO [train.py:715] (4/8) Epoch 6, batch 31650, loss[loss=0.2114, simple_loss=0.2706, pruned_loss=0.0761, over 4868.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2205, pruned_loss=0.03939, over 973202.25 frames.], batch size: 16, lr: 3.22e-04
2022-05-05 17:03:59,730 INFO [train.py:715] (4/8) Epoch 6, batch 31700, loss[loss=0.1286, simple_loss=0.1979, pruned_loss=0.02961, over 4783.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2202, pruned_loss=0.03886, over 972814.46 frames.], batch size: 17, lr: 3.22e-04
2022-05-05 17:04:38,252 INFO [train.py:715] (4/8) Epoch 6, batch 31750, loss[loss=0.1367, simple_loss=0.2043, pruned_loss=0.03452, over 4847.00 frames.], tot_loss[loss=0.1497, simple_loss=0.2208, pruned_loss=0.03926, over 972811.48 frames.], batch size: 12, lr: 3.22e-04
2022-05-05 17:05:17,757 INFO [train.py:715] (4/8) Epoch 6, batch 31800, loss[loss=0.1378, simple_loss=0.2188, pruned_loss=0.02839, over 4779.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2209, pruned_loss=0.03913, over 972865.16 frames.], batch size: 14, lr: 3.22e-04
2022-05-05 17:05:56,238 INFO [train.py:715] (4/8) Epoch 6, batch 31850, loss[loss=0.1456, simple_loss=0.2187, pruned_loss=0.03621, over 4930.00 frames.], tot_loss[loss=0.149, simple_loss=0.2207, pruned_loss=0.03869, over 972682.69 frames.], batch size: 29, lr: 3.22e-04
2022-05-05 17:06:34,778 INFO [train.py:715] (4/8) Epoch 6, batch 31900, loss[loss=0.1503, simple_loss=0.2266, pruned_loss=0.03704, over 4787.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2199, pruned_loss=0.03797, over 972518.28 frames.], batch size: 17, lr: 3.22e-04
2022-05-05 17:07:13,869 INFO [train.py:715] (4/8) Epoch 6, batch 31950, loss[loss=0.1752, simple_loss=0.2448, pruned_loss=0.05281, over 4824.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2212, pruned_loss=0.0389, over 973281.80 frames.], batch size: 25, lr: 3.22e-04
2022-05-05 17:07:52,504 INFO [train.py:715] (4/8) Epoch 6, batch 32000, loss[loss=0.1715, simple_loss=0.246, pruned_loss=0.04848, over 4860.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2202, pruned_loss=0.0384, over 972767.06 frames.], batch size: 32, lr: 3.22e-04
2022-05-05 17:08:31,940 INFO [train.py:715] (4/8) Epoch 6, batch 32050, loss[loss=0.1277, simple_loss=0.1954, pruned_loss=0.03004, over 4945.00 frames.], tot_loss[loss=0.148, simple_loss=0.2197, pruned_loss=0.03819, over 972449.08 frames.], batch size: 29, lr: 3.22e-04
2022-05-05 17:09:11,479 INFO [train.py:715] (4/8) Epoch 6, batch 32100, loss[loss=0.1347, simple_loss=0.2006, pruned_loss=0.0344, over 4765.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2191, pruned_loss=0.03759, over 972036.73 frames.], batch size: 12, lr: 3.22e-04
2022-05-05 17:09:50,453 INFO [train.py:715] (4/8) Epoch 6, batch 32150, loss[loss=0.1385, simple_loss=0.2101, pruned_loss=0.03348, over 4785.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2176, pruned_loss=0.03742, over 971307.83 frames.], batch size: 14, lr: 3.22e-04
2022-05-05 17:10:28,949 INFO [train.py:715] (4/8) Epoch 6, batch 32200, loss[loss=0.1671, simple_loss=0.2408, pruned_loss=0.04667, over 4946.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2185, pruned_loss=0.03742, over 971141.78 frames.], batch size: 23, lr: 3.22e-04
2022-05-05 17:11:08,024 INFO [train.py:715] (4/8) Epoch 6, batch 32250, loss[loss=0.1455, simple_loss=0.2117, pruned_loss=0.03961, over 4807.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03749, over 972048.23 frames.], batch size: 15, lr: 3.22e-04
2022-05-05 17:11:46,853 INFO [train.py:715] (4/8) Epoch 6, batch 32300, loss[loss=0.1639, simple_loss=0.2326, pruned_loss=0.04761, over 4774.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2174, pruned_loss=0.03681, over 971767.91 frames.], batch size: 17, lr: 3.22e-04
2022-05-05 17:12:26,141 INFO [train.py:715] (4/8) Epoch 6, batch 32350, loss[loss=0.146, simple_loss=0.2204, pruned_loss=0.0358, over 4757.00 frames.], tot_loss[loss=0.146, simple_loss=0.2176, pruned_loss=0.03722, over 971439.73 frames.], batch size: 19, lr: 3.22e-04
2022-05-05 17:13:04,503 INFO [train.py:715] (4/8) Epoch 6, batch 32400, loss[loss=0.1256, simple_loss=0.1928, pruned_loss=0.02925, over 4849.00 frames.], tot_loss[loss=0.1461, simple_loss=0.218, pruned_loss=0.03713, over 971824.92 frames.], batch size: 30, lr: 3.22e-04
2022-05-05 17:13:43,922 INFO [train.py:715] (4/8) Epoch 6, batch 32450, loss[loss=0.1519, simple_loss=0.2275, pruned_loss=0.03813, over 4819.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2185, pruned_loss=0.03786, over 971772.96 frames.], batch size: 15, lr: 3.22e-04
2022-05-05 17:14:23,268 INFO [train.py:715] (4/8) Epoch 6, batch 32500, loss[loss=0.1292, simple_loss=0.207, pruned_loss=0.02567, over 4944.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03758, over 971683.97 frames.], batch size: 21, lr: 3.22e-04
2022-05-05 17:15:01,984 INFO [train.py:715] (4/8) Epoch 6, batch 32550, loss[loss=0.1241, simple_loss=0.1951, pruned_loss=0.02657, over 4756.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2186, pruned_loss=0.0379, over 972108.75 frames.], batch size: 18, lr: 3.22e-04
2022-05-05 17:15:40,776 INFO [train.py:715] (4/8) Epoch 6, batch 32600, loss[loss=0.135, simple_loss=0.2069, pruned_loss=0.03156, over 4962.00 frames.], tot_loss[loss=0.1466, simple_loss=0.218, pruned_loss=0.03755, over 971112.84 frames.], batch size: 39, lr: 3.21e-04
2022-05-05 17:16:19,203 INFO [train.py:715] (4/8) Epoch 6, batch 32650, loss[loss=0.1491, simple_loss=0.2289, pruned_loss=0.03463, over 4974.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2181, pruned_loss=0.03766, over 971465.90 frames.], batch size: 28, lr: 3.21e-04
2022-05-05 17:16:57,839 INFO [train.py:715] (4/8) Epoch 6, batch 32700, loss[loss=0.1523, simple_loss=0.2212, pruned_loss=0.04168, over 4935.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2184, pruned_loss=0.03813, over 971643.16 frames.], batch size: 18, lr: 3.21e-04
2022-05-05 17:17:35,889 INFO [train.py:715] (4/8) Epoch 6, batch 32750, loss[loss=0.1292, simple_loss=0.2028, pruned_loss=0.02778, over 4868.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2182, pruned_loss=0.03817, over 971627.75 frames.], batch size: 38, lr: 3.21e-04
2022-05-05 17:18:14,605 INFO [train.py:715] (4/8) Epoch 6, batch 32800, loss[loss=0.1985, simple_loss=0.2572, pruned_loss=0.06991, over 4867.00 frames.], tot_loss[loss=0.147, simple_loss=0.2181, pruned_loss=0.03791, over 971421.20 frames.], batch size: 32, lr: 3.21e-04
2022-05-05 17:18:53,198 INFO [train.py:715] (4/8) Epoch 6, batch 32850, loss[loss=0.1615, simple_loss=0.2336, pruned_loss=0.04465, over 4757.00 frames.], tot_loss[loss=0.1456, simple_loss=0.217, pruned_loss=0.03713, over 971241.56 frames.], batch size: 16, lr: 3.21e-04
2022-05-05 17:19:31,603 INFO [train.py:715] (4/8) Epoch 6, batch 32900, loss[loss=0.1461, simple_loss=0.2184, pruned_loss=0.03686, over 4856.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2171, pruned_loss=0.037, over 971468.94 frames.], batch size: 32, lr: 3.21e-04
2022-05-05 17:20:09,698 INFO [train.py:715] (4/8) Epoch 6, batch 32950, loss[loss=0.1364, simple_loss=0.2115, pruned_loss=0.03062, over 4817.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.03706, over 971019.91 frames.], batch size: 15, lr: 3.21e-04
2022-05-05 17:20:48,507 INFO [train.py:715] (4/8) Epoch 6, batch 33000, loss[loss=0.1788, simple_loss=0.2402, pruned_loss=0.05873, over 4742.00 frames.], tot_loss[loss=0.1464, simple_loss=0.218, pruned_loss=0.03736, over 971342.40 frames.], batch size: 16, lr: 3.21e-04
2022-05-05 17:20:48,507 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 17:20:58,109 INFO [train.py:742] (4/8) Epoch 6, validation: loss=0.1087, simple_loss=0.1938, pruned_loss=0.01183, over 914524.00 frames.
2022-05-05 17:21:36,676 INFO [train.py:715] (4/8) Epoch 6, batch 33050, loss[loss=0.1337, simple_loss=0.2047, pruned_loss=0.03135, over 4804.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2176, pruned_loss=0.03701, over 971742.06 frames.], batch size: 21, lr: 3.21e-04
2022-05-05 17:22:15,262 INFO [train.py:715] (4/8) Epoch 6, batch 33100, loss[loss=0.1507, simple_loss=0.2232, pruned_loss=0.03913, over 4762.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2179, pruned_loss=0.03737, over 972340.73 frames.], batch size: 19, lr: 3.21e-04
2022-05-05 17:22:53,010 INFO [train.py:715] (4/8) Epoch 6, batch 33150, loss[loss=0.1446, simple_loss=0.2232, pruned_loss=0.03305, over 4762.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2181, pruned_loss=0.03784, over 971862.26 frames.], batch size: 19, lr: 3.21e-04
2022-05-05 17:23:31,899 INFO [train.py:715] (4/8) Epoch 6, batch 33200, loss[loss=0.1476, simple_loss=0.2152, pruned_loss=0.04005, over 4963.00 frames.], tot_loss[loss=0.147, simple_loss=0.2182, pruned_loss=0.03794, over 972051.14 frames.], batch size: 24, lr: 3.21e-04
2022-05-05 17:24:10,786 INFO [train.py:715] (4/8) Epoch 6, batch 33250, loss[loss=0.1862, simple_loss=0.2423, pruned_loss=0.06501, over 4863.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2191, pruned_loss=0.03827, over 972344.06 frames.], batch size: 32, lr: 3.21e-04
2022-05-05 17:24:49,863 INFO [train.py:715] (4/8) Epoch 6, batch 33300, loss[loss=0.144, simple_loss=0.2119, pruned_loss=0.03803, over 4874.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2191, pruned_loss=0.03855, over 972376.10 frames.], batch size: 16, lr: 3.21e-04
2022-05-05 17:25:28,469 INFO [train.py:715] (4/8) Epoch 6, batch 33350, loss[loss=0.1608, simple_loss=0.2329, pruned_loss=0.04433, over 4936.00 frames.], tot_loss[loss=0.1482, simple_loss=0.219, pruned_loss=0.03867, over 971986.64 frames.], batch size: 21, lr: 3.21e-04
2022-05-05 17:26:07,936 INFO [train.py:715] (4/8) Epoch 6, batch 33400, loss[loss=0.1524, simple_loss=0.2182, pruned_loss=0.04332, over 4773.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2192, pruned_loss=0.03834, over 971320.97 frames.], batch size: 12, lr: 3.21e-04
2022-05-05 17:26:47,018 INFO [train.py:715] (4/8) Epoch 6, batch 33450, loss[loss=0.1521, simple_loss=0.217, pruned_loss=0.04359, over 4941.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2186, pruned_loss=0.03828, over 970980.01 frames.], batch size: 35, lr: 3.21e-04
2022-05-05 17:27:25,291 INFO [train.py:715] (4/8) Epoch 6, batch 33500, loss[loss=0.1313, simple_loss=0.2077, pruned_loss=0.02748, over 4818.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2186, pruned_loss=0.03828, over 971008.22 frames.], batch size: 26, lr: 3.21e-04
2022-05-05 17:28:04,317 INFO [train.py:715] (4/8) Epoch 6, batch 33550, loss[loss=0.1262, simple_loss=0.2045, pruned_loss=0.02395, over 4895.00 frames.], tot_loss[loss=0.148, simple_loss=0.2191, pruned_loss=0.0384, over 971541.57 frames.], batch size: 19, lr: 3.21e-04
2022-05-05 17:28:43,724 INFO [train.py:715] (4/8) Epoch 6, batch 33600, loss[loss=0.1661, simple_loss=0.242, pruned_loss=0.0451, over 4859.00 frames.], tot_loss[loss=0.1476, simple_loss=0.219, pruned_loss=0.03809, over 972032.90 frames.], batch size: 34, lr: 3.21e-04
2022-05-05 17:29:22,677 INFO [train.py:715] (4/8) Epoch 6, batch 33650, loss[loss=0.1576, simple_loss=0.2279, pruned_loss=0.04364, over 4752.00 frames.], tot_loss[loss=0.1472, simple_loss=0.219, pruned_loss=0.03774, over 971816.96 frames.], batch size: 16, lr: 3.21e-04
2022-05-05 17:30:01,276 INFO [train.py:715] (4/8) Epoch 6, batch 33700, loss[loss=0.1762, simple_loss=0.2262, pruned_loss=0.06313, over 4961.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2185, pruned_loss=0.03765, over 972658.35 frames.], batch size: 14, lr: 3.21e-04
2022-05-05 17:30:39,886 INFO [train.py:715] (4/8) Epoch 6, batch 33750, loss[loss=0.1454, simple_loss=0.2063, pruned_loss=0.04227, over 4917.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2191, pruned_loss=0.03836, over 972077.06 frames.], batch size: 18, lr: 3.21e-04
2022-05-05 17:31:19,208 INFO [train.py:715] (4/8) Epoch 6, batch 33800, loss[loss=0.1308, simple_loss=0.2027, pruned_loss=0.02943, over 4988.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2193, pruned_loss=0.0384, over 971897.14 frames.], batch size: 14, lr: 3.21e-04
2022-05-05 17:31:58,019 INFO [train.py:715] (4/8) Epoch 6, batch 33850, loss[loss=0.148, simple_loss=0.2141, pruned_loss=0.04097, over 4868.00 frames.], tot_loss[loss=0.1485, simple_loss=0.2197, pruned_loss=0.03864, over 972922.51 frames.], batch size: 20, lr: 3.21e-04
2022-05-05 17:32:36,705 INFO [train.py:715] (4/8) Epoch 6, batch 33900, loss[loss=0.1412, simple_loss=0.2081, pruned_loss=0.0371, over 4791.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2195, pruned_loss=0.03845, over 972612.49 frames.], batch size: 17, lr: 3.21e-04
2022-05-05 17:33:16,049 INFO [train.py:715] (4/8) Epoch 6, batch 33950, loss[loss=0.1442, simple_loss=0.2095, pruned_loss=0.03947, over 4981.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2191, pruned_loss=0.0384, over 971575.21 frames.], batch size: 14, lr: 3.21e-04
2022-05-05 17:33:55,028 INFO [train.py:715] (4/8) Epoch 6, batch 34000, loss[loss=0.176, simple_loss=0.2401, pruned_loss=0.05592, over 4911.00 frames.], tot_loss[loss=0.1491, simple_loss=0.2202, pruned_loss=0.039, over 972638.84 frames.], batch size: 17, lr: 3.21e-04
2022-05-05 17:34:33,701 INFO [train.py:715] (4/8) Epoch 6, batch 34050, loss[loss=0.1654, simple_loss=0.2361, pruned_loss=0.04737, over 4973.00 frames.], tot_loss[loss=0.1488, simple_loss=0.2202, pruned_loss=0.03874, over 971983.92 frames.], batch size: 14, lr: 3.21e-04
2022-05-05 17:35:12,975 INFO [train.py:715] (4/8) Epoch 6, batch 34100, loss[loss=0.1241, simple_loss=0.1993, pruned_loss=0.0245, over 4990.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2199, pruned_loss=0.03877, over 971629.23 frames.], batch size: 14, lr: 3.20e-04
2022-05-05 17:35:51,934 INFO [train.py:715] (4/8) Epoch 6, batch 34150, loss[loss=0.16, simple_loss=0.2328, pruned_loss=0.04364, over 4785.00 frames.], tot_loss[loss=0.1488, simple_loss=0.22, pruned_loss=0.03874, over 971740.89 frames.], batch size: 17, lr: 3.20e-04
2022-05-05 17:36:30,536 INFO [train.py:715] (4/8) Epoch 6, batch 34200, loss[loss=0.115, simple_loss=0.1908, pruned_loss=0.01962, over 4873.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2194, pruned_loss=0.03807, over 972490.54 frames.], batch size: 16, lr: 3.20e-04
2022-05-05 17:37:09,177 INFO [train.py:715] (4/8) Epoch 6, batch 34250, loss[loss=0.1457, simple_loss=0.2206, pruned_loss=0.0354, over 4842.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2191, pruned_loss=0.03783, over 971926.83 frames.], batch size: 30, lr: 3.20e-04
2022-05-05 17:37:48,389 INFO [train.py:715] (4/8) Epoch 6, batch 34300, loss[loss=0.1605, simple_loss=0.2266, pruned_loss=0.04717, over 4899.00 frames.], tot_loss[loss=0.1484, simple_loss=0.2198, pruned_loss=0.0385, over 971505.43 frames.], batch size: 18, lr: 3.20e-04
2022-05-05 17:38:26,982 INFO [train.py:715] (4/8) Epoch 6, batch 34350, loss[loss=0.1239, simple_loss=0.2026, pruned_loss=0.02262, over 4863.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2204, pruned_loss=0.03843, over 971800.18 frames.], batch size: 22, lr: 3.20e-04
2022-05-05 17:39:05,618 INFO [train.py:715] (4/8) Epoch 6, batch 34400, loss[loss=0.1852, simple_loss=0.2582, pruned_loss=0.05608, over 4696.00 frames.], tot_loss[loss=0.149, simple_loss=0.2209, pruned_loss=0.0385, over 971306.23 frames.], batch size: 15, lr: 3.20e-04
2022-05-05 17:39:45,299 INFO [train.py:715] (4/8) Epoch 6, batch 34450, loss[loss=0.1496, simple_loss=0.2096, pruned_loss=0.0448, over 4936.00 frames.], tot_loss[loss=0.1496, simple_loss=0.2211, pruned_loss=0.03905, over 970729.85 frames.], batch size: 23, lr: 3.20e-04
2022-05-05 17:40:24,040 INFO [train.py:715] (4/8) Epoch 6, batch 34500, loss[loss=0.1581, simple_loss=0.2226, pruned_loss=0.0468, over 4977.00 frames.], tot_loss[loss=0.1495, simple_loss=0.2211, pruned_loss=0.039, over 971231.32 frames.], batch size: 25, lr: 3.20e-04
2022-05-05 17:41:02,891 INFO [train.py:715] (4/8) Epoch 6, batch 34550, loss[loss=0.1572, simple_loss=0.2299, pruned_loss=0.04221, over 4888.00 frames.], tot_loss[loss=0.1494, simple_loss=0.2209, pruned_loss=0.03892, over 970853.71 frames.], batch size: 22, lr: 3.20e-04
2022-05-05 17:41:41,799 INFO [train.py:715] (4/8) Epoch 6, batch 34600, loss[loss=0.1317, simple_loss=0.2028, pruned_loss=0.03028, over 4704.00 frames.], tot_loss[loss=0.148, simple_loss=0.2195, pruned_loss=0.03828, over 970580.00 frames.], batch size: 15, lr: 3.20e-04
2022-05-05 17:42:20,616 INFO [train.py:715] (4/8) Epoch 6, batch 34650, loss[loss=0.1669, simple_loss=0.2439, pruned_loss=0.04498, over 4752.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2203, pruned_loss=0.03857, over 971431.99 frames.], batch size: 19, lr: 3.20e-04
2022-05-05 17:42:59,316 INFO [train.py:715] (4/8) Epoch 6, batch 34700, loss[loss=0.2027, simple_loss=0.2595, pruned_loss=0.07296, over 4904.00 frames.], tot_loss[loss=0.1487, simple_loss=0.2202, pruned_loss=0.03853, over 971942.10 frames.], batch size: 39, lr: 3.20e-04
2022-05-05 17:43:37,141 INFO [train.py:715] (4/8) Epoch 6, batch 34750, loss[loss=0.1123, simple_loss=0.1949, pruned_loss=0.01489, over 4752.00 frames.], tot_loss[loss=0.1489, simple_loss=0.2204, pruned_loss=0.0387, over 970944.76 frames.], batch size: 14, lr: 3.20e-04
2022-05-05 17:44:13,983 INFO [train.py:715] (4/8) Epoch 6, batch 34800, loss[loss=0.1268, simple_loss=0.2063, pruned_loss=0.02363, over 4737.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2194, pruned_loss=0.03855, over 970921.99 frames.], batch size: 12, lr: 3.20e-04
2022-05-05 17:45:04,005 INFO [train.py:715] (4/8) Epoch 7, batch 0, loss[loss=0.1566, simple_loss=0.2323, pruned_loss=0.04044, over 4955.00 frames.], tot_loss[loss=0.1566, simple_loss=0.2323, pruned_loss=0.04044, over 4955.00 frames.], batch size: 35, lr: 3.03e-04
2022-05-05 17:45:42,574 INFO [train.py:715] (4/8) Epoch 7, batch 50, loss[loss=0.1379, simple_loss=0.2107, pruned_loss=0.03257, over 4863.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2178, pruned_loss=0.03792, over 218580.31 frames.], batch size: 20, lr: 3.03e-04
2022-05-05 17:46:21,355 INFO [train.py:715] (4/8) Epoch 7, batch 100, loss[loss=0.1242, simple_loss=0.2036, pruned_loss=0.02236, over 4979.00 frames.], tot_loss[loss=0.1492, simple_loss=0.2194, pruned_loss=0.03946, over 386193.13 frames.], batch size: 24, lr: 3.03e-04
2022-05-05 17:47:00,257 INFO [train.py:715] (4/8) Epoch 7, batch 150, loss[loss=0.1221, simple_loss=0.1946, pruned_loss=0.02479, over 4776.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2185, pruned_loss=0.03819, over 516827.09 frames.], batch size: 14, lr: 3.03e-04
2022-05-05 17:47:39,938 INFO [train.py:715] (4/8) Epoch 7, batch 200, loss[loss=0.1371, simple_loss=0.2114, pruned_loss=0.03142, over 4829.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2193, pruned_loss=0.03854, over 617310.99 frames.], batch size: 26, lr: 3.03e-04
2022-05-05 17:48:18,731 INFO [train.py:715] (4/8) Epoch 7, batch 250, loss[loss=0.1163, simple_loss=0.1835, pruned_loss=0.0246, over 4959.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2185, pruned_loss=0.03813, over 696083.76 frames.], batch size: 15, lr: 3.03e-04
2022-05-05 17:48:58,165 INFO [train.py:715] (4/8) Epoch 7, batch 300, loss[loss=0.1522, simple_loss=0.2346, pruned_loss=0.03488, over 4985.00 frames.], tot_loss[loss=0.1465, simple_loss=0.218, pruned_loss=0.0375, over 757411.89 frames.], batch size: 25, lr: 3.02e-04
2022-05-05 17:49:36,844 INFO [train.py:715] (4/8) Epoch 7, batch 350, loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02893, over 4885.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2189, pruned_loss=0.03772, over 804998.67 frames.], batch size: 22, lr: 3.02e-04
2022-05-05 17:50:16,224 INFO [train.py:715] (4/8) Epoch 7, batch 400, loss[loss=0.1682, simple_loss=0.2459, pruned_loss=0.04527, over 4840.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2189, pruned_loss=0.0378, over 842506.11 frames.], batch size: 30, lr: 3.02e-04
2022-05-05 17:50:54,886 INFO [train.py:715] (4/8) Epoch 7, batch 450, loss[loss=0.1588, simple_loss=0.2385, pruned_loss=0.03953, over 4783.00 frames.], tot_loss[loss=0.148, simple_loss=0.2195, pruned_loss=0.0383, over 871027.14 frames.], batch size: 17, lr: 3.02e-04
2022-05-05 17:51:33,738 INFO [train.py:715] (4/8) Epoch 7, batch 500, loss[loss=0.1552, simple_loss=0.2364, pruned_loss=0.03698, over 4912.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2182, pruned_loss=0.03756, over 893929.73 frames.], batch size: 18, lr: 3.02e-04
2022-05-05 17:52:12,472 INFO [train.py:715] (4/8) Epoch 7, batch 550, loss[loss=0.181, simple_loss=0.2457, pruned_loss=0.05813, over 4895.00 frames.], tot_loss[loss=0.1464, simple_loss=0.218, pruned_loss=0.03741, over 912044.95 frames.], batch size: 17, lr: 3.02e-04
2022-05-05 17:52:51,634 INFO [train.py:715] (4/8) Epoch 7, batch 600, loss[loss=0.1167, simple_loss=0.1904, pruned_loss=0.02145, over 4788.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2176, pruned_loss=0.03699, over 924959.72 frames.], batch size: 18, lr: 3.02e-04
2022-05-05 17:53:29,948 INFO [train.py:715] (4/8) Epoch 7, batch 650, loss[loss=0.1566, simple_loss=0.2263, pruned_loss=0.04343, over 4964.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2182, pruned_loss=0.03698, over 935737.42 frames.], batch size: 15, lr: 3.02e-04
2022-05-05 17:54:08,327 INFO [train.py:715] (4/8) Epoch 7, batch 700, loss[loss=0.1333, simple_loss=0.1986, pruned_loss=0.03402, over 4779.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2178, pruned_loss=0.03676, over 943190.95 frames.], batch size: 17, lr: 3.02e-04
2022-05-05 17:54:47,592 INFO [train.py:715] (4/8) Epoch 7, batch 750, loss[loss=0.1339, simple_loss=0.2117, pruned_loss=0.02803, over 4861.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.03675, over 949543.88 frames.], batch size: 20, lr: 3.02e-04
2022-05-05 17:55:26,300 INFO [train.py:715] (4/8) Epoch 7, batch 800, loss[loss=0.1395, simple_loss=0.2122, pruned_loss=0.03335, over 4812.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2177, pruned_loss=0.03724, over 954722.12 frames.], batch size: 15, lr: 3.02e-04
2022-05-05 17:56:04,982 INFO [train.py:715] (4/8) Epoch 7, batch 850, loss[loss=0.1565, simple_loss=0.2281, pruned_loss=0.04243, over 4905.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03742, over 958842.43 frames.], batch size: 17, lr: 3.02e-04
2022-05-05 17:56:44,241 INFO [train.py:715] (4/8) Epoch 7, batch 900, loss[loss=0.1356, simple_loss=0.2015, pruned_loss=0.03483, over 4772.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2191, pruned_loss=0.03788, over 960740.87 frames.], batch size: 14, lr: 3.02e-04
2022-05-05 17:57:23,221 INFO [train.py:715] (4/8) Epoch 7, batch 950, loss[loss=0.1682, simple_loss=0.2324, pruned_loss=0.05196, over 4895.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2185, pruned_loss=0.03759, over 963406.38 frames.], batch size: 39, lr: 3.02e-04
2022-05-05 17:58:01,723 INFO [train.py:715] (4/8) Epoch 7, batch 1000, loss[loss=0.1266, simple_loss=0.1919, pruned_loss=0.03067, over 4746.00 frames.], tot_loss[loss=0.1465, simple_loss=0.218, pruned_loss=0.03749, over 965343.43 frames.], batch size: 16, lr: 3.02e-04
2022-05-05 17:58:40,406 INFO [train.py:715] (4/8) Epoch 7, batch 1050, loss[loss=0.1516, simple_loss=0.2237, pruned_loss=0.03976, over 4924.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2167, pruned_loss=0.03697, over 966891.18 frames.], batch size: 19, lr: 3.02e-04
2022-05-05 17:59:19,623 INFO [train.py:715] (4/8) Epoch 7, batch 1100, loss[loss=0.1762, simple_loss=0.2432, pruned_loss=0.05458, over 4751.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2169, pruned_loss=0.03681, over 967629.84 frames.], batch size: 14, lr: 3.02e-04
2022-05-05 17:59:57,783 INFO [train.py:715] (4/8) Epoch 7, batch 1150, loss[loss=0.1908, simple_loss=0.2336, pruned_loss=0.07399, over 4909.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2177, pruned_loss=0.0372, over 969468.60 frames.], batch size: 17, lr: 3.02e-04
2022-05-05 18:00:36,963 INFO [train.py:715] (4/8) Epoch 7, batch 1200, loss[loss=0.1316, simple_loss=0.21, pruned_loss=0.02663, over 4927.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.03668, over 970342.29 frames.], batch size: 23, lr: 3.02e-04
2022-05-05 18:01:16,051 INFO [train.py:715] (4/8) Epoch 7, batch 1250, loss[loss=0.139, simple_loss=0.2183, pruned_loss=0.02989, over 4881.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2171, pruned_loss=0.0366, over 970600.88 frames.], batch size: 22, lr: 3.02e-04
2022-05-05 18:01:55,175 INFO [train.py:715] (4/8) Epoch 7, batch 1300, loss[loss=0.1449, simple_loss=0.2279, pruned_loss=0.03096, over 4801.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2174, pruned_loss=0.03694, over 970586.46 frames.], batch size: 24, lr: 3.02e-04
2022-05-05 18:02:33,765 INFO [train.py:715] (4/8) Epoch 7, batch 1350, loss[loss=0.1584, simple_loss=0.219, pruned_loss=0.04892, over 4692.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.03722, over 970511.77 frames.], batch size: 15, lr: 3.02e-04
2022-05-05 18:03:12,552 INFO [train.py:715] (4/8) Epoch 7, batch 1400, loss[loss=0.09456, simple_loss=0.1632, pruned_loss=0.01297, over 4785.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2172, pruned_loss=0.037, over 970059.06 frames.], batch size: 12, lr: 3.02e-04
2022-05-05 18:03:51,643 INFO [train.py:715] (4/8) Epoch 7, batch 1450, loss[loss=0.1852, simple_loss=0.2511, pruned_loss=0.05961, over 4771.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2168, pruned_loss=0.03693, over 970314.58 frames.], batch size: 17, lr: 3.02e-04
2022-05-05 18:04:29,772 INFO [train.py:715] (4/8) Epoch 7, batch 1500, loss[loss=0.177, simple_loss=0.2356, pruned_loss=0.05926, over 4737.00 frames.], tot_loss[loss=0.146, simple_loss=0.2176, pruned_loss=0.03725, over 970974.32 frames.], batch size: 16, lr: 3.02e-04
2022-05-05 18:05:08,979 INFO [train.py:715] (4/8) Epoch 7, batch 1550, loss[loss=0.1703, simple_loss=0.2371, pruned_loss=0.05177, over 4857.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.03751, over 971746.58 frames.], batch size: 30, lr: 3.02e-04
2022-05-05 18:05:47,789 INFO [train.py:715] (4/8) Epoch 7, batch 1600, loss[loss=0.1226, simple_loss=0.2001, pruned_loss=0.02258, over 4779.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2189, pruned_loss=0.03764, over 972446.84 frames.], batch size: 19, lr: 3.02e-04
2022-05-05 18:06:26,680 INFO [train.py:715] (4/8) Epoch 7, batch 1650, loss[loss=0.177, simple_loss=0.2412, pruned_loss=0.0564, over 4776.00 frames.], tot_loss[loss=0.148, simple_loss=0.2196, pruned_loss=0.03817, over 972274.45 frames.], batch size: 14, lr: 3.02e-04
2022-05-05 18:07:05,257 INFO [train.py:715] (4/8) Epoch 7, batch 1700, loss[loss=0.1835, simple_loss=0.2473, pruned_loss=0.05983, over 4945.00 frames.], tot_loss[loss=0.1476, simple_loss=0.219, pruned_loss=0.03808, over 972473.40 frames.], batch size: 21, lr: 3.02e-04
2022-05-05 18:07:44,160 INFO [train.py:715] (4/8) Epoch 7, batch 1750, loss[loss=0.1434, simple_loss=0.2144, pruned_loss=0.03619, over 4804.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2186, pruned_loss=0.03739, over 973287.06 frames.], batch size: 24, lr: 3.02e-04
2022-05-05 18:08:24,138 INFO [train.py:715] (4/8) Epoch 7, batch 1800, loss[loss=0.1567, simple_loss=0.2331, pruned_loss=0.04008, over 4820.00 frames.], tot_loss[loss=0.147, simple_loss=0.2189, pruned_loss=0.03762, over 973393.49 frames.], batch size: 26, lr: 3.02e-04
2022-05-05 18:09:03,072 INFO [train.py:715] (4/8) Epoch 7, batch 1850, loss[loss=0.1401, simple_loss=0.2201, pruned_loss=0.03012, over 4840.00 frames.], tot_loss[loss=0.147, simple_loss=0.2186, pruned_loss=0.03769, over 973255.27 frames.], batch size: 15, lr: 3.02e-04
2022-05-05 18:09:41,925 INFO [train.py:715] (4/8) Epoch 7, batch 1900, loss[loss=0.1218, simple_loss=0.1963, pruned_loss=0.02363, over 4915.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03756, over 972580.74 frames.], batch size: 29, lr: 3.01e-04
2022-05-05 18:10:20,112 INFO [train.py:715] (4/8) Epoch 7, batch 1950, loss[loss=0.1349, simple_loss=0.1976, pruned_loss=0.03609, over 4816.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2168, pruned_loss=0.03685, over 972229.53 frames.], batch size: 26, lr: 3.01e-04
2022-05-05 18:10:59,290 INFO [train.py:715] (4/8) Epoch 7, batch 2000, loss[loss=0.1548, simple_loss=0.2245, pruned_loss=0.04261, over 4977.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03714, over 972835.15 frames.], batch size: 15, lr: 3.01e-04
2022-05-05 18:11:37,488 INFO [train.py:715] (4/8) Epoch 7, batch 2050, loss[loss=0.1727, simple_loss=0.2584, pruned_loss=0.0435, over 4891.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2174, pruned_loss=0.03701, over 972547.99 frames.], batch size: 22, lr: 3.01e-04
2022-05-05 18:12:16,137 INFO [train.py:715] (4/8) Epoch 7, batch 2100, loss[loss=0.1556, simple_loss=0.2232, pruned_loss=0.04397, over 4830.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2169, pruned_loss=0.03668, over 972256.04 frames.], batch size: 30, lr: 3.01e-04
2022-05-05 18:12:54,591 INFO [train.py:715] (4/8) Epoch 7, batch 2150, loss[loss=0.1417, simple_loss=0.2132, pruned_loss=0.03511, over 4789.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2164, pruned_loss=0.03655, over 972049.39 frames.], batch size: 14, lr: 3.01e-04
2022-05-05 18:13:32,800 INFO [train.py:715] (4/8) Epoch 7, batch 2200, loss[loss=0.1534, simple_loss=0.2214, pruned_loss=0.04273, over 4775.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2171, pruned_loss=0.03698, over 972764.90 frames.], batch size: 18, lr: 3.01e-04
2022-05-05 18:14:11,046 INFO [train.py:715] (4/8) Epoch 7, batch 2250, loss[loss=0.1416, simple_loss=0.2198, pruned_loss=0.03174, over 4932.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2168, pruned_loss=0.03702, over 972317.48 frames.], batch size: 23, lr: 3.01e-04
2022-05-05 18:14:50,045 INFO [train.py:715] (4/8) Epoch 7, batch 2300, loss[loss=0.1151, simple_loss=0.1947, pruned_loss=0.01771, over 4813.00 frames.], tot_loss[loss=0.1455, simple_loss=0.217, pruned_loss=0.03702, over 972797.61 frames.], batch size: 21, lr: 3.01e-04
2022-05-05 18:15:29,527 INFO [train.py:715] (4/8) Epoch 7, batch 2350, loss[loss=0.1441, simple_loss=0.225, pruned_loss=0.03161, over 4929.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2164, pruned_loss=0.0367, over 972419.29 frames.], batch size: 21, lr: 3.01e-04
2022-05-05 18:16:08,312 INFO [train.py:715] (4/8) Epoch 7, batch 2400, loss[loss=0.1405, simple_loss=0.2141, pruned_loss=0.03344, over 4916.00 frames.], tot_loss[loss=0.1458, simple_loss=0.217, pruned_loss=0.03725, over 971809.63 frames.], batch size: 39, lr: 3.01e-04
2022-05-05 18:16:46,789 INFO [train.py:715] (4/8) Epoch 7, batch 2450, loss[loss=0.1483, simple_loss=0.216, pruned_loss=0.04027, over 4826.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2165, pruned_loss=0.03692, over 971700.82 frames.], batch size: 30, lr: 3.01e-04
2022-05-05 18:17:25,559 INFO [train.py:715] (4/8) Epoch 7, batch 2500, loss[loss=0.144, simple_loss=0.2249, pruned_loss=0.03154, over 4927.00 frames.], tot_loss[loss=0.145, simple_loss=0.2163, pruned_loss=0.03688, over 971799.06 frames.], batch size: 39, lr: 3.01e-04
2022-05-05 18:18:03,861 INFO [train.py:715] (4/8) Epoch 7, batch 2550, loss[loss=0.1408, simple_loss=0.2141, pruned_loss=0.03376, over 4754.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2172, pruned_loss=0.03693, over 972390.16 frames.], batch size: 14, lr: 3.01e-04
2022-05-05 18:18:42,384 INFO [train.py:715] (4/8) Epoch 7, batch 2600, loss[loss=0.1559, simple_loss=0.2138, pruned_loss=0.04901, over 4838.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2184, pruned_loss=0.03731, over 972976.80 frames.], batch size: 32, lr: 3.01e-04
2022-05-05 18:19:21,137 INFO [train.py:715] (4/8) Epoch 7, batch 2650, loss[loss=0.15, simple_loss=0.2152, pruned_loss=0.04243, over 4720.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2185, pruned_loss=0.03694, over 972564.07 frames.], batch size: 15, lr: 3.01e-04
2022-05-05 18:19:59,711 INFO [train.py:715] (4/8) Epoch 7, batch 2700, loss[loss=0.1239, simple_loss=0.1971, pruned_loss=0.02529, over 4957.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2182, pruned_loss=0.037, over 972681.20 frames.], batch size: 14, lr: 3.01e-04
2022-05-05 18:20:37,585 INFO [train.py:715] (4/8) Epoch 7, batch 2750, loss[loss=0.1438, simple_loss=0.2062, pruned_loss=0.04075, over 4854.00 frames.], tot_loss[loss=0.146, simple_loss=0.2179, pruned_loss=0.03709, over 972093.59 frames.], batch size: 15, lr: 3.01e-04
2022-05-05 18:21:16,374 INFO [train.py:715] (4/8) Epoch 7, batch 2800, loss[loss=0.1279, simple_loss=0.2106, pruned_loss=0.02259, over 4694.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.03636, over 972467.98 frames.], batch size: 15, lr: 3.01e-04
2022-05-05 18:21:55,734 INFO [train.py:715] (4/8) Epoch 7, batch 2850, loss[loss=0.1359, simple_loss=0.2021, pruned_loss=0.03487, over 4918.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2159, pruned_loss=0.03595, over 972984.77 frames.], batch size: 18, lr: 3.01e-04
2022-05-05 18:22:35,310 INFO [train.py:715] (4/8) Epoch 7, batch 2900, loss[loss=0.1633, simple_loss=0.2427, pruned_loss=0.04192, over 4765.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2169, pruned_loss=0.03685, over 973112.83 frames.], batch size: 19, lr: 3.01e-04
2022-05-05 18:23:14,209 INFO [train.py:715] (4/8) Epoch 7, batch 2950, loss[loss=0.1487, simple_loss=0.2129, pruned_loss=0.0422, over 4941.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2172, pruned_loss=0.03702, over 972582.36 frames.], batch size: 21, lr: 3.01e-04
2022-05-05 18:23:53,379 INFO [train.py:715] (4/8) Epoch 7, batch 3000, loss[loss=0.1431, simple_loss=0.2177, pruned_loss=0.03428, over 4883.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2182, pruned_loss=0.03764, over 973348.67 frames.], batch size: 22, lr: 3.01e-04
2022-05-05 18:23:53,379 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 18:24:04,765 INFO [train.py:742] (4/8) Epoch 7, validation: loss=0.1084, simple_loss=0.1933, pruned_loss=0.01171, over 914524.00 frames.
2022-05-05 18:24:44,251 INFO [train.py:715] (4/8) Epoch 7, batch 3050, loss[loss=0.126, simple_loss=0.2072, pruned_loss=0.02237, over 4822.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2193, pruned_loss=0.03797, over 972971.59 frames.], batch size: 27, lr: 3.01e-04
2022-05-05 18:25:23,054 INFO [train.py:715] (4/8) Epoch 7, batch 3100, loss[loss=0.1481, simple_loss=0.2239, pruned_loss=0.03614, over 4976.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2191, pruned_loss=0.03773, over 972776.85 frames.], batch size: 28, lr: 3.01e-04
2022-05-05 18:26:01,760 INFO [train.py:715] (4/8) Epoch 7, batch 3150, loss[loss=0.1333, simple_loss=0.2051, pruned_loss=0.03075, over 4790.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2192, pruned_loss=0.03815, over 972243.27 frames.], batch size: 14, lr: 3.01e-04
2022-05-05 18:26:39,663 INFO [train.py:715] (4/8) Epoch 7, batch 3200, loss[loss=0.1404, simple_loss=0.2117, pruned_loss=0.03458, over 4952.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2183, pruned_loss=0.03763, over 972347.15 frames.], batch size: 39, lr: 3.01e-04
2022-05-05 18:27:17,882 INFO [train.py:715] (4/8) Epoch 7, batch 3250, loss[loss=0.1569, simple_loss=0.2138, pruned_loss=0.04999, over 4758.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2192, pruned_loss=0.03781, over 971794.41 frames.], batch size: 12, lr: 3.01e-04
2022-05-05 18:27:56,437 INFO [train.py:715] (4/8) Epoch 7, batch 3300, loss[loss=0.1401, simple_loss=0.2087, pruned_loss=0.03575, over 4780.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2195, pruned_loss=0.03762, over 972265.03 frames.], batch size: 12, lr: 3.01e-04
2022-05-05 18:28:35,032 INFO [train.py:715] (4/8) Epoch 7, batch 3350, loss[loss=0.1477, simple_loss=0.2297, pruned_loss=0.03281, over 4930.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2188, pruned_loss=0.03723, over 972053.53 frames.], batch size: 23, lr: 3.01e-04
2022-05-05 18:29:13,824 INFO [train.py:715] (4/8) Epoch 7, batch 3400, loss[loss=0.1606, simple_loss=0.2173, pruned_loss=0.052, over 4976.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2179, pruned_loss=0.03723, over 972278.06 frames.], batch size: 24, lr: 3.01e-04
2022-05-05 18:29:52,251 INFO [train.py:715] (4/8) Epoch 7, batch 3450, loss[loss=0.1525, simple_loss=0.2241, pruned_loss=0.04042, over 4972.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2176, pruned_loss=0.03689, over 972224.56 frames.], batch size: 14, lr: 3.01e-04
2022-05-05 18:30:31,304 INFO [train.py:715] (4/8) Epoch 7, batch 3500, loss[loss=0.1167, simple_loss=0.196, pruned_loss=0.01872, over 4880.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03741, over 972219.35 frames.], batch size: 20, lr: 3.01e-04
2022-05-05 18:31:09,923 INFO [train.py:715] (4/8) Epoch 7, batch 3550, loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03061, over 4789.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2178, pruned_loss=0.03734, over 972444.97 frames.], batch size: 21, lr: 3.00e-04
2022-05-05 18:31:48,695 INFO [train.py:715] (4/8) Epoch 7, batch 3600, loss[loss=0.154, simple_loss=0.2254, pruned_loss=0.04129, over 4954.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2177, pruned_loss=0.03743, over 972708.83 frames.], batch size: 21, lr: 3.00e-04
2022-05-05 18:32:27,425 INFO [train.py:715] (4/8) Epoch 7, batch 3650, loss[loss=0.1399, simple_loss=0.2189, pruned_loss=0.03042, over 4889.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2186, pruned_loss=0.03776, over 973225.31 frames.], batch size: 22, lr: 3.00e-04
2022-05-05 18:33:06,461 INFO [train.py:715] (4/8) Epoch 7, batch 3700, loss[loss=0.1515, simple_loss=0.2171, pruned_loss=0.04295, over 4850.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2186, pruned_loss=0.03762, over 972403.05 frames.], batch size: 32, lr: 3.00e-04
2022-05-05 18:33:45,234 INFO [train.py:715] (4/8) Epoch 7, batch 3750, loss[loss=0.1749, simple_loss=0.2393, pruned_loss=0.05524, over 4864.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2182, pruned_loss=0.03755, over 972582.01 frames.], batch size: 32, lr: 3.00e-04
2022-05-05 18:34:23,490 INFO [train.py:715] (4/8) Epoch 7, batch 3800, loss[loss=0.155, simple_loss=0.2255, pruned_loss=0.04228, over 4884.00 frames.], tot_loss[loss=0.147, simple_loss=0.2183, pruned_loss=0.03783, over 973287.35 frames.], batch size: 16, lr: 3.00e-04
2022-05-05 18:35:01,655 INFO [train.py:715] (4/8) Epoch 7, batch 3850, loss[loss=0.1215, simple_loss=0.1985, pruned_loss=0.02229, over 4908.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2175, pruned_loss=0.03759, over 973342.93 frames.], batch size: 17, lr: 3.00e-04
2022-05-05 18:35:39,928 INFO [train.py:715] (4/8) Epoch 7, batch 3900, loss[loss=0.1733, simple_loss=0.232, pruned_loss=0.0573, over 4778.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2181, pruned_loss=0.03826, over 973239.91 frames.], batch size: 14, lr: 3.00e-04
2022-05-05 18:36:18,411 INFO [train.py:715] (4/8) Epoch 7, batch 3950, loss[loss=0.1319, simple_loss=0.2113, pruned_loss=0.02623, over 4926.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2188, pruned_loss=0.03832, over 972488.43 frames.], batch size: 23, lr: 3.00e-04
2022-05-05 18:36:57,037 INFO [train.py:715] (4/8) Epoch 7, batch 4000, loss[loss=0.1518, simple_loss=0.2197, pruned_loss=0.04192, over 4695.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2184, pruned_loss=0.03824, over 971562.67 frames.], batch size: 15, lr: 3.00e-04
2022-05-05 18:37:35,131 INFO [train.py:715] (4/8) Epoch 7, batch 4050, loss[loss=0.1376, simple_loss=0.2086, pruned_loss=0.03328, over 4788.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2182, pruned_loss=0.03798, over 973094.90 frames.], batch size: 17, lr: 3.00e-04
2022-05-05 18:38:14,042 INFO [train.py:715] (4/8) Epoch 7, batch 4100, loss[loss=0.1482, simple_loss=0.2213, pruned_loss=0.03751, over 4850.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2178, pruned_loss=0.03766, over 973387.36 frames.], batch size: 13, lr: 3.00e-04
2022-05-05 18:38:52,561 INFO [train.py:715] (4/8) Epoch 7, batch 4150, loss[loss=0.1391, simple_loss=0.2153, pruned_loss=0.03145, over 4798.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2191, pruned_loss=0.03814, over 973390.69 frames.], batch size: 14, lr: 3.00e-04
2022-05-05 18:39:31,259 INFO [train.py:715] (4/8) Epoch 7, batch 4200, loss[loss=0.1288, simple_loss=0.199, pruned_loss=0.02933, over 4977.00 frames.], tot_loss[loss=0.147, simple_loss=0.2182, pruned_loss=0.03787, over 973784.84 frames.], batch size: 14, lr: 3.00e-04
2022-05-05 18:40:09,114 INFO [train.py:715] (4/8) Epoch 7, batch 4250, loss[loss=0.16, simple_loss=0.2412, pruned_loss=0.03944, over 4788.00 frames.], tot_loss[loss=0.147, simple_loss=0.2184, pruned_loss=0.03783, over 973481.94 frames.], batch size: 17, lr: 3.00e-04
2022-05-05 18:40:47,959 INFO [train.py:715] (4/8) Epoch 7, batch 4300, loss[loss=0.1122, simple_loss=0.1818, pruned_loss=0.02127, over 4777.00 frames.], tot_loss[loss=0.147, simple_loss=0.2184, pruned_loss=0.03781, over 972474.44 frames.], batch size: 14, lr: 3.00e-04
2022-05-05 18:41:28,766 INFO [train.py:715] (4/8) Epoch 7, batch 4350, loss[loss=0.1435, simple_loss=0.2107, pruned_loss=0.03815, over 4837.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2184, pruned_loss=0.03774, over 972380.91 frames.], batch size: 25, lr: 3.00e-04
2022-05-05 18:42:07,269 INFO [train.py:715] (4/8) Epoch 7, batch 4400, loss[loss=0.1592, simple_loss=0.2256, pruned_loss=0.04641, over 4798.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2189, pruned_loss=0.03838, over 972747.57 frames.], batch size: 24, lr: 3.00e-04
2022-05-05 18:42:46,326 INFO [train.py:715] (4/8) Epoch 7, batch 4450, loss[loss=0.147, simple_loss=0.2267, pruned_loss=0.03368, over 4777.00 frames.], tot_loss[loss=0.148, simple_loss=0.2192, pruned_loss=0.03842, over 972373.16 frames.], batch size: 17, lr: 3.00e-04
2022-05-05 18:43:25,201 INFO [train.py:715] (4/8) Epoch 7, batch 4500, loss[loss=0.1303, simple_loss=0.2021, pruned_loss=0.02926, over 4902.00 frames.], tot_loss[loss=0.147, simple_loss=0.218, pruned_loss=0.038, over 972185.33 frames.], batch size: 19, lr: 3.00e-04
2022-05-05 18:44:03,954 INFO [train.py:715] (4/8) Epoch 7, batch 4550, loss[loss=0.1457, simple_loss=0.2169, pruned_loss=0.03724, over 4773.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2191, pruned_loss=0.03822, over 972273.68 frames.], batch size: 14, lr: 3.00e-04
2022-05-05 18:44:42,555 INFO [train.py:715] (4/8) Epoch 7, batch 4600, loss[loss=0.1907, simple_loss=0.2555, pruned_loss=0.06289, over 4936.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2188, pruned_loss=0.03783, over 971244.07 frames.], batch size: 39, lr: 3.00e-04
2022-05-05 18:45:21,317 INFO [train.py:715] (4/8) Epoch 7, batch 4650, loss[loss=0.142, simple_loss=0.2143, pruned_loss=0.03482, over 4805.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2181, pruned_loss=0.03711, over 970985.49 frames.], batch size: 21, lr: 3.00e-04
2022-05-05 18:45:59,801 INFO [train.py:715] (4/8) Epoch 7, batch 4700, loss[loss=0.1469, simple_loss=0.2085, pruned_loss=0.0426, over 4972.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2189, pruned_loss=0.03738, over 971403.26 frames.], batch size: 14, lr: 3.00e-04
2022-05-05 18:46:37,973 INFO [train.py:715] (4/8) Epoch 7, batch 4750, loss[loss=0.136, simple_loss=0.2062, pruned_loss=0.03288, over 4771.00 frames.], tot_loss[loss=0.1459, simple_loss=0.218, pruned_loss=0.03687, over 972216.56 frames.], batch size: 19, lr: 3.00e-04
2022-05-05 18:47:17,156 INFO [train.py:715] (4/8) Epoch 7, batch 4800, loss[loss=0.1467, simple_loss=0.2191, pruned_loss=0.03716, over 4808.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2179, pruned_loss=0.03674, over 972974.05 frames.], batch size: 21, lr: 3.00e-04
2022-05-05 18:47:55,561 INFO [train.py:715] (4/8) Epoch 7, batch 4850, loss[loss=0.1577, simple_loss=0.229, pruned_loss=0.04318, over 4769.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2182, pruned_loss=0.03729, over 971985.87 frames.], batch size: 17, lr: 3.00e-04
2022-05-05 18:48:34,304 INFO [train.py:715] (4/8) Epoch 7, batch 4900, loss[loss=0.1749, simple_loss=0.2355, pruned_loss=0.05718, over 4942.00 frames.], tot_loss[loss=0.1472, simple_loss=0.219, pruned_loss=0.03766, over 972428.92 frames.], batch size: 35, lr: 3.00e-04
2022-05-05 18:49:12,733 INFO [train.py:715] (4/8) Epoch 7, batch 4950, loss[loss=0.1217, simple_loss=0.1958, pruned_loss=0.02378, over 4815.00 frames.], tot_loss[loss=0.1477, simple_loss=0.219, pruned_loss=0.0382, over 971418.92 frames.], batch size: 13, lr: 3.00e-04
2022-05-05 18:49:51,779 INFO [train.py:715] (4/8) Epoch 7, batch 5000, loss[loss=0.1456, simple_loss=0.2236, pruned_loss=0.03379, over 4829.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03768, over 971615.81 frames.], batch size: 15, lr: 3.00e-04
2022-05-05 18:50:30,775 INFO [train.py:715] (4/8) Epoch 7, batch 5050, loss[loss=0.1512, simple_loss=0.2167, pruned_loss=0.04279, over 4852.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2191, pruned_loss=0.0377, over 971531.84 frames.], batch size: 30, lr: 3.00e-04
2022-05-05 18:51:09,362 INFO [train.py:715] (4/8) Epoch 7, batch 5100, loss[loss=0.1408, simple_loss=0.2189, pruned_loss=0.0313, over 4879.00 frames.], tot_loss[loss=0.1471, simple_loss=0.219, pruned_loss=0.03765, over 972989.87 frames.], batch size: 22, lr: 3.00e-04
2022-05-05 18:51:48,427 INFO [train.py:715] (4/8) Epoch 7, batch 5150, loss[loss=0.1449, simple_loss=0.2169, pruned_loss=0.03647, over 4912.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03774, over 972362.11 frames.], batch size: 17, lr: 3.00e-04
2022-05-05 18:52:27,136 INFO [train.py:715] (4/8) Epoch 7, batch 5200, loss[loss=0.1162, simple_loss=0.1918, pruned_loss=0.02028, over 4777.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03739, over 972010.12 frames.], batch size: 17, lr: 2.99e-04
2022-05-05 18:53:06,161 INFO [train.py:715] (4/8) Epoch 7, batch 5250, loss[loss=0.1414, simple_loss=0.2261, pruned_loss=0.02831, over 4988.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.03723, over 972447.76 frames.], batch size: 26, lr: 2.99e-04
2022-05-05 18:53:44,794 INFO [train.py:715] (4/8) Epoch 7, batch 5300, loss[loss=0.1448, simple_loss=0.2163, pruned_loss=0.03662, over 4977.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.03741, over 973614.19 frames.], batch size: 15, lr: 2.99e-04
2022-05-05 18:54:24,159 INFO [train.py:715] (4/8) Epoch 7, batch 5350, loss[loss=0.1289, simple_loss=0.2114, pruned_loss=0.02325, over 4814.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2178, pruned_loss=0.03698, over 973843.08 frames.], batch size: 25, lr: 2.99e-04
2022-05-05 18:55:02,367 INFO [train.py:715] (4/8) Epoch 7, batch 5400, loss[loss=0.181, simple_loss=0.2533, pruned_loss=0.05436, over 4952.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2188, pruned_loss=0.03748, over 974057.19 frames.], batch size: 23, lr: 2.99e-04
2022-05-05 18:55:41,207 INFO [train.py:715] (4/8) Epoch 7, batch 5450, loss[loss=0.1553, simple_loss=0.2354, pruned_loss=0.03763, over 4790.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2184, pruned_loss=0.03743, over 973584.91 frames.], batch size: 21, lr: 2.99e-04
2022-05-05 18:56:20,340 INFO [train.py:715] (4/8) Epoch 7, batch 5500, loss[loss=0.1508, simple_loss=0.221, pruned_loss=0.04027, over 4881.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03741, over 973287.63 frames.], batch size: 22, lr: 2.99e-04
2022-05-05 18:56:59,123 INFO [train.py:715] (4/8) Epoch 7, batch 5550, loss[loss=0.1863, simple_loss=0.245, pruned_loss=0.06379, over 4872.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2184, pruned_loss=0.03751, over 972148.19 frames.], batch size: 32, lr: 2.99e-04
2022-05-05 18:57:38,239 INFO [train.py:715] (4/8) Epoch 7, batch 5600, loss[loss=0.1475, simple_loss=0.2238, pruned_loss=0.03559, over 4921.00 frames.], tot_loss[loss=0.1457, simple_loss=0.217, pruned_loss=0.03721, over 973136.11 frames.], batch size: 18, lr: 2.99e-04
2022-05-05 18:58:17,274 INFO [train.py:715] (4/8) Epoch 7, batch 5650, loss[loss=0.1371, simple_loss=0.1998, pruned_loss=0.03725, over 4958.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2174, pruned_loss=0.03743, over 973475.99 frames.], batch size: 14, lr: 2.99e-04
2022-05-05 18:58:56,368 INFO [train.py:715] (4/8) Epoch 7, batch 5700, loss[loss=0.1856, simple_loss=0.2416, pruned_loss=0.0648, over 4695.00 frames.], tot_loss[loss=0.1467, simple_loss=0.218, pruned_loss=0.03776, over 974476.05 frames.], batch size: 15, lr: 2.99e-04
2022-05-05 18:59:34,741 INFO [train.py:715] (4/8) Epoch 7, batch 5750, loss[loss=0.1508, simple_loss=0.2207, pruned_loss=0.0405, over 4982.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2182, pruned_loss=0.03772, over 973527.83 frames.], batch size: 35, lr: 2.99e-04
2022-05-05 19:00:12,900 INFO [train.py:715] (4/8) Epoch 7, batch 5800, loss[loss=0.1258, simple_loss=0.2014, pruned_loss=0.02511, over 4802.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2179, pruned_loss=0.03728, over 974191.66 frames.], batch size: 21, lr: 2.99e-04
2022-05-05 19:00:52,630 INFO [train.py:715] (4/8) Epoch 7, batch 5850, loss[loss=0.1551, simple_loss=0.2219, pruned_loss=0.04417, over 4800.00 frames.], tot_loss[loss=0.146, simple_loss=0.2177, pruned_loss=0.03715, over 973622.97 frames.], batch size: 21, lr: 2.99e-04
2022-05-05 19:01:30,924 INFO [train.py:715] (4/8) Epoch 7, batch 5900, loss[loss=0.1281, simple_loss=0.1978, pruned_loss=0.02916, over 4893.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2184, pruned_loss=0.03754, over 972722.15 frames.], batch size: 22, lr: 2.99e-04
2022-05-05 19:02:09,960 INFO [train.py:715] (4/8) Epoch 7, batch 5950, loss[loss=0.1671, simple_loss=0.2333, pruned_loss=0.05044, over 4906.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2189, pruned_loss=0.03767, over 971843.67 frames.], batch size: 17, lr: 2.99e-04
2022-05-05 19:02:48,384 INFO [train.py:715] (4/8) Epoch 7, batch 6000, loss[loss=0.1199, simple_loss=0.1896, pruned_loss=0.02514, over 4973.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2185, pruned_loss=0.03735, over 972202.19 frames.], batch size: 14, lr: 2.99e-04
2022-05-05 19:02:48,385 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 19:02:58,046 INFO [train.py:742] (4/8) Epoch 7, validation: loss=0.1085, simple_loss=0.1933, pruned_loss=0.0119, over 914524.00 frames.
2022-05-05 19:03:36,917 INFO [train.py:715] (4/8) Epoch 7, batch 6050, loss[loss=0.1866, simple_loss=0.256, pruned_loss=0.05866, over 4929.00 frames.], tot_loss[loss=0.1472, simple_loss=0.219, pruned_loss=0.03766, over 972676.96 frames.], batch size: 39, lr: 2.99e-04
2022-05-05 19:04:16,083 INFO [train.py:715] (4/8) Epoch 7, batch 6100, loss[loss=0.1163, simple_loss=0.1842, pruned_loss=0.02418, over 4871.00 frames.], tot_loss[loss=0.1472, simple_loss=0.219, pruned_loss=0.03776, over 972754.90 frames.], batch size: 16, lr: 2.99e-04
2022-05-05 19:04:55,378 INFO [train.py:715] (4/8) Epoch 7, batch 6150, loss[loss=0.1353, simple_loss=0.2129, pruned_loss=0.02888, over 4819.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2194, pruned_loss=0.03786, over 972935.89 frames.], batch size: 27, lr: 2.99e-04
2022-05-05 19:05:33,828 INFO [train.py:715] (4/8) Epoch 7, batch 6200, loss[loss=0.1673, simple_loss=0.2411, pruned_loss=0.04676, over 4901.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2196, pruned_loss=0.03805, over 973233.97 frames.], batch size: 18, lr: 2.99e-04
2022-05-05 19:06:13,680 INFO [train.py:715] (4/8) Epoch 7, batch 6250, loss[loss=0.1527, simple_loss=0.2384, pruned_loss=0.0335, over 4822.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2187, pruned_loss=0.03758, over 972911.82 frames.], batch size: 13, lr: 2.99e-04
2022-05-05 19:06:52,572 INFO [train.py:715] (4/8) Epoch 7, batch 6300, loss[loss=0.1256, simple_loss=0.1987, pruned_loss=0.02624, over 4777.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2185, pruned_loss=0.03744, over 973335.93 frames.], batch size: 18, lr: 2.99e-04
2022-05-05 19:07:30,974 INFO [train.py:715] (4/8) Epoch 7, batch 6350, loss[loss=0.1622, simple_loss=0.2329, pruned_loss=0.04573, over 4867.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2179, pruned_loss=0.03697, over 972954.35 frames.], batch size: 20, lr: 2.99e-04
2022-05-05 19:08:10,035 INFO [train.py:715] (4/8) Epoch 7, batch 6400, loss[loss=0.1192, simple_loss=0.1935, pruned_loss=0.02242, over 4928.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.03739, over 972319.81 frames.], batch size: 29, lr: 2.99e-04
2022-05-05 19:08:49,046 INFO [train.py:715] (4/8) Epoch 7, batch 6450, loss[loss=0.1342, simple_loss=0.1962, pruned_loss=0.0361, over 4987.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2177, pruned_loss=0.0373, over 972894.72 frames.], batch size: 14, lr: 2.99e-04
2022-05-05 19:09:27,584 INFO [train.py:715] (4/8) Epoch 7, batch 6500, loss[loss=0.1355, simple_loss=0.2037, pruned_loss=0.03366, over 4852.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2182, pruned_loss=0.03747, over 972452.53 frames.], batch size: 32, lr: 2.99e-04
2022-05-05 19:10:06,573 INFO [train.py:715] (4/8) Epoch 7, batch 6550, loss[loss=0.1655, simple_loss=0.2286, pruned_loss=0.0512, over 4897.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2193, pruned_loss=0.038, over 973273.93 frames.], batch size: 19, lr: 2.99e-04
2022-05-05 19:10:46,394 INFO [train.py:715] (4/8) Epoch 7, batch 6600, loss[loss=0.1334, simple_loss=0.2103, pruned_loss=0.02828, over 4951.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2191, pruned_loss=0.03785, over 972467.11 frames.], batch size: 23, lr: 2.99e-04
2022-05-05 19:11:25,241 INFO [train.py:715] (4/8) Epoch 7, batch 6650, loss[loss=0.1597, simple_loss=0.2324, pruned_loss=0.04352, over 4976.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2195, pruned_loss=0.03814, over 973163.77 frames.], batch size: 15, lr: 2.99e-04
2022-05-05 19:12:04,477 INFO [train.py:715] (4/8) Epoch 7, batch 6700, loss[loss=0.1485, simple_loss=0.2315, pruned_loss=0.03279, over 4923.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2198, pruned_loss=0.03823, over 973285.71 frames.], batch size: 18, lr: 2.99e-04
2022-05-05 19:12:43,222 INFO [train.py:715] (4/8) Epoch 7, batch 6750, loss[loss=0.1188, simple_loss=0.1912, pruned_loss=0.02319, over 4894.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2188, pruned_loss=0.03747, over 973268.10 frames.], batch size: 19, lr: 2.99e-04
2022-05-05 19:13:22,216 INFO [train.py:715] (4/8) Epoch 7, batch 6800, loss[loss=0.157, simple_loss=0.2279, pruned_loss=0.04305, over 4983.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2178, pruned_loss=0.03698, over 973421.97 frames.], batch size: 28, lr: 2.99e-04
2022-05-05 19:14:00,578 INFO [train.py:715] (4/8) Epoch 7, batch 6850, loss[loss=0.1238, simple_loss=0.1921, pruned_loss=0.02769, over 4943.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2182, pruned_loss=0.03698, over 972432.06 frames.], batch size: 29, lr: 2.99e-04
2022-05-05 19:14:39,179 INFO [train.py:715] (4/8) Epoch 7, batch 6900, loss[loss=0.1073, simple_loss=0.1816, pruned_loss=0.0165, over 4789.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03751, over 972609.65 frames.], batch size: 17, lr: 2.98e-04
2022-05-05 19:15:18,693 INFO [train.py:715] (4/8) Epoch 7, batch 6950, loss[loss=0.1546, simple_loss=0.239, pruned_loss=0.03514, over 4739.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2185, pruned_loss=0.0375, over 972750.08 frames.], batch size: 16, lr: 2.98e-04
2022-05-05 19:15:56,859 INFO [train.py:715] (4/8) Epoch 7, batch 7000, loss[loss=0.1675, simple_loss=0.2297, pruned_loss=0.05265, over 4839.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2192, pruned_loss=0.03795, over 973339.88 frames.], batch size: 34, lr: 2.98e-04
2022-05-05 19:16:35,554 INFO [train.py:715] (4/8) Epoch 7, batch 7050, loss[loss=0.1504, simple_loss=0.219, pruned_loss=0.04089, over 4757.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2192, pruned_loss=0.0382, over 973490.24 frames.], batch size: 19, lr: 2.98e-04
2022-05-05 19:17:14,122 INFO [train.py:715] (4/8) Epoch 7, batch 7100, loss[loss=0.1302, simple_loss=0.1999, pruned_loss=0.03024, over 4858.00 frames.], tot_loss[loss=0.1474, simple_loss=0.219, pruned_loss=0.03792, over 972673.41 frames.], batch size: 32, lr: 2.98e-04
2022-05-05 19:17:52,400 INFO [train.py:715] (4/8) Epoch 7, batch 7150, loss[loss=0.1231, simple_loss=0.1918, pruned_loss=0.02714, over 4991.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2191, pruned_loss=0.03775, over 972393.53 frames.], batch size: 14, lr: 2.98e-04
2022-05-05 19:18:31,019 INFO [train.py:715] (4/8) Epoch 7, batch 7200, loss[loss=0.1248, simple_loss=0.1898, pruned_loss=0.02991, over 4867.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2183, pruned_loss=0.0375, over 972939.45 frames.], batch size: 20, lr: 2.98e-04
2022-05-05 19:19:10,025 INFO [train.py:715] (4/8) Epoch 7, batch 7250, loss[loss=0.1576, simple_loss=0.2265, pruned_loss=0.04433, over 4781.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2185, pruned_loss=0.03759, over 972804.65 frames.], batch size: 14, lr: 2.98e-04
2022-05-05 19:19:49,674 INFO [train.py:715] (4/8) Epoch 7, batch 7300, loss[loss=0.1448, simple_loss=0.2129, pruned_loss=0.03834, over 4795.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2182, pruned_loss=0.03751, over 972677.06 frames.], batch size: 14, lr: 2.98e-04
2022-05-05 19:20:28,207 INFO [train.py:715] (4/8) Epoch 7, batch 7350, loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03062, over 4961.00 frames.], tot_loss[loss=0.1463, simple_loss=0.218, pruned_loss=0.03728, over 973524.85 frames.], batch size: 15, lr: 2.98e-04
2022-05-05 19:21:06,664 INFO [train.py:715] (4/8) Epoch 7, batch 7400, loss[loss=0.1253, simple_loss=0.2001, pruned_loss=0.02531, over 4868.00 frames.], tot_loss[loss=0.1464, simple_loss=0.218, pruned_loss=0.03736, over 973553.63 frames.], batch size: 16, lr: 2.98e-04
2022-05-05 19:21:45,794 INFO [train.py:715] (4/8) Epoch 7, batch 7450, loss[loss=0.182, simple_loss=0.2515, pruned_loss=0.05631, over 4982.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2178, pruned_loss=0.03729, over 974038.84 frames.], batch size: 15, lr: 2.98e-04
2022-05-05 19:22:24,000 INFO [train.py:715] (4/8) Epoch 7, batch 7500, loss[loss=0.1333, simple_loss=0.2143, pruned_loss=0.02617, over 4775.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03718, over 973299.43 frames.], batch size: 18, lr: 2.98e-04
2022-05-05 19:23:02,794 INFO [train.py:715] (4/8) Epoch 7, batch 7550, loss[loss=0.203, simple_loss=0.2786, pruned_loss=0.0637, over 4847.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2176, pruned_loss=0.03729, over 971941.29 frames.], batch size: 20, lr: 2.98e-04
2022-05-05 19:23:41,679 INFO [train.py:715] (4/8) Epoch 7, batch 7600, loss[loss=0.1692, simple_loss=0.2484, pruned_loss=0.04499, over 4923.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2178, pruned_loss=0.03762, over 971525.25 frames.], batch size: 18, lr: 2.98e-04
2022-05-05 19:24:20,769 INFO [train.py:715] (4/8) Epoch 7, batch 7650, loss[loss=0.1424, simple_loss=0.2179, pruned_loss=0.03341, over 4973.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2179, pruned_loss=0.03773, over 971206.52 frames.], batch size: 35, lr: 2.98e-04
2022-05-05 19:24:59,080 INFO [train.py:715] (4/8) Epoch 7, batch 7700, loss[loss=0.169, simple_loss=0.2451, pruned_loss=0.04645, over 4936.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2186, pruned_loss=0.0381, over 972166.15 frames.], batch size: 39, lr: 2.98e-04
2022-05-05 19:25:38,047 INFO [train.py:715] (4/8) Epoch 7, batch 7750, loss[loss=0.1441, simple_loss=0.2134, pruned_loss=0.03737, over 4775.00 frames.], tot_loss[loss=0.1483, simple_loss=0.2193, pruned_loss=0.03862, over 971670.99 frames.], batch size: 14, lr: 2.98e-04
2022-05-05 19:26:17,068 INFO [train.py:715] (4/8) Epoch 7, batch 7800, loss[loss=0.152, simple_loss=0.2258, pruned_loss=0.03914, over 4846.00 frames.], tot_loss[loss=0.1481, simple_loss=0.2194, pruned_loss=0.03845, over 971211.43 frames.], batch size: 26, lr: 2.98e-04
2022-05-05 19:26:55,230 INFO [train.py:715] (4/8) Epoch 7, batch 7850, loss[loss=0.1502, simple_loss=0.227, pruned_loss=0.0367, over 4747.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2191, pruned_loss=0.03785, over 971414.27 frames.], batch size: 16, lr: 2.98e-04
2022-05-05 19:27:34,426 INFO [train.py:715] (4/8) Epoch 7, batch 7900, loss[loss=0.1519, simple_loss=0.2281, pruned_loss=0.03789, over 4965.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2192, pruned_loss=0.03801, over 972149.98 frames.], batch size: 24, lr: 2.98e-04
2022-05-05 19:28:13,175 INFO [train.py:715] (4/8) Epoch 7, batch 7950, loss[loss=0.1372, simple_loss=0.204, pruned_loss=0.03518, over 4911.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2191, pruned_loss=0.03787, over 972366.21 frames.], batch size: 29, lr: 2.98e-04
2022-05-05 19:28:52,648 INFO [train.py:715] (4/8) Epoch 7, batch 8000, loss[loss=0.1448, simple_loss=0.2102, pruned_loss=0.03968, over 4824.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2176, pruned_loss=0.03713, over 971035.06 frames.], batch size: 25, lr: 2.98e-04
2022-05-05 19:29:30,737 INFO [train.py:715] (4/8) Epoch 7, batch 8050, loss[loss=0.1511, simple_loss=0.2259, pruned_loss=0.0381, over 4747.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.03704, over 971190.85 frames.], batch size: 19, lr: 2.98e-04
2022-05-05 19:30:09,297 INFO [train.py:715] (4/8) Epoch 7, batch 8100, loss[loss=0.1367, simple_loss=0.1968, pruned_loss=0.03829, over 4985.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2176, pruned_loss=0.03729, over 971181.37 frames.], batch size: 25, lr: 2.98e-04
2022-05-05 19:30:48,379 INFO [train.py:715] (4/8) Epoch 7, batch 8150, loss[loss=0.1663, simple_loss=0.2282, pruned_loss=0.05218, over 4846.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2174, pruned_loss=0.03742, over 971202.34 frames.], batch size: 32, lr: 2.98e-04
2022-05-05 19:31:26,679 INFO [train.py:715] (4/8) Epoch 7, batch 8200, loss[loss=0.1518, simple_loss=0.2239, pruned_loss=0.03981, over 4805.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03714, over 971093.29 frames.], batch size: 21, lr: 2.98e-04
2022-05-05 19:32:05,127 INFO [train.py:715] (4/8) Epoch 7, batch 8250, loss[loss=0.1494, simple_loss=0.2306, pruned_loss=0.03411, over 4983.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03704, over 971329.85 frames.], batch size: 25, lr: 2.98e-04
2022-05-05 19:32:43,780 INFO [train.py:715] (4/8) Epoch 7, batch 8300, loss[loss=0.1236, simple_loss=0.2124, pruned_loss=0.0174, over 4909.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03685, over 971719.83 frames.], batch size: 22, lr: 2.98e-04
2022-05-05 19:33:22,690 INFO [train.py:715] (4/8) Epoch 7, batch 8350, loss[loss=0.1534, simple_loss=0.2228, pruned_loss=0.042, over 4728.00 frames.], tot_loss[loss=0.1456, simple_loss=0.217, pruned_loss=0.03705, over 970874.20 frames.], batch size: 16, lr: 2.98e-04
2022-05-05 19:34:00,644 INFO [train.py:715] (4/8) Epoch 7, batch 8400, loss[loss=0.1211, simple_loss=0.1951, pruned_loss=0.02354, over 4751.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2182, pruned_loss=0.03733, over 971123.94 frames.], batch size: 19, lr: 2.98e-04
2022-05-05 19:34:39,718 INFO [train.py:715] (4/8) Epoch 7, batch 8450, loss[loss=0.1835, simple_loss=0.2521, pruned_loss=0.0574, over 4843.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2184, pruned_loss=0.03762, over 971373.21 frames.], batch size: 32, lr: 2.98e-04
2022-05-05 19:35:18,878 INFO [train.py:715] (4/8) Epoch 7, batch 8500, loss[loss=0.1549, simple_loss=0.2272, pruned_loss=0.0413, over 4942.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2187, pruned_loss=0.03796, over 970468.80 frames.], batch size: 23, lr: 2.98e-04
2022-05-05 19:35:58,055 INFO [train.py:715] (4/8) Epoch 7, batch 8550, loss[loss=0.1572, simple_loss=0.2287, pruned_loss=0.04282, over 4802.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2191, pruned_loss=0.03809, over 972062.70 frames.], batch size: 24, lr: 2.97e-04
2022-05-05 19:36:36,295 INFO [train.py:715] (4/8) Epoch 7, batch 8600, loss[loss=0.1629, simple_loss=0.2305, pruned_loss=0.04768, over 4869.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2193, pruned_loss=0.03803, over 971514.76 frames.], batch size: 16, lr: 2.97e-04
2022-05-05 19:37:14,984 INFO [train.py:715] (4/8) Epoch 7, batch 8650, loss[loss=0.1533, simple_loss=0.2171, pruned_loss=0.04478, over 4839.00 frames.], tot_loss[loss=0.1476, simple_loss=0.219, pruned_loss=0.03809, over 971322.39 frames.], batch size: 30, lr: 2.97e-04
2022-05-05 19:37:54,309 INFO [train.py:715] (4/8) Epoch 7, batch 8700, loss[loss=0.1227, simple_loss=0.1988, pruned_loss=0.02327, over 4838.00 frames.], tot_loss[loss=0.1478, simple_loss=0.219, pruned_loss=0.03828, over 971488.42 frames.], batch size: 12, lr: 2.97e-04
2022-05-05 19:38:32,517 INFO [train.py:715] (4/8) Epoch 7, batch 8750, loss[loss=0.1536, simple_loss=0.2316, pruned_loss=0.03782, over 4806.00 frames.], tot_loss[loss=0.1468, simple_loss=0.218, pruned_loss=0.03782, over 971419.62 frames.], batch size: 21, lr: 2.97e-04
2022-05-05 19:39:11,385 INFO [train.py:715] (4/8) Epoch 7, batch 8800, loss[loss=0.1786, simple_loss=0.2401, pruned_loss=0.05854, over 4896.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2182, pruned_loss=0.03798, over 972631.09 frames.], batch size: 38, lr: 2.97e-04
2022-05-05 19:39:50,320 INFO [train.py:715] (4/8) Epoch 7, batch 8850, loss[loss=0.1244, simple_loss=0.2036, pruned_loss=0.0226, over 4764.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2176, pruned_loss=0.03748, over 972804.13 frames.], batch size: 18, lr: 2.97e-04
2022-05-05 19:40:30,008 INFO [train.py:715] (4/8) Epoch 7, batch 8900, loss[loss=0.1411, simple_loss=0.2163, pruned_loss=0.03293, over 4809.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2174, pruned_loss=0.03742, over 973637.02 frames.], batch size: 21, lr: 2.97e-04
2022-05-05 19:41:08,238 INFO [train.py:715] (4/8) Epoch 7, batch 8950, loss[loss=0.1572, simple_loss=0.2351, pruned_loss=0.03961, over 4727.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2179, pruned_loss=0.03757, over 973375.54 frames.], batch size: 16, lr: 2.97e-04
2022-05-05 19:41:46,836 INFO [train.py:715] (4/8) Epoch 7, batch 9000, loss[loss=0.1872, simple_loss=0.2348, pruned_loss=0.06977, over 4851.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2179, pruned_loss=0.03774, over 973868.37 frames.], batch size: 32, lr: 2.97e-04
2022-05-05 19:41:46,836 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 19:41:56,558 INFO [train.py:742] (4/8) Epoch 7, validation: loss=0.1085, simple_loss=0.1932, pruned_loss=0.01192, over 914524.00 frames.
2022-05-05 19:42:35,335 INFO [train.py:715] (4/8) Epoch 7, batch 9050, loss[loss=0.1506, simple_loss=0.2138, pruned_loss=0.04374, over 4966.00 frames.], tot_loss[loss=0.146, simple_loss=0.2176, pruned_loss=0.03724, over 973870.75 frames.], batch size: 15, lr: 2.97e-04
2022-05-05 19:43:15,395 INFO [train.py:715] (4/8) Epoch 7, batch 9100, loss[loss=0.1544, simple_loss=0.2198, pruned_loss=0.04449, over 4980.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2185, pruned_loss=0.03758, over 973692.58 frames.], batch size: 14, lr: 2.97e-04
2022-05-05 19:43:54,072 INFO [train.py:715] (4/8) Epoch 7, batch 9150, loss[loss=0.1675, simple_loss=0.2438, pruned_loss=0.04558, over 4930.00 frames.], tot_loss[loss=0.1471, simple_loss=0.219, pruned_loss=0.03757, over 974092.16 frames.], batch size: 39, lr: 2.97e-04
2022-05-05 19:44:32,871 INFO [train.py:715] (4/8) Epoch 7, batch 9200, loss[loss=0.1695, simple_loss=0.23, pruned_loss=0.05453, over 4925.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2189, pruned_loss=0.03745, over 973237.31 frames.], batch size: 39, lr: 2.97e-04
2022-05-05 19:45:12,203 INFO [train.py:715] (4/8) Epoch 7, batch 9250, loss[loss=0.1423, simple_loss=0.2149, pruned_loss=0.03488, over 4945.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2191, pruned_loss=0.03763, over 973742.36 frames.], batch size: 21, lr: 2.97e-04
2022-05-05 19:45:51,290 INFO [train.py:715] (4/8) Epoch 7, batch 9300, loss[loss=0.1447, simple_loss=0.214, pruned_loss=0.03771, over 4804.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2189, pruned_loss=0.03765, over 973462.93 frames.], batch size: 21, lr: 2.97e-04
2022-05-05 19:46:30,345 INFO [train.py:715] (4/8) Epoch 7, batch 9350, loss[loss=0.1494, simple_loss=0.2235, pruned_loss=0.0376, over 4915.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2191, pruned_loss=0.03787, over 973274.67 frames.], batch size: 23, lr: 2.97e-04
2022-05-05 19:47:08,480 INFO [train.py:715] (4/8) Epoch 7, batch 9400, loss[loss=0.1268, simple_loss=0.1986, pruned_loss=0.02748, over 4773.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2188, pruned_loss=0.03784, over 972395.96 frames.], batch size: 19, lr: 2.97e-04
2022-05-05 19:47:48,273 INFO [train.py:715] (4/8) Epoch 7, batch 9450, loss[loss=0.1222, simple_loss=0.2026, pruned_loss=0.02089, over 4941.00 frames.], tot_loss[loss=0.147, simple_loss=0.2187, pruned_loss=0.03763, over 972072.71 frames.], batch size: 21, lr: 2.97e-04
2022-05-05 19:48:27,273 INFO [train.py:715] (4/8) Epoch 7, batch 9500, loss[loss=0.1178, simple_loss=0.1897, pruned_loss=0.02292, over 4743.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2173, pruned_loss=0.03679, over 972146.66 frames.], batch size: 12, lr: 2.97e-04
2022-05-05 19:49:05,879 INFO [train.py:715] (4/8) Epoch 7, batch 9550, loss[loss=0.1244, simple_loss=0.1961, pruned_loss=0.02637, over 4765.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2166, pruned_loss=0.03639, over 972342.43 frames.], batch size: 12, lr: 2.97e-04
2022-05-05 19:49:44,835 INFO [train.py:715] (4/8) Epoch 7, batch 9600, loss[loss=0.193, simple_loss=0.2517, pruned_loss=0.06717, over 4958.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03717, over 971941.76 frames.], batch size: 24, lr: 2.97e-04
2022-05-05 19:50:23,438 INFO [train.py:715] (4/8) Epoch 7, batch 9650, loss[loss=0.1629, simple_loss=0.2233, pruned_loss=0.05126, over 4793.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2182, pruned_loss=0.03754, over 972116.86 frames.], batch size: 21, lr: 2.97e-04
2022-05-05 19:51:02,958 INFO [train.py:715] (4/8) Epoch 7, batch 9700, loss[loss=0.1598, simple_loss=0.2197, pruned_loss=0.04995, over 4863.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2181, pruned_loss=0.03709, over 971355.43 frames.], batch size: 39, lr: 2.97e-04
2022-05-05 19:51:41,571 INFO [train.py:715] (4/8) Epoch 7, batch 9750, loss[loss=0.1536, simple_loss=0.2202, pruned_loss=0.04351, over 4866.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.03723, over 972351.92 frames.], batch size: 32, lr: 2.97e-04
2022-05-05 19:52:20,963 INFO [train.py:715] (4/8) Epoch 7, batch 9800, loss[loss=0.1289, simple_loss=0.2071, pruned_loss=0.02537, over 4968.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2188, pruned_loss=0.03786, over 972765.71 frames.], batch size: 24, lr: 2.97e-04
2022-05-05 19:52:59,041 INFO [train.py:715] (4/8) Epoch 7, batch 9850, loss[loss=0.1521, simple_loss=0.2232, pruned_loss=0.04053, over 4919.00 frames.], tot_loss[loss=0.1475, simple_loss=0.2194, pruned_loss=0.03784, over 972753.40 frames.], batch size: 18, lr: 2.97e-04
2022-05-05 19:53:37,272 INFO [train.py:715] (4/8) Epoch 7, batch 9900, loss[loss=0.1434, simple_loss=0.2218, pruned_loss=0.03247, over 4934.00 frames.], tot_loss[loss=0.1466, simple_loss=0.219, pruned_loss=0.03713, over 973406.59 frames.], batch size: 23, lr: 2.97e-04
2022-05-05 19:54:16,173 INFO [train.py:715] (4/8) Epoch 7, batch 9950, loss[loss=0.1355, simple_loss=0.2075, pruned_loss=0.03172, over 4987.00 frames.], tot_loss[loss=0.146, simple_loss=0.2183, pruned_loss=0.03686, over 973337.43 frames.], batch size: 28, lr: 2.97e-04
2022-05-05 19:54:55,287 INFO [train.py:715] (4/8) Epoch 7, batch 10000, loss[loss=0.1306, simple_loss=0.2012, pruned_loss=0.03002, over 4933.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03719, over 973803.99 frames.], batch size: 29, lr: 2.97e-04
2022-05-05 19:55:33,942 INFO [train.py:715] (4/8) Epoch 7, batch 10050, loss[loss=0.1291, simple_loss=0.2087, pruned_loss=0.02474, over 4797.00 frames.], tot_loss[loss=0.145, simple_loss=0.2171, pruned_loss=0.03642, over 974241.44 frames.], batch size: 24, lr: 2.97e-04
2022-05-05 19:56:12,505 INFO [train.py:715] (4/8) Epoch 7, batch 10100, loss[loss=0.1556, simple_loss=0.2273, pruned_loss=0.04193, over 4849.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2167, pruned_loss=0.03631, over 973370.01 frames.], batch size: 30, lr: 2.97e-04
2022-05-05 19:56:51,793 INFO [train.py:715] (4/8) Epoch 7, batch 10150, loss[loss=0.1585, simple_loss=0.229, pruned_loss=0.04402, over 4738.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2176, pruned_loss=0.03673, over 973242.98 frames.], batch size: 16, lr: 2.97e-04
2022-05-05 19:57:30,414 INFO [train.py:715] (4/8) Epoch 7, batch 10200, loss[loss=0.167, simple_loss=0.2382, pruned_loss=0.04793, over 4800.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2186, pruned_loss=0.03761, over 973664.41 frames.], batch size: 14, lr: 2.97e-04
2022-05-05 19:58:09,059 INFO [train.py:715] (4/8) Epoch 7, batch 10250, loss[loss=0.1261, simple_loss=0.1969, pruned_loss=0.02763, over 4705.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.0372, over 972676.70 frames.], batch size: 15, lr: 2.96e-04
2022-05-05 19:58:48,250 INFO [train.py:715] (4/8) Epoch 7, batch 10300, loss[loss=0.179, simple_loss=0.2382, pruned_loss=0.05989, over 4980.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2184, pruned_loss=0.03736, over 972323.29 frames.], batch size: 14, lr: 2.96e-04
2022-05-05 19:59:26,901 INFO [train.py:715] (4/8) Epoch 7, batch 10350, loss[loss=0.1318, simple_loss=0.1981, pruned_loss=0.03279, over 4914.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.03726, over 972409.56 frames.], batch size: 23, lr: 2.96e-04
2022-05-05 20:00:05,913 INFO [train.py:715] (4/8) Epoch 7, batch 10400, loss[loss=0.1316, simple_loss=0.2022, pruned_loss=0.03046, over 4984.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2184, pruned_loss=0.03711, over 972715.61 frames.], batch size: 25, lr: 2.96e-04
2022-05-05 20:00:44,696 INFO [train.py:715] (4/8) Epoch 7, batch 10450, loss[loss=0.1186, simple_loss=0.1898, pruned_loss=0.02372, over 4959.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2176, pruned_loss=0.03696, over 972010.53 frames.], batch size: 15, lr: 2.96e-04
2022-05-05 20:01:24,297 INFO [train.py:715] (4/8) Epoch 7, batch 10500, loss[loss=0.1473, simple_loss=0.2123, pruned_loss=0.04113, over 4753.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2182, pruned_loss=0.03736, over 970739.07 frames.], batch size: 19, lr: 2.96e-04
2022-05-05 20:02:03,023 INFO [train.py:715] (4/8) Epoch 7, batch 10550, loss[loss=0.1648, simple_loss=0.246, pruned_loss=0.0418, over 4917.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2178, pruned_loss=0.03754, over 971332.54 frames.], batch size: 18, lr: 2.96e-04
2022-05-05 20:02:41,163 INFO [train.py:715] (4/8) Epoch 7, batch 10600, loss[loss=0.1111, simple_loss=0.1835, pruned_loss=0.0194, over 4891.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2175, pruned_loss=0.03702, over 972226.21 frames.], batch size: 19, lr: 2.96e-04
2022-05-05 20:03:20,355 INFO [train.py:715] (4/8) Epoch 7, batch 10650, loss[loss=0.125, simple_loss=0.1996, pruned_loss=0.0252, over 4786.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03742, over 971737.05 frames.], batch size: 18, lr: 2.96e-04
2022-05-05 20:03:59,389 INFO [train.py:715] (4/8) Epoch 7, batch 10700, loss[loss=0.1495, simple_loss=0.2167, pruned_loss=0.04109, over 4937.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2187, pruned_loss=0.03782, over 971698.73 frames.], batch size: 21, lr: 2.96e-04
2022-05-05 20:04:38,882 INFO [train.py:715] (4/8) Epoch 7, batch 10750, loss[loss=0.1283, simple_loss=0.2045, pruned_loss=0.02605, over 4991.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.03752, over 972130.44 frames.], batch size: 20, lr: 2.96e-04
2022-05-05 20:05:17,666 INFO [train.py:715] (4/8) Epoch 7, batch 10800, loss[loss=0.1549, simple_loss=0.231, pruned_loss=0.0394, over 4745.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2193, pruned_loss=0.03756, over 970828.14 frames.], batch size: 16, lr: 2.96e-04
2022-05-05 20:05:57,425 INFO [train.py:715] (4/8) Epoch 7, batch 10850, loss[loss=0.1603, simple_loss=0.2295, pruned_loss=0.04551, over 4771.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2191, pruned_loss=0.03738, over 970789.41 frames.], batch size: 18, lr: 2.96e-04
2022-05-05 20:06:35,666 INFO [train.py:715] (4/8) Epoch 7, batch 10900, loss[loss=0.1432, simple_loss=0.2183, pruned_loss=0.03412, over 4972.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2188, pruned_loss=0.03668, over 971155.63 frames.], batch size: 15, lr: 2.96e-04
2022-05-05 20:07:14,748 INFO [train.py:715] (4/8) Epoch 7, batch 10950, loss[loss=0.1523, simple_loss=0.2225, pruned_loss=0.04109, over 4911.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2184, pruned_loss=0.03663, over 971932.80 frames.], batch size: 23, lr: 2.96e-04
2022-05-05 20:07:53,907 INFO [train.py:715] (4/8) Epoch 7, batch 11000, loss[loss=0.1412, simple_loss=0.2198, pruned_loss=0.03132, over 4779.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2187, pruned_loss=0.03686, over 971110.43 frames.], batch size: 18, lr: 2.96e-04
2022-05-05 20:08:32,746 INFO [train.py:715] (4/8) Epoch 7, batch 11050, loss[loss=0.1441, simple_loss=0.2198, pruned_loss=0.03422, over 4887.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2181, pruned_loss=0.03654, over 970911.95 frames.], batch size: 17, lr: 2.96e-04
2022-05-05 20:09:11,472 INFO [train.py:715] (4/8) Epoch 7, batch 11100, loss[loss=0.173, simple_loss=0.2555, pruned_loss=0.04525, over 4966.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2182, pruned_loss=0.03674, over 972420.04 frames.], batch size: 39, lr: 2.96e-04
2022-05-05 20:09:50,083 INFO [train.py:715] (4/8) Epoch 7, batch 11150, loss[loss=0.1429, simple_loss=0.2181, pruned_loss=0.03389, over 4968.00 frames.], tot_loss[loss=0.146, simple_loss=0.218, pruned_loss=0.03697, over 971914.02 frames.], batch size: 14, lr: 2.96e-04
2022-05-05 20:10:29,709 INFO [train.py:715] (4/8) Epoch 7, batch 11200, loss[loss=0.132, simple_loss=0.2107, pruned_loss=0.02668, over 4951.00 frames.], tot_loss[loss=0.1458, simple_loss=0.218, pruned_loss=0.03686, over 971241.45 frames.], batch size: 23, lr: 2.96e-04
2022-05-05 20:11:08,077 INFO [train.py:715] (4/8) Epoch 7, batch 11250, loss[loss=0.145, simple_loss=0.2049, pruned_loss=0.0425, over 4740.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2163, pruned_loss=0.03657, over 971604.28 frames.], batch size: 16, lr: 2.96e-04
2022-05-05 20:11:46,233 INFO [train.py:715] (4/8) Epoch 7, batch 11300, loss[loss=0.1557, simple_loss=0.2283, pruned_loss=0.04157, over 4851.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2167, pruned_loss=0.03648, over 971904.12 frames.], batch size: 32, lr: 2.96e-04
2022-05-05 20:12:25,979 INFO [train.py:715] (4/8) Epoch 7, batch 11350, loss[loss=0.1416, simple_loss=0.2038, pruned_loss=0.0397, over 4863.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2171, pruned_loss=0.03668, over 972180.88 frames.], batch size: 13, lr: 2.96e-04
2022-05-05 20:13:04,518 INFO [train.py:715] (4/8) Epoch 7, batch 11400, loss[loss=0.1235, simple_loss=0.1961, pruned_loss=0.0254, over 4917.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2173, pruned_loss=0.03681, over 972601.88 frames.], batch size: 17, lr: 2.96e-04
2022-05-05 20:13:43,555 INFO [train.py:715] (4/8) Epoch 7, batch 11450, loss[loss=0.1432, simple_loss=0.2179, pruned_loss=0.0343, over 4854.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2175, pruned_loss=0.03675, over 973874.30 frames.], batch size: 20, lr: 2.96e-04
2022-05-05 20:14:22,159 INFO [train.py:715] (4/8) Epoch 7, batch 11500, loss[loss=0.1523, simple_loss=0.2258, pruned_loss=0.03939, over 4936.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2173, pruned_loss=0.03691, over 973789.98 frames.], batch size: 21, lr: 2.96e-04
2022-05-05 20:15:01,730 INFO [train.py:715] (4/8) Epoch 7, batch 11550, loss[loss=0.1903, simple_loss=0.2574, pruned_loss=0.06161, over 4707.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2168, pruned_loss=0.0367, over 973730.25 frames.], batch size: 15, lr: 2.96e-04
2022-05-05 20:15:39,999 INFO [train.py:715] (4/8) Epoch 7, batch 11600, loss[loss=0.1334, simple_loss=0.1989, pruned_loss=0.03395, over 4934.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2162, pruned_loss=0.03601, over 972901.05 frames.], batch size: 21, lr: 2.96e-04
2022-05-05 20:16:18,809 INFO [train.py:715] (4/8) Epoch 7, batch 11650, loss[loss=0.1161, simple_loss=0.1938, pruned_loss=0.0192, over 4908.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.036, over 972483.80 frames.], batch size: 19, lr: 2.96e-04
2022-05-05 20:16:58,202 INFO [train.py:715] (4/8) Epoch 7, batch 11700, loss[loss=0.1561, simple_loss=0.2217, pruned_loss=0.04522, over 4841.00 frames.], tot_loss[loss=0.145, simple_loss=0.2173, pruned_loss=0.03633, over 973095.55 frames.], batch size: 30, lr: 2.96e-04
2022-05-05 20:17:36,281 INFO [train.py:715] (4/8) Epoch 7, batch 11750, loss[loss=0.1475, simple_loss=0.2252, pruned_loss=0.03487, over 4823.00 frames.], tot_loss[loss=0.1456, simple_loss=0.218, pruned_loss=0.03659, over 972172.75 frames.], batch size: 27, lr: 2.96e-04
2022-05-05 20:18:15,077 INFO [train.py:715] (4/8) Epoch 7, batch 11800, loss[loss=0.143, simple_loss=0.2191, pruned_loss=0.03348, over 4929.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2172, pruned_loss=0.03678, over 972536.93 frames.], batch size: 18, lr: 2.96e-04
2022-05-05 20:18:54,272 INFO [train.py:715] (4/8) Epoch 7, batch 11850, loss[loss=0.1593, simple_loss=0.2356, pruned_loss=0.04149, over 4855.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03713, over 972600.93 frames.], batch size: 20, lr: 2.96e-04
2022-05-05 20:19:32,626 INFO [train.py:715] (4/8) Epoch 7, batch 11900, loss[loss=0.1289, simple_loss=0.2018, pruned_loss=0.02805, over 4861.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2164, pruned_loss=0.03638, over 972293.45 frames.], batch size: 34, lr: 2.96e-04
2022-05-05 20:20:11,922 INFO [train.py:715] (4/8) Epoch 7, batch 11950, loss[loss=0.1229, simple_loss=0.2023, pruned_loss=0.02172, over 4830.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2173, pruned_loss=0.03719, over 971674.46 frames.], batch size: 27, lr: 2.96e-04
2022-05-05 20:20:50,616 INFO [train.py:715] (4/8) Epoch 7, batch 12000, loss[loss=0.1142, simple_loss=0.1843, pruned_loss=0.02209, over 4830.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2177, pruned_loss=0.03751, over 971444.45 frames.], batch size: 13, lr: 2.95e-04
2022-05-05 20:20:50,616 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 20:21:00,226 INFO [train.py:742] (4/8) Epoch 7, validation: loss=0.108, simple_loss=0.193, pruned_loss=0.01154, over 914524.00 frames.
2022-05-05 20:21:38,893 INFO [train.py:715] (4/8) Epoch 7, batch 12050, loss[loss=0.1746, simple_loss=0.2236, pruned_loss=0.06276, over 4964.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.03703, over 972233.65 frames.], batch size: 14, lr: 2.95e-04
2022-05-05 20:22:18,264 INFO [train.py:715] (4/8) Epoch 7, batch 12100, loss[loss=0.1298, simple_loss=0.1988, pruned_loss=0.03042, over 4967.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2178, pruned_loss=0.03755, over 971932.05 frames.], batch size: 15, lr: 2.95e-04
2022-05-05 20:22:56,856 INFO [train.py:715] (4/8) Epoch 7, batch 12150, loss[loss=0.1213, simple_loss=0.1902, pruned_loss=0.02615, over 4807.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2182, pruned_loss=0.03768, over 972850.43 frames.], batch size: 21, lr: 2.95e-04
2022-05-05 20:23:35,617 INFO [train.py:715] (4/8) Epoch 7, batch 12200, loss[loss=0.1258, simple_loss=0.1984, pruned_loss=0.02657, over 4825.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.0372, over 972748.08 frames.], batch size: 12, lr: 2.95e-04
2022-05-05 20:24:14,744 INFO [train.py:715] (4/8) Epoch 7, batch 12250, loss[loss=0.159, simple_loss=0.232, pruned_loss=0.04295, over 4975.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03685, over 972561.35 frames.], batch size: 35, lr: 2.95e-04
2022-05-05 20:24:53,360 INFO [train.py:715] (4/8) Epoch 7, batch 12300, loss[loss=0.11, simple_loss=0.1832, pruned_loss=0.0184, over 4782.00 frames.], tot_loss[loss=0.1452, simple_loss=0.217, pruned_loss=0.03673, over 971638.87 frames.], batch size: 18, lr: 2.95e-04
2022-05-05 20:25:35,091 INFO [train.py:715] (4/8) Epoch 7, batch 12350, loss[loss=0.1388, simple_loss=0.2026, pruned_loss=0.03745, over 4770.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2172, pruned_loss=0.03682, over 972088.02 frames.], batch size: 19, lr: 2.95e-04
2022-05-05 20:26:13,785 INFO [train.py:715] (4/8) Epoch 7, batch 12400, loss[loss=0.1396, simple_loss=0.2047, pruned_loss=0.03723, over 4863.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.03634, over 972742.48 frames.], batch size: 32, lr: 2.95e-04
2022-05-05 20:26:53,003 INFO [train.py:715] (4/8) Epoch 7, batch 12450, loss[loss=0.1477, simple_loss=0.2178, pruned_loss=0.03879, over 4827.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2172, pruned_loss=0.03664, over 972656.39 frames.], batch size: 30, lr: 2.95e-04
2022-05-05 20:27:31,401 INFO [train.py:715] (4/8) Epoch 7, batch 12500, loss[loss=0.1576, simple_loss=0.229, pruned_loss=0.0431, over 4942.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2174, pruned_loss=0.03682, over 971907.50 frames.], batch size: 35, lr: 2.95e-04
2022-05-05 20:28:10,097 INFO [train.py:715] (4/8) Epoch 7, batch 12550, loss[loss=0.1461, simple_loss=0.2115, pruned_loss=0.04034, over 4790.00 frames.], tot_loss[loss=0.146, simple_loss=0.2178, pruned_loss=0.03713, over 970975.45 frames.], batch size: 14, lr: 2.95e-04
2022-05-05 20:28:49,193 INFO [train.py:715] (4/8) Epoch 7, batch 12600, loss[loss=0.1445, simple_loss=0.22, pruned_loss=0.03446, over 4964.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.03666, over 972097.12 frames.], batch size: 29, lr: 2.95e-04
2022-05-05 20:29:27,376 INFO [train.py:715] (4/8) Epoch 7, batch 12650, loss[loss=0.1493, simple_loss=0.2106, pruned_loss=0.04402, over 4844.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.0372, over 971744.84 frames.], batch size: 30, lr: 2.95e-04
2022-05-05 20:30:06,575 INFO [train.py:715] (4/8) Epoch 7, batch 12700, loss[loss=0.1532, simple_loss=0.2194, pruned_loss=0.04351, over 4938.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2184, pruned_loss=0.03752, over 971214.75 frames.], batch size: 18, lr: 2.95e-04
2022-05-05 20:30:44,740 INFO [train.py:715] (4/8) Epoch 7, batch 12750, loss[loss=0.1331, simple_loss=0.2202, pruned_loss=0.02301, over 4796.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2182, pruned_loss=0.03759, over 972022.31 frames.], batch size: 24, lr: 2.95e-04
2022-05-05 20:31:23,968 INFO [train.py:715] (4/8) Epoch 7, batch 12800, loss[loss=0.1618, simple_loss=0.2265, pruned_loss=0.04853, over 4854.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2181, pruned_loss=0.03788, over 972324.05 frames.], batch size: 30, lr: 2.95e-04
2022-05-05 20:32:02,917 INFO [train.py:715] (4/8) Epoch 7, batch 12850, loss[loss=0.1535, simple_loss=0.2225, pruned_loss=0.04218, over 4796.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2177, pruned_loss=0.03754, over 972180.83 frames.], batch size: 12, lr: 2.95e-04
2022-05-05 20:32:41,509 INFO [train.py:715] (4/8) Epoch 7, batch 12900, loss[loss=0.1734, simple_loss=0.2402, pruned_loss=0.05335, over 4876.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2178, pruned_loss=0.03735, over 972415.97 frames.], batch size: 38, lr: 2.95e-04
2022-05-05 20:33:20,984 INFO [train.py:715] (4/8) Epoch 7, batch 12950, loss[loss=0.1523, simple_loss=0.2167, pruned_loss=0.04395, over 4758.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2183, pruned_loss=0.03768, over 972436.31 frames.], batch size: 14, lr: 2.95e-04
2022-05-05 20:33:59,927 INFO [train.py:715] (4/8) Epoch 7, batch 13000, loss[loss=0.1373, simple_loss=0.2076, pruned_loss=0.03353, over 4751.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03751, over 971957.18 frames.], batch size: 19, lr: 2.95e-04
2022-05-05 20:34:38,878 INFO [train.py:715] (4/8) Epoch 7, batch 13050, loss[loss=0.1548, simple_loss=0.2321, pruned_loss=0.03874, over 4817.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03735, over 971161.35 frames.], batch size: 25, lr: 2.95e-04
2022-05-05 20:35:17,656 INFO [train.py:715] (4/8) Epoch 7, batch 13100, loss[loss=0.1465, simple_loss=0.2232, pruned_loss=0.03487, over 4834.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03753, over 971519.03 frames.], batch size: 26, lr: 2.95e-04
2022-05-05 20:35:57,327 INFO [train.py:715] (4/8) Epoch 7, batch 13150, loss[loss=0.1714, simple_loss=0.2348, pruned_loss=0.054, over 4903.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2192, pruned_loss=0.0381, over 971955.06 frames.], batch size: 38, lr: 2.95e-04
2022-05-05 20:36:35,852 INFO [train.py:715] (4/8) Epoch 7, batch 13200, loss[loss=0.1507, simple_loss=0.2158, pruned_loss=0.04278, over 4964.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2182, pruned_loss=0.03775, over 972193.59 frames.], batch size: 15, lr: 2.95e-04
2022-05-05 20:37:15,484 INFO [train.py:715] (4/8) Epoch 7, batch 13250, loss[loss=0.1335, simple_loss=0.2081, pruned_loss=0.02941, over 4961.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2181, pruned_loss=0.03746, over 972286.13 frames.], batch size: 14, lr: 2.95e-04
2022-05-05 20:37:54,873 INFO [train.py:715] (4/8) Epoch 7, batch 13300, loss[loss=0.1547, simple_loss=0.2298, pruned_loss=0.03976, over 4991.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2185, pruned_loss=0.03746, over 973107.61 frames.], batch size: 16, lr: 2.95e-04
2022-05-05 20:38:33,799 INFO [train.py:715] (4/8) Epoch 7, batch 13350, loss[loss=0.1467, simple_loss=0.2221, pruned_loss=0.03561, over 4768.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2196, pruned_loss=0.03807, over 972642.08 frames.], batch size: 17, lr: 2.95e-04
2022-05-05 20:39:12,814 INFO [train.py:715] (4/8) Epoch 7, batch 13400, loss[loss=0.132, simple_loss=0.209, pruned_loss=0.02748, over 4818.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2194, pruned_loss=0.03802, over 972304.44 frames.], batch size: 26, lr: 2.95e-04
2022-05-05 20:39:51,471 INFO [train.py:715] (4/8) Epoch 7, batch 13450, loss[loss=0.1757, simple_loss=0.2476, pruned_loss=0.05192, over 4982.00 frames.], tot_loss[loss=0.148, simple_loss=0.2197, pruned_loss=0.03812, over 972522.76 frames.], batch size: 39, lr: 2.95e-04
2022-05-05 20:40:30,904 INFO [train.py:715] (4/8) Epoch 7, batch 13500, loss[loss=0.1497, simple_loss=0.2232, pruned_loss=0.03811, over 4779.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2192, pruned_loss=0.0376, over 972514.44 frames.], batch size: 14, lr: 2.95e-04
2022-05-05 20:41:09,549 INFO [train.py:715] (4/8) Epoch 7, batch 13550, loss[loss=0.1894, simple_loss=0.2445, pruned_loss=0.06717, over 4854.00 frames.], tot_loss[loss=0.147, simple_loss=0.2189, pruned_loss=0.03754, over 973562.25 frames.], batch size: 30, lr: 2.95e-04
2022-05-05 20:41:48,024 INFO [train.py:715] (4/8) Epoch 7, batch 13600, loss[loss=0.1248, simple_loss=0.2023, pruned_loss=0.02358, over 4954.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2186, pruned_loss=0.03746, over 972837.40 frames.], batch size: 14, lr: 2.95e-04
2022-05-05 20:42:26,942 INFO [train.py:715] (4/8) Epoch 7, batch 13650, loss[loss=0.1342, simple_loss=0.2106, pruned_loss=0.02885, over 4820.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2182, pruned_loss=0.03713, over 972216.57 frames.], batch size: 27, lr: 2.95e-04
2022-05-05 20:43:05,964 INFO [train.py:715] (4/8) Epoch 7, batch 13700, loss[loss=0.1523, simple_loss=0.2187, pruned_loss=0.04293, over 4827.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2175, pruned_loss=0.03676, over 972513.68 frames.], batch size: 12, lr: 2.95e-04
2022-05-05 20:43:44,944 INFO [train.py:715] (4/8) Epoch 7, batch 13750, loss[loss=0.1495, simple_loss=0.2231, pruned_loss=0.03795, over 4884.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2177, pruned_loss=0.03693, over 972943.58 frames.], batch size: 22, lr: 2.94e-04
2022-05-05 20:44:23,923 INFO [train.py:715] (4/8) Epoch 7, batch 13800, loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.0327, over 4958.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2179, pruned_loss=0.03736, over 973675.81 frames.], batch size: 39, lr: 2.94e-04
2022-05-05 20:45:03,234 INFO [train.py:715] (4/8) Epoch 7, batch 13850, loss[loss=0.1442, simple_loss=0.2184, pruned_loss=0.03502, over 4981.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2182, pruned_loss=0.03729, over 974087.65 frames.], batch size: 25, lr: 2.94e-04
2022-05-05 20:45:41,497 INFO [train.py:715] (4/8) Epoch 7, batch 13900, loss[loss=0.1507, simple_loss=0.2277, pruned_loss=0.03689, over 4778.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2179, pruned_loss=0.03733, over 974816.00 frames.], batch size: 18, lr: 2.94e-04
2022-05-05 20:46:20,519 INFO [train.py:715] (4/8) Epoch 7, batch 13950, loss[loss=0.1263, simple_loss=0.1995, pruned_loss=0.02659, over 4844.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03704, over 975268.33 frames.], batch size: 20, lr: 2.94e-04
2022-05-05 20:46:59,563 INFO [train.py:715] (4/8) Epoch 7, batch 14000, loss[loss=0.1323, simple_loss=0.1988, pruned_loss=0.03286, over 4871.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2182, pruned_loss=0.03725, over 974238.12 frames.], batch size: 32, lr: 2.94e-04
2022-05-05 20:47:38,941 INFO [train.py:715] (4/8) Epoch 7, batch 14050, loss[loss=0.1448, simple_loss=0.2163, pruned_loss=0.03671, over 4937.00 frames.], tot_loss[loss=0.146, simple_loss=0.2177, pruned_loss=0.03712, over 973465.90 frames.], batch size: 29, lr: 2.94e-04
2022-05-05 20:48:18,053 INFO [train.py:715] (4/8) Epoch 7, batch 14100, loss[loss=0.1526, simple_loss=0.224, pruned_loss=0.04063, over 4934.00 frames.], tot_loss[loss=0.1461, simple_loss=0.218, pruned_loss=0.03713, over 973453.51 frames.], batch size: 29, lr: 2.94e-04
2022-05-05 20:48:56,864 INFO [train.py:715] (4/8) Epoch 7, batch 14150, loss[loss=0.1529, simple_loss=0.2296, pruned_loss=0.03809, over 4959.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.0374, over 973367.32 frames.], batch size: 15, lr: 2.94e-04
2022-05-05 20:49:36,152 INFO [train.py:715] (4/8) Epoch 7, batch 14200, loss[loss=0.1589, simple_loss=0.2339, pruned_loss=0.04188, over 4978.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2184, pruned_loss=0.038, over 973228.96 frames.], batch size: 28, lr: 2.94e-04
2022-05-05 20:50:14,409 INFO [train.py:715] (4/8) Epoch 7, batch 14250, loss[loss=0.1579, simple_loss=0.2241, pruned_loss=0.04581, over 4914.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2185, pruned_loss=0.03817, over 973987.51 frames.], batch size: 39, lr: 2.94e-04
2022-05-05 20:50:53,729 INFO [train.py:715] (4/8) Epoch 7, batch 14300, loss[loss=0.1432, simple_loss=0.2177, pruned_loss=0.0343, over 4735.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2182, pruned_loss=0.03755, over 973489.30 frames.], batch size: 12, lr: 2.94e-04
2022-05-05 20:51:33,015 INFO [train.py:715] (4/8) Epoch 7, batch 14350, loss[loss=0.1444, simple_loss=0.2169, pruned_loss=0.03595, over 4949.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2182, pruned_loss=0.03764, over 973009.94 frames.], batch size: 35, lr: 2.94e-04
2022-05-05 20:52:12,027 INFO [train.py:715] (4/8) Epoch 7, batch 14400, loss[loss=0.1257, simple_loss=0.1967, pruned_loss=0.02738, over 4990.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2194, pruned_loss=0.03797, over 973503.00 frames.], batch size: 31, lr: 2.94e-04
2022-05-05 20:52:50,741 INFO [train.py:715] (4/8) Epoch 7, batch 14450, loss[loss=0.1638, simple_loss=0.2421, pruned_loss=0.04273, over 4916.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2197, pruned_loss=0.038, over 973924.02 frames.], batch size: 18, lr: 2.94e-04
2022-05-05 20:53:29,523 INFO [train.py:715] (4/8) Epoch 7, batch 14500, loss[loss=0.1191, simple_loss=0.1884, pruned_loss=0.02494, over 4764.00 frames.], tot_loss[loss=0.1482, simple_loss=0.22, pruned_loss=0.03823, over 973406.60 frames.], batch size: 12, lr: 2.94e-04
2022-05-05 20:54:09,102 INFO [train.py:715] (4/8) Epoch 7, batch 14550, loss[loss=0.1175, simple_loss=0.1965, pruned_loss=0.01928, over 4754.00 frames.], tot_loss[loss=0.1481, simple_loss=0.22, pruned_loss=0.03811, over 973227.19 frames.], batch size: 16, lr: 2.94e-04
2022-05-05 20:54:47,909 INFO [train.py:715] (4/8) Epoch 7, batch 14600, loss[loss=0.1518, simple_loss=0.2252, pruned_loss=0.03922, over 4798.00 frames.], tot_loss[loss=0.1482, simple_loss=0.2199, pruned_loss=0.03827, over 974297.52 frames.], batch size: 17, lr: 2.94e-04
2022-05-05 20:55:26,849 INFO [train.py:715] (4/8) Epoch 7, batch 14650, loss[loss=0.1351, simple_loss=0.2142, pruned_loss=0.02807, over 4897.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2191, pruned_loss=0.03777, over 973630.02 frames.], batch size: 17, lr: 2.94e-04
2022-05-05 20:56:05,813 INFO [train.py:715] (4/8) Epoch 7, batch 14700, loss[loss=0.1427, simple_loss=0.21, pruned_loss=0.03773, over 4768.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.03727, over 973719.74 frames.], batch size: 18, lr: 2.94e-04
2022-05-05 20:56:44,942 INFO [train.py:715] (4/8) Epoch 7, batch 14750, loss[loss=0.1579, simple_loss=0.2271, pruned_loss=0.04433, over 4829.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2187, pruned_loss=0.03778, over 973463.71 frames.], batch size: 26, lr: 2.94e-04
2022-05-05 20:57:23,494 INFO [train.py:715] (4/8) Epoch 7, batch 14800, loss[loss=0.1411, simple_loss=0.2206, pruned_loss=0.03082, over 4835.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2189, pruned_loss=0.03774, over 973220.36 frames.], batch size: 15, lr: 2.94e-04
2022-05-05 20:58:03,001 INFO [train.py:715] (4/8) Epoch 7, batch 14850, loss[loss=0.1259, simple_loss=0.1997, pruned_loss=0.02603, over 4848.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2188, pruned_loss=0.03778, over 972749.26 frames.], batch size: 12, lr: 2.94e-04
2022-05-05 20:58:41,953 INFO [train.py:715] (4/8) Epoch 7, batch 14900, loss[loss=0.1543, simple_loss=0.2221, pruned_loss=0.04325, over 4979.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2183, pruned_loss=0.03778, over 973550.56 frames.], batch size: 15, lr: 2.94e-04
2022-05-05 20:59:20,317 INFO [train.py:715] (4/8) Epoch 7, batch 14950, loss[loss=0.1518, simple_loss=0.2286, pruned_loss=0.03754, over 4988.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2171, pruned_loss=0.03718, over 974383.20 frames.], batch size: 25, lr: 2.94e-04
2022-05-05 20:59:59,927 INFO [train.py:715] (4/8) Epoch 7, batch 15000, loss[loss=0.1518, simple_loss=0.221, pruned_loss=0.04126, over 4777.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2158, pruned_loss=0.0366, over 972575.59 frames.], batch size: 14, lr: 2.94e-04
2022-05-05 20:59:59,927 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 21:00:14,353 INFO [train.py:742] (4/8) Epoch 7, validation: loss=0.1083, simple_loss=0.1931, pruned_loss=0.01175, over 914524.00 frames.
2022-05-05 21:00:53,497 INFO [train.py:715] (4/8) Epoch 7, batch 15050, loss[loss=0.1316, simple_loss=0.2045, pruned_loss=0.02928, over 4936.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2159, pruned_loss=0.03652, over 972952.04 frames.], batch size: 23, lr: 2.94e-04
2022-05-05 21:01:32,730 INFO [train.py:715] (4/8) Epoch 7, batch 15100, loss[loss=0.1875, simple_loss=0.2467, pruned_loss=0.06412, over 4923.00 frames.], tot_loss[loss=0.1458, simple_loss=0.217, pruned_loss=0.03734, over 972926.84 frames.], batch size: 18, lr: 2.94e-04
2022-05-05 21:02:11,969 INFO [train.py:715] (4/8) Epoch 7, batch 15150, loss[loss=0.1433, simple_loss=0.2073, pruned_loss=0.03962, over 4856.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2169, pruned_loss=0.03745, over 972427.02 frames.], batch size: 20, lr: 2.94e-04
2022-05-05 21:02:50,724 INFO [train.py:715] (4/8) Epoch 7, batch 15200, loss[loss=0.1343, simple_loss=0.2103, pruned_loss=0.02914, over 4705.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2166, pruned_loss=0.0365, over 971661.97 frames.], batch size: 15, lr: 2.94e-04
2022-05-05 21:03:30,197 INFO [train.py:715] (4/8) Epoch 7, batch 15250, loss[loss=0.1608, simple_loss=0.2185, pruned_loss=0.05158, over 4774.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2173, pruned_loss=0.03665, over 970706.08 frames.], batch size: 14, lr: 2.94e-04
2022-05-05 21:04:09,391 INFO [train.py:715] (4/8) Epoch 7, batch 15300, loss[loss=0.1426, simple_loss=0.2253, pruned_loss=0.02993, over 4698.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2169, pruned_loss=0.03635, over 970096.07 frames.], batch size: 15, lr: 2.94e-04
2022-05-05 21:04:48,396 INFO [train.py:715] (4/8) Epoch 7, batch 15350, loss[loss=0.1512, simple_loss=0.2277, pruned_loss=0.03735, over 4787.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2172, pruned_loss=0.03646, over 970582.60 frames.], batch size: 17, lr: 2.94e-04
2022-05-05 21:05:27,506 INFO [train.py:715] (4/8) Epoch 7, batch 15400, loss[loss=0.1334, simple_loss=0.2019, pruned_loss=0.03248, over 4639.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2181, pruned_loss=0.03691, over 970812.50 frames.], batch size: 13, lr: 2.94e-04
2022-05-05 21:06:05,997 INFO [train.py:715] (4/8) Epoch 7, batch 15450, loss[loss=0.16, simple_loss=0.2403, pruned_loss=0.03988, over 4963.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2189, pruned_loss=0.03723, over 970862.81 frames.], batch size: 15, lr: 2.94e-04
2022-05-05 21:06:45,044 INFO [train.py:715] (4/8) Epoch 7, batch 15500, loss[loss=0.1428, simple_loss=0.2163, pruned_loss=0.03464, over 4915.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2182, pruned_loss=0.03708, over 971117.10 frames.], batch size: 17, lr: 2.93e-04
2022-05-05 21:07:23,167 INFO [train.py:715] (4/8) Epoch 7, batch 15550, loss[loss=0.1089, simple_loss=0.1863, pruned_loss=0.01573, over 4925.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.0367, over 970911.68 frames.], batch size: 18, lr: 2.93e-04
2022-05-05 21:08:02,567 INFO [train.py:715] (4/8) Epoch 7, batch 15600, loss[loss=0.1386, simple_loss=0.2183, pruned_loss=0.02943, over 4903.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2177, pruned_loss=0.03692, over 971253.91 frames.], batch size: 17, lr: 2.93e-04
2022-05-05 21:08:42,087 INFO [train.py:715] (4/8) Epoch 7, batch 15650, loss[loss=0.1298, simple_loss=0.2016, pruned_loss=0.02898, over 4809.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2174, pruned_loss=0.03691, over 971917.79 frames.], batch size: 24, lr: 2.93e-04
2022-05-05 21:09:20,365 INFO [train.py:715] (4/8) Epoch 7, batch 15700, loss[loss=0.1327, simple_loss=0.201, pruned_loss=0.03217, over 4799.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2177, pruned_loss=0.03698, over 970596.24 frames.], batch size: 12, lr: 2.93e-04
2022-05-05 21:09:59,352 INFO [train.py:715] (4/8) Epoch 7, batch 15750, loss[loss=0.1443, simple_loss=0.2125, pruned_loss=0.038, over 4985.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.03719, over 970868.90 frames.], batch size: 39, lr: 2.93e-04
2022-05-05 21:10:39,021 INFO [train.py:715] (4/8) Epoch 7, batch 15800, loss[loss=0.1349, simple_loss=0.2038, pruned_loss=0.03301, over 4862.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03719, over 970301.47 frames.], batch size: 12, lr: 2.93e-04
2022-05-05 21:11:18,132 INFO [train.py:715] (4/8) Epoch 7, batch 15850, loss[loss=0.1595, simple_loss=0.2315, pruned_loss=0.04373, over 4973.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2181, pruned_loss=0.03776, over 971061.68 frames.], batch size: 28, lr: 2.93e-04
2022-05-05 21:11:57,176 INFO [train.py:715] (4/8) Epoch 7, batch 15900, loss[loss=0.1732, simple_loss=0.2443, pruned_loss=0.05106, over 4821.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2183, pruned_loss=0.03829, over 970279.83 frames.], batch size: 15, lr: 2.93e-04
2022-05-05 21:12:36,478 INFO [train.py:715] (4/8) Epoch 7, batch 15950, loss[loss=0.1744, simple_loss=0.2413, pruned_loss=0.05374, over 4752.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2184, pruned_loss=0.0382, over 970376.17 frames.], batch size: 19, lr: 2.93e-04
2022-05-05 21:13:15,927 INFO [train.py:715] (4/8) Epoch 7, batch 16000, loss[loss=0.1327, simple_loss=0.2092, pruned_loss=0.0281, over 4816.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2177, pruned_loss=0.03779, over 970453.90 frames.], batch size: 27, lr: 2.93e-04
2022-05-05 21:13:54,028 INFO [train.py:715] (4/8) Epoch 7, batch 16050, loss[loss=0.1262, simple_loss=0.2027, pruned_loss=0.02487, over 4814.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2179, pruned_loss=0.03733, over 970378.07 frames.], batch size: 21, lr: 2.93e-04
2022-05-05 21:14:33,357 INFO [train.py:715] (4/8) Epoch 7, batch 16100, loss[loss=0.1288, simple_loss=0.1958, pruned_loss=0.03085, over 4744.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2183, pruned_loss=0.03729, over 969983.43 frames.], batch size: 16, lr: 2.93e-04
2022-05-05 21:15:12,281 INFO [train.py:715] (4/8) Epoch 7, batch 16150, loss[loss=0.136, simple_loss=0.204, pruned_loss=0.03394, over 4966.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2175, pruned_loss=0.03678, over 969941.09 frames.], batch size: 39, lr: 2.93e-04
2022-05-05 21:15:50,930 INFO [train.py:715] (4/8) Epoch 7, batch 16200, loss[loss=0.1721, simple_loss=0.2323, pruned_loss=0.05597, over 4928.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.0372, over 970095.35 frames.], batch size: 18, lr: 2.93e-04
2022-05-05 21:16:30,079 INFO [train.py:715] (4/8) Epoch 7, batch 16250, loss[loss=0.1281, simple_loss=0.2075, pruned_loss=0.02433, over 4964.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2185, pruned_loss=0.03732, over 971014.57 frames.], batch size: 14, lr: 2.93e-04
2022-05-05 21:17:08,725 INFO [train.py:715] (4/8) Epoch 7, batch 16300, loss[loss=0.1397, simple_loss=0.2175, pruned_loss=0.03098, over 4783.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2179, pruned_loss=0.03683, over 971634.76 frames.], batch size: 18, lr: 2.93e-04
2022-05-05 21:17:48,273 INFO [train.py:715] (4/8) Epoch 7, batch 16350, loss[loss=0.1724, simple_loss=0.2387, pruned_loss=0.05306, over 4862.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2183, pruned_loss=0.03702, over 972128.98 frames.], batch size: 20, lr: 2.93e-04
2022-05-05 21:18:26,609 INFO [train.py:715] (4/8) Epoch 7, batch 16400, loss[loss=0.1252, simple_loss=0.197, pruned_loss=0.02672, over 4745.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2191, pruned_loss=0.03813, over 972281.47 frames.], batch size: 19, lr: 2.93e-04
2022-05-05 21:19:05,500 INFO [train.py:715] (4/8) Epoch 7, batch 16450, loss[loss=0.1366, simple_loss=0.2132, pruned_loss=0.02997, over 4806.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2179, pruned_loss=0.03725, over 972214.86 frames.], batch size: 21, lr: 2.93e-04
2022-05-05 21:19:44,555 INFO [train.py:715] (4/8) Epoch 7, batch 16500, loss[loss=0.155, simple_loss=0.2267, pruned_loss=0.04168, over 4915.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2184, pruned_loss=0.03773, over 971890.91 frames.], batch size: 39, lr: 2.93e-04
2022-05-05 21:20:22,828 INFO [train.py:715] (4/8) Epoch 7, batch 16550, loss[loss=0.171, simple_loss=0.2414, pruned_loss=0.05032, over 4928.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2188, pruned_loss=0.03798, over 972877.76 frames.], batch size: 39, lr: 2.93e-04
2022-05-05 21:21:02,226 INFO [train.py:715] (4/8) Epoch 7, batch 16600, loss[loss=0.118, simple_loss=0.1898, pruned_loss=0.0231, over 4831.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2183, pruned_loss=0.03744, over 972988.26 frames.], batch size: 26, lr: 2.93e-04
2022-05-05 21:21:41,397 INFO [train.py:715] (4/8) Epoch 7, batch 16650, loss[loss=0.1087, simple_loss=0.1836, pruned_loss=0.01691, over 4912.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2171, pruned_loss=0.03707, over 973215.39 frames.], batch size: 17, lr: 2.93e-04
2022-05-05 21:22:20,542 INFO [train.py:715] (4/8) Epoch 7, batch 16700, loss[loss=0.1516, simple_loss=0.2345, pruned_loss=0.03442, over 4798.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2177, pruned_loss=0.03771, over 973349.14 frames.], batch size: 21, lr: 2.93e-04
2022-05-05 21:22:59,811 INFO [train.py:715] (4/8) Epoch 7, batch 16750, loss[loss=0.1639, simple_loss=0.2343, pruned_loss=0.04678, over 4900.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2179, pruned_loss=0.03785, over 972897.44 frames.], batch size: 19, lr: 2.93e-04
2022-05-05 21:23:38,669 INFO [train.py:715] (4/8) Epoch 7, batch 16800, loss[loss=0.1555, simple_loss=0.2394, pruned_loss=0.03581, over 4942.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2168, pruned_loss=0.03708, over 972789.37 frames.], batch size: 23, lr: 2.93e-04
2022-05-05 21:24:17,715 INFO [train.py:715] (4/8) Epoch 7, batch 16850, loss[loss=0.1722, simple_loss=0.2258, pruned_loss=0.05934, over 4897.00 frames.], tot_loss[loss=0.1448, simple_loss=0.216, pruned_loss=0.03676, over 972706.77 frames.], batch size: 19, lr: 2.93e-04
2022-05-05 21:24:57,016 INFO [train.py:715] (4/8) Epoch 7, batch 16900, loss[loss=0.1857, simple_loss=0.2705, pruned_loss=0.05044, over 4744.00 frames.], tot_loss[loss=0.145, simple_loss=0.2165, pruned_loss=0.03674, over 972344.90 frames.], batch size: 16, lr: 2.93e-04
2022-05-05 21:25:36,247 INFO [train.py:715] (4/8) Epoch 7, batch 16950, loss[loss=0.1417, simple_loss=0.2146, pruned_loss=0.03438, over 4941.00 frames.], tot_loss[loss=0.1443, simple_loss=0.216, pruned_loss=0.03632, over 973199.25 frames.], batch size: 21, lr: 2.93e-04
2022-05-05 21:26:14,897 INFO [train.py:715] (4/8) Epoch 7, batch 17000, loss[loss=0.1562, simple_loss=0.2354, pruned_loss=0.03852, over 4806.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.03634, over 973447.78 frames.], batch size: 21, lr: 2.93e-04
2022-05-05 21:26:54,053 INFO [train.py:715] (4/8) Epoch 7, batch 17050, loss[loss=0.1418, simple_loss=0.22, pruned_loss=0.03175, over 4703.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2167, pruned_loss=0.03638, over 972686.42 frames.], batch size: 15, lr: 2.93e-04
2022-05-05 21:27:32,507 INFO [train.py:715] (4/8) Epoch 7, batch 17100, loss[loss=0.1423, simple_loss=0.2178, pruned_loss=0.0334, over 4934.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2174, pruned_loss=0.03656, over 972904.95 frames.], batch size: 21, lr: 2.93e-04
2022-05-05 21:28:11,644 INFO [train.py:715] (4/8) Epoch 7, batch 17150, loss[loss=0.1509, simple_loss=0.2217, pruned_loss=0.03999, over 4772.00 frames.], tot_loss[loss=0.145, simple_loss=0.2175, pruned_loss=0.03624, over 973029.26 frames.], batch size: 18, lr: 2.93e-04
2022-05-05 21:28:50,898 INFO [train.py:715] (4/8) Epoch 7, batch 17200, loss[loss=0.1695, simple_loss=0.2422, pruned_loss=0.04842, over 4958.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2176, pruned_loss=0.03638, over 973206.60 frames.], batch size: 21, lr: 2.93e-04
2022-05-05 21:29:29,221 INFO [train.py:715] (4/8) Epoch 7, batch 17250, loss[loss=0.1293, simple_loss=0.2145, pruned_loss=0.02208, over 4957.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2174, pruned_loss=0.03651, over 973461.74 frames.], batch size: 21, lr: 2.92e-04
2022-05-05 21:30:08,294 INFO [train.py:715] (4/8) Epoch 7, batch 17300, loss[loss=0.1537, simple_loss=0.2272, pruned_loss=0.04008, over 4823.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2178, pruned_loss=0.03652, over 972614.18 frames.], batch size: 27, lr: 2.92e-04
2022-05-05 21:30:46,576 INFO [train.py:715] (4/8) Epoch 7, batch 17350, loss[loss=0.1377, simple_loss=0.2158, pruned_loss=0.02977, over 4788.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2176, pruned_loss=0.03636, over 972699.72 frames.], batch size: 24, lr: 2.92e-04
2022-05-05 21:31:25,651 INFO [train.py:715] (4/8) Epoch 7, batch 17400, loss[loss=0.1304, simple_loss=0.212, pruned_loss=0.02443, over 4804.00 frames.], tot_loss[loss=0.145, simple_loss=0.2173, pruned_loss=0.03632, over 972716.97 frames.], batch size: 21, lr: 2.92e-04
2022-05-05 21:32:04,440 INFO [train.py:715] (4/8) Epoch 7, batch 17450, loss[loss=0.118, simple_loss=0.1936, pruned_loss=0.02125, over 4745.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2179, pruned_loss=0.03679, over 972864.36 frames.], batch size: 19, lr: 2.92e-04
2022-05-05 21:32:43,221 INFO [train.py:715] (4/8) Epoch 7, batch 17500, loss[loss=0.1316, simple_loss=0.2046, pruned_loss=0.02929, over 4934.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2176, pruned_loss=0.03632, over 973327.23 frames.], batch size: 24, lr: 2.92e-04
2022-05-05 21:33:22,415 INFO [train.py:715] (4/8) Epoch 7, batch 17550, loss[loss=0.1419, simple_loss=0.2122, pruned_loss=0.03582, over 4951.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2175, pruned_loss=0.03614, over 974381.66 frames.], batch size: 21, lr: 2.92e-04
2022-05-05 21:34:00,738 INFO [train.py:715] (4/8) Epoch 7, batch 17600, loss[loss=0.1551, simple_loss=0.2213, pruned_loss=0.04443, over 4912.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2171, pruned_loss=0.03623, over 973795.89 frames.], batch size: 17, lr: 2.92e-04
2022-05-05 21:34:39,810 INFO [train.py:715] (4/8) Epoch 7, batch 17650, loss[loss=0.1272, simple_loss=0.2007, pruned_loss=0.02687, over 4919.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03593, over 973106.17 frames.], batch size: 23, lr: 2.92e-04
2022-05-05 21:35:19,109 INFO [train.py:715] (4/8) Epoch 7, batch 17700, loss[loss=0.1676, simple_loss=0.2386, pruned_loss=0.04835, over 4962.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03613, over 973511.72 frames.], batch size: 14, lr: 2.92e-04
2022-05-05 21:35:58,207 INFO [train.py:715] (4/8) Epoch 7, batch 17750, loss[loss=0.1701, simple_loss=0.2351, pruned_loss=0.05259, over 4832.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.03586, over 973366.58 frames.], batch size: 26, lr: 2.92e-04
2022-05-05 21:36:37,514 INFO [train.py:715] (4/8) Epoch 7, batch 17800, loss[loss=0.1798, simple_loss=0.2438, pruned_loss=0.05793, over 4717.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2165, pruned_loss=0.03605, over 973181.41 frames.], batch size: 15, lr: 2.92e-04
2022-05-05 21:37:16,002 INFO [train.py:715] (4/8) Epoch 7, batch 17850, loss[loss=0.1604, simple_loss=0.2206, pruned_loss=0.05011, over 4852.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2167, pruned_loss=0.03648, over 973404.50 frames.], batch size: 34, lr: 2.92e-04
2022-05-05 21:37:55,610 INFO [train.py:715] (4/8) Epoch 7, batch 17900, loss[loss=0.1503, simple_loss=0.2217, pruned_loss=0.03949, over 4917.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2171, pruned_loss=0.03698, over 973324.78 frames.], batch size: 23, lr: 2.92e-04
2022-05-05 21:38:34,075 INFO [train.py:715] (4/8) Epoch 7, batch 17950, loss[loss=0.1564, simple_loss=0.2159, pruned_loss=0.0485, over 4955.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2168, pruned_loss=0.03668, over 973430.26 frames.], batch size: 35, lr: 2.92e-04
2022-05-05 21:39:13,135 INFO [train.py:715] (4/8) Epoch 7, batch 18000, loss[loss=0.138, simple_loss=0.2178, pruned_loss=0.0291, over 4972.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2174, pruned_loss=0.03708, over 973539.16 frames.], batch size: 24, lr: 2.92e-04
2022-05-05 21:39:13,136 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 21:39:22,792 INFO [train.py:742] (4/8) Epoch 7, validation: loss=0.1081, simple_loss=0.193, pruned_loss=0.01158, over 914524.00 frames.
2022-05-05 21:40:01,808 INFO [train.py:715] (4/8) Epoch 7, batch 18050, loss[loss=0.1166, simple_loss=0.1875, pruned_loss=0.02284, over 4995.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03721, over 972431.50 frames.], batch size: 14, lr: 2.92e-04
2022-05-05 21:40:41,010 INFO [train.py:715] (4/8) Epoch 7, batch 18100, loss[loss=0.1373, simple_loss=0.212, pruned_loss=0.03128, over 4816.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.03739, over 971808.68 frames.], batch size: 25, lr: 2.92e-04
2022-05-05 21:41:19,568 INFO [train.py:715] (4/8) Epoch 7, batch 18150, loss[loss=0.1377, simple_loss=0.2096, pruned_loss=0.03287, over 4814.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2182, pruned_loss=0.0375, over 971764.93 frames.], batch size: 27, lr: 2.92e-04
2022-05-05 21:41:57,882 INFO [train.py:715] (4/8) Epoch 7, batch 18200, loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03435, over 4874.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03694, over 972251.04 frames.], batch size: 22, lr: 2.92e-04
2022-05-05 21:42:36,255 INFO [train.py:715] (4/8) Epoch 7, batch 18250, loss[loss=0.1558, simple_loss=0.2462, pruned_loss=0.03274, over 4967.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2178, pruned_loss=0.03675, over 972464.89 frames.], batch size: 15, lr: 2.92e-04
2022-05-05 21:43:15,544 INFO [train.py:715] (4/8) Epoch 7, batch 18300, loss[loss=0.1802, simple_loss=0.2385, pruned_loss=0.06095, over 4785.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2175, pruned_loss=0.03658, over 972552.73 frames.], batch size: 18, lr: 2.92e-04
2022-05-05 21:43:53,557 INFO [train.py:715] (4/8) Epoch 7, batch 18350, loss[loss=0.1644, simple_loss=0.2303, pruned_loss=0.04923, over 4834.00 frames.], tot_loss[loss=0.1458, simple_loss=0.218, pruned_loss=0.03679, over 972620.31 frames.], batch size: 30, lr: 2.92e-04
2022-05-05 21:44:31,933 INFO [train.py:715] (4/8) Epoch 7, batch 18400, loss[loss=0.1478, simple_loss=0.2289, pruned_loss=0.0333, over 4712.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2183, pruned_loss=0.03703, over 971774.87 frames.], batch size: 15, lr: 2.92e-04
2022-05-05 21:45:11,789 INFO [train.py:715] (4/8) Epoch 7, batch 18450, loss[loss=0.1341, simple_loss=0.2075, pruned_loss=0.03036, over 4807.00 frames.], tot_loss[loss=0.146, simple_loss=0.218, pruned_loss=0.03697, over 971365.45 frames.], batch size: 21, lr: 2.92e-04
2022-05-05 21:45:50,716 INFO [train.py:715] (4/8) Epoch 7, batch 18500, loss[loss=0.1365, simple_loss=0.2013, pruned_loss=0.03581, over 4863.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2166, pruned_loss=0.0362, over 970913.85 frames.], batch size: 32, lr: 2.92e-04
2022-05-05 21:46:29,378 INFO [train.py:715] (4/8) Epoch 7, batch 18550, loss[loss=0.1336, simple_loss=0.2057, pruned_loss=0.03078, over 4991.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2175, pruned_loss=0.03679, over 971177.36 frames.], batch size: 14, lr: 2.92e-04
2022-05-05 21:47:08,451 INFO [train.py:715] (4/8) Epoch 7, batch 18600, loss[loss=0.1364, simple_loss=0.2116, pruned_loss=0.0306, over 4871.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2182, pruned_loss=0.03745, over 971964.45 frames.], batch size: 16, lr: 2.92e-04
2022-05-05 21:47:47,273 INFO [train.py:715] (4/8) Epoch 7, batch 18650, loss[loss=0.1505, simple_loss=0.2167, pruned_loss=0.04218, over 4853.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2186, pruned_loss=0.03781, over 972223.07 frames.], batch size: 13, lr: 2.92e-04
2022-05-05 21:48:25,126 INFO [train.py:715] (4/8) Epoch 7, batch 18700, loss[loss=0.1462, simple_loss=0.2246, pruned_loss=0.03394, over 4777.00 frames.], tot_loss[loss=0.147, simple_loss=0.2183, pruned_loss=0.03783, over 971490.48 frames.], batch size: 17, lr: 2.92e-04
2022-05-05 21:49:03,390 INFO [train.py:715] (4/8) Epoch 7, batch 18750, loss[loss=0.1392, simple_loss=0.2228, pruned_loss=0.02779, over 4908.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03756, over 972672.40 frames.], batch size: 17, lr: 2.92e-04
2022-05-05 21:49:42,761 INFO [train.py:715] (4/8) Epoch 7, batch 18800, loss[loss=0.1258, simple_loss=0.1924, pruned_loss=0.02965, over 4816.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03721, over 972342.19 frames.], batch size: 13, lr: 2.92e-04
2022-05-05 21:50:21,362 INFO [train.py:715] (4/8) Epoch 7, batch 18850, loss[loss=0.1314, simple_loss=0.2027, pruned_loss=0.03002, over 4846.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2175, pruned_loss=0.03706, over 972252.87 frames.], batch size: 32, lr: 2.92e-04
2022-05-05 21:50:59,416 INFO [train.py:715] (4/8) Epoch 7, batch 18900, loss[loss=0.1791, simple_loss=0.2468, pruned_loss=0.05569, over 4869.00 frames.], tot_loss[loss=0.146, simple_loss=0.218, pruned_loss=0.03699, over 972673.54 frames.], batch size: 32, lr: 2.92e-04
2022-05-05 21:51:36,461 INFO [train.py:715] (4/8) Epoch 7, batch 18950, loss[loss=0.1432, simple_loss=0.2187, pruned_loss=0.03387, over 4947.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2177, pruned_loss=0.03683, over 973326.53 frames.], batch size: 21, lr: 2.92e-04
2022-05-05 21:52:14,913 INFO [train.py:715] (4/8) Epoch 7, batch 19000, loss[loss=0.1379, simple_loss=0.2014, pruned_loss=0.03722, over 4799.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2177, pruned_loss=0.03669, over 973472.27 frames.], batch size: 24, lr: 2.92e-04
2022-05-05 21:52:52,513 INFO [train.py:715] (4/8) Epoch 7, batch 19050, loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03197, over 4956.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.037, over 973633.46 frames.], batch size: 24, lr: 2.91e-04
2022-05-05 21:53:30,742 INFO [train.py:715] (4/8) Epoch 7, batch 19100, loss[loss=0.1302, simple_loss=0.202, pruned_loss=0.02919, over 4824.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2166, pruned_loss=0.03656, over 973197.97 frames.], batch size: 27, lr: 2.91e-04
2022-05-05 21:54:09,413 INFO [train.py:715] (4/8) Epoch 7, batch 19150, loss[loss=0.1506, simple_loss=0.2214, pruned_loss=0.03987, over 4776.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.03711, over 973068.41 frames.], batch size: 14, lr: 2.91e-04
2022-05-05 21:54:47,125 INFO [train.py:715] (4/8) Epoch 7, batch 19200, loss[loss=0.1386, simple_loss=0.21, pruned_loss=0.03358, over 4927.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03708, over 973657.75 frames.], batch size: 23, lr: 2.91e-04
2022-05-05 21:55:24,840 INFO [train.py:715] (4/8) Epoch 7, batch 19250, loss[loss=0.1441, simple_loss=0.2218, pruned_loss=0.03315, over 4891.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2175, pruned_loss=0.03707, over 973029.19 frames.], batch size: 16, lr: 2.91e-04
2022-05-05 21:56:02,878 INFO [train.py:715] (4/8) Epoch 7, batch 19300, loss[loss=0.166, simple_loss=0.234, pruned_loss=0.04898, over 4919.00 frames.], tot_loss[loss=0.146, simple_loss=0.2177, pruned_loss=0.03717, over 972871.53 frames.], batch size: 39, lr: 2.91e-04
2022-05-05 21:56:41,357 INFO [train.py:715] (4/8) Epoch 7, batch 19350, loss[loss=0.1556, simple_loss=0.2306, pruned_loss=0.04031, over 4897.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2173, pruned_loss=0.03727, over 972726.86 frames.], batch size: 19, lr: 2.91e-04
2022-05-05 21:57:18,829 INFO [train.py:715] (4/8) Epoch 7, batch 19400, loss[loss=0.1307, simple_loss=0.2028, pruned_loss=0.02932, over 4964.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2168, pruned_loss=0.03656, over 973161.17 frames.], batch size: 24, lr: 2.91e-04
2022-05-05 21:57:56,263 INFO [train.py:715] (4/8) Epoch 7, batch 19450, loss[loss=0.1297, simple_loss=0.2088, pruned_loss=0.02531, over 4853.00 frames.], tot_loss[loss=0.145, simple_loss=0.2166, pruned_loss=0.03665, over 972788.07 frames.], batch size: 20, lr: 2.91e-04
2022-05-05 21:58:34,321 INFO [train.py:715] (4/8) Epoch 7, batch 19500, loss[loss=0.1432, simple_loss=0.212, pruned_loss=0.03722, over 4954.00 frames.], tot_loss[loss=0.1456, simple_loss=0.217, pruned_loss=0.03708, over 972959.27 frames.], batch size: 39, lr: 2.91e-04
2022-05-05 21:59:11,842 INFO [train.py:715] (4/8) Epoch 7, batch 19550, loss[loss=0.1353, simple_loss=0.1959, pruned_loss=0.03735, over 4847.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2181, pruned_loss=0.0378, over 973679.20 frames.], batch size: 15, lr: 2.91e-04
2022-05-05 21:59:49,563 INFO [train.py:715] (4/8) Epoch 7, batch 19600, loss[loss=0.1329, simple_loss=0.2063, pruned_loss=0.02974, over 4943.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2173, pruned_loss=0.03745, over 972607.61 frames.], batch size: 21, lr: 2.91e-04
2022-05-05 22:00:27,123 INFO [train.py:715] (4/8) Epoch 7, batch 19650, loss[loss=0.1461, simple_loss=0.2268, pruned_loss=0.03272, over 4966.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2169, pruned_loss=0.03737, over 973001.88 frames.], batch size: 15, lr: 2.91e-04
2022-05-05 22:01:05,539 INFO [train.py:715] (4/8) Epoch 7, batch 19700, loss[loss=0.125, simple_loss=0.1921, pruned_loss=0.02895, over 4776.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2159, pruned_loss=0.03683, over 972362.90 frames.], batch size: 14, lr: 2.91e-04
2022-05-05 22:01:42,747 INFO [train.py:715] (4/8) Epoch 7, batch 19750, loss[loss=0.1457, simple_loss=0.2231, pruned_loss=0.03413, over 4827.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2157, pruned_loss=0.03657, over 972350.01 frames.], batch size: 26, lr: 2.91e-04
2022-05-05 22:02:20,221 INFO [train.py:715] (4/8) Epoch 7, batch 19800, loss[loss=0.1141, simple_loss=0.1994, pruned_loss=0.01445, over 4794.00 frames.], tot_loss[loss=0.1443, simple_loss=0.216, pruned_loss=0.03632, over 972513.28 frames.], batch size: 12, lr: 2.91e-04
2022-05-05 22:02:58,033 INFO [train.py:715] (4/8) Epoch 7, batch 19850, loss[loss=0.1847, simple_loss=0.2445, pruned_loss=0.06242, over 4862.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2157, pruned_loss=0.03584, over 972708.50 frames.], batch size: 22, lr: 2.91e-04
2022-05-05 22:03:35,857 INFO [train.py:715] (4/8) Epoch 7, batch 19900, loss[loss=0.1736, simple_loss=0.233, pruned_loss=0.0571, over 4800.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2164, pruned_loss=0.03633, over 972780.22 frames.], batch size: 13, lr: 2.91e-04
2022-05-05 22:04:12,821 INFO [train.py:715] (4/8) Epoch 7, batch 19950, loss[loss=0.1505, simple_loss=0.2209, pruned_loss=0.04002, over 4827.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2167, pruned_loss=0.03683, over 973729.91 frames.], batch size: 30, lr: 2.91e-04
2022-05-05 22:04:50,680 INFO [train.py:715] (4/8) Epoch 7, batch 20000, loss[loss=0.1188, simple_loss=0.2018, pruned_loss=0.01796, over 4830.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2165, pruned_loss=0.03646, over 974045.89 frames.], batch size: 26, lr: 2.91e-04
2022-05-05 22:05:28,967 INFO [train.py:715] (4/8) Epoch 7, batch 20050, loss[loss=0.133, simple_loss=0.2081, pruned_loss=0.02889, over 4920.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2157, pruned_loss=0.03591, over 974077.56 frames.], batch size: 17, lr: 2.91e-04
2022-05-05 22:06:06,297 INFO [train.py:715] (4/8) Epoch 7, batch 20100, loss[loss=0.1398, simple_loss=0.2067, pruned_loss=0.03644, over 4931.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2157, pruned_loss=0.03624, over 973675.86 frames.], batch size: 23, lr: 2.91e-04
2022-05-05 22:06:43,748 INFO [train.py:715] (4/8) Epoch 7, batch 20150, loss[loss=0.129, simple_loss=0.2045, pruned_loss=0.02672, over 4797.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2158, pruned_loss=0.03636, over 972573.59 frames.], batch size: 24, lr: 2.91e-04
2022-05-05 22:07:21,915 INFO [train.py:715] (4/8) Epoch 7, batch 20200, loss[loss=0.146, simple_loss=0.2225, pruned_loss=0.03475, over 4972.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2161, pruned_loss=0.03622, over 973265.56 frames.], batch size: 15, lr: 2.91e-04
2022-05-05 22:08:00,053 INFO [train.py:715] (4/8) Epoch 7, batch 20250, loss[loss=0.1749, simple_loss=0.2367, pruned_loss=0.05651, over 4850.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2165, pruned_loss=0.03624, over 972754.60 frames.], batch size: 15, lr: 2.91e-04
2022-05-05 22:08:37,464 INFO [train.py:715] (4/8) Epoch 7, batch 20300, loss[loss=0.1353, simple_loss=0.2117, pruned_loss=0.02943, over 4893.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2177, pruned_loss=0.03663, over 972909.70 frames.], batch size: 19, lr: 2.91e-04
2022-05-05 22:09:17,216 INFO [train.py:715] (4/8) Epoch 7, batch 20350, loss[loss=0.1512, simple_loss=0.2178, pruned_loss=0.0423, over 4864.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2176, pruned_loss=0.03697, over 973259.37 frames.], batch size: 20, lr: 2.91e-04
2022-05-05 22:09:55,131 INFO [train.py:715] (4/8) Epoch 7, batch 20400, loss[loss=0.1561, simple_loss=0.2258, pruned_loss=0.04319, over 4952.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2168, pruned_loss=0.03653, over 973138.09 frames.], batch size: 35, lr: 2.91e-04
2022-05-05 22:10:33,045 INFO [train.py:715] (4/8) Epoch 7, batch 20450, loss[loss=0.1558, simple_loss=0.2327, pruned_loss=0.0394, over 4793.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2165, pruned_loss=0.03638, over 973527.12 frames.], batch size: 18, lr: 2.91e-04
2022-05-05 22:11:10,605 INFO [train.py:715] (4/8) Epoch 7, batch 20500, loss[loss=0.1575, simple_loss=0.2254, pruned_loss=0.04476, over 4846.00 frames.], tot_loss[loss=0.1451, simple_loss=0.217, pruned_loss=0.03659, over 972729.00 frames.], batch size: 30, lr: 2.91e-04
2022-05-05 22:11:48,692 INFO [train.py:715] (4/8) Epoch 7, batch 20550, loss[loss=0.144, simple_loss=0.2143, pruned_loss=0.03691, over 4644.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2173, pruned_loss=0.03691, over 973271.81 frames.], batch size: 13, lr: 2.91e-04
2022-05-05 22:12:26,842 INFO [train.py:715] (4/8) Epoch 7, batch 20600, loss[loss=0.1679, simple_loss=0.2366, pruned_loss=0.0496, over 4789.00 frames.], tot_loss[loss=0.146, simple_loss=0.2171, pruned_loss=0.03743, over 972449.73 frames.], batch size: 17, lr: 2.91e-04
2022-05-05 22:13:04,071 INFO [train.py:715] (4/8) Epoch 7, batch 20650, loss[loss=0.1795, simple_loss=0.2419, pruned_loss=0.05852, over 4883.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2161, pruned_loss=0.03713, over 973466.68 frames.], batch size: 22, lr: 2.91e-04
2022-05-05 22:13:41,770 INFO [train.py:715] (4/8) Epoch 7, batch 20700, loss[loss=0.1569, simple_loss=0.2325, pruned_loss=0.04067, over 4972.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2163, pruned_loss=0.03696, over 972766.27 frames.], batch size: 35, lr: 2.91e-04
2022-05-05 22:14:19,742 INFO [train.py:715] (4/8) Epoch 7, batch 20750, loss[loss=0.153, simple_loss=0.2201, pruned_loss=0.04297, over 4815.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2181, pruned_loss=0.03777, over 972748.84 frames.], batch size: 15, lr: 2.91e-04
2022-05-05 22:14:57,388 INFO [train.py:715] (4/8) Epoch 7, batch 20800, loss[loss=0.1214, simple_loss=0.1931, pruned_loss=0.02487, over 4764.00 frames.], tot_loss[loss=0.146, simple_loss=0.2172, pruned_loss=0.03747, over 972130.08 frames.], batch size: 12, lr: 2.91e-04
2022-05-05 22:15:34,691 INFO [train.py:715] (4/8) Epoch 7, batch 20850, loss[loss=0.1621, simple_loss=0.2403, pruned_loss=0.04195, over 4839.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2162, pruned_loss=0.03671, over 972492.08 frames.], batch size: 15, lr: 2.90e-04
2022-05-05 22:16:13,018 INFO [train.py:715] (4/8) Epoch 7, batch 20900, loss[loss=0.1569, simple_loss=0.223, pruned_loss=0.04538, over 4747.00 frames.], tot_loss[loss=0.1447, simple_loss=0.216, pruned_loss=0.03669, over 972322.85 frames.], batch size: 19, lr: 2.90e-04
2022-05-05 22:16:50,908 INFO [train.py:715] (4/8) Epoch 7, batch 20950, loss[loss=0.1383, simple_loss=0.208, pruned_loss=0.03433, over 4842.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2154, pruned_loss=0.0362, over 972085.18 frames.], batch size: 13, lr: 2.90e-04
2022-05-05 22:17:29,167 INFO [train.py:715] (4/8) Epoch 7, batch 21000, loss[loss=0.1361, simple_loss=0.2082, pruned_loss=0.032, over 4906.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2156, pruned_loss=0.03631, over 972278.36 frames.], batch size: 19, lr: 2.90e-04
2022-05-05 22:17:29,168 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 22:17:39,071 INFO [train.py:742] (4/8) Epoch 7, validation: loss=0.1082, simple_loss=0.193, pruned_loss=0.01169, over 914524.00 frames.
2022-05-05 22:18:17,066 INFO [train.py:715] (4/8) Epoch 7, batch 21050, loss[loss=0.165, simple_loss=0.2381, pruned_loss=0.04595, over 4813.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2157, pruned_loss=0.03643, over 972577.38 frames.], batch size: 25, lr: 2.90e-04
2022-05-05 22:18:54,965 INFO [train.py:715] (4/8) Epoch 7, batch 21100, loss[loss=0.1253, simple_loss=0.1978, pruned_loss=0.02639, over 4816.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2163, pruned_loss=0.03668, over 972900.96 frames.], batch size: 26, lr: 2.90e-04
2022-05-05 22:19:32,989 INFO [train.py:715] (4/8) Epoch 7, batch 21150, loss[loss=0.1485, simple_loss=0.2284, pruned_loss=0.03424, over 4890.00 frames.], tot_loss[loss=0.1445, simple_loss=0.216, pruned_loss=0.03653, over 972234.34 frames.], batch size: 22, lr: 2.90e-04
2022-05-05 22:20:10,777 INFO [train.py:715] (4/8) Epoch 7, batch 21200, loss[loss=0.1335, simple_loss=0.2093, pruned_loss=0.0289, over 4754.00 frames.], tot_loss[loss=0.1444, simple_loss=0.216, pruned_loss=0.03643, over 971707.14 frames.], batch size: 16, lr: 2.90e-04
2022-05-05 22:20:49,001 INFO [train.py:715] (4/8) Epoch 7, batch 21250, loss[loss=0.1455, simple_loss=0.2191, pruned_loss=0.03594, over 4797.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2158, pruned_loss=0.03631, over 970213.62 frames.], batch size: 14, lr: 2.90e-04
2022-05-05 22:21:27,130 INFO [train.py:715] (4/8) Epoch 7, batch 21300, loss[loss=0.1637, simple_loss=0.2368, pruned_loss=0.04532, over 4750.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2156, pruned_loss=0.03644, over 970388.18 frames.], batch size: 16, lr: 2.90e-04
2022-05-05 22:22:04,501 INFO [train.py:715] (4/8) Epoch 7, batch 21350, loss[loss=0.1501, simple_loss=0.218, pruned_loss=0.04111, over 4688.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2159, pruned_loss=0.03651, over 971100.67 frames.], batch size: 15, lr: 2.90e-04
2022-05-05 22:22:42,287 INFO [train.py:715] (4/8) Epoch 7, batch 21400, loss[loss=0.1373, simple_loss=0.2051, pruned_loss=0.03473, over 4991.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2163, pruned_loss=0.03625, over 971324.48 frames.], batch size: 14, lr: 2.90e-04
2022-05-05 22:23:20,548 INFO [train.py:715] (4/8) Epoch 7, batch 21450, loss[loss=0.1318, simple_loss=0.2138, pruned_loss=0.02483, over 4938.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2158, pruned_loss=0.03605, over 971465.76 frames.], batch size: 29, lr: 2.90e-04
2022-05-05 22:23:58,722 INFO [train.py:715] (4/8) Epoch 7, batch 21500, loss[loss=0.1428, simple_loss=0.2193, pruned_loss=0.03312, over 4923.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2164, pruned_loss=0.0364, over 971247.23 frames.], batch size: 18, lr: 2.90e-04
2022-05-05 22:24:36,575 INFO [train.py:715] (4/8) Epoch 7, batch 21550, loss[loss=0.1768, simple_loss=0.2411, pruned_loss=0.0563, over 4969.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2169, pruned_loss=0.03671, over 970985.61 frames.], batch size: 35, lr: 2.90e-04
2022-05-05 22:25:14,831 INFO [train.py:715] (4/8) Epoch 7, batch 21600, loss[loss=0.1478, simple_loss=0.221, pruned_loss=0.03725, over 4799.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2175, pruned_loss=0.03729, over 970655.26 frames.], batch size: 12, lr: 2.90e-04
2022-05-05 22:25:53,301 INFO [train.py:715] (4/8) Epoch 7, batch 21650, loss[loss=0.137, simple_loss=0.2129, pruned_loss=0.03054, over 4824.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2177, pruned_loss=0.03756, over 971289.28 frames.], batch size: 27, lr: 2.90e-04
2022-05-05 22:26:30,667 INFO [train.py:715] (4/8) Epoch 7, batch 21700, loss[loss=0.1714, simple_loss=0.2341, pruned_loss=0.05434, over 4959.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2184, pruned_loss=0.03819, over 970845.68 frames.], batch size: 24, lr: 2.90e-04
2022-05-05 22:27:08,758 INFO [train.py:715] (4/8) Epoch 7, batch 21750, loss[loss=0.1451, simple_loss=0.2185, pruned_loss=0.0358, over 4796.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2179, pruned_loss=0.03766, over 971231.16 frames.], batch size: 21, lr: 2.90e-04
2022-05-05 22:27:46,872 INFO [train.py:715] (4/8) Epoch 7, batch 21800, loss[loss=0.126, simple_loss=0.2074, pruned_loss=0.02226, over 4812.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03685, over 972258.48 frames.], batch size: 27, lr: 2.90e-04
2022-05-05 22:28:24,962 INFO [train.py:715] (4/8) Epoch 7, batch 21850, loss[loss=0.1662, simple_loss=0.227, pruned_loss=0.05274, over 4912.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2171, pruned_loss=0.03692, over 971960.83 frames.], batch size: 18, lr: 2.90e-04
2022-05-05 22:29:02,873 INFO [train.py:715] (4/8) Epoch 7, batch 21900, loss[loss=0.1662, simple_loss=0.2388, pruned_loss=0.04675, over 4959.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2175, pruned_loss=0.03687, over 972806.14 frames.], batch size: 21, lr: 2.90e-04
2022-05-05 22:29:40,815 INFO [train.py:715] (4/8) Epoch 7, batch 21950, loss[loss=0.1116, simple_loss=0.182, pruned_loss=0.02062, over 4779.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2164, pruned_loss=0.03635, over 972690.92 frames.], batch size: 14, lr: 2.90e-04
2022-05-05 22:30:19,542 INFO [train.py:715] (4/8) Epoch 7, batch 22000, loss[loss=0.1415, simple_loss=0.2133, pruned_loss=0.0348, over 4829.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2158, pruned_loss=0.03633, over 972134.47 frames.], batch size: 26, lr: 2.90e-04
2022-05-05 22:30:57,078 INFO [train.py:715] (4/8) Epoch 7, batch 22050, loss[loss=0.1388, simple_loss=0.2108, pruned_loss=0.03338, over 4962.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2153, pruned_loss=0.03587, over 972221.11 frames.], batch size: 24, lr: 2.90e-04
2022-05-05 22:31:35,218 INFO [train.py:715] (4/8) Epoch 7, batch 22100, loss[loss=0.1209, simple_loss=0.1968, pruned_loss=0.02247, over 4925.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2156, pruned_loss=0.03597, over 972603.34 frames.], batch size: 21, lr: 2.90e-04
2022-05-05 22:32:13,474 INFO [train.py:715] (4/8) Epoch 7, batch 22150, loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02913, over 4987.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2164, pruned_loss=0.0362, over 972241.28 frames.], batch size: 28, lr: 2.90e-04
2022-05-05 22:32:51,984 INFO [train.py:715] (4/8) Epoch 7, batch 22200, loss[loss=0.1724, simple_loss=0.2465, pruned_loss=0.0492, over 4988.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2168, pruned_loss=0.03625, over 973274.74 frames.], batch size: 28, lr: 2.90e-04
2022-05-05 22:33:29,482 INFO [train.py:715] (4/8) Epoch 7, batch 22250, loss[loss=0.1495, simple_loss=0.2078, pruned_loss=0.04561, over 4880.00 frames.], tot_loss[loss=0.145, simple_loss=0.2174, pruned_loss=0.03635, over 973501.52 frames.], batch size: 12, lr: 2.90e-04
2022-05-05 22:34:07,239 INFO [train.py:715] (4/8) Epoch 7, batch 22300, loss[loss=0.1355, simple_loss=0.1923, pruned_loss=0.03933, over 4800.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2178, pruned_loss=0.03689, over 972672.25 frames.], batch size: 14, lr: 2.90e-04
2022-05-05 22:34:45,535 INFO [train.py:715] (4/8) Epoch 7, batch 22350, loss[loss=0.1271, simple_loss=0.2024, pruned_loss=0.02593, over 4820.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03714, over 971412.04 frames.], batch size: 13, lr: 2.90e-04
2022-05-05 22:35:22,813 INFO [train.py:715] (4/8) Epoch 7, batch 22400, loss[loss=0.1558, simple_loss=0.2198, pruned_loss=0.04591, over 4948.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2175, pruned_loss=0.0374, over 972240.53 frames.], batch size: 35, lr: 2.90e-04
2022-05-05 22:36:00,505 INFO [train.py:715] (4/8) Epoch 7, batch 22450, loss[loss=0.1285, simple_loss=0.1919, pruned_loss=0.03255, over 4761.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2184, pruned_loss=0.03772, over 972121.58 frames.], batch size: 12, lr: 2.90e-04
2022-05-05 22:36:38,650 INFO [train.py:715] (4/8) Epoch 7, batch 22500, loss[loss=0.112, simple_loss=0.1825, pruned_loss=0.0208, over 4956.00 frames.], tot_loss[loss=0.1468, simple_loss=0.218, pruned_loss=0.03783, over 971922.36 frames.], batch size: 15, lr: 2.90e-04
2022-05-05 22:37:16,690 INFO [train.py:715] (4/8) Epoch 7, batch 22550, loss[loss=0.1431, simple_loss=0.2063, pruned_loss=0.03991, over 4644.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2172, pruned_loss=0.03757, over 971186.33 frames.], batch size: 13, lr: 2.90e-04
2022-05-05 22:37:54,356 INFO [train.py:715] (4/8) Epoch 7, batch 22600, loss[loss=0.153, simple_loss=0.2274, pruned_loss=0.03933, over 4968.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2169, pruned_loss=0.03705, over 971637.12 frames.], batch size: 15, lr: 2.90e-04
2022-05-05 22:38:32,388 INFO [train.py:715] (4/8) Epoch 7, batch 22650, loss[loss=0.1382, simple_loss=0.2073, pruned_loss=0.03454, over 4645.00 frames.], tot_loss[loss=0.146, simple_loss=0.2176, pruned_loss=0.03717, over 972039.38 frames.], batch size: 13, lr: 2.90e-04
2022-05-05 22:39:10,751 INFO [train.py:715] (4/8) Epoch 7, batch 22700, loss[loss=0.1698, simple_loss=0.2454, pruned_loss=0.04714, over 4903.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2184, pruned_loss=0.03764, over 971893.19 frames.], batch size: 19, lr: 2.89e-04
2022-05-05 22:39:48,097 INFO [train.py:715] (4/8) Epoch 7, batch 22750, loss[loss=0.1703, simple_loss=0.2251, pruned_loss=0.05774, over 4773.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2179, pruned_loss=0.03726, over 971691.14 frames.], batch size: 18, lr: 2.89e-04
2022-05-05 22:40:25,727 INFO [train.py:715] (4/8) Epoch 7, batch 22800, loss[loss=0.1328, simple_loss=0.2036, pruned_loss=0.03102, over 4783.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2182, pruned_loss=0.03733, over 972243.22 frames.], batch size: 14, lr: 2.89e-04
2022-05-05 22:41:03,918 INFO [train.py:715] (4/8) Epoch 7, batch 22850, loss[loss=0.1267, simple_loss=0.1924, pruned_loss=0.0305, over 4754.00 frames.], tot_loss[loss=0.146, simple_loss=0.2177, pruned_loss=0.03717, over 971476.60 frames.], batch size: 12, lr: 2.89e-04
2022-05-05 22:41:41,491 INFO [train.py:715] (4/8) Epoch 7, batch 22900, loss[loss=0.1727, simple_loss=0.2332, pruned_loss=0.0561, over 4859.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2186, pruned_loss=0.03793, over 971602.44 frames.], batch size: 20, lr: 2.89e-04
2022-05-05 22:42:19,139 INFO [train.py:715] (4/8) Epoch 7, batch 22950, loss[loss=0.1457, simple_loss=0.2174, pruned_loss=0.03698, over 4759.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2179, pruned_loss=0.03779, over 972458.16 frames.], batch size: 16, lr: 2.89e-04
2022-05-05 22:42:57,045 INFO [train.py:715] (4/8) Epoch 7, batch 23000, loss[loss=0.138, simple_loss=0.21, pruned_loss=0.03298, over 4775.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2179, pruned_loss=0.03755, over 972127.24 frames.], batch size: 18, lr: 2.89e-04
2022-05-05 22:43:35,192 INFO [train.py:715] (4/8) Epoch 7, batch 23050, loss[loss=0.1264, simple_loss=0.2124, pruned_loss=0.02025, over 4933.00 frames.], tot_loss[loss=0.146, simple_loss=0.2175, pruned_loss=0.03722, over 972477.99 frames.], batch size: 29, lr: 2.89e-04
2022-05-05 22:44:12,640 INFO [train.py:715] (4/8) Epoch 7, batch 23100, loss[loss=0.1652, simple_loss=0.229, pruned_loss=0.05072, over 4910.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2172, pruned_loss=0.03695, over 972744.25 frames.], batch size: 18, lr: 2.89e-04
2022-05-05 22:44:49,936 INFO [train.py:715] (4/8) Epoch 7, batch 23150, loss[loss=0.1559, simple_loss=0.2292, pruned_loss=0.0413, over 4946.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2169, pruned_loss=0.03664, over 973086.75 frames.], batch size: 21, lr: 2.89e-04
2022-05-05 22:45:28,254 INFO [train.py:715] (4/8) Epoch 7, batch 23200, loss[loss=0.1563, simple_loss=0.2392, pruned_loss=0.03665, over 4915.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2165, pruned_loss=0.03652, over 971916.48 frames.], batch size: 18, lr: 2.89e-04
2022-05-05 22:46:06,319 INFO [train.py:715] (4/8) Epoch 7, batch 23250, loss[loss=0.1534, simple_loss=0.2208, pruned_loss=0.043, over 4966.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2168, pruned_loss=0.03684, over 971989.78 frames.], batch size: 24, lr: 2.89e-04
2022-05-05 22:46:43,801 INFO [train.py:715] (4/8) Epoch 7, batch 23300, loss[loss=0.1424, simple_loss=0.2094, pruned_loss=0.03774, over 4954.00 frames.], tot_loss[loss=0.146, simple_loss=0.2175, pruned_loss=0.03723, over 972139.34 frames.], batch size: 15, lr: 2.89e-04
2022-05-05 22:47:22,580 INFO [train.py:715] (4/8) Epoch 7, batch 23350, loss[loss=0.1416, simple_loss=0.2177, pruned_loss=0.03281, over 4947.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2168, pruned_loss=0.03693, over 973093.09 frames.], batch size: 21, lr: 2.89e-04
2022-05-05 22:48:01,692 INFO [train.py:715] (4/8) Epoch 7, batch 23400, loss[loss=0.1491, simple_loss=0.2182, pruned_loss=0.04, over 4932.00 frames.], tot_loss[loss=0.1453, simple_loss=0.217, pruned_loss=0.03681, over 974306.38 frames.], batch size: 29, lr: 2.89e-04
2022-05-05 22:48:40,125 INFO [train.py:715] (4/8) Epoch 7, batch 23450, loss[loss=0.1515, simple_loss=0.225, pruned_loss=0.03895, over 4859.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2167, pruned_loss=0.03658, over 974326.23 frames.], batch size: 34, lr: 2.89e-04
2022-05-05 22:49:18,249 INFO [train.py:715] (4/8) Epoch 7, batch 23500, loss[loss=0.1308, simple_loss=0.2129, pruned_loss=0.02435, over 4967.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2169, pruned_loss=0.03595, over 975147.98 frames.], batch size: 24, lr: 2.89e-04
2022-05-05 22:49:56,230 INFO [train.py:715] (4/8) Epoch 7, batch 23550, loss[loss=0.1578, simple_loss=0.2353, pruned_loss=0.04018, over 4789.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2171, pruned_loss=0.03621, over 974732.65 frames.], batch size: 17, lr: 2.89e-04
2022-05-05 22:50:34,438 INFO [train.py:715] (4/8) Epoch 7, batch 23600, loss[loss=0.1511, simple_loss=0.2226, pruned_loss=0.03976, over 4956.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2164, pruned_loss=0.03633, over 973848.50 frames.], batch size: 29, lr: 2.89e-04
2022-05-05 22:51:11,418 INFO [train.py:715] (4/8) Epoch 7, batch 23650, loss[loss=0.1445, simple_loss=0.2175, pruned_loss=0.03577, over 4940.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2161, pruned_loss=0.03607, over 972906.80 frames.], batch size: 39, lr: 2.89e-04
2022-05-05 22:51:49,263 INFO [train.py:715] (4/8) Epoch 7, batch 23700, loss[loss=0.126, simple_loss=0.1868, pruned_loss=0.03261, over 4841.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2169, pruned_loss=0.03625, over 972600.94 frames.], batch size: 13, lr: 2.89e-04
2022-05-05 22:52:27,396 INFO [train.py:715] (4/8) Epoch 7, batch 23750, loss[loss=0.1515, simple_loss=0.2238, pruned_loss=0.03962, over 4853.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2166, pruned_loss=0.03606, over 972373.92 frames.], batch size: 30, lr: 2.89e-04
2022-05-05 22:53:04,577 INFO [train.py:715] (4/8) Epoch 7, batch 23800, loss[loss=0.172, simple_loss=0.234, pruned_loss=0.055, over 4858.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03596, over 972268.71 frames.], batch size: 30, lr: 2.89e-04
2022-05-05 22:53:42,352 INFO [train.py:715] (4/8) Epoch 7, batch 23850, loss[loss=0.1655, simple_loss=0.2259, pruned_loss=0.0525, over 4840.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2166, pruned_loss=0.03606, over 972881.62 frames.], batch size: 32, lr: 2.89e-04
2022-05-05 22:54:21,020 INFO [train.py:715] (4/8) Epoch 7, batch 23900, loss[loss=0.1346, simple_loss=0.2038, pruned_loss=0.03268, over 4937.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2178, pruned_loss=0.0364, over 972533.53 frames.], batch size: 21, lr: 2.89e-04
2022-05-05 22:54:59,166 INFO [train.py:715] (4/8) Epoch 7, batch 23950, loss[loss=0.1888, simple_loss=0.2674, pruned_loss=0.05508, over 4828.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2182, pruned_loss=0.03723, over 972721.21 frames.], batch size: 25, lr: 2.89e-04
2022-05-05 22:55:36,638 INFO [train.py:715] (4/8) Epoch 7, batch 24000, loss[loss=0.1182, simple_loss=0.1925, pruned_loss=0.02197, over 4795.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2173, pruned_loss=0.03645, over 972381.10 frames.], batch size: 24, lr: 2.89e-04
2022-05-05 22:55:36,638 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 22:55:46,185 INFO [train.py:742] (4/8) Epoch 7, validation: loss=0.108, simple_loss=0.1929, pruned_loss=0.01156, over 914524.00 frames.
2022-05-05 22:56:23,728 INFO [train.py:715] (4/8) Epoch 7, batch 24050, loss[loss=0.1415, simple_loss=0.219, pruned_loss=0.03201, over 4784.00 frames.], tot_loss[loss=0.145, simple_loss=0.2174, pruned_loss=0.03633, over 971733.77 frames.], batch size: 18, lr: 2.89e-04
2022-05-05 22:57:02,032 INFO [train.py:715] (4/8) Epoch 7, batch 24100, loss[loss=0.1336, simple_loss=0.2067, pruned_loss=0.03028, over 4911.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2179, pruned_loss=0.03676, over 971418.84 frames.], batch size: 23, lr: 2.89e-04
2022-05-05 22:57:40,436 INFO [train.py:715] (4/8) Epoch 7, batch 24150, loss[loss=0.1436, simple_loss=0.2233, pruned_loss=0.03201, over 4925.00 frames.], tot_loss[loss=0.146, simple_loss=0.2182, pruned_loss=0.03694, over 972680.42 frames.], batch size: 23, lr: 2.89e-04
2022-05-05 22:58:18,171 INFO [train.py:715] (4/8) Epoch 7, batch 24200, loss[loss=0.1209, simple_loss=0.1872, pruned_loss=0.02726, over 4866.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2174, pruned_loss=0.03684, over 972460.80 frames.], batch size: 32, lr: 2.89e-04
2022-05-05 22:58:55,938 INFO [train.py:715] (4/8) Epoch 7, batch 24250, loss[loss=0.1684, simple_loss=0.2309, pruned_loss=0.05294, over 4854.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2174, pruned_loss=0.03685, over 972048.19 frames.], batch size: 32, lr: 2.89e-04
2022-05-05 22:59:34,584 INFO [train.py:715] (4/8) Epoch 7, batch 24300, loss[loss=0.1357, simple_loss=0.2164, pruned_loss=0.02748, over 4858.00 frames.], tot_loss[loss=0.146, simple_loss=0.218, pruned_loss=0.03697, over 971481.69 frames.], batch size: 20, lr: 2.89e-04
2022-05-05 23:00:12,423 INFO [train.py:715] (4/8) Epoch 7, batch 24350, loss[loss=0.1385, simple_loss=0.2179, pruned_loss=0.02959, over 4850.00 frames.], tot_loss[loss=0.147, simple_loss=0.2189, pruned_loss=0.03758, over 971904.23 frames.], batch size: 15, lr: 2.89e-04
2022-05-05 23:00:50,089 INFO [train.py:715] (4/8) Epoch 7, batch 24400, loss[loss=0.1515, simple_loss=0.2211, pruned_loss=0.04097, over 4785.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2192, pruned_loss=0.03745, over 971686.14 frames.], batch size: 18, lr: 2.89e-04
2022-05-05 23:01:28,245 INFO [train.py:715] (4/8) Epoch 7, batch 24450, loss[loss=0.1372, simple_loss=0.2168, pruned_loss=0.02876, over 4770.00 frames.], tot_loss[loss=0.146, simple_loss=0.2183, pruned_loss=0.03689, over 970798.46 frames.], batch size: 14, lr: 2.89e-04
2022-05-05 23:02:06,217 INFO [train.py:715] (4/8) Epoch 7, batch 24500, loss[loss=0.13, simple_loss=0.2021, pruned_loss=0.02897, over 4844.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2179, pruned_loss=0.03692, over 970929.13 frames.], batch size: 15, lr: 2.89e-04
2022-05-05 23:02:43,833 INFO [train.py:715] (4/8) Epoch 7, batch 24550, loss[loss=0.1834, simple_loss=0.2433, pruned_loss=0.0618, over 4705.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03732, over 971021.40 frames.], batch size: 15, lr: 2.88e-04
2022-05-05 23:03:22,003 INFO [train.py:715] (4/8) Epoch 7, batch 24600, loss[loss=0.1384, simple_loss=0.2104, pruned_loss=0.03314, over 4866.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03715, over 970847.05 frames.], batch size: 38, lr: 2.88e-04
2022-05-05 23:04:01,119 INFO [train.py:715] (4/8) Epoch 7, batch 24650, loss[loss=0.1765, simple_loss=0.2542, pruned_loss=0.0494, over 4881.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2179, pruned_loss=0.03756, over 970809.35 frames.], batch size: 16, lr: 2.88e-04
2022-05-05 23:04:39,577 INFO [train.py:715] (4/8) Epoch 7, batch 24700, loss[loss=0.167, simple_loss=0.2264, pruned_loss=0.05375, over 4643.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2179, pruned_loss=0.03757, over 971563.53 frames.], batch size: 13, lr: 2.88e-04
2022-05-05 23:05:17,696 INFO [train.py:715] (4/8) Epoch 7, batch 24750, loss[loss=0.1684, simple_loss=0.2373, pruned_loss=0.04977, over 4860.00 frames.], tot_loss[loss=0.146, simple_loss=0.2177, pruned_loss=0.03711, over 970661.82 frames.], batch size: 30, lr: 2.88e-04
2022-05-05 23:05:56,160 INFO [train.py:715] (4/8) Epoch 7, batch 24800, loss[loss=0.1455, simple_loss=0.2138, pruned_loss=0.03858, over 4821.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2182, pruned_loss=0.03761, over 971560.16 frames.], batch size: 15, lr: 2.88e-04
2022-05-05 23:06:35,230 INFO [train.py:715] (4/8) Epoch 7, batch 24850, loss[loss=0.1228, simple_loss=0.2, pruned_loss=0.0228, over 4744.00 frames.], tot_loss[loss=0.146, simple_loss=0.2174, pruned_loss=0.03733, over 971886.31 frames.], batch size: 19, lr: 2.88e-04
2022-05-05 23:07:13,821 INFO [train.py:715] (4/8) Epoch 7, batch 24900, loss[loss=0.1615, simple_loss=0.2355, pruned_loss=0.04375, over 4894.00 frames.], tot_loss[loss=0.1461, simple_loss=0.217, pruned_loss=0.03753, over 971796.38 frames.], batch size: 17, lr: 2.88e-04
2022-05-05 23:07:53,090 INFO [train.py:715] (4/8) Epoch 7, batch 24950, loss[loss=0.1658, simple_loss=0.2229, pruned_loss=0.05434, over 4842.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2171, pruned_loss=0.03735, over 971849.81 frames.], batch size: 15, lr: 2.88e-04
2022-05-05 23:08:32,941 INFO [train.py:715] (4/8) Epoch 7, batch 25000, loss[loss=0.1602, simple_loss=0.2332, pruned_loss=0.04365, over 4945.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2178, pruned_loss=0.03754, over 971993.52 frames.], batch size: 21, lr: 2.88e-04
2022-05-05 23:09:12,210 INFO [train.py:715] (4/8) Epoch 7, batch 25050, loss[loss=0.1276, simple_loss=0.2032, pruned_loss=0.026, over 4918.00 frames.], tot_loss[loss=0.146, simple_loss=0.2179, pruned_loss=0.03707, over 972851.90 frames.], batch size: 18, lr: 2.88e-04
2022-05-05 23:09:51,233 INFO [train.py:715] (4/8) Epoch 7, batch 25100, loss[loss=0.1936, simple_loss=0.2396, pruned_loss=0.07378, over 4824.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2182, pruned_loss=0.0371, over 973156.36 frames.], batch size: 15, lr: 2.88e-04
2022-05-05 23:10:31,398 INFO [train.py:715] (4/8) Epoch 7, batch 25150, loss[loss=0.1443, simple_loss=0.2111, pruned_loss=0.03872, over 4782.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03732, over 972785.21 frames.], batch size: 14, lr: 2.88e-04
2022-05-05 23:11:11,710 INFO [train.py:715] (4/8) Epoch 7, batch 25200, loss[loss=0.144, simple_loss=0.2168, pruned_loss=0.03567, over 4884.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03703, over 972489.59 frames.], batch size: 22, lr: 2.88e-04
2022-05-05 23:11:51,351 INFO [train.py:715] (4/8) Epoch 7, batch 25250, loss[loss=0.139, simple_loss=0.2128, pruned_loss=0.0326, over 4804.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03725, over 971797.95 frames.], batch size: 21, lr: 2.88e-04
2022-05-05 23:12:31,940 INFO [train.py:715] (4/8) Epoch 7, batch 25300, loss[loss=0.1524, simple_loss=0.2215, pruned_loss=0.04161, over 4691.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.03737, over 971084.01 frames.], batch size: 15, lr: 2.88e-04
2022-05-05 23:13:13,670 INFO [train.py:715] (4/8) Epoch 7, batch 25350, loss[loss=0.1674, simple_loss=0.2326, pruned_loss=0.05114, over 4779.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2184, pruned_loss=0.03771, over 971117.17 frames.], batch size: 14, lr: 2.88e-04
2022-05-05 23:13:55,234 INFO [train.py:715] (4/8) Epoch 7, batch 25400, loss[loss=0.1599, simple_loss=0.2295, pruned_loss=0.0451, over 4835.00 frames.], tot_loss[loss=0.1474, simple_loss=0.219, pruned_loss=0.0379, over 971284.94 frames.], batch size: 30, lr: 2.88e-04
2022-05-05 23:14:36,169 INFO [train.py:715] (4/8) Epoch 7, batch 25450, loss[loss=0.1444, simple_loss=0.2099, pruned_loss=0.03943, over 4990.00 frames.], tot_loss[loss=0.1473, simple_loss=0.219, pruned_loss=0.03781, over 970467.94 frames.], batch size: 16, lr: 2.88e-04
2022-05-05 23:15:18,365 INFO [train.py:715] (4/8) Epoch 7, batch 25500, loss[loss=0.1279, simple_loss=0.2037, pruned_loss=0.02602, over 4768.00 frames.], tot_loss[loss=0.147, simple_loss=0.2189, pruned_loss=0.03755, over 970405.99 frames.], batch size: 19, lr: 2.88e-04
2022-05-05 23:16:00,249 INFO [train.py:715] (4/8) Epoch 7, batch 25550, loss[loss=0.1347, simple_loss=0.2131, pruned_loss=0.02814, over 4812.00 frames.], tot_loss[loss=0.1461, simple_loss=0.218, pruned_loss=0.03706, over 970040.04 frames.], batch size: 27, lr: 2.88e-04
2022-05-05 23:16:41,008 INFO [train.py:715] (4/8) Epoch 7, batch 25600, loss[loss=0.1592, simple_loss=0.2335, pruned_loss=0.04246, over 4978.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2179, pruned_loss=0.03715, over 970336.83 frames.], batch size: 35, lr: 2.88e-04
2022-05-05 23:17:22,275 INFO [train.py:715] (4/8) Epoch 7, batch 25650, loss[loss=0.1529, simple_loss=0.211, pruned_loss=0.04742, over 4859.00 frames.], tot_loss[loss=0.146, simple_loss=0.2177, pruned_loss=0.0371, over 970672.45 frames.], batch size: 20, lr: 2.88e-04
2022-05-05 23:18:03,675 INFO [train.py:715] (4/8) Epoch 7, batch 25700, loss[loss=0.1142, simple_loss=0.1897, pruned_loss=0.01938, over 4930.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2168, pruned_loss=0.03648, over 970581.71 frames.], batch size: 29, lr: 2.88e-04
2022-05-05 23:18:45,517 INFO [train.py:715] (4/8) Epoch 7, batch 25750, loss[loss=0.1884, simple_loss=0.2529, pruned_loss=0.06197, over 4703.00 frames.], tot_loss[loss=0.145, simple_loss=0.2165, pruned_loss=0.03678, over 969932.21 frames.], batch size: 15, lr: 2.88e-04
2022-05-05 23:19:26,146 INFO [train.py:715] (4/8) Epoch 7, batch 25800, loss[loss=0.1353, simple_loss=0.2204, pruned_loss=0.02513, over 4898.00 frames.], tot_loss[loss=0.145, simple_loss=0.2169, pruned_loss=0.03658, over 970863.08 frames.], batch size: 19, lr: 2.88e-04
2022-05-05 23:20:08,460 INFO [train.py:715] (4/8) Epoch 7, batch 25850, loss[loss=0.1619, simple_loss=0.2369, pruned_loss=0.04344, over 4980.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2161, pruned_loss=0.03627, over 971815.03 frames.], batch size: 28, lr: 2.88e-04
2022-05-05 23:20:50,393 INFO [train.py:715] (4/8) Epoch 7, batch 25900, loss[loss=0.1524, simple_loss=0.2158, pruned_loss=0.04451, over 4988.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2159, pruned_loss=0.03612, over 971833.83 frames.], batch size: 15, lr: 2.88e-04
2022-05-05 23:21:31,302 INFO [train.py:715] (4/8) Epoch 7, batch 25950, loss[loss=0.1755, simple_loss=0.2484, pruned_loss=0.05133, over 4799.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03718, over 972517.79 frames.], batch size: 25, lr: 2.88e-04
2022-05-05 23:22:12,741 INFO [train.py:715] (4/8) Epoch 7, batch 26000, loss[loss=0.1345, simple_loss=0.2115, pruned_loss=0.02875, over 4918.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2176, pruned_loss=0.03708, over 972069.61 frames.], batch size: 18, lr: 2.88e-04
2022-05-05 23:22:54,184 INFO [train.py:715] (4/8) Epoch 7, batch 26050, loss[loss=0.1443, simple_loss=0.235, pruned_loss=0.0268, over 4862.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2175, pruned_loss=0.03713, over 972648.29 frames.], batch size: 16, lr: 2.88e-04
2022-05-05 23:23:36,129 INFO [train.py:715] (4/8) Epoch 7, batch 26100, loss[loss=0.1526, simple_loss=0.2294, pruned_loss=0.03793, over 4845.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03679, over 972004.46 frames.], batch size: 15, lr: 2.88e-04
2022-05-05 23:24:16,476 INFO [train.py:715] (4/8) Epoch 7, batch 26150, loss[loss=0.1378, simple_loss=0.2104, pruned_loss=0.03257, over 4931.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2166, pruned_loss=0.03655, over 971903.32 frames.], batch size: 29, lr: 2.88e-04
2022-05-05 23:24:57,983 INFO [train.py:715] (4/8) Epoch 7, batch 26200, loss[loss=0.1315, simple_loss=0.1988, pruned_loss=0.03213, over 4992.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2166, pruned_loss=0.03647, over 971908.14 frames.], batch size: 15, lr: 2.88e-04
2022-05-05 23:25:39,228 INFO [train.py:715] (4/8) Epoch 7, batch 26250, loss[loss=0.1576, simple_loss=0.2201, pruned_loss=0.04753, over 4753.00 frames.], tot_loss[loss=0.1452, simple_loss=0.217, pruned_loss=0.03669, over 971071.07 frames.], batch size: 16, lr: 2.88e-04
2022-05-05 23:26:19,606 INFO [train.py:715] (4/8) Epoch 7, batch 26300, loss[loss=0.127, simple_loss=0.2083, pruned_loss=0.02288, over 4749.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2172, pruned_loss=0.03646, over 972127.24 frames.], batch size: 16, lr: 2.88e-04
2022-05-05 23:26:59,769 INFO [train.py:715] (4/8) Epoch 7, batch 26350, loss[loss=0.1521, simple_loss=0.2165, pruned_loss=0.04385, over 4897.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2176, pruned_loss=0.03687, over 972142.25 frames.], batch size: 19, lr: 2.88e-04
2022-05-05 23:27:40,219 INFO [train.py:715] (4/8) Epoch 7, batch 26400, loss[loss=0.1421, simple_loss=0.215, pruned_loss=0.03457, over 4936.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2187, pruned_loss=0.03715, over 972274.21 frames.], batch size: 35, lr: 2.87e-04
2022-05-05 23:28:20,879 INFO [train.py:715] (4/8) Epoch 7, batch 26450, loss[loss=0.1185, simple_loss=0.194, pruned_loss=0.02151, over 4789.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2176, pruned_loss=0.03643, over 971521.85 frames.], batch size: 14, lr: 2.87e-04
2022-05-05 23:29:00,625 INFO [train.py:715] (4/8) Epoch 7, batch 26500, loss[loss=0.1492, simple_loss=0.2205, pruned_loss=0.03899, over 4820.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2175, pruned_loss=0.03649, over 971547.38 frames.], batch size: 27, lr: 2.87e-04
2022-05-05 23:29:40,312 INFO [train.py:715] (4/8) Epoch 7, batch 26550, loss[loss=0.1455, simple_loss=0.2213, pruned_loss=0.0349, over 4830.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2175, pruned_loss=0.03662, over 971675.32 frames.], batch size: 13, lr: 2.87e-04
2022-05-05 23:30:20,790 INFO [train.py:715] (4/8) Epoch 7, batch 26600, loss[loss=0.1386, simple_loss=0.2017, pruned_loss=0.03779, over 4924.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03673, over 971548.24 frames.], batch size: 29, lr: 2.87e-04
2022-05-05 23:31:00,455 INFO [train.py:715] (4/8) Epoch 7, batch 26650, loss[loss=0.2071, simple_loss=0.2703, pruned_loss=0.07195, over 4840.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2172, pruned_loss=0.03693, over 971678.96 frames.], batch size: 30, lr: 2.87e-04
2022-05-05 23:31:40,551 INFO [train.py:715] (4/8) Epoch 7, batch 26700, loss[loss=0.1287, simple_loss=0.2036, pruned_loss=0.0269, over 4982.00 frames.], tot_loss[loss=0.146, simple_loss=0.2177, pruned_loss=0.0371, over 972347.06 frames.], batch size: 28, lr: 2.87e-04
2022-05-05 23:32:21,233 INFO [train.py:715] (4/8) Epoch 7, batch 26750, loss[loss=0.1259, simple_loss=0.2018, pruned_loss=0.02506, over 4810.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2178, pruned_loss=0.03681, over 971806.09 frames.], batch size: 25, lr: 2.87e-04
2022-05-05 23:33:01,205 INFO [train.py:715] (4/8) Epoch 7, batch 26800, loss[loss=0.1478, simple_loss=0.2246, pruned_loss=0.03548, over 4883.00 frames.], tot_loss[loss=0.1462, simple_loss=0.218, pruned_loss=0.03717, over 971462.80 frames.], batch size: 19, lr: 2.87e-04
2022-05-05 23:33:40,950 INFO [train.py:715] (4/8) Epoch 7, batch 26850, loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02923, over 4903.00 frames.], tot_loss[loss=0.146, simple_loss=0.2176, pruned_loss=0.03717, over 971322.31 frames.], batch size: 18, lr: 2.87e-04
2022-05-05 23:34:21,604 INFO [train.py:715] (4/8) Epoch 7, batch 26900, loss[loss=0.1359, simple_loss=0.2143, pruned_loss=0.02875, over 4846.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2169, pruned_loss=0.03664, over 972178.72 frames.], batch size: 26, lr: 2.87e-04
2022-05-05 23:35:02,615 INFO [train.py:715] (4/8) Epoch 7, batch 26950, loss[loss=0.1128, simple_loss=0.1806, pruned_loss=0.02252, over 4907.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2174, pruned_loss=0.03719, over 971543.48 frames.], batch size: 19, lr: 2.87e-04
2022-05-05 23:35:42,949 INFO [train.py:715] (4/8) Epoch 7, batch 27000, loss[loss=0.1324, simple_loss=0.1955, pruned_loss=0.03466, over 4805.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2174, pruned_loss=0.03744, over 971092.30 frames.], batch size: 14, lr: 2.87e-04
2022-05-05 23:35:42,950 INFO [train.py:733] (4/8) Computing validation loss
2022-05-05 23:35:52,667 INFO [train.py:742] (4/8) Epoch 7, validation: loss=0.108, simple_loss=0.1928, pruned_loss=0.01156, over 914524.00 frames.
2022-05-05 23:36:33,213 INFO [train.py:715] (4/8) Epoch 7, batch 27050, loss[loss=0.126, simple_loss=0.1869, pruned_loss=0.03253, over 4966.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2175, pruned_loss=0.03736, over 971247.11 frames.], batch size: 14, lr: 2.87e-04
2022-05-05 23:37:14,389 INFO [train.py:715] (4/8) Epoch 7, batch 27100, loss[loss=0.1289, simple_loss=0.2151, pruned_loss=0.02138, over 4888.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2172, pruned_loss=0.03702, over 972072.25 frames.], batch size: 22, lr: 2.87e-04
2022-05-05 23:37:56,259 INFO [train.py:715] (4/8) Epoch 7, batch 27150, loss[loss=0.1484, simple_loss=0.2127, pruned_loss=0.04205, over 4831.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03707, over 972819.65 frames.], batch size: 30, lr: 2.87e-04
2022-05-05 23:38:37,509 INFO [train.py:715] (4/8) Epoch 7, batch 27200, loss[loss=0.1285, simple_loss=0.1962, pruned_loss=0.03044, over 4737.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2171, pruned_loss=0.03652, over 972508.92 frames.], batch size: 12, lr: 2.87e-04
2022-05-05 23:39:18,987 INFO [train.py:715] (4/8) Epoch 7, batch 27250, loss[loss=0.12, simple_loss=0.1884, pruned_loss=0.02583, over 4841.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2167, pruned_loss=0.03636, over 972546.07 frames.], batch size: 30, lr: 2.87e-04
2022-05-05 23:40:00,802 INFO [train.py:715] (4/8) Epoch 7, batch 27300, loss[loss=0.1518, simple_loss=0.2179, pruned_loss=0.0429, over 4826.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2161, pruned_loss=0.03601, over 973372.63 frames.], batch size: 15, lr: 2.87e-04
2022-05-05 23:40:41,768 INFO [train.py:715] (4/8) Epoch 7, batch 27350, loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02811, over 4980.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2171, pruned_loss=0.03624, over 973033.81 frames.], batch size: 28, lr: 2.87e-04
2022-05-05 23:41:23,059 INFO [train.py:715] (4/8) Epoch 7, batch 27400, loss[loss=0.1374, simple_loss=0.2119, pruned_loss=0.03142, over 4762.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2176, pruned_loss=0.03671, over 972827.18 frames.], batch size: 14, lr: 2.87e-04
2022-05-05 23:42:04,088 INFO [train.py:715] (4/8) Epoch 7, batch 27450, loss[loss=0.1563, simple_loss=0.2223, pruned_loss=0.04519, over 4851.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2178, pruned_loss=0.03722, over 972560.45 frames.], batch size: 30, lr: 2.87e-04
2022-05-05 23:42:45,310 INFO [train.py:715] (4/8) Epoch 7, batch 27500, loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.03673, over 4900.00 frames.], tot_loss[loss=0.146, simple_loss=0.2174, pruned_loss=0.03736, over 971516.32 frames.], batch size: 17, lr: 2.87e-04
2022-05-05 23:43:25,880 INFO [train.py:715] (4/8) Epoch 7, batch 27550, loss[loss=0.1339, simple_loss=0.2067, pruned_loss=0.03055, over 4975.00 frames.], tot_loss[loss=0.1478, simple_loss=0.2191, pruned_loss=0.03823, over 972044.04 frames.], batch size: 35, lr: 2.87e-04
2022-05-05 23:44:06,397 INFO [train.py:715] (4/8) Epoch 7, batch 27600, loss[loss=0.1575, simple_loss=0.2271, pruned_loss=0.04402, over 4831.00 frames.], tot_loss[loss=0.1476, simple_loss=0.2189, pruned_loss=0.03813, over 971307.88 frames.], batch size: 15, lr: 2.87e-04
2022-05-05 23:44:47,790 INFO [train.py:715] (4/8) Epoch 7, batch 27650, loss[loss=0.1398, simple_loss=0.2101, pruned_loss=0.03474, over 4950.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2182, pruned_loss=0.03779, over 971943.08 frames.], batch size: 21, lr: 2.87e-04
2022-05-05 23:45:28,506 INFO [train.py:715] (4/8) Epoch 7, batch 27700, loss[loss=0.1376, simple_loss=0.2004, pruned_loss=0.0374, over 4802.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2179, pruned_loss=0.03785, over 972653.18 frames.], batch size: 13, lr: 2.87e-04
2022-05-05 23:46:09,246 INFO [train.py:715] (4/8) Epoch 7, batch 27750, loss[loss=0.1408, simple_loss=0.2142, pruned_loss=0.0337, over 4783.00 frames.], tot_loss[loss=0.1477, simple_loss=0.2189, pruned_loss=0.03821, over 972653.84 frames.], batch size: 18, lr: 2.87e-04
2022-05-05 23:46:50,126 INFO [train.py:715] (4/8) Epoch 7, batch 27800, loss[loss=0.1235, simple_loss=0.1972, pruned_loss=0.02489, over 4813.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2181, pruned_loss=0.03764, over 971422.19 frames.], batch size: 27, lr: 2.87e-04
2022-05-05 23:47:31,341 INFO [train.py:715] (4/8) Epoch 7, batch 27850, loss[loss=0.1637, simple_loss=0.2351, pruned_loss=0.04611, over 4800.00 frames.], tot_loss[loss=0.1474, simple_loss=0.2186, pruned_loss=0.03813, over 971185.19 frames.], batch size: 12, lr: 2.87e-04
2022-05-05 23:48:11,407 INFO [train.py:715] (4/8) Epoch 7, batch 27900, loss[loss=0.1518, simple_loss=0.2139, pruned_loss=0.04489, over 4845.00 frames.], tot_loss[loss=0.1477, simple_loss=0.219, pruned_loss=0.03816, over 971279.91 frames.], batch size: 30, lr: 2.87e-04
2022-05-05 23:48:52,367 INFO [train.py:715] (4/8) Epoch 7, batch 27950, loss[loss=0.1127, simple_loss=0.1881, pruned_loss=0.0187, over 4827.00 frames.], tot_loss[loss=0.1472, simple_loss=0.2186, pruned_loss=0.03786, over 971340.74 frames.], batch size: 12, lr: 2.87e-04
2022-05-05 23:49:33,554 INFO [train.py:715] (4/8) Epoch 7, batch 28000, loss[loss=0.1699, simple_loss=0.2421, pruned_loss=0.04889, over 4895.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2185, pruned_loss=0.03786, over 972325.76 frames.], batch size: 19, lr: 2.87e-04
2022-05-05 23:50:14,245 INFO [train.py:715] (4/8) Epoch 7, batch 28050, loss[loss=0.1445, simple_loss=0.2204, pruned_loss=0.03431, over 4896.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2182, pruned_loss=0.03738, over 972533.61 frames.], batch size: 22, lr: 2.87e-04
2022-05-05 23:50:54,410 INFO [train.py:715] (4/8) Epoch 7, batch 28100, loss[loss=0.1193, simple_loss=0.1966, pruned_loss=0.02103, over 4773.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2185, pruned_loss=0.03717, over 972803.48 frames.], batch size: 17, lr: 2.87e-04
2022-05-05 23:51:35,206 INFO [train.py:715] (4/8) Epoch 7, batch 28150, loss[loss=0.1158, simple_loss=0.1917, pruned_loss=0.0199, over 4804.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2189, pruned_loss=0.03748, over 972604.29 frames.], batch size: 13, lr: 2.87e-04
2022-05-05 23:52:16,649 INFO [train.py:715] (4/8) Epoch 7, batch 28200, loss[loss=0.1235, simple_loss=0.2021, pruned_loss=0.02243, over 4879.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2191, pruned_loss=0.037, over 972583.25 frames.], batch size: 22, lr: 2.87e-04
2022-05-05 23:52:56,857 INFO [train.py:715] (4/8) Epoch 7, batch 28250, loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03341, over 4855.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2186, pruned_loss=0.03701, over 972319.96 frames.], batch size: 38, lr: 2.87e-04
2022-05-05 23:53:38,372 INFO [train.py:715] (4/8) Epoch 7, batch 28300, loss[loss=0.1725, simple_loss=0.2345, pruned_loss=0.0553, over 4828.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2183, pruned_loss=0.03705, over 972168.49 frames.], batch size: 30, lr: 2.86e-04
2022-05-05 23:54:21,486 INFO [train.py:715] (4/8) Epoch 7, batch 28350, loss[loss=0.1585, simple_loss=0.2384, pruned_loss=0.03933, over 4759.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2183, pruned_loss=0.03703, over 972051.51 frames.], batch size: 19, lr: 2.86e-04
2022-05-05 23:55:01,298 INFO [train.py:715] (4/8) Epoch 7, batch 28400, loss[loss=0.1549, simple_loss=0.2202, pruned_loss=0.04479, over 4858.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2188, pruned_loss=0.03734, over 970721.16 frames.], batch size: 20, lr: 2.86e-04
2022-05-05 23:55:40,831 INFO [train.py:715] (4/8) Epoch 7, batch 28450, loss[loss=0.1284, simple_loss=0.2002, pruned_loss=0.02835, over 4961.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2187, pruned_loss=0.03761, over 971865.52 frames.], batch size: 35, lr: 2.86e-04
2022-05-05 23:56:20,934 INFO [train.py:715] (4/8) Epoch 7, batch 28500, loss[loss=0.1675, simple_loss=0.2366, pruned_loss=0.04918, over 4791.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2185, pruned_loss=0.03734, over 971529.09 frames.], batch size: 24, lr: 2.86e-04
2022-05-05 23:57:01,425 INFO [train.py:715] (4/8) Epoch 7, batch 28550, loss[loss=0.1294, simple_loss=0.1982, pruned_loss=0.03026, over 4814.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2181, pruned_loss=0.03703, over 971584.65 frames.], batch size: 13, lr: 2.86e-04
2022-05-05 23:57:41,417 INFO [train.py:715] (4/8) Epoch 7, batch 28600, loss[loss=0.1343, simple_loss=0.2064, pruned_loss=0.03107, over 4988.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03689, over 971717.25 frames.], batch size: 31, lr: 2.86e-04
2022-05-05 23:58:21,636 INFO [train.py:715] (4/8) Epoch 7, batch 28650, loss[loss=0.1413, simple_loss=0.2134, pruned_loss=0.03458, over 4938.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2175, pruned_loss=0.03683, over 972110.05 frames.], batch size: 21, lr: 2.86e-04
2022-05-05 23:59:03,073 INFO [train.py:715] (4/8) Epoch 7, batch 28700, loss[loss=0.1621, simple_loss=0.2409, pruned_loss=0.0416, over 4966.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03707, over 972118.86 frames.], batch size: 39, lr: 2.86e-04
2022-05-05 23:59:43,955 INFO [train.py:715] (4/8) Epoch 7, batch 28750, loss[loss=0.1505, simple_loss=0.2303, pruned_loss=0.03532, over 4757.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2178, pruned_loss=0.03695, over 972552.87 frames.], batch size: 19, lr: 2.86e-04
2022-05-06 00:00:24,187 INFO [train.py:715] (4/8) Epoch 7, batch 28800, loss[loss=0.1381, simple_loss=0.2067, pruned_loss=0.03478, over 4681.00 frames.], tot_loss[loss=0.146, simple_loss=0.218, pruned_loss=0.03697, over 972426.97 frames.], batch size: 15, lr: 2.86e-04
2022-05-06 00:01:04,805 INFO [train.py:715] (4/8) Epoch 7, batch 28850, loss[loss=0.1447, simple_loss=0.2153, pruned_loss=0.03706, over 4777.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03676, over 972283.54 frames.], batch size: 18, lr: 2.86e-04
2022-05-06 00:01:45,177 INFO [train.py:715] (4/8) Epoch 7, batch 28900, loss[loss=0.1555, simple_loss=0.2232, pruned_loss=0.04391, over 4859.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2167, pruned_loss=0.03676, over 972060.93 frames.], batch size: 20, lr: 2.86e-04
2022-05-06 00:02:24,695 INFO [train.py:715] (4/8) Epoch 7, batch 28950, loss[loss=0.1349, simple_loss=0.2103, pruned_loss=0.02972, over 4688.00 frames.], tot_loss[loss=0.1441, simple_loss=0.216, pruned_loss=0.03617, over 972847.56 frames.], batch size: 15, lr: 2.86e-04
2022-05-06 00:03:04,250 INFO [train.py:715] (4/8) Epoch 7, batch 29000, loss[loss=0.155, simple_loss=0.2293, pruned_loss=0.04036, over 4813.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2163, pruned_loss=0.03668, over 971545.61 frames.], batch size: 26, lr: 2.86e-04
2022-05-06 00:03:44,915 INFO [train.py:715] (4/8) Epoch 7, batch 29050, loss[loss=0.1654, simple_loss=0.2332, pruned_loss=0.04878, over 4754.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2173, pruned_loss=0.03695, over 971456.41 frames.], batch size: 19, lr: 2.86e-04
2022-05-06 00:04:24,497 INFO [train.py:715] (4/8) Epoch 7, batch 29100, loss[loss=0.1975, simple_loss=0.2779, pruned_loss=0.05857, over 4744.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2171, pruned_loss=0.03673, over 971491.51 frames.], batch size: 16, lr: 2.86e-04
2022-05-06 00:05:04,254 INFO [train.py:715] (4/8) Epoch 7, batch 29150, loss[loss=0.1573, simple_loss=0.2319, pruned_loss=0.04138, over 4978.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2176, pruned_loss=0.03677, over 972182.18 frames.], batch size: 24, lr: 2.86e-04
2022-05-06 00:05:44,148 INFO [train.py:715] (4/8) Epoch 7, batch 29200, loss[loss=0.1537, simple_loss=0.2251, pruned_loss=0.04112, over 4984.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2173, pruned_loss=0.03668, over 972184.17 frames.], batch size: 15, lr: 2.86e-04
2022-05-06 00:06:24,422 INFO [train.py:715] (4/8) Epoch 7, batch 29250, loss[loss=0.1456, simple_loss=0.2215, pruned_loss=0.03485, over 4948.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2176, pruned_loss=0.03663, over 972358.71 frames.], batch size: 29, lr: 2.86e-04
2022-05-06 00:07:04,326 INFO [train.py:715] (4/8) Epoch 7, batch 29300, loss[loss=0.1408, simple_loss=0.2133, pruned_loss=0.03418, over 4778.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03678, over 972593.94 frames.], batch size: 14, lr: 2.86e-04
2022-05-06 00:07:44,017 INFO [train.py:715] (4/8) Epoch 7, batch 29350, loss[loss=0.1314, simple_loss=0.2047, pruned_loss=0.0291, over 4850.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03759, over 972226.67 frames.], batch size: 20, lr: 2.86e-04
2022-05-06 00:08:24,285 INFO [train.py:715] (4/8) Epoch 7, batch 29400, loss[loss=0.1265, simple_loss=0.1999, pruned_loss=0.02655, over 4845.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2176, pruned_loss=0.03707, over 972638.35 frames.], batch size: 26, lr: 2.86e-04
2022-05-06 00:09:03,565 INFO [train.py:715] (4/8) Epoch 7, batch 29450, loss[loss=0.1724, simple_loss=0.2474, pruned_loss=0.0487, over 4828.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2166, pruned_loss=0.03645, over 972014.05 frames.], batch size: 13, lr: 2.86e-04
2022-05-06 00:09:43,848 INFO [train.py:715] (4/8) Epoch 7, batch 29500, loss[loss=0.1462, simple_loss=0.2163, pruned_loss=0.038, over 4834.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03685, over 971416.78 frames.], batch size: 30, lr: 2.86e-04
2022-05-06 00:10:23,571 INFO [train.py:715] (4/8) Epoch 7, batch 29550, loss[loss=0.1247, simple_loss=0.2017, pruned_loss=0.02386, over 4917.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2169, pruned_loss=0.0368, over 971982.48 frames.], batch size: 29, lr: 2.86e-04
2022-05-06 00:11:03,253 INFO [train.py:715] (4/8) Epoch 7, batch 29600, loss[loss=0.2144, simple_loss=0.2756, pruned_loss=0.07663, over 4882.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.03668, over 972317.50 frames.], batch size: 16, lr: 2.86e-04
2022-05-06 00:11:43,209 INFO [train.py:715] (4/8) Epoch 7, batch 29650, loss[loss=0.149, simple_loss=0.2259, pruned_loss=0.036, over 4985.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2168, pruned_loss=0.03686, over 972272.61 frames.], batch size: 25, lr: 2.86e-04
2022-05-06 00:12:23,007 INFO [train.py:715] (4/8) Epoch 7, batch 29700, loss[loss=0.1879, simple_loss=0.2479, pruned_loss=0.06391, over 4883.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2161, pruned_loss=0.03648, over 972644.12 frames.], batch size: 32, lr: 2.86e-04
2022-05-06 00:13:02,661 INFO [train.py:715] (4/8) Epoch 7, batch 29750, loss[loss=0.1559, simple_loss=0.2334, pruned_loss=0.0392, over 4887.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2165, pruned_loss=0.03642, over 972104.72 frames.], batch size: 39, lr: 2.86e-04
2022-05-06 00:13:42,294 INFO [train.py:715] (4/8) Epoch 7, batch 29800, loss[loss=0.1324, simple_loss=0.2148, pruned_loss=0.02494, over 4885.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2171, pruned_loss=0.0366, over 971327.79 frames.], batch size: 22, lr: 2.86e-04
2022-05-06 00:14:22,413 INFO [train.py:715] (4/8) Epoch 7, batch 29850, loss[loss=0.1507, simple_loss=0.2169, pruned_loss=0.04222, over 4919.00 frames.], tot_loss[loss=0.145, simple_loss=0.2168, pruned_loss=0.0366, over 972171.90 frames.], batch size: 17, lr: 2.86e-04
2022-05-06 00:15:02,282 INFO [train.py:715] (4/8) Epoch 7, batch 29900, loss[loss=0.1432, simple_loss=0.2149, pruned_loss=0.03571, over 4803.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2168, pruned_loss=0.03577, over 971642.15 frames.], batch size: 14, lr: 2.86e-04
2022-05-06 00:15:41,860 INFO [train.py:715] (4/8) Epoch 7, batch 29950, loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.03373, over 4869.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.0357, over 971320.25 frames.], batch size: 30, lr: 2.86e-04
2022-05-06 00:16:21,227 INFO [train.py:715] (4/8) Epoch 7, batch 30000, loss[loss=0.1511, simple_loss=0.2221, pruned_loss=0.04009, over 4770.00 frames.], tot_loss[loss=0.1436, simple_loss=0.216, pruned_loss=0.03559, over 970869.67 frames.], batch size: 19, lr: 2.86e-04
2022-05-06 00:16:21,228 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 00:16:41,747 INFO [train.py:742] (4/8) Epoch 7, validation: loss=0.1081, simple_loss=0.1929, pruned_loss=0.01164, over 914524.00 frames.
2022-05-06 00:17:21,556 INFO [train.py:715] (4/8) Epoch 7, batch 30050, loss[loss=0.1477, simple_loss=0.2184, pruned_loss=0.03849, over 4772.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2166, pruned_loss=0.03585, over 971196.75 frames.], batch size: 19, lr: 2.86e-04
2022-05-06 00:18:00,838 INFO [train.py:715] (4/8) Epoch 7, batch 30100, loss[loss=0.1354, simple_loss=0.2009, pruned_loss=0.03491, over 4777.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03588, over 972007.07 frames.], batch size: 17, lr: 2.86e-04
2022-05-06 00:18:40,786 INFO [train.py:715] (4/8) Epoch 7, batch 30150, loss[loss=0.1281, simple_loss=0.2036, pruned_loss=0.02628, over 4803.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.03629, over 971454.91 frames.], batch size: 14, lr: 2.86e-04
2022-05-06 00:19:20,432 INFO [train.py:715] (4/8) Epoch 7, batch 30200, loss[loss=0.1585, simple_loss=0.2312, pruned_loss=0.04288, over 4790.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2159, pruned_loss=0.03616, over 972576.44 frames.], batch size: 24, lr: 2.85e-04
2022-05-06 00:20:00,687 INFO [train.py:715] (4/8) Epoch 7, batch 30250, loss[loss=0.178, simple_loss=0.2488, pruned_loss=0.05356, over 4865.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2158, pruned_loss=0.036, over 972596.24 frames.], batch size: 38, lr: 2.85e-04
2022-05-06 00:20:39,866 INFO [train.py:715] (4/8) Epoch 7, batch 30300, loss[loss=0.153, simple_loss=0.2144, pruned_loss=0.04574, over 4779.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2162, pruned_loss=0.03617, over 972168.60 frames.], batch size: 14, lr: 2.85e-04
2022-05-06 00:21:19,491 INFO [train.py:715] (4/8) Epoch 7, batch 30350, loss[loss=0.1253, simple_loss=0.2027, pruned_loss=0.02399, over 4969.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2164, pruned_loss=0.03638, over 972015.86 frames.], batch size: 28, lr: 2.85e-04
2022-05-06 00:21:58,989 INFO [train.py:715] (4/8) Epoch 7, batch 30400, loss[loss=0.1445, simple_loss=0.2172, pruned_loss=0.03594, over 4879.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.0361, over 972683.60 frames.], batch size: 16, lr: 2.85e-04
2022-05-06 00:22:38,981 INFO [train.py:715] (4/8) Epoch 7, batch 30450, loss[loss=0.1373, simple_loss=0.2165, pruned_loss=0.029, over 4864.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.0359, over 972933.85 frames.], batch size: 22, lr: 2.85e-04
2022-05-06 00:23:18,897 INFO [train.py:715] (4/8) Epoch 7, batch 30500, loss[loss=0.1572, simple_loss=0.2306, pruned_loss=0.04186, over 4873.00 frames.], tot_loss[loss=0.144, simple_loss=0.216, pruned_loss=0.03603, over 973518.21 frames.], batch size: 20, lr: 2.85e-04
2022-05-06 00:23:58,830 INFO [train.py:715] (4/8) Epoch 7, batch 30550, loss[loss=0.139, simple_loss=0.2007, pruned_loss=0.03863, over 4862.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2162, pruned_loss=0.03624, over 973051.11 frames.], batch size: 32, lr: 2.85e-04
2022-05-06 00:24:38,529 INFO [train.py:715] (4/8) Epoch 7, batch 30600, loss[loss=0.1585, simple_loss=0.2433, pruned_loss=0.03681, over 4795.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2164, pruned_loss=0.03632, over 971316.82 frames.], batch size: 21, lr: 2.85e-04
2022-05-06 00:25:18,165 INFO [train.py:715] (4/8) Epoch 7, batch 30650, loss[loss=0.1551, simple_loss=0.2239, pruned_loss=0.04318, over 4871.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2159, pruned_loss=0.03593, over 971377.15 frames.], batch size: 22, lr: 2.85e-04
2022-05-06 00:25:57,786 INFO [train.py:715] (4/8) Epoch 7, batch 30700, loss[loss=0.124, simple_loss=0.2051, pruned_loss=0.02142, over 4806.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2165, pruned_loss=0.03624, over 971638.43 frames.], batch size: 25, lr: 2.85e-04
2022-05-06 00:26:36,841 INFO [train.py:715] (4/8) Epoch 7, batch 30750, loss[loss=0.1589, simple_loss=0.2051, pruned_loss=0.05633, over 4883.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2168, pruned_loss=0.03682, over 971899.38 frames.], batch size: 32, lr: 2.85e-04
2022-05-06 00:27:15,906 INFO [train.py:715] (4/8) Epoch 7, batch 30800, loss[loss=0.1174, simple_loss=0.1899, pruned_loss=0.02248, over 4904.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2173, pruned_loss=0.03708, over 972435.39 frames.], batch size: 19, lr: 2.85e-04
2022-05-06 00:27:55,687 INFO [train.py:715] (4/8) Epoch 7, batch 30850, loss[loss=0.1491, simple_loss=0.2268, pruned_loss=0.03566, over 4970.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2166, pruned_loss=0.03701, over 972387.57 frames.], batch size: 40, lr: 2.85e-04
2022-05-06 00:28:35,192 INFO [train.py:715] (4/8) Epoch 7, batch 30900, loss[loss=0.1253, simple_loss=0.1896, pruned_loss=0.03047, over 4903.00 frames.], tot_loss[loss=0.1456, simple_loss=0.217, pruned_loss=0.03707, over 972078.25 frames.], batch size: 17, lr: 2.85e-04
2022-05-06 00:29:15,591 INFO [train.py:715] (4/8) Epoch 7, batch 30950, loss[loss=0.1224, simple_loss=0.2056, pruned_loss=0.01958, over 4970.00 frames.], tot_loss[loss=0.145, simple_loss=0.2166, pruned_loss=0.03666, over 972402.01 frames.], batch size: 24, lr: 2.85e-04
2022-05-06 00:29:54,981 INFO [train.py:715] (4/8) Epoch 7, batch 31000, loss[loss=0.1221, simple_loss=0.1982, pruned_loss=0.02298, over 4803.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2166, pruned_loss=0.0366, over 972438.71 frames.], batch size: 12, lr: 2.85e-04
2022-05-06 00:30:34,537 INFO [train.py:715] (4/8) Epoch 7, batch 31050, loss[loss=0.1324, simple_loss=0.2089, pruned_loss=0.02796, over 4982.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2168, pruned_loss=0.03668, over 972626.77 frames.], batch size: 14, lr: 2.85e-04
2022-05-06 00:31:14,376 INFO [train.py:715] (4/8) Epoch 7, batch 31100, loss[loss=0.1422, simple_loss=0.2198, pruned_loss=0.03233, over 4831.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03698, over 972800.83 frames.], batch size: 27, lr: 2.85e-04
2022-05-06 00:31:54,494 INFO [train.py:715] (4/8) Epoch 7, batch 31150, loss[loss=0.1556, simple_loss=0.2258, pruned_loss=0.04268, over 4948.00 frames.], tot_loss[loss=0.1461, simple_loss=0.2183, pruned_loss=0.03694, over 972645.29 frames.], batch size: 21, lr: 2.85e-04
2022-05-06 00:32:33,850 INFO [train.py:715] (4/8) Epoch 7, batch 31200, loss[loss=0.1507, simple_loss=0.2192, pruned_loss=0.0411, over 4842.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2178, pruned_loss=0.03656, over 971685.09 frames.], batch size: 30, lr: 2.85e-04
2022-05-06 00:33:13,813 INFO [train.py:715] (4/8) Epoch 7, batch 31250, loss[loss=0.1549, simple_loss=0.2308, pruned_loss=0.03952, over 4930.00 frames.], tot_loss[loss=0.145, simple_loss=0.2176, pruned_loss=0.03625, over 971872.89 frames.], batch size: 23, lr: 2.85e-04
2022-05-06 00:33:54,558 INFO [train.py:715] (4/8) Epoch 7, batch 31300, loss[loss=0.1785, simple_loss=0.2482, pruned_loss=0.05441, over 4700.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2171, pruned_loss=0.03587, over 972294.04 frames.], batch size: 15, lr: 2.85e-04
2022-05-06 00:34:34,121 INFO [train.py:715] (4/8) Epoch 7, batch 31350, loss[loss=0.1322, simple_loss=0.2038, pruned_loss=0.03028, over 4795.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03669, over 971902.31 frames.], batch size: 24, lr: 2.85e-04
2022-05-06 00:35:14,071 INFO [train.py:715] (4/8) Epoch 7, batch 31400, loss[loss=0.1561, simple_loss=0.2202, pruned_loss=0.04597, over 4804.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2181, pruned_loss=0.03664, over 971628.93 frames.], batch size: 24, lr: 2.85e-04
2022-05-06 00:35:53,414 INFO [train.py:715] (4/8) Epoch 7, batch 31450, loss[loss=0.137, simple_loss=0.209, pruned_loss=0.03245, over 4988.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2177, pruned_loss=0.03655, over 972042.59 frames.], batch size: 31, lr: 2.85e-04
2022-05-06 00:36:33,191 INFO [train.py:715] (4/8) Epoch 7, batch 31500, loss[loss=0.145, simple_loss=0.215, pruned_loss=0.03756, over 4815.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2174, pruned_loss=0.03619, over 972165.86 frames.], batch size: 15, lr: 2.85e-04
2022-05-06 00:37:12,317 INFO [train.py:715] (4/8) Epoch 7, batch 31550, loss[loss=0.1108, simple_loss=0.183, pruned_loss=0.01929, over 4920.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2169, pruned_loss=0.03577, over 972644.58 frames.], batch size: 18, lr: 2.85e-04
2022-05-06 00:37:52,277 INFO [train.py:715] (4/8) Epoch 7, batch 31600, loss[loss=0.1593, simple_loss=0.2358, pruned_loss=0.0414, over 4780.00 frames.], tot_loss[loss=0.144, simple_loss=0.2166, pruned_loss=0.03566, over 971819.13 frames.], batch size: 18, lr: 2.85e-04
2022-05-06 00:38:32,124 INFO [train.py:715] (4/8) Epoch 7, batch 31650, loss[loss=0.1242, simple_loss=0.1997, pruned_loss=0.02437, over 4958.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2165, pruned_loss=0.03586, over 971832.88 frames.], batch size: 35, lr: 2.85e-04
2022-05-06 00:39:11,522 INFO [train.py:715] (4/8) Epoch 7, batch 31700, loss[loss=0.1639, simple_loss=0.2297, pruned_loss=0.04911, over 4799.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2166, pruned_loss=0.0364, over 970854.62 frames.], batch size: 15, lr: 2.85e-04
2022-05-06 00:39:51,223 INFO [train.py:715] (4/8) Epoch 7, batch 31750, loss[loss=0.1289, simple_loss=0.2048, pruned_loss=0.02654, over 4968.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2178, pruned_loss=0.03743, over 971338.98 frames.], batch size: 24, lr: 2.85e-04
2022-05-06 00:40:30,494 INFO [train.py:715] (4/8) Epoch 7, batch 31800, loss[loss=0.1449, simple_loss=0.223, pruned_loss=0.03344, over 4984.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2182, pruned_loss=0.03749, over 971478.29 frames.], batch size: 35, lr: 2.85e-04
2022-05-06 00:41:09,623 INFO [train.py:715] (4/8) Epoch 7, batch 31850, loss[loss=0.1421, simple_loss=0.2212, pruned_loss=0.03144, over 4797.00 frames.], tot_loss[loss=0.1469, simple_loss=0.2186, pruned_loss=0.03757, over 972439.63 frames.], batch size: 14, lr: 2.85e-04
2022-05-06 00:41:49,883 INFO [train.py:715] (4/8) Epoch 7, batch 31900, loss[loss=0.1563, simple_loss=0.2293, pruned_loss=0.04162, over 4982.00 frames.], tot_loss[loss=0.1467, simple_loss=0.2184, pruned_loss=0.03752, over 972713.54 frames.], batch size: 24, lr: 2.85e-04
2022-05-06 00:42:30,619 INFO [train.py:715] (4/8) Epoch 7, batch 31950, loss[loss=0.1495, simple_loss=0.2164, pruned_loss=0.04128, over 4960.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2181, pruned_loss=0.03734, over 972101.70 frames.], batch size: 39, lr: 2.85e-04
2022-05-06 00:43:11,087 INFO [train.py:715] (4/8) Epoch 7, batch 32000, loss[loss=0.1588, simple_loss=0.2335, pruned_loss=0.04212, over 4809.00 frames.], tot_loss[loss=0.1463, simple_loss=0.218, pruned_loss=0.03726, over 972294.80 frames.], batch size: 25, lr: 2.85e-04
2022-05-06 00:43:50,735 INFO [train.py:715] (4/8) Epoch 7, batch 32050, loss[loss=0.1389, simple_loss=0.2205, pruned_loss=0.0286, over 4829.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2173, pruned_loss=0.03702, over 972390.12 frames.], batch size: 25, lr: 2.85e-04
2022-05-06 00:44:30,666 INFO [train.py:715] (4/8) Epoch 7, batch 32100, loss[loss=0.1471, simple_loss=0.2229, pruned_loss=0.0357, over 4895.00 frames.], tot_loss[loss=0.1453, simple_loss=0.217, pruned_loss=0.03677, over 972355.70 frames.], batch size: 22, lr: 2.85e-04
2022-05-06 00:45:10,479 INFO [train.py:715] (4/8) Epoch 7, batch 32150, loss[loss=0.176, simple_loss=0.2511, pruned_loss=0.05049, over 4695.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2172, pruned_loss=0.03703, over 972510.27 frames.], batch size: 15, lr: 2.84e-04
2022-05-06 00:45:50,032 INFO [train.py:715] (4/8) Epoch 7, batch 32200, loss[loss=0.1439, simple_loss=0.2181, pruned_loss=0.03482, over 4945.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2167, pruned_loss=0.03677, over 972443.58 frames.], batch size: 29, lr: 2.84e-04
2022-05-06 00:46:29,883 INFO [train.py:715] (4/8) Epoch 7, batch 32250, loss[loss=0.1328, simple_loss=0.2197, pruned_loss=0.02291, over 4908.00 frames.], tot_loss[loss=0.145, simple_loss=0.2165, pruned_loss=0.0368, over 972049.67 frames.], batch size: 17, lr: 2.84e-04
2022-05-06 00:47:09,674 INFO [train.py:715] (4/8) Epoch 7, batch 32300, loss[loss=0.196, simple_loss=0.2697, pruned_loss=0.0611, over 4759.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2173, pruned_loss=0.03693, over 972439.71 frames.], batch size: 14, lr: 2.84e-04
2022-05-06 00:47:50,013 INFO [train.py:715] (4/8) Epoch 7, batch 32350, loss[loss=0.1412, simple_loss=0.2181, pruned_loss=0.03218, over 4985.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2181, pruned_loss=0.03722, over 973239.45 frames.], batch size: 14, lr: 2.84e-04
2022-05-06 00:48:29,374 INFO [train.py:715] (4/8) Epoch 7, batch 32400, loss[loss=0.1632, simple_loss=0.2283, pruned_loss=0.04908, over 4902.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2181, pruned_loss=0.03714, over 973057.49 frames.], batch size: 22, lr: 2.84e-04
2022-05-06 00:49:09,264 INFO [train.py:715] (4/8) Epoch 7, batch 32450, loss[loss=0.1477, simple_loss=0.2202, pruned_loss=0.03762, over 4908.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2175, pruned_loss=0.0367, over 972494.34 frames.], batch size: 29, lr: 2.84e-04
2022-05-06 00:49:48,737 INFO [train.py:715] (4/8) Epoch 7, batch 32500, loss[loss=0.1357, simple_loss=0.2042, pruned_loss=0.03361, over 4883.00 frames.], tot_loss[loss=0.145, simple_loss=0.2172, pruned_loss=0.03645, over 971732.37 frames.], batch size: 16, lr: 2.84e-04
2022-05-06 00:50:28,300 INFO [train.py:715] (4/8) Epoch 7, batch 32550, loss[loss=0.1398, simple_loss=0.2053, pruned_loss=0.03721, over 4820.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2166, pruned_loss=0.03659, over 971908.83 frames.], batch size: 27, lr: 2.84e-04
2022-05-06 00:51:08,056 INFO [train.py:715] (4/8) Epoch 7, batch 32600, loss[loss=0.1517, simple_loss=0.222, pruned_loss=0.04065, over 4789.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.03633, over 972319.93 frames.], batch size: 18, lr: 2.84e-04
2022-05-06 00:51:47,568 INFO [train.py:715] (4/8) Epoch 7, batch 32650, loss[loss=0.1569, simple_loss=0.2191, pruned_loss=0.04731, over 4907.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.03635, over 972044.66 frames.], batch size: 17, lr: 2.84e-04
2022-05-06 00:52:27,415 INFO [train.py:715] (4/8) Epoch 7, batch 32700, loss[loss=0.1327, simple_loss=0.1914, pruned_loss=0.03698, over 4876.00 frames.], tot_loss[loss=0.144, simple_loss=0.216, pruned_loss=0.03599, over 972059.30 frames.], batch size: 32, lr: 2.84e-04
2022-05-06 00:53:06,823 INFO [train.py:715] (4/8) Epoch 7, batch 32750, loss[loss=0.145, simple_loss=0.2347, pruned_loss=0.02764, over 4906.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2153, pruned_loss=0.03589, over 971363.03 frames.], batch size: 19, lr: 2.84e-04
2022-05-06 00:53:47,306 INFO [train.py:715] (4/8) Epoch 7, batch 32800, loss[loss=0.1573, simple_loss=0.2275, pruned_loss=0.04361, over 4882.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2156, pruned_loss=0.03601, over 971102.11 frames.], batch size: 20, lr: 2.84e-04
2022-05-06 00:54:28,007 INFO [train.py:715] (4/8) Epoch 7, batch 32850, loss[loss=0.1365, simple_loss=0.2076, pruned_loss=0.0327, over 4872.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2154, pruned_loss=0.03602, over 970960.05 frames.], batch size: 30, lr: 2.84e-04
2022-05-06 00:55:08,150 INFO [train.py:715] (4/8) Epoch 7, batch 32900, loss[loss=0.1452, simple_loss=0.2205, pruned_loss=0.03492, over 4744.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2157, pruned_loss=0.03633, over 971392.82 frames.], batch size: 12, lr: 2.84e-04
2022-05-06 00:55:48,487 INFO [train.py:715] (4/8) Epoch 7, batch 32950, loss[loss=0.1356, simple_loss=0.2098, pruned_loss=0.03071, over 4794.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.03625, over 971499.43 frames.], batch size: 14, lr: 2.84e-04
2022-05-06 00:56:28,433 INFO [train.py:715] (4/8) Epoch 7, batch 33000, loss[loss=0.1421, simple_loss=0.2064, pruned_loss=0.03897, over 4988.00 frames.], tot_loss[loss=0.144, simple_loss=0.2153, pruned_loss=0.03634, over 971638.31 frames.], batch size: 14, lr: 2.84e-04
2022-05-06 00:56:28,434 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 00:56:38,007 INFO [train.py:742] (4/8) Epoch 7, validation: loss=0.108, simple_loss=0.1927, pruned_loss=0.01164, over 914524.00 frames.
2022-05-06 00:57:17,518 INFO [train.py:715] (4/8) Epoch 7, batch 33050, loss[loss=0.1723, simple_loss=0.2471, pruned_loss=0.04877, over 4969.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2162, pruned_loss=0.03675, over 972158.94 frames.], batch size: 31, lr: 2.84e-04
2022-05-06 00:57:57,502 INFO [train.py:715] (4/8) Epoch 7, batch 33100, loss[loss=0.1458, simple_loss=0.2099, pruned_loss=0.04081, over 4836.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2169, pruned_loss=0.03683, over 972256.53 frames.], batch size: 30, lr: 2.84e-04
2022-05-06 00:58:36,954 INFO [train.py:715] (4/8) Epoch 7, batch 33150, loss[loss=0.1491, simple_loss=0.2166, pruned_loss=0.04077, over 4735.00 frames.], tot_loss[loss=0.1457, simple_loss=0.217, pruned_loss=0.03716, over 971323.64 frames.], batch size: 16, lr: 2.84e-04
2022-05-06 00:59:16,723 INFO [train.py:715] (4/8) Epoch 7, batch 33200, loss[loss=0.1486, simple_loss=0.2332, pruned_loss=0.03199, over 4870.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2172, pruned_loss=0.03709, over 971360.43 frames.], batch size: 22, lr: 2.84e-04
2022-05-06 00:59:56,299 INFO [train.py:715] (4/8) Epoch 7, batch 33250, loss[loss=0.1416, simple_loss=0.2157, pruned_loss=0.03374, over 4860.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2168, pruned_loss=0.03669, over 971620.57 frames.], batch size: 30, lr: 2.84e-04
2022-05-06 01:00:35,761 INFO [train.py:715] (4/8) Epoch 7, batch 33300, loss[loss=0.1528, simple_loss=0.227, pruned_loss=0.03927, over 4862.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2171, pruned_loss=0.03668, over 971495.08 frames.], batch size: 20, lr: 2.84e-04
2022-05-06 01:01:15,276 INFO [train.py:715] (4/8) Epoch 7, batch 33350, loss[loss=0.1492, simple_loss=0.2162, pruned_loss=0.04106, over 4766.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2162, pruned_loss=0.03653, over 971114.12 frames.], batch size: 12, lr: 2.84e-04
2022-05-06 01:01:55,575 INFO [train.py:715] (4/8) Epoch 7, batch 33400, loss[loss=0.1316, simple_loss=0.1992, pruned_loss=0.032, over 4971.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2174, pruned_loss=0.03685, over 971669.53 frames.], batch size: 24, lr: 2.84e-04
2022-05-06 01:02:35,668 INFO [train.py:715] (4/8) Epoch 7, batch 33450, loss[loss=0.1173, simple_loss=0.1984, pruned_loss=0.01807, over 4913.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2175, pruned_loss=0.03697, over 972104.60 frames.], batch size: 19, lr: 2.84e-04
2022-05-06 01:03:16,256 INFO [train.py:715] (4/8) Epoch 7, batch 33500, loss[loss=0.2045, simple_loss=0.2623, pruned_loss=0.07341, over 4835.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2177, pruned_loss=0.03693, over 971471.55 frames.], batch size: 13, lr: 2.84e-04
2022-05-06 01:03:56,834 INFO [train.py:715] (4/8) Epoch 7, batch 33550, loss[loss=0.1162, simple_loss=0.1954, pruned_loss=0.01845, over 4819.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2184, pruned_loss=0.03723, over 971906.88 frames.], batch size: 25, lr: 2.84e-04
2022-05-06 01:04:37,439 INFO [train.py:715] (4/8) Epoch 7, batch 33600, loss[loss=0.1316, simple_loss=0.2018, pruned_loss=0.03069, over 4800.00 frames.], tot_loss[loss=0.1473, simple_loss=0.2193, pruned_loss=0.03763, over 971703.92 frames.], batch size: 21, lr: 2.84e-04
2022-05-06 01:05:17,936 INFO [train.py:715] (4/8) Epoch 7, batch 33650, loss[loss=0.1276, simple_loss=0.207, pruned_loss=0.02407, over 4922.00 frames.], tot_loss[loss=0.1466, simple_loss=0.219, pruned_loss=0.03704, over 972075.93 frames.], batch size: 29, lr: 2.84e-04
2022-05-06 01:05:57,812 INFO [train.py:715] (4/8) Epoch 7, batch 33700, loss[loss=0.1507, simple_loss=0.2344, pruned_loss=0.03346, over 4908.00 frames.], tot_loss[loss=0.1463, simple_loss=0.2185, pruned_loss=0.03707, over 972392.94 frames.], batch size: 17, lr: 2.84e-04
2022-05-06 01:06:37,963 INFO [train.py:715] (4/8) Epoch 7, batch 33750, loss[loss=0.1473, simple_loss=0.2172, pruned_loss=0.03866, over 4836.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2184, pruned_loss=0.03734, over 972014.58 frames.], batch size: 20, lr: 2.84e-04
2022-05-06 01:07:17,445 INFO [train.py:715] (4/8) Epoch 7, batch 33800, loss[loss=0.158, simple_loss=0.2397, pruned_loss=0.03811, over 4789.00 frames.], tot_loss[loss=0.1466, simple_loss=0.2187, pruned_loss=0.03725, over 972371.62 frames.], batch size: 21, lr: 2.84e-04
2022-05-06 01:07:58,046 INFO [train.py:715] (4/8) Epoch 7, batch 33850, loss[loss=0.1261, simple_loss=0.1985, pruned_loss=0.02692, over 4707.00 frames.], tot_loss[loss=0.1459, simple_loss=0.218, pruned_loss=0.03697, over 972495.64 frames.], batch size: 15, lr: 2.84e-04
2022-05-06 01:08:37,725 INFO [train.py:715] (4/8) Epoch 7, batch 33900, loss[loss=0.138, simple_loss=0.2096, pruned_loss=0.03323, over 4867.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2176, pruned_loss=0.03672, over 972395.50 frames.], batch size: 32, lr: 2.84e-04
2022-05-06 01:09:17,828 INFO [train.py:715] (4/8) Epoch 7, batch 33950, loss[loss=0.1454, simple_loss=0.2162, pruned_loss=0.03732, over 4971.00 frames.], tot_loss[loss=0.1464, simple_loss=0.2185, pruned_loss=0.03713, over 972908.96 frames.], batch size: 24, lr: 2.84e-04
2022-05-06 01:09:57,286 INFO [train.py:715] (4/8) Epoch 7, batch 34000, loss[loss=0.1545, simple_loss=0.2314, pruned_loss=0.03881, over 4776.00 frames.], tot_loss[loss=0.1465, simple_loss=0.2183, pruned_loss=0.03738, over 972636.52 frames.], batch size: 17, lr: 2.84e-04
2022-05-06 01:10:37,474 INFO [train.py:715] (4/8) Epoch 7, batch 34050, loss[loss=0.1359, simple_loss=0.1966, pruned_loss=0.03759, over 4702.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2175, pruned_loss=0.03707, over 971957.72 frames.], batch size: 15, lr: 2.84e-04
2022-05-06 01:11:17,478 INFO [train.py:715] (4/8) Epoch 7, batch 34100, loss[loss=0.1468, simple_loss=0.2152, pruned_loss=0.03923, over 4822.00 frames.], tot_loss[loss=0.1462, simple_loss=0.2179, pruned_loss=0.03721, over 972233.61 frames.], batch size: 26, lr: 2.83e-04
2022-05-06 01:11:56,986 INFO [train.py:715] (4/8) Epoch 7, batch 34150, loss[loss=0.1241, simple_loss=0.2057, pruned_loss=0.02123, over 4875.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2177, pruned_loss=0.03704, over 972121.99 frames.], batch size: 19, lr: 2.83e-04
2022-05-06 01:12:37,406 INFO [train.py:715] (4/8) Epoch 7, batch 34200, loss[loss=0.1469, simple_loss=0.2236, pruned_loss=0.03511, over 4877.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2172, pruned_loss=0.03684, over 972190.86 frames.], batch size: 22, lr: 2.83e-04
2022-05-06 01:13:17,638 INFO [train.py:715] (4/8) Epoch 7, batch 34250, loss[loss=0.1251, simple_loss=0.1906, pruned_loss=0.02981, over 4817.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2163, pruned_loss=0.03647, over 971890.47 frames.], batch size: 13, lr: 2.83e-04
2022-05-06 01:13:58,298 INFO [train.py:715] (4/8) Epoch 7, batch 34300, loss[loss=0.168, simple_loss=0.2254, pruned_loss=0.05533, over 4742.00 frames.], tot_loss[loss=0.1443, simple_loss=0.216, pruned_loss=0.03631, over 972302.05 frames.], batch size: 16, lr: 2.83e-04
2022-05-06 01:14:38,115 INFO [train.py:715] (4/8) Epoch 7, batch 34350, loss[loss=0.1547, simple_loss=0.2271, pruned_loss=0.04111, over 4978.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.0363, over 972358.17 frames.], batch size: 28, lr: 2.83e-04
2022-05-06 01:15:18,248 INFO [train.py:715] (4/8) Epoch 7, batch 34400, loss[loss=0.1415, simple_loss=0.2091, pruned_loss=0.03697, over 4923.00 frames.], tot_loss[loss=0.1447, simple_loss=0.217, pruned_loss=0.03625, over 971969.71 frames.], batch size: 23, lr: 2.83e-04
2022-05-06 01:15:58,919 INFO [train.py:715] (4/8) Epoch 7, batch 34450, loss[loss=0.1988, simple_loss=0.2595, pruned_loss=0.06905, over 4966.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2178, pruned_loss=0.03639, over 972476.93 frames.], batch size: 39, lr: 2.83e-04
2022-05-06 01:16:38,146 INFO [train.py:715] (4/8) Epoch 7, batch 34500, loss[loss=0.1234, simple_loss=0.1971, pruned_loss=0.02487, over 4795.00 frames.], tot_loss[loss=0.1457, simple_loss=0.218, pruned_loss=0.03669, over 971840.57 frames.], batch size: 12, lr: 2.83e-04
2022-05-06 01:17:18,211 INFO [train.py:715] (4/8) Epoch 7, batch 34550, loss[loss=0.1493, simple_loss=0.2162, pruned_loss=0.04116, over 4960.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2177, pruned_loss=0.03639, over 972685.77 frames.], batch size: 24, lr: 2.83e-04
2022-05-06 01:17:58,848 INFO [train.py:715] (4/8) Epoch 7, batch 34600, loss[loss=0.1233, simple_loss=0.1958, pruned_loss=0.02543, over 4825.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2173, pruned_loss=0.03645, over 972971.56 frames.], batch size: 12, lr: 2.83e-04
2022-05-06 01:18:38,815 INFO [train.py:715] (4/8) Epoch 7, batch 34650, loss[loss=0.1551, simple_loss=0.2234, pruned_loss=0.04337, over 4831.00 frames.], tot_loss[loss=0.145, simple_loss=0.2169, pruned_loss=0.0365, over 973461.20 frames.], batch size: 30, lr: 2.83e-04
2022-05-06 01:19:19,028 INFO [train.py:715] (4/8) Epoch 7, batch 34700, loss[loss=0.1542, simple_loss=0.2236, pruned_loss=0.04233, over 4909.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2173, pruned_loss=0.03658, over 973564.52 frames.], batch size: 18, lr: 2.83e-04
2022-05-06 01:19:57,506 INFO [train.py:715] (4/8) Epoch 7, batch 34750, loss[loss=0.1306, simple_loss=0.1934, pruned_loss=0.03394, over 4716.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2163, pruned_loss=0.03578, over 973450.70 frames.], batch size: 12, lr: 2.83e-04
2022-05-06 01:20:35,940 INFO [train.py:715] (4/8) Epoch 7, batch 34800, loss[loss=0.1492, simple_loss=0.2183, pruned_loss=0.04006, over 4914.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2154, pruned_loss=0.03576, over 973010.74 frames.], batch size: 18, lr: 2.83e-04
2022-05-06 01:21:27,015 INFO [train.py:715] (4/8) Epoch 8, batch 0, loss[loss=0.1523, simple_loss=0.2353, pruned_loss=0.03462, over 4818.00 frames.], tot_loss[loss=0.1523, simple_loss=0.2353, pruned_loss=0.03462, over 4818.00 frames.], batch size: 26, lr: 2.69e-04
2022-05-06 01:22:06,298 INFO [train.py:715] (4/8) Epoch 8, batch 50, loss[loss=0.1352, simple_loss=0.2145, pruned_loss=0.02796, over 4840.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2122, pruned_loss=0.03357, over 218243.09 frames.], batch size: 15, lr: 2.69e-04
2022-05-06 01:22:47,070 INFO [train.py:715] (4/8) Epoch 8, batch 100, loss[loss=0.1473, simple_loss=0.2231, pruned_loss=0.03571, over 4806.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2155, pruned_loss=0.03533, over 386132.34 frames.], batch size: 26, lr: 2.69e-04
2022-05-06 01:23:26,806 INFO [train.py:715] (4/8) Epoch 8, batch 150, loss[loss=0.1391, simple_loss=0.2146, pruned_loss=0.03174, over 4779.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2163, pruned_loss=0.03665, over 515701.20 frames.], batch size: 12, lr: 2.69e-04
2022-05-06 01:24:07,304 INFO [train.py:715] (4/8) Epoch 8, batch 200, loss[loss=0.1343, simple_loss=0.2023, pruned_loss=0.03311, over 4982.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.03561, over 617032.17 frames.], batch size: 35, lr: 2.69e-04
2022-05-06 01:24:47,114 INFO [train.py:715] (4/8) Epoch 8, batch 250, loss[loss=0.1662, simple_loss=0.2311, pruned_loss=0.05062, over 4861.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2166, pruned_loss=0.03592, over 695976.50 frames.], batch size: 30, lr: 2.69e-04
2022-05-06 01:25:27,374 INFO [train.py:715] (4/8) Epoch 8, batch 300, loss[loss=0.127, simple_loss=0.2077, pruned_loss=0.0231, over 4786.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03555, over 757013.08 frames.], batch size: 24, lr: 2.69e-04
2022-05-06 01:26:07,154 INFO [train.py:715] (4/8) Epoch 8, batch 350, loss[loss=0.1582, simple_loss=0.2143, pruned_loss=0.05104, over 4887.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2154, pruned_loss=0.03599, over 804669.55 frames.], batch size: 16, lr: 2.69e-04
2022-05-06 01:26:46,036 INFO [train.py:715] (4/8) Epoch 8, batch 400, loss[loss=0.1455, simple_loss=0.2154, pruned_loss=0.03781, over 4867.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2161, pruned_loss=0.03605, over 842762.64 frames.], batch size: 20, lr: 2.69e-04
2022-05-06 01:27:26,636 INFO [train.py:715] (4/8) Epoch 8, batch 450, loss[loss=0.1441, simple_loss=0.2204, pruned_loss=0.03388, over 4966.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2155, pruned_loss=0.03592, over 871033.21 frames.], batch size: 24, lr: 2.69e-04
2022-05-06 01:28:06,605 INFO [train.py:715] (4/8) Epoch 8, batch 500, loss[loss=0.1504, simple_loss=0.2213, pruned_loss=0.03979, over 4989.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2164, pruned_loss=0.03615, over 894158.44 frames.], batch size: 15, lr: 2.69e-04
2022-05-06 01:28:47,245 INFO [train.py:715] (4/8) Epoch 8, batch 550, loss[loss=0.1869, simple_loss=0.2513, pruned_loss=0.06121, over 4895.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.03632, over 912226.79 frames.], batch size: 17, lr: 2.69e-04
2022-05-06 01:29:26,912 INFO [train.py:715] (4/8) Epoch 8, batch 600, loss[loss=0.1553, simple_loss=0.2255, pruned_loss=0.04262, over 4906.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2153, pruned_loss=0.03588, over 925229.12 frames.], batch size: 19, lr: 2.69e-04
2022-05-06 01:30:07,130 INFO [train.py:715] (4/8) Epoch 8, batch 650, loss[loss=0.1579, simple_loss=0.2276, pruned_loss=0.04404, over 4874.00 frames.], tot_loss[loss=0.143, simple_loss=0.215, pruned_loss=0.03554, over 935553.09 frames.], batch size: 32, lr: 2.68e-04
2022-05-06 01:30:47,384 INFO [train.py:715] (4/8) Epoch 8, batch 700, loss[loss=0.1479, simple_loss=0.2262, pruned_loss=0.03484, over 4875.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2155, pruned_loss=0.03594, over 942373.02 frames.], batch size: 16, lr: 2.68e-04
2022-05-06 01:31:27,080 INFO [train.py:715] (4/8) Epoch 8, batch 750, loss[loss=0.1312, simple_loss=0.2079, pruned_loss=0.02727, over 4791.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2165, pruned_loss=0.03601, over 949575.88 frames.], batch size: 14, lr: 2.68e-04
2022-05-06 01:32:07,140 INFO [train.py:715] (4/8) Epoch 8, batch 800, loss[loss=0.1516, simple_loss=0.227, pruned_loss=0.03812, over 4899.00 frames.], tot_loss[loss=0.1433, simple_loss=0.216, pruned_loss=0.03528, over 955262.52 frames.], batch size: 17, lr: 2.68e-04
2022-05-06 01:32:47,127 INFO [train.py:715] (4/8) Epoch 8, batch 850, loss[loss=0.134, simple_loss=0.2176, pruned_loss=0.02515, over 4917.00 frames.], tot_loss[loss=0.1433, simple_loss=0.216, pruned_loss=0.03531, over 958653.02 frames.], batch size: 18, lr: 2.68e-04
2022-05-06 01:33:28,540 INFO [train.py:715] (4/8) Epoch 8, batch 900, loss[loss=0.1649, simple_loss=0.2317, pruned_loss=0.04904, over 4879.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2166, pruned_loss=0.03577, over 961887.10 frames.], batch size: 39, lr: 2.68e-04
2022-05-06 01:34:08,648 INFO [train.py:715] (4/8) Epoch 8, batch 950, loss[loss=0.114, simple_loss=0.1848, pruned_loss=0.02158, over 4726.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2177, pruned_loss=0.03658, over 964134.47 frames.], batch size: 16, lr: 2.68e-04
2022-05-06 01:34:49,689 INFO [train.py:715] (4/8) Epoch 8, batch 1000, loss[loss=0.1524, simple_loss=0.2271, pruned_loss=0.03884, over 4694.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2172, pruned_loss=0.03665, over 965028.27 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:35:30,777 INFO [train.py:715] (4/8) Epoch 8, batch 1050, loss[loss=0.1238, simple_loss=0.2004, pruned_loss=0.02356, over 4939.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2165, pruned_loss=0.03624, over 967375.91 frames.], batch size: 21, lr: 2.68e-04
2022-05-06 01:36:11,892 INFO [train.py:715] (4/8) Epoch 8, batch 1100, loss[loss=0.1341, simple_loss=0.2034, pruned_loss=0.0324, over 4960.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2163, pruned_loss=0.03617, over 968295.00 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:36:52,398 INFO [train.py:715] (4/8) Epoch 8, batch 1150, loss[loss=0.142, simple_loss=0.2202, pruned_loss=0.03189, over 4772.00 frames.], tot_loss[loss=0.1446, simple_loss=0.216, pruned_loss=0.03654, over 969424.26 frames.], batch size: 18, lr: 2.68e-04
2022-05-06 01:37:33,423 INFO [train.py:715] (4/8) Epoch 8, batch 1200, loss[loss=0.1616, simple_loss=0.2343, pruned_loss=0.0445, over 4782.00 frames.], tot_loss[loss=0.145, simple_loss=0.2167, pruned_loss=0.03665, over 969205.26 frames.], batch size: 18, lr: 2.68e-04
2022-05-06 01:38:14,742 INFO [train.py:715] (4/8) Epoch 8, batch 1250, loss[loss=0.1532, simple_loss=0.2326, pruned_loss=0.03691, over 4848.00 frames.], tot_loss[loss=0.1445, simple_loss=0.216, pruned_loss=0.03645, over 969229.75 frames.], batch size: 26, lr: 2.68e-04
2022-05-06 01:38:55,087 INFO [train.py:715] (4/8) Epoch 8, batch 1300, loss[loss=0.162, simple_loss=0.2291, pruned_loss=0.04745, over 4976.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2166, pruned_loss=0.03652, over 970616.37 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:39:36,444 INFO [train.py:715] (4/8) Epoch 8, batch 1350, loss[loss=0.1201, simple_loss=0.1948, pruned_loss=0.02272, over 4759.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2162, pruned_loss=0.03625, over 971634.51 frames.], batch size: 19, lr: 2.68e-04
2022-05-06 01:40:17,090 INFO [train.py:715] (4/8) Epoch 8, batch 1400, loss[loss=0.1763, simple_loss=0.2361, pruned_loss=0.05826, over 4839.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2152, pruned_loss=0.03593, over 972602.11 frames.], batch size: 30, lr: 2.68e-04
2022-05-06 01:40:57,921 INFO [train.py:715] (4/8) Epoch 8, batch 1450, loss[loss=0.1348, simple_loss=0.2072, pruned_loss=0.03124, over 4793.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2163, pruned_loss=0.03654, over 972064.21 frames.], batch size: 14, lr: 2.68e-04
2022-05-06 01:41:37,775 INFO [train.py:715] (4/8) Epoch 8, batch 1500, loss[loss=0.1461, simple_loss=0.2258, pruned_loss=0.03317, over 4873.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2172, pruned_loss=0.03672, over 971523.62 frames.], batch size: 22, lr: 2.68e-04
2022-05-06 01:42:20,410 INFO [train.py:715] (4/8) Epoch 8, batch 1550, loss[loss=0.1336, simple_loss=0.2061, pruned_loss=0.03049, over 4957.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2172, pruned_loss=0.0365, over 971960.45 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:43:00,533 INFO [train.py:715] (4/8) Epoch 8, batch 1600, loss[loss=0.1276, simple_loss=0.2085, pruned_loss=0.0234, over 4838.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2169, pruned_loss=0.03608, over 971743.27 frames.], batch size: 26, lr: 2.68e-04
2022-05-06 01:43:39,974 INFO [train.py:715] (4/8) Epoch 8, batch 1650, loss[loss=0.1172, simple_loss=0.1844, pruned_loss=0.02502, over 4808.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03615, over 971215.14 frames.], batch size: 25, lr: 2.68e-04
2022-05-06 01:44:20,194 INFO [train.py:715] (4/8) Epoch 8, batch 1700, loss[loss=0.1419, simple_loss=0.2178, pruned_loss=0.03301, over 4748.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2167, pruned_loss=0.0364, over 971526.11 frames.], batch size: 16, lr: 2.68e-04
2022-05-06 01:44:59,608 INFO [train.py:715] (4/8) Epoch 8, batch 1750, loss[loss=0.1457, simple_loss=0.2103, pruned_loss=0.04053, over 4893.00 frames.], tot_loss[loss=0.1446, simple_loss=0.217, pruned_loss=0.03612, over 971812.83 frames.], batch size: 19, lr: 2.68e-04
2022-05-06 01:45:39,056 INFO [train.py:715] (4/8) Epoch 8, batch 1800, loss[loss=0.1626, simple_loss=0.2168, pruned_loss=0.05416, over 4829.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.0359, over 971761.83 frames.], batch size: 30, lr: 2.68e-04
2022-05-06 01:46:18,113 INFO [train.py:715] (4/8) Epoch 8, batch 1850, loss[loss=0.1225, simple_loss=0.1886, pruned_loss=0.02816, over 4903.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2156, pruned_loss=0.03605, over 972308.81 frames.], batch size: 19, lr: 2.68e-04
2022-05-06 01:46:57,511 INFO [train.py:715] (4/8) Epoch 8, batch 1900, loss[loss=0.1155, simple_loss=0.1917, pruned_loss=0.01968, over 4922.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2162, pruned_loss=0.03576, over 972282.24 frames.], batch size: 29, lr: 2.68e-04
2022-05-06 01:47:37,010 INFO [train.py:715] (4/8) Epoch 8, batch 1950, loss[loss=0.1725, simple_loss=0.2539, pruned_loss=0.04553, over 4886.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2166, pruned_loss=0.03623, over 972374.40 frames.], batch size: 22, lr: 2.68e-04
2022-05-06 01:48:16,131 INFO [train.py:715] (4/8) Epoch 8, batch 2000, loss[loss=0.1644, simple_loss=0.2342, pruned_loss=0.0473, over 4889.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2161, pruned_loss=0.03588, over 972886.48 frames.], batch size: 16, lr: 2.68e-04
2022-05-06 01:48:56,143 INFO [train.py:715] (4/8) Epoch 8, batch 2050, loss[loss=0.1426, simple_loss=0.221, pruned_loss=0.03209, over 4686.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2157, pruned_loss=0.03568, over 972370.65 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:49:35,103 INFO [train.py:715] (4/8) Epoch 8, batch 2100, loss[loss=0.1421, simple_loss=0.2147, pruned_loss=0.03469, over 4875.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2157, pruned_loss=0.03579, over 971955.92 frames.], batch size: 16, lr: 2.68e-04
2022-05-06 01:50:14,046 INFO [train.py:715] (4/8) Epoch 8, batch 2150, loss[loss=0.1529, simple_loss=0.2212, pruned_loss=0.04227, over 4894.00 frames.], tot_loss[loss=0.1441, simple_loss=0.216, pruned_loss=0.03608, over 971612.93 frames.], batch size: 19, lr: 2.68e-04
2022-05-06 01:50:53,034 INFO [train.py:715] (4/8) Epoch 8, batch 2200, loss[loss=0.1452, simple_loss=0.2038, pruned_loss=0.04333, over 4967.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2155, pruned_loss=0.03576, over 971846.05 frames.], batch size: 35, lr: 2.68e-04
2022-05-06 01:51:32,660 INFO [train.py:715] (4/8) Epoch 8, batch 2250, loss[loss=0.1402, simple_loss=0.2218, pruned_loss=0.02924, over 4952.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2157, pruned_loss=0.03641, over 971590.98 frames.], batch size: 21, lr: 2.68e-04
2022-05-06 01:52:12,076 INFO [train.py:715] (4/8) Epoch 8, batch 2300, loss[loss=0.1317, simple_loss=0.2073, pruned_loss=0.02812, over 4789.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2155, pruned_loss=0.03599, over 971676.61 frames.], batch size: 21, lr: 2.68e-04
2022-05-06 01:52:50,786 INFO [train.py:715] (4/8) Epoch 8, batch 2350, loss[loss=0.1433, simple_loss=0.2012, pruned_loss=0.04275, over 4844.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2164, pruned_loss=0.03655, over 972249.46 frames.], batch size: 32, lr: 2.68e-04
2022-05-06 01:53:30,837 INFO [train.py:715] (4/8) Epoch 8, batch 2400, loss[loss=0.1462, simple_loss=0.2235, pruned_loss=0.03444, over 4982.00 frames.], tot_loss[loss=0.145, simple_loss=0.2165, pruned_loss=0.03671, over 972551.50 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:54:10,337 INFO [train.py:715] (4/8) Epoch 8, batch 2450, loss[loss=0.1147, simple_loss=0.1889, pruned_loss=0.02027, over 4947.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2164, pruned_loss=0.03638, over 973063.98 frames.], batch size: 21, lr: 2.68e-04
2022-05-06 01:54:49,891 INFO [train.py:715] (4/8) Epoch 8, batch 2500, loss[loss=0.1712, simple_loss=0.2503, pruned_loss=0.04605, over 4966.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2175, pruned_loss=0.03649, over 972675.89 frames.], batch size: 24, lr: 2.68e-04
2022-05-06 01:55:28,672 INFO [train.py:715] (4/8) Epoch 8, batch 2550, loss[loss=0.1648, simple_loss=0.243, pruned_loss=0.04326, over 4986.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2173, pruned_loss=0.0361, over 972941.76 frames.], batch size: 25, lr: 2.68e-04
2022-05-06 01:56:08,300 INFO [train.py:715] (4/8) Epoch 8, batch 2600, loss[loss=0.1579, simple_loss=0.2312, pruned_loss=0.04227, over 4970.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2169, pruned_loss=0.0359, over 973308.30 frames.], batch size: 33, lr: 2.68e-04
2022-05-06 01:56:47,548 INFO [train.py:715] (4/8) Epoch 8, batch 2650, loss[loss=0.2008, simple_loss=0.2498, pruned_loss=0.07586, over 4699.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03574, over 973120.06 frames.], batch size: 15, lr: 2.68e-04
2022-05-06 01:57:27,028 INFO [train.py:715] (4/8) Epoch 8, batch 2700, loss[loss=0.143, simple_loss=0.2118, pruned_loss=0.03706, over 4787.00 frames.], tot_loss[loss=0.144, simple_loss=0.2164, pruned_loss=0.03579, over 973602.66 frames.], batch size: 17, lr: 2.68e-04
2022-05-06 01:58:06,372 INFO [train.py:715] (4/8) Epoch 8, batch 2750, loss[loss=0.1126, simple_loss=0.1848, pruned_loss=0.02018, over 4692.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03597, over 972496.86 frames.], batch size: 15, lr: 2.67e-04
2022-05-06 01:58:45,749 INFO [train.py:715] (4/8) Epoch 8, batch 2800, loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03146, over 4982.00 frames.], tot_loss[loss=0.1441, simple_loss=0.216, pruned_loss=0.03613, over 972853.79 frames.], batch size: 15, lr: 2.67e-04
2022-05-06 01:59:24,993 INFO [train.py:715] (4/8) Epoch 8, batch 2850, loss[loss=0.1234, simple_loss=0.2027, pruned_loss=0.02207, over 4817.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2162, pruned_loss=0.03605, over 973470.16 frames.], batch size: 27, lr: 2.67e-04
2022-05-06 02:00:03,842 INFO [train.py:715] (4/8) Epoch 8, batch 2900, loss[loss=0.1636, simple_loss=0.2424, pruned_loss=0.04236, over 4862.00 frames.], tot_loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.03548, over 972859.21 frames.], batch size: 16, lr: 2.67e-04
2022-05-06 02:00:43,805 INFO [train.py:715] (4/8) Epoch 8, batch 2950, loss[loss=0.1159, simple_loss=0.1855, pruned_loss=0.02311, over 4802.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2165, pruned_loss=0.03582, over 972996.63 frames.], batch size: 21, lr: 2.67e-04
2022-05-06 02:01:22,466 INFO [train.py:715] (4/8) Epoch 8, batch 3000, loss[loss=0.161, simple_loss=0.2287, pruned_loss=0.04663, over 4862.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2163, pruned_loss=0.03534, over 973016.96 frames.], batch size: 32, lr: 2.67e-04
2022-05-06 02:01:22,466 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 02:01:32,130 INFO [train.py:742] (4/8) Epoch 8, validation: loss=0.1076, simple_loss=0.1923, pruned_loss=0.0115, over 914524.00 frames.
2022-05-06 02:02:11,364 INFO [train.py:715] (4/8) Epoch 8, batch 3050, loss[loss=0.1468, simple_loss=0.2183, pruned_loss=0.03771, over 4985.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.03495, over 972831.65 frames.], batch size: 16, lr: 2.67e-04
2022-05-06 02:02:50,372 INFO [train.py:715] (4/8) Epoch 8, batch 3100, loss[loss=0.1623, simple_loss=0.2205, pruned_loss=0.05199, over 4808.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2161, pruned_loss=0.03538, over 972880.23 frames.], batch size: 24, lr: 2.67e-04
2022-05-06 02:03:29,322 INFO [train.py:715] (4/8) Epoch 8, batch 3150, loss[loss=0.1278, simple_loss=0.1977, pruned_loss=0.02894, over 4884.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2162, pruned_loss=0.03578, over 972782.24 frames.], batch size: 22, lr: 2.67e-04
2022-05-06 02:04:09,015 INFO [train.py:715] (4/8) Epoch 8, batch 3200, loss[loss=0.152, simple_loss=0.2286, pruned_loss=0.03769, over 4752.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03587, over 972868.26 frames.], batch size: 16, lr: 2.67e-04
2022-05-06 02:04:48,445 INFO [train.py:715] (4/8) Epoch 8, batch 3250, loss[loss=0.12, simple_loss=0.2019, pruned_loss=0.01908, over 4936.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2173, pruned_loss=0.03613, over 973262.86 frames.], batch size: 29, lr: 2.67e-04
2022-05-06 02:05:28,475 INFO [train.py:715] (4/8) Epoch 8, batch 3300, loss[loss=0.1543, simple_loss=0.2272, pruned_loss=0.04072, over 4755.00 frames.], tot_loss[loss=0.145, simple_loss=0.2174, pruned_loss=0.03635, over 972630.33 frames.], batch size: 16, lr: 2.67e-04
2022-05-06 02:06:08,831 INFO [train.py:715] (4/8) Epoch 8, batch 3350, loss[loss=0.1409, simple_loss=0.2127, pruned_loss=0.03455, over 4963.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03594, over 972981.95 frames.], batch size: 14, lr: 2.67e-04
2022-05-06 02:06:49,927 INFO [train.py:715] (4/8) Epoch 8, batch 3400, loss[loss=0.141, simple_loss=0.2176, pruned_loss=0.03224, over 4934.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2166, pruned_loss=0.03612, over 973010.19 frames.], batch size: 23, lr: 2.67e-04
2022-05-06 02:07:30,792 INFO [train.py:715] (4/8) Epoch 8, batch 3450, loss[loss=0.1295, simple_loss=0.2069, pruned_loss=0.02603, over 4871.00 frames.], tot_loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.03577, over 972669.52 frames.], batch size: 20, lr: 2.67e-04
2022-05-06 02:08:11,001 INFO [train.py:715] (4/8) Epoch 8, batch 3500, loss[loss=0.1213, simple_loss=0.1932, pruned_loss=0.02474, over 4815.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2165, pruned_loss=0.03624, over 973142.27 frames.], batch size: 27, lr: 2.67e-04
2022-05-06 02:08:52,343 INFO [train.py:715] (4/8) Epoch 8, batch 3550, loss[loss=0.1347, simple_loss=0.1987, pruned_loss=0.03535, over 4815.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2174, pruned_loss=0.03664, over 973512.32 frames.], batch size: 13, lr: 2.67e-04
2022-05-06 02:09:33,194 INFO [train.py:715] (4/8) Epoch 8, batch 3600, loss[loss=0.1324, simple_loss=0.2061, pruned_loss=0.0294, over 4801.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2163, pruned_loss=0.03628, over 973899.11 frames.], batch size: 25, lr: 2.67e-04
2022-05-06 02:10:13,461 INFO [train.py:715] (4/8) Epoch 8, batch 3650, loss[loss=0.1499, simple_loss=0.2284, pruned_loss=0.03566, over 4768.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2163, pruned_loss=0.03644, over 972722.93 frames.], batch size: 19, lr: 2.67e-04
2022-05-06 02:10:53,923 INFO [train.py:715] (4/8) Epoch 8, batch 3700, loss[loss=0.1462, simple_loss=0.2092, pruned_loss=0.04158, over 4975.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2147, pruned_loss=0.03574, over 971814.86 frames.], batch size: 15, lr: 2.67e-04
2022-05-06 02:11:34,274 INFO [train.py:715] (4/8) Epoch 8, batch 3750, loss[loss=0.1443, simple_loss=0.2118, pruned_loss=0.03836, over 4858.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2152, pruned_loss=0.03592, over 971143.33 frames.], batch size: 12, lr: 2.67e-04
2022-05-06 02:12:13,637 INFO [train.py:715] (4/8) Epoch 8, batch 3800, loss[loss=0.1819, simple_loss=0.2418, pruned_loss=0.06095, over 4865.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2153, pruned_loss=0.03582, over 971743.53 frames.], batch size: 16, lr: 2.67e-04
2022-05-06 02:12:54,027 INFO [train.py:715] (4/8) Epoch 8, batch 3850, loss[loss=0.128, simple_loss=0.2013, pruned_loss=0.02736, over 4992.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2153, pruned_loss=0.036, over 972249.59 frames.], batch size: 20, lr: 2.67e-04
2022-05-06 02:13:34,213 INFO [train.py:715] (4/8) Epoch 8, batch 3900, loss[loss=0.1775, simple_loss=0.2357, pruned_loss=0.05966, over 4924.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2154, pruned_loss=0.03602, over 972297.58 frames.], batch size: 18, lr: 2.67e-04
2022-05-06 02:14:14,978 INFO [train.py:715] (4/8) Epoch 8, batch 3950, loss[loss=0.1818, simple_loss=0.2474, pruned_loss=0.05805, over 4794.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2161, pruned_loss=0.0363, over 972321.60 frames.], batch size: 17, lr: 2.67e-04
2022-05-06 02:14:54,897 INFO [train.py:715] (4/8) Epoch 8, batch 4000, loss[loss=0.1599, simple_loss=0.2192, pruned_loss=0.05032, over 4976.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2163, pruned_loss=0.0366, over 972418.48 frames.], batch size: 15, lr: 2.67e-04
2022-05-06 02:15:35,356 INFO [train.py:715] (4/8) Epoch 8, batch 4050, loss[loss=0.1135, simple_loss=0.183, pruned_loss=0.022, over 4941.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2166, pruned_loss=0.03627, over 972282.81 frames.], batch size: 29, lr: 2.67e-04
2022-05-06 02:16:16,174 INFO [train.py:715] (4/8) Epoch 8, batch 4100, loss[loss=0.1416, simple_loss=0.208, pruned_loss=0.03757, over 4901.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2165, pruned_loss=0.03623, over 972758.56 frames.], batch size: 19, lr: 2.67e-04
2022-05-06 02:16:55,924 INFO [train.py:715] (4/8) Epoch 8, batch 4150, loss[loss=0.1166, simple_loss=0.1845, pruned_loss=0.02432, over 4971.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2159, pruned_loss=0.03591, over 972484.50 frames.], batch size: 31, lr: 2.67e-04
2022-05-06 02:17:35,662 INFO [train.py:715] (4/8) Epoch 8, batch 4200, loss[loss=0.166, simple_loss=0.2372, pruned_loss=0.0474, over 4930.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2166, pruned_loss=0.03597, over 973251.02 frames.], batch size: 39, lr: 2.67e-04
2022-05-06 02:18:15,236 INFO [train.py:715] (4/8) Epoch 8, batch 4250, loss[loss=0.1404, simple_loss=0.211, pruned_loss=0.0349, over 4866.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2161, pruned_loss=0.03568, over 972876.40 frames.], batch size: 32, lr: 2.67e-04
2022-05-06 02:18:54,987 INFO [train.py:715] (4/8) Epoch 8, batch 4300, loss[loss=0.1531, simple_loss=0.2263, pruned_loss=0.03993, over 4845.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2158, pruned_loss=0.03543, over 972562.63 frames.], batch size: 15, lr: 2.67e-04
2022-05-06 02:19:34,153 INFO [train.py:715] (4/8) Epoch 8, batch 4350, loss[loss=0.1365, simple_loss=0.1937, pruned_loss=0.03962, over 4782.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2159, pruned_loss=0.03537, over 972671.26 frames.], batch size: 12, lr: 2.67e-04
2022-05-06 02:20:13,545 INFO [train.py:715] (4/8) Epoch 8, batch 4400, loss[loss=0.1233, simple_loss=0.1997, pruned_loss=0.02347, over 4815.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.03549, over 972905.74 frames.], batch size: 25, lr: 2.67e-04
2022-05-06 02:20:53,466 INFO [train.py:715] (4/8) Epoch 8, batch 4450, loss[loss=0.1255, simple_loss=0.1887, pruned_loss=0.03117, over 4864.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2151, pruned_loss=0.03559, over 972235.35 frames.], batch size: 20, lr: 2.67e-04
2022-05-06 02:21:33,239 INFO [train.py:715] (4/8) Epoch 8, batch 4500, loss[loss=0.1451, simple_loss=0.2191, pruned_loss=0.0355, over 4991.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2157, pruned_loss=0.03584, over 972996.18 frames.], batch size: 25, lr: 2.67e-04
2022-05-06 02:22:12,202 INFO [train.py:715] (4/8) Epoch 8, batch 4550, loss[loss=0.1247, simple_loss=0.1998, pruned_loss=0.02479, over 4941.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2155, pruned_loss=0.03581, over 972910.26 frames.], batch size: 21, lr: 2.67e-04
2022-05-06 02:22:52,186 INFO [train.py:715] (4/8) Epoch 8, batch 4600, loss[loss=0.09869, simple_loss=0.1682, pruned_loss=0.01457, over 4786.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2152, pruned_loss=0.03569, over 972861.67 frames.], batch size: 14, lr: 2.67e-04
2022-05-06 02:23:31,719 INFO [train.py:715] (4/8) Epoch 8, batch 4650, loss[loss=0.1657, simple_loss=0.2337, pruned_loss=0.04885, over 4794.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2159, pruned_loss=0.03631, over 973191.29 frames.], batch size: 18, lr: 2.67e-04
2022-05-06 02:24:11,301 INFO [train.py:715] (4/8) Epoch 8, batch 4700, loss[loss=0.139, simple_loss=0.2076, pruned_loss=0.03516, over 4819.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2149, pruned_loss=0.03584, over 972551.38 frames.], batch size: 26, lr: 2.67e-04
2022-05-06 02:24:50,831 INFO [train.py:715] (4/8) Epoch 8, batch 4750, loss[loss=0.142, simple_loss=0.2104, pruned_loss=0.03677, over 4902.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2156, pruned_loss=0.03634, over 973473.60 frames.], batch size: 17, lr: 2.67e-04
2022-05-06 02:25:30,488 INFO [train.py:715] (4/8) Epoch 8, batch 4800, loss[loss=0.1305, simple_loss=0.1944, pruned_loss=0.03331, over 4776.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2148, pruned_loss=0.0358, over 973149.58 frames.], batch size: 17, lr: 2.67e-04
2022-05-06 02:26:10,389 INFO [train.py:715] (4/8) Epoch 8, batch 4850, loss[loss=0.1508, simple_loss=0.2089, pruned_loss=0.04634, over 4844.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2147, pruned_loss=0.03575, over 972752.02 frames.], batch size: 30, lr: 2.66e-04
2022-05-06 02:26:49,514 INFO [train.py:715] (4/8) Epoch 8, batch 4900, loss[loss=0.1456, simple_loss=0.2227, pruned_loss=0.03424, over 4969.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2154, pruned_loss=0.03589, over 973057.61 frames.], batch size: 15, lr: 2.66e-04
2022-05-06 02:27:29,277 INFO [train.py:715] (4/8) Epoch 8, batch 4950, loss[loss=0.1677, simple_loss=0.2217, pruned_loss=0.05679, over 4970.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2163, pruned_loss=0.03635, over 972220.67 frames.], batch size: 15, lr: 2.66e-04
2022-05-06 02:28:08,943 INFO [train.py:715] (4/8) Epoch 8, batch 5000, loss[loss=0.123, simple_loss=0.1935, pruned_loss=0.02626, over 4797.00 frames.], tot_loss[loss=0.1448, simple_loss=0.217, pruned_loss=0.03631, over 972111.75 frames.], batch size: 24, lr: 2.66e-04
2022-05-06 02:28:47,816 INFO [train.py:715] (4/8) Epoch 8, batch 5050, loss[loss=0.1264, simple_loss=0.1953, pruned_loss=0.02873, over 4918.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2167, pruned_loss=0.03626, over 971703.24 frames.], batch size: 18, lr: 2.66e-04
2022-05-06 02:29:26,961 INFO [train.py:715] (4/8) Epoch 8, batch 5100, loss[loss=0.191, simple_loss=0.2528, pruned_loss=0.06462, over 4741.00 frames.], tot_loss[loss=0.1428, simple_loss=0.215, pruned_loss=0.03535, over 971551.06 frames.], batch size: 16, lr: 2.66e-04
2022-05-06 02:30:06,430 INFO [train.py:715] (4/8) Epoch 8, batch 5150, loss[loss=0.1605, simple_loss=0.2387, pruned_loss=0.04109, over 4771.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2149, pruned_loss=0.03543, over 971737.30 frames.], batch size: 19, lr: 2.66e-04
2022-05-06 02:30:45,333 INFO [train.py:715] (4/8) Epoch 8, batch 5200, loss[loss=0.1198, simple_loss=0.1984, pruned_loss=0.0206, over 4887.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2146, pruned_loss=0.03546, over 970415.79 frames.], batch size: 22, lr: 2.66e-04
2022-05-06 02:31:24,027 INFO [train.py:715] (4/8) Epoch 8, batch 5250, loss[loss=0.1535, simple_loss=0.2206, pruned_loss=0.04317, over 4737.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2145, pruned_loss=0.0352, over 970692.25 frames.], batch size: 12, lr: 2.66e-04
2022-05-06 02:32:04,134 INFO [train.py:715] (4/8) Epoch 8, batch 5300, loss[loss=0.137, simple_loss=0.2086, pruned_loss=0.03271, over 4850.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2139, pruned_loss=0.03495, over 971279.16 frames.], batch size: 26, lr: 2.66e-04
2022-05-06 02:32:43,757 INFO [train.py:715] (4/8) Epoch 8, batch 5350, loss[loss=0.1334, simple_loss=0.213, pruned_loss=0.02697, over 4987.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2142, pruned_loss=0.03545, over 971685.70 frames.], batch size: 28, lr: 2.66e-04
2022-05-06 02:33:23,695 INFO [train.py:715] (4/8) Epoch 8, batch 5400, loss[loss=0.1545, simple_loss=0.2247, pruned_loss=0.04215, over 4731.00 frames.], tot_loss[loss=0.143, simple_loss=0.2149, pruned_loss=0.03555, over 971530.68 frames.], batch size: 16, lr: 2.66e-04
2022-05-06 02:34:04,181 INFO [train.py:715] (4/8) Epoch 8, batch 5450, loss[loss=0.1219, simple_loss=0.19, pruned_loss=0.02694, over 4991.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2149, pruned_loss=0.03562, over 972319.62 frames.], batch size: 14, lr: 2.66e-04
2022-05-06 02:34:44,676 INFO [train.py:715] (4/8) Epoch 8, batch 5500, loss[loss=0.1706, simple_loss=0.2464, pruned_loss=0.04741, over 4964.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2147, pruned_loss=0.03568, over 972726.51 frames.], batch size: 35, lr: 2.66e-04
2022-05-06 02:35:24,971 INFO [train.py:715] (4/8) Epoch 8, batch 5550, loss[loss=0.1344, simple_loss=0.213, pruned_loss=0.02787, over 4893.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2149, pruned_loss=0.03594, over 971777.61 frames.], batch size: 19, lr: 2.66e-04
2022-05-06 02:36:04,810 INFO [train.py:715] (4/8) Epoch 8, batch 5600, loss[loss=0.1689, simple_loss=0.24, pruned_loss=0.04892, over 4891.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2156, pruned_loss=0.03625, over 972035.73 frames.], batch size: 19, lr: 2.66e-04
2022-05-06 02:36:44,876 INFO [train.py:715] (4/8) Epoch 8, batch 5650, loss[loss=0.1236, simple_loss=0.1918, pruned_loss=0.02767, over 4769.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2152, pruned_loss=0.03584, over 972491.29 frames.], batch size: 17, lr: 2.66e-04
2022-05-06 02:37:24,003 INFO [train.py:715] (4/8) Epoch 8, batch 5700, loss[loss=0.1318, simple_loss=0.2154, pruned_loss=0.0241, over 4816.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2155, pruned_loss=0.03604, over 972615.56 frames.], batch size: 26, lr: 2.66e-04
2022-05-06 02:38:03,515 INFO [train.py:715] (4/8) Epoch 8, batch 5750, loss[loss=0.134, simple_loss=0.2029, pruned_loss=0.03251, over 4811.00 frames.], tot_loss[loss=0.144, simple_loss=0.2159, pruned_loss=0.03602, over 973620.36 frames.], batch size: 27, lr: 2.66e-04
2022-05-06 02:38:42,302 INFO [train.py:715] (4/8) Epoch 8, batch 5800, loss[loss=0.1547, simple_loss=0.2245, pruned_loss=0.04251, over 4986.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2157, pruned_loss=0.03577, over 972491.57 frames.], batch size: 16, lr: 2.66e-04
2022-05-06 02:39:21,799 INFO [train.py:715] (4/8) Epoch 8, batch 5850, loss[loss=0.1662, simple_loss=0.2473, pruned_loss=0.04253, over 4941.00 frames.], tot_loss[loss=0.1436, simple_loss=0.216, pruned_loss=0.03558, over 972096.76 frames.], batch size: 23, lr: 2.66e-04
2022-05-06 02:40:00,569 INFO [train.py:715] (4/8) Epoch 8, batch 5900, loss[loss=0.1454, simple_loss=0.212, pruned_loss=0.03939, over 4918.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03501, over 971907.24 frames.], batch size: 18, lr: 2.66e-04
2022-05-06 02:40:40,148 INFO [train.py:715] (4/8) Epoch 8, batch 5950, loss[loss=0.1573, simple_loss=0.2193, pruned_loss=0.04766, over 4907.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.03578, over 972388.54 frames.], batch size: 19, lr: 2.66e-04
2022-05-06 02:41:20,033 INFO [train.py:715] (4/8) Epoch 8, batch 6000, loss[loss=0.1468, simple_loss=0.2173, pruned_loss=0.03815, over 4971.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03553, over 972036.24 frames.], batch size: 35, lr: 2.66e-04
2022-05-06 02:41:20,034 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 02:41:29,607 INFO [train.py:742] (4/8) Epoch 8, validation: loss=0.1075, simple_loss=0.1921, pruned_loss=0.01146, over 914524.00 frames.
2022-05-06 02:42:09,069 INFO [train.py:715] (4/8) Epoch 8, batch 6050, loss[loss=0.1494, simple_loss=0.2123, pruned_loss=0.04329, over 4896.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2165, pruned_loss=0.03595, over 972371.55 frames.], batch size: 19, lr: 2.66e-04
2022-05-06 02:42:48,771 INFO [train.py:715] (4/8) Epoch 8, batch 6100, loss[loss=0.1299, simple_loss=0.2032, pruned_loss=0.02827, over 4744.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2168, pruned_loss=0.0363, over 973025.11 frames.], batch size: 16, lr: 2.66e-04
2022-05-06 02:43:28,437 INFO [train.py:715] (4/8) Epoch 8, batch 6150, loss[loss=0.1211, simple_loss=0.192, pruned_loss=0.02515, over 4835.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2169, pruned_loss=0.03648, over 972566.16 frames.], batch size: 15, lr: 2.66e-04
2022-05-06 02:44:08,983 INFO [train.py:715] (4/8) Epoch 8, batch 6200, loss[loss=0.1389, simple_loss=0.2192, pruned_loss=0.02932, over 4852.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2168, pruned_loss=0.03645, over 972027.96 frames.], batch size: 20, lr: 2.66e-04
2022-05-06 02:44:49,471 INFO [train.py:715] (4/8) Epoch 8, batch 6250, loss[loss=0.1502, simple_loss=0.2176, pruned_loss=0.04139, over 4707.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2162, pruned_loss=0.0365, over 972085.42 frames.], batch size: 15, lr: 2.66e-04
2022-05-06 02:45:29,140 INFO [train.py:715] (4/8) Epoch 8, batch 6300, loss[loss=0.1177, simple_loss=0.1881, pruned_loss=0.02361, over 4892.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2158, pruned_loss=0.03621, over 971895.09 frames.], batch size: 17, lr: 2.66e-04
2022-05-06 02:46:08,063 INFO [train.py:715] (4/8) Epoch 8, batch 6350, loss[loss=0.1609, simple_loss=0.23, pruned_loss=0.04585, over 4832.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2167, pruned_loss=0.03626, over 972217.30 frames.], batch size: 15, lr: 2.66e-04
2022-05-06 02:46:47,829 INFO [train.py:715] (4/8) Epoch 8, batch 6400, loss[loss=0.1296, simple_loss=0.2087, pruned_loss=0.02524, over 4864.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2158, pruned_loss=0.03562, over 972275.80 frames.], batch size: 20, lr: 2.66e-04
2022-05-06 02:47:27,068 INFO [train.py:715] (4/8) Epoch 8, batch 6450, loss[loss=0.1421, simple_loss=0.2115, pruned_loss=0.03639, over 4745.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03521, over 972672.24 frames.], batch size: 16, lr: 2.66e-04
2022-05-06 02:48:06,520 INFO [train.py:715] (4/8) Epoch 8, batch 6500, loss[loss=0.1604, simple_loss=0.2372, pruned_loss=0.04184, over 4981.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2151, pruned_loss=0.03577, over 973074.06 frames.], batch size: 35, lr: 2.66e-04
2022-05-06 02:48:45,639 INFO [train.py:715] (4/8) Epoch 8, batch 6550, loss[loss=0.1659, simple_loss=0.2467, pruned_loss=0.04259, over 4928.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2145, pruned_loss=0.03538, over 973179.61 frames.], batch size: 21, lr: 2.66e-04
2022-05-06 02:49:25,300 INFO [train.py:715] (4/8) Epoch 8, batch 6600, loss[loss=0.1463, simple_loss=0.2197, pruned_loss=0.03648, over 4986.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2152, pruned_loss=0.03577, over 972939.82 frames.], batch size: 27, lr: 2.66e-04
2022-05-06 02:50:04,625 INFO [train.py:715] (4/8) Epoch 8, batch 6650, loss[loss=0.1217, simple_loss=0.1883, pruned_loss=0.02756, over 4644.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2145, pruned_loss=0.03535, over 971646.44 frames.], batch size: 13, lr: 2.66e-04
2022-05-06 02:50:43,402 INFO [train.py:715] (4/8) Epoch 8, batch 6700, loss[loss=0.1455, simple_loss=0.2199, pruned_loss=0.03552, over 4985.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2152, pruned_loss=0.03592, over 972192.73 frames.], batch size: 28, lr: 2.66e-04
2022-05-06 02:51:23,631 INFO [train.py:715] (4/8) Epoch 8, batch 6750, loss[loss=0.1762, simple_loss=0.2307, pruned_loss=0.06091, over 4889.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2151, pruned_loss=0.0357, over 972644.27 frames.], batch size: 22, lr: 2.66e-04
2022-05-06 02:52:03,056 INFO [train.py:715] (4/8) Epoch 8, batch 6800, loss[loss=0.1537, simple_loss=0.2283, pruned_loss=0.0396, over 4989.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2147, pruned_loss=0.03544, over 972276.92 frames.], batch size: 26, lr: 2.66e-04
2022-05-06 02:52:42,034 INFO [train.py:715] (4/8) Epoch 8, batch 6850, loss[loss=0.1265, simple_loss=0.2025, pruned_loss=0.0252, over 4805.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03549, over 971626.20 frames.], batch size: 25, lr: 2.66e-04
2022-05-06 02:53:21,946 INFO [train.py:715] (4/8) Epoch 8, batch 6900, loss[loss=0.1189, simple_loss=0.199, pruned_loss=0.0194, over 4975.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03543, over 971862.55 frames.], batch size: 26, lr: 2.66e-04
2022-05-06 02:54:02,359 INFO [train.py:715] (4/8) Epoch 8, batch 6950, loss[loss=0.1288, simple_loss=0.2034, pruned_loss=0.02706, over 4756.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2157, pruned_loss=0.03572, over 972056.67 frames.], batch size: 16, lr: 2.66e-04
2022-05-06 02:54:42,175 INFO [train.py:715] (4/8) Epoch 8, batch 7000, loss[loss=0.1238, simple_loss=0.1906, pruned_loss=0.02848, over 4831.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2159, pruned_loss=0.03569, over 972000.21 frames.], batch size: 30, lr: 2.65e-04
2022-05-06 02:55:21,785 INFO [train.py:715] (4/8) Epoch 8, batch 7050, loss[loss=0.1492, simple_loss=0.2194, pruned_loss=0.03948, over 4845.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2151, pruned_loss=0.03535, over 972218.78 frames.], batch size: 30, lr: 2.65e-04
2022-05-06 02:56:01,476 INFO [train.py:715] (4/8) Epoch 8, batch 7100, loss[loss=0.1538, simple_loss=0.2198, pruned_loss=0.04393, over 4980.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2148, pruned_loss=0.03523, over 972991.40 frames.], batch size: 25, lr: 2.65e-04
2022-05-06 02:56:41,148 INFO [train.py:715] (4/8) Epoch 8, batch 7150, loss[loss=0.1543, simple_loss=0.2274, pruned_loss=0.04059, over 4835.00 frames.], tot_loss[loss=0.142, simple_loss=0.214, pruned_loss=0.03504, over 972384.39 frames.], batch size: 26, lr: 2.65e-04
2022-05-06 02:57:20,446 INFO [train.py:715] (4/8) Epoch 8, batch 7200, loss[loss=0.1528, simple_loss=0.2197, pruned_loss=0.04292, over 4977.00 frames.], tot_loss[loss=0.1429, simple_loss=0.215, pruned_loss=0.0354, over 972160.28 frames.], batch size: 24, lr: 2.65e-04
2022-05-06 02:57:59,448 INFO [train.py:715] (4/8) Epoch 8, batch 7250, loss[loss=0.1425, simple_loss=0.2194, pruned_loss=0.03283, over 4980.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2149, pruned_loss=0.03533, over 972898.86 frames.], batch size: 14, lr: 2.65e-04
2022-05-06 02:58:39,557 INFO [train.py:715] (4/8) Epoch 8, batch 7300, loss[loss=0.1597, simple_loss=0.2357, pruned_loss=0.04183, over 4795.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2145, pruned_loss=0.03543, over 972711.00 frames.], batch size: 14, lr: 2.65e-04
2022-05-06 02:59:18,928 INFO [train.py:715] (4/8) Epoch 8, batch 7350, loss[loss=0.1511, simple_loss=0.2258, pruned_loss=0.0382, over 4821.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2145, pruned_loss=0.03533, over 972939.46 frames.], batch size: 27, lr: 2.65e-04
2022-05-06 02:59:58,522 INFO [train.py:715] (4/8) Epoch 8, batch 7400, loss[loss=0.1212, simple_loss=0.1919, pruned_loss=0.02529, over 4742.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2151, pruned_loss=0.03559, over 973464.29 frames.], batch size: 16, lr: 2.65e-04
2022-05-06 03:00:38,454 INFO [train.py:715] (4/8) Epoch 8, batch 7450, loss[loss=0.125, simple_loss=0.1973, pruned_loss=0.0263, over 4920.00 frames.], tot_loss[loss=0.143, simple_loss=0.2149, pruned_loss=0.03558, over 973634.94 frames.], batch size: 23, lr: 2.65e-04
2022-05-06 03:01:18,180 INFO [train.py:715] (4/8) Epoch 8, batch 7500, loss[loss=0.1541, simple_loss=0.2258, pruned_loss=0.04119, over 4896.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2158, pruned_loss=0.03627, over 972807.45 frames.], batch size: 39, lr: 2.65e-04
2022-05-06 03:01:57,871 INFO [train.py:715] (4/8) Epoch 8, batch 7550, loss[loss=0.1121, simple_loss=0.194, pruned_loss=0.01513, over 4848.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2157, pruned_loss=0.03632, over 972385.84 frames.], batch size: 32, lr: 2.65e-04
2022-05-06 03:02:37,819 INFO [train.py:715] (4/8) Epoch 8, batch 7600, loss[loss=0.1695, simple_loss=0.2477, pruned_loss=0.04568, over 4926.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2157, pruned_loss=0.03596, over 972658.37 frames.], batch size: 23, lr: 2.65e-04
2022-05-06 03:03:17,987 INFO [train.py:715] (4/8) Epoch 8, batch 7650, loss[loss=0.1657, simple_loss=0.2457, pruned_loss=0.04279, over 4909.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2152, pruned_loss=0.03575, over 971809.15 frames.], batch size: 17, lr: 2.65e-04
2022-05-06 03:03:57,437 INFO [train.py:715] (4/8) Epoch 8, batch 7700, loss[loss=0.1586, simple_loss=0.2284, pruned_loss=0.04444, over 4990.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2151, pruned_loss=0.03562, over 972270.58 frames.], batch size: 15, lr: 2.65e-04
2022-05-06 03:04:36,608 INFO [train.py:715] (4/8) Epoch 8, batch 7750, loss[loss=0.1356, simple_loss=0.2026, pruned_loss=0.03424, over 4890.00 frames.], tot_loss[loss=0.143, simple_loss=0.2145, pruned_loss=0.03573, over 972862.43 frames.], batch size: 19, lr: 2.65e-04
2022-05-06 03:05:16,798 INFO [train.py:715] (4/8) Epoch 8, batch 7800, loss[loss=0.1236, simple_loss=0.1971, pruned_loss=0.02504, over 4807.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2153, pruned_loss=0.03595, over 972084.91 frames.], batch size: 21, lr: 2.65e-04
2022-05-06 03:05:56,861 INFO [train.py:715] (4/8) Epoch 8, batch 7850, loss[loss=0.1482, simple_loss=0.2204, pruned_loss=0.03801, over 4797.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2156, pruned_loss=0.03566, over 972218.49 frames.], batch size: 24, lr: 2.65e-04
2022-05-06 03:06:35,515 INFO [train.py:715] (4/8) Epoch 8, batch 7900, loss[loss=0.1329, simple_loss=0.2033, pruned_loss=0.03128, over 4706.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03575, over 972251.34 frames.], batch size: 15, lr: 2.65e-04
2022-05-06 03:07:15,006 INFO [train.py:715] (4/8) Epoch 8, batch 7950, loss[loss=0.1619, simple_loss=0.2381, pruned_loss=0.0428, over 4952.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2164, pruned_loss=0.03641, over 972538.72 frames.], batch size: 21, lr: 2.65e-04
2022-05-06 03:07:54,691 INFO [train.py:715] (4/8) Epoch 8, batch 8000, loss[loss=0.1459, simple_loss=0.2199, pruned_loss=0.03593, over 4889.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2163, pruned_loss=0.03617, over 971836.83 frames.], batch size: 16, lr: 2.65e-04
2022-05-06 03:08:33,645 INFO [train.py:715] (4/8) Epoch 8, batch 8050, loss[loss=0.131, simple_loss=0.1951, pruned_loss=0.03347, over 4911.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2163, pruned_loss=0.03643, over 972071.77 frames.], batch size: 19, lr: 2.65e-04
2022-05-06 03:09:12,022 INFO [train.py:715] (4/8) Epoch 8, batch 8100, loss[loss=0.139, simple_loss=0.2029, pruned_loss=0.03754, over 4982.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2162, pruned_loss=0.03647, over 971747.83 frames.], batch size: 35, lr: 2.65e-04
2022-05-06 03:09:51,245 INFO [train.py:715] (4/8) Epoch 8, batch 8150, loss[loss=0.136, simple_loss=0.2001, pruned_loss=0.03592, over 4966.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2154, pruned_loss=0.03587, over 971787.90 frames.], batch size: 24, lr: 2.65e-04
2022-05-06 03:10:31,278 INFO [train.py:715] (4/8) Epoch 8, batch 8200, loss[loss=0.12, simple_loss=0.1918, pruned_loss=0.02409, over 4756.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2155, pruned_loss=0.03541, over 972000.09 frames.], batch size: 16, lr: 2.65e-04
2022-05-06 03:11:09,918 INFO [train.py:715] (4/8) Epoch 8, batch 8250, loss[loss=0.1228, simple_loss=0.1932, pruned_loss=0.02622, over 4975.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03592, over 972381.72 frames.], batch size: 15, lr: 2.65e-04
2022-05-06 03:11:48,870 INFO [train.py:715] (4/8) Epoch 8, batch 8300, loss[loss=0.1431, simple_loss=0.2068, pruned_loss=0.03968, over 4854.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2178, pruned_loss=0.03655, over 972274.40 frames.], batch size: 34, lr: 2.65e-04
2022-05-06 03:12:28,295 INFO [train.py:715] (4/8) Epoch 8, batch 8350, loss[loss=0.1108, simple_loss=0.18, pruned_loss=0.0208, over 4889.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2173, pruned_loss=0.0367, over 972336.64 frames.], batch size: 16, lr: 2.65e-04
2022-05-06 03:13:07,309 INFO [train.py:715] (4/8) Epoch 8, batch 8400, loss[loss=0.1343, simple_loss=0.194, pruned_loss=0.0373, over 4930.00 frames.], tot_loss[loss=0.145, simple_loss=0.2167, pruned_loss=0.03661, over 971686.71 frames.], batch size: 18, lr: 2.65e-04
2022-05-06 03:13:45,966 INFO [train.py:715] (4/8) Epoch 8, batch 8450, loss[loss=0.15, simple_loss=0.2231, pruned_loss=0.03844, over 4885.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2166, pruned_loss=0.03654, over 971562.66 frames.], batch size: 22, lr: 2.65e-04
2022-05-06 03:14:25,532 INFO [train.py:715] (4/8) Epoch 8, batch 8500, loss[loss=0.1405, simple_loss=0.217, pruned_loss=0.03198, over 4825.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2157, pruned_loss=0.03611, over 971630.71 frames.], batch size: 27, lr: 2.65e-04
2022-05-06 03:15:05,516 INFO [train.py:715] (4/8) Epoch 8, batch 8550, loss[loss=0.1382, simple_loss=0.2102, pruned_loss=0.03307, over 4817.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2155, pruned_loss=0.03582, over 971965.97 frames.], batch size: 25, lr: 2.65e-04
2022-05-06 03:15:44,164 INFO [train.py:715] (4/8) Epoch 8, batch 8600, loss[loss=0.1611, simple_loss=0.2165, pruned_loss=0.05282, over 4854.00 frames.], tot_loss[loss=0.143, simple_loss=0.2147, pruned_loss=0.03559, over 971821.50 frames.], batch size: 30, lr: 2.65e-04
2022-05-06 03:16:23,282 INFO [train.py:715] (4/8) Epoch 8, batch 8650, loss[loss=0.1507, simple_loss=0.2244, pruned_loss=0.03847, over 4986.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2148, pruned_loss=0.03522, over 971928.01 frames.], batch size: 26, lr: 2.65e-04
2022-05-06 03:17:02,902 INFO [train.py:715] (4/8) Epoch 8, batch 8700, loss[loss=0.1359, simple_loss=0.2042, pruned_loss=0.03386, over 4907.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03589, over 971592.22 frames.], batch size: 17, lr: 2.65e-04
2022-05-06 03:17:41,702 INFO [train.py:715] (4/8) Epoch 8, batch 8750, loss[loss=0.1423, simple_loss=0.2114, pruned_loss=0.0366, over 4813.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2164, pruned_loss=0.03656, over 972259.09 frames.], batch size: 13, lr: 2.65e-04
2022-05-06 03:18:20,675 INFO [train.py:715] (4/8) Epoch 8, batch 8800, loss[loss=0.1074, simple_loss=0.1845, pruned_loss=0.01514, over 4931.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2159, pruned_loss=0.03633, over 972898.75 frames.], batch size: 23, lr: 2.65e-04
2022-05-06 03:19:00,218 INFO [train.py:715] (4/8) Epoch 8, batch 8850, loss[loss=0.1489, simple_loss=0.2196, pruned_loss=0.03915, over 4884.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2164, pruned_loss=0.0363, over 972413.49 frames.], batch size: 16, lr: 2.65e-04
2022-05-06 03:19:39,728 INFO [train.py:715] (4/8) Epoch 8, batch 8900, loss[loss=0.1777, simple_loss=0.2499, pruned_loss=0.05277, over 4840.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2162, pruned_loss=0.036, over 971614.06 frames.], batch size: 30, lr: 2.65e-04
2022-05-06 03:20:18,229 INFO [train.py:715] (4/8) Epoch 8, batch 8950, loss[loss=0.1615, simple_loss=0.2355, pruned_loss=0.0438, over 4831.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2157, pruned_loss=0.03588, over 971156.59 frames.], batch size: 15, lr: 2.65e-04
2022-05-06 03:20:57,339 INFO [train.py:715] (4/8) Epoch 8, batch 9000, loss[loss=0.148, simple_loss=0.2255, pruned_loss=0.03523, over 4895.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2157, pruned_loss=0.03571, over 971153.99 frames.], batch size: 18, lr: 2.65e-04
2022-05-06 03:20:57,339 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 03:21:06,880 INFO [train.py:742] (4/8) Epoch 8, validation: loss=0.1075, simple_loss=0.1922, pruned_loss=0.01144, over 914524.00 frames.
2022-05-06 03:21:46,743 INFO [train.py:715] (4/8) Epoch 8, batch 9050, loss[loss=0.1202, simple_loss=0.1887, pruned_loss=0.02584, over 4772.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03582, over 971423.22 frames.], batch size: 18, lr: 2.65e-04
2022-05-06 03:22:26,223 INFO [train.py:715] (4/8) Epoch 8, batch 9100, loss[loss=0.1252, simple_loss=0.1976, pruned_loss=0.02641, over 4988.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2156, pruned_loss=0.03582, over 971904.32 frames.], batch size: 28, lr: 2.65e-04
2022-05-06 03:23:05,921 INFO [train.py:715] (4/8) Epoch 8, batch 9150, loss[loss=0.1293, simple_loss=0.2046, pruned_loss=0.02703, over 4813.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2142, pruned_loss=0.03515, over 971570.12 frames.], batch size: 21, lr: 2.64e-04
2022-05-06 03:23:44,124 INFO [train.py:715] (4/8) Epoch 8, batch 9200, loss[loss=0.1847, simple_loss=0.2358, pruned_loss=0.06674, over 4891.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2136, pruned_loss=0.03511, over 970892.65 frames.], batch size: 32, lr: 2.64e-04
2022-05-06 03:24:23,667 INFO [train.py:715] (4/8) Epoch 8, batch 9250, loss[loss=0.1931, simple_loss=0.2503, pruned_loss=0.06794, over 4923.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2143, pruned_loss=0.03533, over 971430.37 frames.], batch size: 17, lr: 2.64e-04
2022-05-06 03:25:03,200 INFO [train.py:715] (4/8) Epoch 8, batch 9300, loss[loss=0.1405, simple_loss=0.2123, pruned_loss=0.03437, over 4774.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.0356, over 971245.28 frames.], batch size: 18, lr: 2.64e-04
2022-05-06 03:25:42,060 INFO [train.py:715] (4/8) Epoch 8, batch 9350, loss[loss=0.1444, simple_loss=0.2242, pruned_loss=0.03229, over 4880.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2154, pruned_loss=0.03559, over 971461.02 frames.], batch size: 16, lr: 2.64e-04
2022-05-06 03:26:20,916 INFO [train.py:715] (4/8) Epoch 8, batch 9400, loss[loss=0.12, simple_loss=0.192, pruned_loss=0.02402, over 4893.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2157, pruned_loss=0.03581, over 970939.68 frames.], batch size: 17, lr: 2.64e-04
2022-05-06 03:27:00,377 INFO [train.py:715] (4/8) Epoch 8, batch 9450, loss[loss=0.1541, simple_loss=0.2179, pruned_loss=0.04519, over 4857.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2151, pruned_loss=0.03566, over 970995.61 frames.], batch size: 20, lr: 2.64e-04
2022-05-06 03:27:40,540 INFO [train.py:715] (4/8) Epoch 8, batch 9500, loss[loss=0.1252, simple_loss=0.2021, pruned_loss=0.02413, over 4912.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03556, over 970725.23 frames.], batch size: 19, lr: 2.64e-04
2022-05-06 03:28:21,698 INFO [train.py:715] (4/8) Epoch 8, batch 9550, loss[loss=0.1267, simple_loss=0.2044, pruned_loss=0.02448, over 4936.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2157, pruned_loss=0.03569, over 971416.11 frames.], batch size: 21, lr: 2.64e-04
2022-05-06 03:29:01,735 INFO [train.py:715] (4/8) Epoch 8, batch 9600, loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.02932, over 4904.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2153, pruned_loss=0.03526, over 971709.73 frames.], batch size: 17, lr: 2.64e-04
2022-05-06 03:29:41,772 INFO [train.py:715] (4/8) Epoch 8, batch 9650, loss[loss=0.1356, simple_loss=0.2068, pruned_loss=0.03218, over 4738.00 frames.], tot_loss[loss=0.143, simple_loss=0.2149, pruned_loss=0.03557, over 972405.20 frames.], batch size: 16, lr: 2.64e-04
2022-05-06 03:30:21,098 INFO [train.py:715] (4/8) Epoch 8, batch 9700, loss[loss=0.1358, simple_loss=0.212, pruned_loss=0.02974, over 4892.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2156, pruned_loss=0.03581, over 971849.03 frames.], batch size: 22, lr: 2.64e-04
2022-05-06 03:30:59,865 INFO [train.py:715] (4/8) Epoch 8, batch 9750, loss[loss=0.1134, simple_loss=0.1943, pruned_loss=0.01625, over 4989.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2154, pruned_loss=0.03578, over 972026.41 frames.], batch size: 25, lr: 2.64e-04
2022-05-06 03:31:39,480 INFO [train.py:715] (4/8) Epoch 8, batch 9800, loss[loss=0.1019, simple_loss=0.1748, pruned_loss=0.01445, over 4821.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2154, pruned_loss=0.03601, over 971744.50 frames.], batch size: 13, lr: 2.64e-04
2022-05-06 03:32:18,971 INFO [train.py:715] (4/8) Epoch 8, batch 9850, loss[loss=0.1474, simple_loss=0.2147, pruned_loss=0.04005, over 4925.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2146, pruned_loss=0.03546, over 972240.60 frames.], batch size: 23, lr: 2.64e-04
2022-05-06 03:32:58,276 INFO [train.py:715] (4/8) Epoch 8, batch 9900, loss[loss=0.1449, simple_loss=0.2164, pruned_loss=0.03669, over 4846.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2157, pruned_loss=0.03592, over 973420.25 frames.], batch size: 32, lr: 2.64e-04
2022-05-06 03:33:37,621 INFO [train.py:715] (4/8) Epoch 8, batch 9950, loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02846, over 4768.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2149, pruned_loss=0.03526, over 973278.40 frames.], batch size: 16, lr: 2.64e-04
2022-05-06 03:34:17,531 INFO [train.py:715] (4/8) Epoch 8, batch 10000, loss[loss=0.1407, simple_loss=0.2205, pruned_loss=0.03045, over 4821.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2157, pruned_loss=0.03566, over 972278.54 frames.], batch size: 27, lr: 2.64e-04
2022-05-06 03:34:56,511 INFO [train.py:715] (4/8) Epoch 8, batch 10050, loss[loss=0.118, simple_loss=0.1919, pruned_loss=0.02207, over 4793.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2155, pruned_loss=0.03589, over 972038.37 frames.], batch size: 12, lr: 2.64e-04
2022-05-06 03:35:35,062 INFO [train.py:715] (4/8) Epoch 8, batch 10100, loss[loss=0.1568, simple_loss=0.2391, pruned_loss=0.03722, over 4950.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2157, pruned_loss=0.03607, over 972645.87 frames.], batch size: 24, lr: 2.64e-04
2022-05-06 03:36:15,140 INFO [train.py:715] (4/8) Epoch 8, batch 10150, loss[loss=0.1311, simple_loss=0.2021, pruned_loss=0.03003, over 4935.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2159, pruned_loss=0.03596, over 972228.76 frames.], batch size: 21, lr: 2.64e-04
2022-05-06 03:36:55,127 INFO [train.py:715] (4/8) Epoch 8, batch 10200, loss[loss=0.1613, simple_loss=0.2326, pruned_loss=0.04496, over 4976.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2152, pruned_loss=0.0358, over 972338.90 frames.], batch size: 15, lr: 2.64e-04
2022-05-06 03:37:34,623 INFO [train.py:715] (4/8) Epoch 8, batch 10250, loss[loss=0.129, simple_loss=0.2034, pruned_loss=0.02733, over 4942.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03516, over 973256.04 frames.], batch size: 23, lr: 2.64e-04
2022-05-06 03:38:14,429 INFO [train.py:715] (4/8) Epoch 8, batch 10300, loss[loss=0.1404, simple_loss=0.2201, pruned_loss=0.03036, over 4917.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2151, pruned_loss=0.0349, over 973027.33 frames.], batch size: 18, lr: 2.64e-04
2022-05-06 03:38:53,948 INFO [train.py:715] (4/8) Epoch 8, batch 10350, loss[loss=0.1234, simple_loss=0.2101, pruned_loss=0.01831, over 4758.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2152, pruned_loss=0.0348, over 973839.29 frames.], batch size: 19, lr: 2.64e-04
2022-05-06 03:39:32,636 INFO [train.py:715] (4/8) Epoch 8, batch 10400, loss[loss=0.1388, simple_loss=0.2098, pruned_loss=0.03389, over 4779.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2153, pruned_loss=0.03498, over 973610.63 frames.], batch size: 14, lr: 2.64e-04
2022-05-06 03:40:12,241 INFO [train.py:715] (4/8) Epoch 8, batch 10450, loss[loss=0.119, simple_loss=0.1904, pruned_loss=0.02381, over 4783.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2155, pruned_loss=0.03541, over 973610.17 frames.], batch size: 17, lr: 2.64e-04
2022-05-06 03:40:51,304 INFO [train.py:715] (4/8) Epoch 8, batch 10500, loss[loss=0.1643, simple_loss=0.2383, pruned_loss=0.04516, over 4828.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03505, over 972719.97 frames.], batch size: 26, lr: 2.64e-04
2022-05-06 03:41:30,155 INFO [train.py:715] (4/8) Epoch 8, batch 10550, loss[loss=0.1391, simple_loss=0.2059, pruned_loss=0.03612, over 4958.00 frames.], tot_loss[loss=0.1418, simple_loss=0.214, pruned_loss=0.03479, over 972766.90 frames.], batch size: 29, lr: 2.64e-04
2022-05-06 03:42:08,772 INFO [train.py:715] (4/8) Epoch 8, batch 10600, loss[loss=0.1443, simple_loss=0.2293, pruned_loss=0.0297, over 4773.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2162, pruned_loss=0.03564, over 972748.48 frames.], batch size: 17, lr: 2.64e-04
2022-05-06 03:42:48,077 INFO [train.py:715] (4/8) Epoch 8, batch 10650, loss[loss=0.131, simple_loss=0.2069, pruned_loss=0.02754, over 4861.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2167, pruned_loss=0.03593, over 972443.44 frames.], batch size: 20, lr: 2.64e-04
2022-05-06 03:43:27,255 INFO [train.py:715] (4/8) Epoch 8, batch 10700, loss[loss=0.1604, simple_loss=0.2394, pruned_loss=0.04067, over 4701.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2168, pruned_loss=0.03614, over 971860.02 frames.], batch size: 15, lr: 2.64e-04
2022-05-06 03:44:06,352 INFO [train.py:715] (4/8) Epoch 8, batch 10750, loss[loss=0.1265, simple_loss=0.1982, pruned_loss=0.02742, over 4832.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2171, pruned_loss=0.03629, over 972137.73 frames.], batch size: 13, lr: 2.64e-04
2022-05-06 03:44:46,297 INFO [train.py:715] (4/8) Epoch 8, batch 10800, loss[loss=0.1546, simple_loss=0.2158, pruned_loss=0.0467, over 4761.00 frames.], tot_loss[loss=0.1449, simple_loss=0.217, pruned_loss=0.03641, over 970769.58 frames.], batch size: 14, lr: 2.64e-04
2022-05-06 03:45:26,103 INFO [train.py:715] (4/8) Epoch 8, batch 10850, loss[loss=0.1392, simple_loss=0.2128, pruned_loss=0.0328, over 4818.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2159, pruned_loss=0.03596, over 971103.58 frames.], batch size: 15, lr: 2.64e-04
2022-05-06 03:46:05,371 INFO [train.py:715] (4/8) Epoch 8, batch 10900, loss[loss=0.14, simple_loss=0.2268, pruned_loss=0.02657, over 4761.00 frames.], tot_loss[loss=0.145, simple_loss=0.2173, pruned_loss=0.03641, over 971468.03 frames.], batch size: 16, lr: 2.64e-04
2022-05-06 03:46:44,375 INFO [train.py:715] (4/8) Epoch 8, batch 10950, loss[loss=0.154, simple_loss=0.2193, pruned_loss=0.0444, over 4767.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2182, pruned_loss=0.03652, over 972027.81 frames.], batch size: 19, lr: 2.64e-04
2022-05-06 03:47:24,375 INFO [train.py:715] (4/8) Epoch 8, batch 11000, loss[loss=0.1191, simple_loss=0.1854, pruned_loss=0.0264, over 4963.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2177, pruned_loss=0.03657, over 971873.87 frames.], batch size: 15, lr: 2.64e-04
2022-05-06 03:48:03,912 INFO [train.py:715] (4/8) Epoch 8, batch 11050, loss[loss=0.1423, simple_loss=0.2126, pruned_loss=0.03596, over 4759.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2171, pruned_loss=0.03615, over 971995.23 frames.], batch size: 16, lr: 2.64e-04
2022-05-06 03:48:42,671 INFO [train.py:715] (4/8) Epoch 8, batch 11100, loss[loss=0.141, simple_loss=0.2172, pruned_loss=0.03244, over 4820.00 frames.], tot_loss[loss=0.1439, simple_loss=0.216, pruned_loss=0.03587, over 972195.48 frames.], batch size: 27, lr: 2.64e-04
2022-05-06 03:49:22,146 INFO [train.py:715] (4/8) Epoch 8, batch 11150, loss[loss=0.1482, simple_loss=0.2223, pruned_loss=0.03701, over 4876.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.0356, over 972429.44 frames.], batch size: 16, lr: 2.64e-04
2022-05-06 03:50:01,939 INFO [train.py:715] (4/8) Epoch 8, batch 11200, loss[loss=0.1252, simple_loss=0.1989, pruned_loss=0.02577, over 4851.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2166, pruned_loss=0.03613, over 972126.31 frames.], batch size: 20, lr: 2.64e-04
2022-05-06 03:50:40,566 INFO [train.py:715] (4/8) Epoch 8, batch 11250, loss[loss=0.12, simple_loss=0.196, pruned_loss=0.02199, over 4977.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2153, pruned_loss=0.03526, over 972638.25 frames.], batch size: 14, lr: 2.64e-04
2022-05-06 03:51:19,591 INFO [train.py:715] (4/8) Epoch 8, batch 11300, loss[loss=0.119, simple_loss=0.1933, pruned_loss=0.02238, over 4804.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.03507, over 972955.73 frames.], batch size: 21, lr: 2.64e-04
2022-05-06 03:51:58,924 INFO [train.py:715] (4/8) Epoch 8, batch 11350, loss[loss=0.1438, simple_loss=0.2214, pruned_loss=0.03313, over 4820.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03533, over 973245.52 frames.], batch size: 13, lr: 2.63e-04
2022-05-06 03:52:37,405 INFO [train.py:715] (4/8) Epoch 8, batch 11400, loss[loss=0.157, simple_loss=0.2218, pruned_loss=0.04607, over 4841.00 frames.], tot_loss[loss=0.143, simple_loss=0.2157, pruned_loss=0.03512, over 972475.75 frames.], batch size: 15, lr: 2.63e-04
2022-05-06 03:53:16,049 INFO [train.py:715] (4/8) Epoch 8, batch 11450, loss[loss=0.1583, simple_loss=0.2213, pruned_loss=0.0476, over 4906.00 frames.], tot_loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.03487, over 972609.75 frames.], batch size: 17, lr: 2.63e-04
2022-05-06 03:53:55,352 INFO [train.py:715] (4/8) Epoch 8, batch 11500, loss[loss=0.118, simple_loss=0.1953, pruned_loss=0.02034, over 4918.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03475, over 972086.71 frames.], batch size: 17, lr: 2.63e-04
2022-05-06 03:54:34,456 INFO [train.py:715] (4/8) Epoch 8, batch 11550, loss[loss=0.1386, simple_loss=0.2104, pruned_loss=0.03339, over 4735.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.03508, over 971980.76 frames.], batch size: 12, lr: 2.63e-04
2022-05-06 03:55:13,509 INFO [train.py:715] (4/8) Epoch 8, batch 11600, loss[loss=0.1608, simple_loss=0.2145, pruned_loss=0.05352, over 4977.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2159, pruned_loss=0.03524, over 972460.59 frames.], batch size: 14, lr: 2.63e-04
2022-05-06 03:55:53,460 INFO [train.py:715] (4/8) Epoch 8, batch 11650, loss[loss=0.1248, simple_loss=0.1997, pruned_loss=0.02496, over 4760.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03531, over 971935.30 frames.], batch size: 12, lr: 2.63e-04
2022-05-06 03:56:33,835 INFO [train.py:715] (4/8) Epoch 8, batch 11700, loss[loss=0.1197, simple_loss=0.1927, pruned_loss=0.02331, over 4929.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.03519, over 971882.70 frames.], batch size: 18, lr: 2.63e-04
2022-05-06 03:57:13,266 INFO [train.py:715] (4/8) Epoch 8, batch 11750, loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02872, over 4952.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.03511, over 971974.66 frames.], batch size: 29, lr: 2.63e-04
2022-05-06 03:57:52,304 INFO [train.py:715] (4/8) Epoch 8, batch 11800, loss[loss=0.1695, simple_loss=0.2272, pruned_loss=0.05593, over 4888.00 frames.], tot_loss[loss=0.1432, simple_loss=0.216, pruned_loss=0.0352, over 971834.71 frames.], batch size: 32, lr: 2.63e-04
2022-05-06 03:58:32,050 INFO [train.py:715] (4/8) Epoch 8, batch 11850, loss[loss=0.1567, simple_loss=0.2235, pruned_loss=0.0449, over 4876.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2163, pruned_loss=0.03505, over 971687.96 frames.], batch size: 22, lr: 2.63e-04
2022-05-06 03:59:11,744 INFO [train.py:715] (4/8) Epoch 8, batch 11900, loss[loss=0.1328, simple_loss=0.1952, pruned_loss=0.03521, over 4798.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2161, pruned_loss=0.03545, over 971182.28 frames.], batch size: 12, lr: 2.63e-04
2022-05-06 03:59:51,345 INFO [train.py:715] (4/8) Epoch 8, batch 11950, loss[loss=0.1496, simple_loss=0.2248, pruned_loss=0.03723, over 4810.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2159, pruned_loss=0.03533, over 970899.15 frames.], batch size: 21, lr: 2.63e-04
2022-05-06 04:00:30,528 INFO [train.py:715] (4/8) Epoch 8, batch 12000, loss[loss=0.1485, simple_loss=0.2283, pruned_loss=0.03434, over 4934.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.03528, over 971524.64 frames.], batch size: 23, lr: 2.63e-04
2022-05-06 04:00:30,529 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 04:00:40,090 INFO [train.py:742] (4/8) Epoch 8, validation: loss=0.1076, simple_loss=0.1923, pruned_loss=0.0115, over 914524.00 frames.
2022-05-06 04:01:19,838 INFO [train.py:715] (4/8) Epoch 8, batch 12050, loss[loss=0.1379, simple_loss=0.2183, pruned_loss=0.02877, over 4926.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2147, pruned_loss=0.03502, over 971230.18 frames.], batch size: 17, lr: 2.63e-04
2022-05-06 04:01:59,445 INFO [train.py:715] (4/8) Epoch 8, batch 12100, loss[loss=0.1286, simple_loss=0.203, pruned_loss=0.02711, over 4887.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2151, pruned_loss=0.03484, over 971599.10 frames.], batch size: 22, lr: 2.63e-04
2022-05-06 04:02:38,518 INFO [train.py:715] (4/8) Epoch 8, batch 12150, loss[loss=0.1299, simple_loss=0.2069, pruned_loss=0.02649, over 4866.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.0349, over 971444.11 frames.], batch size: 20, lr: 2.63e-04
2022-05-06 04:03:17,589 INFO [train.py:715] (4/8) Epoch 8, batch 12200, loss[loss=0.1318, simple_loss=0.2015, pruned_loss=0.03106, over 4771.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03511, over 971505.58 frames.], batch size: 19, lr: 2.63e-04
2022-05-06 04:03:57,160 INFO [train.py:715] (4/8) Epoch 8, batch 12250, loss[loss=0.1806, simple_loss=0.2517, pruned_loss=0.05476, over 4835.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2142, pruned_loss=0.0347, over 971462.39 frames.], batch size: 30, lr: 2.63e-04
2022-05-06 04:04:36,391 INFO [train.py:715] (4/8) Epoch 8, batch 12300, loss[loss=0.1762, simple_loss=0.2556, pruned_loss=0.04837, over 4778.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03516, over 971524.18 frames.], batch size: 18, lr: 2.63e-04
2022-05-06 04:05:15,233 INFO [train.py:715] (4/8) Epoch 8, batch 12350, loss[loss=0.1353, simple_loss=0.2115, pruned_loss=0.02953, over 4976.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2155, pruned_loss=0.03549, over 971660.04 frames.], batch size: 28, lr: 2.63e-04
2022-05-06 04:05:54,658 INFO [train.py:715] (4/8) Epoch 8, batch 12400, loss[loss=0.1126, simple_loss=0.1847, pruned_loss=0.02026, over 4985.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.0355, over 971884.00 frames.], batch size: 14, lr: 2.63e-04
2022-05-06 04:06:34,253 INFO [train.py:715] (4/8) Epoch 8, batch 12450, loss[loss=0.1313, simple_loss=0.215, pruned_loss=0.02374, over 4843.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2161, pruned_loss=0.03541, over 972064.10 frames.], batch size: 20, lr: 2.63e-04
2022-05-06 04:07:13,257 INFO [train.py:715] (4/8) Epoch 8, batch 12500, loss[loss=0.1264, simple_loss=0.1973, pruned_loss=0.02771, over 4848.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.03533, over 971932.66 frames.], batch size: 12, lr: 2.63e-04
2022-05-06 04:07:52,123 INFO [train.py:715] (4/8) Epoch 8, batch 12550, loss[loss=0.1281, simple_loss=0.2038, pruned_loss=0.02618, over 4870.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2153, pruned_loss=0.03526, over 972080.96 frames.], batch size: 20, lr: 2.63e-04
2022-05-06 04:08:31,832 INFO [train.py:715] (4/8) Epoch 8, batch 12600, loss[loss=0.142, simple_loss=0.2159, pruned_loss=0.03404, over 4961.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2153, pruned_loss=0.03519, over 972820.87 frames.], batch size: 24, lr: 2.63e-04
2022-05-06 04:09:10,878 INFO [train.py:715] (4/8) Epoch 8, batch 12650, loss[loss=0.13, simple_loss=0.2033, pruned_loss=0.02829, over 4901.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.03518, over 973432.52 frames.], batch size: 17, lr: 2.63e-04
2022-05-06 04:09:50,737 INFO [train.py:715] (4/8) Epoch 8, batch 12700, loss[loss=0.1782, simple_loss=0.2584, pruned_loss=0.04898, over 4949.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2147, pruned_loss=0.03529, over 972290.32 frames.], batch size: 21, lr: 2.63e-04
2022-05-06 04:10:30,123 INFO [train.py:715] (4/8) Epoch 8, batch 12750, loss[loss=0.1886, simple_loss=0.2653, pruned_loss=0.056, over 4866.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2146, pruned_loss=0.03513, over 971762.02 frames.], batch size: 16, lr: 2.63e-04
2022-05-06 04:11:10,321 INFO [train.py:715] (4/8) Epoch 8, batch 12800, loss[loss=0.1423, simple_loss=0.208, pruned_loss=0.03835, over 4894.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2136, pruned_loss=0.03486, over 971486.85 frames.], batch size: 17, lr: 2.63e-04
2022-05-06 04:11:48,982 INFO [train.py:715] (4/8) Epoch 8, batch 12850, loss[loss=0.1642, simple_loss=0.245, pruned_loss=0.04175, over 4963.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2146, pruned_loss=0.03557, over 971930.18 frames.], batch size: 24, lr: 2.63e-04
2022-05-06 04:12:28,015 INFO [train.py:715] (4/8) Epoch 8, batch 12900, loss[loss=0.139, simple_loss=0.1949, pruned_loss=0.04149, over 4696.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2157, pruned_loss=0.03637, over 971352.35 frames.], batch size: 15, lr: 2.63e-04
2022-05-06 04:13:07,523 INFO [train.py:715] (4/8) Epoch 8, batch 12950, loss[loss=0.1278, simple_loss=0.2099, pruned_loss=0.02287, over 4834.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2154, pruned_loss=0.03606, over 971777.43 frames.], batch size: 13, lr: 2.63e-04
2022-05-06 04:13:46,911 INFO [train.py:715] (4/8) Epoch 8, batch 13000, loss[loss=0.1446, simple_loss=0.217, pruned_loss=0.03608, over 4840.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2151, pruned_loss=0.03579, over 971593.38 frames.], batch size: 20, lr: 2.63e-04
2022-05-06 04:14:26,215 INFO [train.py:715] (4/8) Epoch 8, batch 13050, loss[loss=0.1334, simple_loss=0.2062, pruned_loss=0.03032, over 4873.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2152, pruned_loss=0.03595, over 971590.44 frames.], batch size: 22, lr: 2.63e-04
2022-05-06 04:15:05,641 INFO [train.py:715] (4/8) Epoch 8, batch 13100, loss[loss=0.1813, simple_loss=0.2606, pruned_loss=0.05106, over 4782.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2151, pruned_loss=0.03579, over 971585.85 frames.], batch size: 18, lr: 2.63e-04
2022-05-06 04:15:45,372 INFO [train.py:715] (4/8) Epoch 8, batch 13150, loss[loss=0.1542, simple_loss=0.2227, pruned_loss=0.04288, over 4984.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2156, pruned_loss=0.03586, over 970279.16 frames.], batch size: 35, lr: 2.63e-04
2022-05-06 04:16:24,328 INFO [train.py:715] (4/8) Epoch 8, batch 13200, loss[loss=0.1449, simple_loss=0.213, pruned_loss=0.03834, over 4831.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2165, pruned_loss=0.03597, over 970605.12 frames.], batch size: 25, lr: 2.63e-04
2022-05-06 04:17:03,715 INFO [train.py:715] (4/8) Epoch 8, batch 13250, loss[loss=0.1609, simple_loss=0.2266, pruned_loss=0.04761, over 4768.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.03588, over 970832.60 frames.], batch size: 19, lr: 2.63e-04
2022-05-06 04:17:43,334 INFO [train.py:715] (4/8) Epoch 8, batch 13300, loss[loss=0.1389, simple_loss=0.2202, pruned_loss=0.0288, over 4858.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2172, pruned_loss=0.03649, over 971315.15 frames.], batch size: 20, lr: 2.63e-04
2022-05-06 04:18:22,354 INFO [train.py:715] (4/8) Epoch 8, batch 13350, loss[loss=0.1276, simple_loss=0.1969, pruned_loss=0.02914, over 4872.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2164, pruned_loss=0.03599, over 971189.29 frames.], batch size: 22, lr: 2.63e-04
2022-05-06 04:19:01,000 INFO [train.py:715] (4/8) Epoch 8, batch 13400, loss[loss=0.1496, simple_loss=0.2321, pruned_loss=0.03358, over 4899.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2157, pruned_loss=0.03555, over 971884.60 frames.], batch size: 19, lr: 2.63e-04
2022-05-06 04:19:39,797 INFO [train.py:715] (4/8) Epoch 8, batch 13450, loss[loss=0.1534, simple_loss=0.2062, pruned_loss=0.05028, over 4966.00 frames.], tot_loss[loss=0.1447, simple_loss=0.217, pruned_loss=0.03623, over 972265.98 frames.], batch size: 14, lr: 2.63e-04
2022-05-06 04:20:19,854 INFO [train.py:715] (4/8) Epoch 8, batch 13500, loss[loss=0.1326, simple_loss=0.2031, pruned_loss=0.03107, over 4830.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2168, pruned_loss=0.03597, over 973307.50 frames.], batch size: 27, lr: 2.63e-04
2022-05-06 04:20:58,642 INFO [train.py:715] (4/8) Epoch 8, batch 13550, loss[loss=0.1597, simple_loss=0.223, pruned_loss=0.0482, over 4868.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2175, pruned_loss=0.03636, over 973861.97 frames.], batch size: 16, lr: 2.62e-04
2022-05-06 04:21:37,837 INFO [train.py:715] (4/8) Epoch 8, batch 13600, loss[loss=0.1314, simple_loss=0.2052, pruned_loss=0.02878, over 4847.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2169, pruned_loss=0.03594, over 973942.34 frames.], batch size: 30, lr: 2.62e-04
2022-05-06 04:22:16,975 INFO [train.py:715] (4/8) Epoch 8, batch 13650, loss[loss=0.1354, simple_loss=0.208, pruned_loss=0.03137, over 4930.00 frames.], tot_loss[loss=0.1445, simple_loss=0.217, pruned_loss=0.036, over 973881.09 frames.], batch size: 18, lr: 2.62e-04
2022-05-06 04:22:56,126 INFO [train.py:715] (4/8) Epoch 8, batch 13700, loss[loss=0.1787, simple_loss=0.2403, pruned_loss=0.05857, over 4827.00 frames.], tot_loss[loss=0.145, simple_loss=0.2173, pruned_loss=0.03629, over 973806.48 frames.], batch size: 30, lr: 2.62e-04
2022-05-06 04:23:34,771 INFO [train.py:715] (4/8) Epoch 8, batch 13750, loss[loss=0.1369, simple_loss=0.2047, pruned_loss=0.03454, over 4968.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2169, pruned_loss=0.03634, over 972867.31 frames.], batch size: 24, lr: 2.62e-04
2022-05-06 04:24:13,492 INFO [train.py:715] (4/8) Epoch 8, batch 13800, loss[loss=0.1325, simple_loss=0.2081, pruned_loss=0.02841, over 4905.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03587, over 972573.65 frames.], batch size: 23, lr: 2.62e-04
2022-05-06 04:24:52,947 INFO [train.py:715] (4/8) Epoch 8, batch 13850, loss[loss=0.1502, simple_loss=0.2146, pruned_loss=0.04287, over 4973.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2165, pruned_loss=0.03596, over 972648.27 frames.], batch size: 14, lr: 2.62e-04
2022-05-06 04:25:31,240 INFO [train.py:715] (4/8) Epoch 8, batch 13900, loss[loss=0.1325, simple_loss=0.2113, pruned_loss=0.02689, over 4926.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2162, pruned_loss=0.03574, over 972257.75 frames.], batch size: 23, lr: 2.62e-04
2022-05-06 04:26:10,331 INFO [train.py:715] (4/8) Epoch 8, batch 13950, loss[loss=0.1386, simple_loss=0.2103, pruned_loss=0.03344, over 4807.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03598, over 972407.48 frames.], batch size: 24, lr: 2.62e-04
2022-05-06 04:26:49,431 INFO [train.py:715] (4/8) Epoch 8, batch 14000, loss[loss=0.1447, simple_loss=0.2171, pruned_loss=0.03617, over 4894.00 frames.], tot_loss[loss=0.1439, simple_loss=0.216, pruned_loss=0.0359, over 972032.19 frames.], batch size: 19, lr: 2.62e-04
2022-05-06 04:27:28,485 INFO [train.py:715] (4/8) Epoch 8, batch 14050, loss[loss=0.155, simple_loss=0.2202, pruned_loss=0.04488, over 4884.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03602, over 972638.36 frames.], batch size: 22, lr: 2.62e-04
2022-05-06 04:28:06,679 INFO [train.py:715] (4/8) Epoch 8, batch 14100, loss[loss=0.1715, simple_loss=0.2513, pruned_loss=0.04581, over 4827.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03607, over 972018.53 frames.], batch size: 26, lr: 2.62e-04
2022-05-06 04:28:45,330 INFO [train.py:715] (4/8) Epoch 8, batch 14150, loss[loss=0.1554, simple_loss=0.2244, pruned_loss=0.04325, over 4919.00 frames.], tot_loss[loss=0.145, simple_loss=0.217, pruned_loss=0.03651, over 972360.35 frames.], batch size: 18, lr: 2.62e-04
2022-05-06 04:29:25,591 INFO [train.py:715] (4/8) Epoch 8, batch 14200, loss[loss=0.1576, simple_loss=0.2203, pruned_loss=0.04743, over 4845.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2165, pruned_loss=0.03658, over 972472.25 frames.], batch size: 26, lr: 2.62e-04
2022-05-06 04:30:04,163 INFO [train.py:715] (4/8) Epoch 8, batch 14250, loss[loss=0.1224, simple_loss=0.1806, pruned_loss=0.03212, over 4832.00 frames.], tot_loss[loss=0.145, simple_loss=0.2166, pruned_loss=0.03672, over 972129.01 frames.], batch size: 12, lr: 2.62e-04
2022-05-06 04:30:44,067 INFO [train.py:715] (4/8) Epoch 8, batch 14300, loss[loss=0.1199, simple_loss=0.1912, pruned_loss=0.02431, over 4889.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2155, pruned_loss=0.03589, over 971445.59 frames.], batch size: 22, lr: 2.62e-04
2022-05-06 04:31:23,529 INFO [train.py:715] (4/8) Epoch 8, batch 14350, loss[loss=0.1478, simple_loss=0.2299, pruned_loss=0.03279, over 4764.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2163, pruned_loss=0.03619, over 972086.61 frames.], batch size: 19, lr: 2.62e-04
2022-05-06 04:32:02,823 INFO [train.py:715] (4/8) Epoch 8, batch 14400, loss[loss=0.1191, simple_loss=0.1913, pruned_loss=0.02344, over 4975.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2172, pruned_loss=0.03652, over 972294.17 frames.], batch size: 28, lr: 2.62e-04
2022-05-06 04:32:41,515 INFO [train.py:715] (4/8) Epoch 8, batch 14450, loss[loss=0.1392, simple_loss=0.2159, pruned_loss=0.03119, over 4802.00 frames.], tot_loss[loss=0.1455, simple_loss=0.2173, pruned_loss=0.03688, over 972659.72 frames.], batch size: 14, lr: 2.62e-04
2022-05-06 04:33:20,778 INFO [train.py:715] (4/8) Epoch 8, batch 14500, loss[loss=0.1516, simple_loss=0.2259, pruned_loss=0.0387, over 4934.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2172, pruned_loss=0.03658, over 973739.63 frames.], batch size: 23, lr: 2.62e-04
2022-05-06 04:34:00,252 INFO [train.py:715] (4/8) Epoch 8, batch 14550, loss[loss=0.127, simple_loss=0.1944, pruned_loss=0.02975, over 4747.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2168, pruned_loss=0.03611, over 972925.69 frames.], batch size: 19, lr: 2.62e-04
2022-05-06 04:34:38,288 INFO [train.py:715] (4/8) Epoch 8, batch 14600, loss[loss=0.1426, simple_loss=0.221, pruned_loss=0.03212, over 4937.00 frames.], tot_loss[loss=0.145, simple_loss=0.2173, pruned_loss=0.03635, over 972269.10 frames.], batch size: 23, lr: 2.62e-04
2022-05-06 04:35:17,876 INFO [train.py:715] (4/8) Epoch 8, batch 14650, loss[loss=0.1478, simple_loss=0.2207, pruned_loss=0.03746, over 4914.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.03585, over 972718.86 frames.], batch size: 39, lr: 2.62e-04
2022-05-06 04:35:57,138 INFO [train.py:715] (4/8) Epoch 8, batch 14700, loss[loss=0.1505, simple_loss=0.2202, pruned_loss=0.04038, over 4875.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2156, pruned_loss=0.03558, over 972728.42 frames.], batch size: 16, lr: 2.62e-04
2022-05-06 04:36:35,954 INFO [train.py:715] (4/8) Epoch 8, batch 14750, loss[loss=0.1591, simple_loss=0.2253, pruned_loss=0.04644, over 4745.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.03546, over 971904.57 frames.], batch size: 16, lr: 2.62e-04
2022-05-06 04:37:14,352 INFO [train.py:715] (4/8) Epoch 8, batch 14800, loss[loss=0.1652, simple_loss=0.2423, pruned_loss=0.04408, over 4905.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03573, over 972380.72 frames.], batch size: 39, lr: 2.62e-04
2022-05-06 04:37:54,164 INFO [train.py:715] (4/8) Epoch 8, batch 14850, loss[loss=0.1639, simple_loss=0.2366, pruned_loss=0.04557, over 4981.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2164, pruned_loss=0.03576, over 972634.47 frames.], batch size: 25, lr: 2.62e-04
2022-05-06 04:38:33,085 INFO [train.py:715] (4/8) Epoch 8, batch 14900, loss[loss=0.1244, simple_loss=0.1963, pruned_loss=0.02626, over 4633.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.036, over 972165.66 frames.], batch size: 13, lr: 2.62e-04
2022-05-06 04:39:11,870 INFO [train.py:715] (4/8) Epoch 8, batch 14950, loss[loss=0.1457, simple_loss=0.216, pruned_loss=0.03765, over 4863.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2166, pruned_loss=0.03601, over 972042.96 frames.], batch size: 20, lr: 2.62e-04
2022-05-06 04:39:51,070 INFO [train.py:715] (4/8) Epoch 8, batch 15000, loss[loss=0.163, simple_loss=0.2265, pruned_loss=0.0497, over 4955.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2168, pruned_loss=0.03644, over 972232.68 frames.], batch size: 15, lr: 2.62e-04
2022-05-06 04:39:51,071 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 04:40:00,791 INFO [train.py:742] (4/8) Epoch 8, validation: loss=0.1076, simple_loss=0.1921, pruned_loss=0.01153, over 914524.00 frames.
2022-05-06 04:40:40,556 INFO [train.py:715] (4/8) Epoch 8, batch 15050, loss[loss=0.2004, simple_loss=0.2702, pruned_loss=0.06534, over 4825.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2169, pruned_loss=0.03663, over 973470.59 frames.], batch size: 13, lr: 2.62e-04
2022-05-06 04:41:19,876 INFO [train.py:715] (4/8) Epoch 8, batch 15100, loss[loss=0.1555, simple_loss=0.2255, pruned_loss=0.0428, over 4771.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.0368, over 973461.79 frames.], batch size: 19, lr: 2.62e-04
2022-05-06 04:41:59,413 INFO [train.py:715] (4/8) Epoch 8, batch 15150, loss[loss=0.169, simple_loss=0.2331, pruned_loss=0.0524, over 4955.00 frames.], tot_loss[loss=0.1459, simple_loss=0.2176, pruned_loss=0.03709, over 972635.90 frames.], batch size: 35, lr: 2.62e-04
2022-05-06 04:42:38,834 INFO [train.py:715] (4/8) Epoch 8, batch 15200, loss[loss=0.1219, simple_loss=0.1932, pruned_loss=0.02533, over 4938.00 frames.], tot_loss[loss=0.1458, simple_loss=0.2172, pruned_loss=0.03715, over 973259.99 frames.], batch size: 23, lr: 2.62e-04
2022-05-06 04:43:18,559 INFO [train.py:715] (4/8) Epoch 8, batch 15250, loss[loss=0.1491, simple_loss=0.2073, pruned_loss=0.04549, over 4749.00 frames.], tot_loss[loss=0.1455, simple_loss=0.217, pruned_loss=0.03697, over 972892.74 frames.], batch size: 16, lr: 2.62e-04
2022-05-06 04:43:58,532 INFO [train.py:715] (4/8) Epoch 8, batch 15300, loss[loss=0.1138, simple_loss=0.1865, pruned_loss=0.02053, over 4972.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2172, pruned_loss=0.03682, over 973121.38 frames.], batch size: 25, lr: 2.62e-04
2022-05-06 04:44:37,105 INFO [train.py:715] (4/8) Epoch 8, batch 15350, loss[loss=0.1357, simple_loss=0.2117, pruned_loss=0.02991, over 4813.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2168, pruned_loss=0.03638, over 972646.05 frames.], batch size: 27, lr: 2.62e-04
2022-05-06 04:45:17,012 INFO [train.py:715] (4/8) Epoch 8, batch 15400, loss[loss=0.1205, simple_loss=0.1947, pruned_loss=0.02314, over 4747.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2167, pruned_loss=0.03653, over 973657.02 frames.], batch size: 19, lr: 2.62e-04
2022-05-06 04:45:55,981 INFO [train.py:715] (4/8) Epoch 8, batch 15450, loss[loss=0.1837, simple_loss=0.2489, pruned_loss=0.05929, over 4905.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2164, pruned_loss=0.03636, over 973326.48 frames.], batch size: 17, lr: 2.62e-04
2022-05-06 04:46:34,942 INFO [train.py:715] (4/8) Epoch 8, batch 15500, loss[loss=0.1408, simple_loss=0.2238, pruned_loss=0.02894, over 4970.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2166, pruned_loss=0.0361, over 972958.93 frames.], batch size: 24, lr: 2.62e-04
2022-05-06 04:47:13,677 INFO [train.py:715] (4/8) Epoch 8, batch 15550, loss[loss=0.1131, simple_loss=0.199, pruned_loss=0.01358, over 4751.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2166, pruned_loss=0.03581, over 973127.95 frames.], batch size: 19, lr: 2.62e-04
2022-05-06 04:47:52,417 INFO [train.py:715] (4/8) Epoch 8, batch 15600, loss[loss=0.1581, simple_loss=0.2271, pruned_loss=0.0445, over 4780.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2171, pruned_loss=0.036, over 973094.30 frames.], batch size: 17, lr: 2.62e-04
2022-05-06 04:48:32,583 INFO [train.py:715] (4/8) Epoch 8, batch 15650, loss[loss=0.1502, simple_loss=0.2226, pruned_loss=0.03895, over 4769.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2167, pruned_loss=0.03596, over 973067.59 frames.], batch size: 14, lr: 2.62e-04
2022-05-06 04:49:11,088 INFO [train.py:715] (4/8) Epoch 8, batch 15700, loss[loss=0.1587, simple_loss=0.2233, pruned_loss=0.04706, over 4934.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2162, pruned_loss=0.03566, over 972795.33 frames.], batch size: 29, lr: 2.62e-04
2022-05-06 04:49:50,912 INFO [train.py:715] (4/8) Epoch 8, batch 15750, loss[loss=0.1362, simple_loss=0.2012, pruned_loss=0.03566, over 4771.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2162, pruned_loss=0.03608, over 971780.44 frames.], batch size: 14, lr: 2.62e-04
2022-05-06 04:50:30,389 INFO [train.py:715] (4/8) Epoch 8, batch 15800, loss[loss=0.1468, simple_loss=0.2072, pruned_loss=0.0432, over 4736.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2157, pruned_loss=0.03578, over 971916.16 frames.], batch size: 12, lr: 2.61e-04
2022-05-06 04:51:09,451 INFO [train.py:715] (4/8) Epoch 8, batch 15850, loss[loss=0.1523, simple_loss=0.2314, pruned_loss=0.03658, over 4744.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03545, over 972694.91 frames.], batch size: 16, lr: 2.61e-04
2022-05-06 04:51:48,553 INFO [train.py:715] (4/8) Epoch 8, batch 15900, loss[loss=0.1565, simple_loss=0.2232, pruned_loss=0.04497, over 4898.00 frames.], tot_loss[loss=0.142, simple_loss=0.2143, pruned_loss=0.03488, over 973094.10 frames.], batch size: 17, lr: 2.61e-04
2022-05-06 04:52:27,775 INFO [train.py:715] (4/8) Epoch 8, batch 15950, loss[loss=0.118, simple_loss=0.1897, pruned_loss=0.02321, over 4985.00 frames.], tot_loss[loss=0.1417, simple_loss=0.214, pruned_loss=0.03466, over 972645.44 frames.], batch size: 25, lr: 2.61e-04
2022-05-06 04:53:07,056 INFO [train.py:715] (4/8) Epoch 8, batch 16000, loss[loss=0.1538, simple_loss=0.2295, pruned_loss=0.03905, over 4697.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2153, pruned_loss=0.03555, over 972584.49 frames.], batch size: 15, lr: 2.61e-04
2022-05-06 04:53:45,654 INFO [train.py:715] (4/8) Epoch 8, batch 16050, loss[loss=0.1935, simple_loss=0.261, pruned_loss=0.06299, over 4790.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.0356, over 971639.19 frames.], batch size: 13, lr: 2.61e-04
2022-05-06 04:54:25,523 INFO [train.py:715] (4/8) Epoch 8, batch 16100, loss[loss=0.1767, simple_loss=0.2343, pruned_loss=0.0596, over 4829.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2154, pruned_loss=0.03559, over 971460.72 frames.], batch size: 15, lr: 2.61e-04
2022-05-06 04:55:04,003 INFO [train.py:715] (4/8) Epoch 8, batch 16150, loss[loss=0.1567, simple_loss=0.2335, pruned_loss=0.03994, over 4818.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03555, over 971313.58 frames.], batch size: 26, lr: 2.61e-04
2022-05-06 04:55:43,546 INFO [train.py:715] (4/8) Epoch 8, batch 16200, loss[loss=0.1711, simple_loss=0.2377, pruned_loss=0.05232, over 4944.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03547, over 971628.16 frames.], batch size: 21, lr: 2.61e-04
2022-05-06 04:56:21,929 INFO [train.py:715] (4/8) Epoch 8, batch 16250, loss[loss=0.1252, simple_loss=0.1989, pruned_loss=0.02573, over 4948.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2151, pruned_loss=0.03539, over 971406.95 frames.], batch size: 21, lr: 2.61e-04
2022-05-06 04:57:01,392 INFO [train.py:715] (4/8) Epoch 8, batch 16300, loss[loss=0.1759, simple_loss=0.232, pruned_loss=0.05993, over 4869.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2151, pruned_loss=0.0353, over 971824.46 frames.], batch size: 32, lr: 2.61e-04
2022-05-06 04:57:40,824 INFO [train.py:715] (4/8) Epoch 8, batch 16350, loss[loss=0.1606, simple_loss=0.2333, pruned_loss=0.0439, over 4839.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03546, over 971319.94 frames.], batch size: 13, lr: 2.61e-04
2022-05-06 04:58:19,597 INFO [train.py:715] (4/8) Epoch 8, batch 16400, loss[loss=0.1565, simple_loss=0.2291, pruned_loss=0.0419, over 4772.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.03513, over 970895.19 frames.], batch size: 14, lr: 2.61e-04
2022-05-06 04:58:58,710 INFO [train.py:715] (4/8) Epoch 8, batch 16450, loss[loss=0.145, simple_loss=0.2012, pruned_loss=0.04441, over 4852.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2159, pruned_loss=0.03537, over 971564.53 frames.], batch size: 30, lr: 2.61e-04
2022-05-06 04:59:37,557 INFO [train.py:715] (4/8) Epoch 8, batch 16500, loss[loss=0.1401, simple_loss=0.215, pruned_loss=0.03258, over 4809.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2153, pruned_loss=0.03512, over 971715.32 frames.], batch size: 13, lr: 2.61e-04
2022-05-06 05:00:17,261 INFO [train.py:715] (4/8) Epoch 8, batch 16550, loss[loss=0.1278, simple_loss=0.1998, pruned_loss=0.02793, over 4785.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2151, pruned_loss=0.03489, over 971961.73 frames.], batch size: 14, lr: 2.61e-04
2022-05-06 05:00:56,281 INFO [train.py:715] (4/8) Epoch 8, batch 16600, loss[loss=0.1418, simple_loss=0.2076, pruned_loss=0.038, over 4845.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.0351, over 972496.85 frames.], batch size: 13, lr: 2.61e-04
2022-05-06 05:01:35,314 INFO [train.py:715] (4/8) Epoch 8, batch 16650, loss[loss=0.1391, simple_loss=0.2187, pruned_loss=0.02973, over 4921.00 frames.], tot_loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.03574, over 972660.50 frames.], batch size: 23, lr: 2.61e-04
2022-05-06 05:02:14,552 INFO [train.py:715] (4/8) Epoch 8, batch 16700, loss[loss=0.1384, simple_loss=0.2249, pruned_loss=0.02596, over 4832.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2169, pruned_loss=0.03577, over 972429.03 frames.], batch size: 27, lr: 2.61e-04
2022-05-06 05:02:53,473 INFO [train.py:715] (4/8) Epoch 8, batch 16750, loss[loss=0.1468, simple_loss=0.2114, pruned_loss=0.04105, over 4908.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2165, pruned_loss=0.03589, over 972358.14 frames.], batch size: 17, lr: 2.61e-04
2022-05-06 05:03:33,069 INFO [train.py:715] (4/8) Epoch 8, batch 16800, loss[loss=0.1682, simple_loss=0.2417, pruned_loss=0.04739, over 4971.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03593, over 972990.77 frames.], batch size: 15, lr: 2.61e-04
2022-05-06 05:04:12,045 INFO [train.py:715] (4/8) Epoch 8, batch 16850, loss[loss=0.1431, simple_loss=0.2187, pruned_loss=0.03372, over 4770.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2165, pruned_loss=0.03564, over 973442.65 frames.], batch size: 17, lr: 2.61e-04
2022-05-06 05:04:51,955 INFO [train.py:715] (4/8) Epoch 8, batch 16900, loss[loss=0.1529, simple_loss=0.2315, pruned_loss=0.03715, over 4931.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2172, pruned_loss=0.03617, over 973959.02 frames.], batch size: 23, lr: 2.61e-04
2022-05-06 05:05:30,452 INFO [train.py:715] (4/8) Epoch 8, batch 16950, loss[loss=0.15, simple_loss=0.2281, pruned_loss=0.03601, over 4752.00 frames.], tot_loss[loss=0.1445, simple_loss=0.217, pruned_loss=0.03597, over 974290.91 frames.], batch size: 16, lr: 2.61e-04
2022-05-06 05:06:10,149 INFO [train.py:715] (4/8) Epoch 8, batch 17000, loss[loss=0.1657, simple_loss=0.2387, pruned_loss=0.0464, over 4750.00 frames.], tot_loss[loss=0.1444, simple_loss=0.217, pruned_loss=0.03592, over 973885.53 frames.], batch size: 16, lr: 2.61e-04
2022-05-06 05:06:49,663 INFO [train.py:715] (4/8) Epoch 8, batch 17050, loss[loss=0.1423, simple_loss=0.2191, pruned_loss=0.03276, over 4860.00 frames.], tot_loss[loss=0.145, simple_loss=0.2173, pruned_loss=0.03638, over 973409.81 frames.], batch size: 20, lr: 2.61e-04
2022-05-06 05:07:28,337 INFO [train.py:715] (4/8) Epoch 8, batch 17100, loss[loss=0.136, simple_loss=0.205, pruned_loss=0.03356, over 4859.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2167, pruned_loss=0.03618, over 973005.99 frames.], batch size: 39, lr: 2.61e-04
2022-05-06 05:08:08,033 INFO [train.py:715] (4/8) Epoch 8, batch 17150, loss[loss=0.1333, simple_loss=0.2094, pruned_loss=0.02857, over 4980.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2158, pruned_loss=0.0356, over 973190.20 frames.], batch size: 25, lr: 2.61e-04
2022-05-06 05:08:47,205 INFO [train.py:715] (4/8) Epoch 8, batch 17200, loss[loss=0.1381, simple_loss=0.2194, pruned_loss=0.02837, over 4921.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2156, pruned_loss=0.03558, over 973207.75 frames.], batch size: 39, lr: 2.61e-04
2022-05-06 05:09:26,326 INFO [train.py:715] (4/8) Epoch 8, batch 17250, loss[loss=0.1681, simple_loss=0.253, pruned_loss=0.04157, over 4798.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2155, pruned_loss=0.03534, over 973885.62 frames.], batch size: 21, lr: 2.61e-04
2022-05-06 05:10:04,660 INFO [train.py:715] (4/8) Epoch 8, batch 17300, loss[loss=0.1257, simple_loss=0.2017, pruned_loss=0.02488, over 4849.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.0359, over 974456.35 frames.], batch size: 13, lr: 2.61e-04
2022-05-06 05:10:44,495 INFO [train.py:715] (4/8) Epoch 8, batch 17350, loss[loss=0.139, simple_loss=0.2109, pruned_loss=0.03353, over 4818.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2161, pruned_loss=0.03556, over 973350.42 frames.], batch size: 25, lr: 2.61e-04
2022-05-06 05:11:23,594 INFO [train.py:715] (4/8) Epoch 8, batch 17400, loss[loss=0.1528, simple_loss=0.2333, pruned_loss=0.03615, over 4898.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2161, pruned_loss=0.03546, over 972941.30 frames.], batch size: 22, lr: 2.61e-04
2022-05-06 05:12:02,691 INFO [train.py:715] (4/8) Epoch 8, batch 17450, loss[loss=0.1554, simple_loss=0.2179, pruned_loss=0.04651, over 4993.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2163, pruned_loss=0.0358, over 972828.35 frames.], batch size: 14, lr: 2.61e-04
2022-05-06 05:12:42,122 INFO [train.py:715] (4/8) Epoch 8, batch 17500, loss[loss=0.1349, simple_loss=0.2025, pruned_loss=0.0337, over 4862.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.03529, over 973553.15 frames.], batch size: 32, lr: 2.61e-04
2022-05-06 05:13:23,165 INFO [train.py:715] (4/8) Epoch 8, batch 17550, loss[loss=0.1227, simple_loss=0.1939, pruned_loss=0.02572, over 4642.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.0351, over 973101.34 frames.], batch size: 13, lr: 2.61e-04
2022-05-06 05:14:02,976 INFO [train.py:715] (4/8) Epoch 8, batch 17600, loss[loss=0.1454, simple_loss=0.1994, pruned_loss=0.04565, over 4838.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.0355, over 972954.53 frames.], batch size: 13, lr: 2.61e-04
2022-05-06 05:14:41,720 INFO [train.py:715] (4/8) Epoch 8, batch 17650, loss[loss=0.1511, simple_loss=0.2217, pruned_loss=0.04028, over 4914.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.03517, over 973048.06 frames.], batch size: 17, lr: 2.61e-04
2022-05-06 05:15:22,836 INFO [train.py:715] (4/8) Epoch 8, batch 17700, loss[loss=0.1399, simple_loss=0.2205, pruned_loss=0.02969, over 4833.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2153, pruned_loss=0.03482, over 973075.60 frames.], batch size: 30, lr: 2.61e-04
2022-05-06 05:16:02,813 INFO [train.py:715] (4/8) Epoch 8, batch 17750, loss[loss=0.1249, simple_loss=0.2068, pruned_loss=0.02157, over 4830.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2152, pruned_loss=0.03531, over 973791.96 frames.], batch size: 26, lr: 2.61e-04
2022-05-06 05:16:43,282 INFO [train.py:715] (4/8) Epoch 8, batch 17800, loss[loss=0.119, simple_loss=0.1899, pruned_loss=0.0241, over 4808.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03532, over 972991.21 frames.], batch size: 13, lr: 2.61e-04
2022-05-06 05:17:23,941 INFO [train.py:715] (4/8) Epoch 8, batch 17850, loss[loss=0.1535, simple_loss=0.2313, pruned_loss=0.03787, over 4957.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2155, pruned_loss=0.03508, over 972647.40 frames.], batch size: 24, lr: 2.61e-04
2022-05-06 05:18:04,804 INFO [train.py:715] (4/8) Epoch 8, batch 17900, loss[loss=0.1295, simple_loss=0.2079, pruned_loss=0.02557, over 4773.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2153, pruned_loss=0.03483, over 973244.99 frames.], batch size: 14, lr: 2.61e-04
2022-05-06 05:18:46,215 INFO [train.py:715] (4/8) Epoch 8, batch 17950, loss[loss=0.1287, simple_loss=0.198, pruned_loss=0.02974, over 4992.00 frames.], tot_loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.03551, over 973284.84 frames.], batch size: 14, lr: 2.61e-04
2022-05-06 05:19:26,636 INFO [train.py:715] (4/8) Epoch 8, batch 18000, loss[loss=0.1291, simple_loss=0.2039, pruned_loss=0.02711, over 4906.00 frames.], tot_loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03544, over 973967.60 frames.], batch size: 17, lr: 2.61e-04
2022-05-06 05:19:26,637 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 05:19:36,399 INFO [train.py:742] (4/8) Epoch 8, validation: loss=0.1073, simple_loss=0.1919, pruned_loss=0.01138, over 914524.00 frames.
2022-05-06 05:20:17,001 INFO [train.py:715] (4/8) Epoch 8, batch 18050, loss[loss=0.1259, simple_loss=0.2103, pruned_loss=0.02079, over 4986.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2154, pruned_loss=0.03495, over 973027.20 frames.], batch size: 28, lr: 2.60e-04
2022-05-06 05:20:59,053 INFO [train.py:715] (4/8) Epoch 8, batch 18100, loss[loss=0.1385, simple_loss=0.1993, pruned_loss=0.03883, over 4745.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.03502, over 972490.00 frames.], batch size: 19, lr: 2.60e-04
2022-05-06 05:21:40,104 INFO [train.py:715] (4/8) Epoch 8, batch 18150, loss[loss=0.1738, simple_loss=0.2525, pruned_loss=0.04758, over 4923.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2162, pruned_loss=0.03568, over 972529.32 frames.], batch size: 17, lr: 2.60e-04
2022-05-06 05:22:21,017 INFO [train.py:715] (4/8) Epoch 8, batch 18200, loss[loss=0.1445, simple_loss=0.225, pruned_loss=0.03197, over 4867.00 frames.], tot_loss[loss=0.1445, simple_loss=0.217, pruned_loss=0.03603, over 972599.99 frames.], batch size: 22, lr: 2.60e-04
2022-05-06 05:23:02,796 INFO [train.py:715] (4/8) Epoch 8, batch 18250, loss[loss=0.1536, simple_loss=0.2271, pruned_loss=0.04005, over 4909.00 frames.], tot_loss[loss=0.145, simple_loss=0.2173, pruned_loss=0.03637, over 973443.55 frames.], batch size: 17, lr: 2.60e-04
2022-05-06 05:23:43,811 INFO [train.py:715] (4/8) Epoch 8, batch 18300, loss[loss=0.1515, simple_loss=0.2254, pruned_loss=0.0388, over 4781.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2178, pruned_loss=0.03667, over 973256.91 frames.], batch size: 18, lr: 2.60e-04
2022-05-06 05:24:25,286 INFO [train.py:715] (4/8) Epoch 8, batch 18350, loss[loss=0.1304, simple_loss=0.211, pruned_loss=0.02488, over 4896.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2172, pruned_loss=0.03628, over 973851.77 frames.], batch size: 19, lr: 2.60e-04
2022-05-06 05:25:06,139 INFO [train.py:715] (4/8) Epoch 8, batch 18400, loss[loss=0.1165, simple_loss=0.1848, pruned_loss=0.02404, over 4824.00 frames.], tot_loss[loss=0.144, simple_loss=0.2162, pruned_loss=0.03588, over 973598.44 frames.], batch size: 25, lr: 2.60e-04
2022-05-06 05:25:47,821 INFO [train.py:715] (4/8) Epoch 8, batch 18450, loss[loss=0.1306, simple_loss=0.198, pruned_loss=0.03158, over 4777.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2162, pruned_loss=0.03603, over 973181.24 frames.], batch size: 17, lr: 2.60e-04
2022-05-06 05:26:28,555 INFO [train.py:715] (4/8) Epoch 8, batch 18500, loss[loss=0.1379, simple_loss=0.2049, pruned_loss=0.03545, over 4895.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2162, pruned_loss=0.03525, over 972023.38 frames.], batch size: 17, lr: 2.60e-04
2022-05-06 05:27:08,959 INFO [train.py:715] (4/8) Epoch 8, batch 18550, loss[loss=0.1306, simple_loss=0.207, pruned_loss=0.02714, over 4805.00 frames.], tot_loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03538, over 972131.83 frames.], batch size: 14, lr: 2.60e-04
2022-05-06 05:27:50,208 INFO [train.py:715] (4/8) Epoch 8, batch 18600, loss[loss=0.1478, simple_loss=0.2163, pruned_loss=0.03963, over 4798.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.0351, over 972543.10 frames.], batch size: 14, lr: 2.60e-04
2022-05-06 05:28:30,416 INFO [train.py:715] (4/8) Epoch 8, batch 18650, loss[loss=0.1949, simple_loss=0.2535, pruned_loss=0.06812, over 4866.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2158, pruned_loss=0.03557, over 971699.60 frames.], batch size: 16, lr: 2.60e-04
2022-05-06 05:29:09,924 INFO [train.py:715] (4/8) Epoch 8, batch 18700, loss[loss=0.1613, simple_loss=0.2245, pruned_loss=0.04908, over 4947.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2163, pruned_loss=0.03622, over 971987.55 frames.], batch size: 29, lr: 2.60e-04
2022-05-06 05:29:49,894 INFO [train.py:715] (4/8) Epoch 8, batch 18750, loss[loss=0.1367, simple_loss=0.2185, pruned_loss=0.02747, over 4930.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.03549, over 972179.94 frames.], batch size: 23, lr: 2.60e-04
2022-05-06 05:30:30,988 INFO [train.py:715] (4/8) Epoch 8, batch 18800, loss[loss=0.1496, simple_loss=0.2234, pruned_loss=0.0379, over 4973.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2155, pruned_loss=0.03565, over 972669.88 frames.], batch size: 35, lr: 2.60e-04
2022-05-06 05:31:10,612 INFO [train.py:715] (4/8) Epoch 8, batch 18850, loss[loss=0.1461, simple_loss=0.2258, pruned_loss=0.03323, over 4816.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2166, pruned_loss=0.03587, over 972500.93 frames.], batch size: 26, lr: 2.60e-04
2022-05-06 05:31:50,017 INFO [train.py:715] (4/8) Epoch 8, batch 18900, loss[loss=0.1655, simple_loss=0.2461, pruned_loss=0.04248, over 4837.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2169, pruned_loss=0.03617, over 972507.57 frames.], batch size: 26, lr: 2.60e-04
2022-05-06 05:32:30,287 INFO [train.py:715] (4/8) Epoch 8, batch 18950, loss[loss=0.1411, simple_loss=0.2147, pruned_loss=0.03373, over 4879.00 frames.], tot_loss[loss=0.1445, simple_loss=0.217, pruned_loss=0.03598, over 973262.13 frames.], batch size: 16, lr: 2.60e-04
2022-05-06 05:33:10,175 INFO [train.py:715] (4/8) Epoch 8, batch 19000, loss[loss=0.1364, simple_loss=0.2136, pruned_loss=0.02957, over 4742.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2166, pruned_loss=0.03596, over 972367.19 frames.], batch size: 16, lr: 2.60e-04
2022-05-06 05:33:50,108 INFO [train.py:715] (4/8) Epoch 8, batch 19050, loss[loss=0.1539, simple_loss=0.2169, pruned_loss=0.04549, over 4794.00 frames.], tot_loss[loss=0.144, simple_loss=0.2161, pruned_loss=0.03595, over 973145.72 frames.], batch size: 21, lr: 2.60e-04
2022-05-06 05:34:31,415 INFO [train.py:715] (4/8) Epoch 8, batch 19100, loss[loss=0.1482, simple_loss=0.236, pruned_loss=0.03023, over 4809.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2154, pruned_loss=0.03585, over 972784.62 frames.], batch size: 15, lr: 2.60e-04
2022-05-06 05:35:13,332 INFO [train.py:715] (4/8) Epoch 8, batch 19150, loss[loss=0.1217, simple_loss=0.187, pruned_loss=0.02814, over 4909.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2151, pruned_loss=0.0357, over 972636.95 frames.], batch size: 18, lr: 2.60e-04
2022-05-06 05:35:54,990 INFO [train.py:715] (4/8) Epoch 8, batch 19200, loss[loss=0.1352, simple_loss=0.2142, pruned_loss=0.0281, over 4782.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2146, pruned_loss=0.03525, over 972048.14 frames.], batch size: 18, lr: 2.60e-04
2022-05-06 05:36:35,258 INFO [train.py:715] (4/8) Epoch 8, batch 19250, loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03482, over 4834.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.03459, over 971595.94 frames.], batch size: 15, lr: 2.60e-04
2022-05-06 05:37:17,465 INFO [train.py:715] (4/8) Epoch 8, batch 19300, loss[loss=0.09187, simple_loss=0.1634, pruned_loss=0.01015, over 4813.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2146, pruned_loss=0.03497, over 971926.01 frames.], batch size: 12, lr: 2.60e-04
2022-05-06 05:37:58,605 INFO [train.py:715] (4/8) Epoch 8, batch 19350, loss[loss=0.1442, simple_loss=0.2137, pruned_loss=0.03737, over 4992.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.03536, over 971841.65 frames.], batch size: 15, lr: 2.60e-04
2022-05-06 05:38:39,845 INFO [train.py:715] (4/8) Epoch 8, batch 19400, loss[loss=0.1626, simple_loss=0.2264, pruned_loss=0.04943, over 4769.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2147, pruned_loss=0.03511, over 971436.27 frames.], batch size: 18, lr: 2.60e-04
2022-05-06 05:39:21,785 INFO [train.py:715] (4/8) Epoch 8, batch 19450, loss[loss=0.1157, simple_loss=0.19, pruned_loss=0.02073, over 4802.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2148, pruned_loss=0.03492, over 970882.90 frames.], batch size: 18, lr: 2.60e-04
2022-05-06 05:40:03,269 INFO [train.py:715] (4/8) Epoch 8, batch 19500, loss[loss=0.1648, simple_loss=0.2447, pruned_loss=0.04242, over 4921.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2151, pruned_loss=0.03522, over 970517.33 frames.], batch size: 23, lr: 2.60e-04
2022-05-06 05:40:44,557 INFO [train.py:715] (4/8) Epoch 8, batch 19550, loss[loss=0.1324, simple_loss=0.1973, pruned_loss=0.03378, over 4983.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2148, pruned_loss=0.035, over 970698.30 frames.], batch size: 24, lr: 2.60e-04
2022-05-06 05:41:25,034 INFO [train.py:715] (4/8) Epoch 8, batch 19600, loss[loss=0.1404, simple_loss=0.2171, pruned_loss=0.03182, over 4825.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2148, pruned_loss=0.03497, over 970956.14 frames.], batch size: 27, lr: 2.60e-04
2022-05-06 05:42:06,539 INFO [train.py:715] (4/8) Epoch 8, batch 19650, loss[loss=0.134, simple_loss=0.2014, pruned_loss=0.03333, over 4749.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2146, pruned_loss=0.03506, over 971005.36 frames.], batch size: 16, lr: 2.60e-04
2022-05-06 05:42:47,227 INFO [train.py:715] (4/8) Epoch 8, batch 19700, loss[loss=0.1687, simple_loss=0.2433, pruned_loss=0.04706, over 4935.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.0349, over 970851.16 frames.], batch size: 39, lr: 2.60e-04
2022-05-06 05:43:28,186 INFO [train.py:715] (4/8) Epoch 8, batch 19750, loss[loss=0.1375, simple_loss=0.2135, pruned_loss=0.03075, over 4968.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03501, over 970955.63 frames.], batch size: 35, lr: 2.60e-04
2022-05-06 05:44:09,856 INFO [train.py:715] (4/8) Epoch 8, batch 19800, loss[loss=0.1351, simple_loss=0.2007, pruned_loss=0.03471, over 4797.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2147, pruned_loss=0.03496, over 971417.68 frames.], batch size: 12, lr: 2.60e-04
2022-05-06 05:44:50,900 INFO [train.py:715] (4/8) Epoch 8, batch 19850, loss[loss=0.1429, simple_loss=0.2161, pruned_loss=0.03483, over 4978.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.03477, over 970974.83 frames.], batch size: 14, lr: 2.60e-04
2022-05-06 05:45:31,215 INFO [train.py:715] (4/8) Epoch 8, batch 19900, loss[loss=0.1562, simple_loss=0.2259, pruned_loss=0.04324, over 4820.00 frames.], tot_loss[loss=0.142, simple_loss=0.2149, pruned_loss=0.03457, over 970457.15 frames.], batch size: 15, lr: 2.60e-04
2022-05-06 05:46:10,973 INFO [train.py:715] (4/8) Epoch 8, batch 19950, loss[loss=0.1409, simple_loss=0.2155, pruned_loss=0.0331, over 4829.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2161, pruned_loss=0.0352, over 970419.28 frames.], batch size: 30, lr: 2.60e-04
2022-05-06 05:46:51,587 INFO [train.py:715] (4/8) Epoch 8, batch 20000, loss[loss=0.1833, simple_loss=0.2531, pruned_loss=0.0568, over 4933.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2159, pruned_loss=0.03527, over 971674.64 frames.], batch size: 39, lr: 2.60e-04
2022-05-06 05:47:32,109 INFO [train.py:715] (4/8) Epoch 8, batch 20050, loss[loss=0.1494, simple_loss=0.219, pruned_loss=0.03989, over 4964.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2155, pruned_loss=0.03537, over 971261.20 frames.], batch size: 35, lr: 2.60e-04
2022-05-06 05:48:12,612 INFO [train.py:715] (4/8) Epoch 8, batch 20100, loss[loss=0.1382, simple_loss=0.2086, pruned_loss=0.03388, over 4884.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.03546, over 971933.34 frames.], batch size: 22, lr: 2.60e-04
2022-05-06 05:48:53,751 INFO [train.py:715] (4/8) Epoch 8, batch 20150, loss[loss=0.1279, simple_loss=0.1942, pruned_loss=0.03081, over 4874.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2154, pruned_loss=0.03509, over 971346.74 frames.], batch size: 16, lr: 2.60e-04
2022-05-06 05:49:34,570 INFO [train.py:715] (4/8) Epoch 8, batch 20200, loss[loss=0.1389, simple_loss=0.2211, pruned_loss=0.02834, over 4977.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2153, pruned_loss=0.03497, over 971871.66 frames.], batch size: 28, lr: 2.60e-04
2022-05-06 05:50:15,436 INFO [train.py:715] (4/8) Epoch 8, batch 20250, loss[loss=0.1456, simple_loss=0.2203, pruned_loss=0.0355, over 4876.00 frames.], tot_loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.03469, over 972510.42 frames.], batch size: 32, lr: 2.60e-04
2022-05-06 05:50:56,700 INFO [train.py:715] (4/8) Epoch 8, batch 20300, loss[loss=0.1361, simple_loss=0.2062, pruned_loss=0.03297, over 4836.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2149, pruned_loss=0.03444, over 971831.48 frames.], batch size: 15, lr: 2.60e-04
2022-05-06 05:51:37,702 INFO [train.py:715] (4/8) Epoch 8, batch 20350, loss[loss=0.1709, simple_loss=0.2453, pruned_loss=0.04828, over 4753.00 frames.], tot_loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.03468, over 971349.47 frames.], batch size: 19, lr: 2.59e-04
2022-05-06 05:52:18,252 INFO [train.py:715] (4/8) Epoch 8, batch 20400, loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03013, over 4789.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2161, pruned_loss=0.03523, over 971776.98 frames.], batch size: 12, lr: 2.59e-04
2022-05-06 05:52:58,509 INFO [train.py:715] (4/8) Epoch 8, batch 20450, loss[loss=0.1252, simple_loss=0.1895, pruned_loss=0.03045, over 4931.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2165, pruned_loss=0.03526, over 972242.79 frames.], batch size: 18, lr: 2.59e-04
2022-05-06 05:53:39,586 INFO [train.py:715] (4/8) Epoch 8, batch 20500, loss[loss=0.1325, simple_loss=0.2027, pruned_loss=0.03117, over 4955.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.03532, over 972047.63 frames.], batch size: 24, lr: 2.59e-04
2022-05-06 05:54:20,082 INFO [train.py:715] (4/8) Epoch 8, batch 20550, loss[loss=0.1552, simple_loss=0.2337, pruned_loss=0.03837, over 4828.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2159, pruned_loss=0.03548, over 971597.82 frames.], batch size: 15, lr: 2.59e-04
2022-05-06 05:55:00,449 INFO [train.py:715] (4/8) Epoch 8, batch 20600, loss[loss=0.1248, simple_loss=0.1959, pruned_loss=0.02685, over 4968.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.03505, over 971325.31 frames.], batch size: 24, lr: 2.59e-04
2022-05-06 05:55:41,397 INFO [train.py:715] (4/8) Epoch 8, batch 20650, loss[loss=0.1853, simple_loss=0.2558, pruned_loss=0.05742, over 4774.00 frames.], tot_loss[loss=0.144, simple_loss=0.2167, pruned_loss=0.03561, over 971858.99 frames.], batch size: 17, lr: 2.59e-04
2022-05-06 05:56:22,553 INFO [train.py:715] (4/8) Epoch 8, batch 20700, loss[loss=0.1395, simple_loss=0.2084, pruned_loss=0.03535, over 4795.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2155, pruned_loss=0.03538, over 971395.58 frames.], batch size: 14, lr: 2.59e-04
2022-05-06 05:57:02,752 INFO [train.py:715] (4/8) Epoch 8, batch 20750, loss[loss=0.1403, simple_loss=0.2086, pruned_loss=0.03602, over 4760.00 frames.], tot_loss[loss=0.144, simple_loss=0.2164, pruned_loss=0.03585, over 971164.15 frames.], batch size: 17, lr: 2.59e-04
2022-05-06 05:57:42,959 INFO [train.py:715] (4/8) Epoch 8, batch 20800, loss[loss=0.1393, simple_loss=0.1985, pruned_loss=0.04005, over 4979.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2155, pruned_loss=0.03581, over 971728.56 frames.], batch size: 15, lr: 2.59e-04
2022-05-06 05:58:24,022 INFO [train.py:715] (4/8) Epoch 8, batch 20850, loss[loss=0.159, simple_loss=0.2192, pruned_loss=0.04933, over 4862.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2155, pruned_loss=0.03586, over 971867.70 frames.], batch size: 32, lr: 2.59e-04
2022-05-06 05:59:04,453 INFO [train.py:715] (4/8) Epoch 8, batch 20900, loss[loss=0.1439, simple_loss=0.2122, pruned_loss=0.03782, over 4846.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2156, pruned_loss=0.03601, over 971791.67 frames.], batch size: 13, lr: 2.59e-04
2022-05-06 05:59:43,023 INFO [train.py:715] (4/8) Epoch 8, batch 20950, loss[loss=0.1059, simple_loss=0.1812, pruned_loss=0.01533, over 4821.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2148, pruned_loss=0.03551, over 972155.60 frames.], batch size: 25, lr: 2.59e-04
2022-05-06 06:00:22,704 INFO [train.py:715] (4/8) Epoch 8, batch 21000, loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02978, over 4781.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2146, pruned_loss=0.03542, over 971966.41 frames.], batch size: 18, lr: 2.59e-04
2022-05-06 06:00:22,705 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 06:00:32,253 INFO [train.py:742] (4/8) Epoch 8, validation: loss=0.1072, simple_loss=0.1919, pruned_loss=0.01129, over 914524.00 frames.
2022-05-06 06:01:12,648 INFO [train.py:715] (4/8) Epoch 8, batch 21050, loss[loss=0.1731, simple_loss=0.242, pruned_loss=0.05205, over 4801.00 frames.], tot_loss[loss=0.143, simple_loss=0.2147, pruned_loss=0.03567, over 972416.75 frames.], batch size: 17, lr: 2.59e-04
2022-05-06 06:01:52,991 INFO [train.py:715] (4/8) Epoch 8, batch 21100, loss[loss=0.1327, simple_loss=0.2091, pruned_loss=0.02816, over 4696.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2159, pruned_loss=0.03619, over 972130.88 frames.], batch size: 15, lr: 2.59e-04
2022-05-06 06:02:31,461 INFO [train.py:715] (4/8) Epoch 8, batch 21150, loss[loss=0.1521, simple_loss=0.2228, pruned_loss=0.04071, over 4985.00 frames.], tot_loss[loss=0.1442, simple_loss=0.216, pruned_loss=0.0362, over 972218.63 frames.], batch size: 28, lr: 2.59e-04
2022-05-06 06:03:10,261 INFO [train.py:715] (4/8) Epoch 8, batch 21200, loss[loss=0.1597, simple_loss=0.2366, pruned_loss=0.04139, over 4821.00 frames.], tot_loss[loss=0.1446, simple_loss=0.2164, pruned_loss=0.03641, over 971959.58 frames.], batch size: 26, lr: 2.59e-04
2022-05-06 06:03:49,966 INFO [train.py:715] (4/8) Epoch 8, batch 21250, loss[loss=0.1414, simple_loss=0.2181, pruned_loss=0.03233, over 4821.00 frames.], tot_loss[loss=0.1442, simple_loss=0.216, pruned_loss=0.03618, over 971420.83 frames.], batch size: 26, lr: 2.59e-04
2022-05-06 06:04:29,228 INFO [train.py:715] (4/8) Epoch 8, batch 21300, loss[loss=0.1428, simple_loss=0.2245, pruned_loss=0.03055, over 4906.00 frames.], tot_loss[loss=0.1453, simple_loss=0.2173, pruned_loss=0.03663, over 972069.40 frames.], batch size: 22, lr: 2.59e-04
2022-05-06 06:05:07,762 INFO [train.py:715] (4/8) Epoch 8, batch 21350, loss[loss=0.1157, simple_loss=0.1842, pruned_loss=0.02357, over 4943.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2156, pruned_loss=0.03591, over 972496.69 frames.], batch size: 23, lr: 2.59e-04
2022-05-06 06:05:47,406 INFO [train.py:715] (4/8) Epoch 8, batch 21400, loss[loss=0.1238, simple_loss=0.1906, pruned_loss=0.02845, over 4782.00 frames.], tot_loss[loss=0.144, simple_loss=0.2155, pruned_loss=0.03623, over 972324.03 frames.], batch size: 18, lr: 2.59e-04
2022-05-06 06:06:27,495 INFO [train.py:715] (4/8) Epoch 8, batch 21450, loss[loss=0.1581, simple_loss=0.2348, pruned_loss=0.04071, over 4924.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2148, pruned_loss=0.03578, over 973405.56 frames.], batch size: 18, lr: 2.59e-04
2022-05-06 06:07:06,788 INFO [train.py:715] (4/8) Epoch 8, batch 21500, loss[loss=0.1122, simple_loss=0.1881, pruned_loss=0.01815, over 4916.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2149, pruned_loss=0.03602, over 973878.66 frames.], batch size: 19, lr: 2.59e-04
2022-05-06 06:07:45,791 INFO [train.py:715] (4/8) Epoch 8, batch 21550, loss[loss=0.1332, simple_loss=0.2054, pruned_loss=0.03052, over 4949.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2157, pruned_loss=0.03649, over 972997.80 frames.], batch size: 21, lr: 2.59e-04
2022-05-06 06:08:25,814 INFO [train.py:715] (4/8) Epoch 8, batch 21600, loss[loss=0.1193, simple_loss=0.2049, pruned_loss=0.01683, over 4916.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2153, pruned_loss=0.03594, over 972512.79 frames.], batch size: 17, lr: 2.59e-04
2022-05-06 06:09:04,796 INFO [train.py:715] (4/8) Epoch 8, batch 21650, loss[loss=0.1511, simple_loss=0.2259, pruned_loss=0.03813, over 4890.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03615, over 972602.66 frames.], batch size: 22, lr: 2.59e-04
2022-05-06 06:09:43,493 INFO [train.py:715] (4/8) Epoch 8, batch 21700, loss[loss=0.1225, simple_loss=0.1931, pruned_loss=0.02595, over 4769.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2169, pruned_loss=0.03634, over 972398.63 frames.], batch size: 18, lr: 2.59e-04
2022-05-06 06:10:23,860 INFO [train.py:715] (4/8) Epoch 8, batch 21750, loss[loss=0.1644, simple_loss=0.2407, pruned_loss=0.04409, over 4937.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2174, pruned_loss=0.03694, over 972617.35 frames.], batch size: 29, lr: 2.59e-04
2022-05-06 06:11:03,698 INFO [train.py:715] (4/8) Epoch 8, batch 21800, loss[loss=0.1392, simple_loss=0.2127, pruned_loss=0.03286, over 4822.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2161, pruned_loss=0.03638, over 972716.75 frames.], batch size: 27, lr: 2.59e-04
2022-05-06 06:11:42,812 INFO [train.py:715] (4/8) Epoch 8, batch 21850, loss[loss=0.1547, simple_loss=0.2295, pruned_loss=0.03993, over 4926.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2161, pruned_loss=0.03645, over 972856.09 frames.], batch size: 17, lr: 2.59e-04
2022-05-06 06:12:21,178 INFO [train.py:715] (4/8) Epoch 8, batch 21900, loss[loss=0.1344, simple_loss=0.1995, pruned_loss=0.03465, over 4786.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2155, pruned_loss=0.03596, over 972894.48 frames.], batch size: 17, lr: 2.59e-04
2022-05-06 06:13:00,616 INFO [train.py:715] (4/8) Epoch 8, batch 21950, loss[loss=0.1583, simple_loss=0.2287, pruned_loss=0.04395, over 4754.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2155, pruned_loss=0.03599, over 972694.89 frames.], batch size: 16, lr: 2.59e-04
2022-05-06 06:13:39,699 INFO [train.py:715] (4/8) Epoch 8, batch 22000, loss[loss=0.1429, simple_loss=0.2116, pruned_loss=0.03709, over 4821.00 frames.], tot_loss[loss=0.1432, simple_loss=0.215, pruned_loss=0.03574, over 972737.18 frames.], batch size: 13, lr: 2.59e-04
2022-05-06 06:14:18,327 INFO [train.py:715] (4/8) Epoch 8, batch 22050, loss[loss=0.1485, simple_loss=0.2152, pruned_loss=0.04087, over 4900.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2151, pruned_loss=0.03579, over 972875.55 frames.], batch size: 39, lr: 2.59e-04
2022-05-06 06:14:58,045 INFO [train.py:715] (4/8) Epoch 8, batch 22100, loss[loss=0.1408, simple_loss=0.2159, pruned_loss=0.03281, over 4879.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2146, pruned_loss=0.03522, over 972019.63 frames.], batch size: 19, lr: 2.59e-04
2022-05-06 06:15:37,422 INFO [train.py:715] (4/8) Epoch 8, batch 22150, loss[loss=0.1496, simple_loss=0.2311, pruned_loss=0.03404, over 4974.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2154, pruned_loss=0.03561, over 972588.03 frames.], batch size: 15, lr: 2.59e-04
2022-05-06 06:16:16,518 INFO [train.py:715] (4/8) Epoch 8, batch 22200, loss[loss=0.137, simple_loss=0.2183, pruned_loss=0.02785, over 4986.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2161, pruned_loss=0.03559, over 972731.45 frames.], batch size: 25, lr: 2.59e-04
2022-05-06 06:16:55,349 INFO [train.py:715] (4/8) Epoch 8, batch 22250, loss[loss=0.1674, simple_loss=0.2389, pruned_loss=0.04796, over 4827.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03574, over 973174.41 frames.], batch size: 15, lr: 2.59e-04
2022-05-06 06:17:34,566 INFO [train.py:715] (4/8) Epoch 8, batch 22300, loss[loss=0.1305, simple_loss=0.208, pruned_loss=0.02652, over 4788.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2169, pruned_loss=0.03583, over 973726.12 frames.], batch size: 21, lr: 2.59e-04
2022-05-06 06:18:13,308 INFO [train.py:715] (4/8) Epoch 8, batch 22350, loss[loss=0.1452, simple_loss=0.2184, pruned_loss=0.03599, over 4966.00 frames.], tot_loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.03547, over 973993.06 frames.], batch size: 24, lr: 2.59e-04
2022-05-06 06:18:51,905 INFO [train.py:715] (4/8) Epoch 8, batch 22400, loss[loss=0.1366, simple_loss=0.2198, pruned_loss=0.02667, over 4858.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2163, pruned_loss=0.03566, over 973164.57 frames.], batch size: 34, lr: 2.59e-04
2022-05-06 06:19:31,235 INFO [train.py:715] (4/8) Epoch 8, batch 22450, loss[loss=0.1545, simple_loss=0.2198, pruned_loss=0.04457, over 4963.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.03551, over 973558.98 frames.], batch size: 24, lr: 2.59e-04
2022-05-06 06:20:10,737 INFO [train.py:715] (4/8) Epoch 8, batch 22500, loss[loss=0.1208, simple_loss=0.1952, pruned_loss=0.02323, over 4841.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2147, pruned_loss=0.03517, over 973357.05 frames.], batch size: 30, lr: 2.59e-04
2022-05-06 06:20:49,332 INFO [train.py:715] (4/8) Epoch 8, batch 22550, loss[loss=0.1192, simple_loss=0.1996, pruned_loss=0.01936, over 4707.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03502, over 973492.62 frames.], batch size: 15, lr: 2.59e-04
2022-05-06 06:21:28,254 INFO [train.py:715] (4/8) Epoch 8, batch 22600, loss[loss=0.1693, simple_loss=0.2487, pruned_loss=0.04501, over 4907.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2152, pruned_loss=0.0353, over 973600.71 frames.], batch size: 39, lr: 2.59e-04
2022-05-06 06:22:07,735 INFO [train.py:715] (4/8) Epoch 8, batch 22650, loss[loss=0.1357, simple_loss=0.2152, pruned_loss=0.02815, over 4977.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03498, over 973321.23 frames.], batch size: 14, lr: 2.58e-04
2022-05-06 06:22:46,457 INFO [train.py:715] (4/8) Epoch 8, batch 22700, loss[loss=0.1305, simple_loss=0.2087, pruned_loss=0.02614, over 4988.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2158, pruned_loss=0.03555, over 973347.13 frames.], batch size: 25, lr: 2.58e-04
2022-05-06 06:23:24,776 INFO [train.py:715] (4/8) Epoch 8, batch 22750, loss[loss=0.1239, simple_loss=0.1953, pruned_loss=0.02628, over 4929.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2168, pruned_loss=0.03573, over 973377.72 frames.], batch size: 18, lr: 2.58e-04
2022-05-06 06:24:04,594 INFO [train.py:715] (4/8) Epoch 8, batch 22800, loss[loss=0.14, simple_loss=0.2159, pruned_loss=0.03202, over 4974.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2172, pruned_loss=0.03589, over 973834.49 frames.], batch size: 24, lr: 2.58e-04
2022-05-06 06:24:43,767 INFO [train.py:715] (4/8) Epoch 8, batch 22850, loss[loss=0.1411, simple_loss=0.2151, pruned_loss=0.03361, over 4975.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2174, pruned_loss=0.03653, over 973801.57 frames.], batch size: 14, lr: 2.58e-04
2022-05-06 06:25:22,842 INFO [train.py:715] (4/8) Epoch 8, batch 22900, loss[loss=0.1159, simple_loss=0.1928, pruned_loss=0.01954, over 4775.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.03588, over 972792.02 frames.], batch size: 17, lr: 2.58e-04
2022-05-06 06:26:01,956 INFO [train.py:715] (4/8) Epoch 8, batch 22950, loss[loss=0.1717, simple_loss=0.2452, pruned_loss=0.04914, over 4884.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2169, pruned_loss=0.03632, over 973380.43 frames.], batch size: 22, lr: 2.58e-04
2022-05-06 06:26:41,733 INFO [train.py:715] (4/8) Epoch 8, batch 23000, loss[loss=0.1431, simple_loss=0.2084, pruned_loss=0.03897, over 4882.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2166, pruned_loss=0.03619, over 973117.05 frames.], batch size: 22, lr: 2.58e-04
2022-05-06 06:27:20,528 INFO [train.py:715] (4/8) Epoch 8, batch 23050, loss[loss=0.1382, simple_loss=0.2191, pruned_loss=0.0286, over 4858.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03589, over 972327.11 frames.], batch size: 32, lr: 2.58e-04
2022-05-06 06:27:59,220 INFO [train.py:715] (4/8) Epoch 8, batch 23100, loss[loss=0.1372, simple_loss=0.2161, pruned_loss=0.02918, over 4935.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2154, pruned_loss=0.03525, over 972285.84 frames.], batch size: 21, lr: 2.58e-04
2022-05-06 06:28:39,375 INFO [train.py:715] (4/8) Epoch 8, batch 23150, loss[loss=0.1365, simple_loss=0.2162, pruned_loss=0.02843, over 4975.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.03531, over 972121.13 frames.], batch size: 28, lr: 2.58e-04
2022-05-06 06:29:18,754 INFO [train.py:715] (4/8) Epoch 8, batch 23200, loss[loss=0.1487, simple_loss=0.2205, pruned_loss=0.03849, over 4747.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03554, over 972739.09 frames.], batch size: 19, lr: 2.58e-04
2022-05-06 06:29:57,396 INFO [train.py:715] (4/8) Epoch 8, batch 23250, loss[loss=0.1324, simple_loss=0.2045, pruned_loss=0.03013, over 4826.00 frames.], tot_loss[loss=0.144, simple_loss=0.2162, pruned_loss=0.03592, over 972664.53 frames.], batch size: 26, lr: 2.58e-04
2022-05-06 06:30:36,512 INFO [train.py:715] (4/8) Epoch 8, batch 23300, loss[loss=0.154, simple_loss=0.2243, pruned_loss=0.04185, over 4766.00 frames.], tot_loss[loss=0.145, simple_loss=0.2171, pruned_loss=0.03645, over 972030.79 frames.], batch size: 19, lr: 2.58e-04
2022-05-06 06:31:16,260 INFO [train.py:715] (4/8) Epoch 8, batch 23350, loss[loss=0.1396, simple_loss=0.2089, pruned_loss=0.03521, over 4794.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.03608, over 972136.08 frames.], batch size: 12, lr: 2.58e-04
2022-05-06 06:31:55,024 INFO [train.py:715] (4/8) Epoch 8, batch 23400, loss[loss=0.1232, simple_loss=0.1969, pruned_loss=0.02475, over 4940.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2163, pruned_loss=0.03613, over 971867.06 frames.], batch size: 23, lr: 2.58e-04
2022-05-06 06:32:33,889 INFO [train.py:715] (4/8) Epoch 8, batch 23450, loss[loss=0.1503, simple_loss=0.2161, pruned_loss=0.04228, over 4866.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2165, pruned_loss=0.03609, over 972208.34 frames.], batch size: 16, lr: 2.58e-04
2022-05-06 06:33:13,364 INFO [train.py:715] (4/8) Epoch 8, batch 23500, loss[loss=0.1711, simple_loss=0.2346, pruned_loss=0.05381, over 4961.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2164, pruned_loss=0.03605, over 972403.66 frames.], batch size: 35, lr: 2.58e-04
2022-05-06 06:33:52,530 INFO [train.py:715] (4/8) Epoch 8, batch 23550, loss[loss=0.1571, simple_loss=0.223, pruned_loss=0.04561, over 4957.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2171, pruned_loss=0.03682, over 971534.28 frames.], batch size: 21, lr: 2.58e-04
2022-05-06 06:34:31,318 INFO [train.py:715] (4/8) Epoch 8, batch 23600, loss[loss=0.1634, simple_loss=0.232, pruned_loss=0.04738, over 4828.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2164, pruned_loss=0.03627, over 971673.82 frames.], batch size: 25, lr: 2.58e-04
2022-05-06 06:35:10,240 INFO [train.py:715] (4/8) Epoch 8, batch 23650, loss[loss=0.1608, simple_loss=0.2335, pruned_loss=0.0441, over 4786.00 frames.], tot_loss[loss=0.1452, simple_loss=0.2173, pruned_loss=0.03651, over 971468.37 frames.], batch size: 17, lr: 2.58e-04
2022-05-06 06:35:50,046 INFO [train.py:715] (4/8) Epoch 8, batch 23700, loss[loss=0.1549, simple_loss=0.2368, pruned_loss=0.03645, over 4972.00 frames.], tot_loss[loss=0.1454, simple_loss=0.2173, pruned_loss=0.03673, over 971869.73 frames.], batch size: 39, lr: 2.58e-04
2022-05-06 06:36:28,663 INFO [train.py:715] (4/8) Epoch 8, batch 23750, loss[loss=0.1324, simple_loss=0.2028, pruned_loss=0.03104, over 4848.00 frames.], tot_loss[loss=0.1449, simple_loss=0.2169, pruned_loss=0.03646, over 971725.20 frames.], batch size: 20, lr: 2.58e-04
2022-05-06 06:37:07,512 INFO [train.py:715] (4/8) Epoch 8, batch 23800, loss[loss=0.1738, simple_loss=0.2426, pruned_loss=0.05254, over 4780.00 frames.], tot_loss[loss=0.145, simple_loss=0.2171, pruned_loss=0.03649, over 970940.22 frames.], batch size: 17, lr: 2.58e-04
2022-05-06 06:37:46,981 INFO [train.py:715] (4/8) Epoch 8, batch 23850, loss[loss=0.1477, simple_loss=0.233, pruned_loss=0.03123, over 4860.00 frames.], tot_loss[loss=0.1456, simple_loss=0.2176, pruned_loss=0.03676, over 970004.97 frames.], batch size: 32, lr: 2.58e-04
2022-05-06 06:38:26,640 INFO [train.py:715] (4/8) Epoch 8, batch 23900, loss[loss=0.1328, simple_loss=0.2136, pruned_loss=0.02596, over 4957.00 frames.], tot_loss[loss=0.1451, simple_loss=0.2172, pruned_loss=0.03657, over 970389.79 frames.], batch size: 24, lr: 2.58e-04
2022-05-06 06:39:05,504 INFO [train.py:715] (4/8) Epoch 8, batch 23950, loss[loss=0.1166, simple_loss=0.1856, pruned_loss=0.02384, over 4643.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2165, pruned_loss=0.03612, over 969968.11 frames.], batch size: 13, lr: 2.58e-04
2022-05-06 06:39:44,886 INFO [train.py:715] (4/8) Epoch 8, batch 24000, loss[loss=0.1578, simple_loss=0.2241, pruned_loss=0.04576, over 4825.00 frames.], tot_loss[loss=0.1446, simple_loss=0.217, pruned_loss=0.03611, over 969999.78 frames.], batch size: 25, lr: 2.58e-04
2022-05-06 06:39:44,887 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 06:39:54,529 INFO [train.py:742] (4/8) Epoch 8, validation: loss=0.1075, simple_loss=0.192, pruned_loss=0.01146, over 914524.00 frames.
2022-05-06 06:40:33,719 INFO [train.py:715] (4/8) Epoch 8, batch 24050, loss[loss=0.1606, simple_loss=0.2199, pruned_loss=0.05061, over 4744.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2166, pruned_loss=0.03598, over 969908.13 frames.], batch size: 16, lr: 2.58e-04
2022-05-06 06:41:13,151 INFO [train.py:715] (4/8) Epoch 8, batch 24100, loss[loss=0.121, simple_loss=0.189, pruned_loss=0.02647, over 4836.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2167, pruned_loss=0.03622, over 971361.97 frames.], batch size: 13, lr: 2.58e-04
2022-05-06 06:41:52,113 INFO [train.py:715] (4/8) Epoch 8, batch 24150, loss[loss=0.1422, simple_loss=0.214, pruned_loss=0.03521, over 4756.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.03549, over 971581.65 frames.], batch size: 19, lr: 2.58e-04
2022-05-06 06:42:31,050 INFO [train.py:715] (4/8) Epoch 8, batch 24200, loss[loss=0.138, simple_loss=0.2143, pruned_loss=0.03087, over 4919.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.03518, over 972291.82 frames.], batch size: 29, lr: 2.58e-04
2022-05-06 06:43:11,239 INFO [train.py:715] (4/8) Epoch 8, batch 24250, loss[loss=0.1416, simple_loss=0.2108, pruned_loss=0.03622, over 4943.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03498, over 972925.84 frames.], batch size: 29, lr: 2.58e-04
2022-05-06 06:43:50,603 INFO [train.py:715] (4/8) Epoch 8, batch 24300, loss[loss=0.1277, simple_loss=0.2111, pruned_loss=0.02209, over 4827.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2147, pruned_loss=0.03444, over 972456.75 frames.], batch size: 27, lr: 2.58e-04
2022-05-06 06:44:29,316 INFO [train.py:715] (4/8) Epoch 8, batch 24350, loss[loss=0.1502, simple_loss=0.2401, pruned_loss=0.03011, over 4753.00 frames.], tot_loss[loss=0.142, simple_loss=0.2149, pruned_loss=0.03455, over 972644.42 frames.], batch size: 19, lr: 2.58e-04
2022-05-06 06:45:08,117 INFO [train.py:715] (4/8) Epoch 8, batch 24400, loss[loss=0.1179, simple_loss=0.1831, pruned_loss=0.02635, over 4773.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.03442, over 971387.13 frames.], batch size: 17, lr: 2.58e-04
2022-05-06 06:45:47,152 INFO [train.py:715] (4/8) Epoch 8, batch 24450, loss[loss=0.1561, simple_loss=0.2285, pruned_loss=0.04186, over 4793.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2136, pruned_loss=0.03439, over 971352.84 frames.], batch size: 14, lr: 2.58e-04
2022-05-06 06:46:26,137 INFO [train.py:715] (4/8) Epoch 8, batch 24500, loss[loss=0.156, simple_loss=0.2225, pruned_loss=0.04474, over 4902.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.03454, over 971547.89 frames.], batch size: 18, lr: 2.58e-04
2022-05-06 06:47:04,985 INFO [train.py:715] (4/8) Epoch 8, batch 24550, loss[loss=0.1813, simple_loss=0.2502, pruned_loss=0.05617, over 4697.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03476, over 970784.91 frames.], batch size: 15, lr: 2.58e-04
2022-05-06 06:47:44,927 INFO [train.py:715] (4/8) Epoch 8, batch 24600, loss[loss=0.1445, simple_loss=0.2138, pruned_loss=0.03761, over 4902.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03544, over 971340.85 frames.], batch size: 17, lr: 2.58e-04
2022-05-06 06:48:24,235 INFO [train.py:715] (4/8) Epoch 8, batch 24650, loss[loss=0.1486, simple_loss=0.2219, pruned_loss=0.03766, over 4920.00 frames.], tot_loss[loss=0.1424, simple_loss=0.215, pruned_loss=0.03491, over 972228.41 frames.], batch size: 17, lr: 2.58e-04
2022-05-06 06:49:02,874 INFO [train.py:715] (4/8) Epoch 8, batch 24700, loss[loss=0.1196, simple_loss=0.1933, pruned_loss=0.023, over 4823.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2154, pruned_loss=0.03496, over 972295.73 frames.], batch size: 13, lr: 2.58e-04
2022-05-06 06:49:42,048 INFO [train.py:715] (4/8) Epoch 8, batch 24750, loss[loss=0.1259, simple_loss=0.1939, pruned_loss=0.02892, over 4844.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2154, pruned_loss=0.03519, over 971936.39 frames.], batch size: 12, lr: 2.58e-04
2022-05-06 06:50:21,621 INFO [train.py:715] (4/8) Epoch 8, batch 24800, loss[loss=0.1305, simple_loss=0.193, pruned_loss=0.03405, over 4827.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2152, pruned_loss=0.0353, over 971755.73 frames.], batch size: 13, lr: 2.58e-04
2022-05-06 06:51:00,472 INFO [train.py:715] (4/8) Epoch 8, batch 24850, loss[loss=0.1317, simple_loss=0.2072, pruned_loss=0.02808, over 4959.00 frames.], tot_loss[loss=0.143, simple_loss=0.2158, pruned_loss=0.0351, over 971835.41 frames.], batch size: 21, lr: 2.58e-04
2022-05-06 06:51:39,141 INFO [train.py:715] (4/8) Epoch 8, batch 24900, loss[loss=0.112, simple_loss=0.1902, pruned_loss=0.01691, over 4758.00 frames.], tot_loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.03466, over 972237.95 frames.], batch size: 19, lr: 2.58e-04
2022-05-06 06:52:19,143 INFO [train.py:715] (4/8) Epoch 8, batch 24950, loss[loss=0.1644, simple_loss=0.2211, pruned_loss=0.05382, over 4828.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03527, over 972008.25 frames.], batch size: 26, lr: 2.58e-04
2022-05-06 06:52:58,630 INFO [train.py:715] (4/8) Epoch 8, batch 25000, loss[loss=0.14, simple_loss=0.2089, pruned_loss=0.03557, over 4762.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2156, pruned_loss=0.03539, over 971787.84 frames.], batch size: 18, lr: 2.57e-04
2022-05-06 06:53:37,562 INFO [train.py:715] (4/8) Epoch 8, batch 25050, loss[loss=0.1087, simple_loss=0.1853, pruned_loss=0.01609, over 4919.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2151, pruned_loss=0.03495, over 971634.09 frames.], batch size: 23, lr: 2.57e-04
2022-05-06 06:54:16,390 INFO [train.py:715] (4/8) Epoch 8, batch 25100, loss[loss=0.1532, simple_loss=0.2148, pruned_loss=0.04581, over 4764.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03511, over 971952.82 frames.], batch size: 19, lr: 2.57e-04
2022-05-06 06:54:55,808 INFO [train.py:715] (4/8) Epoch 8, batch 25150, loss[loss=0.1498, simple_loss=0.222, pruned_loss=0.03875, over 4972.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03568, over 972690.50 frames.], batch size: 35, lr: 2.57e-04
2022-05-06 06:55:34,832 INFO [train.py:715] (4/8) Epoch 8, batch 25200, loss[loss=0.1539, simple_loss=0.2188, pruned_loss=0.04453, over 4894.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2162, pruned_loss=0.03598, over 972352.13 frames.], batch size: 22, lr: 2.57e-04
2022-05-06 06:56:13,820 INFO [train.py:715] (4/8) Epoch 8, batch 25250, loss[loss=0.1357, simple_loss=0.2088, pruned_loss=0.03131, over 4925.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2172, pruned_loss=0.03612, over 971797.35 frames.], batch size: 18, lr: 2.57e-04
2022-05-06 06:56:53,389 INFO [train.py:715] (4/8) Epoch 8, batch 25300, loss[loss=0.1282, simple_loss=0.2052, pruned_loss=0.02564, over 4687.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2158, pruned_loss=0.03537, over 971255.62 frames.], batch size: 15, lr: 2.57e-04
2022-05-06 06:57:32,352 INFO [train.py:715] (4/8) Epoch 8, batch 25350, loss[loss=0.1605, simple_loss=0.2339, pruned_loss=0.04357, over 4884.00 frames.], tot_loss[loss=0.143, simple_loss=0.2158, pruned_loss=0.03513, over 971553.03 frames.], batch size: 38, lr: 2.57e-04
2022-05-06 06:58:11,169 INFO [train.py:715] (4/8) Epoch 8, batch 25400, loss[loss=0.1532, simple_loss=0.2307, pruned_loss=0.03789, over 4775.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2155, pruned_loss=0.0347, over 971764.89 frames.], batch size: 17, lr: 2.57e-04
2022-05-06 06:58:50,228 INFO [train.py:715] (4/8) Epoch 8, batch 25450, loss[loss=0.1693, simple_loss=0.25, pruned_loss=0.04435, over 4773.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2162, pruned_loss=0.03536, over 971123.78 frames.], batch size: 14, lr: 2.57e-04
2022-05-06 06:59:30,373 INFO [train.py:715] (4/8) Epoch 8, batch 25500, loss[loss=0.1577, simple_loss=0.2297, pruned_loss=0.04281, over 4918.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2172, pruned_loss=0.03622, over 971348.75 frames.], batch size: 17, lr: 2.57e-04
2022-05-06 07:00:12,378 INFO [train.py:715] (4/8) Epoch 8, batch 25550, loss[loss=0.1367, simple_loss=0.2049, pruned_loss=0.03421, over 4952.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2166, pruned_loss=0.03605, over 971555.35 frames.], batch size: 24, lr: 2.57e-04
2022-05-06 07:00:51,653 INFO [train.py:715] (4/8) Epoch 8, batch 25600, loss[loss=0.1609, simple_loss=0.232, pruned_loss=0.04493, over 4881.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2161, pruned_loss=0.03566, over 972009.95 frames.], batch size: 16, lr: 2.57e-04
2022-05-06 07:01:30,733 INFO [train.py:715] (4/8) Epoch 8, batch 25650, loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02942, over 4757.00 frames.], tot_loss[loss=0.145, simple_loss=0.2172, pruned_loss=0.03639, over 972311.78 frames.], batch size: 19, lr: 2.57e-04
2022-05-06 07:02:09,696 INFO [train.py:715] (4/8) Epoch 8, batch 25700, loss[loss=0.1432, simple_loss=0.2139, pruned_loss=0.0362, over 4780.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2168, pruned_loss=0.03606, over 971843.96 frames.], batch size: 14, lr: 2.57e-04
2022-05-06 07:02:48,863 INFO [train.py:715] (4/8) Epoch 8, batch 25750, loss[loss=0.149, simple_loss=0.2268, pruned_loss=0.03561, over 4803.00 frames.], tot_loss[loss=0.1447, simple_loss=0.217, pruned_loss=0.03619, over 972133.71 frames.], batch size: 24, lr: 2.57e-04
2022-05-06 07:03:27,687 INFO [train.py:715] (4/8) Epoch 8, batch 25800, loss[loss=0.1501, simple_loss=0.224, pruned_loss=0.03812, over 4775.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2167, pruned_loss=0.03605, over 972108.96 frames.], batch size: 18, lr: 2.57e-04
2022-05-06 07:04:06,653 INFO [train.py:715] (4/8) Epoch 8, batch 25850, loss[loss=0.1623, simple_loss=0.2398, pruned_loss=0.04233, over 4693.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2168, pruned_loss=0.03593, over 973056.61 frames.], batch size: 15, lr: 2.57e-04
2022-05-06 07:04:45,939 INFO [train.py:715] (4/8) Epoch 8, batch 25900, loss[loss=0.1202, simple_loss=0.2001, pruned_loss=0.02021, over 4804.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2166, pruned_loss=0.03563, over 972896.78 frames.], batch size: 12, lr: 2.57e-04
2022-05-06 07:05:24,606 INFO [train.py:715] (4/8) Epoch 8, batch 25950, loss[loss=0.1346, simple_loss=0.1897, pruned_loss=0.03977, over 4782.00 frames.], tot_loss[loss=0.1448, simple_loss=0.2172, pruned_loss=0.03618, over 972808.71 frames.], batch size: 12, lr: 2.57e-04
2022-05-06 07:06:03,740 INFO [train.py:715] (4/8) Epoch 8, batch 26000, loss[loss=0.158, simple_loss=0.2199, pruned_loss=0.048, over 4930.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2166, pruned_loss=0.03617, over 973302.08 frames.], batch size: 39, lr: 2.57e-04
2022-05-06 07:06:42,907 INFO [train.py:715] (4/8) Epoch 8, batch 26050, loss[loss=0.1294, simple_loss=0.2035, pruned_loss=0.02761, over 4890.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.03542, over 972911.31 frames.], batch size: 32, lr: 2.57e-04
2022-05-06 07:07:21,668 INFO [train.py:715] (4/8) Epoch 8, batch 26100, loss[loss=0.127, simple_loss=0.1883, pruned_loss=0.03289, over 4855.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2158, pruned_loss=0.03542, over 973397.00 frames.], batch size: 32, lr: 2.57e-04
2022-05-06 07:08:01,300 INFO [train.py:715] (4/8) Epoch 8, batch 26150, loss[loss=0.1443, simple_loss=0.2131, pruned_loss=0.03777, over 4912.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2159, pruned_loss=0.03539, over 972597.49 frames.], batch size: 18, lr: 2.57e-04
2022-05-06 07:08:40,493 INFO [train.py:715] (4/8) Epoch 8, batch 26200, loss[loss=0.1409, simple_loss=0.2089, pruned_loss=0.03638, over 4770.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2154, pruned_loss=0.03492, over 972461.12 frames.], batch size: 18, lr: 2.57e-04
2022-05-06 07:09:19,621 INFO [train.py:715] (4/8) Epoch 8, batch 26250, loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03241, over 4845.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2149, pruned_loss=0.03524, over 972519.59 frames.], batch size: 15, lr: 2.57e-04
2022-05-06 07:09:57,935 INFO [train.py:715] (4/8) Epoch 8, batch 26300, loss[loss=0.1682, simple_loss=0.2257, pruned_loss=0.05534, over 4751.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.03573, over 972563.48 frames.], batch size: 19, lr: 2.57e-04
2022-05-06 07:10:37,571 INFO [train.py:715] (4/8) Epoch 8, batch 26350, loss[loss=0.1335, simple_loss=0.2023, pruned_loss=0.0323, over 4850.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2158, pruned_loss=0.0357, over 972196.57 frames.], batch size: 20, lr: 2.57e-04
2022-05-06 07:11:16,885 INFO [train.py:715] (4/8) Epoch 8, batch 26400, loss[loss=0.1376, simple_loss=0.1968, pruned_loss=0.0392, over 4786.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2164, pruned_loss=0.03603, over 971371.15 frames.], batch size: 12, lr: 2.57e-04
2022-05-06 07:11:55,836 INFO [train.py:715] (4/8) Epoch 8, batch 26450, loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03193, over 4763.00 frames.], tot_loss[loss=0.1444, simple_loss=0.2164, pruned_loss=0.03616, over 971549.04 frames.], batch size: 19, lr: 2.57e-04
2022-05-06 07:12:34,671 INFO [train.py:715] (4/8) Epoch 8, batch 26500, loss[loss=0.1478, simple_loss=0.2217, pruned_loss=0.03699, over 4807.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03589, over 971447.87 frames.], batch size: 21, lr: 2.57e-04
2022-05-06 07:13:13,273 INFO [train.py:715] (4/8) Epoch 8, batch 26550, loss[loss=0.1531, simple_loss=0.2215, pruned_loss=0.04229, over 4970.00 frames.], tot_loss[loss=0.1433, simple_loss=0.215, pruned_loss=0.03579, over 971168.36 frames.], batch size: 35, lr: 2.57e-04
2022-05-06 07:13:52,654 INFO [train.py:715] (4/8) Epoch 8, batch 26600, loss[loss=0.1281, simple_loss=0.2012, pruned_loss=0.02752, over 4932.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2158, pruned_loss=0.03585, over 971720.27 frames.], batch size: 23, lr: 2.57e-04
2022-05-06 07:14:30,714 INFO [train.py:715] (4/8) Epoch 8, batch 26650, loss[loss=0.1187, simple_loss=0.1911, pruned_loss=0.02318, over 4800.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2167, pruned_loss=0.03611, over 971565.76 frames.], batch size: 17, lr: 2.57e-04
2022-05-06 07:15:10,077 INFO [train.py:715] (4/8) Epoch 8, batch 26700, loss[loss=0.1512, simple_loss=0.2307, pruned_loss=0.03586, over 4851.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2165, pruned_loss=0.03562, over 971802.58 frames.], batch size: 20, lr: 2.57e-04
2022-05-06 07:15:49,151 INFO [train.py:715] (4/8) Epoch 8, batch 26750, loss[loss=0.1431, simple_loss=0.2199, pruned_loss=0.03317, over 4745.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2166, pruned_loss=0.03594, over 972094.63 frames.], batch size: 12, lr: 2.57e-04
2022-05-06 07:16:27,934 INFO [train.py:715] (4/8) Epoch 8, batch 26800, loss[loss=0.1389, simple_loss=0.2229, pruned_loss=0.02743, over 4890.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2163, pruned_loss=0.03557, over 972844.77 frames.], batch size: 22, lr: 2.57e-04
2022-05-06 07:17:07,166 INFO [train.py:715] (4/8) Epoch 8, batch 26850, loss[loss=0.1358, simple_loss=0.2071, pruned_loss=0.03219, over 4948.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2158, pruned_loss=0.03544, over 972929.25 frames.], batch size: 21, lr: 2.57e-04
2022-05-06 07:17:46,412 INFO [train.py:715] (4/8) Epoch 8, batch 26900, loss[loss=0.1377, simple_loss=0.2001, pruned_loss=0.03765, over 4761.00 frames.], tot_loss[loss=0.144, simple_loss=0.2166, pruned_loss=0.03569, over 972501.64 frames.], batch size: 19, lr: 2.57e-04
2022-05-06 07:18:25,464 INFO [train.py:715] (4/8) Epoch 8, batch 26950, loss[loss=0.1487, simple_loss=0.2173, pruned_loss=0.04009, over 4940.00 frames.], tot_loss[loss=0.1445, simple_loss=0.2169, pruned_loss=0.03601, over 972259.09 frames.], batch size: 35, lr: 2.57e-04
2022-05-06 07:19:04,351 INFO [train.py:715] (4/8) Epoch 8, batch 27000, loss[loss=0.1624, simple_loss=0.2349, pruned_loss=0.04497, over 4976.00 frames.], tot_loss[loss=0.1436, simple_loss=0.216, pruned_loss=0.0356, over 972059.90 frames.], batch size: 15, lr: 2.57e-04
2022-05-06 07:19:04,352 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 07:19:13,678 INFO [train.py:742] (4/8) Epoch 8, validation: loss=0.1072, simple_loss=0.1919, pruned_loss=0.01129, over 914524.00 frames.
2022-05-06 07:19:52,525 INFO [train.py:715] (4/8) Epoch 8, batch 27050, loss[loss=0.1197, simple_loss=0.1916, pruned_loss=0.02394, over 4828.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03547, over 971804.46 frames.], batch size: 30, lr: 2.57e-04
2022-05-06 07:20:31,870 INFO [train.py:715] (4/8) Epoch 8, batch 27100, loss[loss=0.1506, simple_loss=0.2219, pruned_loss=0.03967, over 4765.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2147, pruned_loss=0.03521, over 971334.04 frames.], batch size: 19, lr: 2.57e-04
2022-05-06 07:21:10,970 INFO [train.py:715] (4/8) Epoch 8, batch 27150, loss[loss=0.1251, simple_loss=0.2019, pruned_loss=0.02417, over 4816.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.0348, over 972319.15 frames.], batch size: 21, lr: 2.57e-04
2022-05-06 07:21:49,183 INFO [train.py:715] (4/8) Epoch 8, batch 27200, loss[loss=0.1454, simple_loss=0.2106, pruned_loss=0.04006, over 4902.00 frames.], tot_loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03543, over 972452.70 frames.], batch size: 17, lr: 2.57e-04
2022-05-06 07:22:28,510 INFO [train.py:715] (4/8) Epoch 8, batch 27250, loss[loss=0.1306, simple_loss=0.203, pruned_loss=0.02912, over 4862.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2159, pruned_loss=0.0352, over 972656.42 frames.], batch size: 16, lr: 2.57e-04
2022-05-06 07:23:07,825 INFO [train.py:715] (4/8) Epoch 8, batch 27300, loss[loss=0.1375, simple_loss=0.2223, pruned_loss=0.02638, over 4830.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2157, pruned_loss=0.03539, over 972566.64 frames.], batch size: 25, lr: 2.57e-04
2022-05-06 07:23:46,492 INFO [train.py:715] (4/8) Epoch 8, batch 27350, loss[loss=0.1524, simple_loss=0.2259, pruned_loss=0.03946, over 4838.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2161, pruned_loss=0.03558, over 973208.16 frames.], batch size: 26, lr: 2.57e-04
2022-05-06 07:24:25,182 INFO [train.py:715] (4/8) Epoch 8, batch 27400, loss[loss=0.1207, simple_loss=0.1869, pruned_loss=0.02722, over 4872.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2157, pruned_loss=0.03541, over 972692.20 frames.], batch size: 16, lr: 2.56e-04
2022-05-06 07:25:04,322 INFO [train.py:715] (4/8) Epoch 8, batch 27450, loss[loss=0.1505, simple_loss=0.2229, pruned_loss=0.03908, over 4921.00 frames.], tot_loss[loss=0.144, simple_loss=0.2165, pruned_loss=0.03575, over 972098.36 frames.], batch size: 18, lr: 2.56e-04
2022-05-06 07:25:43,017 INFO [train.py:715] (4/8) Epoch 8, batch 27500, loss[loss=0.1449, simple_loss=0.2173, pruned_loss=0.03627, over 4885.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2163, pruned_loss=0.03596, over 972123.13 frames.], batch size: 22, lr: 2.56e-04
2022-05-06 07:26:21,671 INFO [train.py:715] (4/8) Epoch 8, batch 27550, loss[loss=0.1521, simple_loss=0.2261, pruned_loss=0.03902, over 4919.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2162, pruned_loss=0.03573, over 972400.77 frames.], batch size: 18, lr: 2.56e-04
2022-05-06 07:27:01,334 INFO [train.py:715] (4/8) Epoch 8, batch 27600, loss[loss=0.1231, simple_loss=0.2001, pruned_loss=0.02304, over 4890.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2161, pruned_loss=0.0356, over 972982.22 frames.], batch size: 22, lr: 2.56e-04
2022-05-06 07:27:40,425 INFO [train.py:715] (4/8) Epoch 8, batch 27650, loss[loss=0.1489, simple_loss=0.2181, pruned_loss=0.03984, over 4694.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2153, pruned_loss=0.03494, over 973093.32 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:28:19,092 INFO [train.py:715] (4/8) Epoch 8, batch 27700, loss[loss=0.1476, simple_loss=0.2178, pruned_loss=0.03875, over 4840.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03505, over 973284.62 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:28:58,323 INFO [train.py:715] (4/8) Epoch 8, batch 27750, loss[loss=0.1804, simple_loss=0.2618, pruned_loss=0.04951, over 4833.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2139, pruned_loss=0.03467, over 973102.95 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:29:38,021 INFO [train.py:715] (4/8) Epoch 8, batch 27800, loss[loss=0.1344, simple_loss=0.2066, pruned_loss=0.03109, over 4988.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03442, over 972604.06 frames.], batch size: 14, lr: 2.56e-04
2022-05-06 07:30:16,791 INFO [train.py:715] (4/8) Epoch 8, batch 27850, loss[loss=0.138, simple_loss=0.2124, pruned_loss=0.03178, over 4972.00 frames.], tot_loss[loss=0.1424, simple_loss=0.215, pruned_loss=0.03494, over 972352.47 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:30:54,917 INFO [train.py:715] (4/8) Epoch 8, batch 27900, loss[loss=0.1214, simple_loss=0.1995, pruned_loss=0.02169, over 4751.00 frames.], tot_loss[loss=0.1415, simple_loss=0.214, pruned_loss=0.03452, over 972462.01 frames.], batch size: 19, lr: 2.56e-04
2022-05-06 07:31:34,146 INFO [train.py:715] (4/8) Epoch 8, batch 27950, loss[loss=0.1398, simple_loss=0.2208, pruned_loss=0.02936, over 4778.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2142, pruned_loss=0.03455, over 972441.01 frames.], batch size: 18, lr: 2.56e-04
2022-05-06 07:32:13,474 INFO [train.py:715] (4/8) Epoch 8, batch 28000, loss[loss=0.1362, simple_loss=0.2086, pruned_loss=0.03191, over 4964.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.03474, over 972452.35 frames.], batch size: 35, lr: 2.56e-04
2022-05-06 07:32:51,689 INFO [train.py:715] (4/8) Epoch 8, batch 28050, loss[loss=0.128, simple_loss=0.2186, pruned_loss=0.01866, over 4820.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.03527, over 972310.37 frames.], batch size: 25, lr: 2.56e-04
2022-05-06 07:33:31,443 INFO [train.py:715] (4/8) Epoch 8, batch 28100, loss[loss=0.1139, simple_loss=0.1851, pruned_loss=0.02129, over 4852.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2158, pruned_loss=0.03524, over 973076.32 frames.], batch size: 20, lr: 2.56e-04
2022-05-06 07:34:10,511 INFO [train.py:715] (4/8) Epoch 8, batch 28150, loss[loss=0.1529, simple_loss=0.2218, pruned_loss=0.04199, over 4869.00 frames.], tot_loss[loss=0.1447, simple_loss=0.2172, pruned_loss=0.03614, over 972653.31 frames.], batch size: 20, lr: 2.56e-04
2022-05-06 07:34:49,971 INFO [train.py:715] (4/8) Epoch 8, batch 28200, loss[loss=0.1324, simple_loss=0.2133, pruned_loss=0.02577, over 4796.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2166, pruned_loss=0.03593, over 972770.28 frames.], batch size: 18, lr: 2.56e-04
2022-05-06 07:35:29,401 INFO [train.py:715] (4/8) Epoch 8, batch 28250, loss[loss=0.1465, simple_loss=0.2136, pruned_loss=0.03975, over 4978.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03577, over 972422.28 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:36:09,674 INFO [train.py:715] (4/8) Epoch 8, batch 28300, loss[loss=0.123, simple_loss=0.1944, pruned_loss=0.02585, over 4872.00 frames.], tot_loss[loss=0.1436, simple_loss=0.216, pruned_loss=0.03562, over 971906.56 frames.], batch size: 32, lr: 2.56e-04
2022-05-06 07:36:49,590 INFO [train.py:715] (4/8) Epoch 8, batch 28350, loss[loss=0.1311, simple_loss=0.2147, pruned_loss=0.02375, over 4984.00 frames.], tot_loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03543, over 971989.84 frames.], batch size: 26, lr: 2.56e-04
2022-05-06 07:37:28,936 INFO [train.py:715] (4/8) Epoch 8, batch 28400, loss[loss=0.1535, simple_loss=0.2219, pruned_loss=0.04254, over 4887.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2155, pruned_loss=0.03501, over 972758.99 frames.], batch size: 22, lr: 2.56e-04
2022-05-06 07:38:08,994 INFO [train.py:715] (4/8) Epoch 8, batch 28450, loss[loss=0.1767, simple_loss=0.2415, pruned_loss=0.05599, over 4848.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.03516, over 972463.54 frames.], batch size: 34, lr: 2.56e-04
2022-05-06 07:38:48,157 INFO [train.py:715] (4/8) Epoch 8, batch 28500, loss[loss=0.1605, simple_loss=0.2246, pruned_loss=0.04823, over 4950.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2162, pruned_loss=0.03579, over 973163.23 frames.], batch size: 39, lr: 2.56e-04
2022-05-06 07:39:26,865 INFO [train.py:715] (4/8) Epoch 8, batch 28550, loss[loss=0.1396, simple_loss=0.2222, pruned_loss=0.02852, over 4820.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.03574, over 972622.41 frames.], batch size: 26, lr: 2.56e-04
2022-05-06 07:40:05,722 INFO [train.py:715] (4/8) Epoch 8, batch 28600, loss[loss=0.137, simple_loss=0.2015, pruned_loss=0.03626, over 4870.00 frames.], tot_loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03546, over 972703.89 frames.], batch size: 32, lr: 2.56e-04
2022-05-06 07:40:45,400 INFO [train.py:715] (4/8) Epoch 8, batch 28650, loss[loss=0.1268, simple_loss=0.2064, pruned_loss=0.02354, over 4921.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2162, pruned_loss=0.03536, over 973061.67 frames.], batch size: 18, lr: 2.56e-04
2022-05-06 07:41:24,254 INFO [train.py:715] (4/8) Epoch 8, batch 28700, loss[loss=0.1475, simple_loss=0.2135, pruned_loss=0.04069, over 4938.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.03553, over 973510.15 frames.], batch size: 18, lr: 2.56e-04
2022-05-06 07:42:02,603 INFO [train.py:715] (4/8) Epoch 8, batch 28750, loss[loss=0.1475, simple_loss=0.207, pruned_loss=0.04397, over 4775.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2158, pruned_loss=0.03577, over 973705.93 frames.], batch size: 17, lr: 2.56e-04
2022-05-06 07:42:42,146 INFO [train.py:715] (4/8) Epoch 8, batch 28800, loss[loss=0.1494, simple_loss=0.2196, pruned_loss=0.03962, over 4817.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.03544, over 973313.82 frames.], batch size: 13, lr: 2.56e-04
2022-05-06 07:43:21,535 INFO [train.py:715] (4/8) Epoch 8, batch 28850, loss[loss=0.1684, simple_loss=0.2288, pruned_loss=0.054, over 4839.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2158, pruned_loss=0.03588, over 973384.33 frames.], batch size: 30, lr: 2.56e-04
2022-05-06 07:44:00,545 INFO [train.py:715] (4/8) Epoch 8, batch 28900, loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.03444, over 4779.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2154, pruned_loss=0.03554, over 973421.26 frames.], batch size: 12, lr: 2.56e-04
2022-05-06 07:44:39,169 INFO [train.py:715] (4/8) Epoch 8, batch 28950, loss[loss=0.1722, simple_loss=0.2523, pruned_loss=0.04606, over 4820.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03547, over 972953.55 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:45:18,515 INFO [train.py:715] (4/8) Epoch 8, batch 29000, loss[loss=0.163, simple_loss=0.2325, pruned_loss=0.04679, over 4922.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2158, pruned_loss=0.03576, over 973058.94 frames.], batch size: 18, lr: 2.56e-04
2022-05-06 07:45:57,177 INFO [train.py:715] (4/8) Epoch 8, batch 29050, loss[loss=0.1431, simple_loss=0.2237, pruned_loss=0.03122, over 4857.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2152, pruned_loss=0.03552, over 972784.20 frames.], batch size: 20, lr: 2.56e-04
2022-05-06 07:46:36,419 INFO [train.py:715] (4/8) Epoch 8, batch 29100, loss[loss=0.1283, simple_loss=0.2097, pruned_loss=0.02344, over 4827.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2152, pruned_loss=0.03545, over 972733.06 frames.], batch size: 27, lr: 2.56e-04
2022-05-06 07:47:14,941 INFO [train.py:715] (4/8) Epoch 8, batch 29150, loss[loss=0.1314, simple_loss=0.2052, pruned_loss=0.02884, over 4957.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2157, pruned_loss=0.03564, over 972763.11 frames.], batch size: 29, lr: 2.56e-04
2022-05-06 07:47:54,240 INFO [train.py:715] (4/8) Epoch 8, batch 29200, loss[loss=0.138, simple_loss=0.2126, pruned_loss=0.03167, over 4984.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.03549, over 973228.40 frames.], batch size: 25, lr: 2.56e-04
2022-05-06 07:48:32,865 INFO [train.py:715] (4/8) Epoch 8, batch 29250, loss[loss=0.1342, simple_loss=0.2114, pruned_loss=0.02847, over 4768.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2147, pruned_loss=0.03498, over 972357.00 frames.], batch size: 14, lr: 2.56e-04
2022-05-06 07:49:11,137 INFO [train.py:715] (4/8) Epoch 8, batch 29300, loss[loss=0.1242, simple_loss=0.1926, pruned_loss=0.02786, over 4861.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03485, over 972979.52 frames.], batch size: 13, lr: 2.56e-04
2022-05-06 07:49:50,318 INFO [train.py:715] (4/8) Epoch 8, batch 29350, loss[loss=0.1873, simple_loss=0.2583, pruned_loss=0.05812, over 4885.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.03501, over 973242.42 frames.], batch size: 19, lr: 2.56e-04
2022-05-06 07:50:29,148 INFO [train.py:715] (4/8) Epoch 8, batch 29400, loss[loss=0.1262, simple_loss=0.1991, pruned_loss=0.02666, over 4941.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03498, over 972301.09 frames.], batch size: 21, lr: 2.56e-04
2022-05-06 07:51:08,795 INFO [train.py:715] (4/8) Epoch 8, batch 29450, loss[loss=0.1431, simple_loss=0.208, pruned_loss=0.03909, over 4651.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2153, pruned_loss=0.03576, over 971914.06 frames.], batch size: 13, lr: 2.56e-04
2022-05-06 07:51:48,078 INFO [train.py:715] (4/8) Epoch 8, batch 29500, loss[loss=0.1124, simple_loss=0.1747, pruned_loss=0.025, over 4972.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2153, pruned_loss=0.03557, over 972688.72 frames.], batch size: 14, lr: 2.56e-04
2022-05-06 07:52:27,548 INFO [train.py:715] (4/8) Epoch 8, batch 29550, loss[loss=0.1393, simple_loss=0.2178, pruned_loss=0.03043, over 4829.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2144, pruned_loss=0.03549, over 972527.25 frames.], batch size: 27, lr: 2.56e-04
2022-05-06 07:53:06,113 INFO [train.py:715] (4/8) Epoch 8, batch 29600, loss[loss=0.1666, simple_loss=0.2415, pruned_loss=0.04582, over 4959.00 frames.], tot_loss[loss=0.1434, simple_loss=0.215, pruned_loss=0.03587, over 972756.48 frames.], batch size: 15, lr: 2.56e-04
2022-05-06 07:53:45,381 INFO [train.py:715] (4/8) Epoch 8, batch 29650, loss[loss=0.1245, simple_loss=0.2056, pruned_loss=0.02172, over 4810.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2149, pruned_loss=0.03547, over 973231.45 frames.], batch size: 25, lr: 2.56e-04
2022-05-06 07:54:24,985 INFO [train.py:715] (4/8) Epoch 8, batch 29700, loss[loss=0.1451, simple_loss=0.2174, pruned_loss=0.03641, over 4944.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2146, pruned_loss=0.03538, over 972709.14 frames.], batch size: 35, lr: 2.56e-04
2022-05-06 07:55:03,539 INFO [train.py:715] (4/8) Epoch 8, batch 29750, loss[loss=0.1502, simple_loss=0.2126, pruned_loss=0.04391, over 4758.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2154, pruned_loss=0.03603, over 972634.31 frames.], batch size: 16, lr: 2.56e-04
2022-05-06 07:55:42,375 INFO [train.py:715] (4/8) Epoch 8, batch 29800, loss[loss=0.1344, simple_loss=0.2143, pruned_loss=0.0273, over 4855.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2156, pruned_loss=0.036, over 972513.07 frames.], batch size: 32, lr: 2.55e-04
2022-05-06 07:56:21,282 INFO [train.py:715] (4/8) Epoch 8, batch 29850, loss[loss=0.1688, simple_loss=0.2414, pruned_loss=0.04814, over 4983.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2161, pruned_loss=0.03589, over 972282.14 frames.], batch size: 24, lr: 2.55e-04
2022-05-06 07:57:00,652 INFO [train.py:715] (4/8) Epoch 8, batch 29900, loss[loss=0.2001, simple_loss=0.2683, pruned_loss=0.06593, over 4839.00 frames.], tot_loss[loss=0.1436, simple_loss=0.216, pruned_loss=0.0356, over 973011.14 frames.], batch size: 30, lr: 2.55e-04
2022-05-06 07:57:39,540 INFO [train.py:715] (4/8) Epoch 8, batch 29950, loss[loss=0.1312, simple_loss=0.2143, pruned_loss=0.02404, over 4853.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2163, pruned_loss=0.03542, over 972598.78 frames.], batch size: 20, lr: 2.55e-04
2022-05-06 07:58:18,654 INFO [train.py:715] (4/8) Epoch 8, batch 30000, loss[loss=0.1561, simple_loss=0.2353, pruned_loss=0.03848, over 4866.00 frames.], tot_loss[loss=0.144, simple_loss=0.2164, pruned_loss=0.03575, over 972230.15 frames.], batch size: 20, lr: 2.55e-04
2022-05-06 07:58:18,654 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 07:58:28,239 INFO [train.py:742] (4/8) Epoch 8, validation: loss=0.1073, simple_loss=0.1918, pruned_loss=0.01141, over 914524.00 frames.
2022-05-06 07:59:07,026 INFO [train.py:715] (4/8) Epoch 8, batch 30050, loss[loss=0.141, simple_loss=0.2148, pruned_loss=0.03358, over 4926.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2167, pruned_loss=0.03595, over 972504.27 frames.], batch size: 23, lr: 2.55e-04
2022-05-06 07:59:46,358 INFO [train.py:715] (4/8) Epoch 8, batch 30100, loss[loss=0.1611, simple_loss=0.2421, pruned_loss=0.04009, over 4940.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2168, pruned_loss=0.03591, over 972459.76 frames.], batch size: 21, lr: 2.55e-04
2022-05-06 08:00:25,656 INFO [train.py:715] (4/8) Epoch 8, batch 30150, loss[loss=0.1456, simple_loss=0.2032, pruned_loss=0.04401, over 4871.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03573, over 972430.33 frames.], batch size: 16, lr: 2.55e-04
2022-05-06 08:01:04,253 INFO [train.py:715] (4/8) Epoch 8, batch 30200, loss[loss=0.1475, simple_loss=0.2149, pruned_loss=0.04007, over 4787.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2159, pruned_loss=0.03559, over 971927.91 frames.], batch size: 14, lr: 2.55e-04
2022-05-06 08:01:43,183 INFO [train.py:715] (4/8) Epoch 8, batch 30250, loss[loss=0.1256, simple_loss=0.1992, pruned_loss=0.02598, over 4942.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.03514, over 972417.09 frames.], batch size: 23, lr: 2.55e-04
2022-05-06 08:02:22,869 INFO [train.py:715] (4/8) Epoch 8, batch 30300, loss[loss=0.152, simple_loss=0.2173, pruned_loss=0.04331, over 4980.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.03494, over 972280.61 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 08:03:01,869 INFO [train.py:715] (4/8) Epoch 8, batch 30350, loss[loss=0.1609, simple_loss=0.2249, pruned_loss=0.04842, over 4779.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03506, over 972150.33 frames.], batch size: 14, lr: 2.55e-04
2022-05-06 08:03:40,561 INFO [train.py:715] (4/8) Epoch 8, batch 30400, loss[loss=0.1507, simple_loss=0.218, pruned_loss=0.04166, over 4978.00 frames.], tot_loss[loss=0.143, simple_loss=0.2152, pruned_loss=0.0354, over 972398.65 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 08:04:19,871 INFO [train.py:715] (4/8) Epoch 8, batch 30450, loss[loss=0.1337, simple_loss=0.2085, pruned_loss=0.02942, over 4841.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.03551, over 972196.39 frames.], batch size: 26, lr: 2.55e-04
2022-05-06 08:04:58,850 INFO [train.py:715] (4/8) Epoch 8, batch 30500, loss[loss=0.1228, simple_loss=0.193, pruned_loss=0.02625, over 4849.00 frames.], tot_loss[loss=0.1437, simple_loss=0.216, pruned_loss=0.03571, over 972996.21 frames.], batch size: 32, lr: 2.55e-04
2022-05-06 08:05:37,495 INFO [train.py:715] (4/8) Epoch 8, batch 30550, loss[loss=0.1399, simple_loss=0.215, pruned_loss=0.03243, over 4915.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.0358, over 973902.64 frames.], batch size: 18, lr: 2.55e-04
2022-05-06 08:06:16,534 INFO [train.py:715] (4/8) Epoch 8, batch 30600, loss[loss=0.1478, simple_loss=0.2213, pruned_loss=0.03712, over 4943.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2164, pruned_loss=0.03605, over 973234.76 frames.], batch size: 21, lr: 2.55e-04
2022-05-06 08:06:56,249 INFO [train.py:715] (4/8) Epoch 8, batch 30650, loss[loss=0.1364, simple_loss=0.2133, pruned_loss=0.02973, over 4976.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2159, pruned_loss=0.0357, over 974017.72 frames.], batch size: 28, lr: 2.55e-04
2022-05-06 08:07:35,432 INFO [train.py:715] (4/8) Epoch 8, batch 30700, loss[loss=0.1269, simple_loss=0.1955, pruned_loss=0.0292, over 4701.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.03518, over 973268.08 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 08:08:15,308 INFO [train.py:715] (4/8) Epoch 8, batch 30750, loss[loss=0.1353, simple_loss=0.2121, pruned_loss=0.02925, over 4871.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2145, pruned_loss=0.03443, over 974014.46 frames.], batch size: 32, lr: 2.55e-04
2022-05-06 08:08:55,427 INFO [train.py:715] (4/8) Epoch 8, batch 30800, loss[loss=0.1059, simple_loss=0.1792, pruned_loss=0.01631, over 4830.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2144, pruned_loss=0.03429, over 973226.18 frames.], batch size: 12, lr: 2.55e-04
2022-05-06 08:09:33,881 INFO [train.py:715] (4/8) Epoch 8, batch 30850, loss[loss=0.1322, simple_loss=0.2121, pruned_loss=0.02612, over 4936.00 frames.], tot_loss[loss=0.1424, simple_loss=0.215, pruned_loss=0.03487, over 972164.74 frames.], batch size: 29, lr: 2.55e-04
2022-05-06 08:10:12,783 INFO [train.py:715] (4/8) Epoch 8, batch 30900, loss[loss=0.1491, simple_loss=0.2252, pruned_loss=0.03643, over 4754.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.03467, over 972565.39 frames.], batch size: 14, lr: 2.55e-04
2022-05-06 08:10:52,540 INFO [train.py:715] (4/8) Epoch 8, batch 30950, loss[loss=0.1487, simple_loss=0.2259, pruned_loss=0.03578, over 4909.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03445, over 973676.44 frames.], batch size: 17, lr: 2.55e-04
2022-05-06 08:11:32,559 INFO [train.py:715] (4/8) Epoch 8, batch 31000, loss[loss=0.1403, simple_loss=0.2041, pruned_loss=0.03825, over 4697.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2136, pruned_loss=0.03455, over 973400.53 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 08:12:11,803 INFO [train.py:715] (4/8) Epoch 8, batch 31050, loss[loss=0.1549, simple_loss=0.2159, pruned_loss=0.04696, over 4833.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2145, pruned_loss=0.03501, over 972490.08 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 08:12:51,404 INFO [train.py:715] (4/8) Epoch 8, batch 31100, loss[loss=0.1523, simple_loss=0.233, pruned_loss=0.03583, over 4920.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2151, pruned_loss=0.03533, over 972758.62 frames.], batch size: 29, lr: 2.55e-04
2022-05-06 08:13:30,939 INFO [train.py:715] (4/8) Epoch 8, batch 31150, loss[loss=0.148, simple_loss=0.2254, pruned_loss=0.03532, over 4789.00 frames.], tot_loss[loss=0.143, simple_loss=0.2157, pruned_loss=0.03518, over 972628.93 frames.], batch size: 21, lr: 2.55e-04
2022-05-06 08:14:09,968 INFO [train.py:715] (4/8) Epoch 8, batch 31200, loss[loss=0.1248, simple_loss=0.1889, pruned_loss=0.03038, over 4865.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2156, pruned_loss=0.03539, over 972504.33 frames.], batch size: 20, lr: 2.55e-04
2022-05-06 08:14:48,714 INFO [train.py:715] (4/8) Epoch 8, batch 31250, loss[loss=0.1635, simple_loss=0.2399, pruned_loss=0.04356, over 4877.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2159, pruned_loss=0.03551, over 972068.26 frames.], batch size: 22, lr: 2.55e-04
2022-05-06 08:15:28,181 INFO [train.py:715] (4/8) Epoch 8, batch 31300, loss[loss=0.1145, simple_loss=0.1837, pruned_loss=0.02268, over 4821.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.03587, over 972033.23 frames.], batch size: 26, lr: 2.55e-04
2022-05-06 08:16:07,683 INFO [train.py:715] (4/8) Epoch 8, batch 31350, loss[loss=0.1614, simple_loss=0.2272, pruned_loss=0.04784, over 4909.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2162, pruned_loss=0.0355, over 972139.11 frames.], batch size: 17, lr: 2.55e-04
2022-05-06 08:16:46,298 INFO [train.py:715] (4/8) Epoch 8, batch 31400, loss[loss=0.1409, simple_loss=0.2053, pruned_loss=0.03822, over 4758.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2153, pruned_loss=0.03547, over 972436.22 frames.], batch size: 19, lr: 2.55e-04
2022-05-06 08:17:25,750 INFO [train.py:715] (4/8) Epoch 8, batch 31450, loss[loss=0.1236, simple_loss=0.1928, pruned_loss=0.0272, over 4964.00 frames.], tot_loss[loss=0.143, simple_loss=0.2157, pruned_loss=0.03515, over 972753.68 frames.], batch size: 24, lr: 2.55e-04
2022-05-06 08:18:05,872 INFO [train.py:715] (4/8) Epoch 8, batch 31500, loss[loss=0.1311, simple_loss=0.2037, pruned_loss=0.02922, over 4922.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03477, over 973103.47 frames.], batch size: 17, lr: 2.55e-04
2022-05-06 08:18:45,115 INFO [train.py:715] (4/8) Epoch 8, batch 31550, loss[loss=0.1317, simple_loss=0.2027, pruned_loss=0.03035, over 4833.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2146, pruned_loss=0.03505, over 972630.97 frames.], batch size: 30, lr: 2.55e-04
2022-05-06 08:19:24,101 INFO [train.py:715] (4/8) Epoch 8, batch 31600, loss[loss=0.1347, simple_loss=0.2113, pruned_loss=0.02904, over 4870.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.03492, over 972037.26 frames.], batch size: 38, lr: 2.55e-04
2022-05-06 08:20:03,752 INFO [train.py:715] (4/8) Epoch 8, batch 31650, loss[loss=0.1438, simple_loss=0.2177, pruned_loss=0.03491, over 4872.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2153, pruned_loss=0.03553, over 972892.04 frames.], batch size: 16, lr: 2.55e-04
2022-05-06 08:20:43,074 INFO [train.py:715] (4/8) Epoch 8, batch 31700, loss[loss=0.1138, simple_loss=0.1819, pruned_loss=0.02285, over 4948.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2139, pruned_loss=0.03464, over 972739.66 frames.], batch size: 14, lr: 2.55e-04
2022-05-06 08:21:22,752 INFO [train.py:715] (4/8) Epoch 8, batch 31750, loss[loss=0.147, simple_loss=0.2245, pruned_loss=0.03475, over 4821.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03506, over 972414.08 frames.], batch size: 15, lr: 2.55e-04
2022-05-06 08:22:01,966 INFO [train.py:715] (4/8) Epoch 8, batch 31800, loss[loss=0.1395, simple_loss=0.2137, pruned_loss=0.03268, over 4871.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2151, pruned_loss=0.03495, over 972559.07 frames.], batch size: 16, lr: 2.55e-04
2022-05-06 08:22:41,010 INFO [train.py:715] (4/8) Epoch 8, batch 31850, loss[loss=0.1642, simple_loss=0.2229, pruned_loss=0.05273, over 4908.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03495, over 973584.92 frames.], batch size: 19, lr: 2.55e-04
2022-05-06 08:23:19,919 INFO [train.py:715] (4/8) Epoch 8, batch 31900, loss[loss=0.1659, simple_loss=0.2487, pruned_loss=0.04161, over 4869.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2152, pruned_loss=0.0351, over 973732.18 frames.], batch size: 22, lr: 2.55e-04
2022-05-06 08:23:58,316 INFO [train.py:715] (4/8) Epoch 8, batch 31950, loss[loss=0.1355, simple_loss=0.2153, pruned_loss=0.0278, over 4906.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.03528, over 973320.79 frames.], batch size: 18, lr: 2.55e-04
2022-05-06 08:24:37,604 INFO [train.py:715] (4/8) Epoch 8, batch 32000, loss[loss=0.1127, simple_loss=0.1911, pruned_loss=0.01712, over 4927.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2152, pruned_loss=0.03561, over 973611.07 frames.], batch size: 29, lr: 2.55e-04
2022-05-06 08:25:17,172 INFO [train.py:715] (4/8) Epoch 8, batch 32050, loss[loss=0.1674, simple_loss=0.2377, pruned_loss=0.04856, over 4900.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2136, pruned_loss=0.03491, over 973039.89 frames.], batch size: 19, lr: 2.55e-04
2022-05-06 08:25:55,736 INFO [train.py:715] (4/8) Epoch 8, batch 32100, loss[loss=0.1105, simple_loss=0.1796, pruned_loss=0.02071, over 4656.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2142, pruned_loss=0.03506, over 971525.43 frames.], batch size: 13, lr: 2.55e-04
2022-05-06 08:26:34,466 INFO [train.py:715] (4/8) Epoch 8, batch 32150, loss[loss=0.1438, simple_loss=0.2132, pruned_loss=0.03724, over 4862.00 frames.], tot_loss[loss=0.143, simple_loss=0.2154, pruned_loss=0.03536, over 972230.95 frames.], batch size: 38, lr: 2.55e-04
2022-05-06 08:27:14,044 INFO [train.py:715] (4/8) Epoch 8, batch 32200, loss[loss=0.129, simple_loss=0.2007, pruned_loss=0.02865, over 4771.00 frames.], tot_loss[loss=0.143, simple_loss=0.2153, pruned_loss=0.03531, over 972411.15 frames.], batch size: 18, lr: 2.54e-04
2022-05-06 08:27:52,861 INFO [train.py:715] (4/8) Epoch 8, batch 32250, loss[loss=0.1425, simple_loss=0.2188, pruned_loss=0.03314, over 4795.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2155, pruned_loss=0.0352, over 972703.89 frames.], batch size: 21, lr: 2.54e-04
2022-05-06 08:28:32,331 INFO [train.py:715] (4/8) Epoch 8, batch 32300, loss[loss=0.1447, simple_loss=0.2226, pruned_loss=0.03338, over 4918.00 frames.], tot_loss[loss=0.143, simple_loss=0.2155, pruned_loss=0.03527, over 972850.48 frames.], batch size: 18, lr: 2.54e-04
2022-05-06 08:29:11,542 INFO [train.py:715] (4/8) Epoch 8, batch 32350, loss[loss=0.1155, simple_loss=0.1816, pruned_loss=0.02472, over 4823.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2154, pruned_loss=0.03488, over 973172.96 frames.], batch size: 13, lr: 2.54e-04
2022-05-06 08:29:51,458 INFO [train.py:715] (4/8) Epoch 8, batch 32400, loss[loss=0.1479, simple_loss=0.2215, pruned_loss=0.03715, over 4749.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2155, pruned_loss=0.03502, over 972883.42 frames.], batch size: 19, lr: 2.54e-04
2022-05-06 08:30:30,381 INFO [train.py:715] (4/8) Epoch 8, batch 32450, loss[loss=0.1797, simple_loss=0.2355, pruned_loss=0.06201, over 4932.00 frames.], tot_loss[loss=0.143, simple_loss=0.2158, pruned_loss=0.03506, over 972651.45 frames.], batch size: 35, lr: 2.54e-04
2022-05-06 08:31:09,402 INFO [train.py:715] (4/8) Epoch 8, batch 32500, loss[loss=0.1508, simple_loss=0.2386, pruned_loss=0.03155, over 4868.00 frames.], tot_loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.03477, over 972200.98 frames.], batch size: 16, lr: 2.54e-04
2022-05-06 08:31:48,952 INFO [train.py:715] (4/8) Epoch 8, batch 32550, loss[loss=0.1308, simple_loss=0.2096, pruned_loss=0.02601, over 4819.00 frames.], tot_loss[loss=0.143, simple_loss=0.2156, pruned_loss=0.03527, over 971822.95 frames.], batch size: 26, lr: 2.54e-04
2022-05-06 08:32:27,501 INFO [train.py:715] (4/8) Epoch 8, batch 32600, loss[loss=0.1367, simple_loss=0.2065, pruned_loss=0.03343, over 4809.00 frames.], tot_loss[loss=0.143, simple_loss=0.2152, pruned_loss=0.0354, over 972354.36 frames.], batch size: 13, lr: 2.54e-04
2022-05-06 08:33:06,727 INFO [train.py:715] (4/8) Epoch 8, batch 32650, loss[loss=0.1577, simple_loss=0.2317, pruned_loss=0.04187, over 4868.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2154, pruned_loss=0.03545, over 972812.63 frames.], batch size: 20, lr: 2.54e-04
2022-05-06 08:33:45,981 INFO [train.py:715] (4/8) Epoch 8, batch 32700, loss[loss=0.138, simple_loss=0.2036, pruned_loss=0.03625, over 4816.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2152, pruned_loss=0.03557, over 972240.53 frames.], batch size: 21, lr: 2.54e-04
2022-05-06 08:34:26,178 INFO [train.py:715] (4/8) Epoch 8, batch 32750, loss[loss=0.129, simple_loss=0.208, pruned_loss=0.02502, over 4876.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2147, pruned_loss=0.0352, over 972933.30 frames.], batch size: 22, lr: 2.54e-04
2022-05-06 08:35:04,665 INFO [train.py:715] (4/8) Epoch 8, batch 32800, loss[loss=0.1494, simple_loss=0.221, pruned_loss=0.03894, over 4872.00 frames.], tot_loss[loss=0.143, simple_loss=0.2153, pruned_loss=0.03537, over 972377.68 frames.], batch size: 16, lr: 2.54e-04
2022-05-06 08:35:43,309 INFO [train.py:715] (4/8) Epoch 8, batch 32850, loss[loss=0.1607, simple_loss=0.2388, pruned_loss=0.04125, over 4780.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2141, pruned_loss=0.0353, over 973189.33 frames.], batch size: 14, lr: 2.54e-04
2022-05-06 08:36:22,461 INFO [train.py:715] (4/8) Epoch 8, batch 32900, loss[loss=0.1347, simple_loss=0.2079, pruned_loss=0.03077, over 4816.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2136, pruned_loss=0.03498, over 972888.47 frames.], batch size: 27, lr: 2.54e-04
2022-05-06 08:37:00,743 INFO [train.py:715] (4/8) Epoch 8, batch 32950, loss[loss=0.1514, simple_loss=0.2243, pruned_loss=0.03921, over 4690.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2142, pruned_loss=0.03546, over 972320.67 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:37:39,628 INFO [train.py:715] (4/8) Epoch 8, batch 33000, loss[loss=0.1292, simple_loss=0.2106, pruned_loss=0.02393, over 4956.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2136, pruned_loss=0.03485, over 973018.55 frames.], batch size: 14, lr: 2.54e-04
2022-05-06 08:37:39,629 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 08:37:52,639 INFO [train.py:742] (4/8) Epoch 8, validation: loss=0.1071, simple_loss=0.1917, pruned_loss=0.01126, over 914524.00 frames.
2022-05-06 08:38:31,973 INFO [train.py:715] (4/8) Epoch 8, batch 33050, loss[loss=0.123, simple_loss=0.2051, pruned_loss=0.02043, over 4802.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2142, pruned_loss=0.03516, over 972655.75 frames.], batch size: 21, lr: 2.54e-04
2022-05-06 08:39:10,828 INFO [train.py:715] (4/8) Epoch 8, batch 33100, loss[loss=0.146, simple_loss=0.2168, pruned_loss=0.03761, over 4814.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2144, pruned_loss=0.03494, over 972780.95 frames.], batch size: 26, lr: 2.54e-04
2022-05-06 08:39:50,123 INFO [train.py:715] (4/8) Epoch 8, batch 33150, loss[loss=0.1534, simple_loss=0.2248, pruned_loss=0.04101, over 4989.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2155, pruned_loss=0.0352, over 972663.97 frames.], batch size: 25, lr: 2.54e-04
2022-05-06 08:40:28,832 INFO [train.py:715] (4/8) Epoch 8, batch 33200, loss[loss=0.1332, simple_loss=0.2106, pruned_loss=0.02793, over 4793.00 frames.], tot_loss[loss=0.142, simple_loss=0.2148, pruned_loss=0.03454, over 973522.11 frames.], batch size: 18, lr: 2.54e-04
2022-05-06 08:41:08,503 INFO [train.py:715] (4/8) Epoch 8, batch 33250, loss[loss=0.1267, simple_loss=0.1999, pruned_loss=0.02679, over 4788.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2151, pruned_loss=0.03425, over 973294.11 frames.], batch size: 17, lr: 2.54e-04
2022-05-06 08:41:48,102 INFO [train.py:715] (4/8) Epoch 8, batch 33300, loss[loss=0.1788, simple_loss=0.2564, pruned_loss=0.05066, over 4861.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2152, pruned_loss=0.0343, over 972897.73 frames.], batch size: 20, lr: 2.54e-04
2022-05-06 08:42:26,898 INFO [train.py:715] (4/8) Epoch 8, batch 33350, loss[loss=0.1417, simple_loss=0.2041, pruned_loss=0.03963, over 4709.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2145, pruned_loss=0.03447, over 972207.68 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:43:06,277 INFO [train.py:715] (4/8) Epoch 8, batch 33400, loss[loss=0.1597, simple_loss=0.2368, pruned_loss=0.04129, over 4925.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03466, over 972633.11 frames.], batch size: 23, lr: 2.54e-04
2022-05-06 08:43:45,177 INFO [train.py:715] (4/8) Epoch 8, batch 33450, loss[loss=0.1485, simple_loss=0.2191, pruned_loss=0.03892, over 4937.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2153, pruned_loss=0.03499, over 972850.60 frames.], batch size: 35, lr: 2.54e-04
2022-05-06 08:44:24,007 INFO [train.py:715] (4/8) Epoch 8, batch 33500, loss[loss=0.1363, simple_loss=0.2046, pruned_loss=0.034, over 4984.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.035, over 972549.54 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:45:05,007 INFO [train.py:715] (4/8) Epoch 8, batch 33550, loss[loss=0.1247, simple_loss=0.2072, pruned_loss=0.02108, over 4916.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03532, over 972241.12 frames.], batch size: 29, lr: 2.54e-04
2022-05-06 08:45:44,463 INFO [train.py:715] (4/8) Epoch 8, batch 33600, loss[loss=0.1441, simple_loss=0.2138, pruned_loss=0.03719, over 4798.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03552, over 972030.84 frames.], batch size: 18, lr: 2.54e-04
2022-05-06 08:46:23,909 INFO [train.py:715] (4/8) Epoch 8, batch 33650, loss[loss=0.1708, simple_loss=0.2397, pruned_loss=0.05095, over 4856.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2161, pruned_loss=0.03624, over 971321.31 frames.], batch size: 13, lr: 2.54e-04
2022-05-06 08:47:02,972 INFO [train.py:715] (4/8) Epoch 8, batch 33700, loss[loss=0.1452, simple_loss=0.2202, pruned_loss=0.03514, over 4828.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2151, pruned_loss=0.03569, over 971006.69 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:47:41,967 INFO [train.py:715] (4/8) Epoch 8, batch 33750, loss[loss=0.1576, simple_loss=0.2282, pruned_loss=0.0435, over 4936.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2152, pruned_loss=0.03559, over 970648.61 frames.], batch size: 21, lr: 2.54e-04
2022-05-06 08:48:20,686 INFO [train.py:715] (4/8) Epoch 8, batch 33800, loss[loss=0.1343, simple_loss=0.2177, pruned_loss=0.02545, over 4983.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2154, pruned_loss=0.03582, over 972024.54 frames.], batch size: 28, lr: 2.54e-04
2022-05-06 08:48:59,304 INFO [train.py:715] (4/8) Epoch 8, batch 33850, loss[loss=0.169, simple_loss=0.2399, pruned_loss=0.04909, over 4793.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2154, pruned_loss=0.03585, over 972738.81 frames.], batch size: 17, lr: 2.54e-04
2022-05-06 08:49:38,115 INFO [train.py:715] (4/8) Epoch 8, batch 33900, loss[loss=0.1192, simple_loss=0.1868, pruned_loss=0.0258, over 4788.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2152, pruned_loss=0.03573, over 973765.27 frames.], batch size: 12, lr: 2.54e-04
2022-05-06 08:50:17,036 INFO [train.py:715] (4/8) Epoch 8, batch 33950, loss[loss=0.1384, simple_loss=0.2142, pruned_loss=0.03129, over 4818.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03552, over 972653.57 frames.], batch size: 27, lr: 2.54e-04
2022-05-06 08:50:56,649 INFO [train.py:715] (4/8) Epoch 8, batch 34000, loss[loss=0.1694, simple_loss=0.2311, pruned_loss=0.05387, over 4707.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2159, pruned_loss=0.0356, over 972673.17 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:51:35,566 INFO [train.py:715] (4/8) Epoch 8, batch 34050, loss[loss=0.1537, simple_loss=0.2356, pruned_loss=0.03591, over 4978.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2158, pruned_loss=0.03543, over 973080.09 frames.], batch size: 28, lr: 2.54e-04
2022-05-06 08:52:14,816 INFO [train.py:715] (4/8) Epoch 8, batch 34100, loss[loss=0.1409, simple_loss=0.2176, pruned_loss=0.03214, over 4785.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2161, pruned_loss=0.03561, over 972303.18 frames.], batch size: 14, lr: 2.54e-04
2022-05-06 08:52:53,779 INFO [train.py:715] (4/8) Epoch 8, batch 34150, loss[loss=0.1108, simple_loss=0.1814, pruned_loss=0.0201, over 4788.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2165, pruned_loss=0.03607, over 972494.19 frames.], batch size: 12, lr: 2.54e-04
2022-05-06 08:53:32,396 INFO [train.py:715] (4/8) Epoch 8, batch 34200, loss[loss=0.1841, simple_loss=0.2532, pruned_loss=0.05748, over 4994.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2166, pruned_loss=0.03563, over 972490.12 frames.], batch size: 20, lr: 2.54e-04
2022-05-06 08:54:11,301 INFO [train.py:715] (4/8) Epoch 8, batch 34250, loss[loss=0.1656, simple_loss=0.2329, pruned_loss=0.04915, over 4842.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2164, pruned_loss=0.03549, over 972567.25 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:54:50,275 INFO [train.py:715] (4/8) Epoch 8, batch 34300, loss[loss=0.1634, simple_loss=0.2233, pruned_loss=0.05175, over 4694.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2162, pruned_loss=0.03543, over 971940.18 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:55:29,025 INFO [train.py:715] (4/8) Epoch 8, batch 34350, loss[loss=0.1241, simple_loss=0.1942, pruned_loss=0.02701, over 4831.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2163, pruned_loss=0.03581, over 972704.50 frames.], batch size: 27, lr: 2.54e-04
2022-05-06 08:56:07,452 INFO [train.py:715] (4/8) Epoch 8, batch 34400, loss[loss=0.1006, simple_loss=0.1684, pruned_loss=0.01637, over 4823.00 frames.], tot_loss[loss=0.144, simple_loss=0.2163, pruned_loss=0.03581, over 972073.43 frames.], batch size: 12, lr: 2.54e-04
2022-05-06 08:56:46,676 INFO [train.py:715] (4/8) Epoch 8, batch 34450, loss[loss=0.1074, simple_loss=0.179, pruned_loss=0.01789, over 4811.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03594, over 972396.01 frames.], batch size: 12, lr: 2.54e-04
2022-05-06 08:57:26,047 INFO [train.py:715] (4/8) Epoch 8, batch 34500, loss[loss=0.1307, simple_loss=0.2046, pruned_loss=0.02839, over 4987.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2165, pruned_loss=0.03608, over 972339.37 frames.], batch size: 33, lr: 2.54e-04
2022-05-06 08:58:04,289 INFO [train.py:715] (4/8) Epoch 8, batch 34550, loss[loss=0.1387, simple_loss=0.206, pruned_loss=0.03571, over 4703.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2159, pruned_loss=0.03557, over 972284.83 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:58:42,924 INFO [train.py:715] (4/8) Epoch 8, batch 34600, loss[loss=0.1394, simple_loss=0.2149, pruned_loss=0.03189, over 4696.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2155, pruned_loss=0.03516, over 972519.82 frames.], batch size: 15, lr: 2.54e-04
2022-05-06 08:59:21,847 INFO [train.py:715] (4/8) Epoch 8, batch 34650, loss[loss=0.1264, simple_loss=0.2014, pruned_loss=0.02573, over 4864.00 frames.], tot_loss[loss=0.1426, simple_loss=0.215, pruned_loss=0.03505, over 973154.81 frames.], batch size: 32, lr: 2.53e-04
2022-05-06 09:00:01,502 INFO [train.py:715] (4/8) Epoch 8, batch 34700, loss[loss=0.1442, simple_loss=0.231, pruned_loss=0.02869, over 4753.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2138, pruned_loss=0.03496, over 973085.79 frames.], batch size: 19, lr: 2.53e-04
2022-05-06 09:00:38,662 INFO [train.py:715] (4/8) Epoch 8, batch 34750, loss[loss=0.1426, simple_loss=0.2216, pruned_loss=0.03183, over 4787.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.03527, over 972451.91 frames.], batch size: 17, lr: 2.53e-04
2022-05-06 09:01:15,265 INFO [train.py:715] (4/8) Epoch 8, batch 34800, loss[loss=0.1432, simple_loss=0.2251, pruned_loss=0.0306, over 4923.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2145, pruned_loss=0.03539, over 972132.02 frames.], batch size: 18, lr: 2.53e-04
2022-05-06 09:02:04,642 INFO [train.py:715] (4/8) Epoch 9, batch 0, loss[loss=0.1438, simple_loss=0.2216, pruned_loss=0.03304, over 4926.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2216, pruned_loss=0.03304, over 4926.00 frames.], batch size: 29, lr: 2.42e-04
2022-05-06 09:02:43,974 INFO [train.py:715] (4/8) Epoch 9, batch 50, loss[loss=0.1114, simple_loss=0.1839, pruned_loss=0.0194, over 4944.00 frames.], tot_loss[loss=0.1479, simple_loss=0.2196, pruned_loss=0.03805, over 220175.90 frames.], batch size: 29, lr: 2.41e-04
2022-05-06 09:03:23,608 INFO [train.py:715] (4/8) Epoch 9, batch 100, loss[loss=0.1386, simple_loss=0.2097, pruned_loss=0.03372, over 4982.00 frames.], tot_loss[loss=0.1471, simple_loss=0.2188, pruned_loss=0.03774, over 387089.38 frames.], batch size: 25, lr: 2.41e-04
2022-05-06 09:04:02,103 INFO [train.py:715] (4/8) Epoch 9, batch 150, loss[loss=0.1487, simple_loss=0.2156, pruned_loss=0.04085, over 4912.00 frames.], tot_loss[loss=0.146, simple_loss=0.2175, pruned_loss=0.03728, over 517515.93 frames.], batch size: 38, lr: 2.41e-04
2022-05-06 09:04:42,540 INFO [train.py:715] (4/8) Epoch 9, batch 200, loss[loss=0.1581, simple_loss=0.229, pruned_loss=0.04356, over 4694.00 frames.], tot_loss[loss=0.1441, simple_loss=0.2164, pruned_loss=0.03587, over 618266.84 frames.], batch size: 15, lr: 2.41e-04
2022-05-06 09:05:21,802 INFO [train.py:715] (4/8) Epoch 9, batch 250, loss[loss=0.1642, simple_loss=0.2388, pruned_loss=0.04482, over 4819.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2153, pruned_loss=0.03509, over 696507.68 frames.], batch size: 27, lr: 2.41e-04
2022-05-06 09:06:01,094 INFO [train.py:715] (4/8) Epoch 9, batch 300, loss[loss=0.1601, simple_loss=0.2371, pruned_loss=0.04155, over 4797.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03508, over 756902.29 frames.], batch size: 21, lr: 2.41e-04
2022-05-06 09:06:40,661 INFO [train.py:715] (4/8) Epoch 9, batch 350, loss[loss=0.1207, simple_loss=0.1913, pruned_loss=0.02509, over 4819.00 frames.], tot_loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.0346, over 804085.10 frames.], batch size: 12, lr: 2.41e-04
2022-05-06 09:07:20,401 INFO [train.py:715] (4/8) Epoch 9, batch 400, loss[loss=0.1454, simple_loss=0.2105, pruned_loss=0.04009, over 4873.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2149, pruned_loss=0.03471, over 842155.06 frames.], batch size: 20, lr: 2.41e-04
2022-05-06 09:07:59,733 INFO [train.py:715] (4/8) Epoch 9, batch 450, loss[loss=0.1207, simple_loss=0.2021, pruned_loss=0.01965, over 4825.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2154, pruned_loss=0.03417, over 870246.45 frames.], batch size: 27, lr: 2.41e-04
2022-05-06 09:08:38,886 INFO [train.py:715] (4/8) Epoch 9, batch 500, loss[loss=0.1351, simple_loss=0.2079, pruned_loss=0.03114, over 4916.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2158, pruned_loss=0.03471, over 892561.80 frames.], batch size: 17, lr: 2.41e-04
2022-05-06 09:09:19,201 INFO [train.py:715] (4/8) Epoch 9, batch 550, loss[loss=0.1542, simple_loss=0.214, pruned_loss=0.04723, over 4967.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2153, pruned_loss=0.03486, over 910625.15 frames.], batch size: 35, lr: 2.41e-04
2022-05-06 09:09:58,809 INFO [train.py:715] (4/8) Epoch 9, batch 600, loss[loss=0.1294, simple_loss=0.2017, pruned_loss=0.02851, over 4951.00 frames.], tot_loss[loss=0.143, simple_loss=0.2156, pruned_loss=0.03518, over 923863.07 frames.], batch size: 24, lr: 2.41e-04
2022-05-06 09:10:37,824 INFO [train.py:715] (4/8) Epoch 9, batch 650, loss[loss=0.1467, simple_loss=0.2243, pruned_loss=0.03451, over 4894.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2152, pruned_loss=0.03501, over 934620.82 frames.], batch size: 19, lr: 2.41e-04
2022-05-06 09:11:16,916 INFO [train.py:715] (4/8) Epoch 9, batch 700, loss[loss=0.1467, simple_loss=0.2226, pruned_loss=0.03545, over 4988.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03502, over 944103.01 frames.], batch size: 25, lr: 2.41e-04
2022-05-06 09:11:56,396 INFO [train.py:715] (4/8) Epoch 9, batch 750, loss[loss=0.1237, simple_loss=0.2039, pruned_loss=0.02175, over 4756.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2149, pruned_loss=0.0344, over 950844.09 frames.], batch size: 19, lr: 2.41e-04
2022-05-06 09:12:35,538 INFO [train.py:715] (4/8) Epoch 9, batch 800, loss[loss=0.1411, simple_loss=0.2239, pruned_loss=0.02918, over 4920.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2145, pruned_loss=0.03437, over 955434.13 frames.], batch size: 23, lr: 2.41e-04
2022-05-06 09:13:14,318 INFO [train.py:715] (4/8) Epoch 9, batch 850, loss[loss=0.14, simple_loss=0.2106, pruned_loss=0.03466, over 4871.00 frames.], tot_loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03411, over 959499.25 frames.], batch size: 20, lr: 2.41e-04
2022-05-06 09:13:53,318 INFO [train.py:715] (4/8) Epoch 9, batch 900, loss[loss=0.1375, simple_loss=0.2099, pruned_loss=0.03258, over 4909.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03446, over 962757.53 frames.], batch size: 39, lr: 2.41e-04
2022-05-06 09:14:32,595 INFO [train.py:715] (4/8) Epoch 9, batch 950, loss[loss=0.1817, simple_loss=0.2501, pruned_loss=0.05667, over 4793.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2142, pruned_loss=0.03464, over 965457.98 frames.], batch size: 18, lr: 2.41e-04
2022-05-06 09:15:12,210 INFO [train.py:715] (4/8) Epoch 9, batch 1000, loss[loss=0.1136, simple_loss=0.1865, pruned_loss=0.02034, over 4865.00 frames.], tot_loss[loss=0.142, simple_loss=0.2145, pruned_loss=0.03473, over 966189.53 frames.], batch size: 20, lr: 2.41e-04
2022-05-06 09:15:50,366 INFO [train.py:715] (4/8) Epoch 9, batch 1050, loss[loss=0.1558, simple_loss=0.2299, pruned_loss=0.04086, over 4923.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2142, pruned_loss=0.03462, over 968568.13 frames.], batch size: 23, lr: 2.41e-04
2022-05-06 09:16:30,509 INFO [train.py:715] (4/8) Epoch 9, batch 1100, loss[loss=0.1467, simple_loss=0.2218, pruned_loss=0.03579, over 4947.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.03471, over 969340.14 frames.], batch size: 21, lr: 2.41e-04
2022-05-06 09:17:10,346 INFO [train.py:715] (4/8) Epoch 9, batch 1150, loss[loss=0.1511, simple_loss=0.2171, pruned_loss=0.04253, over 4916.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2156, pruned_loss=0.03482, over 969414.84 frames.], batch size: 19, lr: 2.41e-04
2022-05-06 09:17:49,484 INFO [train.py:715] (4/8) Epoch 9, batch 1200, loss[loss=0.1483, simple_loss=0.2284, pruned_loss=0.03408, over 4952.00 frames.], tot_loss[loss=0.143, simple_loss=0.2158, pruned_loss=0.03504, over 970232.25 frames.], batch size: 39, lr: 2.41e-04
2022-05-06 09:18:28,818 INFO [train.py:715] (4/8) Epoch 9, batch 1250, loss[loss=0.1357, simple_loss=0.2091, pruned_loss=0.03114, over 4953.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2163, pruned_loss=0.03505, over 971320.82 frames.], batch size: 21, lr: 2.41e-04
2022-05-06 09:19:08,558 INFO [train.py:715] (4/8) Epoch 9, batch 1300, loss[loss=0.1387, simple_loss=0.2173, pruned_loss=0.03005, over 4889.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2157, pruned_loss=0.03484, over 971554.12 frames.], batch size: 19, lr: 2.41e-04
2022-05-06 09:19:48,097 INFO [train.py:715] (4/8) Epoch 9, batch 1350, loss[loss=0.1451, simple_loss=0.2118, pruned_loss=0.03923, over 4803.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2164, pruned_loss=0.0353, over 971384.53 frames.], batch size: 21, lr: 2.41e-04
2022-05-06 09:20:26,896 INFO [train.py:715] (4/8) Epoch 9, batch 1400, loss[loss=0.1456, simple_loss=0.2295, pruned_loss=0.03079, over 4986.00 frames.], tot_loss[loss=0.1443, simple_loss=0.2168, pruned_loss=0.03583, over 971941.36 frames.], batch size: 25, lr: 2.41e-04
2022-05-06 09:21:06,499 INFO [train.py:715] (4/8) Epoch 9, batch 1450, loss[loss=0.1246, simple_loss=0.1967, pruned_loss=0.02621, over 4904.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2153, pruned_loss=0.03501, over 972386.49 frames.], batch size: 18, lr: 2.41e-04
2022-05-06 09:21:45,310 INFO [train.py:715] (4/8) Epoch 9, batch 1500, loss[loss=0.1783, simple_loss=0.2414, pruned_loss=0.05764, over 4960.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2162, pruned_loss=0.03556, over 971984.99 frames.], batch size: 35, lr: 2.41e-04
2022-05-06 09:22:24,144 INFO [train.py:715] (4/8) Epoch 9, batch 1550, loss[loss=0.1135, simple_loss=0.1828, pruned_loss=0.02208, over 4747.00 frames.], tot_loss[loss=0.1435, simple_loss=0.216, pruned_loss=0.03551, over 971088.22 frames.], batch size: 16, lr: 2.41e-04
2022-05-06 09:23:03,175 INFO [train.py:715] (4/8) Epoch 9, batch 1600, loss[loss=0.1282, simple_loss=0.2021, pruned_loss=0.02712, over 4978.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2163, pruned_loss=0.03558, over 972122.42 frames.], batch size: 14, lr: 2.41e-04
2022-05-06 09:23:42,083 INFO [train.py:715] (4/8) Epoch 9, batch 1650, loss[loss=0.1452, simple_loss=0.2095, pruned_loss=0.04041, over 4969.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2157, pruned_loss=0.03496, over 973747.95 frames.], batch size: 35, lr: 2.41e-04
2022-05-06 09:24:21,072 INFO [train.py:715] (4/8) Epoch 9, batch 1700, loss[loss=0.1556, simple_loss=0.2397, pruned_loss=0.03575, over 4815.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2159, pruned_loss=0.03537, over 973547.65 frames.], batch size: 13, lr: 2.41e-04
2022-05-06 09:25:00,144 INFO [train.py:715] (4/8) Epoch 9, batch 1750, loss[loss=0.1257, simple_loss=0.1964, pruned_loss=0.02753, over 4885.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2158, pruned_loss=0.03544, over 972340.39 frames.], batch size: 32, lr: 2.41e-04
2022-05-06 09:25:39,672 INFO [train.py:715] (4/8) Epoch 9, batch 1800, loss[loss=0.1528, simple_loss=0.2159, pruned_loss=0.04487, over 4906.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2153, pruned_loss=0.03521, over 971641.96 frames.], batch size: 29, lr: 2.41e-04
2022-05-06 09:26:18,853 INFO [train.py:715] (4/8) Epoch 9, batch 1850, loss[loss=0.1491, simple_loss=0.2264, pruned_loss=0.03594, over 4964.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2157, pruned_loss=0.03533, over 971786.27 frames.], batch size: 24, lr: 2.41e-04
2022-05-06 09:26:57,982 INFO [train.py:715] (4/8) Epoch 9, batch 1900, loss[loss=0.1352, simple_loss=0.2145, pruned_loss=0.02798, over 4872.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03477, over 972184.57 frames.], batch size: 22, lr: 2.41e-04
2022-05-06 09:27:38,006 INFO [train.py:715] (4/8) Epoch 9, batch 1950, loss[loss=0.1435, simple_loss=0.2174, pruned_loss=0.03486, over 4889.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2145, pruned_loss=0.03508, over 972962.47 frames.], batch size: 16, lr: 2.41e-04
2022-05-06 09:28:17,647 INFO [train.py:715] (4/8) Epoch 9, batch 2000, loss[loss=0.1529, simple_loss=0.222, pruned_loss=0.04187, over 4922.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03502, over 974123.83 frames.], batch size: 18, lr: 2.41e-04
2022-05-06 09:28:56,801 INFO [train.py:715] (4/8) Epoch 9, batch 2050, loss[loss=0.1312, simple_loss=0.1982, pruned_loss=0.03214, over 4758.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2156, pruned_loss=0.03548, over 973393.14 frames.], batch size: 19, lr: 2.41e-04
2022-05-06 09:29:35,326 INFO [train.py:715] (4/8) Epoch 9, batch 2100, loss[loss=0.147, simple_loss=0.233, pruned_loss=0.03048, over 4801.00 frames.], tot_loss[loss=0.1435, simple_loss=0.2156, pruned_loss=0.03573, over 973026.77 frames.], batch size: 21, lr: 2.41e-04
2022-05-06 09:30:14,644 INFO [train.py:715] (4/8) Epoch 9, batch 2150, loss[loss=0.121, simple_loss=0.195, pruned_loss=0.02349, over 4876.00 frames.], tot_loss[loss=0.1433, simple_loss=0.216, pruned_loss=0.03536, over 972984.28 frames.], batch size: 22, lr: 2.41e-04
2022-05-06 09:30:53,733 INFO [train.py:715] (4/8) Epoch 9, batch 2200, loss[loss=0.1321, simple_loss=0.1956, pruned_loss=0.03432, over 4762.00 frames.], tot_loss[loss=0.143, simple_loss=0.2158, pruned_loss=0.03511, over 973129.14 frames.], batch size: 19, lr: 2.41e-04
2022-05-06 09:31:32,489 INFO [train.py:715] (4/8) Epoch 9, batch 2250, loss[loss=0.13, simple_loss=0.2106, pruned_loss=0.02471, over 4953.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2148, pruned_loss=0.0348, over 973066.00 frames.], batch size: 24, lr: 2.41e-04
2022-05-06 09:32:11,658 INFO [train.py:715] (4/8) Epoch 9, batch 2300, loss[loss=0.1229, simple_loss=0.2075, pruned_loss=0.01911, over 4898.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.03434, over 972578.75 frames.], batch size: 19, lr: 2.41e-04
2022-05-06 09:32:50,736 INFO [train.py:715] (4/8) Epoch 9, batch 2350, loss[loss=0.1726, simple_loss=0.2375, pruned_loss=0.05388, over 4796.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03414, over 972066.97 frames.], batch size: 24, lr: 2.41e-04
2022-05-06 09:33:30,100 INFO [train.py:715] (4/8) Epoch 9, batch 2400, loss[loss=0.14, simple_loss=0.2093, pruned_loss=0.03539, over 4875.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03423, over 972057.03 frames.], batch size: 20, lr: 2.41e-04
2022-05-06 09:34:08,886 INFO [train.py:715] (4/8) Epoch 9, batch 2450, loss[loss=0.1573, simple_loss=0.2253, pruned_loss=0.0447, over 4891.00 frames.], tot_loss[loss=0.1407, simple_loss=0.213, pruned_loss=0.03423, over 971305.14 frames.], batch size: 19, lr: 2.41e-04
2022-05-06 09:34:48,500 INFO [train.py:715] (4/8) Epoch 9, batch 2500, loss[loss=0.1283, simple_loss=0.2027, pruned_loss=0.02692, over 4711.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03457, over 971789.35 frames.], batch size: 15, lr: 2.41e-04
2022-05-06 09:35:27,019 INFO [train.py:715] (4/8) Epoch 9, batch 2550, loss[loss=0.1228, simple_loss=0.1895, pruned_loss=0.02808, over 4983.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2131, pruned_loss=0.03449, over 972634.11 frames.], batch size: 14, lr: 2.41e-04
2022-05-06 09:36:06,039 INFO [train.py:715] (4/8) Epoch 9, batch 2600, loss[loss=0.1669, simple_loss=0.2408, pruned_loss=0.04653, over 4910.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2143, pruned_loss=0.03535, over 973537.05 frames.], batch size: 39, lr: 2.41e-04
2022-05-06 09:36:45,108 INFO [train.py:715] (4/8) Epoch 9, batch 2650, loss[loss=0.1235, simple_loss=0.1982, pruned_loss=0.0244, over 4987.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2138, pruned_loss=0.03532, over 972380.29 frames.], batch size: 14, lr: 2.41e-04
2022-05-06 09:37:24,473 INFO [train.py:715] (4/8) Epoch 9, batch 2700, loss[loss=0.1308, simple_loss=0.2019, pruned_loss=0.0298, over 4770.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2137, pruned_loss=0.03493, over 972588.56 frames.], batch size: 19, lr: 2.40e-04
2022-05-06 09:38:03,293 INFO [train.py:715] (4/8) Epoch 9, batch 2750, loss[loss=0.1274, simple_loss=0.1998, pruned_loss=0.02749, over 4745.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2144, pruned_loss=0.03516, over 973077.49 frames.], batch size: 16, lr: 2.40e-04
2022-05-06 09:38:42,263 INFO [train.py:715] (4/8) Epoch 9, batch 2800, loss[loss=0.1317, simple_loss=0.201, pruned_loss=0.03119, over 4839.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03479, over 972993.17 frames.], batch size: 30, lr: 2.40e-04
2022-05-06 09:39:21,839 INFO [train.py:715] (4/8) Epoch 9, batch 2850, loss[loss=0.1255, simple_loss=0.2011, pruned_loss=0.02494, over 4766.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2139, pruned_loss=0.03419, over 972301.40 frames.], batch size: 12, lr: 2.40e-04
2022-05-06 09:40:00,913 INFO [train.py:715] (4/8) Epoch 9, batch 2900, loss[loss=0.1205, simple_loss=0.1826, pruned_loss=0.0292, over 4757.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.03464, over 971541.66 frames.], batch size: 12, lr: 2.40e-04
2022-05-06 09:40:39,676 INFO [train.py:715] (4/8) Epoch 9, batch 2950, loss[loss=0.1669, simple_loss=0.2399, pruned_loss=0.04691, over 4857.00 frames.], tot_loss[loss=0.1417, simple_loss=0.214, pruned_loss=0.03468, over 972211.06 frames.], batch size: 20, lr: 2.40e-04
2022-05-06 09:41:18,902 INFO [train.py:715] (4/8) Epoch 9, batch 3000, loss[loss=0.1206, simple_loss=0.1925, pruned_loss=0.02436, over 4777.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2151, pruned_loss=0.03535, over 972688.37 frames.], batch size: 18, lr: 2.40e-04
2022-05-06 09:41:18,903 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 09:41:28,534 INFO [train.py:742] (4/8) Epoch 9, validation: loss=0.1069, simple_loss=0.1915, pruned_loss=0.01118, over 914524.00 frames.
2022-05-06 09:42:08,252 INFO [train.py:715] (4/8) Epoch 9, batch 3050, loss[loss=0.1315, simple_loss=0.1914, pruned_loss=0.03584, over 4826.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2148, pruned_loss=0.03498, over 971381.14 frames.], batch size: 15, lr: 2.40e-04
2022-05-06 09:42:47,735 INFO [train.py:715] (4/8) Epoch 9, batch 3100, loss[loss=0.1467, simple_loss=0.2255, pruned_loss=0.03396, over 4834.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.0349, over 971783.40 frames.], batch size: 15, lr: 2.40e-04
2022-05-06 09:43:27,212 INFO [train.py:715] (4/8) Epoch 9, batch 3150, loss[loss=0.1577, simple_loss=0.2298, pruned_loss=0.04276, over 4772.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2152, pruned_loss=0.03561, over 972127.61 frames.], batch size: 17, lr: 2.40e-04
2022-05-06 09:44:06,425 INFO [train.py:715] (4/8) Epoch 9, batch 3200, loss[loss=0.1438, simple_loss=0.2232, pruned_loss=0.0322, over 4784.00 frames.], tot_loss[loss=0.143, simple_loss=0.2151, pruned_loss=0.0355, over 971350.74 frames.], batch size: 18, lr: 2.40e-04
2022-05-06 09:44:45,580 INFO [train.py:715] (4/8) Epoch 9, batch 3250, loss[loss=0.1537, simple_loss=0.2218, pruned_loss=0.04276, over 4794.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2159, pruned_loss=0.03581, over 971767.33 frames.], batch size: 17, lr: 2.40e-04
2022-05-06 09:45:24,838 INFO [train.py:715] (4/8) Epoch 9, batch 3300, loss[loss=0.1293, simple_loss=0.2001, pruned_loss=0.02928, over 4940.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2152, pruned_loss=0.03484, over 971832.99 frames.], batch size: 23, lr: 2.40e-04
2022-05-06 09:46:03,661 INFO [train.py:715] (4/8) Epoch 9, batch 3350, loss[loss=0.1437, simple_loss=0.2255, pruned_loss=0.03096, over 4801.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2155, pruned_loss=0.03492, over 971713.21 frames.], batch size: 24, lr: 2.40e-04
2022-05-06 09:46:42,983 INFO [train.py:715] (4/8) Epoch 9, batch 3400, loss[loss=0.1589, simple_loss=0.2223, pruned_loss=0.04773, over 4918.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2156, pruned_loss=0.03514, over 972431.31 frames.], batch size: 39, lr: 2.40e-04
2022-05-06 09:47:22,073 INFO [train.py:715] (4/8) Epoch 9, batch 3450, loss[loss=0.1146, simple_loss=0.1848, pruned_loss=0.0222, over 4952.00 frames.], tot_loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03537, over 971801.64 frames.], batch size: 29, lr: 2.40e-04
2022-05-06 09:48:00,725 INFO [train.py:715] (4/8) Epoch 9, batch 3500, loss[loss=0.1663, simple_loss=0.226, pruned_loss=0.05334, over 4847.00 frames.], tot_loss[loss=0.1431, simple_loss=0.216, pruned_loss=0.03514, over 971332.40 frames.], batch size: 20, lr: 2.40e-04
2022-05-06 09:48:40,283 INFO [train.py:715] (4/8) Epoch 9, batch 3550, loss[loss=0.1272, simple_loss=0.2016, pruned_loss=0.02636, over 4809.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2158, pruned_loss=0.03515, over 971389.83 frames.], batch size: 13, lr: 2.40e-04
2022-05-06 09:49:19,723 INFO [train.py:715] (4/8) Epoch 9, batch 3600, loss[loss=0.1589, simple_loss=0.2298, pruned_loss=0.04393, over 4768.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2151, pruned_loss=0.03538, over 971384.74 frames.], batch size: 14, lr: 2.40e-04
2022-05-06 09:49:59,014 INFO [train.py:715] (4/8) Epoch 9, batch 3650, loss[loss=0.1672, simple_loss=0.2463, pruned_loss=0.04408, over 4878.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03483, over 971767.13 frames.], batch size: 22, lr: 2.40e-04
2022-05-06 09:50:37,658 INFO [train.py:715] (4/8) Epoch 9, batch 3700, loss[loss=0.1464, simple_loss=0.2254, pruned_loss=0.03371, over 4881.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.03513, over 971442.92 frames.], batch size: 16, lr: 2.40e-04
2022-05-06 09:51:17,144 INFO [train.py:715] (4/8) Epoch 9, batch 3750, loss[loss=0.1476, simple_loss=0.2204, pruned_loss=0.03738, over 4813.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2152, pruned_loss=0.03512, over 971208.32 frames.], batch size: 25, lr: 2.40e-04
2022-05-06 09:51:56,918 INFO [train.py:715] (4/8) Epoch 9, batch 3800, loss[loss=0.1444, simple_loss=0.2122, pruned_loss=0.03832, over 4793.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2146, pruned_loss=0.03499, over 971618.29 frames.], batch size: 17, lr: 2.40e-04
2022-05-06 09:52:35,336 INFO [train.py:715] (4/8) Epoch 9, batch 3850, loss[loss=0.1768, simple_loss=0.2443, pruned_loss=0.05465, over 4903.00 frames.], tot_loss[loss=0.1428, simple_loss=0.215, pruned_loss=0.03533, over 971616.30 frames.], batch size: 17, lr: 2.40e-04
2022-05-06 09:53:14,339 INFO [train.py:715] (4/8) Epoch 9, batch 3900, loss[loss=0.1597, simple_loss=0.2376, pruned_loss=0.0409, over 4695.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2158, pruned_loss=0.03522, over 972105.17 frames.], batch size: 15, lr: 2.40e-04
2022-05-06 09:53:53,826 INFO [train.py:715] (4/8) Epoch 9, batch 3950, loss[loss=0.1357, simple_loss=0.2065, pruned_loss=0.03247, over 4828.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2159, pruned_loss=0.03493, over 971132.77 frames.], batch size: 27, lr: 2.40e-04
2022-05-06 09:54:33,403 INFO [train.py:715] (4/8) Epoch 9, batch 4000, loss[loss=0.1269, simple_loss=0.2035, pruned_loss=0.02518, over 4790.00 frames.], tot_loss[loss=0.1426, simple_loss=0.215, pruned_loss=0.03509, over 970975.04 frames.], batch size: 24, lr: 2.40e-04
2022-05-06 09:55:12,123 INFO [train.py:715] (4/8) Epoch 9, batch 4050, loss[loss=0.1533, simple_loss=0.2233, pruned_loss=0.04168, over 4701.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2149, pruned_loss=0.0352, over 970153.20 frames.], batch size: 15, lr: 2.40e-04
2022-05-06 09:55:52,120 INFO [train.py:715] (4/8) Epoch 9, batch 4100, loss[loss=0.1271, simple_loss=0.2087, pruned_loss=0.02272, over 4962.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2138, pruned_loss=0.03463, over 970936.11 frames.], batch size: 24, lr: 2.40e-04
2022-05-06 09:56:30,804 INFO [train.py:715] (4/8) Epoch 9, batch 4150, loss[loss=0.1293, simple_loss=0.1969, pruned_loss=0.03086, over 4967.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03425, over 970903.11 frames.], batch size: 25, lr: 2.40e-04
2022-05-06 09:57:10,158 INFO [train.py:715] (4/8) Epoch 9, batch 4200, loss[loss=0.1423, simple_loss=0.22, pruned_loss=0.03232, over 4879.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2136, pruned_loss=0.03452, over 971565.79 frames.], batch size: 16, lr: 2.40e-04
2022-05-06 09:57:49,720 INFO [train.py:715] (4/8) Epoch 9, batch 4250, loss[loss=0.1169, simple_loss=0.1934, pruned_loss=0.02025, over 4747.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2141, pruned_loss=0.03518, over 970369.60 frames.], batch size: 12, lr: 2.40e-04
2022-05-06 09:58:29,617 INFO [train.py:715] (4/8) Epoch 9, batch 4300, loss[loss=0.1304, simple_loss=0.1982, pruned_loss=0.03129, over 4992.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2144, pruned_loss=0.03531, over 970573.70 frames.], batch size: 14, lr: 2.40e-04
2022-05-06 09:59:09,597 INFO [train.py:715] (4/8) Epoch 9, batch 4350, loss[loss=0.141, simple_loss=0.2151, pruned_loss=0.03349, over 4806.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2151, pruned_loss=0.03554, over 971473.98 frames.], batch size: 21, lr: 2.40e-04
2022-05-06 09:59:48,191 INFO [train.py:715] (4/8) Epoch 9, batch 4400, loss[loss=0.1253, simple_loss=0.2055, pruned_loss=0.02253, over 4933.00 frames.], tot_loss[loss=0.143, simple_loss=0.215, pruned_loss=0.03547, over 972271.86 frames.], batch size: 23, lr: 2.40e-04
2022-05-06 10:00:27,688 INFO [train.py:715] (4/8) Epoch 9, batch 4450, loss[loss=0.1727, simple_loss=0.2518, pruned_loss=0.04675, over 4920.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2147, pruned_loss=0.03539, over 972720.48 frames.], batch size: 17, lr: 2.40e-04
2022-05-06 10:01:06,477 INFO [train.py:715] (4/8) Epoch 9, batch 4500, loss[loss=0.1342, simple_loss=0.1967, pruned_loss=0.03586, over 4904.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2149, pruned_loss=0.03531, over 972624.97 frames.], batch size: 17, lr: 2.40e-04
2022-05-06 10:01:45,449 INFO [train.py:715] (4/8) Epoch 9, batch 4550, loss[loss=0.1443, simple_loss=0.2093, pruned_loss=0.03961, over 4977.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03501, over 972430.94 frames.], batch size: 28, lr: 2.40e-04
2022-05-06 10:02:24,724 INFO [train.py:715] (4/8) Epoch 9, batch 4600, loss[loss=0.1085, simple_loss=0.1817, pruned_loss=0.01764, over 4983.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.0349, over 972844.68 frames.], batch size: 24, lr: 2.40e-04
2022-05-06 10:03:04,291 INFO [train.py:715] (4/8) Epoch 9, batch 4650, loss[loss=0.1563, simple_loss=0.2234, pruned_loss=0.04454, over 4810.00 frames.], tot_loss[loss=0.142, simple_loss=0.2142, pruned_loss=0.03488, over 971835.11 frames.], batch size: 21, lr: 2.40e-04
2022-05-06 10:03:43,900 INFO [train.py:715] (4/8) Epoch 9, batch 4700, loss[loss=0.1678, simple_loss=0.2466, pruned_loss=0.04448, over 4894.00 frames.], tot_loss[loss=0.143, simple_loss=0.2157, pruned_loss=0.03516, over 972172.27 frames.], batch size: 19, lr: 2.40e-04
2022-05-06 10:04:22,846 INFO [train.py:715] (4/8) Epoch 9, batch 4750, loss[loss=0.1341, simple_loss=0.2048, pruned_loss=0.03175, over 4915.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2155, pruned_loss=0.03508, over 971858.10 frames.], batch size: 19, lr: 2.40e-04
2022-05-06 10:05:02,420 INFO [train.py:715] (4/8) Epoch 9, batch 4800, loss[loss=0.1164, simple_loss=0.2015, pruned_loss=0.01569, over 4979.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2151, pruned_loss=0.03479, over 972327.70 frames.], batch size: 25, lr: 2.40e-04
2022-05-06 10:05:41,421 INFO [train.py:715] (4/8) Epoch 9, batch 4850, loss[loss=0.2056, simple_loss=0.2738, pruned_loss=0.06863, over 4743.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2152, pruned_loss=0.03494, over 972885.02 frames.], batch size: 16, lr: 2.40e-04
2022-05-06 10:06:20,852 INFO [train.py:715] (4/8) Epoch 9, batch 4900, loss[loss=0.1619, simple_loss=0.2353, pruned_loss=0.04426, over 4767.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2153, pruned_loss=0.03508, over 972531.35 frames.], batch size: 19, lr: 2.40e-04
2022-05-06 10:06:59,743 INFO [train.py:715] (4/8) Epoch 9, batch 4950, loss[loss=0.1282, simple_loss=0.2077, pruned_loss=0.02439, over 4783.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2151, pruned_loss=0.03488, over 972765.44 frames.], batch size: 14, lr: 2.40e-04
2022-05-06 10:07:39,114 INFO [train.py:715] (4/8) Epoch 9, batch 5000, loss[loss=0.1266, simple_loss=0.1895, pruned_loss=0.03181, over 4982.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2152, pruned_loss=0.03507, over 972953.10 frames.], batch size: 35, lr: 2.40e-04
2022-05-06 10:08:18,415 INFO [train.py:715] (4/8) Epoch 9, batch 5050, loss[loss=0.1634, simple_loss=0.2289, pruned_loss=0.04891, over 4861.00 frames.], tot_loss[loss=0.143, simple_loss=0.2157, pruned_loss=0.03518, over 972870.57 frames.], batch size: 32, lr: 2.40e-04
2022-05-06 10:08:57,171 INFO [train.py:715] (4/8) Epoch 9, batch 5100, loss[loss=0.1436, simple_loss=0.2157, pruned_loss=0.03573, over 4899.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2157, pruned_loss=0.03503, over 973085.89 frames.], batch size: 17, lr: 2.40e-04
2022-05-06 10:09:36,559 INFO [train.py:715] (4/8) Epoch 9, batch 5150, loss[loss=0.1337, simple_loss=0.2155, pruned_loss=0.0259, over 4934.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2152, pruned_loss=0.03487, over 973604.47 frames.], batch size: 21, lr: 2.40e-04
2022-05-06 10:10:15,463 INFO [train.py:715] (4/8) Epoch 9, batch 5200, loss[loss=0.1178, simple_loss=0.1843, pruned_loss=0.02566, over 4936.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2148, pruned_loss=0.03483, over 973971.41 frames.], batch size: 18, lr: 2.40e-04
2022-05-06 10:10:54,748 INFO [train.py:715] (4/8) Epoch 9, batch 5250, loss[loss=0.146, simple_loss=0.2225, pruned_loss=0.03474, over 4878.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2142, pruned_loss=0.0347, over 972668.13 frames.], batch size: 38, lr: 2.40e-04
2022-05-06 10:11:33,954 INFO [train.py:715] (4/8) Epoch 9, batch 5300, loss[loss=0.1741, simple_loss=0.2436, pruned_loss=0.05232, over 4968.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03446, over 972244.72 frames.], batch size: 35, lr: 2.39e-04
2022-05-06 10:12:13,443 INFO [train.py:715] (4/8) Epoch 9, batch 5350, loss[loss=0.1494, simple_loss=0.2188, pruned_loss=0.03996, over 4821.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2146, pruned_loss=0.03449, over 973105.06 frames.], batch size: 26, lr: 2.39e-04
2022-05-06 10:12:52,102 INFO [train.py:715] (4/8) Epoch 9, batch 5400, loss[loss=0.1677, simple_loss=0.2321, pruned_loss=0.05163, over 4979.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2152, pruned_loss=0.03492, over 972440.87 frames.], batch size: 15, lr: 2.39e-04
2022-05-06 10:13:30,897 INFO [train.py:715] (4/8) Epoch 9, batch 5450, loss[loss=0.1316, simple_loss=0.2108, pruned_loss=0.02616, over 4924.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2148, pruned_loss=0.03498, over 972984.40 frames.], batch size: 23, lr: 2.39e-04
2022-05-06 10:14:10,209 INFO [train.py:715] (4/8) Epoch 9, batch 5500, loss[loss=0.1278, simple_loss=0.2067, pruned_loss=0.02444, over 4977.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.03488, over 972805.71 frames.], batch size: 28, lr: 2.39e-04
2022-05-06 10:14:49,295 INFO [train.py:715] (4/8) Epoch 9, batch 5550, loss[loss=0.1416, simple_loss=0.2156, pruned_loss=0.03383, over 4970.00 frames.], tot_loss[loss=0.142, simple_loss=0.2144, pruned_loss=0.03481, over 973047.77 frames.], batch size: 24, lr: 2.39e-04
2022-05-06 10:15:28,464 INFO [train.py:715] (4/8) Epoch 9, batch 5600, loss[loss=0.1333, simple_loss=0.2041, pruned_loss=0.03125, over 4937.00 frames.], tot_loss[loss=0.1407, simple_loss=0.213, pruned_loss=0.03417, over 973495.38 frames.], batch size: 29, lr: 2.39e-04
2022-05-06 10:16:07,456 INFO [train.py:715] (4/8) Epoch 9, batch 5650, loss[loss=0.1368, simple_loss=0.2149, pruned_loss=0.02935, over 4895.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2132, pruned_loss=0.03448, over 972733.89 frames.], batch size: 19, lr: 2.39e-04
2022-05-06 10:16:47,095 INFO [train.py:715] (4/8) Epoch 9, batch 5700, loss[loss=0.188, simple_loss=0.2541, pruned_loss=0.0609, over 4876.00 frames.], tot_loss[loss=0.1417, simple_loss=0.214, pruned_loss=0.03474, over 972183.54 frames.], batch size: 16, lr: 2.39e-04
2022-05-06 10:17:26,139 INFO [train.py:715] (4/8) Epoch 9, batch 5750, loss[loss=0.131, simple_loss=0.2052, pruned_loss=0.0284, over 4854.00 frames.], tot_loss[loss=0.141, simple_loss=0.2133, pruned_loss=0.03435, over 972776.55 frames.], batch size: 20, lr: 2.39e-04
2022-05-06 10:18:04,785 INFO [train.py:715] (4/8) Epoch 9, batch 5800, loss[loss=0.1202, simple_loss=0.2005, pruned_loss=0.01995, over 4871.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2142, pruned_loss=0.03512, over 972595.52 frames.], batch size: 20, lr: 2.39e-04
2022-05-06 10:18:44,316 INFO [train.py:715] (4/8) Epoch 9, batch 5850, loss[loss=0.1469, simple_loss=0.2136, pruned_loss=0.04013, over 4746.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2145, pruned_loss=0.03512, over 972776.72 frames.], batch size: 16, lr: 2.39e-04
2022-05-06 10:19:23,126 INFO [train.py:715] (4/8) Epoch 9, batch 5900, loss[loss=0.1572, simple_loss=0.2345, pruned_loss=0.03989, over 4778.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2136, pruned_loss=0.03496, over 972435.21 frames.], batch size: 19, lr: 2.39e-04
2022-05-06 10:20:02,777 INFO [train.py:715] (4/8) Epoch 9, batch 5950, loss[loss=0.1585, simple_loss=0.2325, pruned_loss=0.04231, over 4894.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2134, pruned_loss=0.03474, over 972630.15 frames.], batch size: 19, lr: 2.39e-04
2022-05-06 10:20:41,533 INFO [train.py:715] (4/8) Epoch 9, batch 6000, loss[loss=0.1293, simple_loss=0.1957, pruned_loss=0.03142, over 4828.00 frames.], tot_loss[loss=0.1408, simple_loss=0.213, pruned_loss=0.03426, over 971731.39 frames.], batch size: 26, lr: 2.39e-04
2022-05-06 10:20:41,534 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 10:20:51,192 INFO [train.py:742] (4/8) Epoch 9, validation: loss=0.107, simple_loss=0.1914, pruned_loss=0.0113, over 914524.00 frames.
2022-05-06 10:21:30,882 INFO [train.py:715] (4/8) Epoch 9, batch 6050, loss[loss=0.1323, simple_loss=0.2094, pruned_loss=0.02765, over 4809.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2144, pruned_loss=0.03495, over 971839.50 frames.], batch size: 21, lr: 2.39e-04
2022-05-06 10:22:10,753 INFO [train.py:715] (4/8) Epoch 9, batch 6100, loss[loss=0.1383, simple_loss=0.2067, pruned_loss=0.03497, over 4905.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2142, pruned_loss=0.03462, over 971613.63 frames.], batch size: 19, lr: 2.39e-04
2022-05-06 10:22:49,972 INFO [train.py:715] (4/8) Epoch 9, batch 6150, loss[loss=0.1514, simple_loss=0.2211, pruned_loss=0.04088, over 4781.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03461, over 971316.69 frames.], batch size: 17, lr: 2.39e-04
2022-05-06 10:23:28,785 INFO [train.py:715] (4/8) Epoch 9, batch 6200, loss[loss=0.1119, simple_loss=0.1854, pruned_loss=0.01916, over 4827.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.0342, over 971514.81 frames.], batch size: 15, lr: 2.39e-04
2022-05-06 10:24:08,419 INFO [train.py:715] (4/8) Epoch 9, batch 6250, loss[loss=0.1325, simple_loss=0.2009, pruned_loss=0.03202, over 4788.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2127, pruned_loss=0.03397, over 971736.11 frames.], batch size: 14, lr: 2.39e-04
2022-05-06 10:24:47,200 INFO [train.py:715] (4/8) Epoch 9, batch 6300, loss[loss=0.1368, simple_loss=0.2118, pruned_loss=0.03089, over 4900.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2132, pruned_loss=0.03477, over 971946.44 frames.], batch size: 17, lr: 2.39e-04
2022-05-06 10:25:26,319 INFO [train.py:715] (4/8) Epoch 9, batch 6350, loss[loss=0.1522, simple_loss=0.2131, pruned_loss=0.0456, over 4956.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2138, pruned_loss=0.03463, over 972960.12 frames.], batch size: 35, lr: 2.39e-04
2022-05-06 10:26:05,951 INFO [train.py:715] (4/8) Epoch 9, batch 6400, loss[loss=0.137, simple_loss=0.2143, pruned_loss=0.0298, over 4798.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.03484, over 973023.33 frames.], batch size: 21, lr: 2.39e-04
2022-05-06 10:26:46,099 INFO [train.py:715] (4/8) Epoch 9, batch 6450, loss[loss=0.1201, simple_loss=0.1999, pruned_loss=0.02013, over 4945.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2141, pruned_loss=0.03434, over 972823.14 frames.], batch size: 21, lr: 2.39e-04
2022-05-06 10:27:25,423 INFO [train.py:715] (4/8) Epoch 9, batch 6500, loss[loss=0.1474, simple_loss=0.2181, pruned_loss=0.0383, over 4911.00 frames.], tot_loss[loss=0.141, simple_loss=0.2134, pruned_loss=0.03427, over 972857.78 frames.], batch size: 19, lr: 2.39e-04
2022-05-06 10:28:04,256 INFO [train.py:715] (4/8) Epoch 9, batch 6550, loss[loss=0.151, simple_loss=0.2193, pruned_loss=0.04131, over 4818.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2131, pruned_loss=0.034, over 971745.42 frames.], batch size: 15, lr: 2.39e-04
2022-05-06 10:28:44,036 INFO [train.py:715] (4/8) Epoch 9, batch 6600, loss[loss=0.1311, simple_loss=0.2148, pruned_loss=0.02364, over 4983.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2138, pruned_loss=0.03468, over 972035.93 frames.], batch size: 14, lr: 2.39e-04
2022-05-06 10:29:23,595 INFO [train.py:715] (4/8) Epoch 9, batch 6650, loss[loss=0.1427, simple_loss=0.2163, pruned_loss=0.03453, over 4829.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2131, pruned_loss=0.03456, over 971668.46 frames.], batch size: 12, lr: 2.39e-04
2022-05-06 10:30:02,749 INFO [train.py:715] (4/8) Epoch 9, batch 6700, loss[loss=0.164, simple_loss=0.2369, pruned_loss=0.04551, over 4836.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2129, pruned_loss=0.03433, over 971264.11 frames.], batch size: 25, lr: 2.39e-04
2022-05-06 10:30:44,171 INFO [train.py:715] (4/8) Epoch 9, batch 6750, loss[loss=0.1398, simple_loss=0.2123, pruned_loss=0.03367, over 4847.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2132, pruned_loss=0.03469, over 971550.22 frames.], batch size: 20, lr: 2.39e-04
2022-05-06 10:31:23,603 INFO [train.py:715] (4/8) Epoch 9, batch 6800, loss[loss=0.1374, simple_loss=0.2076, pruned_loss=0.03364, over 4837.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2129, pruned_loss=0.03414, over 971387.55 frames.], batch size: 30, lr: 2.39e-04
2022-05-06 10:32:02,562 INFO [train.py:715] (4/8) Epoch 9, batch 6850, loss[loss=0.1213, simple_loss=0.2005, pruned_loss=0.02102, over 4855.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2139, pruned_loss=0.03463, over 971958.59 frames.], batch size: 20, lr: 2.39e-04
2022-05-06 10:32:40,754 INFO [train.py:715] (4/8) Epoch 9, batch 6900, loss[loss=0.1413, simple_loss=0.2126, pruned_loss=0.03493, over 4962.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2141, pruned_loss=0.03451, over 972176.71 frames.], batch size: 35, lr: 2.39e-04
2022-05-06 10:33:20,060 INFO [train.py:715] (4/8) Epoch 9, batch 6950, loss[loss=0.1202, simple_loss=0.1926, pruned_loss=0.02384, over 4811.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03482, over 971195.35 frames.], batch size: 21, lr: 2.39e-04
2022-05-06 10:33:59,864 INFO [train.py:715] (4/8) Epoch 9, batch 7000, loss[loss=0.1646, simple_loss=0.2281, pruned_loss=0.05052, over 4961.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.03497, over 971686.43 frames.], batch size: 15, lr: 2.39e-04
2022-05-06 10:34:38,728 INFO [train.py:715] (4/8) Epoch 9, batch 7050, loss[loss=0.1432, simple_loss=0.2186, pruned_loss=0.03394, over 4798.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2142, pruned_loss=0.03512, over 971892.94 frames.], batch size: 21, lr: 2.39e-04
2022-05-06 10:35:17,347 INFO [train.py:715] (4/8) Epoch 9, batch 7100, loss[loss=0.1537, simple_loss=0.2227, pruned_loss=0.04237, over 4898.00 frames.], tot_loss[loss=0.143, simple_loss=0.2148, pruned_loss=0.03555, over 971270.03 frames.], batch size: 39, lr: 2.39e-04
2022-05-06 10:35:56,809 INFO [train.py:715] (4/8) Epoch 9, batch 7150, loss[loss=0.1454, simple_loss=0.2109, pruned_loss=0.03995, over 4989.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2138, pruned_loss=0.03486, over 971790.21 frames.], batch size: 25, lr: 2.39e-04
2022-05-06 10:36:35,505 INFO [train.py:715] (4/8) Epoch 9, batch 7200, loss[loss=0.1096, simple_loss=0.186, pruned_loss=0.01663, over 4797.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2139, pruned_loss=0.03474, over 971848.80 frames.], batch size: 12, lr: 2.39e-04
2022-05-06 10:37:14,247 INFO [train.py:715] (4/8) Epoch 9, batch 7250, loss[loss=0.2004, simple_loss=0.2676, pruned_loss=0.06658, over 4879.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.03445, over 971904.26 frames.], batch size: 32, lr: 2.39e-04
2022-05-06 10:37:53,495 INFO [train.py:715] (4/8) Epoch 9, batch 7300, loss[loss=0.1696, simple_loss=0.2363, pruned_loss=0.05142, over 4786.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2152, pruned_loss=0.03492, over 971808.73 frames.], batch size: 14, lr: 2.39e-04
2022-05-06 10:38:32,800 INFO [train.py:715] (4/8) Epoch 9, batch 7350, loss[loss=0.1371, simple_loss=0.2122, pruned_loss=0.03099, over 4988.00 frames.], tot_loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.0348, over 971395.61 frames.], batch size: 25, lr: 2.39e-04
2022-05-06 10:39:11,300 INFO [train.py:715] (4/8) Epoch 9, batch 7400, loss[loss=0.1162, simple_loss=0.1875, pruned_loss=0.02245, over 4760.00 frames.], tot_loss[loss=0.1415, simple_loss=0.214, pruned_loss=0.03452, over 971663.35 frames.], batch size: 18, lr: 2.39e-04
2022-05-06 10:39:50,257 INFO [train.py:715] (4/8) Epoch 9, batch 7450, loss[loss=0.1461, simple_loss=0.2194, pruned_loss=0.03639, over 4822.00 frames.], tot_loss[loss=0.142, simple_loss=0.2146, pruned_loss=0.03472, over 971537.18 frames.], batch size: 25, lr: 2.39e-04
2022-05-06 10:40:30,202 INFO [train.py:715] (4/8) Epoch 9, batch 7500, loss[loss=0.1551, simple_loss=0.2273, pruned_loss=0.04147, over 4981.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.03496, over 971077.94 frames.], batch size: 15, lr: 2.39e-04
2022-05-06 10:41:09,247 INFO [train.py:715] (4/8) Epoch 9, batch 7550, loss[loss=0.1472, simple_loss=0.2342, pruned_loss=0.03005, over 4947.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.03464, over 970760.36 frames.], batch size: 35, lr: 2.39e-04
2022-05-06 10:41:48,087 INFO [train.py:715] (4/8) Epoch 9, batch 7600, loss[loss=0.1453, simple_loss=0.2123, pruned_loss=0.03909, over 4962.00 frames.], tot_loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.03469, over 970867.00 frames.], batch size: 24, lr: 2.39e-04
2022-05-06 10:42:27,542 INFO [train.py:715] (4/8) Epoch 9, batch 7650, loss[loss=0.1315, simple_loss=0.2122, pruned_loss=0.02541, over 4813.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2148, pruned_loss=0.03495, over 971233.33 frames.], batch size: 27, lr: 2.39e-04
2022-05-06 10:43:06,739 INFO [train.py:715] (4/8) Epoch 9, batch 7700, loss[loss=0.1566, simple_loss=0.2309, pruned_loss=0.04119, over 4781.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2147, pruned_loss=0.03509, over 971755.23 frames.], batch size: 17, lr: 2.39e-04
2022-05-06 10:43:45,562 INFO [train.py:715] (4/8) Epoch 9, batch 7750, loss[loss=0.1098, simple_loss=0.1865, pruned_loss=0.01661, over 4780.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2151, pruned_loss=0.03487, over 972697.48 frames.], batch size: 18, lr: 2.39e-04
2022-05-06 10:44:24,376 INFO [train.py:715] (4/8) Epoch 9, batch 7800, loss[loss=0.1527, simple_loss=0.2353, pruned_loss=0.03509, over 4815.00 frames.], tot_loss[loss=0.144, simple_loss=0.2164, pruned_loss=0.03581, over 971820.94 frames.], batch size: 27, lr: 2.39e-04
2022-05-06 10:45:04,415 INFO [train.py:715] (4/8) Epoch 9, batch 7850, loss[loss=0.1316, simple_loss=0.1905, pruned_loss=0.03635, over 4822.00 frames.], tot_loss[loss=0.1442, simple_loss=0.2163, pruned_loss=0.036, over 971197.71 frames.], batch size: 12, lr: 2.39e-04
2022-05-06 10:45:43,394 INFO [train.py:715] (4/8) Epoch 9, batch 7900, loss[loss=0.1333, simple_loss=0.2065, pruned_loss=0.03002, over 4782.00 frames.], tot_loss[loss=0.1439, simple_loss=0.2165, pruned_loss=0.03566, over 970964.46 frames.], batch size: 14, lr: 2.39e-04
2022-05-06 10:46:21,528 INFO [train.py:715] (4/8) Epoch 9, batch 7950, loss[loss=0.1249, simple_loss=0.1983, pruned_loss=0.02576, over 4824.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2152, pruned_loss=0.03512, over 970916.44 frames.], batch size: 27, lr: 2.39e-04
2022-05-06 10:47:00,915 INFO [train.py:715] (4/8) Epoch 9, batch 8000, loss[loss=0.1404, simple_loss=0.2102, pruned_loss=0.03533, over 4752.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03471, over 971353.26 frames.], batch size: 16, lr: 2.38e-04
2022-05-06 10:47:39,934 INFO [train.py:715] (4/8) Epoch 9, batch 8050, loss[loss=0.145, simple_loss=0.2084, pruned_loss=0.04075, over 4793.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03421, over 971131.34 frames.], batch size: 14, lr: 2.38e-04
2022-05-06 10:48:18,557 INFO [train.py:715] (4/8) Epoch 9, batch 8100, loss[loss=0.1202, simple_loss=0.1956, pruned_loss=0.02238, over 4830.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03434, over 971311.68 frames.], batch size: 15, lr: 2.38e-04
2022-05-06 10:48:57,107 INFO [train.py:715] (4/8) Epoch 9, batch 8150, loss[loss=0.1405, simple_loss=0.2167, pruned_loss=0.03219, over 4768.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2137, pruned_loss=0.03469, over 971442.34 frames.], batch size: 18, lr: 2.38e-04
2022-05-06 10:49:36,458 INFO [train.py:715] (4/8) Epoch 9, batch 8200, loss[loss=0.1615, simple_loss=0.2273, pruned_loss=0.04788, over 4965.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2129, pruned_loss=0.03445, over 971516.68 frames.], batch size: 39, lr: 2.38e-04
2022-05-06 10:50:15,123 INFO [train.py:715] (4/8) Epoch 9, batch 8250, loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02861, over 4803.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2131, pruned_loss=0.03494, over 971394.17 frames.], batch size: 21, lr: 2.38e-04
2022-05-06 10:50:53,695 INFO [train.py:715] (4/8) Epoch 9, batch 8300, loss[loss=0.1446, simple_loss=0.2277, pruned_loss=0.03079, over 4934.00 frames.], tot_loss[loss=0.141, simple_loss=0.2127, pruned_loss=0.03459, over 971741.39 frames.], batch size: 23, lr: 2.38e-04
2022-05-06 10:51:32,739 INFO [train.py:715] (4/8) Epoch 9, batch 8350, loss[loss=0.1432, simple_loss=0.2297, pruned_loss=0.02833, over 4822.00 frames.], tot_loss[loss=0.142, simple_loss=0.2137, pruned_loss=0.03514, over 972102.73 frames.], batch size: 13, lr: 2.38e-04
2022-05-06 10:52:12,415 INFO [train.py:715] (4/8) Epoch 9, batch 8400, loss[loss=0.1322, simple_loss=0.2101, pruned_loss=0.02711, over 4946.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2139, pruned_loss=0.03473, over 972540.16 frames.], batch size: 24, lr: 2.38e-04
2022-05-06 10:52:50,771 INFO [train.py:715] (4/8) Epoch 9, batch 8450, loss[loss=0.1709, simple_loss=0.2414, pruned_loss=0.0502, over 4762.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2139, pruned_loss=0.03485, over 972375.87 frames.], batch size: 16, lr: 2.38e-04
2022-05-06 10:53:29,412 INFO [train.py:715] (4/8) Epoch 9, batch 8500, loss[loss=0.1478, simple_loss=0.2198, pruned_loss=0.0379, over 4945.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2146, pruned_loss=0.03532, over 972083.37 frames.], batch size: 35, lr: 2.38e-04
2022-05-06 10:54:08,958 INFO [train.py:715] (4/8) Epoch 9, batch 8550, loss[loss=0.1765, simple_loss=0.2548, pruned_loss=0.04912, over 4986.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2153, pruned_loss=0.03563, over 972544.48 frames.], batch size: 28, lr: 2.38e-04
2022-05-06 10:54:48,126 INFO [train.py:715] (4/8) Epoch 9, batch 8600, loss[loss=0.1428, simple_loss=0.2224, pruned_loss=0.03157, over 4953.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2155, pruned_loss=0.03516, over 972320.69 frames.], batch size: 24, lr: 2.38e-04
2022-05-06 10:55:26,985 INFO [train.py:715] (4/8) Epoch 9, batch 8650, loss[loss=0.1653, simple_loss=0.2356, pruned_loss=0.04753, over 4760.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.03525, over 971577.98 frames.], batch size: 18, lr: 2.38e-04
2022-05-06 10:56:06,799 INFO [train.py:715] (4/8) Epoch 9, batch 8700, loss[loss=0.172, simple_loss=0.2497, pruned_loss=0.04713, over 4934.00 frames.], tot_loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03539, over 972276.94 frames.], batch size: 23, lr: 2.38e-04
2022-05-06 10:56:46,701 INFO [train.py:715] (4/8) Epoch 9, batch 8750, loss[loss=0.1169, simple_loss=0.1845, pruned_loss=0.02463, over 4794.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2147, pruned_loss=0.03496, over 972954.92 frames.], batch size: 18, lr: 2.38e-04
2022-05-06 10:57:25,009 INFO [train.py:715] (4/8) Epoch 9, batch 8800, loss[loss=0.148, simple_loss=0.2125, pruned_loss=0.0418, over 4838.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2149, pruned_loss=0.03529, over 972715.93 frames.], batch size: 13, lr: 2.38e-04
2022-05-06 10:58:04,390 INFO [train.py:715] (4/8) Epoch 9, batch 8850, loss[loss=0.147, simple_loss=0.2108, pruned_loss=0.04161, over 4788.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2146, pruned_loss=0.03519, over 972175.88 frames.], batch size: 14, lr: 2.38e-04
2022-05-06 10:58:43,838 INFO [train.py:715] (4/8) Epoch 9, batch 8900, loss[loss=0.1424, simple_loss=0.218, pruned_loss=0.03337, over 4897.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03512, over 972569.33 frames.], batch size: 19, lr: 2.38e-04
2022-05-06 10:59:22,970 INFO [train.py:715] (4/8) Epoch 9, batch 8950, loss[loss=0.1622, simple_loss=0.2355, pruned_loss=0.04445, over 4966.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2144, pruned_loss=0.03533, over 972978.74 frames.], batch size: 15, lr: 2.38e-04
2022-05-06 11:00:01,617 INFO [train.py:715] (4/8) Epoch 9, batch 9000, loss[loss=0.1638, simple_loss=0.2432, pruned_loss=0.04214, over 4964.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2146, pruned_loss=0.03551, over 972467.85 frames.], batch size: 24, lr: 2.38e-04
2022-05-06 11:00:01,617 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 11:00:11,231 INFO [train.py:742] (4/8) Epoch 9, validation: loss=0.107, simple_loss=0.1914, pruned_loss=0.0113, over 914524.00 frames.
2022-05-06 11:00:49,915 INFO [train.py:715] (4/8) Epoch 9, batch 9050, loss[loss=0.1298, simple_loss=0.2076, pruned_loss=0.02595, over 4932.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.03499, over 972267.83 frames.], batch size: 23, lr: 2.38e-04
2022-05-06 11:01:30,081 INFO [train.py:715] (4/8) Epoch 9, batch 9100, loss[loss=0.1637, simple_loss=0.2483, pruned_loss=0.03954, over 4764.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2144, pruned_loss=0.03492, over 971727.30 frames.], batch size: 18, lr: 2.38e-04
2022-05-06 11:02:09,668 INFO [train.py:715] (4/8) Epoch 9, batch 9150, loss[loss=0.1464, simple_loss=0.2128, pruned_loss=0.03997, over 4856.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.03444, over 971383.31 frames.], batch size: 32, lr: 2.38e-04
2022-05-06 11:02:48,629 INFO [train.py:715] (4/8) Epoch 9, batch 9200, loss[loss=0.1187, simple_loss=0.187, pruned_loss=0.02522, over 4906.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.03433, over 971610.10 frames.], batch size: 29, lr: 2.38e-04
2022-05-06 11:03:28,185 INFO [train.py:715] (4/8) Epoch 9, batch 9250, loss[loss=0.209, simple_loss=0.2765, pruned_loss=0.0707, over 4793.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2146, pruned_loss=0.0346, over 972180.28 frames.], batch size: 24, lr: 2.38e-04
2022-05-06 11:04:07,598 INFO [train.py:715] (4/8) Epoch 9, batch 9300, loss[loss=0.1537, simple_loss=0.2242, pruned_loss=0.0416, over 4935.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2144, pruned_loss=0.0343, over 972229.02 frames.], batch size: 23, lr: 2.38e-04
2022-05-06 11:04:46,766 INFO [train.py:715] (4/8) Epoch 9, batch 9350, loss[loss=0.1139, simple_loss=0.2007, pruned_loss=0.01353, over 4821.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2133, pruned_loss=0.03375, over 973251.00 frames.], batch size: 25, lr: 2.38e-04
2022-05-06 11:05:25,229 INFO [train.py:715] (4/8) Epoch 9, batch 9400, loss[loss=0.1236, simple_loss=0.1993, pruned_loss=0.02396, over 4831.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03389, over 973232.90 frames.], batch size: 13, lr: 2.38e-04
2022-05-06 11:06:05,137 INFO [train.py:715] (4/8) Epoch 9, batch 9450, loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02932, over 4921.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.03387, over 972922.21 frames.], batch size: 18, lr: 2.38e-04
2022-05-06 11:06:44,278 INFO [train.py:715] (4/8) Epoch 9, batch 9500, loss[loss=0.1596, simple_loss=0.232, pruned_loss=0.04354, over 4878.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03443, over 973018.39 frames.], batch size: 16, lr: 2.38e-04
2022-05-06 11:07:22,929 INFO [train.py:715] (4/8) Epoch 9, batch 9550, loss[loss=0.1455, simple_loss=0.2168, pruned_loss=0.03713, over 4807.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03421, over 972947.85 frames.], batch size: 21, lr: 2.38e-04
2022-05-06 11:08:02,128 INFO [train.py:715] (4/8) Epoch 9, batch 9600, loss[loss=0.1727, simple_loss=0.2508, pruned_loss=0.04728, over 4773.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.03464, over 972428.73 frames.], batch size: 18, lr: 2.38e-04
2022-05-06 11:08:41,396 INFO [train.py:715] (4/8) Epoch 9, batch 9650, loss[loss=0.153, simple_loss=0.2195, pruned_loss=0.04319, over 4929.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2146, pruned_loss=0.03502, over 971429.90 frames.], batch size: 23, lr: 2.38e-04
2022-05-06 11:09:20,425 INFO [train.py:715] (4/8) Epoch 9, batch 9700, loss[loss=0.1406, simple_loss=0.2075, pruned_loss=0.03689, over 4835.00 frames.], tot_loss[loss=0.142, simple_loss=0.2141, pruned_loss=0.03497, over 972128.25 frames.], batch size: 15, lr: 2.38e-04
2022-05-06 11:09:58,453 INFO [train.py:715] (4/8) Epoch 9, batch 9750, loss[loss=0.1363, simple_loss=0.1978, pruned_loss=0.03739, over 4685.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2139, pruned_loss=0.03473, over 971182.88 frames.], batch size: 15, lr: 2.38e-04
2022-05-06 11:10:38,607 INFO [train.py:715] (4/8) Epoch 9, batch 9800, loss[loss=0.1571, simple_loss=0.2302, pruned_loss=0.04203, over 4935.00 frames.], tot_loss[loss=0.142, simple_loss=0.2142, pruned_loss=0.03493, over 970901.62 frames.], batch size: 21, lr: 2.38e-04
2022-05-06 11:11:18,276 INFO [train.py:715] (4/8) Epoch 9, batch 9850, loss[loss=0.1382, simple_loss=0.2122, pruned_loss=0.03209, over 4908.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2149, pruned_loss=0.03522, over 971872.43 frames.], batch size: 18, lr: 2.38e-04
2022-05-06 11:11:56,606 INFO [train.py:715] (4/8) Epoch 9, batch 9900, loss[loss=0.1605, simple_loss=0.2174, pruned_loss=0.05177, over 4839.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2143, pruned_loss=0.03507, over 971372.87 frames.], batch size: 13, lr: 2.38e-04
2022-05-06 11:12:35,818 INFO [train.py:715] (4/8) Epoch 9, batch 9950, loss[loss=0.2092, simple_loss=0.2686, pruned_loss=0.07496, over 4871.00 frames.], tot_loss[loss=0.1432, simple_loss=0.215, pruned_loss=0.03572, over 972363.47 frames.], batch size: 30, lr: 2.38e-04
2022-05-06 11:13:15,752 INFO [train.py:715] (4/8) Epoch 9, batch 10000, loss[loss=0.1307, simple_loss=0.1977, pruned_loss=0.03183, over 4849.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2144, pruned_loss=0.03491, over 972310.30 frames.], batch size: 32, lr: 2.38e-04
2022-05-06 11:13:55,091 INFO [train.py:715] (4/8) Epoch 9, batch 10050, loss[loss=0.1304, simple_loss=0.198, pruned_loss=0.03142, over 4962.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2147, pruned_loss=0.03516, over 972917.15 frames.], batch size: 24, lr: 2.38e-04
2022-05-06 11:14:33,374 INFO [train.py:715] (4/8) Epoch 9, batch 10100, loss[loss=0.1186, simple_loss=0.1938, pruned_loss=0.02176, over 4958.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.03467, over 972885.07 frames.], batch size: 24, lr: 2.38e-04
2022-05-06 11:15:12,910 INFO [train.py:715] (4/8) Epoch 9, batch 10150, loss[loss=0.1529, simple_loss=0.2314, pruned_loss=0.03719, over 4972.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2144, pruned_loss=0.03444, over 973405.80 frames.], batch size: 28, lr: 2.38e-04
2022-05-06 11:15:52,570 INFO [train.py:715] (4/8) Epoch 9, batch 10200, loss[loss=0.1458, simple_loss=0.2136, pruned_loss=0.03899, over 4781.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03465, over 973615.97 frames.], batch size: 14, lr: 2.38e-04
2022-05-06 11:16:31,361 INFO [train.py:715] (4/8) Epoch 9, batch 10250, loss[loss=0.1398, simple_loss=0.2228, pruned_loss=0.0284, over 4793.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.03493, over 972746.08 frames.], batch size: 17, lr: 2.38e-04
2022-05-06 11:17:10,102 INFO [train.py:715] (4/8) Epoch 9, batch 10300, loss[loss=0.1611, simple_loss=0.2321, pruned_loss=0.04508, over 4829.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.03514, over 972409.89 frames.], batch size: 15, lr: 2.38e-04
2022-05-06 11:17:49,727 INFO [train.py:715] (4/8) Epoch 9, batch 10350, loss[loss=0.162, simple_loss=0.2408, pruned_loss=0.04155, over 4775.00 frames.], tot_loss[loss=0.1417, simple_loss=0.214, pruned_loss=0.03465, over 972173.88 frames.], batch size: 17, lr: 2.38e-04
2022-05-06 11:18:28,422 INFO [train.py:715] (4/8) Epoch 9, batch 10400, loss[loss=0.1224, simple_loss=0.2017, pruned_loss=0.02157, over 4791.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2138, pruned_loss=0.03482, over 972651.46 frames.], batch size: 24, lr: 2.38e-04
2022-05-06 11:19:06,741 INFO [train.py:715] (4/8) Epoch 9, batch 10450, loss[loss=0.154, simple_loss=0.2213, pruned_loss=0.04331, over 4914.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.0345, over 972792.47 frames.], batch size: 17, lr: 2.38e-04
2022-05-06 11:19:45,851 INFO [train.py:715] (4/8) Epoch 9, batch 10500, loss[loss=0.1378, simple_loss=0.2121, pruned_loss=0.03174, over 4885.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2137, pruned_loss=0.03453, over 971831.59 frames.], batch size: 22, lr: 2.38e-04
2022-05-06 11:20:25,281 INFO [train.py:715] (4/8) Epoch 9, batch 10550, loss[loss=0.1247, simple_loss=0.2005, pruned_loss=0.02444, over 4793.00 frames.], tot_loss[loss=0.142, simple_loss=0.2149, pruned_loss=0.03455, over 972565.10 frames.], batch size: 17, lr: 2.38e-04
2022-05-06 11:21:04,102 INFO [train.py:715] (4/8) Epoch 9, batch 10600, loss[loss=0.1259, simple_loss=0.2038, pruned_loss=0.02401, over 4985.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.0347, over 972855.92 frames.], batch size: 24, lr: 2.38e-04
2022-05-06 11:21:42,611 INFO [train.py:715] (4/8) Epoch 9, batch 10650, loss[loss=0.1337, simple_loss=0.2169, pruned_loss=0.02529, over 4873.00 frames.], tot_loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.03479, over 972795.01 frames.], batch size: 22, lr: 2.38e-04
2022-05-06 11:22:21,911 INFO [train.py:715] (4/8) Epoch 9, batch 10700, loss[loss=0.1527, simple_loss=0.2204, pruned_loss=0.0425, over 4889.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2154, pruned_loss=0.03465, over 973264.14 frames.], batch size: 22, lr: 2.37e-04
2022-05-06 11:23:01,944 INFO [train.py:715] (4/8) Epoch 9, batch 10750, loss[loss=0.1783, simple_loss=0.247, pruned_loss=0.05481, over 4744.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2157, pruned_loss=0.03468, over 973205.40 frames.], batch size: 16, lr: 2.37e-04
2022-05-06 11:23:40,535 INFO [train.py:715] (4/8) Epoch 9, batch 10800, loss[loss=0.1187, simple_loss=0.19, pruned_loss=0.02367, over 4911.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03472, over 973123.47 frames.], batch size: 23, lr: 2.37e-04
2022-05-06 11:24:20,014 INFO [train.py:715] (4/8) Epoch 9, batch 10850, loss[loss=0.1482, simple_loss=0.2233, pruned_loss=0.03656, over 4802.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.03477, over 972856.94 frames.], batch size: 14, lr: 2.37e-04
2022-05-06 11:24:59,841 INFO [train.py:715] (4/8) Epoch 9, batch 10900, loss[loss=0.161, simple_loss=0.2272, pruned_loss=0.04742, over 4919.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2146, pruned_loss=0.03457, over 973105.85 frames.], batch size: 18, lr: 2.37e-04
2022-05-06 11:25:40,135 INFO [train.py:715] (4/8) Epoch 9, batch 10950, loss[loss=0.1817, simple_loss=0.2599, pruned_loss=0.05175, over 4830.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2143, pruned_loss=0.03454, over 972945.69 frames.], batch size: 15, lr: 2.37e-04
2022-05-06 11:26:20,006 INFO [train.py:715] (4/8) Epoch 9, batch 11000, loss[loss=0.1351, simple_loss=0.2071, pruned_loss=0.03151, over 4953.00 frames.], tot_loss[loss=0.142, simple_loss=0.2144, pruned_loss=0.03478, over 972502.43 frames.], batch size: 35, lr: 2.37e-04
2022-05-06 11:27:00,842 INFO [train.py:715] (4/8) Epoch 9, batch 11050, loss[loss=0.1476, simple_loss=0.2175, pruned_loss=0.0389, over 4858.00 frames.], tot_loss[loss=0.141, simple_loss=0.2132, pruned_loss=0.03437, over 972290.97 frames.], batch size: 13, lr: 2.37e-04
2022-05-06 11:27:42,121 INFO [train.py:715] (4/8) Epoch 9, batch 11100, loss[loss=0.1418, simple_loss=0.2159, pruned_loss=0.03383, over 4966.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.03453, over 971770.41 frames.], batch size: 24, lr: 2.37e-04
2022-05-06 11:28:22,794 INFO [train.py:715] (4/8) Epoch 9, batch 11150, loss[loss=0.1419, simple_loss=0.2107, pruned_loss=0.03652, over 4790.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.03464, over 972667.78 frames.], batch size: 17, lr: 2.37e-04
2022-05-06 11:29:03,602 INFO [train.py:715] (4/8) Epoch 9, batch 11200, loss[loss=0.1435, simple_loss=0.2208, pruned_loss=0.03312, over 4899.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2155, pruned_loss=0.03498, over 971859.82 frames.], batch size: 39, lr: 2.37e-04
2022-05-06 11:29:45,081 INFO [train.py:715] (4/8) Epoch 9, batch 11250, loss[loss=0.1556, simple_loss=0.2268, pruned_loss=0.04224, over 4819.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2153, pruned_loss=0.0351, over 970878.01 frames.], batch size: 15, lr: 2.37e-04
2022-05-06 11:30:26,198 INFO [train.py:715] (4/8) Epoch 9, batch 11300, loss[loss=0.1167, simple_loss=0.1935, pruned_loss=0.01997, over 4754.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2143, pruned_loss=0.03429, over 971366.58 frames.], batch size: 16, lr: 2.37e-04
2022-05-06 11:31:06,644 INFO [train.py:715] (4/8) Epoch 9, batch 11350, loss[loss=0.1431, simple_loss=0.2142, pruned_loss=0.03594, over 4931.00 frames.], tot_loss[loss=0.1415, simple_loss=0.214, pruned_loss=0.03454, over 971448.36 frames.], batch size: 39, lr: 2.37e-04
2022-05-06 11:31:47,932 INFO [train.py:715] (4/8) Epoch 9, batch 11400, loss[loss=0.1371, simple_loss=0.2161, pruned_loss=0.02902, over 4980.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2147, pruned_loss=0.03499, over 971198.33 frames.], batch size: 24, lr: 2.37e-04
2022-05-06 11:32:29,488 INFO [train.py:715] (4/8) Epoch 9, batch 11450, loss[loss=0.1225, simple_loss=0.1865, pruned_loss=0.02925, over 4806.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2145, pruned_loss=0.03526, over 971613.43 frames.], batch size: 12, lr: 2.37e-04
2022-05-06 11:33:10,068 INFO [train.py:715] (4/8) Epoch 9, batch 11500, loss[loss=0.1202, simple_loss=0.2002, pruned_loss=0.0201, over 4926.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2137, pruned_loss=0.03468, over 971863.45 frames.], batch size: 23, lr: 2.37e-04
2022-05-06 11:33:50,767 INFO [train.py:715] (4/8) Epoch 9, batch 11550, loss[loss=0.1772, simple_loss=0.2432, pruned_loss=0.05561, over 4859.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2131, pruned_loss=0.03471, over 972103.51 frames.], batch size: 38, lr: 2.37e-04
2022-05-06 11:34:32,079 INFO [train.py:715] (4/8) Epoch 9, batch 11600, loss[loss=0.1357, simple_loss=0.2153, pruned_loss=0.02803, over 4933.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2133, pruned_loss=0.03449, over 972781.30 frames.], batch size: 29, lr: 2.37e-04
2022-05-06 11:35:13,591 INFO [train.py:715] (4/8) Epoch 9, batch 11650, loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02817, over 4922.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03469, over 972806.34 frames.], batch size: 17, lr: 2.37e-04
2022-05-06 11:35:53,527 INFO [train.py:715] (4/8) Epoch 9, batch 11700, loss[loss=0.1433, simple_loss=0.2086, pruned_loss=0.039, over 4809.00 frames.], tot_loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.03467, over 973579.00 frames.], batch size: 14, lr: 2.37e-04
2022-05-06 11:36:34,963 INFO [train.py:715] (4/8) Epoch 9, batch 11750, loss[loss=0.1418, simple_loss=0.2206, pruned_loss=0.0315, over 4768.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03429, over 973612.01 frames.], batch size: 17, lr: 2.37e-04
2022-05-06 11:37:16,465 INFO [train.py:715] (4/8) Epoch 9, batch 11800, loss[loss=0.1154, simple_loss=0.1966, pruned_loss=0.01707, over 4938.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.03489, over 973256.15 frames.], batch size: 21, lr: 2.37e-04
2022-05-06 11:37:56,810 INFO [train.py:715] (4/8) Epoch 9, batch 11850, loss[loss=0.1365, simple_loss=0.1965, pruned_loss=0.03824, over 4938.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2148, pruned_loss=0.03499, over 972379.63 frames.], batch size: 29, lr: 2.37e-04
2022-05-06 11:38:37,228 INFO [train.py:715] (4/8) Epoch 9, batch 11900, loss[loss=0.1511, simple_loss=0.2345, pruned_loss=0.03383, over 4952.00 frames.], tot_loss[loss=0.142, simple_loss=0.214, pruned_loss=0.035, over 972755.17 frames.], batch size: 21, lr: 2.37e-04
2022-05-06 11:39:18,255 INFO [train.py:715] (4/8) Epoch 9, batch 11950, loss[loss=0.1397, simple_loss=0.2148, pruned_loss=0.03237, over 4803.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2144, pruned_loss=0.03502, over 972127.31 frames.], batch size: 21, lr: 2.37e-04
2022-05-06 11:39:59,366 INFO [train.py:715] (4/8) Epoch 9, batch 12000, loss[loss=0.1314, simple_loss=0.2046, pruned_loss=0.02907, over 4841.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03497, over 972258.66 frames.], batch size: 26, lr: 2.37e-04
2022-05-06 11:39:59,367 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 11:40:09,081 INFO [train.py:742] (4/8) Epoch 9, validation: loss=0.107, simple_loss=0.1913, pruned_loss=0.01136, over 914524.00 frames.
2022-05-06 11:40:50,121 INFO [train.py:715] (4/8) Epoch 9, batch 12050, loss[loss=0.1307, simple_loss=0.2057, pruned_loss=0.0278, over 4910.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03497, over 972608.52 frames.], batch size: 23, lr: 2.37e-04
2022-05-06 11:41:29,620 INFO [train.py:715] (4/8) Epoch 9, batch 12100, loss[loss=0.1024, simple_loss=0.1798, pruned_loss=0.01249, over 4959.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2149, pruned_loss=0.03522, over 973411.26 frames.], batch size: 14, lr: 2.37e-04
2022-05-06 11:42:10,005 INFO [train.py:715] (4/8) Epoch 9, batch 12150, loss[loss=0.1099, simple_loss=0.1801, pruned_loss=0.01986, over 4793.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03511, over 973232.22 frames.], batch size: 12, lr: 2.37e-04
2022-05-06 11:42:50,005 INFO [train.py:715] (4/8) Epoch 9, batch 12200, loss[loss=0.1283, simple_loss=0.2069, pruned_loss=0.02489, over 4876.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03481, over 973501.26 frames.], batch size: 22, lr: 2.37e-04
2022-05-06 11:43:29,259 INFO [train.py:715] (4/8) Epoch 9, batch 12250, loss[loss=0.1387, simple_loss=0.2105, pruned_loss=0.03345, over 4907.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2155, pruned_loss=0.03532, over 973254.83 frames.], batch size: 17, lr: 2.37e-04
2022-05-06 11:44:08,222 INFO [train.py:715] (4/8) Epoch 9, batch 12300, loss[loss=0.1375, simple_loss=0.2206, pruned_loss=0.02716, over 4777.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2148, pruned_loss=0.03498, over 971996.82 frames.], batch size: 17, lr: 2.37e-04
2022-05-06 11:44:47,989 INFO [train.py:715] (4/8) Epoch 9, batch 12350, loss[loss=0.1359, simple_loss=0.2057, pruned_loss=0.03309, over 4927.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.0348, over 972046.41 frames.], batch size: 23, lr: 2.37e-04
2022-05-06 11:45:28,033 INFO [train.py:715] (4/8) Epoch 9, batch 12400, loss[loss=0.1234, simple_loss=0.1851, pruned_loss=0.03084, over 4982.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03439, over 971669.39 frames.], batch size: 15, lr: 2.37e-04
2022-05-06 11:46:07,545 INFO [train.py:715] (4/8) Epoch 9, batch 12450, loss[loss=0.1202, simple_loss=0.2002, pruned_loss=0.02009, over 4854.00 frames.], tot_loss[loss=0.141, simple_loss=0.2133, pruned_loss=0.03435, over 971878.89 frames.], batch size: 20, lr: 2.37e-04
2022-05-06 11:46:47,598 INFO [train.py:715] (4/8) Epoch 9, batch 12500, loss[loss=0.1458, simple_loss=0.2112, pruned_loss=0.04023, over 4862.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2139, pruned_loss=0.03463, over 972232.37 frames.], batch size: 32, lr: 2.37e-04
2022-05-06 11:47:27,731 INFO [train.py:715] (4/8) Epoch 9, batch 12550, loss[loss=0.1215, simple_loss=0.1935, pruned_loss=0.02474, over 4938.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.03464, over 972417.25 frames.], batch size: 21, lr: 2.37e-04
2022-05-06 11:48:07,693 INFO [train.py:715] (4/8) Epoch 9, batch 12600, loss[loss=0.1278, simple_loss=0.2038, pruned_loss=0.02592, over 4932.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2141, pruned_loss=0.03442, over 972112.89 frames.], batch size: 21, lr: 2.37e-04
2022-05-06 11:48:46,463 INFO [train.py:715] (4/8) Epoch 9, batch 12650, loss[loss=0.1385, simple_loss=0.2109, pruned_loss=0.03307, over 4829.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2147, pruned_loss=0.03454, over 971609.64 frames.], batch size: 25, lr: 2.37e-04
2022-05-06 11:49:26,599 INFO [train.py:715] (4/8) Epoch 9, batch 12700, loss[loss=0.1146, simple_loss=0.1916, pruned_loss=0.01884, over 4940.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2148, pruned_loss=0.0344, over 970605.66 frames.], batch size: 29, lr: 2.37e-04
2022-05-06 11:50:06,589 INFO [train.py:715] (4/8) Epoch 9, batch 12750, loss[loss=0.1336, simple_loss=0.217, pruned_loss=0.02513, over 4763.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.03431, over 971260.82 frames.], batch size: 14, lr: 2.37e-04
2022-05-06 11:50:45,778 INFO [train.py:715] (4/8) Epoch 9, batch 12800, loss[loss=0.113, simple_loss=0.1875, pruned_loss=0.01925, over 4859.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.0338, over 971642.57 frames.], batch size: 15, lr: 2.37e-04
2022-05-06 11:51:25,603 INFO [train.py:715] (4/8) Epoch 9, batch 12850, loss[loss=0.1581, simple_loss=0.232, pruned_loss=0.04213, over 4976.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03337, over 972040.64 frames.], batch size: 15, lr: 2.37e-04
2022-05-06 11:52:05,499 INFO [train.py:715] (4/8) Epoch 9, batch 12900, loss[loss=0.1417, simple_loss=0.2236, pruned_loss=0.02984, over 4972.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2133, pruned_loss=0.03347, over 972311.00 frames.], batch size: 24, lr: 2.37e-04
2022-05-06 11:52:45,476 INFO [train.py:715] (4/8) Epoch 9, batch 12950, loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03166, over 4954.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2142, pruned_loss=0.03398, over 971554.35 frames.], batch size: 29, lr: 2.37e-04
2022-05-06 11:53:24,503 INFO [train.py:715] (4/8) Epoch 9, batch 13000, loss[loss=0.1453, simple_loss=0.2273, pruned_loss=0.03168, over 4821.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03409, over 971588.03 frames.], batch size: 26, lr: 2.37e-04
2022-05-06 11:54:04,864 INFO [train.py:715] (4/8) Epoch 9, batch 13050, loss[loss=0.1376, simple_loss=0.2224, pruned_loss=0.02639, over 4939.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03418, over 971899.12 frames.], batch size: 29, lr: 2.37e-04
2022-05-06 11:54:44,621 INFO [train.py:715] (4/8) Epoch 9, batch 13100, loss[loss=0.1189, simple_loss=0.2061, pruned_loss=0.01582, over 4834.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2133, pruned_loss=0.0342, over 972594.72 frames.], batch size: 26, lr: 2.37e-04
2022-05-06 11:55:23,867 INFO [train.py:715] (4/8) Epoch 9, batch 13150, loss[loss=0.1357, simple_loss=0.2084, pruned_loss=0.03152, over 4921.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.0346, over 973099.94 frames.], batch size: 18, lr: 2.37e-04
2022-05-06 11:56:03,853 INFO [train.py:715] (4/8) Epoch 9, batch 13200, loss[loss=0.1468, simple_loss=0.2097, pruned_loss=0.04197, over 4988.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2145, pruned_loss=0.03505, over 973882.71 frames.], batch size: 33, lr: 2.37e-04
2022-05-06 11:56:44,169 INFO [train.py:715] (4/8) Epoch 9, batch 13250, loss[loss=0.1515, simple_loss=0.2255, pruned_loss=0.03875, over 4736.00 frames.], tot_loss[loss=0.142, simple_loss=0.2145, pruned_loss=0.03475, over 973405.00 frames.], batch size: 16, lr: 2.37e-04
2022-05-06 11:57:23,742 INFO [train.py:715] (4/8) Epoch 9, batch 13300, loss[loss=0.1398, simple_loss=0.2087, pruned_loss=0.03543, over 4699.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2141, pruned_loss=0.03476, over 973279.11 frames.], batch size: 15, lr: 2.37e-04
2022-05-06 11:58:03,445 INFO [train.py:715] (4/8) Epoch 9, batch 13350, loss[loss=0.1449, simple_loss=0.2234, pruned_loss=0.0332, over 4872.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2143, pruned_loss=0.03505, over 972434.66 frames.], batch size: 32, lr: 2.37e-04
2022-05-06 11:58:43,521 INFO [train.py:715] (4/8) Epoch 9, batch 13400, loss[loss=0.1209, simple_loss=0.2043, pruned_loss=0.01878, over 4947.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2143, pruned_loss=0.03456, over 972325.11 frames.], batch size: 23, lr: 2.37e-04
2022-05-06 11:59:23,794 INFO [train.py:715] (4/8) Epoch 9, batch 13450, loss[loss=0.134, simple_loss=0.2008, pruned_loss=0.03355, over 4778.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2144, pruned_loss=0.03409, over 971438.19 frames.], batch size: 17, lr: 2.36e-04
2022-05-06 12:00:02,967 INFO [train.py:715] (4/8) Epoch 9, batch 13500, loss[loss=0.1714, simple_loss=0.2353, pruned_loss=0.05378, over 4977.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2145, pruned_loss=0.03424, over 972346.75 frames.], batch size: 39, lr: 2.36e-04
2022-05-06 12:00:42,986 INFO [train.py:715] (4/8) Epoch 9, batch 13550, loss[loss=0.1235, simple_loss=0.1979, pruned_loss=0.02457, over 4832.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2145, pruned_loss=0.03424, over 972856.43 frames.], batch size: 15, lr: 2.36e-04
2022-05-06 12:01:22,497 INFO [train.py:715] (4/8) Epoch 9, batch 13600, loss[loss=0.1369, simple_loss=0.2042, pruned_loss=0.03476, over 4893.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.03397, over 972481.08 frames.], batch size: 17, lr: 2.36e-04
2022-05-06 12:02:01,622 INFO [train.py:715] (4/8) Epoch 9, batch 13650, loss[loss=0.1527, simple_loss=0.2226, pruned_loss=0.04146, over 4860.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03429, over 972363.83 frames.], batch size: 38, lr: 2.36e-04
2022-05-06 12:02:40,851 INFO [train.py:715] (4/8) Epoch 9, batch 13700, loss[loss=0.1616, simple_loss=0.2272, pruned_loss=0.04802, over 4958.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03409, over 973218.29 frames.], batch size: 35, lr: 2.36e-04
2022-05-06 12:03:20,735 INFO [train.py:715] (4/8) Epoch 9, batch 13750, loss[loss=0.1493, simple_loss=0.2283, pruned_loss=0.03512, over 4767.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2139, pruned_loss=0.03364, over 972909.97 frames.], batch size: 19, lr: 2.36e-04
2022-05-06 12:03:59,886 INFO [train.py:715] (4/8) Epoch 9, batch 13800, loss[loss=0.1176, simple_loss=0.1913, pruned_loss=0.02197, over 4983.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.03395, over 972641.03 frames.], batch size: 27, lr: 2.36e-04
2022-05-06 12:04:38,381 INFO [train.py:715] (4/8) Epoch 9, batch 13850, loss[loss=0.1373, simple_loss=0.2057, pruned_loss=0.03443, over 4843.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03438, over 971986.50 frames.], batch size: 30, lr: 2.36e-04
2022-05-06 12:05:17,812 INFO [train.py:715] (4/8) Epoch 9, batch 13900, loss[loss=0.1539, simple_loss=0.2347, pruned_loss=0.03658, over 4831.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03439, over 972006.74 frames.], batch size: 15, lr: 2.36e-04
2022-05-06 12:05:57,957 INFO [train.py:715] (4/8) Epoch 9, batch 13950, loss[loss=0.1431, simple_loss=0.2176, pruned_loss=0.03426, over 4722.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03474, over 971321.35 frames.], batch size: 16, lr: 2.36e-04
2022-05-06 12:06:36,916 INFO [train.py:715] (4/8) Epoch 9, batch 14000, loss[loss=0.1176, simple_loss=0.1828, pruned_loss=0.0262, over 4822.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2147, pruned_loss=0.03425, over 970790.51 frames.], batch size: 12, lr: 2.36e-04
2022-05-06 12:07:16,028 INFO [train.py:715] (4/8) Epoch 9, batch 14050, loss[loss=0.2156, simple_loss=0.2921, pruned_loss=0.06952, over 4831.00 frames.], tot_loss[loss=0.1419, simple_loss=0.215, pruned_loss=0.03443, over 970996.76 frames.], batch size: 15, lr: 2.36e-04
2022-05-06 12:07:55,578 INFO [train.py:715] (4/8) Epoch 9, batch 14100, loss[loss=0.1625, simple_loss=0.2401, pruned_loss=0.0424, over 4936.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.03456, over 971725.19 frames.], batch size: 39, lr: 2.36e-04
2022-05-06 12:08:35,148 INFO [train.py:715] (4/8) Epoch 9, batch 14150, loss[loss=0.1456, simple_loss=0.2163, pruned_loss=0.03748, over 4886.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.0346, over 971676.46 frames.], batch size: 39, lr: 2.36e-04
2022-05-06 12:09:14,476 INFO [train.py:715] (4/8) Epoch 9, batch 14200, loss[loss=0.1712, simple_loss=0.2431, pruned_loss=0.04966, over 4830.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03442, over 971675.30 frames.], batch size: 15, lr: 2.36e-04
2022-05-06 12:09:53,801 INFO [train.py:715] (4/8) Epoch 9, batch 14250, loss[loss=0.1541, simple_loss=0.2312, pruned_loss=0.03853, over 4763.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03483, over 971618.75 frames.], batch size: 14, lr: 2.36e-04
2022-05-06 12:10:33,295 INFO [train.py:715] (4/8) Epoch 9, batch 14300, loss[loss=0.1354, simple_loss=0.2036, pruned_loss=0.03359, over 4945.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2136, pruned_loss=0.03427, over 972369.49 frames.], batch size: 21, lr: 2.36e-04
2022-05-06 12:11:11,972 INFO [train.py:715] (4/8) Epoch 9, batch 14350, loss[loss=0.1499, simple_loss=0.2196, pruned_loss=0.04012, over 4956.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03448, over 972984.50 frames.], batch size: 15, lr: 2.36e-04
2022-05-06 12:11:50,597 INFO [train.py:715] (4/8) Epoch 9, batch 14400, loss[loss=0.156, simple_loss=0.2296, pruned_loss=0.04119, over 4785.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03462, over 972779.85 frames.], batch size: 17, lr: 2.36e-04
2022-05-06 12:12:30,353 INFO [train.py:715] (4/8) Epoch 9, batch 14450, loss[loss=0.1427, simple_loss=0.2185, pruned_loss=0.0334, over 4885.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03449, over 972842.16 frames.], batch size: 16, lr: 2.36e-04
2022-05-06 12:13:09,685 INFO [train.py:715] (4/8) Epoch 9, batch 14500, loss[loss=0.1108, simple_loss=0.1855, pruned_loss=0.0181, over 4887.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2142, pruned_loss=0.03467, over 972756.95 frames.], batch size: 16, lr: 2.36e-04
2022-05-06 12:13:48,634 INFO [train.py:715] (4/8) Epoch 9, batch 14550, loss[loss=0.1288, simple_loss=0.211, pruned_loss=0.0233, over 4935.00 frames.], tot_loss[loss=0.1415, simple_loss=0.214, pruned_loss=0.03456, over 972498.30 frames.], batch size: 35, lr: 2.36e-04
2022-05-06 12:14:27,683 INFO [train.py:715] (4/8) Epoch 9, batch 14600, loss[loss=0.1319, simple_loss=0.2047, pruned_loss=0.02953, over 4910.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03457, over 972711.98 frames.], batch size: 19, lr: 2.36e-04
2022-05-06 12:15:07,386 INFO [train.py:715] (4/8) Epoch 9, batch 14650, loss[loss=0.1518, simple_loss=0.2113, pruned_loss=0.04612, over 4982.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03485, over 972657.69 frames.], batch size: 31, lr: 2.36e-04
2022-05-06 12:15:45,916 INFO [train.py:715] (4/8) Epoch 9, batch 14700, loss[loss=0.1189, simple_loss=0.1986, pruned_loss=0.01957, over 4896.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2138, pruned_loss=0.03458, over 972893.34 frames.], batch size: 19, lr: 2.36e-04
2022-05-06 12:16:27,517 INFO [train.py:715] (4/8) Epoch 9, batch 14750, loss[loss=0.1162, simple_loss=0.1844, pruned_loss=0.02398, over 4641.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2131, pruned_loss=0.03428, over 972562.75 frames.], batch size: 13, lr: 2.36e-04
2022-05-06 12:17:06,568 INFO [train.py:715] (4/8) Epoch 9, batch 14800, loss[loss=0.1369, simple_loss=0.2135, pruned_loss=0.03012, over 4874.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2135, pruned_loss=0.0347, over 973115.19 frames.], batch size: 22, lr: 2.36e-04
2022-05-06 12:17:45,495 INFO [train.py:715] (4/8) Epoch 9, batch 14850, loss[loss=0.1602, simple_loss=0.2166, pruned_loss=0.05189, over 4733.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2134, pruned_loss=0.03471, over 972899.57 frames.], batch size: 16, lr: 2.36e-04
2022-05-06 12:18:24,546 INFO [train.py:715] (4/8) Epoch 9, batch 14900, loss[loss=0.1304, simple_loss=0.2042, pruned_loss=0.02834, over 4939.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2139, pruned_loss=0.03525, over 973255.12 frames.], batch size: 24, lr: 2.36e-04
2022-05-06 12:19:03,081 INFO [train.py:715] (4/8) Epoch 9, batch 14950, loss[loss=0.1239, simple_loss=0.1972, pruned_loss=0.02531, over 4884.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2139, pruned_loss=0.03493, over 973170.76 frames.], batch size: 22, lr: 2.36e-04
2022-05-06 12:19:42,675 INFO [train.py:715] (4/8) Epoch 9, batch 15000, loss[loss=0.1886, simple_loss=0.2709, pruned_loss=0.05314, over 4830.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03485, over 973203.16 frames.], batch size: 30, lr: 2.36e-04
2022-05-06 12:19:42,676 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 12:19:52,342 INFO [train.py:742] (4/8) Epoch 9, validation: loss=0.1071, simple_loss=0.1915, pruned_loss=0.01139, over 914524.00 frames.
2022-05-06 12:20:32,096 INFO [train.py:715] (4/8) Epoch 9, batch 15050, loss[loss=0.114, simple_loss=0.1858, pruned_loss=0.02113, over 4855.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.0346, over 973189.55 frames.], batch size: 20, lr: 2.36e-04
2022-05-06 12:21:11,098 INFO [train.py:715] (4/8) Epoch 9, batch 15100, loss[loss=0.1417, simple_loss=0.2207, pruned_loss=0.03139, over 4955.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03397, over 972339.51 frames.], batch size: 15, lr: 2.36e-04
2022-05-06 12:21:50,201 INFO [train.py:715] (4/8) Epoch 9, batch 15150, loss[loss=0.1269, simple_loss=0.2062, pruned_loss=0.02379, over 4974.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2137, pruned_loss=0.0338, over 971257.23 frames.], batch size: 28, lr: 2.36e-04
2022-05-06 12:22:30,011 INFO [train.py:715] (4/8) Epoch 9, batch 15200, loss[loss=0.1175, simple_loss=0.1971, pruned_loss=0.01892, over 4879.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2134, pruned_loss=0.03391, over 971742.47 frames.], batch size: 22, lr: 2.36e-04
2022-05-06 12:23:09,314 INFO [train.py:715] (4/8) Epoch 9, batch 15250, loss[loss=0.1312, simple_loss=0.2138, pruned_loss=0.02428, over 4757.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03416, over 971863.35 frames.], batch size: 18, lr: 2.36e-04
2022-05-06 12:23:48,033 INFO [train.py:715] (4/8) Epoch 9, batch 15300, loss[loss=0.1193, simple_loss=0.1912, pruned_loss=0.02368, over 4991.00 frames.], tot_loss[loss=0.141, simple_loss=0.2139, pruned_loss=0.03406, over 972635.50 frames.], batch size: 26, lr: 2.36e-04
2022-05-06 12:24:27,149 INFO [train.py:715] (4/8) Epoch 9, batch 15350, loss[loss=0.1316, simple_loss=0.2006, pruned_loss=0.03128, over 4948.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2143, pruned_loss=0.03422, over 972898.34 frames.], batch size: 21, lr: 2.36e-04
2022-05-06 12:25:06,185 INFO [train.py:715] (4/8) Epoch 9, batch 15400, loss[loss=0.1218, simple_loss=0.1903, pruned_loss=0.02667, over 4895.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2144, pruned_loss=0.03436, over 973407.00 frames.], batch size: 17, lr: 2.36e-04
2022-05-06 12:25:44,959 INFO [train.py:715] (4/8) Epoch 9, batch 15450, loss[loss=0.1703, simple_loss=0.2457, pruned_loss=0.04749, over 4761.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2143, pruned_loss=0.03421, over 973458.36 frames.], batch size: 19, lr: 2.36e-04
2022-05-06 12:26:23,387 INFO [train.py:715] (4/8) Epoch 9, batch 15500, loss[loss=0.132, simple_loss=0.2105, pruned_loss=0.02675, over 4772.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.03438, over 971965.71 frames.], batch size: 18, lr: 2.36e-04
2022-05-06 12:27:03,115 INFO [train.py:715] (4/8) Epoch 9, batch 15550, loss[loss=0.1714, simple_loss=0.247, pruned_loss=0.04789, over 4825.00 frames.], tot_loss[loss=0.142, simple_loss=0.2146, pruned_loss=0.03467, over 971685.79 frames.], batch size: 26, lr: 2.36e-04
2022-05-06 12:27:41,877 INFO [train.py:715] (4/8) Epoch 9, batch 15600, loss[loss=0.1367, simple_loss=0.2107, pruned_loss=0.03136, over 4779.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2142, pruned_loss=0.03473, over 971261.97 frames.], batch size: 18, lr: 2.36e-04
2022-05-06 12:28:20,225 INFO [train.py:715] (4/8) Epoch 9, batch 15650, loss[loss=0.1319, simple_loss=0.2044, pruned_loss=0.02973, over 4753.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2142, pruned_loss=0.03419, over 971488.97 frames.], batch size: 19, lr: 2.36e-04
2022-05-06 12:28:59,315 INFO [train.py:715] (4/8) Epoch 9, batch 15700, loss[loss=0.1247, simple_loss=0.1967, pruned_loss=0.02638, over 4837.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2139, pruned_loss=0.03422, over 971323.50 frames.], batch size: 15, lr: 2.36e-04
2022-05-06 12:29:39,070 INFO [train.py:715] (4/8) Epoch 9, batch 15750, loss[loss=0.1582, simple_loss=0.2353, pruned_loss=0.04054, over 4912.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03443, over 971430.11 frames.], batch size: 17, lr: 2.36e-04
2022-05-06 12:30:17,875 INFO [train.py:715] (4/8) Epoch 9, batch 15800, loss[loss=0.1099, simple_loss=0.1781, pruned_loss=0.0209, over 4636.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03438, over 971383.13 frames.], batch size: 13, lr: 2.36e-04
2022-05-06 12:30:56,796 INFO [train.py:715] (4/8) Epoch 9, batch 15850, loss[loss=0.1408, simple_loss=0.2218, pruned_loss=0.02983, over 4778.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2146, pruned_loss=0.03433, over 971695.64 frames.], batch size: 18, lr: 2.36e-04
2022-05-06 12:31:36,399 INFO [train.py:715] (4/8) Epoch 9, batch 15900, loss[loss=0.143, simple_loss=0.2299, pruned_loss=0.02799, over 4784.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.03399, over 971390.14 frames.], batch size: 18, lr: 2.36e-04
2022-05-06 12:32:15,974 INFO [train.py:715] (4/8) Epoch 9, batch 15950, loss[loss=0.1529, simple_loss=0.2283, pruned_loss=0.0388, over 4838.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2143, pruned_loss=0.03446, over 972054.78 frames.], batch size: 32, lr: 2.36e-04
2022-05-06 12:32:54,619 INFO [train.py:715] (4/8) Epoch 9, batch 16000, loss[loss=0.1453, simple_loss=0.2162, pruned_loss=0.03715, over 4792.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2139, pruned_loss=0.03364, over 972322.90 frames.], batch size: 14, lr: 2.36e-04
2022-05-06 12:33:33,296 INFO [train.py:715] (4/8) Epoch 9, batch 16050, loss[loss=0.1535, simple_loss=0.2242, pruned_loss=0.04138, over 4757.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2146, pruned_loss=0.03378, over 971809.23 frames.], batch size: 14, lr: 2.36e-04
2022-05-06 12:34:12,505 INFO [train.py:715] (4/8) Epoch 9, batch 16100, loss[loss=0.135, simple_loss=0.2038, pruned_loss=0.03314, over 4760.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2154, pruned_loss=0.03446, over 971075.99 frames.], batch size: 12, lr: 2.36e-04
2022-05-06 12:34:51,591 INFO [train.py:715] (4/8) Epoch 9, batch 16150, loss[loss=0.1715, simple_loss=0.2434, pruned_loss=0.0498, over 4752.00 frames.], tot_loss[loss=0.142, simple_loss=0.2152, pruned_loss=0.03437, over 971387.53 frames.], batch size: 16, lr: 2.36e-04
2022-05-06 12:35:30,768 INFO [train.py:715] (4/8) Epoch 9, batch 16200, loss[loss=0.1303, simple_loss=0.2055, pruned_loss=0.02757, over 4916.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2142, pruned_loss=0.03399, over 970959.71 frames.], batch size: 23, lr: 2.36e-04
2022-05-06 12:36:10,109 INFO [train.py:715] (4/8) Epoch 9, batch 16250, loss[loss=0.1366, simple_loss=0.2181, pruned_loss=0.02749, over 4953.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2148, pruned_loss=0.0345, over 970679.95 frames.], batch size: 29, lr: 2.35e-04
2022-05-06 12:36:49,785 INFO [train.py:715] (4/8) Epoch 9, batch 16300, loss[loss=0.1526, simple_loss=0.2335, pruned_loss=0.03584, over 4899.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03402, over 971097.42 frames.], batch size: 19, lr: 2.35e-04
2022-05-06 12:37:27,728 INFO [train.py:715] (4/8) Epoch 9, batch 16350, loss[loss=0.175, simple_loss=0.2541, pruned_loss=0.04791, over 4780.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2139, pruned_loss=0.03463, over 971346.61 frames.], batch size: 17, lr: 2.35e-04
2022-05-06 12:38:07,160 INFO [train.py:715] (4/8) Epoch 9, batch 16400, loss[loss=0.1584, simple_loss=0.2324, pruned_loss=0.04217, over 4757.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03418, over 971747.59 frames.], batch size: 19, lr: 2.35e-04
2022-05-06 12:38:47,053 INFO [train.py:715] (4/8) Epoch 9, batch 16450, loss[loss=0.139, simple_loss=0.2131, pruned_loss=0.03243, over 4824.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2147, pruned_loss=0.03476, over 972045.01 frames.], batch size: 26, lr: 2.35e-04
2022-05-06 12:39:25,805 INFO [train.py:715] (4/8) Epoch 9, batch 16500, loss[loss=0.1279, simple_loss=0.2018, pruned_loss=0.02697, over 4983.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2146, pruned_loss=0.03464, over 972524.50 frames.], batch size: 28, lr: 2.35e-04
2022-05-06 12:40:04,383 INFO [train.py:715] (4/8) Epoch 9, batch 16550, loss[loss=0.1522, simple_loss=0.214, pruned_loss=0.04518, over 4861.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2149, pruned_loss=0.03487, over 972711.69 frames.], batch size: 16, lr: 2.35e-04
2022-05-06 12:40:43,845 INFO [train.py:715] (4/8) Epoch 9, batch 16600, loss[loss=0.1377, simple_loss=0.2149, pruned_loss=0.03023, over 4786.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2149, pruned_loss=0.03484, over 972400.55 frames.], batch size: 18, lr: 2.35e-04
2022-05-06 12:41:23,435 INFO [train.py:715] (4/8) Epoch 9, batch 16650, loss[loss=0.1205, simple_loss=0.1871, pruned_loss=0.02695, over 4865.00 frames.], tot_loss[loss=0.1413, simple_loss=0.214, pruned_loss=0.03425, over 972678.05 frames.], batch size: 20, lr: 2.35e-04
2022-05-06 12:42:02,350 INFO [train.py:715] (4/8) Epoch 9, batch 16700, loss[loss=0.1476, simple_loss=0.2237, pruned_loss=0.03571, over 4695.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03363, over 971870.26 frames.], batch size: 15, lr: 2.35e-04
2022-05-06 12:42:41,631 INFO [train.py:715] (4/8) Epoch 9, batch 16750, loss[loss=0.1168, simple_loss=0.1892, pruned_loss=0.02227, over 4922.00 frames.], tot_loss[loss=0.14, simple_loss=0.2132, pruned_loss=0.03341, over 972537.18 frames.], batch size: 29, lr: 2.35e-04
2022-05-06 12:43:21,426 INFO [train.py:715] (4/8) Epoch 9, batch 16800, loss[loss=0.1345, simple_loss=0.2093, pruned_loss=0.02989, over 4802.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2134, pruned_loss=0.03381, over 973216.19 frames.], batch size: 14, lr: 2.35e-04
2022-05-06 12:44:01,050 INFO [train.py:715] (4/8) Epoch 9, batch 16850, loss[loss=0.1445, simple_loss=0.205, pruned_loss=0.04198, over 4915.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03403, over 972252.12 frames.], batch size: 23, lr: 2.35e-04
2022-05-06 12:44:40,471 INFO [train.py:715] (4/8) Epoch 9, batch 16900, loss[loss=0.1776, simple_loss=0.2532, pruned_loss=0.05103, over 4884.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.0341, over 972205.85 frames.], batch size: 22, lr: 2.35e-04
2022-05-06 12:45:20,534 INFO [train.py:715] (4/8) Epoch 9, batch 16950, loss[loss=0.1605, simple_loss=0.2202, pruned_loss=0.05044, over 4839.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2147, pruned_loss=0.03453, over 972653.42 frames.], batch size: 15, lr: 2.35e-04
2022-05-06 12:46:00,232 INFO [train.py:715] (4/8) Epoch 9, batch 17000, loss[loss=0.1456, simple_loss=0.2217, pruned_loss=0.03472, over 4697.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2154, pruned_loss=0.03487, over 970967.65 frames.], batch size: 15, lr: 2.35e-04
2022-05-06 12:46:38,806 INFO [train.py:715] (4/8) Epoch 9, batch 17050, loss[loss=0.1791, simple_loss=0.2395, pruned_loss=0.05936, over 4929.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2156, pruned_loss=0.0351, over 971827.60 frames.], batch size: 38, lr: 2.35e-04
2022-05-06 12:47:18,388 INFO [train.py:715] (4/8) Epoch 9, batch 17100, loss[loss=0.1093, simple_loss=0.1848, pruned_loss=0.01687, over 4747.00 frames.], tot_loss[loss=0.143, simple_loss=0.2157, pruned_loss=0.03518, over 971247.40 frames.], batch size: 19, lr: 2.35e-04
2022-05-06 12:47:58,062 INFO [train.py:715] (4/8) Epoch 9, batch 17150, loss[loss=0.1186, simple_loss=0.1902, pruned_loss=0.02349, over 4929.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2149, pruned_loss=0.0347, over 972562.72 frames.], batch size: 29, lr: 2.35e-04
2022-05-06 12:48:37,321 INFO [train.py:715] (4/8) Epoch 9, batch 17200, loss[loss=0.1567, simple_loss=0.2434, pruned_loss=0.03499, over 4808.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2144, pruned_loss=0.03444, over 972407.68 frames.], batch size: 13, lr: 2.35e-04
2022-05-06 12:49:15,994 INFO [train.py:715] (4/8) Epoch 9, batch 17250, loss[loss=0.1634, simple_loss=0.225, pruned_loss=0.05086, over 4848.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.0342, over 972492.58 frames.], batch size: 30, lr: 2.35e-04
2022-05-06 12:49:54,884 INFO [train.py:715] (4/8) Epoch 9, batch 17300, loss[loss=0.1395, simple_loss=0.2187, pruned_loss=0.03017, over 4831.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2138, pruned_loss=0.03422, over 971644.54 frames.], batch size: 25, lr: 2.35e-04
2022-05-06 12:50:33,971 INFO [train.py:715] (4/8) Epoch 9, batch 17350, loss[loss=0.1755, simple_loss=0.258, pruned_loss=0.04654, over 4938.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2145, pruned_loss=0.03457, over 971809.26 frames.], batch size: 23, lr: 2.35e-04
2022-05-06 12:51:13,078 INFO [train.py:715] (4/8) Epoch 9, batch 17400, loss[loss=0.1164, simple_loss=0.1954, pruned_loss=0.01873, over 4909.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03397, over 971316.33 frames.], batch size: 18, lr: 2.35e-04
2022-05-06 12:51:52,391 INFO [train.py:715] (4/8) Epoch 9, batch 17450, loss[loss=0.1366, simple_loss=0.2122, pruned_loss=0.03052, over 4825.00 frames.], tot_loss[loss=0.1421, simple_loss=0.215, pruned_loss=0.03463, over 971514.06 frames.], batch size: 27, lr: 2.35e-04
2022-05-06 12:52:31,597 INFO [train.py:715] (4/8) Epoch 9, batch 17500, loss[loss=0.1483, simple_loss=0.2116, pruned_loss=0.04253, over 4793.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2151, pruned_loss=0.03454, over 970941.59 frames.], batch size: 17, lr: 2.35e-04
2022-05-06 12:53:10,812 INFO [train.py:715] (4/8) Epoch 9, batch 17550, loss[loss=0.1149, simple_loss=0.1929, pruned_loss=0.01841, over 4810.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2148, pruned_loss=0.03444, over 971272.06 frames.], batch size: 26, lr: 2.35e-04
2022-05-06 12:53:49,891 INFO [train.py:715] (4/8) Epoch 9, batch 17600, loss[loss=0.1261, simple_loss=0.1926, pruned_loss=0.02974, over 4853.00 frames.], tot_loss[loss=0.142, simple_loss=0.2148, pruned_loss=0.03464, over 971328.07 frames.], batch size: 20, lr: 2.35e-04
2022-05-06 12:54:29,583 INFO [train.py:715] (4/8) Epoch 9, batch 17650, loss[loss=0.1301, simple_loss=0.2136, pruned_loss=0.02329, over 4796.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03414, over 971256.74 frames.], batch size: 21, lr: 2.35e-04
2022-05-06 12:55:08,478 INFO [train.py:715] (4/8) Epoch 9, batch 17700, loss[loss=0.1378, simple_loss=0.2157, pruned_loss=0.02998, over 4954.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2134, pruned_loss=0.03374, over 970835.31 frames.], batch size: 24, lr: 2.35e-04
2022-05-06 12:55:47,742 INFO [train.py:715] (4/8) Epoch 9, batch 17750, loss[loss=0.1541, simple_loss=0.2253, pruned_loss=0.04148, over 4777.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2129, pruned_loss=0.03365, over 972137.75 frames.], batch size: 14, lr: 2.35e-04
2022-05-06 12:56:27,546 INFO [train.py:715] (4/8) Epoch 9, batch 17800, loss[loss=0.1228, simple_loss=0.1976, pruned_loss=0.02406, over 4935.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2138, pruned_loss=0.03421, over 972184.64 frames.], batch size: 29, lr: 2.35e-04
2022-05-06 12:57:06,521 INFO [train.py:715] (4/8) Epoch 9, batch 17850, loss[loss=0.1302, simple_loss=0.2009, pruned_loss=0.02974, over 4984.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.0336, over 971890.98 frames.], batch size: 14, lr: 2.35e-04
2022-05-06 12:57:45,749 INFO [train.py:715] (4/8) Epoch 9, batch 17900, loss[loss=0.1622, simple_loss=0.2348, pruned_loss=0.04476, over 4949.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2123, pruned_loss=0.03318, over 973015.37 frames.], batch size: 35, lr: 2.35e-04
2022-05-06 12:58:25,610 INFO [train.py:715] (4/8) Epoch 9, batch 17950, loss[loss=0.1557, simple_loss=0.2293, pruned_loss=0.04104, over 4766.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2123, pruned_loss=0.03335, over 972850.66 frames.], batch size: 16, lr: 2.35e-04
2022-05-06 12:59:04,971 INFO [train.py:715] (4/8) Epoch 9, batch 18000, loss[loss=0.1518, simple_loss=0.2228, pruned_loss=0.04044, over 4970.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2139, pruned_loss=0.03421, over 972830.72 frames.], batch size: 39, lr: 2.35e-04
2022-05-06 12:59:04,972 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 12:59:14,500 INFO [train.py:742] (4/8) Epoch 9, validation: loss=0.1068, simple_loss=0.1912, pruned_loss=0.01121, over 914524.00 frames.
2022-05-06 12:59:53,953 INFO [train.py:715] (4/8) Epoch 9, batch 18050, loss[loss=0.14, simple_loss=0.218, pruned_loss=0.03102, over 4804.00 frames.], tot_loss[loss=0.1412, simple_loss=0.214, pruned_loss=0.03421, over 973328.65 frames.], batch size: 21, lr: 2.35e-04
2022-05-06 13:00:33,775 INFO [train.py:715] (4/8) Epoch 9, batch 18100, loss[loss=0.1581, simple_loss=0.2274, pruned_loss=0.04442, over 4880.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2155, pruned_loss=0.03497, over 973299.72 frames.], batch size: 16, lr: 2.35e-04
2022-05-06 13:01:13,063 INFO [train.py:715] (4/8) Epoch 9, batch 18150, loss[loss=0.1201, simple_loss=0.1903, pruned_loss=0.02496, over 4854.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2162, pruned_loss=0.03556, over 972882.07 frames.], batch size: 20, lr: 2.35e-04
2022-05-06 13:01:52,673 INFO [train.py:715] (4/8) Epoch 9, batch 18200, loss[loss=0.1284, simple_loss=0.2059, pruned_loss=0.02547, over 4744.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03481, over 972249.81 frames.], batch size: 19, lr: 2.35e-04
2022-05-06 13:02:31,901 INFO [train.py:715] (4/8) Epoch 9, batch 18250, loss[loss=0.1452, simple_loss=0.213, pruned_loss=0.03869, over 4926.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03486, over 972730.33 frames.], batch size: 29, lr: 2.35e-04
2022-05-06 13:03:11,074 INFO [train.py:715] (4/8) Epoch 9, batch 18300, loss[loss=0.1325, simple_loss=0.2159, pruned_loss=0.02455, over 4749.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03482, over 972357.13 frames.], batch size: 16, lr: 2.35e-04
2022-05-06 13:03:50,426 INFO [train.py:715] (4/8) Epoch 9, batch 18350, loss[loss=0.1642, simple_loss=0.2154, pruned_loss=0.05648, over 4758.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03454, over 972417.10 frames.], batch size: 19, lr: 2.35e-04
2022-05-06 13:04:29,596 INFO [train.py:715] (4/8) Epoch 9, batch 18400, loss[loss=0.156, simple_loss=0.2315, pruned_loss=0.04026, over 4815.00 frames.], tot_loss[loss=0.1418, simple_loss=0.214, pruned_loss=0.03476, over 971974.40 frames.], batch size: 25, lr: 2.35e-04
2022-05-06 13:05:08,636 INFO [train.py:715] (4/8) Epoch 9, batch 18450, loss[loss=0.1542, simple_loss=0.2276, pruned_loss=0.04044, over 4815.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2133, pruned_loss=0.03455, over 971727.07 frames.], batch size: 27, lr: 2.35e-04
2022-05-06 13:05:47,599 INFO [train.py:715] (4/8) Epoch 9, batch 18500, loss[loss=0.1631, simple_loss=0.2391, pruned_loss=0.04358, over 4842.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2137, pruned_loss=0.03477, over 972054.30 frames.], batch size: 26, lr: 2.35e-04
2022-05-06 13:06:26,996 INFO [train.py:715] (4/8) Epoch 9, batch 18550, loss[loss=0.147, simple_loss=0.2226, pruned_loss=0.03573, over 4943.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2131, pruned_loss=0.03462, over 971584.37 frames.], batch size: 21, lr: 2.35e-04
2022-05-06 13:07:06,065 INFO [train.py:715] (4/8) Epoch 9, batch 18600, loss[loss=0.1425, simple_loss=0.2064, pruned_loss=0.0393, over 4786.00 frames.], tot_loss[loss=0.1398, simple_loss=0.212, pruned_loss=0.03379, over 972274.62 frames.], batch size: 14, lr: 2.35e-04
2022-05-06 13:07:44,915 INFO [train.py:715] (4/8) Epoch 9, batch 18650, loss[loss=0.1601, simple_loss=0.2286, pruned_loss=0.0458, over 4775.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2123, pruned_loss=0.03408, over 972172.32 frames.], batch size: 17, lr: 2.35e-04
2022-05-06 13:08:24,473 INFO [train.py:715] (4/8) Epoch 9, batch 18700, loss[loss=0.1154, simple_loss=0.19, pruned_loss=0.02034, over 4763.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03386, over 972599.96 frames.], batch size: 19, lr: 2.35e-04
2022-05-06 13:09:03,185 INFO [train.py:715] (4/8) Epoch 9, batch 18750, loss[loss=0.1499, simple_loss=0.2273, pruned_loss=0.03621, over 4874.00 frames.], tot_loss[loss=0.14, simple_loss=0.2126, pruned_loss=0.03373, over 972435.89 frames.], batch size: 16, lr: 2.35e-04
2022-05-06 13:09:42,756 INFO [train.py:715] (4/8) Epoch 9, batch 18800, loss[loss=0.1544, simple_loss=0.2278, pruned_loss=0.04052, over 4929.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2129, pruned_loss=0.03384, over 972643.48 frames.], batch size: 39, lr: 2.35e-04
2022-05-06 13:10:21,586 INFO [train.py:715] (4/8) Epoch 9, batch 18850, loss[loss=0.1471, simple_loss=0.224, pruned_loss=0.03513, over 4892.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03386, over 971249.43 frames.], batch size: 22, lr: 2.35e-04
2022-05-06 13:11:00,817 INFO [train.py:715] (4/8) Epoch 9, batch 18900, loss[loss=0.1678, simple_loss=0.2273, pruned_loss=0.05413, over 4809.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2139, pruned_loss=0.03424, over 972466.55 frames.], batch size: 24, lr: 2.35e-04
2022-05-06 13:11:40,178 INFO [train.py:715] (4/8) Epoch 9, batch 18950, loss[loss=0.1376, simple_loss=0.2027, pruned_loss=0.03621, over 4786.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03436, over 972176.82 frames.], batch size: 12, lr: 2.35e-04
2022-05-06 13:12:18,867 INFO [train.py:715] (4/8) Epoch 9, batch 19000, loss[loss=0.1239, simple_loss=0.1989, pruned_loss=0.02439, over 4966.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03367, over 972345.94 frames.], batch size: 28, lr: 2.35e-04
2022-05-06 13:12:58,959 INFO [train.py:715] (4/8) Epoch 9, batch 19050, loss[loss=0.187, simple_loss=0.2413, pruned_loss=0.06636, over 4914.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2142, pruned_loss=0.03396, over 972452.47 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:13:38,428 INFO [train.py:715] (4/8) Epoch 9, batch 19100, loss[loss=0.1241, simple_loss=0.2082, pruned_loss=0.01997, over 4746.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.03407, over 972471.96 frames.], batch size: 19, lr: 2.34e-04
2022-05-06 13:14:17,256 INFO [train.py:715] (4/8) Epoch 9, batch 19150, loss[loss=0.172, simple_loss=0.2365, pruned_loss=0.05373, over 4855.00 frames.], tot_loss[loss=0.141, simple_loss=0.2137, pruned_loss=0.03418, over 972564.14 frames.], batch size: 30, lr: 2.34e-04
2022-05-06 13:14:57,087 INFO [train.py:715] (4/8) Epoch 9, batch 19200, loss[loss=0.1378, simple_loss=0.214, pruned_loss=0.03084, over 4977.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03438, over 973327.18 frames.], batch size: 24, lr: 2.34e-04
2022-05-06 13:15:36,594 INFO [train.py:715] (4/8) Epoch 9, batch 19250, loss[loss=0.1451, simple_loss=0.217, pruned_loss=0.03662, over 4783.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2136, pruned_loss=0.03439, over 972464.13 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:16:15,483 INFO [train.py:715] (4/8) Epoch 9, batch 19300, loss[loss=0.1619, simple_loss=0.2389, pruned_loss=0.04246, over 4934.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2137, pruned_loss=0.03456, over 972906.23 frames.], batch size: 21, lr: 2.34e-04
2022-05-06 13:16:54,061 INFO [train.py:715] (4/8) Epoch 9, batch 19350, loss[loss=0.1289, simple_loss=0.2049, pruned_loss=0.02641, over 4981.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2141, pruned_loss=0.0344, over 973312.64 frames.], batch size: 28, lr: 2.34e-04
2022-05-06 13:17:34,089 INFO [train.py:715] (4/8) Epoch 9, batch 19400, loss[loss=0.1366, simple_loss=0.215, pruned_loss=0.0291, over 4796.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.03467, over 972358.16 frames.], batch size: 24, lr: 2.34e-04
2022-05-06 13:18:13,121 INFO [train.py:715] (4/8) Epoch 9, batch 19450, loss[loss=0.1443, simple_loss=0.2188, pruned_loss=0.03488, over 4928.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.03496, over 972219.10 frames.], batch size: 23, lr: 2.34e-04
2022-05-06 13:18:51,810 INFO [train.py:715] (4/8) Epoch 9, batch 19500, loss[loss=0.1424, simple_loss=0.2151, pruned_loss=0.03484, over 4742.00 frames.], tot_loss[loss=0.1417, simple_loss=0.214, pruned_loss=0.03465, over 972072.48 frames.], batch size: 16, lr: 2.34e-04
2022-05-06 13:19:30,941 INFO [train.py:715] (4/8) Epoch 9, batch 19550, loss[loss=0.1464, simple_loss=0.2128, pruned_loss=0.04004, over 4917.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03443, over 972247.17 frames.], batch size: 35, lr: 2.34e-04
2022-05-06 13:20:10,203 INFO [train.py:715] (4/8) Epoch 9, batch 19600, loss[loss=0.1327, simple_loss=0.2147, pruned_loss=0.02535, over 4798.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2137, pruned_loss=0.03463, over 971961.22 frames.], batch size: 21, lr: 2.34e-04
2022-05-06 13:20:48,781 INFO [train.py:715] (4/8) Epoch 9, batch 19650, loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03019, over 4960.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2148, pruned_loss=0.03523, over 971769.25 frames.], batch size: 24, lr: 2.34e-04
2022-05-06 13:21:27,272 INFO [train.py:715] (4/8) Epoch 9, batch 19700, loss[loss=0.1504, simple_loss=0.2216, pruned_loss=0.03959, over 4921.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2152, pruned_loss=0.03511, over 972646.76 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:22:07,182 INFO [train.py:715] (4/8) Epoch 9, batch 19750, loss[loss=0.1343, simple_loss=0.1983, pruned_loss=0.03521, over 4844.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2151, pruned_loss=0.03483, over 971824.16 frames.], batch size: 13, lr: 2.34e-04
2022-05-06 13:22:46,851 INFO [train.py:715] (4/8) Epoch 9, batch 19800, loss[loss=0.1325, simple_loss=0.2075, pruned_loss=0.02878, over 4798.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.03506, over 971470.58 frames.], batch size: 21, lr: 2.34e-04
2022-05-06 13:23:26,647 INFO [train.py:715] (4/8) Epoch 9, batch 19850, loss[loss=0.1438, simple_loss=0.2116, pruned_loss=0.03799, over 4844.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2145, pruned_loss=0.03513, over 971477.96 frames.], batch size: 30, lr: 2.34e-04
2022-05-06 13:24:06,289 INFO [train.py:715] (4/8) Epoch 9, batch 19900, loss[loss=0.1455, simple_loss=0.2231, pruned_loss=0.03391, over 4764.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2147, pruned_loss=0.03543, over 970973.29 frames.], batch size: 19, lr: 2.34e-04
2022-05-06 13:24:45,453 INFO [train.py:715] (4/8) Epoch 9, batch 19950, loss[loss=0.1586, simple_loss=0.2217, pruned_loss=0.04774, over 4862.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2147, pruned_loss=0.03503, over 971599.52 frames.], batch size: 32, lr: 2.34e-04
2022-05-06 13:25:24,504 INFO [train.py:715] (4/8) Epoch 9, batch 20000, loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03062, over 4922.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2131, pruned_loss=0.0343, over 972093.69 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:26:02,952 INFO [train.py:715] (4/8) Epoch 9, batch 20050, loss[loss=0.1475, simple_loss=0.2252, pruned_loss=0.03491, over 4981.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03425, over 972736.47 frames.], batch size: 39, lr: 2.34e-04
2022-05-06 13:26:42,421 INFO [train.py:715] (4/8) Epoch 9, batch 20100, loss[loss=0.1294, simple_loss=0.209, pruned_loss=0.02494, over 4793.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2132, pruned_loss=0.03388, over 972095.11 frames.], batch size: 24, lr: 2.34e-04
2022-05-06 13:27:21,486 INFO [train.py:715] (4/8) Epoch 9, batch 20150, loss[loss=0.1167, simple_loss=0.1917, pruned_loss=0.0208, over 4772.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03407, over 972384.90 frames.], batch size: 14, lr: 2.34e-04
2022-05-06 13:27:59,967 INFO [train.py:715] (4/8) Epoch 9, batch 20200, loss[loss=0.1242, simple_loss=0.2032, pruned_loss=0.02263, over 4935.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.03382, over 972349.69 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:28:39,473 INFO [train.py:715] (4/8) Epoch 9, batch 20250, loss[loss=0.1331, simple_loss=0.2083, pruned_loss=0.02898, over 4801.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2143, pruned_loss=0.03443, over 971705.50 frames.], batch size: 24, lr: 2.34e-04
2022-05-06 13:29:18,327 INFO [train.py:715] (4/8) Epoch 9, batch 20300, loss[loss=0.1511, simple_loss=0.224, pruned_loss=0.03904, over 4808.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.03389, over 971798.34 frames.], batch size: 25, lr: 2.34e-04
2022-05-06 13:29:57,719 INFO [train.py:715] (4/8) Epoch 9, batch 20350, loss[loss=0.1168, simple_loss=0.1905, pruned_loss=0.02151, over 4853.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2139, pruned_loss=0.03372, over 971273.53 frames.], batch size: 13, lr: 2.34e-04
2022-05-06 13:30:37,200 INFO [train.py:715] (4/8) Epoch 9, batch 20400, loss[loss=0.1288, simple_loss=0.2007, pruned_loss=0.02843, over 4844.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03401, over 971151.62 frames.], batch size: 30, lr: 2.34e-04
2022-05-06 13:31:17,090 INFO [train.py:715] (4/8) Epoch 9, batch 20450, loss[loss=0.1267, simple_loss=0.1904, pruned_loss=0.03151, over 4809.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2138, pruned_loss=0.03453, over 971540.39 frames.], batch size: 13, lr: 2.34e-04
2022-05-06 13:31:56,597 INFO [train.py:715] (4/8) Epoch 9, batch 20500, loss[loss=0.1507, simple_loss=0.2289, pruned_loss=0.03627, over 4767.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.03444, over 972290.31 frames.], batch size: 19, lr: 2.34e-04
2022-05-06 13:32:35,667 INFO [train.py:715] (4/8) Epoch 9, batch 20550, loss[loss=0.1155, simple_loss=0.1906, pruned_loss=0.02023, over 4746.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2139, pruned_loss=0.03477, over 972161.54 frames.], batch size: 19, lr: 2.34e-04
2022-05-06 13:33:14,861 INFO [train.py:715] (4/8) Epoch 9, batch 20600, loss[loss=0.1564, simple_loss=0.2263, pruned_loss=0.04322, over 4989.00 frames.], tot_loss[loss=0.1416, simple_loss=0.214, pruned_loss=0.03466, over 971556.42 frames.], batch size: 25, lr: 2.34e-04
2022-05-06 13:33:53,311 INFO [train.py:715] (4/8) Epoch 9, batch 20650, loss[loss=0.1232, simple_loss=0.1884, pruned_loss=0.02899, over 4902.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.0348, over 971550.85 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:34:32,416 INFO [train.py:715] (4/8) Epoch 9, batch 20700, loss[loss=0.142, simple_loss=0.2105, pruned_loss=0.03673, over 4818.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03429, over 972083.82 frames.], batch size: 13, lr: 2.34e-04
2022-05-06 13:35:11,247 INFO [train.py:715] (4/8) Epoch 9, batch 20750, loss[loss=0.1361, simple_loss=0.2029, pruned_loss=0.03463, over 4802.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03442, over 972159.48 frames.], batch size: 13, lr: 2.34e-04
2022-05-06 13:35:50,838 INFO [train.py:715] (4/8) Epoch 9, batch 20800, loss[loss=0.1551, simple_loss=0.2273, pruned_loss=0.04143, over 4906.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2139, pruned_loss=0.03426, over 972265.88 frames.], batch size: 39, lr: 2.34e-04
2022-05-06 13:36:30,207 INFO [train.py:715] (4/8) Epoch 9, batch 20850, loss[loss=0.1398, simple_loss=0.2076, pruned_loss=0.036, over 4914.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.0349, over 971637.09 frames.], batch size: 39, lr: 2.34e-04
2022-05-06 13:37:09,648 INFO [train.py:715] (4/8) Epoch 9, batch 20900, loss[loss=0.1621, simple_loss=0.242, pruned_loss=0.04113, over 4744.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2145, pruned_loss=0.03463, over 971263.51 frames.], batch size: 16, lr: 2.34e-04
2022-05-06 13:37:49,144 INFO [train.py:715] (4/8) Epoch 9, batch 20950, loss[loss=0.1587, simple_loss=0.2229, pruned_loss=0.04728, over 4917.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2157, pruned_loss=0.03541, over 971273.41 frames.], batch size: 18, lr: 2.34e-04
2022-05-06 13:38:28,443 INFO [train.py:715] (4/8) Epoch 9, batch 21000, loss[loss=0.1453, simple_loss=0.2112, pruned_loss=0.03969, over 4882.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.035, over 971680.03 frames.], batch size: 16, lr: 2.34e-04
2022-05-06 13:38:28,444 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 13:38:38,082 INFO [train.py:742] (4/8) Epoch 9, validation: loss=0.1069, simple_loss=0.1912, pruned_loss=0.01129, over 914524.00 frames.
2022-05-06 13:39:17,241 INFO [train.py:715] (4/8) Epoch 9, batch 21050, loss[loss=0.1403, simple_loss=0.2183, pruned_loss=0.03111, over 4846.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03452, over 971734.48 frames.], batch size: 15, lr: 2.34e-04
2022-05-06 13:39:56,159 INFO [train.py:715] (4/8) Epoch 9, batch 21100, loss[loss=0.1573, simple_loss=0.2175, pruned_loss=0.04853, over 4858.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03463, over 971993.75 frames.], batch size: 32, lr: 2.34e-04
2022-05-06 13:40:35,519 INFO [train.py:715] (4/8) Epoch 9, batch 21150, loss[loss=0.1441, simple_loss=0.2107, pruned_loss=0.03875, over 4818.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.03429, over 971375.15 frames.], batch size: 13, lr: 2.34e-04
2022-05-06 13:41:14,527 INFO [train.py:715] (4/8) Epoch 9, batch 21200, loss[loss=0.1352, simple_loss=0.2041, pruned_loss=0.03319, over 4929.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.03396, over 971631.62 frames.], batch size: 29, lr: 2.34e-04
2022-05-06 13:41:54,098 INFO [train.py:715] (4/8) Epoch 9, batch 21250, loss[loss=0.155, simple_loss=0.213, pruned_loss=0.04845, over 4767.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2136, pruned_loss=0.03398, over 971793.20 frames.], batch size: 17, lr: 2.34e-04
2022-05-06 13:42:32,486 INFO [train.py:715] (4/8) Epoch 9, batch 21300, loss[loss=0.1613, simple_loss=0.2418, pruned_loss=0.04043, over 4744.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2139, pruned_loss=0.03444, over 971535.90 frames.], batch size: 19, lr: 2.34e-04
2022-05-06 13:43:11,098 INFO [train.py:715] (4/8) Epoch 9, batch 21350, loss[loss=0.1399, simple_loss=0.2162, pruned_loss=0.03184, over 4781.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03424, over 971861.90 frames.], batch size: 17, lr: 2.34e-04
2022-05-06 13:43:50,029 INFO [train.py:715] (4/8) Epoch 9, batch 21400, loss[loss=0.1114, simple_loss=0.1757, pruned_loss=0.02359, over 4808.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2127, pruned_loss=0.03416, over 972052.87 frames.], batch size: 13, lr: 2.34e-04
2022-05-06 13:44:28,775 INFO [train.py:715] (4/8) Epoch 9, batch 21450, loss[loss=0.1388, simple_loss=0.2246, pruned_loss=0.02654, over 4940.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2135, pruned_loss=0.03431, over 972819.21 frames.], batch size: 21, lr: 2.34e-04
2022-05-06 13:45:07,165 INFO [train.py:715] (4/8) Epoch 9, batch 21500, loss[loss=0.15, simple_loss=0.2227, pruned_loss=0.0387, over 4791.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03468, over 972651.75 frames.], batch size: 17, lr: 2.34e-04
2022-05-06 13:45:46,282 INFO [train.py:715] (4/8) Epoch 9, batch 21550, loss[loss=0.1523, simple_loss=0.2132, pruned_loss=0.04574, over 4977.00 frames.], tot_loss[loss=0.1418, simple_loss=0.214, pruned_loss=0.03486, over 971898.16 frames.], batch size: 15, lr: 2.34e-04
2022-05-06 13:46:24,997 INFO [train.py:715] (4/8) Epoch 9, batch 21600, loss[loss=0.154, simple_loss=0.235, pruned_loss=0.03653, over 4880.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03484, over 971741.57 frames.], batch size: 38, lr: 2.34e-04
2022-05-06 13:47:04,088 INFO [train.py:715] (4/8) Epoch 9, batch 21650, loss[loss=0.1934, simple_loss=0.2745, pruned_loss=0.05617, over 4985.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.03499, over 971895.34 frames.], batch size: 15, lr: 2.34e-04
2022-05-06 13:47:43,366 INFO [train.py:715] (4/8) Epoch 9, batch 21700, loss[loss=0.1783, simple_loss=0.2444, pruned_loss=0.0561, over 4944.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03479, over 971811.66 frames.], batch size: 35, lr: 2.34e-04
2022-05-06 13:48:22,454 INFO [train.py:715] (4/8) Epoch 9, batch 21750, loss[loss=0.136, simple_loss=0.2054, pruned_loss=0.03332, over 4743.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03428, over 971110.31 frames.], batch size: 16, lr: 2.34e-04
2022-05-06 13:49:01,562 INFO [train.py:715] (4/8) Epoch 9, batch 21800, loss[loss=0.134, simple_loss=0.2021, pruned_loss=0.03294, over 4756.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03439, over 970961.90 frames.], batch size: 16, lr: 2.34e-04
2022-05-06 13:49:41,088 INFO [train.py:715] (4/8) Epoch 9, batch 21850, loss[loss=0.1499, simple_loss=0.2266, pruned_loss=0.0366, over 4808.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2149, pruned_loss=0.0349, over 971383.98 frames.], batch size: 25, lr: 2.34e-04
2022-05-06 13:50:20,437 INFO [train.py:715] (4/8) Epoch 9, batch 21900, loss[loss=0.143, simple_loss=0.2089, pruned_loss=0.03853, over 4681.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03502, over 971245.30 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 13:50:59,007 INFO [train.py:715] (4/8) Epoch 9, batch 21950, loss[loss=0.1484, simple_loss=0.2225, pruned_loss=0.03717, over 4954.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.03448, over 972022.80 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 13:51:37,910 INFO [train.py:715] (4/8) Epoch 9, batch 22000, loss[loss=0.1249, simple_loss=0.2009, pruned_loss=0.0245, over 4816.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.034, over 972962.18 frames.], batch size: 25, lr: 2.33e-04
2022-05-06 13:52:16,809 INFO [train.py:715] (4/8) Epoch 9, batch 22050, loss[loss=0.1352, simple_loss=0.2056, pruned_loss=0.03245, over 4971.00 frames.], tot_loss[loss=0.141, simple_loss=0.2132, pruned_loss=0.03441, over 972499.16 frames.], batch size: 21, lr: 2.33e-04
2022-05-06 13:52:56,513 INFO [train.py:715] (4/8) Epoch 9, batch 22100, loss[loss=0.1114, simple_loss=0.1831, pruned_loss=0.01991, over 4788.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2139, pruned_loss=0.03479, over 973286.37 frames.], batch size: 14, lr: 2.33e-04
2022-05-06 13:53:35,796 INFO [train.py:715] (4/8) Epoch 9, batch 22150, loss[loss=0.136, simple_loss=0.2064, pruned_loss=0.03281, over 4835.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2139, pruned_loss=0.0351, over 972437.24 frames.], batch size: 27, lr: 2.33e-04
2022-05-06 13:54:14,966 INFO [train.py:715] (4/8) Epoch 9, batch 22200, loss[loss=0.1272, simple_loss=0.1972, pruned_loss=0.02867, over 4871.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2133, pruned_loss=0.03467, over 973009.90 frames.], batch size: 16, lr: 2.33e-04
2022-05-06 13:54:54,444 INFO [train.py:715] (4/8) Epoch 9, batch 22250, loss[loss=0.162, simple_loss=0.2244, pruned_loss=0.0498, over 4943.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2134, pruned_loss=0.03454, over 972509.81 frames.], batch size: 21, lr: 2.33e-04
2022-05-06 13:55:33,231 INFO [train.py:715] (4/8) Epoch 9, batch 22300, loss[loss=0.1209, simple_loss=0.2011, pruned_loss=0.02035, over 4928.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03404, over 973161.47 frames.], batch size: 29, lr: 2.33e-04
2022-05-06 13:56:11,832 INFO [train.py:715] (4/8) Epoch 9, batch 22350, loss[loss=0.1298, simple_loss=0.2061, pruned_loss=0.02672, over 4745.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03401, over 972969.08 frames.], batch size: 16, lr: 2.33e-04
2022-05-06 13:56:50,720 INFO [train.py:715] (4/8) Epoch 9, batch 22400, loss[loss=0.1409, simple_loss=0.2162, pruned_loss=0.03282, over 4861.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2134, pruned_loss=0.03386, over 972769.42 frames.], batch size: 20, lr: 2.33e-04
2022-05-06 13:57:29,424 INFO [train.py:715] (4/8) Epoch 9, batch 22450, loss[loss=0.1332, simple_loss=0.2044, pruned_loss=0.03101, over 4777.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2142, pruned_loss=0.03406, over 972549.87 frames.], batch size: 18, lr: 2.33e-04
2022-05-06 13:58:08,127 INFO [train.py:715] (4/8) Epoch 9, batch 22500, loss[loss=0.1304, simple_loss=0.2094, pruned_loss=0.02571, over 4980.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2142, pruned_loss=0.03376, over 971996.45 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 13:58:47,016 INFO [train.py:715] (4/8) Epoch 9, batch 22550, loss[loss=0.1304, simple_loss=0.2061, pruned_loss=0.02738, over 4837.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.03437, over 972083.10 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 13:59:26,037 INFO [train.py:715] (4/8) Epoch 9, batch 22600, loss[loss=0.1322, simple_loss=0.2021, pruned_loss=0.03111, over 4909.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2142, pruned_loss=0.03424, over 972523.20 frames.], batch size: 19, lr: 2.33e-04
2022-05-06 14:00:05,202 INFO [train.py:715] (4/8) Epoch 9, batch 22650, loss[loss=0.1517, simple_loss=0.2144, pruned_loss=0.04452, over 4822.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2146, pruned_loss=0.03423, over 972496.98 frames.], batch size: 21, lr: 2.33e-04
2022-05-06 14:00:44,243 INFO [train.py:715] (4/8) Epoch 9, batch 22700, loss[loss=0.1152, simple_loss=0.1877, pruned_loss=0.02137, over 4961.00 frames.], tot_loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03405, over 972827.44 frames.], batch size: 14, lr: 2.33e-04
2022-05-06 14:01:26,074 INFO [train.py:715] (4/8) Epoch 9, batch 22750, loss[loss=0.1042, simple_loss=0.168, pruned_loss=0.02023, over 4765.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2132, pruned_loss=0.0341, over 973162.74 frames.], batch size: 12, lr: 2.33e-04
2022-05-06 14:02:04,854 INFO [train.py:715] (4/8) Epoch 9, batch 22800, loss[loss=0.1513, simple_loss=0.2203, pruned_loss=0.04108, over 4887.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03437, over 972316.26 frames.], batch size: 39, lr: 2.33e-04
2022-05-06 14:02:44,149 INFO [train.py:715] (4/8) Epoch 9, batch 22850, loss[loss=0.1583, simple_loss=0.2182, pruned_loss=0.0492, over 4771.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2142, pruned_loss=0.03471, over 972334.55 frames.], batch size: 12, lr: 2.33e-04
2022-05-06 14:03:22,718 INFO [train.py:715] (4/8) Epoch 9, batch 22900, loss[loss=0.152, simple_loss=0.2195, pruned_loss=0.04228, over 4908.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2135, pruned_loss=0.03448, over 972367.44 frames.], batch size: 18, lr: 2.33e-04
2022-05-06 14:04:01,802 INFO [train.py:715] (4/8) Epoch 9, batch 22950, loss[loss=0.1285, simple_loss=0.203, pruned_loss=0.02705, over 4748.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2144, pruned_loss=0.0346, over 971723.72 frames.], batch size: 16, lr: 2.33e-04
2022-05-06 14:04:40,857 INFO [train.py:715] (4/8) Epoch 9, batch 23000, loss[loss=0.1279, simple_loss=0.2077, pruned_loss=0.02405, over 4806.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2137, pruned_loss=0.03469, over 971578.07 frames.], batch size: 21, lr: 2.33e-04
2022-05-06 14:05:20,249 INFO [train.py:715] (4/8) Epoch 9, batch 23050, loss[loss=0.1461, simple_loss=0.2254, pruned_loss=0.03342, over 4804.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03501, over 971912.45 frames.], batch size: 21, lr: 2.33e-04
2022-05-06 14:05:59,521 INFO [train.py:715] (4/8) Epoch 9, batch 23100, loss[loss=0.1393, simple_loss=0.2094, pruned_loss=0.03453, over 4802.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03483, over 971133.45 frames.], batch size: 14, lr: 2.33e-04
2022-05-06 14:06:38,546 INFO [train.py:715] (4/8) Epoch 9, batch 23150, loss[loss=0.1553, simple_loss=0.2267, pruned_loss=0.04198, over 4868.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2135, pruned_loss=0.03451, over 971133.42 frames.], batch size: 16, lr: 2.33e-04
2022-05-06 14:07:18,153 INFO [train.py:715] (4/8) Epoch 9, batch 23200, loss[loss=0.1447, simple_loss=0.2191, pruned_loss=0.03517, over 4790.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.03451, over 971868.78 frames.], batch size: 17, lr: 2.33e-04
2022-05-06 14:07:57,930 INFO [train.py:715] (4/8) Epoch 9, batch 23250, loss[loss=0.1486, simple_loss=0.208, pruned_loss=0.04461, over 4696.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03485, over 971884.96 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:08:37,699 INFO [train.py:715] (4/8) Epoch 9, batch 23300, loss[loss=0.1552, simple_loss=0.2342, pruned_loss=0.03808, over 4910.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2148, pruned_loss=0.03504, over 972357.93 frames.], batch size: 17, lr: 2.33e-04
2022-05-06 14:09:17,439 INFO [train.py:715] (4/8) Epoch 9, batch 23350, loss[loss=0.1188, simple_loss=0.184, pruned_loss=0.02685, over 4825.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.03494, over 972075.05 frames.], batch size: 13, lr: 2.33e-04
2022-05-06 14:09:56,734 INFO [train.py:715] (4/8) Epoch 9, batch 23400, loss[loss=0.1391, simple_loss=0.2117, pruned_loss=0.03322, over 4882.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.03514, over 971646.94 frames.], batch size: 22, lr: 2.33e-04
2022-05-06 14:10:35,593 INFO [train.py:715] (4/8) Epoch 9, batch 23450, loss[loss=0.1364, simple_loss=0.2195, pruned_loss=0.02666, over 4971.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2139, pruned_loss=0.03483, over 972007.75 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:11:14,356 INFO [train.py:715] (4/8) Epoch 9, batch 23500, loss[loss=0.147, simple_loss=0.2134, pruned_loss=0.0403, over 4788.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2135, pruned_loss=0.0346, over 971969.98 frames.], batch size: 14, lr: 2.33e-04
2022-05-06 14:11:52,877 INFO [train.py:715] (4/8) Epoch 9, batch 23550, loss[loss=0.1264, simple_loss=0.1839, pruned_loss=0.03444, over 4822.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2137, pruned_loss=0.03451, over 972002.58 frames.], batch size: 12, lr: 2.33e-04
2022-05-06 14:12:32,345 INFO [train.py:715] (4/8) Epoch 9, batch 23600, loss[loss=0.135, simple_loss=0.2096, pruned_loss=0.03021, over 4911.00 frames.], tot_loss[loss=0.1404, simple_loss=0.213, pruned_loss=0.0339, over 972525.50 frames.], batch size: 18, lr: 2.33e-04
2022-05-06 14:13:11,524 INFO [train.py:715] (4/8) Epoch 9, batch 23650, loss[loss=0.1408, simple_loss=0.2118, pruned_loss=0.03491, over 4912.00 frames.], tot_loss[loss=0.1405, simple_loss=0.213, pruned_loss=0.03396, over 972817.18 frames.], batch size: 17, lr: 2.33e-04
2022-05-06 14:13:50,883 INFO [train.py:715] (4/8) Epoch 9, batch 23700, loss[loss=0.1344, simple_loss=0.2028, pruned_loss=0.03304, over 4966.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2129, pruned_loss=0.03426, over 973006.93 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:14:30,051 INFO [train.py:715] (4/8) Epoch 9, batch 23750, loss[loss=0.1662, simple_loss=0.2254, pruned_loss=0.05349, over 4791.00 frames.], tot_loss[loss=0.142, simple_loss=0.2139, pruned_loss=0.03507, over 972989.78 frames.], batch size: 18, lr: 2.33e-04
2022-05-06 14:15:09,283 INFO [train.py:715] (4/8) Epoch 9, batch 23800, loss[loss=0.1597, simple_loss=0.2258, pruned_loss=0.04682, over 4716.00 frames.], tot_loss[loss=0.142, simple_loss=0.214, pruned_loss=0.03497, over 973117.43 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:15:48,392 INFO [train.py:715] (4/8) Epoch 9, batch 23850, loss[loss=0.1661, simple_loss=0.2402, pruned_loss=0.04597, over 4891.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03477, over 972725.58 frames.], batch size: 39, lr: 2.33e-04
2022-05-06 14:16:27,642 INFO [train.py:715] (4/8) Epoch 9, batch 23900, loss[loss=0.1434, simple_loss=0.2157, pruned_loss=0.03559, over 4980.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03439, over 972349.50 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:17:06,535 INFO [train.py:715] (4/8) Epoch 9, batch 23950, loss[loss=0.1343, simple_loss=0.2159, pruned_loss=0.02641, over 4912.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2144, pruned_loss=0.03443, over 972908.05 frames.], batch size: 29, lr: 2.33e-04
2022-05-06 14:17:45,502 INFO [train.py:715] (4/8) Epoch 9, batch 24000, loss[loss=0.1735, simple_loss=0.2353, pruned_loss=0.05584, over 4717.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03485, over 971677.90 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:17:45,503 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 14:17:55,355 INFO [train.py:742] (4/8) Epoch 9, validation: loss=0.1069, simple_loss=0.1913, pruned_loss=0.01128, over 914524.00 frames.
2022-05-06 14:18:34,693 INFO [train.py:715] (4/8) Epoch 9, batch 24050, loss[loss=0.1355, simple_loss=0.2081, pruned_loss=0.03145, over 4979.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2135, pruned_loss=0.0347, over 972495.55 frames.], batch size: 28, lr: 2.33e-04
2022-05-06 14:19:14,961 INFO [train.py:715] (4/8) Epoch 9, batch 24100, loss[loss=0.1241, simple_loss=0.1983, pruned_loss=0.02498, over 4861.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2127, pruned_loss=0.03402, over 972028.11 frames.], batch size: 20, lr: 2.33e-04
2022-05-06 14:19:54,469 INFO [train.py:715] (4/8) Epoch 9, batch 24150, loss[loss=0.1865, simple_loss=0.2682, pruned_loss=0.05242, over 4952.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2135, pruned_loss=0.03448, over 973025.82 frames.], batch size: 21, lr: 2.33e-04
2022-05-06 14:20:33,561 INFO [train.py:715] (4/8) Epoch 9, batch 24200, loss[loss=0.1247, simple_loss=0.2026, pruned_loss=0.02337, over 4812.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2137, pruned_loss=0.03453, over 973069.28 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:21:12,481 INFO [train.py:715] (4/8) Epoch 9, batch 24250, loss[loss=0.1408, simple_loss=0.2158, pruned_loss=0.03291, over 4842.00 frames.], tot_loss[loss=0.1417, simple_loss=0.214, pruned_loss=0.03469, over 973436.67 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:21:52,132 INFO [train.py:715] (4/8) Epoch 9, batch 24300, loss[loss=0.1594, simple_loss=0.2266, pruned_loss=0.04617, over 4703.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2137, pruned_loss=0.03445, over 973252.57 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:22:31,314 INFO [train.py:715] (4/8) Epoch 9, batch 24350, loss[loss=0.1627, simple_loss=0.2264, pruned_loss=0.04951, over 4834.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2144, pruned_loss=0.03522, over 973742.11 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:23:10,724 INFO [train.py:715] (4/8) Epoch 9, batch 24400, loss[loss=0.157, simple_loss=0.2167, pruned_loss=0.04871, over 4940.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2138, pruned_loss=0.03499, over 973275.09 frames.], batch size: 21, lr: 2.33e-04
2022-05-06 14:23:50,614 INFO [train.py:715] (4/8) Epoch 9, batch 24450, loss[loss=0.1696, simple_loss=0.2406, pruned_loss=0.0493, over 4908.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03502, over 972654.74 frames.], batch size: 18, lr: 2.33e-04
2022-05-06 14:24:30,637 INFO [train.py:715] (4/8) Epoch 9, batch 24500, loss[loss=0.1548, simple_loss=0.2287, pruned_loss=0.04038, over 4956.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2154, pruned_loss=0.03501, over 972905.38 frames.], batch size: 15, lr: 2.33e-04
2022-05-06 14:25:10,997 INFO [train.py:715] (4/8) Epoch 9, batch 24550, loss[loss=0.1372, simple_loss=0.2196, pruned_loss=0.02745, over 4887.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2147, pruned_loss=0.03432, over 972566.33 frames.], batch size: 22, lr: 2.33e-04
2022-05-06 14:25:50,742 INFO [train.py:715] (4/8) Epoch 9, batch 24600, loss[loss=0.1491, simple_loss=0.2235, pruned_loss=0.03736, over 4816.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2144, pruned_loss=0.0344, over 972566.90 frames.], batch size: 13, lr: 2.33e-04
2022-05-06 14:26:30,738 INFO [train.py:715] (4/8) Epoch 9, batch 24650, loss[loss=0.1423, simple_loss=0.2187, pruned_loss=0.03295, over 4803.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03391, over 973534.16 frames.], batch size: 24, lr: 2.33e-04
2022-05-06 14:27:09,791 INFO [train.py:715] (4/8) Epoch 9, batch 24700, loss[loss=0.1352, simple_loss=0.212, pruned_loss=0.0292, over 4938.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2142, pruned_loss=0.03373, over 973668.63 frames.], batch size: 29, lr: 2.33e-04
2022-05-06 14:27:48,504 INFO [train.py:715] (4/8) Epoch 9, batch 24750, loss[loss=0.1538, simple_loss=0.2307, pruned_loss=0.03841, over 4928.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2149, pruned_loss=0.03406, over 973945.90 frames.], batch size: 17, lr: 2.33e-04
2022-05-06 14:28:28,023 INFO [train.py:715] (4/8) Epoch 9, batch 24800, loss[loss=0.1534, simple_loss=0.2247, pruned_loss=0.04102, over 4755.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2153, pruned_loss=0.03444, over 972598.66 frames.], batch size: 16, lr: 2.32e-04
2022-05-06 14:29:07,591 INFO [train.py:715] (4/8) Epoch 9, batch 24850, loss[loss=0.1293, simple_loss=0.2064, pruned_loss=0.02611, over 4877.00 frames.], tot_loss[loss=0.142, simple_loss=0.2149, pruned_loss=0.03459, over 972927.24 frames.], batch size: 16, lr: 2.32e-04
2022-05-06 14:29:46,971 INFO [train.py:715] (4/8) Epoch 9, batch 24900, loss[loss=0.1265, simple_loss=0.1878, pruned_loss=0.0326, over 4823.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2153, pruned_loss=0.03507, over 972904.57 frames.], batch size: 12, lr: 2.32e-04
2022-05-06 14:30:26,386 INFO [train.py:715] (4/8) Epoch 9, batch 24950, loss[loss=0.122, simple_loss=0.1929, pruned_loss=0.02556, over 4976.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2156, pruned_loss=0.03492, over 972933.69 frames.], batch size: 28, lr: 2.32e-04
2022-05-06 14:31:06,084 INFO [train.py:715] (4/8) Epoch 9, batch 25000, loss[loss=0.1546, simple_loss=0.2291, pruned_loss=0.04006, over 4801.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2148, pruned_loss=0.0343, over 972753.77 frames.], batch size: 21, lr: 2.32e-04
2022-05-06 14:31:44,920 INFO [train.py:715] (4/8) Epoch 9, batch 25050, loss[loss=0.1397, simple_loss=0.2028, pruned_loss=0.03833, over 4809.00 frames.], tot_loss[loss=0.1419, simple_loss=0.215, pruned_loss=0.03442, over 973407.50 frames.], batch size: 25, lr: 2.32e-04
2022-05-06 14:32:24,415 INFO [train.py:715] (4/8) Epoch 9, batch 25100, loss[loss=0.1677, simple_loss=0.2303, pruned_loss=0.05251, over 4854.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2147, pruned_loss=0.03443, over 974185.23 frames.], batch size: 20, lr: 2.32e-04
2022-05-06 14:33:03,523 INFO [train.py:715] (4/8) Epoch 9, batch 25150, loss[loss=0.1416, simple_loss=0.2219, pruned_loss=0.03065, over 4913.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2146, pruned_loss=0.03454, over 972987.28 frames.], batch size: 23, lr: 2.32e-04
2022-05-06 14:33:42,581 INFO [train.py:715] (4/8) Epoch 9, batch 25200, loss[loss=0.1165, simple_loss=0.1884, pruned_loss=0.02231, over 4877.00 frames.], tot_loss[loss=0.142, simple_loss=0.2148, pruned_loss=0.03457, over 972522.66 frames.], batch size: 32, lr: 2.32e-04
2022-05-06 14:34:21,839 INFO [train.py:715] (4/8) Epoch 9, batch 25250, loss[loss=0.1316, simple_loss=0.1984, pruned_loss=0.03238, over 4831.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2156, pruned_loss=0.03468, over 971886.26 frames.], batch size: 12, lr: 2.32e-04
2022-05-06 14:35:00,582 INFO [train.py:715] (4/8) Epoch 9, batch 25300, loss[loss=0.1157, simple_loss=0.1999, pruned_loss=0.0157, over 4811.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2149, pruned_loss=0.03466, over 972237.86 frames.], batch size: 12, lr: 2.32e-04
2022-05-06 14:35:40,266 INFO [train.py:715] (4/8) Epoch 9, batch 25350, loss[loss=0.1483, simple_loss=0.2051, pruned_loss=0.04569, over 4760.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2154, pruned_loss=0.03493, over 972842.10 frames.], batch size: 16, lr: 2.32e-04
2022-05-06 14:36:20,107 INFO [train.py:715] (4/8) Epoch 9, batch 25400, loss[loss=0.1671, simple_loss=0.2258, pruned_loss=0.05417, over 4981.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2148, pruned_loss=0.03521, over 972410.06 frames.], batch size: 31, lr: 2.32e-04
2022-05-06 14:37:00,345 INFO [train.py:715] (4/8) Epoch 9, batch 25450, loss[loss=0.148, simple_loss=0.2034, pruned_loss=0.04635, over 4905.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2136, pruned_loss=0.03431, over 972210.88 frames.], batch size: 18, lr: 2.32e-04
2022-05-06 14:37:38,911 INFO [train.py:715] (4/8) Epoch 9, batch 25500, loss[loss=0.1474, simple_loss=0.2202, pruned_loss=0.03735, over 4946.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.03493, over 972563.55 frames.], batch size: 24, lr: 2.32e-04
2022-05-06 14:38:18,074 INFO [train.py:715] (4/8) Epoch 9, batch 25550, loss[loss=0.1386, simple_loss=0.2152, pruned_loss=0.03099, over 4807.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2144, pruned_loss=0.03515, over 972677.82 frames.], batch size: 15, lr: 2.32e-04
2022-05-06 14:38:57,225 INFO [train.py:715] (4/8) Epoch 9, batch 25600, loss[loss=0.1505, simple_loss=0.2218, pruned_loss=0.03963, over 4882.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2151, pruned_loss=0.03501, over 972207.75 frames.], batch size: 39, lr: 2.32e-04
2022-05-06 14:39:36,161 INFO [train.py:715] (4/8) Epoch 9, batch 25650, loss[loss=0.1336, simple_loss=0.2088, pruned_loss=0.02916, over 4772.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03432, over 972199.92 frames.], batch size: 18, lr: 2.32e-04
2022-05-06 14:40:15,296 INFO [train.py:715] (4/8) Epoch 9, batch 25700, loss[loss=0.1276, simple_loss=0.196, pruned_loss=0.02961, over 4802.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03433, over 972101.26 frames.], batch size: 14, lr: 2.32e-04
2022-05-06 14:40:54,416 INFO [train.py:715] (4/8) Epoch 9, batch 25750, loss[loss=0.1507, simple_loss=0.2071, pruned_loss=0.04718, over 4826.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2142, pruned_loss=0.03456, over 971906.42 frames.], batch size: 30, lr: 2.32e-04
2022-05-06 14:41:33,410 INFO [train.py:715] (4/8) Epoch 9, batch 25800, loss[loss=0.1222, simple_loss=0.2041, pruned_loss=0.02014, over 4809.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2148, pruned_loss=0.035, over 970785.80 frames.], batch size: 26, lr: 2.32e-04
2022-05-06 14:42:13,644 INFO [train.py:715] (4/8) Epoch 9, batch 25850, loss[loss=0.1521, simple_loss=0.2214, pruned_loss=0.0414, over 4835.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2148, pruned_loss=0.03497, over 970944.89 frames.], batch size: 32, lr: 2.32e-04
2022-05-06 14:42:53,087 INFO [train.py:715] (4/8) Epoch 9, batch 25900, loss[loss=0.1552, simple_loss=0.2157, pruned_loss=0.0473, over 4643.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03482, over 971693.57 frames.], batch size: 13, lr: 2.32e-04
2022-05-06 14:43:32,745 INFO [train.py:715] (4/8) Epoch 9, batch 25950, loss[loss=0.1586, simple_loss=0.2305, pruned_loss=0.04336, over 4823.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2147, pruned_loss=0.03486, over 973389.16 frames.], batch size: 27, lr: 2.32e-04
2022-05-06 14:44:11,976 INFO [train.py:715] (4/8) Epoch 9, batch 26000, loss[loss=0.151, simple_loss=0.2304, pruned_loss=0.03574, over 4751.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2151, pruned_loss=0.03496, over 972853.66 frames.], batch size: 19, lr: 2.32e-04
2022-05-06 14:44:51,307 INFO [train.py:715] (4/8) Epoch 9, batch 26050, loss[loss=0.1436, simple_loss=0.2207, pruned_loss=0.03331, over 4921.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2146, pruned_loss=0.03465, over 972442.64 frames.], batch size: 23, lr: 2.32e-04
2022-05-06 14:45:30,099 INFO [train.py:715] (4/8) Epoch 9, batch 26100, loss[loss=0.115, simple_loss=0.1851, pruned_loss=0.02245, over 4810.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03432, over 972456.25 frames.], batch size: 13, lr: 2.32e-04
2022-05-06 14:46:09,819 INFO [train.py:715] (4/8) Epoch 9, batch 26150, loss[loss=0.1423, simple_loss=0.2131, pruned_loss=0.03581, over 4971.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03474, over 973573.51 frames.], batch size: 35, lr: 2.32e-04
2022-05-06 14:46:50,068 INFO [train.py:715] (4/8) Epoch 9, batch 26200, loss[loss=0.1371, simple_loss=0.2069, pruned_loss=0.03364, over 4962.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2141, pruned_loss=0.03489, over 973464.68 frames.], batch size: 39, lr: 2.32e-04
2022-05-06 14:47:29,932 INFO [train.py:715] (4/8) Epoch 9, batch 26250, loss[loss=0.1527, simple_loss=0.2164, pruned_loss=0.04452, over 4801.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2138, pruned_loss=0.03496, over 973370.95 frames.], batch size: 12, lr: 2.32e-04
2022-05-06 14:48:09,856 INFO [train.py:715] (4/8) Epoch 9, batch 26300, loss[loss=0.1662, simple_loss=0.2279, pruned_loss=0.0522, over 4776.00 frames.], tot_loss[loss=0.1408, simple_loss=0.213, pruned_loss=0.03428, over 972944.61 frames.], batch size: 14, lr: 2.32e-04
2022-05-06 14:48:49,364 INFO [train.py:715] (4/8) Epoch 9, batch 26350, loss[loss=0.1428, simple_loss=0.22, pruned_loss=0.03283, over 4949.00 frames.], tot_loss[loss=0.1415, simple_loss=0.214, pruned_loss=0.03449, over 971772.06 frames.], batch size: 21, lr: 2.32e-04
2022-05-06 14:49:28,726 INFO [train.py:715] (4/8) Epoch 9, batch 26400, loss[loss=0.1157, simple_loss=0.192, pruned_loss=0.01977, over 4737.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2145, pruned_loss=0.03439, over 972007.13 frames.], batch size: 16, lr: 2.32e-04
2022-05-06 14:50:07,637 INFO [train.py:715] (4/8) Epoch 9, batch 26450, loss[loss=0.1265, simple_loss=0.1955, pruned_loss=0.02875, over 4881.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2146, pruned_loss=0.03452, over 972252.02 frames.], batch size: 22, lr: 2.32e-04
2022-05-06 14:50:46,955 INFO [train.py:715] (4/8) Epoch 9, batch 26500, loss[loss=0.1595, simple_loss=0.2367, pruned_loss=0.0412, over 4829.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2145, pruned_loss=0.03461, over 971757.73 frames.], batch size: 26, lr: 2.32e-04
2022-05-06 14:51:26,813 INFO [train.py:715] (4/8) Epoch 9, batch 26550, loss[loss=0.1917, simple_loss=0.2619, pruned_loss=0.06078, over 4748.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2147, pruned_loss=0.03439, over 972115.54 frames.], batch size: 16, lr: 2.32e-04
2022-05-06 14:52:06,149 INFO [train.py:715] (4/8) Epoch 9, batch 26600, loss[loss=0.1567, simple_loss=0.2278, pruned_loss=0.04279, over 4739.00 frames.], tot_loss[loss=0.141, simple_loss=0.2142, pruned_loss=0.03388, over 972346.47 frames.], batch size: 16, lr: 2.32e-04
2022-05-06 14:52:46,086 INFO [train.py:715] (4/8) Epoch 9, batch 26650, loss[loss=0.1423, simple_loss=0.2168, pruned_loss=0.03391, over 4740.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.03438, over 971943.69 frames.], batch size: 16, lr: 2.32e-04
2022-05-06 14:53:25,378 INFO [train.py:715] (4/8) Epoch 9, batch 26700, loss[loss=0.1464, simple_loss=0.2119, pruned_loss=0.04049, over 4908.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03435, over 971618.81 frames.], batch size: 17, lr: 2.32e-04
2022-05-06 14:54:04,745 INFO [train.py:715] (4/8) Epoch 9, batch 26750, loss[loss=0.1466, simple_loss=0.2201, pruned_loss=0.03649, over 4862.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2148, pruned_loss=0.03486, over 971548.22 frames.], batch size: 20, lr: 2.32e-04
2022-05-06 14:54:43,923 INFO [train.py:715] (4/8) Epoch 9, batch 26800, loss[loss=0.1196, simple_loss=0.1938, pruned_loss=0.02265, over 4892.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03441, over 971861.01 frames.], batch size: 17, lr: 2.32e-04
2022-05-06 14:55:22,920 INFO [train.py:715] (4/8) Epoch 9, batch 26850, loss[loss=0.1234, simple_loss=0.2049, pruned_loss=0.0209, over 4978.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.03384, over 971187.23 frames.], batch size: 14, lr: 2.32e-04
2022-05-06 14:56:02,399 INFO [train.py:715] (4/8) Epoch 9, batch 26900, loss[loss=0.1445, simple_loss=0.2195, pruned_loss=0.03482, over 4855.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2135, pruned_loss=0.03353, over 972141.91 frames.], batch size: 20, lr: 2.32e-04
2022-05-06 14:56:42,229 INFO [train.py:715] (4/8) Epoch 9, batch 26950, loss[loss=0.1477, simple_loss=0.2236, pruned_loss=0.03592, over 4779.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2145, pruned_loss=0.03396, over 971850.49 frames.], batch size: 14, lr: 2.32e-04
2022-05-06 14:57:21,398 INFO [train.py:715] (4/8) Epoch 9, batch 27000, loss[loss=0.1201, simple_loss=0.1985, pruned_loss=0.02086, over 4814.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2149, pruned_loss=0.03406, over 971927.13 frames.], batch size: 21, lr: 2.32e-04
2022-05-06 14:57:21,399 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 14:57:30,963 INFO [train.py:742] (4/8) Epoch 9, validation: loss=0.1068, simple_loss=0.1912, pruned_loss=0.01121, over 914524.00 frames.
2022-05-06 14:58:10,507 INFO [train.py:715] (4/8) Epoch 9, batch 27050, loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03091, over 4815.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2154, pruned_loss=0.03463, over 972066.34 frames.], batch size: 21, lr: 2.32e-04
2022-05-06 14:58:50,072 INFO [train.py:715] (4/8) Epoch 9, batch 27100, loss[loss=0.1427, simple_loss=0.2053, pruned_loss=0.04001, over 4775.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2161, pruned_loss=0.03505, over 972623.69 frames.], batch size: 14, lr: 2.32e-04
2022-05-06 14:59:30,123 INFO [train.py:715] (4/8) Epoch 9, batch 27150, loss[loss=0.1435, simple_loss=0.211, pruned_loss=0.03806, over 4815.00 frames.], tot_loss[loss=0.1436, simple_loss=0.2161, pruned_loss=0.03551, over 972407.66 frames.], batch size: 26, lr: 2.32e-04
2022-05-06 15:00:09,246 INFO [train.py:715] (4/8) Epoch 9, batch 27200, loss[loss=0.1551, simple_loss=0.2318, pruned_loss=0.03915, over 4764.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2158, pruned_loss=0.03528, over 972542.73 frames.], batch size: 19, lr: 2.32e-04
2022-05-06 15:00:48,162 INFO [train.py:715] (4/8) Epoch 9, batch 27250, loss[loss=0.157, simple_loss=0.2254, pruned_loss=0.04428, over 4936.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2161, pruned_loss=0.0351, over 973182.57 frames.], batch size: 21, lr: 2.32e-04
2022-05-06 15:01:27,381 INFO [train.py:715] (4/8) Epoch 9, batch 27300, loss[loss=0.1228, simple_loss=0.2018, pruned_loss=0.02191, over 4904.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2162, pruned_loss=0.0353, over 972418.08 frames.], batch size: 23, lr: 2.32e-04
2022-05-06 15:02:06,269 INFO [train.py:715] (4/8) Epoch 9, batch 27350, loss[loss=0.1293, simple_loss=0.2122, pruned_loss=0.02324, over 4913.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2162, pruned_loss=0.03521, over 972572.17 frames.], batch size: 19, lr: 2.32e-04
2022-05-06 15:02:45,300 INFO [train.py:715] (4/8) Epoch 9, batch 27400, loss[loss=0.1274, simple_loss=0.1962, pruned_loss=0.02928, over 4958.00 frames.], tot_loss[loss=0.1434, simple_loss=0.2165, pruned_loss=0.03515, over 972947.49 frames.], batch size: 15, lr: 2.32e-04
2022-05-06 15:03:24,467 INFO [train.py:715] (4/8) Epoch 9, batch 27450, loss[loss=0.1377, simple_loss=0.2021, pruned_loss=0.03663, over 4778.00 frames.], tot_loss[loss=0.143, simple_loss=0.2159, pruned_loss=0.03507, over 973208.88 frames.], batch size: 14, lr: 2.32e-04
2022-05-06 15:04:03,432 INFO [train.py:715] (4/8) Epoch 9, batch 27500, loss[loss=0.1474, simple_loss=0.2125, pruned_loss=0.04116, over 4822.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2159, pruned_loss=0.03493, over 973680.41 frames.], batch size: 15, lr: 2.32e-04
2022-05-06 15:04:42,461 INFO [train.py:715] (4/8) Epoch 9, batch 27550, loss[loss=0.1572, simple_loss=0.2326, pruned_loss=0.0409, over 4903.00 frames.], tot_loss[loss=0.143, simple_loss=0.2159, pruned_loss=0.03502, over 974288.66 frames.], batch size: 18, lr: 2.32e-04
2022-05-06 15:05:21,386 INFO [train.py:715] (4/8) Epoch 9, batch 27600, loss[loss=0.1303, simple_loss=0.2157, pruned_loss=0.02246, over 4810.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2153, pruned_loss=0.03455, over 973514.26 frames.], batch size: 25, lr: 2.32e-04
2022-05-06 15:06:00,165 INFO [train.py:715] (4/8) Epoch 9, batch 27650, loss[loss=0.1379, simple_loss=0.2149, pruned_loss=0.03043, over 4821.00 frames.], tot_loss[loss=0.142, simple_loss=0.215, pruned_loss=0.03451, over 973533.20 frames.], batch size: 15, lr: 2.32e-04
2022-05-06 15:06:39,016 INFO [train.py:715] (4/8) Epoch 9, batch 27700, loss[loss=0.1777, simple_loss=0.2573, pruned_loss=0.04906, over 4897.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2145, pruned_loss=0.03461, over 972615.38 frames.], batch size: 16, lr: 2.32e-04
2022-05-06 15:07:18,263 INFO [train.py:715] (4/8) Epoch 9, batch 27750, loss[loss=0.1311, simple_loss=0.2113, pruned_loss=0.02548, over 4746.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2134, pruned_loss=0.03413, over 973153.17 frames.], batch size: 16, lr: 2.31e-04
2022-05-06 15:07:57,614 INFO [train.py:715] (4/8) Epoch 9, batch 27800, loss[loss=0.1245, simple_loss=0.2048, pruned_loss=0.02216, over 4947.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2141, pruned_loss=0.03413, over 973696.74 frames.], batch size: 21, lr: 2.31e-04
2022-05-06 15:08:36,546 INFO [train.py:715] (4/8) Epoch 9, batch 27850, loss[loss=0.145, simple_loss=0.2165, pruned_loss=0.03676, over 4972.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2145, pruned_loss=0.03435, over 973940.37 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:09:16,415 INFO [train.py:715] (4/8) Epoch 9, batch 27900, loss[loss=0.1348, simple_loss=0.2055, pruned_loss=0.03204, over 4838.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03364, over 973953.36 frames.], batch size: 30, lr: 2.31e-04
2022-05-06 15:09:54,911 INFO [train.py:715] (4/8) Epoch 9, batch 27950, loss[loss=0.127, simple_loss=0.2069, pruned_loss=0.02359, over 4828.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2137, pruned_loss=0.03386, over 973498.18 frames.], batch size: 26, lr: 2.31e-04
2022-05-06 15:10:34,267 INFO [train.py:715] (4/8) Epoch 9, batch 28000, loss[loss=0.1383, simple_loss=0.2127, pruned_loss=0.0319, over 4772.00 frames.], tot_loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03412, over 973520.18 frames.], batch size: 14, lr: 2.31e-04
2022-05-06 15:11:13,572 INFO [train.py:715] (4/8) Epoch 9, batch 28050, loss[loss=0.1505, simple_loss=0.2236, pruned_loss=0.03875, over 4804.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2142, pruned_loss=0.03452, over 972678.18 frames.], batch size: 21, lr: 2.31e-04
2022-05-06 15:11:52,642 INFO [train.py:715] (4/8) Epoch 9, batch 28100, loss[loss=0.1635, simple_loss=0.2328, pruned_loss=0.04706, over 4960.00 frames.], tot_loss[loss=0.142, simple_loss=0.2143, pruned_loss=0.03484, over 971880.31 frames.], batch size: 21, lr: 2.31e-04
2022-05-06 15:12:31,906 INFO [train.py:715] (4/8) Epoch 9, batch 28150, loss[loss=0.1188, simple_loss=0.1997, pruned_loss=0.01902, over 4823.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.0344, over 972010.23 frames.], batch size: 25, lr: 2.31e-04
2022-05-06 15:13:10,821 INFO [train.py:715] (4/8) Epoch 9, batch 28200, loss[loss=0.1247, simple_loss=0.2018, pruned_loss=0.02381, over 4922.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03425, over 972327.00 frames.], batch size: 18, lr: 2.31e-04
2022-05-06 15:13:50,249 INFO [train.py:715] (4/8) Epoch 9, batch 28250, loss[loss=0.1273, simple_loss=0.2061, pruned_loss=0.02428, over 4832.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03404, over 972287.36 frames.], batch size: 27, lr: 2.31e-04
2022-05-06 15:14:28,526 INFO [train.py:715] (4/8) Epoch 9, batch 28300, loss[loss=0.1376, simple_loss=0.2131, pruned_loss=0.03099, over 4798.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03361, over 972882.55 frames.], batch size: 14, lr: 2.31e-04
2022-05-06 15:15:07,476 INFO [train.py:715] (4/8) Epoch 9, batch 28350, loss[loss=0.1541, simple_loss=0.2284, pruned_loss=0.0399, over 4909.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2137, pruned_loss=0.03396, over 974082.55 frames.], batch size: 17, lr: 2.31e-04
2022-05-06 15:15:46,871 INFO [train.py:715] (4/8) Epoch 9, batch 28400, loss[loss=0.1459, simple_loss=0.21, pruned_loss=0.04095, over 4838.00 frames.], tot_loss[loss=0.141, simple_loss=0.2137, pruned_loss=0.03415, over 973295.24 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:16:25,966 INFO [train.py:715] (4/8) Epoch 9, batch 28450, loss[loss=0.1471, simple_loss=0.2143, pruned_loss=0.03995, over 4781.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03437, over 973295.40 frames.], batch size: 17, lr: 2.31e-04
2022-05-06 15:17:04,385 INFO [train.py:715] (4/8) Epoch 9, batch 28500, loss[loss=0.1383, simple_loss=0.2062, pruned_loss=0.03514, over 4840.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03444, over 972960.91 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:17:43,521 INFO [train.py:715] (4/8) Epoch 9, batch 28550, loss[loss=0.1497, simple_loss=0.2211, pruned_loss=0.03917, over 4927.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2147, pruned_loss=0.03455, over 973611.27 frames.], batch size: 23, lr: 2.31e-04
2022-05-06 15:18:22,911 INFO [train.py:715] (4/8) Epoch 9, batch 28600, loss[loss=0.1196, simple_loss=0.1884, pruned_loss=0.0254, over 4779.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2141, pruned_loss=0.03447, over 973907.09 frames.], batch size: 12, lr: 2.31e-04
2022-05-06 15:19:01,329 INFO [train.py:715] (4/8) Epoch 9, batch 28650, loss[loss=0.1152, simple_loss=0.1881, pruned_loss=0.02112, over 4828.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03429, over 973717.15 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:19:40,172 INFO [train.py:715] (4/8) Epoch 9, batch 28700, loss[loss=0.1401, simple_loss=0.2162, pruned_loss=0.03199, over 4862.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.034, over 974028.96 frames.], batch size: 20, lr: 2.31e-04
2022-05-06 15:20:19,621 INFO [train.py:715] (4/8) Epoch 9, batch 28750, loss[loss=0.1557, simple_loss=0.2355, pruned_loss=0.03791, over 4905.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03364, over 973716.13 frames.], batch size: 17, lr: 2.31e-04
2022-05-06 15:20:58,322 INFO [train.py:715] (4/8) Epoch 9, batch 28800, loss[loss=0.1491, simple_loss=0.2211, pruned_loss=0.03859, over 4949.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03347, over 972809.98 frames.], batch size: 21, lr: 2.31e-04
2022-05-06 15:21:36,720 INFO [train.py:715] (4/8) Epoch 9, batch 28850, loss[loss=0.1736, simple_loss=0.2461, pruned_loss=0.05058, over 4768.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03426, over 972585.81 frames.], batch size: 18, lr: 2.31e-04
2022-05-06 15:22:16,101 INFO [train.py:715] (4/8) Epoch 9, batch 28900, loss[loss=0.1409, simple_loss=0.2158, pruned_loss=0.03303, over 4701.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03398, over 972433.09 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:22:55,366 INFO [train.py:715] (4/8) Epoch 9, batch 28950, loss[loss=0.1221, simple_loss=0.2029, pruned_loss=0.02065, over 4769.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2142, pruned_loss=0.03447, over 971958.72 frames.], batch size: 19, lr: 2.31e-04
2022-05-06 15:23:33,685 INFO [train.py:715] (4/8) Epoch 9, batch 29000, loss[loss=0.1277, simple_loss=0.2027, pruned_loss=0.02639, over 4783.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2145, pruned_loss=0.03478, over 971393.81 frames.], batch size: 14, lr: 2.31e-04
2022-05-06 15:24:12,156 INFO [train.py:715] (4/8) Epoch 9, batch 29050, loss[loss=0.1489, simple_loss=0.222, pruned_loss=0.03794, over 4855.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2146, pruned_loss=0.03475, over 971118.10 frames.], batch size: 13, lr: 2.31e-04
2022-05-06 15:24:51,098 INFO [train.py:715] (4/8) Epoch 9, batch 29100, loss[loss=0.1392, simple_loss=0.2068, pruned_loss=0.03578, over 4781.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.03438, over 971727.16 frames.], batch size: 14, lr: 2.31e-04
2022-05-06 15:25:30,247 INFO [train.py:715] (4/8) Epoch 9, batch 29150, loss[loss=0.1444, simple_loss=0.2189, pruned_loss=0.03499, over 4989.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2142, pruned_loss=0.03441, over 971718.06 frames.], batch size: 31, lr: 2.31e-04
2022-05-06 15:26:09,095 INFO [train.py:715] (4/8) Epoch 9, batch 29200, loss[loss=0.1545, simple_loss=0.2284, pruned_loss=0.04024, over 4718.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2154, pruned_loss=0.03486, over 971849.19 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:26:48,459 INFO [train.py:715] (4/8) Epoch 9, batch 29250, loss[loss=0.1594, simple_loss=0.2286, pruned_loss=0.04509, over 4747.00 frames.], tot_loss[loss=0.1425, simple_loss=0.215, pruned_loss=0.03499, over 971151.52 frames.], batch size: 16, lr: 2.31e-04
2022-05-06 15:27:27,197 INFO [train.py:715] (4/8) Epoch 9, batch 29300, loss[loss=0.1428, simple_loss=0.2165, pruned_loss=0.0345, over 4986.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2151, pruned_loss=0.03481, over 972303.11 frames.], batch size: 27, lr: 2.31e-04
2022-05-06 15:28:06,267 INFO [train.py:715] (4/8) Epoch 9, batch 29350, loss[loss=0.1423, simple_loss=0.2128, pruned_loss=0.03596, over 4940.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2142, pruned_loss=0.03453, over 972603.12 frames.], batch size: 40, lr: 2.31e-04
2022-05-06 15:28:45,210 INFO [train.py:715] (4/8) Epoch 9, batch 29400, loss[loss=0.1464, simple_loss=0.2265, pruned_loss=0.03315, over 4923.00 frames.], tot_loss[loss=0.142, simple_loss=0.2144, pruned_loss=0.03474, over 972452.57 frames.], batch size: 23, lr: 2.31e-04
2022-05-06 15:29:23,946 INFO [train.py:715] (4/8) Epoch 9, batch 29450, loss[loss=0.1281, simple_loss=0.2017, pruned_loss=0.02728, over 4725.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2153, pruned_loss=0.03508, over 971479.52 frames.], batch size: 12, lr: 2.31e-04
2022-05-06 15:30:02,404 INFO [train.py:715] (4/8) Epoch 9, batch 29500, loss[loss=0.1173, simple_loss=0.1917, pruned_loss=0.02141, over 4839.00 frames.], tot_loss[loss=0.143, simple_loss=0.2155, pruned_loss=0.03525, over 970661.79 frames.], batch size: 13, lr: 2.31e-04
2022-05-06 15:30:41,337 INFO [train.py:715] (4/8) Epoch 9, batch 29550, loss[loss=0.1816, simple_loss=0.2562, pruned_loss=0.05354, over 4769.00 frames.], tot_loss[loss=0.1437, simple_loss=0.2162, pruned_loss=0.03566, over 971105.74 frames.], batch size: 18, lr: 2.31e-04
2022-05-06 15:31:20,278 INFO [train.py:715] (4/8) Epoch 9, batch 29600, loss[loss=0.1456, simple_loss=0.2319, pruned_loss=0.02968, over 4882.00 frames.], tot_loss[loss=0.1438, simple_loss=0.2161, pruned_loss=0.03581, over 970856.20 frames.], batch size: 16, lr: 2.31e-04
2022-05-06 15:31:59,539 INFO [train.py:715] (4/8) Epoch 9, batch 29650, loss[loss=0.1533, simple_loss=0.2249, pruned_loss=0.04084, over 4876.00 frames.], tot_loss[loss=0.143, simple_loss=0.2154, pruned_loss=0.03525, over 970607.12 frames.], batch size: 32, lr: 2.31e-04
2022-05-06 15:32:39,147 INFO [train.py:715] (4/8) Epoch 9, batch 29700, loss[loss=0.1508, simple_loss=0.2225, pruned_loss=0.03959, over 4825.00 frames.], tot_loss[loss=0.1426, simple_loss=0.2153, pruned_loss=0.0349, over 970484.16 frames.], batch size: 30, lr: 2.31e-04
2022-05-06 15:33:17,089 INFO [train.py:715] (4/8) Epoch 9, batch 29750, loss[loss=0.137, simple_loss=0.2219, pruned_loss=0.02598, over 4857.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2161, pruned_loss=0.03517, over 970700.37 frames.], batch size: 20, lr: 2.31e-04
2022-05-06 15:33:55,772 INFO [train.py:715] (4/8) Epoch 9, batch 29800, loss[loss=0.1654, simple_loss=0.2583, pruned_loss=0.03621, over 4782.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2161, pruned_loss=0.0348, over 970049.84 frames.], batch size: 17, lr: 2.31e-04
2022-05-06 15:34:34,891 INFO [train.py:715] (4/8) Epoch 9, batch 29850, loss[loss=0.125, simple_loss=0.209, pruned_loss=0.02049, over 4862.00 frames.], tot_loss[loss=0.142, simple_loss=0.2152, pruned_loss=0.03435, over 970522.51 frames.], batch size: 30, lr: 2.31e-04
2022-05-06 15:35:13,058 INFO [train.py:715] (4/8) Epoch 9, batch 29900, loss[loss=0.1388, simple_loss=0.219, pruned_loss=0.0293, over 4969.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2157, pruned_loss=0.03485, over 969805.26 frames.], batch size: 21, lr: 2.31e-04
2022-05-06 15:35:52,534 INFO [train.py:715] (4/8) Epoch 9, batch 29950, loss[loss=0.1414, simple_loss=0.2156, pruned_loss=0.03357, over 4648.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2158, pruned_loss=0.03516, over 969880.39 frames.], batch size: 13, lr: 2.31e-04
2022-05-06 15:36:31,404 INFO [train.py:715] (4/8) Epoch 9, batch 30000, loss[loss=0.1614, simple_loss=0.24, pruned_loss=0.0414, over 4883.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2148, pruned_loss=0.03446, over 970273.68 frames.], batch size: 22, lr: 2.31e-04
2022-05-06 15:36:31,405 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 15:36:40,918 INFO [train.py:742] (4/8) Epoch 9, validation: loss=0.1068, simple_loss=0.1911, pruned_loss=0.01124, over 914524.00 frames.
2022-05-06 15:37:20,160 INFO [train.py:715] (4/8) Epoch 9, batch 30050, loss[loss=0.1266, simple_loss=0.1994, pruned_loss=0.02695, over 4802.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2153, pruned_loss=0.03466, over 970981.52 frames.], batch size: 25, lr: 2.31e-04
2022-05-06 15:37:58,804 INFO [train.py:715] (4/8) Epoch 9, batch 30100, loss[loss=0.1629, simple_loss=0.2318, pruned_loss=0.04702, over 4791.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2153, pruned_loss=0.03492, over 970683.64 frames.], batch size: 21, lr: 2.31e-04
2022-05-06 15:38:38,126 INFO [train.py:715] (4/8) Epoch 9, batch 30150, loss[loss=0.1286, simple_loss=0.2038, pruned_loss=0.02676, over 4870.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2145, pruned_loss=0.03464, over 969911.44 frames.], batch size: 38, lr: 2.31e-04
2022-05-06 15:39:17,503 INFO [train.py:715] (4/8) Epoch 9, batch 30200, loss[loss=0.1279, simple_loss=0.1984, pruned_loss=0.02868, over 4921.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2141, pruned_loss=0.03451, over 971336.12 frames.], batch size: 18, lr: 2.31e-04
2022-05-06 15:39:56,688 INFO [train.py:715] (4/8) Epoch 9, batch 30250, loss[loss=0.1385, simple_loss=0.2143, pruned_loss=0.03135, over 4797.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2149, pruned_loss=0.03486, over 971394.96 frames.], batch size: 17, lr: 2.31e-04
2022-05-06 15:40:35,247 INFO [train.py:715] (4/8) Epoch 9, batch 30300, loss[loss=0.1428, simple_loss=0.228, pruned_loss=0.0288, over 4981.00 frames.], tot_loss[loss=0.1424, simple_loss=0.215, pruned_loss=0.03491, over 971456.34 frames.], batch size: 24, lr: 2.31e-04
2022-05-06 15:41:14,056 INFO [train.py:715] (4/8) Epoch 9, batch 30350, loss[loss=0.1273, simple_loss=0.2022, pruned_loss=0.02623, over 4826.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.0351, over 971452.40 frames.], batch size: 15, lr: 2.31e-04
2022-05-06 15:41:53,484 INFO [train.py:715] (4/8) Epoch 9, batch 30400, loss[loss=0.1262, simple_loss=0.2022, pruned_loss=0.02512, over 4774.00 frames.], tot_loss[loss=0.142, simple_loss=0.2143, pruned_loss=0.03481, over 972198.43 frames.], batch size: 17, lr: 2.31e-04
2022-05-06 15:42:32,292 INFO [train.py:715] (4/8) Epoch 9, batch 30450, loss[loss=0.1259, simple_loss=0.1982, pruned_loss=0.02682, over 4952.00 frames.], tot_loss[loss=0.1422, simple_loss=0.215, pruned_loss=0.03473, over 972437.78 frames.], batch size: 23, lr: 2.31e-04
2022-05-06 15:43:10,916 INFO [train.py:715] (4/8) Epoch 9, batch 30500, loss[loss=0.1482, simple_loss=0.227, pruned_loss=0.03466, over 4925.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2151, pruned_loss=0.0346, over 972904.28 frames.], batch size: 18, lr: 2.31e-04
2022-05-06 15:43:49,986 INFO [train.py:715] (4/8) Epoch 9, batch 30550, loss[loss=0.152, simple_loss=0.2272, pruned_loss=0.03844, over 4914.00 frames.], tot_loss[loss=0.142, simple_loss=0.2148, pruned_loss=0.03463, over 972861.34 frames.], batch size: 39, lr: 2.31e-04
2022-05-06 15:44:28,846 INFO [train.py:715] (4/8) Epoch 9, batch 30600, loss[loss=0.1399, simple_loss=0.2092, pruned_loss=0.03533, over 4977.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03432, over 972539.29 frames.], batch size: 33, lr: 2.31e-04
2022-05-06 15:45:06,879 INFO [train.py:715] (4/8) Epoch 9, batch 30650, loss[loss=0.1512, simple_loss=0.2143, pruned_loss=0.04402, over 4851.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03415, over 972522.75 frames.], batch size: 13, lr: 2.31e-04
2022-05-06 15:45:45,880 INFO [train.py:715] (4/8) Epoch 9, batch 30700, loss[loss=0.1253, simple_loss=0.1934, pruned_loss=0.02859, over 4970.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2129, pruned_loss=0.03372, over 972852.43 frames.], batch size: 35, lr: 2.30e-04
2022-05-06 15:46:27,571 INFO [train.py:715] (4/8) Epoch 9, batch 30750, loss[loss=0.1379, simple_loss=0.2255, pruned_loss=0.02513, over 4925.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2123, pruned_loss=0.03337, over 972652.83 frames.], batch size: 29, lr: 2.30e-04
2022-05-06 15:47:06,256 INFO [train.py:715] (4/8) Epoch 9, batch 30800, loss[loss=0.1497, simple_loss=0.2237, pruned_loss=0.03782, over 4794.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2128, pruned_loss=0.03322, over 973022.55 frames.], batch size: 21, lr: 2.30e-04
2022-05-06 15:47:44,603 INFO [train.py:715] (4/8) Epoch 9, batch 30850, loss[loss=0.1409, simple_loss=0.211, pruned_loss=0.0354, over 4962.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2132, pruned_loss=0.03372, over 974019.22 frames.], batch size: 21, lr: 2.30e-04
2022-05-06 15:48:23,856 INFO [train.py:715] (4/8) Epoch 9, batch 30900, loss[loss=0.1374, simple_loss=0.2059, pruned_loss=0.03446, over 4867.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.03351, over 973356.62 frames.], batch size: 32, lr: 2.30e-04
2022-05-06 15:49:03,046 INFO [train.py:715] (4/8) Epoch 9, batch 30950, loss[loss=0.144, simple_loss=0.2042, pruned_loss=0.0419, over 4766.00 frames.], tot_loss[loss=0.1403, simple_loss=0.213, pruned_loss=0.03381, over 972743.40 frames.], batch size: 19, lr: 2.30e-04
2022-05-06 15:49:41,533 INFO [train.py:715] (4/8) Epoch 9, batch 31000, loss[loss=0.1532, simple_loss=0.2165, pruned_loss=0.04491, over 4975.00 frames.], tot_loss[loss=0.141, simple_loss=0.2134, pruned_loss=0.03427, over 972276.83 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 15:50:20,507 INFO [train.py:715] (4/8) Epoch 9, batch 31050, loss[loss=0.1775, simple_loss=0.2458, pruned_loss=0.05464, over 4786.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.03469, over 972314.37 frames.], batch size: 18, lr: 2.30e-04
2022-05-06 15:50:59,766 INFO [train.py:715] (4/8) Epoch 9, batch 31100, loss[loss=0.1457, simple_loss=0.2106, pruned_loss=0.04041, over 4901.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2128, pruned_loss=0.03375, over 972388.91 frames.], batch size: 17, lr: 2.30e-04
2022-05-06 15:51:38,435 INFO [train.py:715] (4/8) Epoch 9, batch 31150, loss[loss=0.1275, simple_loss=0.196, pruned_loss=0.02945, over 4841.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03353, over 971811.68 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 15:52:17,018 INFO [train.py:715] (4/8) Epoch 9, batch 31200, loss[loss=0.1171, simple_loss=0.1883, pruned_loss=0.02291, over 4816.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2143, pruned_loss=0.03395, over 972480.73 frames.], batch size: 27, lr: 2.30e-04
2022-05-06 15:52:56,546 INFO [train.py:715] (4/8) Epoch 9, batch 31250, loss[loss=0.1838, simple_loss=0.2401, pruned_loss=0.0637, over 4839.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2142, pruned_loss=0.03409, over 972601.69 frames.], batch size: 30, lr: 2.30e-04
2022-05-06 15:53:35,998 INFO [train.py:715] (4/8) Epoch 9, batch 31300, loss[loss=0.1677, simple_loss=0.251, pruned_loss=0.04222, over 4992.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2142, pruned_loss=0.03416, over 973751.55 frames.], batch size: 16, lr: 2.30e-04
2022-05-06 15:54:14,967 INFO [train.py:715] (4/8) Epoch 9, batch 31350, loss[loss=0.1278, simple_loss=0.2048, pruned_loss=0.02536, over 4791.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2137, pruned_loss=0.03395, over 973131.09 frames.], batch size: 18, lr: 2.30e-04
2022-05-06 15:54:53,758 INFO [train.py:715] (4/8) Epoch 9, batch 31400, loss[loss=0.1632, simple_loss=0.2441, pruned_loss=0.04112, over 4965.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.03425, over 972886.79 frames.], batch size: 24, lr: 2.30e-04
2022-05-06 15:55:32,698 INFO [train.py:715] (4/8) Epoch 9, batch 31450, loss[loss=0.141, simple_loss=0.2074, pruned_loss=0.03725, over 4836.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03362, over 972658.01 frames.], batch size: 13, lr: 2.30e-04
2022-05-06 15:56:11,771 INFO [train.py:715] (4/8) Epoch 9, batch 31500, loss[loss=0.1482, simple_loss=0.2161, pruned_loss=0.0401, over 4834.00 frames.], tot_loss[loss=0.1416, simple_loss=0.214, pruned_loss=0.03464, over 972647.63 frames.], batch size: 26, lr: 2.30e-04
2022-05-06 15:56:50,182 INFO [train.py:715] (4/8) Epoch 9, batch 31550, loss[loss=0.1537, simple_loss=0.2144, pruned_loss=0.04653, over 4803.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2139, pruned_loss=0.03452, over 972375.49 frames.], batch size: 21, lr: 2.30e-04
2022-05-06 15:57:29,718 INFO [train.py:715] (4/8) Epoch 9, batch 31600, loss[loss=0.1545, simple_loss=0.2333, pruned_loss=0.03782, over 4983.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2155, pruned_loss=0.03513, over 971991.07 frames.], batch size: 35, lr: 2.30e-04
2022-05-06 15:58:09,720 INFO [train.py:715] (4/8) Epoch 9, batch 31650, loss[loss=0.1262, simple_loss=0.207, pruned_loss=0.02273, over 4754.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2155, pruned_loss=0.03541, over 971557.20 frames.], batch size: 16, lr: 2.30e-04
2022-05-06 15:58:48,438 INFO [train.py:715] (4/8) Epoch 9, batch 31700, loss[loss=0.1554, simple_loss=0.2292, pruned_loss=0.04079, over 4917.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2158, pruned_loss=0.03497, over 971626.32 frames.], batch size: 23, lr: 2.30e-04
2022-05-06 15:59:27,452 INFO [train.py:715] (4/8) Epoch 9, batch 31750, loss[loss=0.1477, simple_loss=0.2201, pruned_loss=0.03762, over 4926.00 frames.], tot_loss[loss=0.1432, simple_loss=0.2162, pruned_loss=0.03506, over 971483.00 frames.], batch size: 29, lr: 2.30e-04
2022-05-06 16:00:06,076 INFO [train.py:715] (4/8) Epoch 9, batch 31800, loss[loss=0.129, simple_loss=0.2048, pruned_loss=0.02658, over 4843.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2156, pruned_loss=0.03445, over 972410.95 frames.], batch size: 30, lr: 2.30e-04
2022-05-06 16:00:45,144 INFO [train.py:715] (4/8) Epoch 9, batch 31850, loss[loss=0.1367, simple_loss=0.2166, pruned_loss=0.02839, over 4930.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2164, pruned_loss=0.03455, over 971924.90 frames.], batch size: 21, lr: 2.30e-04
2022-05-06 16:01:23,638 INFO [train.py:715] (4/8) Epoch 9, batch 31900, loss[loss=0.1543, simple_loss=0.2201, pruned_loss=0.04425, over 4748.00 frames.], tot_loss[loss=0.143, simple_loss=0.2164, pruned_loss=0.03485, over 971369.71 frames.], batch size: 19, lr: 2.30e-04
2022-05-06 16:02:02,944 INFO [train.py:715] (4/8) Epoch 9, batch 31950, loss[loss=0.153, simple_loss=0.2245, pruned_loss=0.04078, over 4849.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2164, pruned_loss=0.03512, over 971841.40 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 16:02:42,213 INFO [train.py:715] (4/8) Epoch 9, batch 32000, loss[loss=0.1389, simple_loss=0.2086, pruned_loss=0.03458, over 4793.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2151, pruned_loss=0.03471, over 972502.51 frames.], batch size: 14, lr: 2.30e-04
2022-05-06 16:03:20,780 INFO [train.py:715] (4/8) Epoch 9, batch 32050, loss[loss=0.1215, simple_loss=0.1889, pruned_loss=0.02705, over 4685.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2146, pruned_loss=0.03488, over 972987.22 frames.], batch size: 13, lr: 2.30e-04
2022-05-06 16:03:59,265 INFO [train.py:715] (4/8) Epoch 9, batch 32100, loss[loss=0.1302, simple_loss=0.2007, pruned_loss=0.02986, over 4798.00 frames.], tot_loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.03478, over 971689.48 frames.], batch size: 12, lr: 2.30e-04
2022-05-06 16:04:38,260 INFO [train.py:715] (4/8) Epoch 9, batch 32150, loss[loss=0.1402, simple_loss=0.2059, pruned_loss=0.03727, over 4735.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2151, pruned_loss=0.03523, over 971279.56 frames.], batch size: 12, lr: 2.30e-04
2022-05-06 16:05:17,702 INFO [train.py:715] (4/8) Epoch 9, batch 32200, loss[loss=0.1237, simple_loss=0.2025, pruned_loss=0.02246, over 4829.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2142, pruned_loss=0.03473, over 970524.04 frames.], batch size: 25, lr: 2.30e-04
2022-05-06 16:05:55,461 INFO [train.py:715] (4/8) Epoch 9, batch 32250, loss[loss=0.1183, simple_loss=0.1877, pruned_loss=0.02449, over 4761.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2148, pruned_loss=0.03543, over 970995.56 frames.], batch size: 12, lr: 2.30e-04
2022-05-06 16:06:34,664 INFO [train.py:715] (4/8) Epoch 9, batch 32300, loss[loss=0.1497, simple_loss=0.2173, pruned_loss=0.04104, over 4959.00 frames.], tot_loss[loss=0.1429, simple_loss=0.215, pruned_loss=0.03543, over 971263.83 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 16:07:13,841 INFO [train.py:715] (4/8) Epoch 9, batch 32350, loss[loss=0.144, simple_loss=0.2187, pruned_loss=0.03472, over 4774.00 frames.], tot_loss[loss=0.1428, simple_loss=0.2149, pruned_loss=0.03529, over 971663.03 frames.], batch size: 17, lr: 2.30e-04
2022-05-06 16:07:52,332 INFO [train.py:715] (4/8) Epoch 9, batch 32400, loss[loss=0.1274, simple_loss=0.2017, pruned_loss=0.02655, over 4946.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2153, pruned_loss=0.03508, over 972437.54 frames.], batch size: 21, lr: 2.30e-04
2022-05-06 16:08:31,414 INFO [train.py:715] (4/8) Epoch 9, batch 32450, loss[loss=0.1034, simple_loss=0.1715, pruned_loss=0.01761, over 4731.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2147, pruned_loss=0.03472, over 973342.49 frames.], batch size: 12, lr: 2.30e-04
2022-05-06 16:09:10,514 INFO [train.py:715] (4/8) Epoch 9, batch 32500, loss[loss=0.1147, simple_loss=0.1904, pruned_loss=0.01955, over 4884.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03398, over 972834.52 frames.], batch size: 22, lr: 2.30e-04
2022-05-06 16:09:49,358 INFO [train.py:715] (4/8) Epoch 9, batch 32550, loss[loss=0.144, simple_loss=0.2092, pruned_loss=0.03935, over 4982.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2134, pruned_loss=0.03433, over 974029.39 frames.], batch size: 14, lr: 2.30e-04
2022-05-06 16:10:27,861 INFO [train.py:715] (4/8) Epoch 9, batch 32600, loss[loss=0.1637, simple_loss=0.2349, pruned_loss=0.04619, over 4785.00 frames.], tot_loss[loss=0.1425, simple_loss=0.2149, pruned_loss=0.03511, over 974214.77 frames.], batch size: 17, lr: 2.30e-04
2022-05-06 16:11:06,892 INFO [train.py:715] (4/8) Epoch 9, batch 32650, loss[loss=0.1551, simple_loss=0.2321, pruned_loss=0.03906, over 4891.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2144, pruned_loss=0.03508, over 974073.39 frames.], batch size: 22, lr: 2.30e-04
2022-05-06 16:11:45,870 INFO [train.py:715] (4/8) Epoch 9, batch 32700, loss[loss=0.1293, simple_loss=0.2023, pruned_loss=0.02812, over 4835.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2147, pruned_loss=0.03529, over 973551.65 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 16:12:24,795 INFO [train.py:715] (4/8) Epoch 9, batch 32750, loss[loss=0.1373, simple_loss=0.2174, pruned_loss=0.02862, over 4993.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03477, over 972764.66 frames.], batch size: 16, lr: 2.30e-04
2022-05-06 16:13:03,522 INFO [train.py:715] (4/8) Epoch 9, batch 32800, loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.029, over 4937.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03438, over 972568.29 frames.], batch size: 29, lr: 2.30e-04
2022-05-06 16:13:42,565 INFO [train.py:715] (4/8) Epoch 9, batch 32850, loss[loss=0.1578, simple_loss=0.2249, pruned_loss=0.04541, over 4965.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03407, over 972928.33 frames.], batch size: 35, lr: 2.30e-04
2022-05-06 16:14:21,302 INFO [train.py:715] (4/8) Epoch 9, batch 32900, loss[loss=0.1264, simple_loss=0.2036, pruned_loss=0.02456, over 4983.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03396, over 972335.75 frames.], batch size: 28, lr: 2.30e-04
2022-05-06 16:14:59,681 INFO [train.py:715] (4/8) Epoch 9, batch 32950, loss[loss=0.1304, simple_loss=0.1963, pruned_loss=0.0322, over 4907.00 frames.], tot_loss[loss=0.1413, simple_loss=0.214, pruned_loss=0.0343, over 972204.62 frames.], batch size: 17, lr: 2.30e-04
2022-05-06 16:15:38,639 INFO [train.py:715] (4/8) Epoch 9, batch 33000, loss[loss=0.1427, simple_loss=0.2093, pruned_loss=0.03801, over 4812.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03402, over 971807.53 frames.], batch size: 21, lr: 2.30e-04
2022-05-06 16:15:38,640 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 16:15:48,000 INFO [train.py:742] (4/8) Epoch 9, validation: loss=0.1068, simple_loss=0.1913, pruned_loss=0.01119, over 914524.00 frames.
2022-05-06 16:16:27,262 INFO [train.py:715] (4/8) Epoch 9, batch 33050, loss[loss=0.1478, simple_loss=0.2201, pruned_loss=0.03776, over 4771.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2135, pruned_loss=0.03414, over 972237.11 frames.], batch size: 14, lr: 2.30e-04
2022-05-06 16:17:06,452 INFO [train.py:715] (4/8) Epoch 9, batch 33100, loss[loss=0.1248, simple_loss=0.1962, pruned_loss=0.02667, over 4940.00 frames.], tot_loss[loss=0.1415, simple_loss=0.214, pruned_loss=0.03449, over 972152.90 frames.], batch size: 21, lr: 2.30e-04
2022-05-06 16:17:45,641 INFO [train.py:715] (4/8) Epoch 9, batch 33150, loss[loss=0.1368, simple_loss=0.2132, pruned_loss=0.03021, over 4980.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.03462, over 972466.29 frames.], batch size: 25, lr: 2.30e-04
2022-05-06 16:18:25,451 INFO [train.py:715] (4/8) Epoch 9, batch 33200, loss[loss=0.1385, simple_loss=0.2177, pruned_loss=0.02968, over 4935.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03439, over 972896.97 frames.], batch size: 23, lr: 2.30e-04
2022-05-06 16:19:04,996 INFO [train.py:715] (4/8) Epoch 9, batch 33250, loss[loss=0.1719, simple_loss=0.2388, pruned_loss=0.05249, over 4977.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2138, pruned_loss=0.03459, over 972558.20 frames.], batch size: 40, lr: 2.30e-04
2022-05-06 16:19:44,068 INFO [train.py:715] (4/8) Epoch 9, batch 33300, loss[loss=0.1287, simple_loss=0.2032, pruned_loss=0.02707, over 4975.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2129, pruned_loss=0.03386, over 972715.26 frames.], batch size: 28, lr: 2.30e-04
2022-05-06 16:20:23,567 INFO [train.py:715] (4/8) Epoch 9, batch 33350, loss[loss=0.1257, simple_loss=0.1997, pruned_loss=0.0258, over 4881.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.03392, over 973477.18 frames.], batch size: 22, lr: 2.30e-04
2022-05-06 16:21:03,314 INFO [train.py:715] (4/8) Epoch 9, batch 33400, loss[loss=0.1383, simple_loss=0.2162, pruned_loss=0.03019, over 4754.00 frames.], tot_loss[loss=0.141, simple_loss=0.2132, pruned_loss=0.03438, over 972200.56 frames.], batch size: 16, lr: 2.30e-04
2022-05-06 16:21:43,068 INFO [train.py:715] (4/8) Epoch 9, batch 33450, loss[loss=0.1227, simple_loss=0.2019, pruned_loss=0.02177, over 4990.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2134, pruned_loss=0.03442, over 971590.03 frames.], batch size: 14, lr: 2.30e-04
2022-05-06 16:22:22,076 INFO [train.py:715] (4/8) Epoch 9, batch 33500, loss[loss=0.1498, simple_loss=0.2188, pruned_loss=0.04041, over 4833.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2131, pruned_loss=0.03413, over 971941.88 frames.], batch size: 13, lr: 2.30e-04
2022-05-06 16:23:00,825 INFO [train.py:715] (4/8) Epoch 9, batch 33550, loss[loss=0.1477, simple_loss=0.228, pruned_loss=0.03371, over 4901.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2132, pruned_loss=0.03408, over 971685.04 frames.], batch size: 17, lr: 2.30e-04
2022-05-06 16:23:40,547 INFO [train.py:715] (4/8) Epoch 9, batch 33600, loss[loss=0.1343, simple_loss=0.2055, pruned_loss=0.03157, over 4824.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2133, pruned_loss=0.03386, over 971825.85 frames.], batch size: 15, lr: 2.30e-04
2022-05-06 16:24:19,320 INFO [train.py:715] (4/8) Epoch 9, batch 33650, loss[loss=0.1121, simple_loss=0.1881, pruned_loss=0.01803, over 4827.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03366, over 972129.25 frames.], batch size: 26, lr: 2.30e-04
2022-05-06 16:24:58,232 INFO [train.py:715] (4/8) Epoch 9, batch 33700, loss[loss=0.1423, simple_loss=0.2086, pruned_loss=0.03795, over 4842.00 frames.], tot_loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.03365, over 972551.32 frames.], batch size: 13, lr: 2.29e-04
2022-05-06 16:25:37,408 INFO [train.py:715] (4/8) Epoch 9, batch 33750, loss[loss=0.129, simple_loss=0.2052, pruned_loss=0.02639, over 4911.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2131, pruned_loss=0.03397, over 973503.38 frames.], batch size: 18, lr: 2.29e-04
2022-05-06 16:26:16,197 INFO [train.py:715] (4/8) Epoch 9, batch 33800, loss[loss=0.1417, simple_loss=0.2159, pruned_loss=0.03374, over 4865.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2136, pruned_loss=0.03403, over 972991.13 frames.], batch size: 16, lr: 2.29e-04
2022-05-06 16:26:54,913 INFO [train.py:715] (4/8) Epoch 9, batch 33850, loss[loss=0.1297, simple_loss=0.2116, pruned_loss=0.02386, over 4923.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2151, pruned_loss=0.03432, over 973370.07 frames.], batch size: 18, lr: 2.29e-04
2022-05-06 16:27:33,754 INFO [train.py:715] (4/8) Epoch 9, batch 33900, loss[loss=0.1505, simple_loss=0.2232, pruned_loss=0.03889, over 4861.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2142, pruned_loss=0.03404, over 973527.73 frames.], batch size: 15, lr: 2.29e-04
2022-05-06 16:28:13,482 INFO [train.py:715] (4/8) Epoch 9, batch 33950, loss[loss=0.1188, simple_loss=0.1815, pruned_loss=0.028, over 4971.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03397, over 973028.76 frames.], batch size: 14, lr: 2.29e-04
2022-05-06 16:28:52,281 INFO [train.py:715] (4/8) Epoch 9, batch 34000, loss[loss=0.1346, simple_loss=0.1962, pruned_loss=0.03651, over 4799.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2131, pruned_loss=0.0341, over 971942.08 frames.], batch size: 12, lr: 2.29e-04
2022-05-06 16:29:31,510 INFO [train.py:715] (4/8) Epoch 9, batch 34050, loss[loss=0.135, simple_loss=0.2044, pruned_loss=0.03274, over 4706.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2127, pruned_loss=0.03389, over 972539.72 frames.], batch size: 15, lr: 2.29e-04
2022-05-06 16:30:09,975 INFO [train.py:715] (4/8) Epoch 9, batch 34100, loss[loss=0.1451, simple_loss=0.2172, pruned_loss=0.03651, over 4969.00 frames.], tot_loss[loss=0.141, simple_loss=0.2136, pruned_loss=0.03417, over 973042.74 frames.], batch size: 24, lr: 2.29e-04
2022-05-06 16:30:49,070 INFO [train.py:715] (4/8) Epoch 9, batch 34150, loss[loss=0.1667, simple_loss=0.2342, pruned_loss=0.04958, over 4748.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2136, pruned_loss=0.03459, over 971946.71 frames.], batch size: 16, lr: 2.29e-04
2022-05-06 16:31:27,540 INFO [train.py:715] (4/8) Epoch 9, batch 34200, loss[loss=0.1617, simple_loss=0.2472, pruned_loss=0.03811, over 4948.00 frames.], tot_loss[loss=0.1415, simple_loss=0.214, pruned_loss=0.03446, over 972324.78 frames.], batch size: 15, lr: 2.29e-04
2022-05-06 16:32:05,772 INFO [train.py:715] (4/8) Epoch 9, batch 34250, loss[loss=0.1674, simple_loss=0.2274, pruned_loss=0.05369, over 4841.00 frames.], tot_loss[loss=0.1412, simple_loss=0.214, pruned_loss=0.03417, over 972149.63 frames.], batch size: 32, lr: 2.29e-04
2022-05-06 16:32:45,092 INFO [train.py:715] (4/8) Epoch 9, batch 34300, loss[loss=0.1613, simple_loss=0.2334, pruned_loss=0.0446, over 4879.00 frames.], tot_loss[loss=0.1433, simple_loss=0.2161, pruned_loss=0.03522, over 971952.01 frames.], batch size: 32, lr: 2.29e-04
2022-05-06 16:33:23,850 INFO [train.py:715] (4/8) Epoch 9, batch 34350, loss[loss=0.1223, simple_loss=0.1948, pruned_loss=0.02487, over 4776.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2155, pruned_loss=0.03465, over 971445.88 frames.], batch size: 12, lr: 2.29e-04
2022-05-06 16:34:02,523 INFO [train.py:715] (4/8) Epoch 9, batch 34400, loss[loss=0.1464, simple_loss=0.221, pruned_loss=0.03592, over 4849.00 frames.], tot_loss[loss=0.1419, simple_loss=0.215, pruned_loss=0.03445, over 971776.34 frames.], batch size: 30, lr: 2.29e-04
2022-05-06 16:34:41,410 INFO [train.py:715] (4/8) Epoch 9, batch 34450, loss[loss=0.1233, simple_loss=0.1935, pruned_loss=0.02654, over 4792.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2148, pruned_loss=0.03441, over 971356.59 frames.], batch size: 18, lr: 2.29e-04
2022-05-06 16:35:20,339 INFO [train.py:715] (4/8) Epoch 9, batch 34500, loss[loss=0.1256, simple_loss=0.2005, pruned_loss=0.02534, over 4987.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2152, pruned_loss=0.03467, over 971874.79 frames.], batch size: 28, lr: 2.29e-04
2022-05-06 16:35:59,392 INFO [train.py:715] (4/8) Epoch 9, batch 34550, loss[loss=0.1203, simple_loss=0.1938, pruned_loss=0.02333, over 4938.00 frames.], tot_loss[loss=0.1424, simple_loss=0.2154, pruned_loss=0.03473, over 972249.96 frames.], batch size: 29, lr: 2.29e-04
2022-05-06 16:36:38,004 INFO [train.py:715] (4/8) Epoch 9, batch 34600, loss[loss=0.136, simple_loss=0.2085, pruned_loss=0.03177, over 4820.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2144, pruned_loss=0.03425, over 971403.17 frames.], batch size: 27, lr: 2.29e-04
2022-05-06 16:37:17,108 INFO [train.py:715] (4/8) Epoch 9, batch 34650, loss[loss=0.1448, simple_loss=0.2232, pruned_loss=0.03316, over 4835.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2144, pruned_loss=0.03423, over 971012.70 frames.], batch size: 15, lr: 2.29e-04
2022-05-06 16:37:56,491 INFO [train.py:715] (4/8) Epoch 9, batch 34700, loss[loss=0.1618, simple_loss=0.2398, pruned_loss=0.0419, over 4917.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2146, pruned_loss=0.03452, over 971617.09 frames.], batch size: 18, lr: 2.29e-04
2022-05-06 16:38:34,783 INFO [train.py:715] (4/8) Epoch 9, batch 34750, loss[loss=0.1174, simple_loss=0.1879, pruned_loss=0.0235, over 4804.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2142, pruned_loss=0.03476, over 971784.42 frames.], batch size: 17, lr: 2.29e-04
2022-05-06 16:39:12,243 INFO [train.py:715] (4/8) Epoch 9, batch 34800, loss[loss=0.134, simple_loss=0.1995, pruned_loss=0.03421, over 4773.00 frames.], tot_loss[loss=0.141, simple_loss=0.2134, pruned_loss=0.03424, over 971543.83 frames.], batch size: 12, lr: 2.29e-04
2022-05-06 16:40:01,165 INFO [train.py:715] (4/8) Epoch 10, batch 0, loss[loss=0.1674, simple_loss=0.2368, pruned_loss=0.049, over 4930.00 frames.], tot_loss[loss=0.1674, simple_loss=0.2368, pruned_loss=0.049, over 4930.00 frames.], batch size: 18, lr: 2.19e-04
2022-05-06 16:40:41,025 INFO [train.py:715] (4/8) Epoch 10, batch 50, loss[loss=0.1128, simple_loss=0.196, pruned_loss=0.01485, over 4989.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03462, over 219354.55 frames.], batch size: 14, lr: 2.19e-04
2022-05-06 16:41:20,749 INFO [train.py:715] (4/8) Epoch 10, batch 100, loss[loss=0.134, simple_loss=0.2179, pruned_loss=0.02503, over 4748.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2138, pruned_loss=0.03423, over 385988.51 frames.], batch size: 16, lr: 2.19e-04
2022-05-06 16:42:00,756 INFO [train.py:715] (4/8) Epoch 10, batch 150, loss[loss=0.1462, simple_loss=0.2089, pruned_loss=0.04177, over 4758.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.03497, over 516171.98 frames.], batch size: 19, lr: 2.19e-04
2022-05-06 16:42:41,338 INFO [train.py:715] (4/8) Epoch 10, batch 200, loss[loss=0.1575, simple_loss=0.231, pruned_loss=0.04199, over 4838.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2144, pruned_loss=0.03501, over 617049.78 frames.], batch size: 13, lr: 2.19e-04
2022-05-06 16:43:22,386 INFO [train.py:715] (4/8) Epoch 10, batch 250, loss[loss=0.1493, simple_loss=0.2269, pruned_loss=0.03578, over 4750.00 frames.], tot_loss[loss=0.1429, simple_loss=0.2154, pruned_loss=0.0352, over 695907.43 frames.], batch size: 19, lr: 2.19e-04
2022-05-06 16:44:03,226 INFO [train.py:715] (4/8) Epoch 10, batch 300, loss[loss=0.1144, simple_loss=0.186, pruned_loss=0.02134, over 4784.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2148, pruned_loss=0.03493, over 756997.15 frames.], batch size: 17, lr: 2.19e-04
2022-05-06 16:44:43,674 INFO [train.py:715] (4/8) Epoch 10, batch 350, loss[loss=0.1372, simple_loss=0.2156, pruned_loss=0.0294, over 4808.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03427, over 804627.33 frames.], batch size: 25, lr: 2.19e-04
2022-05-06 16:45:25,018 INFO [train.py:715] (4/8) Epoch 10, batch 400, loss[loss=0.1805, simple_loss=0.2562, pruned_loss=0.05239, over 4839.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03423, over 842013.47 frames.], batch size: 30, lr: 2.19e-04
2022-05-06 16:46:06,721 INFO [train.py:715] (4/8) Epoch 10, batch 450, loss[loss=0.1364, simple_loss=0.2052, pruned_loss=0.03379, over 4931.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2132, pruned_loss=0.03407, over 870936.89 frames.], batch size: 23, lr: 2.19e-04
2022-05-06 16:46:47,452 INFO [train.py:715] (4/8) Epoch 10, batch 500, loss[loss=0.1481, simple_loss=0.2144, pruned_loss=0.04084, over 4760.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2118, pruned_loss=0.03387, over 892938.04 frames.], batch size: 19, lr: 2.19e-04
2022-05-06 16:47:28,872 INFO [train.py:715] (4/8) Epoch 10, batch 550, loss[loss=0.1401, simple_loss=0.2143, pruned_loss=0.03293, over 4807.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2122, pruned_loss=0.03369, over 911041.18 frames.], batch size: 21, lr: 2.19e-04
2022-05-06 16:48:10,016 INFO [train.py:715] (4/8) Epoch 10, batch 600, loss[loss=0.1475, simple_loss=0.2168, pruned_loss=0.03915, over 4919.00 frames.], tot_loss[loss=0.14, simple_loss=0.2123, pruned_loss=0.03389, over 923490.73 frames.], batch size: 39, lr: 2.19e-04
2022-05-06 16:48:50,530 INFO [train.py:715] (4/8) Epoch 10, batch 650, loss[loss=0.1543, simple_loss=0.227, pruned_loss=0.04083, over 4812.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2127, pruned_loss=0.03396, over 935293.13 frames.], batch size: 24, lr: 2.19e-04
2022-05-06 16:49:31,181 INFO [train.py:715] (4/8) Epoch 10, batch 700, loss[loss=0.2039, simple_loss=0.2796, pruned_loss=0.06408, over 4813.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03428, over 943594.04 frames.], batch size: 25, lr: 2.19e-04
2022-05-06 16:50:12,717 INFO [train.py:715] (4/8) Epoch 10, batch 750, loss[loss=0.1306, simple_loss=0.206, pruned_loss=0.02754, over 4970.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.0337, over 949486.09 frames.], batch size: 15, lr: 2.19e-04
2022-05-06 16:50:54,000 INFO [train.py:715] (4/8) Epoch 10, batch 800, loss[loss=0.1393, simple_loss=0.2157, pruned_loss=0.03143, over 4855.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2121, pruned_loss=0.03356, over 954813.63 frames.], batch size: 20, lr: 2.19e-04
2022-05-06 16:51:34,427 INFO [train.py:715] (4/8) Epoch 10, batch 850, loss[loss=0.1419, simple_loss=0.2216, pruned_loss=0.03106, over 4853.00 frames.], tot_loss[loss=0.1394, simple_loss=0.212, pruned_loss=0.03337, over 958142.56 frames.], batch size: 20, lr: 2.19e-04
2022-05-06 16:52:15,216 INFO [train.py:715] (4/8) Epoch 10, batch 900, loss[loss=0.1277, simple_loss=0.2003, pruned_loss=0.02756, over 4989.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03333, over 961391.16 frames.], batch size: 26, lr: 2.19e-04
2022-05-06 16:52:55,734 INFO [train.py:715] (4/8) Epoch 10, batch 950, loss[loss=0.1224, simple_loss=0.2013, pruned_loss=0.02181, over 4924.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03345, over 964542.63 frames.], batch size: 18, lr: 2.19e-04
2022-05-06 16:53:35,731 INFO [train.py:715] (4/8) Epoch 10, batch 1000, loss[loss=0.1686, simple_loss=0.2481, pruned_loss=0.04456, over 4853.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.03388, over 966228.25 frames.], batch size: 15, lr: 2.19e-04
2022-05-06 16:54:14,972 INFO [train.py:715] (4/8) Epoch 10, batch 1050, loss[loss=0.1422, simple_loss=0.2069, pruned_loss=0.0388, over 4780.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2134, pruned_loss=0.0334, over 966985.95 frames.], batch size: 12, lr: 2.19e-04
2022-05-06 16:54:55,346 INFO [train.py:715] (4/8) Epoch 10, batch 1100, loss[loss=0.1779, simple_loss=0.2407, pruned_loss=0.05755, over 4776.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.03359, over 967910.26 frames.], batch size: 14, lr: 2.19e-04
2022-05-06 16:55:34,643 INFO [train.py:715] (4/8) Epoch 10, batch 1150, loss[loss=0.1721, simple_loss=0.2242, pruned_loss=0.06, over 4912.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2125, pruned_loss=0.03359, over 969817.05 frames.], batch size: 18, lr: 2.19e-04
2022-05-06 16:56:13,846 INFO [train.py:715] (4/8) Epoch 10, batch 1200, loss[loss=0.1162, simple_loss=0.1995, pruned_loss=0.01646, over 4927.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.03354, over 970339.64 frames.], batch size: 29, lr: 2.19e-04
2022-05-06 16:56:53,601 INFO [train.py:715] (4/8) Epoch 10, batch 1250, loss[loss=0.13, simple_loss=0.1953, pruned_loss=0.03233, over 4870.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.03277, over 971031.85 frames.], batch size: 16, lr: 2.19e-04
2022-05-06 16:57:32,221 INFO [train.py:715] (4/8) Epoch 10, batch 1300, loss[loss=0.1378, simple_loss=0.2181, pruned_loss=0.02871, over 4811.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03269, over 970891.94 frames.], batch size: 26, lr: 2.19e-04
2022-05-06 16:58:11,020 INFO [train.py:715] (4/8) Epoch 10, batch 1350, loss[loss=0.1288, simple_loss=0.2033, pruned_loss=0.02712, over 4834.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03236, over 972312.72 frames.], batch size: 26, lr: 2.19e-04
2022-05-06 16:58:49,195 INFO [train.py:715] (4/8) Epoch 10, batch 1400, loss[loss=0.1196, simple_loss=0.1936, pruned_loss=0.02275, over 4976.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2102, pruned_loss=0.03229, over 972573.18 frames.], batch size: 24, lr: 2.19e-04
2022-05-06 16:59:28,744 INFO [train.py:715] (4/8) Epoch 10, batch 1450, loss[loss=0.1536, simple_loss=0.2257, pruned_loss=0.0408, over 4776.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.03248, over 973124.65 frames.], batch size: 14, lr: 2.19e-04
2022-05-06 17:00:07,716 INFO [train.py:715] (4/8) Epoch 10, batch 1500, loss[loss=0.1113, simple_loss=0.1873, pruned_loss=0.01763, over 4788.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.03192, over 972858.43 frames.], batch size: 17, lr: 2.19e-04
2022-05-06 17:00:46,474 INFO [train.py:715] (4/8) Epoch 10, batch 1550, loss[loss=0.1469, simple_loss=0.2147, pruned_loss=0.0396, over 4854.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03297, over 972813.74 frames.], batch size: 30, lr: 2.19e-04
2022-05-06 17:01:25,571 INFO [train.py:715] (4/8) Epoch 10, batch 1600, loss[loss=0.146, simple_loss=0.2237, pruned_loss=0.03415, over 4788.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.0331, over 973700.16 frames.], batch size: 17, lr: 2.19e-04
2022-05-06 17:02:04,988 INFO [train.py:715] (4/8) Epoch 10, batch 1650, loss[loss=0.1387, simple_loss=0.2213, pruned_loss=0.02805, over 4889.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03294, over 973772.10 frames.], batch size: 22, lr: 2.19e-04
2022-05-06 17:02:43,709 INFO [train.py:715] (4/8) Epoch 10, batch 1700, loss[loss=0.1498, simple_loss=0.2302, pruned_loss=0.03467, over 4932.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.03331, over 973830.48 frames.], batch size: 23, lr: 2.19e-04
2022-05-06 17:03:22,053 INFO [train.py:715] (4/8) Epoch 10, batch 1750, loss[loss=0.1304, simple_loss=0.1981, pruned_loss=0.03132, over 4979.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03375, over 973616.91 frames.], batch size: 15, lr: 2.19e-04
2022-05-06 17:04:02,177 INFO [train.py:715] (4/8) Epoch 10, batch 1800, loss[loss=0.1581, simple_loss=0.2212, pruned_loss=0.04757, over 4877.00 frames.], tot_loss[loss=0.14, simple_loss=0.2126, pruned_loss=0.03366, over 973340.36 frames.], batch size: 32, lr: 2.19e-04
2022-05-06 17:04:41,814 INFO [train.py:715] (4/8) Epoch 10, batch 1850, loss[loss=0.1412, simple_loss=0.2177, pruned_loss=0.03235, over 4822.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.03368, over 973368.38 frames.], batch size: 25, lr: 2.19e-04
2022-05-06 17:05:20,550 INFO [train.py:715] (4/8) Epoch 10, batch 1900, loss[loss=0.126, simple_loss=0.1996, pruned_loss=0.02622, over 4773.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03332, over 972830.49 frames.], batch size: 18, lr: 2.19e-04
2022-05-06 17:05:59,511 INFO [train.py:715] (4/8) Epoch 10, batch 1950, loss[loss=0.1505, simple_loss=0.2224, pruned_loss=0.03933, over 4787.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.03367, over 972392.78 frames.], batch size: 17, lr: 2.18e-04
2022-05-06 17:06:39,837 INFO [train.py:715] (4/8) Epoch 10, batch 2000, loss[loss=0.1248, simple_loss=0.203, pruned_loss=0.02326, over 4870.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.03337, over 973110.05 frames.], batch size: 38, lr: 2.18e-04
2022-05-06 17:07:19,134 INFO [train.py:715] (4/8) Epoch 10, batch 2050, loss[loss=0.1559, simple_loss=0.2256, pruned_loss=0.04307, over 4977.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03357, over 972404.08 frames.], batch size: 14, lr: 2.18e-04
2022-05-06 17:07:57,715 INFO [train.py:715] (4/8) Epoch 10, batch 2100, loss[loss=0.118, simple_loss=0.1956, pruned_loss=0.02025, over 4953.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03326, over 972168.98 frames.], batch size: 24, lr: 2.18e-04
2022-05-06 17:08:37,348 INFO [train.py:715] (4/8) Epoch 10, batch 2150, loss[loss=0.1696, simple_loss=0.2462, pruned_loss=0.04651, over 4879.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.03317, over 971884.87 frames.], batch size: 16, lr: 2.18e-04
2022-05-06 17:09:16,485 INFO [train.py:715] (4/8) Epoch 10, batch 2200, loss[loss=0.1472, simple_loss=0.2205, pruned_loss=0.03697, over 4912.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2138, pruned_loss=0.03392, over 972582.31 frames.], batch size: 18, lr: 2.18e-04
2022-05-06 17:09:55,192 INFO [train.py:715] (4/8) Epoch 10, batch 2250, loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02807, over 4725.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2144, pruned_loss=0.03412, over 972360.14 frames.], batch size: 15, lr: 2.18e-04
2022-05-06 17:10:33,967 INFO [train.py:715] (4/8) Epoch 10, batch 2300, loss[loss=0.1378, simple_loss=0.2167, pruned_loss=0.02947, over 4977.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2136, pruned_loss=0.03356, over 972688.23 frames.], batch size: 24, lr: 2.18e-04
2022-05-06 17:11:13,694 INFO [train.py:715] (4/8) Epoch 10, batch 2350, loss[loss=0.1301, simple_loss=0.204, pruned_loss=0.02803, over 4816.00 frames.], tot_loss[loss=0.14, simple_loss=0.2131, pruned_loss=0.0335, over 973088.16 frames.], batch size: 26, lr: 2.18e-04
2022-05-06 17:11:52,498 INFO [train.py:715] (4/8) Epoch 10, batch 2400, loss[loss=0.1364, simple_loss=0.2016, pruned_loss=0.03556, over 4843.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03335, over 972391.26 frames.], batch size: 13, lr: 2.18e-04
2022-05-06 17:12:31,235 INFO [train.py:715] (4/8) Epoch 10, batch 2450, loss[loss=0.1336, simple_loss=0.2115, pruned_loss=0.0279, over 4979.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03333, over 972473.67 frames.], batch size: 14, lr: 2.18e-04
2022-05-06 17:13:10,536 INFO [train.py:715] (4/8) Epoch 10, batch 2500, loss[loss=0.1359, simple_loss=0.2155, pruned_loss=0.02816, over 4856.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2116, pruned_loss=0.03307, over 972993.87 frames.], batch size: 20, lr: 2.18e-04
2022-05-06 17:13:49,922 INFO [train.py:715] (4/8) Epoch 10, batch 2550, loss[loss=0.1239, simple_loss=0.194, pruned_loss=0.02692, over 4785.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03298, over 972706.28 frames.], batch size: 17, lr: 2.18e-04
2022-05-06 17:14:29,358 INFO [train.py:715] (4/8) Epoch 10, batch 2600, loss[loss=0.1412, simple_loss=0.2133, pruned_loss=0.03458, over 4962.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.0328, over 973135.91 frames.], batch size: 15, lr: 2.18e-04
2022-05-06 17:15:08,460 INFO [train.py:715] (4/8) Epoch 10, batch 2650, loss[loss=0.1302, simple_loss=0.2019, pruned_loss=0.02927, over 4830.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2125, pruned_loss=0.03288, over 972631.56 frames.], batch size: 27, lr: 2.18e-04
2022-05-06 17:15:47,657 INFO [train.py:715] (4/8) Epoch 10, batch 2700, loss[loss=0.117, simple_loss=0.1873, pruned_loss=0.02336, over 4922.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03292, over 972835.94 frames.], batch size: 18, lr: 2.18e-04
2022-05-06 17:16:26,375 INFO [train.py:715] (4/8) Epoch 10, batch 2750, loss[loss=0.1472, simple_loss=0.2167, pruned_loss=0.0389, over 4885.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2128, pruned_loss=0.03305, over 972212.25 frames.], batch size: 38, lr: 2.18e-04
2022-05-06 17:17:05,077 INFO [train.py:715] (4/8) Epoch 10, batch 2800, loss[loss=0.1362, simple_loss=0.2065, pruned_loss=0.03298, over 4861.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2133, pruned_loss=0.03389, over 971930.00 frames.], batch size: 20, lr: 2.18e-04
2022-05-06 17:17:43,817 INFO [train.py:715] (4/8) Epoch 10, batch 2850, loss[loss=0.1693, simple_loss=0.2345, pruned_loss=0.05204, over 4709.00 frames.], tot_loss[loss=0.14, simple_loss=0.2124, pruned_loss=0.03378, over 971303.08 frames.], batch size: 15, lr: 2.18e-04
2022-05-06 17:18:23,064 INFO [train.py:715] (4/8) Epoch 10, batch 2900, loss[loss=0.1491, simple_loss=0.2185, pruned_loss=0.03987, over 4973.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2112, pruned_loss=0.0331, over 971981.96 frames.], batch size: 24, lr: 2.18e-04
2022-05-06 17:19:02,252 INFO [train.py:715] (4/8) Epoch 10, batch 2950, loss[loss=0.1485, simple_loss=0.2293, pruned_loss=0.03384, over 4903.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2109, pruned_loss=0.03305, over 971681.17 frames.], batch size: 19, lr: 2.18e-04
2022-05-06 17:19:40,635 INFO [train.py:715] (4/8) Epoch 10, batch 3000, loss[loss=0.1435, simple_loss=0.2027, pruned_loss=0.04219, over 4872.00 frames.], tot_loss[loss=0.139, simple_loss=0.2114, pruned_loss=0.03327, over 971879.26 frames.], batch size: 32, lr: 2.18e-04
2022-05-06 17:19:40,636 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 17:19:50,100 INFO [train.py:742] (4/8) Epoch 10, validation: loss=0.1065, simple_loss=0.1908, pruned_loss=0.01113, over 914524.00 frames.
2022-05-06 17:20:28,625 INFO [train.py:715] (4/8) Epoch 10, batch 3050, loss[loss=0.1544, simple_loss=0.2312, pruned_loss=0.03879, over 4919.00 frames.], tot_loss[loss=0.14, simple_loss=0.2125, pruned_loss=0.0338, over 972704.69 frames.], batch size: 29, lr: 2.18e-04
2022-05-06 17:21:07,568 INFO [train.py:715] (4/8) Epoch 10, batch 3100, loss[loss=0.1024, simple_loss=0.1748, pruned_loss=0.01504, over 4816.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2125, pruned_loss=0.03353, over 971721.64 frames.], batch size: 13, lr: 2.18e-04
2022-05-06 17:21:46,721 INFO [train.py:715] (4/8) Epoch 10, batch 3150, loss[loss=0.1389, simple_loss=0.2087, pruned_loss=0.03455, over 4914.00 frames.], tot_loss[loss=0.14, simple_loss=0.2125, pruned_loss=0.03374, over 972385.96 frames.], batch size: 23, lr: 2.18e-04
2022-05-06 17:22:25,538 INFO [train.py:715] (4/8) Epoch 10, batch 3200, loss[loss=0.1507, simple_loss=0.2213, pruned_loss=0.04009, over 4965.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2132, pruned_loss=0.03403, over 972573.33 frames.], batch size: 15, lr: 2.18e-04
2022-05-06 17:23:03,970 INFO [train.py:715] (4/8) Epoch 10, batch 3250, loss[loss=0.1441, simple_loss=0.2159, pruned_loss=0.03612, over 4879.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2135, pruned_loss=0.03414, over 971955.43 frames.], batch size: 32, lr: 2.18e-04
2022-05-06 17:23:44,486 INFO [train.py:715] (4/8) Epoch 10, batch 3300, loss[loss=0.136, simple_loss=0.2142, pruned_loss=0.02895, over 4780.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2136, pruned_loss=0.03433, over 971628.66 frames.], batch size: 17, lr: 2.18e-04
2022-05-06 17:24:24,198 INFO [train.py:715] (4/8) Epoch 10, batch 3350, loss[loss=0.1481, simple_loss=0.2277, pruned_loss=0.03425, over 4831.00 frames.], tot_loss[loss=0.1422, simple_loss=0.2145, pruned_loss=0.03498, over 971948.67 frames.], batch size: 26, lr: 2.18e-04
2022-05-06 17:25:04,066 INFO [train.py:715] (4/8) Epoch 10, batch 3400, loss[loss=0.1323, simple_loss=0.2126, pruned_loss=0.026, over 4777.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03441, over 971544.33 frames.], batch size: 18, lr: 2.18e-04
2022-05-06 17:25:44,873 INFO [train.py:715] (4/8) Epoch 10, batch 3450, loss[loss=0.1602, simple_loss=0.2244, pruned_loss=0.04801, over 4968.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2141, pruned_loss=0.03456, over 971802.95 frames.], batch size: 35, lr: 2.18e-04
2022-05-06 17:26:26,597 INFO [train.py:715] (4/8) Epoch 10, batch 3500, loss[loss=0.1543, simple_loss=0.2401, pruned_loss=0.03426, over 4941.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2142, pruned_loss=0.03452, over 972089.31 frames.], batch size: 21, lr: 2.18e-04
2022-05-06 17:27:07,253 INFO [train.py:715] (4/8) Epoch 10, batch 3550, loss[loss=0.1946, simple_loss=0.2704, pruned_loss=0.05933, over 4946.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.03379, over 972551.69 frames.], batch size: 23, lr: 2.18e-04
2022-05-06 17:27:48,531 INFO [train.py:715] (4/8) Epoch 10, batch 3600, loss[loss=0.1171, simple_loss=0.1887, pruned_loss=0.02276, over 4650.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2143, pruned_loss=0.03424, over 972425.72 frames.], batch size: 13, lr: 2.18e-04
2022-05-06 17:28:29,162 INFO [train.py:715] (4/8) Epoch 10, batch 3650, loss[loss=0.1476, simple_loss=0.2109, pruned_loss=0.0421, over 4793.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2144, pruned_loss=0.03419, over 971963.02 frames.], batch size: 17, lr: 2.18e-04
2022-05-06 17:29:10,555 INFO [train.py:715] (4/8) Epoch 10, batch 3700, loss[loss=0.1363, simple_loss=0.2141, pruned_loss=0.02922, over 4924.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2144, pruned_loss=0.03438, over 972517.76 frames.], batch size: 18, lr: 2.18e-04
2022-05-06 17:29:51,150 INFO [train.py:715] (4/8) Epoch 10, batch 3750, loss[loss=0.1583, simple_loss=0.2285, pruned_loss=0.04405, over 4856.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.0343, over 972285.83 frames.], batch size: 20, lr: 2.18e-04
2022-05-06 17:30:32,373 INFO [train.py:715] (4/8) Epoch 10, batch 3800, loss[loss=0.1265, simple_loss=0.2064, pruned_loss=0.02327, over 4686.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2133, pruned_loss=0.03339, over 972261.93 frames.], batch size: 15, lr: 2.18e-04
2022-05-06 17:31:13,741 INFO [train.py:715] (4/8) Epoch 10, batch 3850, loss[loss=0.1387, simple_loss=0.2088, pruned_loss=0.03426, over 4935.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03325, over 972633.57 frames.], batch size: 18, lr: 2.18e-04
2022-05-06 17:31:54,715 INFO [train.py:715] (4/8) Epoch 10, batch 3900, loss[loss=0.1384, simple_loss=0.2155, pruned_loss=0.03069, over 4904.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2133, pruned_loss=0.03359, over 973401.81 frames.], batch size: 22, lr: 2.18e-04
2022-05-06 17:32:36,892 INFO [train.py:715] (4/8) Epoch 10, batch 3950, loss[loss=0.1265, simple_loss=0.2009, pruned_loss=0.02602, over 4934.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03391, over 973496.42 frames.], batch size: 23, lr: 2.18e-04
2022-05-06 17:33:16,174 INFO [train.py:715] (4/8) Epoch 10, batch 4000, loss[loss=0.1297, simple_loss=0.1994, pruned_loss=0.03003, over 4874.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2134, pruned_loss=0.03366, over 973384.91 frames.], batch size: 22, lr: 2.18e-04
2022-05-06 17:33:55,835 INFO [train.py:715] (4/8) Epoch 10, batch 4050, loss[loss=0.1462, simple_loss=0.2035, pruned_loss=0.04443, over 4841.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2139, pruned_loss=0.03392, over 974056.57 frames.], batch size: 30, lr: 2.18e-04
2022-05-06 17:34:34,555 INFO [train.py:715] (4/8) Epoch 10, batch 4100, loss[loss=0.1356, simple_loss=0.2104, pruned_loss=0.03041, over 4950.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2139, pruned_loss=0.03366, over 973322.30 frames.], batch size: 39, lr: 2.18e-04
2022-05-06 17:35:13,432 INFO [train.py:715] (4/8) Epoch 10, batch 4150, loss[loss=0.1493, simple_loss=0.2239, pruned_loss=0.0373, over 4975.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03361, over 973033.22 frames.], batch size: 24, lr: 2.18e-04
2022-05-06 17:35:52,989 INFO [train.py:715] (4/8) Epoch 10, batch 4200, loss[loss=0.1253, simple_loss=0.2019, pruned_loss=0.02437, over 4969.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2132, pruned_loss=0.03347, over 972982.79 frames.], batch size: 28, lr: 2.18e-04
2022-05-06 17:36:31,673 INFO [train.py:715] (4/8) Epoch 10, batch 4250, loss[loss=0.1281, simple_loss=0.2005, pruned_loss=0.02789, over 4852.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2139, pruned_loss=0.03401, over 972924.53 frames.], batch size: 34, lr: 2.18e-04
2022-05-06 17:37:10,485 INFO [train.py:715] (4/8) Epoch 10, batch 4300, loss[loss=0.1642, simple_loss=0.2357, pruned_loss=0.04637, over 4930.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03374, over 972715.18 frames.], batch size: 29, lr: 2.18e-04
2022-05-06 17:37:49,692 INFO [train.py:715] (4/8) Epoch 10, batch 4350, loss[loss=0.1628, simple_loss=0.2281, pruned_loss=0.04874, over 4774.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2133, pruned_loss=0.03362, over 972943.96 frames.], batch size: 18, lr: 2.18e-04
2022-05-06 17:38:28,651 INFO [train.py:715] (4/8) Epoch 10, batch 4400, loss[loss=0.1283, simple_loss=0.2044, pruned_loss=0.02606, over 4938.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03357, over 972747.68 frames.], batch size: 21, lr: 2.18e-04
2022-05-06 17:39:07,611 INFO [train.py:715] (4/8) Epoch 10, batch 4450, loss[loss=0.1408, simple_loss=0.2061, pruned_loss=0.03778, over 4880.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2136, pruned_loss=0.03356, over 973461.31 frames.], batch size: 32, lr: 2.18e-04
2022-05-06 17:39:46,321 INFO [train.py:715] (4/8) Epoch 10, batch 4500, loss[loss=0.1245, simple_loss=0.2022, pruned_loss=0.02337, over 4793.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2133, pruned_loss=0.03315, over 972793.85 frames.], batch size: 18, lr: 2.18e-04
2022-05-06 17:40:25,795 INFO [train.py:715] (4/8) Epoch 10, batch 4550, loss[loss=0.1677, simple_loss=0.2361, pruned_loss=0.04968, over 4794.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03359, over 972649.36 frames.], batch size: 18, lr: 2.18e-04
2022-05-06 17:41:04,678 INFO [train.py:715] (4/8) Epoch 10, batch 4600, loss[loss=0.1508, simple_loss=0.218, pruned_loss=0.04174, over 4828.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.03381, over 972269.96 frames.], batch size: 25, lr: 2.18e-04
2022-05-06 17:41:43,576 INFO [train.py:715] (4/8) Epoch 10, batch 4650, loss[loss=0.1402, simple_loss=0.2147, pruned_loss=0.03281, over 4754.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2154, pruned_loss=0.03442, over 972685.67 frames.], batch size: 19, lr: 2.18e-04
2022-05-06 17:42:23,846 INFO [train.py:715] (4/8) Epoch 10, batch 4700, loss[loss=0.1399, simple_loss=0.2105, pruned_loss=0.03468, over 4828.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2152, pruned_loss=0.03469, over 972249.32 frames.], batch size: 27, lr: 2.18e-04
2022-05-06 17:43:03,992 INFO [train.py:715] (4/8) Epoch 10, batch 4750, loss[loss=0.124, simple_loss=0.2093, pruned_loss=0.01933, over 4822.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2148, pruned_loss=0.03449, over 972286.85 frames.], batch size: 26, lr: 2.18e-04
2022-05-06 17:43:43,178 INFO [train.py:715] (4/8) Epoch 10, batch 4800, loss[loss=0.1193, simple_loss=0.1882, pruned_loss=0.0252, over 4976.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2141, pruned_loss=0.03422, over 973324.47 frames.], batch size: 35, lr: 2.18e-04
2022-05-06 17:44:23,014 INFO [train.py:715] (4/8) Epoch 10, batch 4850, loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03156, over 4868.00 frames.], tot_loss[loss=0.141, simple_loss=0.2137, pruned_loss=0.03413, over 973387.89 frames.], batch size: 20, lr: 2.18e-04
2022-05-06 17:45:02,963 INFO [train.py:715] (4/8) Epoch 10, batch 4900, loss[loss=0.1236, simple_loss=0.2012, pruned_loss=0.02294, over 4757.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2138, pruned_loss=0.0345, over 972846.98 frames.], batch size: 12, lr: 2.18e-04
2022-05-06 17:45:42,413 INFO [train.py:715] (4/8) Epoch 10, batch 4950, loss[loss=0.144, simple_loss=0.2143, pruned_loss=0.03684, over 4700.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2137, pruned_loss=0.03468, over 971885.72 frames.], batch size: 15, lr: 2.18e-04
2022-05-06 17:46:21,437 INFO [train.py:715] (4/8) Epoch 10, batch 5000, loss[loss=0.1448, simple_loss=0.2172, pruned_loss=0.03625, over 4790.00 frames.], tot_loss[loss=0.1413, simple_loss=0.214, pruned_loss=0.03434, over 971574.25 frames.], batch size: 17, lr: 2.18e-04
2022-05-06 17:47:00,598 INFO [train.py:715] (4/8) Epoch 10, batch 5050, loss[loss=0.1153, simple_loss=0.1804, pruned_loss=0.02508, over 4741.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.0341, over 972003.39 frames.], batch size: 12, lr: 2.18e-04
2022-05-06 17:47:39,527 INFO [train.py:715] (4/8) Epoch 10, batch 5100, loss[loss=0.1427, simple_loss=0.2111, pruned_loss=0.03714, over 4803.00 frames.], tot_loss[loss=0.1404, simple_loss=0.213, pruned_loss=0.03387, over 972504.56 frames.], batch size: 21, lr: 2.18e-04
2022-05-06 17:48:18,799 INFO [train.py:715] (4/8) Epoch 10, batch 5150, loss[loss=0.1768, simple_loss=0.246, pruned_loss=0.05382, over 4977.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2124, pruned_loss=0.03337, over 973108.46 frames.], batch size: 24, lr: 2.18e-04
2022-05-06 17:48:58,634 INFO [train.py:715] (4/8) Epoch 10, batch 5200, loss[loss=0.1156, simple_loss=0.1957, pruned_loss=0.01774, over 4810.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03303, over 971744.13 frames.], batch size: 27, lr: 2.17e-04
2022-05-06 17:49:38,471 INFO [train.py:715] (4/8) Epoch 10, batch 5250, loss[loss=0.1222, simple_loss=0.2065, pruned_loss=0.01896, over 4979.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03327, over 972384.27 frames.], batch size: 25, lr: 2.17e-04
2022-05-06 17:50:17,852 INFO [train.py:715] (4/8) Epoch 10, batch 5300, loss[loss=0.1346, simple_loss=0.2158, pruned_loss=0.02667, over 4978.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03322, over 972518.35 frames.], batch size: 25, lr: 2.17e-04
2022-05-06 17:50:57,191 INFO [train.py:715] (4/8) Epoch 10, batch 5350, loss[loss=0.1587, simple_loss=0.2181, pruned_loss=0.04966, over 4990.00 frames.], tot_loss[loss=0.14, simple_loss=0.2128, pruned_loss=0.03361, over 973334.76 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 17:51:37,022 INFO [train.py:715] (4/8) Epoch 10, batch 5400, loss[loss=0.1257, simple_loss=0.1887, pruned_loss=0.03132, over 4753.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2129, pruned_loss=0.03375, over 972274.85 frames.], batch size: 19, lr: 2.17e-04
2022-05-06 17:52:16,938 INFO [train.py:715] (4/8) Epoch 10, batch 5450, loss[loss=0.1474, simple_loss=0.208, pruned_loss=0.0434, over 4962.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.0331, over 972490.30 frames.], batch size: 35, lr: 2.17e-04
2022-05-06 17:52:56,344 INFO [train.py:715] (4/8) Epoch 10, batch 5500, loss[loss=0.1211, simple_loss=0.1928, pruned_loss=0.02472, over 4829.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2128, pruned_loss=0.03331, over 972553.39 frames.], batch size: 13, lr: 2.17e-04
2022-05-06 17:53:36,102 INFO [train.py:715] (4/8) Epoch 10, batch 5550, loss[loss=0.1327, simple_loss=0.2106, pruned_loss=0.02739, over 4954.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2125, pruned_loss=0.03343, over 972778.15 frames.], batch size: 21, lr: 2.17e-04
2022-05-06 17:54:16,053 INFO [train.py:715] (4/8) Epoch 10, batch 5600, loss[loss=0.1667, simple_loss=0.235, pruned_loss=0.04918, over 4826.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03329, over 972772.31 frames.], batch size: 26, lr: 2.17e-04
2022-05-06 17:54:55,812 INFO [train.py:715] (4/8) Epoch 10, batch 5650, loss[loss=0.174, simple_loss=0.2622, pruned_loss=0.04289, over 4884.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.0333, over 972926.07 frames.], batch size: 19, lr: 2.17e-04
2022-05-06 17:55:34,978 INFO [train.py:715] (4/8) Epoch 10, batch 5700, loss[loss=0.1514, simple_loss=0.2232, pruned_loss=0.03982, over 4934.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2132, pruned_loss=0.03387, over 973693.56 frames.], batch size: 35, lr: 2.17e-04
2022-05-06 17:56:15,021 INFO [train.py:715] (4/8) Epoch 10, batch 5750, loss[loss=0.1155, simple_loss=0.1934, pruned_loss=0.01873, over 4803.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03434, over 972798.49 frames.], batch size: 24, lr: 2.17e-04
2022-05-06 17:56:54,685 INFO [train.py:715] (4/8) Epoch 10, batch 5800, loss[loss=0.1344, simple_loss=0.2137, pruned_loss=0.02752, over 4767.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03427, over 972752.06 frames.], batch size: 12, lr: 2.17e-04
2022-05-06 17:57:34,208 INFO [train.py:715] (4/8) Epoch 10, batch 5850, loss[loss=0.136, simple_loss=0.2131, pruned_loss=0.02944, over 4814.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03467, over 972416.18 frames.], batch size: 25, lr: 2.17e-04
2022-05-06 17:58:14,026 INFO [train.py:715] (4/8) Epoch 10, batch 5900, loss[loss=0.1198, simple_loss=0.188, pruned_loss=0.02583, over 4910.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2137, pruned_loss=0.03403, over 971317.52 frames.], batch size: 17, lr: 2.17e-04
2022-05-06 17:58:53,765 INFO [train.py:715] (4/8) Epoch 10, batch 5950, loss[loss=0.1583, simple_loss=0.2352, pruned_loss=0.04069, over 4863.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2138, pruned_loss=0.03384, over 971967.28 frames.], batch size: 20, lr: 2.17e-04
2022-05-06 17:59:33,428 INFO [train.py:715] (4/8) Epoch 10, batch 6000, loss[loss=0.1421, simple_loss=0.2111, pruned_loss=0.03654, over 4907.00 frames.], tot_loss[loss=0.141, simple_loss=0.2139, pruned_loss=0.03407, over 972083.71 frames.], batch size: 17, lr: 2.17e-04
2022-05-06 17:59:33,428 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 17:59:42,752 INFO [train.py:742] (4/8) Epoch 10, validation: loss=0.1067, simple_loss=0.1909, pruned_loss=0.01126, over 914524.00 frames.
2022-05-06 18:00:22,326 INFO [train.py:715] (4/8) Epoch 10, batch 6050, loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.0289, over 4867.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2145, pruned_loss=0.03429, over 972163.30 frames.], batch size: 20, lr: 2.17e-04
2022-05-06 18:01:00,749 INFO [train.py:715] (4/8) Epoch 10, batch 6100, loss[loss=0.1326, simple_loss=0.2096, pruned_loss=0.02784, over 4809.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2144, pruned_loss=0.03429, over 971349.54 frames.], batch size: 12, lr: 2.17e-04
2022-05-06 18:01:40,208 INFO [train.py:715] (4/8) Epoch 10, batch 6150, loss[loss=0.1643, simple_loss=0.2226, pruned_loss=0.053, over 4971.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2144, pruned_loss=0.03473, over 970938.18 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 18:02:20,067 INFO [train.py:715] (4/8) Epoch 10, batch 6200, loss[loss=0.136, simple_loss=0.2053, pruned_loss=0.03332, over 4777.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2134, pruned_loss=0.03407, over 971551.62 frames.], batch size: 14, lr: 2.17e-04
2022-05-06 18:02:59,938 INFO [train.py:715] (4/8) Epoch 10, batch 6250, loss[loss=0.1127, simple_loss=0.1931, pruned_loss=0.01613, over 4927.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03392, over 971713.23 frames.], batch size: 18, lr: 2.17e-04
2022-05-06 18:03:39,467 INFO [train.py:715] (4/8) Epoch 10, batch 6300, loss[loss=0.1175, simple_loss=0.1904, pruned_loss=0.02227, over 4896.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2128, pruned_loss=0.03376, over 971608.46 frames.], batch size: 22, lr: 2.17e-04
2022-05-06 18:04:19,281 INFO [train.py:715] (4/8) Epoch 10, batch 6350, loss[loss=0.1338, simple_loss=0.2055, pruned_loss=0.03105, over 4986.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03373, over 971045.88 frames.], batch size: 26, lr: 2.17e-04
2022-05-06 18:04:58,325 INFO [train.py:715] (4/8) Epoch 10, batch 6400, loss[loss=0.1377, simple_loss=0.2178, pruned_loss=0.02885, over 4890.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2123, pruned_loss=0.03317, over 971210.66 frames.], batch size: 22, lr: 2.17e-04
2022-05-06 18:05:36,734 INFO [train.py:715] (4/8) Epoch 10, batch 6450, loss[loss=0.1158, simple_loss=0.1832, pruned_loss=0.02422, over 4865.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.03411, over 971677.46 frames.], batch size: 16, lr: 2.17e-04
2022-05-06 18:06:15,660 INFO [train.py:715] (4/8) Epoch 10, batch 6500, loss[loss=0.1684, simple_loss=0.2312, pruned_loss=0.05283, over 4983.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2132, pruned_loss=0.03403, over 971659.16 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 18:06:54,790 INFO [train.py:715] (4/8) Epoch 10, batch 6550, loss[loss=0.1647, simple_loss=0.2272, pruned_loss=0.05113, over 4778.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.03353, over 971358.85 frames.], batch size: 14, lr: 2.17e-04
2022-05-06 18:07:33,933 INFO [train.py:715] (4/8) Epoch 10, batch 6600, loss[loss=0.1266, simple_loss=0.2036, pruned_loss=0.02482, over 4787.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03308, over 971062.69 frames.], batch size: 14, lr: 2.17e-04
2022-05-06 18:08:12,486 INFO [train.py:715] (4/8) Epoch 10, batch 6650, loss[loss=0.1599, simple_loss=0.2387, pruned_loss=0.04053, over 4934.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2117, pruned_loss=0.03303, over 970982.52 frames.], batch size: 23, lr: 2.17e-04
2022-05-06 18:08:52,599 INFO [train.py:715] (4/8) Epoch 10, batch 6700, loss[loss=0.1484, simple_loss=0.2142, pruned_loss=0.04134, over 4822.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.033, over 972224.85 frames.], batch size: 26, lr: 2.17e-04
2022-05-06 18:09:31,852 INFO [train.py:715] (4/8) Epoch 10, batch 6750, loss[loss=0.1791, simple_loss=0.2371, pruned_loss=0.06052, over 4878.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03335, over 973143.03 frames.], batch size: 16, lr: 2.17e-04
2022-05-06 18:10:10,541 INFO [train.py:715] (4/8) Epoch 10, batch 6800, loss[loss=0.1848, simple_loss=0.2383, pruned_loss=0.06564, over 4834.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2131, pruned_loss=0.03405, over 972771.19 frames.], batch size: 30, lr: 2.17e-04
2022-05-06 18:10:50,411 INFO [train.py:715] (4/8) Epoch 10, batch 6850, loss[loss=0.1523, simple_loss=0.2298, pruned_loss=0.03736, over 4884.00 frames.], tot_loss[loss=0.141, simple_loss=0.2139, pruned_loss=0.03404, over 972745.56 frames.], batch size: 32, lr: 2.17e-04
2022-05-06 18:11:29,656 INFO [train.py:715] (4/8) Epoch 10, batch 6900, loss[loss=0.1697, simple_loss=0.2426, pruned_loss=0.04836, over 4947.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2145, pruned_loss=0.03424, over 973436.19 frames.], batch size: 21, lr: 2.17e-04
2022-05-06 18:12:08,732 INFO [train.py:715] (4/8) Epoch 10, batch 6950, loss[loss=0.1402, simple_loss=0.2127, pruned_loss=0.03388, over 4741.00 frames.], tot_loss[loss=0.1412, simple_loss=0.214, pruned_loss=0.03418, over 972816.95 frames.], batch size: 16, lr: 2.17e-04
2022-05-06 18:12:48,641 INFO [train.py:715] (4/8) Epoch 10, batch 7000, loss[loss=0.1252, simple_loss=0.1995, pruned_loss=0.02547, over 4813.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2133, pruned_loss=0.03377, over 972671.96 frames.], batch size: 27, lr: 2.17e-04
2022-05-06 18:13:28,548 INFO [train.py:715] (4/8) Epoch 10, batch 7050, loss[loss=0.1241, simple_loss=0.1951, pruned_loss=0.02652, over 4840.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03356, over 972171.95 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 18:14:07,741 INFO [train.py:715] (4/8) Epoch 10, batch 7100, loss[loss=0.1675, simple_loss=0.2472, pruned_loss=0.04387, over 4745.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2137, pruned_loss=0.03393, over 972119.68 frames.], batch size: 19, lr: 2.17e-04
2022-05-06 18:14:46,915 INFO [train.py:715] (4/8) Epoch 10, batch 7150, loss[loss=0.1424, simple_loss=0.2101, pruned_loss=0.03733, over 4923.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2136, pruned_loss=0.03401, over 972278.56 frames.], batch size: 18, lr: 2.17e-04
2022-05-06 18:15:26,295 INFO [train.py:715] (4/8) Epoch 10, batch 7200, loss[loss=0.1337, simple_loss=0.2055, pruned_loss=0.03097, over 4650.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03426, over 971868.86 frames.], batch size: 13, lr: 2.17e-04
2022-05-06 18:16:05,420 INFO [train.py:715] (4/8) Epoch 10, batch 7250, loss[loss=0.1384, simple_loss=0.2157, pruned_loss=0.0305, over 4792.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03399, over 972133.21 frames.], batch size: 21, lr: 2.17e-04
2022-05-06 18:16:44,408 INFO [train.py:715] (4/8) Epoch 10, batch 7300, loss[loss=0.1294, simple_loss=0.1979, pruned_loss=0.03042, over 4826.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2144, pruned_loss=0.03446, over 972415.93 frames.], batch size: 26, lr: 2.17e-04
2022-05-06 18:17:23,331 INFO [train.py:715] (4/8) Epoch 10, batch 7350, loss[loss=0.144, simple_loss=0.2179, pruned_loss=0.03508, over 4954.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2148, pruned_loss=0.03452, over 971514.85 frames.], batch size: 39, lr: 2.17e-04
2022-05-06 18:18:02,743 INFO [train.py:715] (4/8) Epoch 10, batch 7400, loss[loss=0.1311, simple_loss=0.195, pruned_loss=0.03358, over 4816.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2146, pruned_loss=0.03424, over 971657.03 frames.], batch size: 26, lr: 2.17e-04
2022-05-06 18:18:41,885 INFO [train.py:715] (4/8) Epoch 10, batch 7450, loss[loss=0.1421, simple_loss=0.2141, pruned_loss=0.03503, over 4885.00 frames.], tot_loss[loss=0.141, simple_loss=0.2141, pruned_loss=0.03388, over 970898.49 frames.], batch size: 19, lr: 2.17e-04
2022-05-06 18:19:20,015 INFO [train.py:715] (4/8) Epoch 10, batch 7500, loss[loss=0.1489, simple_loss=0.2303, pruned_loss=0.03372, over 4734.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.03336, over 971235.83 frames.], batch size: 16, lr: 2.17e-04
2022-05-06 18:19:59,645 INFO [train.py:715] (4/8) Epoch 10, batch 7550, loss[loss=0.1282, simple_loss=0.2146, pruned_loss=0.0209, over 4989.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.0331, over 970469.60 frames.], batch size: 26, lr: 2.17e-04
2022-05-06 18:20:38,459 INFO [train.py:715] (4/8) Epoch 10, batch 7600, loss[loss=0.1337, simple_loss=0.2091, pruned_loss=0.02917, over 4932.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.03337, over 970791.99 frames.], batch size: 21, lr: 2.17e-04
2022-05-06 18:21:17,037 INFO [train.py:715] (4/8) Epoch 10, batch 7650, loss[loss=0.1244, simple_loss=0.1989, pruned_loss=0.0249, over 4878.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03307, over 971423.43 frames.], batch size: 16, lr: 2.17e-04
2022-05-06 18:21:56,436 INFO [train.py:715] (4/8) Epoch 10, batch 7700, loss[loss=0.1611, simple_loss=0.224, pruned_loss=0.04913, over 4975.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03349, over 971498.23 frames.], batch size: 31, lr: 2.17e-04
2022-05-06 18:22:35,792 INFO [train.py:715] (4/8) Epoch 10, batch 7750, loss[loss=0.1208, simple_loss=0.1927, pruned_loss=0.02449, over 4883.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.03333, over 971679.39 frames.], batch size: 19, lr: 2.17e-04
2022-05-06 18:23:15,171 INFO [train.py:715] (4/8) Epoch 10, batch 7800, loss[loss=0.1469, simple_loss=0.2264, pruned_loss=0.0337, over 4970.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2137, pruned_loss=0.03396, over 971579.68 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 18:23:53,545 INFO [train.py:715] (4/8) Epoch 10, batch 7850, loss[loss=0.1406, simple_loss=0.2223, pruned_loss=0.02944, over 4944.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.03384, over 972232.84 frames.], batch size: 29, lr: 2.17e-04
2022-05-06 18:24:33,024 INFO [train.py:715] (4/8) Epoch 10, batch 7900, loss[loss=0.1735, simple_loss=0.2425, pruned_loss=0.05221, over 4964.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2148, pruned_loss=0.03423, over 972604.12 frames.], batch size: 39, lr: 2.17e-04
2022-05-06 18:25:12,544 INFO [train.py:715] (4/8) Epoch 10, batch 7950, loss[loss=0.1271, simple_loss=0.202, pruned_loss=0.02609, over 4754.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2148, pruned_loss=0.03443, over 972875.84 frames.], batch size: 19, lr: 2.17e-04
2022-05-06 18:25:51,361 INFO [train.py:715] (4/8) Epoch 10, batch 8000, loss[loss=0.1398, simple_loss=0.2086, pruned_loss=0.03556, over 4786.00 frames.], tot_loss[loss=0.1431, simple_loss=0.2157, pruned_loss=0.03528, over 973189.55 frames.], batch size: 12, lr: 2.17e-04
2022-05-06 18:26:30,785 INFO [train.py:715] (4/8) Epoch 10, batch 8050, loss[loss=0.1143, simple_loss=0.1953, pruned_loss=0.01667, over 4761.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2142, pruned_loss=0.0346, over 973498.46 frames.], batch size: 14, lr: 2.17e-04
2022-05-06 18:27:10,411 INFO [train.py:715] (4/8) Epoch 10, batch 8100, loss[loss=0.1699, simple_loss=0.2395, pruned_loss=0.05009, over 4970.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2141, pruned_loss=0.03465, over 972687.45 frames.], batch size: 24, lr: 2.17e-04
2022-05-06 18:27:49,301 INFO [train.py:715] (4/8) Epoch 10, batch 8150, loss[loss=0.1746, simple_loss=0.2327, pruned_loss=0.0582, over 4917.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2147, pruned_loss=0.03497, over 973883.61 frames.], batch size: 18, lr: 2.17e-04
2022-05-06 18:28:27,914 INFO [train.py:715] (4/8) Epoch 10, batch 8200, loss[loss=0.1282, simple_loss=0.199, pruned_loss=0.02872, over 4823.00 frames.], tot_loss[loss=0.1427, simple_loss=0.2151, pruned_loss=0.03519, over 973312.61 frames.], batch size: 12, lr: 2.17e-04
2022-05-06 18:29:07,589 INFO [train.py:715] (4/8) Epoch 10, batch 8250, loss[loss=0.1081, simple_loss=0.1746, pruned_loss=0.02085, over 4801.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2144, pruned_loss=0.0349, over 973367.47 frames.], batch size: 12, lr: 2.17e-04
2022-05-06 18:29:46,989 INFO [train.py:715] (4/8) Epoch 10, batch 8300, loss[loss=0.1182, simple_loss=0.191, pruned_loss=0.02266, over 4685.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2136, pruned_loss=0.0343, over 973309.44 frames.], batch size: 15, lr: 2.17e-04
2022-05-06 18:30:25,735 INFO [train.py:715] (4/8) Epoch 10, batch 8350, loss[loss=0.09912, simple_loss=0.1745, pruned_loss=0.01189, over 4819.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03339, over 972936.86 frames.], batch size: 25, lr: 2.17e-04
2022-05-06 18:31:05,470 INFO [train.py:715] (4/8) Epoch 10, batch 8400, loss[loss=0.1635, simple_loss=0.2396, pruned_loss=0.04367, over 4929.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03299, over 972230.65 frames.], batch size: 18, lr: 2.17e-04
2022-05-06 18:31:44,983 INFO [train.py:715] (4/8) Epoch 10, batch 8450, loss[loss=0.1284, simple_loss=0.2143, pruned_loss=0.02124, over 4815.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03368, over 972350.87 frames.], batch size: 26, lr: 2.16e-04
2022-05-06 18:32:23,259 INFO [train.py:715] (4/8) Epoch 10, batch 8500, loss[loss=0.134, simple_loss=0.2115, pruned_loss=0.02824, over 4839.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.03351, over 972449.74 frames.], batch size: 15, lr: 2.16e-04
2022-05-06 18:33:02,053 INFO [train.py:715] (4/8) Epoch 10, batch 8550, loss[loss=0.108, simple_loss=0.1774, pruned_loss=0.01929, over 4644.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2131, pruned_loss=0.03398, over 972420.67 frames.], batch size: 13, lr: 2.16e-04
2022-05-06 18:33:41,304 INFO [train.py:715] (4/8) Epoch 10, batch 8600, loss[loss=0.1327, simple_loss=0.1961, pruned_loss=0.03466, over 4976.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03366, over 971319.25 frames.], batch size: 24, lr: 2.16e-04
2022-05-06 18:34:19,985 INFO [train.py:715] (4/8) Epoch 10, batch 8650, loss[loss=0.1023, simple_loss=0.1687, pruned_loss=0.0179, over 4753.00 frames.], tot_loss[loss=0.14, simple_loss=0.2126, pruned_loss=0.03368, over 970501.56 frames.], batch size: 12, lr: 2.16e-04
2022-05-06 18:34:58,632 INFO [train.py:715] (4/8) Epoch 10, batch 8700, loss[loss=0.1337, simple_loss=0.2101, pruned_loss=0.02865, over 4989.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2122, pruned_loss=0.03345, over 971317.86 frames.], batch size: 14, lr: 2.16e-04
2022-05-06 18:35:37,458 INFO [train.py:715] (4/8) Epoch 10, batch 8750, loss[loss=0.1366, simple_loss=0.2177, pruned_loss=0.02774, over 4698.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03327, over 972049.57 frames.], batch size: 15, lr: 2.16e-04
2022-05-06 18:36:15,826 INFO [train.py:715] (4/8) Epoch 10, batch 8800, loss[loss=0.1774, simple_loss=0.2448, pruned_loss=0.05496, over 4944.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2125, pruned_loss=0.03343, over 971581.75 frames.], batch size: 39, lr: 2.16e-04
2022-05-06 18:36:54,723 INFO [train.py:715] (4/8) Epoch 10, batch 8850, loss[loss=0.1424, simple_loss=0.2219, pruned_loss=0.03143, over 4970.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03391, over 970621.03 frames.], batch size: 15, lr: 2.16e-04
2022-05-06 18:37:34,291 INFO [train.py:715] (4/8) Epoch 10, batch 8900, loss[loss=0.1679, simple_loss=0.2404, pruned_loss=0.04769, over 4743.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03433, over 970931.87 frames.], batch size: 16, lr: 2.16e-04
2022-05-06 18:38:13,805 INFO [train.py:715] (4/8) Epoch 10, batch 8950, loss[loss=0.1329, simple_loss=0.2131, pruned_loss=0.02634, over 4889.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03443, over 971539.63 frames.], batch size: 22, lr: 2.16e-04
2022-05-06 18:38:53,320 INFO [train.py:715] (4/8) Epoch 10, batch 9000, loss[loss=0.1429, simple_loss=0.2071, pruned_loss=0.03931, over 4795.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03446, over 972001.41 frames.], batch size: 21, lr: 2.16e-04
2022-05-06 18:38:53,321 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 18:39:02,857 INFO [train.py:742] (4/8) Epoch 10, validation: loss=0.1064, simple_loss=0.1907, pruned_loss=0.01106, over 914524.00 frames.
2022-05-06 18:39:42,086 INFO [train.py:715] (4/8) Epoch 10, batch 9050, loss[loss=0.125, simple_loss=0.1964, pruned_loss=0.02674, over 4966.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2143, pruned_loss=0.03411, over 973429.56 frames.], batch size: 15, lr: 2.16e-04
2022-05-06 18:40:21,150 INFO [train.py:715] (4/8) Epoch 10, batch 9100, loss[loss=0.1316, simple_loss=0.2081, pruned_loss=0.02755, over 4842.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2144, pruned_loss=0.0343, over 973646.57 frames.], batch size: 15, lr: 2.16e-04
2022-05-06 18:41:01,479 INFO [train.py:715] (4/8) Epoch 10, batch 9150, loss[loss=0.1352, simple_loss=0.2029, pruned_loss=0.03369, over 4771.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2134, pruned_loss=0.03378, over 973204.20 frames.], batch size: 18, lr: 2.16e-04
2022-05-06 18:41:40,997 INFO [train.py:715] (4/8) Epoch 10, batch 9200, loss[loss=0.1377, simple_loss=0.2142, pruned_loss=0.03064, over 4763.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03381, over 972023.66 frames.], batch size: 17, lr: 2.16e-04
2022-05-06 18:42:20,443 INFO [train.py:715] (4/8) Epoch 10, batch 9250, loss[loss=0.1527, simple_loss=0.2205, pruned_loss=0.04245, over 4881.00 frames.], tot_loss[loss=0.1407, simple_loss=0.214, pruned_loss=0.03372, over 971936.08 frames.], batch size: 20, lr: 2.16e-04
2022-05-06 18:43:00,265 INFO [train.py:715] (4/8) Epoch 10, batch 9300, loss[loss=0.1466, simple_loss=0.2092, pruned_loss=0.04196, over 4847.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2141, pruned_loss=0.03386, over 971182.75 frames.], batch size: 20, lr: 2.16e-04
2022-05-06 18:43:39,883 INFO [train.py:715] (4/8) Epoch 10, batch 9350, loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03284, over 4915.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2141, pruned_loss=0.03384, over 971077.92 frames.], batch size: 23, lr: 2.16e-04
2022-05-06 18:44:19,393 INFO [train.py:715] (4/8) Epoch 10, batch 9400, loss[loss=0.1138, simple_loss=0.1929, pruned_loss=0.01741, over 4759.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03365, over 970917.68 frames.], batch size: 19, lr: 2.16e-04
2022-05-06 18:44:58,979 INFO [train.py:715] (4/8) Epoch 10, batch 9450, loss[loss=0.1566, simple_loss=0.2215, pruned_loss=0.04587, over 4914.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2139, pruned_loss=0.03394, over 970904.28 frames.], batch size: 39, lr: 2.16e-04
2022-05-06 18:45:38,376 INFO [train.py:715] (4/8) Epoch 10, batch 9500, loss[loss=0.1279, simple_loss=0.2029, pruned_loss=0.02646, over 4979.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2135, pruned_loss=0.03371, over 971793.65 frames.], batch size: 25, lr: 2.16e-04
2022-05-06 18:46:17,353 INFO [train.py:715] (4/8) Epoch 10, batch 9550, loss[loss=0.1222, simple_loss=0.1961, pruned_loss=0.02412, over 4897.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2135, pruned_loss=0.0336, over 972153.02 frames.], batch size: 17, lr: 2.16e-04
2022-05-06 18:46:55,765 INFO [train.py:715] (4/8) Epoch 10, batch 9600, loss[loss=0.1472, simple_loss=0.2121, pruned_loss=0.04117, over 4966.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2134, pruned_loss=0.03368, over 972113.75 frames.], batch size: 28, lr: 2.16e-04
2022-05-06 18:47:34,906 INFO [train.py:715] (4/8) Epoch 10, batch 9650, loss[loss=0.1361, simple_loss=0.2125, pruned_loss=0.02982, over 4941.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2135, pruned_loss=0.03415, over 972807.86 frames.], batch size: 29, lr: 2.16e-04
2022-05-06 18:48:14,558 INFO [train.py:715] (4/8) Epoch 10, batch 9700, loss[loss=0.1471, simple_loss=0.2216, pruned_loss=0.03626, over 4754.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2129, pruned_loss=0.03399, over 972537.69 frames.], batch size: 16, lr: 2.16e-04
2022-05-06 18:48:52,976 INFO [train.py:715] (4/8) Epoch 10, batch 9750, loss[loss=0.1417, simple_loss=0.2021, pruned_loss=0.0406, over 4979.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2127, pruned_loss=0.03371, over 973385.58 frames.], batch size: 15, lr: 2.16e-04
2022-05-06 18:49:32,213 INFO [train.py:715] (4/8) Epoch 10, batch 9800, loss[loss=0.1311, simple_loss=0.2032, pruned_loss=0.02952, over 4784.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2129, pruned_loss=0.03376, over 973159.42 frames.], batch size: 14, lr: 2.16e-04
2022-05-06 18:50:11,747 INFO [train.py:715] (4/8) Epoch 10, batch 9850, loss[loss=0.177, simple_loss=0.2438, pruned_loss=0.05514, over 4920.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2128, pruned_loss=0.03382, over 973113.46 frames.], batch size: 39, lr: 2.16e-04
2022-05-06 18:50:51,053 INFO [train.py:715] (4/8) Epoch 10, batch 9900, loss[loss=0.1368, simple_loss=0.205, pruned_loss=0.03433, over 4848.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2128, pruned_loss=0.03405, over 973152.51 frames.], batch size: 30, lr: 2.16e-04
2022-05-06 18:51:30,046 INFO [train.py:715] (4/8) Epoch 10, batch 9950, loss[loss=0.124, simple_loss=0.1965, pruned_loss=0.0258, over 4899.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2131, pruned_loss=0.03399, over 972808.40 frames.], batch size: 19, lr: 2.16e-04
2022-05-06 18:52:10,246 INFO [train.py:715] (4/8) Epoch 10, batch 10000, loss[loss=0.1465, simple_loss=0.2141, pruned_loss=0.03942, over 4928.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2127, pruned_loss=0.03401, over 973137.65 frames.], batch size: 29, lr: 2.16e-04
2022-05-06 18:52:49,844 INFO [train.py:715] (4/8) Epoch 10, batch 10050, loss[loss=0.136, simple_loss=0.2077, pruned_loss=0.03216, over 4796.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2124, pruned_loss=0.03351, over 972455.44 frames.], batch size: 17, lr: 2.16e-04
2022-05-06 18:53:27,869 INFO [train.py:715] (4/8) Epoch 10, batch 10100, loss[loss=0.1324, simple_loss=0.1947, pruned_loss=0.03503, over 4924.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03339, over 972406.18 frames.], batch size: 18, lr: 2.16e-04
2022-05-06 18:54:06,606 INFO [train.py:715] (4/8) Epoch 10, batch 10150, loss[loss=0.1259, simple_loss=0.2041, pruned_loss=0.02392, over 4904.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.03268, over 971477.77 frames.], batch size: 22, lr: 2.16e-04
2022-05-06 18:54:46,537 INFO [train.py:715] (4/8) Epoch 10, batch 10200, loss[loss=0.1365, simple_loss=0.2095, pruned_loss=0.03176, over 4686.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03261, over 970983.74 frames.], batch size: 15, lr: 2.16e-04
2022-05-06 18:55:25,657 INFO [train.py:715] (4/8) Epoch 10, batch 10250, loss[loss=0.1442, simple_loss=0.2159, pruned_loss=0.03627, over 4801.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.0327, over 971128.09 frames.], batch size: 21, lr: 2.16e-04
2022-05-06 18:56:04,510 INFO [train.py:715] (4/8) Epoch 10, batch 10300, loss[loss=0.1574, simple_loss=0.2179, pruned_loss=0.04842, over 4847.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03283, over 971336.92 frames.], batch size: 32, lr: 2.16e-04
2022-05-06 18:56:44,439 INFO [train.py:715] (4/8) Epoch 10, batch 10350, loss[loss=0.132, simple_loss=0.1998, pruned_loss=0.03214, over 4784.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03328, over 970656.61 frames.], batch size: 12, lr: 2.16e-04
2022-05-06 18:57:24,438 INFO [train.py:715] (4/8) Epoch 10, batch 10400, loss[loss=0.149, simple_loss=0.2105, pruned_loss=0.04379, over 4885.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2118, pruned_loss=0.03348, over 970582.95 frames.], batch size: 32, lr: 2.16e-04
2022-05-06 18:58:02,842 INFO [train.py:715] (4/8) Epoch 10, batch 10450, loss[loss=0.1571, simple_loss=0.2286, pruned_loss=0.04283, over 4950.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2119, pruned_loss=0.03319, over 969951.34 frames.], batch size: 39, lr: 2.16e-04
2022-05-06 18:58:41,113 INFO [train.py:715] (4/8) Epoch 10, batch 10500, loss[loss=0.12, simple_loss=0.1936, pruned_loss=0.02317, over 4780.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03302, over 969862.22 frames.], batch size: 12, lr: 2.16e-04
2022-05-06 18:59:20,242 INFO [train.py:715] (4/8) Epoch 10, batch 10550, loss[loss=0.1587, simple_loss=0.2277, pruned_loss=0.04484, over 4928.00 frames.], tot_loss[loss=0.14, simple_loss=0.2131, pruned_loss=0.03349, over 970931.34 frames.], batch size: 23, lr: 2.16e-04
2022-05-06 18:59:59,203 INFO [train.py:715] (4/8) Epoch 10, batch 10600, loss[loss=0.1588, simple_loss=0.2298, pruned_loss=0.04387, over 4847.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.03395, over 972076.88 frames.], batch size: 30, lr: 2.16e-04
2022-05-06 19:00:37,418 INFO [train.py:715] (4/8) Epoch 10, batch 10650, loss[loss=0.1506, simple_loss=0.2258, pruned_loss=0.03768, over 4924.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.034, over 972419.97 frames.], batch size: 18, lr: 2.16e-04
2022-05-06 19:01:16,840 INFO [train.py:715] (4/8) Epoch 10, batch 10700, loss[loss=0.1571, simple_loss=0.2189, pruned_loss=0.04762, over 4827.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2144, pruned_loss=0.03441, over 972555.63 frames.], batch size: 13, lr: 2.16e-04
2022-05-06 19:01:56,164 INFO [train.py:715] (4/8) Epoch 10, batch 10750, loss[loss=0.14, simple_loss=0.2222, pruned_loss=0.02887, over 4794.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03401, over 973196.68 frames.], batch size: 24, lr: 2.16e-04
2022-05-06 19:02:34,992 INFO [train.py:715] (4/8) Epoch 10, batch 10800, loss[loss=0.1294, simple_loss=0.2072, pruned_loss=0.02584, over 4915.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2137, pruned_loss=0.03407, over 973583.55 frames.], batch size: 39, lr: 2.16e-04
2022-05-06 19:03:13,439 INFO [train.py:715] (4/8) Epoch 10, batch 10850, loss[loss=0.1213, simple_loss=0.2037, pruned_loss=0.01943, over 4979.00 frames.], tot_loss[loss=0.1412, simple_loss=0.214, pruned_loss=0.03425, over 973741.99 frames.], batch size: 28, lr: 2.16e-04
2022-05-06 19:03:52,880 INFO [train.py:715] (4/8) Epoch 10, batch 10900, loss[loss=0.1487, simple_loss=0.2195, pruned_loss=0.03891, over 4835.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2145, pruned_loss=0.03427, over 972861.30 frames.], batch size: 30, lr: 2.16e-04
2022-05-06 19:04:31,790 INFO [train.py:715] (4/8) Epoch 10, batch 10950, loss[loss=0.1266, simple_loss=0.201, pruned_loss=0.02611, over 4752.00 frames.], tot_loss[loss=0.141, simple_loss=0.2139, pruned_loss=0.034, over 972392.55 frames.], batch size: 16, lr: 2.16e-04
2022-05-06 19:05:10,344 INFO [train.py:715] (4/8) Epoch 10, batch 11000, loss[loss=0.1385, simple_loss=0.2133, pruned_loss=0.03187, over 4872.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2135, pruned_loss=0.03361, over 972183.98 frames.], batch size: 20, lr: 2.16e-04
2022-05-06 19:05:49,498 INFO [train.py:715] (4/8) Epoch 10, batch 11050, loss[loss=0.1234, simple_loss=0.2009, pruned_loss=0.02295, over 4889.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03357, over 971718.80 frames.], batch size: 22, lr: 2.16e-04
2022-05-06 19:06:29,280 INFO [train.py:715] (4/8) Epoch 10, batch 11100, loss[loss=0.1257, simple_loss=0.1926, pruned_loss=0.02942, over 4834.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03391, over 971791.99 frames.], batch size: 30, lr: 2.16e-04
2022-05-06 19:07:07,073 INFO [train.py:715] (4/8) Epoch 10, batch 11150, loss[loss=0.1624, simple_loss=0.2365, pruned_loss=0.04412, over 4903.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03415, over 972196.85 frames.], batch size: 19, lr: 2.16e-04
2022-05-06 19:07:46,334 INFO [train.py:715] (4/8) Epoch 10, batch 11200, loss[loss=0.1447, simple_loss=0.216, pruned_loss=0.03665, over 4837.00 frames.], tot_loss[loss=0.1414, simple_loss=0.214, pruned_loss=0.03437, over 971851.97 frames.], batch size: 13, lr: 2.16e-04
2022-05-06 19:08:25,400 INFO [train.py:715] (4/8) Epoch 10, batch 11250, loss[loss=0.1479, simple_loss=0.2245, pruned_loss=0.03569, over 4934.00 frames.], tot_loss[loss=0.141, simple_loss=0.2139, pruned_loss=0.03401, over 971566.14 frames.], batch size: 35, lr: 2.16e-04
2022-05-06 19:09:03,753 INFO [train.py:715] (4/8) Epoch 10, batch 11300, loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02985, over 4785.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2137, pruned_loss=0.03375, over 971945.62 frames.], batch size: 17, lr: 2.16e-04
2022-05-06 19:09:42,490 INFO [train.py:715] (4/8) Epoch 10, batch 11350, loss[loss=0.1403, simple_loss=0.2157, pruned_loss=0.03251, over 4966.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2138, pruned_loss=0.0338, over 972666.09 frames.], batch size: 15, lr: 2.16e-04
2022-05-06 19:10:21,472 INFO [train.py:715] (4/8) Epoch 10, batch 11400, loss[loss=0.1571, simple_loss=0.2238, pruned_loss=0.04526, over 4982.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.0336, over 972447.98 frames.], batch size: 25, lr: 2.16e-04
2022-05-06 19:11:00,938 INFO [train.py:715] (4/8) Epoch 10, batch 11450, loss[loss=0.1353, simple_loss=0.2124, pruned_loss=0.02916, over 4744.00 frames.], tot_loss[loss=0.141, simple_loss=0.2139, pruned_loss=0.03405, over 972779.65 frames.], batch size: 16, lr: 2.16e-04
2022-05-06 19:11:38,821 INFO [train.py:715] (4/8) Epoch 10, batch 11500, loss[loss=0.1223, simple_loss=0.1939, pruned_loss=0.02539, over 4938.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2135, pruned_loss=0.03373, over 972225.88 frames.], batch size: 21, lr: 2.16e-04
2022-05-06 19:12:17,874 INFO [train.py:715] (4/8) Epoch 10, batch 11550, loss[loss=0.1497, simple_loss=0.2328, pruned_loss=0.03334, over 4911.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03349, over 972764.16 frames.], batch size: 18, lr: 2.16e-04
2022-05-06 19:12:57,424 INFO [train.py:715] (4/8) Epoch 10, batch 11600, loss[loss=0.1567, simple_loss=0.222, pruned_loss=0.04568, over 4753.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2132, pruned_loss=0.03372, over 972684.86 frames.], batch size: 16, lr: 2.16e-04
2022-05-06 19:13:35,825 INFO [train.py:715] (4/8) Epoch 10, batch 11650, loss[loss=0.1356, simple_loss=0.2061, pruned_loss=0.03256, over 4890.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03431, over 971737.34 frames.], batch size: 16, lr: 2.16e-04
2022-05-06 19:14:14,880 INFO [train.py:715] (4/8) Epoch 10, batch 11700, loss[loss=0.1187, simple_loss=0.1824, pruned_loss=0.02751, over 4813.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2127, pruned_loss=0.03393, over 971495.12 frames.], batch size: 13, lr: 2.16e-04
2022-05-06 19:14:53,449 INFO [train.py:715] (4/8) Epoch 10, batch 11750, loss[loss=0.13, simple_loss=0.2067, pruned_loss=0.02662, over 4946.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2129, pruned_loss=0.03392, over 971905.41 frames.], batch size: 29, lr: 2.15e-04
2022-05-06 19:15:32,369 INFO [train.py:715] (4/8) Epoch 10, batch 11800, loss[loss=0.1258, simple_loss=0.2036, pruned_loss=0.02404, over 4936.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.0332, over 971621.59 frames.], batch size: 23, lr: 2.15e-04
2022-05-06 19:16:10,395 INFO [train.py:715] (4/8) Epoch 10, batch 11850, loss[loss=0.1467, simple_loss=0.2153, pruned_loss=0.03907, over 4986.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2116, pruned_loss=0.0333, over 971874.45 frames.], batch size: 14, lr: 2.15e-04
2022-05-06 19:16:49,165 INFO [train.py:715] (4/8) Epoch 10, batch 11900, loss[loss=0.1329, simple_loss=0.2084, pruned_loss=0.02873, over 4932.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2123, pruned_loss=0.03374, over 972013.56 frames.], batch size: 23, lr: 2.15e-04
2022-05-06 19:17:30,481 INFO [train.py:715] (4/8) Epoch 10, batch 11950, loss[loss=0.1261, simple_loss=0.2008, pruned_loss=0.02567, over 4780.00 frames.], tot_loss[loss=0.1405, simple_loss=0.213, pruned_loss=0.03396, over 971960.93 frames.], batch size: 17, lr: 2.15e-04
2022-05-06 19:18:09,365 INFO [train.py:715] (4/8) Epoch 10, batch 12000, loss[loss=0.157, simple_loss=0.2275, pruned_loss=0.0432, over 4968.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03385, over 971960.19 frames.], batch size: 28, lr: 2.15e-04
2022-05-06 19:18:09,366 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 19:18:19,015 INFO [train.py:742] (4/8) Epoch 10, validation: loss=0.1065, simple_loss=0.1908, pruned_loss=0.01105, over 914524.00 frames.
2022-05-06 19:18:57,892 INFO [train.py:715] (4/8) Epoch 10, batch 12050, loss[loss=0.1666, simple_loss=0.2404, pruned_loss=0.04641, over 4849.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2125, pruned_loss=0.03356, over 971956.68 frames.], batch size: 30, lr: 2.15e-04
2022-05-06 19:19:37,113 INFO [train.py:715] (4/8) Epoch 10, batch 12100, loss[loss=0.1366, simple_loss=0.2012, pruned_loss=0.03597, over 4767.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2127, pruned_loss=0.03383, over 971269.57 frames.], batch size: 14, lr: 2.15e-04
2022-05-06 19:20:16,372 INFO [train.py:715] (4/8) Epoch 10, batch 12150, loss[loss=0.1196, simple_loss=0.1876, pruned_loss=0.02583, over 4636.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2129, pruned_loss=0.03376, over 970466.63 frames.], batch size: 13, lr: 2.15e-04
2022-05-06 19:20:55,541 INFO [train.py:715] (4/8) Epoch 10, batch 12200, loss[loss=0.1285, simple_loss=0.2072, pruned_loss=0.02494, over 4782.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03423, over 970944.45 frames.], batch size: 18, lr: 2.15e-04
2022-05-06 19:21:34,085 INFO [train.py:715] (4/8) Epoch 10, batch 12250, loss[loss=0.1186, simple_loss=0.1956, pruned_loss=0.02082, over 4951.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2138, pruned_loss=0.03418, over 971625.20 frames.], batch size: 24, lr: 2.15e-04
2022-05-06 19:22:13,027 INFO [train.py:715] (4/8) Epoch 10, batch 12300, loss[loss=0.1218, simple_loss=0.1954, pruned_loss=0.02413, over 4775.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.0334, over 970721.84 frames.], batch size: 14, lr: 2.15e-04
2022-05-06 19:22:51,958 INFO [train.py:715] (4/8) Epoch 10, batch 12350, loss[loss=0.1125, simple_loss=0.1745, pruned_loss=0.02526, over 4850.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.03382, over 970818.05 frames.], batch size: 12, lr: 2.15e-04
2022-05-06 19:23:30,789 INFO [train.py:715] (4/8) Epoch 10, batch 12400, loss[loss=0.1344, simple_loss=0.205, pruned_loss=0.03188, over 4802.00 frames.], tot_loss[loss=0.14, simple_loss=0.2131, pruned_loss=0.03347, over 971441.51 frames.], batch size: 15, lr: 2.15e-04
2022-05-06 19:24:09,216 INFO [train.py:715] (4/8) Epoch 10, batch 12450, loss[loss=0.145, simple_loss=0.2156, pruned_loss=0.03721, over 4801.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03328, over 971260.51 frames.], batch size: 25, lr: 2.15e-04
2022-05-06 19:24:48,248 INFO [train.py:715] (4/8) Epoch 10, batch 12500, loss[loss=0.1188, simple_loss=0.1899, pruned_loss=0.02387, over 4982.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.0335, over 971804.80 frames.], batch size: 28, lr: 2.15e-04
2022-05-06 19:25:27,026 INFO [train.py:715] (4/8) Epoch 10, batch 12550, loss[loss=0.1365, simple_loss=0.2075, pruned_loss=0.03276, over 4936.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.03356, over 972971.58 frames.], batch size: 21, lr: 2.15e-04
2022-05-06 19:26:05,180 INFO [train.py:715] (4/8) Epoch 10, batch 12600, loss[loss=0.1479, simple_loss=0.2196, pruned_loss=0.03815, over 4856.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03357, over 971135.92 frames.], batch size: 20, lr: 2.15e-04
2022-05-06 19:26:43,470 INFO [train.py:715] (4/8) Epoch 10, batch 12650, loss[loss=0.12, simple_loss=0.1931, pruned_loss=0.02343, over 4750.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03435, over 971667.13 frames.], batch size: 19, lr: 2.15e-04
2022-05-06 19:27:22,407 INFO [train.py:715] (4/8) Epoch 10, batch 12700, loss[loss=0.1256, simple_loss=0.2012, pruned_loss=0.02498, over 4940.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2137, pruned_loss=0.03478, over 972520.98 frames.], batch size: 29, lr: 2.15e-04
2022-05-06 19:28:00,753 INFO [train.py:715] (4/8) Epoch 10, batch 12750, loss[loss=0.125, simple_loss=0.1962, pruned_loss=0.02694, over 4868.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2137, pruned_loss=0.03465, over 972389.00 frames.], batch size: 16, lr: 2.15e-04
2022-05-06 19:28:39,213 INFO [train.py:715] (4/8) Epoch 10, batch 12800, loss[loss=0.1399, simple_loss=0.2169, pruned_loss=0.03146, over 4795.00 frames.], tot_loss[loss=0.1406, simple_loss=0.213, pruned_loss=0.03412, over 972396.43 frames.], batch size: 17, lr: 2.15e-04
2022-05-06 19:29:18,644 INFO [train.py:715] (4/8) Epoch 10, batch 12850, loss[loss=0.1456, simple_loss=0.2133, pruned_loss=0.03893, over 4887.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2123, pruned_loss=0.03369, over 972384.34 frames.], batch size: 16, lr: 2.15e-04
2022-05-06 19:29:57,809 INFO [train.py:715] (4/8) Epoch 10, batch 12900, loss[loss=0.1381, simple_loss=0.195, pruned_loss=0.0406, over 4747.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03329, over 972766.24 frames.], batch size: 16, lr: 2.15e-04
2022-05-06 19:30:36,227 INFO [train.py:715] (4/8) Epoch 10, batch 12950, loss[loss=0.1221, simple_loss=0.1968, pruned_loss=0.02365, over 4984.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.03342, over 973106.57 frames.], batch size: 28, lr: 2.15e-04
2022-05-06 19:31:14,797 INFO [train.py:715] (4/8) Epoch 10, batch 13000, loss[loss=0.1253, simple_loss=0.1993, pruned_loss=0.02568, over 4903.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03367, over 972367.41 frames.], batch size: 19, lr: 2.15e-04
2022-05-06 19:31:54,374 INFO [train.py:715] (4/8) Epoch 10, batch 13050, loss[loss=0.1145, simple_loss=0.1933, pruned_loss=0.0179, over 4959.00 frames.], tot_loss[loss=0.14, simple_loss=0.2128, pruned_loss=0.03355, over 972635.80 frames.], batch size: 24, lr: 2.15e-04
2022-05-06 19:32:32,877 INFO [train.py:715] (4/8) Epoch 10, batch 13100, loss[loss=0.1539, simple_loss=0.2271, pruned_loss=0.04033, over 4954.00 frames.], tot_loss[loss=0.14, simple_loss=0.2125, pruned_loss=0.03369, over 972683.23 frames.], batch size: 21, lr: 2.15e-04
2022-05-06 19:33:11,983 INFO [train.py:715] (4/8) Epoch 10, batch 13150, loss[loss=0.1201, simple_loss=0.1948, pruned_loss=0.02269, over 4792.00 frames.], tot_loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.03355, over 972858.16 frames.], batch size: 24, lr: 2.15e-04
2022-05-06 19:33:51,011 INFO [train.py:715] (4/8) Epoch 10, batch 13200, loss[loss=0.1499, simple_loss=0.2295, pruned_loss=0.03511, over 4893.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2134, pruned_loss=0.03379, over 971962.47 frames.], batch size: 22, lr: 2.15e-04
2022-05-06 19:34:30,051 INFO [train.py:715] (4/8) Epoch 10, batch 13250, loss[loss=0.1278, simple_loss=0.1961, pruned_loss=0.0298, over 4953.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2137, pruned_loss=0.03375, over 971947.50 frames.], batch size: 24, lr: 2.15e-04
2022-05-06 19:35:08,699 INFO [train.py:715] (4/8) Epoch 10, batch 13300, loss[loss=0.1301, simple_loss=0.2082, pruned_loss=0.02596, over 4928.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2143, pruned_loss=0.03414, over 972504.99 frames.], batch size: 29, lr: 2.15e-04
2022-05-06 19:35:47,100 INFO [train.py:715] (4/8) Epoch 10, batch 13350, loss[loss=0.1332, simple_loss=0.2104, pruned_loss=0.028, over 4749.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2144, pruned_loss=0.03413, over 972491.10 frames.], batch size: 19, lr: 2.15e-04
2022-05-06 19:36:26,373 INFO [train.py:715] (4/8) Epoch 10, batch 13400, loss[loss=0.1428, simple_loss=0.2242, pruned_loss=0.03071, over 4915.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2135, pruned_loss=0.03371, over 972284.52 frames.], batch size: 17, lr: 2.15e-04
2022-05-06 19:37:04,722 INFO [train.py:715] (4/8) Epoch 10, batch 13450, loss[loss=0.1357, simple_loss=0.2068, pruned_loss=0.03226, over 4958.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2137, pruned_loss=0.03386, over 972184.53 frames.], batch size: 24, lr: 2.15e-04
2022-05-06 19:37:42,965 INFO [train.py:715] (4/8) Epoch 10, batch 13500, loss[loss=0.1382, simple_loss=0.2207, pruned_loss=0.02788, over 4973.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03347, over 972159.34 frames.], batch size: 14, lr: 2.15e-04
2022-05-06 19:38:22,035 INFO [train.py:715] (4/8) Epoch 10, batch 13550, loss[loss=0.1565, simple_loss=0.2214, pruned_loss=0.04575, over 4886.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2133, pruned_loss=0.03353, over 973154.30 frames.], batch size: 16, lr: 2.15e-04
2022-05-06 19:39:00,608 INFO [train.py:715] (4/8) Epoch 10, batch 13600, loss[loss=0.1372, simple_loss=0.212, pruned_loss=0.03124, over 4931.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03356, over 972651.93 frames.], batch size: 23, lr: 2.15e-04
2022-05-06 19:39:39,007 INFO [train.py:715] (4/8) Epoch 10, batch 13650, loss[loss=0.1457, simple_loss=0.2226, pruned_loss=0.03437, over 4762.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03373, over 972039.78 frames.], batch size: 19, lr: 2.15e-04
2022-05-06 19:40:17,577 INFO [train.py:715] (4/8) Epoch 10, batch 13700, loss[loss=0.1252, simple_loss=0.1975, pruned_loss=0.02651, over 4835.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2122, pruned_loss=0.03365, over 971660.59 frames.], batch size: 15, lr: 2.15e-04
2022-05-06 19:40:57,657 INFO [train.py:715] (4/8) Epoch 10, batch 13750, loss[loss=0.1587, simple_loss=0.2262, pruned_loss=0.04554, over 4811.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2123, pruned_loss=0.03359, over 971836.15 frames.], batch size: 21, lr: 2.15e-04
2022-05-06 19:41:37,004 INFO [train.py:715] (4/8) Epoch 10, batch 13800, loss[loss=0.1368, simple_loss=0.2082, pruned_loss=0.03266, over 4976.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2137, pruned_loss=0.03426, over 972453.02 frames.], batch size: 28, lr: 2.15e-04
2022-05-06 19:42:15,510 INFO [train.py:715] (4/8) Epoch 10, batch 13850, loss[loss=0.1486, simple_loss=0.2152, pruned_loss=0.041, over 4763.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03429, over 972699.63 frames.], batch size: 19, lr: 2.15e-04
2022-05-06 19:42:55,147 INFO [train.py:715] (4/8) Epoch 10, batch 13900, loss[loss=0.1401, simple_loss=0.2162, pruned_loss=0.032, over 4814.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03406, over 972107.16 frames.], batch size: 21, lr: 2.15e-04
2022-05-06 19:43:33,822 INFO [train.py:715] (4/8) Epoch 10, batch 13950, loss[loss=0.1411, simple_loss=0.205, pruned_loss=0.03862, over 4787.00 frames.], tot_loss[loss=0.141, simple_loss=0.2137, pruned_loss=0.03417, over 971916.80 frames.], batch size: 14, lr: 2.15e-04
2022-05-06 19:44:12,829 INFO [train.py:715] (4/8) Epoch 10, batch 14000, loss[loss=0.1395, simple_loss=0.2216, pruned_loss=0.02868, over 4935.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.03359, over 972436.30 frames.], batch size: 39, lr: 2.15e-04
2022-05-06 19:44:51,235 INFO [train.py:715] (4/8) Epoch 10, batch 14050, loss[loss=0.1261, simple_loss=0.2065, pruned_loss=0.02289, over 4786.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03332, over 972536.15 frames.], batch size: 12, lr: 2.15e-04
2022-05-06 19:45:30,764 INFO [train.py:715] (4/8) Epoch 10, batch 14100, loss[loss=0.1472, simple_loss=0.2103, pruned_loss=0.04202, over 4801.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03393, over 972116.91 frames.], batch size: 25, lr: 2.15e-04
2022-05-06 19:46:09,126 INFO [train.py:715] (4/8) Epoch 10, batch 14150, loss[loss=0.1396, simple_loss=0.2124, pruned_loss=0.03338, over 4966.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2145, pruned_loss=0.03431, over 971808.62 frames.], batch size: 21, lr: 2.15e-04
2022-05-06 19:46:47,033 INFO [train.py:715] (4/8) Epoch 10, batch 14200, loss[loss=0.1512, simple_loss=0.2123, pruned_loss=0.0451, over 4975.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2145, pruned_loss=0.03417, over 971792.92 frames.], batch size: 35, lr: 2.15e-04
2022-05-06 19:47:26,634 INFO [train.py:715] (4/8) Epoch 10, batch 14250, loss[loss=0.1118, simple_loss=0.1916, pruned_loss=0.01602, over 4985.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2132, pruned_loss=0.03367, over 972368.84 frames.], batch size: 35, lr: 2.15e-04
2022-05-06 19:48:05,008 INFO [train.py:715] (4/8) Epoch 10, batch 14300, loss[loss=0.1293, simple_loss=0.2058, pruned_loss=0.0264, over 4834.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03353, over 972299.85 frames.], batch size: 20, lr: 2.15e-04
2022-05-06 19:48:43,127 INFO [train.py:715] (4/8) Epoch 10, batch 14350, loss[loss=0.1258, simple_loss=0.2021, pruned_loss=0.02478, over 4817.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.03347, over 972580.76 frames.], batch size: 25, lr: 2.15e-04
2022-05-06 19:49:21,566 INFO [train.py:715] (4/8) Epoch 10, batch 14400, loss[loss=0.1219, simple_loss=0.1981, pruned_loss=0.02279, over 4808.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.034, over 971944.78 frames.], batch size: 24, lr: 2.15e-04
2022-05-06 19:50:01,194 INFO [train.py:715] (4/8) Epoch 10, batch 14450, loss[loss=0.1541, simple_loss=0.2263, pruned_loss=0.04092, over 4749.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2127, pruned_loss=0.03398, over 971559.90 frames.], batch size: 19, lr: 2.15e-04
2022-05-06 19:50:39,561 INFO [train.py:715] (4/8) Epoch 10, batch 14500, loss[loss=0.1764, simple_loss=0.2389, pruned_loss=0.05691, over 4885.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2132, pruned_loss=0.03404, over 972226.64 frames.], batch size: 16, lr: 2.15e-04
2022-05-06 19:51:17,696 INFO [train.py:715] (4/8) Epoch 10, batch 14550, loss[loss=0.1128, simple_loss=0.1833, pruned_loss=0.02116, over 4903.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03339, over 972413.82 frames.], batch size: 22, lr: 2.15e-04
2022-05-06 19:51:57,346 INFO [train.py:715] (4/8) Epoch 10, batch 14600, loss[loss=0.1152, simple_loss=0.1809, pruned_loss=0.02475, over 4778.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2119, pruned_loss=0.03335, over 972914.27 frames.], batch size: 14, lr: 2.15e-04
2022-05-06 19:52:35,981 INFO [train.py:715] (4/8) Epoch 10, batch 14650, loss[loss=0.1271, simple_loss=0.2034, pruned_loss=0.02544, over 4792.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03334, over 973228.56 frames.], batch size: 21, lr: 2.15e-04
2022-05-06 19:53:14,371 INFO [train.py:715] (4/8) Epoch 10, batch 14700, loss[loss=0.1629, simple_loss=0.2324, pruned_loss=0.04668, over 4748.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2115, pruned_loss=0.03291, over 972675.78 frames.], batch size: 16, lr: 2.15e-04
2022-05-06 19:53:53,325 INFO [train.py:715] (4/8) Epoch 10, batch 14750, loss[loss=0.1327, simple_loss=0.2153, pruned_loss=0.02506, over 4803.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03266, over 972891.67 frames.], batch size: 24, lr: 2.15e-04
2022-05-06 19:54:33,138 INFO [train.py:715] (4/8) Epoch 10, batch 14800, loss[loss=0.1352, simple_loss=0.1962, pruned_loss=0.03709, over 4993.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03241, over 972981.64 frames.], batch size: 16, lr: 2.15e-04
2022-05-06 19:55:12,160 INFO [train.py:715] (4/8) Epoch 10, batch 14850, loss[loss=0.1261, simple_loss=0.1961, pruned_loss=0.02802, over 4880.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03261, over 972771.07 frames.], batch size: 16, lr: 2.15e-04
2022-05-06 19:55:50,176 INFO [train.py:715] (4/8) Epoch 10, batch 14900, loss[loss=0.1451, simple_loss=0.2143, pruned_loss=0.03799, over 4882.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03289, over 972504.95 frames.], batch size: 39, lr: 2.15e-04
2022-05-06 19:56:30,294 INFO [train.py:715] (4/8) Epoch 10, batch 14950, loss[loss=0.1553, simple_loss=0.2268, pruned_loss=0.04195, over 4836.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03282, over 973171.69 frames.], batch size: 15, lr: 2.15e-04
2022-05-06 19:57:09,817 INFO [train.py:715] (4/8) Epoch 10, batch 15000, loss[loss=0.2398, simple_loss=0.321, pruned_loss=0.07932, over 4936.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03265, over 973587.02 frames.], batch size: 23, lr: 2.15e-04
2022-05-06 19:57:09,817 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 19:57:19,460 INFO [train.py:742] (4/8) Epoch 10, validation: loss=0.1065, simple_loss=0.1909, pruned_loss=0.01111, over 914524.00 frames.
2022-05-06 19:57:59,083 INFO [train.py:715] (4/8) Epoch 10, batch 15050, loss[loss=0.1381, simple_loss=0.2174, pruned_loss=0.02944, over 4811.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2126, pruned_loss=0.03282, over 974000.04 frames.], batch size: 27, lr: 2.15e-04
2022-05-06 19:58:38,147 INFO [train.py:715] (4/8) Epoch 10, batch 15100, loss[loss=0.1281, simple_loss=0.1976, pruned_loss=0.02931, over 4800.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.03274, over 973306.34 frames.], batch size: 25, lr: 2.15e-04
2022-05-06 19:59:17,365 INFO [train.py:715] (4/8) Epoch 10, batch 15150, loss[loss=0.1479, simple_loss=0.2127, pruned_loss=0.04152, over 4872.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2121, pruned_loss=0.03245, over 973796.99 frames.], batch size: 16, lr: 2.14e-04
2022-05-06 19:59:56,361 INFO [train.py:715] (4/8) Epoch 10, batch 15200, loss[loss=0.142, simple_loss=0.2197, pruned_loss=0.03212, over 4919.00 frames.], tot_loss[loss=0.139, simple_loss=0.2124, pruned_loss=0.03284, over 974283.89 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:00:35,741 INFO [train.py:715] (4/8) Epoch 10, batch 15250, loss[loss=0.1127, simple_loss=0.1802, pruned_loss=0.02257, over 4985.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03302, over 974446.69 frames.], batch size: 31, lr: 2.14e-04
2022-05-06 20:01:14,786 INFO [train.py:715] (4/8) Epoch 10, batch 15300, loss[loss=0.1296, simple_loss=0.2158, pruned_loss=0.02166, over 4817.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2135, pruned_loss=0.03394, over 974117.32 frames.], batch size: 26, lr: 2.14e-04
2022-05-06 20:01:54,058 INFO [train.py:715] (4/8) Epoch 10, batch 15350, loss[loss=0.1461, simple_loss=0.2174, pruned_loss=0.03742, over 4951.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2148, pruned_loss=0.0342, over 974503.94 frames.], batch size: 21, lr: 2.14e-04
2022-05-06 20:02:34,139 INFO [train.py:715] (4/8) Epoch 10, batch 15400, loss[loss=0.1271, simple_loss=0.1981, pruned_loss=0.02811, over 4796.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.03412, over 973203.62 frames.], batch size: 14, lr: 2.14e-04
2022-05-06 20:03:13,409 INFO [train.py:715] (4/8) Epoch 10, batch 15450, loss[loss=0.1465, simple_loss=0.2088, pruned_loss=0.04206, over 4812.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2138, pruned_loss=0.03426, over 973754.54 frames.], batch size: 21, lr: 2.14e-04
2022-05-06 20:03:53,465 INFO [train.py:715] (4/8) Epoch 10, batch 15500, loss[loss=0.1409, simple_loss=0.2127, pruned_loss=0.0346, over 4887.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.03402, over 973917.83 frames.], batch size: 22, lr: 2.14e-04
2022-05-06 20:04:32,471 INFO [train.py:715] (4/8) Epoch 10, batch 15550, loss[loss=0.1174, simple_loss=0.1759, pruned_loss=0.02944, over 4816.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03338, over 973229.09 frames.], batch size: 12, lr: 2.14e-04
2022-05-06 20:05:11,887 INFO [train.py:715] (4/8) Epoch 10, batch 15600, loss[loss=0.1362, simple_loss=0.2048, pruned_loss=0.0338, over 4797.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2119, pruned_loss=0.03294, over 972743.62 frames.], batch size: 24, lr: 2.14e-04
2022-05-06 20:05:50,244 INFO [train.py:715] (4/8) Epoch 10, batch 15650, loss[loss=0.1354, simple_loss=0.2138, pruned_loss=0.0285, over 4748.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03272, over 972996.27 frames.], batch size: 16, lr: 2.14e-04
2022-05-06 20:06:28,932 INFO [train.py:715] (4/8) Epoch 10, batch 15700, loss[loss=0.1334, simple_loss=0.1975, pruned_loss=0.03467, over 4787.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.03271, over 972479.88 frames.], batch size: 14, lr: 2.14e-04
2022-05-06 20:07:08,405 INFO [train.py:715] (4/8) Epoch 10, batch 15750, loss[loss=0.1608, simple_loss=0.2383, pruned_loss=0.04164, over 4912.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2118, pruned_loss=0.03297, over 972753.35 frames.], batch size: 17, lr: 2.14e-04
2022-05-06 20:07:46,971 INFO [train.py:715] (4/8) Epoch 10, batch 15800, loss[loss=0.1188, simple_loss=0.1941, pruned_loss=0.0218, over 4930.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2115, pruned_loss=0.03284, over 972364.86 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:08:26,773 INFO [train.py:715] (4/8) Epoch 10, batch 15850, loss[loss=0.1248, simple_loss=0.1919, pruned_loss=0.02884, over 4811.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2113, pruned_loss=0.03298, over 972851.13 frames.], batch size: 13, lr: 2.14e-04
2022-05-06 20:09:05,639 INFO [train.py:715] (4/8) Epoch 10, batch 15900, loss[loss=0.1375, simple_loss=0.2088, pruned_loss=0.03309, over 4916.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2109, pruned_loss=0.03283, over 973149.95 frames.], batch size: 23, lr: 2.14e-04
2022-05-06 20:09:44,835 INFO [train.py:715] (4/8) Epoch 10, batch 15950, loss[loss=0.1433, simple_loss=0.2134, pruned_loss=0.0366, over 4883.00 frames.], tot_loss[loss=0.139, simple_loss=0.2117, pruned_loss=0.03311, over 973184.70 frames.], batch size: 16, lr: 2.14e-04
2022-05-06 20:10:23,752 INFO [train.py:715] (4/8) Epoch 10, batch 16000, loss[loss=0.1267, simple_loss=0.1967, pruned_loss=0.02834, over 4792.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2116, pruned_loss=0.0331, over 972558.59 frames.], batch size: 17, lr: 2.14e-04
2022-05-06 20:11:02,643 INFO [train.py:715] (4/8) Epoch 10, batch 16050, loss[loss=0.1203, simple_loss=0.1925, pruned_loss=0.02404, over 4908.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03311, over 972402.99 frames.], batch size: 23, lr: 2.14e-04
2022-05-06 20:11:41,915 INFO [train.py:715] (4/8) Epoch 10, batch 16100, loss[loss=0.1385, simple_loss=0.2131, pruned_loss=0.03199, over 4948.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03342, over 972499.07 frames.], batch size: 21, lr: 2.14e-04
2022-05-06 20:12:21,125 INFO [train.py:715] (4/8) Epoch 10, batch 16150, loss[loss=0.1322, simple_loss=0.2084, pruned_loss=0.02802, over 4921.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2127, pruned_loss=0.03313, over 971958.25 frames.], batch size: 23, lr: 2.14e-04
2022-05-06 20:13:01,095 INFO [train.py:715] (4/8) Epoch 10, batch 16200, loss[loss=0.1321, simple_loss=0.2055, pruned_loss=0.02928, over 4836.00 frames.], tot_loss[loss=0.1396, simple_loss=0.213, pruned_loss=0.0331, over 972478.99 frames.], batch size: 13, lr: 2.14e-04
2022-05-06 20:13:40,632 INFO [train.py:715] (4/8) Epoch 10, batch 16250, loss[loss=0.1184, simple_loss=0.1928, pruned_loss=0.02195, over 4910.00 frames.], tot_loss[loss=0.139, simple_loss=0.2123, pruned_loss=0.03287, over 972054.12 frames.], batch size: 29, lr: 2.14e-04
2022-05-06 20:14:19,846 INFO [train.py:715] (4/8) Epoch 10, batch 16300, loss[loss=0.1372, simple_loss=0.204, pruned_loss=0.03518, over 4900.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03321, over 972670.15 frames.], batch size: 29, lr: 2.14e-04
2022-05-06 20:14:59,848 INFO [train.py:715] (4/8) Epoch 10, batch 16350, loss[loss=0.1336, simple_loss=0.2063, pruned_loss=0.0305, over 4838.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.03312, over 971732.73 frames.], batch size: 26, lr: 2.14e-04
2022-05-06 20:15:39,243 INFO [train.py:715] (4/8) Epoch 10, batch 16400, loss[loss=0.1531, simple_loss=0.2297, pruned_loss=0.03828, over 4887.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03322, over 972235.80 frames.], batch size: 22, lr: 2.14e-04
2022-05-06 20:16:18,979 INFO [train.py:715] (4/8) Epoch 10, batch 16450, loss[loss=0.1422, simple_loss=0.2187, pruned_loss=0.0328, over 4758.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2124, pruned_loss=0.03345, over 972484.60 frames.], batch size: 16, lr: 2.14e-04
2022-05-06 20:16:57,468 INFO [train.py:715] (4/8) Epoch 10, batch 16500, loss[loss=0.1333, simple_loss=0.2045, pruned_loss=0.03101, over 4938.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2129, pruned_loss=0.03373, over 971438.41 frames.], batch size: 29, lr: 2.14e-04
2022-05-06 20:17:36,174 INFO [train.py:715] (4/8) Epoch 10, batch 16550, loss[loss=0.1361, simple_loss=0.2122, pruned_loss=0.03, over 4942.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2123, pruned_loss=0.03323, over 971169.49 frames.], batch size: 29, lr: 2.14e-04
2022-05-06 20:18:15,833 INFO [train.py:715] (4/8) Epoch 10, batch 16600, loss[loss=0.1322, simple_loss=0.2107, pruned_loss=0.02683, over 4802.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2118, pruned_loss=0.03336, over 970484.88 frames.], batch size: 25, lr: 2.14e-04
2022-05-06 20:18:54,010 INFO [train.py:715] (4/8) Epoch 10, batch 16650, loss[loss=0.1565, simple_loss=0.2251, pruned_loss=0.04396, over 4905.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2112, pruned_loss=0.03352, over 970200.42 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:19:33,369 INFO [train.py:715] (4/8) Epoch 10, batch 16700, loss[loss=0.1525, simple_loss=0.2307, pruned_loss=0.03717, over 4922.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2124, pruned_loss=0.03342, over 970152.91 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:20:12,353 INFO [train.py:715] (4/8) Epoch 10, batch 16750, loss[loss=0.1448, simple_loss=0.2143, pruned_loss=0.03765, over 4869.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2114, pruned_loss=0.03303, over 970364.84 frames.], batch size: 20, lr: 2.14e-04
2022-05-06 20:20:52,509 INFO [train.py:715] (4/8) Epoch 10, batch 16800, loss[loss=0.1472, simple_loss=0.224, pruned_loss=0.03518, over 4874.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03314, over 970695.96 frames.], batch size: 16, lr: 2.14e-04
2022-05-06 20:21:31,829 INFO [train.py:715] (4/8) Epoch 10, batch 16850, loss[loss=0.1385, simple_loss=0.2212, pruned_loss=0.02791, over 4758.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.03352, over 971951.17 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:22:11,632 INFO [train.py:715] (4/8) Epoch 10, batch 16900, loss[loss=0.1351, simple_loss=0.2022, pruned_loss=0.034, over 4795.00 frames.], tot_loss[loss=0.1398, simple_loss=0.213, pruned_loss=0.03325, over 971996.64 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:22:51,672 INFO [train.py:715] (4/8) Epoch 10, batch 16950, loss[loss=0.1781, simple_loss=0.2664, pruned_loss=0.04485, over 4963.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2138, pruned_loss=0.03356, over 972730.35 frames.], batch size: 24, lr: 2.14e-04
2022-05-06 20:23:29,922 INFO [train.py:715] (4/8) Epoch 10, batch 17000, loss[loss=0.1551, simple_loss=0.2296, pruned_loss=0.04028, over 4787.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.03346, over 972513.23 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:24:09,514 INFO [train.py:715] (4/8) Epoch 10, batch 17050, loss[loss=0.1382, simple_loss=0.2142, pruned_loss=0.03106, over 4925.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03381, over 972816.48 frames.], batch size: 29, lr: 2.14e-04
2022-05-06 20:24:48,212 INFO [train.py:715] (4/8) Epoch 10, batch 17100, loss[loss=0.1207, simple_loss=0.1894, pruned_loss=0.02599, over 4847.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03335, over 972120.80 frames.], batch size: 32, lr: 2.14e-04
2022-05-06 20:25:27,434 INFO [train.py:715] (4/8) Epoch 10, batch 17150, loss[loss=0.1323, simple_loss=0.2037, pruned_loss=0.03041, over 4884.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.0329, over 972528.91 frames.], batch size: 32, lr: 2.14e-04
2022-05-06 20:26:07,416 INFO [train.py:715] (4/8) Epoch 10, batch 17200, loss[loss=0.1493, simple_loss=0.209, pruned_loss=0.04482, over 4897.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.03346, over 972982.41 frames.], batch size: 19, lr: 2.14e-04
2022-05-06 20:26:47,026 INFO [train.py:715] (4/8) Epoch 10, batch 17250, loss[loss=0.1235, simple_loss=0.1877, pruned_loss=0.02964, over 4814.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03363, over 971686.35 frames.], batch size: 12, lr: 2.14e-04
2022-05-06 20:27:26,663 INFO [train.py:715] (4/8) Epoch 10, batch 17300, loss[loss=0.1696, simple_loss=0.2284, pruned_loss=0.05538, over 4766.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2125, pruned_loss=0.0335, over 971708.23 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:28:05,423 INFO [train.py:715] (4/8) Epoch 10, batch 17350, loss[loss=0.1419, simple_loss=0.213, pruned_loss=0.0354, over 4854.00 frames.], tot_loss[loss=0.1413, simple_loss=0.214, pruned_loss=0.03433, over 971121.60 frames.], batch size: 30, lr: 2.14e-04
2022-05-06 20:28:44,830 INFO [train.py:715] (4/8) Epoch 10, batch 17400, loss[loss=0.1353, simple_loss=0.2079, pruned_loss=0.03138, over 4927.00 frames.], tot_loss[loss=0.141, simple_loss=0.2135, pruned_loss=0.03422, over 971871.46 frames.], batch size: 21, lr: 2.14e-04
2022-05-06 20:29:24,007 INFO [train.py:715] (4/8) Epoch 10, batch 17450, loss[loss=0.1109, simple_loss=0.1826, pruned_loss=0.01956, over 4773.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2118, pruned_loss=0.03346, over 972001.44 frames.], batch size: 12, lr: 2.14e-04
2022-05-06 20:30:02,982 INFO [train.py:715] (4/8) Epoch 10, batch 17500, loss[loss=0.1199, simple_loss=0.2012, pruned_loss=0.01932, over 4853.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03329, over 971990.06 frames.], batch size: 13, lr: 2.14e-04
2022-05-06 20:30:42,973 INFO [train.py:715] (4/8) Epoch 10, batch 17550, loss[loss=0.1372, simple_loss=0.2199, pruned_loss=0.02726, over 4798.00 frames.], tot_loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.03356, over 971981.53 frames.], batch size: 21, lr: 2.14e-04
2022-05-06 20:31:21,945 INFO [train.py:715] (4/8) Epoch 10, batch 17600, loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03143, over 4817.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.03347, over 971670.01 frames.], batch size: 15, lr: 2.14e-04
2022-05-06 20:32:01,507 INFO [train.py:715] (4/8) Epoch 10, batch 17650, loss[loss=0.1368, simple_loss=0.2118, pruned_loss=0.03086, over 4860.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03326, over 971911.54 frames.], batch size: 16, lr: 2.14e-04
2022-05-06 20:32:40,268 INFO [train.py:715] (4/8) Epoch 10, batch 17700, loss[loss=0.1273, simple_loss=0.1983, pruned_loss=0.02816, over 4989.00 frames.], tot_loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.03369, over 972473.73 frames.], batch size: 25, lr: 2.14e-04
2022-05-06 20:33:20,043 INFO [train.py:715] (4/8) Epoch 10, batch 17750, loss[loss=0.1554, simple_loss=0.2452, pruned_loss=0.03279, over 4776.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03365, over 972231.34 frames.], batch size: 17, lr: 2.14e-04
2022-05-06 20:33:59,768 INFO [train.py:715] (4/8) Epoch 10, batch 17800, loss[loss=0.1785, simple_loss=0.2544, pruned_loss=0.05125, over 4829.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2138, pruned_loss=0.03397, over 972424.78 frames.], batch size: 15, lr: 2.14e-04
2022-05-06 20:34:38,714 INFO [train.py:715] (4/8) Epoch 10, batch 17850, loss[loss=0.1216, simple_loss=0.2022, pruned_loss=0.02051, over 4807.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2134, pruned_loss=0.03382, over 972903.86 frames.], batch size: 26, lr: 2.14e-04
2022-05-06 20:35:18,468 INFO [train.py:715] (4/8) Epoch 10, batch 17900, loss[loss=0.1374, simple_loss=0.2087, pruned_loss=0.03303, over 4901.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2138, pruned_loss=0.03392, over 973258.78 frames.], batch size: 19, lr: 2.14e-04
2022-05-06 20:35:57,402 INFO [train.py:715] (4/8) Epoch 10, batch 17950, loss[loss=0.1389, simple_loss=0.2112, pruned_loss=0.03329, over 4920.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2138, pruned_loss=0.03392, over 973533.82 frames.], batch size: 18, lr: 2.14e-04
2022-05-06 20:36:36,020 INFO [train.py:715] (4/8) Epoch 10, batch 18000, loss[loss=0.1364, simple_loss=0.2096, pruned_loss=0.03163, over 4692.00 frames.], tot_loss[loss=0.141, simple_loss=0.214, pruned_loss=0.03396, over 972864.83 frames.], batch size: 15, lr: 2.14e-04
2022-05-06 20:36:36,021 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 20:36:45,528 INFO [train.py:742] (4/8) Epoch 10, validation: loss=0.1064, simple_loss=0.1906, pruned_loss=0.01104, over 914524.00 frames.
2022-05-06 20:37:24,884 INFO [train.py:715] (4/8) Epoch 10, batch 18050, loss[loss=0.1153, simple_loss=0.1848, pruned_loss=0.02289, over 4636.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2132, pruned_loss=0.03373, over 972854.45 frames.], batch size: 13, lr: 2.14e-04
2022-05-06 20:38:03,991 INFO [train.py:715] (4/8) Epoch 10, batch 18100, loss[loss=0.1118, simple_loss=0.1927, pruned_loss=0.01542, over 4948.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.03366, over 972855.65 frames.], batch size: 21, lr: 2.14e-04
2022-05-06 20:38:43,263 INFO [train.py:715] (4/8) Epoch 10, batch 18150, loss[loss=0.1295, simple_loss=0.2054, pruned_loss=0.02679, over 4832.00 frames.], tot_loss[loss=0.1403, simple_loss=0.213, pruned_loss=0.0338, over 971917.56 frames.], batch size: 26, lr: 2.14e-04
2022-05-06 20:39:21,946 INFO [train.py:715] (4/8) Epoch 10, batch 18200, loss[loss=0.1284, simple_loss=0.1979, pruned_loss=0.02948, over 4724.00 frames.], tot_loss[loss=0.1407, simple_loss=0.213, pruned_loss=0.03417, over 971610.10 frames.], batch size: 15, lr: 2.14e-04
2022-05-06 20:40:00,620 INFO [train.py:715] (4/8) Epoch 10, batch 18250, loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02916, over 4805.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2126, pruned_loss=0.03414, over 971788.65 frames.], batch size: 24, lr: 2.14e-04
2022-05-06 20:40:40,107 INFO [train.py:715] (4/8) Epoch 10, batch 18300, loss[loss=0.157, simple_loss=0.2326, pruned_loss=0.04067, over 4858.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2127, pruned_loss=0.03417, over 970880.23 frames.], batch size: 20, lr: 2.14e-04
2022-05-06 20:41:19,472 INFO [train.py:715] (4/8) Epoch 10, batch 18350, loss[loss=0.117, simple_loss=0.1922, pruned_loss=0.02093, over 4972.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2126, pruned_loss=0.03408, over 971393.74 frames.], batch size: 14, lr: 2.14e-04
2022-05-06 20:41:57,962 INFO [train.py:715] (4/8) Epoch 10, batch 18400, loss[loss=0.1206, simple_loss=0.2058, pruned_loss=0.01772, over 4847.00 frames.], tot_loss[loss=0.1421, simple_loss=0.2143, pruned_loss=0.03491, over 972269.76 frames.], batch size: 20, lr: 2.14e-04
2022-05-06 20:42:37,148 INFO [train.py:715] (4/8) Epoch 10, batch 18450, loss[loss=0.1309, simple_loss=0.1938, pruned_loss=0.03401, over 4848.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.03398, over 972258.45 frames.], batch size: 32, lr: 2.14e-04
2022-05-06 20:43:16,003 INFO [train.py:715] (4/8) Epoch 10, batch 18500, loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03551, over 4922.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2134, pruned_loss=0.03386, over 972517.19 frames.], batch size: 29, lr: 2.14e-04
2022-05-06 20:43:55,527 INFO [train.py:715] (4/8) Epoch 10, batch 18550, loss[loss=0.1241, simple_loss=0.2026, pruned_loss=0.02285, over 4749.00 frames.], tot_loss[loss=0.1407, simple_loss=0.214, pruned_loss=0.03372, over 972010.22 frames.], batch size: 16, lr: 2.13e-04
2022-05-06 20:44:33,845 INFO [train.py:715] (4/8) Epoch 10, batch 18600, loss[loss=0.1175, simple_loss=0.1961, pruned_loss=0.01949, over 4831.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03391, over 972818.74 frames.], batch size: 26, lr: 2.13e-04
2022-05-06 20:45:13,254 INFO [train.py:715] (4/8) Epoch 10, batch 18650, loss[loss=0.127, simple_loss=0.2089, pruned_loss=0.02256, over 4926.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03332, over 972014.55 frames.], batch size: 29, lr: 2.13e-04
2022-05-06 20:45:52,991 INFO [train.py:715] (4/8) Epoch 10, batch 18700, loss[loss=0.1648, simple_loss=0.2486, pruned_loss=0.04047, over 4828.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2135, pruned_loss=0.03355, over 971984.07 frames.], batch size: 26, lr: 2.13e-04
2022-05-06 20:46:31,253 INFO [train.py:715] (4/8) Epoch 10, batch 18750, loss[loss=0.1167, simple_loss=0.1865, pruned_loss=0.02344, over 4813.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2134, pruned_loss=0.03379, over 972131.38 frames.], batch size: 13, lr: 2.13e-04
2022-05-06 20:47:10,632 INFO [train.py:715] (4/8) Epoch 10, batch 18800, loss[loss=0.1752, simple_loss=0.2499, pruned_loss=0.05023, over 4968.00 frames.], tot_loss[loss=0.141, simple_loss=0.2145, pruned_loss=0.03381, over 972510.56 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 20:47:50,112 INFO [train.py:715] (4/8) Epoch 10, batch 18850, loss[loss=0.1577, simple_loss=0.2348, pruned_loss=0.04032, over 4799.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2144, pruned_loss=0.03389, over 973185.12 frames.], batch size: 24, lr: 2.13e-04
2022-05-06 20:48:29,009 INFO [train.py:715] (4/8) Epoch 10, batch 18900, loss[loss=0.1324, simple_loss=0.2009, pruned_loss=0.03194, over 4755.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2143, pruned_loss=0.03438, over 973295.41 frames.], batch size: 16, lr: 2.13e-04
2022-05-06 20:49:08,079 INFO [train.py:715] (4/8) Epoch 10, batch 18950, loss[loss=0.1649, simple_loss=0.2326, pruned_loss=0.04854, over 4981.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2149, pruned_loss=0.03485, over 973486.53 frames.], batch size: 35, lr: 2.13e-04
2022-05-06 20:49:48,334 INFO [train.py:715] (4/8) Epoch 10, batch 19000, loss[loss=0.1449, simple_loss=0.2229, pruned_loss=0.03344, over 4776.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2142, pruned_loss=0.03452, over 973781.66 frames.], batch size: 17, lr: 2.13e-04
2022-05-06 20:50:27,641 INFO [train.py:715] (4/8) Epoch 10, batch 19050, loss[loss=0.1325, simple_loss=0.1932, pruned_loss=0.03594, over 4917.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2138, pruned_loss=0.03406, over 974137.37 frames.], batch size: 23, lr: 2.13e-04
2022-05-06 20:51:06,452 INFO [train.py:715] (4/8) Epoch 10, batch 19100, loss[loss=0.16, simple_loss=0.2459, pruned_loss=0.03709, over 4870.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03341, over 972438.84 frames.], batch size: 22, lr: 2.13e-04
2022-05-06 20:51:46,324 INFO [train.py:715] (4/8) Epoch 10, batch 19150, loss[loss=0.1292, simple_loss=0.2003, pruned_loss=0.02899, over 4919.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.03305, over 972988.13 frames.], batch size: 18, lr: 2.13e-04
2022-05-06 20:52:26,498 INFO [train.py:715] (4/8) Epoch 10, batch 19200, loss[loss=0.1421, simple_loss=0.2148, pruned_loss=0.03473, over 4768.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03271, over 972834.10 frames.], batch size: 16, lr: 2.13e-04
2022-05-06 20:53:06,171 INFO [train.py:715] (4/8) Epoch 10, batch 19250, loss[loss=0.1339, simple_loss=0.2171, pruned_loss=0.02534, over 4814.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03205, over 971895.26 frames.], batch size: 27, lr: 2.13e-04
2022-05-06 20:53:46,067 INFO [train.py:715] (4/8) Epoch 10, batch 19300, loss[loss=0.1069, simple_loss=0.1816, pruned_loss=0.0161, over 4687.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2113, pruned_loss=0.03189, over 971491.64 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 20:54:26,473 INFO [train.py:715] (4/8) Epoch 10, batch 19350, loss[loss=0.1496, simple_loss=0.2226, pruned_loss=0.0383, over 4774.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03204, over 970817.53 frames.], batch size: 18, lr: 2.13e-04
2022-05-06 20:55:06,649 INFO [train.py:715] (4/8) Epoch 10, batch 19400, loss[loss=0.1295, simple_loss=0.2108, pruned_loss=0.02408, over 4798.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2115, pruned_loss=0.03206, over 970965.73 frames.], batch size: 21, lr: 2.13e-04
2022-05-06 20:55:45,795 INFO [train.py:715] (4/8) Epoch 10, batch 19450, loss[loss=0.1862, simple_loss=0.254, pruned_loss=0.05923, over 4814.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.0327, over 971730.94 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 20:56:25,407 INFO [train.py:715] (4/8) Epoch 10, batch 19500, loss[loss=0.1245, simple_loss=0.1987, pruned_loss=0.02513, over 4820.00 frames.], tot_loss[loss=0.139, simple_loss=0.2122, pruned_loss=0.03292, over 971419.07 frames.], batch size: 26, lr: 2.13e-04
2022-05-06 20:57:04,607 INFO [train.py:715] (4/8) Epoch 10, batch 19550, loss[loss=0.1387, simple_loss=0.2093, pruned_loss=0.03406, over 4910.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03357, over 971551.58 frames.], batch size: 19, lr: 2.13e-04
2022-05-06 20:57:43,330 INFO [train.py:715] (4/8) Epoch 10, batch 19600, loss[loss=0.1319, simple_loss=0.1973, pruned_loss=0.03318, over 4977.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03303, over 972158.37 frames.], batch size: 14, lr: 2.13e-04
2022-05-06 20:58:22,307 INFO [train.py:715] (4/8) Epoch 10, batch 19650, loss[loss=0.1417, simple_loss=0.2142, pruned_loss=0.03459, over 4794.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2122, pruned_loss=0.03262, over 972020.00 frames.], batch size: 24, lr: 2.13e-04
2022-05-06 20:59:01,942 INFO [train.py:715] (4/8) Epoch 10, batch 19700, loss[loss=0.1402, simple_loss=0.2318, pruned_loss=0.0243, over 4867.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2118, pruned_loss=0.03229, over 972111.79 frames.], batch size: 20, lr: 2.13e-04
2022-05-06 20:59:41,296 INFO [train.py:715] (4/8) Epoch 10, batch 19750, loss[loss=0.1322, simple_loss=0.2051, pruned_loss=0.02964, over 4886.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03237, over 971632.41 frames.], batch size: 22, lr: 2.13e-04
2022-05-06 21:00:19,603 INFO [train.py:715] (4/8) Epoch 10, batch 19800, loss[loss=0.185, simple_loss=0.2502, pruned_loss=0.05993, over 4848.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03295, over 972584.27 frames.], batch size: 32, lr: 2.13e-04
2022-05-06 21:00:59,241 INFO [train.py:715] (4/8) Epoch 10, batch 19850, loss[loss=0.122, simple_loss=0.1935, pruned_loss=0.02532, over 4798.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03332, over 972196.97 frames.], batch size: 14, lr: 2.13e-04
2022-05-06 21:01:38,757 INFO [train.py:715] (4/8) Epoch 10, batch 19900, loss[loss=0.1473, simple_loss=0.2157, pruned_loss=0.03946, over 4957.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03335, over 971551.32 frames.], batch size: 35, lr: 2.13e-04
2022-05-06 21:02:19,874 INFO [train.py:715] (4/8) Epoch 10, batch 19950, loss[loss=0.144, simple_loss=0.2153, pruned_loss=0.03637, over 4913.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2116, pruned_loss=0.03328, over 971754.58 frames.], batch size: 38, lr: 2.13e-04
2022-05-06 21:02:58,932 INFO [train.py:715] (4/8) Epoch 10, batch 20000, loss[loss=0.1509, simple_loss=0.2233, pruned_loss=0.03929, over 4969.00 frames.], tot_loss[loss=0.139, simple_loss=0.2117, pruned_loss=0.0332, over 972462.95 frames.], batch size: 21, lr: 2.13e-04
2022-05-06 21:03:37,944 INFO [train.py:715] (4/8) Epoch 10, batch 20050, loss[loss=0.1132, simple_loss=0.1934, pruned_loss=0.0165, over 4921.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2118, pruned_loss=0.03302, over 972586.21 frames.], batch size: 23, lr: 2.13e-04
2022-05-06 21:04:17,425 INFO [train.py:715] (4/8) Epoch 10, batch 20100, loss[loss=0.1654, simple_loss=0.2331, pruned_loss=0.04883, over 4791.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.033, over 972471.52 frames.], batch size: 18, lr: 2.13e-04
2022-05-06 21:04:55,529 INFO [train.py:715] (4/8) Epoch 10, batch 20150, loss[loss=0.129, simple_loss=0.2072, pruned_loss=0.02539, over 4770.00 frames.], tot_loss[loss=0.1397, simple_loss=0.213, pruned_loss=0.03321, over 972213.89 frames.], batch size: 17, lr: 2.13e-04
2022-05-06 21:05:34,942 INFO [train.py:715] (4/8) Epoch 10, batch 20200, loss[loss=0.1581, simple_loss=0.2382, pruned_loss=0.03899, over 4967.00 frames.], tot_loss[loss=0.1398, simple_loss=0.213, pruned_loss=0.03326, over 972660.38 frames.], batch size: 35, lr: 2.13e-04
2022-05-06 21:06:13,958 INFO [train.py:715] (4/8) Epoch 10, batch 20250, loss[loss=0.1553, simple_loss=0.2229, pruned_loss=0.04384, over 4850.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03248, over 973332.69 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 21:06:52,617 INFO [train.py:715] (4/8) Epoch 10, batch 20300, loss[loss=0.1427, simple_loss=0.2064, pruned_loss=0.03951, over 4799.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2121, pruned_loss=0.03239, over 972745.57 frames.], batch size: 13, lr: 2.13e-04
2022-05-06 21:07:31,400 INFO [train.py:715] (4/8) Epoch 10, batch 20350, loss[loss=0.1496, simple_loss=0.2209, pruned_loss=0.03916, over 4839.00 frames.], tot_loss[loss=0.1384, simple_loss=0.212, pruned_loss=0.03243, over 972529.47 frames.], batch size: 30, lr: 2.13e-04
2022-05-06 21:08:10,506 INFO [train.py:715] (4/8) Epoch 10, batch 20400, loss[loss=0.1768, simple_loss=0.2408, pruned_loss=0.05646, over 4838.00 frames.], tot_loss[loss=0.1396, simple_loss=0.213, pruned_loss=0.03311, over 972352.29 frames.], batch size: 30, lr: 2.13e-04
2022-05-06 21:08:49,426 INFO [train.py:715] (4/8) Epoch 10, batch 20450, loss[loss=0.1574, simple_loss=0.234, pruned_loss=0.04041, over 4895.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2127, pruned_loss=0.03289, over 972370.04 frames.], batch size: 22, lr: 2.13e-04
2022-05-06 21:09:27,877 INFO [train.py:715] (4/8) Epoch 10, batch 20500, loss[loss=0.1104, simple_loss=0.1887, pruned_loss=0.01604, over 4862.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03295, over 973204.30 frames.], batch size: 20, lr: 2.13e-04
2022-05-06 21:10:06,955 INFO [train.py:715] (4/8) Epoch 10, batch 20550, loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03144, over 4829.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03337, over 973188.60 frames.], batch size: 13, lr: 2.13e-04
2022-05-06 21:10:46,031 INFO [train.py:715] (4/8) Epoch 10, batch 20600, loss[loss=0.1274, simple_loss=0.2058, pruned_loss=0.02446, over 4980.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2141, pruned_loss=0.03383, over 973060.45 frames.], batch size: 26, lr: 2.13e-04
2022-05-06 21:11:25,462 INFO [train.py:715] (4/8) Epoch 10, batch 20650, loss[loss=0.1253, simple_loss=0.2013, pruned_loss=0.02467, over 4822.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.0336, over 973514.30 frames.], batch size: 25, lr: 2.13e-04
2022-05-06 21:12:04,252 INFO [train.py:715] (4/8) Epoch 10, batch 20700, loss[loss=0.1593, simple_loss=0.2178, pruned_loss=0.05037, over 4940.00 frames.], tot_loss[loss=0.1398, simple_loss=0.213, pruned_loss=0.03329, over 974117.11 frames.], batch size: 39, lr: 2.13e-04
2022-05-06 21:12:44,588 INFO [train.py:715] (4/8) Epoch 10, batch 20750, loss[loss=0.1105, simple_loss=0.1925, pruned_loss=0.01424, over 4796.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03302, over 973839.48 frames.], batch size: 24, lr: 2.13e-04
2022-05-06 21:13:24,571 INFO [train.py:715] (4/8) Epoch 10, batch 20800, loss[loss=0.1607, simple_loss=0.2324, pruned_loss=0.04446, over 4900.00 frames.], tot_loss[loss=0.14, simple_loss=0.2131, pruned_loss=0.03351, over 974232.54 frames.], batch size: 22, lr: 2.13e-04
2022-05-06 21:14:03,345 INFO [train.py:715] (4/8) Epoch 10, batch 20850, loss[loss=0.1471, simple_loss=0.2313, pruned_loss=0.03145, over 4837.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.0333, over 974207.31 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 21:14:43,292 INFO [train.py:715] (4/8) Epoch 10, batch 20900, loss[loss=0.1151, simple_loss=0.1886, pruned_loss=0.02084, over 4687.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2111, pruned_loss=0.03277, over 973121.60 frames.], batch size: 15, lr: 2.13e-04
2022-05-06 21:15:23,752 INFO [train.py:715] (4/8) Epoch 10, batch 20950, loss[loss=0.1349, simple_loss=0.2017, pruned_loss=0.03402, over 4646.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2123, pruned_loss=0.03359, over 973043.34 frames.], batch size: 13, lr: 2.13e-04
2022-05-06 21:16:02,699 INFO [train.py:715] (4/8) Epoch 10, batch 21000, loss[loss=0.1561, simple_loss=0.2337, pruned_loss=0.03923, over 4823.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03352, over 972053.59 frames.], batch size: 25, lr: 2.13e-04
2022-05-06 21:16:02,699 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 21:16:12,202 INFO [train.py:742] (4/8) Epoch 10, validation: loss=0.1065, simple_loss=0.1909, pruned_loss=0.01111, over 914524.00 frames.
2022-05-06 21:16:51,720 INFO [train.py:715] (4/8) Epoch 10, batch 21050, loss[loss=0.1336, simple_loss=0.199, pruned_loss=0.03405, over 4771.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.03369, over 973209.39 frames.], batch size: 19, lr: 2.13e-04
2022-05-06 21:17:32,557 INFO [train.py:715] (4/8) Epoch 10, batch 21100, loss[loss=0.139, simple_loss=0.2144, pruned_loss=0.03174, over 4784.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2129, pruned_loss=0.03398, over 973298.58 frames.], batch size: 18, lr: 2.13e-04
2022-05-06 21:18:14,005 INFO [train.py:715] (4/8) Epoch 10, batch 21150, loss[loss=0.1209, simple_loss=0.1942, pruned_loss=0.02379, over 4758.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2123, pruned_loss=0.03363, over 972900.86 frames.], batch size: 19, lr: 2.13e-04
2022-05-06 21:18:55,090 INFO [train.py:715] (4/8) Epoch 10, batch 21200, loss[loss=0.1377, simple_loss=0.2122, pruned_loss=0.03156, over 4968.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.0336, over 972678.33 frames.], batch size: 24, lr: 2.13e-04
2022-05-06 21:19:35,768 INFO [train.py:715] (4/8) Epoch 10, batch 21250, loss[loss=0.1916, simple_loss=0.2675, pruned_loss=0.05784, over 4895.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2121, pruned_loss=0.03356, over 972574.45 frames.], batch size: 19, lr: 2.13e-04
2022-05-06 21:20:17,422 INFO [train.py:715] (4/8) Epoch 10, batch 21300, loss[loss=0.1362, simple_loss=0.2106, pruned_loss=0.0309, over 4860.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2119, pruned_loss=0.0334, over 971756.04 frames.], batch size: 32, lr: 2.13e-04
2022-05-06 21:20:58,700 INFO [train.py:715] (4/8) Epoch 10, batch 21350, loss[loss=0.1152, simple_loss=0.1839, pruned_loss=0.02321, over 4777.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2111, pruned_loss=0.03253, over 972472.61 frames.], batch size: 12, lr: 2.13e-04
2022-05-06 21:21:39,097 INFO [train.py:715] (4/8) Epoch 10, batch 21400, loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03149, over 4975.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2112, pruned_loss=0.03286, over 972629.99 frames.], batch size: 28, lr: 2.13e-04
2022-05-06 21:22:20,540 INFO [train.py:715] (4/8) Epoch 10, batch 21450, loss[loss=0.1367, simple_loss=0.2058, pruned_loss=0.03379, over 4942.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.03323, over 972431.14 frames.], batch size: 23, lr: 2.13e-04
2022-05-06 21:23:02,358 INFO [train.py:715] (4/8) Epoch 10, batch 21500, loss[loss=0.1223, simple_loss=0.1909, pruned_loss=0.0269, over 4772.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2125, pruned_loss=0.0336, over 971159.92 frames.], batch size: 14, lr: 2.13e-04
2022-05-06 21:23:43,367 INFO [train.py:715] (4/8) Epoch 10, batch 21550, loss[loss=0.1158, simple_loss=0.1808, pruned_loss=0.02537, over 4958.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2132, pruned_loss=0.03388, over 972264.04 frames.], batch size: 24, lr: 2.13e-04
2022-05-06 21:24:24,260 INFO [train.py:715] (4/8) Epoch 10, batch 21600, loss[loss=0.1454, simple_loss=0.2215, pruned_loss=0.03468, over 4967.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2134, pruned_loss=0.03373, over 973524.44 frames.], batch size: 35, lr: 2.13e-04
2022-05-06 21:25:06,203 INFO [train.py:715] (4/8) Epoch 10, batch 21650, loss[loss=0.1198, simple_loss=0.2088, pruned_loss=0.01541, over 4850.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2133, pruned_loss=0.03346, over 973081.82 frames.], batch size: 20, lr: 2.13e-04
2022-05-06 21:25:47,752 INFO [train.py:715] (4/8) Epoch 10, batch 21700, loss[loss=0.1566, simple_loss=0.2202, pruned_loss=0.04647, over 4761.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03299, over 973408.17 frames.], batch size: 14, lr: 2.13e-04
2022-05-06 21:26:27,996 INFO [train.py:715] (4/8) Epoch 10, batch 21750, loss[loss=0.152, simple_loss=0.2308, pruned_loss=0.03659, over 4831.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2127, pruned_loss=0.03313, over 973474.23 frames.], batch size: 26, lr: 2.13e-04
2022-05-06 21:27:08,999 INFO [train.py:715] (4/8) Epoch 10, batch 21800, loss[loss=0.1571, simple_loss=0.229, pruned_loss=0.04256, over 4760.00 frames.], tot_loss[loss=0.139, simple_loss=0.2122, pruned_loss=0.03294, over 973353.84 frames.], batch size: 14, lr: 2.13e-04
2022-05-06 21:27:50,686 INFO [train.py:715] (4/8) Epoch 10, batch 21850, loss[loss=0.1526, simple_loss=0.2154, pruned_loss=0.04489, over 4832.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2132, pruned_loss=0.0335, over 973512.34 frames.], batch size: 12, lr: 2.13e-04
2022-05-06 21:28:31,153 INFO [train.py:715] (4/8) Epoch 10, batch 21900, loss[loss=0.1452, simple_loss=0.2163, pruned_loss=0.03707, over 4948.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03307, over 973783.54 frames.], batch size: 29, lr: 2.13e-04
2022-05-06 21:29:11,905 INFO [train.py:715] (4/8) Epoch 10, batch 21950, loss[loss=0.1665, simple_loss=0.2396, pruned_loss=0.04672, over 4933.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03355, over 974038.26 frames.], batch size: 23, lr: 2.13e-04
2022-05-06 21:29:53,125 INFO [train.py:715] (4/8) Epoch 10, batch 22000, loss[loss=0.1664, simple_loss=0.2413, pruned_loss=0.0458, over 4938.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2131, pruned_loss=0.03371, over 973721.97 frames.], batch size: 29, lr: 2.12e-04
2022-05-06 21:30:33,455 INFO [train.py:715] (4/8) Epoch 10, batch 22050, loss[loss=0.1236, simple_loss=0.2095, pruned_loss=0.01891, over 4803.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2131, pruned_loss=0.03334, over 974140.20 frames.], batch size: 21, lr: 2.12e-04
2022-05-06 21:31:14,067 INFO [train.py:715] (4/8) Epoch 10, batch 22100, loss[loss=0.1484, simple_loss=0.2213, pruned_loss=0.03773, over 4852.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2135, pruned_loss=0.03353, over 973817.71 frames.], batch size: 15, lr: 2.12e-04
2022-05-06 21:31:54,927 INFO [train.py:715] (4/8) Epoch 10, batch 22150, loss[loss=0.1279, simple_loss=0.1937, pruned_loss=0.03108, over 4741.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2135, pruned_loss=0.03349, over 972843.35 frames.], batch size: 19, lr: 2.12e-04
2022-05-06 21:32:35,985 INFO [train.py:715] (4/8) Epoch 10, batch 22200, loss[loss=0.119, simple_loss=0.1903, pruned_loss=0.02387, over 4934.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2135, pruned_loss=0.0334, over 973222.42 frames.], batch size: 29, lr: 2.12e-04
2022-05-06 21:33:16,079 INFO [train.py:715] (4/8) Epoch 10, batch 22250, loss[loss=0.1338, simple_loss=0.2065, pruned_loss=0.03057, over 4891.00 frames.], tot_loss[loss=0.14, simple_loss=0.2133, pruned_loss=0.03334, over 973062.08 frames.], batch size: 16, lr: 2.12e-04
2022-05-06 21:33:56,730 INFO [train.py:715] (4/8) Epoch 10, batch 22300, loss[loss=0.1204, simple_loss=0.1926, pruned_loss=0.02406, over 4947.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2139, pruned_loss=0.03362, over 972548.11 frames.], batch size: 18, lr: 2.12e-04
2022-05-06 21:34:37,767 INFO [train.py:715] (4/8) Epoch 10, batch 22350, loss[loss=0.1201, simple_loss=0.1911, pruned_loss=0.02456, over 4811.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2136, pruned_loss=0.03385, over 971626.73 frames.], batch size: 26, lr: 2.12e-04
2022-05-06 21:35:17,620 INFO [train.py:715] (4/8) Epoch 10, batch 22400, loss[loss=0.1141, simple_loss=0.196, pruned_loss=0.01614, over 4924.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.03413, over 971503.44 frames.], batch size: 29, lr: 2.12e-04
2022-05-06 21:35:56,790 INFO [train.py:715] (4/8) Epoch 10, batch 22450, loss[loss=0.1463, simple_loss=0.2201, pruned_loss=0.03622, over 4968.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2135, pruned_loss=0.03413, over 971956.85 frames.], batch size: 15, lr: 2.12e-04
2022-05-06 21:36:36,730 INFO [train.py:715] (4/8) Epoch 10, batch 22500, loss[loss=0.1111, simple_loss=0.1865, pruned_loss=0.01782, over 4795.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2124, pruned_loss=0.03369, over 971923.59 frames.], batch size: 18, lr: 2.12e-04
2022-05-06 21:37:17,615 INFO [train.py:715] (4/8) Epoch 10, batch 22550, loss[loss=0.155, simple_loss=0.2319, pruned_loss=0.03902, over 4809.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2116, pruned_loss=0.03336, over 971940.59 frames.], batch size: 25, lr: 2.12e-04
2022-05-06 21:37:56,431 INFO [train.py:715] (4/8) Epoch 10, batch 22600, loss[loss=0.1364, simple_loss=0.2062, pruned_loss=0.03332, over 4964.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2122, pruned_loss=0.03344, over 972517.85 frames.], batch size: 35, lr: 2.12e-04
2022-05-06 21:38:37,513 INFO [train.py:715] (4/8) Epoch 10, batch 22650, loss[loss=0.1153, simple_loss=0.1979, pruned_loss=0.01633, over 4758.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2116, pruned_loss=0.03276, over 972551.03 frames.], batch size: 16, lr: 2.12e-04
2022-05-06 21:39:19,366 INFO [train.py:715] (4/8) Epoch 10, batch 22700, loss[loss=0.1783, simple_loss=0.2463, pruned_loss=0.0552, over 4747.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.0331, over 972346.21 frames.], batch size: 19, lr: 2.12e-04
2022-05-06 21:40:00,102 INFO [train.py:715] (4/8) Epoch 10, batch 22750, loss[loss=0.1649, simple_loss=0.2336, pruned_loss=0.04813, over 4898.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03333, over 972631.14 frames.], batch size: 16, lr: 2.12e-04
2022-05-06 21:40:41,323 INFO [train.py:715] (4/8) Epoch 10, batch 22800, loss[loss=0.1437, simple_loss=0.2211, pruned_loss=0.03316, over 4888.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2139, pruned_loss=0.03374, over 973553.05 frames.], batch size: 16, lr: 2.12e-04
2022-05-06 21:41:22,876 INFO [train.py:715] (4/8) Epoch 10, batch 22850, loss[loss=0.1234, simple_loss=0.1881, pruned_loss=0.02937, over 4780.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2137, pruned_loss=0.03348, over 973090.94 frames.], batch size: 12, lr: 2.12e-04
2022-05-06 21:42:04,580 INFO [train.py:715] (4/8) Epoch 10, batch 22900, loss[loss=0.1429, simple_loss=0.212, pruned_loss=0.03689, over 4868.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2141, pruned_loss=0.03408, over 972896.96 frames.], batch size: 30, lr: 2.12e-04
2022-05-06 21:42:45,054 INFO [train.py:715] (4/8) Epoch 10, batch 22950, loss[loss=0.1267, simple_loss=0.2101, pruned_loss=0.02169, over 4888.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2138, pruned_loss=0.03415, over 972896.27 frames.], batch size: 19, lr: 2.12e-04
2022-05-06 21:43:27,078 INFO [train.py:715] (4/8) Epoch 10, batch 23000, loss[loss=0.1275, simple_loss=0.2006, pruned_loss=0.02713, over 4922.00 frames.], tot_loss[loss=0.1411, simple_loss=0.214, pruned_loss=0.03413, over 973032.58 frames.], batch size: 18, lr: 2.12e-04
2022-05-06 21:44:09,138 INFO [train.py:715] (4/8) Epoch 10, batch 23050, loss[loss=0.1431, simple_loss=0.2092, pruned_loss=0.03853, over 4794.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2142, pruned_loss=0.03407, over 973709.47 frames.], batch size: 24, lr: 2.12e-04
2022-05-06 21:44:49,657 INFO [train.py:715] (4/8) Epoch 10, batch 23100, loss[loss=0.1264, simple_loss=0.19, pruned_loss=0.03143, over 4866.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2137, pruned_loss=0.034, over 972902.29 frames.], batch size: 32, lr: 2.12e-04
2022-05-06 21:45:30,865 INFO [train.py:715] (4/8) Epoch 10, batch 23150, loss[loss=0.1627, simple_loss=0.2374, pruned_loss=0.04398, over 4988.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2131, pruned_loss=0.03406, over 973393.28 frames.], batch size: 28, lr: 2.12e-04
2022-05-06 21:46:12,872 INFO [train.py:715] (4/8) Epoch 10, batch 23200, loss[loss=0.1251, simple_loss=0.2075, pruned_loss=0.02133, over 4889.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.03349, over 973315.75 frames.], batch size: 22, lr: 2.12e-04
2022-05-06 21:46:54,161 INFO [train.py:715] (4/8) Epoch 10, batch 23250, loss[loss=0.1484, simple_loss=0.2125, pruned_loss=0.04216, over 4753.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2133, pruned_loss=0.03359, over 974045.11 frames.], batch size: 19, lr: 2.12e-04
2022-05-06 21:47:34,834 INFO [train.py:715] (4/8) Epoch 10, batch 23300, loss[loss=0.1432, simple_loss=0.217, pruned_loss=0.03467, over 4982.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2129, pruned_loss=0.03311, over 973221.45 frames.], batch size: 14, lr: 2.12e-04
2022-05-06 21:48:16,743 INFO [train.py:715] (4/8) Epoch 10, batch 23350, loss[loss=0.1706, simple_loss=0.2461, pruned_loss=0.04753, over 4922.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03328, over 973398.17 frames.], batch size: 18, lr: 2.12e-04
2022-05-06 21:48:58,862 INFO [train.py:715] (4/8) Epoch 10, batch 23400, loss[loss=0.1411, simple_loss=0.2126, pruned_loss=0.03475, over 4964.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2126, pruned_loss=0.03307, over 973872.44 frames.], batch size: 14, lr: 2.12e-04
2022-05-06 21:49:39,772 INFO [train.py:715] (4/8) Epoch 10, batch 23450, loss[loss=0.1674, simple_loss=0.2317, pruned_loss=0.0516, over 4935.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03349, over 972325.98 frames.], batch size: 23, lr: 2.12e-04
2022-05-06 21:50:20,134 INFO [train.py:715] (4/8) Epoch 10, batch 23500, loss[loss=0.1775, simple_loss=0.2526, pruned_loss=0.05125, over 4937.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03328, over 972615.31 frames.], batch size: 21, lr: 2.12e-04
2022-05-06 21:51:02,209 INFO [train.py:715] (4/8) Epoch 10, batch 23550, loss[loss=0.158, simple_loss=0.2199, pruned_loss=0.04809, over 4700.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.03302, over 972337.19 frames.], batch size: 15, lr: 2.12e-04
2022-05-06 21:51:43,364 INFO [train.py:715] (4/8) Epoch 10, batch 23600, loss[loss=0.1305, simple_loss=0.2042, pruned_loss=0.02843, over 4824.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2122, pruned_loss=0.03262, over 972107.47 frames.], batch size: 13, lr: 2.12e-04
2022-05-06 21:52:23,127 INFO [train.py:715] (4/8) Epoch 10, batch 23650, loss[loss=0.1302, simple_loss=0.2054, pruned_loss=0.02746, over 4877.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2118, pruned_loss=0.03238, over 972319.32 frames.], batch size: 22, lr: 2.12e-04
2022-05-06 21:53:03,642 INFO [train.py:715] (4/8) Epoch 10, batch 23700, loss[loss=0.1467, simple_loss=0.2281, pruned_loss=0.03262, over 4931.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.03299, over 972398.01 frames.], batch size: 23, lr: 2.12e-04
2022-05-06 21:53:44,215 INFO [train.py:715] (4/8) Epoch 10, batch 23750, loss[loss=0.1374, simple_loss=0.2053, pruned_loss=0.03477, over 4853.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2128, pruned_loss=0.03328, over 973754.16 frames.], batch size: 34, lr: 2.12e-04
2022-05-06 21:54:24,357 INFO [train.py:715] (4/8) Epoch 10, batch 23800, loss[loss=0.1995, simple_loss=0.2556, pruned_loss=0.07173, over 4885.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2133, pruned_loss=0.03392, over 973671.33 frames.], batch size: 16, lr: 2.12e-04
2022-05-06 21:55:04,941 INFO [train.py:715] (4/8) Epoch 10, batch 23850, loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03243, over 4784.00 frames.], tot_loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.03364, over 974081.07 frames.], batch size: 14, lr: 2.12e-04
2022-05-06 21:55:46,215 INFO [train.py:715] (4/8) Epoch 10, batch 23900, loss[loss=0.2009, simple_loss=0.2585, pruned_loss=0.07163, over 4956.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2127, pruned_loss=0.03374, over 972881.31 frames.], batch size: 15, lr: 2.12e-04
2022-05-06 21:56:25,835 INFO [train.py:715] (4/8) Epoch 10, batch 23950, loss[loss=0.1312, simple_loss=0.2116, pruned_loss=0.02541, over 4845.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2132, pruned_loss=0.03398, over 972808.43 frames.], batch size: 13, lr: 2.12e-04
2022-05-06 21:57:06,212 INFO [train.py:715] (4/8) Epoch 10, batch 24000, loss[loss=0.1346, simple_loss=0.2016, pruned_loss=0.03378, over 4806.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.03352, over 972696.79 frames.], batch size: 14, lr: 2.12e-04
2022-05-06 21:57:06,213 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 21:57:15,892 INFO [train.py:742] (4/8) Epoch 10, validation: loss=0.1061, simple_loss=0.1905, pruned_loss=0.01087, over 914524.00 frames.
2022-05-06 21:57:55,794 INFO [train.py:715] (4/8) Epoch 10, batch 24050, loss[loss=0.1303, simple_loss=0.2132, pruned_loss=0.02366, over 4950.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.03339, over 973113.89 frames.], batch size: 29, lr: 2.12e-04
2022-05-06 21:58:36,842 INFO [train.py:715] (4/8) Epoch 10, batch 24100, loss[loss=0.1633, simple_loss=0.2314, pruned_loss=0.0476, over 4827.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2117, pruned_loss=0.03338, over 972503.75 frames.], batch size: 26, lr: 2.12e-04
2022-05-06 21:59:18,099 INFO [train.py:715] (4/8) Epoch 10, batch 24150, loss[loss=0.1467, simple_loss=0.2183, pruned_loss=0.03758, over 4840.00 frames.], tot_loss[loss=0.1395, simple_loss=0.212, pruned_loss=0.03357, over 971957.88 frames.], batch size: 26, lr: 2.12e-04
2022-05-06 21:59:57,425 INFO [train.py:715] (4/8) Epoch 10, batch 24200, loss[loss=0.1345, simple_loss=0.2036, pruned_loss=0.03265, over 4832.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2121, pruned_loss=0.03349, over 971914.29 frames.], batch size: 12, lr: 2.12e-04
2022-05-06 22:00:38,172 INFO [train.py:715] (4/8) Epoch 10, batch 24250, loss[loss=0.1324, simple_loss=0.2047, pruned_loss=0.03007, over 4950.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.03321, over 971695.86 frames.], batch size: 23, lr: 2.12e-04
2022-05-06 22:01:19,285 INFO [train.py:715] (4/8) Epoch 10, batch 24300, loss[loss=0.1309, simple_loss=0.2003, pruned_loss=0.03072, over 4782.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2123, pruned_loss=0.03366, over 972459.36 frames.], batch size: 14, lr: 2.12e-04
2022-05-06 22:01:59,408 INFO [train.py:715] (4/8) Epoch 10, batch 24350, loss[loss=0.1036, simple_loss=0.1687, pruned_loss=0.01923, over 4801.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.0332, over 972213.59 frames.], batch size: 25, lr: 2.12e-04
2022-05-06 22:02:39,454 INFO [train.py:715] (4/8) Epoch 10, batch 24400, loss[loss=0.1567, simple_loss=0.2282, pruned_loss=0.04263, over 4639.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.03315, over 972352.95 frames.], batch size: 13, lr: 2.12e-04
2022-05-06 22:03:20,169 INFO [train.py:715] (4/8) Epoch 10, batch 24450, loss[loss=0.153, simple_loss=0.2208, pruned_loss=0.04265, over 4794.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03322, over 971685.16 frames.], batch size: 18, lr: 2.12e-04
2022-05-06 22:04:01,130 INFO [train.py:715] (4/8) Epoch 10, batch 24500, loss[loss=0.1258, simple_loss=0.1986, pruned_loss=0.02651, over 4859.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03243, over 971372.66 frames.], batch size: 30, lr: 2.12e-04
2022-05-06 22:04:40,217 INFO [train.py:715] (4/8) Epoch 10, batch 24550, loss[loss=0.1335, simple_loss=0.2025, pruned_loss=0.03229, over 4975.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2112, pruned_loss=0.0326, over 971812.66 frames.], batch size: 35, lr: 2.12e-04
2022-05-06 22:05:20,204 INFO [train.py:715] (4/8) Epoch 10, batch 24600, loss[loss=0.1449, simple_loss=0.2197, pruned_loss=0.03508, over 4891.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03275, over 971875.20 frames.], batch size: 19, lr: 2.12e-04
2022-05-06 22:06:00,588 INFO [train.py:715] (4/8) Epoch 10, batch 24650, loss[loss=0.1346, simple_loss=0.1989, pruned_loss=0.03513, over 4912.00 frames.], tot_loss[loss=0.1395, simple_loss=0.212, pruned_loss=0.03354, over 971589.99 frames.], batch size: 18, lr: 2.12e-04
2022-05-06 22:06:39,584 INFO [train.py:715] (4/8) Epoch 10, batch 24700, loss[loss=0.1502, simple_loss=0.2236, pruned_loss=0.03836, over 4733.00 frames.], tot_loss[loss=0.1404, simple_loss=0.213, pruned_loss=0.03396, over 971978.90 frames.], batch size: 16, lr: 2.12e-04
2022-05-06 22:07:18,183 INFO [train.py:715] (4/8) Epoch 10, batch 24750, loss[loss=0.1308, simple_loss=0.2122, pruned_loss=0.02468, over 4904.00 frames.], tot_loss[loss=0.141, simple_loss=0.2133, pruned_loss=0.03432, over 972009.30 frames.], batch size: 19, lr: 2.12e-04
2022-05-06 22:07:57,674 INFO [train.py:715] (4/8) Epoch 10, batch 24800, loss[loss=0.155, simple_loss=0.2109, pruned_loss=0.04956, over 4780.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2135, pruned_loss=0.03439, over 972357.79 frames.], batch size: 18, lr: 2.12e-04
2022-05-06 22:08:36,822 INFO [train.py:715] (4/8) Epoch 10, batch 24850, loss[loss=0.1448, simple_loss=0.2209, pruned_loss=0.03432, over 4884.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03387, over 972485.83 frames.], batch size: 22, lr: 2.12e-04
2022-05-06 22:09:14,895 INFO [train.py:715] (4/8) Epoch 10, batch 24900, loss[loss=0.141, simple_loss=0.2111, pruned_loss=0.03544, over 4969.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03383, over 972141.32 frames.], batch size: 25, lr: 2.12e-04
2022-05-06 22:09:54,540 INFO [train.py:715] (4/8) Epoch 10, batch 24950, loss[loss=0.1566, simple_loss=0.224, pruned_loss=0.04465, over 4861.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2135, pruned_loss=0.03409, over 972154.08 frames.], batch size: 32, lr: 2.12e-04
2022-05-06 22:10:34,390 INFO [train.py:715] (4/8) Epoch 10, batch 25000, loss[loss=0.1236, simple_loss=0.1869, pruned_loss=0.03018, over 4968.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2132, pruned_loss=0.03396, over 972761.26 frames.], batch size: 14, lr: 2.12e-04
2022-05-06 22:11:13,242 INFO [train.py:715] (4/8) Epoch 10, batch 25050, loss[loss=0.1506, simple_loss=0.2242, pruned_loss=0.03847, over 4819.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2137, pruned_loss=0.03433, over 972536.97 frames.], batch size: 26, lr: 2.12e-04
2022-05-06 22:11:52,713 INFO [train.py:715] (4/8) Epoch 10, batch 25100, loss[loss=0.1245, simple_loss=0.2042, pruned_loss=0.02239, over 4941.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2139, pruned_loss=0.03466, over 972728.90 frames.], batch size: 24, lr: 2.12e-04
2022-05-06 22:12:32,718 INFO [train.py:715] (4/8) Epoch 10, batch 25150, loss[loss=0.1416, simple_loss=0.2078, pruned_loss=0.03775, over 4981.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2125, pruned_loss=0.03418, over 972822.73 frames.], batch size: 28, lr: 2.12e-04
2022-05-06 22:13:12,209 INFO [train.py:715] (4/8) Epoch 10, batch 25200, loss[loss=0.1247, simple_loss=0.1989, pruned_loss=0.02523, over 4927.00 frames.], tot_loss[loss=0.141, simple_loss=0.2132, pruned_loss=0.03437, over 971470.63 frames.], batch size: 18, lr: 2.12e-04
2022-05-06 22:13:50,342 INFO [train.py:715] (4/8) Epoch 10, batch 25250, loss[loss=0.1442, simple_loss=0.2205, pruned_loss=0.03395, over 4830.00 frames.], tot_loss[loss=0.141, simple_loss=0.2133, pruned_loss=0.0343, over 971600.33 frames.], batch size: 26, lr: 2.12e-04
2022-05-06 22:14:29,218 INFO [train.py:715] (4/8) Epoch 10, batch 25300, loss[loss=0.1501, simple_loss=0.2151, pruned_loss=0.04256, over 4975.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2128, pruned_loss=0.03382, over 971493.29 frames.], batch size: 14, lr: 2.12e-04
2022-05-06 22:15:08,862 INFO [train.py:715] (4/8) Epoch 10, batch 25350, loss[loss=0.1155, simple_loss=0.1939, pruned_loss=0.01854, over 4770.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2129, pruned_loss=0.03395, over 972384.43 frames.], batch size: 17, lr: 2.12e-04
2022-05-06 22:15:47,380 INFO [train.py:715] (4/8) Epoch 10, batch 25400, loss[loss=0.1357, simple_loss=0.212, pruned_loss=0.02969, over 4742.00 frames.], tot_loss[loss=0.14, simple_loss=0.2128, pruned_loss=0.03361, over 972518.79 frames.], batch size: 19, lr: 2.12e-04
2022-05-06 22:16:26,236 INFO [train.py:715] (4/8) Epoch 10, batch 25450, loss[loss=0.1363, simple_loss=0.2228, pruned_loss=0.02485, over 4818.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.0334, over 972179.09 frames.], batch size: 15, lr: 2.12e-04
2022-05-06 22:17:06,159 INFO [train.py:715] (4/8) Epoch 10, batch 25500, loss[loss=0.1663, simple_loss=0.2384, pruned_loss=0.04714, over 4968.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2139, pruned_loss=0.03368, over 972886.10 frames.], batch size: 15, lr: 2.11e-04
2022-05-06 22:17:45,976 INFO [train.py:715] (4/8) Epoch 10, batch 25550, loss[loss=0.1089, simple_loss=0.1892, pruned_loss=0.01434, over 4960.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2137, pruned_loss=0.03381, over 972726.03 frames.], batch size: 21, lr: 2.11e-04
2022-05-06 22:18:24,958 INFO [train.py:715] (4/8) Epoch 10, batch 25600, loss[loss=0.1191, simple_loss=0.2004, pruned_loss=0.0189, over 4841.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2135, pruned_loss=0.03359, over 973185.12 frames.], batch size: 13, lr: 2.11e-04
2022-05-06 22:19:05,112 INFO [train.py:715] (4/8) Epoch 10, batch 25650, loss[loss=0.1292, simple_loss=0.1987, pruned_loss=0.02985, over 4976.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2131, pruned_loss=0.03364, over 971825.62 frames.], batch size: 25, lr: 2.11e-04
2022-05-06 22:19:45,486 INFO [train.py:715] (4/8) Epoch 10, batch 25700, loss[loss=0.1136, simple_loss=0.1912, pruned_loss=0.01799, over 4648.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2131, pruned_loss=0.03335, over 971763.45 frames.], batch size: 13, lr: 2.11e-04
2022-05-06 22:20:25,348 INFO [train.py:715] (4/8) Epoch 10, batch 25750, loss[loss=0.1611, simple_loss=0.2261, pruned_loss=0.04807, over 4952.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.03335, over 971522.47 frames.], batch size: 40, lr: 2.11e-04
2022-05-06 22:21:04,754 INFO [train.py:715] (4/8) Epoch 10, batch 25800, loss[loss=0.1239, simple_loss=0.2027, pruned_loss=0.02259, over 4752.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2129, pruned_loss=0.03328, over 971115.46 frames.], batch size: 19, lr: 2.11e-04
2022-05-06 22:21:45,291 INFO [train.py:715] (4/8) Epoch 10, batch 25850, loss[loss=0.162, simple_loss=0.2364, pruned_loss=0.04381, over 4978.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2126, pruned_loss=0.03308, over 971857.71 frames.], batch size: 24, lr: 2.11e-04
2022-05-06 22:22:25,223 INFO [train.py:715] (4/8) Epoch 10, batch 25900, loss[loss=0.1331, simple_loss=0.2156, pruned_loss=0.02527, over 4906.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03294, over 971831.67 frames.], batch size: 17, lr: 2.11e-04
2022-05-06 22:23:03,943 INFO [train.py:715] (4/8) Epoch 10, batch 25950, loss[loss=0.1462, simple_loss=0.2133, pruned_loss=0.03956, over 4753.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.03355, over 972011.14 frames.], batch size: 16, lr: 2.11e-04
2022-05-06 22:23:42,716 INFO [train.py:715] (4/8) Epoch 10, batch 26000, loss[loss=0.149, simple_loss=0.2204, pruned_loss=0.03874, over 4760.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2144, pruned_loss=0.03418, over 971370.75 frames.], batch size: 17, lr: 2.11e-04
2022-05-06 22:24:21,988 INFO [train.py:715] (4/8) Epoch 10, batch 26050, loss[loss=0.1328, simple_loss=0.2046, pruned_loss=0.03049, over 4740.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2134, pruned_loss=0.03351, over 970699.93 frames.], batch size: 16, lr: 2.11e-04
2022-05-06 22:25:00,975 INFO [train.py:715] (4/8) Epoch 10, batch 26100, loss[loss=0.1179, simple_loss=0.1859, pruned_loss=0.02494, over 4978.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03358, over 971267.54 frames.], batch size: 28, lr: 2.11e-04
2022-05-06 22:25:40,337 INFO [train.py:715] (4/8) Epoch 10, batch 26150, loss[loss=0.1468, simple_loss=0.221, pruned_loss=0.03636, over 4787.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2126, pruned_loss=0.03347, over 971669.67 frames.], batch size: 17, lr: 2.11e-04
2022-05-06 22:26:21,097 INFO [train.py:715] (4/8) Epoch 10, batch 26200, loss[loss=0.1338, simple_loss=0.2041, pruned_loss=0.03177, over 4793.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03306, over 971588.19 frames.], batch size: 24, lr: 2.11e-04
2022-05-06 22:27:00,350 INFO [train.py:715] (4/8) Epoch 10, batch 26250, loss[loss=0.1412, simple_loss=0.2051, pruned_loss=0.0387, over 4769.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03356, over 971434.33 frames.], batch size: 19, lr: 2.11e-04
2022-05-06 22:27:40,000 INFO [train.py:715] (4/8) Epoch 10, batch 26300, loss[loss=0.1414, simple_loss=0.2102, pruned_loss=0.03627, over 4960.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2124, pruned_loss=0.0334, over 971903.52 frames.], batch size: 35, lr: 2.11e-04
2022-05-06 22:28:19,566 INFO [train.py:715] (4/8) Epoch 10, batch 26350, loss[loss=0.1464, simple_loss=0.2051, pruned_loss=0.0438, over 4868.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2117, pruned_loss=0.03299, over 971604.10 frames.], batch size: 32, lr: 2.11e-04
2022-05-06 22:28:59,166 INFO [train.py:715] (4/8) Epoch 10, batch 26400, loss[loss=0.165, simple_loss=0.2312, pruned_loss=0.04942, over 4743.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2123, pruned_loss=0.03332, over 971617.50 frames.], batch size: 16, lr: 2.11e-04
2022-05-06 22:29:38,871 INFO [train.py:715] (4/8) Epoch 10, batch 26450, loss[loss=0.1269, simple_loss=0.2005, pruned_loss=0.02667, over 4841.00 frames.], tot_loss[loss=0.139, simple_loss=0.2119, pruned_loss=0.03311, over 972356.32 frames.], batch size: 15, lr: 2.11e-04
2022-05-06 22:30:18,683 INFO [train.py:715] (4/8) Epoch 10, batch 26500, loss[loss=0.1057, simple_loss=0.1773, pruned_loss=0.01704, over 4782.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03329, over 971196.45 frames.], batch size: 18, lr: 2.11e-04
2022-05-06 22:30:59,099 INFO [train.py:715] (4/8) Epoch 10, batch 26550, loss[loss=0.1192, simple_loss=0.1843, pruned_loss=0.02711, over 4785.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03335, over 971765.76 frames.], batch size: 12, lr: 2.11e-04
2022-05-06 22:31:37,640 INFO [train.py:715] (4/8) Epoch 10, batch 26600, loss[loss=0.1627, simple_loss=0.2323, pruned_loss=0.0465, over 4854.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.03353, over 972023.57 frames.], batch size: 20, lr: 2.11e-04
2022-05-06 22:32:17,161 INFO [train.py:715] (4/8) Epoch 10, batch 26650, loss[loss=0.1427, simple_loss=0.2066, pruned_loss=0.03935, over 4984.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03323, over 972130.87 frames.], batch size: 15, lr: 2.11e-04
2022-05-06 22:32:56,672 INFO [train.py:715] (4/8) Epoch 10, batch 26700, loss[loss=0.1567, simple_loss=0.2181, pruned_loss=0.04764, over 4764.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2129, pruned_loss=0.03384, over 972612.10 frames.], batch size: 14, lr: 2.11e-04
2022-05-06 22:33:36,176 INFO [train.py:715] (4/8) Epoch 10, batch 26750, loss[loss=0.1634, simple_loss=0.224, pruned_loss=0.05146, over 4917.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2125, pruned_loss=0.0339, over 973473.99 frames.], batch size: 18, lr: 2.11e-04
2022-05-06 22:34:14,863 INFO [train.py:715] (4/8) Epoch 10, batch 26800, loss[loss=0.128, simple_loss=0.1954, pruned_loss=0.03029, over 4966.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2127, pruned_loss=0.03398, over 973482.09 frames.], batch size: 35, lr: 2.11e-04
2022-05-06 22:34:54,618 INFO [train.py:715] (4/8) Epoch 10, batch 26850, loss[loss=0.1267, simple_loss=0.2072, pruned_loss=0.02308, over 4785.00 frames.], tot_loss[loss=0.1397, simple_loss=0.212, pruned_loss=0.03366, over 973802.90 frames.], batch size: 14, lr: 2.11e-04
2022-05-06 22:35:34,126 INFO [train.py:715] (4/8) Epoch 10, batch 26900, loss[loss=0.1123, simple_loss=0.1847, pruned_loss=0.01997, over 4900.00 frames.], tot_loss[loss=0.139, simple_loss=0.2117, pruned_loss=0.03315, over 973027.31 frames.], batch size: 19, lr: 2.11e-04
2022-05-06 22:36:12,943 INFO [train.py:715] (4/8) Epoch 10, batch 26950, loss[loss=0.144, simple_loss=0.2103, pruned_loss=0.03892, over 4989.00 frames.], tot_loss[loss=0.1393, simple_loss=0.212, pruned_loss=0.03334, over 972459.26 frames.], batch size: 28, lr: 2.11e-04
2022-05-06 22:36:51,894 INFO [train.py:715] (4/8) Epoch 10, batch 27000, loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02996, over 4742.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2122, pruned_loss=0.0336, over 973060.46 frames.], batch size: 16, lr: 2.11e-04
2022-05-06 22:36:51,895 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 22:37:01,642 INFO [train.py:742] (4/8) Epoch 10, validation: loss=0.1063, simple_loss=0.1906, pruned_loss=0.01104, over 914524.00 frames.
2022-05-06 22:37:41,041 INFO [train.py:715] (4/8) Epoch 10, batch 27050, loss[loss=0.1474, simple_loss=0.2167, pruned_loss=0.03901, over 4771.00 frames.], tot_loss[loss=0.14, simple_loss=0.2125, pruned_loss=0.03376, over 972063.37 frames.], batch size: 18, lr: 2.11e-04
2022-05-06 22:38:21,000 INFO [train.py:715] (4/8) Epoch 10, batch 27100, loss[loss=0.1997, simple_loss=0.2663, pruned_loss=0.06656, over 4796.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2132, pruned_loss=0.03394, over 971362.35 frames.], batch size: 24, lr: 2.11e-04
2022-05-06 22:38:59,617 INFO [train.py:715] (4/8) Epoch 10, batch 27150, loss[loss=0.1449, simple_loss=0.2209, pruned_loss=0.03447, over 4760.00 frames.], tot_loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.03365, over 971826.34 frames.], batch size: 17, lr: 2.11e-04
2022-05-06 22:39:38,785 INFO [train.py:715] (4/8) Epoch 10, batch 27200, loss[loss=0.1407, simple_loss=0.2146, pruned_loss=0.03337, over 4824.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2123, pruned_loss=0.03369, over 971440.64 frames.], batch size: 27, lr: 2.11e-04
2022-05-06 22:40:18,813 INFO [train.py:715] (4/8) Epoch 10, batch 27250, loss[loss=0.1036, simple_loss=0.178, pruned_loss=0.01461, over 4924.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03383, over 972259.72 frames.], batch size: 29, lr: 2.11e-04
2022-05-06 22:40:58,229 INFO [train.py:715] (4/8) Epoch 10, batch 27300, loss[loss=0.1152, simple_loss=0.1943, pruned_loss=0.01807, over 4833.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2129, pruned_loss=0.03406, over 971557.28 frames.], batch size: 12, lr: 2.11e-04
2022-05-06 22:41:36,436 INFO [train.py:715] (4/8) Epoch 10, batch 27350, loss[loss=0.1329, simple_loss=0.1952, pruned_loss=0.03526, over 4700.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2124, pruned_loss=0.03367, over 971372.73 frames.], batch size: 15, lr: 2.11e-04
2022-05-06 22:42:15,730 INFO [train.py:715] (4/8) Epoch 10, batch 27400, loss[loss=0.1506, simple_loss=0.2237, pruned_loss=0.03876, over 4899.00 frames.], tot_loss[loss=0.1388, simple_loss=0.211, pruned_loss=0.0333, over 970811.22 frames.], batch size: 19, lr: 2.11e-04
2022-05-06 22:42:55,895 INFO [train.py:715] (4/8) Epoch 10, batch 27450, loss[loss=0.1395, simple_loss=0.2083, pruned_loss=0.03531, over 4774.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2111, pruned_loss=0.03317, over 972180.43 frames.], batch size: 18, lr: 2.11e-04
2022-05-06 22:43:34,160 INFO [train.py:715] (4/8) Epoch 10, batch 27500, loss[loss=0.1367, simple_loss=0.211, pruned_loss=0.03117, over 4944.00 frames.], tot_loss[loss=0.139, simple_loss=0.2115, pruned_loss=0.03324, over 972070.56 frames.], batch size: 23, lr: 2.11e-04
2022-05-06 22:44:13,414 INFO [train.py:715] (4/8) Epoch 10, batch 27550, loss[loss=0.1345, simple_loss=0.2177, pruned_loss=0.02558, over 4982.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2117, pruned_loss=0.03302, over 972201.50 frames.], batch size: 25, lr: 2.11e-04
2022-05-06 22:44:52,783 INFO [train.py:715] (4/8) Epoch 10, batch 27600, loss[loss=0.1385, simple_loss=0.2155, pruned_loss=0.03077, over 4810.00 frames.], tot_loss[loss=0.139, simple_loss=0.2117, pruned_loss=0.03317, over 971650.33 frames.], batch size: 26, lr: 2.11e-04
2022-05-06 22:45:32,113 INFO [train.py:715] (4/8) Epoch 10, batch 27650, loss[loss=0.1383, simple_loss=0.2123, pruned_loss=0.0322, over 4866.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.0335, over 971457.86 frames.], batch size: 30, lr: 2.11e-04
2022-05-06 22:46:11,031 INFO [train.py:715] (4/8) Epoch 10, batch 27700, loss[loss=0.1548, simple_loss=0.2194, pruned_loss=0.04516, over 4982.00 frames.], tot_loss[loss=0.14, simple_loss=0.2125, pruned_loss=0.0337, over 972010.98 frames.], batch size: 39, lr: 2.11e-04
2022-05-06 22:46:51,026 INFO [train.py:715] (4/8) Epoch 10, batch 27750, loss[loss=0.1301, simple_loss=0.2084, pruned_loss=0.02594, over 4837.00 frames.], tot_loss[loss=0.14, simple_loss=0.2128, pruned_loss=0.03359, over 971786.04 frames.], batch size: 26, lr: 2.11e-04
2022-05-06 22:47:31,100 INFO [train.py:715] (4/8) Epoch 10, batch 27800, loss[loss=0.13, simple_loss=0.2028, pruned_loss=0.02857, over 4813.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03317, over 972808.43 frames.], batch size: 27, lr: 2.11e-04
2022-05-06 22:48:10,301 INFO [train.py:715] (4/8) Epoch 10, batch 27850, loss[loss=0.2088, simple_loss=0.2876, pruned_loss=0.06498, over 4965.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03336, over 972946.45 frames.], batch size: 39, lr: 2.11e-04
2022-05-06 22:48:50,675 INFO [train.py:715] (4/8) Epoch 10, batch 27900, loss[loss=0.1279, simple_loss=0.2034, pruned_loss=0.02619, over 4932.00 frames.], tot_loss[loss=0.139, simple_loss=0.2115, pruned_loss=0.03324, over 972101.38 frames.], batch size: 23, lr: 2.11e-04
2022-05-06 22:49:34,036 INFO [train.py:715] (4/8) Epoch 10, batch 27950, loss[loss=0.1313, simple_loss=0.2107, pruned_loss=0.02597, over 4743.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2119, pruned_loss=0.03337, over 972256.80 frames.], batch size: 16, lr: 2.11e-04
2022-05-06 22:50:13,531 INFO [train.py:715] (4/8) Epoch 10, batch 28000, loss[loss=0.1311, simple_loss=0.2113, pruned_loss=0.02545, over 4831.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.03345, over 972188.87 frames.], batch size: 25, lr: 2.11e-04
2022-05-06 22:50:53,591 INFO [train.py:715] (4/8) Epoch 10, batch 28050, loss[loss=0.1372, simple_loss=0.2192, pruned_loss=0.02757, over 4903.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2123, pruned_loss=0.03331, over 972937.80 frames.], batch size: 17, lr: 2.11e-04
2022-05-06 22:51:34,459 INFO [train.py:715] (4/8) Epoch 10, batch 28100, loss[loss=0.1155, simple_loss=0.1946, pruned_loss=0.01824, over 4875.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03333, over 973081.24 frames.], batch size: 22, lr: 2.11e-04
2022-05-06 22:52:15,135 INFO [train.py:715] (4/8) Epoch 10, batch 28150, loss[loss=0.1238, simple_loss=0.1962, pruned_loss=0.02572, over 4975.00 frames.], tot_loss[loss=0.14, simple_loss=0.2128, pruned_loss=0.03356, over 973332.63 frames.], batch size: 14, lr: 2.11e-04
2022-05-06 22:52:54,866 INFO [train.py:715] (4/8) Epoch 10, batch 28200, loss[loss=0.1213, simple_loss=0.1948, pruned_loss=0.02395, over 4751.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03354, over 972422.35 frames.], batch size: 16, lr: 2.11e-04
2022-05-06 22:53:35,205 INFO [train.py:715] (4/8) Epoch 10, batch 28250, loss[loss=0.1643, simple_loss=0.2395, pruned_loss=0.04454, over 4799.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2129, pruned_loss=0.03339, over 972049.60 frames.], batch size: 25, lr: 2.11e-04
2022-05-06 22:54:16,798 INFO [train.py:715] (4/8) Epoch 10, batch 28300, loss[loss=0.1142, simple_loss=0.1824, pruned_loss=0.02302, over 4839.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03354, over 972001.09 frames.], batch size: 15, lr: 2.11e-04
2022-05-06 22:54:56,889 INFO [train.py:715] (4/8) Epoch 10, batch 28350, loss[loss=0.1506, simple_loss=0.2194, pruned_loss=0.04089, over 4781.00 frames.], tot_loss[loss=0.1394, simple_loss=0.212, pruned_loss=0.0334, over 972414.67 frames.], batch size: 18, lr: 2.11e-04
2022-05-06 22:55:37,447 INFO [train.py:715] (4/8) Epoch 10, batch 28400, loss[loss=0.1236, simple_loss=0.1966, pruned_loss=0.02526, over 4858.00 frames.], tot_loss[loss=0.1396, simple_loss=0.212, pruned_loss=0.0336, over 971582.37 frames.], batch size: 20, lr: 2.11e-04
2022-05-06 22:56:19,114 INFO [train.py:715] (4/8) Epoch 10, batch 28450, loss[loss=0.1389, simple_loss=0.2094, pruned_loss=0.03418, over 4844.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.03361, over 972010.51 frames.], batch size: 32, lr: 2.11e-04
2022-05-06 22:57:00,129 INFO [train.py:715] (4/8) Epoch 10, batch 28500, loss[loss=0.142, simple_loss=0.2114, pruned_loss=0.03632, over 4902.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2123, pruned_loss=0.03355, over 971507.36 frames.], batch size: 18, lr: 2.11e-04
2022-05-06 22:57:40,542 INFO [train.py:715] (4/8) Epoch 10, batch 28550, loss[loss=0.1433, simple_loss=0.2219, pruned_loss=0.03234, over 4980.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2124, pruned_loss=0.03333, over 972396.89 frames.], batch size: 27, lr: 2.11e-04
2022-05-06 22:58:21,438 INFO [train.py:715] (4/8) Epoch 10, batch 28600, loss[loss=0.1492, simple_loss=0.2259, pruned_loss=0.03628, over 4817.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.0326, over 972227.85 frames.], batch size: 21, lr: 2.11e-04
2022-05-06 22:59:03,580 INFO [train.py:715] (4/8) Epoch 10, batch 28650, loss[loss=0.1115, simple_loss=0.1872, pruned_loss=0.0179, over 4986.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2106, pruned_loss=0.03204, over 972249.67 frames.], batch size: 25, lr: 2.11e-04
2022-05-06 22:59:43,737 INFO [train.py:715] (4/8) Epoch 10, batch 28700, loss[loss=0.1322, simple_loss=0.2027, pruned_loss=0.03088, over 4966.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03218, over 971997.98 frames.], batch size: 24, lr: 2.11e-04
2022-05-06 23:00:24,810 INFO [train.py:715] (4/8) Epoch 10, batch 28750, loss[loss=0.1445, simple_loss=0.2217, pruned_loss=0.03362, over 4843.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2108, pruned_loss=0.0324, over 972889.64 frames.], batch size: 20, lr: 2.11e-04
2022-05-06 23:01:05,925 INFO [train.py:715] (4/8) Epoch 10, batch 28800, loss[loss=0.1289, simple_loss=0.2001, pruned_loss=0.02884, over 4877.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.03295, over 973207.98 frames.], batch size: 16, lr: 2.11e-04
2022-05-06 23:01:46,820 INFO [train.py:715] (4/8) Epoch 10, batch 28850, loss[loss=0.123, simple_loss=0.2068, pruned_loss=0.01963, over 4926.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03302, over 972970.41 frames.], batch size: 23, lr: 2.11e-04
2022-05-06 23:02:27,337 INFO [train.py:715] (4/8) Epoch 10, batch 28900, loss[loss=0.1372, simple_loss=0.2098, pruned_loss=0.03235, over 4864.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2126, pruned_loss=0.0331, over 971755.13 frames.], batch size: 16, lr: 2.11e-04
2022-05-06 23:03:08,203 INFO [train.py:715] (4/8) Epoch 10, batch 28950, loss[loss=0.1464, simple_loss=0.2098, pruned_loss=0.04145, over 4842.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03298, over 972153.42 frames.], batch size: 20, lr: 2.11e-04
2022-05-06 23:03:49,289 INFO [train.py:715] (4/8) Epoch 10, batch 29000, loss[loss=0.1627, simple_loss=0.2261, pruned_loss=0.0496, over 4985.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03275, over 971664.24 frames.], batch size: 15, lr: 2.11e-04
2022-05-06 23:04:28,431 INFO [train.py:715] (4/8) Epoch 10, batch 29050, loss[loss=0.128, simple_loss=0.2012, pruned_loss=0.02738, over 4830.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2126, pruned_loss=0.03277, over 971034.31 frames.], batch size: 27, lr: 2.10e-04
2022-05-06 23:05:07,299 INFO [train.py:715] (4/8) Epoch 10, batch 29100, loss[loss=0.1631, simple_loss=0.2445, pruned_loss=0.0408, over 4764.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2132, pruned_loss=0.03326, over 970971.07 frames.], batch size: 19, lr: 2.10e-04
2022-05-06 23:05:47,481 INFO [train.py:715] (4/8) Epoch 10, batch 29150, loss[loss=0.1312, simple_loss=0.2234, pruned_loss=0.01955, over 4865.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2138, pruned_loss=0.03352, over 971430.98 frames.], batch size: 38, lr: 2.10e-04
2022-05-06 23:06:27,775 INFO [train.py:715] (4/8) Epoch 10, batch 29200, loss[loss=0.1201, simple_loss=0.2085, pruned_loss=0.01586, over 4901.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2139, pruned_loss=0.03363, over 970883.96 frames.], batch size: 19, lr: 2.10e-04
2022-05-06 23:07:06,673 INFO [train.py:715] (4/8) Epoch 10, batch 29250, loss[loss=0.1496, simple_loss=0.2057, pruned_loss=0.04672, over 4689.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.03367, over 970157.96 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:07:46,921 INFO [train.py:715] (4/8) Epoch 10, batch 29300, loss[loss=0.1424, simple_loss=0.216, pruned_loss=0.03437, over 4777.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03337, over 969619.85 frames.], batch size: 18, lr: 2.10e-04
2022-05-06 23:08:27,014 INFO [train.py:715] (4/8) Epoch 10, batch 29350, loss[loss=0.1354, simple_loss=0.2124, pruned_loss=0.02925, over 4807.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2131, pruned_loss=0.03355, over 970216.06 frames.], batch size: 13, lr: 2.10e-04
2022-05-06 23:09:06,022 INFO [train.py:715] (4/8) Epoch 10, batch 29400, loss[loss=0.116, simple_loss=0.1897, pruned_loss=0.0211, over 4845.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2117, pruned_loss=0.03298, over 970242.79 frames.], batch size: 26, lr: 2.10e-04
2022-05-06 23:09:45,802 INFO [train.py:715] (4/8) Epoch 10, batch 29450, loss[loss=0.1429, simple_loss=0.224, pruned_loss=0.03089, over 4832.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03292, over 971045.45 frames.], batch size: 26, lr: 2.10e-04
2022-05-06 23:10:26,001 INFO [train.py:715] (4/8) Epoch 10, batch 29500, loss[loss=0.1104, simple_loss=0.1773, pruned_loss=0.0218, over 4771.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2124, pruned_loss=0.03311, over 971730.95 frames.], batch size: 12, lr: 2.10e-04
2022-05-06 23:11:05,707 INFO [train.py:715] (4/8) Epoch 10, batch 29550, loss[loss=0.1565, simple_loss=0.2362, pruned_loss=0.03845, over 4699.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03348, over 971500.44 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:11:44,343 INFO [train.py:715] (4/8) Epoch 10, batch 29600, loss[loss=0.1163, simple_loss=0.181, pruned_loss=0.02583, over 4842.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.03351, over 971904.25 frames.], batch size: 26, lr: 2.10e-04
2022-05-06 23:12:23,997 INFO [train.py:715] (4/8) Epoch 10, batch 29650, loss[loss=0.1311, simple_loss=0.2144, pruned_loss=0.02389, over 4916.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03339, over 972154.30 frames.], batch size: 18, lr: 2.10e-04
2022-05-06 23:13:03,432 INFO [train.py:715] (4/8) Epoch 10, batch 29700, loss[loss=0.1224, simple_loss=0.1919, pruned_loss=0.02644, over 4976.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03317, over 971920.92 frames.], batch size: 28, lr: 2.10e-04
2022-05-06 23:13:42,105 INFO [train.py:715] (4/8) Epoch 10, batch 29750, loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.03137, over 4942.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2129, pruned_loss=0.03308, over 972174.26 frames.], batch size: 29, lr: 2.10e-04
2022-05-06 23:14:21,081 INFO [train.py:715] (4/8) Epoch 10, batch 29800, loss[loss=0.159, simple_loss=0.2206, pruned_loss=0.0487, over 4940.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2133, pruned_loss=0.0335, over 972930.62 frames.], batch size: 35, lr: 2.10e-04
2022-05-06 23:15:00,555 INFO [train.py:715] (4/8) Epoch 10, batch 29850, loss[loss=0.1589, simple_loss=0.2301, pruned_loss=0.04382, over 4866.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.0334, over 973141.09 frames.], batch size: 22, lr: 2.10e-04
2022-05-06 23:15:39,438 INFO [train.py:715] (4/8) Epoch 10, batch 29900, loss[loss=0.1172, simple_loss=0.1874, pruned_loss=0.02355, over 4810.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03334, over 973717.98 frames.], batch size: 12, lr: 2.10e-04
2022-05-06 23:16:17,894 INFO [train.py:715] (4/8) Epoch 10, batch 29950, loss[loss=0.1374, simple_loss=0.2236, pruned_loss=0.02564, over 4883.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2129, pruned_loss=0.03319, over 973451.25 frames.], batch size: 22, lr: 2.10e-04
2022-05-06 23:16:57,115 INFO [train.py:715] (4/8) Epoch 10, batch 30000, loss[loss=0.1569, simple_loss=0.235, pruned_loss=0.03943, over 4922.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2125, pruned_loss=0.03266, over 972877.28 frames.], batch size: 23, lr: 2.10e-04
2022-05-06 23:16:57,116 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 23:17:06,541 INFO [train.py:742] (4/8) Epoch 10, validation: loss=0.1063, simple_loss=0.1906, pruned_loss=0.01106, over 914524.00 frames.
2022-05-06 23:17:46,309 INFO [train.py:715] (4/8) Epoch 10, batch 30050, loss[loss=0.1733, simple_loss=0.2421, pruned_loss=0.05226, over 4916.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2125, pruned_loss=0.03259, over 972557.89 frames.], batch size: 17, lr: 2.10e-04
2022-05-06 23:18:25,802 INFO [train.py:715] (4/8) Epoch 10, batch 30100, loss[loss=0.1288, simple_loss=0.2031, pruned_loss=0.02721, over 4773.00 frames.], tot_loss[loss=0.1398, simple_loss=0.213, pruned_loss=0.03332, over 973619.75 frames.], batch size: 14, lr: 2.10e-04
2022-05-06 23:19:04,198 INFO [train.py:715] (4/8) Epoch 10, batch 30150, loss[loss=0.1408, simple_loss=0.2062, pruned_loss=0.03766, over 4929.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03307, over 972859.14 frames.], batch size: 17, lr: 2.10e-04
2022-05-06 23:19:44,548 INFO [train.py:715] (4/8) Epoch 10, batch 30200, loss[loss=0.1609, simple_loss=0.2376, pruned_loss=0.04214, over 4980.00 frames.], tot_loss[loss=0.1399, simple_loss=0.213, pruned_loss=0.03342, over 973345.22 frames.], batch size: 39, lr: 2.10e-04
2022-05-06 23:20:24,571 INFO [train.py:715] (4/8) Epoch 10, batch 30250, loss[loss=0.1101, simple_loss=0.1789, pruned_loss=0.02063, over 4812.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03306, over 972780.37 frames.], batch size: 12, lr: 2.10e-04
2022-05-06 23:21:02,962 INFO [train.py:715] (4/8) Epoch 10, batch 30300, loss[loss=0.1382, simple_loss=0.2244, pruned_loss=0.02598, over 4825.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2116, pruned_loss=0.03311, over 972107.76 frames.], batch size: 26, lr: 2.10e-04
2022-05-06 23:21:41,378 INFO [train.py:715] (4/8) Epoch 10, batch 30350, loss[loss=0.1555, simple_loss=0.2309, pruned_loss=0.04004, over 4972.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.03302, over 972651.32 frames.], batch size: 39, lr: 2.10e-04
2022-05-06 23:22:21,181 INFO [train.py:715] (4/8) Epoch 10, batch 30400, loss[loss=0.1473, simple_loss=0.2104, pruned_loss=0.04212, over 4687.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2109, pruned_loss=0.03273, over 972022.73 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:23:00,548 INFO [train.py:715] (4/8) Epoch 10, batch 30450, loss[loss=0.1729, simple_loss=0.2557, pruned_loss=0.04503, over 4760.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2113, pruned_loss=0.03292, over 972690.27 frames.], batch size: 16, lr: 2.10e-04
2022-05-06 23:23:38,705 INFO [train.py:715] (4/8) Epoch 10, batch 30500, loss[loss=0.1378, simple_loss=0.2104, pruned_loss=0.03263, over 4891.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03304, over 972588.16 frames.], batch size: 17, lr: 2.10e-04
2022-05-06 23:24:18,303 INFO [train.py:715] (4/8) Epoch 10, batch 30550, loss[loss=0.1358, simple_loss=0.1987, pruned_loss=0.03648, over 4861.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03329, over 971908.34 frames.], batch size: 32, lr: 2.10e-04
2022-05-06 23:24:57,943 INFO [train.py:715] (4/8) Epoch 10, batch 30600, loss[loss=0.1299, simple_loss=0.1998, pruned_loss=0.03005, over 4865.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2132, pruned_loss=0.03354, over 971035.86 frames.], batch size: 20, lr: 2.10e-04
2022-05-06 23:25:36,405 INFO [train.py:715] (4/8) Epoch 10, batch 30650, loss[loss=0.1234, simple_loss=0.2027, pruned_loss=0.02204, over 4810.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.03339, over 971041.86 frames.], batch size: 26, lr: 2.10e-04
2022-05-06 23:26:15,885 INFO [train.py:715] (4/8) Epoch 10, batch 30700, loss[loss=0.1466, simple_loss=0.2253, pruned_loss=0.03399, over 4953.00 frames.], tot_loss[loss=0.1389, simple_loss=0.212, pruned_loss=0.03292, over 972125.00 frames.], batch size: 29, lr: 2.10e-04
2022-05-06 23:26:55,009 INFO [train.py:715] (4/8) Epoch 10, batch 30750, loss[loss=0.1053, simple_loss=0.1801, pruned_loss=0.01528, over 4850.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03257, over 970992.27 frames.], batch size: 12, lr: 2.10e-04
2022-05-06 23:27:33,921 INFO [train.py:715] (4/8) Epoch 10, batch 30800, loss[loss=0.1696, simple_loss=0.2464, pruned_loss=0.0464, over 4834.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.03224, over 971134.24 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:28:12,407 INFO [train.py:715] (4/8) Epoch 10, batch 30850, loss[loss=0.1582, simple_loss=0.2264, pruned_loss=0.04502, over 4745.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.0325, over 971442.24 frames.], batch size: 19, lr: 2.10e-04
2022-05-06 23:28:52,165 INFO [train.py:715] (4/8) Epoch 10, batch 30900, loss[loss=0.1375, simple_loss=0.2131, pruned_loss=0.03089, over 4845.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03231, over 971104.19 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:29:32,113 INFO [train.py:715] (4/8) Epoch 10, batch 30950, loss[loss=0.1225, simple_loss=0.2008, pruned_loss=0.02204, over 4977.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2112, pruned_loss=0.03266, over 971821.26 frames.], batch size: 14, lr: 2.10e-04
2022-05-06 23:30:11,643 INFO [train.py:715] (4/8) Epoch 10, batch 31000, loss[loss=0.13, simple_loss=0.2026, pruned_loss=0.02873, over 4778.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03273, over 971541.04 frames.], batch size: 18, lr: 2.10e-04
2022-05-06 23:30:50,320 INFO [train.py:715] (4/8) Epoch 10, batch 31050, loss[loss=0.1502, simple_loss=0.2186, pruned_loss=0.04093, over 4759.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03268, over 971144.29 frames.], batch size: 19, lr: 2.10e-04
2022-05-06 23:31:29,592 INFO [train.py:715] (4/8) Epoch 10, batch 31100, loss[loss=0.1344, simple_loss=0.2187, pruned_loss=0.02501, over 4809.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2125, pruned_loss=0.03282, over 971745.47 frames.], batch size: 25, lr: 2.10e-04
2022-05-06 23:32:09,327 INFO [train.py:715] (4/8) Epoch 10, batch 31150, loss[loss=0.127, simple_loss=0.1974, pruned_loss=0.02834, over 4955.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2134, pruned_loss=0.0331, over 970974.44 frames.], batch size: 24, lr: 2.10e-04
2022-05-06 23:32:47,335 INFO [train.py:715] (4/8) Epoch 10, batch 31200, loss[loss=0.1364, simple_loss=0.204, pruned_loss=0.0344, over 4786.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2134, pruned_loss=0.03338, over 970774.45 frames.], batch size: 17, lr: 2.10e-04
2022-05-06 23:33:26,827 INFO [train.py:715] (4/8) Epoch 10, batch 31250, loss[loss=0.1434, simple_loss=0.2112, pruned_loss=0.0378, over 4905.00 frames.], tot_loss[loss=0.1407, simple_loss=0.214, pruned_loss=0.03372, over 971126.04 frames.], batch size: 17, lr: 2.10e-04
2022-05-06 23:34:06,251 INFO [train.py:715] (4/8) Epoch 10, batch 31300, loss[loss=0.156, simple_loss=0.2287, pruned_loss=0.04161, over 4870.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2138, pruned_loss=0.03368, over 972313.67 frames.], batch size: 22, lr: 2.10e-04
2022-05-06 23:34:45,238 INFO [train.py:715] (4/8) Epoch 10, batch 31350, loss[loss=0.1275, simple_loss=0.1942, pruned_loss=0.03036, over 4855.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2133, pruned_loss=0.03348, over 972010.99 frames.], batch size: 16, lr: 2.10e-04
2022-05-06 23:35:23,741 INFO [train.py:715] (4/8) Epoch 10, batch 31400, loss[loss=0.1477, simple_loss=0.2184, pruned_loss=0.03844, over 4962.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2136, pruned_loss=0.03362, over 972504.59 frames.], batch size: 39, lr: 2.10e-04
2022-05-06 23:36:02,748 INFO [train.py:715] (4/8) Epoch 10, batch 31450, loss[loss=0.1383, simple_loss=0.2122, pruned_loss=0.03215, over 4988.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2137, pruned_loss=0.03356, over 972900.53 frames.], batch size: 14, lr: 2.10e-04
2022-05-06 23:36:42,176 INFO [train.py:715] (4/8) Epoch 10, batch 31500, loss[loss=0.1246, simple_loss=0.2075, pruned_loss=0.02083, over 4699.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2136, pruned_loss=0.03375, over 972727.93 frames.], batch size: 15, lr: 2.10e-04
2022-05-06 23:37:19,853 INFO [train.py:715] (4/8) Epoch 10, batch 31550, loss[loss=0.138, simple_loss=0.2126, pruned_loss=0.03171, over 4850.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2137, pruned_loss=0.03387, over 973597.65 frames.], batch size: 20, lr: 2.10e-04
2022-05-06 23:37:58,955 INFO [train.py:715] (4/8) Epoch 10, batch 31600, loss[loss=0.1628, simple_loss=0.228, pruned_loss=0.04881, over 4887.00 frames.], tot_loss[loss=0.1415, simple_loss=0.214, pruned_loss=0.03447, over 973803.57 frames.], batch size: 39, lr: 2.10e-04
2022-05-06 23:38:38,095 INFO [train.py:715] (4/8) Epoch 10, batch 31650, loss[loss=0.1557, simple_loss=0.2241, pruned_loss=0.0437, over 4758.00 frames.], tot_loss[loss=0.142, simple_loss=0.2144, pruned_loss=0.03473, over 973723.52 frames.], batch size: 19, lr: 2.10e-04
2022-05-06 23:39:17,242 INFO [train.py:715] (4/8) Epoch 10, batch 31700, loss[loss=0.1556, simple_loss=0.2241, pruned_loss=0.04353, over 4972.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2141, pruned_loss=0.03415, over 973013.58 frames.], batch size: 33, lr: 2.10e-04
2022-05-06 23:39:55,909 INFO [train.py:715] (4/8) Epoch 10, batch 31750, loss[loss=0.1552, simple_loss=0.2306, pruned_loss=0.03985, over 4883.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03427, over 973230.45 frames.], batch size: 22, lr: 2.10e-04
2022-05-06 23:40:34,951 INFO [train.py:715] (4/8) Epoch 10, batch 31800, loss[loss=0.1274, simple_loss=0.2103, pruned_loss=0.02229, over 4808.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2138, pruned_loss=0.03389, over 972567.99 frames.], batch size: 21, lr: 2.10e-04
2022-05-06 23:41:14,307 INFO [train.py:715] (4/8) Epoch 10, batch 31850, loss[loss=0.1589, simple_loss=0.2408, pruned_loss=0.03853, over 4942.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2142, pruned_loss=0.03414, over 972839.70 frames.], batch size: 23, lr: 2.10e-04
2022-05-06 23:41:52,372 INFO [train.py:715] (4/8) Epoch 10, batch 31900, loss[loss=0.1483, simple_loss=0.2338, pruned_loss=0.03142, over 4790.00 frames.], tot_loss[loss=0.141, simple_loss=0.2141, pruned_loss=0.03396, over 972076.91 frames.], batch size: 18, lr: 2.10e-04
2022-05-06 23:42:31,526 INFO [train.py:715] (4/8) Epoch 10, batch 31950, loss[loss=0.1398, simple_loss=0.2043, pruned_loss=0.03762, over 4967.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03363, over 972400.77 frames.], batch size: 24, lr: 2.10e-04
2022-05-06 23:43:10,931 INFO [train.py:715] (4/8) Epoch 10, batch 32000, loss[loss=0.1353, simple_loss=0.2101, pruned_loss=0.03024, over 4980.00 frames.], tot_loss[loss=0.1406, simple_loss=0.2135, pruned_loss=0.03386, over 973698.51 frames.], batch size: 28, lr: 2.10e-04
2022-05-06 23:43:49,599 INFO [train.py:715] (4/8) Epoch 10, batch 32050, loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03407, over 4752.00 frames.], tot_loss[loss=0.14, simple_loss=0.2127, pruned_loss=0.03362, over 973704.64 frames.], batch size: 16, lr: 2.10e-04
2022-05-06 23:44:27,917 INFO [train.py:715] (4/8) Epoch 10, batch 32100, loss[loss=0.1208, simple_loss=0.1983, pruned_loss=0.02166, over 4806.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2113, pruned_loss=0.03308, over 972247.11 frames.], batch size: 12, lr: 2.10e-04
2022-05-06 23:45:06,913 INFO [train.py:715] (4/8) Epoch 10, batch 32150, loss[loss=0.1564, simple_loss=0.2291, pruned_loss=0.04185, over 4784.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2114, pruned_loss=0.03311, over 972127.17 frames.], batch size: 17, lr: 2.10e-04
2022-05-06 23:45:45,854 INFO [train.py:715] (4/8) Epoch 10, batch 32200, loss[loss=0.1555, simple_loss=0.2275, pruned_loss=0.04173, over 4855.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03319, over 971160.29 frames.], batch size: 13, lr: 2.10e-04
2022-05-06 23:46:23,727 INFO [train.py:715] (4/8) Epoch 10, batch 32250, loss[loss=0.1445, simple_loss=0.2191, pruned_loss=0.03498, over 4985.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03319, over 971692.14 frames.], batch size: 28, lr: 2.10e-04
2022-05-06 23:47:02,887 INFO [train.py:715] (4/8) Epoch 10, batch 32300, loss[loss=0.1663, simple_loss=0.2228, pruned_loss=0.05487, over 4843.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2133, pruned_loss=0.03356, over 971377.48 frames.], batch size: 30, lr: 2.10e-04
2022-05-06 23:47:42,100 INFO [train.py:715] (4/8) Epoch 10, batch 32350, loss[loss=0.1124, simple_loss=0.1899, pruned_loss=0.01749, over 4727.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2131, pruned_loss=0.03317, over 971097.73 frames.], batch size: 12, lr: 2.10e-04
2022-05-06 23:48:20,901 INFO [train.py:715] (4/8) Epoch 10, batch 32400, loss[loss=0.1265, simple_loss=0.1978, pruned_loss=0.02757, over 4843.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03302, over 971349.14 frames.], batch size: 30, lr: 2.10e-04
2022-05-06 23:48:59,312 INFO [train.py:715] (4/8) Epoch 10, batch 32450, loss[loss=0.1563, simple_loss=0.2366, pruned_loss=0.03797, over 4772.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03294, over 970478.05 frames.], batch size: 19, lr: 2.10e-04
2022-05-06 23:49:38,631 INFO [train.py:715] (4/8) Epoch 10, batch 32500, loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03114, over 4782.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03294, over 970886.58 frames.], batch size: 18, lr: 2.10e-04
2022-05-06 23:50:18,347 INFO [train.py:715] (4/8) Epoch 10, batch 32550, loss[loss=0.1101, simple_loss=0.179, pruned_loss=0.02066, over 4919.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03243, over 970588.72 frames.], batch size: 29, lr: 2.10e-04
2022-05-06 23:50:56,262 INFO [train.py:715] (4/8) Epoch 10, batch 32600, loss[loss=0.1579, simple_loss=0.2341, pruned_loss=0.04083, over 4809.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03262, over 971739.59 frames.], batch size: 21, lr: 2.10e-04
2022-05-06 23:51:35,797 INFO [train.py:715] (4/8) Epoch 10, batch 32650, loss[loss=0.1213, simple_loss=0.1976, pruned_loss=0.02252, over 4806.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03293, over 971292.88 frames.], batch size: 14, lr: 2.10e-04
2022-05-06 23:52:15,565 INFO [train.py:715] (4/8) Epoch 10, batch 32700, loss[loss=0.1336, simple_loss=0.2099, pruned_loss=0.02863, over 4793.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.03291, over 971801.83 frames.], batch size: 24, lr: 2.09e-04
2022-05-06 23:52:53,820 INFO [train.py:715] (4/8) Epoch 10, batch 32750, loss[loss=0.1232, simple_loss=0.2059, pruned_loss=0.02023, over 4939.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.033, over 971578.26 frames.], batch size: 23, lr: 2.09e-04
2022-05-06 23:53:34,507 INFO [train.py:715] (4/8) Epoch 10, batch 32800, loss[loss=0.1153, simple_loss=0.1906, pruned_loss=0.01997, over 4931.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03252, over 971441.50 frames.], batch size: 18, lr: 2.09e-04
2022-05-06 23:54:14,772 INFO [train.py:715] (4/8) Epoch 10, batch 32850, loss[loss=0.1406, simple_loss=0.2092, pruned_loss=0.03599, over 4867.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03231, over 970738.94 frames.], batch size: 34, lr: 2.09e-04
2022-05-06 23:54:54,885 INFO [train.py:715] (4/8) Epoch 10, batch 32900, loss[loss=0.1297, simple_loss=0.2024, pruned_loss=0.02849, over 4970.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2107, pruned_loss=0.03228, over 972168.86 frames.], batch size: 24, lr: 2.09e-04
2022-05-06 23:55:34,227 INFO [train.py:715] (4/8) Epoch 10, batch 32950, loss[loss=0.1416, simple_loss=0.2177, pruned_loss=0.0327, over 4887.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03184, over 972082.90 frames.], batch size: 19, lr: 2.09e-04
2022-05-06 23:56:14,908 INFO [train.py:715] (4/8) Epoch 10, batch 33000, loss[loss=0.1409, simple_loss=0.2085, pruned_loss=0.03661, over 4870.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03251, over 971299.35 frames.], batch size: 32, lr: 2.09e-04
2022-05-06 23:56:14,909 INFO [train.py:733] (4/8) Computing validation loss
2022-05-06 23:56:24,575 INFO [train.py:742] (4/8) Epoch 10, validation: loss=0.1063, simple_loss=0.1905, pruned_loss=0.01103, over 914524.00 frames.
2022-05-06 23:57:03,962 INFO [train.py:715] (4/8) Epoch 10, batch 33050, loss[loss=0.1883, simple_loss=0.25, pruned_loss=0.06326, over 4830.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03289, over 971370.34 frames.], batch size: 15, lr: 2.09e-04
2022-05-06 23:57:43,741 INFO [train.py:715] (4/8) Epoch 10, batch 33100, loss[loss=0.1367, simple_loss=0.2113, pruned_loss=0.03101, over 4820.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.03352, over 971669.79 frames.], batch size: 13, lr: 2.09e-04
2022-05-06 23:58:21,690 INFO [train.py:715] (4/8) Epoch 10, batch 33150, loss[loss=0.1374, simple_loss=0.2139, pruned_loss=0.03049, over 4866.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2137, pruned_loss=0.03325, over 971863.72 frames.], batch size: 22, lr: 2.09e-04
2022-05-06 23:59:00,823 INFO [train.py:715] (4/8) Epoch 10, batch 33200, loss[loss=0.1283, simple_loss=0.2006, pruned_loss=0.02805, over 4850.00 frames.], tot_loss[loss=0.14, simple_loss=0.2135, pruned_loss=0.03324, over 972438.35 frames.], batch size: 32, lr: 2.09e-04
2022-05-06 23:59:40,446 INFO [train.py:715] (4/8) Epoch 10, batch 33250, loss[loss=0.1538, simple_loss=0.2152, pruned_loss=0.04624, over 4835.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2144, pruned_loss=0.03362, over 972648.14 frames.], batch size: 15, lr: 2.09e-04
2022-05-07 00:00:18,362 INFO [train.py:715] (4/8) Epoch 10, batch 33300, loss[loss=0.1421, simple_loss=0.2102, pruned_loss=0.03699, over 4895.00 frames.], tot_loss[loss=0.1415, simple_loss=0.2149, pruned_loss=0.03408, over 972285.19 frames.], batch size: 19, lr: 2.09e-04
2022-05-07 00:00:57,772 INFO [train.py:715] (4/8) Epoch 10, batch 33350, loss[loss=0.1536, simple_loss=0.2214, pruned_loss=0.04287, over 4701.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2142, pruned_loss=0.03421, over 972359.52 frames.], batch size: 15, lr: 2.09e-04
2022-05-07 00:01:37,018 INFO [train.py:715] (4/8) Epoch 10, batch 33400, loss[loss=0.1447, simple_loss=0.2138, pruned_loss=0.03774, over 4691.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2135, pruned_loss=0.03359, over 971365.55 frames.], batch size: 15, lr: 2.09e-04
2022-05-07 00:02:16,545 INFO [train.py:715] (4/8) Epoch 10, batch 33450, loss[loss=0.1312, simple_loss=0.2136, pruned_loss=0.02441, over 4869.00 frames.], tot_loss[loss=0.141, simple_loss=0.2141, pruned_loss=0.03393, over 971619.31 frames.], batch size: 20, lr: 2.09e-04
2022-05-07 00:02:54,364 INFO [train.py:715] (4/8) Epoch 10, batch 33500, loss[loss=0.1614, simple_loss=0.2318, pruned_loss=0.04544, over 4953.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2142, pruned_loss=0.03384, over 972127.92 frames.], batch size: 39, lr: 2.09e-04
2022-05-07 00:03:33,960 INFO [train.py:715] (4/8) Epoch 10, batch 33550, loss[loss=0.1569, simple_loss=0.234, pruned_loss=0.03992, over 4899.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2137, pruned_loss=0.03365, over 971888.73 frames.], batch size: 19, lr: 2.09e-04
2022-05-07 00:04:13,562 INFO [train.py:715] (4/8) Epoch 10, batch 33600, loss[loss=0.1991, simple_loss=0.2593, pruned_loss=0.0695, over 4918.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2138, pruned_loss=0.03379, over 972888.20 frames.], batch size: 18, lr: 2.09e-04
2022-05-07 00:04:52,114 INFO [train.py:715] (4/8) Epoch 10, batch 33650, loss[loss=0.1344, simple_loss=0.2001, pruned_loss=0.03438, over 4932.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2137, pruned_loss=0.03345, over 972672.72 frames.], batch size: 35, lr: 2.09e-04
2022-05-07 00:05:30,843 INFO [train.py:715] (4/8) Epoch 10, batch 33700, loss[loss=0.1449, simple_loss=0.2033, pruned_loss=0.04328, over 4785.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2132, pruned_loss=0.0335, over 973177.77 frames.], batch size: 14, lr: 2.09e-04
2022-05-07 00:06:10,497 INFO [train.py:715] (4/8) Epoch 10, batch 33750, loss[loss=0.1968, simple_loss=0.2608, pruned_loss=0.06637, over 4977.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2126, pruned_loss=0.03333, over 973284.73 frames.], batch size: 15, lr: 2.09e-04
2022-05-07 00:06:50,168 INFO [train.py:715] (4/8) Epoch 10, batch 33800, loss[loss=0.1529, simple_loss=0.2262, pruned_loss=0.03976, over 4849.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03344, over 972713.16 frames.], batch size: 15, lr: 2.09e-04
2022-05-07 00:07:29,175 INFO [train.py:715] (4/8) Epoch 10, batch 33850, loss[loss=0.1459, simple_loss=0.2048, pruned_loss=0.04348, over 4780.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03351, over 973351.74 frames.], batch size: 17, lr: 2.09e-04
2022-05-07 00:08:08,839 INFO [train.py:715] (4/8) Epoch 10, batch 33900, loss[loss=0.1394, simple_loss=0.2269, pruned_loss=0.02593, over 4831.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03356, over 972892.43 frames.], batch size: 26, lr: 2.09e-04
2022-05-07 00:08:48,748 INFO [train.py:715] (4/8) Epoch 10, batch 33950, loss[loss=0.1449, simple_loss=0.2168, pruned_loss=0.03651, over 4707.00 frames.], tot_loss[loss=0.1404, simple_loss=0.213, pruned_loss=0.03387, over 973119.68 frames.], batch size: 15, lr: 2.09e-04
2022-05-07 00:09:27,305 INFO [train.py:715] (4/8) Epoch 10, batch 34000, loss[loss=0.1366, simple_loss=0.2097, pruned_loss=0.03171, over 4881.00 frames.], tot_loss[loss=0.141, simple_loss=0.2134, pruned_loss=0.03428, over 973562.19 frames.], batch size: 20, lr: 2.09e-04
2022-05-07 00:10:06,615 INFO [train.py:715] (4/8) Epoch 10, batch 34050, loss[loss=0.1215, simple_loss=0.196, pruned_loss=0.02349, over 4768.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2133, pruned_loss=0.03411, over 973474.03 frames.], batch size: 17, lr: 2.09e-04
2022-05-07 00:10:45,875 INFO [train.py:715] (4/8) Epoch 10, batch 34100, loss[loss=0.1408, simple_loss=0.2163, pruned_loss=0.03264, over 4898.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2139, pruned_loss=0.03414, over 972428.50 frames.], batch size: 19, lr: 2.09e-04
2022-05-07 00:11:25,377 INFO [train.py:715] (4/8) Epoch 10, batch 34150, loss[loss=0.1235, simple_loss=0.2054, pruned_loss=0.02076, over 4748.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2132, pruned_loss=0.03377, over 972837.32 frames.], batch size: 19, lr: 2.09e-04
2022-05-07 00:12:04,942 INFO [train.py:715] (4/8) Epoch 10, batch 34200, loss[loss=0.1382, simple_loss=0.2263, pruned_loss=0.02507, over 4975.00 frames.], tot_loss[loss=0.1408, simple_loss=0.2142, pruned_loss=0.03369, over 972457.05 frames.], batch size: 24, lr: 2.09e-04
2022-05-07 00:12:44,144 INFO [train.py:715] (4/8) Epoch 10, batch 34250, loss[loss=0.1443, simple_loss=0.2132, pruned_loss=0.03773, over 4936.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2141, pruned_loss=0.03391, over 973195.81 frames.], batch size: 21, lr: 2.09e-04
2022-05-07 00:13:23,643 INFO [train.py:715] (4/8) Epoch 10, batch 34300, loss[loss=0.1461, simple_loss=0.219, pruned_loss=0.03659, over 4875.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03421, over 973063.39 frames.], batch size: 32, lr: 2.09e-04
2022-05-07 00:14:03,553 INFO [train.py:715] (4/8) Epoch 10, batch 34350, loss[loss=0.1235, simple_loss=0.1977, pruned_loss=0.02462, over 4796.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2133, pruned_loss=0.03404, over 972797.69 frames.], batch size: 12, lr: 2.09e-04
2022-05-07 00:14:43,433 INFO [train.py:715] (4/8) Epoch 10, batch 34400, loss[loss=0.1277, simple_loss=0.2029, pruned_loss=0.02624, over 4814.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2136, pruned_loss=0.03438, over 972062.40 frames.], batch size: 27, lr: 2.09e-04
2022-05-07 00:15:23,583 INFO [train.py:715] (4/8) Epoch 10, batch 34450, loss[loss=0.1336, simple_loss=0.2119, pruned_loss=0.02768, over 4767.00 frames.], tot_loss[loss=0.1413, simple_loss=0.2138, pruned_loss=0.03442, over 971832.40 frames.], batch size: 19, lr: 2.09e-04
2022-05-07 00:16:03,652 INFO [train.py:715] (4/8) Epoch 10, batch 34500, loss[loss=0.1597, simple_loss=0.2298, pruned_loss=0.04481, over 4926.00 frames.], tot_loss[loss=0.1423, simple_loss=0.2146, pruned_loss=0.03496, over 971512.12 frames.], batch size: 18, lr: 2.09e-04
2022-05-07 00:16:42,849 INFO [train.py:715] (4/8) Epoch 10, batch 34550, loss[loss=0.1269, simple_loss=0.194, pruned_loss=0.02996, over 4876.00 frames.], tot_loss[loss=0.1419, simple_loss=0.2142, pruned_loss=0.03484, over 971560.97 frames.], batch size: 16, lr: 2.09e-04
2022-05-07 00:17:23,151 INFO [train.py:715] (4/8) Epoch 10, batch 34600, loss[loss=0.1337, simple_loss=0.2088, pruned_loss=0.02929, over 4682.00 frames.], tot_loss[loss=0.1416, simple_loss=0.2145, pruned_loss=0.0344, over 970975.23 frames.], batch size: 15, lr: 2.09e-04
2022-05-07 00:18:03,610 INFO [train.py:715] (4/8) Epoch 10, batch 34650, loss[loss=0.1458, simple_loss=0.2237, pruned_loss=0.03389, over 4825.00 frames.], tot_loss[loss=0.1414, simple_loss=0.2142, pruned_loss=0.03426, over 970529.65 frames.], batch size: 25, lr: 2.09e-04
2022-05-07 00:18:42,654 INFO [train.py:715] (4/8) Epoch 10, batch 34700, loss[loss=0.111, simple_loss=0.1817, pruned_loss=0.02015, over 4862.00 frames.], tot_loss[loss=0.1417, simple_loss=0.2147, pruned_loss=0.03432, over 971111.92 frames.], batch size: 20, lr: 2.09e-04
2022-05-07 00:19:21,232 INFO [train.py:715] (4/8) Epoch 10, batch 34750, loss[loss=0.1815, simple_loss=0.2396, pruned_loss=0.06166, over 4848.00 frames.], tot_loss[loss=0.1411, simple_loss=0.2142, pruned_loss=0.03397, over 972125.38 frames.], batch size: 32, lr: 2.09e-04
2022-05-07 00:19:57,689 INFO [train.py:715] (4/8) Epoch 10, batch 34800, loss[loss=0.1199, simple_loss=0.1892, pruned_loss=0.02528, over 4837.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.03403, over 971679.01 frames.], batch size: 12, lr: 2.09e-04
2022-05-07 00:20:47,595 INFO [train.py:715] (4/8) Epoch 11, batch 0, loss[loss=0.1175, simple_loss=0.1822, pruned_loss=0.02636, over 4801.00 frames.], tot_loss[loss=0.1175, simple_loss=0.1822, pruned_loss=0.02636, over 4801.00 frames.], batch size: 12, lr: 2.00e-04
2022-05-07 00:21:26,499 INFO [train.py:715] (4/8) Epoch 11, batch 50, loss[loss=0.1424, simple_loss=0.2082, pruned_loss=0.03831, over 4912.00 frames.], tot_loss[loss=0.1418, simple_loss=0.2143, pruned_loss=0.0347, over 219971.47 frames.], batch size: 17, lr: 2.00e-04
2022-05-07 00:22:06,398 INFO [train.py:715] (4/8) Epoch 11, batch 100, loss[loss=0.1508, simple_loss=0.2312, pruned_loss=0.03526, over 4686.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2113, pruned_loss=0.03299, over 386630.31 frames.], batch size: 15, lr: 2.00e-04
2022-05-07 00:22:46,272 INFO [train.py:715] (4/8) Epoch 11, batch 150, loss[loss=0.1218, simple_loss=0.1981, pruned_loss=0.02279, over 4895.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2102, pruned_loss=0.03223, over 515936.24 frames.], batch size: 22, lr: 2.00e-04
2022-05-07 00:23:26,825 INFO [train.py:715] (4/8) Epoch 11, batch 200, loss[loss=0.1294, simple_loss=0.2104, pruned_loss=0.02417, over 4966.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03256, over 617502.28 frames.], batch size: 24, lr: 2.00e-04
2022-05-07 00:24:06,700 INFO [train.py:715] (4/8) Epoch 11, batch 250, loss[loss=0.1244, simple_loss=0.198, pruned_loss=0.02541, over 4665.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2127, pruned_loss=0.03316, over 696443.72 frames.], batch size: 13, lr: 2.00e-04
2022-05-07 00:24:45,518 INFO [train.py:715] (4/8) Epoch 11, batch 300, loss[loss=0.1306, simple_loss=0.2001, pruned_loss=0.03058, over 4948.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03325, over 757990.06 frames.], batch size: 21, lr: 2.00e-04
2022-05-07 00:25:26,105 INFO [train.py:715] (4/8) Epoch 11, batch 350, loss[loss=0.1333, simple_loss=0.1964, pruned_loss=0.03508, over 4800.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03346, over 805855.09 frames.], batch size: 14, lr: 2.00e-04
2022-05-07 00:26:05,770 INFO [train.py:715] (4/8) Epoch 11, batch 400, loss[loss=0.1368, simple_loss=0.2087, pruned_loss=0.03248, over 4753.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03326, over 842343.48 frames.], batch size: 19, lr: 2.00e-04
2022-05-07 00:26:46,471 INFO [train.py:715] (4/8) Epoch 11, batch 450, loss[loss=0.143, simple_loss=0.2115, pruned_loss=0.03725, over 4922.00 frames.], tot_loss[loss=0.1403, simple_loss=0.213, pruned_loss=0.03385, over 872334.89 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 00:27:27,794 INFO [train.py:715] (4/8) Epoch 11, batch 500, loss[loss=0.1393, simple_loss=0.2212, pruned_loss=0.02877, over 4861.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2124, pruned_loss=0.03345, over 895093.38 frames.], batch size: 22, lr: 2.00e-04
2022-05-07 00:28:09,387 INFO [train.py:715] (4/8) Epoch 11, batch 550, loss[loss=0.112, simple_loss=0.1857, pruned_loss=0.01915, over 4793.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03351, over 912609.17 frames.], batch size: 14, lr: 2.00e-04
2022-05-07 00:28:50,703 INFO [train.py:715] (4/8) Epoch 11, batch 600, loss[loss=0.1457, simple_loss=0.2087, pruned_loss=0.04136, over 4870.00 frames.], tot_loss[loss=0.1402, simple_loss=0.213, pruned_loss=0.03373, over 926530.22 frames.], batch size: 20, lr: 2.00e-04
2022-05-07 00:29:32,044 INFO [train.py:715] (4/8) Epoch 11, batch 650, loss[loss=0.1285, simple_loss=0.192, pruned_loss=0.0325, over 4843.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2125, pruned_loss=0.03318, over 936833.17 frames.], batch size: 15, lr: 2.00e-04
2022-05-07 00:30:13,310 INFO [train.py:715] (4/8) Epoch 11, batch 700, loss[loss=0.1306, simple_loss=0.2135, pruned_loss=0.02384, over 4851.00 frames.], tot_loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03354, over 945171.56 frames.], batch size: 20, lr: 2.00e-04
2022-05-07 00:30:54,875 INFO [train.py:715] (4/8) Epoch 11, batch 750, loss[loss=0.1334, simple_loss=0.2189, pruned_loss=0.02398, over 4890.00 frames.], tot_loss[loss=0.1398, simple_loss=0.213, pruned_loss=0.03334, over 950933.18 frames.], batch size: 22, lr: 2.00e-04
2022-05-07 00:31:36,033 INFO [train.py:715] (4/8) Epoch 11, batch 800, loss[loss=0.1597, simple_loss=0.2139, pruned_loss=0.05276, over 4786.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2126, pruned_loss=0.03356, over 954943.96 frames.], batch size: 12, lr: 2.00e-04
2022-05-07 00:32:16,765 INFO [train.py:715] (4/8) Epoch 11, batch 850, loss[loss=0.1506, simple_loss=0.2278, pruned_loss=0.03675, over 4903.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2124, pruned_loss=0.03356, over 958748.32 frames.], batch size: 39, lr: 2.00e-04
2022-05-07 00:32:58,355 INFO [train.py:715] (4/8) Epoch 11, batch 900, loss[loss=0.1186, simple_loss=0.188, pruned_loss=0.02461, over 4787.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2114, pruned_loss=0.03296, over 961234.49 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 00:33:38,986 INFO [train.py:715] (4/8) Epoch 11, batch 950, loss[loss=0.1524, simple_loss=0.2289, pruned_loss=0.03795, over 4946.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2115, pruned_loss=0.0331, over 962504.26 frames.], batch size: 21, lr: 2.00e-04
2022-05-07 00:34:19,479 INFO [train.py:715] (4/8) Epoch 11, batch 1000, loss[loss=0.1384, simple_loss=0.2191, pruned_loss=0.02885, over 4820.00 frames.], tot_loss[loss=0.139, simple_loss=0.2116, pruned_loss=0.03324, over 964224.82 frames.], batch size: 21, lr: 2.00e-04
2022-05-07 00:34:58,891 INFO [train.py:715] (4/8) Epoch 11, batch 1050, loss[loss=0.1384, simple_loss=0.2122, pruned_loss=0.03223, over 4778.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2114, pruned_loss=0.03323, over 965983.71 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 00:35:41,049 INFO [train.py:715] (4/8) Epoch 11, batch 1100, loss[loss=0.1485, simple_loss=0.2075, pruned_loss=0.04473, over 4841.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2104, pruned_loss=0.03265, over 967974.89 frames.], batch size: 32, lr: 2.00e-04
2022-05-07 00:36:20,719 INFO [train.py:715] (4/8) Epoch 11, batch 1150, loss[loss=0.118, simple_loss=0.1926, pruned_loss=0.02172, over 4818.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2109, pruned_loss=0.03283, over 968416.30 frames.], batch size: 26, lr: 2.00e-04
2022-05-07 00:37:00,329 INFO [train.py:715] (4/8) Epoch 11, batch 1200, loss[loss=0.121, simple_loss=0.1854, pruned_loss=0.02833, over 4957.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2114, pruned_loss=0.03302, over 968755.38 frames.], batch size: 21, lr: 2.00e-04
2022-05-07 00:37:39,164 INFO [train.py:715] (4/8) Epoch 11, batch 1250, loss[loss=0.1263, simple_loss=0.1999, pruned_loss=0.02637, over 4823.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2114, pruned_loss=0.03309, over 969423.25 frames.], batch size: 13, lr: 2.00e-04
2022-05-07 00:38:18,007 INFO [train.py:715] (4/8) Epoch 11, batch 1300, loss[loss=0.1149, simple_loss=0.1884, pruned_loss=0.02072, over 4815.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2121, pruned_loss=0.03356, over 970332.98 frames.], batch size: 26, lr: 2.00e-04
2022-05-07 00:38:56,861 INFO [train.py:715] (4/8) Epoch 11, batch 1350, loss[loss=0.1388, simple_loss=0.2196, pruned_loss=0.02902, over 4861.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.03301, over 970314.07 frames.], batch size: 20, lr: 2.00e-04
2022-05-07 00:39:35,883 INFO [train.py:715] (4/8) Epoch 11, batch 1400, loss[loss=0.1212, simple_loss=0.1998, pruned_loss=0.02133, over 4835.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2125, pruned_loss=0.03349, over 970937.19 frames.], batch size: 26, lr: 2.00e-04
2022-05-07 00:40:14,713 INFO [train.py:715] (4/8) Epoch 11, batch 1450, loss[loss=0.1266, simple_loss=0.1968, pruned_loss=0.02819, over 4901.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03345, over 971473.27 frames.], batch size: 22, lr: 2.00e-04
2022-05-07 00:40:53,348 INFO [train.py:715] (4/8) Epoch 11, batch 1500, loss[loss=0.1448, simple_loss=0.2267, pruned_loss=0.03147, over 4949.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2136, pruned_loss=0.03369, over 971944.22 frames.], batch size: 21, lr: 2.00e-04
2022-05-07 00:41:31,713 INFO [train.py:715] (4/8) Epoch 11, batch 1550, loss[loss=0.1424, simple_loss=0.2189, pruned_loss=0.03299, over 4818.00 frames.], tot_loss[loss=0.14, simple_loss=0.2131, pruned_loss=0.03342, over 971716.79 frames.], batch size: 26, lr: 2.00e-04
2022-05-07 00:42:10,771 INFO [train.py:715] (4/8) Epoch 11, batch 1600, loss[loss=0.1033, simple_loss=0.1725, pruned_loss=0.01709, over 4984.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03321, over 972522.96 frames.], batch size: 25, lr: 2.00e-04
2022-05-07 00:42:49,741 INFO [train.py:715] (4/8) Epoch 11, batch 1650, loss[loss=0.1817, simple_loss=0.2342, pruned_loss=0.06464, over 4771.00 frames.], tot_loss[loss=0.14, simple_loss=0.213, pruned_loss=0.0335, over 972696.72 frames.], batch size: 19, lr: 2.00e-04
2022-05-07 00:43:28,109 INFO [train.py:715] (4/8) Epoch 11, batch 1700, loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02961, over 4755.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03321, over 972310.87 frames.], batch size: 14, lr: 2.00e-04
2022-05-07 00:44:07,378 INFO [train.py:715] (4/8) Epoch 11, batch 1750, loss[loss=0.1325, simple_loss=0.2054, pruned_loss=0.02984, over 4700.00 frames.], tot_loss[loss=0.138, simple_loss=0.2108, pruned_loss=0.03262, over 973116.41 frames.], batch size: 15, lr: 2.00e-04
2022-05-07 00:44:46,270 INFO [train.py:715] (4/8) Epoch 11, batch 1800, loss[loss=0.13, simple_loss=0.2044, pruned_loss=0.02779, over 4815.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2105, pruned_loss=0.03245, over 972601.42 frames.], batch size: 25, lr: 2.00e-04
2022-05-07 00:45:25,302 INFO [train.py:715] (4/8) Epoch 11, batch 1850, loss[loss=0.1585, simple_loss=0.2209, pruned_loss=0.04803, over 4921.00 frames.], tot_loss[loss=0.138, simple_loss=0.211, pruned_loss=0.03249, over 973367.31 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 00:46:04,484 INFO [train.py:715] (4/8) Epoch 11, batch 1900, loss[loss=0.1377, simple_loss=0.2072, pruned_loss=0.03411, over 4850.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2108, pruned_loss=0.03286, over 972200.11 frames.], batch size: 30, lr: 2.00e-04
2022-05-07 00:46:43,764 INFO [train.py:715] (4/8) Epoch 11, batch 1950, loss[loss=0.1174, simple_loss=0.1821, pruned_loss=0.02632, over 4752.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2102, pruned_loss=0.03264, over 972199.47 frames.], batch size: 19, lr: 2.00e-04
2022-05-07 00:47:23,299 INFO [train.py:715] (4/8) Epoch 11, batch 2000, loss[loss=0.1354, simple_loss=0.2081, pruned_loss=0.0314, over 4958.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.03287, over 971995.80 frames.], batch size: 21, lr: 2.00e-04
2022-05-07 00:48:01,929 INFO [train.py:715] (4/8) Epoch 11, batch 2050, loss[loss=0.1272, simple_loss=0.1982, pruned_loss=0.02806, over 4920.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03312, over 972313.65 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 00:48:41,072 INFO [train.py:715] (4/8) Epoch 11, batch 2100, loss[loss=0.1464, simple_loss=0.2241, pruned_loss=0.03435, over 4937.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03322, over 971511.16 frames.], batch size: 39, lr: 2.00e-04
2022-05-07 00:49:20,361 INFO [train.py:715] (4/8) Epoch 11, batch 2150, loss[loss=0.1217, simple_loss=0.1858, pruned_loss=0.02886, over 4823.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.03362, over 971433.80 frames.], batch size: 15, lr: 2.00e-04
2022-05-07 00:49:59,563 INFO [train.py:715] (4/8) Epoch 11, batch 2200, loss[loss=0.1279, simple_loss=0.2013, pruned_loss=0.02731, over 4818.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03309, over 971814.65 frames.], batch size: 25, lr: 2.00e-04
2022-05-07 00:50:38,221 INFO [train.py:715] (4/8) Epoch 11, batch 2250, loss[loss=0.1755, simple_loss=0.2397, pruned_loss=0.05569, over 4897.00 frames.], tot_loss[loss=0.139, simple_loss=0.2119, pruned_loss=0.033, over 972364.28 frames.], batch size: 17, lr: 2.00e-04
2022-05-07 00:51:17,279 INFO [train.py:715] (4/8) Epoch 11, batch 2300, loss[loss=0.134, simple_loss=0.2102, pruned_loss=0.02888, over 4809.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03321, over 972094.45 frames.], batch size: 21, lr: 2.00e-04
2022-05-07 00:51:56,680 INFO [train.py:715] (4/8) Epoch 11, batch 2350, loss[loss=0.1474, simple_loss=0.2258, pruned_loss=0.03445, over 4898.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.03349, over 972889.24 frames.], batch size: 19, lr: 2.00e-04
2022-05-07 00:52:35,082 INFO [train.py:715] (4/8) Epoch 11, batch 2400, loss[loss=0.1622, simple_loss=0.2267, pruned_loss=0.04883, over 4768.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2122, pruned_loss=0.03368, over 972263.51 frames.], batch size: 12, lr: 2.00e-04
2022-05-07 00:53:14,457 INFO [train.py:715] (4/8) Epoch 11, batch 2450, loss[loss=0.1495, simple_loss=0.2271, pruned_loss=0.03594, over 4973.00 frames.], tot_loss[loss=0.1394, simple_loss=0.212, pruned_loss=0.03341, over 972196.47 frames.], batch size: 35, lr: 2.00e-04
2022-05-07 00:53:54,032 INFO [train.py:715] (4/8) Epoch 11, batch 2500, loss[loss=0.1486, simple_loss=0.2202, pruned_loss=0.0385, over 4943.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2115, pruned_loss=0.03293, over 971570.41 frames.], batch size: 23, lr: 2.00e-04
2022-05-07 00:54:33,179 INFO [train.py:715] (4/8) Epoch 11, batch 2550, loss[loss=0.1323, simple_loss=0.2043, pruned_loss=0.03016, over 4957.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2116, pruned_loss=0.03313, over 972101.21 frames.], batch size: 35, lr: 2.00e-04
2022-05-07 00:55:12,421 INFO [train.py:715] (4/8) Epoch 11, batch 2600, loss[loss=0.1616, simple_loss=0.2358, pruned_loss=0.04372, over 4924.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2114, pruned_loss=0.03323, over 972558.88 frames.], batch size: 23, lr: 2.00e-04
2022-05-07 00:55:51,263 INFO [train.py:715] (4/8) Epoch 11, batch 2650, loss[loss=0.1611, simple_loss=0.2351, pruned_loss=0.04351, over 4894.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03312, over 972680.25 frames.], batch size: 22, lr: 2.00e-04
2022-05-07 00:56:30,347 INFO [train.py:715] (4/8) Epoch 11, batch 2700, loss[loss=0.1402, simple_loss=0.2166, pruned_loss=0.03188, over 4840.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03299, over 972036.80 frames.], batch size: 26, lr: 2.00e-04
2022-05-07 00:57:09,094 INFO [train.py:715] (4/8) Epoch 11, batch 2750, loss[loss=0.1344, simple_loss=0.2017, pruned_loss=0.03361, over 4988.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.0332, over 972710.13 frames.], batch size: 15, lr: 2.00e-04
2022-05-07 00:57:48,072 INFO [train.py:715] (4/8) Epoch 11, batch 2800, loss[loss=0.1274, simple_loss=0.1976, pruned_loss=0.02857, over 4972.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03289, over 971901.10 frames.], batch size: 15, lr: 2.00e-04
2022-05-07 00:58:27,251 INFO [train.py:715] (4/8) Epoch 11, batch 2850, loss[loss=0.1199, simple_loss=0.185, pruned_loss=0.02741, over 4824.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2123, pruned_loss=0.03323, over 972008.10 frames.], batch size: 12, lr: 2.00e-04
2022-05-07 00:59:05,708 INFO [train.py:715] (4/8) Epoch 11, batch 2900, loss[loss=0.1282, simple_loss=0.2003, pruned_loss=0.02804, over 4979.00 frames.], tot_loss[loss=0.139, simple_loss=0.2117, pruned_loss=0.03313, over 972405.45 frames.], batch size: 14, lr: 2.00e-04
2022-05-07 00:59:45,167 INFO [train.py:715] (4/8) Epoch 11, batch 2950, loss[loss=0.1249, simple_loss=0.205, pruned_loss=0.0224, over 4786.00 frames.], tot_loss[loss=0.138, simple_loss=0.2109, pruned_loss=0.03253, over 972009.04 frames.], batch size: 18, lr: 2.00e-04
2022-05-07 01:00:25,032 INFO [train.py:715] (4/8) Epoch 11, batch 3000, loss[loss=0.1462, simple_loss=0.2189, pruned_loss=0.03668, over 4885.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03186, over 972405.92 frames.], batch size: 16, lr: 2.00e-04
2022-05-07 01:00:25,033 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 01:00:34,771 INFO [train.py:742] (4/8) Epoch 11, validation: loss=0.1061, simple_loss=0.1902, pruned_loss=0.01097, over 914524.00 frames.
2022-05-07 01:01:14,747 INFO [train.py:715] (4/8) Epoch 11, batch 3050, loss[loss=0.1342, simple_loss=0.2068, pruned_loss=0.03079, over 4683.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03219, over 971899.03 frames.], batch size: 15, lr: 2.00e-04
2022-05-07 01:01:54,015 INFO [train.py:715] (4/8) Epoch 11, batch 3100, loss[loss=0.1345, simple_loss=0.2029, pruned_loss=0.03302, over 4843.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03275, over 971281.06 frames.], batch size: 30, lr: 2.00e-04
2022-05-07 01:02:34,093 INFO [train.py:715] (4/8) Epoch 11, batch 3150, loss[loss=0.1573, simple_loss=0.2297, pruned_loss=0.04245, over 4927.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03249, over 972135.39 frames.], batch size: 39, lr: 2.00e-04
2022-05-07 01:03:13,127 INFO [train.py:715] (4/8) Epoch 11, batch 3200, loss[loss=0.1844, simple_loss=0.2709, pruned_loss=0.04895, over 4812.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.03228, over 971801.72 frames.], batch size: 27, lr: 2.00e-04
2022-05-07 01:03:52,801 INFO [train.py:715] (4/8) Epoch 11, batch 3250, loss[loss=0.1262, simple_loss=0.2114, pruned_loss=0.02053, over 4853.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03245, over 971124.64 frames.], batch size: 13, lr: 2.00e-04
2022-05-07 01:04:31,530 INFO [train.py:715] (4/8) Epoch 11, batch 3300, loss[loss=0.1286, simple_loss=0.2003, pruned_loss=0.02849, over 4992.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03234, over 971391.00 frames.], batch size: 16, lr: 2.00e-04
2022-05-07 01:05:10,792 INFO [train.py:715] (4/8) Epoch 11, batch 3350, loss[loss=0.1399, simple_loss=0.2074, pruned_loss=0.03619, over 4981.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2108, pruned_loss=0.03239, over 972695.45 frames.], batch size: 25, lr: 2.00e-04
2022-05-07 01:05:50,449 INFO [train.py:715] (4/8) Epoch 11, batch 3400, loss[loss=0.1223, simple_loss=0.1994, pruned_loss=0.02264, over 4907.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2106, pruned_loss=0.03233, over 972397.88 frames.], batch size: 17, lr: 2.00e-04
2022-05-07 01:06:29,437 INFO [train.py:715] (4/8) Epoch 11, batch 3450, loss[loss=0.1446, simple_loss=0.2264, pruned_loss=0.03138, over 4965.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2113, pruned_loss=0.03267, over 971077.43 frames.], batch size: 24, lr: 2.00e-04
2022-05-07 01:07:08,298 INFO [train.py:715] (4/8) Epoch 11, batch 3500, loss[loss=0.154, simple_loss=0.2331, pruned_loss=0.03741, over 4984.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03321, over 972002.32 frames.], batch size: 35, lr: 1.99e-04
2022-05-07 01:07:47,574 INFO [train.py:715] (4/8) Epoch 11, batch 3550, loss[loss=0.1351, simple_loss=0.206, pruned_loss=0.03217, over 4932.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03304, over 971819.46 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:08:27,194 INFO [train.py:715] (4/8) Epoch 11, batch 3600, loss[loss=0.12, simple_loss=0.203, pruned_loss=0.0185, over 4898.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2116, pruned_loss=0.03286, over 971941.95 frames.], batch size: 22, lr: 1.99e-04
2022-05-07 01:09:05,530 INFO [train.py:715] (4/8) Epoch 11, batch 3650, loss[loss=0.1043, simple_loss=0.1747, pruned_loss=0.01693, over 4837.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.03317, over 971586.49 frames.], batch size: 13, lr: 1.99e-04
2022-05-07 01:09:45,168 INFO [train.py:715] (4/8) Epoch 11, batch 3700, loss[loss=0.1159, simple_loss=0.1773, pruned_loss=0.02724, over 4792.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2108, pruned_loss=0.03267, over 971539.47 frames.], batch size: 12, lr: 1.99e-04
2022-05-07 01:10:24,603 INFO [train.py:715] (4/8) Epoch 11, batch 3750, loss[loss=0.1297, simple_loss=0.207, pruned_loss=0.02623, over 4883.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03242, over 971468.64 frames.], batch size: 16, lr: 1.99e-04
2022-05-07 01:11:03,049 INFO [train.py:715] (4/8) Epoch 11, batch 3800, loss[loss=0.1162, simple_loss=0.1948, pruned_loss=0.01878, over 4918.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.03231, over 972164.49 frames.], batch size: 39, lr: 1.99e-04
2022-05-07 01:11:42,112 INFO [train.py:715] (4/8) Epoch 11, batch 3850, loss[loss=0.1344, simple_loss=0.2103, pruned_loss=0.02921, over 4955.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2107, pruned_loss=0.03232, over 972745.55 frames.], batch size: 24, lr: 1.99e-04
2022-05-07 01:12:21,420 INFO [train.py:715] (4/8) Epoch 11, batch 3900, loss[loss=0.1566, simple_loss=0.2302, pruned_loss=0.04154, over 4968.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03252, over 972694.93 frames.], batch size: 24, lr: 1.99e-04
2022-05-07 01:13:01,146 INFO [train.py:715] (4/8) Epoch 11, batch 3950, loss[loss=0.1176, simple_loss=0.1846, pruned_loss=0.0253, over 4974.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.03252, over 973959.59 frames.], batch size: 35, lr: 1.99e-04
2022-05-07 01:13:39,996 INFO [train.py:715] (4/8) Epoch 11, batch 4000, loss[loss=0.1296, simple_loss=0.204, pruned_loss=0.02757, over 4813.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03263, over 974236.56 frames.], batch size: 27, lr: 1.99e-04
2022-05-07 01:14:19,834 INFO [train.py:715] (4/8) Epoch 11, batch 4050, loss[loss=0.1224, simple_loss=0.198, pruned_loss=0.02337, over 4821.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03327, over 974002.40 frames.], batch size: 26, lr: 1.99e-04
2022-05-07 01:14:59,478 INFO [train.py:715] (4/8) Epoch 11, batch 4100, loss[loss=0.1564, simple_loss=0.2322, pruned_loss=0.04034, over 4688.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2129, pruned_loss=0.03312, over 972822.39 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:15:38,032 INFO [train.py:715] (4/8) Epoch 11, batch 4150, loss[loss=0.1122, simple_loss=0.1771, pruned_loss=0.02361, over 4819.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.03324, over 972309.08 frames.], batch size: 13, lr: 1.99e-04
2022-05-07 01:16:16,418 INFO [train.py:715] (4/8) Epoch 11, batch 4200, loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.02852, over 4920.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03282, over 972721.61 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:16:56,659 INFO [train.py:715] (4/8) Epoch 11, batch 4250, loss[loss=0.1352, simple_loss=0.2192, pruned_loss=0.02564, over 4934.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2127, pruned_loss=0.03339, over 972899.99 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:17:36,659 INFO [train.py:715] (4/8) Epoch 11, batch 4300, loss[loss=0.1189, simple_loss=0.1886, pruned_loss=0.02464, over 4806.00 frames.], tot_loss[loss=0.139, simple_loss=0.212, pruned_loss=0.03305, over 973260.35 frames.], batch size: 25, lr: 1.99e-04
2022-05-07 01:18:15,822 INFO [train.py:715] (4/8) Epoch 11, batch 4350, loss[loss=0.1328, simple_loss=0.2021, pruned_loss=0.03172, over 4984.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03336, over 972651.38 frames.], batch size: 28, lr: 1.99e-04
2022-05-07 01:18:56,184 INFO [train.py:715] (4/8) Epoch 11, batch 4400, loss[loss=0.146, simple_loss=0.2155, pruned_loss=0.03825, over 4913.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2128, pruned_loss=0.0339, over 972414.76 frames.], batch size: 39, lr: 1.99e-04
2022-05-07 01:19:36,294 INFO [train.py:715] (4/8) Epoch 11, batch 4450, loss[loss=0.1699, simple_loss=0.2484, pruned_loss=0.04564, over 4943.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2121, pruned_loss=0.03379, over 971797.10 frames.], batch size: 24, lr: 1.99e-04
2022-05-07 01:20:15,924 INFO [train.py:715] (4/8) Epoch 11, batch 4500, loss[loss=0.158, simple_loss=0.2226, pruned_loss=0.04666, over 4778.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2119, pruned_loss=0.03383, over 971753.05 frames.], batch size: 17, lr: 1.99e-04
2022-05-07 01:20:55,941 INFO [train.py:715] (4/8) Epoch 11, batch 4550, loss[loss=0.1167, simple_loss=0.1853, pruned_loss=0.02406, over 4956.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2121, pruned_loss=0.03361, over 972147.66 frames.], batch size: 21, lr: 1.99e-04
2022-05-07 01:21:35,995 INFO [train.py:715] (4/8) Epoch 11, batch 4600, loss[loss=0.1237, simple_loss=0.1914, pruned_loss=0.02795, over 4874.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03355, over 971649.84 frames.], batch size: 32, lr: 1.99e-04
2022-05-07 01:22:15,462 INFO [train.py:715] (4/8) Epoch 11, batch 4650, loss[loss=0.1516, simple_loss=0.2241, pruned_loss=0.03952, over 4851.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03327, over 971921.80 frames.], batch size: 32, lr: 1.99e-04
2022-05-07 01:22:55,178 INFO [train.py:715] (4/8) Epoch 11, batch 4700, loss[loss=0.1294, simple_loss=0.2008, pruned_loss=0.02899, over 4855.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2123, pruned_loss=0.0335, over 971987.44 frames.], batch size: 20, lr: 1.99e-04
2022-05-07 01:23:35,351 INFO [train.py:715] (4/8) Epoch 11, batch 4750, loss[loss=0.1376, simple_loss=0.2047, pruned_loss=0.0352, over 4884.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2124, pruned_loss=0.03352, over 971941.94 frames.], batch size: 19, lr: 1.99e-04
2022-05-07 01:24:15,520 INFO [train.py:715] (4/8) Epoch 11, batch 4800, loss[loss=0.1291, simple_loss=0.1999, pruned_loss=0.02916, over 4750.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2123, pruned_loss=0.03325, over 971415.50 frames.], batch size: 16, lr: 1.99e-04
2022-05-07 01:24:55,133 INFO [train.py:715] (4/8) Epoch 11, batch 4850, loss[loss=0.126, simple_loss=0.2016, pruned_loss=0.02522, over 4787.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2121, pruned_loss=0.03309, over 971757.24 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:25:34,922 INFO [train.py:715] (4/8) Epoch 11, batch 4900, loss[loss=0.123, simple_loss=0.2038, pruned_loss=0.02106, over 4819.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03333, over 971013.46 frames.], batch size: 25, lr: 1.99e-04
2022-05-07 01:26:14,638 INFO [train.py:715] (4/8) Epoch 11, batch 4950, loss[loss=0.1069, simple_loss=0.1861, pruned_loss=0.01381, over 4972.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2119, pruned_loss=0.03325, over 972863.62 frames.], batch size: 28, lr: 1.99e-04
2022-05-07 01:26:53,441 INFO [train.py:715] (4/8) Epoch 11, batch 5000, loss[loss=0.1395, simple_loss=0.2212, pruned_loss=0.02895, over 4890.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03274, over 972586.41 frames.], batch size: 19, lr: 1.99e-04
2022-05-07 01:27:31,884 INFO [train.py:715] (4/8) Epoch 11, batch 5050, loss[loss=0.1048, simple_loss=0.1817, pruned_loss=0.01397, over 4731.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.03269, over 973244.41 frames.], batch size: 12, lr: 1.99e-04
2022-05-07 01:28:11,142 INFO [train.py:715] (4/8) Epoch 11, batch 5100, loss[loss=0.1581, simple_loss=0.2305, pruned_loss=0.0429, over 4685.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2114, pruned_loss=0.0326, over 972577.18 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:28:50,274 INFO [train.py:715] (4/8) Epoch 11, batch 5150, loss[loss=0.1403, simple_loss=0.2152, pruned_loss=0.03266, over 4953.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03286, over 972336.41 frames.], batch size: 39, lr: 1.99e-04
2022-05-07 01:29:29,204 INFO [train.py:715] (4/8) Epoch 11, batch 5200, loss[loss=0.1647, simple_loss=0.2328, pruned_loss=0.04835, over 4858.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2114, pruned_loss=0.03316, over 971999.83 frames.], batch size: 38, lr: 1.99e-04
2022-05-07 01:30:08,610 INFO [train.py:715] (4/8) Epoch 11, batch 5250, loss[loss=0.1422, simple_loss=0.2214, pruned_loss=0.03147, over 4917.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2112, pruned_loss=0.03288, over 971455.21 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:30:48,292 INFO [train.py:715] (4/8) Epoch 11, batch 5300, loss[loss=0.1211, simple_loss=0.1919, pruned_loss=0.02522, over 4832.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2112, pruned_loss=0.03293, over 970645.71 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:31:27,444 INFO [train.py:715] (4/8) Epoch 11, batch 5350, loss[loss=0.1236, simple_loss=0.1941, pruned_loss=0.02659, over 4928.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03248, over 971066.85 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:32:06,514 INFO [train.py:715] (4/8) Epoch 11, batch 5400, loss[loss=0.1411, simple_loss=0.2236, pruned_loss=0.02929, over 4808.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2113, pruned_loss=0.03262, over 971203.21 frames.], batch size: 21, lr: 1.99e-04
2022-05-07 01:32:45,901 INFO [train.py:715] (4/8) Epoch 11, batch 5450, loss[loss=0.1598, simple_loss=0.2323, pruned_loss=0.04366, over 4823.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03265, over 970800.32 frames.], batch size: 25, lr: 1.99e-04
2022-05-07 01:33:25,399 INFO [train.py:715] (4/8) Epoch 11, batch 5500, loss[loss=0.1358, simple_loss=0.2059, pruned_loss=0.03285, over 4840.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03199, over 971243.45 frames.], batch size: 32, lr: 1.99e-04
2022-05-07 01:34:04,255 INFO [train.py:715] (4/8) Epoch 11, batch 5550, loss[loss=0.1475, simple_loss=0.2185, pruned_loss=0.03819, over 4840.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2102, pruned_loss=0.03221, over 972404.25 frames.], batch size: 20, lr: 1.99e-04
2022-05-07 01:34:42,707 INFO [train.py:715] (4/8) Epoch 11, batch 5600, loss[loss=0.1284, simple_loss=0.2092, pruned_loss=0.02375, over 4798.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03251, over 972568.34 frames.], batch size: 24, lr: 1.99e-04
2022-05-07 01:35:22,174 INFO [train.py:715] (4/8) Epoch 11, batch 5650, loss[loss=0.1238, simple_loss=0.1928, pruned_loss=0.02745, over 4826.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03213, over 973154.42 frames.], batch size: 30, lr: 1.99e-04
2022-05-07 01:36:01,616 INFO [train.py:715] (4/8) Epoch 11, batch 5700, loss[loss=0.1744, simple_loss=0.2432, pruned_loss=0.05278, over 4701.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.03232, over 972626.33 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:36:40,399 INFO [train.py:715] (4/8) Epoch 11, batch 5750, loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02972, over 4815.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2112, pruned_loss=0.03266, over 972710.87 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:37:19,376 INFO [train.py:715] (4/8) Epoch 11, batch 5800, loss[loss=0.1405, simple_loss=0.2253, pruned_loss=0.02784, over 4813.00 frames.], tot_loss[loss=0.139, simple_loss=0.2122, pruned_loss=0.03291, over 972837.66 frames.], batch size: 26, lr: 1.99e-04
2022-05-07 01:37:58,487 INFO [train.py:715] (4/8) Epoch 11, batch 5850, loss[loss=0.1452, simple_loss=0.2078, pruned_loss=0.0413, over 4832.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2118, pruned_loss=0.033, over 971235.91 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:38:37,496 INFO [train.py:715] (4/8) Epoch 11, batch 5900, loss[loss=0.1308, simple_loss=0.2059, pruned_loss=0.0279, over 4874.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.0324, over 970984.31 frames.], batch size: 22, lr: 1.99e-04
2022-05-07 01:39:16,657 INFO [train.py:715] (4/8) Epoch 11, batch 5950, loss[loss=0.1694, simple_loss=0.2383, pruned_loss=0.05026, over 4958.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03269, over 971560.75 frames.], batch size: 24, lr: 1.99e-04
2022-05-07 01:39:56,445 INFO [train.py:715] (4/8) Epoch 11, batch 6000, loss[loss=0.155, simple_loss=0.2324, pruned_loss=0.03877, over 4814.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.03246, over 971149.62 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:39:56,446 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 01:40:06,014 INFO [train.py:742] (4/8) Epoch 11, validation: loss=0.1059, simple_loss=0.1901, pruned_loss=0.01082, over 914524.00 frames.
2022-05-07 01:40:45,575 INFO [train.py:715] (4/8) Epoch 11, batch 6050, loss[loss=0.1509, simple_loss=0.2278, pruned_loss=0.03701, over 4710.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.03238, over 971253.72 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:41:24,988 INFO [train.py:715] (4/8) Epoch 11, batch 6100, loss[loss=0.1449, simple_loss=0.2212, pruned_loss=0.03433, over 4941.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2117, pruned_loss=0.03222, over 971866.79 frames.], batch size: 21, lr: 1.99e-04
2022-05-07 01:42:03,737 INFO [train.py:715] (4/8) Epoch 11, batch 6150, loss[loss=0.1462, simple_loss=0.22, pruned_loss=0.03615, over 4776.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2119, pruned_loss=0.03212, over 971909.21 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:42:43,200 INFO [train.py:715] (4/8) Epoch 11, batch 6200, loss[loss=0.1209, simple_loss=0.1987, pruned_loss=0.02157, over 4766.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2116, pruned_loss=0.03204, over 972170.27 frames.], batch size: 14, lr: 1.99e-04
2022-05-07 01:43:22,226 INFO [train.py:715] (4/8) Epoch 11, batch 6250, loss[loss=0.1288, simple_loss=0.2082, pruned_loss=0.02474, over 4974.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03176, over 971769.91 frames.], batch size: 24, lr: 1.99e-04
2022-05-07 01:44:01,016 INFO [train.py:715] (4/8) Epoch 11, batch 6300, loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02851, over 4926.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03164, over 970984.64 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:44:39,692 INFO [train.py:715] (4/8) Epoch 11, batch 6350, loss[loss=0.1447, simple_loss=0.2145, pruned_loss=0.03747, over 4810.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03189, over 971374.53 frames.], batch size: 12, lr: 1.99e-04
2022-05-07 01:45:20,274 INFO [train.py:715] (4/8) Epoch 11, batch 6400, loss[loss=0.1659, simple_loss=0.2337, pruned_loss=0.04908, over 4830.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03259, over 971887.83 frames.], batch size: 26, lr: 1.99e-04
2022-05-07 01:45:59,616 INFO [train.py:715] (4/8) Epoch 11, batch 6450, loss[loss=0.1337, simple_loss=0.2094, pruned_loss=0.02895, over 4868.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2125, pruned_loss=0.03299, over 972203.83 frames.], batch size: 20, lr: 1.99e-04
2022-05-07 01:46:38,690 INFO [train.py:715] (4/8) Epoch 11, batch 6500, loss[loss=0.1345, simple_loss=0.2109, pruned_loss=0.02904, over 4752.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.03321, over 972309.76 frames.], batch size: 16, lr: 1.99e-04
2022-05-07 01:47:18,036 INFO [train.py:715] (4/8) Epoch 11, batch 6550, loss[loss=0.1121, simple_loss=0.1802, pruned_loss=0.02201, over 4824.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2128, pruned_loss=0.03352, over 972973.20 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:47:58,218 INFO [train.py:715] (4/8) Epoch 11, batch 6600, loss[loss=0.146, simple_loss=0.2149, pruned_loss=0.0386, over 4960.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03265, over 971979.62 frames.], batch size: 24, lr: 1.99e-04
2022-05-07 01:48:38,342 INFO [train.py:715] (4/8) Epoch 11, batch 6650, loss[loss=0.1476, simple_loss=0.2221, pruned_loss=0.03659, over 4968.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2128, pruned_loss=0.03341, over 972568.81 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:49:17,552 INFO [train.py:715] (4/8) Epoch 11, batch 6700, loss[loss=0.132, simple_loss=0.2049, pruned_loss=0.02954, over 4788.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2136, pruned_loss=0.03352, over 972709.92 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:49:57,807 INFO [train.py:715] (4/8) Epoch 11, batch 6750, loss[loss=0.1216, simple_loss=0.1997, pruned_loss=0.02178, over 4972.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2131, pruned_loss=0.03338, over 973465.08 frames.], batch size: 14, lr: 1.99e-04
2022-05-07 01:50:37,609 INFO [train.py:715] (4/8) Epoch 11, batch 6800, loss[loss=0.1241, simple_loss=0.2082, pruned_loss=0.02005, over 4940.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.03273, over 973512.08 frames.], batch size: 29, lr: 1.99e-04
2022-05-07 01:51:16,479 INFO [train.py:715] (4/8) Epoch 11, batch 6850, loss[loss=0.1081, simple_loss=0.1819, pruned_loss=0.01717, over 4943.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.0324, over 973158.50 frames.], batch size: 29, lr: 1.99e-04
2022-05-07 01:51:55,545 INFO [train.py:715] (4/8) Epoch 11, batch 6900, loss[loss=0.1376, simple_loss=0.2164, pruned_loss=0.02942, over 4918.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.03235, over 973451.05 frames.], batch size: 39, lr: 1.99e-04
2022-05-07 01:52:34,234 INFO [train.py:715] (4/8) Epoch 11, batch 6950, loss[loss=0.1465, simple_loss=0.2207, pruned_loss=0.03613, over 4692.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03262, over 972679.65 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:53:13,692 INFO [train.py:715] (4/8) Epoch 11, batch 7000, loss[loss=0.1653, simple_loss=0.2431, pruned_loss=0.04376, over 4973.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03269, over 972181.44 frames.], batch size: 15, lr: 1.99e-04
2022-05-07 01:53:52,255 INFO [train.py:715] (4/8) Epoch 11, batch 7050, loss[loss=0.1258, simple_loss=0.2089, pruned_loss=0.02131, over 4935.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2121, pruned_loss=0.03257, over 970965.55 frames.], batch size: 21, lr: 1.99e-04
2022-05-07 01:54:31,697 INFO [train.py:715] (4/8) Epoch 11, batch 7100, loss[loss=0.1343, simple_loss=0.214, pruned_loss=0.02731, over 4982.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.03235, over 970773.51 frames.], batch size: 28, lr: 1.99e-04
2022-05-07 01:55:10,748 INFO [train.py:715] (4/8) Epoch 11, batch 7150, loss[loss=0.1154, simple_loss=0.1907, pruned_loss=0.02003, over 4757.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2122, pruned_loss=0.03235, over 970248.67 frames.], batch size: 16, lr: 1.99e-04
2022-05-07 01:55:49,508 INFO [train.py:715] (4/8) Epoch 11, batch 7200, loss[loss=0.1017, simple_loss=0.1768, pruned_loss=0.01329, over 4789.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2121, pruned_loss=0.03259, over 971147.53 frames.], batch size: 12, lr: 1.99e-04
2022-05-07 01:56:28,452 INFO [train.py:715] (4/8) Epoch 11, batch 7250, loss[loss=0.1167, simple_loss=0.1934, pruned_loss=0.02001, over 4829.00 frames.], tot_loss[loss=0.139, simple_loss=0.2124, pruned_loss=0.03277, over 971747.03 frames.], batch size: 26, lr: 1.99e-04
2022-05-07 01:57:07,430 INFO [train.py:715] (4/8) Epoch 11, batch 7300, loss[loss=0.1191, simple_loss=0.1962, pruned_loss=0.02101, over 4781.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.03266, over 971994.02 frames.], batch size: 18, lr: 1.99e-04
2022-05-07 01:57:46,540 INFO [train.py:715] (4/8) Epoch 11, batch 7350, loss[loss=0.1402, simple_loss=0.2124, pruned_loss=0.03401, over 4930.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03273, over 972998.97 frames.], batch size: 29, lr: 1.99e-04
2022-05-07 01:58:25,304 INFO [train.py:715] (4/8) Epoch 11, batch 7400, loss[loss=0.1154, simple_loss=0.1969, pruned_loss=0.01696, over 4801.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03253, over 973046.45 frames.], batch size: 24, lr: 1.98e-04
2022-05-07 01:59:04,703 INFO [train.py:715] (4/8) Epoch 11, batch 7450, loss[loss=0.1385, simple_loss=0.215, pruned_loss=0.03095, over 4926.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.03242, over 973662.54 frames.], batch size: 23, lr: 1.98e-04
2022-05-07 01:59:43,839 INFO [train.py:715] (4/8) Epoch 11, batch 7500, loss[loss=0.113, simple_loss=0.1914, pruned_loss=0.01729, over 4802.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2122, pruned_loss=0.03238, over 973530.66 frames.], batch size: 14, lr: 1.98e-04
2022-05-07 02:00:23,090 INFO [train.py:715] (4/8) Epoch 11, batch 7550, loss[loss=0.1408, simple_loss=0.2139, pruned_loss=0.03388, over 4974.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2123, pruned_loss=0.03239, over 975036.74 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:01:02,844 INFO [train.py:715] (4/8) Epoch 11, batch 7600, loss[loss=0.12, simple_loss=0.1971, pruned_loss=0.02146, over 4933.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2118, pruned_loss=0.03201, over 974701.69 frames.], batch size: 29, lr: 1.98e-04
2022-05-07 02:01:42,513 INFO [train.py:715] (4/8) Epoch 11, batch 7650, loss[loss=0.1467, simple_loss=0.2072, pruned_loss=0.04312, over 4944.00 frames.], tot_loss[loss=0.139, simple_loss=0.2125, pruned_loss=0.03276, over 974228.46 frames.], batch size: 14, lr: 1.98e-04
2022-05-07 02:02:22,070 INFO [train.py:715] (4/8) Epoch 11, batch 7700, loss[loss=0.1529, simple_loss=0.2279, pruned_loss=0.03897, over 4943.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2119, pruned_loss=0.03223, over 974058.61 frames.], batch size: 39, lr: 1.98e-04
2022-05-07 02:03:01,233 INFO [train.py:715] (4/8) Epoch 11, batch 7750, loss[loss=0.1184, simple_loss=0.1855, pruned_loss=0.02561, over 4849.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2117, pruned_loss=0.03221, over 973987.15 frames.], batch size: 32, lr: 1.98e-04
2022-05-07 02:03:40,566 INFO [train.py:715] (4/8) Epoch 11, batch 7800, loss[loss=0.1298, simple_loss=0.2014, pruned_loss=0.02906, over 4934.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.03254, over 973809.81 frames.], batch size: 29, lr: 1.98e-04
2022-05-07 02:04:19,853 INFO [train.py:715] (4/8) Epoch 11, batch 7850, loss[loss=0.1445, simple_loss=0.2238, pruned_loss=0.03255, over 4704.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.0325, over 973746.19 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:04:58,992 INFO [train.py:715] (4/8) Epoch 11, batch 7900, loss[loss=0.1311, simple_loss=0.1987, pruned_loss=0.03178, over 4873.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03267, over 973289.96 frames.], batch size: 16, lr: 1.98e-04
2022-05-07 02:05:37,728 INFO [train.py:715] (4/8) Epoch 11, batch 7950, loss[loss=0.1662, simple_loss=0.2432, pruned_loss=0.04454, over 4847.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.0318, over 973338.87 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:06:18,375 INFO [train.py:715] (4/8) Epoch 11, batch 8000, loss[loss=0.1272, simple_loss=0.2004, pruned_loss=0.027, over 4955.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2118, pruned_loss=0.03243, over 972982.39 frames.], batch size: 21, lr: 1.98e-04
2022-05-07 02:06:57,623 INFO [train.py:715] (4/8) Epoch 11, batch 8050, loss[loss=0.142, simple_loss=0.2097, pruned_loss=0.0371, over 4831.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03307, over 972703.12 frames.], batch size: 12, lr: 1.98e-04
2022-05-07 02:07:37,871 INFO [train.py:715] (4/8) Epoch 11, batch 8100, loss[loss=0.1485, simple_loss=0.2213, pruned_loss=0.0379, over 4912.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03307, over 972884.47 frames.], batch size: 17, lr: 1.98e-04
2022-05-07 02:08:17,867 INFO [train.py:715] (4/8) Epoch 11, batch 8150, loss[loss=0.1186, simple_loss=0.1994, pruned_loss=0.01892, over 4646.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03286, over 973053.79 frames.], batch size: 13, lr: 1.98e-04
2022-05-07 02:08:57,396 INFO [train.py:715] (4/8) Epoch 11, batch 8200, loss[loss=0.158, simple_loss=0.2256, pruned_loss=0.04517, over 4883.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03219, over 972944.21 frames.], batch size: 16, lr: 1.98e-04
2022-05-07 02:09:36,722 INFO [train.py:715] (4/8) Epoch 11, batch 8250, loss[loss=0.1225, simple_loss=0.1918, pruned_loss=0.02661, over 4834.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03227, over 972955.78 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:10:15,076 INFO [train.py:715] (4/8) Epoch 11, batch 8300, loss[loss=0.1427, simple_loss=0.2055, pruned_loss=0.03993, over 4863.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2124, pruned_loss=0.03228, over 973540.91 frames.], batch size: 32, lr: 1.98e-04
2022-05-07 02:10:54,958 INFO [train.py:715] (4/8) Epoch 11, batch 8350, loss[loss=0.1183, simple_loss=0.1921, pruned_loss=0.02226, over 4746.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2123, pruned_loss=0.03228, over 972422.22 frames.], batch size: 16, lr: 1.98e-04
2022-05-07 02:11:34,527 INFO [train.py:715] (4/8) Epoch 11, batch 8400, loss[loss=0.1365, simple_loss=0.2126, pruned_loss=0.03023, over 4941.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.03237, over 972290.12 frames.], batch size: 21, lr: 1.98e-04
2022-05-07 02:12:13,501 INFO [train.py:715] (4/8) Epoch 11, batch 8450, loss[loss=0.1408, simple_loss=0.2178, pruned_loss=0.03187, over 4776.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03308, over 972298.94 frames.], batch size: 17, lr: 1.98e-04
2022-05-07 02:12:52,195 INFO [train.py:715] (4/8) Epoch 11, batch 8500, loss[loss=0.1648, simple_loss=0.2331, pruned_loss=0.04829, over 4755.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2122, pruned_loss=0.0334, over 972185.85 frames.], batch size: 17, lr: 1.98e-04
2022-05-07 02:13:32,006 INFO [train.py:715] (4/8) Epoch 11, batch 8550, loss[loss=0.1377, simple_loss=0.2114, pruned_loss=0.03204, over 4915.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2122, pruned_loss=0.03316, over 972372.81 frames.], batch size: 39, lr: 1.98e-04
2022-05-07 02:14:11,213 INFO [train.py:715] (4/8) Epoch 11, batch 8600, loss[loss=0.132, simple_loss=0.2097, pruned_loss=0.02717, over 4762.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03326, over 972159.72 frames.], batch size: 19, lr: 1.98e-04
2022-05-07 02:14:49,545 INFO [train.py:715] (4/8) Epoch 11, batch 8650, loss[loss=0.1252, simple_loss=0.1965, pruned_loss=0.02697, over 4707.00 frames.], tot_loss[loss=0.1396, simple_loss=0.212, pruned_loss=0.03354, over 971916.33 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:15:29,403 INFO [train.py:715] (4/8) Epoch 11, batch 8700, loss[loss=0.14, simple_loss=0.218, pruned_loss=0.03101, over 4698.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2117, pruned_loss=0.03351, over 971773.96 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:16:08,721 INFO [train.py:715] (4/8) Epoch 11, batch 8750, loss[loss=0.136, simple_loss=0.2048, pruned_loss=0.03357, over 4773.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2117, pruned_loss=0.03378, over 971724.03 frames.], batch size: 18, lr: 1.98e-04
2022-05-07 02:16:47,706 INFO [train.py:715] (4/8) Epoch 11, batch 8800, loss[loss=0.1225, simple_loss=0.1907, pruned_loss=0.02715, over 4933.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2121, pruned_loss=0.03384, over 972159.08 frames.], batch size: 23, lr: 1.98e-04
2022-05-07 02:17:26,838 INFO [train.py:715] (4/8) Epoch 11, batch 8850, loss[loss=0.1391, simple_loss=0.2026, pruned_loss=0.03778, over 4830.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2124, pruned_loss=0.03368, over 972118.60 frames.], batch size: 13, lr: 1.98e-04
2022-05-07 02:18:06,536 INFO [train.py:715] (4/8) Epoch 11, batch 8900, loss[loss=0.1363, simple_loss=0.2125, pruned_loss=0.03007, over 4699.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2115, pruned_loss=0.03301, over 971740.79 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:18:46,169 INFO [train.py:715] (4/8) Epoch 11, batch 8950, loss[loss=0.1165, simple_loss=0.1995, pruned_loss=0.0168, over 4751.00 frames.], tot_loss[loss=0.14, simple_loss=0.2125, pruned_loss=0.03377, over 972693.55 frames.], batch size: 16, lr: 1.98e-04
2022-05-07 02:19:25,278 INFO [train.py:715] (4/8) Epoch 11, batch 9000, loss[loss=0.1516, simple_loss=0.225, pruned_loss=0.03908, over 4942.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2118, pruned_loss=0.03316, over 972496.38 frames.], batch size: 35, lr: 1.98e-04
2022-05-07 02:19:25,279 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 02:19:34,856 INFO [train.py:742] (4/8) Epoch 11, validation: loss=0.1061, simple_loss=0.1903, pruned_loss=0.011, over 914524.00 frames.
2022-05-07 02:20:13,751 INFO [train.py:715] (4/8) Epoch 11, batch 9050, loss[loss=0.1082, simple_loss=0.1717, pruned_loss=0.02238, over 4980.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2112, pruned_loss=0.03282, over 972286.88 frames.], batch size: 24, lr: 1.98e-04
2022-05-07 02:20:55,922 INFO [train.py:715] (4/8) Epoch 11, batch 9100, loss[loss=0.1821, simple_loss=0.2699, pruned_loss=0.04708, over 4901.00 frames.], tot_loss[loss=0.139, simple_loss=0.2114, pruned_loss=0.03331, over 972752.11 frames.], batch size: 17, lr: 1.98e-04
2022-05-07 02:21:35,544 INFO [train.py:715] (4/8) Epoch 11, batch 9150, loss[loss=0.1249, simple_loss=0.2189, pruned_loss=0.01548, over 4974.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03266, over 973459.70 frames.], batch size: 28, lr: 1.98e-04
2022-05-07 02:22:15,056 INFO [train.py:715] (4/8) Epoch 11, batch 9200, loss[loss=0.1301, simple_loss=0.1946, pruned_loss=0.0328, over 4817.00 frames.], tot_loss[loss=0.138, simple_loss=0.2113, pruned_loss=0.03236, over 973526.10 frames.], batch size: 12, lr: 1.98e-04
2022-05-07 02:22:54,637 INFO [train.py:715] (4/8) Epoch 11, batch 9250, loss[loss=0.1891, simple_loss=0.2616, pruned_loss=0.05833, over 4853.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2126, pruned_loss=0.03279, over 973402.11 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:23:33,872 INFO [train.py:715] (4/8) Epoch 11, batch 9300, loss[loss=0.1466, simple_loss=0.2167, pruned_loss=0.03821, over 4916.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2129, pruned_loss=0.03299, over 973451.61 frames.], batch size: 29, lr: 1.98e-04
2022-05-07 02:24:12,709 INFO [train.py:715] (4/8) Epoch 11, batch 9350, loss[loss=0.1317, simple_loss=0.2003, pruned_loss=0.03159, over 4931.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2132, pruned_loss=0.03316, over 973637.39 frames.], batch size: 23, lr: 1.98e-04
2022-05-07 02:24:51,485 INFO [train.py:715] (4/8) Epoch 11, batch 9400, loss[loss=0.1087, simple_loss=0.1806, pruned_loss=0.01838, over 4864.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2134, pruned_loss=0.03314, over 972928.34 frames.], batch size: 20, lr: 1.98e-04
2022-05-07 02:25:31,001 INFO [train.py:715] (4/8) Epoch 11, batch 9450, loss[loss=0.1523, simple_loss=0.2302, pruned_loss=0.03722, over 4818.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2129, pruned_loss=0.03296, over 973006.14 frames.], batch size: 26, lr: 1.98e-04
2022-05-07 02:26:10,039 INFO [train.py:715] (4/8) Epoch 11, batch 9500, loss[loss=0.1233, simple_loss=0.1901, pruned_loss=0.02828, over 4841.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2122, pruned_loss=0.0328, over 971822.73 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:26:48,574 INFO [train.py:715] (4/8) Epoch 11, batch 9550, loss[loss=0.1075, simple_loss=0.1793, pruned_loss=0.01786, over 4761.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.0326, over 972072.95 frames.], batch size: 12, lr: 1.98e-04
2022-05-07 02:27:28,236 INFO [train.py:715] (4/8) Epoch 11, batch 9600, loss[loss=0.1486, simple_loss=0.2265, pruned_loss=0.03534, over 4810.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03283, over 972059.61 frames.], batch size: 25, lr: 1.98e-04
2022-05-07 02:28:07,059 INFO [train.py:715] (4/8) Epoch 11, batch 9650, loss[loss=0.1444, simple_loss=0.215, pruned_loss=0.03684, over 4970.00 frames.], tot_loss[loss=0.139, simple_loss=0.2118, pruned_loss=0.03308, over 972509.16 frames.], batch size: 21, lr: 1.98e-04
2022-05-07 02:28:45,587 INFO [train.py:715] (4/8) Epoch 11, batch 9700, loss[loss=0.1301, simple_loss=0.1982, pruned_loss=0.03104, over 4823.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2119, pruned_loss=0.03336, over 973163.58 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:29:24,591 INFO [train.py:715] (4/8) Epoch 11, batch 9750, loss[loss=0.1469, simple_loss=0.2245, pruned_loss=0.03466, over 4820.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03327, over 972941.40 frames.], batch size: 25, lr: 1.98e-04
2022-05-07 02:30:03,697 INFO [train.py:715] (4/8) Epoch 11, batch 9800, loss[loss=0.1266, simple_loss=0.201, pruned_loss=0.02607, over 4895.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03344, over 972572.27 frames.], batch size: 22, lr: 1.98e-04
2022-05-07 02:30:43,326 INFO [train.py:715] (4/8) Epoch 11, batch 9850, loss[loss=0.1468, simple_loss=0.2085, pruned_loss=0.04251, over 4789.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2124, pruned_loss=0.03308, over 972779.14 frames.], batch size: 17, lr: 1.98e-04
2022-05-07 02:31:22,284 INFO [train.py:715] (4/8) Epoch 11, batch 9900, loss[loss=0.1585, simple_loss=0.2141, pruned_loss=0.05148, over 4783.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03258, over 972256.95 frames.], batch size: 12, lr: 1.98e-04
2022-05-07 02:32:02,525 INFO [train.py:715] (4/8) Epoch 11, batch 9950, loss[loss=0.1479, simple_loss=0.2147, pruned_loss=0.04048, over 4904.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03253, over 972514.02 frames.], batch size: 17, lr: 1.98e-04
2022-05-07 02:32:41,853 INFO [train.py:715] (4/8) Epoch 11, batch 10000, loss[loss=0.1336, simple_loss=0.205, pruned_loss=0.03114, over 4882.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2126, pruned_loss=0.03279, over 972929.84 frames.], batch size: 16, lr: 1.98e-04
2022-05-07 02:33:21,580 INFO [train.py:715] (4/8) Epoch 11, batch 10050, loss[loss=0.1417, simple_loss=0.217, pruned_loss=0.03321, over 4947.00 frames.], tot_loss[loss=0.139, simple_loss=0.2124, pruned_loss=0.03284, over 973041.49 frames.], batch size: 39, lr: 1.98e-04
2022-05-07 02:33:59,720 INFO [train.py:715] (4/8) Epoch 11, batch 10100, loss[loss=0.1432, simple_loss=0.2203, pruned_loss=0.03303, over 4914.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2128, pruned_loss=0.03319, over 972351.64 frames.], batch size: 19, lr: 1.98e-04
2022-05-07 02:34:38,755 INFO [train.py:715] (4/8) Epoch 11, batch 10150, loss[loss=0.1341, simple_loss=0.2114, pruned_loss=0.02839, over 4932.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.0332, over 972622.11 frames.], batch size: 18, lr: 1.98e-04
2022-05-07 02:35:17,187 INFO [train.py:715] (4/8) Epoch 11, batch 10200, loss[loss=0.1384, simple_loss=0.2158, pruned_loss=0.03048, over 4872.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2109, pruned_loss=0.03263, over 973141.10 frames.], batch size: 20, lr: 1.98e-04
2022-05-07 02:35:55,359 INFO [train.py:715] (4/8) Epoch 11, batch 10250, loss[loss=0.1524, simple_loss=0.2185, pruned_loss=0.04319, over 4845.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03301, over 973918.77 frames.], batch size: 32, lr: 1.98e-04
2022-05-07 02:36:34,757 INFO [train.py:715] (4/8) Epoch 11, batch 10300, loss[loss=0.1279, simple_loss=0.2032, pruned_loss=0.02628, over 4879.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03313, over 973165.66 frames.], batch size: 19, lr: 1.98e-04
2022-05-07 02:37:13,484 INFO [train.py:715] (4/8) Epoch 11, batch 10350, loss[loss=0.1472, simple_loss=0.2268, pruned_loss=0.03376, over 4954.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03298, over 972755.98 frames.], batch size: 24, lr: 1.98e-04
2022-05-07 02:37:52,306 INFO [train.py:715] (4/8) Epoch 11, batch 10400, loss[loss=0.1451, simple_loss=0.2206, pruned_loss=0.03482, over 4890.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03299, over 972986.04 frames.], batch size: 39, lr: 1.98e-04
2022-05-07 02:38:30,786 INFO [train.py:715] (4/8) Epoch 11, batch 10450, loss[loss=0.1211, simple_loss=0.2006, pruned_loss=0.02082, over 4841.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2123, pruned_loss=0.03268, over 973452.55 frames.], batch size: 30, lr: 1.98e-04
2022-05-07 02:39:09,430 INFO [train.py:715] (4/8) Epoch 11, batch 10500, loss[loss=0.1397, simple_loss=0.2113, pruned_loss=0.03405, over 4924.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2127, pruned_loss=0.03291, over 972451.19 frames.], batch size: 29, lr: 1.98e-04
2022-05-07 02:39:48,485 INFO [train.py:715] (4/8) Epoch 11, batch 10550, loss[loss=0.156, simple_loss=0.2243, pruned_loss=0.04388, over 4986.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2126, pruned_loss=0.03285, over 972181.70 frames.], batch size: 33, lr: 1.98e-04
2022-05-07 02:40:27,834 INFO [train.py:715] (4/8) Epoch 11, batch 10600, loss[loss=0.1232, simple_loss=0.1891, pruned_loss=0.02863, over 4764.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03257, over 972676.78 frames.], batch size: 12, lr: 1.98e-04
2022-05-07 02:41:06,624 INFO [train.py:715] (4/8) Epoch 11, batch 10650, loss[loss=0.1653, simple_loss=0.2382, pruned_loss=0.04624, over 4817.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.03291, over 972368.50 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:41:45,867 INFO [train.py:715] (4/8) Epoch 11, batch 10700, loss[loss=0.1256, simple_loss=0.2089, pruned_loss=0.02111, over 4821.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2127, pruned_loss=0.03274, over 971718.56 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:42:25,068 INFO [train.py:715] (4/8) Epoch 11, batch 10750, loss[loss=0.1401, simple_loss=0.2206, pruned_loss=0.02986, over 4848.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2125, pruned_loss=0.03259, over 972075.24 frames.], batch size: 30, lr: 1.98e-04
2022-05-07 02:43:03,990 INFO [train.py:715] (4/8) Epoch 11, batch 10800, loss[loss=0.1461, simple_loss=0.2206, pruned_loss=0.03581, over 4846.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.0324, over 971389.84 frames.], batch size: 20, lr: 1.98e-04
2022-05-07 02:43:43,695 INFO [train.py:715] (4/8) Epoch 11, batch 10850, loss[loss=0.1408, simple_loss=0.2208, pruned_loss=0.03039, over 4985.00 frames.], tot_loss[loss=0.1397, simple_loss=0.213, pruned_loss=0.03315, over 971363.86 frames.], batch size: 28, lr: 1.98e-04
2022-05-07 02:44:23,488 INFO [train.py:715] (4/8) Epoch 11, batch 10900, loss[loss=0.1347, simple_loss=0.2006, pruned_loss=0.03445, over 4978.00 frames.], tot_loss[loss=0.1386, simple_loss=0.212, pruned_loss=0.03258, over 971912.90 frames.], batch size: 33, lr: 1.98e-04
2022-05-07 02:45:02,848 INFO [train.py:715] (4/8) Epoch 11, batch 10950, loss[loss=0.1284, simple_loss=0.2041, pruned_loss=0.02632, over 4917.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03209, over 972973.00 frames.], batch size: 23, lr: 1.98e-04
2022-05-07 02:45:42,048 INFO [train.py:715] (4/8) Epoch 11, batch 11000, loss[loss=0.1387, simple_loss=0.2218, pruned_loss=0.02785, over 4860.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.03245, over 972852.95 frames.], batch size: 20, lr: 1.98e-04
2022-05-07 02:46:21,451 INFO [train.py:715] (4/8) Epoch 11, batch 11050, loss[loss=0.1527, simple_loss=0.2114, pruned_loss=0.04698, over 4885.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.0328, over 971666.63 frames.], batch size: 16, lr: 1.98e-04
2022-05-07 02:47:00,460 INFO [train.py:715] (4/8) Epoch 11, batch 11100, loss[loss=0.1148, simple_loss=0.1857, pruned_loss=0.02192, over 4949.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.03244, over 972122.71 frames.], batch size: 21, lr: 1.98e-04
2022-05-07 02:47:39,066 INFO [train.py:715] (4/8) Epoch 11, batch 11150, loss[loss=0.1645, simple_loss=0.2358, pruned_loss=0.04663, over 4694.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.0325, over 972780.78 frames.], batch size: 15, lr: 1.98e-04
2022-05-07 02:48:18,473 INFO [train.py:715] (4/8) Epoch 11, batch 11200, loss[loss=0.1513, simple_loss=0.2239, pruned_loss=0.03932, over 4847.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2112, pruned_loss=0.03255, over 972267.43 frames.], batch size: 30, lr: 1.98e-04
2022-05-07 02:48:57,589 INFO [train.py:715] (4/8) Epoch 11, batch 11250, loss[loss=0.1277, simple_loss=0.1978, pruned_loss=0.02884, over 4980.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2111, pruned_loss=0.032, over 972703.33 frames.], batch size: 31, lr: 1.98e-04
2022-05-07 02:49:35,930 INFO [train.py:715] (4/8) Epoch 11, batch 11300, loss[loss=0.1413, simple_loss=0.2164, pruned_loss=0.03309, over 4790.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03179, over 972587.84 frames.], batch size: 14, lr: 1.98e-04
2022-05-07 02:50:14,843 INFO [train.py:715] (4/8) Epoch 11, batch 11350, loss[loss=0.1182, simple_loss=0.1965, pruned_loss=0.01999, over 4914.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.03171, over 972269.49 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 02:50:54,388 INFO [train.py:715] (4/8) Epoch 11, batch 11400, loss[loss=0.1435, simple_loss=0.2148, pruned_loss=0.03607, over 4951.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03165, over 973143.92 frames.], batch size: 35, lr: 1.97e-04
2022-05-07 02:51:32,952 INFO [train.py:715] (4/8) Epoch 11, batch 11450, loss[loss=0.1307, simple_loss=0.205, pruned_loss=0.02824, over 4809.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.0316, over 973129.02 frames.], batch size: 21, lr: 1.97e-04
2022-05-07 02:52:11,282 INFO [train.py:715] (4/8) Epoch 11, batch 11500, loss[loss=0.1167, simple_loss=0.1981, pruned_loss=0.01768, over 4931.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2094, pruned_loss=0.03163, over 972508.38 frames.], batch size: 23, lr: 1.97e-04
2022-05-07 02:52:50,111 INFO [train.py:715] (4/8) Epoch 11, batch 11550, loss[loss=0.1519, simple_loss=0.2221, pruned_loss=0.04086, over 4759.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2092, pruned_loss=0.03164, over 972317.78 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 02:53:29,304 INFO [train.py:715] (4/8) Epoch 11, batch 11600, loss[loss=0.1506, simple_loss=0.2245, pruned_loss=0.03838, over 4796.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2092, pruned_loss=0.03151, over 972360.12 frames.], batch size: 18, lr: 1.97e-04
2022-05-07 02:54:08,232 INFO [train.py:715] (4/8) Epoch 11, batch 11650, loss[loss=0.1211, simple_loss=0.1942, pruned_loss=0.02405, over 4890.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2084, pruned_loss=0.03156, over 970875.99 frames.], batch size: 22, lr: 1.97e-04
2022-05-07 02:54:46,493 INFO [train.py:715] (4/8) Epoch 11, batch 11700, loss[loss=0.1259, simple_loss=0.2054, pruned_loss=0.02322, over 4969.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2086, pruned_loss=0.03139, over 971640.80 frames.], batch size: 24, lr: 1.97e-04
2022-05-07 02:55:25,411 INFO [train.py:715] (4/8) Epoch 11, batch 11750, loss[loss=0.1156, simple_loss=0.1933, pruned_loss=0.01897, over 4865.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2091, pruned_loss=0.03152, over 972751.05 frames.], batch size: 20, lr: 1.97e-04
2022-05-07 02:56:04,644 INFO [train.py:715] (4/8) Epoch 11, batch 11800, loss[loss=0.1497, simple_loss=0.2169, pruned_loss=0.04127, over 4979.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03174, over 973218.08 frames.], batch size: 28, lr: 1.97e-04
2022-05-07 02:56:43,733 INFO [train.py:715] (4/8) Epoch 11, batch 11850, loss[loss=0.129, simple_loss=0.202, pruned_loss=0.02802, over 4838.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03174, over 973476.49 frames.], batch size: 26, lr: 1.97e-04
2022-05-07 02:57:23,429 INFO [train.py:715] (4/8) Epoch 11, batch 11900, loss[loss=0.1837, simple_loss=0.2551, pruned_loss=0.05619, over 4840.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03166, over 973249.31 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 02:58:03,769 INFO [train.py:715] (4/8) Epoch 11, batch 11950, loss[loss=0.1372, simple_loss=0.2083, pruned_loss=0.03301, over 4879.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03148, over 972810.12 frames.], batch size: 22, lr: 1.97e-04
2022-05-07 02:58:43,563 INFO [train.py:715] (4/8) Epoch 11, batch 12000, loss[loss=0.1283, simple_loss=0.2052, pruned_loss=0.02575, over 4911.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03196, over 971761.29 frames.], batch size: 17, lr: 1.97e-04
2022-05-07 02:58:43,564 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 02:58:53,274 INFO [train.py:742] (4/8) Epoch 11, validation: loss=0.1061, simple_loss=0.1902, pruned_loss=0.01096, over 914524.00 frames.
2022-05-07 02:59:33,231 INFO [train.py:715] (4/8) Epoch 11, batch 12050, loss[loss=0.1174, simple_loss=0.201, pruned_loss=0.01689, over 4830.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03227, over 971523.63 frames.], batch size: 13, lr: 1.97e-04
2022-05-07 03:00:12,665 INFO [train.py:715] (4/8) Epoch 11, batch 12100, loss[loss=0.1073, simple_loss=0.1865, pruned_loss=0.01408, over 4809.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03251, over 971262.25 frames.], batch size: 25, lr: 1.97e-04
2022-05-07 03:00:51,875 INFO [train.py:715] (4/8) Epoch 11, batch 12150, loss[loss=0.1524, simple_loss=0.2385, pruned_loss=0.03319, over 4802.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.03242, over 971151.55 frames.], batch size: 21, lr: 1.97e-04
2022-05-07 03:01:31,401 INFO [train.py:715] (4/8) Epoch 11, batch 12200, loss[loss=0.1503, simple_loss=0.2295, pruned_loss=0.03554, over 4986.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.0325, over 971387.46 frames.], batch size: 25, lr: 1.97e-04
2022-05-07 03:02:09,902 INFO [train.py:715] (4/8) Epoch 11, batch 12250, loss[loss=0.1484, simple_loss=0.2393, pruned_loss=0.02874, over 4933.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2119, pruned_loss=0.03229, over 971512.91 frames.], batch size: 29, lr: 1.97e-04
2022-05-07 03:02:49,518 INFO [train.py:715] (4/8) Epoch 11, batch 12300, loss[loss=0.1155, simple_loss=0.1884, pruned_loss=0.02131, over 4648.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2123, pruned_loss=0.03261, over 972036.46 frames.], batch size: 13, lr: 1.97e-04
2022-05-07 03:03:29,337 INFO [train.py:715] (4/8) Epoch 11, batch 12350, loss[loss=0.1515, simple_loss=0.2385, pruned_loss=0.03227, over 4909.00 frames.], tot_loss[loss=0.1392, simple_loss=0.213, pruned_loss=0.03275, over 972856.80 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 03:04:08,694 INFO [train.py:715] (4/8) Epoch 11, batch 12400, loss[loss=0.129, simple_loss=0.2121, pruned_loss=0.02296, over 4812.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.03289, over 971750.54 frames.], batch size: 27, lr: 1.97e-04
2022-05-07 03:04:46,932 INFO [train.py:715] (4/8) Epoch 11, batch 12450, loss[loss=0.1255, simple_loss=0.2046, pruned_loss=0.02318, over 4948.00 frames.], tot_loss[loss=0.139, simple_loss=0.2129, pruned_loss=0.03258, over 971391.73 frames.], batch size: 35, lr: 1.97e-04
2022-05-07 03:05:26,165 INFO [train.py:715] (4/8) Epoch 11, batch 12500, loss[loss=0.1323, simple_loss=0.2129, pruned_loss=0.02587, over 4966.00 frames.], tot_loss[loss=0.1393, simple_loss=0.213, pruned_loss=0.0328, over 971940.34 frames.], batch size: 24, lr: 1.97e-04
2022-05-07 03:06:05,434 INFO [train.py:715] (4/8) Epoch 11, batch 12550, loss[loss=0.1221, simple_loss=0.1905, pruned_loss=0.02683, over 4771.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2127, pruned_loss=0.03271, over 971551.48 frames.], batch size: 18, lr: 1.97e-04
2022-05-07 03:06:44,093 INFO [train.py:715] (4/8) Epoch 11, batch 12600, loss[loss=0.1368, simple_loss=0.2047, pruned_loss=0.03444, over 4824.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2125, pruned_loss=0.03268, over 971935.02 frames.], batch size: 13, lr: 1.97e-04
2022-05-07 03:07:23,080 INFO [train.py:715] (4/8) Epoch 11, batch 12650, loss[loss=0.1563, simple_loss=0.2186, pruned_loss=0.04698, over 4772.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2139, pruned_loss=0.03351, over 973168.02 frames.], batch size: 14, lr: 1.97e-04
2022-05-07 03:08:02,195 INFO [train.py:715] (4/8) Epoch 11, batch 12700, loss[loss=0.1412, simple_loss=0.2089, pruned_loss=0.03669, over 4964.00 frames.], tot_loss[loss=0.1405, simple_loss=0.2139, pruned_loss=0.03356, over 972834.03 frames.], batch size: 35, lr: 1.97e-04
2022-05-07 03:08:40,888 INFO [train.py:715] (4/8) Epoch 11, batch 12750, loss[loss=0.1714, simple_loss=0.2417, pruned_loss=0.05049, over 4817.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2129, pruned_loss=0.03316, over 973256.73 frames.], batch size: 26, lr: 1.97e-04
2022-05-07 03:09:19,302 INFO [train.py:715] (4/8) Epoch 11, batch 12800, loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03039, over 4799.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.0336, over 972185.60 frames.], batch size: 21, lr: 1.97e-04
2022-05-07 03:09:58,879 INFO [train.py:715] (4/8) Epoch 11, batch 12850, loss[loss=0.1152, simple_loss=0.1967, pruned_loss=0.0168, over 4934.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03295, over 972290.36 frames.], batch size: 23, lr: 1.97e-04
2022-05-07 03:10:38,289 INFO [train.py:715] (4/8) Epoch 11, batch 12900, loss[loss=0.1197, simple_loss=0.1867, pruned_loss=0.02637, over 4917.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03244, over 972173.55 frames.], batch size: 18, lr: 1.97e-04
2022-05-07 03:11:17,930 INFO [train.py:715] (4/8) Epoch 11, batch 12950, loss[loss=0.1138, simple_loss=0.1917, pruned_loss=0.01795, over 4859.00 frames.], tot_loss[loss=0.1384, simple_loss=0.212, pruned_loss=0.03242, over 972538.89 frames.], batch size: 20, lr: 1.97e-04
2022-05-07 03:11:56,709 INFO [train.py:715] (4/8) Epoch 11, batch 13000, loss[loss=0.1364, simple_loss=0.2052, pruned_loss=0.03381, over 4763.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2115, pruned_loss=0.03219, over 972368.12 frames.], batch size: 16, lr: 1.97e-04
2022-05-07 03:12:36,379 INFO [train.py:715] (4/8) Epoch 11, batch 13050, loss[loss=0.1513, simple_loss=0.2118, pruned_loss=0.04537, over 4942.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2122, pruned_loss=0.03271, over 972608.99 frames.], batch size: 35, lr: 1.97e-04
2022-05-07 03:13:15,473 INFO [train.py:715] (4/8) Epoch 11, batch 13100, loss[loss=0.1114, simple_loss=0.1777, pruned_loss=0.02255, over 4964.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.03249, over 973384.77 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:13:53,586 INFO [train.py:715] (4/8) Epoch 11, batch 13150, loss[loss=0.1287, simple_loss=0.2087, pruned_loss=0.02439, over 4794.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03254, over 972718.04 frames.], batch size: 18, lr: 1.97e-04
2022-05-07 03:14:32,700 INFO [train.py:715] (4/8) Epoch 11, batch 13200, loss[loss=0.1484, simple_loss=0.2228, pruned_loss=0.03697, over 4960.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03333, over 973237.03 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:15:11,059 INFO [train.py:715] (4/8) Epoch 11, batch 13250, loss[loss=0.1381, simple_loss=0.2035, pruned_loss=0.03632, over 4787.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03339, over 973595.97 frames.], batch size: 12, lr: 1.97e-04
2022-05-07 03:15:50,453 INFO [train.py:715] (4/8) Epoch 11, batch 13300, loss[loss=0.1332, simple_loss=0.2018, pruned_loss=0.03233, over 4957.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2128, pruned_loss=0.0337, over 974005.42 frames.], batch size: 21, lr: 1.97e-04
2022-05-07 03:16:29,351 INFO [train.py:715] (4/8) Epoch 11, batch 13350, loss[loss=0.1523, simple_loss=0.2253, pruned_loss=0.0396, over 4856.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2126, pruned_loss=0.03398, over 973653.01 frames.], batch size: 30, lr: 1.97e-04
2022-05-07 03:17:08,598 INFO [train.py:715] (4/8) Epoch 11, batch 13400, loss[loss=0.1549, simple_loss=0.2223, pruned_loss=0.04377, over 4896.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2124, pruned_loss=0.03334, over 973810.95 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 03:17:47,309 INFO [train.py:715] (4/8) Epoch 11, batch 13450, loss[loss=0.1317, simple_loss=0.2042, pruned_loss=0.0296, over 4953.00 frames.], tot_loss[loss=0.14, simple_loss=0.2125, pruned_loss=0.03373, over 973803.98 frames.], batch size: 35, lr: 1.97e-04
2022-05-07 03:18:26,311 INFO [train.py:715] (4/8) Epoch 11, batch 13500, loss[loss=0.1615, simple_loss=0.228, pruned_loss=0.04751, over 4945.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2134, pruned_loss=0.03403, over 973806.52 frames.], batch size: 35, lr: 1.97e-04
2022-05-07 03:19:05,023 INFO [train.py:715] (4/8) Epoch 11, batch 13550, loss[loss=0.143, simple_loss=0.2188, pruned_loss=0.03362, over 4892.00 frames.], tot_loss[loss=0.1409, simple_loss=0.2136, pruned_loss=0.03406, over 973777.52 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 03:19:44,149 INFO [train.py:715] (4/8) Epoch 11, batch 13600, loss[loss=0.1199, simple_loss=0.1898, pruned_loss=0.02502, over 4753.00 frames.], tot_loss[loss=0.1404, simple_loss=0.2133, pruned_loss=0.03376, over 973364.82 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 03:20:22,539 INFO [train.py:715] (4/8) Epoch 11, batch 13650, loss[loss=0.1314, simple_loss=0.2095, pruned_loss=0.02669, over 4903.00 frames.], tot_loss[loss=0.14, simple_loss=0.2129, pruned_loss=0.03356, over 973058.06 frames.], batch size: 17, lr: 1.97e-04
2022-05-07 03:21:00,720 INFO [train.py:715] (4/8) Epoch 11, batch 13700, loss[loss=0.1485, simple_loss=0.2115, pruned_loss=0.04274, over 4785.00 frames.], tot_loss[loss=0.1403, simple_loss=0.2134, pruned_loss=0.03362, over 972939.39 frames.], batch size: 18, lr: 1.97e-04
2022-05-07 03:21:39,795 INFO [train.py:715] (4/8) Epoch 11, batch 13750, loss[loss=0.1439, simple_loss=0.2045, pruned_loss=0.04169, over 4921.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2122, pruned_loss=0.03336, over 971861.52 frames.], batch size: 18, lr: 1.97e-04
2022-05-07 03:22:19,175 INFO [train.py:715] (4/8) Epoch 11, batch 13800, loss[loss=0.144, simple_loss=0.2172, pruned_loss=0.03544, over 4905.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03288, over 972401.82 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 03:22:57,642 INFO [train.py:715] (4/8) Epoch 11, batch 13850, loss[loss=0.1367, simple_loss=0.2045, pruned_loss=0.03442, over 4954.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.03274, over 972221.54 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:23:37,053 INFO [train.py:715] (4/8) Epoch 11, batch 13900, loss[loss=0.1048, simple_loss=0.1761, pruned_loss=0.01673, over 4793.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2124, pruned_loss=0.03305, over 972369.18 frames.], batch size: 24, lr: 1.97e-04
2022-05-07 03:24:16,009 INFO [train.py:715] (4/8) Epoch 11, batch 13950, loss[loss=0.1468, simple_loss=0.2181, pruned_loss=0.03772, over 4696.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03276, over 972726.02 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:24:55,180 INFO [train.py:715] (4/8) Epoch 11, batch 14000, loss[loss=0.1482, simple_loss=0.2227, pruned_loss=0.03686, over 4814.00 frames.], tot_loss[loss=0.1389, simple_loss=0.212, pruned_loss=0.03284, over 971710.05 frames.], batch size: 25, lr: 1.97e-04
2022-05-07 03:25:34,610 INFO [train.py:715] (4/8) Epoch 11, batch 14050, loss[loss=0.1464, simple_loss=0.2128, pruned_loss=0.03999, over 4966.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03256, over 971715.60 frames.], batch size: 35, lr: 1.97e-04
2022-05-07 03:26:14,344 INFO [train.py:715] (4/8) Epoch 11, batch 14100, loss[loss=0.1336, simple_loss=0.2112, pruned_loss=0.02801, over 4903.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2129, pruned_loss=0.03292, over 973177.52 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 03:26:53,615 INFO [train.py:715] (4/8) Epoch 11, batch 14150, loss[loss=0.1462, simple_loss=0.2243, pruned_loss=0.03404, over 4759.00 frames.], tot_loss[loss=0.1392, simple_loss=0.213, pruned_loss=0.03274, over 972869.47 frames.], batch size: 18, lr: 1.97e-04
2022-05-07 03:27:32,883 INFO [train.py:715] (4/8) Epoch 11, batch 14200, loss[loss=0.1536, simple_loss=0.2315, pruned_loss=0.0379, over 4893.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2121, pruned_loss=0.03242, over 972591.77 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 03:28:13,034 INFO [train.py:715] (4/8) Epoch 11, batch 14250, loss[loss=0.1586, simple_loss=0.2438, pruned_loss=0.03669, over 4839.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2118, pruned_loss=0.03244, over 973313.15 frames.], batch size: 30, lr: 1.97e-04
2022-05-07 03:28:53,038 INFO [train.py:715] (4/8) Epoch 11, batch 14300, loss[loss=0.1129, simple_loss=0.1818, pruned_loss=0.02203, over 4919.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03205, over 973329.42 frames.], batch size: 23, lr: 1.97e-04
2022-05-07 03:29:32,305 INFO [train.py:715] (4/8) Epoch 11, batch 14350, loss[loss=0.139, simple_loss=0.2011, pruned_loss=0.03847, over 4788.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03194, over 973548.91 frames.], batch size: 14, lr: 1.97e-04
2022-05-07 03:30:12,255 INFO [train.py:715] (4/8) Epoch 11, batch 14400, loss[loss=0.1479, simple_loss=0.227, pruned_loss=0.03441, over 4744.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.0317, over 972255.92 frames.], batch size: 16, lr: 1.97e-04
2022-05-07 03:30:52,528 INFO [train.py:715] (4/8) Epoch 11, batch 14450, loss[loss=0.1412, simple_loss=0.221, pruned_loss=0.03068, over 4941.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03258, over 972341.02 frames.], batch size: 29, lr: 1.97e-04
2022-05-07 03:31:31,940 INFO [train.py:715] (4/8) Epoch 11, batch 14500, loss[loss=0.1484, simple_loss=0.222, pruned_loss=0.03746, over 4872.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03293, over 972862.63 frames.], batch size: 32, lr: 1.97e-04
2022-05-07 03:32:11,439 INFO [train.py:715] (4/8) Epoch 11, batch 14550, loss[loss=0.1432, simple_loss=0.2084, pruned_loss=0.03896, over 4901.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03257, over 972783.62 frames.], batch size: 16, lr: 1.97e-04
2022-05-07 03:32:51,263 INFO [train.py:715] (4/8) Epoch 11, batch 14600, loss[loss=0.1283, simple_loss=0.197, pruned_loss=0.02978, over 4929.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.03249, over 972445.90 frames.], batch size: 18, lr: 1.97e-04
2022-05-07 03:33:30,637 INFO [train.py:715] (4/8) Epoch 11, batch 14650, loss[loss=0.1451, simple_loss=0.2151, pruned_loss=0.03756, over 4699.00 frames.], tot_loss[loss=0.138, simple_loss=0.2113, pruned_loss=0.03233, over 971689.46 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:34:09,053 INFO [train.py:715] (4/8) Epoch 11, batch 14700, loss[loss=0.1613, simple_loss=0.2387, pruned_loss=0.04194, over 4920.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03201, over 972140.30 frames.], batch size: 18, lr: 1.97e-04
2022-05-07 03:34:48,549 INFO [train.py:715] (4/8) Epoch 11, batch 14750, loss[loss=0.1304, simple_loss=0.2064, pruned_loss=0.02724, over 4758.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.0317, over 971661.09 frames.], batch size: 19, lr: 1.97e-04
2022-05-07 03:35:27,679 INFO [train.py:715] (4/8) Epoch 11, batch 14800, loss[loss=0.1363, simple_loss=0.2168, pruned_loss=0.02794, over 4784.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03145, over 971724.58 frames.], batch size: 18, lr: 1.97e-04
2022-05-07 03:36:06,361 INFO [train.py:715] (4/8) Epoch 11, batch 14850, loss[loss=0.1195, simple_loss=0.1954, pruned_loss=0.02176, over 4820.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03201, over 971395.37 frames.], batch size: 12, lr: 1.97e-04
2022-05-07 03:36:45,863 INFO [train.py:715] (4/8) Epoch 11, batch 14900, loss[loss=0.161, simple_loss=0.2369, pruned_loss=0.04255, over 4912.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03238, over 971605.69 frames.], batch size: 23, lr: 1.97e-04
2022-05-07 03:37:25,088 INFO [train.py:715] (4/8) Epoch 11, batch 14950, loss[loss=0.1295, simple_loss=0.2029, pruned_loss=0.02806, over 4704.00 frames.], tot_loss[loss=0.137, simple_loss=0.2107, pruned_loss=0.03167, over 971319.03 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:38:03,589 INFO [train.py:715] (4/8) Epoch 11, batch 15000, loss[loss=0.129, simple_loss=0.2037, pruned_loss=0.02718, over 4969.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2114, pruned_loss=0.03189, over 970978.79 frames.], batch size: 15, lr: 1.97e-04
2022-05-07 03:38:03,590 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 03:38:13,228 INFO [train.py:742] (4/8) Epoch 11, validation: loss=0.106, simple_loss=0.1901, pruned_loss=0.01091, over 914524.00 frames.
2022-05-07 03:38:52,001 INFO [train.py:715] (4/8) Epoch 11, batch 15050, loss[loss=0.1579, simple_loss=0.2408, pruned_loss=0.03746, over 4940.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03229, over 971004.84 frames.], batch size: 23, lr: 1.97e-04
2022-05-07 03:39:30,959 INFO [train.py:715] (4/8) Epoch 11, batch 15100, loss[loss=0.1112, simple_loss=0.1763, pruned_loss=0.02306, over 4795.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03196, over 970613.68 frames.], batch size: 12, lr: 1.97e-04
2022-05-07 03:40:10,671 INFO [train.py:715] (4/8) Epoch 11, batch 15150, loss[loss=0.1458, simple_loss=0.2188, pruned_loss=0.03641, over 4839.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03222, over 971791.09 frames.], batch size: 25, lr: 1.97e-04
2022-05-07 03:40:49,842 INFO [train.py:715] (4/8) Epoch 11, batch 15200, loss[loss=0.1393, simple_loss=0.2127, pruned_loss=0.0329, over 4961.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03239, over 972206.26 frames.], batch size: 24, lr: 1.97e-04
2022-05-07 03:41:28,411 INFO [train.py:715] (4/8) Epoch 11, batch 15250, loss[loss=0.1083, simple_loss=0.1805, pruned_loss=0.01809, over 4915.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2121, pruned_loss=0.03252, over 971568.77 frames.], batch size: 29, lr: 1.97e-04
2022-05-07 03:42:07,670 INFO [train.py:715] (4/8) Epoch 11, batch 15300, loss[loss=0.146, simple_loss=0.2249, pruned_loss=0.03359, over 4972.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2115, pruned_loss=0.0319, over 971871.56 frames.], batch size: 24, lr: 1.97e-04
2022-05-07 03:42:46,991 INFO [train.py:715] (4/8) Epoch 11, batch 15350, loss[loss=0.1596, simple_loss=0.2278, pruned_loss=0.04566, over 4924.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03247, over 971866.15 frames.], batch size: 29, lr: 1.96e-04
2022-05-07 03:43:25,863 INFO [train.py:715] (4/8) Epoch 11, batch 15400, loss[loss=0.1346, simple_loss=0.2076, pruned_loss=0.03078, over 4787.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2125, pruned_loss=0.03226, over 972281.62 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 03:44:04,606 INFO [train.py:715] (4/8) Epoch 11, batch 15450, loss[loss=0.1318, simple_loss=0.2095, pruned_loss=0.02699, over 4979.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2129, pruned_loss=0.03265, over 972869.27 frames.], batch size: 24, lr: 1.96e-04
2022-05-07 03:44:44,028 INFO [train.py:715] (4/8) Epoch 11, batch 15500, loss[loss=0.1724, simple_loss=0.2363, pruned_loss=0.05422, over 4791.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2137, pruned_loss=0.03305, over 972541.50 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 03:45:23,172 INFO [train.py:715] (4/8) Epoch 11, batch 15550, loss[loss=0.1389, simple_loss=0.2069, pruned_loss=0.0355, over 4882.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2135, pruned_loss=0.03294, over 972016.19 frames.], batch size: 22, lr: 1.96e-04
2022-05-07 03:46:01,707 INFO [train.py:715] (4/8) Epoch 11, batch 15600, loss[loss=0.1428, simple_loss=0.2243, pruned_loss=0.03067, over 4757.00 frames.], tot_loss[loss=0.1393, simple_loss=0.213, pruned_loss=0.03279, over 972309.60 frames.], batch size: 19, lr: 1.96e-04
2022-05-07 03:46:40,879 INFO [train.py:715] (4/8) Epoch 11, batch 15650, loss[loss=0.1653, simple_loss=0.236, pruned_loss=0.04735, over 4971.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2121, pruned_loss=0.03253, over 972438.48 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 03:47:19,840 INFO [train.py:715] (4/8) Epoch 11, batch 15700, loss[loss=0.125, simple_loss=0.2015, pruned_loss=0.02425, over 4919.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2127, pruned_loss=0.03256, over 972531.59 frames.], batch size: 29, lr: 1.96e-04
2022-05-07 03:47:58,645 INFO [train.py:715] (4/8) Epoch 11, batch 15750, loss[loss=0.1276, simple_loss=0.2048, pruned_loss=0.02519, over 4878.00 frames.], tot_loss[loss=0.138, simple_loss=0.2119, pruned_loss=0.03203, over 972194.48 frames.], batch size: 16, lr: 1.96e-04
2022-05-07 03:48:37,391 INFO [train.py:715] (4/8) Epoch 11, batch 15800, loss[loss=0.1469, simple_loss=0.209, pruned_loss=0.04237, over 4775.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03163, over 972117.02 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 03:49:16,771 INFO [train.py:715] (4/8) Epoch 11, batch 15850, loss[loss=0.1411, simple_loss=0.2195, pruned_loss=0.03136, over 4891.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03217, over 972777.26 frames.], batch size: 18, lr: 1.96e-04
2022-05-07 03:49:55,696 INFO [train.py:715] (4/8) Epoch 11, batch 15900, loss[loss=0.1196, simple_loss=0.1884, pruned_loss=0.02542, over 4839.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2118, pruned_loss=0.03227, over 972987.98 frames.], batch size: 13, lr: 1.96e-04
2022-05-07 03:50:34,611 INFO [train.py:715] (4/8) Epoch 11, batch 15950, loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02902, over 4856.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2125, pruned_loss=0.03257, over 972826.35 frames.], batch size: 32, lr: 1.96e-04
2022-05-07 03:51:13,824 INFO [train.py:715] (4/8) Epoch 11, batch 16000, loss[loss=0.188, simple_loss=0.2689, pruned_loss=0.05355, over 4888.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2127, pruned_loss=0.03247, over 972902.39 frames.], batch size: 22, lr: 1.96e-04
2022-05-07 03:51:53,248 INFO [train.py:715] (4/8) Epoch 11, batch 16050, loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03538, over 4702.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2122, pruned_loss=0.03229, over 972285.76 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 03:52:31,938 INFO [train.py:715] (4/8) Epoch 11, batch 16100, loss[loss=0.1132, simple_loss=0.1995, pruned_loss=0.01345, over 4943.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2116, pruned_loss=0.03196, over 973011.20 frames.], batch size: 21, lr: 1.96e-04
2022-05-07 03:53:10,815 INFO [train.py:715] (4/8) Epoch 11, batch 16150, loss[loss=0.1442, simple_loss=0.2121, pruned_loss=0.03818, over 4971.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2124, pruned_loss=0.03232, over 973271.90 frames.], batch size: 14, lr: 1.96e-04
2022-05-07 03:53:50,404 INFO [train.py:715] (4/8) Epoch 11, batch 16200, loss[loss=0.1563, simple_loss=0.2295, pruned_loss=0.04159, over 4894.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2117, pruned_loss=0.03209, over 974153.26 frames.], batch size: 19, lr: 1.96e-04
2022-05-07 03:54:29,885 INFO [train.py:715] (4/8) Epoch 11, batch 16250, loss[loss=0.1594, simple_loss=0.2204, pruned_loss=0.04916, over 4906.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2124, pruned_loss=0.03244, over 973530.48 frames.], batch size: 39, lr: 1.96e-04
2022-05-07 03:55:08,234 INFO [train.py:715] (4/8) Epoch 11, batch 16300, loss[loss=0.1476, simple_loss=0.2185, pruned_loss=0.03836, over 4967.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2115, pruned_loss=0.03201, over 973533.95 frames.], batch size: 35, lr: 1.96e-04
2022-05-07 03:55:47,432 INFO [train.py:715] (4/8) Epoch 11, batch 16350, loss[loss=0.179, simple_loss=0.2335, pruned_loss=0.06224, over 4802.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2111, pruned_loss=0.03188, over 973561.08 frames.], batch size: 13, lr: 1.96e-04
2022-05-07 03:56:26,683 INFO [train.py:715] (4/8) Epoch 11, batch 16400, loss[loss=0.1439, simple_loss=0.2153, pruned_loss=0.03619, over 4692.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2109, pruned_loss=0.03137, over 973336.09 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 03:57:05,178 INFO [train.py:715] (4/8) Epoch 11, batch 16450, loss[loss=0.1227, simple_loss=0.195, pruned_loss=0.02518, over 4774.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2117, pruned_loss=0.03178, over 973093.41 frames.], batch size: 18, lr: 1.96e-04
2022-05-07 03:57:44,149 INFO [train.py:715] (4/8) Epoch 11, batch 16500, loss[loss=0.1358, simple_loss=0.202, pruned_loss=0.03474, over 4938.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03191, over 972158.62 frames.], batch size: 29, lr: 1.96e-04
2022-05-07 03:58:23,674 INFO [train.py:715] (4/8) Epoch 11, batch 16550, loss[loss=0.1369, simple_loss=0.2049, pruned_loss=0.0344, over 4991.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03206, over 972268.29 frames.], batch size: 14, lr: 1.96e-04
2022-05-07 03:59:02,825 INFO [train.py:715] (4/8) Epoch 11, batch 16600, loss[loss=0.1445, simple_loss=0.2149, pruned_loss=0.03704, over 4852.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03188, over 972269.20 frames.], batch size: 32, lr: 1.96e-04
2022-05-07 03:59:41,211 INFO [train.py:715] (4/8) Epoch 11, batch 16650, loss[loss=0.1412, simple_loss=0.216, pruned_loss=0.03318, over 4989.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03219, over 972391.00 frames.], batch size: 14, lr: 1.96e-04
2022-05-07 04:00:20,433 INFO [train.py:715] (4/8) Epoch 11, batch 16700, loss[loss=0.1232, simple_loss=0.199, pruned_loss=0.0237, over 4966.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2108, pruned_loss=0.03177, over 973400.27 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 04:00:59,401 INFO [train.py:715] (4/8) Epoch 11, batch 16750, loss[loss=0.1345, simple_loss=0.2132, pruned_loss=0.02792, over 4979.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03248, over 973372.05 frames.], batch size: 14, lr: 1.96e-04
2022-05-07 04:01:38,342 INFO [train.py:715] (4/8) Epoch 11, batch 16800, loss[loss=0.111, simple_loss=0.1875, pruned_loss=0.01728, over 4793.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03247, over 972568.67 frames.], batch size: 21, lr: 1.96e-04
2022-05-07 04:02:17,996 INFO [train.py:715] (4/8) Epoch 11, batch 16850, loss[loss=0.1393, simple_loss=0.2042, pruned_loss=0.03718, over 4838.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03289, over 973186.84 frames.], batch size: 13, lr: 1.96e-04
2022-05-07 04:02:57,560 INFO [train.py:715] (4/8) Epoch 11, batch 16900, loss[loss=0.1505, simple_loss=0.2327, pruned_loss=0.0342, over 4831.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.03286, over 972983.27 frames.], batch size: 26, lr: 1.96e-04
2022-05-07 04:03:37,028 INFO [train.py:715] (4/8) Epoch 11, batch 16950, loss[loss=0.1255, simple_loss=0.2043, pruned_loss=0.02335, over 4829.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03238, over 972971.62 frames.], batch size: 13, lr: 1.96e-04
2022-05-07 04:04:15,766 INFO [train.py:715] (4/8) Epoch 11, batch 17000, loss[loss=0.1144, simple_loss=0.1881, pruned_loss=0.02032, over 4989.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.03292, over 973362.84 frames.], batch size: 25, lr: 1.96e-04
2022-05-07 04:04:55,495 INFO [train.py:715] (4/8) Epoch 11, batch 17050, loss[loss=0.1334, simple_loss=0.2186, pruned_loss=0.0241, over 4825.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03295, over 974191.82 frames.], batch size: 26, lr: 1.96e-04
2022-05-07 04:05:38,133 INFO [train.py:715] (4/8) Epoch 11, batch 17100, loss[loss=0.1496, simple_loss=0.2428, pruned_loss=0.02819, over 4828.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03271, over 973155.26 frames.], batch size: 27, lr: 1.96e-04
2022-05-07 04:06:17,131 INFO [train.py:715] (4/8) Epoch 11, batch 17150, loss[loss=0.139, simple_loss=0.2144, pruned_loss=0.03182, over 4974.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03274, over 974034.36 frames.], batch size: 24, lr: 1.96e-04
2022-05-07 04:06:56,396 INFO [train.py:715] (4/8) Epoch 11, batch 17200, loss[loss=0.116, simple_loss=0.2025, pruned_loss=0.01479, over 4824.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03272, over 973934.24 frames.], batch size: 26, lr: 1.96e-04
2022-05-07 04:07:35,862 INFO [train.py:715] (4/8) Epoch 11, batch 17250, loss[loss=0.1467, simple_loss=0.2219, pruned_loss=0.03571, over 4816.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.03246, over 973318.61 frames.], batch size: 25, lr: 1.96e-04
2022-05-07 04:08:14,914 INFO [train.py:715] (4/8) Epoch 11, batch 17300, loss[loss=0.1574, simple_loss=0.2264, pruned_loss=0.04421, over 4974.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.0327, over 972425.18 frames.], batch size: 35, lr: 1.96e-04
2022-05-07 04:08:53,648 INFO [train.py:715] (4/8) Epoch 11, batch 17350, loss[loss=0.12, simple_loss=0.1955, pruned_loss=0.02226, over 4798.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2121, pruned_loss=0.03252, over 972735.12 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 04:09:33,976 INFO [train.py:715] (4/8) Epoch 11, batch 17400, loss[loss=0.1285, simple_loss=0.2092, pruned_loss=0.02394, over 4973.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03265, over 972837.59 frames.], batch size: 28, lr: 1.96e-04
2022-05-07 04:10:14,471 INFO [train.py:715] (4/8) Epoch 11, batch 17450, loss[loss=0.1121, simple_loss=0.1909, pruned_loss=0.01662, over 4774.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03216, over 972599.48 frames.], batch size: 14, lr: 1.96e-04
2022-05-07 04:10:53,785 INFO [train.py:715] (4/8) Epoch 11, batch 17500, loss[loss=0.1178, simple_loss=0.1932, pruned_loss=0.02119, over 4817.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03266, over 972514.10 frames.], batch size: 25, lr: 1.96e-04
2022-05-07 04:11:33,221 INFO [train.py:715] (4/8) Epoch 11, batch 17550, loss[loss=0.1282, simple_loss=0.2121, pruned_loss=0.02215, over 4810.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03238, over 972350.87 frames.], batch size: 27, lr: 1.96e-04
2022-05-07 04:12:12,576 INFO [train.py:715] (4/8) Epoch 11, batch 17600, loss[loss=0.1573, simple_loss=0.2274, pruned_loss=0.04357, over 4780.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03226, over 972293.79 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 04:12:51,731 INFO [train.py:715] (4/8) Epoch 11, batch 17650, loss[loss=0.1384, simple_loss=0.2184, pruned_loss=0.02919, over 4782.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03258, over 972725.83 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 04:13:29,968 INFO [train.py:715] (4/8) Epoch 11, batch 17700, loss[loss=0.1533, simple_loss=0.2244, pruned_loss=0.04112, over 4970.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03242, over 972045.65 frames.], batch size: 39, lr: 1.96e-04
2022-05-07 04:14:09,453 INFO [train.py:715] (4/8) Epoch 11, batch 17750, loss[loss=0.1311, simple_loss=0.215, pruned_loss=0.02362, over 4846.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03245, over 972648.01 frames.], batch size: 20, lr: 1.96e-04
2022-05-07 04:14:49,014 INFO [train.py:715] (4/8) Epoch 11, batch 17800, loss[loss=0.1548, simple_loss=0.234, pruned_loss=0.03782, over 4906.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2118, pruned_loss=0.03295, over 972527.03 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 04:15:27,264 INFO [train.py:715] (4/8) Epoch 11, batch 17850, loss[loss=0.1389, simple_loss=0.2038, pruned_loss=0.03697, over 4861.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.03298, over 972744.47 frames.], batch size: 32, lr: 1.96e-04
2022-05-07 04:16:06,255 INFO [train.py:715] (4/8) Epoch 11, batch 17900, loss[loss=0.1467, simple_loss=0.2229, pruned_loss=0.03523, over 4843.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03322, over 972289.87 frames.], batch size: 30, lr: 1.96e-04
2022-05-07 04:16:45,879 INFO [train.py:715] (4/8) Epoch 11, batch 17950, loss[loss=0.1577, simple_loss=0.2206, pruned_loss=0.0474, over 4769.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03296, over 972666.01 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 04:17:24,870 INFO [train.py:715] (4/8) Epoch 11, batch 18000, loss[loss=0.1652, simple_loss=0.2389, pruned_loss=0.0458, over 4885.00 frames.], tot_loss[loss=0.1401, simple_loss=0.2132, pruned_loss=0.03349, over 972863.96 frames.], batch size: 16, lr: 1.96e-04
2022-05-07 04:17:24,871 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 04:17:34,461 INFO [train.py:742] (4/8) Epoch 11, validation: loss=0.1061, simple_loss=0.1903, pruned_loss=0.01092, over 914524.00 frames.
2022-05-07 04:18:14,138 INFO [train.py:715] (4/8) Epoch 11, batch 18050, loss[loss=0.1444, simple_loss=0.219, pruned_loss=0.03496, over 4745.00 frames.], tot_loss[loss=0.139, simple_loss=0.2124, pruned_loss=0.03285, over 972998.35 frames.], batch size: 19, lr: 1.96e-04
2022-05-07 04:18:53,410 INFO [train.py:715] (4/8) Epoch 11, batch 18100, loss[loss=0.1294, simple_loss=0.2059, pruned_loss=0.02644, over 4962.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2135, pruned_loss=0.03287, over 972469.65 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 04:19:32,615 INFO [train.py:715] (4/8) Epoch 11, batch 18150, loss[loss=0.119, simple_loss=0.1878, pruned_loss=0.02515, over 4966.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2138, pruned_loss=0.03283, over 971891.88 frames.], batch size: 14, lr: 1.96e-04
2022-05-07 04:20:12,191 INFO [train.py:715] (4/8) Epoch 11, batch 18200, loss[loss=0.1551, simple_loss=0.228, pruned_loss=0.04108, over 4761.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2131, pruned_loss=0.03275, over 971720.75 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 04:20:50,625 INFO [train.py:715] (4/8) Epoch 11, batch 18250, loss[loss=0.1451, simple_loss=0.2157, pruned_loss=0.03729, over 4932.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2129, pruned_loss=0.03341, over 970977.01 frames.], batch size: 39, lr: 1.96e-04
2022-05-07 04:21:29,929 INFO [train.py:715] (4/8) Epoch 11, batch 18300, loss[loss=0.1401, simple_loss=0.2218, pruned_loss=0.02918, over 4852.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03266, over 971290.57 frames.], batch size: 20, lr: 1.96e-04
2022-05-07 04:22:09,173 INFO [train.py:715] (4/8) Epoch 11, batch 18350, loss[loss=0.1276, simple_loss=0.2069, pruned_loss=0.02411, over 4986.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2112, pruned_loss=0.03269, over 971299.76 frames.], batch size: 28, lr: 1.96e-04
2022-05-07 04:22:47,571 INFO [train.py:715] (4/8) Epoch 11, batch 18400, loss[loss=0.1184, simple_loss=0.1957, pruned_loss=0.02054, over 4791.00 frames.], tot_loss[loss=0.139, simple_loss=0.2121, pruned_loss=0.03293, over 971473.24 frames.], batch size: 14, lr: 1.96e-04
2022-05-07 04:23:25,986 INFO [train.py:715] (4/8) Epoch 11, batch 18450, loss[loss=0.1139, simple_loss=0.1887, pruned_loss=0.01956, over 4868.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03309, over 971540.12 frames.], batch size: 22, lr: 1.96e-04
2022-05-07 04:24:05,022 INFO [train.py:715] (4/8) Epoch 11, batch 18500, loss[loss=0.1305, simple_loss=0.2118, pruned_loss=0.02458, over 4751.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03259, over 972138.96 frames.], batch size: 16, lr: 1.96e-04
2022-05-07 04:24:44,460 INFO [train.py:715] (4/8) Epoch 11, batch 18550, loss[loss=0.141, simple_loss=0.2138, pruned_loss=0.03409, over 4903.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.03216, over 973015.31 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 04:25:22,563 INFO [train.py:715] (4/8) Epoch 11, batch 18600, loss[loss=0.1193, simple_loss=0.1911, pruned_loss=0.02375, over 4818.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.03232, over 972784.70 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 04:26:01,408 INFO [train.py:715] (4/8) Epoch 11, batch 18650, loss[loss=0.1055, simple_loss=0.1815, pruned_loss=0.01475, over 4748.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2112, pruned_loss=0.03188, over 973029.36 frames.], batch size: 19, lr: 1.96e-04
2022-05-07 04:26:40,664 INFO [train.py:715] (4/8) Epoch 11, batch 18700, loss[loss=0.1261, simple_loss=0.1884, pruned_loss=0.0319, over 4818.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2119, pruned_loss=0.03223, over 973676.79 frames.], batch size: 14, lr: 1.96e-04
2022-05-07 04:27:18,908 INFO [train.py:715] (4/8) Epoch 11, batch 18750, loss[loss=0.1198, simple_loss=0.1956, pruned_loss=0.02204, over 4699.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2115, pruned_loss=0.03215, over 972443.69 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 04:27:57,976 INFO [train.py:715] (4/8) Epoch 11, batch 18800, loss[loss=0.1209, simple_loss=0.1844, pruned_loss=0.02868, over 4816.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03209, over 972741.83 frames.], batch size: 13, lr: 1.96e-04
2022-05-07 04:28:36,590 INFO [train.py:715] (4/8) Epoch 11, batch 18850, loss[loss=0.09945, simple_loss=0.1691, pruned_loss=0.0149, over 4980.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.03252, over 972280.35 frames.], batch size: 14, lr: 1.96e-04
2022-05-07 04:29:16,483 INFO [train.py:715] (4/8) Epoch 11, batch 18900, loss[loss=0.1079, simple_loss=0.1709, pruned_loss=0.02245, over 4788.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03198, over 971949.98 frames.], batch size: 12, lr: 1.96e-04
2022-05-07 04:29:55,265 INFO [train.py:715] (4/8) Epoch 11, batch 18950, loss[loss=0.1373, simple_loss=0.2162, pruned_loss=0.02919, over 4830.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03184, over 972119.92 frames.], batch size: 30, lr: 1.96e-04
2022-05-07 04:30:34,363 INFO [train.py:715] (4/8) Epoch 11, batch 19000, loss[loss=0.1569, simple_loss=0.2326, pruned_loss=0.04057, over 4919.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.03237, over 972549.94 frames.], batch size: 19, lr: 1.96e-04
2022-05-07 04:31:13,457 INFO [train.py:715] (4/8) Epoch 11, batch 19050, loss[loss=0.1405, simple_loss=0.2143, pruned_loss=0.03334, over 4711.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2113, pruned_loss=0.03267, over 971509.73 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 04:31:52,052 INFO [train.py:715] (4/8) Epoch 11, batch 19100, loss[loss=0.1306, simple_loss=0.21, pruned_loss=0.02565, over 4910.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03258, over 971546.72 frames.], batch size: 17, lr: 1.96e-04
2022-05-07 04:32:31,177 INFO [train.py:715] (4/8) Epoch 11, batch 19150, loss[loss=0.1412, simple_loss=0.2217, pruned_loss=0.03034, over 4855.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.03273, over 971990.92 frames.], batch size: 20, lr: 1.96e-04
2022-05-07 04:33:10,078 INFO [train.py:715] (4/8) Epoch 11, batch 19200, loss[loss=0.1356, simple_loss=0.2145, pruned_loss=0.02839, over 4978.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.03244, over 972844.48 frames.], batch size: 25, lr: 1.96e-04
2022-05-07 04:33:49,485 INFO [train.py:715] (4/8) Epoch 11, batch 19250, loss[loss=0.1327, simple_loss=0.204, pruned_loss=0.03066, over 4971.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.03245, over 972986.44 frames.], batch size: 15, lr: 1.96e-04
2022-05-07 04:34:27,828 INFO [train.py:715] (4/8) Epoch 11, batch 19300, loss[loss=0.1591, simple_loss=0.231, pruned_loss=0.04362, over 4793.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03242, over 972886.41 frames.], batch size: 24, lr: 1.96e-04
2022-05-07 04:35:06,980 INFO [train.py:715] (4/8) Epoch 11, batch 19350, loss[loss=0.1622, simple_loss=0.2227, pruned_loss=0.05088, over 4904.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.03222, over 973329.03 frames.], batch size: 18, lr: 1.96e-04
2022-05-07 04:35:46,159 INFO [train.py:715] (4/8) Epoch 11, batch 19400, loss[loss=0.153, simple_loss=0.2253, pruned_loss=0.04033, over 4855.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2107, pruned_loss=0.03256, over 972426.89 frames.], batch size: 32, lr: 1.96e-04
2022-05-07 04:36:24,108 INFO [train.py:715] (4/8) Epoch 11, batch 19450, loss[loss=0.1455, simple_loss=0.2179, pruned_loss=0.03649, over 4968.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2102, pruned_loss=0.0323, over 972270.30 frames.], batch size: 24, lr: 1.95e-04
2022-05-07 04:37:03,252 INFO [train.py:715] (4/8) Epoch 11, batch 19500, loss[loss=0.1408, simple_loss=0.1968, pruned_loss=0.04244, over 4968.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2095, pruned_loss=0.03167, over 973291.33 frames.], batch size: 31, lr: 1.95e-04
2022-05-07 04:37:42,221 INFO [train.py:715] (4/8) Epoch 11, batch 19550, loss[loss=0.154, simple_loss=0.2268, pruned_loss=0.04057, over 4771.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03187, over 973646.47 frames.], batch size: 17, lr: 1.95e-04
2022-05-07 04:38:20,965 INFO [train.py:715] (4/8) Epoch 11, batch 19600, loss[loss=0.1122, simple_loss=0.1851, pruned_loss=0.01969, over 4930.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03228, over 973060.61 frames.], batch size: 23, lr: 1.95e-04
2022-05-07 04:38:59,545 INFO [train.py:715] (4/8) Epoch 11, batch 19650, loss[loss=0.1364, simple_loss=0.1995, pruned_loss=0.0366, over 4840.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03217, over 973449.98 frames.], batch size: 30, lr: 1.95e-04
2022-05-07 04:39:38,337 INFO [train.py:715] (4/8) Epoch 11, batch 19700, loss[loss=0.09562, simple_loss=0.1619, pruned_loss=0.01466, over 4987.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03178, over 973425.24 frames.], batch size: 14, lr: 1.95e-04
2022-05-07 04:40:17,421 INFO [train.py:715] (4/8) Epoch 11, batch 19750, loss[loss=0.164, simple_loss=0.233, pruned_loss=0.04753, over 4939.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2112, pruned_loss=0.03191, over 974141.48 frames.], batch size: 39, lr: 1.95e-04
2022-05-07 04:40:55,508 INFO [train.py:715] (4/8) Epoch 11, batch 19800, loss[loss=0.124, simple_loss=0.1972, pruned_loss=0.0254, over 4931.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03272, over 974160.36 frames.], batch size: 29, lr: 1.95e-04
2022-05-07 04:41:35,005 INFO [train.py:715] (4/8) Epoch 11, batch 19850, loss[loss=0.1242, simple_loss=0.1977, pruned_loss=0.0254, over 4953.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03324, over 973905.97 frames.], batch size: 21, lr: 1.95e-04
2022-05-07 04:42:14,373 INFO [train.py:715] (4/8) Epoch 11, batch 19900, loss[loss=0.1207, simple_loss=0.1893, pruned_loss=0.02601, over 4949.00 frames.], tot_loss[loss=0.1392, simple_loss=0.212, pruned_loss=0.03326, over 973331.96 frames.], batch size: 21, lr: 1.95e-04
2022-05-07 04:42:53,604 INFO [train.py:715] (4/8) Epoch 11, batch 19950, loss[loss=0.1221, simple_loss=0.1985, pruned_loss=0.02282, over 4940.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2116, pruned_loss=0.03282, over 973335.97 frames.], batch size: 29, lr: 1.95e-04
2022-05-07 04:43:32,802 INFO [train.py:715] (4/8) Epoch 11, batch 20000, loss[loss=0.1649, simple_loss=0.2209, pruned_loss=0.05448, over 4804.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03284, over 974075.82 frames.], batch size: 21, lr: 1.95e-04
2022-05-07 04:44:11,786 INFO [train.py:715] (4/8) Epoch 11, batch 20050, loss[loss=0.1229, simple_loss=0.1986, pruned_loss=0.02361, over 4907.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03227, over 973343.59 frames.], batch size: 17, lr: 1.95e-04
2022-05-07 04:44:51,049 INFO [train.py:715] (4/8) Epoch 11, batch 20100, loss[loss=0.1478, simple_loss=0.2051, pruned_loss=0.04528, over 4814.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2111, pruned_loss=0.03261, over 973719.87 frames.], batch size: 25, lr: 1.95e-04
2022-05-07 04:45:29,362 INFO [train.py:715] (4/8) Epoch 11, batch 20150, loss[loss=0.1526, simple_loss=0.2359, pruned_loss=0.03462, over 4994.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2114, pruned_loss=0.03263, over 973645.78 frames.], batch size: 14, lr: 1.95e-04
2022-05-07 04:46:08,145 INFO [train.py:715] (4/8) Epoch 11, batch 20200, loss[loss=0.1142, simple_loss=0.191, pruned_loss=0.01871, over 4978.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2107, pruned_loss=0.0323, over 973080.05 frames.], batch size: 28, lr: 1.95e-04
2022-05-07 04:46:46,983 INFO [train.py:715] (4/8) Epoch 11, batch 20250, loss[loss=0.1208, simple_loss=0.1916, pruned_loss=0.02501, over 4945.00 frames.], tot_loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03269, over 973154.55 frames.], batch size: 29, lr: 1.95e-04
2022-05-07 04:47:25,725 INFO [train.py:715] (4/8) Epoch 11, batch 20300, loss[loss=0.1326, simple_loss=0.2037, pruned_loss=0.03077, over 4859.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03277, over 973328.73 frames.], batch size: 30, lr: 1.95e-04
2022-05-07 04:48:04,824 INFO [train.py:715] (4/8) Epoch 11, batch 20350, loss[loss=0.1389, simple_loss=0.2161, pruned_loss=0.03089, over 4904.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.0324, over 972320.62 frames.], batch size: 17, lr: 1.95e-04
2022-05-07 04:48:43,797 INFO [train.py:715] (4/8) Epoch 11, batch 20400, loss[loss=0.1341, simple_loss=0.2112, pruned_loss=0.02854, over 4874.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2121, pruned_loss=0.03227, over 972244.38 frames.], batch size: 20, lr: 1.95e-04
2022-05-07 04:49:23,227 INFO [train.py:715] (4/8) Epoch 11, batch 20450, loss[loss=0.1588, simple_loss=0.2353, pruned_loss=0.04118, over 4832.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2124, pruned_loss=0.03256, over 972383.11 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 04:50:01,759 INFO [train.py:715] (4/8) Epoch 11, batch 20500, loss[loss=0.1514, simple_loss=0.217, pruned_loss=0.04294, over 4859.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03267, over 972934.68 frames.], batch size: 32, lr: 1.95e-04
2022-05-07 04:50:41,079 INFO [train.py:715] (4/8) Epoch 11, batch 20550, loss[loss=0.135, simple_loss=0.2003, pruned_loss=0.03487, over 4895.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03238, over 972895.67 frames.], batch size: 19, lr: 1.95e-04
2022-05-07 04:51:19,710 INFO [train.py:715] (4/8) Epoch 11, batch 20600, loss[loss=0.1356, simple_loss=0.2152, pruned_loss=0.028, over 4937.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03177, over 973314.01 frames.], batch size: 21, lr: 1.95e-04
2022-05-07 04:51:57,489 INFO [train.py:715] (4/8) Epoch 11, batch 20650, loss[loss=0.1385, simple_loss=0.2237, pruned_loss=0.02658, over 4815.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2114, pruned_loss=0.0319, over 972976.18 frames.], batch size: 27, lr: 1.95e-04
2022-05-07 04:52:36,866 INFO [train.py:715] (4/8) Epoch 11, batch 20700, loss[loss=0.1414, simple_loss=0.2194, pruned_loss=0.03173, over 4823.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2114, pruned_loss=0.03181, over 971648.10 frames.], batch size: 26, lr: 1.95e-04
2022-05-07 04:53:16,099 INFO [train.py:715] (4/8) Epoch 11, batch 20750, loss[loss=0.1405, simple_loss=0.2249, pruned_loss=0.0281, over 4775.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03204, over 971102.11 frames.], batch size: 18, lr: 1.95e-04
2022-05-07 04:53:54,799 INFO [train.py:715] (4/8) Epoch 11, batch 20800, loss[loss=0.1759, simple_loss=0.2374, pruned_loss=0.05723, over 4827.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03203, over 971812.22 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 04:54:33,170 INFO [train.py:715] (4/8) Epoch 11, batch 20850, loss[loss=0.1633, simple_loss=0.2367, pruned_loss=0.04495, over 4980.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.03191, over 972170.24 frames.], batch size: 40, lr: 1.95e-04
2022-05-07 04:55:12,418 INFO [train.py:715] (4/8) Epoch 11, batch 20900, loss[loss=0.1306, simple_loss=0.209, pruned_loss=0.02609, over 4815.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2118, pruned_loss=0.03217, over 971796.85 frames.], batch size: 25, lr: 1.95e-04
2022-05-07 04:55:52,029 INFO [train.py:715] (4/8) Epoch 11, batch 20950, loss[loss=0.1286, simple_loss=0.2048, pruned_loss=0.02623, over 4897.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03198, over 972092.21 frames.], batch size: 22, lr: 1.95e-04
2022-05-07 04:56:30,993 INFO [train.py:715] (4/8) Epoch 11, batch 21000, loss[loss=0.1455, simple_loss=0.227, pruned_loss=0.032, over 4823.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.0318, over 972932.62 frames.], batch size: 25, lr: 1.95e-04
2022-05-07 04:56:30,994 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 04:56:40,628 INFO [train.py:742] (4/8) Epoch 11, validation: loss=0.106, simple_loss=0.19, pruned_loss=0.01097, over 914524.00 frames.
2022-05-07 04:57:20,095 INFO [train.py:715] (4/8) Epoch 11, batch 21050, loss[loss=0.1529, simple_loss=0.2311, pruned_loss=0.0373, over 4912.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03205, over 972554.45 frames.], batch size: 39, lr: 1.95e-04
2022-05-07 04:57:59,827 INFO [train.py:715] (4/8) Epoch 11, batch 21100, loss[loss=0.1546, simple_loss=0.2161, pruned_loss=0.04651, over 4991.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.03222, over 971756.60 frames.], batch size: 14, lr: 1.95e-04
2022-05-07 04:58:38,862 INFO [train.py:715] (4/8) Epoch 11, batch 21150, loss[loss=0.1401, simple_loss=0.2142, pruned_loss=0.03297, over 4938.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03215, over 972247.62 frames.], batch size: 21, lr: 1.95e-04
2022-05-07 04:59:18,200 INFO [train.py:715] (4/8) Epoch 11, batch 21200, loss[loss=0.1652, simple_loss=0.2403, pruned_loss=0.0451, over 4855.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.0319, over 972055.08 frames.], batch size: 20, lr: 1.95e-04
2022-05-07 04:59:56,325 INFO [train.py:715] (4/8) Epoch 11, batch 21250, loss[loss=0.1515, simple_loss=0.2267, pruned_loss=0.03811, over 4773.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03225, over 972453.77 frames.], batch size: 18, lr: 1.95e-04
2022-05-07 05:00:35,640 INFO [train.py:715] (4/8) Epoch 11, batch 21300, loss[loss=0.1324, simple_loss=0.2074, pruned_loss=0.02868, over 4979.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2109, pruned_loss=0.03263, over 972846.38 frames.], batch size: 35, lr: 1.95e-04
2022-05-07 05:01:15,026 INFO [train.py:715] (4/8) Epoch 11, batch 21350, loss[loss=0.1429, simple_loss=0.209, pruned_loss=0.03838, over 4871.00 frames.], tot_loss[loss=0.137, simple_loss=0.2101, pruned_loss=0.03193, over 972706.49 frames.], batch size: 39, lr: 1.95e-04
2022-05-07 05:01:53,535 INFO [train.py:715] (4/8) Epoch 11, batch 21400, loss[loss=0.147, simple_loss=0.2192, pruned_loss=0.03746, over 4873.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03177, over 972650.61 frames.], batch size: 32, lr: 1.95e-04
2022-05-07 05:02:32,173 INFO [train.py:715] (4/8) Epoch 11, batch 21450, loss[loss=0.1478, simple_loss=0.2299, pruned_loss=0.03286, over 4913.00 frames.], tot_loss[loss=0.137, simple_loss=0.2102, pruned_loss=0.0319, over 972556.20 frames.], batch size: 19, lr: 1.95e-04
2022-05-07 05:03:11,026 INFO [train.py:715] (4/8) Epoch 11, batch 21500, loss[loss=0.1308, simple_loss=0.2068, pruned_loss=0.02744, over 4816.00 frames.], tot_loss[loss=0.1369, simple_loss=0.21, pruned_loss=0.03188, over 972495.87 frames.], batch size: 25, lr: 1.95e-04
2022-05-07 05:03:50,390 INFO [train.py:715] (4/8) Epoch 11, batch 21550, loss[loss=0.1437, simple_loss=0.2188, pruned_loss=0.0343, over 4836.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.03152, over 972973.38 frames.], batch size: 30, lr: 1.95e-04
2022-05-07 05:04:28,679 INFO [train.py:715] (4/8) Epoch 11, batch 21600, loss[loss=0.13, simple_loss=0.213, pruned_loss=0.0235, over 4693.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.03156, over 972715.15 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 05:05:07,529 INFO [train.py:715] (4/8) Epoch 11, batch 21650, loss[loss=0.1435, simple_loss=0.2119, pruned_loss=0.03757, over 4882.00 frames.], tot_loss[loss=0.1369, simple_loss=0.21, pruned_loss=0.03188, over 973075.20 frames.], batch size: 22, lr: 1.95e-04
2022-05-07 05:05:47,577 INFO [train.py:715] (4/8) Epoch 11, batch 21700, loss[loss=0.1473, simple_loss=0.214, pruned_loss=0.04033, over 4830.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.03206, over 972551.89 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 05:06:26,870 INFO [train.py:715] (4/8) Epoch 11, batch 21750, loss[loss=0.1483, simple_loss=0.2346, pruned_loss=0.03104, over 4850.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03191, over 973634.16 frames.], batch size: 30, lr: 1.95e-04
2022-05-07 05:07:07,059 INFO [train.py:715] (4/8) Epoch 11, batch 21800, loss[loss=0.1511, simple_loss=0.2259, pruned_loss=0.03817, over 4745.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03169, over 973808.04 frames.], batch size: 16, lr: 1.95e-04
2022-05-07 05:07:46,731 INFO [train.py:715] (4/8) Epoch 11, batch 21850, loss[loss=0.1423, simple_loss=0.2118, pruned_loss=0.03635, over 4934.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.03196, over 974194.40 frames.], batch size: 29, lr: 1.95e-04
2022-05-07 05:08:27,222 INFO [train.py:715] (4/8) Epoch 11, batch 21900, loss[loss=0.1605, simple_loss=0.237, pruned_loss=0.04197, over 4832.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2111, pruned_loss=0.03261, over 973274.19 frames.], batch size: 25, lr: 1.95e-04
2022-05-07 05:09:06,444 INFO [train.py:715] (4/8) Epoch 11, batch 21950, loss[loss=0.1416, simple_loss=0.2227, pruned_loss=0.03025, over 4871.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.0322, over 973092.20 frames.], batch size: 22, lr: 1.95e-04
2022-05-07 05:09:46,763 INFO [train.py:715] (4/8) Epoch 11, batch 22000, loss[loss=0.1265, simple_loss=0.2139, pruned_loss=0.01957, over 4923.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2118, pruned_loss=0.03297, over 972722.93 frames.], batch size: 29, lr: 1.95e-04
2022-05-07 05:10:27,229 INFO [train.py:715] (4/8) Epoch 11, batch 22050, loss[loss=0.1661, simple_loss=0.2387, pruned_loss=0.04673, over 4796.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2121, pruned_loss=0.03323, over 972916.03 frames.], batch size: 21, lr: 1.95e-04
2022-05-07 05:11:05,498 INFO [train.py:715] (4/8) Epoch 11, batch 22100, loss[loss=0.1525, simple_loss=0.2146, pruned_loss=0.04523, over 4895.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2107, pruned_loss=0.03237, over 972519.57 frames.], batch size: 19, lr: 1.95e-04
2022-05-07 05:11:45,098 INFO [train.py:715] (4/8) Epoch 11, batch 22150, loss[loss=0.1174, simple_loss=0.1888, pruned_loss=0.02304, over 4650.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2104, pruned_loss=0.03246, over 971541.43 frames.], batch size: 13, lr: 1.95e-04
2022-05-07 05:12:24,690 INFO [train.py:715] (4/8) Epoch 11, batch 22200, loss[loss=0.1409, simple_loss=0.218, pruned_loss=0.03193, over 4815.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.03255, over 972109.98 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 05:13:03,453 INFO [train.py:715] (4/8) Epoch 11, batch 22250, loss[loss=0.1633, simple_loss=0.2399, pruned_loss=0.04332, over 4797.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03247, over 971330.54 frames.], batch size: 21, lr: 1.95e-04
2022-05-07 05:13:41,887 INFO [train.py:715] (4/8) Epoch 11, batch 22300, loss[loss=0.1269, simple_loss=0.1981, pruned_loss=0.02788, over 4949.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03255, over 971592.04 frames.], batch size: 21, lr: 1.95e-04
2022-05-07 05:14:21,103 INFO [train.py:715] (4/8) Epoch 11, batch 22350, loss[loss=0.1337, simple_loss=0.2226, pruned_loss=0.02243, over 4903.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03231, over 971676.88 frames.], batch size: 22, lr: 1.95e-04
2022-05-07 05:15:00,557 INFO [train.py:715] (4/8) Epoch 11, batch 22400, loss[loss=0.1278, simple_loss=0.2041, pruned_loss=0.02578, over 4828.00 frames.], tot_loss[loss=0.1383, simple_loss=0.212, pruned_loss=0.03224, over 971257.92 frames.], batch size: 25, lr: 1.95e-04
2022-05-07 05:15:38,490 INFO [train.py:715] (4/8) Epoch 11, batch 22450, loss[loss=0.1287, simple_loss=0.2069, pruned_loss=0.02528, over 4749.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2122, pruned_loss=0.03242, over 972246.70 frames.], batch size: 16, lr: 1.95e-04
2022-05-07 05:16:18,409 INFO [train.py:715] (4/8) Epoch 11, batch 22500, loss[loss=0.1401, simple_loss=0.203, pruned_loss=0.03865, over 4876.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2116, pruned_loss=0.03179, over 972578.45 frames.], batch size: 16, lr: 1.95e-04
2022-05-07 05:16:57,484 INFO [train.py:715] (4/8) Epoch 11, batch 22550, loss[loss=0.153, simple_loss=0.2175, pruned_loss=0.04426, over 4976.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2117, pruned_loss=0.03186, over 973062.94 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 05:17:36,656 INFO [train.py:715] (4/8) Epoch 11, batch 22600, loss[loss=0.1174, simple_loss=0.1909, pruned_loss=0.02197, over 4972.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03236, over 973027.13 frames.], batch size: 28, lr: 1.95e-04
2022-05-07 05:18:15,034 INFO [train.py:715] (4/8) Epoch 11, batch 22650, loss[loss=0.1658, simple_loss=0.2416, pruned_loss=0.04496, over 4930.00 frames.], tot_loss[loss=0.139, simple_loss=0.2125, pruned_loss=0.0328, over 973725.69 frames.], batch size: 23, lr: 1.95e-04
2022-05-07 05:18:54,213 INFO [train.py:715] (4/8) Epoch 11, batch 22700, loss[loss=0.1367, simple_loss=0.2039, pruned_loss=0.03479, over 4881.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03315, over 972745.35 frames.], batch size: 16, lr: 1.95e-04
2022-05-07 05:19:34,073 INFO [train.py:715] (4/8) Epoch 11, batch 22750, loss[loss=0.139, simple_loss=0.2099, pruned_loss=0.03405, over 4792.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03324, over 971627.18 frames.], batch size: 14, lr: 1.95e-04
2022-05-07 05:20:12,496 INFO [train.py:715] (4/8) Epoch 11, batch 22800, loss[loss=0.1196, simple_loss=0.1926, pruned_loss=0.02329, over 4766.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2121, pruned_loss=0.03333, over 971828.65 frames.], batch size: 19, lr: 1.95e-04
2022-05-07 05:20:52,297 INFO [train.py:715] (4/8) Epoch 11, batch 22850, loss[loss=0.1146, simple_loss=0.1909, pruned_loss=0.01916, over 4806.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2114, pruned_loss=0.03293, over 971846.31 frames.], batch size: 13, lr: 1.95e-04
2022-05-07 05:21:31,222 INFO [train.py:715] (4/8) Epoch 11, batch 22900, loss[loss=0.1611, simple_loss=0.2394, pruned_loss=0.04138, over 4812.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.03321, over 972717.04 frames.], batch size: 24, lr: 1.95e-04
2022-05-07 05:22:10,210 INFO [train.py:715] (4/8) Epoch 11, batch 22950, loss[loss=0.1916, simple_loss=0.2563, pruned_loss=0.06344, over 4776.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2125, pruned_loss=0.03362, over 973023.20 frames.], batch size: 18, lr: 1.95e-04
2022-05-07 05:22:48,360 INFO [train.py:715] (4/8) Epoch 11, batch 23000, loss[loss=0.1176, simple_loss=0.1815, pruned_loss=0.0268, over 4811.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2122, pruned_loss=0.03338, over 972419.86 frames.], batch size: 25, lr: 1.95e-04
2022-05-07 05:23:27,329 INFO [train.py:715] (4/8) Epoch 11, batch 23050, loss[loss=0.1655, simple_loss=0.2268, pruned_loss=0.05208, over 4835.00 frames.], tot_loss[loss=0.1391, simple_loss=0.212, pruned_loss=0.03315, over 973544.39 frames.], batch size: 30, lr: 1.95e-04
2022-05-07 05:24:06,661 INFO [train.py:715] (4/8) Epoch 11, batch 23100, loss[loss=0.1619, simple_loss=0.2337, pruned_loss=0.04506, over 4828.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2119, pruned_loss=0.03298, over 973667.22 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 05:24:44,408 INFO [train.py:715] (4/8) Epoch 11, batch 23150, loss[loss=0.1444, simple_loss=0.2074, pruned_loss=0.04067, over 4884.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2126, pruned_loss=0.03321, over 974165.94 frames.], batch size: 16, lr: 1.95e-04
2022-05-07 05:25:23,978 INFO [train.py:715] (4/8) Epoch 11, batch 23200, loss[loss=0.1367, simple_loss=0.2172, pruned_loss=0.02808, over 4909.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2126, pruned_loss=0.03342, over 973815.89 frames.], batch size: 17, lr: 1.95e-04
2022-05-07 05:26:02,909 INFO [train.py:715] (4/8) Epoch 11, batch 23250, loss[loss=0.1389, simple_loss=0.2157, pruned_loss=0.03104, over 4913.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2125, pruned_loss=0.03337, over 973247.88 frames.], batch size: 17, lr: 1.95e-04
2022-05-07 05:26:41,982 INFO [train.py:715] (4/8) Epoch 11, batch 23300, loss[loss=0.1565, simple_loss=0.2196, pruned_loss=0.04666, over 4710.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03267, over 971979.38 frames.], batch size: 15, lr: 1.95e-04
2022-05-07 05:27:20,071 INFO [train.py:715] (4/8) Epoch 11, batch 23350, loss[loss=0.1374, simple_loss=0.2059, pruned_loss=0.03446, over 4765.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2102, pruned_loss=0.03208, over 972125.57 frames.], batch size: 19, lr: 1.95e-04
2022-05-07 05:27:59,122 INFO [train.py:715] (4/8) Epoch 11, batch 23400, loss[loss=0.1344, simple_loss=0.204, pruned_loss=0.03236, over 4760.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2102, pruned_loss=0.03204, over 971756.86 frames.], batch size: 12, lr: 1.95e-04
2022-05-07 05:28:38,744 INFO [train.py:715] (4/8) Epoch 11, batch 23450, loss[loss=0.1257, simple_loss=0.2065, pruned_loss=0.02248, over 4964.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03192, over 972150.64 frames.], batch size: 25, lr: 1.95e-04
2022-05-07 05:29:16,868 INFO [train.py:715] (4/8) Epoch 11, batch 23500, loss[loss=0.1378, simple_loss=0.2121, pruned_loss=0.03174, over 4929.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03216, over 972089.65 frames.], batch size: 18, lr: 1.95e-04
2022-05-07 05:29:55,782 INFO [train.py:715] (4/8) Epoch 11, batch 23550, loss[loss=0.1113, simple_loss=0.1874, pruned_loss=0.01757, over 4933.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03203, over 972982.27 frames.], batch size: 29, lr: 1.95e-04
2022-05-07 05:30:34,766 INFO [train.py:715] (4/8) Epoch 11, batch 23600, loss[loss=0.1278, simple_loss=0.2093, pruned_loss=0.02318, over 4870.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03211, over 972544.72 frames.], batch size: 20, lr: 1.94e-04
2022-05-07 05:31:14,119 INFO [train.py:715] (4/8) Epoch 11, batch 23650, loss[loss=0.1324, simple_loss=0.2127, pruned_loss=0.02608, over 4889.00 frames.], tot_loss[loss=0.138, simple_loss=0.2116, pruned_loss=0.03219, over 972915.28 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 05:31:51,831 INFO [train.py:715] (4/8) Epoch 11, batch 23700, loss[loss=0.1416, simple_loss=0.2119, pruned_loss=0.03563, over 4885.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03218, over 972079.76 frames.], batch size: 16, lr: 1.94e-04
2022-05-07 05:32:30,812 INFO [train.py:715] (4/8) Epoch 11, batch 23750, loss[loss=0.1171, simple_loss=0.1837, pruned_loss=0.02524, over 4758.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03209, over 971609.02 frames.], batch size: 16, lr: 1.94e-04
2022-05-07 05:33:09,308 INFO [train.py:715] (4/8) Epoch 11, batch 23800, loss[loss=0.1352, simple_loss=0.2195, pruned_loss=0.02544, over 4970.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.0319, over 971963.37 frames.], batch size: 14, lr: 1.94e-04
2022-05-07 05:33:46,737 INFO [train.py:715] (4/8) Epoch 11, batch 23850, loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.03174, over 4986.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03155, over 971625.91 frames.], batch size: 28, lr: 1.94e-04
2022-05-07 05:34:24,310 INFO [train.py:715] (4/8) Epoch 11, batch 23900, loss[loss=0.1569, simple_loss=0.2293, pruned_loss=0.04226, over 4942.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03144, over 971335.92 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 05:35:01,655 INFO [train.py:715] (4/8) Epoch 11, batch 23950, loss[loss=0.159, simple_loss=0.2353, pruned_loss=0.04135, over 4968.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03142, over 971665.61 frames.], batch size: 39, lr: 1.94e-04
2022-05-07 05:35:39,342 INFO [train.py:715] (4/8) Epoch 11, batch 24000, loss[loss=0.1163, simple_loss=0.1947, pruned_loss=0.01899, over 4985.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03205, over 971647.06 frames.], batch size: 25, lr: 1.94e-04
2022-05-07 05:35:39,342 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 05:35:48,812 INFO [train.py:742] (4/8) Epoch 11, validation: loss=0.1059, simple_loss=0.19, pruned_loss=0.01092, over 914524.00 frames.
2022-05-07 05:36:27,138 INFO [train.py:715] (4/8) Epoch 11, batch 24050, loss[loss=0.1275, simple_loss=0.207, pruned_loss=0.02397, over 4820.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.03228, over 972010.55 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 05:37:04,268 INFO [train.py:715] (4/8) Epoch 11, batch 24100, loss[loss=0.1445, simple_loss=0.2189, pruned_loss=0.03504, over 4784.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2115, pruned_loss=0.03297, over 971992.67 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 05:37:42,096 INFO [train.py:715] (4/8) Epoch 11, batch 24150, loss[loss=0.1505, simple_loss=0.2237, pruned_loss=0.03864, over 4768.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2111, pruned_loss=0.03279, over 972557.28 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 05:38:20,368 INFO [train.py:715] (4/8) Epoch 11, batch 24200, loss[loss=0.1418, simple_loss=0.2254, pruned_loss=0.02914, over 4768.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2115, pruned_loss=0.033, over 971999.38 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 05:38:57,453 INFO [train.py:715] (4/8) Epoch 11, batch 24250, loss[loss=0.1322, simple_loss=0.2107, pruned_loss=0.02686, over 4780.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2103, pruned_loss=0.03247, over 971613.07 frames.], batch size: 14, lr: 1.94e-04
2022-05-07 05:39:35,484 INFO [train.py:715] (4/8) Epoch 11, batch 24300, loss[loss=0.1106, simple_loss=0.1883, pruned_loss=0.01643, over 4763.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2104, pruned_loss=0.03241, over 971727.68 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 05:40:13,073 INFO [train.py:715] (4/8) Epoch 11, batch 24350, loss[loss=0.1784, simple_loss=0.2501, pruned_loss=0.05339, over 4952.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03197, over 972091.70 frames.], batch size: 35, lr: 1.94e-04
2022-05-07 05:40:50,677 INFO [train.py:715] (4/8) Epoch 11, batch 24400, loss[loss=0.1336, simple_loss=0.199, pruned_loss=0.03405, over 4789.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2108, pruned_loss=0.03185, over 972492.44 frames.], batch size: 18, lr: 1.94e-04
2022-05-07 05:41:28,272 INFO [train.py:715] (4/8) Epoch 11, batch 24450, loss[loss=0.1328, simple_loss=0.2078, pruned_loss=0.02891, over 4832.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03178, over 972326.16 frames.], batch size: 13, lr: 1.94e-04
2022-05-07 05:42:06,386 INFO [train.py:715] (4/8) Epoch 11, batch 24500, loss[loss=0.1244, simple_loss=0.1857, pruned_loss=0.03161, over 4689.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2098, pruned_loss=0.03183, over 972187.24 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 05:42:45,026 INFO [train.py:715] (4/8) Epoch 11, batch 24550, loss[loss=0.1392, simple_loss=0.2188, pruned_loss=0.02982, over 4875.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03211, over 971926.66 frames.], batch size: 16, lr: 1.94e-04
2022-05-07 05:43:23,050 INFO [train.py:715] (4/8) Epoch 11, batch 24600, loss[loss=0.1654, simple_loss=0.2285, pruned_loss=0.05116, over 4971.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03256, over 972115.62 frames.], batch size: 35, lr: 1.94e-04
2022-05-07 05:44:01,527 INFO [train.py:715] (4/8) Epoch 11, batch 24650, loss[loss=0.1321, simple_loss=0.2135, pruned_loss=0.02535, over 4778.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.0322, over 972262.04 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 05:44:39,862 INFO [train.py:715] (4/8) Epoch 11, batch 24700, loss[loss=0.1168, simple_loss=0.1847, pruned_loss=0.02451, over 4966.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03164, over 972786.05 frames.], batch size: 35, lr: 1.94e-04
2022-05-07 05:45:18,488 INFO [train.py:715] (4/8) Epoch 11, batch 24750, loss[loss=0.1662, simple_loss=0.2347, pruned_loss=0.04884, over 4946.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03186, over 973196.18 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 05:45:56,383 INFO [train.py:715] (4/8) Epoch 11, batch 24800, loss[loss=0.1919, simple_loss=0.2422, pruned_loss=0.07076, over 4928.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03222, over 973384.84 frames.], batch size: 35, lr: 1.94e-04
2022-05-07 05:46:34,702 INFO [train.py:715] (4/8) Epoch 11, batch 24850, loss[loss=0.1158, simple_loss=0.1836, pruned_loss=0.024, over 4857.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03208, over 973752.11 frames.], batch size: 13, lr: 1.94e-04
2022-05-07 05:47:13,629 INFO [train.py:715] (4/8) Epoch 11, batch 24900, loss[loss=0.118, simple_loss=0.179, pruned_loss=0.02847, over 4837.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2102, pruned_loss=0.03199, over 972780.97 frames.], batch size: 12, lr: 1.94e-04
2022-05-07 05:47:51,693 INFO [train.py:715] (4/8) Epoch 11, batch 24950, loss[loss=0.1696, simple_loss=0.2377, pruned_loss=0.05077, over 4796.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03226, over 972920.03 frames.], batch size: 18, lr: 1.94e-04
2022-05-07 05:48:30,022 INFO [train.py:715] (4/8) Epoch 11, batch 25000, loss[loss=0.1238, simple_loss=0.2171, pruned_loss=0.01526, over 4889.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03166, over 972971.02 frames.], batch size: 22, lr: 1.94e-04
2022-05-07 05:49:08,319 INFO [train.py:715] (4/8) Epoch 11, batch 25050, loss[loss=0.1393, simple_loss=0.2097, pruned_loss=0.03442, over 4992.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.0326, over 973133.39 frames.], batch size: 14, lr: 1.94e-04
2022-05-07 05:49:49,680 INFO [train.py:715] (4/8) Epoch 11, batch 25100, loss[loss=0.1663, simple_loss=0.2344, pruned_loss=0.04906, over 4944.00 frames.], tot_loss[loss=0.1388, simple_loss=0.212, pruned_loss=0.03282, over 973092.27 frames.], batch size: 35, lr: 1.94e-04
2022-05-07 05:50:27,839 INFO [train.py:715] (4/8) Epoch 11, batch 25150, loss[loss=0.1309, simple_loss=0.2028, pruned_loss=0.02947, over 4818.00 frames.], tot_loss[loss=0.1388, simple_loss=0.212, pruned_loss=0.03276, over 972392.25 frames.], batch size: 13, lr: 1.94e-04
2022-05-07 05:51:06,431 INFO [train.py:715] (4/8) Epoch 11, batch 25200, loss[loss=0.1369, simple_loss=0.2086, pruned_loss=0.03258, over 4911.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.03297, over 972097.58 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 05:51:45,284 INFO [train.py:715] (4/8) Epoch 11, batch 25250, loss[loss=0.1197, simple_loss=0.1974, pruned_loss=0.02101, over 4887.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2118, pruned_loss=0.0329, over 971757.48 frames.], batch size: 22, lr: 1.94e-04
2022-05-07 05:52:23,561 INFO [train.py:715] (4/8) Epoch 11, batch 25300, loss[loss=0.1513, simple_loss=0.2107, pruned_loss=0.04598, over 4802.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2108, pruned_loss=0.03247, over 971266.45 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 05:53:01,961 INFO [train.py:715] (4/8) Epoch 11, batch 25350, loss[loss=0.1219, simple_loss=0.2052, pruned_loss=0.01933, over 4939.00 frames.], tot_loss[loss=0.1381, simple_loss=0.211, pruned_loss=0.03256, over 971388.87 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 05:53:40,601 INFO [train.py:715] (4/8) Epoch 11, batch 25400, loss[loss=0.1313, simple_loss=0.2069, pruned_loss=0.02788, over 4943.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.03225, over 972125.58 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 05:54:19,418 INFO [train.py:715] (4/8) Epoch 11, batch 25450, loss[loss=0.127, simple_loss=0.2153, pruned_loss=0.0194, over 4911.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03259, over 971693.25 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 05:54:57,470 INFO [train.py:715] (4/8) Epoch 11, batch 25500, loss[loss=0.1297, simple_loss=0.1944, pruned_loss=0.0325, over 4742.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.0324, over 972386.76 frames.], batch size: 16, lr: 1.94e-04
2022-05-07 05:55:36,080 INFO [train.py:715] (4/8) Epoch 11, batch 25550, loss[loss=0.1285, simple_loss=0.2024, pruned_loss=0.02724, over 4913.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2102, pruned_loss=0.03231, over 972599.84 frames.], batch size: 18, lr: 1.94e-04
2022-05-07 05:56:15,314 INFO [train.py:715] (4/8) Epoch 11, batch 25600, loss[loss=0.1318, simple_loss=0.1967, pruned_loss=0.03341, over 4821.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2111, pruned_loss=0.03295, over 971478.23 frames.], batch size: 13, lr: 1.94e-04
2022-05-07 05:56:53,594 INFO [train.py:715] (4/8) Epoch 11, batch 25650, loss[loss=0.1555, simple_loss=0.2334, pruned_loss=0.03875, over 4967.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.03297, over 972035.41 frames.], batch size: 40, lr: 1.94e-04
2022-05-07 05:57:31,751 INFO [train.py:715] (4/8) Epoch 11, batch 25700, loss[loss=0.1547, simple_loss=0.2229, pruned_loss=0.04323, over 4738.00 frames.], tot_loss[loss=0.1383, simple_loss=0.211, pruned_loss=0.03279, over 971447.94 frames.], batch size: 16, lr: 1.94e-04
2022-05-07 05:58:10,581 INFO [train.py:715] (4/8) Epoch 11, batch 25750, loss[loss=0.1115, simple_loss=0.1895, pruned_loss=0.01679, over 4937.00 frames.], tot_loss[loss=0.138, simple_loss=0.2109, pruned_loss=0.03261, over 972301.38 frames.], batch size: 29, lr: 1.94e-04
2022-05-07 05:58:48,900 INFO [train.py:715] (4/8) Epoch 11, batch 25800, loss[loss=0.1517, simple_loss=0.2183, pruned_loss=0.04257, over 4968.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2108, pruned_loss=0.0329, over 972650.52 frames.], batch size: 35, lr: 1.94e-04
2022-05-07 05:59:26,904 INFO [train.py:715] (4/8) Epoch 11, batch 25850, loss[loss=0.1218, simple_loss=0.1944, pruned_loss=0.02454, over 4833.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2099, pruned_loss=0.0325, over 972118.27 frames.], batch size: 26, lr: 1.94e-04
2022-05-07 06:00:05,562 INFO [train.py:715] (4/8) Epoch 11, batch 25900, loss[loss=0.1786, simple_loss=0.2416, pruned_loss=0.05786, over 4984.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2104, pruned_loss=0.03246, over 972408.79 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 06:00:44,269 INFO [train.py:715] (4/8) Epoch 11, batch 25950, loss[loss=0.1401, simple_loss=0.2108, pruned_loss=0.03474, over 4974.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2106, pruned_loss=0.03257, over 971899.33 frames.], batch size: 24, lr: 1.94e-04
2022-05-07 06:01:22,318 INFO [train.py:715] (4/8) Epoch 11, batch 26000, loss[loss=0.1235, simple_loss=0.1962, pruned_loss=0.02535, over 4902.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2105, pruned_loss=0.03252, over 972116.89 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 06:02:00,400 INFO [train.py:715] (4/8) Epoch 11, batch 26050, loss[loss=0.1333, simple_loss=0.2114, pruned_loss=0.02764, over 4986.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2104, pruned_loss=0.03216, over 971410.41 frames.], batch size: 25, lr: 1.94e-04
2022-05-07 06:02:38,954 INFO [train.py:715] (4/8) Epoch 11, batch 26100, loss[loss=0.1645, simple_loss=0.2313, pruned_loss=0.04886, over 4858.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2107, pruned_loss=0.03253, over 971074.64 frames.], batch size: 20, lr: 1.94e-04
2022-05-07 06:03:17,345 INFO [train.py:715] (4/8) Epoch 11, batch 26150, loss[loss=0.1338, simple_loss=0.2027, pruned_loss=0.03239, over 4813.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03211, over 971310.51 frames.], batch size: 25, lr: 1.94e-04
2022-05-07 06:03:55,314 INFO [train.py:715] (4/8) Epoch 11, batch 26200, loss[loss=0.1396, simple_loss=0.2209, pruned_loss=0.02918, over 4989.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2108, pruned_loss=0.03245, over 972287.88 frames.], batch size: 26, lr: 1.94e-04
2022-05-07 06:04:32,931 INFO [train.py:715] (4/8) Epoch 11, batch 26250, loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03153, over 4939.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03239, over 972819.49 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 06:05:10,975 INFO [train.py:715] (4/8) Epoch 11, batch 26300, loss[loss=0.1279, simple_loss=0.203, pruned_loss=0.02636, over 4799.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2107, pruned_loss=0.03261, over 972637.27 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 06:05:48,408 INFO [train.py:715] (4/8) Epoch 11, batch 26350, loss[loss=0.1744, simple_loss=0.2435, pruned_loss=0.05268, over 4828.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2101, pruned_loss=0.0323, over 972754.59 frames.], batch size: 26, lr: 1.94e-04
2022-05-07 06:06:25,428 INFO [train.py:715] (4/8) Epoch 11, batch 26400, loss[loss=0.1405, simple_loss=0.232, pruned_loss=0.02447, over 4905.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.0325, over 972999.37 frames.], batch size: 22, lr: 1.94e-04
2022-05-07 06:07:03,856 INFO [train.py:715] (4/8) Epoch 11, batch 26450, loss[loss=0.1594, simple_loss=0.2291, pruned_loss=0.04483, over 4976.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2106, pruned_loss=0.03243, over 972289.38 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 06:07:41,340 INFO [train.py:715] (4/8) Epoch 11, batch 26500, loss[loss=0.1267, simple_loss=0.2069, pruned_loss=0.02322, over 4908.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03239, over 972346.21 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 06:08:19,085 INFO [train.py:715] (4/8) Epoch 11, batch 26550, loss[loss=0.1429, simple_loss=0.2195, pruned_loss=0.03313, over 4790.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03254, over 972420.88 frames.], batch size: 24, lr: 1.94e-04
2022-05-07 06:08:56,822 INFO [train.py:715] (4/8) Epoch 11, batch 26600, loss[loss=0.1161, simple_loss=0.1916, pruned_loss=0.02032, over 4948.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.03291, over 972602.43 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 06:09:34,847 INFO [train.py:715] (4/8) Epoch 11, batch 26650, loss[loss=0.1358, simple_loss=0.1977, pruned_loss=0.037, over 4961.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.0325, over 972576.68 frames.], batch size: 14, lr: 1.94e-04
2022-05-07 06:10:12,912 INFO [train.py:715] (4/8) Epoch 11, batch 26700, loss[loss=0.1277, simple_loss=0.2118, pruned_loss=0.02182, over 4911.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03258, over 971340.06 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 06:10:49,898 INFO [train.py:715] (4/8) Epoch 11, batch 26750, loss[loss=0.146, simple_loss=0.2258, pruned_loss=0.03312, over 4743.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.0324, over 970809.53 frames.], batch size: 16, lr: 1.94e-04
2022-05-07 06:11:28,541 INFO [train.py:715] (4/8) Epoch 11, batch 26800, loss[loss=0.1731, simple_loss=0.2324, pruned_loss=0.05687, over 4695.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.03239, over 970855.31 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 06:12:06,145 INFO [train.py:715] (4/8) Epoch 11, batch 26850, loss[loss=0.1281, simple_loss=0.2007, pruned_loss=0.02779, over 4710.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2123, pruned_loss=0.03255, over 970623.36 frames.], batch size: 15, lr: 1.94e-04
2022-05-07 06:12:43,632 INFO [train.py:715] (4/8) Epoch 11, batch 26900, loss[loss=0.1251, simple_loss=0.2006, pruned_loss=0.02479, over 4799.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2121, pruned_loss=0.03289, over 972024.73 frames.], batch size: 21, lr: 1.94e-04
2022-05-07 06:13:21,272 INFO [train.py:715] (4/8) Epoch 11, batch 26950, loss[loss=0.1261, simple_loss=0.2035, pruned_loss=0.02431, over 4912.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.03257, over 972820.17 frames.], batch size: 19, lr: 1.94e-04
2022-05-07 06:13:59,654 INFO [train.py:715] (4/8) Epoch 11, batch 27000, loss[loss=0.1175, simple_loss=0.196, pruned_loss=0.01947, over 4812.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03231, over 972352.48 frames.], batch size: 25, lr: 1.94e-04
2022-05-07 06:13:59,654 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 06:14:09,117 INFO [train.py:742] (4/8) Epoch 11, validation: loss=0.1059, simple_loss=0.19, pruned_loss=0.01084, over 914524.00 frames.
2022-05-07 06:14:47,548 INFO [train.py:715] (4/8) Epoch 11, batch 27050, loss[loss=0.1085, simple_loss=0.1797, pruned_loss=0.01864, over 4905.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2111, pruned_loss=0.03267, over 972920.23 frames.], batch size: 23, lr: 1.94e-04
2022-05-07 06:15:25,150 INFO [train.py:715] (4/8) Epoch 11, batch 27100, loss[loss=0.1578, simple_loss=0.2242, pruned_loss=0.04574, over 4880.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2116, pruned_loss=0.033, over 972887.59 frames.], batch size: 16, lr: 1.94e-04
2022-05-07 06:16:02,382 INFO [train.py:715] (4/8) Epoch 11, batch 27150, loss[loss=0.1321, simple_loss=0.2244, pruned_loss=0.01988, over 4777.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03292, over 972611.78 frames.], batch size: 18, lr: 1.94e-04
2022-05-07 06:16:41,021 INFO [train.py:715] (4/8) Epoch 11, batch 27200, loss[loss=0.1289, simple_loss=0.2042, pruned_loss=0.02678, over 4944.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.0325, over 972169.21 frames.], batch size: 29, lr: 1.94e-04
2022-05-07 06:17:18,729 INFO [train.py:715] (4/8) Epoch 11, batch 27250, loss[loss=0.1534, simple_loss=0.232, pruned_loss=0.03745, over 4903.00 frames.], tot_loss[loss=0.138, simple_loss=0.2113, pruned_loss=0.0323, over 973257.90 frames.], batch size: 18, lr: 1.94e-04
2022-05-07 06:17:56,619 INFO [train.py:715] (4/8) Epoch 11, batch 27300, loss[loss=0.1337, simple_loss=0.2058, pruned_loss=0.0308, over 4977.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03215, over 973210.80 frames.], batch size: 25, lr: 1.94e-04
2022-05-07 06:18:34,288 INFO [train.py:715] (4/8) Epoch 11, batch 27350, loss[loss=0.1265, simple_loss=0.2014, pruned_loss=0.02577, over 4835.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03176, over 973582.62 frames.], batch size: 26, lr: 1.94e-04
2022-05-07 06:19:13,065 INFO [train.py:715] (4/8) Epoch 11, batch 27400, loss[loss=0.153, simple_loss=0.2282, pruned_loss=0.0389, over 4886.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03159, over 973627.65 frames.], batch size: 16, lr: 1.94e-04
2022-05-07 06:19:50,857 INFO [train.py:715] (4/8) Epoch 11, batch 27450, loss[loss=0.1195, simple_loss=0.2005, pruned_loss=0.01919, over 4917.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03186, over 973033.55 frames.], batch size: 23, lr: 1.94e-04
2022-05-07 06:20:28,121 INFO [train.py:715] (4/8) Epoch 11, batch 27500, loss[loss=0.1177, simple_loss=0.1999, pruned_loss=0.01777, over 4774.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03212, over 972651.68 frames.], batch size: 17, lr: 1.94e-04
2022-05-07 06:21:07,285 INFO [train.py:715] (4/8) Epoch 11, batch 27550, loss[loss=0.1288, simple_loss=0.2056, pruned_loss=0.026, over 4837.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03248, over 971836.09 frames.], batch size: 13, lr: 1.94e-04
2022-05-07 06:21:45,753 INFO [train.py:715] (4/8) Epoch 11, batch 27600, loss[loss=0.1514, simple_loss=0.2205, pruned_loss=0.04121, over 4851.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03252, over 972058.18 frames.], batch size: 32, lr: 1.94e-04
2022-05-07 06:22:23,478 INFO [train.py:715] (4/8) Epoch 11, batch 27650, loss[loss=0.1171, simple_loss=0.1974, pruned_loss=0.0184, over 4896.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03248, over 971801.67 frames.], batch size: 22, lr: 1.94e-04
2022-05-07 06:23:01,300 INFO [train.py:715] (4/8) Epoch 11, batch 27700, loss[loss=0.1218, simple_loss=0.1948, pruned_loss=0.02442, over 4779.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.0326, over 971479.01 frames.], batch size: 14, lr: 1.94e-04
2022-05-07 06:23:39,626 INFO [train.py:715] (4/8) Epoch 11, batch 27750, loss[loss=0.1662, simple_loss=0.2226, pruned_loss=0.05489, over 4973.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03291, over 971595.76 frames.], batch size: 35, lr: 1.94e-04
2022-05-07 06:24:17,573 INFO [train.py:715] (4/8) Epoch 11, batch 27800, loss[loss=0.1257, simple_loss=0.1997, pruned_loss=0.02584, over 4910.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.0323, over 971682.54 frames.], batch size: 29, lr: 1.93e-04
2022-05-07 06:24:54,557 INFO [train.py:715] (4/8) Epoch 11, batch 27850, loss[loss=0.1168, simple_loss=0.1916, pruned_loss=0.02098, over 4946.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03268, over 971652.28 frames.], batch size: 35, lr: 1.93e-04
2022-05-07 06:25:32,919 INFO [train.py:715] (4/8) Epoch 11, batch 27900, loss[loss=0.1367, simple_loss=0.2005, pruned_loss=0.03641, over 4760.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03283, over 971389.64 frames.], batch size: 16, lr: 1.93e-04
2022-05-07 06:26:10,974 INFO [train.py:715] (4/8) Epoch 11, batch 27950, loss[loss=0.14, simple_loss=0.1994, pruned_loss=0.04029, over 4878.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.0325, over 972397.77 frames.], batch size: 22, lr: 1.93e-04
2022-05-07 06:26:48,583 INFO [train.py:715] (4/8) Epoch 11, batch 28000, loss[loss=0.1437, simple_loss=0.2195, pruned_loss=0.03389, over 4915.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2118, pruned_loss=0.0326, over 972452.70 frames.], batch size: 39, lr: 1.93e-04
2022-05-07 06:27:26,140 INFO [train.py:715] (4/8) Epoch 11, batch 28050, loss[loss=0.2043, simple_loss=0.2602, pruned_loss=0.07422, over 4788.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03262, over 972287.52 frames.], batch size: 14, lr: 1.93e-04
2022-05-07 06:28:04,143 INFO [train.py:715] (4/8) Epoch 11, batch 28100, loss[loss=0.1575, simple_loss=0.2312, pruned_loss=0.0419, over 4922.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2118, pruned_loss=0.033, over 972488.73 frames.], batch size: 39, lr: 1.93e-04
2022-05-07 06:28:41,423 INFO [train.py:715] (4/8) Epoch 11, batch 28150, loss[loss=0.1524, simple_loss=0.2311, pruned_loss=0.03681, over 4816.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2119, pruned_loss=0.03263, over 972460.38 frames.], batch size: 25, lr: 1.93e-04
2022-05-07 06:29:18,870 INFO [train.py:715] (4/8) Epoch 11, batch 28200, loss[loss=0.1622, simple_loss=0.2335, pruned_loss=0.04543, over 4974.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.0332, over 972848.95 frames.], batch size: 24, lr: 1.93e-04
2022-05-07 06:29:57,424 INFO [train.py:715] (4/8) Epoch 11, batch 28250, loss[loss=0.1194, simple_loss=0.1948, pruned_loss=0.022, over 4702.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.03288, over 972597.36 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 06:30:34,928 INFO [train.py:715] (4/8) Epoch 11, batch 28300, loss[loss=0.1341, simple_loss=0.2132, pruned_loss=0.02751, over 4953.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2123, pruned_loss=0.03259, over 972517.29 frames.], batch size: 40, lr: 1.93e-04
2022-05-07 06:31:12,830 INFO [train.py:715] (4/8) Epoch 11, batch 28350, loss[loss=0.1776, simple_loss=0.2546, pruned_loss=0.05023, over 4801.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2126, pruned_loss=0.03267, over 972713.32 frames.], batch size: 25, lr: 1.93e-04
2022-05-07 06:31:50,528 INFO [train.py:715] (4/8) Epoch 11, batch 28400, loss[loss=0.1516, simple_loss=0.2217, pruned_loss=0.04072, over 4984.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2131, pruned_loss=0.0328, over 972811.46 frames.], batch size: 28, lr: 1.93e-04
2022-05-07 06:32:28,901 INFO [train.py:715] (4/8) Epoch 11, batch 28450, loss[loss=0.1606, simple_loss=0.2431, pruned_loss=0.03909, over 4750.00 frames.], tot_loss[loss=0.1393, simple_loss=0.213, pruned_loss=0.03279, over 972485.18 frames.], batch size: 19, lr: 1.93e-04
2022-05-07 06:33:06,939 INFO [train.py:715] (4/8) Epoch 11, batch 28500, loss[loss=0.1725, simple_loss=0.2392, pruned_loss=0.05288, over 4957.00 frames.], tot_loss[loss=0.14, simple_loss=0.2136, pruned_loss=0.03321, over 972888.38 frames.], batch size: 35, lr: 1.93e-04
2022-05-07 06:33:44,629 INFO [train.py:715] (4/8) Epoch 11, batch 28550, loss[loss=0.1273, simple_loss=0.203, pruned_loss=0.02575, over 4831.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2136, pruned_loss=0.03301, over 973262.26 frames.], batch size: 25, lr: 1.93e-04
2022-05-07 06:34:23,470 INFO [train.py:715] (4/8) Epoch 11, batch 28600, loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02906, over 4983.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2131, pruned_loss=0.03283, over 972592.25 frames.], batch size: 14, lr: 1.93e-04
2022-05-07 06:35:01,436 INFO [train.py:715] (4/8) Epoch 11, batch 28650, loss[loss=0.1666, simple_loss=0.2312, pruned_loss=0.05103, over 4713.00 frames.], tot_loss[loss=0.139, simple_loss=0.2127, pruned_loss=0.03262, over 972339.51 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 06:35:39,422 INFO [train.py:715] (4/8) Epoch 11, batch 28700, loss[loss=0.1289, simple_loss=0.2006, pruned_loss=0.02864, over 4938.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2137, pruned_loss=0.03289, over 971621.78 frames.], batch size: 39, lr: 1.93e-04
2022-05-07 06:36:17,175 INFO [train.py:715] (4/8) Epoch 11, batch 28750, loss[loss=0.1473, simple_loss=0.231, pruned_loss=0.03186, over 4698.00 frames.], tot_loss[loss=0.139, simple_loss=0.2129, pruned_loss=0.03255, over 971863.31 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 06:36:55,925 INFO [train.py:715] (4/8) Epoch 11, batch 28800, loss[loss=0.164, simple_loss=0.2484, pruned_loss=0.0398, over 4816.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2133, pruned_loss=0.03251, over 970972.71 frames.], batch size: 25, lr: 1.93e-04
2022-05-07 06:37:33,392 INFO [train.py:715] (4/8) Epoch 11, batch 28850, loss[loss=0.1589, simple_loss=0.23, pruned_loss=0.04386, over 4916.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2119, pruned_loss=0.03209, over 971026.58 frames.], batch size: 29, lr: 1.93e-04
2022-05-07 06:38:10,806 INFO [train.py:715] (4/8) Epoch 11, batch 28900, loss[loss=0.1244, simple_loss=0.1898, pruned_loss=0.02949, over 4913.00 frames.], tot_loss[loss=0.138, simple_loss=0.2118, pruned_loss=0.03214, over 970885.86 frames.], batch size: 18, lr: 1.93e-04
2022-05-07 06:38:49,569 INFO [train.py:715] (4/8) Epoch 11, batch 28950, loss[loss=0.1466, simple_loss=0.2118, pruned_loss=0.04068, over 4649.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2113, pruned_loss=0.03171, over 971443.36 frames.], batch size: 13, lr: 1.93e-04
2022-05-07 06:39:27,039 INFO [train.py:715] (4/8) Epoch 11, batch 29000, loss[loss=0.1275, simple_loss=0.2116, pruned_loss=0.02173, over 4764.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2116, pruned_loss=0.03149, over 971137.02 frames.], batch size: 19, lr: 1.93e-04
2022-05-07 06:40:04,957 INFO [train.py:715] (4/8) Epoch 11, batch 29050, loss[loss=0.135, simple_loss=0.2138, pruned_loss=0.02804, over 4906.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2115, pruned_loss=0.03146, over 970950.47 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 06:40:42,752 INFO [train.py:715] (4/8) Epoch 11, batch 29100, loss[loss=0.1293, simple_loss=0.1991, pruned_loss=0.02973, over 4965.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2115, pruned_loss=0.03152, over 972243.33 frames.], batch size: 35, lr: 1.93e-04
2022-05-07 06:41:21,083 INFO [train.py:715] (4/8) Epoch 11, batch 29150, loss[loss=0.1362, simple_loss=0.2133, pruned_loss=0.02961, over 4939.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03191, over 971780.35 frames.], batch size: 21, lr: 1.93e-04
2022-05-07 06:41:58,821 INFO [train.py:715] (4/8) Epoch 11, batch 29200, loss[loss=0.1541, simple_loss=0.2305, pruned_loss=0.03885, over 4851.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03211, over 970987.68 frames.], batch size: 20, lr: 1.93e-04
2022-05-07 06:42:36,369 INFO [train.py:715] (4/8) Epoch 11, batch 29250, loss[loss=0.1262, simple_loss=0.1886, pruned_loss=0.03192, over 4814.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03214, over 971286.60 frames.], batch size: 13, lr: 1.93e-04
2022-05-07 06:43:15,063 INFO [train.py:715] (4/8) Epoch 11, batch 29300, loss[loss=0.1467, simple_loss=0.2221, pruned_loss=0.03561, over 4813.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03207, over 971254.32 frames.], batch size: 27, lr: 1.93e-04
2022-05-07 06:43:53,136 INFO [train.py:715] (4/8) Epoch 11, batch 29350, loss[loss=0.14, simple_loss=0.2084, pruned_loss=0.03578, over 4832.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03201, over 971009.33 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 06:44:30,902 INFO [train.py:715] (4/8) Epoch 11, batch 29400, loss[loss=0.1279, simple_loss=0.1811, pruned_loss=0.03732, over 4852.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03257, over 971799.80 frames.], batch size: 30, lr: 1.93e-04
2022-05-07 06:45:08,810 INFO [train.py:715] (4/8) Epoch 11, batch 29450, loss[loss=0.1522, simple_loss=0.2288, pruned_loss=0.03786, over 4879.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03234, over 972180.95 frames.], batch size: 16, lr: 1.93e-04
2022-05-07 06:45:46,708 INFO [train.py:715] (4/8) Epoch 11, batch 29500, loss[loss=0.1289, simple_loss=0.1981, pruned_loss=0.02987, over 4809.00 frames.], tot_loss[loss=0.138, simple_loss=0.2109, pruned_loss=0.03254, over 972472.39 frames.], batch size: 25, lr: 1.93e-04
2022-05-07 06:46:25,301 INFO [train.py:715] (4/8) Epoch 11, batch 29550, loss[loss=0.1386, simple_loss=0.2205, pruned_loss=0.02832, over 4901.00 frames.], tot_loss[loss=0.1381, simple_loss=0.211, pruned_loss=0.03254, over 972621.38 frames.], batch size: 19, lr: 1.93e-04
2022-05-07 06:47:02,905 INFO [train.py:715] (4/8) Epoch 11, batch 29600, loss[loss=0.1366, simple_loss=0.2055, pruned_loss=0.03388, over 4925.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2112, pruned_loss=0.03268, over 971639.97 frames.], batch size: 23, lr: 1.93e-04
2022-05-07 06:47:41,473 INFO [train.py:715] (4/8) Epoch 11, batch 29650, loss[loss=0.1012, simple_loss=0.168, pruned_loss=0.01723, over 4772.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03239, over 971402.02 frames.], batch size: 12, lr: 1.93e-04
2022-05-07 06:48:19,466 INFO [train.py:715] (4/8) Epoch 11, batch 29700, loss[loss=0.138, simple_loss=0.208, pruned_loss=0.03401, over 4918.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2112, pruned_loss=0.03259, over 971686.19 frames.], batch size: 29, lr: 1.93e-04
2022-05-07 06:48:57,626 INFO [train.py:715] (4/8) Epoch 11, batch 29750, loss[loss=0.1286, simple_loss=0.2077, pruned_loss=0.0248, over 4769.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03209, over 971242.19 frames.], batch size: 16, lr: 1.93e-04
2022-05-07 06:49:35,438 INFO [train.py:715] (4/8) Epoch 11, batch 29800, loss[loss=0.1542, simple_loss=0.2392, pruned_loss=0.03453, over 4946.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2104, pruned_loss=0.03222, over 972261.75 frames.], batch size: 39, lr: 1.93e-04
2022-05-07 06:50:13,828 INFO [train.py:715] (4/8) Epoch 11, batch 29850, loss[loss=0.1308, simple_loss=0.1909, pruned_loss=0.03531, over 4924.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03214, over 972754.09 frames.], batch size: 18, lr: 1.93e-04
2022-05-07 06:50:52,364 INFO [train.py:715] (4/8) Epoch 11, batch 29900, loss[loss=0.1401, simple_loss=0.213, pruned_loss=0.0336, over 4961.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2101, pruned_loss=0.03205, over 973249.26 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 06:51:29,991 INFO [train.py:715] (4/8) Epoch 11, batch 29950, loss[loss=0.1529, simple_loss=0.2199, pruned_loss=0.04299, over 4696.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.03221, over 972658.55 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 06:52:08,180 INFO [train.py:715] (4/8) Epoch 11, batch 30000, loss[loss=0.1228, simple_loss=0.1978, pruned_loss=0.02395, over 4870.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2099, pruned_loss=0.03191, over 972860.89 frames.], batch size: 22, lr: 1.93e-04
2022-05-07 06:52:08,180 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 06:52:17,625 INFO [train.py:742] (4/8) Epoch 11, validation: loss=0.106, simple_loss=0.19, pruned_loss=0.01095, over 914524.00 frames.
2022-05-07 06:52:56,513 INFO [train.py:715] (4/8) Epoch 11, batch 30050, loss[loss=0.1742, simple_loss=0.2362, pruned_loss=0.05611, over 4838.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03202, over 972780.57 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 06:53:34,388 INFO [train.py:715] (4/8) Epoch 11, batch 30100, loss[loss=0.1678, simple_loss=0.2371, pruned_loss=0.0492, over 4900.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.0323, over 972604.76 frames.], batch size: 19, lr: 1.93e-04
2022-05-07 06:54:13,051 INFO [train.py:715] (4/8) Epoch 11, batch 30150, loss[loss=0.1065, simple_loss=0.1795, pruned_loss=0.01673, over 4911.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2106, pruned_loss=0.03212, over 972545.05 frames.], batch size: 23, lr: 1.93e-04
2022-05-07 06:54:50,400 INFO [train.py:715] (4/8) Epoch 11, batch 30200, loss[loss=0.1143, simple_loss=0.186, pruned_loss=0.02127, over 4811.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03208, over 972796.74 frames.], batch size: 26, lr: 1.93e-04
2022-05-07 06:55:29,245 INFO [train.py:715] (4/8) Epoch 11, batch 30250, loss[loss=0.1477, simple_loss=0.2171, pruned_loss=0.03912, over 4796.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2121, pruned_loss=0.03245, over 972423.49 frames.], batch size: 24, lr: 1.93e-04
2022-05-07 06:56:07,229 INFO [train.py:715] (4/8) Epoch 11, batch 30300, loss[loss=0.1254, simple_loss=0.1998, pruned_loss=0.02554, over 4841.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2122, pruned_loss=0.03232, over 973107.18 frames.], batch size: 20, lr: 1.93e-04
2022-05-07 06:56:45,178 INFO [train.py:715] (4/8) Epoch 11, batch 30350, loss[loss=0.1268, simple_loss=0.2051, pruned_loss=0.02426, over 4645.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03202, over 972184.02 frames.], batch size: 13, lr: 1.93e-04
2022-05-07 06:57:23,261 INFO [train.py:715] (4/8) Epoch 11, batch 30400, loss[loss=0.2002, simple_loss=0.2739, pruned_loss=0.06331, over 4993.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2119, pruned_loss=0.03239, over 972163.34 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 06:58:01,501 INFO [train.py:715] (4/8) Epoch 11, batch 30450, loss[loss=0.1245, simple_loss=0.2029, pruned_loss=0.02309, over 4949.00 frames.], tot_loss[loss=0.1383, simple_loss=0.212, pruned_loss=0.03232, over 972575.06 frames.], batch size: 21, lr: 1.93e-04
2022-05-07 06:58:39,332 INFO [train.py:715] (4/8) Epoch 11, batch 30500, loss[loss=0.1389, simple_loss=0.207, pruned_loss=0.03536, over 4915.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2129, pruned_loss=0.03272, over 972667.25 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 06:59:17,143 INFO [train.py:715] (4/8) Epoch 11, batch 30550, loss[loss=0.1492, simple_loss=0.2278, pruned_loss=0.03528, over 4874.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.03263, over 972441.20 frames.], batch size: 20, lr: 1.93e-04
2022-05-07 06:59:56,405 INFO [train.py:715] (4/8) Epoch 11, batch 30600, loss[loss=0.1311, simple_loss=0.2042, pruned_loss=0.02902, over 4785.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03215, over 972076.51 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 07:00:35,033 INFO [train.py:715] (4/8) Epoch 11, batch 30650, loss[loss=0.1113, simple_loss=0.1864, pruned_loss=0.01811, over 4812.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03241, over 973119.58 frames.], batch size: 27, lr: 1.93e-04
2022-05-07 07:01:13,828 INFO [train.py:715] (4/8) Epoch 11, batch 30700, loss[loss=0.137, simple_loss=0.2139, pruned_loss=0.03009, over 4905.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2114, pruned_loss=0.03204, over 973358.85 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 07:01:52,335 INFO [train.py:715] (4/8) Epoch 11, batch 30750, loss[loss=0.1507, simple_loss=0.2258, pruned_loss=0.03776, over 4805.00 frames.], tot_loss[loss=0.138, simple_loss=0.2116, pruned_loss=0.03222, over 973379.71 frames.], batch size: 24, lr: 1.93e-04
2022-05-07 07:02:30,948 INFO [train.py:715] (4/8) Epoch 11, batch 30800, loss[loss=0.1357, simple_loss=0.224, pruned_loss=0.02368, over 4900.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03206, over 973251.86 frames.], batch size: 18, lr: 1.93e-04
2022-05-07 07:03:09,708 INFO [train.py:715] (4/8) Epoch 11, batch 30850, loss[loss=0.1295, simple_loss=0.2111, pruned_loss=0.02398, over 4860.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.03225, over 972712.08 frames.], batch size: 32, lr: 1.93e-04
2022-05-07 07:03:48,266 INFO [train.py:715] (4/8) Epoch 11, batch 30900, loss[loss=0.1241, simple_loss=0.1986, pruned_loss=0.02478, over 4949.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2111, pruned_loss=0.03199, over 972438.69 frames.], batch size: 21, lr: 1.93e-04
2022-05-07 07:04:27,074 INFO [train.py:715] (4/8) Epoch 11, batch 30950, loss[loss=0.1464, simple_loss=0.212, pruned_loss=0.04038, over 4785.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2115, pruned_loss=0.03192, over 973035.68 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 07:05:06,007 INFO [train.py:715] (4/8) Epoch 11, batch 31000, loss[loss=0.1332, simple_loss=0.2195, pruned_loss=0.02347, over 4986.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2119, pruned_loss=0.03222, over 973538.74 frames.], batch size: 20, lr: 1.93e-04
2022-05-07 07:05:44,521 INFO [train.py:715] (4/8) Epoch 11, batch 31050, loss[loss=0.1176, simple_loss=0.1834, pruned_loss=0.02593, over 4850.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03221, over 973858.41 frames.], batch size: 12, lr: 1.93e-04
2022-05-07 07:06:23,342 INFO [train.py:715] (4/8) Epoch 11, batch 31100, loss[loss=0.1504, simple_loss=0.2208, pruned_loss=0.03998, over 4773.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03282, over 973737.06 frames.], batch size: 18, lr: 1.93e-04
2022-05-07 07:07:01,743 INFO [train.py:715] (4/8) Epoch 11, batch 31150, loss[loss=0.1352, simple_loss=0.2034, pruned_loss=0.03348, over 4968.00 frames.], tot_loss[loss=0.1397, simple_loss=0.2125, pruned_loss=0.03349, over 973222.54 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 07:07:39,379 INFO [train.py:715] (4/8) Epoch 11, batch 31200, loss[loss=0.1295, simple_loss=0.2024, pruned_loss=0.02833, over 4984.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2121, pruned_loss=0.03272, over 972235.81 frames.], batch size: 15, lr: 1.93e-04
2022-05-07 07:08:17,483 INFO [train.py:715] (4/8) Epoch 11, batch 31250, loss[loss=0.1298, simple_loss=0.2008, pruned_loss=0.02942, over 4812.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2122, pruned_loss=0.03316, over 971734.73 frames.], batch size: 21, lr: 1.93e-04
2022-05-07 07:08:55,765 INFO [train.py:715] (4/8) Epoch 11, batch 31300, loss[loss=0.1258, simple_loss=0.1999, pruned_loss=0.02588, over 4981.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2116, pruned_loss=0.03293, over 971960.42 frames.], batch size: 14, lr: 1.93e-04
2022-05-07 07:09:33,561 INFO [train.py:715] (4/8) Epoch 11, batch 31350, loss[loss=0.1557, simple_loss=0.2422, pruned_loss=0.03464, over 4761.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2113, pruned_loss=0.03265, over 971992.85 frames.], batch size: 19, lr: 1.93e-04
2022-05-07 07:10:10,909 INFO [train.py:715] (4/8) Epoch 11, batch 31400, loss[loss=0.1288, simple_loss=0.2015, pruned_loss=0.02809, over 4900.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.0324, over 972801.37 frames.], batch size: 22, lr: 1.93e-04
2022-05-07 07:10:48,406 INFO [train.py:715] (4/8) Epoch 11, batch 31450, loss[loss=0.1303, simple_loss=0.2068, pruned_loss=0.02689, over 4741.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.03218, over 972839.65 frames.], batch size: 16, lr: 1.93e-04
2022-05-07 07:11:26,018 INFO [train.py:715] (4/8) Epoch 11, batch 31500, loss[loss=0.1555, simple_loss=0.2381, pruned_loss=0.03639, over 4824.00 frames.], tot_loss[loss=0.138, simple_loss=0.2117, pruned_loss=0.03216, over 972919.76 frames.], batch size: 25, lr: 1.93e-04
2022-05-07 07:12:03,666 INFO [train.py:715] (4/8) Epoch 11, batch 31550, loss[loss=0.1386, simple_loss=0.2069, pruned_loss=0.03518, over 4858.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03222, over 972979.83 frames.], batch size: 20, lr: 1.93e-04
2022-05-07 07:12:41,672 INFO [train.py:715] (4/8) Epoch 11, batch 31600, loss[loss=0.1316, simple_loss=0.1989, pruned_loss=0.03216, over 4857.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03189, over 972659.11 frames.], batch size: 20, lr: 1.93e-04
2022-05-07 07:13:19,756 INFO [train.py:715] (4/8) Epoch 11, batch 31650, loss[loss=0.1221, simple_loss=0.1912, pruned_loss=0.02651, over 4757.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2111, pruned_loss=0.03197, over 973145.11 frames.], batch size: 19, lr: 1.93e-04
2022-05-07 07:13:57,688 INFO [train.py:715] (4/8) Epoch 11, batch 31700, loss[loss=0.1297, simple_loss=0.2052, pruned_loss=0.02705, over 4914.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03205, over 973205.04 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 07:14:35,211 INFO [train.py:715] (4/8) Epoch 11, batch 31750, loss[loss=0.1281, simple_loss=0.2166, pruned_loss=0.0198, over 4754.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.03223, over 972692.32 frames.], batch size: 19, lr: 1.93e-04
2022-05-07 07:15:14,077 INFO [train.py:715] (4/8) Epoch 11, batch 31800, loss[loss=0.1248, simple_loss=0.1984, pruned_loss=0.02559, over 4828.00 frames.], tot_loss[loss=0.1384, simple_loss=0.212, pruned_loss=0.03234, over 972913.92 frames.], batch size: 13, lr: 1.93e-04
2022-05-07 07:15:52,654 INFO [train.py:715] (4/8) Epoch 11, batch 31850, loss[loss=0.1355, simple_loss=0.1943, pruned_loss=0.03833, over 4810.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2117, pruned_loss=0.03157, over 972925.78 frames.], batch size: 13, lr: 1.93e-04
2022-05-07 07:16:30,886 INFO [train.py:715] (4/8) Epoch 11, batch 31900, loss[loss=0.1241, simple_loss=0.195, pruned_loss=0.02656, over 4889.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2127, pruned_loss=0.03223, over 972457.99 frames.], batch size: 17, lr: 1.93e-04
2022-05-07 07:17:09,178 INFO [train.py:715] (4/8) Epoch 11, batch 31950, loss[loss=0.1762, simple_loss=0.2522, pruned_loss=0.05011, over 4799.00 frames.], tot_loss[loss=0.1382, simple_loss=0.212, pruned_loss=0.03219, over 972098.93 frames.], batch size: 21, lr: 1.93e-04
2022-05-07 07:17:47,960 INFO [train.py:715] (4/8) Epoch 11, batch 32000, loss[loss=0.1251, simple_loss=0.1984, pruned_loss=0.0259, over 4941.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03163, over 971988.99 frames.], batch size: 21, lr: 1.93e-04
2022-05-07 07:18:26,185 INFO [train.py:715] (4/8) Epoch 11, batch 32050, loss[loss=0.1433, simple_loss=0.2155, pruned_loss=0.03558, over 4767.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03169, over 972096.45 frames.], batch size: 18, lr: 1.93e-04
2022-05-07 07:19:04,554 INFO [train.py:715] (4/8) Epoch 11, batch 32100, loss[loss=0.1465, simple_loss=0.2112, pruned_loss=0.04088, over 4919.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03216, over 971956.57 frames.], batch size: 38, lr: 1.92e-04
2022-05-07 07:19:42,572 INFO [train.py:715] (4/8) Epoch 11, batch 32150, loss[loss=0.1592, simple_loss=0.225, pruned_loss=0.04669, over 4875.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2112, pruned_loss=0.0323, over 972111.51 frames.], batch size: 20, lr: 1.92e-04
2022-05-07 07:20:19,990 INFO [train.py:715] (4/8) Epoch 11, batch 32200, loss[loss=0.08848, simple_loss=0.1546, pruned_loss=0.01117, over 4845.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2111, pruned_loss=0.03267, over 971882.77 frames.], batch size: 12, lr: 1.92e-04
2022-05-07 07:20:57,516 INFO [train.py:715] (4/8) Epoch 11, batch 32250, loss[loss=0.1698, simple_loss=0.2391, pruned_loss=0.05018, over 4879.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2109, pruned_loss=0.03268, over 971507.64 frames.], batch size: 16, lr: 1.92e-04
2022-05-07 07:21:35,349 INFO [train.py:715] (4/8) Epoch 11, batch 32300, loss[loss=0.1196, simple_loss=0.1961, pruned_loss=0.0216, over 4881.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2108, pruned_loss=0.03273, over 971844.48 frames.], batch size: 13, lr: 1.92e-04
2022-05-07 07:22:13,997 INFO [train.py:715] (4/8) Epoch 11, batch 32350, loss[loss=0.1368, simple_loss=0.2099, pruned_loss=0.03183, over 4916.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2115, pruned_loss=0.03298, over 971339.59 frames.], batch size: 18, lr: 1.92e-04
2022-05-07 07:22:51,417 INFO [train.py:715] (4/8) Epoch 11, batch 32400, loss[loss=0.1297, simple_loss=0.1933, pruned_loss=0.03301, over 4788.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2106, pruned_loss=0.0325, over 971679.46 frames.], batch size: 12, lr: 1.92e-04
2022-05-07 07:23:29,418 INFO [train.py:715] (4/8) Epoch 11, batch 32450, loss[loss=0.1315, simple_loss=0.2077, pruned_loss=0.02766, over 4833.00 frames.], tot_loss[loss=0.138, simple_loss=0.2108, pruned_loss=0.03255, over 971768.68 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:24:07,458 INFO [train.py:715] (4/8) Epoch 11, batch 32500, loss[loss=0.118, simple_loss=0.202, pruned_loss=0.01695, over 4797.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03215, over 972072.30 frames.], batch size: 24, lr: 1.92e-04
2022-05-07 07:24:45,517 INFO [train.py:715] (4/8) Epoch 11, batch 32550, loss[loss=0.1377, simple_loss=0.2256, pruned_loss=0.02484, over 4779.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03223, over 972240.06 frames.], batch size: 18, lr: 1.92e-04
2022-05-07 07:25:23,169 INFO [train.py:715] (4/8) Epoch 11, batch 32600, loss[loss=0.1447, simple_loss=0.2253, pruned_loss=0.03203, over 4781.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03244, over 972046.06 frames.], batch size: 14, lr: 1.92e-04
2022-05-07 07:26:01,257 INFO [train.py:715] (4/8) Epoch 11, batch 32650, loss[loss=0.1304, simple_loss=0.2026, pruned_loss=0.02915, over 4804.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2118, pruned_loss=0.0328, over 971977.15 frames.], batch size: 25, lr: 1.92e-04
2022-05-07 07:26:39,442 INFO [train.py:715] (4/8) Epoch 11, batch 32700, loss[loss=0.1313, simple_loss=0.21, pruned_loss=0.02629, over 4812.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03223, over 972289.69 frames.], batch size: 26, lr: 1.92e-04
2022-05-07 07:27:16,889 INFO [train.py:715] (4/8) Epoch 11, batch 32750, loss[loss=0.123, simple_loss=0.1943, pruned_loss=0.02588, over 4975.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.03249, over 972542.97 frames.], batch size: 14, lr: 1.92e-04
2022-05-07 07:27:55,658 INFO [train.py:715] (4/8) Epoch 11, batch 32800, loss[loss=0.1445, simple_loss=0.2137, pruned_loss=0.0377, over 4873.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03217, over 972346.14 frames.], batch size: 16, lr: 1.92e-04
2022-05-07 07:28:35,367 INFO [train.py:715] (4/8) Epoch 11, batch 32850, loss[loss=0.116, simple_loss=0.1787, pruned_loss=0.02668, over 4994.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03211, over 972378.81 frames.], batch size: 14, lr: 1.92e-04
2022-05-07 07:29:13,919 INFO [train.py:715] (4/8) Epoch 11, batch 32900, loss[loss=0.1031, simple_loss=0.1788, pruned_loss=0.01369, over 4986.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.032, over 972753.68 frames.], batch size: 24, lr: 1.92e-04
2022-05-07 07:29:52,132 INFO [train.py:715] (4/8) Epoch 11, batch 32950, loss[loss=0.126, simple_loss=0.205, pruned_loss=0.02353, over 4792.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03185, over 972833.11 frames.], batch size: 21, lr: 1.92e-04
2022-05-07 07:30:31,048 INFO [train.py:715] (4/8) Epoch 11, batch 33000, loss[loss=0.1171, simple_loss=0.195, pruned_loss=0.01959, over 4832.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03181, over 972350.87 frames.], batch size: 30, lr: 1.92e-04
2022-05-07 07:30:31,049 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 07:30:40,493 INFO [train.py:742] (4/8) Epoch 11, validation: loss=0.1059, simple_loss=0.1899, pruned_loss=0.0109, over 914524.00 frames.
2022-05-07 07:31:19,415 INFO [train.py:715] (4/8) Epoch 11, batch 33050, loss[loss=0.1121, simple_loss=0.1834, pruned_loss=0.0204, over 4776.00 frames.], tot_loss[loss=0.136, simple_loss=0.2094, pruned_loss=0.03131, over 972276.41 frames.], batch size: 17, lr: 1.92e-04
2022-05-07 07:32:00,913 INFO [train.py:715] (4/8) Epoch 11, batch 33100, loss[loss=0.1193, simple_loss=0.1946, pruned_loss=0.02197, over 4987.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2096, pruned_loss=0.03154, over 972383.96 frames.], batch size: 26, lr: 1.92e-04
2022-05-07 07:32:38,881 INFO [train.py:715] (4/8) Epoch 11, batch 33150, loss[loss=0.1183, simple_loss=0.1933, pruned_loss=0.02164, over 4820.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03124, over 971230.00 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:33:17,492 INFO [train.py:715] (4/8) Epoch 11, batch 33200, loss[loss=0.1388, simple_loss=0.2169, pruned_loss=0.03029, over 4891.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03156, over 971640.48 frames.], batch size: 19, lr: 1.92e-04
2022-05-07 07:33:56,618 INFO [train.py:715] (4/8) Epoch 11, batch 33250, loss[loss=0.1151, simple_loss=0.1927, pruned_loss=0.0188, over 4901.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03194, over 971509.10 frames.], batch size: 17, lr: 1.92e-04
2022-05-07 07:34:35,411 INFO [train.py:715] (4/8) Epoch 11, batch 33300, loss[loss=0.1499, simple_loss=0.2316, pruned_loss=0.03415, over 4821.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2121, pruned_loss=0.03223, over 971746.59 frames.], batch size: 26, lr: 1.92e-04
2022-05-07 07:35:13,283 INFO [train.py:715] (4/8) Epoch 11, batch 33350, loss[loss=0.1443, simple_loss=0.2047, pruned_loss=0.04195, over 4734.00 frames.], tot_loss[loss=0.1386, simple_loss=0.212, pruned_loss=0.03259, over 971484.21 frames.], batch size: 12, lr: 1.92e-04
2022-05-07 07:35:51,705 INFO [train.py:715] (4/8) Epoch 11, batch 33400, loss[loss=0.1498, simple_loss=0.2211, pruned_loss=0.03923, over 4862.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2121, pruned_loss=0.03261, over 973053.19 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:36:30,392 INFO [train.py:715] (4/8) Epoch 11, batch 33450, loss[loss=0.1149, simple_loss=0.1898, pruned_loss=0.01999, over 4769.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2118, pruned_loss=0.03235, over 972111.98 frames.], batch size: 14, lr: 1.92e-04
2022-05-07 07:37:08,730 INFO [train.py:715] (4/8) Epoch 11, batch 33500, loss[loss=0.1314, simple_loss=0.207, pruned_loss=0.02794, over 4739.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2118, pruned_loss=0.03198, over 971522.31 frames.], batch size: 16, lr: 1.92e-04
2022-05-07 07:37:47,173 INFO [train.py:715] (4/8) Epoch 11, batch 33550, loss[loss=0.1147, simple_loss=0.1888, pruned_loss=0.02031, over 4965.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03201, over 972405.54 frames.], batch size: 14, lr: 1.92e-04
2022-05-07 07:38:25,761 INFO [train.py:715] (4/8) Epoch 11, batch 33600, loss[loss=0.1163, simple_loss=0.197, pruned_loss=0.01775, over 4838.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03187, over 971823.02 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:39:04,165 INFO [train.py:715] (4/8) Epoch 11, batch 33650, loss[loss=0.1723, simple_loss=0.2289, pruned_loss=0.05786, over 4977.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03192, over 971782.52 frames.], batch size: 28, lr: 1.92e-04
2022-05-07 07:39:42,290 INFO [train.py:715] (4/8) Epoch 11, batch 33700, loss[loss=0.1504, simple_loss=0.221, pruned_loss=0.03991, over 4783.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03141, over 971824.28 frames.], batch size: 17, lr: 1.92e-04
2022-05-07 07:40:20,578 INFO [train.py:715] (4/8) Epoch 11, batch 33750, loss[loss=0.1342, simple_loss=0.2129, pruned_loss=0.02774, over 4859.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03147, over 972287.37 frames.], batch size: 34, lr: 1.92e-04
2022-05-07 07:40:59,159 INFO [train.py:715] (4/8) Epoch 11, batch 33800, loss[loss=0.1808, simple_loss=0.2573, pruned_loss=0.05214, over 4808.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03147, over 971114.63 frames.], batch size: 21, lr: 1.92e-04
2022-05-07 07:41:37,147 INFO [train.py:715] (4/8) Epoch 11, batch 33850, loss[loss=0.1325, simple_loss=0.2055, pruned_loss=0.02977, over 4882.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03142, over 971567.98 frames.], batch size: 22, lr: 1.92e-04
2022-05-07 07:42:15,180 INFO [train.py:715] (4/8) Epoch 11, batch 33900, loss[loss=0.1144, simple_loss=0.1853, pruned_loss=0.02174, over 4693.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03216, over 971557.01 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:42:53,934 INFO [train.py:715] (4/8) Epoch 11, batch 33950, loss[loss=0.1383, simple_loss=0.2086, pruned_loss=0.03399, over 4820.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03205, over 971595.58 frames.], batch size: 13, lr: 1.92e-04
2022-05-07 07:43:32,252 INFO [train.py:715] (4/8) Epoch 11, batch 34000, loss[loss=0.1467, simple_loss=0.228, pruned_loss=0.03272, over 4874.00 frames.], tot_loss[loss=0.1386, simple_loss=0.212, pruned_loss=0.03259, over 971728.08 frames.], batch size: 16, lr: 1.92e-04
2022-05-07 07:44:10,351 INFO [train.py:715] (4/8) Epoch 11, batch 34050, loss[loss=0.1304, simple_loss=0.2069, pruned_loss=0.02698, over 4760.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03293, over 972080.14 frames.], batch size: 19, lr: 1.92e-04
2022-05-07 07:44:48,873 INFO [train.py:715] (4/8) Epoch 11, batch 34100, loss[loss=0.1084, simple_loss=0.176, pruned_loss=0.02036, over 4919.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2124, pruned_loss=0.03294, over 972190.95 frames.], batch size: 17, lr: 1.92e-04
2022-05-07 07:45:27,613 INFO [train.py:715] (4/8) Epoch 11, batch 34150, loss[loss=0.1451, simple_loss=0.2271, pruned_loss=0.03154, over 4703.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03265, over 971281.61 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:46:05,701 INFO [train.py:715] (4/8) Epoch 11, batch 34200, loss[loss=0.1029, simple_loss=0.1744, pruned_loss=0.01568, over 4751.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03231, over 970515.78 frames.], batch size: 19, lr: 1.92e-04
2022-05-07 07:46:44,126 INFO [train.py:715] (4/8) Epoch 11, batch 34250, loss[loss=0.1566, simple_loss=0.2291, pruned_loss=0.04208, over 4783.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2108, pruned_loss=0.03241, over 971162.55 frames.], batch size: 14, lr: 1.92e-04
2022-05-07 07:47:23,288 INFO [train.py:715] (4/8) Epoch 11, batch 34300, loss[loss=0.151, simple_loss=0.2372, pruned_loss=0.03238, over 4874.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.0323, over 971430.14 frames.], batch size: 16, lr: 1.92e-04
2022-05-07 07:48:01,581 INFO [train.py:715] (4/8) Epoch 11, batch 34350, loss[loss=0.1334, simple_loss=0.2165, pruned_loss=0.02511, over 4816.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2101, pruned_loss=0.03204, over 972554.70 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:48:40,023 INFO [train.py:715] (4/8) Epoch 11, batch 34400, loss[loss=0.1629, simple_loss=0.2288, pruned_loss=0.04851, over 4870.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03156, over 972162.22 frames.], batch size: 16, lr: 1.92e-04
2022-05-07 07:49:18,674 INFO [train.py:715] (4/8) Epoch 11, batch 34450, loss[loss=0.1247, simple_loss=0.1974, pruned_loss=0.02602, over 4813.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03204, over 972568.66 frames.], batch size: 25, lr: 1.92e-04
2022-05-07 07:49:57,850 INFO [train.py:715] (4/8) Epoch 11, batch 34500, loss[loss=0.1609, simple_loss=0.2231, pruned_loss=0.04938, over 4830.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2118, pruned_loss=0.03229, over 971896.23 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:50:35,957 INFO [train.py:715] (4/8) Epoch 11, batch 34550, loss[loss=0.1388, simple_loss=0.2127, pruned_loss=0.03244, over 4975.00 frames.], tot_loss[loss=0.1381, simple_loss=0.212, pruned_loss=0.03211, over 971530.51 frames.], batch size: 15, lr: 1.92e-04
2022-05-07 07:51:12,741 INFO [train.py:715] (4/8) Epoch 11, batch 34600, loss[loss=0.1357, simple_loss=0.2138, pruned_loss=0.02881, over 4977.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2122, pruned_loss=0.03247, over 971258.14 frames.], batch size: 14, lr: 1.92e-04
2022-05-07 07:51:50,531 INFO [train.py:715] (4/8) Epoch 11, batch 34650, loss[loss=0.1488, simple_loss=0.2225, pruned_loss=0.03761, over 4880.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2122, pruned_loss=0.03245, over 971508.03 frames.], batch size: 22, lr: 1.92e-04
2022-05-07 07:52:27,798 INFO [train.py:715] (4/8) Epoch 11, batch 34700, loss[loss=0.1499, simple_loss=0.2249, pruned_loss=0.03739, over 4785.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03289, over 971884.04 frames.], batch size: 17, lr: 1.92e-04
2022-05-07 07:53:04,318 INFO [train.py:715] (4/8) Epoch 11, batch 34750, loss[loss=0.1391, simple_loss=0.2116, pruned_loss=0.03326, over 4868.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2121, pruned_loss=0.03307, over 972436.63 frames.], batch size: 34, lr: 1.92e-04
2022-05-07 07:53:39,313 INFO [train.py:715] (4/8) Epoch 11, batch 34800, loss[loss=0.1352, simple_loss=0.2046, pruned_loss=0.03293, over 4914.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2125, pruned_loss=0.03327, over 972487.05 frames.], batch size: 18, lr: 1.92e-04
2022-05-07 07:54:26,267 INFO [train.py:715] (4/8) Epoch 12, batch 0, loss[loss=0.1412, simple_loss=0.2191, pruned_loss=0.03168, over 4736.00 frames.], tot_loss[loss=0.1412, simple_loss=0.2191, pruned_loss=0.03168, over 4736.00 frames.], batch size: 16, lr: 1.85e-04
2022-05-07 07:55:04,628 INFO [train.py:715] (4/8) Epoch 12, batch 50, loss[loss=0.1399, simple_loss=0.2114, pruned_loss=0.03416, over 4693.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2122, pruned_loss=0.03337, over 219211.74 frames.], batch size: 15, lr: 1.85e-04
2022-05-07 07:55:42,692 INFO [train.py:715] (4/8) Epoch 12, batch 100, loss[loss=0.1192, simple_loss=0.2003, pruned_loss=0.019, over 4822.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2116, pruned_loss=0.03363, over 386535.64 frames.], batch size: 13, lr: 1.85e-04
2022-05-07 07:56:21,320 INFO [train.py:715] (4/8) Epoch 12, batch 150, loss[loss=0.1372, simple_loss=0.2144, pruned_loss=0.03, over 4771.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2124, pruned_loss=0.03318, over 517329.26 frames.], batch size: 18, lr: 1.85e-04
2022-05-07 07:56:59,066 INFO [train.py:715] (4/8) Epoch 12, batch 200, loss[loss=0.1335, simple_loss=0.209, pruned_loss=0.02896, over 4819.00 frames.], tot_loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.03347, over 618223.45 frames.], batch size: 26, lr: 1.85e-04
2022-05-07 07:57:38,280 INFO [train.py:715] (4/8) Epoch 12, batch 250, loss[loss=0.1149, simple_loss=0.183, pruned_loss=0.02336, over 4982.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2119, pruned_loss=0.03285, over 696826.06 frames.], batch size: 25, lr: 1.85e-04
2022-05-07 07:58:16,542 INFO [train.py:715] (4/8) Epoch 12, batch 300, loss[loss=0.1348, simple_loss=0.2113, pruned_loss=0.02909, over 4846.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2127, pruned_loss=0.03314, over 758484.67 frames.], batch size: 13, lr: 1.84e-04
2022-05-07 07:58:54,473 INFO [train.py:715] (4/8) Epoch 12, batch 350, loss[loss=0.1378, simple_loss=0.2079, pruned_loss=0.03384, over 4924.00 frames.], tot_loss[loss=0.1399, simple_loss=0.2132, pruned_loss=0.03329, over 806109.71 frames.], batch size: 35, lr: 1.84e-04
2022-05-07 07:59:32,944 INFO [train.py:715] (4/8) Epoch 12, batch 400, loss[loss=0.1378, simple_loss=0.2161, pruned_loss=0.02971, over 4963.00 frames.], tot_loss[loss=0.1395, simple_loss=0.213, pruned_loss=0.03303, over 843618.08 frames.], batch size: 24, lr: 1.84e-04
2022-05-07 08:00:10,577 INFO [train.py:715] (4/8) Epoch 12, batch 450, loss[loss=0.1047, simple_loss=0.1797, pruned_loss=0.01483, over 4907.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2123, pruned_loss=0.03276, over 872502.39 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:00:48,787 INFO [train.py:715] (4/8) Epoch 12, batch 500, loss[loss=0.1446, simple_loss=0.2109, pruned_loss=0.03913, over 4917.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03232, over 895066.49 frames.], batch size: 18, lr: 1.84e-04
2022-05-07 08:01:26,233 INFO [train.py:715] (4/8) Epoch 12, batch 550, loss[loss=0.1632, simple_loss=0.2406, pruned_loss=0.04288, over 4917.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.0321, over 912545.17 frames.], batch size: 23, lr: 1.84e-04
2022-05-07 08:02:04,573 INFO [train.py:715] (4/8) Epoch 12, batch 600, loss[loss=0.1263, simple_loss=0.2019, pruned_loss=0.0254, over 4846.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03266, over 926426.15 frames.], batch size: 15, lr: 1.84e-04
2022-05-07 08:02:41,618 INFO [train.py:715] (4/8) Epoch 12, batch 650, loss[loss=0.1294, simple_loss=0.2066, pruned_loss=0.02605, over 4909.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2112, pruned_loss=0.03267, over 936327.22 frames.], batch size: 23, lr: 1.84e-04
2022-05-07 08:03:20,186 INFO [train.py:715] (4/8) Epoch 12, batch 700, loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03104, over 4866.00 frames.], tot_loss[loss=0.138, simple_loss=0.2108, pruned_loss=0.03258, over 943645.94 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:03:58,808 INFO [train.py:715] (4/8) Epoch 12, batch 750, loss[loss=0.1402, simple_loss=0.2103, pruned_loss=0.03503, over 4945.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2112, pruned_loss=0.03253, over 949558.08 frames.], batch size: 21, lr: 1.84e-04
2022-05-07 08:04:37,570 INFO [train.py:715] (4/8) Epoch 12, batch 800, loss[loss=0.1521, simple_loss=0.2306, pruned_loss=0.03683, over 4916.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03218, over 954963.32 frames.], batch size: 17, lr: 1.84e-04
2022-05-07 08:05:16,049 INFO [train.py:715] (4/8) Epoch 12, batch 850, loss[loss=0.1455, simple_loss=0.2183, pruned_loss=0.03638, over 4985.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2121, pruned_loss=0.03268, over 959365.89 frames.], batch size: 35, lr: 1.84e-04
2022-05-07 08:05:54,152 INFO [train.py:715] (4/8) Epoch 12, batch 900, loss[loss=0.1365, simple_loss=0.2154, pruned_loss=0.02881, over 4983.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.0322, over 962836.12 frames.], batch size: 28, lr: 1.84e-04
2022-05-07 08:06:32,488 INFO [train.py:715] (4/8) Epoch 12, batch 950, loss[loss=0.1413, simple_loss=0.2164, pruned_loss=0.03309, over 4977.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03199, over 965140.29 frames.], batch size: 24, lr: 1.84e-04
2022-05-07 08:07:09,849 INFO [train.py:715] (4/8) Epoch 12, batch 1000, loss[loss=0.1372, simple_loss=0.2158, pruned_loss=0.02931, over 4803.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03213, over 965620.58 frames.], batch size: 21, lr: 1.84e-04
2022-05-07 08:07:47,343 INFO [train.py:715] (4/8) Epoch 12, batch 1050, loss[loss=0.1573, simple_loss=0.233, pruned_loss=0.04086, over 4937.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03235, over 967122.23 frames.], batch size: 39, lr: 1.84e-04
2022-05-07 08:08:25,194 INFO [train.py:715] (4/8) Epoch 12, batch 1100, loss[loss=0.1503, simple_loss=0.2208, pruned_loss=0.03987, over 4738.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2112, pruned_loss=0.03245, over 967308.43 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:09:03,087 INFO [train.py:715] (4/8) Epoch 12, batch 1150, loss[loss=0.1339, simple_loss=0.2239, pruned_loss=0.022, over 4818.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03239, over 968041.63 frames.], batch size: 27, lr: 1.84e-04
2022-05-07 08:09:41,431 INFO [train.py:715] (4/8) Epoch 12, batch 1200, loss[loss=0.1423, simple_loss=0.2191, pruned_loss=0.03273, over 4780.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2116, pruned_loss=0.0328, over 969072.08 frames.], batch size: 17, lr: 1.84e-04
2022-05-07 08:10:18,738 INFO [train.py:715] (4/8) Epoch 12, batch 1250, loss[loss=0.1254, simple_loss=0.1921, pruned_loss=0.02933, over 4898.00 frames.], tot_loss[loss=0.139, simple_loss=0.2119, pruned_loss=0.03307, over 969111.46 frames.], batch size: 23, lr: 1.84e-04
2022-05-07 08:10:56,843 INFO [train.py:715] (4/8) Epoch 12, batch 1300, loss[loss=0.1653, simple_loss=0.2271, pruned_loss=0.05176, over 4816.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2116, pruned_loss=0.03288, over 969480.35 frames.], batch size: 13, lr: 1.84e-04
2022-05-07 08:11:33,987 INFO [train.py:715] (4/8) Epoch 12, batch 1350, loss[loss=0.1432, simple_loss=0.2128, pruned_loss=0.03683, over 4985.00 frames.], tot_loss[loss=0.138, simple_loss=0.2109, pruned_loss=0.03257, over 971301.02 frames.], batch size: 28, lr: 1.84e-04
2022-05-07 08:12:12,110 INFO [train.py:715] (4/8) Epoch 12, batch 1400, loss[loss=0.1461, simple_loss=0.2204, pruned_loss=0.0359, over 4807.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2108, pruned_loss=0.03274, over 970853.73 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:12:49,762 INFO [train.py:715] (4/8) Epoch 12, batch 1450, loss[loss=0.102, simple_loss=0.1764, pruned_loss=0.01374, over 4926.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2106, pruned_loss=0.03258, over 971227.73 frames.], batch size: 29, lr: 1.84e-04
2022-05-07 08:13:27,680 INFO [train.py:715] (4/8) Epoch 12, batch 1500, loss[loss=0.1186, simple_loss=0.1937, pruned_loss=0.02173, over 4815.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2103, pruned_loss=0.03221, over 971031.74 frames.], batch size: 26, lr: 1.84e-04
2022-05-07 08:14:05,278 INFO [train.py:715] (4/8) Epoch 12, batch 1550, loss[loss=0.1494, simple_loss=0.2165, pruned_loss=0.04114, over 4987.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2111, pruned_loss=0.03268, over 971654.14 frames.], batch size: 33, lr: 1.84e-04
2022-05-07 08:14:42,471 INFO [train.py:715] (4/8) Epoch 12, batch 1600, loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03121, over 4963.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03227, over 972547.37 frames.], batch size: 15, lr: 1.84e-04
2022-05-07 08:15:20,489 INFO [train.py:715] (4/8) Epoch 12, batch 1650, loss[loss=0.1394, simple_loss=0.2164, pruned_loss=0.03123, over 4909.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03252, over 972820.52 frames.], batch size: 18, lr: 1.84e-04
2022-05-07 08:15:57,867 INFO [train.py:715] (4/8) Epoch 12, batch 1700, loss[loss=0.1444, simple_loss=0.2099, pruned_loss=0.03948, over 4892.00 frames.], tot_loss[loss=0.138, simple_loss=0.211, pruned_loss=0.03251, over 973228.29 frames.], batch size: 17, lr: 1.84e-04
2022-05-07 08:16:35,313 INFO [train.py:715] (4/8) Epoch 12, batch 1750, loss[loss=0.1116, simple_loss=0.1849, pruned_loss=0.01916, over 4875.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03238, over 973324.33 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:17:12,472 INFO [train.py:715] (4/8) Epoch 12, batch 1800, loss[loss=0.1565, simple_loss=0.2217, pruned_loss=0.04563, over 4988.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2106, pruned_loss=0.03239, over 972059.47 frames.], batch size: 20, lr: 1.84e-04
2022-05-07 08:17:50,168 INFO [train.py:715] (4/8) Epoch 12, batch 1850, loss[loss=0.1643, simple_loss=0.2437, pruned_loss=0.0425, over 4882.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.03229, over 972501.97 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:18:27,659 INFO [train.py:715] (4/8) Epoch 12, batch 1900, loss[loss=0.1296, simple_loss=0.1995, pruned_loss=0.02988, over 4909.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03184, over 972471.17 frames.], batch size: 39, lr: 1.84e-04
2022-05-07 08:19:05,284 INFO [train.py:715] (4/8) Epoch 12, batch 1950, loss[loss=0.1632, simple_loss=0.2315, pruned_loss=0.04747, over 4736.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03182, over 972237.78 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:19:43,103 INFO [train.py:715] (4/8) Epoch 12, batch 2000, loss[loss=0.1276, simple_loss=0.2018, pruned_loss=0.02671, over 4772.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03156, over 971786.51 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:20:21,263 INFO [train.py:715] (4/8) Epoch 12, batch 2050, loss[loss=0.1436, simple_loss=0.2119, pruned_loss=0.03761, over 4787.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03167, over 972406.18 frames.], batch size: 24, lr: 1.84e-04
2022-05-07 08:20:59,321 INFO [train.py:715] (4/8) Epoch 12, batch 2100, loss[loss=0.1506, simple_loss=0.2322, pruned_loss=0.03446, over 4811.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03191, over 973069.38 frames.], batch size: 15, lr: 1.84e-04
2022-05-07 08:21:36,624 INFO [train.py:715] (4/8) Epoch 12, batch 2150, loss[loss=0.1287, simple_loss=0.2059, pruned_loss=0.02576, over 4813.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2098, pruned_loss=0.03178, over 972670.75 frames.], batch size: 13, lr: 1.84e-04
2022-05-07 08:22:14,600 INFO [train.py:715] (4/8) Epoch 12, batch 2200, loss[loss=0.1261, simple_loss=0.1976, pruned_loss=0.02733, over 4801.00 frames.], tot_loss[loss=0.1371, simple_loss=0.21, pruned_loss=0.03209, over 972483.56 frames.], batch size: 24, lr: 1.84e-04
2022-05-07 08:22:52,523 INFO [train.py:715] (4/8) Epoch 12, batch 2250, loss[loss=0.1167, simple_loss=0.1889, pruned_loss=0.02222, over 4753.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2103, pruned_loss=0.03213, over 971979.29 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:23:30,601 INFO [train.py:715] (4/8) Epoch 12, batch 2300, loss[loss=0.1273, simple_loss=0.1986, pruned_loss=0.02796, over 4935.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2099, pruned_loss=0.03189, over 972558.21 frames.], batch size: 23, lr: 1.84e-04
2022-05-07 08:24:07,787 INFO [train.py:715] (4/8) Epoch 12, batch 2350, loss[loss=0.1321, simple_loss=0.2038, pruned_loss=0.03023, over 4870.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2109, pruned_loss=0.03275, over 972568.86 frames.], batch size: 20, lr: 1.84e-04
2022-05-07 08:24:45,331 INFO [train.py:715] (4/8) Epoch 12, batch 2400, loss[loss=0.139, simple_loss=0.2141, pruned_loss=0.03196, over 4898.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2107, pruned_loss=0.0325, over 972785.37 frames.], batch size: 17, lr: 1.84e-04
2022-05-07 08:25:23,252 INFO [train.py:715] (4/8) Epoch 12, batch 2450, loss[loss=0.1303, simple_loss=0.2084, pruned_loss=0.0261, over 4904.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2111, pruned_loss=0.03264, over 972815.50 frames.], batch size: 22, lr: 1.84e-04
2022-05-07 08:26:00,044 INFO [train.py:715] (4/8) Epoch 12, batch 2500, loss[loss=0.1451, simple_loss=0.2262, pruned_loss=0.03199, over 4900.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2114, pruned_loss=0.03315, over 972211.08 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:26:38,142 INFO [train.py:715] (4/8) Epoch 12, batch 2550, loss[loss=0.1596, simple_loss=0.236, pruned_loss=0.04156, over 4814.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2112, pruned_loss=0.03301, over 972615.61 frames.], batch size: 25, lr: 1.84e-04
2022-05-07 08:27:15,553 INFO [train.py:715] (4/8) Epoch 12, batch 2600, loss[loss=0.1553, simple_loss=0.2209, pruned_loss=0.04486, over 4907.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2108, pruned_loss=0.03248, over 972616.81 frames.], batch size: 17, lr: 1.84e-04
2022-05-07 08:27:54,372 INFO [train.py:715] (4/8) Epoch 12, batch 2650, loss[loss=0.1177, simple_loss=0.1943, pruned_loss=0.02057, over 4905.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2111, pruned_loss=0.03263, over 972275.37 frames.], batch size: 39, lr: 1.84e-04
2022-05-07 08:28:32,743 INFO [train.py:715] (4/8) Epoch 12, batch 2700, loss[loss=0.1418, simple_loss=0.2172, pruned_loss=0.03324, over 4840.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03253, over 972429.12 frames.], batch size: 26, lr: 1.84e-04
2022-05-07 08:29:11,534 INFO [train.py:715] (4/8) Epoch 12, batch 2750, loss[loss=0.1326, simple_loss=0.2055, pruned_loss=0.02987, over 4932.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03272, over 971983.08 frames.], batch size: 18, lr: 1.84e-04
2022-05-07 08:29:50,411 INFO [train.py:715] (4/8) Epoch 12, batch 2800, loss[loss=0.141, simple_loss=0.2284, pruned_loss=0.02685, over 4882.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03231, over 972006.98 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:30:28,421 INFO [train.py:715] (4/8) Epoch 12, batch 2850, loss[loss=0.1294, simple_loss=0.1962, pruned_loss=0.03134, over 4786.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.0324, over 972229.60 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:31:07,090 INFO [train.py:715] (4/8) Epoch 12, batch 2900, loss[loss=0.1386, simple_loss=0.2064, pruned_loss=0.03539, over 4935.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03223, over 971612.91 frames.], batch size: 29, lr: 1.84e-04
2022-05-07 08:31:45,563 INFO [train.py:715] (4/8) Epoch 12, batch 2950, loss[loss=0.1362, simple_loss=0.2127, pruned_loss=0.02981, over 4931.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.0325, over 971302.58 frames.], batch size: 21, lr: 1.84e-04
2022-05-07 08:32:24,276 INFO [train.py:715] (4/8) Epoch 12, batch 3000, loss[loss=0.142, simple_loss=0.2147, pruned_loss=0.03465, over 4787.00 frames.], tot_loss[loss=0.137, simple_loss=0.2098, pruned_loss=0.03204, over 972229.97 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:32:24,276 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 08:32:33,756 INFO [train.py:742] (4/8) Epoch 12, validation: loss=0.1056, simple_loss=0.1896, pruned_loss=0.01082, over 914524.00 frames.
2022-05-07 08:33:11,809 INFO [train.py:715] (4/8) Epoch 12, batch 3050, loss[loss=0.1342, simple_loss=0.2137, pruned_loss=0.02739, over 4817.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03191, over 971325.97 frames.], batch size: 27, lr: 1.84e-04
2022-05-07 08:33:49,493 INFO [train.py:715] (4/8) Epoch 12, batch 3100, loss[loss=0.1541, simple_loss=0.2187, pruned_loss=0.04476, over 4943.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2106, pruned_loss=0.03229, over 971690.27 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:34:27,406 INFO [train.py:715] (4/8) Epoch 12, batch 3150, loss[loss=0.1653, simple_loss=0.2571, pruned_loss=0.03674, over 4644.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.03231, over 972031.90 frames.], batch size: 13, lr: 1.84e-04
2022-05-07 08:35:05,544 INFO [train.py:715] (4/8) Epoch 12, batch 3200, loss[loss=0.153, simple_loss=0.2295, pruned_loss=0.03821, over 4877.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03281, over 972453.24 frames.], batch size: 22, lr: 1.84e-04
2022-05-07 08:35:43,248 INFO [train.py:715] (4/8) Epoch 12, batch 3250, loss[loss=0.1095, simple_loss=0.1796, pruned_loss=0.01972, over 4778.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03252, over 972755.31 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:36:21,485 INFO [train.py:715] (4/8) Epoch 12, batch 3300, loss[loss=0.1054, simple_loss=0.1802, pruned_loss=0.01536, over 4802.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03243, over 971980.46 frames.], batch size: 12, lr: 1.84e-04
2022-05-07 08:36:59,236 INFO [train.py:715] (4/8) Epoch 12, batch 3350, loss[loss=0.1327, simple_loss=0.2138, pruned_loss=0.02578, over 4798.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03242, over 972725.58 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:37:37,376 INFO [train.py:715] (4/8) Epoch 12, batch 3400, loss[loss=0.1373, simple_loss=0.2133, pruned_loss=0.03059, over 4787.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2117, pruned_loss=0.03229, over 973184.82 frames.], batch size: 18, lr: 1.84e-04
2022-05-07 08:38:14,960 INFO [train.py:715] (4/8) Epoch 12, batch 3450, loss[loss=0.1793, simple_loss=0.2561, pruned_loss=0.0513, over 4966.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2117, pruned_loss=0.03228, over 973366.14 frames.], batch size: 21, lr: 1.84e-04
2022-05-07 08:38:52,883 INFO [train.py:715] (4/8) Epoch 12, batch 3500, loss[loss=0.1256, simple_loss=0.1941, pruned_loss=0.02853, over 4969.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03281, over 973136.25 frames.], batch size: 35, lr: 1.84e-04
2022-05-07 08:39:31,087 INFO [train.py:715] (4/8) Epoch 12, batch 3550, loss[loss=0.1231, simple_loss=0.2022, pruned_loss=0.02194, over 4780.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2123, pruned_loss=0.03308, over 973407.59 frames.], batch size: 18, lr: 1.84e-04
2022-05-07 08:40:08,794 INFO [train.py:715] (4/8) Epoch 12, batch 3600, loss[loss=0.1417, simple_loss=0.2113, pruned_loss=0.03602, over 4789.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2123, pruned_loss=0.03296, over 973606.71 frames.], batch size: 24, lr: 1.84e-04
2022-05-07 08:40:46,533 INFO [train.py:715] (4/8) Epoch 12, batch 3650, loss[loss=0.1334, simple_loss=0.2101, pruned_loss=0.0284, over 4959.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.03257, over 973506.92 frames.], batch size: 24, lr: 1.84e-04
2022-05-07 08:41:24,468 INFO [train.py:715] (4/8) Epoch 12, batch 3700, loss[loss=0.1217, simple_loss=0.199, pruned_loss=0.02222, over 4903.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2106, pruned_loss=0.03212, over 973373.82 frames.], batch size: 17, lr: 1.84e-04
2022-05-07 08:42:02,373 INFO [train.py:715] (4/8) Epoch 12, batch 3750, loss[loss=0.1498, simple_loss=0.2239, pruned_loss=0.03781, over 4771.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03215, over 973240.66 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:42:40,469 INFO [train.py:715] (4/8) Epoch 12, batch 3800, loss[loss=0.1313, simple_loss=0.1944, pruned_loss=0.03414, over 4836.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03252, over 972894.73 frames.], batch size: 13, lr: 1.84e-04
2022-05-07 08:43:18,089 INFO [train.py:715] (4/8) Epoch 12, batch 3850, loss[loss=0.1306, simple_loss=0.205, pruned_loss=0.02809, over 4932.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2118, pruned_loss=0.03262, over 972672.92 frames.], batch size: 29, lr: 1.84e-04
2022-05-07 08:43:55,565 INFO [train.py:715] (4/8) Epoch 12, batch 3900, loss[loss=0.1159, simple_loss=0.199, pruned_loss=0.01641, over 4759.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03244, over 972227.31 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:44:33,440 INFO [train.py:715] (4/8) Epoch 12, batch 3950, loss[loss=0.1386, simple_loss=0.2079, pruned_loss=0.03465, over 4779.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03248, over 971941.86 frames.], batch size: 17, lr: 1.84e-04
2022-05-07 08:45:11,213 INFO [train.py:715] (4/8) Epoch 12, batch 4000, loss[loss=0.1371, simple_loss=0.2185, pruned_loss=0.02782, over 4981.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03285, over 972312.96 frames.], batch size: 28, lr: 1.84e-04
2022-05-07 08:45:49,154 INFO [train.py:715] (4/8) Epoch 12, batch 4050, loss[loss=0.141, simple_loss=0.2165, pruned_loss=0.03274, over 4823.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2124, pruned_loss=0.03299, over 972894.92 frames.], batch size: 25, lr: 1.84e-04
2022-05-07 08:46:27,044 INFO [train.py:715] (4/8) Epoch 12, batch 4100, loss[loss=0.1464, simple_loss=0.2238, pruned_loss=0.03447, over 4775.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2115, pruned_loss=0.03243, over 972033.30 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:47:05,070 INFO [train.py:715] (4/8) Epoch 12, batch 4150, loss[loss=0.1216, simple_loss=0.2025, pruned_loss=0.02038, over 4773.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03254, over 971741.24 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:47:43,032 INFO [train.py:715] (4/8) Epoch 12, batch 4200, loss[loss=0.1353, simple_loss=0.2064, pruned_loss=0.03217, over 4932.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.03271, over 971983.66 frames.], batch size: 18, lr: 1.84e-04
2022-05-07 08:48:20,657 INFO [train.py:715] (4/8) Epoch 12, batch 4250, loss[loss=0.1331, simple_loss=0.2058, pruned_loss=0.0302, over 4746.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2116, pruned_loss=0.03264, over 972370.61 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:48:58,346 INFO [train.py:715] (4/8) Epoch 12, batch 4300, loss[loss=0.1697, simple_loss=0.2369, pruned_loss=0.0512, over 4843.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03275, over 970753.86 frames.], batch size: 30, lr: 1.84e-04
2022-05-07 08:49:37,515 INFO [train.py:715] (4/8) Epoch 12, batch 4350, loss[loss=0.1138, simple_loss=0.1908, pruned_loss=0.01839, over 4968.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03197, over 971111.02 frames.], batch size: 14, lr: 1.84e-04
2022-05-07 08:50:16,263 INFO [train.py:715] (4/8) Epoch 12, batch 4400, loss[loss=0.1292, simple_loss=0.2024, pruned_loss=0.02803, over 4914.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.03238, over 970829.43 frames.], batch size: 29, lr: 1.84e-04
2022-05-07 08:50:54,765 INFO [train.py:715] (4/8) Epoch 12, batch 4450, loss[loss=0.1296, simple_loss=0.2093, pruned_loss=0.02495, over 4810.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03196, over 970629.48 frames.], batch size: 25, lr: 1.84e-04
2022-05-07 08:51:33,202 INFO [train.py:715] (4/8) Epoch 12, batch 4500, loss[loss=0.123, simple_loss=0.1958, pruned_loss=0.0251, over 4961.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2108, pruned_loss=0.03238, over 970940.84 frames.], batch size: 23, lr: 1.84e-04
2022-05-07 08:52:12,281 INFO [train.py:715] (4/8) Epoch 12, batch 4550, loss[loss=0.1229, simple_loss=0.202, pruned_loss=0.02191, over 4989.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.03234, over 971765.57 frames.], batch size: 16, lr: 1.84e-04
2022-05-07 08:52:50,490 INFO [train.py:715] (4/8) Epoch 12, batch 4600, loss[loss=0.1495, simple_loss=0.2412, pruned_loss=0.0289, over 4855.00 frames.], tot_loss[loss=0.1383, simple_loss=0.212, pruned_loss=0.03223, over 972545.43 frames.], batch size: 38, lr: 1.84e-04
2022-05-07 08:53:29,038 INFO [train.py:715] (4/8) Epoch 12, batch 4650, loss[loss=0.1275, simple_loss=0.1977, pruned_loss=0.02859, over 4906.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03209, over 971624.31 frames.], batch size: 18, lr: 1.84e-04
2022-05-07 08:54:07,729 INFO [train.py:715] (4/8) Epoch 12, batch 4700, loss[loss=0.1254, simple_loss=0.2057, pruned_loss=0.02254, over 4927.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.03227, over 971018.15 frames.], batch size: 21, lr: 1.84e-04
2022-05-07 08:54:46,298 INFO [train.py:715] (4/8) Epoch 12, batch 4750, loss[loss=0.1208, simple_loss=0.1971, pruned_loss=0.02228, over 4931.00 frames.], tot_loss[loss=0.139, simple_loss=0.2123, pruned_loss=0.03284, over 970911.28 frames.], batch size: 23, lr: 1.84e-04
2022-05-07 08:55:24,998 INFO [train.py:715] (4/8) Epoch 12, batch 4800, loss[loss=0.1157, simple_loss=0.1813, pruned_loss=0.02506, over 4738.00 frames.], tot_loss[loss=0.1396, simple_loss=0.2127, pruned_loss=0.03325, over 970978.62 frames.], batch size: 12, lr: 1.84e-04
2022-05-07 08:56:03,561 INFO [train.py:715] (4/8) Epoch 12, batch 4850, loss[loss=0.1402, simple_loss=0.2182, pruned_loss=0.03107, over 4899.00 frames.], tot_loss[loss=0.1393, simple_loss=0.2126, pruned_loss=0.033, over 971456.59 frames.], batch size: 19, lr: 1.84e-04
2022-05-07 08:56:42,593 INFO [train.py:715] (4/8) Epoch 12, batch 4900, loss[loss=0.1454, simple_loss=0.2139, pruned_loss=0.03841, over 4979.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2116, pruned_loss=0.03285, over 971668.10 frames.], batch size: 35, lr: 1.83e-04
2022-05-07 08:57:20,602 INFO [train.py:715] (4/8) Epoch 12, batch 4950, loss[loss=0.1642, simple_loss=0.2275, pruned_loss=0.05047, over 4970.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.03238, over 971813.65 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 08:57:58,211 INFO [train.py:715] (4/8) Epoch 12, batch 5000, loss[loss=0.1302, simple_loss=0.1967, pruned_loss=0.03182, over 4773.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03219, over 972248.33 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 08:58:36,392 INFO [train.py:715] (4/8) Epoch 12, batch 5050, loss[loss=0.1507, simple_loss=0.2219, pruned_loss=0.03974, over 4908.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03237, over 971976.74 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 08:59:13,984 INFO [train.py:715] (4/8) Epoch 12, batch 5100, loss[loss=0.1644, simple_loss=0.2345, pruned_loss=0.04711, over 4977.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.03243, over 973200.14 frames.], batch size: 31, lr: 1.83e-04
2022-05-07 08:59:52,113 INFO [train.py:715] (4/8) Epoch 12, batch 5150, loss[loss=0.1555, simple_loss=0.2264, pruned_loss=0.04232, over 4752.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.0327, over 973823.19 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 09:00:30,012 INFO [train.py:715] (4/8) Epoch 12, batch 5200, loss[loss=0.1836, simple_loss=0.2594, pruned_loss=0.0539, over 4739.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2113, pruned_loss=0.03251, over 973045.42 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 09:01:08,126 INFO [train.py:715] (4/8) Epoch 12, batch 5250, loss[loss=0.1479, simple_loss=0.2177, pruned_loss=0.03903, over 4881.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2108, pruned_loss=0.03245, over 972086.98 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 09:01:45,993 INFO [train.py:715] (4/8) Epoch 12, batch 5300, loss[loss=0.1213, simple_loss=0.1938, pruned_loss=0.02437, over 4796.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03176, over 970924.86 frames.], batch size: 24, lr: 1.83e-04
2022-05-07 09:02:24,110 INFO [train.py:715] (4/8) Epoch 12, batch 5350, loss[loss=0.1342, simple_loss=0.2072, pruned_loss=0.03065, over 4938.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03137, over 971214.64 frames.], batch size: 21, lr: 1.83e-04
2022-05-07 09:03:02,671 INFO [train.py:715] (4/8) Epoch 12, batch 5400, loss[loss=0.1385, simple_loss=0.2028, pruned_loss=0.03709, over 4983.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.03162, over 971451.85 frames.], batch size: 31, lr: 1.83e-04
2022-05-07 09:03:40,514 INFO [train.py:715] (4/8) Epoch 12, batch 5450, loss[loss=0.161, simple_loss=0.2452, pruned_loss=0.03843, over 4787.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03136, over 972038.33 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:04:18,718 INFO [train.py:715] (4/8) Epoch 12, batch 5500, loss[loss=0.124, simple_loss=0.2027, pruned_loss=0.02265, over 4836.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03166, over 972347.75 frames.], batch size: 13, lr: 1.83e-04
2022-05-07 09:04:56,508 INFO [train.py:715] (4/8) Epoch 12, batch 5550, loss[loss=0.1464, simple_loss=0.2185, pruned_loss=0.03713, over 4972.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03132, over 971900.08 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:05:35,154 INFO [train.py:715] (4/8) Epoch 12, batch 5600, loss[loss=0.1519, simple_loss=0.2244, pruned_loss=0.03967, over 4781.00 frames.], tot_loss[loss=0.137, simple_loss=0.2107, pruned_loss=0.0317, over 972024.38 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 09:06:12,950 INFO [train.py:715] (4/8) Epoch 12, batch 5650, loss[loss=0.112, simple_loss=0.1953, pruned_loss=0.01436, over 4962.00 frames.], tot_loss[loss=0.1371, simple_loss=0.211, pruned_loss=0.03162, over 972353.99 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:06:50,900 INFO [train.py:715] (4/8) Epoch 12, batch 5700, loss[loss=0.1322, simple_loss=0.2024, pruned_loss=0.03099, over 4871.00 frames.], tot_loss[loss=0.1369, simple_loss=0.211, pruned_loss=0.03141, over 971737.42 frames.], batch size: 32, lr: 1.83e-04
2022-05-07 09:07:29,807 INFO [train.py:715] (4/8) Epoch 12, batch 5750, loss[loss=0.1395, simple_loss=0.2141, pruned_loss=0.0324, over 4792.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2117, pruned_loss=0.03197, over 971888.20 frames.], batch size: 24, lr: 1.83e-04
2022-05-07 09:08:07,980 INFO [train.py:715] (4/8) Epoch 12, batch 5800, loss[loss=0.173, simple_loss=0.2484, pruned_loss=0.0488, over 4777.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2111, pruned_loss=0.03152, over 972429.30 frames.], batch size: 14, lr: 1.83e-04
2022-05-07 09:08:46,181 INFO [train.py:715] (4/8) Epoch 12, batch 5850, loss[loss=0.1387, simple_loss=0.212, pruned_loss=0.03269, over 4786.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2105, pruned_loss=0.03131, over 971782.94 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:09:24,395 INFO [train.py:715] (4/8) Epoch 12, batch 5900, loss[loss=0.1382, simple_loss=0.2171, pruned_loss=0.02962, over 4876.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03144, over 972367.31 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 09:10:02,493 INFO [train.py:715] (4/8) Epoch 12, batch 5950, loss[loss=0.1511, simple_loss=0.225, pruned_loss=0.03862, over 4858.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2109, pruned_loss=0.03147, over 973335.63 frames.], batch size: 38, lr: 1.83e-04
2022-05-07 09:10:40,375 INFO [train.py:715] (4/8) Epoch 12, batch 6000, loss[loss=0.1312, simple_loss=0.2086, pruned_loss=0.02691, over 4852.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2111, pruned_loss=0.03155, over 972882.41 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 09:10:40,375 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 09:10:49,852 INFO [train.py:742] (4/8) Epoch 12, validation: loss=0.1057, simple_loss=0.1897, pruned_loss=0.01086, over 914524.00 frames.
2022-05-07 09:11:28,466 INFO [train.py:715] (4/8) Epoch 12, batch 6050, loss[loss=0.1351, simple_loss=0.2185, pruned_loss=0.02583, over 4865.00 frames.], tot_loss[loss=0.1365, simple_loss=0.211, pruned_loss=0.03102, over 972865.03 frames.], batch size: 22, lr: 1.83e-04
2022-05-07 09:12:07,171 INFO [train.py:715] (4/8) Epoch 12, batch 6100, loss[loss=0.1639, simple_loss=0.2256, pruned_loss=0.05116, over 4821.00 frames.], tot_loss[loss=0.137, simple_loss=0.2114, pruned_loss=0.03137, over 972376.05 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:12:46,247 INFO [train.py:715] (4/8) Epoch 12, batch 6150, loss[loss=0.1262, simple_loss=0.1924, pruned_loss=0.03004, over 4815.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2115, pruned_loss=0.03195, over 973410.96 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:13:24,046 INFO [train.py:715] (4/8) Epoch 12, batch 6200, loss[loss=0.1696, simple_loss=0.2349, pruned_loss=0.05211, over 4856.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2117, pruned_loss=0.03196, over 974362.30 frames.], batch size: 30, lr: 1.83e-04
2022-05-07 09:14:02,110 INFO [train.py:715] (4/8) Epoch 12, batch 6250, loss[loss=0.1548, simple_loss=0.2135, pruned_loss=0.04799, over 4903.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03145, over 973775.28 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:14:42,631 INFO [train.py:715] (4/8) Epoch 12, batch 6300, loss[loss=0.1316, simple_loss=0.1959, pruned_loss=0.03365, over 4742.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2105, pruned_loss=0.03126, over 972983.59 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 09:15:20,411 INFO [train.py:715] (4/8) Epoch 12, batch 6350, loss[loss=0.1208, simple_loss=0.2005, pruned_loss=0.02051, over 4972.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2106, pruned_loss=0.03134, over 972792.42 frames.], batch size: 39, lr: 1.83e-04
2022-05-07 09:15:58,260 INFO [train.py:715] (4/8) Epoch 12, batch 6400, loss[loss=0.1201, simple_loss=0.2035, pruned_loss=0.01832, over 4828.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03212, over 972328.87 frames.], batch size: 26, lr: 1.83e-04
2022-05-07 09:16:36,189 INFO [train.py:715] (4/8) Epoch 12, batch 6450, loss[loss=0.1485, simple_loss=0.2223, pruned_loss=0.03733, over 4829.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.0323, over 971209.12 frames.], batch size: 27, lr: 1.83e-04
2022-05-07 09:17:14,182 INFO [train.py:715] (4/8) Epoch 12, batch 6500, loss[loss=0.1238, simple_loss=0.1955, pruned_loss=0.02599, over 4970.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03202, over 971752.70 frames.], batch size: 14, lr: 1.83e-04
2022-05-07 09:17:51,825 INFO [train.py:715] (4/8) Epoch 12, batch 6550, loss[loss=0.1329, simple_loss=0.2034, pruned_loss=0.03121, over 4937.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.0316, over 972902.15 frames.], batch size: 29, lr: 1.83e-04
2022-05-07 09:18:29,933 INFO [train.py:715] (4/8) Epoch 12, batch 6600, loss[loss=0.1419, simple_loss=0.2173, pruned_loss=0.03325, over 4927.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2116, pruned_loss=0.03166, over 972510.46 frames.], batch size: 23, lr: 1.83e-04
2022-05-07 09:19:08,080 INFO [train.py:715] (4/8) Epoch 12, batch 6650, loss[loss=0.1403, simple_loss=0.2177, pruned_loss=0.03146, over 4857.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2122, pruned_loss=0.03226, over 972346.74 frames.], batch size: 30, lr: 1.83e-04
2022-05-07 09:19:46,571 INFO [train.py:715] (4/8) Epoch 12, batch 6700, loss[loss=0.1443, simple_loss=0.2212, pruned_loss=0.03367, over 4836.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2117, pruned_loss=0.03175, over 971774.34 frames.], batch size: 25, lr: 1.83e-04
2022-05-07 09:20:24,046 INFO [train.py:715] (4/8) Epoch 12, batch 6750, loss[loss=0.1369, simple_loss=0.2144, pruned_loss=0.02968, over 4839.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2116, pruned_loss=0.03162, over 971989.84 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:21:02,174 INFO [train.py:715] (4/8) Epoch 12, batch 6800, loss[loss=0.1554, simple_loss=0.2362, pruned_loss=0.03726, over 4912.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2114, pruned_loss=0.03101, over 971662.10 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:21:40,239 INFO [train.py:715] (4/8) Epoch 12, batch 6850, loss[loss=0.1417, simple_loss=0.209, pruned_loss=0.03724, over 4915.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2105, pruned_loss=0.03059, over 971486.93 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:22:18,034 INFO [train.py:715] (4/8) Epoch 12, batch 6900, loss[loss=0.1128, simple_loss=0.1802, pruned_loss=0.0227, over 4880.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2102, pruned_loss=0.03079, over 972443.47 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 09:22:56,143 INFO [train.py:715] (4/8) Epoch 12, batch 6950, loss[loss=0.1184, simple_loss=0.1869, pruned_loss=0.02498, over 4975.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03149, over 972897.80 frames.], batch size: 14, lr: 1.83e-04
2022-05-07 09:23:34,137 INFO [train.py:715] (4/8) Epoch 12, batch 7000, loss[loss=0.1359, simple_loss=0.2182, pruned_loss=0.0268, over 4791.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03139, over 972236.76 frames.], batch size: 24, lr: 1.83e-04
2022-05-07 09:24:12,557 INFO [train.py:715] (4/8) Epoch 12, batch 7050, loss[loss=0.1298, simple_loss=0.2025, pruned_loss=0.02855, over 4830.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03199, over 971644.75 frames.], batch size: 13, lr: 1.83e-04
2022-05-07 09:24:50,037 INFO [train.py:715] (4/8) Epoch 12, batch 7100, loss[loss=0.1377, simple_loss=0.2171, pruned_loss=0.02918, over 4824.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03185, over 972283.36 frames.], batch size: 27, lr: 1.83e-04
2022-05-07 09:25:28,613 INFO [train.py:715] (4/8) Epoch 12, batch 7150, loss[loss=0.1374, simple_loss=0.2152, pruned_loss=0.02981, over 4835.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03182, over 972757.70 frames.], batch size: 26, lr: 1.83e-04
2022-05-07 09:26:06,441 INFO [train.py:715] (4/8) Epoch 12, batch 7200, loss[loss=0.1732, simple_loss=0.2515, pruned_loss=0.04742, over 4879.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03242, over 973249.24 frames.], batch size: 32, lr: 1.83e-04
2022-05-07 09:26:44,292 INFO [train.py:715] (4/8) Epoch 12, batch 7250, loss[loss=0.1279, simple_loss=0.196, pruned_loss=0.02989, over 4806.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.03232, over 972835.99 frames.], batch size: 12, lr: 1.83e-04
2022-05-07 09:27:22,553 INFO [train.py:715] (4/8) Epoch 12, batch 7300, loss[loss=0.1238, simple_loss=0.2038, pruned_loss=0.02189, over 4806.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03207, over 972505.88 frames.], batch size: 21, lr: 1.83e-04
2022-05-07 09:28:00,293 INFO [train.py:715] (4/8) Epoch 12, batch 7350, loss[loss=0.1365, simple_loss=0.2055, pruned_loss=0.03373, over 4857.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03174, over 972909.79 frames.], batch size: 20, lr: 1.83e-04
2022-05-07 09:28:38,318 INFO [train.py:715] (4/8) Epoch 12, batch 7400, loss[loss=0.1293, simple_loss=0.2116, pruned_loss=0.02354, over 4838.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.03222, over 973080.06 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:29:16,072 INFO [train.py:715] (4/8) Epoch 12, batch 7450, loss[loss=0.1271, simple_loss=0.2076, pruned_loss=0.02333, over 4890.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03186, over 973694.89 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 09:29:54,163 INFO [train.py:715] (4/8) Epoch 12, batch 7500, loss[loss=0.1401, simple_loss=0.1948, pruned_loss=0.04273, over 4893.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03144, over 974527.63 frames.], batch size: 32, lr: 1.83e-04
2022-05-07 09:30:32,182 INFO [train.py:715] (4/8) Epoch 12, batch 7550, loss[loss=0.1303, simple_loss=0.1998, pruned_loss=0.03041, over 4824.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2111, pruned_loss=0.03153, over 973483.87 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:31:10,032 INFO [train.py:715] (4/8) Epoch 12, batch 7600, loss[loss=0.1397, simple_loss=0.2128, pruned_loss=0.03331, over 4933.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2116, pruned_loss=0.03184, over 972619.96 frames.], batch size: 29, lr: 1.83e-04
2022-05-07 09:31:48,262 INFO [train.py:715] (4/8) Epoch 12, batch 7650, loss[loss=0.1375, simple_loss=0.206, pruned_loss=0.03453, over 4976.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2114, pruned_loss=0.03193, over 972136.16 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:32:26,439 INFO [train.py:715] (4/8) Epoch 12, batch 7700, loss[loss=0.1394, simple_loss=0.2137, pruned_loss=0.0325, over 4923.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2117, pruned_loss=0.03202, over 971976.12 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:33:04,637 INFO [train.py:715] (4/8) Epoch 12, batch 7750, loss[loss=0.1412, simple_loss=0.2186, pruned_loss=0.03187, over 4806.00 frames.], tot_loss[loss=0.138, simple_loss=0.2118, pruned_loss=0.03209, over 971723.21 frames.], batch size: 21, lr: 1.83e-04
2022-05-07 09:33:42,403 INFO [train.py:715] (4/8) Epoch 12, batch 7800, loss[loss=0.1394, simple_loss=0.2064, pruned_loss=0.03615, over 4876.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2114, pruned_loss=0.03205, over 971419.72 frames.], batch size: 32, lr: 1.83e-04
2022-05-07 09:34:20,596 INFO [train.py:715] (4/8) Epoch 12, batch 7850, loss[loss=0.1191, simple_loss=0.1899, pruned_loss=0.02409, over 4847.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03191, over 971521.90 frames.], batch size: 13, lr: 1.83e-04
2022-05-07 09:34:58,402 INFO [train.py:715] (4/8) Epoch 12, batch 7900, loss[loss=0.1568, simple_loss=0.2274, pruned_loss=0.04309, over 4863.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2107, pruned_loss=0.03153, over 972210.65 frames.], batch size: 32, lr: 1.83e-04
2022-05-07 09:35:36,649 INFO [train.py:715] (4/8) Epoch 12, batch 7950, loss[loss=0.1575, simple_loss=0.2476, pruned_loss=0.03373, over 4749.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03145, over 973053.53 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 09:36:14,622 INFO [train.py:715] (4/8) Epoch 12, batch 8000, loss[loss=0.1333, simple_loss=0.1998, pruned_loss=0.03342, over 4761.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03207, over 972529.29 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 09:36:53,083 INFO [train.py:715] (4/8) Epoch 12, batch 8050, loss[loss=0.1296, simple_loss=0.1948, pruned_loss=0.03226, over 4786.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.0321, over 973074.67 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:37:31,432 INFO [train.py:715] (4/8) Epoch 12, batch 8100, loss[loss=0.1313, simple_loss=0.2001, pruned_loss=0.03129, over 4901.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2111, pruned_loss=0.03218, over 973629.83 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:38:09,022 INFO [train.py:715] (4/8) Epoch 12, batch 8150, loss[loss=0.1274, simple_loss=0.2119, pruned_loss=0.0214, over 4794.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2121, pruned_loss=0.03246, over 973629.19 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:38:47,284 INFO [train.py:715] (4/8) Epoch 12, batch 8200, loss[loss=0.1352, simple_loss=0.2066, pruned_loss=0.03195, over 4865.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03212, over 973236.60 frames.], batch size: 32, lr: 1.83e-04
2022-05-07 09:39:25,280 INFO [train.py:715] (4/8) Epoch 12, batch 8250, loss[loss=0.1293, simple_loss=0.2002, pruned_loss=0.02916, over 4845.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03206, over 973708.53 frames.], batch size: 30, lr: 1.83e-04
2022-05-07 09:40:03,012 INFO [train.py:715] (4/8) Epoch 12, batch 8300, loss[loss=0.1529, simple_loss=0.2337, pruned_loss=0.03605, over 4905.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2112, pruned_loss=0.03193, over 973804.90 frames.], batch size: 39, lr: 1.83e-04
2022-05-07 09:40:41,112 INFO [train.py:715] (4/8) Epoch 12, batch 8350, loss[loss=0.1329, simple_loss=0.2067, pruned_loss=0.02962, over 4821.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03202, over 973394.10 frames.], batch size: 13, lr: 1.83e-04
2022-05-07 09:41:19,301 INFO [train.py:715] (4/8) Epoch 12, batch 8400, loss[loss=0.125, simple_loss=0.1987, pruned_loss=0.02562, over 4991.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.0322, over 973027.78 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 09:41:57,373 INFO [train.py:715] (4/8) Epoch 12, batch 8450, loss[loss=0.1203, simple_loss=0.2031, pruned_loss=0.01874, over 4823.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03158, over 973070.02 frames.], batch size: 25, lr: 1.83e-04
2022-05-07 09:42:34,900 INFO [train.py:715] (4/8) Epoch 12, batch 8500, loss[loss=0.1244, simple_loss=0.2022, pruned_loss=0.02329, over 4837.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03174, over 972153.18 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:43:13,187 INFO [train.py:715] (4/8) Epoch 12, batch 8550, loss[loss=0.1665, simple_loss=0.2262, pruned_loss=0.0534, over 4756.00 frames.], tot_loss[loss=0.137, simple_loss=0.2102, pruned_loss=0.03192, over 972424.31 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 09:43:51,187 INFO [train.py:715] (4/8) Epoch 12, batch 8600, loss[loss=0.1296, simple_loss=0.2065, pruned_loss=0.0263, over 4768.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2109, pruned_loss=0.0325, over 971699.94 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:44:28,879 INFO [train.py:715] (4/8) Epoch 12, batch 8650, loss[loss=0.153, simple_loss=0.2305, pruned_loss=0.03769, over 4855.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03259, over 971990.94 frames.], batch size: 20, lr: 1.83e-04
2022-05-07 09:45:07,104 INFO [train.py:715] (4/8) Epoch 12, batch 8700, loss[loss=0.1397, simple_loss=0.2113, pruned_loss=0.03409, over 4818.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2112, pruned_loss=0.03223, over 971209.97 frames.], batch size: 25, lr: 1.83e-04
2022-05-07 09:45:45,271 INFO [train.py:715] (4/8) Epoch 12, batch 8750, loss[loss=0.1311, simple_loss=0.204, pruned_loss=0.02909, over 4737.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2104, pruned_loss=0.03223, over 971938.33 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 09:46:23,700 INFO [train.py:715] (4/8) Epoch 12, batch 8800, loss[loss=0.1237, simple_loss=0.1937, pruned_loss=0.02685, over 4899.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2096, pruned_loss=0.03181, over 972128.11 frames.], batch size: 19, lr: 1.83e-04
2022-05-07 09:47:01,614 INFO [train.py:715] (4/8) Epoch 12, batch 8850, loss[loss=0.1649, simple_loss=0.2369, pruned_loss=0.04644, over 4873.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.0316, over 971552.69 frames.], batch size: 22, lr: 1.83e-04
2022-05-07 09:47:40,605 INFO [train.py:715] (4/8) Epoch 12, batch 8900, loss[loss=0.115, simple_loss=0.1861, pruned_loss=0.02195, over 4933.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03166, over 971789.84 frames.], batch size: 23, lr: 1.83e-04
2022-05-07 09:48:20,143 INFO [train.py:715] (4/8) Epoch 12, batch 8950, loss[loss=0.1344, simple_loss=0.2054, pruned_loss=0.03168, over 4957.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.0318, over 972196.27 frames.], batch size: 24, lr: 1.83e-04
2022-05-07 09:48:58,103 INFO [train.py:715] (4/8) Epoch 12, batch 9000, loss[loss=0.1331, simple_loss=0.2045, pruned_loss=0.03081, over 4786.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03203, over 973680.63 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:48:58,103 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 09:49:07,573 INFO [train.py:742] (4/8) Epoch 12, validation: loss=0.1057, simple_loss=0.1898, pruned_loss=0.01084, over 914524.00 frames.
2022-05-07 09:49:45,344 INFO [train.py:715] (4/8) Epoch 12, batch 9050, loss[loss=0.1605, simple_loss=0.2366, pruned_loss=0.04216, over 4754.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2114, pruned_loss=0.03201, over 973169.40 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 09:50:23,564 INFO [train.py:715] (4/8) Epoch 12, batch 9100, loss[loss=0.1304, simple_loss=0.1958, pruned_loss=0.0325, over 4901.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03252, over 973470.44 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:51:01,822 INFO [train.py:715] (4/8) Epoch 12, batch 9150, loss[loss=0.1367, simple_loss=0.2147, pruned_loss=0.02936, over 4777.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.0329, over 972576.23 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:51:39,544 INFO [train.py:715] (4/8) Epoch 12, batch 9200, loss[loss=0.1144, simple_loss=0.1879, pruned_loss=0.02042, over 4912.00 frames.], tot_loss[loss=0.1392, simple_loss=0.2126, pruned_loss=0.03289, over 973072.45 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:52:17,394 INFO [train.py:715] (4/8) Epoch 12, batch 9250, loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02886, over 4792.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.03222, over 972904.60 frames.], batch size: 17, lr: 1.83e-04
2022-05-07 09:52:55,473 INFO [train.py:715] (4/8) Epoch 12, batch 9300, loss[loss=0.09433, simple_loss=0.1725, pruned_loss=0.008098, over 4852.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.0317, over 972702.40 frames.], batch size: 20, lr: 1.83e-04
2022-05-07 09:53:33,065 INFO [train.py:715] (4/8) Epoch 12, batch 9350, loss[loss=0.1281, simple_loss=0.1978, pruned_loss=0.0292, over 4774.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2113, pruned_loss=0.03167, over 972618.29 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:54:10,843 INFO [train.py:715] (4/8) Epoch 12, batch 9400, loss[loss=0.1286, simple_loss=0.1973, pruned_loss=0.02995, over 4685.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.03199, over 972281.18 frames.], batch size: 15, lr: 1.83e-04
2022-05-07 09:54:48,555 INFO [train.py:715] (4/8) Epoch 12, batch 9450, loss[loss=0.1437, simple_loss=0.2225, pruned_loss=0.03243, over 4930.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2114, pruned_loss=0.03187, over 972167.54 frames.], batch size: 18, lr: 1.83e-04
2022-05-07 09:55:26,595 INFO [train.py:715] (4/8) Epoch 12, batch 9500, loss[loss=0.1412, simple_loss=0.219, pruned_loss=0.03175, over 4737.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2116, pruned_loss=0.03198, over 972669.01 frames.], batch size: 16, lr: 1.83e-04
2022-05-07 09:56:04,149 INFO [train.py:715] (4/8) Epoch 12, batch 9550, loss[loss=0.1576, simple_loss=0.2177, pruned_loss=0.04874, over 4855.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2122, pruned_loss=0.03258, over 972583.01 frames.], batch size: 32, lr: 1.82e-04
2022-05-07 09:56:41,640 INFO [train.py:715] (4/8) Epoch 12, batch 9600, loss[loss=0.1623, simple_loss=0.2311, pruned_loss=0.0468, over 4862.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03253, over 971634.69 frames.], batch size: 32, lr: 1.82e-04
2022-05-07 09:57:19,884 INFO [train.py:715] (4/8) Epoch 12, batch 9650, loss[loss=0.1281, simple_loss=0.1968, pruned_loss=0.02972, over 4984.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03215, over 972541.62 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 09:57:57,756 INFO [train.py:715] (4/8) Epoch 12, batch 9700, loss[loss=0.1116, simple_loss=0.1862, pruned_loss=0.01845, over 4746.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03169, over 972310.91 frames.], batch size: 12, lr: 1.82e-04
2022-05-07 09:58:35,535 INFO [train.py:715] (4/8) Epoch 12, batch 9750, loss[loss=0.1081, simple_loss=0.1838, pruned_loss=0.01626, over 4978.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03154, over 971567.33 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 09:59:13,483 INFO [train.py:715] (4/8) Epoch 12, batch 9800, loss[loss=0.1303, simple_loss=0.2053, pruned_loss=0.02769, over 4814.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03153, over 971176.09 frames.], batch size: 27, lr: 1.82e-04
2022-05-07 09:59:52,002 INFO [train.py:715] (4/8) Epoch 12, batch 9850, loss[loss=0.1598, simple_loss=0.2482, pruned_loss=0.03566, over 4874.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03146, over 971620.44 frames.], batch size: 22, lr: 1.82e-04
2022-05-07 10:00:29,633 INFO [train.py:715] (4/8) Epoch 12, batch 9900, loss[loss=0.1377, simple_loss=0.2018, pruned_loss=0.03676, over 4966.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03102, over 971319.72 frames.], batch size: 35, lr: 1.82e-04
2022-05-07 10:01:07,879 INFO [train.py:715] (4/8) Epoch 12, batch 9950, loss[loss=0.1624, simple_loss=0.2482, pruned_loss=0.03832, over 4834.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2105, pruned_loss=0.03126, over 972059.45 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:01:46,634 INFO [train.py:715] (4/8) Epoch 12, batch 10000, loss[loss=0.1656, simple_loss=0.2373, pruned_loss=0.04693, over 4852.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03166, over 972887.50 frames.], batch size: 20, lr: 1.82e-04
2022-05-07 10:02:25,166 INFO [train.py:715] (4/8) Epoch 12, batch 10050, loss[loss=0.1444, simple_loss=0.2106, pruned_loss=0.03909, over 4796.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03197, over 972658.19 frames.], batch size: 17, lr: 1.82e-04
2022-05-07 10:03:03,504 INFO [train.py:715] (4/8) Epoch 12, batch 10100, loss[loss=0.1397, simple_loss=0.2139, pruned_loss=0.03273, over 4939.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03206, over 972448.96 frames.], batch size: 21, lr: 1.82e-04
2022-05-07 10:03:41,912 INFO [train.py:715] (4/8) Epoch 12, batch 10150, loss[loss=0.1234, simple_loss=0.1929, pruned_loss=0.02693, over 4855.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.032, over 972636.40 frames.], batch size: 32, lr: 1.82e-04
2022-05-07 10:04:20,551 INFO [train.py:715] (4/8) Epoch 12, batch 10200, loss[loss=0.1215, simple_loss=0.1979, pruned_loss=0.02259, over 4748.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.0316, over 972302.38 frames.], batch size: 16, lr: 1.82e-04
2022-05-07 10:04:57,864 INFO [train.py:715] (4/8) Epoch 12, batch 10250, loss[loss=0.1411, simple_loss=0.2166, pruned_loss=0.03283, over 4916.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03172, over 972488.17 frames.], batch size: 23, lr: 1.82e-04
2022-05-07 10:05:36,038 INFO [train.py:715] (4/8) Epoch 12, batch 10300, loss[loss=0.1234, simple_loss=0.1961, pruned_loss=0.02537, over 4901.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03132, over 973190.12 frames.], batch size: 19, lr: 1.82e-04
2022-05-07 10:06:14,198 INFO [train.py:715] (4/8) Epoch 12, batch 10350, loss[loss=0.187, simple_loss=0.2393, pruned_loss=0.06738, over 4697.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03208, over 973481.49 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:06:52,242 INFO [train.py:715] (4/8) Epoch 12, batch 10400, loss[loss=0.1379, simple_loss=0.21, pruned_loss=0.03294, over 4743.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03187, over 972638.08 frames.], batch size: 16, lr: 1.82e-04
2022-05-07 10:07:29,800 INFO [train.py:715] (4/8) Epoch 12, batch 10450, loss[loss=0.1366, simple_loss=0.2058, pruned_loss=0.03372, over 4837.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03182, over 972274.07 frames.], batch size: 30, lr: 1.82e-04
2022-05-07 10:08:07,729 INFO [train.py:715] (4/8) Epoch 12, batch 10500, loss[loss=0.1062, simple_loss=0.1853, pruned_loss=0.01357, over 4920.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.0313, over 972124.43 frames.], batch size: 29, lr: 1.82e-04
2022-05-07 10:08:46,137 INFO [train.py:715] (4/8) Epoch 12, batch 10550, loss[loss=0.1558, simple_loss=0.2234, pruned_loss=0.0441, over 4837.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03173, over 972171.04 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:09:23,510 INFO [train.py:715] (4/8) Epoch 12, batch 10600, loss[loss=0.1369, simple_loss=0.2106, pruned_loss=0.03162, over 4914.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03153, over 971324.09 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:10:01,494 INFO [train.py:715] (4/8) Epoch 12, batch 10650, loss[loss=0.1516, simple_loss=0.2112, pruned_loss=0.04601, over 4816.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03204, over 972032.52 frames.], batch size: 13, lr: 1.82e-04
2022-05-07 10:10:39,355 INFO [train.py:715] (4/8) Epoch 12, batch 10700, loss[loss=0.1567, simple_loss=0.2279, pruned_loss=0.04273, over 4920.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.03219, over 972021.56 frames.], batch size: 39, lr: 1.82e-04
2022-05-07 10:11:16,858 INFO [train.py:715] (4/8) Epoch 12, batch 10750, loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03079, over 4886.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03239, over 972021.67 frames.], batch size: 22, lr: 1.82e-04
2022-05-07 10:11:54,745 INFO [train.py:715] (4/8) Epoch 12, batch 10800, loss[loss=0.1764, simple_loss=0.2444, pruned_loss=0.0542, over 4959.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.0322, over 972457.77 frames.], batch size: 39, lr: 1.82e-04
2022-05-07 10:12:32,735 INFO [train.py:715] (4/8) Epoch 12, batch 10850, loss[loss=0.125, simple_loss=0.1891, pruned_loss=0.03045, over 4834.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03154, over 972600.03 frames.], batch size: 13, lr: 1.82e-04
2022-05-07 10:13:11,526 INFO [train.py:715] (4/8) Epoch 12, batch 10900, loss[loss=0.1385, simple_loss=0.2223, pruned_loss=0.02738, over 4896.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03136, over 972314.00 frames.], batch size: 19, lr: 1.82e-04
2022-05-07 10:13:48,733 INFO [train.py:715] (4/8) Epoch 12, batch 10950, loss[loss=0.145, simple_loss=0.2199, pruned_loss=0.03505, over 4891.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03173, over 972062.75 frames.], batch size: 32, lr: 1.82e-04
2022-05-07 10:14:26,876 INFO [train.py:715] (4/8) Epoch 12, batch 11000, loss[loss=0.1765, simple_loss=0.2463, pruned_loss=0.05332, over 4856.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03159, over 972426.61 frames.], batch size: 20, lr: 1.82e-04
2022-05-07 10:15:05,147 INFO [train.py:715] (4/8) Epoch 12, batch 11050, loss[loss=0.1133, simple_loss=0.1969, pruned_loss=0.01489, over 4788.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03131, over 972717.09 frames.], batch size: 24, lr: 1.82e-04
2022-05-07 10:15:42,771 INFO [train.py:715] (4/8) Epoch 12, batch 11100, loss[loss=0.153, simple_loss=0.2225, pruned_loss=0.04178, over 4879.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03173, over 973166.46 frames.], batch size: 16, lr: 1.82e-04
2022-05-07 10:16:21,273 INFO [train.py:715] (4/8) Epoch 12, batch 11150, loss[loss=0.155, simple_loss=0.2269, pruned_loss=0.04157, over 4797.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03206, over 973628.76 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:16:58,891 INFO [train.py:715] (4/8) Epoch 12, batch 11200, loss[loss=0.1279, simple_loss=0.1942, pruned_loss=0.03081, over 4892.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03159, over 973331.57 frames.], batch size: 22, lr: 1.82e-04
2022-05-07 10:17:36,988 INFO [train.py:715] (4/8) Epoch 12, batch 11250, loss[loss=0.1436, simple_loss=0.2115, pruned_loss=0.0378, over 4813.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03181, over 972270.76 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:18:14,709 INFO [train.py:715] (4/8) Epoch 12, batch 11300, loss[loss=0.1191, simple_loss=0.1955, pruned_loss=0.02132, over 4884.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.032, over 972913.43 frames.], batch size: 19, lr: 1.82e-04
2022-05-07 10:18:51,981 INFO [train.py:715] (4/8) Epoch 12, batch 11350, loss[loss=0.1452, simple_loss=0.2125, pruned_loss=0.03892, over 4784.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03181, over 973281.38 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:19:30,201 INFO [train.py:715] (4/8) Epoch 12, batch 11400, loss[loss=0.1373, simple_loss=0.2, pruned_loss=0.03731, over 4835.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.03195, over 972624.21 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:20:07,742 INFO [train.py:715] (4/8) Epoch 12, batch 11450, loss[loss=0.1479, simple_loss=0.2166, pruned_loss=0.0396, over 4774.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03211, over 973075.06 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:20:45,258 INFO [train.py:715] (4/8) Epoch 12, batch 11500, loss[loss=0.134, simple_loss=0.2058, pruned_loss=0.0311, over 4790.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2103, pruned_loss=0.0325, over 973090.10 frames.], batch size: 24, lr: 1.82e-04
2022-05-07 10:21:23,004 INFO [train.py:715] (4/8) Epoch 12, batch 11550, loss[loss=0.1371, simple_loss=0.2076, pruned_loss=0.03332, over 4761.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2104, pruned_loss=0.03241, over 972681.05 frames.], batch size: 16, lr: 1.82e-04
2022-05-07 10:22:01,395 INFO [train.py:715] (4/8) Epoch 12, batch 11600, loss[loss=0.1159, simple_loss=0.1875, pruned_loss=0.0221, over 4973.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2106, pruned_loss=0.03236, over 972377.36 frames.], batch size: 25, lr: 1.82e-04
2022-05-07 10:22:38,880 INFO [train.py:715] (4/8) Epoch 12, batch 11650, loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02944, over 4784.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2109, pruned_loss=0.03275, over 972768.02 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:23:16,092 INFO [train.py:715] (4/8) Epoch 12, batch 11700, loss[loss=0.126, simple_loss=0.2066, pruned_loss=0.02271, over 4971.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2112, pruned_loss=0.03269, over 972656.21 frames.], batch size: 24, lr: 1.82e-04
2022-05-07 10:23:53,749 INFO [train.py:715] (4/8) Epoch 12, batch 11750, loss[loss=0.1766, simple_loss=0.2323, pruned_loss=0.06051, over 4837.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03269, over 972799.04 frames.], batch size: 25, lr: 1.82e-04
2022-05-07 10:24:31,084 INFO [train.py:715] (4/8) Epoch 12, batch 11800, loss[loss=0.1132, simple_loss=0.1895, pruned_loss=0.01842, over 4815.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2111, pruned_loss=0.03295, over 972231.72 frames.], batch size: 27, lr: 1.82e-04
2022-05-07 10:25:08,778 INFO [train.py:715] (4/8) Epoch 12, batch 11850, loss[loss=0.1526, simple_loss=0.226, pruned_loss=0.03962, over 4895.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2104, pruned_loss=0.03248, over 972364.18 frames.], batch size: 19, lr: 1.82e-04
2022-05-07 10:25:46,625 INFO [train.py:715] (4/8) Epoch 12, batch 11900, loss[loss=0.1395, simple_loss=0.2017, pruned_loss=0.03865, over 4975.00 frames.], tot_loss[loss=0.137, simple_loss=0.2098, pruned_loss=0.0321, over 972709.11 frames.], batch size: 25, lr: 1.82e-04
2022-05-07 10:26:24,516 INFO [train.py:715] (4/8) Epoch 12, batch 11950, loss[loss=0.1308, simple_loss=0.2042, pruned_loss=0.02874, over 4786.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2089, pruned_loss=0.03169, over 972786.74 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:27:01,978 INFO [train.py:715] (4/8) Epoch 12, batch 12000, loss[loss=0.1566, simple_loss=0.2126, pruned_loss=0.05025, over 4977.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2095, pruned_loss=0.0321, over 972677.71 frames.], batch size: 31, lr: 1.82e-04
2022-05-07 10:27:01,979 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 10:27:11,323 INFO [train.py:742] (4/8) Epoch 12, validation: loss=0.1058, simple_loss=0.1897, pruned_loss=0.01095, over 914524.00 frames.
2022-05-07 10:27:50,014 INFO [train.py:715] (4/8) Epoch 12, batch 12050, loss[loss=0.1317, simple_loss=0.2008, pruned_loss=0.0313, over 4913.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2095, pruned_loss=0.032, over 972846.55 frames.], batch size: 29, lr: 1.82e-04
2022-05-07 10:28:29,092 INFO [train.py:715] (4/8) Epoch 12, batch 12100, loss[loss=0.1379, simple_loss=0.2134, pruned_loss=0.03115, over 4692.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2096, pruned_loss=0.03204, over 971689.77 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:29:08,847 INFO [train.py:715] (4/8) Epoch 12, batch 12150, loss[loss=0.1419, simple_loss=0.2041, pruned_loss=0.03981, over 4699.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2095, pruned_loss=0.03177, over 970288.95 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:29:47,129 INFO [train.py:715] (4/8) Epoch 12, batch 12200, loss[loss=0.1187, simple_loss=0.1942, pruned_loss=0.02157, over 4959.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.0313, over 970407.04 frames.], batch size: 24, lr: 1.82e-04
2022-05-07 10:30:25,386 INFO [train.py:715] (4/8) Epoch 12, batch 12250, loss[loss=0.1286, simple_loss=0.1963, pruned_loss=0.03044, over 4982.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03073, over 970391.77 frames.], batch size: 25, lr: 1.82e-04
2022-05-07 10:31:04,237 INFO [train.py:715] (4/8) Epoch 12, batch 12300, loss[loss=0.1193, simple_loss=0.2028, pruned_loss=0.01789, over 4951.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03158, over 971577.52 frames.], batch size: 29, lr: 1.82e-04
2022-05-07 10:31:42,817 INFO [train.py:715] (4/8) Epoch 12, batch 12350, loss[loss=0.1256, simple_loss=0.2034, pruned_loss=0.02387, over 4940.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03128, over 971316.10 frames.], batch size: 21, lr: 1.82e-04
2022-05-07 10:32:20,260 INFO [train.py:715] (4/8) Epoch 12, batch 12400, loss[loss=0.1355, simple_loss=0.2073, pruned_loss=0.03183, over 4789.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03094, over 971099.69 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:32:57,988 INFO [train.py:715] (4/8) Epoch 12, batch 12450, loss[loss=0.1117, simple_loss=0.175, pruned_loss=0.02421, over 4642.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.03181, over 971401.30 frames.], batch size: 13, lr: 1.82e-04
2022-05-07 10:33:36,210 INFO [train.py:715] (4/8) Epoch 12, batch 12500, loss[loss=0.1607, simple_loss=0.2373, pruned_loss=0.04206, over 4982.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.03164, over 971336.38 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:34:13,317 INFO [train.py:715] (4/8) Epoch 12, batch 12550, loss[loss=0.125, simple_loss=0.2027, pruned_loss=0.02363, over 4941.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.0316, over 971597.18 frames.], batch size: 21, lr: 1.82e-04
2022-05-07 10:34:51,155 INFO [train.py:715] (4/8) Epoch 12, batch 12600, loss[loss=0.1352, simple_loss=0.2121, pruned_loss=0.02912, over 4817.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03154, over 971430.51 frames.], batch size: 27, lr: 1.82e-04
2022-05-07 10:35:28,920 INFO [train.py:715] (4/8) Epoch 12, batch 12650, loss[loss=0.1215, simple_loss=0.2016, pruned_loss=0.02071, over 4915.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03209, over 972013.57 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:36:06,673 INFO [train.py:715] (4/8) Epoch 12, batch 12700, loss[loss=0.136, simple_loss=0.2088, pruned_loss=0.03157, over 4973.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.0321, over 971127.76 frames.], batch size: 24, lr: 1.82e-04
2022-05-07 10:36:44,125 INFO [train.py:715] (4/8) Epoch 12, batch 12750, loss[loss=0.1206, simple_loss=0.1961, pruned_loss=0.02252, over 4820.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2111, pruned_loss=0.03227, over 970386.40 frames.], batch size: 26, lr: 1.82e-04
2022-05-07 10:37:22,153 INFO [train.py:715] (4/8) Epoch 12, batch 12800, loss[loss=0.1447, simple_loss=0.2051, pruned_loss=0.04221, over 4647.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.03222, over 970469.07 frames.], batch size: 13, lr: 1.82e-04
2022-05-07 10:38:00,581 INFO [train.py:715] (4/8) Epoch 12, batch 12850, loss[loss=0.1619, simple_loss=0.2211, pruned_loss=0.05133, over 4917.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03196, over 971119.34 frames.], batch size: 17, lr: 1.82e-04
2022-05-07 10:38:37,909 INFO [train.py:715] (4/8) Epoch 12, batch 12900, loss[loss=0.1281, simple_loss=0.2068, pruned_loss=0.02465, over 4830.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2102, pruned_loss=0.03196, over 970931.59 frames.], batch size: 27, lr: 1.82e-04
2022-05-07 10:39:15,002 INFO [train.py:715] (4/8) Epoch 12, batch 12950, loss[loss=0.1307, simple_loss=0.2146, pruned_loss=0.02336, over 4927.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.03197, over 971547.77 frames.], batch size: 18, lr: 1.82e-04
2022-05-07 10:39:52,998 INFO [train.py:715] (4/8) Epoch 12, batch 13000, loss[loss=0.1187, simple_loss=0.2038, pruned_loss=0.01679, over 4743.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03201, over 971600.45 frames.], batch size: 16, lr: 1.82e-04
2022-05-07 10:40:30,779 INFO [train.py:715] (4/8) Epoch 12, batch 13050, loss[loss=0.1229, simple_loss=0.1974, pruned_loss=0.02418, over 4745.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03235, over 971717.80 frames.], batch size: 16, lr: 1.82e-04
2022-05-07 10:41:08,531 INFO [train.py:715] (4/8) Epoch 12, batch 13100, loss[loss=0.164, simple_loss=0.2503, pruned_loss=0.0388, over 4706.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03222, over 972117.99 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:41:46,120 INFO [train.py:715] (4/8) Epoch 12, batch 13150, loss[loss=0.1229, simple_loss=0.2033, pruned_loss=0.02122, over 4892.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03226, over 972278.24 frames.], batch size: 19, lr: 1.82e-04
2022-05-07 10:42:23,789 INFO [train.py:715] (4/8) Epoch 12, batch 13200, loss[loss=0.1562, simple_loss=0.2247, pruned_loss=0.04386, over 4971.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.0324, over 972412.08 frames.], batch size: 39, lr: 1.82e-04
2022-05-07 10:43:01,012 INFO [train.py:715] (4/8) Epoch 12, batch 13250, loss[loss=0.1285, simple_loss=0.2002, pruned_loss=0.02846, over 4744.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03219, over 972613.97 frames.], batch size: 16, lr: 1.82e-04
2022-05-07 10:43:38,187 INFO [train.py:715] (4/8) Epoch 12, batch 13300, loss[loss=0.1429, simple_loss=0.204, pruned_loss=0.04093, over 4975.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03263, over 972097.02 frames.], batch size: 14, lr: 1.82e-04
2022-05-07 10:44:16,076 INFO [train.py:715] (4/8) Epoch 12, batch 13350, loss[loss=0.1233, simple_loss=0.1915, pruned_loss=0.02755, over 4828.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.0325, over 972734.89 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:44:54,316 INFO [train.py:715] (4/8) Epoch 12, batch 13400, loss[loss=0.1356, simple_loss=0.2069, pruned_loss=0.03218, over 4835.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2116, pruned_loss=0.03293, over 972415.77 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:45:31,691 INFO [train.py:715] (4/8) Epoch 12, batch 13450, loss[loss=0.1223, simple_loss=0.2002, pruned_loss=0.02217, over 4958.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2117, pruned_loss=0.03285, over 972588.35 frames.], batch size: 24, lr: 1.82e-04
2022-05-07 10:46:09,029 INFO [train.py:715] (4/8) Epoch 12, batch 13500, loss[loss=0.1261, simple_loss=0.2034, pruned_loss=0.02437, over 4860.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2114, pruned_loss=0.03268, over 972286.47 frames.], batch size: 22, lr: 1.82e-04
2022-05-07 10:46:47,473 INFO [train.py:715] (4/8) Epoch 12, batch 13550, loss[loss=0.1222, simple_loss=0.1992, pruned_loss=0.02257, over 4978.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2118, pruned_loss=0.03236, over 972117.36 frames.], batch size: 28, lr: 1.82e-04
2022-05-07 10:47:24,685 INFO [train.py:715] (4/8) Epoch 12, batch 13600, loss[loss=0.1073, simple_loss=0.1835, pruned_loss=0.01555, over 4973.00 frames.], tot_loss[loss=0.138, simple_loss=0.2117, pruned_loss=0.03212, over 971752.33 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:48:02,572 INFO [train.py:715] (4/8) Epoch 12, batch 13650, loss[loss=0.1358, simple_loss=0.1971, pruned_loss=0.0373, over 4769.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03199, over 971789.79 frames.], batch size: 12, lr: 1.82e-04
2022-05-07 10:48:40,709 INFO [train.py:715] (4/8) Epoch 12, batch 13700, loss[loss=0.1212, simple_loss=0.195, pruned_loss=0.02366, over 4831.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03203, over 971974.50 frames.], batch size: 13, lr: 1.82e-04
2022-05-07 10:49:18,439 INFO [train.py:715] (4/8) Epoch 12, batch 13750, loss[loss=0.1176, simple_loss=0.1921, pruned_loss=0.02156, over 4840.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03192, over 972179.85 frames.], batch size: 32, lr: 1.82e-04
2022-05-07 10:49:56,508 INFO [train.py:715] (4/8) Epoch 12, batch 13800, loss[loss=0.1257, simple_loss=0.1937, pruned_loss=0.02884, over 4989.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03186, over 972771.44 frames.], batch size: 28, lr: 1.82e-04
2022-05-07 10:50:34,448 INFO [train.py:715] (4/8) Epoch 12, batch 13850, loss[loss=0.1413, simple_loss=0.2063, pruned_loss=0.03817, over 4877.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2105, pruned_loss=0.03213, over 972163.74 frames.], batch size: 16, lr: 1.82e-04
2022-05-07 10:51:12,971 INFO [train.py:715] (4/8) Epoch 12, batch 13900, loss[loss=0.1295, simple_loss=0.1969, pruned_loss=0.03105, over 4931.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2105, pruned_loss=0.03258, over 972300.10 frames.], batch size: 17, lr: 1.82e-04
2022-05-07 10:51:50,184 INFO [train.py:715] (4/8) Epoch 12, batch 13950, loss[loss=0.1624, simple_loss=0.235, pruned_loss=0.04488, over 4872.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2105, pruned_loss=0.0324, over 972240.36 frames.], batch size: 16, lr: 1.82e-04
2022-05-07 10:52:28,376 INFO [train.py:715] (4/8) Epoch 12, batch 14000, loss[loss=0.1418, simple_loss=0.2245, pruned_loss=0.0295, over 4696.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2114, pruned_loss=0.03286, over 971777.86 frames.], batch size: 15, lr: 1.82e-04
2022-05-07 10:53:06,889 INFO [train.py:715] (4/8) Epoch 12, batch 14050, loss[loss=0.1453, simple_loss=0.2142, pruned_loss=0.0382, over 4962.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2114, pruned_loss=0.03264, over 971811.44 frames.], batch size: 35, lr: 1.82e-04
2022-05-07 10:53:44,259 INFO [train.py:715] (4/8) Epoch 12, batch 14100, loss[loss=0.1506, simple_loss=0.2205, pruned_loss=0.04033, over 4983.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2117, pruned_loss=0.0328, over 971311.19 frames.], batch size: 35, lr: 1.82e-04
2022-05-07 10:54:21,695 INFO [train.py:715] (4/8) Epoch 12, batch 14150, loss[loss=0.1353, simple_loss=0.205, pruned_loss=0.03279, over 4948.00 frames.], tot_loss[loss=0.1386, simple_loss=0.2118, pruned_loss=0.03268, over 971587.61 frames.], batch size: 23, lr: 1.82e-04
2022-05-07 10:55:00,103 INFO [train.py:715] (4/8) Epoch 12, batch 14200, loss[loss=0.1227, simple_loss=0.2063, pruned_loss=0.01957, over 4831.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.0319, over 971256.71 frames.], batch size: 13, lr: 1.82e-04
2022-05-07 10:55:38,424 INFO [train.py:715] (4/8) Epoch 12, batch 14250, loss[loss=0.1411, simple_loss=0.224, pruned_loss=0.0291, over 4701.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2116, pruned_loss=0.03168, over 971708.21 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 10:56:18,082 INFO [train.py:715] (4/8) Epoch 12, batch 14300, loss[loss=0.1435, simple_loss=0.2181, pruned_loss=0.03444, over 4962.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2108, pruned_loss=0.03126, over 972077.25 frames.], batch size: 35, lr: 1.81e-04
2022-05-07 10:56:56,581 INFO [train.py:715] (4/8) Epoch 12, batch 14350, loss[loss=0.1413, simple_loss=0.2188, pruned_loss=0.03189, over 4985.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03116, over 972355.43 frames.], batch size: 20, lr: 1.81e-04
2022-05-07 10:57:35,965 INFO [train.py:715] (4/8) Epoch 12, batch 14400, loss[loss=0.16, simple_loss=0.2362, pruned_loss=0.0419, over 4927.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03169, over 971903.84 frames.], batch size: 23, lr: 1.81e-04
2022-05-07 10:58:14,111 INFO [train.py:715] (4/8) Epoch 12, batch 14450, loss[loss=0.1502, simple_loss=0.2132, pruned_loss=0.04355, over 4853.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2108, pruned_loss=0.03244, over 971692.34 frames.], batch size: 32, lr: 1.81e-04
2022-05-07 10:58:53,033 INFO [train.py:715] (4/8) Epoch 12, batch 14500, loss[loss=0.1262, simple_loss=0.1908, pruned_loss=0.03081, over 4818.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2114, pruned_loss=0.03245, over 972108.30 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 10:59:32,144 INFO [train.py:715] (4/8) Epoch 12, batch 14550, loss[loss=0.1432, simple_loss=0.2186, pruned_loss=0.0339, over 4768.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03235, over 972064.13 frames.], batch size: 17, lr: 1.81e-04
2022-05-07 11:00:11,028 INFO [train.py:715] (4/8) Epoch 12, batch 14600, loss[loss=0.1132, simple_loss=0.1902, pruned_loss=0.01809, over 4933.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.03218, over 972265.08 frames.], batch size: 23, lr: 1.81e-04
2022-05-07 11:00:49,646 INFO [train.py:715] (4/8) Epoch 12, batch 14650, loss[loss=0.1143, simple_loss=0.1933, pruned_loss=0.01759, over 4799.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2099, pruned_loss=0.03174, over 972584.77 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:01:27,544 INFO [train.py:715] (4/8) Epoch 12, batch 14700, loss[loss=0.1294, simple_loss=0.2036, pruned_loss=0.02761, over 4983.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.03169, over 973325.23 frames.], batch size: 25, lr: 1.81e-04
2022-05-07 11:02:06,066 INFO [train.py:715] (4/8) Epoch 12, batch 14750, loss[loss=0.1202, simple_loss=0.1883, pruned_loss=0.02601, over 4907.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2101, pruned_loss=0.03233, over 973238.79 frames.], batch size: 17, lr: 1.81e-04
2022-05-07 11:02:43,581 INFO [train.py:715] (4/8) Epoch 12, batch 14800, loss[loss=0.1203, simple_loss=0.2035, pruned_loss=0.01855, over 4922.00 frames.], tot_loss[loss=0.1374, simple_loss=0.21, pruned_loss=0.03241, over 973558.07 frames.], batch size: 19, lr: 1.81e-04
2022-05-07 11:03:21,326 INFO [train.py:715] (4/8) Epoch 12, batch 14850, loss[loss=0.1265, simple_loss=0.2132, pruned_loss=0.01994, over 4973.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2106, pruned_loss=0.03252, over 973360.60 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:03:59,686 INFO [train.py:715] (4/8) Epoch 12, batch 14900, loss[loss=0.1392, simple_loss=0.2106, pruned_loss=0.03387, over 4979.00 frames.], tot_loss[loss=0.1372, simple_loss=0.21, pruned_loss=0.03218, over 973394.04 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:04:38,247 INFO [train.py:715] (4/8) Epoch 12, batch 14950, loss[loss=0.1583, simple_loss=0.222, pruned_loss=0.0473, over 4899.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.03228, over 973672.93 frames.], batch size: 22, lr: 1.81e-04
2022-05-07 11:05:15,439 INFO [train.py:715] (4/8) Epoch 12, batch 15000, loss[loss=0.1539, simple_loss=0.216, pruned_loss=0.04595, over 4911.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03239, over 973664.56 frames.], batch size: 23, lr: 1.81e-04
2022-05-07 11:05:15,439 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 11:05:25,069 INFO [train.py:742] (4/8) Epoch 12, validation: loss=0.1057, simple_loss=0.1897, pruned_loss=0.01083, over 914524.00 frames.
2022-05-07 11:06:02,918 INFO [train.py:715] (4/8) Epoch 12, batch 15050, loss[loss=0.1637, simple_loss=0.2361, pruned_loss=0.04561, over 4876.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03165, over 973817.89 frames.], batch size: 22, lr: 1.81e-04
2022-05-07 11:06:41,207 INFO [train.py:715] (4/8) Epoch 12, batch 15100, loss[loss=0.1448, simple_loss=0.213, pruned_loss=0.03828, over 4856.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2117, pruned_loss=0.03225, over 972691.89 frames.], batch size: 20, lr: 1.81e-04
2022-05-07 11:07:20,387 INFO [train.py:715] (4/8) Epoch 12, batch 15150, loss[loss=0.1224, simple_loss=0.1981, pruned_loss=0.02334, over 4897.00 frames.], tot_loss[loss=0.138, simple_loss=0.2117, pruned_loss=0.03213, over 972409.16 frames.], batch size: 22, lr: 1.81e-04
2022-05-07 11:07:58,861 INFO [train.py:715] (4/8) Epoch 12, batch 15200, loss[loss=0.1449, simple_loss=0.2217, pruned_loss=0.034, over 4892.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03209, over 972232.09 frames.], batch size: 17, lr: 1.81e-04
2022-05-07 11:08:37,648 INFO [train.py:715] (4/8) Epoch 12, batch 15250, loss[loss=0.1162, simple_loss=0.1853, pruned_loss=0.02353, over 4920.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03198, over 972006.35 frames.], batch size: 29, lr: 1.81e-04
2022-05-07 11:09:16,356 INFO [train.py:715] (4/8) Epoch 12, batch 15300, loss[loss=0.1869, simple_loss=0.2473, pruned_loss=0.06324, over 4757.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03191, over 971100.57 frames.], batch size: 16, lr: 1.81e-04
2022-05-07 11:09:54,567 INFO [train.py:715] (4/8) Epoch 12, batch 15350, loss[loss=0.08682, simple_loss=0.1528, pruned_loss=0.01043, over 4812.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.0319, over 970991.46 frames.], batch size: 12, lr: 1.81e-04
2022-05-07 11:10:31,952 INFO [train.py:715] (4/8) Epoch 12, batch 15400, loss[loss=0.1444, simple_loss=0.2214, pruned_loss=0.03371, over 4863.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.03205, over 970565.45 frames.], batch size: 20, lr: 1.81e-04
2022-05-07 11:11:09,689 INFO [train.py:715] (4/8) Epoch 12, batch 15450, loss[loss=0.1288, simple_loss=0.1984, pruned_loss=0.02959, over 4949.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2101, pruned_loss=0.03222, over 971486.20 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:11:48,439 INFO [train.py:715] (4/8) Epoch 12, batch 15500, loss[loss=0.1352, simple_loss=0.2176, pruned_loss=0.02641, over 4920.00 frames.], tot_loss[loss=0.137, simple_loss=0.2101, pruned_loss=0.03197, over 971569.57 frames.], batch size: 39, lr: 1.81e-04
2022-05-07 11:12:26,566 INFO [train.py:715] (4/8) Epoch 12, batch 15550, loss[loss=0.1642, simple_loss=0.2467, pruned_loss=0.04085, over 4898.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.03276, over 971957.82 frames.], batch size: 18, lr: 1.81e-04
2022-05-07 11:13:04,458 INFO [train.py:715] (4/8) Epoch 12, batch 15600, loss[loss=0.1428, simple_loss=0.2099, pruned_loss=0.03788, over 4905.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.03282, over 972410.00 frames.], batch size: 19, lr: 1.81e-04
2022-05-07 11:13:42,238 INFO [train.py:715] (4/8) Epoch 12, batch 15650, loss[loss=0.1397, simple_loss=0.2231, pruned_loss=0.02817, over 4946.00 frames.], tot_loss[loss=0.139, simple_loss=0.2122, pruned_loss=0.03292, over 973026.35 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:14:20,674 INFO [train.py:715] (4/8) Epoch 12, batch 15700, loss[loss=0.1407, simple_loss=0.2154, pruned_loss=0.03297, over 4830.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03268, over 973113.81 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:14:58,369 INFO [train.py:715] (4/8) Epoch 12, batch 15750, loss[loss=0.1241, simple_loss=0.1991, pruned_loss=0.02449, over 4745.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2115, pruned_loss=0.03301, over 973282.98 frames.], batch size: 16, lr: 1.81e-04
2022-05-07 11:15:36,106 INFO [train.py:715] (4/8) Epoch 12, batch 15800, loss[loss=0.124, simple_loss=0.1971, pruned_loss=0.02547, over 4818.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03247, over 972722.88 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:16:14,196 INFO [train.py:715] (4/8) Epoch 12, batch 15850, loss[loss=0.1147, simple_loss=0.1878, pruned_loss=0.02077, over 4795.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2107, pruned_loss=0.03247, over 971820.03 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:16:51,695 INFO [train.py:715] (4/8) Epoch 12, batch 15900, loss[loss=0.1464, simple_loss=0.2197, pruned_loss=0.03653, over 4819.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03216, over 972306.50 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:17:29,508 INFO [train.py:715] (4/8) Epoch 12, batch 15950, loss[loss=0.1303, simple_loss=0.1935, pruned_loss=0.03355, over 4864.00 frames.], tot_loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.0317, over 971849.11 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:18:07,570 INFO [train.py:715] (4/8) Epoch 12, batch 16000, loss[loss=0.1462, simple_loss=0.2264, pruned_loss=0.03296, over 4954.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2111, pruned_loss=0.03184, over 971323.17 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:18:47,327 INFO [train.py:715] (4/8) Epoch 12, batch 16050, loss[loss=0.1042, simple_loss=0.1814, pruned_loss=0.01346, over 4793.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.0313, over 970828.78 frames.], batch size: 12, lr: 1.81e-04
2022-05-07 11:19:25,278 INFO [train.py:715] (4/8) Epoch 12, batch 16100, loss[loss=0.1238, simple_loss=0.1999, pruned_loss=0.02386, over 4795.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2116, pruned_loss=0.03164, over 971447.20 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:20:04,189 INFO [train.py:715] (4/8) Epoch 12, batch 16150, loss[loss=0.1817, simple_loss=0.2469, pruned_loss=0.05824, over 4943.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2105, pruned_loss=0.03109, over 970961.71 frames.], batch size: 35, lr: 1.81e-04
2022-05-07 11:20:43,068 INFO [train.py:715] (4/8) Epoch 12, batch 16200, loss[loss=0.1402, simple_loss=0.2186, pruned_loss=0.03093, over 4952.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2104, pruned_loss=0.03122, over 970875.21 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:21:21,842 INFO [train.py:715] (4/8) Epoch 12, batch 16250, loss[loss=0.1441, simple_loss=0.2184, pruned_loss=0.03485, over 4838.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2113, pruned_loss=0.03147, over 970356.91 frames.], batch size: 30, lr: 1.81e-04
2022-05-07 11:21:59,696 INFO [train.py:715] (4/8) Epoch 12, batch 16300, loss[loss=0.142, simple_loss=0.2161, pruned_loss=0.03396, over 4868.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2118, pruned_loss=0.03186, over 971285.75 frames.], batch size: 22, lr: 1.81e-04
2022-05-07 11:22:37,474 INFO [train.py:715] (4/8) Epoch 12, batch 16350, loss[loss=0.1375, simple_loss=0.2188, pruned_loss=0.02813, over 4787.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2118, pruned_loss=0.03183, over 971194.79 frames.], batch size: 17, lr: 1.81e-04
2022-05-07 11:23:16,253 INFO [train.py:715] (4/8) Epoch 12, batch 16400, loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03185, over 4772.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2115, pruned_loss=0.0319, over 971578.15 frames.], batch size: 18, lr: 1.81e-04
2022-05-07 11:23:54,212 INFO [train.py:715] (4/8) Epoch 12, batch 16450, loss[loss=0.1231, simple_loss=0.2109, pruned_loss=0.01771, over 4753.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2115, pruned_loss=0.03195, over 971136.00 frames.], batch size: 16, lr: 1.81e-04
2022-05-07 11:24:33,098 INFO [train.py:715] (4/8) Epoch 12, batch 16500, loss[loss=0.127, simple_loss=0.207, pruned_loss=0.02346, over 4880.00 frames.], tot_loss[loss=0.1384, simple_loss=0.212, pruned_loss=0.03235, over 971938.43 frames.], batch size: 22, lr: 1.81e-04
2022-05-07 11:25:12,172 INFO [train.py:715] (4/8) Epoch 12, batch 16550, loss[loss=0.1303, simple_loss=0.1936, pruned_loss=0.03347, over 4800.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2116, pruned_loss=0.03248, over 971295.14 frames.], batch size: 13, lr: 1.81e-04
2022-05-07 11:25:51,308 INFO [train.py:715] (4/8) Epoch 12, batch 16600, loss[loss=0.1499, simple_loss=0.2245, pruned_loss=0.03767, over 4832.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03171, over 970360.73 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:26:29,846 INFO [train.py:715] (4/8) Epoch 12, batch 16650, loss[loss=0.1329, simple_loss=0.2084, pruned_loss=0.02873, over 4952.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03154, over 970803.38 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:27:08,907 INFO [train.py:715] (4/8) Epoch 12, batch 16700, loss[loss=0.1288, simple_loss=0.1903, pruned_loss=0.03368, over 4865.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03145, over 971845.46 frames.], batch size: 20, lr: 1.81e-04
2022-05-07 11:27:48,113 INFO [train.py:715] (4/8) Epoch 12, batch 16750, loss[loss=0.1253, simple_loss=0.2044, pruned_loss=0.02305, over 4941.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03155, over 972147.28 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:28:26,499 INFO [train.py:715] (4/8) Epoch 12, batch 16800, loss[loss=0.1196, simple_loss=0.2016, pruned_loss=0.01885, over 4882.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03104, over 973336.71 frames.], batch size: 20, lr: 1.81e-04
2022-05-07 11:29:05,272 INFO [train.py:715] (4/8) Epoch 12, batch 16850, loss[loss=0.1475, simple_loss=0.2168, pruned_loss=0.03913, over 4886.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03128, over 972771.12 frames.], batch size: 22, lr: 1.81e-04
2022-05-07 11:29:44,426 INFO [train.py:715] (4/8) Epoch 12, batch 16900, loss[loss=0.1403, simple_loss=0.2168, pruned_loss=0.03184, over 4969.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03145, over 972085.10 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:30:24,180 INFO [train.py:715] (4/8) Epoch 12, batch 16950, loss[loss=0.1325, simple_loss=0.1984, pruned_loss=0.03328, over 4967.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03162, over 972844.54 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:31:02,692 INFO [train.py:715] (4/8) Epoch 12, batch 17000, loss[loss=0.124, simple_loss=0.1929, pruned_loss=0.02761, over 4975.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03154, over 973364.87 frames.], batch size: 28, lr: 1.81e-04
2022-05-07 11:31:40,882 INFO [train.py:715] (4/8) Epoch 12, batch 17050, loss[loss=0.1421, simple_loss=0.2103, pruned_loss=0.03696, over 4877.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2106, pruned_loss=0.03226, over 974342.86 frames.], batch size: 20, lr: 1.81e-04
2022-05-07 11:32:19,767 INFO [train.py:715] (4/8) Epoch 12, batch 17100, loss[loss=0.1462, simple_loss=0.2227, pruned_loss=0.03491, over 4885.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03245, over 973734.13 frames.], batch size: 16, lr: 1.81e-04
2022-05-07 11:32:58,567 INFO [train.py:715] (4/8) Epoch 12, batch 17150, loss[loss=0.1376, simple_loss=0.2144, pruned_loss=0.03036, over 4799.00 frames.], tot_loss[loss=0.1391, simple_loss=0.2122, pruned_loss=0.03301, over 974935.18 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:33:37,596 INFO [train.py:715] (4/8) Epoch 12, batch 17200, loss[loss=0.1306, simple_loss=0.2101, pruned_loss=0.02555, over 4750.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03223, over 974041.67 frames.], batch size: 16, lr: 1.81e-04
2022-05-07 11:34:16,028 INFO [train.py:715] (4/8) Epoch 12, batch 17250, loss[loss=0.1208, simple_loss=0.1964, pruned_loss=0.02259, over 4763.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03204, over 974306.07 frames.], batch size: 16, lr: 1.81e-04
2022-05-07 11:34:54,494 INFO [train.py:715] (4/8) Epoch 12, batch 17300, loss[loss=0.1209, simple_loss=0.1968, pruned_loss=0.02245, over 4796.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.03216, over 974026.15 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:35:32,126 INFO [train.py:715] (4/8) Epoch 12, batch 17350, loss[loss=0.1176, simple_loss=0.193, pruned_loss=0.0211, over 4964.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03208, over 972996.12 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:36:10,077 INFO [train.py:715] (4/8) Epoch 12, batch 17400, loss[loss=0.1454, simple_loss=0.2204, pruned_loss=0.03519, over 4812.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03203, over 972113.61 frames.], batch size: 25, lr: 1.81e-04
2022-05-07 11:36:47,846 INFO [train.py:715] (4/8) Epoch 12, batch 17450, loss[loss=0.1706, simple_loss=0.2581, pruned_loss=0.04159, over 4897.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2116, pruned_loss=0.03205, over 971477.22 frames.], batch size: 16, lr: 1.81e-04
2022-05-07 11:37:26,178 INFO [train.py:715] (4/8) Epoch 12, batch 17500, loss[loss=0.1499, simple_loss=0.2311, pruned_loss=0.03436, over 4971.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2118, pruned_loss=0.03177, over 971498.22 frames.], batch size: 35, lr: 1.81e-04
2022-05-07 11:38:04,041 INFO [train.py:715] (4/8) Epoch 12, batch 17550, loss[loss=0.1385, simple_loss=0.2161, pruned_loss=0.03049, over 4855.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2112, pruned_loss=0.03156, over 971268.69 frames.], batch size: 20, lr: 1.81e-04
2022-05-07 11:38:42,238 INFO [train.py:715] (4/8) Epoch 12, batch 17600, loss[loss=0.1686, simple_loss=0.2289, pruned_loss=0.05416, over 4912.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03155, over 972433.42 frames.], batch size: 17, lr: 1.81e-04
2022-05-07 11:39:19,888 INFO [train.py:715] (4/8) Epoch 12, batch 17650, loss[loss=0.1695, simple_loss=0.2348, pruned_loss=0.05208, over 4816.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03181, over 972075.66 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:39:57,992 INFO [train.py:715] (4/8) Epoch 12, batch 17700, loss[loss=0.1523, simple_loss=0.224, pruned_loss=0.0403, over 4873.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2105, pruned_loss=0.03213, over 972105.83 frames.], batch size: 16, lr: 1.81e-04
2022-05-07 11:40:36,848 INFO [train.py:715] (4/8) Epoch 12, batch 17750, loss[loss=0.1215, simple_loss=0.1941, pruned_loss=0.02449, over 4706.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03164, over 972743.15 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:41:15,689 INFO [train.py:715] (4/8) Epoch 12, batch 17800, loss[loss=0.146, simple_loss=0.2081, pruned_loss=0.042, over 4951.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2106, pruned_loss=0.03219, over 972633.16 frames.], batch size: 35, lr: 1.81e-04
2022-05-07 11:41:54,189 INFO [train.py:715] (4/8) Epoch 12, batch 17850, loss[loss=0.1171, simple_loss=0.199, pruned_loss=0.01765, over 4768.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.03221, over 972192.70 frames.], batch size: 18, lr: 1.81e-04
2022-05-07 11:42:32,957 INFO [train.py:715] (4/8) Epoch 12, batch 17900, loss[loss=0.1907, simple_loss=0.2781, pruned_loss=0.05166, over 4948.00 frames.], tot_loss[loss=0.1369, simple_loss=0.21, pruned_loss=0.03188, over 972435.49 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:43:10,438 INFO [train.py:715] (4/8) Epoch 12, batch 17950, loss[loss=0.1363, simple_loss=0.2162, pruned_loss=0.02821, over 4937.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03217, over 972880.49 frames.], batch size: 21, lr: 1.81e-04
2022-05-07 11:43:48,629 INFO [train.py:715] (4/8) Epoch 12, batch 18000, loss[loss=0.1259, simple_loss=0.2006, pruned_loss=0.02563, over 4777.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03211, over 972147.63 frames.], batch size: 18, lr: 1.81e-04
2022-05-07 11:43:48,630 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 11:43:58,180 INFO [train.py:742] (4/8) Epoch 12, validation: loss=0.106, simple_loss=0.19, pruned_loss=0.011, over 914524.00 frames.
2022-05-07 11:44:36,606 INFO [train.py:715] (4/8) Epoch 12, batch 18050, loss[loss=0.1428, simple_loss=0.2041, pruned_loss=0.04072, over 4880.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2105, pruned_loss=0.03229, over 972022.22 frames.], batch size: 16, lr: 1.81e-04
2022-05-07 11:45:14,476 INFO [train.py:715] (4/8) Epoch 12, batch 18100, loss[loss=0.1256, simple_loss=0.2071, pruned_loss=0.02202, over 4979.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2103, pruned_loss=0.03222, over 971511.36 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:45:52,626 INFO [train.py:715] (4/8) Epoch 12, batch 18150, loss[loss=0.1122, simple_loss=0.1935, pruned_loss=0.01543, over 4949.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2096, pruned_loss=0.03195, over 971892.32 frames.], batch size: 29, lr: 1.81e-04
2022-05-07 11:46:30,451 INFO [train.py:715] (4/8) Epoch 12, batch 18200, loss[loss=0.1361, simple_loss=0.2137, pruned_loss=0.02928, over 4892.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2098, pruned_loss=0.03204, over 971770.63 frames.], batch size: 19, lr: 1.81e-04
2022-05-07 11:47:08,252 INFO [train.py:715] (4/8) Epoch 12, batch 18250, loss[loss=0.139, simple_loss=0.2138, pruned_loss=0.03208, over 4910.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03185, over 972069.62 frames.], batch size: 39, lr: 1.81e-04
2022-05-07 11:47:46,407 INFO [train.py:715] (4/8) Epoch 12, batch 18300, loss[loss=0.1144, simple_loss=0.1911, pruned_loss=0.01884, over 4755.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03167, over 972721.87 frames.], batch size: 19, lr: 1.81e-04
2022-05-07 11:48:24,293 INFO [train.py:715] (4/8) Epoch 12, batch 18350, loss[loss=0.1222, simple_loss=0.1877, pruned_loss=0.02841, over 4751.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.0317, over 972517.47 frames.], batch size: 12, lr: 1.81e-04
2022-05-07 11:49:02,250 INFO [train.py:715] (4/8) Epoch 12, batch 18400, loss[loss=0.1257, simple_loss=0.2003, pruned_loss=0.02553, over 4918.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.0314, over 972277.23 frames.], batch size: 29, lr: 1.81e-04
2022-05-07 11:49:39,750 INFO [train.py:715] (4/8) Epoch 12, batch 18450, loss[loss=0.1308, simple_loss=0.206, pruned_loss=0.02779, over 4771.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.0315, over 971412.52 frames.], batch size: 19, lr: 1.81e-04
2022-05-07 11:50:17,838 INFO [train.py:715] (4/8) Epoch 12, batch 18500, loss[loss=0.1403, simple_loss=0.2111, pruned_loss=0.0347, over 4821.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03114, over 971647.65 frames.], batch size: 26, lr: 1.81e-04
2022-05-07 11:50:55,666 INFO [train.py:715] (4/8) Epoch 12, batch 18550, loss[loss=0.1394, simple_loss=0.2251, pruned_loss=0.02689, over 4868.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.0312, over 971088.55 frames.], batch size: 20, lr: 1.81e-04
2022-05-07 11:51:33,501 INFO [train.py:715] (4/8) Epoch 12, batch 18600, loss[loss=0.1511, simple_loss=0.2134, pruned_loss=0.04442, over 4837.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03142, over 971418.87 frames.], batch size: 13, lr: 1.81e-04
2022-05-07 11:52:11,113 INFO [train.py:715] (4/8) Epoch 12, batch 18650, loss[loss=0.137, simple_loss=0.2107, pruned_loss=0.03164, over 4922.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03142, over 971752.73 frames.], batch size: 23, lr: 1.81e-04
2022-05-07 11:52:48,674 INFO [train.py:715] (4/8) Epoch 12, batch 18700, loss[loss=0.1368, simple_loss=0.2165, pruned_loss=0.02856, over 4877.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03121, over 971020.49 frames.], batch size: 22, lr: 1.81e-04
2022-05-07 11:53:26,074 INFO [train.py:715] (4/8) Epoch 12, batch 18750, loss[loss=0.1609, simple_loss=0.2413, pruned_loss=0.04024, over 4972.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2106, pruned_loss=0.03135, over 972515.29 frames.], batch size: 24, lr: 1.81e-04
2022-05-07 11:54:04,015 INFO [train.py:715] (4/8) Epoch 12, batch 18800, loss[loss=0.1293, simple_loss=0.2025, pruned_loss=0.02804, over 4705.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03121, over 973076.15 frames.], batch size: 15, lr: 1.81e-04
2022-05-07 11:54:41,890 INFO [train.py:715] (4/8) Epoch 12, batch 18850, loss[loss=0.12, simple_loss=0.2023, pruned_loss=0.0189, over 4983.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.0307, over 973001.90 frames.], batch size: 28, lr: 1.81e-04
2022-05-07 11:55:19,707 INFO [train.py:715] (4/8) Epoch 12, batch 18900, loss[loss=0.1617, simple_loss=0.2289, pruned_loss=0.04724, over 4985.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03109, over 973276.24 frames.], batch size: 35, lr: 1.81e-04
2022-05-07 11:55:57,998 INFO [train.py:715] (4/8) Epoch 12, batch 18950, loss[loss=0.1243, simple_loss=0.2079, pruned_loss=0.02037, over 4981.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.03082, over 973109.63 frames.], batch size: 35, lr: 1.81e-04
2022-05-07 11:56:35,808 INFO [train.py:715] (4/8) Epoch 12, batch 19000, loss[loss=0.1257, simple_loss=0.1964, pruned_loss=0.02749, over 4849.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2091, pruned_loss=0.03117, over 973102.11 frames.], batch size: 20, lr: 1.81e-04
2022-05-07 11:57:13,290 INFO [train.py:715] (4/8) Epoch 12, batch 19050, loss[loss=0.1312, simple_loss=0.2068, pruned_loss=0.0278, over 4846.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03108, over 972830.66 frames.], batch size: 13, lr: 1.80e-04
2022-05-07 11:57:50,569 INFO [train.py:715] (4/8) Epoch 12, batch 19100, loss[loss=0.111, simple_loss=0.1859, pruned_loss=0.01806, over 4769.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2088, pruned_loss=0.03102, over 971849.04 frames.], batch size: 14, lr: 1.80e-04
2022-05-07 11:58:28,558 INFO [train.py:715] (4/8) Epoch 12, batch 19150, loss[loss=0.1201, simple_loss=0.1938, pruned_loss=0.02323, over 4927.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03097, over 972019.83 frames.], batch size: 23, lr: 1.80e-04
2022-05-07 11:59:07,194 INFO [train.py:715] (4/8) Epoch 12, batch 19200, loss[loss=0.1145, simple_loss=0.1923, pruned_loss=0.01829, over 4912.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03115, over 971851.11 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 11:59:45,241 INFO [train.py:715] (4/8) Epoch 12, batch 19250, loss[loss=0.1412, simple_loss=0.2143, pruned_loss=0.03402, over 4783.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.0312, over 971754.59 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:00:23,722 INFO [train.py:715] (4/8) Epoch 12, batch 19300, loss[loss=0.1265, simple_loss=0.1954, pruned_loss=0.02884, over 4825.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03172, over 971722.24 frames.], batch size: 13, lr: 1.80e-04
2022-05-07 12:01:01,907 INFO [train.py:715] (4/8) Epoch 12, batch 19350, loss[loss=0.1746, simple_loss=0.2503, pruned_loss=0.04944, over 4784.00 frames.], tot_loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.03177, over 971524.53 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:01:39,912 INFO [train.py:715] (4/8) Epoch 12, batch 19400, loss[loss=0.1181, simple_loss=0.1935, pruned_loss=0.02137, over 4937.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03181, over 971189.16 frames.], batch size: 23, lr: 1.80e-04
2022-05-07 12:02:17,952 INFO [train.py:715] (4/8) Epoch 12, batch 19450, loss[loss=0.1318, simple_loss=0.2012, pruned_loss=0.03127, over 4885.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03138, over 971540.95 frames.], batch size: 12, lr: 1.80e-04
2022-05-07 12:02:56,772 INFO [train.py:715] (4/8) Epoch 12, batch 19500, loss[loss=0.1415, simple_loss=0.221, pruned_loss=0.03103, over 4789.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03132, over 971568.93 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:03:35,597 INFO [train.py:715] (4/8) Epoch 12, batch 19550, loss[loss=0.1256, simple_loss=0.1947, pruned_loss=0.0282, over 4643.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03122, over 971682.37 frames.], batch size: 13, lr: 1.80e-04
2022-05-07 12:04:14,319 INFO [train.py:715] (4/8) Epoch 12, batch 19600, loss[loss=0.149, simple_loss=0.2224, pruned_loss=0.03775, over 4923.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03149, over 971164.62 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:04:53,461 INFO [train.py:715] (4/8) Epoch 12, batch 19650, loss[loss=0.1247, simple_loss=0.2094, pruned_loss=0.01994, over 4901.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03134, over 971537.56 frames.], batch size: 29, lr: 1.80e-04
2022-05-07 12:05:32,628 INFO [train.py:715] (4/8) Epoch 12, batch 19700, loss[loss=0.1399, simple_loss=0.2153, pruned_loss=0.03224, over 4751.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03177, over 972215.80 frames.], batch size: 16, lr: 1.80e-04
2022-05-07 12:06:12,004 INFO [train.py:715] (4/8) Epoch 12, batch 19750, loss[loss=0.1186, simple_loss=0.1848, pruned_loss=0.02615, over 4839.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03178, over 971782.42 frames.], batch size: 20, lr: 1.80e-04
2022-05-07 12:06:52,651 INFO [train.py:715] (4/8) Epoch 12, batch 19800, loss[loss=0.134, simple_loss=0.2175, pruned_loss=0.02521, over 4638.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2114, pruned_loss=0.03205, over 971338.16 frames.], batch size: 13, lr: 1.80e-04
2022-05-07 12:07:33,087 INFO [train.py:715] (4/8) Epoch 12, batch 19850, loss[loss=0.1441, simple_loss=0.2177, pruned_loss=0.03521, over 4884.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03191, over 970867.37 frames.], batch size: 22, lr: 1.80e-04
2022-05-07 12:08:14,255 INFO [train.py:715] (4/8) Epoch 12, batch 19900, loss[loss=0.1485, simple_loss=0.2243, pruned_loss=0.03637, over 4910.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03185, over 971451.57 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:08:54,593 INFO [train.py:715] (4/8) Epoch 12, batch 19950, loss[loss=0.133, simple_loss=0.21, pruned_loss=0.028, over 4973.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2109, pruned_loss=0.0317, over 971172.76 frames.], batch size: 14, lr: 1.80e-04
2022-05-07 12:09:35,208 INFO [train.py:715] (4/8) Epoch 12, batch 20000, loss[loss=0.1188, simple_loss=0.1986, pruned_loss=0.01949, over 4889.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.0314, over 971395.33 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:10:15,442 INFO [train.py:715] (4/8) Epoch 12, batch 20050, loss[loss=0.1034, simple_loss=0.1685, pruned_loss=0.01918, over 4792.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.0311, over 971554.63 frames.], batch size: 12, lr: 1.80e-04
2022-05-07 12:10:55,691 INFO [train.py:715] (4/8) Epoch 12, batch 20100, loss[loss=0.1274, simple_loss=0.2043, pruned_loss=0.02522, over 4768.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03098, over 971998.51 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:11:35,664 INFO [train.py:715] (4/8) Epoch 12, batch 20150, loss[loss=0.1293, simple_loss=0.1979, pruned_loss=0.03036, over 4759.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.03127, over 972011.51 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:12:16,047 INFO [train.py:715] (4/8) Epoch 12, batch 20200, loss[loss=0.1291, simple_loss=0.2119, pruned_loss=0.02314, over 4825.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03167, over 972181.00 frames.], batch size: 26, lr: 1.80e-04
2022-05-07 12:12:56,157 INFO [train.py:715] (4/8) Epoch 12, batch 20250, loss[loss=0.1266, simple_loss=0.2069, pruned_loss=0.02319, over 4898.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.03177, over 971775.10 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:13:36,212 INFO [train.py:715] (4/8) Epoch 12, batch 20300, loss[loss=0.1501, simple_loss=0.2328, pruned_loss=0.03367, over 4902.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.03199, over 971540.04 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:14:16,801 INFO [train.py:715] (4/8) Epoch 12, batch 20350, loss[loss=0.1494, simple_loss=0.2124, pruned_loss=0.04316, over 4861.00 frames.], tot_loss[loss=0.138, simple_loss=0.2109, pruned_loss=0.03252, over 971738.75 frames.], batch size: 20, lr: 1.80e-04
2022-05-07 12:14:56,475 INFO [train.py:715] (4/8) Epoch 12, batch 20400, loss[loss=0.1354, simple_loss=0.2028, pruned_loss=0.03404, over 4763.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03208, over 972731.01 frames.], batch size: 14, lr: 1.80e-04
2022-05-07 12:15:36,234 INFO [train.py:715] (4/8) Epoch 12, batch 20450, loss[loss=0.1234, simple_loss=0.1978, pruned_loss=0.02446, over 4846.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2108, pruned_loss=0.03232, over 972761.87 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:16:15,881 INFO [train.py:715] (4/8) Epoch 12, batch 20500, loss[loss=0.1214, simple_loss=0.1966, pruned_loss=0.02312, over 4952.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03202, over 972333.97 frames.], batch size: 23, lr: 1.80e-04
2022-05-07 12:16:56,324 INFO [train.py:715] (4/8) Epoch 12, batch 20550, loss[loss=0.09198, simple_loss=0.1621, pruned_loss=0.01093, over 4751.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03146, over 971757.14 frames.], batch size: 12, lr: 1.80e-04
2022-05-07 12:17:36,249 INFO [train.py:715] (4/8) Epoch 12, batch 20600, loss[loss=0.1501, simple_loss=0.2181, pruned_loss=0.04106, over 4915.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03154, over 972341.19 frames.], batch size: 39, lr: 1.80e-04
2022-05-07 12:18:15,186 INFO [train.py:715] (4/8) Epoch 12, batch 20650, loss[loss=0.1115, simple_loss=0.1916, pruned_loss=0.01575, over 4969.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03173, over 972632.11 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:18:54,297 INFO [train.py:715] (4/8) Epoch 12, batch 20700, loss[loss=0.1539, simple_loss=0.2297, pruned_loss=0.03906, over 4782.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2103, pruned_loss=0.03126, over 972221.70 frames.], batch size: 14, lr: 1.80e-04
2022-05-07 12:19:32,273 INFO [train.py:715] (4/8) Epoch 12, batch 20750, loss[loss=0.1345, simple_loss=0.2192, pruned_loss=0.0249, over 4801.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2103, pruned_loss=0.03124, over 971911.28 frames.], batch size: 21, lr: 1.80e-04
2022-05-07 12:20:10,579 INFO [train.py:715] (4/8) Epoch 12, batch 20800, loss[loss=0.1066, simple_loss=0.1648, pruned_loss=0.02423, over 4734.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03108, over 972103.31 frames.], batch size: 12, lr: 1.80e-04
2022-05-07 12:20:48,329 INFO [train.py:715] (4/8) Epoch 12, batch 20850, loss[loss=0.142, simple_loss=0.2207, pruned_loss=0.03169, over 4980.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03072, over 972366.27 frames.], batch size: 40, lr: 1.80e-04
2022-05-07 12:21:26,468 INFO [train.py:715] (4/8) Epoch 12, batch 20900, loss[loss=0.1479, simple_loss=0.2255, pruned_loss=0.03519, over 4850.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03088, over 973429.72 frames.], batch size: 16, lr: 1.80e-04
2022-05-07 12:22:04,011 INFO [train.py:715] (4/8) Epoch 12, batch 20950, loss[loss=0.159, simple_loss=0.2326, pruned_loss=0.04273, over 4958.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03069, over 972922.05 frames.], batch size: 39, lr: 1.80e-04
2022-05-07 12:22:41,375 INFO [train.py:715] (4/8) Epoch 12, batch 21000, loss[loss=0.1249, simple_loss=0.1983, pruned_loss=0.02574, over 4904.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03073, over 972669.20 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:22:41,375 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 12:22:50,899 INFO [train.py:742] (4/8) Epoch 12, validation: loss=0.1056, simple_loss=0.1896, pruned_loss=0.01081, over 914524.00 frames.
2022-05-07 12:23:28,721 INFO [train.py:715] (4/8) Epoch 12, batch 21050, loss[loss=0.1364, simple_loss=0.211, pruned_loss=0.03085, over 4775.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03175, over 972086.83 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:24:06,828 INFO [train.py:715] (4/8) Epoch 12, batch 21100, loss[loss=0.1245, simple_loss=0.1927, pruned_loss=0.02819, over 4908.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03182, over 972532.17 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:24:44,629 INFO [train.py:715] (4/8) Epoch 12, batch 21150, loss[loss=0.1341, simple_loss=0.2069, pruned_loss=0.03063, over 4868.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03165, over 972666.87 frames.], batch size: 20, lr: 1.80e-04
2022-05-07 12:25:22,420 INFO [train.py:715] (4/8) Epoch 12, batch 21200, loss[loss=0.1497, simple_loss=0.2211, pruned_loss=0.03921, over 4847.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2107, pruned_loss=0.03183, over 972520.50 frames.], batch size: 20, lr: 1.80e-04
2022-05-07 12:26:00,702 INFO [train.py:715] (4/8) Epoch 12, batch 21250, loss[loss=0.1183, simple_loss=0.1954, pruned_loss=0.0206, over 4987.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03227, over 972602.89 frames.], batch size: 25, lr: 1.80e-04
2022-05-07 12:26:39,505 INFO [train.py:715] (4/8) Epoch 12, batch 21300, loss[loss=0.1293, simple_loss=0.2082, pruned_loss=0.02519, over 4961.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.0321, over 972262.66 frames.], batch size: 24, lr: 1.80e-04
2022-05-07 12:27:17,266 INFO [train.py:715] (4/8) Epoch 12, batch 21350, loss[loss=0.1197, simple_loss=0.1991, pruned_loss=0.02018, over 4852.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.03171, over 972436.23 frames.], batch size: 20, lr: 1.80e-04
2022-05-07 12:27:56,360 INFO [train.py:715] (4/8) Epoch 12, batch 21400, loss[loss=0.1247, simple_loss=0.2002, pruned_loss=0.02464, over 4956.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03172, over 972042.34 frames.], batch size: 24, lr: 1.80e-04
2022-05-07 12:28:35,914 INFO [train.py:715] (4/8) Epoch 12, batch 21450, loss[loss=0.1365, simple_loss=0.209, pruned_loss=0.03203, over 4761.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2107, pruned_loss=0.03194, over 972421.58 frames.], batch size: 12, lr: 1.80e-04
2022-05-07 12:29:14,513 INFO [train.py:715] (4/8) Epoch 12, batch 21500, loss[loss=0.1484, simple_loss=0.2168, pruned_loss=0.04001, over 4820.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03188, over 971992.55 frames.], batch size: 27, lr: 1.80e-04
2022-05-07 12:29:53,099 INFO [train.py:715] (4/8) Epoch 12, batch 21550, loss[loss=0.1701, simple_loss=0.2492, pruned_loss=0.0455, over 4821.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2105, pruned_loss=0.0319, over 972544.50 frames.], batch size: 21, lr: 1.80e-04
2022-05-07 12:30:31,273 INFO [train.py:715] (4/8) Epoch 12, batch 21600, loss[loss=0.1514, simple_loss=0.2257, pruned_loss=0.03856, over 4977.00 frames.], tot_loss[loss=0.137, simple_loss=0.21, pruned_loss=0.032, over 972839.98 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:31:09,733 INFO [train.py:715] (4/8) Epoch 12, batch 21650, loss[loss=0.1264, simple_loss=0.2031, pruned_loss=0.02483, over 4833.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.032, over 972784.61 frames.], batch size: 26, lr: 1.80e-04
2022-05-07 12:31:46,934 INFO [train.py:715] (4/8) Epoch 12, batch 21700, loss[loss=0.1271, simple_loss=0.1996, pruned_loss=0.02725, over 4937.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03189, over 972952.29 frames.], batch size: 29, lr: 1.80e-04
2022-05-07 12:32:25,496 INFO [train.py:715] (4/8) Epoch 12, batch 21750, loss[loss=0.1418, simple_loss=0.2161, pruned_loss=0.03378, over 4906.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03196, over 972119.52 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:33:04,219 INFO [train.py:715] (4/8) Epoch 12, batch 21800, loss[loss=0.149, simple_loss=0.2094, pruned_loss=0.04434, over 4844.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2107, pruned_loss=0.03157, over 973016.09 frames.], batch size: 13, lr: 1.80e-04
2022-05-07 12:33:42,112 INFO [train.py:715] (4/8) Epoch 12, batch 21850, loss[loss=0.1446, simple_loss=0.214, pruned_loss=0.03758, over 4773.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2107, pruned_loss=0.03138, over 972787.00 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:34:19,727 INFO [train.py:715] (4/8) Epoch 12, batch 21900, loss[loss=0.1435, simple_loss=0.2092, pruned_loss=0.03885, over 4913.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03142, over 972492.56 frames.], batch size: 18, lr: 1.80e-04
2022-05-07 12:34:58,476 INFO [train.py:715] (4/8) Epoch 12, batch 21950, loss[loss=0.1716, simple_loss=0.2496, pruned_loss=0.04676, over 4694.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03148, over 972509.78 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:35:37,480 INFO [train.py:715] (4/8) Epoch 12, batch 22000, loss[loss=0.1428, simple_loss=0.2218, pruned_loss=0.03191, over 4885.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03159, over 972269.53 frames.], batch size: 19, lr: 1.80e-04
2022-05-07 12:36:15,712 INFO [train.py:715] (4/8) Epoch 12, batch 22050, loss[loss=0.1311, simple_loss=0.2043, pruned_loss=0.02899, over 4806.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03114, over 971964.00 frames.], batch size: 21, lr: 1.80e-04
2022-05-07 12:36:54,701 INFO [train.py:715] (4/8) Epoch 12, batch 22100, loss[loss=0.1182, simple_loss=0.1946, pruned_loss=0.02091, over 4938.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.0315, over 971597.18 frames.], batch size: 23, lr: 1.80e-04
2022-05-07 12:37:33,659 INFO [train.py:715] (4/8) Epoch 12, batch 22150, loss[loss=0.1522, simple_loss=0.2214, pruned_loss=0.04152, over 4824.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03145, over 972092.08 frames.], batch size: 26, lr: 1.80e-04
2022-05-07 12:38:11,934 INFO [train.py:715] (4/8) Epoch 12, batch 22200, loss[loss=0.169, simple_loss=0.2454, pruned_loss=0.04634, over 4876.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03122, over 972095.89 frames.], batch size: 16, lr: 1.80e-04
2022-05-07 12:38:49,700 INFO [train.py:715] (4/8) Epoch 12, batch 22250, loss[loss=0.1865, simple_loss=0.2561, pruned_loss=0.05843, over 4689.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03141, over 971969.35 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:39:30,400 INFO [train.py:715] (4/8) Epoch 12, batch 22300, loss[loss=0.137, simple_loss=0.219, pruned_loss=0.0275, over 4945.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03151, over 972189.49 frames.], batch size: 29, lr: 1.80e-04
2022-05-07 12:40:08,652 INFO [train.py:715] (4/8) Epoch 12, batch 22350, loss[loss=0.1249, simple_loss=0.194, pruned_loss=0.02786, over 4987.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03177, over 972328.53 frames.], batch size: 16, lr: 1.80e-04
2022-05-07 12:40:46,765 INFO [train.py:715] (4/8) Epoch 12, batch 22400, loss[loss=0.1307, simple_loss=0.2068, pruned_loss=0.02732, over 4931.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03158, over 971727.20 frames.], batch size: 21, lr: 1.80e-04
2022-05-07 12:41:25,343 INFO [train.py:715] (4/8) Epoch 12, batch 22450, loss[loss=0.1437, simple_loss=0.232, pruned_loss=0.02772, over 4800.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03175, over 972363.85 frames.], batch size: 12, lr: 1.80e-04
2022-05-07 12:42:03,783 INFO [train.py:715] (4/8) Epoch 12, batch 22500, loss[loss=0.1363, simple_loss=0.2145, pruned_loss=0.02908, over 4820.00 frames.], tot_loss[loss=0.137, simple_loss=0.2102, pruned_loss=0.03188, over 972756.46 frames.], batch size: 25, lr: 1.80e-04
2022-05-07 12:42:42,488 INFO [train.py:715] (4/8) Epoch 12, batch 22550, loss[loss=0.1236, simple_loss=0.1936, pruned_loss=0.02681, over 4827.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.03167, over 972522.90 frames.], batch size: 13, lr: 1.80e-04
2022-05-07 12:43:20,634 INFO [train.py:715] (4/8) Epoch 12, batch 22600, loss[loss=0.1428, simple_loss=0.2061, pruned_loss=0.03978, over 4859.00 frames.], tot_loss[loss=0.1367, simple_loss=0.21, pruned_loss=0.03164, over 971743.39 frames.], batch size: 32, lr: 1.80e-04
2022-05-07 12:43:58,689 INFO [train.py:715] (4/8) Epoch 12, batch 22650, loss[loss=0.1719, simple_loss=0.2439, pruned_loss=0.04991, over 4893.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03177, over 972237.21 frames.], batch size: 39, lr: 1.80e-04
2022-05-07 12:44:36,597 INFO [train.py:715] (4/8) Epoch 12, batch 22700, loss[loss=0.1425, simple_loss=0.2124, pruned_loss=0.03635, over 4787.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.03221, over 972716.47 frames.], batch size: 14, lr: 1.80e-04
2022-05-07 12:45:14,815 INFO [train.py:715] (4/8) Epoch 12, batch 22750, loss[loss=0.1335, simple_loss=0.2048, pruned_loss=0.03111, over 4792.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03235, over 972876.75 frames.], batch size: 14, lr: 1.80e-04
2022-05-07 12:45:53,321 INFO [train.py:715] (4/8) Epoch 12, batch 22800, loss[loss=0.1527, simple_loss=0.2243, pruned_loss=0.04053, over 4927.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03168, over 972678.81 frames.], batch size: 23, lr: 1.80e-04
2022-05-07 12:46:32,314 INFO [train.py:715] (4/8) Epoch 12, batch 22850, loss[loss=0.1213, simple_loss=0.1957, pruned_loss=0.02343, over 4961.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2114, pruned_loss=0.03165, over 972553.49 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:47:10,523 INFO [train.py:715] (4/8) Epoch 12, batch 22900, loss[loss=0.1077, simple_loss=0.1783, pruned_loss=0.01855, over 4809.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2115, pruned_loss=0.03202, over 972250.10 frames.], batch size: 13, lr: 1.80e-04
2022-05-07 12:47:48,404 INFO [train.py:715] (4/8) Epoch 12, batch 22950, loss[loss=0.1553, simple_loss=0.2384, pruned_loss=0.03611, over 4927.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2116, pruned_loss=0.03193, over 972075.23 frames.], batch size: 23, lr: 1.80e-04
2022-05-07 12:48:26,678 INFO [train.py:715] (4/8) Epoch 12, batch 23000, loss[loss=0.1515, simple_loss=0.2176, pruned_loss=0.04272, over 4834.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.03182, over 971761.70 frames.], batch size: 30, lr: 1.80e-04
2022-05-07 12:49:04,951 INFO [train.py:715] (4/8) Epoch 12, batch 23050, loss[loss=0.1502, simple_loss=0.215, pruned_loss=0.04276, over 4695.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2113, pruned_loss=0.03205, over 971622.00 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:49:43,056 INFO [train.py:715] (4/8) Epoch 12, batch 23100, loss[loss=0.1129, simple_loss=0.1926, pruned_loss=0.01656, over 4863.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.03124, over 971580.35 frames.], batch size: 32, lr: 1.80e-04
2022-05-07 12:50:21,956 INFO [train.py:715] (4/8) Epoch 12, batch 23150, loss[loss=0.1281, simple_loss=0.211, pruned_loss=0.02256, over 4857.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03139, over 971468.42 frames.], batch size: 20, lr: 1.80e-04
2022-05-07 12:51:01,025 INFO [train.py:715] (4/8) Epoch 12, batch 23200, loss[loss=0.1804, simple_loss=0.2396, pruned_loss=0.06054, over 4817.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03139, over 971131.22 frames.], batch size: 12, lr: 1.80e-04
2022-05-07 12:51:39,417 INFO [train.py:715] (4/8) Epoch 12, batch 23250, loss[loss=0.1421, simple_loss=0.2171, pruned_loss=0.03354, over 4913.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2106, pruned_loss=0.03158, over 970661.19 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:52:17,110 INFO [train.py:715] (4/8) Epoch 12, batch 23300, loss[loss=0.1186, simple_loss=0.182, pruned_loss=0.02758, over 4993.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03244, over 971271.04 frames.], batch size: 14, lr: 1.80e-04
2022-05-07 12:52:55,811 INFO [train.py:715] (4/8) Epoch 12, batch 23350, loss[loss=0.1231, simple_loss=0.2036, pruned_loss=0.02133, over 4931.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.03242, over 971450.28 frames.], batch size: 21, lr: 1.80e-04
2022-05-07 12:53:33,838 INFO [train.py:715] (4/8) Epoch 12, batch 23400, loss[loss=0.1634, simple_loss=0.2278, pruned_loss=0.04945, over 4881.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2115, pruned_loss=0.0324, over 971601.87 frames.], batch size: 39, lr: 1.80e-04
2022-05-07 12:54:11,389 INFO [train.py:715] (4/8) Epoch 12, batch 23450, loss[loss=0.1321, simple_loss=0.2131, pruned_loss=0.02558, over 4985.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2114, pruned_loss=0.03205, over 971254.41 frames.], batch size: 28, lr: 1.80e-04
2022-05-07 12:54:49,572 INFO [train.py:715] (4/8) Epoch 12, batch 23500, loss[loss=0.149, simple_loss=0.2241, pruned_loss=0.037, over 4767.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2111, pruned_loss=0.03185, over 971785.02 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:55:28,413 INFO [train.py:715] (4/8) Epoch 12, batch 23550, loss[loss=0.1378, simple_loss=0.2209, pruned_loss=0.02735, over 4946.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03157, over 972502.09 frames.], batch size: 21, lr: 1.80e-04
2022-05-07 12:56:07,101 INFO [train.py:715] (4/8) Epoch 12, batch 23600, loss[loss=0.1498, simple_loss=0.2171, pruned_loss=0.04124, over 4919.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03175, over 972043.16 frames.], batch size: 39, lr: 1.80e-04
2022-05-07 12:56:45,800 INFO [train.py:715] (4/8) Epoch 12, batch 23650, loss[loss=0.1384, simple_loss=0.1989, pruned_loss=0.03898, over 4836.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03145, over 971738.03 frames.], batch size: 13, lr: 1.80e-04
2022-05-07 12:57:24,208 INFO [train.py:715] (4/8) Epoch 12, batch 23700, loss[loss=0.1385, simple_loss=0.2195, pruned_loss=0.0287, over 4992.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.0317, over 971592.34 frames.], batch size: 20, lr: 1.80e-04
2022-05-07 12:58:02,491 INFO [train.py:715] (4/8) Epoch 12, batch 23750, loss[loss=0.1497, simple_loss=0.2207, pruned_loss=0.03937, over 4832.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03171, over 971465.50 frames.], batch size: 15, lr: 1.80e-04
2022-05-07 12:58:41,204 INFO [train.py:715] (4/8) Epoch 12, batch 23800, loss[loss=0.1114, simple_loss=0.1892, pruned_loss=0.01685, over 4843.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03135, over 971881.63 frames.], batch size: 12, lr: 1.80e-04
2022-05-07 12:59:20,123 INFO [train.py:715] (4/8) Epoch 12, batch 23850, loss[loss=0.1718, simple_loss=0.2428, pruned_loss=0.05045, over 4766.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2105, pruned_loss=0.03122, over 970819.46 frames.], batch size: 17, lr: 1.80e-04
2022-05-07 12:59:59,699 INFO [train.py:715] (4/8) Epoch 12, batch 23900, loss[loss=0.1298, simple_loss=0.2107, pruned_loss=0.02443, over 4984.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2104, pruned_loss=0.03114, over 970765.86 frames.], batch size: 24, lr: 1.80e-04
2022-05-07 13:00:39,414 INFO [train.py:715] (4/8) Epoch 12, batch 23950, loss[loss=0.1514, simple_loss=0.2162, pruned_loss=0.04331, over 4643.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03117, over 970753.86 frames.], batch size: 13, lr: 1.79e-04
2022-05-07 13:01:18,249 INFO [train.py:715] (4/8) Epoch 12, batch 24000, loss[loss=0.1361, simple_loss=0.2046, pruned_loss=0.03377, over 4963.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03138, over 970952.81 frames.], batch size: 35, lr: 1.79e-04
2022-05-07 13:01:18,250 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 13:01:27,802 INFO [train.py:742] (4/8) Epoch 12, validation: loss=0.1054, simple_loss=0.1895, pruned_loss=0.01071, over 914524.00 frames.
2022-05-07 13:02:06,827 INFO [train.py:715] (4/8) Epoch 12, batch 24050, loss[loss=0.136, simple_loss=0.2066, pruned_loss=0.03271, over 4885.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03136, over 971035.61 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:02:47,353 INFO [train.py:715] (4/8) Epoch 12, batch 24100, loss[loss=0.1472, simple_loss=0.225, pruned_loss=0.03467, over 4807.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03157, over 970434.68 frames.], batch size: 25, lr: 1.79e-04
2022-05-07 13:03:27,820 INFO [train.py:715] (4/8) Epoch 12, batch 24150, loss[loss=0.1204, simple_loss=0.2032, pruned_loss=0.01879, over 4943.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03104, over 971489.87 frames.], batch size: 23, lr: 1.79e-04
2022-05-07 13:04:07,858 INFO [train.py:715] (4/8) Epoch 12, batch 24200, loss[loss=0.1364, simple_loss=0.2136, pruned_loss=0.02959, over 4888.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03131, over 971008.54 frames.], batch size: 22, lr: 1.79e-04
2022-05-07 13:04:47,976 INFO [train.py:715] (4/8) Epoch 12, batch 24250, loss[loss=0.1278, simple_loss=0.2002, pruned_loss=0.02771, over 4896.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03154, over 970994.54 frames.], batch size: 22, lr: 1.79e-04
2022-05-07 13:05:28,023 INFO [train.py:715] (4/8) Epoch 12, batch 24300, loss[loss=0.1649, simple_loss=0.2423, pruned_loss=0.04371, over 4988.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03147, over 972059.55 frames.], batch size: 25, lr: 1.79e-04
2022-05-07 13:06:07,752 INFO [train.py:715] (4/8) Epoch 12, batch 24350, loss[loss=0.1488, simple_loss=0.2266, pruned_loss=0.03545, over 4814.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2097, pruned_loss=0.0319, over 971351.28 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:06:47,582 INFO [train.py:715] (4/8) Epoch 12, batch 24400, loss[loss=0.1358, simple_loss=0.2059, pruned_loss=0.03286, over 4776.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2094, pruned_loss=0.03155, over 971867.14 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:07:27,539 INFO [train.py:715] (4/8) Epoch 12, batch 24450, loss[loss=0.136, simple_loss=0.2112, pruned_loss=0.03038, over 4946.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2095, pruned_loss=0.03164, over 972222.33 frames.], batch size: 21, lr: 1.79e-04
2022-05-07 13:08:07,305 INFO [train.py:715] (4/8) Epoch 12, batch 24500, loss[loss=0.1495, simple_loss=0.2253, pruned_loss=0.03684, over 4960.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2097, pruned_loss=0.03193, over 971544.34 frames.], batch size: 21, lr: 1.79e-04
2022-05-07 13:08:46,549 INFO [train.py:715] (4/8) Epoch 12, batch 24550, loss[loss=0.1553, simple_loss=0.2242, pruned_loss=0.04323, over 4980.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2105, pruned_loss=0.03231, over 972128.03 frames.], batch size: 25, lr: 1.79e-04
2022-05-07 13:09:26,200 INFO [train.py:715] (4/8) Epoch 12, batch 24600, loss[loss=0.1266, simple_loss=0.196, pruned_loss=0.02864, over 4986.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2117, pruned_loss=0.03267, over 972268.57 frames.], batch size: 33, lr: 1.79e-04
2022-05-07 13:10:05,920 INFO [train.py:715] (4/8) Epoch 12, batch 24650, loss[loss=0.1325, simple_loss=0.2107, pruned_loss=0.02719, over 4989.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2124, pruned_loss=0.03271, over 972345.53 frames.], batch size: 28, lr: 1.79e-04
2022-05-07 13:10:45,621 INFO [train.py:715] (4/8) Epoch 12, batch 24700, loss[loss=0.1342, simple_loss=0.2109, pruned_loss=0.02878, over 4803.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03227, over 972197.03 frames.], batch size: 25, lr: 1.79e-04
2022-05-07 13:11:24,785 INFO [train.py:715] (4/8) Epoch 12, batch 24750, loss[loss=0.1585, simple_loss=0.2256, pruned_loss=0.04571, over 4949.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2116, pruned_loss=0.03262, over 971934.30 frames.], batch size: 39, lr: 1.79e-04
2022-05-07 13:12:04,997 INFO [train.py:715] (4/8) Epoch 12, batch 24800, loss[loss=0.1766, simple_loss=0.2581, pruned_loss=0.04758, over 4856.00 frames.], tot_loss[loss=0.1387, simple_loss=0.2119, pruned_loss=0.03278, over 972532.99 frames.], batch size: 20, lr: 1.79e-04
2022-05-07 13:12:44,862 INFO [train.py:715] (4/8) Epoch 12, batch 24850, loss[loss=0.1098, simple_loss=0.1765, pruned_loss=0.02156, over 4830.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2108, pruned_loss=0.03241, over 972285.85 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:13:24,108 INFO [train.py:715] (4/8) Epoch 12, batch 24900, loss[loss=0.1342, simple_loss=0.2039, pruned_loss=0.03221, over 4948.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2111, pruned_loss=0.03232, over 972615.97 frames.], batch size: 35, lr: 1.79e-04
2022-05-07 13:14:03,442 INFO [train.py:715] (4/8) Epoch 12, batch 24950, loss[loss=0.1377, simple_loss=0.2181, pruned_loss=0.02868, over 4969.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2106, pruned_loss=0.03204, over 974018.83 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:14:42,359 INFO [train.py:715] (4/8) Epoch 12, batch 25000, loss[loss=0.1363, simple_loss=0.2065, pruned_loss=0.03304, over 4946.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2088, pruned_loss=0.03142, over 973151.63 frames.], batch size: 21, lr: 1.79e-04
2022-05-07 13:15:20,412 INFO [train.py:715] (4/8) Epoch 12, batch 25050, loss[loss=0.1647, simple_loss=0.2395, pruned_loss=0.04491, over 4942.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2089, pruned_loss=0.03143, over 972587.42 frames.], batch size: 23, lr: 1.79e-04
2022-05-07 13:15:58,461 INFO [train.py:715] (4/8) Epoch 12, batch 25100, loss[loss=0.1208, simple_loss=0.1952, pruned_loss=0.02326, over 4772.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2086, pruned_loss=0.03106, over 972756.13 frames.], batch size: 17, lr: 1.79e-04
2022-05-07 13:16:36,853 INFO [train.py:715] (4/8) Epoch 12, batch 25150, loss[loss=0.1165, simple_loss=0.1975, pruned_loss=0.01779, over 4866.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2088, pruned_loss=0.03128, over 973258.10 frames.], batch size: 20, lr: 1.79e-04
2022-05-07 13:17:15,106 INFO [train.py:715] (4/8) Epoch 12, batch 25200, loss[loss=0.1575, simple_loss=0.237, pruned_loss=0.03899, over 4767.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2086, pruned_loss=0.03139, over 972375.87 frames.], batch size: 14, lr: 1.79e-04
2022-05-07 13:17:52,726 INFO [train.py:715] (4/8) Epoch 12, batch 25250, loss[loss=0.128, simple_loss=0.2068, pruned_loss=0.0246, over 4897.00 frames.], tot_loss[loss=0.1362, simple_loss=0.209, pruned_loss=0.03169, over 972094.59 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:18:30,734 INFO [train.py:715] (4/8) Epoch 12, batch 25300, loss[loss=0.1304, simple_loss=0.2108, pruned_loss=0.02493, over 4768.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2088, pruned_loss=0.0311, over 971934.69 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:19:08,813 INFO [train.py:715] (4/8) Epoch 12, batch 25350, loss[loss=0.1167, simple_loss=0.1887, pruned_loss=0.0223, over 4825.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.03135, over 972595.31 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:19:47,792 INFO [train.py:715] (4/8) Epoch 12, batch 25400, loss[loss=0.1333, simple_loss=0.2032, pruned_loss=0.03174, over 4961.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03119, over 972864.13 frames.], batch size: 24, lr: 1.79e-04
2022-05-07 13:20:26,681 INFO [train.py:715] (4/8) Epoch 12, batch 25450, loss[loss=0.1344, simple_loss=0.2191, pruned_loss=0.0248, over 4789.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03108, over 972479.20 frames.], batch size: 14, lr: 1.79e-04
2022-05-07 13:21:06,565 INFO [train.py:715] (4/8) Epoch 12, batch 25500, loss[loss=0.1422, simple_loss=0.224, pruned_loss=0.03023, over 4854.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03122, over 972888.29 frames.], batch size: 16, lr: 1.79e-04
2022-05-07 13:21:45,631 INFO [train.py:715] (4/8) Epoch 12, batch 25550, loss[loss=0.1356, simple_loss=0.2102, pruned_loss=0.03047, over 4817.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03144, over 972636.28 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:22:23,735 INFO [train.py:715] (4/8) Epoch 12, batch 25600, loss[loss=0.1586, simple_loss=0.227, pruned_loss=0.04513, over 4976.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.0313, over 971675.56 frames.], batch size: 35, lr: 1.79e-04
2022-05-07 13:23:02,065 INFO [train.py:715] (4/8) Epoch 12, batch 25650, loss[loss=0.17, simple_loss=0.2352, pruned_loss=0.05244, over 4818.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03178, over 972631.14 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:23:40,758 INFO [train.py:715] (4/8) Epoch 12, batch 25700, loss[loss=0.1265, simple_loss=0.1984, pruned_loss=0.02729, over 4795.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2111, pruned_loss=0.03195, over 972511.37 frames.], batch size: 24, lr: 1.79e-04
2022-05-07 13:24:19,544 INFO [train.py:715] (4/8) Epoch 12, batch 25750, loss[loss=0.1402, simple_loss=0.2158, pruned_loss=0.03234, over 4870.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2117, pruned_loss=0.0323, over 972367.32 frames.], batch size: 32, lr: 1.79e-04
2022-05-07 13:24:58,011 INFO [train.py:715] (4/8) Epoch 12, batch 25800, loss[loss=0.1352, simple_loss=0.2065, pruned_loss=0.03201, over 4821.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2116, pruned_loss=0.03184, over 972774.75 frames.], batch size: 26, lr: 1.79e-04
2022-05-07 13:25:36,922 INFO [train.py:715] (4/8) Epoch 12, batch 25850, loss[loss=0.1351, simple_loss=0.2028, pruned_loss=0.03368, over 4899.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2115, pruned_loss=0.03198, over 973836.67 frames.], batch size: 17, lr: 1.79e-04
2022-05-07 13:26:15,480 INFO [train.py:715] (4/8) Epoch 12, batch 25900, loss[loss=0.1172, simple_loss=0.1946, pruned_loss=0.0199, over 4859.00 frames.], tot_loss[loss=0.1371, simple_loss=0.211, pruned_loss=0.03163, over 973314.19 frames.], batch size: 20, lr: 1.79e-04
2022-05-07 13:26:53,773 INFO [train.py:715] (4/8) Epoch 12, batch 25950, loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.0325, over 4761.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03199, over 972972.87 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:27:31,254 INFO [train.py:715] (4/8) Epoch 12, batch 26000, loss[loss=0.1239, simple_loss=0.2025, pruned_loss=0.02263, over 4969.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2114, pruned_loss=0.03173, over 973123.90 frames.], batch size: 24, lr: 1.79e-04
2022-05-07 13:28:09,533 INFO [train.py:715] (4/8) Epoch 12, batch 26050, loss[loss=0.1231, simple_loss=0.1913, pruned_loss=0.02744, over 4939.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2108, pruned_loss=0.0315, over 973701.94 frames.], batch size: 29, lr: 1.79e-04
2022-05-07 13:28:48,388 INFO [train.py:715] (4/8) Epoch 12, batch 26100, loss[loss=0.132, simple_loss=0.209, pruned_loss=0.02754, over 4806.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2111, pruned_loss=0.03154, over 973681.62 frames.], batch size: 21, lr: 1.79e-04
2022-05-07 13:29:27,202 INFO [train.py:715] (4/8) Epoch 12, batch 26150, loss[loss=0.1616, simple_loss=0.2276, pruned_loss=0.04776, over 4784.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03135, over 974133.57 frames.], batch size: 18, lr: 1.79e-04
2022-05-07 13:30:06,155 INFO [train.py:715] (4/8) Epoch 12, batch 26200, loss[loss=0.1452, simple_loss=0.2123, pruned_loss=0.03909, over 4750.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2108, pruned_loss=0.0318, over 974084.92 frames.], batch size: 16, lr: 1.79e-04
2022-05-07 13:30:44,508 INFO [train.py:715] (4/8) Epoch 12, batch 26250, loss[loss=0.123, simple_loss=0.2066, pruned_loss=0.01966, over 4849.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03149, over 973647.62 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:31:23,015 INFO [train.py:715] (4/8) Epoch 12, batch 26300, loss[loss=0.1241, simple_loss=0.1944, pruned_loss=0.02692, over 4787.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03134, over 973400.32 frames.], batch size: 14, lr: 1.79e-04
2022-05-07 13:32:02,155 INFO [train.py:715] (4/8) Epoch 12, batch 26350, loss[loss=0.1437, simple_loss=0.2073, pruned_loss=0.04006, over 4782.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2095, pruned_loss=0.03161, over 972686.75 frames.], batch size: 18, lr: 1.79e-04
2022-05-07 13:32:40,220 INFO [train.py:715] (4/8) Epoch 12, batch 26400, loss[loss=0.1056, simple_loss=0.1834, pruned_loss=0.01391, over 4915.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2094, pruned_loss=0.03175, over 972855.65 frames.], batch size: 23, lr: 1.79e-04
2022-05-07 13:33:18,355 INFO [train.py:715] (4/8) Epoch 12, batch 26450, loss[loss=0.1878, simple_loss=0.272, pruned_loss=0.05184, over 4848.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2094, pruned_loss=0.03148, over 972958.19 frames.], batch size: 20, lr: 1.79e-04
2022-05-07 13:33:56,293 INFO [train.py:715] (4/8) Epoch 12, batch 26500, loss[loss=0.1461, simple_loss=0.2151, pruned_loss=0.03856, over 4862.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03091, over 972851.08 frames.], batch size: 32, lr: 1.79e-04
2022-05-07 13:34:34,593 INFO [train.py:715] (4/8) Epoch 12, batch 26550, loss[loss=0.1462, simple_loss=0.2175, pruned_loss=0.03746, over 4913.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.031, over 972400.21 frames.], batch size: 18, lr: 1.79e-04
2022-05-07 13:35:12,933 INFO [train.py:715] (4/8) Epoch 12, batch 26600, loss[loss=0.132, simple_loss=0.2131, pruned_loss=0.02541, over 4926.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03088, over 972566.66 frames.], batch size: 29, lr: 1.79e-04
2022-05-07 13:35:51,456 INFO [train.py:715] (4/8) Epoch 12, batch 26650, loss[loss=0.127, simple_loss=0.2044, pruned_loss=0.02483, over 4736.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03095, over 972513.42 frames.], batch size: 16, lr: 1.79e-04
2022-05-07 13:36:30,043 INFO [train.py:715] (4/8) Epoch 12, batch 26700, loss[loss=0.1368, simple_loss=0.2195, pruned_loss=0.02708, over 4806.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.03155, over 972555.97 frames.], batch size: 24, lr: 1.79e-04
2022-05-07 13:37:08,437 INFO [train.py:715] (4/8) Epoch 12, batch 26750, loss[loss=0.1162, simple_loss=0.2029, pruned_loss=0.01472, over 4924.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03189, over 972893.45 frames.], batch size: 23, lr: 1.79e-04
2022-05-07 13:37:47,891 INFO [train.py:715] (4/8) Epoch 12, batch 26800, loss[loss=0.1478, simple_loss=0.2084, pruned_loss=0.04358, over 4861.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2119, pruned_loss=0.03248, over 972836.24 frames.], batch size: 13, lr: 1.79e-04
2022-05-07 13:38:27,719 INFO [train.py:715] (4/8) Epoch 12, batch 26850, loss[loss=0.1373, simple_loss=0.2086, pruned_loss=0.033, over 4781.00 frames.], tot_loss[loss=0.138, simple_loss=0.2114, pruned_loss=0.03228, over 971908.71 frames.], batch size: 17, lr: 1.79e-04
2022-05-07 13:39:07,110 INFO [train.py:715] (4/8) Epoch 12, batch 26900, loss[loss=0.1155, simple_loss=0.1826, pruned_loss=0.0242, over 4752.00 frames.], tot_loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03239, over 972244.71 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 13:39:45,953 INFO [train.py:715] (4/8) Epoch 12, batch 26950, loss[loss=0.1184, simple_loss=0.1891, pruned_loss=0.02384, over 4697.00 frames.], tot_loss[loss=0.138, simple_loss=0.2113, pruned_loss=0.0323, over 972497.07 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:40:25,485 INFO [train.py:715] (4/8) Epoch 12, batch 27000, loss[loss=0.1227, simple_loss=0.2021, pruned_loss=0.02165, over 4887.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03207, over 972163.93 frames.], batch size: 16, lr: 1.79e-04
2022-05-07 13:40:25,486 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 13:40:37,911 INFO [train.py:742] (4/8) Epoch 12, validation: loss=0.1054, simple_loss=0.1894, pruned_loss=0.01072, over 914524.00 frames.
2022-05-07 13:41:17,233 INFO [train.py:715] (4/8) Epoch 12, batch 27050, loss[loss=0.1338, simple_loss=0.203, pruned_loss=0.03229, over 4942.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03153, over 972760.75 frames.], batch size: 29, lr: 1.79e-04
2022-05-07 13:41:55,464 INFO [train.py:715] (4/8) Epoch 12, batch 27100, loss[loss=0.1357, simple_loss=0.2076, pruned_loss=0.0319, over 4773.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03185, over 971708.45 frames.], batch size: 18, lr: 1.79e-04
2022-05-07 13:42:33,820 INFO [train.py:715] (4/8) Epoch 12, batch 27150, loss[loss=0.1372, simple_loss=0.2092, pruned_loss=0.03262, over 4796.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2096, pruned_loss=0.03162, over 972453.44 frames.], batch size: 14, lr: 1.79e-04
2022-05-07 13:43:12,677 INFO [train.py:715] (4/8) Epoch 12, batch 27200, loss[loss=0.1524, simple_loss=0.227, pruned_loss=0.03883, over 4982.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.03199, over 972539.22 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:43:50,978 INFO [train.py:715] (4/8) Epoch 12, batch 27250, loss[loss=0.1246, simple_loss=0.2056, pruned_loss=0.02184, over 4823.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03201, over 972220.19 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:44:29,601 INFO [train.py:715] (4/8) Epoch 12, batch 27300, loss[loss=0.1173, simple_loss=0.1957, pruned_loss=0.0194, over 4859.00 frames.], tot_loss[loss=0.137, simple_loss=0.2102, pruned_loss=0.03187, over 972595.56 frames.], batch size: 13, lr: 1.79e-04
2022-05-07 13:45:08,185 INFO [train.py:715] (4/8) Epoch 12, batch 27350, loss[loss=0.1033, simple_loss=0.1775, pruned_loss=0.01457, over 4827.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03168, over 971178.26 frames.], batch size: 13, lr: 1.79e-04
2022-05-07 13:45:47,171 INFO [train.py:715] (4/8) Epoch 12, batch 27400, loss[loss=0.1279, simple_loss=0.2034, pruned_loss=0.02618, over 4769.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2109, pruned_loss=0.0319, over 972136.90 frames.], batch size: 18, lr: 1.79e-04
2022-05-07 13:46:25,847 INFO [train.py:715] (4/8) Epoch 12, batch 27450, loss[loss=0.1643, simple_loss=0.2398, pruned_loss=0.04446, over 4843.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03164, over 972107.45 frames.], batch size: 30, lr: 1.79e-04
2022-05-07 13:47:04,344 INFO [train.py:715] (4/8) Epoch 12, batch 27500, loss[loss=0.1667, simple_loss=0.2288, pruned_loss=0.05224, over 4981.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.0315, over 973209.95 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:47:43,118 INFO [train.py:715] (4/8) Epoch 12, batch 27550, loss[loss=0.1302, simple_loss=0.2074, pruned_loss=0.02647, over 4988.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.0319, over 973200.62 frames.], batch size: 25, lr: 1.79e-04
2022-05-07 13:48:21,798 INFO [train.py:715] (4/8) Epoch 12, batch 27600, loss[loss=0.131, simple_loss=0.2047, pruned_loss=0.02867, over 4783.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2109, pruned_loss=0.03221, over 973183.90 frames.], batch size: 14, lr: 1.79e-04
2022-05-07 13:49:00,948 INFO [train.py:715] (4/8) Epoch 12, batch 27650, loss[loss=0.1527, simple_loss=0.2287, pruned_loss=0.0384, over 4909.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2112, pruned_loss=0.03234, over 973601.09 frames.], batch size: 17, lr: 1.79e-04
2022-05-07 13:49:39,560 INFO [train.py:715] (4/8) Epoch 12, batch 27700, loss[loss=0.1613, simple_loss=0.2308, pruned_loss=0.0459, over 4838.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2111, pruned_loss=0.03269, over 973453.95 frames.], batch size: 30, lr: 1.79e-04
2022-05-07 13:50:18,423 INFO [train.py:715] (4/8) Epoch 12, batch 27750, loss[loss=0.1718, simple_loss=0.2418, pruned_loss=0.05093, over 4963.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2103, pruned_loss=0.0323, over 972888.13 frames.], batch size: 14, lr: 1.79e-04
2022-05-07 13:50:56,329 INFO [train.py:715] (4/8) Epoch 12, batch 27800, loss[loss=0.1532, simple_loss=0.2383, pruned_loss=0.03404, over 4702.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.03198, over 972991.27 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:51:34,004 INFO [train.py:715] (4/8) Epoch 12, batch 27850, loss[loss=0.1578, simple_loss=0.2334, pruned_loss=0.04105, over 4914.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.03214, over 972472.74 frames.], batch size: 17, lr: 1.79e-04
2022-05-07 13:52:12,422 INFO [train.py:715] (4/8) Epoch 12, batch 27900, loss[loss=0.1498, simple_loss=0.215, pruned_loss=0.04228, over 4797.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2111, pruned_loss=0.03253, over 972764.51 frames.], batch size: 24, lr: 1.79e-04
2022-05-07 13:52:50,385 INFO [train.py:715] (4/8) Epoch 12, batch 27950, loss[loss=0.1354, simple_loss=0.2059, pruned_loss=0.03246, over 4953.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2113, pruned_loss=0.03244, over 973081.26 frames.], batch size: 35, lr: 1.79e-04
2022-05-07 13:53:28,677 INFO [train.py:715] (4/8) Epoch 12, batch 28000, loss[loss=0.1416, simple_loss=0.2145, pruned_loss=0.03432, over 4884.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2113, pruned_loss=0.03262, over 972859.10 frames.], batch size: 30, lr: 1.79e-04
2022-05-07 13:54:06,332 INFO [train.py:715] (4/8) Epoch 12, batch 28050, loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03049, over 4776.00 frames.], tot_loss[loss=0.1395, simple_loss=0.2127, pruned_loss=0.03316, over 971314.44 frames.], batch size: 14, lr: 1.79e-04
2022-05-07 13:54:44,517 INFO [train.py:715] (4/8) Epoch 12, batch 28100, loss[loss=0.1034, simple_loss=0.1738, pruned_loss=0.01655, over 4790.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.03235, over 971061.66 frames.], batch size: 12, lr: 1.79e-04
2022-05-07 13:55:22,259 INFO [train.py:715] (4/8) Epoch 12, batch 28150, loss[loss=0.1494, simple_loss=0.2241, pruned_loss=0.03736, over 4835.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2117, pruned_loss=0.03243, over 971907.48 frames.], batch size: 13, lr: 1.79e-04
2022-05-07 13:56:00,667 INFO [train.py:715] (4/8) Epoch 12, batch 28200, loss[loss=0.1214, simple_loss=0.1968, pruned_loss=0.02304, over 4890.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.0322, over 972766.09 frames.], batch size: 16, lr: 1.79e-04
2022-05-07 13:56:39,077 INFO [train.py:715] (4/8) Epoch 12, batch 28250, loss[loss=0.1547, simple_loss=0.2239, pruned_loss=0.04275, over 4830.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2108, pruned_loss=0.03209, over 972498.32 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 13:57:17,044 INFO [train.py:715] (4/8) Epoch 12, batch 28300, loss[loss=0.1153, simple_loss=0.1868, pruned_loss=0.0219, over 4830.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03154, over 972138.46 frames.], batch size: 12, lr: 1.79e-04
2022-05-07 13:57:55,847 INFO [train.py:715] (4/8) Epoch 12, batch 28350, loss[loss=0.1502, simple_loss=0.2143, pruned_loss=0.04301, over 4927.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03157, over 972918.49 frames.], batch size: 17, lr: 1.79e-04
2022-05-07 13:58:33,886 INFO [train.py:715] (4/8) Epoch 12, batch 28400, loss[loss=0.1525, simple_loss=0.2219, pruned_loss=0.04153, over 4860.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03154, over 973669.80 frames.], batch size: 32, lr: 1.79e-04
2022-05-07 13:59:12,073 INFO [train.py:715] (4/8) Epoch 12, batch 28450, loss[loss=0.1328, simple_loss=0.2001, pruned_loss=0.03278, over 4971.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03131, over 973298.84 frames.], batch size: 24, lr: 1.79e-04
2022-05-07 13:59:49,933 INFO [train.py:715] (4/8) Epoch 12, batch 28500, loss[loss=0.158, simple_loss=0.224, pruned_loss=0.04603, over 4862.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.03147, over 972496.07 frames.], batch size: 32, lr: 1.79e-04
2022-05-07 14:00:27,901 INFO [train.py:715] (4/8) Epoch 12, batch 28550, loss[loss=0.137, simple_loss=0.2156, pruned_loss=0.0292, over 4760.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03123, over 972759.30 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 14:01:06,320 INFO [train.py:715] (4/8) Epoch 12, batch 28600, loss[loss=0.1337, simple_loss=0.2099, pruned_loss=0.0288, over 4918.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2102, pruned_loss=0.03177, over 972219.47 frames.], batch size: 17, lr: 1.79e-04
2022-05-07 14:01:44,218 INFO [train.py:715] (4/8) Epoch 12, batch 28650, loss[loss=0.1204, simple_loss=0.2009, pruned_loss=0.01995, over 4746.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03202, over 972677.24 frames.], batch size: 19, lr: 1.79e-04
2022-05-07 14:02:23,316 INFO [train.py:715] (4/8) Epoch 12, batch 28700, loss[loss=0.1175, simple_loss=0.1884, pruned_loss=0.02326, over 4793.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2098, pruned_loss=0.03178, over 973104.07 frames.], batch size: 18, lr: 1.79e-04
2022-05-07 14:03:01,820 INFO [train.py:715] (4/8) Epoch 12, batch 28750, loss[loss=0.1084, simple_loss=0.1823, pruned_loss=0.01727, over 4688.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2094, pruned_loss=0.03163, over 973944.73 frames.], batch size: 15, lr: 1.79e-04
2022-05-07 14:03:40,788 INFO [train.py:715] (4/8) Epoch 12, batch 28800, loss[loss=0.1331, simple_loss=0.2014, pruned_loss=0.03243, over 4831.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2092, pruned_loss=0.03151, over 972785.59 frames.], batch size: 30, lr: 1.79e-04
2022-05-07 14:04:18,675 INFO [train.py:715] (4/8) Epoch 12, batch 28850, loss[loss=0.1349, simple_loss=0.2061, pruned_loss=0.03182, over 4854.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2097, pruned_loss=0.03163, over 972192.60 frames.], batch size: 32, lr: 1.79e-04
2022-05-07 14:04:57,033 INFO [train.py:715] (4/8) Epoch 12, batch 28900, loss[loss=0.1082, simple_loss=0.1794, pruned_loss=0.01851, over 4856.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2094, pruned_loss=0.03182, over 972349.85 frames.], batch size: 13, lr: 1.78e-04
2022-05-07 14:05:35,790 INFO [train.py:715] (4/8) Epoch 12, batch 28950, loss[loss=0.1345, simple_loss=0.1988, pruned_loss=0.03508, over 4859.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2086, pruned_loss=0.03136, over 972457.52 frames.], batch size: 13, lr: 1.78e-04
2022-05-07 14:06:14,145 INFO [train.py:715] (4/8) Epoch 12, batch 29000, loss[loss=0.1189, simple_loss=0.1901, pruned_loss=0.02386, over 4963.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2088, pruned_loss=0.03146, over 972393.03 frames.], batch size: 21, lr: 1.78e-04
2022-05-07 14:06:53,417 INFO [train.py:715] (4/8) Epoch 12, batch 29050, loss[loss=0.1734, simple_loss=0.232, pruned_loss=0.05739, over 4850.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.03131, over 972463.34 frames.], batch size: 32, lr: 1.78e-04
2022-05-07 14:07:31,884 INFO [train.py:715] (4/8) Epoch 12, batch 29100, loss[loss=0.1366, simple_loss=0.2157, pruned_loss=0.02876, over 4892.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03123, over 972926.10 frames.], batch size: 22, lr: 1.78e-04
2022-05-07 14:08:10,553 INFO [train.py:715] (4/8) Epoch 12, batch 29150, loss[loss=0.1618, simple_loss=0.2354, pruned_loss=0.04407, over 4955.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03147, over 973425.03 frames.], batch size: 24, lr: 1.78e-04
2022-05-07 14:08:48,980 INFO [train.py:715] (4/8) Epoch 12, batch 29200, loss[loss=0.1286, simple_loss=0.2012, pruned_loss=0.02803, over 4755.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03109, over 973713.56 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:09:27,674 INFO [train.py:715] (4/8) Epoch 12, batch 29250, loss[loss=0.1239, simple_loss=0.201, pruned_loss=0.0234, over 4809.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03108, over 974197.08 frames.], batch size: 21, lr: 1.78e-04
2022-05-07 14:10:05,809 INFO [train.py:715] (4/8) Epoch 12, batch 29300, loss[loss=0.1201, simple_loss=0.1911, pruned_loss=0.02456, over 4919.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03133, over 973916.78 frames.], batch size: 23, lr: 1.78e-04
2022-05-07 14:10:43,234 INFO [train.py:715] (4/8) Epoch 12, batch 29350, loss[loss=0.129, simple_loss=0.2044, pruned_loss=0.02683, over 4974.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03129, over 973530.89 frames.], batch size: 14, lr: 1.78e-04
2022-05-07 14:11:22,339 INFO [train.py:715] (4/8) Epoch 12, batch 29400, loss[loss=0.1244, simple_loss=0.1859, pruned_loss=0.03147, over 4984.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03149, over 973937.27 frames.], batch size: 14, lr: 1.78e-04
2022-05-07 14:12:00,593 INFO [train.py:715] (4/8) Epoch 12, batch 29450, loss[loss=0.1481, simple_loss=0.2253, pruned_loss=0.03545, over 4815.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.03197, over 973636.19 frames.], batch size: 24, lr: 1.78e-04
2022-05-07 14:12:38,753 INFO [train.py:715] (4/8) Epoch 12, batch 29500, loss[loss=0.1183, simple_loss=0.1947, pruned_loss=0.021, over 4900.00 frames.], tot_loss[loss=0.1379, simple_loss=0.211, pruned_loss=0.03238, over 973806.65 frames.], batch size: 22, lr: 1.78e-04
2022-05-07 14:13:16,879 INFO [train.py:715] (4/8) Epoch 12, batch 29550, loss[loss=0.1312, simple_loss=0.2037, pruned_loss=0.02941, over 4843.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2104, pruned_loss=0.03221, over 972672.87 frames.], batch size: 13, lr: 1.78e-04
2022-05-07 14:13:55,809 INFO [train.py:715] (4/8) Epoch 12, batch 29600, loss[loss=0.1465, simple_loss=0.2199, pruned_loss=0.03658, over 4806.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2104, pruned_loss=0.03208, over 972071.58 frames.], batch size: 14, lr: 1.78e-04
2022-05-07 14:14:34,033 INFO [train.py:715] (4/8) Epoch 12, batch 29650, loss[loss=0.1434, simple_loss=0.2193, pruned_loss=0.0338, over 4911.00 frames.], tot_loss[loss=0.1371, simple_loss=0.21, pruned_loss=0.03205, over 972338.16 frames.], batch size: 39, lr: 1.78e-04
2022-05-07 14:15:11,742 INFO [train.py:715] (4/8) Epoch 12, batch 29700, loss[loss=0.1345, simple_loss=0.2047, pruned_loss=0.0321, over 4752.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2105, pruned_loss=0.03202, over 972771.23 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:15:51,284 INFO [train.py:715] (4/8) Epoch 12, batch 29750, loss[loss=0.116, simple_loss=0.1969, pruned_loss=0.01755, over 4950.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.03179, over 973148.52 frames.], batch size: 24, lr: 1.78e-04
2022-05-07 14:16:30,393 INFO [train.py:715] (4/8) Epoch 12, batch 29800, loss[loss=0.1612, simple_loss=0.2294, pruned_loss=0.04652, over 4950.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.03155, over 973402.04 frames.], batch size: 35, lr: 1.78e-04
2022-05-07 14:17:09,203 INFO [train.py:715] (4/8) Epoch 12, batch 29850, loss[loss=0.1713, simple_loss=0.2482, pruned_loss=0.04718, over 4871.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03148, over 973026.76 frames.], batch size: 32, lr: 1.78e-04
2022-05-07 14:17:47,534 INFO [train.py:715] (4/8) Epoch 12, batch 29900, loss[loss=0.1125, simple_loss=0.1931, pruned_loss=0.016, over 4819.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03122, over 973065.06 frames.], batch size: 26, lr: 1.78e-04
2022-05-07 14:18:26,386 INFO [train.py:715] (4/8) Epoch 12, batch 29950, loss[loss=0.1639, simple_loss=0.2227, pruned_loss=0.05253, over 4856.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03176, over 972518.31 frames.], batch size: 32, lr: 1.78e-04
2022-05-07 14:19:04,509 INFO [train.py:715] (4/8) Epoch 12, batch 30000, loss[loss=0.1229, simple_loss=0.191, pruned_loss=0.02737, over 4767.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2091, pruned_loss=0.03139, over 971883.77 frames.], batch size: 17, lr: 1.78e-04
2022-05-07 14:19:04,510 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 14:19:14,011 INFO [train.py:742] (4/8) Epoch 12, validation: loss=0.1054, simple_loss=0.1894, pruned_loss=0.01072, over 914524.00 frames.
2022-05-07 14:19:52,927 INFO [train.py:715] (4/8) Epoch 12, batch 30050, loss[loss=0.1237, simple_loss=0.1996, pruned_loss=0.02391, over 4941.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2082, pruned_loss=0.03134, over 971162.80 frames.], batch size: 21, lr: 1.78e-04
2022-05-07 14:20:31,345 INFO [train.py:715] (4/8) Epoch 12, batch 30100, loss[loss=0.138, simple_loss=0.2127, pruned_loss=0.03167, over 4958.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2086, pruned_loss=0.03117, over 972392.90 frames.], batch size: 21, lr: 1.78e-04
2022-05-07 14:21:10,513 INFO [train.py:715] (4/8) Epoch 12, batch 30150, loss[loss=0.1112, simple_loss=0.1816, pruned_loss=0.02045, over 4894.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2088, pruned_loss=0.03112, over 971864.93 frames.], batch size: 22, lr: 1.78e-04
2022-05-07 14:21:48,975 INFO [train.py:715] (4/8) Epoch 12, batch 30200, loss[loss=0.1579, simple_loss=0.2321, pruned_loss=0.04184, over 4876.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2089, pruned_loss=0.03118, over 972127.63 frames.], batch size: 22, lr: 1.78e-04
2022-05-07 14:22:28,456 INFO [train.py:715] (4/8) Epoch 12, batch 30250, loss[loss=0.1454, simple_loss=0.2126, pruned_loss=0.03908, over 4804.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03176, over 972463.79 frames.], batch size: 14, lr: 1.78e-04
2022-05-07 14:23:07,603 INFO [train.py:715] (4/8) Epoch 12, batch 30300, loss[loss=0.172, simple_loss=0.24, pruned_loss=0.05201, over 4902.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2104, pruned_loss=0.03195, over 972647.69 frames.], batch size: 39, lr: 1.78e-04
2022-05-07 14:23:45,574 INFO [train.py:715] (4/8) Epoch 12, batch 30350, loss[loss=0.1234, simple_loss=0.1993, pruned_loss=0.02378, over 4817.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03186, over 972780.74 frames.], batch size: 25, lr: 1.78e-04
2022-05-07 14:24:23,563 INFO [train.py:715] (4/8) Epoch 12, batch 30400, loss[loss=0.1311, simple_loss=0.2067, pruned_loss=0.02772, over 4877.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03111, over 972858.40 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:25:01,302 INFO [train.py:715] (4/8) Epoch 12, batch 30450, loss[loss=0.1357, simple_loss=0.2126, pruned_loss=0.02936, over 4748.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03124, over 972326.32 frames.], batch size: 16, lr: 1.78e-04
2022-05-07 14:25:39,285 INFO [train.py:715] (4/8) Epoch 12, batch 30500, loss[loss=0.129, simple_loss=0.1952, pruned_loss=0.03144, over 4977.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03127, over 972256.20 frames.], batch size: 15, lr: 1.78e-04
2022-05-07 14:26:17,289 INFO [train.py:715] (4/8) Epoch 12, batch 30550, loss[loss=0.121, simple_loss=0.1988, pruned_loss=0.0216, over 4972.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2106, pruned_loss=0.03133, over 972162.26 frames.], batch size: 28, lr: 1.78e-04
2022-05-07 14:26:55,238 INFO [train.py:715] (4/8) Epoch 12, batch 30600, loss[loss=0.1298, simple_loss=0.2011, pruned_loss=0.02926, over 4899.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03123, over 973298.71 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:27:32,191 INFO [train.py:715] (4/8) Epoch 12, batch 30650, loss[loss=0.1499, simple_loss=0.2224, pruned_loss=0.03873, over 4856.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.0316, over 972810.54 frames.], batch size: 20, lr: 1.78e-04
2022-05-07 14:28:10,734 INFO [train.py:715] (4/8) Epoch 12, batch 30700, loss[loss=0.1258, simple_loss=0.2146, pruned_loss=0.01853, over 4833.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03109, over 972836.14 frames.], batch size: 15, lr: 1.78e-04
2022-05-07 14:28:48,656 INFO [train.py:715] (4/8) Epoch 12, batch 30750, loss[loss=0.146, simple_loss=0.2217, pruned_loss=0.03514, over 4844.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03128, over 973060.48 frames.], batch size: 30, lr: 1.78e-04
2022-05-07 14:29:27,169 INFO [train.py:715] (4/8) Epoch 12, batch 30800, loss[loss=0.1365, simple_loss=0.2039, pruned_loss=0.03456, over 4851.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03172, over 972495.65 frames.], batch size: 32, lr: 1.78e-04
2022-05-07 14:30:05,816 INFO [train.py:715] (4/8) Epoch 12, batch 30850, loss[loss=0.1263, simple_loss=0.1917, pruned_loss=0.03047, over 4970.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2113, pruned_loss=0.03197, over 972281.04 frames.], batch size: 24, lr: 1.78e-04
2022-05-07 14:30:45,016 INFO [train.py:715] (4/8) Epoch 12, batch 30900, loss[loss=0.1408, simple_loss=0.2241, pruned_loss=0.02876, over 4897.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2116, pruned_loss=0.03207, over 972473.77 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:31:23,359 INFO [train.py:715] (4/8) Epoch 12, batch 30950, loss[loss=0.1488, simple_loss=0.2233, pruned_loss=0.03713, over 4847.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2116, pruned_loss=0.03228, over 971749.55 frames.], batch size: 20, lr: 1.78e-04
2022-05-07 14:32:02,065 INFO [train.py:715] (4/8) Epoch 12, batch 31000, loss[loss=0.141, simple_loss=0.2213, pruned_loss=0.03029, over 4907.00 frames.], tot_loss[loss=0.1389, simple_loss=0.2126, pruned_loss=0.03262, over 971686.81 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:32:41,211 INFO [train.py:715] (4/8) Epoch 12, batch 31050, loss[loss=0.1396, simple_loss=0.2163, pruned_loss=0.03142, over 4720.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2127, pruned_loss=0.03245, over 971409.15 frames.], batch size: 16, lr: 1.78e-04
2022-05-07 14:33:19,691 INFO [train.py:715] (4/8) Epoch 12, batch 31100, loss[loss=0.1382, simple_loss=0.2014, pruned_loss=0.03751, over 4805.00 frames.], tot_loss[loss=0.1394, simple_loss=0.2127, pruned_loss=0.03304, over 971931.43 frames.], batch size: 25, lr: 1.78e-04
2022-05-07 14:33:57,507 INFO [train.py:715] (4/8) Epoch 12, batch 31150, loss[loss=0.136, simple_loss=0.2112, pruned_loss=0.03043, over 4854.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2121, pruned_loss=0.03215, over 971632.28 frames.], batch size: 20, lr: 1.78e-04
2022-05-07 14:34:36,504 INFO [train.py:715] (4/8) Epoch 12, batch 31200, loss[loss=0.1313, simple_loss=0.198, pruned_loss=0.03234, over 4809.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03215, over 971908.59 frames.], batch size: 12, lr: 1.78e-04
2022-05-07 14:35:15,343 INFO [train.py:715] (4/8) Epoch 12, batch 31250, loss[loss=0.1457, simple_loss=0.2153, pruned_loss=0.03809, over 4798.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2115, pruned_loss=0.032, over 972186.14 frames.], batch size: 17, lr: 1.78e-04
2022-05-07 14:35:54,048 INFO [train.py:715] (4/8) Epoch 12, batch 31300, loss[loss=0.1464, simple_loss=0.2199, pruned_loss=0.0364, over 4924.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2113, pruned_loss=0.0319, over 972188.03 frames.], batch size: 39, lr: 1.78e-04
2022-05-07 14:36:32,568 INFO [train.py:715] (4/8) Epoch 12, batch 31350, loss[loss=0.1169, simple_loss=0.2003, pruned_loss=0.01676, over 4927.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2108, pruned_loss=0.03185, over 972588.42 frames.], batch size: 23, lr: 1.78e-04
2022-05-07 14:37:11,736 INFO [train.py:715] (4/8) Epoch 12, batch 31400, loss[loss=0.1311, simple_loss=0.2171, pruned_loss=0.02251, over 4965.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03162, over 972774.69 frames.], batch size: 24, lr: 1.78e-04
2022-05-07 14:37:50,138 INFO [train.py:715] (4/8) Epoch 12, batch 31450, loss[loss=0.1422, simple_loss=0.2182, pruned_loss=0.0331, over 4844.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2117, pruned_loss=0.03193, over 972198.47 frames.], batch size: 13, lr: 1.78e-04
2022-05-07 14:38:28,380 INFO [train.py:715] (4/8) Epoch 12, batch 31500, loss[loss=0.1384, simple_loss=0.2115, pruned_loss=0.03265, over 4845.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2117, pruned_loss=0.03192, over 972251.10 frames.], batch size: 30, lr: 1.78e-04
2022-05-07 14:39:06,658 INFO [train.py:715] (4/8) Epoch 12, batch 31550, loss[loss=0.1197, simple_loss=0.1786, pruned_loss=0.0304, over 4797.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03161, over 972617.45 frames.], batch size: 12, lr: 1.78e-04
2022-05-07 14:39:45,222 INFO [train.py:715] (4/8) Epoch 12, batch 31600, loss[loss=0.1576, simple_loss=0.2255, pruned_loss=0.04484, over 4959.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03147, over 973747.55 frames.], batch size: 21, lr: 1.78e-04
2022-05-07 14:40:22,891 INFO [train.py:715] (4/8) Epoch 12, batch 31650, loss[loss=0.1308, simple_loss=0.2092, pruned_loss=0.02616, over 4964.00 frames.], tot_loss[loss=0.137, simple_loss=0.2105, pruned_loss=0.03178, over 974002.73 frames.], batch size: 15, lr: 1.78e-04
2022-05-07 14:41:00,518 INFO [train.py:715] (4/8) Epoch 12, batch 31700, loss[loss=0.1393, simple_loss=0.2246, pruned_loss=0.02693, over 4958.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03208, over 973345.21 frames.], batch size: 24, lr: 1.78e-04
2022-05-07 14:41:38,634 INFO [train.py:715] (4/8) Epoch 12, batch 31750, loss[loss=0.1387, simple_loss=0.2103, pruned_loss=0.03354, over 4847.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.03222, over 973071.95 frames.], batch size: 34, lr: 1.78e-04
2022-05-07 14:42:16,748 INFO [train.py:715] (4/8) Epoch 12, batch 31800, loss[loss=0.1286, simple_loss=0.2013, pruned_loss=0.02791, over 4923.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2113, pruned_loss=0.03186, over 973528.76 frames.], batch size: 23, lr: 1.78e-04
2022-05-07 14:42:54,700 INFO [train.py:715] (4/8) Epoch 12, batch 31850, loss[loss=0.125, simple_loss=0.207, pruned_loss=0.02157, over 4930.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2114, pruned_loss=0.03158, over 973694.72 frames.], batch size: 23, lr: 1.78e-04
2022-05-07 14:43:32,404 INFO [train.py:715] (4/8) Epoch 12, batch 31900, loss[loss=0.1364, simple_loss=0.2109, pruned_loss=0.03092, over 4916.00 frames.], tot_loss[loss=0.137, simple_loss=0.211, pruned_loss=0.0315, over 974271.92 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 14:44:10,697 INFO [train.py:715] (4/8) Epoch 12, batch 31950, loss[loss=0.1369, simple_loss=0.2182, pruned_loss=0.02781, over 4891.00 frames.], tot_loss[loss=0.137, simple_loss=0.2111, pruned_loss=0.03145, over 975003.00 frames.], batch size: 22, lr: 1.78e-04
2022-05-07 14:44:48,296 INFO [train.py:715] (4/8) Epoch 12, batch 32000, loss[loss=0.122, simple_loss=0.1974, pruned_loss=0.02328, over 4975.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2115, pruned_loss=0.03203, over 974586.22 frames.], batch size: 15, lr: 1.78e-04
2022-05-07 14:45:26,162 INFO [train.py:715] (4/8) Epoch 12, batch 32050, loss[loss=0.1571, simple_loss=0.2291, pruned_loss=0.04255, over 4832.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2111, pruned_loss=0.03158, over 974552.33 frames.], batch size: 30, lr: 1.78e-04
2022-05-07 14:46:04,020 INFO [train.py:715] (4/8) Epoch 12, batch 32100, loss[loss=0.104, simple_loss=0.1827, pruned_loss=0.01268, over 4805.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2106, pruned_loss=0.03156, over 973459.26 frames.], batch size: 26, lr: 1.78e-04
2022-05-07 14:46:42,429 INFO [train.py:715] (4/8) Epoch 12, batch 32150, loss[loss=0.1649, simple_loss=0.2341, pruned_loss=0.0479, over 4760.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2115, pruned_loss=0.03221, over 973426.15 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:47:20,024 INFO [train.py:715] (4/8) Epoch 12, batch 32200, loss[loss=0.1183, simple_loss=0.1908, pruned_loss=0.02294, over 4782.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2114, pruned_loss=0.03207, over 974070.98 frames.], batch size: 12, lr: 1.78e-04
2022-05-07 14:47:58,174 INFO [train.py:715] (4/8) Epoch 12, batch 32250, loss[loss=0.1296, simple_loss=0.2066, pruned_loss=0.02628, over 4758.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03207, over 973568.47 frames.], batch size: 16, lr: 1.78e-04
2022-05-07 14:48:36,824 INFO [train.py:715] (4/8) Epoch 12, batch 32300, loss[loss=0.1333, simple_loss=0.2047, pruned_loss=0.03095, over 4732.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03214, over 972748.47 frames.], batch size: 12, lr: 1.78e-04
2022-05-07 14:49:14,383 INFO [train.py:715] (4/8) Epoch 12, batch 32350, loss[loss=0.1247, simple_loss=0.1973, pruned_loss=0.02609, over 4916.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03178, over 972407.09 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 14:49:52,727 INFO [train.py:715] (4/8) Epoch 12, batch 32400, loss[loss=0.1452, simple_loss=0.223, pruned_loss=0.03368, over 4935.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2106, pruned_loss=0.03138, over 973093.38 frames.], batch size: 21, lr: 1.78e-04
2022-05-07 14:50:30,827 INFO [train.py:715] (4/8) Epoch 12, batch 32450, loss[loss=0.1229, simple_loss=0.205, pruned_loss=0.02043, over 4898.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03103, over 972245.33 frames.], batch size: 17, lr: 1.78e-04
2022-05-07 14:51:09,333 INFO [train.py:715] (4/8) Epoch 12, batch 32500, loss[loss=0.1281, simple_loss=0.2056, pruned_loss=0.02531, over 4813.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03121, over 972539.50 frames.], batch size: 27, lr: 1.78e-04
2022-05-07 14:51:46,831 INFO [train.py:715] (4/8) Epoch 12, batch 32550, loss[loss=0.1394, simple_loss=0.1997, pruned_loss=0.03951, over 4832.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03132, over 972786.62 frames.], batch size: 12, lr: 1.78e-04
2022-05-07 14:52:25,071 INFO [train.py:715] (4/8) Epoch 12, batch 32600, loss[loss=0.1156, simple_loss=0.1859, pruned_loss=0.02268, over 4792.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.0313, over 973560.02 frames.], batch size: 14, lr: 1.78e-04
2022-05-07 14:53:03,208 INFO [train.py:715] (4/8) Epoch 12, batch 32650, loss[loss=0.1187, simple_loss=0.1917, pruned_loss=0.02283, over 4806.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.0313, over 973222.43 frames.], batch size: 17, lr: 1.78e-04
2022-05-07 14:53:40,737 INFO [train.py:715] (4/8) Epoch 12, batch 32700, loss[loss=0.1463, simple_loss=0.206, pruned_loss=0.0433, over 4870.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2087, pruned_loss=0.03117, over 973331.95 frames.], batch size: 22, lr: 1.78e-04
2022-05-07 14:54:18,461 INFO [train.py:715] (4/8) Epoch 12, batch 32750, loss[loss=0.1163, simple_loss=0.186, pruned_loss=0.02332, over 4801.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.0307, over 972917.92 frames.], batch size: 21, lr: 1.78e-04
2022-05-07 14:54:56,866 INFO [train.py:715] (4/8) Epoch 12, batch 32800, loss[loss=0.136, simple_loss=0.207, pruned_loss=0.03254, over 4890.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03056, over 972700.95 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 14:55:35,235 INFO [train.py:715] (4/8) Epoch 12, batch 32850, loss[loss=0.1413, simple_loss=0.2224, pruned_loss=0.03013, over 4873.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03102, over 973020.45 frames.], batch size: 16, lr: 1.78e-04
2022-05-07 14:56:12,922 INFO [train.py:715] (4/8) Epoch 12, batch 32900, loss[loss=0.1371, simple_loss=0.2097, pruned_loss=0.03224, over 4967.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03103, over 972336.64 frames.], batch size: 39, lr: 1.78e-04
2022-05-07 14:56:51,022 INFO [train.py:715] (4/8) Epoch 12, batch 32950, loss[loss=0.1548, simple_loss=0.228, pruned_loss=0.04078, over 4925.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03108, over 972689.42 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 14:57:29,167 INFO [train.py:715] (4/8) Epoch 12, batch 33000, loss[loss=0.1496, simple_loss=0.2211, pruned_loss=0.03903, over 4782.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03088, over 972661.41 frames.], batch size: 17, lr: 1.78e-04
2022-05-07 14:57:29,167 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 14:57:38,688 INFO [train.py:742] (4/8) Epoch 12, validation: loss=0.1057, simple_loss=0.1896, pruned_loss=0.01085, over 914524.00 frames.
2022-05-07 14:58:18,205 INFO [train.py:715] (4/8) Epoch 12, batch 33050, loss[loss=0.1408, simple_loss=0.207, pruned_loss=0.03731, over 4939.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03101, over 972478.93 frames.], batch size: 23, lr: 1.78e-04
2022-05-07 14:58:56,556 INFO [train.py:715] (4/8) Epoch 12, batch 33100, loss[loss=0.1508, simple_loss=0.2203, pruned_loss=0.04062, over 4889.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03128, over 972386.26 frames.], batch size: 39, lr: 1.78e-04
2022-05-07 14:59:34,842 INFO [train.py:715] (4/8) Epoch 12, batch 33150, loss[loss=0.1363, simple_loss=0.2045, pruned_loss=0.03404, over 4886.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.0312, over 972790.72 frames.], batch size: 17, lr: 1.78e-04
2022-05-07 15:00:12,868 INFO [train.py:715] (4/8) Epoch 12, batch 33200, loss[loss=0.1219, simple_loss=0.194, pruned_loss=0.02494, over 4966.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03119, over 973181.88 frames.], batch size: 15, lr: 1.78e-04
2022-05-07 15:00:51,450 INFO [train.py:715] (4/8) Epoch 12, batch 33250, loss[loss=0.1198, simple_loss=0.1943, pruned_loss=0.02267, over 4978.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03106, over 972411.32 frames.], batch size: 25, lr: 1.78e-04
2022-05-07 15:01:29,591 INFO [train.py:715] (4/8) Epoch 12, batch 33300, loss[loss=0.1249, simple_loss=0.2024, pruned_loss=0.02372, over 4830.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03113, over 972367.50 frames.], batch size: 26, lr: 1.78e-04
2022-05-07 15:02:07,721 INFO [train.py:715] (4/8) Epoch 12, batch 33350, loss[loss=0.1394, simple_loss=0.2181, pruned_loss=0.03035, over 4885.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03078, over 972369.26 frames.], batch size: 20, lr: 1.78e-04
2022-05-07 15:02:46,383 INFO [train.py:715] (4/8) Epoch 12, batch 33400, loss[loss=0.1063, simple_loss=0.192, pruned_loss=0.01031, over 4939.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.031, over 973606.16 frames.], batch size: 23, lr: 1.78e-04
2022-05-07 15:03:25,037 INFO [train.py:715] (4/8) Epoch 12, batch 33450, loss[loss=0.1261, simple_loss=0.2011, pruned_loss=0.02554, over 4982.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03108, over 973768.95 frames.], batch size: 15, lr: 1.78e-04
2022-05-07 15:04:03,395 INFO [train.py:715] (4/8) Epoch 12, batch 33500, loss[loss=0.1405, simple_loss=0.2224, pruned_loss=0.02931, over 4800.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03053, over 973153.58 frames.], batch size: 24, lr: 1.78e-04
2022-05-07 15:04:42,494 INFO [train.py:715] (4/8) Epoch 12, batch 33550, loss[loss=0.126, simple_loss=0.2012, pruned_loss=0.02539, over 4819.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03066, over 973293.80 frames.], batch size: 25, lr: 1.78e-04
2022-05-07 15:05:21,127 INFO [train.py:715] (4/8) Epoch 12, batch 33600, loss[loss=0.1403, simple_loss=0.2101, pruned_loss=0.03525, over 4759.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03077, over 973347.87 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 15:05:59,984 INFO [train.py:715] (4/8) Epoch 12, batch 33650, loss[loss=0.099, simple_loss=0.1705, pruned_loss=0.01376, over 4770.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2099, pruned_loss=0.03077, over 972765.92 frames.], batch size: 19, lr: 1.78e-04
2022-05-07 15:06:38,063 INFO [train.py:715] (4/8) Epoch 12, batch 33700, loss[loss=0.1406, simple_loss=0.2169, pruned_loss=0.0321, over 4777.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03149, over 973651.46 frames.], batch size: 18, lr: 1.78e-04
2022-05-07 15:07:16,846 INFO [train.py:715] (4/8) Epoch 12, batch 33750, loss[loss=0.1084, simple_loss=0.1773, pruned_loss=0.01974, over 4930.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03105, over 973437.62 frames.], batch size: 21, lr: 1.78e-04
2022-05-07 15:07:55,113 INFO [train.py:715] (4/8) Epoch 12, batch 33800, loss[loss=0.1552, simple_loss=0.2184, pruned_loss=0.04597, over 4746.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03127, over 973165.13 frames.], batch size: 16, lr: 1.78e-04
2022-05-07 15:08:32,476 INFO [train.py:715] (4/8) Epoch 12, batch 33850, loss[loss=0.1452, simple_loss=0.2233, pruned_loss=0.03361, over 4764.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03087, over 972745.58 frames.], batch size: 16, lr: 1.78e-04
2022-05-07 15:09:10,655 INFO [train.py:715] (4/8) Epoch 12, batch 33900, loss[loss=0.1486, simple_loss=0.2256, pruned_loss=0.03576, over 4809.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03074, over 972022.04 frames.], batch size: 25, lr: 1.78e-04
2022-05-07 15:09:47,908 INFO [train.py:715] (4/8) Epoch 12, batch 33950, loss[loss=0.1429, simple_loss=0.2148, pruned_loss=0.03553, over 4922.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03074, over 971963.51 frames.], batch size: 17, lr: 1.77e-04
2022-05-07 15:10:26,069 INFO [train.py:715] (4/8) Epoch 12, batch 34000, loss[loss=0.1279, simple_loss=0.2002, pruned_loss=0.02775, over 4802.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03083, over 971078.05 frames.], batch size: 14, lr: 1.77e-04
2022-05-07 15:11:03,702 INFO [train.py:715] (4/8) Epoch 12, batch 34050, loss[loss=0.1272, simple_loss=0.212, pruned_loss=0.02121, over 4755.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03105, over 971488.43 frames.], batch size: 14, lr: 1.77e-04
2022-05-07 15:11:41,637 INFO [train.py:715] (4/8) Epoch 12, batch 34100, loss[loss=0.1832, simple_loss=0.2559, pruned_loss=0.05527, over 4913.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03149, over 971716.25 frames.], batch size: 39, lr: 1.77e-04
2022-05-07 15:12:19,673 INFO [train.py:715] (4/8) Epoch 12, batch 34150, loss[loss=0.1463, simple_loss=0.2234, pruned_loss=0.03458, over 4796.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2106, pruned_loss=0.03151, over 971319.21 frames.], batch size: 24, lr: 1.77e-04
2022-05-07 15:12:57,180 INFO [train.py:715] (4/8) Epoch 12, batch 34200, loss[loss=0.1269, simple_loss=0.1962, pruned_loss=0.02876, over 4869.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03167, over 971954.18 frames.], batch size: 16, lr: 1.77e-04
2022-05-07 15:13:35,449 INFO [train.py:715] (4/8) Epoch 12, batch 34250, loss[loss=0.1454, simple_loss=0.2128, pruned_loss=0.039, over 4696.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03126, over 971819.09 frames.], batch size: 15, lr: 1.77e-04
2022-05-07 15:14:12,818 INFO [train.py:715] (4/8) Epoch 12, batch 34300, loss[loss=0.1743, simple_loss=0.2386, pruned_loss=0.05495, over 4961.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.0312, over 972627.61 frames.], batch size: 24, lr: 1.77e-04
2022-05-07 15:14:51,107 INFO [train.py:715] (4/8) Epoch 12, batch 34350, loss[loss=0.1385, simple_loss=0.2161, pruned_loss=0.03049, over 4854.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03144, over 973204.22 frames.], batch size: 20, lr: 1.77e-04
2022-05-07 15:15:28,881 INFO [train.py:715] (4/8) Epoch 12, batch 34400, loss[loss=0.1436, simple_loss=0.2203, pruned_loss=0.03342, over 4696.00 frames.], tot_loss[loss=0.1368, simple_loss=0.21, pruned_loss=0.03176, over 972615.30 frames.], batch size: 15, lr: 1.77e-04
2022-05-07 15:16:07,247 INFO [train.py:715] (4/8) Epoch 12, batch 34450, loss[loss=0.1434, simple_loss=0.2078, pruned_loss=0.03956, over 4845.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03136, over 973030.89 frames.], batch size: 32, lr: 1.77e-04
2022-05-07 15:16:45,350 INFO [train.py:715] (4/8) Epoch 12, batch 34500, loss[loss=0.1506, simple_loss=0.2208, pruned_loss=0.04017, over 4736.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03161, over 972509.33 frames.], batch size: 16, lr: 1.77e-04
2022-05-07 15:17:23,595 INFO [train.py:715] (4/8) Epoch 12, batch 34550, loss[loss=0.1438, simple_loss=0.216, pruned_loss=0.03577, over 4911.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2105, pruned_loss=0.0314, over 973122.59 frames.], batch size: 19, lr: 1.77e-04
2022-05-07 15:18:02,262 INFO [train.py:715] (4/8) Epoch 12, batch 34600, loss[loss=0.1438, simple_loss=0.2243, pruned_loss=0.03166, over 4753.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03121, over 972741.05 frames.], batch size: 19, lr: 1.77e-04
2022-05-07 15:18:41,656 INFO [train.py:715] (4/8) Epoch 12, batch 34650, loss[loss=0.1315, simple_loss=0.2032, pruned_loss=0.02995, over 4793.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03113, over 972779.85 frames.], batch size: 18, lr: 1.77e-04
2022-05-07 15:19:21,042 INFO [train.py:715] (4/8) Epoch 12, batch 34700, loss[loss=0.1169, simple_loss=0.1901, pruned_loss=0.02191, over 4820.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2096, pruned_loss=0.03169, over 972727.10 frames.], batch size: 25, lr: 1.77e-04
2022-05-07 15:19:58,682 INFO [train.py:715] (4/8) Epoch 12, batch 34750, loss[loss=0.1359, simple_loss=0.2087, pruned_loss=0.0316, over 4731.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2098, pruned_loss=0.0315, over 972104.01 frames.], batch size: 16, lr: 1.77e-04
2022-05-07 15:20:34,681 INFO [train.py:715] (4/8) Epoch 12, batch 34800, loss[loss=0.2032, simple_loss=0.2551, pruned_loss=0.07563, over 4787.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03157, over 972190.48 frames.], batch size: 14, lr: 1.77e-04
2022-05-07 15:21:23,127 INFO [train.py:715] (4/8) Epoch 13, batch 0, loss[loss=0.14, simple_loss=0.2187, pruned_loss=0.03063, over 4736.00 frames.], tot_loss[loss=0.14, simple_loss=0.2187, pruned_loss=0.03063, over 4736.00 frames.], batch size: 16, lr: 1.71e-04
2022-05-07 15:22:01,156 INFO [train.py:715] (4/8) Epoch 13, batch 50, loss[loss=0.1265, simple_loss=0.2002, pruned_loss=0.02643, over 4790.00 frames.], tot_loss[loss=0.1385, simple_loss=0.212, pruned_loss=0.03244, over 219090.61 frames.], batch size: 21, lr: 1.71e-04
2022-05-07 15:22:39,464 INFO [train.py:715] (4/8) Epoch 13, batch 100, loss[loss=0.1134, simple_loss=0.1901, pruned_loss=0.01832, over 4846.00 frames.], tot_loss[loss=0.1388, simple_loss=0.2125, pruned_loss=0.03261, over 387064.24 frames.], batch size: 34, lr: 1.71e-04
2022-05-07 15:23:17,857 INFO [train.py:715] (4/8) Epoch 13, batch 150, loss[loss=0.1076, simple_loss=0.1797, pruned_loss=0.01777, over 4832.00 frames.], tot_loss[loss=0.138, simple_loss=0.2116, pruned_loss=0.03224, over 516278.41 frames.], batch size: 12, lr: 1.71e-04
2022-05-07 15:23:57,326 INFO [train.py:715] (4/8) Epoch 13, batch 200, loss[loss=0.1464, simple_loss=0.2223, pruned_loss=0.03522, over 4862.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2116, pruned_loss=0.0324, over 617175.02 frames.], batch size: 32, lr: 1.71e-04
2022-05-07 15:24:35,736 INFO [train.py:715] (4/8) Epoch 13, batch 250, loss[loss=0.1131, simple_loss=0.1805, pruned_loss=0.02283, over 4959.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03142, over 695529.10 frames.], batch size: 15, lr: 1.71e-04
2022-05-07 15:25:15,233 INFO [train.py:715] (4/8) Epoch 13, batch 300, loss[loss=0.1615, simple_loss=0.2404, pruned_loss=0.04126, over 4867.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03207, over 757436.27 frames.], batch size: 20, lr: 1.71e-04
2022-05-07 15:25:53,990 INFO [train.py:715] (4/8) Epoch 13, batch 350, loss[loss=0.113, simple_loss=0.1837, pruned_loss=0.02121, over 4927.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.0312, over 805483.66 frames.], batch size: 29, lr: 1.71e-04
2022-05-07 15:26:33,528 INFO [train.py:715] (4/8) Epoch 13, batch 400, loss[loss=0.1432, simple_loss=0.2156, pruned_loss=0.0354, over 4778.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03071, over 842257.91 frames.], batch size: 18, lr: 1.71e-04
2022-05-07 15:27:13,019 INFO [train.py:715] (4/8) Epoch 13, batch 450, loss[loss=0.1336, simple_loss=0.2131, pruned_loss=0.02704, over 4962.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2085, pruned_loss=0.03068, over 871526.04 frames.], batch size: 24, lr: 1.71e-04
2022-05-07 15:27:53,184 INFO [train.py:715] (4/8) Epoch 13, batch 500, loss[loss=0.1256, simple_loss=0.1956, pruned_loss=0.02785, over 4936.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03076, over 894916.16 frames.], batch size: 29, lr: 1.71e-04
2022-05-07 15:28:33,639 INFO [train.py:715] (4/8) Epoch 13, batch 550, loss[loss=0.1306, simple_loss=0.2097, pruned_loss=0.02576, over 4935.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2088, pruned_loss=0.03096, over 911907.74 frames.], batch size: 18, lr: 1.71e-04
2022-05-07 15:29:12,913 INFO [train.py:715] (4/8) Epoch 13, batch 600, loss[loss=0.1379, simple_loss=0.2062, pruned_loss=0.03481, over 4827.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2089, pruned_loss=0.03109, over 925039.25 frames.], batch size: 27, lr: 1.71e-04
2022-05-07 15:29:53,397 INFO [train.py:715] (4/8) Epoch 13, batch 650, loss[loss=0.1449, simple_loss=0.2074, pruned_loss=0.04126, over 4971.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.0309, over 935678.31 frames.], batch size: 24, lr: 1.71e-04
2022-05-07 15:30:33,371 INFO [train.py:715] (4/8) Epoch 13, batch 700, loss[loss=0.1405, simple_loss=0.2113, pruned_loss=0.03488, over 4955.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03081, over 943748.11 frames.], batch size: 29, lr: 1.71e-04
2022-05-07 15:31:13,980 INFO [train.py:715] (4/8) Epoch 13, batch 750, loss[loss=0.1374, simple_loss=0.2009, pruned_loss=0.037, over 4648.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03108, over 949663.59 frames.], batch size: 13, lr: 1.71e-04
2022-05-07 15:31:53,296 INFO [train.py:715] (4/8) Epoch 13, batch 800, loss[loss=0.1422, simple_loss=0.2062, pruned_loss=0.03915, over 4933.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03123, over 954708.11 frames.], batch size: 23, lr: 1.71e-04
2022-05-07 15:32:32,552 INFO [train.py:715] (4/8) Epoch 13, batch 850, loss[loss=0.1412, simple_loss=0.2002, pruned_loss=0.04108, over 4961.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2098, pruned_loss=0.03178, over 959406.68 frames.], batch size: 24, lr: 1.71e-04
2022-05-07 15:33:12,806 INFO [train.py:715] (4/8) Epoch 13, batch 900, loss[loss=0.1377, simple_loss=0.2223, pruned_loss=0.02651, over 4811.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03172, over 961493.04 frames.], batch size: 25, lr: 1.71e-04
2022-05-07 15:33:52,192 INFO [train.py:715] (4/8) Epoch 13, batch 950, loss[loss=0.1494, simple_loss=0.2175, pruned_loss=0.04068, over 4912.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2098, pruned_loss=0.03152, over 963590.60 frames.], batch size: 17, lr: 1.71e-04
2022-05-07 15:34:32,772 INFO [train.py:715] (4/8) Epoch 13, batch 1000, loss[loss=0.1345, simple_loss=0.2184, pruned_loss=0.02526, over 4814.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.0315, over 964914.99 frames.], batch size: 25, lr: 1.71e-04
2022-05-07 15:35:12,236 INFO [train.py:715] (4/8) Epoch 13, batch 1050, loss[loss=0.1349, simple_loss=0.2147, pruned_loss=0.02754, over 4850.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03138, over 965891.02 frames.], batch size: 20, lr: 1.71e-04
2022-05-07 15:35:52,550 INFO [train.py:715] (4/8) Epoch 13, batch 1100, loss[loss=0.123, simple_loss=0.1895, pruned_loss=0.0283, over 4826.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03118, over 967312.59 frames.], batch size: 13, lr: 1.71e-04
2022-05-07 15:36:32,010 INFO [train.py:715] (4/8) Epoch 13, batch 1150, loss[loss=0.1233, simple_loss=0.1973, pruned_loss=0.02461, over 4804.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03116, over 967927.02 frames.], batch size: 13, lr: 1.71e-04
2022-05-07 15:37:11,795 INFO [train.py:715] (4/8) Epoch 13, batch 1200, loss[loss=0.1182, simple_loss=0.2014, pruned_loss=0.01752, over 4780.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03076, over 967598.93 frames.], batch size: 18, lr: 1.71e-04
2022-05-07 15:37:52,135 INFO [train.py:715] (4/8) Epoch 13, batch 1250, loss[loss=0.1087, simple_loss=0.1805, pruned_loss=0.01847, over 4848.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2082, pruned_loss=0.03075, over 968263.22 frames.], batch size: 13, lr: 1.71e-04
2022-05-07 15:38:31,090 INFO [train.py:715] (4/8) Epoch 13, batch 1300, loss[loss=0.1524, simple_loss=0.2187, pruned_loss=0.04302, over 4789.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.03089, over 968986.17 frames.], batch size: 18, lr: 1.71e-04
2022-05-07 15:39:11,006 INFO [train.py:715] (4/8) Epoch 13, batch 1350, loss[loss=0.1588, simple_loss=0.226, pruned_loss=0.04583, over 4882.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2092, pruned_loss=0.03157, over 970149.27 frames.], batch size: 22, lr: 1.71e-04
2022-05-07 15:39:49,772 INFO [train.py:715] (4/8) Epoch 13, batch 1400, loss[loss=0.1742, simple_loss=0.2435, pruned_loss=0.05252, over 4777.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2089, pruned_loss=0.03133, over 969828.14 frames.], batch size: 18, lr: 1.71e-04
2022-05-07 15:40:28,860 INFO [train.py:715] (4/8) Epoch 13, batch 1450, loss[loss=0.1331, simple_loss=0.2107, pruned_loss=0.02774, over 4693.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2087, pruned_loss=0.03108, over 971025.82 frames.], batch size: 15, lr: 1.71e-04
2022-05-07 15:41:06,534 INFO [train.py:715] (4/8) Epoch 13, batch 1500, loss[loss=0.147, simple_loss=0.2303, pruned_loss=0.03181, over 4794.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.03131, over 971063.29 frames.], batch size: 18, lr: 1.71e-04
2022-05-07 15:41:44,152 INFO [train.py:715] (4/8) Epoch 13, batch 1550, loss[loss=0.1484, simple_loss=0.2271, pruned_loss=0.03491, over 4859.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2089, pruned_loss=0.03106, over 971996.69 frames.], batch size: 20, lr: 1.71e-04
2022-05-07 15:42:22,723 INFO [train.py:715] (4/8) Epoch 13, batch 1600, loss[loss=0.1737, simple_loss=0.256, pruned_loss=0.04573, over 4970.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03095, over 971803.93 frames.], batch size: 24, lr: 1.71e-04
2022-05-07 15:43:00,640 INFO [train.py:715] (4/8) Epoch 13, batch 1650, loss[loss=0.1362, simple_loss=0.2187, pruned_loss=0.02684, over 4873.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2104, pruned_loss=0.03114, over 972132.74 frames.], batch size: 22, lr: 1.71e-04
2022-05-07 15:43:39,377 INFO [train.py:715] (4/8) Epoch 13, batch 1700, loss[loss=0.1301, simple_loss=0.2098, pruned_loss=0.02523, over 4892.00 frames.], tot_loss[loss=0.1371, simple_loss=0.211, pruned_loss=0.03157, over 971899.57 frames.], batch size: 19, lr: 1.71e-04
2022-05-07 15:44:17,662 INFO [train.py:715] (4/8) Epoch 13, batch 1750, loss[loss=0.1641, simple_loss=0.2266, pruned_loss=0.05085, over 4935.00 frames.], tot_loss[loss=0.1374, simple_loss=0.211, pruned_loss=0.03188, over 972077.99 frames.], batch size: 35, lr: 1.71e-04
2022-05-07 15:44:57,089 INFO [train.py:715] (4/8) Epoch 13, batch 1800, loss[loss=0.1826, simple_loss=0.2335, pruned_loss=0.06585, over 4986.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03192, over 972615.42 frames.], batch size: 14, lr: 1.71e-04
2022-05-07 15:45:35,168 INFO [train.py:715] (4/8) Epoch 13, batch 1850, loss[loss=0.1215, simple_loss=0.1899, pruned_loss=0.02656, over 4988.00 frames.], tot_loss[loss=0.1376, simple_loss=0.211, pruned_loss=0.0321, over 972832.86 frames.], batch size: 28, lr: 1.71e-04
2022-05-07 15:46:13,429 INFO [train.py:715] (4/8) Epoch 13, batch 1900, loss[loss=0.1155, simple_loss=0.1982, pruned_loss=0.01642, over 4723.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03171, over 972660.35 frames.], batch size: 12, lr: 1.71e-04
2022-05-07 15:46:52,088 INFO [train.py:715] (4/8) Epoch 13, batch 1950, loss[loss=0.1298, simple_loss=0.1975, pruned_loss=0.03103, over 4776.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03141, over 972328.51 frames.], batch size: 17, lr: 1.71e-04
2022-05-07 15:47:30,463 INFO [train.py:715] (4/8) Epoch 13, batch 2000, loss[loss=0.1185, simple_loss=0.1917, pruned_loss=0.02266, over 4817.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03128, over 971076.99 frames.], batch size: 26, lr: 1.71e-04
2022-05-07 15:48:09,018 INFO [train.py:715] (4/8) Epoch 13, batch 2050, loss[loss=0.136, simple_loss=0.2081, pruned_loss=0.03193, over 4787.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03149, over 971218.51 frames.], batch size: 24, lr: 1.71e-04
2022-05-07 15:48:47,022 INFO [train.py:715] (4/8) Epoch 13, batch 2100, loss[loss=0.132, simple_loss=0.2121, pruned_loss=0.02594, over 4929.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2102, pruned_loss=0.03206, over 971970.90 frames.], batch size: 23, lr: 1.71e-04
2022-05-07 15:49:26,189 INFO [train.py:715] (4/8) Epoch 13, batch 2150, loss[loss=0.1308, simple_loss=0.2023, pruned_loss=0.02961, over 4785.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.0317, over 971383.47 frames.], batch size: 14, lr: 1.71e-04
2022-05-07 15:50:04,032 INFO [train.py:715] (4/8) Epoch 13, batch 2200, loss[loss=0.1256, simple_loss=0.1928, pruned_loss=0.0292, over 4920.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03125, over 971599.96 frames.], batch size: 17, lr: 1.71e-04
2022-05-07 15:50:42,241 INFO [train.py:715] (4/8) Epoch 13, batch 2250, loss[loss=0.1513, simple_loss=0.2355, pruned_loss=0.03359, over 4883.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03138, over 972081.18 frames.], batch size: 19, lr: 1.71e-04
2022-05-07 15:51:20,492 INFO [train.py:715] (4/8) Epoch 13, batch 2300, loss[loss=0.1736, simple_loss=0.2483, pruned_loss=0.0494, over 4817.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03139, over 972251.36 frames.], batch size: 26, lr: 1.71e-04
2022-05-07 15:51:59,646 INFO [train.py:715] (4/8) Epoch 13, batch 2350, loss[loss=0.1149, simple_loss=0.1838, pruned_loss=0.02303, over 4757.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2089, pruned_loss=0.03125, over 971999.97 frames.], batch size: 19, lr: 1.71e-04
2022-05-07 15:52:38,011 INFO [train.py:715] (4/8) Epoch 13, batch 2400, loss[loss=0.1078, simple_loss=0.1822, pruned_loss=0.01664, over 4751.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2089, pruned_loss=0.03119, over 972580.77 frames.], batch size: 12, lr: 1.71e-04
2022-05-07 15:53:16,748 INFO [train.py:715] (4/8) Epoch 13, batch 2450, loss[loss=0.134, simple_loss=0.2037, pruned_loss=0.03214, over 4865.00 frames.], tot_loss[loss=0.136, simple_loss=0.2092, pruned_loss=0.03139, over 972164.68 frames.], batch size: 32, lr: 1.71e-04
2022-05-07 15:53:55,655 INFO [train.py:715] (4/8) Epoch 13, batch 2500, loss[loss=0.1754, simple_loss=0.2473, pruned_loss=0.05175, over 4797.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03164, over 972186.71 frames.], batch size: 12, lr: 1.71e-04
2022-05-07 15:54:34,064 INFO [train.py:715] (4/8) Epoch 13, batch 2550, loss[loss=0.1186, simple_loss=0.1915, pruned_loss=0.02287, over 4828.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03184, over 972186.17 frames.], batch size: 26, lr: 1.71e-04
2022-05-07 15:55:12,160 INFO [train.py:715] (4/8) Epoch 13, batch 2600, loss[loss=0.1435, simple_loss=0.2105, pruned_loss=0.03821, over 4769.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03183, over 972208.67 frames.], batch size: 17, lr: 1.71e-04
2022-05-07 15:55:50,583 INFO [train.py:715] (4/8) Epoch 13, batch 2650, loss[loss=0.1378, simple_loss=0.2039, pruned_loss=0.03589, over 4847.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.0318, over 972549.81 frames.], batch size: 30, lr: 1.71e-04
2022-05-07 15:56:28,664 INFO [train.py:715] (4/8) Epoch 13, batch 2700, loss[loss=0.1257, simple_loss=0.1984, pruned_loss=0.02652, over 4705.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03158, over 972409.27 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 15:57:06,439 INFO [train.py:715] (4/8) Epoch 13, batch 2750, loss[loss=0.1152, simple_loss=0.2068, pruned_loss=0.01182, over 4753.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03152, over 972027.79 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 15:57:43,968 INFO [train.py:715] (4/8) Epoch 13, batch 2800, loss[loss=0.1402, simple_loss=0.2093, pruned_loss=0.03554, over 4793.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03138, over 972773.83 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 15:58:22,562 INFO [train.py:715] (4/8) Epoch 13, batch 2850, loss[loss=0.1415, simple_loss=0.2202, pruned_loss=0.0314, over 4888.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2104, pruned_loss=0.03103, over 972994.49 frames.], batch size: 38, lr: 1.70e-04
2022-05-07 15:59:00,069 INFO [train.py:715] (4/8) Epoch 13, batch 2900, loss[loss=0.1727, simple_loss=0.2493, pruned_loss=0.04807, over 4840.00 frames.], tot_loss[loss=0.1359, simple_loss=0.21, pruned_loss=0.03087, over 973836.15 frames.], batch size: 30, lr: 1.70e-04
2022-05-07 15:59:37,967 INFO [train.py:715] (4/8) Epoch 13, batch 2950, loss[loss=0.1309, simple_loss=0.2072, pruned_loss=0.02725, over 4793.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03089, over 973867.55 frames.], batch size: 24, lr: 1.70e-04
2022-05-07 16:00:15,987 INFO [train.py:715] (4/8) Epoch 13, batch 3000, loss[loss=0.1315, simple_loss=0.2067, pruned_loss=0.0282, over 4886.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03133, over 973316.52 frames.], batch size: 22, lr: 1.70e-04
2022-05-07 16:00:15,988 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 16:00:25,445 INFO [train.py:742] (4/8) Epoch 13, validation: loss=0.1052, simple_loss=0.1893, pruned_loss=0.01058, over 914524.00 frames.
2022-05-07 16:01:03,672 INFO [train.py:715] (4/8) Epoch 13, batch 3050, loss[loss=0.1353, simple_loss=0.2161, pruned_loss=0.02728, over 4790.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.0314, over 972735.13 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:01:42,202 INFO [train.py:715] (4/8) Epoch 13, batch 3100, loss[loss=0.2148, simple_loss=0.2797, pruned_loss=0.07494, over 4752.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.0313, over 972148.42 frames.], batch size: 16, lr: 1.70e-04
2022-05-07 16:02:19,746 INFO [train.py:715] (4/8) Epoch 13, batch 3150, loss[loss=0.1488, simple_loss=0.2294, pruned_loss=0.03409, over 4965.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2103, pruned_loss=0.03123, over 972243.19 frames.], batch size: 24, lr: 1.70e-04
2022-05-07 16:02:57,076 INFO [train.py:715] (4/8) Epoch 13, batch 3200, loss[loss=0.1201, simple_loss=0.196, pruned_loss=0.02216, over 4919.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.03134, over 972096.22 frames.], batch size: 23, lr: 1.70e-04
2022-05-07 16:03:35,542 INFO [train.py:715] (4/8) Epoch 13, batch 3250, loss[loss=0.1354, simple_loss=0.2087, pruned_loss=0.03107, over 4818.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03185, over 971668.23 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:04:13,564 INFO [train.py:715] (4/8) Epoch 13, batch 3300, loss[loss=0.134, simple_loss=0.2141, pruned_loss=0.0269, over 4764.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03165, over 971671.82 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:04:51,381 INFO [train.py:715] (4/8) Epoch 13, batch 3350, loss[loss=0.1404, simple_loss=0.209, pruned_loss=0.03588, over 4807.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03122, over 971199.84 frames.], batch size: 17, lr: 1.70e-04
2022-05-07 16:05:29,078 INFO [train.py:715] (4/8) Epoch 13, batch 3400, loss[loss=0.1337, simple_loss=0.2037, pruned_loss=0.03184, over 4874.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2086, pruned_loss=0.03124, over 971617.74 frames.], batch size: 32, lr: 1.70e-04
2022-05-07 16:06:07,373 INFO [train.py:715] (4/8) Epoch 13, batch 3450, loss[loss=0.1495, simple_loss=0.2248, pruned_loss=0.03714, over 4882.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2094, pruned_loss=0.03159, over 972098.22 frames.], batch size: 20, lr: 1.70e-04
2022-05-07 16:06:47,671 INFO [train.py:715] (4/8) Epoch 13, batch 3500, loss[loss=0.1462, simple_loss=0.227, pruned_loss=0.03269, over 4777.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03107, over 972653.95 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:07:25,032 INFO [train.py:715] (4/8) Epoch 13, batch 3550, loss[loss=0.1406, simple_loss=0.2113, pruned_loss=0.03496, over 4859.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03129, over 972559.45 frames.], batch size: 20, lr: 1.70e-04
2022-05-07 16:08:03,490 INFO [train.py:715] (4/8) Epoch 13, batch 3600, loss[loss=0.1636, simple_loss=0.2408, pruned_loss=0.04325, over 4933.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03145, over 971948.07 frames.], batch size: 39, lr: 1.70e-04
2022-05-07 16:08:41,279 INFO [train.py:715] (4/8) Epoch 13, batch 3650, loss[loss=0.1307, simple_loss=0.2025, pruned_loss=0.02949, over 4773.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.0313, over 971640.70 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:09:18,851 INFO [train.py:715] (4/8) Epoch 13, batch 3700, loss[loss=0.1281, simple_loss=0.2064, pruned_loss=0.0249, over 4812.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03116, over 971467.11 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:09:56,570 INFO [train.py:715] (4/8) Epoch 13, batch 3750, loss[loss=0.1219, simple_loss=0.1951, pruned_loss=0.02437, over 4933.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2086, pruned_loss=0.03094, over 971445.33 frames.], batch size: 23, lr: 1.70e-04
2022-05-07 16:10:34,803 INFO [train.py:715] (4/8) Epoch 13, batch 3800, loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02938, over 4838.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03068, over 971258.60 frames.], batch size: 25, lr: 1.70e-04
2022-05-07 16:11:11,949 INFO [train.py:715] (4/8) Epoch 13, batch 3850, loss[loss=0.1246, simple_loss=0.1991, pruned_loss=0.02505, over 4909.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03065, over 971838.35 frames.], batch size: 29, lr: 1.70e-04
2022-05-07 16:11:49,244 INFO [train.py:715] (4/8) Epoch 13, batch 3900, loss[loss=0.1334, simple_loss=0.2179, pruned_loss=0.02446, over 4887.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03062, over 971695.80 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:12:27,132 INFO [train.py:715] (4/8) Epoch 13, batch 3950, loss[loss=0.1346, simple_loss=0.2043, pruned_loss=0.03243, over 4981.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03081, over 972180.42 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:13:05,300 INFO [train.py:715] (4/8) Epoch 13, batch 4000, loss[loss=0.1337, simple_loss=0.2032, pruned_loss=0.03212, over 4912.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03104, over 973338.94 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:13:42,997 INFO [train.py:715] (4/8) Epoch 13, batch 4050, loss[loss=0.1408, simple_loss=0.2146, pruned_loss=0.03353, over 4969.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03107, over 973236.16 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:14:20,643 INFO [train.py:715] (4/8) Epoch 13, batch 4100, loss[loss=0.1774, simple_loss=0.2546, pruned_loss=0.05009, over 4974.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.03124, over 973187.82 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:14:59,186 INFO [train.py:715] (4/8) Epoch 13, batch 4150, loss[loss=0.1461, simple_loss=0.2251, pruned_loss=0.03349, over 4768.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03171, over 972313.64 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:15:36,529 INFO [train.py:715] (4/8) Epoch 13, batch 4200, loss[loss=0.1356, simple_loss=0.2222, pruned_loss=0.02454, over 4788.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03148, over 971092.91 frames.], batch size: 17, lr: 1.70e-04
2022-05-07 16:16:14,501 INFO [train.py:715] (4/8) Epoch 13, batch 4250, loss[loss=0.1595, simple_loss=0.2295, pruned_loss=0.04474, over 4934.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2105, pruned_loss=0.03215, over 971922.71 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:16:52,600 INFO [train.py:715] (4/8) Epoch 13, batch 4300, loss[loss=0.1171, simple_loss=0.1925, pruned_loss=0.02085, over 4819.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2109, pruned_loss=0.0324, over 972751.04 frames.], batch size: 26, lr: 1.70e-04
2022-05-07 16:17:30,606 INFO [train.py:715] (4/8) Epoch 13, batch 4350, loss[loss=0.1205, simple_loss=0.1935, pruned_loss=0.0238, over 4869.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2105, pruned_loss=0.03214, over 972798.86 frames.], batch size: 20, lr: 1.70e-04
2022-05-07 16:18:08,279 INFO [train.py:715] (4/8) Epoch 13, batch 4400, loss[loss=0.1392, simple_loss=0.2223, pruned_loss=0.02805, over 4917.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2109, pruned_loss=0.03217, over 972911.24 frames.], batch size: 17, lr: 1.70e-04
2022-05-07 16:18:46,444 INFO [train.py:715] (4/8) Epoch 13, batch 4450, loss[loss=0.1276, simple_loss=0.1993, pruned_loss=0.028, over 4957.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2115, pruned_loss=0.03257, over 972613.56 frames.], batch size: 35, lr: 1.70e-04
2022-05-07 16:19:25,667 INFO [train.py:715] (4/8) Epoch 13, batch 4500, loss[loss=0.1168, simple_loss=0.1896, pruned_loss=0.02198, over 4897.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03229, over 972145.13 frames.], batch size: 39, lr: 1.70e-04
2022-05-07 16:20:03,831 INFO [train.py:715] (4/8) Epoch 13, batch 4550, loss[loss=0.1606, simple_loss=0.2241, pruned_loss=0.04854, over 4806.00 frames.], tot_loss[loss=0.138, simple_loss=0.2111, pruned_loss=0.03245, over 972614.44 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:20:40,817 INFO [train.py:715] (4/8) Epoch 13, batch 4600, loss[loss=0.1271, simple_loss=0.2023, pruned_loss=0.02591, over 4967.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2103, pruned_loss=0.03229, over 971905.11 frames.], batch size: 24, lr: 1.70e-04
2022-05-07 16:21:19,533 INFO [train.py:715] (4/8) Epoch 13, batch 4650, loss[loss=0.1505, simple_loss=0.2259, pruned_loss=0.03756, over 4846.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2105, pruned_loss=0.03215, over 972437.01 frames.], batch size: 34, lr: 1.70e-04
2022-05-07 16:21:57,440 INFO [train.py:715] (4/8) Epoch 13, batch 4700, loss[loss=0.1472, simple_loss=0.2204, pruned_loss=0.03697, over 4871.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2095, pruned_loss=0.03174, over 972621.82 frames.], batch size: 32, lr: 1.70e-04
2022-05-07 16:22:35,614 INFO [train.py:715] (4/8) Epoch 13, batch 4750, loss[loss=0.1257, simple_loss=0.1902, pruned_loss=0.03058, over 4889.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2089, pruned_loss=0.03176, over 972297.58 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:23:13,886 INFO [train.py:715] (4/8) Epoch 13, batch 4800, loss[loss=0.1777, simple_loss=0.2624, pruned_loss=0.04647, over 4850.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2091, pruned_loss=0.03192, over 972517.06 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:23:53,167 INFO [train.py:715] (4/8) Epoch 13, batch 4850, loss[loss=0.1565, simple_loss=0.2184, pruned_loss=0.04732, over 4752.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2093, pruned_loss=0.03202, over 972314.99 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:24:31,308 INFO [train.py:715] (4/8) Epoch 13, batch 4900, loss[loss=0.1138, simple_loss=0.1943, pruned_loss=0.01665, over 4782.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2094, pruned_loss=0.03208, over 971146.06 frames.], batch size: 14, lr: 1.70e-04
2022-05-07 16:25:10,150 INFO [train.py:715] (4/8) Epoch 13, batch 4950, loss[loss=0.1463, simple_loss=0.2293, pruned_loss=0.03167, over 4804.00 frames.], tot_loss[loss=0.137, simple_loss=0.21, pruned_loss=0.03204, over 971698.38 frames.], batch size: 25, lr: 1.70e-04
2022-05-07 16:25:49,562 INFO [train.py:715] (4/8) Epoch 13, batch 5000, loss[loss=0.1178, simple_loss=0.1931, pruned_loss=0.02122, over 4908.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2099, pruned_loss=0.0322, over 971879.86 frames.], batch size: 23, lr: 1.70e-04
2022-05-07 16:26:28,895 INFO [train.py:715] (4/8) Epoch 13, batch 5050, loss[loss=0.1156, simple_loss=0.1847, pruned_loss=0.02324, over 4792.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2095, pruned_loss=0.03198, over 971862.48 frames.], batch size: 24, lr: 1.70e-04
2022-05-07 16:27:07,530 INFO [train.py:715] (4/8) Epoch 13, batch 5100, loss[loss=0.1224, simple_loss=0.2004, pruned_loss=0.02225, over 4977.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2094, pruned_loss=0.03163, over 972783.09 frames.], batch size: 25, lr: 1.70e-04
2022-05-07 16:27:46,963 INFO [train.py:715] (4/8) Epoch 13, batch 5150, loss[loss=0.1519, simple_loss=0.2246, pruned_loss=0.0396, over 4904.00 frames.], tot_loss[loss=0.1359, simple_loss=0.209, pruned_loss=0.03136, over 972546.86 frames.], batch size: 39, lr: 1.70e-04
2022-05-07 16:28:26,700 INFO [train.py:715] (4/8) Epoch 13, batch 5200, loss[loss=0.1555, simple_loss=0.2292, pruned_loss=0.04091, over 4791.00 frames.], tot_loss[loss=0.137, simple_loss=0.2101, pruned_loss=0.03197, over 971579.42 frames.], batch size: 17, lr: 1.70e-04
2022-05-07 16:29:06,543 INFO [train.py:715] (4/8) Epoch 13, batch 5250, loss[loss=0.1208, simple_loss=0.1896, pruned_loss=0.02595, over 4889.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03177, over 972055.65 frames.], batch size: 20, lr: 1.70e-04
2022-05-07 16:29:45,221 INFO [train.py:715] (4/8) Epoch 13, batch 5300, loss[loss=0.1539, simple_loss=0.2264, pruned_loss=0.04069, over 4964.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03115, over 971468.20 frames.], batch size: 24, lr: 1.70e-04
2022-05-07 16:30:25,370 INFO [train.py:715] (4/8) Epoch 13, batch 5350, loss[loss=0.1517, simple_loss=0.2178, pruned_loss=0.04278, over 4947.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03061, over 971541.71 frames.], batch size: 24, lr: 1.70e-04
2022-05-07 16:31:05,467 INFO [train.py:715] (4/8) Epoch 13, batch 5400, loss[loss=0.1309, simple_loss=0.2048, pruned_loss=0.0285, over 4927.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03063, over 971760.76 frames.], batch size: 23, lr: 1.70e-04
2022-05-07 16:31:45,403 INFO [train.py:715] (4/8) Epoch 13, batch 5450, loss[loss=0.1218, simple_loss=0.2053, pruned_loss=0.01911, over 4811.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03159, over 972251.49 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:32:24,981 INFO [train.py:715] (4/8) Epoch 13, batch 5500, loss[loss=0.1055, simple_loss=0.1841, pruned_loss=0.01345, over 4900.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03168, over 971965.67 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:33:04,811 INFO [train.py:715] (4/8) Epoch 13, batch 5550, loss[loss=0.126, simple_loss=0.2116, pruned_loss=0.02025, over 4864.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03169, over 972677.97 frames.], batch size: 20, lr: 1.70e-04
2022-05-07 16:33:44,058 INFO [train.py:715] (4/8) Epoch 13, batch 5600, loss[loss=0.1191, simple_loss=0.1977, pruned_loss=0.02023, over 4875.00 frames.], tot_loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.0317, over 972839.69 frames.], batch size: 22, lr: 1.70e-04
2022-05-07 16:34:23,508 INFO [train.py:715] (4/8) Epoch 13, batch 5650, loss[loss=0.1316, simple_loss=0.2109, pruned_loss=0.0262, over 4990.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2105, pruned_loss=0.03117, over 973163.67 frames.], batch size: 20, lr: 1.70e-04
2022-05-07 16:35:03,781 INFO [train.py:715] (4/8) Epoch 13, batch 5700, loss[loss=0.1164, simple_loss=0.1876, pruned_loss=0.02257, over 4987.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2105, pruned_loss=0.03111, over 972979.66 frames.], batch size: 25, lr: 1.70e-04
2022-05-07 16:35:43,884 INFO [train.py:715] (4/8) Epoch 13, batch 5750, loss[loss=0.1896, simple_loss=0.2584, pruned_loss=0.06039, over 4865.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2101, pruned_loss=0.03102, over 973455.78 frames.], batch size: 20, lr: 1.70e-04
2022-05-07 16:36:22,741 INFO [train.py:715] (4/8) Epoch 13, batch 5800, loss[loss=0.1406, simple_loss=0.2089, pruned_loss=0.03616, over 4827.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03099, over 973210.50 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:37:02,227 INFO [train.py:715] (4/8) Epoch 13, batch 5850, loss[loss=0.1425, simple_loss=0.2242, pruned_loss=0.03043, over 4810.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03118, over 972978.31 frames.], batch size: 27, lr: 1.70e-04
2022-05-07 16:37:42,368 INFO [train.py:715] (4/8) Epoch 13, batch 5900, loss[loss=0.1277, simple_loss=0.2098, pruned_loss=0.02282, over 4758.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03107, over 972617.40 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:38:21,732 INFO [train.py:715] (4/8) Epoch 13, batch 5950, loss[loss=0.1211, simple_loss=0.1984, pruned_loss=0.02193, over 4961.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03117, over 972781.23 frames.], batch size: 24, lr: 1.70e-04
2022-05-07 16:39:01,207 INFO [train.py:715] (4/8) Epoch 13, batch 6000, loss[loss=0.1345, simple_loss=0.2208, pruned_loss=0.02407, over 4909.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03083, over 973279.19 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:39:01,208 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 16:39:10,778 INFO [train.py:742] (4/8) Epoch 13, validation: loss=0.1054, simple_loss=0.1893, pruned_loss=0.01078, over 914524.00 frames.
2022-05-07 16:39:50,259 INFO [train.py:715] (4/8) Epoch 13, batch 6050, loss[loss=0.135, simple_loss=0.2078, pruned_loss=0.0311, over 4948.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03076, over 973228.88 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:40:29,775 INFO [train.py:715] (4/8) Epoch 13, batch 6100, loss[loss=0.1078, simple_loss=0.1734, pruned_loss=0.02108, over 4795.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.0313, over 973658.56 frames.], batch size: 12, lr: 1.70e-04
2022-05-07 16:41:09,343 INFO [train.py:715] (4/8) Epoch 13, batch 6150, loss[loss=0.1259, simple_loss=0.1884, pruned_loss=0.03173, over 4800.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2106, pruned_loss=0.03141, over 972854.82 frames.], batch size: 12, lr: 1.70e-04
2022-05-07 16:41:47,239 INFO [train.py:715] (4/8) Epoch 13, batch 6200, loss[loss=0.13, simple_loss=0.2099, pruned_loss=0.02504, over 4803.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03093, over 972539.77 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:42:26,318 INFO [train.py:715] (4/8) Epoch 13, batch 6250, loss[loss=0.1555, simple_loss=0.232, pruned_loss=0.03951, over 4782.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03141, over 972307.27 frames.], batch size: 14, lr: 1.70e-04
2022-05-07 16:43:05,825 INFO [train.py:715] (4/8) Epoch 13, batch 6300, loss[loss=0.148, simple_loss=0.2208, pruned_loss=0.03755, over 4975.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03151, over 973042.33 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:43:44,430 INFO [train.py:715] (4/8) Epoch 13, batch 6350, loss[loss=0.1395, simple_loss=0.2004, pruned_loss=0.03927, over 4746.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03156, over 973084.27 frames.], batch size: 16, lr: 1.70e-04
2022-05-07 16:44:24,248 INFO [train.py:715] (4/8) Epoch 13, batch 6400, loss[loss=0.1312, simple_loss=0.2094, pruned_loss=0.02653, over 4835.00 frames.], tot_loss[loss=0.136, simple_loss=0.2089, pruned_loss=0.03157, over 972506.06 frames.], batch size: 30, lr: 1.70e-04
2022-05-07 16:45:04,065 INFO [train.py:715] (4/8) Epoch 13, batch 6450, loss[loss=0.1332, simple_loss=0.2205, pruned_loss=0.023, over 4876.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2087, pruned_loss=0.03115, over 972558.74 frames.], batch size: 22, lr: 1.70e-04
2022-05-07 16:45:44,160 INFO [train.py:715] (4/8) Epoch 13, batch 6500, loss[loss=0.1402, simple_loss=0.2146, pruned_loss=0.03292, over 4967.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.03152, over 972737.11 frames.], batch size: 31, lr: 1.70e-04
2022-05-07 16:46:23,330 INFO [train.py:715] (4/8) Epoch 13, batch 6550, loss[loss=0.1269, simple_loss=0.2084, pruned_loss=0.02272, over 4881.00 frames.], tot_loss[loss=0.1358, simple_loss=0.209, pruned_loss=0.03129, over 973077.83 frames.], batch size: 22, lr: 1.70e-04
2022-05-07 16:47:02,666 INFO [train.py:715] (4/8) Epoch 13, batch 6600, loss[loss=0.1534, simple_loss=0.2113, pruned_loss=0.04778, over 4919.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2101, pruned_loss=0.03167, over 973378.24 frames.], batch size: 17, lr: 1.70e-04
2022-05-07 16:47:42,043 INFO [train.py:715] (4/8) Epoch 13, batch 6650, loss[loss=0.1291, simple_loss=0.2023, pruned_loss=0.02791, over 4764.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03201, over 972501.98 frames.], batch size: 19, lr: 1.70e-04
2022-05-07 16:48:20,276 INFO [train.py:715] (4/8) Epoch 13, batch 6700, loss[loss=0.1202, simple_loss=0.1999, pruned_loss=0.02023, over 4804.00 frames.], tot_loss[loss=0.138, simple_loss=0.2115, pruned_loss=0.03227, over 973014.79 frames.], batch size: 24, lr: 1.70e-04
2022-05-07 16:48:58,717 INFO [train.py:715] (4/8) Epoch 13, batch 6750, loss[loss=0.1324, simple_loss=0.2121, pruned_loss=0.02636, over 4788.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2113, pruned_loss=0.0322, over 972908.14 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:49:37,983 INFO [train.py:715] (4/8) Epoch 13, batch 6800, loss[loss=0.127, simple_loss=0.1975, pruned_loss=0.02829, over 4691.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2109, pruned_loss=0.03176, over 973150.53 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:50:17,432 INFO [train.py:715] (4/8) Epoch 13, batch 6850, loss[loss=0.1373, simple_loss=0.2063, pruned_loss=0.03413, over 4888.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03139, over 973533.77 frames.], batch size: 22, lr: 1.70e-04
2022-05-07 16:50:55,365 INFO [train.py:715] (4/8) Epoch 13, batch 6900, loss[loss=0.1519, simple_loss=0.2219, pruned_loss=0.04091, over 4848.00 frames.], tot_loss[loss=0.137, simple_loss=0.2111, pruned_loss=0.03142, over 972298.27 frames.], batch size: 32, lr: 1.70e-04
2022-05-07 16:51:33,403 INFO [train.py:715] (4/8) Epoch 13, batch 6950, loss[loss=0.1558, simple_loss=0.2289, pruned_loss=0.04136, over 4970.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2113, pruned_loss=0.03168, over 973239.27 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:52:12,640 INFO [train.py:715] (4/8) Epoch 13, batch 7000, loss[loss=0.1476, simple_loss=0.2217, pruned_loss=0.03677, over 4700.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2108, pruned_loss=0.03148, over 972817.51 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:52:51,283 INFO [train.py:715] (4/8) Epoch 13, batch 7050, loss[loss=0.1252, simple_loss=0.1991, pruned_loss=0.02568, over 4947.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03136, over 972792.71 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 16:53:30,247 INFO [train.py:715] (4/8) Epoch 13, batch 7100, loss[loss=0.1454, simple_loss=0.2129, pruned_loss=0.039, over 4855.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03122, over 972135.38 frames.], batch size: 32, lr: 1.70e-04
2022-05-07 16:54:09,706 INFO [train.py:715] (4/8) Epoch 13, batch 7150, loss[loss=0.1199, simple_loss=0.1912, pruned_loss=0.0243, over 4849.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03155, over 971811.06 frames.], batch size: 30, lr: 1.70e-04
2022-05-07 16:54:49,407 INFO [train.py:715] (4/8) Epoch 13, batch 7200, loss[loss=0.1455, simple_loss=0.2156, pruned_loss=0.03769, over 4854.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03116, over 972028.92 frames.], batch size: 38, lr: 1.70e-04
2022-05-07 16:55:27,555 INFO [train.py:715] (4/8) Epoch 13, batch 7250, loss[loss=0.1305, simple_loss=0.2028, pruned_loss=0.02904, over 4990.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03142, over 971797.42 frames.], batch size: 25, lr: 1.70e-04
2022-05-07 16:56:05,827 INFO [train.py:715] (4/8) Epoch 13, batch 7300, loss[loss=0.1344, simple_loss=0.2126, pruned_loss=0.02816, over 4777.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03188, over 972212.30 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:56:45,077 INFO [train.py:715] (4/8) Epoch 13, batch 7350, loss[loss=0.1119, simple_loss=0.1919, pruned_loss=0.016, over 4753.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2113, pruned_loss=0.03219, over 972918.65 frames.], batch size: 12, lr: 1.70e-04
2022-05-07 16:57:23,718 INFO [train.py:715] (4/8) Epoch 13, batch 7400, loss[loss=0.1212, simple_loss=0.2, pruned_loss=0.02125, over 4824.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2118, pruned_loss=0.0323, over 972992.60 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 16:58:01,544 INFO [train.py:715] (4/8) Epoch 13, batch 7450, loss[loss=0.1376, simple_loss=0.2117, pruned_loss=0.0318, over 4910.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03171, over 973117.07 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 16:58:40,995 INFO [train.py:715] (4/8) Epoch 13, batch 7500, loss[loss=0.1211, simple_loss=0.1938, pruned_loss=0.02422, over 4833.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03201, over 972572.27 frames.], batch size: 26, lr: 1.70e-04
2022-05-07 16:59:20,237 INFO [train.py:715] (4/8) Epoch 13, batch 7550, loss[loss=0.1149, simple_loss=0.1942, pruned_loss=0.01773, over 4881.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03149, over 972528.94 frames.], batch size: 22, lr: 1.70e-04
2022-05-07 16:59:57,839 INFO [train.py:715] (4/8) Epoch 13, batch 7600, loss[loss=0.1518, simple_loss=0.2263, pruned_loss=0.03869, over 4786.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03113, over 972552.64 frames.], batch size: 12, lr: 1.70e-04
2022-05-07 17:00:36,715 INFO [train.py:715] (4/8) Epoch 13, batch 7650, loss[loss=0.12, simple_loss=0.1957, pruned_loss=0.02212, over 4794.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03132, over 972299.22 frames.], batch size: 24, lr: 1.70e-04
2022-05-07 17:01:15,688 INFO [train.py:715] (4/8) Epoch 13, batch 7700, loss[loss=0.1286, simple_loss=0.1955, pruned_loss=0.03088, over 4780.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2105, pruned_loss=0.03128, over 972784.62 frames.], batch size: 14, lr: 1.70e-04
2022-05-07 17:01:54,652 INFO [train.py:715] (4/8) Epoch 13, batch 7750, loss[loss=0.1428, simple_loss=0.2199, pruned_loss=0.03283, over 4958.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2112, pruned_loss=0.03155, over 972885.75 frames.], batch size: 21, lr: 1.70e-04
2022-05-07 17:02:32,579 INFO [train.py:715] (4/8) Epoch 13, batch 7800, loss[loss=0.1598, simple_loss=0.23, pruned_loss=0.04482, over 4900.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2104, pruned_loss=0.0309, over 973190.06 frames.], batch size: 22, lr: 1.70e-04
2022-05-07 17:03:11,063 INFO [train.py:715] (4/8) Epoch 13, batch 7850, loss[loss=0.1314, simple_loss=0.2106, pruned_loss=0.02605, over 4885.00 frames.], tot_loss[loss=0.1357, simple_loss=0.21, pruned_loss=0.03073, over 972630.18 frames.], batch size: 22, lr: 1.70e-04
2022-05-07 17:03:50,704 INFO [train.py:715] (4/8) Epoch 13, batch 7900, loss[loss=0.1456, simple_loss=0.2255, pruned_loss=0.03284, over 4960.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2101, pruned_loss=0.03083, over 972004.11 frames.], batch size: 15, lr: 1.70e-04
2022-05-07 17:04:28,754 INFO [train.py:715] (4/8) Epoch 13, batch 7950, loss[loss=0.1591, simple_loss=0.2425, pruned_loss=0.03787, over 4895.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03102, over 971429.99 frames.], batch size: 22, lr: 1.70e-04
2022-05-07 17:05:07,216 INFO [train.py:715] (4/8) Epoch 13, batch 8000, loss[loss=0.1688, simple_loss=0.2395, pruned_loss=0.04906, over 4772.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.0309, over 971044.78 frames.], batch size: 18, lr: 1.70e-04
2022-05-07 17:05:45,984 INFO [train.py:715] (4/8) Epoch 13, batch 8050, loss[loss=0.127, simple_loss=0.2026, pruned_loss=0.02567, over 4841.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03088, over 971331.66 frames.], batch size: 13, lr: 1.70e-04
2022-05-07 17:06:24,536 INFO [train.py:715] (4/8) Epoch 13, batch 8100, loss[loss=0.1514, simple_loss=0.2224, pruned_loss=0.04018, over 4775.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03122, over 971962.56 frames.], batch size: 17, lr: 1.69e-04
2022-05-07 17:07:02,516 INFO [train.py:715] (4/8) Epoch 13, batch 8150, loss[loss=0.1264, simple_loss=0.2027, pruned_loss=0.025, over 4866.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2099, pruned_loss=0.03159, over 971703.07 frames.], batch size: 20, lr: 1.69e-04
2022-05-07 17:07:40,994 INFO [train.py:715] (4/8) Epoch 13, batch 8200, loss[loss=0.1473, simple_loss=0.2182, pruned_loss=0.03826, over 4915.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03161, over 972291.30 frames.], batch size: 23, lr: 1.69e-04
2022-05-07 17:08:20,204 INFO [train.py:715] (4/8) Epoch 13, batch 8250, loss[loss=0.1317, simple_loss=0.2093, pruned_loss=0.02707, over 4983.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03168, over 972192.94 frames.], batch size: 25, lr: 1.69e-04
2022-05-07 17:08:58,110 INFO [train.py:715] (4/8) Epoch 13, batch 8300, loss[loss=0.1259, simple_loss=0.2106, pruned_loss=0.02056, over 4981.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03155, over 972610.22 frames.], batch size: 25, lr: 1.69e-04
2022-05-07 17:09:36,543 INFO [train.py:715] (4/8) Epoch 13, batch 8350, loss[loss=0.1354, simple_loss=0.2047, pruned_loss=0.03301, over 4933.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2091, pruned_loss=0.03114, over 973460.51 frames.], batch size: 29, lr: 1.69e-04
2022-05-07 17:10:15,703 INFO [train.py:715] (4/8) Epoch 13, batch 8400, loss[loss=0.1539, simple_loss=0.2293, pruned_loss=0.03925, over 4762.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2088, pruned_loss=0.03108, over 972609.66 frames.], batch size: 16, lr: 1.69e-04
2022-05-07 17:10:54,563 INFO [train.py:715] (4/8) Epoch 13, batch 8450, loss[loss=0.1407, simple_loss=0.2199, pruned_loss=0.03078, over 4858.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2089, pruned_loss=0.0314, over 972260.92 frames.], batch size: 20, lr: 1.69e-04
2022-05-07 17:11:32,556 INFO [train.py:715] (4/8) Epoch 13, batch 8500, loss[loss=0.1563, simple_loss=0.2188, pruned_loss=0.04687, over 4921.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2089, pruned_loss=0.03129, over 971702.31 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:12:11,696 INFO [train.py:715] (4/8) Epoch 13, batch 8550, loss[loss=0.1394, simple_loss=0.2158, pruned_loss=0.03153, over 4985.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03083, over 971767.32 frames.], batch size: 28, lr: 1.69e-04
2022-05-07 17:12:50,648 INFO [train.py:715] (4/8) Epoch 13, batch 8600, loss[loss=0.1306, simple_loss=0.2016, pruned_loss=0.02976, over 4747.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03074, over 971882.16 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 17:13:28,884 INFO [train.py:715] (4/8) Epoch 13, batch 8650, loss[loss=0.1478, simple_loss=0.2257, pruned_loss=0.03492, over 4979.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03049, over 972317.30 frames.], batch size: 35, lr: 1.69e-04
2022-05-07 17:14:07,227 INFO [train.py:715] (4/8) Epoch 13, batch 8700, loss[loss=0.1109, simple_loss=0.1833, pruned_loss=0.01927, over 4969.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03088, over 971570.87 frames.], batch size: 25, lr: 1.69e-04
2022-05-07 17:14:45,869 INFO [train.py:715] (4/8) Epoch 13, batch 8750, loss[loss=0.1335, simple_loss=0.2055, pruned_loss=0.03071, over 4828.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03097, over 971494.25 frames.], batch size: 13, lr: 1.69e-04
2022-05-07 17:15:24,586 INFO [train.py:715] (4/8) Epoch 13, batch 8800, loss[loss=0.1104, simple_loss=0.1856, pruned_loss=0.01765, over 4985.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03115, over 971511.96 frames.], batch size: 39, lr: 1.69e-04
2022-05-07 17:16:02,887 INFO [train.py:715] (4/8) Epoch 13, batch 8850, loss[loss=0.0959, simple_loss=0.1615, pruned_loss=0.01513, over 4787.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.0309, over 971625.38 frames.], batch size: 12, lr: 1.69e-04
2022-05-07 17:16:40,975 INFO [train.py:715] (4/8) Epoch 13, batch 8900, loss[loss=0.1373, simple_loss=0.208, pruned_loss=0.03331, over 4889.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03078, over 972367.70 frames.], batch size: 22, lr: 1.69e-04
2022-05-07 17:17:19,700 INFO [train.py:715] (4/8) Epoch 13, batch 8950, loss[loss=0.102, simple_loss=0.1758, pruned_loss=0.01412, over 4859.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03111, over 971718.39 frames.], batch size: 13, lr: 1.69e-04
2022-05-07 17:17:57,827 INFO [train.py:715] (4/8) Epoch 13, batch 9000, loss[loss=0.1429, simple_loss=0.2193, pruned_loss=0.03321, over 4842.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.0314, over 971576.05 frames.], batch size: 32, lr: 1.69e-04
2022-05-07 17:17:57,828 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 17:18:07,451 INFO [train.py:742] (4/8) Epoch 13, validation: loss=0.1055, simple_loss=0.1893, pruned_loss=0.01084, over 914524.00 frames.
2022-05-07 17:18:45,502 INFO [train.py:715] (4/8) Epoch 13, batch 9050, loss[loss=0.1674, simple_loss=0.2508, pruned_loss=0.04203, over 4833.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03141, over 972320.22 frames.], batch size: 26, lr: 1.69e-04
2022-05-07 17:19:23,913 INFO [train.py:715] (4/8) Epoch 13, batch 9100, loss[loss=0.1266, simple_loss=0.2019, pruned_loss=0.0256, over 4859.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03145, over 971993.14 frames.], batch size: 20, lr: 1.69e-04
2022-05-07 17:20:03,101 INFO [train.py:715] (4/8) Epoch 13, batch 9150, loss[loss=0.1385, simple_loss=0.2114, pruned_loss=0.03283, over 4814.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03177, over 972968.65 frames.], batch size: 25, lr: 1.69e-04
2022-05-07 17:20:42,097 INFO [train.py:715] (4/8) Epoch 13, batch 9200, loss[loss=0.1353, simple_loss=0.2181, pruned_loss=0.02621, over 4814.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03129, over 972404.66 frames.], batch size: 27, lr: 1.69e-04
2022-05-07 17:21:20,013 INFO [train.py:715] (4/8) Epoch 13, batch 9250, loss[loss=0.1352, simple_loss=0.199, pruned_loss=0.03565, over 4765.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03154, over 972426.24 frames.], batch size: 12, lr: 1.69e-04
2022-05-07 17:21:58,915 INFO [train.py:715] (4/8) Epoch 13, batch 9300, loss[loss=0.09884, simple_loss=0.1718, pruned_loss=0.01294, over 4752.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03154, over 973331.73 frames.], batch size: 19, lr: 1.69e-04
2022-05-07 17:22:37,767 INFO [train.py:715] (4/8) Epoch 13, batch 9350, loss[loss=0.1587, simple_loss=0.2445, pruned_loss=0.03644, over 4767.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03176, over 972866.19 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:23:15,581 INFO [train.py:715] (4/8) Epoch 13, batch 9400, loss[loss=0.123, simple_loss=0.2008, pruned_loss=0.02257, over 4984.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2093, pruned_loss=0.03151, over 972309.09 frames.], batch size: 25, lr: 1.69e-04
2022-05-07 17:23:54,035 INFO [train.py:715] (4/8) Epoch 13, batch 9450, loss[loss=0.1139, simple_loss=0.1933, pruned_loss=0.01725, over 4952.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03131, over 973099.41 frames.], batch size: 24, lr: 1.69e-04
2022-05-07 17:24:32,855 INFO [train.py:715] (4/8) Epoch 13, batch 9500, loss[loss=0.1422, simple_loss=0.2109, pruned_loss=0.03679, over 4793.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03132, over 972808.18 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 17:25:11,109 INFO [train.py:715] (4/8) Epoch 13, batch 9550, loss[loss=0.1264, simple_loss=0.1992, pruned_loss=0.0268, over 4806.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03151, over 972445.98 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 17:25:49,081 INFO [train.py:715] (4/8) Epoch 13, batch 9600, loss[loss=0.1149, simple_loss=0.1878, pruned_loss=0.02099, over 4820.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03162, over 972454.47 frames.], batch size: 27, lr: 1.69e-04
2022-05-07 17:26:28,024 INFO [train.py:715] (4/8) Epoch 13, batch 9650, loss[loss=0.1113, simple_loss=0.1888, pruned_loss=0.01689, over 4925.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2108, pruned_loss=0.03202, over 971925.87 frames.], batch size: 29, lr: 1.69e-04
2022-05-07 17:27:06,437 INFO [train.py:715] (4/8) Epoch 13, batch 9700, loss[loss=0.1296, simple_loss=0.1991, pruned_loss=0.03005, over 4751.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2107, pruned_loss=0.03212, over 971992.50 frames.], batch size: 19, lr: 1.69e-04
2022-05-07 17:27:44,999 INFO [train.py:715] (4/8) Epoch 13, batch 9750, loss[loss=0.1575, simple_loss=0.2344, pruned_loss=0.04029, over 4912.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2106, pruned_loss=0.03189, over 972564.90 frames.], batch size: 17, lr: 1.69e-04
2022-05-07 17:28:23,844 INFO [train.py:715] (4/8) Epoch 13, batch 9800, loss[loss=0.1377, simple_loss=0.2158, pruned_loss=0.02975, over 4976.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2105, pruned_loss=0.03164, over 972526.28 frames.], batch size: 24, lr: 1.69e-04
2022-05-07 17:29:03,035 INFO [train.py:715] (4/8) Epoch 13, batch 9850, loss[loss=0.1421, simple_loss=0.2095, pruned_loss=0.03737, over 4850.00 frames.], tot_loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.03168, over 972609.63 frames.], batch size: 16, lr: 1.69e-04
2022-05-07 17:29:41,587 INFO [train.py:715] (4/8) Epoch 13, batch 9900, loss[loss=0.1311, simple_loss=0.1988, pruned_loss=0.0317, over 4860.00 frames.], tot_loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.03175, over 972406.65 frames.], batch size: 20, lr: 1.69e-04
2022-05-07 17:30:19,824 INFO [train.py:715] (4/8) Epoch 13, batch 9950, loss[loss=0.1327, simple_loss=0.2183, pruned_loss=0.0236, over 4804.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2106, pruned_loss=0.03127, over 972311.80 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 17:30:58,618 INFO [train.py:715] (4/8) Epoch 13, batch 10000, loss[loss=0.1303, simple_loss=0.2023, pruned_loss=0.02916, over 4800.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.0309, over 972668.83 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 17:31:37,789 INFO [train.py:715] (4/8) Epoch 13, batch 10050, loss[loss=0.1463, simple_loss=0.2296, pruned_loss=0.0315, over 4769.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2105, pruned_loss=0.03112, over 972649.80 frames.], batch size: 19, lr: 1.69e-04
2022-05-07 17:32:16,725 INFO [train.py:715] (4/8) Epoch 13, batch 10100, loss[loss=0.1408, simple_loss=0.2232, pruned_loss=0.02923, over 4856.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03093, over 972908.62 frames.], batch size: 30, lr: 1.69e-04
2022-05-07 17:32:54,966 INFO [train.py:715] (4/8) Epoch 13, batch 10150, loss[loss=0.1649, simple_loss=0.2319, pruned_loss=0.04902, over 4744.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03119, over 972998.96 frames.], batch size: 16, lr: 1.69e-04
2022-05-07 17:33:34,000 INFO [train.py:715] (4/8) Epoch 13, batch 10200, loss[loss=0.1545, simple_loss=0.2185, pruned_loss=0.04526, over 4837.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2091, pruned_loss=0.03113, over 972818.86 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 17:34:13,396 INFO [train.py:715] (4/8) Epoch 13, batch 10250, loss[loss=0.104, simple_loss=0.184, pruned_loss=0.01205, over 4785.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03054, over 972316.93 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:34:52,084 INFO [train.py:715] (4/8) Epoch 13, batch 10300, loss[loss=0.1367, simple_loss=0.2135, pruned_loss=0.02995, over 4813.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02985, over 972040.31 frames.], batch size: 25, lr: 1.69e-04
2022-05-07 17:35:31,129 INFO [train.py:715] (4/8) Epoch 13, batch 10350, loss[loss=0.1482, simple_loss=0.2292, pruned_loss=0.03366, over 4862.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03015, over 972482.02 frames.], batch size: 20, lr: 1.69e-04
2022-05-07 17:36:10,306 INFO [train.py:715] (4/8) Epoch 13, batch 10400, loss[loss=0.1378, simple_loss=0.2034, pruned_loss=0.03609, over 4916.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03033, over 972408.96 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:36:49,251 INFO [train.py:715] (4/8) Epoch 13, batch 10450, loss[loss=0.1574, simple_loss=0.2228, pruned_loss=0.04598, over 4885.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2081, pruned_loss=0.03065, over 971987.20 frames.], batch size: 16, lr: 1.69e-04
2022-05-07 17:37:26,679 INFO [train.py:715] (4/8) Epoch 13, batch 10500, loss[loss=0.1364, simple_loss=0.2121, pruned_loss=0.03031, over 4926.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03096, over 971843.09 frames.], batch size: 29, lr: 1.69e-04
2022-05-07 17:38:05,567 INFO [train.py:715] (4/8) Epoch 13, batch 10550, loss[loss=0.1383, simple_loss=0.217, pruned_loss=0.02979, over 4806.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03023, over 971034.64 frames.], batch size: 25, lr: 1.69e-04
2022-05-07 17:38:44,487 INFO [train.py:715] (4/8) Epoch 13, batch 10600, loss[loss=0.1579, simple_loss=0.2266, pruned_loss=0.04459, over 4845.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.03018, over 972136.27 frames.], batch size: 32, lr: 1.69e-04
2022-05-07 17:39:22,595 INFO [train.py:715] (4/8) Epoch 13, batch 10650, loss[loss=0.1376, simple_loss=0.2128, pruned_loss=0.03123, over 4921.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03072, over 971822.23 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:40:01,764 INFO [train.py:715] (4/8) Epoch 13, batch 10700, loss[loss=0.1223, simple_loss=0.1912, pruned_loss=0.02671, over 4991.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03058, over 972325.07 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 17:40:41,063 INFO [train.py:715] (4/8) Epoch 13, batch 10750, loss[loss=0.1647, simple_loss=0.2401, pruned_loss=0.04465, over 4824.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03064, over 971535.33 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 17:41:19,860 INFO [train.py:715] (4/8) Epoch 13, batch 10800, loss[loss=0.1863, simple_loss=0.2411, pruned_loss=0.06577, over 4808.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.0313, over 971954.77 frames.], batch size: 12, lr: 1.69e-04
2022-05-07 17:41:57,879 INFO [train.py:715] (4/8) Epoch 13, batch 10850, loss[loss=0.1244, simple_loss=0.1954, pruned_loss=0.02669, over 4791.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03132, over 971764.78 frames.], batch size: 12, lr: 1.69e-04
2022-05-07 17:42:37,034 INFO [train.py:715] (4/8) Epoch 13, batch 10900, loss[loss=0.1535, simple_loss=0.2226, pruned_loss=0.04224, over 4938.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2103, pruned_loss=0.03175, over 971745.46 frames.], batch size: 23, lr: 1.69e-04
2022-05-07 17:43:16,893 INFO [train.py:715] (4/8) Epoch 13, batch 10950, loss[loss=0.1447, simple_loss=0.2229, pruned_loss=0.03323, over 4769.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03139, over 971558.07 frames.], batch size: 17, lr: 1.69e-04
2022-05-07 17:43:56,320 INFO [train.py:715] (4/8) Epoch 13, batch 11000, loss[loss=0.1173, simple_loss=0.1852, pruned_loss=0.0247, over 4833.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.03122, over 971559.72 frames.], batch size: 30, lr: 1.69e-04
2022-05-07 17:44:34,954 INFO [train.py:715] (4/8) Epoch 13, batch 11050, loss[loss=0.139, simple_loss=0.2103, pruned_loss=0.03383, over 4950.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03078, over 971087.61 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 17:45:14,251 INFO [train.py:715] (4/8) Epoch 13, batch 11100, loss[loss=0.1242, simple_loss=0.1968, pruned_loss=0.02575, over 4818.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03072, over 971322.79 frames.], batch size: 27, lr: 1.69e-04
2022-05-07 17:45:53,237 INFO [train.py:715] (4/8) Epoch 13, batch 11150, loss[loss=0.143, simple_loss=0.2081, pruned_loss=0.03899, over 4968.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03038, over 972430.25 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 17:46:30,991 INFO [train.py:715] (4/8) Epoch 13, batch 11200, loss[loss=0.13, simple_loss=0.2105, pruned_loss=0.02472, over 4930.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03032, over 972015.99 frames.], batch size: 23, lr: 1.69e-04
2022-05-07 17:47:09,193 INFO [train.py:715] (4/8) Epoch 13, batch 11250, loss[loss=0.1371, simple_loss=0.2144, pruned_loss=0.02991, over 4861.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03001, over 972561.78 frames.], batch size: 16, lr: 1.69e-04
2022-05-07 17:47:48,157 INFO [train.py:715] (4/8) Epoch 13, batch 11300, loss[loss=0.1384, simple_loss=0.2164, pruned_loss=0.03014, over 4980.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03071, over 971802.46 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 17:48:27,087 INFO [train.py:715] (4/8) Epoch 13, batch 11350, loss[loss=0.1099, simple_loss=0.1848, pruned_loss=0.01751, over 4798.00 frames.], tot_loss[loss=0.137, simple_loss=0.2101, pruned_loss=0.03195, over 972152.87 frames.], batch size: 24, lr: 1.69e-04
2022-05-07 17:49:05,291 INFO [train.py:715] (4/8) Epoch 13, batch 11400, loss[loss=0.1308, simple_loss=0.1966, pruned_loss=0.03257, over 4692.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2098, pruned_loss=0.03163, over 973085.81 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 17:49:44,157 INFO [train.py:715] (4/8) Epoch 13, batch 11450, loss[loss=0.1323, simple_loss=0.2104, pruned_loss=0.02711, over 4876.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2105, pruned_loss=0.03194, over 972162.73 frames.], batch size: 16, lr: 1.69e-04
2022-05-07 17:50:25,719 INFO [train.py:715] (4/8) Epoch 13, batch 11500, loss[loss=0.1268, simple_loss=0.2018, pruned_loss=0.02593, over 4741.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.0316, over 972272.53 frames.], batch size: 16, lr: 1.69e-04
2022-05-07 17:51:03,649 INFO [train.py:715] (4/8) Epoch 13, batch 11550, loss[loss=0.1194, simple_loss=0.1994, pruned_loss=0.01975, over 4813.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2096, pruned_loss=0.03158, over 971509.21 frames.], batch size: 26, lr: 1.69e-04
2022-05-07 17:51:42,316 INFO [train.py:715] (4/8) Epoch 13, batch 11600, loss[loss=0.1279, simple_loss=0.2061, pruned_loss=0.02486, over 4795.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.0317, over 971642.16 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:52:21,600 INFO [train.py:715] (4/8) Epoch 13, batch 11650, loss[loss=0.1504, simple_loss=0.2165, pruned_loss=0.04218, over 4967.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03086, over 971991.17 frames.], batch size: 35, lr: 1.69e-04
2022-05-07 17:53:00,310 INFO [train.py:715] (4/8) Epoch 13, batch 11700, loss[loss=0.1339, simple_loss=0.2013, pruned_loss=0.03323, over 4790.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03072, over 971578.12 frames.], batch size: 17, lr: 1.69e-04
2022-05-07 17:53:38,278 INFO [train.py:715] (4/8) Epoch 13, batch 11750, loss[loss=0.1066, simple_loss=0.177, pruned_loss=0.0181, over 4926.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03091, over 972081.75 frames.], batch size: 23, lr: 1.69e-04
2022-05-07 17:54:16,754 INFO [train.py:715] (4/8) Epoch 13, batch 11800, loss[loss=0.11, simple_loss=0.1881, pruned_loss=0.01597, over 4815.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03136, over 972003.88 frames.], batch size: 27, lr: 1.69e-04
2022-05-07 17:54:55,480 INFO [train.py:715] (4/8) Epoch 13, batch 11850, loss[loss=0.1237, simple_loss=0.1948, pruned_loss=0.02628, over 4917.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03129, over 972072.88 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:55:32,888 INFO [train.py:715] (4/8) Epoch 13, batch 11900, loss[loss=0.136, simple_loss=0.2123, pruned_loss=0.02985, over 4890.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03138, over 971091.55 frames.], batch size: 22, lr: 1.69e-04
2022-05-07 17:56:11,546 INFO [train.py:715] (4/8) Epoch 13, batch 11950, loss[loss=0.1496, simple_loss=0.2326, pruned_loss=0.03327, over 4930.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2102, pruned_loss=0.03161, over 971747.53 frames.], batch size: 23, lr: 1.69e-04
2022-05-07 17:56:50,611 INFO [train.py:715] (4/8) Epoch 13, batch 12000, loss[loss=0.11, simple_loss=0.1809, pruned_loss=0.01953, over 4778.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03177, over 971837.13 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 17:56:50,612 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 17:57:00,356 INFO [train.py:742] (4/8) Epoch 13, validation: loss=0.1055, simple_loss=0.1893, pruned_loss=0.01081, over 914524.00 frames.
2022-05-07 17:57:40,026 INFO [train.py:715] (4/8) Epoch 13, batch 12050, loss[loss=0.1223, simple_loss=0.1964, pruned_loss=0.02405, over 4940.00 frames.], tot_loss[loss=0.1377, simple_loss=0.2115, pruned_loss=0.03198, over 972175.02 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 17:58:18,318 INFO [train.py:715] (4/8) Epoch 13, batch 12100, loss[loss=0.1418, simple_loss=0.2214, pruned_loss=0.03106, over 4761.00 frames.], tot_loss[loss=0.1381, simple_loss=0.2122, pruned_loss=0.03201, over 972236.98 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 17:58:56,073 INFO [train.py:715] (4/8) Epoch 13, batch 12150, loss[loss=0.1164, simple_loss=0.196, pruned_loss=0.01834, over 4702.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2123, pruned_loss=0.03213, over 971917.39 frames.], batch size: 15, lr: 1.69e-04
2022-05-07 17:59:34,973 INFO [train.py:715] (4/8) Epoch 13, batch 12200, loss[loss=0.1431, simple_loss=0.2197, pruned_loss=0.03327, over 4872.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2122, pruned_loss=0.03218, over 972659.37 frames.], batch size: 22, lr: 1.69e-04
2022-05-07 18:00:13,890 INFO [train.py:715] (4/8) Epoch 13, batch 12250, loss[loss=0.1345, simple_loss=0.2131, pruned_loss=0.02802, over 4922.00 frames.], tot_loss[loss=0.1378, simple_loss=0.2116, pruned_loss=0.03198, over 973246.20 frames.], batch size: 23, lr: 1.69e-04
2022-05-07 18:00:52,460 INFO [train.py:715] (4/8) Epoch 13, batch 12300, loss[loss=0.1233, simple_loss=0.2014, pruned_loss=0.02256, over 4822.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2112, pruned_loss=0.03157, over 973095.52 frames.], batch size: 26, lr: 1.69e-04
2022-05-07 18:01:30,137 INFO [train.py:715] (4/8) Epoch 13, batch 12350, loss[loss=0.122, simple_loss=0.1906, pruned_loss=0.02672, over 4800.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.03141, over 973084.24 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 18:02:09,067 INFO [train.py:715] (4/8) Epoch 13, batch 12400, loss[loss=0.1474, simple_loss=0.2146, pruned_loss=0.04008, over 4888.00 frames.], tot_loss[loss=0.137, simple_loss=0.211, pruned_loss=0.03146, over 972925.38 frames.], batch size: 19, lr: 1.69e-04
2022-05-07 18:02:47,459 INFO [train.py:715] (4/8) Epoch 13, batch 12450, loss[loss=0.1058, simple_loss=0.1814, pruned_loss=0.01509, over 4970.00 frames.], tot_loss[loss=0.136, simple_loss=0.2101, pruned_loss=0.03093, over 972224.88 frames.], batch size: 21, lr: 1.69e-04
2022-05-07 18:03:24,474 INFO [train.py:715] (4/8) Epoch 13, batch 12500, loss[loss=0.1241, simple_loss=0.2028, pruned_loss=0.0227, over 4982.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03144, over 972900.33 frames.], batch size: 35, lr: 1.69e-04
2022-05-07 18:04:03,261 INFO [train.py:715] (4/8) Epoch 13, batch 12550, loss[loss=0.1253, simple_loss=0.1967, pruned_loss=0.02702, over 4650.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2112, pruned_loss=0.03187, over 972172.33 frames.], batch size: 13, lr: 1.69e-04
2022-05-07 18:04:41,886 INFO [train.py:715] (4/8) Epoch 13, batch 12600, loss[loss=0.1649, simple_loss=0.2343, pruned_loss=0.04775, over 4838.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03218, over 972159.68 frames.], batch size: 30, lr: 1.69e-04
2022-05-07 18:05:20,411 INFO [train.py:715] (4/8) Epoch 13, batch 12650, loss[loss=0.149, simple_loss=0.2108, pruned_loss=0.04353, over 4835.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2109, pruned_loss=0.03177, over 972086.43 frames.], batch size: 30, lr: 1.69e-04
2022-05-07 18:05:58,206 INFO [train.py:715] (4/8) Epoch 13, batch 12700, loss[loss=0.1908, simple_loss=0.2504, pruned_loss=0.06559, over 4839.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2104, pruned_loss=0.03162, over 972398.40 frames.], batch size: 30, lr: 1.69e-04
2022-05-07 18:06:37,495 INFO [train.py:715] (4/8) Epoch 13, batch 12750, loss[loss=0.1228, simple_loss=0.1949, pruned_loss=0.02528, over 4658.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03084, over 972504.80 frames.], batch size: 13, lr: 1.69e-04
2022-05-07 18:07:16,116 INFO [train.py:715] (4/8) Epoch 13, batch 12800, loss[loss=0.1443, simple_loss=0.2126, pruned_loss=0.03807, over 4929.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03117, over 972461.61 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 18:07:53,800 INFO [train.py:715] (4/8) Epoch 13, batch 12850, loss[loss=0.1451, simple_loss=0.2228, pruned_loss=0.03373, over 4902.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03065, over 971986.32 frames.], batch size: 19, lr: 1.69e-04
2022-05-07 18:08:32,303 INFO [train.py:715] (4/8) Epoch 13, batch 12900, loss[loss=0.1225, simple_loss=0.1986, pruned_loss=0.02322, over 4899.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03056, over 972432.36 frames.], batch size: 19, lr: 1.69e-04
2022-05-07 18:09:10,902 INFO [train.py:715] (4/8) Epoch 13, batch 12950, loss[loss=0.1218, simple_loss=0.1944, pruned_loss=0.02457, over 4880.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03038, over 972890.92 frames.], batch size: 16, lr: 1.69e-04
2022-05-07 18:09:48,873 INFO [train.py:715] (4/8) Epoch 13, batch 13000, loss[loss=0.1409, simple_loss=0.2123, pruned_loss=0.03475, over 4990.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03044, over 974877.20 frames.], batch size: 26, lr: 1.69e-04
2022-05-07 18:10:26,258 INFO [train.py:715] (4/8) Epoch 13, batch 13050, loss[loss=0.1208, simple_loss=0.1994, pruned_loss=0.02104, over 4878.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03041, over 974537.27 frames.], batch size: 39, lr: 1.69e-04
2022-05-07 18:11:05,303 INFO [train.py:715] (4/8) Epoch 13, batch 13100, loss[loss=0.1379, simple_loss=0.2126, pruned_loss=0.03161, over 4762.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03022, over 973524.98 frames.], batch size: 19, lr: 1.69e-04
2022-05-07 18:11:43,998 INFO [train.py:715] (4/8) Epoch 13, batch 13150, loss[loss=0.1339, simple_loss=0.2091, pruned_loss=0.02931, over 4911.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03031, over 972888.57 frames.], batch size: 17, lr: 1.69e-04
2022-05-07 18:12:21,746 INFO [train.py:715] (4/8) Epoch 13, batch 13200, loss[loss=0.1425, simple_loss=0.2142, pruned_loss=0.03542, over 4934.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03067, over 973278.05 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 18:13:00,177 INFO [train.py:715] (4/8) Epoch 13, batch 13250, loss[loss=0.1141, simple_loss=0.1819, pruned_loss=0.02312, over 4809.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.0312, over 973874.22 frames.], batch size: 26, lr: 1.69e-04
2022-05-07 18:13:38,868 INFO [train.py:715] (4/8) Epoch 13, batch 13300, loss[loss=0.1167, simple_loss=0.1876, pruned_loss=0.02293, over 4748.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03103, over 974198.43 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 18:14:17,605 INFO [train.py:715] (4/8) Epoch 13, batch 13350, loss[loss=0.1429, simple_loss=0.2232, pruned_loss=0.03133, over 4787.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03107, over 973710.04 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 18:14:55,892 INFO [train.py:715] (4/8) Epoch 13, batch 13400, loss[loss=0.1229, simple_loss=0.1995, pruned_loss=0.02321, over 4773.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03103, over 973003.56 frames.], batch size: 18, lr: 1.69e-04
2022-05-07 18:15:35,682 INFO [train.py:715] (4/8) Epoch 13, batch 13450, loss[loss=0.1232, simple_loss=0.2044, pruned_loss=0.02103, over 4752.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03098, over 973121.08 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 18:16:14,408 INFO [train.py:715] (4/8) Epoch 13, batch 13500, loss[loss=0.1583, simple_loss=0.2264, pruned_loss=0.04507, over 4854.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03124, over 972786.57 frames.], batch size: 32, lr: 1.69e-04
2022-05-07 18:16:52,061 INFO [train.py:715] (4/8) Epoch 13, batch 13550, loss[loss=0.12, simple_loss=0.2009, pruned_loss=0.01956, over 4779.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03125, over 972904.88 frames.], batch size: 14, lr: 1.69e-04
2022-05-07 18:17:29,850 INFO [train.py:715] (4/8) Epoch 13, batch 13600, loss[loss=0.1391, simple_loss=0.2102, pruned_loss=0.03402, over 4990.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03135, over 973382.22 frames.], batch size: 16, lr: 1.68e-04
2022-05-07 18:18:08,971 INFO [train.py:715] (4/8) Epoch 13, batch 13650, loss[loss=0.1482, simple_loss=0.222, pruned_loss=0.03719, over 4918.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03077, over 973352.19 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:18:47,087 INFO [train.py:715] (4/8) Epoch 13, batch 13700, loss[loss=0.1404, simple_loss=0.2131, pruned_loss=0.03388, over 4906.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03085, over 973691.66 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:19:24,726 INFO [train.py:715] (4/8) Epoch 13, batch 13750, loss[loss=0.139, simple_loss=0.2216, pruned_loss=0.02826, over 4819.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2103, pruned_loss=0.03113, over 973859.27 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 18:20:03,321 INFO [train.py:715] (4/8) Epoch 13, batch 13800, loss[loss=0.1224, simple_loss=0.1932, pruned_loss=0.02581, over 4984.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2107, pruned_loss=0.03106, over 973417.45 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 18:20:41,460 INFO [train.py:715] (4/8) Epoch 13, batch 13850, loss[loss=0.1526, simple_loss=0.2212, pruned_loss=0.04195, over 4767.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.0309, over 972444.59 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 18:21:19,873 INFO [train.py:715] (4/8) Epoch 13, batch 13900, loss[loss=0.1419, simple_loss=0.2132, pruned_loss=0.03529, over 4864.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2104, pruned_loss=0.03107, over 972450.55 frames.], batch size: 20, lr: 1.68e-04
2022-05-07 18:21:58,634 INFO [train.py:715] (4/8) Epoch 13, batch 13950, loss[loss=0.147, simple_loss=0.2099, pruned_loss=0.04203, over 4833.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2108, pruned_loss=0.03144, over 972947.25 frames.], batch size: 30, lr: 1.68e-04
2022-05-07 18:22:37,441 INFO [train.py:715] (4/8) Epoch 13, batch 14000, loss[loss=0.1288, simple_loss=0.2056, pruned_loss=0.026, over 4781.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2117, pruned_loss=0.03181, over 972763.55 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 18:23:15,661 INFO [train.py:715] (4/8) Epoch 13, batch 14050, loss[loss=0.1322, simple_loss=0.2029, pruned_loss=0.03074, over 4750.00 frames.], tot_loss[loss=0.1372, simple_loss=0.211, pruned_loss=0.03169, over 972147.48 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 18:23:53,254 INFO [train.py:715] (4/8) Epoch 13, batch 14100, loss[loss=0.1158, simple_loss=0.1934, pruned_loss=0.01908, over 4775.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03143, over 972250.46 frames.], batch size: 12, lr: 1.68e-04
2022-05-07 18:24:32,483 INFO [train.py:715] (4/8) Epoch 13, batch 14150, loss[loss=0.1463, simple_loss=0.2112, pruned_loss=0.04068, over 4871.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2112, pruned_loss=0.03236, over 971664.54 frames.], batch size: 39, lr: 1.68e-04
2022-05-07 18:25:10,630 INFO [train.py:715] (4/8) Epoch 13, batch 14200, loss[loss=0.1381, simple_loss=0.2007, pruned_loss=0.03779, over 4796.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03183, over 971280.81 frames.], batch size: 12, lr: 1.68e-04
2022-05-07 18:25:48,510 INFO [train.py:715] (4/8) Epoch 13, batch 14250, loss[loss=0.1762, simple_loss=0.2519, pruned_loss=0.05028, over 4839.00 frames.], tot_loss[loss=0.137, simple_loss=0.2104, pruned_loss=0.03175, over 970588.13 frames.], batch size: 30, lr: 1.68e-04
2022-05-07 18:26:26,774 INFO [train.py:715] (4/8) Epoch 13, batch 14300, loss[loss=0.1118, simple_loss=0.1899, pruned_loss=0.01684, over 4748.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03171, over 971477.95 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 18:27:06,171 INFO [train.py:715] (4/8) Epoch 13, batch 14350, loss[loss=0.1425, simple_loss=0.2188, pruned_loss=0.03304, over 4992.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2114, pruned_loss=0.03195, over 971342.83 frames.], batch size: 16, lr: 1.68e-04
2022-05-07 18:27:44,510 INFO [train.py:715] (4/8) Epoch 13, batch 14400, loss[loss=0.1581, simple_loss=0.2389, pruned_loss=0.03864, over 4929.00 frames.], tot_loss[loss=0.138, simple_loss=0.2116, pruned_loss=0.03225, over 971629.09 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:28:22,436 INFO [train.py:715] (4/8) Epoch 13, batch 14450, loss[loss=0.1344, simple_loss=0.2218, pruned_loss=0.0235, over 4766.00 frames.], tot_loss[loss=0.1383, simple_loss=0.2113, pruned_loss=0.03265, over 971997.18 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 18:29:01,540 INFO [train.py:715] (4/8) Epoch 13, batch 14500, loss[loss=0.1257, simple_loss=0.2041, pruned_loss=0.02368, over 4874.00 frames.], tot_loss[loss=0.1379, simple_loss=0.2114, pruned_loss=0.03225, over 972407.44 frames.], batch size: 20, lr: 1.68e-04
2022-05-07 18:29:40,346 INFO [train.py:715] (4/8) Epoch 13, batch 14550, loss[loss=0.1435, simple_loss=0.2182, pruned_loss=0.03441, over 4867.00 frames.], tot_loss[loss=0.1385, simple_loss=0.2119, pruned_loss=0.03252, over 972131.79 frames.], batch size: 20, lr: 1.68e-04
2022-05-07 18:30:18,694 INFO [train.py:715] (4/8) Epoch 13, batch 14600, loss[loss=0.16, simple_loss=0.2291, pruned_loss=0.04548, over 4857.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2104, pruned_loss=0.03235, over 972225.72 frames.], batch size: 32, lr: 1.68e-04
2022-05-07 18:30:57,059 INFO [train.py:715] (4/8) Epoch 13, batch 14650, loss[loss=0.1473, simple_loss=0.2263, pruned_loss=0.03416, over 4783.00 frames.], tot_loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03228, over 972923.88 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:31:35,710 INFO [train.py:715] (4/8) Epoch 13, batch 14700, loss[loss=0.1132, simple_loss=0.1854, pruned_loss=0.02046, over 4908.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03182, over 972054.03 frames.], batch size: 22, lr: 1.68e-04
2022-05-07 18:32:13,645 INFO [train.py:715] (4/8) Epoch 13, batch 14750, loss[loss=0.1255, simple_loss=0.1971, pruned_loss=0.02692, over 4758.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03111, over 971505.05 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 18:32:50,801 INFO [train.py:715] (4/8) Epoch 13, batch 14800, loss[loss=0.136, simple_loss=0.2074, pruned_loss=0.03224, over 4849.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03135, over 971444.15 frames.], batch size: 20, lr: 1.68e-04
2022-05-07 18:33:29,890 INFO [train.py:715] (4/8) Epoch 13, batch 14850, loss[loss=0.1319, simple_loss=0.1984, pruned_loss=0.03269, over 4860.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03123, over 971858.57 frames.], batch size: 32, lr: 1.68e-04
2022-05-07 18:34:08,570 INFO [train.py:715] (4/8) Epoch 13, batch 14900, loss[loss=0.1238, simple_loss=0.201, pruned_loss=0.02328, over 4908.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03126, over 972001.26 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 18:34:46,495 INFO [train.py:715] (4/8) Epoch 13, batch 14950, loss[loss=0.1564, simple_loss=0.2257, pruned_loss=0.04349, over 4905.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.0314, over 971022.84 frames.], batch size: 39, lr: 1.68e-04
2022-05-07 18:35:24,994 INFO [train.py:715] (4/8) Epoch 13, batch 15000, loss[loss=0.1329, simple_loss=0.2109, pruned_loss=0.0274, over 4983.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03144, over 971206.33 frames.], batch size: 25, lr: 1.68e-04
2022-05-07 18:35:24,995 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 18:35:34,566 INFO [train.py:742] (4/8) Epoch 13, validation: loss=0.1052, simple_loss=0.189, pruned_loss=0.01074, over 914524.00 frames.
2022-05-07 18:36:13,159 INFO [train.py:715] (4/8) Epoch 13, batch 15050, loss[loss=0.1406, simple_loss=0.2118, pruned_loss=0.03472, over 4784.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03137, over 971036.76 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 18:36:52,713 INFO [train.py:715] (4/8) Epoch 13, batch 15100, loss[loss=0.1294, simple_loss=0.2025, pruned_loss=0.02816, over 4895.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03153, over 971657.99 frames.], batch size: 29, lr: 1.68e-04
2022-05-07 18:37:31,193 INFO [train.py:715] (4/8) Epoch 13, batch 15150, loss[loss=0.1174, simple_loss=0.1986, pruned_loss=0.01811, over 4810.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03107, over 971844.00 frames.], batch size: 27, lr: 1.68e-04
2022-05-07 18:38:09,446 INFO [train.py:715] (4/8) Epoch 13, batch 15200, loss[loss=0.1288, simple_loss=0.2019, pruned_loss=0.02787, over 4926.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03114, over 971651.14 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 18:38:49,229 INFO [train.py:715] (4/8) Epoch 13, batch 15250, loss[loss=0.1316, simple_loss=0.199, pruned_loss=0.03207, over 4839.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03151, over 971124.49 frames.], batch size: 13, lr: 1.68e-04
2022-05-07 18:39:27,975 INFO [train.py:715] (4/8) Epoch 13, batch 15300, loss[loss=0.1309, simple_loss=0.2023, pruned_loss=0.02972, over 4903.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2098, pruned_loss=0.03192, over 971034.48 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 18:40:06,014 INFO [train.py:715] (4/8) Epoch 13, batch 15350, loss[loss=0.1508, simple_loss=0.2225, pruned_loss=0.03959, over 4913.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.0315, over 972211.50 frames.], batch size: 39, lr: 1.68e-04
2022-05-07 18:40:45,012 INFO [train.py:715] (4/8) Epoch 13, batch 15400, loss[loss=0.1418, simple_loss=0.2188, pruned_loss=0.03245, over 4916.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03121, over 972534.36 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 18:41:23,909 INFO [train.py:715] (4/8) Epoch 13, batch 15450, loss[loss=0.1294, simple_loss=0.2083, pruned_loss=0.02522, over 4868.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03153, over 972560.33 frames.], batch size: 32, lr: 1.68e-04
2022-05-07 18:42:03,715 INFO [train.py:715] (4/8) Epoch 13, batch 15500, loss[loss=0.1096, simple_loss=0.178, pruned_loss=0.02065, over 4903.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2088, pruned_loss=0.03138, over 971373.37 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:42:41,963 INFO [train.py:715] (4/8) Epoch 13, batch 15550, loss[loss=0.1933, simple_loss=0.26, pruned_loss=0.06326, over 4702.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03086, over 971114.10 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 18:43:21,699 INFO [train.py:715] (4/8) Epoch 13, batch 15600, loss[loss=0.1144, simple_loss=0.1888, pruned_loss=0.02002, over 4942.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03104, over 971628.72 frames.], batch size: 23, lr: 1.68e-04
2022-05-07 18:44:01,140 INFO [train.py:715] (4/8) Epoch 13, batch 15650, loss[loss=0.1281, simple_loss=0.2072, pruned_loss=0.02449, over 4754.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2099, pruned_loss=0.03134, over 971344.48 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 18:44:39,651 INFO [train.py:715] (4/8) Epoch 13, batch 15700, loss[loss=0.1303, simple_loss=0.2029, pruned_loss=0.02888, over 4804.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03096, over 971404.55 frames.], batch size: 25, lr: 1.68e-04
2022-05-07 18:45:18,632 INFO [train.py:715] (4/8) Epoch 13, batch 15750, loss[loss=0.1532, simple_loss=0.2262, pruned_loss=0.04012, over 4773.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03087, over 971930.82 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:45:57,410 INFO [train.py:715] (4/8) Epoch 13, batch 15800, loss[loss=0.1362, simple_loss=0.2065, pruned_loss=0.03292, over 4865.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03089, over 972317.53 frames.], batch size: 20, lr: 1.68e-04
2022-05-07 18:46:35,695 INFO [train.py:715] (4/8) Epoch 13, batch 15850, loss[loss=0.1262, simple_loss=0.1971, pruned_loss=0.02766, over 4836.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03108, over 973293.21 frames.], batch size: 30, lr: 1.68e-04
2022-05-07 18:47:13,600 INFO [train.py:715] (4/8) Epoch 13, batch 15900, loss[loss=0.1376, simple_loss=0.2041, pruned_loss=0.0355, over 4971.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03125, over 972757.96 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 18:47:52,836 INFO [train.py:715] (4/8) Epoch 13, batch 15950, loss[loss=0.148, simple_loss=0.2251, pruned_loss=0.03546, over 4872.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03126, over 972738.06 frames.], batch size: 16, lr: 1.68e-04
2022-05-07 18:48:31,350 INFO [train.py:715] (4/8) Epoch 13, batch 16000, loss[loss=0.1371, simple_loss=0.2182, pruned_loss=0.02798, over 4989.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03101, over 972274.57 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 18:49:09,602 INFO [train.py:715] (4/8) Epoch 13, batch 16050, loss[loss=0.1637, simple_loss=0.2405, pruned_loss=0.04347, over 4913.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03129, over 971876.22 frames.], batch size: 23, lr: 1.68e-04
2022-05-07 18:49:48,080 INFO [train.py:715] (4/8) Epoch 13, batch 16100, loss[loss=0.1537, simple_loss=0.2275, pruned_loss=0.03999, over 4925.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03089, over 972052.73 frames.], batch size: 39, lr: 1.68e-04
2022-05-07 18:50:27,336 INFO [train.py:715] (4/8) Epoch 13, batch 16150, loss[loss=0.1585, simple_loss=0.2141, pruned_loss=0.05146, over 4966.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03113, over 973178.90 frames.], batch size: 39, lr: 1.68e-04
2022-05-07 18:51:05,993 INFO [train.py:715] (4/8) Epoch 13, batch 16200, loss[loss=0.1342, simple_loss=0.2163, pruned_loss=0.02606, over 4873.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03116, over 974034.97 frames.], batch size: 20, lr: 1.68e-04
2022-05-07 18:51:42,925 INFO [train.py:715] (4/8) Epoch 13, batch 16250, loss[loss=0.1055, simple_loss=0.1853, pruned_loss=0.01282, over 4805.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.03127, over 973979.73 frames.], batch size: 24, lr: 1.68e-04
2022-05-07 18:52:22,101 INFO [train.py:715] (4/8) Epoch 13, batch 16300, loss[loss=0.1372, simple_loss=0.2068, pruned_loss=0.03383, over 4772.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2097, pruned_loss=0.03164, over 973187.73 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 18:53:00,700 INFO [train.py:715] (4/8) Epoch 13, batch 16350, loss[loss=0.1318, simple_loss=0.219, pruned_loss=0.02232, over 4961.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03119, over 972536.15 frames.], batch size: 24, lr: 1.68e-04
2022-05-07 18:53:39,045 INFO [train.py:715] (4/8) Epoch 13, batch 16400, loss[loss=0.1143, simple_loss=0.1876, pruned_loss=0.02055, over 4780.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2088, pruned_loss=0.031, over 972035.88 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 18:54:18,189 INFO [train.py:715] (4/8) Epoch 13, batch 16450, loss[loss=0.1327, simple_loss=0.211, pruned_loss=0.02716, over 4808.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03105, over 971736.47 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 18:54:57,404 INFO [train.py:715] (4/8) Epoch 13, batch 16500, loss[loss=0.1452, simple_loss=0.2232, pruned_loss=0.03363, over 4880.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03112, over 971948.99 frames.], batch size: 22, lr: 1.68e-04
2022-05-07 18:55:36,543 INFO [train.py:715] (4/8) Epoch 13, batch 16550, loss[loss=0.1284, simple_loss=0.2004, pruned_loss=0.02814, over 4921.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03101, over 971533.87 frames.], batch size: 23, lr: 1.68e-04
2022-05-07 18:56:13,926 INFO [train.py:715] (4/8) Epoch 13, batch 16600, loss[loss=0.1499, simple_loss=0.23, pruned_loss=0.03484, over 4770.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03102, over 971392.72 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 18:56:53,166 INFO [train.py:715] (4/8) Epoch 13, batch 16650, loss[loss=0.1245, simple_loss=0.2031, pruned_loss=0.02292, over 4899.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03096, over 972183.57 frames.], batch size: 22, lr: 1.68e-04
2022-05-07 18:57:31,700 INFO [train.py:715] (4/8) Epoch 13, batch 16700, loss[loss=0.1187, simple_loss=0.1928, pruned_loss=0.02225, over 4775.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03096, over 972422.34 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 18:58:09,690 INFO [train.py:715] (4/8) Epoch 13, batch 16750, loss[loss=0.1546, simple_loss=0.2131, pruned_loss=0.04805, over 4648.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03145, over 972545.49 frames.], batch size: 13, lr: 1.68e-04
2022-05-07 18:58:48,288 INFO [train.py:715] (4/8) Epoch 13, batch 16800, loss[loss=0.1605, simple_loss=0.2299, pruned_loss=0.04554, over 4768.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03146, over 972617.22 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 18:59:27,921 INFO [train.py:715] (4/8) Epoch 13, batch 16850, loss[loss=0.1269, simple_loss=0.2088, pruned_loss=0.02252, over 4815.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.0314, over 971471.44 frames.], batch size: 25, lr: 1.68e-04
2022-05-07 19:00:06,301 INFO [train.py:715] (4/8) Epoch 13, batch 16900, loss[loss=0.1244, simple_loss=0.2039, pruned_loss=0.02245, over 4818.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03149, over 971768.70 frames.], batch size: 26, lr: 1.68e-04
2022-05-07 19:00:44,803 INFO [train.py:715] (4/8) Epoch 13, batch 16950, loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03072, over 4967.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.03143, over 971990.57 frames.], batch size: 35, lr: 1.68e-04
2022-05-07 19:01:23,717 INFO [train.py:715] (4/8) Epoch 13, batch 17000, loss[loss=0.1555, simple_loss=0.2444, pruned_loss=0.03329, over 4872.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2097, pruned_loss=0.03173, over 972241.32 frames.], batch size: 22, lr: 1.68e-04
2022-05-07 19:02:02,416 INFO [train.py:715] (4/8) Epoch 13, batch 17050, loss[loss=0.1583, simple_loss=0.2295, pruned_loss=0.04356, over 4894.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2108, pruned_loss=0.03217, over 972261.28 frames.], batch size: 17, lr: 1.68e-04
2022-05-07 19:02:40,531 INFO [train.py:715] (4/8) Epoch 13, batch 17100, loss[loss=0.1435, simple_loss=0.2184, pruned_loss=0.03433, over 4733.00 frames.], tot_loss[loss=0.138, simple_loss=0.211, pruned_loss=0.03248, over 972953.50 frames.], batch size: 16, lr: 1.68e-04
2022-05-07 19:03:19,263 INFO [train.py:715] (4/8) Epoch 13, batch 17150, loss[loss=0.1175, simple_loss=0.19, pruned_loss=0.0225, over 4866.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2103, pruned_loss=0.03203, over 972902.65 frames.], batch size: 20, lr: 1.68e-04
2022-05-07 19:03:58,102 INFO [train.py:715] (4/8) Epoch 13, batch 17200, loss[loss=0.1265, simple_loss=0.2114, pruned_loss=0.02084, over 4960.00 frames.], tot_loss[loss=0.137, simple_loss=0.2102, pruned_loss=0.03189, over 972802.08 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 19:04:36,808 INFO [train.py:715] (4/8) Epoch 13, batch 17250, loss[loss=0.134, simple_loss=0.2031, pruned_loss=0.03246, over 4783.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.0317, over 973065.23 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 19:05:14,781 INFO [train.py:715] (4/8) Epoch 13, batch 17300, loss[loss=0.1071, simple_loss=0.1766, pruned_loss=0.01882, over 4770.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03152, over 972459.90 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 19:05:53,538 INFO [train.py:715] (4/8) Epoch 13, batch 17350, loss[loss=0.1304, simple_loss=0.2053, pruned_loss=0.02774, over 4960.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03165, over 973252.25 frames.], batch size: 35, lr: 1.68e-04
2022-05-07 19:06:32,453 INFO [train.py:715] (4/8) Epoch 13, batch 17400, loss[loss=0.1482, simple_loss=0.2171, pruned_loss=0.03965, over 4850.00 frames.], tot_loss[loss=0.1382, simple_loss=0.2114, pruned_loss=0.03251, over 973023.60 frames.], batch size: 20, lr: 1.68e-04
2022-05-07 19:07:10,067 INFO [train.py:715] (4/8) Epoch 13, batch 17450, loss[loss=0.137, simple_loss=0.2071, pruned_loss=0.03348, over 4969.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2108, pruned_loss=0.03181, over 972849.49 frames.], batch size: 40, lr: 1.68e-04
2022-05-07 19:07:48,569 INFO [train.py:715] (4/8) Epoch 13, batch 17500, loss[loss=0.1276, simple_loss=0.2025, pruned_loss=0.02636, over 4895.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2098, pruned_loss=0.03145, over 972099.13 frames.], batch size: 22, lr: 1.68e-04
2022-05-07 19:08:27,655 INFO [train.py:715] (4/8) Epoch 13, batch 17550, loss[loss=0.1129, simple_loss=0.1967, pruned_loss=0.01454, over 4809.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03139, over 972481.56 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 19:09:06,326 INFO [train.py:715] (4/8) Epoch 13, batch 17600, loss[loss=0.1379, simple_loss=0.2166, pruned_loss=0.02962, over 4917.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03137, over 973391.57 frames.], batch size: 29, lr: 1.68e-04
2022-05-07 19:09:43,948 INFO [train.py:715] (4/8) Epoch 13, batch 17650, loss[loss=0.1213, simple_loss=0.1968, pruned_loss=0.02292, over 4827.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03062, over 973315.76 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 19:10:23,206 INFO [train.py:715] (4/8) Epoch 13, batch 17700, loss[loss=0.1606, simple_loss=0.2248, pruned_loss=0.04815, over 4806.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03042, over 972430.54 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 19:11:02,062 INFO [train.py:715] (4/8) Epoch 13, batch 17750, loss[loss=0.1362, simple_loss=0.2063, pruned_loss=0.03308, over 4816.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03098, over 973024.40 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 19:11:39,680 INFO [train.py:715] (4/8) Epoch 13, batch 17800, loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.0353, over 4927.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03147, over 973340.50 frames.], batch size: 18, lr: 1.68e-04
2022-05-07 19:12:18,455 INFO [train.py:715] (4/8) Epoch 13, batch 17850, loss[loss=0.1288, simple_loss=0.2061, pruned_loss=0.02582, over 4932.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2098, pruned_loss=0.03149, over 973312.30 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 19:12:57,286 INFO [train.py:715] (4/8) Epoch 13, batch 17900, loss[loss=0.1307, simple_loss=0.2087, pruned_loss=0.02636, over 4970.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2106, pruned_loss=0.0321, over 971909.20 frames.], batch size: 28, lr: 1.68e-04
2022-05-07 19:13:35,478 INFO [train.py:715] (4/8) Epoch 13, batch 17950, loss[loss=0.1493, simple_loss=0.2145, pruned_loss=0.04203, over 4878.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03168, over 972676.89 frames.], batch size: 16, lr: 1.68e-04
2022-05-07 19:14:13,540 INFO [train.py:715] (4/8) Epoch 13, batch 18000, loss[loss=0.1305, simple_loss=0.2064, pruned_loss=0.02732, over 4881.00 frames.], tot_loss[loss=0.1369, simple_loss=0.21, pruned_loss=0.0319, over 972151.77 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 19:14:13,541 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 19:14:23,027 INFO [train.py:742] (4/8) Epoch 13, validation: loss=0.1055, simple_loss=0.1892, pruned_loss=0.01083, over 914524.00 frames.
2022-05-07 19:15:00,699 INFO [train.py:715] (4/8) Epoch 13, batch 18050, loss[loss=0.1465, simple_loss=0.2271, pruned_loss=0.03291, over 4701.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.0316, over 972341.97 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 19:15:39,774 INFO [train.py:715] (4/8) Epoch 13, batch 18100, loss[loss=0.1496, simple_loss=0.2139, pruned_loss=0.04272, over 4853.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03177, over 972152.16 frames.], batch size: 34, lr: 1.68e-04
2022-05-07 19:16:18,123 INFO [train.py:715] (4/8) Epoch 13, batch 18150, loss[loss=0.1318, simple_loss=0.2104, pruned_loss=0.02662, over 4816.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2099, pruned_loss=0.03185, over 972094.44 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 19:16:55,375 INFO [train.py:715] (4/8) Epoch 13, batch 18200, loss[loss=0.09884, simple_loss=0.1684, pruned_loss=0.01464, over 4974.00 frames.], tot_loss[loss=0.136, simple_loss=0.2094, pruned_loss=0.03133, over 972238.27 frames.], batch size: 25, lr: 1.68e-04
2022-05-07 19:17:33,692 INFO [train.py:715] (4/8) Epoch 13, batch 18250, loss[loss=0.1289, simple_loss=0.2041, pruned_loss=0.02683, over 4828.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03136, over 971872.67 frames.], batch size: 26, lr: 1.68e-04
2022-05-07 19:18:12,484 INFO [train.py:715] (4/8) Epoch 13, batch 18300, loss[loss=0.1255, simple_loss=0.2005, pruned_loss=0.02523, over 4969.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03093, over 971279.54 frames.], batch size: 24, lr: 1.68e-04
2022-05-07 19:18:51,122 INFO [train.py:715] (4/8) Epoch 13, batch 18350, loss[loss=0.1227, simple_loss=0.1973, pruned_loss=0.02405, over 4989.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03077, over 971458.79 frames.], batch size: 28, lr: 1.68e-04
2022-05-07 19:19:29,015 INFO [train.py:715] (4/8) Epoch 13, batch 18400, loss[loss=0.137, simple_loss=0.2036, pruned_loss=0.0352, over 4945.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03108, over 971979.06 frames.], batch size: 29, lr: 1.68e-04
2022-05-07 19:20:07,826 INFO [train.py:715] (4/8) Epoch 13, batch 18450, loss[loss=0.1341, simple_loss=0.2093, pruned_loss=0.02945, over 4825.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03105, over 971823.61 frames.], batch size: 25, lr: 1.68e-04
2022-05-07 19:20:46,497 INFO [train.py:715] (4/8) Epoch 13, batch 18500, loss[loss=0.1165, simple_loss=0.1978, pruned_loss=0.01761, over 4922.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03094, over 972379.57 frames.], batch size: 29, lr: 1.68e-04
2022-05-07 19:21:23,938 INFO [train.py:715] (4/8) Epoch 13, batch 18550, loss[loss=0.1445, simple_loss=0.2194, pruned_loss=0.03477, over 4910.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03072, over 972210.14 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 19:22:01,960 INFO [train.py:715] (4/8) Epoch 13, batch 18600, loss[loss=0.1303, simple_loss=0.2039, pruned_loss=0.02836, over 4762.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03004, over 972489.09 frames.], batch size: 14, lr: 1.68e-04
2022-05-07 19:22:40,556 INFO [train.py:715] (4/8) Epoch 13, batch 18650, loss[loss=0.1181, simple_loss=0.1983, pruned_loss=0.01897, over 4814.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03, over 971866.64 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 19:23:18,502 INFO [train.py:715] (4/8) Epoch 13, batch 18700, loss[loss=0.1517, simple_loss=0.2141, pruned_loss=0.0447, over 4831.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03036, over 971231.47 frames.], batch size: 15, lr: 1.68e-04
2022-05-07 19:23:56,288 INFO [train.py:715] (4/8) Epoch 13, batch 18750, loss[loss=0.121, simple_loss=0.2013, pruned_loss=0.02038, over 4901.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03056, over 971121.09 frames.], batch size: 19, lr: 1.68e-04
2022-05-07 19:24:35,597 INFO [train.py:715] (4/8) Epoch 13, batch 18800, loss[loss=0.1258, simple_loss=0.1986, pruned_loss=0.02651, over 4933.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03096, over 971780.22 frames.], batch size: 29, lr: 1.68e-04
2022-05-07 19:25:14,016 INFO [train.py:715] (4/8) Epoch 13, batch 18850, loss[loss=0.1402, simple_loss=0.2132, pruned_loss=0.03357, over 4933.00 frames.], tot_loss[loss=0.136, simple_loss=0.2102, pruned_loss=0.03092, over 972051.36 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 19:25:52,040 INFO [train.py:715] (4/8) Epoch 13, batch 18900, loss[loss=0.116, simple_loss=0.1984, pruned_loss=0.01676, over 4863.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2093, pruned_loss=0.03019, over 972057.49 frames.], batch size: 20, lr: 1.68e-04
2022-05-07 19:26:30,901 INFO [train.py:715] (4/8) Epoch 13, batch 18950, loss[loss=0.1354, simple_loss=0.2198, pruned_loss=0.02555, over 4810.00 frames.], tot_loss[loss=0.1354, simple_loss=0.21, pruned_loss=0.03037, over 972604.59 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 19:27:09,785 INFO [train.py:715] (4/8) Epoch 13, batch 19000, loss[loss=0.1256, simple_loss=0.2071, pruned_loss=0.02211, over 4940.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2096, pruned_loss=0.03035, over 972487.88 frames.], batch size: 21, lr: 1.68e-04
2022-05-07 19:27:48,130 INFO [train.py:715] (4/8) Epoch 13, batch 19050, loss[loss=0.1223, simple_loss=0.1961, pruned_loss=0.02425, over 4749.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03068, over 971472.53 frames.], batch size: 12, lr: 1.68e-04
2022-05-07 19:28:26,455 INFO [train.py:715] (4/8) Epoch 13, batch 19100, loss[loss=0.1266, simple_loss=0.2139, pruned_loss=0.01961, over 4920.00 frames.], tot_loss[loss=0.1359, simple_loss=0.21, pruned_loss=0.0309, over 971828.51 frames.], batch size: 29, lr: 1.68e-04
2022-05-07 19:29:05,458 INFO [train.py:715] (4/8) Epoch 13, batch 19150, loss[loss=0.1194, simple_loss=0.1928, pruned_loss=0.02306, over 4821.00 frames.], tot_loss[loss=0.136, simple_loss=0.2102, pruned_loss=0.03094, over 971668.45 frames.], batch size: 13, lr: 1.67e-04
2022-05-07 19:29:44,106 INFO [train.py:715] (4/8) Epoch 13, batch 19200, loss[loss=0.1282, simple_loss=0.2051, pruned_loss=0.02572, over 4962.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2098, pruned_loss=0.03071, over 972455.59 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:30:21,502 INFO [train.py:715] (4/8) Epoch 13, batch 19250, loss[loss=0.1077, simple_loss=0.1905, pruned_loss=0.01242, over 4957.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03089, over 972134.52 frames.], batch size: 29, lr: 1.67e-04
2022-05-07 19:31:00,095 INFO [train.py:715] (4/8) Epoch 13, batch 19300, loss[loss=0.1741, simple_loss=0.2458, pruned_loss=0.05118, over 4938.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03065, over 972954.39 frames.], batch size: 23, lr: 1.67e-04
2022-05-07 19:31:39,559 INFO [train.py:715] (4/8) Epoch 13, batch 19350, loss[loss=0.134, simple_loss=0.209, pruned_loss=0.0295, over 4779.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03075, over 973014.00 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 19:32:18,098 INFO [train.py:715] (4/8) Epoch 13, batch 19400, loss[loss=0.1432, simple_loss=0.2085, pruned_loss=0.03889, over 4969.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03031, over 972951.83 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 19:32:56,532 INFO [train.py:715] (4/8) Epoch 13, batch 19450, loss[loss=0.1459, simple_loss=0.2111, pruned_loss=0.04032, over 4913.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03076, over 973070.93 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 19:33:37,825 INFO [train.py:715] (4/8) Epoch 13, batch 19500, loss[loss=0.1437, simple_loss=0.2166, pruned_loss=0.03542, over 4848.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.0305, over 972455.33 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:34:16,750 INFO [train.py:715] (4/8) Epoch 13, batch 19550, loss[loss=0.1002, simple_loss=0.1667, pruned_loss=0.0168, over 4692.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03107, over 973090.58 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:34:54,319 INFO [train.py:715] (4/8) Epoch 13, batch 19600, loss[loss=0.1477, simple_loss=0.2146, pruned_loss=0.04044, over 4682.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.0313, over 973055.68 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:35:32,449 INFO [train.py:715] (4/8) Epoch 13, batch 19650, loss[loss=0.1114, simple_loss=0.186, pruned_loss=0.01841, over 4655.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03117, over 972566.40 frames.], batch size: 13, lr: 1.67e-04
2022-05-07 19:36:11,256 INFO [train.py:715] (4/8) Epoch 13, batch 19700, loss[loss=0.1191, simple_loss=0.1929, pruned_loss=0.02265, over 4762.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03136, over 972662.42 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 19:36:49,084 INFO [train.py:715] (4/8) Epoch 13, batch 19750, loss[loss=0.1469, simple_loss=0.2299, pruned_loss=0.03194, over 4968.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2107, pruned_loss=0.03203, over 973348.47 frames.], batch size: 24, lr: 1.67e-04
2022-05-07 19:37:26,940 INFO [train.py:715] (4/8) Epoch 13, batch 19800, loss[loss=0.1503, simple_loss=0.2181, pruned_loss=0.04122, over 4860.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2104, pruned_loss=0.03226, over 972659.41 frames.], batch size: 38, lr: 1.67e-04
2022-05-07 19:38:05,611 INFO [train.py:715] (4/8) Epoch 13, batch 19850, loss[loss=0.1438, simple_loss=0.2224, pruned_loss=0.03264, over 4925.00 frames.], tot_loss[loss=0.1375, simple_loss=0.2109, pruned_loss=0.03202, over 973239.62 frames.], batch size: 29, lr: 1.67e-04
2022-05-07 19:38:44,223 INFO [train.py:715] (4/8) Epoch 13, batch 19900, loss[loss=0.145, simple_loss=0.2206, pruned_loss=0.03469, over 4757.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2098, pruned_loss=0.03179, over 972319.87 frames.], batch size: 16, lr: 1.67e-04
2022-05-07 19:39:22,424 INFO [train.py:715] (4/8) Epoch 13, batch 19950, loss[loss=0.1211, simple_loss=0.2001, pruned_loss=0.0211, over 4917.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.0315, over 972699.79 frames.], batch size: 23, lr: 1.67e-04
2022-05-07 19:40:01,314 INFO [train.py:715] (4/8) Epoch 13, batch 20000, loss[loss=0.1147, simple_loss=0.1817, pruned_loss=0.0239, over 4961.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03163, over 973397.46 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 19:40:39,757 INFO [train.py:715] (4/8) Epoch 13, batch 20050, loss[loss=0.137, simple_loss=0.2161, pruned_loss=0.02896, over 4886.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2111, pruned_loss=0.03204, over 972675.21 frames.], batch size: 22, lr: 1.67e-04
2022-05-07 19:41:16,930 INFO [train.py:715] (4/8) Epoch 13, batch 20100, loss[loss=0.1161, simple_loss=0.1746, pruned_loss=0.02877, over 4830.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2103, pruned_loss=0.03221, over 973771.88 frames.], batch size: 12, lr: 1.67e-04
2022-05-07 19:41:54,381 INFO [train.py:715] (4/8) Epoch 13, batch 20150, loss[loss=0.1317, simple_loss=0.213, pruned_loss=0.02519, over 4749.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2102, pruned_loss=0.03222, over 973435.60 frames.], batch size: 16, lr: 1.67e-04
2022-05-07 19:42:33,107 INFO [train.py:715] (4/8) Epoch 13, batch 20200, loss[loss=0.1392, simple_loss=0.2195, pruned_loss=0.02947, over 4902.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2095, pruned_loss=0.03181, over 973119.78 frames.], batch size: 19, lr: 1.67e-04
2022-05-07 19:43:11,186 INFO [train.py:715] (4/8) Epoch 13, batch 20250, loss[loss=0.1715, simple_loss=0.2323, pruned_loss=0.05537, over 4796.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2102, pruned_loss=0.03222, over 973426.29 frames.], batch size: 21, lr: 1.67e-04
2022-05-07 19:43:48,891 INFO [train.py:715] (4/8) Epoch 13, batch 20300, loss[loss=0.1425, simple_loss=0.2052, pruned_loss=0.03986, over 4796.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2103, pruned_loss=0.032, over 974042.03 frames.], batch size: 24, lr: 1.67e-04
2022-05-07 19:44:26,994 INFO [train.py:715] (4/8) Epoch 13, batch 20350, loss[loss=0.1417, simple_loss=0.2082, pruned_loss=0.03759, over 4921.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03171, over 973804.44 frames.], batch size: 35, lr: 1.67e-04
2022-05-07 19:45:05,763 INFO [train.py:715] (4/8) Epoch 13, batch 20400, loss[loss=0.1193, simple_loss=0.1975, pruned_loss=0.02058, over 4749.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2104, pruned_loss=0.0314, over 973463.29 frames.], batch size: 19, lr: 1.67e-04
2022-05-07 19:45:43,492 INFO [train.py:715] (4/8) Epoch 13, batch 20450, loss[loss=0.1209, simple_loss=0.1948, pruned_loss=0.02352, over 4804.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.03124, over 973934.31 frames.], batch size: 26, lr: 1.67e-04
2022-05-07 19:46:21,265 INFO [train.py:715] (4/8) Epoch 13, batch 20500, loss[loss=0.1263, simple_loss=0.1997, pruned_loss=0.02647, over 4964.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03114, over 974288.52 frames.], batch size: 24, lr: 1.67e-04
2022-05-07 19:46:59,824 INFO [train.py:715] (4/8) Epoch 13, batch 20550, loss[loss=0.1149, simple_loss=0.1963, pruned_loss=0.01672, over 4989.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2109, pruned_loss=0.03143, over 973320.58 frames.], batch size: 28, lr: 1.67e-04
2022-05-07 19:47:37,480 INFO [train.py:715] (4/8) Epoch 13, batch 20600, loss[loss=0.1364, simple_loss=0.2191, pruned_loss=0.02687, over 4855.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2107, pruned_loss=0.03087, over 973745.00 frames.], batch size: 20, lr: 1.67e-04
2022-05-07 19:48:15,107 INFO [train.py:715] (4/8) Epoch 13, batch 20650, loss[loss=0.1267, simple_loss=0.2115, pruned_loss=0.02094, over 4815.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03041, over 973635.55 frames.], batch size: 27, lr: 1.67e-04
2022-05-07 19:48:52,914 INFO [train.py:715] (4/8) Epoch 13, batch 20700, loss[loss=0.1448, simple_loss=0.2104, pruned_loss=0.03959, over 4795.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03032, over 973954.39 frames.], batch size: 24, lr: 1.67e-04
2022-05-07 19:49:31,350 INFO [train.py:715] (4/8) Epoch 13, batch 20750, loss[loss=0.1844, simple_loss=0.2569, pruned_loss=0.05601, over 4945.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03028, over 974023.08 frames.], batch size: 35, lr: 1.67e-04
2022-05-07 19:50:08,696 INFO [train.py:715] (4/8) Epoch 13, batch 20800, loss[loss=0.1133, simple_loss=0.1834, pruned_loss=0.02161, over 4743.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03033, over 974125.43 frames.], batch size: 12, lr: 1.67e-04
2022-05-07 19:50:46,281 INFO [train.py:715] (4/8) Epoch 13, batch 20850, loss[loss=0.1312, simple_loss=0.2147, pruned_loss=0.02382, over 4919.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03003, over 973739.97 frames.], batch size: 29, lr: 1.67e-04
2022-05-07 19:51:24,970 INFO [train.py:715] (4/8) Epoch 13, batch 20900, loss[loss=0.1414, simple_loss=0.2027, pruned_loss=0.04001, over 4865.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03024, over 973656.10 frames.], batch size: 32, lr: 1.67e-04
2022-05-07 19:52:03,243 INFO [train.py:715] (4/8) Epoch 13, batch 20950, loss[loss=0.1333, simple_loss=0.2102, pruned_loss=0.02817, over 4982.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03009, over 973652.65 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:52:40,748 INFO [train.py:715] (4/8) Epoch 13, batch 21000, loss[loss=0.1884, simple_loss=0.2581, pruned_loss=0.05931, over 4835.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03066, over 973997.30 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:52:40,748 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 19:52:50,263 INFO [train.py:742] (4/8) Epoch 13, validation: loss=0.1054, simple_loss=0.1891, pruned_loss=0.01084, over 914524.00 frames.
2022-05-07 19:53:28,437 INFO [train.py:715] (4/8) Epoch 13, batch 21050, loss[loss=0.1306, simple_loss=0.2114, pruned_loss=0.02484, over 4859.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03068, over 973416.65 frames.], batch size: 20, lr: 1.67e-04
2022-05-07 19:54:06,970 INFO [train.py:715] (4/8) Epoch 13, batch 21100, loss[loss=0.09839, simple_loss=0.1743, pruned_loss=0.01125, over 4799.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03034, over 972893.94 frames.], batch size: 12, lr: 1.67e-04
2022-05-07 19:54:46,058 INFO [train.py:715] (4/8) Epoch 13, batch 21150, loss[loss=0.1604, simple_loss=0.2336, pruned_loss=0.04355, over 4923.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03021, over 972902.48 frames.], batch size: 21, lr: 1.67e-04
2022-05-07 19:55:23,880 INFO [train.py:715] (4/8) Epoch 13, batch 21200, loss[loss=0.1516, simple_loss=0.2193, pruned_loss=0.04197, over 4793.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2095, pruned_loss=0.0303, over 973477.49 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 19:56:02,467 INFO [train.py:715] (4/8) Epoch 13, batch 21250, loss[loss=0.1246, simple_loss=0.206, pruned_loss=0.02161, over 4931.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2106, pruned_loss=0.03094, over 973774.80 frames.], batch size: 29, lr: 1.67e-04
2022-05-07 19:56:41,279 INFO [train.py:715] (4/8) Epoch 13, batch 21300, loss[loss=0.1817, simple_loss=0.2526, pruned_loss=0.05538, over 4780.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2106, pruned_loss=0.0309, over 973379.74 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 19:57:19,155 INFO [train.py:715] (4/8) Epoch 13, batch 21350, loss[loss=0.1254, simple_loss=0.1982, pruned_loss=0.02629, over 4761.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2101, pruned_loss=0.03071, over 972842.12 frames.], batch size: 19, lr: 1.67e-04
2022-05-07 19:57:57,083 INFO [train.py:715] (4/8) Epoch 13, batch 21400, loss[loss=0.1408, simple_loss=0.2208, pruned_loss=0.03037, over 4691.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2099, pruned_loss=0.03067, over 973319.19 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 19:58:35,344 INFO [train.py:715] (4/8) Epoch 13, batch 21450, loss[loss=0.1624, simple_loss=0.2347, pruned_loss=0.0451, over 4909.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03114, over 973133.85 frames.], batch size: 19, lr: 1.67e-04
2022-05-07 19:59:14,500 INFO [train.py:715] (4/8) Epoch 13, batch 21500, loss[loss=0.166, simple_loss=0.2365, pruned_loss=0.04777, over 4929.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03153, over 972061.60 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 19:59:52,264 INFO [train.py:715] (4/8) Epoch 13, batch 21550, loss[loss=0.1566, simple_loss=0.2304, pruned_loss=0.04144, over 4961.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03146, over 972344.42 frames.], batch size: 39, lr: 1.67e-04
2022-05-07 20:00:30,898 INFO [train.py:715] (4/8) Epoch 13, batch 21600, loss[loss=0.1419, simple_loss=0.2131, pruned_loss=0.03533, over 4694.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2088, pruned_loss=0.03125, over 972503.88 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:01:09,861 INFO [train.py:715] (4/8) Epoch 13, batch 21650, loss[loss=0.1311, simple_loss=0.2148, pruned_loss=0.02365, over 4995.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03081, over 972467.32 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 20:01:48,621 INFO [train.py:715] (4/8) Epoch 13, batch 21700, loss[loss=0.1251, simple_loss=0.2003, pruned_loss=0.025, over 4780.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.0303, over 972595.13 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 20:02:27,464 INFO [train.py:715] (4/8) Epoch 13, batch 21750, loss[loss=0.1463, simple_loss=0.2231, pruned_loss=0.03478, over 4978.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02997, over 972093.78 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:03:06,113 INFO [train.py:715] (4/8) Epoch 13, batch 21800, loss[loss=0.1483, simple_loss=0.2125, pruned_loss=0.04203, over 4936.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03065, over 972524.52 frames.], batch size: 29, lr: 1.67e-04
2022-05-07 20:03:45,413 INFO [train.py:715] (4/8) Epoch 13, batch 21850, loss[loss=0.1162, simple_loss=0.1926, pruned_loss=0.01991, over 4958.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03058, over 972835.19 frames.], batch size: 21, lr: 1.67e-04
2022-05-07 20:04:23,521 INFO [train.py:715] (4/8) Epoch 13, batch 21900, loss[loss=0.1646, simple_loss=0.2378, pruned_loss=0.04567, over 4784.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03072, over 972578.39 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 20:05:01,703 INFO [train.py:715] (4/8) Epoch 13, batch 21950, loss[loss=0.1465, simple_loss=0.209, pruned_loss=0.04206, over 4898.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.0304, over 973204.88 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 20:05:40,176 INFO [train.py:715] (4/8) Epoch 13, batch 22000, loss[loss=0.1313, simple_loss=0.2066, pruned_loss=0.02803, over 4974.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03067, over 974384.84 frames.], batch size: 35, lr: 1.67e-04
2022-05-07 20:06:17,894 INFO [train.py:715] (4/8) Epoch 13, batch 22050, loss[loss=0.1379, simple_loss=0.1956, pruned_loss=0.04014, over 4644.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2098, pruned_loss=0.03079, over 973876.71 frames.], batch size: 13, lr: 1.67e-04
2022-05-07 20:06:55,941 INFO [train.py:715] (4/8) Epoch 13, batch 22100, loss[loss=0.1132, simple_loss=0.1924, pruned_loss=0.01699, over 4885.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03059, over 973757.37 frames.], batch size: 22, lr: 1.67e-04
2022-05-07 20:07:33,696 INFO [train.py:715] (4/8) Epoch 13, batch 22150, loss[loss=0.1372, simple_loss=0.2096, pruned_loss=0.03237, over 4911.00 frames.], tot_loss[loss=0.1358, simple_loss=0.21, pruned_loss=0.03083, over 973328.61 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 20:08:12,652 INFO [train.py:715] (4/8) Epoch 13, batch 22200, loss[loss=0.1604, simple_loss=0.2334, pruned_loss=0.04373, over 4903.00 frames.], tot_loss[loss=0.1358, simple_loss=0.21, pruned_loss=0.03081, over 973130.87 frames.], batch size: 39, lr: 1.67e-04
2022-05-07 20:08:50,195 INFO [train.py:715] (4/8) Epoch 13, batch 22250, loss[loss=0.1252, simple_loss=0.2063, pruned_loss=0.02202, over 4991.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2092, pruned_loss=0.03022, over 973581.18 frames.], batch size: 25, lr: 1.67e-04
2022-05-07 20:09:28,955 INFO [train.py:715] (4/8) Epoch 13, batch 22300, loss[loss=0.1547, simple_loss=0.2323, pruned_loss=0.03855, over 4965.00 frames.], tot_loss[loss=0.136, simple_loss=0.2102, pruned_loss=0.03084, over 972533.01 frames.], batch size: 35, lr: 1.67e-04
2022-05-07 20:10:07,703 INFO [train.py:715] (4/8) Epoch 13, batch 22350, loss[loss=0.1429, simple_loss=0.2076, pruned_loss=0.03913, over 4882.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.03066, over 972315.33 frames.], batch size: 32, lr: 1.67e-04
2022-05-07 20:10:45,730 INFO [train.py:715] (4/8) Epoch 13, batch 22400, loss[loss=0.1226, simple_loss=0.1954, pruned_loss=0.02489, over 4814.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03061, over 971966.62 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 20:11:23,411 INFO [train.py:715] (4/8) Epoch 13, batch 22450, loss[loss=0.141, simple_loss=0.2134, pruned_loss=0.03434, over 4970.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2098, pruned_loss=0.03074, over 972128.72 frames.], batch size: 39, lr: 1.67e-04
2022-05-07 20:12:01,254 INFO [train.py:715] (4/8) Epoch 13, batch 22500, loss[loss=0.1263, simple_loss=0.1937, pruned_loss=0.02947, over 4756.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2098, pruned_loss=0.03074, over 971775.48 frames.], batch size: 16, lr: 1.67e-04
2022-05-07 20:12:39,613 INFO [train.py:715] (4/8) Epoch 13, batch 22550, loss[loss=0.1646, simple_loss=0.2478, pruned_loss=0.04065, over 4862.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03057, over 971042.87 frames.], batch size: 20, lr: 1.67e-04
2022-05-07 20:13:16,804 INFO [train.py:715] (4/8) Epoch 13, batch 22600, loss[loss=0.1155, simple_loss=0.1875, pruned_loss=0.02172, over 4789.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03119, over 970998.62 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 20:13:54,710 INFO [train.py:715] (4/8) Epoch 13, batch 22650, loss[loss=0.1082, simple_loss=0.1767, pruned_loss=0.01987, over 4835.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.03131, over 970366.43 frames.], batch size: 12, lr: 1.67e-04
2022-05-07 20:14:32,805 INFO [train.py:715] (4/8) Epoch 13, batch 22700, loss[loss=0.1601, simple_loss=0.2274, pruned_loss=0.04637, over 4755.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03122, over 970248.53 frames.], batch size: 19, lr: 1.67e-04
2022-05-07 20:15:11,037 INFO [train.py:715] (4/8) Epoch 13, batch 22750, loss[loss=0.1366, simple_loss=0.2109, pruned_loss=0.03114, over 4981.00 frames.], tot_loss[loss=0.1364, simple_loss=0.21, pruned_loss=0.03138, over 970705.59 frames.], batch size: 25, lr: 1.67e-04
2022-05-07 20:15:49,015 INFO [train.py:715] (4/8) Epoch 13, batch 22800, loss[loss=0.1331, simple_loss=0.2058, pruned_loss=0.03024, over 4972.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03134, over 971894.13 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:16:27,581 INFO [train.py:715] (4/8) Epoch 13, batch 22850, loss[loss=0.1502, simple_loss=0.2261, pruned_loss=0.03718, over 4836.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03114, over 972446.85 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:17:06,830 INFO [train.py:715] (4/8) Epoch 13, batch 22900, loss[loss=0.1339, simple_loss=0.211, pruned_loss=0.02846, over 4853.00 frames.], tot_loss[loss=0.1359, simple_loss=0.209, pruned_loss=0.03136, over 972415.29 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:17:44,515 INFO [train.py:715] (4/8) Epoch 13, batch 22950, loss[loss=0.09934, simple_loss=0.1776, pruned_loss=0.01052, over 4821.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2092, pruned_loss=0.03159, over 972373.56 frames.], batch size: 12, lr: 1.67e-04
2022-05-07 20:18:23,099 INFO [train.py:715] (4/8) Epoch 13, batch 23000, loss[loss=0.1256, simple_loss=0.1926, pruned_loss=0.0293, over 4797.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2091, pruned_loss=0.03159, over 973187.20 frames.], batch size: 21, lr: 1.67e-04
2022-05-07 20:19:01,745 INFO [train.py:715] (4/8) Epoch 13, batch 23050, loss[loss=0.124, simple_loss=0.1941, pruned_loss=0.02692, over 4912.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2092, pruned_loss=0.03177, over 972827.86 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 20:19:40,070 INFO [train.py:715] (4/8) Epoch 13, batch 23100, loss[loss=0.1437, simple_loss=0.2167, pruned_loss=0.03531, over 4978.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2087, pruned_loss=0.03139, over 974173.34 frames.], batch size: 35, lr: 1.67e-04
2022-05-07 20:20:17,988 INFO [train.py:715] (4/8) Epoch 13, batch 23150, loss[loss=0.158, simple_loss=0.224, pruned_loss=0.04595, over 4826.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2085, pruned_loss=0.03129, over 973488.95 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:20:56,165 INFO [train.py:715] (4/8) Epoch 13, batch 23200, loss[loss=0.1585, simple_loss=0.2355, pruned_loss=0.0407, over 4878.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2081, pruned_loss=0.0312, over 972451.38 frames.], batch size: 39, lr: 1.67e-04
2022-05-07 20:21:34,317 INFO [train.py:715] (4/8) Epoch 13, batch 23250, loss[loss=0.1146, simple_loss=0.1807, pruned_loss=0.02423, over 4808.00 frames.], tot_loss[loss=0.135, simple_loss=0.208, pruned_loss=0.03096, over 972356.25 frames.], batch size: 12, lr: 1.67e-04
2022-05-07 20:22:11,787 INFO [train.py:715] (4/8) Epoch 13, batch 23300, loss[loss=0.1482, simple_loss=0.2156, pruned_loss=0.04037, over 4817.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2084, pruned_loss=0.03096, over 971615.23 frames.], batch size: 26, lr: 1.67e-04
2022-05-07 20:22:50,104 INFO [train.py:715] (4/8) Epoch 13, batch 23350, loss[loss=0.1161, simple_loss=0.1913, pruned_loss=0.02042, over 4789.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2081, pruned_loss=0.03088, over 972027.82 frames.], batch size: 21, lr: 1.67e-04
2022-05-07 20:23:28,679 INFO [train.py:715] (4/8) Epoch 13, batch 23400, loss[loss=0.112, simple_loss=0.1933, pruned_loss=0.01528, over 4965.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2085, pruned_loss=0.0312, over 971704.79 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:24:06,994 INFO [train.py:715] (4/8) Epoch 13, batch 23450, loss[loss=0.1243, simple_loss=0.2029, pruned_loss=0.0228, over 4894.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2085, pruned_loss=0.03136, over 972398.43 frames.], batch size: 22, lr: 1.67e-04
2022-05-07 20:24:45,014 INFO [train.py:715] (4/8) Epoch 13, batch 23500, loss[loss=0.1291, simple_loss=0.1937, pruned_loss=0.03226, over 4900.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2082, pruned_loss=0.03108, over 971610.36 frames.], batch size: 22, lr: 1.67e-04
2022-05-07 20:25:23,769 INFO [train.py:715] (4/8) Epoch 13, batch 23550, loss[loss=0.1259, simple_loss=0.2029, pruned_loss=0.0244, over 4972.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2084, pruned_loss=0.03105, over 971107.71 frames.], batch size: 15, lr: 1.67e-04
2022-05-07 20:26:02,270 INFO [train.py:715] (4/8) Epoch 13, batch 23600, loss[loss=0.1253, simple_loss=0.1983, pruned_loss=0.02611, over 4952.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2083, pruned_loss=0.03073, over 971909.49 frames.], batch size: 35, lr: 1.67e-04
2022-05-07 20:26:39,841 INFO [train.py:715] (4/8) Epoch 13, batch 23650, loss[loss=0.1318, simple_loss=0.1893, pruned_loss=0.03719, over 4780.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2091, pruned_loss=0.03115, over 971585.23 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 20:27:18,104 INFO [train.py:715] (4/8) Epoch 13, batch 23700, loss[loss=0.1333, simple_loss=0.212, pruned_loss=0.02727, over 4785.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.03089, over 972201.84 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 20:27:56,589 INFO [train.py:715] (4/8) Epoch 13, batch 23750, loss[loss=0.1685, simple_loss=0.2337, pruned_loss=0.0516, over 4860.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03124, over 972611.13 frames.], batch size: 32, lr: 1.67e-04
2022-05-07 20:28:34,761 INFO [train.py:715] (4/8) Epoch 13, batch 23800, loss[loss=0.1431, simple_loss=0.2132, pruned_loss=0.03652, over 4980.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03173, over 972720.72 frames.], batch size: 39, lr: 1.67e-04
2022-05-07 20:29:12,136 INFO [train.py:715] (4/8) Epoch 13, batch 23850, loss[loss=0.1241, simple_loss=0.2065, pruned_loss=0.02085, over 4858.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03182, over 972748.48 frames.], batch size: 20, lr: 1.67e-04
2022-05-07 20:29:51,249 INFO [train.py:715] (4/8) Epoch 13, batch 23900, loss[loss=0.1837, simple_loss=0.2688, pruned_loss=0.04936, over 4896.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03152, over 972016.63 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 20:30:29,201 INFO [train.py:715] (4/8) Epoch 13, batch 23950, loss[loss=0.127, simple_loss=0.1897, pruned_loss=0.03214, over 4783.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2105, pruned_loss=0.03153, over 971630.30 frames.], batch size: 12, lr: 1.67e-04
2022-05-07 20:31:06,578 INFO [train.py:715] (4/8) Epoch 13, batch 24000, loss[loss=0.122, simple_loss=0.1887, pruned_loss=0.02771, over 4806.00 frames.], tot_loss[loss=0.1375, simple_loss=0.211, pruned_loss=0.03203, over 972129.79 frames.], batch size: 12, lr: 1.67e-04
2022-05-07 20:31:06,578 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 20:31:16,108 INFO [train.py:742] (4/8) Epoch 13, validation: loss=0.1053, simple_loss=0.1891, pruned_loss=0.01069, over 914524.00 frames.
2022-05-07 20:31:53,723 INFO [train.py:715] (4/8) Epoch 13, batch 24050, loss[loss=0.1157, simple_loss=0.1873, pruned_loss=0.02211, over 4824.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2106, pruned_loss=0.03177, over 971698.62 frames.], batch size: 26, lr: 1.67e-04
2022-05-07 20:32:31,542 INFO [train.py:715] (4/8) Epoch 13, batch 24100, loss[loss=0.1266, simple_loss=0.2006, pruned_loss=0.02631, over 4970.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03189, over 971968.93 frames.], batch size: 24, lr: 1.67e-04
2022-05-07 20:33:10,919 INFO [train.py:715] (4/8) Epoch 13, batch 24150, loss[loss=0.1267, simple_loss=0.1987, pruned_loss=0.0273, over 4950.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03133, over 971202.62 frames.], batch size: 21, lr: 1.67e-04
2022-05-07 20:33:49,885 INFO [train.py:715] (4/8) Epoch 13, batch 24200, loss[loss=0.1156, simple_loss=0.1829, pruned_loss=0.02416, over 4913.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03139, over 971560.97 frames.], batch size: 17, lr: 1.67e-04
2022-05-07 20:34:28,087 INFO [train.py:715] (4/8) Epoch 13, batch 24250, loss[loss=0.1128, simple_loss=0.1897, pruned_loss=0.01797, over 4822.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.03084, over 972637.62 frames.], batch size: 12, lr: 1.67e-04
2022-05-07 20:35:06,952 INFO [train.py:715] (4/8) Epoch 13, batch 24300, loss[loss=0.1481, simple_loss=0.2236, pruned_loss=0.03624, over 4872.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03044, over 972582.44 frames.], batch size: 20, lr: 1.67e-04
2022-05-07 20:35:45,650 INFO [train.py:715] (4/8) Epoch 13, batch 24350, loss[loss=0.1109, simple_loss=0.1807, pruned_loss=0.02054, over 4747.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03036, over 971758.86 frames.], batch size: 16, lr: 1.67e-04
2022-05-07 20:36:23,175 INFO [train.py:715] (4/8) Epoch 13, batch 24400, loss[loss=0.1152, simple_loss=0.1916, pruned_loss=0.01943, over 4975.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03059, over 972058.11 frames.], batch size: 25, lr: 1.67e-04
2022-05-07 20:37:01,582 INFO [train.py:715] (4/8) Epoch 13, batch 24450, loss[loss=0.1587, simple_loss=0.2251, pruned_loss=0.04611, over 4773.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03117, over 971610.87 frames.], batch size: 18, lr: 1.67e-04
2022-05-07 20:37:40,237 INFO [train.py:715] (4/8) Epoch 13, batch 24500, loss[loss=0.1264, simple_loss=0.1977, pruned_loss=0.02754, over 4993.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2107, pruned_loss=0.03153, over 971583.36 frames.], batch size: 16, lr: 1.67e-04
2022-05-07 20:38:18,537 INFO [train.py:715] (4/8) Epoch 13, batch 24550, loss[loss=0.1266, simple_loss=0.1933, pruned_loss=0.02995, over 4917.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03123, over 971395.69 frames.], batch size: 23, lr: 1.67e-04
2022-05-07 20:38:56,898 INFO [train.py:715] (4/8) Epoch 13, batch 24600, loss[loss=0.1432, simple_loss=0.2264, pruned_loss=0.03003, over 4767.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03108, over 971076.90 frames.], batch size: 14, lr: 1.67e-04
2022-05-07 20:39:36,089 INFO [train.py:715] (4/8) Epoch 13, batch 24650, loss[loss=0.1262, simple_loss=0.2061, pruned_loss=0.02313, over 4804.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.031, over 971262.10 frames.], batch size: 25, lr: 1.67e-04
2022-05-07 20:40:14,989 INFO [train.py:715] (4/8) Epoch 13, batch 24700, loss[loss=0.1388, simple_loss=0.2097, pruned_loss=0.0339, over 4808.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03092, over 971532.05 frames.], batch size: 25, lr: 1.67e-04
2022-05-07 20:40:52,895 INFO [train.py:715] (4/8) Epoch 13, batch 24750, loss[loss=0.1121, simple_loss=0.1857, pruned_loss=0.0192, over 4834.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03084, over 970989.28 frames.], batch size: 13, lr: 1.67e-04
2022-05-07 20:41:31,284 INFO [train.py:715] (4/8) Epoch 13, batch 24800, loss[loss=0.1417, simple_loss=0.2086, pruned_loss=0.03741, over 4988.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.0307, over 971102.31 frames.], batch size: 28, lr: 1.67e-04
2022-05-07 20:42:10,092 INFO [train.py:715] (4/8) Epoch 13, batch 24850, loss[loss=0.1544, simple_loss=0.2241, pruned_loss=0.04235, over 4977.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03035, over 971668.76 frames.], batch size: 14, lr: 1.66e-04
2022-05-07 20:42:48,217 INFO [train.py:715] (4/8) Epoch 13, batch 24900, loss[loss=0.1647, simple_loss=0.2419, pruned_loss=0.0437, over 4862.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03046, over 972109.89 frames.], batch size: 20, lr: 1.66e-04
2022-05-07 20:43:26,335 INFO [train.py:715] (4/8) Epoch 13, batch 24950, loss[loss=0.1221, simple_loss=0.1965, pruned_loss=0.02382, over 4885.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03017, over 972487.95 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 20:44:04,944 INFO [train.py:715] (4/8) Epoch 13, batch 25000, loss[loss=0.1145, simple_loss=0.178, pruned_loss=0.02553, over 4793.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03037, over 973142.90 frames.], batch size: 24, lr: 1.66e-04
2022-05-07 20:44:43,239 INFO [train.py:715] (4/8) Epoch 13, batch 25050, loss[loss=0.1489, simple_loss=0.2339, pruned_loss=0.03194, over 4927.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2093, pruned_loss=0.03055, over 972843.43 frames.], batch size: 23, lr: 1.66e-04
2022-05-07 20:45:20,925 INFO [train.py:715] (4/8) Epoch 13, batch 25100, loss[loss=0.1422, simple_loss=0.2059, pruned_loss=0.03928, over 4738.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03042, over 973218.38 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 20:46:00,045 INFO [train.py:715] (4/8) Epoch 13, batch 25150, loss[loss=0.1136, simple_loss=0.1925, pruned_loss=0.01739, over 4895.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2094, pruned_loss=0.03043, over 972281.53 frames.], batch size: 22, lr: 1.66e-04
2022-05-07 20:46:38,587 INFO [train.py:715] (4/8) Epoch 13, batch 25200, loss[loss=0.1341, simple_loss=0.2016, pruned_loss=0.03327, over 4982.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2092, pruned_loss=0.03018, over 973312.66 frames.], batch size: 31, lr: 1.66e-04
2022-05-07 20:47:17,720 INFO [train.py:715] (4/8) Epoch 13, batch 25250, loss[loss=0.1249, simple_loss=0.1975, pruned_loss=0.02621, over 4762.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2095, pruned_loss=0.03048, over 972921.03 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 20:47:55,930 INFO [train.py:715] (4/8) Epoch 13, batch 25300, loss[loss=0.1548, simple_loss=0.2268, pruned_loss=0.0414, over 4885.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03081, over 972166.51 frames.], batch size: 22, lr: 1.66e-04
2022-05-07 20:48:34,493 INFO [train.py:715] (4/8) Epoch 13, batch 25350, loss[loss=0.1376, simple_loss=0.2051, pruned_loss=0.03504, over 4824.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.03127, over 972220.30 frames.], batch size: 27, lr: 1.66e-04
2022-05-07 20:49:13,703 INFO [train.py:715] (4/8) Epoch 13, batch 25400, loss[loss=0.111, simple_loss=0.1883, pruned_loss=0.01682, over 4826.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03079, over 972298.29 frames.], batch size: 13, lr: 1.66e-04
2022-05-07 20:49:51,567 INFO [train.py:715] (4/8) Epoch 13, batch 25450, loss[loss=0.1463, simple_loss=0.2135, pruned_loss=0.03956, over 4938.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03143, over 972033.77 frames.], batch size: 23, lr: 1.66e-04
2022-05-07 20:50:30,631 INFO [train.py:715] (4/8) Epoch 13, batch 25500, loss[loss=0.1242, simple_loss=0.1974, pruned_loss=0.02556, over 4956.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03157, over 972469.67 frames.], batch size: 14, lr: 1.66e-04
2022-05-07 20:51:09,204 INFO [train.py:715] (4/8) Epoch 13, batch 25550, loss[loss=0.1458, simple_loss=0.2084, pruned_loss=0.04156, over 4912.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03156, over 973040.07 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 20:51:47,750 INFO [train.py:715] (4/8) Epoch 13, batch 25600, loss[loss=0.1414, simple_loss=0.2145, pruned_loss=0.03413, over 4910.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03165, over 973391.12 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 20:52:25,799 INFO [train.py:715] (4/8) Epoch 13, batch 25650, loss[loss=0.1885, simple_loss=0.2587, pruned_loss=0.05916, over 4939.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03151, over 972724.15 frames.], batch size: 39, lr: 1.66e-04
2022-05-07 20:53:05,135 INFO [train.py:715] (4/8) Epoch 13, batch 25700, loss[loss=0.1348, simple_loss=0.2052, pruned_loss=0.03222, over 4795.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2104, pruned_loss=0.03168, over 972300.33 frames.], batch size: 24, lr: 1.66e-04
2022-05-07 20:53:43,488 INFO [train.py:715] (4/8) Epoch 13, batch 25750, loss[loss=0.1258, simple_loss=0.1938, pruned_loss=0.02883, over 4977.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03185, over 971511.05 frames.], batch size: 14, lr: 1.66e-04
2022-05-07 20:54:21,675 INFO [train.py:715] (4/8) Epoch 13, batch 25800, loss[loss=0.1113, simple_loss=0.1909, pruned_loss=0.01589, over 4814.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2095, pruned_loss=0.03166, over 971145.36 frames.], batch size: 27, lr: 1.66e-04
2022-05-07 20:55:00,567 INFO [train.py:715] (4/8) Epoch 13, batch 25850, loss[loss=0.1339, simple_loss=0.2141, pruned_loss=0.0269, over 4921.00 frames.], tot_loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03082, over 970653.32 frames.], batch size: 29, lr: 1.66e-04
2022-05-07 20:55:39,359 INFO [train.py:715] (4/8) Epoch 13, batch 25900, loss[loss=0.1461, simple_loss=0.2132, pruned_loss=0.03945, over 4958.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2081, pruned_loss=0.03066, over 971062.51 frames.], batch size: 24, lr: 1.66e-04
2022-05-07 20:56:18,196 INFO [train.py:715] (4/8) Epoch 13, batch 25950, loss[loss=0.1322, simple_loss=0.1991, pruned_loss=0.0327, over 4872.00 frames.], tot_loss[loss=0.135, simple_loss=0.2082, pruned_loss=0.03092, over 971883.34 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 20:56:57,182 INFO [train.py:715] (4/8) Epoch 13, batch 26000, loss[loss=0.1416, simple_loss=0.2165, pruned_loss=0.03338, over 4976.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03135, over 972425.43 frames.], batch size: 28, lr: 1.66e-04
2022-05-07 20:57:36,543 INFO [train.py:715] (4/8) Epoch 13, batch 26050, loss[loss=0.12, simple_loss=0.194, pruned_loss=0.02294, over 4787.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03053, over 972283.43 frames.], batch size: 14, lr: 1.66e-04
2022-05-07 20:58:15,740 INFO [train.py:715] (4/8) Epoch 13, batch 26100, loss[loss=0.1469, simple_loss=0.218, pruned_loss=0.03795, over 4766.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2079, pruned_loss=0.03036, over 972169.27 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 20:58:54,124 INFO [train.py:715] (4/8) Epoch 13, batch 26150, loss[loss=0.1258, simple_loss=0.1913, pruned_loss=0.03011, over 4660.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03075, over 970906.55 frames.], batch size: 13, lr: 1.66e-04
2022-05-07 20:59:33,346 INFO [train.py:715] (4/8) Epoch 13, batch 26200, loss[loss=0.1417, simple_loss=0.2136, pruned_loss=0.03492, over 4847.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2087, pruned_loss=0.03098, over 970949.18 frames.], batch size: 20, lr: 1.66e-04
2022-05-07 21:00:12,171 INFO [train.py:715] (4/8) Epoch 13, batch 26250, loss[loss=0.1812, simple_loss=0.2524, pruned_loss=0.05503, over 4777.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.03146, over 970938.27 frames.], batch size: 14, lr: 1.66e-04
2022-05-07 21:00:50,345 INFO [train.py:715] (4/8) Epoch 13, batch 26300, loss[loss=0.1487, simple_loss=0.2258, pruned_loss=0.03583, over 4988.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.03122, over 971043.47 frames.], batch size: 25, lr: 1.66e-04
2022-05-07 21:01:28,298 INFO [train.py:715] (4/8) Epoch 13, batch 26350, loss[loss=0.1452, simple_loss=0.2262, pruned_loss=0.03211, over 4832.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.0309, over 971567.58 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:02:07,165 INFO [train.py:715] (4/8) Epoch 13, batch 26400, loss[loss=0.1254, simple_loss=0.2039, pruned_loss=0.02344, over 4929.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.03142, over 971029.24 frames.], batch size: 29, lr: 1.66e-04
2022-05-07 21:02:46,112 INFO [train.py:715] (4/8) Epoch 13, batch 26450, loss[loss=0.1534, simple_loss=0.2193, pruned_loss=0.04377, over 4855.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03164, over 971430.60 frames.], batch size: 34, lr: 1.66e-04
2022-05-07 21:03:24,279 INFO [train.py:715] (4/8) Epoch 13, batch 26500, loss[loss=0.1047, simple_loss=0.1676, pruned_loss=0.02089, over 4966.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2087, pruned_loss=0.03128, over 971994.17 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:04:03,399 INFO [train.py:715] (4/8) Epoch 13, batch 26550, loss[loss=0.1268, simple_loss=0.2034, pruned_loss=0.0251, over 4888.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2081, pruned_loss=0.03061, over 972124.39 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 21:04:41,839 INFO [train.py:715] (4/8) Epoch 13, batch 26600, loss[loss=0.1242, simple_loss=0.2012, pruned_loss=0.02362, over 4906.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2082, pruned_loss=0.03082, over 971740.04 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:05:20,067 INFO [train.py:715] (4/8) Epoch 13, batch 26650, loss[loss=0.1349, simple_loss=0.216, pruned_loss=0.02692, over 4984.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03091, over 971767.13 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:05:58,316 INFO [train.py:715] (4/8) Epoch 13, batch 26700, loss[loss=0.1537, simple_loss=0.2295, pruned_loss=0.0389, over 4771.00 frames.], tot_loss[loss=0.1363, simple_loss=0.21, pruned_loss=0.03135, over 972101.30 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 21:06:37,482 INFO [train.py:715] (4/8) Epoch 13, batch 26750, loss[loss=0.1118, simple_loss=0.1898, pruned_loss=0.01691, over 4975.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2093, pruned_loss=0.03132, over 972626.66 frames.], batch size: 28, lr: 1.66e-04
2022-05-07 21:07:15,990 INFO [train.py:715] (4/8) Epoch 13, batch 26800, loss[loss=0.139, simple_loss=0.2135, pruned_loss=0.03227, over 4766.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2094, pruned_loss=0.03176, over 972505.70 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 21:07:54,603 INFO [train.py:715] (4/8) Epoch 13, batch 26850, loss[loss=0.1157, simple_loss=0.1848, pruned_loss=0.02328, over 4804.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03135, over 972770.15 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 21:08:33,348 INFO [train.py:715] (4/8) Epoch 13, batch 26900, loss[loss=0.1189, simple_loss=0.1939, pruned_loss=0.02194, over 4791.00 frames.], tot_loss[loss=0.1358, simple_loss=0.209, pruned_loss=0.03133, over 971872.52 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:09:11,796 INFO [train.py:715] (4/8) Epoch 13, batch 26950, loss[loss=0.1143, simple_loss=0.1916, pruned_loss=0.01848, over 4799.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2094, pruned_loss=0.03162, over 971830.73 frames.], batch size: 25, lr: 1.66e-04
2022-05-07 21:09:50,379 INFO [train.py:715] (4/8) Epoch 13, batch 27000, loss[loss=0.1794, simple_loss=0.2363, pruned_loss=0.06123, over 4868.00 frames.], tot_loss[loss=0.1362, simple_loss=0.209, pruned_loss=0.03167, over 971319.74 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 21:09:50,380 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 21:09:59,935 INFO [train.py:742] (4/8) Epoch 13, validation: loss=0.1053, simple_loss=0.1891, pruned_loss=0.01077, over 914524.00 frames.
2022-05-07 21:10:39,028 INFO [train.py:715] (4/8) Epoch 13, batch 27050, loss[loss=0.1204, simple_loss=0.1966, pruned_loss=0.02216, over 4784.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2098, pruned_loss=0.03168, over 971636.60 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:11:17,913 INFO [train.py:715] (4/8) Epoch 13, batch 27100, loss[loss=0.1238, simple_loss=0.1901, pruned_loss=0.02879, over 4908.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03134, over 971842.20 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:11:57,147 INFO [train.py:715] (4/8) Epoch 13, batch 27150, loss[loss=0.1226, simple_loss=0.1972, pruned_loss=0.02405, over 4825.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03114, over 972500.71 frames.], batch size: 27, lr: 1.66e-04
2022-05-07 21:12:36,111 INFO [train.py:715] (4/8) Epoch 13, batch 27200, loss[loss=0.1156, simple_loss=0.181, pruned_loss=0.0251, over 4828.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03101, over 972613.95 frames.], batch size: 13, lr: 1.66e-04
2022-05-07 21:13:14,912 INFO [train.py:715] (4/8) Epoch 13, batch 27250, loss[loss=0.1348, simple_loss=0.2145, pruned_loss=0.02759, over 4927.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.0313, over 972444.15 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:13:54,908 INFO [train.py:715] (4/8) Epoch 13, batch 27300, loss[loss=0.1186, simple_loss=0.1972, pruned_loss=0.01997, over 4977.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.0314, over 971467.98 frames.], batch size: 25, lr: 1.66e-04
2022-05-07 21:14:33,864 INFO [train.py:715] (4/8) Epoch 13, batch 27350, loss[loss=0.1839, simple_loss=0.2409, pruned_loss=0.06344, over 4923.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2105, pruned_loss=0.03142, over 970957.73 frames.], batch size: 23, lr: 1.66e-04
2022-05-07 21:15:11,632 INFO [train.py:715] (4/8) Epoch 13, batch 27400, loss[loss=0.156, simple_loss=0.2332, pruned_loss=0.03938, over 4846.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03123, over 971665.87 frames.], batch size: 30, lr: 1.66e-04
2022-05-07 21:15:49,744 INFO [train.py:715] (4/8) Epoch 13, batch 27450, loss[loss=0.1241, simple_loss=0.1903, pruned_loss=0.02893, over 4888.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03093, over 972055.46 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 21:16:30,590 INFO [train.py:715] (4/8) Epoch 13, batch 27500, loss[loss=0.1365, simple_loss=0.2117, pruned_loss=0.03066, over 4874.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03104, over 973231.60 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 21:17:08,828 INFO [train.py:715] (4/8) Epoch 13, batch 27550, loss[loss=0.1637, simple_loss=0.243, pruned_loss=0.04217, over 4798.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03111, over 973647.89 frames.], batch size: 24, lr: 1.66e-04
2022-05-07 21:17:46,778 INFO [train.py:715] (4/8) Epoch 13, batch 27600, loss[loss=0.1286, simple_loss=0.197, pruned_loss=0.03008, over 4806.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03085, over 972761.20 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:18:25,957 INFO [train.py:715] (4/8) Epoch 13, batch 27650, loss[loss=0.1283, simple_loss=0.2075, pruned_loss=0.02459, over 4906.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03095, over 973902.02 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 21:19:03,877 INFO [train.py:715] (4/8) Epoch 13, batch 27700, loss[loss=0.1189, simple_loss=0.2061, pruned_loss=0.01586, over 4817.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2086, pruned_loss=0.03098, over 973424.89 frames.], batch size: 26, lr: 1.66e-04
2022-05-07 21:19:42,880 INFO [train.py:715] (4/8) Epoch 13, batch 27750, loss[loss=0.1544, simple_loss=0.2145, pruned_loss=0.04712, over 4799.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2084, pruned_loss=0.03094, over 973223.39 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:20:21,394 INFO [train.py:715] (4/8) Epoch 13, batch 27800, loss[loss=0.1602, simple_loss=0.2247, pruned_loss=0.04787, over 4846.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2078, pruned_loss=0.03075, over 972756.48 frames.], batch size: 30, lr: 1.66e-04
2022-05-07 21:21:00,120 INFO [train.py:715] (4/8) Epoch 13, batch 27850, loss[loss=0.1196, simple_loss=0.1987, pruned_loss=0.02022, over 4763.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2074, pruned_loss=0.03058, over 972739.51 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 21:21:38,315 INFO [train.py:715] (4/8) Epoch 13, batch 27900, loss[loss=0.1478, simple_loss=0.2207, pruned_loss=0.03741, over 4917.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2075, pruned_loss=0.03083, over 973070.28 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:22:16,099 INFO [train.py:715] (4/8) Epoch 13, batch 27950, loss[loss=0.1586, simple_loss=0.2255, pruned_loss=0.04578, over 4855.00 frames.], tot_loss[loss=0.135, simple_loss=0.2082, pruned_loss=0.03088, over 972603.02 frames.], batch size: 32, lr: 1.66e-04
2022-05-07 21:22:55,057 INFO [train.py:715] (4/8) Epoch 13, batch 28000, loss[loss=0.1449, simple_loss=0.2155, pruned_loss=0.03721, over 4971.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03069, over 972967.50 frames.], batch size: 35, lr: 1.66e-04
2022-05-07 21:23:33,525 INFO [train.py:715] (4/8) Epoch 13, batch 28050, loss[loss=0.1272, simple_loss=0.204, pruned_loss=0.02524, over 4884.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.03047, over 972684.34 frames.], batch size: 30, lr: 1.66e-04
2022-05-07 21:24:11,555 INFO [train.py:715] (4/8) Epoch 13, batch 28100, loss[loss=0.1215, simple_loss=0.2031, pruned_loss=0.01996, over 4955.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.03046, over 973799.66 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:24:49,600 INFO [train.py:715] (4/8) Epoch 13, batch 28150, loss[loss=0.1207, simple_loss=0.2037, pruned_loss=0.01887, over 4968.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03094, over 973609.60 frames.], batch size: 24, lr: 1.66e-04
2022-05-07 21:25:28,817 INFO [train.py:715] (4/8) Epoch 13, batch 28200, loss[loss=0.1358, simple_loss=0.2156, pruned_loss=0.02796, over 4755.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2103, pruned_loss=0.03125, over 972420.94 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 21:26:06,612 INFO [train.py:715] (4/8) Epoch 13, batch 28250, loss[loss=0.1545, simple_loss=0.2259, pruned_loss=0.04159, over 4703.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03116, over 970940.66 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:26:44,754 INFO [train.py:715] (4/8) Epoch 13, batch 28300, loss[loss=0.1402, simple_loss=0.2037, pruned_loss=0.03829, over 4821.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03103, over 971401.63 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:27:23,462 INFO [train.py:715] (4/8) Epoch 13, batch 28350, loss[loss=0.1775, simple_loss=0.2415, pruned_loss=0.05671, over 4895.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2101, pruned_loss=0.031, over 971711.51 frames.], batch size: 39, lr: 1.66e-04
2022-05-07 21:28:01,609 INFO [train.py:715] (4/8) Epoch 13, batch 28400, loss[loss=0.118, simple_loss=0.1816, pruned_loss=0.02725, over 4961.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03068, over 971829.56 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:28:40,047 INFO [train.py:715] (4/8) Epoch 13, batch 28450, loss[loss=0.1195, simple_loss=0.195, pruned_loss=0.022, over 4989.00 frames.], tot_loss[loss=0.136, simple_loss=0.21, pruned_loss=0.03105, over 971907.68 frames.], batch size: 26, lr: 1.66e-04
2022-05-07 21:29:18,387 INFO [train.py:715] (4/8) Epoch 13, batch 28500, loss[loss=0.1533, simple_loss=0.2294, pruned_loss=0.03863, over 4803.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03132, over 971811.33 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:29:57,061 INFO [train.py:715] (4/8) Epoch 13, batch 28550, loss[loss=0.1246, simple_loss=0.1888, pruned_loss=0.03019, over 4805.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2106, pruned_loss=0.03117, over 972562.52 frames.], batch size: 13, lr: 1.66e-04
2022-05-07 21:30:35,260 INFO [train.py:715] (4/8) Epoch 13, batch 28600, loss[loss=0.1385, simple_loss=0.2128, pruned_loss=0.0321, over 4899.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2103, pruned_loss=0.03081, over 972867.88 frames.], batch size: 17, lr: 1.66e-04
2022-05-07 21:31:13,617 INFO [train.py:715] (4/8) Epoch 13, batch 28650, loss[loss=0.1178, simple_loss=0.1879, pruned_loss=0.0238, over 4866.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2095, pruned_loss=0.03042, over 972615.13 frames.], batch size: 22, lr: 1.66e-04
2022-05-07 21:31:52,263 INFO [train.py:715] (4/8) Epoch 13, batch 28700, loss[loss=0.1216, simple_loss=0.191, pruned_loss=0.02611, over 4954.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2102, pruned_loss=0.031, over 973423.53 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:32:30,334 INFO [train.py:715] (4/8) Epoch 13, batch 28750, loss[loss=0.1395, simple_loss=0.2116, pruned_loss=0.03366, over 4920.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2104, pruned_loss=0.03088, over 973730.22 frames.], batch size: 39, lr: 1.66e-04
2022-05-07 21:33:08,638 INFO [train.py:715] (4/8) Epoch 13, batch 28800, loss[loss=0.1442, simple_loss=0.2175, pruned_loss=0.03542, over 4943.00 frames.], tot_loss[loss=0.136, simple_loss=0.2106, pruned_loss=0.03072, over 973787.95 frames.], batch size: 29, lr: 1.66e-04
2022-05-07 21:33:47,849 INFO [train.py:715] (4/8) Epoch 13, batch 28850, loss[loss=0.1411, simple_loss=0.2061, pruned_loss=0.03808, over 4877.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2098, pruned_loss=0.03083, over 973356.44 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 21:34:26,367 INFO [train.py:715] (4/8) Epoch 13, batch 28900, loss[loss=0.1366, simple_loss=0.1985, pruned_loss=0.03738, over 4771.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03078, over 972853.87 frames.], batch size: 17, lr: 1.66e-04
2022-05-07 21:35:04,281 INFO [train.py:715] (4/8) Epoch 13, batch 28950, loss[loss=0.1435, simple_loss=0.2215, pruned_loss=0.03279, over 4763.00 frames.], tot_loss[loss=0.136, simple_loss=0.21, pruned_loss=0.03099, over 972884.78 frames.], batch size: 19, lr: 1.66e-04
2022-05-07 21:35:42,446 INFO [train.py:715] (4/8) Epoch 13, batch 29000, loss[loss=0.1296, simple_loss=0.2017, pruned_loss=0.02877, over 4774.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2107, pruned_loss=0.03138, over 973119.91 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 21:36:21,625 INFO [train.py:715] (4/8) Epoch 13, batch 29050, loss[loss=0.1398, simple_loss=0.2162, pruned_loss=0.03175, over 4945.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2103, pruned_loss=0.03123, over 972909.21 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:37:00,159 INFO [train.py:715] (4/8) Epoch 13, batch 29100, loss[loss=0.1415, simple_loss=0.2161, pruned_loss=0.0334, over 4918.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2107, pruned_loss=0.03119, over 972553.53 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:37:38,205 INFO [train.py:715] (4/8) Epoch 13, batch 29150, loss[loss=0.1236, simple_loss=0.2046, pruned_loss=0.02127, over 4990.00 frames.], tot_loss[loss=0.136, simple_loss=0.2102, pruned_loss=0.03091, over 972629.54 frames.], batch size: 25, lr: 1.66e-04
2022-05-07 21:38:16,963 INFO [train.py:715] (4/8) Epoch 13, batch 29200, loss[loss=0.1446, simple_loss=0.2134, pruned_loss=0.03793, over 4822.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03094, over 972069.44 frames.], batch size: 25, lr: 1.66e-04
2022-05-07 21:38:55,212 INFO [train.py:715] (4/8) Epoch 13, batch 29250, loss[loss=0.1303, simple_loss=0.2057, pruned_loss=0.0274, over 4952.00 frames.], tot_loss[loss=0.1358, simple_loss=0.21, pruned_loss=0.03076, over 972237.98 frames.], batch size: 24, lr: 1.66e-04
2022-05-07 21:39:34,052 INFO [train.py:715] (4/8) Epoch 13, batch 29300, loss[loss=0.1406, simple_loss=0.2173, pruned_loss=0.03198, over 4808.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03116, over 971850.03 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:40:12,800 INFO [train.py:715] (4/8) Epoch 13, batch 29350, loss[loss=0.1342, simple_loss=0.1967, pruned_loss=0.03586, over 4909.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.03125, over 971396.16 frames.], batch size: 17, lr: 1.66e-04
2022-05-07 21:40:51,676 INFO [train.py:715] (4/8) Epoch 13, batch 29400, loss[loss=0.1379, simple_loss=0.2135, pruned_loss=0.03117, over 4911.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.03131, over 971141.60 frames.], batch size: 17, lr: 1.66e-04
2022-05-07 21:41:29,698 INFO [train.py:715] (4/8) Epoch 13, batch 29450, loss[loss=0.1472, simple_loss=0.2256, pruned_loss=0.03445, over 4806.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03092, over 971201.92 frames.], batch size: 25, lr: 1.66e-04
2022-05-07 21:42:08,738 INFO [train.py:715] (4/8) Epoch 13, batch 29500, loss[loss=0.1226, simple_loss=0.2026, pruned_loss=0.0213, over 4802.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.03106, over 971225.23 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:42:47,371 INFO [train.py:715] (4/8) Epoch 13, batch 29550, loss[loss=0.1191, simple_loss=0.1964, pruned_loss=0.02088, over 4980.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03073, over 971746.10 frames.], batch size: 24, lr: 1.66e-04
2022-05-07 21:43:25,735 INFO [train.py:715] (4/8) Epoch 13, batch 29600, loss[loss=0.1425, simple_loss=0.225, pruned_loss=0.02997, over 4987.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03097, over 972880.77 frames.], batch size: 25, lr: 1.66e-04
2022-05-07 21:44:03,483 INFO [train.py:715] (4/8) Epoch 13, batch 29650, loss[loss=0.1288, simple_loss=0.1999, pruned_loss=0.02883, over 4955.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.0315, over 973365.56 frames.], batch size: 35, lr: 1.66e-04
2022-05-07 21:44:41,768 INFO [train.py:715] (4/8) Epoch 13, batch 29700, loss[loss=0.1213, simple_loss=0.1901, pruned_loss=0.0263, over 4925.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2086, pruned_loss=0.03141, over 973965.77 frames.], batch size: 29, lr: 1.66e-04
2022-05-07 21:45:20,121 INFO [train.py:715] (4/8) Epoch 13, batch 29750, loss[loss=0.1649, simple_loss=0.2227, pruned_loss=0.05352, over 4796.00 frames.], tot_loss[loss=0.136, simple_loss=0.209, pruned_loss=0.03151, over 973310.42 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 21:45:59,493 INFO [train.py:715] (4/8) Epoch 13, batch 29800, loss[loss=0.1396, simple_loss=0.1996, pruned_loss=0.03982, over 4826.00 frames.], tot_loss[loss=0.136, simple_loss=0.2092, pruned_loss=0.03137, over 974200.05 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:46:38,721 INFO [train.py:715] (4/8) Epoch 13, batch 29850, loss[loss=0.1482, simple_loss=0.2258, pruned_loss=0.03534, over 4818.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03131, over 973584.30 frames.], batch size: 26, lr: 1.66e-04
2022-05-07 21:47:18,328 INFO [train.py:715] (4/8) Epoch 13, batch 29900, loss[loss=0.1242, simple_loss=0.1959, pruned_loss=0.0262, over 4910.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03122, over 973258.36 frames.], batch size: 23, lr: 1.66e-04
2022-05-07 21:47:57,739 INFO [train.py:715] (4/8) Epoch 13, batch 29950, loss[loss=0.09875, simple_loss=0.1669, pruned_loss=0.01529, over 4784.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2101, pruned_loss=0.03156, over 973054.41 frames.], batch size: 14, lr: 1.66e-04
2022-05-07 21:48:36,357 INFO [train.py:715] (4/8) Epoch 13, batch 30000, loss[loss=0.1493, simple_loss=0.227, pruned_loss=0.03581, over 4976.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2106, pruned_loss=0.03124, over 973527.91 frames.], batch size: 24, lr: 1.66e-04
2022-05-07 21:48:36,358 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 21:48:45,861 INFO [train.py:742] (4/8) Epoch 13, validation: loss=0.1054, simple_loss=0.1891, pruned_loss=0.01083, over 914524.00 frames.
2022-05-07 21:49:25,289 INFO [train.py:715] (4/8) Epoch 13, batch 30050, loss[loss=0.1797, simple_loss=0.2459, pruned_loss=0.05677, over 4742.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.0316, over 973699.75 frames.], batch size: 16, lr: 1.66e-04
2022-05-07 21:50:05,103 INFO [train.py:715] (4/8) Epoch 13, batch 30100, loss[loss=0.1294, simple_loss=0.1982, pruned_loss=0.03027, over 4822.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2111, pruned_loss=0.0316, over 973867.74 frames.], batch size: 26, lr: 1.66e-04
2022-05-07 21:50:44,574 INFO [train.py:715] (4/8) Epoch 13, batch 30150, loss[loss=0.1361, simple_loss=0.2104, pruned_loss=0.03093, over 4829.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03153, over 973887.77 frames.], batch size: 30, lr: 1.66e-04
2022-05-07 21:51:23,150 INFO [train.py:715] (4/8) Epoch 13, batch 30200, loss[loss=0.1359, simple_loss=0.2044, pruned_loss=0.03373, over 4841.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2104, pruned_loss=0.03189, over 973416.73 frames.], batch size: 30, lr: 1.66e-04
2022-05-07 21:52:02,987 INFO [train.py:715] (4/8) Epoch 13, batch 30250, loss[loss=0.1388, simple_loss=0.2182, pruned_loss=0.02972, over 4794.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2101, pruned_loss=0.03179, over 972787.08 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:52:42,784 INFO [train.py:715] (4/8) Epoch 13, batch 30300, loss[loss=0.1758, simple_loss=0.2432, pruned_loss=0.05419, over 4990.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03157, over 973226.82 frames.], batch size: 25, lr: 1.66e-04
2022-05-07 21:53:22,297 INFO [train.py:715] (4/8) Epoch 13, batch 30350, loss[loss=0.1328, simple_loss=0.2047, pruned_loss=0.03048, over 4932.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03132, over 973574.00 frames.], batch size: 18, lr: 1.66e-04
2022-05-07 21:54:01,876 INFO [train.py:715] (4/8) Epoch 13, batch 30400, loss[loss=0.1395, simple_loss=0.2088, pruned_loss=0.03512, over 4878.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.0312, over 973585.15 frames.], batch size: 32, lr: 1.66e-04
2022-05-07 21:54:42,497 INFO [train.py:715] (4/8) Epoch 13, batch 30450, loss[loss=0.1278, simple_loss=0.1945, pruned_loss=0.03053, over 4821.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2099, pruned_loss=0.03156, over 973644.81 frames.], batch size: 12, lr: 1.66e-04
2022-05-07 21:55:22,603 INFO [train.py:715] (4/8) Epoch 13, batch 30500, loss[loss=0.1587, simple_loss=0.2292, pruned_loss=0.04407, over 4963.00 frames.], tot_loss[loss=0.137, simple_loss=0.2103, pruned_loss=0.03179, over 973068.95 frames.], batch size: 35, lr: 1.66e-04
2022-05-07 21:56:02,391 INFO [train.py:715] (4/8) Epoch 13, batch 30550, loss[loss=0.1385, simple_loss=0.2107, pruned_loss=0.03319, over 4940.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2103, pruned_loss=0.03171, over 972620.65 frames.], batch size: 21, lr: 1.66e-04
2022-05-07 21:56:43,827 INFO [train.py:715] (4/8) Epoch 13, batch 30600, loss[loss=0.1539, simple_loss=0.2315, pruned_loss=0.03821, over 4949.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2102, pruned_loss=0.03167, over 972629.35 frames.], batch size: 15, lr: 1.66e-04
2022-05-07 21:57:24,944 INFO [train.py:715] (4/8) Epoch 13, batch 30650, loss[loss=0.1453, simple_loss=0.2109, pruned_loss=0.0398, over 4985.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2106, pruned_loss=0.03201, over 973384.46 frames.], batch size: 25, lr: 1.65e-04
2022-05-07 21:58:05,363 INFO [train.py:715] (4/8) Epoch 13, batch 30700, loss[loss=0.129, simple_loss=0.2013, pruned_loss=0.02832, over 4803.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2107, pruned_loss=0.03172, over 972944.45 frames.], batch size: 21, lr: 1.65e-04
2022-05-07 21:58:45,822 INFO [train.py:715] (4/8) Epoch 13, batch 30750, loss[loss=0.1206, simple_loss=0.195, pruned_loss=0.02314, over 4805.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03171, over 972390.61 frames.], batch size: 12, lr: 1.65e-04
2022-05-07 21:59:26,811 INFO [train.py:715] (4/8) Epoch 13, batch 30800, loss[loss=0.1573, simple_loss=0.236, pruned_loss=0.03937, over 4751.00 frames.], tot_loss[loss=0.1374, simple_loss=0.2109, pruned_loss=0.03197, over 972091.70 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:00:07,573 INFO [train.py:715] (4/8) Epoch 13, batch 30850, loss[loss=0.144, simple_loss=0.2181, pruned_loss=0.03493, over 4897.00 frames.], tot_loss[loss=0.137, simple_loss=0.2107, pruned_loss=0.03164, over 971855.81 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:00:48,200 INFO [train.py:715] (4/8) Epoch 13, batch 30900, loss[loss=0.1446, simple_loss=0.2154, pruned_loss=0.03694, over 4720.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03093, over 971813.26 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:01:29,261 INFO [train.py:715] (4/8) Epoch 13, batch 30950, loss[loss=0.1392, simple_loss=0.2273, pruned_loss=0.02559, over 4992.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.03059, over 972146.52 frames.], batch size: 28, lr: 1.65e-04
2022-05-07 22:02:09,959 INFO [train.py:715] (4/8) Epoch 13, batch 31000, loss[loss=0.1397, simple_loss=0.2072, pruned_loss=0.03608, over 4970.00 frames.], tot_loss[loss=0.136, simple_loss=0.2103, pruned_loss=0.03087, over 972438.97 frames.], batch size: 15, lr: 1.65e-04
2022-05-07 22:02:50,135 INFO [train.py:715] (4/8) Epoch 13, batch 31050, loss[loss=0.1841, simple_loss=0.2505, pruned_loss=0.05887, over 4988.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2104, pruned_loss=0.03129, over 972787.13 frames.], batch size: 25, lr: 1.65e-04
2022-05-07 22:03:30,703 INFO [train.py:715] (4/8) Epoch 13, batch 31100, loss[loss=0.1301, simple_loss=0.2046, pruned_loss=0.02779, over 4987.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03092, over 973132.61 frames.], batch size: 20, lr: 1.65e-04
2022-05-07 22:04:11,675 INFO [train.py:715] (4/8) Epoch 13, batch 31150, loss[loss=0.1549, simple_loss=0.2276, pruned_loss=0.04116, over 4976.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03111, over 972700.41 frames.], batch size: 15, lr: 1.65e-04
2022-05-07 22:04:52,781 INFO [train.py:715] (4/8) Epoch 13, batch 31200, loss[loss=0.1154, simple_loss=0.1938, pruned_loss=0.01849, over 4903.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03107, over 972165.21 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:05:32,914 INFO [train.py:715] (4/8) Epoch 13, batch 31250, loss[loss=0.1311, simple_loss=0.2084, pruned_loss=0.02686, over 4968.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03125, over 972974.16 frames.], batch size: 28, lr: 1.65e-04
2022-05-07 22:06:13,229 INFO [train.py:715] (4/8) Epoch 13, batch 31300, loss[loss=0.1315, simple_loss=0.2021, pruned_loss=0.03046, over 4809.00 frames.], tot_loss[loss=0.1359, simple_loss=0.209, pruned_loss=0.03145, over 973531.02 frames.], batch size: 21, lr: 1.65e-04
2022-05-07 22:06:53,507 INFO [train.py:715] (4/8) Epoch 13, batch 31350, loss[loss=0.1556, simple_loss=0.2326, pruned_loss=0.03926, over 4860.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2098, pruned_loss=0.03189, over 973768.29 frames.], batch size: 32, lr: 1.65e-04
2022-05-07 22:07:33,254 INFO [train.py:715] (4/8) Epoch 13, batch 31400, loss[loss=0.1467, simple_loss=0.2154, pruned_loss=0.039, over 4953.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2094, pruned_loss=0.03162, over 973209.05 frames.], batch size: 24, lr: 1.65e-04
2022-05-07 22:08:13,731 INFO [train.py:715] (4/8) Epoch 13, batch 31450, loss[loss=0.1331, simple_loss=0.2048, pruned_loss=0.03072, over 4878.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.0313, over 972468.59 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:08:54,096 INFO [train.py:715] (4/8) Epoch 13, batch 31500, loss[loss=0.1498, simple_loss=0.2276, pruned_loss=0.03606, over 4779.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.03125, over 972579.50 frames.], batch size: 17, lr: 1.65e-04
2022-05-07 22:09:33,916 INFO [train.py:715] (4/8) Epoch 13, batch 31550, loss[loss=0.1591, simple_loss=0.2389, pruned_loss=0.03966, over 4865.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03094, over 972523.73 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:10:14,437 INFO [train.py:715] (4/8) Epoch 13, batch 31600, loss[loss=0.121, simple_loss=0.2034, pruned_loss=0.01932, over 4813.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03101, over 973007.31 frames.], batch size: 27, lr: 1.65e-04
2022-05-07 22:10:55,005 INFO [train.py:715] (4/8) Epoch 13, batch 31650, loss[loss=0.1339, simple_loss=0.2146, pruned_loss=0.02663, over 4788.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03116, over 973126.96 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:11:35,394 INFO [train.py:715] (4/8) Epoch 13, batch 31700, loss[loss=0.1691, simple_loss=0.2397, pruned_loss=0.04922, over 4975.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.03115, over 973348.67 frames.], batch size: 15, lr: 1.65e-04
2022-05-07 22:12:15,832 INFO [train.py:715] (4/8) Epoch 13, batch 31750, loss[loss=0.1351, simple_loss=0.2064, pruned_loss=0.03189, over 4907.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.0314, over 973092.64 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:12:56,361 INFO [train.py:715] (4/8) Epoch 13, batch 31800, loss[loss=0.1583, simple_loss=0.2268, pruned_loss=0.04487, over 4827.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2113, pruned_loss=0.03166, over 973001.89 frames.], batch size: 27, lr: 1.65e-04
2022-05-07 22:13:37,269 INFO [train.py:715] (4/8) Epoch 13, batch 31850, loss[loss=0.1374, simple_loss=0.224, pruned_loss=0.02535, over 4904.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03161, over 973354.16 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:14:18,118 INFO [train.py:715] (4/8) Epoch 13, batch 31900, loss[loss=0.1352, simple_loss=0.2027, pruned_loss=0.03382, over 4856.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03131, over 973046.20 frames.], batch size: 32, lr: 1.65e-04
2022-05-07 22:14:59,149 INFO [train.py:715] (4/8) Epoch 13, batch 31950, loss[loss=0.1386, simple_loss=0.2155, pruned_loss=0.0309, over 4938.00 frames.], tot_loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03159, over 973437.58 frames.], batch size: 29, lr: 1.65e-04
2022-05-07 22:15:39,538 INFO [train.py:715] (4/8) Epoch 13, batch 32000, loss[loss=0.1217, simple_loss=0.1989, pruned_loss=0.02219, over 4951.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.03109, over 973385.01 frames.], batch size: 24, lr: 1.65e-04
2022-05-07 22:16:20,148 INFO [train.py:715] (4/8) Epoch 13, batch 32050, loss[loss=0.1279, simple_loss=0.2105, pruned_loss=0.02266, over 4808.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2106, pruned_loss=0.03152, over 973352.71 frames.], batch size: 24, lr: 1.65e-04
2022-05-07 22:17:00,686 INFO [train.py:715] (4/8) Epoch 13, batch 32100, loss[loss=0.1214, simple_loss=0.1894, pruned_loss=0.02672, over 4969.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03132, over 973331.25 frames.], batch size: 14, lr: 1.65e-04
2022-05-07 22:17:41,700 INFO [train.py:715] (4/8) Epoch 13, batch 32150, loss[loss=0.1465, simple_loss=0.2121, pruned_loss=0.0405, over 4875.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03121, over 973072.08 frames.], batch size: 22, lr: 1.65e-04
2022-05-07 22:18:22,391 INFO [train.py:715] (4/8) Epoch 13, batch 32200, loss[loss=0.1531, simple_loss=0.2228, pruned_loss=0.04173, over 4923.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.0309, over 972522.68 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:19:03,050 INFO [train.py:715] (4/8) Epoch 13, batch 32250, loss[loss=0.1454, simple_loss=0.2258, pruned_loss=0.0325, over 4823.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03057, over 971926.37 frames.], batch size: 26, lr: 1.65e-04
2022-05-07 22:19:43,872 INFO [train.py:715] (4/8) Epoch 13, batch 32300, loss[loss=0.1216, simple_loss=0.2026, pruned_loss=0.02025, over 4740.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03048, over 972920.20 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:20:24,916 INFO [train.py:715] (4/8) Epoch 13, batch 32350, loss[loss=0.1241, simple_loss=0.2058, pruned_loss=0.02117, over 4947.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03046, over 972405.27 frames.], batch size: 39, lr: 1.65e-04
2022-05-07 22:21:06,367 INFO [train.py:715] (4/8) Epoch 13, batch 32400, loss[loss=0.1396, simple_loss=0.2174, pruned_loss=0.03097, over 4891.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03037, over 972147.45 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:21:47,424 INFO [train.py:715] (4/8) Epoch 13, batch 32450, loss[loss=0.1384, simple_loss=0.207, pruned_loss=0.03486, over 4914.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03071, over 972009.65 frames.], batch size: 23, lr: 1.65e-04
2022-05-07 22:22:28,211 INFO [train.py:715] (4/8) Epoch 13, batch 32500, loss[loss=0.1481, simple_loss=0.2203, pruned_loss=0.03792, over 4802.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03064, over 971131.72 frames.], batch size: 21, lr: 1.65e-04
2022-05-07 22:23:09,249 INFO [train.py:715] (4/8) Epoch 13, batch 32550, loss[loss=0.1232, simple_loss=0.1944, pruned_loss=0.026, over 4915.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03046, over 971699.50 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:23:49,646 INFO [train.py:715] (4/8) Epoch 13, batch 32600, loss[loss=0.1463, simple_loss=0.2202, pruned_loss=0.03618, over 4971.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03062, over 972424.47 frames.], batch size: 24, lr: 1.65e-04
2022-05-07 22:24:29,995 INFO [train.py:715] (4/8) Epoch 13, batch 32650, loss[loss=0.1424, simple_loss=0.2183, pruned_loss=0.03327, over 4917.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03106, over 971580.58 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:25:10,589 INFO [train.py:715] (4/8) Epoch 13, batch 32700, loss[loss=0.1332, simple_loss=0.2054, pruned_loss=0.03046, over 4706.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2087, pruned_loss=0.03101, over 971692.41 frames.], batch size: 15, lr: 1.65e-04
2022-05-07 22:25:50,909 INFO [train.py:715] (4/8) Epoch 13, batch 32750, loss[loss=0.1323, simple_loss=0.2026, pruned_loss=0.03101, over 4905.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03077, over 971866.89 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:26:31,932 INFO [train.py:715] (4/8) Epoch 13, batch 32800, loss[loss=0.1263, simple_loss=0.2068, pruned_loss=0.02288, over 4774.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2079, pruned_loss=0.03053, over 972616.95 frames.], batch size: 17, lr: 1.65e-04
2022-05-07 22:27:12,668 INFO [train.py:715] (4/8) Epoch 13, batch 32850, loss[loss=0.1553, simple_loss=0.2258, pruned_loss=0.0424, over 4751.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2073, pruned_loss=0.03022, over 972434.99 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:27:53,744 INFO [train.py:715] (4/8) Epoch 13, batch 32900, loss[loss=0.1218, simple_loss=0.2022, pruned_loss=0.02066, over 4768.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03017, over 972529.24 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:28:33,952 INFO [train.py:715] (4/8) Epoch 13, batch 32950, loss[loss=0.1354, simple_loss=0.2251, pruned_loss=0.02281, over 4975.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03082, over 972849.70 frames.], batch size: 24, lr: 1.65e-04
2022-05-07 22:29:14,625 INFO [train.py:715] (4/8) Epoch 13, batch 33000, loss[loss=0.1421, simple_loss=0.2095, pruned_loss=0.03736, over 4780.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03131, over 973130.27 frames.], batch size: 12, lr: 1.65e-04
2022-05-07 22:29:14,625 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 22:29:24,502 INFO [train.py:742] (4/8) Epoch 13, validation: loss=0.1054, simple_loss=0.1892, pruned_loss=0.01081, over 914524.00 frames.
2022-05-07 22:30:05,549 INFO [train.py:715] (4/8) Epoch 13, batch 33050, loss[loss=0.1434, simple_loss=0.2222, pruned_loss=0.03233, over 4884.00 frames.], tot_loss[loss=0.136, simple_loss=0.2094, pruned_loss=0.03136, over 973469.61 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:30:45,199 INFO [train.py:715] (4/8) Epoch 13, batch 33100, loss[loss=0.1435, simple_loss=0.2162, pruned_loss=0.03542, over 4784.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2087, pruned_loss=0.03105, over 973481.84 frames.], batch size: 17, lr: 1.65e-04
2022-05-07 22:31:25,138 INFO [train.py:715] (4/8) Epoch 13, batch 33150, loss[loss=0.162, simple_loss=0.2449, pruned_loss=0.0396, over 4855.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2094, pruned_loss=0.03157, over 973909.40 frames.], batch size: 20, lr: 1.65e-04
2022-05-07 22:32:05,566 INFO [train.py:715] (4/8) Epoch 13, batch 33200, loss[loss=0.1537, simple_loss=0.2217, pruned_loss=0.04289, over 4761.00 frames.], tot_loss[loss=0.1369, simple_loss=0.21, pruned_loss=0.03192, over 972775.16 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:32:46,027 INFO [train.py:715] (4/8) Epoch 13, batch 33250, loss[loss=0.1373, simple_loss=0.2141, pruned_loss=0.03032, over 4974.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03154, over 972368.03 frames.], batch size: 39, lr: 1.65e-04
2022-05-07 22:33:26,584 INFO [train.py:715] (4/8) Epoch 13, batch 33300, loss[loss=0.1337, simple_loss=0.2188, pruned_loss=0.02427, over 4760.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03135, over 972508.23 frames.], batch size: 16, lr: 1.65e-04
2022-05-07 22:34:07,012 INFO [train.py:715] (4/8) Epoch 13, batch 33350, loss[loss=0.1355, simple_loss=0.2174, pruned_loss=0.02684, over 4797.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03112, over 972140.40 frames.], batch size: 21, lr: 1.65e-04
2022-05-07 22:34:47,630 INFO [train.py:715] (4/8) Epoch 13, batch 33400, loss[loss=0.167, simple_loss=0.2262, pruned_loss=0.05387, over 4951.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.0312, over 971615.21 frames.], batch size: 21, lr: 1.65e-04
2022-05-07 22:35:28,230 INFO [train.py:715] (4/8) Epoch 13, batch 33450, loss[loss=0.1306, simple_loss=0.2012, pruned_loss=0.03004, over 4950.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2092, pruned_loss=0.0313, over 971602.68 frames.], batch size: 21, lr: 1.65e-04
2022-05-07 22:36:08,954 INFO [train.py:715] (4/8) Epoch 13, batch 33500, loss[loss=0.1486, simple_loss=0.2244, pruned_loss=0.03638, over 4906.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03153, over 972355.02 frames.], batch size: 17, lr: 1.65e-04
2022-05-07 22:36:49,602 INFO [train.py:715] (4/8) Epoch 13, batch 33550, loss[loss=0.1363, simple_loss=0.2112, pruned_loss=0.03067, over 4842.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2089, pruned_loss=0.03112, over 972093.80 frames.], batch size: 32, lr: 1.65e-04
2022-05-07 22:37:30,300 INFO [train.py:715] (4/8) Epoch 13, batch 33600, loss[loss=0.148, simple_loss=0.2112, pruned_loss=0.04245, over 4987.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03071, over 972180.66 frames.], batch size: 31, lr: 1.65e-04
2022-05-07 22:38:10,825 INFO [train.py:715] (4/8) Epoch 13, batch 33650, loss[loss=0.139, simple_loss=0.2064, pruned_loss=0.03584, over 4775.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03083, over 971017.77 frames.], batch size: 14, lr: 1.65e-04
2022-05-07 22:38:51,057 INFO [train.py:715] (4/8) Epoch 13, batch 33700, loss[loss=0.1134, simple_loss=0.1945, pruned_loss=0.01612, over 4836.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03082, over 970909.76 frames.], batch size: 26, lr: 1.65e-04
2022-05-07 22:39:32,027 INFO [train.py:715] (4/8) Epoch 13, batch 33750, loss[loss=0.1212, simple_loss=0.2017, pruned_loss=0.02031, over 4920.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2094, pruned_loss=0.03048, over 971511.70 frames.], batch size: 23, lr: 1.65e-04
2022-05-07 22:40:12,824 INFO [train.py:715] (4/8) Epoch 13, batch 33800, loss[loss=0.1296, simple_loss=0.2081, pruned_loss=0.02551, over 4923.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03044, over 971966.72 frames.], batch size: 23, lr: 1.65e-04
2022-05-07 22:40:53,566 INFO [train.py:715] (4/8) Epoch 13, batch 33850, loss[loss=0.1302, simple_loss=0.21, pruned_loss=0.02516, over 4761.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03088, over 971343.60 frames.], batch size: 14, lr: 1.65e-04
2022-05-07 22:41:34,019 INFO [train.py:715] (4/8) Epoch 13, batch 33900, loss[loss=0.1238, simple_loss=0.1988, pruned_loss=0.02439, over 4933.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03064, over 972061.56 frames.], batch size: 23, lr: 1.65e-04
2022-05-07 22:42:15,275 INFO [train.py:715] (4/8) Epoch 13, batch 33950, loss[loss=0.1448, simple_loss=0.2155, pruned_loss=0.03701, over 4794.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.0306, over 971980.47 frames.], batch size: 25, lr: 1.65e-04
2022-05-07 22:42:56,285 INFO [train.py:715] (4/8) Epoch 13, batch 34000, loss[loss=0.1324, simple_loss=0.202, pruned_loss=0.03138, over 4765.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.0308, over 972768.59 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:43:36,853 INFO [train.py:715] (4/8) Epoch 13, batch 34050, loss[loss=0.1228, simple_loss=0.2041, pruned_loss=0.02073, over 4777.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03094, over 972489.85 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:44:17,680 INFO [train.py:715] (4/8) Epoch 13, batch 34100, loss[loss=0.1159, simple_loss=0.1948, pruned_loss=0.01848, over 4970.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.0314, over 972118.30 frames.], batch size: 24, lr: 1.65e-04
2022-05-07 22:44:57,548 INFO [train.py:715] (4/8) Epoch 13, batch 34150, loss[loss=0.1674, simple_loss=0.2302, pruned_loss=0.05225, over 4765.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03101, over 971916.94 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:45:38,241 INFO [train.py:715] (4/8) Epoch 13, batch 34200, loss[loss=0.1346, simple_loss=0.2117, pruned_loss=0.02876, over 4815.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03101, over 972096.06 frames.], batch size: 21, lr: 1.65e-04
2022-05-07 22:46:18,597 INFO [train.py:715] (4/8) Epoch 13, batch 34250, loss[loss=0.1357, simple_loss=0.2148, pruned_loss=0.02828, over 4800.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03108, over 971736.79 frames.], batch size: 21, lr: 1.65e-04
2022-05-07 22:46:59,517 INFO [train.py:715] (4/8) Epoch 13, batch 34300, loss[loss=0.1318, simple_loss=0.2099, pruned_loss=0.02679, over 4977.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03123, over 972267.78 frames.], batch size: 25, lr: 1.65e-04
2022-05-07 22:47:39,589 INFO [train.py:715] (4/8) Epoch 13, batch 34350, loss[loss=0.1387, simple_loss=0.214, pruned_loss=0.03172, over 4800.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03115, over 972410.82 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:48:20,179 INFO [train.py:715] (4/8) Epoch 13, batch 34400, loss[loss=0.1338, simple_loss=0.2139, pruned_loss=0.02682, over 4747.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03098, over 972153.74 frames.], batch size: 19, lr: 1.65e-04
2022-05-07 22:49:01,279 INFO [train.py:715] (4/8) Epoch 13, batch 34450, loss[loss=0.1439, simple_loss=0.2221, pruned_loss=0.03283, over 4885.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.0313, over 971435.94 frames.], batch size: 22, lr: 1.65e-04
2022-05-07 22:49:41,684 INFO [train.py:715] (4/8) Epoch 13, batch 34500, loss[loss=0.1275, simple_loss=0.2044, pruned_loss=0.02531, over 4847.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03117, over 971620.59 frames.], batch size: 34, lr: 1.65e-04
2022-05-07 22:50:21,520 INFO [train.py:715] (4/8) Epoch 13, batch 34550, loss[loss=0.1393, simple_loss=0.2195, pruned_loss=0.02954, over 4950.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03134, over 971640.58 frames.], batch size: 15, lr: 1.65e-04
2022-05-07 22:51:01,497 INFO [train.py:715] (4/8) Epoch 13, batch 34600, loss[loss=0.1477, simple_loss=0.2164, pruned_loss=0.03949, over 4935.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2097, pruned_loss=0.03122, over 972207.30 frames.], batch size: 23, lr: 1.65e-04
2022-05-07 22:51:40,867 INFO [train.py:715] (4/8) Epoch 13, batch 34650, loss[loss=0.1151, simple_loss=0.1944, pruned_loss=0.01795, over 4956.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03093, over 973003.77 frames.], batch size: 29, lr: 1.65e-04
2022-05-07 22:52:20,402 INFO [train.py:715] (4/8) Epoch 13, batch 34700, loss[loss=0.126, simple_loss=0.2028, pruned_loss=0.02455, over 4933.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03084, over 972834.55 frames.], batch size: 18, lr: 1.65e-04
2022-05-07 22:52:59,352 INFO [train.py:715] (4/8) Epoch 13, batch 34750, loss[loss=0.1331, simple_loss=0.1924, pruned_loss=0.03691, over 4782.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03118, over 972020.91 frames.], batch size: 14, lr: 1.65e-04
2022-05-07 22:53:36,105 INFO [train.py:715] (4/8) Epoch 13, batch 34800, loss[loss=0.1328, simple_loss=0.2188, pruned_loss=0.02342, over 4911.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03091, over 971679.64 frames.], batch size: 23, lr: 1.65e-04
2022-05-07 22:54:25,042 INFO [train.py:715] (4/8) Epoch 14, batch 0, loss[loss=0.1468, simple_loss=0.2142, pruned_loss=0.03969, over 4911.00 frames.], tot_loss[loss=0.1468, simple_loss=0.2142, pruned_loss=0.03969, over 4911.00 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 22:55:04,006 INFO [train.py:715] (4/8) Epoch 14, batch 50, loss[loss=0.1415, simple_loss=0.2222, pruned_loss=0.03036, over 4897.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2069, pruned_loss=0.02988, over 219333.86 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 22:55:42,423 INFO [train.py:715] (4/8) Epoch 14, batch 100, loss[loss=0.1326, simple_loss=0.2119, pruned_loss=0.02668, over 4925.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03115, over 386716.37 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 22:56:21,309 INFO [train.py:715] (4/8) Epoch 14, batch 150, loss[loss=0.1474, simple_loss=0.2047, pruned_loss=0.04506, over 4939.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2084, pruned_loss=0.03111, over 516222.26 frames.], batch size: 35, lr: 1.59e-04
2022-05-07 22:56:59,878 INFO [train.py:715] (4/8) Epoch 14, batch 200, loss[loss=0.1371, simple_loss=0.2174, pruned_loss=0.0284, over 4791.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2102, pruned_loss=0.03141, over 617202.13 frames.], batch size: 21, lr: 1.59e-04
2022-05-07 22:57:38,472 INFO [train.py:715] (4/8) Epoch 14, batch 250, loss[loss=0.1325, simple_loss=0.2003, pruned_loss=0.03232, over 4837.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03095, over 695966.60 frames.], batch size: 30, lr: 1.59e-04
2022-05-07 22:58:17,254 INFO [train.py:715] (4/8) Epoch 14, batch 300, loss[loss=0.1836, simple_loss=0.2565, pruned_loss=0.05531, over 4949.00 frames.], tot_loss[loss=0.1384, simple_loss=0.2117, pruned_loss=0.03252, over 757147.25 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 22:58:56,807 INFO [train.py:715] (4/8) Epoch 14, batch 350, loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.03177, over 4943.00 frames.], tot_loss[loss=0.1377, simple_loss=0.211, pruned_loss=0.03226, over 804706.60 frames.], batch size: 21, lr: 1.59e-04
2022-05-07 22:59:35,349 INFO [train.py:715] (4/8) Epoch 14, batch 400, loss[loss=0.128, simple_loss=0.1998, pruned_loss=0.0281, over 4887.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.03163, over 841999.86 frames.], batch size: 32, lr: 1.59e-04
2022-05-07 23:00:14,776 INFO [train.py:715] (4/8) Epoch 14, batch 450, loss[loss=0.1409, simple_loss=0.2148, pruned_loss=0.0335, over 4928.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.0312, over 870656.85 frames.], batch size: 29, lr: 1.59e-04
2022-05-07 23:00:54,074 INFO [train.py:715] (4/8) Epoch 14, batch 500, loss[loss=0.1376, simple_loss=0.2123, pruned_loss=0.03146, over 4885.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2084, pruned_loss=0.03112, over 892696.81 frames.], batch size: 16, lr: 1.59e-04
2022-05-07 23:01:33,697 INFO [train.py:715] (4/8) Epoch 14, batch 550, loss[loss=0.1233, simple_loss=0.2049, pruned_loss=0.02089, over 4828.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2093, pruned_loss=0.03172, over 909616.32 frames.], batch size: 26, lr: 1.59e-04
2022-05-07 23:02:12,474 INFO [train.py:715] (4/8) Epoch 14, batch 600, loss[loss=0.1273, simple_loss=0.2008, pruned_loss=0.02689, over 4922.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2088, pruned_loss=0.03144, over 923739.16 frames.], batch size: 29, lr: 1.59e-04
2022-05-07 23:02:51,124 INFO [train.py:715] (4/8) Epoch 14, batch 650, loss[loss=0.1314, simple_loss=0.2172, pruned_loss=0.02279, over 4812.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2081, pruned_loss=0.0309, over 933655.98 frames.], batch size: 26, lr: 1.59e-04
2022-05-07 23:03:32,630 INFO [train.py:715] (4/8) Epoch 14, batch 700, loss[loss=0.1652, simple_loss=0.243, pruned_loss=0.04377, over 4794.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2078, pruned_loss=0.03069, over 942364.19 frames.], batch size: 14, lr: 1.59e-04
2022-05-07 23:04:11,049 INFO [train.py:715] (4/8) Epoch 14, batch 750, loss[loss=0.1261, simple_loss=0.2045, pruned_loss=0.02384, over 4888.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2079, pruned_loss=0.03041, over 948486.42 frames.], batch size: 16, lr: 1.59e-04
2022-05-07 23:04:51,158 INFO [train.py:715] (4/8) Epoch 14, batch 800, loss[loss=0.1559, simple_loss=0.2404, pruned_loss=0.03574, over 4921.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03034, over 953826.56 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 23:05:30,247 INFO [train.py:715] (4/8) Epoch 14, batch 850, loss[loss=0.1068, simple_loss=0.1727, pruned_loss=0.02045, over 4907.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03031, over 958046.76 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 23:06:09,708 INFO [train.py:715] (4/8) Epoch 14, batch 900, loss[loss=0.1352, simple_loss=0.2082, pruned_loss=0.03107, over 4864.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03019, over 961595.97 frames.], batch size: 22, lr: 1.59e-04
2022-05-07 23:06:48,331 INFO [train.py:715] (4/8) Epoch 14, batch 950, loss[loss=0.1435, simple_loss=0.2214, pruned_loss=0.03286, over 4815.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03034, over 964399.05 frames.], batch size: 25, lr: 1.59e-04
2022-05-07 23:07:27,882 INFO [train.py:715] (4/8) Epoch 14, batch 1000, loss[loss=0.1279, simple_loss=0.1881, pruned_loss=0.03382, over 4792.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2071, pruned_loss=0.03017, over 965223.61 frames.], batch size: 12, lr: 1.59e-04
2022-05-07 23:08:07,942 INFO [train.py:715] (4/8) Epoch 14, batch 1050, loss[loss=0.1352, simple_loss=0.2135, pruned_loss=0.02844, over 4834.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2071, pruned_loss=0.0303, over 966273.31 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:08:47,255 INFO [train.py:715] (4/8) Epoch 14, batch 1100, loss[loss=0.1394, simple_loss=0.2112, pruned_loss=0.03383, over 4641.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2077, pruned_loss=0.03044, over 967659.92 frames.], batch size: 13, lr: 1.59e-04
2022-05-07 23:09:26,961 INFO [train.py:715] (4/8) Epoch 14, batch 1150, loss[loss=0.146, simple_loss=0.2123, pruned_loss=0.03986, over 4809.00 frames.], tot_loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03078, over 969084.71 frames.], batch size: 12, lr: 1.59e-04
2022-05-07 23:10:07,016 INFO [train.py:715] (4/8) Epoch 14, batch 1200, loss[loss=0.1295, simple_loss=0.2079, pruned_loss=0.02557, over 4858.00 frames.], tot_loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03052, over 969508.42 frames.], batch size: 20, lr: 1.59e-04
2022-05-07 23:10:47,173 INFO [train.py:715] (4/8) Epoch 14, batch 1250, loss[loss=0.1204, simple_loss=0.1891, pruned_loss=0.02587, over 4637.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2075, pruned_loss=0.03036, over 969474.88 frames.], batch size: 13, lr: 1.59e-04
2022-05-07 23:11:26,192 INFO [train.py:715] (4/8) Epoch 14, batch 1300, loss[loss=0.1177, simple_loss=0.1978, pruned_loss=0.01878, over 4989.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.03077, over 970549.68 frames.], batch size: 20, lr: 1.59e-04
2022-05-07 23:12:05,713 INFO [train.py:715] (4/8) Epoch 14, batch 1350, loss[loss=0.1504, simple_loss=0.2166, pruned_loss=0.04208, over 4827.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03071, over 970794.35 frames.], batch size: 13, lr: 1.59e-04
2022-05-07 23:12:45,084 INFO [train.py:715] (4/8) Epoch 14, batch 1400, loss[loss=0.1378, simple_loss=0.2135, pruned_loss=0.03103, over 4832.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03048, over 970318.59 frames.], batch size: 13, lr: 1.59e-04
2022-05-07 23:13:24,651 INFO [train.py:715] (4/8) Epoch 14, batch 1450, loss[loss=0.1765, simple_loss=0.2439, pruned_loss=0.05457, over 4961.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.0308, over 971348.41 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:14:04,618 INFO [train.py:715] (4/8) Epoch 14, batch 1500, loss[loss=0.1184, simple_loss=0.1891, pruned_loss=0.02385, over 4772.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.0306, over 971611.35 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:14:44,294 INFO [train.py:715] (4/8) Epoch 14, batch 1550, loss[loss=0.131, simple_loss=0.1939, pruned_loss=0.03412, over 4788.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03077, over 972158.35 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 23:15:24,190 INFO [train.py:715] (4/8) Epoch 14, batch 1600, loss[loss=0.1304, simple_loss=0.2124, pruned_loss=0.02423, over 4801.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03108, over 972809.69 frames.], batch size: 24, lr: 1.59e-04
2022-05-07 23:16:03,425 INFO [train.py:715] (4/8) Epoch 14, batch 1650, loss[loss=0.1363, simple_loss=0.2229, pruned_loss=0.02485, over 4983.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03145, over 972529.11 frames.], batch size: 25, lr: 1.59e-04
2022-05-07 23:16:43,079 INFO [train.py:715] (4/8) Epoch 14, batch 1700, loss[loss=0.1534, simple_loss=0.2208, pruned_loss=0.043, over 4700.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03139, over 972030.05 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:17:22,565 INFO [train.py:715] (4/8) Epoch 14, batch 1750, loss[loss=0.1318, simple_loss=0.2055, pruned_loss=0.02904, over 4818.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03095, over 972674.07 frames.], batch size: 25, lr: 1.59e-04
2022-05-07 23:18:02,281 INFO [train.py:715] (4/8) Epoch 14, batch 1800, loss[loss=0.157, simple_loss=0.2223, pruned_loss=0.04579, over 4822.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03108, over 973057.76 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:18:40,627 INFO [train.py:715] (4/8) Epoch 14, batch 1850, loss[loss=0.1366, simple_loss=0.2067, pruned_loss=0.03323, over 4846.00 frames.], tot_loss[loss=0.1357, simple_loss=0.209, pruned_loss=0.03115, over 972764.06 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:19:19,860 INFO [train.py:715] (4/8) Epoch 14, batch 1900, loss[loss=0.135, simple_loss=0.2071, pruned_loss=0.03151, over 4893.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2093, pruned_loss=0.03143, over 972913.56 frames.], batch size: 32, lr: 1.59e-04
2022-05-07 23:19:59,660 INFO [train.py:715] (4/8) Epoch 14, batch 1950, loss[loss=0.1228, simple_loss=0.1924, pruned_loss=0.02662, over 4958.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2087, pruned_loss=0.03154, over 971774.74 frames.], batch size: 14, lr: 1.59e-04
2022-05-07 23:20:39,805 INFO [train.py:715] (4/8) Epoch 14, batch 2000, loss[loss=0.1357, simple_loss=0.2065, pruned_loss=0.03243, over 4975.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2086, pruned_loss=0.03123, over 971330.99 frames.], batch size: 31, lr: 1.59e-04
2022-05-07 23:21:19,092 INFO [train.py:715] (4/8) Epoch 14, batch 2050, loss[loss=0.1716, simple_loss=0.2389, pruned_loss=0.05218, over 4689.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2086, pruned_loss=0.03112, over 971472.76 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:21:58,531 INFO [train.py:715] (4/8) Epoch 14, batch 2100, loss[loss=0.1441, simple_loss=0.2073, pruned_loss=0.04044, over 4761.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03047, over 971873.48 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:22:38,243 INFO [train.py:715] (4/8) Epoch 14, batch 2150, loss[loss=0.1351, simple_loss=0.2094, pruned_loss=0.03039, over 4813.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03091, over 971666.11 frames.], batch size: 13, lr: 1.59e-04
2022-05-07 23:23:16,935 INFO [train.py:715] (4/8) Epoch 14, batch 2200, loss[loss=0.1544, simple_loss=0.2194, pruned_loss=0.04468, over 4962.00 frames.], tot_loss[loss=0.135, simple_loss=0.2082, pruned_loss=0.03086, over 971636.98 frames.], batch size: 39, lr: 1.59e-04
2022-05-07 23:23:55,886 INFO [train.py:715] (4/8) Epoch 14, batch 2250, loss[loss=0.1352, simple_loss=0.2075, pruned_loss=0.03145, over 4783.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2095, pruned_loss=0.03158, over 972057.15 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 23:24:34,962 INFO [train.py:715] (4/8) Epoch 14, batch 2300, loss[loss=0.1696, simple_loss=0.2345, pruned_loss=0.05229, over 4966.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03136, over 971713.32 frames.], batch size: 35, lr: 1.59e-04
2022-05-07 23:25:14,125 INFO [train.py:715] (4/8) Epoch 14, batch 2350, loss[loss=0.1316, simple_loss=0.2083, pruned_loss=0.02746, over 4782.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03071, over 971926.55 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 23:25:53,237 INFO [train.py:715] (4/8) Epoch 14, batch 2400, loss[loss=0.1405, simple_loss=0.2138, pruned_loss=0.03362, over 4901.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2078, pruned_loss=0.03041, over 971697.89 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 23:26:32,283 INFO [train.py:715] (4/8) Epoch 14, batch 2450, loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.0296, over 4899.00 frames.], tot_loss[loss=0.134, simple_loss=0.2075, pruned_loss=0.03026, over 971610.88 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 23:27:11,604 INFO [train.py:715] (4/8) Epoch 14, batch 2500, loss[loss=0.125, simple_loss=0.1985, pruned_loss=0.02578, over 4932.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2078, pruned_loss=0.03074, over 972271.49 frames.], batch size: 23, lr: 1.59e-04
2022-05-07 23:27:50,105 INFO [train.py:715] (4/8) Epoch 14, batch 2550, loss[loss=0.1404, simple_loss=0.2048, pruned_loss=0.03804, over 4977.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.03087, over 972549.50 frames.], batch size: 14, lr: 1.59e-04
2022-05-07 23:28:29,683 INFO [train.py:715] (4/8) Epoch 14, batch 2600, loss[loss=0.09054, simple_loss=0.1566, pruned_loss=0.01223, over 4807.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2086, pruned_loss=0.0311, over 972319.20 frames.], batch size: 12, lr: 1.59e-04
2022-05-07 23:29:09,139 INFO [train.py:715] (4/8) Epoch 14, batch 2650, loss[loss=0.1424, simple_loss=0.2107, pruned_loss=0.03705, over 4749.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2088, pruned_loss=0.03123, over 972435.65 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:29:48,493 INFO [train.py:715] (4/8) Epoch 14, batch 2700, loss[loss=0.1193, simple_loss=0.1969, pruned_loss=0.02084, over 4824.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.03081, over 972107.02 frames.], batch size: 25, lr: 1.59e-04
2022-05-07 23:30:27,052 INFO [train.py:715] (4/8) Epoch 14, batch 2750, loss[loss=0.1158, simple_loss=0.1908, pruned_loss=0.02046, over 4804.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03055, over 972702.10 frames.], batch size: 25, lr: 1.59e-04
2022-05-07 23:31:06,232 INFO [train.py:715] (4/8) Epoch 14, batch 2800, loss[loss=0.109, simple_loss=0.1855, pruned_loss=0.01627, over 4963.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03022, over 972603.27 frames.], batch size: 24, lr: 1.59e-04
2022-05-07 23:31:45,882 INFO [train.py:715] (4/8) Epoch 14, batch 2850, loss[loss=0.1403, simple_loss=0.2077, pruned_loss=0.03638, over 4935.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02989, over 971831.29 frames.], batch size: 23, lr: 1.59e-04
2022-05-07 23:32:24,328 INFO [train.py:715] (4/8) Epoch 14, batch 2900, loss[loss=0.1421, simple_loss=0.2214, pruned_loss=0.03141, over 4701.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.0304, over 971625.72 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:33:06,133 INFO [train.py:715] (4/8) Epoch 14, batch 2950, loss[loss=0.1156, simple_loss=0.1819, pruned_loss=0.02459, over 4950.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03081, over 970936.90 frames.], batch size: 14, lr: 1.59e-04
2022-05-07 23:33:45,668 INFO [train.py:715] (4/8) Epoch 14, batch 3000, loss[loss=0.1487, simple_loss=0.2238, pruned_loss=0.03674, over 4775.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2088, pruned_loss=0.03122, over 971028.48 frames.], batch size: 14, lr: 1.59e-04
2022-05-07 23:33:45,669 INFO [train.py:733] (4/8) Computing validation loss
2022-05-07 23:33:55,239 INFO [train.py:742] (4/8) Epoch 14, validation: loss=0.1052, simple_loss=0.1891, pruned_loss=0.01067, over 914524.00 frames.
2022-05-07 23:34:34,252 INFO [train.py:715] (4/8) Epoch 14, batch 3050, loss[loss=0.1394, simple_loss=0.2058, pruned_loss=0.03656, over 4968.00 frames.], tot_loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03084, over 972126.18 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:35:14,220 INFO [train.py:715] (4/8) Epoch 14, batch 3100, loss[loss=0.106, simple_loss=0.1789, pruned_loss=0.01661, over 4817.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2085, pruned_loss=0.03081, over 972187.33 frames.], batch size: 12, lr: 1.59e-04
2022-05-07 23:35:53,769 INFO [train.py:715] (4/8) Epoch 14, batch 3150, loss[loss=0.1379, simple_loss=0.2129, pruned_loss=0.03141, over 4862.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.03139, over 972729.42 frames.], batch size: 32, lr: 1.59e-04
2022-05-07 23:36:33,461 INFO [train.py:715] (4/8) Epoch 14, batch 3200, loss[loss=0.1265, simple_loss=0.1995, pruned_loss=0.02668, over 4760.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.0311, over 973003.70 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:37:14,485 INFO [train.py:715] (4/8) Epoch 14, batch 3250, loss[loss=0.1352, simple_loss=0.2107, pruned_loss=0.02982, over 4990.00 frames.], tot_loss[loss=0.1365, simple_loss=0.21, pruned_loss=0.03146, over 974526.34 frames.], batch size: 14, lr: 1.59e-04
2022-05-07 23:37:54,309 INFO [train.py:715] (4/8) Epoch 14, batch 3300, loss[loss=0.1449, simple_loss=0.2105, pruned_loss=0.0397, over 4827.00 frames.], tot_loss[loss=0.1373, simple_loss=0.2108, pruned_loss=0.03192, over 973814.89 frames.], batch size: 26, lr: 1.59e-04
2022-05-07 23:38:34,437 INFO [train.py:715] (4/8) Epoch 14, batch 3350, loss[loss=0.1121, simple_loss=0.1907, pruned_loss=0.01676, over 4807.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2102, pruned_loss=0.03127, over 974557.89 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 23:39:15,378 INFO [train.py:715] (4/8) Epoch 14, batch 3400, loss[loss=0.1463, simple_loss=0.2187, pruned_loss=0.03699, over 4773.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03071, over 974301.83 frames.], batch size: 14, lr: 1.59e-04
2022-05-07 23:39:56,035 INFO [train.py:715] (4/8) Epoch 14, batch 3450, loss[loss=0.1502, simple_loss=0.2197, pruned_loss=0.04029, over 4756.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03089, over 973427.19 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:40:35,907 INFO [train.py:715] (4/8) Epoch 14, batch 3500, loss[loss=0.1313, simple_loss=0.2124, pruned_loss=0.02507, over 4941.00 frames.], tot_loss[loss=0.137, simple_loss=0.2109, pruned_loss=0.03154, over 972082.19 frames.], batch size: 23, lr: 1.59e-04
2022-05-07 23:41:15,987 INFO [train.py:715] (4/8) Epoch 14, batch 3550, loss[loss=0.1387, simple_loss=0.2126, pruned_loss=0.03241, over 4878.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2101, pruned_loss=0.03142, over 972859.05 frames.], batch size: 16, lr: 1.59e-04
2022-05-07 23:41:56,122 INFO [train.py:715] (4/8) Epoch 14, batch 3600, loss[loss=0.1342, simple_loss=0.2025, pruned_loss=0.03289, over 4695.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03071, over 973198.54 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:42:36,128 INFO [train.py:715] (4/8) Epoch 14, batch 3650, loss[loss=0.1485, simple_loss=0.2386, pruned_loss=0.02918, over 4813.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03103, over 972877.34 frames.], batch size: 27, lr: 1.59e-04
2022-05-07 23:43:16,032 INFO [train.py:715] (4/8) Epoch 14, batch 3700, loss[loss=0.1429, simple_loss=0.214, pruned_loss=0.03587, over 4907.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03135, over 972328.72 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 23:43:56,761 INFO [train.py:715] (4/8) Epoch 14, batch 3750, loss[loss=0.1582, simple_loss=0.2235, pruned_loss=0.04642, over 4748.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03119, over 971702.35 frames.], batch size: 16, lr: 1.59e-04
2022-05-07 23:44:36,922 INFO [train.py:715] (4/8) Epoch 14, batch 3800, loss[loss=0.1344, simple_loss=0.2163, pruned_loss=0.02624, over 4811.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2082, pruned_loss=0.0308, over 971871.63 frames.], batch size: 13, lr: 1.59e-04
2022-05-07 23:45:16,163 INFO [train.py:715] (4/8) Epoch 14, batch 3850, loss[loss=0.1668, simple_loss=0.24, pruned_loss=0.04681, over 4753.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03109, over 971574.05 frames.], batch size: 14, lr: 1.59e-04
2022-05-07 23:45:56,640 INFO [train.py:715] (4/8) Epoch 14, batch 3900, loss[loss=0.1186, simple_loss=0.1947, pruned_loss=0.02122, over 4758.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2085, pruned_loss=0.03093, over 972212.46 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:46:37,876 INFO [train.py:715] (4/8) Epoch 14, batch 3950, loss[loss=0.1317, simple_loss=0.2045, pruned_loss=0.02941, over 4843.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03081, over 972464.32 frames.], batch size: 20, lr: 1.59e-04
2022-05-07 23:47:18,821 INFO [train.py:715] (4/8) Epoch 14, batch 4000, loss[loss=0.1422, simple_loss=0.2124, pruned_loss=0.03594, over 4830.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2089, pruned_loss=0.03129, over 972364.66 frames.], batch size: 26, lr: 1.59e-04
2022-05-07 23:47:59,307 INFO [train.py:715] (4/8) Epoch 14, batch 4050, loss[loss=0.1253, simple_loss=0.2033, pruned_loss=0.0237, over 4952.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2084, pruned_loss=0.03087, over 972233.73 frames.], batch size: 21, lr: 1.59e-04
2022-05-07 23:48:40,114 INFO [train.py:715] (4/8) Epoch 14, batch 4100, loss[loss=0.1343, simple_loss=0.2057, pruned_loss=0.03142, over 4962.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03113, over 972349.85 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:49:21,561 INFO [train.py:715] (4/8) Epoch 14, batch 4150, loss[loss=0.1505, simple_loss=0.2404, pruned_loss=0.03026, over 4779.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2092, pruned_loss=0.03124, over 972286.76 frames.], batch size: 18, lr: 1.59e-04
2022-05-07 23:50:02,211 INFO [train.py:715] (4/8) Epoch 14, batch 4200, loss[loss=0.1253, simple_loss=0.1936, pruned_loss=0.02852, over 4784.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03103, over 972398.40 frames.], batch size: 17, lr: 1.59e-04
2022-05-07 23:50:43,292 INFO [train.py:715] (4/8) Epoch 14, batch 4250, loss[loss=0.1337, simple_loss=0.2122, pruned_loss=0.02763, over 4800.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03127, over 972576.10 frames.], batch size: 13, lr: 1.59e-04
2022-05-07 23:51:25,168 INFO [train.py:715] (4/8) Epoch 14, batch 4300, loss[loss=0.1132, simple_loss=0.1966, pruned_loss=0.0149, over 4819.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03128, over 972540.79 frames.], batch size: 25, lr: 1.59e-04
2022-05-07 23:52:06,410 INFO [train.py:715] (4/8) Epoch 14, batch 4350, loss[loss=0.1392, simple_loss=0.2027, pruned_loss=0.03782, over 4872.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03101, over 972718.83 frames.], batch size: 16, lr: 1.59e-04
2022-05-07 23:52:46,949 INFO [train.py:715] (4/8) Epoch 14, batch 4400, loss[loss=0.1263, simple_loss=0.2019, pruned_loss=0.02536, over 4988.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03089, over 972645.44 frames.], batch size: 31, lr: 1.59e-04
2022-05-07 23:53:27,636 INFO [train.py:715] (4/8) Epoch 14, batch 4450, loss[loss=0.1406, simple_loss=0.2206, pruned_loss=0.03033, over 4935.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03049, over 972656.23 frames.], batch size: 23, lr: 1.59e-04
2022-05-07 23:54:08,630 INFO [train.py:715] (4/8) Epoch 14, batch 4500, loss[loss=0.1277, simple_loss=0.1998, pruned_loss=0.02782, over 4763.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03037, over 972489.49 frames.], batch size: 16, lr: 1.59e-04
2022-05-07 23:54:48,677 INFO [train.py:715] (4/8) Epoch 14, batch 4550, loss[loss=0.1215, simple_loss=0.1947, pruned_loss=0.02411, over 4893.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03068, over 972361.35 frames.], batch size: 19, lr: 1.59e-04
2022-05-07 23:55:27,632 INFO [train.py:715] (4/8) Epoch 14, batch 4600, loss[loss=0.1428, simple_loss=0.2199, pruned_loss=0.03281, over 4928.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03076, over 972627.16 frames.], batch size: 23, lr: 1.59e-04
2022-05-07 23:56:08,466 INFO [train.py:715] (4/8) Epoch 14, batch 4650, loss[loss=0.1279, simple_loss=0.2007, pruned_loss=0.0275, over 4819.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03028, over 972477.02 frames.], batch size: 25, lr: 1.59e-04
2022-05-07 23:56:48,196 INFO [train.py:715] (4/8) Epoch 14, batch 4700, loss[loss=0.1194, simple_loss=0.1865, pruned_loss=0.02617, over 4987.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03018, over 973174.16 frames.], batch size: 15, lr: 1.59e-04
2022-05-07 23:57:26,878 INFO [train.py:715] (4/8) Epoch 14, batch 4750, loss[loss=0.1174, simple_loss=0.1895, pruned_loss=0.02264, over 4757.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03023, over 972372.37 frames.], batch size: 19, lr: 1.58e-04
2022-05-07 23:58:06,244 INFO [train.py:715] (4/8) Epoch 14, batch 4800, loss[loss=0.1641, simple_loss=0.2362, pruned_loss=0.04603, over 4757.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03053, over 972286.31 frames.], batch size: 14, lr: 1.58e-04
2022-05-07 23:58:46,079 INFO [train.py:715] (4/8) Epoch 14, batch 4850, loss[loss=0.1216, simple_loss=0.2001, pruned_loss=0.02158, over 4811.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03074, over 972238.30 frames.], batch size: 21, lr: 1.58e-04
2022-05-07 23:59:25,003 INFO [train.py:715] (4/8) Epoch 14, batch 4900, loss[loss=0.1385, simple_loss=0.2115, pruned_loss=0.0328, over 4930.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.0308, over 973044.71 frames.], batch size: 29, lr: 1.58e-04
2022-05-08 00:00:04,153 INFO [train.py:715] (4/8) Epoch 14, batch 4950, loss[loss=0.1283, simple_loss=0.1928, pruned_loss=0.03191, over 4791.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03058, over 972945.57 frames.], batch size: 12, lr: 1.58e-04
2022-05-08 00:00:44,229 INFO [train.py:715] (4/8) Epoch 14, batch 5000, loss[loss=0.1612, simple_loss=0.2386, pruned_loss=0.04195, over 4758.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03066, over 972568.33 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:01:23,509 INFO [train.py:715] (4/8) Epoch 14, batch 5050, loss[loss=0.1599, simple_loss=0.2382, pruned_loss=0.04081, over 4781.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.0312, over 971820.17 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:02:02,198 INFO [train.py:715] (4/8) Epoch 14, batch 5100, loss[loss=0.123, simple_loss=0.206, pruned_loss=0.01998, over 4880.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03104, over 972060.94 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 00:02:41,794 INFO [train.py:715] (4/8) Epoch 14, batch 5150, loss[loss=0.1164, simple_loss=0.1802, pruned_loss=0.02629, over 4919.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03097, over 972628.42 frames.], batch size: 18, lr: 1.58e-04
2022-05-08 00:03:21,426 INFO [train.py:715] (4/8) Epoch 14, batch 5200, loss[loss=0.1521, simple_loss=0.2226, pruned_loss=0.04085, over 4883.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03077, over 973170.02 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 00:03:59,951 INFO [train.py:715] (4/8) Epoch 14, batch 5250, loss[loss=0.1402, simple_loss=0.2181, pruned_loss=0.03109, over 4849.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03077, over 973181.96 frames.], batch size: 20, lr: 1.58e-04
2022-05-08 00:04:38,444 INFO [train.py:715] (4/8) Epoch 14, batch 5300, loss[loss=0.1305, simple_loss=0.207, pruned_loss=0.02701, over 4820.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03101, over 972761.36 frames.], batch size: 27, lr: 1.58e-04
2022-05-08 00:05:17,626 INFO [train.py:715] (4/8) Epoch 14, batch 5350, loss[loss=0.133, simple_loss=0.2092, pruned_loss=0.02838, over 4745.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03106, over 972769.67 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 00:05:56,197 INFO [train.py:715] (4/8) Epoch 14, batch 5400, loss[loss=0.1229, simple_loss=0.1957, pruned_loss=0.02509, over 4979.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03087, over 972462.14 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:06:34,704 INFO [train.py:715] (4/8) Epoch 14, batch 5450, loss[loss=0.1355, simple_loss=0.2143, pruned_loss=0.0284, over 4904.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03019, over 972518.75 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:07:13,538 INFO [train.py:715] (4/8) Epoch 14, batch 5500, loss[loss=0.1349, simple_loss=0.2082, pruned_loss=0.03075, over 4986.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03054, over 972517.49 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 00:07:53,214 INFO [train.py:715] (4/8) Epoch 14, batch 5550, loss[loss=0.117, simple_loss=0.1973, pruned_loss=0.01836, over 4978.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03102, over 972119.32 frames.], batch size: 24, lr: 1.58e-04
2022-05-08 00:08:31,528 INFO [train.py:715] (4/8) Epoch 14, batch 5600, loss[loss=0.1285, simple_loss=0.2057, pruned_loss=0.02567, over 4965.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.0309, over 972528.30 frames.], batch size: 28, lr: 1.58e-04
2022-05-08 00:09:10,033 INFO [train.py:715] (4/8) Epoch 14, batch 5650, loss[loss=0.1439, simple_loss=0.209, pruned_loss=0.03936, over 4740.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03077, over 971163.93 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 00:09:49,144 INFO [train.py:715] (4/8) Epoch 14, batch 5700, loss[loss=0.1177, simple_loss=0.1833, pruned_loss=0.02607, over 4980.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03039, over 971407.33 frames.], batch size: 28, lr: 1.58e-04
2022-05-08 00:10:27,419 INFO [train.py:715] (4/8) Epoch 14, batch 5750, loss[loss=0.1357, simple_loss=0.2025, pruned_loss=0.03442, over 4780.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03036, over 971603.40 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:11:05,798 INFO [train.py:715] (4/8) Epoch 14, batch 5800, loss[loss=0.1128, simple_loss=0.1939, pruned_loss=0.01586, over 4935.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.02999, over 971524.63 frames.], batch size: 23, lr: 1.58e-04
2022-05-08 00:11:44,415 INFO [train.py:715] (4/8) Epoch 14, batch 5850, loss[loss=0.1164, simple_loss=0.1814, pruned_loss=0.02574, over 4956.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02969, over 971566.09 frames.], batch size: 21, lr: 1.58e-04
2022-05-08 00:12:23,185 INFO [train.py:715] (4/8) Epoch 14, batch 5900, loss[loss=0.128, simple_loss=0.2008, pruned_loss=0.02756, over 4788.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02951, over 970939.47 frames.], batch size: 24, lr: 1.58e-04
2022-05-08 00:13:02,943 INFO [train.py:715] (4/8) Epoch 14, batch 5950, loss[loss=0.1364, simple_loss=0.2053, pruned_loss=0.03378, over 4773.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02969, over 970423.16 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:13:42,636 INFO [train.py:715] (4/8) Epoch 14, batch 6000, loss[loss=0.1269, simple_loss=0.2021, pruned_loss=0.0258, over 4775.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02985, over 970822.29 frames.], batch size: 12, lr: 1.58e-04
2022-05-08 00:13:42,637 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 00:13:52,502 INFO [train.py:742] (4/8) Epoch 14, validation: loss=0.105, simple_loss=0.1888, pruned_loss=0.01057, over 914524.00 frames.
2022-05-08 00:14:31,596 INFO [train.py:715] (4/8) Epoch 14, batch 6050, loss[loss=0.1267, simple_loss=0.1975, pruned_loss=0.02798, over 4955.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02996, over 971262.16 frames.], batch size: 35, lr: 1.58e-04
2022-05-08 00:15:10,772 INFO [train.py:715] (4/8) Epoch 14, batch 6100, loss[loss=0.1047, simple_loss=0.1826, pruned_loss=0.01347, over 4776.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02976, over 971772.79 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:15:50,786 INFO [train.py:715] (4/8) Epoch 14, batch 6150, loss[loss=0.1378, simple_loss=0.2135, pruned_loss=0.03102, over 4776.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.0305, over 971913.18 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:16:30,400 INFO [train.py:715] (4/8) Epoch 14, batch 6200, loss[loss=0.1414, simple_loss=0.2201, pruned_loss=0.03134, over 4748.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03091, over 972571.96 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 00:17:10,274 INFO [train.py:715] (4/8) Epoch 14, batch 6250, loss[loss=0.1344, simple_loss=0.2074, pruned_loss=0.03072, over 4762.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2084, pruned_loss=0.03094, over 972697.65 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:17:49,641 INFO [train.py:715] (4/8) Epoch 14, batch 6300, loss[loss=0.1484, simple_loss=0.2264, pruned_loss=0.03523, over 4946.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2079, pruned_loss=0.03066, over 972801.41 frames.], batch size: 39, lr: 1.58e-04
2022-05-08 00:18:29,669 INFO [train.py:715] (4/8) Epoch 14, batch 6350, loss[loss=0.1434, simple_loss=0.216, pruned_loss=0.03535, over 4921.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2084, pruned_loss=0.0309, over 972605.75 frames.], batch size: 23, lr: 1.58e-04
2022-05-08 00:19:09,445 INFO [train.py:715] (4/8) Epoch 14, batch 6400, loss[loss=0.1402, simple_loss=0.2133, pruned_loss=0.0336, over 4863.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03111, over 972515.42 frames.], batch size: 32, lr: 1.58e-04
2022-05-08 00:19:49,533 INFO [train.py:715] (4/8) Epoch 14, batch 6450, loss[loss=0.1102, simple_loss=0.1832, pruned_loss=0.01856, over 4964.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03076, over 972042.25 frames.], batch size: 24, lr: 1.58e-04
2022-05-08 00:20:29,521 INFO [train.py:715] (4/8) Epoch 14, batch 6500, loss[loss=0.1184, simple_loss=0.1915, pruned_loss=0.02266, over 4954.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03102, over 972852.15 frames.], batch size: 21, lr: 1.58e-04
2022-05-08 00:21:09,179 INFO [train.py:715] (4/8) Epoch 14, batch 6550, loss[loss=0.1457, simple_loss=0.2216, pruned_loss=0.03491, over 4924.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2107, pruned_loss=0.0313, over 972826.75 frames.], batch size: 23, lr: 1.58e-04
2022-05-08 00:21:49,049 INFO [train.py:715] (4/8) Epoch 14, batch 6600, loss[loss=0.1552, simple_loss=0.2304, pruned_loss=0.03999, over 4976.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2111, pruned_loss=0.03156, over 972711.58 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:22:29,237 INFO [train.py:715] (4/8) Epoch 14, batch 6650, loss[loss=0.1276, simple_loss=0.1961, pruned_loss=0.02955, over 4917.00 frames.], tot_loss[loss=0.1368, simple_loss=0.211, pruned_loss=0.03133, over 973185.12 frames.], batch size: 18, lr: 1.58e-04
2022-05-08 00:23:08,971 INFO [train.py:715] (4/8) Epoch 14, batch 6700, loss[loss=0.1166, simple_loss=0.184, pruned_loss=0.02465, over 4795.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2104, pruned_loss=0.03099, over 972747.68 frames.], batch size: 12, lr: 1.58e-04
2022-05-08 00:23:48,846 INFO [train.py:715] (4/8) Epoch 14, batch 6750, loss[loss=0.1414, simple_loss=0.2132, pruned_loss=0.03476, over 4792.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03155, over 973739.48 frames.], batch size: 21, lr: 1.58e-04
2022-05-08 00:24:28,844 INFO [train.py:715] (4/8) Epoch 14, batch 6800, loss[loss=0.1308, simple_loss=0.2012, pruned_loss=0.03024, over 4870.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03173, over 973160.60 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 00:25:08,851 INFO [train.py:715] (4/8) Epoch 14, batch 6850, loss[loss=0.123, simple_loss=0.2009, pruned_loss=0.02256, over 4943.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03079, over 973145.38 frames.], batch size: 29, lr: 1.58e-04
2022-05-08 00:25:48,270 INFO [train.py:715] (4/8) Epoch 14, batch 6900, loss[loss=0.144, simple_loss=0.2172, pruned_loss=0.03538, over 4923.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03076, over 972632.55 frames.], batch size: 39, lr: 1.58e-04
2022-05-08 00:26:28,462 INFO [train.py:715] (4/8) Epoch 14, batch 6950, loss[loss=0.1253, simple_loss=0.1972, pruned_loss=0.02671, over 4950.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03083, over 972180.50 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:27:08,572 INFO [train.py:715] (4/8) Epoch 14, batch 7000, loss[loss=0.1438, simple_loss=0.2069, pruned_loss=0.04033, over 4758.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03065, over 972557.33 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 00:27:48,555 INFO [train.py:715] (4/8) Epoch 14, batch 7050, loss[loss=0.1442, simple_loss=0.2232, pruned_loss=0.03259, over 4908.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02996, over 973147.87 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:28:27,883 INFO [train.py:715] (4/8) Epoch 14, batch 7100, loss[loss=0.1237, simple_loss=0.1969, pruned_loss=0.02522, over 4982.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02983, over 973562.51 frames.], batch size: 28, lr: 1.58e-04
2022-05-08 00:29:07,967 INFO [train.py:715] (4/8) Epoch 14, batch 7150, loss[loss=0.1353, simple_loss=0.2117, pruned_loss=0.02946, over 4716.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02976, over 972399.17 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 00:29:48,176 INFO [train.py:715] (4/8) Epoch 14, batch 7200, loss[loss=0.13, simple_loss=0.2053, pruned_loss=0.0274, over 4879.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03029, over 972888.06 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 00:30:28,020 INFO [train.py:715] (4/8) Epoch 14, batch 7250, loss[loss=0.1181, simple_loss=0.1969, pruned_loss=0.01967, over 4880.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03031, over 971994.56 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 00:31:08,149 INFO [train.py:715] (4/8) Epoch 14, batch 7300, loss[loss=0.13, simple_loss=0.1992, pruned_loss=0.03037, over 4792.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03044, over 972766.33 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:31:48,270 INFO [train.py:715] (4/8) Epoch 14, batch 7350, loss[loss=0.1294, simple_loss=0.2039, pruned_loss=0.02739, over 4813.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03033, over 971420.52 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 00:32:28,614 INFO [train.py:715] (4/8) Epoch 14, batch 7400, loss[loss=0.1374, simple_loss=0.2181, pruned_loss=0.02829, over 4758.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03015, over 971522.26 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 00:33:08,065 INFO [train.py:715] (4/8) Epoch 14, batch 7450, loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03078, over 4910.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03017, over 971868.41 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:33:47,758 INFO [train.py:715] (4/8) Epoch 14, batch 7500, loss[loss=0.1322, simple_loss=0.2112, pruned_loss=0.02659, over 4812.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02989, over 972303.98 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 00:34:27,410 INFO [train.py:715] (4/8) Epoch 14, batch 7550, loss[loss=0.1774, simple_loss=0.2442, pruned_loss=0.05532, over 4944.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03023, over 972281.01 frames.], batch size: 29, lr: 1.58e-04
2022-05-08 00:35:06,411 INFO [train.py:715] (4/8) Epoch 14, batch 7600, loss[loss=0.1396, simple_loss=0.2105, pruned_loss=0.03439, over 4948.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03034, over 972482.78 frames.], batch size: 21, lr: 1.58e-04
2022-05-08 00:35:46,366 INFO [train.py:715] (4/8) Epoch 14, batch 7650, loss[loss=0.137, simple_loss=0.211, pruned_loss=0.03154, over 4783.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03019, over 972111.23 frames.], batch size: 18, lr: 1.58e-04
2022-05-08 00:36:25,269 INFO [train.py:715] (4/8) Epoch 14, batch 7700, loss[loss=0.1351, simple_loss=0.2108, pruned_loss=0.02971, over 4852.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03012, over 971883.25 frames.], batch size: 20, lr: 1.58e-04
2022-05-08 00:37:05,576 INFO [train.py:715] (4/8) Epoch 14, batch 7750, loss[loss=0.1296, simple_loss=0.2105, pruned_loss=0.0243, over 4975.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03001, over 971652.70 frames.], batch size: 33, lr: 1.58e-04
2022-05-08 00:37:44,378 INFO [train.py:715] (4/8) Epoch 14, batch 7800, loss[loss=0.1166, simple_loss=0.1932, pruned_loss=0.01999, over 4937.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02991, over 972783.19 frames.], batch size: 29, lr: 1.58e-04
2022-05-08 00:38:23,469 INFO [train.py:715] (4/8) Epoch 14, batch 7850, loss[loss=0.1316, simple_loss=0.2173, pruned_loss=0.02299, over 4868.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.02998, over 973191.12 frames.], batch size: 20, lr: 1.58e-04
2022-05-08 00:39:03,274 INFO [train.py:715] (4/8) Epoch 14, batch 7900, loss[loss=0.1311, simple_loss=0.2029, pruned_loss=0.02964, over 4853.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2101, pruned_loss=0.03038, over 972127.30 frames.], batch size: 30, lr: 1.58e-04
2022-05-08 00:39:42,080 INFO [train.py:715] (4/8) Epoch 14, batch 7950, loss[loss=0.1211, simple_loss=0.1907, pruned_loss=0.02575, over 4796.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2107, pruned_loss=0.03104, over 971627.32 frames.], batch size: 12, lr: 1.58e-04
2022-05-08 00:40:21,690 INFO [train.py:715] (4/8) Epoch 14, batch 8000, loss[loss=0.1343, simple_loss=0.1976, pruned_loss=0.03548, over 4837.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.03109, over 971289.74 frames.], batch size: 32, lr: 1.58e-04
2022-05-08 00:41:00,526 INFO [train.py:715] (4/8) Epoch 14, batch 8050, loss[loss=0.1226, simple_loss=0.1953, pruned_loss=0.02499, over 4750.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03114, over 971031.63 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 00:41:40,053 INFO [train.py:715] (4/8) Epoch 14, batch 8100, loss[loss=0.1515, simple_loss=0.2279, pruned_loss=0.03752, over 4813.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.0307, over 971261.54 frames.], batch size: 25, lr: 1.58e-04
2022-05-08 00:42:18,787 INFO [train.py:715] (4/8) Epoch 14, batch 8150, loss[loss=0.1149, simple_loss=0.1849, pruned_loss=0.02244, over 4954.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03102, over 972247.06 frames.], batch size: 15, lr: 1.58e-04
2022-05-08 00:42:58,273 INFO [train.py:715] (4/8) Epoch 14, batch 8200, loss[loss=0.1134, simple_loss=0.1919, pruned_loss=0.01749, over 4945.00 frames.], tot_loss[loss=0.1357, simple_loss=0.21, pruned_loss=0.03075, over 972344.66 frames.], batch size: 23, lr: 1.58e-04
2022-05-08 00:43:37,712 INFO [train.py:715] (4/8) Epoch 14, batch 8250, loss[loss=0.1422, simple_loss=0.2267, pruned_loss=0.02885, over 4915.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2102, pruned_loss=0.03079, over 973277.42 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 00:44:17,183 INFO [train.py:715] (4/8) Epoch 14, batch 8300, loss[loss=0.1456, simple_loss=0.2131, pruned_loss=0.03901, over 4855.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2106, pruned_loss=0.03128, over 973015.89 frames.], batch size: 32, lr: 1.58e-04
2022-05-08 00:44:56,125 INFO [train.py:715] (4/8) Epoch 14, batch 8350, loss[loss=0.134, simple_loss=0.2089, pruned_loss=0.02954, over 4802.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03123, over 972382.16 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:45:35,325 INFO [train.py:715] (4/8) Epoch 14, batch 8400, loss[loss=0.1655, simple_loss=0.2383, pruned_loss=0.04638, over 4779.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.031, over 971537.74 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:46:14,804 INFO [train.py:715] (4/8) Epoch 14, batch 8450, loss[loss=0.1277, simple_loss=0.1999, pruned_loss=0.02774, over 4883.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.0306, over 971848.71 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 00:46:53,356 INFO [train.py:715] (4/8) Epoch 14, batch 8500, loss[loss=0.1189, simple_loss=0.1997, pruned_loss=0.01909, over 4850.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03007, over 971898.18 frames.], batch size: 34, lr: 1.58e-04
2022-05-08 00:47:32,470 INFO [train.py:715] (4/8) Epoch 14, batch 8550, loss[loss=0.1119, simple_loss=0.1845, pruned_loss=0.01964, over 4759.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.0301, over 972408.19 frames.], batch size: 18, lr: 1.58e-04
2022-05-08 00:48:13,441 INFO [train.py:715] (4/8) Epoch 14, batch 8600, loss[loss=0.1183, simple_loss=0.1907, pruned_loss=0.02295, over 4798.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02996, over 973058.43 frames.], batch size: 18, lr: 1.58e-04
2022-05-08 00:48:52,731 INFO [train.py:715] (4/8) Epoch 14, batch 8650, loss[loss=0.121, simple_loss=0.193, pruned_loss=0.02448, over 4761.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.0301, over 972518.30 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 00:49:34,157 INFO [train.py:715] (4/8) Epoch 14, batch 8700, loss[loss=0.1191, simple_loss=0.1947, pruned_loss=0.02171, over 4913.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03093, over 973110.83 frames.], batch size: 29, lr: 1.58e-04
2022-05-08 00:50:13,526 INFO [train.py:715] (4/8) Epoch 14, batch 8750, loss[loss=0.1313, simple_loss=0.2115, pruned_loss=0.0256, over 4915.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03103, over 973193.66 frames.], batch size: 22, lr: 1.58e-04
2022-05-08 00:50:53,246 INFO [train.py:715] (4/8) Epoch 14, batch 8800, loss[loss=0.1451, simple_loss=0.2122, pruned_loss=0.03898, over 4881.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03108, over 973687.30 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 00:51:32,824 INFO [train.py:715] (4/8) Epoch 14, batch 8850, loss[loss=0.1487, simple_loss=0.2288, pruned_loss=0.03432, over 4830.00 frames.], tot_loss[loss=0.135, simple_loss=0.2087, pruned_loss=0.0307, over 972200.12 frames.], batch size: 26, lr: 1.58e-04
2022-05-08 00:52:13,342 INFO [train.py:715] (4/8) Epoch 14, batch 8900, loss[loss=0.1353, simple_loss=0.2071, pruned_loss=0.03172, over 4922.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.0303, over 971812.23 frames.], batch size: 18, lr: 1.58e-04
2022-05-08 00:52:53,215 INFO [train.py:715] (4/8) Epoch 14, batch 8950, loss[loss=0.1193, simple_loss=0.1984, pruned_loss=0.02008, over 4957.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.0306, over 971048.21 frames.], batch size: 39, lr: 1.58e-04
2022-05-08 00:53:33,010 INFO [train.py:715] (4/8) Epoch 14, batch 9000, loss[loss=0.1192, simple_loss=0.2005, pruned_loss=0.01901, over 4858.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03034, over 972235.36 frames.], batch size: 20, lr: 1.58e-04
2022-05-08 00:53:33,011 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 00:53:47,939 INFO [train.py:742] (4/8) Epoch 14, validation: loss=0.1052, simple_loss=0.189, pruned_loss=0.01074, over 914524.00 frames.
2022-05-08 00:54:27,483 INFO [train.py:715] (4/8) Epoch 14, batch 9050, loss[loss=0.138, simple_loss=0.2232, pruned_loss=0.02635, over 4785.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03026, over 973070.85 frames.], batch size: 18, lr: 1.58e-04
2022-05-08 00:55:07,804 INFO [train.py:715] (4/8) Epoch 14, batch 9100, loss[loss=0.1552, simple_loss=0.2396, pruned_loss=0.03544, over 4931.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03012, over 973776.65 frames.], batch size: 29, lr: 1.58e-04
2022-05-08 00:55:47,315 INFO [train.py:715] (4/8) Epoch 14, batch 9150, loss[loss=0.1212, simple_loss=0.1981, pruned_loss=0.02218, over 4787.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03001, over 973484.56 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:56:27,173 INFO [train.py:715] (4/8) Epoch 14, batch 9200, loss[loss=0.1412, simple_loss=0.2111, pruned_loss=0.0356, over 4750.00 frames.], tot_loss[loss=0.1346, simple_loss=0.208, pruned_loss=0.03061, over 972992.38 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 00:57:06,889 INFO [train.py:715] (4/8) Epoch 14, batch 9250, loss[loss=0.1608, simple_loss=0.2338, pruned_loss=0.04387, over 4899.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03058, over 972872.28 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 00:57:46,606 INFO [train.py:715] (4/8) Epoch 14, batch 9300, loss[loss=0.1165, simple_loss=0.1931, pruned_loss=0.01994, over 4950.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03085, over 972698.42 frames.], batch size: 21, lr: 1.58e-04
2022-05-08 00:58:26,528 INFO [train.py:715] (4/8) Epoch 14, batch 9350, loss[loss=0.1256, simple_loss=0.2004, pruned_loss=0.02543, over 4921.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.0298, over 973281.06 frames.], batch size: 29, lr: 1.58e-04
2022-05-08 00:59:06,673 INFO [train.py:715] (4/8) Epoch 14, batch 9400, loss[loss=0.1366, simple_loss=0.2221, pruned_loss=0.0255, over 4925.00 frames.], tot_loss[loss=0.1335, simple_loss=0.207, pruned_loss=0.02997, over 972641.61 frames.], batch size: 23, lr: 1.58e-04
2022-05-08 00:59:46,292 INFO [train.py:715] (4/8) Epoch 14, batch 9450, loss[loss=0.1601, simple_loss=0.2308, pruned_loss=0.0447, over 4894.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2073, pruned_loss=0.03011, over 972507.03 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 01:00:26,050 INFO [train.py:715] (4/8) Epoch 14, batch 9500, loss[loss=0.1263, simple_loss=0.1989, pruned_loss=0.02686, over 4757.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2069, pruned_loss=0.02966, over 972112.32 frames.], batch size: 17, lr: 1.58e-04
2022-05-08 01:01:05,842 INFO [train.py:715] (4/8) Epoch 14, batch 9550, loss[loss=0.1248, simple_loss=0.2061, pruned_loss=0.02174, over 4809.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02956, over 972133.10 frames.], batch size: 26, lr: 1.58e-04
2022-05-08 01:01:46,021 INFO [train.py:715] (4/8) Epoch 14, batch 9600, loss[loss=0.1307, simple_loss=0.214, pruned_loss=0.02368, over 4804.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2075, pruned_loss=0.03018, over 972384.60 frames.], batch size: 21, lr: 1.58e-04
2022-05-08 01:02:25,428 INFO [train.py:715] (4/8) Epoch 14, batch 9650, loss[loss=0.1162, simple_loss=0.1956, pruned_loss=0.01833, over 4930.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2074, pruned_loss=0.03017, over 971662.53 frames.], batch size: 23, lr: 1.58e-04
2022-05-08 01:03:05,453 INFO [train.py:715] (4/8) Epoch 14, batch 9700, loss[loss=0.115, simple_loss=0.1923, pruned_loss=0.01884, over 4809.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2078, pruned_loss=0.03073, over 971056.18 frames.], batch size: 21, lr: 1.58e-04
2022-05-08 01:03:45,039 INFO [train.py:715] (4/8) Epoch 14, batch 9750, loss[loss=0.1239, simple_loss=0.1978, pruned_loss=0.02495, over 4958.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2083, pruned_loss=0.03105, over 970800.80 frames.], batch size: 21, lr: 1.58e-04
2022-05-08 01:04:25,348 INFO [train.py:715] (4/8) Epoch 14, batch 9800, loss[loss=0.1203, simple_loss=0.2012, pruned_loss=0.01966, over 4888.00 frames.], tot_loss[loss=0.135, simple_loss=0.2083, pruned_loss=0.03086, over 970805.29 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 01:05:04,566 INFO [train.py:715] (4/8) Epoch 14, batch 9850, loss[loss=0.1027, simple_loss=0.1696, pruned_loss=0.0179, over 4847.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.0304, over 970842.18 frames.], batch size: 13, lr: 1.58e-04
2022-05-08 01:05:44,640 INFO [train.py:715] (4/8) Epoch 14, batch 9900, loss[loss=0.163, simple_loss=0.2438, pruned_loss=0.04106, over 4957.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02981, over 971110.93 frames.], batch size: 24, lr: 1.58e-04
2022-05-08 01:06:24,618 INFO [train.py:715] (4/8) Epoch 14, batch 9950, loss[loss=0.1206, simple_loss=0.1987, pruned_loss=0.02129, over 4897.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03028, over 971024.68 frames.], batch size: 19, lr: 1.58e-04
2022-05-08 01:07:03,943 INFO [train.py:715] (4/8) Epoch 14, batch 10000, loss[loss=0.1344, simple_loss=0.2072, pruned_loss=0.0308, over 4766.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03031, over 971078.42 frames.], batch size: 18, lr: 1.58e-04
2022-05-08 01:07:43,993 INFO [train.py:715] (4/8) Epoch 14, batch 10050, loss[loss=0.1533, simple_loss=0.2203, pruned_loss=0.04312, over 4885.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03019, over 970491.22 frames.], batch size: 22, lr: 1.58e-04
2022-05-08 01:08:23,514 INFO [train.py:715] (4/8) Epoch 14, batch 10100, loss[loss=0.1249, simple_loss=0.1934, pruned_loss=0.0282, over 4887.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03091, over 971467.47 frames.], batch size: 22, lr: 1.58e-04
2022-05-08 01:09:03,292 INFO [train.py:715] (4/8) Epoch 14, batch 10150, loss[loss=0.1415, simple_loss=0.2214, pruned_loss=0.0308, over 4932.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03019, over 972318.01 frames.], batch size: 39, lr: 1.58e-04
2022-05-08 01:09:42,487 INFO [train.py:715] (4/8) Epoch 14, batch 10200, loss[loss=0.1362, simple_loss=0.2139, pruned_loss=0.02923, over 4955.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03019, over 973323.08 frames.], batch size: 24, lr: 1.58e-04
2022-05-08 01:10:22,732 INFO [train.py:715] (4/8) Epoch 14, batch 10250, loss[loss=0.1175, simple_loss=0.2011, pruned_loss=0.01693, over 4846.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03039, over 973554.47 frames.], batch size: 20, lr: 1.58e-04
2022-05-08 01:11:02,456 INFO [train.py:715] (4/8) Epoch 14, batch 10300, loss[loss=0.1148, simple_loss=0.1984, pruned_loss=0.01557, over 4875.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03065, over 973368.55 frames.], batch size: 20, lr: 1.58e-04
2022-05-08 01:11:41,906 INFO [train.py:715] (4/8) Epoch 14, batch 10350, loss[loss=0.1201, simple_loss=0.1893, pruned_loss=0.02546, over 4823.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2076, pruned_loss=0.0306, over 973122.03 frames.], batch size: 13, lr: 1.58e-04
2022-05-08 01:12:22,109 INFO [train.py:715] (4/8) Epoch 14, batch 10400, loss[loss=0.1534, simple_loss=0.2332, pruned_loss=0.03683, over 4871.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.0301, over 973115.74 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 01:13:01,497 INFO [train.py:715] (4/8) Epoch 14, batch 10450, loss[loss=0.1375, simple_loss=0.2097, pruned_loss=0.03266, over 4915.00 frames.], tot_loss[loss=0.134, simple_loss=0.2077, pruned_loss=0.03012, over 972941.98 frames.], batch size: 18, lr: 1.58e-04
2022-05-08 01:13:41,729 INFO [train.py:715] (4/8) Epoch 14, batch 10500, loss[loss=0.1474, simple_loss=0.2032, pruned_loss=0.04579, over 4830.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2073, pruned_loss=0.02992, over 972128.59 frames.], batch size: 30, lr: 1.58e-04
2022-05-08 01:14:21,000 INFO [train.py:715] (4/8) Epoch 14, batch 10550, loss[loss=0.1395, simple_loss=0.2173, pruned_loss=0.03087, over 4872.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03036, over 973493.39 frames.], batch size: 16, lr: 1.58e-04
2022-05-08 01:15:01,260 INFO [train.py:715] (4/8) Epoch 14, batch 10600, loss[loss=0.1059, simple_loss=0.1771, pruned_loss=0.01737, over 4864.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02993, over 972599.07 frames.], batch size: 12, lr: 1.58e-04
2022-05-08 01:15:40,589 INFO [train.py:715] (4/8) Epoch 14, batch 10650, loss[loss=0.1442, simple_loss=0.2262, pruned_loss=0.03109, over 4826.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02998, over 972538.74 frames.], batch size: 26, lr: 1.58e-04
2022-05-08 01:16:19,717 INFO [train.py:715] (4/8) Epoch 14, batch 10700, loss[loss=0.156, simple_loss=0.216, pruned_loss=0.04803, over 4801.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02982, over 972507.37 frames.], batch size: 12, lr: 1.58e-04
2022-05-08 01:16:58,897 INFO [train.py:715] (4/8) Epoch 14, batch 10750, loss[loss=0.1298, simple_loss=0.2032, pruned_loss=0.02816, over 4822.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.0295, over 972437.41 frames.], batch size: 13, lr: 1.58e-04
2022-05-08 01:17:38,325 INFO [train.py:715] (4/8) Epoch 14, batch 10800, loss[loss=0.1789, simple_loss=0.2472, pruned_loss=0.05533, over 4991.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02943, over 972494.61 frames.], batch size: 14, lr: 1.58e-04
2022-05-08 01:18:17,863 INFO [train.py:715] (4/8) Epoch 14, batch 10850, loss[loss=0.1228, simple_loss=0.2051, pruned_loss=0.02022, over 4846.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03015, over 973072.51 frames.], batch size: 26, lr: 1.58e-04
2022-05-08 01:18:56,528 INFO [train.py:715] (4/8) Epoch 14, batch 10900, loss[loss=0.1236, simple_loss=0.2009, pruned_loss=0.02319, over 4799.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03019, over 973038.52 frames.], batch size: 21, lr: 1.58e-04
2022-05-08 01:19:36,744 INFO [train.py:715] (4/8) Epoch 14, batch 10950, loss[loss=0.1026, simple_loss=0.177, pruned_loss=0.01411, over 4937.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.03022, over 973430.88 frames.], batch size: 23, lr: 1.58e-04
2022-05-08 01:20:17,493 INFO [train.py:715] (4/8) Epoch 14, batch 11000, loss[loss=0.1347, simple_loss=0.2073, pruned_loss=0.03108, over 4938.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.0302, over 974152.32 frames.], batch size: 23, lr: 1.58e-04
2022-05-08 01:20:56,618 INFO [train.py:715] (4/8) Epoch 14, batch 11050, loss[loss=0.1232, simple_loss=0.1934, pruned_loss=0.02648, over 4795.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03054, over 973932.78 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 01:21:37,661 INFO [train.py:715] (4/8) Epoch 14, batch 11100, loss[loss=0.1211, simple_loss=0.1922, pruned_loss=0.02497, over 4719.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03012, over 973856.60 frames.], batch size: 12, lr: 1.57e-04
2022-05-08 01:22:18,219 INFO [train.py:715] (4/8) Epoch 14, batch 11150, loss[loss=0.1763, simple_loss=0.2424, pruned_loss=0.05509, over 4942.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.0302, over 973800.48 frames.], batch size: 35, lr: 1.57e-04
2022-05-08 01:22:58,452 INFO [train.py:715] (4/8) Epoch 14, batch 11200, loss[loss=0.1445, simple_loss=0.2203, pruned_loss=0.03438, over 4906.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03059, over 972305.60 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 01:23:37,876 INFO [train.py:715] (4/8) Epoch 14, batch 11250, loss[loss=0.1479, simple_loss=0.2281, pruned_loss=0.03388, over 4893.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03063, over 972471.10 frames.], batch size: 19, lr: 1.57e-04
2022-05-08 01:24:18,307 INFO [train.py:715] (4/8) Epoch 14, batch 11300, loss[loss=0.1603, simple_loss=0.2305, pruned_loss=0.04508, over 4759.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.03043, over 971276.15 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 01:24:58,565 INFO [train.py:715] (4/8) Epoch 14, batch 11350, loss[loss=0.1105, simple_loss=0.1833, pruned_loss=0.01882, over 4892.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2085, pruned_loss=0.03059, over 972309.69 frames.], batch size: 22, lr: 1.57e-04
2022-05-08 01:25:37,728 INFO [train.py:715] (4/8) Epoch 14, batch 11400, loss[loss=0.1503, simple_loss=0.2213, pruned_loss=0.03964, over 4854.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2081, pruned_loss=0.03081, over 972418.00 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 01:26:18,739 INFO [train.py:715] (4/8) Epoch 14, batch 11450, loss[loss=0.156, simple_loss=0.2153, pruned_loss=0.04838, over 4823.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2086, pruned_loss=0.03099, over 972205.92 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 01:26:59,118 INFO [train.py:715] (4/8) Epoch 14, batch 11500, loss[loss=0.1396, simple_loss=0.2086, pruned_loss=0.03534, over 4933.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03109, over 972257.84 frames.], batch size: 23, lr: 1.57e-04
2022-05-08 01:27:39,025 INFO [train.py:715] (4/8) Epoch 14, batch 11550, loss[loss=0.1321, simple_loss=0.2044, pruned_loss=0.02986, over 4851.00 frames.], tot_loss[loss=0.135, simple_loss=0.2082, pruned_loss=0.03095, over 972027.42 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 01:28:18,474 INFO [train.py:715] (4/8) Epoch 14, batch 11600, loss[loss=0.1273, simple_loss=0.2019, pruned_loss=0.0264, over 4777.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2091, pruned_loss=0.03114, over 971673.06 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 01:28:58,176 INFO [train.py:715] (4/8) Epoch 14, batch 11650, loss[loss=0.1319, simple_loss=0.2071, pruned_loss=0.0283, over 4815.00 frames.], tot_loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03079, over 971689.08 frames.], batch size: 12, lr: 1.57e-04
2022-05-08 01:29:37,887 INFO [train.py:715] (4/8) Epoch 14, batch 11700, loss[loss=0.1275, simple_loss=0.2164, pruned_loss=0.01937, over 4926.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03047, over 971167.01 frames.], batch size: 29, lr: 1.57e-04
2022-05-08 01:30:17,151 INFO [train.py:715] (4/8) Epoch 14, batch 11750, loss[loss=0.1308, simple_loss=0.2066, pruned_loss=0.02755, over 4981.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03077, over 971988.66 frames.], batch size: 31, lr: 1.57e-04
2022-05-08 01:30:56,855 INFO [train.py:715] (4/8) Epoch 14, batch 11800, loss[loss=0.1357, simple_loss=0.206, pruned_loss=0.03264, over 4933.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03021, over 971779.17 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 01:31:35,984 INFO [train.py:715] (4/8) Epoch 14, batch 11850, loss[loss=0.136, simple_loss=0.212, pruned_loss=0.02998, over 4901.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03015, over 971833.66 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 01:32:14,890 INFO [train.py:715] (4/8) Epoch 14, batch 11900, loss[loss=0.139, simple_loss=0.213, pruned_loss=0.03249, over 4864.00 frames.], tot_loss[loss=0.134, simple_loss=0.2087, pruned_loss=0.02965, over 971408.56 frames.], batch size: 32, lr: 1.57e-04
2022-05-08 01:32:54,216 INFO [train.py:715] (4/8) Epoch 14, batch 11950, loss[loss=0.1295, simple_loss=0.1994, pruned_loss=0.02976, over 4774.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2084, pruned_loss=0.02956, over 970546.50 frames.], batch size: 18, lr: 1.57e-04
2022-05-08 01:33:33,586 INFO [train.py:715] (4/8) Epoch 14, batch 12000, loss[loss=0.1433, simple_loss=0.216, pruned_loss=0.03529, over 4902.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02933, over 970700.17 frames.], batch size: 19, lr: 1.57e-04
2022-05-08 01:33:33,586 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 01:33:43,198 INFO [train.py:742] (4/8) Epoch 14, validation: loss=0.1051, simple_loss=0.1889, pruned_loss=0.01067, over 914524.00 frames.
2022-05-08 01:34:22,504 INFO [train.py:715] (4/8) Epoch 14, batch 12050, loss[loss=0.1508, simple_loss=0.2187, pruned_loss=0.04147, over 4958.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2082, pruned_loss=0.02957, over 970658.70 frames.], batch size: 35, lr: 1.57e-04
2022-05-08 01:35:01,859 INFO [train.py:715] (4/8) Epoch 14, batch 12100, loss[loss=0.1729, simple_loss=0.2318, pruned_loss=0.05702, over 4777.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2086, pruned_loss=0.02966, over 970790.31 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 01:35:41,278 INFO [train.py:715] (4/8) Epoch 14, batch 12150, loss[loss=0.118, simple_loss=0.1942, pruned_loss=0.02092, over 4969.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.0294, over 971043.50 frames.], batch size: 35, lr: 1.57e-04
2022-05-08 01:36:20,618 INFO [train.py:715] (4/8) Epoch 14, batch 12200, loss[loss=0.1335, simple_loss=0.2131, pruned_loss=0.02695, over 4820.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02943, over 971239.26 frames.], batch size: 25, lr: 1.57e-04
2022-05-08 01:37:00,489 INFO [train.py:715] (4/8) Epoch 14, batch 12250, loss[loss=0.1151, simple_loss=0.1916, pruned_loss=0.01929, over 4775.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.0298, over 971684.94 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 01:37:39,677 INFO [train.py:715] (4/8) Epoch 14, batch 12300, loss[loss=0.1165, simple_loss=0.1979, pruned_loss=0.01757, over 4915.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02982, over 971790.20 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 01:38:19,191 INFO [train.py:715] (4/8) Epoch 14, batch 12350, loss[loss=0.1162, simple_loss=0.1986, pruned_loss=0.01689, over 4904.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02985, over 971810.34 frames.], batch size: 22, lr: 1.57e-04
2022-05-08 01:38:58,798 INFO [train.py:715] (4/8) Epoch 14, batch 12400, loss[loss=0.1329, simple_loss=0.2012, pruned_loss=0.03236, over 4792.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.02999, over 972755.48 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 01:39:37,831 INFO [train.py:715] (4/8) Epoch 14, batch 12450, loss[loss=0.1447, simple_loss=0.2225, pruned_loss=0.03346, over 4904.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03085, over 972540.08 frames.], batch size: 18, lr: 1.57e-04
2022-05-08 01:40:17,257 INFO [train.py:715] (4/8) Epoch 14, batch 12500, loss[loss=0.135, simple_loss=0.2061, pruned_loss=0.03199, over 4798.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.03126, over 972693.37 frames.], batch size: 24, lr: 1.57e-04
2022-05-08 01:40:57,007 INFO [train.py:715] (4/8) Epoch 14, batch 12550, loss[loss=0.13, simple_loss=0.1962, pruned_loss=0.0319, over 4993.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2086, pruned_loss=0.03097, over 972416.24 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 01:41:36,647 INFO [train.py:715] (4/8) Epoch 14, batch 12600, loss[loss=0.1512, simple_loss=0.2227, pruned_loss=0.03982, over 4973.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03089, over 972947.30 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 01:42:15,592 INFO [train.py:715] (4/8) Epoch 14, batch 12650, loss[loss=0.1144, simple_loss=0.1909, pruned_loss=0.01897, over 4852.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03079, over 973615.50 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 01:42:55,473 INFO [train.py:715] (4/8) Epoch 14, batch 12700, loss[loss=0.1515, simple_loss=0.2302, pruned_loss=0.03636, over 4890.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03105, over 972997.29 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 01:43:35,529 INFO [train.py:715] (4/8) Epoch 14, batch 12750, loss[loss=0.1583, simple_loss=0.2325, pruned_loss=0.04205, over 4943.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.031, over 973687.56 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 01:44:15,523 INFO [train.py:715] (4/8) Epoch 14, batch 12800, loss[loss=0.1257, simple_loss=0.2, pruned_loss=0.02568, over 4799.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03088, over 972945.04 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 01:44:55,316 INFO [train.py:715] (4/8) Epoch 14, batch 12850, loss[loss=0.1311, simple_loss=0.2106, pruned_loss=0.02576, over 4703.00 frames.], tot_loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03081, over 972319.94 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 01:45:35,523 INFO [train.py:715] (4/8) Epoch 14, batch 12900, loss[loss=0.1122, simple_loss=0.1746, pruned_loss=0.02491, over 4758.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2091, pruned_loss=0.03113, over 972123.48 frames.], batch size: 12, lr: 1.57e-04
2022-05-08 01:46:15,876 INFO [train.py:715] (4/8) Epoch 14, batch 12950, loss[loss=0.1677, simple_loss=0.2427, pruned_loss=0.04637, over 4835.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.03112, over 972119.08 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 01:46:55,838 INFO [train.py:715] (4/8) Epoch 14, batch 13000, loss[loss=0.1232, simple_loss=0.1949, pruned_loss=0.02578, over 4819.00 frames.], tot_loss[loss=0.1365, simple_loss=0.2103, pruned_loss=0.03135, over 971764.76 frames.], batch size: 27, lr: 1.57e-04
2022-05-08 01:47:36,081 INFO [train.py:715] (4/8) Epoch 14, batch 13050, loss[loss=0.1324, simple_loss=0.1944, pruned_loss=0.03522, over 4806.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03116, over 972356.02 frames.], batch size: 24, lr: 1.57e-04
2022-05-08 01:48:16,099 INFO [train.py:715] (4/8) Epoch 14, batch 13100, loss[loss=0.1007, simple_loss=0.1846, pruned_loss=0.008373, over 4976.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03106, over 972148.25 frames.], batch size: 24, lr: 1.57e-04
2022-05-08 01:48:56,284 INFO [train.py:715] (4/8) Epoch 14, batch 13150, loss[loss=0.1337, simple_loss=0.2016, pruned_loss=0.03295, over 4794.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2096, pruned_loss=0.03134, over 971835.03 frames.], batch size: 24, lr: 1.57e-04
2022-05-08 01:49:36,379 INFO [train.py:715] (4/8) Epoch 14, batch 13200, loss[loss=0.1434, simple_loss=0.2227, pruned_loss=0.03206, over 4985.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2089, pruned_loss=0.03147, over 971766.09 frames.], batch size: 28, lr: 1.57e-04
2022-05-08 01:50:16,585 INFO [train.py:715] (4/8) Epoch 14, batch 13250, loss[loss=0.1273, simple_loss=0.2059, pruned_loss=0.02435, over 4914.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2079, pruned_loss=0.0308, over 971790.31 frames.], batch size: 39, lr: 1.57e-04
2022-05-08 01:50:56,842 INFO [train.py:715] (4/8) Epoch 14, batch 13300, loss[loss=0.1524, simple_loss=0.2188, pruned_loss=0.04299, over 4989.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2078, pruned_loss=0.03053, over 971633.06 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 01:51:36,426 INFO [train.py:715] (4/8) Epoch 14, batch 13350, loss[loss=0.1631, simple_loss=0.2406, pruned_loss=0.0428, over 4861.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03068, over 971997.65 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 01:52:15,921 INFO [train.py:715] (4/8) Epoch 14, batch 13400, loss[loss=0.1301, simple_loss=0.2065, pruned_loss=0.02687, over 4920.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03107, over 972037.90 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 01:52:55,516 INFO [train.py:715] (4/8) Epoch 14, batch 13450, loss[loss=0.1313, simple_loss=0.2084, pruned_loss=0.02715, over 4925.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03084, over 971569.21 frames.], batch size: 23, lr: 1.57e-04
2022-05-08 01:53:35,077 INFO [train.py:715] (4/8) Epoch 14, batch 13500, loss[loss=0.1109, simple_loss=0.1886, pruned_loss=0.01661, over 4933.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03056, over 972272.98 frames.], batch size: 23, lr: 1.57e-04
2022-05-08 01:54:14,284 INFO [train.py:715] (4/8) Epoch 14, batch 13550, loss[loss=0.1274, simple_loss=0.2065, pruned_loss=0.02415, over 4872.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03045, over 973572.55 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 01:54:53,676 INFO [train.py:715] (4/8) Epoch 14, batch 13600, loss[loss=0.1363, simple_loss=0.2178, pruned_loss=0.02738, over 4957.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03035, over 972952.34 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 01:55:32,972 INFO [train.py:715] (4/8) Epoch 14, batch 13650, loss[loss=0.1246, simple_loss=0.2038, pruned_loss=0.02268, over 4875.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03034, over 971382.36 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 01:56:12,538 INFO [train.py:715] (4/8) Epoch 14, batch 13700, loss[loss=0.135, simple_loss=0.2011, pruned_loss=0.03441, over 4769.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03032, over 971165.12 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 01:56:51,586 INFO [train.py:715] (4/8) Epoch 14, batch 13750, loss[loss=0.1188, simple_loss=0.1946, pruned_loss=0.02155, over 4967.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.0302, over 970824.08 frames.], batch size: 24, lr: 1.57e-04
2022-05-08 01:57:30,924 INFO [train.py:715] (4/8) Epoch 14, batch 13800, loss[loss=0.1362, simple_loss=0.2092, pruned_loss=0.03156, over 4971.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03065, over 970816.15 frames.], batch size: 39, lr: 1.57e-04
2022-05-08 01:58:12,475 INFO [train.py:715] (4/8) Epoch 14, batch 13850, loss[loss=0.1687, simple_loss=0.251, pruned_loss=0.04316, over 4864.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03067, over 971686.35 frames.], batch size: 38, lr: 1.57e-04
2022-05-08 01:58:51,820 INFO [train.py:715] (4/8) Epoch 14, batch 13900, loss[loss=0.125, simple_loss=0.1898, pruned_loss=0.03008, over 4974.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03086, over 972416.30 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 01:59:31,447 INFO [train.py:715] (4/8) Epoch 14, batch 13950, loss[loss=0.1676, simple_loss=0.2317, pruned_loss=0.05168, over 4873.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2095, pruned_loss=0.03144, over 971873.60 frames.], batch size: 22, lr: 1.57e-04
2022-05-08 02:00:10,941 INFO [train.py:715] (4/8) Epoch 14, batch 14000, loss[loss=0.1104, simple_loss=0.1829, pruned_loss=0.01898, over 4941.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03124, over 971854.52 frames.], batch size: 29, lr: 1.57e-04
2022-05-08 02:00:50,380 INFO [train.py:715] (4/8) Epoch 14, batch 14050, loss[loss=0.1444, simple_loss=0.2196, pruned_loss=0.0346, over 4954.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03112, over 972617.02 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 02:01:30,046 INFO [train.py:715] (4/8) Epoch 14, batch 14100, loss[loss=0.132, simple_loss=0.1998, pruned_loss=0.03204, over 4702.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03091, over 973350.69 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:02:09,595 INFO [train.py:715] (4/8) Epoch 14, batch 14150, loss[loss=0.1784, simple_loss=0.2443, pruned_loss=0.05624, over 4937.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2101, pruned_loss=0.03111, over 973312.89 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 02:02:49,094 INFO [train.py:715] (4/8) Epoch 14, batch 14200, loss[loss=0.1373, simple_loss=0.2098, pruned_loss=0.03239, over 4752.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03098, over 972973.32 frames.], batch size: 19, lr: 1.57e-04
2022-05-08 02:03:28,352 INFO [train.py:715] (4/8) Epoch 14, batch 14250, loss[loss=0.1229, simple_loss=0.1955, pruned_loss=0.02514, over 4898.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03122, over 973274.09 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 02:04:08,206 INFO [train.py:715] (4/8) Epoch 14, batch 14300, loss[loss=0.1441, simple_loss=0.211, pruned_loss=0.03862, over 4767.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03055, over 972667.08 frames.], batch size: 19, lr: 1.57e-04
2022-05-08 02:04:47,397 INFO [train.py:715] (4/8) Epoch 14, batch 14350, loss[loss=0.1351, simple_loss=0.2128, pruned_loss=0.02869, over 4878.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03052, over 972072.31 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 02:05:26,852 INFO [train.py:715] (4/8) Epoch 14, batch 14400, loss[loss=0.1655, simple_loss=0.2356, pruned_loss=0.04769, over 4945.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03071, over 972129.10 frames.], batch size: 39, lr: 1.57e-04
2022-05-08 02:06:06,343 INFO [train.py:715] (4/8) Epoch 14, batch 14450, loss[loss=0.1313, simple_loss=0.2091, pruned_loss=0.02679, over 4779.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03068, over 970539.88 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 02:06:45,899 INFO [train.py:715] (4/8) Epoch 14, batch 14500, loss[loss=0.1236, simple_loss=0.1939, pruned_loss=0.02668, over 4694.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03049, over 970609.63 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:07:25,175 INFO [train.py:715] (4/8) Epoch 14, batch 14550, loss[loss=0.1592, simple_loss=0.2261, pruned_loss=0.04618, over 4925.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.03047, over 970926.19 frames.], batch size: 23, lr: 1.57e-04
2022-05-08 02:08:04,456 INFO [train.py:715] (4/8) Epoch 14, batch 14600, loss[loss=0.09694, simple_loss=0.1689, pruned_loss=0.01249, over 4844.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03024, over 971880.62 frames.], batch size: 13, lr: 1.57e-04
2022-05-08 02:08:44,677 INFO [train.py:715] (4/8) Epoch 14, batch 14650, loss[loss=0.1299, simple_loss=0.2088, pruned_loss=0.0255, over 4878.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03016, over 971442.41 frames.], batch size: 22, lr: 1.57e-04
2022-05-08 02:09:24,104 INFO [train.py:715] (4/8) Epoch 14, batch 14700, loss[loss=0.1227, simple_loss=0.2003, pruned_loss=0.02256, over 4798.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.02995, over 970666.62 frames.], batch size: 18, lr: 1.57e-04
2022-05-08 02:10:03,918 INFO [train.py:715] (4/8) Epoch 14, batch 14750, loss[loss=0.1471, simple_loss=0.2131, pruned_loss=0.04059, over 4851.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03009, over 970346.01 frames.], batch size: 30, lr: 1.57e-04
2022-05-08 02:10:43,093 INFO [train.py:715] (4/8) Epoch 14, batch 14800, loss[loss=0.1345, simple_loss=0.2047, pruned_loss=0.03217, over 4845.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03008, over 971232.83 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 02:11:23,009 INFO [train.py:715] (4/8) Epoch 14, batch 14850, loss[loss=0.1467, simple_loss=0.2096, pruned_loss=0.0419, over 4838.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2073, pruned_loss=0.03014, over 971373.27 frames.], batch size: 32, lr: 1.57e-04
2022-05-08 02:12:02,550 INFO [train.py:715] (4/8) Epoch 14, batch 14900, loss[loss=0.1355, simple_loss=0.2036, pruned_loss=0.03372, over 4875.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2079, pruned_loss=0.03034, over 972597.02 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 02:12:41,998 INFO [train.py:715] (4/8) Epoch 14, batch 14950, loss[loss=0.1187, simple_loss=0.194, pruned_loss=0.02173, over 4822.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03032, over 972602.10 frames.], batch size: 27, lr: 1.57e-04
2022-05-08 02:13:22,058 INFO [train.py:715] (4/8) Epoch 14, batch 15000, loss[loss=0.1277, simple_loss=0.2047, pruned_loss=0.02532, over 4777.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02989, over 972551.53 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 02:13:22,059 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 02:13:31,706 INFO [train.py:742] (4/8) Epoch 14, validation: loss=0.1052, simple_loss=0.1889, pruned_loss=0.01079, over 914524.00 frames.
2022-05-08 02:14:12,573 INFO [train.py:715] (4/8) Epoch 14, batch 15050, loss[loss=0.127, simple_loss=0.1985, pruned_loss=0.02772, over 4817.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03063, over 972403.56 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:14:52,656 INFO [train.py:715] (4/8) Epoch 14, batch 15100, loss[loss=0.1204, simple_loss=0.197, pruned_loss=0.02196, over 4773.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03093, over 972157.56 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 02:15:33,303 INFO [train.py:715] (4/8) Epoch 14, batch 15150, loss[loss=0.1127, simple_loss=0.1798, pruned_loss=0.02284, over 4936.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03122, over 973564.39 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 02:16:13,412 INFO [train.py:715] (4/8) Epoch 14, batch 15200, loss[loss=0.1203, simple_loss=0.1899, pruned_loss=0.02535, over 4835.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.03113, over 973998.54 frames.], batch size: 13, lr: 1.57e-04
2022-05-08 02:16:54,055 INFO [train.py:715] (4/8) Epoch 14, batch 15250, loss[loss=0.1261, simple_loss=0.2009, pruned_loss=0.02568, over 4977.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03067, over 974095.06 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 02:17:33,927 INFO [train.py:715] (4/8) Epoch 14, batch 15300, loss[loss=0.1497, simple_loss=0.2245, pruned_loss=0.03743, over 4928.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03067, over 974601.92 frames.], batch size: 18, lr: 1.57e-04
2022-05-08 02:18:13,475 INFO [train.py:715] (4/8) Epoch 14, batch 15350, loss[loss=0.1551, simple_loss=0.2273, pruned_loss=0.04139, over 4792.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2095, pruned_loss=0.03041, over 975033.51 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 02:18:53,583 INFO [train.py:715] (4/8) Epoch 14, batch 15400, loss[loss=0.1207, simple_loss=0.2, pruned_loss=0.02072, over 4788.00 frames.], tot_loss[loss=0.1358, simple_loss=0.21, pruned_loss=0.03079, over 974382.29 frames.], batch size: 24, lr: 1.57e-04
2022-05-08 02:19:32,974 INFO [train.py:715] (4/8) Epoch 14, batch 15450, loss[loss=0.1341, simple_loss=0.2231, pruned_loss=0.02257, over 4635.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03036, over 974094.99 frames.], batch size: 13, lr: 1.57e-04
2022-05-08 02:20:12,212 INFO [train.py:715] (4/8) Epoch 14, batch 15500, loss[loss=0.1269, simple_loss=0.2067, pruned_loss=0.02355, over 4868.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03036, over 973827.53 frames.], batch size: 22, lr: 1.57e-04
2022-05-08 02:20:51,548 INFO [train.py:715] (4/8) Epoch 14, batch 15550, loss[loss=0.1293, simple_loss=0.2063, pruned_loss=0.02615, over 4860.00 frames.], tot_loss[loss=0.136, simple_loss=0.2102, pruned_loss=0.03089, over 973039.69 frames.], batch size: 20, lr: 1.57e-04
2022-05-08 02:21:31,492 INFO [train.py:715] (4/8) Epoch 14, batch 15600, loss[loss=0.1482, simple_loss=0.2181, pruned_loss=0.03917, over 4946.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03064, over 973483.65 frames.], batch size: 39, lr: 1.57e-04
2022-05-08 02:22:10,935 INFO [train.py:715] (4/8) Epoch 14, batch 15650, loss[loss=0.1327, simple_loss=0.2024, pruned_loss=0.03151, over 4861.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03038, over 972778.69 frames.], batch size: 30, lr: 1.57e-04
2022-05-08 02:22:49,322 INFO [train.py:715] (4/8) Epoch 14, batch 15700, loss[loss=0.1575, simple_loss=0.2292, pruned_loss=0.04288, over 4884.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02995, over 973567.06 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 02:23:29,530 INFO [train.py:715] (4/8) Epoch 14, batch 15750, loss[loss=0.1369, simple_loss=0.2073, pruned_loss=0.03326, over 4995.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02988, over 973290.24 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 02:24:09,056 INFO [train.py:715] (4/8) Epoch 14, batch 15800, loss[loss=0.1482, simple_loss=0.2208, pruned_loss=0.03775, over 4913.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03004, over 972395.04 frames.], batch size: 17, lr: 1.57e-04
2022-05-08 02:24:48,296 INFO [train.py:715] (4/8) Epoch 14, batch 15850, loss[loss=0.1531, simple_loss=0.2198, pruned_loss=0.04318, over 4878.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03017, over 972361.81 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 02:25:27,575 INFO [train.py:715] (4/8) Epoch 14, batch 15900, loss[loss=0.1059, simple_loss=0.179, pruned_loss=0.01642, over 4836.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02999, over 972640.11 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:26:07,618 INFO [train.py:715] (4/8) Epoch 14, batch 15950, loss[loss=0.124, simple_loss=0.2032, pruned_loss=0.02239, over 4791.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03025, over 972684.52 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 02:26:47,030 INFO [train.py:715] (4/8) Epoch 14, batch 16000, loss[loss=0.1214, simple_loss=0.1969, pruned_loss=0.02302, over 4948.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03045, over 973381.25 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:27:25,749 INFO [train.py:715] (4/8) Epoch 14, batch 16050, loss[loss=0.1612, simple_loss=0.2431, pruned_loss=0.03967, over 4880.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03064, over 973207.09 frames.], batch size: 22, lr: 1.57e-04
2022-05-08 02:28:04,469 INFO [train.py:715] (4/8) Epoch 14, batch 16100, loss[loss=0.1489, simple_loss=0.2134, pruned_loss=0.04218, over 4694.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2097, pruned_loss=0.03078, over 973122.78 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:28:42,585 INFO [train.py:715] (4/8) Epoch 14, batch 16150, loss[loss=0.1343, simple_loss=0.2159, pruned_loss=0.02638, over 4964.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2105, pruned_loss=0.03115, over 972796.11 frames.], batch size: 24, lr: 1.57e-04
2022-05-08 02:29:20,835 INFO [train.py:715] (4/8) Epoch 14, batch 16200, loss[loss=0.1309, simple_loss=0.2085, pruned_loss=0.02662, over 4696.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.0311, over 972520.74 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:29:59,440 INFO [train.py:715] (4/8) Epoch 14, batch 16250, loss[loss=0.1293, simple_loss=0.2086, pruned_loss=0.02503, over 4925.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2104, pruned_loss=0.03104, over 972978.77 frames.], batch size: 29, lr: 1.57e-04
2022-05-08 02:30:38,582 INFO [train.py:715] (4/8) Epoch 14, batch 16300, loss[loss=0.1176, simple_loss=0.1872, pruned_loss=0.024, over 4728.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2096, pruned_loss=0.03037, over 973433.82 frames.], batch size: 12, lr: 1.57e-04
2022-05-08 02:31:16,528 INFO [train.py:715] (4/8) Epoch 14, batch 16350, loss[loss=0.1696, simple_loss=0.2414, pruned_loss=0.04895, over 4860.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.03068, over 973971.15 frames.], batch size: 32, lr: 1.57e-04
2022-05-08 02:31:55,703 INFO [train.py:715] (4/8) Epoch 14, batch 16400, loss[loss=0.1364, simple_loss=0.2109, pruned_loss=0.03098, over 4931.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03062, over 973731.60 frames.], batch size: 23, lr: 1.57e-04
2022-05-08 02:32:35,415 INFO [train.py:715] (4/8) Epoch 14, batch 16450, loss[loss=0.1557, simple_loss=0.2289, pruned_loss=0.04124, over 4801.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03079, over 974081.95 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 02:33:14,851 INFO [train.py:715] (4/8) Epoch 14, batch 16500, loss[loss=0.1323, simple_loss=0.2111, pruned_loss=0.02671, over 4738.00 frames.], tot_loss[loss=0.1344, simple_loss=0.208, pruned_loss=0.03042, over 973102.78 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 02:33:53,745 INFO [train.py:715] (4/8) Epoch 14, batch 16550, loss[loss=0.1329, simple_loss=0.2124, pruned_loss=0.02666, over 4787.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.0306, over 972501.12 frames.], batch size: 14, lr: 1.57e-04
2022-05-08 02:34:34,127 INFO [train.py:715] (4/8) Epoch 14, batch 16600, loss[loss=0.1551, simple_loss=0.2239, pruned_loss=0.04318, over 4939.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03081, over 971837.72 frames.], batch size: 21, lr: 1.57e-04
2022-05-08 02:35:13,400 INFO [train.py:715] (4/8) Epoch 14, batch 16650, loss[loss=0.1198, simple_loss=0.194, pruned_loss=0.0228, over 4988.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03057, over 972016.63 frames.], batch size: 26, lr: 1.57e-04
2022-05-08 02:35:55,020 INFO [train.py:715] (4/8) Epoch 14, batch 16700, loss[loss=0.1413, simple_loss=0.2192, pruned_loss=0.03167, over 4637.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.0307, over 971832.59 frames.], batch size: 13, lr: 1.57e-04
2022-05-08 02:36:34,901 INFO [train.py:715] (4/8) Epoch 14, batch 16750, loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03145, over 4900.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2099, pruned_loss=0.03113, over 972619.90 frames.], batch size: 19, lr: 1.57e-04
2022-05-08 02:37:15,256 INFO [train.py:715] (4/8) Epoch 14, batch 16800, loss[loss=0.1632, simple_loss=0.2286, pruned_loss=0.04895, over 4874.00 frames.], tot_loss[loss=0.1371, simple_loss=0.2108, pruned_loss=0.03176, over 972972.28 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 02:37:54,765 INFO [train.py:715] (4/8) Epoch 14, batch 16850, loss[loss=0.1696, simple_loss=0.2355, pruned_loss=0.05185, over 4949.00 frames.], tot_loss[loss=0.137, simple_loss=0.2106, pruned_loss=0.03166, over 972426.06 frames.], batch size: 39, lr: 1.57e-04
2022-05-08 02:38:34,394 INFO [train.py:715] (4/8) Epoch 14, batch 16900, loss[loss=0.1378, simple_loss=0.2069, pruned_loss=0.0343, over 4836.00 frames.], tot_loss[loss=0.1373, simple_loss=0.211, pruned_loss=0.03175, over 972809.40 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:39:15,367 INFO [train.py:715] (4/8) Epoch 14, batch 16950, loss[loss=0.1358, simple_loss=0.2034, pruned_loss=0.03407, over 4735.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2109, pruned_loss=0.0318, over 973135.20 frames.], batch size: 16, lr: 1.57e-04
2022-05-08 02:39:56,910 INFO [train.py:715] (4/8) Epoch 14, batch 17000, loss[loss=0.1441, simple_loss=0.2256, pruned_loss=0.03127, over 4975.00 frames.], tot_loss[loss=0.1372, simple_loss=0.2109, pruned_loss=0.03177, over 972849.11 frames.], batch size: 25, lr: 1.57e-04
2022-05-08 02:40:37,806 INFO [train.py:715] (4/8) Epoch 14, batch 17050, loss[loss=0.1496, simple_loss=0.2307, pruned_loss=0.03426, over 4837.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2109, pruned_loss=0.03149, over 972327.35 frames.], batch size: 15, lr: 1.57e-04
2022-05-08 02:41:18,902 INFO [train.py:715] (4/8) Epoch 14, batch 17100, loss[loss=0.144, simple_loss=0.2113, pruned_loss=0.03838, over 4859.00 frames.], tot_loss[loss=0.1376, simple_loss=0.2112, pruned_loss=0.03197, over 972357.77 frames.], batch size: 13, lr: 1.57e-04
2022-05-08 02:42:00,997 INFO [train.py:715] (4/8) Epoch 14, batch 17150, loss[loss=0.1418, simple_loss=0.2193, pruned_loss=0.0321, over 4917.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03133, over 972901.78 frames.], batch size: 23, lr: 1.57e-04
2022-05-08 02:42:41,738 INFO [train.py:715] (4/8) Epoch 14, batch 17200, loss[loss=0.1815, simple_loss=0.2605, pruned_loss=0.05124, over 4864.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2107, pruned_loss=0.03141, over 972331.88 frames.], batch size: 32, lr: 1.57e-04
2022-05-08 02:43:22,713 INFO [train.py:715] (4/8) Epoch 14, batch 17250, loss[loss=0.1332, simple_loss=0.2109, pruned_loss=0.02775, over 4848.00 frames.], tot_loss[loss=0.1359, simple_loss=0.21, pruned_loss=0.03091, over 972608.40 frames.], batch size: 30, lr: 1.57e-04
2022-05-08 02:44:04,207 INFO [train.py:715] (4/8) Epoch 14, batch 17300, loss[loss=0.114, simple_loss=0.1825, pruned_loss=0.02278, over 4836.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03047, over 972595.97 frames.], batch size: 13, lr: 1.57e-04
2022-05-08 02:44:45,856 INFO [train.py:715] (4/8) Epoch 14, batch 17350, loss[loss=0.15, simple_loss=0.2192, pruned_loss=0.04045, over 4895.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.0306, over 973299.38 frames.], batch size: 19, lr: 1.57e-04
2022-05-08 02:45:26,221 INFO [train.py:715] (4/8) Epoch 14, batch 17400, loss[loss=0.1171, simple_loss=0.1913, pruned_loss=0.02149, over 4927.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2094, pruned_loss=0.03048, over 973321.17 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 02:46:07,479 INFO [train.py:715] (4/8) Epoch 14, batch 17450, loss[loss=0.1376, simple_loss=0.2134, pruned_loss=0.03085, over 4963.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03086, over 973666.35 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 02:46:49,053 INFO [train.py:715] (4/8) Epoch 14, batch 17500, loss[loss=0.1245, simple_loss=0.2051, pruned_loss=0.02195, over 4849.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2102, pruned_loss=0.031, over 973115.77 frames.], batch size: 34, lr: 1.56e-04
2022-05-08 02:47:29,790 INFO [train.py:715] (4/8) Epoch 14, batch 17550, loss[loss=0.1546, simple_loss=0.229, pruned_loss=0.04004, over 4890.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03091, over 972341.02 frames.], batch size: 22, lr: 1.56e-04
2022-05-08 02:48:10,318 INFO [train.py:715] (4/8) Epoch 14, batch 17600, loss[loss=0.1215, simple_loss=0.1981, pruned_loss=0.02242, over 4917.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2101, pruned_loss=0.03127, over 972150.83 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 02:48:52,023 INFO [train.py:715] (4/8) Epoch 14, batch 17650, loss[loss=0.1351, simple_loss=0.2114, pruned_loss=0.02943, over 4988.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2102, pruned_loss=0.0311, over 971996.04 frames.], batch size: 40, lr: 1.56e-04
2022-05-08 02:49:33,154 INFO [train.py:715] (4/8) Epoch 14, batch 17700, loss[loss=0.1488, simple_loss=0.2115, pruned_loss=0.04309, over 4696.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03067, over 971966.47 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 02:50:13,639 INFO [train.py:715] (4/8) Epoch 14, batch 17750, loss[loss=0.1322, simple_loss=0.2093, pruned_loss=0.02752, over 4829.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03055, over 972169.13 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 02:50:55,010 INFO [train.py:715] (4/8) Epoch 14, batch 17800, loss[loss=0.1011, simple_loss=0.1725, pruned_loss=0.01487, over 4801.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03051, over 972217.46 frames.], batch size: 12, lr: 1.56e-04
2022-05-08 02:51:35,957 INFO [train.py:715] (4/8) Epoch 14, batch 17850, loss[loss=0.1304, simple_loss=0.1982, pruned_loss=0.03131, over 4982.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03043, over 972351.39 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 02:52:16,729 INFO [train.py:715] (4/8) Epoch 14, batch 17900, loss[loss=0.1474, simple_loss=0.2313, pruned_loss=0.03172, over 4899.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03053, over 972801.72 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 02:52:57,206 INFO [train.py:715] (4/8) Epoch 14, batch 17950, loss[loss=0.1229, simple_loss=0.1906, pruned_loss=0.0276, over 4921.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03076, over 972679.88 frames.], batch size: 23, lr: 1.56e-04
2022-05-08 02:53:38,590 INFO [train.py:715] (4/8) Epoch 14, batch 18000, loss[loss=0.1384, simple_loss=0.2143, pruned_loss=0.0313, over 4681.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.0304, over 972848.04 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 02:53:38,591 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 02:53:48,446 INFO [train.py:742] (4/8) Epoch 14, validation: loss=0.1052, simple_loss=0.1889, pruned_loss=0.01075, over 914524.00 frames.
2022-05-08 02:54:29,829 INFO [train.py:715] (4/8) Epoch 14, batch 18050, loss[loss=0.1108, simple_loss=0.1939, pruned_loss=0.01386, over 4985.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03082, over 973388.65 frames.], batch size: 25, lr: 1.56e-04
2022-05-08 02:55:10,975 INFO [train.py:715] (4/8) Epoch 14, batch 18100, loss[loss=0.189, simple_loss=0.271, pruned_loss=0.05346, over 4866.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03091, over 973568.57 frames.], batch size: 30, lr: 1.56e-04
2022-05-08 02:55:52,580 INFO [train.py:715] (4/8) Epoch 14, batch 18150, loss[loss=0.1279, simple_loss=0.2013, pruned_loss=0.02728, over 4960.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03105, over 973242.32 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 02:56:33,500 INFO [train.py:715] (4/8) Epoch 14, batch 18200, loss[loss=0.1502, simple_loss=0.2191, pruned_loss=0.04062, over 4845.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03084, over 972990.18 frames.], batch size: 30, lr: 1.56e-04
2022-05-08 02:57:15,443 INFO [train.py:715] (4/8) Epoch 14, batch 18250, loss[loss=0.1579, simple_loss=0.2232, pruned_loss=0.04633, over 4825.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03085, over 972379.48 frames.], batch size: 13, lr: 1.56e-04
2022-05-08 02:57:56,887 INFO [train.py:715] (4/8) Epoch 14, batch 18300, loss[loss=0.1766, simple_loss=0.2629, pruned_loss=0.04514, over 4950.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03059, over 971149.89 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 02:58:36,493 INFO [train.py:715] (4/8) Epoch 14, batch 18350, loss[loss=0.1223, simple_loss=0.2072, pruned_loss=0.0187, over 4927.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2092, pruned_loss=0.03024, over 971667.47 frames.], batch size: 23, lr: 1.56e-04
2022-05-08 02:59:17,357 INFO [train.py:715] (4/8) Epoch 14, batch 18400, loss[loss=0.1314, simple_loss=0.2157, pruned_loss=0.02353, over 4820.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03052, over 970449.11 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 02:59:58,006 INFO [train.py:715] (4/8) Epoch 14, batch 18450, loss[loss=0.1339, simple_loss=0.219, pruned_loss=0.02443, over 4943.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2093, pruned_loss=0.03052, over 971019.58 frames.], batch size: 29, lr: 1.56e-04
2022-05-08 03:00:38,225 INFO [train.py:715] (4/8) Epoch 14, batch 18500, loss[loss=0.1253, simple_loss=0.2065, pruned_loss=0.02206, over 4694.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03035, over 971183.62 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:01:18,698 INFO [train.py:715] (4/8) Epoch 14, batch 18550, loss[loss=0.1348, simple_loss=0.2193, pruned_loss=0.0251, over 4924.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.0305, over 970358.25 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:01:59,556 INFO [train.py:715] (4/8) Epoch 14, batch 18600, loss[loss=0.1299, simple_loss=0.1988, pruned_loss=0.03051, over 4757.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03068, over 970354.40 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:02:39,862 INFO [train.py:715] (4/8) Epoch 14, batch 18650, loss[loss=0.1369, simple_loss=0.2101, pruned_loss=0.03182, over 4954.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.0306, over 970783.31 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:03:20,566 INFO [train.py:715] (4/8) Epoch 14, batch 18700, loss[loss=0.13, simple_loss=0.2064, pruned_loss=0.02678, over 4798.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03109, over 970501.21 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 03:04:01,157 INFO [train.py:715] (4/8) Epoch 14, batch 18750, loss[loss=0.1174, simple_loss=0.1862, pruned_loss=0.02431, over 4813.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2093, pruned_loss=0.03113, over 970614.29 frames.], batch size: 13, lr: 1.56e-04
2022-05-08 03:04:41,123 INFO [train.py:715] (4/8) Epoch 14, batch 18800, loss[loss=0.1423, simple_loss=0.2247, pruned_loss=0.02995, over 4903.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03154, over 970380.19 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 03:05:21,093 INFO [train.py:715] (4/8) Epoch 14, batch 18850, loss[loss=0.1418, simple_loss=0.2125, pruned_loss=0.03559, over 4854.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2103, pruned_loss=0.03153, over 971267.35 frames.], batch size: 30, lr: 1.56e-04
2022-05-08 03:06:01,824 INFO [train.py:715] (4/8) Epoch 14, batch 18900, loss[loss=0.1583, simple_loss=0.2231, pruned_loss=0.04668, over 4846.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03084, over 971640.12 frames.], batch size: 34, lr: 1.56e-04
2022-05-08 03:06:42,898 INFO [train.py:715] (4/8) Epoch 14, batch 18950, loss[loss=0.1359, simple_loss=0.2072, pruned_loss=0.03225, over 4976.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.0308, over 972101.82 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 03:07:23,140 INFO [train.py:715] (4/8) Epoch 14, batch 19000, loss[loss=0.1525, simple_loss=0.2412, pruned_loss=0.03187, over 4777.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03094, over 971781.63 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:08:04,068 INFO [train.py:715] (4/8) Epoch 14, batch 19050, loss[loss=0.1423, simple_loss=0.2098, pruned_loss=0.03739, over 4972.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03068, over 972095.66 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 03:08:45,083 INFO [train.py:715] (4/8) Epoch 14, batch 19100, loss[loss=0.133, simple_loss=0.2067, pruned_loss=0.02963, over 4782.00 frames.], tot_loss[loss=0.1353, simple_loss=0.209, pruned_loss=0.03083, over 972148.08 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:09:25,464 INFO [train.py:715] (4/8) Epoch 14, batch 19150, loss[loss=0.13, simple_loss=0.2096, pruned_loss=0.0252, over 4780.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03055, over 972339.48 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:10:04,872 INFO [train.py:715] (4/8) Epoch 14, batch 19200, loss[loss=0.1178, simple_loss=0.2029, pruned_loss=0.01636, over 4789.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03018, over 971437.19 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 03:10:45,984 INFO [train.py:715] (4/8) Epoch 14, batch 19250, loss[loss=0.1489, simple_loss=0.2176, pruned_loss=0.04008, over 4855.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03002, over 970497.81 frames.], batch size: 32, lr: 1.56e-04
2022-05-08 03:11:26,905 INFO [train.py:715] (4/8) Epoch 14, batch 19300, loss[loss=0.122, simple_loss=0.2065, pruned_loss=0.01872, over 4931.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02999, over 971236.65 frames.], batch size: 29, lr: 1.56e-04
2022-05-08 03:12:06,951 INFO [train.py:715] (4/8) Epoch 14, batch 19350, loss[loss=0.1329, simple_loss=0.1958, pruned_loss=0.03501, over 4840.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.03003, over 971194.16 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:12:47,196 INFO [train.py:715] (4/8) Epoch 14, batch 19400, loss[loss=0.1529, simple_loss=0.2334, pruned_loss=0.03621, over 4859.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03005, over 972172.90 frames.], batch size: 32, lr: 1.56e-04
2022-05-08 03:13:28,654 INFO [train.py:715] (4/8) Epoch 14, batch 19450, loss[loss=0.1558, simple_loss=0.2294, pruned_loss=0.04112, over 4856.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03028, over 971858.84 frames.], batch size: 30, lr: 1.56e-04
2022-05-08 03:14:08,960 INFO [train.py:715] (4/8) Epoch 14, batch 19500, loss[loss=0.129, simple_loss=0.209, pruned_loss=0.02447, over 4690.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03008, over 972376.58 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:14:49,606 INFO [train.py:715] (4/8) Epoch 14, batch 19550, loss[loss=0.09941, simple_loss=0.1658, pruned_loss=0.0165, over 4692.00 frames.], tot_loss[loss=0.1335, simple_loss=0.208, pruned_loss=0.02951, over 972569.49 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:15:30,069 INFO [train.py:715] (4/8) Epoch 14, batch 19600, loss[loss=0.1136, simple_loss=0.19, pruned_loss=0.01858, over 4979.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02899, over 973385.46 frames.], batch size: 28, lr: 1.56e-04
2022-05-08 03:16:10,998 INFO [train.py:715] (4/8) Epoch 14, batch 19650, loss[loss=0.1347, simple_loss=0.2042, pruned_loss=0.03256, over 4771.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02917, over 972842.98 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 03:16:51,974 INFO [train.py:715] (4/8) Epoch 14, batch 19700, loss[loss=0.1393, simple_loss=0.2086, pruned_loss=0.03495, over 4819.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02999, over 973275.28 frames.], batch size: 25, lr: 1.56e-04
2022-05-08 03:17:32,730 INFO [train.py:715] (4/8) Epoch 14, batch 19750, loss[loss=0.1616, simple_loss=0.2221, pruned_loss=0.0506, over 4774.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02999, over 973344.24 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 03:18:13,650 INFO [train.py:715] (4/8) Epoch 14, batch 19800, loss[loss=0.1454, simple_loss=0.2119, pruned_loss=0.03942, over 4933.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03041, over 972530.46 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:18:54,280 INFO [train.py:715] (4/8) Epoch 14, batch 19850, loss[loss=0.1516, simple_loss=0.2207, pruned_loss=0.04127, over 4869.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2098, pruned_loss=0.03107, over 971782.19 frames.], batch size: 32, lr: 1.56e-04
2022-05-08 03:19:35,280 INFO [train.py:715] (4/8) Epoch 14, batch 19900, loss[loss=0.1377, simple_loss=0.2168, pruned_loss=0.02928, over 4934.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03081, over 972400.81 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:20:15,388 INFO [train.py:715] (4/8) Epoch 14, batch 19950, loss[loss=0.1115, simple_loss=0.185, pruned_loss=0.01906, over 4969.00 frames.], tot_loss[loss=0.1357, simple_loss=0.209, pruned_loss=0.03117, over 972654.96 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 03:20:55,687 INFO [train.py:715] (4/8) Epoch 14, batch 20000, loss[loss=0.1066, simple_loss=0.1849, pruned_loss=0.01411, over 4753.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03066, over 972527.92 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 03:21:35,498 INFO [train.py:715] (4/8) Epoch 14, batch 20050, loss[loss=0.1153, simple_loss=0.1868, pruned_loss=0.02191, over 4774.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03053, over 972772.64 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:22:15,342 INFO [train.py:715] (4/8) Epoch 14, batch 20100, loss[loss=0.1562, simple_loss=0.2312, pruned_loss=0.04061, over 4759.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03054, over 972934.58 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 03:22:55,783 INFO [train.py:715] (4/8) Epoch 14, batch 20150, loss[loss=0.1226, simple_loss=0.1934, pruned_loss=0.02586, over 4802.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2103, pruned_loss=0.03101, over 973188.75 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 03:23:35,883 INFO [train.py:715] (4/8) Epoch 14, batch 20200, loss[loss=0.1339, simple_loss=0.2138, pruned_loss=0.02698, over 4852.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03086, over 972986.58 frames.], batch size: 13, lr: 1.56e-04
2022-05-08 03:24:16,355 INFO [train.py:715] (4/8) Epoch 14, batch 20250, loss[loss=0.1237, simple_loss=0.2023, pruned_loss=0.02254, over 4985.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2097, pruned_loss=0.0307, over 973563.63 frames.], batch size: 28, lr: 1.56e-04
2022-05-08 03:24:56,501 INFO [train.py:715] (4/8) Epoch 14, batch 20300, loss[loss=0.1226, simple_loss=0.201, pruned_loss=0.02209, over 4968.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03035, over 972785.34 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 03:25:37,272 INFO [train.py:715] (4/8) Epoch 14, batch 20350, loss[loss=0.1249, simple_loss=0.1907, pruned_loss=0.02961, over 4910.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03021, over 973006.17 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:26:17,609 INFO [train.py:715] (4/8) Epoch 14, batch 20400, loss[loss=0.1147, simple_loss=0.1864, pruned_loss=0.02152, over 4919.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03052, over 972473.14 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 03:26:58,057 INFO [train.py:715] (4/8) Epoch 14, batch 20450, loss[loss=0.1403, simple_loss=0.2073, pruned_loss=0.03672, over 4652.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03098, over 971623.97 frames.], batch size: 13, lr: 1.56e-04
2022-05-08 03:27:39,214 INFO [train.py:715] (4/8) Epoch 14, batch 20500, loss[loss=0.1313, simple_loss=0.2013, pruned_loss=0.0306, over 4922.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.0309, over 971619.59 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:28:19,567 INFO [train.py:715] (4/8) Epoch 14, batch 20550, loss[loss=0.1406, simple_loss=0.2069, pruned_loss=0.03714, over 4858.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.03141, over 971692.57 frames.], batch size: 30, lr: 1.56e-04
2022-05-08 03:29:00,471 INFO [train.py:715] (4/8) Epoch 14, batch 20600, loss[loss=0.1379, simple_loss=0.2073, pruned_loss=0.03419, over 4954.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2098, pruned_loss=0.03186, over 971454.28 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 03:29:41,265 INFO [train.py:715] (4/8) Epoch 14, batch 20650, loss[loss=0.1335, simple_loss=0.2129, pruned_loss=0.02711, over 4983.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2099, pruned_loss=0.03177, over 971369.63 frames.], batch size: 25, lr: 1.56e-04
2022-05-08 03:30:22,919 INFO [train.py:715] (4/8) Epoch 14, batch 20700, loss[loss=0.1437, simple_loss=0.223, pruned_loss=0.03224, over 4778.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.03146, over 971678.75 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:31:03,257 INFO [train.py:715] (4/8) Epoch 14, batch 20750, loss[loss=0.1234, simple_loss=0.1922, pruned_loss=0.02734, over 4865.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03154, over 971173.62 frames.], batch size: 32, lr: 1.56e-04
2022-05-08 03:31:43,456 INFO [train.py:715] (4/8) Epoch 14, batch 20800, loss[loss=0.1221, simple_loss=0.194, pruned_loss=0.02512, over 4903.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2091, pruned_loss=0.03124, over 972316.76 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 03:32:24,154 INFO [train.py:715] (4/8) Epoch 14, batch 20850, loss[loss=0.1422, simple_loss=0.2206, pruned_loss=0.03189, over 4705.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2089, pruned_loss=0.03105, over 971997.32 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:33:04,691 INFO [train.py:715] (4/8) Epoch 14, batch 20900, loss[loss=0.1332, simple_loss=0.2123, pruned_loss=0.02702, over 4931.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2089, pruned_loss=0.0312, over 971969.77 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:33:45,367 INFO [train.py:715] (4/8) Epoch 14, batch 20950, loss[loss=0.1299, simple_loss=0.1942, pruned_loss=0.03279, over 4745.00 frames.], tot_loss[loss=0.1366, simple_loss=0.21, pruned_loss=0.0316, over 972664.54 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 03:34:25,915 INFO [train.py:715] (4/8) Epoch 14, batch 21000, loss[loss=0.145, simple_loss=0.2213, pruned_loss=0.03433, over 4768.00 frames.], tot_loss[loss=0.136, simple_loss=0.2096, pruned_loss=0.0312, over 971556.12 frames.], batch size: 12, lr: 1.56e-04
2022-05-08 03:34:25,916 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 03:34:36,999 INFO [train.py:742] (4/8) Epoch 14, validation: loss=0.1051, simple_loss=0.1889, pruned_loss=0.0107, over 914524.00 frames.
2022-05-08 03:35:17,899 INFO [train.py:715] (4/8) Epoch 14, batch 21050, loss[loss=0.1598, simple_loss=0.247, pruned_loss=0.0363, over 4813.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2098, pruned_loss=0.03114, over 971862.17 frames.], batch size: 25, lr: 1.56e-04
2022-05-08 03:35:58,607 INFO [train.py:715] (4/8) Epoch 14, batch 21100, loss[loss=0.1293, simple_loss=0.198, pruned_loss=0.03025, over 4839.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03065, over 972075.76 frames.], batch size: 13, lr: 1.56e-04
2022-05-08 03:36:39,417 INFO [train.py:715] (4/8) Epoch 14, batch 21150, loss[loss=0.1113, simple_loss=0.1812, pruned_loss=0.02069, over 4769.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03044, over 972640.43 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 03:37:18,915 INFO [train.py:715] (4/8) Epoch 14, batch 21200, loss[loss=0.1434, simple_loss=0.215, pruned_loss=0.03593, over 4732.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03056, over 972667.92 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 03:37:59,328 INFO [train.py:715] (4/8) Epoch 14, batch 21250, loss[loss=0.1636, simple_loss=0.2308, pruned_loss=0.04817, over 4812.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2089, pruned_loss=0.03109, over 972759.91 frames.], batch size: 27, lr: 1.56e-04
2022-05-08 03:38:39,034 INFO [train.py:715] (4/8) Epoch 14, batch 21300, loss[loss=0.1384, simple_loss=0.2089, pruned_loss=0.03393, over 4961.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.0315, over 973291.50 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:39:17,956 INFO [train.py:715] (4/8) Epoch 14, batch 21350, loss[loss=0.1362, simple_loss=0.2069, pruned_loss=0.0328, over 4806.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2096, pruned_loss=0.03147, over 972169.92 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 03:39:58,399 INFO [train.py:715] (4/8) Epoch 14, batch 21400, loss[loss=0.1639, simple_loss=0.2202, pruned_loss=0.0538, over 4949.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2094, pruned_loss=0.03148, over 972607.41 frames.], batch size: 35, lr: 1.56e-04
2022-05-08 03:40:38,646 INFO [train.py:715] (4/8) Epoch 14, batch 21450, loss[loss=0.1193, simple_loss=0.1941, pruned_loss=0.02224, over 4886.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2088, pruned_loss=0.03123, over 973013.67 frames.], batch size: 22, lr: 1.56e-04
2022-05-08 03:41:18,060 INFO [train.py:715] (4/8) Epoch 14, batch 21500, loss[loss=0.2032, simple_loss=0.2573, pruned_loss=0.07452, over 4970.00 frames.], tot_loss[loss=0.1359, simple_loss=0.209, pruned_loss=0.03142, over 973241.14 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:41:57,081 INFO [train.py:715] (4/8) Epoch 14, batch 21550, loss[loss=0.1467, simple_loss=0.2299, pruned_loss=0.03172, over 4789.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2088, pruned_loss=0.03116, over 972089.66 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 03:42:37,071 INFO [train.py:715] (4/8) Epoch 14, batch 21600, loss[loss=0.144, simple_loss=0.2159, pruned_loss=0.03601, over 4710.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2088, pruned_loss=0.0312, over 972659.76 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:43:16,850 INFO [train.py:715] (4/8) Epoch 14, batch 21650, loss[loss=0.1107, simple_loss=0.1866, pruned_loss=0.01741, over 4761.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2087, pruned_loss=0.03105, over 971910.38 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 03:43:55,950 INFO [train.py:715] (4/8) Epoch 14, batch 21700, loss[loss=0.1127, simple_loss=0.1827, pruned_loss=0.02131, over 4914.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2089, pruned_loss=0.03114, over 971980.79 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 03:44:36,361 INFO [train.py:715] (4/8) Epoch 14, batch 21750, loss[loss=0.1574, simple_loss=0.2302, pruned_loss=0.04231, over 4795.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03101, over 972465.31 frames.], batch size: 24, lr: 1.56e-04
2022-05-08 03:45:16,754 INFO [train.py:715] (4/8) Epoch 14, batch 21800, loss[loss=0.1478, simple_loss=0.222, pruned_loss=0.03681, over 4916.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03121, over 973330.90 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 03:45:56,148 INFO [train.py:715] (4/8) Epoch 14, batch 21850, loss[loss=0.1352, simple_loss=0.2158, pruned_loss=0.02727, over 4840.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2084, pruned_loss=0.03106, over 972669.36 frames.], batch size: 20, lr: 1.56e-04
2022-05-08 03:46:35,753 INFO [train.py:715] (4/8) Epoch 14, batch 21900, loss[loss=0.165, simple_loss=0.231, pruned_loss=0.04955, over 4830.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2079, pruned_loss=0.03067, over 971956.93 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 03:47:16,028 INFO [train.py:715] (4/8) Epoch 14, batch 21950, loss[loss=0.1028, simple_loss=0.1743, pruned_loss=0.01572, over 4909.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2077, pruned_loss=0.03036, over 971858.96 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 03:47:55,287 INFO [train.py:715] (4/8) Epoch 14, batch 22000, loss[loss=0.1349, simple_loss=0.2112, pruned_loss=0.02933, over 4985.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.03001, over 973224.17 frames.], batch size: 31, lr: 1.56e-04
2022-05-08 03:48:34,006 INFO [train.py:715] (4/8) Epoch 14, batch 22050, loss[loss=0.1681, simple_loss=0.2332, pruned_loss=0.05151, over 4793.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.03019, over 973310.82 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 03:49:14,109 INFO [train.py:715] (4/8) Epoch 14, batch 22100, loss[loss=0.1202, simple_loss=0.1946, pruned_loss=0.02288, over 4949.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03055, over 974049.33 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 03:49:53,818 INFO [train.py:715] (4/8) Epoch 14, batch 22150, loss[loss=0.1277, simple_loss=0.1999, pruned_loss=0.02776, over 4768.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03054, over 973422.61 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 03:50:32,844 INFO [train.py:715] (4/8) Epoch 14, batch 22200, loss[loss=0.1215, simple_loss=0.2068, pruned_loss=0.01807, over 4866.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03081, over 973247.31 frames.], batch size: 20, lr: 1.56e-04
2022-05-08 03:51:12,589 INFO [train.py:715] (4/8) Epoch 14, batch 22250, loss[loss=0.1454, simple_loss=0.2244, pruned_loss=0.03316, over 4940.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03029, over 973277.78 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 03:51:52,765 INFO [train.py:715] (4/8) Epoch 14, batch 22300, loss[loss=0.105, simple_loss=0.1808, pruned_loss=0.01454, over 4896.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03024, over 974180.53 frames.], batch size: 22, lr: 1.56e-04
2022-05-08 03:52:32,252 INFO [train.py:715] (4/8) Epoch 14, batch 22350, loss[loss=0.132, simple_loss=0.2078, pruned_loss=0.02812, over 4779.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03043, over 973813.35 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 03:53:11,403 INFO [train.py:715] (4/8) Epoch 14, batch 22400, loss[loss=0.1681, simple_loss=0.2401, pruned_loss=0.04808, over 4871.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.0311, over 974318.63 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 03:53:51,750 INFO [train.py:715] (4/8) Epoch 14, batch 22450, loss[loss=0.1496, simple_loss=0.2229, pruned_loss=0.03818, over 4847.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2097, pruned_loss=0.03151, over 973280.21 frames.], batch size: 32, lr: 1.56e-04
2022-05-08 03:54:31,160 INFO [train.py:715] (4/8) Epoch 14, batch 22500, loss[loss=0.1729, simple_loss=0.245, pruned_loss=0.05039, over 4982.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2089, pruned_loss=0.03117, over 973928.09 frames.], batch size: 33, lr: 1.56e-04
2022-05-08 03:55:10,457 INFO [train.py:715] (4/8) Epoch 14, batch 22550, loss[loss=0.1212, simple_loss=0.2039, pruned_loss=0.01931, over 4878.00 frames.], tot_loss[loss=0.1347, simple_loss=0.208, pruned_loss=0.03071, over 973915.65 frames.], batch size: 38, lr: 1.56e-04
2022-05-08 03:55:50,814 INFO [train.py:715] (4/8) Epoch 14, batch 22600, loss[loss=0.1426, simple_loss=0.2161, pruned_loss=0.0346, over 4776.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2083, pruned_loss=0.03112, over 974206.21 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 03:56:31,697 INFO [train.py:715] (4/8) Epoch 14, batch 22650, loss[loss=0.1646, simple_loss=0.2318, pruned_loss=0.04873, over 4850.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2081, pruned_loss=0.03067, over 974469.39 frames.], batch size: 20, lr: 1.56e-04
2022-05-08 03:57:11,534 INFO [train.py:715] (4/8) Epoch 14, batch 22700, loss[loss=0.1533, simple_loss=0.2213, pruned_loss=0.04271, over 4869.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.0314, over 973964.54 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 03:57:50,681 INFO [train.py:715] (4/8) Epoch 14, batch 22750, loss[loss=0.1369, simple_loss=0.2065, pruned_loss=0.03362, over 4827.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03097, over 974016.43 frames.], batch size: 26, lr: 1.56e-04
2022-05-08 03:58:32,020 INFO [train.py:715] (4/8) Epoch 14, batch 22800, loss[loss=0.1412, simple_loss=0.211, pruned_loss=0.03572, over 4992.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03064, over 973933.59 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 03:59:12,933 INFO [train.py:715] (4/8) Epoch 14, batch 22850, loss[loss=0.09852, simple_loss=0.1722, pruned_loss=0.0124, over 4754.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03097, over 973765.50 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 03:59:53,208 INFO [train.py:715] (4/8) Epoch 14, batch 22900, loss[loss=0.1611, simple_loss=0.2446, pruned_loss=0.03879, over 4809.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03102, over 973004.00 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 04:00:33,082 INFO [train.py:715] (4/8) Epoch 14, batch 22950, loss[loss=0.1269, simple_loss=0.2034, pruned_loss=0.02524, over 4890.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03088, over 973533.63 frames.], batch size: 22, lr: 1.56e-04
2022-05-08 04:01:13,588 INFO [train.py:715] (4/8) Epoch 14, batch 23000, loss[loss=0.1574, simple_loss=0.244, pruned_loss=0.03544, over 4775.00 frames.], tot_loss[loss=0.1358, simple_loss=0.21, pruned_loss=0.03077, over 972597.48 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 04:01:53,102 INFO [train.py:715] (4/8) Epoch 14, batch 23050, loss[loss=0.1491, simple_loss=0.2315, pruned_loss=0.03332, over 4940.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2105, pruned_loss=0.03101, over 972226.34 frames.], batch size: 29, lr: 1.56e-04
2022-05-08 04:02:32,415 INFO [train.py:715] (4/8) Epoch 14, batch 23100, loss[loss=0.136, simple_loss=0.2117, pruned_loss=0.03014, over 4925.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2097, pruned_loss=0.03071, over 971864.24 frames.], batch size: 23, lr: 1.56e-04
2022-05-08 04:03:13,066 INFO [train.py:715] (4/8) Epoch 14, batch 23150, loss[loss=0.1023, simple_loss=0.1763, pruned_loss=0.01413, over 4910.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03053, over 971864.94 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 04:03:54,322 INFO [train.py:715] (4/8) Epoch 14, batch 23200, loss[loss=0.1397, simple_loss=0.2147, pruned_loss=0.03239, over 4694.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03078, over 972381.89 frames.], batch size: 15, lr: 1.56e-04
2022-05-08 04:04:33,067 INFO [train.py:715] (4/8) Epoch 14, batch 23250, loss[loss=0.147, simple_loss=0.2227, pruned_loss=0.03559, over 4859.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.0305, over 972378.50 frames.], batch size: 38, lr: 1.56e-04
2022-05-08 04:05:13,473 INFO [train.py:715] (4/8) Epoch 14, batch 23300, loss[loss=0.1266, simple_loss=0.2001, pruned_loss=0.02654, over 4910.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03078, over 971917.18 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 04:05:54,160 INFO [train.py:715] (4/8) Epoch 14, batch 23350, loss[loss=0.1442, simple_loss=0.2218, pruned_loss=0.03329, over 4929.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03121, over 971708.73 frames.], batch size: 18, lr: 1.56e-04
2022-05-08 04:06:33,755 INFO [train.py:715] (4/8) Epoch 14, batch 23400, loss[loss=0.1522, simple_loss=0.2267, pruned_loss=0.03888, over 4873.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03094, over 971849.43 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 04:07:12,806 INFO [train.py:715] (4/8) Epoch 14, batch 23450, loss[loss=0.1384, simple_loss=0.2168, pruned_loss=0.02998, over 4935.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03041, over 971797.91 frames.], batch size: 23, lr: 1.56e-04
2022-05-08 04:07:53,416 INFO [train.py:715] (4/8) Epoch 14, batch 23500, loss[loss=0.1052, simple_loss=0.1812, pruned_loss=0.01459, over 4785.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03009, over 971874.79 frames.], batch size: 14, lr: 1.56e-04
2022-05-08 04:08:34,059 INFO [train.py:715] (4/8) Epoch 14, batch 23550, loss[loss=0.1262, simple_loss=0.2051, pruned_loss=0.02358, over 4758.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.0298, over 971356.95 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 04:09:13,316 INFO [train.py:715] (4/8) Epoch 14, batch 23600, loss[loss=0.1624, simple_loss=0.2395, pruned_loss=0.04267, over 4754.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03005, over 970873.57 frames.], batch size: 19, lr: 1.56e-04
2022-05-08 04:09:52,600 INFO [train.py:715] (4/8) Epoch 14, batch 23650, loss[loss=0.1179, simple_loss=0.1952, pruned_loss=0.02034, over 4961.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.0303, over 971588.22 frames.], batch size: 21, lr: 1.56e-04
2022-05-08 04:10:32,138 INFO [train.py:715] (4/8) Epoch 14, batch 23700, loss[loss=0.125, simple_loss=0.205, pruned_loss=0.02248, over 4742.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03034, over 972368.82 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 04:11:11,200 INFO [train.py:715] (4/8) Epoch 14, batch 23750, loss[loss=0.1537, simple_loss=0.2317, pruned_loss=0.03782, over 4782.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03039, over 972302.91 frames.], batch size: 17, lr: 1.56e-04
2022-05-08 04:11:50,483 INFO [train.py:715] (4/8) Epoch 14, batch 23800, loss[loss=0.1281, simple_loss=0.2003, pruned_loss=0.02793, over 4637.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03013, over 972728.30 frames.], batch size: 13, lr: 1.56e-04
2022-05-08 04:12:30,657 INFO [train.py:715] (4/8) Epoch 14, batch 23850, loss[loss=0.1442, simple_loss=0.2155, pruned_loss=0.03649, over 4890.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03019, over 973018.86 frames.], batch size: 22, lr: 1.56e-04
2022-05-08 04:13:10,489 INFO [train.py:715] (4/8) Epoch 14, batch 23900, loss[loss=0.1111, simple_loss=0.1843, pruned_loss=0.01892, over 4748.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2098, pruned_loss=0.03027, over 973062.96 frames.], batch size: 16, lr: 1.56e-04
2022-05-08 04:13:49,738 INFO [train.py:715] (4/8) Epoch 14, batch 23950, loss[loss=0.1551, simple_loss=0.2396, pruned_loss=0.03527, over 4696.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2098, pruned_loss=0.03018, over 972806.68 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 04:14:30,061 INFO [train.py:715] (4/8) Epoch 14, batch 24000, loss[loss=0.12, simple_loss=0.1944, pruned_loss=0.02278, over 4782.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2097, pruned_loss=0.03023, over 972774.68 frames.], batch size: 17, lr: 1.55e-04
2022-05-08 04:14:30,061 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 04:14:41,437 INFO [train.py:742] (4/8) Epoch 14, validation: loss=0.1052, simple_loss=0.1889, pruned_loss=0.01074, over 914524.00 frames.
2022-05-08 04:15:21,386 INFO [train.py:715] (4/8) Epoch 14, batch 24050, loss[loss=0.1456, simple_loss=0.2211, pruned_loss=0.03502, over 4967.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2095, pruned_loss=0.0304, over 973743.21 frames.], batch size: 24, lr: 1.55e-04
2022-05-08 04:16:02,437 INFO [train.py:715] (4/8) Epoch 14, batch 24100, loss[loss=0.1136, simple_loss=0.182, pruned_loss=0.02261, over 4921.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03087, over 972951.30 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 04:16:41,513 INFO [train.py:715] (4/8) Epoch 14, batch 24150, loss[loss=0.1316, simple_loss=0.2019, pruned_loss=0.03064, over 4865.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03078, over 972645.71 frames.], batch size: 22, lr: 1.55e-04
2022-05-08 04:17:21,102 INFO [train.py:715] (4/8) Epoch 14, batch 24200, loss[loss=0.1349, simple_loss=0.205, pruned_loss=0.03238, over 4983.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03014, over 972425.93 frames.], batch size: 33, lr: 1.55e-04
2022-05-08 04:18:01,395 INFO [train.py:715] (4/8) Epoch 14, batch 24250, loss[loss=0.1108, simple_loss=0.1842, pruned_loss=0.01869, over 4966.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03037, over 973402.03 frames.], batch size: 24, lr: 1.55e-04
2022-05-08 04:18:41,665 INFO [train.py:715] (4/8) Epoch 14, batch 24300, loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03075, over 4871.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03056, over 973264.92 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 04:19:20,605 INFO [train.py:715] (4/8) Epoch 14, batch 24350, loss[loss=0.1284, simple_loss=0.2019, pruned_loss=0.02742, over 4757.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2085, pruned_loss=0.03064, over 972929.22 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 04:20:01,378 INFO [train.py:715] (4/8) Epoch 14, batch 24400, loss[loss=0.1288, simple_loss=0.2046, pruned_loss=0.02645, over 4926.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03034, over 973236.26 frames.], batch size: 29, lr: 1.55e-04
2022-05-08 04:20:43,002 INFO [train.py:715] (4/8) Epoch 14, batch 24450, loss[loss=0.1266, simple_loss=0.2098, pruned_loss=0.02166, over 4984.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03017, over 973435.70 frames.], batch size: 28, lr: 1.55e-04
2022-05-08 04:21:22,334 INFO [train.py:715] (4/8) Epoch 14, batch 24500, loss[loss=0.143, simple_loss=0.2054, pruned_loss=0.0403, over 4940.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03012, over 972913.30 frames.], batch size: 21, lr: 1.55e-04
2022-05-08 04:22:02,596 INFO [train.py:715] (4/8) Epoch 14, batch 24550, loss[loss=0.1272, simple_loss=0.1906, pruned_loss=0.03189, over 4954.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03015, over 973498.50 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 04:22:43,752 INFO [train.py:715] (4/8) Epoch 14, batch 24600, loss[loss=0.1139, simple_loss=0.1915, pruned_loss=0.01816, over 4790.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02984, over 972650.84 frames.], batch size: 12, lr: 1.55e-04
2022-05-08 04:23:25,374 INFO [train.py:715] (4/8) Epoch 14, batch 24650, loss[loss=0.1623, simple_loss=0.2257, pruned_loss=0.04947, over 4860.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03019, over 973082.78 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 04:24:07,554 INFO [train.py:715] (4/8) Epoch 14, batch 24700, loss[loss=0.1313, simple_loss=0.1984, pruned_loss=0.03206, over 4960.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03018, over 971769.16 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 04:24:48,435 INFO [train.py:715] (4/8) Epoch 14, batch 24750, loss[loss=0.1198, simple_loss=0.1924, pruned_loss=0.02358, over 4685.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02986, over 971976.16 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 04:25:30,052 INFO [train.py:715] (4/8) Epoch 14, batch 24800, loss[loss=0.1331, simple_loss=0.1977, pruned_loss=0.03427, over 4784.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02975, over 972470.01 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 04:26:10,630 INFO [train.py:715] (4/8) Epoch 14, batch 24850, loss[loss=0.157, simple_loss=0.2136, pruned_loss=0.05024, over 4910.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02997, over 971941.56 frames.], batch size: 17, lr: 1.55e-04
2022-05-08 04:26:50,216 INFO [train.py:715] (4/8) Epoch 14, batch 24900, loss[loss=0.1227, simple_loss=0.1997, pruned_loss=0.02283, over 4820.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03009, over 971555.22 frames.], batch size: 27, lr: 1.55e-04
2022-05-08 04:27:31,156 INFO [train.py:715] (4/8) Epoch 14, batch 24950, loss[loss=0.1612, simple_loss=0.2488, pruned_loss=0.03682, over 4975.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03011, over 971814.83 frames.], batch size: 39, lr: 1.55e-04
2022-05-08 04:28:12,051 INFO [train.py:715] (4/8) Epoch 14, batch 25000, loss[loss=0.1352, simple_loss=0.1975, pruned_loss=0.03642, over 4931.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02966, over 972538.17 frames.], batch size: 39, lr: 1.55e-04
2022-05-08 04:28:51,314 INFO [train.py:715] (4/8) Epoch 14, batch 25050, loss[loss=0.1406, simple_loss=0.2076, pruned_loss=0.03677, over 4782.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02975, over 972755.75 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 04:29:32,178 INFO [train.py:715] (4/8) Epoch 14, batch 25100, loss[loss=0.166, simple_loss=0.2356, pruned_loss=0.04821, over 4916.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02962, over 973187.77 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 04:30:13,134 INFO [train.py:715] (4/8) Epoch 14, batch 25150, loss[loss=0.1419, simple_loss=0.2198, pruned_loss=0.03202, over 4929.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02934, over 973064.51 frames.], batch size: 29, lr: 1.55e-04
2022-05-08 04:30:53,334 INFO [train.py:715] (4/8) Epoch 14, batch 25200, loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02805, over 4789.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.02999, over 972991.31 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 04:31:31,960 INFO [train.py:715] (4/8) Epoch 14, batch 25250, loss[loss=0.1466, simple_loss=0.2237, pruned_loss=0.03479, over 4918.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02983, over 973117.12 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 04:32:12,606 INFO [train.py:715] (4/8) Epoch 14, batch 25300, loss[loss=0.1326, simple_loss=0.1958, pruned_loss=0.03468, over 4948.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02964, over 972903.72 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 04:32:53,032 INFO [train.py:715] (4/8) Epoch 14, batch 25350, loss[loss=0.1469, simple_loss=0.2218, pruned_loss=0.03602, over 4976.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02989, over 972051.28 frames.], batch size: 28, lr: 1.55e-04
2022-05-08 04:33:31,586 INFO [train.py:715] (4/8) Epoch 14, batch 25400, loss[loss=0.1697, simple_loss=0.2346, pruned_loss=0.05242, over 4942.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03029, over 972586.18 frames.], batch size: 39, lr: 1.55e-04
2022-05-08 04:34:11,982 INFO [train.py:715] (4/8) Epoch 14, batch 25450, loss[loss=0.1288, simple_loss=0.2047, pruned_loss=0.02643, over 4902.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03029, over 973049.41 frames.], batch size: 22, lr: 1.55e-04
2022-05-08 04:34:52,378 INFO [train.py:715] (4/8) Epoch 14, batch 25500, loss[loss=0.1568, simple_loss=0.2379, pruned_loss=0.03787, over 4807.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03047, over 972802.61 frames.], batch size: 21, lr: 1.55e-04
2022-05-08 04:35:31,818 INFO [train.py:715] (4/8) Epoch 14, batch 25550, loss[loss=0.1304, simple_loss=0.2015, pruned_loss=0.02963, over 4957.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03074, over 972596.19 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 04:36:10,561 INFO [train.py:715] (4/8) Epoch 14, batch 25600, loss[loss=0.1291, simple_loss=0.1959, pruned_loss=0.03111, over 4753.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.0307, over 973488.54 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 04:36:50,636 INFO [train.py:715] (4/8) Epoch 14, batch 25650, loss[loss=0.1585, simple_loss=0.232, pruned_loss=0.04252, over 4847.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03055, over 973402.33 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 04:37:30,746 INFO [train.py:715] (4/8) Epoch 14, batch 25700, loss[loss=0.1489, simple_loss=0.2196, pruned_loss=0.03911, over 4880.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03071, over 973427.17 frames.], batch size: 22, lr: 1.55e-04
2022-05-08 04:38:09,213 INFO [train.py:715] (4/8) Epoch 14, batch 25750, loss[loss=0.1388, simple_loss=0.219, pruned_loss=0.0293, over 4829.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03037, over 973098.73 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 04:38:48,530 INFO [train.py:715] (4/8) Epoch 14, batch 25800, loss[loss=0.129, simple_loss=0.193, pruned_loss=0.0325, over 4653.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03028, over 972332.78 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 04:39:28,743 INFO [train.py:715] (4/8) Epoch 14, batch 25850, loss[loss=0.1466, simple_loss=0.2279, pruned_loss=0.03261, over 4683.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03064, over 971932.86 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 04:40:07,961 INFO [train.py:715] (4/8) Epoch 14, batch 25900, loss[loss=0.1226, simple_loss=0.1911, pruned_loss=0.02707, over 4913.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02982, over 972428.96 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 04:40:46,740 INFO [train.py:715] (4/8) Epoch 14, batch 25950, loss[loss=0.1222, simple_loss=0.1984, pruned_loss=0.02304, over 4769.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03023, over 971703.94 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 04:41:26,883 INFO [train.py:715] (4/8) Epoch 14, batch 26000, loss[loss=0.1469, simple_loss=0.2231, pruned_loss=0.03539, over 4768.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2092, pruned_loss=0.03018, over 971584.94 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 04:42:06,869 INFO [train.py:715] (4/8) Epoch 14, batch 26050, loss[loss=0.1451, simple_loss=0.2048, pruned_loss=0.04269, over 4985.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2101, pruned_loss=0.03073, over 971969.70 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 04:42:44,778 INFO [train.py:715] (4/8) Epoch 14, batch 26100, loss[loss=0.1625, simple_loss=0.2159, pruned_loss=0.0545, over 4929.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03054, over 971267.97 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 04:43:24,714 INFO [train.py:715] (4/8) Epoch 14, batch 26150, loss[loss=0.1079, simple_loss=0.1941, pruned_loss=0.0109, over 4812.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03014, over 972005.34 frames.], batch size: 27, lr: 1.55e-04
2022-05-08 04:44:05,198 INFO [train.py:715] (4/8) Epoch 14, batch 26200, loss[loss=0.1442, simple_loss=0.2074, pruned_loss=0.04052, over 4945.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02977, over 972119.91 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 04:44:44,004 INFO [train.py:715] (4/8) Epoch 14, batch 26250, loss[loss=0.09856, simple_loss=0.1718, pruned_loss=0.01267, over 4800.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.02995, over 971359.38 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 04:45:23,184 INFO [train.py:715] (4/8) Epoch 14, batch 26300, loss[loss=0.1409, simple_loss=0.2179, pruned_loss=0.03193, over 4840.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2065, pruned_loss=0.02959, over 971255.22 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 04:46:03,660 INFO [train.py:715] (4/8) Epoch 14, batch 26350, loss[loss=0.1129, simple_loss=0.1798, pruned_loss=0.02303, over 4746.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02969, over 971395.62 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 04:46:43,191 INFO [train.py:715] (4/8) Epoch 14, batch 26400, loss[loss=0.1325, simple_loss=0.2143, pruned_loss=0.02534, over 4816.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03017, over 972531.01 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 04:47:21,824 INFO [train.py:715] (4/8) Epoch 14, batch 26450, loss[loss=0.1319, simple_loss=0.2132, pruned_loss=0.02536, over 4915.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03007, over 972536.27 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 04:48:02,184 INFO [train.py:715] (4/8) Epoch 14, batch 26500, loss[loss=0.116, simple_loss=0.1937, pruned_loss=0.01917, over 4978.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2095, pruned_loss=0.03037, over 972697.40 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 04:48:42,599 INFO [train.py:715] (4/8) Epoch 14, batch 26550, loss[loss=0.1223, simple_loss=0.2044, pruned_loss=0.0201, over 4897.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.03001, over 972792.22 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 04:49:21,894 INFO [train.py:715] (4/8) Epoch 14, batch 26600, loss[loss=0.1304, simple_loss=0.211, pruned_loss=0.02494, over 4790.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.03019, over 972587.63 frames.], batch size: 24, lr: 1.55e-04
2022-05-08 04:50:00,871 INFO [train.py:715] (4/8) Epoch 14, batch 26650, loss[loss=0.1492, simple_loss=0.2264, pruned_loss=0.03596, over 4745.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2087, pruned_loss=0.02992, over 972791.02 frames.], batch size: 12, lr: 1.55e-04
2022-05-08 04:50:41,181 INFO [train.py:715] (4/8) Epoch 14, batch 26700, loss[loss=0.1507, simple_loss=0.2229, pruned_loss=0.03931, over 4958.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.0298, over 972891.04 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 04:51:21,697 INFO [train.py:715] (4/8) Epoch 14, batch 26750, loss[loss=0.156, simple_loss=0.2288, pruned_loss=0.04163, over 4892.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.0296, over 972432.44 frames.], batch size: 17, lr: 1.55e-04
2022-05-08 04:52:00,709 INFO [train.py:715] (4/8) Epoch 14, batch 26800, loss[loss=0.1336, simple_loss=0.2088, pruned_loss=0.02919, over 4814.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02956, over 972301.65 frames.], batch size: 21, lr: 1.55e-04
2022-05-08 04:52:40,497 INFO [train.py:715] (4/8) Epoch 14, batch 26850, loss[loss=0.1461, simple_loss=0.2247, pruned_loss=0.03374, over 4967.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02975, over 972424.12 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 04:53:20,931 INFO [train.py:715] (4/8) Epoch 14, batch 26900, loss[loss=0.1261, simple_loss=0.1958, pruned_loss=0.02822, over 4983.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02991, over 973027.25 frames.], batch size: 28, lr: 1.55e-04
2022-05-08 04:54:00,776 INFO [train.py:715] (4/8) Epoch 14, batch 26950, loss[loss=0.1446, simple_loss=0.2111, pruned_loss=0.03909, over 4911.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03013, over 972237.93 frames.], batch size: 39, lr: 1.55e-04
2022-05-08 04:54:39,982 INFO [train.py:715] (4/8) Epoch 14, batch 27000, loss[loss=0.1193, simple_loss=0.198, pruned_loss=0.02032, over 4886.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02985, over 972711.71 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 04:54:39,983 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 04:54:49,613 INFO [train.py:742] (4/8) Epoch 14, validation: loss=0.1049, simple_loss=0.1886, pruned_loss=0.01053, over 914524.00 frames.
2022-05-08 04:55:29,148 INFO [train.py:715] (4/8) Epoch 14, batch 27050, loss[loss=0.1233, simple_loss=0.1927, pruned_loss=0.02693, over 4942.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02998, over 973357.50 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 04:56:09,800 INFO [train.py:715] (4/8) Epoch 14, batch 27100, loss[loss=0.1714, simple_loss=0.2413, pruned_loss=0.05073, over 4749.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2094, pruned_loss=0.03041, over 973120.35 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 04:56:50,326 INFO [train.py:715] (4/8) Epoch 14, batch 27150, loss[loss=0.1261, simple_loss=0.2101, pruned_loss=0.02104, over 4829.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2094, pruned_loss=0.03022, over 972762.85 frames.], batch size: 20, lr: 1.55e-04
2022-05-08 04:57:29,047 INFO [train.py:715] (4/8) Epoch 14, batch 27200, loss[loss=0.1277, simple_loss=0.2018, pruned_loss=0.02684, over 4783.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2089, pruned_loss=0.03007, over 972025.02 frames.], batch size: 17, lr: 1.55e-04
2022-05-08 04:58:08,435 INFO [train.py:715] (4/8) Epoch 14, batch 27250, loss[loss=0.1392, simple_loss=0.2177, pruned_loss=0.03031, over 4933.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2087, pruned_loss=0.02977, over 972580.89 frames.], batch size: 23, lr: 1.55e-04
2022-05-08 04:58:48,575 INFO [train.py:715] (4/8) Epoch 14, batch 27300, loss[loss=0.1329, simple_loss=0.2083, pruned_loss=0.02874, over 4823.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03006, over 971774.23 frames.], batch size: 26, lr: 1.55e-04
2022-05-08 04:59:28,192 INFO [train.py:715] (4/8) Epoch 14, batch 27350, loss[loss=0.1197, simple_loss=0.1907, pruned_loss=0.02439, over 4988.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03021, over 972132.94 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 05:00:06,588 INFO [train.py:715] (4/8) Epoch 14, batch 27400, loss[loss=0.1279, simple_loss=0.195, pruned_loss=0.03038, over 4982.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03053, over 971804.22 frames.], batch size: 31, lr: 1.55e-04
2022-05-08 05:00:46,866 INFO [train.py:715] (4/8) Epoch 14, batch 27450, loss[loss=0.1574, simple_loss=0.2175, pruned_loss=0.04866, over 4636.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03047, over 971257.94 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 05:01:26,695 INFO [train.py:715] (4/8) Epoch 14, batch 27500, loss[loss=0.1509, simple_loss=0.2227, pruned_loss=0.03956, over 4829.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.03039, over 971687.79 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 05:02:05,455 INFO [train.py:715] (4/8) Epoch 14, batch 27550, loss[loss=0.1409, simple_loss=0.2058, pruned_loss=0.03797, over 4866.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03051, over 971020.35 frames.], batch size: 12, lr: 1.55e-04
2022-05-08 05:02:45,160 INFO [train.py:715] (4/8) Epoch 14, batch 27600, loss[loss=0.1338, simple_loss=0.2132, pruned_loss=0.02718, over 4870.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.0303, over 971408.46 frames.], batch size: 22, lr: 1.55e-04
2022-05-08 05:03:25,490 INFO [train.py:715] (4/8) Epoch 14, batch 27650, loss[loss=0.1351, simple_loss=0.2059, pruned_loss=0.03215, over 4816.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03041, over 971858.98 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 05:04:04,754 INFO [train.py:715] (4/8) Epoch 14, batch 27700, loss[loss=0.1161, simple_loss=0.1853, pruned_loss=0.02341, over 4695.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03106, over 972090.34 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:04:43,281 INFO [train.py:715] (4/8) Epoch 14, batch 27750, loss[loss=0.1094, simple_loss=0.1788, pruned_loss=0.02003, over 4824.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03075, over 971710.04 frames.], batch size: 27, lr: 1.55e-04
2022-05-08 05:05:23,450 INFO [train.py:715] (4/8) Epoch 14, batch 27800, loss[loss=0.1326, simple_loss=0.2137, pruned_loss=0.02573, over 4817.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03103, over 971368.73 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:06:03,187 INFO [train.py:715] (4/8) Epoch 14, batch 27850, loss[loss=0.1253, simple_loss=0.1999, pruned_loss=0.02534, over 4778.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.03131, over 972465.96 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 05:06:41,701 INFO [train.py:715] (4/8) Epoch 14, batch 27900, loss[loss=0.1459, simple_loss=0.2165, pruned_loss=0.03763, over 4773.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2097, pruned_loss=0.03132, over 972010.26 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 05:07:21,719 INFO [train.py:715] (4/8) Epoch 14, batch 27950, loss[loss=0.1156, simple_loss=0.1878, pruned_loss=0.02166, over 4816.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2095, pruned_loss=0.0313, over 972572.08 frames.], batch size: 25, lr: 1.55e-04
2022-05-08 05:08:01,577 INFO [train.py:715] (4/8) Epoch 14, batch 28000, loss[loss=0.1624, simple_loss=0.2265, pruned_loss=0.04913, over 4772.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2105, pruned_loss=0.03138, over 972173.44 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 05:08:40,619 INFO [train.py:715] (4/8) Epoch 14, batch 28050, loss[loss=0.1222, simple_loss=0.1946, pruned_loss=0.02486, over 4896.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2098, pruned_loss=0.03073, over 972106.96 frames.], batch size: 22, lr: 1.55e-04
2022-05-08 05:09:19,677 INFO [train.py:715] (4/8) Epoch 14, batch 28100, loss[loss=0.1315, simple_loss=0.1942, pruned_loss=0.0344, over 4848.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03089, over 971362.47 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 05:10:00,232 INFO [train.py:715] (4/8) Epoch 14, batch 28150, loss[loss=0.1541, simple_loss=0.2411, pruned_loss=0.03352, over 4755.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03117, over 971061.95 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 05:10:39,941 INFO [train.py:715] (4/8) Epoch 14, batch 28200, loss[loss=0.09789, simple_loss=0.1589, pruned_loss=0.01845, over 4795.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.03047, over 970305.74 frames.], batch size: 12, lr: 1.55e-04
2022-05-08 05:11:17,981 INFO [train.py:715] (4/8) Epoch 14, batch 28250, loss[loss=0.1268, simple_loss=0.1938, pruned_loss=0.02987, over 4967.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03077, over 970180.39 frames.], batch size: 24, lr: 1.55e-04
2022-05-08 05:11:58,122 INFO [train.py:715] (4/8) Epoch 14, batch 28300, loss[loss=0.1662, simple_loss=0.2325, pruned_loss=0.04997, over 4829.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03067, over 970947.41 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:12:38,002 INFO [train.py:715] (4/8) Epoch 14, batch 28350, loss[loss=0.1357, simple_loss=0.213, pruned_loss=0.02923, over 4836.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2095, pruned_loss=0.03116, over 971518.91 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:13:16,549 INFO [train.py:715] (4/8) Epoch 14, batch 28400, loss[loss=0.137, simple_loss=0.1937, pruned_loss=0.04012, over 4843.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03094, over 971778.35 frames.], batch size: 32, lr: 1.55e-04
2022-05-08 05:13:56,136 INFO [train.py:715] (4/8) Epoch 14, batch 28450, loss[loss=0.1167, simple_loss=0.1943, pruned_loss=0.01954, over 4977.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.0305, over 971742.07 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 05:14:36,399 INFO [train.py:715] (4/8) Epoch 14, batch 28500, loss[loss=0.1311, simple_loss=0.2103, pruned_loss=0.02595, over 4914.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03041, over 972059.61 frames.], batch size: 23, lr: 1.55e-04
2022-05-08 05:15:15,661 INFO [train.py:715] (4/8) Epoch 14, batch 28550, loss[loss=0.1306, simple_loss=0.2002, pruned_loss=0.0305, over 4985.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03027, over 971886.16 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 05:15:54,180 INFO [train.py:715] (4/8) Epoch 14, batch 28600, loss[loss=0.1155, simple_loss=0.1818, pruned_loss=0.02455, over 4886.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03039, over 972156.49 frames.], batch size: 22, lr: 1.55e-04
2022-05-08 05:16:34,505 INFO [train.py:715] (4/8) Epoch 14, batch 28650, loss[loss=0.1382, simple_loss=0.2069, pruned_loss=0.03471, over 4799.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03049, over 972843.04 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 05:17:14,555 INFO [train.py:715] (4/8) Epoch 14, batch 28700, loss[loss=0.1438, simple_loss=0.2197, pruned_loss=0.03393, over 4937.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02988, over 973463.85 frames.], batch size: 39, lr: 1.55e-04
2022-05-08 05:17:52,650 INFO [train.py:715] (4/8) Epoch 14, batch 28750, loss[loss=0.1387, simple_loss=0.2027, pruned_loss=0.0374, over 4775.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03008, over 972768.90 frames.], batch size: 17, lr: 1.55e-04
2022-05-08 05:18:32,371 INFO [train.py:715] (4/8) Epoch 14, batch 28800, loss[loss=0.1078, simple_loss=0.1791, pruned_loss=0.01828, over 4901.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.03021, over 972558.84 frames.], batch size: 22, lr: 1.55e-04
2022-05-08 05:19:12,480 INFO [train.py:715] (4/8) Epoch 14, batch 28850, loss[loss=0.1374, simple_loss=0.2116, pruned_loss=0.03165, over 4986.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03066, over 972747.17 frames.], batch size: 31, lr: 1.55e-04
2022-05-08 05:19:52,376 INFO [train.py:715] (4/8) Epoch 14, batch 28900, loss[loss=0.1397, simple_loss=0.213, pruned_loss=0.03323, over 4864.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03034, over 972168.40 frames.], batch size: 20, lr: 1.55e-04
2022-05-08 05:20:30,225 INFO [train.py:715] (4/8) Epoch 14, batch 28950, loss[loss=0.1329, simple_loss=0.211, pruned_loss=0.02745, over 4945.00 frames.], tot_loss[loss=0.135, simple_loss=0.2094, pruned_loss=0.03032, over 972023.27 frames.], batch size: 29, lr: 1.55e-04
2022-05-08 05:21:10,702 INFO [train.py:715] (4/8) Epoch 14, batch 29000, loss[loss=0.1384, simple_loss=0.2097, pruned_loss=0.03355, over 4986.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02981, over 972457.26 frames.], batch size: 31, lr: 1.55e-04
2022-05-08 05:21:50,333 INFO [train.py:715] (4/8) Epoch 14, batch 29050, loss[loss=0.1605, simple_loss=0.2277, pruned_loss=0.04665, over 4844.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03004, over 972764.89 frames.], batch size: 34, lr: 1.55e-04
2022-05-08 05:22:29,102 INFO [train.py:715] (4/8) Epoch 14, batch 29100, loss[loss=0.114, simple_loss=0.1866, pruned_loss=0.02072, over 4858.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03022, over 972994.76 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 05:23:08,495 INFO [train.py:715] (4/8) Epoch 14, batch 29150, loss[loss=0.1432, simple_loss=0.2235, pruned_loss=0.03143, over 4972.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03029, over 973096.51 frames.], batch size: 39, lr: 1.55e-04
2022-05-08 05:23:48,532 INFO [train.py:715] (4/8) Epoch 14, batch 29200, loss[loss=0.137, simple_loss=0.2205, pruned_loss=0.0267, over 4946.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.03045, over 972457.72 frames.], batch size: 21, lr: 1.55e-04
2022-05-08 05:24:28,395 INFO [train.py:715] (4/8) Epoch 14, batch 29250, loss[loss=0.1533, simple_loss=0.2344, pruned_loss=0.03607, over 4964.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03052, over 972556.47 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:25:06,488 INFO [train.py:715] (4/8) Epoch 14, batch 29300, loss[loss=0.1587, simple_loss=0.2249, pruned_loss=0.04626, over 4843.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03099, over 971187.93 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 05:25:46,608 INFO [train.py:715] (4/8) Epoch 14, batch 29350, loss[loss=0.1235, simple_loss=0.2098, pruned_loss=0.01867, over 4759.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03103, over 971759.58 frames.], batch size: 19, lr: 1.55e-04
2022-05-08 05:26:26,516 INFO [train.py:715] (4/8) Epoch 14, batch 29400, loss[loss=0.1355, simple_loss=0.2063, pruned_loss=0.03238, over 4761.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2089, pruned_loss=0.03112, over 971227.83 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 05:27:05,390 INFO [train.py:715] (4/8) Epoch 14, batch 29450, loss[loss=0.1475, simple_loss=0.2124, pruned_loss=0.0413, over 4963.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03059, over 971508.58 frames.], batch size: 35, lr: 1.55e-04
2022-05-08 05:27:45,241 INFO [train.py:715] (4/8) Epoch 14, batch 29500, loss[loss=0.1567, simple_loss=0.2348, pruned_loss=0.03933, over 4839.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2083, pruned_loss=0.03099, over 972068.59 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:28:25,579 INFO [train.py:715] (4/8) Epoch 14, batch 29550, loss[loss=0.1282, simple_loss=0.2001, pruned_loss=0.02814, over 4792.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2085, pruned_loss=0.031, over 971998.90 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 05:29:05,388 INFO [train.py:715] (4/8) Epoch 14, batch 29600, loss[loss=0.1513, simple_loss=0.2209, pruned_loss=0.04083, over 4905.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2089, pruned_loss=0.03103, over 971806.38 frames.], batch size: 39, lr: 1.55e-04
2022-05-08 05:29:44,399 INFO [train.py:715] (4/8) Epoch 14, batch 29650, loss[loss=0.1635, simple_loss=0.2242, pruned_loss=0.05143, over 4777.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03094, over 971814.72 frames.], batch size: 14, lr: 1.55e-04
2022-05-08 05:30:25,202 INFO [train.py:715] (4/8) Epoch 14, batch 29700, loss[loss=0.1163, simple_loss=0.1987, pruned_loss=0.01693, over 4838.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2088, pruned_loss=0.03108, over 972009.75 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:31:06,275 INFO [train.py:715] (4/8) Epoch 14, batch 29750, loss[loss=0.1426, simple_loss=0.2143, pruned_loss=0.03548, over 4963.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03112, over 971435.89 frames.], batch size: 39, lr: 1.55e-04
2022-05-08 05:31:45,879 INFO [train.py:715] (4/8) Epoch 14, batch 29800, loss[loss=0.1487, simple_loss=0.2184, pruned_loss=0.03953, over 4829.00 frames.], tot_loss[loss=0.1369, simple_loss=0.2108, pruned_loss=0.03154, over 972154.72 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:32:26,700 INFO [train.py:715] (4/8) Epoch 14, batch 29850, loss[loss=0.1262, simple_loss=0.198, pruned_loss=0.02716, over 4836.00 frames.], tot_loss[loss=0.136, simple_loss=0.2097, pruned_loss=0.03118, over 972257.94 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 05:33:06,680 INFO [train.py:715] (4/8) Epoch 14, batch 29900, loss[loss=0.1563, simple_loss=0.2354, pruned_loss=0.03863, over 4961.00 frames.], tot_loss[loss=0.1364, simple_loss=0.2099, pruned_loss=0.03145, over 972314.25 frames.], batch size: 39, lr: 1.55e-04
2022-05-08 05:33:46,352 INFO [train.py:715] (4/8) Epoch 14, batch 29950, loss[loss=0.1546, simple_loss=0.2298, pruned_loss=0.03964, over 4816.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03107, over 972812.66 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:34:25,087 INFO [train.py:715] (4/8) Epoch 14, batch 30000, loss[loss=0.1524, simple_loss=0.2285, pruned_loss=0.03816, over 4836.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03128, over 972487.64 frames.], batch size: 30, lr: 1.55e-04
2022-05-08 05:34:25,088 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 05:34:42,241 INFO [train.py:742] (4/8) Epoch 14, validation: loss=0.1052, simple_loss=0.189, pruned_loss=0.01075, over 914524.00 frames.
2022-05-08 05:35:21,217 INFO [train.py:715] (4/8) Epoch 14, batch 30050, loss[loss=0.1242, simple_loss=0.1901, pruned_loss=0.02917, over 4647.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2098, pruned_loss=0.03127, over 972371.70 frames.], batch size: 13, lr: 1.55e-04
2022-05-08 05:36:01,186 INFO [train.py:715] (4/8) Epoch 14, batch 30100, loss[loss=0.1243, simple_loss=0.2051, pruned_loss=0.02172, over 4967.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2097, pruned_loss=0.0315, over 971743.75 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:36:42,304 INFO [train.py:715] (4/8) Epoch 14, batch 30150, loss[loss=0.1347, simple_loss=0.2146, pruned_loss=0.0274, over 4771.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2085, pruned_loss=0.03111, over 971715.61 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 05:37:21,237 INFO [train.py:715] (4/8) Epoch 14, batch 30200, loss[loss=0.1406, simple_loss=0.2293, pruned_loss=0.02595, over 4753.00 frames.], tot_loss[loss=0.1355, simple_loss=0.209, pruned_loss=0.03106, over 972915.93 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 05:38:01,176 INFO [train.py:715] (4/8) Epoch 14, batch 30250, loss[loss=0.1468, simple_loss=0.2138, pruned_loss=0.03991, over 4886.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.0311, over 973266.88 frames.], batch size: 16, lr: 1.55e-04
2022-05-08 05:38:41,858 INFO [train.py:715] (4/8) Epoch 14, batch 30300, loss[loss=0.1272, simple_loss=0.2031, pruned_loss=0.02566, over 4922.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03075, over 972534.25 frames.], batch size: 29, lr: 1.55e-04
2022-05-08 05:39:21,362 INFO [train.py:715] (4/8) Epoch 14, batch 30350, loss[loss=0.1414, simple_loss=0.217, pruned_loss=0.03285, over 4834.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03104, over 972939.07 frames.], batch size: 15, lr: 1.55e-04
2022-05-08 05:40:00,594 INFO [train.py:715] (4/8) Epoch 14, batch 30400, loss[loss=0.1306, simple_loss=0.2088, pruned_loss=0.02621, over 4794.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.03043, over 972234.59 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 05:40:40,493 INFO [train.py:715] (4/8) Epoch 14, batch 30450, loss[loss=0.1284, simple_loss=0.2019, pruned_loss=0.02741, over 4774.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.03077, over 972253.26 frames.], batch size: 18, lr: 1.55e-04
2022-05-08 05:41:20,816 INFO [train.py:715] (4/8) Epoch 14, batch 30500, loss[loss=0.1452, simple_loss=0.2209, pruned_loss=0.0347, over 4834.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03076, over 972380.55 frames.], batch size: 26, lr: 1.55e-04
2022-05-08 05:41:59,765 INFO [train.py:715] (4/8) Epoch 14, batch 30550, loss[loss=0.168, simple_loss=0.2435, pruned_loss=0.04622, over 4882.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03082, over 972477.79 frames.], batch size: 16, lr: 1.54e-04
2022-05-08 05:42:39,671 INFO [train.py:715] (4/8) Epoch 14, batch 30600, loss[loss=0.157, simple_loss=0.2286, pruned_loss=0.04266, over 4811.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.03083, over 972089.05 frames.], batch size: 25, lr: 1.54e-04
2022-05-08 05:43:20,416 INFO [train.py:715] (4/8) Epoch 14, batch 30650, loss[loss=0.1456, simple_loss=0.2064, pruned_loss=0.04234, over 4871.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03099, over 972196.85 frames.], batch size: 16, lr: 1.54e-04
2022-05-08 05:44:00,001 INFO [train.py:715] (4/8) Epoch 14, batch 30700, loss[loss=0.1253, simple_loss=0.2023, pruned_loss=0.02421, over 4827.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03075, over 970830.62 frames.], batch size: 25, lr: 1.54e-04
2022-05-08 05:44:39,751 INFO [train.py:715] (4/8) Epoch 14, batch 30750, loss[loss=0.1297, simple_loss=0.2001, pruned_loss=0.02965, over 4753.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03057, over 971527.48 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 05:45:19,650 INFO [train.py:715] (4/8) Epoch 14, batch 30800, loss[loss=0.1887, simple_loss=0.2544, pruned_loss=0.0615, over 4855.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03059, over 971378.10 frames.], batch size: 38, lr: 1.54e-04
2022-05-08 05:46:00,444 INFO [train.py:715] (4/8) Epoch 14, batch 30850, loss[loss=0.1572, simple_loss=0.2319, pruned_loss=0.04124, over 4891.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03054, over 971537.68 frames.], batch size: 18, lr: 1.54e-04
2022-05-08 05:46:39,514 INFO [train.py:715] (4/8) Epoch 14, batch 30900, loss[loss=0.1642, simple_loss=0.2325, pruned_loss=0.04794, over 4775.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03041, over 971735.49 frames.], batch size: 17, lr: 1.54e-04
2022-05-08 05:47:18,030 INFO [train.py:715] (4/8) Epoch 14, batch 30950, loss[loss=0.1468, simple_loss=0.2321, pruned_loss=0.03074, over 4920.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03043, over 972797.90 frames.], batch size: 18, lr: 1.54e-04
2022-05-08 05:47:57,793 INFO [train.py:715] (4/8) Epoch 14, batch 31000, loss[loss=0.1415, simple_loss=0.2089, pruned_loss=0.03705, over 4943.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2095, pruned_loss=0.03047, over 972944.55 frames.], batch size: 35, lr: 1.54e-04
2022-05-08 05:48:37,477 INFO [train.py:715] (4/8) Epoch 14, batch 31050, loss[loss=0.1463, simple_loss=0.2119, pruned_loss=0.04032, over 4929.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2091, pruned_loss=0.03014, over 972567.69 frames.], batch size: 23, lr: 1.54e-04
2022-05-08 05:49:17,843 INFO [train.py:715] (4/8) Epoch 14, batch 31100, loss[loss=0.1411, simple_loss=0.2052, pruned_loss=0.03851, over 4825.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03039, over 972164.57 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 05:49:58,965 INFO [train.py:715] (4/8) Epoch 14, batch 31150, loss[loss=0.1102, simple_loss=0.191, pruned_loss=0.01469, over 4853.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2097, pruned_loss=0.03027, over 972524.84 frames.], batch size: 20, lr: 1.54e-04
2022-05-08 05:50:40,120 INFO [train.py:715] (4/8) Epoch 14, batch 31200, loss[loss=0.1144, simple_loss=0.1856, pruned_loss=0.02161, over 4802.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02965, over 972805.81 frames.], batch size: 14, lr: 1.54e-04
2022-05-08 05:51:19,910 INFO [train.py:715] (4/8) Epoch 14, batch 31250, loss[loss=0.1424, simple_loss=0.216, pruned_loss=0.03435, over 4967.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02986, over 973005.96 frames.], batch size: 21, lr: 1.54e-04
2022-05-08 05:52:00,304 INFO [train.py:715] (4/8) Epoch 14, batch 31300, loss[loss=0.1436, simple_loss=0.2215, pruned_loss=0.03287, over 4941.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02936, over 972746.57 frames.], batch size: 29, lr: 1.54e-04
2022-05-08 05:52:41,149 INFO [train.py:715] (4/8) Epoch 14, batch 31350, loss[loss=0.1582, simple_loss=0.2289, pruned_loss=0.04374, over 4910.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02985, over 972365.17 frames.], batch size: 17, lr: 1.54e-04
2022-05-08 05:53:21,032 INFO [train.py:715] (4/8) Epoch 14, batch 31400, loss[loss=0.1185, simple_loss=0.2021, pruned_loss=0.01742, over 4925.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02915, over 972349.76 frames.], batch size: 23, lr: 1.54e-04
2022-05-08 05:54:00,703 INFO [train.py:715] (4/8) Epoch 14, batch 31450, loss[loss=0.136, simple_loss=0.2047, pruned_loss=0.03368, over 4890.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02963, over 972846.32 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 05:54:40,743 INFO [train.py:715] (4/8) Epoch 14, batch 31500, loss[loss=0.1389, simple_loss=0.2132, pruned_loss=0.03228, over 4790.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02996, over 973224.13 frames.], batch size: 14, lr: 1.54e-04
2022-05-08 05:55:21,329 INFO [train.py:715] (4/8) Epoch 14, batch 31550, loss[loss=0.1244, simple_loss=0.2032, pruned_loss=0.02273, over 4754.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02978, over 972956.10 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 05:56:01,190 INFO [train.py:715] (4/8) Epoch 14, batch 31600, loss[loss=0.1523, simple_loss=0.2233, pruned_loss=0.0406, over 4955.00 frames.], tot_loss[loss=0.1333, simple_loss=0.207, pruned_loss=0.02985, over 972696.36 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 05:56:40,685 INFO [train.py:715] (4/8) Epoch 14, batch 31650, loss[loss=0.1165, simple_loss=0.1913, pruned_loss=0.0208, over 4878.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02976, over 971874.81 frames.], batch size: 16, lr: 1.54e-04
2022-05-08 05:57:21,067 INFO [train.py:715] (4/8) Epoch 14, batch 31700, loss[loss=0.1368, simple_loss=0.2189, pruned_loss=0.0273, over 4928.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.0298, over 971898.83 frames.], batch size: 23, lr: 1.54e-04
2022-05-08 05:58:00,665 INFO [train.py:715] (4/8) Epoch 14, batch 31750, loss[loss=0.1437, simple_loss=0.214, pruned_loss=0.03666, over 4904.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03011, over 972167.05 frames.], batch size: 17, lr: 1.54e-04
2022-05-08 05:58:40,565 INFO [train.py:715] (4/8) Epoch 14, batch 31800, loss[loss=0.1161, simple_loss=0.1921, pruned_loss=0.02003, over 4966.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03009, over 972896.97 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 05:59:20,872 INFO [train.py:715] (4/8) Epoch 14, batch 31850, loss[loss=0.1121, simple_loss=0.1827, pruned_loss=0.02075, over 4799.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03, over 972456.06 frames.], batch size: 24, lr: 1.54e-04
2022-05-08 06:00:01,586 INFO [train.py:715] (4/8) Epoch 14, batch 31900, loss[loss=0.1544, simple_loss=0.2203, pruned_loss=0.04425, over 4872.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03029, over 972961.45 frames.], batch size: 22, lr: 1.54e-04
2022-05-08 06:00:40,981 INFO [train.py:715] (4/8) Epoch 14, batch 31950, loss[loss=0.1379, simple_loss=0.2077, pruned_loss=0.03404, over 4828.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03046, over 973567.43 frames.], batch size: 14, lr: 1.54e-04
2022-05-08 06:01:20,557 INFO [train.py:715] (4/8) Epoch 14, batch 32000, loss[loss=0.1512, simple_loss=0.2219, pruned_loss=0.04028, over 4828.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03041, over 973354.91 frames.], batch size: 13, lr: 1.54e-04
2022-05-08 06:02:01,139 INFO [train.py:715] (4/8) Epoch 14, batch 32050, loss[loss=0.1664, simple_loss=0.2308, pruned_loss=0.05101, over 4913.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03103, over 972559.54 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 06:02:40,614 INFO [train.py:715] (4/8) Epoch 14, batch 32100, loss[loss=0.1412, simple_loss=0.2097, pruned_loss=0.03636, over 4970.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2092, pruned_loss=0.03099, over 973430.98 frames.], batch size: 35, lr: 1.54e-04
2022-05-08 06:03:20,377 INFO [train.py:715] (4/8) Epoch 14, batch 32150, loss[loss=0.118, simple_loss=0.1906, pruned_loss=0.02267, over 4803.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03123, over 973340.65 frames.], batch size: 25, lr: 1.54e-04
2022-05-08 06:04:00,803 INFO [train.py:715] (4/8) Epoch 14, batch 32200, loss[loss=0.125, simple_loss=0.1996, pruned_loss=0.02516, over 4978.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2091, pruned_loss=0.0308, over 973210.57 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 06:04:41,242 INFO [train.py:715] (4/8) Epoch 14, batch 32250, loss[loss=0.1185, simple_loss=0.1792, pruned_loss=0.02887, over 4964.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03037, over 972896.20 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 06:05:20,517 INFO [train.py:715] (4/8) Epoch 14, batch 32300, loss[loss=0.1338, simple_loss=0.2086, pruned_loss=0.02944, over 4884.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02951, over 972730.12 frames.], batch size: 32, lr: 1.54e-04
2022-05-08 06:06:00,144 INFO [train.py:715] (4/8) Epoch 14, batch 32350, loss[loss=0.1463, simple_loss=0.2171, pruned_loss=0.03777, over 4801.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02976, over 972627.04 frames.], batch size: 21, lr: 1.54e-04
2022-05-08 06:06:40,251 INFO [train.py:715] (4/8) Epoch 14, batch 32400, loss[loss=0.1297, simple_loss=0.1949, pruned_loss=0.0323, over 4904.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03003, over 972309.78 frames.], batch size: 17, lr: 1.54e-04
2022-05-08 06:07:19,943 INFO [train.py:715] (4/8) Epoch 14, batch 32450, loss[loss=0.1268, simple_loss=0.1984, pruned_loss=0.02753, over 4946.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03045, over 972655.14 frames.], batch size: 29, lr: 1.54e-04
2022-05-08 06:07:59,618 INFO [train.py:715] (4/8) Epoch 14, batch 32500, loss[loss=0.1368, simple_loss=0.2085, pruned_loss=0.03254, over 4774.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03069, over 972544.58 frames.], batch size: 12, lr: 1.54e-04
2022-05-08 06:08:39,979 INFO [train.py:715] (4/8) Epoch 14, batch 32550, loss[loss=0.1176, simple_loss=0.1925, pruned_loss=0.02138, over 4953.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03031, over 972703.03 frames.], batch size: 35, lr: 1.54e-04
2022-05-08 06:09:20,726 INFO [train.py:715] (4/8) Epoch 14, batch 32600, loss[loss=0.13, simple_loss=0.206, pruned_loss=0.02703, over 4644.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03003, over 972219.78 frames.], batch size: 13, lr: 1.54e-04
2022-05-08 06:10:00,304 INFO [train.py:715] (4/8) Epoch 14, batch 32650, loss[loss=0.142, simple_loss=0.2125, pruned_loss=0.03577, over 4779.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03048, over 972471.67 frames.], batch size: 18, lr: 1.54e-04
2022-05-08 06:10:43,596 INFO [train.py:715] (4/8) Epoch 14, batch 32700, loss[loss=0.1181, simple_loss=0.2018, pruned_loss=0.01724, over 4647.00 frames.], tot_loss[loss=0.135, simple_loss=0.2092, pruned_loss=0.03042, over 972192.70 frames.], batch size: 13, lr: 1.54e-04
2022-05-08 06:11:24,757 INFO [train.py:715] (4/8) Epoch 14, batch 32750, loss[loss=0.143, simple_loss=0.2181, pruned_loss=0.03395, over 4763.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03045, over 972272.08 frames.], batch size: 16, lr: 1.54e-04
2022-05-08 06:12:05,074 INFO [train.py:715] (4/8) Epoch 14, batch 32800, loss[loss=0.1362, simple_loss=0.2221, pruned_loss=0.0251, over 4986.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03033, over 972490.27 frames.], batch size: 39, lr: 1.54e-04
2022-05-08 06:12:45,502 INFO [train.py:715] (4/8) Epoch 14, batch 32850, loss[loss=0.1197, simple_loss=0.1861, pruned_loss=0.02662, over 4988.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03054, over 972680.16 frames.], batch size: 14, lr: 1.54e-04
2022-05-08 06:13:26,799 INFO [train.py:715] (4/8) Epoch 14, batch 32900, loss[loss=0.1244, simple_loss=0.205, pruned_loss=0.02189, over 4836.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03055, over 972436.86 frames.], batch size: 27, lr: 1.54e-04
2022-05-08 06:14:07,963 INFO [train.py:715] (4/8) Epoch 14, batch 32950, loss[loss=0.1257, simple_loss=0.2008, pruned_loss=0.02532, over 4871.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2083, pruned_loss=0.03069, over 973042.57 frames.], batch size: 20, lr: 1.54e-04
2022-05-08 06:14:47,661 INFO [train.py:715] (4/8) Epoch 14, batch 33000, loss[loss=0.1451, simple_loss=0.2203, pruned_loss=0.03498, over 4816.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03024, over 973180.77 frames.], batch size: 26, lr: 1.54e-04
2022-05-08 06:14:47,662 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 06:15:25,559 INFO [train.py:742] (4/8) Epoch 14, validation: loss=0.1051, simple_loss=0.1889, pruned_loss=0.01071, over 914524.00 frames.
2022-05-08 06:16:05,283 INFO [train.py:715] (4/8) Epoch 14, batch 33050, loss[loss=0.1345, simple_loss=0.2048, pruned_loss=0.03209, over 4859.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03033, over 973030.55 frames.], batch size: 20, lr: 1.54e-04
2022-05-08 06:16:46,133 INFO [train.py:715] (4/8) Epoch 14, batch 33100, loss[loss=0.1596, simple_loss=0.224, pruned_loss=0.04766, over 4979.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2085, pruned_loss=0.03098, over 973128.85 frames.], batch size: 35, lr: 1.54e-04
2022-05-08 06:17:27,355 INFO [train.py:715] (4/8) Epoch 14, batch 33150, loss[loss=0.1146, simple_loss=0.1928, pruned_loss=0.01819, over 4988.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.03069, over 972589.72 frames.], batch size: 26, lr: 1.54e-04
2022-05-08 06:18:07,421 INFO [train.py:715] (4/8) Epoch 14, batch 33200, loss[loss=0.1568, simple_loss=0.2218, pruned_loss=0.04594, over 4969.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.0311, over 972907.12 frames.], batch size: 39, lr: 1.54e-04
2022-05-08 06:18:47,766 INFO [train.py:715] (4/8) Epoch 14, batch 33250, loss[loss=0.1535, simple_loss=0.2287, pruned_loss=0.03914, over 4780.00 frames.], tot_loss[loss=0.136, simple_loss=0.2094, pruned_loss=0.03129, over 972521.68 frames.], batch size: 14, lr: 1.54e-04
2022-05-08 06:19:28,520 INFO [train.py:715] (4/8) Epoch 14, batch 33300, loss[loss=0.1008, simple_loss=0.1828, pruned_loss=0.009441, over 4924.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.03109, over 972482.30 frames.], batch size: 29, lr: 1.54e-04
2022-05-08 06:20:09,718 INFO [train.py:715] (4/8) Epoch 14, batch 33350, loss[loss=0.1311, simple_loss=0.1984, pruned_loss=0.03187, over 4842.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2094, pruned_loss=0.03122, over 972771.82 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 06:20:49,886 INFO [train.py:715] (4/8) Epoch 14, batch 33400, loss[loss=0.1226, simple_loss=0.1906, pruned_loss=0.02726, over 4952.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2097, pruned_loss=0.03082, over 972670.71 frames.], batch size: 24, lr: 1.54e-04
2022-05-08 06:21:30,267 INFO [train.py:715] (4/8) Epoch 14, batch 33450, loss[loss=0.1299, simple_loss=0.2066, pruned_loss=0.02657, over 4794.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2097, pruned_loss=0.03098, over 971301.03 frames.], batch size: 21, lr: 1.54e-04
2022-05-08 06:22:11,498 INFO [train.py:715] (4/8) Epoch 14, batch 33500, loss[loss=0.1424, simple_loss=0.211, pruned_loss=0.0369, over 4807.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03127, over 971192.28 frames.], batch size: 21, lr: 1.54e-04
2022-05-08 06:22:51,804 INFO [train.py:715] (4/8) Epoch 14, batch 33550, loss[loss=0.1499, simple_loss=0.2175, pruned_loss=0.04114, over 4892.00 frames.], tot_loss[loss=0.1357, simple_loss=0.209, pruned_loss=0.03116, over 971201.97 frames.], batch size: 16, lr: 1.54e-04
2022-05-08 06:23:32,994 INFO [train.py:715] (4/8) Epoch 14, batch 33600, loss[loss=0.1343, simple_loss=0.2111, pruned_loss=0.02874, over 4926.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2085, pruned_loss=0.03094, over 971772.32 frames.], batch size: 23, lr: 1.54e-04
2022-05-08 06:24:14,046 INFO [train.py:715] (4/8) Epoch 14, batch 33650, loss[loss=0.1207, simple_loss=0.2029, pruned_loss=0.01924, over 4762.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.03033, over 971869.32 frames.], batch size: 12, lr: 1.54e-04
2022-05-08 06:24:54,963 INFO [train.py:715] (4/8) Epoch 14, batch 33700, loss[loss=0.1456, simple_loss=0.2076, pruned_loss=0.04175, over 4911.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03003, over 971034.61 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 06:25:35,106 INFO [train.py:715] (4/8) Epoch 14, batch 33750, loss[loss=0.1249, simple_loss=0.2015, pruned_loss=0.02417, over 4793.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03075, over 971009.53 frames.], batch size: 24, lr: 1.54e-04
2022-05-08 06:26:15,677 INFO [train.py:715] (4/8) Epoch 14, batch 33800, loss[loss=0.15, simple_loss=0.2208, pruned_loss=0.0396, over 4745.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03076, over 971231.56 frames.], batch size: 16, lr: 1.54e-04
2022-05-08 06:26:56,926 INFO [train.py:715] (4/8) Epoch 14, batch 33850, loss[loss=0.125, simple_loss=0.1994, pruned_loss=0.0253, over 4895.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03031, over 971833.35 frames.], batch size: 22, lr: 1.54e-04
2022-05-08 06:27:37,001 INFO [train.py:715] (4/8) Epoch 14, batch 33900, loss[loss=0.1248, simple_loss=0.2013, pruned_loss=0.02418, over 4790.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03059, over 971883.33 frames.], batch size: 18, lr: 1.54e-04
2022-05-08 06:28:17,543 INFO [train.py:715] (4/8) Epoch 14, batch 33950, loss[loss=0.1247, simple_loss=0.1986, pruned_loss=0.02542, over 4708.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03075, over 971664.89 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 06:28:58,264 INFO [train.py:715] (4/8) Epoch 14, batch 34000, loss[loss=0.1593, simple_loss=0.2423, pruned_loss=0.03822, over 4775.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03086, over 972189.14 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 06:29:39,252 INFO [train.py:715] (4/8) Epoch 14, batch 34050, loss[loss=0.1384, simple_loss=0.2118, pruned_loss=0.03244, over 4947.00 frames.], tot_loss[loss=0.135, simple_loss=0.2095, pruned_loss=0.03029, over 972759.49 frames.], batch size: 21, lr: 1.54e-04
2022-05-08 06:30:19,201 INFO [train.py:715] (4/8) Epoch 14, batch 34100, loss[loss=0.1479, simple_loss=0.2196, pruned_loss=0.03812, over 4900.00 frames.], tot_loss[loss=0.1357, simple_loss=0.21, pruned_loss=0.03075, over 972810.57 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 06:30:59,692 INFO [train.py:715] (4/8) Epoch 14, batch 34150, loss[loss=0.1453, simple_loss=0.2216, pruned_loss=0.03449, over 4959.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.03062, over 972714.42 frames.], batch size: 39, lr: 1.54e-04
2022-05-08 06:31:40,126 INFO [train.py:715] (4/8) Epoch 14, batch 34200, loss[loss=0.126, simple_loss=0.2013, pruned_loss=0.02535, over 4796.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2094, pruned_loss=0.0305, over 973014.54 frames.], batch size: 12, lr: 1.54e-04
2022-05-08 06:32:20,289 INFO [train.py:715] (4/8) Epoch 14, batch 34250, loss[loss=0.1234, simple_loss=0.2007, pruned_loss=0.0231, over 4737.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2101, pruned_loss=0.0308, over 973630.38 frames.], batch size: 16, lr: 1.54e-04
2022-05-08 06:33:00,827 INFO [train.py:715] (4/8) Epoch 14, batch 34300, loss[loss=0.1469, simple_loss=0.2184, pruned_loss=0.03772, over 4830.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03068, over 973753.44 frames.], batch size: 15, lr: 1.54e-04
2022-05-08 06:33:41,480 INFO [train.py:715] (4/8) Epoch 14, batch 34350, loss[loss=0.1677, simple_loss=0.2402, pruned_loss=0.04765, over 4926.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2089, pruned_loss=0.03003, over 974520.93 frames.], batch size: 23, lr: 1.54e-04
2022-05-08 06:34:22,180 INFO [train.py:715] (4/8) Epoch 14, batch 34400, loss[loss=0.1523, simple_loss=0.2305, pruned_loss=0.03705, over 4735.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2097, pruned_loss=0.03053, over 974001.66 frames.], batch size: 16, lr: 1.54e-04
2022-05-08 06:35:01,766 INFO [train.py:715] (4/8) Epoch 14, batch 34450, loss[loss=0.1293, simple_loss=0.2022, pruned_loss=0.02817, over 4798.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2091, pruned_loss=0.0302, over 972616.96 frames.], batch size: 21, lr: 1.54e-04
2022-05-08 06:35:42,621 INFO [train.py:715] (4/8) Epoch 14, batch 34500, loss[loss=0.1284, simple_loss=0.2084, pruned_loss=0.02422, over 4785.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03026, over 972435.43 frames.], batch size: 18, lr: 1.54e-04
2022-05-08 06:36:23,317 INFO [train.py:715] (4/8) Epoch 14, batch 34550, loss[loss=0.1087, simple_loss=0.1829, pruned_loss=0.01722, over 4917.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03034, over 972456.89 frames.], batch size: 17, lr: 1.54e-04
2022-05-08 06:37:03,429 INFO [train.py:715] (4/8) Epoch 14, batch 34600, loss[loss=0.1458, simple_loss=0.2284, pruned_loss=0.03157, over 4936.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03017, over 971932.70 frames.], batch size: 29, lr: 1.54e-04
2022-05-08 06:37:43,642 INFO [train.py:715] (4/8) Epoch 14, batch 34650, loss[loss=0.1175, simple_loss=0.1891, pruned_loss=0.0229, over 4875.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03076, over 972371.54 frames.], batch size: 16, lr: 1.54e-04
2022-05-08 06:38:24,395 INFO [train.py:715] (4/8) Epoch 14, batch 34700, loss[loss=0.1381, simple_loss=0.2127, pruned_loss=0.03168, over 4771.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03039, over 972040.56 frames.], batch size: 18, lr: 1.54e-04
2022-05-08 06:39:03,260 INFO [train.py:715] (4/8) Epoch 14, batch 34750, loss[loss=0.1545, simple_loss=0.2134, pruned_loss=0.04782, over 4917.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03093, over 971988.52 frames.], batch size: 19, lr: 1.54e-04
2022-05-08 06:39:40,046 INFO [train.py:715] (4/8) Epoch 14, batch 34800, loss[loss=0.1527, simple_loss=0.2304, pruned_loss=0.03752, over 4792.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03105, over 972323.38 frames.], batch size: 14, lr: 1.54e-04
2022-05-08 06:40:33,604 INFO [train.py:715] (4/8) Epoch 15, batch 0, loss[loss=0.1457, simple_loss=0.2211, pruned_loss=0.03517, over 4955.00 frames.], tot_loss[loss=0.1457, simple_loss=0.2211, pruned_loss=0.03517, over 4955.00 frames.], batch size: 35, lr: 1.49e-04
2022-05-08 06:41:12,924 INFO [train.py:715] (4/8) Epoch 15, batch 50, loss[loss=0.1464, simple_loss=0.2192, pruned_loss=0.03677, over 4988.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02984, over 219290.33 frames.], batch size: 28, lr: 1.49e-04
2022-05-08 06:41:54,160 INFO [train.py:715] (4/8) Epoch 15, batch 100, loss[loss=0.125, simple_loss=0.2012, pruned_loss=0.02437, over 4935.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02982, over 385504.13 frames.], batch size: 29, lr: 1.49e-04
2022-05-08 06:42:35,653 INFO [train.py:715] (4/8) Epoch 15, batch 150, loss[loss=0.1148, simple_loss=0.1869, pruned_loss=0.02134, over 4971.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2071, pruned_loss=0.03, over 515615.94 frames.], batch size: 14, lr: 1.49e-04
2022-05-08 06:43:15,913 INFO [train.py:715] (4/8) Epoch 15, batch 200, loss[loss=0.122, simple_loss=0.2045, pruned_loss=0.01971, over 4924.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03051, over 617456.47 frames.], batch size: 18, lr: 1.49e-04
2022-05-08 06:43:56,377 INFO [train.py:715] (4/8) Epoch 15, batch 250, loss[loss=0.1302, simple_loss=0.2005, pruned_loss=0.02991, over 4792.00 frames.], tot_loss[loss=0.1361, simple_loss=0.21, pruned_loss=0.03108, over 696790.56 frames.], batch size: 14, lr: 1.49e-04
2022-05-08 06:44:37,760 INFO [train.py:715] (4/8) Epoch 15, batch 300, loss[loss=0.1365, simple_loss=0.2205, pruned_loss=0.02619, over 4788.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03097, over 758617.66 frames.], batch size: 13, lr: 1.49e-04
2022-05-08 06:45:18,782 INFO [train.py:715] (4/8) Epoch 15, batch 350, loss[loss=0.1295, simple_loss=0.1992, pruned_loss=0.02989, over 4788.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03066, over 805581.62 frames.], batch size: 17, lr: 1.49e-04
2022-05-08 06:45:58,467 INFO [train.py:715] (4/8) Epoch 15, batch 400, loss[loss=0.1524, simple_loss=0.2321, pruned_loss=0.03636, over 4789.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2099, pruned_loss=0.03124, over 843006.19 frames.], batch size: 18, lr: 1.49e-04
2022-05-08 06:46:39,360 INFO [train.py:715] (4/8) Epoch 15, batch 450, loss[loss=0.1346, simple_loss=0.2054, pruned_loss=0.03192, over 4766.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.0307, over 871508.57 frames.], batch size: 18, lr: 1.49e-04
2022-05-08 06:47:20,094 INFO [train.py:715] (4/8) Epoch 15, batch 500, loss[loss=0.1245, simple_loss=0.1968, pruned_loss=0.0261, over 4972.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03132, over 893968.41 frames.], batch size: 25, lr: 1.49e-04
2022-05-08 06:48:00,508 INFO [train.py:715] (4/8) Epoch 15, batch 550, loss[loss=0.1505, simple_loss=0.2313, pruned_loss=0.0348, over 4807.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.0308, over 910989.88 frames.], batch size: 14, lr: 1.49e-04
2022-05-08 06:48:40,051 INFO [train.py:715] (4/8) Epoch 15, batch 600, loss[loss=0.101, simple_loss=0.1719, pruned_loss=0.01502, over 4976.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2082, pruned_loss=0.03079, over 924433.68 frames.], batch size: 35, lr: 1.49e-04
2022-05-08 06:49:21,139 INFO [train.py:715] (4/8) Epoch 15, batch 650, loss[loss=0.1287, simple_loss=0.2077, pruned_loss=0.02481, over 4765.00 frames.], tot_loss[loss=0.136, simple_loss=0.2095, pruned_loss=0.03128, over 935058.91 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 06:50:01,502 INFO [train.py:715] (4/8) Epoch 15, batch 700, loss[loss=0.1139, simple_loss=0.1877, pruned_loss=0.02008, over 4945.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03096, over 943134.60 frames.], batch size: 29, lr: 1.49e-04
2022-05-08 06:50:41,519 INFO [train.py:715] (4/8) Epoch 15, batch 750, loss[loss=0.1541, simple_loss=0.2285, pruned_loss=0.03984, over 4830.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03115, over 949079.42 frames.], batch size: 26, lr: 1.49e-04
2022-05-08 06:51:21,998 INFO [train.py:715] (4/8) Epoch 15, batch 800, loss[loss=0.1358, simple_loss=0.2108, pruned_loss=0.03041, over 4906.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2101, pruned_loss=0.03112, over 954953.33 frames.], batch size: 17, lr: 1.49e-04
2022-05-08 06:52:02,781 INFO [train.py:715] (4/8) Epoch 15, batch 850, loss[loss=0.1139, simple_loss=0.1865, pruned_loss=0.02072, over 4913.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2091, pruned_loss=0.03055, over 957879.63 frames.], batch size: 18, lr: 1.49e-04
2022-05-08 06:52:43,859 INFO [train.py:715] (4/8) Epoch 15, batch 900, loss[loss=0.135, simple_loss=0.2307, pruned_loss=0.01964, over 4826.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03039, over 960884.29 frames.], batch size: 26, lr: 1.49e-04
2022-05-08 06:53:23,522 INFO [train.py:715] (4/8) Epoch 15, batch 950, loss[loss=0.1618, simple_loss=0.2274, pruned_loss=0.04805, over 4761.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03063, over 963010.67 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 06:54:04,064 INFO [train.py:715] (4/8) Epoch 15, batch 1000, loss[loss=0.1298, simple_loss=0.2059, pruned_loss=0.02686, over 4739.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03066, over 965007.88 frames.], batch size: 16, lr: 1.49e-04
2022-05-08 06:54:44,290 INFO [train.py:715] (4/8) Epoch 15, batch 1050, loss[loss=0.1313, simple_loss=0.2068, pruned_loss=0.02792, over 4978.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03049, over 966702.58 frames.], batch size: 25, lr: 1.49e-04
2022-05-08 06:55:23,571 INFO [train.py:715] (4/8) Epoch 15, batch 1100, loss[loss=0.1397, simple_loss=0.2058, pruned_loss=0.03684, over 4824.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2092, pruned_loss=0.03089, over 967508.72 frames.], batch size: 13, lr: 1.49e-04
2022-05-08 06:56:04,675 INFO [train.py:715] (4/8) Epoch 15, batch 1150, loss[loss=0.1272, simple_loss=0.1999, pruned_loss=0.02722, over 4874.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.0307, over 968888.85 frames.], batch size: 32, lr: 1.49e-04
2022-05-08 06:56:45,822 INFO [train.py:715] (4/8) Epoch 15, batch 1200, loss[loss=0.1287, simple_loss=0.1839, pruned_loss=0.03679, over 4895.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03042, over 969738.69 frames.], batch size: 17, lr: 1.49e-04
2022-05-08 06:57:26,535 INFO [train.py:715] (4/8) Epoch 15, batch 1250, loss[loss=0.1126, simple_loss=0.1894, pruned_loss=0.0179, over 4759.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.0305, over 969920.58 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 06:58:05,997 INFO [train.py:715] (4/8) Epoch 15, batch 1300, loss[loss=0.1019, simple_loss=0.1786, pruned_loss=0.01257, over 4736.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03035, over 969394.20 frames.], batch size: 16, lr: 1.49e-04
2022-05-08 06:58:46,678 INFO [train.py:715] (4/8) Epoch 15, batch 1350, loss[loss=0.1346, simple_loss=0.2015, pruned_loss=0.03382, over 4988.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2078, pruned_loss=0.03047, over 970988.45 frames.], batch size: 14, lr: 1.49e-04
2022-05-08 06:59:27,339 INFO [train.py:715] (4/8) Epoch 15, batch 1400, loss[loss=0.1344, simple_loss=0.2118, pruned_loss=0.02847, over 4943.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2082, pruned_loss=0.03076, over 971307.37 frames.], batch size: 29, lr: 1.49e-04
2022-05-08 07:00:07,531 INFO [train.py:715] (4/8) Epoch 15, batch 1450, loss[loss=0.1239, simple_loss=0.1965, pruned_loss=0.02563, over 4987.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2079, pruned_loss=0.03036, over 971854.64 frames.], batch size: 28, lr: 1.49e-04
2022-05-08 07:00:47,334 INFO [train.py:715] (4/8) Epoch 15, batch 1500, loss[loss=0.1428, simple_loss=0.2183, pruned_loss=0.0336, over 4811.00 frames.], tot_loss[loss=0.1345, simple_loss=0.208, pruned_loss=0.03049, over 972252.33 frames.], batch size: 21, lr: 1.49e-04
2022-05-08 07:01:28,502 INFO [train.py:715] (4/8) Epoch 15, batch 1550, loss[loss=0.1313, simple_loss=0.2044, pruned_loss=0.02915, over 4993.00 frames.], tot_loss[loss=0.135, simple_loss=0.2084, pruned_loss=0.03079, over 971613.49 frames.], batch size: 14, lr: 1.49e-04
2022-05-08 07:02:08,727 INFO [train.py:715] (4/8) Epoch 15, batch 1600, loss[loss=0.1275, simple_loss=0.1997, pruned_loss=0.02758, over 4961.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03031, over 971979.95 frames.], batch size: 35, lr: 1.49e-04
2022-05-08 07:02:47,765 INFO [train.py:715] (4/8) Epoch 15, batch 1650, loss[loss=0.1171, simple_loss=0.1928, pruned_loss=0.02066, over 4795.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03039, over 972451.12 frames.], batch size: 21, lr: 1.49e-04
2022-05-08 07:03:28,297 INFO [train.py:715] (4/8) Epoch 15, batch 1700, loss[loss=0.1185, simple_loss=0.1847, pruned_loss=0.02616, over 4813.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03022, over 972144.74 frames.], batch size: 13, lr: 1.49e-04
2022-05-08 07:04:08,876 INFO [train.py:715] (4/8) Epoch 15, batch 1750, loss[loss=0.1177, simple_loss=0.2, pruned_loss=0.01766, over 4957.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03036, over 972729.82 frames.], batch size: 28, lr: 1.49e-04
2022-05-08 07:04:48,957 INFO [train.py:715] (4/8) Epoch 15, batch 1800, loss[loss=0.1352, simple_loss=0.2018, pruned_loss=0.03433, over 4787.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.03021, over 971565.71 frames.], batch size: 17, lr: 1.49e-04
2022-05-08 07:05:28,935 INFO [train.py:715] (4/8) Epoch 15, batch 1850, loss[loss=0.154, simple_loss=0.2111, pruned_loss=0.04848, over 4929.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03019, over 971031.86 frames.], batch size: 18, lr: 1.49e-04
2022-05-08 07:06:09,782 INFO [train.py:715] (4/8) Epoch 15, batch 1900, loss[loss=0.1515, simple_loss=0.2132, pruned_loss=0.04489, over 4802.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03046, over 971161.18 frames.], batch size: 12, lr: 1.49e-04
2022-05-08 07:06:50,228 INFO [train.py:715] (4/8) Epoch 15, batch 1950, loss[loss=0.1362, simple_loss=0.2069, pruned_loss=0.03277, over 4964.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2079, pruned_loss=0.03045, over 971541.81 frames.], batch size: 35, lr: 1.49e-04
2022-05-08 07:07:29,402 INFO [train.py:715] (4/8) Epoch 15, batch 2000, loss[loss=0.1616, simple_loss=0.2358, pruned_loss=0.04371, over 4901.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.0303, over 972482.94 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 07:08:10,500 INFO [train.py:715] (4/8) Epoch 15, batch 2050, loss[loss=0.1275, simple_loss=0.2057, pruned_loss=0.02467, over 4839.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03025, over 972880.71 frames.], batch size: 26, lr: 1.49e-04
2022-05-08 07:08:50,813 INFO [train.py:715] (4/8) Epoch 15, batch 2100, loss[loss=0.1918, simple_loss=0.2485, pruned_loss=0.06759, over 4832.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03029, over 973683.81 frames.], batch size: 30, lr: 1.49e-04
2022-05-08 07:09:30,718 INFO [train.py:715] (4/8) Epoch 15, batch 2150, loss[loss=0.1639, simple_loss=0.2301, pruned_loss=0.04879, over 4978.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03046, over 972864.83 frames.], batch size: 39, lr: 1.49e-04
2022-05-08 07:10:10,971 INFO [train.py:715] (4/8) Epoch 15, batch 2200, loss[loss=0.1367, simple_loss=0.2035, pruned_loss=0.03495, over 4980.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02983, over 972658.16 frames.], batch size: 15, lr: 1.49e-04
2022-05-08 07:10:51,404 INFO [train.py:715] (4/8) Epoch 15, batch 2250, loss[loss=0.09933, simple_loss=0.1699, pruned_loss=0.01438, over 4991.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.03003, over 972867.57 frames.], batch size: 14, lr: 1.49e-04
2022-05-08 07:11:31,544 INFO [train.py:715] (4/8) Epoch 15, batch 2300, loss[loss=0.122, simple_loss=0.2062, pruned_loss=0.01888, over 4968.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2079, pruned_loss=0.03057, over 972888.11 frames.], batch size: 14, lr: 1.49e-04
2022-05-08 07:12:11,044 INFO [train.py:715] (4/8) Epoch 15, batch 2350, loss[loss=0.1298, simple_loss=0.2063, pruned_loss=0.02662, over 4965.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03005, over 972403.80 frames.], batch size: 21, lr: 1.49e-04
2022-05-08 07:12:51,318 INFO [train.py:715] (4/8) Epoch 15, batch 2400, loss[loss=0.1317, simple_loss=0.2104, pruned_loss=0.02646, over 4802.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03035, over 972388.33 frames.], batch size: 13, lr: 1.49e-04
2022-05-08 07:13:31,553 INFO [train.py:715] (4/8) Epoch 15, batch 2450, loss[loss=0.135, simple_loss=0.2172, pruned_loss=0.02639, over 4981.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2091, pruned_loss=0.03039, over 973113.74 frames.], batch size: 25, lr: 1.49e-04
2022-05-08 07:14:11,482 INFO [train.py:715] (4/8) Epoch 15, batch 2500, loss[loss=0.1453, simple_loss=0.2166, pruned_loss=0.03704, over 4695.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03017, over 973330.16 frames.], batch size: 15, lr: 1.49e-04
2022-05-08 07:14:50,600 INFO [train.py:715] (4/8) Epoch 15, batch 2550, loss[loss=0.1281, simple_loss=0.1975, pruned_loss=0.02936, over 4838.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03007, over 972595.86 frames.], batch size: 32, lr: 1.49e-04
2022-05-08 07:15:31,410 INFO [train.py:715] (4/8) Epoch 15, batch 2600, loss[loss=0.1201, simple_loss=0.1971, pruned_loss=0.0215, over 4881.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02982, over 972873.90 frames.], batch size: 22, lr: 1.49e-04
2022-05-08 07:16:12,097 INFO [train.py:715] (4/8) Epoch 15, batch 2650, loss[loss=0.1418, simple_loss=0.2146, pruned_loss=0.03446, over 4841.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02959, over 973197.84 frames.], batch size: 32, lr: 1.49e-04
2022-05-08 07:16:51,589 INFO [train.py:715] (4/8) Epoch 15, batch 2700, loss[loss=0.1367, simple_loss=0.2134, pruned_loss=0.02998, over 4763.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.0297, over 973419.81 frames.], batch size: 18, lr: 1.49e-04
2022-05-08 07:17:33,111 INFO [train.py:715] (4/8) Epoch 15, batch 2750, loss[loss=0.1435, simple_loss=0.2288, pruned_loss=0.02908, over 4845.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02977, over 972833.19 frames.], batch size: 32, lr: 1.49e-04
2022-05-08 07:18:14,180 INFO [train.py:715] (4/8) Epoch 15, batch 2800, loss[loss=0.1337, simple_loss=0.2196, pruned_loss=0.02386, over 4968.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.03002, over 972879.02 frames.], batch size: 14, lr: 1.49e-04
2022-05-08 07:18:54,878 INFO [train.py:715] (4/8) Epoch 15, batch 2850, loss[loss=0.1627, simple_loss=0.2454, pruned_loss=0.04002, over 4710.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.0302, over 973507.17 frames.], batch size: 15, lr: 1.49e-04
2022-05-08 07:19:34,212 INFO [train.py:715] (4/8) Epoch 15, batch 2900, loss[loss=0.1247, simple_loss=0.2038, pruned_loss=0.02282, over 4812.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02988, over 973694.76 frames.], batch size: 26, lr: 1.49e-04
2022-05-08 07:20:14,826 INFO [train.py:715] (4/8) Epoch 15, batch 2950, loss[loss=0.1264, simple_loss=0.1836, pruned_loss=0.03462, over 4975.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02977, over 973981.93 frames.], batch size: 15, lr: 1.49e-04
2022-05-08 07:20:55,625 INFO [train.py:715] (4/8) Epoch 15, batch 3000, loss[loss=0.1499, simple_loss=0.2234, pruned_loss=0.0382, over 4754.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03018, over 974259.37 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 07:20:55,626 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 07:21:13,095 INFO [train.py:742] (4/8) Epoch 15, validation: loss=0.1049, simple_loss=0.1887, pruned_loss=0.01057, over 914524.00 frames.
2022-05-08 07:21:54,019 INFO [train.py:715] (4/8) Epoch 15, batch 3050, loss[loss=0.1621, simple_loss=0.2365, pruned_loss=0.04385, over 4870.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03013, over 974677.20 frames.], batch size: 32, lr: 1.49e-04
2022-05-08 07:22:33,933 INFO [train.py:715] (4/8) Epoch 15, batch 3100, loss[loss=0.1413, simple_loss=0.2087, pruned_loss=0.03699, over 4823.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03005, over 974049.63 frames.], batch size: 26, lr: 1.49e-04
2022-05-08 07:23:14,650 INFO [train.py:715] (4/8) Epoch 15, batch 3150, loss[loss=0.135, simple_loss=0.2132, pruned_loss=0.02835, over 4836.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03086, over 973049.16 frames.], batch size: 15, lr: 1.49e-04
2022-05-08 07:23:55,195 INFO [train.py:715] (4/8) Epoch 15, batch 3200, loss[loss=0.144, simple_loss=0.2117, pruned_loss=0.03821, over 4782.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2096, pruned_loss=0.03106, over 972510.94 frames.], batch size: 17, lr: 1.49e-04
2022-05-08 07:24:35,381 INFO [train.py:715] (4/8) Epoch 15, batch 3250, loss[loss=0.1391, simple_loss=0.2111, pruned_loss=0.03356, over 4989.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2096, pruned_loss=0.03133, over 971942.02 frames.], batch size: 25, lr: 1.49e-04
2022-05-08 07:25:15,318 INFO [train.py:715] (4/8) Epoch 15, batch 3300, loss[loss=0.1423, simple_loss=0.2161, pruned_loss=0.03429, over 4967.00 frames.], tot_loss[loss=0.136, simple_loss=0.2099, pruned_loss=0.031, over 971771.77 frames.], batch size: 21, lr: 1.49e-04
2022-05-08 07:25:56,109 INFO [train.py:715] (4/8) Epoch 15, batch 3350, loss[loss=0.1433, simple_loss=0.2224, pruned_loss=0.03215, over 4862.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03082, over 971707.24 frames.], batch size: 20, lr: 1.49e-04
2022-05-08 07:26:36,431 INFO [train.py:715] (4/8) Epoch 15, batch 3400, loss[loss=0.145, simple_loss=0.2162, pruned_loss=0.03688, over 4810.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03073, over 971564.42 frames.], batch size: 21, lr: 1.49e-04
2022-05-08 07:27:16,661 INFO [train.py:715] (4/8) Epoch 15, batch 3450, loss[loss=0.1239, simple_loss=0.1913, pruned_loss=0.02826, over 4946.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03051, over 972102.75 frames.], batch size: 35, lr: 1.49e-04
2022-05-08 07:27:56,921 INFO [train.py:715] (4/8) Epoch 15, batch 3500, loss[loss=0.1473, simple_loss=0.2248, pruned_loss=0.0349, over 4931.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03037, over 971433.77 frames.], batch size: 23, lr: 1.49e-04
2022-05-08 07:28:37,333 INFO [train.py:715] (4/8) Epoch 15, batch 3550, loss[loss=0.1431, simple_loss=0.2102, pruned_loss=0.03803, over 4914.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03041, over 970916.00 frames.], batch size: 19, lr: 1.49e-04
2022-05-08 07:29:17,839 INFO [train.py:715] (4/8) Epoch 15, batch 3600, loss[loss=0.1677, simple_loss=0.2351, pruned_loss=0.05021, over 4922.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03025, over 971443.69 frames.], batch size: 18, lr: 1.49e-04
2022-05-08 07:29:57,636 INFO [train.py:715] (4/8) Epoch 15, batch 3650, loss[loss=0.1506, simple_loss=0.2122, pruned_loss=0.0445, over 4929.00 frames.], tot_loss[loss=0.135, simple_loss=0.2093, pruned_loss=0.03033, over 971642.92 frames.], batch size: 35, lr: 1.48e-04
2022-05-08 07:30:38,277 INFO [train.py:715] (4/8) Epoch 15, batch 3700, loss[loss=0.1481, simple_loss=0.219, pruned_loss=0.03863, over 4850.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.0303, over 972288.67 frames.], batch size: 20, lr: 1.48e-04
2022-05-08 07:31:19,136 INFO [train.py:715] (4/8) Epoch 15, batch 3750, loss[loss=0.1291, simple_loss=0.2136, pruned_loss=0.02228, over 4969.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02967, over 972023.07 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 07:31:58,792 INFO [train.py:715] (4/8) Epoch 15, batch 3800, loss[loss=0.1246, simple_loss=0.1998, pruned_loss=0.02469, over 4966.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02968, over 971551.76 frames.], batch size: 25, lr: 1.48e-04
2022-05-08 07:32:38,792 INFO [train.py:715] (4/8) Epoch 15, batch 3850, loss[loss=0.1273, simple_loss=0.1982, pruned_loss=0.02818, over 4868.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.02992, over 972442.28 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 07:33:19,078 INFO [train.py:715] (4/8) Epoch 15, batch 3900, loss[loss=0.1246, simple_loss=0.2005, pruned_loss=0.02433, over 4925.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02966, over 972503.74 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 07:33:58,247 INFO [train.py:715] (4/8) Epoch 15, batch 3950, loss[loss=0.1328, simple_loss=0.2008, pruned_loss=0.03236, over 4942.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02998, over 972745.46 frames.], batch size: 23, lr: 1.48e-04
2022-05-08 07:34:37,991 INFO [train.py:715] (4/8) Epoch 15, batch 4000, loss[loss=0.1284, simple_loss=0.2065, pruned_loss=0.02513, over 4988.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03013, over 972333.70 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 07:35:17,771 INFO [train.py:715] (4/8) Epoch 15, batch 4050, loss[loss=0.1283, simple_loss=0.21, pruned_loss=0.0233, over 4927.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2088, pruned_loss=0.02984, over 972126.90 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 07:35:58,779 INFO [train.py:715] (4/8) Epoch 15, batch 4100, loss[loss=0.1729, simple_loss=0.2414, pruned_loss=0.05226, over 4903.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2089, pruned_loss=0.02971, over 972641.29 frames.], batch size: 22, lr: 1.48e-04
2022-05-08 07:36:37,612 INFO [train.py:715] (4/8) Epoch 15, batch 4150, loss[loss=0.1344, simple_loss=0.2063, pruned_loss=0.03124, over 4937.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02972, over 972871.20 frames.], batch size: 29, lr: 1.48e-04
2022-05-08 07:37:17,773 INFO [train.py:715] (4/8) Epoch 15, batch 4200, loss[loss=0.1067, simple_loss=0.1822, pruned_loss=0.01561, over 4923.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02962, over 972308.27 frames.], batch size: 29, lr: 1.48e-04
2022-05-08 07:37:58,196 INFO [train.py:715] (4/8) Epoch 15, batch 4250, loss[loss=0.1093, simple_loss=0.1859, pruned_loss=0.01631, over 4887.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02967, over 972349.14 frames.], batch size: 22, lr: 1.48e-04
2022-05-08 07:38:38,217 INFO [train.py:715] (4/8) Epoch 15, batch 4300, loss[loss=0.1418, simple_loss=0.2072, pruned_loss=0.03824, over 4986.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02954, over 973168.94 frames.], batch size: 35, lr: 1.48e-04
2022-05-08 07:39:18,234 INFO [train.py:715] (4/8) Epoch 15, batch 4350, loss[loss=0.1365, simple_loss=0.2093, pruned_loss=0.03191, over 4962.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02943, over 972861.72 frames.], batch size: 35, lr: 1.48e-04
2022-05-08 07:39:58,271 INFO [train.py:715] (4/8) Epoch 15, batch 4400, loss[loss=0.1445, simple_loss=0.2112, pruned_loss=0.03889, over 4978.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.0294, over 972931.33 frames.], batch size: 20, lr: 1.48e-04
2022-05-08 07:40:38,798 INFO [train.py:715] (4/8) Epoch 15, batch 4450, loss[loss=0.1329, simple_loss=0.2078, pruned_loss=0.02895, over 4831.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02959, over 972770.14 frames.], batch size: 25, lr: 1.48e-04
2022-05-08 07:41:18,468 INFO [train.py:715] (4/8) Epoch 15, batch 4500, loss[loss=0.1176, simple_loss=0.1942, pruned_loss=0.02053, over 4814.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02948, over 972731.30 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 07:41:58,876 INFO [train.py:715] (4/8) Epoch 15, batch 4550, loss[loss=0.1438, simple_loss=0.2214, pruned_loss=0.03308, over 4902.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.0297, over 973249.46 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 07:42:39,493 INFO [train.py:715] (4/8) Epoch 15, batch 4600, loss[loss=0.1284, simple_loss=0.2087, pruned_loss=0.02404, over 4900.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02979, over 972779.58 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 07:43:19,666 INFO [train.py:715] (4/8) Epoch 15, batch 4650, loss[loss=0.1467, simple_loss=0.2084, pruned_loss=0.04244, over 4799.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02979, over 971368.07 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 07:43:59,051 INFO [train.py:715] (4/8) Epoch 15, batch 4700, loss[loss=0.1303, simple_loss=0.2067, pruned_loss=0.02698, over 4806.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02985, over 970798.25 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 07:44:39,326 INFO [train.py:715] (4/8) Epoch 15, batch 4750, loss[loss=0.1382, simple_loss=0.2183, pruned_loss=0.02909, over 4874.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.02994, over 970820.31 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 07:45:20,567 INFO [train.py:715] (4/8) Epoch 15, batch 4800, loss[loss=0.1499, simple_loss=0.2304, pruned_loss=0.03467, over 4925.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03018, over 971382.03 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 07:46:00,524 INFO [train.py:715] (4/8) Epoch 15, batch 4850, loss[loss=0.1234, simple_loss=0.1968, pruned_loss=0.025, over 4687.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02951, over 971102.05 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 07:46:41,240 INFO [train.py:715] (4/8) Epoch 15, batch 4900, loss[loss=0.1684, simple_loss=0.2404, pruned_loss=0.04821, over 4893.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02959, over 971836.14 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 07:47:21,680 INFO [train.py:715] (4/8) Epoch 15, batch 4950, loss[loss=0.1246, simple_loss=0.1987, pruned_loss=0.02527, over 4988.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2073, pruned_loss=0.03015, over 972155.90 frames.], batch size: 25, lr: 1.48e-04
2022-05-08 07:48:02,262 INFO [train.py:715] (4/8) Epoch 15, batch 5000, loss[loss=0.1382, simple_loss=0.2047, pruned_loss=0.03587, over 4843.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.03007, over 971936.55 frames.], batch size: 13, lr: 1.48e-04
2022-05-08 07:48:41,753 INFO [train.py:715] (4/8) Epoch 15, batch 5050, loss[loss=0.1292, simple_loss=0.2095, pruned_loss=0.02444, over 4908.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03063, over 972400.95 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 07:49:21,839 INFO [train.py:715] (4/8) Epoch 15, batch 5100, loss[loss=0.1384, simple_loss=0.218, pruned_loss=0.02935, over 4951.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03035, over 973823.12 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 07:50:02,143 INFO [train.py:715] (4/8) Epoch 15, batch 5150, loss[loss=0.1468, simple_loss=0.2255, pruned_loss=0.03408, over 4789.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.03, over 973832.08 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 07:50:42,064 INFO [train.py:715] (4/8) Epoch 15, batch 5200, loss[loss=0.1473, simple_loss=0.2279, pruned_loss=0.03332, over 4933.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.02998, over 973266.14 frames.], batch size: 23, lr: 1.48e-04
2022-05-08 07:51:22,085 INFO [train.py:715] (4/8) Epoch 15, batch 5250, loss[loss=0.136, simple_loss=0.2094, pruned_loss=0.03123, over 4800.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02985, over 973300.48 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 07:52:03,627 INFO [train.py:715] (4/8) Epoch 15, batch 5300, loss[loss=0.1156, simple_loss=0.1808, pruned_loss=0.0252, over 4786.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03012, over 972947.70 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 07:52:45,865 INFO [train.py:715] (4/8) Epoch 15, batch 5350, loss[loss=0.1409, simple_loss=0.217, pruned_loss=0.0324, over 4860.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02991, over 973106.34 frames.], batch size: 20, lr: 1.48e-04
2022-05-08 07:53:26,855 INFO [train.py:715] (4/8) Epoch 15, batch 5400, loss[loss=0.1502, simple_loss=0.2201, pruned_loss=0.04018, over 4947.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.03043, over 973031.48 frames.], batch size: 21, lr: 1.48e-04
2022-05-08 07:54:08,830 INFO [train.py:715] (4/8) Epoch 15, batch 5450, loss[loss=0.1409, simple_loss=0.2132, pruned_loss=0.0343, over 4927.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03073, over 972284.61 frames.], batch size: 23, lr: 1.48e-04
2022-05-08 07:54:50,462 INFO [train.py:715] (4/8) Epoch 15, batch 5500, loss[loss=0.1485, simple_loss=0.2267, pruned_loss=0.0351, over 4960.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.0304, over 972893.27 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 07:55:32,151 INFO [train.py:715] (4/8) Epoch 15, batch 5550, loss[loss=0.1354, simple_loss=0.2077, pruned_loss=0.03151, over 4691.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.03048, over 972970.83 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 07:56:12,918 INFO [train.py:715] (4/8) Epoch 15, batch 5600, loss[loss=0.1148, simple_loss=0.1889, pruned_loss=0.02035, over 4779.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03044, over 972764.30 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 07:56:54,797 INFO [train.py:715] (4/8) Epoch 15, batch 5650, loss[loss=0.1162, simple_loss=0.1971, pruned_loss=0.0176, over 4802.00 frames.], tot_loss[loss=0.134, simple_loss=0.2074, pruned_loss=0.03026, over 971341.89 frames.], batch size: 26, lr: 1.48e-04
2022-05-08 07:57:37,293 INFO [train.py:715] (4/8) Epoch 15, batch 5700, loss[loss=0.1404, simple_loss=0.2017, pruned_loss=0.03961, over 4863.00 frames.], tot_loss[loss=0.134, simple_loss=0.2073, pruned_loss=0.0303, over 971710.68 frames.], batch size: 30, lr: 1.48e-04
2022-05-08 07:58:18,520 INFO [train.py:715] (4/8) Epoch 15, batch 5750, loss[loss=0.1472, simple_loss=0.234, pruned_loss=0.03025, over 4938.00 frames.], tot_loss[loss=0.135, simple_loss=0.2083, pruned_loss=0.03085, over 972863.21 frames.], batch size: 23, lr: 1.48e-04
2022-05-08 07:58:59,971 INFO [train.py:715] (4/8) Epoch 15, batch 5800, loss[loss=0.1148, simple_loss=0.1868, pruned_loss=0.02142, over 4939.00 frames.], tot_loss[loss=0.135, simple_loss=0.2082, pruned_loss=0.03087, over 972769.34 frames.], batch size: 35, lr: 1.48e-04
2022-05-08 07:59:41,226 INFO [train.py:715] (4/8) Epoch 15, batch 5850, loss[loss=0.1408, simple_loss=0.2187, pruned_loss=0.03142, over 4793.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2077, pruned_loss=0.03065, over 972853.29 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:00:25,528 INFO [train.py:715] (4/8) Epoch 15, batch 5900, loss[loss=0.1336, simple_loss=0.2094, pruned_loss=0.02888, over 4767.00 frames.], tot_loss[loss=0.134, simple_loss=0.2074, pruned_loss=0.03031, over 973276.20 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:01:06,122 INFO [train.py:715] (4/8) Epoch 15, batch 5950, loss[loss=0.1453, simple_loss=0.2113, pruned_loss=0.03961, over 4902.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2068, pruned_loss=0.02977, over 973028.52 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:01:47,589 INFO [train.py:715] (4/8) Epoch 15, batch 6000, loss[loss=0.1302, simple_loss=0.2047, pruned_loss=0.02787, over 4863.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02979, over 973443.29 frames.], batch size: 13, lr: 1.48e-04
2022-05-08 08:01:47,590 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 08:01:57,157 INFO [train.py:742] (4/8) Epoch 15, validation: loss=0.1051, simple_loss=0.1887, pruned_loss=0.01077, over 914524.00 frames.
2022-05-08 08:02:38,326 INFO [train.py:715] (4/8) Epoch 15, batch 6050, loss[loss=0.1447, simple_loss=0.207, pruned_loss=0.04121, over 4853.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02947, over 972887.51 frames.], batch size: 32, lr: 1.48e-04
2022-05-08 08:03:20,396 INFO [train.py:715] (4/8) Epoch 15, batch 6100, loss[loss=0.1445, simple_loss=0.2246, pruned_loss=0.03222, over 4931.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03015, over 973148.69 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:04:00,151 INFO [train.py:715] (4/8) Epoch 15, batch 6150, loss[loss=0.145, simple_loss=0.2187, pruned_loss=0.03568, over 4993.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03027, over 973443.12 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:04:41,028 INFO [train.py:715] (4/8) Epoch 15, batch 6200, loss[loss=0.1266, simple_loss=0.2025, pruned_loss=0.02538, over 4944.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02985, over 973935.22 frames.], batch size: 21, lr: 1.48e-04
2022-05-08 08:05:20,632 INFO [train.py:715] (4/8) Epoch 15, batch 6250, loss[loss=0.1308, simple_loss=0.1986, pruned_loss=0.0315, over 4701.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03007, over 973382.08 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 08:06:01,387 INFO [train.py:715] (4/8) Epoch 15, batch 6300, loss[loss=0.1148, simple_loss=0.1903, pruned_loss=0.01963, over 4778.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2062, pruned_loss=0.02959, over 973591.59 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 08:06:41,223 INFO [train.py:715] (4/8) Epoch 15, batch 6350, loss[loss=0.1106, simple_loss=0.1915, pruned_loss=0.01481, over 4983.00 frames.], tot_loss[loss=0.1335, simple_loss=0.207, pruned_loss=0.02996, over 973921.89 frames.], batch size: 28, lr: 1.48e-04
2022-05-08 08:07:21,267 INFO [train.py:715] (4/8) Epoch 15, batch 6400, loss[loss=0.1301, simple_loss=0.2059, pruned_loss=0.02722, over 4930.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03064, over 973269.26 frames.], batch size: 29, lr: 1.48e-04
2022-05-08 08:08:01,841 INFO [train.py:715] (4/8) Epoch 15, batch 6450, loss[loss=0.1405, simple_loss=0.2221, pruned_loss=0.02948, over 4774.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03036, over 973390.83 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:08:41,384 INFO [train.py:715] (4/8) Epoch 15, batch 6500, loss[loss=0.1374, simple_loss=0.2171, pruned_loss=0.02891, over 4934.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.03051, over 973684.33 frames.], batch size: 29, lr: 1.48e-04
2022-05-08 08:09:21,807 INFO [train.py:715] (4/8) Epoch 15, batch 6550, loss[loss=0.1388, simple_loss=0.2174, pruned_loss=0.03015, over 4742.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.0304, over 972355.92 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:10:02,124 INFO [train.py:715] (4/8) Epoch 15, batch 6600, loss[loss=0.1421, simple_loss=0.2168, pruned_loss=0.03373, over 4774.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03074, over 972724.48 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 08:10:42,805 INFO [train.py:715] (4/8) Epoch 15, batch 6650, loss[loss=0.1232, simple_loss=0.1976, pruned_loss=0.02439, over 4876.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03086, over 972210.27 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:11:22,254 INFO [train.py:715] (4/8) Epoch 15, batch 6700, loss[loss=0.1694, simple_loss=0.2355, pruned_loss=0.05167, over 4855.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.03038, over 972634.23 frames.], batch size: 32, lr: 1.48e-04
2022-05-08 08:12:02,753 INFO [train.py:715] (4/8) Epoch 15, batch 6750, loss[loss=0.1224, simple_loss=0.1912, pruned_loss=0.02676, over 4847.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03001, over 972710.17 frames.], batch size: 32, lr: 1.48e-04
2022-05-08 08:12:44,109 INFO [train.py:715] (4/8) Epoch 15, batch 6800, loss[loss=0.1341, simple_loss=0.2098, pruned_loss=0.0292, over 4896.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.02995, over 973058.88 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:13:23,942 INFO [train.py:715] (4/8) Epoch 15, batch 6850, loss[loss=0.1252, simple_loss=0.199, pruned_loss=0.0257, over 4867.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.03006, over 972986.96 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:14:03,536 INFO [train.py:715] (4/8) Epoch 15, batch 6900, loss[loss=0.1363, simple_loss=0.2124, pruned_loss=0.03007, over 4873.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2074, pruned_loss=0.03037, over 972401.65 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:14:44,358 INFO [train.py:715] (4/8) Epoch 15, batch 6950, loss[loss=0.1128, simple_loss=0.1949, pruned_loss=0.01536, over 4828.00 frames.], tot_loss[loss=0.1346, simple_loss=0.208, pruned_loss=0.03061, over 972413.84 frames.], batch size: 26, lr: 1.48e-04
2022-05-08 08:15:24,996 INFO [train.py:715] (4/8) Epoch 15, batch 7000, loss[loss=0.1581, simple_loss=0.2401, pruned_loss=0.03806, over 4831.00 frames.], tot_loss[loss=0.134, simple_loss=0.2077, pruned_loss=0.03019, over 972837.37 frames.], batch size: 26, lr: 1.48e-04
2022-05-08 08:16:03,953 INFO [train.py:715] (4/8) Epoch 15, batch 7050, loss[loss=0.1334, simple_loss=0.216, pruned_loss=0.0254, over 4904.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03003, over 972801.30 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:16:44,705 INFO [train.py:715] (4/8) Epoch 15, batch 7100, loss[loss=0.1261, simple_loss=0.1941, pruned_loss=0.02899, over 4741.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03034, over 972227.60 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:17:25,230 INFO [train.py:715] (4/8) Epoch 15, batch 7150, loss[loss=0.1434, simple_loss=0.1971, pruned_loss=0.04486, over 4641.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2073, pruned_loss=0.02997, over 972313.66 frames.], batch size: 13, lr: 1.48e-04
2022-05-08 08:18:05,127 INFO [train.py:715] (4/8) Epoch 15, batch 7200, loss[loss=0.1197, simple_loss=0.1879, pruned_loss=0.02581, over 4795.00 frames.], tot_loss[loss=0.1346, simple_loss=0.208, pruned_loss=0.03062, over 972017.85 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 08:18:44,333 INFO [train.py:715] (4/8) Epoch 15, batch 7250, loss[loss=0.1235, simple_loss=0.1956, pruned_loss=0.0257, over 4926.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03099, over 973188.35 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:19:25,086 INFO [train.py:715] (4/8) Epoch 15, batch 7300, loss[loss=0.1512, simple_loss=0.2222, pruned_loss=0.04011, over 4831.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.0307, over 973489.54 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:20:06,075 INFO [train.py:715] (4/8) Epoch 15, batch 7350, loss[loss=0.1712, simple_loss=0.2359, pruned_loss=0.05327, over 4824.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2086, pruned_loss=0.03114, over 973263.96 frames.], batch size: 30, lr: 1.48e-04
2022-05-08 08:20:45,510 INFO [train.py:715] (4/8) Epoch 15, batch 7400, loss[loss=0.1096, simple_loss=0.1903, pruned_loss=0.01442, over 4868.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03032, over 973530.33 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:21:25,982 INFO [train.py:715] (4/8) Epoch 15, batch 7450, loss[loss=0.1413, simple_loss=0.217, pruned_loss=0.0328, over 4920.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03006, over 973602.24 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:22:06,367 INFO [train.py:715] (4/8) Epoch 15, batch 7500, loss[loss=0.1217, simple_loss=0.2065, pruned_loss=0.01847, over 4934.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03018, over 973735.32 frames.], batch size: 39, lr: 1.48e-04
2022-05-08 08:22:46,660 INFO [train.py:715] (4/8) Epoch 15, batch 7550, loss[loss=0.1093, simple_loss=0.1769, pruned_loss=0.02087, over 4865.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03002, over 973656.86 frames.], batch size: 20, lr: 1.48e-04
2022-05-08 08:23:25,901 INFO [train.py:715] (4/8) Epoch 15, batch 7600, loss[loss=0.1102, simple_loss=0.1835, pruned_loss=0.01848, over 4970.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2069, pruned_loss=0.03003, over 973818.85 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 08:24:05,909 INFO [train.py:715] (4/8) Epoch 15, batch 7650, loss[loss=0.1323, simple_loss=0.2044, pruned_loss=0.03008, over 4849.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2079, pruned_loss=0.03033, over 973395.70 frames.], batch size: 30, lr: 1.48e-04
2022-05-08 08:24:45,955 INFO [train.py:715] (4/8) Epoch 15, batch 7700, loss[loss=0.1393, simple_loss=0.2079, pruned_loss=0.0353, over 4781.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.03053, over 973325.95 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 08:25:24,893 INFO [train.py:715] (4/8) Epoch 15, batch 7750, loss[loss=0.1431, simple_loss=0.2097, pruned_loss=0.03819, over 4851.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2081, pruned_loss=0.03049, over 972559.03 frames.], batch size: 20, lr: 1.48e-04
2022-05-08 08:26:04,531 INFO [train.py:715] (4/8) Epoch 15, batch 7800, loss[loss=0.15, simple_loss=0.2195, pruned_loss=0.0403, over 4983.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03, over 972845.36 frames.], batch size: 35, lr: 1.48e-04
2022-05-08 08:26:43,768 INFO [train.py:715] (4/8) Epoch 15, batch 7850, loss[loss=0.1412, simple_loss=0.2169, pruned_loss=0.03276, over 4797.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.02997, over 973084.95 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 08:27:23,764 INFO [train.py:715] (4/8) Epoch 15, batch 7900, loss[loss=0.1534, simple_loss=0.2345, pruned_loss=0.03616, over 4724.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02991, over 972594.36 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:28:01,916 INFO [train.py:715] (4/8) Epoch 15, batch 7950, loss[loss=0.1306, simple_loss=0.2046, pruned_loss=0.02832, over 4956.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03026, over 973074.89 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:28:41,234 INFO [train.py:715] (4/8) Epoch 15, batch 8000, loss[loss=0.1288, simple_loss=0.2216, pruned_loss=0.01796, over 4975.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2096, pruned_loss=0.0305, over 972682.01 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 08:29:20,814 INFO [train.py:715] (4/8) Epoch 15, batch 8050, loss[loss=0.1286, simple_loss=0.212, pruned_loss=0.02255, over 4948.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03089, over 972278.48 frames.], batch size: 29, lr: 1.48e-04
2022-05-08 08:29:59,782 INFO [train.py:715] (4/8) Epoch 15, batch 8100, loss[loss=0.1249, simple_loss=0.2017, pruned_loss=0.0241, over 4811.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03062, over 972004.13 frames.], batch size: 26, lr: 1.48e-04
2022-05-08 08:30:38,779 INFO [train.py:715] (4/8) Epoch 15, batch 8150, loss[loss=0.116, simple_loss=0.1914, pruned_loss=0.02035, over 4923.00 frames.], tot_loss[loss=0.135, simple_loss=0.2086, pruned_loss=0.03072, over 971714.54 frames.], batch size: 29, lr: 1.48e-04
2022-05-08 08:31:18,841 INFO [train.py:715] (4/8) Epoch 15, batch 8200, loss[loss=0.1275, simple_loss=0.2127, pruned_loss=0.02114, over 4899.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03051, over 972708.89 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:31:57,572 INFO [train.py:715] (4/8) Epoch 15, batch 8250, loss[loss=0.1294, simple_loss=0.203, pruned_loss=0.02786, over 4773.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.03047, over 972885.89 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:32:36,547 INFO [train.py:715] (4/8) Epoch 15, batch 8300, loss[loss=0.1621, simple_loss=0.2374, pruned_loss=0.04337, over 4934.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03049, over 973373.36 frames.], batch size: 39, lr: 1.48e-04
2022-05-08 08:33:15,772 INFO [train.py:715] (4/8) Epoch 15, batch 8350, loss[loss=0.1289, simple_loss=0.1981, pruned_loss=0.0299, over 4797.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03019, over 972954.39 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 08:33:55,968 INFO [train.py:715] (4/8) Epoch 15, batch 8400, loss[loss=0.1265, simple_loss=0.2034, pruned_loss=0.02485, over 4899.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03032, over 972835.16 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:34:35,507 INFO [train.py:715] (4/8) Epoch 15, batch 8450, loss[loss=0.1277, simple_loss=0.2025, pruned_loss=0.02642, over 4960.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03063, over 973583.73 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 08:35:14,647 INFO [train.py:715] (4/8) Epoch 15, batch 8500, loss[loss=0.1267, simple_loss=0.1941, pruned_loss=0.0297, over 4980.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03069, over 974409.01 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 08:35:54,836 INFO [train.py:715] (4/8) Epoch 15, batch 8550, loss[loss=0.1497, simple_loss=0.2224, pruned_loss=0.03846, over 4980.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03061, over 975143.24 frames.], batch size: 25, lr: 1.48e-04
2022-05-08 08:36:33,509 INFO [train.py:715] (4/8) Epoch 15, batch 8600, loss[loss=0.1273, simple_loss=0.2014, pruned_loss=0.02659, over 4770.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2097, pruned_loss=0.03052, over 974761.86 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:37:12,322 INFO [train.py:715] (4/8) Epoch 15, batch 8650, loss[loss=0.1436, simple_loss=0.2185, pruned_loss=0.03432, over 4773.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03072, over 973658.33 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:37:51,174 INFO [train.py:715] (4/8) Epoch 15, batch 8700, loss[loss=0.1226, simple_loss=0.1962, pruned_loss=0.0245, over 4776.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03067, over 973993.23 frames.], batch size: 17, lr: 1.48e-04
2022-05-08 08:38:30,424 INFO [train.py:715] (4/8) Epoch 15, batch 8750, loss[loss=0.1243, simple_loss=0.1932, pruned_loss=0.0277, over 4858.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03063, over 973830.50 frames.], batch size: 20, lr: 1.48e-04
2022-05-08 08:39:08,910 INFO [train.py:715] (4/8) Epoch 15, batch 8800, loss[loss=0.1332, simple_loss=0.1964, pruned_loss=0.03499, over 4692.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.0305, over 974161.27 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:39:47,401 INFO [train.py:715] (4/8) Epoch 15, batch 8850, loss[loss=0.1081, simple_loss=0.1707, pruned_loss=0.02275, over 4811.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03035, over 974177.81 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 08:40:26,824 INFO [train.py:715] (4/8) Epoch 15, batch 8900, loss[loss=0.155, simple_loss=0.2251, pruned_loss=0.04243, over 4991.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2077, pruned_loss=0.03052, over 973409.70 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 08:41:06,359 INFO [train.py:715] (4/8) Epoch 15, batch 8950, loss[loss=0.139, simple_loss=0.2104, pruned_loss=0.03385, over 4933.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.031, over 973376.29 frames.], batch size: 29, lr: 1.48e-04
2022-05-08 08:41:45,472 INFO [train.py:715] (4/8) Epoch 15, batch 9000, loss[loss=0.1635, simple_loss=0.2383, pruned_loss=0.04438, over 4968.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03094, over 974184.66 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:41:45,473 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 08:42:05,028 INFO [train.py:742] (4/8) Epoch 15, validation: loss=0.1051, simple_loss=0.1887, pruned_loss=0.01074, over 914524.00 frames.
2022-05-08 08:42:44,047 INFO [train.py:715] (4/8) Epoch 15, batch 9050, loss[loss=0.1194, simple_loss=0.1996, pruned_loss=0.01957, over 4968.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.03072, over 973383.52 frames.], batch size: 25, lr: 1.48e-04
2022-05-08 08:43:23,566 INFO [train.py:715] (4/8) Epoch 15, batch 9100, loss[loss=0.128, simple_loss=0.209, pruned_loss=0.02349, over 4918.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03023, over 972576.55 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:44:03,261 INFO [train.py:715] (4/8) Epoch 15, batch 9150, loss[loss=0.122, simple_loss=0.2044, pruned_loss=0.01982, over 4744.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03047, over 972541.39 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:44:42,056 INFO [train.py:715] (4/8) Epoch 15, batch 9200, loss[loss=0.1269, simple_loss=0.21, pruned_loss=0.02194, over 4755.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03063, over 971984.81 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:45:21,336 INFO [train.py:715] (4/8) Epoch 15, batch 9250, loss[loss=0.1307, simple_loss=0.2001, pruned_loss=0.03067, over 4882.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2093, pruned_loss=0.03064, over 972191.62 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 08:46:01,215 INFO [train.py:715] (4/8) Epoch 15, batch 9300, loss[loss=0.1184, simple_loss=0.1961, pruned_loss=0.02031, over 4980.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03058, over 972300.76 frames.], batch size: 28, lr: 1.48e-04
2022-05-08 08:46:41,139 INFO [train.py:715] (4/8) Epoch 15, batch 9350, loss[loss=0.1049, simple_loss=0.1653, pruned_loss=0.02227, over 4825.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03049, over 972683.15 frames.], batch size: 12, lr: 1.48e-04
2022-05-08 08:47:19,984 INFO [train.py:715] (4/8) Epoch 15, batch 9400, loss[loss=0.1536, simple_loss=0.2274, pruned_loss=0.03991, over 4812.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03106, over 972854.77 frames.], batch size: 26, lr: 1.48e-04
2022-05-08 08:47:59,298 INFO [train.py:715] (4/8) Epoch 15, batch 9450, loss[loss=0.1484, simple_loss=0.2129, pruned_loss=0.04201, over 4778.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03092, over 972900.76 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:48:38,584 INFO [train.py:715] (4/8) Epoch 15, batch 9500, loss[loss=0.1461, simple_loss=0.2172, pruned_loss=0.03747, over 4945.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2091, pruned_loss=0.03119, over 973892.49 frames.], batch size: 21, lr: 1.48e-04
2022-05-08 08:49:16,966 INFO [train.py:715] (4/8) Epoch 15, batch 9550, loss[loss=0.1583, simple_loss=0.2314, pruned_loss=0.04265, over 4990.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2094, pruned_loss=0.03098, over 973715.80 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:49:56,302 INFO [train.py:715] (4/8) Epoch 15, batch 9600, loss[loss=0.1304, simple_loss=0.2067, pruned_loss=0.02705, over 4921.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2086, pruned_loss=0.03081, over 973570.12 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:50:35,891 INFO [train.py:715] (4/8) Epoch 15, batch 9650, loss[loss=0.1462, simple_loss=0.2202, pruned_loss=0.03611, over 4908.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2083, pruned_loss=0.0306, over 973022.40 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:51:15,438 INFO [train.py:715] (4/8) Epoch 15, batch 9700, loss[loss=0.1378, simple_loss=0.2146, pruned_loss=0.03048, over 4700.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02973, over 972225.87 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:51:53,982 INFO [train.py:715] (4/8) Epoch 15, batch 9750, loss[loss=0.1364, simple_loss=0.2094, pruned_loss=0.03164, over 4895.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02971, over 972577.97 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:52:33,225 INFO [train.py:715] (4/8) Epoch 15, batch 9800, loss[loss=0.1159, simple_loss=0.1897, pruned_loss=0.021, over 4929.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02963, over 972325.84 frames.], batch size: 23, lr: 1.48e-04
2022-05-08 08:53:12,403 INFO [train.py:715] (4/8) Epoch 15, batch 9850, loss[loss=0.1297, simple_loss=0.2089, pruned_loss=0.02528, over 4810.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02971, over 971629.69 frames.], batch size: 26, lr: 1.48e-04
2022-05-08 08:53:51,006 INFO [train.py:715] (4/8) Epoch 15, batch 9900, loss[loss=0.1836, simple_loss=0.2512, pruned_loss=0.05796, over 4918.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03026, over 972681.24 frames.], batch size: 18, lr: 1.48e-04
2022-05-08 08:54:30,412 INFO [train.py:715] (4/8) Epoch 15, batch 9950, loss[loss=0.1358, simple_loss=0.213, pruned_loss=0.02923, over 4865.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2091, pruned_loss=0.02991, over 973751.62 frames.], batch size: 20, lr: 1.48e-04
2022-05-08 08:55:09,381 INFO [train.py:715] (4/8) Epoch 15, batch 10000, loss[loss=0.1277, simple_loss=0.2006, pruned_loss=0.0274, over 4826.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03015, over 973462.95 frames.], batch size: 15, lr: 1.48e-04
2022-05-08 08:55:48,594 INFO [train.py:715] (4/8) Epoch 15, batch 10050, loss[loss=0.1367, simple_loss=0.2073, pruned_loss=0.033, over 4830.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02992, over 973145.27 frames.], batch size: 13, lr: 1.48e-04
2022-05-08 08:56:26,955 INFO [train.py:715] (4/8) Epoch 15, batch 10100, loss[loss=0.1387, simple_loss=0.2114, pruned_loss=0.03297, over 4976.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03007, over 972566.40 frames.], batch size: 35, lr: 1.48e-04
2022-05-08 08:57:05,755 INFO [train.py:715] (4/8) Epoch 15, batch 10150, loss[loss=0.1363, simple_loss=0.2132, pruned_loss=0.0297, over 4800.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03012, over 973338.62 frames.], batch size: 25, lr: 1.48e-04
2022-05-08 08:57:45,595 INFO [train.py:715] (4/8) Epoch 15, batch 10200, loss[loss=0.1202, simple_loss=0.1921, pruned_loss=0.02417, over 4893.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02945, over 973319.77 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:58:23,918 INFO [train.py:715] (4/8) Epoch 15, batch 10250, loss[loss=0.1292, simple_loss=0.2073, pruned_loss=0.0255, over 4752.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02949, over 972684.56 frames.], batch size: 19, lr: 1.48e-04
2022-05-08 08:59:03,214 INFO [train.py:715] (4/8) Epoch 15, batch 10300, loss[loss=0.1383, simple_loss=0.1991, pruned_loss=0.03873, over 4775.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02929, over 972026.10 frames.], batch size: 14, lr: 1.48e-04
2022-05-08 08:59:42,674 INFO [train.py:715] (4/8) Epoch 15, batch 10350, loss[loss=0.1425, simple_loss=0.2137, pruned_loss=0.03568, over 4871.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02983, over 972387.88 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 09:00:21,801 INFO [train.py:715] (4/8) Epoch 15, batch 10400, loss[loss=0.1261, simple_loss=0.1913, pruned_loss=0.03049, over 4978.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03014, over 971749.38 frames.], batch size: 28, lr: 1.48e-04
2022-05-08 09:00:59,815 INFO [train.py:715] (4/8) Epoch 15, batch 10450, loss[loss=0.1281, simple_loss=0.2101, pruned_loss=0.02308, over 4869.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.02998, over 971420.79 frames.], batch size: 22, lr: 1.48e-04
2022-05-08 09:01:38,798 INFO [train.py:715] (4/8) Epoch 15, batch 10500, loss[loss=0.1423, simple_loss=0.215, pruned_loss=0.0348, over 4937.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2071, pruned_loss=0.02995, over 971886.31 frames.], batch size: 29, lr: 1.48e-04
2022-05-08 09:02:18,510 INFO [train.py:715] (4/8) Epoch 15, batch 10550, loss[loss=0.1391, simple_loss=0.2152, pruned_loss=0.03155, over 4872.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02999, over 971879.26 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 09:02:56,675 INFO [train.py:715] (4/8) Epoch 15, batch 10600, loss[loss=0.1261, simple_loss=0.2047, pruned_loss=0.02374, over 4949.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03002, over 973327.65 frames.], batch size: 21, lr: 1.48e-04
2022-05-08 09:03:35,330 INFO [train.py:715] (4/8) Epoch 15, batch 10650, loss[loss=0.1397, simple_loss=0.222, pruned_loss=0.02866, over 4759.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02986, over 973022.53 frames.], batch size: 16, lr: 1.48e-04
2022-05-08 09:04:14,410 INFO [train.py:715] (4/8) Epoch 15, batch 10700, loss[loss=0.1158, simple_loss=0.1934, pruned_loss=0.01905, over 4961.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02936, over 973070.38 frames.], batch size: 24, lr: 1.48e-04
2022-05-08 09:04:53,620 INFO [train.py:715] (4/8) Epoch 15, batch 10750, loss[loss=0.1368, simple_loss=0.2138, pruned_loss=0.02991, over 4858.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.0295, over 973893.54 frames.], batch size: 38, lr: 1.48e-04
2022-05-08 09:05:31,569 INFO [train.py:715] (4/8) Epoch 15, batch 10800, loss[loss=0.1767, simple_loss=0.2442, pruned_loss=0.0546, over 4874.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02935, over 973575.76 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 09:06:11,120 INFO [train.py:715] (4/8) Epoch 15, batch 10850, loss[loss=0.1302, simple_loss=0.1993, pruned_loss=0.0306, over 4865.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02953, over 972945.70 frames.], batch size: 30, lr: 1.47e-04
2022-05-08 09:06:50,381 INFO [train.py:715] (4/8) Epoch 15, batch 10900, loss[loss=0.1388, simple_loss=0.2142, pruned_loss=0.03169, over 4917.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02949, over 972596.66 frames.], batch size: 39, lr: 1.47e-04
2022-05-08 09:07:28,750 INFO [train.py:715] (4/8) Epoch 15, batch 10950, loss[loss=0.1357, simple_loss=0.2087, pruned_loss=0.03133, over 4842.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02924, over 973290.36 frames.], batch size: 30, lr: 1.47e-04
2022-05-08 09:08:06,751 INFO [train.py:715] (4/8) Epoch 15, batch 11000, loss[loss=0.1256, simple_loss=0.2035, pruned_loss=0.02385, over 4924.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02937, over 973356.51 frames.], batch size: 29, lr: 1.47e-04
2022-05-08 09:08:45,832 INFO [train.py:715] (4/8) Epoch 15, batch 11050, loss[loss=0.1477, simple_loss=0.2317, pruned_loss=0.03181, over 4966.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02964, over 973307.31 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 09:09:25,312 INFO [train.py:715] (4/8) Epoch 15, batch 11100, loss[loss=0.1108, simple_loss=0.1808, pruned_loss=0.02039, over 4920.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2061, pruned_loss=0.02932, over 972522.32 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 09:10:03,217 INFO [train.py:715] (4/8) Epoch 15, batch 11150, loss[loss=0.124, simple_loss=0.2048, pruned_loss=0.02159, over 4956.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02885, over 972751.67 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 09:10:41,862 INFO [train.py:715] (4/8) Epoch 15, batch 11200, loss[loss=0.1241, simple_loss=0.2019, pruned_loss=0.02309, over 4992.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2064, pruned_loss=0.0295, over 972356.83 frames.], batch size: 14, lr: 1.47e-04
2022-05-08 09:11:20,805 INFO [train.py:715] (4/8) Epoch 15, batch 11250, loss[loss=0.1491, simple_loss=0.2202, pruned_loss=0.03902, over 4741.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2062, pruned_loss=0.02946, over 972234.12 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 09:11:59,325 INFO [train.py:715] (4/8) Epoch 15, batch 11300, loss[loss=0.1364, simple_loss=0.1994, pruned_loss=0.03669, over 4828.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2067, pruned_loss=0.03002, over 972725.96 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 09:12:37,829 INFO [train.py:715] (4/8) Epoch 15, batch 11350, loss[loss=0.1349, simple_loss=0.2104, pruned_loss=0.0297, over 4876.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2066, pruned_loss=0.0299, over 973170.29 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 09:13:17,184 INFO [train.py:715] (4/8) Epoch 15, batch 11400, loss[loss=0.1365, simple_loss=0.2145, pruned_loss=0.02925, over 4813.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2069, pruned_loss=0.02984, over 973263.39 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:13:55,475 INFO [train.py:715] (4/8) Epoch 15, batch 11450, loss[loss=0.1416, simple_loss=0.2158, pruned_loss=0.03367, over 4856.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02989, over 973079.40 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 09:14:34,167 INFO [train.py:715] (4/8) Epoch 15, batch 11500, loss[loss=0.1211, simple_loss=0.1805, pruned_loss=0.03088, over 4855.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03037, over 972370.47 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:15:13,142 INFO [train.py:715] (4/8) Epoch 15, batch 11550, loss[loss=0.1439, simple_loss=0.2149, pruned_loss=0.03641, over 4774.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02995, over 971861.66 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 09:15:52,412 INFO [train.py:715] (4/8) Epoch 15, batch 11600, loss[loss=0.1382, simple_loss=0.2046, pruned_loss=0.03588, over 4837.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02989, over 971075.38 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:16:30,746 INFO [train.py:715] (4/8) Epoch 15, batch 11650, loss[loss=0.1521, simple_loss=0.2234, pruned_loss=0.04033, over 4897.00 frames.], tot_loss[loss=0.133, simple_loss=0.2066, pruned_loss=0.02971, over 971205.87 frames.], batch size: 22, lr: 1.47e-04
2022-05-08 09:17:09,221 INFO [train.py:715] (4/8) Epoch 15, batch 11700, loss[loss=0.1208, simple_loss=0.2058, pruned_loss=0.01787, over 4928.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2066, pruned_loss=0.0299, over 971987.56 frames.], batch size: 29, lr: 1.47e-04
2022-05-08 09:17:48,438 INFO [train.py:715] (4/8) Epoch 15, batch 11750, loss[loss=0.1428, simple_loss=0.2066, pruned_loss=0.03955, over 4826.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.03018, over 971227.24 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 09:18:27,439 INFO [train.py:715] (4/8) Epoch 15, batch 11800, loss[loss=0.1171, simple_loss=0.1866, pruned_loss=0.02379, over 4792.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03004, over 971173.35 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 09:19:05,524 INFO [train.py:715] (4/8) Epoch 15, batch 11850, loss[loss=0.1229, simple_loss=0.1882, pruned_loss=0.0288, over 4804.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02981, over 971952.18 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 09:19:45,050 INFO [train.py:715] (4/8) Epoch 15, batch 11900, loss[loss=0.157, simple_loss=0.2248, pruned_loss=0.04461, over 4985.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03005, over 972237.17 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:20:25,130 INFO [train.py:715] (4/8) Epoch 15, batch 11950, loss[loss=0.1538, simple_loss=0.2323, pruned_loss=0.03764, over 4931.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.03016, over 972431.67 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 09:21:03,719 INFO [train.py:715] (4/8) Epoch 15, batch 12000, loss[loss=0.1233, simple_loss=0.1906, pruned_loss=0.02803, over 4753.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03024, over 971921.58 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 09:21:03,719 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 09:21:20,395 INFO [train.py:742] (4/8) Epoch 15, validation: loss=0.105, simple_loss=0.1887, pruned_loss=0.01066, over 914524.00 frames.
2022-05-08 09:21:59,123 INFO [train.py:715] (4/8) Epoch 15, batch 12050, loss[loss=0.1523, simple_loss=0.2231, pruned_loss=0.04079, over 4972.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03055, over 972982.73 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:22:38,254 INFO [train.py:715] (4/8) Epoch 15, batch 12100, loss[loss=0.1375, simple_loss=0.2209, pruned_loss=0.02701, over 4913.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03066, over 973232.77 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 09:23:17,962 INFO [train.py:715] (4/8) Epoch 15, batch 12150, loss[loss=0.1943, simple_loss=0.263, pruned_loss=0.06279, over 4863.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2095, pruned_loss=0.03051, over 972513.90 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 09:23:56,409 INFO [train.py:715] (4/8) Epoch 15, batch 12200, loss[loss=0.1391, simple_loss=0.2048, pruned_loss=0.0367, over 4790.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2094, pruned_loss=0.03043, over 973357.73 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 09:24:35,176 INFO [train.py:715] (4/8) Epoch 15, batch 12250, loss[loss=0.1613, simple_loss=0.2315, pruned_loss=0.0455, over 4779.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2089, pruned_loss=0.03006, over 972663.09 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 09:25:14,190 INFO [train.py:715] (4/8) Epoch 15, batch 12300, loss[loss=0.1417, simple_loss=0.2264, pruned_loss=0.02852, over 4965.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03084, over 972697.75 frames.], batch size: 14, lr: 1.47e-04
2022-05-08 09:25:54,055 INFO [train.py:715] (4/8) Epoch 15, batch 12350, loss[loss=0.1543, simple_loss=0.2252, pruned_loss=0.04173, over 4742.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2098, pruned_loss=0.03079, over 973045.87 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 09:26:32,316 INFO [train.py:715] (4/8) Epoch 15, batch 12400, loss[loss=0.1257, simple_loss=0.2015, pruned_loss=0.02499, over 4700.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03079, over 973172.95 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:27:11,075 INFO [train.py:715] (4/8) Epoch 15, batch 12450, loss[loss=0.1314, simple_loss=0.2063, pruned_loss=0.02824, over 4801.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2088, pruned_loss=0.03047, over 973301.86 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 09:27:51,092 INFO [train.py:715] (4/8) Epoch 15, batch 12500, loss[loss=0.1392, simple_loss=0.2226, pruned_loss=0.02796, over 4778.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03013, over 972098.47 frames.], batch size: 18, lr: 1.47e-04
2022-05-08 09:28:29,281 INFO [train.py:715] (4/8) Epoch 15, batch 12550, loss[loss=0.1282, simple_loss=0.2064, pruned_loss=0.02497, over 4971.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02998, over 972433.91 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 09:29:08,341 INFO [train.py:715] (4/8) Epoch 15, batch 12600, loss[loss=0.1439, simple_loss=0.2194, pruned_loss=0.03417, over 4835.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02993, over 971960.85 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:29:46,866 INFO [train.py:715] (4/8) Epoch 15, batch 12650, loss[loss=0.1419, simple_loss=0.2116, pruned_loss=0.03611, over 4837.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03027, over 972374.66 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:30:26,460 INFO [train.py:715] (4/8) Epoch 15, batch 12700, loss[loss=0.1329, simple_loss=0.2012, pruned_loss=0.03225, over 4913.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2076, pruned_loss=0.0303, over 972334.61 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 09:31:04,794 INFO [train.py:715] (4/8) Epoch 15, batch 12750, loss[loss=0.1368, simple_loss=0.2134, pruned_loss=0.03011, over 4955.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2083, pruned_loss=0.03076, over 972521.73 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:31:43,631 INFO [train.py:715] (4/8) Epoch 15, batch 12800, loss[loss=0.1261, simple_loss=0.198, pruned_loss=0.02714, over 4965.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03026, over 973019.99 frames.], batch size: 35, lr: 1.47e-04
2022-05-08 09:32:23,161 INFO [train.py:715] (4/8) Epoch 15, batch 12850, loss[loss=0.1241, simple_loss=0.1939, pruned_loss=0.02712, over 4962.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2081, pruned_loss=0.03042, over 971946.61 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:33:01,776 INFO [train.py:715] (4/8) Epoch 15, batch 12900, loss[loss=0.1273, simple_loss=0.2091, pruned_loss=0.02278, over 4950.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2091, pruned_loss=0.03093, over 971815.39 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 09:33:40,807 INFO [train.py:715] (4/8) Epoch 15, batch 12950, loss[loss=0.1352, simple_loss=0.2074, pruned_loss=0.03145, over 4848.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2082, pruned_loss=0.03075, over 971685.43 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 09:34:20,119 INFO [train.py:715] (4/8) Epoch 15, batch 13000, loss[loss=0.1235, simple_loss=0.202, pruned_loss=0.02248, over 4947.00 frames.], tot_loss[loss=0.135, simple_loss=0.2085, pruned_loss=0.03074, over 972312.66 frames.], batch size: 29, lr: 1.47e-04
2022-05-08 09:34:59,682 INFO [train.py:715] (4/8) Epoch 15, batch 13050, loss[loss=0.1301, simple_loss=0.204, pruned_loss=0.02805, over 4935.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.0303, over 972418.75 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 09:35:38,141 INFO [train.py:715] (4/8) Epoch 15, batch 13100, loss[loss=0.1406, simple_loss=0.2136, pruned_loss=0.03384, over 4806.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2073, pruned_loss=0.02997, over 972347.81 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 09:36:17,621 INFO [train.py:715] (4/8) Epoch 15, batch 13150, loss[loss=0.1298, simple_loss=0.2044, pruned_loss=0.02759, over 4984.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02983, over 972275.23 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 09:36:57,401 INFO [train.py:715] (4/8) Epoch 15, batch 13200, loss[loss=0.1295, simple_loss=0.2046, pruned_loss=0.0272, over 4874.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02973, over 972168.29 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 09:37:35,197 INFO [train.py:715] (4/8) Epoch 15, batch 13250, loss[loss=0.1065, simple_loss=0.1876, pruned_loss=0.0127, over 4827.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02982, over 972320.17 frames.], batch size: 26, lr: 1.47e-04
2022-05-08 09:38:14,325 INFO [train.py:715] (4/8) Epoch 15, batch 13300, loss[loss=0.1542, simple_loss=0.2264, pruned_loss=0.04101, over 4869.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2082, pruned_loss=0.02955, over 972683.48 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 09:38:53,947 INFO [train.py:715] (4/8) Epoch 15, batch 13350, loss[loss=0.1395, simple_loss=0.2105, pruned_loss=0.03427, over 4841.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.0297, over 972340.73 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 09:39:34,555 INFO [train.py:715] (4/8) Epoch 15, batch 13400, loss[loss=0.1231, simple_loss=0.1964, pruned_loss=0.02493, over 4920.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2088, pruned_loss=0.02977, over 972178.58 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 09:40:13,177 INFO [train.py:715] (4/8) Epoch 15, batch 13450, loss[loss=0.1683, simple_loss=0.2447, pruned_loss=0.04591, over 4809.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2091, pruned_loss=0.02981, over 971949.41 frames.], batch size: 26, lr: 1.47e-04
2022-05-08 09:40:51,763 INFO [train.py:715] (4/8) Epoch 15, batch 13500, loss[loss=0.1217, simple_loss=0.1977, pruned_loss=0.02281, over 4818.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2091, pruned_loss=0.02994, over 972038.06 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 09:41:31,298 INFO [train.py:715] (4/8) Epoch 15, batch 13550, loss[loss=0.1462, simple_loss=0.2207, pruned_loss=0.03581, over 4830.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2098, pruned_loss=0.03075, over 971934.49 frames.], batch size: 26, lr: 1.47e-04
2022-05-08 09:42:09,578 INFO [train.py:715] (4/8) Epoch 15, batch 13600, loss[loss=0.1259, simple_loss=0.2026, pruned_loss=0.02459, over 4756.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.03029, over 971787.71 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 09:42:48,559 INFO [train.py:715] (4/8) Epoch 15, batch 13650, loss[loss=0.1302, simple_loss=0.2016, pruned_loss=0.02944, over 4865.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03008, over 972166.88 frames.], batch size: 20, lr: 1.47e-04
2022-05-08 09:43:27,802 INFO [train.py:715] (4/8) Epoch 15, batch 13700, loss[loss=0.1446, simple_loss=0.2179, pruned_loss=0.03564, over 4793.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03025, over 970818.05 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 09:44:06,255 INFO [train.py:715] (4/8) Epoch 15, batch 13750, loss[loss=0.1338, simple_loss=0.1929, pruned_loss=0.03739, over 4913.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.0303, over 970742.00 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 09:44:44,978 INFO [train.py:715] (4/8) Epoch 15, batch 13800, loss[loss=0.1336, simple_loss=0.2048, pruned_loss=0.03122, over 4963.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03028, over 970732.47 frames.], batch size: 35, lr: 1.47e-04
2022-05-08 09:45:23,192 INFO [train.py:715] (4/8) Epoch 15, batch 13850, loss[loss=0.1315, simple_loss=0.2032, pruned_loss=0.02993, over 4982.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03012, over 971909.50 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 09:46:05,195 INFO [train.py:715] (4/8) Epoch 15, batch 13900, loss[loss=0.1103, simple_loss=0.1811, pruned_loss=0.01968, over 4719.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03031, over 971473.28 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 09:46:43,307 INFO [train.py:715] (4/8) Epoch 15, batch 13950, loss[loss=0.1267, simple_loss=0.206, pruned_loss=0.02373, over 4754.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03047, over 971620.81 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 09:47:21,600 INFO [train.py:715] (4/8) Epoch 15, batch 14000, loss[loss=0.1312, simple_loss=0.2022, pruned_loss=0.03007, over 4944.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03044, over 971742.02 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 09:48:00,894 INFO [train.py:715] (4/8) Epoch 15, batch 14050, loss[loss=0.1296, simple_loss=0.1988, pruned_loss=0.03022, over 4808.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2096, pruned_loss=0.03086, over 972099.74 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 09:48:38,845 INFO [train.py:715] (4/8) Epoch 15, batch 14100, loss[loss=0.1327, simple_loss=0.208, pruned_loss=0.02871, over 4875.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03105, over 971548.15 frames.], batch size: 22, lr: 1.47e-04
2022-05-08 09:49:17,893 INFO [train.py:715] (4/8) Epoch 15, batch 14150, loss[loss=0.1217, simple_loss=0.198, pruned_loss=0.02268, over 4798.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03087, over 972218.44 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 09:49:56,536 INFO [train.py:715] (4/8) Epoch 15, batch 14200, loss[loss=0.1484, simple_loss=0.2174, pruned_loss=0.03975, over 4769.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2091, pruned_loss=0.03101, over 973118.54 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 09:50:35,493 INFO [train.py:715] (4/8) Epoch 15, batch 14250, loss[loss=0.1081, simple_loss=0.1908, pruned_loss=0.01276, over 4984.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2083, pruned_loss=0.03072, over 972895.87 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 09:51:13,320 INFO [train.py:715] (4/8) Epoch 15, batch 14300, loss[loss=0.1297, simple_loss=0.206, pruned_loss=0.02672, over 4875.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03051, over 973352.71 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 09:51:51,760 INFO [train.py:715] (4/8) Epoch 15, batch 14350, loss[loss=0.1913, simple_loss=0.265, pruned_loss=0.05879, over 4839.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.03075, over 973671.50 frames.], batch size: 32, lr: 1.47e-04
2022-05-08 09:52:30,860 INFO [train.py:715] (4/8) Epoch 15, batch 14400, loss[loss=0.1464, simple_loss=0.2253, pruned_loss=0.03373, over 4815.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03086, over 973077.82 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 09:53:08,603 INFO [train.py:715] (4/8) Epoch 15, batch 14450, loss[loss=0.1654, simple_loss=0.2186, pruned_loss=0.05613, over 4898.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03108, over 973742.19 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 09:53:47,584 INFO [train.py:715] (4/8) Epoch 15, batch 14500, loss[loss=0.123, simple_loss=0.1994, pruned_loss=0.02326, over 4824.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03087, over 973020.20 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:54:25,848 INFO [train.py:715] (4/8) Epoch 15, batch 14550, loss[loss=0.1214, simple_loss=0.1894, pruned_loss=0.02673, over 4750.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2093, pruned_loss=0.03106, over 973028.77 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 09:55:04,847 INFO [train.py:715] (4/8) Epoch 15, batch 14600, loss[loss=0.1351, simple_loss=0.214, pruned_loss=0.02808, over 4947.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03043, over 973178.71 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 09:55:42,671 INFO [train.py:715] (4/8) Epoch 15, batch 14650, loss[loss=0.1571, simple_loss=0.2332, pruned_loss=0.04048, over 4823.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2089, pruned_loss=0.03088, over 972887.07 frames.], batch size: 27, lr: 1.47e-04
2022-05-08 09:56:20,650 INFO [train.py:715] (4/8) Epoch 15, batch 14700, loss[loss=0.1174, simple_loss=0.1874, pruned_loss=0.02375, over 4973.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03054, over 972936.68 frames.], batch size: 35, lr: 1.47e-04
2022-05-08 09:56:59,716 INFO [train.py:715] (4/8) Epoch 15, batch 14750, loss[loss=0.1546, simple_loss=0.2207, pruned_loss=0.04426, over 4848.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.03054, over 973495.00 frames.], batch size: 34, lr: 1.47e-04
2022-05-08 09:57:37,352 INFO [train.py:715] (4/8) Epoch 15, batch 14800, loss[loss=0.1184, simple_loss=0.195, pruned_loss=0.02087, over 4980.00 frames.], tot_loss[loss=0.1344, simple_loss=0.208, pruned_loss=0.03039, over 974236.48 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 09:58:16,193 INFO [train.py:715] (4/8) Epoch 15, batch 14850, loss[loss=0.1094, simple_loss=0.171, pruned_loss=0.02387, over 4794.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2079, pruned_loss=0.03054, over 973637.14 frames.], batch size: 14, lr: 1.47e-04
2022-05-08 09:58:55,098 INFO [train.py:715] (4/8) Epoch 15, batch 14900, loss[loss=0.1185, simple_loss=0.204, pruned_loss=0.01654, over 4825.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.0305, over 974125.01 frames.], batch size: 26, lr: 1.47e-04
2022-05-08 09:59:33,266 INFO [train.py:715] (4/8) Epoch 15, batch 14950, loss[loss=0.1174, simple_loss=0.1913, pruned_loss=0.02177, over 4739.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2088, pruned_loss=0.03093, over 973799.54 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 10:00:11,562 INFO [train.py:715] (4/8) Epoch 15, batch 15000, loss[loss=0.1555, simple_loss=0.2303, pruned_loss=0.04035, over 4807.00 frames.], tot_loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03104, over 973361.06 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 10:00:11,563 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 10:00:26,343 INFO [train.py:742] (4/8) Epoch 15, validation: loss=0.1051, simple_loss=0.1887, pruned_loss=0.01077, over 914524.00 frames.
2022-05-08 10:01:05,813 INFO [train.py:715] (4/8) Epoch 15, batch 15050, loss[loss=0.1415, simple_loss=0.2168, pruned_loss=0.03313, over 4753.00 frames.], tot_loss[loss=0.136, simple_loss=0.2093, pruned_loss=0.03131, over 972807.31 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:01:43,978 INFO [train.py:715] (4/8) Epoch 15, batch 15100, loss[loss=0.1286, simple_loss=0.1987, pruned_loss=0.02926, over 4924.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2094, pruned_loss=0.03138, over 974074.94 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 10:02:23,329 INFO [train.py:715] (4/8) Epoch 15, batch 15150, loss[loss=0.1246, simple_loss=0.1982, pruned_loss=0.0255, over 4979.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.03153, over 973799.74 frames.], batch size: 28, lr: 1.47e-04
2022-05-08 10:03:01,052 INFO [train.py:715] (4/8) Epoch 15, batch 15200, loss[loss=0.1228, simple_loss=0.2015, pruned_loss=0.02204, over 4824.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2089, pruned_loss=0.0308, over 973239.03 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:03:39,351 INFO [train.py:715] (4/8) Epoch 15, batch 15250, loss[loss=0.1161, simple_loss=0.1872, pruned_loss=0.02244, over 4928.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02983, over 972415.70 frames.], batch size: 18, lr: 1.47e-04
2022-05-08 10:04:18,900 INFO [train.py:715] (4/8) Epoch 15, batch 15300, loss[loss=0.1229, simple_loss=0.1998, pruned_loss=0.02297, over 4976.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02978, over 972888.90 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 10:04:56,982 INFO [train.py:715] (4/8) Epoch 15, batch 15350, loss[loss=0.1111, simple_loss=0.1922, pruned_loss=0.015, over 4970.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02988, over 972722.22 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 10:05:35,892 INFO [train.py:715] (4/8) Epoch 15, batch 15400, loss[loss=0.1142, simple_loss=0.193, pruned_loss=0.01772, over 4752.00 frames.], tot_loss[loss=0.134, simple_loss=0.2077, pruned_loss=0.03013, over 972163.71 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:06:13,984 INFO [train.py:715] (4/8) Epoch 15, batch 15450, loss[loss=0.1228, simple_loss=0.2023, pruned_loss=0.02168, over 4836.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03015, over 972481.69 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 10:06:52,879 INFO [train.py:715] (4/8) Epoch 15, batch 15500, loss[loss=0.1242, simple_loss=0.2141, pruned_loss=0.01714, over 4896.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02994, over 972823.18 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:07:31,438 INFO [train.py:715] (4/8) Epoch 15, batch 15550, loss[loss=0.1575, simple_loss=0.2233, pruned_loss=0.04589, over 4864.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03066, over 973210.03 frames.], batch size: 20, lr: 1.47e-04
2022-05-08 10:08:10,328 INFO [train.py:715] (4/8) Epoch 15, batch 15600, loss[loss=0.1255, simple_loss=0.2033, pruned_loss=0.02382, over 4755.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2099, pruned_loss=0.03069, over 973594.56 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:08:49,133 INFO [train.py:715] (4/8) Epoch 15, batch 15650, loss[loss=0.1327, simple_loss=0.2053, pruned_loss=0.0301, over 4778.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03006, over 973488.59 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 10:09:27,217 INFO [train.py:715] (4/8) Epoch 15, batch 15700, loss[loss=0.1424, simple_loss=0.2085, pruned_loss=0.03814, over 4930.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2088, pruned_loss=0.03024, over 972851.59 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 10:10:05,786 INFO [train.py:715] (4/8) Epoch 15, batch 15750, loss[loss=0.1129, simple_loss=0.1805, pruned_loss=0.02264, over 4736.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.0302, over 972106.70 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 10:10:44,346 INFO [train.py:715] (4/8) Epoch 15, batch 15800, loss[loss=0.1273, simple_loss=0.1988, pruned_loss=0.02795, over 4965.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02982, over 972782.85 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 10:11:23,019 INFO [train.py:715] (4/8) Epoch 15, batch 15850, loss[loss=0.1197, simple_loss=0.1974, pruned_loss=0.02105, over 4952.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2067, pruned_loss=0.02954, over 972574.67 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 10:12:01,146 INFO [train.py:715] (4/8) Epoch 15, batch 15900, loss[loss=0.1294, simple_loss=0.2027, pruned_loss=0.0281, over 4913.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.0301, over 971797.73 frames.], batch size: 18, lr: 1.47e-04
2022-05-08 10:12:39,299 INFO [train.py:715] (4/8) Epoch 15, batch 15950, loss[loss=0.1659, simple_loss=0.2395, pruned_loss=0.04611, over 4790.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.0301, over 971381.49 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 10:13:18,369 INFO [train.py:715] (4/8) Epoch 15, batch 16000, loss[loss=0.1124, simple_loss=0.1928, pruned_loss=0.01598, over 4852.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03049, over 971613.10 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:13:56,002 INFO [train.py:715] (4/8) Epoch 15, batch 16050, loss[loss=0.1314, simple_loss=0.2008, pruned_loss=0.03104, over 4751.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03003, over 970961.40 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 10:14:34,593 INFO [train.py:715] (4/8) Epoch 15, batch 16100, loss[loss=0.1222, simple_loss=0.1947, pruned_loss=0.02487, over 4976.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.03038, over 971174.59 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:15:13,036 INFO [train.py:715] (4/8) Epoch 15, batch 16150, loss[loss=0.1591, simple_loss=0.228, pruned_loss=0.04515, over 4823.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.0299, over 971674.14 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 10:15:51,555 INFO [train.py:715] (4/8) Epoch 15, batch 16200, loss[loss=0.1316, simple_loss=0.2132, pruned_loss=0.02495, over 4986.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02986, over 971436.54 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 10:16:29,837 INFO [train.py:715] (4/8) Epoch 15, batch 16250, loss[loss=0.1485, simple_loss=0.2092, pruned_loss=0.04387, over 4745.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03022, over 971700.47 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 10:17:08,215 INFO [train.py:715] (4/8) Epoch 15, batch 16300, loss[loss=0.1346, simple_loss=0.2181, pruned_loss=0.02557, over 4757.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02953, over 972469.05 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:17:46,751 INFO [train.py:715] (4/8) Epoch 15, batch 16350, loss[loss=0.1181, simple_loss=0.1916, pruned_loss=0.02231, over 4827.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02951, over 972201.29 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 10:18:24,621 INFO [train.py:715] (4/8) Epoch 15, batch 16400, loss[loss=0.1188, simple_loss=0.1932, pruned_loss=0.02221, over 4944.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.02997, over 972683.11 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 10:19:03,503 INFO [train.py:715] (4/8) Epoch 15, batch 16450, loss[loss=0.1116, simple_loss=0.1886, pruned_loss=0.01724, over 4693.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03022, over 972807.35 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:19:41,758 INFO [train.py:715] (4/8) Epoch 15, batch 16500, loss[loss=0.1154, simple_loss=0.1827, pruned_loss=0.02406, over 4905.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2082, pruned_loss=0.03061, over 972591.69 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 10:20:20,130 INFO [train.py:715] (4/8) Epoch 15, batch 16550, loss[loss=0.1578, simple_loss=0.226, pruned_loss=0.04484, over 4799.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03048, over 972648.55 frames.], batch size: 14, lr: 1.47e-04
2022-05-08 10:20:58,277 INFO [train.py:715] (4/8) Epoch 15, batch 16600, loss[loss=0.1283, simple_loss=0.1983, pruned_loss=0.02917, over 4930.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2082, pruned_loss=0.03069, over 972158.78 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 10:21:37,034 INFO [train.py:715] (4/8) Epoch 15, batch 16650, loss[loss=0.1068, simple_loss=0.1824, pruned_loss=0.0156, over 4772.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.03029, over 972155.41 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 10:22:16,801 INFO [train.py:715] (4/8) Epoch 15, batch 16700, loss[loss=0.1183, simple_loss=0.1973, pruned_loss=0.01966, over 4955.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03024, over 973547.28 frames.], batch size: 29, lr: 1.47e-04
2022-05-08 10:22:55,522 INFO [train.py:715] (4/8) Epoch 15, batch 16750, loss[loss=0.1622, simple_loss=0.2365, pruned_loss=0.04391, over 4749.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03024, over 973225.86 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:23:34,512 INFO [train.py:715] (4/8) Epoch 15, batch 16800, loss[loss=0.1372, simple_loss=0.2076, pruned_loss=0.03339, over 4903.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03011, over 972971.12 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:24:13,669 INFO [train.py:715] (4/8) Epoch 15, batch 16850, loss[loss=0.1317, simple_loss=0.2127, pruned_loss=0.02534, over 4936.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2081, pruned_loss=0.03059, over 973393.28 frames.], batch size: 29, lr: 1.47e-04
2022-05-08 10:24:52,754 INFO [train.py:715] (4/8) Epoch 15, batch 16900, loss[loss=0.1434, simple_loss=0.2116, pruned_loss=0.0376, over 4777.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03008, over 973454.27 frames.], batch size: 12, lr: 1.47e-04
2022-05-08 10:25:31,721 INFO [train.py:715] (4/8) Epoch 15, batch 16950, loss[loss=0.146, simple_loss=0.2255, pruned_loss=0.03322, over 4819.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03001, over 973349.94 frames.], batch size: 27, lr: 1.47e-04
2022-05-08 10:26:10,072 INFO [train.py:715] (4/8) Epoch 15, batch 17000, loss[loss=0.1415, simple_loss=0.2235, pruned_loss=0.02972, over 4814.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03038, over 973400.85 frames.], batch size: 13, lr: 1.47e-04
2022-05-08 10:26:49,333 INFO [train.py:715] (4/8) Epoch 15, batch 17050, loss[loss=0.1246, simple_loss=0.2014, pruned_loss=0.02388, over 4825.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2078, pruned_loss=0.03052, over 972358.49 frames.], batch size: 25, lr: 1.47e-04
2022-05-08 10:27:27,262 INFO [train.py:715] (4/8) Epoch 15, batch 17100, loss[loss=0.1121, simple_loss=0.1852, pruned_loss=0.01952, over 4917.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2088, pruned_loss=0.03069, over 971969.07 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 10:28:06,075 INFO [train.py:715] (4/8) Epoch 15, batch 17150, loss[loss=0.1031, simple_loss=0.1765, pruned_loss=0.01481, over 4952.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03033, over 972205.91 frames.], batch size: 24, lr: 1.47e-04
2022-05-08 10:28:44,478 INFO [train.py:715] (4/8) Epoch 15, batch 17200, loss[loss=0.1262, simple_loss=0.2021, pruned_loss=0.02515, over 4911.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03023, over 972057.53 frames.], batch size: 17, lr: 1.47e-04
2022-05-08 10:29:23,148 INFO [train.py:715] (4/8) Epoch 15, batch 17250, loss[loss=0.1106, simple_loss=0.1856, pruned_loss=0.01779, over 4950.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2086, pruned_loss=0.03051, over 972846.75 frames.], batch size: 29, lr: 1.47e-04
2022-05-08 10:30:01,721 INFO [train.py:715] (4/8) Epoch 15, batch 17300, loss[loss=0.1227, simple_loss=0.2051, pruned_loss=0.02013, over 4930.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2079, pruned_loss=0.03036, over 972497.71 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 10:30:40,360 INFO [train.py:715] (4/8) Epoch 15, batch 17350, loss[loss=0.1425, simple_loss=0.2158, pruned_loss=0.03463, over 4967.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03021, over 971710.03 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:31:19,950 INFO [train.py:715] (4/8) Epoch 15, batch 17400, loss[loss=0.1175, simple_loss=0.1896, pruned_loss=0.0227, over 4859.00 frames.], tot_loss[loss=0.1334, simple_loss=0.207, pruned_loss=0.02993, over 972163.42 frames.], batch size: 16, lr: 1.47e-04
2022-05-08 10:31:57,891 INFO [train.py:715] (4/8) Epoch 15, batch 17450, loss[loss=0.1375, simple_loss=0.2185, pruned_loss=0.02827, over 4930.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02973, over 972982.49 frames.], batch size: 21, lr: 1.47e-04
2022-05-08 10:32:36,870 INFO [train.py:715] (4/8) Epoch 15, batch 17500, loss[loss=0.1227, simple_loss=0.1958, pruned_loss=0.02482, over 4875.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02988, over 972793.86 frames.], batch size: 38, lr: 1.47e-04
2022-05-08 10:33:15,844 INFO [train.py:715] (4/8) Epoch 15, batch 17550, loss[loss=0.1047, simple_loss=0.1761, pruned_loss=0.01664, over 4857.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03018, over 973165.61 frames.], batch size: 20, lr: 1.47e-04
2022-05-08 10:33:54,433 INFO [train.py:715] (4/8) Epoch 15, batch 17600, loss[loss=0.1574, simple_loss=0.2206, pruned_loss=0.04712, over 4859.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03079, over 972302.39 frames.], batch size: 34, lr: 1.47e-04
2022-05-08 10:34:32,813 INFO [train.py:715] (4/8) Epoch 15, batch 17650, loss[loss=0.1108, simple_loss=0.1799, pruned_loss=0.02086, over 4854.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03017, over 972639.77 frames.], batch size: 30, lr: 1.47e-04
2022-05-08 10:35:11,433 INFO [train.py:715] (4/8) Epoch 15, batch 17700, loss[loss=0.1708, simple_loss=0.2521, pruned_loss=0.04472, over 4980.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.0304, over 972703.19 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:35:50,323 INFO [train.py:715] (4/8) Epoch 15, batch 17750, loss[loss=0.1315, simple_loss=0.2052, pruned_loss=0.02886, over 4801.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03048, over 973332.93 frames.], batch size: 14, lr: 1.47e-04
2022-05-08 10:36:28,683 INFO [train.py:715] (4/8) Epoch 15, batch 17800, loss[loss=0.1422, simple_loss=0.2167, pruned_loss=0.03387, over 4751.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2092, pruned_loss=0.03078, over 973234.55 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:37:07,667 INFO [train.py:715] (4/8) Epoch 15, batch 17850, loss[loss=0.1363, simple_loss=0.2098, pruned_loss=0.03138, over 4915.00 frames.], tot_loss[loss=0.136, simple_loss=0.2098, pruned_loss=0.0311, over 972784.79 frames.], batch size: 23, lr: 1.47e-04
2022-05-08 10:37:46,656 INFO [train.py:715] (4/8) Epoch 15, batch 17900, loss[loss=0.1259, simple_loss=0.21, pruned_loss=0.02087, over 4852.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2094, pruned_loss=0.0306, over 972637.84 frames.], batch size: 20, lr: 1.47e-04
2022-05-08 10:38:25,488 INFO [train.py:715] (4/8) Epoch 15, batch 17950, loss[loss=0.16, simple_loss=0.2234, pruned_loss=0.04827, over 4756.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03062, over 972401.19 frames.], batch size: 19, lr: 1.47e-04
2022-05-08 10:39:03,818 INFO [train.py:715] (4/8) Epoch 15, batch 18000, loss[loss=0.1424, simple_loss=0.2232, pruned_loss=0.03084, over 4977.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2095, pruned_loss=0.03074, over 972650.31 frames.], batch size: 15, lr: 1.47e-04
2022-05-08 10:39:03,818 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 10:39:13,328 INFO [train.py:742] (4/8) Epoch 15, validation: loss=0.1048, simple_loss=0.1885, pruned_loss=0.01059, over 914524.00 frames.
2022-05-08 10:39:51,810 INFO [train.py:715] (4/8) Epoch 15, batch 18050, loss[loss=0.137, simple_loss=0.1998, pruned_loss=0.03714, over 4829.00 frames.], tot_loss[loss=0.1348, simple_loss=0.209, pruned_loss=0.03033, over 971948.58 frames.], batch size: 30, lr: 1.47e-04
2022-05-08 10:40:30,477 INFO [train.py:715] (4/8) Epoch 15, batch 18100, loss[loss=0.1427, simple_loss=0.2148, pruned_loss=0.03535, over 4916.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03022, over 972008.31 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 10:41:09,231 INFO [train.py:715] (4/8) Epoch 15, batch 18150, loss[loss=0.1183, simple_loss=0.1912, pruned_loss=0.0227, over 4930.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03059, over 971836.18 frames.], batch size: 29, lr: 1.46e-04
2022-05-08 10:41:47,120 INFO [train.py:715] (4/8) Epoch 15, batch 18200, loss[loss=0.1626, simple_loss=0.2363, pruned_loss=0.04449, over 4740.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03042, over 971843.13 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 10:42:25,781 INFO [train.py:715] (4/8) Epoch 15, batch 18250, loss[loss=0.1753, simple_loss=0.2642, pruned_loss=0.04319, over 4967.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2084, pruned_loss=0.03086, over 972822.47 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 10:43:04,442 INFO [train.py:715] (4/8) Epoch 15, batch 18300, loss[loss=0.1589, simple_loss=0.2169, pruned_loss=0.05045, over 4805.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2092, pruned_loss=0.03109, over 972081.04 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 10:43:42,533 INFO [train.py:715] (4/8) Epoch 15, batch 18350, loss[loss=0.1308, simple_loss=0.2011, pruned_loss=0.03026, over 4862.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03098, over 972204.47 frames.], batch size: 34, lr: 1.46e-04
2022-05-08 10:44:21,120 INFO [train.py:715] (4/8) Epoch 15, batch 18400, loss[loss=0.1446, simple_loss=0.223, pruned_loss=0.03305, over 4800.00 frames.], tot_loss[loss=0.1361, simple_loss=0.2103, pruned_loss=0.031, over 971630.33 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 10:44:59,634 INFO [train.py:715] (4/8) Epoch 15, batch 18450, loss[loss=0.1232, simple_loss=0.1968, pruned_loss=0.02481, over 4960.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2091, pruned_loss=0.03017, over 972270.19 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 10:45:38,895 INFO [train.py:715] (4/8) Epoch 15, batch 18500, loss[loss=0.1473, simple_loss=0.2235, pruned_loss=0.03554, over 4972.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02973, over 972285.56 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 10:46:17,389 INFO [train.py:715] (4/8) Epoch 15, batch 18550, loss[loss=0.1461, simple_loss=0.2094, pruned_loss=0.04144, over 4933.00 frames.], tot_loss[loss=0.1346, simple_loss=0.209, pruned_loss=0.03007, over 972629.56 frames.], batch size: 23, lr: 1.46e-04
2022-05-08 10:46:55,978 INFO [train.py:715] (4/8) Epoch 15, batch 18600, loss[loss=0.1153, simple_loss=0.1929, pruned_loss=0.01886, over 4826.00 frames.], tot_loss[loss=0.1344, simple_loss=0.209, pruned_loss=0.0299, over 973315.69 frames.], batch size: 27, lr: 1.46e-04
2022-05-08 10:47:34,895 INFO [train.py:715] (4/8) Epoch 15, batch 18650, loss[loss=0.1382, simple_loss=0.2118, pruned_loss=0.03226, over 4784.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2087, pruned_loss=0.02998, over 972706.33 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 10:48:13,552 INFO [train.py:715] (4/8) Epoch 15, batch 18700, loss[loss=0.1481, simple_loss=0.2221, pruned_loss=0.03703, over 4916.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02972, over 972042.27 frames.], batch size: 29, lr: 1.46e-04
2022-05-08 10:48:52,385 INFO [train.py:715] (4/8) Epoch 15, batch 18750, loss[loss=0.1412, simple_loss=0.2033, pruned_loss=0.03959, over 4836.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02975, over 971473.03 frames.], batch size: 32, lr: 1.46e-04
2022-05-08 10:49:31,672 INFO [train.py:715] (4/8) Epoch 15, batch 18800, loss[loss=0.1452, simple_loss=0.2201, pruned_loss=0.03517, over 4806.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02971, over 970463.78 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 10:50:10,916 INFO [train.py:715] (4/8) Epoch 15, batch 18850, loss[loss=0.1288, simple_loss=0.2064, pruned_loss=0.02558, over 4979.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02936, over 971279.28 frames.], batch size: 35, lr: 1.46e-04
2022-05-08 10:50:49,337 INFO [train.py:715] (4/8) Epoch 15, batch 18900, loss[loss=0.12, simple_loss=0.187, pruned_loss=0.0265, over 4930.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02995, over 971693.89 frames.], batch size: 29, lr: 1.46e-04
2022-05-08 10:51:28,549 INFO [train.py:715] (4/8) Epoch 15, batch 18950, loss[loss=0.1225, simple_loss=0.2032, pruned_loss=0.02088, over 4766.00 frames.], tot_loss[loss=0.1346, simple_loss=0.209, pruned_loss=0.03009, over 972327.88 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 10:52:07,861 INFO [train.py:715] (4/8) Epoch 15, batch 19000, loss[loss=0.1307, simple_loss=0.2082, pruned_loss=0.02663, over 4871.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.02992, over 972567.61 frames.], batch size: 22, lr: 1.46e-04
2022-05-08 10:52:46,218 INFO [train.py:715] (4/8) Epoch 15, batch 19050, loss[loss=0.1522, simple_loss=0.2198, pruned_loss=0.04235, over 4905.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03007, over 972320.37 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 10:53:25,395 INFO [train.py:715] (4/8) Epoch 15, batch 19100, loss[loss=0.1111, simple_loss=0.192, pruned_loss=0.01506, over 4813.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03009, over 972764.77 frames.], batch size: 26, lr: 1.46e-04
2022-05-08 10:54:03,698 INFO [train.py:715] (4/8) Epoch 15, batch 19150, loss[loss=0.1332, simple_loss=0.2114, pruned_loss=0.0275, over 4979.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02984, over 973050.65 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 10:54:41,931 INFO [train.py:715] (4/8) Epoch 15, batch 19200, loss[loss=0.1333, simple_loss=0.2143, pruned_loss=0.02615, over 4855.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03063, over 973076.60 frames.], batch size: 32, lr: 1.46e-04
2022-05-08 10:55:19,946 INFO [train.py:715] (4/8) Epoch 15, batch 19250, loss[loss=0.1571, simple_loss=0.2283, pruned_loss=0.04301, over 4834.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.0306, over 973787.82 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 10:55:58,063 INFO [train.py:715] (4/8) Epoch 15, batch 19300, loss[loss=0.1517, simple_loss=0.2307, pruned_loss=0.03637, over 4928.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03012, over 973674.47 frames.], batch size: 29, lr: 1.46e-04
2022-05-08 10:56:36,948 INFO [train.py:715] (4/8) Epoch 15, batch 19350, loss[loss=0.1197, simple_loss=0.2035, pruned_loss=0.01797, over 4756.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03009, over 973510.56 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 10:57:14,726 INFO [train.py:715] (4/8) Epoch 15, batch 19400, loss[loss=0.1203, simple_loss=0.1979, pruned_loss=0.02134, over 4826.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02965, over 972750.89 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 10:57:53,613 INFO [train.py:715] (4/8) Epoch 15, batch 19450, loss[loss=0.1684, simple_loss=0.2408, pruned_loss=0.048, over 4814.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03034, over 972480.49 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 10:58:31,634 INFO [train.py:715] (4/8) Epoch 15, batch 19500, loss[loss=0.1322, simple_loss=0.2055, pruned_loss=0.02951, over 4775.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03019, over 971558.36 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 10:59:09,773 INFO [train.py:715] (4/8) Epoch 15, batch 19550, loss[loss=0.1562, simple_loss=0.2332, pruned_loss=0.03963, over 4919.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03074, over 972589.08 frames.], batch size: 23, lr: 1.46e-04
2022-05-08 10:59:48,217 INFO [train.py:715] (4/8) Epoch 15, batch 19600, loss[loss=0.1188, simple_loss=0.1897, pruned_loss=0.024, over 4813.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.03025, over 971892.94 frames.], batch size: 25, lr: 1.46e-04
2022-05-08 11:00:26,253 INFO [train.py:715] (4/8) Epoch 15, batch 19650, loss[loss=0.1492, simple_loss=0.2308, pruned_loss=0.03376, over 4829.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2083, pruned_loss=0.03101, over 971592.12 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 11:01:05,291 INFO [train.py:715] (4/8) Epoch 15, batch 19700, loss[loss=0.1438, simple_loss=0.222, pruned_loss=0.0328, over 4813.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2079, pruned_loss=0.03074, over 972406.86 frames.], batch size: 27, lr: 1.46e-04
2022-05-08 11:01:42,980 INFO [train.py:715] (4/8) Epoch 15, batch 19750, loss[loss=0.1107, simple_loss=0.1807, pruned_loss=0.02037, over 4692.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.03034, over 971965.89 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:02:21,390 INFO [train.py:715] (4/8) Epoch 15, batch 19800, loss[loss=0.1213, simple_loss=0.192, pruned_loss=0.02532, over 4693.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2076, pruned_loss=0.0305, over 972605.85 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:02:59,696 INFO [train.py:715] (4/8) Epoch 15, batch 19850, loss[loss=0.1282, simple_loss=0.1974, pruned_loss=0.02951, over 4797.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2076, pruned_loss=0.03056, over 972243.59 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 11:03:37,786 INFO [train.py:715] (4/8) Epoch 15, batch 19900, loss[loss=0.1255, simple_loss=0.2077, pruned_loss=0.02163, over 4949.00 frames.], tot_loss[loss=0.1343, simple_loss=0.208, pruned_loss=0.03031, over 972395.19 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 11:04:16,956 INFO [train.py:715] (4/8) Epoch 15, batch 19950, loss[loss=0.1143, simple_loss=0.1902, pruned_loss=0.01917, over 4918.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.02998, over 973516.96 frames.], batch size: 29, lr: 1.46e-04
2022-05-08 11:04:55,166 INFO [train.py:715] (4/8) Epoch 15, batch 20000, loss[loss=0.133, simple_loss=0.2178, pruned_loss=0.02407, over 4881.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02937, over 973829.26 frames.], batch size: 22, lr: 1.46e-04
2022-05-08 11:05:33,565 INFO [train.py:715] (4/8) Epoch 15, batch 20050, loss[loss=0.13, simple_loss=0.212, pruned_loss=0.02398, over 4813.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02921, over 973584.57 frames.], batch size: 25, lr: 1.46e-04
2022-05-08 11:06:11,838 INFO [train.py:715] (4/8) Epoch 15, batch 20100, loss[loss=0.1311, simple_loss=0.2064, pruned_loss=0.02795, over 4962.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02959, over 973983.71 frames.], batch size: 39, lr: 1.46e-04
2022-05-08 11:06:50,115 INFO [train.py:715] (4/8) Epoch 15, batch 20150, loss[loss=0.1369, simple_loss=0.2025, pruned_loss=0.03565, over 4790.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.0294, over 972803.47 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 11:07:28,123 INFO [train.py:715] (4/8) Epoch 15, batch 20200, loss[loss=0.1413, simple_loss=0.2139, pruned_loss=0.03438, over 4846.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02973, over 973174.65 frames.], batch size: 30, lr: 1.46e-04
2022-05-08 11:08:05,820 INFO [train.py:715] (4/8) Epoch 15, batch 20250, loss[loss=0.1377, simple_loss=0.2112, pruned_loss=0.03209, over 4831.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2079, pruned_loss=0.03031, over 972927.24 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 11:08:44,516 INFO [train.py:715] (4/8) Epoch 15, batch 20300, loss[loss=0.1012, simple_loss=0.1805, pruned_loss=0.01093, over 4798.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2083, pruned_loss=0.03044, over 972168.25 frames.], batch size: 12, lr: 1.46e-04
2022-05-08 11:09:22,704 INFO [train.py:715] (4/8) Epoch 15, batch 20350, loss[loss=0.1268, simple_loss=0.2048, pruned_loss=0.0244, over 4936.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2085, pruned_loss=0.03046, over 971651.19 frames.], batch size: 23, lr: 1.46e-04
2022-05-08 11:10:01,085 INFO [train.py:715] (4/8) Epoch 15, batch 20400, loss[loss=0.1479, simple_loss=0.2184, pruned_loss=0.03875, over 4978.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03028, over 971925.59 frames.], batch size: 35, lr: 1.46e-04
2022-05-08 11:10:38,946 INFO [train.py:715] (4/8) Epoch 15, batch 20450, loss[loss=0.111, simple_loss=0.1819, pruned_loss=0.01999, over 4896.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03033, over 972665.71 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 11:11:17,697 INFO [train.py:715] (4/8) Epoch 15, batch 20500, loss[loss=0.1647, simple_loss=0.2301, pruned_loss=0.04962, over 4868.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2088, pruned_loss=0.03077, over 972537.19 frames.], batch size: 38, lr: 1.46e-04
2022-05-08 11:11:55,869 INFO [train.py:715] (4/8) Epoch 15, batch 20550, loss[loss=0.1169, simple_loss=0.1941, pruned_loss=0.01982, over 4922.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2089, pruned_loss=0.03097, over 972927.94 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:12:33,918 INFO [train.py:715] (4/8) Epoch 15, batch 20600, loss[loss=0.1344, simple_loss=0.2033, pruned_loss=0.03279, over 4849.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03058, over 973310.07 frames.], batch size: 30, lr: 1.46e-04
2022-05-08 11:13:12,978 INFO [train.py:715] (4/8) Epoch 15, batch 20650, loss[loss=0.145, simple_loss=0.2279, pruned_loss=0.03105, over 4727.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2095, pruned_loss=0.03088, over 972639.00 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 11:13:51,737 INFO [train.py:715] (4/8) Epoch 15, batch 20700, loss[loss=0.1169, simple_loss=0.1963, pruned_loss=0.01874, over 4844.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.0307, over 971944.20 frames.], batch size: 30, lr: 1.46e-04
2022-05-08 11:14:31,081 INFO [train.py:715] (4/8) Epoch 15, batch 20750, loss[loss=0.1342, simple_loss=0.1969, pruned_loss=0.03571, over 4863.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2094, pruned_loss=0.03084, over 972137.31 frames.], batch size: 32, lr: 1.46e-04
2022-05-08 11:15:09,385 INFO [train.py:715] (4/8) Epoch 15, batch 20800, loss[loss=0.1206, simple_loss=0.2017, pruned_loss=0.01976, over 4895.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03144, over 972947.97 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 11:15:48,761 INFO [train.py:715] (4/8) Epoch 15, batch 20850, loss[loss=0.1349, simple_loss=0.2191, pruned_loss=0.02533, over 4849.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2102, pruned_loss=0.03144, over 973554.18 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 11:16:27,990 INFO [train.py:715] (4/8) Epoch 15, batch 20900, loss[loss=0.1311, simple_loss=0.2027, pruned_loss=0.02977, over 4828.00 frames.], tot_loss[loss=0.1366, simple_loss=0.2105, pruned_loss=0.03135, over 972783.91 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 11:17:06,241 INFO [train.py:715] (4/8) Epoch 15, batch 20950, loss[loss=0.1564, simple_loss=0.2273, pruned_loss=0.04277, over 4784.00 frames.], tot_loss[loss=0.1367, simple_loss=0.2104, pruned_loss=0.0315, over 972069.96 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:17:45,526 INFO [train.py:715] (4/8) Epoch 15, batch 21000, loss[loss=0.1068, simple_loss=0.173, pruned_loss=0.02025, over 4869.00 frames.], tot_loss[loss=0.1362, simple_loss=0.21, pruned_loss=0.03117, over 971975.55 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 11:17:45,527 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 11:17:56,037 INFO [train.py:742] (4/8) Epoch 15, validation: loss=0.1051, simple_loss=0.1887, pruned_loss=0.01075, over 914524.00 frames.
2022-05-08 11:18:35,286 INFO [train.py:715] (4/8) Epoch 15, batch 21050, loss[loss=0.1307, simple_loss=0.1966, pruned_loss=0.03241, over 4756.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03065, over 972526.78 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 11:19:14,769 INFO [train.py:715] (4/8) Epoch 15, batch 21100, loss[loss=0.1208, simple_loss=0.1981, pruned_loss=0.02176, over 4782.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.0308, over 972783.19 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 11:19:53,786 INFO [train.py:715] (4/8) Epoch 15, batch 21150, loss[loss=0.137, simple_loss=0.2097, pruned_loss=0.03215, over 4991.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03038, over 972714.88 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 11:20:32,267 INFO [train.py:715] (4/8) Epoch 15, batch 21200, loss[loss=0.1527, simple_loss=0.2302, pruned_loss=0.03762, over 4823.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2095, pruned_loss=0.03066, over 973105.11 frames.], batch size: 26, lr: 1.46e-04
2022-05-08 11:21:11,104 INFO [train.py:715] (4/8) Epoch 15, batch 21250, loss[loss=0.1638, simple_loss=0.2396, pruned_loss=0.04398, over 4865.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2097, pruned_loss=0.031, over 972867.18 frames.], batch size: 30, lr: 1.46e-04
2022-05-08 11:21:49,143 INFO [train.py:715] (4/8) Epoch 15, batch 21300, loss[loss=0.1362, simple_loss=0.2115, pruned_loss=0.0304, over 4691.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03053, over 972233.28 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:22:26,788 INFO [train.py:715] (4/8) Epoch 15, batch 21350, loss[loss=0.1251, simple_loss=0.1913, pruned_loss=0.02941, over 4970.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02974, over 972259.61 frames.], batch size: 35, lr: 1.46e-04
2022-05-08 11:23:05,096 INFO [train.py:715] (4/8) Epoch 15, batch 21400, loss[loss=0.1235, simple_loss=0.196, pruned_loss=0.02547, over 4992.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.03002, over 971876.29 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 11:23:43,352 INFO [train.py:715] (4/8) Epoch 15, batch 21450, loss[loss=0.1308, simple_loss=0.2098, pruned_loss=0.02596, over 4964.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02985, over 972130.35 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:24:21,357 INFO [train.py:715] (4/8) Epoch 15, batch 21500, loss[loss=0.1432, simple_loss=0.209, pruned_loss=0.03868, over 4789.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.03037, over 971387.20 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:24:59,647 INFO [train.py:715] (4/8) Epoch 15, batch 21550, loss[loss=0.1322, simple_loss=0.199, pruned_loss=0.03271, over 4824.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2098, pruned_loss=0.03073, over 972003.01 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:25:38,152 INFO [train.py:715] (4/8) Epoch 15, batch 21600, loss[loss=0.1335, simple_loss=0.2107, pruned_loss=0.02814, over 4830.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2097, pruned_loss=0.0306, over 972572.56 frames.], batch size: 30, lr: 1.46e-04
2022-05-08 11:26:16,020 INFO [train.py:715] (4/8) Epoch 15, batch 21650, loss[loss=0.1302, simple_loss=0.2143, pruned_loss=0.02306, over 4899.00 frames.], tot_loss[loss=0.1347, simple_loss=0.209, pruned_loss=0.03023, over 972534.89 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 11:26:54,238 INFO [train.py:715] (4/8) Epoch 15, batch 21700, loss[loss=0.1162, simple_loss=0.1915, pruned_loss=0.02049, over 4757.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.03, over 972117.12 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 11:27:32,376 INFO [train.py:715] (4/8) Epoch 15, batch 21750, loss[loss=0.1327, simple_loss=0.2011, pruned_loss=0.03213, over 4720.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2096, pruned_loss=0.03044, over 972163.36 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:28:10,475 INFO [train.py:715] (4/8) Epoch 15, batch 21800, loss[loss=0.1255, simple_loss=0.2069, pruned_loss=0.02209, over 4820.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03044, over 971571.89 frames.], batch size: 26, lr: 1.46e-04
2022-05-08 11:28:48,402 INFO [train.py:715] (4/8) Epoch 15, batch 21850, loss[loss=0.1086, simple_loss=0.19, pruned_loss=0.01356, over 4792.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02996, over 971977.20 frames.], batch size: 12, lr: 1.46e-04
2022-05-08 11:29:29,600 INFO [train.py:715] (4/8) Epoch 15, batch 21900, loss[loss=0.1208, simple_loss=0.1984, pruned_loss=0.0216, over 4776.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.0305, over 972331.36 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:30:08,750 INFO [train.py:715] (4/8) Epoch 15, batch 21950, loss[loss=0.1177, simple_loss=0.1908, pruned_loss=0.02228, over 4898.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03022, over 971732.83 frames.], batch size: 22, lr: 1.46e-04
2022-05-08 11:30:47,283 INFO [train.py:715] (4/8) Epoch 15, batch 22000, loss[loss=0.1739, simple_loss=0.2302, pruned_loss=0.05881, over 4866.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03012, over 972009.05 frames.], batch size: 32, lr: 1.46e-04
2022-05-08 11:31:25,805 INFO [train.py:715] (4/8) Epoch 15, batch 22050, loss[loss=0.1423, simple_loss=0.209, pruned_loss=0.0378, over 4859.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03058, over 971801.19 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 11:32:05,128 INFO [train.py:715] (4/8) Epoch 15, batch 22100, loss[loss=0.1116, simple_loss=0.1874, pruned_loss=0.01791, over 4823.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03031, over 971689.67 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:32:43,929 INFO [train.py:715] (4/8) Epoch 15, batch 22150, loss[loss=0.1287, simple_loss=0.2067, pruned_loss=0.02531, over 4970.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2083, pruned_loss=0.03034, over 971327.67 frames.], batch size: 28, lr: 1.46e-04
2022-05-08 11:33:22,300 INFO [train.py:715] (4/8) Epoch 15, batch 22200, loss[loss=0.1316, simple_loss=0.2033, pruned_loss=0.03, over 4848.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2081, pruned_loss=0.0304, over 971717.70 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 11:34:01,342 INFO [train.py:715] (4/8) Epoch 15, batch 22250, loss[loss=0.1226, simple_loss=0.1925, pruned_loss=0.02632, over 4780.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2079, pruned_loss=0.03041, over 972359.40 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:34:40,273 INFO [train.py:715] (4/8) Epoch 15, batch 22300, loss[loss=0.1373, simple_loss=0.2113, pruned_loss=0.03162, over 4943.00 frames.], tot_loss[loss=0.1346, simple_loss=0.208, pruned_loss=0.0306, over 972746.10 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 11:35:18,810 INFO [train.py:715] (4/8) Epoch 15, batch 22350, loss[loss=0.1395, simple_loss=0.2072, pruned_loss=0.03588, over 4857.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2071, pruned_loss=0.03009, over 972129.38 frames.], batch size: 30, lr: 1.46e-04
2022-05-08 11:35:57,384 INFO [train.py:715] (4/8) Epoch 15, batch 22400, loss[loss=0.1179, simple_loss=0.1785, pruned_loss=0.02871, over 4848.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2067, pruned_loss=0.03001, over 972120.55 frames.], batch size: 13, lr: 1.46e-04
2022-05-08 11:36:36,644 INFO [train.py:715] (4/8) Epoch 15, batch 22450, loss[loss=0.1241, simple_loss=0.2005, pruned_loss=0.02382, over 4866.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2077, pruned_loss=0.03058, over 971684.34 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 11:37:15,532 INFO [train.py:715] (4/8) Epoch 15, batch 22500, loss[loss=0.1757, simple_loss=0.2519, pruned_loss=0.04981, over 4909.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2081, pruned_loss=0.03069, over 971069.53 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 11:37:54,258 INFO [train.py:715] (4/8) Epoch 15, batch 22550, loss[loss=0.1125, simple_loss=0.1998, pruned_loss=0.01257, over 4980.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2079, pruned_loss=0.03055, over 971502.79 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 11:38:32,812 INFO [train.py:715] (4/8) Epoch 15, batch 22600, loss[loss=0.1594, simple_loss=0.2322, pruned_loss=0.0433, over 4972.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2085, pruned_loss=0.0309, over 971998.56 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:39:11,736 INFO [train.py:715] (4/8) Epoch 15, batch 22650, loss[loss=0.1333, simple_loss=0.2062, pruned_loss=0.0302, over 4702.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2087, pruned_loss=0.03091, over 972137.57 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:39:50,391 INFO [train.py:715] (4/8) Epoch 15, batch 22700, loss[loss=0.1023, simple_loss=0.1816, pruned_loss=0.01143, over 4822.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.03057, over 972123.30 frames.], batch size: 26, lr: 1.46e-04
2022-05-08 11:40:29,129 INFO [train.py:715] (4/8) Epoch 15, batch 22750, loss[loss=0.1386, simple_loss=0.2201, pruned_loss=0.02855, over 4884.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2084, pruned_loss=0.03054, over 972567.20 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 11:41:08,471 INFO [train.py:715] (4/8) Epoch 15, batch 22800, loss[loss=0.145, simple_loss=0.2054, pruned_loss=0.04227, over 4716.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2087, pruned_loss=0.03073, over 971795.74 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:41:47,295 INFO [train.py:715] (4/8) Epoch 15, batch 22850, loss[loss=0.146, simple_loss=0.2267, pruned_loss=0.03268, over 4910.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2096, pruned_loss=0.0307, over 972411.77 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 11:42:26,039 INFO [train.py:715] (4/8) Epoch 15, batch 22900, loss[loss=0.1215, simple_loss=0.1981, pruned_loss=0.02239, over 4790.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03027, over 972875.62 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 11:43:05,208 INFO [train.py:715] (4/8) Epoch 15, batch 22950, loss[loss=0.1129, simple_loss=0.1872, pruned_loss=0.01926, over 4874.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03007, over 973060.27 frames.], batch size: 38, lr: 1.46e-04
2022-05-08 11:43:43,825 INFO [train.py:715] (4/8) Epoch 15, batch 23000, loss[loss=0.1106, simple_loss=0.1851, pruned_loss=0.01804, over 4876.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03019, over 973552.21 frames.], batch size: 22, lr: 1.46e-04
2022-05-08 11:44:22,235 INFO [train.py:715] (4/8) Epoch 15, batch 23050, loss[loss=0.1241, simple_loss=0.1989, pruned_loss=0.02463, over 4939.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02963, over 973075.52 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:45:00,625 INFO [train.py:715] (4/8) Epoch 15, batch 23100, loss[loss=0.1258, simple_loss=0.2078, pruned_loss=0.02192, over 4768.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02945, over 973147.62 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 11:45:39,477 INFO [train.py:715] (4/8) Epoch 15, batch 23150, loss[loss=0.1451, simple_loss=0.2175, pruned_loss=0.03633, over 4975.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02971, over 972962.31 frames.], batch size: 28, lr: 1.46e-04
2022-05-08 11:46:17,452 INFO [train.py:715] (4/8) Epoch 15, batch 23200, loss[loss=0.1304, simple_loss=0.2084, pruned_loss=0.02617, over 4743.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.0297, over 972543.19 frames.], batch size: 19, lr: 1.46e-04
2022-05-08 11:46:55,707 INFO [train.py:715] (4/8) Epoch 15, batch 23250, loss[loss=0.1413, simple_loss=0.2132, pruned_loss=0.03467, over 4944.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02963, over 972521.43 frames.], batch size: 35, lr: 1.46e-04
2022-05-08 11:47:34,385 INFO [train.py:715] (4/8) Epoch 15, batch 23300, loss[loss=0.1248, simple_loss=0.1943, pruned_loss=0.02763, over 4956.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02973, over 971970.78 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:48:12,428 INFO [train.py:715] (4/8) Epoch 15, batch 23350, loss[loss=0.1674, simple_loss=0.2467, pruned_loss=0.04406, over 4797.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02956, over 972127.71 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 11:48:50,738 INFO [train.py:715] (4/8) Epoch 15, batch 23400, loss[loss=0.1158, simple_loss=0.189, pruned_loss=0.0213, over 4871.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02963, over 971727.64 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 11:49:28,561 INFO [train.py:715] (4/8) Epoch 15, batch 23450, loss[loss=0.1271, simple_loss=0.2111, pruned_loss=0.02152, over 4821.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02923, over 971682.36 frames.], batch size: 25, lr: 1.46e-04
2022-05-08 11:50:07,085 INFO [train.py:715] (4/8) Epoch 15, batch 23500, loss[loss=0.166, simple_loss=0.2368, pruned_loss=0.04755, over 4848.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02923, over 972222.02 frames.], batch size: 30, lr: 1.46e-04
2022-05-08 11:50:44,859 INFO [train.py:715] (4/8) Epoch 15, batch 23550, loss[loss=0.1183, simple_loss=0.1921, pruned_loss=0.02224, over 4960.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02935, over 972054.49 frames.], batch size: 35, lr: 1.46e-04
2022-05-08 11:51:22,852 INFO [train.py:715] (4/8) Epoch 15, batch 23600, loss[loss=0.1435, simple_loss=0.217, pruned_loss=0.03501, over 4985.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2068, pruned_loss=0.02971, over 971713.34 frames.], batch size: 28, lr: 1.46e-04
2022-05-08 11:52:01,277 INFO [train.py:715] (4/8) Epoch 15, batch 23650, loss[loss=0.129, simple_loss=0.2027, pruned_loss=0.02772, over 4862.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2067, pruned_loss=0.02952, over 971142.29 frames.], batch size: 32, lr: 1.46e-04
2022-05-08 11:52:39,165 INFO [train.py:715] (4/8) Epoch 15, batch 23700, loss[loss=0.117, simple_loss=0.1834, pruned_loss=0.02524, over 4770.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02962, over 970536.81 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 11:53:17,230 INFO [train.py:715] (4/8) Epoch 15, batch 23750, loss[loss=0.1028, simple_loss=0.1745, pruned_loss=0.01555, over 4830.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03008, over 970649.86 frames.], batch size: 27, lr: 1.46e-04
2022-05-08 11:53:55,058 INFO [train.py:715] (4/8) Epoch 15, batch 23800, loss[loss=0.1226, simple_loss=0.1964, pruned_loss=0.0244, over 4941.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02992, over 970866.63 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 11:54:33,045 INFO [train.py:715] (4/8) Epoch 15, batch 23850, loss[loss=0.164, simple_loss=0.2364, pruned_loss=0.04583, over 4932.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.03, over 971237.84 frames.], batch size: 23, lr: 1.46e-04
2022-05-08 11:55:11,362 INFO [train.py:715] (4/8) Epoch 15, batch 23900, loss[loss=0.1432, simple_loss=0.2215, pruned_loss=0.0324, over 4861.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03032, over 971758.87 frames.], batch size: 30, lr: 1.46e-04
2022-05-08 11:55:48,902 INFO [train.py:715] (4/8) Epoch 15, batch 23950, loss[loss=0.1502, simple_loss=0.215, pruned_loss=0.0427, over 4825.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.0303, over 971784.12 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 11:56:27,443 INFO [train.py:715] (4/8) Epoch 15, batch 24000, loss[loss=0.1242, simple_loss=0.189, pruned_loss=0.0297, over 4741.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03058, over 971955.14 frames.], batch size: 12, lr: 1.46e-04
2022-05-08 11:56:27,443 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 11:56:37,033 INFO [train.py:742] (4/8) Epoch 15, validation: loss=0.105, simple_loss=0.1886, pruned_loss=0.01071, over 914524.00 frames.
2022-05-08 11:57:15,621 INFO [train.py:715] (4/8) Epoch 15, batch 24050, loss[loss=0.1093, simple_loss=0.1794, pruned_loss=0.01957, over 4978.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2071, pruned_loss=0.03023, over 972013.21 frames.], batch size: 26, lr: 1.46e-04
2022-05-08 11:57:54,189 INFO [train.py:715] (4/8) Epoch 15, batch 24100, loss[loss=0.104, simple_loss=0.1797, pruned_loss=0.01411, over 4936.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2067, pruned_loss=0.02992, over 972813.07 frames.], batch size: 23, lr: 1.46e-04
2022-05-08 11:58:32,190 INFO [train.py:715] (4/8) Epoch 15, batch 24150, loss[loss=0.1661, simple_loss=0.245, pruned_loss=0.04359, over 4845.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2068, pruned_loss=0.02994, over 972377.89 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 11:59:10,406 INFO [train.py:715] (4/8) Epoch 15, batch 24200, loss[loss=0.1583, simple_loss=0.2242, pruned_loss=0.04616, over 4924.00 frames.], tot_loss[loss=0.1338, simple_loss=0.207, pruned_loss=0.03034, over 972384.42 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 11:59:48,421 INFO [train.py:715] (4/8) Epoch 15, batch 24250, loss[loss=0.176, simple_loss=0.2559, pruned_loss=0.04811, over 4775.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2073, pruned_loss=0.03014, over 972700.96 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 12:00:26,746 INFO [train.py:715] (4/8) Epoch 15, batch 24300, loss[loss=0.1453, simple_loss=0.2171, pruned_loss=0.03678, over 4871.00 frames.], tot_loss[loss=0.134, simple_loss=0.2077, pruned_loss=0.03017, over 972964.92 frames.], batch size: 16, lr: 1.46e-04
2022-05-08 12:01:03,898 INFO [train.py:715] (4/8) Epoch 15, batch 24350, loss[loss=0.1293, simple_loss=0.1961, pruned_loss=0.03129, over 4705.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02976, over 972236.90 frames.], batch size: 15, lr: 1.46e-04
2022-05-08 12:01:42,321 INFO [train.py:715] (4/8) Epoch 15, batch 24400, loss[loss=0.1333, simple_loss=0.212, pruned_loss=0.02725, over 4848.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02935, over 973014.44 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 12:02:20,845 INFO [train.py:715] (4/8) Epoch 15, batch 24450, loss[loss=0.1293, simple_loss=0.2031, pruned_loss=0.0278, over 4942.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02933, over 972759.22 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 12:02:58,826 INFO [train.py:715] (4/8) Epoch 15, batch 24500, loss[loss=0.1393, simple_loss=0.2111, pruned_loss=0.03374, over 4824.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02953, over 973069.31 frames.], batch size: 26, lr: 1.46e-04
2022-05-08 12:03:36,483 INFO [train.py:715] (4/8) Epoch 15, batch 24550, loss[loss=0.1081, simple_loss=0.1809, pruned_loss=0.01771, over 4974.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02908, over 972554.28 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 12:04:14,726 INFO [train.py:715] (4/8) Epoch 15, batch 24600, loss[loss=0.1444, simple_loss=0.2178, pruned_loss=0.03551, over 4797.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02927, over 971932.74 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 12:04:53,495 INFO [train.py:715] (4/8) Epoch 15, batch 24650, loss[loss=0.1564, simple_loss=0.225, pruned_loss=0.04387, over 4778.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02979, over 971651.55 frames.], batch size: 18, lr: 1.46e-04
2022-05-08 12:05:31,175 INFO [train.py:715] (4/8) Epoch 15, batch 24700, loss[loss=0.1127, simple_loss=0.1863, pruned_loss=0.0195, over 4970.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.0298, over 971419.37 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 12:06:09,580 INFO [train.py:715] (4/8) Epoch 15, batch 24750, loss[loss=0.1312, simple_loss=0.2172, pruned_loss=0.02266, over 4985.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03035, over 972121.78 frames.], batch size: 25, lr: 1.46e-04
2022-05-08 12:06:47,906 INFO [train.py:715] (4/8) Epoch 15, batch 24800, loss[loss=0.1438, simple_loss=0.2226, pruned_loss=0.0325, over 4987.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02988, over 972699.53 frames.], batch size: 25, lr: 1.46e-04
2022-05-08 12:07:25,660 INFO [train.py:715] (4/8) Epoch 15, batch 24850, loss[loss=0.1101, simple_loss=0.1885, pruned_loss=0.01587, over 4918.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.0298, over 972494.55 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 12:08:03,592 INFO [train.py:715] (4/8) Epoch 15, batch 24900, loss[loss=0.1383, simple_loss=0.2047, pruned_loss=0.03599, over 4969.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02945, over 972752.72 frames.], batch size: 35, lr: 1.46e-04
2022-05-08 12:08:41,840 INFO [train.py:715] (4/8) Epoch 15, batch 24950, loss[loss=0.1415, simple_loss=0.2227, pruned_loss=0.03018, over 4873.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02974, over 974332.19 frames.], batch size: 20, lr: 1.46e-04
2022-05-08 12:09:20,946 INFO [train.py:715] (4/8) Epoch 15, batch 25000, loss[loss=0.1358, simple_loss=0.2048, pruned_loss=0.03341, over 4811.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02962, over 973656.50 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 12:09:58,498 INFO [train.py:715] (4/8) Epoch 15, batch 25050, loss[loss=0.1278, simple_loss=0.2048, pruned_loss=0.02541, over 4961.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02985, over 973568.43 frames.], batch size: 28, lr: 1.46e-04
2022-05-08 12:10:36,536 INFO [train.py:715] (4/8) Epoch 15, batch 25100, loss[loss=0.1133, simple_loss=0.182, pruned_loss=0.02237, over 4810.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2085, pruned_loss=0.02942, over 973580.69 frames.], batch size: 25, lr: 1.46e-04
2022-05-08 12:11:14,986 INFO [train.py:715] (4/8) Epoch 15, batch 25150, loss[loss=0.1328, simple_loss=0.2155, pruned_loss=0.02506, over 4929.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2093, pruned_loss=0.02999, over 973863.54 frames.], batch size: 29, lr: 1.46e-04
2022-05-08 12:11:53,002 INFO [train.py:715] (4/8) Epoch 15, batch 25200, loss[loss=0.1354, simple_loss=0.2058, pruned_loss=0.03249, over 4984.00 frames.], tot_loss[loss=0.1345, simple_loss=0.209, pruned_loss=0.03002, over 973598.19 frames.], batch size: 14, lr: 1.46e-04
2022-05-08 12:12:30,794 INFO [train.py:715] (4/8) Epoch 15, batch 25250, loss[loss=0.1145, simple_loss=0.1886, pruned_loss=0.02024, over 4804.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.02997, over 972737.29 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 12:13:09,118 INFO [train.py:715] (4/8) Epoch 15, batch 25300, loss[loss=0.1204, simple_loss=0.1948, pruned_loss=0.02304, over 4796.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02958, over 973070.92 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 12:13:47,200 INFO [train.py:715] (4/8) Epoch 15, batch 25350, loss[loss=0.1153, simple_loss=0.1913, pruned_loss=0.01965, over 4809.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02914, over 971957.49 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 12:14:24,744 INFO [train.py:715] (4/8) Epoch 15, batch 25400, loss[loss=0.1317, simple_loss=0.2164, pruned_loss=0.02349, over 4983.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02922, over 971486.47 frames.], batch size: 24, lr: 1.46e-04
2022-05-08 12:15:02,817 INFO [train.py:715] (4/8) Epoch 15, batch 25450, loss[loss=0.1341, simple_loss=0.2168, pruned_loss=0.02568, over 4911.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02922, over 972242.37 frames.], batch size: 17, lr: 1.46e-04
2022-05-08 12:15:41,206 INFO [train.py:715] (4/8) Epoch 15, batch 25500, loss[loss=0.1459, simple_loss=0.2322, pruned_loss=0.02978, over 4949.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2081, pruned_loss=0.02905, over 973129.69 frames.], batch size: 21, lr: 1.46e-04
2022-05-08 12:16:18,762 INFO [train.py:715] (4/8) Epoch 15, batch 25550, loss[loss=0.159, simple_loss=0.2372, pruned_loss=0.0404, over 4897.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2091, pruned_loss=0.02956, over 972468.93 frames.], batch size: 39, lr: 1.45e-04
2022-05-08 12:16:56,914 INFO [train.py:715] (4/8) Epoch 15, batch 25600, loss[loss=0.1343, simple_loss=0.2007, pruned_loss=0.03396, over 4914.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2086, pruned_loss=0.02951, over 972440.79 frames.], batch size: 39, lr: 1.45e-04
2022-05-08 12:17:35,536 INFO [train.py:715] (4/8) Epoch 15, batch 25650, loss[loss=0.1289, simple_loss=0.2067, pruned_loss=0.02559, over 4940.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2084, pruned_loss=0.02955, over 972291.06 frames.], batch size: 21, lr: 1.45e-04
2022-05-08 12:18:13,814 INFO [train.py:715] (4/8) Epoch 15, batch 25700, loss[loss=0.1203, simple_loss=0.1919, pruned_loss=0.02434, over 4861.00 frames.], tot_loss[loss=0.134, simple_loss=0.2089, pruned_loss=0.02955, over 973204.48 frames.], batch size: 20, lr: 1.45e-04
2022-05-08 12:18:51,201 INFO [train.py:715] (4/8) Epoch 15, batch 25750, loss[loss=0.1258, simple_loss=0.1965, pruned_loss=0.0276, over 4831.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2094, pruned_loss=0.02966, over 972825.75 frames.], batch size: 26, lr: 1.45e-04
2022-05-08 12:19:29,348 INFO [train.py:715] (4/8) Epoch 15, batch 25800, loss[loss=0.1212, simple_loss=0.1941, pruned_loss=0.02416, over 4792.00 frames.], tot_loss[loss=0.1346, simple_loss=0.209, pruned_loss=0.03012, over 972947.18 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 12:20:07,974 INFO [train.py:715] (4/8) Epoch 15, batch 25850, loss[loss=0.1318, simple_loss=0.2075, pruned_loss=0.02805, over 4921.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03004, over 971912.70 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:20:45,415 INFO [train.py:715] (4/8) Epoch 15, batch 25900, loss[loss=0.1581, simple_loss=0.2387, pruned_loss=0.03875, over 4743.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02953, over 972025.14 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 12:21:24,013 INFO [train.py:715] (4/8) Epoch 15, batch 25950, loss[loss=0.1114, simple_loss=0.1855, pruned_loss=0.01871, over 4909.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02962, over 972350.03 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 12:22:02,166 INFO [train.py:715] (4/8) Epoch 15, batch 26000, loss[loss=0.1224, simple_loss=0.1931, pruned_loss=0.02582, over 4655.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02973, over 972305.54 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 12:22:39,852 INFO [train.py:715] (4/8) Epoch 15, batch 26050, loss[loss=0.128, simple_loss=0.2051, pruned_loss=0.02545, over 4823.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02999, over 971100.17 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 12:23:17,645 INFO [train.py:715] (4/8) Epoch 15, batch 26100, loss[loss=0.1425, simple_loss=0.2155, pruned_loss=0.03472, over 4754.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03, over 970799.77 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 12:23:56,076 INFO [train.py:715] (4/8) Epoch 15, batch 26150, loss[loss=0.1409, simple_loss=0.221, pruned_loss=0.03039, over 4808.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02957, over 970962.37 frames.], batch size: 21, lr: 1.45e-04
2022-05-08 12:24:33,866 INFO [train.py:715] (4/8) Epoch 15, batch 26200, loss[loss=0.1149, simple_loss=0.1907, pruned_loss=0.01954, over 4948.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02943, over 971324.56 frames.], batch size: 24, lr: 1.45e-04
2022-05-08 12:25:11,684 INFO [train.py:715] (4/8) Epoch 15, batch 26250, loss[loss=0.1349, simple_loss=0.2156, pruned_loss=0.02707, over 4971.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02954, over 971635.71 frames.], batch size: 28, lr: 1.45e-04
2022-05-08 12:25:50,002 INFO [train.py:715] (4/8) Epoch 15, batch 26300, loss[loss=0.1319, simple_loss=0.2084, pruned_loss=0.02767, over 4873.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02973, over 971765.53 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 12:26:28,460 INFO [train.py:715] (4/8) Epoch 15, batch 26350, loss[loss=0.1312, simple_loss=0.2104, pruned_loss=0.02604, over 4687.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02956, over 970549.71 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 12:27:06,219 INFO [train.py:715] (4/8) Epoch 15, batch 26400, loss[loss=0.1522, simple_loss=0.2205, pruned_loss=0.04192, over 4856.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02983, over 971486.63 frames.], batch size: 32, lr: 1.45e-04
2022-05-08 12:27:44,349 INFO [train.py:715] (4/8) Epoch 15, batch 26450, loss[loss=0.1453, simple_loss=0.2228, pruned_loss=0.03391, over 4855.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.03015, over 972197.53 frames.], batch size: 39, lr: 1.45e-04
2022-05-08 12:28:22,635 INFO [train.py:715] (4/8) Epoch 15, batch 26500, loss[loss=0.1259, simple_loss=0.2017, pruned_loss=0.02502, over 4842.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03026, over 972260.41 frames.], batch size: 32, lr: 1.45e-04
2022-05-08 12:29:00,418 INFO [train.py:715] (4/8) Epoch 15, batch 26550, loss[loss=0.1099, simple_loss=0.1843, pruned_loss=0.01774, over 4984.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2086, pruned_loss=0.03058, over 972042.97 frames.], batch size: 25, lr: 1.45e-04
2022-05-08 12:29:38,153 INFO [train.py:715] (4/8) Epoch 15, batch 26600, loss[loss=0.1381, simple_loss=0.2221, pruned_loss=0.02706, over 4810.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03002, over 971564.74 frames.], batch size: 25, lr: 1.45e-04
2022-05-08 12:30:16,186 INFO [train.py:715] (4/8) Epoch 15, batch 26650, loss[loss=0.1145, simple_loss=0.1881, pruned_loss=0.02044, over 4828.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03009, over 971655.52 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 12:30:54,317 INFO [train.py:715] (4/8) Epoch 15, batch 26700, loss[loss=0.1234, simple_loss=0.1889, pruned_loss=0.02897, over 4981.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03034, over 972227.03 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 12:31:31,944 INFO [train.py:715] (4/8) Epoch 15, batch 26750, loss[loss=0.174, simple_loss=0.2593, pruned_loss=0.04433, over 4870.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03023, over 972023.34 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 12:32:10,362 INFO [train.py:715] (4/8) Epoch 15, batch 26800, loss[loss=0.119, simple_loss=0.1996, pruned_loss=0.01919, over 4851.00 frames.], tot_loss[loss=0.1355, simple_loss=0.2093, pruned_loss=0.03079, over 971806.34 frames.], batch size: 20, lr: 1.45e-04
2022-05-08 12:32:48,681 INFO [train.py:715] (4/8) Epoch 15, batch 26850, loss[loss=0.1677, simple_loss=0.2314, pruned_loss=0.05194, over 4870.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03096, over 971177.90 frames.], batch size: 20, lr: 1.45e-04
2022-05-08 12:33:26,760 INFO [train.py:715] (4/8) Epoch 15, batch 26900, loss[loss=0.1055, simple_loss=0.1844, pruned_loss=0.01332, over 4793.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03026, over 970904.67 frames.], batch size: 24, lr: 1.45e-04
2022-05-08 12:34:04,500 INFO [train.py:715] (4/8) Epoch 15, batch 26950, loss[loss=0.1386, simple_loss=0.2098, pruned_loss=0.03366, over 4686.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03026, over 970930.01 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 12:34:42,583 INFO [train.py:715] (4/8) Epoch 15, batch 27000, loss[loss=0.1259, simple_loss=0.2008, pruned_loss=0.02553, over 4878.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02988, over 971183.92 frames.], batch size: 22, lr: 1.45e-04
2022-05-08 12:34:42,584 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 12:34:52,202 INFO [train.py:742] (4/8) Epoch 15, validation: loss=0.1049, simple_loss=0.1884, pruned_loss=0.01064, over 914524.00 frames.
2022-05-08 12:35:31,297 INFO [train.py:715] (4/8) Epoch 15, batch 27050, loss[loss=0.1245, simple_loss=0.1905, pruned_loss=0.02923, over 4868.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.03035, over 971546.69 frames.], batch size: 20, lr: 1.45e-04
2022-05-08 12:36:10,019 INFO [train.py:715] (4/8) Epoch 15, batch 27100, loss[loss=0.1362, simple_loss=0.1958, pruned_loss=0.03833, over 4887.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2085, pruned_loss=0.03024, over 971398.38 frames.], batch size: 22, lr: 1.45e-04
2022-05-08 12:36:48,673 INFO [train.py:715] (4/8) Epoch 15, batch 27150, loss[loss=0.1601, simple_loss=0.2283, pruned_loss=0.04593, over 4868.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02986, over 971582.92 frames.], batch size: 30, lr: 1.45e-04
2022-05-08 12:37:26,865 INFO [train.py:715] (4/8) Epoch 15, batch 27200, loss[loss=0.1386, simple_loss=0.2211, pruned_loss=0.02804, over 4764.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02959, over 971741.15 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 12:38:05,901 INFO [train.py:715] (4/8) Epoch 15, batch 27250, loss[loss=0.1511, simple_loss=0.2213, pruned_loss=0.04044, over 4777.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2088, pruned_loss=0.02978, over 972206.85 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:38:43,692 INFO [train.py:715] (4/8) Epoch 15, batch 27300, loss[loss=0.1284, simple_loss=0.2015, pruned_loss=0.02763, over 4934.00 frames.], tot_loss[loss=0.135, simple_loss=0.2094, pruned_loss=0.03027, over 973142.02 frames.], batch size: 39, lr: 1.45e-04
2022-05-08 12:39:21,920 INFO [train.py:715] (4/8) Epoch 15, batch 27350, loss[loss=0.1322, simple_loss=0.2007, pruned_loss=0.03186, over 4983.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03, over 973248.68 frames.], batch size: 31, lr: 1.45e-04
2022-05-08 12:40:00,099 INFO [train.py:715] (4/8) Epoch 15, batch 27400, loss[loss=0.1444, simple_loss=0.2189, pruned_loss=0.03489, over 4833.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03009, over 973776.65 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 12:40:38,395 INFO [train.py:715] (4/8) Epoch 15, batch 27450, loss[loss=0.1256, simple_loss=0.1992, pruned_loss=0.02596, over 4789.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02982, over 973302.98 frames.], batch size: 24, lr: 1.45e-04
2022-05-08 12:41:16,659 INFO [train.py:715] (4/8) Epoch 15, batch 27500, loss[loss=0.1592, simple_loss=0.233, pruned_loss=0.04272, over 4829.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03001, over 972908.69 frames.], batch size: 30, lr: 1.45e-04
2022-05-08 12:41:54,849 INFO [train.py:715] (4/8) Epoch 15, batch 27550, loss[loss=0.1571, simple_loss=0.2394, pruned_loss=0.03743, over 4771.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02986, over 973602.53 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:42:33,402 INFO [train.py:715] (4/8) Epoch 15, batch 27600, loss[loss=0.1301, simple_loss=0.2086, pruned_loss=0.02578, over 4863.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02994, over 972972.89 frames.], batch size: 20, lr: 1.45e-04
2022-05-08 12:43:10,759 INFO [train.py:715] (4/8) Epoch 15, batch 27650, loss[loss=0.1189, simple_loss=0.2009, pruned_loss=0.01845, over 4790.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2067, pruned_loss=0.02957, over 972231.99 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 12:43:49,458 INFO [train.py:715] (4/8) Epoch 15, batch 27700, loss[loss=0.1268, simple_loss=0.2028, pruned_loss=0.02535, over 4820.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2058, pruned_loss=0.02918, over 972657.73 frames.], batch size: 27, lr: 1.45e-04
2022-05-08 12:44:27,754 INFO [train.py:715] (4/8) Epoch 15, batch 27750, loss[loss=0.1343, simple_loss=0.2109, pruned_loss=0.02884, over 4868.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2064, pruned_loss=0.02944, over 971903.68 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 12:45:06,220 INFO [train.py:715] (4/8) Epoch 15, batch 27800, loss[loss=0.1425, simple_loss=0.2161, pruned_loss=0.03448, over 4834.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02957, over 972029.09 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 12:45:44,232 INFO [train.py:715] (4/8) Epoch 15, batch 27850, loss[loss=0.1376, simple_loss=0.2246, pruned_loss=0.02532, over 4913.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2067, pruned_loss=0.02987, over 972859.37 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:46:21,973 INFO [train.py:715] (4/8) Epoch 15, batch 27900, loss[loss=0.1231, simple_loss=0.2012, pruned_loss=0.02252, over 4960.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02993, over 972540.56 frames.], batch size: 24, lr: 1.45e-04
2022-05-08 12:47:00,798 INFO [train.py:715] (4/8) Epoch 15, batch 27950, loss[loss=0.1194, simple_loss=0.1894, pruned_loss=0.02476, over 4933.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02996, over 972400.15 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:47:38,666 INFO [train.py:715] (4/8) Epoch 15, batch 28000, loss[loss=0.129, simple_loss=0.2057, pruned_loss=0.0261, over 4806.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02995, over 972484.41 frames.], batch size: 25, lr: 1.45e-04
2022-05-08 12:48:16,879 INFO [train.py:715] (4/8) Epoch 15, batch 28050, loss[loss=0.1463, simple_loss=0.221, pruned_loss=0.03583, over 4835.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03001, over 972480.82 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 12:48:55,111 INFO [train.py:715] (4/8) Epoch 15, batch 28100, loss[loss=0.1065, simple_loss=0.1769, pruned_loss=0.01808, over 4753.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02994, over 972700.97 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 12:49:33,361 INFO [train.py:715] (4/8) Epoch 15, batch 28150, loss[loss=0.146, simple_loss=0.2235, pruned_loss=0.03426, over 4835.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02998, over 973286.51 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 12:50:11,123 INFO [train.py:715] (4/8) Epoch 15, batch 28200, loss[loss=0.1386, simple_loss=0.229, pruned_loss=0.02409, over 4936.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03023, over 973257.90 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 12:50:49,026 INFO [train.py:715] (4/8) Epoch 15, batch 28250, loss[loss=0.1237, simple_loss=0.1955, pruned_loss=0.02592, over 4833.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2088, pruned_loss=0.03009, over 973169.94 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 12:51:28,179 INFO [train.py:715] (4/8) Epoch 15, batch 28300, loss[loss=0.1535, simple_loss=0.2339, pruned_loss=0.03653, over 4800.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03054, over 972789.70 frames.], batch size: 25, lr: 1.45e-04
2022-05-08 12:52:05,676 INFO [train.py:715] (4/8) Epoch 15, batch 28350, loss[loss=0.1484, simple_loss=0.2208, pruned_loss=0.03799, over 4947.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03099, over 972514.85 frames.], batch size: 23, lr: 1.45e-04
2022-05-08 12:52:43,905 INFO [train.py:715] (4/8) Epoch 15, batch 28400, loss[loss=0.1714, simple_loss=0.2434, pruned_loss=0.04972, over 4961.00 frames.], tot_loss[loss=0.1352, simple_loss=0.209, pruned_loss=0.03068, over 972967.14 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 12:53:22,223 INFO [train.py:715] (4/8) Epoch 15, batch 28450, loss[loss=0.1456, simple_loss=0.225, pruned_loss=0.03315, over 4904.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03013, over 972398.10 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 12:54:00,367 INFO [train.py:715] (4/8) Epoch 15, batch 28500, loss[loss=0.1472, simple_loss=0.2259, pruned_loss=0.03427, over 4645.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03053, over 972950.09 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 12:54:38,501 INFO [train.py:715] (4/8) Epoch 15, batch 28550, loss[loss=0.1296, simple_loss=0.2051, pruned_loss=0.027, over 4800.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03029, over 972890.80 frames.], batch size: 21, lr: 1.45e-04
2022-05-08 12:55:16,671 INFO [train.py:715] (4/8) Epoch 15, batch 28600, loss[loss=0.1101, simple_loss=0.1908, pruned_loss=0.01473, over 4960.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02988, over 973496.88 frames.], batch size: 24, lr: 1.45e-04
2022-05-08 12:55:55,088 INFO [train.py:715] (4/8) Epoch 15, batch 28650, loss[loss=0.1228, simple_loss=0.1942, pruned_loss=0.0257, over 4848.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03016, over 973119.13 frames.], batch size: 20, lr: 1.45e-04
2022-05-08 12:56:32,940 INFO [train.py:715] (4/8) Epoch 15, batch 28700, loss[loss=0.1358, simple_loss=0.2089, pruned_loss=0.03137, over 4934.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2087, pruned_loss=0.03017, over 972812.11 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:57:11,382 INFO [train.py:715] (4/8) Epoch 15, batch 28750, loss[loss=0.1162, simple_loss=0.1908, pruned_loss=0.02081, over 4932.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02976, over 973549.31 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 12:57:50,112 INFO [train.py:715] (4/8) Epoch 15, batch 28800, loss[loss=0.1309, simple_loss=0.2026, pruned_loss=0.02955, over 4917.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02986, over 973236.90 frames.], batch size: 23, lr: 1.45e-04
2022-05-08 12:58:28,471 INFO [train.py:715] (4/8) Epoch 15, batch 28850, loss[loss=0.1508, simple_loss=0.2336, pruned_loss=0.03404, over 4793.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2092, pruned_loss=0.03063, over 973136.70 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 12:59:06,964 INFO [train.py:715] (4/8) Epoch 15, batch 28900, loss[loss=0.1357, simple_loss=0.2019, pruned_loss=0.0347, over 4906.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03035, over 973214.49 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 12:59:45,681 INFO [train.py:715] (4/8) Epoch 15, batch 28950, loss[loss=0.1335, simple_loss=0.2182, pruned_loss=0.02443, over 4987.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.02991, over 972771.53 frames.], batch size: 27, lr: 1.45e-04
2022-05-08 13:00:24,852 INFO [train.py:715] (4/8) Epoch 15, batch 29000, loss[loss=0.09386, simple_loss=0.165, pruned_loss=0.01137, over 4637.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02991, over 972271.98 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 13:01:03,427 INFO [train.py:715] (4/8) Epoch 15, batch 29050, loss[loss=0.1378, simple_loss=0.2161, pruned_loss=0.02974, over 4754.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03012, over 971566.25 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 13:01:42,351 INFO [train.py:715] (4/8) Epoch 15, batch 29100, loss[loss=0.1655, simple_loss=0.23, pruned_loss=0.05051, over 4833.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03034, over 971832.12 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:02:21,517 INFO [train.py:715] (4/8) Epoch 15, batch 29150, loss[loss=0.1268, simple_loss=0.2064, pruned_loss=0.02359, over 4801.00 frames.], tot_loss[loss=0.135, simple_loss=0.2095, pruned_loss=0.03029, over 971643.94 frames.], batch size: 25, lr: 1.45e-04
2022-05-08 13:03:00,528 INFO [train.py:715] (4/8) Epoch 15, batch 29200, loss[loss=0.122, simple_loss=0.1949, pruned_loss=0.0246, over 4833.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2086, pruned_loss=0.02983, over 971852.55 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:03:38,940 INFO [train.py:715] (4/8) Epoch 15, batch 29250, loss[loss=0.1386, simple_loss=0.2169, pruned_loss=0.03011, over 4929.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02977, over 971808.82 frames.], batch size: 23, lr: 1.45e-04
2022-05-08 13:04:17,999 INFO [train.py:715] (4/8) Epoch 15, batch 29300, loss[loss=0.157, simple_loss=0.2253, pruned_loss=0.04431, over 4937.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.0298, over 972201.55 frames.], batch size: 21, lr: 1.45e-04
2022-05-08 13:04:56,887 INFO [train.py:715] (4/8) Epoch 15, batch 29350, loss[loss=0.1259, simple_loss=0.1919, pruned_loss=0.02995, over 4909.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03015, over 972189.74 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:05:35,474 INFO [train.py:715] (4/8) Epoch 15, batch 29400, loss[loss=0.1177, simple_loss=0.1888, pruned_loss=0.0233, over 4794.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2084, pruned_loss=0.03038, over 971469.34 frames.], batch size: 21, lr: 1.45e-04
2022-05-08 13:06:14,532 INFO [train.py:715] (4/8) Epoch 15, batch 29450, loss[loss=0.138, simple_loss=0.217, pruned_loss=0.02948, over 4773.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2071, pruned_loss=0.03009, over 970908.49 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:06:53,807 INFO [train.py:715] (4/8) Epoch 15, batch 29500, loss[loss=0.09612, simple_loss=0.1626, pruned_loss=0.01481, over 4836.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02948, over 970348.76 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 13:07:31,955 INFO [train.py:715] (4/8) Epoch 15, batch 29550, loss[loss=0.1479, simple_loss=0.2204, pruned_loss=0.03769, over 4872.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02922, over 970341.80 frames.], batch size: 32, lr: 1.45e-04
2022-05-08 13:08:09,733 INFO [train.py:715] (4/8) Epoch 15, batch 29600, loss[loss=0.1315, simple_loss=0.2073, pruned_loss=0.02789, over 4785.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02972, over 971257.87 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:08:48,780 INFO [train.py:715] (4/8) Epoch 15, batch 29650, loss[loss=0.1182, simple_loss=0.1979, pruned_loss=0.01919, over 4975.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.02935, over 971947.87 frames.], batch size: 28, lr: 1.45e-04
2022-05-08 13:09:27,543 INFO [train.py:715] (4/8) Epoch 15, batch 29700, loss[loss=0.1492, simple_loss=0.2192, pruned_loss=0.03954, over 4975.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.0299, over 973179.25 frames.], batch size: 25, lr: 1.45e-04
2022-05-08 13:10:05,827 INFO [train.py:715] (4/8) Epoch 15, batch 29750, loss[loss=0.1474, simple_loss=0.2111, pruned_loss=0.04186, over 4776.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.0299, over 973184.32 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:10:43,495 INFO [train.py:715] (4/8) Epoch 15, batch 29800, loss[loss=0.1165, simple_loss=0.1861, pruned_loss=0.02339, over 4848.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02975, over 972781.52 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:11:22,784 INFO [train.py:715] (4/8) Epoch 15, batch 29850, loss[loss=0.1049, simple_loss=0.1786, pruned_loss=0.01561, over 4828.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02938, over 972436.46 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 13:12:04,494 INFO [train.py:715] (4/8) Epoch 15, batch 29900, loss[loss=0.1283, simple_loss=0.1999, pruned_loss=0.02837, over 4987.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02989, over 973277.13 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 13:12:43,054 INFO [train.py:715] (4/8) Epoch 15, batch 29950, loss[loss=0.1477, simple_loss=0.2236, pruned_loss=0.03585, over 4857.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02986, over 973564.95 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 13:13:21,389 INFO [train.py:715] (4/8) Epoch 15, batch 30000, loss[loss=0.1449, simple_loss=0.2234, pruned_loss=0.03321, over 4940.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02963, over 973755.60 frames.], batch size: 39, lr: 1.45e-04
2022-05-08 13:13:21,389 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 13:13:30,914 INFO [train.py:742] (4/8) Epoch 15, validation: loss=0.1049, simple_loss=0.1885, pruned_loss=0.01066, over 914524.00 frames.
2022-05-08 13:14:09,968 INFO [train.py:715] (4/8) Epoch 15, batch 30050, loss[loss=0.1045, simple_loss=0.1862, pruned_loss=0.01143, over 4921.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02973, over 973639.75 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 13:14:49,057 INFO [train.py:715] (4/8) Epoch 15, batch 30100, loss[loss=0.1303, simple_loss=0.2189, pruned_loss=0.02078, over 4921.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.02997, over 972544.89 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 13:15:28,215 INFO [train.py:715] (4/8) Epoch 15, batch 30150, loss[loss=0.1376, simple_loss=0.2057, pruned_loss=0.03478, over 4983.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.03018, over 972153.05 frames.], batch size: 28, lr: 1.45e-04
2022-05-08 13:16:07,095 INFO [train.py:715] (4/8) Epoch 15, batch 30200, loss[loss=0.1408, simple_loss=0.2162, pruned_loss=0.03275, over 4772.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03012, over 971693.69 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:16:46,389 INFO [train.py:715] (4/8) Epoch 15, batch 30250, loss[loss=0.1197, simple_loss=0.1857, pruned_loss=0.02683, over 4780.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2084, pruned_loss=0.03013, over 971514.51 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:17:25,213 INFO [train.py:715] (4/8) Epoch 15, batch 30300, loss[loss=0.1189, simple_loss=0.1929, pruned_loss=0.0225, over 4933.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2089, pruned_loss=0.02996, over 971706.12 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:18:03,183 INFO [train.py:715] (4/8) Epoch 15, batch 30350, loss[loss=0.1081, simple_loss=0.1819, pruned_loss=0.01711, over 4854.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.02996, over 972900.78 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 13:18:42,405 INFO [train.py:715] (4/8) Epoch 15, batch 30400, loss[loss=0.1474, simple_loss=0.2235, pruned_loss=0.0357, over 4866.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02958, over 972686.71 frames.], batch size: 22, lr: 1.45e-04
2022-05-08 13:19:21,268 INFO [train.py:715] (4/8) Epoch 15, batch 30450, loss[loss=0.1243, simple_loss=0.192, pruned_loss=0.02827, over 4974.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02979, over 972518.33 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 13:20:00,133 INFO [train.py:715] (4/8) Epoch 15, batch 30500, loss[loss=0.1567, simple_loss=0.22, pruned_loss=0.04669, over 4839.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03029, over 972012.82 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:20:38,343 INFO [train.py:715] (4/8) Epoch 15, batch 30550, loss[loss=0.1116, simple_loss=0.1953, pruned_loss=0.01394, over 4874.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03048, over 971694.40 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 13:21:17,387 INFO [train.py:715] (4/8) Epoch 15, batch 30600, loss[loss=0.1045, simple_loss=0.1739, pruned_loss=0.01757, over 4784.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2087, pruned_loss=0.0304, over 971967.38 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 13:21:56,193 INFO [train.py:715] (4/8) Epoch 15, batch 30650, loss[loss=0.1193, simple_loss=0.1888, pruned_loss=0.02496, over 4810.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2093, pruned_loss=0.03051, over 972662.92 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 13:22:34,335 INFO [train.py:715] (4/8) Epoch 15, batch 30700, loss[loss=0.1337, simple_loss=0.2092, pruned_loss=0.02907, over 4899.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.03011, over 972566.68 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 13:23:13,404 INFO [train.py:715] (4/8) Epoch 15, batch 30750, loss[loss=0.1307, simple_loss=0.2056, pruned_loss=0.02789, over 4928.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03043, over 972850.79 frames.], batch size: 21, lr: 1.45e-04
2022-05-08 13:23:52,074 INFO [train.py:715] (4/8) Epoch 15, batch 30800, loss[loss=0.1391, simple_loss=0.2093, pruned_loss=0.03449, over 4855.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03018, over 971886.04 frames.], batch size: 32, lr: 1.45e-04
2022-05-08 13:24:30,181 INFO [train.py:715] (4/8) Epoch 15, batch 30850, loss[loss=0.1347, simple_loss=0.2131, pruned_loss=0.02818, over 4934.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.03002, over 971753.67 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:25:08,417 INFO [train.py:715] (4/8) Epoch 15, batch 30900, loss[loss=0.1196, simple_loss=0.2041, pruned_loss=0.01755, over 4955.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02974, over 972617.96 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:25:46,855 INFO [train.py:715] (4/8) Epoch 15, batch 30950, loss[loss=0.1261, simple_loss=0.2006, pruned_loss=0.02578, over 4785.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03028, over 972616.05 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:26:25,012 INFO [train.py:715] (4/8) Epoch 15, batch 31000, loss[loss=0.1189, simple_loss=0.1898, pruned_loss=0.02401, over 4780.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02986, over 972258.61 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 13:27:02,424 INFO [train.py:715] (4/8) Epoch 15, batch 31050, loss[loss=0.1209, simple_loss=0.2015, pruned_loss=0.0202, over 4887.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2081, pruned_loss=0.02941, over 972297.61 frames.], batch size: 22, lr: 1.45e-04
2022-05-08 13:27:40,734 INFO [train.py:715] (4/8) Epoch 15, batch 31100, loss[loss=0.1494, simple_loss=0.2306, pruned_loss=0.03407, over 4774.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2085, pruned_loss=0.02963, over 972252.06 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:28:18,885 INFO [train.py:715] (4/8) Epoch 15, batch 31150, loss[loss=0.1183, simple_loss=0.1942, pruned_loss=0.02119, over 4804.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2094, pruned_loss=0.02976, over 973103.69 frames.], batch size: 21, lr: 1.45e-04
2022-05-08 13:28:57,277 INFO [train.py:715] (4/8) Epoch 15, batch 31200, loss[loss=0.1484, simple_loss=0.2331, pruned_loss=0.03186, over 4787.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2092, pruned_loss=0.02993, over 971744.61 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:29:34,875 INFO [train.py:715] (4/8) Epoch 15, batch 31250, loss[loss=0.1309, simple_loss=0.1895, pruned_loss=0.03611, over 4977.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02961, over 972010.41 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:30:13,197 INFO [train.py:715] (4/8) Epoch 15, batch 31300, loss[loss=0.125, simple_loss=0.2021, pruned_loss=0.02398, over 4872.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02962, over 972624.17 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 13:30:51,249 INFO [train.py:715] (4/8) Epoch 15, batch 31350, loss[loss=0.1545, simple_loss=0.2189, pruned_loss=0.04505, over 4954.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03005, over 972819.70 frames.], batch size: 24, lr: 1.45e-04
2022-05-08 13:31:28,510 INFO [train.py:715] (4/8) Epoch 15, batch 31400, loss[loss=0.1628, simple_loss=0.2356, pruned_loss=0.04502, over 4941.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03026, over 972057.63 frames.], batch size: 39, lr: 1.45e-04
2022-05-08 13:32:06,855 INFO [train.py:715] (4/8) Epoch 15, batch 31450, loss[loss=0.1602, simple_loss=0.2332, pruned_loss=0.04363, over 4853.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2094, pruned_loss=0.03069, over 972313.16 frames.], batch size: 30, lr: 1.45e-04
2022-05-08 13:32:45,119 INFO [train.py:715] (4/8) Epoch 15, batch 31500, loss[loss=0.1252, simple_loss=0.1961, pruned_loss=0.02716, over 4812.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02972, over 972270.81 frames.], batch size: 27, lr: 1.45e-04
2022-05-08 13:33:23,445 INFO [train.py:715] (4/8) Epoch 15, batch 31550, loss[loss=0.1445, simple_loss=0.2246, pruned_loss=0.03222, over 4656.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.0293, over 971808.54 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 13:34:01,212 INFO [train.py:715] (4/8) Epoch 15, batch 31600, loss[loss=0.1193, simple_loss=0.2028, pruned_loss=0.01791, over 4883.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02918, over 971765.00 frames.], batch size: 22, lr: 1.45e-04
2022-05-08 13:34:39,668 INFO [train.py:715] (4/8) Epoch 15, batch 31650, loss[loss=0.1133, simple_loss=0.1925, pruned_loss=0.01705, over 4854.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02921, over 972897.69 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 13:35:18,002 INFO [train.py:715] (4/8) Epoch 15, batch 31700, loss[loss=0.1783, simple_loss=0.2513, pruned_loss=0.05267, over 4778.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02921, over 972633.54 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 13:35:55,496 INFO [train.py:715] (4/8) Epoch 15, batch 31750, loss[loss=0.134, simple_loss=0.205, pruned_loss=0.03149, over 4863.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02897, over 971776.25 frames.], batch size: 30, lr: 1.45e-04
2022-05-08 13:36:34,377 INFO [train.py:715] (4/8) Epoch 15, batch 31800, loss[loss=0.1254, simple_loss=0.2022, pruned_loss=0.02429, over 4916.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02875, over 972321.16 frames.], batch size: 17, lr: 1.45e-04
2022-05-08 13:37:12,848 INFO [train.py:715] (4/8) Epoch 15, batch 31850, loss[loss=0.1391, simple_loss=0.2134, pruned_loss=0.03243, over 4882.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02942, over 972750.47 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 13:37:52,388 INFO [train.py:715] (4/8) Epoch 15, batch 31900, loss[loss=0.1478, simple_loss=0.2199, pruned_loss=0.03785, over 4906.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02926, over 972852.39 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:38:29,677 INFO [train.py:715] (4/8) Epoch 15, batch 31950, loss[loss=0.1351, simple_loss=0.2152, pruned_loss=0.0275, over 4976.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.0294, over 971684.78 frames.], batch size: 25, lr: 1.45e-04
2022-05-08 13:39:08,340 INFO [train.py:715] (4/8) Epoch 15, batch 32000, loss[loss=0.1283, simple_loss=0.1915, pruned_loss=0.03256, over 4900.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.0294, over 971249.56 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 13:39:46,517 INFO [train.py:715] (4/8) Epoch 15, batch 32050, loss[loss=0.1249, simple_loss=0.2074, pruned_loss=0.02123, over 4927.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02913, over 971744.33 frames.], batch size: 29, lr: 1.45e-04
2022-05-08 13:40:23,947 INFO [train.py:715] (4/8) Epoch 15, batch 32100, loss[loss=0.1266, simple_loss=0.2138, pruned_loss=0.01974, over 4874.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03007, over 971412.38 frames.], batch size: 20, lr: 1.45e-04
2022-05-08 13:41:02,341 INFO [train.py:715] (4/8) Epoch 15, batch 32150, loss[loss=0.1283, simple_loss=0.2059, pruned_loss=0.0253, over 4903.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02958, over 971617.59 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:41:40,505 INFO [train.py:715] (4/8) Epoch 15, batch 32200, loss[loss=0.1211, simple_loss=0.1859, pruned_loss=0.02812, over 4843.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2065, pruned_loss=0.02959, over 972470.50 frames.], batch size: 32, lr: 1.45e-04
2022-05-08 13:42:19,022 INFO [train.py:715] (4/8) Epoch 15, batch 32250, loss[loss=0.1561, simple_loss=0.2224, pruned_loss=0.04489, over 4752.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2064, pruned_loss=0.02965, over 972275.66 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 13:42:56,891 INFO [train.py:715] (4/8) Epoch 15, batch 32300, loss[loss=0.1684, simple_loss=0.2531, pruned_loss=0.04182, over 4699.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2069, pruned_loss=0.02983, over 971848.32 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:43:35,757 INFO [train.py:715] (4/8) Epoch 15, batch 32350, loss[loss=0.1262, simple_loss=0.1961, pruned_loss=0.02815, over 4914.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02971, over 971558.86 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:44:14,154 INFO [train.py:715] (4/8) Epoch 15, batch 32400, loss[loss=0.1563, simple_loss=0.2214, pruned_loss=0.04566, over 4833.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02982, over 972100.20 frames.], batch size: 30, lr: 1.45e-04
2022-05-08 13:44:51,907 INFO [train.py:715] (4/8) Epoch 15, batch 32450, loss[loss=0.1437, simple_loss=0.22, pruned_loss=0.03368, over 4982.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02956, over 972879.28 frames.], batch size: 15, lr: 1.45e-04
2022-05-08 13:45:30,471 INFO [train.py:715] (4/8) Epoch 15, batch 32500, loss[loss=0.1454, simple_loss=0.2213, pruned_loss=0.03477, over 4955.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02962, over 972696.72 frames.], batch size: 14, lr: 1.45e-04
2022-05-08 13:46:08,936 INFO [train.py:715] (4/8) Epoch 15, batch 32550, loss[loss=0.133, simple_loss=0.2099, pruned_loss=0.02806, over 4920.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02956, over 972865.83 frames.], batch size: 23, lr: 1.45e-04
2022-05-08 13:46:47,811 INFO [train.py:715] (4/8) Epoch 15, batch 32600, loss[loss=0.1256, simple_loss=0.2091, pruned_loss=0.02111, over 4918.00 frames.], tot_loss[loss=0.134, simple_loss=0.2086, pruned_loss=0.02967, over 972351.99 frames.], batch size: 39, lr: 1.45e-04
2022-05-08 13:47:26,414 INFO [train.py:715] (4/8) Epoch 15, batch 32650, loss[loss=0.1412, simple_loss=0.2175, pruned_loss=0.03249, over 4854.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2084, pruned_loss=0.02921, over 972226.12 frames.], batch size: 32, lr: 1.45e-04
2022-05-08 13:48:05,085 INFO [train.py:715] (4/8) Epoch 15, batch 32700, loss[loss=0.1378, simple_loss=0.211, pruned_loss=0.03231, over 4743.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2084, pruned_loss=0.02914, over 972040.48 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 13:48:43,311 INFO [train.py:715] (4/8) Epoch 15, batch 32750, loss[loss=0.148, simple_loss=0.2267, pruned_loss=0.0346, over 4841.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2085, pruned_loss=0.02949, over 972136.99 frames.], batch size: 30, lr: 1.45e-04
2022-05-08 13:49:21,521 INFO [train.py:715] (4/8) Epoch 15, batch 32800, loss[loss=0.1288, simple_loss=0.2004, pruned_loss=0.02861, over 4747.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2089, pruned_loss=0.03014, over 971916.17 frames.], batch size: 16, lr: 1.45e-04
2022-05-08 13:49:59,266 INFO [train.py:715] (4/8) Epoch 15, batch 32850, loss[loss=0.1247, simple_loss=0.2061, pruned_loss=0.02166, over 4817.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02982, over 971800.03 frames.], batch size: 26, lr: 1.45e-04
2022-05-08 13:50:37,485 INFO [train.py:715] (4/8) Epoch 15, batch 32900, loss[loss=0.135, simple_loss=0.2151, pruned_loss=0.02744, over 4942.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.02997, over 972417.70 frames.], batch size: 39, lr: 1.45e-04
2022-05-08 13:51:16,078 INFO [train.py:715] (4/8) Epoch 15, batch 32950, loss[loss=0.1235, simple_loss=0.1886, pruned_loss=0.02924, over 4912.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02982, over 973690.67 frames.], batch size: 19, lr: 1.45e-04
2022-05-08 13:51:54,464 INFO [train.py:715] (4/8) Epoch 15, batch 33000, loss[loss=0.1294, simple_loss=0.2083, pruned_loss=0.02528, over 4921.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02968, over 973306.93 frames.], batch size: 18, lr: 1.45e-04
2022-05-08 13:51:54,465 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 13:52:03,984 INFO [train.py:742] (4/8) Epoch 15, validation: loss=0.1052, simple_loss=0.1886, pruned_loss=0.01088, over 914524.00 frames.
2022-05-08 13:52:42,025 INFO [train.py:715] (4/8) Epoch 15, batch 33050, loss[loss=0.09599, simple_loss=0.165, pruned_loss=0.01351, over 4794.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02991, over 972426.94 frames.], batch size: 12, lr: 1.45e-04
2022-05-08 13:53:20,376 INFO [train.py:715] (4/8) Epoch 15, batch 33100, loss[loss=0.1266, simple_loss=0.1925, pruned_loss=0.03037, over 4834.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.0294, over 972087.40 frames.], batch size: 13, lr: 1.45e-04
2022-05-08 13:53:58,081 INFO [train.py:715] (4/8) Epoch 15, batch 33150, loss[loss=0.1601, simple_loss=0.2375, pruned_loss=0.04135, over 4862.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02981, over 971941.86 frames.], batch size: 20, lr: 1.44e-04
2022-05-08 13:54:37,161 INFO [train.py:715] (4/8) Epoch 15, batch 33200, loss[loss=0.1469, simple_loss=0.2305, pruned_loss=0.03166, over 4782.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02964, over 972215.03 frames.], batch size: 17, lr: 1.44e-04
2022-05-08 13:55:15,594 INFO [train.py:715] (4/8) Epoch 15, batch 33250, loss[loss=0.1398, simple_loss=0.2103, pruned_loss=0.03466, over 4926.00 frames.], tot_loss[loss=0.1334, simple_loss=0.207, pruned_loss=0.02985, over 972779.02 frames.], batch size: 29, lr: 1.44e-04
2022-05-08 13:55:53,705 INFO [train.py:715] (4/8) Epoch 15, batch 33300, loss[loss=0.1444, simple_loss=0.2083, pruned_loss=0.04025, over 4836.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.03024, over 972544.85 frames.], batch size: 15, lr: 1.44e-04
2022-05-08 13:56:31,675 INFO [train.py:715] (4/8) Epoch 15, batch 33350, loss[loss=0.1639, simple_loss=0.2429, pruned_loss=0.04246, over 4812.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02974, over 972547.76 frames.], batch size: 25, lr: 1.44e-04
2022-05-08 13:57:09,331 INFO [train.py:715] (4/8) Epoch 15, batch 33400, loss[loss=0.1238, simple_loss=0.194, pruned_loss=0.02686, over 4794.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02931, over 973269.33 frames.], batch size: 14, lr: 1.44e-04
2022-05-08 13:57:47,384 INFO [train.py:715] (4/8) Epoch 15, batch 33450, loss[loss=0.166, simple_loss=0.2353, pruned_loss=0.04839, over 4861.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2081, pruned_loss=0.02929, over 972958.98 frames.], batch size: 30, lr: 1.44e-04
2022-05-08 13:58:25,103 INFO [train.py:715] (4/8) Epoch 15, batch 33500, loss[loss=0.1658, simple_loss=0.2398, pruned_loss=0.04594, over 4792.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2081, pruned_loss=0.02928, over 972159.25 frames.], batch size: 24, lr: 1.44e-04
2022-05-08 13:59:02,922 INFO [train.py:715] (4/8) Epoch 15, batch 33550, loss[loss=0.1281, simple_loss=0.196, pruned_loss=0.03006, over 4861.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02893, over 971558.80 frames.], batch size: 22, lr: 1.44e-04
2022-05-08 13:59:40,600 INFO [train.py:715] (4/8) Epoch 15, batch 33600, loss[loss=0.147, simple_loss=0.2108, pruned_loss=0.04155, over 4984.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02929, over 972026.43 frames.], batch size: 14, lr: 1.44e-04
2022-05-08 14:00:18,651 INFO [train.py:715] (4/8) Epoch 15, batch 33650, loss[loss=0.1271, simple_loss=0.208, pruned_loss=0.02307, over 4845.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02986, over 971551.29 frames.], batch size: 30, lr: 1.44e-04
2022-05-08 14:00:56,117 INFO [train.py:715] (4/8) Epoch 15, batch 33700, loss[loss=0.12, simple_loss=0.1968, pruned_loss=0.02157, over 4813.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03032, over 971113.32 frames.], batch size: 25, lr: 1.44e-04
2022-05-08 14:01:33,644 INFO [train.py:715] (4/8) Epoch 15, batch 33750, loss[loss=0.1085, simple_loss=0.1809, pruned_loss=0.018, over 4802.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03031, over 971078.44 frames.], batch size: 24, lr: 1.44e-04
2022-05-08 14:02:11,482 INFO [train.py:715] (4/8) Epoch 15, batch 33800, loss[loss=0.1428, simple_loss=0.222, pruned_loss=0.03178, over 4807.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.03028, over 971327.51 frames.], batch size: 21, lr: 1.44e-04
2022-05-08 14:02:48,673 INFO [train.py:715] (4/8) Epoch 15, batch 33850, loss[loss=0.1179, simple_loss=0.1941, pruned_loss=0.02084, over 4941.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02978, over 971134.69 frames.], batch size: 21, lr: 1.44e-04
2022-05-08 14:03:26,484 INFO [train.py:715] (4/8) Epoch 15, batch 33900, loss[loss=0.1576, simple_loss=0.228, pruned_loss=0.04356, over 4751.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02984, over 971520.92 frames.], batch size: 19, lr: 1.44e-04
2022-05-08 14:04:04,821 INFO [train.py:715] (4/8) Epoch 15, batch 33950, loss[loss=0.1182, simple_loss=0.1868, pruned_loss=0.02486, over 4940.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02983, over 971466.66 frames.], batch size: 18, lr: 1.44e-04
2022-05-08 14:04:42,873 INFO [train.py:715] (4/8) Epoch 15, batch 34000, loss[loss=0.1433, simple_loss=0.2145, pruned_loss=0.03599, over 4831.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02991, over 972241.06 frames.], batch size: 15, lr: 1.44e-04
2022-05-08 14:05:20,769 INFO [train.py:715] (4/8) Epoch 15, batch 34050, loss[loss=0.1067, simple_loss=0.1818, pruned_loss=0.01581, over 4911.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02927, over 971473.47 frames.], batch size: 17, lr: 1.44e-04
2022-05-08 14:05:58,929 INFO [train.py:715] (4/8) Epoch 15, batch 34100, loss[loss=0.1335, simple_loss=0.2135, pruned_loss=0.02671, over 4971.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2059, pruned_loss=0.02935, over 971276.47 frames.], batch size: 24, lr: 1.44e-04
2022-05-08 14:06:37,189 INFO [train.py:715] (4/8) Epoch 15, batch 34150, loss[loss=0.1343, simple_loss=0.2098, pruned_loss=0.02941, over 4858.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2067, pruned_loss=0.02953, over 971363.28 frames.], batch size: 32, lr: 1.44e-04
2022-05-08 14:07:14,888 INFO [train.py:715] (4/8) Epoch 15, batch 34200, loss[loss=0.1002, simple_loss=0.1703, pruned_loss=0.01502, over 4814.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2069, pruned_loss=0.02973, over 971691.80 frames.], batch size: 13, lr: 1.44e-04
2022-05-08 14:07:52,718 INFO [train.py:715] (4/8) Epoch 15, batch 34250, loss[loss=0.1247, simple_loss=0.2078, pruned_loss=0.02082, over 4936.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02945, over 971860.70 frames.], batch size: 39, lr: 1.44e-04
2022-05-08 14:08:30,683 INFO [train.py:715] (4/8) Epoch 15, batch 34300, loss[loss=0.1268, simple_loss=0.1962, pruned_loss=0.02869, over 4749.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2068, pruned_loss=0.02968, over 972462.32 frames.], batch size: 19, lr: 1.44e-04
2022-05-08 14:09:08,609 INFO [train.py:715] (4/8) Epoch 15, batch 34350, loss[loss=0.1563, simple_loss=0.2265, pruned_loss=0.04302, over 4966.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02988, over 972366.61 frames.], batch size: 39, lr: 1.44e-04
2022-05-08 14:09:45,970 INFO [train.py:715] (4/8) Epoch 15, batch 34400, loss[loss=0.1471, simple_loss=0.2228, pruned_loss=0.03568, over 4889.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02999, over 972036.24 frames.], batch size: 22, lr: 1.44e-04
2022-05-08 14:10:24,171 INFO [train.py:715] (4/8) Epoch 15, batch 34450, loss[loss=0.1468, simple_loss=0.2253, pruned_loss=0.03414, over 4948.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.0301, over 972349.33 frames.], batch size: 24, lr: 1.44e-04
2022-05-08 14:11:02,052 INFO [train.py:715] (4/8) Epoch 15, batch 34500, loss[loss=0.115, simple_loss=0.2, pruned_loss=0.01502, over 4962.00 frames.], tot_loss[loss=0.135, simple_loss=0.2089, pruned_loss=0.03054, over 973300.07 frames.], batch size: 24, lr: 1.44e-04
2022-05-08 14:11:39,388 INFO [train.py:715] (4/8) Epoch 15, batch 34550, loss[loss=0.1434, simple_loss=0.2167, pruned_loss=0.03502, over 4887.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03022, over 973446.92 frames.], batch size: 16, lr: 1.44e-04
2022-05-08 14:12:17,004 INFO [train.py:715] (4/8) Epoch 15, batch 34600, loss[loss=0.1171, simple_loss=0.187, pruned_loss=0.02364, over 4782.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2096, pruned_loss=0.03055, over 973418.53 frames.], batch size: 17, lr: 1.44e-04
2022-05-08 14:12:54,930 INFO [train.py:715] (4/8) Epoch 15, batch 34650, loss[loss=0.1587, simple_loss=0.219, pruned_loss=0.04917, over 4948.00 frames.], tot_loss[loss=0.1368, simple_loss=0.2109, pruned_loss=0.03131, over 973337.12 frames.], batch size: 29, lr: 1.44e-04
2022-05-08 14:13:32,474 INFO [train.py:715] (4/8) Epoch 15, batch 34700, loss[loss=0.1409, simple_loss=0.207, pruned_loss=0.03739, over 4842.00 frames.], tot_loss[loss=0.1362, simple_loss=0.2102, pruned_loss=0.03108, over 972893.38 frames.], batch size: 30, lr: 1.44e-04
2022-05-08 14:14:09,603 INFO [train.py:715] (4/8) Epoch 15, batch 34750, loss[loss=0.114, simple_loss=0.1827, pruned_loss=0.02271, over 4892.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03031, over 971984.70 frames.], batch size: 19, lr: 1.44e-04
2022-05-08 14:14:44,839 INFO [train.py:715] (4/8) Epoch 15, batch 34800, loss[loss=0.1287, simple_loss=0.2028, pruned_loss=0.02731, over 4914.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2089, pruned_loss=0.02998, over 972008.70 frames.], batch size: 18, lr: 1.44e-04
2022-05-08 14:15:33,453 INFO [train.py:715] (4/8) Epoch 16, batch 0, loss[loss=0.1347, simple_loss=0.2107, pruned_loss=0.02938, over 4935.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2107, pruned_loss=0.02938, over 4935.00 frames.], batch size: 21, lr: 1.40e-04
2022-05-08 14:16:11,641 INFO [train.py:715] (4/8) Epoch 16, batch 50, loss[loss=0.1185, simple_loss=0.1936, pruned_loss=0.02175, over 4894.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.03008, over 219632.27 frames.], batch size: 32, lr: 1.40e-04
2022-05-08 14:16:50,213 INFO [train.py:715] (4/8) Epoch 16, batch 100, loss[loss=0.1603, simple_loss=0.2357, pruned_loss=0.04244, over 4967.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2102, pruned_loss=0.03072, over 387665.45 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:17:27,947 INFO [train.py:715] (4/8) Epoch 16, batch 150, loss[loss=0.13, simple_loss=0.209, pruned_loss=0.02549, over 4878.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2092, pruned_loss=0.03064, over 517311.06 frames.], batch size: 30, lr: 1.40e-04
2022-05-08 14:18:06,151 INFO [train.py:715] (4/8) Epoch 16, batch 200, loss[loss=0.14, simple_loss=0.2171, pruned_loss=0.03142, over 4813.00 frames.], tot_loss[loss=0.1353, simple_loss=0.2091, pruned_loss=0.03073, over 617807.93 frames.], batch size: 21, lr: 1.40e-04
2022-05-08 14:18:44,279 INFO [train.py:715] (4/8) Epoch 16, batch 250, loss[loss=0.1436, simple_loss=0.2091, pruned_loss=0.03906, over 4665.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2089, pruned_loss=0.03043, over 695633.52 frames.], batch size: 13, lr: 1.40e-04
2022-05-08 14:19:22,600 INFO [train.py:715] (4/8) Epoch 16, batch 300, loss[loss=0.1342, simple_loss=0.2111, pruned_loss=0.02869, over 4891.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2094, pruned_loss=0.03052, over 757788.58 frames.], batch size: 19, lr: 1.40e-04
2022-05-08 14:20:01,025 INFO [train.py:715] (4/8) Epoch 16, batch 350, loss[loss=0.1292, simple_loss=0.2135, pruned_loss=0.02239, over 4982.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2101, pruned_loss=0.03089, over 806241.58 frames.], batch size: 25, lr: 1.40e-04
2022-05-08 14:20:38,707 INFO [train.py:715] (4/8) Epoch 16, batch 400, loss[loss=0.153, simple_loss=0.2193, pruned_loss=0.04332, over 4910.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2099, pruned_loss=0.03088, over 842645.26 frames.], batch size: 17, lr: 1.40e-04
2022-05-08 14:21:17,412 INFO [train.py:715] (4/8) Epoch 16, batch 450, loss[loss=0.1672, simple_loss=0.2382, pruned_loss=0.04812, over 4713.00 frames.], tot_loss[loss=0.1359, simple_loss=0.21, pruned_loss=0.03094, over 870558.22 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:21:55,826 INFO [train.py:715] (4/8) Epoch 16, batch 500, loss[loss=0.1034, simple_loss=0.1855, pruned_loss=0.01067, over 4985.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03092, over 893908.32 frames.], batch size: 25, lr: 1.40e-04
2022-05-08 14:22:33,536 INFO [train.py:715] (4/8) Epoch 16, batch 550, loss[loss=0.1474, simple_loss=0.2226, pruned_loss=0.03616, over 4693.00 frames.], tot_loss[loss=0.1363, simple_loss=0.2102, pruned_loss=0.03119, over 910968.77 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:23:12,213 INFO [train.py:715] (4/8) Epoch 16, batch 600, loss[loss=0.1584, simple_loss=0.2245, pruned_loss=0.0461, over 4745.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2096, pruned_loss=0.03103, over 923964.07 frames.], batch size: 14, lr: 1.40e-04
2022-05-08 14:23:50,875 INFO [train.py:715] (4/8) Epoch 16, batch 650, loss[loss=0.1226, simple_loss=0.2018, pruned_loss=0.02177, over 4807.00 frames.], tot_loss[loss=0.1354, simple_loss=0.2093, pruned_loss=0.03079, over 934515.45 frames.], batch size: 21, lr: 1.40e-04
2022-05-08 14:24:28,547 INFO [train.py:715] (4/8) Epoch 16, batch 700, loss[loss=0.1159, simple_loss=0.1978, pruned_loss=0.01704, over 4855.00 frames.], tot_loss[loss=0.135, simple_loss=0.2091, pruned_loss=0.03047, over 943113.73 frames.], batch size: 20, lr: 1.40e-04
2022-05-08 14:25:06,446 INFO [train.py:715] (4/8) Epoch 16, batch 750, loss[loss=0.1492, simple_loss=0.219, pruned_loss=0.03965, over 4891.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2091, pruned_loss=0.03069, over 948917.79 frames.], batch size: 22, lr: 1.40e-04
2022-05-08 14:25:45,232 INFO [train.py:715] (4/8) Epoch 16, batch 800, loss[loss=0.1504, simple_loss=0.2292, pruned_loss=0.03581, over 4975.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2093, pruned_loss=0.03046, over 954988.66 frames.], batch size: 25, lr: 1.40e-04
2022-05-08 14:26:23,549 INFO [train.py:715] (4/8) Epoch 16, batch 850, loss[loss=0.1315, simple_loss=0.2055, pruned_loss=0.0287, over 4698.00 frames.], tot_loss[loss=0.1358, simple_loss=0.2098, pruned_loss=0.03093, over 958845.66 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:27:01,574 INFO [train.py:715] (4/8) Epoch 16, batch 900, loss[loss=0.144, simple_loss=0.2217, pruned_loss=0.03312, over 4811.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2099, pruned_loss=0.03072, over 962693.25 frames.], batch size: 25, lr: 1.40e-04
2022-05-08 14:27:39,691 INFO [train.py:715] (4/8) Epoch 16, batch 950, loss[loss=0.1365, simple_loss=0.2111, pruned_loss=0.03098, over 4750.00 frames.], tot_loss[loss=0.135, simple_loss=0.209, pruned_loss=0.03047, over 963802.89 frames.], batch size: 19, lr: 1.40e-04
2022-05-08 14:28:18,128 INFO [train.py:715] (4/8) Epoch 16, batch 1000, loss[loss=0.1467, simple_loss=0.2169, pruned_loss=0.03826, over 4948.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2089, pruned_loss=0.03029, over 966261.10 frames.], batch size: 35, lr: 1.40e-04
2022-05-08 14:28:55,785 INFO [train.py:715] (4/8) Epoch 16, batch 1050, loss[loss=0.1093, simple_loss=0.1847, pruned_loss=0.01698, over 4794.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.03094, over 967030.97 frames.], batch size: 21, lr: 1.40e-04
2022-05-08 14:29:33,186 INFO [train.py:715] (4/8) Epoch 16, batch 1100, loss[loss=0.1264, simple_loss=0.1984, pruned_loss=0.02724, over 4884.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2094, pruned_loss=0.03095, over 968044.69 frames.], batch size: 32, lr: 1.40e-04
2022-05-08 14:30:11,812 INFO [train.py:715] (4/8) Epoch 16, batch 1150, loss[loss=0.137, simple_loss=0.2042, pruned_loss=0.03494, over 4916.00 frames.], tot_loss[loss=0.1359, simple_loss=0.2099, pruned_loss=0.03093, over 968892.55 frames.], batch size: 18, lr: 1.40e-04
2022-05-08 14:30:49,881 INFO [train.py:715] (4/8) Epoch 16, batch 1200, loss[loss=0.1385, simple_loss=0.2187, pruned_loss=0.02911, over 4933.00 frames.], tot_loss[loss=0.1357, simple_loss=0.2096, pruned_loss=0.03089, over 969542.39 frames.], batch size: 29, lr: 1.40e-04
2022-05-08 14:31:27,245 INFO [train.py:715] (4/8) Epoch 16, batch 1250, loss[loss=0.1358, simple_loss=0.2094, pruned_loss=0.03115, over 4905.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03057, over 969652.80 frames.], batch size: 18, lr: 1.40e-04
2022-05-08 14:32:05,203 INFO [train.py:715] (4/8) Epoch 16, batch 1300, loss[loss=0.1238, simple_loss=0.2006, pruned_loss=0.02346, over 4757.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2082, pruned_loss=0.03006, over 970310.25 frames.], batch size: 16, lr: 1.40e-04
2022-05-08 14:32:43,364 INFO [train.py:715] (4/8) Epoch 16, batch 1350, loss[loss=0.1629, simple_loss=0.2335, pruned_loss=0.04618, over 4765.00 frames.], tot_loss[loss=0.133, simple_loss=0.2068, pruned_loss=0.02958, over 970132.10 frames.], batch size: 17, lr: 1.40e-04
2022-05-08 14:33:21,096 INFO [train.py:715] (4/8) Epoch 16, batch 1400, loss[loss=0.1178, simple_loss=0.1833, pruned_loss=0.02609, over 4763.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02955, over 970933.21 frames.], batch size: 12, lr: 1.40e-04
2022-05-08 14:33:59,219 INFO [train.py:715] (4/8) Epoch 16, batch 1450, loss[loss=0.1245, simple_loss=0.2023, pruned_loss=0.02336, over 4974.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02986, over 971727.20 frames.], batch size: 28, lr: 1.40e-04
2022-05-08 14:34:37,201 INFO [train.py:715] (4/8) Epoch 16, batch 1500, loss[loss=0.1345, simple_loss=0.2185, pruned_loss=0.02532, over 4957.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02935, over 972050.59 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:35:14,924 INFO [train.py:715] (4/8) Epoch 16, batch 1550, loss[loss=0.1496, simple_loss=0.2163, pruned_loss=0.04149, over 4971.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02957, over 971696.60 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:35:52,770 INFO [train.py:715] (4/8) Epoch 16, batch 1600, loss[loss=0.1415, simple_loss=0.2088, pruned_loss=0.03705, over 4782.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.02949, over 972135.12 frames.], batch size: 19, lr: 1.40e-04
2022-05-08 14:36:30,168 INFO [train.py:715] (4/8) Epoch 16, batch 1650, loss[loss=0.1209, simple_loss=0.1989, pruned_loss=0.02147, over 4760.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02968, over 972540.06 frames.], batch size: 16, lr: 1.40e-04
2022-05-08 14:37:07,994 INFO [train.py:715] (4/8) Epoch 16, batch 1700, loss[loss=0.1431, simple_loss=0.2156, pruned_loss=0.03524, over 4954.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.03023, over 972663.15 frames.], batch size: 39, lr: 1.40e-04
2022-05-08 14:37:46,153 INFO [train.py:715] (4/8) Epoch 16, batch 1750, loss[loss=0.1324, simple_loss=0.2082, pruned_loss=0.02834, over 4932.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2077, pruned_loss=0.0303, over 972361.25 frames.], batch size: 23, lr: 1.40e-04
2022-05-08 14:38:24,067 INFO [train.py:715] (4/8) Epoch 16, batch 1800, loss[loss=0.1335, simple_loss=0.2044, pruned_loss=0.03132, over 4822.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2085, pruned_loss=0.03039, over 972161.79 frames.], batch size: 25, lr: 1.40e-04
2022-05-08 14:39:02,376 INFO [train.py:715] (4/8) Epoch 16, batch 1850, loss[loss=0.1262, simple_loss=0.2003, pruned_loss=0.02601, over 4751.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.0301, over 972217.85 frames.], batch size: 19, lr: 1.40e-04
2022-05-08 14:39:41,005 INFO [train.py:715] (4/8) Epoch 16, batch 1900, loss[loss=0.1468, simple_loss=0.2198, pruned_loss=0.03695, over 4959.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02991, over 972912.52 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:40:18,873 INFO [train.py:715] (4/8) Epoch 16, batch 1950, loss[loss=0.1482, simple_loss=0.2214, pruned_loss=0.03752, over 4912.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02963, over 972482.13 frames.], batch size: 18, lr: 1.40e-04
2022-05-08 14:40:57,063 INFO [train.py:715] (4/8) Epoch 16, batch 2000, loss[loss=0.1181, simple_loss=0.2003, pruned_loss=0.01797, over 4804.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02956, over 971356.60 frames.], batch size: 24, lr: 1.40e-04
2022-05-08 14:41:35,862 INFO [train.py:715] (4/8) Epoch 16, batch 2050, loss[loss=0.1153, simple_loss=0.1947, pruned_loss=0.01794, over 4975.00 frames.], tot_loss[loss=0.132, simple_loss=0.206, pruned_loss=0.02896, over 971545.43 frames.], batch size: 31, lr: 1.40e-04
2022-05-08 14:42:14,574 INFO [train.py:715] (4/8) Epoch 16, batch 2100, loss[loss=0.1398, simple_loss=0.2044, pruned_loss=0.03756, over 4909.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02923, over 971498.55 frames.], batch size: 17, lr: 1.40e-04
2022-05-08 14:42:52,429 INFO [train.py:715] (4/8) Epoch 16, batch 2150, loss[loss=0.1352, simple_loss=0.2047, pruned_loss=0.03285, over 4970.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02961, over 971276.30 frames.], batch size: 33, lr: 1.40e-04
2022-05-08 14:43:31,558 INFO [train.py:715] (4/8) Epoch 16, batch 2200, loss[loss=0.1148, simple_loss=0.1872, pruned_loss=0.0212, over 4772.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02977, over 971696.68 frames.], batch size: 14, lr: 1.40e-04
2022-05-08 14:44:09,851 INFO [train.py:715] (4/8) Epoch 16, batch 2250, loss[loss=0.1521, simple_loss=0.2279, pruned_loss=0.03811, over 4863.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03006, over 971878.54 frames.], batch size: 20, lr: 1.40e-04
2022-05-08 14:44:47,485 INFO [train.py:715] (4/8) Epoch 16, batch 2300, loss[loss=0.1098, simple_loss=0.1844, pruned_loss=0.01756, over 4883.00 frames.], tot_loss[loss=0.133, simple_loss=0.2068, pruned_loss=0.02962, over 971842.92 frames.], batch size: 22, lr: 1.40e-04
2022-05-08 14:45:25,054 INFO [train.py:715] (4/8) Epoch 16, batch 2350, loss[loss=0.1446, simple_loss=0.2165, pruned_loss=0.03638, over 4978.00 frames.], tot_loss[loss=0.1322, simple_loss=0.206, pruned_loss=0.02919, over 971957.32 frames.], batch size: 35, lr: 1.40e-04
2022-05-08 14:46:03,345 INFO [train.py:715] (4/8) Epoch 16, batch 2400, loss[loss=0.1334, simple_loss=0.2146, pruned_loss=0.02614, over 4836.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2052, pruned_loss=0.02861, over 971432.28 frames.], batch size: 13, lr: 1.40e-04
2022-05-08 14:46:41,420 INFO [train.py:715] (4/8) Epoch 16, batch 2450, loss[loss=0.1365, simple_loss=0.2168, pruned_loss=0.02807, over 4856.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2052, pruned_loss=0.0286, over 971044.11 frames.], batch size: 20, lr: 1.40e-04
2022-05-08 14:47:18,879 INFO [train.py:715] (4/8) Epoch 16, batch 2500, loss[loss=0.1372, simple_loss=0.207, pruned_loss=0.03366, over 4865.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02914, over 971707.38 frames.], batch size: 20, lr: 1.40e-04
2022-05-08 14:47:57,272 INFO [train.py:715] (4/8) Epoch 16, batch 2550, loss[loss=0.1719, simple_loss=0.2321, pruned_loss=0.0558, over 4914.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02934, over 972127.16 frames.], batch size: 19, lr: 1.40e-04
2022-05-08 14:48:35,427 INFO [train.py:715] (4/8) Epoch 16, batch 2600, loss[loss=0.1238, simple_loss=0.2062, pruned_loss=0.0207, over 4798.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02914, over 971708.08 frames.], batch size: 21, lr: 1.40e-04
2022-05-08 14:49:13,160 INFO [train.py:715] (4/8) Epoch 16, batch 2650, loss[loss=0.1401, simple_loss=0.2166, pruned_loss=0.03181, over 4883.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02923, over 971870.68 frames.], batch size: 39, lr: 1.40e-04
2022-05-08 14:49:51,048 INFO [train.py:715] (4/8) Epoch 16, batch 2700, loss[loss=0.1227, simple_loss=0.1968, pruned_loss=0.02434, over 4863.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02904, over 972226.16 frames.], batch size: 20, lr: 1.40e-04
2022-05-08 14:50:29,658 INFO [train.py:715] (4/8) Epoch 16, batch 2750, loss[loss=0.1385, simple_loss=0.2168, pruned_loss=0.03013, over 4965.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02902, over 972299.40 frames.], batch size: 24, lr: 1.40e-04
2022-05-08 14:51:08,569 INFO [train.py:715] (4/8) Epoch 16, batch 2800, loss[loss=0.1219, simple_loss=0.195, pruned_loss=0.02443, over 4755.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02943, over 973024.64 frames.], batch size: 16, lr: 1.40e-04
2022-05-08 14:51:46,948 INFO [train.py:715] (4/8) Epoch 16, batch 2850, loss[loss=0.1417, simple_loss=0.2165, pruned_loss=0.03345, over 4834.00 frames.], tot_loss[loss=0.133, simple_loss=0.2068, pruned_loss=0.02962, over 973382.93 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:52:24,999 INFO [train.py:715] (4/8) Epoch 16, batch 2900, loss[loss=0.1041, simple_loss=0.1754, pruned_loss=0.0164, over 4870.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02972, over 973299.19 frames.], batch size: 13, lr: 1.40e-04
2022-05-08 14:53:03,774 INFO [train.py:715] (4/8) Epoch 16, batch 2950, loss[loss=0.1245, simple_loss=0.1943, pruned_loss=0.02737, over 4898.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02964, over 972742.01 frames.], batch size: 18, lr: 1.40e-04
2022-05-08 14:53:41,757 INFO [train.py:715] (4/8) Epoch 16, batch 3000, loss[loss=0.1137, simple_loss=0.1856, pruned_loss=0.0209, over 4980.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.0295, over 972367.30 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:53:41,757 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 14:53:51,189 INFO [train.py:742] (4/8) Epoch 16, validation: loss=0.105, simple_loss=0.1885, pruned_loss=0.01074, over 914524.00 frames.
2022-05-08 14:54:29,008 INFO [train.py:715] (4/8) Epoch 16, batch 3050, loss[loss=0.1217, simple_loss=0.2135, pruned_loss=0.01495, over 4794.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02975, over 972448.12 frames.], batch size: 14, lr: 1.40e-04
2022-05-08 14:55:09,457 INFO [train.py:715] (4/8) Epoch 16, batch 3100, loss[loss=0.1258, simple_loss=0.2023, pruned_loss=0.02466, over 4988.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.0298, over 972015.29 frames.], batch size: 28, lr: 1.40e-04
2022-05-08 14:55:47,849 INFO [train.py:715] (4/8) Epoch 16, batch 3150, loss[loss=0.1404, simple_loss=0.2236, pruned_loss=0.02858, over 4963.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.02997, over 971770.29 frames.], batch size: 24, lr: 1.40e-04
2022-05-08 14:56:26,005 INFO [train.py:715] (4/8) Epoch 16, batch 3200, loss[loss=0.1224, simple_loss=0.2024, pruned_loss=0.02114, over 4836.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02939, over 971558.39 frames.], batch size: 26, lr: 1.40e-04
2022-05-08 14:57:04,239 INFO [train.py:715] (4/8) Epoch 16, batch 3250, loss[loss=0.1274, simple_loss=0.2007, pruned_loss=0.02703, over 4782.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02947, over 972133.13 frames.], batch size: 17, lr: 1.40e-04
2022-05-08 14:57:42,063 INFO [train.py:715] (4/8) Epoch 16, batch 3300, loss[loss=0.1093, simple_loss=0.1779, pruned_loss=0.0204, over 4981.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02891, over 973174.37 frames.], batch size: 28, lr: 1.40e-04
2022-05-08 14:58:20,053 INFO [train.py:715] (4/8) Epoch 16, batch 3350, loss[loss=0.1672, simple_loss=0.2331, pruned_loss=0.05064, over 4836.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02925, over 973747.23 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 14:58:57,930 INFO [train.py:715] (4/8) Epoch 16, batch 3400, loss[loss=0.1208, simple_loss=0.1953, pruned_loss=0.02311, over 4985.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02957, over 972934.52 frames.], batch size: 28, lr: 1.40e-04
2022-05-08 14:59:35,865 INFO [train.py:715] (4/8) Epoch 16, batch 3450, loss[loss=0.1285, simple_loss=0.199, pruned_loss=0.02903, over 4945.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02957, over 973489.96 frames.], batch size: 35, lr: 1.40e-04
2022-05-08 15:00:13,953 INFO [train.py:715] (4/8) Epoch 16, batch 3500, loss[loss=0.1246, simple_loss=0.2114, pruned_loss=0.01886, over 4818.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.0295, over 974168.70 frames.], batch size: 25, lr: 1.40e-04
2022-05-08 15:00:51,756 INFO [train.py:715] (4/8) Epoch 16, batch 3550, loss[loss=0.1286, simple_loss=0.1972, pruned_loss=0.03003, over 4972.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02974, over 973171.74 frames.], batch size: 14, lr: 1.40e-04
2022-05-08 15:01:30,178 INFO [train.py:715] (4/8) Epoch 16, batch 3600, loss[loss=0.141, simple_loss=0.2171, pruned_loss=0.03245, over 4984.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02973, over 972999.70 frames.], batch size: 25, lr: 1.40e-04
2022-05-08 15:02:07,897 INFO [train.py:715] (4/8) Epoch 16, batch 3650, loss[loss=0.1356, simple_loss=0.209, pruned_loss=0.03112, over 4824.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02953, over 972994.83 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 15:02:46,558 INFO [train.py:715] (4/8) Epoch 16, batch 3700, loss[loss=0.1353, simple_loss=0.2328, pruned_loss=0.0189, over 4947.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2081, pruned_loss=0.02943, over 974382.67 frames.], batch size: 15, lr: 1.40e-04
2022-05-08 15:03:25,044 INFO [train.py:715] (4/8) Epoch 16, batch 3750, loss[loss=0.1272, simple_loss=0.1901, pruned_loss=0.03214, over 4839.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02934, over 974152.13 frames.], batch size: 30, lr: 1.40e-04
2022-05-08 15:04:03,407 INFO [train.py:715] (4/8) Epoch 16, batch 3800, loss[loss=0.1274, simple_loss=0.205, pruned_loss=0.02491, over 4782.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02985, over 973509.76 frames.], batch size: 17, lr: 1.40e-04
2022-05-08 15:04:42,271 INFO [train.py:715] (4/8) Epoch 16, batch 3850, loss[loss=0.156, simple_loss=0.2247, pruned_loss=0.0437, over 4910.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03024, over 973117.84 frames.], batch size: 18, lr: 1.40e-04
2022-05-08 15:05:21,015 INFO [train.py:715] (4/8) Epoch 16, batch 3900, loss[loss=0.1469, simple_loss=0.2251, pruned_loss=0.03436, over 4886.00 frames.], tot_loss[loss=0.1346, simple_loss=0.209, pruned_loss=0.03014, over 973187.15 frames.], batch size: 22, lr: 1.39e-04
2022-05-08 15:05:58,859 INFO [train.py:715] (4/8) Epoch 16, batch 3950, loss[loss=0.1534, simple_loss=0.2224, pruned_loss=0.04222, over 4844.00 frames.], tot_loss[loss=0.135, simple_loss=0.2095, pruned_loss=0.03031, over 973138.99 frames.], batch size: 26, lr: 1.39e-04
2022-05-08 15:06:36,786 INFO [train.py:715] (4/8) Epoch 16, batch 4000, loss[loss=0.1507, simple_loss=0.229, pruned_loss=0.03613, over 4952.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2092, pruned_loss=0.03048, over 972546.23 frames.], batch size: 29, lr: 1.39e-04
2022-05-08 15:07:14,744 INFO [train.py:715] (4/8) Epoch 16, batch 4050, loss[loss=0.1143, simple_loss=0.1937, pruned_loss=0.01744, over 4901.00 frames.], tot_loss[loss=0.136, simple_loss=0.2102, pruned_loss=0.03084, over 971682.84 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 15:07:52,147 INFO [train.py:715] (4/8) Epoch 16, batch 4100, loss[loss=0.1151, simple_loss=0.1811, pruned_loss=0.02454, over 4789.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03039, over 971251.87 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 15:08:29,798 INFO [train.py:715] (4/8) Epoch 16, batch 4150, loss[loss=0.1026, simple_loss=0.1699, pruned_loss=0.01763, over 4835.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03002, over 971782.10 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 15:09:07,465 INFO [train.py:715] (4/8) Epoch 16, batch 4200, loss[loss=0.1406, simple_loss=0.2077, pruned_loss=0.03676, over 4771.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02986, over 971930.00 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 15:09:45,633 INFO [train.py:715] (4/8) Epoch 16, batch 4250, loss[loss=0.1251, simple_loss=0.1995, pruned_loss=0.02535, over 4923.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03042, over 972852.39 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 15:10:23,341 INFO [train.py:715] (4/8) Epoch 16, batch 4300, loss[loss=0.1153, simple_loss=0.1844, pruned_loss=0.02311, over 4858.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2068, pruned_loss=0.02999, over 972838.48 frames.], batch size: 32, lr: 1.39e-04
2022-05-08 15:11:01,195 INFO [train.py:715] (4/8) Epoch 16, batch 4350, loss[loss=0.1014, simple_loss=0.1793, pruned_loss=0.01174, over 4766.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.03006, over 972364.74 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 15:11:39,307 INFO [train.py:715] (4/8) Epoch 16, batch 4400, loss[loss=0.138, simple_loss=0.225, pruned_loss=0.02554, over 4903.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2084, pruned_loss=0.03064, over 972628.92 frames.], batch size: 39, lr: 1.39e-04
2022-05-08 15:12:17,135 INFO [train.py:715] (4/8) Epoch 16, batch 4450, loss[loss=0.142, simple_loss=0.2272, pruned_loss=0.0284, over 4925.00 frames.], tot_loss[loss=0.1351, simple_loss=0.2089, pruned_loss=0.03068, over 971913.18 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 15:12:54,751 INFO [train.py:715] (4/8) Epoch 16, batch 4500, loss[loss=0.132, simple_loss=0.2022, pruned_loss=0.03088, over 4933.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2087, pruned_loss=0.03085, over 972488.57 frames.], batch size: 29, lr: 1.39e-04
2022-05-08 15:13:32,862 INFO [train.py:715] (4/8) Epoch 16, batch 4550, loss[loss=0.1193, simple_loss=0.2016, pruned_loss=0.0185, over 4970.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03016, over 972131.37 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:14:11,254 INFO [train.py:715] (4/8) Epoch 16, batch 4600, loss[loss=0.1692, simple_loss=0.2308, pruned_loss=0.05378, over 4832.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2076, pruned_loss=0.03035, over 971185.92 frames.], batch size: 30, lr: 1.39e-04
2022-05-08 15:14:49,232 INFO [train.py:715] (4/8) Epoch 16, batch 4650, loss[loss=0.1115, simple_loss=0.1859, pruned_loss=0.0186, over 4739.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2069, pruned_loss=0.02986, over 971415.76 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 15:15:27,631 INFO [train.py:715] (4/8) Epoch 16, batch 4700, loss[loss=0.1244, simple_loss=0.1929, pruned_loss=0.02798, over 4829.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02954, over 971319.07 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 15:16:06,226 INFO [train.py:715] (4/8) Epoch 16, batch 4750, loss[loss=0.1296, simple_loss=0.2066, pruned_loss=0.02633, over 4986.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02956, over 971830.86 frames.], batch size: 31, lr: 1.39e-04
2022-05-08 15:16:44,830 INFO [train.py:715] (4/8) Epoch 16, batch 4800, loss[loss=0.1199, simple_loss=0.191, pruned_loss=0.0244, over 4869.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02962, over 972050.36 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 15:17:23,109 INFO [train.py:715] (4/8) Epoch 16, batch 4850, loss[loss=0.155, simple_loss=0.2299, pruned_loss=0.04004, over 4782.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02915, over 971751.62 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 15:18:01,809 INFO [train.py:715] (4/8) Epoch 16, batch 4900, loss[loss=0.09639, simple_loss=0.1692, pruned_loss=0.0118, over 4815.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02933, over 971301.49 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 15:18:40,682 INFO [train.py:715] (4/8) Epoch 16, batch 4950, loss[loss=0.1494, simple_loss=0.2119, pruned_loss=0.04344, over 4865.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02991, over 970707.51 frames.], batch size: 32, lr: 1.39e-04
2022-05-08 15:19:18,925 INFO [train.py:715] (4/8) Epoch 16, batch 5000, loss[loss=0.1245, simple_loss=0.1955, pruned_loss=0.02669, over 4779.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02956, over 970912.96 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 15:19:57,138 INFO [train.py:715] (4/8) Epoch 16, batch 5050, loss[loss=0.123, simple_loss=0.1908, pruned_loss=0.02764, over 4787.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02977, over 970703.62 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 15:20:35,446 INFO [train.py:715] (4/8) Epoch 16, batch 5100, loss[loss=0.1471, simple_loss=0.2185, pruned_loss=0.03787, over 4899.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02937, over 971074.18 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 15:21:13,350 INFO [train.py:715] (4/8) Epoch 16, batch 5150, loss[loss=0.1419, simple_loss=0.2156, pruned_loss=0.03411, over 4915.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03, over 971564.39 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 15:21:50,908 INFO [train.py:715] (4/8) Epoch 16, batch 5200, loss[loss=0.1068, simple_loss=0.1808, pruned_loss=0.01645, over 4893.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02992, over 972475.22 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 15:22:28,868 INFO [train.py:715] (4/8) Epoch 16, batch 5250, loss[loss=0.1109, simple_loss=0.1863, pruned_loss=0.01779, over 4780.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.0298, over 973728.48 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 15:23:07,104 INFO [train.py:715] (4/8) Epoch 16, batch 5300, loss[loss=0.1089, simple_loss=0.1974, pruned_loss=0.0102, over 4860.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02965, over 973056.84 frames.], batch size: 32, lr: 1.39e-04
2022-05-08 15:23:45,226 INFO [train.py:715] (4/8) Epoch 16, batch 5350, loss[loss=0.1339, simple_loss=0.222, pruned_loss=0.02296, over 4830.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.0297, over 973042.54 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:24:23,037 INFO [train.py:715] (4/8) Epoch 16, batch 5400, loss[loss=0.1645, simple_loss=0.2256, pruned_loss=0.05168, over 4651.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02966, over 972547.95 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 15:25:00,888 INFO [train.py:715] (4/8) Epoch 16, batch 5450, loss[loss=0.117, simple_loss=0.1883, pruned_loss=0.02287, over 4798.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02967, over 972031.74 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 15:25:38,706 INFO [train.py:715] (4/8) Epoch 16, batch 5500, loss[loss=0.1254, simple_loss=0.2024, pruned_loss=0.02423, over 4986.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02983, over 971471.14 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 15:26:16,326 INFO [train.py:715] (4/8) Epoch 16, batch 5550, loss[loss=0.1428, simple_loss=0.2152, pruned_loss=0.03521, over 4872.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.02999, over 972418.31 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 15:26:54,075 INFO [train.py:715] (4/8) Epoch 16, batch 5600, loss[loss=0.1272, simple_loss=0.2021, pruned_loss=0.02619, over 4858.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03002, over 972010.34 frames.], batch size: 20, lr: 1.39e-04
2022-05-08 15:27:32,729 INFO [train.py:715] (4/8) Epoch 16, batch 5650, loss[loss=0.14, simple_loss=0.2177, pruned_loss=0.03112, over 4945.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.0303, over 971910.20 frames.], batch size: 35, lr: 1.39e-04
2022-05-08 15:28:10,547 INFO [train.py:715] (4/8) Epoch 16, batch 5700, loss[loss=0.1542, simple_loss=0.2185, pruned_loss=0.04494, over 4958.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2088, pruned_loss=0.03039, over 973591.57 frames.], batch size: 35, lr: 1.39e-04
2022-05-08 15:28:48,368 INFO [train.py:715] (4/8) Epoch 16, batch 5750, loss[loss=0.1301, simple_loss=0.2094, pruned_loss=0.02538, over 4796.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03031, over 973123.07 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 15:29:26,211 INFO [train.py:715] (4/8) Epoch 16, batch 5800, loss[loss=0.1499, simple_loss=0.2225, pruned_loss=0.03865, over 4813.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02986, over 973552.28 frames.], batch size: 26, lr: 1.39e-04
2022-05-08 15:30:04,477 INFO [train.py:715] (4/8) Epoch 16, batch 5850, loss[loss=0.1387, simple_loss=0.2098, pruned_loss=0.03383, over 4934.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2086, pruned_loss=0.02973, over 974434.68 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 15:30:42,017 INFO [train.py:715] (4/8) Epoch 16, batch 5900, loss[loss=0.1603, simple_loss=0.2299, pruned_loss=0.04531, over 4870.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02982, over 973210.47 frames.], batch size: 32, lr: 1.39e-04
2022-05-08 15:31:19,663 INFO [train.py:715] (4/8) Epoch 16, batch 5950, loss[loss=0.1467, simple_loss=0.2274, pruned_loss=0.03302, over 4755.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02966, over 972918.68 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 15:31:58,428 INFO [train.py:715] (4/8) Epoch 16, batch 6000, loss[loss=0.1484, simple_loss=0.2163, pruned_loss=0.04023, over 4975.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2082, pruned_loss=0.02939, over 973719.41 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:31:58,429 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 15:32:07,944 INFO [train.py:742] (4/8) Epoch 16, validation: loss=0.105, simple_loss=0.1885, pruned_loss=0.01082, over 914524.00 frames.
2022-05-08 15:32:46,982 INFO [train.py:715] (4/8) Epoch 16, batch 6050, loss[loss=0.1485, simple_loss=0.2337, pruned_loss=0.03166, over 4900.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2086, pruned_loss=0.02984, over 973282.28 frames.], batch size: 22, lr: 1.39e-04
2022-05-08 15:33:25,023 INFO [train.py:715] (4/8) Epoch 16, batch 6100, loss[loss=0.136, simple_loss=0.2168, pruned_loss=0.02756, over 4953.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2084, pruned_loss=0.0296, over 973977.27 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:34:02,793 INFO [train.py:715] (4/8) Epoch 16, batch 6150, loss[loss=0.118, simple_loss=0.2016, pruned_loss=0.01725, over 4771.00 frames.], tot_loss[loss=0.1343, simple_loss=0.209, pruned_loss=0.02985, over 974154.85 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 15:34:40,934 INFO [train.py:715] (4/8) Epoch 16, batch 6200, loss[loss=0.1505, simple_loss=0.2231, pruned_loss=0.03891, over 4781.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02977, over 973902.35 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 15:35:19,471 INFO [train.py:715] (4/8) Epoch 16, batch 6250, loss[loss=0.1378, simple_loss=0.2029, pruned_loss=0.03633, over 4957.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02989, over 973557.57 frames.], batch size: 35, lr: 1.39e-04
2022-05-08 15:35:57,115 INFO [train.py:715] (4/8) Epoch 16, batch 6300, loss[loss=0.1368, simple_loss=0.2065, pruned_loss=0.03353, over 4968.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02982, over 972671.03 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:36:34,886 INFO [train.py:715] (4/8) Epoch 16, batch 6350, loss[loss=0.1114, simple_loss=0.188, pruned_loss=0.01737, over 4741.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02943, over 972674.00 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 15:37:13,401 INFO [train.py:715] (4/8) Epoch 16, batch 6400, loss[loss=0.1181, simple_loss=0.1787, pruned_loss=0.02876, over 4825.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.0292, over 973240.15 frames.], batch size: 30, lr: 1.39e-04
2022-05-08 15:37:51,669 INFO [train.py:715] (4/8) Epoch 16, batch 6450, loss[loss=0.1103, simple_loss=0.1894, pruned_loss=0.01557, over 4991.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02959, over 973448.87 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 15:38:29,440 INFO [train.py:715] (4/8) Epoch 16, batch 6500, loss[loss=0.1292, simple_loss=0.205, pruned_loss=0.02667, over 4945.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.03003, over 973435.68 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 15:39:07,580 INFO [train.py:715] (4/8) Epoch 16, batch 6550, loss[loss=0.1055, simple_loss=0.171, pruned_loss=0.01999, over 4970.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2068, pruned_loss=0.02987, over 972818.27 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 15:39:46,027 INFO [train.py:715] (4/8) Epoch 16, batch 6600, loss[loss=0.1791, simple_loss=0.2622, pruned_loss=0.04803, over 4825.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.03004, over 972197.71 frames.], batch size: 27, lr: 1.39e-04
2022-05-08 15:40:23,828 INFO [train.py:715] (4/8) Epoch 16, batch 6650, loss[loss=0.1278, simple_loss=0.2063, pruned_loss=0.02463, over 4852.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02985, over 971378.41 frames.], batch size: 20, lr: 1.39e-04
2022-05-08 15:41:01,685 INFO [train.py:715] (4/8) Epoch 16, batch 6700, loss[loss=0.1506, simple_loss=0.2179, pruned_loss=0.04168, over 4993.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2067, pruned_loss=0.02998, over 971591.38 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 15:41:39,712 INFO [train.py:715] (4/8) Epoch 16, batch 6750, loss[loss=0.1615, simple_loss=0.234, pruned_loss=0.04448, over 4906.00 frames.], tot_loss[loss=0.134, simple_loss=0.2075, pruned_loss=0.03023, over 971917.65 frames.], batch size: 39, lr: 1.39e-04
2022-05-08 15:42:17,830 INFO [train.py:715] (4/8) Epoch 16, batch 6800, loss[loss=0.1218, simple_loss=0.2074, pruned_loss=0.01814, over 4822.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02992, over 971515.13 frames.], batch size: 27, lr: 1.39e-04
2022-05-08 15:42:54,812 INFO [train.py:715] (4/8) Epoch 16, batch 6850, loss[loss=0.1328, simple_loss=0.2078, pruned_loss=0.02893, over 4782.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.03002, over 972158.23 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 15:43:32,596 INFO [train.py:715] (4/8) Epoch 16, batch 6900, loss[loss=0.125, simple_loss=0.1978, pruned_loss=0.02604, over 4866.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02981, over 972474.87 frames.], batch size: 39, lr: 1.39e-04
2022-05-08 15:44:10,713 INFO [train.py:715] (4/8) Epoch 16, batch 6950, loss[loss=0.1308, simple_loss=0.2167, pruned_loss=0.02243, over 4799.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02975, over 971605.79 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 15:44:48,419 INFO [train.py:715] (4/8) Epoch 16, batch 7000, loss[loss=0.1153, simple_loss=0.196, pruned_loss=0.0173, over 4941.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.0293, over 971350.81 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 15:45:26,356 INFO [train.py:715] (4/8) Epoch 16, batch 7050, loss[loss=0.13, simple_loss=0.2126, pruned_loss=0.02372, over 4918.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02931, over 971428.06 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 15:46:04,189 INFO [train.py:715] (4/8) Epoch 16, batch 7100, loss[loss=0.182, simple_loss=0.2607, pruned_loss=0.05166, over 4685.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02933, over 972412.00 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:46:42,648 INFO [train.py:715] (4/8) Epoch 16, batch 7150, loss[loss=0.1474, simple_loss=0.2213, pruned_loss=0.03677, over 4808.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02971, over 971526.97 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 15:47:19,960 INFO [train.py:715] (4/8) Epoch 16, batch 7200, loss[loss=0.1283, simple_loss=0.2147, pruned_loss=0.02098, over 4794.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02995, over 972130.03 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 15:47:57,928 INFO [train.py:715] (4/8) Epoch 16, batch 7250, loss[loss=0.1633, simple_loss=0.2324, pruned_loss=0.04709, over 4755.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02997, over 972670.06 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 15:48:36,996 INFO [train.py:715] (4/8) Epoch 16, batch 7300, loss[loss=0.1367, simple_loss=0.2092, pruned_loss=0.03209, over 4763.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03005, over 972668.88 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 15:49:15,790 INFO [train.py:715] (4/8) Epoch 16, batch 7350, loss[loss=0.141, simple_loss=0.2119, pruned_loss=0.03502, over 4879.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02992, over 972894.39 frames.], batch size: 39, lr: 1.39e-04
2022-05-08 15:49:55,230 INFO [train.py:715] (4/8) Epoch 16, batch 7400, loss[loss=0.121, simple_loss=0.2002, pruned_loss=0.02091, over 4977.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02977, over 974012.18 frames.], batch size: 28, lr: 1.39e-04
2022-05-08 15:50:34,949 INFO [train.py:715] (4/8) Epoch 16, batch 7450, loss[loss=0.1243, simple_loss=0.1972, pruned_loss=0.02573, over 4965.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02995, over 974245.71 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 15:51:14,631 INFO [train.py:715] (4/8) Epoch 16, batch 7500, loss[loss=0.1541, simple_loss=0.2346, pruned_loss=0.03682, over 4900.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02942, over 973950.88 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 15:51:53,675 INFO [train.py:715] (4/8) Epoch 16, batch 7550, loss[loss=0.133, simple_loss=0.211, pruned_loss=0.02746, over 4895.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02934, over 973526.85 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 15:52:33,693 INFO [train.py:715] (4/8) Epoch 16, batch 7600, loss[loss=0.1279, simple_loss=0.2038, pruned_loss=0.02597, over 4815.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02985, over 973980.76 frames.], batch size: 26, lr: 1.39e-04
2022-05-08 15:53:14,075 INFO [train.py:715] (4/8) Epoch 16, batch 7650, loss[loss=0.1321, simple_loss=0.2075, pruned_loss=0.02837, over 4791.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02948, over 973812.18 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 15:53:54,208 INFO [train.py:715] (4/8) Epoch 16, batch 7700, loss[loss=0.1404, simple_loss=0.2296, pruned_loss=0.02558, over 4879.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02944, over 973765.17 frames.], batch size: 22, lr: 1.39e-04
2022-05-08 15:54:33,725 INFO [train.py:715] (4/8) Epoch 16, batch 7750, loss[loss=0.1258, simple_loss=0.2064, pruned_loss=0.02265, over 4756.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02921, over 973895.61 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 15:55:13,914 INFO [train.py:715] (4/8) Epoch 16, batch 7800, loss[loss=0.1398, simple_loss=0.2108, pruned_loss=0.03444, over 4868.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02953, over 973526.26 frames.], batch size: 20, lr: 1.39e-04
2022-05-08 15:55:54,776 INFO [train.py:715] (4/8) Epoch 16, batch 7850, loss[loss=0.1201, simple_loss=0.1929, pruned_loss=0.02361, over 4912.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02929, over 973067.23 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 15:56:34,168 INFO [train.py:715] (4/8) Epoch 16, batch 7900, loss[loss=0.1286, simple_loss=0.1962, pruned_loss=0.03047, over 4780.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02972, over 972673.42 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 15:57:14,050 INFO [train.py:715] (4/8) Epoch 16, batch 7950, loss[loss=0.1284, simple_loss=0.1962, pruned_loss=0.03024, over 4846.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02973, over 971920.36 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 15:57:54,556 INFO [train.py:715] (4/8) Epoch 16, batch 8000, loss[loss=0.148, simple_loss=0.2305, pruned_loss=0.03276, over 4912.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02976, over 972482.71 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 15:58:34,600 INFO [train.py:715] (4/8) Epoch 16, batch 8050, loss[loss=0.1089, simple_loss=0.1815, pruned_loss=0.01818, over 4651.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02962, over 972319.39 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 15:59:14,243 INFO [train.py:715] (4/8) Epoch 16, batch 8100, loss[loss=0.1634, simple_loss=0.2333, pruned_loss=0.04678, over 4787.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2084, pruned_loss=0.0301, over 972530.56 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 15:59:54,663 INFO [train.py:715] (4/8) Epoch 16, batch 8150, loss[loss=0.1115, simple_loss=0.1827, pruned_loss=0.02014, over 4966.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03028, over 972754.03 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 16:00:35,743 INFO [train.py:715] (4/8) Epoch 16, batch 8200, loss[loss=0.1322, simple_loss=0.2042, pruned_loss=0.0301, over 4866.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02988, over 972553.58 frames.], batch size: 22, lr: 1.39e-04
2022-05-08 16:01:15,829 INFO [train.py:715] (4/8) Epoch 16, batch 8250, loss[loss=0.1325, simple_loss=0.2116, pruned_loss=0.02672, over 4840.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02952, over 972537.59 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 16:01:55,578 INFO [train.py:715] (4/8) Epoch 16, batch 8300, loss[loss=0.1232, simple_loss=0.1937, pruned_loss=0.02631, over 4946.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02932, over 972557.15 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 16:02:36,298 INFO [train.py:715] (4/8) Epoch 16, batch 8350, loss[loss=0.1458, simple_loss=0.2271, pruned_loss=0.03229, over 4814.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02944, over 972631.70 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 16:03:16,604 INFO [train.py:715] (4/8) Epoch 16, batch 8400, loss[loss=0.1362, simple_loss=0.2103, pruned_loss=0.0311, over 4843.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.0293, over 972772.19 frames.], batch size: 32, lr: 1.39e-04
2022-05-08 16:03:55,138 INFO [train.py:715] (4/8) Epoch 16, batch 8450, loss[loss=0.1243, simple_loss=0.1993, pruned_loss=0.02465, over 4838.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02967, over 973567.77 frames.], batch size: 30, lr: 1.39e-04
2022-05-08 16:04:34,541 INFO [train.py:715] (4/8) Epoch 16, batch 8500, loss[loss=0.1425, simple_loss=0.2242, pruned_loss=0.03035, over 4801.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2081, pruned_loss=0.03016, over 973075.44 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 16:05:13,259 INFO [train.py:715] (4/8) Epoch 16, batch 8550, loss[loss=0.1458, simple_loss=0.2205, pruned_loss=0.03555, over 4767.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02957, over 972535.34 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 16:05:51,576 INFO [train.py:715] (4/8) Epoch 16, batch 8600, loss[loss=0.1227, simple_loss=0.2035, pruned_loss=0.02098, over 4970.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02973, over 972967.68 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 16:06:29,597 INFO [train.py:715] (4/8) Epoch 16, batch 8650, loss[loss=0.1582, simple_loss=0.2248, pruned_loss=0.04579, over 4823.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2083, pruned_loss=0.02942, over 972135.13 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 16:07:08,666 INFO [train.py:715] (4/8) Epoch 16, batch 8700, loss[loss=0.1345, simple_loss=0.2038, pruned_loss=0.03256, over 4871.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.0292, over 971997.01 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 16:07:47,716 INFO [train.py:715] (4/8) Epoch 16, batch 8750, loss[loss=0.1597, simple_loss=0.2337, pruned_loss=0.04285, over 4809.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02932, over 972708.36 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 16:08:26,277 INFO [train.py:715] (4/8) Epoch 16, batch 8800, loss[loss=0.1487, simple_loss=0.2283, pruned_loss=0.03458, over 4947.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02912, over 972973.13 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 16:09:04,967 INFO [train.py:715] (4/8) Epoch 16, batch 8850, loss[loss=0.1397, simple_loss=0.2213, pruned_loss=0.02911, over 4873.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02907, over 972880.58 frames.], batch size: 22, lr: 1.39e-04
2022-05-08 16:09:44,464 INFO [train.py:715] (4/8) Epoch 16, batch 8900, loss[loss=0.1312, simple_loss=0.2173, pruned_loss=0.02258, over 4921.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02892, over 973124.85 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 16:10:22,904 INFO [train.py:715] (4/8) Epoch 16, batch 8950, loss[loss=0.1129, simple_loss=0.1943, pruned_loss=0.01573, over 4785.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02885, over 972864.02 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 16:11:01,136 INFO [train.py:715] (4/8) Epoch 16, batch 9000, loss[loss=0.1157, simple_loss=0.1956, pruned_loss=0.01794, over 4805.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02872, over 972875.15 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 16:11:01,136 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 16:11:23,892 INFO [train.py:742] (4/8) Epoch 16, validation: loss=0.105, simple_loss=0.1884, pruned_loss=0.01076, over 914524.00 frames.
2022-05-08 16:12:02,816 INFO [train.py:715] (4/8) Epoch 16, batch 9050, loss[loss=0.1254, simple_loss=0.2012, pruned_loss=0.02478, over 4963.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02895, over 972474.87 frames.], batch size: 35, lr: 1.39e-04
2022-05-08 16:12:41,943 INFO [train.py:715] (4/8) Epoch 16, batch 9100, loss[loss=0.1258, simple_loss=0.1979, pruned_loss=0.02684, over 4871.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02893, over 972669.82 frames.], batch size: 32, lr: 1.39e-04
2022-05-08 16:13:20,954 INFO [train.py:715] (4/8) Epoch 16, batch 9150, loss[loss=0.1335, simple_loss=0.1931, pruned_loss=0.03693, over 4697.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02914, over 972755.09 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 16:13:58,476 INFO [train.py:715] (4/8) Epoch 16, batch 9200, loss[loss=0.1257, simple_loss=0.1963, pruned_loss=0.02754, over 4821.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.02945, over 974055.94 frames.], batch size: 26, lr: 1.39e-04
2022-05-08 16:14:37,128 INFO [train.py:715] (4/8) Epoch 16, batch 9250, loss[loss=0.1036, simple_loss=0.1645, pruned_loss=0.02137, over 4780.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.02951, over 973779.76 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 16:15:16,082 INFO [train.py:715] (4/8) Epoch 16, batch 9300, loss[loss=0.125, simple_loss=0.2011, pruned_loss=0.02451, over 4828.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02919, over 973430.27 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 16:15:54,778 INFO [train.py:715] (4/8) Epoch 16, batch 9350, loss[loss=0.1267, simple_loss=0.2106, pruned_loss=0.0214, over 4930.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02883, over 971795.43 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 16:16:33,101 INFO [train.py:715] (4/8) Epoch 16, batch 9400, loss[loss=0.1312, simple_loss=0.2085, pruned_loss=0.02694, over 4922.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02902, over 972118.87 frames.], batch size: 29, lr: 1.39e-04
2022-05-08 16:17:11,620 INFO [train.py:715] (4/8) Epoch 16, batch 9450, loss[loss=0.1522, simple_loss=0.2221, pruned_loss=0.0412, over 4944.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02941, over 972727.30 frames.], batch size: 35, lr: 1.39e-04
2022-05-08 16:17:50,525 INFO [train.py:715] (4/8) Epoch 16, batch 9500, loss[loss=0.1432, simple_loss=0.2148, pruned_loss=0.03585, over 4752.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2062, pruned_loss=0.02924, over 971449.09 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 16:18:28,784 INFO [train.py:715] (4/8) Epoch 16, batch 9550, loss[loss=0.1238, simple_loss=0.2067, pruned_loss=0.0205, over 4802.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02934, over 972561.22 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 16:19:08,110 INFO [train.py:715] (4/8) Epoch 16, batch 9600, loss[loss=0.1275, simple_loss=0.2014, pruned_loss=0.0268, over 4873.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02931, over 973113.53 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 16:19:47,954 INFO [train.py:715] (4/8) Epoch 16, batch 9650, loss[loss=0.1239, simple_loss=0.2001, pruned_loss=0.02386, over 4815.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02891, over 972502.13 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 16:20:27,597 INFO [train.py:715] (4/8) Epoch 16, batch 9700, loss[loss=0.1257, simple_loss=0.2022, pruned_loss=0.02463, over 4741.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02954, over 971962.52 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 16:21:08,015 INFO [train.py:715] (4/8) Epoch 16, batch 9750, loss[loss=0.1733, simple_loss=0.2535, pruned_loss=0.04654, over 4965.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03021, over 972219.17 frames.], batch size: 39, lr: 1.39e-04
2022-05-08 16:21:49,082 INFO [train.py:715] (4/8) Epoch 16, batch 9800, loss[loss=0.09516, simple_loss=0.1684, pruned_loss=0.01095, over 4817.00 frames.], tot_loss[loss=0.1349, simple_loss=0.209, pruned_loss=0.03037, over 971905.79 frames.], batch size: 26, lr: 1.39e-04
2022-05-08 16:22:29,510 INFO [train.py:715] (4/8) Epoch 16, batch 9850, loss[loss=0.119, simple_loss=0.1973, pruned_loss=0.02033, over 4757.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02971, over 972288.82 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 16:23:09,296 INFO [train.py:715] (4/8) Epoch 16, batch 9900, loss[loss=0.129, simple_loss=0.2047, pruned_loss=0.02659, over 4746.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2085, pruned_loss=0.02959, over 971987.80 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 16:23:49,479 INFO [train.py:715] (4/8) Epoch 16, batch 9950, loss[loss=0.1293, simple_loss=0.2103, pruned_loss=0.02414, over 4907.00 frames.], tot_loss[loss=0.1335, simple_loss=0.208, pruned_loss=0.02952, over 971794.71 frames.], batch size: 39, lr: 1.39e-04
2022-05-08 16:24:30,457 INFO [train.py:715] (4/8) Epoch 16, batch 10000, loss[loss=0.09241, simple_loss=0.163, pruned_loss=0.01093, over 4830.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02937, over 972409.88 frames.], batch size: 12, lr: 1.39e-04
2022-05-08 16:25:09,383 INFO [train.py:715] (4/8) Epoch 16, batch 10050, loss[loss=0.1231, simple_loss=0.1962, pruned_loss=0.02496, over 4925.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.0295, over 972539.78 frames.], batch size: 23, lr: 1.39e-04
2022-05-08 16:25:49,615 INFO [train.py:715] (4/8) Epoch 16, batch 10100, loss[loss=0.1086, simple_loss=0.1783, pruned_loss=0.01942, over 4798.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02944, over 972342.31 frames.], batch size: 24, lr: 1.39e-04
2022-05-08 16:26:30,390 INFO [train.py:715] (4/8) Epoch 16, batch 10150, loss[loss=0.1551, simple_loss=0.2186, pruned_loss=0.04578, over 4962.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02955, over 972367.11 frames.], batch size: 31, lr: 1.39e-04
2022-05-08 16:27:10,610 INFO [train.py:715] (4/8) Epoch 16, batch 10200, loss[loss=0.1478, simple_loss=0.2254, pruned_loss=0.03506, over 4892.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02917, over 972100.85 frames.], batch size: 22, lr: 1.39e-04
2022-05-08 16:27:49,590 INFO [train.py:715] (4/8) Epoch 16, batch 10250, loss[loss=0.1046, simple_loss=0.1875, pruned_loss=0.01089, over 4923.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02926, over 971245.15 frames.], batch size: 29, lr: 1.39e-04
2022-05-08 16:28:29,498 INFO [train.py:715] (4/8) Epoch 16, batch 10300, loss[loss=0.1437, simple_loss=0.2132, pruned_loss=0.03706, over 4704.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02932, over 971026.43 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 16:29:09,151 INFO [train.py:715] (4/8) Epoch 16, batch 10350, loss[loss=0.1511, simple_loss=0.2226, pruned_loss=0.03975, over 4987.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02967, over 971350.90 frames.], batch size: 28, lr: 1.39e-04
2022-05-08 16:29:47,476 INFO [train.py:715] (4/8) Epoch 16, batch 10400, loss[loss=0.1295, simple_loss=0.1946, pruned_loss=0.03214, over 4862.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02921, over 971708.21 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 16:30:26,268 INFO [train.py:715] (4/8) Epoch 16, batch 10450, loss[loss=0.1187, simple_loss=0.1965, pruned_loss=0.02043, over 4782.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02907, over 971986.61 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 16:31:05,217 INFO [train.py:715] (4/8) Epoch 16, batch 10500, loss[loss=0.1382, simple_loss=0.2185, pruned_loss=0.02898, over 4919.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02911, over 972034.54 frames.], batch size: 17, lr: 1.39e-04
2022-05-08 16:31:44,638 INFO [train.py:715] (4/8) Epoch 16, batch 10550, loss[loss=0.1312, simple_loss=0.2022, pruned_loss=0.03007, over 4830.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02906, over 972367.97 frames.], batch size: 26, lr: 1.39e-04
2022-05-08 16:32:22,611 INFO [train.py:715] (4/8) Epoch 16, batch 10600, loss[loss=0.1184, simple_loss=0.1897, pruned_loss=0.02358, over 4863.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02946, over 972597.03 frames.], batch size: 20, lr: 1.39e-04
2022-05-08 16:33:01,318 INFO [train.py:715] (4/8) Epoch 16, batch 10650, loss[loss=0.1247, simple_loss=0.2008, pruned_loss=0.02432, over 4979.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02926, over 971859.85 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 16:33:40,768 INFO [train.py:715] (4/8) Epoch 16, batch 10700, loss[loss=0.1016, simple_loss=0.1773, pruned_loss=0.01292, over 4932.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02877, over 972105.75 frames.], batch size: 29, lr: 1.39e-04
2022-05-08 16:34:19,601 INFO [train.py:715] (4/8) Epoch 16, batch 10750, loss[loss=0.1307, simple_loss=0.2098, pruned_loss=0.02579, over 4847.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02911, over 971747.87 frames.], batch size: 32, lr: 1.39e-04
2022-05-08 16:34:58,501 INFO [train.py:715] (4/8) Epoch 16, batch 10800, loss[loss=0.1574, simple_loss=0.2186, pruned_loss=0.04808, over 4981.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.0295, over 971616.10 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 16:35:37,666 INFO [train.py:715] (4/8) Epoch 16, batch 10850, loss[loss=0.1135, simple_loss=0.1914, pruned_loss=0.01783, over 4824.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.0295, over 971720.47 frames.], batch size: 25, lr: 1.39e-04
2022-05-08 16:36:17,324 INFO [train.py:715] (4/8) Epoch 16, batch 10900, loss[loss=0.1299, simple_loss=0.209, pruned_loss=0.02537, over 4756.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02915, over 971863.15 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 16:36:55,551 INFO [train.py:715] (4/8) Epoch 16, batch 10950, loss[loss=0.1014, simple_loss=0.1722, pruned_loss=0.01534, over 4832.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02938, over 971740.14 frames.], batch size: 26, lr: 1.39e-04
2022-05-08 16:37:34,521 INFO [train.py:715] (4/8) Epoch 16, batch 11000, loss[loss=0.1695, simple_loss=0.2279, pruned_loss=0.0556, over 4790.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02972, over 972422.55 frames.], batch size: 18, lr: 1.39e-04
2022-05-08 16:38:13,975 INFO [train.py:715] (4/8) Epoch 16, batch 11050, loss[loss=0.1738, simple_loss=0.2508, pruned_loss=0.04838, over 4882.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02947, over 971863.81 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 16:38:55,217 INFO [train.py:715] (4/8) Epoch 16, batch 11100, loss[loss=0.1433, simple_loss=0.2221, pruned_loss=0.03226, over 4796.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.0293, over 972086.02 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 16:39:33,649 INFO [train.py:715] (4/8) Epoch 16, batch 11150, loss[loss=0.1387, simple_loss=0.2059, pruned_loss=0.03574, over 4953.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02989, over 972349.79 frames.], batch size: 15, lr: 1.39e-04
2022-05-08 16:40:12,896 INFO [train.py:715] (4/8) Epoch 16, batch 11200, loss[loss=0.1312, simple_loss=0.2087, pruned_loss=0.02681, over 4760.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02931, over 972029.45 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 16:40:51,684 INFO [train.py:715] (4/8) Epoch 16, batch 11250, loss[loss=0.1242, simple_loss=0.1918, pruned_loss=0.02826, over 4851.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02953, over 972522.96 frames.], batch size: 32, lr: 1.39e-04
2022-05-08 16:41:29,875 INFO [train.py:715] (4/8) Epoch 16, batch 11300, loss[loss=0.1407, simple_loss=0.2119, pruned_loss=0.03479, over 4872.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2059, pruned_loss=0.02921, over 972167.92 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 16:42:08,149 INFO [train.py:715] (4/8) Epoch 16, batch 11350, loss[loss=0.1311, simple_loss=0.2066, pruned_loss=0.02779, over 4754.00 frames.], tot_loss[loss=0.1311, simple_loss=0.205, pruned_loss=0.02866, over 971694.02 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 16:42:47,128 INFO [train.py:715] (4/8) Epoch 16, batch 11400, loss[loss=0.1231, simple_loss=0.2038, pruned_loss=0.02122, over 4864.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2057, pruned_loss=0.02904, over 972085.35 frames.], batch size: 20, lr: 1.39e-04
2022-05-08 16:43:25,156 INFO [train.py:715] (4/8) Epoch 16, batch 11450, loss[loss=0.1274, simple_loss=0.1963, pruned_loss=0.02927, over 4749.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2069, pruned_loss=0.02972, over 972206.54 frames.], batch size: 19, lr: 1.39e-04
2022-05-08 16:44:03,087 INFO [train.py:715] (4/8) Epoch 16, batch 11500, loss[loss=0.1286, simple_loss=0.1999, pruned_loss=0.02862, over 4785.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2067, pruned_loss=0.02981, over 971770.03 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 16:44:41,782 INFO [train.py:715] (4/8) Epoch 16, batch 11550, loss[loss=0.1234, simple_loss=0.2027, pruned_loss=0.02201, over 4934.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02964, over 973031.01 frames.], batch size: 21, lr: 1.39e-04
2022-05-08 16:45:20,367 INFO [train.py:715] (4/8) Epoch 16, batch 11600, loss[loss=0.1245, simple_loss=0.2023, pruned_loss=0.02333, over 4820.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02948, over 972695.66 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 16:45:57,961 INFO [train.py:715] (4/8) Epoch 16, batch 11650, loss[loss=0.09866, simple_loss=0.1756, pruned_loss=0.01086, over 4986.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2067, pruned_loss=0.02983, over 972320.72 frames.], batch size: 14, lr: 1.39e-04
2022-05-08 16:46:36,440 INFO [train.py:715] (4/8) Epoch 16, batch 11700, loss[loss=0.1277, simple_loss=0.2087, pruned_loss=0.02336, over 4743.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2071, pruned_loss=0.02999, over 970780.46 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 16:47:15,522 INFO [train.py:715] (4/8) Epoch 16, batch 11750, loss[loss=0.147, simple_loss=0.2179, pruned_loss=0.03809, over 4875.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2075, pruned_loss=0.03053, over 971144.87 frames.], batch size: 16, lr: 1.39e-04
2022-05-08 16:47:53,672 INFO [train.py:715] (4/8) Epoch 16, batch 11800, loss[loss=0.1219, simple_loss=0.1912, pruned_loss=0.02626, over 4921.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02989, over 970970.50 frames.], batch size: 29, lr: 1.39e-04
2022-05-08 16:48:31,492 INFO [train.py:715] (4/8) Epoch 16, batch 11850, loss[loss=0.1387, simple_loss=0.2161, pruned_loss=0.03063, over 4850.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03017, over 970511.83 frames.], batch size: 30, lr: 1.39e-04
2022-05-08 16:49:10,175 INFO [train.py:715] (4/8) Epoch 16, batch 11900, loss[loss=0.1204, simple_loss=0.1947, pruned_loss=0.02308, over 4806.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02988, over 971133.74 frames.], batch size: 13, lr: 1.39e-04
2022-05-08 16:49:48,594 INFO [train.py:715] (4/8) Epoch 16, batch 11950, loss[loss=0.1244, simple_loss=0.2028, pruned_loss=0.02299, over 4875.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.0296, over 971389.63 frames.], batch size: 20, lr: 1.39e-04
2022-05-08 16:50:26,416 INFO [train.py:715] (4/8) Epoch 16, batch 12000, loss[loss=0.1491, simple_loss=0.2124, pruned_loss=0.04289, over 4850.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.0293, over 972667.26 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 16:50:26,417 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 16:50:37,200 INFO [train.py:742] (4/8) Epoch 16, validation: loss=0.1049, simple_loss=0.1884, pruned_loss=0.01072, over 914524.00 frames.
2022-05-08 16:51:16,047 INFO [train.py:715] (4/8) Epoch 16, batch 12050, loss[loss=0.1415, simple_loss=0.2098, pruned_loss=0.03661, over 4932.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02924, over 972536.67 frames.], batch size: 23, lr: 1.38e-04
2022-05-08 16:51:55,270 INFO [train.py:715] (4/8) Epoch 16, batch 12100, loss[loss=0.1644, simple_loss=0.2446, pruned_loss=0.04212, over 4983.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02964, over 971855.67 frames.], batch size: 24, lr: 1.38e-04
2022-05-08 16:52:34,707 INFO [train.py:715] (4/8) Epoch 16, batch 12150, loss[loss=0.1256, simple_loss=0.2029, pruned_loss=0.02413, over 4987.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03004, over 971731.85 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 16:53:12,371 INFO [train.py:715] (4/8) Epoch 16, batch 12200, loss[loss=0.12, simple_loss=0.1993, pruned_loss=0.02038, over 4874.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02981, over 971968.90 frames.], batch size: 22, lr: 1.38e-04
2022-05-08 16:53:50,653 INFO [train.py:715] (4/8) Epoch 16, batch 12250, loss[loss=0.1485, simple_loss=0.22, pruned_loss=0.03846, over 4943.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.0293, over 972052.19 frames.], batch size: 39, lr: 1.38e-04
2022-05-08 16:54:29,690 INFO [train.py:715] (4/8) Epoch 16, batch 12300, loss[loss=0.1389, simple_loss=0.2177, pruned_loss=0.03012, over 4875.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2082, pruned_loss=0.02962, over 972003.68 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 16:55:08,770 INFO [train.py:715] (4/8) Epoch 16, batch 12350, loss[loss=0.1262, simple_loss=0.1956, pruned_loss=0.02837, over 4981.00 frames.], tot_loss[loss=0.134, simple_loss=0.2082, pruned_loss=0.02991, over 971760.20 frames.], batch size: 35, lr: 1.38e-04
2022-05-08 16:55:47,030 INFO [train.py:715] (4/8) Epoch 16, batch 12400, loss[loss=0.1014, simple_loss=0.1789, pruned_loss=0.01199, over 4842.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03005, over 972096.97 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 16:56:26,127 INFO [train.py:715] (4/8) Epoch 16, batch 12450, loss[loss=0.11, simple_loss=0.1817, pruned_loss=0.01917, over 4766.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02958, over 971526.44 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 16:57:05,988 INFO [train.py:715] (4/8) Epoch 16, batch 12500, loss[loss=0.1256, simple_loss=0.2018, pruned_loss=0.02473, over 4777.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02969, over 972277.96 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 16:57:44,595 INFO [train.py:715] (4/8) Epoch 16, batch 12550, loss[loss=0.1472, simple_loss=0.2209, pruned_loss=0.03677, over 4891.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02991, over 971726.47 frames.], batch size: 22, lr: 1.38e-04
2022-05-08 16:58:23,181 INFO [train.py:715] (4/8) Epoch 16, batch 12600, loss[loss=0.1339, simple_loss=0.2069, pruned_loss=0.03047, over 4859.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02965, over 971281.11 frames.], batch size: 20, lr: 1.38e-04
2022-05-08 16:59:01,904 INFO [train.py:715] (4/8) Epoch 16, batch 12650, loss[loss=0.1129, simple_loss=0.1851, pruned_loss=0.02037, over 4840.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02942, over 972543.16 frames.], batch size: 30, lr: 1.38e-04
2022-05-08 16:59:40,535 INFO [train.py:715] (4/8) Epoch 16, batch 12700, loss[loss=0.1104, simple_loss=0.188, pruned_loss=0.01637, over 4900.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2079, pruned_loss=0.02913, over 972142.67 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 17:00:18,085 INFO [train.py:715] (4/8) Epoch 16, batch 12750, loss[loss=0.1245, simple_loss=0.1949, pruned_loss=0.02708, over 4942.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02936, over 972990.32 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:00:57,705 INFO [train.py:715] (4/8) Epoch 16, batch 12800, loss[loss=0.112, simple_loss=0.1897, pruned_loss=0.01717, over 4859.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.0292, over 972390.27 frames.], batch size: 20, lr: 1.38e-04
2022-05-08 17:01:36,684 INFO [train.py:715] (4/8) Epoch 16, batch 12850, loss[loss=0.1307, simple_loss=0.203, pruned_loss=0.02922, over 4978.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02922, over 973213.27 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:02:15,045 INFO [train.py:715] (4/8) Epoch 16, batch 12900, loss[loss=0.1267, simple_loss=0.2017, pruned_loss=0.02589, over 4899.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02895, over 972392.30 frames.], batch size: 23, lr: 1.38e-04
2022-05-08 17:02:53,759 INFO [train.py:715] (4/8) Epoch 16, batch 12950, loss[loss=0.1397, simple_loss=0.2128, pruned_loss=0.03331, over 4983.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.0291, over 971947.00 frames.], batch size: 28, lr: 1.38e-04
2022-05-08 17:03:32,778 INFO [train.py:715] (4/8) Epoch 16, batch 13000, loss[loss=0.1344, simple_loss=0.2036, pruned_loss=0.03263, over 4766.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02905, over 971438.96 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:04:11,281 INFO [train.py:715] (4/8) Epoch 16, batch 13050, loss[loss=0.1299, simple_loss=0.1859, pruned_loss=0.0369, over 4766.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02933, over 971690.58 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:04:49,802 INFO [train.py:715] (4/8) Epoch 16, batch 13100, loss[loss=0.1135, simple_loss=0.1732, pruned_loss=0.02692, over 4641.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02901, over 971583.47 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 17:05:28,950 INFO [train.py:715] (4/8) Epoch 16, batch 13150, loss[loss=0.1065, simple_loss=0.1811, pruned_loss=0.01598, over 4942.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.0292, over 971386.70 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:06:08,072 INFO [train.py:715] (4/8) Epoch 16, batch 13200, loss[loss=0.1261, simple_loss=0.2044, pruned_loss=0.02387, over 4921.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02931, over 971312.67 frames.], batch size: 39, lr: 1.38e-04
2022-05-08 17:06:46,154 INFO [train.py:715] (4/8) Epoch 16, batch 13250, loss[loss=0.1652, simple_loss=0.2431, pruned_loss=0.04365, over 4737.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.0295, over 971448.99 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 17:07:25,007 INFO [train.py:715] (4/8) Epoch 16, batch 13300, loss[loss=0.1332, simple_loss=0.2118, pruned_loss=0.0273, over 4833.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2066, pruned_loss=0.02937, over 971853.84 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:08:04,361 INFO [train.py:715] (4/8) Epoch 16, batch 13350, loss[loss=0.1177, simple_loss=0.1864, pruned_loss=0.02453, over 4747.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02936, over 971812.92 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 17:08:42,683 INFO [train.py:715] (4/8) Epoch 16, batch 13400, loss[loss=0.139, simple_loss=0.2112, pruned_loss=0.03335, over 4952.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02932, over 972280.38 frames.], batch size: 35, lr: 1.38e-04
2022-05-08 17:09:21,146 INFO [train.py:715] (4/8) Epoch 16, batch 13450, loss[loss=0.1391, simple_loss=0.2117, pruned_loss=0.03322, over 4843.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02982, over 972069.15 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:10:00,909 INFO [train.py:715] (4/8) Epoch 16, batch 13500, loss[loss=0.1076, simple_loss=0.1905, pruned_loss=0.01231, over 4930.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.02995, over 971987.40 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:10:39,239 INFO [train.py:715] (4/8) Epoch 16, batch 13550, loss[loss=0.1338, simple_loss=0.2134, pruned_loss=0.02707, over 4827.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2087, pruned_loss=0.0298, over 972370.48 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:11:17,353 INFO [train.py:715] (4/8) Epoch 16, batch 13600, loss[loss=0.1554, simple_loss=0.2301, pruned_loss=0.04034, over 4716.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02948, over 972387.91 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:11:56,186 INFO [train.py:715] (4/8) Epoch 16, batch 13650, loss[loss=0.1518, simple_loss=0.2159, pruned_loss=0.04388, over 4913.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02997, over 972591.30 frames.], batch size: 39, lr: 1.38e-04
2022-05-08 17:12:35,108 INFO [train.py:715] (4/8) Epoch 16, batch 13700, loss[loss=0.1337, simple_loss=0.2163, pruned_loss=0.02558, over 4730.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03002, over 972759.48 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 17:13:13,501 INFO [train.py:715] (4/8) Epoch 16, batch 13750, loss[loss=0.1764, simple_loss=0.2569, pruned_loss=0.04795, over 4913.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03014, over 972466.57 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:13:52,006 INFO [train.py:715] (4/8) Epoch 16, batch 13800, loss[loss=0.1321, simple_loss=0.1992, pruned_loss=0.0325, over 4845.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.0303, over 972436.05 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 17:14:30,650 INFO [train.py:715] (4/8) Epoch 16, batch 13850, loss[loss=0.1214, simple_loss=0.1967, pruned_loss=0.02312, over 4641.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03021, over 972113.03 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 17:15:08,621 INFO [train.py:715] (4/8) Epoch 16, batch 13900, loss[loss=0.1098, simple_loss=0.1773, pruned_loss=0.02114, over 4814.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03006, over 971797.38 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 17:15:46,307 INFO [train.py:715] (4/8) Epoch 16, batch 13950, loss[loss=0.1709, simple_loss=0.2418, pruned_loss=0.05005, over 4980.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02963, over 973187.40 frames.], batch size: 35, lr: 1.38e-04
2022-05-08 17:16:24,661 INFO [train.py:715] (4/8) Epoch 16, batch 14000, loss[loss=0.1395, simple_loss=0.2186, pruned_loss=0.03022, over 4761.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03018, over 973272.06 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:17:03,281 INFO [train.py:715] (4/8) Epoch 16, batch 14050, loss[loss=0.1211, simple_loss=0.1993, pruned_loss=0.02141, over 4798.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03005, over 972720.98 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:17:41,057 INFO [train.py:715] (4/8) Epoch 16, batch 14100, loss[loss=0.1212, simple_loss=0.1971, pruned_loss=0.02261, over 4761.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03021, over 972450.13 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 17:18:18,776 INFO [train.py:715] (4/8) Epoch 16, batch 14150, loss[loss=0.141, simple_loss=0.2157, pruned_loss=0.03319, over 4775.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02995, over 971997.40 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:18:57,314 INFO [train.py:715] (4/8) Epoch 16, batch 14200, loss[loss=0.1258, simple_loss=0.2086, pruned_loss=0.02148, over 4688.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.0299, over 971557.91 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:19:36,006 INFO [train.py:715] (4/8) Epoch 16, batch 14250, loss[loss=0.1192, simple_loss=0.2027, pruned_loss=0.01781, over 4788.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03014, over 971728.51 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:20:14,628 INFO [train.py:715] (4/8) Epoch 16, batch 14300, loss[loss=0.1523, simple_loss=0.2301, pruned_loss=0.03724, over 4835.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2091, pruned_loss=0.03028, over 971734.79 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:20:53,330 INFO [train.py:715] (4/8) Epoch 16, batch 14350, loss[loss=0.1367, simple_loss=0.2141, pruned_loss=0.02968, over 4747.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2088, pruned_loss=0.02991, over 971470.53 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 17:21:32,523 INFO [train.py:715] (4/8) Epoch 16, batch 14400, loss[loss=0.1361, simple_loss=0.2086, pruned_loss=0.03179, over 4754.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2091, pruned_loss=0.02999, over 970908.60 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 17:22:10,258 INFO [train.py:715] (4/8) Epoch 16, batch 14450, loss[loss=0.09972, simple_loss=0.1648, pruned_loss=0.01734, over 4751.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2082, pruned_loss=0.02956, over 971016.57 frames.], batch size: 12, lr: 1.38e-04
2022-05-08 17:22:49,091 INFO [train.py:715] (4/8) Epoch 16, batch 14500, loss[loss=0.1189, simple_loss=0.1924, pruned_loss=0.02265, over 4882.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02985, over 971255.31 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 17:23:28,025 INFO [train.py:715] (4/8) Epoch 16, batch 14550, loss[loss=0.1231, simple_loss=0.201, pruned_loss=0.02264, over 4933.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02934, over 971553.57 frames.], batch size: 29, lr: 1.38e-04
2022-05-08 17:24:06,691 INFO [train.py:715] (4/8) Epoch 16, batch 14600, loss[loss=0.1417, simple_loss=0.2053, pruned_loss=0.03909, over 4770.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02958, over 972583.46 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 17:24:44,962 INFO [train.py:715] (4/8) Epoch 16, batch 14650, loss[loss=0.139, simple_loss=0.2139, pruned_loss=0.03203, over 4977.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02951, over 972389.80 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:25:23,541 INFO [train.py:715] (4/8) Epoch 16, batch 14700, loss[loss=0.1023, simple_loss=0.1722, pruned_loss=0.01618, over 4967.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02932, over 972440.92 frames.], batch size: 28, lr: 1.38e-04
2022-05-08 17:26:02,838 INFO [train.py:715] (4/8) Epoch 16, batch 14750, loss[loss=0.135, simple_loss=0.2204, pruned_loss=0.02481, over 4946.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2063, pruned_loss=0.02953, over 971697.46 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:26:40,632 INFO [train.py:715] (4/8) Epoch 16, batch 14800, loss[loss=0.1296, simple_loss=0.206, pruned_loss=0.02659, over 4941.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02979, over 971507.38 frames.], batch size: 29, lr: 1.38e-04
2022-05-08 17:27:19,698 INFO [train.py:715] (4/8) Epoch 16, batch 14850, loss[loss=0.1306, simple_loss=0.1991, pruned_loss=0.03103, over 4850.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02986, over 971595.65 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 17:27:58,605 INFO [train.py:715] (4/8) Epoch 16, batch 14900, loss[loss=0.1288, simple_loss=0.2133, pruned_loss=0.02216, over 4804.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.02995, over 971665.89 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 17:28:37,058 INFO [train.py:715] (4/8) Epoch 16, batch 14950, loss[loss=0.1115, simple_loss=0.1847, pruned_loss=0.01916, over 4786.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02966, over 972175.56 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:29:16,115 INFO [train.py:715] (4/8) Epoch 16, batch 15000, loss[loss=0.1624, simple_loss=0.2341, pruned_loss=0.04538, over 4811.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2084, pruned_loss=0.02959, over 972383.78 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:29:16,115 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 17:29:25,725 INFO [train.py:742] (4/8) Epoch 16, validation: loss=0.1049, simple_loss=0.1884, pruned_loss=0.01069, over 914524.00 frames.
2022-05-08 17:30:04,000 INFO [train.py:715] (4/8) Epoch 16, batch 15050, loss[loss=0.1396, simple_loss=0.2143, pruned_loss=0.0324, over 4889.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02977, over 972561.96 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 17:30:42,063 INFO [train.py:715] (4/8) Epoch 16, batch 15100, loss[loss=0.1147, simple_loss=0.1955, pruned_loss=0.01697, over 4820.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02933, over 972771.66 frames.], batch size: 26, lr: 1.38e-04
2022-05-08 17:31:20,869 INFO [train.py:715] (4/8) Epoch 16, batch 15150, loss[loss=0.1748, simple_loss=0.2543, pruned_loss=0.04768, over 4899.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2084, pruned_loss=0.02964, over 972964.05 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 17:31:58,565 INFO [train.py:715] (4/8) Epoch 16, batch 15200, loss[loss=0.1194, simple_loss=0.1953, pruned_loss=0.02177, over 4753.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.0303, over 971784.91 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 17:32:36,117 INFO [train.py:715] (4/8) Epoch 16, batch 15250, loss[loss=0.1311, simple_loss=0.1988, pruned_loss=0.03175, over 4884.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02998, over 972575.22 frames.], batch size: 22, lr: 1.38e-04
2022-05-08 17:33:14,326 INFO [train.py:715] (4/8) Epoch 16, batch 15300, loss[loss=0.115, simple_loss=0.1785, pruned_loss=0.02575, over 4990.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03024, over 972607.60 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:33:52,472 INFO [train.py:715] (4/8) Epoch 16, batch 15350, loss[loss=0.1322, simple_loss=0.216, pruned_loss=0.02417, over 4816.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02958, over 972745.40 frames.], batch size: 27, lr: 1.38e-04
2022-05-08 17:34:30,725 INFO [train.py:715] (4/8) Epoch 16, batch 15400, loss[loss=0.1311, simple_loss=0.2008, pruned_loss=0.03071, over 4864.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2079, pruned_loss=0.02994, over 973385.81 frames.], batch size: 20, lr: 1.38e-04
2022-05-08 17:35:08,738 INFO [train.py:715] (4/8) Epoch 16, batch 15450, loss[loss=0.1418, simple_loss=0.2125, pruned_loss=0.03556, over 4844.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.0296, over 972739.94 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:35:47,168 INFO [train.py:715] (4/8) Epoch 16, batch 15500, loss[loss=0.1274, simple_loss=0.1973, pruned_loss=0.02873, over 4969.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02913, over 972383.13 frames.], batch size: 24, lr: 1.38e-04
2022-05-08 17:36:24,797 INFO [train.py:715] (4/8) Epoch 16, batch 15550, loss[loss=0.1014, simple_loss=0.1726, pruned_loss=0.01514, over 4768.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02898, over 971692.51 frames.], batch size: 12, lr: 1.38e-04
2022-05-08 17:37:02,463 INFO [train.py:715] (4/8) Epoch 16, batch 15600, loss[loss=0.1261, simple_loss=0.2009, pruned_loss=0.02566, over 4639.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02901, over 971117.12 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 17:37:41,081 INFO [train.py:715] (4/8) Epoch 16, batch 15650, loss[loss=0.1158, simple_loss=0.1825, pruned_loss=0.02455, over 4815.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02946, over 971757.79 frames.], batch size: 12, lr: 1.38e-04
2022-05-08 17:38:19,115 INFO [train.py:715] (4/8) Epoch 16, batch 15700, loss[loss=0.1203, simple_loss=0.1932, pruned_loss=0.0237, over 4893.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02976, over 971821.33 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 17:38:56,850 INFO [train.py:715] (4/8) Epoch 16, batch 15750, loss[loss=0.1666, simple_loss=0.2564, pruned_loss=0.03842, over 4639.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.02996, over 971823.33 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 17:39:34,739 INFO [train.py:715] (4/8) Epoch 16, batch 15800, loss[loss=0.1299, simple_loss=0.2081, pruned_loss=0.02585, over 4984.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02965, over 972036.47 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 17:40:13,083 INFO [train.py:715] (4/8) Epoch 16, batch 15850, loss[loss=0.1383, simple_loss=0.215, pruned_loss=0.03082, over 4759.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02962, over 973331.79 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 17:40:50,713 INFO [train.py:715] (4/8) Epoch 16, batch 15900, loss[loss=0.1408, simple_loss=0.2203, pruned_loss=0.03061, over 4988.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2082, pruned_loss=0.02941, over 972711.19 frames.], batch size: 28, lr: 1.38e-04
2022-05-08 17:41:28,315 INFO [train.py:715] (4/8) Epoch 16, batch 15950, loss[loss=0.1278, simple_loss=0.1969, pruned_loss=0.02933, over 4797.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2075, pruned_loss=0.02887, over 972962.26 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:42:06,730 INFO [train.py:715] (4/8) Epoch 16, batch 16000, loss[loss=0.1243, simple_loss=0.2026, pruned_loss=0.02301, over 4975.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02867, over 972884.51 frames.], batch size: 28, lr: 1.38e-04
2022-05-08 17:42:44,834 INFO [train.py:715] (4/8) Epoch 16, batch 16050, loss[loss=0.1462, simple_loss=0.214, pruned_loss=0.03918, over 4875.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02932, over 971974.12 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 17:43:22,459 INFO [train.py:715] (4/8) Epoch 16, batch 16100, loss[loss=0.1282, simple_loss=0.201, pruned_loss=0.02769, over 4828.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02969, over 972026.79 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 17:43:59,972 INFO [train.py:715] (4/8) Epoch 16, batch 16150, loss[loss=0.1456, simple_loss=0.219, pruned_loss=0.03612, over 4867.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02921, over 971148.00 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 17:44:38,353 INFO [train.py:715] (4/8) Epoch 16, batch 16200, loss[loss=0.1283, simple_loss=0.2075, pruned_loss=0.02453, over 4929.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02924, over 972212.49 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:45:15,917 INFO [train.py:715] (4/8) Epoch 16, batch 16250, loss[loss=0.1406, simple_loss=0.2061, pruned_loss=0.03757, over 4981.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02908, over 973029.59 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:45:53,548 INFO [train.py:715] (4/8) Epoch 16, batch 16300, loss[loss=0.1313, simple_loss=0.2133, pruned_loss=0.02458, over 4853.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02917, over 972271.30 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:46:31,875 INFO [train.py:715] (4/8) Epoch 16, batch 16350, loss[loss=0.132, simple_loss=0.2041, pruned_loss=0.02992, over 4871.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02906, over 971709.10 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 17:47:10,534 INFO [train.py:715] (4/8) Epoch 16, batch 16400, loss[loss=0.1298, simple_loss=0.2003, pruned_loss=0.02961, over 4978.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02917, over 972274.74 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 17:47:47,570 INFO [train.py:715] (4/8) Epoch 16, batch 16450, loss[loss=0.1312, simple_loss=0.199, pruned_loss=0.03164, over 4781.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02904, over 972553.60 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 17:48:25,523 INFO [train.py:715] (4/8) Epoch 16, batch 16500, loss[loss=0.1427, simple_loss=0.225, pruned_loss=0.03023, over 4950.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02878, over 972469.05 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:49:04,091 INFO [train.py:715] (4/8) Epoch 16, batch 16550, loss[loss=0.1681, simple_loss=0.2342, pruned_loss=0.05101, over 4961.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02892, over 972568.44 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:49:41,515 INFO [train.py:715] (4/8) Epoch 16, batch 16600, loss[loss=0.1312, simple_loss=0.2106, pruned_loss=0.02593, over 4921.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02921, over 971496.50 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:50:19,531 INFO [train.py:715] (4/8) Epoch 16, batch 16650, loss[loss=0.1553, simple_loss=0.2299, pruned_loss=0.04037, over 4858.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02913, over 972014.70 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 17:50:57,795 INFO [train.py:715] (4/8) Epoch 16, batch 16700, loss[loss=0.1294, simple_loss=0.2055, pruned_loss=0.02664, over 4814.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02982, over 972504.73 frames.], batch size: 26, lr: 1.38e-04
2022-05-08 17:51:35,936 INFO [train.py:715] (4/8) Epoch 16, batch 16750, loss[loss=0.1197, simple_loss=0.1898, pruned_loss=0.0248, over 4837.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02966, over 972377.10 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:52:13,453 INFO [train.py:715] (4/8) Epoch 16, batch 16800, loss[loss=0.1348, simple_loss=0.2218, pruned_loss=0.02384, over 4766.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02982, over 972557.73 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:52:51,537 INFO [train.py:715] (4/8) Epoch 16, batch 16850, loss[loss=0.1262, simple_loss=0.2083, pruned_loss=0.02208, over 4888.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02957, over 972823.54 frames.], batch size: 22, lr: 1.38e-04
2022-05-08 17:53:30,000 INFO [train.py:715] (4/8) Epoch 16, batch 16900, loss[loss=0.1364, simple_loss=0.2127, pruned_loss=0.03006, over 4809.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02974, over 973380.54 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 17:54:07,608 INFO [train.py:715] (4/8) Epoch 16, batch 16950, loss[loss=0.1505, simple_loss=0.2241, pruned_loss=0.03844, over 4812.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02947, over 973359.33 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 17:54:45,478 INFO [train.py:715] (4/8) Epoch 16, batch 17000, loss[loss=0.1428, simple_loss=0.2168, pruned_loss=0.03441, over 4973.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02945, over 973386.08 frames.], batch size: 28, lr: 1.38e-04
2022-05-08 17:55:23,672 INFO [train.py:715] (4/8) Epoch 16, batch 17050, loss[loss=0.1518, simple_loss=0.2208, pruned_loss=0.04135, over 4840.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02964, over 973033.68 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 17:56:02,258 INFO [train.py:715] (4/8) Epoch 16, batch 17100, loss[loss=0.1291, simple_loss=0.205, pruned_loss=0.0266, over 4785.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02963, over 973505.79 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 17:56:39,332 INFO [train.py:715] (4/8) Epoch 16, batch 17150, loss[loss=0.1436, simple_loss=0.2215, pruned_loss=0.03288, over 4982.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02965, over 973476.38 frames.], batch size: 27, lr: 1.38e-04
2022-05-08 17:57:17,464 INFO [train.py:715] (4/8) Epoch 16, batch 17200, loss[loss=0.1273, simple_loss=0.2049, pruned_loss=0.02483, over 4864.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02995, over 973351.10 frames.], batch size: 20, lr: 1.38e-04
2022-05-08 17:57:56,360 INFO [train.py:715] (4/8) Epoch 16, batch 17250, loss[loss=0.1382, simple_loss=0.2232, pruned_loss=0.02658, over 4798.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02988, over 973201.45 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 17:58:33,737 INFO [train.py:715] (4/8) Epoch 16, batch 17300, loss[loss=0.1355, simple_loss=0.2042, pruned_loss=0.03341, over 4829.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02983, over 973616.95 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:59:11,266 INFO [train.py:715] (4/8) Epoch 16, batch 17350, loss[loss=0.1231, simple_loss=0.1926, pruned_loss=0.02678, over 4826.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03013, over 974839.26 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 17:59:49,079 INFO [train.py:715] (4/8) Epoch 16, batch 17400, loss[loss=0.1605, simple_loss=0.2277, pruned_loss=0.04662, over 4975.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03017, over 974220.43 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:00:27,744 INFO [train.py:715] (4/8) Epoch 16, batch 17450, loss[loss=0.1639, simple_loss=0.2292, pruned_loss=0.04932, over 4912.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03028, over 973532.07 frames.], batch size: 39, lr: 1.38e-04
2022-05-08 18:01:04,505 INFO [train.py:715] (4/8) Epoch 16, batch 17500, loss[loss=0.1252, simple_loss=0.1941, pruned_loss=0.02821, over 4990.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03003, over 972504.21 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 18:01:42,654 INFO [train.py:715] (4/8) Epoch 16, batch 17550, loss[loss=0.1465, simple_loss=0.2211, pruned_loss=0.0359, over 4887.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03001, over 972329.33 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 18:02:21,340 INFO [train.py:715] (4/8) Epoch 16, batch 17600, loss[loss=0.1275, simple_loss=0.202, pruned_loss=0.02647, over 4937.00 frames.], tot_loss[loss=0.1342, simple_loss=0.208, pruned_loss=0.03018, over 972049.68 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 18:02:58,692 INFO [train.py:715] (4/8) Epoch 16, batch 17650, loss[loss=0.1554, simple_loss=0.2362, pruned_loss=0.03734, over 4939.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03016, over 972779.75 frames.], batch size: 23, lr: 1.38e-04
2022-05-08 18:03:36,635 INFO [train.py:715] (4/8) Epoch 16, batch 17700, loss[loss=0.1325, simple_loss=0.199, pruned_loss=0.03298, over 4872.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2087, pruned_loss=0.03052, over 972790.05 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 18:04:15,003 INFO [train.py:715] (4/8) Epoch 16, batch 17750, loss[loss=0.1151, simple_loss=0.1845, pruned_loss=0.02282, over 4902.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2078, pruned_loss=0.03021, over 972685.91 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 18:04:53,068 INFO [train.py:715] (4/8) Epoch 16, batch 17800, loss[loss=0.1325, simple_loss=0.2136, pruned_loss=0.02572, over 4804.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2083, pruned_loss=0.03027, over 972818.35 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 18:05:30,278 INFO [train.py:715] (4/8) Epoch 16, batch 17850, loss[loss=0.1125, simple_loss=0.1945, pruned_loss=0.01526, over 4943.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2075, pruned_loss=0.02992, over 972887.08 frames.], batch size: 29, lr: 1.38e-04
2022-05-08 18:06:08,448 INFO [train.py:715] (4/8) Epoch 16, batch 17900, loss[loss=0.138, simple_loss=0.2032, pruned_loss=0.0364, over 4700.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2072, pruned_loss=0.02997, over 972872.54 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:06:46,889 INFO [train.py:715] (4/8) Epoch 16, batch 17950, loss[loss=0.1244, simple_loss=0.2021, pruned_loss=0.02334, over 4769.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02961, over 972229.26 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:07:24,272 INFO [train.py:715] (4/8) Epoch 16, batch 18000, loss[loss=0.1382, simple_loss=0.2187, pruned_loss=0.02884, over 4915.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02968, over 972393.29 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 18:07:24,272 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 18:07:33,811 INFO [train.py:742] (4/8) Epoch 16, validation: loss=0.105, simple_loss=0.1884, pruned_loss=0.01082, over 914524.00 frames.
2022-05-08 18:08:11,783 INFO [train.py:715] (4/8) Epoch 16, batch 18050, loss[loss=0.1202, simple_loss=0.2022, pruned_loss=0.0191, over 4912.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02963, over 972538.41 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 18:08:50,194 INFO [train.py:715] (4/8) Epoch 16, batch 18100, loss[loss=0.1323, simple_loss=0.209, pruned_loss=0.02774, over 4979.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2088, pruned_loss=0.03015, over 972351.12 frames.], batch size: 28, lr: 1.38e-04
2022-05-08 18:09:28,839 INFO [train.py:715] (4/8) Epoch 16, batch 18150, loss[loss=0.138, simple_loss=0.2034, pruned_loss=0.03632, over 4826.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03035, over 971692.88 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:10:07,489 INFO [train.py:715] (4/8) Epoch 16, batch 18200, loss[loss=0.1261, simple_loss=0.2004, pruned_loss=0.02591, over 4749.00 frames.], tot_loss[loss=0.135, simple_loss=0.2088, pruned_loss=0.0306, over 971953.81 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 18:10:45,082 INFO [train.py:715] (4/8) Epoch 16, batch 18250, loss[loss=0.1611, simple_loss=0.2313, pruned_loss=0.04545, over 4740.00 frames.], tot_loss[loss=0.1354, simple_loss=0.209, pruned_loss=0.03091, over 971290.60 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 18:11:23,846 INFO [train.py:715] (4/8) Epoch 16, batch 18300, loss[loss=0.1357, simple_loss=0.2, pruned_loss=0.03568, over 4931.00 frames.], tot_loss[loss=0.1352, simple_loss=0.2086, pruned_loss=0.03092, over 971367.94 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 18:12:02,947 INFO [train.py:715] (4/8) Epoch 16, batch 18350, loss[loss=0.1405, simple_loss=0.2164, pruned_loss=0.03231, over 4704.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2078, pruned_loss=0.0303, over 971730.73 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:12:40,719 INFO [train.py:715] (4/8) Epoch 16, batch 18400, loss[loss=0.1399, simple_loss=0.2127, pruned_loss=0.03351, over 4854.00 frames.], tot_loss[loss=0.1346, simple_loss=0.208, pruned_loss=0.03056, over 971489.22 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 18:13:19,242 INFO [train.py:715] (4/8) Epoch 16, batch 18450, loss[loss=0.1173, simple_loss=0.1864, pruned_loss=0.02415, over 4803.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2083, pruned_loss=0.0306, over 970841.31 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:13:57,851 INFO [train.py:715] (4/8) Epoch 16, batch 18500, loss[loss=0.1281, simple_loss=0.2077, pruned_loss=0.02428, over 4904.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03011, over 970514.72 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:14:36,371 INFO [train.py:715] (4/8) Epoch 16, batch 18550, loss[loss=0.1099, simple_loss=0.181, pruned_loss=0.0194, over 4993.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.03003, over 971291.47 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 18:15:13,855 INFO [train.py:715] (4/8) Epoch 16, batch 18600, loss[loss=0.1265, simple_loss=0.1953, pruned_loss=0.02881, over 4897.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03013, over 971768.25 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:15:52,137 INFO [train.py:715] (4/8) Epoch 16, batch 18650, loss[loss=0.1218, simple_loss=0.1924, pruned_loss=0.0256, over 4972.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03024, over 971887.66 frames.], batch size: 35, lr: 1.38e-04
2022-05-08 18:16:30,640 INFO [train.py:715] (4/8) Epoch 16, batch 18700, loss[loss=0.1154, simple_loss=0.1967, pruned_loss=0.01705, over 4940.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02959, over 973020.81 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 18:17:08,138 INFO [train.py:715] (4/8) Epoch 16, batch 18750, loss[loss=0.1311, simple_loss=0.1957, pruned_loss=0.03326, over 4989.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.02963, over 972439.09 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 18:17:45,511 INFO [train.py:715] (4/8) Epoch 16, batch 18800, loss[loss=0.1317, simple_loss=0.2046, pruned_loss=0.02943, over 4778.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02942, over 973119.78 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 18:18:23,820 INFO [train.py:715] (4/8) Epoch 16, batch 18850, loss[loss=0.1155, simple_loss=0.193, pruned_loss=0.01895, over 4803.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03, over 973230.24 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 18:19:02,089 INFO [train.py:715] (4/8) Epoch 16, batch 18900, loss[loss=0.1377, simple_loss=0.2136, pruned_loss=0.03092, over 4848.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02933, over 973471.88 frames.], batch size: 34, lr: 1.38e-04
2022-05-08 18:19:39,522 INFO [train.py:715] (4/8) Epoch 16, batch 18950, loss[loss=0.1189, simple_loss=0.192, pruned_loss=0.02289, over 4755.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02942, over 973042.33 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 18:20:17,358 INFO [train.py:715] (4/8) Epoch 16, batch 19000, loss[loss=0.1726, simple_loss=0.2396, pruned_loss=0.05279, over 4766.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02985, over 972716.59 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 18:20:55,965 INFO [train.py:715] (4/8) Epoch 16, batch 19050, loss[loss=0.1119, simple_loss=0.1779, pruned_loss=0.02298, over 4779.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03006, over 972497.82 frames.], batch size: 12, lr: 1.38e-04
2022-05-08 18:21:36,427 INFO [train.py:715] (4/8) Epoch 16, batch 19100, loss[loss=0.1261, simple_loss=0.193, pruned_loss=0.02958, over 4964.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02987, over 972907.53 frames.], batch size: 14, lr: 1.38e-04
2022-05-08 18:22:14,089 INFO [train.py:715] (4/8) Epoch 16, batch 19150, loss[loss=0.1323, simple_loss=0.2136, pruned_loss=0.02546, over 4914.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03003, over 972544.64 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 18:22:52,370 INFO [train.py:715] (4/8) Epoch 16, batch 19200, loss[loss=0.1136, simple_loss=0.1904, pruned_loss=0.01843, over 4936.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03009, over 972624.02 frames.], batch size: 23, lr: 1.38e-04
2022-05-08 18:23:31,021 INFO [train.py:715] (4/8) Epoch 16, batch 19250, loss[loss=0.1406, simple_loss=0.2153, pruned_loss=0.03292, over 4930.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03034, over 971967.55 frames.], batch size: 39, lr: 1.38e-04
2022-05-08 18:24:08,554 INFO [train.py:715] (4/8) Epoch 16, batch 19300, loss[loss=0.1319, simple_loss=0.2015, pruned_loss=0.03114, over 4939.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.0299, over 971078.78 frames.], batch size: 23, lr: 1.38e-04
2022-05-08 18:24:46,583 INFO [train.py:715] (4/8) Epoch 16, batch 19350, loss[loss=0.1109, simple_loss=0.1785, pruned_loss=0.02166, over 4638.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03001, over 970569.83 frames.], batch size: 13, lr: 1.38e-04
2022-05-08 18:25:25,226 INFO [train.py:715] (4/8) Epoch 16, batch 19400, loss[loss=0.1402, simple_loss=0.2071, pruned_loss=0.03661, over 4805.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03031, over 970547.14 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 18:26:03,259 INFO [train.py:715] (4/8) Epoch 16, batch 19450, loss[loss=0.1312, simple_loss=0.1958, pruned_loss=0.03333, over 4887.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02961, over 970774.47 frames.], batch size: 32, lr: 1.38e-04
2022-05-08 18:26:40,797 INFO [train.py:715] (4/8) Epoch 16, batch 19500, loss[loss=0.1179, simple_loss=0.1999, pruned_loss=0.01794, over 4842.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02981, over 972035.23 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:27:18,956 INFO [train.py:715] (4/8) Epoch 16, batch 19550, loss[loss=0.1278, simple_loss=0.1994, pruned_loss=0.02807, over 4941.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02962, over 971765.59 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 18:27:57,191 INFO [train.py:715] (4/8) Epoch 16, batch 19600, loss[loss=0.1652, simple_loss=0.2332, pruned_loss=0.04863, over 4683.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02943, over 971771.28 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:28:34,599 INFO [train.py:715] (4/8) Epoch 16, batch 19650, loss[loss=0.1345, simple_loss=0.2032, pruned_loss=0.03288, over 4951.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02936, over 973075.23 frames.], batch size: 21, lr: 1.38e-04
2022-05-08 18:29:12,874 INFO [train.py:715] (4/8) Epoch 16, batch 19700, loss[loss=0.1474, simple_loss=0.2224, pruned_loss=0.03624, over 4781.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2075, pruned_loss=0.03011, over 973173.17 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:29:51,092 INFO [train.py:715] (4/8) Epoch 16, batch 19750, loss[loss=0.1369, simple_loss=0.2051, pruned_loss=0.03436, over 4919.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2082, pruned_loss=0.03049, over 972687.11 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:30:28,917 INFO [train.py:715] (4/8) Epoch 16, batch 19800, loss[loss=0.117, simple_loss=0.1911, pruned_loss=0.02149, over 4978.00 frames.], tot_loss[loss=0.1356, simple_loss=0.2093, pruned_loss=0.03099, over 973788.99 frames.], batch size: 25, lr: 1.38e-04
2022-05-08 18:31:06,636 INFO [train.py:715] (4/8) Epoch 16, batch 19850, loss[loss=0.1468, simple_loss=0.2309, pruned_loss=0.03139, over 4863.00 frames.], tot_loss[loss=0.1351, simple_loss=0.209, pruned_loss=0.03063, over 972670.96 frames.], batch size: 22, lr: 1.38e-04
2022-05-08 18:31:44,940 INFO [train.py:715] (4/8) Epoch 16, batch 19900, loss[loss=0.1752, simple_loss=0.232, pruned_loss=0.05922, over 4977.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2083, pruned_loss=0.03007, over 972216.37 frames.], batch size: 16, lr: 1.38e-04
2022-05-08 18:32:22,972 INFO [train.py:715] (4/8) Epoch 16, batch 19950, loss[loss=0.1169, simple_loss=0.2002, pruned_loss=0.01678, over 4907.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2086, pruned_loss=0.02999, over 972003.58 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 18:33:00,612 INFO [train.py:715] (4/8) Epoch 16, batch 20000, loss[loss=0.1386, simple_loss=0.2015, pruned_loss=0.03789, over 4974.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02965, over 972511.30 frames.], batch size: 15, lr: 1.38e-04
2022-05-08 18:33:38,890 INFO [train.py:715] (4/8) Epoch 16, batch 20050, loss[loss=0.1408, simple_loss=0.2154, pruned_loss=0.03314, over 4776.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02933, over 972880.69 frames.], batch size: 17, lr: 1.38e-04
2022-05-08 18:34:17,305 INFO [train.py:715] (4/8) Epoch 16, batch 20100, loss[loss=0.1318, simple_loss=0.2074, pruned_loss=0.02812, over 4753.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.0291, over 972707.62 frames.], batch size: 19, lr: 1.38e-04
2022-05-08 18:34:54,670 INFO [train.py:715] (4/8) Epoch 16, batch 20150, loss[loss=0.1478, simple_loss=0.2117, pruned_loss=0.04194, over 4777.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02906, over 972614.33 frames.], batch size: 12, lr: 1.38e-04
2022-05-08 18:35:32,575 INFO [train.py:715] (4/8) Epoch 16, batch 20200, loss[loss=0.1487, simple_loss=0.2326, pruned_loss=0.0324, over 4984.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02952, over 972403.69 frames.], batch size: 28, lr: 1.38e-04
2022-05-08 18:36:10,895 INFO [train.py:715] (4/8) Epoch 16, batch 20250, loss[loss=0.1256, simple_loss=0.1974, pruned_loss=0.0269, over 4986.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02929, over 973036.71 frames.], batch size: 28, lr: 1.38e-04
2022-05-08 18:36:49,190 INFO [train.py:715] (4/8) Epoch 16, batch 20300, loss[loss=0.1042, simple_loss=0.1839, pruned_loss=0.01228, over 4799.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02931, over 972528.07 frames.], batch size: 18, lr: 1.38e-04
2022-05-08 18:37:27,016 INFO [train.py:715] (4/8) Epoch 16, batch 20350, loss[loss=0.1511, simple_loss=0.2041, pruned_loss=0.04905, over 4647.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02944, over 971746.05 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 18:38:05,174 INFO [train.py:715] (4/8) Epoch 16, batch 20400, loss[loss=0.1825, simple_loss=0.2609, pruned_loss=0.05207, over 4758.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02914, over 972038.23 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 18:38:43,166 INFO [train.py:715] (4/8) Epoch 16, batch 20450, loss[loss=0.1374, simple_loss=0.205, pruned_loss=0.03491, over 4792.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02932, over 971890.15 frames.], batch size: 12, lr: 1.37e-04
2022-05-08 18:39:21,070 INFO [train.py:715] (4/8) Epoch 16, batch 20500, loss[loss=0.1379, simple_loss=0.2138, pruned_loss=0.03095, over 4959.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02976, over 972598.25 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 18:39:58,716 INFO [train.py:715] (4/8) Epoch 16, batch 20550, loss[loss=0.1206, simple_loss=0.1912, pruned_loss=0.02499, over 4755.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02973, over 971943.57 frames.], batch size: 12, lr: 1.37e-04
2022-05-08 18:40:37,507 INFO [train.py:715] (4/8) Epoch 16, batch 20600, loss[loss=0.1373, simple_loss=0.2176, pruned_loss=0.02848, over 4845.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02987, over 971296.08 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 18:41:15,473 INFO [train.py:715] (4/8) Epoch 16, batch 20650, loss[loss=0.1513, simple_loss=0.223, pruned_loss=0.03979, over 4853.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.0293, over 971482.33 frames.], batch size: 38, lr: 1.37e-04
2022-05-08 18:41:52,932 INFO [train.py:715] (4/8) Epoch 16, batch 20700, loss[loss=0.1432, simple_loss=0.2094, pruned_loss=0.0385, over 4849.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.0294, over 972268.04 frames.], batch size: 30, lr: 1.37e-04
2022-05-08 18:42:31,438 INFO [train.py:715] (4/8) Epoch 16, batch 20750, loss[loss=0.1495, simple_loss=0.2229, pruned_loss=0.03811, over 4772.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02971, over 971802.95 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 18:43:09,456 INFO [train.py:715] (4/8) Epoch 16, batch 20800, loss[loss=0.1366, simple_loss=0.2122, pruned_loss=0.03048, over 4779.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02948, over 972548.95 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 18:43:47,988 INFO [train.py:715] (4/8) Epoch 16, batch 20850, loss[loss=0.1433, simple_loss=0.2094, pruned_loss=0.03855, over 4788.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02937, over 972489.33 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 18:44:25,953 INFO [train.py:715] (4/8) Epoch 16, batch 20900, loss[loss=0.1218, simple_loss=0.2067, pruned_loss=0.01847, over 4973.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02908, over 972854.51 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 18:45:05,223 INFO [train.py:715] (4/8) Epoch 16, batch 20950, loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.0297, over 4982.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02945, over 973592.55 frames.], batch size: 24, lr: 1.37e-04
2022-05-08 18:45:43,429 INFO [train.py:715] (4/8) Epoch 16, batch 21000, loss[loss=0.121, simple_loss=0.199, pruned_loss=0.02151, over 4960.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02941, over 973068.42 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 18:45:43,430 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 18:45:53,027 INFO [train.py:742] (4/8) Epoch 16, validation: loss=0.1047, simple_loss=0.1882, pruned_loss=0.0106, over 914524.00 frames.
2022-05-08 18:46:31,911 INFO [train.py:715] (4/8) Epoch 16, batch 21050, loss[loss=0.1191, simple_loss=0.197, pruned_loss=0.02063, over 4976.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02982, over 973636.48 frames.], batch size: 31, lr: 1.37e-04
2022-05-08 18:47:10,476 INFO [train.py:715] (4/8) Epoch 16, batch 21100, loss[loss=0.1094, simple_loss=0.1843, pruned_loss=0.01724, over 4804.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02918, over 972946.99 frames.], batch size: 12, lr: 1.37e-04
2022-05-08 18:47:49,069 INFO [train.py:715] (4/8) Epoch 16, batch 21150, loss[loss=0.1134, simple_loss=0.1773, pruned_loss=0.02476, over 4772.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02893, over 972185.15 frames.], batch size: 12, lr: 1.37e-04
2022-05-08 18:48:27,789 INFO [train.py:715] (4/8) Epoch 16, batch 21200, loss[loss=0.1146, simple_loss=0.1953, pruned_loss=0.01693, over 4897.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2076, pruned_loss=0.0289, over 972051.83 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 18:49:06,847 INFO [train.py:715] (4/8) Epoch 16, batch 21250, loss[loss=0.1803, simple_loss=0.2476, pruned_loss=0.05657, over 4786.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02934, over 972274.73 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 18:49:44,919 INFO [train.py:715] (4/8) Epoch 16, batch 21300, loss[loss=0.1322, simple_loss=0.2095, pruned_loss=0.02742, over 4994.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.0293, over 972992.26 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 18:50:23,521 INFO [train.py:715] (4/8) Epoch 16, batch 21350, loss[loss=0.1381, simple_loss=0.2003, pruned_loss=0.03793, over 4695.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02941, over 972427.99 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 18:51:01,535 INFO [train.py:715] (4/8) Epoch 16, batch 21400, loss[loss=0.1246, simple_loss=0.202, pruned_loss=0.02363, over 4972.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02909, over 973779.99 frames.], batch size: 28, lr: 1.37e-04
2022-05-08 18:51:39,054 INFO [train.py:715] (4/8) Epoch 16, batch 21450, loss[loss=0.1367, simple_loss=0.2159, pruned_loss=0.02874, over 4767.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2084, pruned_loss=0.02963, over 973803.31 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 18:52:17,448 INFO [train.py:715] (4/8) Epoch 16, batch 21500, loss[loss=0.1652, simple_loss=0.2309, pruned_loss=0.04969, over 4978.00 frames.], tot_loss[loss=0.1335, simple_loss=0.208, pruned_loss=0.02953, over 973567.36 frames.], batch size: 40, lr: 1.37e-04
2022-05-08 18:52:55,411 INFO [train.py:715] (4/8) Epoch 16, batch 21550, loss[loss=0.1358, simple_loss=0.2113, pruned_loss=0.03018, over 4924.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02924, over 974087.44 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 18:53:33,002 INFO [train.py:715] (4/8) Epoch 16, batch 21600, loss[loss=0.1215, simple_loss=0.1983, pruned_loss=0.02237, over 4793.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02946, over 973684.13 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 18:54:11,335 INFO [train.py:715] (4/8) Epoch 16, batch 21650, loss[loss=0.126, simple_loss=0.1952, pruned_loss=0.02838, over 4779.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02902, over 972849.78 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 18:54:49,120 INFO [train.py:715] (4/8) Epoch 16, batch 21700, loss[loss=0.1486, simple_loss=0.2072, pruned_loss=0.04505, over 4962.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02939, over 972921.45 frames.], batch size: 35, lr: 1.37e-04
2022-05-08 18:55:27,324 INFO [train.py:715] (4/8) Epoch 16, batch 21750, loss[loss=0.1227, simple_loss=0.2037, pruned_loss=0.02082, over 4862.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02958, over 973735.56 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 18:56:04,817 INFO [train.py:715] (4/8) Epoch 16, batch 21800, loss[loss=0.1329, simple_loss=0.2052, pruned_loss=0.03027, over 4782.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02953, over 972978.77 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 18:56:42,920 INFO [train.py:715] (4/8) Epoch 16, batch 21850, loss[loss=0.1236, simple_loss=0.2002, pruned_loss=0.02352, over 4858.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02967, over 974108.84 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 18:57:20,562 INFO [train.py:715] (4/8) Epoch 16, batch 21900, loss[loss=0.1411, simple_loss=0.1993, pruned_loss=0.04146, over 4873.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02985, over 973378.92 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 18:57:57,978 INFO [train.py:715] (4/8) Epoch 16, batch 21950, loss[loss=0.1305, simple_loss=0.2032, pruned_loss=0.0289, over 4867.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02971, over 973256.04 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 18:58:36,385 INFO [train.py:715] (4/8) Epoch 16, batch 22000, loss[loss=0.13, simple_loss=0.2016, pruned_loss=0.02922, over 4846.00 frames.], tot_loss[loss=0.133, simple_loss=0.2066, pruned_loss=0.02969, over 972880.66 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 18:59:13,998 INFO [train.py:715] (4/8) Epoch 16, batch 22050, loss[loss=0.1279, simple_loss=0.1889, pruned_loss=0.0335, over 4866.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.0299, over 972541.79 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 18:59:52,237 INFO [train.py:715] (4/8) Epoch 16, batch 22100, loss[loss=0.1303, simple_loss=0.2071, pruned_loss=0.02677, over 4979.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.03014, over 971903.29 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:00:29,950 INFO [train.py:715] (4/8) Epoch 16, batch 22150, loss[loss=0.121, simple_loss=0.2077, pruned_loss=0.01712, over 4840.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02965, over 972666.28 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 19:01:08,386 INFO [train.py:715] (4/8) Epoch 16, batch 22200, loss[loss=0.1497, simple_loss=0.2184, pruned_loss=0.04054, over 4689.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02954, over 972984.60 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:01:46,150 INFO [train.py:715] (4/8) Epoch 16, batch 22250, loss[loss=0.1211, simple_loss=0.1927, pruned_loss=0.02472, over 4766.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02961, over 972793.77 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:02:24,236 INFO [train.py:715] (4/8) Epoch 16, batch 22300, loss[loss=0.1311, simple_loss=0.2037, pruned_loss=0.02921, over 4840.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2085, pruned_loss=0.02982, over 972813.55 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 19:03:02,795 INFO [train.py:715] (4/8) Epoch 16, batch 22350, loss[loss=0.1202, simple_loss=0.199, pruned_loss=0.02063, over 4803.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02957, over 972211.68 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 19:03:40,842 INFO [train.py:715] (4/8) Epoch 16, batch 22400, loss[loss=0.1099, simple_loss=0.1877, pruned_loss=0.01602, over 4860.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02979, over 972383.15 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 19:04:19,200 INFO [train.py:715] (4/8) Epoch 16, batch 22450, loss[loss=0.1358, simple_loss=0.2083, pruned_loss=0.03169, over 4795.00 frames.], tot_loss[loss=0.1334, simple_loss=0.208, pruned_loss=0.02945, over 971946.86 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 19:04:57,326 INFO [train.py:715] (4/8) Epoch 16, batch 22500, loss[loss=0.1219, simple_loss=0.192, pruned_loss=0.02593, over 4782.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02889, over 971627.97 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 19:05:35,512 INFO [train.py:715] (4/8) Epoch 16, batch 22550, loss[loss=0.1268, simple_loss=0.21, pruned_loss=0.0218, over 4875.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02915, over 971919.09 frames.], batch size: 22, lr: 1.37e-04
2022-05-08 19:06:13,251 INFO [train.py:715] (4/8) Epoch 16, batch 22600, loss[loss=0.1135, simple_loss=0.1854, pruned_loss=0.02077, over 4778.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02935, over 971709.02 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 19:06:50,940 INFO [train.py:715] (4/8) Epoch 16, batch 22650, loss[loss=0.1364, simple_loss=0.2113, pruned_loss=0.03074, over 4924.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02959, over 971429.55 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 19:07:29,634 INFO [train.py:715] (4/8) Epoch 16, batch 22700, loss[loss=0.1377, simple_loss=0.2167, pruned_loss=0.02937, over 4965.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02991, over 972358.11 frames.], batch size: 28, lr: 1.37e-04
2022-05-08 19:08:07,678 INFO [train.py:715] (4/8) Epoch 16, batch 22750, loss[loss=0.154, simple_loss=0.2078, pruned_loss=0.05014, over 4850.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02975, over 972095.79 frames.], batch size: 30, lr: 1.37e-04
2022-05-08 19:08:45,789 INFO [train.py:715] (4/8) Epoch 16, batch 22800, loss[loss=0.1358, simple_loss=0.2145, pruned_loss=0.02858, over 4801.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2086, pruned_loss=0.03026, over 971970.45 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 19:09:23,700 INFO [train.py:715] (4/8) Epoch 16, batch 22850, loss[loss=0.1197, simple_loss=0.1904, pruned_loss=0.02445, over 4986.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03027, over 972735.30 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 19:10:01,847 INFO [train.py:715] (4/8) Epoch 16, batch 22900, loss[loss=0.1431, simple_loss=0.2148, pruned_loss=0.03563, over 4859.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02985, over 972262.44 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 19:10:39,882 INFO [train.py:715] (4/8) Epoch 16, batch 22950, loss[loss=0.1373, simple_loss=0.1969, pruned_loss=0.03881, over 4892.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02959, over 973142.52 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 19:11:17,829 INFO [train.py:715] (4/8) Epoch 16, batch 23000, loss[loss=0.1622, simple_loss=0.2297, pruned_loss=0.04737, over 4962.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02932, over 972633.73 frames.], batch size: 35, lr: 1.37e-04
2022-05-08 19:11:56,366 INFO [train.py:715] (4/8) Epoch 16, batch 23050, loss[loss=0.1217, simple_loss=0.1919, pruned_loss=0.0257, over 4780.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02924, over 972254.32 frames.], batch size: 12, lr: 1.37e-04
2022-05-08 19:12:34,515 INFO [train.py:715] (4/8) Epoch 16, batch 23100, loss[loss=0.1302, simple_loss=0.2003, pruned_loss=0.03002, over 4826.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02916, over 972453.18 frames.], batch size: 26, lr: 1.37e-04
2022-05-08 19:13:12,450 INFO [train.py:715] (4/8) Epoch 16, batch 23150, loss[loss=0.1646, simple_loss=0.2396, pruned_loss=0.04478, over 4841.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.03004, over 972298.14 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:13:50,195 INFO [train.py:715] (4/8) Epoch 16, batch 23200, loss[loss=0.1209, simple_loss=0.1921, pruned_loss=0.02492, over 4782.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02975, over 972175.20 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 19:14:28,510 INFO [train.py:715] (4/8) Epoch 16, batch 23250, loss[loss=0.1176, simple_loss=0.1884, pruned_loss=0.02345, over 4890.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.0298, over 972078.29 frames.], batch size: 22, lr: 1.37e-04
2022-05-08 19:15:06,176 INFO [train.py:715] (4/8) Epoch 16, batch 23300, loss[loss=0.1587, simple_loss=0.2315, pruned_loss=0.04296, over 4747.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02974, over 971431.89 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 19:15:44,248 INFO [train.py:715] (4/8) Epoch 16, batch 23350, loss[loss=0.1374, simple_loss=0.2045, pruned_loss=0.03518, over 4823.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02987, over 972132.37 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 19:16:21,895 INFO [train.py:715] (4/8) Epoch 16, batch 23400, loss[loss=0.1413, simple_loss=0.2141, pruned_loss=0.03424, over 4769.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02964, over 971223.49 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 19:16:59,784 INFO [train.py:715] (4/8) Epoch 16, batch 23450, loss[loss=0.1136, simple_loss=0.182, pruned_loss=0.02256, over 4920.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02937, over 971212.83 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 19:17:37,689 INFO [train.py:715] (4/8) Epoch 16, batch 23500, loss[loss=0.1472, simple_loss=0.2116, pruned_loss=0.0414, over 4954.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.02947, over 971283.08 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 19:18:15,673 INFO [train.py:715] (4/8) Epoch 16, batch 23550, loss[loss=0.1492, simple_loss=0.2197, pruned_loss=0.03935, over 4911.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2074, pruned_loss=0.03007, over 971701.53 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:18:54,223 INFO [train.py:715] (4/8) Epoch 16, batch 23600, loss[loss=0.115, simple_loss=0.1911, pruned_loss=0.0194, over 4911.00 frames.], tot_loss[loss=0.1333, simple_loss=0.207, pruned_loss=0.02974, over 971863.29 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 19:19:31,589 INFO [train.py:715] (4/8) Epoch 16, batch 23650, loss[loss=0.1164, simple_loss=0.1956, pruned_loss=0.01861, over 4870.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02937, over 970878.43 frames.], batch size: 34, lr: 1.37e-04
2022-05-08 19:20:09,501 INFO [train.py:715] (4/8) Epoch 16, batch 23700, loss[loss=0.11, simple_loss=0.1853, pruned_loss=0.01737, over 4986.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.029, over 970848.30 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 19:20:47,876 INFO [train.py:715] (4/8) Epoch 16, batch 23750, loss[loss=0.1292, simple_loss=0.2006, pruned_loss=0.02894, over 4858.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2056, pruned_loss=0.0289, over 971234.38 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 19:21:25,949 INFO [train.py:715] (4/8) Epoch 16, batch 23800, loss[loss=0.1399, simple_loss=0.2145, pruned_loss=0.03262, over 4858.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.029, over 971499.79 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 19:22:04,221 INFO [train.py:715] (4/8) Epoch 16, batch 23850, loss[loss=0.1151, simple_loss=0.1999, pruned_loss=0.01517, over 4755.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02881, over 971723.19 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:22:42,141 INFO [train.py:715] (4/8) Epoch 16, batch 23900, loss[loss=0.1229, simple_loss=0.2032, pruned_loss=0.02134, over 4863.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02925, over 972817.05 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 19:23:20,418 INFO [train.py:715] (4/8) Epoch 16, batch 23950, loss[loss=0.1358, simple_loss=0.2085, pruned_loss=0.03158, over 4877.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02925, over 971990.99 frames.], batch size: 22, lr: 1.37e-04
2022-05-08 19:23:57,816 INFO [train.py:715] (4/8) Epoch 16, batch 24000, loss[loss=0.1252, simple_loss=0.2029, pruned_loss=0.02377, over 4826.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02923, over 971250.57 frames.], batch size: 26, lr: 1.37e-04
2022-05-08 19:23:57,817 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 19:24:07,634 INFO [train.py:742] (4/8) Epoch 16, validation: loss=0.1049, simple_loss=0.1883, pruned_loss=0.01074, over 914524.00 frames.
2022-05-08 19:24:46,402 INFO [train.py:715] (4/8) Epoch 16, batch 24050, loss[loss=0.1676, simple_loss=0.2424, pruned_loss=0.04641, over 4706.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02871, over 971336.65 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:25:24,729 INFO [train.py:715] (4/8) Epoch 16, batch 24100, loss[loss=0.1212, simple_loss=0.1845, pruned_loss=0.02892, over 4925.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02916, over 971858.88 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 19:26:03,113 INFO [train.py:715] (4/8) Epoch 16, batch 24150, loss[loss=0.1159, simple_loss=0.1835, pruned_loss=0.0241, over 4694.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02909, over 971368.37 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:26:40,869 INFO [train.py:715] (4/8) Epoch 16, batch 24200, loss[loss=0.1167, simple_loss=0.19, pruned_loss=0.02167, over 4896.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02918, over 972115.99 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:27:19,228 INFO [train.py:715] (4/8) Epoch 16, batch 24250, loss[loss=0.1186, simple_loss=0.1945, pruned_loss=0.0213, over 4933.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02971, over 971989.47 frames.], batch size: 29, lr: 1.37e-04
2022-05-08 19:27:57,172 INFO [train.py:715] (4/8) Epoch 16, batch 24300, loss[loss=0.1096, simple_loss=0.1885, pruned_loss=0.01535, over 4988.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02978, over 971455.88 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 19:28:35,670 INFO [train.py:715] (4/8) Epoch 16, batch 24350, loss[loss=0.1269, simple_loss=0.2119, pruned_loss=0.02092, over 4908.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02963, over 971440.21 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 19:29:13,223 INFO [train.py:715] (4/8) Epoch 16, batch 24400, loss[loss=0.1285, simple_loss=0.2047, pruned_loss=0.02616, over 4985.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2075, pruned_loss=0.02899, over 971721.20 frames.], batch size: 24, lr: 1.37e-04
2022-05-08 19:29:50,782 INFO [train.py:715] (4/8) Epoch 16, batch 24450, loss[loss=0.1361, simple_loss=0.2106, pruned_loss=0.03081, over 4876.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02903, over 971462.73 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 19:30:28,697 INFO [train.py:715] (4/8) Epoch 16, batch 24500, loss[loss=0.1314, simple_loss=0.2076, pruned_loss=0.02762, over 4778.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2079, pruned_loss=0.02924, over 971696.72 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 19:31:06,548 INFO [train.py:715] (4/8) Epoch 16, batch 24550, loss[loss=0.1219, simple_loss=0.1948, pruned_loss=0.02444, over 4691.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2082, pruned_loss=0.02947, over 971446.37 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:31:43,992 INFO [train.py:715] (4/8) Epoch 16, batch 24600, loss[loss=0.1538, simple_loss=0.2186, pruned_loss=0.04449, over 4891.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2091, pruned_loss=0.03002, over 971231.51 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:32:21,347 INFO [train.py:715] (4/8) Epoch 16, batch 24650, loss[loss=0.1593, simple_loss=0.229, pruned_loss=0.04474, over 4761.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.0296, over 971928.36 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 19:32:59,494 INFO [train.py:715] (4/8) Epoch 16, batch 24700, loss[loss=0.166, simple_loss=0.2334, pruned_loss=0.04932, over 4871.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2089, pruned_loss=0.03031, over 972605.07 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 19:33:37,066 INFO [train.py:715] (4/8) Epoch 16, batch 24750, loss[loss=0.117, simple_loss=0.1884, pruned_loss=0.02281, over 4852.00 frames.], tot_loss[loss=0.134, simple_loss=0.2076, pruned_loss=0.03019, over 971678.90 frames.], batch size: 30, lr: 1.37e-04
2022-05-08 19:34:14,865 INFO [train.py:715] (4/8) Epoch 16, batch 24800, loss[loss=0.1352, simple_loss=0.1961, pruned_loss=0.03713, over 4780.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02969, over 971930.03 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 19:34:52,611 INFO [train.py:715] (4/8) Epoch 16, batch 24850, loss[loss=0.1174, simple_loss=0.1898, pruned_loss=0.02251, over 4974.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2071, pruned_loss=0.02987, over 971551.03 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:35:30,367 INFO [train.py:715] (4/8) Epoch 16, batch 24900, loss[loss=0.1222, simple_loss=0.2016, pruned_loss=0.02138, over 4762.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02949, over 971413.09 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 19:36:08,066 INFO [train.py:715] (4/8) Epoch 16, batch 24950, loss[loss=0.1225, simple_loss=0.1879, pruned_loss=0.02856, over 4755.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2063, pruned_loss=0.02948, over 971960.90 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 19:36:45,484 INFO [train.py:715] (4/8) Epoch 16, batch 25000, loss[loss=0.109, simple_loss=0.1969, pruned_loss=0.01053, over 4963.00 frames.], tot_loss[loss=0.1323, simple_loss=0.206, pruned_loss=0.02931, over 972819.43 frames.], batch size: 24, lr: 1.37e-04
2022-05-08 19:37:23,736 INFO [train.py:715] (4/8) Epoch 16, batch 25050, loss[loss=0.1158, simple_loss=0.1881, pruned_loss=0.02176, over 4994.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02978, over 972417.83 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 19:38:02,500 INFO [train.py:715] (4/8) Epoch 16, batch 25100, loss[loss=0.1349, simple_loss=0.2142, pruned_loss=0.0278, over 4967.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02913, over 972473.05 frames.], batch size: 35, lr: 1.37e-04
2022-05-08 19:38:40,220 INFO [train.py:715] (4/8) Epoch 16, batch 25150, loss[loss=0.09593, simple_loss=0.1688, pruned_loss=0.01155, over 4823.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02913, over 972991.38 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 19:39:18,059 INFO [train.py:715] (4/8) Epoch 16, batch 25200, loss[loss=0.1381, simple_loss=0.2091, pruned_loss=0.03354, over 4877.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02919, over 972711.40 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 19:39:56,034 INFO [train.py:715] (4/8) Epoch 16, batch 25250, loss[loss=0.148, simple_loss=0.2233, pruned_loss=0.03634, over 4826.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02914, over 973653.98 frames.], batch size: 27, lr: 1.37e-04
2022-05-08 19:40:33,644 INFO [train.py:715] (4/8) Epoch 16, batch 25300, loss[loss=0.1207, simple_loss=0.1909, pruned_loss=0.02526, over 4910.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02895, over 973568.96 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:41:10,910 INFO [train.py:715] (4/8) Epoch 16, batch 25350, loss[loss=0.1416, simple_loss=0.2076, pruned_loss=0.03774, over 4982.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02929, over 973514.49 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:41:49,014 INFO [train.py:715] (4/8) Epoch 16, batch 25400, loss[loss=0.1388, simple_loss=0.222, pruned_loss=0.02782, over 4930.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02877, over 973643.01 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 19:42:27,347 INFO [train.py:715] (4/8) Epoch 16, batch 25450, loss[loss=0.138, simple_loss=0.2156, pruned_loss=0.03013, over 4973.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02869, over 972847.45 frames.], batch size: 35, lr: 1.37e-04
2022-05-08 19:43:04,843 INFO [train.py:715] (4/8) Epoch 16, batch 25500, loss[loss=0.147, simple_loss=0.2298, pruned_loss=0.03208, over 4757.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02929, over 973290.76 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:43:42,832 INFO [train.py:715] (4/8) Epoch 16, batch 25550, loss[loss=0.1366, simple_loss=0.2157, pruned_loss=0.02876, over 4842.00 frames.], tot_loss[loss=0.1333, simple_loss=0.208, pruned_loss=0.02933, over 972423.11 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:44:21,342 INFO [train.py:715] (4/8) Epoch 16, batch 25600, loss[loss=0.1163, simple_loss=0.1922, pruned_loss=0.02024, over 4908.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2081, pruned_loss=0.02947, over 972387.99 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 19:45:00,127 INFO [train.py:715] (4/8) Epoch 16, batch 25650, loss[loss=0.1203, simple_loss=0.2005, pruned_loss=0.02007, over 4776.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2085, pruned_loss=0.02941, over 972933.39 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 19:45:38,352 INFO [train.py:715] (4/8) Epoch 16, batch 25700, loss[loss=0.1118, simple_loss=0.1966, pruned_loss=0.01348, over 4974.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2081, pruned_loss=0.02919, over 972063.30 frames.], batch size: 24, lr: 1.37e-04
2022-05-08 19:46:16,989 INFO [train.py:715] (4/8) Epoch 16, batch 25750, loss[loss=0.1294, simple_loss=0.1977, pruned_loss=0.03058, over 4684.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2081, pruned_loss=0.02903, over 971909.35 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:46:55,624 INFO [train.py:715] (4/8) Epoch 16, batch 25800, loss[loss=0.1301, simple_loss=0.2074, pruned_loss=0.02641, over 4703.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2069, pruned_loss=0.0287, over 971703.59 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:47:34,229 INFO [train.py:715] (4/8) Epoch 16, batch 25850, loss[loss=0.1206, simple_loss=0.2079, pruned_loss=0.01665, over 4803.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2075, pruned_loss=0.02894, over 971119.09 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 19:48:13,044 INFO [train.py:715] (4/8) Epoch 16, batch 25900, loss[loss=0.1399, simple_loss=0.2216, pruned_loss=0.02909, over 4887.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2081, pruned_loss=0.02949, over 972073.83 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:48:52,465 INFO [train.py:715] (4/8) Epoch 16, batch 25950, loss[loss=0.1383, simple_loss=0.222, pruned_loss=0.02733, over 4890.00 frames.], tot_loss[loss=0.1331, simple_loss=0.208, pruned_loss=0.02907, over 972151.63 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:49:32,203 INFO [train.py:715] (4/8) Epoch 16, batch 26000, loss[loss=0.1217, simple_loss=0.1992, pruned_loss=0.02204, over 4838.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2075, pruned_loss=0.02897, over 972147.04 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 19:50:11,555 INFO [train.py:715] (4/8) Epoch 16, batch 26050, loss[loss=0.1244, simple_loss=0.1933, pruned_loss=0.02772, over 4875.00 frames.], tot_loss[loss=0.133, simple_loss=0.2078, pruned_loss=0.02906, over 972009.58 frames.], batch size: 22, lr: 1.37e-04
2022-05-08 19:50:50,794 INFO [train.py:715] (4/8) Epoch 16, batch 26100, loss[loss=0.1254, simple_loss=0.2004, pruned_loss=0.02523, over 4696.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02883, over 971916.82 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:51:30,060 INFO [train.py:715] (4/8) Epoch 16, batch 26150, loss[loss=0.1302, simple_loss=0.1977, pruned_loss=0.03139, over 4824.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02904, over 972402.30 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:52:08,696 INFO [train.py:715] (4/8) Epoch 16, batch 26200, loss[loss=0.1436, simple_loss=0.2147, pruned_loss=0.03622, over 4932.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02921, over 972089.58 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 19:52:48,173 INFO [train.py:715] (4/8) Epoch 16, batch 26250, loss[loss=0.1075, simple_loss=0.1772, pruned_loss=0.01884, over 4750.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02971, over 972246.48 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 19:53:27,328 INFO [train.py:715] (4/8) Epoch 16, batch 26300, loss[loss=0.1337, simple_loss=0.1998, pruned_loss=0.03378, over 4841.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2094, pruned_loss=0.03012, over 971420.58 frames.], batch size: 30, lr: 1.37e-04
2022-05-08 19:54:06,984 INFO [train.py:715] (4/8) Epoch 16, batch 26350, loss[loss=0.1464, simple_loss=0.216, pruned_loss=0.03842, over 4870.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02978, over 971815.65 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 19:54:46,282 INFO [train.py:715] (4/8) Epoch 16, batch 26400, loss[loss=0.1527, simple_loss=0.2206, pruned_loss=0.04235, over 4798.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2091, pruned_loss=0.03, over 972092.83 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 19:55:26,164 INFO [train.py:715] (4/8) Epoch 16, batch 26450, loss[loss=0.1313, simple_loss=0.1987, pruned_loss=0.03197, over 4916.00 frames.], tot_loss[loss=0.134, simple_loss=0.2089, pruned_loss=0.02959, over 972209.41 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 19:56:05,124 INFO [train.py:715] (4/8) Epoch 16, batch 26500, loss[loss=0.1527, simple_loss=0.2275, pruned_loss=0.03893, over 4961.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.0297, over 972970.89 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 19:56:44,030 INFO [train.py:715] (4/8) Epoch 16, batch 26550, loss[loss=0.1226, simple_loss=0.1998, pruned_loss=0.02269, over 4830.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.02999, over 972616.69 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 19:57:23,102 INFO [train.py:715] (4/8) Epoch 16, batch 26600, loss[loss=0.1123, simple_loss=0.1852, pruned_loss=0.01972, over 4803.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02964, over 972004.78 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 19:58:02,094 INFO [train.py:715] (4/8) Epoch 16, batch 26650, loss[loss=0.161, simple_loss=0.2427, pruned_loss=0.03959, over 4707.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2086, pruned_loss=0.0299, over 972236.36 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 19:58:41,425 INFO [train.py:715] (4/8) Epoch 16, batch 26700, loss[loss=0.1352, simple_loss=0.2052, pruned_loss=0.03257, over 4982.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.0298, over 972473.86 frames.], batch size: 28, lr: 1.37e-04
2022-05-08 19:59:20,660 INFO [train.py:715] (4/8) Epoch 16, batch 26750, loss[loss=0.12, simple_loss=0.1953, pruned_loss=0.02237, over 4764.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02979, over 972713.80 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 20:00:00,472 INFO [train.py:715] (4/8) Epoch 16, batch 26800, loss[loss=0.1411, simple_loss=0.2143, pruned_loss=0.03395, over 4781.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2082, pruned_loss=0.02961, over 972111.04 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 20:00:39,342 INFO [train.py:715] (4/8) Epoch 16, batch 26850, loss[loss=0.1305, simple_loss=0.2061, pruned_loss=0.02746, over 4783.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02975, over 971512.17 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 20:01:18,830 INFO [train.py:715] (4/8) Epoch 16, batch 26900, loss[loss=0.1648, simple_loss=0.2253, pruned_loss=0.05218, over 4867.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02955, over 971620.53 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 20:01:58,324 INFO [train.py:715] (4/8) Epoch 16, batch 26950, loss[loss=0.1454, simple_loss=0.2236, pruned_loss=0.03358, over 4832.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02988, over 972579.87 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 20:02:37,505 INFO [train.py:715] (4/8) Epoch 16, batch 27000, loss[loss=0.1457, simple_loss=0.2265, pruned_loss=0.03249, over 4807.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2092, pruned_loss=0.03032, over 972259.37 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 20:02:37,506 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 20:02:47,198 INFO [train.py:742] (4/8) Epoch 16, validation: loss=0.1048, simple_loss=0.1883, pruned_loss=0.01067, over 914524.00 frames.
2022-05-08 20:03:26,298 INFO [train.py:715] (4/8) Epoch 16, batch 27050, loss[loss=0.1204, simple_loss=0.2005, pruned_loss=0.02015, over 4795.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03003, over 972326.23 frames.], batch size: 24, lr: 1.37e-04
2022-05-08 20:04:08,231 INFO [train.py:715] (4/8) Epoch 16, batch 27100, loss[loss=0.1163, simple_loss=0.193, pruned_loss=0.01976, over 4919.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02964, over 972803.11 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 20:04:47,171 INFO [train.py:715] (4/8) Epoch 16, batch 27150, loss[loss=0.1313, simple_loss=0.2077, pruned_loss=0.02749, over 4881.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02936, over 972786.43 frames.], batch size: 22, lr: 1.37e-04
2022-05-08 20:05:26,600 INFO [train.py:715] (4/8) Epoch 16, batch 27200, loss[loss=0.1222, simple_loss=0.1966, pruned_loss=0.02388, over 4985.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02928, over 972769.63 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 20:06:05,791 INFO [train.py:715] (4/8) Epoch 16, batch 27250, loss[loss=0.1358, simple_loss=0.2142, pruned_loss=0.02872, over 4845.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02929, over 972193.13 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 20:06:45,177 INFO [train.py:715] (4/8) Epoch 16, batch 27300, loss[loss=0.1431, simple_loss=0.2108, pruned_loss=0.03773, over 4919.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02926, over 972363.29 frames.], batch size: 23, lr: 1.37e-04
2022-05-08 20:07:24,244 INFO [train.py:715] (4/8) Epoch 16, batch 27350, loss[loss=0.1365, simple_loss=0.2094, pruned_loss=0.03178, over 4800.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02901, over 972191.93 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 20:08:03,612 INFO [train.py:715] (4/8) Epoch 16, batch 27400, loss[loss=0.1313, simple_loss=0.2067, pruned_loss=0.02799, over 4912.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02934, over 972072.59 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 20:08:42,899 INFO [train.py:715] (4/8) Epoch 16, batch 27450, loss[loss=0.1383, simple_loss=0.2167, pruned_loss=0.02992, over 4979.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02949, over 972443.52 frames.], batch size: 28, lr: 1.37e-04
2022-05-08 20:09:21,910 INFO [train.py:715] (4/8) Epoch 16, batch 27500, loss[loss=0.1572, simple_loss=0.2351, pruned_loss=0.03968, over 4963.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02933, over 973156.05 frames.], batch size: 24, lr: 1.37e-04
2022-05-08 20:10:01,271 INFO [train.py:715] (4/8) Epoch 16, batch 27550, loss[loss=0.1264, simple_loss=0.2028, pruned_loss=0.02497, over 4760.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02938, over 973158.69 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 20:10:41,118 INFO [train.py:715] (4/8) Epoch 16, batch 27600, loss[loss=0.1379, simple_loss=0.2085, pruned_loss=0.03365, over 4814.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02989, over 972281.05 frames.], batch size: 27, lr: 1.37e-04
2022-05-08 20:11:20,146 INFO [train.py:715] (4/8) Epoch 16, batch 27650, loss[loss=0.1325, simple_loss=0.2007, pruned_loss=0.03214, over 4701.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2076, pruned_loss=0.03009, over 971585.49 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 20:11:59,672 INFO [train.py:715] (4/8) Epoch 16, batch 27700, loss[loss=0.1353, simple_loss=0.204, pruned_loss=0.03326, over 4981.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02999, over 973296.62 frames.], batch size: 28, lr: 1.37e-04
2022-05-08 20:12:38,975 INFO [train.py:715] (4/8) Epoch 16, batch 27750, loss[loss=0.1251, simple_loss=0.2045, pruned_loss=0.02292, over 4874.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02961, over 973058.46 frames.], batch size: 20, lr: 1.37e-04
2022-05-08 20:13:18,199 INFO [train.py:715] (4/8) Epoch 16, batch 27800, loss[loss=0.1708, simple_loss=0.25, pruned_loss=0.04584, over 4975.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02933, over 972261.19 frames.], batch size: 39, lr: 1.37e-04
2022-05-08 20:13:57,555 INFO [train.py:715] (4/8) Epoch 16, batch 27850, loss[loss=0.1408, simple_loss=0.2249, pruned_loss=0.02832, over 4914.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02951, over 972360.12 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 20:14:36,985 INFO [train.py:715] (4/8) Epoch 16, batch 27900, loss[loss=0.1447, simple_loss=0.2065, pruned_loss=0.04142, over 4866.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02926, over 971821.73 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 20:15:16,663 INFO [train.py:715] (4/8) Epoch 16, batch 27950, loss[loss=0.113, simple_loss=0.1915, pruned_loss=0.01727, over 4918.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02953, over 971786.64 frames.], batch size: 18, lr: 1.37e-04
2022-05-08 20:15:55,975 INFO [train.py:715] (4/8) Epoch 16, batch 28000, loss[loss=0.1573, simple_loss=0.2279, pruned_loss=0.04331, over 4957.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02907, over 973108.87 frames.], batch size: 15, lr: 1.37e-04
2022-05-08 20:16:35,544 INFO [train.py:715] (4/8) Epoch 16, batch 28050, loss[loss=0.1603, simple_loss=0.2298, pruned_loss=0.04542, over 4899.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02954, over 972745.30 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 20:17:15,205 INFO [train.py:715] (4/8) Epoch 16, batch 28100, loss[loss=0.1404, simple_loss=0.2166, pruned_loss=0.03207, over 4872.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02962, over 972377.32 frames.], batch size: 30, lr: 1.37e-04
2022-05-08 20:17:54,189 INFO [train.py:715] (4/8) Epoch 16, batch 28150, loss[loss=0.1184, simple_loss=0.1989, pruned_loss=0.01898, over 4823.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02937, over 972499.56 frames.], batch size: 25, lr: 1.37e-04
2022-05-08 20:18:33,942 INFO [train.py:715] (4/8) Epoch 16, batch 28200, loss[loss=0.1329, simple_loss=0.2042, pruned_loss=0.03077, over 4781.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02912, over 972171.24 frames.], batch size: 14, lr: 1.37e-04
2022-05-08 20:19:13,272 INFO [train.py:715] (4/8) Epoch 16, batch 28250, loss[loss=0.1425, simple_loss=0.2109, pruned_loss=0.03707, over 4845.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02926, over 972176.79 frames.], batch size: 32, lr: 1.37e-04
2022-05-08 20:19:51,891 INFO [train.py:715] (4/8) Epoch 16, batch 28300, loss[loss=0.1234, simple_loss=0.1965, pruned_loss=0.02516, over 4763.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02916, over 971811.80 frames.], batch size: 16, lr: 1.37e-04
2022-05-08 20:20:31,620 INFO [train.py:715] (4/8) Epoch 16, batch 28350, loss[loss=0.1322, simple_loss=0.2127, pruned_loss=0.02581, over 4821.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02934, over 972091.24 frames.], batch size: 27, lr: 1.37e-04
2022-05-08 20:21:11,558 INFO [train.py:715] (4/8) Epoch 16, batch 28400, loss[loss=0.1057, simple_loss=0.1755, pruned_loss=0.01793, over 4748.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02944, over 971586.91 frames.], batch size: 19, lr: 1.37e-04
2022-05-08 20:21:51,019 INFO [train.py:715] (4/8) Epoch 16, batch 28450, loss[loss=0.09817, simple_loss=0.171, pruned_loss=0.01266, over 4797.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02892, over 971744.48 frames.], batch size: 12, lr: 1.37e-04
2022-05-08 20:22:29,722 INFO [train.py:715] (4/8) Epoch 16, batch 28500, loss[loss=0.1357, simple_loss=0.2068, pruned_loss=0.03229, over 4904.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.0293, over 971606.99 frames.], batch size: 39, lr: 1.37e-04
2022-05-08 20:23:09,887 INFO [train.py:715] (4/8) Epoch 16, batch 28550, loss[loss=0.1298, simple_loss=0.2035, pruned_loss=0.02803, over 4790.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02916, over 971283.92 frames.], batch size: 17, lr: 1.37e-04
2022-05-08 20:23:49,358 INFO [train.py:715] (4/8) Epoch 16, batch 28600, loss[loss=0.1072, simple_loss=0.1818, pruned_loss=0.01629, over 4802.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2077, pruned_loss=0.02897, over 971591.95 frames.], batch size: 21, lr: 1.37e-04
2022-05-08 20:24:28,945 INFO [train.py:715] (4/8) Epoch 16, batch 28650, loss[loss=0.129, simple_loss=0.2067, pruned_loss=0.0256, over 4935.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02915, over 971622.93 frames.], batch size: 35, lr: 1.37e-04
2022-05-08 20:25:08,098 INFO [train.py:715] (4/8) Epoch 16, batch 28700, loss[loss=0.1224, simple_loss=0.1986, pruned_loss=0.02314, over 4823.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2086, pruned_loss=0.02928, over 972318.74 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 20:25:47,663 INFO [train.py:715] (4/8) Epoch 16, batch 28750, loss[loss=0.1433, simple_loss=0.2075, pruned_loss=0.03954, over 4633.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02919, over 971015.39 frames.], batch size: 13, lr: 1.37e-04
2022-05-08 20:26:27,375 INFO [train.py:715] (4/8) Epoch 16, batch 28800, loss[loss=0.133, simple_loss=0.2113, pruned_loss=0.02733, over 4694.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02928, over 971948.40 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 20:27:06,537 INFO [train.py:715] (4/8) Epoch 16, batch 28850, loss[loss=0.1376, simple_loss=0.2178, pruned_loss=0.02873, over 4982.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02914, over 972371.58 frames.], batch size: 25, lr: 1.36e-04
2022-05-08 20:27:46,355 INFO [train.py:715] (4/8) Epoch 16, batch 28900, loss[loss=0.1292, simple_loss=0.193, pruned_loss=0.03268, over 4832.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02958, over 971509.40 frames.], batch size: 30, lr: 1.36e-04
2022-05-08 20:28:25,934 INFO [train.py:715] (4/8) Epoch 16, batch 28950, loss[loss=0.1326, simple_loss=0.2088, pruned_loss=0.02819, over 4922.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02913, over 972236.82 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 20:29:05,875 INFO [train.py:715] (4/8) Epoch 16, batch 29000, loss[loss=0.1526, simple_loss=0.2267, pruned_loss=0.03929, over 4788.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02929, over 971502.28 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 20:29:45,341 INFO [train.py:715] (4/8) Epoch 16, batch 29050, loss[loss=0.1178, simple_loss=0.1934, pruned_loss=0.02114, over 4832.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02998, over 971745.39 frames.], batch size: 26, lr: 1.36e-04
2022-05-08 20:30:25,176 INFO [train.py:715] (4/8) Epoch 16, batch 29100, loss[loss=0.1473, simple_loss=0.2269, pruned_loss=0.03387, over 4820.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03014, over 971445.49 frames.], batch size: 26, lr: 1.36e-04
2022-05-08 20:31:06,247 INFO [train.py:715] (4/8) Epoch 16, batch 29150, loss[loss=0.1451, simple_loss=0.229, pruned_loss=0.03059, over 4937.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.02999, over 972041.46 frames.], batch size: 23, lr: 1.36e-04
2022-05-08 20:31:46,268 INFO [train.py:715] (4/8) Epoch 16, batch 29200, loss[loss=0.1333, simple_loss=0.2101, pruned_loss=0.0282, over 4778.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2077, pruned_loss=0.03036, over 971888.77 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 20:32:27,437 INFO [train.py:715] (4/8) Epoch 16, batch 29250, loss[loss=0.1404, simple_loss=0.2174, pruned_loss=0.03175, over 4824.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2073, pruned_loss=0.0301, over 971983.44 frames.], batch size: 27, lr: 1.36e-04
2022-05-08 20:33:08,449 INFO [train.py:715] (4/8) Epoch 16, batch 29300, loss[loss=0.1309, simple_loss=0.2021, pruned_loss=0.02982, over 4767.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2073, pruned_loss=0.02982, over 972604.22 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 20:33:49,842 INFO [train.py:715] (4/8) Epoch 16, batch 29350, loss[loss=0.1267, simple_loss=0.1975, pruned_loss=0.02791, over 4985.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02957, over 972183.93 frames.], batch size: 28, lr: 1.36e-04
2022-05-08 20:34:30,967 INFO [train.py:715] (4/8) Epoch 16, batch 29400, loss[loss=0.1349, simple_loss=0.2144, pruned_loss=0.02772, over 4811.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02959, over 972257.78 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 20:35:12,720 INFO [train.py:715] (4/8) Epoch 16, batch 29450, loss[loss=0.1334, simple_loss=0.2122, pruned_loss=0.02734, over 4963.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02972, over 971958.05 frames.], batch size: 24, lr: 1.36e-04
2022-05-08 20:35:54,209 INFO [train.py:715] (4/8) Epoch 16, batch 29500, loss[loss=0.1364, simple_loss=0.2132, pruned_loss=0.02981, over 4866.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.0295, over 972246.22 frames.], batch size: 20, lr: 1.36e-04
2022-05-08 20:36:36,037 INFO [train.py:715] (4/8) Epoch 16, batch 29550, loss[loss=0.119, simple_loss=0.1978, pruned_loss=0.0201, over 4866.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2069, pruned_loss=0.02964, over 972362.15 frames.], batch size: 20, lr: 1.36e-04
2022-05-08 20:37:17,260 INFO [train.py:715] (4/8) Epoch 16, batch 29600, loss[loss=0.1572, simple_loss=0.2242, pruned_loss=0.04511, over 4939.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02966, over 973377.94 frames.], batch size: 39, lr: 1.36e-04
2022-05-08 20:37:59,050 INFO [train.py:715] (4/8) Epoch 16, batch 29650, loss[loss=0.1379, simple_loss=0.2042, pruned_loss=0.03584, over 4844.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.02954, over 972067.32 frames.], batch size: 30, lr: 1.36e-04
2022-05-08 20:38:40,541 INFO [train.py:715] (4/8) Epoch 16, batch 29700, loss[loss=0.1413, simple_loss=0.2179, pruned_loss=0.03233, over 4697.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02934, over 971835.01 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 20:39:21,788 INFO [train.py:715] (4/8) Epoch 16, batch 29750, loss[loss=0.1348, simple_loss=0.1952, pruned_loss=0.03719, over 4798.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02915, over 970613.44 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 20:40:02,904 INFO [train.py:715] (4/8) Epoch 16, batch 29800, loss[loss=0.1339, simple_loss=0.2112, pruned_loss=0.02828, over 4767.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02925, over 972234.13 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 20:40:44,775 INFO [train.py:715] (4/8) Epoch 16, batch 29850, loss[loss=0.1511, simple_loss=0.2178, pruned_loss=0.04217, over 4986.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02922, over 972964.81 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 20:41:26,321 INFO [train.py:715] (4/8) Epoch 16, batch 29900, loss[loss=0.122, simple_loss=0.1915, pruned_loss=0.02623, over 4693.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02932, over 973291.71 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 20:42:07,629 INFO [train.py:715] (4/8) Epoch 16, batch 29950, loss[loss=0.1668, simple_loss=0.2236, pruned_loss=0.05497, over 4883.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02943, over 973335.83 frames.], batch size: 38, lr: 1.36e-04
2022-05-08 20:42:50,231 INFO [train.py:715] (4/8) Epoch 16, batch 30000, loss[loss=0.1296, simple_loss=0.2052, pruned_loss=0.02705, over 4694.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02976, over 972804.99 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 20:42:50,232 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 20:43:01,792 INFO [train.py:742] (4/8) Epoch 16, validation: loss=0.1047, simple_loss=0.1883, pruned_loss=0.01058, over 914524.00 frames.
2022-05-08 20:43:44,298 INFO [train.py:715] (4/8) Epoch 16, batch 30050, loss[loss=0.1204, simple_loss=0.1927, pruned_loss=0.02408, over 4955.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03002, over 972546.21 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 20:44:26,137 INFO [train.py:715] (4/8) Epoch 16, batch 30100, loss[loss=0.1115, simple_loss=0.1835, pruned_loss=0.01978, over 4745.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2076, pruned_loss=0.03052, over 972592.65 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 20:45:06,935 INFO [train.py:715] (4/8) Epoch 16, batch 30150, loss[loss=0.1252, simple_loss=0.2071, pruned_loss=0.0217, over 4797.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2069, pruned_loss=0.03018, over 972242.96 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 20:45:48,623 INFO [train.py:715] (4/8) Epoch 16, batch 30200, loss[loss=0.1227, simple_loss=0.1936, pruned_loss=0.02589, over 4990.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2077, pruned_loss=0.0304, over 973508.14 frames.], batch size: 28, lr: 1.36e-04
2022-05-08 20:46:29,881 INFO [train.py:715] (4/8) Epoch 16, batch 30250, loss[loss=0.1143, simple_loss=0.1849, pruned_loss=0.0218, over 4789.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2074, pruned_loss=0.02993, over 973462.74 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 20:47:09,984 INFO [train.py:715] (4/8) Epoch 16, batch 30300, loss[loss=0.1183, simple_loss=0.1956, pruned_loss=0.02052, over 4984.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03012, over 973679.14 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 20:47:50,184 INFO [train.py:715] (4/8) Epoch 16, batch 30350, loss[loss=0.1248, simple_loss=0.198, pruned_loss=0.02583, over 4700.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2068, pruned_loss=0.02978, over 973730.57 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 20:48:30,611 INFO [train.py:715] (4/8) Epoch 16, batch 30400, loss[loss=0.1446, simple_loss=0.2259, pruned_loss=0.03163, over 4812.00 frames.], tot_loss[loss=0.133, simple_loss=0.2068, pruned_loss=0.02958, over 974603.87 frames.], batch size: 26, lr: 1.36e-04
2022-05-08 20:49:10,250 INFO [train.py:715] (4/8) Epoch 16, batch 30450, loss[loss=0.123, simple_loss=0.1936, pruned_loss=0.02614, over 4757.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.0297, over 974247.86 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 20:49:49,409 INFO [train.py:715] (4/8) Epoch 16, batch 30500, loss[loss=0.121, simple_loss=0.1959, pruned_loss=0.02304, over 4738.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02935, over 973776.29 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 20:50:29,336 INFO [train.py:715] (4/8) Epoch 16, batch 30550, loss[loss=0.1396, simple_loss=0.205, pruned_loss=0.03707, over 4905.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02961, over 974153.06 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 20:51:09,799 INFO [train.py:715] (4/8) Epoch 16, batch 30600, loss[loss=0.1396, simple_loss=0.2165, pruned_loss=0.03136, over 4934.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02951, over 972825.06 frames.], batch size: 35, lr: 1.36e-04
2022-05-08 20:51:49,045 INFO [train.py:715] (4/8) Epoch 16, batch 30650, loss[loss=0.1268, simple_loss=0.2064, pruned_loss=0.02364, over 4943.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02942, over 973346.75 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 20:52:28,793 INFO [train.py:715] (4/8) Epoch 16, batch 30700, loss[loss=0.1459, simple_loss=0.2187, pruned_loss=0.03649, over 4904.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02943, over 973487.15 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 20:53:10,034 INFO [train.py:715] (4/8) Epoch 16, batch 30750, loss[loss=0.1561, simple_loss=0.2305, pruned_loss=0.04083, over 4960.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02931, over 973995.76 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 20:53:49,620 INFO [train.py:715] (4/8) Epoch 16, batch 30800, loss[loss=0.1544, simple_loss=0.228, pruned_loss=0.04035, over 4984.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02935, over 973708.55 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 20:54:28,449 INFO [train.py:715] (4/8) Epoch 16, batch 30850, loss[loss=0.1159, simple_loss=0.1906, pruned_loss=0.02063, over 4830.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02931, over 973070.69 frames.], batch size: 26, lr: 1.36e-04
2022-05-08 20:55:08,446 INFO [train.py:715] (4/8) Epoch 16, batch 30900, loss[loss=0.2399, simple_loss=0.2995, pruned_loss=0.09016, over 4781.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02983, over 972147.19 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 20:55:47,875 INFO [train.py:715] (4/8) Epoch 16, batch 30950, loss[loss=0.09977, simple_loss=0.1686, pruned_loss=0.01549, over 4825.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2073, pruned_loss=0.02997, over 972114.04 frames.], batch size: 13, lr: 1.36e-04
2022-05-08 20:56:26,906 INFO [train.py:715] (4/8) Epoch 16, batch 31000, loss[loss=0.1592, simple_loss=0.2318, pruned_loss=0.04329, over 4916.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03021, over 971634.28 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 20:57:06,084 INFO [train.py:715] (4/8) Epoch 16, batch 31050, loss[loss=0.1131, simple_loss=0.1896, pruned_loss=0.01829, over 4988.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2082, pruned_loss=0.03038, over 971923.83 frames.], batch size: 28, lr: 1.36e-04
2022-05-08 20:57:45,838 INFO [train.py:715] (4/8) Epoch 16, batch 31100, loss[loss=0.1431, simple_loss=0.218, pruned_loss=0.03408, over 4905.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2082, pruned_loss=0.03026, over 972382.82 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 20:58:25,689 INFO [train.py:715] (4/8) Epoch 16, batch 31150, loss[loss=0.1364, simple_loss=0.2137, pruned_loss=0.0295, over 4763.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.02992, over 971610.34 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 20:59:04,395 INFO [train.py:715] (4/8) Epoch 16, batch 31200, loss[loss=0.1562, simple_loss=0.2328, pruned_loss=0.0398, over 4894.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03004, over 972321.88 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 20:59:44,069 INFO [train.py:715] (4/8) Epoch 16, batch 31250, loss[loss=0.1305, simple_loss=0.1907, pruned_loss=0.03516, over 4977.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.03021, over 972278.75 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:00:23,618 INFO [train.py:715] (4/8) Epoch 16, batch 31300, loss[loss=0.1336, simple_loss=0.2037, pruned_loss=0.03177, over 4827.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03, over 972021.87 frames.], batch size: 13, lr: 1.36e-04
2022-05-08 21:01:03,207 INFO [train.py:715] (4/8) Epoch 16, batch 31350, loss[loss=0.1261, simple_loss=0.1987, pruned_loss=0.02677, over 4963.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02972, over 972054.60 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 21:01:42,654 INFO [train.py:715] (4/8) Epoch 16, batch 31400, loss[loss=0.108, simple_loss=0.1817, pruned_loss=0.01716, over 4859.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02961, over 972517.25 frames.], batch size: 32, lr: 1.36e-04
2022-05-08 21:02:22,720 INFO [train.py:715] (4/8) Epoch 16, batch 31450, loss[loss=0.1559, simple_loss=0.2279, pruned_loss=0.04199, over 4941.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02952, over 973043.74 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 21:03:01,698 INFO [train.py:715] (4/8) Epoch 16, batch 31500, loss[loss=0.1401, simple_loss=0.1947, pruned_loss=0.04274, over 4856.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02946, over 973241.78 frames.], batch size: 13, lr: 1.36e-04
2022-05-08 21:03:40,541 INFO [train.py:715] (4/8) Epoch 16, batch 31550, loss[loss=0.1237, simple_loss=0.2042, pruned_loss=0.02154, over 4693.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2066, pruned_loss=0.02937, over 972574.72 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:04:19,807 INFO [train.py:715] (4/8) Epoch 16, batch 31600, loss[loss=0.142, simple_loss=0.2227, pruned_loss=0.0307, over 4916.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02926, over 972951.12 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 21:04:58,918 INFO [train.py:715] (4/8) Epoch 16, batch 31650, loss[loss=0.1465, simple_loss=0.2133, pruned_loss=0.03981, over 4929.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02975, over 973011.16 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 21:05:37,855 INFO [train.py:715] (4/8) Epoch 16, batch 31700, loss[loss=0.1178, simple_loss=0.1905, pruned_loss=0.0225, over 4933.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02974, over 973299.78 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:06:17,108 INFO [train.py:715] (4/8) Epoch 16, batch 31750, loss[loss=0.1364, simple_loss=0.2005, pruned_loss=0.03615, over 4733.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02957, over 973151.67 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 21:06:56,940 INFO [train.py:715] (4/8) Epoch 16, batch 31800, loss[loss=0.1331, simple_loss=0.2101, pruned_loss=0.02808, over 4872.00 frames.], tot_loss[loss=0.1335, simple_loss=0.208, pruned_loss=0.02951, over 973368.79 frames.], batch size: 22, lr: 1.36e-04
2022-05-08 21:07:36,869 INFO [train.py:715] (4/8) Epoch 16, batch 31850, loss[loss=0.1174, simple_loss=0.1982, pruned_loss=0.01826, over 4944.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02915, over 973585.50 frames.], batch size: 23, lr: 1.36e-04
2022-05-08 21:08:15,870 INFO [train.py:715] (4/8) Epoch 16, batch 31900, loss[loss=0.158, simple_loss=0.2285, pruned_loss=0.04381, over 4956.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.0292, over 973731.40 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:08:55,062 INFO [train.py:715] (4/8) Epoch 16, batch 31950, loss[loss=0.1617, simple_loss=0.2334, pruned_loss=0.04497, over 4807.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02923, over 972752.85 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 21:09:34,441 INFO [train.py:715] (4/8) Epoch 16, batch 32000, loss[loss=0.1436, simple_loss=0.2067, pruned_loss=0.04027, over 4779.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.0296, over 971831.99 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 21:10:13,547 INFO [train.py:715] (4/8) Epoch 16, batch 32050, loss[loss=0.1044, simple_loss=0.1758, pruned_loss=0.01653, over 4970.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02968, over 971361.88 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 21:10:53,098 INFO [train.py:715] (4/8) Epoch 16, batch 32100, loss[loss=0.1219, simple_loss=0.1997, pruned_loss=0.02208, over 4800.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.02998, over 972284.99 frames.], batch size: 24, lr: 1.36e-04
2022-05-08 21:11:32,625 INFO [train.py:715] (4/8) Epoch 16, batch 32150, loss[loss=0.1823, simple_loss=0.2475, pruned_loss=0.05855, over 4934.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02983, over 972319.28 frames.], batch size: 29, lr: 1.36e-04
2022-05-08 21:12:12,704 INFO [train.py:715] (4/8) Epoch 16, batch 32200, loss[loss=0.1431, simple_loss=0.2131, pruned_loss=0.03657, over 4977.00 frames.], tot_loss[loss=0.134, simple_loss=0.2078, pruned_loss=0.03011, over 971857.96 frames.], batch size: 28, lr: 1.36e-04
2022-05-08 21:12:51,831 INFO [train.py:715] (4/8) Epoch 16, batch 32250, loss[loss=0.1361, simple_loss=0.2252, pruned_loss=0.02348, over 4974.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02968, over 971248.31 frames.], batch size: 28, lr: 1.36e-04
2022-05-08 21:13:31,319 INFO [train.py:715] (4/8) Epoch 16, batch 32300, loss[loss=0.1288, simple_loss=0.2064, pruned_loss=0.0256, over 4696.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02935, over 971188.77 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:14:11,361 INFO [train.py:715] (4/8) Epoch 16, batch 32350, loss[loss=0.1074, simple_loss=0.1866, pruned_loss=0.01406, over 4814.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02923, over 971604.30 frames.], batch size: 26, lr: 1.36e-04
2022-05-08 21:14:50,975 INFO [train.py:715] (4/8) Epoch 16, batch 32400, loss[loss=0.1342, simple_loss=0.2194, pruned_loss=0.02451, over 4945.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02917, over 972537.49 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 21:15:29,999 INFO [train.py:715] (4/8) Epoch 16, batch 32450, loss[loss=0.1338, simple_loss=0.2048, pruned_loss=0.03137, over 4810.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2076, pruned_loss=0.02987, over 972144.53 frames.], batch size: 26, lr: 1.36e-04
2022-05-08 21:16:10,033 INFO [train.py:715] (4/8) Epoch 16, batch 32500, loss[loss=0.1411, simple_loss=0.2122, pruned_loss=0.03499, over 4987.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02983, over 972597.22 frames.], batch size: 35, lr: 1.36e-04
2022-05-08 21:16:49,322 INFO [train.py:715] (4/8) Epoch 16, batch 32550, loss[loss=0.1435, simple_loss=0.2153, pruned_loss=0.0359, over 4961.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2072, pruned_loss=0.02978, over 971530.04 frames.], batch size: 15, lr: 1.36e-04
2022-05-08 21:17:28,287 INFO [train.py:715] (4/8) Epoch 16, batch 32600, loss[loss=0.124, simple_loss=0.1961, pruned_loss=0.02596, over 4771.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02938, over 972440.25 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:18:07,200 INFO [train.py:715] (4/8) Epoch 16, batch 32650, loss[loss=0.1263, simple_loss=0.2105, pruned_loss=0.02103, over 4925.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02909, over 972439.14 frames.], batch size: 29, lr: 1.36e-04
2022-05-08 21:18:46,394 INFO [train.py:715] (4/8) Epoch 16, batch 32700, loss[loss=0.124, simple_loss=0.1987, pruned_loss=0.02464, over 4763.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02918, over 972454.21 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 21:19:25,741 INFO [train.py:715] (4/8) Epoch 16, batch 32750, loss[loss=0.1295, simple_loss=0.2002, pruned_loss=0.02933, over 4809.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02945, over 972871.51 frames.], batch size: 26, lr: 1.36e-04
2022-05-08 21:20:05,462 INFO [train.py:715] (4/8) Epoch 16, batch 32800, loss[loss=0.1511, simple_loss=0.2233, pruned_loss=0.0395, over 4871.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02957, over 973867.75 frames.], batch size: 22, lr: 1.36e-04
2022-05-08 21:20:44,826 INFO [train.py:715] (4/8) Epoch 16, batch 32850, loss[loss=0.1296, simple_loss=0.2114, pruned_loss=0.02396, over 4892.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02978, over 973006.01 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 21:21:24,451 INFO [train.py:715] (4/8) Epoch 16, batch 32900, loss[loss=0.1404, simple_loss=0.2118, pruned_loss=0.03445, over 4733.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.02988, over 973161.36 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 21:22:03,427 INFO [train.py:715] (4/8) Epoch 16, batch 32950, loss[loss=0.1122, simple_loss=0.1858, pruned_loss=0.01925, over 4785.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02973, over 973279.15 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 21:22:42,573 INFO [train.py:715] (4/8) Epoch 16, batch 33000, loss[loss=0.1612, simple_loss=0.2407, pruned_loss=0.0409, over 4990.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2088, pruned_loss=0.02981, over 973375.94 frames.], batch size: 26, lr: 1.36e-04
2022-05-08 21:22:42,574 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 21:22:55,769 INFO [train.py:742] (4/8) Epoch 16, validation: loss=0.105, simple_loss=0.1884, pruned_loss=0.01078, over 914524.00 frames.
2022-05-08 21:23:35,554 INFO [train.py:715] (4/8) Epoch 16, batch 33050, loss[loss=0.1285, simple_loss=0.1963, pruned_loss=0.03034, over 4903.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2091, pruned_loss=0.0299, over 973014.56 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 21:24:14,883 INFO [train.py:715] (4/8) Epoch 16, batch 33100, loss[loss=0.1322, simple_loss=0.2036, pruned_loss=0.03041, over 4980.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2095, pruned_loss=0.02984, over 972779.59 frames.], batch size: 33, lr: 1.36e-04
2022-05-08 21:24:54,241 INFO [train.py:715] (4/8) Epoch 16, batch 33150, loss[loss=0.1454, simple_loss=0.2073, pruned_loss=0.04174, over 4898.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2092, pruned_loss=0.02991, over 972917.89 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 21:25:34,100 INFO [train.py:715] (4/8) Epoch 16, batch 33200, loss[loss=0.1488, simple_loss=0.2287, pruned_loss=0.03448, over 4758.00 frames.], tot_loss[loss=0.1344, simple_loss=0.209, pruned_loss=0.02988, over 973178.80 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 21:26:13,848 INFO [train.py:715] (4/8) Epoch 16, batch 33250, loss[loss=0.138, simple_loss=0.2161, pruned_loss=0.02998, over 4865.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2087, pruned_loss=0.02986, over 973146.23 frames.], batch size: 20, lr: 1.36e-04
2022-05-08 21:26:53,436 INFO [train.py:715] (4/8) Epoch 16, batch 33300, loss[loss=0.1879, simple_loss=0.2612, pruned_loss=0.05733, over 4875.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02947, over 971967.44 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 21:27:32,749 INFO [train.py:715] (4/8) Epoch 16, batch 33350, loss[loss=0.1479, simple_loss=0.2155, pruned_loss=0.04013, over 4782.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02935, over 972320.36 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:28:12,218 INFO [train.py:715] (4/8) Epoch 16, batch 33400, loss[loss=0.1321, simple_loss=0.2083, pruned_loss=0.02796, over 4739.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02974, over 972060.48 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 21:28:51,453 INFO [train.py:715] (4/8) Epoch 16, batch 33450, loss[loss=0.1176, simple_loss=0.1975, pruned_loss=0.01887, over 4905.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2086, pruned_loss=0.03006, over 971290.60 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 21:29:30,507 INFO [train.py:715] (4/8) Epoch 16, batch 33500, loss[loss=0.09624, simple_loss=0.1718, pruned_loss=0.01035, over 4912.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02989, over 970838.30 frames.], batch size: 17, lr: 1.36e-04
2022-05-08 21:30:09,460 INFO [train.py:715] (4/8) Epoch 16, batch 33550, loss[loss=0.1334, simple_loss=0.2133, pruned_loss=0.0268, over 4755.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02964, over 971050.99 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 21:30:49,227 INFO [train.py:715] (4/8) Epoch 16, batch 33600, loss[loss=0.119, simple_loss=0.1897, pruned_loss=0.02411, over 4813.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02981, over 971697.41 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 21:31:28,203 INFO [train.py:715] (4/8) Epoch 16, batch 33650, loss[loss=0.1881, simple_loss=0.2523, pruned_loss=0.06192, over 4918.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2086, pruned_loss=0.02976, over 972005.05 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:32:07,847 INFO [train.py:715] (4/8) Epoch 16, batch 33700, loss[loss=0.1184, simple_loss=0.1989, pruned_loss=0.01891, over 4983.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2081, pruned_loss=0.02977, over 971919.72 frames.], batch size: 16, lr: 1.36e-04
2022-05-08 21:32:46,797 INFO [train.py:715] (4/8) Epoch 16, batch 33750, loss[loss=0.1078, simple_loss=0.1837, pruned_loss=0.01593, over 4946.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.03, over 971804.70 frames.], batch size: 23, lr: 1.36e-04
2022-05-08 21:33:25,787 INFO [train.py:715] (4/8) Epoch 16, batch 33800, loss[loss=0.09663, simple_loss=0.1669, pruned_loss=0.0132, over 4737.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02974, over 972005.45 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 21:34:05,042 INFO [train.py:715] (4/8) Epoch 16, batch 33850, loss[loss=0.1553, simple_loss=0.2463, pruned_loss=0.03216, over 4930.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02987, over 972488.35 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:34:44,268 INFO [train.py:715] (4/8) Epoch 16, batch 33900, loss[loss=0.1401, simple_loss=0.2191, pruned_loss=0.03057, over 4809.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02959, over 972844.94 frames.], batch size: 25, lr: 1.36e-04
2022-05-08 21:35:24,622 INFO [train.py:715] (4/8) Epoch 16, batch 33950, loss[loss=0.1414, simple_loss=0.2252, pruned_loss=0.02878, over 4856.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02932, over 972768.24 frames.], batch size: 32, lr: 1.36e-04
2022-05-08 21:36:03,119 INFO [train.py:715] (4/8) Epoch 16, batch 34000, loss[loss=0.1239, simple_loss=0.1966, pruned_loss=0.02562, over 4787.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02926, over 972822.45 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 21:36:43,151 INFO [train.py:715] (4/8) Epoch 16, batch 34050, loss[loss=0.1768, simple_loss=0.2415, pruned_loss=0.05607, over 4954.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02962, over 972442.13 frames.], batch size: 39, lr: 1.36e-04
2022-05-08 21:37:22,552 INFO [train.py:715] (4/8) Epoch 16, batch 34100, loss[loss=0.1476, simple_loss=0.2293, pruned_loss=0.033, over 4804.00 frames.], tot_loss[loss=0.134, simple_loss=0.2083, pruned_loss=0.02981, over 973051.36 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 21:38:01,718 INFO [train.py:715] (4/8) Epoch 16, batch 34150, loss[loss=0.1553, simple_loss=0.2319, pruned_loss=0.03937, over 4800.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.0298, over 972716.74 frames.], batch size: 21, lr: 1.36e-04
2022-05-08 21:38:41,100 INFO [train.py:715] (4/8) Epoch 16, batch 34200, loss[loss=0.134, simple_loss=0.2034, pruned_loss=0.0323, over 4929.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02956, over 972116.25 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:39:20,449 INFO [train.py:715] (4/8) Epoch 16, batch 34250, loss[loss=0.1765, simple_loss=0.2326, pruned_loss=0.06024, over 4973.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02985, over 972645.48 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 21:40:00,518 INFO [train.py:715] (4/8) Epoch 16, batch 34300, loss[loss=0.1226, simple_loss=0.1938, pruned_loss=0.02568, over 4800.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03028, over 972613.06 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:40:39,494 INFO [train.py:715] (4/8) Epoch 16, batch 34350, loss[loss=0.1299, simple_loss=0.2049, pruned_loss=0.02749, over 4944.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.02995, over 972802.91 frames.], batch size: 29, lr: 1.36e-04
2022-05-08 21:41:18,848 INFO [train.py:715] (4/8) Epoch 16, batch 34400, loss[loss=0.1506, simple_loss=0.2192, pruned_loss=0.04098, over 4894.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2084, pruned_loss=0.03036, over 972593.88 frames.], batch size: 19, lr: 1.36e-04
2022-05-08 21:41:58,449 INFO [train.py:715] (4/8) Epoch 16, batch 34450, loss[loss=0.1201, simple_loss=0.1998, pruned_loss=0.0202, over 4774.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02977, over 971887.77 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:42:37,730 INFO [train.py:715] (4/8) Epoch 16, batch 34500, loss[loss=0.1098, simple_loss=0.1801, pruned_loss=0.0198, over 4750.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02919, over 972430.18 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 21:43:17,125 INFO [train.py:715] (4/8) Epoch 16, batch 34550, loss[loss=0.1007, simple_loss=0.1718, pruned_loss=0.01486, over 4765.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02869, over 971386.39 frames.], batch size: 12, lr: 1.36e-04
2022-05-08 21:43:56,243 INFO [train.py:715] (4/8) Epoch 16, batch 34600, loss[loss=0.1592, simple_loss=0.22, pruned_loss=0.04913, over 4915.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.029, over 971608.34 frames.], batch size: 29, lr: 1.36e-04
2022-05-08 21:44:36,200 INFO [train.py:715] (4/8) Epoch 16, batch 34650, loss[loss=0.1408, simple_loss=0.2072, pruned_loss=0.03718, over 4920.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02902, over 971392.77 frames.], batch size: 18, lr: 1.36e-04
2022-05-08 21:45:15,691 INFO [train.py:715] (4/8) Epoch 16, batch 34700, loss[loss=0.1297, simple_loss=0.2002, pruned_loss=0.02962, over 4956.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02889, over 971497.32 frames.], batch size: 35, lr: 1.36e-04
2022-05-08 21:45:54,802 INFO [train.py:715] (4/8) Epoch 16, batch 34750, loss[loss=0.1196, simple_loss=0.192, pruned_loss=0.02365, over 4804.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02912, over 972246.01 frames.], batch size: 14, lr: 1.36e-04
2022-05-08 21:46:32,021 INFO [train.py:715] (4/8) Epoch 16, batch 34800, loss[loss=0.1461, simple_loss=0.219, pruned_loss=0.03659, over 4920.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2063, pruned_loss=0.02947, over 972014.59 frames.], batch size: 23, lr: 1.36e-04
2022-05-08 21:47:23,861 INFO [train.py:715] (4/8) Epoch 17, batch 0, loss[loss=0.1285, simple_loss=0.2068, pruned_loss=0.02512, over 4883.00 frames.], tot_loss[loss=0.1285, simple_loss=0.2068, pruned_loss=0.02512, over 4883.00 frames.], batch size: 22, lr: 1.32e-04
2022-05-08 21:48:03,324 INFO [train.py:715] (4/8) Epoch 17, batch 50, loss[loss=0.1411, simple_loss=0.2172, pruned_loss=0.0325, over 4988.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02802, over 219298.45 frames.], batch size: 14, lr: 1.32e-04
2022-05-08 21:48:44,378 INFO [train.py:715] (4/8) Epoch 17, batch 100, loss[loss=0.1335, simple_loss=0.2122, pruned_loss=0.02744, over 4865.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2046, pruned_loss=0.02829, over 387396.37 frames.], batch size: 30, lr: 1.32e-04
2022-05-08 21:49:25,324 INFO [train.py:715] (4/8) Epoch 17, batch 150, loss[loss=0.1307, simple_loss=0.1978, pruned_loss=0.03183, over 4694.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2046, pruned_loss=0.02831, over 517033.10 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 21:50:06,391 INFO [train.py:715] (4/8) Epoch 17, batch 200, loss[loss=0.1048, simple_loss=0.1801, pruned_loss=0.01471, over 4948.00 frames.], tot_loss[loss=0.1314, simple_loss=0.205, pruned_loss=0.02889, over 617843.29 frames.], batch size: 28, lr: 1.32e-04
2022-05-08 21:50:49,381 INFO [train.py:715] (4/8) Epoch 17, batch 250, loss[loss=0.1206, simple_loss=0.1936, pruned_loss=0.02379, over 4975.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2059, pruned_loss=0.02925, over 696406.65 frames.], batch size: 14, lr: 1.32e-04
2022-05-08 21:51:30,979 INFO [train.py:715] (4/8) Epoch 17, batch 300, loss[loss=0.1488, simple_loss=0.2263, pruned_loss=0.03562, over 4745.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02845, over 758223.98 frames.], batch size: 16, lr: 1.32e-04
2022-05-08 21:52:11,865 INFO [train.py:715] (4/8) Epoch 17, batch 350, loss[loss=0.1138, simple_loss=0.1887, pruned_loss=0.01941, over 4913.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2059, pruned_loss=0.0282, over 806015.56 frames.], batch size: 17, lr: 1.32e-04
2022-05-08 21:52:52,783 INFO [train.py:715] (4/8) Epoch 17, batch 400, loss[loss=0.1622, simple_loss=0.2251, pruned_loss=0.04966, over 4900.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02822, over 842514.63 frames.], batch size: 17, lr: 1.32e-04
2022-05-08 21:53:33,709 INFO [train.py:715] (4/8) Epoch 17, batch 450, loss[loss=0.1264, simple_loss=0.2034, pruned_loss=0.02473, over 4969.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02868, over 871668.76 frames.], batch size: 35, lr: 1.32e-04
2022-05-08 21:54:14,771 INFO [train.py:715] (4/8) Epoch 17, batch 500, loss[loss=0.154, simple_loss=0.233, pruned_loss=0.03753, over 4860.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02872, over 893371.34 frames.], batch size: 20, lr: 1.32e-04
2022-05-08 21:54:56,761 INFO [train.py:715] (4/8) Epoch 17, batch 550, loss[loss=0.1233, simple_loss=0.2048, pruned_loss=0.02089, over 4959.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02898, over 910419.71 frames.], batch size: 39, lr: 1.32e-04
2022-05-08 21:55:37,892 INFO [train.py:715] (4/8) Epoch 17, batch 600, loss[loss=0.1548, simple_loss=0.218, pruned_loss=0.04577, over 4701.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.02942, over 923921.80 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 21:56:20,083 INFO [train.py:715] (4/8) Epoch 17, batch 650, loss[loss=0.131, simple_loss=0.2076, pruned_loss=0.0272, over 4833.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02955, over 934800.14 frames.], batch size: 26, lr: 1.32e-04
2022-05-08 21:57:01,696 INFO [train.py:715] (4/8) Epoch 17, batch 700, loss[loss=0.108, simple_loss=0.1958, pruned_loss=0.01004, over 4955.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02958, over 942799.75 frames.], batch size: 24, lr: 1.32e-04
2022-05-08 21:57:42,600 INFO [train.py:715] (4/8) Epoch 17, batch 750, loss[loss=0.1162, simple_loss=0.1881, pruned_loss=0.02211, over 4820.00 frames.], tot_loss[loss=0.134, simple_loss=0.2081, pruned_loss=0.02991, over 950390.35 frames.], batch size: 26, lr: 1.32e-04
2022-05-08 21:58:23,365 INFO [train.py:715] (4/8) Epoch 17, batch 800, loss[loss=0.181, simple_loss=0.2359, pruned_loss=0.06302, over 4782.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2087, pruned_loss=0.03023, over 954842.96 frames.], batch size: 14, lr: 1.32e-04
2022-05-08 21:59:03,972 INFO [train.py:715] (4/8) Epoch 17, batch 850, loss[loss=0.1098, simple_loss=0.1852, pruned_loss=0.01724, over 4812.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02977, over 958360.23 frames.], batch size: 13, lr: 1.32e-04
2022-05-08 21:59:45,383 INFO [train.py:715] (4/8) Epoch 17, batch 900, loss[loss=0.1306, simple_loss=0.1994, pruned_loss=0.03091, over 4989.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02962, over 961877.50 frames.], batch size: 26, lr: 1.32e-04
2022-05-08 22:00:26,253 INFO [train.py:715] (4/8) Epoch 17, batch 950, loss[loss=0.1059, simple_loss=0.1704, pruned_loss=0.02065, over 4886.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02965, over 964368.17 frames.], batch size: 16, lr: 1.32e-04
2022-05-08 22:01:07,633 INFO [train.py:715] (4/8) Epoch 17, batch 1000, loss[loss=0.1274, simple_loss=0.1954, pruned_loss=0.02972, over 4791.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02964, over 966163.67 frames.], batch size: 17, lr: 1.32e-04
2022-05-08 22:01:48,886 INFO [train.py:715] (4/8) Epoch 17, batch 1050, loss[loss=0.1477, simple_loss=0.2217, pruned_loss=0.03685, over 4979.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.02998, over 967468.25 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:02:29,895 INFO [train.py:715] (4/8) Epoch 17, batch 1100, loss[loss=0.1019, simple_loss=0.182, pruned_loss=0.01087, over 4942.00 frames.], tot_loss[loss=0.133, simple_loss=0.2068, pruned_loss=0.02962, over 968473.14 frames.], batch size: 21, lr: 1.32e-04
2022-05-08 22:03:10,386 INFO [train.py:715] (4/8) Epoch 17, batch 1150, loss[loss=0.1278, simple_loss=0.2051, pruned_loss=0.02518, over 4689.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02943, over 969327.06 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:03:51,856 INFO [train.py:715] (4/8) Epoch 17, batch 1200, loss[loss=0.1176, simple_loss=0.1885, pruned_loss=0.02329, over 4794.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02935, over 969521.50 frames.], batch size: 17, lr: 1.32e-04
2022-05-08 22:04:32,823 INFO [train.py:715] (4/8) Epoch 17, batch 1250, loss[loss=0.1435, simple_loss=0.2097, pruned_loss=0.03865, over 4820.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02946, over 969398.45 frames.], batch size: 25, lr: 1.32e-04
2022-05-08 22:05:13,879 INFO [train.py:715] (4/8) Epoch 17, batch 1300, loss[loss=0.1279, simple_loss=0.2074, pruned_loss=0.02419, over 4976.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02933, over 970293.26 frames.], batch size: 24, lr: 1.32e-04
2022-05-08 22:05:55,236 INFO [train.py:715] (4/8) Epoch 17, batch 1350, loss[loss=0.1085, simple_loss=0.187, pruned_loss=0.01494, over 4969.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02913, over 971360.00 frames.], batch size: 21, lr: 1.32e-04
2022-05-08 22:06:36,194 INFO [train.py:715] (4/8) Epoch 17, batch 1400, loss[loss=0.1346, simple_loss=0.2186, pruned_loss=0.02529, over 4888.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02909, over 970897.44 frames.], batch size: 22, lr: 1.32e-04
2022-05-08 22:07:16,791 INFO [train.py:715] (4/8) Epoch 17, batch 1450, loss[loss=0.1601, simple_loss=0.2343, pruned_loss=0.04293, over 4834.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02896, over 971358.96 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:07:57,507 INFO [train.py:715] (4/8) Epoch 17, batch 1500, loss[loss=0.1248, simple_loss=0.1947, pruned_loss=0.02746, over 4892.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02928, over 971532.97 frames.], batch size: 19, lr: 1.32e-04
2022-05-08 22:08:39,007 INFO [train.py:715] (4/8) Epoch 17, batch 1550, loss[loss=0.1295, simple_loss=0.2062, pruned_loss=0.02642, over 4844.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2078, pruned_loss=0.02939, over 971972.44 frames.], batch size: 26, lr: 1.32e-04
2022-05-08 22:09:20,347 INFO [train.py:715] (4/8) Epoch 17, batch 1600, loss[loss=0.1193, simple_loss=0.1975, pruned_loss=0.02054, over 4935.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.0296, over 972518.69 frames.], batch size: 21, lr: 1.32e-04
2022-05-08 22:10:01,031 INFO [train.py:715] (4/8) Epoch 17, batch 1650, loss[loss=0.1439, simple_loss=0.2162, pruned_loss=0.03581, over 4791.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02963, over 973510.29 frames.], batch size: 21, lr: 1.32e-04
2022-05-08 22:10:42,362 INFO [train.py:715] (4/8) Epoch 17, batch 1700, loss[loss=0.1253, simple_loss=0.2089, pruned_loss=0.02088, over 4915.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02928, over 973947.48 frames.], batch size: 18, lr: 1.32e-04
2022-05-08 22:11:23,602 INFO [train.py:715] (4/8) Epoch 17, batch 1750, loss[loss=0.1186, simple_loss=0.2003, pruned_loss=0.01845, over 4922.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02916, over 972452.30 frames.], batch size: 23, lr: 1.32e-04
2022-05-08 22:12:04,534 INFO [train.py:715] (4/8) Epoch 17, batch 1800, loss[loss=0.1282, simple_loss=0.1987, pruned_loss=0.02887, over 4904.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02888, over 972145.23 frames.], batch size: 18, lr: 1.32e-04
2022-05-08 22:12:45,633 INFO [train.py:715] (4/8) Epoch 17, batch 1850, loss[loss=0.1419, simple_loss=0.2143, pruned_loss=0.03468, over 4976.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.0288, over 972158.43 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:13:27,325 INFO [train.py:715] (4/8) Epoch 17, batch 1900, loss[loss=0.1761, simple_loss=0.2481, pruned_loss=0.05204, over 4986.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02911, over 972324.68 frames.], batch size: 14, lr: 1.32e-04
2022-05-08 22:14:08,474 INFO [train.py:715] (4/8) Epoch 17, batch 1950, loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02981, over 4922.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02884, over 972447.23 frames.], batch size: 18, lr: 1.32e-04
2022-05-08 22:14:49,360 INFO [train.py:715] (4/8) Epoch 17, batch 2000, loss[loss=0.1448, simple_loss=0.2126, pruned_loss=0.03851, over 4855.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02851, over 973083.85 frames.], batch size: 30, lr: 1.32e-04
2022-05-08 22:15:30,334 INFO [train.py:715] (4/8) Epoch 17, batch 2050, loss[loss=0.1521, simple_loss=0.218, pruned_loss=0.04308, over 4855.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02886, over 973457.37 frames.], batch size: 30, lr: 1.32e-04
2022-05-08 22:16:11,443 INFO [train.py:715] (4/8) Epoch 17, batch 2100, loss[loss=0.1594, simple_loss=0.2252, pruned_loss=0.04685, over 4875.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.029, over 973627.54 frames.], batch size: 16, lr: 1.32e-04
2022-05-08 22:16:52,785 INFO [train.py:715] (4/8) Epoch 17, batch 2150, loss[loss=0.1293, simple_loss=0.2016, pruned_loss=0.02848, over 4946.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02913, over 973661.24 frames.], batch size: 21, lr: 1.32e-04
2022-05-08 22:17:34,175 INFO [train.py:715] (4/8) Epoch 17, batch 2200, loss[loss=0.1418, simple_loss=0.2117, pruned_loss=0.03596, over 4984.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02888, over 974190.66 frames.], batch size: 24, lr: 1.32e-04
2022-05-08 22:18:15,304 INFO [train.py:715] (4/8) Epoch 17, batch 2250, loss[loss=0.1559, simple_loss=0.2288, pruned_loss=0.04144, over 4950.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02907, over 973488.62 frames.], batch size: 39, lr: 1.32e-04
2022-05-08 22:18:56,032 INFO [train.py:715] (4/8) Epoch 17, batch 2300, loss[loss=0.1265, simple_loss=0.197, pruned_loss=0.02796, over 4876.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02922, over 973324.88 frames.], batch size: 22, lr: 1.32e-04
2022-05-08 22:19:36,470 INFO [train.py:715] (4/8) Epoch 17, batch 2350, loss[loss=0.1376, simple_loss=0.2052, pruned_loss=0.03498, over 4771.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02893, over 973371.03 frames.], batch size: 17, lr: 1.32e-04
2022-05-08 22:20:17,305 INFO [train.py:715] (4/8) Epoch 17, batch 2400, loss[loss=0.1575, simple_loss=0.2275, pruned_loss=0.04375, over 4758.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02895, over 973402.90 frames.], batch size: 16, lr: 1.32e-04
2022-05-08 22:20:58,220 INFO [train.py:715] (4/8) Epoch 17, batch 2450, loss[loss=0.13, simple_loss=0.2087, pruned_loss=0.02566, over 4893.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2051, pruned_loss=0.0284, over 972565.56 frames.], batch size: 22, lr: 1.32e-04
2022-05-08 22:21:39,032 INFO [train.py:715] (4/8) Epoch 17, batch 2500, loss[loss=0.1317, simple_loss=0.21, pruned_loss=0.02665, over 4923.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.028, over 972963.73 frames.], batch size: 29, lr: 1.32e-04
2022-05-08 22:22:19,995 INFO [train.py:715] (4/8) Epoch 17, batch 2550, loss[loss=0.147, simple_loss=0.2196, pruned_loss=0.03714, over 4936.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02802, over 972420.00 frames.], batch size: 18, lr: 1.32e-04
2022-05-08 22:23:00,953 INFO [train.py:715] (4/8) Epoch 17, batch 2600, loss[loss=0.1497, simple_loss=0.2169, pruned_loss=0.04131, over 4959.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02842, over 972605.09 frames.], batch size: 35, lr: 1.32e-04
2022-05-08 22:23:42,194 INFO [train.py:715] (4/8) Epoch 17, batch 2650, loss[loss=0.134, simple_loss=0.2067, pruned_loss=0.03067, over 4931.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02839, over 973028.55 frames.], batch size: 23, lr: 1.32e-04
2022-05-08 22:24:22,844 INFO [train.py:715] (4/8) Epoch 17, batch 2700, loss[loss=0.1107, simple_loss=0.186, pruned_loss=0.01771, over 4810.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2073, pruned_loss=0.02872, over 972966.42 frames.], batch size: 26, lr: 1.32e-04
2022-05-08 22:25:04,059 INFO [train.py:715] (4/8) Epoch 17, batch 2750, loss[loss=0.1319, simple_loss=0.2109, pruned_loss=0.02641, over 4838.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02906, over 972287.63 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:25:44,577 INFO [train.py:715] (4/8) Epoch 17, batch 2800, loss[loss=0.1436, simple_loss=0.2192, pruned_loss=0.03402, over 4779.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02964, over 972621.63 frames.], batch size: 18, lr: 1.32e-04
2022-05-08 22:26:25,551 INFO [train.py:715] (4/8) Epoch 17, batch 2850, loss[loss=0.1248, simple_loss=0.21, pruned_loss=0.01974, over 4974.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02938, over 972546.47 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:27:06,290 INFO [train.py:715] (4/8) Epoch 17, batch 2900, loss[loss=0.1222, simple_loss=0.1866, pruned_loss=0.02894, over 4923.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2085, pruned_loss=0.02959, over 972411.79 frames.], batch size: 18, lr: 1.32e-04
2022-05-08 22:27:47,262 INFO [train.py:715] (4/8) Epoch 17, batch 2950, loss[loss=0.1252, simple_loss=0.1966, pruned_loss=0.0269, over 4961.00 frames.], tot_loss[loss=0.1335, simple_loss=0.208, pruned_loss=0.02943, over 972951.61 frames.], batch size: 24, lr: 1.32e-04
2022-05-08 22:28:28,409 INFO [train.py:715] (4/8) Epoch 17, batch 3000, loss[loss=0.1477, simple_loss=0.2143, pruned_loss=0.0405, over 4741.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2082, pruned_loss=0.02938, over 972222.71 frames.], batch size: 12, lr: 1.32e-04
2022-05-08 22:28:28,410 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 22:28:43,492 INFO [train.py:742] (4/8) Epoch 17, validation: loss=0.1047, simple_loss=0.1882, pruned_loss=0.01063, over 914524.00 frames.
2022-05-08 22:29:24,680 INFO [train.py:715] (4/8) Epoch 17, batch 3050, loss[loss=0.1475, simple_loss=0.2176, pruned_loss=0.03873, over 4849.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02909, over 972378.74 frames.], batch size: 32, lr: 1.32e-04
2022-05-08 22:30:05,282 INFO [train.py:715] (4/8) Epoch 17, batch 3100, loss[loss=0.1116, simple_loss=0.1936, pruned_loss=0.01482, over 4847.00 frames.], tot_loss[loss=0.133, simple_loss=0.208, pruned_loss=0.02901, over 972312.75 frames.], batch size: 20, lr: 1.32e-04
2022-05-08 22:30:46,406 INFO [train.py:715] (4/8) Epoch 17, batch 3150, loss[loss=0.1081, simple_loss=0.1744, pruned_loss=0.02095, over 4830.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2079, pruned_loss=0.0291, over 971790.91 frames.], batch size: 13, lr: 1.32e-04
2022-05-08 22:31:26,336 INFO [train.py:715] (4/8) Epoch 17, batch 3200, loss[loss=0.1297, simple_loss=0.2171, pruned_loss=0.02118, over 4741.00 frames.], tot_loss[loss=0.133, simple_loss=0.2079, pruned_loss=0.0291, over 971132.38 frames.], batch size: 19, lr: 1.32e-04
2022-05-08 22:32:07,671 INFO [train.py:715] (4/8) Epoch 17, batch 3250, loss[loss=0.1463, simple_loss=0.2139, pruned_loss=0.03935, over 4879.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02928, over 971278.21 frames.], batch size: 32, lr: 1.32e-04
2022-05-08 22:32:47,733 INFO [train.py:715] (4/8) Epoch 17, batch 3300, loss[loss=0.1354, simple_loss=0.215, pruned_loss=0.02788, over 4848.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.0291, over 970496.94 frames.], batch size: 30, lr: 1.32e-04
2022-05-08 22:33:28,459 INFO [train.py:715] (4/8) Epoch 17, batch 3350, loss[loss=0.1075, simple_loss=0.184, pruned_loss=0.01552, over 4863.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02852, over 970653.40 frames.], batch size: 20, lr: 1.32e-04
2022-05-08 22:34:09,200 INFO [train.py:715] (4/8) Epoch 17, batch 3400, loss[loss=0.1449, simple_loss=0.2135, pruned_loss=0.0381, over 4882.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02875, over 971373.86 frames.], batch size: 16, lr: 1.32e-04
2022-05-08 22:34:50,588 INFO [train.py:715] (4/8) Epoch 17, batch 3450, loss[loss=0.1142, simple_loss=0.1813, pruned_loss=0.02356, over 4727.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02866, over 971886.56 frames.], batch size: 12, lr: 1.32e-04
2022-05-08 22:35:30,941 INFO [train.py:715] (4/8) Epoch 17, batch 3500, loss[loss=0.1344, simple_loss=0.2078, pruned_loss=0.03055, over 4859.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02905, over 972839.12 frames.], batch size: 30, lr: 1.32e-04
2022-05-08 22:36:11,161 INFO [train.py:715] (4/8) Epoch 17, batch 3550, loss[loss=0.1364, simple_loss=0.2151, pruned_loss=0.02884, over 4989.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.0288, over 972215.78 frames.], batch size: 25, lr: 1.32e-04
2022-05-08 22:36:52,126 INFO [train.py:715] (4/8) Epoch 17, batch 3600, loss[loss=0.1327, simple_loss=0.2058, pruned_loss=0.02981, over 4683.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02881, over 972453.90 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:37:31,748 INFO [train.py:715] (4/8) Epoch 17, batch 3650, loss[loss=0.1423, simple_loss=0.217, pruned_loss=0.03385, over 4838.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02876, over 972639.12 frames.], batch size: 30, lr: 1.32e-04
2022-05-08 22:38:11,917 INFO [train.py:715] (4/8) Epoch 17, batch 3700, loss[loss=0.1227, simple_loss=0.2027, pruned_loss=0.02138, over 4802.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02829, over 972430.66 frames.], batch size: 24, lr: 1.32e-04
2022-05-08 22:38:52,839 INFO [train.py:715] (4/8) Epoch 17, batch 3750, loss[loss=0.131, simple_loss=0.2015, pruned_loss=0.0303, over 4968.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2072, pruned_loss=0.02884, over 972444.61 frames.], batch size: 14, lr: 1.32e-04
2022-05-08 22:39:33,612 INFO [train.py:715] (4/8) Epoch 17, batch 3800, loss[loss=0.1193, simple_loss=0.1948, pruned_loss=0.02187, over 4633.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02878, over 971509.63 frames.], batch size: 13, lr: 1.32e-04
2022-05-08 22:40:14,216 INFO [train.py:715] (4/8) Epoch 17, batch 3850, loss[loss=0.1499, simple_loss=0.2173, pruned_loss=0.04129, over 4959.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2081, pruned_loss=0.0292, over 972349.23 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:40:54,271 INFO [train.py:715] (4/8) Epoch 17, batch 3900, loss[loss=0.1384, simple_loss=0.216, pruned_loss=0.0304, over 4786.00 frames.], tot_loss[loss=0.1331, simple_loss=0.208, pruned_loss=0.02909, over 972941.99 frames.], batch size: 18, lr: 1.32e-04
2022-05-08 22:41:35,753 INFO [train.py:715] (4/8) Epoch 17, batch 3950, loss[loss=0.1036, simple_loss=0.1738, pruned_loss=0.01673, over 4974.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2071, pruned_loss=0.0286, over 972807.31 frames.], batch size: 14, lr: 1.32e-04
2022-05-08 22:42:15,632 INFO [train.py:715] (4/8) Epoch 17, batch 4000, loss[loss=0.1386, simple_loss=0.2059, pruned_loss=0.03568, over 4770.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02906, over 972573.11 frames.], batch size: 17, lr: 1.32e-04
2022-05-08 22:42:56,129 INFO [train.py:715] (4/8) Epoch 17, batch 4050, loss[loss=0.1457, simple_loss=0.2169, pruned_loss=0.03727, over 4979.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02934, over 971842.78 frames.], batch size: 33, lr: 1.32e-04
2022-05-08 22:43:36,610 INFO [train.py:715] (4/8) Epoch 17, batch 4100, loss[loss=0.1717, simple_loss=0.251, pruned_loss=0.04621, over 4824.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2082, pruned_loss=0.02965, over 971305.99 frames.], batch size: 15, lr: 1.32e-04
2022-05-08 22:44:17,661 INFO [train.py:715] (4/8) Epoch 17, batch 4150, loss[loss=0.1131, simple_loss=0.19, pruned_loss=0.01812, over 4791.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02956, over 971667.35 frames.], batch size: 18, lr: 1.32e-04
2022-05-08 22:44:56,902 INFO [train.py:715] (4/8) Epoch 17, batch 4200, loss[loss=0.1086, simple_loss=0.1845, pruned_loss=0.01633, over 4809.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02948, over 971463.94 frames.], batch size: 12, lr: 1.32e-04
2022-05-08 22:45:36,944 INFO [train.py:715] (4/8) Epoch 17, batch 4250, loss[loss=0.1391, simple_loss=0.2163, pruned_loss=0.03099, over 4949.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02957, over 971446.85 frames.], batch size: 35, lr: 1.32e-04
2022-05-08 22:46:18,112 INFO [train.py:715] (4/8) Epoch 17, batch 4300, loss[loss=0.1278, simple_loss=0.1854, pruned_loss=0.03512, over 4786.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02985, over 971515.05 frames.], batch size: 14, lr: 1.31e-04
2022-05-08 22:46:58,170 INFO [train.py:715] (4/8) Epoch 17, batch 4350, loss[loss=0.1502, simple_loss=0.2308, pruned_loss=0.03481, over 4975.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02964, over 971819.39 frames.], batch size: 25, lr: 1.31e-04
2022-05-08 22:47:38,038 INFO [train.py:715] (4/8) Epoch 17, batch 4400, loss[loss=0.1068, simple_loss=0.1814, pruned_loss=0.0161, over 4815.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2066, pruned_loss=0.0294, over 972357.05 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 22:48:18,892 INFO [train.py:715] (4/8) Epoch 17, batch 4450, loss[loss=0.1043, simple_loss=0.1842, pruned_loss=0.01214, over 4886.00 frames.], tot_loss[loss=0.1323, simple_loss=0.206, pruned_loss=0.02929, over 972651.83 frames.], batch size: 22, lr: 1.31e-04
2022-05-08 22:48:59,881 INFO [train.py:715] (4/8) Epoch 17, batch 4500, loss[loss=0.1077, simple_loss=0.1746, pruned_loss=0.02033, over 4796.00 frames.], tot_loss[loss=0.1314, simple_loss=0.205, pruned_loss=0.02892, over 972049.63 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 22:49:39,757 INFO [train.py:715] (4/8) Epoch 17, batch 4550, loss[loss=0.1241, simple_loss=0.1936, pruned_loss=0.02733, over 4880.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2057, pruned_loss=0.02887, over 972196.56 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 22:50:20,187 INFO [train.py:715] (4/8) Epoch 17, batch 4600, loss[loss=0.1384, simple_loss=0.2063, pruned_loss=0.03523, over 4890.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2059, pruned_loss=0.02898, over 972755.03 frames.], batch size: 32, lr: 1.31e-04
2022-05-08 22:51:01,205 INFO [train.py:715] (4/8) Epoch 17, batch 4650, loss[loss=0.1221, simple_loss=0.2017, pruned_loss=0.02121, over 4778.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02922, over 972094.78 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 22:51:41,121 INFO [train.py:715] (4/8) Epoch 17, batch 4700, loss[loss=0.136, simple_loss=0.2124, pruned_loss=0.02978, over 4891.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.0294, over 972216.94 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 22:52:21,058 INFO [train.py:715] (4/8) Epoch 17, batch 4750, loss[loss=0.1421, simple_loss=0.216, pruned_loss=0.03404, over 4975.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02913, over 971714.38 frames.], batch size: 25, lr: 1.31e-04
2022-05-08 22:53:02,041 INFO [train.py:715] (4/8) Epoch 17, batch 4800, loss[loss=0.1258, simple_loss=0.1955, pruned_loss=0.02801, over 4891.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02907, over 971757.33 frames.], batch size: 22, lr: 1.31e-04
2022-05-08 22:53:42,797 INFO [train.py:715] (4/8) Epoch 17, batch 4850, loss[loss=0.1484, simple_loss=0.2331, pruned_loss=0.03183, over 4915.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02913, over 971859.42 frames.], batch size: 39, lr: 1.31e-04
2022-05-08 22:54:22,661 INFO [train.py:715] (4/8) Epoch 17, batch 4900, loss[loss=0.1134, simple_loss=0.1864, pruned_loss=0.02017, over 4849.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02918, over 972744.38 frames.], batch size: 26, lr: 1.31e-04
2022-05-08 22:55:03,097 INFO [train.py:715] (4/8) Epoch 17, batch 4950, loss[loss=0.1066, simple_loss=0.1806, pruned_loss=0.01632, over 4837.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02931, over 971780.42 frames.], batch size: 13, lr: 1.31e-04
2022-05-08 22:55:44,130 INFO [train.py:715] (4/8) Epoch 17, batch 5000, loss[loss=0.204, simple_loss=0.2678, pruned_loss=0.07008, over 4709.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.0293, over 971476.55 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 22:56:24,633 INFO [train.py:715] (4/8) Epoch 17, batch 5050, loss[loss=0.1734, simple_loss=0.2389, pruned_loss=0.05399, over 4975.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02927, over 972442.18 frames.], batch size: 24, lr: 1.31e-04
2022-05-08 22:57:04,156 INFO [train.py:715] (4/8) Epoch 17, batch 5100, loss[loss=0.1511, simple_loss=0.2342, pruned_loss=0.03406, over 4973.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02934, over 973224.51 frames.], batch size: 28, lr: 1.31e-04
2022-05-08 22:57:44,980 INFO [train.py:715] (4/8) Epoch 17, batch 5150, loss[loss=0.1609, simple_loss=0.2274, pruned_loss=0.04723, over 4970.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02903, over 973065.71 frames.], batch size: 24, lr: 1.31e-04
2022-05-08 22:58:26,123 INFO [train.py:715] (4/8) Epoch 17, batch 5200, loss[loss=0.1235, simple_loss=0.199, pruned_loss=0.02402, over 4770.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02881, over 971895.71 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 22:59:05,337 INFO [train.py:715] (4/8) Epoch 17, batch 5250, loss[loss=0.1171, simple_loss=0.1889, pruned_loss=0.02269, over 4796.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02927, over 972820.19 frames.], batch size: 21, lr: 1.31e-04
2022-05-08 22:59:44,884 INFO [train.py:715] (4/8) Epoch 17, batch 5300, loss[loss=0.1264, simple_loss=0.1999, pruned_loss=0.02648, over 4922.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02944, over 972103.66 frames.], batch size: 23, lr: 1.31e-04
2022-05-08 23:00:25,462 INFO [train.py:715] (4/8) Epoch 17, batch 5350, loss[loss=0.1524, simple_loss=0.2225, pruned_loss=0.04114, over 4916.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02942, over 971812.38 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:01:06,235 INFO [train.py:715] (4/8) Epoch 17, batch 5400, loss[loss=0.1729, simple_loss=0.2482, pruned_loss=0.04885, over 4693.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02917, over 971964.74 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:01:45,343 INFO [train.py:715] (4/8) Epoch 17, batch 5450, loss[loss=0.09926, simple_loss=0.1736, pruned_loss=0.01246, over 4921.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02916, over 971747.85 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:02:26,541 INFO [train.py:715] (4/8) Epoch 17, batch 5500, loss[loss=0.1355, simple_loss=0.206, pruned_loss=0.03246, over 4738.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.0297, over 971883.67 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:03:07,876 INFO [train.py:715] (4/8) Epoch 17, batch 5550, loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02839, over 4826.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.02998, over 971707.86 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:03:46,988 INFO [train.py:715] (4/8) Epoch 17, batch 5600, loss[loss=0.1521, simple_loss=0.2243, pruned_loss=0.0399, over 4968.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02958, over 972271.57 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:04:27,245 INFO [train.py:715] (4/8) Epoch 17, batch 5650, loss[loss=0.1073, simple_loss=0.1826, pruned_loss=0.01603, over 4945.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.0299, over 973039.08 frames.], batch size: 29, lr: 1.31e-04
2022-05-08 23:05:08,281 INFO [train.py:715] (4/8) Epoch 17, batch 5700, loss[loss=0.1422, simple_loss=0.2139, pruned_loss=0.03529, over 4961.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2076, pruned_loss=0.03001, over 972810.12 frames.], batch size: 24, lr: 1.31e-04
2022-05-08 23:05:48,471 INFO [train.py:715] (4/8) Epoch 17, batch 5750, loss[loss=0.1426, simple_loss=0.2175, pruned_loss=0.0339, over 4928.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2077, pruned_loss=0.03006, over 972520.32 frames.], batch size: 23, lr: 1.31e-04
2022-05-08 23:06:27,747 INFO [train.py:715] (4/8) Epoch 17, batch 5800, loss[loss=0.1466, simple_loss=0.2247, pruned_loss=0.03426, over 4878.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2077, pruned_loss=0.02974, over 972156.91 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:07:08,766 INFO [train.py:715] (4/8) Epoch 17, batch 5850, loss[loss=0.1382, simple_loss=0.2127, pruned_loss=0.0319, over 4814.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02951, over 971826.12 frames.], batch size: 25, lr: 1.31e-04
2022-05-08 23:07:49,074 INFO [train.py:715] (4/8) Epoch 17, batch 5900, loss[loss=0.1123, simple_loss=0.199, pruned_loss=0.01282, over 4651.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02961, over 971463.72 frames.], batch size: 13, lr: 1.31e-04
2022-05-08 23:08:29,705 INFO [train.py:715] (4/8) Epoch 17, batch 5950, loss[loss=0.1078, simple_loss=0.1895, pruned_loss=0.01307, over 4935.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02958, over 971461.67 frames.], batch size: 23, lr: 1.31e-04
2022-05-08 23:09:09,137 INFO [train.py:715] (4/8) Epoch 17, batch 6000, loss[loss=0.1232, simple_loss=0.1915, pruned_loss=0.02745, over 4897.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02978, over 971478.78 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 23:09:09,138 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 23:09:23,453 INFO [train.py:742] (4/8) Epoch 17, validation: loss=0.1047, simple_loss=0.1881, pruned_loss=0.01069, over 914524.00 frames.
2022-05-08 23:10:02,834 INFO [train.py:715] (4/8) Epoch 17, batch 6050, loss[loss=0.1234, simple_loss=0.1975, pruned_loss=0.02461, over 4775.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2067, pruned_loss=0.02974, over 971549.77 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:10:43,306 INFO [train.py:715] (4/8) Epoch 17, batch 6100, loss[loss=0.1164, simple_loss=0.1942, pruned_loss=0.01929, over 4895.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2072, pruned_loss=0.03005, over 971853.66 frames.], batch size: 17, lr: 1.31e-04
2022-05-08 23:11:22,422 INFO [train.py:715] (4/8) Epoch 17, batch 6150, loss[loss=0.127, simple_loss=0.2006, pruned_loss=0.02671, over 4908.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03006, over 972203.69 frames.], batch size: 17, lr: 1.31e-04
2022-05-08 23:12:02,002 INFO [train.py:715] (4/8) Epoch 17, batch 6200, loss[loss=0.1135, simple_loss=0.178, pruned_loss=0.02452, over 4869.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2074, pruned_loss=0.03025, over 973015.73 frames.], batch size: 32, lr: 1.31e-04
2022-05-08 23:12:42,477 INFO [train.py:715] (4/8) Epoch 17, batch 6250, loss[loss=0.1276, simple_loss=0.1996, pruned_loss=0.02775, over 4961.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2064, pruned_loss=0.0295, over 972110.93 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:13:22,262 INFO [train.py:715] (4/8) Epoch 17, batch 6300, loss[loss=0.1289, simple_loss=0.1995, pruned_loss=0.02919, over 4923.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2057, pruned_loss=0.02937, over 972465.24 frames.], batch size: 23, lr: 1.31e-04
2022-05-08 23:14:01,677 INFO [train.py:715] (4/8) Epoch 17, batch 6350, loss[loss=0.1049, simple_loss=0.1843, pruned_loss=0.01274, over 4921.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2061, pruned_loss=0.02958, over 971862.74 frames.], batch size: 23, lr: 1.31e-04
2022-05-08 23:14:41,495 INFO [train.py:715] (4/8) Epoch 17, batch 6400, loss[loss=0.122, simple_loss=0.1951, pruned_loss=0.02447, over 4874.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2058, pruned_loss=0.02965, over 972050.61 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:15:21,777 INFO [train.py:715] (4/8) Epoch 17, batch 6450, loss[loss=0.1222, simple_loss=0.2069, pruned_loss=0.01872, over 4924.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2055, pruned_loss=0.02932, over 972083.57 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:16:01,144 INFO [train.py:715] (4/8) Epoch 17, batch 6500, loss[loss=0.1674, simple_loss=0.2422, pruned_loss=0.04623, over 4816.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2056, pruned_loss=0.02944, over 972722.81 frames.], batch size: 27, lr: 1.31e-04
2022-05-08 23:16:40,472 INFO [train.py:715] (4/8) Epoch 17, batch 6550, loss[loss=0.1263, simple_loss=0.2001, pruned_loss=0.02621, over 4825.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2059, pruned_loss=0.02937, over 972725.40 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:17:20,842 INFO [train.py:715] (4/8) Epoch 17, batch 6600, loss[loss=0.1264, simple_loss=0.2027, pruned_loss=0.02508, over 4886.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02916, over 973388.88 frames.], batch size: 22, lr: 1.31e-04
2022-05-08 23:18:01,036 INFO [train.py:715] (4/8) Epoch 17, batch 6650, loss[loss=0.1431, simple_loss=0.2261, pruned_loss=0.03003, over 4936.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02913, over 973553.66 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:18:40,480 INFO [train.py:715] (4/8) Epoch 17, batch 6700, loss[loss=0.1188, simple_loss=0.1946, pruned_loss=0.02146, over 4965.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2056, pruned_loss=0.02894, over 973915.55 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:19:20,727 INFO [train.py:715] (4/8) Epoch 17, batch 6750, loss[loss=0.131, simple_loss=0.2059, pruned_loss=0.02803, over 4872.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2058, pruned_loss=0.02925, over 974191.68 frames.], batch size: 22, lr: 1.31e-04
2022-05-08 23:20:00,491 INFO [train.py:715] (4/8) Epoch 17, batch 6800, loss[loss=0.1221, simple_loss=0.1835, pruned_loss=0.03033, over 4788.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2057, pruned_loss=0.02908, over 972640.17 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 23:20:41,160 INFO [train.py:715] (4/8) Epoch 17, batch 6850, loss[loss=0.1822, simple_loss=0.2549, pruned_loss=0.05479, over 4836.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02976, over 972820.25 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:21:20,238 INFO [train.py:715] (4/8) Epoch 17, batch 6900, loss[loss=0.09921, simple_loss=0.1673, pruned_loss=0.01554, over 4844.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02966, over 972041.41 frames.], batch size: 13, lr: 1.31e-04
2022-05-08 23:22:00,928 INFO [train.py:715] (4/8) Epoch 17, batch 6950, loss[loss=0.1383, simple_loss=0.2081, pruned_loss=0.03424, over 4876.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02891, over 971898.53 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:22:40,663 INFO [train.py:715] (4/8) Epoch 17, batch 7000, loss[loss=0.1233, simple_loss=0.1962, pruned_loss=0.02524, over 4784.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02883, over 971683.57 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 23:23:20,236 INFO [train.py:715] (4/8) Epoch 17, batch 7050, loss[loss=0.1417, simple_loss=0.2158, pruned_loss=0.03381, over 4931.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02915, over 971535.34 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:24:00,503 INFO [train.py:715] (4/8) Epoch 17, batch 7100, loss[loss=0.1198, simple_loss=0.1931, pruned_loss=0.02324, over 4918.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02926, over 971414.45 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:24:40,020 INFO [train.py:715] (4/8) Epoch 17, batch 7150, loss[loss=0.131, simple_loss=0.2107, pruned_loss=0.02562, over 4881.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02908, over 971756.52 frames.], batch size: 22, lr: 1.31e-04
2022-05-08 23:25:19,626 INFO [train.py:715] (4/8) Epoch 17, batch 7200, loss[loss=0.1125, simple_loss=0.1844, pruned_loss=0.02029, over 4986.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02875, over 971631.10 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:25:58,583 INFO [train.py:715] (4/8) Epoch 17, batch 7250, loss[loss=0.1513, simple_loss=0.2358, pruned_loss=0.03334, over 4889.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02882, over 972424.64 frames.], batch size: 22, lr: 1.31e-04
2022-05-08 23:26:39,071 INFO [train.py:715] (4/8) Epoch 17, batch 7300, loss[loss=0.1116, simple_loss=0.1851, pruned_loss=0.01903, over 4974.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02878, over 973030.84 frames.], batch size: 39, lr: 1.31e-04
2022-05-08 23:27:18,027 INFO [train.py:715] (4/8) Epoch 17, batch 7350, loss[loss=0.1424, simple_loss=0.2156, pruned_loss=0.03457, over 4897.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02863, over 973491.27 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 23:27:56,381 INFO [train.py:715] (4/8) Epoch 17, batch 7400, loss[loss=0.135, simple_loss=0.2116, pruned_loss=0.02924, over 4928.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02921, over 974097.90 frames.], batch size: 23, lr: 1.31e-04
2022-05-08 23:28:36,430 INFO [train.py:715] (4/8) Epoch 17, batch 7450, loss[loss=0.121, simple_loss=0.1901, pruned_loss=0.02596, over 4829.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02918, over 973969.78 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:29:15,435 INFO [train.py:715] (4/8) Epoch 17, batch 7500, loss[loss=0.1631, simple_loss=0.2432, pruned_loss=0.04149, over 4896.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02904, over 973569.97 frames.], batch size: 19, lr: 1.31e-04
2022-05-08 23:29:55,163 INFO [train.py:715] (4/8) Epoch 17, batch 7550, loss[loss=0.1223, simple_loss=0.1925, pruned_loss=0.02602, over 4886.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2051, pruned_loss=0.02887, over 972886.14 frames.], batch size: 22, lr: 1.31e-04
2022-05-08 23:30:34,485 INFO [train.py:715] (4/8) Epoch 17, batch 7600, loss[loss=0.1111, simple_loss=0.1922, pruned_loss=0.01503, over 4746.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2053, pruned_loss=0.0289, over 972127.23 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:31:14,608 INFO [train.py:715] (4/8) Epoch 17, batch 7650, loss[loss=0.1644, simple_loss=0.2419, pruned_loss=0.04345, over 4869.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2051, pruned_loss=0.02869, over 972462.21 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:31:54,512 INFO [train.py:715] (4/8) Epoch 17, batch 7700, loss[loss=0.1131, simple_loss=0.1905, pruned_loss=0.01788, over 4972.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2055, pruned_loss=0.02879, over 973219.30 frames.], batch size: 24, lr: 1.31e-04
2022-05-08 23:32:33,790 INFO [train.py:715] (4/8) Epoch 17, batch 7750, loss[loss=0.1293, simple_loss=0.2127, pruned_loss=0.02294, over 4933.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02923, over 972932.65 frames.], batch size: 21, lr: 1.31e-04
2022-05-08 23:33:14,386 INFO [train.py:715] (4/8) Epoch 17, batch 7800, loss[loss=0.1182, simple_loss=0.1921, pruned_loss=0.02217, over 4869.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02945, over 972896.54 frames.], batch size: 39, lr: 1.31e-04
2022-05-08 23:33:54,602 INFO [train.py:715] (4/8) Epoch 17, batch 7850, loss[loss=0.1183, simple_loss=0.1981, pruned_loss=0.01926, over 4873.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02942, over 972874.43 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:34:34,847 INFO [train.py:715] (4/8) Epoch 17, batch 7900, loss[loss=0.1077, simple_loss=0.1846, pruned_loss=0.01541, over 4794.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2076, pruned_loss=0.02969, over 972635.03 frames.], batch size: 21, lr: 1.31e-04
2022-05-08 23:35:13,813 INFO [train.py:715] (4/8) Epoch 17, batch 7950, loss[loss=0.1081, simple_loss=0.1813, pruned_loss=0.01742, over 4770.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02944, over 972352.77 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 23:35:53,566 INFO [train.py:715] (4/8) Epoch 17, batch 8000, loss[loss=0.1362, simple_loss=0.2074, pruned_loss=0.03248, over 4861.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02941, over 972359.39 frames.], batch size: 32, lr: 1.31e-04
2022-05-08 23:36:33,458 INFO [train.py:715] (4/8) Epoch 17, batch 8050, loss[loss=0.1042, simple_loss=0.1808, pruned_loss=0.01376, over 4821.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02922, over 971960.61 frames.], batch size: 26, lr: 1.31e-04
2022-05-08 23:37:12,790 INFO [train.py:715] (4/8) Epoch 17, batch 8100, loss[loss=0.101, simple_loss=0.1739, pruned_loss=0.01401, over 4815.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2067, pruned_loss=0.02952, over 972183.52 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:37:52,682 INFO [train.py:715] (4/8) Epoch 17, batch 8150, loss[loss=0.1081, simple_loss=0.178, pruned_loss=0.01914, over 4765.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02909, over 971968.74 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 23:38:32,356 INFO [train.py:715] (4/8) Epoch 17, batch 8200, loss[loss=0.1217, simple_loss=0.1962, pruned_loss=0.0236, over 4806.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2058, pruned_loss=0.02896, over 971468.19 frames.], batch size: 14, lr: 1.31e-04
2022-05-08 23:39:14,687 INFO [train.py:715] (4/8) Epoch 17, batch 8250, loss[loss=0.152, simple_loss=0.2174, pruned_loss=0.04328, over 4840.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2053, pruned_loss=0.0286, over 971429.17 frames.], batch size: 30, lr: 1.31e-04
2022-05-08 23:39:53,899 INFO [train.py:715] (4/8) Epoch 17, batch 8300, loss[loss=0.1379, simple_loss=0.2236, pruned_loss=0.02612, over 4840.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02914, over 971889.66 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:40:33,620 INFO [train.py:715] (4/8) Epoch 17, batch 8350, loss[loss=0.1513, simple_loss=0.2344, pruned_loss=0.03414, over 4738.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02963, over 971707.65 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:41:13,220 INFO [train.py:715] (4/8) Epoch 17, batch 8400, loss[loss=0.1233, simple_loss=0.1964, pruned_loss=0.02513, over 4870.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02969, over 972779.06 frames.], batch size: 20, lr: 1.31e-04
2022-05-08 23:41:52,758 INFO [train.py:715] (4/8) Epoch 17, batch 8450, loss[loss=0.1108, simple_loss=0.1854, pruned_loss=0.01809, over 4916.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02942, over 972177.01 frames.], batch size: 23, lr: 1.31e-04
2022-05-08 23:42:32,327 INFO [train.py:715] (4/8) Epoch 17, batch 8500, loss[loss=0.1295, simple_loss=0.1983, pruned_loss=0.03038, over 4981.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2074, pruned_loss=0.02974, over 972575.26 frames.], batch size: 28, lr: 1.31e-04
2022-05-08 23:43:12,140 INFO [train.py:715] (4/8) Epoch 17, batch 8550, loss[loss=0.1445, simple_loss=0.2131, pruned_loss=0.03795, over 4843.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2077, pruned_loss=0.03031, over 972923.58 frames.], batch size: 20, lr: 1.31e-04
2022-05-08 23:43:51,999 INFO [train.py:715] (4/8) Epoch 17, batch 8600, loss[loss=0.1127, simple_loss=0.1873, pruned_loss=0.01904, over 4788.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2075, pruned_loss=0.03007, over 971895.52 frames.], batch size: 17, lr: 1.31e-04
2022-05-08 23:44:31,009 INFO [train.py:715] (4/8) Epoch 17, batch 8650, loss[loss=0.1208, simple_loss=0.2025, pruned_loss=0.01953, over 4880.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.02997, over 972345.36 frames.], batch size: 22, lr: 1.31e-04
2022-05-08 23:45:10,880 INFO [train.py:715] (4/8) Epoch 17, batch 8700, loss[loss=0.1768, simple_loss=0.2405, pruned_loss=0.05654, over 4877.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2074, pruned_loss=0.03003, over 972814.97 frames.], batch size: 32, lr: 1.31e-04
2022-05-08 23:45:50,293 INFO [train.py:715] (4/8) Epoch 17, batch 8750, loss[loss=0.1135, simple_loss=0.1915, pruned_loss=0.01777, over 4827.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2071, pruned_loss=0.03, over 973375.48 frames.], batch size: 26, lr: 1.31e-04
2022-05-08 23:46:29,854 INFO [train.py:715] (4/8) Epoch 17, batch 8800, loss[loss=0.1096, simple_loss=0.1877, pruned_loss=0.01578, over 4758.00 frames.], tot_loss[loss=0.133, simple_loss=0.2067, pruned_loss=0.02967, over 973643.25 frames.], batch size: 16, lr: 1.31e-04
2022-05-08 23:47:09,588 INFO [train.py:715] (4/8) Epoch 17, batch 8850, loss[loss=0.1328, simple_loss=0.2088, pruned_loss=0.02846, over 4879.00 frames.], tot_loss[loss=0.1323, simple_loss=0.206, pruned_loss=0.0293, over 972097.27 frames.], batch size: 22, lr: 1.31e-04
2022-05-08 23:47:48,797 INFO [train.py:715] (4/8) Epoch 17, batch 8900, loss[loss=0.128, simple_loss=0.1896, pruned_loss=0.03316, over 4831.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2062, pruned_loss=0.02941, over 972798.73 frames.], batch size: 13, lr: 1.31e-04
2022-05-08 23:48:28,443 INFO [train.py:715] (4/8) Epoch 17, batch 8950, loss[loss=0.1287, simple_loss=0.2074, pruned_loss=0.02497, over 4824.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2075, pruned_loss=0.02966, over 971938.49 frames.], batch size: 25, lr: 1.31e-04
2022-05-08 23:49:07,465 INFO [train.py:715] (4/8) Epoch 17, batch 9000, loss[loss=0.1265, simple_loss=0.2014, pruned_loss=0.02584, over 4913.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2074, pruned_loss=0.02964, over 972256.79 frames.], batch size: 17, lr: 1.31e-04
2022-05-08 23:49:07,466 INFO [train.py:733] (4/8) Computing validation loss
2022-05-08 23:49:17,245 INFO [train.py:742] (4/8) Epoch 17, validation: loss=0.1048, simple_loss=0.1882, pruned_loss=0.01072, over 914524.00 frames.
2022-05-08 23:49:56,411 INFO [train.py:715] (4/8) Epoch 17, batch 9050, loss[loss=0.1439, simple_loss=0.2209, pruned_loss=0.03341, over 4842.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03005, over 972794.53 frames.], batch size: 30, lr: 1.31e-04
2022-05-08 23:50:36,246 INFO [train.py:715] (4/8) Epoch 17, batch 9100, loss[loss=0.1074, simple_loss=0.179, pruned_loss=0.0179, over 4819.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02967, over 972983.42 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 23:51:15,863 INFO [train.py:715] (4/8) Epoch 17, batch 9150, loss[loss=0.1345, simple_loss=0.2076, pruned_loss=0.03073, over 4981.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02979, over 972098.72 frames.], batch size: 28, lr: 1.31e-04
2022-05-08 23:51:54,740 INFO [train.py:715] (4/8) Epoch 17, batch 9200, loss[loss=0.1311, simple_loss=0.2007, pruned_loss=0.03076, over 4781.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02997, over 973138.71 frames.], batch size: 14, lr: 1.31e-04
2022-05-08 23:52:34,931 INFO [train.py:715] (4/8) Epoch 17, batch 9250, loss[loss=0.1516, simple_loss=0.2249, pruned_loss=0.03913, over 4844.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02991, over 973617.77 frames.], batch size: 30, lr: 1.31e-04
2022-05-08 23:53:14,617 INFO [train.py:715] (4/8) Epoch 17, batch 9300, loss[loss=0.1353, simple_loss=0.2002, pruned_loss=0.03523, over 4791.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.0301, over 974036.05 frames.], batch size: 12, lr: 1.31e-04
2022-05-08 23:53:53,952 INFO [train.py:715] (4/8) Epoch 17, batch 9350, loss[loss=0.1567, simple_loss=0.228, pruned_loss=0.04273, over 4909.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02983, over 973408.50 frames.], batch size: 39, lr: 1.31e-04
2022-05-08 23:54:33,275 INFO [train.py:715] (4/8) Epoch 17, batch 9400, loss[loss=0.1353, simple_loss=0.2221, pruned_loss=0.02425, over 4868.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02939, over 973419.15 frames.], batch size: 22, lr: 1.31e-04
2022-05-08 23:55:13,700 INFO [train.py:715] (4/8) Epoch 17, batch 9450, loss[loss=0.1215, simple_loss=0.1963, pruned_loss=0.02335, over 4808.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02872, over 972556.42 frames.], batch size: 21, lr: 1.31e-04
2022-05-08 23:55:53,691 INFO [train.py:715] (4/8) Epoch 17, batch 9500, loss[loss=0.1323, simple_loss=0.2053, pruned_loss=0.02966, over 4752.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02876, over 971608.13 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:56:32,927 INFO [train.py:715] (4/8) Epoch 17, batch 9550, loss[loss=0.1355, simple_loss=0.2118, pruned_loss=0.02953, over 4783.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02879, over 972271.48 frames.], batch size: 14, lr: 1.31e-04
2022-05-08 23:57:12,478 INFO [train.py:715] (4/8) Epoch 17, batch 9600, loss[loss=0.1173, simple_loss=0.2018, pruned_loss=0.01646, over 4814.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02917, over 971887.73 frames.], batch size: 26, lr: 1.31e-04
2022-05-08 23:57:52,760 INFO [train.py:715] (4/8) Epoch 17, batch 9650, loss[loss=0.1464, simple_loss=0.2284, pruned_loss=0.03218, over 4771.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2079, pruned_loss=0.02928, over 972166.00 frames.], batch size: 18, lr: 1.31e-04
2022-05-08 23:58:31,948 INFO [train.py:715] (4/8) Epoch 17, batch 9700, loss[loss=0.1568, simple_loss=0.2226, pruned_loss=0.04556, over 4986.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02881, over 972059.00 frames.], batch size: 31, lr: 1.31e-04
2022-05-08 23:59:11,715 INFO [train.py:715] (4/8) Epoch 17, batch 9750, loss[loss=0.1272, simple_loss=0.2009, pruned_loss=0.02677, over 4697.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02887, over 971973.18 frames.], batch size: 15, lr: 1.31e-04
2022-05-08 23:59:51,460 INFO [train.py:715] (4/8) Epoch 17, batch 9800, loss[loss=0.1229, simple_loss=0.1891, pruned_loss=0.02838, over 4983.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02975, over 971452.37 frames.], batch size: 28, lr: 1.31e-04
2022-05-09 00:00:31,044 INFO [train.py:715] (4/8) Epoch 17, batch 9850, loss[loss=0.1033, simple_loss=0.1748, pruned_loss=0.01591, over 4821.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02958, over 972349.59 frames.], batch size: 13, lr: 1.31e-04
2022-05-09 00:01:10,447 INFO [train.py:715] (4/8) Epoch 17, batch 9900, loss[loss=0.1247, simple_loss=0.1998, pruned_loss=0.02482, over 4936.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2075, pruned_loss=0.02981, over 971647.17 frames.], batch size: 21, lr: 1.31e-04
2022-05-09 00:01:49,865 INFO [train.py:715] (4/8) Epoch 17, batch 9950, loss[loss=0.117, simple_loss=0.1937, pruned_loss=0.02017, over 4770.00 frames.], tot_loss[loss=0.134, simple_loss=0.2079, pruned_loss=0.03008, over 971178.46 frames.], batch size: 19, lr: 1.31e-04
2022-05-09 00:02:30,158 INFO [train.py:715] (4/8) Epoch 17, batch 10000, loss[loss=0.1734, simple_loss=0.2428, pruned_loss=0.05197, over 4917.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02985, over 971941.60 frames.], batch size: 39, lr: 1.31e-04
2022-05-09 00:03:09,391 INFO [train.py:715] (4/8) Epoch 17, batch 10050, loss[loss=0.1218, simple_loss=0.1949, pruned_loss=0.02434, over 4957.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02956, over 972619.26 frames.], batch size: 35, lr: 1.31e-04
2022-05-09 00:03:48,279 INFO [train.py:715] (4/8) Epoch 17, batch 10100, loss[loss=0.1317, simple_loss=0.2086, pruned_loss=0.02743, over 4816.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2077, pruned_loss=0.02901, over 972941.93 frames.], batch size: 27, lr: 1.31e-04
2022-05-09 00:04:27,595 INFO [train.py:715] (4/8) Epoch 17, batch 10150, loss[loss=0.1191, simple_loss=0.1964, pruned_loss=0.02095, over 4805.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2072, pruned_loss=0.02886, over 972571.50 frames.], batch size: 21, lr: 1.31e-04
2022-05-09 00:05:06,926 INFO [train.py:715] (4/8) Epoch 17, batch 10200, loss[loss=0.1358, simple_loss=0.2028, pruned_loss=0.03444, over 4759.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.029, over 972359.53 frames.], batch size: 19, lr: 1.31e-04
2022-05-09 00:05:44,871 INFO [train.py:715] (4/8) Epoch 17, batch 10250, loss[loss=0.1363, simple_loss=0.2179, pruned_loss=0.02739, over 4848.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02965, over 973135.85 frames.], batch size: 20, lr: 1.31e-04
2022-05-09 00:06:24,647 INFO [train.py:715] (4/8) Epoch 17, batch 10300, loss[loss=0.1162, simple_loss=0.2008, pruned_loss=0.01581, over 4838.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.0293, over 973316.31 frames.], batch size: 30, lr: 1.31e-04
2022-05-09 00:07:04,571 INFO [train.py:715] (4/8) Epoch 17, batch 10350, loss[loss=0.1353, simple_loss=0.2173, pruned_loss=0.02669, over 4663.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02972, over 973165.57 frames.], batch size: 13, lr: 1.31e-04
2022-05-09 00:07:43,244 INFO [train.py:715] (4/8) Epoch 17, batch 10400, loss[loss=0.1547, simple_loss=0.2338, pruned_loss=0.03781, over 4929.00 frames.], tot_loss[loss=0.1334, simple_loss=0.208, pruned_loss=0.02941, over 973443.57 frames.], batch size: 21, lr: 1.31e-04
2022-05-09 00:08:22,347 INFO [train.py:715] (4/8) Epoch 17, batch 10450, loss[loss=0.1175, simple_loss=0.1935, pruned_loss=0.02075, over 4795.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2084, pruned_loss=0.02939, over 972323.03 frames.], batch size: 24, lr: 1.31e-04
2022-05-09 00:09:02,375 INFO [train.py:715] (4/8) Epoch 17, batch 10500, loss[loss=0.1594, simple_loss=0.227, pruned_loss=0.04591, over 4883.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2085, pruned_loss=0.02949, over 973038.82 frames.], batch size: 22, lr: 1.31e-04
2022-05-09 00:09:41,413 INFO [train.py:715] (4/8) Epoch 17, batch 10550, loss[loss=0.1383, simple_loss=0.2213, pruned_loss=0.0276, over 4799.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.02884, over 973419.41 frames.], batch size: 21, lr: 1.31e-04
2022-05-09 00:10:19,762 INFO [train.py:715] (4/8) Epoch 17, batch 10600, loss[loss=0.1007, simple_loss=0.1762, pruned_loss=0.01259, over 4873.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02872, over 973296.41 frames.], batch size: 22, lr: 1.31e-04
2022-05-09 00:10:59,069 INFO [train.py:715] (4/8) Epoch 17, batch 10650, loss[loss=0.142, simple_loss=0.2221, pruned_loss=0.03095, over 4946.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02907, over 973246.44 frames.], batch size: 18, lr: 1.31e-04
2022-05-09 00:11:38,577 INFO [train.py:715] (4/8) Epoch 17, batch 10700, loss[loss=0.1648, simple_loss=0.2426, pruned_loss=0.04354, over 4845.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02912, over 973215.46 frames.], batch size: 32, lr: 1.31e-04
2022-05-09 00:12:17,257 INFO [train.py:715] (4/8) Epoch 17, batch 10750, loss[loss=0.1307, simple_loss=0.1947, pruned_loss=0.03337, over 4775.00 frames.], tot_loss[loss=0.133, simple_loss=0.2078, pruned_loss=0.02913, over 973145.84 frames.], batch size: 14, lr: 1.31e-04
2022-05-09 00:12:56,255 INFO [train.py:715] (4/8) Epoch 17, batch 10800, loss[loss=0.132, simple_loss=0.1974, pruned_loss=0.0333, over 4696.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02907, over 973433.83 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:13:36,022 INFO [train.py:715] (4/8) Epoch 17, batch 10850, loss[loss=0.1297, simple_loss=0.2052, pruned_loss=0.02712, over 4896.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02907, over 973691.93 frames.], batch size: 19, lr: 1.31e-04
2022-05-09 00:14:15,585 INFO [train.py:715] (4/8) Epoch 17, batch 10900, loss[loss=0.1329, simple_loss=0.2135, pruned_loss=0.02615, over 4769.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02869, over 973186.02 frames.], batch size: 19, lr: 1.31e-04
2022-05-09 00:14:53,760 INFO [train.py:715] (4/8) Epoch 17, batch 10950, loss[loss=0.1599, simple_loss=0.2127, pruned_loss=0.05355, over 4821.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02889, over 973135.25 frames.], batch size: 13, lr: 1.31e-04
2022-05-09 00:15:33,875 INFO [train.py:715] (4/8) Epoch 17, batch 11000, loss[loss=0.1676, simple_loss=0.2377, pruned_loss=0.04878, over 4824.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02898, over 972547.22 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:16:13,750 INFO [train.py:715] (4/8) Epoch 17, batch 11050, loss[loss=0.1565, simple_loss=0.2275, pruned_loss=0.0428, over 4695.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.0284, over 971808.67 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:16:52,425 INFO [train.py:715] (4/8) Epoch 17, batch 11100, loss[loss=0.1236, simple_loss=0.2006, pruned_loss=0.02332, over 4963.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2054, pruned_loss=0.02804, over 971605.19 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:17:31,482 INFO [train.py:715] (4/8) Epoch 17, batch 11150, loss[loss=0.1177, simple_loss=0.1926, pruned_loss=0.02141, over 4804.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02871, over 970884.61 frames.], batch size: 21, lr: 1.31e-04
2022-05-09 00:18:11,487 INFO [train.py:715] (4/8) Epoch 17, batch 11200, loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02829, over 4967.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.0291, over 971298.95 frames.], batch size: 24, lr: 1.31e-04
2022-05-09 00:18:51,595 INFO [train.py:715] (4/8) Epoch 17, batch 11250, loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.029, over 4931.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.0291, over 971881.66 frames.], batch size: 23, lr: 1.31e-04
2022-05-09 00:19:29,833 INFO [train.py:715] (4/8) Epoch 17, batch 11300, loss[loss=0.1296, simple_loss=0.2043, pruned_loss=0.02748, over 4797.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02909, over 971847.40 frames.], batch size: 14, lr: 1.31e-04
2022-05-09 00:20:09,300 INFO [train.py:715] (4/8) Epoch 17, batch 11350, loss[loss=0.1187, simple_loss=0.1897, pruned_loss=0.0239, over 4926.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.029, over 972157.96 frames.], batch size: 29, lr: 1.31e-04
2022-05-09 00:20:49,490 INFO [train.py:715] (4/8) Epoch 17, batch 11400, loss[loss=0.1354, simple_loss=0.2085, pruned_loss=0.03118, over 4765.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02881, over 972529.50 frames.], batch size: 18, lr: 1.31e-04
2022-05-09 00:21:28,498 INFO [train.py:715] (4/8) Epoch 17, batch 11450, loss[loss=0.1987, simple_loss=0.2745, pruned_loss=0.06142, over 4766.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02879, over 972575.44 frames.], batch size: 17, lr: 1.31e-04
2022-05-09 00:22:07,511 INFO [train.py:715] (4/8) Epoch 17, batch 11500, loss[loss=0.1389, simple_loss=0.2185, pruned_loss=0.0297, over 4889.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2057, pruned_loss=0.02879, over 971533.32 frames.], batch size: 22, lr: 1.31e-04
2022-05-09 00:22:47,221 INFO [train.py:715] (4/8) Epoch 17, batch 11550, loss[loss=0.1376, simple_loss=0.2091, pruned_loss=0.03301, over 4755.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02894, over 971824.24 frames.], batch size: 19, lr: 1.31e-04
2022-05-09 00:23:27,162 INFO [train.py:715] (4/8) Epoch 17, batch 11600, loss[loss=0.1503, simple_loss=0.2209, pruned_loss=0.03989, over 4926.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02923, over 971453.65 frames.], batch size: 23, lr: 1.31e-04
2022-05-09 00:24:05,130 INFO [train.py:715] (4/8) Epoch 17, batch 11650, loss[loss=0.12, simple_loss=0.1974, pruned_loss=0.02137, over 4958.00 frames.], tot_loss[loss=0.133, simple_loss=0.2067, pruned_loss=0.02963, over 971413.50 frames.], batch size: 35, lr: 1.31e-04
2022-05-09 00:24:44,956 INFO [train.py:715] (4/8) Epoch 17, batch 11700, loss[loss=0.1208, simple_loss=0.2028, pruned_loss=0.01941, over 4897.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2061, pruned_loss=0.02935, over 971659.72 frames.], batch size: 22, lr: 1.31e-04
2022-05-09 00:25:24,935 INFO [train.py:715] (4/8) Epoch 17, batch 11750, loss[loss=0.1411, simple_loss=0.2068, pruned_loss=0.03772, over 4793.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2059, pruned_loss=0.02951, over 972548.42 frames.], batch size: 24, lr: 1.31e-04
2022-05-09 00:26:03,880 INFO [train.py:715] (4/8) Epoch 17, batch 11800, loss[loss=0.1358, simple_loss=0.2052, pruned_loss=0.03318, over 4803.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2056, pruned_loss=0.02929, over 972341.46 frames.], batch size: 21, lr: 1.31e-04
2022-05-09 00:26:42,875 INFO [train.py:715] (4/8) Epoch 17, batch 11850, loss[loss=0.1233, simple_loss=0.2018, pruned_loss=0.02238, over 4826.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2055, pruned_loss=0.02894, over 971961.71 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:27:22,148 INFO [train.py:715] (4/8) Epoch 17, batch 11900, loss[loss=0.1133, simple_loss=0.1784, pruned_loss=0.02414, over 4791.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2055, pruned_loss=0.02861, over 971632.02 frames.], batch size: 13, lr: 1.31e-04
2022-05-09 00:28:01,982 INFO [train.py:715] (4/8) Epoch 17, batch 11950, loss[loss=0.1205, simple_loss=0.1948, pruned_loss=0.02311, over 4962.00 frames.], tot_loss[loss=0.131, simple_loss=0.2047, pruned_loss=0.02868, over 971817.93 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:28:40,962 INFO [train.py:715] (4/8) Epoch 17, batch 12000, loss[loss=0.1229, simple_loss=0.195, pruned_loss=0.02541, over 4850.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2052, pruned_loss=0.0286, over 971643.05 frames.], batch size: 20, lr: 1.31e-04
2022-05-09 00:28:40,962 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 00:28:52,719 INFO [train.py:742] (4/8) Epoch 17, validation: loss=0.1048, simple_loss=0.1882, pruned_loss=0.0107, over 914524.00 frames.
2022-05-09 00:29:31,825 INFO [train.py:715] (4/8) Epoch 17, batch 12050, loss[loss=0.1493, simple_loss=0.2249, pruned_loss=0.03687, over 4802.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2053, pruned_loss=0.0286, over 970913.24 frames.], batch size: 21, lr: 1.31e-04
2022-05-09 00:30:10,919 INFO [train.py:715] (4/8) Epoch 17, batch 12100, loss[loss=0.1043, simple_loss=0.1687, pruned_loss=0.01992, over 4850.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02868, over 971296.87 frames.], batch size: 12, lr: 1.31e-04
2022-05-09 00:30:50,932 INFO [train.py:715] (4/8) Epoch 17, batch 12150, loss[loss=0.1164, simple_loss=0.2003, pruned_loss=0.01625, over 4906.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02859, over 971784.01 frames.], batch size: 19, lr: 1.31e-04
2022-05-09 00:31:29,659 INFO [train.py:715] (4/8) Epoch 17, batch 12200, loss[loss=0.1205, simple_loss=0.1983, pruned_loss=0.02128, over 4974.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02869, over 971270.10 frames.], batch size: 24, lr: 1.31e-04
2022-05-09 00:32:08,194 INFO [train.py:715] (4/8) Epoch 17, batch 12250, loss[loss=0.1175, simple_loss=0.1933, pruned_loss=0.02088, over 4968.00 frames.], tot_loss[loss=0.1321, simple_loss=0.207, pruned_loss=0.02863, over 972151.79 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:32:47,684 INFO [train.py:715] (4/8) Epoch 17, batch 12300, loss[loss=0.1345, simple_loss=0.2133, pruned_loss=0.02785, over 4951.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02921, over 972575.03 frames.], batch size: 21, lr: 1.31e-04
2022-05-09 00:33:26,862 INFO [train.py:715] (4/8) Epoch 17, batch 12350, loss[loss=0.1477, simple_loss=0.2134, pruned_loss=0.04105, over 4909.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02913, over 971981.08 frames.], batch size: 17, lr: 1.31e-04
2022-05-09 00:34:05,566 INFO [train.py:715] (4/8) Epoch 17, batch 12400, loss[loss=0.1324, simple_loss=0.2128, pruned_loss=0.02596, over 4838.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2074, pruned_loss=0.02905, over 972486.52 frames.], batch size: 30, lr: 1.31e-04
2022-05-09 00:34:44,616 INFO [train.py:715] (4/8) Epoch 17, batch 12450, loss[loss=0.1203, simple_loss=0.1888, pruned_loss=0.02593, over 4964.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02861, over 972667.73 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:35:24,995 INFO [train.py:715] (4/8) Epoch 17, batch 12500, loss[loss=0.1322, simple_loss=0.2002, pruned_loss=0.03212, over 4639.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02928, over 972854.15 frames.], batch size: 13, lr: 1.31e-04
2022-05-09 00:36:03,580 INFO [train.py:715] (4/8) Epoch 17, batch 12550, loss[loss=0.1598, simple_loss=0.2289, pruned_loss=0.04541, over 4858.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02925, over 972554.97 frames.], batch size: 38, lr: 1.31e-04
2022-05-09 00:36:42,923 INFO [train.py:715] (4/8) Epoch 17, batch 12600, loss[loss=0.1135, simple_loss=0.181, pruned_loss=0.02301, over 4980.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02855, over 971807.56 frames.], batch size: 24, lr: 1.31e-04
2022-05-09 00:37:22,858 INFO [train.py:715] (4/8) Epoch 17, batch 12650, loss[loss=0.1273, simple_loss=0.2082, pruned_loss=0.02321, over 4849.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.029, over 971793.36 frames.], batch size: 20, lr: 1.31e-04
2022-05-09 00:38:02,852 INFO [train.py:715] (4/8) Epoch 17, batch 12700, loss[loss=0.142, simple_loss=0.2247, pruned_loss=0.02961, over 4784.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02919, over 972107.28 frames.], batch size: 18, lr: 1.31e-04
2022-05-09 00:38:42,162 INFO [train.py:715] (4/8) Epoch 17, batch 12750, loss[loss=0.1912, simple_loss=0.2577, pruned_loss=0.06234, over 4945.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02924, over 972446.94 frames.], batch size: 35, lr: 1.31e-04
2022-05-09 00:39:20,964 INFO [train.py:715] (4/8) Epoch 17, batch 12800, loss[loss=0.1373, simple_loss=0.2158, pruned_loss=0.02939, over 4921.00 frames.], tot_loss[loss=0.1334, simple_loss=0.208, pruned_loss=0.0294, over 972827.76 frames.], batch size: 18, lr: 1.31e-04
2022-05-09 00:40:00,595 INFO [train.py:715] (4/8) Epoch 17, batch 12850, loss[loss=0.1248, simple_loss=0.198, pruned_loss=0.02584, over 4993.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.0294, over 973041.79 frames.], batch size: 16, lr: 1.31e-04
2022-05-09 00:40:39,042 INFO [train.py:715] (4/8) Epoch 17, batch 12900, loss[loss=0.1392, simple_loss=0.2116, pruned_loss=0.03336, over 4687.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02911, over 972184.64 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:41:18,426 INFO [train.py:715] (4/8) Epoch 17, batch 12950, loss[loss=0.152, simple_loss=0.2283, pruned_loss=0.03789, over 4864.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2064, pruned_loss=0.02949, over 972951.01 frames.], batch size: 20, lr: 1.31e-04
2022-05-09 00:41:57,021 INFO [train.py:715] (4/8) Epoch 17, batch 13000, loss[loss=0.1422, simple_loss=0.2009, pruned_loss=0.04176, over 4782.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2062, pruned_loss=0.02939, over 973893.02 frames.], batch size: 14, lr: 1.31e-04
2022-05-09 00:42:36,104 INFO [train.py:715] (4/8) Epoch 17, batch 13050, loss[loss=0.1451, simple_loss=0.224, pruned_loss=0.03316, over 4961.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02965, over 973308.83 frames.], batch size: 24, lr: 1.31e-04
2022-05-09 00:43:15,227 INFO [train.py:715] (4/8) Epoch 17, batch 13100, loss[loss=0.1325, simple_loss=0.212, pruned_loss=0.02648, over 4809.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.0295, over 972876.30 frames.], batch size: 25, lr: 1.31e-04
2022-05-09 00:43:54,021 INFO [train.py:715] (4/8) Epoch 17, batch 13150, loss[loss=0.1127, simple_loss=0.1868, pruned_loss=0.01926, over 4831.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2069, pruned_loss=0.0297, over 971850.24 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:44:33,796 INFO [train.py:715] (4/8) Epoch 17, batch 13200, loss[loss=0.114, simple_loss=0.1854, pruned_loss=0.02131, over 4953.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2069, pruned_loss=0.02977, over 971433.12 frames.], batch size: 15, lr: 1.31e-04
2022-05-09 00:45:12,321 INFO [train.py:715] (4/8) Epoch 17, batch 13250, loss[loss=0.1217, simple_loss=0.192, pruned_loss=0.02566, over 4909.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02948, over 972252.05 frames.], batch size: 19, lr: 1.31e-04
2022-05-09 00:45:51,622 INFO [train.py:715] (4/8) Epoch 17, batch 13300, loss[loss=0.16, simple_loss=0.2441, pruned_loss=0.03789, over 4800.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02934, over 972046.35 frames.], batch size: 17, lr: 1.31e-04
2022-05-09 00:46:30,711 INFO [train.py:715] (4/8) Epoch 17, batch 13350, loss[loss=0.1396, simple_loss=0.2108, pruned_loss=0.03419, over 4864.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02898, over 971745.79 frames.], batch size: 20, lr: 1.31e-04
2022-05-09 00:47:09,939 INFO [train.py:715] (4/8) Epoch 17, batch 13400, loss[loss=0.1236, simple_loss=0.2016, pruned_loss=0.02285, over 4939.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02918, over 972520.48 frames.], batch size: 29, lr: 1.31e-04
2022-05-09 00:47:49,249 INFO [train.py:715] (4/8) Epoch 17, batch 13450, loss[loss=0.1305, simple_loss=0.2138, pruned_loss=0.02364, over 4944.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02929, over 972502.51 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 00:48:27,710 INFO [train.py:715] (4/8) Epoch 17, batch 13500, loss[loss=0.1251, simple_loss=0.1932, pruned_loss=0.02855, over 4803.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02931, over 972773.85 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 00:49:07,422 INFO [train.py:715] (4/8) Epoch 17, batch 13550, loss[loss=0.123, simple_loss=0.2098, pruned_loss=0.01814, over 4968.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02926, over 972770.45 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 00:49:45,776 INFO [train.py:715] (4/8) Epoch 17, batch 13600, loss[loss=0.1275, simple_loss=0.1996, pruned_loss=0.02772, over 4850.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02939, over 972075.31 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 00:50:24,821 INFO [train.py:715] (4/8) Epoch 17, batch 13650, loss[loss=0.1069, simple_loss=0.1756, pruned_loss=0.01911, over 4983.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02903, over 971879.91 frames.], batch size: 28, lr: 1.30e-04
2022-05-09 00:51:04,638 INFO [train.py:715] (4/8) Epoch 17, batch 13700, loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02823, over 4881.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02964, over 972231.36 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 00:51:43,978 INFO [train.py:715] (4/8) Epoch 17, batch 13750, loss[loss=0.1569, simple_loss=0.2326, pruned_loss=0.04057, over 4779.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.0301, over 971140.89 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 00:52:24,097 INFO [train.py:715] (4/8) Epoch 17, batch 13800, loss[loss=0.124, simple_loss=0.2097, pruned_loss=0.0192, over 4876.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2083, pruned_loss=0.03009, over 971369.17 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 00:53:03,509 INFO [train.py:715] (4/8) Epoch 17, batch 13850, loss[loss=0.1184, simple_loss=0.1974, pruned_loss=0.01968, over 4776.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02976, over 971157.38 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 00:53:43,318 INFO [train.py:715] (4/8) Epoch 17, batch 13900, loss[loss=0.1381, simple_loss=0.2107, pruned_loss=0.03278, over 4985.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02983, over 971370.74 frames.], batch size: 28, lr: 1.30e-04
2022-05-09 00:54:22,806 INFO [train.py:715] (4/8) Epoch 17, batch 13950, loss[loss=0.1464, simple_loss=0.223, pruned_loss=0.0349, over 4778.00 frames.], tot_loss[loss=0.1339, simple_loss=0.208, pruned_loss=0.02992, over 970894.24 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 00:55:02,839 INFO [train.py:715] (4/8) Epoch 17, batch 14000, loss[loss=0.1133, simple_loss=0.1927, pruned_loss=0.01695, over 4938.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02928, over 971818.84 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 00:55:42,005 INFO [train.py:715] (4/8) Epoch 17, batch 14050, loss[loss=0.1281, simple_loss=0.1891, pruned_loss=0.03353, over 4893.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02948, over 972002.35 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 00:56:21,072 INFO [train.py:715] (4/8) Epoch 17, batch 14100, loss[loss=0.1467, simple_loss=0.2204, pruned_loss=0.03648, over 4769.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02943, over 972125.55 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 00:57:01,247 INFO [train.py:715] (4/8) Epoch 17, batch 14150, loss[loss=0.1525, simple_loss=0.2142, pruned_loss=0.04535, over 4922.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02945, over 972036.63 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 00:57:40,315 INFO [train.py:715] (4/8) Epoch 17, batch 14200, loss[loss=0.1378, simple_loss=0.2018, pruned_loss=0.03685, over 4986.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02927, over 971559.00 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 00:58:19,831 INFO [train.py:715] (4/8) Epoch 17, batch 14250, loss[loss=0.1458, simple_loss=0.2197, pruned_loss=0.03596, over 4884.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02925, over 971636.47 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 00:58:58,997 INFO [train.py:715] (4/8) Epoch 17, batch 14300, loss[loss=0.1149, simple_loss=0.1902, pruned_loss=0.01983, over 4801.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02904, over 972239.50 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 00:59:38,853 INFO [train.py:715] (4/8) Epoch 17, batch 14350, loss[loss=0.137, simple_loss=0.2108, pruned_loss=0.03163, over 4805.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02913, over 972477.29 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 01:00:17,887 INFO [train.py:715] (4/8) Epoch 17, batch 14400, loss[loss=0.1485, simple_loss=0.2207, pruned_loss=0.03814, over 4874.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02957, over 972185.42 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 01:00:56,578 INFO [train.py:715] (4/8) Epoch 17, batch 14450, loss[loss=0.137, simple_loss=0.2087, pruned_loss=0.03268, over 4860.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02909, over 971951.70 frames.], batch size: 32, lr: 1.30e-04
2022-05-09 01:01:36,311 INFO [train.py:715] (4/8) Epoch 17, batch 14500, loss[loss=0.1407, simple_loss=0.213, pruned_loss=0.03417, over 4775.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02891, over 972112.31 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:02:15,670 INFO [train.py:715] (4/8) Epoch 17, batch 14550, loss[loss=0.1121, simple_loss=0.1851, pruned_loss=0.01958, over 4776.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.02877, over 972760.53 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 01:02:54,148 INFO [train.py:715] (4/8) Epoch 17, batch 14600, loss[loss=0.1119, simple_loss=0.1884, pruned_loss=0.01771, over 4773.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02926, over 972403.12 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 01:03:33,787 INFO [train.py:715] (4/8) Epoch 17, batch 14650, loss[loss=0.1298, simple_loss=0.2149, pruned_loss=0.0224, over 4855.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02964, over 971470.53 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 01:04:13,440 INFO [train.py:715] (4/8) Epoch 17, batch 14700, loss[loss=0.1398, simple_loss=0.2136, pruned_loss=0.03306, over 4827.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02945, over 971586.18 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:04:52,652 INFO [train.py:715] (4/8) Epoch 17, batch 14750, loss[loss=0.1304, simple_loss=0.1987, pruned_loss=0.03106, over 4903.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02899, over 971537.78 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 01:05:31,537 INFO [train.py:715] (4/8) Epoch 17, batch 14800, loss[loss=0.1189, simple_loss=0.1948, pruned_loss=0.02151, over 4988.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02876, over 972415.30 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 01:06:11,601 INFO [train.py:715] (4/8) Epoch 17, batch 14850, loss[loss=0.1227, simple_loss=0.1991, pruned_loss=0.02319, over 4883.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02893, over 971684.75 frames.], batch size: 32, lr: 1.30e-04
2022-05-09 01:06:50,381 INFO [train.py:715] (4/8) Epoch 17, batch 14900, loss[loss=0.1232, simple_loss=0.2052, pruned_loss=0.02062, over 4908.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02871, over 971699.26 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 01:07:29,330 INFO [train.py:715] (4/8) Epoch 17, batch 14950, loss[loss=0.138, simple_loss=0.2198, pruned_loss=0.02809, over 4824.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02891, over 971531.26 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 01:08:09,015 INFO [train.py:715] (4/8) Epoch 17, batch 15000, loss[loss=0.1547, simple_loss=0.2196, pruned_loss=0.04486, over 4777.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02927, over 972088.05 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 01:08:09,016 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 01:08:19,081 INFO [train.py:742] (4/8) Epoch 17, validation: loss=0.1046, simple_loss=0.1881, pruned_loss=0.01059, over 914524.00 frames.
2022-05-09 01:08:59,145 INFO [train.py:715] (4/8) Epoch 17, batch 15050, loss[loss=0.119, simple_loss=0.192, pruned_loss=0.02302, over 4952.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02907, over 972975.87 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 01:09:38,651 INFO [train.py:715] (4/8) Epoch 17, batch 15100, loss[loss=0.1233, simple_loss=0.1965, pruned_loss=0.02507, over 4869.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02884, over 972603.63 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 01:10:17,574 INFO [train.py:715] (4/8) Epoch 17, batch 15150, loss[loss=0.1582, simple_loss=0.2291, pruned_loss=0.04365, over 4772.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02889, over 973025.25 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:10:56,608 INFO [train.py:715] (4/8) Epoch 17, batch 15200, loss[loss=0.1089, simple_loss=0.1867, pruned_loss=0.01554, over 4986.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02884, over 973502.30 frames.], batch size: 28, lr: 1.30e-04
2022-05-09 01:11:36,239 INFO [train.py:715] (4/8) Epoch 17, batch 15250, loss[loss=0.1234, simple_loss=0.2003, pruned_loss=0.02328, over 4797.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02895, over 972499.07 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:12:15,601 INFO [train.py:715] (4/8) Epoch 17, batch 15300, loss[loss=0.135, simple_loss=0.2139, pruned_loss=0.02803, over 4984.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02889, over 972404.38 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 01:12:53,857 INFO [train.py:715] (4/8) Epoch 17, batch 15350, loss[loss=0.1366, simple_loss=0.2046, pruned_loss=0.03425, over 4839.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02895, over 972675.85 frames.], batch size: 30, lr: 1.30e-04
2022-05-09 01:13:33,402 INFO [train.py:715] (4/8) Epoch 17, batch 15400, loss[loss=0.1287, simple_loss=0.2068, pruned_loss=0.02532, over 4742.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2084, pruned_loss=0.02945, over 972607.66 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 01:14:12,475 INFO [train.py:715] (4/8) Epoch 17, batch 15450, loss[loss=0.1175, simple_loss=0.1844, pruned_loss=0.02536, over 4730.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02914, over 971980.94 frames.], batch size: 12, lr: 1.30e-04
2022-05-09 01:14:51,820 INFO [train.py:715] (4/8) Epoch 17, batch 15500, loss[loss=0.1163, simple_loss=0.1911, pruned_loss=0.02076, over 4816.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02937, over 972160.63 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 01:15:30,647 INFO [train.py:715] (4/8) Epoch 17, batch 15550, loss[loss=0.1456, simple_loss=0.2173, pruned_loss=0.037, over 4799.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02907, over 971906.97 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:16:10,370 INFO [train.py:715] (4/8) Epoch 17, batch 15600, loss[loss=0.1534, simple_loss=0.2324, pruned_loss=0.03722, over 4843.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02922, over 971851.76 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:16:49,789 INFO [train.py:715] (4/8) Epoch 17, batch 15650, loss[loss=0.138, simple_loss=0.2274, pruned_loss=0.02429, over 4925.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02908, over 971908.15 frames.], batch size: 23, lr: 1.30e-04
2022-05-09 01:17:27,917 INFO [train.py:715] (4/8) Epoch 17, batch 15700, loss[loss=0.1473, simple_loss=0.2292, pruned_loss=0.03272, over 4767.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.02877, over 971793.82 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:18:07,727 INFO [train.py:715] (4/8) Epoch 17, batch 15750, loss[loss=0.1422, simple_loss=0.2103, pruned_loss=0.03706, over 4988.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02908, over 971729.26 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:18:47,137 INFO [train.py:715] (4/8) Epoch 17, batch 15800, loss[loss=0.1491, simple_loss=0.2264, pruned_loss=0.03596, over 4890.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02946, over 971532.51 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 01:19:26,084 INFO [train.py:715] (4/8) Epoch 17, batch 15850, loss[loss=0.132, simple_loss=0.2026, pruned_loss=0.03068, over 4785.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2084, pruned_loss=0.03001, over 971840.07 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:20:04,721 INFO [train.py:715] (4/8) Epoch 17, batch 15900, loss[loss=0.1322, simple_loss=0.2148, pruned_loss=0.02478, over 4731.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2087, pruned_loss=0.03, over 971832.76 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 01:20:44,129 INFO [train.py:715] (4/8) Epoch 17, batch 15950, loss[loss=0.1405, simple_loss=0.2154, pruned_loss=0.03275, over 4969.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02969, over 972412.80 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 01:21:23,631 INFO [train.py:715] (4/8) Epoch 17, batch 16000, loss[loss=0.1459, simple_loss=0.213, pruned_loss=0.0394, over 4780.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02987, over 971346.73 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 01:22:02,020 INFO [train.py:715] (4/8) Epoch 17, batch 16050, loss[loss=0.1173, simple_loss=0.1998, pruned_loss=0.01747, over 4974.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2078, pruned_loss=0.02956, over 971393.67 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:22:42,057 INFO [train.py:715] (4/8) Epoch 17, batch 16100, loss[loss=0.1619, simple_loss=0.2277, pruned_loss=0.04811, over 4898.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2083, pruned_loss=0.0297, over 971664.64 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 01:23:21,960 INFO [train.py:715] (4/8) Epoch 17, batch 16150, loss[loss=0.1349, simple_loss=0.2046, pruned_loss=0.03254, over 4947.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02954, over 971678.07 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 01:24:01,717 INFO [train.py:715] (4/8) Epoch 17, batch 16200, loss[loss=0.1394, simple_loss=0.2092, pruned_loss=0.03482, over 4736.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2083, pruned_loss=0.02998, over 971802.61 frames.], batch size: 12, lr: 1.30e-04
2022-05-09 01:24:43,135 INFO [train.py:715] (4/8) Epoch 17, batch 16250, loss[loss=0.1269, simple_loss=0.2055, pruned_loss=0.02417, over 4854.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2087, pruned_loss=0.03032, over 971735.55 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 01:25:23,145 INFO [train.py:715] (4/8) Epoch 17, batch 16300, loss[loss=0.1403, simple_loss=0.2162, pruned_loss=0.03225, over 4901.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.0299, over 971579.10 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 01:26:02,216 INFO [train.py:715] (4/8) Epoch 17, batch 16350, loss[loss=0.1349, simple_loss=0.2052, pruned_loss=0.0323, over 4788.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02966, over 971698.99 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:26:40,874 INFO [train.py:715] (4/8) Epoch 17, batch 16400, loss[loss=0.1238, simple_loss=0.1935, pruned_loss=0.02708, over 4970.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02926, over 973089.24 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:27:20,590 INFO [train.py:715] (4/8) Epoch 17, batch 16450, loss[loss=0.1477, simple_loss=0.2198, pruned_loss=0.03783, over 4762.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02918, over 974025.65 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:28:00,550 INFO [train.py:715] (4/8) Epoch 17, batch 16500, loss[loss=0.1266, simple_loss=0.2042, pruned_loss=0.02448, over 4815.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02929, over 974169.53 frames.], batch size: 27, lr: 1.30e-04
2022-05-09 01:28:39,571 INFO [train.py:715] (4/8) Epoch 17, batch 16550, loss[loss=0.1515, simple_loss=0.2256, pruned_loss=0.03865, over 4832.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02909, over 973155.79 frames.], batch size: 30, lr: 1.30e-04
2022-05-09 01:29:18,071 INFO [train.py:715] (4/8) Epoch 17, batch 16600, loss[loss=0.1526, simple_loss=0.2224, pruned_loss=0.04136, over 4864.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02936, over 973200.90 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 01:29:58,263 INFO [train.py:715] (4/8) Epoch 17, batch 16650, loss[loss=0.1373, simple_loss=0.2102, pruned_loss=0.03222, over 4813.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02935, over 973083.17 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 01:30:38,045 INFO [train.py:715] (4/8) Epoch 17, batch 16700, loss[loss=0.1738, simple_loss=0.2292, pruned_loss=0.05917, over 4896.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02969, over 972870.77 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 01:31:16,487 INFO [train.py:715] (4/8) Epoch 17, batch 16750, loss[loss=0.1484, simple_loss=0.2297, pruned_loss=0.03361, over 4980.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02965, over 973209.35 frames.], batch size: 28, lr: 1.30e-04
2022-05-09 01:31:56,314 INFO [train.py:715] (4/8) Epoch 17, batch 16800, loss[loss=0.1267, simple_loss=0.2006, pruned_loss=0.02639, over 4791.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02959, over 972323.40 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:32:35,734 INFO [train.py:715] (4/8) Epoch 17, batch 16850, loss[loss=0.1347, simple_loss=0.2104, pruned_loss=0.02955, over 4812.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02913, over 972133.65 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 01:33:15,640 INFO [train.py:715] (4/8) Epoch 17, batch 16900, loss[loss=0.1243, simple_loss=0.2055, pruned_loss=0.02158, over 4902.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02918, over 972595.71 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 01:33:53,871 INFO [train.py:715] (4/8) Epoch 17, batch 16950, loss[loss=0.1604, simple_loss=0.2375, pruned_loss=0.04166, over 4942.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2082, pruned_loss=0.02939, over 972263.54 frames.], batch size: 23, lr: 1.30e-04
2022-05-09 01:34:33,424 INFO [train.py:715] (4/8) Epoch 17, batch 17000, loss[loss=0.1622, simple_loss=0.2368, pruned_loss=0.04383, over 4747.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2082, pruned_loss=0.02949, over 972752.38 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 01:35:12,910 INFO [train.py:715] (4/8) Epoch 17, batch 17050, loss[loss=0.1742, simple_loss=0.2456, pruned_loss=0.05136, over 4770.00 frames.], tot_loss[loss=0.1335, simple_loss=0.208, pruned_loss=0.02945, over 972275.63 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:35:51,177 INFO [train.py:715] (4/8) Epoch 17, batch 17100, loss[loss=0.1382, simple_loss=0.1956, pruned_loss=0.04034, over 4796.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02917, over 972037.81 frames.], batch size: 12, lr: 1.30e-04
2022-05-09 01:36:30,679 INFO [train.py:715] (4/8) Epoch 17, batch 17150, loss[loss=0.1354, simple_loss=0.2072, pruned_loss=0.03177, over 4841.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02947, over 972932.61 frames.], batch size: 13, lr: 1.30e-04
2022-05-09 01:37:10,049 INFO [train.py:715] (4/8) Epoch 17, batch 17200, loss[loss=0.1051, simple_loss=0.1845, pruned_loss=0.01278, over 4775.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02971, over 973402.43 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:37:48,555 INFO [train.py:715] (4/8) Epoch 17, batch 17250, loss[loss=0.1449, simple_loss=0.2321, pruned_loss=0.02887, over 4748.00 frames.], tot_loss[loss=0.134, simple_loss=0.2084, pruned_loss=0.02987, over 973801.26 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 01:38:26,823 INFO [train.py:715] (4/8) Epoch 17, batch 17300, loss[loss=0.1211, simple_loss=0.2017, pruned_loss=0.02019, over 4886.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2089, pruned_loss=0.03005, over 973864.73 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 01:39:06,137 INFO [train.py:715] (4/8) Epoch 17, batch 17350, loss[loss=0.1157, simple_loss=0.1908, pruned_loss=0.02032, over 4908.00 frames.], tot_loss[loss=0.1346, simple_loss=0.209, pruned_loss=0.0301, over 973448.85 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:39:45,335 INFO [train.py:715] (4/8) Epoch 17, batch 17400, loss[loss=0.1317, simple_loss=0.2151, pruned_loss=0.02412, over 4794.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2089, pruned_loss=0.02977, over 973326.59 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:40:23,323 INFO [train.py:715] (4/8) Epoch 17, batch 17450, loss[loss=0.1026, simple_loss=0.1754, pruned_loss=0.0149, over 4918.00 frames.], tot_loss[loss=0.1338, simple_loss=0.208, pruned_loss=0.02982, over 972713.56 frames.], batch size: 29, lr: 1.30e-04
2022-05-09 01:41:03,009 INFO [train.py:715] (4/8) Epoch 17, batch 17500, loss[loss=0.1191, simple_loss=0.1933, pruned_loss=0.02239, over 4902.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02915, over 973736.61 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 01:41:42,132 INFO [train.py:715] (4/8) Epoch 17, batch 17550, loss[loss=0.1262, simple_loss=0.2019, pruned_loss=0.02527, over 4858.00 frames.], tot_loss[loss=0.1321, simple_loss=0.207, pruned_loss=0.0286, over 973224.75 frames.], batch size: 38, lr: 1.30e-04
2022-05-09 01:42:20,892 INFO [train.py:715] (4/8) Epoch 17, batch 17600, loss[loss=0.1616, simple_loss=0.2368, pruned_loss=0.04321, over 4859.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.02877, over 973485.81 frames.], batch size: 34, lr: 1.30e-04
2022-05-09 01:42:59,400 INFO [train.py:715] (4/8) Epoch 17, batch 17650, loss[loss=0.1219, simple_loss=0.1949, pruned_loss=0.02449, over 4780.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02882, over 973420.87 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:43:38,884 INFO [train.py:715] (4/8) Epoch 17, batch 17700, loss[loss=0.1129, simple_loss=0.1857, pruned_loss=0.02002, over 4899.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02883, over 973654.84 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 01:44:17,597 INFO [train.py:715] (4/8) Epoch 17, batch 17750, loss[loss=0.1199, simple_loss=0.1996, pruned_loss=0.02008, over 4952.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02888, over 974216.03 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:44:56,094 INFO [train.py:715] (4/8) Epoch 17, batch 17800, loss[loss=0.1209, simple_loss=0.1955, pruned_loss=0.02314, over 4834.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.029, over 974221.52 frames.], batch size: 30, lr: 1.30e-04
2022-05-09 01:45:35,677 INFO [train.py:715] (4/8) Epoch 17, batch 17850, loss[loss=0.1369, simple_loss=0.1988, pruned_loss=0.03751, over 4954.00 frames.], tot_loss[loss=0.1334, simple_loss=0.208, pruned_loss=0.02939, over 973839.25 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:46:14,666 INFO [train.py:715] (4/8) Epoch 17, batch 17900, loss[loss=0.1261, simple_loss=0.2048, pruned_loss=0.02373, over 4928.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02918, over 973366.56 frames.], batch size: 23, lr: 1.30e-04
2022-05-09 01:46:54,015 INFO [train.py:715] (4/8) Epoch 17, batch 17950, loss[loss=0.1083, simple_loss=0.1902, pruned_loss=0.01324, over 4916.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2074, pruned_loss=0.02901, over 973875.00 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 01:47:32,294 INFO [train.py:715] (4/8) Epoch 17, batch 18000, loss[loss=0.1105, simple_loss=0.1867, pruned_loss=0.01711, over 4954.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02903, over 974140.43 frames.], batch size: 39, lr: 1.30e-04
2022-05-09 01:47:32,295 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 01:47:42,060 INFO [train.py:742] (4/8) Epoch 17, validation: loss=0.1047, simple_loss=0.1881, pruned_loss=0.01066, over 914524.00 frames.
2022-05-09 01:48:20,782 INFO [train.py:715] (4/8) Epoch 17, batch 18050, loss[loss=0.1205, simple_loss=0.1898, pruned_loss=0.0256, over 4930.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02893, over 974117.73 frames.], batch size: 29, lr: 1.30e-04
2022-05-09 01:49:00,410 INFO [train.py:715] (4/8) Epoch 17, batch 18100, loss[loss=0.1304, simple_loss=0.2055, pruned_loss=0.02765, over 4839.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2067, pruned_loss=0.02852, over 973933.17 frames.], batch size: 30, lr: 1.30e-04
2022-05-09 01:49:39,797 INFO [train.py:715] (4/8) Epoch 17, batch 18150, loss[loss=0.1301, simple_loss=0.1826, pruned_loss=0.03883, over 4836.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02887, over 973004.71 frames.], batch size: 13, lr: 1.30e-04
2022-05-09 01:50:17,778 INFO [train.py:715] (4/8) Epoch 17, batch 18200, loss[loss=0.1441, simple_loss=0.2078, pruned_loss=0.04021, over 4848.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02932, over 972540.79 frames.], batch size: 32, lr: 1.30e-04
2022-05-09 01:50:57,536 INFO [train.py:715] (4/8) Epoch 17, batch 18250, loss[loss=0.1294, simple_loss=0.1966, pruned_loss=0.03105, over 4757.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2075, pruned_loss=0.02985, over 972270.88 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 01:51:37,062 INFO [train.py:715] (4/8) Epoch 17, batch 18300, loss[loss=0.1577, simple_loss=0.218, pruned_loss=0.04871, over 4800.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.0298, over 972795.94 frames.], batch size: 12, lr: 1.30e-04
2022-05-09 01:52:15,576 INFO [train.py:715] (4/8) Epoch 17, batch 18350, loss[loss=0.1328, simple_loss=0.2094, pruned_loss=0.02807, over 4843.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02947, over 972374.43 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 01:52:55,001 INFO [train.py:715] (4/8) Epoch 17, batch 18400, loss[loss=0.1279, simple_loss=0.209, pruned_loss=0.02343, over 4827.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02932, over 972234.89 frames.], batch size: 27, lr: 1.30e-04
2022-05-09 01:53:33,898 INFO [train.py:715] (4/8) Epoch 17, batch 18450, loss[loss=0.1224, simple_loss=0.2004, pruned_loss=0.02223, over 4749.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02905, over 972588.13 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 01:54:13,088 INFO [train.py:715] (4/8) Epoch 17, batch 18500, loss[loss=0.1429, simple_loss=0.217, pruned_loss=0.03434, over 4802.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.0289, over 971538.30 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 01:54:51,418 INFO [train.py:715] (4/8) Epoch 17, batch 18550, loss[loss=0.119, simple_loss=0.1947, pruned_loss=0.02163, over 4957.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.02902, over 970909.99 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 01:55:30,372 INFO [train.py:715] (4/8) Epoch 17, batch 18600, loss[loss=0.1208, simple_loss=0.1922, pruned_loss=0.02468, over 4972.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02908, over 971566.65 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 01:56:09,530 INFO [train.py:715] (4/8) Epoch 17, batch 18650, loss[loss=0.1441, simple_loss=0.2201, pruned_loss=0.03402, over 4747.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02885, over 972361.39 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 01:56:47,377 INFO [train.py:715] (4/8) Epoch 17, batch 18700, loss[loss=0.1582, simple_loss=0.2328, pruned_loss=0.04177, over 4764.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02922, over 973280.07 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 01:57:27,054 INFO [train.py:715] (4/8) Epoch 17, batch 18750, loss[loss=0.1325, simple_loss=0.212, pruned_loss=0.02649, over 4758.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02921, over 972937.89 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 01:58:06,643 INFO [train.py:715] (4/8) Epoch 17, batch 18800, loss[loss=0.1922, simple_loss=0.2583, pruned_loss=0.06309, over 4911.00 frames.], tot_loss[loss=0.1334, simple_loss=0.208, pruned_loss=0.02945, over 972969.83 frames.], batch size: 39, lr: 1.30e-04
2022-05-09 01:58:45,352 INFO [train.py:715] (4/8) Epoch 17, batch 18850, loss[loss=0.1303, simple_loss=0.2057, pruned_loss=0.02749, over 4701.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.0288, over 971827.21 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 01:59:23,457 INFO [train.py:715] (4/8) Epoch 17, batch 18900, loss[loss=0.1079, simple_loss=0.1873, pruned_loss=0.01425, over 4798.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2084, pruned_loss=0.02917, over 971487.06 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 02:00:02,553 INFO [train.py:715] (4/8) Epoch 17, batch 18950, loss[loss=0.124, simple_loss=0.1987, pruned_loss=0.02468, over 4913.00 frames.], tot_loss[loss=0.1332, simple_loss=0.208, pruned_loss=0.02918, over 972352.68 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:00:41,836 INFO [train.py:715] (4/8) Epoch 17, batch 19000, loss[loss=0.121, simple_loss=0.1963, pruned_loss=0.0229, over 4809.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02905, over 972177.95 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 02:01:20,325 INFO [train.py:715] (4/8) Epoch 17, batch 19050, loss[loss=0.1294, simple_loss=0.214, pruned_loss=0.0224, over 4964.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02908, over 973264.36 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 02:01:59,754 INFO [train.py:715] (4/8) Epoch 17, batch 19100, loss[loss=0.1761, simple_loss=0.2406, pruned_loss=0.05582, over 4792.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02901, over 972864.56 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:02:38,885 INFO [train.py:715] (4/8) Epoch 17, batch 19150, loss[loss=0.1155, simple_loss=0.1973, pruned_loss=0.01688, over 4763.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02934, over 972744.96 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 02:03:17,328 INFO [train.py:715] (4/8) Epoch 17, batch 19200, loss[loss=0.1199, simple_loss=0.1891, pruned_loss=0.02532, over 4967.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02926, over 973531.68 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 02:03:56,157 INFO [train.py:715] (4/8) Epoch 17, batch 19250, loss[loss=0.1353, simple_loss=0.2046, pruned_loss=0.03305, over 4792.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02898, over 972203.67 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 02:04:35,742 INFO [train.py:715] (4/8) Epoch 17, batch 19300, loss[loss=0.1537, simple_loss=0.2286, pruned_loss=0.03936, over 4759.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02924, over 971743.32 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 02:05:15,463 INFO [train.py:715] (4/8) Epoch 17, batch 19350, loss[loss=0.1399, simple_loss=0.212, pruned_loss=0.03394, over 4972.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.0291, over 971727.31 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 02:05:54,626 INFO [train.py:715] (4/8) Epoch 17, batch 19400, loss[loss=0.1285, simple_loss=0.209, pruned_loss=0.02398, over 4890.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2053, pruned_loss=0.02875, over 971765.41 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 02:06:34,192 INFO [train.py:715] (4/8) Epoch 17, batch 19450, loss[loss=0.1215, simple_loss=0.1934, pruned_loss=0.0248, over 4986.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2049, pruned_loss=0.02882, over 970802.12 frames.], batch size: 31, lr: 1.30e-04
2022-05-09 02:07:13,756 INFO [train.py:715] (4/8) Epoch 17, batch 19500, loss[loss=0.1277, simple_loss=0.1937, pruned_loss=0.03085, over 4881.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2045, pruned_loss=0.02884, over 970069.84 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:07:53,344 INFO [train.py:715] (4/8) Epoch 17, batch 19550, loss[loss=0.1252, simple_loss=0.2077, pruned_loss=0.02138, over 4752.00 frames.], tot_loss[loss=0.1315, simple_loss=0.205, pruned_loss=0.029, over 970499.22 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 02:08:31,622 INFO [train.py:715] (4/8) Epoch 17, batch 19600, loss[loss=0.1575, simple_loss=0.2272, pruned_loss=0.04386, over 4873.00 frames.], tot_loss[loss=0.1317, simple_loss=0.205, pruned_loss=0.02919, over 971573.79 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 02:09:11,587 INFO [train.py:715] (4/8) Epoch 17, batch 19650, loss[loss=0.1325, simple_loss=0.2035, pruned_loss=0.03072, over 4785.00 frames.], tot_loss[loss=0.132, simple_loss=0.2055, pruned_loss=0.02922, over 971327.36 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 02:09:51,455 INFO [train.py:715] (4/8) Epoch 17, batch 19700, loss[loss=0.1228, simple_loss=0.1968, pruned_loss=0.0244, over 4752.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02926, over 971877.30 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 02:10:30,060 INFO [train.py:715] (4/8) Epoch 17, batch 19750, loss[loss=0.1695, simple_loss=0.2337, pruned_loss=0.05261, over 4898.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02954, over 971612.34 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:11:09,370 INFO [train.py:715] (4/8) Epoch 17, batch 19800, loss[loss=0.123, simple_loss=0.2053, pruned_loss=0.02033, over 4773.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02924, over 971824.35 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 02:11:47,960 INFO [train.py:715] (4/8) Epoch 17, batch 19850, loss[loss=0.1228, simple_loss=0.1986, pruned_loss=0.02346, over 4792.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02949, over 972222.00 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 02:12:26,931 INFO [train.py:715] (4/8) Epoch 17, batch 19900, loss[loss=0.138, simple_loss=0.2211, pruned_loss=0.02744, over 4892.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02885, over 972722.93 frames.], batch size: 39, lr: 1.30e-04
2022-05-09 02:13:05,188 INFO [train.py:715] (4/8) Epoch 17, batch 19950, loss[loss=0.1098, simple_loss=0.186, pruned_loss=0.01685, over 4885.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2056, pruned_loss=0.02894, over 972869.78 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 02:13:44,432 INFO [train.py:715] (4/8) Epoch 17, batch 20000, loss[loss=0.1258, simple_loss=0.2015, pruned_loss=0.02504, over 4932.00 frames.], tot_loss[loss=0.132, simple_loss=0.2055, pruned_loss=0.02925, over 973091.79 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 02:14:24,053 INFO [train.py:715] (4/8) Epoch 17, batch 20050, loss[loss=0.1188, simple_loss=0.1974, pruned_loss=0.02006, over 4782.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2055, pruned_loss=0.02887, over 974027.79 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:15:03,200 INFO [train.py:715] (4/8) Epoch 17, batch 20100, loss[loss=0.1258, simple_loss=0.2054, pruned_loss=0.02312, over 4913.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2061, pruned_loss=0.02912, over 974615.57 frames.], batch size: 29, lr: 1.30e-04
2022-05-09 02:15:42,009 INFO [train.py:715] (4/8) Epoch 17, batch 20150, loss[loss=0.1341, simple_loss=0.2007, pruned_loss=0.03381, over 4976.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.0294, over 973773.73 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 02:16:22,283 INFO [train.py:715] (4/8) Epoch 17, batch 20200, loss[loss=0.1227, simple_loss=0.197, pruned_loss=0.02423, over 4812.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2061, pruned_loss=0.02932, over 973339.89 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 02:17:02,697 INFO [train.py:715] (4/8) Epoch 17, batch 20250, loss[loss=0.1134, simple_loss=0.1885, pruned_loss=0.01919, over 4954.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02904, over 973541.76 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 02:17:40,775 INFO [train.py:715] (4/8) Epoch 17, batch 20300, loss[loss=0.1525, simple_loss=0.2224, pruned_loss=0.04131, over 4778.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02931, over 973085.07 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:18:20,511 INFO [train.py:715] (4/8) Epoch 17, batch 20350, loss[loss=0.1473, simple_loss=0.2185, pruned_loss=0.03808, over 4772.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02939, over 973388.73 frames.], batch size: 12, lr: 1.30e-04
2022-05-09 02:19:00,635 INFO [train.py:715] (4/8) Epoch 17, batch 20400, loss[loss=0.1297, simple_loss=0.2044, pruned_loss=0.02747, over 4877.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02923, over 973463.30 frames.], batch size: 22, lr: 1.30e-04
2022-05-09 02:19:39,222 INFO [train.py:715] (4/8) Epoch 17, batch 20450, loss[loss=0.159, simple_loss=0.224, pruned_loss=0.04699, over 4967.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.0295, over 973923.30 frames.], batch size: 39, lr: 1.30e-04
2022-05-09 02:20:17,922 INFO [train.py:715] (4/8) Epoch 17, batch 20500, loss[loss=0.1373, simple_loss=0.212, pruned_loss=0.03127, over 4928.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02941, over 974158.05 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 02:20:57,776 INFO [train.py:715] (4/8) Epoch 17, batch 20550, loss[loss=0.1111, simple_loss=0.1835, pruned_loss=0.01938, over 4815.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2082, pruned_loss=0.02998, over 973535.72 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 02:21:36,910 INFO [train.py:715] (4/8) Epoch 17, batch 20600, loss[loss=0.1391, simple_loss=0.2192, pruned_loss=0.02952, over 4957.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2083, pruned_loss=0.02949, over 973782.68 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 02:22:15,099 INFO [train.py:715] (4/8) Epoch 17, batch 20650, loss[loss=0.1352, simple_loss=0.2209, pruned_loss=0.02478, over 4843.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02949, over 974014.74 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 02:22:54,073 INFO [train.py:715] (4/8) Epoch 17, batch 20700, loss[loss=0.122, simple_loss=0.2011, pruned_loss=0.0215, over 4947.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.0292, over 973573.92 frames.], batch size: 29, lr: 1.30e-04
2022-05-09 02:23:33,732 INFO [train.py:715] (4/8) Epoch 17, batch 20750, loss[loss=0.1342, simple_loss=0.2027, pruned_loss=0.03281, over 4968.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02901, over 972992.00 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 02:24:12,678 INFO [train.py:715] (4/8) Epoch 17, batch 20800, loss[loss=0.1029, simple_loss=0.1735, pruned_loss=0.01612, over 4806.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02884, over 972329.89 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 02:24:51,253 INFO [train.py:715] (4/8) Epoch 17, batch 20850, loss[loss=0.1731, simple_loss=0.2397, pruned_loss=0.05326, over 4841.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02878, over 971901.92 frames.], batch size: 32, lr: 1.30e-04
2022-05-09 02:25:30,262 INFO [train.py:715] (4/8) Epoch 17, batch 20900, loss[loss=0.1218, simple_loss=0.1989, pruned_loss=0.02242, over 4820.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02891, over 972997.79 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 02:26:10,245 INFO [train.py:715] (4/8) Epoch 17, batch 20950, loss[loss=0.1383, simple_loss=0.2111, pruned_loss=0.03279, over 4759.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2055, pruned_loss=0.02865, over 972505.83 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 02:26:48,270 INFO [train.py:715] (4/8) Epoch 17, batch 21000, loss[loss=0.1609, simple_loss=0.2277, pruned_loss=0.04702, over 4825.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02852, over 972795.78 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 02:26:48,270 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 02:27:00,911 INFO [train.py:742] (4/8) Epoch 17, validation: loss=0.1049, simple_loss=0.1882, pruned_loss=0.01077, over 914524.00 frames.
2022-05-09 02:27:38,932 INFO [train.py:715] (4/8) Epoch 17, batch 21050, loss[loss=0.1481, simple_loss=0.2185, pruned_loss=0.03889, over 4954.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.02926, over 972076.97 frames.], batch size: 23, lr: 1.30e-04
2022-05-09 02:28:18,323 INFO [train.py:715] (4/8) Epoch 17, batch 21100, loss[loss=0.1343, simple_loss=0.207, pruned_loss=0.03074, over 4842.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2057, pruned_loss=0.02895, over 971963.90 frames.], batch size: 32, lr: 1.30e-04
2022-05-09 02:28:58,368 INFO [train.py:715] (4/8) Epoch 17, batch 21150, loss[loss=0.1359, simple_loss=0.2166, pruned_loss=0.02763, over 4959.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2053, pruned_loss=0.02876, over 971846.59 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 02:29:37,031 INFO [train.py:715] (4/8) Epoch 17, batch 21200, loss[loss=0.1105, simple_loss=0.1794, pruned_loss=0.0208, over 4894.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.0289, over 972012.71 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:30:15,713 INFO [train.py:715] (4/8) Epoch 17, batch 21250, loss[loss=0.1192, simple_loss=0.2123, pruned_loss=0.01303, over 4911.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.0286, over 972213.43 frames.], batch size: 29, lr: 1.30e-04
2022-05-09 02:30:55,577 INFO [train.py:715] (4/8) Epoch 17, batch 21300, loss[loss=0.09771, simple_loss=0.1719, pruned_loss=0.01178, over 4989.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.0284, over 972361.59 frames.], batch size: 27, lr: 1.30e-04
2022-05-09 02:31:35,364 INFO [train.py:715] (4/8) Epoch 17, batch 21350, loss[loss=0.1545, simple_loss=0.2366, pruned_loss=0.03617, over 4691.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02914, over 972661.40 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 02:32:13,590 INFO [train.py:715] (4/8) Epoch 17, batch 21400, loss[loss=0.1624, simple_loss=0.2409, pruned_loss=0.04195, over 4873.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02871, over 972703.30 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 02:32:53,764 INFO [train.py:715] (4/8) Epoch 17, batch 21450, loss[loss=0.1557, simple_loss=0.2316, pruned_loss=0.03989, over 4821.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02924, over 972907.70 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 02:33:33,555 INFO [train.py:715] (4/8) Epoch 17, batch 21500, loss[loss=0.1138, simple_loss=0.1926, pruned_loss=0.01751, over 4751.00 frames.], tot_loss[loss=0.133, simple_loss=0.2076, pruned_loss=0.02922, over 972855.11 frames.], batch size: 19, lr: 1.30e-04
2022-05-09 02:34:12,048 INFO [train.py:715] (4/8) Epoch 17, batch 21550, loss[loss=0.1413, simple_loss=0.2048, pruned_loss=0.03886, over 4746.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02935, over 973106.47 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 02:34:51,491 INFO [train.py:715] (4/8) Epoch 17, batch 21600, loss[loss=0.1266, simple_loss=0.2043, pruned_loss=0.02443, over 4789.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02955, over 972468.47 frames.], batch size: 18, lr: 1.30e-04
2022-05-09 02:35:31,959 INFO [train.py:715] (4/8) Epoch 17, batch 21650, loss[loss=0.1308, simple_loss=0.2074, pruned_loss=0.02706, over 4949.00 frames.], tot_loss[loss=0.1333, simple_loss=0.208, pruned_loss=0.02927, over 971933.02 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 02:36:11,044 INFO [train.py:715] (4/8) Epoch 17, batch 21700, loss[loss=0.116, simple_loss=0.1866, pruned_loss=0.02267, over 4873.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02958, over 972022.30 frames.], batch size: 16, lr: 1.30e-04
2022-05-09 02:36:49,695 INFO [train.py:715] (4/8) Epoch 17, batch 21750, loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02861, over 4986.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02957, over 973158.72 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 02:37:29,253 INFO [train.py:715] (4/8) Epoch 17, batch 21800, loss[loss=0.1243, simple_loss=0.2008, pruned_loss=0.02389, over 4833.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02944, over 972970.74 frames.], batch size: 26, lr: 1.30e-04
2022-05-09 02:38:08,215 INFO [train.py:715] (4/8) Epoch 17, batch 21850, loss[loss=0.1612, simple_loss=0.2402, pruned_loss=0.0411, over 4898.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02944, over 972636.01 frames.], batch size: 17, lr: 1.30e-04
2022-05-09 02:38:47,461 INFO [train.py:715] (4/8) Epoch 17, batch 21900, loss[loss=0.1279, simple_loss=0.1928, pruned_loss=0.03153, over 4857.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2072, pruned_loss=0.02958, over 971782.77 frames.], batch size: 32, lr: 1.30e-04
2022-05-09 02:39:25,952 INFO [train.py:715] (4/8) Epoch 17, batch 21950, loss[loss=0.13, simple_loss=0.2048, pruned_loss=0.02758, over 4955.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02903, over 971175.06 frames.], batch size: 21, lr: 1.30e-04
2022-05-09 02:40:05,671 INFO [train.py:715] (4/8) Epoch 17, batch 22000, loss[loss=0.144, simple_loss=0.2118, pruned_loss=0.03811, over 4947.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02912, over 971312.59 frames.], batch size: 35, lr: 1.30e-04
2022-05-09 02:40:45,437 INFO [train.py:715] (4/8) Epoch 17, batch 22050, loss[loss=0.09914, simple_loss=0.1724, pruned_loss=0.01295, over 4990.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02859, over 971807.09 frames.], batch size: 27, lr: 1.30e-04
2022-05-09 02:41:23,864 INFO [train.py:715] (4/8) Epoch 17, batch 22100, loss[loss=0.1278, simple_loss=0.2081, pruned_loss=0.02372, over 4816.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02827, over 970977.31 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 02:42:03,599 INFO [train.py:715] (4/8) Epoch 17, batch 22150, loss[loss=0.1061, simple_loss=0.178, pruned_loss=0.01711, over 4831.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02818, over 971445.40 frames.], batch size: 13, lr: 1.30e-04
2022-05-09 02:42:43,485 INFO [train.py:715] (4/8) Epoch 17, batch 22200, loss[loss=0.1281, simple_loss=0.1964, pruned_loss=0.02986, over 4780.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2049, pruned_loss=0.02766, over 971776.23 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 02:43:22,389 INFO [train.py:715] (4/8) Epoch 17, batch 22250, loss[loss=0.1479, simple_loss=0.2085, pruned_loss=0.04362, over 4971.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2055, pruned_loss=0.02779, over 972322.76 frames.], batch size: 24, lr: 1.30e-04
2022-05-09 02:44:01,342 INFO [train.py:715] (4/8) Epoch 17, batch 22300, loss[loss=0.1442, simple_loss=0.213, pruned_loss=0.03775, over 4827.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02805, over 972048.06 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 02:44:41,264 INFO [train.py:715] (4/8) Epoch 17, batch 22350, loss[loss=0.1503, simple_loss=0.2273, pruned_loss=0.0367, over 4864.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02862, over 971687.10 frames.], batch size: 38, lr: 1.30e-04
2022-05-09 02:45:20,837 INFO [train.py:715] (4/8) Epoch 17, batch 22400, loss[loss=0.1493, simple_loss=0.2182, pruned_loss=0.04023, over 4921.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.0298, over 972066.85 frames.], batch size: 23, lr: 1.30e-04
2022-05-09 02:45:59,649 INFO [train.py:715] (4/8) Epoch 17, batch 22450, loss[loss=0.144, simple_loss=0.2208, pruned_loss=0.03356, over 4976.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02954, over 972217.52 frames.], batch size: 28, lr: 1.30e-04
2022-05-09 02:46:38,623 INFO [train.py:715] (4/8) Epoch 17, batch 22500, loss[loss=0.1227, simple_loss=0.1932, pruned_loss=0.0261, over 4860.00 frames.], tot_loss[loss=0.1325, simple_loss=0.206, pruned_loss=0.02944, over 972001.91 frames.], batch size: 20, lr: 1.30e-04
2022-05-09 02:47:18,396 INFO [train.py:715] (4/8) Epoch 17, batch 22550, loss[loss=0.1267, simple_loss=0.2005, pruned_loss=0.02644, over 4935.00 frames.], tot_loss[loss=0.133, simple_loss=0.2066, pruned_loss=0.02964, over 973167.31 frames.], batch size: 23, lr: 1.30e-04
2022-05-09 02:47:56,724 INFO [train.py:715] (4/8) Epoch 17, batch 22600, loss[loss=0.1307, simple_loss=0.212, pruned_loss=0.0247, over 4718.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02905, over 972861.39 frames.], batch size: 12, lr: 1.30e-04
2022-05-09 02:48:36,266 INFO [train.py:715] (4/8) Epoch 17, batch 22650, loss[loss=0.1254, simple_loss=0.1944, pruned_loss=0.02817, over 4808.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02887, over 972859.55 frames.], batch size: 25, lr: 1.30e-04
2022-05-09 02:49:15,733 INFO [train.py:715] (4/8) Epoch 17, batch 22700, loss[loss=0.142, simple_loss=0.2115, pruned_loss=0.03623, over 4974.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02886, over 973509.75 frames.], batch size: 14, lr: 1.30e-04
2022-05-09 02:49:54,663 INFO [train.py:715] (4/8) Epoch 17, batch 22750, loss[loss=0.1246, simple_loss=0.1917, pruned_loss=0.02872, over 4695.00 frames.], tot_loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02871, over 973575.09 frames.], batch size: 15, lr: 1.30e-04
2022-05-09 02:50:33,047 INFO [train.py:715] (4/8) Epoch 17, batch 22800, loss[loss=0.1422, simple_loss=0.2188, pruned_loss=0.03278, over 4977.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02902, over 972782.45 frames.], batch size: 28, lr: 1.30e-04
2022-05-09 02:51:12,440 INFO [train.py:715] (4/8) Epoch 17, batch 22850, loss[loss=0.1312, simple_loss=0.2113, pruned_loss=0.02553, over 4908.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.0293, over 972629.50 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 02:51:52,337 INFO [train.py:715] (4/8) Epoch 17, batch 22900, loss[loss=0.1034, simple_loss=0.1815, pruned_loss=0.01265, over 4890.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02964, over 972236.84 frames.], batch size: 22, lr: 1.29e-04
2022-05-09 02:52:30,188 INFO [train.py:715] (4/8) Epoch 17, batch 22950, loss[loss=0.1334, simple_loss=0.2098, pruned_loss=0.02851, over 4939.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2082, pruned_loss=0.02958, over 972095.85 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 02:53:10,084 INFO [train.py:715] (4/8) Epoch 17, batch 23000, loss[loss=0.1377, simple_loss=0.2081, pruned_loss=0.0336, over 4851.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.0295, over 972302.14 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 02:53:50,346 INFO [train.py:715] (4/8) Epoch 17, batch 23050, loss[loss=0.1281, simple_loss=0.2134, pruned_loss=0.02138, over 4897.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02912, over 973233.07 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 02:54:29,510 INFO [train.py:715] (4/8) Epoch 17, batch 23100, loss[loss=0.1085, simple_loss=0.1839, pruned_loss=0.01659, over 4776.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02903, over 973343.26 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 02:55:07,924 INFO [train.py:715] (4/8) Epoch 17, batch 23150, loss[loss=0.1106, simple_loss=0.1871, pruned_loss=0.01708, over 4810.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02893, over 973063.50 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 02:55:47,707 INFO [train.py:715] (4/8) Epoch 17, batch 23200, loss[loss=0.1273, simple_loss=0.2013, pruned_loss=0.02664, over 4761.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02898, over 973216.00 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 02:56:27,703 INFO [train.py:715] (4/8) Epoch 17, batch 23250, loss[loss=0.1427, simple_loss=0.2036, pruned_loss=0.04089, over 4861.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02883, over 973224.77 frames.], batch size: 30, lr: 1.29e-04
2022-05-09 02:57:05,643 INFO [train.py:715] (4/8) Epoch 17, batch 23300, loss[loss=0.112, simple_loss=0.1934, pruned_loss=0.0153, over 4941.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2056, pruned_loss=0.02882, over 972838.57 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 02:57:44,993 INFO [train.py:715] (4/8) Epoch 17, batch 23350, loss[loss=0.1211, simple_loss=0.1952, pruned_loss=0.02348, over 4937.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02885, over 972582.97 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 02:58:25,086 INFO [train.py:715] (4/8) Epoch 17, batch 23400, loss[loss=0.1138, simple_loss=0.1848, pruned_loss=0.02136, over 4785.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.0288, over 971934.37 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 02:59:03,871 INFO [train.py:715] (4/8) Epoch 17, batch 23450, loss[loss=0.13, simple_loss=0.209, pruned_loss=0.02544, over 4976.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02867, over 971937.70 frames.], batch size: 31, lr: 1.29e-04
2022-05-09 02:59:42,965 INFO [train.py:715] (4/8) Epoch 17, batch 23500, loss[loss=0.1413, simple_loss=0.2143, pruned_loss=0.03413, over 4922.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02856, over 972324.16 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 03:00:22,296 INFO [train.py:715] (4/8) Epoch 17, batch 23550, loss[loss=0.1174, simple_loss=0.1945, pruned_loss=0.02018, over 4937.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.02812, over 973500.27 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:01:01,966 INFO [train.py:715] (4/8) Epoch 17, batch 23600, loss[loss=0.1455, simple_loss=0.2273, pruned_loss=0.03185, over 4808.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02848, over 973479.32 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:01:40,305 INFO [train.py:715] (4/8) Epoch 17, batch 23650, loss[loss=0.1473, simple_loss=0.2193, pruned_loss=0.03765, over 4931.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02892, over 974276.08 frames.], batch size: 39, lr: 1.29e-04
2022-05-09 03:02:19,918 INFO [train.py:715] (4/8) Epoch 17, batch 23700, loss[loss=0.1531, simple_loss=0.2198, pruned_loss=0.04318, over 4832.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.0291, over 973628.02 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 03:02:59,508 INFO [train.py:715] (4/8) Epoch 17, batch 23750, loss[loss=0.161, simple_loss=0.2316, pruned_loss=0.04523, over 4971.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02887, over 973743.08 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:03:38,384 INFO [train.py:715] (4/8) Epoch 17, batch 23800, loss[loss=0.1133, simple_loss=0.1905, pruned_loss=0.01805, over 4967.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02882, over 973350.76 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:04:16,663 INFO [train.py:715] (4/8) Epoch 17, batch 23850, loss[loss=0.1258, simple_loss=0.2085, pruned_loss=0.02159, over 4812.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02893, over 972718.93 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:04:56,706 INFO [train.py:715] (4/8) Epoch 17, batch 23900, loss[loss=0.1358, simple_loss=0.2146, pruned_loss=0.0285, over 4925.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02879, over 971622.94 frames.], batch size: 23, lr: 1.29e-04
2022-05-09 03:05:35,870 INFO [train.py:715] (4/8) Epoch 17, batch 23950, loss[loss=0.1184, simple_loss=0.1861, pruned_loss=0.02532, over 4821.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02893, over 971175.53 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:06:14,199 INFO [train.py:715] (4/8) Epoch 17, batch 24000, loss[loss=0.1688, simple_loss=0.2397, pruned_loss=0.04892, over 4982.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02945, over 971126.01 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:06:14,200 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 03:06:24,067 INFO [train.py:742] (4/8) Epoch 17, validation: loss=0.1047, simple_loss=0.1881, pruned_loss=0.01067, over 914524.00 frames.
2022-05-09 03:07:02,581 INFO [train.py:715] (4/8) Epoch 17, batch 24050, loss[loss=0.1258, simple_loss=0.206, pruned_loss=0.02279, over 4768.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02905, over 971212.40 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:07:41,974 INFO [train.py:715] (4/8) Epoch 17, batch 24100, loss[loss=0.1241, simple_loss=0.2046, pruned_loss=0.02178, over 4767.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02881, over 971819.07 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:08:22,153 INFO [train.py:715] (4/8) Epoch 17, batch 24150, loss[loss=0.1138, simple_loss=0.1887, pruned_loss=0.01945, over 4993.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02911, over 972761.67 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:09:00,901 INFO [train.py:715] (4/8) Epoch 17, batch 24200, loss[loss=0.1297, simple_loss=0.2003, pruned_loss=0.02951, over 4851.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.0288, over 973049.65 frames.], batch size: 12, lr: 1.29e-04
2022-05-09 03:09:42,456 INFO [train.py:715] (4/8) Epoch 17, batch 24250, loss[loss=0.155, simple_loss=0.2249, pruned_loss=0.04254, over 4872.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02823, over 973173.45 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 03:10:23,057 INFO [train.py:715] (4/8) Epoch 17, batch 24300, loss[loss=0.128, simple_loss=0.2, pruned_loss=0.02802, over 4823.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02872, over 973190.50 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 03:11:02,616 INFO [train.py:715] (4/8) Epoch 17, batch 24350, loss[loss=0.1316, simple_loss=0.2094, pruned_loss=0.02692, over 4979.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02853, over 972911.32 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:11:41,992 INFO [train.py:715] (4/8) Epoch 17, batch 24400, loss[loss=0.1335, simple_loss=0.2083, pruned_loss=0.0293, over 4983.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02808, over 974000.33 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:12:21,144 INFO [train.py:715] (4/8) Epoch 17, batch 24450, loss[loss=0.1148, simple_loss=0.1864, pruned_loss=0.02162, over 4853.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02843, over 973600.78 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 03:13:01,330 INFO [train.py:715] (4/8) Epoch 17, batch 24500, loss[loss=0.1402, simple_loss=0.219, pruned_loss=0.0307, over 4890.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02887, over 973498.57 frames.], batch size: 22, lr: 1.29e-04
2022-05-09 03:13:40,455 INFO [train.py:715] (4/8) Epoch 17, batch 24550, loss[loss=0.1415, simple_loss=0.2128, pruned_loss=0.03509, over 4801.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02897, over 973896.94 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:14:19,284 INFO [train.py:715] (4/8) Epoch 17, batch 24600, loss[loss=0.1466, simple_loss=0.2178, pruned_loss=0.03768, over 4948.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.0292, over 972649.28 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:14:59,436 INFO [train.py:715] (4/8) Epoch 17, batch 24650, loss[loss=0.1198, simple_loss=0.195, pruned_loss=0.02229, over 4812.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02922, over 972818.80 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:15:39,738 INFO [train.py:715] (4/8) Epoch 17, batch 24700, loss[loss=0.1321, simple_loss=0.2096, pruned_loss=0.02727, over 4970.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02916, over 972601.78 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:16:18,261 INFO [train.py:715] (4/8) Epoch 17, batch 24750, loss[loss=0.1366, simple_loss=0.2025, pruned_loss=0.03534, over 4857.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02925, over 971889.69 frames.], batch size: 32, lr: 1.29e-04
2022-05-09 03:16:58,087 INFO [train.py:715] (4/8) Epoch 17, batch 24800, loss[loss=0.1147, simple_loss=0.1906, pruned_loss=0.01943, over 4935.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02935, over 972722.20 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 03:17:37,937 INFO [train.py:715] (4/8) Epoch 17, batch 24850, loss[loss=0.114, simple_loss=0.1886, pruned_loss=0.0197, over 4792.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.0296, over 972689.79 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 03:18:17,564 INFO [train.py:715] (4/8) Epoch 17, batch 24900, loss[loss=0.129, simple_loss=0.2137, pruned_loss=0.02218, over 4809.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02939, over 972080.30 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:18:56,116 INFO [train.py:715] (4/8) Epoch 17, batch 24950, loss[loss=0.1103, simple_loss=0.1916, pruned_loss=0.01452, over 4879.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02934, over 972109.72 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:19:35,619 INFO [train.py:715] (4/8) Epoch 17, batch 25000, loss[loss=0.119, simple_loss=0.1893, pruned_loss=0.0244, over 4916.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.0294, over 971488.66 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 03:20:14,002 INFO [train.py:715] (4/8) Epoch 17, batch 25050, loss[loss=0.1273, simple_loss=0.2086, pruned_loss=0.023, over 4835.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02932, over 971720.11 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 03:20:52,999 INFO [train.py:715] (4/8) Epoch 17, batch 25100, loss[loss=0.1276, simple_loss=0.199, pruned_loss=0.02806, over 4845.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2087, pruned_loss=0.02973, over 972554.91 frames.], batch size: 32, lr: 1.29e-04
2022-05-09 03:21:32,980 INFO [train.py:715] (4/8) Epoch 17, batch 25150, loss[loss=0.1215, simple_loss=0.1949, pruned_loss=0.02401, over 4988.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2081, pruned_loss=0.02946, over 971803.10 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:22:12,872 INFO [train.py:715] (4/8) Epoch 17, batch 25200, loss[loss=0.1278, simple_loss=0.2001, pruned_loss=0.02777, over 4932.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02914, over 971367.08 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:22:51,915 INFO [train.py:715] (4/8) Epoch 17, batch 25250, loss[loss=0.1156, simple_loss=0.1943, pruned_loss=0.01849, over 4811.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02921, over 971182.52 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:23:31,035 INFO [train.py:715] (4/8) Epoch 17, batch 25300, loss[loss=0.1359, simple_loss=0.2074, pruned_loss=0.03222, over 4988.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.029, over 970683.24 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:24:11,040 INFO [train.py:715] (4/8) Epoch 17, batch 25350, loss[loss=0.1176, simple_loss=0.1916, pruned_loss=0.02179, over 4974.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02911, over 970440.01 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:24:49,784 INFO [train.py:715] (4/8) Epoch 17, batch 25400, loss[loss=0.1491, simple_loss=0.2215, pruned_loss=0.03837, over 4804.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02931, over 970674.10 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:25:28,940 INFO [train.py:715] (4/8) Epoch 17, batch 25450, loss[loss=0.1315, simple_loss=0.2077, pruned_loss=0.02765, over 4885.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02931, over 971146.86 frames.], batch size: 22, lr: 1.29e-04
2022-05-09 03:26:08,063 INFO [train.py:715] (4/8) Epoch 17, batch 25500, loss[loss=0.1314, simple_loss=0.2001, pruned_loss=0.03129, over 4830.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02888, over 970843.04 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:26:47,843 INFO [train.py:715] (4/8) Epoch 17, batch 25550, loss[loss=0.1513, simple_loss=0.2177, pruned_loss=0.04243, over 4810.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02895, over 969846.30 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:27:26,917 INFO [train.py:715] (4/8) Epoch 17, batch 25600, loss[loss=0.1344, simple_loss=0.2025, pruned_loss=0.03319, over 4849.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.0289, over 970059.86 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 03:28:05,427 INFO [train.py:715] (4/8) Epoch 17, batch 25650, loss[loss=0.1186, simple_loss=0.1957, pruned_loss=0.02073, over 4783.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02892, over 969909.04 frames.], batch size: 12, lr: 1.29e-04
2022-05-09 03:28:45,198 INFO [train.py:715] (4/8) Epoch 17, batch 25700, loss[loss=0.1167, simple_loss=0.1957, pruned_loss=0.01881, over 4701.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02918, over 968975.44 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:29:24,288 INFO [train.py:715] (4/8) Epoch 17, batch 25750, loss[loss=0.1618, simple_loss=0.2341, pruned_loss=0.04478, over 4827.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02885, over 969018.43 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:30:03,681 INFO [train.py:715] (4/8) Epoch 17, batch 25800, loss[loss=0.1416, simple_loss=0.2229, pruned_loss=0.03013, over 4936.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02853, over 969251.65 frames.], batch size: 23, lr: 1.29e-04
2022-05-09 03:30:43,161 INFO [train.py:715] (4/8) Epoch 17, batch 25850, loss[loss=0.1428, simple_loss=0.2102, pruned_loss=0.0377, over 4902.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02828, over 969385.02 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 03:31:22,524 INFO [train.py:715] (4/8) Epoch 17, batch 25900, loss[loss=0.1416, simple_loss=0.2193, pruned_loss=0.03193, over 4969.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.0283, over 970413.15 frames.], batch size: 35, lr: 1.29e-04
2022-05-09 03:32:01,051 INFO [train.py:715] (4/8) Epoch 17, batch 25950, loss[loss=0.1382, simple_loss=0.2093, pruned_loss=0.03357, over 4987.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02831, over 970792.48 frames.], batch size: 33, lr: 1.29e-04
2022-05-09 03:32:39,483 INFO [train.py:715] (4/8) Epoch 17, batch 26000, loss[loss=0.1274, simple_loss=0.1985, pruned_loss=0.02814, over 4902.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02884, over 971209.57 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 03:33:19,121 INFO [train.py:715] (4/8) Epoch 17, batch 26050, loss[loss=0.1426, simple_loss=0.2143, pruned_loss=0.03543, over 4814.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02923, over 971028.03 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:33:57,727 INFO [train.py:715] (4/8) Epoch 17, batch 26100, loss[loss=0.1268, simple_loss=0.2039, pruned_loss=0.02491, over 4756.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02932, over 971509.36 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:34:37,124 INFO [train.py:715] (4/8) Epoch 17, batch 26150, loss[loss=0.1168, simple_loss=0.1971, pruned_loss=0.01825, over 4933.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02941, over 971735.01 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:35:16,508 INFO [train.py:715] (4/8) Epoch 17, batch 26200, loss[loss=0.1074, simple_loss=0.1795, pruned_loss=0.01768, over 4746.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02901, over 972121.65 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:35:56,477 INFO [train.py:715] (4/8) Epoch 17, batch 26250, loss[loss=0.1395, simple_loss=0.2123, pruned_loss=0.03331, over 4799.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02856, over 971856.65 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:36:35,146 INFO [train.py:715] (4/8) Epoch 17, batch 26300, loss[loss=0.1258, simple_loss=0.1981, pruned_loss=0.02679, over 4795.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02854, over 971757.98 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:37:13,922 INFO [train.py:715] (4/8) Epoch 17, batch 26350, loss[loss=0.1303, simple_loss=0.2066, pruned_loss=0.02702, over 4807.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02861, over 971552.01 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 03:37:53,865 INFO [train.py:715] (4/8) Epoch 17, batch 26400, loss[loss=0.1502, simple_loss=0.2201, pruned_loss=0.04021, over 4798.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02889, over 972455.45 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:38:32,580 INFO [train.py:715] (4/8) Epoch 17, batch 26450, loss[loss=0.1115, simple_loss=0.1872, pruned_loss=0.01786, over 4968.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2055, pruned_loss=0.02898, over 972240.14 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:39:11,787 INFO [train.py:715] (4/8) Epoch 17, batch 26500, loss[loss=0.1285, simple_loss=0.2137, pruned_loss=0.02169, over 4704.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2054, pruned_loss=0.02887, over 971694.82 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:39:51,010 INFO [train.py:715] (4/8) Epoch 17, batch 26550, loss[loss=0.1552, simple_loss=0.2257, pruned_loss=0.04237, over 4723.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02889, over 971481.49 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 03:40:29,942 INFO [train.py:715] (4/8) Epoch 17, batch 26600, loss[loss=0.1236, simple_loss=0.1993, pruned_loss=0.02396, over 4826.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02915, over 972241.95 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 03:41:08,353 INFO [train.py:715] (4/8) Epoch 17, batch 26650, loss[loss=0.1391, simple_loss=0.2112, pruned_loss=0.03344, over 4905.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02909, over 972364.54 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 03:41:47,385 INFO [train.py:715] (4/8) Epoch 17, batch 26700, loss[loss=0.1544, simple_loss=0.2249, pruned_loss=0.04196, over 4848.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02919, over 971975.26 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 03:42:26,792 INFO [train.py:715] (4/8) Epoch 17, batch 26750, loss[loss=0.142, simple_loss=0.2143, pruned_loss=0.03486, over 4807.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02935, over 972379.84 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:43:05,134 INFO [train.py:715] (4/8) Epoch 17, batch 26800, loss[loss=0.1267, simple_loss=0.1997, pruned_loss=0.0269, over 4813.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02962, over 972569.84 frames.], batch size: 27, lr: 1.29e-04
2022-05-09 03:43:43,932 INFO [train.py:715] (4/8) Epoch 17, batch 26850, loss[loss=0.144, simple_loss=0.2181, pruned_loss=0.03497, over 4647.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02945, over 972121.18 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 03:44:23,812 INFO [train.py:715] (4/8) Epoch 17, batch 26900, loss[loss=0.1166, simple_loss=0.1898, pruned_loss=0.02168, over 4806.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.0296, over 971983.34 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 03:45:02,980 INFO [train.py:715] (4/8) Epoch 17, batch 26950, loss[loss=0.1354, simple_loss=0.2131, pruned_loss=0.0289, over 4968.00 frames.], tot_loss[loss=0.1341, simple_loss=0.208, pruned_loss=0.03008, over 972100.06 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:45:41,693 INFO [train.py:715] (4/8) Epoch 17, batch 27000, loss[loss=0.1661, simple_loss=0.2245, pruned_loss=0.0539, over 4783.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02985, over 971717.21 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 03:45:41,693 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 03:45:51,478 INFO [train.py:742] (4/8) Epoch 17, validation: loss=0.1047, simple_loss=0.188, pruned_loss=0.0107, over 914524.00 frames.
2022-05-09 03:46:30,447 INFO [train.py:715] (4/8) Epoch 17, batch 27050, loss[loss=0.1227, simple_loss=0.2014, pruned_loss=0.02199, over 4819.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2085, pruned_loss=0.03016, over 971003.90 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 03:47:09,963 INFO [train.py:715] (4/8) Epoch 17, batch 27100, loss[loss=0.1147, simple_loss=0.1811, pruned_loss=0.02414, over 4990.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02984, over 971723.83 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 03:47:49,459 INFO [train.py:715] (4/8) Epoch 17, batch 27150, loss[loss=0.1584, simple_loss=0.2427, pruned_loss=0.03701, over 4785.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02931, over 971994.88 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 03:48:27,663 INFO [train.py:715] (4/8) Epoch 17, batch 27200, loss[loss=0.1144, simple_loss=0.1747, pruned_loss=0.02707, over 4980.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02887, over 972154.83 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:49:06,449 INFO [train.py:715] (4/8) Epoch 17, batch 27250, loss[loss=0.1169, simple_loss=0.1915, pruned_loss=0.0211, over 4765.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02889, over 972585.13 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:49:46,078 INFO [train.py:715] (4/8) Epoch 17, batch 27300, loss[loss=0.1252, simple_loss=0.2114, pruned_loss=0.01946, over 4911.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02938, over 972024.39 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 03:50:25,158 INFO [train.py:715] (4/8) Epoch 17, batch 27350, loss[loss=0.1152, simple_loss=0.1925, pruned_loss=0.01901, over 4941.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02925, over 972119.28 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 03:51:04,597 INFO [train.py:715] (4/8) Epoch 17, batch 27400, loss[loss=0.1362, simple_loss=0.2179, pruned_loss=0.02724, over 4873.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2079, pruned_loss=0.02918, over 972400.78 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 03:51:43,497 INFO [train.py:715] (4/8) Epoch 17, batch 27450, loss[loss=0.1293, simple_loss=0.2002, pruned_loss=0.02924, over 4806.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2091, pruned_loss=0.02989, over 972107.21 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 03:52:23,142 INFO [train.py:715] (4/8) Epoch 17, batch 27500, loss[loss=0.1395, simple_loss=0.205, pruned_loss=0.03702, over 4747.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2081, pruned_loss=0.02969, over 971734.53 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 03:53:01,812 INFO [train.py:715] (4/8) Epoch 17, batch 27550, loss[loss=0.1449, simple_loss=0.2099, pruned_loss=0.03994, over 4960.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2078, pruned_loss=0.02978, over 971861.77 frames.], batch size: 35, lr: 1.29e-04
2022-05-09 03:53:40,307 INFO [train.py:715] (4/8) Epoch 17, batch 27600, loss[loss=0.1095, simple_loss=0.1822, pruned_loss=0.01845, over 4978.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2079, pruned_loss=0.02984, over 971440.04 frames.], batch size: 28, lr: 1.29e-04
2022-05-09 03:54:19,258 INFO [train.py:715] (4/8) Epoch 17, batch 27650, loss[loss=0.1184, simple_loss=0.1983, pruned_loss=0.01928, over 4836.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.0297, over 972070.35 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 03:54:57,853 INFO [train.py:715] (4/8) Epoch 17, batch 27700, loss[loss=0.1517, simple_loss=0.2173, pruned_loss=0.04306, over 4865.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02924, over 972532.96 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 03:55:37,196 INFO [train.py:715] (4/8) Epoch 17, batch 27750, loss[loss=0.1216, simple_loss=0.2056, pruned_loss=0.01877, over 4909.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02937, over 971418.90 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 03:56:16,929 INFO [train.py:715] (4/8) Epoch 17, batch 27800, loss[loss=0.1682, simple_loss=0.24, pruned_loss=0.04813, over 4851.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02973, over 971985.70 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 03:56:57,499 INFO [train.py:715] (4/8) Epoch 17, batch 27850, loss[loss=0.1432, simple_loss=0.2153, pruned_loss=0.03553, over 4896.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02951, over 972484.96 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 03:57:37,297 INFO [train.py:715] (4/8) Epoch 17, batch 27900, loss[loss=0.1389, simple_loss=0.2158, pruned_loss=0.031, over 4809.00 frames.], tot_loss[loss=0.1334, simple_loss=0.208, pruned_loss=0.02938, over 973152.33 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 03:58:16,571 INFO [train.py:715] (4/8) Epoch 17, batch 27950, loss[loss=0.1313, simple_loss=0.1957, pruned_loss=0.03347, over 4831.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2079, pruned_loss=0.02965, over 972439.21 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 03:58:56,530 INFO [train.py:715] (4/8) Epoch 17, batch 28000, loss[loss=0.1343, simple_loss=0.2181, pruned_loss=0.02525, over 4929.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02951, over 972422.48 frames.], batch size: 23, lr: 1.29e-04
2022-05-09 03:59:36,540 INFO [train.py:715] (4/8) Epoch 17, batch 28050, loss[loss=0.1385, simple_loss=0.2144, pruned_loss=0.03129, over 4696.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.0291, over 971873.90 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:00:15,251 INFO [train.py:715] (4/8) Epoch 17, batch 28100, loss[loss=0.1513, simple_loss=0.2155, pruned_loss=0.0436, over 4863.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02919, over 971810.30 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 04:00:54,614 INFO [train.py:715] (4/8) Epoch 17, batch 28150, loss[loss=0.1499, simple_loss=0.2148, pruned_loss=0.04253, over 4861.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02918, over 971867.91 frames.], batch size: 32, lr: 1.29e-04
2022-05-09 04:01:33,613 INFO [train.py:715] (4/8) Epoch 17, batch 28200, loss[loss=0.1615, simple_loss=0.2339, pruned_loss=0.04459, over 4702.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02934, over 971137.78 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:02:12,001 INFO [train.py:715] (4/8) Epoch 17, batch 28250, loss[loss=0.1419, simple_loss=0.2205, pruned_loss=0.03169, over 4849.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02949, over 971878.09 frames.], batch size: 32, lr: 1.29e-04
2022-05-09 04:02:50,452 INFO [train.py:715] (4/8) Epoch 17, batch 28300, loss[loss=0.1474, simple_loss=0.208, pruned_loss=0.04337, over 4818.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2078, pruned_loss=0.02969, over 971278.42 frames.], batch size: 12, lr: 1.29e-04
2022-05-09 04:03:29,616 INFO [train.py:715] (4/8) Epoch 17, batch 28350, loss[loss=0.1285, simple_loss=0.2118, pruned_loss=0.02257, over 4750.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02931, over 971439.86 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 04:04:09,193 INFO [train.py:715] (4/8) Epoch 17, batch 28400, loss[loss=0.1207, simple_loss=0.1927, pruned_loss=0.0244, over 4974.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02927, over 972227.19 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 04:04:48,213 INFO [train.py:715] (4/8) Epoch 17, batch 28450, loss[loss=0.1232, simple_loss=0.2078, pruned_loss=0.01926, over 4897.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2084, pruned_loss=0.02972, over 971870.19 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 04:05:26,442 INFO [train.py:715] (4/8) Epoch 17, batch 28500, loss[loss=0.1156, simple_loss=0.1986, pruned_loss=0.01626, over 4909.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2085, pruned_loss=0.02958, over 971971.20 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 04:06:06,462 INFO [train.py:715] (4/8) Epoch 17, batch 28550, loss[loss=0.1439, simple_loss=0.218, pruned_loss=0.03485, over 4775.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02921, over 971934.85 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:06:45,102 INFO [train.py:715] (4/8) Epoch 17, batch 28600, loss[loss=0.1664, simple_loss=0.2346, pruned_loss=0.04912, over 4899.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02957, over 972844.45 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 04:07:23,874 INFO [train.py:715] (4/8) Epoch 17, batch 28650, loss[loss=0.1021, simple_loss=0.1847, pruned_loss=0.009752, over 4982.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.0296, over 972924.99 frames.], batch size: 28, lr: 1.29e-04
2022-05-09 04:08:02,258 INFO [train.py:715] (4/8) Epoch 17, batch 28700, loss[loss=0.1295, simple_loss=0.2198, pruned_loss=0.01953, over 4811.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02984, over 972933.10 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 04:08:41,576 INFO [train.py:715] (4/8) Epoch 17, batch 28750, loss[loss=0.1395, simple_loss=0.2102, pruned_loss=0.0344, over 4969.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2073, pruned_loss=0.02958, over 972876.81 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:09:20,209 INFO [train.py:715] (4/8) Epoch 17, batch 28800, loss[loss=0.1175, simple_loss=0.1884, pruned_loss=0.02335, over 4948.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02945, over 972477.95 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 04:09:58,905 INFO [train.py:715] (4/8) Epoch 17, batch 28850, loss[loss=0.1683, simple_loss=0.2447, pruned_loss=0.04594, over 4983.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2065, pruned_loss=0.02966, over 972983.28 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 04:10:37,994 INFO [train.py:715] (4/8) Epoch 17, batch 28900, loss[loss=0.1208, simple_loss=0.193, pruned_loss=0.02427, over 4981.00 frames.], tot_loss[loss=0.132, simple_loss=0.2058, pruned_loss=0.02909, over 973507.16 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:11:16,523 INFO [train.py:715] (4/8) Epoch 17, batch 28950, loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02954, over 4803.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02945, over 973722.43 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 04:11:54,927 INFO [train.py:715] (4/8) Epoch 17, batch 29000, loss[loss=0.1453, simple_loss=0.2081, pruned_loss=0.04125, over 4753.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02899, over 973897.54 frames.], batch size: 19, lr: 1.29e-04
2022-05-09 04:12:33,659 INFO [train.py:715] (4/8) Epoch 17, batch 29050, loss[loss=0.1309, simple_loss=0.2088, pruned_loss=0.02655, over 4866.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.0291, over 972410.51 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 04:13:13,023 INFO [train.py:715] (4/8) Epoch 17, batch 29100, loss[loss=0.1319, simple_loss=0.1919, pruned_loss=0.03594, over 4978.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.0291, over 972447.11 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:13:51,908 INFO [train.py:715] (4/8) Epoch 17, batch 29150, loss[loss=0.1612, simple_loss=0.2248, pruned_loss=0.04883, over 4989.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02928, over 972789.69 frames.], batch size: 31, lr: 1.29e-04
2022-05-09 04:14:30,016 INFO [train.py:715] (4/8) Epoch 17, batch 29200, loss[loss=0.1259, simple_loss=0.1966, pruned_loss=0.02765, over 4840.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02879, over 973775.79 frames.], batch size: 30, lr: 1.29e-04
2022-05-09 04:15:09,521 INFO [train.py:715] (4/8) Epoch 17, batch 29250, loss[loss=0.1406, simple_loss=0.2099, pruned_loss=0.03567, over 4941.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.029, over 973159.67 frames.], batch size: 23, lr: 1.29e-04
2022-05-09 04:15:49,145 INFO [train.py:715] (4/8) Epoch 17, batch 29300, loss[loss=0.1401, simple_loss=0.2214, pruned_loss=0.0294, over 4795.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02914, over 972857.78 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 04:16:27,572 INFO [train.py:715] (4/8) Epoch 17, batch 29350, loss[loss=0.1274, simple_loss=0.2009, pruned_loss=0.02697, over 4868.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02922, over 972338.58 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 04:17:06,161 INFO [train.py:715] (4/8) Epoch 17, batch 29400, loss[loss=0.1174, simple_loss=0.1887, pruned_loss=0.02305, over 4820.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02897, over 973083.22 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 04:17:45,843 INFO [train.py:715] (4/8) Epoch 17, batch 29450, loss[loss=0.1562, simple_loss=0.2414, pruned_loss=0.03551, over 4795.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.029, over 972141.75 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 04:18:24,965 INFO [train.py:715] (4/8) Epoch 17, batch 29500, loss[loss=0.1658, simple_loss=0.2279, pruned_loss=0.05188, over 4963.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02906, over 972699.92 frames.], batch size: 24, lr: 1.29e-04
2022-05-09 04:19:03,885 INFO [train.py:715] (4/8) Epoch 17, batch 29550, loss[loss=0.1305, simple_loss=0.21, pruned_loss=0.02549, over 4984.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02845, over 971875.84 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 04:19:43,165 INFO [train.py:715] (4/8) Epoch 17, batch 29600, loss[loss=0.1204, simple_loss=0.2037, pruned_loss=0.01852, over 4958.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.02798, over 971240.51 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:20:22,740 INFO [train.py:715] (4/8) Epoch 17, batch 29650, loss[loss=0.1247, simple_loss=0.1971, pruned_loss=0.02617, over 4914.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02839, over 972377.15 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 04:21:01,516 INFO [train.py:715] (4/8) Epoch 17, batch 29700, loss[loss=0.1713, simple_loss=0.2223, pruned_loss=0.06016, over 4765.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02855, over 971998.84 frames.], batch size: 12, lr: 1.29e-04
2022-05-09 04:21:40,465 INFO [train.py:715] (4/8) Epoch 17, batch 29750, loss[loss=0.1635, simple_loss=0.2308, pruned_loss=0.04811, over 4970.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02886, over 971926.87 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:22:20,621 INFO [train.py:715] (4/8) Epoch 17, batch 29800, loss[loss=0.134, simple_loss=0.2049, pruned_loss=0.03157, over 4942.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02887, over 971422.23 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 04:22:59,614 INFO [train.py:715] (4/8) Epoch 17, batch 29850, loss[loss=0.1608, simple_loss=0.2289, pruned_loss=0.04633, over 4899.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.029, over 970957.04 frames.], batch size: 39, lr: 1.29e-04
2022-05-09 04:23:38,912 INFO [train.py:715] (4/8) Epoch 17, batch 29900, loss[loss=0.1477, simple_loss=0.214, pruned_loss=0.04074, over 4807.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02904, over 971008.68 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 04:24:18,622 INFO [train.py:715] (4/8) Epoch 17, batch 29950, loss[loss=0.1453, simple_loss=0.2209, pruned_loss=0.03482, over 4915.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02895, over 971669.03 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 04:24:58,029 INFO [train.py:715] (4/8) Epoch 17, batch 30000, loss[loss=0.1296, simple_loss=0.1972, pruned_loss=0.03102, over 4974.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2075, pruned_loss=0.02886, over 971698.40 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:24:58,030 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 04:25:08,260 INFO [train.py:742] (4/8) Epoch 17, validation: loss=0.1047, simple_loss=0.188, pruned_loss=0.01065, over 914524.00 frames.
2022-05-09 04:25:48,090 INFO [train.py:715] (4/8) Epoch 17, batch 30050, loss[loss=0.1473, simple_loss=0.2168, pruned_loss=0.03888, over 4806.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2078, pruned_loss=0.02924, over 971433.74 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 04:26:27,726 INFO [train.py:715] (4/8) Epoch 17, batch 30100, loss[loss=0.1212, simple_loss=0.1945, pruned_loss=0.02399, over 4950.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2081, pruned_loss=0.02912, over 971741.57 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 04:27:06,815 INFO [train.py:715] (4/8) Epoch 17, batch 30150, loss[loss=0.1326, simple_loss=0.2125, pruned_loss=0.02634, over 4955.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02913, over 972321.42 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 04:27:46,312 INFO [train.py:715] (4/8) Epoch 17, batch 30200, loss[loss=0.126, simple_loss=0.2037, pruned_loss=0.02414, over 4811.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2069, pruned_loss=0.02862, over 971355.62 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 04:28:25,422 INFO [train.py:715] (4/8) Epoch 17, batch 30250, loss[loss=0.1128, simple_loss=0.2039, pruned_loss=0.01083, over 4809.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2074, pruned_loss=0.02858, over 971985.58 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 04:29:04,422 INFO [train.py:715] (4/8) Epoch 17, batch 30300, loss[loss=0.1, simple_loss=0.1697, pruned_loss=0.01519, over 4859.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2076, pruned_loss=0.02877, over 972463.31 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 04:29:44,186 INFO [train.py:715] (4/8) Epoch 17, batch 30350, loss[loss=0.1398, simple_loss=0.2083, pruned_loss=0.03568, over 4782.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.0285, over 972221.25 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 04:30:23,369 INFO [train.py:715] (4/8) Epoch 17, batch 30400, loss[loss=0.1592, simple_loss=0.2291, pruned_loss=0.04465, over 4879.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.02881, over 972197.11 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 04:31:02,091 INFO [train.py:715] (4/8) Epoch 17, batch 30450, loss[loss=0.1145, simple_loss=0.1968, pruned_loss=0.01612, over 4952.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2077, pruned_loss=0.02893, over 972839.10 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 04:31:41,824 INFO [train.py:715] (4/8) Epoch 17, batch 30500, loss[loss=0.1223, simple_loss=0.2062, pruned_loss=0.01924, over 4891.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02883, over 972788.28 frames.], batch size: 23, lr: 1.29e-04
2022-05-09 04:32:21,637 INFO [train.py:715] (4/8) Epoch 17, batch 30550, loss[loss=0.1388, simple_loss=0.2098, pruned_loss=0.03391, over 4837.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.029, over 972492.24 frames.], batch size: 30, lr: 1.29e-04
2022-05-09 04:33:01,421 INFO [train.py:715] (4/8) Epoch 17, batch 30600, loss[loss=0.1253, simple_loss=0.2007, pruned_loss=0.02493, over 4820.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02918, over 972807.41 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 04:33:40,315 INFO [train.py:715] (4/8) Epoch 17, batch 30650, loss[loss=0.1394, simple_loss=0.2065, pruned_loss=0.03614, over 4742.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.0291, over 972902.21 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 04:34:20,060 INFO [train.py:715] (4/8) Epoch 17, batch 30700, loss[loss=0.1231, simple_loss=0.1987, pruned_loss=0.02377, over 4776.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02907, over 972537.53 frames.], batch size: 17, lr: 1.29e-04
2022-05-09 04:34:59,084 INFO [train.py:715] (4/8) Epoch 17, batch 30750, loss[loss=0.1417, simple_loss=0.2111, pruned_loss=0.03615, over 4863.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.0289, over 973289.99 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 04:35:38,913 INFO [train.py:715] (4/8) Epoch 17, batch 30800, loss[loss=0.1415, simple_loss=0.2156, pruned_loss=0.03376, over 4644.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02913, over 972220.53 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 04:36:18,140 INFO [train.py:715] (4/8) Epoch 17, batch 30850, loss[loss=0.1388, simple_loss=0.202, pruned_loss=0.03778, over 4877.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02912, over 972517.47 frames.], batch size: 32, lr: 1.29e-04
2022-05-09 04:36:58,359 INFO [train.py:715] (4/8) Epoch 17, batch 30900, loss[loss=0.1149, simple_loss=0.1915, pruned_loss=0.01914, over 4840.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02899, over 973136.70 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 04:37:38,029 INFO [train.py:715] (4/8) Epoch 17, batch 30950, loss[loss=0.1341, simple_loss=0.2055, pruned_loss=0.0313, over 4780.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02894, over 973179.71 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:38:17,301 INFO [train.py:715] (4/8) Epoch 17, batch 31000, loss[loss=0.1352, simple_loss=0.2121, pruned_loss=0.02912, over 4907.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02893, over 973283.33 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 04:38:57,009 INFO [train.py:715] (4/8) Epoch 17, batch 31050, loss[loss=0.1412, simple_loss=0.2168, pruned_loss=0.03282, over 4944.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02877, over 973953.55 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 04:39:36,077 INFO [train.py:715] (4/8) Epoch 17, batch 31100, loss[loss=0.109, simple_loss=0.1777, pruned_loss=0.02012, over 4807.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2073, pruned_loss=0.02897, over 973225.52 frames.], batch size: 25, lr: 1.29e-04
2022-05-09 04:40:15,209 INFO [train.py:715] (4/8) Epoch 17, batch 31150, loss[loss=0.1358, simple_loss=0.2, pruned_loss=0.03582, over 4923.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2076, pruned_loss=0.02881, over 973530.85 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 04:40:54,503 INFO [train.py:715] (4/8) Epoch 17, batch 31200, loss[loss=0.1475, simple_loss=0.2193, pruned_loss=0.03781, over 4779.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2079, pruned_loss=0.02939, over 973030.87 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:41:34,596 INFO [train.py:715] (4/8) Epoch 17, batch 31250, loss[loss=0.1682, simple_loss=0.2622, pruned_loss=0.03704, over 4877.00 frames.], tot_loss[loss=0.1337, simple_loss=0.208, pruned_loss=0.02969, over 973189.43 frames.], batch size: 22, lr: 1.29e-04
2022-05-09 04:42:13,893 INFO [train.py:715] (4/8) Epoch 17, batch 31300, loss[loss=0.1202, simple_loss=0.1862, pruned_loss=0.0271, over 4875.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02918, over 973377.59 frames.], batch size: 32, lr: 1.29e-04
2022-05-09 04:42:53,280 INFO [train.py:715] (4/8) Epoch 17, batch 31350, loss[loss=0.1415, simple_loss=0.2262, pruned_loss=0.02842, over 4834.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02926, over 973402.33 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:43:32,644 INFO [train.py:715] (4/8) Epoch 17, batch 31400, loss[loss=0.1554, simple_loss=0.2398, pruned_loss=0.03548, over 4782.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.0299, over 973847.92 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 04:44:11,253 INFO [train.py:715] (4/8) Epoch 17, batch 31450, loss[loss=0.1251, simple_loss=0.1933, pruned_loss=0.02846, over 4792.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2085, pruned_loss=0.03006, over 973444.43 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:44:51,216 INFO [train.py:715] (4/8) Epoch 17, batch 31500, loss[loss=0.133, simple_loss=0.2114, pruned_loss=0.02733, over 4932.00 frames.], tot_loss[loss=0.134, simple_loss=0.2085, pruned_loss=0.02981, over 973149.68 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 04:45:29,942 INFO [train.py:715] (4/8) Epoch 17, batch 31550, loss[loss=0.1285, simple_loss=0.1999, pruned_loss=0.02859, over 4847.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.0299, over 972836.35 frames.], batch size: 32, lr: 1.29e-04
2022-05-09 04:46:09,493 INFO [train.py:715] (4/8) Epoch 17, batch 31600, loss[loss=0.1264, simple_loss=0.1932, pruned_loss=0.02983, over 4890.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2084, pruned_loss=0.0299, over 972594.60 frames.], batch size: 22, lr: 1.29e-04
2022-05-09 04:46:48,899 INFO [train.py:715] (4/8) Epoch 17, batch 31650, loss[loss=0.1512, simple_loss=0.2286, pruned_loss=0.03693, over 4964.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2086, pruned_loss=0.03022, over 973244.09 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:47:28,182 INFO [train.py:715] (4/8) Epoch 17, batch 31700, loss[loss=0.1273, simple_loss=0.1997, pruned_loss=0.02747, over 4929.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2081, pruned_loss=0.03028, over 973547.48 frames.], batch size: 29, lr: 1.29e-04
2022-05-09 04:48:07,937 INFO [train.py:715] (4/8) Epoch 17, batch 31750, loss[loss=0.159, simple_loss=0.2252, pruned_loss=0.04639, over 4869.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2082, pruned_loss=0.03023, over 973379.21 frames.], batch size: 16, lr: 1.29e-04
2022-05-09 04:48:47,176 INFO [train.py:715] (4/8) Epoch 17, batch 31800, loss[loss=0.1469, simple_loss=0.2207, pruned_loss=0.03651, over 4826.00 frames.], tot_loss[loss=0.1347, simple_loss=0.2086, pruned_loss=0.0304, over 972605.15 frames.], batch size: 27, lr: 1.29e-04
2022-05-09 04:49:27,379 INFO [train.py:715] (4/8) Epoch 17, batch 31850, loss[loss=0.1183, simple_loss=0.1795, pruned_loss=0.02857, over 4970.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2079, pruned_loss=0.0302, over 972825.46 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:50:06,506 INFO [train.py:715] (4/8) Epoch 17, batch 31900, loss[loss=0.1295, simple_loss=0.2033, pruned_loss=0.0279, over 4820.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2071, pruned_loss=0.02973, over 972431.49 frames.], batch size: 26, lr: 1.29e-04
2022-05-09 04:50:45,988 INFO [train.py:715] (4/8) Epoch 17, batch 31950, loss[loss=0.1167, simple_loss=0.1914, pruned_loss=0.02105, over 4806.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02942, over 972195.16 frames.], batch size: 13, lr: 1.29e-04
2022-05-09 04:51:25,761 INFO [train.py:715] (4/8) Epoch 17, batch 32000, loss[loss=0.166, simple_loss=0.2363, pruned_loss=0.04786, over 4916.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02954, over 972359.15 frames.], batch size: 18, lr: 1.29e-04
2022-05-09 04:52:04,648 INFO [train.py:715] (4/8) Epoch 17, batch 32050, loss[loss=0.1551, simple_loss=0.2284, pruned_loss=0.04088, over 4873.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02909, over 972574.81 frames.], batch size: 38, lr: 1.29e-04
2022-05-09 04:52:44,367 INFO [train.py:715] (4/8) Epoch 17, batch 32100, loss[loss=0.1475, simple_loss=0.2232, pruned_loss=0.03591, over 4809.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02894, over 973055.03 frames.], batch size: 21, lr: 1.29e-04
2022-05-09 04:53:23,405 INFO [train.py:715] (4/8) Epoch 17, batch 32150, loss[loss=0.137, simple_loss=0.212, pruned_loss=0.03097, over 4873.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02856, over 973242.88 frames.], batch size: 20, lr: 1.29e-04
2022-05-09 04:54:02,758 INFO [train.py:715] (4/8) Epoch 17, batch 32200, loss[loss=0.1522, simple_loss=0.2377, pruned_loss=0.03333, over 4927.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02882, over 973523.85 frames.], batch size: 23, lr: 1.29e-04
2022-05-09 04:54:45,063 INFO [train.py:715] (4/8) Epoch 17, batch 32250, loss[loss=0.1267, simple_loss=0.2038, pruned_loss=0.02482, over 4822.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02878, over 972967.17 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:55:24,425 INFO [train.py:715] (4/8) Epoch 17, batch 32300, loss[loss=0.09915, simple_loss=0.1697, pruned_loss=0.01429, over 4783.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02894, over 972722.40 frames.], batch size: 14, lr: 1.29e-04
2022-05-09 04:56:04,329 INFO [train.py:715] (4/8) Epoch 17, batch 32350, loss[loss=0.1652, simple_loss=0.2335, pruned_loss=0.04839, over 4690.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02891, over 973022.98 frames.], batch size: 15, lr: 1.29e-04
2022-05-09 04:56:43,382 INFO [train.py:715] (4/8) Epoch 17, batch 32400, loss[loss=0.1236, simple_loss=0.1954, pruned_loss=0.02594, over 4834.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02834, over 971963.21 frames.], batch size: 32, lr: 1.29e-04
2022-05-09 04:57:22,532 INFO [train.py:715] (4/8) Epoch 17, batch 32450, loss[loss=0.1541, simple_loss=0.2358, pruned_loss=0.03618, over 4770.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02837, over 971832.47 frames.], batch size: 18, lr: 1.28e-04
2022-05-09 04:58:02,555 INFO [train.py:715] (4/8) Epoch 17, batch 32500, loss[loss=0.1483, simple_loss=0.2228, pruned_loss=0.03696, over 4808.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02876, over 972312.21 frames.], batch size: 25, lr: 1.28e-04
2022-05-09 04:58:41,970 INFO [train.py:715] (4/8) Epoch 17, batch 32550, loss[loss=0.1189, simple_loss=0.1883, pruned_loss=0.02473, over 4758.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02883, over 972074.28 frames.], batch size: 19, lr: 1.28e-04
2022-05-09 04:59:21,560 INFO [train.py:715] (4/8) Epoch 17, batch 32600, loss[loss=0.1428, simple_loss=0.2213, pruned_loss=0.03209, over 4795.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.0287, over 971165.63 frames.], batch size: 17, lr: 1.28e-04
2022-05-09 05:00:01,067 INFO [train.py:715] (4/8) Epoch 17, batch 32650, loss[loss=0.1486, simple_loss=0.2268, pruned_loss=0.03516, over 4781.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02903, over 971239.58 frames.], batch size: 14, lr: 1.28e-04
2022-05-09 05:00:39,805 INFO [train.py:715] (4/8) Epoch 17, batch 32700, loss[loss=0.129, simple_loss=0.2088, pruned_loss=0.02465, over 4966.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02892, over 970922.64 frames.], batch size: 24, lr: 1.28e-04
2022-05-09 05:01:19,988 INFO [train.py:715] (4/8) Epoch 17, batch 32750, loss[loss=0.1162, simple_loss=0.1899, pruned_loss=0.02123, over 4799.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2057, pruned_loss=0.02883, over 970048.34 frames.], batch size: 25, lr: 1.28e-04
2022-05-09 05:01:59,335 INFO [train.py:715] (4/8) Epoch 17, batch 32800, loss[loss=0.1306, simple_loss=0.2099, pruned_loss=0.02564, over 4892.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02885, over 970643.82 frames.], batch size: 22, lr: 1.28e-04
2022-05-09 05:02:38,969 INFO [train.py:715] (4/8) Epoch 17, batch 32850, loss[loss=0.1574, simple_loss=0.2303, pruned_loss=0.04226, over 4873.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02885, over 972091.24 frames.], batch size: 16, lr: 1.28e-04
2022-05-09 05:03:18,527 INFO [train.py:715] (4/8) Epoch 17, batch 32900, loss[loss=0.1217, simple_loss=0.1868, pruned_loss=0.02829, over 4650.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02882, over 971087.35 frames.], batch size: 13, lr: 1.28e-04
2022-05-09 05:03:58,029 INFO [train.py:715] (4/8) Epoch 17, batch 32950, loss[loss=0.1422, simple_loss=0.2161, pruned_loss=0.03417, over 4842.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02891, over 971556.92 frames.], batch size: 34, lr: 1.28e-04
2022-05-09 05:04:36,959 INFO [train.py:715] (4/8) Epoch 17, batch 33000, loss[loss=0.1204, simple_loss=0.1991, pruned_loss=0.02087, over 4759.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02916, over 970493.38 frames.], batch size: 19, lr: 1.28e-04
2022-05-09 05:04:36,960 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 05:04:49,645 INFO [train.py:742] (4/8) Epoch 17, validation: loss=0.1049, simple_loss=0.1881, pruned_loss=0.0108, over 914524.00 frames.
2022-05-09 05:05:28,990 INFO [train.py:715] (4/8) Epoch 17, batch 33050, loss[loss=0.1508, simple_loss=0.2315, pruned_loss=0.03512, over 4903.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2077, pruned_loss=0.02932, over 971589.68 frames.], batch size: 39, lr: 1.28e-04
2022-05-09 05:06:08,146 INFO [train.py:715] (4/8) Epoch 17, batch 33100, loss[loss=0.1325, simple_loss=0.216, pruned_loss=0.02446, over 4748.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2077, pruned_loss=0.02888, over 972002.63 frames.], batch size: 19, lr: 1.28e-04
2022-05-09 05:06:47,449 INFO [train.py:715] (4/8) Epoch 17, batch 33150, loss[loss=0.1432, simple_loss=0.2153, pruned_loss=0.03553, over 4935.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02909, over 972455.43 frames.], batch size: 23, lr: 1.28e-04
2022-05-09 05:07:27,185 INFO [train.py:715] (4/8) Epoch 17, batch 33200, loss[loss=0.1368, simple_loss=0.2091, pruned_loss=0.03218, over 4748.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02893, over 971333.46 frames.], batch size: 16, lr: 1.28e-04
2022-05-09 05:08:06,796 INFO [train.py:715] (4/8) Epoch 17, batch 33250, loss[loss=0.1433, simple_loss=0.2215, pruned_loss=0.03261, over 4881.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02907, over 971410.36 frames.], batch size: 22, lr: 1.28e-04
2022-05-09 05:08:46,104 INFO [train.py:715] (4/8) Epoch 17, batch 33300, loss[loss=0.1293, simple_loss=0.1984, pruned_loss=0.03005, over 4820.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02931, over 971684.56 frames.], batch size: 13, lr: 1.28e-04
2022-05-09 05:09:25,686 INFO [train.py:715] (4/8) Epoch 17, batch 33350, loss[loss=0.1264, simple_loss=0.2017, pruned_loss=0.02548, over 4758.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.0289, over 971637.67 frames.], batch size: 16, lr: 1.28e-04
2022-05-09 05:10:05,483 INFO [train.py:715] (4/8) Epoch 17, batch 33400, loss[loss=0.1516, simple_loss=0.2151, pruned_loss=0.04409, over 4957.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2078, pruned_loss=0.02923, over 971762.44 frames.], batch size: 35, lr: 1.28e-04
2022-05-09 05:10:44,825 INFO [train.py:715] (4/8) Epoch 17, batch 33450, loss[loss=0.1278, simple_loss=0.2042, pruned_loss=0.02572, over 4882.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02896, over 971884.63 frames.], batch size: 22, lr: 1.28e-04
2022-05-09 05:11:24,364 INFO [train.py:715] (4/8) Epoch 17, batch 33500, loss[loss=0.1828, simple_loss=0.2461, pruned_loss=0.0597, over 4684.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2082, pruned_loss=0.02951, over 972087.34 frames.], batch size: 15, lr: 1.28e-04
2022-05-09 05:12:04,587 INFO [train.py:715] (4/8) Epoch 17, batch 33550, loss[loss=0.1311, simple_loss=0.2019, pruned_loss=0.03021, over 4966.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2079, pruned_loss=0.02915, over 972259.49 frames.], batch size: 15, lr: 1.28e-04
2022-05-09 05:12:44,744 INFO [train.py:715] (4/8) Epoch 17, batch 33600, loss[loss=0.1348, simple_loss=0.2104, pruned_loss=0.02955, over 4816.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2072, pruned_loss=0.02852, over 972770.67 frames.], batch size: 25, lr: 1.28e-04
2022-05-09 05:13:23,738 INFO [train.py:715] (4/8) Epoch 17, batch 33650, loss[loss=0.1324, simple_loss=0.2139, pruned_loss=0.02544, over 4968.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.029, over 973056.96 frames.], batch size: 24, lr: 1.28e-04
2022-05-09 05:14:03,358 INFO [train.py:715] (4/8) Epoch 17, batch 33700, loss[loss=0.1319, simple_loss=0.2147, pruned_loss=0.02457, over 4812.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02853, over 972445.59 frames.], batch size: 27, lr: 1.28e-04
2022-05-09 05:14:42,577 INFO [train.py:715] (4/8) Epoch 17, batch 33750, loss[loss=0.1232, simple_loss=0.2099, pruned_loss=0.01823, over 4766.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02845, over 972397.50 frames.], batch size: 16, lr: 1.28e-04
2022-05-09 05:15:21,395 INFO [train.py:715] (4/8) Epoch 17, batch 33800, loss[loss=0.1719, simple_loss=0.238, pruned_loss=0.05287, over 4843.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02883, over 972490.95 frames.], batch size: 34, lr: 1.28e-04
2022-05-09 05:16:01,528 INFO [train.py:715] (4/8) Epoch 17, batch 33850, loss[loss=0.1355, simple_loss=0.2145, pruned_loss=0.0282, over 4793.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2067, pruned_loss=0.02854, over 972832.57 frames.], batch size: 17, lr: 1.28e-04
2022-05-09 05:16:41,837 INFO [train.py:715] (4/8) Epoch 17, batch 33900, loss[loss=0.1255, simple_loss=0.1932, pruned_loss=0.02888, over 4768.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.0288, over 971822.51 frames.], batch size: 12, lr: 1.28e-04
2022-05-09 05:17:21,090 INFO [train.py:715] (4/8) Epoch 17, batch 33950, loss[loss=0.1409, simple_loss=0.2164, pruned_loss=0.03271, over 4741.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02864, over 971031.66 frames.], batch size: 16, lr: 1.28e-04
2022-05-09 05:18:00,092 INFO [train.py:715] (4/8) Epoch 17, batch 34000, loss[loss=0.1674, simple_loss=0.2531, pruned_loss=0.04085, over 4772.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2069, pruned_loss=0.02864, over 971795.13 frames.], batch size: 18, lr: 1.28e-04
2022-05-09 05:18:39,509 INFO [train.py:715] (4/8) Epoch 17, batch 34050, loss[loss=0.1307, simple_loss=0.2048, pruned_loss=0.02826, over 4931.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2073, pruned_loss=0.02878, over 972366.06 frames.], batch size: 35, lr: 1.28e-04
2022-05-09 05:19:19,504 INFO [train.py:715] (4/8) Epoch 17, batch 34100, loss[loss=0.1125, simple_loss=0.1962, pruned_loss=0.01441, over 4804.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2076, pruned_loss=0.02888, over 972262.75 frames.], batch size: 25, lr: 1.28e-04
2022-05-09 05:19:58,310 INFO [train.py:715] (4/8) Epoch 17, batch 34150, loss[loss=0.1125, simple_loss=0.1865, pruned_loss=0.01926, over 4814.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2076, pruned_loss=0.02891, over 972563.35 frames.], batch size: 15, lr: 1.28e-04
2022-05-09 05:20:37,450 INFO [train.py:715] (4/8) Epoch 17, batch 34200, loss[loss=0.1344, simple_loss=0.2017, pruned_loss=0.03358, over 4983.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2078, pruned_loss=0.02946, over 972136.04 frames.], batch size: 14, lr: 1.28e-04
2022-05-09 05:21:16,559 INFO [train.py:715] (4/8) Epoch 17, batch 34250, loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02835, over 4989.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02875, over 972281.72 frames.], batch size: 16, lr: 1.28e-04
2022-05-09 05:21:55,280 INFO [train.py:715] (4/8) Epoch 17, batch 34300, loss[loss=0.1428, simple_loss=0.2165, pruned_loss=0.03449, over 4877.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02871, over 972620.88 frames.], batch size: 19, lr: 1.28e-04
2022-05-09 05:22:34,166 INFO [train.py:715] (4/8) Epoch 17, batch 34350, loss[loss=0.1389, simple_loss=0.215, pruned_loss=0.03134, over 4879.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02892, over 971811.17 frames.], batch size: 16, lr: 1.28e-04
2022-05-09 05:23:13,527 INFO [train.py:715] (4/8) Epoch 17, batch 34400, loss[loss=0.1364, simple_loss=0.2103, pruned_loss=0.03123, over 4915.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02827, over 972470.00 frames.], batch size: 18, lr: 1.28e-04
2022-05-09 05:23:52,517 INFO [train.py:715] (4/8) Epoch 17, batch 34450, loss[loss=0.1286, simple_loss=0.1999, pruned_loss=0.02868, over 4939.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02819, over 971909.38 frames.], batch size: 29, lr: 1.28e-04
2022-05-09 05:24:30,968 INFO [train.py:715] (4/8) Epoch 17, batch 34500, loss[loss=0.1121, simple_loss=0.1787, pruned_loss=0.02282, over 4872.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02832, over 972810.70 frames.], batch size: 16, lr: 1.28e-04
2022-05-09 05:25:09,847 INFO [train.py:715] (4/8) Epoch 17, batch 34550, loss[loss=0.1306, simple_loss=0.2068, pruned_loss=0.02713, over 4813.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02832, over 971786.08 frames.], batch size: 26, lr: 1.28e-04
2022-05-09 05:25:48,994 INFO [train.py:715] (4/8) Epoch 17, batch 34600, loss[loss=0.1395, simple_loss=0.2026, pruned_loss=0.03815, over 4770.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02853, over 972284.42 frames.], batch size: 14, lr: 1.28e-04
2022-05-09 05:26:27,694 INFO [train.py:715] (4/8) Epoch 17, batch 34650, loss[loss=0.1329, simple_loss=0.1903, pruned_loss=0.03773, over 4801.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02863, over 972101.30 frames.], batch size: 13, lr: 1.28e-04
2022-05-09 05:27:06,961 INFO [train.py:715] (4/8) Epoch 17, batch 34700, loss[loss=0.1515, simple_loss=0.2263, pruned_loss=0.03835, over 4805.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02909, over 971399.25 frames.], batch size: 21, lr: 1.28e-04
2022-05-09 05:27:45,506 INFO [train.py:715] (4/8) Epoch 17, batch 34750, loss[loss=0.1433, simple_loss=0.2199, pruned_loss=0.03337, over 4980.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02934, over 971768.98 frames.], batch size: 31, lr: 1.28e-04
2022-05-09 05:28:22,197 INFO [train.py:715] (4/8) Epoch 17, batch 34800, loss[loss=0.1237, simple_loss=0.1814, pruned_loss=0.03298, over 4768.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.02925, over 971218.07 frames.], batch size: 12, lr: 1.28e-04
2022-05-09 05:29:12,358 INFO [train.py:715] (4/8) Epoch 18, batch 0, loss[loss=0.1407, simple_loss=0.2146, pruned_loss=0.0334, over 4935.00 frames.], tot_loss[loss=0.1407, simple_loss=0.2146, pruned_loss=0.0334, over 4935.00 frames.], batch size: 23, lr: 1.25e-04
2022-05-09 05:29:51,052 INFO [train.py:715] (4/8) Epoch 18, batch 50, loss[loss=0.1176, simple_loss=0.1919, pruned_loss=0.02161, over 4821.00 frames.], tot_loss[loss=0.1349, simple_loss=0.2084, pruned_loss=0.03065, over 218643.75 frames.], batch size: 26, lr: 1.25e-04
2022-05-09 05:30:31,044 INFO [train.py:715] (4/8) Epoch 18, batch 100, loss[loss=0.1141, simple_loss=0.1844, pruned_loss=0.02191, over 4897.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2079, pruned_loss=0.02865, over 385719.22 frames.], batch size: 19, lr: 1.25e-04
2022-05-09 05:31:10,972 INFO [train.py:715] (4/8) Epoch 18, batch 150, loss[loss=0.141, simple_loss=0.213, pruned_loss=0.03452, over 4865.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02869, over 515697.55 frames.], batch size: 30, lr: 1.25e-04
2022-05-09 05:31:50,264 INFO [train.py:715] (4/8) Epoch 18, batch 200, loss[loss=0.1346, simple_loss=0.2046, pruned_loss=0.03231, over 4928.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02915, over 617205.73 frames.], batch size: 29, lr: 1.25e-04
2022-05-09 05:32:29,111 INFO [train.py:715] (4/8) Epoch 18, batch 250, loss[loss=0.1495, simple_loss=0.21, pruned_loss=0.04446, over 4923.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02913, over 696221.84 frames.], batch size: 18, lr: 1.25e-04
2022-05-09 05:33:08,567 INFO [train.py:715] (4/8) Epoch 18, batch 300, loss[loss=0.1365, simple_loss=0.214, pruned_loss=0.02948, over 4701.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2084, pruned_loss=0.0294, over 756959.04 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:33:48,411 INFO [train.py:715] (4/8) Epoch 18, batch 350, loss[loss=0.1801, simple_loss=0.2497, pruned_loss=0.05523, over 4986.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2084, pruned_loss=0.02943, over 805654.76 frames.], batch size: 14, lr: 1.25e-04
2022-05-09 05:34:27,355 INFO [train.py:715] (4/8) Epoch 18, batch 400, loss[loss=0.1402, simple_loss=0.2181, pruned_loss=0.03115, over 4765.00 frames.], tot_loss[loss=0.134, simple_loss=0.2086, pruned_loss=0.02969, over 842632.07 frames.], batch size: 18, lr: 1.25e-04
2022-05-09 05:35:07,143 INFO [train.py:715] (4/8) Epoch 18, batch 450, loss[loss=0.104, simple_loss=0.1781, pruned_loss=0.01491, over 4959.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02958, over 870946.17 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:35:47,326 INFO [train.py:715] (4/8) Epoch 18, batch 500, loss[loss=0.1248, simple_loss=0.1939, pruned_loss=0.02787, over 4843.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02946, over 893509.99 frames.], batch size: 34, lr: 1.25e-04
2022-05-09 05:36:27,099 INFO [train.py:715] (4/8) Epoch 18, batch 550, loss[loss=0.1501, simple_loss=0.2194, pruned_loss=0.04037, over 4690.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2073, pruned_loss=0.02999, over 911555.19 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:37:06,107 INFO [train.py:715] (4/8) Epoch 18, batch 600, loss[loss=0.1342, simple_loss=0.2163, pruned_loss=0.02608, over 4784.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2079, pruned_loss=0.0301, over 924175.42 frames.], batch size: 17, lr: 1.25e-04
2022-05-09 05:37:45,639 INFO [train.py:715] (4/8) Epoch 18, batch 650, loss[loss=0.1317, simple_loss=0.2081, pruned_loss=0.02765, over 4993.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02968, over 935618.73 frames.], batch size: 14, lr: 1.25e-04
2022-05-09 05:38:25,480 INFO [train.py:715] (4/8) Epoch 18, batch 700, loss[loss=0.1105, simple_loss=0.1895, pruned_loss=0.01573, over 4814.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02977, over 944711.02 frames.], batch size: 27, lr: 1.25e-04
2022-05-09 05:39:04,427 INFO [train.py:715] (4/8) Epoch 18, batch 750, loss[loss=0.1436, simple_loss=0.2188, pruned_loss=0.0342, over 4903.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2081, pruned_loss=0.02986, over 950676.26 frames.], batch size: 17, lr: 1.25e-04
2022-05-09 05:39:43,256 INFO [train.py:715] (4/8) Epoch 18, batch 800, loss[loss=0.1143, simple_loss=0.1975, pruned_loss=0.01557, over 4808.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2077, pruned_loss=0.02982, over 954916.52 frames.], batch size: 21, lr: 1.25e-04
2022-05-09 05:40:22,748 INFO [train.py:715] (4/8) Epoch 18, batch 850, loss[loss=0.1215, simple_loss=0.2007, pruned_loss=0.02118, over 4796.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02933, over 958754.68 frames.], batch size: 18, lr: 1.25e-04
2022-05-09 05:41:02,300 INFO [train.py:715] (4/8) Epoch 18, batch 900, loss[loss=0.1245, simple_loss=0.1969, pruned_loss=0.02608, over 4797.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02947, over 961668.15 frames.], batch size: 21, lr: 1.25e-04
2022-05-09 05:41:41,276 INFO [train.py:715] (4/8) Epoch 18, batch 950, loss[loss=0.1339, simple_loss=0.214, pruned_loss=0.0269, over 4859.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2067, pruned_loss=0.02944, over 964247.25 frames.], batch size: 22, lr: 1.25e-04
2022-05-09 05:42:20,888 INFO [train.py:715] (4/8) Epoch 18, batch 1000, loss[loss=0.1318, simple_loss=0.2027, pruned_loss=0.03048, over 4753.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2078, pruned_loss=0.02987, over 965476.01 frames.], batch size: 16, lr: 1.25e-04
2022-05-09 05:43:00,533 INFO [train.py:715] (4/8) Epoch 18, batch 1050, loss[loss=0.1376, simple_loss=0.2132, pruned_loss=0.031, over 4682.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2063, pruned_loss=0.02945, over 965979.99 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:43:39,936 INFO [train.py:715] (4/8) Epoch 18, batch 1100, loss[loss=0.1537, simple_loss=0.2263, pruned_loss=0.04055, over 4801.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2068, pruned_loss=0.02982, over 966646.03 frames.], batch size: 13, lr: 1.25e-04
2022-05-09 05:44:18,724 INFO [train.py:715] (4/8) Epoch 18, batch 1150, loss[loss=0.1242, simple_loss=0.2043, pruned_loss=0.02201, over 4899.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02932, over 967861.29 frames.], batch size: 22, lr: 1.25e-04
2022-05-09 05:44:58,550 INFO [train.py:715] (4/8) Epoch 18, batch 1200, loss[loss=0.1283, simple_loss=0.2011, pruned_loss=0.02775, over 4815.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02914, over 969422.12 frames.], batch size: 27, lr: 1.25e-04
2022-05-09 05:45:38,520 INFO [train.py:715] (4/8) Epoch 18, batch 1250, loss[loss=0.136, simple_loss=0.197, pruned_loss=0.03749, over 4925.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02928, over 970489.26 frames.], batch size: 18, lr: 1.25e-04
2022-05-09 05:46:17,551 INFO [train.py:715] (4/8) Epoch 18, batch 1300, loss[loss=0.1206, simple_loss=0.1989, pruned_loss=0.02114, over 4973.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02977, over 970881.52 frames.], batch size: 24, lr: 1.25e-04
2022-05-09 05:46:56,375 INFO [train.py:715] (4/8) Epoch 18, batch 1350, loss[loss=0.1497, simple_loss=0.2112, pruned_loss=0.04407, over 4761.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2068, pruned_loss=0.02953, over 970117.10 frames.], batch size: 12, lr: 1.25e-04
2022-05-09 05:47:35,781 INFO [train.py:715] (4/8) Epoch 18, batch 1400, loss[loss=0.1238, simple_loss=0.1984, pruned_loss=0.02459, over 4900.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2064, pruned_loss=0.02957, over 971019.01 frames.], batch size: 19, lr: 1.25e-04
2022-05-09 05:48:15,007 INFO [train.py:715] (4/8) Epoch 18, batch 1450, loss[loss=0.1644, simple_loss=0.2311, pruned_loss=0.04886, over 4744.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2061, pruned_loss=0.02953, over 971169.14 frames.], batch size: 19, lr: 1.25e-04
2022-05-09 05:48:53,403 INFO [train.py:715] (4/8) Epoch 18, batch 1500, loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.0296, over 4915.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2067, pruned_loss=0.02974, over 970752.13 frames.], batch size: 17, lr: 1.25e-04
2022-05-09 05:49:32,908 INFO [train.py:715] (4/8) Epoch 18, batch 1550, loss[loss=0.119, simple_loss=0.1936, pruned_loss=0.0222, over 4806.00 frames.], tot_loss[loss=0.1332, simple_loss=0.207, pruned_loss=0.02967, over 971473.35 frames.], batch size: 25, lr: 1.25e-04
2022-05-09 05:50:12,323 INFO [train.py:715] (4/8) Epoch 18, batch 1600, loss[loss=0.1463, simple_loss=0.2298, pruned_loss=0.03141, over 4700.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02918, over 971432.11 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:50:51,521 INFO [train.py:715] (4/8) Epoch 18, batch 1650, loss[loss=0.1424, simple_loss=0.2233, pruned_loss=0.03076, over 4983.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.0289, over 972233.54 frames.], batch size: 26, lr: 1.25e-04
2022-05-09 05:51:30,470 INFO [train.py:715] (4/8) Epoch 18, batch 1700, loss[loss=0.1024, simple_loss=0.1787, pruned_loss=0.01304, over 4764.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02859, over 971954.28 frames.], batch size: 19, lr: 1.25e-04
2022-05-09 05:52:09,888 INFO [train.py:715] (4/8) Epoch 18, batch 1750, loss[loss=0.1168, simple_loss=0.1959, pruned_loss=0.01883, over 4817.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02871, over 971843.49 frames.], batch size: 21, lr: 1.25e-04
2022-05-09 05:52:49,170 INFO [train.py:715] (4/8) Epoch 18, batch 1800, loss[loss=0.1478, simple_loss=0.2151, pruned_loss=0.04026, over 4810.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02899, over 972445.55 frames.], batch size: 14, lr: 1.25e-04
2022-05-09 05:53:27,452 INFO [train.py:715] (4/8) Epoch 18, batch 1850, loss[loss=0.1191, simple_loss=0.1974, pruned_loss=0.02038, over 4751.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02889, over 972878.06 frames.], batch size: 19, lr: 1.25e-04
2022-05-09 05:54:06,242 INFO [train.py:715] (4/8) Epoch 18, batch 1900, loss[loss=0.1314, simple_loss=0.2105, pruned_loss=0.02617, over 4781.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02929, over 973242.74 frames.], batch size: 18, lr: 1.25e-04
2022-05-09 05:54:45,621 INFO [train.py:715] (4/8) Epoch 18, batch 1950, loss[loss=0.1041, simple_loss=0.1758, pruned_loss=0.01616, over 4858.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02876, over 973481.14 frames.], batch size: 12, lr: 1.25e-04
2022-05-09 05:55:24,352 INFO [train.py:715] (4/8) Epoch 18, batch 2000, loss[loss=0.1321, simple_loss=0.2088, pruned_loss=0.02766, over 4821.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2071, pruned_loss=0.02865, over 973971.74 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:56:02,841 INFO [train.py:715] (4/8) Epoch 18, batch 2050, loss[loss=0.1173, simple_loss=0.1954, pruned_loss=0.01956, over 4821.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2063, pruned_loss=0.02809, over 972204.16 frames.], batch size: 25, lr: 1.25e-04
2022-05-09 05:56:42,078 INFO [train.py:715] (4/8) Epoch 18, batch 2100, loss[loss=0.1412, simple_loss=0.2128, pruned_loss=0.03483, over 4976.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02815, over 972526.41 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:57:21,524 INFO [train.py:715] (4/8) Epoch 18, batch 2150, loss[loss=0.1261, simple_loss=0.196, pruned_loss=0.02808, over 4825.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02822, over 972259.22 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:57:59,831 INFO [train.py:715] (4/8) Epoch 18, batch 2200, loss[loss=0.1181, simple_loss=0.1834, pruned_loss=0.0264, over 4785.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.028, over 972104.17 frames.], batch size: 18, lr: 1.25e-04
2022-05-09 05:58:39,482 INFO [train.py:715] (4/8) Epoch 18, batch 2250, loss[loss=0.1239, simple_loss=0.1944, pruned_loss=0.02671, over 4897.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2046, pruned_loss=0.02778, over 971572.70 frames.], batch size: 32, lr: 1.25e-04
2022-05-09 05:59:18,829 INFO [train.py:715] (4/8) Epoch 18, batch 2300, loss[loss=0.1557, simple_loss=0.2262, pruned_loss=0.04265, over 4979.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2051, pruned_loss=0.02819, over 971297.97 frames.], batch size: 15, lr: 1.25e-04
2022-05-09 05:59:57,623 INFO [train.py:715] (4/8) Epoch 18, batch 2350, loss[loss=0.1132, simple_loss=0.1828, pruned_loss=0.02183, over 4879.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2051, pruned_loss=0.02864, over 971057.27 frames.], batch size: 22, lr: 1.25e-04
2022-05-09 06:00:36,234 INFO [train.py:715] (4/8) Epoch 18, batch 2400, loss[loss=0.136, simple_loss=0.219, pruned_loss=0.02647, over 4847.00 frames.], tot_loss[loss=0.1313, simple_loss=0.205, pruned_loss=0.02878, over 971751.47 frames.], batch size: 32, lr: 1.25e-04
2022-05-09 06:01:15,721 INFO [train.py:715] (4/8) Epoch 18, batch 2450, loss[loss=0.1206, simple_loss=0.204, pruned_loss=0.01859, over 4849.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2057, pruned_loss=0.02893, over 971283.04 frames.], batch size: 32, lr: 1.25e-04
2022-05-09 06:01:55,086 INFO [train.py:715] (4/8) Epoch 18, batch 2500, loss[loss=0.1333, simple_loss=0.204, pruned_loss=0.03136, over 4750.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02895, over 970638.37 frames.], batch size: 16, lr: 1.25e-04
2022-05-09 06:02:33,096 INFO [train.py:715] (4/8) Epoch 18, batch 2550, loss[loss=0.1337, simple_loss=0.2016, pruned_loss=0.03288, over 4770.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.0291, over 971037.52 frames.], batch size: 14, lr: 1.25e-04
2022-05-09 06:03:11,865 INFO [train.py:715] (4/8) Epoch 18, batch 2600, loss[loss=0.1352, simple_loss=0.2032, pruned_loss=0.03357, over 4838.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02928, over 971094.00 frames.], batch size: 26, lr: 1.25e-04
2022-05-09 06:03:51,792 INFO [train.py:715] (4/8) Epoch 18, batch 2650, loss[loss=0.1365, simple_loss=0.2155, pruned_loss=0.02876, over 4841.00 frames.], tot_loss[loss=0.1331, simple_loss=0.207, pruned_loss=0.0296, over 970722.41 frames.], batch size: 32, lr: 1.25e-04
2022-05-09 06:04:30,525 INFO [train.py:715] (4/8) Epoch 18, batch 2700, loss[loss=0.1218, simple_loss=0.2028, pruned_loss=0.02034, over 4936.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02906, over 971118.19 frames.], batch size: 29, lr: 1.25e-04
2022-05-09 06:05:08,892 INFO [train.py:715] (4/8) Epoch 18, batch 2750, loss[loss=0.1518, simple_loss=0.2148, pruned_loss=0.04444, over 4866.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02916, over 971898.92 frames.], batch size: 38, lr: 1.25e-04
2022-05-09 06:05:47,975 INFO [train.py:715] (4/8) Epoch 18, batch 2800, loss[loss=0.1372, simple_loss=0.2094, pruned_loss=0.0325, over 4966.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02955, over 972657.28 frames.], batch size: 24, lr: 1.25e-04
2022-05-09 06:06:27,523 INFO [train.py:715] (4/8) Epoch 18, batch 2850, loss[loss=0.1377, simple_loss=0.2124, pruned_loss=0.0315, over 4882.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02933, over 972744.39 frames.], batch size: 16, lr: 1.25e-04
2022-05-09 06:07:06,090 INFO [train.py:715] (4/8) Epoch 18, batch 2900, loss[loss=0.1378, simple_loss=0.2044, pruned_loss=0.03562, over 4891.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02887, over 972974.89 frames.], batch size: 17, lr: 1.25e-04
2022-05-09 06:07:44,917 INFO [train.py:715] (4/8) Epoch 18, batch 2950, loss[loss=0.1323, simple_loss=0.1946, pruned_loss=0.03502, over 4868.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02892, over 973072.02 frames.], batch size: 32, lr: 1.25e-04
2022-05-09 06:08:24,282 INFO [train.py:715] (4/8) Epoch 18, batch 3000, loss[loss=0.1679, simple_loss=0.2317, pruned_loss=0.05203, over 4810.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2063, pruned_loss=0.02931, over 972760.51 frames.], batch size: 25, lr: 1.25e-04
2022-05-09 06:08:24,282 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 06:08:34,096 INFO [train.py:742] (4/8) Epoch 18, validation: loss=0.1047, simple_loss=0.1881, pruned_loss=0.01065, over 914524.00 frames.
2022-05-09 06:09:14,107 INFO [train.py:715] (4/8) Epoch 18, batch 3050, loss[loss=0.1429, simple_loss=0.2267, pruned_loss=0.02951, over 4987.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02941, over 972178.67 frames.], batch size: 25, lr: 1.25e-04
2022-05-09 06:09:52,622 INFO [train.py:715] (4/8) Epoch 18, batch 3100, loss[loss=0.1069, simple_loss=0.1765, pruned_loss=0.01866, over 4825.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2069, pruned_loss=0.02959, over 973155.08 frames.], batch size: 12, lr: 1.25e-04
2022-05-09 06:10:31,510 INFO [train.py:715] (4/8) Epoch 18, batch 3150, loss[loss=0.1435, simple_loss=0.2127, pruned_loss=0.03719, over 4915.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02961, over 973459.51 frames.], batch size: 18, lr: 1.25e-04
2022-05-09 06:11:10,547 INFO [train.py:715] (4/8) Epoch 18, batch 3200, loss[loss=0.1514, simple_loss=0.2195, pruned_loss=0.0417, over 4787.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02946, over 972756.38 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 06:11:50,028 INFO [train.py:715] (4/8) Epoch 18, batch 3250, loss[loss=0.1265, simple_loss=0.1995, pruned_loss=0.02669, over 4918.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02896, over 972808.12 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 06:12:28,191 INFO [train.py:715] (4/8) Epoch 18, batch 3300, loss[loss=0.1553, simple_loss=0.2247, pruned_loss=0.04293, over 4963.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02877, over 973667.50 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 06:13:07,648 INFO [train.py:715] (4/8) Epoch 18, batch 3350, loss[loss=0.1648, simple_loss=0.2371, pruned_loss=0.04628, over 4856.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.02908, over 974046.01 frames.], batch size: 32, lr: 1.24e-04
2022-05-09 06:13:47,788 INFO [train.py:715] (4/8) Epoch 18, batch 3400, loss[loss=0.1288, simple_loss=0.2124, pruned_loss=0.02253, over 4876.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02875, over 973242.41 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 06:14:26,391 INFO [train.py:715] (4/8) Epoch 18, batch 3450, loss[loss=0.1153, simple_loss=0.1882, pruned_loss=0.02114, over 4824.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02877, over 973419.59 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 06:15:05,249 INFO [train.py:715] (4/8) Epoch 18, batch 3500, loss[loss=0.1187, simple_loss=0.193, pruned_loss=0.02221, over 4685.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02859, over 973305.86 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:15:45,336 INFO [train.py:715] (4/8) Epoch 18, batch 3550, loss[loss=0.1294, simple_loss=0.2055, pruned_loss=0.02665, over 4969.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02846, over 973408.50 frames.], batch size: 28, lr: 1.24e-04
2022-05-09 06:16:24,511 INFO [train.py:715] (4/8) Epoch 18, batch 3600, loss[loss=0.1708, simple_loss=0.2497, pruned_loss=0.04596, over 4788.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02845, over 972042.16 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 06:17:03,259 INFO [train.py:715] (4/8) Epoch 18, batch 3650, loss[loss=0.1118, simple_loss=0.1832, pruned_loss=0.02019, over 4962.00 frames.], tot_loss[loss=0.131, simple_loss=0.2055, pruned_loss=0.02828, over 971925.30 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 06:17:42,732 INFO [train.py:715] (4/8) Epoch 18, batch 3700, loss[loss=0.1165, simple_loss=0.193, pruned_loss=0.02003, over 4964.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02841, over 971601.75 frames.], batch size: 28, lr: 1.24e-04
2022-05-09 06:18:22,002 INFO [train.py:715] (4/8) Epoch 18, batch 3750, loss[loss=0.1329, simple_loss=0.2084, pruned_loss=0.02866, over 4870.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02878, over 971189.27 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 06:18:59,956 INFO [train.py:715] (4/8) Epoch 18, batch 3800, loss[loss=0.1222, simple_loss=0.1899, pruned_loss=0.02721, over 4935.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02832, over 971347.93 frames.], batch size: 23, lr: 1.24e-04
2022-05-09 06:19:39,328 INFO [train.py:715] (4/8) Epoch 18, batch 3850, loss[loss=0.09394, simple_loss=0.1621, pruned_loss=0.01289, over 4795.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2047, pruned_loss=0.02789, over 971585.84 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 06:20:19,343 INFO [train.py:715] (4/8) Epoch 18, batch 3900, loss[loss=0.109, simple_loss=0.1935, pruned_loss=0.01219, over 4965.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02847, over 971227.07 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 06:20:57,824 INFO [train.py:715] (4/8) Epoch 18, batch 3950, loss[loss=0.1341, simple_loss=0.2142, pruned_loss=0.02698, over 4876.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02821, over 971594.52 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:21:37,237 INFO [train.py:715] (4/8) Epoch 18, batch 4000, loss[loss=0.1349, simple_loss=0.2244, pruned_loss=0.02272, over 4910.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02813, over 971081.86 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 06:22:16,737 INFO [train.py:715] (4/8) Epoch 18, batch 4050, loss[loss=0.1107, simple_loss=0.187, pruned_loss=0.01719, over 4972.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.0282, over 970721.08 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:22:56,013 INFO [train.py:715] (4/8) Epoch 18, batch 4100, loss[loss=0.1347, simple_loss=0.2165, pruned_loss=0.02644, over 4862.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02844, over 971560.98 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 06:23:34,760 INFO [train.py:715] (4/8) Epoch 18, batch 4150, loss[loss=0.1343, simple_loss=0.2051, pruned_loss=0.03178, over 4973.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2062, pruned_loss=0.02803, over 972264.97 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:24:14,199 INFO [train.py:715] (4/8) Epoch 18, batch 4200, loss[loss=0.1295, simple_loss=0.2084, pruned_loss=0.02529, over 4836.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02847, over 972551.44 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 06:24:53,583 INFO [train.py:715] (4/8) Epoch 18, batch 4250, loss[loss=0.1522, simple_loss=0.2242, pruned_loss=0.0401, over 4992.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02848, over 972269.68 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:25:32,491 INFO [train.py:715] (4/8) Epoch 18, batch 4300, loss[loss=0.1233, simple_loss=0.1955, pruned_loss=0.0255, over 4956.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02862, over 972171.16 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 06:26:12,600 INFO [train.py:715] (4/8) Epoch 18, batch 4350, loss[loss=0.1232, simple_loss=0.1903, pruned_loss=0.02808, over 4959.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02902, over 972833.58 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 06:26:52,061 INFO [train.py:715] (4/8) Epoch 18, batch 4400, loss[loss=0.1348, simple_loss=0.2067, pruned_loss=0.03147, over 4800.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02929, over 973011.52 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 06:27:31,549 INFO [train.py:715] (4/8) Epoch 18, batch 4450, loss[loss=0.1296, simple_loss=0.2033, pruned_loss=0.02801, over 4857.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02935, over 972335.74 frames.], batch size: 32, lr: 1.24e-04
2022-05-09 06:28:09,901 INFO [train.py:715] (4/8) Epoch 18, batch 4500, loss[loss=0.1556, simple_loss=0.2209, pruned_loss=0.04518, over 4831.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02924, over 971687.94 frames.], batch size: 30, lr: 1.24e-04
2022-05-09 06:28:49,167 INFO [train.py:715] (4/8) Epoch 18, batch 4550, loss[loss=0.1519, simple_loss=0.2172, pruned_loss=0.04324, over 4986.00 frames.], tot_loss[loss=0.133, simple_loss=0.2078, pruned_loss=0.02917, over 972916.09 frames.], batch size: 31, lr: 1.24e-04
2022-05-09 06:29:29,017 INFO [train.py:715] (4/8) Epoch 18, batch 4600, loss[loss=0.1447, simple_loss=0.2167, pruned_loss=0.03636, over 4876.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2083, pruned_loss=0.02918, over 972683.53 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 06:30:07,895 INFO [train.py:715] (4/8) Epoch 18, batch 4650, loss[loss=0.1184, simple_loss=0.1992, pruned_loss=0.01882, over 4903.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2078, pruned_loss=0.02936, over 972276.34 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:30:47,009 INFO [train.py:715] (4/8) Epoch 18, batch 4700, loss[loss=0.1302, simple_loss=0.2051, pruned_loss=0.02769, over 4934.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02941, over 972378.47 frames.], batch size: 29, lr: 1.24e-04
2022-05-09 06:31:26,065 INFO [train.py:715] (4/8) Epoch 18, batch 4750, loss[loss=0.1248, simple_loss=0.2011, pruned_loss=0.02426, over 4776.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02921, over 972566.68 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:32:06,181 INFO [train.py:715] (4/8) Epoch 18, batch 4800, loss[loss=0.1191, simple_loss=0.1886, pruned_loss=0.02483, over 4958.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02923, over 972547.41 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 06:32:44,916 INFO [train.py:715] (4/8) Epoch 18, batch 4850, loss[loss=0.1616, simple_loss=0.2402, pruned_loss=0.0415, over 4783.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02913, over 973617.98 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 06:33:24,373 INFO [train.py:715] (4/8) Epoch 18, batch 4900, loss[loss=0.1536, simple_loss=0.2271, pruned_loss=0.04003, over 4906.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02909, over 972614.52 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:34:04,566 INFO [train.py:715] (4/8) Epoch 18, batch 4950, loss[loss=0.1504, simple_loss=0.2206, pruned_loss=0.04003, over 4883.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02943, over 972468.89 frames.], batch size: 39, lr: 1.24e-04
2022-05-09 06:34:43,674 INFO [train.py:715] (4/8) Epoch 18, batch 5000, loss[loss=0.1331, simple_loss=0.205, pruned_loss=0.03061, over 4745.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02908, over 972425.26 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:35:22,355 INFO [train.py:715] (4/8) Epoch 18, batch 5050, loss[loss=0.1241, simple_loss=0.1949, pruned_loss=0.02667, over 4778.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02882, over 972392.82 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 06:36:01,524 INFO [train.py:715] (4/8) Epoch 18, batch 5100, loss[loss=0.131, simple_loss=0.2085, pruned_loss=0.02676, over 4983.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02861, over 971398.55 frames.], batch size: 35, lr: 1.24e-04
2022-05-09 06:36:41,092 INFO [train.py:715] (4/8) Epoch 18, batch 5150, loss[loss=0.1302, simple_loss=0.2036, pruned_loss=0.02841, over 4754.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02908, over 972237.09 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:37:19,649 INFO [train.py:715] (4/8) Epoch 18, batch 5200, loss[loss=0.1442, simple_loss=0.2146, pruned_loss=0.03696, over 4872.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02902, over 972164.57 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 06:37:59,018 INFO [train.py:715] (4/8) Epoch 18, batch 5250, loss[loss=0.1229, simple_loss=0.2042, pruned_loss=0.02074, over 4917.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02941, over 972953.20 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:38:38,937 INFO [train.py:715] (4/8) Epoch 18, batch 5300, loss[loss=0.1601, simple_loss=0.2375, pruned_loss=0.04132, over 4741.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2064, pruned_loss=0.02935, over 973320.42 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 06:39:18,964 INFO [train.py:715] (4/8) Epoch 18, batch 5350, loss[loss=0.1108, simple_loss=0.1927, pruned_loss=0.01445, over 4905.00 frames.], tot_loss[loss=0.132, simple_loss=0.2059, pruned_loss=0.02904, over 972725.91 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 06:39:57,062 INFO [train.py:715] (4/8) Epoch 18, batch 5400, loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02878, over 4737.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2059, pruned_loss=0.02913, over 972249.97 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 06:40:38,721 INFO [train.py:715] (4/8) Epoch 18, batch 5450, loss[loss=0.1452, simple_loss=0.2156, pruned_loss=0.0374, over 4705.00 frames.], tot_loss[loss=0.132, simple_loss=0.206, pruned_loss=0.02898, over 972428.46 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:41:19,097 INFO [train.py:715] (4/8) Epoch 18, batch 5500, loss[loss=0.1377, simple_loss=0.2128, pruned_loss=0.03132, over 4873.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02896, over 972515.97 frames.], batch size: 32, lr: 1.24e-04
2022-05-09 06:41:58,080 INFO [train.py:715] (4/8) Epoch 18, batch 5550, loss[loss=0.1246, simple_loss=0.2029, pruned_loss=0.0231, over 4877.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02965, over 971813.34 frames.], batch size: 32, lr: 1.24e-04
2022-05-09 06:42:36,883 INFO [train.py:715] (4/8) Epoch 18, batch 5600, loss[loss=0.1604, simple_loss=0.2319, pruned_loss=0.0444, over 4701.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02979, over 972913.35 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 06:43:15,924 INFO [train.py:715] (4/8) Epoch 18, batch 5650, loss[loss=0.1464, simple_loss=0.2197, pruned_loss=0.03656, over 4916.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02972, over 972838.31 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 06:43:55,547 INFO [train.py:715] (4/8) Epoch 18, batch 5700, loss[loss=0.1266, simple_loss=0.1933, pruned_loss=0.02992, over 4987.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.0292, over 973630.16 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 06:44:33,666 INFO [train.py:715] (4/8) Epoch 18, batch 5750, loss[loss=0.119, simple_loss=0.1944, pruned_loss=0.02185, over 4782.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02878, over 973334.94 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 06:45:12,597 INFO [train.py:715] (4/8) Epoch 18, batch 5800, loss[loss=0.1363, simple_loss=0.208, pruned_loss=0.03226, over 4752.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02878, over 972820.51 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 06:45:52,340 INFO [train.py:715] (4/8) Epoch 18, batch 5850, loss[loss=0.1101, simple_loss=0.1786, pruned_loss=0.02078, over 4855.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02915, over 972713.76 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 06:46:31,447 INFO [train.py:715] (4/8) Epoch 18, batch 5900, loss[loss=0.1113, simple_loss=0.1802, pruned_loss=0.02118, over 4875.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02874, over 972027.11 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 06:47:10,158 INFO [train.py:715] (4/8) Epoch 18, batch 5950, loss[loss=0.1512, simple_loss=0.2397, pruned_loss=0.03133, over 4741.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02932, over 971684.18 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 06:47:49,550 INFO [train.py:715] (4/8) Epoch 18, batch 6000, loss[loss=0.1095, simple_loss=0.1844, pruned_loss=0.01731, over 4757.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02929, over 971905.21 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:47:49,550 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 06:47:59,474 INFO [train.py:742] (4/8) Epoch 18, validation: loss=0.1047, simple_loss=0.188, pruned_loss=0.01075, over 914524.00 frames.
2022-05-09 06:48:39,113 INFO [train.py:715] (4/8) Epoch 18, batch 6050, loss[loss=0.129, simple_loss=0.2124, pruned_loss=0.0228, over 4797.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02919, over 972310.35 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 06:49:18,283 INFO [train.py:715] (4/8) Epoch 18, batch 6100, loss[loss=0.1047, simple_loss=0.1699, pruned_loss=0.01978, over 4795.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02865, over 973174.90 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 06:49:56,632 INFO [train.py:715] (4/8) Epoch 18, batch 6150, loss[loss=0.1218, simple_loss=0.1991, pruned_loss=0.02222, over 4985.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02864, over 972982.72 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 06:50:35,920 INFO [train.py:715] (4/8) Epoch 18, batch 6200, loss[loss=0.1227, simple_loss=0.2028, pruned_loss=0.02124, over 4984.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02856, over 973386.87 frames.], batch size: 28, lr: 1.24e-04
2022-05-09 06:51:15,501 INFO [train.py:715] (4/8) Epoch 18, batch 6250, loss[loss=0.1177, simple_loss=0.2017, pruned_loss=0.01686, over 4983.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02881, over 973148.41 frames.], batch size: 28, lr: 1.24e-04
2022-05-09 06:51:54,532 INFO [train.py:715] (4/8) Epoch 18, batch 6300, loss[loss=0.1158, simple_loss=0.184, pruned_loss=0.02382, over 4797.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02867, over 972607.28 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 06:52:33,701 INFO [train.py:715] (4/8) Epoch 18, batch 6350, loss[loss=0.1172, simple_loss=0.192, pruned_loss=0.02116, over 4870.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02846, over 972853.72 frames.], batch size: 32, lr: 1.24e-04
2022-05-09 06:53:12,891 INFO [train.py:715] (4/8) Epoch 18, batch 6400, loss[loss=0.12, simple_loss=0.1959, pruned_loss=0.02199, over 4859.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2071, pruned_loss=0.02866, over 972799.54 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 06:53:52,077 INFO [train.py:715] (4/8) Epoch 18, batch 6450, loss[loss=0.1265, simple_loss=0.2004, pruned_loss=0.02633, over 4904.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02882, over 973573.07 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 06:54:30,358 INFO [train.py:715] (4/8) Epoch 18, batch 6500, loss[loss=0.1173, simple_loss=0.1955, pruned_loss=0.01955, over 4878.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02879, over 973647.70 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 06:55:08,642 INFO [train.py:715] (4/8) Epoch 18, batch 6550, loss[loss=0.1353, simple_loss=0.214, pruned_loss=0.02828, over 4872.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02878, over 973425.64 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 06:55:48,101 INFO [train.py:715] (4/8) Epoch 18, batch 6600, loss[loss=0.1413, simple_loss=0.2231, pruned_loss=0.02978, over 4771.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2056, pruned_loss=0.02884, over 973177.21 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 06:56:27,457 INFO [train.py:715] (4/8) Epoch 18, batch 6650, loss[loss=0.1299, simple_loss=0.2145, pruned_loss=0.02268, over 4948.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02883, over 973372.96 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 06:57:05,502 INFO [train.py:715] (4/8) Epoch 18, batch 6700, loss[loss=0.1593, simple_loss=0.2299, pruned_loss=0.04434, over 4871.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02922, over 973015.91 frames.], batch size: 32, lr: 1.24e-04
2022-05-09 06:57:44,485 INFO [train.py:715] (4/8) Epoch 18, batch 6750, loss[loss=0.1448, simple_loss=0.2173, pruned_loss=0.03614, over 4896.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02918, over 973136.07 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 06:58:23,843 INFO [train.py:715] (4/8) Epoch 18, batch 6800, loss[loss=0.1421, simple_loss=0.2111, pruned_loss=0.03655, over 4884.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02876, over 972135.65 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 06:59:02,550 INFO [train.py:715] (4/8) Epoch 18, batch 6850, loss[loss=0.1287, simple_loss=0.2077, pruned_loss=0.02483, over 4759.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02946, over 972348.78 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 06:59:40,722 INFO [train.py:715] (4/8) Epoch 18, batch 6900, loss[loss=0.125, simple_loss=0.2014, pruned_loss=0.02427, over 4723.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2076, pruned_loss=0.02954, over 972868.56 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 07:00:20,315 INFO [train.py:715] (4/8) Epoch 18, batch 6950, loss[loss=0.116, simple_loss=0.1959, pruned_loss=0.01802, over 4699.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02933, over 972385.12 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:00:59,042 INFO [train.py:715] (4/8) Epoch 18, batch 7000, loss[loss=0.1296, simple_loss=0.1994, pruned_loss=0.02995, over 4878.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02911, over 971915.20 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 07:01:37,420 INFO [train.py:715] (4/8) Epoch 18, batch 7050, loss[loss=0.1507, simple_loss=0.2329, pruned_loss=0.03426, over 4778.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02901, over 971574.58 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 07:02:16,623 INFO [train.py:715] (4/8) Epoch 18, batch 7100, loss[loss=0.1713, simple_loss=0.2543, pruned_loss=0.04413, over 4891.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2068, pruned_loss=0.02919, over 970839.94 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 07:02:56,205 INFO [train.py:715] (4/8) Epoch 18, batch 7150, loss[loss=0.1212, simple_loss=0.2032, pruned_loss=0.01956, over 4800.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02926, over 971028.47 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 07:03:34,829 INFO [train.py:715] (4/8) Epoch 18, batch 7200, loss[loss=0.1301, simple_loss=0.2031, pruned_loss=0.02854, over 4935.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02919, over 971213.43 frames.], batch size: 35, lr: 1.24e-04
2022-05-09 07:04:13,065 INFO [train.py:715] (4/8) Epoch 18, batch 7250, loss[loss=0.1411, simple_loss=0.2044, pruned_loss=0.03885, over 4800.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02909, over 971347.18 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 07:04:52,163 INFO [train.py:715] (4/8) Epoch 18, batch 7300, loss[loss=0.1152, simple_loss=0.1902, pruned_loss=0.0201, over 4873.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02899, over 972290.83 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 07:05:31,287 INFO [train.py:715] (4/8) Epoch 18, batch 7350, loss[loss=0.1112, simple_loss=0.1763, pruned_loss=0.023, over 4881.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.0291, over 972662.73 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 07:06:09,357 INFO [train.py:715] (4/8) Epoch 18, batch 7400, loss[loss=0.1785, simple_loss=0.2558, pruned_loss=0.05059, over 4793.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02904, over 972709.71 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:06:48,513 INFO [train.py:715] (4/8) Epoch 18, batch 7450, loss[loss=0.1643, simple_loss=0.2273, pruned_loss=0.05066, over 4894.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02903, over 972683.45 frames.], batch size: 32, lr: 1.24e-04
2022-05-09 07:07:27,763 INFO [train.py:715] (4/8) Epoch 18, batch 7500, loss[loss=0.1228, simple_loss=0.2044, pruned_loss=0.02055, over 4806.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.0289, over 972711.25 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 07:08:05,375 INFO [train.py:715] (4/8) Epoch 18, batch 7550, loss[loss=0.1119, simple_loss=0.179, pruned_loss=0.02238, over 4795.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02875, over 972756.20 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:08:43,906 INFO [train.py:715] (4/8) Epoch 18, batch 7600, loss[loss=0.1223, simple_loss=0.2032, pruned_loss=0.02072, over 4778.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02845, over 972217.71 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:09:23,639 INFO [train.py:715] (4/8) Epoch 18, batch 7650, loss[loss=0.1313, simple_loss=0.2071, pruned_loss=0.02776, over 4828.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02863, over 972267.91 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:10:02,903 INFO [train.py:715] (4/8) Epoch 18, batch 7700, loss[loss=0.1286, simple_loss=0.2061, pruned_loss=0.02551, over 4866.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02855, over 971903.83 frames.], batch size: 38, lr: 1.24e-04
2022-05-09 07:10:41,612 INFO [train.py:715] (4/8) Epoch 18, batch 7750, loss[loss=0.1526, simple_loss=0.2405, pruned_loss=0.03239, over 4890.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02926, over 971775.25 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 07:11:21,214 INFO [train.py:715] (4/8) Epoch 18, batch 7800, loss[loss=0.12, simple_loss=0.1978, pruned_loss=0.02106, over 4903.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.0294, over 971587.03 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 07:12:01,092 INFO [train.py:715] (4/8) Epoch 18, batch 7850, loss[loss=0.1425, simple_loss=0.22, pruned_loss=0.03248, over 4987.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02928, over 972503.78 frames.], batch size: 26, lr: 1.24e-04
2022-05-09 07:12:40,479 INFO [train.py:715] (4/8) Epoch 18, batch 7900, loss[loss=0.1327, simple_loss=0.2132, pruned_loss=0.02609, over 4892.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2086, pruned_loss=0.02966, over 971931.34 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 07:13:19,681 INFO [train.py:715] (4/8) Epoch 18, batch 7950, loss[loss=0.111, simple_loss=0.1763, pruned_loss=0.02288, over 4836.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02973, over 971922.65 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:13:59,119 INFO [train.py:715] (4/8) Epoch 18, batch 8000, loss[loss=0.1301, simple_loss=0.2077, pruned_loss=0.02627, over 4819.00 frames.], tot_loss[loss=0.1335, simple_loss=0.208, pruned_loss=0.02945, over 972228.47 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 07:14:38,129 INFO [train.py:715] (4/8) Epoch 18, batch 8050, loss[loss=0.1251, simple_loss=0.1913, pruned_loss=0.02942, over 4766.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2082, pruned_loss=0.02945, over 971680.38 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:15:16,607 INFO [train.py:715] (4/8) Epoch 18, batch 8100, loss[loss=0.1214, simple_loss=0.1968, pruned_loss=0.02299, over 4966.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2074, pruned_loss=0.02902, over 972396.03 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:15:55,249 INFO [train.py:715] (4/8) Epoch 18, batch 8150, loss[loss=0.1329, simple_loss=0.2291, pruned_loss=0.01839, over 4911.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.0293, over 973178.59 frames.], batch size: 29, lr: 1.24e-04
2022-05-09 07:16:34,308 INFO [train.py:715] (4/8) Epoch 18, batch 8200, loss[loss=0.138, simple_loss=0.2112, pruned_loss=0.03245, over 4871.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02946, over 973730.41 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 07:17:12,927 INFO [train.py:715] (4/8) Epoch 18, batch 8250, loss[loss=0.1329, simple_loss=0.2108, pruned_loss=0.02751, over 4804.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02955, over 972366.00 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:17:51,219 INFO [train.py:715] (4/8) Epoch 18, batch 8300, loss[loss=0.1221, simple_loss=0.2074, pruned_loss=0.01843, over 4761.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2083, pruned_loss=0.02969, over 972345.10 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 07:18:31,282 INFO [train.py:715] (4/8) Epoch 18, batch 8350, loss[loss=0.1376, simple_loss=0.2148, pruned_loss=0.03027, over 4884.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02969, over 972134.66 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 07:19:10,480 INFO [train.py:715] (4/8) Epoch 18, batch 8400, loss[loss=0.1181, simple_loss=0.1984, pruned_loss=0.01885, over 4935.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.0295, over 972525.09 frames.], batch size: 23, lr: 1.24e-04
2022-05-09 07:19:48,919 INFO [train.py:715] (4/8) Epoch 18, batch 8450, loss[loss=0.1275, simple_loss=0.192, pruned_loss=0.03153, over 4698.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2061, pruned_loss=0.02916, over 973352.11 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:20:28,155 INFO [train.py:715] (4/8) Epoch 18, batch 8500, loss[loss=0.1296, simple_loss=0.2012, pruned_loss=0.02901, over 4982.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02919, over 973895.61 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:21:07,334 INFO [train.py:715] (4/8) Epoch 18, batch 8550, loss[loss=0.159, simple_loss=0.2257, pruned_loss=0.04615, over 4917.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2071, pruned_loss=0.02948, over 973278.47 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:21:46,039 INFO [train.py:715] (4/8) Epoch 18, batch 8600, loss[loss=0.1341, simple_loss=0.2104, pruned_loss=0.02886, over 4968.00 frames.], tot_loss[loss=0.134, simple_loss=0.208, pruned_loss=0.02996, over 973100.27 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:22:24,245 INFO [train.py:715] (4/8) Epoch 18, batch 8650, loss[loss=0.1067, simple_loss=0.183, pruned_loss=0.01522, over 4971.00 frames.], tot_loss[loss=0.1348, simple_loss=0.2085, pruned_loss=0.03052, over 973043.84 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:23:03,809 INFO [train.py:715] (4/8) Epoch 18, batch 8700, loss[loss=0.101, simple_loss=0.1757, pruned_loss=0.01309, over 4804.00 frames.], tot_loss[loss=0.1341, simple_loss=0.2081, pruned_loss=0.03007, over 973399.19 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 07:23:43,634 INFO [train.py:715] (4/8) Epoch 18, batch 8750, loss[loss=0.1252, simple_loss=0.2078, pruned_loss=0.02124, over 4950.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2079, pruned_loss=0.02978, over 973571.92 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 07:24:23,136 INFO [train.py:715] (4/8) Epoch 18, batch 8800, loss[loss=0.1181, simple_loss=0.2014, pruned_loss=0.01738, over 4939.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02938, over 973572.86 frames.], batch size: 29, lr: 1.24e-04
2022-05-09 07:25:01,506 INFO [train.py:715] (4/8) Epoch 18, batch 8850, loss[loss=0.1387, simple_loss=0.2068, pruned_loss=0.03526, over 4979.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02934, over 973466.02 frames.], batch size: 31, lr: 1.24e-04
2022-05-09 07:25:41,125 INFO [train.py:715] (4/8) Epoch 18, batch 8900, loss[loss=0.1221, simple_loss=0.1857, pruned_loss=0.02923, over 4884.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02887, over 973374.13 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 07:26:19,639 INFO [train.py:715] (4/8) Epoch 18, batch 8950, loss[loss=0.1057, simple_loss=0.1832, pruned_loss=0.01415, over 4884.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.02926, over 972580.22 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 07:26:58,104 INFO [train.py:715] (4/8) Epoch 18, batch 9000, loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02945, over 4888.00 frames.], tot_loss[loss=0.1334, simple_loss=0.207, pruned_loss=0.02986, over 971607.02 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 07:26:58,104 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 07:27:08,039 INFO [train.py:742] (4/8) Epoch 18, validation: loss=0.1045, simple_loss=0.1879, pruned_loss=0.01057, over 914524.00 frames.
2022-05-09 07:27:46,932 INFO [train.py:715] (4/8) Epoch 18, batch 9050, loss[loss=0.1192, simple_loss=0.206, pruned_loss=0.01625, over 4930.00 frames.], tot_loss[loss=0.133, simple_loss=0.2067, pruned_loss=0.02966, over 972210.22 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:28:26,538 INFO [train.py:715] (4/8) Epoch 18, batch 9100, loss[loss=0.1232, simple_loss=0.1979, pruned_loss=0.02425, over 4699.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2072, pruned_loss=0.02974, over 972169.49 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:29:05,675 INFO [train.py:715] (4/8) Epoch 18, batch 9150, loss[loss=0.1402, simple_loss=0.2079, pruned_loss=0.03627, over 4965.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2075, pruned_loss=0.03019, over 972496.26 frames.], batch size: 35, lr: 1.24e-04
2022-05-09 07:29:43,361 INFO [train.py:715] (4/8) Epoch 18, batch 9200, loss[loss=0.1074, simple_loss=0.1863, pruned_loss=0.01421, over 4777.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2073, pruned_loss=0.03006, over 972740.57 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 07:30:22,561 INFO [train.py:715] (4/8) Epoch 18, batch 9250, loss[loss=0.1285, simple_loss=0.1994, pruned_loss=0.02882, over 4773.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2078, pruned_loss=0.03002, over 972448.48 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:31:01,723 INFO [train.py:715] (4/8) Epoch 18, batch 9300, loss[loss=0.1506, simple_loss=0.2257, pruned_loss=0.03778, over 4968.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2076, pruned_loss=0.02979, over 972144.90 frames.], batch size: 39, lr: 1.24e-04
2022-05-09 07:31:39,924 INFO [train.py:715] (4/8) Epoch 18, batch 9350, loss[loss=0.117, simple_loss=0.1907, pruned_loss=0.02159, over 4915.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02943, over 972989.28 frames.], batch size: 23, lr: 1.24e-04
2022-05-09 07:32:18,512 INFO [train.py:715] (4/8) Epoch 18, batch 9400, loss[loss=0.111, simple_loss=0.185, pruned_loss=0.01846, over 4883.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2063, pruned_loss=0.02942, over 973707.58 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 07:32:58,077 INFO [train.py:715] (4/8) Epoch 18, batch 9450, loss[loss=0.1494, simple_loss=0.2168, pruned_loss=0.04103, over 4828.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2066, pruned_loss=0.02998, over 973506.95 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:33:36,484 INFO [train.py:715] (4/8) Epoch 18, batch 9500, loss[loss=0.1311, simple_loss=0.2091, pruned_loss=0.02659, over 4985.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2065, pruned_loss=0.02984, over 972971.25 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 07:34:14,736 INFO [train.py:715] (4/8) Epoch 18, batch 9550, loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.0289, over 4712.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02992, over 973247.79 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:34:53,871 INFO [train.py:715] (4/8) Epoch 18, batch 9600, loss[loss=0.1431, simple_loss=0.227, pruned_loss=0.02964, over 4810.00 frames.], tot_loss[loss=0.133, simple_loss=0.2069, pruned_loss=0.02957, over 973053.73 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 07:35:33,428 INFO [train.py:715] (4/8) Epoch 18, batch 9650, loss[loss=0.1078, simple_loss=0.1771, pruned_loss=0.0193, over 4830.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02906, over 972064.84 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 07:36:12,258 INFO [train.py:715] (4/8) Epoch 18, batch 9700, loss[loss=0.1255, simple_loss=0.197, pruned_loss=0.02701, over 4942.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02946, over 972113.30 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:36:50,931 INFO [train.py:715] (4/8) Epoch 18, batch 9750, loss[loss=0.107, simple_loss=0.1877, pruned_loss=0.0132, over 4816.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2077, pruned_loss=0.02995, over 971791.60 frames.], batch size: 26, lr: 1.24e-04
2022-05-09 07:37:31,032 INFO [train.py:715] (4/8) Epoch 18, batch 9800, loss[loss=0.1168, simple_loss=0.1872, pruned_loss=0.02324, over 4838.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02928, over 972066.83 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 07:38:09,635 INFO [train.py:715] (4/8) Epoch 18, batch 9850, loss[loss=0.1217, simple_loss=0.2041, pruned_loss=0.01967, over 4898.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02887, over 971129.36 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 07:38:47,994 INFO [train.py:715] (4/8) Epoch 18, batch 9900, loss[loss=0.1575, simple_loss=0.2257, pruned_loss=0.04472, over 4794.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02883, over 971315.93 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:39:27,318 INFO [train.py:715] (4/8) Epoch 18, batch 9950, loss[loss=0.1252, simple_loss=0.202, pruned_loss=0.02416, over 4775.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02908, over 971823.94 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:40:06,405 INFO [train.py:715] (4/8) Epoch 18, batch 10000, loss[loss=0.1281, simple_loss=0.2005, pruned_loss=0.02787, over 4945.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02883, over 972116.74 frames.], batch size: 35, lr: 1.24e-04
2022-05-09 07:40:45,255 INFO [train.py:715] (4/8) Epoch 18, batch 10050, loss[loss=0.1164, simple_loss=0.1923, pruned_loss=0.02028, over 4786.00 frames.], tot_loss[loss=0.131, simple_loss=0.2048, pruned_loss=0.02857, over 972736.96 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 07:41:23,500 INFO [train.py:715] (4/8) Epoch 18, batch 10100, loss[loss=0.1355, simple_loss=0.1962, pruned_loss=0.03741, over 4736.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2056, pruned_loss=0.02881, over 971936.28 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 07:42:02,486 INFO [train.py:715] (4/8) Epoch 18, batch 10150, loss[loss=0.151, simple_loss=0.2206, pruned_loss=0.0407, over 4980.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.0289, over 971750.06 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:42:41,662 INFO [train.py:715] (4/8) Epoch 18, batch 10200, loss[loss=0.1381, simple_loss=0.2052, pruned_loss=0.03554, over 4751.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.0288, over 971381.31 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 07:43:20,197 INFO [train.py:715] (4/8) Epoch 18, batch 10250, loss[loss=0.1321, simple_loss=0.1982, pruned_loss=0.03294, over 4806.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02902, over 972006.51 frames.], batch size: 21, lr: 1.24e-04
2022-05-09 07:43:59,315 INFO [train.py:715] (4/8) Epoch 18, batch 10300, loss[loss=0.1127, simple_loss=0.1893, pruned_loss=0.01806, over 4697.00 frames.], tot_loss[loss=0.1333, simple_loss=0.208, pruned_loss=0.02931, over 971363.27 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:44:39,642 INFO [train.py:715] (4/8) Epoch 18, batch 10350, loss[loss=0.1179, simple_loss=0.1942, pruned_loss=0.02079, over 4815.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2076, pruned_loss=0.02886, over 971566.79 frames.], batch size: 26, lr: 1.24e-04
2022-05-09 07:45:18,120 INFO [train.py:715] (4/8) Epoch 18, batch 10400, loss[loss=0.1257, simple_loss=0.1983, pruned_loss=0.02656, over 4875.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02913, over 971195.71 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 07:45:56,567 INFO [train.py:715] (4/8) Epoch 18, batch 10450, loss[loss=0.1226, simple_loss=0.1939, pruned_loss=0.02563, over 4771.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2082, pruned_loss=0.02923, over 971205.40 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:46:36,303 INFO [train.py:715] (4/8) Epoch 18, batch 10500, loss[loss=0.1365, simple_loss=0.215, pruned_loss=0.02902, over 4885.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2072, pruned_loss=0.02863, over 971693.88 frames.], batch size: 39, lr: 1.24e-04
2022-05-09 07:47:15,165 INFO [train.py:715] (4/8) Epoch 18, batch 10550, loss[loss=0.1348, simple_loss=0.206, pruned_loss=0.03182, over 4978.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.0291, over 972047.54 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 07:47:53,899 INFO [train.py:715] (4/8) Epoch 18, batch 10600, loss[loss=0.1368, simple_loss=0.2129, pruned_loss=0.03038, over 4824.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02955, over 972555.12 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:48:33,500 INFO [train.py:715] (4/8) Epoch 18, batch 10650, loss[loss=0.1289, simple_loss=0.1986, pruned_loss=0.02956, over 4769.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02901, over 971953.78 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 07:49:13,191 INFO [train.py:715] (4/8) Epoch 18, batch 10700, loss[loss=0.1248, simple_loss=0.1998, pruned_loss=0.02489, over 4864.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02877, over 972266.75 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 07:49:52,137 INFO [train.py:715] (4/8) Epoch 18, batch 10750, loss[loss=0.1239, simple_loss=0.2011, pruned_loss=0.02339, over 4793.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02882, over 972197.41 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 07:50:31,139 INFO [train.py:715] (4/8) Epoch 18, batch 10800, loss[loss=0.1548, simple_loss=0.2192, pruned_loss=0.0452, over 4949.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02822, over 971953.63 frames.], batch size: 35, lr: 1.24e-04
2022-05-09 07:51:10,554 INFO [train.py:715] (4/8) Epoch 18, batch 10850, loss[loss=0.1134, simple_loss=0.1957, pruned_loss=0.01553, over 4742.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2049, pruned_loss=0.02799, over 972092.35 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 07:51:49,055 INFO [train.py:715] (4/8) Epoch 18, batch 10900, loss[loss=0.1254, simple_loss=0.2141, pruned_loss=0.01836, over 4772.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2051, pruned_loss=0.02765, over 972120.82 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 07:52:27,639 INFO [train.py:715] (4/8) Epoch 18, batch 10950, loss[loss=0.1236, simple_loss=0.2089, pruned_loss=0.01921, over 4882.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2056, pruned_loss=0.02801, over 971775.27 frames.], batch size: 22, lr: 1.24e-04
2022-05-09 07:53:07,688 INFO [train.py:715] (4/8) Epoch 18, batch 11000, loss[loss=0.1071, simple_loss=0.1841, pruned_loss=0.01504, over 4909.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2057, pruned_loss=0.02781, over 971340.02 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:53:46,747 INFO [train.py:715] (4/8) Epoch 18, batch 11050, loss[loss=0.1419, simple_loss=0.2224, pruned_loss=0.03069, over 4984.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2064, pruned_loss=0.02801, over 971624.48 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 07:54:26,301 INFO [train.py:715] (4/8) Epoch 18, batch 11100, loss[loss=0.1229, simple_loss=0.1962, pruned_loss=0.02474, over 4939.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02825, over 972818.01 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:55:05,200 INFO [train.py:715] (4/8) Epoch 18, batch 11150, loss[loss=0.1258, simple_loss=0.2002, pruned_loss=0.02575, over 4688.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02835, over 971991.98 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:55:44,747 INFO [train.py:715] (4/8) Epoch 18, batch 11200, loss[loss=0.1548, simple_loss=0.2221, pruned_loss=0.04369, over 4851.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02898, over 972431.75 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 07:56:23,195 INFO [train.py:715] (4/8) Epoch 18, batch 11250, loss[loss=0.1413, simple_loss=0.2193, pruned_loss=0.03167, over 4824.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02889, over 971808.47 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:57:01,931 INFO [train.py:715] (4/8) Epoch 18, batch 11300, loss[loss=0.1286, simple_loss=0.2146, pruned_loss=0.02128, over 4812.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02822, over 971888.27 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 07:57:41,019 INFO [train.py:715] (4/8) Epoch 18, batch 11350, loss[loss=0.1224, simple_loss=0.2053, pruned_loss=0.0197, over 4706.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02824, over 972259.63 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 07:58:20,185 INFO [train.py:715] (4/8) Epoch 18, batch 11400, loss[loss=0.126, simple_loss=0.1957, pruned_loss=0.02818, over 4914.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02821, over 971474.64 frames.], batch size: 18, lr: 1.24e-04
2022-05-09 07:58:59,553 INFO [train.py:715] (4/8) Epoch 18, batch 11450, loss[loss=0.1047, simple_loss=0.1829, pruned_loss=0.01327, over 4984.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2048, pruned_loss=0.02818, over 972370.42 frames.], batch size: 28, lr: 1.24e-04
2022-05-09 07:59:38,061 INFO [train.py:715] (4/8) Epoch 18, batch 11500, loss[loss=0.1334, simple_loss=0.2137, pruned_loss=0.02654, over 4723.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02842, over 972950.21 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 08:00:17,724 INFO [train.py:715] (4/8) Epoch 18, batch 11550, loss[loss=0.1134, simple_loss=0.1955, pruned_loss=0.01568, over 4828.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02848, over 973111.00 frames.], batch size: 26, lr: 1.24e-04
2022-05-09 08:00:57,123 INFO [train.py:715] (4/8) Epoch 18, batch 11600, loss[loss=0.1391, simple_loss=0.2177, pruned_loss=0.03025, over 4979.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02884, over 973316.94 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 08:01:35,951 INFO [train.py:715] (4/8) Epoch 18, batch 11650, loss[loss=0.1474, simple_loss=0.2239, pruned_loss=0.03542, over 4834.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02858, over 972683.84 frames.], batch size: 30, lr: 1.24e-04
2022-05-09 08:02:15,657 INFO [train.py:715] (4/8) Epoch 18, batch 11700, loss[loss=0.1364, simple_loss=0.2093, pruned_loss=0.03169, over 4796.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2049, pruned_loss=0.02822, over 972449.06 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 08:02:54,933 INFO [train.py:715] (4/8) Epoch 18, batch 11750, loss[loss=0.1146, simple_loss=0.1851, pruned_loss=0.02201, over 4869.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02834, over 972950.69 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 08:03:34,977 INFO [train.py:715] (4/8) Epoch 18, batch 11800, loss[loss=0.1478, simple_loss=0.2257, pruned_loss=0.03494, over 4760.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02856, over 972508.71 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 08:04:13,541 INFO [train.py:715] (4/8) Epoch 18, batch 11850, loss[loss=0.1109, simple_loss=0.1861, pruned_loss=0.01783, over 4816.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02891, over 972158.68 frames.], batch size: 25, lr: 1.24e-04
2022-05-09 08:04:53,376 INFO [train.py:715] (4/8) Epoch 18, batch 11900, loss[loss=0.1261, simple_loss=0.2039, pruned_loss=0.02414, over 4870.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02859, over 973099.97 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 08:05:32,231 INFO [train.py:715] (4/8) Epoch 18, batch 11950, loss[loss=0.1215, simple_loss=0.1912, pruned_loss=0.02585, over 4758.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02883, over 972051.73 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 08:06:10,824 INFO [train.py:715] (4/8) Epoch 18, batch 12000, loss[loss=0.1269, simple_loss=0.2067, pruned_loss=0.02357, over 4854.00 frames.], tot_loss[loss=0.1322, simple_loss=0.207, pruned_loss=0.02871, over 972213.61 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 08:06:10,824 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 08:06:20,736 INFO [train.py:742] (4/8) Epoch 18, validation: loss=0.1046, simple_loss=0.188, pruned_loss=0.01063, over 914524.00 frames.
2022-05-09 08:07:00,009 INFO [train.py:715] (4/8) Epoch 18, batch 12050, loss[loss=0.1055, simple_loss=0.1784, pruned_loss=0.0163, over 4805.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02871, over 971552.81 frames.], batch size: 12, lr: 1.24e-04
2022-05-09 08:07:39,524 INFO [train.py:715] (4/8) Epoch 18, batch 12100, loss[loss=0.1392, simple_loss=0.2174, pruned_loss=0.03051, over 4868.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02838, over 970502.50 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 08:08:19,050 INFO [train.py:715] (4/8) Epoch 18, batch 12150, loss[loss=0.1438, simple_loss=0.2147, pruned_loss=0.03642, over 4784.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.0286, over 970635.08 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 08:08:59,339 INFO [train.py:715] (4/8) Epoch 18, batch 12200, loss[loss=0.1361, simple_loss=0.2109, pruned_loss=0.03069, over 4898.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2073, pruned_loss=0.0286, over 970819.45 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 08:09:38,277 INFO [train.py:715] (4/8) Epoch 18, batch 12250, loss[loss=0.1082, simple_loss=0.1845, pruned_loss=0.01595, over 4793.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02885, over 970565.54 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 08:10:18,803 INFO [train.py:715] (4/8) Epoch 18, batch 12300, loss[loss=0.1638, simple_loss=0.231, pruned_loss=0.04826, over 4742.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02896, over 971391.34 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 08:10:58,222 INFO [train.py:715] (4/8) Epoch 18, batch 12350, loss[loss=0.1221, simple_loss=0.1923, pruned_loss=0.02592, over 4981.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.0285, over 972036.63 frames.], batch size: 35, lr: 1.24e-04
2022-05-09 08:11:37,139 INFO [train.py:715] (4/8) Epoch 18, batch 12400, loss[loss=0.09943, simple_loss=0.1702, pruned_loss=0.01434, over 4809.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02847, over 972635.59 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 08:12:16,681 INFO [train.py:715] (4/8) Epoch 18, batch 12450, loss[loss=0.1312, simple_loss=0.2019, pruned_loss=0.03028, over 4692.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02865, over 972283.19 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 08:12:55,935 INFO [train.py:715] (4/8) Epoch 18, batch 12500, loss[loss=0.1414, simple_loss=0.2127, pruned_loss=0.03506, over 4935.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02878, over 972854.18 frames.], batch size: 39, lr: 1.24e-04
2022-05-09 08:13:36,312 INFO [train.py:715] (4/8) Epoch 18, batch 12550, loss[loss=0.1346, simple_loss=0.2116, pruned_loss=0.02879, over 4865.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02868, over 972914.29 frames.], batch size: 20, lr: 1.24e-04
2022-05-09 08:14:14,820 INFO [train.py:715] (4/8) Epoch 18, batch 12600, loss[loss=0.1399, simple_loss=0.2079, pruned_loss=0.03591, over 4752.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02868, over 972162.17 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 08:14:54,513 INFO [train.py:715] (4/8) Epoch 18, batch 12650, loss[loss=0.1572, simple_loss=0.2364, pruned_loss=0.03904, over 4866.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.0287, over 971145.25 frames.], batch size: 32, lr: 1.24e-04
2022-05-09 08:15:33,310 INFO [train.py:715] (4/8) Epoch 18, batch 12700, loss[loss=0.1422, simple_loss=0.2196, pruned_loss=0.03242, over 4986.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02875, over 971881.90 frames.], batch size: 27, lr: 1.24e-04
2022-05-09 08:16:12,930 INFO [train.py:715] (4/8) Epoch 18, batch 12750, loss[loss=0.127, simple_loss=0.1975, pruned_loss=0.02824, over 4791.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02862, over 972471.47 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 08:16:52,481 INFO [train.py:715] (4/8) Epoch 18, batch 12800, loss[loss=0.126, simple_loss=0.192, pruned_loss=0.02997, over 4827.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02841, over 972247.51 frames.], batch size: 13, lr: 1.24e-04
2022-05-09 08:17:31,836 INFO [train.py:715] (4/8) Epoch 18, batch 12850, loss[loss=0.1416, simple_loss=0.2239, pruned_loss=0.02972, over 4704.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02822, over 972771.37 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 08:18:11,706 INFO [train.py:715] (4/8) Epoch 18, batch 12900, loss[loss=0.1253, simple_loss=0.1957, pruned_loss=0.02747, over 4797.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02813, over 972160.04 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 08:18:50,195 INFO [train.py:715] (4/8) Epoch 18, batch 12950, loss[loss=0.1529, simple_loss=0.2315, pruned_loss=0.03716, over 4755.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02857, over 971765.45 frames.], batch size: 19, lr: 1.24e-04
2022-05-09 08:19:30,194 INFO [train.py:715] (4/8) Epoch 18, batch 13000, loss[loss=0.1555, simple_loss=0.2215, pruned_loss=0.04475, over 4740.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.02829, over 971017.55 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 08:20:09,527 INFO [train.py:715] (4/8) Epoch 18, batch 13050, loss[loss=0.1174, simple_loss=0.1982, pruned_loss=0.01836, over 4761.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02809, over 970405.98 frames.], batch size: 14, lr: 1.24e-04
2022-05-09 08:20:48,610 INFO [train.py:715] (4/8) Epoch 18, batch 13100, loss[loss=0.1583, simple_loss=0.2324, pruned_loss=0.04208, over 4726.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2063, pruned_loss=0.02819, over 970601.62 frames.], batch size: 16, lr: 1.24e-04
2022-05-09 08:21:28,135 INFO [train.py:715] (4/8) Epoch 18, batch 13150, loss[loss=0.1033, simple_loss=0.1817, pruned_loss=0.01246, over 4796.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2068, pruned_loss=0.02849, over 970984.05 frames.], batch size: 24, lr: 1.24e-04
2022-05-09 08:22:07,408 INFO [train.py:715] (4/8) Epoch 18, batch 13200, loss[loss=0.133, simple_loss=0.2028, pruned_loss=0.03161, over 4823.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.02879, over 971626.49 frames.], batch size: 27, lr: 1.24e-04
2022-05-09 08:22:47,220 INFO [train.py:715] (4/8) Epoch 18, batch 13250, loss[loss=0.1242, simple_loss=0.2011, pruned_loss=0.02367, over 4940.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.02884, over 971412.51 frames.], batch size: 35, lr: 1.24e-04
2022-05-09 08:23:25,811 INFO [train.py:715] (4/8) Epoch 18, batch 13300, loss[loss=0.1529, simple_loss=0.2232, pruned_loss=0.0413, over 4882.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02909, over 971696.11 frames.], batch size: 17, lr: 1.24e-04
2022-05-09 08:24:05,552 INFO [train.py:715] (4/8) Epoch 18, batch 13350, loss[loss=0.1452, simple_loss=0.2183, pruned_loss=0.03608, over 4938.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02908, over 971358.06 frames.], batch size: 29, lr: 1.24e-04
2022-05-09 08:24:44,553 INFO [train.py:715] (4/8) Epoch 18, batch 13400, loss[loss=0.1104, simple_loss=0.1872, pruned_loss=0.01679, over 4711.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02864, over 970838.90 frames.], batch size: 15, lr: 1.24e-04
2022-05-09 08:25:25,444 INFO [train.py:715] (4/8) Epoch 18, batch 13450, loss[loss=0.13, simple_loss=0.2118, pruned_loss=0.02409, over 4836.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02883, over 972594.06 frames.], batch size: 26, lr: 1.23e-04
2022-05-09 08:26:05,139 INFO [train.py:715] (4/8) Epoch 18, batch 13500, loss[loss=0.1296, simple_loss=0.2127, pruned_loss=0.02327, over 4813.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02932, over 972935.40 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 08:26:44,082 INFO [train.py:715] (4/8) Epoch 18, batch 13550, loss[loss=0.1146, simple_loss=0.1862, pruned_loss=0.02144, over 4817.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2066, pruned_loss=0.02954, over 973043.78 frames.], batch size: 27, lr: 1.23e-04
2022-05-09 08:27:23,344 INFO [train.py:715] (4/8) Epoch 18, batch 13600, loss[loss=0.1262, simple_loss=0.2071, pruned_loss=0.02269, over 4834.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02962, over 972779.00 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 08:28:02,157 INFO [train.py:715] (4/8) Epoch 18, batch 13650, loss[loss=0.1295, simple_loss=0.2093, pruned_loss=0.02485, over 4908.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2065, pruned_loss=0.02932, over 972960.27 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 08:28:41,562 INFO [train.py:715] (4/8) Epoch 18, batch 13700, loss[loss=0.138, simple_loss=0.2127, pruned_loss=0.03166, over 4856.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02951, over 972414.90 frames.], batch size: 34, lr: 1.23e-04
2022-05-09 08:29:20,647 INFO [train.py:715] (4/8) Epoch 18, batch 13750, loss[loss=0.119, simple_loss=0.1959, pruned_loss=0.02102, over 4753.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02901, over 972692.98 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 08:29:59,714 INFO [train.py:715] (4/8) Epoch 18, batch 13800, loss[loss=0.1361, simple_loss=0.1971, pruned_loss=0.03759, over 4880.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02877, over 972733.33 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 08:30:39,485 INFO [train.py:715] (4/8) Epoch 18, batch 13850, loss[loss=0.1755, simple_loss=0.2341, pruned_loss=0.05845, over 4985.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02857, over 973246.82 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 08:31:18,290 INFO [train.py:715] (4/8) Epoch 18, batch 13900, loss[loss=0.1242, simple_loss=0.2022, pruned_loss=0.02303, over 4762.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02824, over 973138.78 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 08:31:57,755 INFO [train.py:715] (4/8) Epoch 18, batch 13950, loss[loss=0.1306, simple_loss=0.2097, pruned_loss=0.02569, over 4888.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.02826, over 972938.16 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 08:32:37,348 INFO [train.py:715] (4/8) Epoch 18, batch 14000, loss[loss=0.1201, simple_loss=0.1932, pruned_loss=0.02351, over 4810.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.0282, over 972721.62 frames.], batch size: 27, lr: 1.23e-04
2022-05-09 08:33:17,109 INFO [train.py:715] (4/8) Epoch 18, batch 14050, loss[loss=0.1356, simple_loss=0.2063, pruned_loss=0.03244, over 4903.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02824, over 972027.46 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 08:33:56,294 INFO [train.py:715] (4/8) Epoch 18, batch 14100, loss[loss=0.1421, simple_loss=0.2058, pruned_loss=0.03918, over 4902.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02932, over 972638.97 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 08:34:35,395 INFO [train.py:715] (4/8) Epoch 18, batch 14150, loss[loss=0.1434, simple_loss=0.2211, pruned_loss=0.0328, over 4889.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02938, over 972612.15 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 08:35:14,780 INFO [train.py:715] (4/8) Epoch 18, batch 14200, loss[loss=0.176, simple_loss=0.2417, pruned_loss=0.05519, over 4764.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2062, pruned_loss=0.02951, over 972443.25 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 08:35:54,058 INFO [train.py:715] (4/8) Epoch 18, batch 14250, loss[loss=0.1495, simple_loss=0.2171, pruned_loss=0.041, over 4755.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2054, pruned_loss=0.02915, over 973754.32 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 08:36:33,988 INFO [train.py:715] (4/8) Epoch 18, batch 14300, loss[loss=0.1311, simple_loss=0.2021, pruned_loss=0.03, over 4798.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2055, pruned_loss=0.029, over 973301.51 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 08:37:13,313 INFO [train.py:715] (4/8) Epoch 18, batch 14350, loss[loss=0.1295, simple_loss=0.2035, pruned_loss=0.02777, over 4821.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2061, pruned_loss=0.02928, over 973155.18 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 08:37:52,855 INFO [train.py:715] (4/8) Epoch 18, batch 14400, loss[loss=0.1464, simple_loss=0.229, pruned_loss=0.0319, over 4755.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02977, over 972842.32 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 08:38:32,502 INFO [train.py:715] (4/8) Epoch 18, batch 14450, loss[loss=0.1349, simple_loss=0.2184, pruned_loss=0.02569, over 4965.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02949, over 973416.55 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 08:39:11,245 INFO [train.py:715] (4/8) Epoch 18, batch 14500, loss[loss=0.1487, simple_loss=0.2154, pruned_loss=0.04098, over 4847.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02955, over 973779.09 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 08:39:50,389 INFO [train.py:715] (4/8) Epoch 18, batch 14550, loss[loss=0.135, simple_loss=0.2066, pruned_loss=0.0317, over 4925.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02946, over 973819.14 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 08:40:29,525 INFO [train.py:715] (4/8) Epoch 18, batch 14600, loss[loss=0.1189, simple_loss=0.1915, pruned_loss=0.02315, over 4973.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02945, over 973767.44 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 08:41:09,223 INFO [train.py:715] (4/8) Epoch 18, batch 14650, loss[loss=0.1223, simple_loss=0.2003, pruned_loss=0.02215, over 4952.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02928, over 973224.61 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 08:41:48,680 INFO [train.py:715] (4/8) Epoch 18, batch 14700, loss[loss=0.1193, simple_loss=0.1973, pruned_loss=0.02061, over 4902.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02927, over 972284.98 frames.], batch size: 22, lr: 1.23e-04
2022-05-09 08:42:28,035 INFO [train.py:715] (4/8) Epoch 18, batch 14750, loss[loss=0.1398, simple_loss=0.2127, pruned_loss=0.03343, over 4963.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02855, over 971810.43 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 08:43:07,466 INFO [train.py:715] (4/8) Epoch 18, batch 14800, loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02975, over 4804.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.0286, over 971685.58 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 08:43:46,220 INFO [train.py:715] (4/8) Epoch 18, batch 14850, loss[loss=0.1542, simple_loss=0.2255, pruned_loss=0.04148, over 4926.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2061, pruned_loss=0.0291, over 972108.77 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 08:44:25,880 INFO [train.py:715] (4/8) Epoch 18, batch 14900, loss[loss=0.1336, simple_loss=0.2107, pruned_loss=0.02822, over 4969.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02912, over 972110.78 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 08:45:05,550 INFO [train.py:715] (4/8) Epoch 18, batch 14950, loss[loss=0.1345, simple_loss=0.2048, pruned_loss=0.03209, over 4828.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02904, over 971739.38 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 08:45:44,812 INFO [train.py:715] (4/8) Epoch 18, batch 15000, loss[loss=0.1231, simple_loss=0.1949, pruned_loss=0.0256, over 4871.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02881, over 972042.49 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 08:45:44,813 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 08:45:54,765 INFO [train.py:742] (4/8) Epoch 18, validation: loss=0.1048, simple_loss=0.1881, pruned_loss=0.01071, over 914524.00 frames.
2022-05-09 08:46:34,349 INFO [train.py:715] (4/8) Epoch 18, batch 15050, loss[loss=0.1594, simple_loss=0.2318, pruned_loss=0.04354, over 4967.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02942, over 973052.26 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 08:47:13,526 INFO [train.py:715] (4/8) Epoch 18, batch 15100, loss[loss=0.1295, simple_loss=0.204, pruned_loss=0.02747, over 4883.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02902, over 973374.82 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 08:47:53,257 INFO [train.py:715] (4/8) Epoch 18, batch 15150, loss[loss=0.1207, simple_loss=0.1895, pruned_loss=0.02596, over 4925.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02941, over 973386.06 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 08:48:32,385 INFO [train.py:715] (4/8) Epoch 18, batch 15200, loss[loss=0.1378, simple_loss=0.208, pruned_loss=0.03376, over 4941.00 frames.], tot_loss[loss=0.1321, simple_loss=0.206, pruned_loss=0.02903, over 972863.48 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 08:49:11,929 INFO [train.py:715] (4/8) Epoch 18, batch 15250, loss[loss=0.1361, simple_loss=0.2155, pruned_loss=0.02833, over 4892.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02908, over 972849.00 frames.], batch size: 22, lr: 1.23e-04
2022-05-09 08:49:51,791 INFO [train.py:715] (4/8) Epoch 18, batch 15300, loss[loss=0.1327, simple_loss=0.2112, pruned_loss=0.0271, over 4902.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02909, over 973079.12 frames.], batch size: 22, lr: 1.23e-04
2022-05-09 08:50:31,162 INFO [train.py:715] (4/8) Epoch 18, batch 15350, loss[loss=0.1185, simple_loss=0.187, pruned_loss=0.025, over 4840.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02885, over 973156.88 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 08:51:10,083 INFO [train.py:715] (4/8) Epoch 18, batch 15400, loss[loss=0.1348, simple_loss=0.208, pruned_loss=0.03081, over 4889.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02876, over 973771.34 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 08:51:49,372 INFO [train.py:715] (4/8) Epoch 18, batch 15450, loss[loss=0.1174, simple_loss=0.2002, pruned_loss=0.01725, over 4886.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02885, over 973718.94 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 08:52:29,004 INFO [train.py:715] (4/8) Epoch 18, batch 15500, loss[loss=0.1537, simple_loss=0.2371, pruned_loss=0.03518, over 4898.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02908, over 973880.21 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 08:53:08,159 INFO [train.py:715] (4/8) Epoch 18, batch 15550, loss[loss=0.1182, simple_loss=0.1848, pruned_loss=0.02578, over 4962.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02872, over 973989.60 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 08:53:47,905 INFO [train.py:715] (4/8) Epoch 18, batch 15600, loss[loss=0.1451, simple_loss=0.2205, pruned_loss=0.03486, over 4895.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02873, over 973341.73 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 08:54:28,014 INFO [train.py:715] (4/8) Epoch 18, batch 15650, loss[loss=0.1366, simple_loss=0.2103, pruned_loss=0.03144, over 4970.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02895, over 973974.23 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 08:55:07,612 INFO [train.py:715] (4/8) Epoch 18, batch 15700, loss[loss=0.1569, simple_loss=0.2387, pruned_loss=0.03751, over 4962.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02882, over 973635.95 frames.], batch size: 28, lr: 1.23e-04
2022-05-09 08:55:46,518 INFO [train.py:715] (4/8) Epoch 18, batch 15750, loss[loss=0.1423, simple_loss=0.2256, pruned_loss=0.02949, over 4919.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02902, over 974188.13 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 08:56:25,956 INFO [train.py:715] (4/8) Epoch 18, batch 15800, loss[loss=0.1358, simple_loss=0.2095, pruned_loss=0.03102, over 4779.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02906, over 974186.49 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 08:57:05,870 INFO [train.py:715] (4/8) Epoch 18, batch 15850, loss[loss=0.123, simple_loss=0.1978, pruned_loss=0.02414, over 4783.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02889, over 974307.91 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 08:57:45,100 INFO [train.py:715] (4/8) Epoch 18, batch 15900, loss[loss=0.1741, simple_loss=0.2504, pruned_loss=0.04894, over 4854.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02871, over 974430.90 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 08:58:24,413 INFO [train.py:715] (4/8) Epoch 18, batch 15950, loss[loss=0.1231, simple_loss=0.2055, pruned_loss=0.02035, over 4781.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02849, over 973099.98 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 08:59:04,886 INFO [train.py:715] (4/8) Epoch 18, batch 16000, loss[loss=0.1372, simple_loss=0.2172, pruned_loss=0.02862, over 4785.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2057, pruned_loss=0.02888, over 973296.96 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 08:59:45,385 INFO [train.py:715] (4/8) Epoch 18, batch 16050, loss[loss=0.1467, simple_loss=0.2287, pruned_loss=0.03231, over 4779.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.0289, over 973271.51 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:00:24,421 INFO [train.py:715] (4/8) Epoch 18, batch 16100, loss[loss=0.1891, simple_loss=0.2537, pruned_loss=0.06226, over 4904.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02944, over 973042.99 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 09:01:03,601 INFO [train.py:715] (4/8) Epoch 18, batch 16150, loss[loss=0.1365, simple_loss=0.2157, pruned_loss=0.02864, over 4816.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2069, pruned_loss=0.02935, over 972925.40 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 09:01:43,698 INFO [train.py:715] (4/8) Epoch 18, batch 16200, loss[loss=0.1114, simple_loss=0.1924, pruned_loss=0.01515, over 4983.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2077, pruned_loss=0.02943, over 972543.32 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 09:02:22,641 INFO [train.py:715] (4/8) Epoch 18, batch 16250, loss[loss=0.1269, simple_loss=0.2095, pruned_loss=0.02208, over 4811.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2072, pruned_loss=0.02884, over 973239.91 frames.], batch size: 27, lr: 1.23e-04
2022-05-09 09:03:01,669 INFO [train.py:715] (4/8) Epoch 18, batch 16300, loss[loss=0.1649, simple_loss=0.2403, pruned_loss=0.04479, over 4750.00 frames.], tot_loss[loss=0.1321, simple_loss=0.207, pruned_loss=0.02856, over 972818.24 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 09:03:41,210 INFO [train.py:715] (4/8) Epoch 18, batch 16350, loss[loss=0.148, simple_loss=0.2267, pruned_loss=0.03471, over 4823.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.0289, over 972389.32 frames.], batch size: 26, lr: 1.23e-04
2022-05-09 09:04:20,331 INFO [train.py:715] (4/8) Epoch 18, batch 16400, loss[loss=0.1323, simple_loss=0.2031, pruned_loss=0.03076, over 4784.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02854, over 971615.63 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:04:59,287 INFO [train.py:715] (4/8) Epoch 18, batch 16450, loss[loss=0.1239, simple_loss=0.2044, pruned_loss=0.02166, over 4904.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02861, over 971570.22 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 09:05:38,805 INFO [train.py:715] (4/8) Epoch 18, batch 16500, loss[loss=0.1258, simple_loss=0.1983, pruned_loss=0.02661, over 4941.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02854, over 971934.94 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 09:06:18,647 INFO [train.py:715] (4/8) Epoch 18, batch 16550, loss[loss=0.1241, simple_loss=0.2016, pruned_loss=0.02333, over 4907.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02828, over 971357.69 frames.], batch size: 29, lr: 1.23e-04
2022-05-09 09:06:57,075 INFO [train.py:715] (4/8) Epoch 18, batch 16600, loss[loss=0.1351, simple_loss=0.2117, pruned_loss=0.02927, over 4914.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02814, over 971444.37 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:07:36,514 INFO [train.py:715] (4/8) Epoch 18, batch 16650, loss[loss=0.1476, simple_loss=0.2377, pruned_loss=0.02881, over 4761.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.0285, over 971186.88 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:08:15,859 INFO [train.py:715] (4/8) Epoch 18, batch 16700, loss[loss=0.1593, simple_loss=0.241, pruned_loss=0.03877, over 4747.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02824, over 972180.75 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 09:08:55,198 INFO [train.py:715] (4/8) Epoch 18, batch 16750, loss[loss=0.1349, simple_loss=0.2184, pruned_loss=0.02566, over 4820.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02845, over 971941.67 frames.], batch size: 26, lr: 1.23e-04
2022-05-09 09:09:34,648 INFO [train.py:715] (4/8) Epoch 18, batch 16800, loss[loss=0.1516, simple_loss=0.2215, pruned_loss=0.04084, over 4897.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02852, over 971844.26 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:10:13,854 INFO [train.py:715] (4/8) Epoch 18, batch 16850, loss[loss=0.1243, simple_loss=0.2003, pruned_loss=0.02416, over 4992.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02832, over 971815.75 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 09:10:53,310 INFO [train.py:715] (4/8) Epoch 18, batch 16900, loss[loss=0.143, simple_loss=0.2201, pruned_loss=0.03295, over 4769.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02851, over 972426.46 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:11:32,155 INFO [train.py:715] (4/8) Epoch 18, batch 16950, loss[loss=0.1064, simple_loss=0.1823, pruned_loss=0.01525, over 4935.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2053, pruned_loss=0.02856, over 972360.00 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:12:11,611 INFO [train.py:715] (4/8) Epoch 18, batch 17000, loss[loss=0.1515, simple_loss=0.2208, pruned_loss=0.04108, over 4918.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02852, over 972840.54 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 09:12:51,062 INFO [train.py:715] (4/8) Epoch 18, batch 17050, loss[loss=0.1244, simple_loss=0.2017, pruned_loss=0.02358, over 4965.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02838, over 972147.99 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 09:13:30,535 INFO [train.py:715] (4/8) Epoch 18, batch 17100, loss[loss=0.1012, simple_loss=0.1766, pruned_loss=0.01284, over 4751.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02871, over 972712.18 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 09:14:10,114 INFO [train.py:715] (4/8) Epoch 18, batch 17150, loss[loss=0.1465, simple_loss=0.217, pruned_loss=0.03798, over 4862.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.0286, over 971826.21 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 09:14:49,241 INFO [train.py:715] (4/8) Epoch 18, batch 17200, loss[loss=0.1025, simple_loss=0.1758, pruned_loss=0.01463, over 4812.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.02811, over 972084.66 frames.], batch size: 27, lr: 1.23e-04
2022-05-09 09:15:28,978 INFO [train.py:715] (4/8) Epoch 18, batch 17250, loss[loss=0.1361, simple_loss=0.2111, pruned_loss=0.03051, over 4810.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02839, over 971586.35 frames.], batch size: 27, lr: 1.23e-04
2022-05-09 09:16:08,238 INFO [train.py:715] (4/8) Epoch 18, batch 17300, loss[loss=0.1168, simple_loss=0.1918, pruned_loss=0.02086, over 4981.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02866, over 971634.30 frames.], batch size: 28, lr: 1.23e-04
2022-05-09 09:16:48,171 INFO [train.py:715] (4/8) Epoch 18, batch 17350, loss[loss=0.139, simple_loss=0.203, pruned_loss=0.0375, over 4838.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02821, over 971416.45 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 09:17:27,233 INFO [train.py:715] (4/8) Epoch 18, batch 17400, loss[loss=0.1298, simple_loss=0.2024, pruned_loss=0.02859, over 4824.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2054, pruned_loss=0.02791, over 971371.44 frames.], batch size: 27, lr: 1.23e-04
2022-05-09 09:18:07,024 INFO [train.py:715] (4/8) Epoch 18, batch 17450, loss[loss=0.1292, simple_loss=0.2051, pruned_loss=0.02668, over 4805.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2054, pruned_loss=0.02793, over 971028.47 frames.], batch size: 26, lr: 1.23e-04
2022-05-09 09:18:46,084 INFO [train.py:715] (4/8) Epoch 18, batch 17500, loss[loss=0.1231, simple_loss=0.2034, pruned_loss=0.02138, over 4844.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2053, pruned_loss=0.02765, over 971560.67 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 09:19:24,714 INFO [train.py:715] (4/8) Epoch 18, batch 17550, loss[loss=0.1314, simple_loss=0.2155, pruned_loss=0.02359, over 4798.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2052, pruned_loss=0.02775, over 971530.05 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:20:04,281 INFO [train.py:715] (4/8) Epoch 18, batch 17600, loss[loss=0.145, simple_loss=0.2073, pruned_loss=0.0414, over 4992.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02865, over 971614.05 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 09:20:43,551 INFO [train.py:715] (4/8) Epoch 18, batch 17650, loss[loss=0.1316, simple_loss=0.1926, pruned_loss=0.03532, over 4854.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02877, over 971529.72 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 09:21:22,849 INFO [train.py:715] (4/8) Epoch 18, batch 17700, loss[loss=0.1123, simple_loss=0.1828, pruned_loss=0.02091, over 4832.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02891, over 971893.69 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 09:22:01,951 INFO [train.py:715] (4/8) Epoch 18, batch 17750, loss[loss=0.1345, simple_loss=0.2138, pruned_loss=0.02763, over 4895.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02887, over 972144.49 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 09:22:41,553 INFO [train.py:715] (4/8) Epoch 18, batch 17800, loss[loss=0.1465, simple_loss=0.2138, pruned_loss=0.03954, over 4840.00 frames.], tot_loss[loss=0.132, simple_loss=0.2059, pruned_loss=0.02907, over 972418.37 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 09:23:20,834 INFO [train.py:715] (4/8) Epoch 18, batch 17850, loss[loss=0.1264, simple_loss=0.2118, pruned_loss=0.02047, over 4764.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02884, over 972510.22 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:23:59,347 INFO [train.py:715] (4/8) Epoch 18, batch 17900, loss[loss=0.1828, simple_loss=0.2471, pruned_loss=0.05928, over 4977.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2059, pruned_loss=0.02914, over 972747.06 frames.], batch size: 28, lr: 1.23e-04
2022-05-09 09:24:39,458 INFO [train.py:715] (4/8) Epoch 18, batch 17950, loss[loss=0.1201, simple_loss=0.1975, pruned_loss=0.02138, over 4786.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2057, pruned_loss=0.02879, over 972238.52 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:25:18,519 INFO [train.py:715] (4/8) Epoch 18, batch 18000, loss[loss=0.1663, simple_loss=0.2382, pruned_loss=0.04721, over 4902.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02885, over 971944.07 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 09:25:18,520 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 09:25:28,382 INFO [train.py:742] (4/8) Epoch 18, validation: loss=0.1046, simple_loss=0.1878, pruned_loss=0.01063, over 914524.00 frames.
2022-05-09 09:26:07,770 INFO [train.py:715] (4/8) Epoch 18, batch 18050, loss[loss=0.138, simple_loss=0.212, pruned_loss=0.03198, over 4875.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02886, over 972105.81 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 09:26:47,169 INFO [train.py:715] (4/8) Epoch 18, batch 18100, loss[loss=0.1525, simple_loss=0.2223, pruned_loss=0.04134, over 4990.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02932, over 972537.64 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 09:27:26,275 INFO [train.py:715] (4/8) Epoch 18, batch 18150, loss[loss=0.1243, simple_loss=0.2057, pruned_loss=0.02148, over 4917.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02887, over 972068.69 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:28:06,059 INFO [train.py:715] (4/8) Epoch 18, batch 18200, loss[loss=0.1269, simple_loss=0.1948, pruned_loss=0.02951, over 4858.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02879, over 972068.93 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 09:28:45,757 INFO [train.py:715] (4/8) Epoch 18, batch 18250, loss[loss=0.1244, simple_loss=0.1943, pruned_loss=0.02725, over 4753.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02894, over 970738.72 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 09:29:24,155 INFO [train.py:715] (4/8) Epoch 18, batch 18300, loss[loss=0.1262, simple_loss=0.208, pruned_loss=0.02216, over 4740.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02914, over 970310.51 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 09:30:03,826 INFO [train.py:715] (4/8) Epoch 18, batch 18350, loss[loss=0.1144, simple_loss=0.1917, pruned_loss=0.01858, over 4890.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02863, over 969641.96 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 09:30:43,382 INFO [train.py:715] (4/8) Epoch 18, batch 18400, loss[loss=0.1338, simple_loss=0.2059, pruned_loss=0.03079, over 4901.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02858, over 969123.49 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 09:31:22,381 INFO [train.py:715] (4/8) Epoch 18, batch 18450, loss[loss=0.1213, simple_loss=0.1992, pruned_loss=0.02175, over 4786.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2065, pruned_loss=0.02819, over 970744.10 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:32:01,512 INFO [train.py:715] (4/8) Epoch 18, batch 18500, loss[loss=0.1532, simple_loss=0.2185, pruned_loss=0.04393, over 4704.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2062, pruned_loss=0.02779, over 970554.69 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 09:32:40,870 INFO [train.py:715] (4/8) Epoch 18, batch 18550, loss[loss=0.1136, simple_loss=0.189, pruned_loss=0.01909, over 4690.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2066, pruned_loss=0.02794, over 971205.56 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 09:33:20,090 INFO [train.py:715] (4/8) Epoch 18, batch 18600, loss[loss=0.1423, simple_loss=0.2105, pruned_loss=0.03709, over 4914.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2054, pruned_loss=0.02767, over 971547.21 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:33:58,716 INFO [train.py:715] (4/8) Epoch 18, batch 18650, loss[loss=0.1062, simple_loss=0.1794, pruned_loss=0.01655, over 4931.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2049, pruned_loss=0.02778, over 971046.24 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 09:34:38,208 INFO [train.py:715] (4/8) Epoch 18, batch 18700, loss[loss=0.1332, simple_loss=0.2061, pruned_loss=0.03016, over 4780.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2053, pruned_loss=0.02785, over 970457.57 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:35:17,419 INFO [train.py:715] (4/8) Epoch 18, batch 18750, loss[loss=0.12, simple_loss=0.1931, pruned_loss=0.0235, over 4825.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02823, over 970394.46 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 09:35:56,634 INFO [train.py:715] (4/8) Epoch 18, batch 18800, loss[loss=0.1428, simple_loss=0.213, pruned_loss=0.03627, over 4910.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.02803, over 970870.45 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 09:36:36,000 INFO [train.py:715] (4/8) Epoch 18, batch 18850, loss[loss=0.1216, simple_loss=0.2077, pruned_loss=0.01776, over 4927.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02804, over 970992.96 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:37:15,846 INFO [train.py:715] (4/8) Epoch 18, batch 18900, loss[loss=0.1548, simple_loss=0.2382, pruned_loss=0.03565, over 4837.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.0282, over 970846.64 frames.], batch size: 26, lr: 1.23e-04
2022-05-09 09:37:54,909 INFO [train.py:715] (4/8) Epoch 18, batch 18950, loss[loss=0.1184, simple_loss=0.1887, pruned_loss=0.02409, over 4884.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02849, over 971972.74 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 09:38:33,359 INFO [train.py:715] (4/8) Epoch 18, batch 19000, loss[loss=0.1416, simple_loss=0.2168, pruned_loss=0.03323, over 4762.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02876, over 971756.45 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 09:39:12,867 INFO [train.py:715] (4/8) Epoch 18, batch 19050, loss[loss=0.1396, simple_loss=0.2224, pruned_loss=0.02842, over 4864.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02925, over 972751.48 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 09:39:51,874 INFO [train.py:715] (4/8) Epoch 18, batch 19100, loss[loss=0.1562, simple_loss=0.2271, pruned_loss=0.04271, over 4871.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.0293, over 972597.29 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 09:40:31,187 INFO [train.py:715] (4/8) Epoch 18, batch 19150, loss[loss=0.1286, simple_loss=0.2025, pruned_loss=0.02739, over 4782.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02909, over 972635.95 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:41:11,057 INFO [train.py:715] (4/8) Epoch 18, batch 19200, loss[loss=0.1314, simple_loss=0.196, pruned_loss=0.03342, over 4641.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02866, over 971614.97 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 09:41:50,578 INFO [train.py:715] (4/8) Epoch 18, batch 19250, loss[loss=0.1679, simple_loss=0.2512, pruned_loss=0.04236, over 4918.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02853, over 971396.79 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:42:29,654 INFO [train.py:715] (4/8) Epoch 18, batch 19300, loss[loss=0.1325, simple_loss=0.2084, pruned_loss=0.02825, over 4851.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02881, over 971484.52 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 09:43:08,117 INFO [train.py:715] (4/8) Epoch 18, batch 19350, loss[loss=0.1361, simple_loss=0.2107, pruned_loss=0.03072, over 4971.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.0284, over 972476.59 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 09:43:47,525 INFO [train.py:715] (4/8) Epoch 18, batch 19400, loss[loss=0.1114, simple_loss=0.1921, pruned_loss=0.01537, over 4804.00 frames.], tot_loss[loss=0.132, simple_loss=0.2069, pruned_loss=0.02856, over 972466.51 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 09:44:26,736 INFO [train.py:715] (4/8) Epoch 18, batch 19450, loss[loss=0.1389, simple_loss=0.2056, pruned_loss=0.03607, over 4887.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02858, over 973154.65 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 09:45:05,481 INFO [train.py:715] (4/8) Epoch 18, batch 19500, loss[loss=0.1097, simple_loss=0.1926, pruned_loss=0.01345, over 4806.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02896, over 973062.85 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:45:44,652 INFO [train.py:715] (4/8) Epoch 18, batch 19550, loss[loss=0.1181, simple_loss=0.1972, pruned_loss=0.01954, over 4939.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02856, over 973234.65 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:46:24,059 INFO [train.py:715] (4/8) Epoch 18, batch 19600, loss[loss=0.131, simple_loss=0.2046, pruned_loss=0.02873, over 4918.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2068, pruned_loss=0.02854, over 973434.00 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 09:47:02,884 INFO [train.py:715] (4/8) Epoch 18, batch 19650, loss[loss=0.204, simple_loss=0.2791, pruned_loss=0.06448, over 4781.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02921, over 972996.01 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 09:47:41,711 INFO [train.py:715] (4/8) Epoch 18, batch 19700, loss[loss=0.2035, simple_loss=0.2751, pruned_loss=0.06595, over 4927.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02965, over 973122.83 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 09:48:21,728 INFO [train.py:715] (4/8) Epoch 18, batch 19750, loss[loss=0.1596, simple_loss=0.231, pruned_loss=0.0441, over 4944.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2089, pruned_loss=0.03009, over 972631.79 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 09:49:01,596 INFO [train.py:715] (4/8) Epoch 18, batch 19800, loss[loss=0.1186, simple_loss=0.1964, pruned_loss=0.02042, over 4975.00 frames.], tot_loss[loss=0.1343, simple_loss=0.2089, pruned_loss=0.02988, over 972237.32 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 09:49:40,677 INFO [train.py:715] (4/8) Epoch 18, batch 19850, loss[loss=0.1555, simple_loss=0.2262, pruned_loss=0.04241, over 4870.00 frames.], tot_loss[loss=0.1346, simple_loss=0.2092, pruned_loss=0.03004, over 971779.95 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 09:50:20,119 INFO [train.py:715] (4/8) Epoch 18, batch 19900, loss[loss=0.1503, simple_loss=0.2298, pruned_loss=0.03536, over 4895.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2085, pruned_loss=0.02962, over 971889.23 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 09:50:59,797 INFO [train.py:715] (4/8) Epoch 18, batch 19950, loss[loss=0.1223, simple_loss=0.1923, pruned_loss=0.02618, over 4845.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02935, over 972472.45 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 09:51:39,045 INFO [train.py:715] (4/8) Epoch 18, batch 20000, loss[loss=0.1285, simple_loss=0.2005, pruned_loss=0.0283, over 4842.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02922, over 972156.91 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 09:52:18,801 INFO [train.py:715] (4/8) Epoch 18, batch 20050, loss[loss=0.1473, simple_loss=0.2165, pruned_loss=0.0391, over 4879.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02943, over 972255.06 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 09:52:59,023 INFO [train.py:715] (4/8) Epoch 18, batch 20100, loss[loss=0.1519, simple_loss=0.2368, pruned_loss=0.03347, over 4959.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02937, over 972362.46 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 09:53:39,140 INFO [train.py:715] (4/8) Epoch 18, batch 20150, loss[loss=0.1367, simple_loss=0.206, pruned_loss=0.03366, over 4759.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02915, over 971968.91 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 09:54:18,208 INFO [train.py:715] (4/8) Epoch 18, batch 20200, loss[loss=0.1295, simple_loss=0.1988, pruned_loss=0.03004, over 4711.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.0289, over 972598.65 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 09:54:57,196 INFO [train.py:715] (4/8) Epoch 18, batch 20250, loss[loss=0.1503, simple_loss=0.225, pruned_loss=0.03782, over 4939.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02849, over 973011.23 frames.], batch size: 39, lr: 1.23e-04
2022-05-09 09:55:36,876 INFO [train.py:715] (4/8) Epoch 18, batch 20300, loss[loss=0.1664, simple_loss=0.2411, pruned_loss=0.04583, over 4746.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02843, over 972141.55 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 09:56:16,003 INFO [train.py:715] (4/8) Epoch 18, batch 20350, loss[loss=0.1557, simple_loss=0.226, pruned_loss=0.04271, over 4704.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02839, over 971926.61 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 09:56:55,259 INFO [train.py:715] (4/8) Epoch 18, batch 20400, loss[loss=0.1361, simple_loss=0.2082, pruned_loss=0.03204, over 4688.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02866, over 972291.56 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 09:57:34,098 INFO [train.py:715] (4/8) Epoch 18, batch 20450, loss[loss=0.1535, simple_loss=0.2207, pruned_loss=0.04316, over 4835.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02903, over 973101.54 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 09:58:14,212 INFO [train.py:715] (4/8) Epoch 18, batch 20500, loss[loss=0.1301, simple_loss=0.1969, pruned_loss=0.03164, over 4967.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.0288, over 973249.17 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 09:58:52,924 INFO [train.py:715] (4/8) Epoch 18, batch 20550, loss[loss=0.1357, simple_loss=0.2052, pruned_loss=0.03311, over 4689.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02893, over 973007.67 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 09:59:31,853 INFO [train.py:715] (4/8) Epoch 18, batch 20600, loss[loss=0.1441, simple_loss=0.2067, pruned_loss=0.04078, over 4966.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02879, over 972710.20 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 10:00:10,870 INFO [train.py:715] (4/8) Epoch 18, batch 20650, loss[loss=0.1159, simple_loss=0.1888, pruned_loss=0.02152, over 4984.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02916, over 972484.58 frames.], batch size: 27, lr: 1.23e-04
2022-05-09 10:00:50,419 INFO [train.py:715] (4/8) Epoch 18, batch 20700, loss[loss=0.1861, simple_loss=0.2477, pruned_loss=0.06225, over 4951.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02913, over 972491.47 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 10:01:28,858 INFO [train.py:715] (4/8) Epoch 18, batch 20750, loss[loss=0.1329, simple_loss=0.2024, pruned_loss=0.0317, over 4830.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.0292, over 973205.15 frames.], batch size: 27, lr: 1.23e-04
2022-05-09 10:02:08,325 INFO [train.py:715] (4/8) Epoch 18, batch 20800, loss[loss=0.134, simple_loss=0.2136, pruned_loss=0.02715, over 4970.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02923, over 973620.53 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 10:02:47,764 INFO [train.py:715] (4/8) Epoch 18, batch 20850, loss[loss=0.09515, simple_loss=0.1562, pruned_loss=0.01706, over 4734.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2074, pruned_loss=0.02936, over 973376.39 frames.], batch size: 12, lr: 1.23e-04
2022-05-09 10:03:26,623 INFO [train.py:715] (4/8) Epoch 18, batch 20900, loss[loss=0.1384, simple_loss=0.2261, pruned_loss=0.02537, over 4825.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02955, over 973133.92 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 10:04:05,318 INFO [train.py:715] (4/8) Epoch 18, batch 20950, loss[loss=0.1162, simple_loss=0.1884, pruned_loss=0.02201, over 4903.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02952, over 973180.77 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 10:04:44,840 INFO [train.py:715] (4/8) Epoch 18, batch 21000, loss[loss=0.1378, simple_loss=0.2153, pruned_loss=0.03018, over 4831.00 frames.], tot_loss[loss=0.1328, simple_loss=0.207, pruned_loss=0.02929, over 972695.16 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 10:04:44,841 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 10:04:54,815 INFO [train.py:742] (4/8) Epoch 18, validation: loss=0.1046, simple_loss=0.1879, pruned_loss=0.01059, over 914524.00 frames.
2022-05-09 10:05:34,567 INFO [train.py:715] (4/8) Epoch 18, batch 21050, loss[loss=0.1309, simple_loss=0.2146, pruned_loss=0.02359, over 4910.00 frames.], tot_loss[loss=0.1327, simple_loss=0.207, pruned_loss=0.02919, over 972583.72 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 10:06:14,353 INFO [train.py:715] (4/8) Epoch 18, batch 21100, loss[loss=0.1199, simple_loss=0.1889, pruned_loss=0.02539, over 4819.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2073, pruned_loss=0.02906, over 972409.72 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 10:06:53,516 INFO [train.py:715] (4/8) Epoch 18, batch 21150, loss[loss=0.125, simple_loss=0.2027, pruned_loss=0.02363, over 4933.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02903, over 972942.55 frames.], batch size: 29, lr: 1.23e-04
2022-05-09 10:07:33,003 INFO [train.py:715] (4/8) Epoch 18, batch 21200, loss[loss=0.1208, simple_loss=0.206, pruned_loss=0.01783, over 4941.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.0285, over 973242.37 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 10:08:12,710 INFO [train.py:715] (4/8) Epoch 18, batch 21250, loss[loss=0.1241, simple_loss=0.1894, pruned_loss=0.02943, over 4828.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02869, over 973498.13 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 10:08:51,640 INFO [train.py:715] (4/8) Epoch 18, batch 21300, loss[loss=0.1574, simple_loss=0.2287, pruned_loss=0.04308, over 4984.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02907, over 973585.79 frames.], batch size: 31, lr: 1.23e-04
2022-05-09 10:09:30,195 INFO [train.py:715] (4/8) Epoch 18, batch 21350, loss[loss=0.1607, simple_loss=0.2288, pruned_loss=0.04636, over 4843.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02935, over 973107.90 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 10:10:09,587 INFO [train.py:715] (4/8) Epoch 18, batch 21400, loss[loss=0.1035, simple_loss=0.1673, pruned_loss=0.01978, over 4855.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2069, pruned_loss=0.02949, over 972840.14 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 10:10:51,764 INFO [train.py:715] (4/8) Epoch 18, batch 21450, loss[loss=0.1257, simple_loss=0.2049, pruned_loss=0.02318, over 4904.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02885, over 972697.11 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 10:11:30,942 INFO [train.py:715] (4/8) Epoch 18, batch 21500, loss[loss=0.1386, simple_loss=0.2191, pruned_loss=0.02906, over 4924.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.029, over 973005.93 frames.], batch size: 29, lr: 1.23e-04
2022-05-09 10:12:09,695 INFO [train.py:715] (4/8) Epoch 18, batch 21550, loss[loss=0.121, simple_loss=0.2039, pruned_loss=0.01898, over 4914.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02861, over 972128.33 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 10:12:49,092 INFO [train.py:715] (4/8) Epoch 18, batch 21600, loss[loss=0.1211, simple_loss=0.2038, pruned_loss=0.01919, over 4801.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2074, pruned_loss=0.02898, over 972051.93 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 10:13:28,301 INFO [train.py:715] (4/8) Epoch 18, batch 21650, loss[loss=0.1419, simple_loss=0.2093, pruned_loss=0.03722, over 4779.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02872, over 972700.32 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 10:14:06,696 INFO [train.py:715] (4/8) Epoch 18, batch 21700, loss[loss=0.1095, simple_loss=0.1898, pruned_loss=0.01461, over 4973.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02889, over 973793.75 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 10:14:45,678 INFO [train.py:715] (4/8) Epoch 18, batch 21750, loss[loss=0.1291, simple_loss=0.2089, pruned_loss=0.02466, over 4857.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02854, over 973180.94 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 10:15:24,826 INFO [train.py:715] (4/8) Epoch 18, batch 21800, loss[loss=0.1518, simple_loss=0.2263, pruned_loss=0.03862, over 4983.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02834, over 972779.55 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 10:16:04,132 INFO [train.py:715] (4/8) Epoch 18, batch 21850, loss[loss=0.1259, simple_loss=0.1986, pruned_loss=0.02656, over 4752.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.02884, over 973388.11 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 10:16:43,560 INFO [train.py:715] (4/8) Epoch 18, batch 21900, loss[loss=0.1068, simple_loss=0.1808, pruned_loss=0.01639, over 4917.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2074, pruned_loss=0.029, over 974098.98 frames.], batch size: 29, lr: 1.23e-04
2022-05-09 10:17:23,084 INFO [train.py:715] (4/8) Epoch 18, batch 21950, loss[loss=0.1484, simple_loss=0.2213, pruned_loss=0.03775, over 4939.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2072, pruned_loss=0.02864, over 973878.80 frames.], batch size: 23, lr: 1.23e-04
2022-05-09 10:18:02,137 INFO [train.py:715] (4/8) Epoch 18, batch 22000, loss[loss=0.1122, simple_loss=0.1893, pruned_loss=0.01752, over 4796.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2067, pruned_loss=0.02844, over 973539.21 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 10:18:41,238 INFO [train.py:715] (4/8) Epoch 18, batch 22050, loss[loss=0.1161, simple_loss=0.1865, pruned_loss=0.02283, over 4755.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02853, over 972679.75 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 10:19:20,735 INFO [train.py:715] (4/8) Epoch 18, batch 22100, loss[loss=0.1341, simple_loss=0.2044, pruned_loss=0.03193, over 4935.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02835, over 972280.71 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 10:19:59,606 INFO [train.py:715] (4/8) Epoch 18, batch 22150, loss[loss=0.1071, simple_loss=0.177, pruned_loss=0.01865, over 4865.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02829, over 971136.64 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 10:20:39,095 INFO [train.py:715] (4/8) Epoch 18, batch 22200, loss[loss=0.1604, simple_loss=0.2292, pruned_loss=0.0458, over 4789.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02878, over 971472.76 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 10:21:17,771 INFO [train.py:715] (4/8) Epoch 18, batch 22250, loss[loss=0.1572, simple_loss=0.231, pruned_loss=0.04173, over 4745.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02903, over 971696.72 frames.], batch size: 12, lr: 1.23e-04
2022-05-09 10:21:57,019 INFO [train.py:715] (4/8) Epoch 18, batch 22300, loss[loss=0.1349, simple_loss=0.216, pruned_loss=0.02686, over 4753.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02901, over 972243.00 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 10:22:35,717 INFO [train.py:715] (4/8) Epoch 18, batch 22350, loss[loss=0.1483, simple_loss=0.2325, pruned_loss=0.03202, over 4909.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02848, over 972510.28 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 10:23:14,497 INFO [train.py:715] (4/8) Epoch 18, batch 22400, loss[loss=0.1146, simple_loss=0.1886, pruned_loss=0.02032, over 4764.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2067, pruned_loss=0.02852, over 971231.10 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 10:23:53,398 INFO [train.py:715] (4/8) Epoch 18, batch 22450, loss[loss=0.1385, simple_loss=0.2093, pruned_loss=0.03382, over 4886.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02831, over 971406.42 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 10:24:32,484 INFO [train.py:715] (4/8) Epoch 18, batch 22500, loss[loss=0.1114, simple_loss=0.1874, pruned_loss=0.01771, over 4974.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02843, over 972503.19 frames.], batch size: 24, lr: 1.23e-04
2022-05-09 10:25:11,274 INFO [train.py:715] (4/8) Epoch 18, batch 22550, loss[loss=0.127, simple_loss=0.1963, pruned_loss=0.02885, over 4970.00 frames.], tot_loss[loss=0.1311, simple_loss=0.206, pruned_loss=0.02808, over 972657.85 frames.], batch size: 35, lr: 1.23e-04
2022-05-09 10:25:50,059 INFO [train.py:715] (4/8) Epoch 18, batch 22600, loss[loss=0.1179, simple_loss=0.1994, pruned_loss=0.01824, over 4774.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2065, pruned_loss=0.02829, over 972257.19 frames.], batch size: 17, lr: 1.23e-04
2022-05-09 10:26:29,081 INFO [train.py:715] (4/8) Epoch 18, batch 22650, loss[loss=0.1189, simple_loss=0.1825, pruned_loss=0.02767, over 4788.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02838, over 971946.83 frames.], batch size: 12, lr: 1.23e-04
2022-05-09 10:27:07,864 INFO [train.py:715] (4/8) Epoch 18, batch 22700, loss[loss=0.1687, simple_loss=0.2299, pruned_loss=0.05379, over 4864.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02869, over 972742.91 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 10:27:46,841 INFO [train.py:715] (4/8) Epoch 18, batch 22750, loss[loss=0.1311, simple_loss=0.1849, pruned_loss=0.0386, over 4837.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02883, over 972698.46 frames.], batch size: 15, lr: 1.23e-04
2022-05-09 10:28:26,215 INFO [train.py:715] (4/8) Epoch 18, batch 22800, loss[loss=0.1604, simple_loss=0.2446, pruned_loss=0.03807, over 4878.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02862, over 972183.63 frames.], batch size: 38, lr: 1.23e-04
2022-05-09 10:29:04,924 INFO [train.py:715] (4/8) Epoch 18, batch 22850, loss[loss=0.1454, simple_loss=0.2138, pruned_loss=0.03846, over 4841.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02886, over 972715.66 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 10:29:43,880 INFO [train.py:715] (4/8) Epoch 18, batch 22900, loss[loss=0.1562, simple_loss=0.2235, pruned_loss=0.04443, over 4896.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02903, over 973588.46 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 10:30:22,780 INFO [train.py:715] (4/8) Epoch 18, batch 22950, loss[loss=0.1363, simple_loss=0.219, pruned_loss=0.0268, over 4939.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02905, over 972933.21 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 10:31:02,200 INFO [train.py:715] (4/8) Epoch 18, batch 23000, loss[loss=0.1668, simple_loss=0.2492, pruned_loss=0.04213, over 4877.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.02918, over 973188.59 frames.], batch size: 16, lr: 1.23e-04
2022-05-09 10:31:40,967 INFO [train.py:715] (4/8) Epoch 18, batch 23050, loss[loss=0.1436, simple_loss=0.2117, pruned_loss=0.0377, over 4805.00 frames.], tot_loss[loss=0.1338, simple_loss=0.2082, pruned_loss=0.02971, over 973642.25 frames.], batch size: 21, lr: 1.23e-04
2022-05-09 10:32:20,093 INFO [train.py:715] (4/8) Epoch 18, batch 23100, loss[loss=0.1497, simple_loss=0.2175, pruned_loss=0.04098, over 4821.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2077, pruned_loss=0.02968, over 973341.50 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 10:32:59,657 INFO [train.py:715] (4/8) Epoch 18, batch 23150, loss[loss=0.1329, simple_loss=0.1888, pruned_loss=0.03844, over 4815.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02937, over 973119.69 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 10:33:38,764 INFO [train.py:715] (4/8) Epoch 18, batch 23200, loss[loss=0.1289, simple_loss=0.1988, pruned_loss=0.02944, over 4816.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2077, pruned_loss=0.02922, over 972429.53 frames.], batch size: 13, lr: 1.23e-04
2022-05-09 10:34:17,633 INFO [train.py:715] (4/8) Epoch 18, batch 23250, loss[loss=0.1476, simple_loss=0.2226, pruned_loss=0.03629, over 4777.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2073, pruned_loss=0.02877, over 972900.67 frames.], batch size: 14, lr: 1.23e-04
2022-05-09 10:34:56,941 INFO [train.py:715] (4/8) Epoch 18, batch 23300, loss[loss=0.1297, simple_loss=0.2045, pruned_loss=0.02744, over 4755.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02848, over 972833.57 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 10:35:36,584 INFO [train.py:715] (4/8) Epoch 18, batch 23350, loss[loss=0.1363, simple_loss=0.2122, pruned_loss=0.03024, over 4816.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02868, over 973162.00 frames.], batch size: 26, lr: 1.23e-04
2022-05-09 10:36:15,531 INFO [train.py:715] (4/8) Epoch 18, batch 23400, loss[loss=0.1174, simple_loss=0.1969, pruned_loss=0.01891, over 4932.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02818, over 973478.76 frames.], batch size: 29, lr: 1.23e-04
2022-05-09 10:36:54,043 INFO [train.py:715] (4/8) Epoch 18, batch 23450, loss[loss=0.1213, simple_loss=0.1886, pruned_loss=0.02701, over 4848.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02846, over 973830.50 frames.], batch size: 30, lr: 1.23e-04
2022-05-09 10:37:33,555 INFO [train.py:715] (4/8) Epoch 18, batch 23500, loss[loss=0.1617, simple_loss=0.2229, pruned_loss=0.05022, over 4837.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02907, over 973560.63 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 10:38:12,431 INFO [train.py:715] (4/8) Epoch 18, batch 23550, loss[loss=0.1328, simple_loss=0.2168, pruned_loss=0.0244, over 4852.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02914, over 973461.30 frames.], batch size: 20, lr: 1.23e-04
2022-05-09 10:38:51,085 INFO [train.py:715] (4/8) Epoch 18, batch 23600, loss[loss=0.1362, simple_loss=0.2261, pruned_loss=0.02314, over 4805.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02928, over 972249.04 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 10:39:30,021 INFO [train.py:715] (4/8) Epoch 18, batch 23650, loss[loss=0.1175, simple_loss=0.193, pruned_loss=0.02102, over 4808.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02907, over 972303.28 frames.], batch size: 25, lr: 1.23e-04
2022-05-09 10:40:08,660 INFO [train.py:715] (4/8) Epoch 18, batch 23700, loss[loss=0.1336, simple_loss=0.2032, pruned_loss=0.03206, over 4858.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2056, pruned_loss=0.02891, over 971475.77 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 10:40:47,470 INFO [train.py:715] (4/8) Epoch 18, batch 23750, loss[loss=0.1024, simple_loss=0.1762, pruned_loss=0.01427, over 4769.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2049, pruned_loss=0.02859, over 971443.39 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 10:41:26,881 INFO [train.py:715] (4/8) Epoch 18, batch 23800, loss[loss=0.1282, simple_loss=0.195, pruned_loss=0.03069, over 4851.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2042, pruned_loss=0.02811, over 972050.33 frames.], batch size: 32, lr: 1.23e-04
2022-05-09 10:42:06,532 INFO [train.py:715] (4/8) Epoch 18, batch 23850, loss[loss=0.1234, simple_loss=0.1934, pruned_loss=0.02672, over 4768.00 frames.], tot_loss[loss=0.13, simple_loss=0.2043, pruned_loss=0.02788, over 971502.01 frames.], batch size: 18, lr: 1.23e-04
2022-05-09 10:42:45,370 INFO [train.py:715] (4/8) Epoch 18, batch 23900, loss[loss=0.1164, simple_loss=0.188, pruned_loss=0.02243, over 4756.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2047, pruned_loss=0.02841, over 971976.66 frames.], batch size: 19, lr: 1.23e-04
2022-05-09 10:43:24,101 INFO [train.py:715] (4/8) Epoch 18, batch 23950, loss[loss=0.1373, simple_loss=0.216, pruned_loss=0.02928, over 4867.00 frames.], tot_loss[loss=0.131, simple_loss=0.2049, pruned_loss=0.0286, over 972028.62 frames.], batch size: 22, lr: 1.22e-04
2022-05-09 10:44:03,428 INFO [train.py:715] (4/8) Epoch 18, batch 24000, loss[loss=0.1104, simple_loss=0.1736, pruned_loss=0.02363, over 4816.00 frames.], tot_loss[loss=0.131, simple_loss=0.2048, pruned_loss=0.02855, over 971664.44 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 10:44:03,428 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 10:44:13,350 INFO [train.py:742] (4/8) Epoch 18, validation: loss=0.1045, simple_loss=0.1878, pruned_loss=0.01057, over 914524.00 frames.
2022-05-09 10:44:52,994 INFO [train.py:715] (4/8) Epoch 18, batch 24050, loss[loss=0.1346, simple_loss=0.2211, pruned_loss=0.024, over 4642.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2056, pruned_loss=0.02903, over 972274.27 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 10:45:31,812 INFO [train.py:715] (4/8) Epoch 18, batch 24100, loss[loss=0.1429, simple_loss=0.2138, pruned_loss=0.03599, over 4910.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2049, pruned_loss=0.02831, over 972623.63 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 10:46:10,744 INFO [train.py:715] (4/8) Epoch 18, batch 24150, loss[loss=0.1428, simple_loss=0.2118, pruned_loss=0.03688, over 4664.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2051, pruned_loss=0.0287, over 972539.46 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 10:46:50,171 INFO [train.py:715] (4/8) Epoch 18, batch 24200, loss[loss=0.1171, simple_loss=0.1865, pruned_loss=0.02382, over 4824.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2044, pruned_loss=0.0286, over 972926.85 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 10:47:29,222 INFO [train.py:715] (4/8) Epoch 18, batch 24250, loss[loss=0.1227, simple_loss=0.1949, pruned_loss=0.0252, over 4994.00 frames.], tot_loss[loss=0.132, simple_loss=0.2056, pruned_loss=0.02919, over 972792.67 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 10:48:08,105 INFO [train.py:715] (4/8) Epoch 18, batch 24300, loss[loss=0.1332, simple_loss=0.2139, pruned_loss=0.02624, over 4942.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2055, pruned_loss=0.0288, over 972467.83 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 10:48:46,585 INFO [train.py:715] (4/8) Epoch 18, batch 24350, loss[loss=0.1472, simple_loss=0.206, pruned_loss=0.04419, over 4822.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02909, over 972287.88 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 10:49:25,641 INFO [train.py:715] (4/8) Epoch 18, batch 24400, loss[loss=0.1064, simple_loss=0.1769, pruned_loss=0.01792, over 4812.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02912, over 972740.41 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 10:50:04,249 INFO [train.py:715] (4/8) Epoch 18, batch 24450, loss[loss=0.1153, simple_loss=0.1918, pruned_loss=0.01942, over 4749.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02912, over 971947.40 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 10:50:42,848 INFO [train.py:715] (4/8) Epoch 18, batch 24500, loss[loss=0.1233, simple_loss=0.2028, pruned_loss=0.02186, over 4957.00 frames.], tot_loss[loss=0.132, simple_loss=0.206, pruned_loss=0.02898, over 972645.55 frames.], batch size: 39, lr: 1.22e-04
2022-05-09 10:51:22,305 INFO [train.py:715] (4/8) Epoch 18, batch 24550, loss[loss=0.1498, simple_loss=0.2193, pruned_loss=0.04019, over 4886.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.0291, over 972926.88 frames.], batch size: 39, lr: 1.22e-04
2022-05-09 10:52:01,526 INFO [train.py:715] (4/8) Epoch 18, batch 24600, loss[loss=0.1284, simple_loss=0.2005, pruned_loss=0.02816, over 4822.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02905, over 973582.65 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 10:52:40,238 INFO [train.py:715] (4/8) Epoch 18, batch 24650, loss[loss=0.1538, simple_loss=0.2319, pruned_loss=0.03784, over 4743.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02901, over 973246.72 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 10:53:18,842 INFO [train.py:715] (4/8) Epoch 18, batch 24700, loss[loss=0.132, simple_loss=0.2103, pruned_loss=0.02686, over 4863.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02895, over 972672.93 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 10:53:58,060 INFO [train.py:715] (4/8) Epoch 18, batch 24750, loss[loss=0.1219, simple_loss=0.1993, pruned_loss=0.02227, over 4752.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2054, pruned_loss=0.02849, over 972963.40 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 10:54:37,026 INFO [train.py:715] (4/8) Epoch 18, batch 24800, loss[loss=0.1072, simple_loss=0.1859, pruned_loss=0.01424, over 4988.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02862, over 971836.10 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 10:55:16,442 INFO [train.py:715] (4/8) Epoch 18, batch 24850, loss[loss=0.1253, simple_loss=0.2063, pruned_loss=0.02213, over 4878.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02866, over 971534.46 frames.], batch size: 22, lr: 1.22e-04
2022-05-09 10:55:55,499 INFO [train.py:715] (4/8) Epoch 18, batch 24900, loss[loss=0.138, simple_loss=0.2064, pruned_loss=0.03478, over 4968.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02912, over 971855.31 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 10:56:35,062 INFO [train.py:715] (4/8) Epoch 18, batch 24950, loss[loss=0.1268, simple_loss=0.1971, pruned_loss=0.02823, over 4846.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02948, over 972262.53 frames.], batch size: 32, lr: 1.22e-04
2022-05-09 10:57:14,185 INFO [train.py:715] (4/8) Epoch 18, batch 25000, loss[loss=0.1099, simple_loss=0.1934, pruned_loss=0.01316, over 4833.00 frames.], tot_loss[loss=0.132, simple_loss=0.2061, pruned_loss=0.02894, over 972589.59 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 10:57:52,842 INFO [train.py:715] (4/8) Epoch 18, batch 25050, loss[loss=0.1475, simple_loss=0.2193, pruned_loss=0.03784, over 4861.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02902, over 972078.41 frames.], batch size: 30, lr: 1.22e-04
2022-05-09 10:58:32,133 INFO [train.py:715] (4/8) Epoch 18, batch 25100, loss[loss=0.145, simple_loss=0.2169, pruned_loss=0.03654, over 4773.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.0291, over 972166.43 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 10:59:11,693 INFO [train.py:715] (4/8) Epoch 18, batch 25150, loss[loss=0.1202, simple_loss=0.1932, pruned_loss=0.02358, over 4806.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02909, over 972371.26 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 10:59:50,259 INFO [train.py:715] (4/8) Epoch 18, batch 25200, loss[loss=0.1466, simple_loss=0.223, pruned_loss=0.03512, over 4791.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02904, over 973123.39 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:00:29,819 INFO [train.py:715] (4/8) Epoch 18, batch 25250, loss[loss=0.143, simple_loss=0.2253, pruned_loss=0.0303, over 4851.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02875, over 973848.10 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 11:01:09,551 INFO [train.py:715] (4/8) Epoch 18, batch 25300, loss[loss=0.1173, simple_loss=0.1938, pruned_loss=0.0204, over 4978.00 frames.], tot_loss[loss=0.1309, simple_loss=0.205, pruned_loss=0.02839, over 973217.81 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 11:01:48,681 INFO [train.py:715] (4/8) Epoch 18, batch 25350, loss[loss=0.09964, simple_loss=0.1819, pruned_loss=0.008673, over 4962.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2041, pruned_loss=0.02801, over 972820.19 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 11:02:27,382 INFO [train.py:715] (4/8) Epoch 18, batch 25400, loss[loss=0.1327, simple_loss=0.2153, pruned_loss=0.02501, over 4931.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2047, pruned_loss=0.02793, over 972551.24 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 11:03:06,964 INFO [train.py:715] (4/8) Epoch 18, batch 25450, loss[loss=0.1481, simple_loss=0.2256, pruned_loss=0.03526, over 4829.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2046, pruned_loss=0.0278, over 972009.30 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 11:03:45,936 INFO [train.py:715] (4/8) Epoch 18, batch 25500, loss[loss=0.1495, simple_loss=0.2281, pruned_loss=0.03543, over 4976.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2048, pruned_loss=0.02808, over 972029.93 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:04:24,925 INFO [train.py:715] (4/8) Epoch 18, batch 25550, loss[loss=0.1233, simple_loss=0.1949, pruned_loss=0.0259, over 4912.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2051, pruned_loss=0.02857, over 971788.19 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:05:04,556 INFO [train.py:715] (4/8) Epoch 18, batch 25600, loss[loss=0.1277, simple_loss=0.2108, pruned_loss=0.02236, over 4830.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02839, over 972020.30 frames.], batch size: 30, lr: 1.22e-04
2022-05-09 11:05:44,107 INFO [train.py:715] (4/8) Epoch 18, batch 25650, loss[loss=0.1406, simple_loss=0.2146, pruned_loss=0.03334, over 4697.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.0289, over 971701.82 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:06:23,311 INFO [train.py:715] (4/8) Epoch 18, batch 25700, loss[loss=0.1211, simple_loss=0.1796, pruned_loss=0.03131, over 4862.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2046, pruned_loss=0.02816, over 971553.43 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 11:07:02,568 INFO [train.py:715] (4/8) Epoch 18, batch 25750, loss[loss=0.1169, simple_loss=0.1845, pruned_loss=0.02461, over 4804.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2049, pruned_loss=0.02828, over 971805.99 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 11:07:41,970 INFO [train.py:715] (4/8) Epoch 18, batch 25800, loss[loss=0.1556, simple_loss=0.2496, pruned_loss=0.03076, over 4974.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2055, pruned_loss=0.02858, over 972029.17 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:08:20,794 INFO [train.py:715] (4/8) Epoch 18, batch 25850, loss[loss=0.1249, simple_loss=0.1929, pruned_loss=0.02841, over 4879.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2048, pruned_loss=0.02811, over 972672.10 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 11:08:59,115 INFO [train.py:715] (4/8) Epoch 18, batch 25900, loss[loss=0.1304, simple_loss=0.2141, pruned_loss=0.0233, over 4859.00 frames.], tot_loss[loss=0.131, simple_loss=0.2055, pruned_loss=0.02827, over 972632.26 frames.], batch size: 20, lr: 1.22e-04
2022-05-09 11:09:38,439 INFO [train.py:715] (4/8) Epoch 18, batch 25950, loss[loss=0.1327, simple_loss=0.2099, pruned_loss=0.02772, over 4922.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02825, over 973123.14 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 11:10:17,516 INFO [train.py:715] (4/8) Epoch 18, batch 26000, loss[loss=0.1494, simple_loss=0.2122, pruned_loss=0.04331, over 4845.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2051, pruned_loss=0.02834, over 972770.17 frames.], batch size: 34, lr: 1.22e-04
2022-05-09 11:10:56,985 INFO [train.py:715] (4/8) Epoch 18, batch 26050, loss[loss=0.132, simple_loss=0.206, pruned_loss=0.02902, over 4733.00 frames.], tot_loss[loss=0.131, simple_loss=0.2052, pruned_loss=0.02842, over 972038.33 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 11:11:36,114 INFO [train.py:715] (4/8) Epoch 18, batch 26100, loss[loss=0.1218, simple_loss=0.1951, pruned_loss=0.0242, over 4923.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2047, pruned_loss=0.02841, over 972038.24 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:12:15,694 INFO [train.py:715] (4/8) Epoch 18, batch 26150, loss[loss=0.122, simple_loss=0.2018, pruned_loss=0.02106, over 4800.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02878, over 972363.15 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 11:12:54,904 INFO [train.py:715] (4/8) Epoch 18, batch 26200, loss[loss=0.1351, simple_loss=0.2117, pruned_loss=0.02924, over 4877.00 frames.], tot_loss[loss=0.1312, simple_loss=0.205, pruned_loss=0.02865, over 972244.33 frames.], batch size: 32, lr: 1.22e-04
2022-05-09 11:13:33,238 INFO [train.py:715] (4/8) Epoch 18, batch 26250, loss[loss=0.1559, simple_loss=0.2473, pruned_loss=0.03228, over 4875.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2056, pruned_loss=0.02882, over 971612.91 frames.], batch size: 20, lr: 1.22e-04
2022-05-09 11:14:12,859 INFO [train.py:715] (4/8) Epoch 18, batch 26300, loss[loss=0.1463, simple_loss=0.228, pruned_loss=0.0323, over 4814.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2067, pruned_loss=0.02932, over 973130.00 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 11:14:51,548 INFO [train.py:715] (4/8) Epoch 18, batch 26350, loss[loss=0.1306, simple_loss=0.2041, pruned_loss=0.02854, over 4927.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.02941, over 972801.19 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:15:30,590 INFO [train.py:715] (4/8) Epoch 18, batch 26400, loss[loss=0.1276, simple_loss=0.2072, pruned_loss=0.024, over 4897.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02913, over 972837.44 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 11:16:09,485 INFO [train.py:715] (4/8) Epoch 18, batch 26450, loss[loss=0.1205, simple_loss=0.2039, pruned_loss=0.01852, over 4928.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02912, over 973327.28 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 11:16:49,039 INFO [train.py:715] (4/8) Epoch 18, batch 26500, loss[loss=0.1425, simple_loss=0.2204, pruned_loss=0.03229, over 4803.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2069, pruned_loss=0.02881, over 972581.73 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 11:17:28,073 INFO [train.py:715] (4/8) Epoch 18, batch 26550, loss[loss=0.136, simple_loss=0.2133, pruned_loss=0.02935, over 4752.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02899, over 972527.86 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:18:06,862 INFO [train.py:715] (4/8) Epoch 18, batch 26600, loss[loss=0.1254, simple_loss=0.2074, pruned_loss=0.02171, over 4873.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02912, over 972615.58 frames.], batch size: 20, lr: 1.22e-04
2022-05-09 11:18:46,127 INFO [train.py:715] (4/8) Epoch 18, batch 26650, loss[loss=0.1422, simple_loss=0.2137, pruned_loss=0.03536, over 4749.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2067, pruned_loss=0.02922, over 972740.03 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 11:19:25,269 INFO [train.py:715] (4/8) Epoch 18, batch 26700, loss[loss=0.1258, simple_loss=0.2071, pruned_loss=0.02228, over 4928.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02888, over 972983.19 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 11:20:05,261 INFO [train.py:715] (4/8) Epoch 18, batch 26750, loss[loss=0.1524, simple_loss=0.2154, pruned_loss=0.04472, over 4866.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02904, over 971764.36 frames.], batch size: 32, lr: 1.22e-04
2022-05-09 11:20:43,660 INFO [train.py:715] (4/8) Epoch 18, batch 26800, loss[loss=0.1481, simple_loss=0.2118, pruned_loss=0.04221, over 4986.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02881, over 972851.74 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:21:23,701 INFO [train.py:715] (4/8) Epoch 18, batch 26850, loss[loss=0.1319, simple_loss=0.1984, pruned_loss=0.03267, over 4956.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.0281, over 972234.29 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:22:03,381 INFO [train.py:715] (4/8) Epoch 18, batch 26900, loss[loss=0.152, simple_loss=0.2307, pruned_loss=0.03666, over 4810.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02845, over 972894.57 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 11:22:41,420 INFO [train.py:715] (4/8) Epoch 18, batch 26950, loss[loss=0.1199, simple_loss=0.2089, pruned_loss=0.01545, over 4982.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02884, over 974083.94 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 11:23:20,805 INFO [train.py:715] (4/8) Epoch 18, batch 27000, loss[loss=0.1404, simple_loss=0.2077, pruned_loss=0.0366, over 4769.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02909, over 973619.35 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:23:20,806 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 11:23:30,796 INFO [train.py:742] (4/8) Epoch 18, validation: loss=0.1044, simple_loss=0.1877, pruned_loss=0.01055, over 914524.00 frames.
2022-05-09 11:24:11,109 INFO [train.py:715] (4/8) Epoch 18, batch 27050, loss[loss=0.1126, simple_loss=0.18, pruned_loss=0.02261, over 4989.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02908, over 973590.13 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:24:50,012 INFO [train.py:715] (4/8) Epoch 18, batch 27100, loss[loss=0.1412, simple_loss=0.2165, pruned_loss=0.03293, over 4740.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02885, over 973676.06 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 11:25:29,321 INFO [train.py:715] (4/8) Epoch 18, batch 27150, loss[loss=0.1184, simple_loss=0.1894, pruned_loss=0.02372, over 4778.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02892, over 973411.44 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:26:08,684 INFO [train.py:715] (4/8) Epoch 18, batch 27200, loss[loss=0.1149, simple_loss=0.1832, pruned_loss=0.02328, over 4979.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.0286, over 972812.13 frames.], batch size: 35, lr: 1.22e-04
2022-05-09 11:26:47,915 INFO [train.py:715] (4/8) Epoch 18, batch 27250, loss[loss=0.1474, simple_loss=0.2168, pruned_loss=0.03903, over 4971.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2056, pruned_loss=0.02868, over 972314.77 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:27:26,982 INFO [train.py:715] (4/8) Epoch 18, batch 27300, loss[loss=0.1442, simple_loss=0.2141, pruned_loss=0.03717, over 4853.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.0289, over 972091.70 frames.], batch size: 20, lr: 1.22e-04
2022-05-09 11:28:05,825 INFO [train.py:715] (4/8) Epoch 18, batch 27350, loss[loss=0.1214, simple_loss=0.1948, pruned_loss=0.02403, over 4692.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2064, pruned_loss=0.02919, over 972470.53 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:28:46,020 INFO [train.py:715] (4/8) Epoch 18, batch 27400, loss[loss=0.1376, simple_loss=0.2068, pruned_loss=0.03417, over 4891.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.029, over 972332.84 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:29:25,405 INFO [train.py:715] (4/8) Epoch 18, batch 27450, loss[loss=0.1559, simple_loss=0.228, pruned_loss=0.04187, over 4918.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02899, over 972888.61 frames.], batch size: 39, lr: 1.22e-04
2022-05-09 11:30:04,464 INFO [train.py:715] (4/8) Epoch 18, batch 27500, loss[loss=0.119, simple_loss=0.1851, pruned_loss=0.02639, over 4972.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2068, pruned_loss=0.02933, over 972565.30 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:30:44,181 INFO [train.py:715] (4/8) Epoch 18, batch 27550, loss[loss=0.1323, simple_loss=0.2138, pruned_loss=0.02539, over 4769.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.0293, over 972003.38 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:31:23,281 INFO [train.py:715] (4/8) Epoch 18, batch 27600, loss[loss=0.1471, simple_loss=0.2252, pruned_loss=0.03447, over 4786.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02887, over 972029.69 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:32:01,946 INFO [train.py:715] (4/8) Epoch 18, batch 27650, loss[loss=0.1233, simple_loss=0.1982, pruned_loss=0.02426, over 4787.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.029, over 971796.28 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:32:40,855 INFO [train.py:715] (4/8) Epoch 18, batch 27700, loss[loss=0.1192, simple_loss=0.1941, pruned_loss=0.02215, over 4938.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02933, over 971875.94 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 11:33:20,160 INFO [train.py:715] (4/8) Epoch 18, batch 27750, loss[loss=0.1396, simple_loss=0.2118, pruned_loss=0.03365, over 4832.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2072, pruned_loss=0.02925, over 972801.21 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:33:59,620 INFO [train.py:715] (4/8) Epoch 18, batch 27800, loss[loss=0.1335, simple_loss=0.1992, pruned_loss=0.03387, over 4786.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02945, over 972464.50 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:34:38,868 INFO [train.py:715] (4/8) Epoch 18, batch 27850, loss[loss=0.1601, simple_loss=0.2228, pruned_loss=0.04874, over 4904.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.0296, over 971658.59 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:35:18,480 INFO [train.py:715] (4/8) Epoch 18, batch 27900, loss[loss=0.1044, simple_loss=0.1825, pruned_loss=0.01315, over 4918.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02932, over 971855.05 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 11:35:57,742 INFO [train.py:715] (4/8) Epoch 18, batch 27950, loss[loss=0.1402, simple_loss=0.2099, pruned_loss=0.03528, over 4922.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02886, over 972657.69 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:36:36,984 INFO [train.py:715] (4/8) Epoch 18, batch 28000, loss[loss=0.1108, simple_loss=0.1899, pruned_loss=0.01585, over 4980.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02888, over 971929.33 frames.], batch size: 28, lr: 1.22e-04
2022-05-09 11:37:16,534 INFO [train.py:715] (4/8) Epoch 18, batch 28050, loss[loss=0.12, simple_loss=0.1924, pruned_loss=0.02379, over 4919.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.0291, over 972768.55 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:37:56,319 INFO [train.py:715] (4/8) Epoch 18, batch 28100, loss[loss=0.145, simple_loss=0.2108, pruned_loss=0.03958, over 4763.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02916, over 972375.04 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 11:38:35,508 INFO [train.py:715] (4/8) Epoch 18, batch 28150, loss[loss=0.135, simple_loss=0.2063, pruned_loss=0.03185, over 4940.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2074, pruned_loss=0.02923, over 971572.07 frames.], batch size: 35, lr: 1.22e-04
2022-05-09 11:39:13,846 INFO [train.py:715] (4/8) Epoch 18, batch 28200, loss[loss=0.1282, simple_loss=0.1974, pruned_loss=0.02953, over 4807.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02942, over 972391.91 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 11:39:53,467 INFO [train.py:715] (4/8) Epoch 18, batch 28250, loss[loss=0.1502, simple_loss=0.233, pruned_loss=0.03364, over 4683.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02928, over 972116.65 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:40:32,292 INFO [train.py:715] (4/8) Epoch 18, batch 28300, loss[loss=0.1324, simple_loss=0.2061, pruned_loss=0.02935, over 4835.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02929, over 972400.25 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 11:41:11,197 INFO [train.py:715] (4/8) Epoch 18, batch 28350, loss[loss=0.155, simple_loss=0.2214, pruned_loss=0.04435, over 4830.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02961, over 971727.66 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 11:41:50,495 INFO [train.py:715] (4/8) Epoch 18, batch 28400, loss[loss=0.1313, simple_loss=0.2145, pruned_loss=0.02407, over 4927.00 frames.], tot_loss[loss=0.1342, simple_loss=0.2085, pruned_loss=0.02995, over 971386.59 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:42:29,771 INFO [train.py:715] (4/8) Epoch 18, batch 28450, loss[loss=0.1412, simple_loss=0.2112, pruned_loss=0.03561, over 4877.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2087, pruned_loss=0.03009, over 971845.68 frames.], batch size: 22, lr: 1.22e-04
2022-05-09 11:43:08,847 INFO [train.py:715] (4/8) Epoch 18, batch 28500, loss[loss=0.1157, simple_loss=0.1943, pruned_loss=0.01853, over 4926.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2082, pruned_loss=0.02981, over 972814.53 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:43:47,953 INFO [train.py:715] (4/8) Epoch 18, batch 28550, loss[loss=0.1563, simple_loss=0.2263, pruned_loss=0.04317, over 4816.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2075, pruned_loss=0.02958, over 972829.61 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 11:44:27,961 INFO [train.py:715] (4/8) Epoch 18, batch 28600, loss[loss=0.1282, simple_loss=0.2088, pruned_loss=0.02382, over 4823.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2079, pruned_loss=0.02951, over 972567.65 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 11:45:06,654 INFO [train.py:715] (4/8) Epoch 18, batch 28650, loss[loss=0.1186, simple_loss=0.197, pruned_loss=0.02016, over 4821.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02857, over 972688.62 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 11:45:45,609 INFO [train.py:715] (4/8) Epoch 18, batch 28700, loss[loss=0.1227, simple_loss=0.1949, pruned_loss=0.02521, over 4784.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2062, pruned_loss=0.02816, over 974070.01 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 11:46:25,176 INFO [train.py:715] (4/8) Epoch 18, batch 28750, loss[loss=0.1262, simple_loss=0.2019, pruned_loss=0.02525, over 4979.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.028, over 973578.19 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 11:47:04,223 INFO [train.py:715] (4/8) Epoch 18, batch 28800, loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02943, over 4832.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2052, pruned_loss=0.02784, over 973245.78 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 11:47:43,077 INFO [train.py:715] (4/8) Epoch 18, batch 28850, loss[loss=0.1371, simple_loss=0.2141, pruned_loss=0.02999, over 4768.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2059, pruned_loss=0.02819, over 973134.05 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:48:21,622 INFO [train.py:715] (4/8) Epoch 18, batch 28900, loss[loss=0.1208, simple_loss=0.182, pruned_loss=0.02978, over 4844.00 frames.], tot_loss[loss=0.1312, simple_loss=0.206, pruned_loss=0.02827, over 973188.51 frames.], batch size: 30, lr: 1.22e-04
2022-05-09 11:49:01,749 INFO [train.py:715] (4/8) Epoch 18, batch 28950, loss[loss=0.1154, simple_loss=0.1888, pruned_loss=0.02098, over 4687.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2046, pruned_loss=0.02784, over 973351.39 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 11:49:40,555 INFO [train.py:715] (4/8) Epoch 18, batch 29000, loss[loss=0.1209, simple_loss=0.1888, pruned_loss=0.02651, over 4915.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02829, over 972915.66 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 11:50:19,732 INFO [train.py:715] (4/8) Epoch 18, batch 29050, loss[loss=0.1238, simple_loss=0.2083, pruned_loss=0.01963, over 4872.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02827, over 972798.13 frames.], batch size: 22, lr: 1.22e-04
2022-05-09 11:50:59,123 INFO [train.py:715] (4/8) Epoch 18, batch 29100, loss[loss=0.1328, simple_loss=0.2005, pruned_loss=0.03253, over 4874.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2063, pruned_loss=0.02829, over 972629.74 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 11:51:38,414 INFO [train.py:715] (4/8) Epoch 18, batch 29150, loss[loss=0.1356, simple_loss=0.2021, pruned_loss=0.03453, over 4920.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2054, pruned_loss=0.02793, over 972839.23 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 11:52:17,126 INFO [train.py:715] (4/8) Epoch 18, batch 29200, loss[loss=0.1283, simple_loss=0.2106, pruned_loss=0.02302, over 4798.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2061, pruned_loss=0.02816, over 972329.43 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 11:52:55,643 INFO [train.py:715] (4/8) Epoch 18, batch 29250, loss[loss=0.1241, simple_loss=0.2038, pruned_loss=0.02223, over 4761.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02821, over 972336.76 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 11:53:35,210 INFO [train.py:715] (4/8) Epoch 18, batch 29300, loss[loss=0.1068, simple_loss=0.1832, pruned_loss=0.01518, over 4814.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02856, over 972435.54 frames.], batch size: 27, lr: 1.22e-04
2022-05-09 11:54:13,912 INFO [train.py:715] (4/8) Epoch 18, batch 29350, loss[loss=0.1285, simple_loss=0.2062, pruned_loss=0.02543, over 4786.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02839, over 971488.80 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 11:54:52,613 INFO [train.py:715] (4/8) Epoch 18, batch 29400, loss[loss=0.1351, simple_loss=0.2132, pruned_loss=0.02855, over 4942.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02863, over 972365.45 frames.], batch size: 39, lr: 1.22e-04
2022-05-09 11:55:33,952 INFO [train.py:715] (4/8) Epoch 18, batch 29450, loss[loss=0.1068, simple_loss=0.1834, pruned_loss=0.01508, over 4928.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02844, over 972355.17 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 11:56:12,981 INFO [train.py:715] (4/8) Epoch 18, batch 29500, loss[loss=0.1022, simple_loss=0.1762, pruned_loss=0.01407, over 4828.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2056, pruned_loss=0.02799, over 972460.44 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 11:56:52,074 INFO [train.py:715] (4/8) Epoch 18, batch 29550, loss[loss=0.1397, simple_loss=0.224, pruned_loss=0.02765, over 4910.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02828, over 972188.94 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 11:57:30,046 INFO [train.py:715] (4/8) Epoch 18, batch 29600, loss[loss=0.1351, simple_loss=0.2165, pruned_loss=0.0268, over 4891.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02853, over 972471.03 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 11:58:09,260 INFO [train.py:715] (4/8) Epoch 18, batch 29650, loss[loss=0.1089, simple_loss=0.1669, pruned_loss=0.02543, over 4851.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02833, over 972614.66 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 11:58:48,236 INFO [train.py:715] (4/8) Epoch 18, batch 29700, loss[loss=0.1053, simple_loss=0.182, pruned_loss=0.01435, over 4917.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2068, pruned_loss=0.02828, over 972912.55 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 11:59:26,591 INFO [train.py:715] (4/8) Epoch 18, batch 29750, loss[loss=0.1509, simple_loss=0.2139, pruned_loss=0.04398, over 4796.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.0289, over 972474.70 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 12:00:05,930 INFO [train.py:715] (4/8) Epoch 18, batch 29800, loss[loss=0.1281, simple_loss=0.2037, pruned_loss=0.02628, over 4783.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2066, pruned_loss=0.02895, over 971412.83 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 12:00:45,625 INFO [train.py:715] (4/8) Epoch 18, batch 29850, loss[loss=0.1418, simple_loss=0.2234, pruned_loss=0.03008, over 4775.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02887, over 971118.56 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 12:01:24,703 INFO [train.py:715] (4/8) Epoch 18, batch 29900, loss[loss=0.1231, simple_loss=0.1907, pruned_loss=0.02782, over 4864.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2071, pruned_loss=0.02903, over 970419.17 frames.], batch size: 20, lr: 1.22e-04
2022-05-09 12:02:03,292 INFO [train.py:715] (4/8) Epoch 18, batch 29950, loss[loss=0.1085, simple_loss=0.1923, pruned_loss=0.01236, over 4952.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02912, over 971379.91 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 12:02:43,063 INFO [train.py:715] (4/8) Epoch 18, batch 30000, loss[loss=0.1499, simple_loss=0.2227, pruned_loss=0.03856, over 4798.00 frames.], tot_loss[loss=0.1332, simple_loss=0.208, pruned_loss=0.02916, over 971489.04 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 12:02:43,063 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 12:02:52,967 INFO [train.py:742] (4/8) Epoch 18, validation: loss=0.1047, simple_loss=0.188, pruned_loss=0.01071, over 914524.00 frames.
2022-05-09 12:03:33,194 INFO [train.py:715] (4/8) Epoch 18, batch 30050, loss[loss=0.1306, simple_loss=0.2028, pruned_loss=0.02923, over 4811.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.0288, over 971032.14 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:04:12,321 INFO [train.py:715] (4/8) Epoch 18, batch 30100, loss[loss=0.1187, simple_loss=0.1927, pruned_loss=0.0223, over 4823.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2074, pruned_loss=0.02889, over 972362.34 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 12:04:50,503 INFO [train.py:715] (4/8) Epoch 18, batch 30150, loss[loss=0.1247, simple_loss=0.1948, pruned_loss=0.02735, over 4844.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2076, pruned_loss=0.02911, over 971768.88 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 12:05:29,935 INFO [train.py:715] (4/8) Epoch 18, batch 30200, loss[loss=0.1271, simple_loss=0.2007, pruned_loss=0.02669, over 4968.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02927, over 971551.63 frames.], batch size: 35, lr: 1.22e-04
2022-05-09 12:06:09,183 INFO [train.py:715] (4/8) Epoch 18, batch 30250, loss[loss=0.1183, simple_loss=0.1842, pruned_loss=0.02613, over 4965.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2079, pruned_loss=0.02945, over 972224.78 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 12:06:48,900 INFO [train.py:715] (4/8) Epoch 18, batch 30300, loss[loss=0.1848, simple_loss=0.2275, pruned_loss=0.07101, over 4975.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2076, pruned_loss=0.02964, over 972025.26 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:07:27,508 INFO [train.py:715] (4/8) Epoch 18, batch 30350, loss[loss=0.116, simple_loss=0.1955, pruned_loss=0.01826, over 4871.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.029, over 971670.99 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:08:07,404 INFO [train.py:715] (4/8) Epoch 18, batch 30400, loss[loss=0.1296, simple_loss=0.206, pruned_loss=0.02655, over 4821.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02876, over 972610.00 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 12:08:46,435 INFO [train.py:715] (4/8) Epoch 18, batch 30450, loss[loss=0.1245, simple_loss=0.2063, pruned_loss=0.02132, over 4814.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02863, over 972786.59 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:09:24,922 INFO [train.py:715] (4/8) Epoch 18, batch 30500, loss[loss=0.119, simple_loss=0.1998, pruned_loss=0.01914, over 4963.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02882, over 973087.98 frames.], batch size: 24, lr: 1.22e-04
2022-05-09 12:10:04,131 INFO [train.py:715] (4/8) Epoch 18, batch 30550, loss[loss=0.147, simple_loss=0.223, pruned_loss=0.0355, over 4870.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02895, over 972778.11 frames.], batch size: 32, lr: 1.22e-04
2022-05-09 12:10:42,817 INFO [train.py:715] (4/8) Epoch 18, batch 30600, loss[loss=0.1444, simple_loss=0.2322, pruned_loss=0.0283, over 4741.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02932, over 972840.77 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:11:21,483 INFO [train.py:715] (4/8) Epoch 18, batch 30650, loss[loss=0.1306, simple_loss=0.1878, pruned_loss=0.03665, over 4837.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02918, over 973659.20 frames.], batch size: 13, lr: 1.22e-04
2022-05-09 12:12:00,154 INFO [train.py:715] (4/8) Epoch 18, batch 30700, loss[loss=0.1258, simple_loss=0.2024, pruned_loss=0.02463, over 4933.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02959, over 973796.87 frames.], batch size: 35, lr: 1.22e-04
2022-05-09 12:12:39,282 INFO [train.py:715] (4/8) Epoch 18, batch 30750, loss[loss=0.1448, simple_loss=0.2124, pruned_loss=0.03864, over 4871.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2075, pruned_loss=0.02936, over 973251.80 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:13:18,038 INFO [train.py:715] (4/8) Epoch 18, batch 30800, loss[loss=0.1166, simple_loss=0.1913, pruned_loss=0.02096, over 4945.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.029, over 973531.81 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 12:13:56,474 INFO [train.py:715] (4/8) Epoch 18, batch 30850, loss[loss=0.1165, simple_loss=0.1886, pruned_loss=0.02221, over 4800.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2053, pruned_loss=0.02893, over 973704.02 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:14:35,510 INFO [train.py:715] (4/8) Epoch 18, batch 30900, loss[loss=0.163, simple_loss=0.2332, pruned_loss=0.04644, over 4985.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2061, pruned_loss=0.02952, over 973382.02 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 12:15:14,123 INFO [train.py:715] (4/8) Epoch 18, batch 30950, loss[loss=0.1172, simple_loss=0.1933, pruned_loss=0.02061, over 4760.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2065, pruned_loss=0.02943, over 973037.80 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:15:52,435 INFO [train.py:715] (4/8) Epoch 18, batch 31000, loss[loss=0.1188, simple_loss=0.1971, pruned_loss=0.02023, over 4959.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2056, pruned_loss=0.02886, over 972609.68 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:16:31,401 INFO [train.py:715] (4/8) Epoch 18, batch 31050, loss[loss=0.1075, simple_loss=0.1806, pruned_loss=0.01722, over 4907.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2053, pruned_loss=0.02891, over 973095.14 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 12:17:10,962 INFO [train.py:715] (4/8) Epoch 18, batch 31100, loss[loss=0.1651, simple_loss=0.2411, pruned_loss=0.04454, over 4950.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2054, pruned_loss=0.02889, over 973236.38 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 12:17:49,895 INFO [train.py:715] (4/8) Epoch 18, batch 31150, loss[loss=0.1203, simple_loss=0.1925, pruned_loss=0.024, over 4937.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2054, pruned_loss=0.02846, over 973356.87 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 12:18:28,837 INFO [train.py:715] (4/8) Epoch 18, batch 31200, loss[loss=0.1244, simple_loss=0.2016, pruned_loss=0.02359, over 4914.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2049, pruned_loss=0.02812, over 973248.39 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 12:19:08,214 INFO [train.py:715] (4/8) Epoch 18, batch 31250, loss[loss=0.1076, simple_loss=0.1845, pruned_loss=0.01532, over 4886.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02799, over 972446.04 frames.], batch size: 22, lr: 1.22e-04
2022-05-09 12:19:47,256 INFO [train.py:715] (4/8) Epoch 18, batch 31300, loss[loss=0.1322, simple_loss=0.2018, pruned_loss=0.03127, over 4846.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2046, pruned_loss=0.02806, over 972996.08 frames.], batch size: 30, lr: 1.22e-04
2022-05-09 12:20:25,878 INFO [train.py:715] (4/8) Epoch 18, batch 31350, loss[loss=0.1378, simple_loss=0.2157, pruned_loss=0.02993, over 4910.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2044, pruned_loss=0.0282, over 972658.88 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 12:21:05,049 INFO [train.py:715] (4/8) Epoch 18, batch 31400, loss[loss=0.1471, simple_loss=0.2123, pruned_loss=0.04097, over 4950.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2051, pruned_loss=0.02852, over 972709.46 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:21:44,554 INFO [train.py:715] (4/8) Epoch 18, batch 31450, loss[loss=0.1319, simple_loss=0.2055, pruned_loss=0.02915, over 4833.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2053, pruned_loss=0.0286, over 973156.63 frames.], batch size: 30, lr: 1.22e-04
2022-05-09 12:22:23,389 INFO [train.py:715] (4/8) Epoch 18, batch 31500, loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02865, over 4946.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2052, pruned_loss=0.02832, over 973333.84 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:23:01,620 INFO [train.py:715] (4/8) Epoch 18, batch 31550, loss[loss=0.1686, simple_loss=0.2487, pruned_loss=0.04422, over 4759.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02854, over 972926.20 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 12:23:41,437 INFO [train.py:715] (4/8) Epoch 18, batch 31600, loss[loss=0.1442, simple_loss=0.2133, pruned_loss=0.03762, over 4921.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02827, over 973338.41 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:24:20,708 INFO [train.py:715] (4/8) Epoch 18, batch 31650, loss[loss=0.1251, simple_loss=0.1992, pruned_loss=0.02547, over 4692.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02849, over 973902.01 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:24:59,690 INFO [train.py:715] (4/8) Epoch 18, batch 31700, loss[loss=0.1539, simple_loss=0.23, pruned_loss=0.03886, over 4706.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02834, over 973385.88 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:25:38,810 INFO [train.py:715] (4/8) Epoch 18, batch 31750, loss[loss=0.1452, simple_loss=0.213, pruned_loss=0.03872, over 4828.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2076, pruned_loss=0.02928, over 972748.19 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 12:26:18,650 INFO [train.py:715] (4/8) Epoch 18, batch 31800, loss[loss=0.115, simple_loss=0.1927, pruned_loss=0.01866, over 4825.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.0291, over 972407.06 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 12:26:58,017 INFO [train.py:715] (4/8) Epoch 18, batch 31850, loss[loss=0.1459, simple_loss=0.2151, pruned_loss=0.03833, over 4907.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2073, pruned_loss=0.02923, over 972149.58 frames.], batch size: 17, lr: 1.22e-04
2022-05-09 12:27:36,974 INFO [train.py:715] (4/8) Epoch 18, batch 31900, loss[loss=0.1736, simple_loss=0.2459, pruned_loss=0.05064, over 4793.00 frames.], tot_loss[loss=0.1329, simple_loss=0.207, pruned_loss=0.02939, over 972697.15 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 12:28:16,149 INFO [train.py:715] (4/8) Epoch 18, batch 31950, loss[loss=0.1112, simple_loss=0.1755, pruned_loss=0.02342, over 4960.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2069, pruned_loss=0.02929, over 973138.12 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 12:28:54,462 INFO [train.py:715] (4/8) Epoch 18, batch 32000, loss[loss=0.1389, simple_loss=0.2207, pruned_loss=0.02861, over 4845.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02875, over 972961.95 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:29:32,616 INFO [train.py:715] (4/8) Epoch 18, batch 32050, loss[loss=0.1303, simple_loss=0.2079, pruned_loss=0.02631, over 4861.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02837, over 972688.90 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:30:11,880 INFO [train.py:715] (4/8) Epoch 18, batch 32100, loss[loss=0.1386, simple_loss=0.2179, pruned_loss=0.02961, over 4961.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02838, over 973005.94 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:30:51,368 INFO [train.py:715] (4/8) Epoch 18, batch 32150, loss[loss=0.1254, simple_loss=0.1985, pruned_loss=0.02617, over 4925.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02835, over 972865.55 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 12:31:30,533 INFO [train.py:715] (4/8) Epoch 18, batch 32200, loss[loss=0.1364, simple_loss=0.2055, pruned_loss=0.03363, over 4974.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02834, over 972715.13 frames.], batch size: 35, lr: 1.22e-04
2022-05-09 12:32:08,906 INFO [train.py:715] (4/8) Epoch 18, batch 32250, loss[loss=0.1556, simple_loss=0.2326, pruned_loss=0.03925, over 4875.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02856, over 972912.51 frames.], batch size: 39, lr: 1.22e-04
2022-05-09 12:32:48,156 INFO [train.py:715] (4/8) Epoch 18, batch 32300, loss[loss=0.127, simple_loss=0.1978, pruned_loss=0.02808, over 4875.00 frames.], tot_loss[loss=0.1321, simple_loss=0.206, pruned_loss=0.02912, over 972444.09 frames.], batch size: 32, lr: 1.22e-04
2022-05-09 12:33:26,710 INFO [train.py:715] (4/8) Epoch 18, batch 32350, loss[loss=0.1268, simple_loss=0.2039, pruned_loss=0.02484, over 4752.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02878, over 972976.91 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 12:34:05,358 INFO [train.py:715] (4/8) Epoch 18, batch 32400, loss[loss=0.1608, simple_loss=0.2265, pruned_loss=0.04755, over 4963.00 frames.], tot_loss[loss=0.133, simple_loss=0.2075, pruned_loss=0.02929, over 973198.24 frames.], batch size: 35, lr: 1.22e-04
2022-05-09 12:34:44,784 INFO [train.py:715] (4/8) Epoch 18, batch 32450, loss[loss=0.1146, simple_loss=0.1963, pruned_loss=0.01647, over 4830.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02888, over 971865.89 frames.], batch size: 27, lr: 1.22e-04
2022-05-09 12:35:23,650 INFO [train.py:715] (4/8) Epoch 18, batch 32500, loss[loss=0.1706, simple_loss=0.2436, pruned_loss=0.04883, over 4809.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2063, pruned_loss=0.02907, over 971223.84 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 12:36:02,852 INFO [train.py:715] (4/8) Epoch 18, batch 32550, loss[loss=0.1552, simple_loss=0.2243, pruned_loss=0.04303, over 4977.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02853, over 971399.51 frames.], batch size: 35, lr: 1.22e-04
2022-05-09 12:36:42,028 INFO [train.py:715] (4/8) Epoch 18, batch 32600, loss[loss=0.1456, simple_loss=0.2172, pruned_loss=0.03698, over 4899.00 frames.], tot_loss[loss=0.131, simple_loss=0.2058, pruned_loss=0.02813, over 971157.20 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 12:37:21,455 INFO [train.py:715] (4/8) Epoch 18, batch 32650, loss[loss=0.1146, simple_loss=0.1949, pruned_loss=0.0171, over 4919.00 frames.], tot_loss[loss=0.131, simple_loss=0.206, pruned_loss=0.02804, over 970933.58 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 12:37:59,896 INFO [train.py:715] (4/8) Epoch 18, batch 32700, loss[loss=0.1432, simple_loss=0.2289, pruned_loss=0.0288, over 4758.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2071, pruned_loss=0.02871, over 971422.63 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:38:38,644 INFO [train.py:715] (4/8) Epoch 18, batch 32750, loss[loss=0.1208, simple_loss=0.1979, pruned_loss=0.02184, over 4783.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2072, pruned_loss=0.02872, over 971675.64 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 12:39:17,960 INFO [train.py:715] (4/8) Epoch 18, batch 32800, loss[loss=0.1412, simple_loss=0.2151, pruned_loss=0.03364, over 4772.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2075, pruned_loss=0.0291, over 971909.06 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 12:39:57,153 INFO [train.py:715] (4/8) Epoch 18, batch 32850, loss[loss=0.1251, simple_loss=0.1888, pruned_loss=0.03074, over 4787.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02912, over 972020.90 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 12:40:35,663 INFO [train.py:715] (4/8) Epoch 18, batch 32900, loss[loss=0.1385, simple_loss=0.2074, pruned_loss=0.03481, over 4845.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02892, over 971164.74 frames.], batch size: 32, lr: 1.22e-04
2022-05-09 12:41:14,762 INFO [train.py:715] (4/8) Epoch 18, batch 32950, loss[loss=0.1464, simple_loss=0.2262, pruned_loss=0.03328, over 4876.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02894, over 971977.45 frames.], batch size: 22, lr: 1.22e-04
2022-05-09 12:41:53,956 INFO [train.py:715] (4/8) Epoch 18, batch 33000, loss[loss=0.1037, simple_loss=0.1739, pruned_loss=0.0168, over 4794.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02895, over 972993.22 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 12:41:53,957 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 12:42:03,825 INFO [train.py:742] (4/8) Epoch 18, validation: loss=0.1046, simple_loss=0.1878, pruned_loss=0.01068, over 914524.00 frames.
2022-05-09 12:42:43,655 INFO [train.py:715] (4/8) Epoch 18, batch 33050, loss[loss=0.1333, simple_loss=0.2042, pruned_loss=0.03121, over 4933.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02874, over 971926.65 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 12:43:22,621 INFO [train.py:715] (4/8) Epoch 18, batch 33100, loss[loss=0.1111, simple_loss=0.1832, pruned_loss=0.01955, over 4772.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02892, over 972611.03 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 12:44:02,107 INFO [train.py:715] (4/8) Epoch 18, batch 33150, loss[loss=0.1393, simple_loss=0.2077, pruned_loss=0.03541, over 4945.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02888, over 972356.00 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:44:41,946 INFO [train.py:715] (4/8) Epoch 18, batch 33200, loss[loss=0.1379, simple_loss=0.2067, pruned_loss=0.03452, over 4852.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.02902, over 973128.36 frames.], batch size: 32, lr: 1.22e-04
2022-05-09 12:45:20,898 INFO [train.py:715] (4/8) Epoch 18, batch 33250, loss[loss=0.14, simple_loss=0.2116, pruned_loss=0.03419, over 4775.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02836, over 972809.26 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 12:45:59,528 INFO [train.py:715] (4/8) Epoch 18, batch 33300, loss[loss=0.153, simple_loss=0.2234, pruned_loss=0.04131, over 4940.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02833, over 972874.06 frames.], batch size: 35, lr: 1.22e-04
2022-05-09 12:46:38,968 INFO [train.py:715] (4/8) Epoch 18, batch 33350, loss[loss=0.1064, simple_loss=0.1773, pruned_loss=0.01776, over 4831.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02831, over 972506.67 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 12:47:18,354 INFO [train.py:715] (4/8) Epoch 18, batch 33400, loss[loss=0.1445, simple_loss=0.2193, pruned_loss=0.03483, over 4848.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.0285, over 971691.16 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:47:57,078 INFO [train.py:715] (4/8) Epoch 18, batch 33450, loss[loss=0.1228, simple_loss=0.2052, pruned_loss=0.0202, over 4823.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2066, pruned_loss=0.02826, over 971240.86 frames.], batch size: 27, lr: 1.22e-04
2022-05-09 12:48:36,023 INFO [train.py:715] (4/8) Epoch 18, batch 33500, loss[loss=0.1173, simple_loss=0.1901, pruned_loss=0.02228, over 4784.00 frames.], tot_loss[loss=0.1318, simple_loss=0.207, pruned_loss=0.02827, over 970930.76 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 12:49:15,395 INFO [train.py:715] (4/8) Epoch 18, batch 33550, loss[loss=0.1097, simple_loss=0.188, pruned_loss=0.01568, over 4908.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2074, pruned_loss=0.02835, over 970390.57 frames.], batch size: 23, lr: 1.22e-04
2022-05-09 12:49:54,440 INFO [train.py:715] (4/8) Epoch 18, batch 33600, loss[loss=0.1292, simple_loss=0.2051, pruned_loss=0.02662, over 4984.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2067, pruned_loss=0.02842, over 971083.14 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 12:50:32,504 INFO [train.py:715] (4/8) Epoch 18, batch 33650, loss[loss=0.1199, simple_loss=0.202, pruned_loss=0.01894, over 4864.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02847, over 971183.77 frames.], batch size: 20, lr: 1.22e-04
2022-05-09 12:51:11,946 INFO [train.py:715] (4/8) Epoch 18, batch 33700, loss[loss=0.1119, simple_loss=0.1858, pruned_loss=0.01899, over 4887.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02836, over 971223.42 frames.], batch size: 22, lr: 1.22e-04
2022-05-09 12:51:51,114 INFO [train.py:715] (4/8) Epoch 18, batch 33750, loss[loss=0.1283, simple_loss=0.206, pruned_loss=0.0253, over 4986.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02864, over 971956.88 frames.], batch size: 14, lr: 1.22e-04
2022-05-09 12:52:30,431 INFO [train.py:715] (4/8) Epoch 18, batch 33800, loss[loss=0.1204, simple_loss=0.1974, pruned_loss=0.02167, over 4944.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02878, over 972073.08 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 12:53:09,706 INFO [train.py:715] (4/8) Epoch 18, batch 33850, loss[loss=0.1445, simple_loss=0.2184, pruned_loss=0.03532, over 4901.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2074, pruned_loss=0.02944, over 972074.36 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 12:53:49,535 INFO [train.py:715] (4/8) Epoch 18, batch 33900, loss[loss=0.1318, simple_loss=0.203, pruned_loss=0.03028, over 4759.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.0288, over 972270.06 frames.], batch size: 19, lr: 1.22e-04
2022-05-09 12:54:28,737 INFO [train.py:715] (4/8) Epoch 18, batch 33950, loss[loss=0.1232, simple_loss=0.1964, pruned_loss=0.02504, over 4734.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02867, over 972624.13 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 12:55:07,056 INFO [train.py:715] (4/8) Epoch 18, batch 34000, loss[loss=0.1769, simple_loss=0.2409, pruned_loss=0.05646, over 4959.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02837, over 973133.88 frames.], batch size: 15, lr: 1.22e-04
2022-05-09 12:55:46,476 INFO [train.py:715] (4/8) Epoch 18, batch 34050, loss[loss=0.1353, simple_loss=0.2184, pruned_loss=0.02609, over 4795.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02802, over 972878.72 frames.], batch size: 21, lr: 1.22e-04
2022-05-09 12:56:25,890 INFO [train.py:715] (4/8) Epoch 18, batch 34100, loss[loss=0.1148, simple_loss=0.193, pruned_loss=0.01826, over 4860.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02817, over 972456.37 frames.], batch size: 20, lr: 1.22e-04
2022-05-09 12:57:05,036 INFO [train.py:715] (4/8) Epoch 18, batch 34150, loss[loss=0.1198, simple_loss=0.195, pruned_loss=0.0223, over 4878.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.02827, over 972553.27 frames.], batch size: 22, lr: 1.22e-04
2022-05-09 12:57:44,078 INFO [train.py:715] (4/8) Epoch 18, batch 34200, loss[loss=0.1393, simple_loss=0.2214, pruned_loss=0.02859, over 4779.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2054, pruned_loss=0.02773, over 971829.27 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 12:58:23,224 INFO [train.py:715] (4/8) Epoch 18, batch 34250, loss[loss=0.1331, simple_loss=0.2081, pruned_loss=0.02903, over 4934.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.02806, over 970665.87 frames.], batch size: 29, lr: 1.22e-04
2022-05-09 12:59:02,029 INFO [train.py:715] (4/8) Epoch 18, batch 34300, loss[loss=0.1009, simple_loss=0.1783, pruned_loss=0.01174, over 4828.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2055, pruned_loss=0.02782, over 971041.73 frames.], batch size: 26, lr: 1.22e-04
2022-05-09 12:59:40,336 INFO [train.py:715] (4/8) Epoch 18, batch 34350, loss[loss=0.1225, simple_loss=0.1991, pruned_loss=0.02294, over 4830.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02805, over 971777.24 frames.], batch size: 27, lr: 1.22e-04
2022-05-09 13:00:19,866 INFO [train.py:715] (4/8) Epoch 18, batch 34400, loss[loss=0.113, simple_loss=0.1909, pruned_loss=0.0175, over 4783.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2062, pruned_loss=0.02821, over 971983.98 frames.], batch size: 12, lr: 1.22e-04
2022-05-09 13:00:59,442 INFO [train.py:715] (4/8) Epoch 18, batch 34450, loss[loss=0.1326, simple_loss=0.2002, pruned_loss=0.03247, over 4820.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2076, pruned_loss=0.02887, over 972402.25 frames.], batch size: 25, lr: 1.22e-04
2022-05-09 13:01:39,371 INFO [train.py:715] (4/8) Epoch 18, batch 34500, loss[loss=0.1345, simple_loss=0.201, pruned_loss=0.03394, over 4755.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.02879, over 972814.64 frames.], batch size: 16, lr: 1.22e-04
2022-05-09 13:02:18,896 INFO [train.py:715] (4/8) Epoch 18, batch 34550, loss[loss=0.1135, simple_loss=0.178, pruned_loss=0.02445, over 4841.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2067, pruned_loss=0.0283, over 972185.05 frames.], batch size: 32, lr: 1.22e-04
2022-05-09 13:02:58,571 INFO [train.py:715] (4/8) Epoch 18, batch 34600, loss[loss=0.1448, simple_loss=0.219, pruned_loss=0.03532, over 4857.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2074, pruned_loss=0.02869, over 971434.28 frames.], batch size: 30, lr: 1.22e-04
2022-05-09 13:03:37,767 INFO [train.py:715] (4/8) Epoch 18, batch 34650, loss[loss=0.127, simple_loss=0.202, pruned_loss=0.02603, over 4912.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2077, pruned_loss=0.02878, over 970900.45 frames.], batch size: 18, lr: 1.22e-04
2022-05-09 13:04:17,404 INFO [train.py:715] (4/8) Epoch 18, batch 34700, loss[loss=0.1314, simple_loss=0.2073, pruned_loss=0.02777, over 4811.00 frames.], tot_loss[loss=0.133, simple_loss=0.2077, pruned_loss=0.02912, over 971101.94 frames.], batch size: 25, lr: 1.21e-04
2022-05-09 13:04:56,539 INFO [train.py:715] (4/8) Epoch 18, batch 34750, loss[loss=0.14, simple_loss=0.2067, pruned_loss=0.03668, over 4744.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2069, pruned_loss=0.02906, over 970610.08 frames.], batch size: 19, lr: 1.21e-04
2022-05-09 13:05:34,160 INFO [train.py:715] (4/8) Epoch 18, batch 34800, loss[loss=0.1219, simple_loss=0.1977, pruned_loss=0.02299, over 4779.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02933, over 969286.07 frames.], batch size: 12, lr: 1.21e-04
2022-05-09 13:06:24,923 INFO [train.py:715] (4/8) Epoch 19, batch 0, loss[loss=0.1199, simple_loss=0.1909, pruned_loss=0.02452, over 4901.00 frames.], tot_loss[loss=0.1199, simple_loss=0.1909, pruned_loss=0.02452, over 4901.00 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:07:03,498 INFO [train.py:715] (4/8) Epoch 19, batch 50, loss[loss=0.1304, simple_loss=0.2116, pruned_loss=0.02464, over 4787.00 frames.], tot_loss[loss=0.1339, simple_loss=0.2089, pruned_loss=0.02943, over 219422.15 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 13:07:43,523 INFO [train.py:715] (4/8) Epoch 19, batch 100, loss[loss=0.1399, simple_loss=0.2071, pruned_loss=0.03638, over 4947.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2077, pruned_loss=0.02961, over 386986.38 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 13:08:23,942 INFO [train.py:715] (4/8) Epoch 19, batch 150, loss[loss=0.1353, simple_loss=0.2061, pruned_loss=0.03229, over 4828.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02891, over 516628.03 frames.], batch size: 13, lr: 1.18e-04
2022-05-09 13:09:04,142 INFO [train.py:715] (4/8) Epoch 19, batch 200, loss[loss=0.115, simple_loss=0.201, pruned_loss=0.01445, over 4766.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02871, over 617446.31 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:09:44,076 INFO [train.py:715] (4/8) Epoch 19, batch 250, loss[loss=0.1425, simple_loss=0.2154, pruned_loss=0.03486, over 4711.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2062, pruned_loss=0.02811, over 696552.32 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:10:24,217 INFO [train.py:715] (4/8) Epoch 19, batch 300, loss[loss=0.1374, simple_loss=0.2176, pruned_loss=0.02861, over 4986.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2054, pruned_loss=0.02757, over 758535.58 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:11:04,671 INFO [train.py:715] (4/8) Epoch 19, batch 350, loss[loss=0.1085, simple_loss=0.1864, pruned_loss=0.01525, over 4931.00 frames.], tot_loss[loss=0.13, simple_loss=0.2048, pruned_loss=0.02759, over 805337.14 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 13:11:43,720 INFO [train.py:715] (4/8) Epoch 19, batch 400, loss[loss=0.1264, simple_loss=0.2028, pruned_loss=0.02501, over 4982.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2051, pruned_loss=0.02761, over 842565.01 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 13:12:24,043 INFO [train.py:715] (4/8) Epoch 19, batch 450, loss[loss=0.1142, simple_loss=0.1876, pruned_loss=0.02046, over 4797.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2046, pruned_loss=0.02727, over 870880.12 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 13:13:04,619 INFO [train.py:715] (4/8) Epoch 19, batch 500, loss[loss=0.1304, simple_loss=0.2084, pruned_loss=0.02624, over 4874.00 frames.], tot_loss[loss=0.1291, simple_loss=0.204, pruned_loss=0.02711, over 893902.61 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 13:13:44,285 INFO [train.py:715] (4/8) Epoch 19, batch 550, loss[loss=0.1105, simple_loss=0.1841, pruned_loss=0.01841, over 4832.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2049, pruned_loss=0.02799, over 911426.77 frames.], batch size: 26, lr: 1.18e-04
2022-05-09 13:14:24,234 INFO [train.py:715] (4/8) Epoch 19, batch 600, loss[loss=0.1392, simple_loss=0.2196, pruned_loss=0.02938, over 4947.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02823, over 925537.05 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:15:04,544 INFO [train.py:715] (4/8) Epoch 19, batch 650, loss[loss=0.125, simple_loss=0.1941, pruned_loss=0.02797, over 4981.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02837, over 935696.56 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 13:15:44,871 INFO [train.py:715] (4/8) Epoch 19, batch 700, loss[loss=0.1285, simple_loss=0.2029, pruned_loss=0.02699, over 4839.00 frames.], tot_loss[loss=0.131, simple_loss=0.2059, pruned_loss=0.02805, over 943052.15 frames.], batch size: 30, lr: 1.18e-04
2022-05-09 13:16:24,138 INFO [train.py:715] (4/8) Epoch 19, batch 750, loss[loss=0.1425, simple_loss=0.2244, pruned_loss=0.03029, over 4920.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2059, pruned_loss=0.02813, over 950020.91 frames.], batch size: 23, lr: 1.18e-04
2022-05-09 13:17:03,937 INFO [train.py:715] (4/8) Epoch 19, batch 800, loss[loss=0.1341, simple_loss=0.2171, pruned_loss=0.02554, over 4940.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2059, pruned_loss=0.02795, over 955342.60 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 13:17:44,203 INFO [train.py:715] (4/8) Epoch 19, batch 850, loss[loss=0.1366, simple_loss=0.2076, pruned_loss=0.03282, over 4895.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2055, pruned_loss=0.02796, over 958141.61 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:18:24,382 INFO [train.py:715] (4/8) Epoch 19, batch 900, loss[loss=0.1151, simple_loss=0.1918, pruned_loss=0.01923, over 4722.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02825, over 961245.85 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:19:03,888 INFO [train.py:715] (4/8) Epoch 19, batch 950, loss[loss=0.1165, simple_loss=0.1876, pruned_loss=0.02266, over 4945.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.0284, over 963352.48 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 13:19:43,252 INFO [train.py:715] (4/8) Epoch 19, batch 1000, loss[loss=0.1442, simple_loss=0.2227, pruned_loss=0.03284, over 4788.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02876, over 964286.85 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:20:23,191 INFO [train.py:715] (4/8) Epoch 19, batch 1050, loss[loss=0.1266, simple_loss=0.2099, pruned_loss=0.02167, over 4783.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02866, over 966209.14 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:21:02,192 INFO [train.py:715] (4/8) Epoch 19, batch 1100, loss[loss=0.1235, simple_loss=0.2064, pruned_loss=0.02031, over 4822.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.0286, over 967658.81 frames.], batch size: 26, lr: 1.18e-04
2022-05-09 13:21:42,015 INFO [train.py:715] (4/8) Epoch 19, batch 1150, loss[loss=0.1256, simple_loss=0.1975, pruned_loss=0.0268, over 4914.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02867, over 967880.15 frames.], batch size: 23, lr: 1.18e-04
2022-05-09 13:22:21,962 INFO [train.py:715] (4/8) Epoch 19, batch 1200, loss[loss=0.162, simple_loss=0.2389, pruned_loss=0.0425, over 4949.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02856, over 968770.15 frames.], batch size: 39, lr: 1.18e-04
2022-05-09 13:23:01,715 INFO [train.py:715] (4/8) Epoch 19, batch 1250, loss[loss=0.1297, simple_loss=0.1996, pruned_loss=0.02989, over 4776.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02842, over 969070.57 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 13:23:41,055 INFO [train.py:715] (4/8) Epoch 19, batch 1300, loss[loss=0.1468, simple_loss=0.2208, pruned_loss=0.03642, over 4974.00 frames.], tot_loss[loss=0.1318, simple_loss=0.206, pruned_loss=0.02882, over 969716.50 frames.], batch size: 40, lr: 1.18e-04
2022-05-09 13:24:20,596 INFO [train.py:715] (4/8) Epoch 19, batch 1350, loss[loss=0.1217, simple_loss=0.1883, pruned_loss=0.02759, over 4987.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2059, pruned_loss=0.02895, over 970946.35 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:25:00,615 INFO [train.py:715] (4/8) Epoch 19, batch 1400, loss[loss=0.1464, simple_loss=0.2236, pruned_loss=0.03458, over 4863.00 frames.], tot_loss[loss=0.1321, simple_loss=0.206, pruned_loss=0.02914, over 970698.22 frames.], batch size: 20, lr: 1.18e-04
2022-05-09 13:25:39,918 INFO [train.py:715] (4/8) Epoch 19, batch 1450, loss[loss=0.1633, simple_loss=0.2279, pruned_loss=0.04934, over 4815.00 frames.], tot_loss[loss=0.1321, simple_loss=0.206, pruned_loss=0.0291, over 971602.53 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:26:20,264 INFO [train.py:715] (4/8) Epoch 19, batch 1500, loss[loss=0.1151, simple_loss=0.204, pruned_loss=0.01309, over 4785.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2059, pruned_loss=0.02897, over 972671.90 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 13:27:00,282 INFO [train.py:715] (4/8) Epoch 19, batch 1550, loss[loss=0.1482, simple_loss=0.2232, pruned_loss=0.03663, over 4969.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02913, over 972584.43 frames.], batch size: 35, lr: 1.18e-04
2022-05-09 13:27:40,364 INFO [train.py:715] (4/8) Epoch 19, batch 1600, loss[loss=0.1647, simple_loss=0.2356, pruned_loss=0.0469, over 4933.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02878, over 973301.17 frames.], batch size: 39, lr: 1.18e-04
2022-05-09 13:28:19,706 INFO [train.py:715] (4/8) Epoch 19, batch 1650, loss[loss=0.1612, simple_loss=0.2471, pruned_loss=0.0377, over 4771.00 frames.], tot_loss[loss=0.1333, simple_loss=0.2073, pruned_loss=0.02963, over 973142.43 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 13:28:59,072 INFO [train.py:715] (4/8) Epoch 19, batch 1700, loss[loss=0.1253, simple_loss=0.2026, pruned_loss=0.02403, over 4990.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.0294, over 973495.43 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:29:39,072 INFO [train.py:715] (4/8) Epoch 19, batch 1750, loss[loss=0.141, simple_loss=0.2198, pruned_loss=0.03109, over 4929.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2069, pruned_loss=0.02914, over 973724.32 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:30:18,169 INFO [train.py:715] (4/8) Epoch 19, batch 1800, loss[loss=0.1465, simple_loss=0.2168, pruned_loss=0.03812, over 4757.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02938, over 973648.88 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 13:30:57,611 INFO [train.py:715] (4/8) Epoch 19, batch 1850, loss[loss=0.1121, simple_loss=0.1894, pruned_loss=0.01734, over 4846.00 frames.], tot_loss[loss=0.133, simple_loss=0.2072, pruned_loss=0.02943, over 973229.75 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:31:36,857 INFO [train.py:715] (4/8) Epoch 19, batch 1900, loss[loss=0.1237, simple_loss=0.1997, pruned_loss=0.0238, over 4960.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02931, over 973462.57 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 13:32:16,780 INFO [train.py:715] (4/8) Epoch 19, batch 1950, loss[loss=0.1321, simple_loss=0.2055, pruned_loss=0.02932, over 4847.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2065, pruned_loss=0.02966, over 973223.08 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:32:55,077 INFO [train.py:715] (4/8) Epoch 19, batch 2000, loss[loss=0.1349, simple_loss=0.2083, pruned_loss=0.03073, over 4954.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2068, pruned_loss=0.02945, over 973868.33 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 13:33:34,211 INFO [train.py:715] (4/8) Epoch 19, batch 2050, loss[loss=0.1307, simple_loss=0.1998, pruned_loss=0.03083, over 4893.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2072, pruned_loss=0.02985, over 973440.74 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:34:13,317 INFO [train.py:715] (4/8) Epoch 19, batch 2100, loss[loss=0.1278, simple_loss=0.2007, pruned_loss=0.02745, over 4833.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.0292, over 973585.56 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:34:52,132 INFO [train.py:715] (4/8) Epoch 19, batch 2150, loss[loss=0.1333, simple_loss=0.2143, pruned_loss=0.02621, over 4915.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02902, over 973144.97 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:35:31,126 INFO [train.py:715] (4/8) Epoch 19, batch 2200, loss[loss=0.1214, simple_loss=0.1974, pruned_loss=0.02271, over 4919.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02878, over 973057.75 frames.], batch size: 23, lr: 1.18e-04
2022-05-09 13:36:09,823 INFO [train.py:715] (4/8) Epoch 19, batch 2250, loss[loss=0.1386, simple_loss=0.2233, pruned_loss=0.02692, over 4817.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2075, pruned_loss=0.02943, over 973822.83 frames.], batch size: 26, lr: 1.18e-04
2022-05-09 13:36:49,414 INFO [train.py:715] (4/8) Epoch 19, batch 2300, loss[loss=0.1061, simple_loss=0.1799, pruned_loss=0.01618, over 4795.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02884, over 972862.91 frames.], batch size: 12, lr: 1.18e-04
2022-05-09 13:37:28,006 INFO [train.py:715] (4/8) Epoch 19, batch 2350, loss[loss=0.1193, simple_loss=0.1932, pruned_loss=0.02274, over 4833.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2059, pruned_loss=0.02829, over 971899.04 frames.], batch size: 13, lr: 1.18e-04
2022-05-09 13:38:07,165 INFO [train.py:715] (4/8) Epoch 19, batch 2400, loss[loss=0.1459, simple_loss=0.2147, pruned_loss=0.03853, over 4959.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02866, over 971602.81 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:38:46,615 INFO [train.py:715] (4/8) Epoch 19, batch 2450, loss[loss=0.151, simple_loss=0.2199, pruned_loss=0.04105, over 4647.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.02895, over 971667.04 frames.], batch size: 13, lr: 1.18e-04
2022-05-09 13:39:25,449 INFO [train.py:715] (4/8) Epoch 19, batch 2500, loss[loss=0.1148, simple_loss=0.1872, pruned_loss=0.02118, over 4790.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02873, over 972102.29 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:40:04,469 INFO [train.py:715] (4/8) Epoch 19, batch 2550, loss[loss=0.121, simple_loss=0.1914, pruned_loss=0.02526, over 4972.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02836, over 972379.62 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 13:40:44,011 INFO [train.py:715] (4/8) Epoch 19, batch 2600, loss[loss=0.1361, simple_loss=0.2136, pruned_loss=0.02925, over 4752.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02826, over 971777.87 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:41:26,471 INFO [train.py:715] (4/8) Epoch 19, batch 2650, loss[loss=0.1432, simple_loss=0.2244, pruned_loss=0.03097, over 4857.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2066, pruned_loss=0.02836, over 972304.91 frames.], batch size: 30, lr: 1.18e-04
2022-05-09 13:42:05,377 INFO [train.py:715] (4/8) Epoch 19, batch 2700, loss[loss=0.1534, simple_loss=0.2311, pruned_loss=0.03782, over 4893.00 frames.], tot_loss[loss=0.1321, simple_loss=0.207, pruned_loss=0.02862, over 971747.07 frames.], batch size: 38, lr: 1.18e-04
2022-05-09 13:42:44,052 INFO [train.py:715] (4/8) Epoch 19, batch 2750, loss[loss=0.1273, simple_loss=0.2007, pruned_loss=0.02692, over 4793.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2069, pruned_loss=0.02862, over 972502.05 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 13:43:23,786 INFO [train.py:715] (4/8) Epoch 19, batch 2800, loss[loss=0.1364, simple_loss=0.197, pruned_loss=0.03793, over 4861.00 frames.], tot_loss[loss=0.1321, simple_loss=0.207, pruned_loss=0.02865, over 972864.26 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 13:44:03,072 INFO [train.py:715] (4/8) Epoch 19, batch 2850, loss[loss=0.147, simple_loss=0.2214, pruned_loss=0.03627, over 4848.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02853, over 972800.23 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 13:44:42,006 INFO [train.py:715] (4/8) Epoch 19, batch 2900, loss[loss=0.1002, simple_loss=0.1763, pruned_loss=0.01209, over 4994.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2068, pruned_loss=0.02842, over 972322.72 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:45:20,759 INFO [train.py:715] (4/8) Epoch 19, batch 2950, loss[loss=0.09736, simple_loss=0.1755, pruned_loss=0.00963, over 4919.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2059, pruned_loss=0.02794, over 973878.44 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:46:00,076 INFO [train.py:715] (4/8) Epoch 19, batch 3000, loss[loss=0.1182, simple_loss=0.1958, pruned_loss=0.02026, over 4842.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02798, over 974151.99 frames.], batch size: 20, lr: 1.18e-04
2022-05-09 13:46:00,077 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 13:46:10,049 INFO [train.py:742] (4/8) Epoch 19, validation: loss=0.1045, simple_loss=0.1877, pruned_loss=0.01062, over 914524.00 frames.
2022-05-09 13:46:50,340 INFO [train.py:715] (4/8) Epoch 19, batch 3050, loss[loss=0.1212, simple_loss=0.1971, pruned_loss=0.02263, over 4885.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2056, pruned_loss=0.02777, over 974181.56 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 13:47:29,684 INFO [train.py:715] (4/8) Epoch 19, batch 3100, loss[loss=0.1274, simple_loss=0.2013, pruned_loss=0.02674, over 4766.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2056, pruned_loss=0.02799, over 974143.75 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:48:08,830 INFO [train.py:715] (4/8) Epoch 19, batch 3150, loss[loss=0.178, simple_loss=0.237, pruned_loss=0.05946, over 4753.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02881, over 973343.09 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:48:48,669 INFO [train.py:715] (4/8) Epoch 19, batch 3200, loss[loss=0.1266, simple_loss=0.1948, pruned_loss=0.02918, over 4764.00 frames.], tot_loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.0291, over 972484.91 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:49:27,688 INFO [train.py:715] (4/8) Epoch 19, batch 3250, loss[loss=0.1421, simple_loss=0.2124, pruned_loss=0.03584, over 4884.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02859, over 973116.39 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:50:07,131 INFO [train.py:715] (4/8) Epoch 19, batch 3300, loss[loss=0.1648, simple_loss=0.2253, pruned_loss=0.05218, over 4885.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02906, over 973524.00 frames.], batch size: 22, lr: 1.18e-04
2022-05-09 13:50:46,363 INFO [train.py:715] (4/8) Epoch 19, batch 3350, loss[loss=0.1276, simple_loss=0.1982, pruned_loss=0.02848, over 4977.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02852, over 973159.36 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:51:26,506 INFO [train.py:715] (4/8) Epoch 19, batch 3400, loss[loss=0.1235, simple_loss=0.1985, pruned_loss=0.02427, over 4756.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02848, over 972680.64 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:52:05,356 INFO [train.py:715] (4/8) Epoch 19, batch 3450, loss[loss=0.1278, simple_loss=0.2099, pruned_loss=0.02289, over 4922.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02825, over 972743.77 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:52:44,615 INFO [train.py:715] (4/8) Epoch 19, batch 3500, loss[loss=0.1158, simple_loss=0.1857, pruned_loss=0.02292, over 4974.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02801, over 972477.88 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:53:23,733 INFO [train.py:715] (4/8) Epoch 19, batch 3550, loss[loss=0.1377, simple_loss=0.215, pruned_loss=0.03017, over 4925.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02819, over 973097.16 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:54:02,619 INFO [train.py:715] (4/8) Epoch 19, batch 3600, loss[loss=0.1273, simple_loss=0.2102, pruned_loss=0.02217, over 4747.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2049, pruned_loss=0.02818, over 973496.23 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 13:54:42,248 INFO [train.py:715] (4/8) Epoch 19, batch 3650, loss[loss=0.1212, simple_loss=0.1996, pruned_loss=0.02145, over 4797.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2042, pruned_loss=0.02802, over 972262.24 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:55:21,394 INFO [train.py:715] (4/8) Epoch 19, batch 3700, loss[loss=0.1215, simple_loss=0.1979, pruned_loss=0.02251, over 4975.00 frames.], tot_loss[loss=0.1306, simple_loss=0.205, pruned_loss=0.02804, over 972319.57 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:56:01,851 INFO [train.py:715] (4/8) Epoch 19, batch 3750, loss[loss=0.1194, simple_loss=0.2024, pruned_loss=0.01821, over 4813.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.0282, over 971843.53 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 13:56:40,835 INFO [train.py:715] (4/8) Epoch 19, batch 3800, loss[loss=0.174, simple_loss=0.2367, pruned_loss=0.05566, over 4753.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02819, over 971779.12 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 13:57:19,813 INFO [train.py:715] (4/8) Epoch 19, batch 3850, loss[loss=0.1094, simple_loss=0.184, pruned_loss=0.01737, over 4708.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02881, over 971728.57 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 13:57:59,508 INFO [train.py:715] (4/8) Epoch 19, batch 3900, loss[loss=0.1343, simple_loss=0.2063, pruned_loss=0.03117, over 4778.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02858, over 971264.59 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 13:58:38,560 INFO [train.py:715] (4/8) Epoch 19, batch 3950, loss[loss=0.1428, simple_loss=0.2169, pruned_loss=0.0344, over 4858.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02926, over 970893.66 frames.], batch size: 20, lr: 1.18e-04
2022-05-09 13:59:17,191 INFO [train.py:715] (4/8) Epoch 19, batch 4000, loss[loss=0.1279, simple_loss=0.2005, pruned_loss=0.02765, over 4923.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2064, pruned_loss=0.02961, over 971338.08 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 13:59:56,646 INFO [train.py:715] (4/8) Epoch 19, batch 4050, loss[loss=0.1865, simple_loss=0.2649, pruned_loss=0.05402, over 4754.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2067, pruned_loss=0.02981, over 970612.71 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:00:36,795 INFO [train.py:715] (4/8) Epoch 19, batch 4100, loss[loss=0.1192, simple_loss=0.1904, pruned_loss=0.02395, over 4973.00 frames.], tot_loss[loss=0.1334, simple_loss=0.2073, pruned_loss=0.02981, over 971558.25 frames.], batch size: 35, lr: 1.18e-04
2022-05-09 14:01:15,965 INFO [train.py:715] (4/8) Epoch 19, batch 4150, loss[loss=0.1197, simple_loss=0.1938, pruned_loss=0.02281, over 4912.00 frames.], tot_loss[loss=0.133, simple_loss=0.207, pruned_loss=0.02947, over 971916.91 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 14:01:54,739 INFO [train.py:715] (4/8) Epoch 19, batch 4200, loss[loss=0.1453, simple_loss=0.2199, pruned_loss=0.03537, over 4912.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2064, pruned_loss=0.02944, over 972214.47 frames.], batch size: 39, lr: 1.18e-04
2022-05-09 14:02:33,999 INFO [train.py:715] (4/8) Epoch 19, batch 4250, loss[loss=0.1072, simple_loss=0.1843, pruned_loss=0.01503, over 4973.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2071, pruned_loss=0.02965, over 972300.62 frames.], batch size: 35, lr: 1.18e-04
2022-05-09 14:03:13,061 INFO [train.py:715] (4/8) Epoch 19, batch 4300, loss[loss=0.1246, simple_loss=0.206, pruned_loss=0.02157, over 4953.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2071, pruned_loss=0.02939, over 972338.95 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 14:03:52,547 INFO [train.py:715] (4/8) Epoch 19, batch 4350, loss[loss=0.1362, simple_loss=0.2076, pruned_loss=0.0324, over 4969.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02896, over 972343.39 frames.], batch size: 35, lr: 1.18e-04
2022-05-09 14:04:31,617 INFO [train.py:715] (4/8) Epoch 19, batch 4400, loss[loss=0.1462, simple_loss=0.2194, pruned_loss=0.03653, over 4687.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2073, pruned_loss=0.02942, over 971128.88 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:05:11,661 INFO [train.py:715] (4/8) Epoch 19, batch 4450, loss[loss=0.1069, simple_loss=0.1808, pruned_loss=0.0165, over 4861.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02914, over 971017.04 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 14:05:50,509 INFO [train.py:715] (4/8) Epoch 19, batch 4500, loss[loss=0.1347, simple_loss=0.2088, pruned_loss=0.03029, over 4969.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02912, over 971792.82 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 14:06:29,202 INFO [train.py:715] (4/8) Epoch 19, batch 4550, loss[loss=0.1263, simple_loss=0.2038, pruned_loss=0.02436, over 4991.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02859, over 972017.85 frames.], batch size: 28, lr: 1.18e-04
2022-05-09 14:07:08,892 INFO [train.py:715] (4/8) Epoch 19, batch 4600, loss[loss=0.1168, simple_loss=0.1877, pruned_loss=0.02296, over 4923.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.0288, over 971855.81 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 14:07:48,135 INFO [train.py:715] (4/8) Epoch 19, batch 4650, loss[loss=0.1422, simple_loss=0.2076, pruned_loss=0.03838, over 4769.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02869, over 972497.18 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 14:08:27,121 INFO [train.py:715] (4/8) Epoch 19, batch 4700, loss[loss=0.1469, simple_loss=0.2115, pruned_loss=0.04119, over 4752.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02891, over 972380.62 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:09:06,334 INFO [train.py:715] (4/8) Epoch 19, batch 4750, loss[loss=0.132, simple_loss=0.2037, pruned_loss=0.03017, over 4967.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02908, over 972264.89 frames.], batch size: 40, lr: 1.18e-04
2022-05-09 14:09:46,297 INFO [train.py:715] (4/8) Epoch 19, batch 4800, loss[loss=0.1303, simple_loss=0.2187, pruned_loss=0.02097, over 4817.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2062, pruned_loss=0.02911, over 971590.02 frames.], batch size: 27, lr: 1.18e-04
2022-05-09 14:10:25,678 INFO [train.py:715] (4/8) Epoch 19, batch 4850, loss[loss=0.1299, simple_loss=0.1996, pruned_loss=0.03009, over 4864.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2064, pruned_loss=0.02885, over 971999.02 frames.], batch size: 20, lr: 1.18e-04
2022-05-09 14:11:04,336 INFO [train.py:715] (4/8) Epoch 19, batch 4900, loss[loss=0.1122, simple_loss=0.192, pruned_loss=0.01623, over 4750.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.0285, over 971709.80 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:11:44,092 INFO [train.py:715] (4/8) Epoch 19, batch 4950, loss[loss=0.134, simple_loss=0.2102, pruned_loss=0.02896, over 4965.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.0288, over 972151.87 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 14:12:23,740 INFO [train.py:715] (4/8) Epoch 19, batch 5000, loss[loss=0.1541, simple_loss=0.2232, pruned_loss=0.0425, over 4904.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2064, pruned_loss=0.02929, over 972624.16 frames.], batch size: 39, lr: 1.18e-04
2022-05-09 14:13:02,751 INFO [train.py:715] (4/8) Epoch 19, batch 5050, loss[loss=0.1217, simple_loss=0.2072, pruned_loss=0.01812, over 4761.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.0289, over 972888.30 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 14:13:41,117 INFO [train.py:715] (4/8) Epoch 19, batch 5100, loss[loss=0.1297, simple_loss=0.2074, pruned_loss=0.02594, over 4823.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02883, over 973077.68 frames.], batch size: 26, lr: 1.18e-04
2022-05-09 14:14:21,159 INFO [train.py:715] (4/8) Epoch 19, batch 5150, loss[loss=0.125, simple_loss=0.2073, pruned_loss=0.0214, over 4863.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02854, over 973253.72 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 14:15:00,190 INFO [train.py:715] (4/8) Epoch 19, batch 5200, loss[loss=0.1044, simple_loss=0.1763, pruned_loss=0.0162, over 4872.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02894, over 973540.46 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:15:38,853 INFO [train.py:715] (4/8) Epoch 19, batch 5250, loss[loss=0.1165, simple_loss=0.1885, pruned_loss=0.02223, over 4749.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2055, pruned_loss=0.02863, over 972346.69 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:16:18,533 INFO [train.py:715] (4/8) Epoch 19, batch 5300, loss[loss=0.1037, simple_loss=0.1721, pruned_loss=0.0176, over 4765.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2055, pruned_loss=0.02862, over 972203.94 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:16:58,483 INFO [train.py:715] (4/8) Epoch 19, batch 5350, loss[loss=0.1527, simple_loss=0.226, pruned_loss=0.03966, over 4970.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02851, over 972426.62 frames.], batch size: 39, lr: 1.18e-04
2022-05-09 14:17:38,562 INFO [train.py:715] (4/8) Epoch 19, batch 5400, loss[loss=0.1195, simple_loss=0.1998, pruned_loss=0.01955, over 4929.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2053, pruned_loss=0.02851, over 971972.41 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 14:18:17,825 INFO [train.py:715] (4/8) Epoch 19, batch 5450, loss[loss=0.1189, simple_loss=0.1951, pruned_loss=0.02129, over 4939.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2048, pruned_loss=0.02853, over 972747.83 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 14:18:58,016 INFO [train.py:715] (4/8) Epoch 19, batch 5500, loss[loss=0.1466, simple_loss=0.2271, pruned_loss=0.03306, over 4750.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02879, over 973912.57 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:19:37,205 INFO [train.py:715] (4/8) Epoch 19, batch 5550, loss[loss=0.1479, simple_loss=0.2252, pruned_loss=0.03531, over 4737.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02852, over 973421.84 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:20:16,794 INFO [train.py:715] (4/8) Epoch 19, batch 5600, loss[loss=0.1392, simple_loss=0.2125, pruned_loss=0.03297, over 4894.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02851, over 973175.94 frames.], batch size: 22, lr: 1.18e-04
2022-05-09 14:20:56,104 INFO [train.py:715] (4/8) Epoch 19, batch 5650, loss[loss=0.1073, simple_loss=0.1849, pruned_loss=0.01487, over 4799.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.0287, over 973080.40 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 14:21:35,827 INFO [train.py:715] (4/8) Epoch 19, batch 5700, loss[loss=0.1064, simple_loss=0.1831, pruned_loss=0.01487, over 4886.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02879, over 973389.78 frames.], batch size: 22, lr: 1.18e-04
2022-05-09 14:22:15,333 INFO [train.py:715] (4/8) Epoch 19, batch 5750, loss[loss=0.1125, simple_loss=0.1824, pruned_loss=0.02126, over 4977.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02869, over 973928.19 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 14:22:53,919 INFO [train.py:715] (4/8) Epoch 19, batch 5800, loss[loss=0.131, simple_loss=0.2091, pruned_loss=0.02643, over 4931.00 frames.], tot_loss[loss=0.132, simple_loss=0.2063, pruned_loss=0.02881, over 973887.10 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 14:23:33,193 INFO [train.py:715] (4/8) Epoch 19, batch 5850, loss[loss=0.1438, simple_loss=0.2188, pruned_loss=0.03441, over 4864.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02848, over 974039.52 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:24:11,659 INFO [train.py:715] (4/8) Epoch 19, batch 5900, loss[loss=0.1383, simple_loss=0.2096, pruned_loss=0.03349, over 4860.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2057, pruned_loss=0.02898, over 973049.45 frames.], batch size: 20, lr: 1.18e-04
2022-05-09 14:24:51,083 INFO [train.py:715] (4/8) Epoch 19, batch 5950, loss[loss=0.1196, simple_loss=0.1982, pruned_loss=0.02046, over 4919.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2046, pruned_loss=0.02812, over 973172.67 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 14:25:30,285 INFO [train.py:715] (4/8) Epoch 19, batch 6000, loss[loss=0.1309, simple_loss=0.2179, pruned_loss=0.02191, over 4959.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2057, pruned_loss=0.02847, over 973839.88 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 14:25:30,286 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 14:25:40,195 INFO [train.py:742] (4/8) Epoch 19, validation: loss=0.1046, simple_loss=0.1878, pruned_loss=0.01067, over 914524.00 frames.
2022-05-09 14:26:19,489 INFO [train.py:715] (4/8) Epoch 19, batch 6050, loss[loss=0.1145, simple_loss=0.1814, pruned_loss=0.02377, over 4897.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02899, over 974132.04 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 14:26:58,345 INFO [train.py:715] (4/8) Epoch 19, batch 6100, loss[loss=0.1585, simple_loss=0.2373, pruned_loss=0.03979, over 4966.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02891, over 974077.48 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 14:27:37,412 INFO [train.py:715] (4/8) Epoch 19, batch 6150, loss[loss=0.1213, simple_loss=0.1884, pruned_loss=0.02712, over 4944.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2061, pruned_loss=0.02904, over 973713.54 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 14:28:15,611 INFO [train.py:715] (4/8) Epoch 19, batch 6200, loss[loss=0.1223, simple_loss=0.1891, pruned_loss=0.02776, over 4824.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02863, over 973609.27 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 14:28:55,856 INFO [train.py:715] (4/8) Epoch 19, batch 6250, loss[loss=0.1463, simple_loss=0.215, pruned_loss=0.03878, over 4885.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2049, pruned_loss=0.02837, over 973429.93 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:29:35,037 INFO [train.py:715] (4/8) Epoch 19, batch 6300, loss[loss=0.1031, simple_loss=0.1784, pruned_loss=0.01391, over 4816.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2042, pruned_loss=0.02843, over 973467.83 frames.], batch size: 12, lr: 1.18e-04
2022-05-09 14:30:14,721 INFO [train.py:715] (4/8) Epoch 19, batch 6350, loss[loss=0.1533, simple_loss=0.2278, pruned_loss=0.03943, over 4976.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2048, pruned_loss=0.0285, over 974000.07 frames.], batch size: 39, lr: 1.18e-04
2022-05-09 14:30:54,199 INFO [train.py:715] (4/8) Epoch 19, batch 6400, loss[loss=0.1347, simple_loss=0.2011, pruned_loss=0.03413, over 4823.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2045, pruned_loss=0.02853, over 973953.02 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:31:33,475 INFO [train.py:715] (4/8) Epoch 19, batch 6450, loss[loss=0.1279, simple_loss=0.2025, pruned_loss=0.02663, over 4984.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2052, pruned_loss=0.02871, over 973801.55 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 14:32:12,981 INFO [train.py:715] (4/8) Epoch 19, batch 6500, loss[loss=0.1326, simple_loss=0.2169, pruned_loss=0.02417, over 4932.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2059, pruned_loss=0.02893, over 973445.95 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 14:32:51,555 INFO [train.py:715] (4/8) Epoch 19, batch 6550, loss[loss=0.12, simple_loss=0.1965, pruned_loss=0.02179, over 4983.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02884, over 974094.60 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:33:31,049 INFO [train.py:715] (4/8) Epoch 19, batch 6600, loss[loss=0.1466, simple_loss=0.219, pruned_loss=0.03715, over 4793.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02847, over 974208.62 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 14:34:10,195 INFO [train.py:715] (4/8) Epoch 19, batch 6650, loss[loss=0.1221, simple_loss=0.2004, pruned_loss=0.02193, over 4809.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02887, over 973574.35 frames.], batch size: 13, lr: 1.18e-04
2022-05-09 14:34:48,938 INFO [train.py:715] (4/8) Epoch 19, batch 6700, loss[loss=0.1209, simple_loss=0.1945, pruned_loss=0.02368, over 4804.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2063, pruned_loss=0.02913, over 972698.85 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 14:35:28,067 INFO [train.py:715] (4/8) Epoch 19, batch 6750, loss[loss=0.131, simple_loss=0.201, pruned_loss=0.03053, over 4776.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02895, over 972281.31 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 14:36:07,535 INFO [train.py:715] (4/8) Epoch 19, batch 6800, loss[loss=0.1568, simple_loss=0.2297, pruned_loss=0.04194, over 4892.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02864, over 972454.20 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:36:46,927 INFO [train.py:715] (4/8) Epoch 19, batch 6850, loss[loss=0.105, simple_loss=0.1751, pruned_loss=0.0174, over 4748.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02839, over 972242.37 frames.], batch size: 12, lr: 1.18e-04
2022-05-09 14:37:25,088 INFO [train.py:715] (4/8) Epoch 19, batch 6900, loss[loss=0.1034, simple_loss=0.1809, pruned_loss=0.01291, over 4787.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2062, pruned_loss=0.02823, over 972621.77 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 14:38:04,131 INFO [train.py:715] (4/8) Epoch 19, batch 6950, loss[loss=0.1228, simple_loss=0.191, pruned_loss=0.0273, over 4912.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2067, pruned_loss=0.0282, over 972653.16 frames.], batch size: 23, lr: 1.18e-04
2022-05-09 14:38:43,600 INFO [train.py:715] (4/8) Epoch 19, batch 7000, loss[loss=0.1316, simple_loss=0.2102, pruned_loss=0.02646, over 4933.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2071, pruned_loss=0.02832, over 972746.57 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 14:39:22,851 INFO [train.py:715] (4/8) Epoch 19, batch 7050, loss[loss=0.1078, simple_loss=0.1767, pruned_loss=0.01945, over 4797.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2059, pruned_loss=0.02788, over 971173.70 frames.], batch size: 12, lr: 1.18e-04
2022-05-09 14:40:02,451 INFO [train.py:715] (4/8) Epoch 19, batch 7100, loss[loss=0.141, simple_loss=0.2146, pruned_loss=0.03366, over 4853.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.0288, over 971152.47 frames.], batch size: 20, lr: 1.18e-04
2022-05-09 14:40:42,073 INFO [train.py:715] (4/8) Epoch 19, batch 7150, loss[loss=0.1197, simple_loss=0.1994, pruned_loss=0.02001, over 4945.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02861, over 971179.95 frames.], batch size: 35, lr: 1.18e-04
2022-05-09 14:41:20,981 INFO [train.py:715] (4/8) Epoch 19, batch 7200, loss[loss=0.1477, simple_loss=0.2235, pruned_loss=0.03598, over 4903.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02877, over 971239.82 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:41:59,732 INFO [train.py:715] (4/8) Epoch 19, batch 7250, loss[loss=0.1554, simple_loss=0.2263, pruned_loss=0.04228, over 4932.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02855, over 971744.70 frames.], batch size: 39, lr: 1.18e-04
2022-05-09 14:42:39,094 INFO [train.py:715] (4/8) Epoch 19, batch 7300, loss[loss=0.1288, simple_loss=0.2059, pruned_loss=0.02584, over 4823.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02865, over 972263.48 frames.], batch size: 26, lr: 1.18e-04
2022-05-09 14:43:18,258 INFO [train.py:715] (4/8) Epoch 19, batch 7350, loss[loss=0.125, simple_loss=0.2088, pruned_loss=0.02057, over 4693.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2067, pruned_loss=0.02855, over 971714.22 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:43:57,163 INFO [train.py:715] (4/8) Epoch 19, batch 7400, loss[loss=0.1387, simple_loss=0.2111, pruned_loss=0.03318, over 4853.00 frames.], tot_loss[loss=0.1306, simple_loss=0.205, pruned_loss=0.02804, over 971051.80 frames.], batch size: 20, lr: 1.18e-04
2022-05-09 14:44:37,623 INFO [train.py:715] (4/8) Epoch 19, batch 7450, loss[loss=0.1118, simple_loss=0.1898, pruned_loss=0.01687, over 4809.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02785, over 971661.25 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 14:45:17,478 INFO [train.py:715] (4/8) Epoch 19, batch 7500, loss[loss=0.1425, simple_loss=0.2234, pruned_loss=0.03082, over 4903.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2049, pruned_loss=0.02762, over 971494.20 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:45:56,702 INFO [train.py:715] (4/8) Epoch 19, batch 7550, loss[loss=0.1761, simple_loss=0.2303, pruned_loss=0.06097, over 4830.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02804, over 971935.12 frames.], batch size: 30, lr: 1.18e-04
2022-05-09 14:46:36,053 INFO [train.py:715] (4/8) Epoch 19, batch 7600, loss[loss=0.1403, simple_loss=0.2087, pruned_loss=0.03592, over 4971.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02805, over 972619.40 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:47:16,835 INFO [train.py:715] (4/8) Epoch 19, batch 7650, loss[loss=0.1561, simple_loss=0.2462, pruned_loss=0.03304, over 4892.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2067, pruned_loss=0.02858, over 972584.52 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:47:56,151 INFO [train.py:715] (4/8) Epoch 19, batch 7700, loss[loss=0.1371, simple_loss=0.1978, pruned_loss=0.03822, over 4965.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02864, over 972547.12 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 14:48:34,960 INFO [train.py:715] (4/8) Epoch 19, batch 7750, loss[loss=0.1235, simple_loss=0.1918, pruned_loss=0.02755, over 4763.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.0286, over 973343.07 frames.], batch size: 12, lr: 1.18e-04
2022-05-09 14:49:14,657 INFO [train.py:715] (4/8) Epoch 19, batch 7800, loss[loss=0.1534, simple_loss=0.2189, pruned_loss=0.04391, over 4891.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.02883, over 973013.45 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 14:49:54,093 INFO [train.py:715] (4/8) Epoch 19, batch 7850, loss[loss=0.127, simple_loss=0.2126, pruned_loss=0.02071, over 4819.00 frames.], tot_loss[loss=0.132, simple_loss=0.207, pruned_loss=0.0285, over 972631.04 frames.], batch size: 27, lr: 1.18e-04
2022-05-09 14:50:33,359 INFO [train.py:715] (4/8) Epoch 19, batch 7900, loss[loss=0.1539, simple_loss=0.2171, pruned_loss=0.04532, over 4853.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2073, pruned_loss=0.0285, over 972718.74 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 14:51:11,761 INFO [train.py:715] (4/8) Epoch 19, batch 7950, loss[loss=0.152, simple_loss=0.2313, pruned_loss=0.03634, over 4810.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2065, pruned_loss=0.02816, over 972284.61 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 14:51:51,089 INFO [train.py:715] (4/8) Epoch 19, batch 8000, loss[loss=0.1397, simple_loss=0.2123, pruned_loss=0.03349, over 4946.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2073, pruned_loss=0.02815, over 973015.52 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 14:52:30,294 INFO [train.py:715] (4/8) Epoch 19, batch 8050, loss[loss=0.1273, simple_loss=0.2086, pruned_loss=0.02304, over 4797.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2068, pruned_loss=0.02798, over 974055.06 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 14:53:08,821 INFO [train.py:715] (4/8) Epoch 19, batch 8100, loss[loss=0.1139, simple_loss=0.1888, pruned_loss=0.01946, over 4901.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2061, pruned_loss=0.02808, over 973028.26 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 14:53:48,276 INFO [train.py:715] (4/8) Epoch 19, batch 8150, loss[loss=0.1058, simple_loss=0.1726, pruned_loss=0.01952, over 4968.00 frames.], tot_loss[loss=0.131, simple_loss=0.2057, pruned_loss=0.02813, over 972715.65 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 14:54:27,923 INFO [train.py:715] (4/8) Epoch 19, batch 8200, loss[loss=0.1077, simple_loss=0.1762, pruned_loss=0.01957, over 4950.00 frames.], tot_loss[loss=0.13, simple_loss=0.2045, pruned_loss=0.02771, over 972555.04 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 14:55:06,906 INFO [train.py:715] (4/8) Epoch 19, batch 8250, loss[loss=0.1454, simple_loss=0.2179, pruned_loss=0.03642, over 4794.00 frames.], tot_loss[loss=0.1297, simple_loss=0.2044, pruned_loss=0.02751, over 972318.93 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 14:55:45,536 INFO [train.py:715] (4/8) Epoch 19, batch 8300, loss[loss=0.1295, simple_loss=0.1938, pruned_loss=0.03256, over 4786.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2044, pruned_loss=0.02766, over 972631.39 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 14:56:25,220 INFO [train.py:715] (4/8) Epoch 19, batch 8350, loss[loss=0.1198, simple_loss=0.1988, pruned_loss=0.02035, over 4897.00 frames.], tot_loss[loss=0.13, simple_loss=0.2044, pruned_loss=0.02774, over 972130.42 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 14:57:04,448 INFO [train.py:715] (4/8) Epoch 19, batch 8400, loss[loss=0.1631, simple_loss=0.2276, pruned_loss=0.04937, over 4859.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2047, pruned_loss=0.02788, over 971334.41 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 14:57:43,452 INFO [train.py:715] (4/8) Epoch 19, batch 8450, loss[loss=0.106, simple_loss=0.1807, pruned_loss=0.01563, over 4818.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2041, pruned_loss=0.02777, over 971535.84 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 14:58:23,232 INFO [train.py:715] (4/8) Epoch 19, batch 8500, loss[loss=0.1136, simple_loss=0.1922, pruned_loss=0.01751, over 4922.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2043, pruned_loss=0.02825, over 971958.95 frames.], batch size: 23, lr: 1.18e-04
2022-05-09 14:59:01,924 INFO [train.py:715] (4/8) Epoch 19, batch 8550, loss[loss=0.1273, simple_loss=0.2064, pruned_loss=0.02407, over 4810.00 frames.], tot_loss[loss=0.131, simple_loss=0.205, pruned_loss=0.02848, over 971335.02 frames.], batch size: 13, lr: 1.18e-04
2022-05-09 14:59:41,017 INFO [train.py:715] (4/8) Epoch 19, batch 8600, loss[loss=0.1248, simple_loss=0.2035, pruned_loss=0.02305, over 4867.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2048, pruned_loss=0.02834, over 971168.29 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 15:00:20,522 INFO [train.py:715] (4/8) Epoch 19, batch 8650, loss[loss=0.1124, simple_loss=0.1803, pruned_loss=0.02229, over 4814.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02846, over 971133.23 frames.], batch size: 13, lr: 1.18e-04
2022-05-09 15:01:00,039 INFO [train.py:715] (4/8) Epoch 19, batch 8700, loss[loss=0.1265, simple_loss=0.2022, pruned_loss=0.0254, over 4879.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02855, over 971270.02 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 15:01:39,198 INFO [train.py:715] (4/8) Epoch 19, batch 8750, loss[loss=0.1303, simple_loss=0.1919, pruned_loss=0.03437, over 4843.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2066, pruned_loss=0.02943, over 971936.41 frames.], batch size: 30, lr: 1.18e-04
2022-05-09 15:02:17,958 INFO [train.py:715] (4/8) Epoch 19, batch 8800, loss[loss=0.1693, simple_loss=0.2406, pruned_loss=0.04902, over 4701.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2074, pruned_loss=0.02976, over 972670.92 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 15:02:57,606 INFO [train.py:715] (4/8) Epoch 19, batch 8850, loss[loss=0.1159, simple_loss=0.1947, pruned_loss=0.01855, over 4942.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2066, pruned_loss=0.02942, over 972694.91 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 15:03:36,661 INFO [train.py:715] (4/8) Epoch 19, batch 8900, loss[loss=0.1148, simple_loss=0.1876, pruned_loss=0.02106, over 4822.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02925, over 973010.72 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 15:04:16,006 INFO [train.py:715] (4/8) Epoch 19, batch 8950, loss[loss=0.121, simple_loss=0.1981, pruned_loss=0.02192, over 4933.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2063, pruned_loss=0.02923, over 973363.23 frames.], batch size: 29, lr: 1.18e-04
2022-05-09 15:04:54,904 INFO [train.py:715] (4/8) Epoch 19, batch 9000, loss[loss=0.1248, simple_loss=0.1988, pruned_loss=0.02544, over 4806.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.029, over 973298.70 frames.], batch size: 21, lr: 1.18e-04
2022-05-09 15:04:54,905 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 15:05:04,818 INFO [train.py:742] (4/8) Epoch 19, validation: loss=0.1047, simple_loss=0.1879, pruned_loss=0.01072, over 914524.00 frames.
2022-05-09 15:05:44,268 INFO [train.py:715] (4/8) Epoch 19, batch 9050, loss[loss=0.1165, simple_loss=0.1916, pruned_loss=0.0207, over 4754.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2067, pruned_loss=0.0288, over 973191.71 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 15:06:23,991 INFO [train.py:715] (4/8) Epoch 19, batch 9100, loss[loss=0.1553, simple_loss=0.2285, pruned_loss=0.04099, over 4881.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02867, over 973457.99 frames.], batch size: 38, lr: 1.18e-04
2022-05-09 15:07:03,254 INFO [train.py:715] (4/8) Epoch 19, batch 9150, loss[loss=0.1545, simple_loss=0.225, pruned_loss=0.04199, over 4849.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02868, over 973479.79 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 15:07:42,033 INFO [train.py:715] (4/8) Epoch 19, batch 9200, loss[loss=0.1155, simple_loss=0.1959, pruned_loss=0.0175, over 4988.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2044, pruned_loss=0.02772, over 973719.81 frames.], batch size: 25, lr: 1.18e-04
2022-05-09 15:08:21,755 INFO [train.py:715] (4/8) Epoch 19, batch 9250, loss[loss=0.1013, simple_loss=0.1746, pruned_loss=0.014, over 4809.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2041, pruned_loss=0.02778, over 973745.25 frames.], batch size: 13, lr: 1.18e-04
2022-05-09 15:09:00,949 INFO [train.py:715] (4/8) Epoch 19, batch 9300, loss[loss=0.1124, simple_loss=0.1701, pruned_loss=0.02737, over 4916.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02829, over 973864.27 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 15:09:39,864 INFO [train.py:715] (4/8) Epoch 19, batch 9350, loss[loss=0.1282, simple_loss=0.2051, pruned_loss=0.02562, over 4769.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2048, pruned_loss=0.02805, over 973749.15 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 15:10:19,954 INFO [train.py:715] (4/8) Epoch 19, batch 9400, loss[loss=0.1521, simple_loss=0.2396, pruned_loss=0.03223, over 4967.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02838, over 973544.79 frames.], batch size: 24, lr: 1.18e-04
2022-05-09 15:11:00,061 INFO [train.py:715] (4/8) Epoch 19, batch 9450, loss[loss=0.1256, simple_loss=0.1954, pruned_loss=0.02788, over 4978.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02873, over 972829.42 frames.], batch size: 15, lr: 1.18e-04
2022-05-09 15:11:38,882 INFO [train.py:715] (4/8) Epoch 19, batch 9500, loss[loss=0.1387, simple_loss=0.2063, pruned_loss=0.03552, over 4834.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02876, over 972066.17 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 15:12:18,095 INFO [train.py:715] (4/8) Epoch 19, batch 9550, loss[loss=0.1774, simple_loss=0.2342, pruned_loss=0.06026, over 4739.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02883, over 972515.11 frames.], batch size: 16, lr: 1.18e-04
2022-05-09 15:12:57,474 INFO [train.py:715] (4/8) Epoch 19, batch 9600, loss[loss=0.1292, simple_loss=0.1964, pruned_loss=0.03102, over 4757.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02903, over 972158.80 frames.], batch size: 12, lr: 1.18e-04
2022-05-09 15:13:36,648 INFO [train.py:715] (4/8) Epoch 19, batch 9650, loss[loss=0.1329, simple_loss=0.2145, pruned_loss=0.02568, over 4904.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02881, over 971947.41 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 15:14:14,974 INFO [train.py:715] (4/8) Epoch 19, batch 9700, loss[loss=0.1315, simple_loss=0.2053, pruned_loss=0.02887, over 4976.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.0285, over 971604.28 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 15:14:54,705 INFO [train.py:715] (4/8) Epoch 19, batch 9750, loss[loss=0.1271, simple_loss=0.2011, pruned_loss=0.02659, over 4775.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02838, over 970884.60 frames.], batch size: 17, lr: 1.18e-04
2022-05-09 15:15:34,782 INFO [train.py:715] (4/8) Epoch 19, batch 9800, loss[loss=0.1133, simple_loss=0.1893, pruned_loss=0.01864, over 4860.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02841, over 971194.99 frames.], batch size: 20, lr: 1.18e-04
2022-05-09 15:16:14,506 INFO [train.py:715] (4/8) Epoch 19, batch 9850, loss[loss=0.1361, simple_loss=0.2145, pruned_loss=0.02887, over 4896.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02832, over 971555.72 frames.], batch size: 19, lr: 1.18e-04
2022-05-09 15:16:53,380 INFO [train.py:715] (4/8) Epoch 19, batch 9900, loss[loss=0.1738, simple_loss=0.225, pruned_loss=0.06128, over 4843.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02869, over 971344.73 frames.], batch size: 32, lr: 1.18e-04
2022-05-09 15:17:33,334 INFO [train.py:715] (4/8) Epoch 19, batch 9950, loss[loss=0.1269, simple_loss=0.1978, pruned_loss=0.02799, over 4783.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02854, over 971109.90 frames.], batch size: 18, lr: 1.18e-04
2022-05-09 15:18:12,862 INFO [train.py:715] (4/8) Epoch 19, batch 10000, loss[loss=0.09733, simple_loss=0.1715, pruned_loss=0.01159, over 4981.00 frames.], tot_loss[loss=0.131, simple_loss=0.2052, pruned_loss=0.02839, over 972211.38 frames.], batch size: 14, lr: 1.18e-04
2022-05-09 15:18:51,543 INFO [train.py:715] (4/8) Epoch 19, batch 10050, loss[loss=0.1049, simple_loss=0.1791, pruned_loss=0.01538, over 4865.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2047, pruned_loss=0.02778, over 971950.97 frames.], batch size: 22, lr: 1.18e-04
2022-05-09 15:19:31,279 INFO [train.py:715] (4/8) Epoch 19, batch 10100, loss[loss=0.1477, simple_loss=0.2179, pruned_loss=0.0388, over 4771.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2045, pruned_loss=0.02757, over 972017.11 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 15:20:10,773 INFO [train.py:715] (4/8) Epoch 19, batch 10150, loss[loss=0.1119, simple_loss=0.1936, pruned_loss=0.01506, over 4822.00 frames.], tot_loss[loss=0.1291, simple_loss=0.2038, pruned_loss=0.02722, over 972235.97 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 15:20:49,760 INFO [train.py:715] (4/8) Epoch 19, batch 10200, loss[loss=0.1514, simple_loss=0.2171, pruned_loss=0.04287, over 4774.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2044, pruned_loss=0.02763, over 971633.40 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 15:21:29,139 INFO [train.py:715] (4/8) Epoch 19, batch 10250, loss[loss=0.1378, simple_loss=0.2099, pruned_loss=0.03289, over 4765.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02861, over 971585.74 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 15:22:09,267 INFO [train.py:715] (4/8) Epoch 19, batch 10300, loss[loss=0.1176, simple_loss=0.1939, pruned_loss=0.02063, over 4932.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02858, over 971582.86 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 15:22:48,846 INFO [train.py:715] (4/8) Epoch 19, batch 10350, loss[loss=0.1525, simple_loss=0.2213, pruned_loss=0.04187, over 4922.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02888, over 971396.77 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 15:23:27,531 INFO [train.py:715] (4/8) Epoch 19, batch 10400, loss[loss=0.1414, simple_loss=0.2157, pruned_loss=0.03362, over 4863.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2058, pruned_loss=0.02889, over 972142.70 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 15:24:07,292 INFO [train.py:715] (4/8) Epoch 19, batch 10450, loss[loss=0.1132, simple_loss=0.1887, pruned_loss=0.01883, over 4866.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02842, over 971753.12 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 15:24:47,013 INFO [train.py:715] (4/8) Epoch 19, batch 10500, loss[loss=0.1593, simple_loss=0.2301, pruned_loss=0.04423, over 4692.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02833, over 971130.29 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 15:25:25,929 INFO [train.py:715] (4/8) Epoch 19, batch 10550, loss[loss=0.1169, simple_loss=0.1917, pruned_loss=0.02107, over 4922.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2046, pruned_loss=0.02787, over 970755.03 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 15:26:04,897 INFO [train.py:715] (4/8) Epoch 19, batch 10600, loss[loss=0.1244, simple_loss=0.1948, pruned_loss=0.027, over 4815.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02828, over 970470.36 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 15:26:47,169 INFO [train.py:715] (4/8) Epoch 19, batch 10650, loss[loss=0.1283, simple_loss=0.2123, pruned_loss=0.02213, over 4948.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2048, pruned_loss=0.02783, over 971583.34 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 15:27:26,342 INFO [train.py:715] (4/8) Epoch 19, batch 10700, loss[loss=0.1022, simple_loss=0.1778, pruned_loss=0.01331, over 4941.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2054, pruned_loss=0.02804, over 971468.12 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 15:28:05,701 INFO [train.py:715] (4/8) Epoch 19, batch 10750, loss[loss=0.1145, simple_loss=0.1874, pruned_loss=0.02077, over 4744.00 frames.], tot_loss[loss=0.13, simple_loss=0.2047, pruned_loss=0.02763, over 972131.44 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 15:28:45,281 INFO [train.py:715] (4/8) Epoch 19, batch 10800, loss[loss=0.1813, simple_loss=0.2528, pruned_loss=0.05492, over 4916.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2044, pruned_loss=0.02768, over 971432.37 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 15:29:25,024 INFO [train.py:715] (4/8) Epoch 19, batch 10850, loss[loss=0.1429, simple_loss=0.2143, pruned_loss=0.03569, over 4988.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2047, pruned_loss=0.02787, over 970468.09 frames.], batch size: 31, lr: 1.17e-04
2022-05-09 15:30:03,632 INFO [train.py:715] (4/8) Epoch 19, batch 10900, loss[loss=0.1234, simple_loss=0.19, pruned_loss=0.02837, over 4967.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2055, pruned_loss=0.02789, over 971835.78 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 15:30:42,651 INFO [train.py:715] (4/8) Epoch 19, batch 10950, loss[loss=0.124, simple_loss=0.2052, pruned_loss=0.02142, over 4757.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2044, pruned_loss=0.02761, over 971607.00 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 15:31:22,352 INFO [train.py:715] (4/8) Epoch 19, batch 11000, loss[loss=0.1286, simple_loss=0.205, pruned_loss=0.02609, over 4975.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2054, pruned_loss=0.02791, over 972106.74 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 15:32:02,211 INFO [train.py:715] (4/8) Epoch 19, batch 11050, loss[loss=0.1171, simple_loss=0.1889, pruned_loss=0.02262, over 4938.00 frames.], tot_loss[loss=0.13, simple_loss=0.205, pruned_loss=0.02752, over 972312.00 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 15:32:40,681 INFO [train.py:715] (4/8) Epoch 19, batch 11100, loss[loss=0.1296, simple_loss=0.2037, pruned_loss=0.02773, over 4930.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2052, pruned_loss=0.02783, over 971969.05 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 15:33:20,041 INFO [train.py:715] (4/8) Epoch 19, batch 11150, loss[loss=0.1067, simple_loss=0.1809, pruned_loss=0.01625, over 4906.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2057, pruned_loss=0.02785, over 971877.75 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 15:33:59,453 INFO [train.py:715] (4/8) Epoch 19, batch 11200, loss[loss=0.1183, simple_loss=0.1928, pruned_loss=0.02191, over 4845.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2052, pruned_loss=0.02783, over 972333.03 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 15:34:38,834 INFO [train.py:715] (4/8) Epoch 19, batch 11250, loss[loss=0.1162, simple_loss=0.1891, pruned_loss=0.02169, over 4768.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02802, over 972585.89 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 15:35:18,204 INFO [train.py:715] (4/8) Epoch 19, batch 11300, loss[loss=0.1215, simple_loss=0.1928, pruned_loss=0.02511, over 4788.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2043, pruned_loss=0.02765, over 972809.73 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 15:35:56,991 INFO [train.py:715] (4/8) Epoch 19, batch 11350, loss[loss=0.1237, simple_loss=0.2022, pruned_loss=0.02264, over 4691.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2049, pruned_loss=0.02796, over 972788.00 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 15:36:36,601 INFO [train.py:715] (4/8) Epoch 19, batch 11400, loss[loss=0.1638, simple_loss=0.2353, pruned_loss=0.04614, over 4905.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2051, pruned_loss=0.02795, over 972864.49 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 15:37:16,209 INFO [train.py:715] (4/8) Epoch 19, batch 11450, loss[loss=0.1308, simple_loss=0.2018, pruned_loss=0.02988, over 4945.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02842, over 972344.10 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 15:37:56,152 INFO [train.py:715] (4/8) Epoch 19, batch 11500, loss[loss=0.1335, simple_loss=0.2046, pruned_loss=0.03113, over 4971.00 frames.], tot_loss[loss=0.1307, simple_loss=0.205, pruned_loss=0.02821, over 971973.80 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 15:38:35,579 INFO [train.py:715] (4/8) Epoch 19, batch 11550, loss[loss=0.1318, simple_loss=0.2028, pruned_loss=0.03045, over 4896.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02844, over 972482.46 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 15:39:14,552 INFO [train.py:715] (4/8) Epoch 19, batch 11600, loss[loss=0.1532, simple_loss=0.2295, pruned_loss=0.03849, over 4827.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2057, pruned_loss=0.02865, over 973226.07 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 15:39:54,373 INFO [train.py:715] (4/8) Epoch 19, batch 11650, loss[loss=0.1216, simple_loss=0.1969, pruned_loss=0.02319, over 4686.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.0287, over 972467.84 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 15:40:33,462 INFO [train.py:715] (4/8) Epoch 19, batch 11700, loss[loss=0.1243, simple_loss=0.21, pruned_loss=0.01933, over 4981.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02893, over 973042.31 frames.], batch size: 27, lr: 1.17e-04
2022-05-09 15:41:13,005 INFO [train.py:715] (4/8) Epoch 19, batch 11750, loss[loss=0.1368, simple_loss=0.2082, pruned_loss=0.03267, over 4829.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02855, over 974076.57 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 15:41:52,543 INFO [train.py:715] (4/8) Epoch 19, batch 11800, loss[loss=0.1453, simple_loss=0.2191, pruned_loss=0.03572, over 4905.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02867, over 974287.30 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 15:42:32,204 INFO [train.py:715] (4/8) Epoch 19, batch 11850, loss[loss=0.1341, simple_loss=0.1974, pruned_loss=0.03537, over 4819.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.02825, over 973532.25 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 15:43:11,795 INFO [train.py:715] (4/8) Epoch 19, batch 11900, loss[loss=0.1179, simple_loss=0.185, pruned_loss=0.02539, over 4816.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02804, over 973161.85 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 15:43:51,291 INFO [train.py:715] (4/8) Epoch 19, batch 11950, loss[loss=0.1685, simple_loss=0.2369, pruned_loss=0.05008, over 4909.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02831, over 972657.17 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 15:44:30,454 INFO [train.py:715] (4/8) Epoch 19, batch 12000, loss[loss=0.1409, simple_loss=0.2134, pruned_loss=0.03421, over 4931.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02785, over 972644.84 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 15:44:30,455 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 15:44:40,310 INFO [train.py:742] (4/8) Epoch 19, validation: loss=0.1044, simple_loss=0.1877, pruned_loss=0.01054, over 914524.00 frames.
2022-05-09 15:45:20,291 INFO [train.py:715] (4/8) Epoch 19, batch 12050, loss[loss=0.1335, simple_loss=0.2139, pruned_loss=0.02654, over 4861.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.02799, over 972782.12 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 15:46:00,178 INFO [train.py:715] (4/8) Epoch 19, batch 12100, loss[loss=0.1403, simple_loss=0.2119, pruned_loss=0.03439, over 4770.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02822, over 972715.45 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 15:46:39,302 INFO [train.py:715] (4/8) Epoch 19, batch 12150, loss[loss=0.1294, simple_loss=0.2043, pruned_loss=0.02725, over 4922.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02837, over 971733.42 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 15:47:18,768 INFO [train.py:715] (4/8) Epoch 19, batch 12200, loss[loss=0.1592, simple_loss=0.2397, pruned_loss=0.03934, over 4745.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2048, pruned_loss=0.02775, over 971808.10 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 15:47:58,231 INFO [train.py:715] (4/8) Epoch 19, batch 12250, loss[loss=0.133, simple_loss=0.2111, pruned_loss=0.02748, over 4933.00 frames.], tot_loss[loss=0.1312, simple_loss=0.206, pruned_loss=0.02819, over 971828.15 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 15:48:37,870 INFO [train.py:715] (4/8) Epoch 19, batch 12300, loss[loss=0.1485, simple_loss=0.2256, pruned_loss=0.03568, over 4934.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02798, over 971853.00 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 15:49:17,549 INFO [train.py:715] (4/8) Epoch 19, batch 12350, loss[loss=0.1327, simple_loss=0.1907, pruned_loss=0.03739, over 4960.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2053, pruned_loss=0.02781, over 972558.35 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 15:49:56,110 INFO [train.py:715] (4/8) Epoch 19, batch 12400, loss[loss=0.1291, simple_loss=0.206, pruned_loss=0.02606, over 4919.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2051, pruned_loss=0.02782, over 972719.37 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 15:50:35,579 INFO [train.py:715] (4/8) Epoch 19, batch 12450, loss[loss=0.1263, simple_loss=0.1977, pruned_loss=0.02751, over 4870.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2048, pruned_loss=0.02814, over 973530.35 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 15:51:14,298 INFO [train.py:715] (4/8) Epoch 19, batch 12500, loss[loss=0.1283, simple_loss=0.2069, pruned_loss=0.02487, over 4782.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02833, over 973532.12 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 15:51:53,638 INFO [train.py:715] (4/8) Epoch 19, batch 12550, loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.02804, over 4787.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.0285, over 972997.12 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 15:52:33,121 INFO [train.py:715] (4/8) Epoch 19, batch 12600, loss[loss=0.1652, simple_loss=0.2228, pruned_loss=0.05383, over 4870.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2053, pruned_loss=0.02843, over 972189.24 frames.], batch size: 30, lr: 1.17e-04
2022-05-09 15:53:12,606 INFO [train.py:715] (4/8) Epoch 19, batch 12650, loss[loss=0.1314, simple_loss=0.2119, pruned_loss=0.0255, over 4905.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02869, over 972180.64 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 15:53:51,559 INFO [train.py:715] (4/8) Epoch 19, batch 12700, loss[loss=0.1237, simple_loss=0.2012, pruned_loss=0.02307, over 4865.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02874, over 972561.99 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 15:54:30,745 INFO [train.py:715] (4/8) Epoch 19, batch 12750, loss[loss=0.1146, simple_loss=0.1998, pruned_loss=0.01468, over 4936.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02823, over 972129.47 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 15:55:10,390 INFO [train.py:715] (4/8) Epoch 19, batch 12800, loss[loss=0.1307, simple_loss=0.2055, pruned_loss=0.02795, over 4892.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02847, over 971196.24 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 15:55:49,791 INFO [train.py:715] (4/8) Epoch 19, batch 12850, loss[loss=0.1458, simple_loss=0.2169, pruned_loss=0.03736, over 4909.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2054, pruned_loss=0.02839, over 972078.85 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 15:56:28,727 INFO [train.py:715] (4/8) Epoch 19, batch 12900, loss[loss=0.1402, simple_loss=0.2108, pruned_loss=0.03483, over 4969.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02832, over 971940.13 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 15:57:08,290 INFO [train.py:715] (4/8) Epoch 19, batch 12950, loss[loss=0.1671, simple_loss=0.2288, pruned_loss=0.05266, over 4908.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2054, pruned_loss=0.02839, over 971871.12 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 15:57:47,533 INFO [train.py:715] (4/8) Epoch 19, batch 13000, loss[loss=0.1362, simple_loss=0.2165, pruned_loss=0.02793, over 4901.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02832, over 972825.66 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 15:58:26,679 INFO [train.py:715] (4/8) Epoch 19, batch 13050, loss[loss=0.1366, simple_loss=0.2188, pruned_loss=0.02719, over 4899.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02836, over 972086.03 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 15:59:05,573 INFO [train.py:715] (4/8) Epoch 19, batch 13100, loss[loss=0.136, simple_loss=0.2116, pruned_loss=0.03016, over 4920.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2052, pruned_loss=0.02789, over 971849.80 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 15:59:44,831 INFO [train.py:715] (4/8) Epoch 19, batch 13150, loss[loss=0.1053, simple_loss=0.1769, pruned_loss=0.01683, over 4810.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02821, over 971368.80 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 16:00:24,446 INFO [train.py:715] (4/8) Epoch 19, batch 13200, loss[loss=0.1098, simple_loss=0.1827, pruned_loss=0.01848, over 4886.00 frames.], tot_loss[loss=0.131, simple_loss=0.205, pruned_loss=0.02854, over 972049.49 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 16:01:03,677 INFO [train.py:715] (4/8) Epoch 19, batch 13250, loss[loss=0.1442, simple_loss=0.2199, pruned_loss=0.03427, over 4968.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02866, over 972182.91 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 16:01:42,978 INFO [train.py:715] (4/8) Epoch 19, batch 13300, loss[loss=0.1554, simple_loss=0.2302, pruned_loss=0.04024, over 4987.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02857, over 973003.11 frames.], batch size: 31, lr: 1.17e-04
2022-05-09 16:02:22,612 INFO [train.py:715] (4/8) Epoch 19, batch 13350, loss[loss=0.1439, simple_loss=0.21, pruned_loss=0.03889, over 4903.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02829, over 973574.63 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 16:03:01,277 INFO [train.py:715] (4/8) Epoch 19, batch 13400, loss[loss=0.1201, simple_loss=0.1912, pruned_loss=0.02451, over 4803.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2051, pruned_loss=0.02825, over 972334.24 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 16:03:40,786 INFO [train.py:715] (4/8) Epoch 19, batch 13450, loss[loss=0.1385, simple_loss=0.2218, pruned_loss=0.02764, over 4947.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02815, over 973215.61 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 16:04:20,047 INFO [train.py:715] (4/8) Epoch 19, batch 13500, loss[loss=0.1219, simple_loss=0.1929, pruned_loss=0.02549, over 4848.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02825, over 973178.89 frames.], batch size: 32, lr: 1.17e-04
2022-05-09 16:04:59,471 INFO [train.py:715] (4/8) Epoch 19, batch 13550, loss[loss=0.1023, simple_loss=0.1748, pruned_loss=0.01489, over 4847.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2052, pruned_loss=0.02786, over 973313.21 frames.], batch size: 32, lr: 1.17e-04
2022-05-09 16:05:38,404 INFO [train.py:715] (4/8) Epoch 19, batch 13600, loss[loss=0.144, simple_loss=0.2187, pruned_loss=0.03459, over 4968.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2047, pruned_loss=0.02774, over 973237.00 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 16:06:17,569 INFO [train.py:715] (4/8) Epoch 19, batch 13650, loss[loss=0.1546, simple_loss=0.2271, pruned_loss=0.04102, over 4931.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02836, over 973463.24 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 16:06:57,011 INFO [train.py:715] (4/8) Epoch 19, batch 13700, loss[loss=0.1438, simple_loss=0.2108, pruned_loss=0.03837, over 4839.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02829, over 972865.76 frames.], batch size: 30, lr: 1.17e-04
2022-05-09 16:07:35,731 INFO [train.py:715] (4/8) Epoch 19, batch 13750, loss[loss=0.1176, simple_loss=0.1969, pruned_loss=0.01917, over 4682.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2049, pruned_loss=0.02803, over 972112.76 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:08:14,998 INFO [train.py:715] (4/8) Epoch 19, batch 13800, loss[loss=0.1386, simple_loss=0.2103, pruned_loss=0.0334, over 4763.00 frames.], tot_loss[loss=0.13, simple_loss=0.2042, pruned_loss=0.0279, over 971814.06 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 16:08:55,062 INFO [train.py:715] (4/8) Epoch 19, batch 13850, loss[loss=0.1299, simple_loss=0.2042, pruned_loss=0.02779, over 4883.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2044, pruned_loss=0.02774, over 971719.25 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 16:09:34,681 INFO [train.py:715] (4/8) Epoch 19, batch 13900, loss[loss=0.1579, simple_loss=0.2274, pruned_loss=0.04424, over 4788.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.0282, over 972026.73 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 16:10:14,443 INFO [train.py:715] (4/8) Epoch 19, batch 13950, loss[loss=0.1058, simple_loss=0.185, pruned_loss=0.01331, over 4883.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02785, over 972498.74 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 16:10:53,214 INFO [train.py:715] (4/8) Epoch 19, batch 14000, loss[loss=0.1369, simple_loss=0.2071, pruned_loss=0.03333, over 4955.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02783, over 972566.52 frames.], batch size: 35, lr: 1.17e-04
2022-05-09 16:11:32,644 INFO [train.py:715] (4/8) Epoch 19, batch 14050, loss[loss=0.1334, simple_loss=0.2267, pruned_loss=0.02004, over 4792.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02806, over 973317.53 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 16:12:11,843 INFO [train.py:715] (4/8) Epoch 19, batch 14100, loss[loss=0.1455, simple_loss=0.2057, pruned_loss=0.04263, over 4889.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02882, over 973113.00 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 16:12:51,003 INFO [train.py:715] (4/8) Epoch 19, batch 14150, loss[loss=0.1249, simple_loss=0.2024, pruned_loss=0.02369, over 4764.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2072, pruned_loss=0.02874, over 972987.58 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 16:13:30,121 INFO [train.py:715] (4/8) Epoch 19, batch 14200, loss[loss=0.1211, simple_loss=0.1913, pruned_loss=0.02546, over 4854.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2067, pruned_loss=0.02904, over 973218.63 frames.], batch size: 32, lr: 1.17e-04
2022-05-09 16:14:08,936 INFO [train.py:715] (4/8) Epoch 19, batch 14250, loss[loss=0.1346, simple_loss=0.2045, pruned_loss=0.03233, over 4743.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02864, over 972690.41 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 16:14:48,114 INFO [train.py:715] (4/8) Epoch 19, batch 14300, loss[loss=0.1351, simple_loss=0.2109, pruned_loss=0.02968, over 4927.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.0288, over 972578.23 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 16:15:27,232 INFO [train.py:715] (4/8) Epoch 19, batch 14350, loss[loss=0.1179, simple_loss=0.1916, pruned_loss=0.02209, over 4872.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2058, pruned_loss=0.02857, over 973258.03 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 16:16:06,786 INFO [train.py:715] (4/8) Epoch 19, batch 14400, loss[loss=0.1199, simple_loss=0.2046, pruned_loss=0.01765, over 4808.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02831, over 973607.19 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 16:16:45,670 INFO [train.py:715] (4/8) Epoch 19, batch 14450, loss[loss=0.1461, simple_loss=0.2216, pruned_loss=0.0353, over 4947.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.0284, over 973247.50 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 16:17:24,668 INFO [train.py:715] (4/8) Epoch 19, batch 14500, loss[loss=0.1596, simple_loss=0.2285, pruned_loss=0.04536, over 4899.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.0285, over 972584.63 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 16:18:03,480 INFO [train.py:715] (4/8) Epoch 19, batch 14550, loss[loss=0.1281, simple_loss=0.2043, pruned_loss=0.02594, over 4902.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2072, pruned_loss=0.02883, over 972105.45 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 16:18:43,170 INFO [train.py:715] (4/8) Epoch 19, batch 14600, loss[loss=0.1442, simple_loss=0.2153, pruned_loss=0.03653, over 4831.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02883, over 972650.30 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:19:22,222 INFO [train.py:715] (4/8) Epoch 19, batch 14650, loss[loss=0.2016, simple_loss=0.2608, pruned_loss=0.07119, over 4753.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02884, over 972089.56 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 16:20:01,158 INFO [train.py:715] (4/8) Epoch 19, batch 14700, loss[loss=0.1195, simple_loss=0.2049, pruned_loss=0.01708, over 4792.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02867, over 971984.63 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 16:20:40,519 INFO [train.py:715] (4/8) Epoch 19, batch 14750, loss[loss=0.1375, simple_loss=0.2183, pruned_loss=0.02833, over 4859.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02887, over 971525.12 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 16:21:19,782 INFO [train.py:715] (4/8) Epoch 19, batch 14800, loss[loss=0.1324, simple_loss=0.2127, pruned_loss=0.02607, over 4937.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02914, over 972654.80 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 16:21:58,084 INFO [train.py:715] (4/8) Epoch 19, batch 14850, loss[loss=0.1347, simple_loss=0.2168, pruned_loss=0.02629, over 4696.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02843, over 971789.01 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:22:37,373 INFO [train.py:715] (4/8) Epoch 19, batch 14900, loss[loss=0.1211, simple_loss=0.1995, pruned_loss=0.02131, over 4970.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.0285, over 971729.24 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 16:23:16,321 INFO [train.py:715] (4/8) Epoch 19, batch 14950, loss[loss=0.1284, simple_loss=0.2007, pruned_loss=0.02808, over 4930.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02827, over 972862.59 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 16:23:55,095 INFO [train.py:715] (4/8) Epoch 19, batch 15000, loss[loss=0.1283, simple_loss=0.2049, pruned_loss=0.02585, over 4858.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2053, pruned_loss=0.02809, over 972316.27 frames.], batch size: 13, lr: 1.17e-04
2022-05-09 16:23:55,095 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 16:24:07,487 INFO [train.py:742] (4/8) Epoch 19, validation: loss=0.1045, simple_loss=0.1877, pruned_loss=0.01064, over 914524.00 frames.
2022-05-09 16:24:46,703 INFO [train.py:715] (4/8) Epoch 19, batch 15050, loss[loss=0.1362, simple_loss=0.203, pruned_loss=0.03473, over 4972.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2051, pruned_loss=0.02789, over 972932.20 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:25:26,174 INFO [train.py:715] (4/8) Epoch 19, batch 15100, loss[loss=0.1414, simple_loss=0.2217, pruned_loss=0.03055, over 4976.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02821, over 973026.40 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 16:26:05,808 INFO [train.py:715] (4/8) Epoch 19, batch 15150, loss[loss=0.1377, simple_loss=0.2228, pruned_loss=0.02632, over 4774.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02874, over 972813.35 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 16:26:45,269 INFO [train.py:715] (4/8) Epoch 19, batch 15200, loss[loss=0.1265, simple_loss=0.2089, pruned_loss=0.02201, over 4765.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02839, over 972513.94 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 16:27:24,248 INFO [train.py:715] (4/8) Epoch 19, batch 15250, loss[loss=0.1117, simple_loss=0.1822, pruned_loss=0.02061, over 4793.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2054, pruned_loss=0.02865, over 971635.66 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 16:28:04,172 INFO [train.py:715] (4/8) Epoch 19, batch 15300, loss[loss=0.1351, simple_loss=0.206, pruned_loss=0.03214, over 4852.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02843, over 971227.82 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 16:28:43,723 INFO [train.py:715] (4/8) Epoch 19, batch 15350, loss[loss=0.1115, simple_loss=0.1886, pruned_loss=0.01719, over 4940.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2048, pruned_loss=0.02829, over 971792.20 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 16:29:23,527 INFO [train.py:715] (4/8) Epoch 19, batch 15400, loss[loss=0.1301, simple_loss=0.1964, pruned_loss=0.03196, over 4785.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02828, over 972256.73 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:30:03,012 INFO [train.py:715] (4/8) Epoch 19, batch 15450, loss[loss=0.1338, simple_loss=0.2145, pruned_loss=0.02652, over 4972.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2048, pruned_loss=0.0277, over 972341.13 frames.], batch size: 28, lr: 1.17e-04
2022-05-09 16:30:42,450 INFO [train.py:715] (4/8) Epoch 19, batch 15500, loss[loss=0.1178, simple_loss=0.1909, pruned_loss=0.02234, over 4751.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2055, pruned_loss=0.02813, over 972243.34 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 16:31:21,337 INFO [train.py:715] (4/8) Epoch 19, batch 15550, loss[loss=0.1129, simple_loss=0.1876, pruned_loss=0.01914, over 4750.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2052, pruned_loss=0.02786, over 971877.17 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 16:32:00,421 INFO [train.py:715] (4/8) Epoch 19, batch 15600, loss[loss=0.1512, simple_loss=0.2201, pruned_loss=0.04119, over 4856.00 frames.], tot_loss[loss=0.131, simple_loss=0.2056, pruned_loss=0.02824, over 971442.43 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 16:32:40,088 INFO [train.py:715] (4/8) Epoch 19, batch 15650, loss[loss=0.1665, simple_loss=0.2376, pruned_loss=0.04769, over 4980.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02837, over 972338.55 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:33:19,038 INFO [train.py:715] (4/8) Epoch 19, batch 15700, loss[loss=0.116, simple_loss=0.1891, pruned_loss=0.02147, over 4787.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2053, pruned_loss=0.02846, over 972800.59 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 16:33:59,139 INFO [train.py:715] (4/8) Epoch 19, batch 15750, loss[loss=0.1013, simple_loss=0.1685, pruned_loss=0.01705, over 4843.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02843, over 972033.40 frames.], batch size: 13, lr: 1.17e-04
2022-05-09 16:34:38,393 INFO [train.py:715] (4/8) Epoch 19, batch 15800, loss[loss=0.1087, simple_loss=0.179, pruned_loss=0.01917, over 4836.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02829, over 972407.97 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:35:17,528 INFO [train.py:715] (4/8) Epoch 19, batch 15850, loss[loss=0.1219, simple_loss=0.1979, pruned_loss=0.02293, over 4924.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02824, over 972567.56 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 16:35:56,468 INFO [train.py:715] (4/8) Epoch 19, batch 15900, loss[loss=0.1537, simple_loss=0.2334, pruned_loss=0.03703, over 4818.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.02812, over 972165.50 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 16:36:35,616 INFO [train.py:715] (4/8) Epoch 19, batch 15950, loss[loss=0.1413, simple_loss=0.2194, pruned_loss=0.03157, over 4979.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02858, over 972168.55 frames.], batch size: 28, lr: 1.17e-04
2022-05-09 16:37:15,276 INFO [train.py:715] (4/8) Epoch 19, batch 16000, loss[loss=0.1184, simple_loss=0.1946, pruned_loss=0.02104, over 4783.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2051, pruned_loss=0.02835, over 972359.97 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 16:37:53,933 INFO [train.py:715] (4/8) Epoch 19, batch 16050, loss[loss=0.129, simple_loss=0.1967, pruned_loss=0.03068, over 4848.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02822, over 972467.62 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:38:33,244 INFO [train.py:715] (4/8) Epoch 19, batch 16100, loss[loss=0.1314, simple_loss=0.2087, pruned_loss=0.02704, over 4927.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02804, over 972301.80 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 16:39:12,546 INFO [train.py:715] (4/8) Epoch 19, batch 16150, loss[loss=0.09862, simple_loss=0.177, pruned_loss=0.01014, over 4992.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2054, pruned_loss=0.02803, over 973228.67 frames.], batch size: 28, lr: 1.17e-04
2022-05-09 16:39:51,598 INFO [train.py:715] (4/8) Epoch 19, batch 16200, loss[loss=0.1286, simple_loss=0.2026, pruned_loss=0.02731, over 4813.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02804, over 973134.62 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 16:40:29,893 INFO [train.py:715] (4/8) Epoch 19, batch 16250, loss[loss=0.128, simple_loss=0.2069, pruned_loss=0.02458, over 4808.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02823, over 972908.12 frames.], batch size: 13, lr: 1.17e-04
2022-05-09 16:41:08,935 INFO [train.py:715] (4/8) Epoch 19, batch 16300, loss[loss=0.147, simple_loss=0.2307, pruned_loss=0.03169, over 4864.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2051, pruned_loss=0.02775, over 971667.94 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 16:41:48,393 INFO [train.py:715] (4/8) Epoch 19, batch 16350, loss[loss=0.1223, simple_loss=0.1931, pruned_loss=0.02575, over 4763.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2057, pruned_loss=0.02774, over 973207.70 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 16:42:26,932 INFO [train.py:715] (4/8) Epoch 19, batch 16400, loss[loss=0.1421, simple_loss=0.2236, pruned_loss=0.03037, over 4984.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2059, pruned_loss=0.02744, over 973035.27 frames.], batch size: 28, lr: 1.17e-04
2022-05-09 16:43:05,776 INFO [train.py:715] (4/8) Epoch 19, batch 16450, loss[loss=0.1328, simple_loss=0.2061, pruned_loss=0.02979, over 4891.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2055, pruned_loss=0.0276, over 972915.58 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 16:43:44,322 INFO [train.py:715] (4/8) Epoch 19, batch 16500, loss[loss=0.1597, simple_loss=0.2234, pruned_loss=0.04797, over 4736.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2048, pruned_loss=0.02741, over 972555.06 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 16:44:23,742 INFO [train.py:715] (4/8) Epoch 19, batch 16550, loss[loss=0.1349, simple_loss=0.2106, pruned_loss=0.02965, over 4796.00 frames.], tot_loss[loss=0.131, simple_loss=0.2059, pruned_loss=0.028, over 972355.17 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 16:45:02,745 INFO [train.py:715] (4/8) Epoch 19, batch 16600, loss[loss=0.133, simple_loss=0.222, pruned_loss=0.02197, over 4742.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2047, pruned_loss=0.02769, over 971820.52 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 16:45:41,759 INFO [train.py:715] (4/8) Epoch 19, batch 16650, loss[loss=0.1484, simple_loss=0.2178, pruned_loss=0.03951, over 4921.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2054, pruned_loss=0.02786, over 972157.72 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 16:46:21,734 INFO [train.py:715] (4/8) Epoch 19, batch 16700, loss[loss=0.1649, simple_loss=0.2367, pruned_loss=0.04658, over 4644.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02843, over 971907.53 frames.], batch size: 13, lr: 1.17e-04
2022-05-09 16:47:00,841 INFO [train.py:715] (4/8) Epoch 19, batch 16750, loss[loss=0.1109, simple_loss=0.1878, pruned_loss=0.01701, over 4803.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02834, over 971784.46 frames.], batch size: 25, lr: 1.17e-04
2022-05-09 16:47:40,567 INFO [train.py:715] (4/8) Epoch 19, batch 16800, loss[loss=0.1622, simple_loss=0.2357, pruned_loss=0.04433, over 4909.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02822, over 971462.16 frames.], batch size: 40, lr: 1.17e-04
2022-05-09 16:48:19,961 INFO [train.py:715] (4/8) Epoch 19, batch 16850, loss[loss=0.1432, simple_loss=0.2137, pruned_loss=0.03633, over 4894.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02809, over 970924.62 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 16:48:59,494 INFO [train.py:715] (4/8) Epoch 19, batch 16900, loss[loss=0.1296, simple_loss=0.2125, pruned_loss=0.02338, over 4969.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2057, pruned_loss=0.02792, over 970919.10 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 16:49:38,111 INFO [train.py:715] (4/8) Epoch 19, batch 16950, loss[loss=0.1047, simple_loss=0.1769, pruned_loss=0.01621, over 4726.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02834, over 971626.82 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 16:50:17,689 INFO [train.py:715] (4/8) Epoch 19, batch 17000, loss[loss=0.2374, simple_loss=0.2627, pruned_loss=0.1061, over 4987.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2062, pruned_loss=0.02873, over 972018.37 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 16:50:57,094 INFO [train.py:715] (4/8) Epoch 19, batch 17050, loss[loss=0.121, simple_loss=0.1973, pruned_loss=0.02237, over 4918.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02892, over 972476.53 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:51:36,156 INFO [train.py:715] (4/8) Epoch 19, batch 17100, loss[loss=0.138, simple_loss=0.2181, pruned_loss=0.02889, over 4905.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02878, over 972887.72 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 16:52:15,342 INFO [train.py:715] (4/8) Epoch 19, batch 17150, loss[loss=0.1329, simple_loss=0.2102, pruned_loss=0.02775, over 4963.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02902, over 973562.13 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:52:54,352 INFO [train.py:715] (4/8) Epoch 19, batch 17200, loss[loss=0.1125, simple_loss=0.1925, pruned_loss=0.01628, over 4908.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2062, pruned_loss=0.02902, over 973945.29 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 16:53:33,090 INFO [train.py:715] (4/8) Epoch 19, batch 17250, loss[loss=0.1264, simple_loss=0.2078, pruned_loss=0.02248, over 4882.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02874, over 973148.32 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 16:54:12,078 INFO [train.py:715] (4/8) Epoch 19, batch 17300, loss[loss=0.1216, simple_loss=0.193, pruned_loss=0.0251, over 4986.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02901, over 973406.71 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 16:54:51,730 INFO [train.py:715] (4/8) Epoch 19, batch 17350, loss[loss=0.1047, simple_loss=0.177, pruned_loss=0.01619, over 4819.00 frames.], tot_loss[loss=0.131, simple_loss=0.2055, pruned_loss=0.02828, over 973701.69 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 16:55:31,272 INFO [train.py:715] (4/8) Epoch 19, batch 17400, loss[loss=0.1503, simple_loss=0.2148, pruned_loss=0.04295, over 4809.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02884, over 973624.07 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 16:56:10,523 INFO [train.py:715] (4/8) Epoch 19, batch 17450, loss[loss=0.1222, simple_loss=0.1891, pruned_loss=0.02768, over 4921.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2058, pruned_loss=0.02833, over 973826.34 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 16:56:49,868 INFO [train.py:715] (4/8) Epoch 19, batch 17500, loss[loss=0.1491, simple_loss=0.2209, pruned_loss=0.03869, over 4979.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02854, over 972931.44 frames.], batch size: 31, lr: 1.17e-04
2022-05-09 16:57:29,146 INFO [train.py:715] (4/8) Epoch 19, batch 17550, loss[loss=0.1676, simple_loss=0.2484, pruned_loss=0.04334, over 4694.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2058, pruned_loss=0.02841, over 973161.87 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:58:08,755 INFO [train.py:715] (4/8) Epoch 19, batch 17600, loss[loss=0.1067, simple_loss=0.1793, pruned_loss=0.01698, over 4915.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2052, pruned_loss=0.02809, over 973041.99 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 16:58:47,928 INFO [train.py:715] (4/8) Epoch 19, batch 17650, loss[loss=0.1193, simple_loss=0.1809, pruned_loss=0.02889, over 4705.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02831, over 972229.99 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 16:59:27,081 INFO [train.py:715] (4/8) Epoch 19, batch 17700, loss[loss=0.1079, simple_loss=0.178, pruned_loss=0.01895, over 4773.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2048, pruned_loss=0.02815, over 972197.29 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 17:00:06,646 INFO [train.py:715] (4/8) Epoch 19, batch 17750, loss[loss=0.1456, simple_loss=0.2121, pruned_loss=0.03948, over 4744.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2043, pruned_loss=0.02815, over 971609.73 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 17:00:45,237 INFO [train.py:715] (4/8) Epoch 19, batch 17800, loss[loss=0.1421, simple_loss=0.2081, pruned_loss=0.03798, over 4828.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2052, pruned_loss=0.02835, over 972191.57 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:01:24,010 INFO [train.py:715] (4/8) Epoch 19, batch 17850, loss[loss=0.1315, simple_loss=0.2024, pruned_loss=0.03025, over 4824.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2053, pruned_loss=0.02851, over 972609.36 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:02:03,485 INFO [train.py:715] (4/8) Epoch 19, batch 17900, loss[loss=0.1339, simple_loss=0.2135, pruned_loss=0.02716, over 4933.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2056, pruned_loss=0.02857, over 972982.80 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 17:02:41,971 INFO [train.py:715] (4/8) Epoch 19, batch 17950, loss[loss=0.1383, simple_loss=0.2194, pruned_loss=0.02867, over 4880.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02832, over 973433.61 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 17:03:21,255 INFO [train.py:715] (4/8) Epoch 19, batch 18000, loss[loss=0.1004, simple_loss=0.1758, pruned_loss=0.01252, over 4815.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02822, over 973437.58 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 17:03:21,256 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 17:03:31,127 INFO [train.py:742] (4/8) Epoch 19, validation: loss=0.1046, simple_loss=0.1877, pruned_loss=0.01074, over 914524.00 frames.
2022-05-09 17:04:10,639 INFO [train.py:715] (4/8) Epoch 19, batch 18050, loss[loss=0.1218, simple_loss=0.1994, pruned_loss=0.02207, over 4949.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2047, pruned_loss=0.02781, over 973678.57 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 17:04:50,208 INFO [train.py:715] (4/8) Epoch 19, batch 18100, loss[loss=0.1603, simple_loss=0.2429, pruned_loss=0.03884, over 4805.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2045, pruned_loss=0.02792, over 972932.73 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 17:05:30,065 INFO [train.py:715] (4/8) Epoch 19, batch 18150, loss[loss=0.1383, simple_loss=0.2152, pruned_loss=0.03064, over 4932.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2043, pruned_loss=0.02802, over 973455.20 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 17:06:09,191 INFO [train.py:715] (4/8) Epoch 19, batch 18200, loss[loss=0.1488, simple_loss=0.2248, pruned_loss=0.03641, over 4838.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2046, pruned_loss=0.0279, over 973729.57 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:06:48,114 INFO [train.py:715] (4/8) Epoch 19, batch 18250, loss[loss=0.1357, simple_loss=0.209, pruned_loss=0.03119, over 4766.00 frames.], tot_loss[loss=0.1307, simple_loss=0.205, pruned_loss=0.02816, over 973451.97 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 17:07:28,076 INFO [train.py:715] (4/8) Epoch 19, batch 18300, loss[loss=0.1116, simple_loss=0.1876, pruned_loss=0.0178, over 4973.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2051, pruned_loss=0.02787, over 973852.05 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 17:08:07,531 INFO [train.py:715] (4/8) Epoch 19, batch 18350, loss[loss=0.137, simple_loss=0.2088, pruned_loss=0.03258, over 4766.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.028, over 973118.12 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 17:08:47,418 INFO [train.py:715] (4/8) Epoch 19, batch 18400, loss[loss=0.1357, simple_loss=0.2095, pruned_loss=0.0309, over 4892.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02904, over 973467.65 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 17:09:26,676 INFO [train.py:715] (4/8) Epoch 19, batch 18450, loss[loss=0.1681, simple_loss=0.2411, pruned_loss=0.04757, over 4721.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2075, pruned_loss=0.029, over 972813.26 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:10:06,113 INFO [train.py:715] (4/8) Epoch 19, batch 18500, loss[loss=0.1199, simple_loss=0.1935, pruned_loss=0.02311, over 4793.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.02878, over 972605.38 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 17:10:45,348 INFO [train.py:715] (4/8) Epoch 19, batch 18550, loss[loss=0.1302, simple_loss=0.2063, pruned_loss=0.02703, over 4868.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2071, pruned_loss=0.02853, over 973102.91 frames.], batch size: 30, lr: 1.17e-04
2022-05-09 17:11:24,400 INFO [train.py:715] (4/8) Epoch 19, batch 18600, loss[loss=0.1141, simple_loss=0.1907, pruned_loss=0.01871, over 4812.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02865, over 973832.61 frames.], batch size: 13, lr: 1.17e-04
2022-05-09 17:12:06,306 INFO [train.py:715] (4/8) Epoch 19, batch 18650, loss[loss=0.0963, simple_loss=0.1615, pruned_loss=0.01555, over 4843.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02835, over 975007.82 frames.], batch size: 13, lr: 1.17e-04
2022-05-09 17:12:45,149 INFO [train.py:715] (4/8) Epoch 19, batch 18700, loss[loss=0.1298, simple_loss=0.2106, pruned_loss=0.02452, over 4783.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02863, over 973463.29 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 17:13:24,439 INFO [train.py:715] (4/8) Epoch 19, batch 18750, loss[loss=0.1135, simple_loss=0.1864, pruned_loss=0.02028, over 4981.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2055, pruned_loss=0.02855, over 972407.88 frames.], batch size: 28, lr: 1.17e-04
2022-05-09 17:14:04,383 INFO [train.py:715] (4/8) Epoch 19, batch 18800, loss[loss=0.1275, simple_loss=0.2053, pruned_loss=0.02483, over 4933.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2061, pruned_loss=0.02863, over 972434.24 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 17:14:44,266 INFO [train.py:715] (4/8) Epoch 19, batch 18850, loss[loss=0.1324, simple_loss=0.2186, pruned_loss=0.02305, over 4821.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02861, over 972067.96 frames.], batch size: 27, lr: 1.17e-04
2022-05-09 17:15:23,448 INFO [train.py:715] (4/8) Epoch 19, batch 18900, loss[loss=0.1444, simple_loss=0.2151, pruned_loss=0.03682, over 4850.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02905, over 972028.65 frames.], batch size: 32, lr: 1.17e-04
2022-05-09 17:16:02,833 INFO [train.py:715] (4/8) Epoch 19, batch 18950, loss[loss=0.1292, simple_loss=0.1919, pruned_loss=0.03324, over 4919.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02911, over 972181.94 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 17:16:42,870 INFO [train.py:715] (4/8) Epoch 19, batch 19000, loss[loss=0.1365, simple_loss=0.2055, pruned_loss=0.03371, over 4761.00 frames.], tot_loss[loss=0.133, simple_loss=0.2071, pruned_loss=0.02948, over 971696.10 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 17:17:22,370 INFO [train.py:715] (4/8) Epoch 19, batch 19050, loss[loss=0.1232, simple_loss=0.1947, pruned_loss=0.02586, over 4775.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2065, pruned_loss=0.02929, over 972201.45 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 17:18:01,435 INFO [train.py:715] (4/8) Epoch 19, batch 19100, loss[loss=0.1214, simple_loss=0.1898, pruned_loss=0.0265, over 4964.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2065, pruned_loss=0.02894, over 972182.17 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 17:18:41,050 INFO [train.py:715] (4/8) Epoch 19, batch 19150, loss[loss=0.1318, simple_loss=0.2094, pruned_loss=0.02713, over 4766.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2066, pruned_loss=0.02909, over 971943.62 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 17:19:20,393 INFO [train.py:715] (4/8) Epoch 19, batch 19200, loss[loss=0.1319, simple_loss=0.2053, pruned_loss=0.0292, over 4858.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2064, pruned_loss=0.02897, over 972272.50 frames.], batch size: 30, lr: 1.17e-04
2022-05-09 17:19:59,878 INFO [train.py:715] (4/8) Epoch 19, batch 19250, loss[loss=0.1556, simple_loss=0.2329, pruned_loss=0.03908, over 4929.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2067, pruned_loss=0.02918, over 972390.68 frames.], batch size: 29, lr: 1.17e-04
2022-05-09 17:20:39,161 INFO [train.py:715] (4/8) Epoch 19, batch 19300, loss[loss=0.1276, simple_loss=0.2137, pruned_loss=0.02079, over 4888.00 frames.], tot_loss[loss=0.133, simple_loss=0.2073, pruned_loss=0.02935, over 972887.41 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 17:21:19,525 INFO [train.py:715] (4/8) Epoch 19, batch 19350, loss[loss=0.1156, simple_loss=0.1915, pruned_loss=0.01985, over 4792.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02902, over 972864.87 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 17:21:58,942 INFO [train.py:715] (4/8) Epoch 19, batch 19400, loss[loss=0.1428, simple_loss=0.2265, pruned_loss=0.02952, over 4872.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02883, over 972516.43 frames.], batch size: 32, lr: 1.17e-04
2022-05-09 17:22:38,648 INFO [train.py:715] (4/8) Epoch 19, batch 19450, loss[loss=0.13, simple_loss=0.1998, pruned_loss=0.0301, over 4853.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02857, over 971928.54 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 17:23:18,394 INFO [train.py:715] (4/8) Epoch 19, batch 19500, loss[loss=0.1247, simple_loss=0.1987, pruned_loss=0.02536, over 4782.00 frames.], tot_loss[loss=0.1324, simple_loss=0.207, pruned_loss=0.0289, over 971803.46 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 17:23:57,781 INFO [train.py:715] (4/8) Epoch 19, batch 19550, loss[loss=0.1367, simple_loss=0.2075, pruned_loss=0.03296, over 4752.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02874, over 971175.53 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 17:24:36,950 INFO [train.py:715] (4/8) Epoch 19, batch 19600, loss[loss=0.116, simple_loss=0.2032, pruned_loss=0.01439, over 4889.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02851, over 971204.66 frames.], batch size: 22, lr: 1.17e-04
2022-05-09 17:25:17,640 INFO [train.py:715] (4/8) Epoch 19, batch 19650, loss[loss=0.1139, simple_loss=0.1871, pruned_loss=0.02038, over 4835.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.0285, over 971229.83 frames.], batch size: 13, lr: 1.17e-04
2022-05-09 17:25:56,966 INFO [train.py:715] (4/8) Epoch 19, batch 19700, loss[loss=0.118, simple_loss=0.1846, pruned_loss=0.02571, over 4699.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.02883, over 970609.42 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:26:35,805 INFO [train.py:715] (4/8) Epoch 19, batch 19750, loss[loss=0.131, simple_loss=0.2067, pruned_loss=0.02763, over 4883.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.02918, over 971684.47 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 17:27:16,060 INFO [train.py:715] (4/8) Epoch 19, batch 19800, loss[loss=0.169, simple_loss=0.2352, pruned_loss=0.05146, over 4960.00 frames.], tot_loss[loss=0.1337, simple_loss=0.2083, pruned_loss=0.02952, over 972335.05 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:27:55,917 INFO [train.py:715] (4/8) Epoch 19, batch 19850, loss[loss=0.1119, simple_loss=0.1938, pruned_loss=0.01502, over 4992.00 frames.], tot_loss[loss=0.1336, simple_loss=0.2081, pruned_loss=0.02949, over 972073.70 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 17:28:35,199 INFO [train.py:715] (4/8) Epoch 19, batch 19900, loss[loss=0.1064, simple_loss=0.1783, pruned_loss=0.01723, over 4816.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02915, over 972577.45 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 17:29:13,881 INFO [train.py:715] (4/8) Epoch 19, batch 19950, loss[loss=0.1412, simple_loss=0.2174, pruned_loss=0.03247, over 4813.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2072, pruned_loss=0.0289, over 972646.63 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:29:53,614 INFO [train.py:715] (4/8) Epoch 19, batch 20000, loss[loss=0.1392, simple_loss=0.2077, pruned_loss=0.03537, over 4846.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02909, over 972572.92 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:30:33,006 INFO [train.py:715] (4/8) Epoch 19, batch 20050, loss[loss=0.1134, simple_loss=0.1854, pruned_loss=0.02074, over 4840.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2059, pruned_loss=0.02853, over 972534.64 frames.], batch size: 12, lr: 1.17e-04
2022-05-09 17:31:12,644 INFO [train.py:715] (4/8) Epoch 19, batch 20100, loss[loss=0.09818, simple_loss=0.1675, pruned_loss=0.01442, over 4797.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02851, over 972759.15 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 17:31:52,173 INFO [train.py:715] (4/8) Epoch 19, batch 20150, loss[loss=0.1379, simple_loss=0.2128, pruned_loss=0.03148, over 4794.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02856, over 971975.38 frames.], batch size: 24, lr: 1.17e-04
2022-05-09 17:32:31,825 INFO [train.py:715] (4/8) Epoch 19, batch 20200, loss[loss=0.1291, simple_loss=0.2013, pruned_loss=0.02843, over 4794.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2047, pruned_loss=0.02829, over 971855.14 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 17:33:11,345 INFO [train.py:715] (4/8) Epoch 19, batch 20250, loss[loss=0.1179, simple_loss=0.192, pruned_loss=0.02188, over 4932.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2042, pruned_loss=0.02778, over 972497.98 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 17:33:50,680 INFO [train.py:715] (4/8) Epoch 19, batch 20300, loss[loss=0.1426, simple_loss=0.2123, pruned_loss=0.03642, over 4958.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2048, pruned_loss=0.02817, over 971763.72 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 17:34:30,220 INFO [train.py:715] (4/8) Epoch 19, batch 20350, loss[loss=0.09895, simple_loss=0.1799, pruned_loss=0.008996, over 4856.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2048, pruned_loss=0.02849, over 971726.96 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 17:35:09,434 INFO [train.py:715] (4/8) Epoch 19, batch 20400, loss[loss=0.1199, simple_loss=0.1997, pruned_loss=0.02011, over 4775.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2049, pruned_loss=0.02811, over 972305.44 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 17:35:48,299 INFO [train.py:715] (4/8) Epoch 19, batch 20450, loss[loss=0.1626, simple_loss=0.246, pruned_loss=0.03959, over 4890.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02826, over 971104.21 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 17:36:28,040 INFO [train.py:715] (4/8) Epoch 19, batch 20500, loss[loss=0.1252, simple_loss=0.206, pruned_loss=0.02224, over 4817.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2048, pruned_loss=0.02798, over 972436.19 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:37:07,743 INFO [train.py:715] (4/8) Epoch 19, batch 20550, loss[loss=0.1253, simple_loss=0.2041, pruned_loss=0.02324, over 4953.00 frames.], tot_loss[loss=0.13, simple_loss=0.2044, pruned_loss=0.02778, over 972560.29 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 17:37:46,562 INFO [train.py:715] (4/8) Epoch 19, batch 20600, loss[loss=0.157, simple_loss=0.2242, pruned_loss=0.04491, over 4865.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2055, pruned_loss=0.02793, over 972627.11 frames.], batch size: 30, lr: 1.17e-04
2022-05-09 17:38:26,013 INFO [train.py:715] (4/8) Epoch 19, batch 20650, loss[loss=0.1148, simple_loss=0.1825, pruned_loss=0.02351, over 4902.00 frames.], tot_loss[loss=0.131, simple_loss=0.2059, pruned_loss=0.02801, over 973562.73 frames.], batch size: 18, lr: 1.17e-04
2022-05-09 17:39:05,346 INFO [train.py:715] (4/8) Epoch 19, batch 20700, loss[loss=0.1666, simple_loss=0.2382, pruned_loss=0.04748, over 4856.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02808, over 974332.78 frames.], batch size: 32, lr: 1.17e-04
2022-05-09 17:39:44,824 INFO [train.py:715] (4/8) Epoch 19, batch 20750, loss[loss=0.1172, simple_loss=0.1862, pruned_loss=0.02406, over 4892.00 frames.], tot_loss[loss=0.131, simple_loss=0.2059, pruned_loss=0.02803, over 973169.48 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 17:40:23,537 INFO [train.py:715] (4/8) Epoch 19, batch 20800, loss[loss=0.1438, simple_loss=0.2208, pruned_loss=0.03341, over 4973.00 frames.], tot_loss[loss=0.1313, simple_loss=0.206, pruned_loss=0.02827, over 972442.25 frames.], batch size: 39, lr: 1.17e-04
2022-05-09 17:41:02,812 INFO [train.py:715] (4/8) Epoch 19, batch 20850, loss[loss=0.1133, simple_loss=0.1884, pruned_loss=0.01906, over 4754.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2054, pruned_loss=0.02777, over 972513.97 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 17:41:42,482 INFO [train.py:715] (4/8) Epoch 19, batch 20900, loss[loss=0.1359, simple_loss=0.2172, pruned_loss=0.02727, over 4932.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2059, pruned_loss=0.02779, over 972103.90 frames.], batch size: 23, lr: 1.17e-04
2022-05-09 17:42:21,287 INFO [train.py:715] (4/8) Epoch 19, batch 20950, loss[loss=0.1428, simple_loss=0.2172, pruned_loss=0.03416, over 4860.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2061, pruned_loss=0.02803, over 972998.53 frames.], batch size: 32, lr: 1.17e-04
2022-05-09 17:43:01,039 INFO [train.py:715] (4/8) Epoch 19, batch 21000, loss[loss=0.1287, simple_loss=0.2126, pruned_loss=0.02242, over 4937.00 frames.], tot_loss[loss=0.1308, simple_loss=0.206, pruned_loss=0.02782, over 973195.11 frames.], batch size: 21, lr: 1.17e-04
2022-05-09 17:43:01,040 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 17:43:11,504 INFO [train.py:742] (4/8) Epoch 19, validation: loss=0.1045, simple_loss=0.1878, pruned_loss=0.01062, over 914524.00 frames.
2022-05-09 17:43:51,340 INFO [train.py:715] (4/8) Epoch 19, batch 21050, loss[loss=0.1551, simple_loss=0.2219, pruned_loss=0.04412, over 4837.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02845, over 973252.62 frames.], batch size: 32, lr: 1.17e-04
2022-05-09 17:44:31,302 INFO [train.py:715] (4/8) Epoch 19, batch 21100, loss[loss=0.1326, simple_loss=0.2066, pruned_loss=0.02934, over 4897.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02805, over 972135.04 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 17:45:10,124 INFO [train.py:715] (4/8) Epoch 19, batch 21150, loss[loss=0.1514, simple_loss=0.2212, pruned_loss=0.04082, over 4965.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02802, over 972554.94 frames.], batch size: 14, lr: 1.17e-04
2022-05-09 17:45:49,701 INFO [train.py:715] (4/8) Epoch 19, batch 21200, loss[loss=0.1288, simple_loss=0.1994, pruned_loss=0.02913, over 4985.00 frames.], tot_loss[loss=0.131, simple_loss=0.206, pruned_loss=0.02801, over 972834.64 frames.], batch size: 28, lr: 1.17e-04
2022-05-09 17:46:28,950 INFO [train.py:715] (4/8) Epoch 19, batch 21250, loss[loss=0.1134, simple_loss=0.1935, pruned_loss=0.01668, over 4824.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2058, pruned_loss=0.02798, over 973603.24 frames.], batch size: 15, lr: 1.17e-04
2022-05-09 17:47:07,995 INFO [train.py:715] (4/8) Epoch 19, batch 21300, loss[loss=0.1097, simple_loss=0.1917, pruned_loss=0.01382, over 4898.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2051, pruned_loss=0.02757, over 972722.17 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 17:47:46,810 INFO [train.py:715] (4/8) Epoch 19, batch 21350, loss[loss=0.1434, simple_loss=0.2217, pruned_loss=0.03257, over 4772.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.0283, over 972236.51 frames.], batch size: 17, lr: 1.17e-04
2022-05-09 17:48:26,360 INFO [train.py:715] (4/8) Epoch 19, batch 21400, loss[loss=0.128, simple_loss=0.2138, pruned_loss=0.0211, over 4817.00 frames.], tot_loss[loss=0.1312, simple_loss=0.206, pruned_loss=0.02818, over 972626.65 frames.], batch size: 26, lr: 1.17e-04
2022-05-09 17:49:05,854 INFO [train.py:715] (4/8) Epoch 19, batch 21450, loss[loss=0.118, simple_loss=0.1934, pruned_loss=0.02132, over 4822.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02829, over 973211.49 frames.], batch size: 27, lr: 1.17e-04
2022-05-09 17:49:44,648 INFO [train.py:715] (4/8) Epoch 19, batch 21500, loss[loss=0.1301, simple_loss=0.2105, pruned_loss=0.02483, over 4861.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2062, pruned_loss=0.02832, over 972230.70 frames.], batch size: 16, lr: 1.17e-04
2022-05-09 17:50:24,358 INFO [train.py:715] (4/8) Epoch 19, batch 21550, loss[loss=0.1219, simple_loss=0.1943, pruned_loss=0.02477, over 4770.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2053, pruned_loss=0.02821, over 972044.22 frames.], batch size: 19, lr: 1.17e-04
2022-05-09 17:51:04,079 INFO [train.py:715] (4/8) Epoch 19, batch 21600, loss[loss=0.1389, simple_loss=0.224, pruned_loss=0.02691, over 4871.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02839, over 971430.50 frames.], batch size: 20, lr: 1.17e-04
2022-05-09 17:51:43,838 INFO [train.py:715] (4/8) Epoch 19, batch 21650, loss[loss=0.1106, simple_loss=0.1877, pruned_loss=0.01677, over 4785.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02831, over 971476.34 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 17:52:22,732 INFO [train.py:715] (4/8) Epoch 19, batch 21700, loss[loss=0.1174, simple_loss=0.1962, pruned_loss=0.01935, over 4899.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02876, over 972226.17 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 17:53:02,146 INFO [train.py:715] (4/8) Epoch 19, batch 21750, loss[loss=0.1543, simple_loss=0.2243, pruned_loss=0.04217, over 4780.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02839, over 971684.87 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 17:53:43,112 INFO [train.py:715] (4/8) Epoch 19, batch 21800, loss[loss=0.1195, simple_loss=0.1961, pruned_loss=0.02145, over 4900.00 frames.], tot_loss[loss=0.131, simple_loss=0.2053, pruned_loss=0.02835, over 971411.37 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 17:54:22,936 INFO [train.py:715] (4/8) Epoch 19, batch 21850, loss[loss=0.1679, simple_loss=0.2227, pruned_loss=0.05655, over 4968.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02864, over 972267.51 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 17:55:03,315 INFO [train.py:715] (4/8) Epoch 19, batch 21900, loss[loss=0.09809, simple_loss=0.1713, pruned_loss=0.01244, over 4817.00 frames.], tot_loss[loss=0.1316, simple_loss=0.206, pruned_loss=0.02865, over 972348.49 frames.], batch size: 26, lr: 1.16e-04
2022-05-09 17:55:43,306 INFO [train.py:715] (4/8) Epoch 19, batch 21950, loss[loss=0.1798, simple_loss=0.2371, pruned_loss=0.06123, over 4759.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02879, over 972211.40 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 17:56:22,525 INFO [train.py:715] (4/8) Epoch 19, batch 22000, loss[loss=0.1314, simple_loss=0.2016, pruned_loss=0.03063, over 4928.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02847, over 972577.84 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 17:57:01,818 INFO [train.py:715] (4/8) Epoch 19, batch 22050, loss[loss=0.1327, simple_loss=0.205, pruned_loss=0.0302, over 4816.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02872, over 972666.48 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 17:57:41,390 INFO [train.py:715] (4/8) Epoch 19, batch 22100, loss[loss=0.1428, simple_loss=0.2246, pruned_loss=0.03047, over 4844.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2066, pruned_loss=0.02922, over 972414.31 frames.], batch size: 26, lr: 1.16e-04
2022-05-09 17:58:21,390 INFO [train.py:715] (4/8) Epoch 19, batch 22150, loss[loss=0.14, simple_loss=0.2137, pruned_loss=0.0332, over 4928.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02892, over 972054.33 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 17:59:00,690 INFO [train.py:715] (4/8) Epoch 19, batch 22200, loss[loss=0.1657, simple_loss=0.2355, pruned_loss=0.04788, over 4802.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2066, pruned_loss=0.02878, over 971131.64 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 17:59:40,597 INFO [train.py:715] (4/8) Epoch 19, batch 22250, loss[loss=0.1198, simple_loss=0.2017, pruned_loss=0.01894, over 4823.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02866, over 971665.91 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 18:00:20,342 INFO [train.py:715] (4/8) Epoch 19, batch 22300, loss[loss=0.109, simple_loss=0.1761, pruned_loss=0.02099, over 4962.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2061, pruned_loss=0.02831, over 971947.07 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:00:59,303 INFO [train.py:715] (4/8) Epoch 19, batch 22350, loss[loss=0.138, simple_loss=0.2054, pruned_loss=0.03528, over 4867.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2056, pruned_loss=0.02792, over 971583.29 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 18:01:38,320 INFO [train.py:715] (4/8) Epoch 19, batch 22400, loss[loss=0.1146, simple_loss=0.195, pruned_loss=0.01706, over 4807.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2048, pruned_loss=0.02737, over 972049.09 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 18:02:17,606 INFO [train.py:715] (4/8) Epoch 19, batch 22450, loss[loss=0.1397, simple_loss=0.2174, pruned_loss=0.03101, over 4933.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2055, pruned_loss=0.0277, over 972697.74 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 18:02:57,545 INFO [train.py:715] (4/8) Epoch 19, batch 22500, loss[loss=0.1436, simple_loss=0.2113, pruned_loss=0.0379, over 4920.00 frames.], tot_loss[loss=0.1309, simple_loss=0.206, pruned_loss=0.0279, over 973210.32 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 18:03:36,399 INFO [train.py:715] (4/8) Epoch 19, batch 22550, loss[loss=0.1271, simple_loss=0.204, pruned_loss=0.02513, over 4766.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2065, pruned_loss=0.02829, over 972928.41 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 18:04:16,058 INFO [train.py:715] (4/8) Epoch 19, batch 22600, loss[loss=0.1392, simple_loss=0.2091, pruned_loss=0.03463, over 4754.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.02879, over 972484.58 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 18:04:55,710 INFO [train.py:715] (4/8) Epoch 19, batch 22650, loss[loss=0.124, simple_loss=0.2002, pruned_loss=0.02394, over 4696.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2076, pruned_loss=0.02904, over 971508.35 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:05:34,681 INFO [train.py:715] (4/8) Epoch 19, batch 22700, loss[loss=0.1248, simple_loss=0.1986, pruned_loss=0.02552, over 4807.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2076, pruned_loss=0.02879, over 971619.65 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 18:06:13,667 INFO [train.py:715] (4/8) Epoch 19, batch 22750, loss[loss=0.1373, simple_loss=0.2117, pruned_loss=0.03147, over 4859.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2072, pruned_loss=0.02862, over 971526.36 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 18:06:53,392 INFO [train.py:715] (4/8) Epoch 19, batch 22800, loss[loss=0.1209, simple_loss=0.1969, pruned_loss=0.02241, over 4937.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2074, pruned_loss=0.02875, over 971472.11 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 18:07:33,729 INFO [train.py:715] (4/8) Epoch 19, batch 22850, loss[loss=0.1283, simple_loss=0.2097, pruned_loss=0.02349, over 4910.00 frames.], tot_loss[loss=0.132, simple_loss=0.2069, pruned_loss=0.02853, over 972025.16 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 18:08:11,748 INFO [train.py:715] (4/8) Epoch 19, batch 22900, loss[loss=0.1418, simple_loss=0.2214, pruned_loss=0.03117, over 4638.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2074, pruned_loss=0.02879, over 971307.31 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 18:08:51,143 INFO [train.py:715] (4/8) Epoch 19, batch 22950, loss[loss=0.1161, simple_loss=0.189, pruned_loss=0.02156, over 4780.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02859, over 972020.08 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 18:09:31,739 INFO [train.py:715] (4/8) Epoch 19, batch 23000, loss[loss=0.1197, simple_loss=0.1988, pruned_loss=0.02032, over 4885.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02873, over 971782.50 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 18:10:12,236 INFO [train.py:715] (4/8) Epoch 19, batch 23050, loss[loss=0.1116, simple_loss=0.1923, pruned_loss=0.01542, over 4815.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02868, over 971908.06 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 18:10:52,452 INFO [train.py:715] (4/8) Epoch 19, batch 23100, loss[loss=0.1323, simple_loss=0.1989, pruned_loss=0.03287, over 4982.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02872, over 972094.23 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:11:33,189 INFO [train.py:715] (4/8) Epoch 19, batch 23150, loss[loss=0.1327, simple_loss=0.2024, pruned_loss=0.03153, over 4751.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2069, pruned_loss=0.02889, over 971669.04 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 18:12:14,186 INFO [train.py:715] (4/8) Epoch 19, batch 23200, loss[loss=0.1169, simple_loss=0.1827, pruned_loss=0.02552, over 4778.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2071, pruned_loss=0.02896, over 971272.74 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:12:53,604 INFO [train.py:715] (4/8) Epoch 19, batch 23250, loss[loss=0.1304, simple_loss=0.1975, pruned_loss=0.03166, over 4973.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2068, pruned_loss=0.02901, over 970995.67 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:13:34,369 INFO [train.py:715] (4/8) Epoch 19, batch 23300, loss[loss=0.1346, simple_loss=0.2079, pruned_loss=0.03064, over 4931.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2072, pruned_loss=0.02907, over 971955.89 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 18:14:16,091 INFO [train.py:715] (4/8) Epoch 19, batch 23350, loss[loss=0.1452, simple_loss=0.2287, pruned_loss=0.03081, over 4888.00 frames.], tot_loss[loss=0.1336, simple_loss=0.208, pruned_loss=0.02963, over 972439.61 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 18:14:56,721 INFO [train.py:715] (4/8) Epoch 19, batch 23400, loss[loss=0.1164, simple_loss=0.1968, pruned_loss=0.018, over 4972.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2074, pruned_loss=0.02912, over 972637.38 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 18:15:37,874 INFO [train.py:715] (4/8) Epoch 19, batch 23450, loss[loss=0.1336, simple_loss=0.2219, pruned_loss=0.02265, over 4791.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.0287, over 972933.28 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 18:16:19,146 INFO [train.py:715] (4/8) Epoch 19, batch 23500, loss[loss=0.1566, simple_loss=0.2241, pruned_loss=0.04458, over 4835.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02876, over 972957.77 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:17:00,521 INFO [train.py:715] (4/8) Epoch 19, batch 23550, loss[loss=0.1352, simple_loss=0.2109, pruned_loss=0.02974, over 4799.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.0286, over 971745.25 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:17:41,327 INFO [train.py:715] (4/8) Epoch 19, batch 23600, loss[loss=0.1256, simple_loss=0.1976, pruned_loss=0.02674, over 4982.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02899, over 971923.82 frames.], batch size: 28, lr: 1.16e-04
2022-05-09 18:18:22,143 INFO [train.py:715] (4/8) Epoch 19, batch 23650, loss[loss=0.1248, simple_loss=0.183, pruned_loss=0.03334, over 4833.00 frames.], tot_loss[loss=0.1329, simple_loss=0.2072, pruned_loss=0.02934, over 972442.03 frames.], batch size: 30, lr: 1.16e-04
2022-05-09 18:19:04,120 INFO [train.py:715] (4/8) Epoch 19, batch 23700, loss[loss=0.1368, simple_loss=0.2154, pruned_loss=0.02917, over 4818.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2065, pruned_loss=0.02909, over 972195.54 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 18:19:44,518 INFO [train.py:715] (4/8) Epoch 19, batch 23750, loss[loss=0.1176, simple_loss=0.1962, pruned_loss=0.01946, over 4810.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02831, over 972727.98 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 18:20:24,714 INFO [train.py:715] (4/8) Epoch 19, batch 23800, loss[loss=0.1142, simple_loss=0.1786, pruned_loss=0.0249, over 4881.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2063, pruned_loss=0.02889, over 972533.33 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 18:21:05,133 INFO [train.py:715] (4/8) Epoch 19, batch 23850, loss[loss=0.1349, simple_loss=0.2034, pruned_loss=0.03321, over 4941.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02872, over 972606.74 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 18:21:45,584 INFO [train.py:715] (4/8) Epoch 19, batch 23900, loss[loss=0.1112, simple_loss=0.1899, pruned_loss=0.01623, over 4906.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02879, over 972979.73 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 18:22:24,878 INFO [train.py:715] (4/8) Epoch 19, batch 23950, loss[loss=0.1092, simple_loss=0.1843, pruned_loss=0.01701, over 4958.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.0282, over 972727.12 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 18:23:05,244 INFO [train.py:715] (4/8) Epoch 19, batch 24000, loss[loss=0.1833, simple_loss=0.2461, pruned_loss=0.06027, over 4763.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2064, pruned_loss=0.02846, over 972409.82 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:23:05,245 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 18:23:15,156 INFO [train.py:742] (4/8) Epoch 19, validation: loss=0.1046, simple_loss=0.1878, pruned_loss=0.01073, over 914524.00 frames.
2022-05-09 18:23:55,481 INFO [train.py:715] (4/8) Epoch 19, batch 24050, loss[loss=0.1163, simple_loss=0.1763, pruned_loss=0.02813, over 4975.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02872, over 973000.95 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:24:36,268 INFO [train.py:715] (4/8) Epoch 19, batch 24100, loss[loss=0.1265, simple_loss=0.1976, pruned_loss=0.02766, over 4984.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02888, over 973413.94 frames.], batch size: 33, lr: 1.16e-04
2022-05-09 18:25:16,107 INFO [train.py:715] (4/8) Epoch 19, batch 24150, loss[loss=0.1282, simple_loss=0.2074, pruned_loss=0.02445, over 4811.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02879, over 973399.11 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 18:25:56,269 INFO [train.py:715] (4/8) Epoch 19, batch 24200, loss[loss=0.1487, simple_loss=0.2118, pruned_loss=0.04284, over 4749.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.0289, over 973627.61 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 18:26:36,612 INFO [train.py:715] (4/8) Epoch 19, batch 24250, loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02873, over 4863.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2055, pruned_loss=0.02857, over 974166.96 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 18:27:17,345 INFO [train.py:715] (4/8) Epoch 19, batch 24300, loss[loss=0.1321, simple_loss=0.1916, pruned_loss=0.03627, over 4858.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2059, pruned_loss=0.0288, over 973418.84 frames.], batch size: 30, lr: 1.16e-04
2022-05-09 18:27:56,395 INFO [train.py:715] (4/8) Epoch 19, batch 24350, loss[loss=0.128, simple_loss=0.2049, pruned_loss=0.02553, over 4850.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02839, over 973184.97 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:28:36,034 INFO [train.py:715] (4/8) Epoch 19, batch 24400, loss[loss=0.1431, simple_loss=0.2108, pruned_loss=0.0377, over 4822.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02887, over 972528.94 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:29:16,437 INFO [train.py:715] (4/8) Epoch 19, batch 24450, loss[loss=0.1198, simple_loss=0.1992, pruned_loss=0.02015, over 4980.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02847, over 972172.30 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 18:29:55,852 INFO [train.py:715] (4/8) Epoch 19, batch 24500, loss[loss=0.1812, simple_loss=0.2481, pruned_loss=0.05713, over 4826.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2053, pruned_loss=0.02865, over 972142.79 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:30:34,369 INFO [train.py:715] (4/8) Epoch 19, batch 24550, loss[loss=0.1114, simple_loss=0.1837, pruned_loss=0.01954, over 4970.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02878, over 972043.59 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:31:13,266 INFO [train.py:715] (4/8) Epoch 19, batch 24600, loss[loss=0.1397, simple_loss=0.2098, pruned_loss=0.03479, over 4913.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2064, pruned_loss=0.02906, over 972898.29 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 18:31:52,759 INFO [train.py:715] (4/8) Epoch 19, batch 24650, loss[loss=0.1229, simple_loss=0.2015, pruned_loss=0.02212, over 4804.00 frames.], tot_loss[loss=0.1311, simple_loss=0.205, pruned_loss=0.02861, over 972289.08 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 18:32:31,486 INFO [train.py:715] (4/8) Epoch 19, batch 24700, loss[loss=0.1412, simple_loss=0.2089, pruned_loss=0.03672, over 4971.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2049, pruned_loss=0.02808, over 972275.10 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 18:33:10,029 INFO [train.py:715] (4/8) Epoch 19, batch 24750, loss[loss=0.1456, simple_loss=0.2215, pruned_loss=0.0349, over 4883.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2049, pruned_loss=0.02832, over 971686.57 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 18:33:50,381 INFO [train.py:715] (4/8) Epoch 19, batch 24800, loss[loss=0.131, simple_loss=0.2073, pruned_loss=0.02735, over 4741.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2057, pruned_loss=0.02876, over 971796.35 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 18:34:30,019 INFO [train.py:715] (4/8) Epoch 19, batch 24850, loss[loss=0.1531, simple_loss=0.2296, pruned_loss=0.03834, over 4699.00 frames.], tot_loss[loss=0.1307, simple_loss=0.205, pruned_loss=0.02822, over 972006.74 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:35:09,084 INFO [train.py:715] (4/8) Epoch 19, batch 24900, loss[loss=0.1401, simple_loss=0.2183, pruned_loss=0.03098, over 4898.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2042, pruned_loss=0.02751, over 971459.73 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 18:35:48,551 INFO [train.py:715] (4/8) Epoch 19, batch 24950, loss[loss=0.1148, simple_loss=0.1882, pruned_loss=0.02075, over 4779.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2051, pruned_loss=0.0282, over 971195.19 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:36:28,356 INFO [train.py:715] (4/8) Epoch 19, batch 25000, loss[loss=0.1103, simple_loss=0.185, pruned_loss=0.01783, over 4725.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2049, pruned_loss=0.02796, over 971741.64 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 18:37:07,182 INFO [train.py:715] (4/8) Epoch 19, batch 25050, loss[loss=0.1254, simple_loss=0.192, pruned_loss=0.0294, over 4930.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2042, pruned_loss=0.02783, over 972401.74 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 18:37:46,485 INFO [train.py:715] (4/8) Epoch 19, batch 25100, loss[loss=0.1373, simple_loss=0.2207, pruned_loss=0.02701, over 4690.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2042, pruned_loss=0.02747, over 973016.40 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:38:26,082 INFO [train.py:715] (4/8) Epoch 19, batch 25150, loss[loss=0.1278, simple_loss=0.2079, pruned_loss=0.02391, over 4983.00 frames.], tot_loss[loss=0.1292, simple_loss=0.2038, pruned_loss=0.02731, over 973354.75 frames.], batch size: 28, lr: 1.16e-04
2022-05-09 18:39:05,719 INFO [train.py:715] (4/8) Epoch 19, batch 25200, loss[loss=0.1142, simple_loss=0.1896, pruned_loss=0.01942, over 4817.00 frames.], tot_loss[loss=0.1293, simple_loss=0.2041, pruned_loss=0.02729, over 972783.41 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 18:39:44,329 INFO [train.py:715] (4/8) Epoch 19, batch 25250, loss[loss=0.1278, simple_loss=0.2081, pruned_loss=0.02369, over 4850.00 frames.], tot_loss[loss=0.1295, simple_loss=0.2043, pruned_loss=0.02738, over 973281.09 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 18:40:23,574 INFO [train.py:715] (4/8) Epoch 19, batch 25300, loss[loss=0.158, simple_loss=0.2285, pruned_loss=0.04378, over 4911.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2044, pruned_loss=0.02742, over 972864.85 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 18:41:03,219 INFO [train.py:715] (4/8) Epoch 19, batch 25350, loss[loss=0.1388, simple_loss=0.2182, pruned_loss=0.02967, over 4812.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2041, pruned_loss=0.02758, over 972995.63 frames.], batch size: 26, lr: 1.16e-04
2022-05-09 18:41:42,431 INFO [train.py:715] (4/8) Epoch 19, batch 25400, loss[loss=0.1317, simple_loss=0.2022, pruned_loss=0.03064, over 4875.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2052, pruned_loss=0.02834, over 973009.31 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 18:42:21,493 INFO [train.py:715] (4/8) Epoch 19, batch 25450, loss[loss=0.1195, simple_loss=0.1948, pruned_loss=0.02215, over 4646.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2052, pruned_loss=0.0283, over 972725.34 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 18:43:00,716 INFO [train.py:715] (4/8) Epoch 19, batch 25500, loss[loss=0.1259, simple_loss=0.1901, pruned_loss=0.03085, over 4830.00 frames.], tot_loss[loss=0.1305, simple_loss=0.205, pruned_loss=0.02804, over 972761.55 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 18:43:39,820 INFO [train.py:715] (4/8) Epoch 19, batch 25550, loss[loss=0.1175, simple_loss=0.1949, pruned_loss=0.02001, over 4925.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.02816, over 973164.27 frames.], batch size: 29, lr: 1.16e-04
2022-05-09 18:44:18,031 INFO [train.py:715] (4/8) Epoch 19, batch 25600, loss[loss=0.1357, simple_loss=0.2274, pruned_loss=0.02202, over 4736.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2049, pruned_loss=0.02774, over 973316.86 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 18:44:56,956 INFO [train.py:715] (4/8) Epoch 19, batch 25650, loss[loss=0.1426, simple_loss=0.2142, pruned_loss=0.03543, over 4804.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2049, pruned_loss=0.02788, over 972043.63 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:45:36,031 INFO [train.py:715] (4/8) Epoch 19, batch 25700, loss[loss=0.1117, simple_loss=0.1817, pruned_loss=0.02092, over 4778.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2041, pruned_loss=0.02753, over 972478.06 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 18:46:14,566 INFO [train.py:715] (4/8) Epoch 19, batch 25750, loss[loss=0.1041, simple_loss=0.1794, pruned_loss=0.01438, over 4692.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2047, pruned_loss=0.02743, over 972042.55 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:46:53,572 INFO [train.py:715] (4/8) Epoch 19, batch 25800, loss[loss=0.1107, simple_loss=0.1787, pruned_loss=0.02136, over 4792.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2051, pruned_loss=0.02761, over 971738.07 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 18:47:32,969 INFO [train.py:715] (4/8) Epoch 19, batch 25850, loss[loss=0.1247, simple_loss=0.2008, pruned_loss=0.02431, over 4971.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2057, pruned_loss=0.02836, over 971874.65 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 18:48:12,300 INFO [train.py:715] (4/8) Epoch 19, batch 25900, loss[loss=0.1324, simple_loss=0.2104, pruned_loss=0.0272, over 4956.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02826, over 973053.32 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 18:48:50,876 INFO [train.py:715] (4/8) Epoch 19, batch 25950, loss[loss=0.1755, simple_loss=0.2641, pruned_loss=0.04352, over 4780.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02882, over 973420.04 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 18:49:30,500 INFO [train.py:715] (4/8) Epoch 19, batch 26000, loss[loss=0.1241, simple_loss=0.2128, pruned_loss=0.01771, over 4921.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02909, over 973877.55 frames.], batch size: 29, lr: 1.16e-04
2022-05-09 18:50:10,474 INFO [train.py:715] (4/8) Epoch 19, batch 26050, loss[loss=0.1375, simple_loss=0.2095, pruned_loss=0.03274, over 4793.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2072, pruned_loss=0.02907, over 973071.45 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 18:50:49,159 INFO [train.py:715] (4/8) Epoch 19, batch 26100, loss[loss=0.1593, simple_loss=0.2272, pruned_loss=0.0457, over 4903.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2068, pruned_loss=0.02887, over 973536.44 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 18:51:28,554 INFO [train.py:715] (4/8) Epoch 19, batch 26150, loss[loss=0.1272, simple_loss=0.2039, pruned_loss=0.02521, over 4980.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2066, pruned_loss=0.02849, over 973156.83 frames.], batch size: 28, lr: 1.16e-04
2022-05-09 18:52:07,553 INFO [train.py:715] (4/8) Epoch 19, batch 26200, loss[loss=0.1295, simple_loss=0.1948, pruned_loss=0.03216, over 4801.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2055, pruned_loss=0.02803, over 972593.82 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 18:52:47,073 INFO [train.py:715] (4/8) Epoch 19, batch 26250, loss[loss=0.1314, simple_loss=0.2048, pruned_loss=0.02898, over 4827.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2056, pruned_loss=0.0281, over 973522.24 frames.], batch size: 30, lr: 1.16e-04
2022-05-09 18:53:25,454 INFO [train.py:715] (4/8) Epoch 19, batch 26300, loss[loss=0.1171, simple_loss=0.1975, pruned_loss=0.01832, over 4925.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.0282, over 972566.95 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 18:54:04,837 INFO [train.py:715] (4/8) Epoch 19, batch 26350, loss[loss=0.1217, simple_loss=0.2013, pruned_loss=0.021, over 4856.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02837, over 972799.00 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 18:54:44,060 INFO [train.py:715] (4/8) Epoch 19, batch 26400, loss[loss=0.1486, simple_loss=0.2281, pruned_loss=0.03456, over 4943.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02856, over 972479.80 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 18:55:23,157 INFO [train.py:715] (4/8) Epoch 19, batch 26450, loss[loss=0.1414, simple_loss=0.2149, pruned_loss=0.03396, over 4822.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2054, pruned_loss=0.02844, over 971574.59 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 18:56:02,218 INFO [train.py:715] (4/8) Epoch 19, batch 26500, loss[loss=0.1314, simple_loss=0.2086, pruned_loss=0.02708, over 4807.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2042, pruned_loss=0.02773, over 972152.65 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 18:56:40,882 INFO [train.py:715] (4/8) Epoch 19, batch 26550, loss[loss=0.1121, simple_loss=0.1851, pruned_loss=0.0196, over 4937.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2049, pruned_loss=0.02808, over 970828.49 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 18:57:21,642 INFO [train.py:715] (4/8) Epoch 19, batch 26600, loss[loss=0.1549, simple_loss=0.2242, pruned_loss=0.04283, over 4660.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2054, pruned_loss=0.02815, over 970617.38 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 18:58:02,784 INFO [train.py:715] (4/8) Epoch 19, batch 26650, loss[loss=0.1181, simple_loss=0.1893, pruned_loss=0.0235, over 4800.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2052, pruned_loss=0.02819, over 971328.02 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 18:58:41,697 INFO [train.py:715] (4/8) Epoch 19, batch 26700, loss[loss=0.1415, simple_loss=0.2228, pruned_loss=0.03009, over 4788.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02827, over 971425.53 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 18:59:21,014 INFO [train.py:715] (4/8) Epoch 19, batch 26750, loss[loss=0.146, simple_loss=0.2237, pruned_loss=0.03412, over 4909.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2049, pruned_loss=0.02829, over 971874.00 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 19:00:00,959 INFO [train.py:715] (4/8) Epoch 19, batch 26800, loss[loss=0.138, simple_loss=0.2133, pruned_loss=0.03135, over 4688.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2056, pruned_loss=0.02833, over 971906.89 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:00:41,173 INFO [train.py:715] (4/8) Epoch 19, batch 26850, loss[loss=0.1307, simple_loss=0.2047, pruned_loss=0.02836, over 4830.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2065, pruned_loss=0.02902, over 971750.82 frames.], batch size: 30, lr: 1.16e-04
2022-05-09 19:01:20,365 INFO [train.py:715] (4/8) Epoch 19, batch 26900, loss[loss=0.1307, simple_loss=0.1921, pruned_loss=0.03467, over 4801.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2061, pruned_loss=0.02882, over 971398.57 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 19:02:00,248 INFO [train.py:715] (4/8) Epoch 19, batch 26950, loss[loss=0.1321, simple_loss=0.2057, pruned_loss=0.02928, over 4889.00 frames.], tot_loss[loss=0.133, simple_loss=0.2074, pruned_loss=0.02926, over 971975.44 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 19:02:39,713 INFO [train.py:715] (4/8) Epoch 19, batch 27000, loss[loss=0.1417, simple_loss=0.2045, pruned_loss=0.03942, over 4796.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2076, pruned_loss=0.02938, over 971848.11 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 19:02:39,714 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 19:02:49,598 INFO [train.py:742] (4/8) Epoch 19, validation: loss=0.1047, simple_loss=0.1878, pruned_loss=0.0108, over 914524.00 frames.
2022-05-09 19:03:29,468 INFO [train.py:715] (4/8) Epoch 19, batch 27050, loss[loss=0.1186, simple_loss=0.2001, pruned_loss=0.01854, over 4947.00 frames.], tot_loss[loss=0.1344, simple_loss=0.2088, pruned_loss=0.02998, over 971553.23 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 19:04:09,793 INFO [train.py:715] (4/8) Epoch 19, batch 27100, loss[loss=0.1373, simple_loss=0.2029, pruned_loss=0.03584, over 4953.00 frames.], tot_loss[loss=0.1345, simple_loss=0.2091, pruned_loss=0.02995, over 971137.27 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 19:04:50,653 INFO [train.py:715] (4/8) Epoch 19, batch 27150, loss[loss=0.1175, simple_loss=0.1985, pruned_loss=0.0182, over 4807.00 frames.], tot_loss[loss=0.1335, simple_loss=0.2081, pruned_loss=0.02943, over 971064.90 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 19:05:30,586 INFO [train.py:715] (4/8) Epoch 19, batch 27200, loss[loss=0.1185, simple_loss=0.1969, pruned_loss=0.02001, over 4818.00 frames.], tot_loss[loss=0.1326, simple_loss=0.2076, pruned_loss=0.0288, over 971035.03 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 19:06:11,132 INFO [train.py:715] (4/8) Epoch 19, batch 27250, loss[loss=0.1435, simple_loss=0.2167, pruned_loss=0.03515, over 4978.00 frames.], tot_loss[loss=0.1332, simple_loss=0.2081, pruned_loss=0.02914, over 971051.89 frames.], batch size: 31, lr: 1.16e-04
2022-05-09 19:06:52,941 INFO [train.py:715] (4/8) Epoch 19, batch 27300, loss[loss=0.1069, simple_loss=0.1821, pruned_loss=0.01582, over 4981.00 frames.], tot_loss[loss=0.133, simple_loss=0.208, pruned_loss=0.02902, over 970835.09 frames.], batch size: 28, lr: 1.16e-04
2022-05-09 19:07:33,651 INFO [train.py:715] (4/8) Epoch 19, batch 27350, loss[loss=0.14, simple_loss=0.214, pruned_loss=0.03299, over 4813.00 frames.], tot_loss[loss=0.133, simple_loss=0.2079, pruned_loss=0.02909, over 970361.50 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 19:08:14,910 INFO [train.py:715] (4/8) Epoch 19, batch 27400, loss[loss=0.1246, simple_loss=0.1988, pruned_loss=0.02519, over 4859.00 frames.], tot_loss[loss=0.1318, simple_loss=0.207, pruned_loss=0.02832, over 971284.70 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 19:08:54,854 INFO [train.py:715] (4/8) Epoch 19, batch 27450, loss[loss=0.09709, simple_loss=0.1683, pruned_loss=0.01297, over 4985.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2067, pruned_loss=0.02852, over 971458.91 frames.], batch size: 26, lr: 1.16e-04
2022-05-09 19:09:36,482 INFO [train.py:715] (4/8) Epoch 19, batch 27500, loss[loss=0.1329, simple_loss=0.2022, pruned_loss=0.03181, over 4754.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2058, pruned_loss=0.02778, over 971817.80 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 19:10:17,097 INFO [train.py:715] (4/8) Epoch 19, batch 27550, loss[loss=0.1062, simple_loss=0.18, pruned_loss=0.01617, over 4882.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2057, pruned_loss=0.02749, over 972336.06 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 19:10:57,700 INFO [train.py:715] (4/8) Epoch 19, batch 27600, loss[loss=0.1138, simple_loss=0.182, pruned_loss=0.02282, over 4789.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2063, pruned_loss=0.02797, over 972255.85 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 19:11:38,779 INFO [train.py:715] (4/8) Epoch 19, batch 27650, loss[loss=0.1377, simple_loss=0.2212, pruned_loss=0.02714, over 4900.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2056, pruned_loss=0.0277, over 971955.81 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 19:12:19,403 INFO [train.py:715] (4/8) Epoch 19, batch 27700, loss[loss=0.1447, simple_loss=0.2157, pruned_loss=0.03686, over 4884.00 frames.], tot_loss[loss=0.1304, simple_loss=0.2053, pruned_loss=0.02775, over 972531.81 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 19:13:00,039 INFO [train.py:715] (4/8) Epoch 19, batch 27750, loss[loss=0.1105, simple_loss=0.1893, pruned_loss=0.01589, over 4822.00 frames.], tot_loss[loss=0.1303, simple_loss=0.2052, pruned_loss=0.02775, over 972810.18 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 19:13:40,111 INFO [train.py:715] (4/8) Epoch 19, batch 27800, loss[loss=0.1165, simple_loss=0.1847, pruned_loss=0.02415, over 4751.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2048, pruned_loss=0.02769, over 972913.43 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 19:14:21,131 INFO [train.py:715] (4/8) Epoch 19, batch 27850, loss[loss=0.1166, simple_loss=0.1883, pruned_loss=0.02244, over 4819.00 frames.], tot_loss[loss=0.1298, simple_loss=0.2043, pruned_loss=0.02762, over 972684.53 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 19:15:01,155 INFO [train.py:715] (4/8) Epoch 19, batch 27900, loss[loss=0.1311, simple_loss=0.2083, pruned_loss=0.02696, over 4802.00 frames.], tot_loss[loss=0.1296, simple_loss=0.2038, pruned_loss=0.02772, over 972675.90 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 19:15:41,294 INFO [train.py:715] (4/8) Epoch 19, batch 27950, loss[loss=0.1262, simple_loss=0.2023, pruned_loss=0.02501, over 4964.00 frames.], tot_loss[loss=0.13, simple_loss=0.204, pruned_loss=0.02798, over 972662.07 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 19:16:21,263 INFO [train.py:715] (4/8) Epoch 19, batch 28000, loss[loss=0.1291, simple_loss=0.2056, pruned_loss=0.02635, over 4823.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2046, pruned_loss=0.02818, over 973265.50 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 19:17:02,089 INFO [train.py:715] (4/8) Epoch 19, batch 28050, loss[loss=0.1265, simple_loss=0.2043, pruned_loss=0.02437, over 4977.00 frames.], tot_loss[loss=0.1297, simple_loss=0.2041, pruned_loss=0.02769, over 973195.31 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 19:17:42,526 INFO [train.py:715] (4/8) Epoch 19, batch 28100, loss[loss=0.1174, simple_loss=0.1963, pruned_loss=0.01927, over 4984.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2051, pruned_loss=0.02793, over 973322.36 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 19:18:22,473 INFO [train.py:715] (4/8) Epoch 19, batch 28150, loss[loss=0.1151, simple_loss=0.1925, pruned_loss=0.01888, over 4818.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2059, pruned_loss=0.02828, over 972438.50 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 19:19:02,900 INFO [train.py:715] (4/8) Epoch 19, batch 28200, loss[loss=0.11, simple_loss=0.1848, pruned_loss=0.01764, over 4780.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02807, over 972924.07 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 19:19:42,610 INFO [train.py:715] (4/8) Epoch 19, batch 28250, loss[loss=0.1401, simple_loss=0.2186, pruned_loss=0.03085, over 4987.00 frames.], tot_loss[loss=0.1311, simple_loss=0.206, pruned_loss=0.02808, over 972249.58 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:20:22,518 INFO [train.py:715] (4/8) Epoch 19, batch 28300, loss[loss=0.1614, simple_loss=0.2287, pruned_loss=0.04704, over 4917.00 frames.], tot_loss[loss=0.131, simple_loss=0.206, pruned_loss=0.02804, over 971701.65 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 19:21:02,187 INFO [train.py:715] (4/8) Epoch 19, batch 28350, loss[loss=0.1631, simple_loss=0.2434, pruned_loss=0.04141, over 4953.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2056, pruned_loss=0.02793, over 971525.87 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 19:21:42,213 INFO [train.py:715] (4/8) Epoch 19, batch 28400, loss[loss=0.1424, simple_loss=0.224, pruned_loss=0.03041, over 4736.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.0284, over 972295.05 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 19:22:22,334 INFO [train.py:715] (4/8) Epoch 19, batch 28450, loss[loss=0.119, simple_loss=0.1878, pruned_loss=0.02511, over 4684.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02837, over 972499.22 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:23:02,149 INFO [train.py:715] (4/8) Epoch 19, batch 28500, loss[loss=0.1292, simple_loss=0.2004, pruned_loss=0.02901, over 4921.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2063, pruned_loss=0.02817, over 973110.18 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 19:23:42,826 INFO [train.py:715] (4/8) Epoch 19, batch 28550, loss[loss=0.1138, simple_loss=0.191, pruned_loss=0.01832, over 4828.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2064, pruned_loss=0.02853, over 972481.36 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 19:24:22,313 INFO [train.py:715] (4/8) Epoch 19, batch 28600, loss[loss=0.1302, simple_loss=0.2072, pruned_loss=0.02655, over 4795.00 frames.], tot_loss[loss=0.132, simple_loss=0.2064, pruned_loss=0.02879, over 971987.64 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 19:25:02,344 INFO [train.py:715] (4/8) Epoch 19, batch 28650, loss[loss=0.1402, simple_loss=0.2105, pruned_loss=0.03496, over 4878.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02913, over 972247.84 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 19:25:43,121 INFO [train.py:715] (4/8) Epoch 19, batch 28700, loss[loss=0.1239, simple_loss=0.2011, pruned_loss=0.02334, over 4893.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2071, pruned_loss=0.02912, over 973364.63 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 19:26:22,654 INFO [train.py:715] (4/8) Epoch 19, batch 28750, loss[loss=0.1225, simple_loss=0.1997, pruned_loss=0.0227, over 4840.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2068, pruned_loss=0.02907, over 972817.14 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 19:27:02,568 INFO [train.py:715] (4/8) Epoch 19, batch 28800, loss[loss=0.1293, simple_loss=0.2039, pruned_loss=0.02738, over 4970.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2072, pruned_loss=0.02946, over 972967.81 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:27:41,945 INFO [train.py:715] (4/8) Epoch 19, batch 28850, loss[loss=0.1333, simple_loss=0.2185, pruned_loss=0.024, over 4897.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02904, over 972067.65 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 19:28:21,326 INFO [train.py:715] (4/8) Epoch 19, batch 28900, loss[loss=0.1391, simple_loss=0.217, pruned_loss=0.03064, over 4862.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.02898, over 971105.69 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 19:28:59,435 INFO [train.py:715] (4/8) Epoch 19, batch 28950, loss[loss=0.1101, simple_loss=0.1833, pruned_loss=0.0184, over 4751.00 frames.], tot_loss[loss=0.1331, simple_loss=0.2078, pruned_loss=0.02921, over 971776.66 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 19:29:38,324 INFO [train.py:715] (4/8) Epoch 19, batch 29000, loss[loss=0.1279, simple_loss=0.1912, pruned_loss=0.03237, over 4812.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2068, pruned_loss=0.02867, over 972220.83 frames.], batch size: 26, lr: 1.16e-04
2022-05-09 19:30:17,558 INFO [train.py:715] (4/8) Epoch 19, batch 29050, loss[loss=0.1667, simple_loss=0.2409, pruned_loss=0.04621, over 4809.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2071, pruned_loss=0.0292, over 972204.66 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:30:56,439 INFO [train.py:715] (4/8) Epoch 19, batch 29100, loss[loss=0.1215, simple_loss=0.1974, pruned_loss=0.02278, over 4977.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.0289, over 972881.41 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 19:31:35,382 INFO [train.py:715] (4/8) Epoch 19, batch 29150, loss[loss=0.1225, simple_loss=0.1885, pruned_loss=0.0282, over 4971.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2067, pruned_loss=0.0289, over 972715.05 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 19:32:14,169 INFO [train.py:715] (4/8) Epoch 19, batch 29200, loss[loss=0.125, simple_loss=0.2002, pruned_loss=0.02487, over 4891.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2065, pruned_loss=0.02863, over 973095.40 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 19:32:53,529 INFO [train.py:715] (4/8) Epoch 19, batch 29250, loss[loss=0.154, simple_loss=0.2216, pruned_loss=0.04315, over 4781.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.0284, over 972836.40 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 19:33:32,155 INFO [train.py:715] (4/8) Epoch 19, batch 29300, loss[loss=0.123, simple_loss=0.1959, pruned_loss=0.02506, over 4845.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2061, pruned_loss=0.02836, over 972283.09 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 19:34:11,675 INFO [train.py:715] (4/8) Epoch 19, batch 29350, loss[loss=0.1218, simple_loss=0.1943, pruned_loss=0.02469, over 4903.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2063, pruned_loss=0.02849, over 971871.64 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 19:34:50,602 INFO [train.py:715] (4/8) Epoch 19, batch 29400, loss[loss=0.1241, simple_loss=0.2028, pruned_loss=0.02269, over 4923.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02851, over 971152.33 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 19:35:29,744 INFO [train.py:715] (4/8) Epoch 19, batch 29450, loss[loss=0.1215, simple_loss=0.2006, pruned_loss=0.02123, over 4990.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2057, pruned_loss=0.02861, over 972092.77 frames.], batch size: 26, lr: 1.16e-04
2022-05-09 19:36:09,169 INFO [train.py:715] (4/8) Epoch 19, batch 29500, loss[loss=0.146, simple_loss=0.207, pruned_loss=0.04251, over 4972.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2058, pruned_loss=0.02854, over 972430.43 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:36:48,558 INFO [train.py:715] (4/8) Epoch 19, batch 29550, loss[loss=0.1283, simple_loss=0.2034, pruned_loss=0.02657, over 4816.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2068, pruned_loss=0.02876, over 972820.67 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 19:37:28,172 INFO [train.py:715] (4/8) Epoch 19, batch 29600, loss[loss=0.1283, simple_loss=0.2016, pruned_loss=0.02752, over 4983.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2062, pruned_loss=0.02866, over 973487.19 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 19:38:07,298 INFO [train.py:715] (4/8) Epoch 19, batch 29650, loss[loss=0.1469, simple_loss=0.215, pruned_loss=0.03944, over 4837.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2054, pruned_loss=0.02838, over 974061.41 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:38:47,453 INFO [train.py:715] (4/8) Epoch 19, batch 29700, loss[loss=0.1419, simple_loss=0.221, pruned_loss=0.03139, over 4916.00 frames.], tot_loss[loss=0.1302, simple_loss=0.2046, pruned_loss=0.02784, over 972858.34 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 19:39:26,744 INFO [train.py:715] (4/8) Epoch 19, batch 29750, loss[loss=0.1215, simple_loss=0.1963, pruned_loss=0.02338, over 4873.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2051, pruned_loss=0.02792, over 972733.45 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 19:40:06,089 INFO [train.py:715] (4/8) Epoch 19, batch 29800, loss[loss=0.1346, simple_loss=0.2018, pruned_loss=0.03367, over 4884.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2062, pruned_loss=0.02879, over 972615.50 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 19:40:45,392 INFO [train.py:715] (4/8) Epoch 19, batch 29850, loss[loss=0.1007, simple_loss=0.1819, pruned_loss=0.009735, over 4776.00 frames.], tot_loss[loss=0.131, simple_loss=0.2051, pruned_loss=0.02841, over 972173.56 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 19:41:24,810 INFO [train.py:715] (4/8) Epoch 19, batch 29900, loss[loss=0.1246, simple_loss=0.2065, pruned_loss=0.02133, over 4989.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.02833, over 973299.45 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 19:42:04,770 INFO [train.py:715] (4/8) Epoch 19, batch 29950, loss[loss=0.1457, simple_loss=0.216, pruned_loss=0.03766, over 4974.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2055, pruned_loss=0.02835, over 973338.31 frames.], batch size: 31, lr: 1.16e-04
2022-05-09 19:42:43,616 INFO [train.py:715] (4/8) Epoch 19, batch 30000, loss[loss=0.1434, simple_loss=0.2266, pruned_loss=0.03011, over 4970.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.0284, over 972942.84 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 19:42:43,617 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 19:42:53,507 INFO [train.py:742] (4/8) Epoch 19, validation: loss=0.1045, simple_loss=0.1877, pruned_loss=0.01067, over 914524.00 frames.
2022-05-09 19:43:32,625 INFO [train.py:715] (4/8) Epoch 19, batch 30050, loss[loss=0.1245, simple_loss=0.1967, pruned_loss=0.02611, over 4985.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2065, pruned_loss=0.02843, over 973941.74 frames.], batch size: 28, lr: 1.16e-04
2022-05-09 19:44:12,189 INFO [train.py:715] (4/8) Epoch 19, batch 30100, loss[loss=0.1347, simple_loss=0.2198, pruned_loss=0.02474, over 4963.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02857, over 974014.59 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 19:44:51,312 INFO [train.py:715] (4/8) Epoch 19, batch 30150, loss[loss=0.1486, simple_loss=0.2218, pruned_loss=0.03767, over 4772.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02846, over 973357.41 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 19:45:31,084 INFO [train.py:715] (4/8) Epoch 19, batch 30200, loss[loss=0.1165, simple_loss=0.1906, pruned_loss=0.02124, over 4988.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2066, pruned_loss=0.02864, over 973332.92 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 19:46:09,574 INFO [train.py:715] (4/8) Epoch 19, batch 30250, loss[loss=0.1359, simple_loss=0.2111, pruned_loss=0.03034, over 4821.00 frames.], tot_loss[loss=0.1328, simple_loss=0.2073, pruned_loss=0.02911, over 973841.97 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 19:46:48,894 INFO [train.py:715] (4/8) Epoch 19, batch 30300, loss[loss=0.123, simple_loss=0.1974, pruned_loss=0.02433, over 4905.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2059, pruned_loss=0.02867, over 973484.18 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 19:47:28,483 INFO [train.py:715] (4/8) Epoch 19, batch 30350, loss[loss=0.1594, simple_loss=0.2265, pruned_loss=0.04617, over 4842.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02843, over 972929.50 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:48:08,088 INFO [train.py:715] (4/8) Epoch 19, batch 30400, loss[loss=0.1207, simple_loss=0.192, pruned_loss=0.02465, over 4896.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.02849, over 972506.58 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 19:48:47,856 INFO [train.py:715] (4/8) Epoch 19, batch 30450, loss[loss=0.13, simple_loss=0.2037, pruned_loss=0.02817, over 4860.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2063, pruned_loss=0.02856, over 972818.26 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 19:49:26,660 INFO [train.py:715] (4/8) Epoch 19, batch 30500, loss[loss=0.1413, simple_loss=0.2121, pruned_loss=0.03523, over 4919.00 frames.], tot_loss[loss=0.132, simple_loss=0.2068, pruned_loss=0.02856, over 973297.48 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 19:50:06,590 INFO [train.py:715] (4/8) Epoch 19, batch 30550, loss[loss=0.1685, simple_loss=0.2339, pruned_loss=0.0516, over 4766.00 frames.], tot_loss[loss=0.1314, simple_loss=0.206, pruned_loss=0.02837, over 971752.14 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 19:50:45,744 INFO [train.py:715] (4/8) Epoch 19, batch 30600, loss[loss=0.1508, simple_loss=0.2251, pruned_loss=0.03823, over 4896.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2052, pruned_loss=0.02852, over 970594.46 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 19:51:25,828 INFO [train.py:715] (4/8) Epoch 19, batch 30650, loss[loss=0.1478, simple_loss=0.2232, pruned_loss=0.03616, over 4795.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2048, pruned_loss=0.02837, over 970350.75 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 19:52:05,611 INFO [train.py:715] (4/8) Epoch 19, batch 30700, loss[loss=0.1439, simple_loss=0.2131, pruned_loss=0.03732, over 4902.00 frames.], tot_loss[loss=0.1306, simple_loss=0.205, pruned_loss=0.02813, over 971195.60 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 19:52:45,186 INFO [train.py:715] (4/8) Epoch 19, batch 30750, loss[loss=0.1312, simple_loss=0.2052, pruned_loss=0.02864, over 4876.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2051, pruned_loss=0.02808, over 970891.99 frames.], batch size: 22, lr: 1.16e-04
2022-05-09 19:53:25,710 INFO [train.py:715] (4/8) Epoch 19, batch 30800, loss[loss=0.1405, simple_loss=0.2222, pruned_loss=0.02944, over 4697.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2057, pruned_loss=0.02825, over 971711.56 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:54:05,653 INFO [train.py:715] (4/8) Epoch 19, batch 30850, loss[loss=0.1167, simple_loss=0.1816, pruned_loss=0.02591, over 4991.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2065, pruned_loss=0.02832, over 970955.47 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 19:54:46,446 INFO [train.py:715] (4/8) Epoch 19, batch 30900, loss[loss=0.1522, simple_loss=0.2179, pruned_loss=0.04327, over 4693.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2063, pruned_loss=0.02837, over 970749.20 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 19:55:26,506 INFO [train.py:715] (4/8) Epoch 19, batch 30950, loss[loss=0.1435, simple_loss=0.2063, pruned_loss=0.04036, over 4943.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2061, pruned_loss=0.02856, over 971532.22 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 19:56:07,123 INFO [train.py:715] (4/8) Epoch 19, batch 31000, loss[loss=0.1423, simple_loss=0.2199, pruned_loss=0.03235, over 4931.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2062, pruned_loss=0.02837, over 971558.87 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 19:56:47,795 INFO [train.py:715] (4/8) Epoch 19, batch 31050, loss[loss=0.1364, simple_loss=0.2101, pruned_loss=0.03131, over 4792.00 frames.], tot_loss[loss=0.131, simple_loss=0.2055, pruned_loss=0.0282, over 971443.12 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 19:57:28,109 INFO [train.py:715] (4/8) Epoch 19, batch 31100, loss[loss=0.1453, simple_loss=0.2272, pruned_loss=0.03174, over 4877.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2057, pruned_loss=0.02804, over 972494.03 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 19:58:08,815 INFO [train.py:715] (4/8) Epoch 19, batch 31150, loss[loss=0.1301, simple_loss=0.2089, pruned_loss=0.02564, over 4985.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02881, over 972980.47 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 19:58:49,190 INFO [train.py:715] (4/8) Epoch 19, batch 31200, loss[loss=0.1487, simple_loss=0.2223, pruned_loss=0.03751, over 4839.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02881, over 972951.72 frames.], batch size: 30, lr: 1.16e-04
2022-05-09 19:59:30,191 INFO [train.py:715] (4/8) Epoch 19, batch 31250, loss[loss=0.118, simple_loss=0.1995, pruned_loss=0.01822, over 4907.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2065, pruned_loss=0.02888, over 972797.48 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 20:00:09,916 INFO [train.py:715] (4/8) Epoch 19, batch 31300, loss[loss=0.1133, simple_loss=0.1847, pruned_loss=0.02096, over 4860.00 frames.], tot_loss[loss=0.1309, simple_loss=0.2054, pruned_loss=0.02822, over 973389.91 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 20:00:50,564 INFO [train.py:715] (4/8) Epoch 19, batch 31350, loss[loss=0.109, simple_loss=0.1796, pruned_loss=0.01922, over 4944.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02844, over 973331.95 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 20:01:31,158 INFO [train.py:715] (4/8) Epoch 19, batch 31400, loss[loss=0.1374, simple_loss=0.2161, pruned_loss=0.02937, over 4964.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02866, over 973099.89 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 20:02:11,475 INFO [train.py:715] (4/8) Epoch 19, batch 31450, loss[loss=0.1252, simple_loss=0.1952, pruned_loss=0.02759, over 4864.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02878, over 972805.40 frames.], batch size: 32, lr: 1.16e-04
2022-05-09 20:02:52,729 INFO [train.py:715] (4/8) Epoch 19, batch 31500, loss[loss=0.1347, simple_loss=0.2167, pruned_loss=0.02635, over 4695.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2072, pruned_loss=0.0287, over 972898.49 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 20:03:32,844 INFO [train.py:715] (4/8) Epoch 19, batch 31550, loss[loss=0.1299, simple_loss=0.1979, pruned_loss=0.031, over 4936.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2062, pruned_loss=0.0285, over 973334.33 frames.], batch size: 35, lr: 1.16e-04
2022-05-09 20:04:13,423 INFO [train.py:715] (4/8) Epoch 19, batch 31600, loss[loss=0.1315, simple_loss=0.1876, pruned_loss=0.0377, over 4784.00 frames.], tot_loss[loss=0.1319, simple_loss=0.206, pruned_loss=0.02886, over 973217.24 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 20:04:53,552 INFO [train.py:715] (4/8) Epoch 19, batch 31650, loss[loss=0.1264, simple_loss=0.2005, pruned_loss=0.02617, over 4799.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2067, pruned_loss=0.02889, over 973590.24 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 20:05:33,934 INFO [train.py:715] (4/8) Epoch 19, batch 31700, loss[loss=0.1307, simple_loss=0.2094, pruned_loss=0.02598, over 4896.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2056, pruned_loss=0.02845, over 973049.00 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 20:06:14,401 INFO [train.py:715] (4/8) Epoch 19, batch 31750, loss[loss=0.1303, simple_loss=0.2161, pruned_loss=0.02223, over 4833.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2054, pruned_loss=0.02838, over 973137.83 frames.], batch size: 26, lr: 1.16e-04
2022-05-09 20:06:54,579 INFO [train.py:715] (4/8) Epoch 19, batch 31800, loss[loss=0.1309, simple_loss=0.2075, pruned_loss=0.02715, over 4891.00 frames.], tot_loss[loss=0.131, simple_loss=0.2054, pruned_loss=0.02835, over 972205.35 frames.], batch size: 17, lr: 1.16e-04
2022-05-09 20:07:35,669 INFO [train.py:715] (4/8) Epoch 19, batch 31850, loss[loss=0.1149, simple_loss=0.1895, pruned_loss=0.02013, over 4925.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.0287, over 972696.19 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 20:08:15,987 INFO [train.py:715] (4/8) Epoch 19, batch 31900, loss[loss=0.1347, simple_loss=0.203, pruned_loss=0.03317, over 4813.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2066, pruned_loss=0.02887, over 972794.61 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 20:08:56,585 INFO [train.py:715] (4/8) Epoch 19, batch 31950, loss[loss=0.1343, simple_loss=0.1981, pruned_loss=0.03523, over 4859.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2071, pruned_loss=0.0289, over 972980.61 frames.], batch size: 12, lr: 1.16e-04
2022-05-09 20:09:36,637 INFO [train.py:715] (4/8) Epoch 19, batch 32000, loss[loss=0.1146, simple_loss=0.1841, pruned_loss=0.02259, over 4773.00 frames.], tot_loss[loss=0.1325, simple_loss=0.2073, pruned_loss=0.02889, over 972013.41 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 20:10:16,972 INFO [train.py:715] (4/8) Epoch 19, batch 32050, loss[loss=0.1353, simple_loss=0.2199, pruned_loss=0.02538, over 4925.00 frames.], tot_loss[loss=0.132, simple_loss=0.2067, pruned_loss=0.02864, over 971503.75 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 20:10:57,298 INFO [train.py:715] (4/8) Epoch 19, batch 32100, loss[loss=0.1326, simple_loss=0.207, pruned_loss=0.02909, over 4907.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2064, pruned_loss=0.02847, over 971761.78 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 20:11:37,099 INFO [train.py:715] (4/8) Epoch 19, batch 32150, loss[loss=0.1302, simple_loss=0.2052, pruned_loss=0.02764, over 4942.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2072, pruned_loss=0.02878, over 972496.57 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 20:12:18,357 INFO [train.py:715] (4/8) Epoch 19, batch 32200, loss[loss=0.1384, simple_loss=0.2163, pruned_loss=0.03029, over 4875.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02871, over 972146.68 frames.], batch size: 20, lr: 1.16e-04
2022-05-09 20:12:58,097 INFO [train.py:715] (4/8) Epoch 19, batch 32250, loss[loss=0.1417, simple_loss=0.2178, pruned_loss=0.03282, over 4939.00 frames.], tot_loss[loss=0.1325, simple_loss=0.207, pruned_loss=0.02897, over 971629.82 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 20:13:38,500 INFO [train.py:715] (4/8) Epoch 19, batch 32300, loss[loss=0.1104, simple_loss=0.1845, pruned_loss=0.01812, over 4928.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2071, pruned_loss=0.02873, over 971549.73 frames.], batch size: 18, lr: 1.16e-04
2022-05-09 20:14:19,659 INFO [train.py:715] (4/8) Epoch 19, batch 32350, loss[loss=0.1164, simple_loss=0.1919, pruned_loss=0.02039, over 4826.00 frames.], tot_loss[loss=0.132, simple_loss=0.2065, pruned_loss=0.02873, over 971953.41 frames.], batch size: 26, lr: 1.16e-04
2022-05-09 20:15:00,201 INFO [train.py:715] (4/8) Epoch 19, batch 32400, loss[loss=0.1745, simple_loss=0.2375, pruned_loss=0.05573, over 4821.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2064, pruned_loss=0.02868, over 970903.55 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 20:15:40,795 INFO [train.py:715] (4/8) Epoch 19, batch 32450, loss[loss=0.1133, simple_loss=0.1871, pruned_loss=0.01973, over 4811.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02846, over 971606.28 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 20:16:20,798 INFO [train.py:715] (4/8) Epoch 19, batch 32500, loss[loss=0.11, simple_loss=0.1827, pruned_loss=0.01869, over 4801.00 frames.], tot_loss[loss=0.1307, simple_loss=0.2055, pruned_loss=0.02798, over 971943.05 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 20:17:01,569 INFO [train.py:715] (4/8) Epoch 19, batch 32550, loss[loss=0.09972, simple_loss=0.1713, pruned_loss=0.01409, over 4784.00 frames.], tot_loss[loss=0.1307, simple_loss=0.205, pruned_loss=0.02813, over 972338.62 frames.], batch size: 14, lr: 1.16e-04
2022-05-09 20:17:41,585 INFO [train.py:715] (4/8) Epoch 19, batch 32600, loss[loss=0.1382, simple_loss=0.2138, pruned_loss=0.03129, over 4892.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2047, pruned_loss=0.02828, over 971565.80 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 20:18:21,661 INFO [train.py:715] (4/8) Epoch 19, batch 32650, loss[loss=0.1273, simple_loss=0.2027, pruned_loss=0.02599, over 4796.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2051, pruned_loss=0.02852, over 972208.21 frames.], batch size: 24, lr: 1.16e-04
2022-05-09 20:19:02,292 INFO [train.py:715] (4/8) Epoch 19, batch 32700, loss[loss=0.1382, simple_loss=0.2026, pruned_loss=0.03694, over 4980.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2058, pruned_loss=0.02877, over 972815.10 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 20:19:42,122 INFO [train.py:715] (4/8) Epoch 19, batch 32750, loss[loss=0.136, simple_loss=0.2067, pruned_loss=0.03269, over 4881.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2058, pruned_loss=0.02883, over 972885.50 frames.], batch size: 39, lr: 1.16e-04
2022-05-09 20:20:21,841 INFO [train.py:715] (4/8) Epoch 19, batch 32800, loss[loss=0.1081, simple_loss=0.1881, pruned_loss=0.01409, over 4804.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2055, pruned_loss=0.02846, over 972070.95 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 20:21:00,654 INFO [train.py:715] (4/8) Epoch 19, batch 32850, loss[loss=0.1351, simple_loss=0.2057, pruned_loss=0.03223, over 4733.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02852, over 972207.51 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 20:21:39,681 INFO [train.py:715] (4/8) Epoch 19, batch 32900, loss[loss=0.1351, simple_loss=0.2171, pruned_loss=0.02661, over 4836.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2061, pruned_loss=0.02848, over 972526.65 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 20:22:18,347 INFO [train.py:715] (4/8) Epoch 19, batch 32950, loss[loss=0.1143, simple_loss=0.186, pruned_loss=0.0213, over 4949.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2059, pruned_loss=0.02845, over 973541.19 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 20:22:57,660 INFO [train.py:715] (4/8) Epoch 19, batch 33000, loss[loss=0.1345, simple_loss=0.2018, pruned_loss=0.03359, over 4637.00 frames.], tot_loss[loss=0.1319, simple_loss=0.2063, pruned_loss=0.02875, over 972894.68 frames.], batch size: 13, lr: 1.16e-04
2022-05-09 20:22:57,661 INFO [train.py:733] (4/8) Computing validation loss
2022-05-09 20:23:07,490 INFO [train.py:742] (4/8) Epoch 19, validation: loss=0.1048, simple_loss=0.1878, pruned_loss=0.01088, over 914524.00 frames.
2022-05-09 20:23:46,771 INFO [train.py:715] (4/8) Epoch 19, batch 33050, loss[loss=0.1442, simple_loss=0.2216, pruned_loss=0.03336, over 4882.00 frames.], tot_loss[loss=0.1317, simple_loss=0.206, pruned_loss=0.02871, over 973466.91 frames.], batch size: 16, lr: 1.16e-04
2022-05-09 20:24:26,212 INFO [train.py:715] (4/8) Epoch 19, batch 33100, loss[loss=0.1291, simple_loss=0.1983, pruned_loss=0.02997, over 4836.00 frames.], tot_loss[loss=0.1312, simple_loss=0.2051, pruned_loss=0.0286, over 972486.81 frames.], batch size: 30, lr: 1.16e-04
2022-05-09 20:25:05,032 INFO [train.py:715] (4/8) Epoch 19, batch 33150, loss[loss=0.1556, simple_loss=0.2268, pruned_loss=0.0422, over 4709.00 frames.], tot_loss[loss=0.1308, simple_loss=0.205, pruned_loss=0.0283, over 972474.01 frames.], batch size: 15, lr: 1.16e-04
2022-05-09 20:25:44,208 INFO [train.py:715] (4/8) Epoch 19, batch 33200, loss[loss=0.11, simple_loss=0.188, pruned_loss=0.01596, over 4823.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2055, pruned_loss=0.0288, over 972604.22 frames.], batch size: 25, lr: 1.16e-04
2022-05-09 20:26:23,767 INFO [train.py:715] (4/8) Epoch 19, batch 33250, loss[loss=0.1306, simple_loss=0.2163, pruned_loss=0.0225, over 4963.00 frames.], tot_loss[loss=0.1308, simple_loss=0.2051, pruned_loss=0.02822, over 972557.14 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 20:27:03,192 INFO [train.py:715] (4/8) Epoch 19, batch 33300, loss[loss=0.1329, simple_loss=0.2049, pruned_loss=0.03039, over 4926.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2052, pruned_loss=0.02804, over 972734.39 frames.], batch size: 23, lr: 1.16e-04
2022-05-09 20:27:42,908 INFO [train.py:715] (4/8) Epoch 19, batch 33350, loss[loss=0.1237, simple_loss=0.1923, pruned_loss=0.02753, over 4986.00 frames.], tot_loss[loss=0.1306, simple_loss=0.2053, pruned_loss=0.02801, over 972806.66 frames.], batch size: 31, lr: 1.16e-04
2022-05-09 20:28:22,077 INFO [train.py:715] (4/8) Epoch 19, batch 33400, loss[loss=0.1202, simple_loss=0.201, pruned_loss=0.01967, over 4814.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2056, pruned_loss=0.02772, over 972607.65 frames.], batch size: 27, lr: 1.16e-04
2022-05-09 20:29:01,057 INFO [train.py:715] (4/8) Epoch 19, batch 33450, loss[loss=0.125, simple_loss=0.201, pruned_loss=0.02449, over 4915.00 frames.], tot_loss[loss=0.1305, simple_loss=0.2055, pruned_loss=0.02777, over 971847.34 frames.], batch size: 19, lr: 1.16e-04
2022-05-09 20:29:40,022 INFO [train.py:715] (4/8) Epoch 19, batch 33500, loss[loss=0.1508, simple_loss=0.2247, pruned_loss=0.03845, over 4946.00 frames.], tot_loss[loss=0.1301, simple_loss=0.2046, pruned_loss=0.02774, over 972060.25 frames.], batch size: 21, lr: 1.16e-04
2022-05-09 20:30:18,903 INFO [train.py:715] (4/8) Epoch 19, batch 33550, loss[loss=0.1369, simple_loss=0.217, pruned_loss=0.02839, over 4861.00 frames.], tot_loss[loss=0.1299, simple_loss=0.2041, pruned_loss=0.02789, over 972863.73 frames.], batch size: 16, lr: 1.15e-04
2022-05-09 20:30:58,237 INFO [train.py:715] (4/8) Epoch 19, batch 33600, loss[loss=0.1303, simple_loss=0.2009, pruned_loss=0.02987, over 4826.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2056, pruned_loss=0.02855, over 973202.62 frames.], batch size: 13, lr: 1.15e-04
2022-05-09 20:31:37,215 INFO [train.py:715] (4/8) Epoch 19, batch 33650, loss[loss=0.1397, simple_loss=0.2137, pruned_loss=0.03284, over 4868.00 frames.], tot_loss[loss=0.1316, simple_loss=0.2055, pruned_loss=0.02885, over 972970.24 frames.], batch size: 22, lr: 1.15e-04
2022-05-09 20:32:16,618 INFO [train.py:715] (4/8) Epoch 19, batch 33700, loss[loss=0.1441, simple_loss=0.2063, pruned_loss=0.04093, over 4944.00 frames.], tot_loss[loss=0.1317, simple_loss=0.2059, pruned_loss=0.02881, over 973273.62 frames.], batch size: 21, lr: 1.15e-04
2022-05-09 20:32:55,331 INFO [train.py:715] (4/8) Epoch 19, batch 33750, loss[loss=0.1227, simple_loss=0.1934, pruned_loss=0.02594, over 4788.00 frames.], tot_loss[loss=0.1315, simple_loss=0.2053, pruned_loss=0.02888, over 973174.93 frames.], batch size: 17, lr: 1.15e-04
2022-05-09 20:33:34,125 INFO [train.py:715] (4/8) Epoch 19, batch 33800, loss[loss=0.1439, simple_loss=0.2228, pruned_loss=0.03253, over 4980.00 frames.], tot_loss[loss=0.132, simple_loss=0.2062, pruned_loss=0.02896, over 973142.98 frames.], batch size: 15, lr: 1.15e-04
2022-05-09 20:34:12,736 INFO [train.py:715] (4/8) Epoch 19, batch 33850, loss[loss=0.1286, simple_loss=0.2035, pruned_loss=0.02688, over 4980.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02872, over 972566.39 frames.], batch size: 35, lr: 1.15e-04
2022-05-09 20:34:51,545 INFO [train.py:715] (4/8) Epoch 19, batch 33900, loss[loss=0.1116, simple_loss=0.1815, pruned_loss=0.02087, over 4923.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2061, pruned_loss=0.02872, over 972892.65 frames.], batch size: 29, lr: 1.15e-04
2022-05-09 20:35:31,246 INFO [train.py:715] (4/8) Epoch 19, batch 33950, loss[loss=0.1354, simple_loss=0.2171, pruned_loss=0.02688, over 4765.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02882, over 972611.19 frames.], batch size: 18, lr: 1.15e-04
2022-05-09 20:36:10,893 INFO [train.py:715] (4/8) Epoch 19, batch 34000, loss[loss=0.1188, simple_loss=0.1943, pruned_loss=0.02163, over 4912.00 frames.], tot_loss[loss=0.132, simple_loss=0.2066, pruned_loss=0.02874, over 973469.62 frames.], batch size: 18, lr: 1.15e-04
2022-05-09 20:36:50,180 INFO [train.py:715] (4/8) Epoch 19, batch 34050, loss[loss=0.1252, simple_loss=0.2034, pruned_loss=0.02354, over 4941.00 frames.], tot_loss[loss=0.1323, simple_loss=0.207, pruned_loss=0.02879, over 972972.28 frames.], batch size: 23, lr: 1.15e-04
2022-05-09 20:37:28,969 INFO [train.py:715] (4/8) Epoch 19, batch 34100, loss[loss=0.1264, simple_loss=0.202, pruned_loss=0.02535, over 4761.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2063, pruned_loss=0.02864, over 972231.64 frames.], batch size: 19, lr: 1.15e-04
2022-05-09 20:38:08,482 INFO [train.py:715] (4/8) Epoch 19, batch 34150, loss[loss=0.1133, simple_loss=0.1916, pruned_loss=0.01747, over 4868.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2065, pruned_loss=0.02852, over 971083.46 frames.], batch size: 16, lr: 1.15e-04
2022-05-09 20:38:48,075 INFO [train.py:715] (4/8) Epoch 19, batch 34200, loss[loss=0.1337, simple_loss=0.2006, pruned_loss=0.0334, over 4826.00 frames.], tot_loss[loss=0.1315, simple_loss=0.206, pruned_loss=0.02847, over 970964.15 frames.], batch size: 13, lr: 1.15e-04
2022-05-09 20:39:27,598 INFO [train.py:715] (4/8) Epoch 19, batch 34250, loss[loss=0.1225, simple_loss=0.1887, pruned_loss=0.02816, over 4843.00 frames.], tot_loss[loss=0.1311, simple_loss=0.2058, pruned_loss=0.02816, over 972183.85 frames.], batch size: 15, lr: 1.15e-04
2022-05-09 20:40:06,931 INFO [train.py:715] (4/8) Epoch 19, batch 34300, loss[loss=0.1193, simple_loss=0.1993, pruned_loss=0.01968, over 4946.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2063, pruned_loss=0.02825, over 971553.80 frames.], batch size: 23, lr: 1.15e-04
2022-05-09 20:40:46,125 INFO [train.py:715] (4/8) Epoch 19, batch 34350, loss[loss=0.1398, simple_loss=0.2202, pruned_loss=0.02973, over 4701.00 frames.], tot_loss[loss=0.1314, simple_loss=0.2064, pruned_loss=0.02826, over 971550.67 frames.], batch size: 15, lr: 1.15e-04
2022-05-09 20:41:25,881 INFO [train.py:715] (4/8) Epoch 19, batch 34400, loss[loss=0.1235, simple_loss=0.1953, pruned_loss=0.02589, over 4886.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2067, pruned_loss=0.02795, over 971220.84 frames.], batch size: 22, lr: 1.15e-04
2022-05-09 20:42:05,039 INFO [train.py:715] (4/8) Epoch 19, batch 34450, loss[loss=0.1187, simple_loss=0.1982, pruned_loss=0.01962, over 4950.00 frames.], tot_loss[loss=0.1313, simple_loss=0.2067, pruned_loss=0.02796, over 971236.38 frames.], batch size: 23, lr: 1.15e-04
2022-05-09 20:42:44,560 INFO [train.py:715] (4/8) Epoch 19, batch 34500, loss[loss=0.1449, simple_loss=0.2192, pruned_loss=0.0353, over 4777.00 frames.], tot_loss[loss=0.131, simple_loss=0.206, pruned_loss=0.02797, over 971677.04 frames.], batch size: 18, lr: 1.15e-04
2022-05-09 20:43:24,265 INFO [train.py:715] (4/8) Epoch 19, batch 34550, loss[loss=0.1289, simple_loss=0.2084, pruned_loss=0.02467, over 4960.00 frames.], tot_loss[loss=0.1322, simple_loss=0.2071, pruned_loss=0.02864, over 971928.80 frames.], batch size: 24, lr: 1.15e-04
2022-05-09 20:44:03,126 INFO [train.py:715] (4/8) Epoch 19, batch 34600, loss[loss=0.1526, simple_loss=0.217, pruned_loss=0.04405, over 4980.00 frames.], tot_loss[loss=0.1321, simple_loss=0.2072, pruned_loss=0.02852, over 972223.56 frames.], batch size: 15, lr: 1.15e-04
2022-05-09 20:44:45,165 INFO [train.py:715] (4/8) Epoch 19, batch 34650, loss[loss=0.1177, simple_loss=0.1909, pruned_loss=0.02219, over 4811.00 frames.], tot_loss[loss=0.1327, simple_loss=0.2077, pruned_loss=0.02885, over 973068.45 frames.], batch size: 12, lr: 1.15e-04
2022-05-09 20:45:24,629 INFO [train.py:715] (4/8) Epoch 19, batch 34700, loss[loss=0.118, simple_loss=0.1871, pruned_loss=0.0245, over 4911.00 frames.], tot_loss[loss=0.1318, simple_loss=0.2069, pruned_loss=0.02838, over 972235.42 frames.], batch size: 17, lr: 1.15e-04
2022-05-09 20:46:02,677 INFO [train.py:715] (4/8) Epoch 19, batch 34750, loss[loss=0.175, simple_loss=0.2483, pruned_loss=0.05087, over 4655.00 frames.], tot_loss[loss=0.1324, simple_loss=0.2072, pruned_loss=0.02881, over 972886.85 frames.], batch size: 13, lr: 1.15e-04
2022-05-09 20:46:39,959 INFO [train.py:715] (4/8) Epoch 19, batch 34800, loss[loss=0.1171, simple_loss=0.1899, pruned_loss=0.02218, over 4805.00 frames.], tot_loss[loss=0.1323, simple_loss=0.2069, pruned_loss=0.02881, over 972951.15 frames.], batch size: 12, lr: 1.15e-04
2022-05-09 20:46:48,444 INFO [train.py:915] (4/8) Done!